1 files changed, 262 insertions, 111 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5bab6c3f7a2f..ea6e4cff9faf 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -79,7 +79,7 @@
 
 #define pr_fmt(fmt) "UDP: " fmt
 
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
 #include <asm/ioctls.h>
 #include <linux/bootmem.h>
 #include <linux/highmem.h>
@@ -134,14 +134,21 @@ EXPORT_SYMBOL(udp_memory_allocated);
 #define MAX_UDP_PORTS 65536
 #define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN)
 
+/* IPCB reference means this can not be used from early demux */
+static bool udp_lib_exact_dif_match(struct net *net, struct sk_buff *skb)
+{
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	if (!net->ipv4.sysctl_udp_l3mdev_accept &&
+	    skb && ipv4_l3mdev_skb(IPCB(skb)->flags))
+		return true;
+#endif
+	return false;
+}
+
 static int udp_lib_lport_inuse(struct net *net, __u16 num,
 			       const struct udp_hslot *hslot,
 			       unsigned long *bitmap,
-			       struct sock *sk,
-			       int (*saddr_comp)(const struct sock *sk1,
-						 const struct sock *sk2,
-						 bool match_wildcard),
-			       unsigned int log)
+			       struct sock *sk, unsigned int log)
 {
 	struct sock *sk2;
 	kuid_t uid = sock_i_uid(sk);
@@ -153,13 +160,18 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
 		    (!sk2->sk_reuse || !sk->sk_reuse) &&
 		    (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
 		     sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
-		    (!sk2->sk_reuseport || !sk->sk_reuseport ||
-		     rcu_access_pointer(sk->sk_reuseport_cb) ||
-		     !uid_eq(uid, sock_i_uid(sk2))) &&
-		    saddr_comp(sk, sk2, true)) {
-			if (!bitmap)
-				return 1;
-			__set_bit(udp_sk(sk2)->udp_port_hash >> log, bitmap);
+		    inet_rcv_saddr_equal(sk, sk2, true)) {
+			if (sk2->sk_reuseport && sk->sk_reuseport &&
+			    !rcu_access_pointer(sk->sk_reuseport_cb) &&
+			    uid_eq(uid, sock_i_uid(sk2))) {
+				if (!bitmap)
+					return 0;
+			} else {
+				if (!bitmap)
+					return 1;
+				__set_bit(udp_sk(sk2)->udp_port_hash >> log,
+					  bitmap);
+			}
 		}
 	}
 	return 0;
@@ -171,10 +183,7 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num,
  */
 static int udp_lib_lport_inuse2(struct net *net, __u16 num,
 				struct udp_hslot *hslot2,
-				struct sock *sk,
-				int (*saddr_comp)(const struct sock *sk1,
-						  const struct sock *sk2,
-						  bool match_wildcard))
+				struct sock *sk)
 {
 	struct sock *sk2;
 	kuid_t uid = sock_i_uid(sk);
@@ -188,11 +197,14 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num,
 		    (!sk2->sk_reuse || !sk->sk_reuse) &&
 		    (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if ||
 		     sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
-		    (!sk2->sk_reuseport || !sk->sk_reuseport ||
-		     rcu_access_pointer(sk->sk_reuseport_cb) ||
-		     !uid_eq(uid, sock_i_uid(sk2))) &&
-		    saddr_comp(sk, sk2, true)) {
-			res = 1;
+		    inet_rcv_saddr_equal(sk, sk2, true)) {
+			if (sk2->sk_reuseport && sk->sk_reuseport &&
+			    !rcu_access_pointer(sk->sk_reuseport_cb) &&
+			    uid_eq(uid, sock_i_uid(sk2))) {
+				res = 0;
+			} else {
+				res = 1;
+			}
 			break;
 		}
 	}
@@ -200,10 +212,7 @@ static int udp_lib_lport_inuse2(struct net *net, __u16 num,
 	return res;
 }
 
-static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot,
-				  int (*saddr_same)(const struct sock *sk1,
-						    const struct sock *sk2,
-						    bool match_wildcard))
+static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot)
 {
 	struct net *net = sock_net(sk);
 	kuid_t uid = sock_i_uid(sk);
@@ -217,7 +226,7 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot,
 		    (udp_sk(sk2)->udp_port_hash == udp_sk(sk)->udp_port_hash) &&
 		    (sk2->sk_bound_dev_if == sk->sk_bound_dev_if) &&
 		    sk2->sk_reuseport && uid_eq(uid, sock_i_uid(sk2)) &&
-		    (*saddr_same)(sk, sk2, false)) {
+		    inet_rcv_saddr_equal(sk, sk2, false)) {
 			return reuseport_add_sock(sk, sk2);
 		}
 	}
@@ -233,14 +242,10 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot,
  *
  *  @sk:          socket struct in question
  *  @snum:        port number to look up
- *  @saddr_comp:  AF-dependent comparison of bound local IP addresses
  *  @hash2_nulladdr: AF-dependent hash value in secondary hash chains,
  *                   with NULL address
  */
 int udp_lib_get_port(struct sock *sk, unsigned short snum,
-		     int (*saddr_comp)(const struct sock *sk1,
-				       const struct sock *sk2,
-				       bool match_wildcard),
 		     unsigned int hash2_nulladdr)
 {
 	struct udp_hslot *hslot, *hslot2;
@@ -269,7 +274,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 			bitmap_zero(bitmap, PORTS_PER_CHAIN);
 			spin_lock_bh(&hslot->lock);
 			udp_lib_lport_inuse(net, snum, hslot, bitmap, sk,
-					    saddr_comp, udptable->log);
+					    udptable->log);
 
 			snum = first;
 			/*
@@ -285,6 +290,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 				snum += rand;
 			} while (snum != first);
 			spin_unlock_bh(&hslot->lock);
+			cond_resched();
 		} while (++first != last);
 		goto fail;
 	} else {
@@ -301,12 +307,11 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 			if (hslot->count < hslot2->count)
 				goto scan_primary_hash;
 
-			exist = udp_lib_lport_inuse2(net, snum, hslot2,
-						     sk, saddr_comp);
+			exist = udp_lib_lport_inuse2(net, snum, hslot2, sk);
 			if (!exist && (hash2_nulladdr != slot2)) {
 				hslot2 = udp_hashslot2(udptable, hash2_nulladdr);
 				exist = udp_lib_lport_inuse2(net, snum, hslot2,
-							     sk, saddr_comp);
+							     sk);
 			}
 			if (exist)
 				goto fail_unlock;
@@ -314,8 +319,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
 				goto found;
 		}
 scan_primary_hash:
-		if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk,
-					saddr_comp, 0))
+		if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, 0))
 			goto fail_unlock;
 	}
 found:
@@ -324,7 +328,7 @@ found:
 	udp_sk(sk)->udp_portaddr_hash ^= snum;
 	if (sk_unhashed(sk)) {
 		if (sk->sk_reuseport &&
-		    udp_reuseport_add_sock(sk, hslot, saddr_comp)) {
+		    udp_reuseport_add_sock(sk, hslot)) {
 			inet_sk(sk)->inet_num = 0;
 			udp_sk(sk)->udp_port_hash = 0;
 			udp_sk(sk)->udp_portaddr_hash ^= snum;
@@ -356,24 +360,6 @@ fail:
 }
 EXPORT_SYMBOL(udp_lib_get_port);
 
-/* match_wildcard == true:  0.0.0.0 equals to any IPv4 addresses
- * match_wildcard == false: addresses must be exactly the same, i.e.
- *                          0.0.0.0 only equals to 0.0.0.0
- */
-int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2,
-			 bool match_wildcard)
-{
-	struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2);
-
-	if (!ipv6_only_sock(sk2)) {
-		if (inet1->inet_rcv_saddr == inet2->inet_rcv_saddr)
-			return 1;
-		if (!inet1->inet_rcv_saddr || !inet2->inet_rcv_saddr)
-			return match_wildcard;
-	}
-	return 0;
-}
-
 static u32 udp4_portaddr_hash(const struct net *net, __be32 saddr,
 			      unsigned int port)
 {
@@ -389,12 +375,13 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum)
 
 	/* precompute partial secondary hash */
 	udp_sk(sk)->udp_portaddr_hash = hash2_partial;
-	return udp_lib_get_port(sk, snum, ipv4_rcv_saddr_equal, hash2_nulladdr);
+	return udp_lib_get_port(sk, snum, hash2_nulladdr);
 }
 
 static int compute_score(struct sock *sk, struct net *net,
 			 __be32 saddr, __be16 sport,
-			 __be32 daddr, unsigned short hnum, int dif)
+			 __be32 daddr, unsigned short hnum, int dif,
+			 bool exact_dif)
 {
 	int score;
 	struct inet_sock *inet;
@@ -425,7 +412,7 @@ static int compute_score(struct sock *sk, struct net *net,
 		score += 4;
 	}
 
-	if (sk->sk_bound_dev_if) {
+	if (sk->sk_bound_dev_if || exact_dif) {
 		if (sk->sk_bound_dev_if != dif)
 			return -1;
 		score += 4;
@@ -450,7 +437,7 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr,
 /* called with rcu_read_lock() */
 static struct sock *udp4_lib_lookup2(struct net *net,
 		__be32 saddr, __be16 sport,
-		__be32 daddr, unsigned int hnum, int dif,
+		__be32 daddr, unsigned int hnum, int dif, bool exact_dif,
 		struct udp_hslot *hslot2,
 		struct sk_buff *skb)
 {
@@ -462,7 +449,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 	badness = 0;
 	udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
 		score = compute_score(sk, net, saddr, sport,
-				      daddr, hnum, dif);
+				      daddr, hnum, dif, exact_dif);
 		if (score > badness) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
@@ -497,6 +484,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 	unsigned short hnum = ntohs(dport);
 	unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask);
 	struct udp_hslot *hslot2, *hslot = &udptable->hash[slot];
+	bool exact_dif = udp_lib_exact_dif_match(net, skb);
 	int score, badness, matches = 0, reuseport = 0;
 	u32 hash = 0;
 
@@ -509,7 +497,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 
 		result = udp4_lib_lookup2(net, saddr, sport,
 					  daddr, hnum, dif,
-					  hslot2, skb);
+					  exact_dif, hslot2, skb);
 		if (!result) {
 			unsigned int old_slot2 = slot2;
 			hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum);
@@ -524,7 +512,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 
 			result = udp4_lib_lookup2(net, saddr, sport,
 						  daddr, hnum, dif,
-						  hslot2, skb);
+						  exact_dif, hslot2, skb);
 		}
 		return result;
 	}
@@ -533,7 +521,7 @@ begin:
 	badness = 0;
 	sk_for_each_rcu(sk, &hslot->head) {
 		score = compute_score(sk, net, saddr, sport,
-				      daddr, hnum, dif);
+				      daddr, hnum, dif, exact_dif);
 		if (score > badness) {
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
@@ -580,7 +568,8 @@ EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb);
  * Does increment socket refcount.
  */
 #if IS_ENABLED(CONFIG_NETFILTER_XT_MATCH_SOCKET) || \
-    IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY)
+    IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TPROXY) || \
+    IS_ENABLED(CONFIG_NF_SOCKET_IPV4)
 struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
 			     __be32 daddr, __be16 dport, int dif)
 {
@@ -1019,7 +1008,8 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 		flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos,
 				   RT_SCOPE_UNIVERSE, sk->sk_protocol,
 				   flow_flags,
-				   faddr, saddr, dport, inet->inet_sport);
+				   faddr, saddr, dport, inet->inet_sport,
+				   sk->sk_uid);
 
 		security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
 		rt = ip_route_output_flow(net, fl4, sk);
@@ -1111,7 +1101,8 @@ out:
 	return err;
 
 do_confirm:
-	dst_confirm(&rt->dst);
+	if (msg->msg_flags & MSG_PROBE)
+		dst_confirm_neigh(&rt->dst, &fl4->daddr);
 	if (!(msg->msg_flags&MSG_PROBE) || len)
 		goto back_from_confirm;
 	err = 0;
@@ -1172,6 +1163,181 @@ out:
 	return ret;
 }
 
+/* fully reclaim rmem/fwd memory allocated for skb */
+static void udp_rmem_release(struct sock *sk, int size, int partial)
+{
+	struct udp_sock *up = udp_sk(sk);
+	int amt;
+
+	if (likely(partial)) {
+		up->forward_deficit += size;
+		size = up->forward_deficit;
+		if (size < (sk->sk_rcvbuf >> 2) &&
+		    !skb_queue_empty(&sk->sk_receive_queue))
+			return;
+	} else {
+		size += up->forward_deficit;
+	}
+	up->forward_deficit = 0;
+
+	sk->sk_forward_alloc += size;
+	amt = (sk->sk_forward_alloc - partial) & ~(SK_MEM_QUANTUM - 1);
+	sk->sk_forward_alloc -= amt;
+
+	if (amt)
+		__sk_mem_reduce_allocated(sk, amt >> SK_MEM_QUANTUM_SHIFT);
+
+	atomic_sub(size, &sk->sk_rmem_alloc);
+}
+
+/* Note: called with sk_receive_queue.lock held.
+ * Instead of using skb->truesize here, find a copy of it in skb->dev_scratch
+ * This avoids a cache line miss while receive_queue lock is held.
+ * Look at __udp_enqueue_schedule_skb() to find where this copy is done.
+ */
+void udp_skb_destructor(struct sock *sk, struct sk_buff *skb)
+{
+	udp_rmem_release(sk, skb->dev_scratch, 1);
+}
+EXPORT_SYMBOL(udp_skb_destructor);
+
+/* Idea of busylocks is to let producers grab an extra spinlock
+ * to relieve pressure on the receive_queue spinlock shared by consumer.
+ * Under flood, this means that only one producer can be in line
+ * trying to acquire the receive_queue spinlock.
+ * These busylock can be allocated on a per cpu manner, instead of a
+ * per socket one (that would consume a cache line per socket)
+ */
+static int udp_busylocks_log __read_mostly;
+static spinlock_t *udp_busylocks __read_mostly;
+
+static spinlock_t *busylock_acquire(void *ptr)
+{
+	spinlock_t *busy;
+
+	busy = udp_busylocks + hash_ptr(ptr, udp_busylocks_log);
+	spin_lock(busy);
+	return busy;
+}
+
+static void busylock_release(spinlock_t *busy)
+{
+	if (busy)
+		spin_unlock(busy);
+}
+
+int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb)
+{
+	struct sk_buff_head *list = &sk->sk_receive_queue;
+	int rmem, delta, amt, err = -ENOMEM;
+	spinlock_t *busy = NULL;
+	int size;
+
+	/* try to avoid the costly atomic add/sub pair when the receive
+	 * queue is full; always allow at least a packet
+	 */
+	rmem = atomic_read(&sk->sk_rmem_alloc);
+	if (rmem > sk->sk_rcvbuf)
+		goto drop;
+
+	/* Under mem pressure, it might be helpful to help udp_recvmsg()
+	 * having linear skbs :
+	 * - Reduce memory overhead and thus increase receive queue capacity
+	 * - Less cache line misses at copyout() time
+	 * - Less work at consume_skb() (less alien page frag freeing)
+	 */
+	if (rmem > (sk->sk_rcvbuf >> 1)) {
+		skb_condense(skb);
+
+		busy = busylock_acquire(sk);
+	}
+	size = skb->truesize;
+	/* Copy skb->truesize into skb->dev_scratch to avoid a cache line miss
+	 * in udp_skb_destructor()
+	 */
+	skb->dev_scratch = size;
+
+	/* we drop only if the receive buf is full and the receive
+	 * queue contains some other skb
+	 */
+	rmem = atomic_add_return(size, &sk->sk_rmem_alloc);
+	if (rmem > (size + sk->sk_rcvbuf))
+		goto uncharge_drop;
+
+	spin_lock(&list->lock);
+	if (size >= sk->sk_forward_alloc) {
+		amt = sk_mem_pages(size);
+		delta = amt << SK_MEM_QUANTUM_SHIFT;
+		if (!__sk_mem_raise_allocated(sk, delta, amt, SK_MEM_RECV)) {
+			err = -ENOBUFS;
+			spin_unlock(&list->lock);
+			goto uncharge_drop;
+		}
+
+		sk->sk_forward_alloc += delta;
+	}
+
+	sk->sk_forward_alloc -= size;
+
+	/* no need to setup a destructor, we will explicitly release the
+	 * forward allocated memory on dequeue
+	 */
+	sock_skb_set_dropcount(sk, skb);
+
+	__skb_queue_tail(list, skb);
+	spin_unlock(&list->lock);
+
+	if (!sock_flag(sk, SOCK_DEAD))
+		sk->sk_data_ready(sk);
+
+	busylock_release(busy);
+	return 0;
+
+uncharge_drop:
+	atomic_sub(skb->truesize, &sk->sk_rmem_alloc);
+
+drop:
+	atomic_inc(&sk->sk_drops);
+	busylock_release(busy);
+	return err;
+}
+EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb);
+
+void udp_destruct_sock(struct sock *sk)
+{
+	/* reclaim completely the forward allocated memory */
+	unsigned int total = 0;
+	struct sk_buff *skb;
+
+	while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) {
+		total += skb->truesize;
+		kfree_skb(skb);
+	}
+	udp_rmem_release(sk, total, 0);
+
+	inet_sock_destruct(sk);
+}
+EXPORT_SYMBOL_GPL(udp_destruct_sock);
+
+int udp_init_sock(struct sock *sk)
+{
+	sk->sk_destruct = udp_destruct_sock;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(udp_init_sock);
+
+void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len)
+{
+	if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) {
+		bool slow = lock_sock_fast(sk);
+
+		sk_peek_offset_bwd(sk, len);
+		unlock_sock_fast(sk, slow);
+	}
+	consume_skb(skb);
+}
+EXPORT_SYMBOL_GPL(skb_consume_udp);
+
 /**
  *	first_packet_length	- return length of first packet in receive queue
  *	@sk: socket
@@ -1181,12 +1347,11 @@ out:
  */
 static int first_packet_length(struct sock *sk)
 {
-	struct sk_buff_head list_kill, *rcvq = &sk->sk_receive_queue;
+	struct sk_buff_head *rcvq = &sk->sk_receive_queue;
 	struct sk_buff *skb;
+	int total = 0;
 	int res;
 
-	__skb_queue_head_init(&list_kill);
-
 	spin_lock_bh(&rcvq->lock);
 	while ((skb = skb_peek(rcvq)) != NULL &&
 		udp_lib_checksum_complete(skb)) {
@@ -1196,18 +1361,13 @@ static int first_packet_length(struct sock *sk)
 				IS_UDPLITE(sk));
 		atomic_inc(&sk->sk_drops);
 		__skb_unlink(skb, rcvq);
-		__skb_queue_tail(&list_kill, skb);
+		total += skb->truesize;
+		kfree_skb(skb);
 	}
 	res = skb ? skb->len : -1;
+	if (total)
+		udp_rmem_release(sk, total, 1);
 	spin_unlock_bh(&rcvq->lock);
-
-	if (!skb_queue_empty(&list_kill)) {
-		bool slow = lock_sock_fast(sk);
-
-		__skb_queue_purge(&list_kill);
-		sk_mem_reclaim_partial(sk);
-		unlock_sock_fast(sk, slow);
-	}
 	return res;
 }
 
@@ -1256,15 +1416,13 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
 	int err;
 	int is_udplite = IS_UDPLITE(sk);
 	bool checksum_valid = false;
-	bool slow;
 
 	if (flags & MSG_ERRQUEUE)
 		return ip_recv_error(sk, msg, len, addr_len);
 
 try_again:
 	peeking = off = sk_peek_offset(sk, flags);
-	skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
-				  &peeked, &off, &err);
+	skb = __skb_recv_udp(sk, flags, noblock, &peeked, &off, &err);
 	if (!skb)
 		return err;
 
@@ -1281,7 +1439,8 @@ try_again:
 	 * coverage checksum (UDP-Lite), do it before the copy.
 	 */
 
-	if (copied < ulen || UDP_SKB_CB(skb)->partial_cov || peeking) {
+	if (copied < ulen || peeking ||
+	    (is_udplite && UDP_SKB_CB(skb)->partial_cov)) {
 		checksum_valid = !udp_lib_checksum_complete(skb);
 		if (!checksum_valid)
 			goto csum_copy_err;
@@ -1297,13 +1456,12 @@ try_again:
 	}
 
 	if (unlikely(err)) {
-		trace_kfree_skb(skb, udp_recvmsg);
 		if (!peeked) {
 			atomic_inc(&sk->sk_drops);
 			UDP_INC_STATS(sock_net(sk),
 				      UDP_MIB_INERRORS, is_udplite);
 		}
-		skb_free_datagram_locked(sk, skb);
+		kfree_skb(skb);
 		return err;
 	}
 
@@ -1322,22 +1480,21 @@ try_again:
 		*addr_len = sizeof(*sin);
 	}
 	if (inet->cmsg_flags)
-		ip_cmsg_recv_offset(msg, skb, sizeof(struct udphdr), off);
+		ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off);
 
 	err = copied;
 	if (flags & MSG_TRUNC)
 		err = ulen;
 
-	__skb_free_datagram_locked(sk, skb, peeking ? -err : err);
+	skb_consume_udp(sk, skb, peeking ? -err : err);
 	return err;
 
 csum_copy_err:
-	slow = lock_sock_fast(sk);
-	if (!skb_kill_datagram(sk, skb, flags)) {
+	if (!__sk_queue_drop_skb(sk, skb, flags, udp_skb_destructor)) {
 		UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
 		UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite);
 	}
-	unlock_sock_fast(sk, slow);
+	kfree_skb(skb);
 
 	/* starting over for a new packet, but check if we need to yield */
 	cond_resched();
@@ -1463,9 +1620,11 @@ int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		sock_rps_save_rxhash(sk, skb);
 		sk_mark_napi_id(sk, skb);
 		sk_incoming_cpu_update(sk);
+	} else {
+		sk_mark_napi_id_once(sk, skb);
 	}
 
-	rc = __sock_queue_rcv_skb(sk, skb);
+	rc = __udp_enqueue_schedule_skb(sk, skb);
 	if (rc < 0) {
 		int is_udplite = IS_UDPLITE(sk);
 
@@ -1480,7 +1639,6 @@ int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 	}
 
 	return 0;
-
 }
 
 static struct static_key udp_encap_needed __read_mostly;
@@ -1502,7 +1660,6 @@ EXPORT_SYMBOL(udp_encap_enable);
 int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	struct udp_sock *up = udp_sk(sk);
-	int rc;
 	int is_udplite = IS_UDPLITE(sk);
 
 	/*
@@ -1589,25 +1746,9 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
 		goto drop;
 
 	udp_csum_pull_header(skb);
-	if (sk_rcvqueues_full(sk, sk->sk_rcvbuf)) {
-		__UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS,
-				is_udplite);
-		goto drop;
-	}
-
-	rc = 0;
 
 	ipv4_pktinfo_prepare(sk, skb);
-	bh_lock_sock(sk);
-	if (!sock_owned_by_user(sk))
-		rc = __udp_queue_rcv_skb(sk, skb);
-	else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) {
-		bh_unlock_sock(sk);
-		goto drop;
-	}
-	bh_unlock_sock(sk);
-
-	return rc;
+	return __udp_queue_rcv_skb(sk, skb);
 
 csum_error:
 	__UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite);
@@ -2217,13 +2358,13 @@ struct proto udp_prot = {
 	.connect	   = ip4_datagram_connect,
 	.disconnect	   = udp_disconnect,
 	.ioctl		   = udp_ioctl,
+	.init		   = udp_init_sock,
 	.destroy	   = udp_destroy_sock,
 	.setsockopt	   = udp_setsockopt,
 	.getsockopt	   = udp_getsockopt,
 	.sendmsg	   = udp_sendmsg,
 	.recvmsg	   = udp_recvmsg,
 	.sendpage	   = udp_sendpage,
-	.backlog_rcv	   = __udp_queue_rcv_skb,
 	.release_cb	   = ip4_datagram_release_cb,
 	.hash		   = udp_lib_hash,
 	.unhash		   = udp_lib_unhash,
@@ -2512,6 +2653,7 @@ EXPORT_SYMBOL(udp_flow_hashrnd);
 void __init udp_init(void)
 {
 	unsigned long limit;
+	unsigned int i;
 
 	udp_table_init(&udp_table, "UDP");
 	limit = nr_free_buffer_pages() / 8;
@@ -2522,4 +2664,13 @@ void __init udp_init(void)
 
 	sysctl_udp_rmem_min = SK_MEM_QUANTUM;
 	sysctl_udp_wmem_min = SK_MEM_QUANTUM;
+
+	/* 16 spinlocks per cpu */
+	udp_busylocks_log = ilog2(nr_cpu_ids) + 4;
+	udp_busylocks = kmalloc(sizeof(spinlock_t) << udp_busylocks_log,
+				GFP_KERNEL);
+	if (!udp_busylocks)
+		panic("UDP: failed to alloc udp_busylocks\n");
+	for (i = 0; i < (1U << udp_busylocks_log); i++)
+		spin_lock_init(udp_busylocks + i);
 }