1 files changed, 208 insertions, 46 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 5bab6c3..9ca279b 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -580,7 +580,8 @@ 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 +1020,8 @@ 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);
@@ -1172,6 +1174,181 @@ 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 +1358,11 @@ 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 +1372,13 @@ 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 +1427,13 @@ 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 +1450,8 @@ 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 +1467,12 @@ 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 +1491,21 @@ 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_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 +1631,11 @@ 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 +1650,6 @@ 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 +1671,6 @@ 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 +1757,9 @@ 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 +2369,13 @@ 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 +2664,7 @@ 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 +2675,13 @@ 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);
 }