X-Git-Url: https://git.karo-electronics.de/?a=blobdiff_plain;f=net%2Fipv4%2Fudp.c;h=db313d96488489de2e8c0d2100176e0ab893e171;hb=b7b5f487ab39bc10ed0694af35651a03d9cb97ff;hp=21901d2c53242c3ab937e94ac3bf019747bcbb73;hpb=6516c65573fde5e421c6c92c4b180bbe2245b23b;p=karo-tx-linux.git

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 21901d2c5324..db313d964884 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -114,14 +114,33 @@ DEFINE_RWLOCK(udp_hash_lock);
 
 static int udp_port_rover;
 
-static inline int __udp_lib_lport_inuse(__u16 num, struct hlist_head udptable[])
+/*
+ * Note about this hash function :
+ * Typical use is probably daddr = 0, only dport is going to vary hash
+ */
+static inline unsigned int hash_port_and_addr(__u16 port, __be32 addr)
+{
+	addr ^= addr >> 16;
+	addr ^= addr >> 8;
+	return port ^ addr;
+}
+
+static inline int __udp_lib_port_inuse(unsigned int hash, int port,
+	__be32 daddr, struct hlist_head udptable[])
 {
 	struct sock *sk;
 	struct hlist_node *node;
+	struct inet_sock *inet;
 
-	sk_for_each(sk, node, &udptable[num & (UDP_HTABLE_SIZE - 1)])
-		if (sk->sk_hash == num)
+	sk_for_each(sk, node, &udptable[hash & (UDP_HTABLE_SIZE - 1)]) {
+		if (sk->sk_hash != hash)
+			continue;
+		inet = inet_sk(sk);
+		if (inet->num != port)
+			continue;
+		if (inet->rcv_saddr == daddr)
 			return 1;
+	}
 	return 0;
 }
 
@@ -142,6 +161,7 @@ int __udp_lib_get_port(struct sock *sk, unsigned short snum,
 	struct hlist_node *node;
 	struct hlist_head *head;
 	struct sock *sk2;
+	unsigned int hash;
 	int    error = 1;
 
 	write_lock_bh(&udp_hash_lock);
@@ -156,7 +176,9 @@ int __udp_lib_get_port(struct sock *sk, unsigned short snum,
 		for (i = 0; i < UDP_HTABLE_SIZE; i++, result++) {
 			int size;
 
-			head = &udptable[result & (UDP_HTABLE_SIZE - 1)];
+			hash = hash_port_and_addr(result,
+					inet_sk(sk)->rcv_saddr);
+			head = &udptable[hash & (UDP_HTABLE_SIZE - 1)];
 			if (hlist_empty(head)) {
 				if (result > sysctl_local_port_range[1])
 					result = sysctl_local_port_range[0] +
@@ -181,7 +203,10 @@ int __udp_lib_get_port(struct sock *sk, unsigned short snum,
 				result = sysctl_local_port_range[0]
 					+ ((result - sysctl_local_port_range[0]) &
 					   (UDP_HTABLE_SIZE - 1));
-			if (! __udp_lib_lport_inuse(result, udptable))
+			hash = hash_port_and_addr(result,
+					inet_sk(sk)->rcv_saddr);
+			if (! __udp_lib_port_inuse(hash, result,
+				inet_sk(sk)->rcv_saddr, udptable))
 				break;
 		}
 		if (i >= (1 << 16) / UDP_HTABLE_SIZE)
@@ -189,11 +214,13 @@ int __udp_lib_get_port(struct sock *sk, unsigned short snum,
 gotit:
 		*port_rover = snum = result;
 	} else {
-		head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];
+		hash = hash_port_and_addr(snum, inet_sk(sk)->rcv_saddr);
+		head = &udptable[hash & (UDP_HTABLE_SIZE - 1)];
 
 		sk_for_each(sk2, node, head)
-			if (sk2->sk_hash == snum                             &&
+			if (sk2->sk_hash == hash                             &&
 			    sk2 != sk                                        &&
+			    inet_sk(sk2)->num == snum	                     &&
 			    (!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) &&
@@ -201,9 +228,9 @@ gotit:
 				goto fail;
 	}
 	inet_sk(sk)->num = snum;
-	sk->sk_hash = snum;
+	sk->sk_hash = hash;
 	if (sk_unhashed(sk)) {
-		head = &udptable[snum & (UDP_HTABLE_SIZE - 1)];
+		head = &udptable[hash & (UDP_HTABLE_SIZE - 1)];
 		sk_add_node(sk, head);
 		sock_prot_inc_use(sk->sk_prot);
 	}
@@ -213,13 +240,13 @@ fail:
 	return error;
 }
 
-__inline__ int udp_get_port(struct sock *sk, unsigned short snum,
+int udp_get_port(struct sock *sk, unsigned short snum,
 			int (*scmp)(const struct sock *, const struct sock *))
 {
 	return  __udp_lib_get_port(sk, snum, udp_hash, &udp_port_rover, scmp);
 }
 
-inline int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
+int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2)
 {
 	struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2);
 
@@ -242,63 +269,77 @@ static struct sock *__udp4_lib_lookup(__be32 saddr, __be16 sport,
 {
 	struct sock *sk, *result = NULL;
 	struct hlist_node *node;
-	unsigned short hnum = ntohs(dport);
-	int badness = -1;
+	unsigned int hash, hashwild;
+	int score, best = -1, hport = ntohs(dport);
+
+ 	hash = hash_port_and_addr(hport, daddr);
+ 	hashwild = hash_port_and_addr(hport, 0);
 
 	read_lock(&udp_hash_lock);
-	sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) {
+
+lookup:
+
+	sk_for_each(sk, node, &udptable[hash & (UDP_HTABLE_SIZE - 1)]) {
 		struct inet_sock *inet = inet_sk(sk);
 
-		if (sk->sk_hash == hnum && !ipv6_only_sock(sk)) {
-			int score = (sk->sk_family == PF_INET ? 1 : 0);
-			if (inet->rcv_saddr) {
-				if (inet->rcv_saddr != daddr)
-					continue;
-				score+=2;
-			}
-			if (inet->daddr) {
-				if (inet->daddr != saddr)
-					continue;
-				score+=2;
-			}
-			if (inet->dport) {
-				if (inet->dport != sport)
-					continue;
-				score+=2;
-			}
-			if (sk->sk_bound_dev_if) {
-				if (sk->sk_bound_dev_if != dif)
-					continue;
-				score+=2;
-			}
-			if (score == 9) {
-				result = sk;
-				break;
-			} else if (score > badness) {
-				result = sk;
-				badness = score;
-			}
+		if (sk->sk_hash != hash || ipv6_only_sock(sk) ||
+			inet->num != hport)
+			continue;
+
+		score = (sk->sk_family == PF_INET ? 1 : 0);
+		if (inet->rcv_saddr) {
+			if (inet->rcv_saddr != daddr)
+				continue;
+			score+=2;
+		}
+		if (inet->daddr) {
+			if (inet->daddr != saddr)
+				continue;
+			score+=2;
+		}
+		if (inet->dport) {
+			if (inet->dport != sport)
+				continue;
+			score+=2;
+		}
+		if (sk->sk_bound_dev_if) {
+			if (sk->sk_bound_dev_if != dif)
+				continue;
+			score+=2;
+		}
+		if (score == 9) {
+			result = sk;
+			goto found;
+		} else if (score > best) {
+			result = sk;
+			best = score;
 		}
 	}
+
+	if (hash != hashwild) {
+		hash = hashwild;
+		goto lookup;
+	}
+found:
 	if (result)
 		sock_hold(result);
 	read_unlock(&udp_hash_lock);
 	return result;
 }
 
-static inline struct sock *udp_v4_mcast_next(struct sock *sk,
-					     __be16 loc_port, __be32 loc_addr,
+static inline struct sock *udp_v4_mcast_next(struct sock *sk, unsigned int hnum,
+					     int hport, __be32 loc_addr,
 					     __be16 rmt_port, __be32 rmt_addr,
 					     int dif)
 {
 	struct hlist_node *node;
 	struct sock *s = sk;
-	unsigned short hnum = ntohs(loc_port);
 
 	sk_for_each_from(s, node) {
 		struct inet_sock *inet = inet_sk(s);
 
 		if (s->sk_hash != hnum					||
+		    inet->num != hport					||
 		    (inet->daddr && inet->daddr != rmt_addr)		||
 		    (inet->dport != rmt_port && inet->dport)		||
 		    (inet->rcv_saddr && inet->rcv_saddr != loc_addr)	||
@@ -330,8 +371,8 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct hlist_head udptable[])
 	struct inet_sock *inet;
 	struct iphdr *iph = (struct iphdr*)skb->data;
 	struct udphdr *uh = (struct udphdr*)(skb->data+(iph->ihl<<2));
-	int type = skb->h.icmph->type;
-	int code = skb->h.icmph->code;
+	const int type = icmp_hdr(skb)->type;
+	const int code = icmp_hdr(skb)->code;
 	struct sock *sk;
 	int harderr;
 	int err;
@@ -391,7 +432,7 @@ out:
 	sock_put(sk);
 }
 
-__inline__ void udp_err(struct sk_buff *skb, u32 info)
+void udp_err(struct sk_buff *skb, u32 info)
 {
 	return __udp4_lib_err(skb, info, udp_hash);
 }
@@ -420,13 +461,14 @@ static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
 				 __be32 src, __be32 dst, int len      )
 {
 	unsigned int offset;
-	struct udphdr *uh = skb->h.uh;
+	struct udphdr *uh = udp_hdr(skb);
 	__wsum csum = 0;
 
 	if (skb_queue_len(&sk->sk_write_queue) == 1) {
 		/*
 		 * Only one fragment on the socket.
 		 */
+		skb->csum_start = skb_transport_header(skb) - skb->head;
 		skb->csum_offset = offsetof(struct udphdr, check);
 		uh->check = ~csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, 0);
 	} else {
@@ -435,7 +477,7 @@ static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb,
 		 * fragments on the socket so that all csums of sk_buffs
 		 * should be together
 		 */
-		offset = skb->h.raw - skb->data;
+		offset = skb_transport_offset(skb);
 		skb->csum = skb_checksum(skb, offset, skb->len - offset, 0);
 
 		skb->ip_summed = CHECKSUM_NONE;
@@ -470,7 +512,7 @@ static int udp_push_pending_frames(struct sock *sk)
 	/*
 	 * Create a UDP header
 	 */
-	uh = skb->h.uh;
+	uh = udp_hdr(skb);
 	uh->source = fl->fl_ip_sport;
 	uh->dest = fl->fl_ip_dport;
 	uh->len = htons(up->len);
@@ -847,7 +889,7 @@ try_again:
 			goto csum_copy_err;
 	}
 
-	if (skb->ip_summed == CHECKSUM_UNNECESSARY)
+	if (skb_csum_unnecessary(skb))
 		err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr),
 					      msg->msg_iov, copied       );
 	else {
@@ -866,8 +908,8 @@ try_again:
 	if (sin)
 	{
 		sin->sin_family = AF_INET;
-		sin->sin_port = skb->h.uh->source;
-		sin->sin_addr.s_addr = skb->nh.iph->saddr;
+		sin->sin_port = udp_hdr(skb)->source;
+		sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
 		memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
 	}
 	if (inet->cmsg_flags)
@@ -949,7 +991,7 @@ static int udp_encap_rcv(struct sock * sk, struct sk_buff *skb)
 		return 1;
 
 	/* Now we can get the pointers */
-	uh = skb->h.uh;
+	uh = udp_hdr(skb);
 	udpdata = (__u8 *)uh + sizeof(struct udphdr);
 	udpdata32 = (__be32 *)udpdata;
 
@@ -990,7 +1032,7 @@ static int udp_encap_rcv(struct sock * sk, struct sk_buff *skb)
 		return 0;
 
 	/* Now we can update and verify the packet length... */
-	iph = skb->nh.iph;
+	iph = ip_hdr(skb);
 	iphlen = iph->ihl << 2;
 	iph->tot_len = htons(ntohs(iph->tot_len) - len);
 	if (skb->len < iphlen + len) {
@@ -1002,7 +1044,8 @@ static int udp_encap_rcv(struct sock * sk, struct sk_buff *skb)
 	 * transport header to point to ESP.  Keep UDP on the stack
 	 * for later.
 	 */
-	skb->h.raw = skb_pull(skb, len);
+	__skb_pull(skb, len);
+	skb_reset_transport_header(skb);
 
 	/* modify the protocol (it's ESP!) */
 	iph->protocol = IPPROTO_ESP;
@@ -1127,29 +1170,45 @@ static int __udp4_lib_mcast_deliver(struct sk_buff *skb,
 				    __be32 saddr, __be32 daddr,
 				    struct hlist_head udptable[])
 {
-	struct sock *sk;
+	struct sock *sk, *skw, *sknext;
 	int dif;
+	int hport = ntohs(uh->dest);
+	unsigned int hash = hash_port_and_addr(hport, daddr);
+	unsigned int hashwild = hash_port_and_addr(hport, 0);
 
-	read_lock(&udp_hash_lock);
-	sk = sk_head(&udptable[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]);
 	dif = skb->dev->ifindex;
-	sk = udp_v4_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif);
-	if (sk) {
-		struct sock *sknext = NULL;
 
+	read_lock(&udp_hash_lock);
+
+	sk = sk_head(&udptable[hash & (UDP_HTABLE_SIZE - 1)]);
+	skw = sk_head(&udptable[hashwild & (UDP_HTABLE_SIZE - 1)]);
+
+	sk = udp_v4_mcast_next(sk, hash, hport, daddr, uh->source, saddr, dif);
+	if (!sk) {
+		hash = hashwild;
+		sk = udp_v4_mcast_next(skw, hash, hport, daddr, uh->source,
+			saddr, dif);
+	}
+	if (sk) {
 		do {
 			struct sk_buff *skb1 = skb;
-
-			sknext = udp_v4_mcast_next(sk_next(sk), uh->dest, daddr,
-						   uh->source, saddr, dif);
+			sknext = udp_v4_mcast_next(sk_next(sk), hash, hport,
+						daddr, uh->source, saddr, dif);
+			if (!sknext && hash != hashwild) {
+				hash = hashwild;
+				sknext = udp_v4_mcast_next(skw, hash, hport,
+					daddr, uh->source, saddr, dif);
+			}
 			if (sknext)
 				skb1 = skb_clone(skb, GFP_ATOMIC);
 
 			if (skb1) {
 				int ret = udp_queue_rcv_skb(sk, skb1);
 				if (ret > 0)
-					/* we should probably re-process instead
-					 * of dropping packets here. */
+					/*
+					 * we should probably re-process
+					 * instead of dropping packets here.
+					 */
 					kfree_skb(skb1);
 			}
 			sk = sknext;
@@ -1168,6 +1227,7 @@ static int __udp4_lib_mcast_deliver(struct sk_buff *skb,
 static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 				 int proto)
 {
+	const struct iphdr *iph;
 	int err;
 
 	UDP_SKB_CB(skb)->partial_cov = 0;
@@ -1179,16 +1239,16 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 			return err;
 	}
 
+	iph = ip_hdr(skb);
 	if (uh->check == 0) {
 		skb->ip_summed = CHECKSUM_UNNECESSARY;
 	} else if (skb->ip_summed == CHECKSUM_COMPLETE) {
-	       if (!csum_tcpudp_magic(skb->nh.iph->saddr, skb->nh.iph->daddr,
-				      skb->len, proto, skb->csum))
+	       if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len,
+				      proto, skb->csum))
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
 	}
-	if (skb->ip_summed != CHECKSUM_UNNECESSARY)
-		skb->csum = csum_tcpudp_nofold(skb->nh.iph->saddr,
-					       skb->nh.iph->daddr,
+	if (!skb_csum_unnecessary(skb))
+		skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr,
 					       skb->len, proto, 0);
 	/* Probably, we should checksum udp header (it should be in cache
 	 * in any case) and data in tiny packets (< rx copybreak).
@@ -1205,11 +1265,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
 		   int proto)
 {
 	struct sock *sk;
-	struct udphdr *uh = skb->h.uh;
+	struct udphdr *uh = udp_hdr(skb);
 	unsigned short ulen;
 	struct rtable *rt = (struct rtable*)skb->dst;
-	__be32 saddr = skb->nh.iph->saddr;
-	__be32 daddr = skb->nh.iph->daddr;
+	__be32 saddr = ip_hdr(skb)->saddr;
+	__be32 daddr = ip_hdr(skb)->daddr;
 
 	/*
 	 *  Validate the packet.
@@ -1225,7 +1285,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
 		/* UDP validates ulen. */
 		if (ulen < sizeof(*uh) || pskb_trim_rcsum(skb, ulen))
 			goto short_packet;
-		uh = skb->h.uh;
+		uh = udp_hdr(skb);
 	}
 
 	if (udp4_csum_init(skb, uh, proto))
@@ -1235,7 +1295,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[],
 		return __udp4_lib_mcast_deliver(skb, uh, saddr, daddr, udptable);
 
 	sk = __udp4_lib_lookup(saddr, uh->source, daddr, uh->dest,
-			       skb->dev->ifindex, udptable        );
+			       skb->dev->ifindex, udptable);
 
 	if (sk != NULL) {
 		int ret = udp_queue_rcv_skb(sk, skb);
@@ -1296,7 +1356,7 @@ drop:
 	return 0;
 }
 
-__inline__ int udp_rcv(struct sk_buff *skb)
+int udp_rcv(struct sk_buff *skb)
 {
 	return __udp4_lib_rcv(skb, udp_hash, IPPROTO_UDP);
 }