summary refs log tree commit diff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig1
-rw-r--r--net/ipv4/devinet.c2
-rw-r--r--net/ipv4/fib_trie.c7
-rw-r--r--net/ipv4/inet_connection_sock.c14
-rw-r--r--net/ipv4/inet_diag.c21
-rw-r--r--net/ipv4/ip_fragment.c1
-rw-r--r--net/ipv4/ip_gre.c13
-rw-r--r--net/ipv4/ip_input.c5
-rw-r--r--net/ipv4/ip_sockglue.c2
-rw-r--r--net/ipv4/ip_tunnel.c20
-rw-r--r--net/ipv4/ipconfig.c4
-rw-r--r--net/ipv4/netfilter/nf_defrag_ipv4.c2
-rw-r--r--net/ipv4/ping.c4
-rw-r--r--net/ipv4/raw.c4
-rw-r--r--net/ipv4/route.c77
-rw-r--r--net/ipv4/tcp.c18
-rw-r--r--net/ipv4/tcp_input.c17
-rw-r--r--net/ipv4/tcp_ipv4.c44
-rw-r--r--net/ipv4/udp.c36
19 files changed, 206 insertions, 86 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index c22920525e5d..775824720b6b 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -353,6 +353,7 @@ config INET_ESP
 	select CRYPTO_CBC
 	select CRYPTO_SHA1
 	select CRYPTO_DES
+	select CRYPTO_ECHAINIV
 	---help---
 	  Support for IPsec ESP.
 
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index cebd9d31e65a..f6303b17546b 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1847,7 +1847,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb,
 	if (err < 0)
 		goto errout;
 
-	err = EINVAL;
+	err = -EINVAL;
 	if (!tb[NETCONFA_IFINDEX])
 		goto errout;
 
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 7aea0ccb6be6..d07fc076bea0 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -1394,9 +1394,10 @@ found:
 		struct fib_info *fi = fa->fa_info;
 		int nhsel, err;
 
-		if ((index >= (1ul << fa->fa_slen)) &&
-		    ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen != KEYLENGTH)))
-			continue;
+		if ((BITS_PER_LONG > KEYLENGTH) || (fa->fa_slen < KEYLENGTH)) {
+			if (index >= (1ul << fa->fa_slen))
+				continue;
+		}
 		if (fa->fa_tos && fa->fa_tos != flp->flowi4_tos)
 			continue;
 		if (fi->fib_dead)
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 46b9c887bede..64148914803a 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -789,14 +789,16 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
 	reqsk_put(req);
 }
 
-void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
-			      struct sock *child)
+struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
+				      struct request_sock *req,
+				      struct sock *child)
 {
 	struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
 
 	spin_lock(&queue->rskq_lock);
 	if (unlikely(sk->sk_state != TCP_LISTEN)) {
 		inet_child_forget(sk, req, child);
+		child = NULL;
 	} else {
 		req->sk = child;
 		req->dl_next = NULL;
@@ -808,6 +810,7 @@ void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
 		sk_acceptq_added(sk);
 	}
 	spin_unlock(&queue->rskq_lock);
+	return child;
 }
 EXPORT_SYMBOL(inet_csk_reqsk_queue_add);
 
@@ -817,11 +820,8 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
 	if (own_req) {
 		inet_csk_reqsk_queue_drop(sk, req);
 		reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
-		inet_csk_reqsk_queue_add(sk, req, child);
-		/* Warning: caller must not call reqsk_put(req);
-		 * child stole last reference on it.
-		 */
-		return child;
+		if (inet_csk_reqsk_queue_add(sk, req, child))
+			return child;
 	}
 	/* Too bad, another child took ownership of the request, undo. */
 	bh_unlock_sock(child);
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 8bb8e7ad8548..6029157a19ed 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -361,13 +361,20 @@ struct sock *inet_diag_find_one_icsk(struct net *net,
 				 req->id.idiag_dport, req->id.idiag_src[0],
 				 req->id.idiag_sport, req->id.idiag_if);
 #if IS_ENABLED(CONFIG_IPV6)
-	else if (req->sdiag_family == AF_INET6)
-		sk = inet6_lookup(net, hashinfo,
-				  (struct in6_addr *)req->id.idiag_dst,
-				  req->id.idiag_dport,
-				  (struct in6_addr *)req->id.idiag_src,
-				  req->id.idiag_sport,
-				  req->id.idiag_if);
+	else if (req->sdiag_family == AF_INET6) {
+		if (ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_dst) &&
+		    ipv6_addr_v4mapped((struct in6_addr *)req->id.idiag_src))
+			sk = inet_lookup(net, hashinfo, req->id.idiag_dst[3],
+					 req->id.idiag_dport, req->id.idiag_src[3],
+					 req->id.idiag_sport, req->id.idiag_if);
+		else
+			sk = inet6_lookup(net, hashinfo,
+					  (struct in6_addr *)req->id.idiag_dst,
+					  req->id.idiag_dport,
+					  (struct in6_addr *)req->id.idiag_src,
+					  req->id.idiag_sport,
+					  req->id.idiag_if);
+	}
 #endif
 	else
 		return ERR_PTR(-EINVAL);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 3f00810b7288..187c6fcc3027 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -661,6 +661,7 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
 	struct ipq *qp;
 
 	IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);
+	skb_orphan(skb);
 
 	/* Lookup (or create) queue header */
 	qp = ip_find(net, ip_hdr(skb), user, vif);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 7c51c4e1661f..41ba68de46d8 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -1054,8 +1054,9 @@ static const struct net_device_ops gre_tap_netdev_ops = {
 static void ipgre_tap_setup(struct net_device *dev)
 {
 	ether_setup(dev);
-	dev->netdev_ops		= &gre_tap_netdev_ops;
-	dev->priv_flags 	|= IFF_LIVE_ADDR_CHANGE;
+	dev->netdev_ops	= &gre_tap_netdev_ops;
+	dev->priv_flags &= ~IFF_TX_SKB_SHARING;
+	dev->priv_flags	|= IFF_LIVE_ADDR_CHANGE;
 	ip_tunnel_setup(dev, gre_tap_net_id);
 }
 
@@ -1240,6 +1241,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
 	err = ipgre_newlink(net, dev, tb, NULL);
 	if (err < 0)
 		goto out;
+
+	/* openvswitch users expect packet sizes to be unrestricted,
+	 * so set the largest MTU we can.
+	 */
+	err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false);
+	if (err)
+		goto out;
+
 	return dev;
 out:
 	free_netdev(dev);
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index b1209b63381f..d77eb0c3b684 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -316,7 +316,10 @@ static int ip_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
 	const struct iphdr *iph = ip_hdr(skb);
 	struct rtable *rt;
 
-	if (sysctl_ip_early_demux && !skb_dst(skb) && !skb->sk) {
+	if (sysctl_ip_early_demux &&
+	    !skb_dst(skb) &&
+	    !skb->sk &&
+	    !ip_is_fragment(iph)) {
 		const struct net_protocol *ipprot;
 		int protocol = iph->protocol;
 
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5f73a7c03e27..a50124260f5a 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -249,6 +249,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
 		switch (cmsg->cmsg_type) {
 		case IP_RETOPTS:
 			err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr));
+
+			/* Our caller is responsible for freeing ipc->opt */
 			err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg),
 					     err < 40 ? err : 40);
 			if (err)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index c7bd72e9b544..89e8861e05fc 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -943,17 +943,31 @@ done:
 }
 EXPORT_SYMBOL_GPL(ip_tunnel_ioctl);
 
-int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
 {
 	struct ip_tunnel *tunnel = netdev_priv(dev);
 	int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+	int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
 
-	if (new_mtu < 68 ||
-	    new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen)
+	if (new_mtu < 68)
 		return -EINVAL;
+
+	if (new_mtu > max_mtu) {
+		if (strict)
+			return -EINVAL;
+
+		new_mtu = max_mtu;
+	}
+
 	dev->mtu = new_mtu;
 	return 0;
 }
+EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu);
+
+int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+{
+	return __ip_tunnel_change_mtu(dev, new_mtu, true);
+}
 EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu);
 
 static void ip_tunnel_dev_free(struct net_device *dev)
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 67f7c9de0b16..2ed9dd2b5f2f 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -143,7 +143,11 @@ static char dhcp_client_identifier[253] __initdata;
 
 /* Persistent data: */
 
+#ifdef IPCONFIG_DYNAMIC
 static int ic_proto_used;			/* Protocol used, if any */
+#else
+#define ic_proto_used 0
+#endif
 static __be32 ic_nameservers[CONF_NAMESERVERS_MAX]; /* DNS Server IP addresses */
 static u8 ic_domain[64];		/* DNS (not NIS) domain name */
 
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 6fb869f646bf..a04dee536b8e 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -27,8 +27,6 @@ static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb,
 {
 	int err;
 
-	skb_orphan(skb);
-
 	local_bh_disable();
 	err = ip_defrag(net, skb, user);
 	local_bh_enable();
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index c117b21b937d..d3a27165f9cc 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -746,8 +746,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index bc35f1842512..7113bae4e6a0 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -547,8 +547,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(net, msg, &ipc, false);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			goto out;
+		}
 		if (ipc.opt)
 			free = 1;
 	}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 85f184e429c6..02c62299d717 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -129,6 +129,7 @@ static int ip_rt_mtu_expires __read_mostly	= 10 * 60 * HZ;
 static int ip_rt_min_pmtu __read_mostly		= 512 + 20 + 20;
 static int ip_rt_min_advmss __read_mostly	= 256;
 
+static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 /*
  *	Interface to generic destination cache.
  */
@@ -755,7 +756,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
 				struct fib_nh *nh = &FIB_RES_NH(res);
 
 				update_or_create_fnhe(nh, fl4->daddr, new_gw,
-						      0, 0);
+						0, jiffies + ip_rt_gc_timeout);
 			}
 			if (kill_route)
 				rt->dst.obsolete = DST_OBSOLETE_KILL;
@@ -1556,6 +1557,36 @@ static void ip_handle_martian_source(struct net_device *dev,
 #endif
 }
 
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+	struct fnhe_hash_bucket *hash;
+	struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+	u32 hval = fnhe_hashfun(daddr);
+
+	spin_lock_bh(&fnhe_lock);
+
+	hash = rcu_dereference_protected(nh->nh_exceptions,
+					 lockdep_is_held(&fnhe_lock));
+	hash += hval;
+
+	fnhe_p = &hash->chain;
+	fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+	while (fnhe) {
+		if (fnhe->fnhe_daddr == daddr) {
+			rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+				fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+			fnhe_flush_routes(fnhe);
+			kfree_rcu(fnhe, rcu);
+			break;
+		}
+		fnhe_p = &fnhe->fnhe_next;
+		fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+						 lockdep_is_held(&fnhe_lock));
+	}
+
+	spin_unlock_bh(&fnhe_lock);
+}
+
 /* called in rcu_read_lock() section */
 static int __mkroute_input(struct sk_buff *skb,
 			   const struct fib_result *res,
@@ -1609,11 +1640,20 @@ static int __mkroute_input(struct sk_buff *skb,
 
 	fnhe = find_exception(&FIB_RES_NH(*res), daddr);
 	if (do_cache) {
-		if (fnhe)
+		if (fnhe) {
 			rth = rcu_dereference(fnhe->fnhe_rth_input);
-		else
-			rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(&FIB_RES_NH(*res), daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
+			}
+		}
+
+		rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
 
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			skb_dst_set_noref(skb, &rth->dst);
 			goto out;
@@ -2014,19 +2054,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
 		struct fib_nh *nh = &FIB_RES_NH(*res);
 
 		fnhe = find_exception(nh, fl4->daddr);
-		if (fnhe)
+		if (fnhe) {
 			prth = &fnhe->fnhe_rth_output;
-		else {
-			if (unlikely(fl4->flowi4_flags &
-				     FLOWI_FLAG_KNOWN_NH &&
-				     !(nh->nh_gw &&
-				       nh->nh_scope == RT_SCOPE_LINK))) {
-				do_cache = false;
-				goto add;
+			rth = rcu_dereference(*prth);
+			if (rth && rth->dst.expires &&
+			    time_after(jiffies, rth->dst.expires)) {
+				ip_del_fnhe(nh, fl4->daddr);
+				fnhe = NULL;
+			} else {
+				goto rt_cache;
 			}
-			prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		}
+
+		if (unlikely(fl4->flowi4_flags &
+			     FLOWI_FLAG_KNOWN_NH &&
+			     !(nh->nh_gw &&
+			       nh->nh_scope == RT_SCOPE_LINK))) {
+			do_cache = false;
+			goto add;
+		}
+		prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
 		rth = rcu_dereference(*prth);
+
+rt_cache:
 		if (rt_cache_valid(rth)) {
 			dst_hold(&rth->dst);
 			return rth;
@@ -2569,7 +2619,6 @@ void ip_rt_multicast_event(struct in_device *in_dev)
 }
 
 #ifdef CONFIG_SYSCTL
-static int ip_rt_gc_timeout __read_mostly	= RT_GC_TIMEOUT;
 static int ip_rt_gc_interval __read_mostly  = 60 * HZ;
 static int ip_rt_gc_min_interval __read_mostly	= HZ / 2;
 static int ip_rt_gc_elasticity __read_mostly	= 8;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index fd17eec93525..483ffdf5aa4d 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -279,6 +279,7 @@
 
 #include <asm/uaccess.h>
 #include <asm/ioctls.h>
+#include <asm/unaligned.h>
 #include <net/busy_poll.h>
 
 int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
@@ -939,7 +940,7 @@ new_segment:
 
 		i = skb_shinfo(skb)->nr_frags;
 		can_coalesce = skb_can_coalesce(skb, i, page, offset);
-		if (!can_coalesce && i >= MAX_SKB_FRAGS) {
+		if (!can_coalesce && i >= sysctl_max_skb_frags) {
 			tcp_mark_push(tp, skb);
 			goto new_segment;
 		}
@@ -1212,7 +1213,7 @@ new_segment:
 
 			if (!skb_can_coalesce(skb, i, pfrag->page,
 					      pfrag->offset)) {
-				if (i == MAX_SKB_FRAGS || !sg) {
+				if (i == sysctl_max_skb_frags || !sg) {
 					tcp_mark_push(tp, skb);
 					goto new_segment;
 				}
@@ -2638,6 +2639,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	const struct inet_connection_sock *icsk = inet_csk(sk);
 	u32 now = tcp_time_stamp;
 	unsigned int start;
+	u64 rate64;
 	u32 rate;
 
 	memset(info, 0, sizeof(*info));
@@ -2703,15 +2705,17 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_total_retrans = tp->total_retrans;
 
 	rate = READ_ONCE(sk->sk_pacing_rate);
-	info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL;
+	rate64 = rate != ~0U ? rate : ~0ULL;
+	put_unaligned(rate64, &info->tcpi_pacing_rate);
 
 	rate = READ_ONCE(sk->sk_max_pacing_rate);
-	info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
+	rate64 = rate != ~0U ? rate : ~0ULL;
+	put_unaligned(rate64, &info->tcpi_max_pacing_rate);
 
 	do {
 		start = u64_stats_fetch_begin_irq(&tp->syncp);
-		info->tcpi_bytes_acked = tp->bytes_acked;
-		info->tcpi_bytes_received = tp->bytes_received;
+		put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked);
+		put_unaligned(tp->bytes_received, &info->tcpi_bytes_received);
 	} while (u64_stats_fetch_retry_irq(&tp->syncp, start));
 	info->tcpi_segs_out = tp->segs_out;
 	info->tcpi_segs_in = tp->segs_in;
@@ -2946,7 +2950,7 @@ static void __tcp_alloc_md5sig_pool(void)
 			struct crypto_hash *hash;
 
 			hash = crypto_alloc_hash("md5", 0, CRYPTO_ALG_ASYNC);
-			if (IS_ERR_OR_NULL(hash))
+			if (IS_ERR(hash))
 				return;
 			per_cpu(tcp_md5sig_pool, cpu).md5_desc.tfm = hash;
 		}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 0003d409fec5..3b2c8e90a475 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -2164,8 +2164,7 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
-	int cnt, oldcnt;
-	int err;
+	int cnt, oldcnt, lost;
 	unsigned int mss;
 	/* Use SACK to deduce losses of new sequences sent during recovery */
 	const u32 loss_high = tcp_is_sack(tp) ?  tp->snd_nxt : tp->high_seq;
@@ -2205,9 +2204,10 @@ static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head)
 				break;
 
 			mss = tcp_skb_mss(skb);
-			err = tcp_fragment(sk, skb, (packets - oldcnt) * mss,
-					   mss, GFP_ATOMIC);
-			if (err < 0)
+			/* If needed, chop off the prefix to mark as lost. */
+			lost = (packets - oldcnt) * mss;
+			if (lost < skb->len &&
+			    tcp_fragment(sk, skb, lost, mss, GFP_ATOMIC) < 0)
 				break;
 			cnt = packets;
 		}
@@ -2366,8 +2366,6 @@ static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
 			tp->snd_ssthresh = tp->prior_ssthresh;
 			tcp_ecn_withdraw_cwr(tp);
 		}
-	} else {
-		tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh);
 	}
 	tp->snd_cwnd_stamp = tcp_time_stamp;
 	tp->undo_marker = 0;
@@ -2898,7 +2896,10 @@ static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us)
 {
 	const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ;
 	struct rtt_meas *m = tcp_sk(sk)->rtt_min;
-	struct rtt_meas rttm = { .rtt = (rtt_us ? : 1), .ts = now };
+	struct rtt_meas rttm = {
+		.rtt = likely(rtt_us) ? rtt_us : jiffies_to_usecs(1),
+		.ts = now,
+	};
 	u32 elapsed;
 
 	/* Check if the new measurement updates the 1st, 2nd, or 3rd choices */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5ced3e4013e3..487ac67059e2 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -311,7 +311,7 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk)
 
 
 /* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */
-void tcp_req_err(struct sock *sk, u32 seq)
+void tcp_req_err(struct sock *sk, u32 seq, bool abort)
 {
 	struct request_sock *req = inet_reqsk(sk);
 	struct net *net = sock_net(sk);
@@ -323,7 +323,7 @@ void tcp_req_err(struct sock *sk, u32 seq)
 
 	if (seq != tcp_rsk(req)->snt_isn) {
 		NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
-	} else {
+	} else if (abort) {
 		/*
 		 * Still in SYN_RECV, just remove it silently.
 		 * There is no good way to pass the error to the newly
@@ -383,7 +383,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
 	}
 	seq = ntohl(th->seq);
 	if (sk->sk_state == TCP_NEW_SYN_RECV)
-		return tcp_req_err(sk, seq);
+		return tcp_req_err(sk, seq,
+				  type == ICMP_PARAMETERPROB ||
+				  type == ICMP_TIME_EXCEEDED ||
+				  (type == ICMP_DEST_UNREACH &&
+				   (code == ICMP_NET_UNREACH ||
+				    code == ICMP_HOST_UNREACH)));
 
 	bh_lock_sock(sk);
 	/* If too many ICMPs get dropped on busy
@@ -707,7 +712,8 @@ release_sk1:
    outside socket context is ugly, certainly. What can I do?
  */
 
-static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
+static void tcp_v4_send_ack(struct net *net,
+			    struct sk_buff *skb, u32 seq, u32 ack,
 			    u32 win, u32 tsval, u32 tsecr, int oif,
 			    struct tcp_md5sig_key *key,
 			    int reply_flags, u8 tos)
@@ -722,7 +728,6 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
 			];
 	} rep;
 	struct ip_reply_arg arg;
-	struct net *net = dev_net(skb_dst(skb)->dev);
 
 	memset(&rep.th, 0, sizeof(struct tcphdr));
 	memset(&arg, 0, sizeof(arg));
@@ -784,7 +789,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
 	struct inet_timewait_sock *tw = inet_twsk(sk);
 	struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
 
-	tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+	tcp_v4_send_ack(sock_net(sk), skb,
+			tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
 			tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
 			tcp_time_stamp + tcptw->tw_ts_offset,
 			tcptw->tw_ts_recent,
@@ -803,8 +809,10 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 	/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
 	 * sk->sk_state == TCP_SYN_RECV -> for Fast Open.
 	 */
-	tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
-			tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
+	u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
+					     tcp_sk(sk)->snd_nxt;
+
+	tcp_v4_send_ack(sock_net(sk), skb, seq,
 			tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
 			tcp_time_stamp,
 			req->ts_recent,
@@ -1589,28 +1597,30 @@ process:
 
 	if (sk->sk_state == TCP_NEW_SYN_RECV) {
 		struct request_sock *req = inet_reqsk(sk);
-		struct sock *nsk = NULL;
+		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (tcp_v4_inbound_md5_hash(sk, skb))
-			goto discard_and_relse;
-		if (likely(sk->sk_state == TCP_LISTEN)) {
-			nsk = tcp_check_req(sk, skb, req, false);
-		} else {
+		if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) {
+			reqsk_put(req);
+			goto discard_it;
+		}
+		if (unlikely(sk->sk_state != TCP_LISTEN)) {
 			inet_csk_reqsk_queue_drop_and_put(sk, req);
 			goto lookup;
 		}
+		sock_hold(sk);
+		nsk = tcp_check_req(sk, skb, req, false);
 		if (!nsk) {
 			reqsk_put(req);
-			goto discard_it;
+			goto discard_and_relse;
 		}
 		if (nsk == sk) {
-			sock_hold(sk);
 			reqsk_put(req);
 		} else if (tcp_child_process(sk, nsk, skb)) {
 			tcp_v4_send_reset(nsk, skb);
-			goto discard_it;
+			goto discard_and_relse;
 		} else {
+			sock_put(sk);
 			return 0;
 		}
 	}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index dc45b538e237..95d2f198017e 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -499,6 +499,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 	struct sock *sk, *result;
 	struct hlist_nulls_node *node;
 	int score, badness, matches = 0, reuseport = 0;
+	bool select_ok = true;
 	u32 hash = 0;
 
 begin:
@@ -512,14 +513,18 @@ begin:
 			badness = score;
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
-				struct sock *sk2;
 				hash = udp_ehashfn(net, daddr, hnum,
 						   saddr, sport);
-				sk2 = reuseport_select_sock(sk, hash, skb,
-							    sizeof(struct udphdr));
-				if (sk2) {
-					result = sk2;
-					goto found;
+				if (select_ok) {
+					struct sock *sk2;
+
+					sk2 = reuseport_select_sock(sk, hash, skb,
+							sizeof(struct udphdr));
+					if (sk2) {
+						result = sk2;
+						select_ok = false;
+						goto found;
+					}
 				}
 				matches = 1;
 			}
@@ -563,6 +568,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 	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();
@@ -601,14 +607,18 @@ begin:
 			badness = score;
 			reuseport = sk->sk_reuseport;
 			if (reuseport) {
-				struct sock *sk2;
 				hash = udp_ehashfn(net, daddr, hnum,
 						   saddr, sport);
-				sk2 = reuseport_select_sock(sk, hash, skb,
+				if (select_ok) {
+					struct sock *sk2;
+
+					sk2 = reuseport_select_sock(sk, hash, skb,
 							sizeof(struct udphdr));
-				if (sk2) {
-					result = sk2;
-					goto found;
+					if (sk2) {
+						result = sk2;
+						select_ok = false;
+						goto found;
+					}
 				}
 				matches = 1;
 			}
@@ -1038,8 +1048,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
 	if (msg->msg_controllen) {
 		err = ip_cmsg_send(sock_net(sk), msg, &ipc,
 				   sk->sk_family == AF_INET6);
-		if (err)
+		if (unlikely(err)) {
+			kfree(ipc.opt);
 			return err;
+		}
 		if (ipc.opt)
 			free = 1;
 		connected = 0;
generated by cgit-pink 1.4.1 (git 2.36.1) at 2024-10-10 13:25:54 +0000