1 files changed, 61 insertions, 111 deletions

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fec656f5a39e..f9cec624068d 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -91,6 +91,8 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 struct inet_hashinfo tcp_hashinfo;
 EXPORT_SYMBOL(tcp_hashinfo);
 
+static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk);
+
 static u32 tcp_v4_init_seq(const struct sk_buff *skb)
 {
 	return secure_tcp_seq(ip_hdr(skb)->daddr,
@@ -206,7 +208,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
 	struct rtable *rt;
 	int err;
 	struct ip_options_rcu *inet_opt;
-	struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row;
+	struct inet_timewait_death_row *tcp_death_row = sock_net(sk)->ipv4.tcp_death_row;
 
 	if (addr_len < sizeof(struct sockaddr_in))
 		return -EINVAL;
@@ -810,7 +812,8 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 	arg.tos = ip_hdr(skb)->tos;
 	arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
 	local_bh_disable();
-	ctl_sk = this_cpu_read(*net->ipv4.tcp_sk);
+	ctl_sk = this_cpu_read(ipv4_tcp_sk);
+	sock_net_set(ctl_sk, net);
 	if (sk) {
 		ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
 				   inet_twsk(sk)->tw_mark : sk->sk_mark;
@@ -825,6 +828,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb)
 			      transmit_time);
 
 	ctl_sk->sk_mark = 0;
+	sock_net_set(ctl_sk, &init_net);
 	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
 	__TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
 	local_bh_enable();
@@ -908,7 +912,8 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	arg.tos = tos;
 	arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
 	local_bh_disable();
-	ctl_sk = this_cpu_read(*net->ipv4.tcp_sk);
+	ctl_sk = this_cpu_read(ipv4_tcp_sk);
+	sock_net_set(ctl_sk, net);
 	ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
 			   inet_twsk(sk)->tw_mark : sk->sk_mark;
 	ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ?
@@ -921,6 +926,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
 			      transmit_time);
 
 	ctl_sk->sk_mark = 0;
+	sock_net_set(ctl_sk, &init_net);
 	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
 	local_bh_enable();
 }
@@ -1403,72 +1409,6 @@ EXPORT_SYMBOL(tcp_v4_md5_hash_skb);
 
 #endif
 
-/* Called with rcu_read_lock() */
-static bool tcp_v4_inbound_md5_hash(const struct sock *sk,
-				    const struct sk_buff *skb,
-				    int dif, int sdif)
-{
-#ifdef CONFIG_TCP_MD5SIG
-	/*
-	 * This gets called for each TCP segment that arrives
-	 * so we want to be efficient.
-	 * We have 3 drop cases:
-	 * o No MD5 hash and one expected.
-	 * o MD5 hash and we're not expecting one.
-	 * o MD5 hash and its wrong.
-	 */
-	const __u8 *hash_location = NULL;
-	struct tcp_md5sig_key *hash_expected;
-	const struct iphdr *iph = ip_hdr(skb);
-	const struct tcphdr *th = tcp_hdr(skb);
-	const union tcp_md5_addr *addr;
-	unsigned char newhash[16];
-	int genhash, l3index;
-
-	/* sdif set, means packet ingressed via a device
-	 * in an L3 domain and dif is set to the l3mdev
-	 */
-	l3index = sdif ? dif : 0;
-
-	addr = (union tcp_md5_addr *)&iph->saddr;
-	hash_expected = tcp_md5_do_lookup(sk, l3index, addr, AF_INET);
-	hash_location = tcp_parse_md5sig_option(th);
-
-	/* We've parsed the options - do we have a hash? */
-	if (!hash_expected && !hash_location)
-		return false;
-
-	if (hash_expected && !hash_location) {
-		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND);
-		return true;
-	}
-
-	if (!hash_expected && hash_location) {
-		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED);
-		return true;
-	}
-
-	/* Okay, so this is hash_expected and hash_location -
-	 * so we need to calculate the checksum.
-	 */
-	genhash = tcp_v4_md5_hash_skb(newhash,
-				      hash_expected,
-				      NULL, skb);
-
-	if (genhash || memcmp(hash_location, newhash, 16) != 0) {
-		NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE);
-		net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s L3 index %d\n",
-				     &iph->saddr, ntohs(th->source),
-				     &iph->daddr, ntohs(th->dest),
-				     genhash ? " tcp_v4_calc_md5_hash failed"
-				     : "", l3index);
-		return true;
-	}
-	return false;
-#endif
-	return false;
-}
-
 static void tcp_v4_init_req(struct request_sock *req,
 			    const struct sock *sk_listener,
 			    struct sk_buff *skb)
@@ -1698,6 +1638,7 @@ INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *,
  */
 int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 {
+	enum skb_drop_reason reason;
 	struct sock *rsk;
 
 	if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
@@ -1720,6 +1661,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 		return 0;
 	}
 
+	reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	if (tcp_checksum_complete(skb))
 		goto csum_err;
 
@@ -1747,7 +1689,7 @@ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb)
 reset:
 	tcp_v4_send_reset(rsk, skb);
 discard:
-	kfree_skb(skb);
+	kfree_skb_reason(skb, reason);
 	/* Be careful here. If this function gets more complicated and
 	 * gcc suffers from register pressure on the x86, sk (in %ebx)
 	 * might be destroyed here. This current version compiles correctly,
@@ -1756,6 +1698,7 @@ discard:
 	return 0;
 
 csum_err:
+	reason = SKB_DROP_REASON_TCP_CSUM;
 	trace_tcp_bad_csum(skb);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
 	TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
@@ -1801,7 +1744,8 @@ int tcp_v4_early_demux(struct sk_buff *skb)
 	return 0;
 }
 
-bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
+bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
+		     enum skb_drop_reason *reason)
 {
 	u32 limit, tail_gso_size, tail_gso_segs;
 	struct skb_shared_info *shinfo;
@@ -1827,6 +1771,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
 	if (unlikely(tcp_checksum_complete(skb))) {
 		bh_unlock_sock(sk);
 		trace_tcp_bad_csum(skb);
+		*reason = SKB_DROP_REASON_TCP_CSUM;
 		__TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS);
 		__TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
 		return true;
@@ -1915,6 +1860,7 @@ no_coalesce:
 
 	if (unlikely(sk_add_backlog(sk, skb, limit))) {
 		bh_unlock_sock(sk);
+		*reason = SKB_DROP_REASON_SOCKET_BACKLOG;
 		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP);
 		return true;
 	}
@@ -1965,13 +1911,13 @@ static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph,
 int tcp_v4_rcv(struct sk_buff *skb)
 {
 	struct net *net = dev_net(skb->dev);
+	enum skb_drop_reason drop_reason;
 	int sdif = inet_sdif(skb);
 	int dif = inet_iif(skb);
 	const struct iphdr *iph;
 	const struct tcphdr *th;
 	bool refcounted;
 	struct sock *sk;
-	int drop_reason;
 	int ret;
 
 	drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
@@ -2019,7 +1965,10 @@ process:
 		struct sock *nsk;
 
 		sk = req->rsk_listener;
-		if (unlikely(tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) {
+		drop_reason = tcp_inbound_md5_hash(sk, skb,
+						   &iph->saddr, &iph->daddr,
+						   AF_INET, dif, sdif);
+		if (unlikely(drop_reason)) {
 			sk_drops_add(sk, skb);
 			reqsk_put(req);
 			goto discard_it;
@@ -2051,6 +2000,8 @@ process:
 			iph = ip_hdr(skb);
 			tcp_v4_fill_cb(skb, iph, th);
 			nsk = tcp_check_req(sk, skb, req, false, &req_stolen);
+		} else {
+			drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
 		}
 		if (!nsk) {
 			reqsk_put(req);
@@ -2086,10 +2037,14 @@ process:
 		}
 	}
 
-	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb))
+	if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) {
+		drop_reason = SKB_DROP_REASON_XFRM_POLICY;
 		goto discard_and_relse;
+	}
 
-	if (tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))
+	drop_reason = tcp_inbound_md5_hash(sk, skb, &iph->saddr,
+					   &iph->daddr, AF_INET, dif, sdif);
+	if (drop_reason)
 		goto discard_and_relse;
 
 	nf_reset_ct(skb);
@@ -2118,7 +2073,7 @@ process:
 	if (!sock_owned_by_user(sk)) {
 		ret = tcp_v4_do_rcv(sk, skb);
 	} else {
-		if (tcp_add_backlog(sk, skb))
+		if (tcp_add_backlog(sk, skb, &drop_reason))
 			goto discard_and_relse;
 	}
 	bh_unlock_sock(sk);
@@ -2160,6 +2115,7 @@ discard_and_relse:
 
 do_time_wait:
 	if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
+		drop_reason = SKB_DROP_REASON_XFRM_POLICY;
 		inet_twsk_put(inet_twsk(sk));
 		goto discard_it;
 	}
@@ -3111,41 +3067,18 @@ EXPORT_SYMBOL(tcp_prot);
 
 static void __net_exit tcp_sk_exit(struct net *net)
 {
-	int cpu;
+	struct inet_timewait_death_row *tcp_death_row = net->ipv4.tcp_death_row;
 
 	if (net->ipv4.tcp_congestion_control)
 		bpf_module_put(net->ipv4.tcp_congestion_control,
 			       net->ipv4.tcp_congestion_control->owner);
-
-	for_each_possible_cpu(cpu)
-		inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu));
-	free_percpu(net->ipv4.tcp_sk);
+	if (refcount_dec_and_test(&tcp_death_row->tw_refcount))
+		kfree(tcp_death_row);
 }
 
 static int __net_init tcp_sk_init(struct net *net)
 {
-	int res, cpu, cnt;
-
-	net->ipv4.tcp_sk = alloc_percpu(struct sock *);
-	if (!net->ipv4.tcp_sk)
-		return -ENOMEM;
-
-	for_each_possible_cpu(cpu) {
-		struct sock *sk;
-
-		res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
-					   IPPROTO_TCP, net);
-		if (res)
-			goto fail;
-		sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
-
-		/* Please enforce IP_DF and IPID==0 for RST and
-		 * ACK sent in SYN-RECV and TIME-WAIT state.
-		 */
-		inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO;
-
-		*per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk;
-	}
+	int cnt;
 
 	net->ipv4.sysctl_tcp_ecn = 2;
 	net->ipv4.sysctl_tcp_ecn_fallback = 1;
@@ -3172,9 +3105,13 @@ static int __net_init tcp_sk_init(struct net *net)
 	net->ipv4.sysctl_tcp_tw_reuse = 2;
 	net->ipv4.sysctl_tcp_no_ssthresh_metrics_save = 1;
 
+	net->ipv4.tcp_death_row = kzalloc(sizeof(struct inet_timewait_death_row), GFP_KERNEL);
+	if (!net->ipv4.tcp_death_row)
+		return -ENOMEM;
+	refcount_set(&net->ipv4.tcp_death_row->tw_refcount, 1);
 	cnt = tcp_hashinfo.ehash_mask + 1;
-	net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2;
-	net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo;
+	net->ipv4.tcp_death_row->sysctl_max_tw_buckets = cnt / 2;
+	net->ipv4.tcp_death_row->hashinfo = &tcp_hashinfo;
 
 	net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128);
 	net->ipv4.sysctl_tcp_sack = 1;
@@ -3200,6 +3137,7 @@ static int __net_init tcp_sk_init(struct net *net)
 	/* rfc5961 challenge ack rate limiting */
 	net->ipv4.sysctl_tcp_challenge_ack_limit = 1000;
 	net->ipv4.sysctl_tcp_min_tso_segs = 2;
+	net->ipv4.sysctl_tcp_tso_rtt_log = 9;  /* 2^9 = 512 usec */
 	net->ipv4.sysctl_tcp_min_rtt_wlen = 300;
 	net->ipv4.sysctl_tcp_autocorking = 1;
 	net->ipv4.sysctl_tcp_invalid_ratelimit = HZ/2;
@@ -3229,18 +3167,12 @@ static int __net_init tcp_sk_init(struct net *net)
 		net->ipv4.tcp_congestion_control = &tcp_reno;
 
 	return 0;
-fail:
-	tcp_sk_exit(net);
-
-	return res;
 }
 
 static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
 {
 	struct net *net;
 
-	inet_twsk_purge(&tcp_hashinfo, AF_INET);
-
 	list_for_each_entry(net, net_exit_list, exit_list)
 		tcp_fastopen_ctx_destroy(net);
 }
@@ -3326,6 +3258,24 @@ static void __init bpf_iter_register(void)
 
 void __init tcp_v4_init(void)
 {
+	int cpu, res;
+
+	for_each_possible_cpu(cpu) {
+		struct sock *sk;
+
+		res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW,
+					   IPPROTO_TCP, &init_net);
+		if (res)
+			panic("Failed to create the TCP control socket.\n");
+		sock_set_flag(sk, SOCK_USE_WRITE_QUEUE);
+
+		/* Please enforce IP_DF and IPID==0 for RST and
+		 * ACK sent in SYN-RECV and TIME-WAIT state.
+		 */
+		inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO;
+
+		per_cpu(ipv4_tcp_sk, cpu) = sk;
+	}
 	if (register_pernet_subsys(&tcp_sk_ops))
 		panic("Failed to create the TCP control socket.\n");