1 files changed, 35 insertions, 48 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index cf18fbcbf123..9984d23a7f3e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -429,7 +429,7 @@ void tcp_init_sock(struct sock *sk)
 	 * algorithms that we must have the following bandaid to talk
 	 * efficiently to them.  -DaveM
 	 */
-	tp->snd_cwnd = TCP_INIT_CWND;
+	tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
 
 	/* There's a bubble in the pipe until at least the first ACK. */
 	tp->app_limited = ~0U;
@@ -843,7 +843,6 @@ ssize_t tcp_splice_read(struct socket *sock, loff_t *ppos,
 	}
 
 	release_sock(sk);
-	sk_defer_free_flush(sk);
 
 	if (spliced)
 		return spliced;
@@ -1589,20 +1588,6 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied)
 		tcp_send_ack(sk);
 }
 
-void __sk_defer_free_flush(struct sock *sk)
-{
-	struct llist_node *head;
-	struct sk_buff *skb, *n;
-
-	head = llist_del_all(&sk->defer_list);
-	llist_for_each_entry_safe(skb, n, head, ll_node) {
-		prefetch(n);
-		skb_mark_not_on_list(skb);
-		__kfree_skb(skb);
-	}
-}
-EXPORT_SYMBOL(__sk_defer_free_flush);
-
 static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb)
 {
 	__skb_unlink(skb, &sk->sk_receive_queue);
@@ -1610,11 +1595,7 @@ static void tcp_eat_recv_skb(struct sock *sk, struct sk_buff *skb)
 		sock_rfree(skb);
 		skb->destructor = NULL;
 		skb->sk = NULL;
-		if (!skb_queue_empty(&sk->sk_receive_queue) ||
-		    !llist_empty(&sk->defer_list)) {
-			llist_add(&skb->ll_node, &sk->defer_list);
-			return;
-		}
+		return skb_attempt_defer_free(skb);
 	}
 	__kfree_skb(skb);
 }
@@ -1877,8 +1858,7 @@ static void tcp_zerocopy_set_hint_for_skb(struct sock *sk,
 }
 
 static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
-			      int nonblock, int flags,
-			      struct scm_timestamping_internal *tss,
+			      int flags, struct scm_timestamping_internal *tss,
 			      int *cmsg_flags);
 static int receive_fallback_to_copy(struct sock *sk,
 				    struct tcp_zerocopy_receive *zc, int inq,
@@ -1900,7 +1880,7 @@ static int receive_fallback_to_copy(struct sock *sk,
 	if (err)
 		return err;
 
-	err = tcp_recvmsg_locked(sk, &msg, inq, /*nonblock=*/1, /*flags=*/0,
+	err = tcp_recvmsg_locked(sk, &msg, inq, MSG_DONTWAIT,
 				 tss, &zc->msg_flags);
 	if (err < 0)
 		return err;
@@ -2316,8 +2296,7 @@ static int tcp_inq_hint(struct sock *sk)
  */
 
 static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
-			      int nonblock, int flags,
-			      struct scm_timestamping_internal *tss,
+			      int flags, struct scm_timestamping_internal *tss,
 			      int *cmsg_flags)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
@@ -2335,9 +2314,11 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 	if (sk->sk_state == TCP_LISTEN)
 		goto out;
 
-	if (tp->recvmsg_inq)
+	if (tp->recvmsg_inq) {
 		*cmsg_flags = TCP_CMSG_INQ;
-	timeo = sock_rcvtimeo(sk, nonblock);
+		msg->msg_get_inq = 1;
+	}
+	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
 
 	/* Urgent data needs to be handled specially. */
 	if (flags & MSG_OOB)
@@ -2455,7 +2436,6 @@ static int tcp_recvmsg_locked(struct sock *sk, struct msghdr *msg, size_t len,
 			__sk_flush_backlog(sk);
 		} else {
 			tcp_cleanup_rbuf(sk, copied);
-			sk_defer_free_flush(sk);
 			sk_wait_data(sk, &timeo, last);
 		}
 
@@ -2556,10 +2536,10 @@ recv_sndq:
 	goto out;
 }
 
-int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
-		int flags, int *addr_len)
+int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags,
+		int *addr_len)
 {
-	int cmsg_flags = 0, ret, inq;
+	int cmsg_flags = 0, ret;
 	struct scm_timestamping_internal tss;
 
 	if (unlikely(flags & MSG_ERRQUEUE))
@@ -2568,20 +2548,20 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock,
 	if (sk_can_busy_loop(sk) &&
 	    skb_queue_empty_lockless(&sk->sk_receive_queue) &&
 	    sk->sk_state == TCP_ESTABLISHED)
-		sk_busy_loop(sk, nonblock);
+		sk_busy_loop(sk, flags & MSG_DONTWAIT);
 
 	lock_sock(sk);
-	ret = tcp_recvmsg_locked(sk, msg, len, nonblock, flags, &tss,
-				 &cmsg_flags);
+	ret = tcp_recvmsg_locked(sk, msg, len, flags, &tss, &cmsg_flags);
 	release_sock(sk);
-	sk_defer_free_flush(sk);
 
-	if (cmsg_flags && ret >= 0) {
+	if ((cmsg_flags || msg->msg_get_inq) && ret >= 0) {
 		if (cmsg_flags & TCP_CMSG_TS)
 			tcp_recv_timestamp(msg, sk, &tss);
-		if (cmsg_flags & TCP_CMSG_INQ) {
-			inq = tcp_inq_hint(sk);
-			put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq);
+		if (msg->msg_get_inq) {
+			msg->msg_inq = tcp_inq_hint(sk);
+			if (cmsg_flags & TCP_CMSG_INQ)
+				put_cmsg(msg, SOL_TCP, TCP_CM_INQ,
+					 sizeof(msg->msg_inq), &msg->msg_inq);
 		}
 	}
 	return ret;
@@ -3033,7 +3013,7 @@ int tcp_disconnect(struct sock *sk, int flags)
 	icsk->icsk_rto_min = TCP_RTO_MIN;
 	icsk->icsk_delack_max = TCP_DELACK_MAX;
 	tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
-	tp->snd_cwnd = TCP_INIT_CWND;
+	tcp_snd_cwnd_set(tp, TCP_INIT_CWND);
 	tp->snd_cwnd_cnt = 0;
 	tp->window_clamp = 0;
 	tp->delivered = 0;
@@ -3099,7 +3079,6 @@ int tcp_disconnect(struct sock *sk, int flags)
 		sk->sk_frag.page = NULL;
 		sk->sk_frag.offset = 0;
 	}
-	sk_defer_free_flush(sk);
 	sk_error_report(sk);
 	return 0;
 }
@@ -3744,7 +3723,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
 	info->tcpi_max_pacing_rate = rate64;
 
 	info->tcpi_reordering = tp->reordering;
-	info->tcpi_snd_cwnd = tp->snd_cwnd;
+	info->tcpi_snd_cwnd = tcp_snd_cwnd(tp);
 
 	if (info->tcpi_state == TCP_LISTEN) {
 		/* listeners aliased fields :
@@ -3915,7 +3894,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk,
 	rate64 = tcp_compute_delivery_rate(tp);
 	nla_put_u64_64bit(stats, TCP_NLA_DELIVERY_RATE, rate64, TCP_NLA_PAD);
 
-	nla_put_u32(stats, TCP_NLA_SND_CWND, tp->snd_cwnd);
+	nla_put_u32(stats, TCP_NLA_SND_CWND, tcp_snd_cwnd(tp));
 	nla_put_u32(stats, TCP_NLA_REORDERING, tp->reordering);
 	nla_put_u32(stats, TCP_NLA_MIN_RTT, tcp_min_rtt(tp));
 
@@ -4228,7 +4207,6 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
 		err = BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sk, level, optname,
 							  &zc, &len, err);
 		release_sock(sk);
-		sk_defer_free_flush(sk);
 		if (len >= offsetofend(struct tcp_zerocopy_receive, msg_flags))
 			goto zerocopy_rcv_cmsg;
 		switch (len) {
@@ -4617,7 +4595,6 @@ void __init tcp_init(void)
 	timer_setup(&tcp_orphan_timer, tcp_orphan_update, TIMER_DEFERRABLE);
 	mod_timer(&tcp_orphan_timer, jiffies + TCP_ORPHAN_TIMER_PERIOD);
 
-	inet_hashinfo_init(&tcp_hashinfo);
 	inet_hashinfo2_init(&tcp_hashinfo, "tcp_listen_portaddr_hash",
 			    thash_entries, 21,  /* one slot per 2 MB*/
 			    0, 64 * 1024);
@@ -4627,6 +4604,12 @@ void __init tcp_init(void)
 				  SLAB_HWCACHE_ALIGN | SLAB_PANIC |
 				  SLAB_ACCOUNT,
 				  NULL);
+	tcp_hashinfo.bind2_bucket_cachep =
+		kmem_cache_create("tcp_bind2_bucket",
+				  sizeof(struct inet_bind2_bucket), 0,
+				  SLAB_HWCACHE_ALIGN | SLAB_PANIC |
+				  SLAB_ACCOUNT,
+				  NULL);
 
 	/* Size and allocate the main established and bind bucket
 	 * hash tables.
@@ -4649,8 +4632,9 @@ void __init tcp_init(void)
 	if (inet_ehash_locks_alloc(&tcp_hashinfo))
 		panic("TCP: failed to alloc ehash_locks");
 	tcp_hashinfo.bhash =
-		alloc_large_system_hash("TCP bind",
-					sizeof(struct inet_bind_hashbucket),
+		alloc_large_system_hash("TCP bind bhash tables",
+					sizeof(struct inet_bind_hashbucket) +
+					sizeof(struct inet_bind2_hashbucket),
 					tcp_hashinfo.ehash_mask + 1,
 					17, /* one slot per 128 KB of memory */
 					0,
@@ -4659,9 +4643,12 @@ void __init tcp_init(void)
 					0,
 					64 * 1024);
 	tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size;
+	tcp_hashinfo.bhash2 =
+		(struct inet_bind2_hashbucket *)(tcp_hashinfo.bhash + tcp_hashinfo.bhash_size);
 	for (i = 0; i < tcp_hashinfo.bhash_size; i++) {
 		spin_lock_init(&tcp_hashinfo.bhash[i].lock);
 		INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain);
+		INIT_HLIST_HEAD(&tcp_hashinfo.bhash2[i].chain);
 	}