Commit 762d17b9 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'tcp-mem-pressure-vs-SO_RCVLOWAT' 



Eric Dumazet says:

====================
tcp: mem pressure vs SO_RCVLOWAT

First patch fixes an issue for applications using SO_RCVLOWAT
to reduce context switches.

Second patch is a cleanup.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 5cdaf9d6 05dc72ab

include/net/tcp.h

+19 −2
Original line number Diff line number Diff line
@@ -1431,12 +1431,29 @@ void tcp_cleanup_rbuf(struct sock *sk, int copied); 
 */

static inline bool tcp_rmem_pressure(const struct sock *sk)

{

	int rcvbuf = READ_ONCE(sk->sk_rcvbuf);

	int threshold = rcvbuf - (rcvbuf >> 3);

	int rcvbuf, threshold;



	if (tcp_under_memory_pressure(sk))

		return true;



	rcvbuf = READ_ONCE(sk->sk_rcvbuf);

	threshold = rcvbuf - (rcvbuf >> 3);



	return atomic_read(&sk->sk_rmem_alloc) > threshold;

}



static inline bool tcp_epollin_ready(const struct sock *sk, int target)

{

	const struct tcp_sock *tp = tcp_sk(sk);

	int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);



	if (avail <= 0)

		return false;



	return (avail >= target) || tcp_rmem_pressure(sk) ||

	       (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss);

}



extern void tcp_openreq_init_rwin(struct request_sock *req,

				  const struct sock *sk_listener,

				  const struct dst_entry *dst);

net/ipv4/tcp.c

+5 −13
Original line number Diff line number Diff line
@@ -481,19 +481,11 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) 
	}

}



static inline bool tcp_stream_is_readable(const struct tcp_sock *tp,

					  int target, struct sock *sk)

static bool tcp_stream_is_readable(struct sock *sk, int target)

{

	int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq);



	if (avail > 0) {

		if (avail >= target)

			return true;

		if (tcp_rmem_pressure(sk))

			return true;

		if (tcp_receive_window(tp) <= inet_csk(sk)->icsk_ack.rcv_mss)

	if (tcp_epollin_ready(sk, target))

		return true;

	}



	if (sk->sk_prot->stream_memory_read)

		return sk->sk_prot->stream_memory_read(sk);

	return false;
@@ -568,7 +560,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) 
		    tp->urg_data)

			target++;



		if (tcp_stream_is_readable(tp, target, sk))

		if (tcp_stream_is_readable(sk, target))

			mask |= EPOLLIN | EPOLLRDNORM;



		if (!(sk->sk_shutdown & SEND_SHUTDOWN)) {

net/ipv4/tcp_input.c

+2 −9
Original line number Diff line number Diff line
@@ -4924,14 +4924,7 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size) 


void tcp_data_ready(struct sock *sk)

{

	const struct tcp_sock *tp = tcp_sk(sk);

	int avail = tp->rcv_nxt - tp->copied_seq;



	if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) &&

	    !sock_flag(sk, SOCK_DONE) &&

	    tcp_receive_window(tp) > inet_csk(sk)->icsk_ack.rcv_mss)

		return;



	if (tcp_epollin_ready(sk, sk->sk_rcvlowat))

		sk->sk_data_ready(sk);

}