Commit b1e014a1 authored by Eric Dumazet's avatar Eric Dumazet Committed by Jakub Kicinski
Browse files

tcp: add newval parameter to tcp_rcvbuf_grow() 



This patch has no functional change, and prepares the following one.

tcp_rcvbuf_grow() will need to have access to tp->rcvq_space.space
old and new values.

Change mptcp_rcvbuf_grow() in a similar way.

Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
[ Moved 'oldval' declaration to the next patch to avoid warnings at
 build time. ]
Signed-off-by: default avatarMatthieu Baerts (NGI0) <matttbe@kernel.org>
Reviewed-by: default avatarNeal Cardwell <ncardwell@google.com>
Link: https://patch.msgid.link/20251028-net-tcp-recv-autotune-v3-3-74b43ba4c84c@kernel.org


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent 24990d89

include/net/tcp.h

+1 −1
Original line number Diff line number Diff line
@@ -370,7 +370,7 @@ void tcp_delack_timer_handler(struct sock *sk); 
int tcp_ioctl(struct sock *sk, int cmd, int *karg);

enum skb_drop_reason tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb);

void tcp_rcv_established(struct sock *sk, struct sk_buff *skb);

void tcp_rcvbuf_grow(struct sock *sk);

void tcp_rcvbuf_grow(struct sock *sk, u32 newval);

void tcp_rcv_space_adjust(struct sock *sk);

int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp);

void tcp_twsk_destructor(struct sock *sk);

net/ipv4/tcp_input.c

+7 −7
Original line number Diff line number Diff line
@@ -891,18 +891,20 @@ static inline void tcp_rcv_rtt_measure_ts(struct sock *sk, 
	}

}



void tcp_rcvbuf_grow(struct sock *sk)

void tcp_rcvbuf_grow(struct sock *sk, u32 newval)

{

	const struct net *net = sock_net(sk);

	struct tcp_sock *tp = tcp_sk(sk);

	int rcvwin, rcvbuf, cap;

	u32 rcvwin, rcvbuf, cap;



	tp->rcvq_space.space = newval;



	if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) ||

	    (sk->sk_userlocks & SOCK_RCVBUF_LOCK))

		return;



	/* slow start: allow the sender to double its rate. */

	rcvwin = tp->rcvq_space.space << 1;

	rcvwin = newval << 1;



	if (!RB_EMPTY_ROOT(&tp->out_of_order_queue))

		rcvwin += TCP_SKB_CB(tp->ooo_last_skb)->end_seq - tp->rcv_nxt;
@@ -943,9 +945,7 @@ void tcp_rcv_space_adjust(struct sock *sk) 


	trace_tcp_rcvbuf_grow(sk, time);



	tp->rcvq_space.space = copied;



	tcp_rcvbuf_grow(sk);

	tcp_rcvbuf_grow(sk, copied);



new_measure:

	tp->rcvq_space.seq = tp->copied_seq;
@@ -5270,7 +5270,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) 
	}

	/* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */

	if (sk->sk_socket)

		tcp_rcvbuf_grow(sk);

		tcp_rcvbuf_grow(sk, tp->rcvq_space.space);

}



static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb,

net/mptcp/protocol.c

+8 −12
Original line number Diff line number Diff line
@@ -194,17 +194,18 @@ static bool mptcp_ooo_try_coalesce(struct mptcp_sock *msk, struct sk_buff *to, 
 * - mptcp does not maintain a msk-level window clamp

 * - returns true when  the receive buffer is actually updated

 */

static bool mptcp_rcvbuf_grow(struct sock *sk)

static bool mptcp_rcvbuf_grow(struct sock *sk, u32 newval)

{

	struct mptcp_sock *msk = mptcp_sk(sk);

	const struct net *net = sock_net(sk);

	int rcvwin, rcvbuf, cap;

	u32 rcvwin, rcvbuf, cap;



	msk->rcvq_space.space = newval;

	if (!READ_ONCE(net->ipv4.sysctl_tcp_moderate_rcvbuf) ||

	    (sk->sk_userlocks & SOCK_RCVBUF_LOCK))

		return false;



	rcvwin = msk->rcvq_space.space << 1;

	rcvwin = newval << 1;



	if (!RB_EMPTY_ROOT(&msk->out_of_order_queue))

		rcvwin += MPTCP_SKB_CB(msk->ooo_last_skb)->end_seq - msk->ack_seq;
@@ -334,7 +335,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb) 
	skb_set_owner_r(skb, sk);

	/* do not grow rcvbuf for not-yet-accepted or orphaned sockets. */

	if (sk->sk_socket)

		mptcp_rcvbuf_grow(sk);

		mptcp_rcvbuf_grow(sk, msk->rcvq_space.space);

}



static void mptcp_init_skb(struct sock *ssk, struct sk_buff *skb, int offset,
@@ -2049,10 +2050,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) 
	if (msk->rcvq_space.copied <= msk->rcvq_space.space)

		goto new_measure;



	msk->rcvq_space.space = msk->rcvq_space.copied;

	if (mptcp_rcvbuf_grow(sk)) {

		int copied = msk->rcvq_space.copied;



	if (mptcp_rcvbuf_grow(sk, msk->rcvq_space.copied)) {

		/* Make subflows follow along.  If we do not do this, we

		 * get drops at subflow level if skbs can't be moved to

		 * the mptcp rx queue fast enough (announced rcv_win can
@@ -2065,10 +2063,8 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) 
			ssk = mptcp_subflow_tcp_sock(subflow);

			slow = lock_sock_fast(ssk);

			/* subflows can be added before tcp_init_transfer() */

			if (tcp_sk(ssk)->rcvq_space.space) {

				tcp_sk(ssk)->rcvq_space.space = copied;

				tcp_rcvbuf_grow(ssk);

			}

			if (tcp_sk(ssk)->rcvq_space.space)

				tcp_rcvbuf_grow(ssk, msk->rcvq_space.copied);

			unlock_sock_fast(ssk, slow);

		}

	}