Commit 85712484 authored by Mat Martineau's avatar Mat Martineau Committed by David S. Miller
Browse files

tcp: coalesce/collapse must respect MPTCP extensions 



Coalesce and collapse of packets carrying MPTCP extensions is allowed
when the newer packet has no extension or the extensions carried by both
packets are equal.

This allows merging of TSO packet trains and even cross-TSO packets, and
does not require any additional action when moving data into existing
SKBs.

v3 -> v4:
 - allow collapsing, under mptcp_skb_can_collapse() constraint

v5 -> v6:
 - clarify MPTCP skb extensions must always be cleared at allocation
   time

Co-developed-by: default avatarPaolo Abeni <pabeni@redhat.com>
Signed-off-by: default avatarPaolo Abeni <pabeni@redhat.com>
Signed-off-by: default avatarMat Martineau <mathew.j.martineau@linux.intel.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 3ee17bc7

include/net/mptcp.h

+57 −0
Original line number Diff line number Diff line
@@ -8,6 +8,7 @@ 
#ifndef __NET_MPTCP_H

#define __NET_MPTCP_H



#include <linux/skbuff.h>

#include <linux/types.h>



/* MPTCP sk_buff extension data */
@@ -25,4 +26,60 @@ struct mptcp_ext { 
	/* one byte hole */

};



#ifdef CONFIG_MPTCP



/* move the skb extension owership, with the assumption that 'to' is

 * newly allocated

 */

static inline void mptcp_skb_ext_move(struct sk_buff *to,

				      struct sk_buff *from)

{

	if (!skb_ext_exist(from, SKB_EXT_MPTCP))

		return;



	if (WARN_ON_ONCE(to->active_extensions))

		skb_ext_put(to);



	to->active_extensions = from->active_extensions;

	to->extensions = from->extensions;

	from->active_extensions = 0;

}



static inline bool mptcp_ext_matches(const struct mptcp_ext *to_ext,

				     const struct mptcp_ext *from_ext)

{

	/* MPTCP always clears the ext when adding it to the skb, so

	 * holes do not bother us here

	 */

	return !from_ext ||

	       (to_ext && from_ext &&

	        !memcmp(from_ext, to_ext, sizeof(struct mptcp_ext)));

}



/* check if skbs can be collapsed.

 * MPTCP collapse is allowed if neither @to or @from carry an mptcp data

 * mapping, or if the extension of @to is the same as @from.

 * Collapsing is not possible if @to lacks an extension, but @from carries one.

 */

static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,

					  const struct sk_buff *from)

{

	return mptcp_ext_matches(skb_ext_find(to, SKB_EXT_MPTCP),

				 skb_ext_find(from, SKB_EXT_MPTCP));

}



#else



static inline void mptcp_skb_ext_move(struct sk_buff *to,

				      const struct sk_buff *from)

{

}



static inline bool mptcp_skb_can_collapse(const struct sk_buff *to,

					  const struct sk_buff *from)

{

	return true;

}



#endif /* CONFIG_MPTCP */

#endif /* __NET_MPTCP_H */

include/net/tcp.h

+8 −0
Original line number Diff line number Diff line
@@ -39,6 +39,7 @@ 
#include <net/tcp_states.h>

#include <net/inet_ecn.h>

#include <net/dst.h>

#include <net/mptcp.h>



#include <linux/seq_file.h>

#include <linux/memcontrol.h>
@@ -978,6 +979,13 @@ static inline bool tcp_skb_can_collapse_to(const struct sk_buff *skb) 
	return likely(!TCP_SKB_CB(skb)->eor);

}



static inline bool tcp_skb_can_collapse(const struct sk_buff *to,

					const struct sk_buff *from)

{

	return likely(tcp_skb_can_collapse_to(to) &&

		      mptcp_skb_can_collapse(to, from));

}



/* Events passed to congestion control interface */

enum tcp_ca_event {

	CA_EVENT_TX_START,	/* first transmit when no packets in flight */

net/ipv4/tcp_input.c

+8 −3
Original line number Diff line number Diff line
@@ -1422,7 +1422,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, 
	if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)

		goto fallback;



	if (!tcp_skb_can_collapse_to(prev))

	if (!tcp_skb_can_collapse(prev, skb))

		goto fallback;



	in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
@@ -4423,6 +4423,9 @@ static bool tcp_try_coalesce(struct sock *sk, 
	if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)

		return false;



	if (!mptcp_skb_can_collapse(to, from))

		return false;



#ifdef CONFIG_TLS_DEVICE

	if (from->decrypted != to->decrypted)

		return false;
@@ -4932,7 +4935,7 @@ restart: 
		/* The first skb to collapse is:

		 * - not SYN/FIN and

		 * - bloated or contains data before "start" or

		 *   overlaps to the next one.

		 *   overlaps to the next one and mptcp allow collapsing.

		 */

		if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) &&

		    (tcp_win_from_space(sk, skb->truesize) > skb->len ||
@@ -4941,7 +4944,7 @@ restart: 
			break;

		}



		if (n && n != tail &&

		if (n && n != tail && mptcp_skb_can_collapse(skb, n) &&

		    TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) {

			end_of_skbs = false;

			break;
@@ -4974,6 +4977,7 @@ restart: 
		else

			__skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */

		skb_set_owner_r(nskb, sk);

		mptcp_skb_ext_move(nskb, skb);



		/* Copy data, releasing collapsed skbs. */

		while (copy > 0) {
@@ -4993,6 +4997,7 @@ restart: 
				skb = tcp_collapse_one(sk, skb, list, root);

				if (!skb ||

				    skb == tail ||

				    !mptcp_skb_can_collapse(nskb, skb) ||

				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))

					goto end;

#ifdef CONFIG_TLS_DEVICE

net/ipv4/tcp_output.c

+1 −1
Original line number Diff line number Diff line
@@ -2865,7 +2865,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, 
		if (!tcp_can_collapse(sk, skb))

			break;



		if (!tcp_skb_can_collapse_to(to))

		if (!tcp_skb_can_collapse(to, skb))

			break;



		space -= skb->len;

CRA Git | Maintained and supported by SUSTech CRA and CCSE