Commit 3a9b76fd authored by Eric Dumazet's avatar Eric Dumazet Committed by David S. Miller
Browse files

tcp: allow drivers to tweak TSQ logic 

I had many reports that TSQ logic breaks wifi aggregation.

Current logic is to allow up to 1 ms of bytes to be queued into qdisc
and drivers queues.

But Wifi aggregation needs a bigger budget to allow bigger rates to
be discovered by various TCP Congestion Controls algorithms.

This patch adds an extra socket field, allowing wifi drivers to select
another log scale to derive TCP Small Queue credit from current pacing
rate.

Initial value is 10, meaning that this patch does not change current
behavior.

We expect wifi drivers to set this field to smaller values (tests have
been done with values from 6 to 9)

They would have to use following template :

if (skb->sk && skb->sk->sk_pacing_shift != MY_PACING_SHIFT)
     skb->sk->sk_pacing_shift = MY_PACING_SHIFT;

Ref: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/1670041


Signed-off-by: default avatarEric Dumazet <edumazet@google.com>
Cc: Johannes Berg <johannes.berg@intel.com>
Cc: Toke Høiland-Jørgensen <toke@toke.dk>
Cc: Kir Kolyshkin <kir@openvz.org>
Acked-by: default avatarNeal Cardwell <ncardwell@google.com>
Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parent 166c8818

include/net/sock.h

+2 −0
Original line number Diff line number Diff line
@@ -267,6 +267,7 @@ struct sock_common { 
  *	@sk_gso_type: GSO type (e.g. %SKB_GSO_TCPV4)

  *	@sk_gso_max_size: Maximum GSO segment size to build

  *	@sk_gso_max_segs: Maximum number of GSO segments

  *	@sk_pacing_shift: scaling factor for TCP Small Queues

  *	@sk_lingertime: %SO_LINGER l_linger setting

  *	@sk_backlog: always used with the per-socket spinlock held

  *	@sk_callback_lock: used with the callbacks in the end of this struct
@@ -451,6 +452,7 @@ struct sock { 
	kmemcheck_bitfield_end(flags);



	u16			sk_gso_max_segs;

	u8			sk_pacing_shift;

	unsigned long	        sk_lingertime;

	struct proto		*sk_prot_creator;

	rwlock_t		sk_callback_lock;

net/core/sock.c

+1 −0
Original line number Diff line number Diff line
@@ -2746,6 +2746,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) 


	sk->sk_max_pacing_rate = ~0U;

	sk->sk_pacing_rate = ~0U;

	sk->sk_pacing_shift = 10;

	sk->sk_incoming_cpu = -1;

	/*

	 * Before updating sk_refcnt, we must commit prior changes to memory

net/ipv4/tcp_output.c

+2 −2
Original line number Diff line number Diff line
@@ -1720,7 +1720,7 @@ u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, 
{

	u32 bytes, segs;



	bytes = min(sk->sk_pacing_rate >> 10,

	bytes = min(sk->sk_pacing_rate >> sk->sk_pacing_shift,

		    sk->sk_gso_max_size - 1 - MAX_TCP_HEADER);



	/* Goal is to send at least one packet per ms,
@@ -2198,7 +2198,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, 
{

	unsigned int limit;



	limit = max(2 * skb->truesize, sk->sk_pacing_rate >> 10);

	limit = max(2 * skb->truesize, sk->sk_pacing_rate >> sk->sk_pacing_shift);

	limit = min_t(u32, limit,

		      sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);

	limit <<= factor;

CRA Git | Maintained and supported by SUSTech CRA and CCSE