86 lines
2.9 KiB
Diff
86 lines
2.9 KiB
Diff
|
From: Eric Dumazet <edumazet@google.com>
|
|||
|
|
Date: Sat, 11 Nov 2017 15:54:12 -0800
|
|||
|
|
Subject: [PATCH] tcp: allow drivers to tweak TSQ logic
|
|||
|
|
MIME-Version: 1.0
|
|||
|
|
Content-Type: text/plain; charset=UTF-8
|
|||
|
|
Content-Transfer-Encoding: 8bit
|
|||
|
|
|
|||
|
|
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: Eric Dumazet <edumazet@google.com>
|
|||
|
|
Cc: Johannes Berg <johannes.berg@intel.com>
|
|||
|
|
Cc: Toke Høiland-Jørgensen <toke@toke.dk>
|
|||
|
|
Cc: Kir Kolyshkin <kir@openvz.org>
|
|||
|
|
---
|
|||
|
|
--- a/include/net/sock.h
|
|||
|
|
+++ b/include/net/sock.h
|
|||
|
|
@@ -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
|
|||
|
|
@@ -448,6 +449,8 @@ struct sock {
|
|||
|
|
kmemcheck_bitfield_end(flags);
|
|||
|
|
|
|||
|
|
u16 sk_gso_max_segs;
|
|||
|
|
+#define sk_pacing_shift sk_pacing_shift /* for backport checks */
|
|||
|
|
+ u8 sk_pacing_shift;
|
|||
|
|
unsigned long sk_lingertime;
|
|||
|
|
struct proto *sk_prot_creator;
|
|||
|
|
rwlock_t sk_callback_lock;
|
|||
|
|
--- a/net/core/sock.c
|
|||
|
|
+++ b/net/core/sock.c
|
|||
|
|
@@ -2744,6 +2744,7 @@ void sock_init_data(struct socket *sock,
|
|||
|
|
|
|||
|
|
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
|
|||
|
|
--- a/net/ipv4/tcp_output.c
|
|||
|
|
+++ b/net/ipv4/tcp_output.c
|
|||
|
|
@@ -1671,7 +1671,7 @@ u32 tcp_tso_autosize(const struct sock *
|
|||
|
|
{
|
|||
|
|
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,
|
|||
|
|
@@ -2145,7 +2145,7 @@ static bool tcp_small_queue_check(struct
|
|||
|
|
{
|
|||
|
|
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, sysctl_tcp_limit_output_bytes);
|
|||
|
|
limit <<= factor;
|
|||
|
|
|