mirror of
https://github.com/edk2-porting/linux-next.git
synced 2024-12-22 20:23:57 +08:00
78dc70ebaa
Aggregation effects are extremely common with wifi, cellular, and cable modem link technologies, ACK decimation in middleboxes, and LRO and GRO in receiving hosts. The aggregation can happen in either direction, data or ACKs, but in either case the aggregation effect is visible to the sender in the ACK stream. Previously BBR's sending was often limited by cwnd under severe ACK aggregation/decimation because BBR sized the cwnd at 2*BDP. If packets were acked in bursts after long delays (e.g. one ACK acking 5*BDP after 5*RTT), BBR's sending was halted after sending 2*BDP over 2*RTT, leaving the bottleneck idle for potentially long periods. Note that loss-based congestion control does not have this issue because when facing aggregation it continues increasing cwnd after bursts of ACKs, growing cwnd until the buffer is full. To achieve good throughput in the presence of aggregation effects, this algorithm allows the BBR sender to put extra data in flight to keep the bottleneck utilized during silences in the ACK stream that it has evidence to suggest were caused by aggregation. A summary of the algorithm: when a burst of packets are acked by a stretched ACK or a burst of ACKs or both, BBR first estimates the expected amount of data that should have been acked, based on its estimated bandwidth. Then the surplus ("extra_acked") is recorded in a windowed-max filter to estimate the recent level of observed ACK aggregation. Then cwnd is increased by the ACK aggregation estimate. The larger cwnd avoids BBR being cwnd-limited in the face of ACK silences that recent history suggests were caused by aggregation. As a sanity check, the ACK aggregation degree is upper-bounded by the cwnd (at the time of measurement) and a global max of BW * 100ms. The algorithm is further described by the following presentation: https://datatracker.ietf.org/meeting/101/materials/slides-101-iccrg-an-update-on-bbr-work-at-google-00 In our internal testing, we observed a significant increase in BBR throughput (measured using netperf), in a basic wifi setup. - Host1 (sender on ethernet) -> AP -> Host2 (receiver on wifi) - 2.4 GHz -> BBR before: ~73 Mbps; BBR after: ~102 Mbps; CUBIC: ~100 Mbps - 5.0 GHz -> BBR before: ~362 Mbps; BBR after: ~593 Mbps; CUBIC: ~601 Mbps Also, this code is running globally on YouTube TCP connections and produced significant bandwidth increases for YouTube traffic. This is based on Ian Swett's max_ack_height_ algorithm from the QUIC BBR implementation. Signed-off-by: Priyaranjan Jha <priyarjha@google.com> Signed-off-by: Neal Cardwell <ncardwell@google.com> Signed-off-by: Yuchung Cheng <ycheng@google.com> Signed-off-by: David S. Miller <davem@davemloft.net>
318 lines
10 KiB
C
318 lines
10 KiB
C
/*
|
|
* NET Generic infrastructure for INET connection oriented protocols.
|
|
*
|
|
* Definitions for inet_connection_sock
|
|
*
|
|
* Authors: Many people, see the TCP sources
|
|
*
|
|
* From code originally in TCP
|
|
*
|
|
* This program is free software; you can redistribute it and/or
|
|
* modify it under the terms of the GNU General Public License
|
|
* as published by the Free Software Foundation; either version
|
|
* 2 of the License, or (at your option) any later version.
|
|
*/
|
|
#ifndef _INET_CONNECTION_SOCK_H
|
|
#define _INET_CONNECTION_SOCK_H
|
|
|
|
#include <linux/compiler.h>
|
|
#include <linux/string.h>
|
|
#include <linux/timer.h>
|
|
#include <linux/poll.h>
|
|
#include <linux/kernel.h>
|
|
|
|
#include <net/inet_sock.h>
|
|
#include <net/request_sock.h>
|
|
|
|
/* Cancel timers, when they are not required. */
|
|
#undef INET_CSK_CLEAR_TIMERS
|
|
|
|
struct inet_bind_bucket;
|
|
struct tcp_congestion_ops;
|
|
|
|
/*
|
|
* Pointers to address related TCP functions
|
|
* (i.e. things that depend on the address family)
|
|
*/
|
|
struct inet_connection_sock_af_ops {
|
|
int (*queue_xmit)(struct sock *sk, struct sk_buff *skb, struct flowi *fl);
|
|
void (*send_check)(struct sock *sk, struct sk_buff *skb);
|
|
int (*rebuild_header)(struct sock *sk);
|
|
void (*sk_rx_dst_set)(struct sock *sk, const struct sk_buff *skb);
|
|
int (*conn_request)(struct sock *sk, struct sk_buff *skb);
|
|
struct sock *(*syn_recv_sock)(const struct sock *sk, struct sk_buff *skb,
|
|
struct request_sock *req,
|
|
struct dst_entry *dst,
|
|
struct request_sock *req_unhash,
|
|
bool *own_req);
|
|
u16 net_header_len;
|
|
u16 net_frag_header_len;
|
|
u16 sockaddr_len;
|
|
int (*setsockopt)(struct sock *sk, int level, int optname,
|
|
char __user *optval, unsigned int optlen);
|
|
int (*getsockopt)(struct sock *sk, int level, int optname,
|
|
char __user *optval, int __user *optlen);
|
|
#ifdef CONFIG_COMPAT
|
|
int (*compat_setsockopt)(struct sock *sk,
|
|
int level, int optname,
|
|
char __user *optval, unsigned int optlen);
|
|
int (*compat_getsockopt)(struct sock *sk,
|
|
int level, int optname,
|
|
char __user *optval, int __user *optlen);
|
|
#endif
|
|
void (*addr2sockaddr)(struct sock *sk, struct sockaddr *);
|
|
void (*mtu_reduced)(struct sock *sk);
|
|
};
|
|
|
|
/** inet_connection_sock - INET connection oriented sock
|
|
*
|
|
* @icsk_accept_queue: FIFO of established children
|
|
* @icsk_bind_hash: Bind node
|
|
* @icsk_timeout: Timeout
|
|
* @icsk_retransmit_timer: Resend (no ack)
|
|
* @icsk_rto: Retransmit timeout
|
|
* @icsk_pmtu_cookie Last pmtu seen by socket
|
|
* @icsk_ca_ops Pluggable congestion control hook
|
|
* @icsk_af_ops Operations which are AF_INET{4,6} specific
|
|
* @icsk_ulp_ops Pluggable ULP control hook
|
|
* @icsk_ulp_data ULP private data
|
|
* @icsk_clean_acked Clean acked data hook
|
|
* @icsk_listen_portaddr_node hash to the portaddr listener hashtable
|
|
* @icsk_ca_state: Congestion control state
|
|
* @icsk_retransmits: Number of unrecovered [RTO] timeouts
|
|
* @icsk_pending: Scheduled timer event
|
|
* @icsk_backoff: Backoff
|
|
* @icsk_syn_retries: Number of allowed SYN (or equivalent) retries
|
|
* @icsk_probes_out: unanswered 0 window probes
|
|
* @icsk_ext_hdr_len: Network protocol overhead (IP/IPv6 options)
|
|
* @icsk_ack: Delayed ACK control data
|
|
* @icsk_mtup; MTU probing control data
|
|
*/
|
|
struct inet_connection_sock {
|
|
/* inet_sock has to be the first member! */
|
|
struct inet_sock icsk_inet;
|
|
struct request_sock_queue icsk_accept_queue;
|
|
struct inet_bind_bucket *icsk_bind_hash;
|
|
unsigned long icsk_timeout;
|
|
struct timer_list icsk_retransmit_timer;
|
|
struct timer_list icsk_delack_timer;
|
|
__u32 icsk_rto;
|
|
__u32 icsk_pmtu_cookie;
|
|
const struct tcp_congestion_ops *icsk_ca_ops;
|
|
const struct inet_connection_sock_af_ops *icsk_af_ops;
|
|
const struct tcp_ulp_ops *icsk_ulp_ops;
|
|
void *icsk_ulp_data;
|
|
void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq);
|
|
struct hlist_node icsk_listen_portaddr_node;
|
|
unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
|
|
__u8 icsk_ca_state:6,
|
|
icsk_ca_setsockopt:1,
|
|
icsk_ca_dst_locked:1;
|
|
__u8 icsk_retransmits;
|
|
__u8 icsk_pending;
|
|
__u8 icsk_backoff;
|
|
__u8 icsk_syn_retries;
|
|
__u8 icsk_probes_out;
|
|
__u16 icsk_ext_hdr_len;
|
|
struct {
|
|
__u8 pending; /* ACK is pending */
|
|
__u8 quick; /* Scheduled number of quick acks */
|
|
__u8 pingpong; /* The session is interactive */
|
|
__u8 blocked; /* Delayed ACK was blocked by socket lock */
|
|
__u32 ato; /* Predicted tick of soft clock */
|
|
unsigned long timeout; /* Currently scheduled timeout */
|
|
__u32 lrcvtime; /* timestamp of last received data packet */
|
|
__u16 last_seg_size; /* Size of last incoming segment */
|
|
__u16 rcv_mss; /* MSS used for delayed ACK decisions */
|
|
} icsk_ack;
|
|
struct {
|
|
int enabled;
|
|
|
|
/* Range of MTUs to search */
|
|
int search_high;
|
|
int search_low;
|
|
|
|
/* Information on the current probe. */
|
|
int probe_size;
|
|
|
|
u32 probe_timestamp;
|
|
} icsk_mtup;
|
|
u32 icsk_user_timeout;
|
|
|
|
u64 icsk_ca_priv[104 / sizeof(u64)];
|
|
#define ICSK_CA_PRIV_SIZE (13 * sizeof(u64))
|
|
};
|
|
|
|
#define ICSK_TIME_RETRANS 1 /* Retransmit timer */
|
|
#define ICSK_TIME_DACK 2 /* Delayed ack timer */
|
|
#define ICSK_TIME_PROBE0 3 /* Zero window probe timer */
|
|
#define ICSK_TIME_EARLY_RETRANS 4 /* Early retransmit timer */
|
|
#define ICSK_TIME_LOSS_PROBE 5 /* Tail loss probe timer */
|
|
#define ICSK_TIME_REO_TIMEOUT 6 /* Reordering timer */
|
|
|
|
static inline struct inet_connection_sock *inet_csk(const struct sock *sk)
|
|
{
|
|
return (struct inet_connection_sock *)sk;
|
|
}
|
|
|
|
static inline void *inet_csk_ca(const struct sock *sk)
|
|
{
|
|
return (void *)inet_csk(sk)->icsk_ca_priv;
|
|
}
|
|
|
|
struct sock *inet_csk_clone_lock(const struct sock *sk,
|
|
const struct request_sock *req,
|
|
const gfp_t priority);
|
|
|
|
enum inet_csk_ack_state_t {
|
|
ICSK_ACK_SCHED = 1,
|
|
ICSK_ACK_TIMER = 2,
|
|
ICSK_ACK_PUSHED = 4,
|
|
ICSK_ACK_PUSHED2 = 8,
|
|
ICSK_ACK_NOW = 16 /* Send the next ACK immediately (once) */
|
|
};
|
|
|
|
void inet_csk_init_xmit_timers(struct sock *sk,
|
|
void (*retransmit_handler)(struct timer_list *),
|
|
void (*delack_handler)(struct timer_list *),
|
|
void (*keepalive_handler)(struct timer_list *));
|
|
void inet_csk_clear_xmit_timers(struct sock *sk);
|
|
|
|
static inline void inet_csk_schedule_ack(struct sock *sk)
|
|
{
|
|
inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_SCHED;
|
|
}
|
|
|
|
static inline int inet_csk_ack_scheduled(const struct sock *sk)
|
|
{
|
|
return inet_csk(sk)->icsk_ack.pending & ICSK_ACK_SCHED;
|
|
}
|
|
|
|
static inline void inet_csk_delack_init(struct sock *sk)
|
|
{
|
|
memset(&inet_csk(sk)->icsk_ack, 0, sizeof(inet_csk(sk)->icsk_ack));
|
|
}
|
|
|
|
void inet_csk_delete_keepalive_timer(struct sock *sk);
|
|
void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
|
|
|
|
static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what)
|
|
{
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
|
|
|
if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
|
|
icsk->icsk_pending = 0;
|
|
#ifdef INET_CSK_CLEAR_TIMERS
|
|
sk_stop_timer(sk, &icsk->icsk_retransmit_timer);
|
|
#endif
|
|
} else if (what == ICSK_TIME_DACK) {
|
|
icsk->icsk_ack.blocked = icsk->icsk_ack.pending = 0;
|
|
#ifdef INET_CSK_CLEAR_TIMERS
|
|
sk_stop_timer(sk, &icsk->icsk_delack_timer);
|
|
#endif
|
|
} else {
|
|
pr_debug("inet_csk BUG: unknown timer value\n");
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Reset the retransmission timer
|
|
*/
|
|
static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what,
|
|
unsigned long when,
|
|
const unsigned long max_when)
|
|
{
|
|
struct inet_connection_sock *icsk = inet_csk(sk);
|
|
|
|
if (when > max_when) {
|
|
pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n",
|
|
sk, what, when, (void *)_THIS_IP_);
|
|
when = max_when;
|
|
}
|
|
|
|
if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0 ||
|
|
what == ICSK_TIME_EARLY_RETRANS || what == ICSK_TIME_LOSS_PROBE ||
|
|
what == ICSK_TIME_REO_TIMEOUT) {
|
|
icsk->icsk_pending = what;
|
|
icsk->icsk_timeout = jiffies + when;
|
|
sk_reset_timer(sk, &icsk->icsk_retransmit_timer, icsk->icsk_timeout);
|
|
} else if (what == ICSK_TIME_DACK) {
|
|
icsk->icsk_ack.pending |= ICSK_ACK_TIMER;
|
|
icsk->icsk_ack.timeout = jiffies + when;
|
|
sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout);
|
|
} else {
|
|
pr_debug("inet_csk BUG: unknown timer value\n");
|
|
}
|
|
}
|
|
|
|
static inline unsigned long
|
|
inet_csk_rto_backoff(const struct inet_connection_sock *icsk,
|
|
unsigned long max_when)
|
|
{
|
|
u64 when = (u64)icsk->icsk_rto << icsk->icsk_backoff;
|
|
|
|
return (unsigned long)min_t(u64, when, max_when);
|
|
}
|
|
|
|
struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern);
|
|
|
|
int inet_csk_get_port(struct sock *sk, unsigned short snum);
|
|
|
|
struct dst_entry *inet_csk_route_req(const struct sock *sk, struct flowi4 *fl4,
|
|
const struct request_sock *req);
|
|
struct dst_entry *inet_csk_route_child_sock(const struct sock *sk,
|
|
struct sock *newsk,
|
|
const struct request_sock *req);
|
|
|
|
struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
|
|
struct request_sock *req,
|
|
struct sock *child);
|
|
void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
|
|
unsigned long timeout);
|
|
struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
|
|
struct request_sock *req,
|
|
bool own_req);
|
|
|
|
static inline void inet_csk_reqsk_queue_added(struct sock *sk)
|
|
{
|
|
reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue);
|
|
}
|
|
|
|
static inline int inet_csk_reqsk_queue_len(const struct sock *sk)
|
|
{
|
|
return reqsk_queue_len(&inet_csk(sk)->icsk_accept_queue);
|
|
}
|
|
|
|
static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
|
|
{
|
|
return inet_csk_reqsk_queue_len(sk) >= sk->sk_max_ack_backlog;
|
|
}
|
|
|
|
void inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
|
|
void inet_csk_reqsk_queue_drop_and_put(struct sock *sk, struct request_sock *req);
|
|
|
|
void inet_csk_destroy_sock(struct sock *sk);
|
|
void inet_csk_prepare_forced_close(struct sock *sk);
|
|
|
|
/*
|
|
* LISTEN is a special case for poll..
|
|
*/
|
|
static inline __poll_t inet_csk_listen_poll(const struct sock *sk)
|
|
{
|
|
return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ?
|
|
(EPOLLIN | EPOLLRDNORM) : 0;
|
|
}
|
|
|
|
int inet_csk_listen_start(struct sock *sk, int backlog);
|
|
void inet_csk_listen_stop(struct sock *sk);
|
|
|
|
void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
|
|
|
|
int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
|
|
char __user *optval, int __user *optlen);
|
|
int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
|
|
char __user *optval, unsigned int optlen);
|
|
|
|
struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu);
|
|
#endif /* _INET_CONNECTION_SOCK_H */
|