Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit a624f93c authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'tcp-bbr' 



Neal Cardwell says:

====================
tcp: BBR congestion control algorithm

This patch series implements a new TCP congestion control algorithm:
BBR (Bottleneck Bandwidth and RTT). A paper with a detailed
description of BBR will be published in ACM Queue, September-October
2016, as "BBR: Congestion-Based Congestion Control". BBR is widely
deployed in production at Google.

The patch series starts with a set of supporting infrastructure
changes, including a few that extend the congestion control
framework. The last patch adds BBR as a TCP congestion control
module. Please see individual patches for the details.

- v3 -> v4:
 - Updated tcp_bbr.c in "tcp_bbr: add BBR congestion control"
   to use const to qualify all the constant parameters.
   Thanks to Stephen Hemminger.
 - In "tcp_bbr: add BBR congestion control", remove the bbr_rate_kbps()
   function, which had a 64-bit divide that would be problematic on some
   architectures, and just use bbr_rate_bytes_per_sec() directly.
   Thanks to Kenneth Klette Jonassen for suggesting this.
 - In "tcp: switch back to proper tcp_skb_cb size check in tcp_init()",
   switched from sizeof(skb->cb) to FIELD_SIZEOF.
   Thanks to Lance Richardson for suggesting this.
 - Updated "tcp_bbr: add BBR congestion control" commit message with
   performance data, more details about deployment at Google, and
   another reminder to use fq with BBR.
 - Updated tcp_bbr.c in "tcp_bbr: add BBR congestion control"
   to use MODULE_LICENSE("Dual BSD/GPL").

- v2 -> v3: fix another issue caught by build bots:
 - adjust rate_sample struct initialization syntax to allow gcc-4.4 to compile
   the "tcp: track data delivery rate for a TCP connection" patch; also
   adjusted some similar syntax in "tcp_bbr: add BBR congestion control"

- v1 -> v2: fix issues caught by build bots:
 - fix "tcp: export data delivery rate" to use rate64 instead of rate,
   so there is a 64-bit numerator for the do_div call
 - fix conflicting definitions for minmax caused by
   "tcp: use windowed min filter library for TCP min_rtt estimation"
   with a new commit:
   tcp: cdg: rename struct minmax in tcp_cdg.c to avoid a naming conflict
 - fix warning about the use of __packed in
   "tcp: track data delivery rate for a TCP connection",
   which involves the addition of a new commit:
   tcp: switch back to proper tcp_skb_cb size check in tcp_init()
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 94d308d0 0f8782ea

include/linux/tcp.h

+10 −4
Original line number Diff line number Diff line
@@ -19,6 +19,7 @@ 




#include <linux/skbuff.h>

#include <linux/win_minmax.h>

#include <net/sock.h>

#include <net/inet_connection_sock.h>

#include <net/inet_timewait_sock.h>
@@ -212,7 +213,8 @@ struct tcp_sock { 
		u8 reord;    /* reordering detected */

	} rack;

	u16	advmss;		/* Advertised MSS			*/

	u8	unused;

	u8	rate_app_limited:1,  /* rate_{delivered,interval_us} limited? */

		unused:7;

	u8	nonagle     : 4,/* Disable Nagle algorithm?             */

		thin_lto    : 1,/* Use linear timeouts for thin streams */

		thin_dupack : 1,/* Fast retransmit on first dupack      */
@@ -234,9 +236,7 @@ struct tcp_sock { 
	u32	mdev_max_us;	/* maximal mdev for the last rtt period	*/

	u32	rttvar_us;	/* smoothed mdev_max			*/

	u32	rtt_seq;	/* sequence number to update rttvar	*/

	struct rtt_meas {

		u32 rtt, ts;	/* RTT in usec and sampling time in jiffies. */

	} rtt_min[3];

	struct  minmax rtt_min;



	u32	packets_out;	/* Packets which are "in flight"	*/

	u32	retrans_out;	/* Retransmitted packets out		*/
@@ -268,6 +268,12 @@ struct tcp_sock { 
				 * receiver in Recovery. */

	u32	prr_out;	/* Total number of pkts sent during Recovery. */

	u32	delivered;	/* Total data packets delivered incl. rexmits */

	u32	lost;		/* Total data packets lost incl. rexmits */

	u32	app_limited;	/* limited until "delivered" reaches this val */

	struct skb_mstamp first_tx_mstamp;  /* start of window send phase */

	struct skb_mstamp delivered_mstamp; /* time we reached "delivered" */

	u32	rate_delivered;    /* saved rate sample: packets delivered */

	u32	rate_interval_us;  /* saved rate sample: time elapsed */



 	u32	rcv_wnd;	/* Current receiver window		*/

	u32	write_seq;	/* Tail(+1) of data held in tcp send buffer */

include/linux/win_minmax.h

0 → 100644
+37 −0
Original line number Diff line number Diff line 
/**

 * lib/minmax.c: windowed min/max tracker by Kathleen Nichols.

 *

 */

#ifndef MINMAX_H

#define MINMAX_H



#include <linux/types.h>



/* A single data point for our parameterized min-max tracker */

struct minmax_sample {

	u32	t;	/* time measurement was taken */

	u32	v;	/* value measured */

};



/* State for the parameterized min-max tracker */

struct minmax {

	struct minmax_sample s[3];

};



static inline u32 minmax_get(const struct minmax *m)

{

	return m->s[0].v;

}



static inline u32 minmax_reset(struct minmax *m, u32 t, u32 meas)

{

	struct minmax_sample val = { .t = t, .v = meas };



	m->s[2] = m->s[1] = m->s[0] = val;

	return m->s[0].v;

}



u32 minmax_running_max(struct minmax *m, u32 win, u32 t, u32 meas);

u32 minmax_running_min(struct minmax *m, u32 win, u32 t, u32 meas);



#endif

include/net/inet_connection_sock.h

+2 −2
Original line number Diff line number Diff line
@@ -134,8 +134,8 @@ struct inet_connection_sock { 
	} icsk_mtup;

	u32			  icsk_user_timeout;



	u64			  icsk_ca_priv[64 / sizeof(u64)];

#define ICSK_CA_PRIV_SIZE      (8 * sizeof(u64))

	u64			  icsk_ca_priv[88 / sizeof(u64)];

#define ICSK_CA_PRIV_SIZE      (11 * sizeof(u64))

};



#define ICSK_TIME_RETRANS	1	/* Retransmit timer */

include/net/tcp.h

+50 −3
Original line number Diff line number Diff line
@@ -533,6 +533,8 @@ __u32 cookie_v6_init_sequence(const struct sk_buff *skb, __u16 *mss); 
#endif

/* tcp_output.c */



u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now,

		     int min_tso_segs);

void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss,

			       int nonagle);

bool tcp_may_send_now(struct sock *sk);
@@ -671,7 +673,7 @@ static inline bool tcp_ca_dst_locked(const struct dst_entry *dst) 
/* Minimum RTT in usec. ~0 means not available. */

static inline u32 tcp_min_rtt(const struct tcp_sock *tp)

{

	return tp->rtt_min[0].rtt;

	return minmax_get(&tp->rtt_min);

}



/* Compute the actual receive window we are currently advertising.
@@ -763,8 +765,16 @@ struct tcp_skb_cb { 
	__u32		ack_seq;	/* Sequence number ACK'd	*/

	union {

		struct {

			/* There is space for up to 20 bytes */

			__u32 in_flight;/* Bytes in flight when packet sent */

			/* There is space for up to 24 bytes */

			__u32 in_flight:30,/* Bytes in flight at transmit */

			      is_app_limited:1, /* cwnd not fully used? */

			      unused:1;

			/* pkts S/ACKed so far upon tx of skb, incl retrans: */

			__u32 delivered;

			/* start of send pipeline phase */

			struct skb_mstamp first_tx_mstamp;

			/* when we reached the "delivered" count */

			struct skb_mstamp delivered_mstamp;

		} tx;   /* only used for outgoing skbs */

		union {

			struct inet_skb_parm	h4;
@@ -860,6 +870,27 @@ struct ack_sample { 
	u32 in_flight;

};



/* A rate sample measures the number of (original/retransmitted) data

 * packets delivered "delivered" over an interval of time "interval_us".

 * The tcp_rate.c code fills in the rate sample, and congestion

 * control modules that define a cong_control function to run at the end

 * of ACK processing can optionally chose to consult this sample when

 * setting cwnd and pacing rate.

 * A sample is invalid if "delivered" or "interval_us" is negative.

 */

struct rate_sample {

	struct	skb_mstamp prior_mstamp; /* starting timestamp for interval */

	u32  prior_delivered;	/* tp->delivered at "prior_mstamp" */

	s32  delivered;		/* number of packets delivered over interval */

	long interval_us;	/* time for tp->delivered to incr "delivered" */

	long rtt_us;		/* RTT of last (S)ACKed packet (or -1) */

	int  losses;		/* number of packets marked lost upon ACK */

	u32  acked_sacked;	/* number of packets newly (S)ACKed upon ACK */

	u32  prior_in_flight;	/* in flight before this ACK */

	bool is_app_limited;	/* is sample from packet with bubble in pipe? */

	bool is_retrans;	/* is sample from retransmission? */

};



struct tcp_congestion_ops {

	struct list_head	list;

	u32 key;
@@ -884,6 +915,14 @@ struct tcp_congestion_ops { 
	u32  (*undo_cwnd)(struct sock *sk);

	/* hook for packet ack accounting (optional) */

	void (*pkts_acked)(struct sock *sk, const struct ack_sample *sample);

	/* suggest number of segments for each skb to transmit (optional) */

	u32 (*tso_segs_goal)(struct sock *sk);

	/* returns the multiplier used in tcp_sndbuf_expand (optional) */

	u32 (*sndbuf_expand)(struct sock *sk);

	/* call when packets are delivered to update cwnd and pacing rate,

	 * after all the ca_state processing. (optional)

	 */

	void (*cong_control)(struct sock *sk, const struct rate_sample *rs);

	/* get info for inet_diag (optional) */

	size_t (*get_info)(struct sock *sk, u32 ext, int *attr,

			   union tcp_cc_info *info);
@@ -946,6 +985,14 @@ static inline void tcp_ca_event(struct sock *sk, const enum tcp_ca_event event) 
		icsk->icsk_ca_ops->cwnd_event(sk, event);

}



/* From tcp_rate.c */

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

void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,

			    struct rate_sample *rs);

void tcp_rate_gen(struct sock *sk, u32 delivered, u32 lost,

		  struct skb_mstamp *now, struct rate_sample *rs);

void tcp_rate_check_app_limited(struct sock *sk);



/* These functions determine how the current flow behaves in respect of SACK

 * handling. SACK is negotiated with the peer, and therefore it can vary

 * between different flows.

include/uapi/linux/inet_diag.h

+13 −0
Original line number Diff line number Diff line
@@ -124,6 +124,7 @@ enum { 
	INET_DIAG_PEERS,

	INET_DIAG_PAD,

	INET_DIAG_MARK,

	INET_DIAG_BBRINFO,

	__INET_DIAG_MAX,

};
@@ -157,8 +158,20 @@ struct tcp_dctcp_info { 
	__u32	dctcp_ab_tot;

};



/* INET_DIAG_BBRINFO */



struct tcp_bbr_info {

	/* u64 bw: max-filtered BW (app throughput) estimate in Byte per sec: */

	__u32	bbr_bw_lo;		/* lower 32 bits of bw */

	__u32	bbr_bw_hi;		/* upper 32 bits of bw */

	__u32	bbr_min_rtt;		/* min-filtered RTT in uSec */

	__u32	bbr_pacing_gain;	/* pacing gain shifted left 8 bits */

	__u32	bbr_cwnd_gain;		/* cwnd gain shifted left 8 bits */

};



union tcp_cc_info {

	struct tcpvegas_info	vegas;

	struct tcp_dctcp_info	dctcp;

	struct tcp_bbr_info	bbr;

};

#endif /* _UAPI_INET_DIAG_H_ */