kernel-ark/include/net/inet_connection_sock.h
Eric Dumazet 6746960140 ipv6: RTAX_FEATURE_ALLFRAG causes inefficient TCP segment sizing
Quoting Tore Anderson from :
https://bugzilla.kernel.org/show_bug.cgi?id=42572

When RTAX_FEATURE_ALLFRAG is set on a route, the effective TCP segment
size does not take into account the size of the IPv6 Fragmentation
header that needs to be included in outbound packets, causing every
transmitted TCP segment to be fragmented across two IPv6 packets, the
latter of which will only contain 8 bytes of actual payload.

RTAX_FEATURE_ALLFRAG is typically set on a route in response to
receving a ICMPv6 Packet Too Big message indicating a Path MTU of less
than 1280 bytes. 1280 bytes is the minimum IPv6 MTU, however ICMPv6
PTBs with MTU < 1280 are still valid, in particular when an IPv6
packet is sent to an IPv4 destination through a stateless translator.
Any ICMPv4 Need To Fragment packets originated from the IPv4 part of
the path will be translated to ICMPv6 PTB which may then indicate an
MTU of less than 1280.

The Linux kernel refuses to reduce the effective MTU to anything below
1280 bytes, instead it sets it to exactly 1280 bytes, and
RTAX_FEATURE_ALLFRAG is also set. However, the TCP segment size appears
to be set to 1240 bytes (1280 Path MTU - 40 bytes of IPv6 header),
instead of 1232 (additionally taking into account the 8 bytes required
by the IPv6 Fragmentation extension header).

This in turn results in rather inefficient transmission, as every
transmitted TCP segment now is split in two fragments containing
1232+8 bytes of payload.

After this patch, all the outgoing packets that includes a
Fragmentation header all are "atomic" or "non-fragmented" fragments,
i.e., they both have Offset=0 and More Fragments=0.

With help from David S. Miller

Reported-by: Tore Anderson <tore@fud.no>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Maciej Żenczykowski <maze@google.com>
Cc: Tom Herbert <therbert@google.com>
Tested-by: Tore Anderson <tore@fud.no>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-04-27 00:03:34 -04:00

341 lines
11 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 <net/inet_sock.h>
#include <net/request_sock.h>
#define INET_CSK_DEBUG 1
/* 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 sk_buff *skb, struct flowi *fl);
void (*send_check)(struct sock *sk, struct sk_buff *skb);
int (*rebuild_header)(struct sock *sk);
int (*conn_request)(struct sock *sk, struct sk_buff *skb);
struct sock *(*syn_recv_sock)(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct dst_entry *dst);
struct inet_peer *(*get_peer)(struct sock *sk, bool *release_it);
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 *);
int (*bind_conflict)(const struct sock *sk,
const struct inet_bind_bucket *tb, bool relax);
};
/** 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_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;
unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu);
__u8 icsk_ca_state;
__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;
} icsk_mtup;
u32 icsk_ca_priv[16];
u32 icsk_user_timeout;
#define ICSK_CA_PRIV_SIZE (16 * sizeof(u32))
};
#define ICSK_TIME_RETRANS 1 /* Retransmit timer */
#define ICSK_TIME_DACK 2 /* Delayed ack timer */
#define ICSK_TIME_PROBE0 3 /* Zero window probe 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;
}
extern 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
};
extern void inet_csk_init_xmit_timers(struct sock *sk,
void (*retransmit_handler)(unsigned long),
void (*delack_handler)(unsigned long),
void (*keepalive_handler)(unsigned long));
extern 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));
}
extern void inet_csk_delete_keepalive_timer(struct sock *sk);
extern void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout);
#ifdef INET_CSK_DEBUG
extern const char inet_csk_timer_bug_msg[];
#endif
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
}
#ifdef INET_CSK_DEBUG
else {
pr_debug("%s", inet_csk_timer_bug_msg);
}
#endif
}
/*
* 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) {
#ifdef INET_CSK_DEBUG
pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n",
sk, what, when, current_text_addr());
#endif
when = max_when;
}
if (what == ICSK_TIME_RETRANS || what == ICSK_TIME_PROBE0) {
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);
}
#ifdef INET_CSK_DEBUG
else {
pr_debug("%s", inet_csk_timer_bug_msg);
}
#endif
}
extern struct sock *inet_csk_accept(struct sock *sk, int flags, int *err);
extern struct request_sock *inet_csk_search_req(const struct sock *sk,
struct request_sock ***prevp,
const __be16 rport,
const __be32 raddr,
const __be32 laddr);
extern int inet_csk_bind_conflict(const struct sock *sk,
const struct inet_bind_bucket *tb, bool relax);
extern int inet_csk_get_port(struct sock *sk, unsigned short snum);
extern struct dst_entry* inet_csk_route_req(struct sock *sk,
struct flowi4 *fl4,
const struct request_sock *req);
extern struct dst_entry* inet_csk_route_child_sock(struct sock *sk,
struct sock *newsk,
const struct request_sock *req);
static inline void inet_csk_reqsk_queue_add(struct sock *sk,
struct request_sock *req,
struct sock *child)
{
reqsk_queue_add(&inet_csk(sk)->icsk_accept_queue, req, sk, child);
}
extern void inet_csk_reqsk_queue_hash_add(struct sock *sk,
struct request_sock *req,
unsigned long timeout);
static inline void inet_csk_reqsk_queue_removed(struct sock *sk,
struct request_sock *req)
{
if (reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req) == 0)
inet_csk_delete_keepalive_timer(sk);
}
static inline void inet_csk_reqsk_queue_added(struct sock *sk,
const unsigned long timeout)
{
if (reqsk_queue_added(&inet_csk(sk)->icsk_accept_queue) == 0)
inet_csk_reset_keepalive_timer(sk, timeout);
}
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_young(const struct sock *sk)
{
return reqsk_queue_len_young(&inet_csk(sk)->icsk_accept_queue);
}
static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
{
return reqsk_queue_is_full(&inet_csk(sk)->icsk_accept_queue);
}
static inline void inet_csk_reqsk_queue_unlink(struct sock *sk,
struct request_sock *req,
struct request_sock **prev)
{
reqsk_queue_unlink(&inet_csk(sk)->icsk_accept_queue, req, prev);
}
static inline void inet_csk_reqsk_queue_drop(struct sock *sk,
struct request_sock *req,
struct request_sock **prev)
{
inet_csk_reqsk_queue_unlink(sk, req, prev);
inet_csk_reqsk_queue_removed(sk, req);
reqsk_free(req);
}
extern void inet_csk_reqsk_queue_prune(struct sock *parent,
const unsigned long interval,
const unsigned long timeout,
const unsigned long max_rto);
extern void inet_csk_destroy_sock(struct sock *sk);
/*
* LISTEN is a special case for poll..
*/
static inline unsigned int inet_csk_listen_poll(const struct sock *sk)
{
return !reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue) ?
(POLLIN | POLLRDNORM) : 0;
}
extern int inet_csk_listen_start(struct sock *sk, const int nr_table_entries);
extern void inet_csk_listen_stop(struct sock *sk);
extern void inet_csk_addr2sockaddr(struct sock *sk, struct sockaddr *uaddr);
extern int inet_csk_compat_getsockopt(struct sock *sk, int level, int optname,
char __user *optval, int __user *optlen);
extern int inet_csk_compat_setsockopt(struct sock *sk, int level, int optname,
char __user *optval, unsigned int optlen);
#endif /* _INET_CONNECTION_SOCK_H */