linux/include/net/request_sock.h
Eric Dumazet e6c022a4fa tcp: better retrans tracking for defer-accept
For passive TCP connections using TCP_DEFER_ACCEPT facility,
we incorrectly increment req->retrans each time timeout triggers
while no SYNACK is sent.

SYNACK are not sent for TCP_DEFER_ACCEPT that were established (for
which we received the ACK from client). Only the last SYNACK is sent
so that we can receive again an ACK from client, to move the req into
accept queue. We plan to change this later to avoid the useless
retransmit (and potential problem as this SYNACK could be lost)

TCP_INFO later gives wrong information to user, claiming imaginary
retransmits.

Decouple req->retrans field into two independent fields :

num_retrans : number of retransmit
num_timeout : number of timeouts

num_timeout is the counter that is incremented at each timeout,
regardless of actual SYNACK being sent or not, and used to
compute the exponential timeout.

Introduce inet_rtx_syn_ack() helper to increment num_retrans
only if ->rtx_syn_ack() succeeded.

Use inet_rtx_syn_ack() from tcp_check_req() to increment num_retrans
when we re-send a SYNACK in answer to a (retransmitted) SYN.
Prior to this patch, we were not counting these retransmits.

Change tcp_v[46]_rtx_synack() to increment TCP_MIB_RETRANSSEGS
only if a synack packet was successfully queued.

Reported-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Julian Anastasov <ja@ssi.bg>
Cc: Vijay Subramanian <subramanian.vijay@gmail.com>
Cc: Elliott Hughes <enh@google.com>
Cc: Neal Cardwell <ncardwell@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2012-11-03 14:45:00 -04:00

285 lines
8.1 KiB
C

/*
* NET Generic infrastructure for Network protocols.
*
* Definitions for request_sock
*
* Authors: Arnaldo Carvalho de Melo <acme@conectiva.com.br>
*
* From code originally in include/net/tcp.h
*
* 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 _REQUEST_SOCK_H
#define _REQUEST_SOCK_H
#include <linux/slab.h>
#include <linux/spinlock.h>
#include <linux/types.h>
#include <linux/bug.h>
#include <net/sock.h>
struct request_sock;
struct sk_buff;
struct dst_entry;
struct proto;
/* empty to "strongly type" an otherwise void parameter.
*/
struct request_values {
};
struct request_sock_ops {
int family;
int obj_size;
struct kmem_cache *slab;
char *slab_name;
int (*rtx_syn_ack)(struct sock *sk,
struct request_sock *req,
struct request_values *rvp);
void (*send_ack)(struct sock *sk, struct sk_buff *skb,
struct request_sock *req);
void (*send_reset)(struct sock *sk,
struct sk_buff *skb);
void (*destructor)(struct request_sock *req);
void (*syn_ack_timeout)(struct sock *sk,
struct request_sock *req);
};
extern int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req);
/* struct request_sock - mini sock to represent a connection request
*/
struct request_sock {
struct request_sock *dl_next; /* Must be first member! */
u16 mss;
u8 num_retrans; /* number of retransmits */
u8 cookie_ts:1; /* syncookie: encode tcpopts in timestamp */
u8 num_timeout:7; /* number of timeouts */
/* The following two fields can be easily recomputed I think -AK */
u32 window_clamp; /* window clamp at creation time */
u32 rcv_wnd; /* rcv_wnd offered first time */
u32 ts_recent;
unsigned long expires;
const struct request_sock_ops *rsk_ops;
struct sock *sk;
u32 secid;
u32 peer_secid;
};
static inline struct request_sock *reqsk_alloc(const struct request_sock_ops *ops)
{
struct request_sock *req = kmem_cache_alloc(ops->slab, GFP_ATOMIC);
if (req != NULL)
req->rsk_ops = ops;
return req;
}
static inline void __reqsk_free(struct request_sock *req)
{
kmem_cache_free(req->rsk_ops->slab, req);
}
static inline void reqsk_free(struct request_sock *req)
{
req->rsk_ops->destructor(req);
__reqsk_free(req);
}
extern int sysctl_max_syn_backlog;
/** struct listen_sock - listen state
*
* @max_qlen_log - log_2 of maximal queued SYNs/REQUESTs
*/
struct listen_sock {
u8 max_qlen_log;
u8 synflood_warned;
/* 2 bytes hole, try to use */
int qlen;
int qlen_young;
int clock_hand;
u32 hash_rnd;
u32 nr_table_entries;
struct request_sock *syn_table[0];
};
/*
* For a TCP Fast Open listener -
* lock - protects the access to all the reqsk, which is co-owned by
* the listener and the child socket.
* qlen - pending TFO requests (still in TCP_SYN_RECV).
* max_qlen - max TFO reqs allowed before TFO is disabled.
*
* XXX (TFO) - ideally these fields can be made as part of "listen_sock"
* structure above. But there is some implementation difficulty due to
* listen_sock being part of request_sock_queue hence will be freed when
* a listener is stopped. But TFO related fields may continue to be
* accessed even after a listener is closed, until its sk_refcnt drops
* to 0 implying no more outstanding TFO reqs. One solution is to keep
* listen_opt around until sk_refcnt drops to 0. But there is some other
* complexity that needs to be resolved. E.g., a listener can be disabled
* temporarily through shutdown()->tcp_disconnect(), and re-enabled later.
*/
struct fastopen_queue {
struct request_sock *rskq_rst_head; /* Keep track of past TFO */
struct request_sock *rskq_rst_tail; /* requests that caused RST.
* This is part of the defense
* against spoofing attack.
*/
spinlock_t lock;
int qlen; /* # of pending (TCP_SYN_RECV) reqs */
int max_qlen; /* != 0 iff TFO is currently enabled */
};
/** struct request_sock_queue - queue of request_socks
*
* @rskq_accept_head - FIFO head of established children
* @rskq_accept_tail - FIFO tail of established children
* @rskq_defer_accept - User waits for some data after accept()
* @syn_wait_lock - serializer
*
* %syn_wait_lock is necessary only to avoid proc interface having to grab the main
* lock sock while browsing the listening hash (otherwise it's deadlock prone).
*
* This lock is acquired in read mode only from listening_get_next() seq_file
* op and it's acquired in write mode _only_ from code that is actively
* changing rskq_accept_head. All readers that are holding the master sock lock
* don't need to grab this lock in read mode too as rskq_accept_head. writes
* are always protected from the main sock lock.
*/
struct request_sock_queue {
struct request_sock *rskq_accept_head;
struct request_sock *rskq_accept_tail;
rwlock_t syn_wait_lock;
u8 rskq_defer_accept;
/* 3 bytes hole, try to pack */
struct listen_sock *listen_opt;
struct fastopen_queue *fastopenq; /* This is non-NULL iff TFO has been
* enabled on this listener. Check
* max_qlen != 0 in fastopen_queue
* to determine if TFO is enabled
* right at this moment.
*/
};
extern int reqsk_queue_alloc(struct request_sock_queue *queue,
unsigned int nr_table_entries);
extern void __reqsk_queue_destroy(struct request_sock_queue *queue);
extern void reqsk_queue_destroy(struct request_sock_queue *queue);
extern void reqsk_fastopen_remove(struct sock *sk,
struct request_sock *req, bool reset);
static inline struct request_sock *
reqsk_queue_yank_acceptq(struct request_sock_queue *queue)
{
struct request_sock *req = queue->rskq_accept_head;
queue->rskq_accept_head = NULL;
return req;
}
static inline int reqsk_queue_empty(struct request_sock_queue *queue)
{
return queue->rskq_accept_head == NULL;
}
static inline void reqsk_queue_unlink(struct request_sock_queue *queue,
struct request_sock *req,
struct request_sock **prev_req)
{
write_lock(&queue->syn_wait_lock);
*prev_req = req->dl_next;
write_unlock(&queue->syn_wait_lock);
}
static inline void reqsk_queue_add(struct request_sock_queue *queue,
struct request_sock *req,
struct sock *parent,
struct sock *child)
{
req->sk = child;
sk_acceptq_added(parent);
if (queue->rskq_accept_head == NULL)
queue->rskq_accept_head = req;
else
queue->rskq_accept_tail->dl_next = req;
queue->rskq_accept_tail = req;
req->dl_next = NULL;
}
static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue)
{
struct request_sock *req = queue->rskq_accept_head;
WARN_ON(req == NULL);
queue->rskq_accept_head = req->dl_next;
if (queue->rskq_accept_head == NULL)
queue->rskq_accept_tail = NULL;
return req;
}
static inline int reqsk_queue_removed(struct request_sock_queue *queue,
struct request_sock *req)
{
struct listen_sock *lopt = queue->listen_opt;
if (req->num_timeout == 0)
--lopt->qlen_young;
return --lopt->qlen;
}
static inline int reqsk_queue_added(struct request_sock_queue *queue)
{
struct listen_sock *lopt = queue->listen_opt;
const int prev_qlen = lopt->qlen;
lopt->qlen_young++;
lopt->qlen++;
return prev_qlen;
}
static inline int reqsk_queue_len(const struct request_sock_queue *queue)
{
return queue->listen_opt != NULL ? queue->listen_opt->qlen : 0;
}
static inline int reqsk_queue_len_young(const struct request_sock_queue *queue)
{
return queue->listen_opt->qlen_young;
}
static inline int reqsk_queue_is_full(const struct request_sock_queue *queue)
{
return queue->listen_opt->qlen >> queue->listen_opt->max_qlen_log;
}
static inline void reqsk_queue_hash_req(struct request_sock_queue *queue,
u32 hash, struct request_sock *req,
unsigned long timeout)
{
struct listen_sock *lopt = queue->listen_opt;
req->expires = jiffies + timeout;
req->num_retrans = 0;
req->num_timeout = 0;
req->sk = NULL;
req->dl_next = lopt->syn_table[hash];
write_lock(&queue->syn_wait_lock);
lopt->syn_table[hash] = req;
write_unlock(&queue->syn_wait_lock);
}
#endif /* _REQUEST_SOCK_H */