forked from Minki/linux
4dfc281702
Allow the use of SACK and window scaling when syncookies are used and the client supports tcp timestamps. Options are encoded into the timestamp sent in the syn-ack and restored from the timestamp echo when the ack is received. Based on earlier work by Glenn Griffin. This patch avoids increasing the size of structs by encoding TCP options into the least significant bits of the timestamp and by not using any 'timestamp offset'. The downside is that the timestamp sent in the packet after the synack will increase by several seconds. changes since v1: don't duplicate timestamp echo decoding function, put it into ipv4/syncookie.c and have ipv6/syncookies.c use it. Feedback from Glenn Griffin: fix line indented with spaces, kill redundant if () Reviewed-by: Hagen Paul Pfeifer <hagen@jauu.net> Signed-off-by: Florian Westphal <fw@strlen.de> Signed-off-by: David S. Miller <davem@davemloft.net>
248 lines
6.4 KiB
C
248 lines
6.4 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 <net/sock.h>
|
|
|
|
struct request_sock;
|
|
struct sk_buff;
|
|
struct dst_entry;
|
|
struct proto;
|
|
|
|
struct request_sock_ops {
|
|
int family;
|
|
int obj_size;
|
|
struct kmem_cache *slab;
|
|
int (*rtx_syn_ack)(struct sock *sk,
|
|
struct request_sock *req);
|
|
void (*send_ack)(struct sk_buff *skb,
|
|
struct request_sock *req);
|
|
void (*send_reset)(struct sock *sk,
|
|
struct sk_buff *skb);
|
|
void (*destructor)(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 retrans;
|
|
u8 cookie_ts; /* syncookie: encode tcpopts in timestamp */
|
|
/* 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;
|
|
/* 3 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];
|
|
};
|
|
|
|
/** 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;
|
|
u16 rskq_defer_accept;
|
|
/* 2 bytes hole, try to pack */
|
|
struct listen_sock *listen_opt;
|
|
};
|
|
|
|
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);
|
|
|
|
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;
|
|
|
|
BUG_TRAP(req != NULL);
|
|
|
|
queue->rskq_accept_head = req->dl_next;
|
|
if (queue->rskq_accept_head == NULL)
|
|
queue->rskq_accept_tail = NULL;
|
|
|
|
return req;
|
|
}
|
|
|
|
static inline struct sock *reqsk_queue_get_child(struct request_sock_queue *queue,
|
|
struct sock *parent)
|
|
{
|
|
struct request_sock *req = reqsk_queue_remove(queue);
|
|
struct sock *child = req->sk;
|
|
|
|
BUG_TRAP(child != NULL);
|
|
|
|
sk_acceptq_removed(parent);
|
|
__reqsk_free(req);
|
|
return child;
|
|
}
|
|
|
|
static inline int reqsk_queue_removed(struct request_sock_queue *queue,
|
|
struct request_sock *req)
|
|
{
|
|
struct listen_sock *lopt = queue->listen_opt;
|
|
|
|
if (req->retrans == 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->retrans = 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 */
|