OpenCloudOS-Kernel/include/net/request_sock.h

228 lines
6.3 KiB
C
Raw Normal View History

/*
* 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;
struct request_sock_ops {
int family;
int obj_size;
struct kmem_cache *slab;
char *slab_name;
int (*rtx_syn_ack)(const struct sock *sk,
struct request_sock *req);
void (*send_ack)(const struct sock *sk, struct sk_buff *skb,
struct request_sock *req);
void (*send_reset)(const struct sock *sk,
struct sk_buff *skb);
void (*destructor)(struct request_sock *req);
void (*syn_ack_timeout)(const struct request_sock *req);
};
int inet_rtx_syn_ack(const struct sock *parent, struct request_sock *req);
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>
2012-10-28 07:16:46 +08:00
/* struct request_sock - mini sock to represent a connection request
*/
struct request_sock {
struct sock_common __req_common;
#define rsk_refcnt __req_common.skc_refcnt
#define rsk_hash __req_common.skc_hash
#define rsk_listener __req_common.skc_listener
#define rsk_window_clamp __req_common.skc_window_clamp
#define rsk_rcv_wnd __req_common.skc_rcv_wnd
struct request_sock *dl_next;
u16 mss;
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>
2012-10-28 07:16:46 +08:00
u8 num_retrans; /* number of retransmits */
u8 cookie_ts:1; /* syncookie: encode tcpopts in timestamp */
u8 num_timeout:7; /* number of timeouts */
u32 ts_recent;
struct timer_list rsk_timer;
const struct request_sock_ops *rsk_ops;
struct sock *sk;
u32 *saved_syn;
u32 secid;
u32 peer_secid;
};
static inline struct request_sock *inet_reqsk(const struct sock *sk)
{
return (struct request_sock *)sk;
}
static inline struct sock *req_to_sk(struct request_sock *req)
{
return (struct sock *)req;
}
static inline struct request_sock *
reqsk_alloc(const struct request_sock_ops *ops, struct sock *sk_listener,
bool attach_listener)
{
struct request_sock *req;
req = kmem_cache_alloc(ops->slab, GFP_ATOMIC | __GFP_NOWARN);
if (!req)
return NULL;
req->rsk_listener = NULL;
if (attach_listener) {
if (unlikely(!atomic_inc_not_zero(&sk_listener->sk_refcnt))) {
kmem_cache_free(ops->slab, req);
return NULL;
}
req->rsk_listener = sk_listener;
}
req->rsk_ops = ops;
req_to_sk(req)->sk_prot = sk_listener->sk_prot;
sk_node_init(&req_to_sk(req)->sk_node);
sk_tx_queue_clear(req_to_sk(req));
req->saved_syn = NULL;
atomic_set(&req->rsk_refcnt, 0);
return req;
}
static inline void reqsk_free(struct request_sock *req)
{
/* temporary debugging */
WARN_ON_ONCE(atomic_read(&req->rsk_refcnt) != 0);
req->rsk_ops->destructor(req);
if (req->rsk_listener)
sock_put(req->rsk_listener);
kfree(req->saved_syn);
kmem_cache_free(req->rsk_ops->slab, req);
}
static inline void reqsk_put(struct request_sock *req)
{
if (atomic_dec_and_test(&req->rsk_refcnt))
reqsk_free(req);
}
/*
* 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()
*
*/
struct request_sock_queue {
spinlock_t rskq_lock;
u8 rskq_defer_accept;
u32 synflood_warned;
atomic_t qlen;
atomic_t young;
struct request_sock *rskq_accept_head;
struct request_sock *rskq_accept_tail;
struct fastopen_queue fastopenq; /* Check max_qlen != 0 to determine
* if TFO is enabled.
*/
};
void reqsk_queue_alloc(struct request_sock_queue *queue);
void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
bool reset);
static inline bool reqsk_queue_empty(const struct request_sock_queue *queue)
{
return queue->rskq_accept_head == NULL;
}
static inline struct request_sock *reqsk_queue_remove(struct request_sock_queue *queue,
struct sock *parent)
{
struct request_sock *req;
spin_lock_bh(&queue->rskq_lock);
req = queue->rskq_accept_head;
if (req) {
sk_acceptq_removed(parent);
queue->rskq_accept_head = req->dl_next;
if (queue->rskq_accept_head == NULL)
queue->rskq_accept_tail = NULL;
}
spin_unlock_bh(&queue->rskq_lock);
return req;
}
static inline void reqsk_queue_removed(struct request_sock_queue *queue,
const struct request_sock *req)
{
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>
2012-10-28 07:16:46 +08:00
if (req->num_timeout == 0)
atomic_dec(&queue->young);
atomic_dec(&queue->qlen);
}
static inline void reqsk_queue_added(struct request_sock_queue *queue)
{
atomic_inc(&queue->young);
atomic_inc(&queue->qlen);
}
static inline int reqsk_queue_len(const struct request_sock_queue *queue)
{
return atomic_read(&queue->qlen);
}
static inline int reqsk_queue_len_young(const struct request_sock_queue *queue)
{
return atomic_read(&queue->young);
}
#endif /* _REQUEST_SOCK_H */