bb5b7c1126
It creates a regression, triggering badness for SYN_RECV sockets, for example: [19148.022102] Badness at net/ipv4/inet_connection_sock.c:293 [19148.022570] NIP: c02a0914 LR: c02a0904 CTR: 00000000 [19148.023035] REGS: eeecbd30 TRAP: 0700 Not tainted (2.6.32) [19148.023496] MSR: 00029032 <EE,ME,CE,IR,DR> CR: 24002442 XER: 00000000 [19148.024012] TASK = eee9a820[1756] 'privoxy' THREAD: eeeca000 This is likely caused by the change in the 'estab' parameter passed to tcp_parse_options() when invoked by the functions in net/ipv4/tcp_minisocks.c But even if that is fixed, the ->conn_request() changes made in this patch series is fundamentally wrong. They try to use the listening socket's 'dst' to probe the route settings. The listening socket doesn't even have a route, and you can't get the right route (the child request one) until much later after we setup all of the state, and it must be done by hand. This stuff really isn't ready, so the best thing to do is a full revert. This reverts the following commits:f55017a93f
022c3f7d82
1aba721eba
cda42ebd67
345cda2fd6
dc343475ed
05eaade278
6a2a2d6bf8
Signed-off-by: David S. Miller <davem@davemloft.net>
310 lines
6.8 KiB
C
310 lines
6.8 KiB
C
/*
|
|
* net/dst.h Protocol independent destination cache definitions.
|
|
*
|
|
* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
|
|
*
|
|
*/
|
|
|
|
#ifndef _NET_DST_H
|
|
#define _NET_DST_H
|
|
|
|
#include <net/dst_ops.h>
|
|
#include <linux/netdevice.h>
|
|
#include <linux/rtnetlink.h>
|
|
#include <linux/rcupdate.h>
|
|
#include <linux/jiffies.h>
|
|
#include <net/neighbour.h>
|
|
#include <asm/processor.h>
|
|
|
|
/*
|
|
* 0 - no debugging messages
|
|
* 1 - rare events and bugs (default)
|
|
* 2 - trace mode.
|
|
*/
|
|
#define RT_CACHE_DEBUG 0
|
|
|
|
#define DST_GC_MIN (HZ/10)
|
|
#define DST_GC_INC (HZ/2)
|
|
#define DST_GC_MAX (120*HZ)
|
|
|
|
/* Each dst_entry has reference count and sits in some parent list(s).
|
|
* When it is removed from parent list, it is "freed" (dst_free).
|
|
* After this it enters dead state (dst->obsolete > 0) and if its refcnt
|
|
* is zero, it can be destroyed immediately, otherwise it is added
|
|
* to gc list and garbage collector periodically checks the refcnt.
|
|
*/
|
|
|
|
struct sk_buff;
|
|
|
|
struct dst_entry {
|
|
struct rcu_head rcu_head;
|
|
struct dst_entry *child;
|
|
struct net_device *dev;
|
|
short error;
|
|
short obsolete;
|
|
int flags;
|
|
#define DST_HOST 1
|
|
#define DST_NOXFRM 2
|
|
#define DST_NOPOLICY 4
|
|
#define DST_NOHASH 8
|
|
unsigned long expires;
|
|
|
|
unsigned short header_len; /* more space at head required */
|
|
unsigned short trailer_len; /* space to reserve at tail */
|
|
|
|
unsigned int rate_tokens;
|
|
unsigned long rate_last; /* rate limiting for ICMP */
|
|
|
|
struct dst_entry *path;
|
|
|
|
struct neighbour *neighbour;
|
|
struct hh_cache *hh;
|
|
#ifdef CONFIG_XFRM
|
|
struct xfrm_state *xfrm;
|
|
#else
|
|
void *__pad1;
|
|
#endif
|
|
int (*input)(struct sk_buff*);
|
|
int (*output)(struct sk_buff*);
|
|
|
|
struct dst_ops *ops;
|
|
|
|
u32 metrics[RTAX_MAX];
|
|
|
|
#ifdef CONFIG_NET_CLS_ROUTE
|
|
__u32 tclassid;
|
|
#else
|
|
__u32 __pad2;
|
|
#endif
|
|
|
|
|
|
/*
|
|
* Align __refcnt to a 64 bytes alignment
|
|
* (L1_CACHE_SIZE would be too much)
|
|
*/
|
|
#ifdef CONFIG_64BIT
|
|
long __pad_to_align_refcnt[2];
|
|
#else
|
|
long __pad_to_align_refcnt[1];
|
|
#endif
|
|
/*
|
|
* __refcnt wants to be on a different cache line from
|
|
* input/output/ops or performance tanks badly
|
|
*/
|
|
atomic_t __refcnt; /* client references */
|
|
int __use;
|
|
unsigned long lastuse;
|
|
union {
|
|
struct dst_entry *next;
|
|
struct rtable *rt_next;
|
|
struct rt6_info *rt6_next;
|
|
struct dn_route *dn_next;
|
|
};
|
|
};
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
static inline u32
|
|
dst_metric(const struct dst_entry *dst, int metric)
|
|
{
|
|
return dst->metrics[metric-1];
|
|
}
|
|
|
|
static inline u32
|
|
dst_feature(const struct dst_entry *dst, u32 feature)
|
|
{
|
|
return dst_metric(dst, RTAX_FEATURES) & feature;
|
|
}
|
|
|
|
static inline u32 dst_mtu(const struct dst_entry *dst)
|
|
{
|
|
u32 mtu = dst_metric(dst, RTAX_MTU);
|
|
/*
|
|
* Alexey put it here, so ask him about it :)
|
|
*/
|
|
barrier();
|
|
return mtu;
|
|
}
|
|
|
|
/* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */
|
|
static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metric)
|
|
{
|
|
return msecs_to_jiffies(dst_metric(dst, metric));
|
|
}
|
|
|
|
static inline void set_dst_metric_rtt(struct dst_entry *dst, int metric,
|
|
unsigned long rtt)
|
|
{
|
|
dst->metrics[metric-1] = jiffies_to_msecs(rtt);
|
|
}
|
|
|
|
static inline u32
|
|
dst_allfrag(const struct dst_entry *dst)
|
|
{
|
|
int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG);
|
|
/* Yes, _exactly_. This is paranoia. */
|
|
barrier();
|
|
return ret;
|
|
}
|
|
|
|
static inline int
|
|
dst_metric_locked(struct dst_entry *dst, int metric)
|
|
{
|
|
return dst_metric(dst, RTAX_LOCK) & (1<<metric);
|
|
}
|
|
|
|
static inline void dst_hold(struct dst_entry * dst)
|
|
{
|
|
/*
|
|
* If your kernel compilation stops here, please check
|
|
* __pad_to_align_refcnt declaration in struct dst_entry
|
|
*/
|
|
BUILD_BUG_ON(offsetof(struct dst_entry, __refcnt) & 63);
|
|
atomic_inc(&dst->__refcnt);
|
|
}
|
|
|
|
static inline void dst_use(struct dst_entry *dst, unsigned long time)
|
|
{
|
|
dst_hold(dst);
|
|
dst->__use++;
|
|
dst->lastuse = time;
|
|
}
|
|
|
|
static inline
|
|
struct dst_entry * dst_clone(struct dst_entry * dst)
|
|
{
|
|
if (dst)
|
|
atomic_inc(&dst->__refcnt);
|
|
return dst;
|
|
}
|
|
|
|
extern void dst_release(struct dst_entry *dst);
|
|
static inline void skb_dst_drop(struct sk_buff *skb)
|
|
{
|
|
if (skb->_skb_dst)
|
|
dst_release(skb_dst(skb));
|
|
skb->_skb_dst = 0UL;
|
|
}
|
|
|
|
/* Children define the path of the packet through the
|
|
* Linux networking. Thus, destinations are stackable.
|
|
*/
|
|
|
|
static inline struct dst_entry *dst_pop(struct dst_entry *dst)
|
|
{
|
|
struct dst_entry *child = dst_clone(dst->child);
|
|
|
|
dst_release(dst);
|
|
return child;
|
|
}
|
|
|
|
extern int dst_discard(struct sk_buff *skb);
|
|
extern void * dst_alloc(struct dst_ops * ops);
|
|
extern void __dst_free(struct dst_entry * dst);
|
|
extern struct dst_entry *dst_destroy(struct dst_entry * dst);
|
|
|
|
static inline void dst_free(struct dst_entry * dst)
|
|
{
|
|
if (dst->obsolete > 1)
|
|
return;
|
|
if (!atomic_read(&dst->__refcnt)) {
|
|
dst = dst_destroy(dst);
|
|
if (!dst)
|
|
return;
|
|
}
|
|
__dst_free(dst);
|
|
}
|
|
|
|
static inline void dst_rcu_free(struct rcu_head *head)
|
|
{
|
|
struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
|
|
dst_free(dst);
|
|
}
|
|
|
|
static inline void dst_confirm(struct dst_entry *dst)
|
|
{
|
|
if (dst)
|
|
neigh_confirm(dst->neighbour);
|
|
}
|
|
|
|
static inline void dst_negative_advice(struct dst_entry **dst_p,
|
|
struct sock *sk)
|
|
{
|
|
struct dst_entry * dst = *dst_p;
|
|
if (dst && dst->ops->negative_advice) {
|
|
*dst_p = dst->ops->negative_advice(dst);
|
|
|
|
if (dst != *dst_p) {
|
|
extern void sk_reset_txq(struct sock *sk);
|
|
|
|
sk_reset_txq(sk);
|
|
}
|
|
}
|
|
}
|
|
|
|
static inline void dst_link_failure(struct sk_buff *skb)
|
|
{
|
|
struct dst_entry *dst = skb_dst(skb);
|
|
if (dst && dst->ops && dst->ops->link_failure)
|
|
dst->ops->link_failure(skb);
|
|
}
|
|
|
|
static inline void dst_set_expires(struct dst_entry *dst, int timeout)
|
|
{
|
|
unsigned long expires = jiffies + timeout;
|
|
|
|
if (expires == 0)
|
|
expires = 1;
|
|
|
|
if (dst->expires == 0 || time_before(expires, dst->expires))
|
|
dst->expires = expires;
|
|
}
|
|
|
|
/* Output packet to network from transport. */
|
|
static inline int dst_output(struct sk_buff *skb)
|
|
{
|
|
return skb_dst(skb)->output(skb);
|
|
}
|
|
|
|
/* Input packet from network to transport. */
|
|
static inline int dst_input(struct sk_buff *skb)
|
|
{
|
|
return skb_dst(skb)->input(skb);
|
|
}
|
|
|
|
static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie)
|
|
{
|
|
if (dst->obsolete)
|
|
dst = dst->ops->check(dst, cookie);
|
|
return dst;
|
|
}
|
|
|
|
extern void dst_init(void);
|
|
|
|
/* Flags for xfrm_lookup flags argument. */
|
|
enum {
|
|
XFRM_LOOKUP_WAIT = 1 << 0,
|
|
XFRM_LOOKUP_ICMP = 1 << 1,
|
|
};
|
|
|
|
struct flowi;
|
|
#ifndef CONFIG_XFRM
|
|
static inline int xfrm_lookup(struct net *net, struct dst_entry **dst_p,
|
|
struct flowi *fl, struct sock *sk, int flags)
|
|
{
|
|
return 0;
|
|
}
|
|
static inline int __xfrm_lookup(struct net *net, struct dst_entry **dst_p,
|
|
struct flowi *fl, struct sock *sk, int flags)
|
|
{
|
|
return 0;
|
|
}
|
|
#else
|
|
extern int xfrm_lookup(struct net *net, struct dst_entry **dst_p,
|
|
struct flowi *fl, struct sock *sk, int flags);
|
|
extern int __xfrm_lookup(struct net *net, struct dst_entry **dst_p,
|
|
struct flowi *fl, struct sock *sk, int flags);
|
|
#endif
|
|
#endif
|
|
|
|
#endif /* _NET_DST_H */
|