[linux-block.git] / include / net / dst.h

/*
 * 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/bug.h>
#include <linux/jiffies.h>
#include <linux/refcount.h>
#include <net/neighbour.h>
#include <asm/processor.h>

#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 net_device       *dev;
	struct rcu_head		rcu_head;
	struct dst_entry	*child;
	struct  dst_ops	        *ops;
	unsigned long		_metrics;
	unsigned long           expires;
	struct dst_entry	*path;
	struct dst_entry	*from;
#ifdef CONFIG_XFRM
	struct xfrm_state	*xfrm;
#else
	void			*__pad1;
#endif
	int			(*input)(struct sk_buff *);
	int			(*output)(struct net *net, struct sock *sk, struct sk_buff *skb);

	unsigned short		flags;
#define DST_HOST		0x0001
#define DST_NOXFRM		0x0002
#define DST_NOPOLICY		0x0004
#define DST_NOCOUNT		0x0008
#define DST_FAKE_RTABLE		0x0010
#define DST_XFRM_TUNNEL		0x0020
#define DST_XFRM_QUEUE		0x0040
#define DST_METADATA		0x0080

	short			error;

	/* A non-zero value of dst->obsolete forces by-hand validation
	 * of the route entry.  Positive values are set by the generic
	 * dst layer to indicate that the entry has been forcefully
	 * destroyed.
	 *
	 * Negative values are used by the implementation layer code to
	 * force invocation of the dst_ops->check() method.
	 */
	short			obsolete;
#define DST_OBSOLETE_NONE	0
#define DST_OBSOLETE_DEAD	2
#define DST_OBSOLETE_FORCE_CHK	-1
#define DST_OBSOLETE_KILL	-2
	unsigned short		header_len;	/* more space at head required */
	unsigned short		trailer_len;	/* space to reserve at tail */
	unsigned short		__pad3;

#ifdef CONFIG_IP_ROUTE_CLASSID
	__u32			tclassid;
#else
	__u32			__pad2;
#endif

#ifdef CONFIG_64BIT
	/*
	 * Align __refcnt to a 64 bytes alignment
	 * (L1_CACHE_SIZE would be too much)
	 */
	long			__pad_to_align_refcnt[2];
#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;
	struct lwtunnel_state   *lwtstate;
	union {
		struct dst_entry	*next;
		struct rtable __rcu	*rt_next;
		struct rt6_info		*rt6_next;
		struct dn_route __rcu	*dn_next;
	};
};

struct dst_metrics {
	u32		metrics[RTAX_MAX];
	refcount_t	refcnt;
};
extern const struct dst_metrics dst_default_metrics;

u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old);

#define DST_METRICS_READ_ONLY		0x1UL
#define DST_METRICS_REFCOUNTED		0x2UL
#define DST_METRICS_FLAGS		0x3UL
#define __DST_METRICS_PTR(Y)	\
	((u32 *)((Y) & ~DST_METRICS_FLAGS))
#define DST_METRICS_PTR(X)	__DST_METRICS_PTR((X)->_metrics)

static inline bool dst_metrics_read_only(const struct dst_entry *dst)
{
	return dst->_metrics & DST_METRICS_READ_ONLY;
}

void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old);

static inline void dst_destroy_metrics_generic(struct dst_entry *dst)
{
	unsigned long val = dst->_metrics;
	if (!(val & DST_METRICS_READ_ONLY))
		__dst_destroy_metrics_generic(dst, val);
}

static inline u32 *dst_metrics_write_ptr(struct dst_entry *dst)
{
	unsigned long p = dst->_metrics;

	BUG_ON(!p);

	if (p & DST_METRICS_READ_ONLY)
		return dst->ops->cow_metrics(dst, p);
	return __DST_METRICS_PTR(p);
}

/* This may only be invoked before the entry has reached global
 * visibility.
 */
static inline void dst_init_metrics(struct dst_entry *dst,
				    const u32 *src_metrics,
				    bool read_only)
{
	dst->_metrics = ((unsigned long) src_metrics) |
		(read_only ? DST_METRICS_READ_ONLY : 0);
}

static inline void dst_copy_metrics(struct dst_entry *dest, const struct dst_entry *src)
{
	u32 *dst_metrics = dst_metrics_write_ptr(dest);

	if (dst_metrics) {
		u32 *src_metrics = DST_METRICS_PTR(src);

		memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32));
	}
}

static inline u32 *dst_metrics_ptr(struct dst_entry *dst)
{
	return DST_METRICS_PTR(dst);
}

static inline u32
dst_metric_raw(const struct dst_entry *dst, const int metric)
{
	u32 *p = DST_METRICS_PTR(dst);

	return p[metric-1];
}

static inline u32
dst_metric(const struct dst_entry *dst, const int metric)
{
	WARN_ON_ONCE(metric == RTAX_HOPLIMIT ||
		     metric == RTAX_ADVMSS ||
		     metric == RTAX_MTU);
	return dst_metric_raw(dst, metric);
}

static inline u32
dst_metric_advmss(const struct dst_entry *dst)
{
	u32 advmss = dst_metric_raw(dst, RTAX_ADVMSS);

	if (!advmss)
		advmss = dst->ops->default_advmss(dst);

	return advmss;
}

static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val)
{
	u32 *p = dst_metrics_write_ptr(dst);

	if (p)
		p[metric-1] = val;
}

/* Kernel-internal feature bits that are unallocated in user space. */
#define DST_FEATURE_ECN_CA	(1 << 31)

#define DST_FEATURE_MASK	(DST_FEATURE_ECN_CA)
#define DST_FEATURE_ECN_MASK	(DST_FEATURE_ECN_CA | RTAX_FEATURE_ECN)

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)
{
	return dst->ops->mtu(dst);
}

/* 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 u32
dst_allfrag(const struct dst_entry *dst)
{
	int ret = dst_feature(dst,  RTAX_FEATURE_ALLFRAG);
	return ret;
}

static inline int
dst_metric_locked(const 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);
	WARN_ON(atomic_inc_not_zero(&dst->__refcnt) == 0);
}

static inline void dst_use(struct dst_entry *dst, unsigned long time)
{
	dst_hold(dst);
	dst->__use++;
	dst->lastuse = time;
}

static inline void dst_use_noref(struct dst_entry *dst, unsigned long time)
{
	dst->__use++;
	dst->lastuse = time;
}

static inline struct dst_entry *dst_clone(struct dst_entry *dst)
{
	if (dst)
		atomic_inc(&dst->__refcnt);
	return dst;
}

void dst_release(struct dst_entry *dst);

void dst_release_immediate(struct dst_entry *dst);

static inline void refdst_drop(unsigned long refdst)
{
	if (!(refdst & SKB_DST_NOREF))
		dst_release((struct dst_entry *)(refdst & SKB_DST_PTRMASK));
}

/**
 * skb_dst_drop - drops skb dst
 * @skb: buffer
 *
 * Drops dst reference count if a reference was taken.
 */
static inline void skb_dst_drop(struct sk_buff *skb)
{
	if (skb->_skb_refdst) {
		refdst_drop(skb->_skb_refdst);
		skb->_skb_refdst = 0UL;
	}
}

static inline void __skb_dst_copy(struct sk_buff *nskb, unsigned long refdst)
{
	nskb->_skb_refdst = refdst;
	if (!(nskb->_skb_refdst & SKB_DST_NOREF))
		dst_clone(skb_dst(nskb));
}

static inline void skb_dst_copy(struct sk_buff *nskb, const struct sk_buff *oskb)
{
	__skb_dst_copy(nskb, oskb->_skb_refdst);
}

/**
 * skb_dst_force - makes sure skb dst is refcounted
 * @skb: buffer
 *
 * If dst is not yet refcounted, let's do it
 */
static inline void skb_dst_force(struct sk_buff *skb)
{
	if (skb_dst_is_noref(skb)) {
		WARN_ON(!rcu_read_lock_held());
		skb->_skb_refdst &= ~SKB_DST_NOREF;
		dst_clone(skb_dst(skb));
	}
}

/**
 * dst_hold_safe - Take a reference on a dst if possible
 * @dst: pointer to dst entry
 *
 * This helper returns false if it could not safely
 * take a reference on a dst.
 */
static inline bool dst_hold_safe(struct dst_entry *dst)
{
	return atomic_inc_not_zero(&dst->__refcnt);
}

/**
 * skb_dst_force_safe - makes sure skb dst is refcounted
 * @skb: buffer
 *
 * If dst is not yet refcounted and not destroyed, grab a ref on it.
 */
static inline void skb_dst_force_safe(struct sk_buff *skb)
{
	if (skb_dst_is_noref(skb)) {
		struct dst_entry *dst = skb_dst(skb);

		if (!dst_hold_safe(dst))
			dst = NULL;

		skb->_skb_refdst = (unsigned long)dst;
	}
}


/**
 *	__skb_tunnel_rx - prepare skb for rx reinsert
 *	@skb: buffer
 *	@dev: tunnel device
 *	@net: netns for packet i/o
 *
 *	After decapsulation, packet is going to re-enter (netif_rx()) our stack,
 *	so make some cleanups. (no accounting done)
 */
static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev,
				   struct net *net)
{
	skb->dev = dev;

	/*
	 * Clear hash so that we can recalulate the hash for the
	 * encapsulated packet, unless we have already determine the hash
	 * over the L4 4-tuple.
	 */
	skb_clear_hash_if_not_l4(skb);
	skb_set_queue_mapping(skb, 0);
	skb_scrub_packet(skb, !net_eq(net, dev_net(dev)));
}

/**
 *	skb_tunnel_rx - prepare skb for rx reinsert
 *	@skb: buffer
 *	@dev: tunnel device
 *
 *	After decapsulation, packet is going to re-enter (netif_rx()) our stack,
 *	so make some cleanups, and perform accounting.
 *	Note: this accounting is not SMP safe.
 */
static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev,
				 struct net *net)
{
	/* TODO : stats should be SMP safe */
	dev->stats.rx_packets++;
	dev->stats.rx_bytes += skb->len;
	__skb_tunnel_rx(skb, dev, net);
}

static inline u32 dst_tclassid(const struct sk_buff *skb)
{
#ifdef CONFIG_IP_ROUTE_CLASSID
	const struct dst_entry *dst;

	dst = skb_dst(skb);
	if (dst)
		return dst->tclassid;
#endif
	return 0;
}

int dst_discard_out(struct net *net, struct sock *sk, struct sk_buff *skb);
static inline int dst_discard(struct sk_buff *skb)
{
	return dst_discard_out(&init_net, skb->sk, skb);
}
void *dst_alloc(struct dst_ops *ops, struct net_device *dev, int initial_ref,
		int initial_obsolete, unsigned short flags);
void dst_init(struct dst_entry *dst, struct dst_ops *ops,
	      struct net_device *dev, int initial_ref, int initial_obsolete,
	      unsigned short flags);
struct dst_entry *dst_destroy(struct dst_entry *dst);
void dst_dev_put(struct dst_entry *dst);

static inline void dst_confirm(struct dst_entry *dst)
{
}

static inline struct neighbour *dst_neigh_lookup(const struct dst_entry *dst, const void *daddr)
{
	struct neighbour *n = dst->ops->neigh_lookup(dst, NULL, daddr);
	return IS_ERR(n) ? NULL : n;
}

static inline struct neighbour *dst_neigh_lookup_skb(const struct dst_entry *dst,
						     struct sk_buff *skb)
{
	struct neighbour *n =  dst->ops->neigh_lookup(dst, skb, NULL);
	return IS_ERR(n) ? NULL : n;
}

static inline void dst_confirm_neigh(const struct dst_entry *dst,
				     const void *daddr)
{
	if (dst->ops->confirm_neigh)
		dst->ops->confirm_neigh(dst, daddr);
}

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 net *net, struct sock *sk, struct sk_buff *skb)
{
	return skb_dst(skb)->output(net, sk, 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;
}

/* Flags for xfrm_lookup flags argument. */
enum {
	XFRM_LOOKUP_ICMP = 1 << 0,
	XFRM_LOOKUP_QUEUE = 1 << 1,
	XFRM_LOOKUP_KEEP_DST_REF = 1 << 2,
};

struct flowi;
#ifndef CONFIG_XFRM
static inline struct dst_entry *xfrm_lookup(struct net *net,
					    struct dst_entry *dst_orig,
					    const struct flowi *fl,
					    const struct sock *sk,
					    int flags)
{
	return dst_orig;
}

static inline struct dst_entry *xfrm_lookup_route(struct net *net,
						  struct dst_entry *dst_orig,
						  const struct flowi *fl,
						  const struct sock *sk,
						  int flags)
{
	return dst_orig;
}

static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
{
	return NULL;
}

#else
struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig,
			      const struct flowi *fl, const struct sock *sk,
			      int flags);

struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig,
				    const struct flowi *fl, const struct sock *sk,
				    int flags);

/* skb attached with this dst needs transformation if dst->xfrm is valid */
static inline struct xfrm_state *dst_xfrm(const struct dst_entry *dst)
{
	return dst->xfrm;
}
#endif

#endif /* _NET_DST_H */
Commit	Line	Data
1da177e4 LT	1	/*
	2	* net/dst.h Protocol independent destination cache definitions.
	3	*
	4	* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
	5	*
	6	*/
	7
	8	#ifndef _NET_DST_H
	9	#define _NET_DST_H
	10
86393e52	11	#include <net/dst_ops.h>
14c85021	12	#include <linux/netdevice.h>
1da177e4 LT	13	#include <linux/rtnetlink.h>
1da177e4 LT	14	#include <linux/rcupdate.h>
187f1882	15	#include <linux/bug.h>
1da177e4	16	#include <linux/jiffies.h>
9620fef2	17	#include <linux/refcount.h>
1da177e4 LT	18	#include <net/neighbour.h>
	19	#include <asm/processor.h>
	20
1da177e4 LT	21	#define DST_GC_MIN (HZ/10)
	22	#define DST_GC_INC (HZ/2)
	23	#define DST_GC_MAX (120*HZ)
	24
	25	/* Each dst_entry has reference count and sits in some parent list(s).
	26	* When it is removed from parent list, it is "freed" (dst_free).
	27	* After this it enters dead state (dst->obsolete > 0) and if its refcnt
	28	* is zero, it can be destroyed immediately, otherwise it is added
	29	* to gc list and garbage collector periodically checks the refcnt.
	30	*/
	31
	32	struct sk_buff;
	33
fd2c3ef7	34	struct dst_entry {
66727145	35	struct net_device *dev;
1e19e02c	36	struct rcu_head rcu_head;
1da177e4	37	struct dst_entry *child;
62fa8a84 DM	38	struct dst_ops *ops;
62fa8a84 DM	39	unsigned long _metrics;
ecd98837	40	unsigned long expires;
f1dd9c37	41	struct dst_entry *path;
ecd98837	42	struct dst_entry *from;
def8b4fa	43	#ifdef CONFIG_XFRM
1da177e4	44	struct xfrm_state *xfrm;
5635c10d ED	45	#else
5635c10d ED	46	void *__pad1;
def8b4fa	47	#endif
7f95e188	48	int (input)(struct sk_buff );
ede2059d	49	int (output)(struct net net, struct sock sk, struct sk_buff skb);
1da177e4	50
5110effe	51	unsigned short flags;
f6b72b62 DM	52	#define DST_HOST 0x0001
	53	#define DST_NOXFRM 0x0002
	54	#define DST_NOPOLICY 0x0004
1eb04e7c WW	55	#define DST_NOCOUNT 0x0008
	56	#define DST_FAKE_RTABLE 0x0010
	57	#define DST_XFRM_TUNNEL 0x0020
	58	#define DST_XFRM_QUEUE 0x0040
	59	#define DST_METADATA 0x0080
f6b72b62	60
62fa8a84	61	short error;
f5b0a874 DM	62
	63	/* A non-zero value of dst->obsolete forces by-hand validation
	64	* of the route entry. Positive values are set by the generic
	65	* dst layer to indicate that the entry has been forcefully
	66	* destroyed.
	67	*
	68	* Negative values are used by the implementation layer code to
	69	* force invocation of the dst_ops->check() method.
	70	*/
62fa8a84	71	short obsolete;
f5b0a874 DM	72	#define DST_OBSOLETE_NONE 0
	73	#define DST_OBSOLETE_DEAD 2
	74	#define DST_OBSOLETE_FORCE_CHK -1
ceb33206	75	#define DST_OBSOLETE_KILL -2
62fa8a84 DM	76	unsigned short header_len; /* more space at head required */
62fa8a84 DM	77	unsigned short trailer_len; /* space to reserve at tail */
51ce8bd4 JA	78	unsigned short __pad3;
51ce8bd4 JA	79
c7066f70	80	#ifdef CONFIG_IP_ROUTE_CLASSID
f1dd9c37	81	__u32 tclassid;
5635c10d ED	82	#else
5635c10d ED	83	__u32 __pad2;
f1dd9c37 ZY	84	#endif
f1dd9c37 ZY	85
751a587a	86	#ifdef CONFIG_64BIT
5635c10d ED	87	/*
	88	* Align __refcnt to a 64 bytes alignment
	89	* (L1_CACHE_SIZE would be too much)
	90	*/
0868e253	91	long __pad_to_align_refcnt[2];
5635c10d	92	#endif
f1dd9c37 ZY	93	/*
	94	* __refcnt wants to be on a different cache line from
	95	* input/output/ops or performance tanks badly
	96	*/
1e19e02c ED	97	atomic_t __refcnt; /* client references */
1e19e02c ED	98	int __use;
f1dd9c37	99	unsigned long lastuse;
751a587a	100	struct lwtunnel_state *lwtstate;
1e19e02c	101	union {
fc766e4c ED	102	struct dst_entry *next;
	103	struct rtable __rcu *rt_next;
	104	struct rt6_info *rt6_next;
	105	struct dn_route __rcu *dn_next;
1e19e02c	106	};
1da177e4 LT	107	};
1da177e4 LT	108
3fb07daf ED	109	struct dst_metrics {
3fb07daf ED	110	u32 metrics[RTAX_MAX];
9620fef2	111	refcount_t refcnt;
3fb07daf ED	112	};
	113	extern const struct dst_metrics dst_default_metrics;
	114
a4023dd0	115	u32 dst_cow_metrics_generic(struct dst_entry dst, unsigned long old);
62fa8a84	116
e5fd387a	117	#define DST_METRICS_READ_ONLY 0x1UL
3fb07daf	118	#define DST_METRICS_REFCOUNTED 0x2UL
e5fd387a	119	#define DST_METRICS_FLAGS 0x3UL
62fa8a84	120	#define __DST_METRICS_PTR(Y) \
e5fd387a	121	((u32 *)((Y) & ~DST_METRICS_FLAGS))
62fa8a84 DM	122	#define DST_METRICS_PTR(X) __DST_METRICS_PTR((X)->_metrics)
	123
	124	static inline bool dst_metrics_read_only(const struct dst_entry *dst)
	125	{
	126	return dst->_metrics & DST_METRICS_READ_ONLY;
	127	}
	128
a4023dd0	129	void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old);
62fa8a84 DM	130
	131	static inline void dst_destroy_metrics_generic(struct dst_entry *dst)
	132	{
	133	unsigned long val = dst->_metrics;
	134	if (!(val & DST_METRICS_READ_ONLY))
	135	__dst_destroy_metrics_generic(dst, val);
	136	}
	137
	138	static inline u32 dst_metrics_write_ptr(struct dst_entry dst)
	139	{
	140	unsigned long p = dst->_metrics;
	141
1f37070d SH	142	BUG_ON(!p);
1f37070d SH	143
62fa8a84 DM	144	if (p & DST_METRICS_READ_ONLY)
	145	return dst->ops->cow_metrics(dst, p);
	146	return __DST_METRICS_PTR(p);
	147	}
	148
	149	/* This may only be invoked before the entry has reached global
	150	* visibility.
	151	*/
	152	static inline void dst_init_metrics(struct dst_entry *dst,
	153	const u32 *src_metrics,
	154	bool read_only)
	155	{
	156	dst->_metrics = ((unsigned long) src_metrics) \|
	157	(read_only ? DST_METRICS_READ_ONLY : 0);
	158	}
	159
	160	static inline void dst_copy_metrics(struct dst_entry dest, const struct dst_entry src)
	161	{
	162	u32 *dst_metrics = dst_metrics_write_ptr(dest);
	163
	164	if (dst_metrics) {
	165	u32 *src_metrics = DST_METRICS_PTR(src);
	166
	167	memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32));
	168	}
	169	}
	170
	171	static inline u32 dst_metrics_ptr(struct dst_entry dst)
	172	{
	173	return DST_METRICS_PTR(dst);
	174	}
	175
1da177e4	176	static inline u32
5170ae82	177	dst_metric_raw(const struct dst_entry *dst, const int metric)
1da177e4	178	{
62fa8a84 DM	179	u32 *p = DST_METRICS_PTR(dst);
	180
	181	return p[metric-1];
defb3519 DM	182	}
defb3519 DM	183
5170ae82 DM	184	static inline u32
	185	dst_metric(const struct dst_entry *dst, const int metric)
	186	{
0dbaee3b	187	WARN_ON_ONCE(metric == RTAX_HOPLIMIT \|\|
d33e4553 DM	188	metric == RTAX_ADVMSS \|\|
d33e4553 DM	189	metric == RTAX_MTU);
5170ae82 DM	190	return dst_metric_raw(dst, metric);
	191	}
	192
0dbaee3b DM	193	static inline u32
	194	dst_metric_advmss(const struct dst_entry *dst)
	195	{
	196	u32 advmss = dst_metric_raw(dst, RTAX_ADVMSS);
	197
	198	if (!advmss)
	199	advmss = dst->ops->default_advmss(dst);
	200
	201	return advmss;
	202	}
	203
defb3519 DM	204	static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val)
defb3519 DM	205	{
62fa8a84	206	u32 *p = dst_metrics_write_ptr(dst);
defb3519	207
62fa8a84 DM	208	if (p)
62fa8a84 DM	209	p[metric-1] = val;
1da177e4 LT	210	}
1da177e4 LT	211
c3a8d947 DB	212	/* Kernel-internal feature bits that are unallocated in user space. */
	213	#define DST_FEATURE_ECN_CA (1 << 31)
	214
	215	#define DST_FEATURE_MASK (DST_FEATURE_ECN_CA)
	216	#define DST_FEATURE_ECN_MASK (DST_FEATURE_ECN_CA \| RTAX_FEATURE_ECN)
	217
0c3adfb8 GBY	218	static inline u32
	219	dst_feature(const struct dst_entry *dst, u32 feature)
	220	{
bb5b7c11	221	return dst_metric(dst, RTAX_FEATURES) & feature;
0c3adfb8 GBY	222	}
0c3adfb8 GBY	223
1da177e4 LT	224	static inline u32 dst_mtu(const struct dst_entry *dst)
1da177e4 LT	225	{
618f9bc7	226	return dst->ops->mtu(dst);
1da177e4 LT	227	}
1da177e4 LT	228
c1e20f7c SH	229	/* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */
	230	static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metric)
	231	{
	232	return msecs_to_jiffies(dst_metric(dst, metric));
	233	}
	234
1da177e4 LT	235	static inline u32
	236	dst_allfrag(const struct dst_entry *dst)
	237	{
0c3adfb8	238	int ret = dst_feature(dst, RTAX_FEATURE_ALLFRAG);
1da177e4 LT	239	return ret;
	240	}
	241
	242	static inline int
d33e4553	243	dst_metric_locked(const struct dst_entry *dst, int metric)
1da177e4 LT	244	{
	245	return dst_metric(dst, RTAX_LOCK) & (1<<metric);
	246	}
	247
7f95e188	248	static inline void dst_hold(struct dst_entry *dst)
1da177e4	249	{
5635c10d ED	250	/*
	251	* If your kernel compilation stops here, please check
	252	* __pad_to_align_refcnt declaration in struct dst_entry
	253	*/
	254	BUILD_BUG_ON(offsetof(struct dst_entry, __refcnt) & 63);
44ebe791	255	WARN_ON(atomic_inc_not_zero(&dst->__refcnt) == 0);
1da177e4 LT	256	}
1da177e4 LT	257
03f49f34 PE	258	static inline void dst_use(struct dst_entry *dst, unsigned long time)
	259	{
	260	dst_hold(dst);
	261	dst->__use++;
	262	dst->lastuse = time;
	263	}
	264
7fee226a ED	265	static inline void dst_use_noref(struct dst_entry *dst, unsigned long time)
	266	{
	267	dst->__use++;
	268	dst->lastuse = time;
	269	}
	270
7f95e188	271	static inline struct dst_entry dst_clone(struct dst_entry dst)
1da177e4 LT	272	{
	273	if (dst)
	274	atomic_inc(&dst->__refcnt);
	275	return dst;
	276	}
	277
a4023dd0	278	void dst_release(struct dst_entry *dst);
7fee226a	279
5f56f409 WW	280	void dst_release_immediate(struct dst_entry *dst);
5f56f409 WW	281
7fee226a ED	282	static inline void refdst_drop(unsigned long refdst)
	283	{
	284	if (!(refdst & SKB_DST_NOREF))
	285	dst_release((struct dst_entry *)(refdst & SKB_DST_PTRMASK));
	286	}
	287
	288	/**
	289	* skb_dst_drop - drops skb dst
	290	* @skb: buffer
	291	*
	292	* Drops dst reference count if a reference was taken.
	293	*/
adf30907 ED	294	static inline void skb_dst_drop(struct sk_buff *skb)
adf30907 ED	295	{
7fee226a ED	296	if (skb->_skb_refdst) {
	297	refdst_drop(skb->_skb_refdst);
	298	skb->_skb_refdst = 0UL;
	299	}
	300	}
	301
e79e2595	302	static inline void __skb_dst_copy(struct sk_buff *nskb, unsigned long refdst)
7fee226a	303	{
e79e2595	304	nskb->_skb_refdst = refdst;
7fee226a ED	305	if (!(nskb->_skb_refdst & SKB_DST_NOREF))
	306	dst_clone(skb_dst(nskb));
	307	}
	308
e79e2595 JS	309	static inline void skb_dst_copy(struct sk_buff nskb, const struct sk_buff oskb)
	310	{
	311	__skb_dst_copy(nskb, oskb->_skb_refdst);
	312	}
	313
7fee226a ED	314	/**
	315	* skb_dst_force - makes sure skb dst is refcounted
	316	* @skb: buffer
	317	*
	318	* If dst is not yet refcounted, let's do it
	319	*/
	320	static inline void skb_dst_force(struct sk_buff *skb)
	321	{
	322	if (skb_dst_is_noref(skb)) {
	323	WARN_ON(!rcu_read_lock_held());
	324	skb->_skb_refdst &= ~SKB_DST_NOREF;
	325	dst_clone(skb_dst(skb));
	326	}
adf30907	327	}
1da177e4	328
5037e9ef ED	329	/**
	330	* dst_hold_safe - Take a reference on a dst if possible
	331	* @dst: pointer to dst entry
	332	*
	333	* This helper returns false if it could not safely
	334	* take a reference on a dst.
	335	*/
	336	static inline bool dst_hold_safe(struct dst_entry *dst)
	337	{
b2a9c0ed	338	return atomic_inc_not_zero(&dst->__refcnt);
5037e9ef ED	339	}
	340
	341	/**
	342	* skb_dst_force_safe - makes sure skb dst is refcounted
	343	* @skb: buffer
	344	*
	345	* If dst is not yet refcounted and not destroyed, grab a ref on it.
	346	*/
	347	static inline void skb_dst_force_safe(struct sk_buff *skb)
	348	{
	349	if (skb_dst_is_noref(skb)) {
	350	struct dst_entry *dst = skb_dst(skb);
	351
	352	if (!dst_hold_safe(dst))
	353	dst = NULL;
	354
	355	skb->_skb_refdst = (unsigned long)dst;
	356	}
	357	}
	358
d19d56dd	359
290b895e ED	360	/**
	361	* __skb_tunnel_rx - prepare skb for rx reinsert
	362	* @skb: buffer
	363	* @dev: tunnel device
ea23192e	364	* @net: netns for packet i/o
290b895e ED	365	*
	366	* After decapsulation, packet is going to re-enter (netif_rx()) our stack,
	367	* so make some cleanups. (no accounting done)
	368	*/
ea23192e ND	369	static inline void __skb_tunnel_rx(struct sk_buff skb, struct net_device dev,
ea23192e ND	370	struct net *net)
290b895e ED	371	{
290b895e ED	372	skb->dev = dev;
bdeab991 TH	373
bdeab991 TH	374	/*
7539fadc	375	* Clear hash so that we can recalulate the hash for the
bdeab991 TH	376	* encapsulated packet, unless we have already determine the hash
	377	* over the L4 4-tuple.
	378	*/
7539fadc	379	skb_clear_hash_if_not_l4(skb);
290b895e	380	skb_set_queue_mapping(skb, 0);
ea23192e	381	skb_scrub_packet(skb, !net_eq(net, dev_net(dev)));
290b895e ED	382	}
290b895e ED	383
d19d56dd ED	384	/**
	385	* skb_tunnel_rx - prepare skb for rx reinsert
	386	* @skb: buffer
	387	* @dev: tunnel device
	388	*
	389	* After decapsulation, packet is going to re-enter (netif_rx()) our stack,
	390	* so make some cleanups, and perform accounting.
290b895e	391	* Note: this accounting is not SMP safe.
d19d56dd	392	*/
ea23192e ND	393	static inline void skb_tunnel_rx(struct sk_buff skb, struct net_device dev,
ea23192e ND	394	struct net *net)
d19d56dd	395	{
d19d56dd ED	396	/* TODO : stats should be SMP safe */
	397	dev->stats.rx_packets++;
	398	dev->stats.rx_bytes += skb->len;
ea23192e	399	__skb_tunnel_rx(skb, dev, net);
d19d56dd ED	400	}
d19d56dd ED	401
808c1b69 DB	402	static inline u32 dst_tclassid(const struct sk_buff *skb)
	403	{
	404	#ifdef CONFIG_IP_ROUTE_CLASSID
	405	const struct dst_entry *dst;
	406
	407	dst = skb_dst(skb);
	408	if (dst)
	409	return dst->tclassid;
	410	#endif
	411	return 0;
	412	}
	413
ede2059d	414	int dst_discard_out(struct net net, struct sock sk, struct sk_buff *skb);
aad88724 ED	415	static inline int dst_discard(struct sk_buff *skb)
aad88724 ED	416	{
ede2059d	417	return dst_discard_out(&init_net, skb->sk, skb);
aad88724	418	}
a4023dd0 JP	419	void dst_alloc(struct dst_ops ops, struct net_device *dev, int initial_ref,
a4023dd0 JP	420	int initial_obsolete, unsigned short flags);
f38a9eb1 TG	421	void dst_init(struct dst_entry dst, struct dst_ops ops,
	422	struct net_device *dev, int initial_ref, int initial_obsolete,
	423	unsigned short flags);
a4023dd0	424	struct dst_entry dst_destroy(struct dst_entry dst);
4a6ce2b6	425	void dst_dev_put(struct dst_entry *dst);
1da177e4	426
1da177e4 LT	427	static inline void dst_confirm(struct dst_entry *dst)
1da177e4 LT	428	{
5110effe	429	}
f2c31e32	430
d3aaeb38 DM	431	static inline struct neighbour dst_neigh_lookup(const struct dst_entry dst, const void *daddr)
d3aaeb38 DM	432	{
aaa0c23c ZZ	433	struct neighbour *n = dst->ops->neigh_lookup(dst, NULL, daddr);
aaa0c23c ZZ	434	return IS_ERR(n) ? NULL : n;
f894cbf8 DM	435	}
	436
	437	static inline struct neighbour dst_neigh_lookup_skb(const struct dst_entry dst,
	438	struct sk_buff *skb)
	439	{
aaa0c23c ZZ	440	struct neighbour *n = dst->ops->neigh_lookup(dst, skb, NULL);
aaa0c23c ZZ	441	return IS_ERR(n) ? NULL : n;
d3aaeb38 DM	442	}
d3aaeb38 DM	443
63fca65d JA	444	static inline void dst_confirm_neigh(const struct dst_entry *dst,
	445	const void *daddr)
	446	{
	447	if (dst->ops->confirm_neigh)
	448	dst->ops->confirm_neigh(dst, daddr);
	449	}
	450
1da177e4 LT	451	static inline void dst_link_failure(struct sk_buff *skb)
1da177e4 LT	452	{
adf30907	453	struct dst_entry *dst = skb_dst(skb);
1da177e4 LT	454	if (dst && dst->ops && dst->ops->link_failure)
	455	dst->ops->link_failure(skb);
	456	}
	457
	458	static inline void dst_set_expires(struct dst_entry *dst, int timeout)
	459	{
	460	unsigned long expires = jiffies + timeout;
	461
	462	if (expires == 0)
	463	expires = 1;
	464
	465	if (dst->expires == 0 \|\| time_before(expires, dst->expires))
	466	dst->expires = expires;
	467	}
	468
	469	/* Output packet to network from transport. */
13206b6b	470	static inline int dst_output(struct net net, struct sock sk, struct sk_buff *skb)
aad88724	471	{
ede2059d	472	return skb_dst(skb)->output(net, sk, skb);
aad88724	473	}
1da177e4 LT	474
	475	/* Input packet from network to transport. */
	476	static inline int dst_input(struct sk_buff *skb)
	477	{
adf30907	478	return skb_dst(skb)->input(skb);
1da177e4 LT	479	}
	480
	481	static inline struct dst_entry dst_check(struct dst_entry dst, u32 cookie)
	482	{
	483	if (dst->obsolete)
	484	dst = dst->ops->check(dst, cookie);
	485	return dst;
	486	}
	487
815f4e57 HX	488	/* Flags for xfrm_lookup flags argument. */
815f4e57 HX	489	enum {
80c0bc9e	490	XFRM_LOOKUP_ICMP = 1 << 0,
b8c203b2	491	XFRM_LOOKUP_QUEUE = 1 << 1,
ac37e251	492	XFRM_LOOKUP_KEEP_DST_REF = 1 << 2,
815f4e57 HX	493	};
815f4e57 HX	494
1da177e4 LT	495	struct flowi;
1da177e4 LT	496	#ifndef CONFIG_XFRM
452edd59 DM	497	static inline struct dst_entry xfrm_lookup(struct net net,
452edd59 DM	498	struct dst_entry *dst_orig,
6f9c9615 ED	499	const struct flowi *fl,
6f9c9615 ED	500	const struct sock *sk,
452edd59	501	int flags)
1da177e4	502	{
452edd59	503	return dst_orig;
f92ee619 SK	504	}
	505
	506	static inline struct dst_entry xfrm_lookup_route(struct net net,
	507	struct dst_entry *dst_orig,
	508	const struct flowi *fl,
6f9c9615	509	const struct sock *sk,
f92ee619 SK	510	int flags)
	511	{
	512	return dst_orig;
	513	}
e87b3998 VY	514
	515	static inline struct xfrm_state dst_xfrm(const struct dst_entry dst)
	516	{
	517	return NULL;
	518	}
	519
1da177e4	520	#else
a4023dd0	521	struct dst_entry xfrm_lookup(struct net net, struct dst_entry *dst_orig,
6f9c9615	522	const struct flowi fl, const struct sock sk,
a4023dd0	523	int flags);
e87b3998	524
f92ee619	525	struct dst_entry xfrm_lookup_route(struct net net, struct dst_entry *dst_orig,
6f9c9615	526	const struct flowi fl, const struct sock sk,
f92ee619 SK	527	int flags);
f92ee619 SK	528
e87b3998 VY	529	/* skb attached with this dst needs transformation if dst->xfrm is valid */
	530	static inline struct xfrm_state dst_xfrm(const struct dst_entry dst)
	531	{
	532	return dst->xfrm;
	533	}
1da177e4	534	#endif
1da177e4 LT	535
1da177e4 LT	536	#endif /* _NET_DST_H */