[linux-2.6-block.git] / include / net / dst.h

/* SPDX-License-Identifier: GPL-2.0 */
/*
 * 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 <linux/rcuref.h>
#include <net/neighbour.h>
#include <asm/processor.h>
#include <linux/indirect_call_wrapper.h>

struct sk_buff;

struct dst_entry {
	struct net_device       *dev;
	struct  dst_ops	        *ops;
	unsigned long		_metrics;
	unsigned long           expires;
#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_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

	/* 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 */

	/*
	 * __rcuref wants to be on a different cache line from
	 * input/output/ops or performance tanks badly
	 */
#ifdef CONFIG_64BIT
	rcuref_t		__rcuref;	/* 64-bit offset 64 */
#endif
	int			__use;
	unsigned long		lastuse;
	struct rcu_head		rcu_head;
	short			error;
	short			__pad;
	__u32			tclassid;
#ifndef CONFIG_64BIT
	struct lwtunnel_state   *lwtstate;
	rcuref_t		__rcuref;	/* 32-bit offset 64 */
#endif
	netdevice_tracker	dev_tracker;

	/*
	 * Used by rtable and rt6_info. Moves lwtstate into the next cache
	 * line on 64bit so that lwtstate does not cause false sharing with
	 * __rcuref under contention of __rcuref. This also puts the
	 * frequently accessed members of rtable and rt6_info out of the
	 * __rcuref cache line.
	 */
	struct list_head	rt_uncached;
	struct uncached_list	*rt_uncached_list;
#ifdef CONFIG_64BIT
	struct lwtunnel_state   *lwtstate;
#endif
};

struct dst_metrics {
	u32		metrics[RTAX_MAX];
	refcount_t	refcnt;
} __aligned(4);		/* Low pointer bits contain DST_METRICS_FLAGS */
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	(1U << 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;
}

INDIRECT_CALLABLE_DECLARE(unsigned int ip6_mtu(const struct dst_entry *));
INDIRECT_CALLABLE_DECLARE(unsigned int ipv4_mtu(const struct dst_entry *));
static inline u32 dst_mtu(const struct dst_entry *dst)
{
	return INDIRECT_CALL_INET(dst->ops->mtu, ip6_mtu, ipv4_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 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
	 * the placement of __rcuref in struct dst_entry
	 */
	BUILD_BUG_ON(offsetof(struct dst_entry, __rcuref) & 63);
	WARN_ON(!rcuref_get(&dst->__rcuref));
}

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

static inline struct dst_entry *dst_clone(struct dst_entry *dst)
{
	if (dst)
		dst_hold(dst);
	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->slow_gro |= !!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);
}

/**
 * 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 rcuref_get(&dst->__rcuref);
}

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

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

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

	return skb->_skb_refdst != 0UL;
}


/**
 *	__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
 *	@net: netns for packet i/o
 *
 *	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)
{
	DEV_STATS_INC(dev, rx_packets);
	DEV_STATS_ADD(dev, 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_obsolete, unsigned short flags);
void dst_init(struct dst_entry *dst, struct dst_ops *ops,
	      struct net_device *dev, 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;

	if (WARN_ON_ONCE(!dst->ops->neigh_lookup))
		return NULL;

	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;
}

INDIRECT_CALLABLE_DECLARE(int ip6_output(struct net *, struct sock *,
					 struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(int ip_output(struct net *, struct sock *,
					 struct sk_buff *));
/* Output packet to network from transport.  */
static inline int dst_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
	return INDIRECT_CALL_INET(skb_dst(skb)->output,
				  ip6_output, ip_output,
				  net, sk, skb);
}

INDIRECT_CALLABLE_DECLARE(int ip6_input(struct sk_buff *));
INDIRECT_CALLABLE_DECLARE(int ip_local_deliver(struct sk_buff *));
/* Input packet from network to transport.  */
static inline int dst_input(struct sk_buff *skb)
{
	return INDIRECT_CALL_INET(skb_dst(skb)->input,
				  ip6_input, ip_local_deliver, skb);
}

INDIRECT_CALLABLE_DECLARE(struct dst_entry *ip6_dst_check(struct dst_entry *,
							  u32));
INDIRECT_CALLABLE_DECLARE(struct dst_entry *ipv4_dst_check(struct dst_entry *,
							   u32));
static inline struct dst_entry *dst_check(struct dst_entry *dst, u32 cookie)
{
	if (dst->obsolete)
		dst = INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check,
					 ipv4_dst_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_with_ifid(struct net *net, struct dst_entry *dst_orig,
		      const struct flowi *fl, const struct sock *sk,
		      int flags, u32 if_id)
{
	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_with_ifid(struct net *net,
					struct dst_entry *dst_orig,
					const struct flowi *fl,
					const struct sock *sk, int flags,
					u32 if_id);

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

static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu)
{
	struct dst_entry *dst = skb_dst(skb);

	if (dst && dst->ops->update_pmtu)
		dst->ops->update_pmtu(dst, NULL, skb, mtu, true);
}

/* update dst pmtu but not do neighbor confirm */
static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu)
{
	struct dst_entry *dst = skb_dst(skb);

	if (dst && dst->ops->update_pmtu)
		dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
}

struct dst_entry *dst_blackhole_check(struct dst_entry *dst, u32 cookie);
void dst_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
			       struct sk_buff *skb, u32 mtu, bool confirm_neigh);
void dst_blackhole_redirect(struct dst_entry *dst, struct sock *sk,
			    struct sk_buff *skb);
u32 *dst_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old);
struct neighbour *dst_blackhole_neigh_lookup(const struct dst_entry *dst,
					     struct sk_buff *skb,
					     const void *daddr);
unsigned int dst_blackhole_mtu(const struct dst_entry *dst);

#endif /* _NET_DST_H */
Commit	Line	Data
b2441318	1	/* SPDX-License-Identifier: GPL-2.0 */
1da177e4 LT	2	/*
	3	* net/dst.h Protocol independent destination cache definitions.
	4	*
	5	* Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
	6	*
	7	*/
	8
	9	#ifndef _NET_DST_H
	10	#define _NET_DST_H
	11
86393e52	12	#include <net/dst_ops.h>
14c85021	13	#include <linux/netdevice.h>
1da177e4 LT	14	#include <linux/rtnetlink.h>
1da177e4 LT	15	#include <linux/rcupdate.h>
187f1882	16	#include <linux/bug.h>
1da177e4	17	#include <linux/jiffies.h>
9620fef2	18	#include <linux/refcount.h>
bc9d3a9f	19	#include <linux/rcuref.h>
1da177e4 LT	20	#include <net/neighbour.h>
1da177e4 LT	21	#include <asm/processor.h>
e43b2190	22	#include <linux/indirect_call_wrapper.h>
1da177e4	23
1da177e4 LT	24	struct sk_buff;
1da177e4 LT	25
fd2c3ef7	26	struct dst_entry {
66727145	27	struct net_device *dev;
62fa8a84 DM	28	struct dst_ops *ops;
62fa8a84 DM	29	unsigned long _metrics;
ecd98837	30	unsigned long expires;
def8b4fa	31	#ifdef CONFIG_XFRM
1da177e4	32	struct xfrm_state *xfrm;
5635c10d ED	33	#else
5635c10d ED	34	void *__pad1;
def8b4fa	35	#endif
7f95e188	36	int (input)(struct sk_buff );
ede2059d	37	int (output)(struct net net, struct sock sk, struct sk_buff skb);
1da177e4	38
5110effe	39	unsigned short flags;
f6b72b62 DM	40	#define DST_NOXFRM 0x0002
f6b72b62 DM	41	#define DST_NOPOLICY 0x0004
1eb04e7c WW	42	#define DST_NOCOUNT 0x0008
	43	#define DST_FAKE_RTABLE 0x0010
	44	#define DST_XFRM_TUNNEL 0x0020
	45	#define DST_XFRM_QUEUE 0x0040
	46	#define DST_METADATA 0x0080
f6b72b62	47
f5b0a874 DM	48	/* A non-zero value of dst->obsolete forces by-hand validation
	49	* of the route entry. Positive values are set by the generic
	50	* dst layer to indicate that the entry has been forcefully
	51	* destroyed.
	52	*
	53	* Negative values are used by the implementation layer code to
	54	* force invocation of the dst_ops->check() method.
	55	*/
62fa8a84	56	short obsolete;
f5b0a874 DM	57	#define DST_OBSOLETE_NONE 0
	58	#define DST_OBSOLETE_DEAD 2
	59	#define DST_OBSOLETE_FORCE_CHK -1
ceb33206	60	#define DST_OBSOLETE_KILL -2
62fa8a84 DM	61	unsigned short header_len; /* more space at head required */
62fa8a84 DM	62	unsigned short trailer_len; /* space to reserve at tail */
51ce8bd4	63
f1dd9c37	64	/*
bc9d3a9f	65	* __rcuref wants to be on a different cache line from
f1dd9c37 ZY	66	* input/output/ops or performance tanks badly
f1dd9c37 ZY	67	*/
8b207e73	68	#ifdef CONFIG_64BIT
bc9d3a9f	69	rcuref_t __rcuref; /* 64-bit offset 64 */
8b207e73	70	#endif
1e19e02c	71	int __use;
f1dd9c37	72	unsigned long lastuse;
8b207e73 DM	73	struct rcu_head rcu_head;
	74	short error;
	75	short __pad;
	76	__u32 tclassid;
	77	#ifndef CONFIG_64BIT
d288a162	78	struct lwtunnel_state *lwtstate;
bc9d3a9f	79	rcuref_t __rcuref; /* 32-bit offset 64 */
8b207e73	80	#endif
9038c320	81	netdevice_tracker dev_tracker;
d288a162 WG	82
	83	/*
	84	* Used by rtable and rt6_info. Moves lwtstate into the next cache
	85	* line on 64bit so that lwtstate does not cause false sharing with
bc9d3a9f	86	* __rcuref under contention of __rcuref. This also puts the
d288a162	87	* frequently accessed members of rtable and rt6_info out of the
bc9d3a9f	88	* __rcuref cache line.
d288a162 WG	89	*/
	90	struct list_head rt_uncached;
	91	struct uncached_list *rt_uncached_list;
	92	#ifdef CONFIG_64BIT
	93	struct lwtunnel_state *lwtstate;
	94	#endif
1da177e4 LT	95	};
1da177e4 LT	96
3fb07daf ED	97	struct dst_metrics {
3fb07daf ED	98	u32 metrics[RTAX_MAX];
9620fef2	99	refcount_t refcnt;
258a980d	100	} __aligned(4); /* Low pointer bits contain DST_METRICS_FLAGS */
3fb07daf ED	101	extern const struct dst_metrics dst_default_metrics;
3fb07daf ED	102
a4023dd0	103	u32 dst_cow_metrics_generic(struct dst_entry dst, unsigned long old);
62fa8a84	104
e5fd387a	105	#define DST_METRICS_READ_ONLY 0x1UL
3fb07daf	106	#define DST_METRICS_REFCOUNTED 0x2UL
e5fd387a	107	#define DST_METRICS_FLAGS 0x3UL
62fa8a84	108	#define __DST_METRICS_PTR(Y) \
e5fd387a	109	((u32 *)((Y) & ~DST_METRICS_FLAGS))
62fa8a84 DM	110	#define DST_METRICS_PTR(X) __DST_METRICS_PTR((X)->_metrics)
	111
	112	static inline bool dst_metrics_read_only(const struct dst_entry *dst)
	113	{
	114	return dst->_metrics & DST_METRICS_READ_ONLY;
	115	}
	116
a4023dd0	117	void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old);
62fa8a84 DM	118
	119	static inline void dst_destroy_metrics_generic(struct dst_entry *dst)
	120	{
	121	unsigned long val = dst->_metrics;
	122	if (!(val & DST_METRICS_READ_ONLY))
	123	__dst_destroy_metrics_generic(dst, val);
	124	}
	125
	126	static inline u32 dst_metrics_write_ptr(struct dst_entry dst)
	127	{
	128	unsigned long p = dst->_metrics;
	129
1f37070d SH	130	BUG_ON(!p);
1f37070d SH	131
62fa8a84 DM	132	if (p & DST_METRICS_READ_ONLY)
	133	return dst->ops->cow_metrics(dst, p);
	134	return __DST_METRICS_PTR(p);
	135	}
	136
	137	/* This may only be invoked before the entry has reached global
	138	* visibility.
	139	*/
	140	static inline void dst_init_metrics(struct dst_entry *dst,
	141	const u32 *src_metrics,
	142	bool read_only)
	143	{
	144	dst->_metrics = ((unsigned long) src_metrics) \|
	145	(read_only ? DST_METRICS_READ_ONLY : 0);
	146	}
	147
	148	static inline void dst_copy_metrics(struct dst_entry dest, const struct dst_entry src)
	149	{
	150	u32 *dst_metrics = dst_metrics_write_ptr(dest);
	151
	152	if (dst_metrics) {
	153	u32 *src_metrics = DST_METRICS_PTR(src);
	154
	155	memcpy(dst_metrics, src_metrics, RTAX_MAX * sizeof(u32));
	156	}
	157	}
	158
	159	static inline u32 dst_metrics_ptr(struct dst_entry dst)
	160	{
	161	return DST_METRICS_PTR(dst);
	162	}
	163
1da177e4	164	static inline u32
5170ae82	165	dst_metric_raw(const struct dst_entry *dst, const int metric)
1da177e4	166	{
62fa8a84 DM	167	u32 *p = DST_METRICS_PTR(dst);
	168
	169	return p[metric-1];
defb3519 DM	170	}
defb3519 DM	171
5170ae82 DM	172	static inline u32
	173	dst_metric(const struct dst_entry *dst, const int metric)
	174	{
0dbaee3b	175	WARN_ON_ONCE(metric == RTAX_HOPLIMIT \|\|
d33e4553 DM	176	metric == RTAX_ADVMSS \|\|
d33e4553 DM	177	metric == RTAX_MTU);
5170ae82 DM	178	return dst_metric_raw(dst, metric);
	179	}
	180
0dbaee3b DM	181	static inline u32
	182	dst_metric_advmss(const struct dst_entry *dst)
	183	{
	184	u32 advmss = dst_metric_raw(dst, RTAX_ADVMSS);
	185
	186	if (!advmss)
	187	advmss = dst->ops->default_advmss(dst);
	188
	189	return advmss;
	190	}
	191
defb3519 DM	192	static inline void dst_metric_set(struct dst_entry *dst, int metric, u32 val)
defb3519 DM	193	{
62fa8a84	194	u32 *p = dst_metrics_write_ptr(dst);
defb3519	195
62fa8a84 DM	196	if (p)
62fa8a84 DM	197	p[metric-1] = val;
1da177e4 LT	198	}
1da177e4 LT	199
c3a8d947	200	/* Kernel-internal feature bits that are unallocated in user space. */
40f6a2cb	201	#define DST_FEATURE_ECN_CA (1U << 31)
c3a8d947 DB	202
	203	#define DST_FEATURE_MASK (DST_FEATURE_ECN_CA)
	204	#define DST_FEATURE_ECN_MASK (DST_FEATURE_ECN_CA \| RTAX_FEATURE_ECN)
	205
0c3adfb8 GBY	206	static inline u32
	207	dst_feature(const struct dst_entry *dst, u32 feature)
	208	{
bb5b7c11	209	return dst_metric(dst, RTAX_FEATURES) & feature;
0c3adfb8 GBY	210	}
0c3adfb8 GBY	211
f67fbeae BV	212	INDIRECT_CALLABLE_DECLARE(unsigned int ip6_mtu(const struct dst_entry *));
f67fbeae BV	213	INDIRECT_CALLABLE_DECLARE(unsigned int ipv4_mtu(const struct dst_entry *));
1da177e4 LT	214	static inline u32 dst_mtu(const struct dst_entry *dst)
1da177e4 LT	215	{
f67fbeae	216	return INDIRECT_CALL_INET(dst->ops->mtu, ip6_mtu, ipv4_mtu, dst);
1da177e4 LT	217	}
1da177e4 LT	218
c1e20f7c SH	219	/* RTT metrics are stored in milliseconds for user ABI, but used as jiffies */
	220	static inline unsigned long dst_metric_rtt(const struct dst_entry *dst, int metric)
	221	{
	222	return msecs_to_jiffies(dst_metric(dst, metric));
	223	}
	224
1da177e4	225	static inline int
d33e4553	226	dst_metric_locked(const struct dst_entry *dst, int metric)
1da177e4	227	{
5af68891	228	return dst_metric(dst, RTAX_LOCK) & (1 << metric);
1da177e4 LT	229	}
1da177e4 LT	230
7f95e188	231	static inline void dst_hold(struct dst_entry *dst)
1da177e4	232	{
5635c10d ED	233	/*
5635c10d ED	234	* If your kernel compilation stops here, please check
bc9d3a9f	235	* the placement of __rcuref in struct dst_entry
5635c10d	236	*/
bc9d3a9f TG	237	BUILD_BUG_ON(offsetof(struct dst_entry, __rcuref) & 63);
bc9d3a9f TG	238	WARN_ON(!rcuref_get(&dst->__rcuref));
1da177e4 LT	239	}
1da177e4 LT	240
0da4af00	241	static inline void dst_use_noref(struct dst_entry *dst, unsigned long time)
03f49f34	242	{
32d18ab1	243	if (unlikely(time != dst->lastuse)) {
0da4af00 WW	244	dst->__use++;
	245	dst->lastuse = time;
	246	}
03f49f34 PE	247	}
03f49f34 PE	248
7f95e188	249	static inline struct dst_entry dst_clone(struct dst_entry dst)
1da177e4 LT	250	{
1da177e4 LT	251	if (dst)
222d7dbd	252	dst_hold(dst);
1da177e4 LT	253	return dst;
	254	}
	255
a4023dd0	256	void dst_release(struct dst_entry *dst);
7fee226a	257
5f56f409 WW	258	void dst_release_immediate(struct dst_entry *dst);
5f56f409 WW	259
7fee226a ED	260	static inline void refdst_drop(unsigned long refdst)
	261	{
	262	if (!(refdst & SKB_DST_NOREF))
	263	dst_release((struct dst_entry *)(refdst & SKB_DST_PTRMASK));
	264	}
	265
	266	/**
	267	* skb_dst_drop - drops skb dst
	268	* @skb: buffer
	269	*
	270	* Drops dst reference count if a reference was taken.
	271	*/
adf30907 ED	272	static inline void skb_dst_drop(struct sk_buff *skb)
adf30907 ED	273	{
7fee226a ED	274	if (skb->_skb_refdst) {
	275	refdst_drop(skb->_skb_refdst);
	276	skb->_skb_refdst = 0UL;
	277	}
	278	}
	279
e79e2595	280	static inline void __skb_dst_copy(struct sk_buff *nskb, unsigned long refdst)
7fee226a	281	{
8a886b14	282	nskb->slow_gro \|= !!refdst;
e79e2595	283	nskb->_skb_refdst = refdst;
7fee226a ED	284	if (!(nskb->_skb_refdst & SKB_DST_NOREF))
	285	dst_clone(skb_dst(nskb));
	286	}
	287
e79e2595 JS	288	static inline void skb_dst_copy(struct sk_buff nskb, const struct sk_buff oskb)
	289	{
	290	__skb_dst_copy(nskb, oskb->_skb_refdst);
	291	}
	292
5037e9ef ED	293	/**
	294	* dst_hold_safe - Take a reference on a dst if possible
	295	* @dst: pointer to dst entry
	296	*
	297	* This helper returns false if it could not safely
	298	* take a reference on a dst.
	299	*/
	300	static inline bool dst_hold_safe(struct dst_entry *dst)
	301	{
bc9d3a9f	302	return rcuref_get(&dst->__rcuref);
5037e9ef ED	303	}
	304
	305	/**
222d7dbd	306	* skb_dst_force - makes sure skb dst is refcounted
5037e9ef ED	307	* @skb: buffer
	308	*
	309	* If dst is not yet refcounted and not destroyed, grab a ref on it.
b60a7738	310	* Returns true if dst is refcounted.
5037e9ef	311	*/
b60a7738	312	static inline bool skb_dst_force(struct sk_buff *skb)
5037e9ef ED	313	{
	314	if (skb_dst_is_noref(skb)) {
	315	struct dst_entry *dst = skb_dst(skb);
	316
222d7dbd	317	WARN_ON(!rcu_read_lock_held());
5037e9ef ED	318	if (!dst_hold_safe(dst))
	319	dst = NULL;
	320
	321	skb->_skb_refdst = (unsigned long)dst;
8a886b14	322	skb->slow_gro \|= !!dst;
5037e9ef	323	}
b60a7738 FW	324
b60a7738 FW	325	return skb->_skb_refdst != 0UL;
5037e9ef ED	326	}
5037e9ef ED	327
d19d56dd	328
290b895e ED	329	/**
	330	* __skb_tunnel_rx - prepare skb for rx reinsert
	331	* @skb: buffer
	332	* @dev: tunnel device
ea23192e	333	* @net: netns for packet i/o
290b895e ED	334	*
	335	* After decapsulation, packet is going to re-enter (netif_rx()) our stack,
	336	* so make some cleanups. (no accounting done)
	337	*/
ea23192e ND	338	static inline void __skb_tunnel_rx(struct sk_buff skb, struct net_device dev,
ea23192e ND	339	struct net *net)
290b895e ED	340	{
290b895e ED	341	skb->dev = dev;
bdeab991 TH	342
bdeab991 TH	343	/*
7539fadc	344	* Clear hash so that we can recalulate the hash for the
bdeab991 TH	345	* encapsulated packet, unless we have already determine the hash
	346	* over the L4 4-tuple.
	347	*/
7539fadc	348	skb_clear_hash_if_not_l4(skb);
290b895e	349	skb_set_queue_mapping(skb, 0);
ea23192e	350	skb_scrub_packet(skb, !net_eq(net, dev_net(dev)));
290b895e ED	351	}
290b895e ED	352
d19d56dd ED	353	/**
	354	* skb_tunnel_rx - prepare skb for rx reinsert
	355	* @skb: buffer
	356	* @dev: tunnel device
8eb1a859	357	* @net: netns for packet i/o
d19d56dd ED	358	*
	359	* After decapsulation, packet is going to re-enter (netif_rx()) our stack,
	360	* so make some cleanups, and perform accounting.
290b895e	361	* Note: this accounting is not SMP safe.
d19d56dd	362	*/
ea23192e ND	363	static inline void skb_tunnel_rx(struct sk_buff skb, struct net_device dev,
ea23192e ND	364	struct net *net)
d19d56dd	365	{
6c1c5097 ED	366	DEV_STATS_INC(dev, rx_packets);
6c1c5097 ED	367	DEV_STATS_ADD(dev, rx_bytes, skb->len);
ea23192e	368	__skb_tunnel_rx(skb, dev, net);
d19d56dd ED	369	}
d19d56dd ED	370
808c1b69 DB	371	static inline u32 dst_tclassid(const struct sk_buff *skb)
	372	{
	373	#ifdef CONFIG_IP_ROUTE_CLASSID
	374	const struct dst_entry *dst;
	375
	376	dst = skb_dst(skb);
	377	if (dst)
	378	return dst->tclassid;
	379	#endif
	380	return 0;
	381	}
	382
ede2059d	383	int dst_discard_out(struct net net, struct sock sk, struct sk_buff *skb);
aad88724 ED	384	static inline int dst_discard(struct sk_buff *skb)
aad88724 ED	385	{
ede2059d	386	return dst_discard_out(&init_net, skb->sk, skb);
aad88724	387	}
762c8dc7	388	void dst_alloc(struct dst_ops ops, struct net_device *dev,
a4023dd0	389	int initial_obsolete, unsigned short flags);
f38a9eb1	390	void dst_init(struct dst_entry dst, struct dst_ops ops,
762c8dc7	391	struct net_device *dev, int initial_obsolete,
f38a9eb1	392	unsigned short flags);
a4023dd0	393	struct dst_entry dst_destroy(struct dst_entry dst);
4a6ce2b6	394	void dst_dev_put(struct dst_entry *dst);
1da177e4	395
1da177e4 LT	396	static inline void dst_confirm(struct dst_entry *dst)
1da177e4 LT	397	{
5110effe	398	}
f2c31e32	399
d3aaeb38 DM	400	static inline struct neighbour dst_neigh_lookup(const struct dst_entry dst, const void *daddr)
d3aaeb38 DM	401	{
aaa0c23c ZZ	402	struct neighbour *n = dst->ops->neigh_lookup(dst, NULL, daddr);
aaa0c23c ZZ	403	return IS_ERR(n) ? NULL : n;
f894cbf8 DM	404	}
	405
	406	static inline struct neighbour dst_neigh_lookup_skb(const struct dst_entry dst,
	407	struct sk_buff *skb)
	408	{
0992d67b	409	struct neighbour *n;
394de110	410
0992d67b GN	411	if (WARN_ON_ONCE(!dst->ops->neigh_lookup))
	412	return NULL;
	413
	414	n = dst->ops->neigh_lookup(dst, skb, NULL);
394de110	415
aaa0c23c	416	return IS_ERR(n) ? NULL : n;
d3aaeb38 DM	417	}
d3aaeb38 DM	418
63fca65d JA	419	static inline void dst_confirm_neigh(const struct dst_entry *dst,
	420	const void *daddr)
	421	{
	422	if (dst->ops->confirm_neigh)
	423	dst->ops->confirm_neigh(dst, daddr);
	424	}
	425
1da177e4 LT	426	static inline void dst_link_failure(struct sk_buff *skb)
1da177e4 LT	427	{
adf30907	428	struct dst_entry *dst = skb_dst(skb);
1da177e4 LT	429	if (dst && dst->ops && dst->ops->link_failure)
	430	dst->ops->link_failure(skb);
	431	}
	432
	433	static inline void dst_set_expires(struct dst_entry *dst, int timeout)
	434	{
	435	unsigned long expires = jiffies + timeout;
	436
	437	if (expires == 0)
	438	expires = 1;
	439
	440	if (dst->expires == 0 \|\| time_before(expires, dst->expires))
	441	dst->expires = expires;
	442	}
	443
6585d7dc BV	444	INDIRECT_CALLABLE_DECLARE(int ip6_output(struct net , struct sock ,
	445	struct sk_buff *));
	446	INDIRECT_CALLABLE_DECLARE(int ip_output(struct net , struct sock ,
	447	struct sk_buff *));
1da177e4	448	/* Output packet to network from transport. */
13206b6b	449	static inline int dst_output(struct net net, struct sock sk, struct sk_buff *skb)
aad88724	450	{
6585d7dc BV	451	return INDIRECT_CALL_INET(skb_dst(skb)->output,
	452	ip6_output, ip_output,
	453	net, sk, skb);
aad88724	454	}
1da177e4	455
e43b2190 BV	456	INDIRECT_CALLABLE_DECLARE(int ip6_input(struct sk_buff *));
e43b2190 BV	457	INDIRECT_CALLABLE_DECLARE(int ip_local_deliver(struct sk_buff *));
1da177e4 LT	458	/* Input packet from network to transport. */
	459	static inline int dst_input(struct sk_buff *skb)
	460	{
e43b2190 BV	461	return INDIRECT_CALL_INET(skb_dst(skb)->input,
e43b2190 BV	462	ip6_input, ip_local_deliver, skb);
1da177e4 LT	463	}
1da177e4 LT	464
bbd807df BV	465	INDIRECT_CALLABLE_DECLARE(struct dst_entry ip6_dst_check(struct dst_entry ,
	466	u32));
	467	INDIRECT_CALLABLE_DECLARE(struct dst_entry ipv4_dst_check(struct dst_entry ,
	468	u32));
1da177e4 LT	469	static inline struct dst_entry dst_check(struct dst_entry dst, u32 cookie)
	470	{
	471	if (dst->obsolete)
bbd807df BV	472	dst = INDIRECT_CALL_INET(dst->ops->check, ip6_dst_check,
bbd807df BV	473	ipv4_dst_check, dst, cookie);
1da177e4 LT	474	return dst;
	475	}
	476
815f4e57 HX	477	/* Flags for xfrm_lookup flags argument. */
815f4e57 HX	478	enum {
80c0bc9e	479	XFRM_LOOKUP_ICMP = 1 << 0,
b8c203b2	480	XFRM_LOOKUP_QUEUE = 1 << 1,
ac37e251	481	XFRM_LOOKUP_KEEP_DST_REF = 1 << 2,
815f4e57 HX	482	};
815f4e57 HX	483
1da177e4 LT	484	struct flowi;
1da177e4 LT	485	#ifndef CONFIG_XFRM
452edd59 DM	486	static inline struct dst_entry xfrm_lookup(struct net net,
452edd59 DM	487	struct dst_entry *dst_orig,
6f9c9615 ED	488	const struct flowi *fl,
6f9c9615 ED	489	const struct sock *sk,
452edd59	490	int flags)
1da177e4	491	{
452edd59	492	return dst_orig;
f92ee619 SK	493	}
f92ee619 SK	494
bc56b334 BW	495	static inline struct dst_entry *
	496	xfrm_lookup_with_ifid(struct net net, struct dst_entry dst_orig,
	497	const struct flowi fl, const struct sock sk,
	498	int flags, u32 if_id)
	499	{
	500	return dst_orig;
	501	}
	502
f92ee619 SK	503	static inline struct dst_entry xfrm_lookup_route(struct net net,
	504	struct dst_entry *dst_orig,
	505	const struct flowi *fl,
6f9c9615	506	const struct sock *sk,
f92ee619 SK	507	int flags)
	508	{
	509	return dst_orig;
	510	}
e87b3998 VY	511
	512	static inline struct xfrm_state dst_xfrm(const struct dst_entry dst)
	513	{
	514	return NULL;
	515	}
	516
1da177e4	517	#else
a4023dd0	518	struct dst_entry xfrm_lookup(struct net net, struct dst_entry *dst_orig,
6f9c9615	519	const struct flowi fl, const struct sock sk,
a4023dd0	520	int flags);
e87b3998	521
bc56b334 BW	522	struct dst_entry xfrm_lookup_with_ifid(struct net net,
	523	struct dst_entry *dst_orig,
	524	const struct flowi *fl,
	525	const struct sock *sk, int flags,
	526	u32 if_id);
	527
f92ee619	528	struct dst_entry xfrm_lookup_route(struct net net, struct dst_entry *dst_orig,
6f9c9615	529	const struct flowi fl, const struct sock sk,
f92ee619 SK	530	int flags);
f92ee619 SK	531
e87b3998 VY	532	/* skb attached with this dst needs transformation if dst->xfrm is valid */
	533	static inline struct xfrm_state dst_xfrm(const struct dst_entry dst)
	534	{
	535	return dst->xfrm;
	536	}
1da177e4	537	#endif
1da177e4	538
f15ca723 ND	539	static inline void skb_dst_update_pmtu(struct sk_buff *skb, u32 mtu)
	540	{
	541	struct dst_entry *dst = skb_dst(skb);
	542
	543	if (dst && dst->ops->update_pmtu)
bd085ef6	544	dst->ops->update_pmtu(dst, NULL, skb, mtu, true);
f15ca723 ND	545	}
f15ca723 ND	546
07dc35c6 HL	547	/* update dst pmtu but not do neighbor confirm */
	548	static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu)
	549	{
	550	struct dst_entry *dst = skb_dst(skb);
	551
	552	if (dst && dst->ops->update_pmtu)
	553	dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
	554	}
	555
c4c877b2 DB	556	struct dst_entry dst_blackhole_check(struct dst_entry dst, u32 cookie);
	557	void dst_blackhole_update_pmtu(struct dst_entry dst, struct sock sk,
	558	struct sk_buff *skb, u32 mtu, bool confirm_neigh);
	559	void dst_blackhole_redirect(struct dst_entry dst, struct sock sk,
	560	struct sk_buff *skb);
	561	u32 dst_blackhole_cow_metrics(struct dst_entry dst, unsigned long old);
	562	struct neighbour dst_blackhole_neigh_lookup(const struct dst_entry dst,
	563	struct sk_buff *skb,
	564	const void *daddr);
	565	unsigned int dst_blackhole_mtu(const struct dst_entry *dst);
	566
1da177e4	567	#endif /* _NET_DST_H */