linux/include/net/ip6_tunnel.h
Alexander Lobakin 5832c4a77d ip_tunnel: convert __be16 tunnel flags to bitmaps
Historically, tunnel flags like TUNNEL_CSUM or TUNNEL_ERSPAN_OPT
have been defined as __be16. Now all of those 16 bits are occupied
and there's no more free space for new flags.
It can't be simply switched to a bigger container with no
adjustments to the values, since it's an explicit Endian storage,
and on LE systems (__be16)0x0001 equals to
(__be64)0x0001000000000000.
We could probably define new 64-bit flags depending on the
Endianness, i.e. (__be64)0x0001 on BE and (__be64)0x00010000... on
LE, but that would introduce an Endianness dependency and spawn a
ton of Sparse warnings. To mitigate them, all of those places which
were adjusted with this change would be touched anyway, so why not
define stuff properly if there's no choice.

Define IP_TUNNEL_*_BIT counterparts as a bit number instead of the
value already coded and a fistful of <16 <-> bitmap> converters and
helpers. The two flags which have a different bit position are
SIT_ISATAP_BIT and VTI_ISVTI_BIT, as they were defined not as
__cpu_to_be16(), but as (__force __be16), i.e. had different
positions on LE and BE. Now they both have strongly defined places.
Change all __be16 fields which were used to store those flags, to
IP_TUNNEL_DECLARE_FLAGS() -> DECLARE_BITMAP(__IP_TUNNEL_FLAG_NUM) ->
unsigned long[1] for now, and replace all TUNNEL_* occurrences to
their bitmap counterparts. Use the converters in the places which talk
to the userspace, hardware (NFP) or other hosts (GRE header). The rest
must explicitly use the new flags only. This must be done at once,
otherwise there will be too many conversions throughout the code in
the intermediate commits.
Finally, disable the old __be16 flags for use in the kernel code
(except for the two 'irregular' flags mentioned above), to prevent
any accidental (mis)use of them. For the userspace, nothing is
changed, only additions were made.

Most noticeable bloat-o-meter difference (.text):

vmlinux:	307/-1 (306)
gre.ko:		62/0 (62)
ip_gre.ko:	941/-217 (724)	[*]
ip_tunnel.ko:	390/-900 (-510)	[**]
ip_vti.ko:	138/0 (138)
ip6_gre.ko:	534/-18 (516)	[*]
ip6_tunnel.ko:	118/-10 (108)

[*] gre_flags_to_tnl_flags() grew, but still is inlined
[**] ip_tunnel_find() got uninlined, hence such decrease

The average code size increase in non-extreme case is 100-200 bytes
per module, mostly due to sizeof(long) > sizeof(__be16), as
%__IP_TUNNEL_FLAG_NUM is less than %BITS_PER_LONG and the compilers
are able to expand the majority of bitmap_*() calls here into direct
operations on scalars.

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2024-04-01 10:49:28 +01:00

171 lines
5.0 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _NET_IP6_TUNNEL_H
#define _NET_IP6_TUNNEL_H
#include <linux/ipv6.h>
#include <linux/netdevice.h>
#include <linux/if_tunnel.h>
#include <linux/ip6_tunnel.h>
#include <net/ip_tunnels.h>
#include <net/dst_cache.h>
#define IP6TUNNEL_ERR_TIMEO (30*HZ)
/* capable of sending packets */
#define IP6_TNL_F_CAP_XMIT 0x10000
/* capable of receiving packets */
#define IP6_TNL_F_CAP_RCV 0x20000
/* determine capability on a per-packet basis */
#define IP6_TNL_F_CAP_PER_PACKET 0x40000
struct __ip6_tnl_parm {
char name[IFNAMSIZ]; /* name of tunnel device */
int link; /* ifindex of underlying L2 interface */
__u8 proto; /* tunnel protocol */
__u8 encap_limit; /* encapsulation limit for tunnel */
__u8 hop_limit; /* hop limit for tunnel */
bool collect_md;
__be32 flowinfo; /* traffic class and flowlabel for tunnel */
__u32 flags; /* tunnel flags */
struct in6_addr laddr; /* local tunnel end-point address */
struct in6_addr raddr; /* remote tunnel end-point address */
IP_TUNNEL_DECLARE_FLAGS(i_flags);
IP_TUNNEL_DECLARE_FLAGS(o_flags);
__be32 i_key;
__be32 o_key;
__u32 fwmark;
__u32 index; /* ERSPAN type II index */
__u8 erspan_ver; /* ERSPAN version */
__u8 dir; /* direction */
__u16 hwid; /* hwid */
};
/* IPv6 tunnel */
struct ip6_tnl {
struct ip6_tnl __rcu *next; /* next tunnel in list */
struct net_device *dev; /* virtual device associated with tunnel */
netdevice_tracker dev_tracker;
struct net *net; /* netns for packet i/o */
struct __ip6_tnl_parm parms; /* tunnel configuration parameters */
struct flowi fl; /* flowi template for xmit */
struct dst_cache dst_cache; /* cached dst */
struct gro_cells gro_cells;
int err_count;
unsigned long err_time;
/* These fields used only by GRE */
__u32 i_seqno; /* The last seen seqno */
atomic_t o_seqno; /* The last output seqno */
int hlen; /* tun_hlen + encap_hlen */
int tun_hlen; /* Precalculated header length */
int encap_hlen; /* Encap header length (FOU,GUE) */
struct ip_tunnel_encap encap;
int mlink;
};
struct ip6_tnl_encap_ops {
size_t (*encap_hlen)(struct ip_tunnel_encap *e);
int (*build_header)(struct sk_buff *skb, struct ip_tunnel_encap *e,
u8 *protocol, struct flowi6 *fl6);
int (*err_handler)(struct sk_buff *skb, struct inet6_skb_parm *opt,
u8 type, u8 code, int offset, __be32 info);
};
#ifdef CONFIG_INET
extern const struct ip6_tnl_encap_ops __rcu *
ip6tun_encaps[MAX_IPTUN_ENCAP_OPS];
int ip6_tnl_encap_add_ops(const struct ip6_tnl_encap_ops *ops,
unsigned int num);
int ip6_tnl_encap_del_ops(const struct ip6_tnl_encap_ops *ops,
unsigned int num);
int ip6_tnl_encap_setup(struct ip6_tnl *t,
struct ip_tunnel_encap *ipencap);
static inline int ip6_encap_hlen(struct ip_tunnel_encap *e)
{
const struct ip6_tnl_encap_ops *ops;
int hlen = -EINVAL;
if (e->type == TUNNEL_ENCAP_NONE)
return 0;
if (e->type >= MAX_IPTUN_ENCAP_OPS)
return -EINVAL;
rcu_read_lock();
ops = rcu_dereference(ip6tun_encaps[e->type]);
if (likely(ops && ops->encap_hlen))
hlen = ops->encap_hlen(e);
rcu_read_unlock();
return hlen;
}
static inline int ip6_tnl_encap(struct sk_buff *skb, struct ip6_tnl *t,
u8 *protocol, struct flowi6 *fl6)
{
const struct ip6_tnl_encap_ops *ops;
int ret = -EINVAL;
if (t->encap.type == TUNNEL_ENCAP_NONE)
return 0;
if (t->encap.type >= MAX_IPTUN_ENCAP_OPS)
return -EINVAL;
rcu_read_lock();
ops = rcu_dereference(ip6tun_encaps[t->encap.type]);
if (likely(ops && ops->build_header))
ret = ops->build_header(skb, &t->encap, protocol, fl6);
rcu_read_unlock();
return ret;
}
/* Tunnel encapsulation limit destination sub-option */
struct ipv6_tlv_tnl_enc_lim {
__u8 type; /* type-code for option */
__u8 length; /* option length */
__u8 encap_limit; /* tunnel encapsulation limit */
} __packed;
int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
const struct in6_addr *raddr);
int ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst,
bool log_ecn_error);
int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
const struct in6_addr *raddr);
int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield,
struct flowi6 *fl6, int encap_limit, __u32 *pmtu, __u8 proto);
__u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw);
__u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr,
const struct in6_addr *raddr);
struct net *ip6_tnl_get_link_net(const struct net_device *dev);
int ip6_tnl_get_iflink(const struct net_device *dev);
int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu);
static inline void ip6tunnel_xmit(struct sock *sk, struct sk_buff *skb,
struct net_device *dev)
{
int pkt_len, err;
memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
pkt_len = skb->len - skb_inner_network_offset(skb);
err = ip6_local_out(dev_net(skb_dst(skb)->dev), sk, skb);
if (dev) {
if (unlikely(net_xmit_eval(err)))
pkt_len = -1;
iptunnel_xmit_stats(dev, pkt_len);
}
}
#endif
#endif