结构体定义
struct net {
...
struct netns_ipv4 ipv4;
...
};
struct netns_ipv4 {
...
struct hlist_head *fib_table_hash; // 长度为FIB_TABLE_HASHSZ
...
};
struct fib_table {
struct hlist_node tb_hlist; // 用来将各个fib_table链成双向链表
u32 tb_id;
int tb_default;
int (*tb_lookup)(struct fib_table *tb, const struct flowi *flp, struct fib_result *res);
int (*tb_insert)(struct fib_table *, struct fib_config *);
int (*tb_delete)(struct fib_table *, struct fib_config *);
int (*tb_dump)(struct fib_table *table, struct sk_buff *skb,
struct netlink_callback *cb);
int (*tb_flush)(struct fib_table *table);
void (*tb_select_default)(struct fib_table *table,
const struct flowi *flp, struct fib_result *res);
unsigned char tb_data[0]; // fn_hash紧随其后
};
struct fn_hash {
struct fn_zone *fn_zones[33]; // 对应33个掩码长度（0-32）
struct fn_zone *fn_zone_list; // 非空fn_zone组成链表表头
};
// 一个fn_zone表示一个由同一掩码长度路由表项组成的集合
struct fn_zone {
struct fn_zone *fz_next; /* Next not empty zone */ // 用来将各个非空fn_zone链成链表
struct hlist_head *fz_hash; /* Hash table pointer */ // 长度为fz_divisor
int fz_nent; /* Number of entries */
int fz_divisor; /* Hash divisor */
u32 fz_hashmask; /* (fz_divisor - 1) */
#define FZ_HASHMASK(fz) ((fz)->fz_hashmask)
int fz_order; /* Zone order */ // 掩码长度
__be32 fz_mask; // 掩码
#define FZ_MASK(fz) ((fz)->fz_mask)
};
// 一个fib_node表示一个目的网段
struct fib_node {
struct hlist_node fn_hash; // 用来将各个fib_node链成双向链表
struct list_head fn_alias; // fib_alias组成链表表头
__be32 fn_key; // 目的网段
struct fib_alias fn_embedded_alias;
};
// 一个fib_alias表示一个路由表项
struct fib_alias {
struct list_head fa_list; // 用来将各个fib_alias链成链表
struct fib_info *fa_info; // 指向fib_info
u8 fa_tos;
u8 fa_type;
u8 fa_scope;
u8 fa_state;
#ifdef CONFIG_IP_FIB_TRIE
struct rcu_head rcu;
#endif
};
// 一个fib_info表示一个下一跳
struct fib_info {
struct hlist_node fib_hash;
struct hlist_node fib_lhash;
struct net *fib_net;
int fib_treeref;
atomic_t fib_clntref;
int fib_dead;
unsigned fib_flags;
int fib_protocol;
__be32 fib_prefsrc;
u32 fib_priority;
u32 fib_metrics[RTAX_MAX];
#define fib_mtu fib_metrics[RTAX_MTU-1]
#define fib_window fib_metrics[RTAX_WINDOW-1]
#define fib_rtt fib_metrics[RTAX_RTT-1]
#define fib_advmss fib_metrics[RTAX_ADVMSS-1]
int fib_nhs;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
int fib_power;
#endif
struct fib_nh fib_nh[0];
#define fib_dev fib_nh[0].nh_dev
};
struct fib_nh {
struct net_device *nh_dev;
struct hlist_node nh_hash;
struct fib_info *nh_parent;
unsigned nh_flags;
unsigned char nh_scope;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
int nh_weight;
int nh_power;
#endif
#ifdef CONFIG_NET_CLS_ROUTE
__u32 nh_tclassid;
#endif
int nh_oif;
__be32 nh_gw;
};
结构体图示
一个fib_alias表示一个路由表项，一个fib_node表示一个目的网段，一个fib_info表示一个下一跳
多个fib_alias可能共享一个fib_node，也可能共享一个fib_info
fib_alias插入fib_table过程
根据掩码长度决定fn_zone
根据目的网段决定fib_node
创建fib_alias并链入fib_node->fn_alias
初始化
fs_initcall() -> inet_init() -> ip_init() -> ip_rt_init() -> ip_fib_init()
void __init ip_fib_init(void)
{
rtnl_register(PF_INET, RTM_NEWROUTE, inet_rtm_newroute, NULL);
rtnl_register(PF_INET, RTM_DELROUTE, inet_rtm_delroute, NULL);
rtnl_register(PF_INET, RTM_GETROUTE, NULL, inet_dump_fib);
register_pernet_subsys(&fib_net_ops);
register_netdevice_notifier(&fib_netdev_notifier);
register_inetaddr_notifier(&fib_inetaddr_notifier);
fib_hash_init();
}
static struct pernet_operations fib_net_ops = {
.init = fib_net_init,
.exit = fib_net_exit,
};
int register_pernet_subsys(struct pernet_operations *ops)
{
int error;
mutex_lock(&net_mutex);
error = register_pernet_operations(first_device, ops);
mutex_unlock(&net_mutex);
return error;
}
static int register_pernet_operations(struct list_head *list,
struct pernet_operations *ops)
{
struct net *net, *undo_net;
int error;
list_add_tail(&ops->list, list);
if (ops->init) {
for_each_net(net) {
error = ops->init(net);
if (error)
goto out_undo;
}
}
return 0;
out_undo:
/* If I have an error cleanup all namespaces I initialized */
list_del(&ops->list);
if (ops->exit) {
for_each_net(undo_net) {
if (undo_net == net)
goto undone;
ops->exit(undo_net);
}
}
undone:
return error;
}
static int __net_init fib_net_init(struct net *net)
{
int error;
error = ip_fib_net_init(net);
if (error < 0)
goto out;
error = nl_fib_lookup_init(net);
if (error < 0)
goto out_nlfl;
error = fib_proc_init(net);
if (error < 0)
goto out_proc;
out:
return error;
out_proc:
nl_fib_lookup_exit(net);
out_nlfl:
ip_fib_net_exit(net);
goto out;
}
static int __net_init ip_fib_net_init(struct net *net)
{
int err;
unsigned int i;
// 分配fib_table_hash
net->ipv4.fib_table_hash = kzalloc(
sizeof(struct hlist_head)*FIB_TABLE_HASHSZ, GFP_KERNEL);
if (net->ipv4.fib_table_hash == NULL)
return -ENOMEM;
for (i = 0; i < FIB_TABLE_HASHSZ; i++)
INIT_HLIST_HEAD(&net->ipv4.fib_table_hash[i]);
err = fib4_rules_init(net); // 分配本地/主路由表
if (err < 0)
goto fail;
return 0;
fail:
kfree(net->ipv4.fib_table_hash);
return err;
}
static int __net_init fib4_rules_init(struct net *net)
{
struct fib_table *local_table, *main_table;
local_table = fib_hash_table(RT_TABLE_LOCAL); // 分配本地路由表（0）
if (local_table == NULL)
return -ENOMEM;
main_table = fib_hash_table(RT_TABLE_MAIN); // 分配主路由表（1）
if (main_table == NULL)
goto fail;
// 将fib_table链入fib_table_hash
hlist_add_head_rcu(&local_table->tb_hlist,
&net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX]);
hlist_add_head_rcu(&main_table->tb_hlist,
&net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]);
return 0;
fail:
kfree(local_table);
return -ENOMEM;
}
struct fib_table *fib_hash_table(u32 id)
{
struct fib_table *tb;
// 分配fib_table和fn_hash
tb = kmalloc(sizeof(struct fib_table) + sizeof(struct fn_hash),
GFP_KERNEL);
if (tb == NULL)
return NULL;
tb->tb_id = id;
tb->tb_default = -1;
tb->tb_lookup = fn_hash_lookup;
tb->tb_insert = fn_hash_insert;
tb->tb_delete = fn_hash_delete;
tb->tb_flush = fn_hash_flush;
tb->tb_select_default = fn_hash_select_default;
tb->tb_dump = fn_hash_dump;
memset(tb->tb_data, 0, sizeof(struct fn_hash));
return tb;
}
ip_route_input()
int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev)
{
struct rtable * rth;
unsigned hash;
int iif = dev->ifindex;
struct net *net;
net = dev_net(dev);
if (!rt_caching(net))
goto skip_cache;
tos &= IPTOS_RT_MASK;
hash = rt_hash(daddr, saddr, iif, rt_genid(net));
rcu_read_lock();
for (rth = rcu_dereference(rt_hash_table[hash].chain); rth;
rth = rcu_dereference(rth->u.dst.rt_next)) {
if (((rth->fl.fl4_dst ^ daddr) |
(rth->fl.fl4_src ^ saddr) |
(rth->fl.iif ^ iif) |
rth->fl.oif |
(rth->fl.fl4_tos ^ tos)) == 0 &&
rth->fl.mark == skb->mark &&
net_eq(dev_net(rth->u.dst.dev), net) &&
!rt_is_expired(rth)) { // 若查找到输入路由缓存
dst_use(&rth->u.dst, jiffies);
RT_CACHE_STAT_INC(in_hit);
rcu_read_unlock();
skb_dst_set(skb, &rth->u.dst); // 设置skb->_skb_dst
return 0;
}
RT_CACHE_STAT_INC(in_hlist_search);
}
rcu_read_unlock();
skip_cache:
/* Multicast recognition logic is moved from route cache to here.
The problem was that too many Ethernet cards have broken/missing
hardware multicast filters :-( As result the host on multicasting
network acquires a lot of useless route cache entries, sort of
SDR messages from all the world. Now we try to get rid of them.
Really, provided software IP multicast filter is organized
reasonably (at least, hashed), it does not result in a slowdown
comparing with route cache reject entries.
Note, that multicast routers are not affected, because
route cache entry is created eventually.
*/
if (ipv4_is_multicast(daddr)) {
struct in_device *in_dev;
rcu_read_lock();
if ((in_dev = __in_dev_get_rcu(dev)) != NULL) {
int our = ip_check_mc(in_dev, daddr, saddr,
ip_hdr(skb)->protocol);
if (our
#ifdef CONFIG_IP_MROUTE
|| (!ipv4_is_local_multicast(daddr) &&
IN_DEV_MFORWARD(in_dev))
#endif
) {
rcu_read_unlock();
return ip_route_input_mc(skb, daddr, saddr,
tos, dev, our);
}
}
rcu_read_unlock();
return -EINVAL;
}
return ip_route_input_slow(skb, daddr, saddr, tos, dev); // 调用ip_route_input_slow()
}
ip_route_input_slow()
根据fib_lookup()的查找结果设置rth->u.dst.input
static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr,
u8 tos, struct net_device *dev)
{
struct fib_result res;
struct in_device *in_dev = in_dev_get(dev);
struct flowi fl = { .nl_u = { .ip4_u =
{ .daddr = daddr,
.saddr = saddr,
.tos = tos,
.scope = RT_SCOPE_UNIVERSE,
} },
.mark = skb->mark,
.iif = dev->ifindex };
unsigned flags = 0;
u32 itag = 0;
struct rtable * rth;
unsigned hash;
__be32 spec_dst;
int err = -EINVAL;
int free_res = 0;
struct net * net = dev_net(dev);
/* IP on this device is disabled. */
if (!in_dev)
goto out;
/* Check for the most weird martians, which can be not detected
by fib_lookup.
*/
if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) ||
ipv4_is_loopback(saddr))
goto martian_source;
if (daddr == htonl(0xFFFFFFFF) || (saddr == 0 && daddr == 0))
goto brd_input;
/* Accept zero addresses only to limited broadcast;
* I even do not know to fix it or not. Waiting for complains :-)
*/
if (ipv4_is_zeronet(saddr))
goto martian_source;
if (ipv4_is_lbcast(daddr) || ipv4_is_zeronet(daddr) ||
ipv4_is_loopback(daddr))
goto martian_destination;
/*
* Now we are ready to route packet.
*/
if ((err = fib_lookup(net, &fl, &res)) != 0) { // 查找路由表
if (!IN_DEV_FORWARD(in_dev))
goto e_hostunreach;
goto no_route;
}
free_res = 1;
RT_CACHE_STAT_INC(in_slow_tot);
if (res.type == RTN_BROADCAST)
goto brd_input;
if (res.type == RTN_LOCAL) { // 若目的地址为本地地址，res.type由fib_alias的fa_type决定
int result;
result = fib_validate_source(saddr, daddr, tos,
net->loopback_dev->ifindex,
dev, &spec_dst, &itag, skb->mark);
if (result < 0)
goto martian_source;
if (result)
flags |= RTCF_DIRECTSRC;
spec_dst = daddr;
goto local_input; // 跳转到local_input
}
if (!IN_DEV_FORWARD(in_dev)) // 若禁止转发
goto e_hostunreach;
if (res.type != RTN_UNICAST) // 若目的地址不是单播
goto martian_destination;
err = ip_mkroute_input(skb, &res, &fl, in_dev, daddr, saddr, tos); // 调用ip_mkroute_input()
done:
in_dev_put(in_dev);
if (free_res)
fib_res_put(&res);
out: return err;
brd_input:
if (skb->protocol != htons(ETH_P_IP))
goto e_inval;
if (ipv4_is_zeronet(saddr))
spec_dst = inet_select_addr(dev, 0, RT_SCOPE_LINK);
else {
err = fib_validate_source(saddr, 0, tos, 0, dev, &spec_dst,
&itag, skb->mark);
if (err < 0)
goto martian_source;
if (err)
flags |= RTCF_DIRECTSRC;
}
flags |= RTCF_BROADCAST;
res.type = RTN_BROADCAST;
RT_CACHE_STAT_INC(in_brd);
local_input:
rth = dst_alloc(&ipv4_dst_ops);
if (!rth)
goto e_nobufs;
rth->u.dst.output= ip_rt_bug;
rth->rt_genid = rt_genid(net);
atomic_set(&rth->u.dst.__refcnt, 1);
rth->u.dst.flags= DST_HOST;
if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
rth->u.dst.flags |= DST_NOPOLICY;
rth->fl.fl4_dst = daddr;
rth->rt_dst = daddr;
rth->fl.fl4_tos = tos;
rth->fl.mark = skb->mark;
rth->fl.fl4_src = saddr;
rth->rt_src = saddr;
#ifdef CONFIG_NET_CLS_ROUTE
rth->u.dst.tclassid = itag;
#endif
rth->rt_iif =
rth->fl.iif = dev->ifindex;
rth->u.dst.dev = net->loopback_dev;
dev_hold(rth->u.dst.dev);
rth->idev = in_dev_get(rth->u.dst.dev);
rth->rt_gateway = daddr;
rth->rt_spec_dst= spec_dst;
rth->u.dst.input= ip_local_deliver; // 设置rth->u.dst.input
rth->rt_flags = flags|RTCF_LOCAL;
if (res.type == RTN_UNREACHABLE) {
rth->u.dst.input= ip_error;
rth->u.dst.error= -err;
rth->rt_flags &= ~RTCF_LOCAL;
}
rth->rt_type = res.type;
hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net));
err = rt_intern_hash(hash, rth, NULL, skb); // rt_intern_hash() -> skb_dst_set()
goto done;
no_route:
RT_CACHE_STAT_INC(in_no_route);
spec_dst = inet_select_addr(dev, 0, RT_SCOPE_UNIVERSE);
res.type = RTN_UNREACHABLE;
if (err == -ESRCH)
err = -ENETUNREACH;
goto local_input;
/*
* Do not cache martian addresses: they should be logged (RFC1812)
*/
martian_destination:
RT_CACHE_STAT_INC(in_martian_dst);
#ifdef CONFIG_IP_ROUTE_VERBOSE
if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit())
printk(KERN_WARNING "martian destination %pI4 from %pI4, dev %s\n",
&daddr, &saddr, dev->name);
#endif
e_hostunreach:
err = -EHOSTUNREACH;
goto done;
e_inval:
err = -EINVAL;
goto done;
e_nobufs:
err = -ENOBUFS;
goto done;
martian_source:
ip_handle_martian_source(dev, in_dev, skb, daddr, saddr);
goto e_inval;
}
ip_mkroute_input() -> __mkroute_input()
static int ip_mkroute_input(struct sk_buff *skb,
struct fib_result *res,
const struct flowi *fl,
struct in_device *in_dev,
__be32 daddr, __be32 saddr, u32 tos)
{
struct rtable* rth = NULL;
int err;
unsigned hash;
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (res->fi && res->fi->fib_nhs > 1 && fl->oif == 0)
fib_select_multipath(fl, res);
#endif
/* create a routing cache entry */
err = __mkroute_input(skb, res, in_dev, daddr, saddr, tos, &rth); // 调用__mkroute_input()
if (err)
return err;
/* put it into the cache */
hash = rt_hash(daddr, saddr, fl->iif,
rt_genid(dev_net(rth->u.dst.dev)));
return rt_intern_hash(hash, rth, NULL, skb); // rt_intern_hash() -> skb_dst_set()
}
static int __mkroute_input(struct sk_buff *skb,
struct fib_result *res,
struct in_device *in_dev,
__be32 daddr, __be32 saddr, u32 tos,
struct rtable **result)
{
struct rtable *rth;
int err;
struct in_device *out_dev;
unsigned flags = 0;
__be32 spec_dst;
u32 itag;
/* get a working reference to the output device */
out_dev = in_dev_get(FIB_RES_DEV(*res));
if (out_dev == NULL) {
if (net_ratelimit())
printk(KERN_CRIT "Bug in ip_route_input" \
"_slow(). Please, report\n");
return -EINVAL;
}
err = fib_validate_source(saddr, daddr, tos, FIB_RES_OIF(*res),
in_dev->dev, &spec_dst, &itag, skb->mark);
if (err < 0) {
ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr,
saddr);
err = -EINVAL;
goto cleanup;
}
if (err)
flags |= RTCF_DIRECTSRC;
if (out_dev == in_dev && err &&
(IN_DEV_SHARED_MEDIA(out_dev) ||
inet_addr_onlink(out_dev, saddr, FIB_RES_GW(*res))))
flags |= RTCF_DOREDIRECT;
if (skb->protocol != htons(ETH_P_IP)) {
/* Not IP (i.e. ARP). Do not create route, if it is
* invalid for proxy arp. DNAT routes are always valid.
*/
if (out_dev == in_dev) {
err = -EINVAL;
goto cleanup;
}
}
rth = dst_alloc(&ipv4_dst_ops);
if (!rth) {
err = -ENOBUFS;
goto cleanup;
}
atomic_set(&rth->u.dst.__refcnt, 1);
rth->u.dst.flags= DST_HOST;
if (IN_DEV_CONF_GET(in_dev, NOPOLICY))
rth->u.dst.flags |= DST_NOPOLICY;
if (IN_DEV_CONF_GET(out_dev, NOXFRM))
rth->u.dst.flags |= DST_NOXFRM;
rth->fl.fl4_dst = daddr;
rth->rt_dst = daddr;
rth->fl.fl4_tos = tos;
rth->fl.mark = skb->mark;
rth->fl.fl4_src = saddr;
rth->rt_src = saddr;
rth->rt_gateway = daddr;
rth->rt_iif =
rth->fl.iif = in_dev->dev->ifindex;
rth->u.dst.dev = (out_dev)->dev;
dev_hold(rth->u.dst.dev);
rth->idev = in_dev_get(rth->u.dst.dev);
rth->fl.oif = 0;
rth->rt_spec_dst= spec_dst;
rth->u.dst.input = ip_forward; // 设置rth->u.dst.input
rth->u.dst.output = ip_output; // 设置rth->u.dst.output
rth->rt_genid = rt_genid(dev_net(rth->u.dst.dev));
rt_set_nexthop(rth, res, itag);
rth->rt_flags = flags;
*result = rth;
err = 0;
cleanup:
/* release the working reference to the output device */
in_dev_put(out_dev);
return err;
}
fib_lookup() -> fn_hash_lookup() -> fib_semantic_match()
static inline int fib_lookup(struct net *net, const struct flowi *flp,
struct fib_result *res)
{
struct fib_table *table;
table = fib_get_table(net, RT_TABLE_LOCAL);
if (!table->tb_lookup(table, flp, res)) // 调用fn_hash_lookup()
return 0;
table = fib_get_table(net, RT_TABLE_MAIN);
if (!table->tb_lookup(table, flp, res))
return 0;
return -ENETUNREACH;
}
static int
fn_hash_lookup(struct fib_table *tb, const struct flowi *flp, struct fib_result *res)
{
int err;
struct fn_zone *fz;
struct fn_hash *t = (struct fn_hash *)tb->tb_data;
read_lock(&fib_hash_lock);
for (fz = t->fn_zone_list; fz; fz = fz->fz_next) { // 遍历非空fn_zone组成链表
struct hlist_head *head;
struct hlist_node *node;
struct fib_node *f;
__be32 k = fz_key(flp->fl4_dst, fz);
head = &fz->fz_hash[fn_hash(k, fz)];
hlist_for_each_entry(f, node, head, fn_hash) { // 遍历fib_node组成双向链表
if (f->fn_key != k)
continue;
err = fib_semantic_match(&f->fn_alias,
flp, res,
fz->fz_order); // 调用fib_semantic_match()
if (err <= 0)
goto out;
}
}
err = 1;
out:
read_unlock(&fib_hash_lock);
return err;
}
int fib_semantic_match(struct list_head *head, const struct flowi *flp,
struct fib_result *res, int prefixlen)
{
struct fib_alias *fa;
int nh_sel = 0;
list_for_each_entry_rcu(fa, head, fa_list) { // 遍历fib_alias组成链表
int err;
if (fa->fa_tos &&
fa->fa_tos != flp->fl4_tos)
continue;
if (fa->fa_scope < flp->fl4_scope)
continue;
fa->fa_state |= FA_S_ACCESSED;
err = fib_props[fa->fa_type].error;
if (err == 0) {
struct fib_info *fi = fa->fa_info;
if (fi->fib_flags & RTNH_F_DEAD)
continue;
switch (fa->fa_type) {
case RTN_UNICAST:
case RTN_LOCAL:
case RTN_BROADCAST:
case RTN_ANYCAST:
case RTN_MULTICAST:
for_nexthops(fi) {
if (nh->nh_flags&RTNH_F_DEAD)
continue;
if (!flp->oif || flp->oif == nh->nh_oif)
break;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (nhsel < fi->fib_nhs) {
nh_sel = nhsel;
goto out_fill_res;
}
#else
if (nhsel < 1) {
goto out_fill_res; // 跳转到out_fill_res
}
#endif
endfor_nexthops(fi);
continue;
default:
printk(KERN_WARNING "fib_semantic_match bad type %#x\n",
fa->fa_type);
return -EINVAL;
}
}
return err;
}
return 1;
out_fill_res:
res->prefixlen = prefixlen;
res->nh_sel = nh_sel;
res->type = fa->fa_type; // 设置res->type
res->scope = fa->fa_scope;
res->fi = fa->fa_info;
atomic_inc(&res->fi->fib_clntref);
return 0;
}
2559
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
