leandrof/linux
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'ipv6-Separate-data-structures-for-FIB-and-data-path'

Browse Source 
David Ahern says:

====================
net/ipv6: Separate data structures for FIB and data path

IPv6 uses the same data struct for both control plane (FIB entries) and
data path (dst entries). This struct has elements needed for both paths
adding memory overhead and complexity (taking a dst hold in most places
but an additional reference on rt6i_ref in a few). Furthermore, because
of the dst_alloc tie, all FIB entries are allocated with GFP_ATOMIC.

This patch set separates FIB entries from dst entries, better aligning
IPv6 code with IPv4, simplifying the reference counting and allowing
FIB entries added by userspace (not autoconf) to use GFP_KERNEL. It is
first step to a number of performance and scalability changes.

The end result of this patch set:
  - FIB entries (fib6_info):
        /* size: 208, cachelines: 4, members: 25 */
        /* sum members: 207, holes: 1, sum holes: 1 */

  - dst entries (rt6_info)
       /* size: 240, cachelines: 4, members: 11 */

Versus the the single rt6_info struct today for both paths:
      /* size: 320, cachelines: 5, members: 28 */

This amounts to a 35% reduction in memory use for FIB entries and a
25% reduction for dst entries.

With respect to locking FIB entries use RCU and a single atomic
counter with fib6_info_hold and fib6_info_release helpers to manage
the reference counting. dst entries use only the traditional dst
refcounts with dst_hold and dst_release.

FIB entries for host routes are referenced by inet6_ifaddr and
ifacaddr6. In both cases, additional holds are taken -- similar to
what is done for devices.

This set is the first of many changes to improve the scalability of the
IPv6 code. Follow on changes include:
- consolidating duplicate fib6_info references like IPv4 does with
  duplicate fib_info

- moving fib6_info into a slab cache to avoid allocation roundups to
  power of 2 (the 208 size becomes a 256 actual allocation)

- Allow FIB lookups without generating a dst (e.g., most rt6_lookup
  users just want to verify the egress device). Means moving dst
  allocation to the other side of fib6_rule_lookup which again aligns
  with IPv4 behavior

- using separate standalone nexthop objects which have performance
  benefits beyond fib_info consolidation

At this point I am not seeing any refcount leaks or underflows, no
oops or bug_ons, or warnings from kasan, so I think it is ready for
others to beat up on it finding errors in code paths I have missed.

v2 changes
- rebased to top of tree
- improved commit message on patch 7

v1 changes
- rebased to top of tree
- fix memory leak of metrics as noted by Ido
- MTU fixes based on pmtu tests (thanks Stefano Brivio for writing)

RFC v2 changes
- improved commit messages
- move common metrics code from dst.c to net/ipv4/metrics.c (comment
  from DaveM)
- address comments from Wei Wang and Martin KaFai Lau (let me know if
  I missed something)
- fixes detected by kernel test robots
  + added fib6_metric_set to change metric on a FIB entry which could
    be pointing to read-only dst_default_metrics
  + 0day testing found a problem with an intermediate patch; added
    dst_hold_safe on rt->from. Code is removed 3 patches later
- allow cacheinfo to handle NULL dst; means only expires is pushed to
  userspace
====================

Signed-off-by: David S. Miller <davem@davemloft.net>
This commit is contained in:
David S. Miller 2018-04-17 23:41:18 -04:00
commit 0565de29cb
19 changed files with 1221 additions and 1139 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

96
drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
View File

@ -442,7 +442,7 @@ struct mlxsw_sp_fib6_entry {
struct mlxsw_sp_rt6 {
struct list_head list;
struct rt6_info *rt;
struct fib6_info *rt;
};
struct mlxsw_sp_lpm_tree {
@ -2770,9 +2770,9 @@ mlxsw_sp_nexthop6_group_cmp(const struct mlxsw_sp_nexthop_group *nh_grp,
struct in6_addr *gw;
int ifindex, weight;
ifindex = mlxsw_sp_rt6->rt->dst.dev->ifindex;
weight = mlxsw_sp_rt6->rt->rt6i_nh_weight;
gw = &mlxsw_sp_rt6->rt->rt6i_gateway;
ifindex = mlxsw_sp_rt6->rt->fib6_nh.nh_dev->ifindex;
weight = mlxsw_sp_rt6->rt->fib6_nh.nh_weight;
gw = &mlxsw_sp_rt6->rt->fib6_nh.nh_gw;
if (!mlxsw_sp_nexthop6_group_has_nexthop(nh_grp, gw, ifindex,
weight))
return false;
@ -2838,7 +2838,7 @@ mlxsw_sp_nexthop6_group_hash(struct mlxsw_sp_fib6_entry *fib6_entry, u32 seed)
struct net_device *dev;
list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
dev = mlxsw_sp_rt6->rt->dst.dev;
dev = mlxsw_sp_rt6->rt->fib6_nh.nh_dev;
val ^= dev->ifindex;
}
@ -3834,11 +3834,11 @@ mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp,
for (i = 0; i < nh_grp->count; i++) {
struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i];
struct rt6_info *rt = mlxsw_sp_rt6->rt;
struct fib6_info *rt = mlxsw_sp_rt6->rt;
if (nh->rif && nh->rif->dev == rt->dst.dev &&
if (nh->rif && nh->rif->dev == rt->fib6_nh.nh_dev &&
ipv6_addr_equal((const struct in6_addr *) &nh->gw_addr,
&rt->rt6i_gateway))
&rt->fib6_nh.nh_gw))
return nh;
continue;
}
@ -3895,7 +3895,7 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL) {
list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6,
list)->rt->rt6i_nh_flags |= RTNH_F_OFFLOAD;
list)->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD;
return;
}
@ -3905,9 +3905,9 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry)
nh = mlxsw_sp_rt6_nexthop(nh_grp, mlxsw_sp_rt6);
if (nh && nh->offloaded)
mlxsw_sp_rt6->rt->rt6i_nh_flags |= RTNH_F_OFFLOAD;
mlxsw_sp_rt6->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD;
else
mlxsw_sp_rt6->rt->rt6i_nh_flags &= ~RTNH_F_OFFLOAD;
mlxsw_sp_rt6->rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD;
}
}
@ -3920,9 +3920,9 @@ mlxsw_sp_fib6_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry)
fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry,
common);
list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) {
struct rt6_info *rt = mlxsw_sp_rt6->rt;
struct fib6_info *rt = mlxsw_sp_rt6->rt;
rt->rt6i_nh_flags &= ~RTNH_F_OFFLOAD;
rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD;
}
}
@ -4699,7 +4699,7 @@ static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp,
mlxsw_sp_fib_node_put(mlxsw_sp, fib_node);
}
static bool mlxsw_sp_fib6_rt_should_ignore(const struct rt6_info *rt)
static bool mlxsw_sp_fib6_rt_should_ignore(const struct fib6_info *rt)
{
/* Packets with link-local destination IP arriving to the router
* are trapped to the CPU, so no need to program specific routes
@ -4721,7 +4721,7 @@ static bool mlxsw_sp_fib6_rt_should_ignore(const struct rt6_info *rt)
return false;
}
static struct mlxsw_sp_rt6 *mlxsw_sp_rt6_create(struct rt6_info *rt)
static struct mlxsw_sp_rt6 *mlxsw_sp_rt6_create(struct fib6_info *rt)
{
struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
@ -4734,18 +4734,18 @@ static struct mlxsw_sp_rt6 *mlxsw_sp_rt6_create(struct rt6_info *rt)
* memory.
*/
mlxsw_sp_rt6->rt = rt;
rt6_hold(rt);
fib6_info_hold(rt);
return mlxsw_sp_rt6;
}
#if IS_ENABLED(CONFIG_IPV6)
static void mlxsw_sp_rt6_release(struct rt6_info *rt)
static void mlxsw_sp_rt6_release(struct fib6_info *rt)
{
rt6_release(rt);
fib6_info_release(rt);
}
#else
static void mlxsw_sp_rt6_release(struct rt6_info *rt)
static void mlxsw_sp_rt6_release(struct fib6_info *rt)
{
}
#endif
@ -4756,13 +4756,13 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6)
kfree(mlxsw_sp_rt6);
}
static bool mlxsw_sp_fib6_rt_can_mp(const struct rt6_info *rt)
static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt)
{
/* RTF_CACHE routes are ignored */
return (rt->rt6i_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY;
}
static struct rt6_info *
static struct fib6_info *
mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry)
{
return list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6,
@ -4771,7 +4771,7 @@ mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry)
static struct mlxsw_sp_fib6_entry *
mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node,
const struct rt6_info *nrt, bool replace)
const struct fib6_info *nrt, bool replace)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
@ -4779,7 +4779,7 @@ mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node,
return NULL;
list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) {
struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
/* RT6_TABLE_LOCAL and RT6_TABLE_MAIN share the same
* virtual router.
@ -4802,7 +4802,7 @@ mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node,
static struct mlxsw_sp_rt6 *
mlxsw_sp_fib6_entry_rt_find(const struct mlxsw_sp_fib6_entry *fib6_entry,
const struct rt6_info *rt)
const struct fib6_info *rt)
{
struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
@ -4815,21 +4815,21 @@ mlxsw_sp_fib6_entry_rt_find(const struct mlxsw_sp_fib6_entry *fib6_entry,
}
static bool mlxsw_sp_nexthop6_ipip_type(const struct mlxsw_sp *mlxsw_sp,
const struct rt6_info *rt,
const struct fib6_info *rt,
enum mlxsw_sp_ipip_type *ret)
{
return rt->dst.dev &&
mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->dst.dev, ret);
return rt->fib6_nh.nh_dev &&
mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->fib6_nh.nh_dev, ret);
}
static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop_group *nh_grp,
struct mlxsw_sp_nexthop *nh,
const struct rt6_info *rt)
const struct fib6_info *rt)
{
const struct mlxsw_sp_ipip_ops *ipip_ops;
struct mlxsw_sp_ipip_entry *ipip_entry;
struct net_device *dev = rt->dst.dev;
struct net_device *dev = rt->fib6_nh.nh_dev;
struct mlxsw_sp_rif *rif;
int err;
@ -4870,13 +4870,13 @@ static void mlxsw_sp_nexthop6_type_fini(struct mlxsw_sp *mlxsw_sp,
static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_nexthop_group *nh_grp,
struct mlxsw_sp_nexthop *nh,
const struct rt6_info *rt)
const struct fib6_info *rt)
{
struct net_device *dev = rt->dst.dev;
struct net_device *dev = rt->fib6_nh.nh_dev;
nh->nh_grp = nh_grp;
nh->nh_weight = rt->rt6i_nh_weight;
memcpy(&nh->gw_addr, &rt->rt6i_gateway, sizeof(nh->gw_addr));
nh->nh_weight = rt->fib6_nh.nh_weight;
memcpy(&nh->gw_addr, &rt->fib6_nh.nh_gw, sizeof(nh->gw_addr));
mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh);
list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list);
@ -4897,7 +4897,7 @@ static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp,
}
static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp,
const struct rt6_info *rt)
const struct fib6_info *rt)
{
return rt->rt6i_flags & RTF_GATEWAY ||
mlxsw_sp_nexthop6_ipip_type(mlxsw_sp, rt, NULL);
@ -4928,7 +4928,7 @@ mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp,
nh_grp->gateway = mlxsw_sp_rt6_is_gateway(mlxsw_sp, mlxsw_sp_rt6->rt);
nh_grp->count = fib6_entry->nrt6;
for (i = 0; i < nh_grp->count; i++) {
struct rt6_info *rt = mlxsw_sp_rt6->rt;
struct fib6_info *rt = mlxsw_sp_rt6->rt;
nh = &nh_grp->nexthops[i];
err = mlxsw_sp_nexthop6_init(mlxsw_sp, nh_grp, nh, rt);
@ -5040,7 +5040,7 @@ err_nexthop6_group_get:
static int
mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib6_entry *fib6_entry,
struct rt6_info *rt)
struct fib6_info *rt)
{
struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
int err;
@ -5068,7 +5068,7 @@ err_nexthop6_group_update:
static void
mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib6_entry *fib6_entry,
struct rt6_info *rt)
struct fib6_info *rt)
{
struct mlxsw_sp_rt6 *mlxsw_sp_rt6;
@ -5084,7 +5084,7 @@ mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp,
static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_entry *fib_entry,
const struct rt6_info *rt)
const struct fib6_info *rt)
{
/* Packets hitting RTF_REJECT routes need to be discarded by the
* stack. We can rely on their destination device not having a
@ -5118,7 +5118,7 @@ mlxsw_sp_fib6_entry_rt_destroy_all(struct mlxsw_sp_fib6_entry *fib6_entry)
static struct mlxsw_sp_fib6_entry *
mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp,
struct mlxsw_sp_fib_node *fib_node,
struct rt6_info *rt)
struct fib6_info *rt)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
struct mlxsw_sp_fib_entry *fib_entry;
@ -5168,12 +5168,12 @@ static void mlxsw_sp_fib6_entry_destroy(struct mlxsw_sp *mlxsw_sp,
static struct mlxsw_sp_fib6_entry *
mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node,
const struct rt6_info *nrt, bool replace)
const struct fib6_info *nrt, bool replace)
{
struct mlxsw_sp_fib6_entry *fib6_entry, *fallback = NULL;
list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) {
struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
if (rt->rt6i_table->tb6_id > nrt->rt6i_table->tb6_id)
continue;
@ -5198,7 +5198,7 @@ mlxsw_sp_fib6_node_list_insert(struct mlxsw_sp_fib6_entry *new6_entry,
bool replace)
{
struct mlxsw_sp_fib_node *fib_node = new6_entry->common.fib_node;
struct rt6_info *nrt = mlxsw_sp_fib6_entry_rt(new6_entry);
struct fib6_info *nrt = mlxsw_sp_fib6_entry_rt(new6_entry);
struct mlxsw_sp_fib6_entry *fib6_entry;
fib6_entry = mlxsw_sp_fib6_node_entry_find(fib_node, nrt, replace);
@ -5213,7 +5213,7 @@ mlxsw_sp_fib6_node_list_insert(struct mlxsw_sp_fib6_entry *new6_entry,
struct mlxsw_sp_fib6_entry *last;
list_for_each_entry(last, &fib_node->entry_list, common.list) {
struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(last);
struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(last);
if (nrt->rt6i_table->tb6_id > rt->rt6i_table->tb6_id)
break;
@ -5268,7 +5268,7 @@ mlxsw_sp_fib6_node_entry_unlink(struct mlxsw_sp *mlxsw_sp,
static struct mlxsw_sp_fib6_entry *
mlxsw_sp_fib6_entry_lookup(struct mlxsw_sp *mlxsw_sp,
const struct rt6_info *rt)
const struct fib6_info *rt)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
struct mlxsw_sp_fib_node *fib_node;
@ -5287,7 +5287,7 @@ mlxsw_sp_fib6_entry_lookup(struct mlxsw_sp *mlxsw_sp,
return NULL;
list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) {
struct rt6_info *iter_rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
struct fib6_info *iter_rt = mlxsw_sp_fib6_entry_rt(fib6_entry);
if (rt->rt6i_table->tb6_id == iter_rt->rt6i_table->tb6_id &&
rt->rt6i_metric == iter_rt->rt6i_metric &&
@ -5316,7 +5316,7 @@ static void mlxsw_sp_fib6_entry_replace(struct mlxsw_sp *mlxsw_sp,
}
static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp,
struct rt6_info *rt, bool replace)
struct fib6_info *rt, bool replace)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
struct mlxsw_sp_fib_node *fib_node;
@ -5373,7 +5373,7 @@ err_fib6_entry_nexthop_add:
}
static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp,
struct rt6_info *rt)
struct fib6_info *rt)
{
struct mlxsw_sp_fib6_entry *fib6_entry;
struct mlxsw_sp_fib_node *fib_node;
@ -5836,7 +5836,7 @@ static void mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work,
fen6_info = container_of(info, struct fib6_entry_notifier_info,
info);
fib_work->fen6_info = *fen6_info;
rt6_hold(fib_work->fen6_info.rt);
fib6_info_hold(fib_work->fen6_info.rt);
break;
}
}

25
drivers/net/vrf.c
View File

@ -48,6 +48,9 @@ static unsigned int vrf_net_id;
struct net_vrf {
struct rtable __rcu *rth;
struct rt6_info __rcu *rt6;
#if IS_ENABLED(CONFIG_IPV6)
struct fib6_table *fib6_table;
#endif
u32 tb_id;
};
@ -496,7 +499,6 @@ static int vrf_rt6_create(struct net_device *dev)
int flags = DST_HOST | DST_NOPOLICY | DST_NOXFRM;
struct net_vrf *vrf = netdev_priv(dev);
struct net *net = dev_net(dev);
struct fib6_table *rt6i_table;
struct rt6_info *rt6;
int rc = -ENOMEM;
@ -504,8 +506,8 @@ static int vrf_rt6_create(struct net_device *dev)
if (!ipv6_mod_enabled())
return 0;
rt6i_table = fib6_new_table(net, vrf->tb_id);
if (!rt6i_table)
vrf->fib6_table = fib6_new_table(net, vrf->tb_id);
if (!vrf->fib6_table)
goto out;
/* create a dst for routing packets out a VRF device */
@ -513,7 +515,6 @@ static int vrf_rt6_create(struct net_device *dev)
if (!rt6)
goto out;
rt6->rt6i_table = rt6i_table;
rt6->dst.output = vrf_output6;
rcu_assign_pointer(vrf->rt6, rt6);
@ -946,22 +947,8 @@ static struct rt6_info *vrf_ip6_route_lookup(struct net *net,
int flags)
{
struct net_vrf *vrf = netdev_priv(dev);
struct fib6_table *table = NULL;
struct rt6_info *rt6;
rcu_read_lock();
/* fib6_table does not have a refcnt and can not be freed */
rt6 = rcu_dereference(vrf->rt6);
if (likely(rt6))
table = rt6->rt6i_table;
rcu_read_unlock();
if (!table)
return NULL;
return ip6_pol_route(net, table, ifindex, fl6, skb, flags);
return ip6_pol_route(net, vrf->fib6_table, ifindex, fl6, skb, flags);
}
static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev,

4
include/net/if_inet6.h
View File

@ -64,7 +64,7 @@ struct inet6_ifaddr {
struct delayed_work dad_work;
struct inet6_dev *idev;
struct rt6_info *rt;
struct fib6_info *rt;
struct hlist_node addr_lst;
struct list_head if_list;
@ -144,7 +144,7 @@ struct ipv6_ac_socklist {
struct ifacaddr6 {
struct in6_addr aca_addr;
struct inet6_dev *aca_idev;
struct rt6_info *aca_rt;
struct fib6_info *aca_rt;
struct ifacaddr6 *aca_next;
int aca_users;
refcount_t aca_refcnt;

3
include/net/ip.h
View File

@ -396,6 +396,9 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU);
}
int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len,
u32 *metrics);
u32 ip_idents_reserve(u32 hash, int segs);
void __ip_select_ident(struct net *net, struct iphdr *iph, int segs);

155
include/net/ip6_fib.h
View File

@ -38,6 +38,7 @@
#endif
struct rt6_info;
struct fib6_info;
struct fib6_config {
u32 fc_table;
@ -74,12 +75,12 @@ struct fib6_node {
#ifdef CONFIG_IPV6_SUBTREES
struct fib6_node __rcu *subtree;
#endif
struct rt6_info __rcu *leaf;
struct fib6_info __rcu *leaf;
__u16 fn_bit; /* bit key */
__u16 fn_flags;
int fn_sernum;
struct rt6_info __rcu *rr_ptr;
struct fib6_info __rcu *rr_ptr;
struct rcu_head rcu;
};
@ -94,11 +95,6 @@ struct fib6_gc_args {
#define FIB6_SUBTREE(fn) (rcu_dereference_protected((fn)->subtree, 1))
#endif
struct mx6_config {
const u32 *mx;
DECLARE_BITMAP(mx_valid, RTAX_MAX);
};
/*
* routing information
*
@ -127,56 +123,72 @@ struct rt6_exception {
#define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT)
#define FIB6_MAX_DEPTH 5
struct rt6_info {
struct dst_entry dst;
struct rt6_info __rcu *rt6_next;
struct rt6_info *from;
struct fib6_nh {
struct in6_addr nh_gw;
struct net_device *nh_dev;
struct lwtunnel_state *nh_lwtstate;
/*
* Tail elements of dst_entry (__refcnt etc.)
* and these elements (rarely used in hot path) are in
* the same cache line.
*/
unsigned int nh_flags;
atomic_t nh_upper_bound;
int nh_weight;
};
struct fib6_info {
struct fib6_table *rt6i_table;
struct fib6_info __rcu *rt6_next;
struct fib6_node __rcu *rt6i_node;
struct in6_addr rt6i_gateway;
/* Multipath routes:
* siblings is a list of rt6_info that have the the same metric/weight,
* siblings is a list of fib6_info that have the the same metric/weight,
* destination, but not the same gateway. nsiblings is just a cache
* to speed up lookup.
*/
struct list_head rt6i_siblings;
unsigned int rt6i_nsiblings;
atomic_t rt6i_nh_upper_bound;
atomic_t rt6i_ref;
struct inet6_dev *rt6i_idev;
unsigned long expires;
struct dst_metrics *fib6_metrics;
#define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1]
unsigned int rt6i_nh_flags;
/* These are in a separate cache line. */
struct rt6key rt6i_dst ____cacheline_aligned_in_smp;
struct rt6key rt6i_dst;
u32 rt6i_flags;
struct rt6key rt6i_src;
struct rt6key rt6i_prefsrc;
struct rt6_info * __percpu *rt6i_pcpu;
struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
u32 rt6i_metric;
u8 rt6i_protocol;
u8 fib6_type;
u8 exception_bucket_flushed:1,
should_flush:1,
dst_nocount:1,
dst_nopolicy:1,
dst_host:1,
unused:3;
struct fib6_nh fib6_nh;
};
struct rt6_info {
struct dst_entry dst;
struct fib6_info *from;
struct rt6key rt6i_dst;
struct rt6key rt6i_src;
struct in6_addr rt6i_gateway;
struct inet6_dev *rt6i_idev;
u32 rt6i_flags;
struct rt6key rt6i_prefsrc;
struct list_head rt6i_uncached;
struct uncached_list *rt6i_uncached_list;
struct inet6_dev *rt6i_idev;
struct rt6_info * __percpu *rt6i_pcpu;
struct rt6_exception_bucket __rcu *rt6i_exception_bucket;
u32 rt6i_metric;
u32 rt6i_pmtu;
/* more non-fragment space at head required */
int rt6i_nh_weight;
unsigned short rt6i_nfheader_len;
u8 rt6i_protocol;
u8 exception_bucket_flushed:1,
should_flush:1,
unused:6;
};
#define for_each_fib6_node_rt_rcu(fn) \
@ -192,6 +204,26 @@ static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst)
return ((struct rt6_info *)dst)->rt6i_idev;
}
static inline void fib6_clean_expires(struct fib6_info *f6i)
{
f6i->rt6i_flags &= ~RTF_EXPIRES;
f6i->expires = 0;
}
static inline void fib6_set_expires(struct fib6_info *f6i,
unsigned long expires)
{
f6i->expires = expires;
f6i->rt6i_flags |= RTF_EXPIRES;
}
static inline bool fib6_check_expired(const struct fib6_info *f6i)
{
if (f6i->rt6i_flags & RTF_EXPIRES)
return time_after(jiffies, f6i->expires);
return false;
}
static inline void rt6_clean_expires(struct rt6_info *rt)
{
rt->rt6i_flags &= ~RTF_EXPIRES;
@ -206,11 +238,9 @@ static inline void rt6_set_expires(struct rt6_info *rt, unsigned long expires)
static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
{
struct rt6_info *rt;
if (!(rt0->rt6i_flags & RTF_EXPIRES) && rt0->from)
rt0->dst.expires = rt0->from->expires;
for (rt = rt0; rt && !(rt->rt6i_flags & RTF_EXPIRES); rt = rt->from);
if (rt && rt != rt0)
rt0->dst.expires = rt->dst.expires;
dst_set_expires(&rt0->dst, timeout);
rt0->rt6i_flags |= RTF_EXPIRES;
}
@ -220,7 +250,7 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout)
* Return true if we can get cookie safely
* Return false if not
*/
static inline bool rt6_get_cookie_safe(const struct rt6_info *rt,
static inline bool rt6_get_cookie_safe(const struct fib6_info *rt,
u32 *cookie)
{
struct fib6_node *fn;
@ -246,9 +276,7 @@ static inline u32 rt6_get_cookie(const struct rt6_info *rt)
if (rt->rt6i_flags & RTF_PCPU ||
(unlikely(!list_empty(&rt->rt6i_uncached)) && rt->from))
rt = rt->from;
rt6_get_cookie_safe(rt, &cookie);
rt6_get_cookie_safe(rt->from, &cookie);
return cookie;
}
@ -262,20 +290,18 @@ static inline void ip6_rt_put(struct rt6_info *rt)
dst_release(&rt->dst);
}
void rt6_free_pcpu(struct rt6_info *non_pcpu_rt);
struct fib6_info *fib6_info_alloc(gfp_t gfp_flags);
void fib6_info_destroy(struct fib6_info *f6i);
static inline void rt6_hold(struct rt6_info *rt)
static inline void fib6_info_hold(struct fib6_info *f6i)
{
atomic_inc(&rt->rt6i_ref);
atomic_inc(&f6i->rt6i_ref);
}
static inline void rt6_release(struct rt6_info *rt)
static inline void fib6_info_release(struct fib6_info *f6i)
{
if (atomic_dec_and_test(&rt->rt6i_ref)) {
rt6_free_pcpu(rt);
dst_dev_put(&rt->dst);
dst_release(&rt->dst);
}
if (f6i && atomic_dec_and_test(&f6i->rt6i_ref))
fib6_info_destroy(f6i);
}
enum fib6_walk_state {
@ -291,7 +317,7 @@ enum fib6_walk_state {
struct fib6_walker {
struct list_head lh;
struct fib6_node *root, *node;
struct rt6_info *leaf;
struct fib6_info *leaf;
enum fib6_walk_state state;
unsigned int skip;
unsigned int count;
@ -355,7 +381,7 @@ typedef struct rt6_info *(*pol_lookup_t)(struct net *,
struct fib6_entry_notifier_info {
struct fib_notifier_info info; /* must be first */
struct rt6_info *rt;
struct fib6_info *rt;
};
/*
@ -377,15 +403,14 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
const struct in6_addr *saddr, int src_len,
bool exact_match);
void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg),
void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *arg),
void *arg);
int fib6_add(struct fib6_node *root, struct rt6_info *rt,
struct nl_info *info, struct mx6_config *mxc,
struct netlink_ext_ack *extack);
int fib6_del(struct rt6_info *rt, struct nl_info *info);
int fib6_add(struct fib6_node *root, struct fib6_info *rt,
struct nl_info *info, struct netlink_ext_ack *extack);
int fib6_del(struct fib6_info *rt, struct nl_info *info);
void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info,
void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info,
unsigned int flags);
void fib6_run_gc(unsigned long expires, struct net *net, bool force);
@ -408,8 +433,14 @@ void __net_exit fib6_notifier_exit(struct net *net);
unsigned int fib6_tables_seq_read(struct net *net);
int fib6_tables_dump(struct net *net, struct notifier_block *nb);
void fib6_update_sernum(struct rt6_info *rt);
void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt);
void fib6_update_sernum(struct net *net, struct fib6_info *rt);
void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt);
void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val);
static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric)
{
return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric));
}
#ifdef CONFIG_IPV6_MULTIPLE_TABLES
int fib6_rules_init(void);

45
include/net/ip6_route.h
View File

@ -66,7 +66,7 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr)
(IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK);
}
static inline bool rt6_qualify_for_ecmp(const struct rt6_info *rt)
static inline bool rt6_qualify_for_ecmp(const struct fib6_info *rt)
{
return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) ==
RTF_GATEWAY;
@ -100,22 +100,21 @@ void ip6_route_cleanup(void);
int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg);
int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack);
int ip6_ins_rt(struct rt6_info *);
int ip6_del_rt(struct rt6_info *);
int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags,
struct netlink_ext_ack *extack);
int ip6_ins_rt(struct net *net, struct fib6_info *rt);
int ip6_del_rt(struct net *net, struct fib6_info *rt);
void rt6_flush_exceptions(struct rt6_info *rt);
int rt6_remove_exception_rt(struct rt6_info *rt);
void rt6_age_exceptions(struct rt6_info *rt, struct fib6_gc_args *gc_args,
void rt6_flush_exceptions(struct fib6_info *rt);
void rt6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args,
unsigned long now);
static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt,
static inline int ip6_route_get_saddr(struct net *net, struct fib6_info *rt,
const struct in6_addr *daddr,
unsigned int prefs,
struct in6_addr *saddr)
{
struct inet6_dev *idev =
rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL;
struct inet6_dev *idev = rt ? rt->rt6i_idev : NULL;
int err = 0;
if (rt && rt->rt6i_prefsrc.plen)
@ -137,8 +136,9 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6);
void fib6_force_start_gc(struct net *net);
struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
const struct in6_addr *addr, bool anycast);
struct fib6_info *addrconf_dst_alloc(struct net *net, struct inet6_dev *idev,
const struct in6_addr *addr, bool anycast,
gfp_t gfp_flags);
struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
int flags);
@ -147,9 +147,11 @@ struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev,
* support functions for ND
*
*/
struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr,
struct fib6_info *rt6_get_dflt_router(struct net *net,
const struct in6_addr *addr,
struct net_device *dev);
struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr,
struct fib6_info *rt6_add_dflt_router(struct net *net,
const struct in6_addr *gwaddr,
struct net_device *dev, unsigned int pref);
void rt6_purge_dflt_routers(struct net *net);
@ -174,14 +176,14 @@ struct rt6_rtnl_dump_arg {
struct net *net;
};
int rt6_dump_route(struct rt6_info *rt, void *p_arg);
int rt6_dump_route(struct fib6_info *rt, void *p_arg);
void rt6_mtu_change(struct net_device *dev, unsigned int mtu);
void rt6_remove_prefsrc(struct inet6_ifaddr *ifp);
void rt6_clean_tohost(struct net *net, struct in6_addr *gateway);
void rt6_sync_up(struct net_device *dev, unsigned int nh_flags);
void rt6_disable_ip(struct net_device *dev, unsigned long event);
void rt6_sync_down_dev(struct net_device *dev, unsigned long event);
void rt6_multipath_rebalance(struct rt6_info *rt);
void rt6_multipath_rebalance(struct fib6_info *rt);
void rt6_uncached_list_add(struct rt6_info *rt);
void rt6_uncached_list_del(struct rt6_info *rt);
@ -269,12 +271,15 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt,
return daddr;
}
static inline bool rt6_duplicate_nexthop(struct rt6_info *a, struct rt6_info *b)
static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *b)
{
return a->dst.dev == b->dst.dev &&
return a->fib6_nh.nh_dev == b->fib6_nh.nh_dev &&
a->rt6i_idev == b->rt6i_idev &&
ipv6_addr_equal(&a->rt6i_gateway, &b->rt6i_gateway) &&
!lwtunnel_cmp_encap(a->dst.lwtstate, b->dst.lwtstate);
ipv6_addr_equal(&a->fib6_nh.nh_gw, &b->fib6_nh.nh_gw) &&
!lwtunnel_cmp_encap(a->fib6_nh.nh_lwtstate, b->fib6_nh.nh_lwtstate);
}
struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw,
struct net_device *dev, struct sk_buff *skb,
const void *daddr);
#endif

3
include/net/netns/ipv6.h
View File

@ -60,7 +60,8 @@ struct netns_ipv6 {
#endif
struct xt_table *ip6table_nat;
#endif
struct rt6_info *ip6_null_entry;
struct fib6_info *fib6_null_entry;
struct rt6_info *ip6_null_entry;
struct rt6_statistics *rt6_stats;
struct timer_list ip6_fib_timer;
struct hlist_head *fib_table_hash;

1
net/core/dst.c
View File

@ -58,6 +58,7 @@ const struct dst_metrics dst_default_metrics = {
*/
.refcnt = REFCOUNT_INIT(1),
};
EXPORT_SYMBOL(dst_default_metrics);
void dst_init(struct dst_entry *dst, struct dst_ops *ops,
struct net_device *dev, int initial_ref, int initial_obsolete,

8
net/core/rtnetlink.c
View File

@ -785,13 +785,15 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id,
long expires, u32 error)
{
struct rta_cacheinfo ci = {
.rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse),
.rta_used = dst->__use,
.rta_clntref = atomic_read(&(dst->__refcnt)),
.rta_error = error,
.rta_id = id,
};
if (dst) {
ci.rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse);
ci.rta_used = dst->__use;
ci.rta_clntref = atomic_read(&dst->__refcnt);
}
if (expires) {
unsigned long clock;

3
net/ipv4/Makefile
View File

@ -13,7 +13,8 @@ obj-y := route.o inetpeer.o protocol.o \
tcp_offload.o datagram.o raw.o udp.o udplite.o \
udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \
fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \
inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o
inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \
metrics.o
obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o
obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o

43
net/ipv4/fib_semantics.c
View File

@ -1019,47 +1019,8 @@ static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc)
static int
fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
{
bool ecn_ca = false;
struct nlattr *nla;
int remaining;
if (!cfg->fc_mx)
return 0;
nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) {
int type = nla_type(nla);
u32 val;
if (!type)
continue;
if (type > RTAX_MAX)
return -EINVAL;
if (type == RTAX_CC_ALGO) {
char tmp[TCP_CA_NAME_MAX];
nla_strlcpy(tmp, nla, sizeof(tmp));
val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
if (val == TCP_CA_UNSPEC)
return -EINVAL;
} else {
val = nla_get_u32(nla);
}
if (type == RTAX_ADVMSS && val > 65535 - 40)
val = 65535 - 40;
if (type == RTAX_MTU && val > 65535 - 15)
val = 65535 - 15;
if (type == RTAX_HOPLIMIT && val > 255)
val = 255;
if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
return -EINVAL;
fi->fib_metrics->metrics[type - 1] = val;
}
if (ecn_ca)
fi->fib_metrics->metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
return 0;
return ip_metrics_convert(fi->fib_net, cfg->fc_mx, cfg->fc_mx_len,
fi->fib_metrics->metrics);
}
struct fib_info *fib_create_info(struct fib_config *cfg,

53
net/ipv4/metrics.c Normal file
View File

@ -0,0 +1,53 @@
#include <linux/netlink.h>
#include <linux/rtnetlink.h>
#include <linux/types.h>
#include <net/ip.h>
#include <net/net_namespace.h>
#include <net/tcp.h>
int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len,
u32 *metrics)
{
bool ecn_ca = false;
struct nlattr *nla;
int remaining;
if (!fc_mx)
return 0;
nla_for_each_attr(nla, fc_mx, fc_mx_len, remaining) {
int type = nla_type(nla);
u32 val;
if (!type)
continue;
if (type > RTAX_MAX)
return -EINVAL;
if (type == RTAX_CC_ALGO) {
char tmp[TCP_CA_NAME_MAX];
nla_strlcpy(tmp, nla, sizeof(tmp));
val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca);
if (val == TCP_CA_UNSPEC)
return -EINVAL;
} else {
val = nla_get_u32(nla);
}
if (type == RTAX_ADVMSS && val > 65535 - 40)
val = 65535 - 40;
if (type == RTAX_MTU && val > 65535 - 15)
val = 65535 - 15;
if (type == RTAX_HOPLIMIT && val > 255)
val = 255;
if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
return -EINVAL;
metrics[type - 1] = val;
}
if (ecn_ca)
metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA;
return 0;
}
EXPORT_SYMBOL_GPL(ip_metrics_convert);

118
net/ipv6/addrconf.c
View File

@ -170,7 +170,7 @@ static void addrconf_type_change(struct net_device *dev,
unsigned long event);
static int addrconf_ifdown(struct net_device *dev, int how);
static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
int plen,
const struct net_device *dev,
u32 flags, u32 noflags);
@ -916,7 +916,6 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp)
pr_warn("Freeing alive inet6 address %p\n", ifp);
return;
}
ip6_rt_put(ifp->rt);
kfree_rcu(ifp, rcu);
}
@ -995,7 +994,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
gfp_t gfp_flags = can_block ? GFP_KERNEL : GFP_ATOMIC;
struct net *net = dev_net(idev->dev);
struct inet6_ifaddr *ifa = NULL;
struct rt6_info *rt = NULL;
struct fib6_info *rt = NULL;
int err = 0;
int addr_type = ipv6_addr_type(addr);
@ -1037,7 +1036,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
goto out;
}
rt = addrconf_dst_alloc(idev, addr, false);
rt = addrconf_dst_alloc(net, idev, addr, false, gfp_flags);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
rt = NULL;
@ -1046,7 +1045,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
if (net->ipv6.devconf_all->disable_policy ||
idev->cnf.disable_policy)
rt->dst.flags |= DST_NOPOLICY;
rt->dst_nopolicy = true;
neigh_parms_data_state_setall(idev->nd_parms);
@ -1102,8 +1101,8 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr,
inet6addr_notifier_call_chain(NETDEV_UP, ifa);
out:
if (unlikely(err < 0)) {
if (rt)
ip6_rt_put(rt);
fib6_info_release(rt);
if (ifa) {
if (ifa->idev)
in6_dev_put(ifa->idev);
@ -1179,7 +1178,7 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires)
static void
cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt)
{
struct rt6_info *rt;
struct fib6_info *rt;
rt = addrconf_get_prefix_route(&ifp->addr,
ifp->prefix_len,
@ -1187,11 +1186,11 @@ cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_r
0, RTF_GATEWAY | RTF_DEFAULT);
if (rt) {
if (del_rt)
ip6_del_rt(rt);
ip6_del_rt(dev_net(ifp->idev->dev), rt);
else {
if (!(rt->rt6i_flags & RTF_EXPIRES))
rt6_set_expires(rt, expires);
ip6_rt_put(rt);
fib6_set_expires(rt, expires);
fib6_info_release(rt);
}
}
}
@ -2320,7 +2319,7 @@ static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpad
static void
addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
unsigned long expires, u32 flags)
unsigned long expires, u32 flags, gfp_t gfp_flags)
{
struct fib6_config cfg = {
.fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX,
@ -2331,6 +2330,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
.fc_flags = RTF_UP | flags,
.fc_nlinfo.nl_net = dev_net(dev),
.fc_protocol = RTPROT_KERNEL,
.fc_type = RTN_UNICAST,
};
cfg.fc_dst = *pfx;
@ -2344,17 +2344,17 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev,
cfg.fc_flags |= RTF_NONEXTHOP;
#endif
ip6_route_add(&cfg, NULL);
ip6_route_add(&cfg, gfp_flags, NULL);
}
static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
int plen,
const struct net_device *dev,
u32 flags, u32 noflags)
{
struct fib6_node *fn;
struct rt6_info *rt = NULL;
struct fib6_info *rt = NULL;
struct fib6_table *table;
u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX;
@ -2368,14 +2368,13 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx,
goto out;
for_each_fib6_node_rt_rcu(fn) {
if (rt->dst.dev->ifindex != dev->ifindex)
if (rt->fib6_nh.nh_dev->ifindex != dev->ifindex)
continue;
if ((rt->rt6i_flags & flags) != flags)
continue;
if ((rt->rt6i_flags & noflags) != 0)
continue;
if (!dst_hold_safe(&rt->dst))
rt = NULL;
fib6_info_hold(rt);
break;
}
out:
@ -2394,12 +2393,13 @@ static void addrconf_add_mroute(struct net_device *dev)
.fc_ifindex = dev->ifindex,
.fc_dst_len = 8,
.fc_flags = RTF_UP,
.fc_type = RTN_UNICAST,
.fc_nlinfo.nl_net = dev_net(dev),
};
ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0);
ip6_route_add(&cfg, NULL);
ip6_route_add(&cfg, GFP_ATOMIC, NULL);
}
static struct inet6_dev *addrconf_add_dev(struct net_device *dev)
@ -2641,7 +2641,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
*/
if (pinfo->onlink) {
struct rt6_info *rt;
struct fib6_info *rt;
unsigned long rt_expires;
/* Avoid arithmetic overflow. Really, we could
@ -2666,13 +2666,13 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
if (rt) {
/* Autoconf prefix route */
if (valid_lft == 0) {
ip6_del_rt(rt);
ip6_del_rt(net, rt);
rt = NULL;
} else if (addrconf_finite_timeout(rt_expires)) {
/* not infinity */
rt6_set_expires(rt, jiffies + rt_expires);
fib6_set_expires(rt, jiffies + rt_expires);
} else {
rt6_clean_expires(rt);
fib6_clean_expires(rt);
}
} else if (valid_lft) {
clock_t expires = 0;
@ -2683,9 +2683,9 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao)
expires = jiffies_to_clock_t(rt_expires);
}
addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len,
dev, expires, flags);
dev, expires, flags, GFP_ATOMIC);
}
ip6_rt_put(rt);
fib6_info_release(rt);
}
/* Try to figure out our local address for this prefix */
@ -2898,7 +2898,7 @@ static int inet6_addr_add(struct net *net, int ifindex,
if (!IS_ERR(ifp)) {
if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) {
addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev,
expires, flags);
expires, flags, GFP_KERNEL);
}
/* Send a netlink notification if DAD is enabled and
@ -3051,7 +3051,8 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
if (addr.s6_addr32[3]) {
add_addr(idev, &addr, plen, scope);
addrconf_prefix_route(&addr, plen, idev->dev, 0, pflags);
addrconf_prefix_route(&addr, plen, idev->dev, 0, pflags,
GFP_ATOMIC);
return;
}
@ -3076,7 +3077,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev)
add_addr(idev, &addr, plen, flag);
addrconf_prefix_route(&addr, plen, idev->dev, 0,
pflags);
pflags, GFP_ATOMIC);
}
}
}
@ -3116,7 +3117,8 @@ void addrconf_add_linklocal(struct inet6_dev *idev,
ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags,
INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, true, NULL);
if (!IS_ERR(ifp)) {
addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0);
addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev,
0, 0, GFP_ATOMIC);
addrconf_dad_start(ifp);
in6_ifa_put(ifp);
}
@ -3231,7 +3233,8 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route)
addrconf_add_linklocal(idev, &addr,
IFA_F_STABLE_PRIVACY);
else if (prefix_route)
addrconf_prefix_route(&addr, 64, idev->dev, 0, 0);
addrconf_prefix_route(&addr, 64, idev->dev,
0, 0, GFP_KERNEL);
break;
case IN6_ADDR_GEN_MODE_EUI64:
/* addrconf_add_linklocal also adds a prefix_route and we
@ -3241,7 +3244,8 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route)
if (ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) == 0)
addrconf_add_linklocal(idev, &addr, 0);
else if (prefix_route)
addrconf_prefix_route(&addr, 64, idev->dev, 0, 0);
addrconf_prefix_route(&addr, 64, idev->dev,
0, 0, GFP_ATOMIC);
break;
case IN6_ADDR_GEN_MODE_NONE:
default:
@ -3333,7 +3337,8 @@ static void addrconf_gre_config(struct net_device *dev)
}
#endif
static int fixup_permanent_addr(struct inet6_dev *idev,
static int fixup_permanent_addr(struct net *net,
struct inet6_dev *idev,
struct inet6_ifaddr *ifp)
{
/* !rt6i_node means the host route was removed from the
@ -3341,9 +3346,10 @@ static int fixup_permanent_addr(struct inet6_dev *idev,
* case regenerate the host route.
*/
if (!ifp->rt || !ifp->rt->rt6i_node) {
struct rt6_info *rt, *prev;
struct fib6_info *rt, *prev;
rt = addrconf_dst_alloc(idev, &ifp->addr, false);
rt = addrconf_dst_alloc(net, idev, &ifp->addr, false,
GFP_ATOMIC);
if (IS_ERR(rt))
return PTR_ERR(rt);
@ -3353,12 +3359,12 @@ static int fixup_permanent_addr(struct inet6_dev *idev,
ifp->rt = rt;
spin_unlock(&ifp->lock);
ip6_rt_put(prev);
fib6_info_release(prev);
}
if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) {
addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
idev->dev, 0, 0);
idev->dev, 0, 0, GFP_ATOMIC);
}
if (ifp->state == INET6_IFADDR_STATE_PREDAD)
@ -3367,7 +3373,7 @@ static int fixup_permanent_addr(struct inet6_dev *idev,
return 0;
}
static void addrconf_permanent_addr(struct net_device *dev)
static void addrconf_permanent_addr(struct net *net, struct net_device *dev)
{
struct inet6_ifaddr *ifp, *tmp;
struct inet6_dev *idev;
@ -3380,7 +3386,7 @@ static void addrconf_permanent_addr(struct net_device *dev)
list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) {
if ((ifp->flags & IFA_F_PERMANENT) &&
fixup_permanent_addr(idev, ifp) < 0) {
fixup_permanent_addr(net, idev, ifp) < 0) {
write_unlock_bh(&idev->lock);
in6_ifa_hold(ifp);
ipv6_del_addr(ifp);
@ -3449,7 +3455,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event,
if (event == NETDEV_UP) {
/* restore routes for permanent addresses */
addrconf_permanent_addr(dev);
addrconf_permanent_addr(net, dev);
if (!addrconf_link_ready(dev)) {
/* device is not ready yet. */
@ -3707,7 +3713,7 @@ restart:
keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6);
list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) {
struct rt6_info *rt = NULL;
struct fib6_info *rt = NULL;
bool keep;
addrconf_del_dad_work(ifa);
@ -3735,7 +3741,7 @@ restart:
spin_unlock_bh(&ifa->lock);
if (rt)
ip6_del_rt(rt);
ip6_del_rt(net, rt);
if (state != INET6_IFADDR_STATE_DEAD) {
__ipv6_ifa_notify(RTM_DELADDR, ifa);
@ -3853,6 +3859,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
struct inet6_dev *idev = ifp->idev;
struct net_device *dev = idev->dev;
bool bump_id, notify = false;
struct net *net;
addrconf_join_solict(dev, &ifp->addr);
@ -3863,8 +3870,9 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
if (ifp->state == INET6_IFADDR_STATE_DEAD)
goto out;
net = dev_net(dev);
if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) ||
(dev_net(dev)->ipv6.devconf_all->accept_dad < 1 &&
(net->ipv6.devconf_all->accept_dad < 1 &&
idev->cnf.accept_dad < 1) ||
!(ifp->flags&IFA_F_TENTATIVE) ||
ifp->flags & IFA_F_NODAD) {
@ -3900,8 +3908,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp)
* Frames right away
*/
if (ifp->flags & IFA_F_OPTIMISTIC) {
ip6_ins_rt(ifp->rt);
if (ipv6_use_optimistic_addr(dev_net(dev), idev)) {
ip6_ins_rt(net, ifp->rt);
if (ipv6_use_optimistic_addr(net, idev)) {
/* Because optimistic nodes can use this address,
* notify listeners. If DAD fails, RTM_DELADDR is sent.
*/
@ -4567,8 +4575,9 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags,
ipv6_ifa_notify(0, ifp);
if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) {
addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev,
expires, flags);
addrconf_prefix_route(&ifp->addr, ifp->prefix_len,
ifp->idev->dev, expires, flags,
GFP_KERNEL);
} else if (had_prefixroute) {
enum cleanup_prefix_rt_t action;
unsigned long rt_expires;
@ -5604,28 +5613,29 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp)
* to do it again
*/
if (!rcu_access_pointer(ifp->rt->rt6i_node))
ip6_ins_rt(ifp->rt);
ip6_ins_rt(net, ifp->rt);
if (ifp->idev->cnf.forwarding)
addrconf_join_anycast(ifp);
if (!ipv6_addr_any(&ifp->peer_addr))
addrconf_prefix_route(&ifp->peer_addr, 128,
ifp->idev->dev, 0, 0);
ifp->idev->dev, 0, 0,
GFP_KERNEL);
break;
case RTM_DELADDR:
if (ifp->idev->cnf.forwarding)
addrconf_leave_anycast(ifp);
addrconf_leave_solict(ifp->idev, &ifp->addr);
if (!ipv6_addr_any(&ifp->peer_addr)) {
struct rt6_info *rt;
struct fib6_info *rt;
rt = addrconf_get_prefix_route(&ifp->peer_addr, 128,
ifp->idev->dev, 0, 0);
if (rt)
ip6_del_rt(rt);
ip6_del_rt(net, rt);
}
if (ifp->rt) {
if (dst_hold_safe(&ifp->rt->dst))
ip6_del_rt(ifp->rt);
ip6_del_rt(net, ifp->rt);
ifp->rt = NULL;
}
rt_genid_bump_ipv6(net);
break;
@ -5972,11 +5982,11 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val)
list_for_each_entry(ifa, &idev->addr_list, if_list) {
spin_lock(&ifa->lock);
if (ifa->rt) {
struct rt6_info *rt = ifa->rt;
struct fib6_info *rt = ifa->rt;
int cpu;
rcu_read_lock();
addrconf_set_nopolicy(ifa->rt, val);
ifa->rt->dst_nopolicy = val ? true : false;
if (rt->rt6i_pcpu) {
for_each_possible_cpu(cpu) {
struct rt6_info **rtp;

21
net/ipv6/anycast.c
View File

@ -213,12 +213,12 @@ static void aca_put(struct ifacaddr6 *ac)
{
if (refcount_dec_and_test(&ac->aca_refcnt)) {
in6_dev_put(ac->aca_idev);
dst_release(&ac->aca_rt->dst);
fib6_info_release(ac->aca_rt);
kfree(ac);
}
}
static struct ifacaddr6 *aca_alloc(struct rt6_info *rt,
static struct ifacaddr6 *aca_alloc(struct fib6_info *rt,
const struct in6_addr *addr)
{
struct inet6_dev *idev = rt->rt6i_idev;
@ -231,6 +231,7 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt,
aca->aca_addr = *addr;
in6_dev_hold(idev);
aca->aca_idev = idev;
fib6_info_hold(rt);
aca->aca_rt = rt;
aca->aca_users = 1;
/* aca_tstamp should be updated upon changes */
@ -246,7 +247,8 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt,
int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
{
struct ifacaddr6 *aca;
struct rt6_info *rt;
struct fib6_info *rt;
struct net *net;
int err;
ASSERT_RTNL();
@ -265,14 +267,15 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
}
}
rt = addrconf_dst_alloc(idev, addr, true);
net = dev_net(idev->dev);
rt = addrconf_dst_alloc(net, idev, addr, true, GFP_ATOMIC);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
goto out;
}
aca = aca_alloc(rt, addr);
if (!aca) {
ip6_rt_put(rt);
fib6_info_release(rt);
err = -ENOMEM;
goto out;
}
@ -286,7 +289,7 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
aca_get(aca);
write_unlock_bh(&idev->lock);
ip6_ins_rt(rt);
ip6_ins_rt(net, rt);
addrconf_join_solict(idev->dev, &aca->aca_addr);
@ -328,8 +331,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
write_unlock_bh(&idev->lock);
addrconf_leave_solict(idev, &aca->aca_addr);
dst_hold(&aca->aca_rt->dst);
ip6_del_rt(aca->aca_rt);
ip6_del_rt(dev_net(idev->dev), aca->aca_rt);
aca_put(aca);
return 0;
@ -356,8 +358,7 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev)
addrconf_leave_solict(idev, &aca->aca_addr);
dst_hold(&aca->aca_rt->dst);
ip6_del_rt(aca->aca_rt);
ip6_del_rt(dev_net(idev->dev), aca->aca_rt);
aca_put(aca);

366
net/ipv6/ip6_fib.c
View File

@ -43,7 +43,7 @@ static struct kmem_cache *fib6_node_kmem __read_mostly;
struct fib6_cleaner {
struct fib6_walker w;
struct net *net;
int (*func)(struct rt6_info *, void *arg);
int (*func)(struct fib6_info *, void *arg);
int sernum;
void *arg;
};
@ -54,7 +54,7 @@ struct fib6_cleaner {
#define FWS_INIT FWS_L
#endif
static struct rt6_info *fib6_find_prefix(struct net *net,
static struct fib6_info *fib6_find_prefix(struct net *net,
struct fib6_table *table,
struct fib6_node *fn);
static struct fib6_node *fib6_repair_tree(struct net *net,
@ -105,9 +105,8 @@ enum {
FIB6_NO_SERNUM_CHANGE = 0,
};
void fib6_update_sernum(struct rt6_info *rt)
void fib6_update_sernum(struct net *net, struct fib6_info *rt)
{
struct net *net = dev_net(rt->dst.dev);
struct fib6_node *fn;
fn = rcu_dereference_protected(rt->rt6i_node,
@ -146,6 +145,71 @@ static __be32 addr_bit_set(const void *token, int fn_bit)
addr[fn_bit >> 5];
}
struct fib6_info *fib6_info_alloc(gfp_t gfp_flags)
{
struct fib6_info *f6i;
f6i = kzalloc(sizeof(*f6i), gfp_flags);
if (!f6i)
return NULL;
f6i->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags);
if (!f6i->rt6i_pcpu) {
kfree(f6i);
return NULL;
}
INIT_LIST_HEAD(&f6i->rt6i_siblings);
f6i->fib6_metrics = (struct dst_metrics *)&dst_default_metrics;
atomic_inc(&f6i->rt6i_ref);
return f6i;
}
void fib6_info_destroy(struct fib6_info *f6i)
{
struct rt6_exception_bucket *bucket;
struct dst_metrics *m;
WARN_ON(f6i->rt6i_node);
bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket, 1);
if (bucket) {
f6i->rt6i_exception_bucket = NULL;
kfree(bucket);
}
if (f6i->rt6i_pcpu) {
int cpu;
for_each_possible_cpu(cpu) {
struct rt6_info **ppcpu_rt;
struct rt6_info *pcpu_rt;
ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu);
pcpu_rt = *ppcpu_rt;
if (pcpu_rt) {
dst_dev_put(&pcpu_rt->dst);
dst_release(&pcpu_rt->dst);
*ppcpu_rt = NULL;
}
}
}
if (f6i->rt6i_idev)
in6_dev_put(f6i->rt6i_idev);
if (f6i->fib6_nh.nh_dev)
dev_put(f6i->fib6_nh.nh_dev);
m = f6i->fib6_metrics;
if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt))
kfree(m);
kfree(f6i);
}
EXPORT_SYMBOL_GPL(fib6_info_destroy);
static struct fib6_node *node_alloc(struct net *net)
{
struct fib6_node *fn;
@ -176,28 +240,6 @@ static void node_free(struct net *net, struct fib6_node *fn)
net->ipv6.rt6_stats->fib_nodes--;
}
void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
{
int cpu;
if (!non_pcpu_rt->rt6i_pcpu)
return;
for_each_possible_cpu(cpu) {
struct rt6_info **ppcpu_rt;
struct rt6_info *pcpu_rt;
ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu);
pcpu_rt = *ppcpu_rt;
if (pcpu_rt) {
dst_dev_put(&pcpu_rt->dst);
dst_release(&pcpu_rt->dst);
*ppcpu_rt = NULL;
}
}
}
EXPORT_SYMBOL_GPL(rt6_free_pcpu);
static void fib6_free_table(struct fib6_table *table)
{
inetpeer_invalidate_tree(&table->tb6_peers);
@ -232,7 +274,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id)
if (table) {
table->tb6_id = id;
rcu_assign_pointer(table->tb6_root.leaf,
net->ipv6.ip6_null_entry);
net->ipv6.fib6_null_entry);
table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&table->tb6_peers);
}
@ -340,7 +382,7 @@ unsigned int fib6_tables_seq_read(struct net *net)
static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net,
enum fib_event_type event_type,
struct rt6_info *rt)
struct fib6_info *rt)
{
struct fib6_entry_notifier_info info = {
.rt = rt,
@ -351,7 +393,7 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net,
static int call_fib6_entry_notifiers(struct net *net,
enum fib_event_type event_type,
struct rt6_info *rt,
struct fib6_info *rt,
struct netlink_ext_ack *extack)
{
struct fib6_entry_notifier_info info = {
@ -368,16 +410,16 @@ struct fib6_dump_arg {
struct notifier_block *nb;
};
static void fib6_rt_dump(struct rt6_info *rt, struct fib6_dump_arg *arg)
static void fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg)
{
if (rt == arg->net->ipv6.ip6_null_entry)
if (rt == arg->net->ipv6.fib6_null_entry)
return;
call_fib6_entry_notifier(arg->nb, arg->net, FIB_EVENT_ENTRY_ADD, rt);
}
static int fib6_node_dump(struct fib6_walker *w)
{
struct rt6_info *rt;
struct fib6_info *rt;
for_each_fib6_walker_rt(w)
fib6_rt_dump(rt, w->args);
@ -426,7 +468,7 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb)
static int fib6_dump_node(struct fib6_walker *w)
{
int res;
struct rt6_info *rt;
struct fib6_info *rt;
for_each_fib6_walker_rt(w) {
res = rt6_dump_route(rt, w->args);
@ -443,7 +485,7 @@ static int fib6_dump_node(struct fib6_walker *w)
*/
if (rt->rt6i_nsiblings)
rt = list_last_entry(&rt->rt6i_siblings,
struct rt6_info,
struct fib6_info,
rt6i_siblings);
}
w->leaf = NULL;
@ -579,6 +621,24 @@ out:
return res;
}
void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val)
{
if (!f6i)
return;
if (f6i->fib6_metrics == &dst_default_metrics) {
struct dst_metrics *p = kzalloc(sizeof(*p), GFP_ATOMIC);
if (!p)
return;
refcount_set(&p->refcnt, 1);
f6i->fib6_metrics = p;
}
f6i->fib6_metrics->metrics[metric - 1] = val;
}
/*
* Routing Table
*
@ -608,7 +668,7 @@ static struct fib6_node *fib6_add_1(struct net *net,
fn = root;
do {
struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
lockdep_is_held(&table->tb6_lock));
key = (struct rt6key *)((u8 *)leaf + offset);
@ -637,11 +697,11 @@ static struct fib6_node *fib6_add_1(struct net *net,
/* clean up an intermediate node */
if (!(fn->fn_flags & RTN_RTINFO)) {
RCU_INIT_POINTER(fn->leaf, NULL);
rt6_release(leaf);
fib6_info_release(leaf);
/* remove null_entry in the root node */
} else if (fn->fn_flags & RTN_TL_ROOT &&
rcu_access_pointer(fn->leaf) ==
net->ipv6.ip6_null_entry) {
net->ipv6.fib6_null_entry) {
RCU_INIT_POINTER(fn->leaf, NULL);
}
@ -802,39 +862,7 @@ insert_above:
return ln;
}
static void fib6_copy_metrics(u32 *mp, const struct mx6_config *mxc)
{
int i;
for (i = 0; i < RTAX_MAX; i++) {
if (test_bit(i, mxc->mx_valid))
mp[i] = mxc->mx[i];
}
}
static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc)
{
if (!mxc->mx)
return 0;
if (dst->flags & DST_HOST) {
u32 *mp = dst_metrics_write_ptr(dst);
if (unlikely(!mp))
return -ENOMEM;
fib6_copy_metrics(mp, mxc);
} else {
dst_init_metrics(dst, mxc->mx, false);
/* We've stolen mx now. */
mxc->mx = NULL;
}
return 0;
}
static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn,
struct net *net)
{
struct fib6_table *table = rt->rt6i_table;
@ -847,18 +875,38 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
* to still alive ones.
*/
while (fn) {
struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
lockdep_is_held(&table->tb6_lock));
struct rt6_info *new_leaf;
struct fib6_info *new_leaf;
if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) {
new_leaf = fib6_find_prefix(net, table, fn);
atomic_inc(&new_leaf->rt6i_ref);
rcu_assign_pointer(fn->leaf, new_leaf);
rt6_release(rt);
fib6_info_release(rt);
}
fn = rcu_dereference_protected(fn->parent,
lockdep_is_held(&table->tb6_lock));
}
if (rt->rt6i_pcpu) {
int cpu;
/* release the reference to this fib entry from
* all of its cached pcpu routes
*/
for_each_possible_cpu(cpu) {
struct rt6_info **ppcpu_rt;
struct rt6_info *pcpu_rt;
ppcpu_rt = per_cpu_ptr(rt->rt6i_pcpu, cpu);
pcpu_rt = *ppcpu_rt;
if (pcpu_rt) {
fib6_info_release(pcpu_rt->from);
pcpu_rt->from = NULL;
}
}
}
}
}
@ -866,15 +914,15 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn,
* Insert routing information in a node.
*/
static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
struct nl_info *info, struct mx6_config *mxc,
static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt,
struct nl_info *info,
struct netlink_ext_ack *extack)
{
struct rt6_info *leaf = rcu_dereference_protected(fn->leaf,
struct fib6_info *leaf = rcu_dereference_protected(fn->leaf,
lockdep_is_held(&rt->rt6i_table->tb6_lock));
struct rt6_info *iter = NULL;
struct rt6_info __rcu **ins;
struct rt6_info __rcu **fallback_ins = NULL;
struct fib6_info *iter = NULL;
struct fib6_info __rcu **ins;
struct fib6_info __rcu **fallback_ins = NULL;
int replace = (info->nlh &&
(info->nlh->nlmsg_flags & NLM_F_REPLACE));
int add = (!info->nlh ||
@ -921,10 +969,10 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt,
if (!(iter->rt6i_flags & RTF_EXPIRES))
return -EEXIST;
if (!(rt->rt6i_flags & RTF_EXPIRES))
rt6_clean_expires(iter);
fib6_clean_expires(iter);
else
rt6_set_expires(iter, rt->dst.expires);
iter->rt6i_pmtu = rt->rt6i_pmtu;
fib6_set_expires(iter, rt->expires);
fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu);
return -EEXIST;
}
/* If we have the same destination and the same metric,
@ -965,7 +1013,7 @@ next_iter:
/* Link this route to others same route. */
if (rt->rt6i_nsiblings) {
unsigned int rt6i_nsiblings;
struct rt6_info *sibling, *temp_sibling;
struct fib6_info *sibling, *temp_sibling;
/* Find the first route that have the same metric */
sibling = leaf;
@ -1003,9 +1051,6 @@ next_iter:
add:
nlflags |= NLM_F_CREATE;
err = fib6_commit_metrics(&rt->dst, mxc);
if (err)
return err;
err = call_fib6_entry_notifiers(info->nl_net,
FIB_EVENT_ENTRY_ADD,
@ -1036,10 +1081,6 @@ add:
return -ENOENT;
}
err = fib6_commit_metrics(&rt->dst, mxc);
if (err)
return err;
err = call_fib6_entry_notifiers(info->nl_net,
FIB_EVENT_ENTRY_REPLACE,
rt, extack);
@ -1061,7 +1102,7 @@ add:
fib6_purge_rt(iter, fn, info->nl_net);
if (rcu_access_pointer(fn->rr_ptr) == iter)
fn->rr_ptr = NULL;
rt6_release(iter);
fib6_info_release(iter);
if (nsiblings) {
/* Replacing an ECMP route, remove all siblings */
@ -1077,7 +1118,7 @@ add:
fib6_purge_rt(iter, fn, info->nl_net);
if (rcu_access_pointer(fn->rr_ptr) == iter)
fn->rr_ptr = NULL;
rt6_release(iter);
fib6_info_release(iter);
nsiblings--;
info->nl_net->ipv6.rt6_stats->fib_rt_entries--;
} else {
@ -1093,10 +1134,10 @@ add:
return 0;
}
static void fib6_start_gc(struct net *net, struct rt6_info *rt)
static void fib6_start_gc(struct net *net, struct fib6_info *rt)
{
if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
(rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE)))
(rt->rt6i_flags & RTF_EXPIRES))
mod_timer(&net->ipv6.ip6_fib_timer,
jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
}
@ -1108,7 +1149,7 @@ void fib6_force_start_gc(struct net *net)
jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
}
static void __fib6_update_sernum_upto_root(struct rt6_info *rt,
static void __fib6_update_sernum_upto_root(struct fib6_info *rt,
int sernum)
{
struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
@ -1123,7 +1164,7 @@ static void __fib6_update_sernum_upto_root(struct rt6_info *rt,
}
}
void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt)
void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt)
{
__fib6_update_sernum_upto_root(rt, fib6_new_sernum(net));
}
@ -1135,9 +1176,8 @@ void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt)
* Need to own table->tb6_lock
*/
int fib6_add(struct fib6_node *root, struct rt6_info *rt,
struct nl_info *info, struct mx6_config *mxc,
struct netlink_ext_ack *extack)
int fib6_add(struct fib6_node *root, struct fib6_info *rt,
struct nl_info *info, struct netlink_ext_ack *extack)
{
struct fib6_table *table = rt->rt6i_table;
struct fib6_node *fn, *pn = NULL;
@ -1146,11 +1186,6 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
int replace_required = 0;
int sernum = fib6_new_sernum(info->nl_net);
if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt)))
return -EINVAL;
if (WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE))
return -EINVAL;
if (info->nlh) {
if (!(info->nlh->nlmsg_flags & NLM_F_CREATE))
allow_create = 0;
@ -1162,7 +1197,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
fn = fib6_add_1(info->nl_net, table, root,
&rt->rt6i_dst.addr, rt->rt6i_dst.plen,
offsetof(struct rt6_info, rt6i_dst), allow_create,
offsetof(struct fib6_info, rt6i_dst), allow_create,
replace_required, extack);
if (IS_ERR(fn)) {
err = PTR_ERR(fn);
@ -1194,16 +1229,16 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
if (!sfn)
goto failure;
atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref);
atomic_inc(&info->nl_net->ipv6.fib6_null_entry->rt6i_ref);
rcu_assign_pointer(sfn->leaf,
info->nl_net->ipv6.ip6_null_entry);
info->nl_net->ipv6.fib6_null_entry);
sfn->fn_flags = RTN_ROOT;
/* Now add the first leaf node to new subtree */
sn = fib6_add_1(info->nl_net, table, sfn,
&rt->rt6i_src.addr, rt->rt6i_src.plen,
offsetof(struct rt6_info, rt6i_src),
offsetof(struct fib6_info, rt6i_src),
allow_create, replace_required, extack);
if (IS_ERR(sn)) {
@ -1222,7 +1257,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
} else {
sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn),
&rt->rt6i_src.addr, rt->rt6i_src.plen,
offsetof(struct rt6_info, rt6i_src),
offsetof(struct fib6_info, rt6i_src),
allow_create, replace_required, extack);
if (IS_ERR(sn)) {
@ -1235,7 +1270,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
if (fn->fn_flags & RTN_TL_ROOT) {
/* put back null_entry for root node */
rcu_assign_pointer(fn->leaf,
info->nl_net->ipv6.ip6_null_entry);
info->nl_net->ipv6.fib6_null_entry);
} else {
atomic_inc(&rt->rt6i_ref);
rcu_assign_pointer(fn->leaf, rt);
@ -1245,7 +1280,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt,
}
#endif
err = fib6_add_rt2node(fn, rt, info, mxc, extack);
err = fib6_add_rt2node(fn, rt, info, extack);
if (!err) {
__fib6_update_sernum_upto_root(rt, sernum);
fib6_start_gc(info->nl_net, rt);
@ -1259,13 +1294,13 @@ out:
* super-tree leaf node we have to find a new one for it.
*/
if (pn != fn) {
struct rt6_info *pn_leaf =
struct fib6_info *pn_leaf =
rcu_dereference_protected(pn->leaf,
lockdep_is_held(&table->tb6_lock));
if (pn_leaf == rt) {
pn_leaf = NULL;
RCU_INIT_POINTER(pn->leaf, NULL);
atomic_dec(&rt->rt6i_ref);
fib6_info_release(rt);
}
if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) {
pn_leaf = fib6_find_prefix(info->nl_net, table,
@ -1274,10 +1309,10 @@ out:
if (!pn_leaf) {
WARN_ON(!pn_leaf);
pn_leaf =
info->nl_net->ipv6.ip6_null_entry;
info->nl_net->ipv6.fib6_null_entry;
}
#endif
atomic_inc(&pn_leaf->rt6i_ref);
fib6_info_hold(pn_leaf);
rcu_assign_pointer(pn->leaf, pn_leaf);
}
}
@ -1299,10 +1334,6 @@ failure:
(fn->fn_flags & RTN_TL_ROOT &&
!rcu_access_pointer(fn->leaf))))
fib6_repair_tree(info->nl_net, table, fn);
/* Always release dst as dst->__refcnt is guaranteed
* to be taken before entering this function
*/
dst_release_immediate(&rt->dst);
return err;
}
@ -1312,7 +1343,7 @@ failure:
*/
struct lookup_args {
int offset; /* key offset on rt6_info */
int offset; /* key offset on fib6_info */
const struct in6_addr *addr; /* search key */
};
@ -1350,7 +1381,7 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root,
struct fib6_node *subtree = FIB6_SUBTREE(fn);
if (subtree || fn->fn_flags & RTN_RTINFO) {
struct rt6_info *leaf = rcu_dereference(fn->leaf);
struct fib6_info *leaf = rcu_dereference(fn->leaf);
struct rt6key *key;
if (!leaf)
@ -1390,12 +1421,12 @@ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *dad
struct fib6_node *fn;
struct lookup_args args[] = {
{
.offset = offsetof(struct rt6_info, rt6i_dst),
.offset = offsetof(struct fib6_info, rt6i_dst),
.addr = daddr,
},
#ifdef CONFIG_IPV6_SUBTREES
{
.offset = offsetof(struct rt6_info, rt6i_src),
.offset = offsetof(struct fib6_info, rt6i_src),
.addr = saddr,
},
#endif
@ -1431,7 +1462,7 @@ static struct fib6_node *fib6_locate_1(struct fib6_node *root,
struct fib6_node *fn, *prev = NULL;
for (fn = root; fn ; ) {
struct rt6_info *leaf = rcu_dereference(fn->leaf);
struct fib6_info *leaf = rcu_dereference(fn->leaf);
struct rt6key *key;
/* This node is being deleted */
@ -1480,7 +1511,7 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
struct fib6_node *fn;
fn = fib6_locate_1(root, daddr, dst_len,
offsetof(struct rt6_info, rt6i_dst),
offsetof(struct fib6_info, rt6i_dst),
exact_match);
#ifdef CONFIG_IPV6_SUBTREES
@ -1491,7 +1522,7 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
if (subtree) {
fn = fib6_locate_1(subtree, saddr, src_len,
offsetof(struct rt6_info, rt6i_src),
offsetof(struct fib6_info, rt6i_src),
exact_match);
}
}
@ -1510,14 +1541,14 @@ struct fib6_node *fib6_locate(struct fib6_node *root,
*
*/
static struct rt6_info *fib6_find_prefix(struct net *net,
static struct fib6_info *fib6_find_prefix(struct net *net,
struct fib6_table *table,
struct fib6_node *fn)
{
struct fib6_node *child_left, *child_right;
if (fn->fn_flags & RTN_ROOT)
return net->ipv6.ip6_null_entry;
return net->ipv6.fib6_null_entry;
while (fn) {
child_left = rcu_dereference_protected(fn->left,
@ -1554,7 +1585,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
/* Set fn->leaf to null_entry for root node. */
if (fn->fn_flags & RTN_TL_ROOT) {
rcu_assign_pointer(fn->leaf, net->ipv6.ip6_null_entry);
rcu_assign_pointer(fn->leaf, net->ipv6.fib6_null_entry);
return fn;
}
@ -1569,11 +1600,11 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
lockdep_is_held(&table->tb6_lock));
struct fib6_node *pn_l = rcu_dereference_protected(pn->left,
lockdep_is_held(&table->tb6_lock));
struct rt6_info *fn_leaf = rcu_dereference_protected(fn->leaf,
struct fib6_info *fn_leaf = rcu_dereference_protected(fn->leaf,
lockdep_is_held(&table->tb6_lock));
struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf,
struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf,
lockdep_is_held(&table->tb6_lock));
struct rt6_info *new_fn_leaf;
struct fib6_info *new_fn_leaf;
RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter);
iter++;
@ -1599,10 +1630,10 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
#if RT6_DEBUG >= 2
if (!new_fn_leaf) {
WARN_ON(!new_fn_leaf);
new_fn_leaf = net->ipv6.ip6_null_entry;
new_fn_leaf = net->ipv6.fib6_null_entry;
}
#endif
atomic_inc(&new_fn_leaf->rt6i_ref);
fib6_info_hold(new_fn_leaf);
rcu_assign_pointer(fn->leaf, new_fn_leaf);
return pn;
}
@ -1658,23 +1689,21 @@ static struct fib6_node *fib6_repair_tree(struct net *net,
return pn;
RCU_INIT_POINTER(pn->leaf, NULL);
rt6_release(pn_leaf);
fib6_info_release(pn_leaf);
fn = pn;
}
}
static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
struct rt6_info __rcu **rtp, struct nl_info *info)
struct fib6_info __rcu **rtp, struct nl_info *info)
{
struct fib6_walker *w;
struct rt6_info *rt = rcu_dereference_protected(*rtp,
struct fib6_info *rt = rcu_dereference_protected(*rtp,
lockdep_is_held(&table->tb6_lock));
struct net *net = info->nl_net;
RT6_TRACE("fib6_del_route\n");
WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE);
/* Unlink it */
*rtp = rt->rt6_next;
rt->rt6i_node = NULL;
@ -1690,7 +1719,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
/* Remove this entry from other siblings */
if (rt->rt6i_nsiblings) {
struct rt6_info *sibling, *next_sibling;
struct fib6_info *sibling, *next_sibling;
list_for_each_entry_safe(sibling, next_sibling,
&rt->rt6i_siblings, rt6i_siblings)
@ -1730,40 +1759,30 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn,
call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL);
if (!info->skip_notify)
inet6_rt_notify(RTM_DELROUTE, rt, info, 0);
rt6_release(rt);
fib6_info_release(rt);
}
/* Need to own table->tb6_lock */
int fib6_del(struct rt6_info *rt, struct nl_info *info)
int fib6_del(struct fib6_info *rt, struct nl_info *info)
{
struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node,
lockdep_is_held(&rt->rt6i_table->tb6_lock));
struct fib6_table *table = rt->rt6i_table;
struct net *net = info->nl_net;
struct rt6_info __rcu **rtp;
struct rt6_info __rcu **rtp_next;
struct fib6_info __rcu **rtp;
struct fib6_info __rcu **rtp_next;
#if RT6_DEBUG >= 2
if (rt->dst.obsolete > 0) {
WARN_ON(fn);
return -ENOENT;
}
#endif
if (!fn || rt == net->ipv6.ip6_null_entry)
if (!fn || rt == net->ipv6.fib6_null_entry)
return -ENOENT;
WARN_ON(!(fn->fn_flags & RTN_RTINFO));
/* remove cached dst from exception table */
if (rt->rt6i_flags & RTF_CACHE)
return rt6_remove_exception_rt(rt);
/*
* Walk the leaf entries looking for ourself
*/
for (rtp = &fn->leaf; *rtp; rtp = rtp_next) {
struct rt6_info *cur = rcu_dereference_protected(*rtp,
struct fib6_info *cur = rcu_dereference_protected(*rtp,
lockdep_is_held(&table->tb6_lock));
if (rt == cur) {
fib6_del_route(table, fn, rtp, info);
@ -1907,7 +1926,7 @@ static int fib6_walk(struct net *net, struct fib6_walker *w)
static int fib6_clean_node(struct fib6_walker *w)
{
int res;
struct rt6_info *rt;
struct fib6_info *rt;
struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w);
struct nl_info info = {
.nl_net = c->net,
@ -1942,7 +1961,7 @@ static int fib6_clean_node(struct fib6_walker *w)
if (WARN_ON(!rt->rt6i_nsiblings))
continue;
rt = list_last_entry(&rt->rt6i_siblings,
struct rt6_info, rt6i_siblings);
struct fib6_info, rt6i_siblings);
continue;
}
WARN_ON(res != 0);
@ -1961,7 +1980,7 @@ static int fib6_clean_node(struct fib6_walker *w)
*/
static void fib6_clean_tree(struct net *net, struct fib6_node *root,
int (*func)(struct rt6_info *, void *arg),
int (*func)(struct fib6_info *, void *arg),
int sernum, void *arg)
{
struct fib6_cleaner c;
@ -1979,7 +1998,7 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root,
}
static void __fib6_clean_all(struct net *net,
int (*func)(struct rt6_info *, void *),
int (*func)(struct fib6_info *, void *),
int sernum, void *arg)
{
struct fib6_table *table;
@ -1999,7 +2018,7 @@ static void __fib6_clean_all(struct net *net,
rcu_read_unlock();
}
void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *),
void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *),
void *arg)
{
__fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg);
@ -2016,7 +2035,7 @@ static void fib6_flush_trees(struct net *net)
* Garbage collection
*/
static int fib6_age(struct rt6_info *rt, void *arg)
static int fib6_age(struct fib6_info *rt, void *arg)
{
struct fib6_gc_args *gc_args = arg;
unsigned long now = jiffies;
@ -2026,8 +2045,8 @@ static int fib6_age(struct rt6_info *rt, void *arg)
* Routes are expired even if they are in use.
*/
if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) {
if (time_after(now, rt->dst.expires)) {
if (rt->rt6i_flags & RTF_EXPIRES && rt->expires) {
if (time_after(now, rt->expires)) {
RT6_TRACE("expiring %p\n", rt);
return -1;
}
@ -2110,7 +2129,7 @@ static int __net_init fib6_net_init(struct net *net)
net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN;
rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf,
net->ipv6.ip6_null_entry);
net->ipv6.fib6_null_entry);
net->ipv6.fib6_main_tbl->tb6_root.fn_flags =
RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers);
@ -2122,7 +2141,7 @@ static int __net_init fib6_net_init(struct net *net)
goto out_fib6_main_tbl;
net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL;
rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf,
net->ipv6.ip6_null_entry);
net->ipv6.fib6_null_entry);
net->ipv6.fib6_local_tbl->tb6_root.fn_flags =
RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO;
inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers);
@ -2220,8 +2239,9 @@ struct ipv6_route_iter {
static int ipv6_route_seq_show(struct seq_file *seq, void *v)
{
struct rt6_info *rt = v;
struct fib6_info *rt = v;
struct ipv6_route_iter *iter = seq->private;
const struct net_device *dev;
seq_printf(seq, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen);
@ -2231,14 +2251,14 @@ static int ipv6_route_seq_show(struct seq_file *seq, void *v)
seq_puts(seq, "00000000000000000000000000000000 00 ");
#endif
if (rt->rt6i_flags & RTF_GATEWAY)
seq_printf(seq, "%pi6", &rt->rt6i_gateway);
seq_printf(seq, "%pi6", &rt->fib6_nh.nh_gw);
else
seq_puts(seq, "00000000000000000000000000000000");
dev = rt->fib6_nh.nh_dev;
seq_printf(seq, " %08x %08x %08x %08x %8s\n",
rt->rt6i_metric, atomic_read(&rt->dst.__refcnt),
rt->dst.__use, rt->rt6i_flags,
rt->dst.dev ? rt->dst.dev->name : "");
rt->rt6i_metric, atomic_read(&rt->rt6i_ref), 0,
rt->rt6i_flags, dev ? dev->name : "");
iter->w.leaf = NULL;
return 0;
}
@ -2311,14 +2331,14 @@ static void ipv6_route_check_sernum(struct ipv6_route_iter *iter)
static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
int r;
struct rt6_info *n;
struct fib6_info *n;
struct net *net = seq_file_net(seq);
struct ipv6_route_iter *iter = seq->private;
if (!v)
goto iter_table;
n = rcu_dereference_bh(((struct rt6_info *)v)->rt6_next);
n = rcu_dereference_bh(((struct fib6_info *)v)->rt6_next);
if (n) {
++*pos;
return n;

3
net/ipv6/ip6_output.c
View File

@ -968,7 +968,8 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
if (!had_dst)
*dst = ip6_route_output(net, sk, fl6);
rt = (*dst)->error ? NULL : (struct rt6_info *)*dst;
err = ip6_route_get_saddr(net, rt, &fl6->daddr,
err = ip6_route_get_saddr(net, rt ? rt->from : NULL,
&fl6->daddr,
sk ? inet6_sk(sk)->srcprefs : 0,
&fl6->saddr);
if (err)

40
net/ipv6/ndisc.c
View File

@ -1155,7 +1155,8 @@ static void ndisc_router_discovery(struct sk_buff *skb)
struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb);
struct neighbour *neigh = NULL;
struct inet6_dev *in6_dev;
struct rt6_info *rt = NULL;
struct fib6_info *rt = NULL;
struct net *net;
int lifetime;
struct ndisc_options ndopts;
int optlen;
@ -1253,9 +1254,9 @@ static void ndisc_router_discovery(struct sk_buff *skb)
/* Do not accept RA with source-addr found on local machine unless
* accept_ra_from_local is set to true.
*/
net = dev_net(in6_dev->dev);
if (!in6_dev->cnf.accept_ra_from_local &&
ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr,
in6_dev->dev, 0)) {
ipv6_chk_addr(net, &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) {
ND_PRINTK(2, info,
"RA from local address detected on dev: %s: default router ignored\n",
skb->dev->name);
@ -1272,20 +1273,22 @@ static void ndisc_router_discovery(struct sk_buff *skb)
pref = ICMPV6_ROUTER_PREF_MEDIUM;
#endif
rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev);
rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev);
if (rt) {
neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr);
neigh = ip6_neigh_lookup(&rt->fib6_nh.nh_gw,
rt->fib6_nh.nh_dev, NULL,
&ipv6_hdr(skb)->saddr);
if (!neigh) {
ND_PRINTK(0, err,
"RA: %s got default router without neighbour\n",
__func__);
ip6_rt_put(rt);
fib6_info_release(rt);
return;
}
}
if (rt && lifetime == 0) {
ip6_del_rt(rt);
ip6_del_rt(net, rt);
rt = NULL;
}
@ -1294,7 +1297,8 @@ static void ndisc_router_discovery(struct sk_buff *skb)
if (!rt && lifetime) {
ND_PRINTK(3, info, "RA: adding default router\n");
rt = rt6_add_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev, pref);
rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr,
skb->dev, pref);
if (!rt) {
ND_PRINTK(0, err,
"RA: %s failed to add default route\n",
@ -1302,12 +1306,14 @@ static void ndisc_router_discovery(struct sk_buff *skb)
return;
}
neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr);
neigh = ip6_neigh_lookup(&rt->fib6_nh.nh_gw,
rt->fib6_nh.nh_dev, NULL,
&ipv6_hdr(skb)->saddr);
if (!neigh) {
ND_PRINTK(0, err,
"RA: %s got default router without neighbour\n",
__func__);
ip6_rt_put(rt);
fib6_info_release(rt);
return;
}
neigh->flags |= NTF_ROUTER;
@ -1316,14 +1322,13 @@ static void ndisc_router_discovery(struct sk_buff *skb)
}
if (rt)
rt6_set_expires(rt, jiffies + (HZ * lifetime));
fib6_set_expires(rt, jiffies + (HZ * lifetime));
if (in6_dev->cnf.accept_ra_min_hop_limit < 256 &&
ra_msg->icmph.icmp6_hop_limit) {
if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) {
in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit;
if (rt)
dst_metric_set(&rt->dst, RTAX_HOPLIMIT,
ra_msg->icmph.icmp6_hop_limit);
fib6_metric_set(rt, RTAX_HOPLIMIT,
ra_msg->icmph.icmp6_hop_limit);
} else {
ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n");
}
@ -1475,10 +1480,7 @@ skip_routeinfo:
ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu);
} else if (in6_dev->cnf.mtu6 != mtu) {
in6_dev->cnf.mtu6 = mtu;
if (rt)
dst_metric_set(&rt->dst, RTAX_MTU, mtu);
fib6_metric_set(rt, RTAX_MTU, mtu);
rt6_mtu_change(skb->dev, mtu);
}
}
@ -1497,7 +1499,7 @@ skip_routeinfo:
ND_PRINTK(2, warn, "RA: invalid RA options\n");
}
out:
ip6_rt_put(rt);
fib6_info_release(rt);
if (neigh)
neigh_release(neigh);
}

1371
net/ipv6/route.c
View File

File diff suppressed because it is too large Load Diff

2
net/ipv6/xfrm6_policy.c
View File

@ -107,8 +107,6 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev,
* it was magically lost, so this code needs audit */
xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST |
RTF_LOCAL);
xdst->u.rt6.rt6i_metric = rt->rt6i_metric;
xdst->u.rt6.rt6i_node = rt->rt6i_node;
xdst->route_cookie = rt6_get_cookie(rt);
xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway;
xdst->u.rt6.rt6i_dst = rt->rt6i_dst;