Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
提交 3c5aa0bc 编写于 作者: D David S. Miller
浏览文件
操作

Merge branch 'ipv4-ipv6-mcast-align' 

Yuval Mintz says:

====================
ipmr, ip6mr: Align multicast routing for IPv4 & IPv6

Historically ip6mr was based [cut-n-paste] on ipmr and the two have not
diverged too much. Apparently as ipv4 multicast routing is more common
than its ipv6 brethren modifications since then are mostly one-way,
affecting ipmr while leaving ip6mr unchanged.

This series is meant to re-factor both ipmr and ip6mr into having common
structures [and some functionality], adding 2 new common files -
mroute_base.h and ipmr_base.c.

The series begins by bringing ip6mr up to speed to some of the changes
applied in the past to ipmr [#2, #3].
It is then possible to re-factor a lot of the common structures -
vif devices [#1], mr_table [#4] mfc_cache [#6], and use the common
structures in both ipmr and ip6mr.

The rest of the patches re-factor some choice flows used by both ipmr
and ip6mr and eliminates duplicity.

This series would later allow for easy extension of ipmr offloading
to support ip6mr offloading as well, as almost all structures
related to the offloading would be shared between the two protocols.

Changes from previous versions
------------------------------
v2:
  - #6 Corrected reporting logic when hitting an unresolved cache
  - #7 Addressed kernel doc style [Thanks Nikolay]

RFC -> v1:
  - Corrected support for CONFIG_IP{,V6}_MROUTE_MULTIPLE_TABLES
  - Addressed a couple of kbuild test robot issues
====================
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
上级 a25724b0 7b0db857
隐藏空白更改
内联 并排
Showing with 1249 addition and 1172 deletion
drivers/net/ethernet/mellanox/mlxsw/spectrum_mr.c
浏览文件 @ 3c5aa0bc
......@@ -126,8 +126,8 @@ mlxsw_sp_mr_route_ivif_in_evifs(const struct mlxsw_sp_mr_route *mr_route)
switch (mr_route->mr_table->proto) {
case MLXSW_SP_L3_PROTO_IPV4:
ivif = mr_route->mfc4->mfc_parent;
return mr_route->mfc4->mfc_un.res.ttls[ivif] != 255;
ivif = mr_route->mfc4->_c.mfc_parent;
return mr_route->mfc4->_c.mfc_un.res.ttls[ivif] != 255;
case MLXSW_SP_L3_PROTO_IPV6:
/* fall through */
default:
......@@ -364,7 +364,7 @@ mlxsw_sp_mr_route4_create(struct mlxsw_sp_mr_table *mr_table,
mr_route->mfc4 = mfc;
mr_route->mr_table = mr_table;
for (i = 0; i < MAXVIFS; i++) {
if (mfc->mfc_un.res.ttls[i] != 255) {
if (mfc->_c.mfc_un.res.ttls[i] != 255) {
err = mlxsw_sp_mr_route_evif_link(mr_route,
&mr_table->vifs[i]);
if (err)
......@@ -374,7 +374,8 @@ mlxsw_sp_mr_route4_create(struct mlxsw_sp_mr_table *mr_table,
mr_route->min_mtu = mr_table->vifs[i].dev->mtu;
}
}
mlxsw_sp_mr_route_ivif_link(mr_route, &mr_table->vifs[mfc->mfc_parent]);
mlxsw_sp_mr_route_ivif_link(mr_route,
&mr_table->vifs[mfc->_c.mfc_parent]);
mr_route->route_action = mlxsw_sp_mr_route_action(mr_route);
return mr_route;
......@@ -418,9 +419,9 @@ static void mlxsw_sp_mr_mfc_offload_set(struct mlxsw_sp_mr_route *mr_route,
switch (mr_route->mr_table->proto) {
case MLXSW_SP_L3_PROTO_IPV4:
if (offload)
mr_route->mfc4->mfc_flags |= MFC_OFFLOAD;
mr_route->mfc4->_c.mfc_flags |= MFC_OFFLOAD;
else
mr_route->mfc4->mfc_flags &= ~MFC_OFFLOAD;
mr_route->mfc4->_c.mfc_flags &= ~MFC_OFFLOAD;
break;
case MLXSW_SP_L3_PROTO_IPV6:
/* fall through */
......@@ -943,10 +944,10 @@ static void mlxsw_sp_mr_route_stats_update(struct mlxsw_sp *mlxsw_sp,
switch (mr_route->mr_table->proto) {
case MLXSW_SP_L3_PROTO_IPV4:
if (mr_route->mfc4->mfc_un.res.pkt != packets)
mr_route->mfc4->mfc_un.res.lastuse = jiffies;
mr_route->mfc4->mfc_un.res.pkt = packets;
mr_route->mfc4->mfc_un.res.bytes = bytes;
if (mr_route->mfc4->_c.mfc_un.res.pkt != packets)
mr_route->mfc4->_c.mfc_un.res.lastuse = jiffies;
mr_route->mfc4->_c.mfc_un.res.pkt = packets;
mr_route->mfc4->_c.mfc_un.res.bytes = bytes;
break;
case MLXSW_SP_L3_PROTO_IPV6:
/* fall through */
......
include/linux/mroute.h
浏览文件 @ 3c5aa0bc
......@@ -4,11 +4,10 @@
#include <linux/in.h>
#include <linux/pim.h>
#include <linux/rhashtable.h>
#include <net/sock.h>
#include <net/fib_rules.h>
#include <net/fib_notifier.h>
#include <uapi/linux/mroute.h>
#include <linux/mroute_base.h>
#ifdef CONFIG_IP_MROUTE
static inline int ip_mroute_opt(int opt)
......@@ -56,18 +55,6 @@ static inline bool ipmr_rule_default(const struct fib_rule *rule)
}
#endif
struct vif_device {
struct net_device *dev; /* Device we are using */
struct netdev_phys_item_id dev_parent_id; /* Device parent ID */
unsigned long bytes_in,bytes_out;
unsigned long pkt_in,pkt_out; /* Statistics */
unsigned long rate_limit; /* Traffic shaping (NI) */
unsigned char threshold; /* TTL threshold */
unsigned short flags; /* Control flags */
__be32 local,remote; /* Addresses(remote for tunnels)*/
int link; /* Physical interface index */
};
struct vif_entry_notifier_info {
struct fib_notifier_info info;
struct net_device *dev;
......@@ -78,34 +65,6 @@ struct vif_entry_notifier_info {
#define VIFF_STATIC 0x8000
#define VIF_EXISTS(_mrt, _idx) ((_mrt)->vif_table[_idx].dev != NULL)
struct mr_table {
struct list_head list;
possible_net_t net;
u32 id;
struct sock __rcu *mroute_sk;
struct timer_list ipmr_expire_timer;
struct list_head mfc_unres_queue;
struct vif_device vif_table[MAXVIFS];
struct rhltable mfc_hash;
struct list_head mfc_cache_list;
int maxvif;
atomic_t cache_resolve_queue_len;
bool mroute_do_assert;
bool mroute_do_pim;
int mroute_reg_vif_num;
};
/* mfc_flags:
* MFC_STATIC - the entry was added statically (not by a routing daemon)
* MFC_OFFLOAD - the entry was offloaded to the hardware
*/
enum {
MFC_STATIC = BIT(0),
MFC_OFFLOAD = BIT(1),
};
struct mfc_cache_cmp_arg {
__be32 mfc_mcastgrp;
__be32 mfc_origin;
......@@ -113,28 +72,13 @@ struct mfc_cache_cmp_arg {
/**
* struct mfc_cache - multicast routing entries
* @mnode: rhashtable list
* @_c: Common multicast routing information; has to be first [for casting]
* @mfc_mcastgrp: destination multicast group address
* @mfc_origin: source address
* @cmparg: used for rhashtable comparisons
* @mfc_parent: source interface (iif)
* @mfc_flags: entry flags
* @expires: unresolved entry expire time
* @unresolved: unresolved cached skbs
* @last_assert: time of last assert
* @minvif: minimum VIF id
* @maxvif: maximum VIF id
* @bytes: bytes that have passed for this entry
* @pkt: packets that have passed for this entry
* @wrong_if: number of wrong source interface hits
* @lastuse: time of last use of the group (traffic or update)
* @ttls: OIF TTL threshold array
* @refcount: reference count for this entry
* @list: global entry list
* @rcu: used for entry destruction
*/
struct mfc_cache {
struct rhlist_head mnode;
struct mr_mfc _c;
union {
struct {
__be32 mfc_mcastgrp;
......@@ -142,28 +86,6 @@ struct mfc_cache {
};
struct mfc_cache_cmp_arg cmparg;
};
vifi_t mfc_parent;
int mfc_flags;
union {
struct {
unsigned long expires;
struct sk_buff_head unresolved;
} unres;
struct {
unsigned long last_assert;
int minvif;
int maxvif;
unsigned long bytes;
unsigned long pkt;
unsigned long wrong_if;
unsigned long lastuse;
unsigned char ttls[MAXVIFS];
refcount_t refcount;
} res;
} mfc_un;
struct list_head list;
struct rcu_head rcu;
};
struct mfc_entry_notifier_info {
......@@ -187,12 +109,12 @@ static inline void ipmr_cache_free(struct mfc_cache *mfc_cache)
static inline void ipmr_cache_put(struct mfc_cache *c)
{
if (refcount_dec_and_test(&c->mfc_un.res.refcount))
if (refcount_dec_and_test(&c->_c.mfc_un.res.refcount))
ipmr_cache_free(c);
}
static inline void ipmr_cache_hold(struct mfc_cache *c)
{
refcount_inc(&c->mfc_un.res.refcount);
refcount_inc(&c->_c.mfc_un.res.refcount);
}
#endif
include/linux/mroute6.h
浏览文件 @ 3c5aa0bc
......@@ -7,6 +7,7 @@
#include <linux/skbuff.h> /* for struct sk_buff_head */
#include <net/net_namespace.h>
#include <uapi/linux/mroute6.h>
#include <linux/mroute_base.h>
#ifdef CONFIG_IPV6_MROUTE
static inline int ip6_mroute_opt(int opt)
......@@ -62,57 +63,24 @@ static inline void ip6_mr_cleanup(void)
}
#endif
struct mif_device {
struct net_device *dev; /* Device we are using */
unsigned long bytes_in,bytes_out;
unsigned long pkt_in,pkt_out; /* Statistics */
unsigned long rate_limit; /* Traffic shaping (NI) */
unsigned char threshold; /* TTL threshold */
unsigned short flags; /* Control flags */
int link; /* Physical interface index */
};
#define VIFF_STATIC 0x8000
struct mfc6_cache {
struct list_head list;
struct in6_addr mf6c_mcastgrp; /* Group the entry belongs to */
struct in6_addr mf6c_origin; /* Source of packet */
mifi_t mf6c_parent; /* Source interface */
int mfc_flags; /* Flags on line */
struct mfc6_cache_cmp_arg {
struct in6_addr mf6c_mcastgrp;
struct in6_addr mf6c_origin;
};
struct mfc6_cache {
struct mr_mfc _c;
union {
struct {
unsigned long expires;
struct sk_buff_head unresolved; /* Unresolved buffers */
} unres;
struct {
unsigned long last_assert;
int minvif;
int maxvif;
unsigned long bytes;
unsigned long pkt;
unsigned long wrong_if;
unsigned long lastuse;
unsigned char ttls[MAXMIFS]; /* TTL thresholds */
} res;
} mfc_un;
struct in6_addr mf6c_mcastgrp;
struct in6_addr mf6c_origin;
};
struct mfc6_cache_cmp_arg cmparg;
};
};
#define MFC_STATIC 1
#define MFC_NOTIFY 2
#define MFC6_LINES 64
#define MFC6_HASH(a, g) (((__force u32)(a)->s6_addr32[0] ^ \
(__force u32)(a)->s6_addr32[1] ^ \
(__force u32)(a)->s6_addr32[2] ^ \
(__force u32)(a)->s6_addr32[3] ^ \
(__force u32)(g)->s6_addr32[0] ^ \
(__force u32)(g)->s6_addr32[1] ^ \
(__force u32)(g)->s6_addr32[2] ^ \
(__force u32)(g)->s6_addr32[3]) % MFC6_LINES)
#define MFC_ASSERT_THRESH (3*HZ) /* Maximal freq. of asserts */
struct rtmsg;
......@@ -120,12 +88,12 @@ extern int ip6mr_get_route(struct net *net, struct sk_buff *skb,
struct rtmsg *rtm, u32 portid);
#ifdef CONFIG_IPV6_MROUTE
extern struct sock *mroute6_socket(struct net *net, struct sk_buff *skb);
bool mroute6_is_socket(struct net *net, struct sk_buff *skb);
extern int ip6mr_sk_done(struct sock *sk);
#else
static inline struct sock *mroute6_socket(struct net *net, struct sk_buff *skb)
static inline bool mroute6_is_socket(struct net *net, struct sk_buff *skb)
{
return NULL;
return false;
}
static inline int ip6mr_sk_done(struct sock *sk)
{
......
include/linux/mroute_base.h 0 → 100644
浏览文件 @ 3c5aa0bc
#ifndef __LINUX_MROUTE_BASE_H
#define __LINUX_MROUTE_BASE_H
#include <linux/netdevice.h>
#include <linux/rhashtable.h>
#include <linux/spinlock.h>
#include <net/net_namespace.h>
#include <net/sock.h>
/**
* struct vif_device - interface representor for multicast routing
* @dev: network device being used
* @bytes_in: statistic; bytes ingressing
* @bytes_out: statistic; bytes egresing
* @pkt_in: statistic; packets ingressing
* @pkt_out: statistic; packets egressing
* @rate_limit: Traffic shaping (NI)
* @threshold: TTL threshold
* @flags: Control flags
* @link: Physical interface index
* @dev_parent_id: device parent id
* @local: Local address
* @remote: Remote address for tunnels
*/
struct vif_device {
struct net_device *dev;
unsigned long bytes_in, bytes_out;
unsigned long pkt_in, pkt_out;
unsigned long rate_limit;
unsigned char threshold;
unsigned short flags;
int link;
/* Currently only used by ipmr */
struct netdev_phys_item_id dev_parent_id;
__be32 local, remote;
};
#ifndef MAXVIFS
/* This one is nasty; value is defined in uapi using different symbols for
* mroute and morute6 but both map into same 32.
*/
#define MAXVIFS 32
#endif
#define VIF_EXISTS(_mrt, _idx) (!!((_mrt)->vif_table[_idx].dev))
/* mfc_flags:
* MFC_STATIC - the entry was added statically (not by a routing daemon)
* MFC_OFFLOAD - the entry was offloaded to the hardware
*/
enum {
MFC_STATIC = BIT(0),
MFC_OFFLOAD = BIT(1),
};
/**
* struct mr_mfc - common multicast routing entries
* @mnode: rhashtable list
* @mfc_parent: source interface (iif)
* @mfc_flags: entry flags
* @expires: unresolved entry expire time
* @unresolved: unresolved cached skbs
* @last_assert: time of last assert
* @minvif: minimum VIF id
* @maxvif: maximum VIF id
* @bytes: bytes that have passed for this entry
* @pkt: packets that have passed for this entry
* @wrong_if: number of wrong source interface hits
* @lastuse: time of last use of the group (traffic or update)
* @ttls: OIF TTL threshold array
* @refcount: reference count for this entry
* @list: global entry list
* @rcu: used for entry destruction
*/
struct mr_mfc {
struct rhlist_head mnode;
unsigned short mfc_parent;
int mfc_flags;
union {
struct {
unsigned long expires;
struct sk_buff_head unresolved;
} unres;
struct {
unsigned long last_assert;
int minvif;
int maxvif;
unsigned long bytes;
unsigned long pkt;
unsigned long wrong_if;
unsigned long lastuse;
unsigned char ttls[MAXVIFS];
refcount_t refcount;
} res;
} mfc_un;
struct list_head list;
struct rcu_head rcu;
};
struct mr_table;
/**
* struct mr_table_ops - callbacks and info for protocol-specific ops
* @rht_params: parameters for accessing the MFC hash
* @cmparg_any: a hash key to be used for matching on (*,*) routes
*/
struct mr_table_ops {
const struct rhashtable_params *rht_params;
void *cmparg_any;
};
/**
* struct mr_table - a multicast routing table
* @list: entry within a list of multicast routing tables
* @net: net where this table belongs
* @ops: protocol specific operations
* @id: identifier of the table
* @mroute_sk: socket associated with the table
* @ipmr_expire_timer: timer for handling unresolved routes
* @mfc_unres_queue: list of unresolved MFC entries
* @vif_table: array containing all possible vifs
* @mfc_hash: Hash table of all resolved routes for easy lookup
* @mfc_cache_list: list of resovled routes for possible traversal
* @maxvif: Identifier of highest value vif currently in use
* @cache_resolve_queue_len: current size of unresolved queue
* @mroute_do_assert: Whether to inform userspace on wrong ingress
* @mroute_do_pim: Whether to receive IGMP PIMv1
* @mroute_reg_vif_num: PIM-device vif index
*/
struct mr_table {
struct list_head list;
possible_net_t net;
struct mr_table_ops ops;
u32 id;
struct sock __rcu *mroute_sk;
struct timer_list ipmr_expire_timer;
struct list_head mfc_unres_queue;
struct vif_device vif_table[MAXVIFS];
struct rhltable mfc_hash;
struct list_head mfc_cache_list;
int maxvif;
atomic_t cache_resolve_queue_len;
bool mroute_do_assert;
bool mroute_do_pim;
int mroute_reg_vif_num;
};
#ifdef CONFIG_IP_MROUTE_COMMON
void vif_device_init(struct vif_device *v,
struct net_device *dev,
unsigned long rate_limit,
unsigned char threshold,
unsigned short flags,
unsigned short get_iflink_mask);
struct mr_table *
mr_table_alloc(struct net *net, u32 id,
struct mr_table_ops *ops,
void (*expire_func)(struct timer_list *t),
void (*table_set)(struct mr_table *mrt,
struct net *net));
/* These actually return 'struct mr_mfc *', but to avoid need for explicit
* castings they simply return void.
*/
void *mr_mfc_find_parent(struct mr_table *mrt,
void *hasharg, int parent);
void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi);
void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg);
int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
struct mr_mfc *c, struct rtmsg *rtm);
int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb,
struct mr_table *(*iter)(struct net *net,
struct mr_table *mrt),
int (*fill)(struct mr_table *mrt,
struct sk_buff *skb,
u32 portid, u32 seq, struct mr_mfc *c,
int cmd, int flags),
spinlock_t *lock);
#else
static inline void vif_device_init(struct vif_device *v,
struct net_device *dev,
unsigned long rate_limit,
unsigned char threshold,
unsigned short flags,
unsigned short get_iflink_mask)
{
}
static inline void *
mr_table_alloc(struct net *net, u32 id,
struct mr_table_ops *ops,
void (*expire_func)(struct timer_list *t),
void (*table_set)(struct mr_table *mrt,
struct net *net))
{
return NULL;
}
static inline void *mr_mfc_find_parent(struct mr_table *mrt,
void *hasharg, int parent)
{
return NULL;
}
static inline void *mr_mfc_find_any_parent(struct mr_table *mrt,
int vifi)
{
return NULL;
}
static inline struct mr_mfc *mr_mfc_find_any(struct mr_table *mrt,
int vifi, void *hasharg)
{
return NULL;
}
static inline int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
struct mr_mfc *c, struct rtmsg *rtm)
{
return -EINVAL;
}
static inline int
mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb,
struct mr_table *(*iter)(struct net *net,
struct mr_table *mrt),
int (*fill)(struct mr_table *mrt,
struct sk_buff *skb,
u32 portid, u32 seq, struct mr_mfc *c,
int cmd, int flags),
spinlock_t *lock)
{
return -EINVAL;
}
#endif
static inline void *mr_mfc_find(struct mr_table *mrt, void *hasharg)
{
return mr_mfc_find_parent(mrt, hasharg, -1);
}
#ifdef CONFIG_PROC_FS
struct mr_vif_iter {
struct seq_net_private p;
struct mr_table *mrt;
int ct;
};
struct mr_mfc_iter {
struct seq_net_private p;
struct mr_table *mrt;
struct list_head *cache;
/* Lock protecting the mr_table's unresolved queue */
spinlock_t *lock;
};
#ifdef CONFIG_IP_MROUTE_COMMON
void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos);
void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos);
static inline void *mr_vif_seq_start(struct seq_file *seq, loff_t *pos)
{
return *pos ? mr_vif_seq_idx(seq_file_net(seq),
seq->private, *pos - 1)
: SEQ_START_TOKEN;
}
/* These actually return 'struct mr_mfc *', but to avoid need for explicit
* castings they simply return void.
*/
void *mr_mfc_seq_idx(struct net *net,
struct mr_mfc_iter *it, loff_t pos);
void *mr_mfc_seq_next(struct seq_file *seq, void *v,
loff_t *pos);
static inline void *mr_mfc_seq_start(struct seq_file *seq, loff_t *pos,
struct mr_table *mrt, spinlock_t *lock)
{
struct mr_mfc_iter *it = seq->private;
it->mrt = mrt;
it->cache = NULL;
it->lock = lock;
return *pos ? mr_mfc_seq_idx(seq_file_net(seq),
seq->private, *pos - 1)
: SEQ_START_TOKEN;
}
static inline void mr_mfc_seq_stop(struct seq_file *seq, void *v)
{
struct mr_mfc_iter *it = seq->private;
struct mr_table *mrt = it->mrt;
if (it->cache == &mrt->mfc_unres_queue)
spin_unlock_bh(it->lock);
else if (it->cache == &mrt->mfc_cache_list)
rcu_read_unlock();
}
#else
static inline void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter,
loff_t pos)
{
return NULL;
}
static inline void *mr_vif_seq_next(struct seq_file *seq,
void *v, loff_t *pos)
{
return NULL;
}
static inline void *mr_vif_seq_start(struct seq_file *seq, loff_t *pos)
{
return NULL;
}
static inline void *mr_mfc_seq_idx(struct net *net,
struct mr_mfc_iter *it, loff_t pos)
{
return NULL;
}
static inline void *mr_mfc_seq_next(struct seq_file *seq, void *v,
loff_t *pos)
{
return NULL;
}
static inline void *mr_mfc_seq_start(struct seq_file *seq, loff_t *pos,
struct mr_table *mrt, spinlock_t *lock)
{
return NULL;
}
static inline void mr_mfc_seq_stop(struct seq_file *seq, void *v)
{
}
#endif
#endif
#endif
include/net/netns/ipv6.h
浏览文件 @ 3c5aa0bc
......@@ -85,7 +85,7 @@ struct netns_ipv6 {
struct sock *mc_autojoin_sk;
#ifdef CONFIG_IPV6_MROUTE
#ifndef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
struct mr6_table *mrt6;
struct mr_table *mrt6;
#else
struct list_head mr6_tables;
struct fib_rules_ops *mr6_rules_ops;
......
net/ipv4/Kconfig
浏览文件 @ 3c5aa0bc
......@@ -212,9 +212,14 @@ config NET_IPGRE_BROADCAST
Network), but can be distributed all over the Internet. If you want
to do that, say Y here and to "IP multicast routing" below.
config IP_MROUTE_COMMON
bool
depends on IP_MROUTE || IPV6_MROUTE
config IP_MROUTE
bool "IP: multicast routing"
depends on IP_MULTICAST
select IP_MROUTE_COMMON
help
This is used if you want your machine to act as a router for IP
packets that have several destination addresses. It is needed on the
......
net/ipv4/Makefile
浏览文件 @ 3c5aa0bc
......@@ -20,6 +20,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o
obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
obj-$(CONFIG_IP_MROUTE) += ipmr.o
obj-$(CONFIG_IP_MROUTE_COMMON) += ipmr_base.o
obj-$(CONFIG_NET_IPIP) += ipip.o
gre-y := gre_demux.o
obj-$(CONFIG_NET_FOU) += fou.o
......
net/ipv4/ipmr.c
浏览文件 @ 3c5aa0bc
......@@ -31,7 +31,6 @@
#include <linux/cache.h>
#include <linux/capability.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/kernel.h>
#include <linux/fcntl.h>
......@@ -53,7 +52,6 @@
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/route.h>
#include <net/sock.h>
#include <net/icmp.h>
#include <net/udp.h>
#include <net/raw.h>
......@@ -107,8 +105,6 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt,
struct mfc_cache *cache, int local);
static int ipmr_cache_report(struct mr_table *mrt,
struct sk_buff *pkt, vifi_t vifi, int assert);
static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
struct mfc_cache *c, struct rtmsg *rtm);
static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
int cmd);
static void igmpmsg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt);
......@@ -119,6 +115,23 @@ static void ipmr_expire_process(struct timer_list *t);
#define ipmr_for_each_table(mrt, net) \
list_for_each_entry_rcu(mrt, &net->ipv4.mr_tables, list)
static struct mr_table *ipmr_mr_table_iter(struct net *net,
struct mr_table *mrt)
{
struct mr_table *ret;
if (!mrt)
ret = list_entry_rcu(net->ipv4.mr_tables.next,
struct mr_table, list);
else
ret = list_entry_rcu(mrt->list.next,
struct mr_table, list);
if (&ret->list == &net->ipv4.mr_tables)
return NULL;
return ret;
}
static struct mr_table *ipmr_get_table(struct net *net, u32 id)
{
struct mr_table *mrt;
......@@ -286,6 +299,14 @@ EXPORT_SYMBOL(ipmr_rule_default);
#define ipmr_for_each_table(mrt, net) \
for (mrt = net->ipv4.mrt; mrt; mrt = NULL)
static struct mr_table *ipmr_mr_table_iter(struct net *net,
struct mr_table *mrt)
{
if (!mrt)
return net->ipv4.mrt;
return NULL;
}
static struct mr_table *ipmr_get_table(struct net *net, u32 id)
{
return net->ipv4.mrt;
......@@ -345,7 +366,7 @@ static inline int ipmr_hash_cmp(struct rhashtable_compare_arg *arg,
}
static const struct rhashtable_params ipmr_rht_params = {
.head_offset = offsetof(struct mfc_cache, mnode),
.head_offset = offsetof(struct mr_mfc, mnode),
.key_offset = offsetof(struct mfc_cache, cmparg),
.key_len = sizeof(struct mfc_cache_cmp_arg),
.nelem_hint = 3,
......@@ -354,6 +375,24 @@ static const struct rhashtable_params ipmr_rht_params = {
.automatic_shrinking = true,
};
static void ipmr_new_table_set(struct mr_table *mrt,
struct net *net)
{
#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables);
#endif
}
static struct mfc_cache_cmp_arg ipmr_mr_table_ops_cmparg_any = {
.mfc_mcastgrp = htonl(INADDR_ANY),
.mfc_origin = htonl(INADDR_ANY),
};
static struct mr_table_ops ipmr_mr_table_ops = {
.rht_params = &ipmr_rht_params,
.cmparg_any = &ipmr_mr_table_ops_cmparg_any,
};
static struct mr_table *ipmr_new_table(struct net *net, u32 id)
{
struct mr_table *mrt;
......@@ -366,23 +405,8 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
if (mrt)
return mrt;
mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
if (!mrt)
return ERR_PTR(-ENOMEM);
write_pnet(&mrt->net, net);
mrt->id = id;
rhltable_init(&mrt->mfc_hash, &ipmr_rht_params);
INIT_LIST_HEAD(&mrt->mfc_cache_list);
INIT_LIST_HEAD(&mrt->mfc_unres_queue);
timer_setup(&mrt->ipmr_expire_timer, ipmr_expire_process, 0);
mrt->mroute_reg_vif_num = -1;
#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
list_add_tail_rcu(&mrt->list, &net->ipv4.mr_tables);
#endif
return mrt;
return mr_table_alloc(net, id, &ipmr_mr_table_ops,
ipmr_expire_process, ipmr_new_table_set);
}
static void ipmr_free_table(struct mr_table *mrt)
......@@ -761,14 +785,14 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify,
static void ipmr_cache_free_rcu(struct rcu_head *head)
{
struct mfc_cache *c = container_of(head, struct mfc_cache, rcu);
struct mr_mfc *c = container_of(head, struct mr_mfc, rcu);
kmem_cache_free(mrt_cachep, c);
kmem_cache_free(mrt_cachep, (struct mfc_cache *)c);
}
void ipmr_cache_free(struct mfc_cache *c)
{
call_rcu(&c->rcu, ipmr_cache_free_rcu);
call_rcu(&c->_c.rcu, ipmr_cache_free_rcu);
}
EXPORT_SYMBOL(ipmr_cache_free);
......@@ -783,7 +807,7 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c)
atomic_dec(&mrt->cache_resolve_queue_len);
while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved))) {
while ((skb = skb_dequeue(&c->_c.mfc_un.unres.unresolved))) {
if (ip_hdr(skb)->version == 0) {
struct nlmsghdr *nlh = skb_pull(skb,
sizeof(struct iphdr));
......@@ -807,9 +831,9 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c)
static void ipmr_expire_process(struct timer_list *t)
{
struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer);
unsigned long now;
struct mr_mfc *c, *next;
unsigned long expires;
struct mfc_cache *c, *next;
unsigned long now;
if (!spin_trylock(&mfc_unres_lock)) {
mod_timer(&mrt->ipmr_expire_timer, jiffies+HZ/10);
......@@ -831,8 +855,8 @@ static void ipmr_expire_process(struct timer_list *t)
}
list_del(&c->list);
mroute_netlink_event(mrt, c, RTM_DELROUTE);
ipmr_destroy_unres(mrt, c);
mroute_netlink_event(mrt, (struct mfc_cache *)c, RTM_DELROUTE);
ipmr_destroy_unres(mrt, (struct mfc_cache *)c);
}
if (!list_empty(&mrt->mfc_unres_queue))
......@@ -843,7 +867,7 @@ static void ipmr_expire_process(struct timer_list *t)
}
/* Fill oifs list. It is called under write locked mrt_lock. */
static void ipmr_update_thresholds(struct mr_table *mrt, struct mfc_cache *cache,
static void ipmr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache,
unsigned char *ttls)
{
int vifi;
......@@ -945,6 +969,10 @@ static int vif_add(struct net *net, struct mr_table *mrt,
ip_rt_multicast_event(in_dev);
/* Fill in the VIF structures */
vif_device_init(v, dev, vifc->vifc_rate_limit,
vifc->vifc_threshold,
vifc->vifc_flags | (!mrtsock ? VIFF_STATIC : 0),
(VIFF_TUNNEL | VIFF_REGISTER));
attr.orig_dev = dev;
if (!switchdev_port_attr_get(dev, &attr)) {
......@@ -953,20 +981,9 @@ static int vif_add(struct net *net, struct mr_table *mrt,
} else {
v->dev_parent_id.id_len = 0;
}
v->rate_limit = vifc->vifc_rate_limit;
v->local = vifc->vifc_lcl_addr.s_addr;
v->remote = vifc->vifc_rmt_addr.s_addr;
v->flags = vifc->vifc_flags;
if (!mrtsock)
v->flags |= VIFF_STATIC;
v->threshold = vifc->vifc_threshold;
v->bytes_in = 0;
v->bytes_out = 0;
v->pkt_in = 0;
v->pkt_out = 0;
v->link = dev->ifindex;
if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER))
v->link = dev_get_iflink(dev);
/* And finish update writing critical data */
write_lock_bh(&mrt_lock);
......@@ -989,33 +1006,8 @@ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt,
.mfc_mcastgrp = mcastgrp,
.mfc_origin = origin
};
struct rhlist_head *tmp, *list;
struct mfc_cache *c;
list = rhltable_lookup(&mrt->mfc_hash, &arg, ipmr_rht_params);
rhl_for_each_entry_rcu(c, tmp, list, mnode)
return c;
return NULL;
}
/* Look for a (*,*,oif) entry */
static struct mfc_cache *ipmr_cache_find_any_parent(struct mr_table *mrt,
int vifi)
{
struct mfc_cache_cmp_arg arg = {
.mfc_mcastgrp = htonl(INADDR_ANY),
.mfc_origin = htonl(INADDR_ANY)
};
struct rhlist_head *tmp, *list;
struct mfc_cache *c;
list = rhltable_lookup(&mrt->mfc_hash, &arg, ipmr_rht_params);
rhl_for_each_entry_rcu(c, tmp, list, mnode)
if (c->mfc_un.res.ttls[vifi] < 255)
return c;
return NULL;
return mr_mfc_find(mrt, &arg);
}
/* Look for a (*,G) entry */
......@@ -1026,25 +1018,10 @@ static struct mfc_cache *ipmr_cache_find_any(struct mr_table *mrt,
.mfc_mcastgrp = mcastgrp,
.mfc_origin = htonl(INADDR_ANY)
};
struct rhlist_head *tmp, *list;
struct mfc_cache *c, *proxy;
if (mcastgrp == htonl(INADDR_ANY))
goto skip;
list = rhltable_lookup(&mrt->mfc_hash, &arg, ipmr_rht_params);
rhl_for_each_entry_rcu(c, tmp, list, mnode) {
if (c->mfc_un.res.ttls[vifi] < 255)
return c;
/* It's ok if the vifi is part of the static tree */
proxy = ipmr_cache_find_any_parent(mrt, c->mfc_parent);
if (proxy && proxy->mfc_un.res.ttls[vifi] < 255)
return c;
}
skip:
return ipmr_cache_find_any_parent(mrt, vifi);
return mr_mfc_find_any_parent(mrt, vifi);
return mr_mfc_find_any(mrt, vifi, &arg);
}
/* Look for a (S,G,iif) entry if parent != -1 */
......@@ -1056,15 +1033,8 @@ static struct mfc_cache *ipmr_cache_find_parent(struct mr_table *mrt,
.mfc_mcastgrp = mcastgrp,
.mfc_origin = origin,
};
struct rhlist_head *tmp, *list;
struct mfc_cache *c;
list = rhltable_lookup(&mrt->mfc_hash, &arg, ipmr_rht_params);
rhl_for_each_entry_rcu(c, tmp, list, mnode)
if (parent == -1 || parent == c->mfc_parent)
return c;
return NULL;
return mr_mfc_find_parent(mrt, &arg, parent);
}
/* Allocate a multicast cache entry */
......@@ -1073,9 +1043,9 @@ static struct mfc_cache *ipmr_cache_alloc(void)
struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
if (c) {
c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
c->mfc_un.res.minvif = MAXVIFS;
refcount_set(&c->mfc_un.res.refcount, 1);
c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
c->_c.mfc_un.res.minvif = MAXVIFS;
refcount_set(&c->_c.mfc_un.res.refcount, 1);
}
return c;
}
......@@ -1085,8 +1055,8 @@ static struct mfc_cache *ipmr_cache_alloc_unres(void)
struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC);
if (c) {
skb_queue_head_init(&c->mfc_un.unres.unresolved);
c->mfc_un.unres.expires = jiffies + 10*HZ;
skb_queue_head_init(&c->_c.mfc_un.unres.unresolved);
c->_c.mfc_un.unres.expires = jiffies + 10 * HZ;
}
return c;
}
......@@ -1099,12 +1069,13 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt,
struct nlmsgerr *e;
/* Play the pending entries through our router */
while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) {
while ((skb = __skb_dequeue(&uc->_c.mfc_un.unres.unresolved))) {
if (ip_hdr(skb)->version == 0) {
struct nlmsghdr *nlh = skb_pull(skb,
sizeof(struct iphdr));
if (__ipmr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) {
if (mr_fill_mroute(mrt, skb, &c->_c,
nlmsg_data(nlh)) > 0) {
nlh->nlmsg_len = skb_tail_pointer(skb) -
(u8 *)nlh;
} else {
......@@ -1212,7 +1183,7 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi,
int err;
spin_lock_bh(&mfc_unres_lock);
list_for_each_entry(c, &mrt->mfc_unres_queue, list) {
list_for_each_entry(c, &mrt->mfc_unres_queue, _c.list) {
if (c->mfc_mcastgrp == iph->daddr &&
c->mfc_origin == iph->saddr) {
found = true;
......@@ -1231,12 +1202,13 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi,
}
/* Fill in the new cache entry */
c->mfc_parent = -1;
c->_c.mfc_parent = -1;
c->mfc_origin = iph->saddr;
c->mfc_mcastgrp = iph->daddr;
/* Reflect first query at mrouted. */
err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE);
if (err < 0) {
/* If the report failed throw the cache entry
out - Brad Parker
......@@ -1249,15 +1221,16 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi,
}
atomic_inc(&mrt->cache_resolve_queue_len);
list_add(&c->list, &mrt->mfc_unres_queue);
list_add(&c->_c.list, &mrt->mfc_unres_queue);
mroute_netlink_event(mrt, c, RTM_NEWROUTE);
if (atomic_read(&mrt->cache_resolve_queue_len) == 1)
mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires);
mod_timer(&mrt->ipmr_expire_timer,
c->_c.mfc_un.unres.expires);
}
/* See if we can append the packet */
if (c->mfc_un.unres.unresolved.qlen > 3) {
if (c->_c.mfc_un.unres.unresolved.qlen > 3) {
kfree_skb(skb);
err = -ENOBUFS;
} else {
......@@ -1265,7 +1238,7 @@ static int ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi,
skb->dev = dev;
skb->skb_iif = dev->ifindex;
}
skb_queue_tail(&c->mfc_un.unres.unresolved, skb);
skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb);
err = 0;
}
......@@ -1287,8 +1260,8 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc, int parent)
rcu_read_unlock();
if (!c)
return -ENOENT;
rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params);
list_del_rcu(&c->list);
rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ipmr_rht_params);
list_del_rcu(&c->_c.list);
call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c, mrt->id);
mroute_netlink_event(mrt, c, RTM_DELROUTE);
ipmr_cache_put(c);
......@@ -1300,6 +1273,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
struct mfcctl *mfc, int mrtsock, int parent)
{
struct mfc_cache *uc, *c;
struct mr_mfc *_uc;
bool found;
int ret;
......@@ -1313,10 +1287,10 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
rcu_read_unlock();
if (c) {
write_lock_bh(&mrt_lock);
c->mfc_parent = mfc->mfcc_parent;
ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls);
c->_c.mfc_parent = mfc->mfcc_parent;
ipmr_update_thresholds(mrt, &c->_c, mfc->mfcc_ttls);
if (!mrtsock)
c->mfc_flags |= MFC_STATIC;
c->_c.mfc_flags |= MFC_STATIC;
write_unlock_bh(&mrt_lock);
call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE, c,
mrt->id);
......@@ -1334,28 +1308,29 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
c->mfc_origin = mfc->mfcc_origin.s_addr;
c->mfc_mcastgrp = mfc->mfcc_mcastgrp.s_addr;
c->mfc_parent = mfc->mfcc_parent;
ipmr_update_thresholds(mrt, c, mfc->mfcc_ttls);
c->_c.mfc_parent = mfc->mfcc_parent;
ipmr_update_thresholds(mrt, &c->_c, mfc->mfcc_ttls);
if (!mrtsock)
c->mfc_flags |= MFC_STATIC;
c->_c.mfc_flags |= MFC_STATIC;
ret = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->mnode,
ret = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->_c.mnode,
ipmr_rht_params);
if (ret) {
pr_err("ipmr: rhtable insert error %d\n", ret);
ipmr_cache_free(c);
return ret;
}
list_add_tail_rcu(&c->list, &mrt->mfc_cache_list);
list_add_tail_rcu(&c->_c.list, &mrt->mfc_cache_list);
/* Check to see if we resolved a queued list. If so we
* need to send on the frames and tidy up.
*/
found = false;
spin_lock_bh(&mfc_unres_lock);
list_for_each_entry(uc, &mrt->mfc_unres_queue, list) {
list_for_each_entry(_uc, &mrt->mfc_unres_queue, list) {
uc = (struct mfc_cache *)_uc;
if (uc->mfc_origin == c->mfc_origin &&
uc->mfc_mcastgrp == c->mfc_mcastgrp) {
list_del(&uc->list);
list_del(&_uc->list);
atomic_dec(&mrt->cache_resolve_queue_len);
found = true;
break;
......@@ -1378,7 +1353,8 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
static void mroute_clean_tables(struct mr_table *mrt, bool all)
{
struct net *net = read_pnet(&mrt->net);
struct mfc_cache *c, *tmp;
struct mr_mfc *c, *tmp;
struct mfc_cache *cache;
LIST_HEAD(list);
int i;
......@@ -1396,18 +1372,20 @@ static void mroute_clean_tables(struct mr_table *mrt, bool all)
continue;
rhltable_remove(&mrt->mfc_hash, &c->mnode, ipmr_rht_params);
list_del_rcu(&c->list);
call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, c,
cache = (struct mfc_cache *)c;
call_ipmr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, cache,
mrt->id);
mroute_netlink_event(mrt, c, RTM_DELROUTE);
ipmr_cache_put(c);
mroute_netlink_event(mrt, cache, RTM_DELROUTE);
ipmr_cache_put(cache);
}
if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
spin_lock_bh(&mfc_unres_lock);
list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) {
list_del(&c->list);
mroute_netlink_event(mrt, c, RTM_DELROUTE);
ipmr_destroy_unres(mrt, c);
cache = (struct mfc_cache *)c;
mroute_netlink_event(mrt, cache, RTM_DELROUTE);
ipmr_destroy_unres(mrt, cache);
}
spin_unlock_bh(&mfc_unres_lock);
}
......@@ -1699,9 +1677,9 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg)
rcu_read_lock();
c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr);
if (c) {
sr.pktcnt = c->mfc_un.res.pkt;
sr.bytecnt = c->mfc_un.res.bytes;
sr.wrong_if = c->mfc_un.res.wrong_if;
sr.pktcnt = c->_c.mfc_un.res.pkt;
sr.bytecnt = c->_c.mfc_un.res.bytes;
sr.wrong_if = c->_c.mfc_un.res.wrong_if;
rcu_read_unlock();
if (copy_to_user(arg, &sr, sizeof(sr)))
......@@ -1773,9 +1751,9 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
rcu_read_lock();
c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr);
if (c) {
sr.pktcnt = c->mfc_un.res.pkt;
sr.bytecnt = c->mfc_un.res.bytes;
sr.wrong_if = c->mfc_un.res.wrong_if;
sr.pktcnt = c->_c.mfc_un.res.pkt;
sr.bytecnt = c->_c.mfc_un.res.bytes;
sr.wrong_if = c->_c.mfc_un.res.wrong_if;
rcu_read_unlock();
if (copy_to_user(arg, &sr, sizeof(sr)))
......@@ -1999,26 +1977,26 @@ static int ipmr_find_vif(struct mr_table *mrt, struct net_device *dev)
/* "local" means that we should preserve one skb (for local delivery) */
static void ip_mr_forward(struct net *net, struct mr_table *mrt,
struct net_device *dev, struct sk_buff *skb,
struct mfc_cache *cache, int local)
struct mfc_cache *c, int local)
{
int true_vifi = ipmr_find_vif(mrt, dev);
int psend = -1;
int vif, ct;
vif = cache->mfc_parent;
cache->mfc_un.res.pkt++;
cache->mfc_un.res.bytes += skb->len;
cache->mfc_un.res.lastuse = jiffies;
vif = c->_c.mfc_parent;
c->_c.mfc_un.res.pkt++;
c->_c.mfc_un.res.bytes += skb->len;
c->_c.mfc_un.res.lastuse = jiffies;
if (cache->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) {
if (c->mfc_origin == htonl(INADDR_ANY) && true_vifi >= 0) {
struct mfc_cache *cache_proxy;
/* For an (*,G) entry, we only check that the incomming
* interface is part of the static tree.
*/
cache_proxy = ipmr_cache_find_any_parent(mrt, vif);
cache_proxy = mr_mfc_find_any_parent(mrt, vif);
if (cache_proxy &&
cache_proxy->mfc_un.res.ttls[true_vifi] < 255)
cache_proxy->_c.mfc_un.res.ttls[true_vifi] < 255)
goto forward;
}
......@@ -2039,7 +2017,7 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt,
goto dont_forward;
}
cache->mfc_un.res.wrong_if++;
c->_c.mfc_un.res.wrong_if++;
if (true_vifi >= 0 && mrt->mroute_do_assert &&
/* pimsm uses asserts, when switching from RPT to SPT,
......@@ -2048,10 +2026,11 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt,
* large chunk of pimd to kernel. Ough... --ANK
*/
(mrt->mroute_do_pim ||
cache->mfc_un.res.ttls[true_vifi] < 255) &&
c->_c.mfc_un.res.ttls[true_vifi] < 255) &&
time_after(jiffies,
cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) {
cache->mfc_un.res.last_assert = jiffies;
c->_c.mfc_un.res.last_assert +
MFC_ASSERT_THRESH)) {
c->_c.mfc_un.res.last_assert = jiffies;
ipmr_cache_report(mrt, skb, true_vifi, IGMPMSG_WRONGVIF);
}
goto dont_forward;
......@@ -2062,33 +2041,33 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt,
mrt->vif_table[vif].bytes_in += skb->len;
/* Forward the frame */
if (cache->mfc_origin == htonl(INADDR_ANY) &&
cache->mfc_mcastgrp == htonl(INADDR_ANY)) {
if (c->mfc_origin == htonl(INADDR_ANY) &&
c->mfc_mcastgrp == htonl(INADDR_ANY)) {
if (true_vifi >= 0 &&
true_vifi != cache->mfc_parent &&
true_vifi != c->_c.mfc_parent &&
ip_hdr(skb)->ttl >
cache->mfc_un.res.ttls[cache->mfc_parent]) {
c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) {
/* It's an (*,*) entry and the packet is not coming from
* the upstream: forward the packet to the upstream
* only.
*/
psend = cache->mfc_parent;
psend = c->_c.mfc_parent;
goto last_forward;
}
goto dont_forward;
}
for (ct = cache->mfc_un.res.maxvif - 1;
ct >= cache->mfc_un.res.minvif; ct--) {
for (ct = c->_c.mfc_un.res.maxvif - 1;
ct >= c->_c.mfc_un.res.minvif; ct--) {
/* For (*,G) entry, don't forward to the incoming interface */
if ((cache->mfc_origin != htonl(INADDR_ANY) ||
if ((c->mfc_origin != htonl(INADDR_ANY) ||
ct != true_vifi) &&
ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) {
ip_hdr(skb)->ttl > c->_c.mfc_un.res.ttls[ct]) {
if (psend != -1) {
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2)
ipmr_queue_xmit(net, mrt, true_vifi,
skb2, cache, psend);
skb2, c, psend);
}
psend = ct;
}
......@@ -2100,9 +2079,9 @@ static void ip_mr_forward(struct net *net, struct mr_table *mrt,
if (skb2)
ipmr_queue_xmit(net, mrt, true_vifi, skb2,
cache, psend);
c, psend);
} else {
ipmr_queue_xmit(net, mrt, true_vifi, skb, cache, psend);
ipmr_queue_xmit(net, mrt, true_vifi, skb, c, psend);
return;
}
}
......@@ -2300,62 +2279,6 @@ static int pim_rcv(struct sk_buff *skb)
}
#endif
static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
struct mfc_cache *c, struct rtmsg *rtm)
{
struct rta_mfc_stats mfcs;
struct nlattr *mp_attr;
struct rtnexthop *nhp;
unsigned long lastuse;
int ct;
/* If cache is unresolved, don't try to parse IIF and OIF */
if (c->mfc_parent >= MAXVIFS) {
rtm->rtm_flags |= RTNH_F_UNRESOLVED;
return -ENOENT;
}
if (VIF_EXISTS(mrt, c->mfc_parent) &&
nla_put_u32(skb, RTA_IIF, mrt->vif_table[c->mfc_parent].dev->ifindex) < 0)
return -EMSGSIZE;
if (c->mfc_flags & MFC_OFFLOAD)
rtm->rtm_flags |= RTNH_F_OFFLOAD;
if (!(mp_attr = nla_nest_start(skb, RTA_MULTIPATH)))
return -EMSGSIZE;
for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) {
if (!(nhp = nla_reserve_nohdr(skb, sizeof(*nhp)))) {
nla_nest_cancel(skb, mp_attr);
return -EMSGSIZE;
}
nhp->rtnh_flags = 0;
nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
nhp->rtnh_ifindex = mrt->vif_table[ct].dev->ifindex;
nhp->rtnh_len = sizeof(*nhp);
}
}
nla_nest_end(skb, mp_attr);
lastuse = READ_ONCE(c->mfc_un.res.lastuse);
lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0;
mfcs.mfcs_packets = c->mfc_un.res.pkt;
mfcs.mfcs_bytes = c->mfc_un.res.bytes;
mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) ||
nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse),
RTA_PAD))
return -EMSGSIZE;
rtm->rtm_type = RTN_MULTICAST;
return 1;
}
int ipmr_get_route(struct net *net, struct sk_buff *skb,
__be32 saddr, __be32 daddr,
struct rtmsg *rtm, u32 portid)
......@@ -2413,7 +2336,7 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb,
}
read_lock(&mrt_lock);
err = __ipmr_fill_mroute(mrt, skb, cache, rtm);
err = mr_fill_mroute(mrt, skb, &cache->_c, rtm);
read_unlock(&mrt_lock);
rcu_read_unlock();
return err;
......@@ -2441,7 +2364,7 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
goto nla_put_failure;
rtm->rtm_type = RTN_MULTICAST;
rtm->rtm_scope = RT_SCOPE_UNIVERSE;
if (c->mfc_flags & MFC_STATIC)
if (c->_c.mfc_flags & MFC_STATIC)
rtm->rtm_protocol = RTPROT_STATIC;
else
rtm->rtm_protocol = RTPROT_MROUTED;
......@@ -2450,7 +2373,7 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
if (nla_put_in_addr(skb, RTA_SRC, c->mfc_origin) ||
nla_put_in_addr(skb, RTA_DST, c->mfc_mcastgrp))
goto nla_put_failure;
err = __ipmr_fill_mroute(mrt, skb, c, rtm);
err = mr_fill_mroute(mrt, skb, &c->_c, rtm);
/* do not break the dump if cache is unresolved */
if (err < 0 && err != -ENOENT)
goto nla_put_failure;
......@@ -2463,6 +2386,14 @@ static int ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
return -EMSGSIZE;
}
static int _ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
u32 portid, u32 seq, struct mr_mfc *c, int cmd,
int flags)
{
return ipmr_fill_mroute(mrt, skb, portid, seq, (struct mfc_cache *)c,
cmd, flags);
}
static size_t mroute_msgsize(bool unresolved, int maxvif)
{
size_t len =
......@@ -2491,7 +2422,8 @@ static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
struct sk_buff *skb;
int err = -ENOBUFS;
skb = nlmsg_new(mroute_msgsize(mfc->mfc_parent >= MAXVIFS, mrt->maxvif),
skb = nlmsg_new(mroute_msgsize(mfc->_c.mfc_parent >= MAXVIFS,
mrt->maxvif),
GFP_ATOMIC);
if (!skb)
goto errout;
......@@ -2635,62 +2567,8 @@ static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
struct mr_table *mrt;
struct mfc_cache *mfc;
unsigned int t = 0, s_t;
unsigned int e = 0, s_e;
s_t = cb->args[0];
s_e = cb->args[1];
rcu_read_lock();
ipmr_for_each_table(mrt, net) {
if (t < s_t)
goto next_table;
list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) {
if (e < s_e)
goto next_entry;
if (ipmr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
mfc, RTM_NEWROUTE,
NLM_F_MULTI) < 0)
goto done;
next_entry:
e++;
}
e = 0;
s_e = 0;
spin_lock_bh(&mfc_unres_lock);
list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) {
if (e < s_e)
goto next_entry2;
if (ipmr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
mfc, RTM_NEWROUTE,
NLM_F_MULTI) < 0) {
spin_unlock_bh(&mfc_unres_lock);
goto done;
}
next_entry2:
e++;
}
spin_unlock_bh(&mfc_unres_lock);
e = 0;
s_e = 0;
next_table:
t++;
}
done:
rcu_read_unlock();
cb->args[1] = e;
cb->args[0] = t;
return skb->len;
return mr_rtm_dumproute(skb, cb, ipmr_mr_table_iter,
_ipmr_fill_mroute, &mfc_unres_lock);
}
static const struct nla_policy rtm_ipmr_policy[RTA_MAX + 1] = {
......@@ -2947,31 +2825,11 @@ static int ipmr_rtm_dumplink(struct sk_buff *skb, struct netlink_callback *cb)
/* The /proc interfaces to multicast routing :
* /proc/net/ip_mr_cache & /proc/net/ip_mr_vif
*/
struct ipmr_vif_iter {
struct seq_net_private p;
struct mr_table *mrt;
int ct;
};
static struct vif_device *ipmr_vif_seq_idx(struct net *net,
struct ipmr_vif_iter *iter,
loff_t pos)
{
struct mr_table *mrt = iter->mrt;
for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) {
if (!VIF_EXISTS(mrt, iter->ct))
continue;
if (pos-- == 0)
return &mrt->vif_table[iter->ct];
}
return NULL;
}
static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(mrt_lock)
{
struct ipmr_vif_iter *iter = seq->private;
struct mr_vif_iter *iter = seq->private;
struct net *net = seq_file_net(seq);
struct mr_table *mrt;
......@@ -2982,26 +2840,7 @@ static void *ipmr_vif_seq_start(struct seq_file *seq, loff_t *pos)
iter->mrt = mrt;
read_lock(&mrt_lock);
return *pos ? ipmr_vif_seq_idx(net, seq->private, *pos - 1)
: SEQ_START_TOKEN;
}
static void *ipmr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct ipmr_vif_iter *iter = seq->private;
struct net *net = seq_file_net(seq);
struct mr_table *mrt = iter->mrt;
++*pos;
if (v == SEQ_START_TOKEN)
return ipmr_vif_seq_idx(net, iter, 0);
while (++iter->ct < mrt->maxvif) {
if (!VIF_EXISTS(mrt, iter->ct))
continue;
return &mrt->vif_table[iter->ct];
}
return NULL;
return mr_vif_seq_start(seq, pos);
}
static void ipmr_vif_seq_stop(struct seq_file *seq, void *v)
......@@ -3012,7 +2851,7 @@ static void ipmr_vif_seq_stop(struct seq_file *seq, void *v)
static int ipmr_vif_seq_show(struct seq_file *seq, void *v)
{
struct ipmr_vif_iter *iter = seq->private;
struct mr_vif_iter *iter = seq->private;
struct mr_table *mrt = iter->mrt;
if (v == SEQ_START_TOKEN) {
......@@ -3020,7 +2859,8 @@ static int ipmr_vif_seq_show(struct seq_file *seq, void *v)
"Interface BytesIn PktsIn BytesOut PktsOut Flags Local Remote\n");
} else {
const struct vif_device *vif = v;
const char *name = vif->dev ? vif->dev->name : "none";
const char *name = vif->dev ?
vif->dev->name : "none";
seq_printf(seq,
"%2td %-10s %8ld %7ld %8ld %7ld %05X %08X %08X\n",
......@@ -3034,7 +2874,7 @@ static int ipmr_vif_seq_show(struct seq_file *seq, void *v)
static const struct seq_operations ipmr_vif_seq_ops = {
.start = ipmr_vif_seq_start,
.next = ipmr_vif_seq_next,
.next = mr_vif_seq_next,
.stop = ipmr_vif_seq_stop,
.show = ipmr_vif_seq_show,
};
......@@ -3042,7 +2882,7 @@ static const struct seq_operations ipmr_vif_seq_ops = {
static int ipmr_vif_open(struct inode *inode, struct file *file)
{
return seq_open_net(inode, file, &ipmr_vif_seq_ops,
sizeof(struct ipmr_vif_iter));
sizeof(struct mr_vif_iter));
}
static const struct file_operations ipmr_vif_fops = {
......@@ -3052,40 +2892,8 @@ static const struct file_operations ipmr_vif_fops = {
.release = seq_release_net,
};
struct ipmr_mfc_iter {
struct seq_net_private p;
struct mr_table *mrt;
struct list_head *cache;
};
static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net,
struct ipmr_mfc_iter *it, loff_t pos)
{
struct mr_table *mrt = it->mrt;
struct mfc_cache *mfc;
rcu_read_lock();
it->cache = &mrt->mfc_cache_list;
list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
if (pos-- == 0)
return mfc;
rcu_read_unlock();
spin_lock_bh(&mfc_unres_lock);
it->cache = &mrt->mfc_unres_queue;
list_for_each_entry(mfc, it->cache, list)
if (pos-- == 0)
return mfc;
spin_unlock_bh(&mfc_unres_lock);
it->cache = NULL;
return NULL;
}
static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
{
struct ipmr_mfc_iter *it = seq->private;
struct net *net = seq_file_net(seq);
struct mr_table *mrt;
......@@ -3093,54 +2901,7 @@ static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
if (!mrt)
return ERR_PTR(-ENOENT);
it->mrt = mrt;
it->cache = NULL;
return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1)
: SEQ_START_TOKEN;
}
static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct ipmr_mfc_iter *it = seq->private;
struct net *net = seq_file_net(seq);
struct mr_table *mrt = it->mrt;
struct mfc_cache *mfc = v;
++*pos;
if (v == SEQ_START_TOKEN)
return ipmr_mfc_seq_idx(net, seq->private, 0);
if (mfc->list.next != it->cache)
return list_entry(mfc->list.next, struct mfc_cache, list);
if (it->cache == &mrt->mfc_unres_queue)
goto end_of_list;
/* exhausted cache_array, show unresolved */
rcu_read_unlock();
it->cache = &mrt->mfc_unres_queue;
spin_lock_bh(&mfc_unres_lock);
if (!list_empty(it->cache))
return list_first_entry(it->cache, struct mfc_cache, list);
end_of_list:
spin_unlock_bh(&mfc_unres_lock);
it->cache = NULL;
return NULL;
}
static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
{
struct ipmr_mfc_iter *it = seq->private;
struct mr_table *mrt = it->mrt;
if (it->cache == &mrt->mfc_unres_queue)
spin_unlock_bh(&mfc_unres_lock);
else if (it->cache == &mrt->mfc_cache_list)
rcu_read_unlock();
return mr_mfc_seq_start(seq, pos, mrt, &mfc_unres_lock);
}
static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
......@@ -3152,26 +2913,26 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
"Group Origin Iif Pkts Bytes Wrong Oifs\n");
} else {
const struct mfc_cache *mfc = v;
const struct ipmr_mfc_iter *it = seq->private;
const struct mr_mfc_iter *it = seq->private;
const struct mr_table *mrt = it->mrt;
seq_printf(seq, "%08X %08X %-3hd",
(__force u32) mfc->mfc_mcastgrp,
(__force u32) mfc->mfc_origin,
mfc->mfc_parent);
mfc->_c.mfc_parent);
if (it->cache != &mrt->mfc_unres_queue) {
seq_printf(seq, " %8lu %8lu %8lu",
mfc->mfc_un.res.pkt,
mfc->mfc_un.res.bytes,
mfc->mfc_un.res.wrong_if);
for (n = mfc->mfc_un.res.minvif;
n < mfc->mfc_un.res.maxvif; n++) {
mfc->_c.mfc_un.res.pkt,
mfc->_c.mfc_un.res.bytes,
mfc->_c.mfc_un.res.wrong_if);
for (n = mfc->_c.mfc_un.res.minvif;
n < mfc->_c.mfc_un.res.maxvif; n++) {
if (VIF_EXISTS(mrt, n) &&
mfc->mfc_un.res.ttls[n] < 255)
mfc->_c.mfc_un.res.ttls[n] < 255)
seq_printf(seq,
" %2d:%-3d",
n, mfc->mfc_un.res.ttls[n]);
n, mfc->_c.mfc_un.res.ttls[n]);
}
} else {
/* unresolved mfc_caches don't contain
......@@ -3186,15 +2947,15 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
static const struct seq_operations ipmr_mfc_seq_ops = {
.start = ipmr_mfc_seq_start,
.next = ipmr_mfc_seq_next,
.stop = ipmr_mfc_seq_stop,
.next = mr_mfc_seq_next,
.stop = mr_mfc_seq_stop,
.show = ipmr_mfc_seq_show,
};
static int ipmr_mfc_open(struct inode *inode, struct file *file)
{
return seq_open_net(inode, file, &ipmr_mfc_seq_ops,
sizeof(struct ipmr_mfc_iter));
sizeof(struct mr_mfc_iter));
}
static const struct file_operations ipmr_mfc_fops = {
......@@ -3230,7 +2991,7 @@ static int ipmr_dump(struct net *net, struct notifier_block *nb)
ipmr_for_each_table(mrt, net) {
struct vif_device *v = &mrt->vif_table[0];
struct mfc_cache *mfc;
struct mr_mfc *mfc;
int vifi;
/* Notifiy on table VIF entries */
......@@ -3247,7 +3008,8 @@ static int ipmr_dump(struct net *net, struct notifier_block *nb)
/* Notify on table MFC entries */
list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
call_ipmr_mfc_entry_notifier(nb, net,
FIB_EVENT_ENTRY_ADD, mfc,
FIB_EVENT_ENTRY_ADD,
(struct mfc_cache *)mfc,
mrt->id);
}
......
net/ipv4/ipmr_base.c 0 → 100644
浏览文件 @ 3c5aa0bc
/* Linux multicast routing support
* Common logic shared by IPv4 [ipmr] and IPv6 [ip6mr] implementation
*/
#include <linux/mroute_base.h>
/* Sets everything common except 'dev', since that is done under locking */
void vif_device_init(struct vif_device *v,
struct net_device *dev,
unsigned long rate_limit,
unsigned char threshold,
unsigned short flags,
unsigned short get_iflink_mask)
{
v->dev = NULL;
v->bytes_in = 0;
v->bytes_out = 0;
v->pkt_in = 0;
v->pkt_out = 0;
v->rate_limit = rate_limit;
v->flags = flags;
v->threshold = threshold;
if (v->flags & get_iflink_mask)
v->link = dev_get_iflink(dev);
else
v->link = dev->ifindex;
}
EXPORT_SYMBOL(vif_device_init);
struct mr_table *
mr_table_alloc(struct net *net, u32 id,
struct mr_table_ops *ops,
void (*expire_func)(struct timer_list *t),
void (*table_set)(struct mr_table *mrt,
struct net *net))
{
struct mr_table *mrt;
mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
if (!mrt)
return NULL;
mrt->id = id;
write_pnet(&mrt->net, net);
mrt->ops = *ops;
rhltable_init(&mrt->mfc_hash, mrt->ops.rht_params);
INIT_LIST_HEAD(&mrt->mfc_cache_list);
INIT_LIST_HEAD(&mrt->mfc_unres_queue);
timer_setup(&mrt->ipmr_expire_timer, expire_func, 0);
mrt->mroute_reg_vif_num = -1;
table_set(mrt, net);
return mrt;
}
EXPORT_SYMBOL(mr_table_alloc);
void *mr_mfc_find_parent(struct mr_table *mrt, void *hasharg, int parent)
{
struct rhlist_head *tmp, *list;
struct mr_mfc *c;
list = rhltable_lookup(&mrt->mfc_hash, hasharg, *mrt->ops.rht_params);
rhl_for_each_entry_rcu(c, tmp, list, mnode)
if (parent == -1 || parent == c->mfc_parent)
return c;
return NULL;
}
EXPORT_SYMBOL(mr_mfc_find_parent);
void *mr_mfc_find_any_parent(struct mr_table *mrt, int vifi)
{
struct rhlist_head *tmp, *list;
struct mr_mfc *c;
list = rhltable_lookup(&mrt->mfc_hash, mrt->ops.cmparg_any,
*mrt->ops.rht_params);
rhl_for_each_entry_rcu(c, tmp, list, mnode)
if (c->mfc_un.res.ttls[vifi] < 255)
return c;
return NULL;
}
EXPORT_SYMBOL(mr_mfc_find_any_parent);
void *mr_mfc_find_any(struct mr_table *mrt, int vifi, void *hasharg)
{
struct rhlist_head *tmp, *list;
struct mr_mfc *c, *proxy;
list = rhltable_lookup(&mrt->mfc_hash, hasharg, *mrt->ops.rht_params);
rhl_for_each_entry_rcu(c, tmp, list, mnode) {
if (c->mfc_un.res.ttls[vifi] < 255)
return c;
/* It's ok if the vifi is part of the static tree */
proxy = mr_mfc_find_any_parent(mrt, c->mfc_parent);
if (proxy && proxy->mfc_un.res.ttls[vifi] < 255)
return c;
}
return mr_mfc_find_any_parent(mrt, vifi);
}
EXPORT_SYMBOL(mr_mfc_find_any);
#ifdef CONFIG_PROC_FS
void *mr_vif_seq_idx(struct net *net, struct mr_vif_iter *iter, loff_t pos)
{
struct mr_table *mrt = iter->mrt;
for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) {
if (!VIF_EXISTS(mrt, iter->ct))
continue;
if (pos-- == 0)
return &mrt->vif_table[iter->ct];
}
return NULL;
}
EXPORT_SYMBOL(mr_vif_seq_idx);
void *mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct mr_vif_iter *iter = seq->private;
struct net *net = seq_file_net(seq);
struct mr_table *mrt = iter->mrt;
++*pos;
if (v == SEQ_START_TOKEN)
return mr_vif_seq_idx(net, iter, 0);
while (++iter->ct < mrt->maxvif) {
if (!VIF_EXISTS(mrt, iter->ct))
continue;
return &mrt->vif_table[iter->ct];
}
return NULL;
}
EXPORT_SYMBOL(mr_vif_seq_next);
void *mr_mfc_seq_idx(struct net *net,
struct mr_mfc_iter *it, loff_t pos)
{
struct mr_table *mrt = it->mrt;
struct mr_mfc *mfc;
rcu_read_lock();
it->cache = &mrt->mfc_cache_list;
list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list)
if (pos-- == 0)
return mfc;
rcu_read_unlock();
spin_lock_bh(it->lock);
it->cache = &mrt->mfc_unres_queue;
list_for_each_entry(mfc, it->cache, list)
if (pos-- == 0)
return mfc;
spin_unlock_bh(it->lock);
it->cache = NULL;
return NULL;
}
EXPORT_SYMBOL(mr_mfc_seq_idx);
void *mr_mfc_seq_next(struct seq_file *seq, void *v,
loff_t *pos)
{
struct mr_mfc_iter *it = seq->private;
struct net *net = seq_file_net(seq);
struct mr_table *mrt = it->mrt;
struct mr_mfc *c = v;
++*pos;
if (v == SEQ_START_TOKEN)
return mr_mfc_seq_idx(net, seq->private, 0);
if (c->list.next != it->cache)
return list_entry(c->list.next, struct mr_mfc, list);
if (it->cache == &mrt->mfc_unres_queue)
goto end_of_list;
/* exhausted cache_array, show unresolved */
rcu_read_unlock();
it->cache = &mrt->mfc_unres_queue;
spin_lock_bh(it->lock);
if (!list_empty(it->cache))
return list_first_entry(it->cache, struct mr_mfc, list);
end_of_list:
spin_unlock_bh(it->lock);
it->cache = NULL;
return NULL;
}
EXPORT_SYMBOL(mr_mfc_seq_next);
#endif
int mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
struct mr_mfc *c, struct rtmsg *rtm)
{
struct rta_mfc_stats mfcs;
struct nlattr *mp_attr;
struct rtnexthop *nhp;
unsigned long lastuse;
int ct;
/* If cache is unresolved, don't try to parse IIF and OIF */
if (c->mfc_parent >= MAXVIFS) {
rtm->rtm_flags |= RTNH_F_UNRESOLVED;
return -ENOENT;
}
if (VIF_EXISTS(mrt, c->mfc_parent) &&
nla_put_u32(skb, RTA_IIF,
mrt->vif_table[c->mfc_parent].dev->ifindex) < 0)
return -EMSGSIZE;
if (c->mfc_flags & MFC_OFFLOAD)
rtm->rtm_flags |= RTNH_F_OFFLOAD;
mp_attr = nla_nest_start(skb, RTA_MULTIPATH);
if (!mp_attr)
return -EMSGSIZE;
for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
if (VIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) {
struct vif_device *vif;
nhp = nla_reserve_nohdr(skb, sizeof(*nhp));
if (!nhp) {
nla_nest_cancel(skb, mp_attr);
return -EMSGSIZE;
}
nhp->rtnh_flags = 0;
nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
vif = &mrt->vif_table[ct];
nhp->rtnh_ifindex = vif->dev->ifindex;
nhp->rtnh_len = sizeof(*nhp);
}
}
nla_nest_end(skb, mp_attr);
lastuse = READ_ONCE(c->mfc_un.res.lastuse);
lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0;
mfcs.mfcs_packets = c->mfc_un.res.pkt;
mfcs.mfcs_bytes = c->mfc_un.res.bytes;
mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) ||
nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse),
RTA_PAD))
return -EMSGSIZE;
rtm->rtm_type = RTN_MULTICAST;
return 1;
}
EXPORT_SYMBOL(mr_fill_mroute);
int mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb,
struct mr_table *(*iter)(struct net *net,
struct mr_table *mrt),
int (*fill)(struct mr_table *mrt,
struct sk_buff *skb,
u32 portid, u32 seq, struct mr_mfc *c,
int cmd, int flags),
spinlock_t *lock)
{
unsigned int t = 0, e = 0, s_t = cb->args[0], s_e = cb->args[1];
struct net *net = sock_net(skb->sk);
struct mr_table *mrt;
struct mr_mfc *mfc;
rcu_read_lock();
for (mrt = iter(net, NULL); mrt; mrt = iter(net, mrt)) {
if (t < s_t)
goto next_table;
list_for_each_entry_rcu(mfc, &mrt->mfc_cache_list, list) {
if (e < s_e)
goto next_entry;
if (fill(mrt, skb, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, mfc,
RTM_NEWROUTE, NLM_F_MULTI) < 0)
goto done;
next_entry:
e++;
}
e = 0;
s_e = 0;
spin_lock_bh(lock);
list_for_each_entry(mfc, &mrt->mfc_unres_queue, list) {
if (e < s_e)
goto next_entry2;
if (fill(mrt, skb, NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq, mfc,
RTM_NEWROUTE, NLM_F_MULTI) < 0) {
spin_unlock_bh(lock);
goto done;
}
next_entry2:
e++;
}
spin_unlock_bh(lock);
e = 0;
s_e = 0;
next_table:
t++;
}
done:
rcu_read_unlock();
cb->args[1] = e;
cb->args[0] = t;
return skb->len;
}
EXPORT_SYMBOL(mr_rtm_dumproute);
net/ipv6/Kconfig
浏览文件 @ 3c5aa0bc
......@@ -278,6 +278,7 @@ config IPV6_SUBTREES
config IPV6_MROUTE
bool "IPv6: multicast routing"
depends on IPV6
select IP_MROUTE_COMMON
---help---
Experimental support for IPv6 multicast forwarding.
If unsure, say N.
......
net/ipv6/ip6_output.c
浏览文件 @ 3c5aa0bc
......@@ -71,7 +71,7 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
struct inet6_dev *idev = ip6_dst_idev(skb_dst(skb));
if (!(dev->flags & IFF_LOOPBACK) && sk_mc_loop(sk) &&
((mroute6_socket(net, skb) &&
((mroute6_is_socket(net, skb) &&
!(IP6CB(skb)->flags & IP6SKB_FORWARDED)) ||
ipv6_chk_mcast_addr(dev, &ipv6_hdr(skb)->daddr,
&ipv6_hdr(skb)->saddr))) {
......
net/ipv6/ip6mr.c
浏览文件 @ 3c5aa0bc
......@@ -20,7 +20,6 @@
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/errno.h>
#include <linux/timer.h>
#include <linux/mm.h>
#include <linux/kernel.h>
#include <linux/fcntl.h>
......@@ -32,11 +31,9 @@
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/init.h>
#include <linux/slab.h>
#include <linux/compat.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
#include <net/sock.h>
#include <net/raw.h>
#include <linux/notifier.h>
#include <linux/if_arp.h>
......@@ -54,30 +51,12 @@
#include <net/ip6_checksum.h>
#include <linux/netconf.h>
struct mr6_table {
struct list_head list;
possible_net_t net;
u32 id;
struct sock *mroute6_sk;
struct timer_list ipmr_expire_timer;
struct list_head mfc6_unres_queue;
struct list_head mfc6_cache_array[MFC6_LINES];
struct mif_device vif6_table[MAXMIFS];
int maxvif;
atomic_t cache_resolve_queue_len;
bool mroute_do_assert;
bool mroute_do_pim;
#ifdef CONFIG_IPV6_PIMSM_V2
int mroute_reg_vif_num;
#endif
};
struct ip6mr_rule {
struct fib_rule common;
};
struct ip6mr_result {
struct mr6_table *mrt;
struct mr_table *mrt;
};
/* Big lock, protecting vif table, mrt cache and mroute socket state.
......@@ -86,11 +65,7 @@ struct ip6mr_result {
static DEFINE_RWLOCK(mrt_lock);
/*
* Multicast router control variables
*/
#define MIF_EXISTS(_mrt, _idx) ((_mrt)->vif6_table[_idx].dev != NULL)
/* Multicast router control variables */
/* Special spinlock for queue of unresolved entries */
static DEFINE_SPINLOCK(mfc_unres_lock);
......@@ -105,30 +80,45 @@ static DEFINE_SPINLOCK(mfc_unres_lock);
static struct kmem_cache *mrt_cachep __read_mostly;
static struct mr6_table *ip6mr_new_table(struct net *net, u32 id);
static void ip6mr_free_table(struct mr6_table *mrt);
static struct mr_table *ip6mr_new_table(struct net *net, u32 id);
static void ip6mr_free_table(struct mr_table *mrt);
static void ip6_mr_forward(struct net *net, struct mr6_table *mrt,
static void ip6_mr_forward(struct net *net, struct mr_table *mrt,
struct sk_buff *skb, struct mfc6_cache *cache);
static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt,
mifi_t mifi, int assert);
static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
struct mfc6_cache *c, struct rtmsg *rtm);
static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc,
int cmd);
static void mrt6msg_netlink_event(struct mr6_table *mrt, struct sk_buff *pkt);
static void mrt6msg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt);
static int ip6mr_rtm_dumproute(struct sk_buff *skb,
struct netlink_callback *cb);
static void mroute_clean_tables(struct mr6_table *mrt, bool all);
static void mroute_clean_tables(struct mr_table *mrt, bool all);
static void ipmr_expire_process(struct timer_list *t);
#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
#define ip6mr_for_each_table(mrt, net) \
list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list)
static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
static struct mr_table *ip6mr_mr_table_iter(struct net *net,
struct mr_table *mrt)
{
struct mr_table *ret;
if (!mrt)
ret = list_entry_rcu(net->ipv6.mr6_tables.next,
struct mr_table, list);
else
ret = list_entry_rcu(mrt->list.next,
struct mr_table, list);
if (&ret->list == &net->ipv6.mr6_tables)
return NULL;
return ret;
}
static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
{
struct mr6_table *mrt;
struct mr_table *mrt;
ip6mr_for_each_table(mrt, net) {
if (mrt->id == id)
......@@ -138,7 +128,7 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
}
static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
struct mr6_table **mrt)
struct mr_table **mrt)
{
int err;
struct ip6mr_result res;
......@@ -159,7 +149,7 @@ static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp,
int flags, struct fib_lookup_arg *arg)
{
struct ip6mr_result *res = arg->result;
struct mr6_table *mrt;
struct mr_table *mrt;
switch (rule->action) {
case FR_ACT_TO_TBL:
......@@ -227,7 +217,7 @@ static const struct fib_rules_ops __net_initconst ip6mr_rules_ops_template = {
static int __net_init ip6mr_rules_init(struct net *net)
{
struct fib_rules_ops *ops;
struct mr6_table *mrt;
struct mr_table *mrt;
int err;
ops = fib_rules_register(&ip6mr_rules_ops_template, net);
......@@ -258,7 +248,7 @@ static int __net_init ip6mr_rules_init(struct net *net)
static void __net_exit ip6mr_rules_exit(struct net *net)
{
struct mr6_table *mrt, *next;
struct mr_table *mrt, *next;
rtnl_lock();
list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) {
......@@ -272,13 +262,21 @@ static void __net_exit ip6mr_rules_exit(struct net *net)
#define ip6mr_for_each_table(mrt, net) \
for (mrt = net->ipv6.mrt6; mrt; mrt = NULL)
static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
static struct mr_table *ip6mr_mr_table_iter(struct net *net,
struct mr_table *mrt)
{
if (!mrt)
return net->ipv6.mrt6;
return NULL;
}
static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
{
return net->ipv6.mrt6;
}
static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
struct mr6_table **mrt)
struct mr_table **mrt)
{
*mrt = net->ipv6.mrt6;
return 0;
......@@ -299,112 +297,75 @@ static void __net_exit ip6mr_rules_exit(struct net *net)
}
#endif
static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
static int ip6mr_hash_cmp(struct rhashtable_compare_arg *arg,
const void *ptr)
{
struct mr6_table *mrt;
unsigned int i;
const struct mfc6_cache_cmp_arg *cmparg = arg->key;
struct mfc6_cache *c = (struct mfc6_cache *)ptr;
mrt = ip6mr_get_table(net, id);
if (mrt)
return mrt;
mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
if (!mrt)
return NULL;
mrt->id = id;
write_pnet(&mrt->net, net);
/* Forwarding cache */
for (i = 0; i < MFC6_LINES; i++)
INIT_LIST_HEAD(&mrt->mfc6_cache_array[i]);
INIT_LIST_HEAD(&mrt->mfc6_unres_queue);
return !ipv6_addr_equal(&c->mf6c_mcastgrp, &cmparg->mf6c_mcastgrp) ||
!ipv6_addr_equal(&c->mf6c_origin, &cmparg->mf6c_origin);
}
timer_setup(&mrt->ipmr_expire_timer, ipmr_expire_process, 0);
static const struct rhashtable_params ip6mr_rht_params = {
.head_offset = offsetof(struct mr_mfc, mnode),
.key_offset = offsetof(struct mfc6_cache, cmparg),
.key_len = sizeof(struct mfc6_cache_cmp_arg),
.nelem_hint = 3,
.locks_mul = 1,
.obj_cmpfn = ip6mr_hash_cmp,
.automatic_shrinking = true,
};
#ifdef CONFIG_IPV6_PIMSM_V2
mrt->mroute_reg_vif_num = -1;
#endif
static void ip6mr_new_table_set(struct mr_table *mrt,
struct net *net)
{
#ifdef CONFIG_IPV6_MROUTE_MULTIPLE_TABLES
list_add_tail_rcu(&mrt->list, &net->ipv6.mr6_tables);
#endif
return mrt;
}
static void ip6mr_free_table(struct mr6_table *mrt)
{
del_timer_sync(&mrt->ipmr_expire_timer);
mroute_clean_tables(mrt, true);
kfree(mrt);
}
#ifdef CONFIG_PROC_FS
struct ipmr_mfc_iter {
struct seq_net_private p;
struct mr6_table *mrt;
struct list_head *cache;
int ct;
static struct mfc6_cache_cmp_arg ip6mr_mr_table_ops_cmparg_any = {
.mf6c_origin = IN6ADDR_ANY_INIT,
.mf6c_mcastgrp = IN6ADDR_ANY_INIT,
};
static struct mr_table_ops ip6mr_mr_table_ops = {
.rht_params = &ip6mr_rht_params,
.cmparg_any = &ip6mr_mr_table_ops_cmparg_any,
};
static struct mfc6_cache *ipmr_mfc_seq_idx(struct net *net,
struct ipmr_mfc_iter *it, loff_t pos)
static struct mr_table *ip6mr_new_table(struct net *net, u32 id)
{
struct mr6_table *mrt = it->mrt;
struct mfc6_cache *mfc;
read_lock(&mrt_lock);
for (it->ct = 0; it->ct < MFC6_LINES; it->ct++) {
it->cache = &mrt->mfc6_cache_array[it->ct];
list_for_each_entry(mfc, it->cache, list)
if (pos-- == 0)
return mfc;
}
read_unlock(&mrt_lock);
struct mr_table *mrt;
spin_lock_bh(&mfc_unres_lock);
it->cache = &mrt->mfc6_unres_queue;
list_for_each_entry(mfc, it->cache, list)
if (pos-- == 0)
return mfc;
spin_unlock_bh(&mfc_unres_lock);
mrt = ip6mr_get_table(net, id);
if (mrt)
return mrt;
it->cache = NULL;
return NULL;
return mr_table_alloc(net, id, &ip6mr_mr_table_ops,
ipmr_expire_process, ip6mr_new_table_set);
}
/*
* The /proc interfaces to multicast routing /proc/ip6_mr_cache /proc/ip6_mr_vif
*/
struct ipmr_vif_iter {
struct seq_net_private p;
struct mr6_table *mrt;
int ct;
};
static struct mif_device *ip6mr_vif_seq_idx(struct net *net,
struct ipmr_vif_iter *iter,
loff_t pos)
static void ip6mr_free_table(struct mr_table *mrt)
{
struct mr6_table *mrt = iter->mrt;
for (iter->ct = 0; iter->ct < mrt->maxvif; ++iter->ct) {
if (!MIF_EXISTS(mrt, iter->ct))
continue;
if (pos-- == 0)
return &mrt->vif6_table[iter->ct];
}
return NULL;
del_timer_sync(&mrt->ipmr_expire_timer);
mroute_clean_tables(mrt, true);
rhltable_destroy(&mrt->mfc_hash);
kfree(mrt);
}
#ifdef CONFIG_PROC_FS
/* The /proc interfaces to multicast routing
* /proc/ip6_mr_cache /proc/ip6_mr_vif
*/
static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos)
__acquires(mrt_lock)
{
struct ipmr_vif_iter *iter = seq->private;
struct mr_vif_iter *iter = seq->private;
struct net *net = seq_file_net(seq);
struct mr6_table *mrt;
struct mr_table *mrt;
mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
if (!mrt)
......@@ -413,26 +374,7 @@ static void *ip6mr_vif_seq_start(struct seq_file *seq, loff_t *pos)
iter->mrt = mrt;
read_lock(&mrt_lock);
return *pos ? ip6mr_vif_seq_idx(net, seq->private, *pos - 1)
: SEQ_START_TOKEN;
}
static void *ip6mr_vif_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct ipmr_vif_iter *iter = seq->private;
struct net *net = seq_file_net(seq);
struct mr6_table *mrt = iter->mrt;
++*pos;
if (v == SEQ_START_TOKEN)
return ip6mr_vif_seq_idx(net, iter, 0);
while (++iter->ct < mrt->maxvif) {
if (!MIF_EXISTS(mrt, iter->ct))
continue;
return &mrt->vif6_table[iter->ct];
}
return NULL;
return mr_vif_seq_start(seq, pos);
}
static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v)
......@@ -443,19 +385,19 @@ static void ip6mr_vif_seq_stop(struct seq_file *seq, void *v)
static int ip6mr_vif_seq_show(struct seq_file *seq, void *v)
{
struct ipmr_vif_iter *iter = seq->private;
struct mr6_table *mrt = iter->mrt;
struct mr_vif_iter *iter = seq->private;
struct mr_table *mrt = iter->mrt;
if (v == SEQ_START_TOKEN) {
seq_puts(seq,
"Interface BytesIn PktsIn BytesOut PktsOut Flags\n");
} else {
const struct mif_device *vif = v;
const struct vif_device *vif = v;
const char *name = vif->dev ? vif->dev->name : "none";
seq_printf(seq,
"%2td %-10s %8ld %7ld %8ld %7ld %05X\n",
vif - mrt->vif6_table,
vif - mrt->vif_table,
name, vif->bytes_in, vif->pkt_in,
vif->bytes_out, vif->pkt_out,
vif->flags);
......@@ -465,7 +407,7 @@ static int ip6mr_vif_seq_show(struct seq_file *seq, void *v)
static const struct seq_operations ip6mr_vif_seq_ops = {
.start = ip6mr_vif_seq_start,
.next = ip6mr_vif_seq_next,
.next = mr_vif_seq_next,
.stop = ip6mr_vif_seq_stop,
.show = ip6mr_vif_seq_show,
};
......@@ -473,7 +415,7 @@ static const struct seq_operations ip6mr_vif_seq_ops = {
static int ip6mr_vif_open(struct inode *inode, struct file *file)
{
return seq_open_net(inode, file, &ip6mr_vif_seq_ops,
sizeof(struct ipmr_vif_iter));
sizeof(struct mr_vif_iter));
}
static const struct file_operations ip6mr_vif_fops = {
......@@ -485,72 +427,14 @@ static const struct file_operations ip6mr_vif_fops = {
static void *ipmr_mfc_seq_start(struct seq_file *seq, loff_t *pos)
{
struct ipmr_mfc_iter *it = seq->private;
struct net *net = seq_file_net(seq);
struct mr6_table *mrt;
struct mr_table *mrt;
mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
if (!mrt)
return ERR_PTR(-ENOENT);
it->mrt = mrt;
it->cache = NULL;
return *pos ? ipmr_mfc_seq_idx(net, seq->private, *pos - 1)
: SEQ_START_TOKEN;
}
static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct mfc6_cache *mfc = v;
struct ipmr_mfc_iter *it = seq->private;
struct net *net = seq_file_net(seq);
struct mr6_table *mrt = it->mrt;
++*pos;
if (v == SEQ_START_TOKEN)
return ipmr_mfc_seq_idx(net, seq->private, 0);
if (mfc->list.next != it->cache)
return list_entry(mfc->list.next, struct mfc6_cache, list);
if (it->cache == &mrt->mfc6_unres_queue)
goto end_of_list;
BUG_ON(it->cache != &mrt->mfc6_cache_array[it->ct]);
while (++it->ct < MFC6_LINES) {
it->cache = &mrt->mfc6_cache_array[it->ct];
if (list_empty(it->cache))
continue;
return list_first_entry(it->cache, struct mfc6_cache, list);
}
/* exhausted cache_array, show unresolved */
read_unlock(&mrt_lock);
it->cache = &mrt->mfc6_unres_queue;
it->ct = 0;
spin_lock_bh(&mfc_unres_lock);
if (!list_empty(it->cache))
return list_first_entry(it->cache, struct mfc6_cache, list);
end_of_list:
spin_unlock_bh(&mfc_unres_lock);
it->cache = NULL;
return NULL;
}
static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v)
{
struct ipmr_mfc_iter *it = seq->private;
struct mr6_table *mrt = it->mrt;
if (it->cache == &mrt->mfc6_unres_queue)
spin_unlock_bh(&mfc_unres_lock);
else if (it->cache == &mrt->mfc6_cache_array[it->ct])
read_unlock(&mrt_lock);
return mr_mfc_seq_start(seq, pos, mrt, &mfc_unres_lock);
}
static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
......@@ -564,25 +448,25 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
"Iif Pkts Bytes Wrong Oifs\n");
} else {
const struct mfc6_cache *mfc = v;
const struct ipmr_mfc_iter *it = seq->private;
struct mr6_table *mrt = it->mrt;
const struct mr_mfc_iter *it = seq->private;
struct mr_table *mrt = it->mrt;
seq_printf(seq, "%pI6 %pI6 %-3hd",
&mfc->mf6c_mcastgrp, &mfc->mf6c_origin,
mfc->mf6c_parent);
mfc->_c.mfc_parent);
if (it->cache != &mrt->mfc6_unres_queue) {
if (it->cache != &mrt->mfc_unres_queue) {
seq_printf(seq, " %8lu %8lu %8lu",
mfc->mfc_un.res.pkt,
mfc->mfc_un.res.bytes,
mfc->mfc_un.res.wrong_if);
for (n = mfc->mfc_un.res.minvif;
n < mfc->mfc_un.res.maxvif; n++) {
if (MIF_EXISTS(mrt, n) &&
mfc->mfc_un.res.ttls[n] < 255)
mfc->_c.mfc_un.res.pkt,
mfc->_c.mfc_un.res.bytes,
mfc->_c.mfc_un.res.wrong_if);
for (n = mfc->_c.mfc_un.res.minvif;
n < mfc->_c.mfc_un.res.maxvif; n++) {
if (VIF_EXISTS(mrt, n) &&
mfc->_c.mfc_un.res.ttls[n] < 255)
seq_printf(seq,
" %2d:%-3d",
n, mfc->mfc_un.res.ttls[n]);
" %2d:%-3d", n,
mfc->_c.mfc_un.res.ttls[n]);
}
} else {
/* unresolved mfc_caches don't contain
......@@ -597,15 +481,15 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v)
static const struct seq_operations ipmr_mfc_seq_ops = {
.start = ipmr_mfc_seq_start,
.next = ipmr_mfc_seq_next,
.stop = ipmr_mfc_seq_stop,
.next = mr_mfc_seq_next,
.stop = mr_mfc_seq_stop,
.show = ipmr_mfc_seq_show,
};
static int ipmr_mfc_open(struct inode *inode, struct file *file)
{
return seq_open_net(inode, file, &ipmr_mfc_seq_ops,
sizeof(struct ipmr_mfc_iter));
sizeof(struct mr_mfc_iter));
}
static const struct file_operations ip6mr_mfc_fops = {
......@@ -624,7 +508,7 @@ static int pim6_rcv(struct sk_buff *skb)
struct ipv6hdr *encap;
struct net_device *reg_dev = NULL;
struct net *net = dev_net(skb->dev);
struct mr6_table *mrt;
struct mr_table *mrt;
struct flowi6 fl6 = {
.flowi6_iif = skb->dev->ifindex,
.flowi6_mark = skb->mark,
......@@ -658,7 +542,7 @@ static int pim6_rcv(struct sk_buff *skb)
read_lock(&mrt_lock);
if (reg_vif_num >= 0)
reg_dev = mrt->vif6_table[reg_vif_num].dev;
reg_dev = mrt->vif_table[reg_vif_num].dev;
if (reg_dev)
dev_hold(reg_dev);
read_unlock(&mrt_lock);
......@@ -693,7 +577,7 @@ static netdev_tx_t reg_vif_xmit(struct sk_buff *skb,
struct net_device *dev)
{
struct net *net = dev_net(dev);
struct mr6_table *mrt;
struct mr_table *mrt;
struct flowi6 fl6 = {
.flowi6_oif = dev->ifindex,
.flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX,
......@@ -736,7 +620,7 @@ static void reg_vif_setup(struct net_device *dev)
dev->features |= NETIF_F_NETNS_LOCAL;
}
static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt)
static struct net_device *ip6mr_reg_vif(struct net *net, struct mr_table *mrt)
{
struct net_device *dev;
char name[IFNAMSIZ];
......@@ -773,17 +657,17 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt)
* Delete a VIF entry
*/
static int mif6_delete(struct mr6_table *mrt, int vifi, int notify,
static int mif6_delete(struct mr_table *mrt, int vifi, int notify,
struct list_head *head)
{
struct mif_device *v;
struct vif_device *v;
struct net_device *dev;
struct inet6_dev *in6_dev;
if (vifi < 0 || vifi >= mrt->maxvif)
return -EADDRNOTAVAIL;
v = &mrt->vif6_table[vifi];
v = &mrt->vif_table[vifi];
write_lock_bh(&mrt_lock);
dev = v->dev;
......@@ -802,7 +686,7 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, int notify,
if (vifi + 1 == mrt->maxvif) {
int tmp;
for (tmp = vifi - 1; tmp >= 0; tmp--) {
if (MIF_EXISTS(mrt, tmp))
if (VIF_EXISTS(mrt, tmp))
break;
}
mrt->maxvif = tmp + 1;
......@@ -827,23 +711,30 @@ static int mif6_delete(struct mr6_table *mrt, int vifi, int notify,
return 0;
}
static inline void ip6mr_cache_free_rcu(struct rcu_head *head)
{
struct mr_mfc *c = container_of(head, struct mr_mfc, rcu);
kmem_cache_free(mrt_cachep, (struct mfc6_cache *)c);
}
static inline void ip6mr_cache_free(struct mfc6_cache *c)
{
kmem_cache_free(mrt_cachep, c);
call_rcu(&c->_c.rcu, ip6mr_cache_free_rcu);
}
/* Destroy an unresolved cache entry, killing queued skbs
and reporting error to netlink readers.
*/
static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c)
static void ip6mr_destroy_unres(struct mr_table *mrt, struct mfc6_cache *c)
{
struct net *net = read_pnet(&mrt->net);
struct sk_buff *skb;
atomic_dec(&mrt->cache_resolve_queue_len);
while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved)) != NULL) {
while ((skb = skb_dequeue(&c->_c.mfc_un.unres.unresolved)) != NULL) {
if (ipv6_hdr(skb)->version == 0) {
struct nlmsghdr *nlh = skb_pull(skb,
sizeof(struct ipv6hdr));
......@@ -862,13 +753,13 @@ static void ip6mr_destroy_unres(struct mr6_table *mrt, struct mfc6_cache *c)
/* Timer process for all the unresolved queue. */
static void ipmr_do_expire_process(struct mr6_table *mrt)
static void ipmr_do_expire_process(struct mr_table *mrt)
{
unsigned long now = jiffies;
unsigned long expires = 10 * HZ;
struct mfc6_cache *c, *next;
struct mr_mfc *c, *next;
list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) {
list_for_each_entry_safe(c, next, &mrt->mfc_unres_queue, list) {
if (time_after(c->mfc_un.unres.expires, now)) {
/* not yet... */
unsigned long interval = c->mfc_un.unres.expires - now;
......@@ -878,24 +769,24 @@ static void ipmr_do_expire_process(struct mr6_table *mrt)
}
list_del(&c->list);
mr6_netlink_event(mrt, c, RTM_DELROUTE);
ip6mr_destroy_unres(mrt, c);
mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE);
ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c);
}
if (!list_empty(&mrt->mfc6_unres_queue))
if (!list_empty(&mrt->mfc_unres_queue))
mod_timer(&mrt->ipmr_expire_timer, jiffies + expires);
}
static void ipmr_expire_process(struct timer_list *t)
{
struct mr6_table *mrt = from_timer(mrt, t, ipmr_expire_timer);
struct mr_table *mrt = from_timer(mrt, t, ipmr_expire_timer);
if (!spin_trylock(&mfc_unres_lock)) {
mod_timer(&mrt->ipmr_expire_timer, jiffies + 1);
return;
}
if (!list_empty(&mrt->mfc6_unres_queue))
if (!list_empty(&mrt->mfc_unres_queue))
ipmr_do_expire_process(mrt);
spin_unlock(&mfc_unres_lock);
......@@ -903,7 +794,8 @@ static void ipmr_expire_process(struct timer_list *t)
/* Fill oifs list. It is called under write locked mrt_lock. */
static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *cache,
static void ip6mr_update_thresholds(struct mr_table *mrt,
struct mr_mfc *cache,
unsigned char *ttls)
{
int vifi;
......@@ -913,7 +805,7 @@ static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *ca
memset(cache->mfc_un.res.ttls, 255, MAXMIFS);
for (vifi = 0; vifi < mrt->maxvif; vifi++) {
if (MIF_EXISTS(mrt, vifi) &&
if (VIF_EXISTS(mrt, vifi) &&
ttls[vifi] && ttls[vifi] < 255) {
cache->mfc_un.res.ttls[vifi] = ttls[vifi];
if (cache->mfc_un.res.minvif > vifi)
......@@ -925,17 +817,17 @@ static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *ca
cache->mfc_un.res.lastuse = jiffies;
}
static int mif6_add(struct net *net, struct mr6_table *mrt,
static int mif6_add(struct net *net, struct mr_table *mrt,
struct mif6ctl *vifc, int mrtsock)
{
int vifi = vifc->mif6c_mifi;
struct mif_device *v = &mrt->vif6_table[vifi];
struct vif_device *v = &mrt->vif_table[vifi];
struct net_device *dev;
struct inet6_dev *in6_dev;
int err;
/* Is vif busy ? */
if (MIF_EXISTS(mrt, vifi))
if (VIF_EXISTS(mrt, vifi))
return -EADDRINUSE;
switch (vifc->mif6c_flags) {
......@@ -980,21 +872,10 @@ static int mif6_add(struct net *net, struct mr6_table *mrt,
dev->ifindex, &in6_dev->cnf);
}
/*
* Fill in the VIF structures
*/
v->rate_limit = vifc->vifc_rate_limit;
v->flags = vifc->mif6c_flags;
if (!mrtsock)
v->flags |= VIFF_STATIC;
v->threshold = vifc->vifc_threshold;
v->bytes_in = 0;
v->bytes_out = 0;
v->pkt_in = 0;
v->pkt_out = 0;
v->link = dev->ifindex;
if (v->flags & MIFF_REGISTER)
v->link = dev_get_iflink(dev);
/* Fill in the VIF structures */
vif_device_init(v, dev, vifc->vifc_rate_limit, vifc->vifc_threshold,
vifc->mif6c_flags | (!mrtsock ? VIFF_STATIC : 0),
MIFF_REGISTER);
/* And finish update writing critical data */
write_lock_bh(&mrt_lock);
......@@ -1009,75 +890,56 @@ static int mif6_add(struct net *net, struct mr6_table *mrt,
return 0;
}
static struct mfc6_cache *ip6mr_cache_find(struct mr6_table *mrt,
static struct mfc6_cache *ip6mr_cache_find(struct mr_table *mrt,
const struct in6_addr *origin,
const struct in6_addr *mcastgrp)
{
int line = MFC6_HASH(mcastgrp, origin);
struct mfc6_cache *c;
list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) {
if (ipv6_addr_equal(&c->mf6c_origin, origin) &&
ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp))
return c;
}
return NULL;
}
/* Look for a (*,*,oif) entry */
static struct mfc6_cache *ip6mr_cache_find_any_parent(struct mr6_table *mrt,
mifi_t mifi)
{
int line = MFC6_HASH(&in6addr_any, &in6addr_any);
struct mfc6_cache *c;
list_for_each_entry(c, &mrt->mfc6_cache_array[line], list)
if (ipv6_addr_any(&c->mf6c_origin) &&
ipv6_addr_any(&c->mf6c_mcastgrp) &&
(c->mfc_un.res.ttls[mifi] < 255))
return c;
struct mfc6_cache_cmp_arg arg = {
.mf6c_origin = *origin,
.mf6c_mcastgrp = *mcastgrp,
};
return NULL;
return mr_mfc_find(mrt, &arg);
}
/* Look for a (*,G) entry */
static struct mfc6_cache *ip6mr_cache_find_any(struct mr6_table *mrt,
static struct mfc6_cache *ip6mr_cache_find_any(struct mr_table *mrt,
struct in6_addr *mcastgrp,
mifi_t mifi)
{
int line = MFC6_HASH(mcastgrp, &in6addr_any);
struct mfc6_cache *c, *proxy;
struct mfc6_cache_cmp_arg arg = {
.mf6c_origin = in6addr_any,
.mf6c_mcastgrp = *mcastgrp,
};
if (ipv6_addr_any(mcastgrp))
goto skip;
list_for_each_entry(c, &mrt->mfc6_cache_array[line], list)
if (ipv6_addr_any(&c->mf6c_origin) &&
ipv6_addr_equal(&c->mf6c_mcastgrp, mcastgrp)) {
if (c->mfc_un.res.ttls[mifi] < 255)
return c;
/* It's ok if the mifi is part of the static tree */
proxy = ip6mr_cache_find_any_parent(mrt,
c->mf6c_parent);
if (proxy && proxy->mfc_un.res.ttls[mifi] < 255)
return c;
}
return mr_mfc_find_any_parent(mrt, mifi);
return mr_mfc_find_any(mrt, mifi, &arg);
}
skip:
return ip6mr_cache_find_any_parent(mrt, mifi);
/* Look for a (S,G,iif) entry if parent != -1 */
static struct mfc6_cache *
ip6mr_cache_find_parent(struct mr_table *mrt,
const struct in6_addr *origin,
const struct in6_addr *mcastgrp,
int parent)
{
struct mfc6_cache_cmp_arg arg = {
.mf6c_origin = *origin,
.mf6c_mcastgrp = *mcastgrp,
};
return mr_mfc_find_parent(mrt, &arg, parent);
}
/*
* Allocate a multicast cache entry
*/
/* Allocate a multicast cache entry */
static struct mfc6_cache *ip6mr_cache_alloc(void)
{
struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
if (!c)
return NULL;
c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
c->mfc_un.res.minvif = MAXMIFS;
c->_c.mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
c->_c.mfc_un.res.minvif = MAXMIFS;
return c;
}
......@@ -1086,8 +948,8 @@ static struct mfc6_cache *ip6mr_cache_alloc_unres(void)
struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC);
if (!c)
return NULL;
skb_queue_head_init(&c->mfc_un.unres.unresolved);
c->mfc_un.unres.expires = jiffies + 10 * HZ;
skb_queue_head_init(&c->_c.mfc_un.unres.unresolved);
c->_c.mfc_un.unres.expires = jiffies + 10 * HZ;
return c;
}
......@@ -1095,7 +957,7 @@ static struct mfc6_cache *ip6mr_cache_alloc_unres(void)
* A cache entry has gone into a resolved state from queued
*/
static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt,
static void ip6mr_cache_resolve(struct net *net, struct mr_table *mrt,
struct mfc6_cache *uc, struct mfc6_cache *c)
{
struct sk_buff *skb;
......@@ -1104,12 +966,13 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt,
* Play the pending entries through our router
*/
while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) {
while ((skb = __skb_dequeue(&uc->_c.mfc_un.unres.unresolved))) {
if (ipv6_hdr(skb)->version == 0) {
struct nlmsghdr *nlh = skb_pull(skb,
sizeof(struct ipv6hdr));
if (__ip6mr_fill_mroute(mrt, skb, c, nlmsg_data(nlh)) > 0) {
if (mr_fill_mroute(mrt, skb, &c->_c,
nlmsg_data(nlh)) > 0) {
nlh->nlmsg_len = skb_tail_pointer(skb) - (u8 *)nlh;
} else {
nlh->nlmsg_type = NLMSG_ERROR;
......@@ -1129,9 +992,10 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt,
* Called under mrt_lock.
*/
static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
static int ip6mr_cache_report(struct mr_table *mrt, struct sk_buff *pkt,
mifi_t mifi, int assert)
{
struct sock *mroute6_sk;
struct sk_buff *skb;
struct mrt6msg *msg;
int ret;
......@@ -1201,17 +1065,19 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
if (!mrt->mroute6_sk) {
rcu_read_lock();
mroute6_sk = rcu_dereference(mrt->mroute_sk);
if (!mroute6_sk) {
rcu_read_unlock();
kfree_skb(skb);
return -EINVAL;
}
mrt6msg_netlink_event(mrt, skb);
/*
* Deliver to user space multicast routing algorithms
*/
ret = sock_queue_rcv_skb(mrt->mroute6_sk, skb);
/* Deliver to user space multicast routing algorithms */
ret = sock_queue_rcv_skb(mroute6_sk, skb);
rcu_read_unlock();
if (ret < 0) {
net_warn_ratelimited("mroute6: pending queue full, dropping entries\n");
kfree_skb(skb);
......@@ -1220,19 +1086,16 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
return ret;
}
/*
* Queue a packet for resolution. It gets locked cache entry!
*/
static int
ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb)
/* Queue a packet for resolution. It gets locked cache entry! */
static int ip6mr_cache_unresolved(struct mr_table *mrt, mifi_t mifi,
struct sk_buff *skb)
{
struct mfc6_cache *c;
bool found = false;
int err;
struct mfc6_cache *c;
spin_lock_bh(&mfc_unres_lock);
list_for_each_entry(c, &mrt->mfc6_unres_queue, list) {
list_for_each_entry(c, &mrt->mfc_unres_queue, _c.list) {
if (ipv6_addr_equal(&c->mf6c_mcastgrp, &ipv6_hdr(skb)->daddr) &&
ipv6_addr_equal(&c->mf6c_origin, &ipv6_hdr(skb)->saddr)) {
found = true;
......@@ -1253,10 +1116,8 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb)
return -ENOBUFS;
}
/*
* Fill in the new cache entry
*/
c->mf6c_parent = -1;
/* Fill in the new cache entry */
c->_c.mfc_parent = -1;
c->mf6c_origin = ipv6_hdr(skb)->saddr;
c->mf6c_mcastgrp = ipv6_hdr(skb)->daddr;
......@@ -1276,20 +1137,18 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb)
}
atomic_inc(&mrt->cache_resolve_queue_len);
list_add(&c->list, &mrt->mfc6_unres_queue);
list_add(&c->_c.list, &mrt->mfc_unres_queue);
mr6_netlink_event(mrt, c, RTM_NEWROUTE);
ipmr_do_expire_process(mrt);
}
/*
* See if we can append the packet
*/
if (c->mfc_un.unres.unresolved.qlen > 3) {
/* See if we can append the packet */
if (c->_c.mfc_un.unres.unresolved.qlen > 3) {
kfree_skb(skb);
err = -ENOBUFS;
} else {
skb_queue_tail(&c->mfc_un.unres.unresolved, skb);
skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb);
err = 0;
}
......@@ -1301,29 +1160,24 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb)
* MFC6 cache manipulation by user space
*/
static int ip6mr_mfc_delete(struct mr6_table *mrt, struct mf6cctl *mfc,
static int ip6mr_mfc_delete(struct mr_table *mrt, struct mf6cctl *mfc,
int parent)
{
int line;
struct mfc6_cache *c, *next;
line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr);
struct mfc6_cache *c;
list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[line], list) {
if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) &&
ipv6_addr_equal(&c->mf6c_mcastgrp,
&mfc->mf6cc_mcastgrp.sin6_addr) &&
(parent == -1 || parent == c->mf6c_parent)) {
write_lock_bh(&mrt_lock);
list_del(&c->list);
write_unlock_bh(&mrt_lock);
/* The entries are added/deleted only under RTNL */
rcu_read_lock();
c = ip6mr_cache_find_parent(mrt, &mfc->mf6cc_origin.sin6_addr,
&mfc->mf6cc_mcastgrp.sin6_addr, parent);
rcu_read_unlock();
if (!c)
return -ENOENT;
rhltable_remove(&mrt->mfc_hash, &c->_c.mnode, ip6mr_rht_params);
list_del_rcu(&c->_c.list);
mr6_netlink_event(mrt, c, RTM_DELROUTE);
ip6mr_cache_free(c);
return 0;
}
}
return -ENOENT;
mr6_netlink_event(mrt, c, RTM_DELROUTE);
ip6mr_cache_free(c);
return 0;
}
static int ip6mr_device_event(struct notifier_block *this,
......@@ -1331,15 +1185,15 @@ static int ip6mr_device_event(struct notifier_block *this,
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
struct mr6_table *mrt;
struct mif_device *v;
struct mr_table *mrt;
struct vif_device *v;
int ct;
if (event != NETDEV_UNREGISTER)
return NOTIFY_DONE;
ip6mr_for_each_table(mrt, net) {
v = &mrt->vif6_table[0];
v = &mrt->vif_table[0];
for (ct = 0; ct < mrt->maxvif; ct++, v++) {
if (v->dev == dev)
mif6_delete(mrt, ct, 1, NULL);
......@@ -1453,14 +1307,14 @@ void ip6_mr_cleanup(void)
kmem_cache_destroy(mrt_cachep);
}
static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
static int ip6mr_mfc_add(struct net *net, struct mr_table *mrt,
struct mf6cctl *mfc, int mrtsock, int parent)
{
bool found = false;
int line;
struct mfc6_cache *uc, *c;
unsigned char ttls[MAXMIFS];
int i;
struct mfc6_cache *uc, *c;
struct mr_mfc *_uc;
bool found;
int i, err;
if (mfc->mf6cc_parent >= MAXMIFS)
return -ENFILE;
......@@ -1469,27 +1323,19 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
for (i = 0; i < MAXMIFS; i++) {
if (IF_ISSET(i, &mfc->mf6cc_ifset))
ttls[i] = 1;
}
line = MFC6_HASH(&mfc->mf6cc_mcastgrp.sin6_addr, &mfc->mf6cc_origin.sin6_addr);
list_for_each_entry(c, &mrt->mfc6_cache_array[line], list) {
if (ipv6_addr_equal(&c->mf6c_origin, &mfc->mf6cc_origin.sin6_addr) &&
ipv6_addr_equal(&c->mf6c_mcastgrp,
&mfc->mf6cc_mcastgrp.sin6_addr) &&
(parent == -1 || parent == mfc->mf6cc_parent)) {
found = true;
break;
}
}
if (found) {
/* The entries are added/deleted only under RTNL */
rcu_read_lock();
c = ip6mr_cache_find_parent(mrt, &mfc->mf6cc_origin.sin6_addr,
&mfc->mf6cc_mcastgrp.sin6_addr, parent);
rcu_read_unlock();
if (c) {
write_lock_bh(&mrt_lock);
c->mf6c_parent = mfc->mf6cc_parent;
ip6mr_update_thresholds(mrt, c, ttls);
c->_c.mfc_parent = mfc->mf6cc_parent;
ip6mr_update_thresholds(mrt, &c->_c, ttls);
if (!mrtsock)
c->mfc_flags |= MFC_STATIC;
c->_c.mfc_flags |= MFC_STATIC;
write_unlock_bh(&mrt_lock);
mr6_netlink_event(mrt, c, RTM_NEWROUTE);
return 0;
......@@ -1505,31 +1351,36 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
c->mf6c_origin = mfc->mf6cc_origin.sin6_addr;
c->mf6c_mcastgrp = mfc->mf6cc_mcastgrp.sin6_addr;
c->mf6c_parent = mfc->mf6cc_parent;
ip6mr_update_thresholds(mrt, c, ttls);
c->_c.mfc_parent = mfc->mf6cc_parent;
ip6mr_update_thresholds(mrt, &c->_c, ttls);
if (!mrtsock)
c->mfc_flags |= MFC_STATIC;
c->_c.mfc_flags |= MFC_STATIC;
write_lock_bh(&mrt_lock);
list_add(&c->list, &mrt->mfc6_cache_array[line]);
write_unlock_bh(&mrt_lock);
err = rhltable_insert_key(&mrt->mfc_hash, &c->cmparg, &c->_c.mnode,
ip6mr_rht_params);
if (err) {
pr_err("ip6mr: rhtable insert error %d\n", err);
ip6mr_cache_free(c);
return err;
}
list_add_tail_rcu(&c->_c.list, &mrt->mfc_cache_list);
/*
* Check to see if we resolved a queued list. If so we
* need to send on the frames and tidy up.
/* Check to see if we resolved a queued list. If so we
* need to send on the frames and tidy up.
*/
found = false;
spin_lock_bh(&mfc_unres_lock);
list_for_each_entry(uc, &mrt->mfc6_unres_queue, list) {
list_for_each_entry(_uc, &mrt->mfc_unres_queue, list) {
uc = (struct mfc6_cache *)_uc;
if (ipv6_addr_equal(&uc->mf6c_origin, &c->mf6c_origin) &&
ipv6_addr_equal(&uc->mf6c_mcastgrp, &c->mf6c_mcastgrp)) {
list_del(&uc->list);
list_del(&_uc->list);
atomic_dec(&mrt->cache_resolve_queue_len);
found = true;
break;
}
}
if (list_empty(&mrt->mfc6_unres_queue))
if (list_empty(&mrt->mfc_unres_queue))
del_timer(&mrt->ipmr_expire_timer);
spin_unlock_bh(&mfc_unres_lock);
......@@ -1545,61 +1396,54 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
* Close the multicast socket, and clear the vif tables etc
*/
static void mroute_clean_tables(struct mr6_table *mrt, bool all)
static void mroute_clean_tables(struct mr_table *mrt, bool all)
{
int i;
struct mr_mfc *c, *tmp;
LIST_HEAD(list);
struct mfc6_cache *c, *next;
int i;
/*
* Shut down all active vif entries
*/
/* Shut down all active vif entries */
for (i = 0; i < mrt->maxvif; i++) {
if (!all && (mrt->vif6_table[i].flags & VIFF_STATIC))
if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
continue;
mif6_delete(mrt, i, 0, &list);
}
unregister_netdevice_many(&list);
/*
* Wipe the cache
*/
for (i = 0; i < MFC6_LINES; i++) {
list_for_each_entry_safe(c, next, &mrt->mfc6_cache_array[i], list) {
if (!all && (c->mfc_flags & MFC_STATIC))
continue;
write_lock_bh(&mrt_lock);
list_del(&c->list);
write_unlock_bh(&mrt_lock);
mr6_netlink_event(mrt, c, RTM_DELROUTE);
ip6mr_cache_free(c);
}
/* Wipe the cache */
list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) {
if (!all && (c->mfc_flags & MFC_STATIC))
continue;
rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params);
list_del_rcu(&c->list);
mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE);
ip6mr_cache_free((struct mfc6_cache *)c);
}
if (atomic_read(&mrt->cache_resolve_queue_len) != 0) {
spin_lock_bh(&mfc_unres_lock);
list_for_each_entry_safe(c, next, &mrt->mfc6_unres_queue, list) {
list_for_each_entry_safe(c, tmp, &mrt->mfc_unres_queue, list) {
list_del(&c->list);
mr6_netlink_event(mrt, c, RTM_DELROUTE);
ip6mr_destroy_unres(mrt, c);
mr6_netlink_event(mrt, (struct mfc6_cache *)c,
RTM_DELROUTE);
ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c);
}
spin_unlock_bh(&mfc_unres_lock);
}
}
static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk)
static int ip6mr_sk_init(struct mr_table *mrt, struct sock *sk)
{
int err = 0;
struct net *net = sock_net(sk);
rtnl_lock();
write_lock_bh(&mrt_lock);
if (likely(mrt->mroute6_sk == NULL)) {
mrt->mroute6_sk = sk;
net->ipv6.devconf_all->mc_forwarding++;
} else {
if (rtnl_dereference(mrt->mroute_sk)) {
err = -EADDRINUSE;
} else {
rcu_assign_pointer(mrt->mroute_sk, sk);
net->ipv6.devconf_all->mc_forwarding++;
}
write_unlock_bh(&mrt_lock);
......@@ -1617,7 +1461,7 @@ int ip6mr_sk_done(struct sock *sk)
{
int err = -EACCES;
struct net *net = sock_net(sk);
struct mr6_table *mrt;
struct mr_table *mrt;
if (sk->sk_type != SOCK_RAW ||
inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
......@@ -1625,9 +1469,9 @@ int ip6mr_sk_done(struct sock *sk)
rtnl_lock();
ip6mr_for_each_table(mrt, net) {
if (sk == mrt->mroute6_sk) {
if (sk == rtnl_dereference(mrt->mroute_sk)) {
write_lock_bh(&mrt_lock);
mrt->mroute6_sk = NULL;
RCU_INIT_POINTER(mrt->mroute_sk, NULL);
net->ipv6.devconf_all->mc_forwarding--;
write_unlock_bh(&mrt_lock);
inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
......@@ -1641,13 +1485,14 @@ int ip6mr_sk_done(struct sock *sk)
}
}
rtnl_unlock();
synchronize_rcu();
return err;
}
struct sock *mroute6_socket(struct net *net, struct sk_buff *skb)
bool mroute6_is_socket(struct net *net, struct sk_buff *skb)
{
struct mr6_table *mrt;
struct mr_table *mrt;
struct flowi6 fl6 = {
.flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX,
.flowi6_oif = skb->dev->ifindex,
......@@ -1657,8 +1502,9 @@ struct sock *mroute6_socket(struct net *net, struct sk_buff *skb)
if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0)
return NULL;
return mrt->mroute6_sk;
return rcu_access_pointer(mrt->mroute_sk);
}
EXPORT_SYMBOL(mroute6_is_socket);
/*
* Socket options and virtual interface manipulation. The whole
......@@ -1674,7 +1520,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
struct mf6cctl mfc;
mifi_t mifi;
struct net *net = sock_net(sk);
struct mr6_table *mrt;
struct mr_table *mrt;
if (sk->sk_type != SOCK_RAW ||
inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
......@@ -1685,7 +1531,8 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
return -ENOENT;
if (optname != MRT6_INIT) {
if (sk != mrt->mroute6_sk && !ns_capable(net->user_ns, CAP_NET_ADMIN))
if (sk != rcu_access_pointer(mrt->mroute_sk) &&
!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EACCES;
}
......@@ -1707,7 +1554,8 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
if (vif.mif6c_mifi >= MAXMIFS)
return -ENFILE;
rtnl_lock();
ret = mif6_add(net, mrt, &vif, sk == mrt->mroute6_sk);
ret = mif6_add(net, mrt, &vif,
sk == rtnl_dereference(mrt->mroute_sk));
rtnl_unlock();
return ret;
......@@ -1742,7 +1590,9 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
ret = ip6mr_mfc_delete(mrt, &mfc, parent);
else
ret = ip6mr_mfc_add(net, mrt, &mfc,
sk == mrt->mroute6_sk, parent);
sk ==
rtnl_dereference(mrt->mroute_sk),
parent);
rtnl_unlock();
return ret;
......@@ -1794,7 +1644,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
/* "pim6reg%u" should not exceed 16 bytes (IFNAMSIZ) */
if (v != RT_TABLE_DEFAULT && v >= 100000000)
return -EINVAL;
if (sk == mrt->mroute6_sk)
if (sk == rcu_access_pointer(mrt->mroute_sk))
return -EBUSY;
rtnl_lock();
......@@ -1825,7 +1675,7 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
int olr;
int val;
struct net *net = sock_net(sk);
struct mr6_table *mrt;
struct mr_table *mrt;
if (sk->sk_type != SOCK_RAW ||
inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
......@@ -1873,10 +1723,10 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
{
struct sioc_sg_req6 sr;
struct sioc_mif_req6 vr;
struct mif_device *vif;
struct vif_device *vif;
struct mfc6_cache *c;
struct net *net = sock_net(sk);
struct mr6_table *mrt;
struct mr_table *mrt;
mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
if (!mrt)
......@@ -1889,8 +1739,8 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
if (vr.mifi >= mrt->maxvif)
return -EINVAL;
read_lock(&mrt_lock);
vif = &mrt->vif6_table[vr.mifi];
if (MIF_EXISTS(mrt, vr.mifi)) {
vif = &mrt->vif_table[vr.mifi];
if (VIF_EXISTS(mrt, vr.mifi)) {
vr.icount = vif->pkt_in;
vr.ocount = vif->pkt_out;
vr.ibytes = vif->bytes_in;
......@@ -1907,19 +1757,19 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
if (copy_from_user(&sr, arg, sizeof(sr)))
return -EFAULT;
read_lock(&mrt_lock);
rcu_read_lock();
c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr);
if (c) {
sr.pktcnt = c->mfc_un.res.pkt;
sr.bytecnt = c->mfc_un.res.bytes;
sr.wrong_if = c->mfc_un.res.wrong_if;
read_unlock(&mrt_lock);
sr.pktcnt = c->_c.mfc_un.res.pkt;
sr.bytecnt = c->_c.mfc_un.res.bytes;
sr.wrong_if = c->_c.mfc_un.res.wrong_if;
rcu_read_unlock();
if (copy_to_user(arg, &sr, sizeof(sr)))
return -EFAULT;
return 0;
}
read_unlock(&mrt_lock);
rcu_read_unlock();
return -EADDRNOTAVAIL;
default:
return -ENOIOCTLCMD;
......@@ -1947,10 +1797,10 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
{
struct compat_sioc_sg_req6 sr;
struct compat_sioc_mif_req6 vr;
struct mif_device *vif;
struct vif_device *vif;
struct mfc6_cache *c;
struct net *net = sock_net(sk);
struct mr6_table *mrt;
struct mr_table *mrt;
mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
if (!mrt)
......@@ -1963,8 +1813,8 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
if (vr.mifi >= mrt->maxvif)
return -EINVAL;
read_lock(&mrt_lock);
vif = &mrt->vif6_table[vr.mifi];
if (MIF_EXISTS(mrt, vr.mifi)) {
vif = &mrt->vif_table[vr.mifi];
if (VIF_EXISTS(mrt, vr.mifi)) {
vr.icount = vif->pkt_in;
vr.ocount = vif->pkt_out;
vr.ibytes = vif->bytes_in;
......@@ -1981,19 +1831,19 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
if (copy_from_user(&sr, arg, sizeof(sr)))
return -EFAULT;
read_lock(&mrt_lock);
rcu_read_lock();
c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr);
if (c) {
sr.pktcnt = c->mfc_un.res.pkt;
sr.bytecnt = c->mfc_un.res.bytes;
sr.wrong_if = c->mfc_un.res.wrong_if;
read_unlock(&mrt_lock);
sr.pktcnt = c->_c.mfc_un.res.pkt;
sr.bytecnt = c->_c.mfc_un.res.bytes;
sr.wrong_if = c->_c.mfc_un.res.wrong_if;
rcu_read_unlock();
if (copy_to_user(arg, &sr, sizeof(sr)))
return -EFAULT;
return 0;
}
read_unlock(&mrt_lock);
rcu_read_unlock();
return -EADDRNOTAVAIL;
default:
return -ENOIOCTLCMD;
......@@ -2014,11 +1864,11 @@ static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct
* Processing handlers for ip6mr_forward
*/
static int ip6mr_forward2(struct net *net, struct mr6_table *mrt,
static int ip6mr_forward2(struct net *net, struct mr_table *mrt,
struct sk_buff *skb, struct mfc6_cache *c, int vifi)
{
struct ipv6hdr *ipv6h;
struct mif_device *vif = &mrt->vif6_table[vifi];
struct vif_device *vif = &mrt->vif_table[vifi];
struct net_device *dev;
struct dst_entry *dst;
struct flowi6 fl6;
......@@ -2088,46 +1938,50 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt,
return 0;
}
static int ip6mr_find_vif(struct mr6_table *mrt, struct net_device *dev)
static int ip6mr_find_vif(struct mr_table *mrt, struct net_device *dev)
{
int ct;
for (ct = mrt->maxvif - 1; ct >= 0; ct--) {
if (mrt->vif6_table[ct].dev == dev)
if (mrt->vif_table[ct].dev == dev)
break;
}
return ct;
}
static void ip6_mr_forward(struct net *net, struct mr6_table *mrt,
struct sk_buff *skb, struct mfc6_cache *cache)
static void ip6_mr_forward(struct net *net, struct mr_table *mrt,
struct sk_buff *skb, struct mfc6_cache *c)
{
int psend = -1;
int vif, ct;
int true_vifi = ip6mr_find_vif(mrt, skb->dev);
vif = cache->mf6c_parent;
cache->mfc_un.res.pkt++;
cache->mfc_un.res.bytes += skb->len;
cache->mfc_un.res.lastuse = jiffies;
vif = c->_c.mfc_parent;
c->_c.mfc_un.res.pkt++;
c->_c.mfc_un.res.bytes += skb->len;
c->_c.mfc_un.res.lastuse = jiffies;
if (ipv6_addr_any(&cache->mf6c_origin) && true_vifi >= 0) {
if (ipv6_addr_any(&c->mf6c_origin) && true_vifi >= 0) {
struct mfc6_cache *cache_proxy;
/* For an (*,G) entry, we only check that the incoming
* interface is part of the static tree.
*/
cache_proxy = ip6mr_cache_find_any_parent(mrt, vif);
rcu_read_lock();
cache_proxy = mr_mfc_find_any_parent(mrt, vif);
if (cache_proxy &&
cache_proxy->mfc_un.res.ttls[true_vifi] < 255)
cache_proxy->_c.mfc_un.res.ttls[true_vifi] < 255) {
rcu_read_unlock();
goto forward;
}
rcu_read_unlock();
}
/*
* Wrong interface: drop packet and (maybe) send PIM assert.
*/
if (mrt->vif6_table[vif].dev != skb->dev) {
cache->mfc_un.res.wrong_if++;
if (mrt->vif_table[vif].dev != skb->dev) {
c->_c.mfc_un.res.wrong_if++;
if (true_vifi >= 0 && mrt->mroute_do_assert &&
/* pimsm uses asserts, when switching from RPT to SPT,
......@@ -2136,52 +1990,55 @@ static void ip6_mr_forward(struct net *net, struct mr6_table *mrt,
large chunk of pimd to kernel. Ough... --ANK
*/
(mrt->mroute_do_pim ||
cache->mfc_un.res.ttls[true_vifi] < 255) &&
c->_c.mfc_un.res.ttls[true_vifi] < 255) &&
time_after(jiffies,
cache->mfc_un.res.last_assert + MFC_ASSERT_THRESH)) {
cache->mfc_un.res.last_assert = jiffies;
c->_c.mfc_un.res.last_assert +
MFC_ASSERT_THRESH)) {
c->_c.mfc_un.res.last_assert = jiffies;
ip6mr_cache_report(mrt, skb, true_vifi, MRT6MSG_WRONGMIF);
}
goto dont_forward;
}
forward:
mrt->vif6_table[vif].pkt_in++;
mrt->vif6_table[vif].bytes_in += skb->len;
mrt->vif_table[vif].pkt_in++;
mrt->vif_table[vif].bytes_in += skb->len;
/*
* Forward the frame
*/
if (ipv6_addr_any(&cache->mf6c_origin) &&
ipv6_addr_any(&cache->mf6c_mcastgrp)) {
if (ipv6_addr_any(&c->mf6c_origin) &&
ipv6_addr_any(&c->mf6c_mcastgrp)) {
if (true_vifi >= 0 &&
true_vifi != cache->mf6c_parent &&
true_vifi != c->_c.mfc_parent &&
ipv6_hdr(skb)->hop_limit >
cache->mfc_un.res.ttls[cache->mf6c_parent]) {
c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) {
/* It's an (*,*) entry and the packet is not coming from
* the upstream: forward the packet to the upstream
* only.
*/
psend = cache->mf6c_parent;
psend = c->_c.mfc_parent;
goto last_forward;
}
goto dont_forward;
}
for (ct = cache->mfc_un.res.maxvif - 1; ct >= cache->mfc_un.res.minvif; ct--) {
for (ct = c->_c.mfc_un.res.maxvif - 1;
ct >= c->_c.mfc_un.res.minvif; ct--) {
/* For (*,G) entry, don't forward to the incoming interface */
if ((!ipv6_addr_any(&cache->mf6c_origin) || ct != true_vifi) &&
ipv6_hdr(skb)->hop_limit > cache->mfc_un.res.ttls[ct]) {
if ((!ipv6_addr_any(&c->mf6c_origin) || ct != true_vifi) &&
ipv6_hdr(skb)->hop_limit > c->_c.mfc_un.res.ttls[ct]) {
if (psend != -1) {
struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC);
if (skb2)
ip6mr_forward2(net, mrt, skb2, cache, psend);
ip6mr_forward2(net, mrt, skb2,
c, psend);
}
psend = ct;
}
}
last_forward:
if (psend != -1) {
ip6mr_forward2(net, mrt, skb, cache, psend);
ip6mr_forward2(net, mrt, skb, c, psend);
return;
}
......@@ -2198,7 +2055,7 @@ int ip6_mr_input(struct sk_buff *skb)
{
struct mfc6_cache *cache;
struct net *net = dev_net(skb->dev);
struct mr6_table *mrt;
struct mr_table *mrt;
struct flowi6 fl6 = {
.flowi6_iif = skb->dev->ifindex,
.flowi6_mark = skb->mark,
......@@ -2248,66 +2105,11 @@ int ip6_mr_input(struct sk_buff *skb)
return 0;
}
static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
struct mfc6_cache *c, struct rtmsg *rtm)
{
struct rta_mfc_stats mfcs;
struct nlattr *mp_attr;
struct rtnexthop *nhp;
unsigned long lastuse;
int ct;
/* If cache is unresolved, don't try to parse IIF and OIF */
if (c->mf6c_parent >= MAXMIFS) {
rtm->rtm_flags |= RTNH_F_UNRESOLVED;
return -ENOENT;
}
if (MIF_EXISTS(mrt, c->mf6c_parent) &&
nla_put_u32(skb, RTA_IIF, mrt->vif6_table[c->mf6c_parent].dev->ifindex) < 0)
return -EMSGSIZE;
mp_attr = nla_nest_start(skb, RTA_MULTIPATH);
if (!mp_attr)
return -EMSGSIZE;
for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) {
if (MIF_EXISTS(mrt, ct) && c->mfc_un.res.ttls[ct] < 255) {
nhp = nla_reserve_nohdr(skb, sizeof(*nhp));
if (!nhp) {
nla_nest_cancel(skb, mp_attr);
return -EMSGSIZE;
}
nhp->rtnh_flags = 0;
nhp->rtnh_hops = c->mfc_un.res.ttls[ct];
nhp->rtnh_ifindex = mrt->vif6_table[ct].dev->ifindex;
nhp->rtnh_len = sizeof(*nhp);
}
}
nla_nest_end(skb, mp_attr);
lastuse = READ_ONCE(c->mfc_un.res.lastuse);
lastuse = time_after_eq(jiffies, lastuse) ? jiffies - lastuse : 0;
mfcs.mfcs_packets = c->mfc_un.res.pkt;
mfcs.mfcs_bytes = c->mfc_un.res.bytes;
mfcs.mfcs_wrong_if = c->mfc_un.res.wrong_if;
if (nla_put_64bit(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs, RTA_PAD) ||
nla_put_u64_64bit(skb, RTA_EXPIRES, jiffies_to_clock_t(lastuse),
RTA_PAD))
return -EMSGSIZE;
rtm->rtm_type = RTN_MULTICAST;
return 1;
}
int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
u32 portid)
{
int err;
struct mr6_table *mrt;
struct mr_table *mrt;
struct mfc6_cache *cache;
struct rt6_info *rt = (struct rt6_info *)skb_dst(skb);
......@@ -2368,15 +2170,12 @@ int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
return err;
}
if (rtm->rtm_flags & RTM_F_NOTIFY)
cache->mfc_flags |= MFC_NOTIFY;
err = __ip6mr_fill_mroute(mrt, skb, cache, rtm);
err = mr_fill_mroute(mrt, skb, &cache->_c, rtm);
read_unlock(&mrt_lock);
return err;
}
static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
static int ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
u32 portid, u32 seq, struct mfc6_cache *c, int cmd,
int flags)
{
......@@ -2398,7 +2197,7 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
goto nla_put_failure;
rtm->rtm_type = RTN_MULTICAST;
rtm->rtm_scope = RT_SCOPE_UNIVERSE;
if (c->mfc_flags & MFC_STATIC)
if (c->_c.mfc_flags & MFC_STATIC)
rtm->rtm_protocol = RTPROT_STATIC;
else
rtm->rtm_protocol = RTPROT_MROUTED;
......@@ -2407,7 +2206,7 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
if (nla_put_in6_addr(skb, RTA_SRC, &c->mf6c_origin) ||
nla_put_in6_addr(skb, RTA_DST, &c->mf6c_mcastgrp))
goto nla_put_failure;
err = __ip6mr_fill_mroute(mrt, skb, c, rtm);
err = mr_fill_mroute(mrt, skb, &c->_c, rtm);
/* do not break the dump if cache is unresolved */
if (err < 0 && err != -ENOENT)
goto nla_put_failure;
......@@ -2420,6 +2219,14 @@ static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
return -EMSGSIZE;
}
static int _ip6mr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
u32 portid, u32 seq, struct mr_mfc *c,
int cmd, int flags)
{
return ip6mr_fill_mroute(mrt, skb, portid, seq, (struct mfc6_cache *)c,
cmd, flags);
}
static int mr6_msgsize(bool unresolved, int maxvif)
{
size_t len =
......@@ -2441,14 +2248,14 @@ static int mr6_msgsize(bool unresolved, int maxvif)
return len;
}
static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
static void mr6_netlink_event(struct mr_table *mrt, struct mfc6_cache *mfc,
int cmd)
{
struct net *net = read_pnet(&mrt->net);
struct sk_buff *skb;
int err = -ENOBUFS;
skb = nlmsg_new(mr6_msgsize(mfc->mf6c_parent >= MAXMIFS, mrt->maxvif),
skb = nlmsg_new(mr6_msgsize(mfc->_c.mfc_parent >= MAXMIFS, mrt->maxvif),
GFP_ATOMIC);
if (!skb)
goto errout;
......@@ -2483,7 +2290,7 @@ static size_t mrt6msg_netlink_msgsize(size_t payloadlen)
return len;
}
static void mrt6msg_netlink_event(struct mr6_table *mrt, struct sk_buff *pkt)
static void mrt6msg_netlink_event(struct mr_table *mrt, struct sk_buff *pkt)
{
struct net *net = read_pnet(&mrt->net);
struct nlmsghdr *nlh;
......@@ -2533,65 +2340,6 @@ static void mrt6msg_netlink_event(struct mr6_table *mrt, struct sk_buff *pkt)
static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
{
struct net *net = sock_net(skb->sk);
struct mr6_table *mrt;
struct mfc6_cache *mfc;
unsigned int t = 0, s_t;
unsigned int h = 0, s_h;
unsigned int e = 0, s_e;
s_t = cb->args[0];
s_h = cb->args[1];
s_e = cb->args[2];
read_lock(&mrt_lock);
ip6mr_for_each_table(mrt, net) {
if (t < s_t)
goto next_table;
if (t > s_t)
s_h = 0;
for (h = s_h; h < MFC6_LINES; h++) {
list_for_each_entry(mfc, &mrt->mfc6_cache_array[h], list) {
if (e < s_e)
goto next_entry;
if (ip6mr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
mfc, RTM_NEWROUTE,
NLM_F_MULTI) < 0)
goto done;
next_entry:
e++;
}
e = s_e = 0;
}
spin_lock_bh(&mfc_unres_lock);
list_for_each_entry(mfc, &mrt->mfc6_unres_queue, list) {
if (e < s_e)
goto next_entry2;
if (ip6mr_fill_mroute(mrt, skb,
NETLINK_CB(cb->skb).portid,
cb->nlh->nlmsg_seq,
mfc, RTM_NEWROUTE,
NLM_F_MULTI) < 0) {
spin_unlock_bh(&mfc_unres_lock);
goto done;
}
next_entry2:
e++;
}
spin_unlock_bh(&mfc_unres_lock);
e = s_e = 0;
s_h = 0;
next_table:
t++;
}
done:
read_unlock(&mrt_lock);
cb->args[2] = e;
cb->args[1] = h;
cb->args[0] = t;
return skb->len;
return mr_rtm_dumproute(skb, cb, ip6mr_mr_table_iter,
_ip6mr_fill_mroute, &mfc_unres_lock);
}
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或