summaryrefslogtreecommitdiff
path: root/net/ipv6/ip6mr.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/ip6mr.c')
-rw-r--r--net/ipv6/ip6mr.c2060
1 files changed, 1170 insertions, 890 deletions
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index 583e8d435f9a..e047a4680ab0 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
/*
* Linux IPv6 multicast routing support for BSD pim6sd
* Based on net/ipv4/ipmr.c.
@@ -8,19 +9,12 @@
* 6WIND, Paris, France
* Copyright (C)2007,2008 USAGI/WIDE Project
* YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org>
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License
- * as published by the Free Software Foundation; either version
- * 2 of the License, or (at your option) any later version.
- *
*/
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
#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 +26,10 @@
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/init.h>
-#include <linux/slab.h>
#include <linux/compat.h>
+#include <linux/rhashtable.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>
@@ -53,46 +46,30 @@
#include <linux/export.h>
#include <net/ip6_checksum.h>
#include <linux/netconf.h>
+#include <net/ip_tunnels.h>
-struct mr6_table {
- struct list_head list;
-#ifdef CONFIG_NET_NS
- struct net *net;
-#endif
- 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
-};
+#include <linux/nospec.h>
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.
Note that the changes are semaphored via rtnl_lock.
*/
-static DEFINE_RWLOCK(mrt_lock);
+static DEFINE_SPINLOCK(mrt_lock);
-/*
- * Multicast router control variables
- */
+static struct net_device *vif_dev_read(const struct vif_device *vif)
+{
+ return rcu_dereference(vif->dev);
+}
-#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);
@@ -107,29 +84,50 @@ 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 int ip6_mr_forward(struct net *net, struct mr6_table *mrt,
- struct sk_buff *skb, struct mfc6_cache *cache);
-static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
+static void ip6_mr_forward(struct net *net, struct mr_table *mrt,
+ struct net_device *dev, struct sk_buff *skb,
+ struct mfc6_cache *cache);
+static int ip6mr_cache_report(const 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(const struct mr_table *mrt, struct sk_buff *pkt);
+static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack);
static int ip6mr_rtm_dumproute(struct sk_buff *skb,
struct netlink_callback *cb);
-static void mroute_clean_tables(struct mr6_table *mrt);
-static void ipmr_expire_process(unsigned long arg);
+static void mroute_clean_tables(struct mr_table *mrt, int flags);
+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)
+ list_for_each_entry_rcu(mrt, &net->ipv6.mr6_tables, list, \
+ lockdep_rtnl_is_held() || \
+ list_empty(&net->ipv6.mr6_tables))
-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 mr6_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 mr_table *mrt;
ip6mr_for_each_table(mrt, net) {
if (mrt->id == id)
@@ -138,12 +136,28 @@ static struct mr6_table *ip6mr_get_table(struct net *net, u32 id)
return NULL;
}
+static struct mr_table *ip6mr_get_table(struct net *net, u32 id)
+{
+ struct mr_table *mrt;
+
+ rcu_read_lock();
+ mrt = __ip6mr_get_table(net, id);
+ rcu_read_unlock();
+ return mrt;
+}
+
static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
- struct mr6_table **mrt)
+ struct mr_table **mrt)
{
- struct ip6mr_result res;
- struct fib_lookup_arg arg = { .result = &res, };
int err;
+ struct ip6mr_result res;
+ struct fib_lookup_arg arg = {
+ .result = &res,
+ .flags = FIB_LOOKUP_NOREF,
+ };
+
+ /* update flow if oif or iif point to device enslaved to l3mdev */
+ l3mdev_update_flow(net, flowi6_to_flowi(flp6));
err = fib_rules_lookup(net->ipv6.mr6_rules_ops,
flowi6_to_flowi(flp6), 0, &arg);
@@ -157,7 +171,7 @@ 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:
@@ -171,8 +185,10 @@ static int ip6mr_rule_action(struct fib_rule *rule, struct flowi *flp,
return -EINVAL;
}
- mrt = ip6mr_get_table(rule->fr_net, rule->table);
- if (mrt == NULL)
+ arg->table = fib_rule_get_table(rule, arg);
+
+ mrt = __ip6mr_get_table(rule->fr_net, arg->table);
+ if (!mrt)
return -EAGAIN;
res->mrt = mrt;
return 0;
@@ -183,12 +199,9 @@ static int ip6mr_rule_match(struct fib_rule *rule, struct flowi *flp, int flags)
return 1;
}
-static const struct nla_policy ip6mr_rule_policy[FRA_MAX + 1] = {
- FRA_GENERIC_POLICY,
-};
-
static int ip6mr_rule_configure(struct fib_rule *rule, struct sk_buff *skb,
- struct fib_rule_hdr *frh, struct nlattr **tb)
+ struct fib_rule_hdr *frh, struct nlattr **tb,
+ struct netlink_ext_ack *extack)
{
return 0;
}
@@ -216,17 +229,15 @@ static const struct fib_rules_ops __net_initconst ip6mr_rules_ops_template = {
.match = ip6mr_rule_match,
.configure = ip6mr_rule_configure,
.compare = ip6mr_rule_compare,
- .default_pref = fib_default_rule_pref,
.fill = ip6mr_rule_fill,
.nlgroup = RTNLGRP_IPV6_RULE,
- .policy = ip6mr_rule_policy,
.owner = THIS_MODULE,
};
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);
@@ -236,12 +247,12 @@ static int __net_init ip6mr_rules_init(struct net *net)
INIT_LIST_HEAD(&net->ipv6.mr6_tables);
mrt = ip6mr_new_table(net, RT6_TABLE_DFLT);
- if (mrt == NULL) {
- err = -ENOMEM;
+ if (IS_ERR(mrt)) {
+ err = PTR_ERR(mrt);
goto err1;
}
- err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT, 0);
+ err = fib_default_rule_add(ops, 0x7fff, RT6_TABLE_DFLT);
if (err < 0)
goto err2;
@@ -249,7 +260,9 @@ static int __net_init ip6mr_rules_init(struct net *net)
return 0;
err2:
- kfree(mrt);
+ rtnl_lock();
+ ip6mr_free_table(mrt);
+ rtnl_unlock();
err1:
fib_rules_unregister(ops);
return err;
@@ -257,25 +270,54 @@ err1:
static void __net_exit ip6mr_rules_exit(struct net *net)
{
- struct mr6_table *mrt, *next;
+ struct mr_table *mrt, *next;
+ ASSERT_RTNL();
list_for_each_entry_safe(mrt, next, &net->ipv6.mr6_tables, list) {
list_del(&mrt->list);
ip6mr_free_table(mrt);
}
fib_rules_unregister(net->ipv6.mr6_rules_ops);
}
+
+static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
+{
+ return fib_rules_dump(net, nb, RTNL_FAMILY_IP6MR, extack);
+}
+
+static unsigned int ip6mr_rules_seq_read(const struct net *net)
+{
+ return fib_rules_seq_read(net, RTNL_FAMILY_IP6MR);
+}
+
+bool ip6mr_rule_default(const struct fib_rule *rule)
+{
+ return fib_rule_matchall(rule) && rule->action == FR_ACT_TO_TBL &&
+ rule->table == RT6_TABLE_DFLT && !rule->l3mdev;
+}
+EXPORT_SYMBOL(ip6mr_rule_default);
#else
#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;
}
+#define __ip6mr_get_table ip6mr_get_table
+
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;
@@ -283,174 +325,145 @@ static int ip6mr_fib_lookup(struct net *net, struct flowi6 *flp6,
static int __net_init ip6mr_rules_init(struct net *net)
{
- net->ipv6.mrt6 = ip6mr_new_table(net, RT6_TABLE_DFLT);
- return net->ipv6.mrt6 ? 0 : -ENOMEM;
+ struct mr_table *mrt;
+
+ mrt = ip6mr_new_table(net, RT6_TABLE_DFLT);
+ if (IS_ERR(mrt))
+ return PTR_ERR(mrt);
+ net->ipv6.mrt6 = mrt;
+ return 0;
}
static void __net_exit ip6mr_rules_exit(struct net *net)
{
+ ASSERT_RTNL();
ip6mr_free_table(net->ipv6.mrt6);
+ net->ipv6.mrt6 = NULL;
}
-#endif
-static struct mr6_table *ip6mr_new_table(struct net *net, u32 id)
+static int ip6mr_rules_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
{
- struct mr6_table *mrt;
- unsigned int i;
-
- mrt = ip6mr_get_table(net, id);
- if (mrt != NULL)
- return mrt;
+ return 0;
+}
- mrt = kzalloc(sizeof(*mrt), GFP_KERNEL);
- if (mrt == NULL)
- return NULL;
- mrt->id = id;
- write_pnet(&mrt->net, net);
+static unsigned int ip6mr_rules_seq_read(const struct net *net)
+{
+ return 0;
+}
+#endif
- /* Forwarding cache */
- for (i = 0; i < MFC6_LINES; i++)
- INIT_LIST_HEAD(&mrt->mfc6_cache_array[i]);
+static int ip6mr_hash_cmp(struct rhashtable_compare_arg *arg,
+ const void *ptr)
+{
+ const struct mfc6_cache_cmp_arg *cmparg = arg->key;
+ struct mfc6_cache *c = (struct mfc6_cache *)ptr;
- 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);
+}
- setup_timer(&mrt->ipmr_expire_timer, ipmr_expire_process,
- (unsigned long)mrt);
+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,
+ .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(&mrt->ipmr_expire_timer);
- mroute_clean_tables(mrt);
- 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;
+ struct mr_table *mrt;
- 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);
-
- 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;
+ struct net *net = read_pnet(&mrt->net);
- 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;
+ WARN_ON_ONCE(!mr_can_free_table(net));
+
+ timer_shutdown_sync(&mrt->ipmr_expire_timer);
+ mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC |
+ MRT6_FLUSH_MFC | MRT6_FLUSH_MFC_STATIC);
+ 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)
+ __acquires(RCU)
{
- 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 == NULL)
+ rcu_read_lock();
+ mrt = __ip6mr_get_table(net, RT6_TABLE_DFLT);
+ if (!mrt) {
+ rcu_read_unlock();
return ERR_PTR(-ENOENT);
+ }
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)
- __releases(mrt_lock)
+ __releases(RCU)
{
- read_unlock(&mrt_lock);
+ rcu_read_unlock();
}
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 char *name = vif->dev ? vif->dev->name : "none";
+ const struct vif_device *vif = v;
+ const struct net_device *vif_dev;
+ const char *name;
+
+ vif_dev = vif_dev_read(vif);
+ 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);
@@ -460,92 +473,21 @@ 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,
};
-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));
-}
-
-static const struct file_operations ip6mr_vif_fops = {
- .owner = THIS_MODULE,
- .open = ip6mr_vif_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
-
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 == NULL)
+ if (!mrt)
return ERR_PTR(-ENOENT);
- it->mrt = mrt;
- 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)
- 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)
@@ -559,25 +501,25 @@ 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)
+ atomic_long_read(&mfc->_c.mfc_un.res.pkt),
+ atomic_long_read(&mfc->_c.mfc_un.res.bytes),
+ atomic_long_read(&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
@@ -592,24 +534,10 @@ 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));
-}
-
-static const struct file_operations ip6mr_mfc_fops = {
- .owner = THIS_MODULE,
- .open = ipmr_mfc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = seq_release_net,
-};
#endif
#ifdef CONFIG_IPV6_PIMSM_V2
@@ -620,7 +548,7 @@ 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,
@@ -631,7 +559,7 @@ static int pim6_rcv(struct sk_buff *skb)
goto drop;
pim = (struct pimreghdr *)skb_transport_header(skb);
- if (pim->type != ((PIM_VERSION << 4) | PIM_REGISTER) ||
+ if (pim->type != ((PIM_VERSION << 4) | PIM_TYPE_REGISTER) ||
(pim->flags & PIM_NULL_REGISTER) ||
(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr,
sizeof(*pim), IPPROTO_PIM,
@@ -650,16 +578,13 @@ static int pim6_rcv(struct sk_buff *skb)
if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0)
goto drop;
- reg_vif_num = mrt->mroute_reg_vif_num;
- read_lock(&mrt_lock);
+ /* Pairs with WRITE_ONCE() in mif6_add()/mif6_delete() */
+ reg_vif_num = READ_ONCE(mrt->mroute_reg_vif_num);
if (reg_vif_num >= 0)
- reg_dev = mrt->vif6_table[reg_vif_num].dev;
- if (reg_dev)
- dev_hold(reg_dev);
- read_unlock(&mrt_lock);
+ reg_dev = vif_dev_read(&mrt->vif_table[reg_vif_num]);
- if (reg_dev == NULL)
+ if (!reg_dev)
goto drop;
skb->mac_header = skb->network_header;
@@ -667,13 +592,11 @@ static int pim6_rcv(struct sk_buff *skb)
skb_reset_network_header(skb);
skb->protocol = htons(ETH_P_IPV6);
skb->ip_summed = CHECKSUM_NONE;
- skb->pkt_type = PACKET_HOST;
- skb_tunnel_rx(skb, reg_dev);
+ skb_tunnel_rx(skb, reg_dev, dev_net(reg_dev));
netif_rx(skb);
- dev_put(reg_dev);
return 0;
drop:
kfree_skb(skb);
@@ -690,31 +613,42 @@ 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,
+ .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX,
.flowi6_mark = skb->mark,
};
- int err;
- err = ip6mr_fib_lookup(net, &fl6, &mrt);
- if (err < 0) {
- kfree_skb(skb);
- return err;
- }
+ if (!pskb_inet_may_pull(skb))
+ goto tx_err;
- read_lock(&mrt_lock);
- dev->stats.tx_bytes += skb->len;
- dev->stats.tx_packets++;
- ip6mr_cache_report(mrt, skb, mrt->mroute_reg_vif_num, MRT6MSG_WHOLEPKT);
- read_unlock(&mrt_lock);
+ if (ip6mr_fib_lookup(net, &fl6, &mrt) < 0)
+ goto tx_err;
+
+ DEV_STATS_ADD(dev, tx_bytes, skb->len);
+ DEV_STATS_INC(dev, tx_packets);
+ rcu_read_lock();
+ ip6mr_cache_report(mrt, skb, READ_ONCE(mrt->mroute_reg_vif_num),
+ MRT6MSG_WHOLEPKT);
+ rcu_read_unlock();
kfree_skb(skb);
return NETDEV_TX_OK;
+
+tx_err:
+ DEV_STATS_INC(dev, tx_errors);
+ kfree_skb(skb);
+ return NETDEV_TX_OK;
+}
+
+static int reg_vif_get_iflink(const struct net_device *dev)
+{
+ return 0;
}
static const struct net_device_ops reg_vif_netdev_ops = {
.ndo_start_xmit = reg_vif_xmit,
+ .ndo_get_iflink = reg_vif_get_iflink,
};
static void reg_vif_setup(struct net_device *dev)
@@ -723,11 +657,11 @@ static void reg_vif_setup(struct net_device *dev)
dev->mtu = 1500 - sizeof(struct ipv6hdr) - 8;
dev->flags = IFF_NOARP;
dev->netdev_ops = &reg_vif_netdev_ops;
- dev->destructor = free_netdev;
- dev->features |= NETIF_F_NETNS_LOCAL;
+ dev->needs_free_netdev = true;
+ dev->netns_immutable = true;
}
-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];
@@ -737,8 +671,8 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt)
else
sprintf(name, "pim6reg%u", mrt->id);
- dev = alloc_netdev(0, name, reg_vif_setup);
- if (dev == NULL)
+ dev = alloc_netdev(0, name, NET_NAME_UNKNOWN, reg_vif_setup);
+ if (!dev)
return NULL;
dev_net_set(dev, net);
@@ -747,100 +681,123 @@ static struct net_device *ip6mr_reg_vif(struct net *net, struct mr6_table *mrt)
free_netdev(dev);
return NULL;
}
- dev->iflink = 0;
- if (dev_open(dev))
+ if (dev_open(dev, NULL))
goto failure;
dev_hold(dev);
return dev;
failure:
- /* allow the register to be completed before unregistering. */
- rtnl_unlock();
- rtnl_lock();
-
unregister_netdevice(dev);
return NULL;
}
#endif
-/*
- * Delete a VIF entry
- */
+static int call_ip6mr_vif_entry_notifiers(struct net *net,
+ enum fib_event_type event_type,
+ struct vif_device *vif,
+ struct net_device *vif_dev,
+ mifi_t vif_index, u32 tb_id)
+{
+ return mr_call_vif_notifiers(net, RTNL_FAMILY_IP6MR, event_type,
+ vif, vif_dev, vif_index, tb_id,
+ &net->ipv6.ipmr_seq);
+}
+
+static int call_ip6mr_mfc_entry_notifiers(struct net *net,
+ enum fib_event_type event_type,
+ struct mfc6_cache *mfc, u32 tb_id)
+{
+ return mr_call_mfc_notifiers(net, RTNL_FAMILY_IP6MR, event_type,
+ &mfc->_c, tb_id, &net->ipv6.ipmr_seq);
+}
-static int mif6_delete(struct mr6_table *mrt, int vifi, struct list_head *head)
+/* Delete a VIF entry */
+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;
- v->dev = NULL;
-
- if (!dev) {
- write_unlock_bh(&mrt_lock);
+ dev = rtnl_dereference(v->dev);
+ if (!dev)
return -EADDRNOTAVAIL;
- }
+
+ call_ip6mr_vif_entry_notifiers(read_pnet(&mrt->net),
+ FIB_EVENT_VIF_DEL, v, dev,
+ vifi, mrt->id);
+ spin_lock(&mrt_lock);
+ RCU_INIT_POINTER(v->dev, NULL);
#ifdef CONFIG_IPV6_PIMSM_V2
- if (vifi == mrt->mroute_reg_vif_num)
- mrt->mroute_reg_vif_num = -1;
+ if (vifi == mrt->mroute_reg_vif_num) {
+ /* Pairs with READ_ONCE() in ip6mr_cache_report() and reg_vif_xmit() */
+ WRITE_ONCE(mrt->mroute_reg_vif_num, -1);
+ }
#endif
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;
+ WRITE_ONCE(mrt->maxvif, tmp + 1);
}
- write_unlock_bh(&mrt_lock);
+ spin_unlock(&mrt_lock);
dev_set_allmulti(dev, -1);
in6_dev = __in6_dev_get(dev);
if (in6_dev) {
- in6_dev->cnf.mc_forwarding--;
- inet6_netconf_notify_devconf(dev_net(dev),
+ atomic_dec(&in6_dev->cnf.mc_forwarding);
+ inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
NETCONFA_MC_FORWARDING,
dev->ifindex, &in6_dev->cnf);
}
- if (v->flags & MIFF_REGISTER)
+ if ((v->flags & MIFF_REGISTER) && !notify)
unregister_netdevice_queue(dev, head);
- dev_put(dev);
+ netdev_put(dev, &v->dev_tracker);
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 = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr));
+ struct nlmsghdr *nlh = skb_pull(skb,
+ sizeof(struct ipv6hdr));
nlh->nlmsg_type = NLMSG_ERROR;
nlh->nlmsg_len = nlmsg_msg_size(sizeof(struct nlmsgerr));
skb_trim(skb, nlh->nlmsg_len);
@@ -856,13 +813,13 @@ 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;
@@ -872,32 +829,33 @@ 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(unsigned long arg)
+static void ipmr_expire_process(struct timer_list *t)
{
- struct mr6_table *mrt = (struct mr6_table *)arg;
+ struct mr_table *mrt = timer_container_of(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);
}
-/* Fill oifs list. It is called under write locked mrt_lock. */
+/* Fill oifs list. It is called under 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;
@@ -907,7 +865,7 @@ 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)
@@ -916,19 +874,20 @@ static void ip6mr_update_thresholds(struct mr6_table *mrt, struct mfc6_cache *ca
cache->mfc_un.res.maxvif = vifi + 1;
}
}
+ WRITE_ONCE(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) {
@@ -967,119 +926,95 @@ static int mif6_add(struct net *net, struct mr6_table *mrt,
in6_dev = __in6_dev_get(dev);
if (in6_dev) {
- in6_dev->cnf.mc_forwarding++;
- inet6_netconf_notify_devconf(dev_net(dev),
+ atomic_inc(&in6_dev->cnf.mc_forwarding);
+ inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
NETCONFA_MC_FORWARDING,
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->iflink;
+ /* 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);
- v->dev = dev;
+ spin_lock(&mrt_lock);
+ rcu_assign_pointer(v->dev, dev);
+ netdev_tracker_alloc(dev, &v->dev_tracker, GFP_ATOMIC);
#ifdef CONFIG_IPV6_PIMSM_V2
if (v->flags & MIFF_REGISTER)
- mrt->mroute_reg_vif_num = vifi;
+ WRITE_ONCE(mrt->mroute_reg_vif_num, vifi);
#endif
if (vifi + 1 > mrt->maxvif)
- mrt->maxvif = vifi + 1;
- write_unlock_bh(&mrt_lock);
+ WRITE_ONCE(mrt->maxvif, vifi + 1);
+ spin_unlock(&mrt_lock);
+ call_ip6mr_vif_entry_notifiers(net, FIB_EVENT_VIF_ADD,
+ v, dev, vifi, mrt->id);
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);
+}
+
+/* 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,
+ };
-skip:
- return ip6mr_cache_find_any_parent(mrt, mifi);
+ 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 == NULL)
+ if (!c)
return NULL;
- 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;
+ c->_c.free = ip6mr_cache_free_rcu;
+ refcount_set(&c->_c.mfc_un.res.refcount, 1);
return c;
}
static struct mfc6_cache *ip6mr_cache_alloc_unres(void)
{
struct mfc6_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC);
- if (c == NULL)
+ 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;
}
@@ -1087,7 +1022,7 @@ 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;
@@ -1096,11 +1031,13 @@ 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 = (struct nlmsghdr *)skb_pull(skb, sizeof(struct ipv6hdr));
+ 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;
@@ -1109,27 +1046,30 @@ static void ip6mr_cache_resolve(struct net *net, struct mr6_table *mrt,
((struct nlmsgerr *)nlmsg_data(nlh))->error = -EMSGSIZE;
}
rtnl_unicast(skb, net, NETLINK_CB(skb).portid);
- } else
- ip6_mr_forward(net, mrt, skb, c);
+ } else {
+ rcu_read_lock();
+ ip6_mr_forward(net, mrt, skb->dev, skb, c);
+ rcu_read_unlock();
+ }
}
}
/*
- * Bounce a cache query up to pim6sd. We could use netlink for this but pim6sd
- * expects the following bizarre scheme.
+ * Bounce a cache query up to pim6sd and netlink.
*
- * Called under mrt_lock.
+ * Called under rcu_read_lock()
*/
-static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
+static int ip6mr_cache_report(const 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;
#ifdef CONFIG_IPV6_PIMSM_V2
- if (assert == MRT6MSG_WHOLEPKT)
+ if (assert == MRT6MSG_WHOLEPKT || assert == MRT6MSG_WRMIFWHOLE)
skb = skb_realloc_headroom(pkt, -skb_network_offset(pkt)
+sizeof(*msg));
else
@@ -1145,20 +1085,23 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
skb->ip_summed = CHECKSUM_UNNECESSARY;
#ifdef CONFIG_IPV6_PIMSM_V2
- if (assert == MRT6MSG_WHOLEPKT) {
+ if (assert == MRT6MSG_WHOLEPKT || assert == MRT6MSG_WRMIFWHOLE) {
/* Ugly, but we have no choice with this interface.
Duplicate old header, fix length etc.
And all this only to mangle msg->im6_msgtype and
to set msg->im6_mbz to "mbz" :-)
*/
- skb_push(skb, -skb_network_offset(pkt));
+ __skb_pull(skb, skb_network_offset(pkt));
skb_push(skb, sizeof(*msg));
skb_reset_transport_header(skb);
msg = (struct mrt6msg *)skb_transport_header(skb);
msg->im6_mbz = 0;
- msg->im6_msgtype = MRT6MSG_WHOLEPKT;
- msg->im6_mif = mrt->mroute_reg_vif_num;
+ msg->im6_msgtype = assert;
+ if (assert == MRT6MSG_WRMIFWHOLE)
+ msg->im6_mif = mifi;
+ else
+ msg->im6_mif = READ_ONCE(mrt->mroute_reg_vif_num);
msg->im6_pad = 0;
msg->im6_src = ipv6_hdr(pkt)->saddr;
msg->im6_dst = ipv6_hdr(pkt)->daddr;
@@ -1193,15 +1136,17 @@ static int ip6mr_cache_report(struct mr6_table *mrt, struct sk_buff *pkt,
skb->ip_summed = CHECKSUM_UNNECESSARY;
}
- if (mrt->mroute6_sk == NULL) {
+ mroute6_sk = rcu_dereference(mrt->mroute_sk);
+ if (!mroute6_sk) {
kfree_skb(skb);
return -EINVAL;
}
- /*
- * Deliver to user space multicast routing algorithms
- */
- ret = sock_queue_rcv_skb(mrt->mroute6_sk, skb);
+ mrt6msg_netlink_event(mrt, skb);
+
+ /* Deliver to user space multicast routing algorithms */
+ ret = sock_queue_rcv_skb(mroute6_sk, skb);
+
if (ret < 0) {
net_warn_ratelimited("mroute6: pending queue full, dropping entries\n");
kfree_skb(skb);
@@ -1210,19 +1155,16 @@ 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 net_device *dev)
{
+ 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;
@@ -1235,18 +1177,16 @@ ip6mr_cache_unresolved(struct mr6_table *mrt, mifi_t mifi, struct sk_buff *skb)
* Create a new entry if allowable
*/
- if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 ||
- (c = ip6mr_cache_alloc_unres()) == NULL) {
+ c = ip6mr_cache_alloc_unres();
+ if (!c) {
spin_unlock_bh(&mfc_unres_lock);
kfree_skb(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;
@@ -1266,20 +1206,22 @@ 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);
+ if (dev) {
+ skb->dev = dev;
+ skb->skb_iif = dev->ifindex;
+ }
+ skb_queue_tail(&c->_c.mfc_un.unres.unresolved, skb);
err = 0;
}
@@ -1291,29 +1233,26 @@ 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;
+ call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
+ FIB_EVENT_ENTRY_DEL, c, mrt->id);
+ mr6_netlink_event(mrt, c, RTM_DELROUTE);
+ mr_cache_put(&c->_c);
+ return 0;
}
static int ip6mr_device_event(struct notifier_block *this,
@@ -1321,47 +1260,88 @@ 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;
- LIST_HEAD(list);
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, &list);
+ if (rcu_access_pointer(v->dev) == dev)
+ mif6_delete(mrt, ct, 1, NULL);
}
}
- unregister_netdevice_many(&list);
return NOTIFY_DONE;
}
+static unsigned int ip6mr_seq_read(const struct net *net)
+{
+ return READ_ONCE(net->ipv6.ipmr_seq) + ip6mr_rules_seq_read(net);
+}
+
+static int ip6mr_dump(struct net *net, struct notifier_block *nb,
+ struct netlink_ext_ack *extack)
+{
+ return mr_dump(net, nb, RTNL_FAMILY_IP6MR, ip6mr_rules_dump,
+ ip6mr_mr_table_iter, extack);
+}
+
static struct notifier_block ip6_mr_notifier = {
.notifier_call = ip6mr_device_event
};
-/*
- * Setup for IP multicast routing
- */
+static const struct fib_notifier_ops ip6mr_notifier_ops_template = {
+ .family = RTNL_FAMILY_IP6MR,
+ .fib_seq_read = ip6mr_seq_read,
+ .fib_dump = ip6mr_dump,
+ .owner = THIS_MODULE,
+};
+
+static int __net_init ip6mr_notifier_init(struct net *net)
+{
+ struct fib_notifier_ops *ops;
+
+ net->ipv6.ipmr_seq = 0;
+
+ ops = fib_notifier_ops_register(&ip6mr_notifier_ops_template, net);
+ if (IS_ERR(ops))
+ return PTR_ERR(ops);
+
+ net->ipv6.ip6mr_notifier_ops = ops;
+
+ return 0;
+}
+
+static void __net_exit ip6mr_notifier_exit(struct net *net)
+{
+ fib_notifier_ops_unregister(net->ipv6.ip6mr_notifier_ops);
+ net->ipv6.ip6mr_notifier_ops = NULL;
+}
+/* Setup for IP multicast routing */
static int __net_init ip6mr_net_init(struct net *net)
{
int err;
+ err = ip6mr_notifier_init(net);
+ if (err)
+ return err;
+
err = ip6mr_rules_init(net);
if (err < 0)
- goto fail;
+ goto ip6mr_rules_fail;
#ifdef CONFIG_PROC_FS
err = -ENOMEM;
- if (!proc_create("ip6_mr_vif", 0, net->proc_net, &ip6mr_vif_fops))
+ if (!proc_create_net("ip6_mr_vif", 0, net->proc_net, &ip6mr_vif_seq_ops,
+ sizeof(struct mr_vif_iter)))
goto proc_vif_fail;
- if (!proc_create("ip6_mr_cache", 0, net->proc_net, &ip6mr_mfc_fops))
+ if (!proc_create_net("ip6_mr_cache", 0, net->proc_net, &ipmr_mfc_seq_ops,
+ sizeof(struct mr_mfc_iter)))
goto proc_cache_fail;
#endif
@@ -1371,9 +1351,12 @@ static int __net_init ip6mr_net_init(struct net *net)
proc_cache_fail:
remove_proc_entry("ip6_mr_vif", net->proc_net);
proc_vif_fail:
+ rtnl_lock();
ip6mr_rules_exit(net);
+ rtnl_unlock();
#endif
-fail:
+ip6mr_rules_fail:
+ ip6mr_notifier_exit(net);
return err;
}
@@ -1383,22 +1366,36 @@ static void __net_exit ip6mr_net_exit(struct net *net)
remove_proc_entry("ip6_mr_cache", net->proc_net);
remove_proc_entry("ip6_mr_vif", net->proc_net);
#endif
- ip6mr_rules_exit(net);
+ ip6mr_notifier_exit(net);
+}
+
+static void __net_exit ip6mr_net_exit_batch(struct list_head *net_list)
+{
+ struct net *net;
+
+ rtnl_lock();
+ list_for_each_entry(net, net_list, exit_list)
+ ip6mr_rules_exit(net);
+ rtnl_unlock();
}
static struct pernet_operations ip6mr_net_ops = {
.init = ip6mr_net_init,
.exit = ip6mr_net_exit,
+ .exit_batch = ip6mr_net_exit_batch,
+};
+
+static const struct rtnl_msg_handler ip6mr_rtnl_msg_handlers[] __initconst_or_module = {
+ {.owner = THIS_MODULE, .protocol = RTNL_FAMILY_IP6MR,
+ .msgtype = RTM_GETROUTE,
+ .doit = ip6mr_rtm_getroute, .dumpit = ip6mr_rtm_dumproute},
};
int __init ip6_mr_init(void)
{
int err;
- mrt_cachep = kmem_cache_create("ip6_mrt_cache",
- sizeof(struct mfc6_cache),
- 0, SLAB_HWCACHE_ALIGN,
- NULL);
+ mrt_cachep = KMEM_CACHE(mfc6_cache, SLAB_HWCACHE_ALIGN);
if (!mrt_cachep)
return -ENOMEM;
@@ -1416,10 +1413,12 @@ int __init ip6_mr_init(void)
goto add_proto_fail;
}
#endif
- rtnl_register(RTNL_FAMILY_IP6MR, RTM_GETROUTE, NULL,
- ip6mr_rtm_dumproute, NULL);
- return 0;
+ err = rtnl_register_many(ip6mr_rtnl_msg_handlers);
+ if (!err)
+ return 0;
+
#ifdef CONFIG_IPV6_PIMSM_V2
+ inet6_del_protocol(&pim6_protocol, IPPROTO_PIM);
add_proto_fail:
unregister_netdevice_notifier(&ip6_mr_notifier);
#endif
@@ -1430,21 +1429,25 @@ reg_pernet_fail:
return err;
}
-void ip6_mr_cleanup(void)
+void __init ip6_mr_cleanup(void)
{
+ rtnl_unregister_many(ip6mr_rtnl_msg_handlers);
+#ifdef CONFIG_IPV6_PIMSM_V2
+ inet6_del_protocol(&pim6_protocol, IPPROTO_PIM);
+#endif
unregister_netdevice_notifier(&ip6_mr_notifier);
unregister_pernet_subsys(&ip6mr_net_ops);
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;
@@ -1453,28 +1456,22 @@ 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) {
- write_lock_bh(&mrt_lock);
- c->mf6c_parent = mfc->mf6cc_parent;
- ip6mr_update_thresholds(mrt, c, ttls);
+ /* 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) {
+ spin_lock(&mrt_lock);
+ c->_c.mfc_parent = mfc->mf6cc_parent;
+ ip6mr_update_thresholds(mrt, &c->_c, ttls);
if (!mrtsock)
- c->mfc_flags |= MFC_STATIC;
- write_unlock_bh(&mrt_lock);
+ c->_c.mfc_flags |= MFC_STATIC;
+ spin_unlock(&mrt_lock);
+ call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_REPLACE,
+ c, mrt->id);
mr6_netlink_event(mrt, c, RTM_NEWROUTE);
return 0;
}
@@ -1484,43 +1481,50 @@ static int ip6mr_mfc_add(struct net *net, struct mr6_table *mrt,
return -EINVAL;
c = ip6mr_cache_alloc();
- if (c == NULL)
+ if (!c)
return -ENOMEM;
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))
- del_timer(&mrt->ipmr_expire_timer);
+ if (list_empty(&mrt->mfc_unres_queue))
+ timer_delete(&mrt->ipmr_expire_timer);
spin_unlock_bh(&mfc_unres_lock);
if (found) {
ip6mr_cache_resolve(net, mrt, uc, c);
ip6mr_cache_free(uc);
}
+ call_ip6mr_mfc_entry_notifiers(net, FIB_EVENT_ENTRY_ADD,
+ c, mrt->id);
mr6_netlink_event(mrt, c, RTM_NEWROUTE);
return 0;
}
@@ -1529,66 +1533,75 @@ 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)
+static void mroute_clean_tables(struct mr_table *mrt, int flags)
{
- int i;
+ struct mr_mfc *c, *tmp;
LIST_HEAD(list);
- struct mfc6_cache *c, *next;
+ int i;
- /*
- * Shut down all active vif entries
- */
- for (i = 0; i < mrt->maxvif; i++) {
- if (!(mrt->vif6_table[i].flags & VIFF_STATIC))
- mif6_delete(mrt, i, &list);
+ /* Shut down all active vif entries */
+ if (flags & (MRT6_FLUSH_MIFS | MRT6_FLUSH_MIFS_STATIC)) {
+ for (i = 0; i < mrt->maxvif; i++) {
+ if (((mrt->vif_table[i].flags & VIFF_STATIC) &&
+ !(flags & MRT6_FLUSH_MIFS_STATIC)) ||
+ (!(mrt->vif_table[i].flags & VIFF_STATIC) && !(flags & MRT6_FLUSH_MIFS)))
+ continue;
+ mif6_delete(mrt, i, 0, &list);
+ }
+ unregister_netdevice_many(&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 (c->mfc_flags & MFC_STATIC)
+ /* Wipe the cache */
+ if (flags & (MRT6_FLUSH_MFC | MRT6_FLUSH_MFC_STATIC)) {
+ list_for_each_entry_safe(c, tmp, &mrt->mfc_cache_list, list) {
+ if (((c->mfc_flags & MFC_STATIC) && !(flags & MRT6_FLUSH_MFC_STATIC)) ||
+ (!(c->mfc_flags & MFC_STATIC) && !(flags & MRT6_FLUSH_MFC)))
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);
+ rhltable_remove(&mrt->mfc_hash, &c->mnode, ip6mr_rht_params);
+ list_del_rcu(&c->list);
+ call_ip6mr_mfc_entry_notifiers(read_pnet(&mrt->net),
+ FIB_EVENT_ENTRY_DEL,
+ (struct mfc6_cache *)c, mrt->id);
+ mr6_netlink_event(mrt, (struct mfc6_cache *)c, RTM_DELROUTE);
+ mr_cache_put(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_del(&c->list);
- mr6_netlink_event(mrt, c, RTM_DELROUTE);
- ip6mr_destroy_unres(mrt, c);
+ if (flags & MRT6_FLUSH_MFC) {
+ 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);
+ mr6_netlink_event(mrt, (struct mfc6_cache *)c,
+ RTM_DELROUTE);
+ ip6mr_destroy_unres(mrt, (struct mfc6_cache *)c);
+ }
+ spin_unlock_bh(&mfc_unres_lock);
}
- 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++;
- inet6_netconf_notify_devconf(net, NETCONFA_MC_FORWARDING,
- NETCONFA_IFINDEX_ALL,
- net->ipv6.devconf_all);
- }
- else
+ spin_lock(&mrt_lock);
+ if (rtnl_dereference(mrt->mroute_sk)) {
err = -EADDRINUSE;
- write_unlock_bh(&mrt_lock);
+ } else {
+ rcu_assign_pointer(mrt->mroute_sk, sk);
+ sock_set_flag(sk, SOCK_RCU_FREE);
+ atomic_inc(&net->ipv6.devconf_all->mc_forwarding);
+ }
+ spin_unlock(&mrt_lock);
+ if (!err)
+ inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+ NETCONFA_MC_FORWARDING,
+ NETCONFA_IFINDEX_ALL,
+ net->ipv6.devconf_all);
rtnl_unlock();
return err;
@@ -1596,23 +1609,36 @@ static int ip6mr_sk_init(struct mr6_table *mrt, struct sock *sk)
int ip6mr_sk_done(struct sock *sk)
{
- int err = -EACCES;
struct net *net = sock_net(sk);
- struct mr6_table *mrt;
+ struct ipv6_devconf *devconf;
+ struct mr_table *mrt;
+ int err = -EACCES;
+
+ if (sk->sk_type != SOCK_RAW ||
+ inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
+ return err;
+
+ devconf = net->ipv6.devconf_all;
+ if (!devconf || !atomic_read(&devconf->mc_forwarding))
+ return err;
rtnl_lock();
ip6mr_for_each_table(mrt, net) {
- if (sk == mrt->mroute6_sk) {
- write_lock_bh(&mrt_lock);
- mrt->mroute6_sk = NULL;
- net->ipv6.devconf_all->mc_forwarding--;
- inet6_netconf_notify_devconf(net,
+ if (sk == rtnl_dereference(mrt->mroute_sk)) {
+ spin_lock(&mrt_lock);
+ RCU_INIT_POINTER(mrt->mroute_sk, NULL);
+ /* Note that mroute_sk had SOCK_RCU_FREE set,
+ * so the RCU grace period before sk freeing
+ * is guaranteed by sk_destruct()
+ */
+ atomic_dec(&devconf->mc_forwarding);
+ spin_unlock(&mrt_lock);
+ inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
NETCONFA_MC_FORWARDING,
NETCONFA_IFINDEX_ALL,
net->ipv6.devconf_all);
- write_unlock_bh(&mrt_lock);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, MRT6_FLUSH_MIFS | MRT6_FLUSH_MFC);
err = 0;
break;
}
@@ -1622,11 +1648,11 @@ int ip6mr_sk_done(struct sock *sk)
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,
+ .flowi6_iif = skb->skb_iif ? : LOOPBACK_IFINDEX,
.flowi6_oif = skb->dev->ifindex,
.flowi6_mark = skb->mark,
};
@@ -1634,8 +1660,9 @@ 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
@@ -1644,29 +1671,32 @@ struct sock *mroute6_socket(struct net *net, struct sk_buff *skb)
* MOSPF/PIM router set up we can clean this up.
*/
-int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsigned int optlen)
+int ip6_mroute_setsockopt(struct sock *sk, int optname, sockptr_t optval,
+ unsigned int optlen)
{
int ret, parent = 0;
struct mif6ctl vif;
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)
+ return -EOPNOTSUPP;
mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
- if (mrt == NULL)
+ if (!mrt)
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;
}
switch (optname) {
case MRT6_INIT:
- if (sk->sk_type != SOCK_RAW ||
- inet_sk(sk)->inet_num != IPPROTO_ICMPV6)
- return -EOPNOTSUPP;
if (optlen < sizeof(int))
return -EINVAL;
@@ -1678,22 +1708,23 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
case MRT6_ADD_MIF:
if (optlen < sizeof(vif))
return -EINVAL;
- if (copy_from_user(&vif, optval, sizeof(vif)))
+ if (copy_from_sockptr(&vif, optval, sizeof(vif)))
return -EFAULT;
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;
case MRT6_DEL_MIF:
if (optlen < sizeof(mifi_t))
return -EINVAL;
- if (copy_from_user(&mifi, optval, sizeof(mifi_t)))
+ if (copy_from_sockptr(&mifi, optval, sizeof(mifi_t)))
return -EFAULT;
rtnl_lock();
- ret = mif6_delete(mrt, mifi, NULL);
+ ret = mif6_delete(mrt, mifi, 0, NULL);
rtnl_unlock();
return ret;
@@ -1704,11 +1735,12 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
case MRT6_ADD_MFC:
case MRT6_DEL_MFC:
parent = -1;
+ fallthrough;
case MRT6_ADD_MFC_PROXY:
case MRT6_DEL_MFC_PROXY:
if (optlen < sizeof(mfc))
return -EINVAL;
- if (copy_from_user(&mfc, optval, sizeof(mfc)))
+ if (copy_from_sockptr(&mfc, optval, sizeof(mfc)))
return -EFAULT;
if (parent == 0)
parent = mfc.mf6cc_parent;
@@ -1717,10 +1749,26 @@ 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;
+ case MRT6_FLUSH:
+ {
+ int flags;
+
+ if (optlen != sizeof(flags))
+ return -EINVAL;
+ if (copy_from_sockptr(&flags, optval, sizeof(flags)))
+ return -EFAULT;
+ rtnl_lock();
+ mroute_clean_tables(mrt, flags);
+ rtnl_unlock();
+ return 0;
+ }
+
/*
* Control PIM assert (to activate pim will activate assert)
*/
@@ -1730,7 +1778,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
if (optlen != sizeof(v))
return -EINVAL;
- if (get_user(v, (int __user *)optval))
+ if (copy_from_sockptr(&v, optval, sizeof(v)))
return -EFAULT;
mrt->mroute_do_assert = v;
return 0;
@@ -1739,18 +1787,22 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
#ifdef CONFIG_IPV6_PIMSM_V2
case MRT6_PIM:
{
+ bool do_wrmifwhole;
int v;
if (optlen != sizeof(v))
return -EINVAL;
- if (get_user(v, (int __user *)optval))
+ if (copy_from_sockptr(&v, optval, sizeof(v)))
return -EFAULT;
+
+ do_wrmifwhole = (v == MRT6MSG_WRMIFWHOLE);
v = !!v;
rtnl_lock();
ret = 0;
if (v != mrt->mroute_do_pim) {
mrt->mroute_do_pim = v;
mrt->mroute_do_assert = v;
+ mrt->mroute_do_wrvifwhole = do_wrmifwhole;
}
rtnl_unlock();
return ret;
@@ -1764,19 +1816,21 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
if (optlen != sizeof(u32))
return -EINVAL;
- if (get_user(v, (u32 __user *)optval))
+ if (copy_from_sockptr(&v, optval, sizeof(v)))
return -EFAULT;
/* "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();
ret = 0;
- if (!ip6mr_new_table(net, v))
- ret = -ENOMEM;
- raw6_sk(sk)->ip6mr_table = v;
+ mrt = ip6mr_new_table(net, v);
+ if (IS_ERR(mrt))
+ ret = PTR_ERR(mrt);
+ else
+ raw6_sk(sk)->ip6mr_table = v;
rtnl_unlock();
return ret;
}
@@ -1794,16 +1848,20 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns
* Getsock opt support for the multicast routing system.
*/
-int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
- int __user *optlen)
+int ip6_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval,
+ sockptr_t optlen)
{
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)
+ return -EOPNOTSUPP;
mrt = ip6mr_get_table(net, raw6_sk(sk)->ip6mr_table ? : RT6_TABLE_DFLT);
- if (mrt == NULL)
+ if (!mrt)
return -ENOENT;
switch (optname) {
@@ -1822,16 +1880,16 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
return -ENOPROTOOPT;
}
- if (get_user(olr, optlen))
+ if (copy_from_sockptr(&olr, optlen, sizeof(int)))
return -EFAULT;
olr = min_t(int, olr, sizeof(int));
if (olr < 0)
return -EINVAL;
- if (put_user(olr, optlen))
+ if (copy_to_sockptr(optlen, &olr, sizeof(int)))
return -EFAULT;
- if (copy_to_user(optval, &val, olr))
+ if (copy_to_sockptr(optval, &val, olr))
return -EFAULT;
return 0;
}
@@ -1839,58 +1897,51 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, char __user *optval,
/*
* The IP multicast ioctl support routines.
*/
-
-int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg)
+int ip6mr_ioctl(struct sock *sk, int cmd, void *arg)
{
- struct sioc_sg_req6 sr;
- struct sioc_mif_req6 vr;
- struct mif_device *vif;
+ struct sioc_sg_req6 *sr;
+ struct sioc_mif_req6 *vr;
+ 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 == NULL)
+ if (!mrt)
return -ENOENT;
switch (cmd) {
case SIOCGETMIFCNT_IN6:
- if (copy_from_user(&vr, arg, sizeof(vr)))
- return -EFAULT;
- if (vr.mifi >= mrt->maxvif)
+ vr = (struct sioc_mif_req6 *)arg;
+ if (vr->mifi >= mrt->maxvif)
return -EINVAL;
- read_lock(&mrt_lock);
- vif = &mrt->vif6_table[vr.mifi];
- if (MIF_EXISTS(mrt, vr.mifi)) {
- vr.icount = vif->pkt_in;
- vr.ocount = vif->pkt_out;
- vr.ibytes = vif->bytes_in;
- vr.obytes = vif->bytes_out;
- read_unlock(&mrt_lock);
-
- if (copy_to_user(arg, &vr, sizeof(vr)))
- return -EFAULT;
+ vr->mifi = array_index_nospec(vr->mifi, mrt->maxvif);
+ rcu_read_lock();
+ vif = &mrt->vif_table[vr->mifi];
+ if (VIF_EXISTS(mrt, vr->mifi)) {
+ vr->icount = READ_ONCE(vif->pkt_in);
+ vr->ocount = READ_ONCE(vif->pkt_out);
+ vr->ibytes = READ_ONCE(vif->bytes_in);
+ vr->obytes = READ_ONCE(vif->bytes_out);
+ rcu_read_unlock();
return 0;
}
- read_unlock(&mrt_lock);
+ rcu_read_unlock();
return -EADDRNOTAVAIL;
case SIOCGETSGCNT_IN6:
- if (copy_from_user(&sr, arg, sizeof(sr)))
- return -EFAULT;
+ sr = (struct sioc_sg_req6 *)arg;
- read_lock(&mrt_lock);
- c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr);
+ 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);
-
- if (copy_to_user(arg, &sr, sizeof(sr)))
- return -EFAULT;
+ sr->pktcnt = atomic_long_read(&c->_c.mfc_un.res.pkt);
+ sr->bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes);
+ sr->wrong_if = atomic_long_read(&c->_c.mfc_un.res.wrong_if);
+ rcu_read_unlock();
return 0;
}
- read_unlock(&mrt_lock);
+ rcu_read_unlock();
return -EADDRNOTAVAIL;
default:
return -ENOIOCTLCMD;
@@ -1918,13 +1969,13 @@ 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 == NULL)
+ if (!mrt)
return -ENOENT;
switch (cmd) {
@@ -1933,38 +1984,39 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
return -EFAULT;
if (vr.mifi >= mrt->maxvif)
return -EINVAL;
- read_lock(&mrt_lock);
- vif = &mrt->vif6_table[vr.mifi];
- if (MIF_EXISTS(mrt, vr.mifi)) {
- vr.icount = vif->pkt_in;
- vr.ocount = vif->pkt_out;
- vr.ibytes = vif->bytes_in;
- vr.obytes = vif->bytes_out;
- read_unlock(&mrt_lock);
+ vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif);
+ rcu_read_lock();
+ vif = &mrt->vif_table[vr.mifi];
+ if (VIF_EXISTS(mrt, vr.mifi)) {
+ vr.icount = READ_ONCE(vif->pkt_in);
+ vr.ocount = READ_ONCE(vif->pkt_out);
+ vr.ibytes = READ_ONCE(vif->bytes_in);
+ vr.obytes = READ_ONCE(vif->bytes_out);
+ rcu_read_unlock();
if (copy_to_user(arg, &vr, sizeof(vr)))
return -EFAULT;
return 0;
}
- read_unlock(&mrt_lock);
+ rcu_read_unlock();
return -EADDRNOTAVAIL;
case SIOCGETSGCNT_IN6:
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 = atomic_long_read(&c->_c.mfc_un.res.pkt);
+ sr.bytecnt = atomic_long_read(&c->_c.mfc_un.res.bytes);
+ sr.wrong_if = atomic_long_read(&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;
@@ -1972,39 +2024,38 @@ int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
}
#endif
-static inline int ip6mr_forward2_finish(struct sk_buff *skb)
+static inline int ip6mr_forward2_finish(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- IP6_INC_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)),
- IPSTATS_MIB_OUTFORWDATAGRAMS);
- IP6_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), ip6_dst_idev(skb_dst(skb)),
- IPSTATS_MIB_OUTOCTETS, skb->len);
- return dst_output(skb);
+ IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
+ IPSTATS_MIB_OUTFORWDATAGRAMS);
+ return dst_output(net, sk, skb);
}
/*
* Processing handlers for ip6mr_forward
*/
-static int ip6mr_forward2(struct net *net, struct mr6_table *mrt,
- struct sk_buff *skb, struct mfc6_cache *c, int vifi)
+static int ip6mr_prepare_xmit(struct net *net, struct mr_table *mrt,
+ struct sk_buff *skb, int vifi)
{
+ struct vif_device *vif = &mrt->vif_table[vifi];
+ struct net_device *vif_dev;
struct ipv6hdr *ipv6h;
- struct mif_device *vif = &mrt->vif6_table[vifi];
- struct net_device *dev;
struct dst_entry *dst;
struct flowi6 fl6;
- if (vif->dev == NULL)
- goto out_free;
+ vif_dev = vif_dev_read(vif);
+ if (!vif_dev)
+ return -1;
#ifdef CONFIG_IPV6_PIMSM_V2
if (vif->flags & MIFF_REGISTER) {
- vif->pkt_out++;
- vif->bytes_out += skb->len;
- vif->dev->stats.tx_bytes += skb->len;
- vif->dev->stats.tx_packets++;
+ WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1);
+ WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len);
+ DEV_STATS_ADD(vif_dev, tx_bytes, skb->len);
+ DEV_STATS_INC(vif_dev, tx_packets);
ip6mr_cache_report(mrt, skb, vifi, MRT6MSG_WHOLEPKT);
- goto out_free;
+ return -1;
}
#endif
@@ -2018,7 +2069,7 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt,
dst = ip6_route_output(net, NULL, &fl6);
if (dst->error) {
dst_release(dst);
- goto out_free;
+ return -1;
}
skb_dst_drop(skb);
@@ -2035,68 +2086,96 @@ static int ip6mr_forward2(struct net *net, struct mr6_table *mrt,
* not mrouter) cannot join to more than one interface - it will
* result in receiving multiple packets.
*/
- dev = vif->dev;
- skb->dev = dev;
- vif->pkt_out++;
- vif->bytes_out += skb->len;
+ skb->dev = vif_dev;
+ WRITE_ONCE(vif->pkt_out, vif->pkt_out + 1);
+ WRITE_ONCE(vif->bytes_out, vif->bytes_out + skb->len);
/* We are about to write */
/* XXX: extension headers? */
- if (skb_cow(skb, sizeof(*ipv6h) + LL_RESERVED_SPACE(dev)))
- goto out_free;
+ if (skb_cow(skb, sizeof(*ipv6h) + LL_RESERVED_SPACE(vif_dev)))
+ return -1;
ipv6h = ipv6_hdr(skb);
ipv6h->hop_limit--;
+ return 0;
+}
+
+static void ip6mr_forward2(struct net *net, struct mr_table *mrt,
+ struct sk_buff *skb, int vifi)
+{
+ struct net_device *indev = skb->dev;
+
+ if (ip6mr_prepare_xmit(net, mrt, skb, vifi))
+ goto out_free;
IP6CB(skb)->flags |= IP6SKB_FORWARDED;
- return NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD, skb, skb->dev, dev,
- ip6mr_forward2_finish);
+ NF_HOOK(NFPROTO_IPV6, NF_INET_FORWARD,
+ net, NULL, skb, indev, skb->dev,
+ ip6mr_forward2_finish);
+ return;
+
+out_free:
+ kfree_skb(skb);
+}
+
+static void ip6mr_output2(struct net *net, struct mr_table *mrt,
+ struct sk_buff *skb, int vifi)
+{
+ if (ip6mr_prepare_xmit(net, mrt, skb, vifi))
+ goto out_free;
+
+ ip6_output(net, NULL, skb);
+ return;
out_free:
kfree_skb(skb);
- return 0;
}
-static int ip6mr_find_vif(struct mr6_table *mrt, struct net_device *dev)
+/* Called with rcu_read_lock() */
+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)
+ /* Pairs with WRITE_ONCE() in mif6_delete()/mif6_add() */
+ for (ct = READ_ONCE(mrt->maxvif) - 1; ct >= 0; ct--) {
+ if (rcu_access_pointer(mrt->vif_table[ct].dev) == dev)
break;
}
return ct;
}
-static int ip6_mr_forward(struct net *net, struct mr6_table *mrt,
- struct sk_buff *skb, struct mfc6_cache *cache)
+/* Called under rcu_read_lock() */
+static void ip6_mr_forward(struct net *net, struct mr_table *mrt,
+ struct net_device *dev, struct sk_buff *skb,
+ struct mfc6_cache *c)
{
int psend = -1;
int vif, ct;
- int true_vifi = ip6mr_find_vif(mrt, skb->dev);
+ int true_vifi = ip6mr_find_vif(mrt, dev);
- vif = cache->mf6c_parent;
- cache->mfc_un.res.pkt++;
- cache->mfc_un.res.bytes += skb->len;
+ vif = c->_c.mfc_parent;
+ atomic_long_inc(&c->_c.mfc_un.res.pkt);
+ atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes);
+ WRITE_ONCE(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 incomming
+ /* 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);
+ 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;
}
/*
* Wrong interface: drop packet and (maybe) send PIM assert.
*/
- if (mrt->vif6_table[vif].dev != skb->dev) {
- cache->mfc_un.res.wrong_if++;
+ if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev) {
+ atomic_long_inc(&c->_c.mfc_un.res.wrong_if);
if (true_vifi >= 0 && mrt->mroute_do_assert &&
/* pimsm uses asserts, when switching from RPT to SPT,
@@ -2105,60 +2184,116 @@ static int 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);
+ if (mrt->mroute_do_wrvifwhole)
+ ip6mr_cache_report(mrt, skb, true_vifi,
+ MRT6MSG_WRMIFWHOLE);
}
goto dont_forward;
}
forward:
- mrt->vif6_table[vif].pkt_in++;
- mrt->vif6_table[vif].bytes_in += skb->len;
+ WRITE_ONCE(mrt->vif_table[vif].pkt_in,
+ mrt->vif_table[vif].pkt_in + 1);
+ WRITE_ONCE(mrt->vif_table[vif].bytes_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, psend);
}
psend = ct;
}
}
last_forward:
if (psend != -1) {
- ip6mr_forward2(net, mrt, skb, cache, psend);
- return 0;
+ ip6mr_forward2(net, mrt, skb, psend);
+ return;
}
dont_forward:
kfree_skb(skb);
- return 0;
}
+/* Called under rcu_read_lock() */
+static void ip6_mr_output_finish(struct net *net, struct mr_table *mrt,
+ struct net_device *dev, struct sk_buff *skb,
+ struct mfc6_cache *c)
+{
+ int psend = -1;
+ int ct;
+
+ WARN_ON_ONCE(!rcu_read_lock_held());
+
+ atomic_long_inc(&c->_c.mfc_un.res.pkt);
+ atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes);
+ WRITE_ONCE(c->_c.mfc_un.res.lastuse, jiffies);
+
+ /* Forward the frame */
+ if (ipv6_addr_any(&c->mf6c_origin) &&
+ ipv6_addr_any(&c->mf6c_mcastgrp)) {
+ if (ipv6_hdr(skb)->hop_limit >
+ 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 = c->_c.mfc_parent;
+ goto last_forward;
+ }
+ goto dont_forward;
+ }
+ for (ct = c->_c.mfc_un.res.maxvif - 1;
+ ct >= c->_c.mfc_un.res.minvif; ct--) {
+ if (ipv6_hdr(skb)->hop_limit > c->_c.mfc_un.res.ttls[ct]) {
+ if (psend != -1) {
+ struct sk_buff *skb2;
+
+ skb2 = skb_clone(skb, GFP_ATOMIC);
+ if (skb2)
+ ip6mr_output2(net, mrt, skb2, psend);
+ }
+ psend = ct;
+ }
+ }
+last_forward:
+ if (psend != -1) {
+ ip6mr_output2(net, mrt, skb, psend);
+ return;
+ }
+
+dont_forward:
+ kfree_skb(skb);
+}
/*
* Multicast packets for forwarding arrive here
@@ -2166,26 +2301,37 @@ dont_forward:
int ip6_mr_input(struct sk_buff *skb)
{
+ struct net_device *dev = skb->dev;
+ struct net *net = dev_net_rcu(dev);
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_iif = dev->ifindex,
.flowi6_mark = skb->mark,
};
int err;
+ /* skb->dev passed in is the master dev for vrfs.
+ * Get the proper interface that does have a vif associated with it.
+ */
+ if (netif_is_l3_master(dev)) {
+ dev = dev_get_by_index_rcu(net, IPCB(skb)->iif);
+ if (!dev) {
+ kfree_skb(skb);
+ return -ENODEV;
+ }
+ }
+
err = ip6mr_fib_lookup(net, &fl6, &mrt);
if (err < 0) {
kfree_skb(skb);
return err;
}
- read_lock(&mrt_lock);
cache = ip6mr_cache_find(mrt,
&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr);
- if (cache == NULL) {
- int vif = ip6mr_find_vif(mrt, skb->dev);
+ if (!cache) {
+ int vif = ip6mr_find_vif(mrt, dev);
if (vif >= 0)
cache = ip6mr_cache_find_any(mrt,
@@ -2196,88 +2342,94 @@ int ip6_mr_input(struct sk_buff *skb)
/*
* No usable cache entry
*/
- if (cache == NULL) {
+ if (!cache) {
int vif;
- vif = ip6mr_find_vif(mrt, skb->dev);
+ vif = ip6mr_find_vif(mrt, dev);
if (vif >= 0) {
- int err = ip6mr_cache_unresolved(mrt, vif, skb);
- read_unlock(&mrt_lock);
+ int err = ip6mr_cache_unresolved(mrt, vif, skb, dev);
return err;
}
- read_unlock(&mrt_lock);
kfree_skb(skb);
return -ENODEV;
}
- ip6_mr_forward(net, mrt, skb, cache);
-
- read_unlock(&mrt_lock);
+ ip6_mr_forward(net, mrt, dev, skb, cache);
return 0;
}
-
-static int __ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
- struct mfc6_cache *c, struct rtmsg *rtm)
+int ip6_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb)
{
- int ct;
- struct rtnexthop *nhp;
- struct nlattr *mp_attr;
- struct rta_mfc_stats mfcs;
+ struct net_device *dev = skb_dst(skb)->dev;
+ struct flowi6 fl6 = (struct flowi6) {
+ .flowi6_iif = LOOPBACK_IFINDEX,
+ .flowi6_mark = skb->mark,
+ };
+ struct mfc6_cache *cache;
+ struct mr_table *mrt;
+ int err;
+ int vif;
- /* If cache is unresolved, don't try to parse IIF and OIF */
- if (c->mf6c_parent >= MAXMIFS)
- return -ENOENT;
+ guard(rcu)();
- 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 == NULL)
- return -EMSGSIZE;
+ if (IP6CB(skb)->flags & IP6SKB_FORWARDED)
+ goto ip6_output;
+ if (!(IP6CB(skb)->flags & IP6SKB_MCROUTE))
+ goto ip6_output;
- 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 == NULL) {
- nla_nest_cancel(skb, mp_attr);
- return -EMSGSIZE;
- }
+ err = ip6mr_fib_lookup(net, &fl6, &mrt);
+ if (err < 0) {
+ kfree_skb(skb);
+ return err;
+ }
- 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);
- }
+ cache = ip6mr_cache_find(mrt,
+ &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr);
+ if (!cache) {
+ vif = ip6mr_find_vif(mrt, dev);
+ if (vif >= 0)
+ cache = ip6mr_cache_find_any(mrt,
+ &ipv6_hdr(skb)->daddr,
+ vif);
}
- nla_nest_end(skb, mp_attr);
+ /* No usable cache entry */
+ if (!cache) {
+ vif = ip6mr_find_vif(mrt, dev);
+ if (vif >= 0)
+ return ip6mr_cache_unresolved(mrt, vif, skb, dev);
+ goto ip6_output;
+ }
- 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(skb, RTA_MFC_STATS, sizeof(mfcs), &mfcs) < 0)
- return -EMSGSIZE;
+ /* Wrong interface */
+ vif = cache->_c.mfc_parent;
+ if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev)
+ goto ip6_output;
- rtm->rtm_type = RTN_MULTICAST;
- return 1;
+ ip6_mr_output_finish(net, mrt, dev, skb, cache);
+ return 0;
+
+ip6_output:
+ return ip6_output(net, sk, skb);
}
-int ip6mr_get_route(struct net *net,
- struct sk_buff *skb, struct rtmsg *rtm, int nowait)
+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);
+ struct rt6_info *rt = dst_rt6_info(skb_dst(skb));
- mrt = ip6mr_get_table(net, RT6_TABLE_DFLT);
- if (mrt == NULL)
+ rcu_read_lock();
+ mrt = __ip6mr_get_table(net, RT6_TABLE_DFLT);
+ if (!mrt) {
+ rcu_read_unlock();
return -ENOENT;
+ }
- read_lock(&mrt_lock);
cache = ip6mr_cache_find(mrt, &rt->rt6i_src.addr, &rt->rt6i_dst.addr);
if (!cache && skb->dev) {
int vif = ip6mr_find_vif(mrt, skb->dev);
@@ -2293,24 +2445,20 @@ int ip6mr_get_route(struct net *net,
struct net_device *dev;
int vif;
- if (nowait) {
- read_unlock(&mrt_lock);
- return -EAGAIN;
- }
-
dev = skb->dev;
- if (dev == NULL || (vif = ip6mr_find_vif(mrt, dev)) < 0) {
- read_unlock(&mrt_lock);
+ if (!dev || (vif = ip6mr_find_vif(mrt, dev)) < 0) {
+ rcu_read_unlock();
return -ENODEV;
}
/* really correct? */
skb2 = alloc_skb(sizeof(struct ipv6hdr), GFP_ATOMIC);
if (!skb2) {
- read_unlock(&mrt_lock);
+ rcu_read_unlock();
return -ENOMEM;
}
+ NETLINK_CB(skb2).portid = portid;
skb_reset_transport_header(skb2);
skb_put(skb2, sizeof(struct ipv6hdr));
@@ -2328,29 +2476,27 @@ int ip6mr_get_route(struct net *net,
iph->saddr = rt->rt6i_src.addr;
iph->daddr = rt->rt6i_dst.addr;
- err = ip6mr_cache_unresolved(mrt, vif, skb2);
- read_unlock(&mrt_lock);
+ err = ip6mr_cache_unresolved(mrt, vif, skb2, dev);
+ rcu_read_unlock();
return err;
}
- if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY))
- cache->mfc_flags |= MFC_NOTIFY;
-
- err = __ip6mr_fill_mroute(mrt, skb, cache, rtm);
- read_unlock(&mrt_lock);
+ err = mr_fill_mroute(mrt, skb, &cache->_c, rtm);
+ rcu_read_unlock();
return err;
}
-static int ip6mr_fill_mroute(struct mr6_table *mrt, struct sk_buff *skb,
- u32 portid, u32 seq, struct mfc6_cache *c, int cmd)
+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)
{
struct nlmsghdr *nlh;
struct rtmsg *rtm;
int err;
- nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), NLM_F_MULTI);
- if (nlh == NULL)
+ nlh = nlmsg_put(skb, portid, seq, cmd, sizeof(*rtm), flags);
+ if (!nlh)
return -EMSGSIZE;
rtm = nlmsg_data(nlh);
@@ -2363,27 +2509,36 @@ 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;
rtm->rtm_flags = 0;
- if (nla_put(skb, RTA_SRC, 16, &c->mf6c_origin) ||
- nla_put(skb, RTA_DST, 16, &c->mf6c_mcastgrp))
+ 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;
- return nlmsg_end(skb, nlh);
+ nlmsg_end(skb, nlh);
+ return 0;
nla_put_failure:
nlmsg_cancel(skb, nlh);
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 =
@@ -2399,25 +2554,25 @@ static int mr6_msgsize(bool unresolved, int maxvif)
+ nla_total_size(0) /* RTA_MULTIPATH */
+ maxvif * NLA_ALIGN(sizeof(struct rtnexthop))
/* RTA_MFC_STATS */
- + nla_total_size(sizeof(struct rta_mfc_stats))
+ + nla_total_size_64bit(sizeof(struct rta_mfc_stats))
;
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 == NULL)
+ if (!skb)
goto errout;
- err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd);
+ err = ip6mr_fill_mroute(mrt, skb, 0, 0, mfc, cmd, 0);
if (err < 0)
goto errout;
@@ -2426,69 +2581,194 @@ static void mr6_netlink_event(struct mr6_table *mrt, struct mfc6_cache *mfc,
errout:
kfree_skb(skb);
+ rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err);
+}
+
+static size_t mrt6msg_netlink_msgsize(size_t payloadlen)
+{
+ size_t len =
+ NLMSG_ALIGN(sizeof(struct rtgenmsg))
+ + nla_total_size(1) /* IP6MRA_CREPORT_MSGTYPE */
+ + nla_total_size(4) /* IP6MRA_CREPORT_MIF_ID */
+ /* IP6MRA_CREPORT_SRC_ADDR */
+ + nla_total_size(sizeof(struct in6_addr))
+ /* IP6MRA_CREPORT_DST_ADDR */
+ + nla_total_size(sizeof(struct in6_addr))
+ /* IP6MRA_CREPORT_PKT */
+ + nla_total_size(payloadlen)
+ ;
+
+ return len;
+}
+
+static void mrt6msg_netlink_event(const struct mr_table *mrt, struct sk_buff *pkt)
+{
+ struct net *net = read_pnet(&mrt->net);
+ struct nlmsghdr *nlh;
+ struct rtgenmsg *rtgenm;
+ struct mrt6msg *msg;
+ struct sk_buff *skb;
+ struct nlattr *nla;
+ int payloadlen;
+
+ payloadlen = pkt->len - sizeof(struct mrt6msg);
+ msg = (struct mrt6msg *)skb_transport_header(pkt);
+
+ skb = nlmsg_new(mrt6msg_netlink_msgsize(payloadlen), GFP_ATOMIC);
+ if (!skb)
+ goto errout;
+
+ nlh = nlmsg_put(skb, 0, 0, RTM_NEWCACHEREPORT,
+ sizeof(struct rtgenmsg), 0);
+ if (!nlh)
+ goto errout;
+ rtgenm = nlmsg_data(nlh);
+ rtgenm->rtgen_family = RTNL_FAMILY_IP6MR;
+ if (nla_put_u8(skb, IP6MRA_CREPORT_MSGTYPE, msg->im6_msgtype) ||
+ nla_put_u32(skb, IP6MRA_CREPORT_MIF_ID, msg->im6_mif) ||
+ nla_put_in6_addr(skb, IP6MRA_CREPORT_SRC_ADDR,
+ &msg->im6_src) ||
+ nla_put_in6_addr(skb, IP6MRA_CREPORT_DST_ADDR,
+ &msg->im6_dst))
+ goto nla_put_failure;
+
+ nla = nla_reserve(skb, IP6MRA_CREPORT_PKT, payloadlen);
+ if (!nla || skb_copy_bits(pkt, sizeof(struct mrt6msg),
+ nla_data(nla), payloadlen))
+ goto nla_put_failure;
+
+ nlmsg_end(skb, nlh);
+
+ rtnl_notify(skb, net, 0, RTNLGRP_IPV6_MROUTE_R, NULL, GFP_ATOMIC);
+ return;
+
+nla_put_failure:
+ nlmsg_cancel(skb, nlh);
+errout:
+ kfree_skb(skb);
+ rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE_R, -ENOBUFS);
+}
+
+static const struct nla_policy ip6mr_getroute_policy[RTA_MAX + 1] = {
+ [RTA_SRC] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
+ [RTA_DST] = NLA_POLICY_EXACT_LEN(sizeof(struct in6_addr)),
+ [RTA_TABLE] = { .type = NLA_U32 },
+};
+
+static int ip6mr_rtm_valid_getroute_req(struct sk_buff *skb,
+ const struct nlmsghdr *nlh,
+ struct nlattr **tb,
+ struct netlink_ext_ack *extack)
+{
+ struct rtmsg *rtm;
+ int err;
+
+ err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, ip6mr_getroute_policy,
+ extack);
+ if (err)
+ return err;
+
+ rtm = nlmsg_data(nlh);
+ if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) ||
+ (rtm->rtm_dst_len && rtm->rtm_dst_len != 128) ||
+ rtm->rtm_tos || rtm->rtm_table || rtm->rtm_protocol ||
+ rtm->rtm_scope || rtm->rtm_type || rtm->rtm_flags) {
+ NL_SET_ERR_MSG_MOD(extack,
+ "Invalid values in header for multicast route get request");
+ return -EINVAL;
+ }
+
+ if ((tb[RTA_SRC] && !rtm->rtm_src_len) ||
+ (tb[RTA_DST] && !rtm->rtm_dst_len)) {
+ NL_SET_ERR_MSG_MOD(extack, "rtm_src_len and rtm_dst_len must be 128 for IPv6");
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int ip6mr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
+ struct netlink_ext_ack *extack)
+{
+ struct net *net = sock_net(in_skb->sk);
+ struct in6_addr src = {}, grp = {};
+ struct nlattr *tb[RTA_MAX + 1];
+ struct mfc6_cache *cache;
+ struct mr_table *mrt;
+ struct sk_buff *skb;
+ u32 tableid;
+ int err;
+
+ err = ip6mr_rtm_valid_getroute_req(in_skb, nlh, tb, extack);
if (err < 0)
- rtnl_set_sk_err(net, RTNLGRP_IPV6_MROUTE, err);
+ return err;
+
+ if (tb[RTA_SRC])
+ src = nla_get_in6_addr(tb[RTA_SRC]);
+ if (tb[RTA_DST])
+ grp = nla_get_in6_addr(tb[RTA_DST]);
+ tableid = nla_get_u32_default(tb[RTA_TABLE], 0);
+
+ mrt = __ip6mr_get_table(net, tableid ?: RT_TABLE_DEFAULT);
+ if (!mrt) {
+ NL_SET_ERR_MSG_MOD(extack, "MR table does not exist");
+ return -ENOENT;
+ }
+
+ /* entries are added/deleted only under RTNL */
+ rcu_read_lock();
+ cache = ip6mr_cache_find(mrt, &src, &grp);
+ rcu_read_unlock();
+ if (!cache) {
+ NL_SET_ERR_MSG_MOD(extack, "MR cache entry not found");
+ return -ENOENT;
+ }
+
+ skb = nlmsg_new(mr6_msgsize(false, mrt->maxvif), GFP_KERNEL);
+ if (!skb)
+ return -ENOBUFS;
+
+ err = ip6mr_fill_mroute(mrt, skb, NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, cache, RTM_NEWROUTE, 0);
+ if (err < 0) {
+ kfree_skb(skb);
+ return err;
+ }
+
+ return rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid);
}
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;
+ const struct nlmsghdr *nlh = cb->nlh;
+ struct fib_dump_filter filter = {
+ .rtnl_held = true,
+ };
+ int err;
+
+ if (cb->strict_check) {
+ err = ip_valid_fib_dump_req(sock_net(skb->sk), nlh,
+ &filter, cb);
+ if (err < 0)
+ return err;
+ }
- s_t = cb->args[0];
- s_h = cb->args[1];
- s_e = cb->args[2];
+ if (filter.table_id) {
+ struct mr_table *mrt;
- 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) < 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) < 0) {
- spin_unlock_bh(&mfc_unres_lock);
- goto done;
- }
-next_entry2:
- e++;
+ mrt = __ip6mr_get_table(sock_net(skb->sk), filter.table_id);
+ if (!mrt) {
+ if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IP6MR)
+ return skb->len;
+
+ NL_SET_ERR_MSG_MOD(cb->extack, "MR table does not exist");
+ return -ENOENT;
}
- spin_unlock_bh(&mfc_unres_lock);
- e = s_e = 0;
- s_h = 0;
-next_table:
- t++;
+ err = mr_table_dump(mrt, skb, cb, _ip6mr_fill_mroute,
+ &mfc_unres_lock, &filter);
+ return skb->len ? : err;
}
-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, &filter);
}
generated by cgit (git 2.34.1) at 2025-12-25 04:18:09 +0000