summaryrefslogtreecommitdiff
path: root/net/ipv6/anycast.c
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6/anycast.c')
-rw-r--r--net/ipv6/anycast.c199
1 files changed, 118 insertions, 81 deletions
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index dacdea7fcb62..52599584422b 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -47,11 +47,15 @@
static struct hlist_head inet6_acaddr_lst[IN6_ADDR_HSIZE];
static DEFINE_SPINLOCK(acaddr_hash_lock);
+#define ac_dereference(a, idev) \
+ rcu_dereference_protected(a, lockdep_is_held(&(idev)->lock))
+
static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr);
-static u32 inet6_acaddr_hash(struct net *net, const struct in6_addr *addr)
+static u32 inet6_acaddr_hash(const struct net *net,
+ const struct in6_addr *addr)
{
- u32 val = ipv6_addr_hash(addr) ^ net_hash_mix(net);
+ u32 val = __ipv6_addr_jhash(addr, net_hash_mix(net));
return hash_32(val, IN6_ADDR_HSIZE_SHIFT);
}
@@ -63,14 +67,12 @@ static u32 inet6_acaddr_hash(struct net *net, const struct in6_addr *addr)
int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
{
struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6_ac_socklist *pac = NULL;
+ struct net *net = sock_net(sk);
+ netdevice_tracker dev_tracker;
struct net_device *dev = NULL;
struct inet6_dev *idev;
- struct ipv6_ac_socklist *pac;
- struct net *net = sock_net(sk);
- int ishost = !net->ipv6.devconf_all->forwarding;
- int err = 0;
-
- ASSERT_RTNL();
+ int err = 0, ishost;
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
@@ -78,32 +80,43 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
return -EINVAL;
if (ifindex)
- dev = __dev_get_by_index(net, ifindex);
+ dev = netdev_get_by_index(net, ifindex, &dev_tracker, GFP_KERNEL);
- if (ipv6_chk_addr_and_flags(net, addr, dev, true, 0, IFA_F_TENTATIVE))
- return -EINVAL;
+ if (ipv6_chk_addr_and_flags(net, addr, dev, true, 0, IFA_F_TENTATIVE)) {
+ err = -EINVAL;
+ goto error;
+ }
pac = sock_kmalloc(sk, sizeof(struct ipv6_ac_socklist), GFP_KERNEL);
- if (!pac)
- return -ENOMEM;
+ if (!pac) {
+ err = -ENOMEM;
+ goto error;
+ }
+
pac->acl_next = NULL;
pac->acl_addr = *addr;
+ ishost = !READ_ONCE(net->ipv6.devconf_all->forwarding);
+
if (ifindex == 0) {
struct rt6_info *rt;
+ rcu_read_lock();
rt = rt6_lookup(net, addr, NULL, 0, NULL, 0);
if (rt) {
- dev = rt->dst.dev;
+ dev = dst_dev_rcu(&rt->dst);
+ netdev_hold(dev, &dev_tracker, GFP_ATOMIC);
ip6_rt_put(rt);
} else if (ishost) {
+ rcu_read_unlock();
err = -EADDRNOTAVAIL;
goto error;
} else {
/* router, no matching interface: just pick one */
- dev = __dev_get_by_flags(net, IFF_UP,
- IFF_UP | IFF_LOOPBACK);
+ dev = netdev_get_by_flags_rcu(net, &dev_tracker, IFF_UP,
+ IFF_UP | IFF_LOOPBACK);
}
+ rcu_read_unlock();
}
if (!dev) {
@@ -111,7 +124,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
goto error;
}
- idev = __in6_dev_get(dev);
+ idev = in6_dev_get(dev);
if (!idev) {
if (ifindex)
err = -ENODEV;
@@ -119,8 +132,9 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
err = -EADDRNOTAVAIL;
goto error;
}
+
/* reset ishost, now that we have a specific device */
- ishost = !idev->cnf.forwarding;
+ ishost = !READ_ONCE(idev->cnf.forwarding);
pac->acl_ifindex = dev->ifindex;
@@ -133,7 +147,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
if (ishost)
err = -EADDRNOTAVAIL;
if (err)
- goto error;
+ goto error_idev;
}
err = __ipv6_dev_ac_inc(idev, addr);
@@ -143,7 +157,11 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
pac = NULL;
}
+error_idev:
+ in6_dev_put(idev);
error:
+ netdev_put(dev, &dev_tracker);
+
if (pac)
sock_kfree_s(sk, pac, sizeof(*pac));
return err;
@@ -154,12 +172,10 @@ error:
*/
int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
{
- struct ipv6_pinfo *np = inet6_sk(sk);
- struct net_device *dev;
struct ipv6_ac_socklist *pac, *prev_pac;
+ struct ipv6_pinfo *np = inet6_sk(sk);
struct net *net = sock_net(sk);
-
- ASSERT_RTNL();
+ struct net_device *dev;
prev_pac = NULL;
for (pac = np->ipv6_ac_list; pac; pac = pac->acl_next) {
@@ -175,9 +191,11 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
else
np->ipv6_ac_list = pac->acl_next;
- dev = __dev_get_by_index(net, pac->acl_ifindex);
- if (dev)
+ dev = dev_get_by_index(net, pac->acl_ifindex);
+ if (dev) {
ipv6_dev_ac_dec(dev, &pac->acl_addr);
+ dev_put(dev);
+ }
sock_kfree_s(sk, pac, sizeof(*pac));
return 0;
@@ -186,21 +204,20 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr)
void __ipv6_sock_ac_close(struct sock *sk)
{
struct ipv6_pinfo *np = inet6_sk(sk);
+ struct net *net = sock_net(sk);
struct net_device *dev = NULL;
struct ipv6_ac_socklist *pac;
- struct net *net = sock_net(sk);
- int prev_index;
+ int prev_index = 0;
- ASSERT_RTNL();
pac = np->ipv6_ac_list;
np->ipv6_ac_list = NULL;
- prev_index = 0;
while (pac) {
struct ipv6_ac_socklist *next = pac->acl_next;
if (pac->acl_ifindex != prev_index) {
- dev = __dev_get_by_index(net, pac->acl_ifindex);
+ dev_put(dev);
+ dev = dev_get_by_index(net, pac->acl_ifindex);
prev_index = pac->acl_ifindex;
}
if (dev)
@@ -208,6 +225,8 @@ void __ipv6_sock_ac_close(struct sock *sk)
sock_kfree_s(sk, pac, sizeof(*pac));
pac = next;
}
+
+ dev_put(dev);
}
void ipv6_sock_ac_close(struct sock *sk)
@@ -216,9 +235,8 @@ void ipv6_sock_ac_close(struct sock *sk)
if (!np->ipv6_ac_list)
return;
- rtnl_lock();
+
__ipv6_sock_ac_close(sk);
- rtnl_unlock();
}
static void ipv6_add_acaddr_hash(struct net *net, struct ifacaddr6 *aca)
@@ -252,9 +270,8 @@ static void aca_free_rcu(struct rcu_head *h)
static void aca_put(struct ifacaddr6 *ac)
{
- if (refcount_dec_and_test(&ac->aca_refcnt)) {
- call_rcu(&ac->rcu, aca_free_rcu);
- }
+ if (refcount_dec_and_test(&ac->aca_refcnt))
+ call_rcu_hurry(&ac->rcu, aca_free_rcu);
}
static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i,
@@ -278,6 +295,37 @@ static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i,
return aca;
}
+static void inet6_ifacaddr_notify(struct net_device *dev,
+ const struct ifacaddr6 *ifaca, int event)
+{
+ struct inet6_fill_args fillargs = {
+ .event = event,
+ .netnsid = -1,
+ };
+ struct net *net = dev_net(dev);
+ struct sk_buff *skb;
+ int err = -ENOMEM;
+
+ skb = nlmsg_new(NLMSG_ALIGN(sizeof(struct ifaddrmsg)) +
+ nla_total_size(sizeof(struct in6_addr)) +
+ nla_total_size(sizeof(struct ifa_cacheinfo)),
+ GFP_KERNEL);
+ if (!skb)
+ goto error;
+
+ err = inet6_fill_ifacaddr(skb, ifaca, &fillargs);
+ if (err < 0) {
+ pr_err("Failed to fill in anycast addresses (err %d)\n", err);
+ nlmsg_free(skb);
+ goto error;
+ }
+
+ rtnl_notify(skb, net, 0, RTNLGRP_IPV6_ACADDR, NULL, GFP_KERNEL);
+ return;
+error:
+ rtnl_set_sk_err(net, RTNLGRP_IPV6_ACADDR, err);
+}
+
/*
* device anycast group inc (add if not found)
*/
@@ -288,15 +336,14 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
struct net *net;
int err;
- ASSERT_RTNL();
-
write_lock_bh(&idev->lock);
if (idev->dead) {
err = -ENODEV;
goto out;
}
- for (aca = idev->ac_list; aca; aca = aca->aca_next) {
+ for (aca = ac_dereference(idev->ac_list, idev); aca;
+ aca = ac_dereference(aca->aca_next, idev)) {
if (ipv6_addr_equal(&aca->aca_addr, addr)) {
aca->aca_users++;
err = 0;
@@ -305,7 +352,7 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
}
net = dev_net(idev->dev);
- f6i = addrconf_f6i_alloc(net, idev, addr, true, GFP_ATOMIC);
+ f6i = addrconf_f6i_alloc(net, idev, addr, true, GFP_ATOMIC, NULL);
if (IS_ERR(f6i)) {
err = PTR_ERR(f6i);
goto out;
@@ -317,13 +364,13 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
goto out;
}
- aca->aca_next = idev->ac_list;
- idev->ac_list = aca;
-
/* Hold this for addrconf_join_solict() below before we unlock,
* it is already exposed via idev->ac_list.
*/
aca_get(aca);
+ aca->aca_next = idev->ac_list;
+ rcu_assign_pointer(idev->ac_list, aca);
+
write_unlock_bh(&idev->lock);
ipv6_add_acaddr_hash(net, aca);
@@ -332,6 +379,8 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr)
addrconf_join_solict(idev->dev, &aca->aca_addr);
+ inet6_ifacaddr_notify(idev->dev, aca, RTM_NEWANYCAST);
+
aca_put(aca);
return 0;
out:
@@ -346,11 +395,10 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
{
struct ifacaddr6 *aca, *prev_aca;
- ASSERT_RTNL();
-
write_lock_bh(&idev->lock);
prev_aca = NULL;
- for (aca = idev->ac_list; aca; aca = aca->aca_next) {
+ for (aca = ac_dereference(idev->ac_list, idev); aca;
+ aca = ac_dereference(aca->aca_next, idev)) {
if (ipv6_addr_equal(&aca->aca_addr, addr))
break;
prev_aca = aca;
@@ -364,27 +412,33 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr)
return 0;
}
if (prev_aca)
- prev_aca->aca_next = aca->aca_next;
+ rcu_assign_pointer(prev_aca->aca_next, aca->aca_next);
else
- idev->ac_list = aca->aca_next;
+ rcu_assign_pointer(idev->ac_list, aca->aca_next);
write_unlock_bh(&idev->lock);
ipv6_del_acaddr_hash(aca);
addrconf_leave_solict(idev, &aca->aca_addr);
ip6_del_rt(dev_net(idev->dev), aca->aca_rt, false);
+ inet6_ifacaddr_notify(idev->dev, aca, RTM_DELANYCAST);
+
aca_put(aca);
return 0;
}
-/* called with rtnl_lock() */
static int ipv6_dev_ac_dec(struct net_device *dev, const struct in6_addr *addr)
{
- struct inet6_dev *idev = __in6_dev_get(dev);
+ struct inet6_dev *idev = in6_dev_get(dev);
+ int err;
if (!idev)
return -ENODEV;
- return __ipv6_dev_ac_dec(idev, addr);
+
+ err = __ipv6_dev_ac_dec(idev, addr);
+ in6_dev_put(idev);
+
+ return err;
}
void ipv6_ac_destroy_dev(struct inet6_dev *idev)
@@ -392,8 +446,8 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev)
struct ifacaddr6 *aca;
write_lock_bh(&idev->lock);
- while ((aca = idev->ac_list) != NULL) {
- idev->ac_list = aca->aca_next;
+ while ((aca = ac_dereference(idev->ac_list, idev)) != NULL) {
+ rcu_assign_pointer(idev->ac_list, aca->aca_next);
write_unlock_bh(&idev->lock);
ipv6_del_acaddr_hash(aca);
@@ -420,11 +474,10 @@ static bool ipv6_chk_acast_dev(struct net_device *dev, const struct in6_addr *ad
idev = __in6_dev_get(dev);
if (idev) {
- read_lock_bh(&idev->lock);
- for (aca = idev->ac_list; aca; aca = aca->aca_next)
+ for (aca = rcu_dereference(idev->ac_list); aca;
+ aca = rcu_dereference(aca->aca_next))
if (ipv6_addr_equal(&aca->aca_addr, addr))
break;
- read_unlock_bh(&idev->lock);
return aca != NULL;
}
return false;
@@ -477,30 +530,25 @@ bool ipv6_chk_acast_addr_src(struct net *net, struct net_device *dev,
struct ac6_iter_state {
struct seq_net_private p;
struct net_device *dev;
- struct inet6_dev *idev;
};
#define ac6_seq_private(seq) ((struct ac6_iter_state *)(seq)->private)
static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq)
{
- struct ifacaddr6 *im = NULL;
struct ac6_iter_state *state = ac6_seq_private(seq);
struct net *net = seq_file_net(seq);
+ struct ifacaddr6 *im = NULL;
- state->idev = NULL;
for_each_netdev_rcu(net, state->dev) {
struct inet6_dev *idev;
+
idev = __in6_dev_get(state->dev);
if (!idev)
continue;
- read_lock_bh(&idev->lock);
- im = idev->ac_list;
- if (im) {
- state->idev = idev;
+ im = rcu_dereference(idev->ac_list);
+ if (im)
break;
- }
- read_unlock_bh(&idev->lock);
}
return im;
}
@@ -508,22 +556,17 @@ static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq)
static struct ifacaddr6 *ac6_get_next(struct seq_file *seq, struct ifacaddr6 *im)
{
struct ac6_iter_state *state = ac6_seq_private(seq);
+ struct inet6_dev *idev;
- im = im->aca_next;
+ im = rcu_dereference(im->aca_next);
while (!im) {
- if (likely(state->idev != NULL))
- read_unlock_bh(&state->idev->lock);
-
state->dev = next_net_device_rcu(state->dev);
- if (!state->dev) {
- state->idev = NULL;
+ if (!state->dev)
break;
- }
- state->idev = __in6_dev_get(state->dev);
- if (!state->idev)
+ idev = __in6_dev_get(state->dev);
+ if (!idev)
continue;
- read_lock_bh(&state->idev->lock);
- im = state->idev->ac_list;
+ im = rcu_dereference(idev->ac_list);
}
return im;
}
@@ -555,12 +598,6 @@ static void *ac6_seq_next(struct seq_file *seq, void *v, loff_t *pos)
static void ac6_seq_stop(struct seq_file *seq, void *v)
__releases(RCU)
{
- struct ac6_iter_state *state = ac6_seq_private(seq);
-
- if (likely(state->idev != NULL)) {
- read_unlock_bh(&state->idev->lock);
- state->idev = NULL;
- }
rcu_read_unlock();
}
generated by cgit (git 2.34.1) at 2025-12-21 18:55:34 +0000