summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/addrconf.c3
-rw-r--r--net/ipv6/datagram.c7
-rw-r--r--net/ipv6/ip6_output.c2
-rw-r--r--net/ipv6/ip6_tunnel.c62
-rw-r--r--net/ipv6/ndisc.c18
-rw-r--r--net/ipv6/netfilter/ip6_tables.c5
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c82
-rw-r--r--net/ipv6/protocol.c32
-rw-r--r--net/ipv6/reassembly.c73
-rw-r--r--net/ipv6/route.c4
-rw-r--r--net/ipv6/sit.c66
-rw-r--r--net/ipv6/tunnel6.c17
-rw-r--r--net/ipv6/udp.c10
-rw-r--r--net/ipv6/xfrm6_tunnel.c4
14 files changed, 151 insertions, 234 deletions
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index ab70a3fbcafa..5bc893e28008 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -2964,7 +2964,8 @@ static void addrconf_dad_completed(struct inet6_ifaddr *ifp)
start sending router solicitations.
*/
- if (ifp->idev->cnf.forwarding == 0 &&
+ if ((ifp->idev->cnf.forwarding == 0 ||
+ ifp->idev->cnf.forwarding == 2) &&
ifp->idev->cnf.rtr_solicits > 0 &&
(dev->flags&IFF_LOOPBACK) == 0 &&
(ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)) {
diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c
index 7d929a22cbc2..ef371aa01ac5 100644
--- a/net/ipv6/datagram.c
+++ b/net/ipv6/datagram.c
@@ -105,9 +105,12 @@ ipv4_connected:
if (ipv6_addr_any(&np->saddr))
ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr);
- if (ipv6_addr_any(&np->rcv_saddr))
+ if (ipv6_addr_any(&np->rcv_saddr)) {
ipv6_addr_set_v4mapped(inet->inet_rcv_saddr,
&np->rcv_saddr);
+ if (sk->sk_prot->rehash)
+ sk->sk_prot->rehash(sk);
+ }
goto out;
}
@@ -181,6 +184,8 @@ ipv4_connected:
if (ipv6_addr_any(&np->rcv_saddr)) {
ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src);
inet->inet_rcv_saddr = LOOPBACK4_IPV6;
+ if (sk->sk_prot->rehash)
+ sk->sk_prot->rehash(sk);
}
ip6_dst_store(sk, dst,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index d40b330c0ee6..1838927a2243 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -637,7 +637,7 @@ static int ip6_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
}
mtu -= hlen + sizeof(struct frag_hdr);
- if (skb_has_frags(skb)) {
+ if (skb_has_frag_list(skb)) {
int first_len = skb_pagelen(skb);
int truesizes = 0;
diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 0fd027f3f47e..9289cecac4de 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -83,15 +83,14 @@ struct ip6_tnl_net {
/* the IPv6 tunnel fallback device */
struct net_device *fb_tnl_dev;
/* lists for storing tunnels in use */
- struct ip6_tnl *tnls_r_l[HASH_SIZE];
- struct ip6_tnl *tnls_wc[1];
- struct ip6_tnl **tnls[2];
+ struct ip6_tnl __rcu *tnls_r_l[HASH_SIZE];
+ struct ip6_tnl __rcu *tnls_wc[1];
+ struct ip6_tnl __rcu **tnls[2];
};
/*
- * Locking : hash tables are protected by RCU and a spinlock
+ * Locking : hash tables are protected by RCU and RTNL
*/
-static DEFINE_SPINLOCK(ip6_tnl_lock);
static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t)
{
@@ -138,8 +137,8 @@ static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst)
static struct ip6_tnl *
ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local)
{
- unsigned h0 = HASH(remote);
- unsigned h1 = HASH(local);
+ unsigned int h0 = HASH(remote);
+ unsigned int h1 = HASH(local);
struct ip6_tnl *t;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
@@ -167,7 +166,7 @@ ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local)
* Return: head of IPv6 tunnel list
**/
-static struct ip6_tnl **
+static struct ip6_tnl __rcu **
ip6_tnl_bucket(struct ip6_tnl_net *ip6n, struct ip6_tnl_parm *p)
{
struct in6_addr *remote = &p->raddr;
@@ -190,12 +189,10 @@ ip6_tnl_bucket(struct ip6_tnl_net *ip6n, struct ip6_tnl_parm *p)
static void
ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
{
- struct ip6_tnl **tp = ip6_tnl_bucket(ip6n, &t->parms);
+ struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms);
- spin_lock_bh(&ip6_tnl_lock);
- t->next = *tp;
+ rcu_assign_pointer(t->next , rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
- spin_unlock_bh(&ip6_tnl_lock);
}
/**
@@ -206,13 +203,14 @@ ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
static void
ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t)
{
- struct ip6_tnl **tp;
-
- for (tp = ip6_tnl_bucket(ip6n, &t->parms); *tp; tp = &(*tp)->next) {
- if (t == *tp) {
- spin_lock_bh(&ip6_tnl_lock);
- *tp = t->next;
- spin_unlock_bh(&ip6_tnl_lock);
+ struct ip6_tnl __rcu **tp;
+ struct ip6_tnl *iter;
+
+ for (tp = ip6_tnl_bucket(ip6n, &t->parms);
+ (iter = rtnl_dereference(*tp)) != NULL;
+ tp = &iter->next) {
+ if (t == iter) {
+ rcu_assign_pointer(*tp, t->next);
break;
}
}
@@ -290,10 +288,13 @@ static struct ip6_tnl *ip6_tnl_locate(struct net *net,
{
struct in6_addr *remote = &p->raddr;
struct in6_addr *local = &p->laddr;
+ struct ip6_tnl __rcu **tp;
struct ip6_tnl *t;
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
- for (t = *ip6_tnl_bucket(ip6n, p); t; t = t->next) {
+ for (tp = ip6_tnl_bucket(ip6n, p);
+ (t = rtnl_dereference(*tp)) != NULL;
+ tp = &t->next) {
if (ipv6_addr_equal(local, &t->parms.laddr) &&
ipv6_addr_equal(remote, &t->parms.raddr))
return t;
@@ -318,13 +319,10 @@ ip6_tnl_dev_uninit(struct net_device *dev)
struct net *net = dev_net(dev);
struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id);
- if (dev == ip6n->fb_tnl_dev) {
- spin_lock_bh(&ip6_tnl_lock);
- ip6n->tnls_wc[0] = NULL;
- spin_unlock_bh(&ip6_tnl_lock);
- } else {
+ if (dev == ip6n->fb_tnl_dev)
+ rcu_assign_pointer(ip6n->tnls_wc[0], NULL);
+ else
ip6_tnl_unlink(ip6n, t);
- }
ip6_tnl_dst_reset(t);
dev_put(dev);
}
@@ -1369,16 +1367,16 @@ static void __net_init ip6_fb_tnl_dev_init(struct net_device *dev)
ip6_tnl_dev_init_gen(dev);
t->parms.proto = IPPROTO_IPV6;
dev_hold(dev);
- ip6n->tnls_wc[0] = t;
+ rcu_assign_pointer(ip6n->tnls_wc[0], t);
}
-static struct xfrm6_tunnel ip4ip6_handler = {
+static struct xfrm6_tunnel ip4ip6_handler __read_mostly = {
.handler = ip4ip6_rcv,
.err_handler = ip4ip6_err,
.priority = 1,
};
-static struct xfrm6_tunnel ip6ip6_handler = {
+static struct xfrm6_tunnel ip6ip6_handler __read_mostly = {
.handler = ip6ip6_rcv,
.err_handler = ip6ip6_err,
.priority = 1,
@@ -1391,14 +1389,14 @@ static void __net_exit ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n)
LIST_HEAD(list);
for (h = 0; h < HASH_SIZE; h++) {
- t = ip6n->tnls_r_l[h];
+ t = rtnl_dereference(ip6n->tnls_r_l[h]);
while (t != NULL) {
unregister_netdevice_queue(t->dev, &list);
- t = t->next;
+ t = rtnl_dereference(t->next);
}
}
- t = ip6n->tnls_wc[0];
+ t = rtnl_dereference(ip6n->tnls_wc[0]);
unregister_netdevice_queue(t->dev, &list);
unregister_netdevice_many(&list);
}
diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
index 58841c4ae947..69a0051cea67 100644
--- a/net/ipv6/ndisc.c
+++ b/net/ipv6/ndisc.c
@@ -1105,6 +1105,18 @@ errout:
rtnl_set_sk_err(net, RTNLGRP_ND_USEROPT, err);
}
+static inline int accept_ra(struct inet6_dev *in6_dev)
+{
+ /*
+ * If forwarding is enabled, RA are not accepted unless the special
+ * hybrid mode (accept_ra=2) is enabled.
+ */
+ if (in6_dev->cnf.forwarding && in6_dev->cnf.accept_ra < 2)
+ return 0;
+
+ return in6_dev->cnf.accept_ra;
+}
+
static void ndisc_router_discovery(struct sk_buff *skb)
{
struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb);
@@ -1158,8 +1170,7 @@ static void ndisc_router_discovery(struct sk_buff *skb)
return;
}
- /* skip route and link configuration on routers */
- if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_ra)
+ if (!accept_ra(in6_dev))
goto skip_linkparms;
#ifdef CONFIG_IPV6_NDISC_NODETYPE
@@ -1309,8 +1320,7 @@ skip_linkparms:
NEIGH_UPDATE_F_ISROUTER);
}
- /* skip route and link configuration on routers */
- if (in6_dev->cnf.forwarding || !in6_dev->cnf.accept_ra)
+ if (!accept_ra(in6_dev))
goto out;
#ifdef CONFIG_IPV6_ROUTE_INFO
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index 5359ef4daac5..8e754be92c24 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -922,6 +922,7 @@ get_counters(const struct xt_table_info *t,
if (cpu == curcpu)
continue;
i = 0;
+ local_bh_disable();
xt_info_wrlock(cpu);
xt_entry_foreach(iter, t->entries[cpu], t->size) {
ADD_COUNTER(counters[i], iter->counters.bcnt,
@@ -929,6 +930,7 @@ get_counters(const struct xt_table_info *t,
++i;
}
xt_info_wrunlock(cpu);
+ local_bh_enable();
}
put_cpu();
}
@@ -1764,6 +1766,9 @@ translate_compat_table(struct net *net,
if (ret != 0)
break;
++i;
+ if (strcmp(ip6t_get_target(iter1)->u.user.name,
+ XT_ERROR_TARGET) == 0)
+ ++newinfo->stacksize;
}
if (ret) {
/*
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 13ef5bc05cf5..138a8b362706 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -113,14 +113,6 @@ static void nf_skb_free(struct sk_buff *skb)
kfree_skb(NFCT_FRAG6_CB(skb)->orig);
}
-/* Memory Tracking Functions. */
-static void frag_kfree_skb(struct sk_buff *skb)
-{
- atomic_sub(skb->truesize, &nf_init_frags.mem);
- nf_skb_free(skb);
- kfree_skb(skb);
-}
-
/* Destruction primitives. */
static __inline__ void fq_put(struct nf_ct_frag6_queue *fq)
@@ -282,66 +274,22 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb,
}
found:
- /* We found where to put this one. Check for overlap with
- * preceding fragment, and, if needed, align things so that
- * any overlaps are eliminated.
- */
- if (prev) {
- int i = (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset;
-
- if (i > 0) {
- offset += i;
- if (end <= offset) {
- pr_debug("overlap\n");
- goto err;
- }
- if (!pskb_pull(skb, i)) {
- pr_debug("Can't pull\n");
- goto err;
- }
- if (skb->ip_summed != CHECKSUM_UNNECESSARY)
- skb->ip_summed = CHECKSUM_NONE;
- }
- }
-
- /* Look for overlap with succeeding segments.
- * If we can merge fragments, do it.
+ /* RFC5722, Section 4:
+ * When reassembling an IPv6 datagram, if
+ * one or more its constituent fragments is determined to be an
+ * overlapping fragment, the entire datagram (and any constituent
+ * fragments, including those not yet received) MUST be silently
+ * discarded.
*/
- while (next && NFCT_FRAG6_CB(next)->offset < end) {
- /* overlap is 'i' bytes */
- int i = end - NFCT_FRAG6_CB(next)->offset;
-
- if (i < next->len) {
- /* Eat head of the next overlapped fragment
- * and leave the loop. The next ones cannot overlap.
- */
- pr_debug("Eat head of the overlapped parts.: %d", i);
- if (!pskb_pull(next, i))
- goto err;
- /* next fragment */
- NFCT_FRAG6_CB(next)->offset += i;
- fq->q.meat -= i;
- if (next->ip_summed != CHECKSUM_UNNECESSARY)
- next->ip_summed = CHECKSUM_NONE;
- break;
- } else {
- struct sk_buff *free_it = next;
-
- /* Old fragmnet is completely overridden with
- * new one drop it.
- */
- next = next->next;
+ /* Check for overlap with preceding fragment. */
+ if (prev &&
+ (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset > 0)
+ goto discard_fq;
- if (prev)
- prev->next = next;
- else
- fq->q.fragments = next;
-
- fq->q.meat -= free_it->len;
- frag_kfree_skb(free_it);
- }
- }
+ /* Look for overlap with succeeding segment. */
+ if (next && NFCT_FRAG6_CB(next)->offset < end)
+ goto discard_fq;
NFCT_FRAG6_CB(skb)->offset = offset;
@@ -371,6 +319,8 @@ found:
write_unlock(&nf_frags.lock);
return 0;
+discard_fq:
+ fq_kill(fq);
err:
return -1;
}
@@ -413,7 +363,7 @@ nf_ct_frag6_reasm(struct nf_ct_frag6_queue *fq, struct net_device *dev)
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
- if (skb_has_frags(head)) {
+ if (skb_has_frag_list(head)) {
struct sk_buff *clone;
int i, plen = 0;
diff --git a/net/ipv6/protocol.c b/net/ipv6/protocol.c
index 1fa3468f0f32..9bb936ae2452 100644
--- a/net/ipv6/protocol.c
+++ b/net/ipv6/protocol.c
@@ -25,28 +25,14 @@
#include <linux/spinlock.h>
#include <net/protocol.h>
-const struct inet6_protocol *inet6_protos[MAX_INET_PROTOS];
-static DEFINE_SPINLOCK(inet6_proto_lock);
-
+const struct inet6_protocol *inet6_protos[MAX_INET_PROTOS] __read_mostly;
int inet6_add_protocol(const struct inet6_protocol *prot, unsigned char protocol)
{
- int ret, hash = protocol & (MAX_INET_PROTOS - 1);
-
- spin_lock_bh(&inet6_proto_lock);
-
- if (inet6_protos[hash]) {
- ret = -1;
- } else {
- inet6_protos[hash] = prot;
- ret = 0;
- }
-
- spin_unlock_bh(&inet6_proto_lock);
+ int hash = protocol & (MAX_INET_PROTOS - 1);
- return ret;
+ return !cmpxchg(&inet6_protos[hash], NULL, prot) ? 0 : -1;
}
-
EXPORT_SYMBOL(inet6_add_protocol);
/*
@@ -57,20 +43,10 @@ int inet6_del_protocol(const struct inet6_protocol *prot, unsigned char protocol
{
int ret, hash = protocol & (MAX_INET_PROTOS - 1);
- spin_lock_bh(&inet6_proto_lock);
-
- if (inet6_protos[hash] != prot) {
- ret = -1;
- } else {
- inet6_protos[hash] = NULL;
- ret = 0;
- }
-
- spin_unlock_bh(&inet6_proto_lock);
+ ret = (cmpxchg(&inet6_protos[hash], prot, NULL) == prot) ? 0 : -1;
synchronize_net();
return ret;
}
-
EXPORT_SYMBOL(inet6_del_protocol);
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 545c4141b755..c7ba3149633f 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -149,13 +149,6 @@ int ip6_frag_match(struct inet_frag_queue *q, void *a)
}
EXPORT_SYMBOL(ip6_frag_match);
-/* Memory Tracking Functions. */
-static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb)
-{
- atomic_sub(skb->truesize, &nf->mem);
- kfree_skb(skb);
-}
-
void ip6_frag_init(struct inet_frag_queue *q, void *a)
{
struct frag_queue *fq = container_of(q, struct frag_queue, q);
@@ -346,58 +339,22 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb,
}
found:
- /* We found where to put this one. Check for overlap with
- * preceding fragment, and, if needed, align things so that
- * any overlaps are eliminated.
+ /* RFC5722, Section 4:
+ * When reassembling an IPv6 datagram, if
+ * one or more its constituent fragments is determined to be an
+ * overlapping fragment, the entire datagram (and any constituent
+ * fragments, including those not yet received) MUST be silently
+ * discarded.
*/
- if (prev) {
- int i = (FRAG6_CB(prev)->offset + prev->len) - offset;
- if (i > 0) {
- offset += i;
- if (end <= offset)
- goto err;
- if (!pskb_pull(skb, i))
- goto err;
- if (skb->ip_summed != CHECKSUM_UNNECESSARY)
- skb->ip_summed = CHECKSUM_NONE;
- }
- }
+ /* Check for overlap with preceding fragment. */
+ if (prev &&
+ (FRAG6_CB(prev)->offset + prev->len) - offset > 0)
+ goto discard_fq;
- /* Look for overlap with succeeding segments.
- * If we can merge fragments, do it.
- */
- while (next && FRAG6_CB(next)->offset < end) {
- int i = end - FRAG6_CB(next)->offset; /* overlap is 'i' bytes */
-
- if (i < next->len) {
- /* Eat head of the next overlapped fragment
- * and leave the loop. The next ones cannot overlap.
- */
- if (!pskb_pull(next, i))
- goto err;
- FRAG6_CB(next)->offset += i; /* next fragment */
- fq->q.meat -= i;
- if (next->ip_summed != CHECKSUM_UNNECESSARY)
- next->ip_summed = CHECKSUM_NONE;
- break;
- } else {
- struct sk_buff *free_it = next;
-
- /* Old fragment is completely overridden with
- * new one drop it.
- */
- next = next->next;
-
- if (prev)
- prev->next = next;
- else
- fq->q.fragments = next;
-
- fq->q.meat -= free_it->len;
- frag_kfree_skb(fq->q.net, free_it);
- }
- }
+ /* Look for overlap with succeeding segment. */
+ if (next && FRAG6_CB(next)->offset < end)
+ goto discard_fq;
FRAG6_CB(skb)->offset = offset;
@@ -436,6 +393,8 @@ found:
write_unlock(&ip6_frags.lock);
return -1;
+discard_fq:
+ fq_kill(fq);
err:
IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)),
IPSTATS_MIB_REASMFAILS);
@@ -499,7 +458,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev,
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
- if (skb_has_frags(head)) {
+ if (skb_has_frag_list(head)) {
struct sk_buff *clone;
int i, plen = 0;
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 8f2d0400cf8a..d126365ac046 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -2580,7 +2580,7 @@ ctl_table ipv6_route_table_template[] = {
.data = &init_net.ipv6.sysctl.ip6_rt_gc_elasticity,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec,
},
{
.procname = "mtu_expires",
@@ -2594,7 +2594,7 @@ ctl_table ipv6_route_table_template[] = {
.data = &init_net.ipv6.sysctl.ip6_rt_min_advmss,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec_jiffies,
+ .proc_handler = proc_dointvec,
},
{
.procname = "gc_min_interval_ms",
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index 4699cd3c3118..6822481ff766 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -68,19 +68,18 @@ static void ipip6_tunnel_setup(struct net_device *dev);
static int sit_net_id __read_mostly;
struct sit_net {
- struct ip_tunnel *tunnels_r_l[HASH_SIZE];
- struct ip_tunnel *tunnels_r[HASH_SIZE];
- struct ip_tunnel *tunnels_l[HASH_SIZE];
- struct ip_tunnel *tunnels_wc[1];
- struct ip_tunnel **tunnels[4];
+ struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE];
+ struct ip_tunnel __rcu *tunnels_r[HASH_SIZE];
+ struct ip_tunnel __rcu *tunnels_l[HASH_SIZE];
+ struct ip_tunnel __rcu *tunnels_wc[1];
+ struct ip_tunnel __rcu **tunnels[4];
struct net_device *fb_tunnel_dev;
};
/*
- * Locking : hash tables are protected by RCU and a spinlock
+ * Locking : hash tables are protected by RCU and RTNL
*/
-static DEFINE_SPINLOCK(ipip6_lock);
#define for_each_ip_tunnel_rcu(start) \
for (t = rcu_dereference(start); t; t = rcu_dereference(t->next))
@@ -91,8 +90,8 @@ static DEFINE_SPINLOCK(ipip6_lock);
static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net,
struct net_device *dev, __be32 remote, __be32 local)
{
- unsigned h0 = HASH(remote);
- unsigned h1 = HASH(local);
+ unsigned int h0 = HASH(remote);
+ unsigned int h1 = HASH(local);
struct ip_tunnel *t;
struct sit_net *sitn = net_generic(net, sit_net_id);
@@ -121,12 +120,12 @@ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net,
return NULL;
}
-static struct ip_tunnel **__ipip6_bucket(struct sit_net *sitn,
+static struct ip_tunnel __rcu **__ipip6_bucket(struct sit_net *sitn,
struct ip_tunnel_parm *parms)
{
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
- unsigned h = 0;
+ unsigned int h = 0;
int prio = 0;
if (remote) {
@@ -140,7 +139,7 @@ static struct ip_tunnel **__ipip6_bucket(struct sit_net *sitn,
return &sitn->tunnels[prio][h];
}
-static inline struct ip_tunnel **ipip6_bucket(struct sit_net *sitn,
+static inline struct ip_tunnel __rcu **ipip6_bucket(struct sit_net *sitn,
struct ip_tunnel *t)
{
return __ipip6_bucket(sitn, &t->parms);
@@ -148,13 +147,14 @@ static inline struct ip_tunnel **ipip6_bucket(struct sit_net *sitn,
static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t)
{
- struct ip_tunnel **tp;
-
- for (tp = ipip6_bucket(sitn, t); *tp; tp = &(*tp)->next) {
- if (t == *tp) {
- spin_lock_bh(&ipip6_lock);
- *tp = t->next;
- spin_unlock_bh(&ipip6_lock);
+ struct ip_tunnel __rcu **tp;
+ struct ip_tunnel *iter;
+
+ for (tp = ipip6_bucket(sitn, t);
+ (iter = rtnl_dereference(*tp)) != NULL;
+ tp = &iter->next) {
+ if (t == iter) {
+ rcu_assign_pointer(*tp, t->next);
break;
}
}
@@ -162,12 +162,10 @@ static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t)
static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t)
{
- struct ip_tunnel **tp = ipip6_bucket(sitn, t);
+ struct ip_tunnel __rcu **tp = ipip6_bucket(sitn, t);
- spin_lock_bh(&ipip6_lock);
- t->next = *tp;
+ rcu_assign_pointer(t->next, rtnl_dereference(*tp));
rcu_assign_pointer(*tp, t);
- spin_unlock_bh(&ipip6_lock);
}
static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
@@ -187,17 +185,20 @@ static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn)
#endif
}
-static struct ip_tunnel * ipip6_tunnel_locate(struct net *net,
+static struct ip_tunnel *ipip6_tunnel_locate(struct net *net,
struct ip_tunnel_parm *parms, int create)
{
__be32 remote = parms->iph.daddr;
__be32 local = parms->iph.saddr;
- struct ip_tunnel *t, **tp, *nt;
+ struct ip_tunnel *t, *nt;
+ struct ip_tunnel __rcu **tp;
struct net_device *dev;
char name[IFNAMSIZ];
struct sit_net *sitn = net_generic(net, sit_net_id);
- for (tp = __ipip6_bucket(sitn, parms); (t = *tp) != NULL; tp = &t->next) {
+ for (tp = __ipip6_bucket(sitn, parms);
+ (t = rtnl_dereference(*tp)) != NULL;
+ tp = &t->next) {
if (local == t->parms.iph.saddr &&
remote == t->parms.iph.daddr &&
parms->link == t->parms.link) {
@@ -340,7 +341,7 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg)
ASSERT_RTNL();
- for (p = t->prl; p; p = p->next) {
+ for (p = rtnl_dereference(t->prl); p; p = rtnl_dereference(p->next)) {
if (p->addr == a->addr) {
if (chg) {
p->flags = a->flags;
@@ -451,15 +452,12 @@ static void ipip6_tunnel_uninit(struct net_device *dev)
struct sit_net *sitn = net_generic(net, sit_net_id);
if (dev == sitn->fb_tunnel_dev) {
- spin_lock_bh(&ipip6_lock);
- sitn->tunnels_wc[0] = NULL;
- spin_unlock_bh(&ipip6_lock);
- dev_put(dev);
+ rcu_assign_pointer(sitn->tunnels_wc[0], NULL);
} else {
ipip6_tunnel_unlink(sitn, netdev_priv(dev));
ipip6_tunnel_del_prl(netdev_priv(dev), NULL);
- dev_put(dev);
}
+ dev_put(dev);
}
@@ -590,7 +588,7 @@ __be32 try_6rd(struct in6_addr *v6dst, struct ip_tunnel *tunnel)
#ifdef CONFIG_IPV6_SIT_6RD
if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix,
tunnel->ip6rd.prefixlen)) {
- unsigned pbw0, pbi0;
+ unsigned int pbw0, pbi0;
int pbi1;
u32 d;
@@ -1132,7 +1130,7 @@ static void __net_init ipip6_fb_tunnel_init(struct net_device *dev)
sitn->tunnels_wc[0] = tunnel;
}
-static struct xfrm_tunnel sit_handler = {
+static struct xfrm_tunnel sit_handler __read_mostly = {
.handler = ipip6_rcv,
.err_handler = ipip6_err,
.priority = 1,
diff --git a/net/ipv6/tunnel6.c b/net/ipv6/tunnel6.c
index fc3c86a47452..d9864725d0c6 100644
--- a/net/ipv6/tunnel6.c
+++ b/net/ipv6/tunnel6.c
@@ -30,8 +30,8 @@
#include <net/protocol.h>
#include <net/xfrm.h>
-static struct xfrm6_tunnel *tunnel6_handlers;
-static struct xfrm6_tunnel *tunnel46_handlers;
+static struct xfrm6_tunnel *tunnel6_handlers __read_mostly;
+static struct xfrm6_tunnel *tunnel46_handlers __read_mostly;
static DEFINE_MUTEX(tunnel6_mutex);
int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family)
@@ -51,7 +51,7 @@ int xfrm6_tunnel_register(struct xfrm6_tunnel *handler, unsigned short family)
}
handler->next = *pprev;
- *pprev = handler;
+ rcu_assign_pointer(*pprev, handler);
ret = 0;
@@ -88,6 +88,11 @@ int xfrm6_tunnel_deregister(struct xfrm6_tunnel *handler, unsigned short family)
EXPORT_SYMBOL(xfrm6_tunnel_deregister);
+#define for_each_tunnel_rcu(head, handler) \
+ for (handler = rcu_dereference(head); \
+ handler != NULL; \
+ handler = rcu_dereference(handler->next)) \
+
static int tunnel6_rcv(struct sk_buff *skb)
{
struct xfrm6_tunnel *handler;
@@ -95,7 +100,7 @@ static int tunnel6_rcv(struct sk_buff *skb)
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto drop;
- for (handler = tunnel6_handlers; handler; handler = handler->next)
+ for_each_tunnel_rcu(tunnel6_handlers, handler)
if (!handler->handler(skb))
return 0;
@@ -113,7 +118,7 @@ static int tunnel46_rcv(struct sk_buff *skb)
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto drop;
- for (handler = tunnel46_handlers; handler; handler = handler->next)
+ for_each_tunnel_rcu(tunnel46_handlers, handler)
if (!handler->handler(skb))
return 0;
@@ -129,7 +134,7 @@ static void tunnel6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
{
struct xfrm6_tunnel *handler;
- for (handler = tunnel6_handlers; handler; handler = handler->next)
+ for_each_tunnel_rcu(tunnel6_handlers, handler)
if (!handler->err_handler(skb, opt, type, code, offset, info))
break;
}
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 1dd1affdead2..5acb3560ff15 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -111,6 +111,15 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum)
return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr);
}
+static void udp_v6_rehash(struct sock *sk)
+{
+ u16 new_hash = udp6_portaddr_hash(sock_net(sk),
+ &inet6_sk(sk)->rcv_saddr,
+ inet_sk(sk)->inet_num);
+
+ udp_lib_rehash(sk, new_hash);
+}
+
static inline int compute_score(struct sock *sk, struct net *net,
unsigned short hnum,
struct in6_addr *saddr, __be16 sport,
@@ -1447,6 +1456,7 @@ struct proto udpv6_prot = {
.backlog_rcv = udpv6_queue_rcv_skb,
.hash = udp_lib_hash,
.unhash = udp_lib_unhash,
+ .rehash = udp_v6_rehash,
.get_port = udp_v6_get_port,
.memory_allocated = &udp_memory_allocated,
.sysctl_mem = sysctl_udp_mem,
diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c
index 2ce3a8278f26..ac7584b946a5 100644
--- a/net/ipv6/xfrm6_tunnel.c
+++ b/net/ipv6/xfrm6_tunnel.c
@@ -317,13 +317,13 @@ static const struct xfrm_type xfrm6_tunnel_type = {
.output = xfrm6_tunnel_output,
};
-static struct xfrm6_tunnel xfrm6_tunnel_handler = {
+static struct xfrm6_tunnel xfrm6_tunnel_handler __read_mostly = {
.handler = xfrm6_tunnel_rcv,
.err_handler = xfrm6_tunnel_err,
.priority = 2,
};
-static struct xfrm6_tunnel xfrm46_tunnel_handler = {
+static struct xfrm6_tunnel xfrm46_tunnel_handler __read_mostly = {
.handler = xfrm6_tunnel_rcv,
.err_handler = xfrm6_tunnel_err,
.priority = 2,
generated by cgit v1.2.3 (git 2.46.0) at 2025-08-21 19:19:05 +0000