summaryrefslogtreecommitdiff
path: root/net/ipv6
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv6')
-rw-r--r--net/ipv6/ip6_fib.c2
-rw-r--r--net/ipv6/mcast_snoop.c33
-rw-r--r--net/ipv6/route.c79
3 files changed, 75 insertions, 39 deletions
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 865e777ae20c..418d9823692b 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -173,6 +173,8 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
*ppcpu_rt = NULL;
}
}
+
+ non_pcpu_rt->rt6i_pcpu = NULL;
}
static void rt6_release(struct rt6_info *rt)
diff --git a/net/ipv6/mcast_snoop.c b/net/ipv6/mcast_snoop.c
index df8afe5ab31e..9405b04eecc6 100644
--- a/net/ipv6/mcast_snoop.c
+++ b/net/ipv6/mcast_snoop.c
@@ -143,34 +143,36 @@ static int __ipv6_mc_check_mld(struct sk_buff *skb,
struct sk_buff *skb_chk = NULL;
unsigned int transport_len;
unsigned int len = skb_transport_offset(skb) + sizeof(struct mld_msg);
- int ret;
+ int ret = -EINVAL;
transport_len = ntohs(ipv6_hdr(skb)->payload_len);
transport_len -= skb_transport_offset(skb) - sizeof(struct ipv6hdr);
- skb_get(skb);
skb_chk = skb_checksum_trimmed(skb, transport_len,
ipv6_mc_validate_checksum);
if (!skb_chk)
- return -EINVAL;
+ goto err;
- if (!pskb_may_pull(skb_chk, len)) {
- kfree_skb(skb_chk);
- return -EINVAL;
- }
+ if (!pskb_may_pull(skb_chk, len))
+ goto err;
ret = ipv6_mc_check_mld_msg(skb_chk);
- if (ret) {
- kfree_skb(skb_chk);
- return ret;
- }
+ if (ret)
+ goto err;
if (skb_trimmed)
*skb_trimmed = skb_chk;
- else
+ /* free now unneeded clone */
+ else if (skb_chk != skb)
kfree_skb(skb_chk);
- return 0;
+ ret = 0;
+
+err:
+ if (ret && skb_chk && skb_chk != skb)
+ kfree_skb(skb_chk);
+
+ return ret;
}
/**
@@ -179,7 +181,7 @@ static int __ipv6_mc_check_mld(struct sk_buff *skb,
* @skb_trimmed: to store an skb pointer trimmed to IPv6 packet tail (optional)
*
* Checks whether an IPv6 packet is a valid MLD packet. If so sets
- * skb network and transport headers accordingly and returns zero.
+ * skb transport header accordingly and returns zero.
*
* -EINVAL: A broken packet was detected, i.e. it violates some internet
* standard
@@ -194,7 +196,8 @@ static int __ipv6_mc_check_mld(struct sk_buff *skb,
* to leave the original skb and its full frame unchanged (which might be
* desirable for layer 2 frame jugglers).
*
- * The caller needs to release a reference count from any returned skb_trimmed.
+ * Caller needs to set the skb network header and free any returned skb if it
+ * differs from the provided skb.
*/
int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed)
{
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 6c0fe4c7ce8d..e476f01add87 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -321,8 +321,7 @@ static const struct rt6_info ip6_blk_hole_entry_template = {
/* allocate dst with ip6_dst_ops */
static struct rt6_info *__ip6_dst_alloc(struct net *net,
struct net_device *dev,
- int flags,
- struct fib6_table *table)
+ int flags)
{
struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev,
0, DST_OBSOLETE_FORCE_CHK, flags);
@@ -339,10 +338,9 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net,
static struct rt6_info *ip6_dst_alloc(struct net *net,
struct net_device *dev,
- int flags,
- struct fib6_table *table)
+ int flags)
{
- struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags, table);
+ struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags);
if (rt) {
rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC);
@@ -959,8 +957,7 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort,
if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU))
ort = (struct rt6_info *)ort->dst.from;
- rt = __ip6_dst_alloc(dev_net(ort->dst.dev), ort->dst.dev,
- 0, ort->rt6i_table);
+ rt = __ip6_dst_alloc(dev_net(ort->dst.dev), ort->dst.dev, 0);
if (!rt)
return NULL;
@@ -992,8 +989,7 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt)
struct rt6_info *pcpu_rt;
pcpu_rt = __ip6_dst_alloc(dev_net(rt->dst.dev),
- rt->dst.dev, rt->dst.flags,
- rt->rt6i_table);
+ rt->dst.dev, rt->dst.flags);
if (!pcpu_rt)
return NULL;
@@ -1006,32 +1002,53 @@ static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt)
/* It should be called with read_lock_bh(&tb6_lock) acquired */
static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt)
{
- struct rt6_info *pcpu_rt, *prev, **p;
+ struct rt6_info *pcpu_rt, **p;
p = this_cpu_ptr(rt->rt6i_pcpu);
pcpu_rt = *p;
- if (pcpu_rt)
- goto done;
+ if (pcpu_rt) {
+ dst_hold(&pcpu_rt->dst);
+ rt6_dst_from_metrics_check(pcpu_rt);
+ }
+ return pcpu_rt;
+}
+
+static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt)
+{
+ struct fib6_table *table = rt->rt6i_table;
+ struct rt6_info *pcpu_rt, *prev, **p;
pcpu_rt = ip6_rt_pcpu_alloc(rt);
if (!pcpu_rt) {
struct net *net = dev_net(rt->dst.dev);
- pcpu_rt = net->ipv6.ip6_null_entry;
- goto done;
+ dst_hold(&net->ipv6.ip6_null_entry->dst);
+ return net->ipv6.ip6_null_entry;
}
- prev = cmpxchg(p, NULL, pcpu_rt);
- if (prev) {
- /* If someone did it before us, return prev instead */
+ read_lock_bh(&table->tb6_lock);
+ if (rt->rt6i_pcpu) {
+ p = this_cpu_ptr(rt->rt6i_pcpu);
+ prev = cmpxchg(p, NULL, pcpu_rt);
+ if (prev) {
+ /* If someone did it before us, return prev instead */
+ dst_destroy(&pcpu_rt->dst);
+ pcpu_rt = prev;
+ }
+ } else {
+ /* rt has been removed from the fib6 tree
+ * before we have a chance to acquire the read_lock.
+ * In this case, don't brother to create a pcpu rt
+ * since rt is going away anyway. The next
+ * dst_check() will trigger a re-lookup.
+ */
dst_destroy(&pcpu_rt->dst);
- pcpu_rt = prev;
+ pcpu_rt = rt;
}
-
-done:
dst_hold(&pcpu_rt->dst);
rt6_dst_from_metrics_check(pcpu_rt);
+ read_unlock_bh(&table->tb6_lock);
return pcpu_rt;
}
@@ -1106,9 +1123,22 @@ redo_rt6_select:
rt->dst.lastuse = jiffies;
rt->dst.__use++;
pcpu_rt = rt6_get_pcpu_route(rt);
- read_unlock_bh(&table->tb6_lock);
+
+ if (pcpu_rt) {
+ read_unlock_bh(&table->tb6_lock);
+ } else {
+ /* We have to do the read_unlock first
+ * because rt6_make_pcpu_route() may trigger
+ * ip6_dst_gc() which will take the write_lock.
+ */
+ dst_hold(&rt->dst);
+ read_unlock_bh(&table->tb6_lock);
+ pcpu_rt = rt6_make_pcpu_route(rt);
+ dst_release(&rt->dst);
+ }
return pcpu_rt;
+
}
}
@@ -1569,7 +1599,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
if (unlikely(!idev))
return ERR_PTR(-ENODEV);
- rt = ip6_dst_alloc(net, dev, 0, NULL);
+ rt = ip6_dst_alloc(net, dev, 0);
if (unlikely(!rt)) {
in6_dev_put(idev);
dst = ERR_PTR(-ENOMEM);
@@ -1756,7 +1786,8 @@ int ip6_route_add(struct fib6_config *cfg)
if (!table)
goto out;
- rt = ip6_dst_alloc(net, NULL, (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT, table);
+ rt = ip6_dst_alloc(net, NULL,
+ (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT);
if (!rt) {
err = -ENOMEM;
@@ -2432,7 +2463,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
{
struct net *net = dev_net(idev->dev);
struct rt6_info *rt = ip6_dst_alloc(net, net->loopback_dev,
- DST_NOCOUNT, NULL);
+ DST_NOCOUNT);
if (!rt)
return ERR_PTR(-ENOMEM);
generated by cgit v1.2.3 (git 2.39.0) at 2024-12-02 06:20:35 +0300