net: replace dst_cache ip6_tunnel implementation with the generic one

This also fix a potential race into the existing tunnel code, which
could lead to the wrong dst to be permanenty cached:

CPU1:					CPU2:
  <xmit on ip6_tunnel>
  <cache lookup fails>
  dst = ip6_route_output(...)
					<tunnel params are changed via nl>
					dst_cache_reset() // no effect,
							// the cache is empty
  dst_cache_set() // the wrong dst
	// is permanenty stored
	// into the cache

With the new dst implementation the above race is not possible
since the first cache lookup after dst_cache_reset will fail due
to the timestamp check

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Suggested-and-acked-by: Hannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/ip6_tunnel.h b/include/net/ip6_tunnel.h
index 0d0ce0b2d8701cb94514933c239996da1cc982ca..499a707765ea68fa010e03716319dcef57de49fe 100644 (file)
--- a/include/net/ip6_tunnel.h
+++ b/include/net/ip6_tunnel.h
@@ -6,6 +6,7 @@
 #include <linux/if_tunnel.h>
 #include <linux/ip6_tunnel.h>
 #include <net/ip_tunnels.h>
+#include <net/dst_cache.h>
 
 #define IP6TUNNEL_ERR_TIMEO (30*HZ)
 
@@ -33,12 +34,6 @@ struct __ip6_tnl_parm {
        __be32                  o_key;
 };
 
-struct ip6_tnl_dst {
-       seqlock_t lock;
-       struct dst_entry __rcu *dst;
-       u32 cookie;
-};
-
 /* IPv6 tunnel */
 struct ip6_tnl {
        struct ip6_tnl __rcu *next;     /* next tunnel in list */
@@ -46,7 +41,7 @@ struct ip6_tnl {
        struct net *net;        /* netns for packet i/o */
        struct __ip6_tnl_parm parms;    /* tunnel configuration parameters */
        struct flowi fl;        /* flowi template for xmit */
-       struct ip6_tnl_dst __percpu *dst_cache; /* cached dst */
+       struct dst_cache dst_cache;     /* cached dst */
 
        int err_count;
        unsigned long err_time;
@@ -66,11 +61,6 @@ struct ipv6_tlv_tnl_enc_lim {
        __u8 encap_limit;       /* tunnel encapsulation limit   */
 } __packed;
 
-struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t);
-int ip6_tnl_dst_init(struct ip6_tnl *t);
-void ip6_tnl_dst_destroy(struct ip6_tnl *t);
-void ip6_tnl_dst_reset(struct ip6_tnl *t);
-void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst);
 int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,
                const struct in6_addr *raddr);
 int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr,

diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index 40c897515ddc44d57c434dcd761c2ddc5e7fad50..11e875ffd7ace7360f3f03759cc0b81bc8a11abf 100644 (file)
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -207,6 +207,7 @@ config IPV6_NDISC_NODETYPE
 config IPV6_TUNNEL
        tristate "IPv6: IP-in-IPv6 tunnel (RFC2473)"
        select INET6_TUNNEL
+       select DST_CACHE
        ---help---
          Support for IPv6-in-IPv6 and IPv4-in-IPv6 tunnels described in
          RFC 2473.

diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c
index f37f18b6b40c9547e24902f4af88bdf6f154f394..a94e50602813ba0640f09755afab8356ba32bbdb 100644 (file)
--- a/net/ipv6/ip6_gre.c
+++ b/net/ipv6/ip6_gre.c
@@ -360,7 +360,7 @@ static void ip6gre_tunnel_uninit(struct net_device *dev)
        struct ip6gre_net *ign = net_generic(t->net, ip6gre_net_id);
 
        ip6gre_tunnel_unlink(ign, t);
-       ip6_tnl_dst_reset(t);
+       dst_cache_reset(&t->dst_cache);
        dev_put(dev);
 }
 
@@ -633,7 +633,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
        }
 
        if (!fl6->flowi6_mark)
-               dst = ip6_tnl_dst_get(tunnel);
+               dst = dst_cache_get(&tunnel->dst_cache);
 
        if (!dst) {
                dst = ip6_route_output(net, NULL, fl6);
@@ -702,7 +702,7 @@ static netdev_tx_t ip6gre_xmit2(struct sk_buff *skb,
        }
 
        if (!fl6->flowi6_mark && ndst)
-               ip6_tnl_dst_set(tunnel, ndst);
+               dst_cache_set_ip6(&tunnel->dst_cache, ndst, &fl6->saddr);
        skb_dst_set(skb, dst);
 
        proto = NEXTHDR_GRE;
@@ -1009,7 +1009,7 @@ static int ip6gre_tnl_change(struct ip6_tnl *t,
        t->parms.o_key = p->o_key;
        t->parms.i_flags = p->i_flags;
        t->parms.o_flags = p->o_flags;
-       ip6_tnl_dst_reset(t);
+       dst_cache_reset(&t->dst_cache);
        ip6gre_tnl_link_config(t, set_mtu);
        return 0;
 }
@@ -1219,7 +1219,7 @@ static void ip6gre_dev_free(struct net_device *dev)
 {
        struct ip6_tnl *t = netdev_priv(dev);
 
-       ip6_tnl_dst_destroy(t);
+       dst_cache_destroy(&t->dst_cache);
        free_percpu(dev->tstats);
        free_netdev(dev);
 }
@@ -1257,7 +1257,7 @@ static int ip6gre_tunnel_init_common(struct net_device *dev)
        if (!dev->tstats)
                return -ENOMEM;
 
-       ret = ip6_tnl_dst_init(tunnel);
+       ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL);
        if (ret) {
                free_percpu(dev->tstats);
                dev->tstats = NULL;

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 137fca42aaa6bb809d46e7809b240d8810d89a04..3f3aabd2f07b8dfe624e3035d5f3743078f36aff 100644 (file)
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -122,97 +122,6 @@ static struct net_device_stats *ip6_get_stats(struct net_device *dev)
        return &dev->stats;
 }
 
-/*
- * Locking : hash tables are protected by RCU and RTNL
- */
-
-static void ip6_tnl_per_cpu_dst_set(struct ip6_tnl_dst *idst,
-                                   struct dst_entry *dst)
-{
-       write_seqlock_bh(&idst->lock);
-       dst_release(rcu_dereference_protected(
-                           idst->dst,
-                           lockdep_is_held(&idst->lock.lock)));
-       if (dst) {
-               dst_hold(dst);
-               idst->cookie = rt6_get_cookie((struct rt6_info *)dst);
-       } else {
-               idst->cookie = 0;
-       }
-       rcu_assign_pointer(idst->dst, dst);
-       write_sequnlock_bh(&idst->lock);
-}
-
-struct dst_entry *ip6_tnl_dst_get(struct ip6_tnl *t)
-{
-       struct ip6_tnl_dst *idst;
-       struct dst_entry *dst;
-       unsigned int seq;
-       u32 cookie;
-
-       idst = raw_cpu_ptr(t->dst_cache);
-
-       rcu_read_lock();
-       do {
-               seq = read_seqbegin(&idst->lock);
-               dst = rcu_dereference(idst->dst);
-               cookie = idst->cookie;
-       } while (read_seqretry(&idst->lock, seq));
-
-       if (dst && !atomic_inc_not_zero(&dst->__refcnt))
-               dst = NULL;
-       rcu_read_unlock();
-
-       if (dst && dst->obsolete && !dst->ops->check(dst, cookie)) {
-               ip6_tnl_per_cpu_dst_set(idst, NULL);
-               dst_release(dst);
-               dst = NULL;
-       }
-       return dst;
-}
-EXPORT_SYMBOL_GPL(ip6_tnl_dst_get);
-
-void ip6_tnl_dst_reset(struct ip6_tnl *t)
-{
-       int i;
-
-       for_each_possible_cpu(i)
-               ip6_tnl_per_cpu_dst_set(per_cpu_ptr(t->dst_cache, i), NULL);
-}
-EXPORT_SYMBOL_GPL(ip6_tnl_dst_reset);
-
-void ip6_tnl_dst_set(struct ip6_tnl *t, struct dst_entry *dst)
-{
-       ip6_tnl_per_cpu_dst_set(raw_cpu_ptr(t->dst_cache), dst);
-
-}
-EXPORT_SYMBOL_GPL(ip6_tnl_dst_set);
-
-void ip6_tnl_dst_destroy(struct ip6_tnl *t)
-{
-       if (!t->dst_cache)
-               return;
-
-       ip6_tnl_dst_reset(t);
-       free_percpu(t->dst_cache);
-}
-EXPORT_SYMBOL_GPL(ip6_tnl_dst_destroy);
-
-int ip6_tnl_dst_init(struct ip6_tnl *t)
-{
-       int i;
-
-       t->dst_cache = alloc_percpu(struct ip6_tnl_dst);
-       if (!t->dst_cache)
-               return -ENOMEM;
-
-       for_each_possible_cpu(i)
-               seqlock_init(&per_cpu_ptr(t->dst_cache, i)->lock);
-
-       return 0;
-}
-EXPORT_SYMBOL_GPL(ip6_tnl_dst_init);
-
 /**
  * ip6_tnl_lookup - fetch tunnel matching the end-point addresses
  *   @remote: the address of the tunnel exit-point
@@ -329,7 +238,7 @@ static void ip6_dev_free(struct net_device *dev)
 {
        struct ip6_tnl *t = netdev_priv(dev);
 
-       ip6_tnl_dst_destroy(t);
+       dst_cache_destroy(&t->dst_cache);
        free_percpu(dev->tstats);
        free_netdev(dev);
 }
@@ -462,7 +371,7 @@ ip6_tnl_dev_uninit(struct net_device *dev)
                RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL);
        else
                ip6_tnl_unlink(ip6n, t);
-       ip6_tnl_dst_reset(t);
+       dst_cache_reset(&t->dst_cache);
        dev_put(dev);
 }
 
@@ -1069,7 +978,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
                memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr));
                neigh_release(neigh);
        } else if (!fl6->flowi6_mark)
-               dst = ip6_tnl_dst_get(t);
+               dst = dst_cache_get(&t->dst_cache);
 
        if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr))
                goto tx_err_link_failure;
@@ -1133,7 +1042,7 @@ static int ip6_tnl_xmit2(struct sk_buff *skb,
        }
 
        if (!fl6->flowi6_mark && ndst)
-               ip6_tnl_dst_set(t, ndst);
+               dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr);
        skb_dst_set(skb, dst);
 
        skb->transport_header = skb->network_header;
@@ -1366,7 +1275,7 @@ ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
        t->parms.flowinfo = p->flowinfo;
        t->parms.link = p->link;
        t->parms.proto = p->proto;
-       ip6_tnl_dst_reset(t);
+       dst_cache_reset(&t->dst_cache);
        ip6_tnl_link_config(t);
        return 0;
 }
@@ -1637,7 +1546,7 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
        if (!dev->tstats)
                return -ENOMEM;
 
-       ret = ip6_tnl_dst_init(t);
+       ret = dst_cache_init(&t->dst_cache, GFP_KERNEL);
        if (ret) {
                free_percpu(dev->tstats);
                dev->tstats = NULL;

diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c
index 0a8610b33d7980e4b1d5290b4266669ddcdc9e0a..d90a11f14040cf8097d3270710ab7db02be60d84 100644 (file)
--- a/net/ipv6/ip6_vti.c
+++ b/net/ipv6/ip6_vti.c
@@ -640,7 +640,7 @@ vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p)
        t->parms.i_key = p->i_key;
        t->parms.o_key = p->o_key;
        t->parms.proto = p->proto;
-       ip6_tnl_dst_reset(t);
+       dst_cache_reset(&t->dst_cache);
        vti6_link_config(t);
        return 0;
 }