From: Ido Schimmel <ido...@mellanox.com>
Listeners of the FIB notification chain are expected to be able to take
and release a reference on notified IPv6 routes. This is needed in the
case of drivers capable of offloading these routes to a capable device.
Since notifications are sent in an atomic context, these drivers need to
take a reference on the route, prepare a work item to offload the route
and release the reference at the end of the work.
Currently, rt6i_ref is used to indicate in how many FIB nodes a route
appears. Different code paths rely on rt6i_ref being 0 to indicate the
route is no longer used by the FIB.
For example, whenever a route is deleted or replaced, fib6_purge_rt() is
run to make sure the route is no longer present in intermediate nodes. A
BUG_ON() at the end of the function is executed in case the reference
count isn't 1, as it's only supposed to appear in the non-intermediate
node from which it's going to be deleted.
Instead of changing the semantics of rt6i_ref, a new reference count is
added, so that external users could also take a reference on routes
without modifying rt6i_ref.
To make sure external users don't release routes used by the FIB, the
reference count is set to 1 upon creation of a route and decremented by
the FIB upon rt6_release().
The reference count is atomic, as it's not protected by any locks and
placed in the 40 bytes hole after the existing rt6i_ref.
rt6_free_pcpu() is exported so that modules could invoke rt6_put().
Similar to commit b423cb10807b ("ipv4: fib: Export free_fib_info()").
Signed-off-by: Ido Schimmel <ido...@mellanox.com>
Signed-off-by: Jiri Pirko <j...@mellanox.com>
---
include/net/ip6_fib.h | 17 +++++++++++++++++
net/ipv6/ip6_fib.c | 10 ++++------
net/ipv6/route.c | 4 ++++
3 files changed, 25 insertions(+), 6 deletions(-)
diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h
index 0b30521..e8ecd08 100644
--- a/include/net/ip6_fib.h
+++ b/include/net/ip6_fib.h
@@ -119,6 +119,7 @@ struct rt6_info {
unsigned int rt6i_nsiblings;
atomic_t rt6i_ref;
+ refcount_t rt6i_extref;
/* These are in a separate cache line. */
struct rt6key rt6i_dst ____cacheline_aligned_in_smp;
@@ -187,6 +188,22 @@ static inline void ip6_rt_put(struct rt6_info *rt)
dst_release(&rt->dst);
}
+void rt6_free_pcpu(struct rt6_info *non_pcpu_rt);
+
+static inline void rt6_get(struct rt6_info *rt)
+{
+ refcount_inc(&rt->rt6i_extref);
+}
+
+static inline void rt6_put(struct rt6_info *rt)
+{
+ if (refcount_dec_and_test(&rt->rt6i_extref)) {
+ rt6_free_pcpu(rt);
+ dst_dev_put(&rt->dst);
+ dst_release(&rt->dst);
+ }
+}
+
enum fib6_walk_state {
#ifdef CONFIG_IPV6_SUBTREES
FWS_S,
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 719c1048..99ca785 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -154,7 +154,7 @@ static void node_free(struct fib6_node *fn)
kmem_cache_free(fib6_node_kmem, fn);
}
-static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
+void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
{
int cpu;
@@ -177,14 +177,12 @@ static void rt6_free_pcpu(struct rt6_info *non_pcpu_rt)
free_percpu(non_pcpu_rt->rt6i_pcpu);
non_pcpu_rt->rt6i_pcpu = NULL;
}
+EXPORT_SYMBOL_GPL(rt6_free_pcpu);
static void rt6_release(struct rt6_info *rt)
{
- if (atomic_dec_and_test(&rt->rt6i_ref)) {
- rt6_free_pcpu(rt);
- dst_dev_put(&rt->dst);
- dst_release(&rt->dst);
- }
+ if (atomic_dec_and_test(&rt->rt6i_ref))
+ rt6_put(rt);
}
static void fib6_link_table(struct net *net, struct fib6_table *tb)
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 924e02d..cabe0c6 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -345,6 +345,10 @@ static void rt6_info_init(struct rt6_info *rt)
memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst));
INIT_LIST_HEAD(&rt->rt6i_siblings);
INIT_LIST_HEAD(&rt->rt6i_uncached);
+ /* Make sure route can't be released as long as it's used by
+ * the FIB.
+ */
+ refcount_set(&rt->rt6i_extref, 1);
}
/* allocate dst with ip6_dst_ops */
--
2.9.3
