@@ -1743,8 +1743,8 @@ sk_dst_get(struct sock *sk)
rcu_read_lock();
dst = rcu_dereference(sk->sk_dst_cache);
- if (dst)
- dst_hold(dst);
+ if (dst && !atomic_inc_not_zero(&dst->__refcnt))
+ dst = NULL;
rcu_read_unlock();
return dst;
}
@@ -267,6 +267,15 @@ again:
}
EXPORT_SYMBOL(dst_destroy);
+static void dst_destroy_rcu(struct rcu_head *head)
+{
+ struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
+
+ dst = dst_destroy(dst);
+ if (dst)
+ __dst_free(dst);
+}
+
void dst_release(struct dst_entry *dst)
{
if (dst) {
@@ -274,11 +283,8 @@ void dst_release(struct dst_entry *dst)
newrefcnt = atomic_dec_return(&dst->__refcnt);
WARN_ON(newrefcnt < 0);
- if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) {
- dst = dst_destroy(dst);
- if (dst)
- __dst_free(dst);
- }
+ if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt)
+ call_rcu(&dst->rcu_head, dst_destroy_rcu);
}
}
EXPORT_SYMBOL(dst_release);
This is a note to let you know that I have just added a patch titled ipv4: fix dst race in sk_dst_get() to the linux-3.13.y-queue branch of the 3.13.y.z extended stable tree which can be found at: http://kernel.ubuntu.com/git?p=ubuntu/linux.git;a=shortlog;h=refs/heads/linux-3.13.y-queue This patch is scheduled to be released in version 3.13.11.6. If you, or anyone else, feels it should not be added to this tree, please reply to this email. For more information about the 3.13.y.z tree, see https://wiki.ubuntu.com/Kernel/Dev/ExtendedStable Thanks. -Kamal ------ From c6d01e03c63620ae7c46f61d92461108dea8a952 Mon Sep 17 00:00:00 2001 From: Eric Dumazet <edumazet@google.com> Date: Tue, 24 Jun 2014 10:05:11 -0700 Subject: ipv4: fix dst race in sk_dst_get() commit f88649721268999bdff09777847080a52004f691 upstream. When IP route cache had been removed in linux-3.6, we broke assumption that dst entries were all freed after rcu grace period. DST_NOCACHE dst were supposed to be freed from dst_release(). But it appears we want to keep such dst around, either in UDP sockets or tunnels. In sk_dst_get() we need to make sure dst refcount is not 0 before incrementing it, or else we might end up freeing a dst twice. DST_NOCACHE set on a dst does not mean this dst can not be attached to a socket or a tunnel. Then, before actual freeing, we need to observe a rcu grace period to make sure all other cpus can catch the fact the dst is no longer usable. Signed-off-by: Eric Dumazet <edumazet@google.com> Reported-by: Dormando <dormando@rydia.net> Signed-off-by: David S. Miller <davem@davemloft.net> [ luis: backported to 3.11: used davem's backport to 3.10 ] Signed-off-by: Luis Henriques <luis.henriques@canonical.com> Signed-off-by: Kamal Mostafa <kamal@canonical.com> --- include/net/sock.h | 4 ++-- net/core/dst.c | 16 +++++++++++----- 2 files changed, 13 insertions(+), 7 deletions(-) -- 1.9.1