filter: fix sk_filter rcu handling

[ Upstream commit 46bcf14f44d8f31ecfdc8b6708ec15a3b33316d9 ]

Pavel Emelyanov tried to fix a race between sk_filter_(de|at)tach and
sk_clone() in commit 47e958eac280c263397

Problem is we can have several clones sharing a common sk_filter, and
these clones might want to sk_filter_attach() their own filters at the
same time, and can overwrite old_filter->rcu, corrupting RCU queues.

We can not use filter->rcu without being sure no other thread could do
the same thing.

Switch code to a more conventional ref-counting technique : Do the
atomic decrement immediately and queue one rcu call back when last
reference is released.

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
Signed-off-by: Andi Kleen <ak@linux.intel.com>

diff --git a/include/net/sock.h b/include/net/sock.h
index e2a9f591a0e3cd0a660097fc292c5dd75d149367..a4089b3500a0e8b97eec4cae2b68e3fe3f9c5c60 100644 (file)
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -1151,6 +1151,8 @@ extern void sk_common_release(struct sock *sk);
 /* Initialise core socket variables */
 extern void sock_init_data(struct socket *sock, struct sock *sk);
 
+extern void sk_filter_release_rcu(struct rcu_head *rcu);
+
 /**
  *     sk_filter_release - release a socket filter
  *     @fp: filter to remove
@@ -1161,7 +1163,7 @@ extern void sock_init_data(struct socket *sock, struct sock *sk);
 static inline void sk_filter_release(struct sk_filter *fp)
 {
        if (atomic_dec_and_test(&fp->refcnt))
-               kfree(fp);
+               call_rcu_bh(&fp->rcu, sk_filter_release_rcu);
 }
 
 static inline void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp)

diff --git a/net/core/filter.c b/net/core/filter.c
index f68e49774829a2e12a88d23dd42966d831da5c11..71a433cdf7d39817ce15da50af746336a352e2a0 100644 (file)
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -589,23 +589,16 @@ int sk_chk_filter(struct sock_filter *filter, int flen)
 EXPORT_SYMBOL(sk_chk_filter);
 
 /**
- *     sk_filter_rcu_release: Release a socket filter by rcu_head
+ *     sk_filter_release_rcu - Release a socket filter by rcu_head
  *     @rcu: rcu_head that contains the sk_filter to free
  */
-static void sk_filter_rcu_release(struct rcu_head *rcu)
+void sk_filter_release_rcu(struct rcu_head *rcu)
 {
        struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu);
 
-       sk_filter_release(fp);
-}
-
-static void sk_filter_delayed_uncharge(struct sock *sk, struct sk_filter *fp)
-{
-       unsigned int size = sk_filter_len(fp);
-
-       atomic_sub(size, &sk->sk_omem_alloc);
-       call_rcu_bh(&fp->rcu, sk_filter_rcu_release);
+       kfree(fp);
 }
+EXPORT_SYMBOL(sk_filter_release_rcu);
 
 /**
  *     sk_attach_filter - attach a socket filter
@@ -650,7 +643,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk)
        rcu_read_unlock_bh();
 
        if (old_fp)
-               sk_filter_delayed_uncharge(sk, old_fp);
+               sk_filter_uncharge(sk, old_fp);
        return 0;
 }
 EXPORT_SYMBOL_GPL(sk_attach_filter);
@@ -664,7 +657,7 @@ int sk_detach_filter(struct sock *sk)
        filter = rcu_dereference_bh(sk->sk_filter);
        if (filter) {
                rcu_assign_pointer(sk->sk_filter, NULL);
-               sk_filter_delayed_uncharge(sk, filter);
+               sk_filter_uncharge(sk, filter);
                ret = 0;
        }
        rcu_read_unlock_bh();