Re: [PATCH 08/17] net: convert sk_filter.refcnt from atomic_t to refcount_t

[Daniel Borkmann]

On 03/16/2017 04:28 PM, Elena Reshetova wrote:

refcount_t type and corresponding API should be
used instead of atomic_t when the variable is used as
a reference counter. This allows to avoid accidental
refcounter overflows that might lead to use-after-free
situations.

Signed-off-by: Elena Reshetova <elena.reshet...@intel.com>
Signed-off-by: Hans Liljestrand <ishkam...@gmail.com>
Signed-off-by: Kees Cook <keesc...@chromium.org>
Signed-off-by: David Windsor <dwind...@gmail.com>
---
  include/linux/filter.h | 3 ++-
  net/core/filter.c      | 7 ++++---
  2 files changed, 6 insertions(+), 4 deletions(-)

diff --git a/include/linux/filter.h b/include/linux/filter.h
index 8053c38..20247e7 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -7,6 +7,7 @@
  #include <stdarg.h>

  #include <linux/atomic.h>
+#include <linux/refcount.h>
  #include <linux/compat.h>
  #include <linux/skbuff.h>
  #include <linux/linkage.h>
@@ -431,7 +432,7 @@ struct bpf_prog {
  };

  struct sk_filter {
-       atomic_t        refcnt;
+       refcount_t      refcnt;
        struct rcu_head rcu;
        struct bpf_prog *prog;
  };
diff --git a/net/core/filter.c b/net/core/filter.c
index ebaeaf2..62267e2 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -928,7 +928,7 @@ static void sk_filter_release_rcu(struct rcu_head *rcu)
   */
  static void sk_filter_release(struct sk_filter *fp)
  {
-       if (atomic_dec_and_test(&fp->refcnt))
+       if (refcount_dec_and_test(&fp->refcnt))
                call_rcu(&fp->rcu, sk_filter_release_rcu);
  }

@@ -950,7 +950,7 @@ bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
        /* same check as in sock_kmalloc() */
        if (filter_size <= sysctl_optmem_max &&
            atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
-               atomic_inc(&fp->refcnt);
+               refcount_inc(&fp->refcnt);
                atomic_add(filter_size, &sk->sk_omem_alloc);
                return true;
        }
@@ -1179,12 +1179,13 @@ static int __sk_attach_prog(struct bpf_prog *prog, 
struct sock *sk)
                return -ENOMEM;

        fp->prog = prog;
-       atomic_set(&fp->refcnt, 0);
+       refcount_set(&fp->refcnt, 1);

        if (!sk_filter_charge(sk, fp)) {
                kfree(fp);
                return -ENOMEM;
        }
+       refcount_set(&fp->refcnt, 1);

Regarding the two subsequent refcount_set(, 1) that look a bit strange
due to the sk_filter_charge() having refcount_inc() I presume ... can't
the refcount API handle such corner case? Or alternatively the let the
sk_filter_charge() handle it, for example:

bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp)
{
        u32 filter_size = bpf_prog_size(fp->prog->len);

        /* same check as in sock_kmalloc() */
        if (filter_size <= sysctl_optmem_max &&
            atomic_read(&sk->sk_omem_alloc) + filter_size < sysctl_optmem_max) {
                atomic_add(filter_size, &sk->sk_omem_alloc);
                return true;
        }
        return false;
}

And this goes to filter.h:

bool __sk_filter_charge(struct sock *sk, struct sk_filter *fp);

bool sk_filter_charge(struct sock *sk, struct sk_filter *fp)
{
        bool ret = __sk_filter_charge(sk, fp);
        if (ret)
                refcount_inc(&fp->refcnt);
        return ret;
}

... and let __sk_attach_prog() call __sk_filter_charge() and only fo
the second refcount_set()?

        old_fp = rcu_dereference_protected(sk->sk_filter,
                                           lockdep_sock_is_held(sk));