inet: frag: don't re-use chainlist for evictor

commit 65ba1f1ec0eff ("inet: frags: fix a race between inet_evict_bucket
and inet_frag_kill") describes the bug, but the fix doesn't work reliably.

Problem is that ->flags member can be set on other cpu without chainlock
being held by that task, i.e. the RMW-Cycle can clear INET_FRAG_EVICTED
bit after we put the element on the evictor private list.

We can crash when walking the 'private' evictor list since an element can
be deleted from list underneath the evictor.

Join work with Nikolay Alexandrov.

Fixes: b13d3cbfb8e8 ("inet: frag: move eviction of queues to work queue")
Reported-by: Johan Schuijt <johan@transip.nl>
Tested-by: Frank Schreuder <fschreuder@transip.nl>
Signed-off-by: Nikolay Alexandrov <nikolay@cumulusnetworks.com>
Signed-off-by: Florian Westphal <fw@strlen.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index e1300b3dd597b9a68db7b6dc9c03a8ea238b4e4c..56a3a5685f76793318781415b3e6f591e7114af7 100644 (file)
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -45,6 +45,7 @@ enum {
  * @flags: fragment queue flags
  * @max_size: maximum received fragment size
  * @net: namespace that this frag belongs to
+ * @list_evictor: list of queues to forcefully evict (e.g. due to low memory)
  */
 struct inet_frag_queue {
        spinlock_t              lock;
@@ -59,6 +60,7 @@ struct inet_frag_queue {
        __u8                    flags;
        u16                     max_size;
        struct netns_frags      *net;
+       struct hlist_node       list_evictor;
 };
 
 #define INETFRAGS_HASHSZ       1024

diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index 5e346a082e5ff05b58cfebb64917ee26001d809d..172234864fec73801b639d68d1dbe634f3892c43 100644 (file)
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -151,14 +151,13 @@ evict_again:
                }
 
                fq->flags |= INET_FRAG_EVICTED;
-               hlist_del(&fq->list);
-               hlist_add_head(&fq->list, &expired);
+               hlist_add_head(&fq->list_evictor, &expired);
                ++evicted;
        }
 
        spin_unlock(&hb->chain_lock);
 
-       hlist_for_each_entry_safe(fq, n, &expired, list)
+       hlist_for_each_entry_safe(fq, n, &expired, list_evictor)
                f->frag_expire((unsigned long) fq);
 
        return evicted;
@@ -284,8 +283,7 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
        struct inet_frag_bucket *hb;
 
        hb = get_frag_bucket_locked(fq, f);
-       if (!(fq->flags & INET_FRAG_EVICTED))
-               hlist_del(&fq->list);
+       hlist_del(&fq->list);
        spin_unlock(&hb->chain_lock);
 }