inet: frags: remove INET_FRAG_EVICTED and use list_evictor for the test

We can simply remove the INET_FRAG_EVICTED flag to avoid all the flags
race conditions with the evictor and use a participation test for the
evictor list, when we're at that point (after inet_frag_kill) in the
timer there're 2 possible cases:

1. The evictor added the entry to its evictor list while the timer was
waiting for the chainlock
or
2. The timer unchained the entry and the evictor won't see it

In both cases we should be able to see list_evictor correctly due
to the sync on the chainlock.

Joint work with Florian Westphal.

Tested-by: Frank Schreuder <fschreuder@transip.nl>
Signed-off-by: Nikolay Aleksandrov <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 e71ca17024f2d55fb607759475031319c6a6c2df..53eead2da74324b47ef8c772663f9bcb4fd1d0e1 100644 (file)
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -21,13 +21,11 @@ struct netns_frags {
  * @INET_FRAG_FIRST_IN: first fragment has arrived
  * @INET_FRAG_LAST_IN: final fragment has arrived
  * @INET_FRAG_COMPLETE: frag queue has been processed and is due for destruction
- * @INET_FRAG_EVICTED: frag queue is being evicted
  */
 enum {
        INET_FRAG_FIRST_IN      = BIT(0),
        INET_FRAG_LAST_IN       = BIT(1),
        INET_FRAG_COMPLETE      = BIT(2),
-       INET_FRAG_EVICTED       = BIT(3)
 };
 
 /**
@@ -127,6 +125,11 @@ static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f
                inet_frag_destroy(q, f);
 }
 
+static inline bool inet_frag_evicting(struct inet_frag_queue *q)
+{
+       return !hlist_unhashed(&q->list_evictor);
+}
+
 /* Memory Tracking Functions. */
 
 /* The default percpu_counter batch size is not big enough to scale to

diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index a00ca4c00c3576e63fae319f4cc3f2e7056bb371..d0a7c0319e3d1b1b73f828717062b6fbbd3be27d 100644 (file)
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -140,7 +140,6 @@ inet_evict_bucket(struct inet_frags *f, struct inet_frag_bucket *hb)
                if (!del_timer(&fq->timer))
                        continue;
 
-               fq->flags |= INET_FRAG_EVICTED;
                hlist_add_head(&fq->list_evictor, &expired);
                ++evicted;
        }

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b4a77d021c0d3c49dba1f25d6cb1c629c28537b4..921138f6c97c9948a7cf5e2e36b7e3dbfabc6e29 100644 (file)
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -202,7 +202,7 @@ static void ip_expire(unsigned long arg)
        ipq_kill(qp);
        IP_INC_STATS_BH(net, IPSTATS_MIB_REASMFAILS);
 
-       if (!(qp->q.flags & INET_FRAG_EVICTED)) {
+       if (!inet_frag_evicting(&qp->q)) {
                struct sk_buff *head = qp->q.fragments;
                const struct iphdr *iph;
                int err;

diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 5c3bbca6a15047e7627b2a7ebf59bb11827304b9..f1159bb76e0a54fb55a3e8e382a6cb80c7a929f9 100644 (file)
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -144,7 +144,7 @@ void ip6_expire_frag_queue(struct net *net, struct frag_queue *fq,
 
        IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS);
 
-       if (fq->q.flags & INET_FRAG_EVICTED)
+       if (inet_frag_evicting(&fq->q))
                goto out_rcu_unlock;
 
        IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT);