net: frag, move LRU list maintenance outside of rwlock
Updating the fragmentation queues LRU (Least-Recently-Used) list,
required taking the hash writer lock. However, the LRU list isn't
tied to the hash at all, so we can use a separate lock for it.
Original-idea-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Jesper Dangaard Brouer <brouer@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index e0eec74..3f237db 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -6,6 +6,7 @@
struct netns_frags {
int nqueues;
struct list_head lru_list;
+ spinlock_t lru_lock;
/* The percpu_counter "mem" need to be cacheline aligned.
* mem.count must not share cacheline with other writers
@@ -116,4 +117,25 @@
return percpu_counter_sum_positive(&nf->mem);
}
+static inline void inet_frag_lru_move(struct inet_frag_queue *q)
+{
+ spin_lock(&q->net->lru_lock);
+ list_move_tail(&q->lru_list, &q->net->lru_list);
+ spin_unlock(&q->net->lru_lock);
+}
+
+static inline void inet_frag_lru_del(struct inet_frag_queue *q)
+{
+ spin_lock(&q->net->lru_lock);
+ list_del(&q->lru_list);
+ spin_unlock(&q->net->lru_lock);
+}
+
+static inline void inet_frag_lru_add(struct netns_frags *nf,
+ struct inet_frag_queue *q)
+{
+ spin_lock(&nf->lru_lock);
+ list_add_tail(&q->lru_list, &nf->lru_list);
+ spin_unlock(&nf->lru_lock);
+}
#endif
diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c
index b825205..2e453bd 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -75,6 +75,7 @@
nf->nqueues = 0;
init_frag_mem_limit(nf);
INIT_LIST_HEAD(&nf->lru_list);
+ spin_lock_init(&nf->lru_lock);
}
EXPORT_SYMBOL(inet_frags_init_net);
@@ -100,9 +101,9 @@
{
write_lock(&f->lock);
hlist_del(&fq->list);
- list_del(&fq->lru_list);
fq->net->nqueues--;
write_unlock(&f->lock);
+ inet_frag_lru_del(fq);
}
void inet_frag_kill(struct inet_frag_queue *fq, struct inet_frags *f)
@@ -170,16 +171,17 @@
work = frag_mem_limit(nf) - nf->low_thresh;
while (work > 0) {
- read_lock(&f->lock);
+ spin_lock(&nf->lru_lock);
+
if (list_empty(&nf->lru_list)) {
- read_unlock(&f->lock);
+ spin_unlock(&nf->lru_lock);
break;
}
q = list_first_entry(&nf->lru_list,
struct inet_frag_queue, lru_list);
atomic_inc(&q->refcnt);
- read_unlock(&f->lock);
+ spin_unlock(&nf->lru_lock);
spin_lock(&q->lock);
if (!(q->last_in & INET_FRAG_COMPLETE))
@@ -233,9 +235,9 @@
atomic_inc(&qp->refcnt);
hlist_add_head(&qp->list, &f->hash[hash]);
- list_add_tail(&qp->lru_list, &nf->lru_list);
nf->nqueues++;
write_unlock(&f->lock);
+ inet_frag_lru_add(nf, qp);
return qp;
}
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 927fe58..1211613 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -529,9 +529,7 @@
qp->q.meat == qp->q.len)
return ip_frag_reasm(qp, prev, dev);
- write_lock(&ip4_frags.lock);
- list_move_tail(&qp->q.lru_list, &qp->q.net->lru_list);
- write_unlock(&ip4_frags.lock);
+ inet_frag_lru_move(&qp->q);
return -EINPROGRESS;
err:
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index 07ef294..c674f15 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -328,9 +328,8 @@
fq->nhoffset = nhoff;
fq->q.last_in |= INET_FRAG_FIRST_IN;
}
- write_lock(&nf_frags.lock);
- list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list);
- write_unlock(&nf_frags.lock);
+
+ inet_frag_lru_move(&fq->q);
return 0;
discard_fq:
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 18cb8de..bab2c27 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -341,9 +341,7 @@
fq->q.meat == fq->q.len)
return ip6_frag_reasm(fq, prev, dev);
- write_lock(&ip6_frags.lock);
- list_move_tail(&fq->q.lru_list, &fq->q.net->lru_list);
- write_unlock(&ip6_frags.lock);
+ inet_frag_lru_move(&fq->q);
return -1;
discard_fq: