| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Thu, 29 Nov 2012 17:12:24 +0100
From: Jesper Dangaard Brouer <brouer@...hat.com>
To: Eric Dumazet <eric.dumazet@...il.com>,
"David S. Miller" <davem@...emloft.net>,
Florian Westphal <fw@...len.de>
Cc: Jesper Dangaard Brouer <brouer@...hat.com>, netdev@...r.kernel.org,
Pablo Neira Ayuso <pablo@...filter.org>,
Thomas Graf <tgraf@...g.ch>, Cong Wang <amwang@...hat.com>,
"Patrick McHardy" <kaber@...sh.net>,
"Paul E. McKenney" <paulmck@...ux.vnet.ibm.com>,
Herbert Xu <herbert@...dor.hengli.com.au>
Subject: [net-next PATCH V2 3/9] 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.
This change, in it self, does not improve performance significantly.
But its part of making the fragmentation code scale.
Original-idea-by: Florian Westphal <fw@...len.de>
Signed-off-by: Jesper Dangaard Brouer <brouer@...hat.com>
---
V2:
- Don't perform inet_frag_lru_move() outside the q.lock (inet_frag_queue)
Because there were a theoretical chance of a race between
inet_frag_lru_move() and fq_unlink() which is called under the
q.lock. I have not been able to provoke this though (it should
result in a list poison error)
include/net/inet_frag.h | 22 ++++++++++++++++++++++
net/ipv4/inet_fragment.c | 14 ++++++++------
net/ipv4/ip_fragment.c | 4 +---
net/ipv6/netfilter/nf_conntrack_reasm.c | 5 ++---
net/ipv6/reassembly.c | 4 +---
5 files changed, 34 insertions(+), 15 deletions(-)
diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h
index 1f75316..312a3fa 100644
--- a/include/net/inet_frag.h
+++ b/include/net/inet_frag.h
@@ -5,6 +5,7 @@ struct netns_frags {
int nqueues;
atomic_t mem;
struct list_head lru_list;
+ spinlock_t lru_lock;
/* sysctls */
int timeout;
@@ -73,4 +74,25 @@ static inline void inet_frag_put(struct inet_frag_queue *q, struct inet_frags *f
inet_frag_destroy(q, f, NULL);
}
+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 9bb6237..4e56587 100644
--- a/net/ipv4/inet_fragment.c
+++ b/net/ipv4/inet_fragment.c
@@ -75,6 +75,7 @@ void inet_frags_init_net(struct netns_frags *nf)
nf->nqueues = 0;
atomic_set(&nf->mem, 0);
INIT_LIST_HEAD(&nf->lru_list);
+ spin_lock_init(&nf->lru_lock);
}
EXPORT_SYMBOL(inet_frags_init_net);
@@ -98,9 +99,9 @@ static inline void fq_unlink(struct inet_frag_queue *fq, struct inet_frags *f)
{
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)
@@ -170,9 +171,10 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force)
work = atomic_read(&nf->mem) - 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;
}
@@ -186,12 +188,12 @@ int inet_frag_evictor(struct netns_frags *nf, struct inet_frags *f, bool force)
* completes.
*/
if (!force && q->creation_ts == (u32) jiffies) {
- read_unlock(&f->lock);
+ spin_unlock(&nf->lru_lock);
break;
}
atomic_inc(&q->refcnt);
- read_unlock(&f->lock);
+ spin_unlock(&nf->lru_lock);
spin_lock(&q->lock);
if (!(q->last_in & INET_FRAG_COMPLETE))
@@ -245,9 +247,9 @@ static struct inet_frag_queue *inet_frag_intern(struct netns_frags *nf,
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 ef00d0a..b2425bf 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -531,9 +531,7 @@ found:
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 22c8ea9..b0a1c96 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -325,9 +325,8 @@ found:
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 e5253ec..b373309 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -341,9 +341,7 @@ found:
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:
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists