net: sched: extend Qdisc with rcu

Currently, Qdisc API functions assume that users have rtnl lock taken. To
implement rtnl unlocked classifiers update interface, Qdisc API must be
extended with functions that do not require rtnl lock.

Extend Qdisc structure with rcu. Implement special version of put function
qdisc_put_unlocked() that is called without rtnl lock taken. This function
only takes rtnl lock if Qdisc reference counter reached zero and is
intended to be used as optimization.

Signed-off-by: Vlad Buslov <vladbu@mellanox.com>
Acked-by: Jiri Pirko <jiri@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h
index 9cdd76348d9ab8849ea712b95d2d02a3ded0283d..bb9cb84114c151059ccac74ca07a113ea22c347a 100644 (file)
--- a/include/linux/rtnetlink.h
+++ b/include/linux/rtnetlink.h
@@ -85,6 +85,11 @@ static inline struct netdev_queue *dev_ingress_queue(struct net_device *dev)
        return rtnl_dereference(dev->ingress_queue);
 }
 
+static inline struct netdev_queue *dev_ingress_queue_rcu(struct net_device *dev)
+{
+       return rcu_dereference(dev->ingress_queue);
+}
+
 struct netdev_queue *dev_ingress_queue_create(struct net_device *dev);
 
 #ifdef CONFIG_NET_INGRESS

diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 7dc769e5452ba6e5eaa92f10808bf2cbfb1d152a..a16fbe9a2a6755e98cf4bf3477a49496d62de9a1 100644 (file)
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -102,6 +102,7 @@ int qdisc_set_default(const char *id);
 void qdisc_hash_add(struct Qdisc *q, bool invisible);
 void qdisc_hash_del(struct Qdisc *q);
 struct Qdisc *qdisc_lookup(struct net_device *dev, u32 handle);
+struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle);
 struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r,
                                        struct nlattr *tab,
                                        struct netlink_ext_ack *extack);

diff --git a/include/net/sch_generic.h b/include/net/sch_generic.h
index fadb1a4d4ee803fdab5cde4871e266c3888a5329..091b40c198ff8a7d80bc6178fce60bb64a16d9e8 100644 (file)
--- a/include/net/sch_generic.h
+++ b/include/net/sch_generic.h
@@ -105,6 +105,7 @@ struct Qdisc {
 
        spinlock_t              busylock ____cacheline_aligned_in_smp;
        spinlock_t              seqlock;
+       struct rcu_head         rcu;
 };
 
 static inline void qdisc_refcount_inc(struct Qdisc *qdisc)
@@ -555,6 +556,7 @@ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
                              struct Qdisc *qdisc);
 void qdisc_reset(struct Qdisc *qdisc);
 void qdisc_put(struct Qdisc *qdisc);
+void qdisc_put_unlocked(struct Qdisc *qdisc);
 void qdisc_tree_reduce_backlog(struct Qdisc *qdisc, unsigned int n,
                               unsigned int len);
 struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue,

diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 2096138c4bf6f7cc1c423bbd5dec7f8ddba88fab..22e9799e5b697f45baee7f1a334ed2ff719c5563 100644 (file)
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -314,6 +314,24 @@ out:
        return q;
 }
 
+struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle)
+{
+       struct netdev_queue *nq;
+       struct Qdisc *q;
+
+       if (!handle)
+               return NULL;
+       q = qdisc_match_from_root(dev->qdisc, handle);
+       if (q)
+               goto out;
+
+       nq = dev_ingress_queue_rcu(dev);
+       if (nq)
+               q = qdisc_match_from_root(nq->qdisc_sleeping, handle);
+out:
+       return q;
+}
+
 static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid)
 {
        unsigned long cl;

diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 3e7696f3e05392d37845a18ef6cbebfd7f93c757..531fac1d287541f76571e5a1b811716321ca289b 100644 (file)
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -941,6 +941,13 @@ void qdisc_free(struct Qdisc *qdisc)
        kfree((char *) qdisc - qdisc->padded);
 }
 
+void qdisc_free_cb(struct rcu_head *head)
+{
+       struct Qdisc *q = container_of(head, struct Qdisc, rcu);
+
+       qdisc_free(q);
+}
+
 static void qdisc_destroy(struct Qdisc *qdisc)
 {
        const struct Qdisc_ops  *ops = qdisc->ops;
@@ -970,7 +977,7 @@ static void qdisc_destroy(struct Qdisc *qdisc)
                kfree_skb_list(skb);
        }
 
-       qdisc_free(qdisc);
+       call_rcu(&qdisc->rcu, qdisc_free_cb);
 }
 
 void qdisc_put(struct Qdisc *qdisc)
@@ -983,6 +990,22 @@ void qdisc_put(struct Qdisc *qdisc)
 }
 EXPORT_SYMBOL(qdisc_put);
 
+/* Version of qdisc_put() that is called with rtnl mutex unlocked.
+ * Intended to be used as optimization, this function only takes rtnl lock if
+ * qdisc reference counter reached zero.
+ */
+
+void qdisc_put_unlocked(struct Qdisc *qdisc)
+{
+       if (qdisc->flags & TCQ_F_BUILTIN ||
+           !refcount_dec_and_rtnl_lock(&qdisc->refcnt))
+               return;
+
+       qdisc_destroy(qdisc);
+       rtnl_unlock();
+}
+EXPORT_SYMBOL(qdisc_put_unlocked);
+
 /* Attach toplevel qdisc to device queue. */
 struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
                              struct Qdisc *qdisc)