net: sched: use Qdisc rcu API instead of relying on rtnl lock
As a preparation from removing rtnl lock dependency from rules update path,
use Qdisc rcu and reference counting capabilities instead of relying on
rtnl lock while working with Qdiscs. Create new tcf_block_release()
function, and use it to free resources taken by tcf_block_find().
Currently, this function only releases Qdisc and it is extended in next
patches in this series.
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/net/sched/cls_api.c b/net/sched/cls_api.c
index 0a75cb2..c33636e 100644
--- a/net/sched/cls_api.c
+++ b/net/sched/cls_api.c
@@ -537,6 +537,7 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
struct netlink_ext_ack *extack)
{
struct tcf_block *block;
+ int err = 0;
if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) {
block = tcf_block_lookup(net, block_index);
@@ -548,55 +549,93 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q,
const struct Qdisc_class_ops *cops;
struct net_device *dev;
+ rcu_read_lock();
+
/* Find link */
- dev = __dev_get_by_index(net, ifindex);
- if (!dev)
+ dev = dev_get_by_index_rcu(net, ifindex);
+ if (!dev) {
+ rcu_read_unlock();
return ERR_PTR(-ENODEV);
+ }
/* Find qdisc */
if (!*parent) {
*q = dev->qdisc;
*parent = (*q)->handle;
} else {
- *q = qdisc_lookup(dev, TC_H_MAJ(*parent));
+ *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent));
if (!*q) {
NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
- return ERR_PTR(-EINVAL);
+ err = -EINVAL;
+ goto errout_rcu;
}
}
+ *q = qdisc_refcount_inc_nz(*q);
+ if (!*q) {
+ NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists");
+ err = -EINVAL;
+ goto errout_rcu;
+ }
+
/* Is it classful? */
cops = (*q)->ops->cl_ops;
if (!cops) {
NL_SET_ERR_MSG(extack, "Qdisc not classful");
- return ERR_PTR(-EINVAL);
+ err = -EINVAL;
+ goto errout_rcu;
}
if (!cops->tcf_block) {
NL_SET_ERR_MSG(extack, "Class doesn't support blocks");
- return ERR_PTR(-EOPNOTSUPP);
+ err = -EOPNOTSUPP;
+ goto errout_rcu;
}
+ /* At this point we know that qdisc is not noop_qdisc,
+ * which means that qdisc holds a reference to net_device
+ * and we hold a reference to qdisc, so it is safe to release
+ * rcu read lock.
+ */
+ rcu_read_unlock();
+
/* Do we search for filter, attached to class? */
if (TC_H_MIN(*parent)) {
*cl = cops->find(*q, *parent);
if (*cl == 0) {
NL_SET_ERR_MSG(extack, "Specified class doesn't exist");
- return ERR_PTR(-ENOENT);
+ err = -ENOENT;
+ goto errout_qdisc;
}
}
/* And the last stroke */
block = cops->tcf_block(*q, *cl, extack);
- if (!block)
- return ERR_PTR(-EINVAL);
+ if (!block) {
+ err = -EINVAL;
+ goto errout_qdisc;
+ }
if (tcf_block_shared(block)) {
NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters");
- return ERR_PTR(-EOPNOTSUPP);
+ err = -EOPNOTSUPP;
+ goto errout_qdisc;
}
}
return block;
+
+errout_rcu:
+ rcu_read_unlock();
+errout_qdisc:
+ if (*q)
+ qdisc_put(*q);
+ return ERR_PTR(err);
+}
+
+static void tcf_block_release(struct Qdisc *q, struct tcf_block *block)
+{
+ if (q)
+ qdisc_put(q);
}
struct tcf_block_owner_item {
@@ -1332,6 +1371,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
errout:
if (chain)
tcf_chain_put(chain);
+ tcf_block_release(q, block);
if (err == -EAGAIN)
/* Replay the request. */
goto replay;
@@ -1453,6 +1493,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
errout:
if (chain)
tcf_chain_put(chain);
+ tcf_block_release(q, block);
return err;
}
@@ -1538,6 +1579,7 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n,
errout:
if (chain)
tcf_chain_put(chain);
+ tcf_block_release(q, block);
return err;
}
@@ -1854,7 +1896,8 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0;
if (chain_index > TC_ACT_EXT_VAL_MASK) {
NL_SET_ERR_MSG(extack, "Specified chain index exceeds upper limit");
- return -EINVAL;
+ err = -EINVAL;
+ goto errout_block;
}
chain = tcf_chain_lookup(block, chain_index);
if (n->nlmsg_type == RTM_NEWCHAIN) {
@@ -1866,23 +1909,27 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
tcf_chain_hold(chain);
} else {
NL_SET_ERR_MSG(extack, "Filter chain already exists");
- return -EEXIST;
+ err = -EEXIST;
+ goto errout_block;
}
} else {
if (!(n->nlmsg_flags & NLM_F_CREATE)) {
NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain");
- return -ENOENT;
+ err = -ENOENT;
+ goto errout_block;
}
chain = tcf_chain_create(block, chain_index);
if (!chain) {
NL_SET_ERR_MSG(extack, "Failed to create filter chain");
- return -ENOMEM;
+ err = -ENOMEM;
+ goto errout_block;
}
}
} else {
if (!chain || tcf_chain_held_by_acts_only(chain)) {
NL_SET_ERR_MSG(extack, "Cannot find specified filter chain");
- return -EINVAL;
+ err = -EINVAL;
+ goto errout_block;
}
tcf_chain_hold(chain);
}
@@ -1926,6 +1973,8 @@ static int tc_ctl_chain(struct sk_buff *skb, struct nlmsghdr *n,
errout:
tcf_chain_put(chain);
+errout_block:
+ tcf_block_release(q, block);
if (err == -EAGAIN)
/* Replay the request. */
goto replay;