Merge branch 'Refactor-classifier-API-to-work-with-Qdisc-blocks-without-rtnl-lock'

Vlad Buslov says:

====================
Refactor classifier API to work with Qdisc/blocks without rtnl lock

Currently, all netlink protocol handlers for updating rules, actions and
qdiscs are protected with single global rtnl lock which removes any
possibility for parallelism. This patch set is a third step to remove
rtnl lock dependency from TC rules update path.

Recently, new rtnl registration flag RTNL_FLAG_DOIT_UNLOCKED was added.
Handlers registered with this flag are called without RTNL taken. End
goal is to have rule update handlers(RTM_NEWTFILTER, RTM_DELTFILTER,
etc.) to be registered with UNLOCKED flag to allow parallel execution.
However, there is no intention to completely remove or split rtnl lock
itself. This patch set addresses specific problems in implementation of
classifiers API that prevent its control path from being executed
concurrently. Additional changes are required to refactor classifiers
API and individual classifiers for parallel execution. This patch set
lays groundwork to eventually register rule update handlers as
rtnl-unlocked by modifying code in cls API that works with Qdiscs and
blocks. Following patch set does the same for chains and classifiers.

The goal of this change is to refactor tcf_block_find() and its
dependencies to allow concurrent execution:
- Extend Qdisc API with rcu to lookup and take reference to Qdisc
  without relying on rtnl lock.
- Extend tcf_block with atomic reference counting and rcu.
- Always take reference to tcf_block while working with it.
- Implement tcf_block_release() to release resources obtained by
  tcf_block_find()
- Create infrastructure to allow registering Qdiscs with class ops that
  do not require the caller to hold rtnl lock.

All three netlink rule update handlers use tcf_block_find() to lookup
Qdisc and block, and this patch set introduces additional means of
synchronization to substitute rtnl lock in cls API.

Some functions in cls and sch APIs have historic names that no longer
clearly describe their intent. In order not make this code even more
confusing when introducing their concurrency-friendly versions, rename
these functions to describe actual implementation.

Changes from V2 to V3:
- Patch 1:
  - Explicitly include refcount.h in rtnetlink.h.
- Patch 3:
  - Move rcu_head field to the end of struct Qdisc.
  - Rearrange local variable declarations in qdisc_lookup_rcu().
- Patch 5:
  - Remove tcf_qdisc_put() and inline its content to callers.

Changes from V1 to V2:
- Rebase on latest net-next.
- Patch 8 - remove.
- Patch 9 - fold into patch 11.
- Patch 11:
  - Rename tcf_block_{get|put}() to tcf_block_refcnt_{get|put}().
- Patch 13 - remove.
====================

Acked-by: Cong Wang <xiyou.wangcong@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

Author: davem330

include/linux/rtnetlink.h

@@ -6,6 +6,7 @@
 #include <linux/mutex.h>
 #include <linux/netdevice.h>
 #include <linux/wait.h>
+#include <linux/refcount.h>
 #include <uapi/linux/rtnetlink.h>
 
 extern int rtnetlink_send(struct sk_buff *skb, struct net *net, u32 pid, u32 group, int echo);
@@ -34,6 +35,7 @@ extern void rtnl_unlock(void);
 extern int rtnl_trylock(void);
 extern int rtnl_is_locked(void);
 extern int rtnl_lock_killable(void);
+extern bool refcount_dec_and_rtnl_lock(refcount_t *r);
 
 extern wait_queue_head_t netdev_unregistering_wq;
 extern struct rw_semaphore pernet_ops_rwsem;
@@ -83,6 +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

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);

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)
@@ -114,6 +115,19 @@ static inline void qdisc_refcount_inc(struct Qdisc *qdisc)
 	refcount_inc(&qdisc->refcnt);
 }
 
+/* Intended to be used by unlocked users, when concurrent qdisc release is
+ * possible.
+ */
+
+static inline struct Qdisc *qdisc_refcount_inc_nz(struct Qdisc *qdisc)
+{
+	if (qdisc->flags & TCQ_F_BUILTIN)
+		return qdisc;
+	if (refcount_inc_not_zero(&qdisc->refcnt))
+		return qdisc;
+	return NULL;
+}
+
 static inline bool qdisc_is_running(struct Qdisc *qdisc)
 {
 	if (qdisc->flags & TCQ_F_NOLOCK)
@@ -331,7 +345,7 @@ struct tcf_chain {
 struct tcf_block {
 	struct list_head chain_list;
 	u32 index; /* block index for shared blocks */
-	unsigned int refcnt;
+	refcount_t refcnt;
 	struct net *net;
 	struct Qdisc *q;
 	struct list_head cb_list;
@@ -343,6 +357,7 @@ struct tcf_block {
 		struct tcf_chain *chain;
 		struct list_head filter_chain_list;
 	} chain0;
+	struct rcu_head rcu;
 };
 
 static inline void tcf_block_offload_inc(struct tcf_block *block, u32 *flags)
@@ -554,7 +569,8 @@ void dev_deactivate_many(struct list_head *head);
 struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue,
 			      struct Qdisc *qdisc);
 void qdisc_reset(struct Qdisc *qdisc);
-void qdisc_destroy(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,

net/core/rtnetlink.c

@@ -130,6 +130,12 @@ int rtnl_is_locked(void)
 }
 EXPORT_SYMBOL(rtnl_is_locked);
 
+bool refcount_dec_and_rtnl_lock(refcount_t *r)
+{
+	return refcount_dec_and_mutex_lock(r, &rtnl_mutex);
+}
+EXPORT_SYMBOL(refcount_dec_and_rtnl_lock);
+
 #ifdef CONFIG_PROVE_LOCKING
 bool lockdep_rtnl_is_held(void)
 {