[PATCH net-next v2 00/12] net: sched: cls_u32 Various improvements

[PATCH net-next v2 00/12] net: sched: cls_u32 Various improvements

[Jamal Hadi Salim]

From: Jamal Hadi Salim <hadi@mojatatu.com>

Various improvements from Al.

Changes from version 1: Add missing commit 

Al Viro (11):
  net: sched: cls_u32: mark root hnode explicitly
  net: sched: cls_u32: disallow linking to root hnode
  net: sched: cls_u32: make sure that divisor is a power of 2
  net: sched: cls_u32: get rid of unused argument of u32_destroy_key()
  net: sched: cls_u32: get rid of tc_u_knode ->tp
  net: sched: cls_u32: get rid of tc_u_common ->rcu
  net: sched: cls_u32: clean tc_u_common hashtable
  net: sched: cls_u32: pass tc_u_common to u32_set_parms() instead of
    tc_u_hnode
  net: sched: cls_u32: the tp_c argument of u32_set_parms() is always
    tp->data
  net: sched: cls_u32: get rid of tp_c
  net: sched: cls_u32: keep track of knodes count in tc_u_common
  net: sched: cls_u32: simplify the hell out u32_delete() emptiness
    check

 net/sched/cls_u32.c | 121 +++++++++++++++++-----------------------------------
 1 file changed, 38 insertions(+), 83 deletions(-)

-- 
2.11.0

[PATCH net-next v2 01/12] net: sched: cls_u32: mark root hnode explicitly

[Jamal Hadi Salim]

From: Al Viro <viro@zeniv.linux.org.uk>

... and produce consistent error on attempt to delete such.
Existing check in u32_delete() is inconsistent - after

tc qdisc add dev eth0 ingress
tc filter add dev eth0 parent ffff: protocol ip prio 100 handle 1: u32 \
divisor 1
tc filter add dev eth0 parent ffff: protocol ip prio 200 handle 2: u32 \
divisor 1

both

tc filter delete dev eth0 parent ffff: protocol ip prio 100 handle 801: u32

and

tc filter delete dev eth0 parent ffff: protocol ip prio 100 handle 800: u32

will fail (at least with refcounting fixes), but the former will complain
about an attempt to remove a busy table, while the latter will recognize
it as root and yield "Not allowed to delete root node" instead.

The problem with the existing check is that several tcf_proto instances
might share the same tp->data and handle-to-hnode lookup will be the same
for all of them. So comparing an hnode to be deleted with tp->root won't
catch the case when one tp is used to try deleting the root of another.
Solution is trivial - mark the root hnodes explicitly upon allocation and
check for that.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
 net/sched/cls_u32.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index f218ccf1e2d9..622f4657da94 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -84,6 +84,7 @@ struct tc_u_hnode {
 	int			refcnt;
 	unsigned int		divisor;
 	struct idr		handle_idr;
+	bool			is_root;
 	struct rcu_head		rcu;
 	u32			flags;
 	/* The 'ht' field MUST be the last field in structure to allow for
@@ -377,6 +378,7 @@ static int u32_init(struct tcf_proto *tp)
 	root_ht->refcnt++;
 	root_ht->handle = tp_c ? gen_new_htid(tp_c, root_ht) : 0x80000000;
 	root_ht->prio = tp->prio;
+	root_ht->is_root = true;
 	idr_init(&root_ht->handle_idr);
 
 	if (tp_c == NULL) {
@@ -692,7 +694,7 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last,
 		goto out;
 	}
 
-	if (root_ht == ht) {
+	if (ht->is_root) {
 		NL_SET_ERR_MSG_MOD(extack, "Not allowed to delete root node");
 		return -EINVAL;
 	}
-- 
2.11.0

[PATCH net-next v2 02/12] net: sched: cls_u32: disallow linking to root hnode

[Jamal Hadi Salim]

From: Al Viro <viro@zeniv.linux.org.uk>

Operation makes no sense.  Nothing will actually break if we do so
(depth limit in u32_classify() will prevent infinite loops), but
according to maintainers it's best prohibited outright.

NOTE: doing so guarantees that u32_destroy() will trigger the call
of u32_destroy_hnode(); we might want to make that unconditional.

Test:
tc qdisc add dev eth0 ingress
tc filter add dev eth0 parent ffff: protocol ip prio 100 u32 \
link 800: offset at 0 mask 0f00 shift 6 plus 0 eat match ip protocol 6 ff
should fail with
Error: cls_u32: Not linking to root node

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
 net/sched/cls_u32.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 622f4657da94..3357331a80a2 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -797,6 +797,10 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
 				NL_SET_ERR_MSG_MOD(extack, "Link hash table not found");
 				return -EINVAL;
 			}
+			if (ht_down->is_root) {
+				NL_SET_ERR_MSG_MOD(extack, "Not linking to root node");
+				return -EINVAL;
+			}
 			ht_down->refcnt++;
 		}
 
-- 
2.11.0

[PATCH net-next v2 03/12] net: sched: cls_u32: make sure that divisor is a power of 2

[Jamal Hadi Salim]

From: Al Viro <viro@zeniv.linux.org.uk>

Tested by modifying iproute2 to allow sending a divisor > 255

Tested-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
 net/sched/cls_u32.c | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 3357331a80a2..ce55eea448a0 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -994,7 +994,11 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	if (tb[TCA_U32_DIVISOR]) {
 		unsigned int divisor = nla_get_u32(tb[TCA_U32_DIVISOR]);
 
-		if (--divisor > 0x100) {
+		if (!is_power_of_2(divisor)) {
+			NL_SET_ERR_MSG_MOD(extack, "Divisor is not a power of 2");
+			return -EINVAL;
+		}
+		if (divisor-- > 0x100) {
 			NL_SET_ERR_MSG_MOD(extack, "Exceeded maximum 256 hash buckets");
 			return -EINVAL;
 		}
-- 
2.11.0

[PATCH net-next v2 04/12] net: sched: cls_u32: get rid of unused argument of u32_destroy_key()

[Jamal Hadi Salim]

From: Al Viro <viro@zeniv.linux.org.uk>

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
 net/sched/cls_u32.c | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index ce55eea448a0..ef0f2e6ec422 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -405,8 +405,7 @@ static int u32_init(struct tcf_proto *tp)
 	return 0;
 }
 
-static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n,
-			   bool free_pf)
+static int u32_destroy_key(struct tc_u_knode *n, bool free_pf)
 {
 	struct tc_u_hnode *ht = rtnl_dereference(n->ht_down);
 
@@ -440,7 +439,7 @@ static void u32_delete_key_work(struct work_struct *work)
 					      struct tc_u_knode,
 					      rwork);
 	rtnl_lock();
-	u32_destroy_key(key->tp, key, false);
+	u32_destroy_key(key, false);
 	rtnl_unlock();
 }
 
@@ -457,7 +456,7 @@ static void u32_delete_key_freepf_work(struct work_struct *work)
 					      struct tc_u_knode,
 					      rwork);
 	rtnl_lock();
-	u32_destroy_key(key->tp, key, true);
+	u32_destroy_key(key, true);
 	rtnl_unlock();
 }
 
@@ -600,7 +599,7 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
 			if (tcf_exts_get_net(&n->exts))
 				tcf_queue_work(&n->rwork, u32_delete_key_freepf_work);
 			else
-				u32_destroy_key(n->tp, n, true);
+				u32_destroy_key(n, true);
 		}
 	}
 }
@@ -971,13 +970,13 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 				    tca[TCA_RATE], ovr, extack);
 
 		if (err) {
-			u32_destroy_key(tp, new, false);
+			u32_destroy_key(new, false);
 			return err;
 		}
 
 		err = u32_replace_hw_knode(tp, new, flags, extack);
 		if (err) {
-			u32_destroy_key(tp, new, false);
+			u32_destroy_key(new, false);
 			return err;
 		}
 
-- 
2.11.0

[PATCH net-next v2 05/12] net: sched: cls_u32: get rid of tc_u_knode ->tp

[Jamal Hadi Salim]

From: Al Viro <viro@zeniv.linux.org.uk>

not used anymore

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
 net/sched/cls_u32.c | 3 ---
 1 file changed, 3 deletions(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index ef0f2e6ec422..810c49ac1bbe 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -68,7 +68,6 @@ struct tc_u_knode {
 	u32			mask;
 	u32 __percpu		*pcpu_success;
 #endif
-	struct tcf_proto	*tp;
 	struct rcu_work		rwork;
 	/* The 'sel' field MUST be the last field in structure to allow for
 	 * tc_u32_keys allocated at end of structure.
@@ -896,7 +895,6 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp,
 	/* Similarly success statistics must be moved as pointers */
 	new->pcpu_success = n->pcpu_success;
 #endif
-	new->tp = tp;
 	memcpy(&new->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key));
 
 	if (tcf_exts_init(&new->exts, TCA_U32_ACT, TCA_U32_POLICE)) {
@@ -1112,7 +1110,6 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	n->handle = handle;
 	n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0;
 	n->flags = flags;
-	n->tp = tp;
 
 	err = tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE);
 	if (err < 0)
-- 
2.11.0

[PATCH net-next v2 06/12] net: sched: cls_u32: get rid of tc_u_common ->rcu

[Jamal Hadi Salim]

From: Al Viro <viro@zeniv.linux.org.uk>

unused

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
 net/sched/cls_u32.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 810c49ac1bbe..c378168f4562 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -98,7 +98,6 @@ struct tc_u_common {
 	int			refcnt;
 	struct idr		handle_idr;
 	struct hlist_node	hnode;
-	struct rcu_head		rcu;
 };
 
 static inline unsigned int u32_hash_fold(__be32 key,
-- 
2.11.0

[PATCH net-next v2 07/12] net: sched: cls_u32: clean tc_u_common hashtable

[Jamal Hadi Salim]

From: Al Viro <viro@zeniv.linux.org.uk>

* calculate key *once*, not for each hash chain element
* let tc_u_hash() return the pointer to chain head rather than index -
callers are cleaner that way.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
 net/sched/cls_u32.c | 24 +++++++++---------------
 1 file changed, 9 insertions(+), 15 deletions(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index c378168f4562..3f6fba831c57 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -343,19 +343,16 @@ static void *tc_u_common_ptr(const struct tcf_proto *tp)
 		return block->q;
 }
 
-static unsigned int tc_u_hash(const struct tcf_proto *tp)
+static struct hlist_head *tc_u_hash(void *key)
 {
-	return hash_ptr(tc_u_common_ptr(tp), U32_HASH_SHIFT);
+	return tc_u_common_hash + hash_ptr(key, U32_HASH_SHIFT);
 }
 
-static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp)
+static struct tc_u_common *tc_u_common_find(void *key)
 {
 	struct tc_u_common *tc;
-	unsigned int h;
-
-	h = tc_u_hash(tp);
-	hlist_for_each_entry(tc, &tc_u_common_hash[h], hnode) {
-		if (tc->ptr == tc_u_common_ptr(tp))
+	hlist_for_each_entry(tc, tc_u_hash(key), hnode) {
+		if (tc->ptr == key)
 			return tc;
 	}
 	return NULL;
@@ -364,10 +361,8 @@ static struct tc_u_common *tc_u_common_find(const struct tcf_proto *tp)
 static int u32_init(struct tcf_proto *tp)
 {
 	struct tc_u_hnode *root_ht;
-	struct tc_u_common *tp_c;
-	unsigned int h;
-
-	tp_c = tc_u_common_find(tp);
+	void *key = tc_u_common_ptr(tp);
+	struct tc_u_common *tp_c = tc_u_common_find(key);
 
 	root_ht = kzalloc(sizeof(*root_ht), GFP_KERNEL);
 	if (root_ht == NULL)
@@ -385,12 +380,11 @@ static int u32_init(struct tcf_proto *tp)
 			kfree(root_ht);
 			return -ENOBUFS;
 		}
-		tp_c->ptr = tc_u_common_ptr(tp);
+		tp_c->ptr = key;
 		INIT_HLIST_NODE(&tp_c->hnode);
 		idr_init(&tp_c->handle_idr);
 
-		h = tc_u_hash(tp);
-		hlist_add_head(&tp_c->hnode, &tc_u_common_hash[h]);
+		hlist_add_head(&tp_c->hnode, tc_u_hash(key));
 	}
 
 	tp_c->refcnt++;
-- 
2.11.0

[PATCH net-next v2 08/12] net: sched: cls_u32: pass tc_u_common to u32_set_parms() instead of tc_u_hnode

[Jamal Hadi Salim]

From: Al Viro <viro@zeniv.linux.org.uk>

the only thing we used ht for was ht->tp_c and callers can get that
without going through ->tp_c at all; start with lifting that into
the callers, next commits will massage those, eventually removing
->tp_c altogether.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
 net/sched/cls_u32.c | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 3f6fba831c57..53f34f8cde8b 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -761,7 +761,7 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = {
 };
 
 static int u32_set_parms(struct net *net, struct tcf_proto *tp,
-			 unsigned long base, struct tc_u_hnode *ht,
+			 unsigned long base, struct tc_u_common *tp_c,
 			 struct tc_u_knode *n, struct nlattr **tb,
 			 struct nlattr *est, bool ovr,
 			 struct netlink_ext_ack *extack)
@@ -782,7 +782,7 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
 		}
 
 		if (handle) {
-			ht_down = u32_lookup_ht(ht->tp_c, handle);
+			ht_down = u32_lookup_ht(tp_c, handle);
 
 			if (!ht_down) {
 				NL_SET_ERR_MSG_MOD(extack, "Link hash table not found");
@@ -957,7 +957,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 			return -ENOMEM;
 
 		err = u32_set_parms(net, tp, base,
-				    rtnl_dereference(n->ht_up), new, tb,
+				    rtnl_dereference(n->ht_up)->tp_c, new, tb,
 				    tca[TCA_RATE], ovr, extack);
 
 		if (err) {
@@ -1124,7 +1124,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	}
 #endif
 
-	err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE], ovr,
+	err = u32_set_parms(net, tp, base, ht->tp_c, n, tb, tca[TCA_RATE], ovr,
 			    extack);
 	if (err == 0) {
 		struct tc_u_knode __rcu **ins;
-- 
2.11.0

[PATCH net-next v2 09/12] net: sched: cls_u32: the tp_c argument of u32_set_parms() is always tp->data

[Jamal Hadi Salim]

From: Al Viro <viro@zeniv.linux.org.uk>

It must be tc_u_common associated with that tp (i.e. tp->data).
Proof:
	* both ->ht_up and ->tp_c are assign-once
	* ->tp_c of anything inserted into tp_c->hlist is tp_c
	* hnodes never get reinserted into the lists or moved
between those, so anything found by u32_lookup_ht(tp->data, ...)
will have ->tp_c equal to tp->data.
	* tp->root->tp_c == tp->data.
	* ->ht_up of anything inserted into hnode->ht[...] is
equal to hnode.
	* knodes never get reinserted into hash chains or moved
between those, so anything returned by u32_lookup_key(ht, ...)
will have ->ht_up equal to ht.
	* any knode returned by u32_get(tp, ...) will have ->ht_up->tp_c
point to tp->data

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
 net/sched/cls_u32.c | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 53f34f8cde8b..3ed2c9866b36 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -956,8 +956,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		if (!new)
 			return -ENOMEM;
 
-		err = u32_set_parms(net, tp, base,
-				    rtnl_dereference(n->ht_up)->tp_c, new, tb,
+		err = u32_set_parms(net, tp, base, tp_c, new, tb,
 				    tca[TCA_RATE], ovr, extack);
 
 		if (err) {
@@ -1124,7 +1123,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	}
 #endif
 
-	err = u32_set_parms(net, tp, base, ht->tp_c, n, tb, tca[TCA_RATE], ovr,
+	err = u32_set_parms(net, tp, base, tp_c, n, tb, tca[TCA_RATE], ovr,
 			    extack);
 	if (err == 0) {
 		struct tc_u_knode __rcu **ins;
-- 
2.11.0

[PATCH net-next v2 10/12] net: sched: cls_u32: get rid of tp_c

[Jamal Hadi Salim]

From: Al Viro <viro@zeniv.linux.org.uk>

Both hnode ->tp_c and tp_c argument of u32_set_parms()
the latter is redundant, the former - never read...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
 net/sched/cls_u32.c | 11 ++++-------
 1 file changed, 4 insertions(+), 7 deletions(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 3ed2c9866b36..3d4c360f9b0c 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -79,7 +79,6 @@ struct tc_u_hnode {
 	struct tc_u_hnode __rcu	*next;
 	u32			handle;
 	u32			prio;
-	struct tc_u_common	*tp_c;
 	int			refcnt;
 	unsigned int		divisor;
 	struct idr		handle_idr;
@@ -390,7 +389,6 @@ static int u32_init(struct tcf_proto *tp)
 	tp_c->refcnt++;
 	RCU_INIT_POINTER(root_ht->next, tp_c->hlist);
 	rcu_assign_pointer(tp_c->hlist, root_ht);
-	root_ht->tp_c = tp_c;
 
 	rcu_assign_pointer(tp->root, root_ht);
 	tp->data = tp_c;
@@ -761,7 +759,7 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = {
 };
 
 static int u32_set_parms(struct net *net, struct tcf_proto *tp,
-			 unsigned long base, struct tc_u_common *tp_c,
+			 unsigned long base,
 			 struct tc_u_knode *n, struct nlattr **tb,
 			 struct nlattr *est, bool ovr,
 			 struct netlink_ext_ack *extack)
@@ -782,7 +780,7 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp,
 		}
 
 		if (handle) {
-			ht_down = u32_lookup_ht(tp_c, handle);
+			ht_down = u32_lookup_ht(tp->data, handle);
 
 			if (!ht_down) {
 				NL_SET_ERR_MSG_MOD(extack, "Link hash table not found");
@@ -956,7 +954,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		if (!new)
 			return -ENOMEM;
 
-		err = u32_set_parms(net, tp, base, tp_c, new, tb,
+		err = u32_set_parms(net, tp, base, new, tb,
 				    tca[TCA_RATE], ovr, extack);
 
 		if (err) {
@@ -1012,7 +1010,6 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 				return err;
 			}
 		}
-		ht->tp_c = tp_c;
 		ht->refcnt = 1;
 		ht->divisor = divisor;
 		ht->handle = handle;
@@ -1123,7 +1120,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	}
 #endif
 
-	err = u32_set_parms(net, tp, base, tp_c, n, tb, tca[TCA_RATE], ovr,
+	err = u32_set_parms(net, tp, base, n, tb, tca[TCA_RATE], ovr,
 			    extack);
 	if (err == 0) {
 		struct tc_u_knode __rcu **ins;
-- 
2.11.0

[PATCH net-next v2 11/12] net: sched: cls_u32: keep track of knodes count in tc_u_common

[Jamal Hadi Salim]

From: Al Viro <viro@zeniv.linux.org.uk>

allows to simplify u32_delete() considerably

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
 net/sched/cls_u32.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 3d4c360f9b0c..61593bee08db 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -97,6 +97,7 @@ struct tc_u_common {
 	int			refcnt;
 	struct idr		handle_idr;
 	struct hlist_node	hnode;
+	long			knodes;
 };
 
 static inline unsigned int u32_hash_fold(__be32 key,
@@ -452,6 +453,7 @@ static void u32_delete_key_freepf_work(struct work_struct *work)
 
 static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
 {
+	struct tc_u_common *tp_c = tp->data;
 	struct tc_u_knode __rcu **kp;
 	struct tc_u_knode *pkp;
 	struct tc_u_hnode *ht = rtnl_dereference(key->ht_up);
@@ -462,6 +464,7 @@ static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
 		     kp = &pkp->next, pkp = rtnl_dereference(*kp)) {
 			if (pkp == key) {
 				RCU_INIT_POINTER(*kp, key->next);
+				tp_c->knodes--;
 
 				tcf_unbind_filter(tp, &key->res);
 				idr_remove(&ht->handle_idr, key->handle);
@@ -576,6 +579,7 @@ static int u32_replace_hw_knode(struct tcf_proto *tp, struct tc_u_knode *n,
 static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
 			    struct netlink_ext_ack *extack)
 {
+	struct tc_u_common *tp_c = tp->data;
 	struct tc_u_knode *n;
 	unsigned int h;
 
@@ -583,6 +587,7 @@ static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
 		while ((n = rtnl_dereference(ht->ht[h])) != NULL) {
 			RCU_INIT_POINTER(ht->ht[h],
 					 rtnl_dereference(n->next));
+			tp_c->knodes--;
 			tcf_unbind_filter(tp, &n->res);
 			u32_remove_hw_knode(tp, n, extack);
 			idr_remove(&ht->handle_idr, n->handle);
@@ -1141,6 +1146,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 
 		RCU_INIT_POINTER(n->next, pins);
 		rcu_assign_pointer(*ins, n);
+		tp_c->knodes++;
 		*arg = n;
 		return 0;
 	}
-- 
2.11.0

[PATCH net-next v2 12/12] net: sched: cls_u32: simplify the hell out u32_delete() emptiness check

[Jamal Hadi Salim]

From: Al Viro <viro@zeniv.linux.org.uk>

Now that we have the knode count, we can instantly check if
any hnodes are non-empty.  And that kills the check for extra
references to root hnode - those could happen only if there was
a knode to carry such a link.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
---
 net/sched/cls_u32.c | 48 +-----------------------------------------------
 1 file changed, 1 insertion(+), 47 deletions(-)

diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c
index 61593bee08db..ac79a40a0392 100644
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -627,17 +627,6 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht,
 	return -ENOENT;
 }
 
-static bool ht_empty(struct tc_u_hnode *ht)
-{
-	unsigned int h;
-
-	for (h = 0; h <= ht->divisor; h++)
-		if (rcu_access_pointer(ht->ht[h]))
-			return false;
-
-	return true;
-}
-
 static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack)
 {
 	struct tc_u_common *tp_c = tp->data;
@@ -675,13 +664,9 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last,
 		      struct netlink_ext_ack *extack)
 {
 	struct tc_u_hnode *ht = arg;
-	struct tc_u_hnode *root_ht = rtnl_dereference(tp->root);
 	struct tc_u_common *tp_c = tp->data;
 	int ret = 0;
 
-	if (ht == NULL)
-		goto out;
-
 	if (TC_U32_KEY(ht->handle)) {
 		u32_remove_hw_knode(tp, (struct tc_u_knode *)ht, extack);
 		ret = u32_delete_key(tp, (struct tc_u_knode *)ht);
@@ -702,38 +687,7 @@ static int u32_delete(struct tcf_proto *tp, void *arg, bool *last,
 	}
 
 out:
-	*last = true;
-	if (root_ht) {
-		if (root_ht->refcnt > 1) {
-			*last = false;
-			goto ret;
-		}
-		if (root_ht->refcnt == 1) {
-			if (!ht_empty(root_ht)) {
-				*last = false;
-				goto ret;
-			}
-		}
-	}
-
-	if (tp_c->refcnt > 1) {
-		*last = false;
-		goto ret;
-	}
-
-	if (tp_c->refcnt == 1) {
-		struct tc_u_hnode *ht;
-
-		for (ht = rtnl_dereference(tp_c->hlist);
-		     ht;
-		     ht = rtnl_dereference(ht->next))
-			if (!ht_empty(ht)) {
-				*last = false;
-				break;
-			}
-	}
-
-ret:
+	*last = tp_c->refcnt == 1 && tp_c->knodes == 0;
 	return ret;
 }
 
-- 
2.11.0

Re: [PATCH net-next v2 00/12] net: sched: cls_u32 Various improvements

[David Miller]

From: Jamal Hadi Salim <jhs@mojatatu.com>
Date: Mon,  8 Oct 2018 06:22:32 -0400

> Various improvements from Al.
> 
> Changes from version 1: Add missing commit 

Series applied.