Merge branch 'act_vlan-rcu'

Manish Kurup says:

====================
net_sched actions: act_vlan now uses RCU

This commit consists of 3 patches:

patch1 (1/3):
The VLAN action maintains one set of stats across all cores, and uses a
spinlock to synchronize updates to it from the same. Changed this to use a
per-CPU stats context instead.
This change will result in better performance.

patch2 (2/3):
Modified netronome nfp flower action to use VLAN helper functions instead
of accessing/referencing TC act_vlan private structures directly.

patch3 (3/3):
Using a spinlock in the VLAN action causes performance issues when the VLAN
action is used on multiple cores. Rewrote the VLAN action to use RCU read
locking for reads and updates instead.
All functions now use an RCU dereferenced pointer to access the VLAN action
context. Modified helper functions used by other modules, to use the RCU as
opposed to directly accessing the structure.

As part of this review, there were some changes suggested by reviewers.
I have incorporated all the changes that were requested.

Here're the changes:
v2: Fixed all helper functions to use RCU (rtnl_dereference) - Eric, Jamal
v2: Fixed indentation, extra line nits - Jamal, Jiri
v2: Moved rcu_head to the end of the struct - Jiri
v2: Re-formatted locals to reverse-christmas-tree - Jiri
v2: Removed mismatched spin_lock() - Cong
v2: Removed spin_lock_bh() in tcf_vlan_init, rtnl_dereference() should
    suffice - Cong, Jiri
v4: Modified the nfp flower action code to use the VLAN helper functions
    instead of referencing the structure directly. Isolated this into a
    separate patch - Pieter Jansen
v5: Got rid of the unlikely() for the allocation case - Simon Horman
v6: Had forgotten cleanup functions for RCU alloc, added them - Dave Miller
v7: Re-formatted more locals to reverse-christmas-tree - Pieter V
v8: Reverted reverse-christmas-tree(v7), not required when dependencies
    make it difficult to implement - Alexander D
v9: Cover letter subject change - Jamal
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 94 insertions, 38 deletions

diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index de64cedf8b26..c1c595f8bb87 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -58,7 +58,6 @@ nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan,
 		 const struct tc_action *action)
 {
 	size_t act_size = sizeof(struct nfp_fl_push_vlan);
-	struct tcf_vlan *vlan = to_vlan(action);
 	u16 tmp_push_vlan_tci;
 
 	push_vlan->head.jump_id = NFP_FL_ACTION_OPCODE_PUSH_VLAN;
@@ -67,8 +66,8 @@ nfp_fl_push_vlan(struct nfp_fl_push_vlan *push_vlan,
 	push_vlan->vlan_tpid = tcf_vlan_push_proto(action);
 
 	tmp_push_vlan_tci =
-		FIELD_PREP(NFP_FL_PUSH_VLAN_PRIO, vlan->tcfv_push_prio) |
-		FIELD_PREP(NFP_FL_PUSH_VLAN_VID, vlan->tcfv_push_vid) |
+		FIELD_PREP(NFP_FL_PUSH_VLAN_PRIO, tcf_vlan_push_prio(action)) |
+		FIELD_PREP(NFP_FL_PUSH_VLAN_VID, tcf_vlan_push_vid(action)) |
 		NFP_FL_PUSH_VLAN_CFI;
 	push_vlan->vlan_tci = cpu_to_be16(tmp_push_vlan_tci);
 }
diff --git a/include/net/tc_act/tc_vlan.h b/include/net/tc_act/tc_vlan.h
index c2090df944ff..22ae260d6869 100644
--- a/include/net/tc_act/tc_vlan.h
+++ b/include/net/tc_act/tc_vlan.h
@@ -13,12 +13,17 @@
 #include <net/act_api.h>
 #include <linux/tc_act/tc_vlan.h>
 
+struct tcf_vlan_params {
+	int               tcfv_action;
+	u16               tcfv_push_vid;
+	__be16            tcfv_push_proto;
+	u8                tcfv_push_prio;
+	struct rcu_head   rcu;
+};
+
 struct tcf_vlan {
 	struct tc_action	common;
-	int			tcfv_action;
-	u16			tcfv_push_vid;
-	__be16			tcfv_push_proto;
-	u8			tcfv_push_prio;
+	struct tcf_vlan_params __rcu *vlan_p;
 };
 #define to_vlan(a) ((struct tcf_vlan *)a)
 
@@ -33,22 +38,45 @@ static inline bool is_tcf_vlan(const struct tc_action *a)
 
 static inline u32 tcf_vlan_action(const struct tc_action *a)
 {
-	return to_vlan(a)->tcfv_action;
+	u32 tcfv_action;
+
+	rcu_read_lock();
+	tcfv_action = rcu_dereference(to_vlan(a)->vlan_p)->tcfv_action;
+	rcu_read_unlock();
+
+	return tcfv_action;
 }
 
 static inline u16 tcf_vlan_push_vid(const struct tc_action *a)
 {
-	return to_vlan(a)->tcfv_push_vid;
+	u16 tcfv_push_vid;
+
+	rcu_read_lock();
+	tcfv_push_vid = rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_vid;
+	rcu_read_unlock();
+
+	return tcfv_push_vid;
 }
 
 static inline __be16 tcf_vlan_push_proto(const struct tc_action *a)
 {
-	return to_vlan(a)->tcfv_push_proto;
+	__be16 tcfv_push_proto;
+
+	rcu_read_lock();
+	tcfv_push_proto = rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_proto;
+	rcu_read_unlock();
+
+	return tcfv_push_proto;
 }
 
 static inline u8 tcf_vlan_push_prio(const struct tc_action *a)
 {
-	return to_vlan(a)->tcfv_push_prio;
-}
+	u8 tcfv_push_prio;
 
+	rcu_read_lock();
+	tcfv_push_prio = rcu_dereference(to_vlan(a)->vlan_p)->tcfv_push_prio;
+	rcu_read_unlock();
+
+	return tcfv_push_prio;
+}
 #endif /* __NET_TC_VLAN_H */
diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c
index 16eb067a8d8f..97f717a13ad5 100644
--- a/net/sched/act_vlan.c
+++ b/net/sched/act_vlan.c
@@ -26,14 +26,13 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
 		    struct tcf_result *res)
 {
 	struct tcf_vlan *v = to_vlan(a);
+	struct tcf_vlan_params *p;
 	int action;
 	int err;
 	u16 tci;
 
-	spin_lock(&v->tcf_lock);
 	tcf_lastuse_update(&v->tcf_tm);
-	bstats_update(&v->tcf_bstats, skb);
-	action = v->tcf_action;
+	bstats_cpu_update(this_cpu_ptr(v->common.cpu_bstats), skb);
 
 	/* Ensure 'data' points at mac_header prior calling vlan manipulating
 	 * functions.
@@ -41,15 +40,21 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
 	if (skb_at_tc_ingress(skb))
 		skb_push_rcsum(skb, skb->mac_len);
 
-	switch (v->tcfv_action) {
+	rcu_read_lock();
+
+	action = READ_ONCE(v->tcf_action);
+
+	p = rcu_dereference(v->vlan_p);
+
+	switch (p->tcfv_action) {
 	case TCA_VLAN_ACT_POP:
 		err = skb_vlan_pop(skb);
 		if (err)
 			goto drop;
 		break;
 	case TCA_VLAN_ACT_PUSH:
-		err = skb_vlan_push(skb, v->tcfv_push_proto, v->tcfv_push_vid |
-				    (v->tcfv_push_prio << VLAN_PRIO_SHIFT));
+		err = skb_vlan_push(skb, p->tcfv_push_proto, p->tcfv_push_vid |
+				    (p->tcfv_push_prio << VLAN_PRIO_SHIFT));
 		if (err)
 			goto drop;
 		break;
@@ -68,14 +73,14 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
 				goto drop;
 		}
 		/* replace the vid */
-		tci = (tci & ~VLAN_VID_MASK) | v->tcfv_push_vid;
+		tci = (tci & ~VLAN_VID_MASK) | p->tcfv_push_vid;
 		/* replace prio bits, if tcfv_push_prio specified */
-		if (v->tcfv_push_prio) {
+		if (p->tcfv_push_prio) {
 			tci &= ~VLAN_PRIO_MASK;
-			tci |= v->tcfv_push_prio << VLAN_PRIO_SHIFT;
+			tci |= p->tcfv_push_prio << VLAN_PRIO_SHIFT;
 		}
 		/* put updated tci as hwaccel tag */
-		__vlan_hwaccel_put_tag(skb, v->tcfv_push_proto, tci);
+		__vlan_hwaccel_put_tag(skb, p->tcfv_push_proto, tci);
 		break;
 	default:
 		BUG();
@@ -85,12 +90,13 @@ static int tcf_vlan(struct sk_buff *skb, const struct tc_action *a,
 
 drop:
 	action = TC_ACT_SHOT;
-	v->tcf_qstats.drops++;
+	qstats_drop_inc(this_cpu_ptr(v->common.cpu_qstats));
+
 unlock:
+	rcu_read_unlock();
 	if (skb_at_tc_ingress(skb))
 		skb_pull_rcsum(skb, skb->mac_len);
 
-	spin_unlock(&v->tcf_lock);
 	return action;
 }
 
@@ -107,6 +113,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 {
 	struct tc_action_net *tn = net_generic(net, vlan_net_id);
 	struct nlattr *tb[TCA_VLAN_MAX + 1];
+	struct tcf_vlan_params *p, *p_old;
 	struct tc_vlan *parm;
 	struct tcf_vlan *v;
 	int action;
@@ -172,7 +179,7 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 
 	if (!exists) {
 		ret = tcf_idr_create(tn, parm->index, est, a,
-				     &act_vlan_ops, bind, false);
+				     &act_vlan_ops, bind, true);
 		if (ret)
 			return ret;
 
@@ -185,46 +192,67 @@ static int tcf_vlan_init(struct net *net, struct nlattr *nla,
 
 	v = to_vlan(*a);
 
-	spin_lock_bh(&v->tcf_lock);
-
-	v->tcfv_action = action;
-	v->tcfv_push_vid = push_vid;
-	v->tcfv_push_prio = push_prio;
-	v->tcfv_push_proto = push_proto;
+	ASSERT_RTNL();
+	p = kzalloc(sizeof(*p), GFP_KERNEL);
+	if (!p) {
+		if (ovr)
+			tcf_idr_release(*a, bind);
+		return -ENOMEM;
+	}
 
 	v->tcf_action = parm->action;
 
-	spin_unlock_bh(&v->tcf_lock);
+	p_old = rtnl_dereference(v->vlan_p);
+
+	p->tcfv_action = action;
+	p->tcfv_push_vid = push_vid;
+	p->tcfv_push_prio = push_prio;
+	p->tcfv_push_proto = push_proto;
+
+	rcu_assign_pointer(v->vlan_p, p);
+
+	if (p_old)
+		kfree_rcu(p_old, rcu);
 
 	if (ret == ACT_P_CREATED)
 		tcf_idr_insert(tn, *a);
 	return ret;
 }
 
+static void tcf_vlan_cleanup(struct tc_action *a, int bind)
+{
+	struct tcf_vlan *v = to_vlan(a);
+	struct tcf_vlan_params *p;
+
+	p = rcu_dereference_protected(v->vlan_p, 1);
+	kfree_rcu(p, rcu);
+}
+
 static int tcf_vlan_dump(struct sk_buff *skb, struct tc_action *a,
 			 int bind, int ref)
 {
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tcf_vlan *v = to_vlan(a);
+	struct tcf_vlan_params *p = rtnl_dereference(v->vlan_p);
 	struct tc_vlan opt = {
 		.index    = v->tcf_index,
 		.refcnt   = v->tcf_refcnt - ref,
 		.bindcnt  = v->tcf_bindcnt - bind,
 		.action   = v->tcf_action,
-		.v_action = v->tcfv_action,
+		.v_action = p->tcfv_action,
 	};
 	struct tcf_t t;
 
 	if (nla_put(skb, TCA_VLAN_PARMS, sizeof(opt), &opt))
 		goto nla_put_failure;
 
-	if ((v->tcfv_action == TCA_VLAN_ACT_PUSH ||
-	     v->tcfv_action == TCA_VLAN_ACT_MODIFY) &&
-	    (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, v->tcfv_push_vid) ||
+	if ((p->tcfv_action == TCA_VLAN_ACT_PUSH ||
+	     p->tcfv_action == TCA_VLAN_ACT_MODIFY) &&
+	    (nla_put_u16(skb, TCA_VLAN_PUSH_VLAN_ID, p->tcfv_push_vid) ||
 	     nla_put_be16(skb, TCA_VLAN_PUSH_VLAN_PROTOCOL,
-			  v->tcfv_push_proto) ||
+			  p->tcfv_push_proto) ||
 	     (nla_put_u8(skb, TCA_VLAN_PUSH_VLAN_PRIORITY,
-					      v->tcfv_push_prio))))
+					      p->tcfv_push_prio))))
 		goto nla_put_failure;
 
 	tcf_tm_dump(&t, &v->tcf_tm);
@@ -260,6 +288,7 @@ static struct tc_action_ops act_vlan_ops = {
 	.act		=	tcf_vlan,
 	.dump		=	tcf_vlan_dump,
 	.init		=	tcf_vlan_init,
+	.cleanup	=	tcf_vlan_cleanup,
 	.walk		=	tcf_vlan_walker,
 	.lookup		=	tcf_vlan_search,
 	.size		=	sizeof(struct tcf_vlan),