Merge branch 'net-sched-optimizations-around-action-binding-and-init'

Pedro Tammela says:

====================
net/sched: optimizations around action binding and init

Scaling optimizations for action binding in rtnl-less filters.
We saw a noticeable lock contention around idrinfo->lock when
testing in a 56 core system, which disappeared after the patches.
====================

Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: kuba-moo

include/net/act_api.h

@@ -191,7 +191,7 @@ int tcf_idr_create_from_flags(struct tc_action_net *tn, u32 index,
 			      struct nlattr *est, struct tc_action **a,
 			      const struct tc_action_ops *ops, int bind,
 			      u32 flags);
-void tcf_idr_insert_many(struct tc_action *actions[]);
+void tcf_idr_insert_many(struct tc_action *actions[], int init_res[]);
 void tcf_idr_cleanup(struct tc_action_net *tn, u32 index);
 int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
 			struct tc_action **a, int bind);

net/sched/act_api.c

@@ -816,6 +816,9 @@ EXPORT_SYMBOL(tcf_idr_cleanup);
  * its reference and bind counters, and return 1. Otherwise insert temporary
  * error pointer (to prevent concurrent users from inserting actions with same
  * index) and return 0.
+ *
+ * May return -EAGAIN for binding actions in case of a parallel add/delete on
+ * the requested index.
  */
 
 int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
@@ -824,43 +827,61 @@ int tcf_idr_check_alloc(struct tc_action_net *tn, u32 *index,
 	struct tcf_idrinfo *idrinfo = tn->idrinfo;
 	struct tc_action *p;
 	int ret;
+	u32 max;
 
-again:
-	mutex_lock(&idrinfo->lock);
 	if (*index) {
+again:
+		rcu_read_lock();
 		p = idr_find(&idrinfo->action_idr, *index);
+
 		if (IS_ERR(p)) {
 			/* This means that another process allocated
 			 * index but did not assign the pointer yet.
 			 */
-			mutex_unlock(&idrinfo->lock);
+			rcu_read_unlock();
 			goto again;
 		}
 
-		if (p) {
-			refcount_inc(&p->tcfa_refcnt);
-			if (bind)
-				atomic_inc(&p->tcfa_bindcnt);
-			*a = p;
-			ret = 1;
-		} else {
-			*a = NULL;
-			ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index,
-					    *index, GFP_KERNEL);
-			if (!ret)
-				idr_replace(&idrinfo->action_idr,
-					    ERR_PTR(-EBUSY), *index);
+		if (!p) {
+			/* Empty slot, try to allocate it */
+			max = *index;
+			rcu_read_unlock();
+			goto new;
 		}
+
+		if (!refcount_inc_not_zero(&p->tcfa_refcnt)) {
+			/* Action was deleted in parallel */
+			rcu_read_unlock();
+			return -EAGAIN;
+		}
+
+		if (bind)
+			atomic_inc(&p->tcfa_bindcnt);
+		*a = p;
+
+		rcu_read_unlock();
+
+		return 1;
 	} else {
+		/* Find a slot */
 		*index = 1;
-		*a = NULL;
-		ret = idr_alloc_u32(&idrinfo->action_idr, NULL, index,
-				    UINT_MAX, GFP_KERNEL);
-		if (!ret)
-			idr_replace(&idrinfo->action_idr, ERR_PTR(-EBUSY),
-				    *index);
+		max = UINT_MAX;
 	}
+
+new:
+	*a = NULL;
+
+	mutex_lock(&idrinfo->lock);
+	ret = idr_alloc_u32(&idrinfo->action_idr, ERR_PTR(-EBUSY), index, max,
+			    GFP_KERNEL);
 	mutex_unlock(&idrinfo->lock);
+
+	/* N binds raced for action allocation,
+	 * retry for all the ones that failed.
+	 */
+	if (ret == -ENOSPC && *index == max)
+		ret = -EAGAIN;
+
 	return ret;
 }
 EXPORT_SYMBOL(tcf_idr_check_alloc);
@@ -1283,19 +1304,20 @@ static const struct nla_policy tcf_action_policy[TCA_ACT_MAX + 1] = {
 	[TCA_ACT_HW_STATS]	= NLA_POLICY_BITFIELD32(TCA_ACT_HW_STATS_ANY),
 };
 
-void tcf_idr_insert_many(struct tc_action *actions[])
+void tcf_idr_insert_many(struct tc_action *actions[], int init_res[])
 {
 	struct tc_action *a;
 	int i;
 
 	tcf_act_for_each_action(i, a, actions) {
 		struct tcf_idrinfo *idrinfo;
 
+		if (init_res[i] == 0) /* Bound */
+			continue;
+
 		idrinfo = a->idrinfo;
 		mutex_lock(&idrinfo->lock);
-		/* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc if
-		 * it is just created, otherwise this is just a nop.
-		 */
+		/* Replace ERR_PTR(-EBUSY) allocated by tcf_idr_check_alloc */
 		idr_replace(&idrinfo->action_idr, a, a->tcfa_index);
 		mutex_unlock(&idrinfo->lock);
 	}
@@ -1495,7 +1517,7 @@ int tcf_action_init(struct net *net, struct tcf_proto *tp, struct nlattr *nla,
 	/* We have to commit them all together, because if any error happened in
 	 * between, we could not handle the failure gracefully.
 	 */
-	tcf_idr_insert_many(actions);
+	tcf_idr_insert_many(actions, init_res);
 
 	*attr_size = tcf_action_full_attrs_size(sz);
 	err = i - 1;

net/sched/cls_api.c

@@ -3313,7 +3313,7 @@ int tcf_exts_validate_ex(struct net *net, struct tcf_proto *tp, struct nlattr **
 			act->type = exts->type = TCA_OLD_COMPAT;
 			exts->actions[0] = act;
 			exts->nr_actions = 1;
-			tcf_idr_insert_many(exts->actions);
+			tcf_idr_insert_many(exts->actions, init_res);
 		} else if (exts->action && tb[exts->action]) {
 			int err;