net/sched: transition act_pedit to rcu and percpu stats

[ Upstream commit 52cf89f78c01bf39973f3e70d366921d70faff7a ]

The software pedit action didn't get the same love as some of the
other actions and it's still using spinlocks and shared stats in the
datapath.
Transition the action to rcu and percpu stats as this improves the
action's performance dramatically on multiple cpu deployments.

Reviewed-by: Jamal Hadi Salim <jhs@mojatatu.com>
Signed-off-by: Pedro Tammela <pctammela@mojatatu.com>
Reviewed-by: Simon Horman <simon.horman@corigine.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Stable-dep-of: e9e42292ea76 ("net/sched: act_pedit: fix action bind logic")
Signed-off-by: Sasha Levin <sashal@kernel.org>

1 files changed, 87 insertions, 61 deletions

diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index 94ed5857ce67..655addb31b7f 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -133,6 +133,17 @@ nla_failure:
 	return -EINVAL;
 }
 
+static void tcf_pedit_cleanup_rcu(struct rcu_head *head)
+{
+	struct tcf_pedit_parms *parms =
+		container_of(head, struct tcf_pedit_parms, rcu);
+
+	kfree(parms->tcfp_keys_ex);
+	kfree(parms->tcfp_keys);
+
+	kfree(parms);
+}
+
 static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 			  struct nlattr *est, struct tc_action **a,
 			  struct tcf_proto *tp, u32 flags,
@@ -140,10 +151,9 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 {
 	struct tc_action_net *tn = net_generic(net, act_pedit_ops.net_id);
 	bool bind = flags & TCA_ACT_FLAGS_BIND;
-	struct nlattr *tb[TCA_PEDIT_MAX + 1];
 	struct tcf_chain *goto_ch = NULL;
-	struct tc_pedit_key *keys = NULL;
-	struct tcf_pedit_key_ex *keys_ex;
+	struct tcf_pedit_parms *oparms, *nparms;
+	struct nlattr *tb[TCA_PEDIT_MAX + 1];
 	struct tc_pedit *parm;
 	struct nlattr *pattr;
 	struct tcf_pedit *p;
@@ -180,18 +190,25 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 		return -EINVAL;
 	}
 
-	keys_ex = tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys);
-	if (IS_ERR(keys_ex))
-		return PTR_ERR(keys_ex);
+	nparms = kzalloc(sizeof(*nparms), GFP_KERNEL);
+	if (!nparms)
+		return -ENOMEM;
+
+	nparms->tcfp_keys_ex =
+		tcf_pedit_keys_ex_parse(tb[TCA_PEDIT_KEYS_EX], parm->nkeys);
+	if (IS_ERR(nparms->tcfp_keys_ex)) {
+		ret = PTR_ERR(nparms->tcfp_keys_ex);
+		goto out_free;
+	}
 
 	index = parm->index;
 	err = tcf_idr_check_alloc(tn, &index, a, bind);
 	if (!err) {
-		ret = tcf_idr_create(tn, index, est, a,
-				     &act_pedit_ops, bind, false, flags);
+		ret = tcf_idr_create_from_flags(tn, index, est, a,
+						&act_pedit_ops, bind, flags);
 		if (ret) {
 			tcf_idr_cleanup(tn, index);
-			goto out_free;
+			goto out_free_ex;
 		}
 		ret = ACT_P_CREATED;
 	} else if (err > 0) {
@@ -203,7 +220,7 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 		}
 	} else {
 		ret = err;
-		goto out_free;
+		goto out_free_ex;
 	}
 
 	err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack);
@@ -211,48 +228,50 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 		ret = err;
 		goto out_release;
 	}
-	p = to_pedit(*a);
-	spin_lock_bh(&p->tcf_lock);
 
-	if (ret == ACT_P_CREATED ||
-	    (p->tcfp_nkeys && p->tcfp_nkeys != parm->nkeys)) {
-		keys = kmalloc(ksize, GFP_ATOMIC);
-		if (!keys) {
-			spin_unlock_bh(&p->tcf_lock);
-			ret = -ENOMEM;
-			goto put_chain;
-		}
-		kfree(p->tcfp_keys);
-		p->tcfp_keys = keys;
-		p->tcfp_nkeys = parm->nkeys;
+	nparms->tcfp_off_max_hint = 0;
+	nparms->tcfp_flags = parm->flags;
+	nparms->tcfp_nkeys = parm->nkeys;
+
+	nparms->tcfp_keys = kmalloc(ksize, GFP_KERNEL);
+	if (!nparms->tcfp_keys) {
+		ret = -ENOMEM;
+		goto put_chain;
 	}
-	memcpy(p->tcfp_keys, parm->keys, ksize);
-	p->tcfp_off_max_hint = 0;
-	for (i = 0; i < p->tcfp_nkeys; ++i) {
-		u32 cur = p->tcfp_keys[i].off;
+
+	memcpy(nparms->tcfp_keys, parm->keys, ksize);
+
+	for (i = 0; i < nparms->tcfp_nkeys; ++i) {
+		u32 cur = nparms->tcfp_keys[i].off;
 
 		/* sanitize the shift value for any later use */
-		p->tcfp_keys[i].shift = min_t(size_t, BITS_PER_TYPE(int) - 1,
-					      p->tcfp_keys[i].shift);
+		nparms->tcfp_keys[i].shift = min_t(size_t,
+						   BITS_PER_TYPE(int) - 1,
+						   nparms->tcfp_keys[i].shift);
 
 		/* The AT option can read a single byte, we can bound the actual
 		 * value with uchar max.
 		 */
-		cur += (0xff & p->tcfp_keys[i].offmask) >> p->tcfp_keys[i].shift;
+		cur += (0xff & nparms->tcfp_keys[i].offmask) >> nparms->tcfp_keys[i].shift;
 
 		/* Each key touches 4 bytes starting from the computed offset */
-		p->tcfp_off_max_hint = max(p->tcfp_off_max_hint, cur + 4);
+		nparms->tcfp_off_max_hint =
+			max(nparms->tcfp_off_max_hint, cur + 4);
 	}
 
-	p->tcfp_flags = parm->flags;
+	p = to_pedit(*a);
+
+	spin_lock_bh(&p->tcf_lock);
 	goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch);
+	oparms = rcu_replace_pointer(p->parms, nparms, 1);
+	spin_unlock_bh(&p->tcf_lock);
 
-	kfree(p->tcfp_keys_ex);
-	p->tcfp_keys_ex = keys_ex;
+	if (oparms)
+		call_rcu(&oparms->rcu, tcf_pedit_cleanup_rcu);
 
-	spin_unlock_bh(&p->tcf_lock);
 	if (goto_ch)
 		tcf_chain_put_by_act(goto_ch);
+
 	return ret;
 
 put_chain:
@@ -260,19 +279,22 @@ put_chain:
 		tcf_chain_put_by_act(goto_ch);
 out_release:
 	tcf_idr_release(*a, bind);
+out_free_ex:
+	kfree(nparms->tcfp_keys_ex);
 out_free:
-	kfree(keys_ex);
+	kfree(nparms);
 	return ret;
-
 }
 
 static void tcf_pedit_cleanup(struct tc_action *a)
 {
 	struct tcf_pedit *p = to_pedit(a);
-	struct tc_pedit_key *keys = p->tcfp_keys;
+	struct tcf_pedit_parms *parms;
 
-	kfree(keys);
-	kfree(p->tcfp_keys_ex);
+	parms = rcu_dereference_protected(p->parms, 1);
+
+	if (parms)
+		call_rcu(&parms->rcu, tcf_pedit_cleanup_rcu);
 }
 
 static bool offset_valid(struct sk_buff *skb, int offset)
@@ -323,28 +345,30 @@ static int tcf_pedit_act(struct sk_buff *skb, const struct tc_action *a,
 			 struct tcf_result *res)
 {
 	struct tcf_pedit *p = to_pedit(a);
+	struct tcf_pedit_parms *parms;
 	u32 max_offset;
 	int i;
 
-	spin_lock(&p->tcf_lock);
+	parms = rcu_dereference_bh(p->parms);
 
 	max_offset = (skb_transport_header_was_set(skb) ?
 		      skb_transport_offset(skb) :
 		      skb_network_offset(skb)) +
-		     p->tcfp_off_max_hint;
+		     parms->tcfp_off_max_hint;
 	if (skb_ensure_writable(skb, min(skb->len, max_offset)))
-		goto unlock;
+		goto done;
 
 	tcf_lastuse_update(&p->tcf_tm);
+	tcf_action_update_bstats(&p->common, skb);
 
-	if (p->tcfp_nkeys > 0) {
-		struct tc_pedit_key *tkey = p->tcfp_keys;
-		struct tcf_pedit_key_ex *tkey_ex = p->tcfp_keys_ex;
+	if (parms->tcfp_nkeys > 0) {
+		struct tc_pedit_key *tkey = parms->tcfp_keys;
+		struct tcf_pedit_key_ex *tkey_ex = parms->tcfp_keys_ex;
 		enum pedit_header_type htype =
 			TCA_PEDIT_KEY_EX_HDR_TYPE_NETWORK;
 		enum pedit_cmd cmd = TCA_PEDIT_KEY_EX_CMD_SET;
 
-		for (i = p->tcfp_nkeys; i > 0; i--, tkey++) {
+		for (i = parms->tcfp_nkeys; i > 0; i--, tkey++) {
 			u32 *ptr, hdata;
 			int offset = tkey->off;
 			int hoffset;
@@ -420,11 +444,10 @@ static int tcf_pedit_act(struct sk_buff *skb, const struct tc_action *a,
 	}
 
 bad:
+	spin_lock(&p->tcf_lock);
 	p->tcf_qstats.overlimits++;
-done:
-	bstats_update(&p->tcf_bstats, skb);
-unlock:
 	spin_unlock(&p->tcf_lock);
+done:
 	return p->tcf_action;
 }
 
@@ -443,30 +466,33 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a,
 {
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tcf_pedit *p = to_pedit(a);
+	struct tcf_pedit_parms *parms;
 	struct tc_pedit *opt;
 	struct tcf_t t;
 	int s;
 
-	s = struct_size(opt, keys, p->tcfp_nkeys);
+	spin_lock_bh(&p->tcf_lock);
+	parms = rcu_dereference_protected(p->parms, 1);
+	s = struct_size(opt, keys, parms->tcfp_nkeys);
 
-	/* netlink spinlocks held above us - must use ATOMIC */
 	opt = kzalloc(s, GFP_ATOMIC);
-	if (unlikely(!opt))
+	if (unlikely(!opt)) {
+		spin_unlock_bh(&p->tcf_lock);
 		return -ENOBUFS;
+	}
 
-	spin_lock_bh(&p->tcf_lock);
-	memcpy(opt->keys, p->tcfp_keys, flex_array_size(opt, keys, p->tcfp_nkeys));
+	memcpy(opt->keys, parms->tcfp_keys,
+	       flex_array_size(opt, keys, parms->tcfp_nkeys));
 	opt->index = p->tcf_index;
-	opt->nkeys = p->tcfp_nkeys;
-	opt->flags = p->tcfp_flags;
+	opt->nkeys = parms->tcfp_nkeys;
+	opt->flags = parms->tcfp_flags;
 	opt->action = p->tcf_action;
 	opt->refcnt = refcount_read(&p->tcf_refcnt) - ref;
 	opt->bindcnt = atomic_read(&p->tcf_bindcnt) - bind;
 
-	if (p->tcfp_keys_ex) {
-		if (tcf_pedit_key_ex_dump(skb,
-					  p->tcfp_keys_ex,
-					  p->tcfp_nkeys))
+	if (parms->tcfp_keys_ex) {
+		if (tcf_pedit_key_ex_dump(skb, parms->tcfp_keys_ex,
+					  parms->tcfp_nkeys))
 			goto nla_put_failure;
 
 		if (nla_put(skb, TCA_PEDIT_PARMS_EX, s, opt))