Merge tag 'v4.20-rc6' into rdma.git for-next

For dependencies in following patches.

6 files changed, 83 insertions, 63 deletions

diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c
index 1dae5f2b358f..c8cf4d10c435 100644
--- a/net/sched/act_mirred.c
+++ b/net/sched/act_mirred.c
@@ -258,7 +258,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a,
 	if (is_redirect) {
 		skb2->tc_redirected = 1;
 		skb2->tc_from_ingress = skb2->tc_at_ingress;
-
+		if (skb2->tc_from_ingress)
+			skb2->tstamp = 0;
 		/* let's the caller reinsert the packet, if possible */
 		if (use_reinsert) {
 			res->ingress = want_ingress;
diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c
index da3dd0f68cc2..2b372a06b432 100644
--- a/net/sched/act_pedit.c
+++ b/net/sched/act_pedit.c
@@ -201,7 +201,8 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla,
 			goto out_release;
 		}
 	} else {
-		return err;
+		ret = err;
+		goto out_free;
 	}
 
 	p = to_pedit(*a);
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index 052855d47354..ec8ec55e0fe8 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -27,10 +27,7 @@ struct tcf_police_params {
 	u32			tcfp_ewma_rate;
 	s64			tcfp_burst;
 	u32			tcfp_mtu;
-	s64			tcfp_toks;
-	s64			tcfp_ptoks;
 	s64			tcfp_mtu_ptoks;
-	s64			tcfp_t_c;
 	struct psched_ratecfg	rate;
 	bool			rate_present;
 	struct psched_ratecfg	peak;
@@ -41,6 +38,11 @@ struct tcf_police_params {
 struct tcf_police {
 	struct tc_action	common;
 	struct tcf_police_params __rcu *params;
+
+	spinlock_t		tcfp_lock ____cacheline_aligned_in_smp;
+	s64			tcfp_toks;
+	s64			tcfp_ptoks;
+	s64			tcfp_t_c;
 };
 
 #define to_police(pc) ((struct tcf_police *)pc)
@@ -83,7 +85,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 			       int ovr, int bind, bool rtnl_held,
 			       struct netlink_ext_ack *extack)
 {
-	int ret = 0, err;
+	int ret = 0, tcfp_result = TC_ACT_OK, err, size;
 	struct nlattr *tb[TCA_POLICE_MAX + 1];
 	struct tc_police *parm;
 	struct tcf_police *police;
@@ -91,7 +93,6 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 	struct tc_action_net *tn = net_generic(net, police_net_id);
 	struct tcf_police_params *new;
 	bool exists = false;
-	int size;
 
 	if (nla == NULL)
 		return -EINVAL;
@@ -122,6 +123,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 			return ret;
 		}
 		ret = ACT_P_CREATED;
+		spin_lock_init(&(to_police(*a)->tcfp_lock));
 	} else if (!ovr) {
 		tcf_idr_release(*a, bind);
 		return -EEXIST;
@@ -157,6 +159,16 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 		goto failure;
 	}
 
+	if (tb[TCA_POLICE_RESULT]) {
+		tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]);
+		if (TC_ACT_EXT_CMP(tcfp_result, TC_ACT_GOTO_CHAIN)) {
+			NL_SET_ERR_MSG(extack,
+				       "goto chain not allowed on fallback");
+			err = -EINVAL;
+			goto failure;
+		}
+	}
+
 	new = kzalloc(sizeof(*new), GFP_KERNEL);
 	if (unlikely(!new)) {
 		err = -ENOMEM;
@@ -164,6 +176,7 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 	}
 
 	/* No failure allowed after this point */
+	new->tcfp_result = tcfp_result;
 	new->tcfp_mtu = parm->mtu;
 	if (!new->tcfp_mtu) {
 		new->tcfp_mtu = ~0;
@@ -186,28 +199,20 @@ static int tcf_police_init(struct net *net, struct nlattr *nla,
 	}
 
 	new->tcfp_burst = PSCHED_TICKS2NS(parm->burst);
-	new->tcfp_toks = new->tcfp_burst;
-	if (new->peak_present) {
+	if (new->peak_present)
 		new->tcfp_mtu_ptoks = (s64)psched_l2t_ns(&new->peak,
 							 new->tcfp_mtu);
-		new->tcfp_ptoks = new->tcfp_mtu_ptoks;
-	}
 
 	if (tb[TCA_POLICE_AVRATE])
 		new->tcfp_ewma_rate = nla_get_u32(tb[TCA_POLICE_AVRATE]);
 
-	if (tb[TCA_POLICE_RESULT]) {
-		new->tcfp_result = nla_get_u32(tb[TCA_POLICE_RESULT]);
-		if (TC_ACT_EXT_CMP(new->tcfp_result, TC_ACT_GOTO_CHAIN)) {
-			NL_SET_ERR_MSG(extack,
-				       "goto chain not allowed on fallback");
-			err = -EINVAL;
-			goto failure;
-		}
-	}
-
 	spin_lock_bh(&police->tcf_lock);
-	new->tcfp_t_c = ktime_get_ns();
+	spin_lock_bh(&police->tcfp_lock);
+	police->tcfp_t_c = ktime_get_ns();
+	police->tcfp_toks = new->tcfp_burst;
+	if (new->peak_present)
+		police->tcfp_ptoks = new->tcfp_mtu_ptoks;
+	spin_unlock_bh(&police->tcfp_lock);
 	police->tcf_action = parm->action;
 	rcu_swap_protected(police->params,
 			   new,
@@ -257,25 +262,28 @@ static int tcf_police_act(struct sk_buff *skb, const struct tc_action *a,
 		}
 
 		now = ktime_get_ns();
-		toks = min_t(s64, now - p->tcfp_t_c, p->tcfp_burst);
+		spin_lock_bh(&police->tcfp_lock);
+		toks = min_t(s64, now - police->tcfp_t_c, p->tcfp_burst);
 		if (p->peak_present) {
-			ptoks = toks + p->tcfp_ptoks;
+			ptoks = toks + police->tcfp_ptoks;
 			if (ptoks > p->tcfp_mtu_ptoks)
 				ptoks = p->tcfp_mtu_ptoks;
 			ptoks -= (s64)psched_l2t_ns(&p->peak,
 						    qdisc_pkt_len(skb));
 		}
-		toks += p->tcfp_toks;
+		toks += police->tcfp_toks;
 		if (toks > p->tcfp_burst)
 			toks = p->tcfp_burst;
 		toks -= (s64)psched_l2t_ns(&p->rate, qdisc_pkt_len(skb));
 		if ((toks|ptoks) >= 0) {
-			p->tcfp_t_c = now;
-			p->tcfp_toks = toks;
-			p->tcfp_ptoks = ptoks;
+			police->tcfp_t_c = now;
+			police->tcfp_toks = toks;
+			police->tcfp_ptoks = ptoks;
+			spin_unlock_bh(&police->tcfp_lock);
 			ret = p->tcfp_result;
 			goto inc_drops;
 		}
+		spin_unlock_bh(&police->tcfp_lock);
 	}
 
 inc_overlimits:
diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c
index 9aada2d0ef06..71312d7bd8f4 100644
--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -709,11 +709,23 @@ static int fl_set_enc_opt(struct nlattr **tb, struct fl_flow_key *key,
 			  struct netlink_ext_ack *extack)
 {
 	const struct nlattr *nla_enc_key, *nla_opt_key, *nla_opt_msk = NULL;
-	int option_len, key_depth, msk_depth = 0;
+	int err, option_len, key_depth, msk_depth = 0;
+
+	err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS],
+				  TCA_FLOWER_KEY_ENC_OPTS_MAX,
+				  enc_opts_policy, extack);
+	if (err)
+		return err;
 
 	nla_enc_key = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS]);
 
 	if (tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]) {
+		err = nla_validate_nested(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK],
+					  TCA_FLOWER_KEY_ENC_OPTS_MAX,
+					  enc_opts_policy, extack);
+		if (err)
+			return err;
+
 		nla_opt_msk = nla_data(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
 		msk_depth = nla_len(tb[TCA_FLOWER_KEY_ENC_OPTS_MASK]);
 	}
@@ -1226,18 +1238,16 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 	if (err)
 		goto errout_idr;
 
-	if (!tc_skip_sw(fnew->flags)) {
-		if (!fold && fl_lookup(fnew->mask, &fnew->mkey)) {
-			err = -EEXIST;
-			goto errout_mask;
-		}
-
-		err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node,
-					     fnew->mask->filter_ht_params);
-		if (err)
-			goto errout_mask;
+	if (!fold && fl_lookup(fnew->mask, &fnew->mkey)) {
+		err = -EEXIST;
+		goto errout_mask;
 	}
 
+	err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node,
+				     fnew->mask->filter_ht_params);
+	if (err)
+		goto errout_mask;
+
 	if (!tc_skip_hw(fnew->flags)) {
 		err = fl_hw_replace_filter(tp, fnew, extack);
 		if (err)
@@ -1291,9 +1301,8 @@ static int fl_delete(struct tcf_proto *tp, void *arg, bool *last,
 	struct cls_fl_head *head = rtnl_dereference(tp->root);
 	struct cls_fl_filter *f = arg;
 
-	if (!tc_skip_sw(f->flags))
-		rhashtable_remove_fast(&f->mask->ht, &f->ht_node,
-				       f->mask->filter_ht_params);
+	rhashtable_remove_fast(&f->mask->ht, &f->ht_node,
+			       f->mask->filter_ht_params);
 	__fl_delete(tp, f, extack);
 	*last = list_empty(&head->masks);
 	return 0;
diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
index 4b1af706896c..25a7cf6d380f 100644
--- a/net/sched/sch_fq.c
+++ b/net/sched/sch_fq.c
@@ -469,22 +469,29 @@ begin:
 		goto begin;
 	}
 	prefetch(&skb->end);
-	f->credit -= qdisc_pkt_len(skb);
+	plen = qdisc_pkt_len(skb);
+	f->credit -= plen;
 
-	if (ktime_to_ns(skb->tstamp) || !q->rate_enable)
+	if (!q->rate_enable)
 		goto out;
 
 	rate = q->flow_max_rate;
-	if (skb->sk)
-		rate = min(skb->sk->sk_pacing_rate, rate);
-
-	if (rate <= q->low_rate_threshold) {
-		f->credit = 0;
-		plen = qdisc_pkt_len(skb);
-	} else {
-		plen = max(qdisc_pkt_len(skb), q->quantum);
-		if (f->credit > 0)
-			goto out;
+
+	/* If EDT time was provided for this skb, we need to
+	 * update f->time_next_packet only if this qdisc enforces
+	 * a flow max rate.
+	 */
+	if (!skb->tstamp) {
+		if (skb->sk)
+			rate = min(skb->sk->sk_pacing_rate, rate);
+
+		if (rate <= q->low_rate_threshold) {
+			f->credit = 0;
+		} else {
+			plen = max(plen, q->quantum);
+			if (f->credit > 0)
+				goto out;
+		}
 	}
 	if (rate != ~0UL) {
 		u64 len = (u64)plen * NSEC_PER_SEC;
diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index 57b3ad9394ad..22cd46a60057 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -431,6 +431,9 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	int count = 1;
 	int rc = NET_XMIT_SUCCESS;
 
+	/* Do not fool qdisc_drop_all() */
+	skb->prev = NULL;
+
 	/* Random duplication */
 	if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor))
 		++count;
@@ -648,15 +651,6 @@ deliver:
 			 */
 			skb->dev = qdisc_dev(sch);
 
-#ifdef CONFIG_NET_CLS_ACT
-			/*
-			 * If it's at ingress let's pretend the delay is
-			 * from the network (tstamp will be updated).
-			 */
-			if (skb->tc_redirected && skb->tc_from_ingress)
-				skb->tstamp = 0;
-#endif
-
 			if (q->slot.slot_next) {
 				q->slot.packets_left--;
 				q->slot.bytes_left -= qdisc_pkt_len(skb);