Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts: net/sched/act_police.c net/sched/sch_drr.c net/sched/sch_hfsc.c net/sched/sch_prio.c net/sched/sch_red.c net/sched/sch_tbf.c In net-next the drop methods of the packet schedulers got removed, so the bug fixes to them in 'net' are irrelevant. A packet action unload crash fix conflicts with the addition of the new firstuse timestamp. Signed-off-by: David S. Miller <davem@davemloft.net>
2016-06-10 11:52:24 -07:00
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -38,7 +38,7 @@ struct tcf_police {
 	bool			peak_present;
 };
 #define to_police(pc)	\
-	container_of(pc, struct tcf_police, common)
+	container_of(pc->priv, struct tcf_police, common)

 #define POL_TAB_MASK     15

@@ -119,14 +119,12 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla,
 				 struct nlattr *est, struct tc_action *a,
 				 int ovr, int bind)
 {
-	unsigned int h;
 	int ret = 0, err;
 	struct nlattr *tb[TCA_POLICE_MAX + 1];
 	struct tc_police *parm;
 	struct tcf_police *police;
 	struct qdisc_rate_table *R_tab = NULL, *P_tab = NULL;
 	struct tc_action_net *tn = net_generic(net, police_net_id);
-	struct tcf_hashinfo *hinfo = tn->hinfo;
 	int size;

 	if (nla == NULL)
@@ -145,7 +143,7 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla,

 	if (parm->index) {
 		if (tcf_hash_search(tn, a, parm->index)) {
-			police = to_police(a->priv);
+			police = to_police(a);
 			if (bind) {
 				police->tcf_bindcnt += 1;
 				police->tcf_refcnt += 1;
@@ -156,16 +154,15 @@ static int tcf_act_police_locate(struct net *net, struct nlattr *nla,
 			/* not replacing */
 			return -EEXIST;
 		}
+	} else {
+		ret = tcf_hash_create(tn, parm->index, NULL, a,
+				      sizeof(*police), bind, false);
+		if (ret)
+			return ret;
+		ret = ACT_P_CREATED;
 	}

-	police = kzalloc(sizeof(*police), GFP_KERNEL);
-	if (police == NULL)
-		return -ENOMEM;
-	ret = ACT_P_CREATED;
-	police->tcf_refcnt = 1;
-	spin_lock_init(&police->tcf_lock);
-	if (bind)
-		police->tcf_bindcnt = 1;
+	police = to_police(a);
 override:
 	if (parm->rate.rate) {
 		err = -ENOMEM;
@@ -238,17 +235,8 @@ override:
 		return ret;

 	police->tcfp_t_c = ktime_get_ns();
-	police->tcf_index = parm->index ? parm->index :
-		tcf_hash_new_index(tn);
-	police->tcf_tm.install = jiffies;
-	police->tcf_tm.lastuse = jiffies;
-	police->tcf_tm.firstuse = 0;
-	h = tcf_hash(police->tcf_index, POL_TAB_MASK);
-	spin_lock_bh(&hinfo->lock);
-	hlist_add_head(&police->tcf_head, &hinfo->htab[h]);
-	spin_unlock_bh(&hinfo->lock);
+	tcf_hash_insert(tn, a);

-	a->priv = police;
 	return ret;

 failure_unlock:
@@ -257,7 +245,7 @@ failure:
 	qdisc_put_rtab(P_tab);
 	qdisc_put_rtab(R_tab);
 	if (ret == ACT_P_CREATED)
-		kfree(police);
+		tcf_hash_cleanup(a, est);
 	return err;
 }

--- a/net/sched/cls_flower.c
+++ b/net/sched/cls_flower.c
@@ -175,7 +175,7 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, unsigned long cookie)
 	struct tc_cls_flower_offload offload = {0};
 	struct tc_to_netdev tc;

-	if (!tc_should_offload(dev, 0))
+	if (!tc_should_offload(dev, tp, 0))
 		return;

 	offload.command = TC_CLSFLOWER_DESTROY;
@@ -198,7 +198,7 @@ static void fl_hw_replace_filter(struct tcf_proto *tp,
 	struct tc_cls_flower_offload offload = {0};
 	struct tc_to_netdev tc;

-	if (!tc_should_offload(dev, flags))
+	if (!tc_should_offload(dev, tp, flags))
 		return;

 	offload.command = TC_CLSFLOWER_REPLACE;
@@ -220,7 +220,7 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f)
 	struct tc_cls_flower_offload offload = {0};
 	struct tc_to_netdev tc;

-	if (!tc_should_offload(dev, 0))
+	if (!tc_should_offload(dev, tp, 0))
 		return;

 	offload.command = TC_CLSFLOWER_STATS;
--- a/net/sched/cls_u32.c
+++ b/net/sched/cls_u32.c
@@ -440,7 +440,7 @@ static void u32_remove_hw_knode(struct tcf_proto *tp, u32 handle)
 	offload.type = TC_SETUP_CLSU32;
 	offload.cls_u32 = &u32_offload;

-	if (tc_should_offload(dev, 0)) {
+	if (tc_should_offload(dev, tp, 0)) {
 		offload.cls_u32->command = TC_CLSU32_DELETE_KNODE;
 		offload.cls_u32->knode.handle = handle;
 		dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
@@ -457,20 +457,21 @@ static int u32_replace_hw_hnode(struct tcf_proto *tp,
 	struct tc_to_netdev offload;
 	int err;

+	if (!tc_should_offload(dev, tp, flags))
+		return tc_skip_sw(flags) ? -EINVAL : 0;
+
 	offload.type = TC_SETUP_CLSU32;
 	offload.cls_u32 = &u32_offload;

-	if (tc_should_offload(dev, flags)) {
-		offload.cls_u32->command = TC_CLSU32_NEW_HNODE;
-		offload.cls_u32->hnode.divisor = h->divisor;
-		offload.cls_u32->hnode.handle = h->handle;
-		offload.cls_u32->hnode.prio = h->prio;
+	offload.cls_u32->command = TC_CLSU32_NEW_HNODE;
+	offload.cls_u32->hnode.divisor = h->divisor;
+	offload.cls_u32->hnode.handle = h->handle;
+	offload.cls_u32->hnode.prio = h->prio;

-		err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
-						    tp->protocol, &offload);
-		if (tc_skip_sw(flags))
-			return err;
-	}
+	err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
+					    tp->protocol, &offload);
+	if (tc_skip_sw(flags))
+		return err;

 	return 0;
 }
@@ -484,7 +485,7 @@ static void u32_clear_hw_hnode(struct tcf_proto *tp, struct tc_u_hnode *h)
 	offload.type = TC_SETUP_CLSU32;
 	offload.cls_u32 = &u32_offload;

-	if (tc_should_offload(dev, 0)) {
+	if (tc_should_offload(dev, tp, 0)) {
 		offload.cls_u32->command = TC_CLSU32_DELETE_HNODE;
 		offload.cls_u32->hnode.divisor = h->divisor;
 		offload.cls_u32->hnode.handle = h->handle;
@@ -507,27 +508,28 @@ static int u32_replace_hw_knode(struct tcf_proto *tp,
 	offload.type = TC_SETUP_CLSU32;
 	offload.cls_u32 = &u32_offload;

-	if (tc_should_offload(dev, flags)) {
-		offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE;
-		offload.cls_u32->knode.handle = n->handle;
-		offload.cls_u32->knode.fshift = n->fshift;
-#ifdef CONFIG_CLS_U32_MARK
-		offload.cls_u32->knode.val = n->val;
-		offload.cls_u32->knode.mask = n->mask;
-#else
-		offload.cls_u32->knode.val = 0;
-		offload.cls_u32->knode.mask = 0;
-#endif
-		offload.cls_u32->knode.sel = &n->sel;
-		offload.cls_u32->knode.exts = &n->exts;
-		if (n->ht_down)
-			offload.cls_u32->knode.link_handle = n->ht_down->handle;
+	if (!tc_should_offload(dev, tp, flags))
+		return tc_skip_sw(flags) ? -EINVAL : 0;

-		err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
-						    tp->protocol, &offload);
-		if (tc_skip_sw(flags))
-			return err;
-	}
+	offload.cls_u32->command = TC_CLSU32_REPLACE_KNODE;
+	offload.cls_u32->knode.handle = n->handle;
+	offload.cls_u32->knode.fshift = n->fshift;
+#ifdef CONFIG_CLS_U32_MARK
+	offload.cls_u32->knode.val = n->val;
+	offload.cls_u32->knode.mask = n->mask;
+#else
+	offload.cls_u32->knode.val = 0;
+	offload.cls_u32->knode.mask = 0;
+#endif
+	offload.cls_u32->knode.sel = &n->sel;
+	offload.cls_u32->knode.exts = &n->exts;
+	if (n->ht_down)
+		offload.cls_u32->knode.link_handle = n->ht_down->handle;
+
+	err = dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle,
+					    tp->protocol, &offload);
+	if (tc_skip_sw(flags))
+		return err;

 	return 0;
 }
@@ -863,7 +865,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 	if (tb[TCA_U32_FLAGS]) {
 		flags = nla_get_u32(tb[TCA_U32_FLAGS]);
 		if (!tc_flags_valid(flags))
-			return err;
+			return -EINVAL;
 	}

 	n = (struct tc_u_knode *)*arg;
@@ -921,11 +923,17 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		ht->divisor = divisor;
 		ht->handle = handle;
 		ht->prio = tp->prio;
+
+		err = u32_replace_hw_hnode(tp, ht, flags);
+		if (err) {
+			kfree(ht);
+			return err;
+		}
+
 		RCU_INIT_POINTER(ht->next, tp_c->hlist);
 		rcu_assign_pointer(tp_c->hlist, ht);
 		*arg = (unsigned long)ht;

-		u32_replace_hw_hnode(tp, ht, flags);
 		return 0;
 	}

--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -378,6 +378,7 @@ static int drr_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		cl->deficit = cl->quantum;
 	}

+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 	return err;
 }
@@ -410,6 +411,7 @@ static struct sk_buff *drr_dequeue(struct Qdisc *sch)

 			bstats_update(&cl->bstats, skb);
 			qdisc_bstats_update(sch, skb);
+			qdisc_qstats_backlog_dec(sch, skb);
 			sch->q.qlen--;
 			return skb;
 		}
@@ -446,6 +448,7 @@ static void drr_reset_qdisc(struct Qdisc *sch)
 			qdisc_reset(cl->qdisc);
 		}
 	}
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }

--- a/net/sched/sch_fq_codel.c
+++ b/net/sched/sch_fq_codel.c
@@ -190,6 +190,7 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	unsigned int idx, prev_backlog, prev_qlen;
 	struct fq_codel_flow *flow;
 	int uninitialized_var(ret);
+	unsigned int pkt_len;
 	bool memory_limited;

 	idx = fq_codel_classify(skb, sch, &ret);
@@ -221,6 +222,8 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	prev_backlog = sch->qstats.backlog;
 	prev_qlen = sch->q.qlen;

+	/* save this packet length as it might be dropped by fq_codel_drop() */
+	pkt_len = qdisc_pkt_len(skb);
 	/* fq_codel_drop() is quite expensive, as it performs a linear search
 	 * in q->backlogs[] to find a fat flow.
 	 * So instead of dropping a single packet, drop half of its backlog
@@ -228,14 +231,23 @@ static int fq_codel_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	 */
 	ret = fq_codel_drop(sch, q->drop_batch_size);

-	q->drop_overlimit += prev_qlen - sch->q.qlen;
+	prev_qlen -= sch->q.qlen;
+	prev_backlog -= sch->qstats.backlog;
+	q->drop_overlimit += prev_qlen;
 	if (memory_limited)
-		q->drop_overmemory += prev_qlen - sch->q.qlen;
-	/* As we dropped packet(s), better let upper stack know this */
-	qdisc_tree_reduce_backlog(sch, prev_qlen - sch->q.qlen,
-				  prev_backlog - sch->qstats.backlog);
+		q->drop_overmemory += prev_qlen;

-	return ret == idx ? NET_XMIT_CN : NET_XMIT_SUCCESS;
+	/* As we dropped packet(s), better let upper stack know this.
+	 * If we dropped a packet for this flow, return NET_XMIT_CN,
+	 * but in this case, our parents wont increase their backlogs.
+	 */
+	if (ret == idx) {
+		qdisc_tree_reduce_backlog(sch, prev_qlen - 1,
+					  prev_backlog - pkt_len);
+		return NET_XMIT_CN;
+	}
+	qdisc_tree_reduce_backlog(sch, prev_qlen, prev_backlog);
+	return NET_XMIT_SUCCESS;
 }

 /* This is the specific function called from codel_dequeue()
@@ -647,7 +659,7 @@ static int fq_codel_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		qs.backlog = q->backlogs[idx];
 		qs.drops = flow->dropped;
 	}
-	if (gnet_stats_copy_queue(d, NULL, &qs, 0) < 0)
+	if (gnet_stats_copy_queue(d, NULL, &qs, qs.qlen) < 0)
 		return -1;
 	if (idx < q->flows_cnt)
 		return gnet_stats_copy_app(d, &xstats, sizeof(xstats));
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -49,6 +49,7 @@ static inline int dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q)
 {
 	q->gso_skb = skb;
 	q->qstats.requeues++;
+	qdisc_qstats_backlog_inc(q, skb);
 	q->q.qlen++;	/* it's still part of the queue */
 	__netif_schedule(q);

@@ -92,6 +93,7 @@ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate,
 		txq = skb_get_tx_queue(txq->dev, skb);
 		if (!netif_xmit_frozen_or_stopped(txq)) {
 			q->gso_skb = NULL;
+			qdisc_qstats_backlog_dec(q, skb);
 			q->q.qlen--;
 		} else
 			skb = NULL;
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1529,6 +1529,7 @@ hfsc_reset_qdisc(struct Qdisc *sch)
 	q->eligible = RB_ROOT;
 	INIT_LIST_HEAD(&q->droplist);
 	qdisc_watchdog_cancel(&q->watchdog);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }

@@ -1559,14 +1560,6 @@ hfsc_dump_qdisc(struct Qdisc *sch, struct sk_buff *skb)
 	struct hfsc_sched *q = qdisc_priv(sch);
 	unsigned char *b = skb_tail_pointer(skb);
 	struct tc_hfsc_qopt qopt;
-	struct hfsc_class *cl;
-	unsigned int i;
-
-	sch->qstats.backlog = 0;
-	for (i = 0; i < q->clhash.hashsize; i++) {
-		hlist_for_each_entry(cl, &q->clhash.hash[i], cl_common.hnode)
-			sch->qstats.backlog += cl->qdisc->qstats.backlog;
-	}

 	qopt.defcls = q->defcls;
 	if (nla_put(skb, TCA_OPTIONS, sizeof(qopt), &qopt))
@@ -1604,6 +1597,7 @@ hfsc_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	if (cl->qdisc->q.qlen == 1)
 		set_active(cl, qdisc_pkt_len(skb));

+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;

 	return NET_XMIT_SUCCESS;
@@ -1672,6 +1666,7 @@ hfsc_dequeue(struct Qdisc *sch)

 	qdisc_unthrottled(sch);
 	qdisc_bstats_update(sch, skb);
+	qdisc_qstats_backlog_dec(sch, skb);
 	sch->q.qlen--;

 	return skb;
--- a/net/sched/sch_ingress.c
+++ b/net/sched/sch_ingress.c
@@ -27,6 +27,11 @@ static unsigned long ingress_get(struct Qdisc *sch, u32 classid)
 	return TC_H_MIN(classid) + 1;
 }

+static bool ingress_cl_offload(u32 classid)
+{
+	return true;
+}
+
 static unsigned long ingress_bind_filter(struct Qdisc *sch,
 					 unsigned long parent, u32 classid)
 {
@@ -86,6 +91,7 @@ static const struct Qdisc_class_ops ingress_class_ops = {
 	.put		=	ingress_put,
 	.walk		=	ingress_walk,
 	.tcf_chain	=	ingress_find_tcf,
+	.tcf_cl_offload	=	ingress_cl_offload,
 	.bind_tcf	=	ingress_bind_filter,
 	.unbind_tcf	=	ingress_put,
 };
@@ -110,6 +116,11 @@ static unsigned long clsact_get(struct Qdisc *sch, u32 classid)
 	}
 }

+static bool clsact_cl_offload(u32 classid)
+{
+	return TC_H_MIN(classid) == TC_H_MIN(TC_H_MIN_INGRESS);
+}
+
 static unsigned long clsact_bind_filter(struct Qdisc *sch,
 					unsigned long parent, u32 classid)
 {
@@ -158,6 +169,7 @@ static const struct Qdisc_class_ops clsact_class_ops = {
 	.put		=	ingress_put,
 	.walk		=	ingress_walk,
 	.tcf_chain	=	clsact_find_tcf,
+	.tcf_cl_offload	=	clsact_cl_offload,
 	.bind_tcf	=	clsact_bind_filter,
 	.unbind_tcf	=	ingress_put,
 };
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -85,6 +85,7 @@ prio_enqueue(struct sk_buff *skb, struct Qdisc *sch)

 	ret = qdisc_enqueue(skb, qdisc);
 	if (ret == NET_XMIT_SUCCESS) {
+		qdisc_qstats_backlog_inc(sch, skb);
 		sch->q.qlen++;
 		return NET_XMIT_SUCCESS;
 	}
@@ -117,6 +118,7 @@ static struct sk_buff *prio_dequeue(struct Qdisc *sch)
 		struct sk_buff *skb = qdisc_dequeue_peeked(qdisc);
 		if (skb) {
 			qdisc_bstats_update(sch, skb);
+			qdisc_qstats_backlog_dec(sch, skb);
 			sch->q.qlen--;
 			return skb;
 		}
@@ -133,6 +135,7 @@ prio_reset(struct Qdisc *sch)

 	for (prio = 0; prio < q->bands; prio++)
 		qdisc_reset(q->queues[prio]);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 }

--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -1238,8 +1238,10 @@ static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 			 cl->agg->lmax, qdisc_pkt_len(skb), cl->common.classid);
 		err = qfq_change_agg(sch, cl, cl->agg->class_weight,
 				     qdisc_pkt_len(skb));
-		if (err)
-			return err;
+		if (err) {
+			cl->qstats.drops++;
+			return qdisc_drop(skb, sch);
+		}
 	}

 	err = qdisc_enqueue(skb, cl->qdisc);
--- a/net/sched/sch_red.c
+++ b/net/sched/sch_red.c
@@ -97,6 +97,7 @@ static int red_enqueue(struct sk_buff *skb, struct Qdisc *sch)

 	ret = qdisc_enqueue(skb, child);
 	if (likely(ret == NET_XMIT_SUCCESS)) {
+		qdisc_qstats_backlog_inc(sch, skb);
 		sch->q.qlen++;
 	} else if (net_xmit_drop_count(ret)) {
 		q->stats.pdrop++;
@@ -118,6 +119,7 @@ static struct sk_buff *red_dequeue(struct Qdisc *sch)
 	skb = child->dequeue(child);
 	if (skb) {
 		qdisc_bstats_update(sch, skb);
+		qdisc_qstats_backlog_dec(sch, skb);
 		sch->q.qlen--;
 	} else {
 		if (!red_is_idling(&q->vars))
@@ -139,6 +141,7 @@ static void red_reset(struct Qdisc *sch)
 	struct red_sched_data *q = qdisc_priv(sch);

 	qdisc_reset(q->qdisc);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 	red_restart(&q->vars);
 }
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -207,6 +207,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 		return ret;
 	}

+	qdisc_qstats_backlog_inc(sch, skb);
 	sch->q.qlen++;
 	return NET_XMIT_SUCCESS;
 }
@@ -251,6 +252,7 @@ static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
 			q->t_c = now;
 			q->tokens = toks;
 			q->ptokens = ptoks;
+			qdisc_qstats_backlog_dec(sch, skb);
 			sch->q.qlen--;
 			qdisc_unthrottled(sch);
 			qdisc_bstats_update(sch, skb);
@@ -282,6 +284,7 @@ static void tbf_reset(struct Qdisc *sch)
 	struct tbf_sched_data *q = qdisc_priv(sch);

 	qdisc_reset(q->qdisc);
+	sch->qstats.backlog = 0;
 	sch->q.qlen = 0;
 	q->t_c = ktime_get_ns();
 	q->tokens = q->buffer;