net: sched: make bstats per cpu and estimator RCU safe

In order to run qdisc's without locking statistics and estimators
need to be handled correctly.

To resolve bstats make the statistics per cpu. And because this is
only needed for qdiscs that are running without locks which is not
the case for most qdiscs in the near future only create percpu
stats when qdiscs set the TCQ_F_CPUSTATS flag.

Next because estimators use the bstats to calculate packets per
second and bytes per second the estimator code paths are updated
to use the per cpu statistics.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

14 files changed, 65 insertions, 33 deletions

diff --git a/net/sched/act_api.c b/net/sched/act_api.c
index 648778a..eca4cf9 100644
--- a/net/sched/act_api.c
+++ b/net/sched/act_api.c
@@ -252,7 +252,8 @@ int tcf_hash_create(u32 index, struct nlattr *est, struct tc_action *a,
 	p->tcfc_tm.install = jiffies;
 	p->tcfc_tm.lastuse = jiffies;
 	if (est) {
-		int err = gen_new_estimator(&p->tcfc_bstats, &p->tcfc_rate_est,
+		int err = gen_new_estimator(&p->tcfc_bstats, NULL,
+					    &p->tcfc_rate_est,
 					    &p->tcfc_lock, est);
 		if (err) {
 			kfree(p);
@@ -619,7 +620,7 @@ int tcf_action_copy_stats(struct sk_buff *skb, struct tc_action *a,
 	if (err < 0)
 		goto errout;
 
-	if (gnet_stats_copy_basic(&d, &p->tcfc_bstats) < 0 ||
+	if (gnet_stats_copy_basic(&d, NULL, &p->tcfc_bstats) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &p->tcfc_bstats,
 				     &p->tcfc_rate_est) < 0 ||
 	    gnet_stats_copy_queue(&d, &p->tcfc_qstats) < 0)
diff --git a/net/sched/act_police.c b/net/sched/act_police.c
index f32bcb0..69791ca 100644
--- a/net/sched/act_police.c
+++ b/net/sched/act_police.c
@@ -178,7 +178,7 @@ override:
 
 	spin_lock_bh(&police->tcf_lock);
 	if (est) {
-		err = gen_replace_estimator(&police->tcf_bstats,
+		err = gen_replace_estimator(&police->tcf_bstats, NULL,
 					    &police->tcf_rate_est,
 					    &police->tcf_lock, est);
 		if (err)
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c
index 15e7bee..a95e3b4 100644
--- a/net/sched/sch_api.c
+++ b/net/sched/sch_api.c
@@ -942,6 +942,13 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 	sch->handle = handle;
 
 	if (!ops->init || (err = ops->init(sch, tca[TCA_OPTIONS])) == 0) {
+		if (qdisc_is_percpu_stats(sch)) {
+			sch->cpu_bstats =
+				alloc_percpu(struct gnet_stats_basic_cpu);
+			if (!sch->cpu_bstats)
+				goto err_out4;
+		}
+
 		if (tca[TCA_STAB]) {
 			stab = qdisc_get_stab(tca[TCA_STAB]);
 			if (IS_ERR(stab)) {
@@ -964,8 +971,11 @@ qdisc_create(struct net_device *dev, struct netdev_queue *dev_queue,
 			else
 				root_lock = qdisc_lock(sch);
 
-			err = gen_new_estimator(&sch->bstats, &sch->rate_est,
-						root_lock, tca[TCA_RATE]);
+			err = gen_new_estimator(&sch->bstats,
+						sch->cpu_bstats,
+						&sch->rate_est,
+						root_lock,
+						tca[TCA_RATE]);
 			if (err)
 				goto err_out4;
 		}
@@ -984,6 +994,7 @@ err_out:
 	return NULL;
 
 err_out4:
+	free_percpu(sch->cpu_bstats);
 	/*
 	 * Any broken qdiscs that would require a ops->reset() here?
 	 * The qdisc was never in action so it shouldn't be necessary.
@@ -1022,9 +1033,11 @@ static int qdisc_change(struct Qdisc *sch, struct nlattr **tca)
 		   because change can't be undone. */
 		if (sch->flags & TCQ_F_MQROOT)
 			goto out;
-		gen_replace_estimator(&sch->bstats, &sch->rate_est,
-					    qdisc_root_sleeping_lock(sch),
-					    tca[TCA_RATE]);
+		gen_replace_estimator(&sch->bstats,
+				      sch->cpu_bstats,
+				      &sch->rate_est,
+				      qdisc_root_sleeping_lock(sch),
+				      tca[TCA_RATE]);
 	}
 out:
 	return 0;
@@ -1299,6 +1312,7 @@ graft:
 static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 			 u32 portid, u32 seq, u16 flags, int event)
 {
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats = NULL;
 	struct tcmsg *tcm;
 	struct nlmsghdr  *nlh;
 	unsigned char *b = skb_tail_pointer(skb);
@@ -1334,7 +1348,10 @@ static int tc_fill_qdisc(struct sk_buff *skb, struct Qdisc *q, u32 clid,
 	if (q->ops->dump_stats && q->ops->dump_stats(q, &d) < 0)
 		goto nla_put_failure;
 
-	if (gnet_stats_copy_basic(&d, &q->bstats) < 0 ||
+	if (qdisc_is_percpu_stats(q))
+		cpu_bstats = q->cpu_bstats;
+
+	if (gnet_stats_copy_basic(&d, cpu_bstats, &q->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(&d, &q->bstats, &q->rate_est) < 0 ||
 	    gnet_stats_copy_queue(&d, &q->qstats) < 0)
 		goto nla_put_failure;
diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c
index c398f9c..0101766 100644
--- a/net/sched/sch_atm.c
+++ b/net/sched/sch_atm.c
@@ -639,7 +639,7 @@ atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 
 	flow->qstats.qlen = flow->q->q.qlen;
 
-	if (gnet_stats_copy_basic(d, &flow->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &flow->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, &flow->qstats) < 0)
 		return -1;
 
diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c
index d2cd981..22a3a02 100644
--- a/net/sched/sch_cbq.c
+++ b/net/sched/sch_cbq.c
@@ -1601,7 +1601,7 @@ cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	if (cl->undertime != PSCHED_PASTPERFECT)
 		cl->xstats.undertime = cl->undertime - q->now;
 
-	if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, &cl->qstats) < 0)
 		return -1;
@@ -1759,7 +1759,8 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 		}
 
 		if (tca[TCA_RATE]) {
-			err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
+			err = gen_replace_estimator(&cl->bstats, NULL,
+						    &cl->rate_est,
 						    qdisc_root_sleeping_lock(sch),
 						    tca[TCA_RATE]);
 			if (err) {
@@ -1852,7 +1853,7 @@ cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **t
 		goto failure;
 
 	if (tca[TCA_RATE]) {
-		err = gen_new_estimator(&cl->bstats, &cl->rate_est,
+		err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est,
 					qdisc_root_sleeping_lock(sch),
 					tca[TCA_RATE]);
 		if (err) {
diff --git a/net/sched/sch_drr.c b/net/sched/sch_drr.c
index d8b5ccf..7a6243c 100644
--- a/net/sched/sch_drr.c
+++ b/net/sched/sch_drr.c
@@ -88,7 +88,8 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 
 	if (cl != NULL) {
 		if (tca[TCA_RATE]) {
-			err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
+			err = gen_replace_estimator(&cl->bstats, NULL,
+						    &cl->rate_est,
 						    qdisc_root_sleeping_lock(sch),
 						    tca[TCA_RATE]);
 			if (err)
@@ -116,7 +117,7 @@ static int drr_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		cl->qdisc = &noop_qdisc;
 
 	if (tca[TCA_RATE]) {
-		err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
+		err = gen_replace_estimator(&cl->bstats, NULL, &cl->rate_est,
 					    qdisc_root_sleeping_lock(sch),
 					    tca[TCA_RATE]);
 		if (err) {
@@ -282,7 +283,7 @@ static int drr_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 		cl->qdisc->qstats.qlen = cl->qdisc->q.qlen;
 	}
 
-	if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, &cl->qdisc->qstats) < 0)
 		return -1;
diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c
index 11b28f6..7c8e5d7 100644
--- a/net/sched/sch_generic.c
+++ b/net/sched/sch_generic.c
@@ -632,6 +632,9 @@ static void qdisc_rcu_free(struct rcu_head *head)
 {
 	struct Qdisc *qdisc = container_of(head, struct Qdisc, rcu_head);
 
+	if (qdisc_is_percpu_stats(qdisc))
+		free_percpu(qdisc->cpu_bstats);
+
 	kfree((char *) qdisc - qdisc->padded);
 }
 
diff --git a/net/sched/sch_hfsc.c b/net/sched/sch_hfsc.c
index 04b0de4..209b966 100644
--- a/net/sched/sch_hfsc.c
+++ b/net/sched/sch_hfsc.c
@@ -1014,9 +1014,12 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		cur_time = psched_get_time();
 
 		if (tca[TCA_RATE]) {
-			err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
-					      qdisc_root_sleeping_lock(sch),
-					      tca[TCA_RATE]);
+			spinlock_t *lock = qdisc_root_sleeping_lock(sch);
+
+			err = gen_replace_estimator(&cl->bstats, NULL,
+						    &cl->rate_est,
+						    lock,
+						    tca[TCA_RATE]);
 			if (err)
 				return err;
 		}
@@ -1063,7 +1066,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		return -ENOBUFS;
 
 	if (tca[TCA_RATE]) {
-		err = gen_new_estimator(&cl->bstats, &cl->rate_est,
+		err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est,
 					qdisc_root_sleeping_lock(sch),
 					tca[TCA_RATE]);
 		if (err) {
@@ -1374,7 +1377,7 @@ hfsc_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	xstats.work    = cl->cl_total;
 	xstats.rtwork  = cl->cl_cumul;
 
-	if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, &cl->qstats) < 0)
 		return -1;
diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c
index 063e953..0256dee 100644
--- a/net/sched/sch_htb.c
+++ b/net/sched/sch_htb.c
@@ -1144,7 +1144,7 @@ htb_dump_class_stats(struct Qdisc *sch, unsigned long arg, struct gnet_dump *d)
 	cl->xstats.tokens = PSCHED_NS2TICKS(cl->tokens);
 	cl->xstats.ctokens = PSCHED_NS2TICKS(cl->ctokens);
 
-	if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, NULL, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, &cl->qstats) < 0)
 		return -1;
@@ -1402,7 +1402,8 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 			goto failure;
 
 		if (htb_rate_est || tca[TCA_RATE]) {
-			err = gen_new_estimator(&cl->bstats, &cl->rate_est,
+			err = gen_new_estimator(&cl->bstats, NULL,
+						&cl->rate_est,
 						qdisc_root_sleeping_lock(sch),
 						tca[TCA_RATE] ? : &est.nla);
 			if (err) {
@@ -1464,8 +1465,11 @@ static int htb_change_class(struct Qdisc *sch, u32 classid,
 			parent->children++;
 	} else {
 		if (tca[TCA_RATE]) {
-			err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
-						    qdisc_root_sleeping_lock(sch),
+			spinlock_t *lock = qdisc_root_sleeping_lock(sch);
+
+			err = gen_replace_estimator(&cl->bstats, NULL,
+						    &cl->rate_est,
+						    lock,
 						    tca[TCA_RATE]);
 			if (err)
 				return err;
diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c
index a8b2864..d3a27fb 100644
--- a/net/sched/sch_mq.c
+++ b/net/sched/sch_mq.c
@@ -201,7 +201,7 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	sch = dev_queue->qdisc_sleeping;
 	sch->qstats.qlen = sch->q.qlen;
-	if (gnet_stats_copy_basic(d, &sch->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &sch->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, &sch->qstats) < 0)
 		return -1;
 	return 0;
diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 37e7d25..8917372 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -355,7 +355,7 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 		}
 		/* Reclaim root sleeping lock before completing stats */
 		spin_lock_bh(d->lock);
-		if (gnet_stats_copy_basic(d, &bstats) < 0 ||
+		if (gnet_stats_copy_basic(d, NULL, &bstats) < 0 ||
 		    gnet_stats_copy_queue(d, &qstats) < 0)
 			return -1;
 	} else {
@@ -363,7 +363,7 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 		sch = dev_queue->qdisc_sleeping;
 		sch->qstats.qlen = sch->q.qlen;
-		if (gnet_stats_copy_basic(d, &sch->bstats) < 0 ||
+		if (gnet_stats_copy_basic(d, NULL, &sch->bstats) < 0 ||
 		    gnet_stats_copy_queue(d, &sch->qstats) < 0)
 			return -1;
 	}
diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c
index c0466c1..4adbf7f 100644
--- a/net/sched/sch_multiq.c
+++ b/net/sched/sch_multiq.c
@@ -361,7 +361,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	cl_q = q->queues[cl - 1];
 	cl_q->qstats.qlen = cl_q->q.qlen;
-	if (gnet_stats_copy_basic(d, &cl_q->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, &cl_q->qstats) < 0)
 		return -1;
 
diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c
index 03ef99e..68a8f25 100644
--- a/net/sched/sch_prio.c
+++ b/net/sched/sch_prio.c
@@ -325,7 +325,7 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl,
 
 	cl_q = q->queues[cl - 1];
 	cl_q->qstats.qlen = cl_q->q.qlen;
-	if (gnet_stats_copy_basic(d, &cl_q->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &cl_q->bstats) < 0 ||
 	    gnet_stats_copy_queue(d, &cl_q->qstats) < 0)
 		return -1;
 
diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c
index 602ea01..d59f857 100644
--- a/net/sched/sch_qfq.c
+++ b/net/sched/sch_qfq.c
@@ -459,7 +459,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 
 	if (cl != NULL) { /* modify existing class */
 		if (tca[TCA_RATE]) {
-			err = gen_replace_estimator(&cl->bstats, &cl->rate_est,
+			err = gen_replace_estimator(&cl->bstats, NULL,
+						    &cl->rate_est,
 						    qdisc_root_sleeping_lock(sch),
 						    tca[TCA_RATE]);
 			if (err)
@@ -484,7 +485,8 @@ static int qfq_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		cl->qdisc = &noop_qdisc;
 
 	if (tca[TCA_RATE]) {
-		err = gen_new_estimator(&cl->bstats, &cl->rate_est,
+		err = gen_new_estimator(&cl->bstats, NULL,
+					&cl->rate_est,
 					qdisc_root_sleeping_lock(sch),
 					tca[TCA_RATE]);
 		if (err)
@@ -667,7 +669,7 @@ static int qfq_dump_class_stats(struct Qdisc *sch, unsigned long arg,
 	xstats.weight = cl->agg->class_weight;
 	xstats.lmax = cl->agg->lmax;
 
-	if (gnet_stats_copy_basic(d, &cl->bstats) < 0 ||
+	if (gnet_stats_copy_basic(d, NULL, &cl->bstats) < 0 ||
 	    gnet_stats_copy_rate_est(d, &cl->bstats, &cl->rate_est) < 0 ||
 	    gnet_stats_copy_queue(d, &cl->qdisc->qstats) < 0)
 		return -1;