1 files changed, 218 insertions, 163 deletions

diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 0b7d78f59d8..18ff6343370 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -19,6 +19,7 @@
 #include <linux/errno.h>
 #include <linux/skbuff.h>
 #include <net/netlink.h>
+#include <net/sch_generic.h>
 #include <net/pkt_sched.h>
 
 
@@ -97,67 +98,118 @@
 	changed the limit is not effective anymore.
 */
 
-struct tbf_sched_data
-{
+struct tbf_sched_data {
 /* Parameters */
 	u32		limit;		/* Maximal length of backlog: bytes */
-	u32		buffer;		/* Token bucket depth/rate: MUST BE >= MTU/B */
-	u32		mtu;
 	u32		max_size;
-	struct qdisc_rate_table	*R_tab;
-	struct qdisc_rate_table	*P_tab;
+	s64		buffer;		/* Token bucket depth/rate: MUST BE >= MTU/B */
+	s64		mtu;
+	struct psched_ratecfg rate;
+	struct psched_ratecfg peak;
 
 /* Variables */
-	long	tokens;			/* Current number of B tokens */
-	long	ptokens;		/* Current number of P tokens */
-	psched_time_t	t_c;		/* Time check-point */
+	s64	tokens;			/* Current number of B tokens */
+	s64	ptokens;		/* Current number of P tokens */
+	s64	t_c;			/* Time check-point */
 	struct Qdisc	*qdisc;		/* Inner qdisc, default - bfifo queue */
 	struct qdisc_watchdog watchdog;	/* Watchdog timer */
 };
 
-#define L2T(q,L)   qdisc_l2t((q)->R_tab,L)
-#define L2T_P(q,L) qdisc_l2t((q)->P_tab,L)
 
-static int tbf_enqueue(struct sk_buff *skb, struct Qdisc* sch)
+/* Time to Length, convert time in ns to length in bytes
+ * to determinate how many bytes can be sent in given time.
+ */
+static u64 psched_ns_t2l(const struct psched_ratecfg *r,
+			 u64 time_in_ns)
 {
-	struct tbf_sched_data *q = qdisc_priv(sch);
-	int ret;
+	/* The formula is :
+	 * len = (time_in_ns * r->rate_bytes_ps) / NSEC_PER_SEC
+	 */
+	u64 len = time_in_ns * r->rate_bytes_ps;
 
-	if (skb->len > q->max_size) {
-		sch->qstats.drops++;
-#ifdef CONFIG_NET_CLS_ACT
-		if (sch->reshape_fail == NULL || sch->reshape_fail(skb, sch))
-#endif
-			kfree_skb(skb);
+	do_div(len, NSEC_PER_SEC);
 
-		return NET_XMIT_DROP;
+	if (unlikely(r->linklayer == TC_LINKLAYER_ATM)) {
+		do_div(len, 53);
+		len = len * 48;
 	}
 
-	if ((ret = q->qdisc->enqueue(skb, q->qdisc)) != 0) {
-		sch->qstats.drops++;
-		return ret;
-	}
+	if (len > r->overhead)
+		len -= r->overhead;
+	else
+		len = 0;
 
-	sch->q.qlen++;
-	sch->bstats.bytes += skb->len;
-	sch->bstats.packets++;
-	return 0;
+	return len;
 }
 
-static int tbf_requeue(struct sk_buff *skb, struct Qdisc* sch)
+/*
+ * Return length of individual segments of a gso packet,
+ * including all headers (MAC, IP, TCP/UDP)
+ */
+static unsigned int skb_gso_mac_seglen(const struct sk_buff *skb)
+{
+	unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
+	return hdr_len + skb_gso_transport_seglen(skb);
+}
+
+/* GSO packet is too big, segment it so that tbf can transmit
+ * each segment in time
+ */
+static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
+{
+	struct tbf_sched_data *q = qdisc_priv(sch);
+	struct sk_buff *segs, *nskb;
+	netdev_features_t features = netif_skb_features(skb);
+	int ret, nb;
+
+	segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
+
+	if (IS_ERR_OR_NULL(segs))
+		return qdisc_reshape_fail(skb, sch);
+
+	nb = 0;
+	while (segs) {
+		nskb = segs->next;
+		segs->next = NULL;
+		qdisc_skb_cb(segs)->pkt_len = segs->len;
+		ret = qdisc_enqueue(segs, q->qdisc);
+		if (ret != NET_XMIT_SUCCESS) {
+			if (net_xmit_drop_count(ret))
+				sch->qstats.drops++;
+		} else {
+			nb++;
+		}
+		segs = nskb;
+	}
+	sch->q.qlen += nb;
+	if (nb > 1)
+		qdisc_tree_decrease_qlen(sch, 1 - nb);
+	consume_skb(skb);
+	return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP;
+}
+
+static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
 	int ret;
 
-	if ((ret = q->qdisc->ops->requeue(skb, q->qdisc)) == 0) {
-		sch->q.qlen++;
-		sch->qstats.requeues++;
+	if (qdisc_pkt_len(skb) > q->max_size) {
+		if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size)
+			return tbf_segment(skb, sch);
+		return qdisc_reshape_fail(skb, sch);
+	}
+	ret = qdisc_enqueue(skb, q->qdisc);
+	if (ret != NET_XMIT_SUCCESS) {
+		if (net_xmit_drop_count(ret))
+			sch->qstats.drops++;
+		return ret;
 	}
 
-	return ret;
+	sch->q.qlen++;
+	return NET_XMIT_SUCCESS;
 }
 
-static unsigned int tbf_drop(struct Qdisc* sch)
+static unsigned int tbf_drop(struct Qdisc *sch)
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
 	unsigned int len = 0;
@@ -169,44 +221,54 @@ static unsigned int tbf_drop(struct Qdisc* sch)
 	return len;
 }
 
-static struct sk_buff *tbf_dequeue(struct Qdisc* sch)
+static bool tbf_peak_present(const struct tbf_sched_data *q)
+{
+	return q->peak.rate_bytes_ps;
+}
+
+static struct sk_buff *tbf_dequeue(struct Qdisc *sch)
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
 	struct sk_buff *skb;
 
-	skb = q->qdisc->dequeue(q->qdisc);
+	skb = q->qdisc->ops->peek(q->qdisc);
 
 	if (skb) {
-		psched_time_t now;
-		long toks;
-		long ptoks = 0;
-		unsigned int len = skb->len;
+		s64 now;
+		s64 toks;
+		s64 ptoks = 0;
+		unsigned int len = qdisc_pkt_len(skb);
 
-		now = psched_get_time();
-		toks = psched_tdiff_bounded(now, q->t_c, q->buffer);
+		now = ktime_to_ns(ktime_get());
+		toks = min_t(s64, now - q->t_c, q->buffer);
 
-		if (q->P_tab) {
+		if (tbf_peak_present(q)) {
 			ptoks = toks + q->ptokens;
-			if (ptoks > (long)q->mtu)
+			if (ptoks > q->mtu)
 				ptoks = q->mtu;
-			ptoks -= L2T_P(q, len);
+			ptoks -= (s64) psched_l2t_ns(&q->peak, len);
 		}
 		toks += q->tokens;
-		if (toks > (long)q->buffer)
+		if (toks > q->buffer)
 			toks = q->buffer;
-		toks -= L2T(q, len);
+		toks -= (s64) psched_l2t_ns(&q->rate, len);
 
 		if ((toks|ptoks) >= 0) {
+			skb = qdisc_dequeue_peeked(q->qdisc);
+			if (unlikely(!skb))
+				return NULL;
+
 			q->t_c = now;
 			q->tokens = toks;
 			q->ptokens = ptoks;
 			sch->q.qlen--;
-			sch->flags &= ~TCQ_F_THROTTLED;
+			qdisc_unthrottled(sch);
+			qdisc_bstats_update(sch, skb);
 			return skb;
 		}
 
-		qdisc_watchdog_schedule(&q->watchdog,
-					now + max_t(long, -toks, -ptoks));
+		qdisc_watchdog_schedule_ns(&q->watchdog,
+					   now + max_t(long, -toks, -ptoks));
 
 		/* Maybe we have a shorter packet in the queue,
 		   which can be sent now. It sounds cool,
@@ -219,75 +281,47 @@ static struct sk_buff *tbf_dequeue(struct Qdisc* sch)
 		   (cf. CSZ, HPFQ, HFSC)
 		 */
 
-		if (q->qdisc->ops->requeue(skb, q->qdisc) != NET_XMIT_SUCCESS) {
-			/* When requeue fails skb is dropped */
-			qdisc_tree_decrease_qlen(q->qdisc, 1);
-			sch->qstats.drops++;
-		}
-
 		sch->qstats.overlimits++;
 	}
 	return NULL;
 }
 
-static void tbf_reset(struct Qdisc* sch)
+static void tbf_reset(struct Qdisc *sch)
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
 
 	qdisc_reset(q->qdisc);
 	sch->q.qlen = 0;
-	q->t_c = psched_get_time();
+	q->t_c = ktime_to_ns(ktime_get());
 	q->tokens = q->buffer;
 	q->ptokens = q->mtu;
 	qdisc_watchdog_cancel(&q->watchdog);
 }
 
-static struct Qdisc *tbf_create_dflt_qdisc(struct Qdisc *sch, u32 limit)
-{
-	struct Qdisc *q;
-	struct nlattr *nla;
-	int ret;
-
-	q = qdisc_create_dflt(sch->dev, &bfifo_qdisc_ops,
-			      TC_H_MAKE(sch->handle, 1));
-	if (q) {
-		nla = kmalloc(nla_attr_size(sizeof(struct tc_fifo_qopt)),
-			      GFP_KERNEL);
-		if (nla) {
-			nla->nla_type = RTM_NEWQDISC;
-			nla->nla_len = nla_attr_size(sizeof(struct tc_fifo_qopt));
-			((struct tc_fifo_qopt *)nla_data(nla))->limit = limit;
-
-			ret = q->ops->change(q, nla);
-			kfree(nla);
-
-			if (ret == 0)
-				return q;
-		}
-		qdisc_destroy(q);
-	}
-
-	return NULL;
-}
-
 static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = {
 	[TCA_TBF_PARMS]	= { .len = sizeof(struct tc_tbf_qopt) },
 	[TCA_TBF_RTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
 	[TCA_TBF_PTAB]	= { .type = NLA_BINARY, .len = TC_RTAB_SIZE },
+	[TCA_TBF_RATE64]	= { .type = NLA_U64 },
+	[TCA_TBF_PRATE64]	= { .type = NLA_U64 },
+	[TCA_TBF_BURST] = { .type = NLA_U32 },
+	[TCA_TBF_PBURST] = { .type = NLA_U32 },
 };
 
-static int tbf_change(struct Qdisc* sch, struct nlattr *opt)
+static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 {
 	int err;
 	struct tbf_sched_data *q = qdisc_priv(sch);
-	struct nlattr *tb[TCA_TBF_PTAB + 1];
+	struct nlattr *tb[TCA_TBF_MAX + 1];
 	struct tc_tbf_qopt *qopt;
-	struct qdisc_rate_table *rtab = NULL;
-	struct qdisc_rate_table *ptab = NULL;
 	struct Qdisc *child = NULL;
-	int max_size,n;
+	struct psched_ratecfg rate;
+	struct psched_ratecfg peak;
+	u64 max_size;
+	s64 buffer, mtu;
+	u64 rate64 = 0, prate64 = 0;
 
-	err = nla_parse_nested(tb, TCA_TBF_PTAB, opt, tbf_policy);
+	err = nla_parse_nested(tb, TCA_TBF_MAX, opt, tbf_policy);
 	if (err < 0)
 		return err;
 
@@ -296,67 +330,108 @@ static int tbf_change(struct Qdisc* sch, struct nlattr *opt)
 		goto done;
 
 	qopt = nla_data(tb[TCA_TBF_PARMS]);
-	rtab = qdisc_get_rtab(&qopt->rate, tb[TCA_TBF_RTAB]);
-	if (rtab == NULL)
-		goto done;
+	if (qopt->rate.linklayer == TC_LINKLAYER_UNAWARE)
+		qdisc_put_rtab(qdisc_get_rtab(&qopt->rate,
+					      tb[TCA_TBF_RTAB]));
+
+	if (qopt->peakrate.linklayer == TC_LINKLAYER_UNAWARE)
+			qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate,
+						      tb[TCA_TBF_PTAB]));
+
+	buffer = min_t(u64, PSCHED_TICKS2NS(qopt->buffer), ~0U);
+	mtu = min_t(u64, PSCHED_TICKS2NS(qopt->mtu), ~0U);
+
+	if (tb[TCA_TBF_RATE64])
+		rate64 = nla_get_u64(tb[TCA_TBF_RATE64]);
+	psched_ratecfg_precompute(&rate, &qopt->rate, rate64);
+
+	if (tb[TCA_TBF_BURST]) {
+		max_size = nla_get_u32(tb[TCA_TBF_BURST]);
+		buffer = psched_l2t_ns(&rate, max_size);
+	} else {
+		max_size = min_t(u64, psched_ns_t2l(&rate, buffer), ~0U);
+	}
 
 	if (qopt->peakrate.rate) {
-		if (qopt->peakrate.rate > qopt->rate.rate)
-			ptab = qdisc_get_rtab(&qopt->peakrate, tb[TCA_TBF_PTAB]);
-		if (ptab == NULL)
+		if (tb[TCA_TBF_PRATE64])
+			prate64 = nla_get_u64(tb[TCA_TBF_PRATE64]);
+		psched_ratecfg_precompute(&peak, &qopt->peakrate, prate64);
+		if (peak.rate_bytes_ps <= rate.rate_bytes_ps) {
+			pr_warn_ratelimited("sch_tbf: peakrate %llu is lower than or equals to rate %llu !\n",
+					peak.rate_bytes_ps, rate.rate_bytes_ps);
+			err = -EINVAL;
 			goto done;
+		}
+
+		if (tb[TCA_TBF_PBURST]) {
+			u32 pburst = nla_get_u32(tb[TCA_TBF_PBURST]);
+			max_size = min_t(u32, max_size, pburst);
+			mtu = psched_l2t_ns(&peak, pburst);
+		} else {
+			max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu));
+		}
+	} else {
+		memset(&peak, 0, sizeof(peak));
 	}
 
-	for (n = 0; n < 256; n++)
-		if (rtab->data[n] > qopt->buffer) break;
-	max_size = (n << qopt->rate.cell_log)-1;
-	if (ptab) {
-		int size;
+	if (max_size < psched_mtu(qdisc_dev(sch)))
+		pr_warn_ratelimited("sch_tbf: burst %llu is lower than device %s mtu (%u) !\n",
+				    max_size, qdisc_dev(sch)->name,
+				    psched_mtu(qdisc_dev(sch)));
 
-		for (n = 0; n < 256; n++)
-			if (ptab->data[n] > qopt->mtu) break;
-		size = (n << qopt->peakrate.cell_log)-1;
-		if (size < max_size) max_size = size;
-	}
-	if (max_size < 0)
+	if (!max_size) {
+		err = -EINVAL;
 		goto done;
+	}
 
-	if (qopt->limit > 0) {
-		if ((child = tbf_create_dflt_qdisc(sch, qopt->limit)) == NULL)
+	if (q->qdisc != &noop_qdisc) {
+		err = fifo_set_limit(q->qdisc, qopt->limit);
+		if (err)
+			goto done;
+	} else if (qopt->limit > 0) {
+		child = fifo_create_dflt(sch, &bfifo_qdisc_ops, qopt->limit);
+		if (IS_ERR(child)) {
+			err = PTR_ERR(child);
 			goto done;
+		}
 	}
 
 	sch_tree_lock(sch);
 	if (child) {
 		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
-		qdisc_destroy(xchg(&q->qdisc, child));
+		qdisc_destroy(q->qdisc);
+		q->qdisc = child;
 	}
 	q->limit = qopt->limit;
-	q->mtu = qopt->mtu;
+	if (tb[TCA_TBF_PBURST])
+		q->mtu = mtu;
+	else
+		q->mtu = PSCHED_TICKS2NS(qopt->mtu);
 	q->max_size = max_size;
-	q->buffer = qopt->buffer;
+	if (tb[TCA_TBF_BURST])
+		q->buffer = buffer;
+	else
+		q->buffer = PSCHED_TICKS2NS(qopt->buffer);
 	q->tokens = q->buffer;
 	q->ptokens = q->mtu;
-	rtab = xchg(&q->R_tab, rtab);
-	ptab = xchg(&q->P_tab, ptab);
+
+	memcpy(&q->rate, &rate, sizeof(struct psched_ratecfg));
+	memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg));
+
 	sch_tree_unlock(sch);
 	err = 0;
 done:
-	if (rtab)
-		qdisc_put_rtab(rtab);
-	if (ptab)
-		qdisc_put_rtab(ptab);
 	return err;
 }
 
-static int tbf_init(struct Qdisc* sch, struct nlattr *opt)
+static int tbf_init(struct Qdisc *sch, struct nlattr *opt)
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
 
 	if (opt == NULL)
 		return -EINVAL;
 
-	q->t_c = psched_get_time();
+	q->t_c = ktime_to_ns(ktime_get());
 	qdisc_watchdog_init(&q->watchdog, sch);
 	q->qdisc = &noop_qdisc;
 
@@ -368,12 +443,6 @@ static void tbf_destroy(struct Qdisc *sch)
 	struct tbf_sched_data *q = qdisc_priv(sch);
 
 	qdisc_watchdog_cancel(&q->watchdog);
-
-	if (q->P_tab)
-		qdisc_put_rtab(q->P_tab);
-	if (q->R_tab)
-		qdisc_put_rtab(q->R_tab);
-
 	qdisc_destroy(q->qdisc);
 }
 
@@ -383,22 +452,30 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb)
 	struct nlattr *nest;
 	struct tc_tbf_qopt opt;
 
+	sch->qstats.backlog = q->qdisc->qstats.backlog;
 	nest = nla_nest_start(skb, TCA_OPTIONS);
 	if (nest == NULL)
 		goto nla_put_failure;
 
 	opt.limit = q->limit;
-	opt.rate = q->R_tab->rate;
-	if (q->P_tab)
-		opt.peakrate = q->P_tab->rate;
+	psched_ratecfg_getrate(&opt.rate, &q->rate);
+	if (tbf_peak_present(q))
+		psched_ratecfg_getrate(&opt.peakrate, &q->peak);
 	else
 		memset(&opt.peakrate, 0, sizeof(opt.peakrate));
-	opt.mtu = q->mtu;
-	opt.buffer = q->buffer;
-	NLA_PUT(skb, TCA_TBF_PARMS, sizeof(opt), &opt);
+	opt.mtu = PSCHED_NS2TICKS(q->mtu);
+	opt.buffer = PSCHED_NS2TICKS(q->buffer);
+	if (nla_put(skb, TCA_TBF_PARMS, sizeof(opt), &opt))
+		goto nla_put_failure;
+	if (q->rate.rate_bytes_ps >= (1ULL << 32) &&
+	    nla_put_u64(skb, TCA_TBF_RATE64, q->rate.rate_bytes_ps))
+		goto nla_put_failure;
+	if (tbf_peak_present(q) &&
+	    q->peak.rate_bytes_ps >= (1ULL << 32) &&
+	    nla_put_u64(skb, TCA_TBF_PRATE64, q->peak.rate_bytes_ps))
+		goto nla_put_failure;
 
-	nla_nest_end(skb, nest);
-	return skb->len;
+	return nla_nest_end(skb, nest);
 
 nla_put_failure:
 	nla_nest_cancel(skb, nest);
@@ -410,9 +487,6 @@ static int tbf_dump_class(struct Qdisc *sch, unsigned long cl,
 {
 	struct tbf_sched_data *q = qdisc_priv(sch);
 
-	if (cl != 1) 	/* only one class */
-		return -ENOENT;
-
 	tcm->tcm_handle |= TC_H_MIN(1);
 	tcm->tcm_info = q->qdisc->handle;
 
@@ -428,7 +502,8 @@ static int tbf_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new,
 		new = &noop_qdisc;
 
 	sch_tree_lock(sch);
-	*old = xchg(&q->qdisc, new);
+	*old = q->qdisc;
+	q->qdisc = new;
 	qdisc_tree_decrease_qlen(*old, (*old)->q.qlen);
 	qdisc_reset(*old);
 	sch_tree_unlock(sch);
@@ -451,17 +526,6 @@ static void tbf_put(struct Qdisc *sch, unsigned long arg)
 {
 }
 
-static int tbf_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
-			    struct nlattr **tca, unsigned long *arg)
-{
-	return -ENOSYS;
-}
-
-static int tbf_delete(struct Qdisc *sch, unsigned long arg)
-{
-	return -ENOSYS;
-}
-
 static void tbf_walk(struct Qdisc *sch, struct qdisc_walker *walker)
 {
 	if (!walker->stop) {
@@ -474,21 +538,12 @@ static void tbf_walk(struct Qdisc *sch, struct qdisc_walker *walker)
 	}
 }
 
-static struct tcf_proto **tbf_find_tcf(struct Qdisc *sch, unsigned long cl)
-{
-	return NULL;
-}
-
-static const struct Qdisc_class_ops tbf_class_ops =
-{
+static const struct Qdisc_class_ops tbf_class_ops = {
 	.graft		=	tbf_graft,
 	.leaf		=	tbf_leaf,
 	.get		=	tbf_get,
 	.put		=	tbf_put,
-	.change		=	tbf_change_class,
-	.delete		=	tbf_delete,
 	.walk		=	tbf_walk,
-	.tcf_chain	=	tbf_find_tcf,
 	.dump		=	tbf_dump_class,
 };
 
@@ -499,7 +554,7 @@ static struct Qdisc_ops tbf_qdisc_ops __read_mostly = {
 	.priv_size	=	sizeof(struct tbf_sched_data),
 	.enqueue	=	tbf_enqueue,
 	.dequeue	=	tbf_dequeue,
-	.requeue	=	tbf_requeue,
+	.peek		=	qdisc_peek_dequeued,
 	.drop		=	tbf_drop,
 	.init		=	tbf_init,
 	.reset		=	tbf_reset,