1 files changed, 92 insertions, 47 deletions

diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 68f98595819c..887e672f9d7d 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -21,6 +21,7 @@
 #include <net/netlink.h>
 #include <net/sch_generic.h>
 #include <net/pkt_sched.h>
+#include <net/tcp.h>
 
 
 /*	Simple Token Bucket Filter.
@@ -117,6 +118,48 @@ struct tbf_sched_data {
 };
 
 
+/* 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)
+{
+	/* The formula is :
+	 * len = (time_in_ns * r->rate_bytes_ps) / NSEC_PER_SEC
+	 */
+	u64 len = time_in_ns * r->rate_bytes_ps;
+
+	do_div(len, NSEC_PER_SEC);
+
+	if (unlikely(r->linklayer == TC_LINKLAYER_ATM)) {
+		do_div(len, 53);
+		len = len * 48;
+	}
+
+	if (len > r->overhead)
+		len -= r->overhead;
+	else
+		len = 0;
+
+	return len;
+}
+
+/*
+ * Return length of individual segments of a gso packet,
+ * including all headers (MAC, IP, TCP/UDP)
+ */
+static unsigned int skb_gso_seglen(const struct sk_buff *skb)
+{
+	unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb);
+	const struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+	if (likely(shinfo->gso_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)))
+		hdr_len += tcp_hdrlen(skb);
+	else
+		hdr_len += sizeof(struct udphdr);
+	return hdr_len + shinfo->gso_size;
+}
+
 /* GSO packet is too big, segment it so that tbf can transmit
  * each segment in time
  */
@@ -136,12 +179,8 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch)
 	while (segs) {
 		nskb = segs->next;
 		segs->next = NULL;
-		if (likely(segs->len <= q->max_size)) {
-			qdisc_skb_cb(segs)->pkt_len = segs->len;
-			ret = qdisc_enqueue(segs, q->qdisc);
-		} else {
-			ret = qdisc_reshape_fail(skb, sch);
-		}
+		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++;
@@ -163,7 +202,7 @@ static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch)
 	int ret;
 
 	if (qdisc_pkt_len(skb) > q->max_size) {
-		if (skb_is_gso(skb))
+		if (skb_is_gso(skb) && skb_gso_seglen(skb) <= q->max_size)
 			return tbf_segment(skb, sch);
 		return qdisc_reshape_fail(skb, sch);
 	}
@@ -276,10 +315,11 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 	struct tbf_sched_data *q = qdisc_priv(sch);
 	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_MAX, opt, tbf_policy);
@@ -291,33 +331,13 @@ 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.rate) {
-		if (qopt->peakrate.rate > qopt->rate.rate)
-			ptab = qdisc_get_rtab(&qopt->peakrate, tb[TCA_TBF_PTAB]);
-		if (ptab == NULL)
-			goto done;
-	}
-
-	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;
-
-		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)
-		goto done;
+	if (qopt->peakrate.linklayer == TC_LINKLAYER_UNAWARE)
+			qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate,
+						      tb[TCA_TBF_PTAB]));
 
 	if (q->qdisc != &noop_qdisc) {
 		err = fifo_set_limit(q->qdisc, qopt->limit);
@@ -331,6 +351,39 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 		}
 	}
 
+	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);
+
+	max_size = min_t(u64, psched_ns_t2l(&rate, buffer), ~0U);
+
+	if (qopt->peakrate.rate) {
+		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;
+		}
+
+		max_size = min_t(u64, max_size, psched_ns_t2l(&peak, mtu));
+	}
+
+	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)));
+
+	if (!max_size) {
+		err = -EINVAL;
+		goto done;
+	}
+
 	sch_tree_lock(sch);
 	if (child) {
 		qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen);
@@ -344,13 +397,9 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 	q->tokens = q->buffer;
 	q->ptokens = q->mtu;
 
-	if (tb[TCA_TBF_RATE64])
-		rate64 = nla_get_u64(tb[TCA_TBF_RATE64]);
-	psched_ratecfg_precompute(&q->rate, &rtab->rate, rate64);
-	if (ptab) {
-		if (tb[TCA_TBF_PRATE64])
-			prate64 = nla_get_u64(tb[TCA_TBF_PRATE64]);
-		psched_ratecfg_precompute(&q->peak, &ptab->rate, prate64);
+	memcpy(&q->rate, &rate, sizeof(struct psched_ratecfg));
+	if (qopt->peakrate.rate) {
+		memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg));
 		q->peak_present = true;
 	} else {
 		q->peak_present = false;
@@ -359,10 +408,6 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 	sch_tree_unlock(sch);
 	err = 0;
 done:
-	if (rtab)
-		qdisc_put_rtab(rtab);
-	if (ptab)
-		qdisc_put_rtab(ptab);
 	return err;
 }