1 files changed, 43 insertions, 11 deletions

diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 1aaf1b6e51a..a6090051c5d 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 +118,22 @@ struct tbf_sched_data {
 };
 
 
+/*
+ * 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 +153,8 @@ 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 +176,7 @@ 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);
 	}
@@ -266,20 +279,23 @@ 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 },
 };
 
 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;
+	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;
 
@@ -316,6 +332,11 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 	if (max_size < 0)
 		goto done;
 
+	if (max_size < psched_mtu(qdisc_dev(sch)))
+		pr_warn_ratelimited("sch_tbf: burst %u is lower than device %s mtu (%u) !\n",
+				    max_size, qdisc_dev(sch)->name,
+				    psched_mtu(qdisc_dev(sch)));
+
 	if (q->qdisc != &noop_qdisc) {
 		err = fifo_set_limit(q->qdisc, qopt->limit);
 		if (err)
@@ -341,9 +362,13 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 	q->tokens = q->buffer;
 	q->ptokens = q->mtu;
 
-	psched_ratecfg_precompute(&q->rate, &rtab->rate);
+	if (tb[TCA_TBF_RATE64])
+		rate64 = nla_get_u64(tb[TCA_TBF_RATE64]);
+	psched_ratecfg_precompute(&q->rate, &rtab->rate, rate64);
 	if (ptab) {
-		psched_ratecfg_precompute(&q->peak, &ptab->rate);
+		if (tb[TCA_TBF_PRATE64])
+			prate64 = nla_get_u64(tb[TCA_TBF_PRATE64]);
+		psched_ratecfg_precompute(&q->peak, &ptab->rate, prate64);
 		q->peak_present = true;
 	} else {
 		q->peak_present = false;
@@ -402,6 +427,13 @@ static int tbf_dump(struct Qdisc *sch, struct sk_buff *skb)
 	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 (q->peak_present &&
+	    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;