sch_tbf: add TBF_BURST/TBF_PBURST attribute

When we set burst to 1514 with low rate in userspace,
the kernel get a value of burst that less than 1514,
which doesn't work.

Because it may make some loss when transform burst
to buffer in userspace. This makes burst lose some
bytes, when the kernel transform the buffer back to
burst.

This patch adds two new attributes to support sending
burst/mtu to kernel directly to avoid the loss.

Signed-off-by: Yang Yingliang <yangyingliang@huawei.com>
Acked-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 26 insertions, 5 deletions

diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 4566993..fe11920 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -173,6 +173,8 @@ enum {
 	TCA_TBF_PTAB,
 	TCA_TBF_RATE64,
 	TCA_TBF_PRATE64,
+	TCA_TBF_BURST,
+	TCA_TBF_PBURST,
 	__TCA_TBF_MAX,
 };
 
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index 887e672..fbba5b0 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -307,6 +307,8 @@ static const struct nla_policy tbf_policy[TCA_TBF_MAX + 1] = {
 	[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)
@@ -358,7 +360,12 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 		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 (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 (tb[TCA_TBF_PRATE64])
@@ -366,12 +373,18 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 		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);
+					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 (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));
+		}
 	}
 
 	if (max_size < psched_mtu(qdisc_dev(sch)))
@@ -391,9 +404,15 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
 		q->qdisc = child;
 	}
 	q->limit = qopt->limit;
-	q->mtu = PSCHED_TICKS2NS(qopt->mtu);
+	if (tb[TCA_TBF_PBURST])
+		q->mtu = mtu;
+	else
+		q->mtu = PSCHED_TICKS2NS(qopt->mtu);
 	q->max_size = max_size;
-	q->buffer = PSCHED_TICKS2NS(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;