| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <1386313205-87660-2-git-send-email-yangyingliang@huawei.com>
Date: Fri, 6 Dec 2013 15:00:04 +0800
From: Yang Yingliang <yangyingliang@...wei.com>
To: <davem@...emloft.net>, <netdev@...r.kernel.org>
CC: <eric.dumazet@...il.com>, <brouer@...hat.com>, <jpirko@...hat.com>,
<jbrouer@...hat.com>
Subject: [PATCH net v6 1/2] net: sched: tbf: fix the calculation of max_size
Current max_size is caluated from rate table. Now, the rate table
has been replaced and it's wrong to caculate max_size based on this
rate table. It can lead wrong calculation of max_size.
The burst in kernel may be lower than user asked, because burst may gets
some loss when transform it to buffer(E.g. "burst 40kb rate 30mbit/s")
and it seems we cannot avoid this loss. Burst's value(max_size) based on
rate table may be equal user asked. If a packet's length is max_size, this
packet will be stalled in tbf_dequeue() because its length is above the
burst in kernel so that it cannot get enough tokens. The max_size guards
against enqueuing packet sizes above q->buffer "time" in tbf_enqueue().
To make consistent with the calculation of tokens, this patch add a helper
psched_ns_t2l() to calculate burst(max_size) directly to fix this problem.
After this fix, we can support to using 64bit rates to calculate burst as well.
Signed-off-by: Yang Yingliang <yangyingliang@...wei.com>
---
net/sched/sch_tbf.c | 104 ++++++++++++++++++++++++++++++----------------------
1 file changed, 61 insertions(+), 43 deletions(-)
diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c
index a609005..dd731f5 100644
--- a/net/sched/sch_tbf.c
+++ b/net/sched/sch_tbf.c
@@ -118,6 +118,30 @@ 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))
+ len = (len / 53) * 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)
@@ -289,10 +313,8 @@ 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;
+ u64 max_size;
u64 rate64 = 0, prate64 = 0;
err = nla_parse_nested(tb, TCA_TBF_MAX, opt, tbf_policy);
@@ -304,38 +326,13 @@ 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->peakrate.rate) {
- if (qopt->peakrate.rate > qopt->rate.rate)
- ptab = qdisc_get_rtab(&qopt->peakrate, tb[TCA_TBF_PTAB]);
- if (ptab == NULL)
- goto done;
- }
+ if (qopt->rate.linklayer == TC_LINKLAYER_UNAWARE)
+ qdisc_put_rtab(qdisc_get_rtab(&qopt->rate,
+ tb[TCA_TBF_RTAB]));
- 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 (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 (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);
@@ -357,30 +354,51 @@ static int tbf_change(struct Qdisc *sch, struct nlattr *opt)
}
q->limit = qopt->limit;
q->mtu = PSCHED_TICKS2NS(qopt->mtu);
- q->max_size = max_size;
q->buffer = PSCHED_TICKS2NS(qopt->buffer);
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) {
+ psched_ratecfg_precompute(&q->rate, &qopt->rate, rate64);
+ if (!q->rate.rate_bytes_ps)
+ goto unlock_done;
+
+ max_size = min_t(u64, psched_ns_t2l(&q->rate, q->buffer), ~0U);
+
+ if (qopt->peakrate.rate) {
if (tb[TCA_TBF_PRATE64])
prate64 = nla_get_u64(tb[TCA_TBF_PRATE64]);
- psched_ratecfg_precompute(&q->peak, &ptab->rate, prate64);
+ psched_ratecfg_precompute(&q->peak, &qopt->peakrate, prate64);
+ if (q->peak.rate_bytes_ps <= q->rate.rate_bytes_ps) {
+ pr_warn_ratelimited("sch_tbf: peakrate %llu is lower than or equals to rate %llu !\n",
+ q->peak.rate_bytes_ps, q->rate.rate_bytes_ps);
+ goto unlock_done;
+ }
+
+ max_size = min_t(u64, max_size, psched_ns_t2l(&q->peak, q->mtu));
q->peak_present = true;
} else {
q->peak_present = false;
}
+ 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)
+ goto unlock_done;
+
+ q->max_size = max_size;
+
sch_tree_unlock(sch);
- err = 0;
+ return 0;
+
+unlock_done:
+ sch_tree_unlock(sch);
+ err = -EINVAL;
done:
- if (rtab)
- qdisc_put_rtab(rtab);
- if (ptab)
- qdisc_put_rtab(ptab);
return err;
}
--
1.8.0
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists