From patchwork Tue Dec 10 03:49:17 2013 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yang Yingliang X-Patchwork-Id: 299264 X-Patchwork-Delegate: davem@davemloft.net Return-Path: X-Original-To: patchwork-incoming@ozlabs.org Delivered-To: patchwork-incoming@ozlabs.org Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 9D9E32C00B3 for ; Tue, 10 Dec 2013 14:49:44 +1100 (EST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1751834Ab3LJDtk (ORCPT ); Mon, 9 Dec 2013 22:49:40 -0500 Received: from szxga02-in.huawei.com ([119.145.14.65]:6000 "EHLO szxga02-in.huawei.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1751632Ab3LJDti (ORCPT ); Mon, 9 Dec 2013 22:49:38 -0500 Received: from 172.24.2.119 (EHLO szxeml205-edg.china.huawei.com) ([172.24.2.119]) by szxrg02-dlp.huawei.com (MOS 4.3.7-GA FastPath queued) with ESMTP id BMS94910; Tue, 10 Dec 2013 11:49:24 +0800 (CST) Received: from szxeml459-hub.china.huawei.com (10.82.67.202) by szxeml205-edg.china.huawei.com (172.24.2.58) with Microsoft SMTP Server (TLS) id 14.3.158.1; Tue, 10 Dec 2013 11:49:21 +0800 Received: from localhost (10.135.68.218) by szxeml459-hub.china.huawei.com (10.82.67.202) with Microsoft SMTP Server id 14.3.158.1; Tue, 10 Dec 2013 11:49:20 +0800 From: Yang Yingliang To: , CC: , , , Subject: [PATCH net v7 1/2] net: sched: tbf: fix the calculation of max_size Date: Tue, 10 Dec 2013 11:49:17 +0800 Message-ID: <1386647358-47944-2-git-send-email-yangyingliang@huawei.com> X-Mailer: git-send-email 1.8.1.msysgit.1 In-Reply-To: <1386647358-47944-1-git-send-email-yangyingliang@huawei.com> References: <1386647358-47944-1-git-send-email-yangyingliang@huawei.com> MIME-Version: 1.0 X-Originating-IP: [10.135.68.218] X-CFilter-Loop: Reflected Sender: netdev-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: netdev@vger.kernel.org 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 --- net/sched/sch_tbf.c | 119 +++++++++++++++++++++++++++++++--------------------- 1 file changed, 71 insertions(+), 48 deletions(-) diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index a609005..b7f0683 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 +313,9 @@ 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; + s64 buffer, mtu; u64 rate64 = 0, prate64 = 0; err = nla_parse_nested(tb, TCA_TBF_MAX, opt, tbf_policy); @@ -304,38 +327,13 @@ 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 (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); @@ -349,38 +347,63 @@ 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); + sch_tree_lock(sch); if (child) { qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen); qdisc_destroy(q->qdisc); q->qdisc = child; } - 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, 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, 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->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; + + sch_tree_unlock(sch); + return 0; + +unlock_done: sch_tree_unlock(sch); - err = 0; + err = -EINVAL; done: - if (rtab) - qdisc_put_rtab(rtab); - if (ptab) - qdisc_put_rtab(ptab); return err; }