--- zzzz-none-000/linux-3.10.107/net/sched/sch_tbf.c 2017-06-27 09:49:32.000000000 +0000 +++ scorpion-7490-727/linux-3.10.107/net/sched/sch_tbf.c 2021-02-04 17:41:59.000000000 +0000 @@ -101,12 +101,11 @@ struct tbf_sched_data { /* Parameters */ u32 limit; /* Maximal length of backlog: bytes */ + u32 max_size; s64 buffer; /* Token bucket depth/rate: MUST BE >= MTU/B */ s64 mtu; - u32 max_size; struct psched_ratecfg rate; struct psched_ratecfg peak; - bool peak_present; /* Variables */ s64 tokens; /* Current number of B tokens */ @@ -116,18 +115,95 @@ struct qdisc_watchdog watchdog; /* Watchdog timer */ }; + +/* 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_mac_seglen(const struct sk_buff *skb) +{ + unsigned int hdr_len = skb_transport_header(skb) - skb_mac_header(skb); + return hdr_len + skb_gso_transport_seglen(skb); +} + +/* GSO packet is too big, segment it so that tbf can transmit + * each segment in time + */ +static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch) +{ + struct tbf_sched_data *q = qdisc_priv(sch); + struct sk_buff *segs, *nskb; + netdev_features_t features = netif_skb_features(skb); + unsigned int len = 0, prev_len = qdisc_pkt_len(skb); + int ret, nb; + + segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK); + + if (IS_ERR_OR_NULL(segs)) + return qdisc_reshape_fail(skb, sch); + + nb = 0; + while (segs) { + nskb = segs->next; + segs->next = NULL; + qdisc_skb_cb(segs)->pkt_len = segs->len; + len += segs->len; + ret = qdisc_enqueue(segs, q->qdisc); + if (ret != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(ret)) + qdisc_qstats_drop(sch); + } else { + nb++; + } + segs = nskb; + } + sch->q.qlen += nb; + if (nb > 1) + qdisc_tree_reduce_backlog(sch, 1 - nb, prev_len - len); + consume_skb(skb); + return nb > 0 ? NET_XMIT_SUCCESS : NET_XMIT_DROP; +} + static int tbf_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); int ret; - if (qdisc_pkt_len(skb) > q->max_size) + if (qdisc_pkt_len(skb) > q->max_size) { + if (skb_is_gso(skb) && skb_gso_mac_seglen(skb) <= q->max_size) + return tbf_segment(skb, sch); return qdisc_reshape_fail(skb, sch); - + } ret = qdisc_enqueue(skb, q->qdisc); if (ret != NET_XMIT_SUCCESS) { if (net_xmit_drop_count(ret)) - sch->qstats.drops++; + qdisc_qstats_drop(sch); return ret; } @@ -142,11 +218,16 @@ if (q->qdisc->ops->drop && (len = q->qdisc->ops->drop(q->qdisc)) != 0) { sch->q.qlen--; - sch->qstats.drops++; + qdisc_qstats_drop(sch); } return len; } +static bool tbf_peak_present(const struct tbf_sched_data *q) +{ + return q->peak.rate_bytes_ps; +} + static struct sk_buff *tbf_dequeue(struct Qdisc *sch) { struct tbf_sched_data *q = qdisc_priv(sch); @@ -160,10 +241,10 @@ s64 ptoks = 0; unsigned int len = qdisc_pkt_len(skb); - now = ktime_to_ns(ktime_get()); + now = ktime_get_ns(); toks = min_t(s64, now - q->t_c, q->buffer); - if (q->peak_present) { + if (tbf_peak_present(q)) { ptoks = toks + q->ptokens; if (ptoks > q->mtu) ptoks = q->mtu; @@ -189,7 +270,8 @@ } qdisc_watchdog_schedule_ns(&q->watchdog, - now + max_t(long, -toks, -ptoks)); + now + max_t(long, -toks, -ptoks), + true); /* Maybe we have a shorter packet in the queue, which can be sent now. It sounds cool, @@ -202,7 +284,7 @@ (cf. CSZ, HPFQ, HFSC) */ - sch->qstats.overlimits++; + qdisc_qstats_overlimit(sch); } return NULL; } @@ -213,7 +295,7 @@ qdisc_reset(q->qdisc); sch->q.qlen = 0; - q->t_c = ktime_to_ns(ktime_get()); + q->t_c = ktime_get_ns(); q->tokens = q->buffer; q->ptokens = q->mtu; qdisc_watchdog_cancel(&q->watchdog); @@ -223,20 +305,26 @@ [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 }, + [TCA_TBF_BURST] = { .type = NLA_U32 }, + [TCA_TBF_PBURST] = { .type = NLA_U32 }, }; 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; + 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_PTAB, opt, tbf_policy); + err = nla_parse_nested(tb, TCA_TBF_MAX, opt, tbf_policy); if (err < 0) return err; @@ -245,33 +333,59 @@ 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.linklayer == TC_LINKLAYER_UNAWARE) + qdisc_put_rtab(qdisc_get_rtab(&qopt->peakrate, + tb[TCA_TBF_PTAB])); + + 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); + + 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 (qopt->peakrate.rate > qopt->rate.rate) - ptab = qdisc_get_rtab(&qopt->peakrate, tb[TCA_TBF_PTAB]); - if (ptab == NULL) + 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; - } + } - 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 (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)); + } + } else { + memset(&peak, 0, sizeof(peak)); } - if (max_size < 0) + + 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; + } if (q->qdisc != &noop_qdisc) { err = fifo_set_limit(q->qdisc, qopt->limit); @@ -287,32 +401,30 @@ sch_tree_lock(sch); if (child) { - qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen); + qdisc_tree_reduce_backlog(q->qdisc, q->qdisc->q.qlen, + q->qdisc->qstats.backlog); qdisc_destroy(q->qdisc); 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; - psched_ratecfg_precompute(&q->rate, &rtab->rate); - if (ptab) { - psched_ratecfg_precompute(&q->peak, &ptab->rate); - q->peak_present = true; - } else { - q->peak_present = false; - } + memcpy(&q->rate, &rate, sizeof(struct psched_ratecfg)); + memcpy(&q->peak, &peak, sizeof(struct psched_ratecfg)); sch_tree_unlock(sch); err = 0; done: - if (rtab) - qdisc_put_rtab(rtab); - if (ptab) - qdisc_put_rtab(ptab); return err; } @@ -323,7 +435,7 @@ if (opt == NULL) return -EINVAL; - q->t_c = ktime_to_ns(ktime_get()); + q->t_c = ktime_get_ns(); qdisc_watchdog_init(&q->watchdog, sch); q->qdisc = &noop_qdisc; @@ -351,7 +463,7 @@ opt.limit = q->limit; psched_ratecfg_getrate(&opt.rate, &q->rate); - if (q->peak_present) + if (tbf_peak_present(q)) psched_ratecfg_getrate(&opt.peakrate, &q->peak); else memset(&opt.peakrate, 0, sizeof(opt.peakrate)); @@ -359,9 +471,15 @@ 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 (tbf_peak_present(q) && + 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; + return nla_nest_end(skb, nest); nla_put_failure: nla_nest_cancel(skb, nest); @@ -387,13 +505,7 @@ if (new == NULL) new = &noop_qdisc; - sch_tree_lock(sch); - *old = q->qdisc; - q->qdisc = new; - qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); - qdisc_reset(*old); - sch_tree_unlock(sch); - + *old = qdisc_replace(sch, new, &q->qdisc); return 0; }