diff options
Diffstat (limited to 'net/sched')
| -rw-r--r-- | net/sched/sch_api.c | 41 | ||||
| -rw-r--r-- | net/sched/sch_atm.c | 1 | ||||
| -rw-r--r-- | net/sched/sch_cbq.c | 1 | ||||
| -rw-r--r-- | net/sched/sch_generic.c | 8 | ||||
| -rw-r--r-- | net/sched/sch_htb.c | 15 | ||||
| -rw-r--r-- | net/sched/sch_qfq.c | 212 |
6 files changed, 183 insertions, 95 deletions
diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 281c1bded1f6..51b968d3febb 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -285,6 +285,45 @@ static struct Qdisc_ops *qdisc_lookup_ops(struct nlattr *kind) return q; } +/* The linklayer setting were not transferred from iproute2, in older + * versions, and the rate tables lookup systems have been dropped in + * the kernel. To keep backward compatible with older iproute2 tc + * utils, we detect the linklayer setting by detecting if the rate + * table were modified. + * + * For linklayer ATM table entries, the rate table will be aligned to + * 48 bytes, thus some table entries will contain the same value. The + * mpu (min packet unit) is also encoded into the old rate table, thus + * starting from the mpu, we find low and high table entries for + * mapping this cell. If these entries contain the same value, when + * the rate tables have been modified for linklayer ATM. + * + * This is done by rounding mpu to the nearest 48 bytes cell/entry, + * and then roundup to the next cell, calc the table entry one below, + * and compare. + */ +static __u8 __detect_linklayer(struct tc_ratespec *r, __u32 *rtab) +{ + int low = roundup(r->mpu, 48); + int high = roundup(low+1, 48); + int cell_low = low >> r->cell_log; + int cell_high = (high >> r->cell_log) - 1; + + /* rtab is too inaccurate at rates > 100Mbit/s */ + if ((r->rate > (100000000/8)) || (rtab[0] == 0)) { + pr_debug("TC linklayer: Giving up ATM detection\n"); + return TC_LINKLAYER_ETHERNET; + } + + if ((cell_high > cell_low) && (cell_high < 256) + && (rtab[cell_low] == rtab[cell_high])) { + pr_debug("TC linklayer: Detected ATM, low(%d)=high(%d)=%u\n", + cell_low, cell_high, rtab[cell_high]); + return TC_LINKLAYER_ATM; + } + return TC_LINKLAYER_ETHERNET; +} + static struct qdisc_rate_table *qdisc_rtab_list; struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *tab) @@ -308,6 +347,8 @@ struct qdisc_rate_table *qdisc_get_rtab(struct tc_ratespec *r, struct nlattr *ta rtab->rate = *r; rtab->refcnt = 1; memcpy(rtab->data, nla_data(tab), 1024); + if (r->linklayer == TC_LINKLAYER_UNAWARE) + r->linklayer = __detect_linklayer(r, rtab->data); rtab->next = qdisc_rtab_list; qdisc_rtab_list = rtab; } diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index ca8e0a57d945..1f9c31411f19 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -605,6 +605,7 @@ static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, struct sockaddr_atmpvc pvc; int state; + memset(&pvc, 0, sizeof(pvc)); pvc.sap_family = AF_ATMPVC; pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1; pvc.sap_addr.vpi = flow->vcc->vpi; diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c index 71a568862557..7a42c81a19eb 100644 --- a/net/sched/sch_cbq.c +++ b/net/sched/sch_cbq.c @@ -1465,6 +1465,7 @@ static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) unsigned char *b = skb_tail_pointer(skb); struct tc_cbq_wrropt opt; + memset(&opt, 0, sizeof(opt)); opt.flags = 0; opt.allot = cl->allot; opt.priority = cl->priority + 1; diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 4626cef4b76e..48be3d5c0d92 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -25,6 +25,7 @@ #include <linux/rcupdate.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/if_vlan.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/dst.h> @@ -207,15 +208,19 @@ void __qdisc_run(struct Qdisc *q) unsigned long dev_trans_start(struct net_device *dev) { - unsigned long val, res = dev->trans_start; + unsigned long val, res; unsigned int i; + if (is_vlan_dev(dev)) + dev = vlan_dev_real_dev(dev); + res = dev->trans_start; for (i = 0; i < dev->num_tx_queues; i++) { val = netdev_get_tx_queue(dev, i)->trans_start; if (val && time_after(val, res)) res = val; } dev->trans_start = res; + return res; } EXPORT_SYMBOL(dev_trans_start); @@ -904,6 +909,7 @@ void psched_ratecfg_precompute(struct psched_ratecfg *r, memset(r, 0, sizeof(*r)); r->overhead = conf->overhead; r->rate_bytes_ps = conf->rate; + r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK); r->mult = 1; /* * The deal here is to replace a divide by a reciprocal one diff --git a/net/sched/sch_htb.c b/net/sched/sch_htb.c index c2124ea29f45..c2178b15ca6e 100644 --- a/net/sched/sch_htb.c +++ b/net/sched/sch_htb.c @@ -100,7 +100,7 @@ struct htb_class { struct psched_ratecfg ceil; s64 buffer, cbuffer;/* token bucket depth/rate */ s64 mbuffer; /* max wait time */ - int prio; /* these two are used only by leaves... */ + u32 prio; /* these two are used only by leaves... */ int quantum; /* but stored for parent-to-leaf return */ struct tcf_proto *filter_list; /* class attached filters */ @@ -1329,6 +1329,7 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, struct htb_sched *q = qdisc_priv(sch); struct htb_class *cl = (struct htb_class *)*arg, *parent; struct nlattr *opt = tca[TCA_OPTIONS]; + struct qdisc_rate_table *rtab = NULL, *ctab = NULL; struct nlattr *tb[TCA_HTB_MAX + 1]; struct tc_htb_opt *hopt; @@ -1350,6 +1351,18 @@ static int htb_change_class(struct Qdisc *sch, u32 classid, if (!hopt->rate.rate || !hopt->ceil.rate) goto failure; + /* Keeping backward compatible with rate_table based iproute2 tc */ + if (hopt->rate.linklayer == TC_LINKLAYER_UNAWARE) { + rtab = qdisc_get_rtab(&hopt->rate, tb[TCA_HTB_RTAB]); + if (rtab) + qdisc_put_rtab(rtab); + } + if (hopt->ceil.linklayer == TC_LINKLAYER_UNAWARE) { + ctab = qdisc_get_rtab(&hopt->ceil, tb[TCA_HTB_CTAB]); + if (ctab) + qdisc_put_rtab(ctab); + } + if (!cl) { /* new class */ struct Qdisc *new_q; int prio; diff --git a/net/sched/sch_qfq.c b/net/sched/sch_qfq.c index 7c195d972bf0..8056fb4e618a 100644 --- a/net/sched/sch_qfq.c +++ b/net/sched/sch_qfq.c @@ -113,7 +113,6 @@ #define FRAC_BITS 30 /* fixed point arithmetic */ #define ONE_FP (1UL << FRAC_BITS) -#define IWSUM (ONE_FP/QFQ_MAX_WSUM) #define QFQ_MTU_SHIFT 16 /* to support TSO/GSO */ #define QFQ_MIN_LMAX 512 /* see qfq_slot_insert */ @@ -189,6 +188,7 @@ struct qfq_sched { struct qfq_aggregate *in_serv_agg; /* Aggregate being served. */ u32 num_active_agg; /* Num. of active aggregates */ u32 wsum; /* weight sum */ + u32 iwsum; /* inverse weight sum */ unsigned long bitmaps[QFQ_MAX_STATE]; /* Group bitmaps. */ struct qfq_group groups[QFQ_MAX_INDEX + 1]; /* The groups. */ @@ -314,6 +314,7 @@ static void qfq_update_agg(struct qfq_sched *q, struct qfq_aggregate *agg, q->wsum += (int) agg->class_weight * (new_num_classes - agg->num_classes); + q->iwsum = ONE_FP / q->wsum; agg->num_classes = new_num_classes; } @@ -340,6 +341,10 @@ static void qfq_destroy_agg(struct qfq_sched *q, struct qfq_aggregate *agg) { if (!hlist_unhashed(&agg->nonfull_next)) hlist_del_init(&agg->nonfull_next); + q->wsum -= agg->class_weight; + if (q->wsum != 0) + q->iwsum = ONE_FP / q->wsum; + if (q->in_serv_agg == agg) q->in_serv_agg = qfq_choose_next_agg(q); kfree(agg); @@ -821,44 +826,73 @@ static void qfq_make_eligible(struct qfq_sched *q) unsigned long old_vslot = q->oldV >> q->min_slot_shift; if (vslot != old_vslot) { - unsigned long mask = (1ULL << fls(vslot ^ old_vslot)) - 1; + unsigned long mask; + int last_flip_pos = fls(vslot ^ old_vslot); + + if (last_flip_pos > 31) /* higher than the number of groups */ + mask = ~0UL; /* make all groups eligible */ + else + mask = (1UL << last_flip_pos) - 1; + qfq_move_groups(q, mask, IR, ER); qfq_move_groups(q, mask, IB, EB); } } - /* - * The index of the slot in which the aggregate is to be inserted must - * not be higher than QFQ_MAX_SLOTS-2. There is a '-2' and not a '-1' - * because the start time of the group may be moved backward by one - * slot after the aggregate has been inserted, and this would cause - * non-empty slots to be right-shifted by one position. + * The index of the slot in which the input aggregate agg is to be + * inserted must not be higher than QFQ_MAX_SLOTS-2. There is a '-2' + * and not a '-1' because the start time of the group may be moved + * backward by one slot after the aggregate has been inserted, and + * this would cause non-empty slots to be right-shifted by one + * position. * - * If the weight and lmax (max_pkt_size) of the classes do not change, - * then QFQ+ does meet the above contraint according to the current - * values of its parameters. In fact, if the weight and lmax of the - * classes do not change, then, from the theory, QFQ+ guarantees that - * the slot index is never higher than - * 2 + QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) * - * (QFQ_MAX_WEIGHT/QFQ_MAX_WSUM) = 2 + 8 * 128 * (1 / 64) = 18 + * QFQ+ fully satisfies this bound to the slot index if the parameters + * of the classes are not changed dynamically, and if QFQ+ never + * happens to postpone the service of agg unjustly, i.e., it never + * happens that the aggregate becomes backlogged and eligible, or just + * eligible, while an aggregate with a higher approximated finish time + * is being served. In particular, in this case QFQ+ guarantees that + * the timestamps of agg are low enough that the slot index is never + * higher than 2. Unfortunately, QFQ+ cannot provide the same + * guarantee if it happens to unjustly postpone the service of agg, or + * if the parameters of some class are changed. * - * When the weight of a class is increased or the lmax of the class is - * decreased, a new aggregate with smaller slot size than the original - * parent aggregate of the class may happen to be activated. The - * activation of this aggregate should be properly delayed to when the - * service of the class has finished in the ideal system tracked by - * QFQ+. If the activation of the aggregate is not delayed to this - * reference time instant, then this aggregate may be unjustly served - * before other aggregates waiting for service. This may cause the - * above bound to the slot index to be violated for some of these - * unlucky aggregates. + * As for the first event, i.e., an out-of-order service, the + * upper bound to the slot index guaranteed by QFQ+ grows to + * 2 + + * QFQ_MAX_AGG_CLASSES * ((1<<QFQ_MTU_SHIFT)/QFQ_MIN_LMAX) * + * (current_max_weight/current_wsum) <= 2 + 8 * 128 * 1. + * + * The following function deals with this problem by backward-shifting + * the timestamps of agg, if needed, so as to guarantee that the slot + * index is never higher than QFQ_MAX_SLOTS-2. This backward-shift may + * cause the service of other aggregates to be postponed, yet the + * worst-case guarantees of these aggregates are not violated. In + * fact, in case of no out-of-order service, the timestamps of agg + * would have been even lower than they are after the backward shift, + * because QFQ+ would have guaranteed a maximum value equal to 2 for + * the slot index, and 2 < QFQ_MAX_SLOTS-2. Hence the aggregates whose + * service is postponed because of the backward-shift would have + * however waited for the service of agg before being served. + * + * The other event that may cause the slot index to be higher than 2 + * for agg is a recent change of the parameters of some class. If the + * weight of a class is increased or the lmax (max_pkt_size) of the + * class is decreased, then a new aggregate with smaller slot size + * than the original parent aggregate of the class may happen to be + * activated. The activation of this aggregate should be properly + * delayed to when the service of the class has finished in the ideal + * system tracked by QFQ+. If the activation of the aggregate is not + * delayed to this reference time instant, then this aggregate may be + * unjustly served before other aggregates waiting for service. This + * may cause the above bound to the slot index to be violated for some + * of these unlucky aggregates. * * Instead of delaying the activation of the new aggregate, which is - * quite complex, the following inaccurate but simple solution is used: - * if the slot index is higher than QFQ_MAX_SLOTS-2, then the - * timestamps of the aggregate are shifted backward so as to let the - * slot index become equal to QFQ_MAX_SLOTS-2. + * quite complex, the above-discussed capping of the slot index is + * used to handle also the consequences of a change of the parameters + * of a class. */ static void qfq_slot_insert(struct qfq_group *grp, struct qfq_aggregate *agg, u64 roundedS) @@ -1003,9 +1037,61 @@ static inline void charge_actual_service(struct qfq_aggregate *agg) agg->F = agg->S + (u64)service_received * agg->inv_w; } -static inline void qfq_update_agg_ts(struct qfq_sched *q, - struct qfq_aggregate *agg, - enum update_reason reason); +/* Assign a reasonable start time for a new aggregate in group i. + * Admissible values for \hat(F) are multiples of \sigma_i + * no greater than V+\sigma_i . Larger values mean that + * we had a wraparound so we consider the timestamp to be stale. + * + * If F is not stale and F >= V then we set S = F. + * Otherwise we should assign S = V, but this may violate + * the ordering in EB (see [2]). So, if we have groups in ER, + * set S to the F_j of the first group j which would be blocking us. + * We are guaranteed not to move S backward because + * otherwise our group i would still be blocked. + */ +static void qfq_update_start(struct qfq_sched *q, struct qfq_aggregate *agg) +{ + unsigned long mask; + u64 limit, roundedF; + int slot_shift = agg->grp->slot_shift; + + roundedF = qfq_round_down(agg->F, slot_shift); + limit = qfq_round_down(q->V, slot_shift) + (1ULL << slot_shift); + + if (!qfq_gt(agg->F, q->V) || qfq_gt(roundedF, limit)) { + /* timestamp was stale */ + mask = mask_from(q->bitmaps[ER], agg->grp->index); + if (mask) { + struct qfq_group *next = qfq_ffs(q, mask); + if (qfq_gt(roundedF, next->F)) { + if (qfq_gt(limit, next->F)) + agg->S = next->F; + else /* preserve timestamp correctness */ + agg->S = limit; + return; + } + } + agg->S = q->V; + } else /* timestamp is not stale */ + agg->S = agg->F; +} + +/* Update the timestamps of agg before scheduling/rescheduling it for + * service. In particular, assign to agg->F its maximum possible + * value, i.e., the virtual finish time with which the aggregate + * should be labeled if it used all its budget once in service. + */ +static inline void +qfq_update_agg_ts(struct qfq_sched *q, + struct qfq_aggregate *agg, enum update_reason reason) +{ + if (reason != requeue) + qfq_update_start(q, agg); + else /* just charge agg for the service received */ + agg->S = agg->F; + + agg->F = agg->S + (u64)agg->budgetmax * agg->inv_w; +} static void qfq_schedule_agg(struct qfq_sched *q, struct qfq_aggregate *agg); @@ -1077,7 +1163,7 @@ static struct sk_buff *qfq_dequeue(struct Qdisc *sch) else in_serv_agg->budget -= len; - q->V += (u64)len * IWSUM; + q->V += (u64)len * q->iwsum; pr_debug("qfq dequeue: len %u F %lld now %lld\n", len, (unsigned long long) in_serv_agg->F, (unsigned long long) q->V); @@ -1128,66 +1214,6 @@ static struct qfq_aggregate *qfq_choose_next_agg(struct qfq_sched *q) return agg; } -/* - * Assign a reasonable start time for a new aggregate in group i. - * Admissible values for \hat(F) are multiples of \sigma_i - * no greater than V+\sigma_i . Larger values mean that - * we had a wraparound so we consider the timestamp to be stale. - * - * If F is not stale and F >= V then we set S = F. - * Otherwise we should assign S = V, but this may violate - * the ordering in EB (see [2]). So, if we have groups in ER, - * set S to the F_j of the first group j which would be blocking us. - * We are guaranteed not to move S backward because - * otherwise our group i would still be blocked. - */ -static void qfq_update_start(struct qfq_sched *q, struct qfq_aggregate *agg) -{ - unsigned long mask; - u64 limit, roundedF; - int slot_shift = agg->grp->slot_shift; - - roundedF = qfq_round_down(agg->F, slot_shift); - limit = qfq_round_down(q->V, slot_shift) + (1ULL << slot_shift); - - if (!qfq_gt(agg->F, q->V) || qfq_gt(roundedF, limit)) { - /* timestamp was stale */ - mask = mask_from(q->bitmaps[ER], agg->grp->index); - if (mask) { - struct qfq_group *next = qfq_ffs(q, mask); - if (qfq_gt(roundedF, next->F)) { - if (qfq_gt(limit, next->F)) - agg->S = next->F; - else /* preserve timestamp correctness */ - agg->S = limit; - return; - } - } - agg->S = q->V; - } else /* timestamp is not stale */ - agg->S = agg->F; -} - -/* - * Update the timestamps of agg before scheduling/rescheduling it for - * service. In particular, assign to agg->F its maximum possible - * value, i.e., the virtual finish time with which the aggregate - * should be labeled if it used all its budget once in service. - */ -static inline void -qfq_update_agg_ts(struct qfq_sched *q, - struct qfq_aggregate *agg, enum update_reason reason) -{ - if (reason != requeue) - qfq_update_start(q, agg); - else /* just charge agg for the service received */ - agg->S = agg->F; - - agg->F = agg->S + (u64)agg->budgetmax * agg->inv_w; -} - -static void qfq_schedule_agg(struct qfq_sched *, struct qfq_aggregate *); - static int qfq_enqueue(struct sk_buff *skb, struct Qdisc *sch) { struct qfq_sched *q = qdisc_priv(sch); |