| Author | Tokens | Token Proportion | Commits | Commit Proportion |
|---|---|---|---|---|
| Eric Dumazet | 1075 | 15.71% | 50 | 16.34% |
| David S. Miller | 982 | 14.35% | 31 | 10.13% |
| Linus Torvalds (pre-git) | 891 | 13.02% | 37 | 12.09% |
| John Fastabend | 887 | 12.96% | 12 | 3.92% |
| Américo Wang | 353 | 5.16% | 13 | 4.25% |
| Lin Yun Sheng | 265 | 3.87% | 6 | 1.96% |
| Jiri Pirko | 227 | 3.32% | 2 | 0.65% |
| Krishna Kumar | 209 | 3.05% | 4 | 1.31% |
| Jesper Dangaard Brouer | 209 | 3.05% | 6 | 1.96% |
| Jakub Kiciński | 174 | 2.54% | 6 | 1.96% |
| Patrick McHardy | 169 | 2.47% | 10 | 3.27% |
| Jarek Poplawski | 109 | 1.59% | 9 | 2.94% |
| Thomas Graf | 95 | 1.39% | 7 | 2.29% |
| Vlad Buslov | 93 | 1.36% | 3 | 0.98% |
| Baowen Zheng | 93 | 1.36% | 1 | 0.33% |
| Jamal Hadi Salim | 84 | 1.23% | 5 | 1.63% |
| Paolo Abeni | 81 | 1.18% | 6 | 1.96% |
| Davide Caratti | 72 | 1.05% | 4 | 1.31% |
| Seth Forshee | 57 | 0.83% | 2 | 0.65% |
| Stephen Hemminger | 56 | 0.82% | 8 | 2.61% |
| Dave Jones | 55 | 0.80% | 1 | 0.33% |
| Steffen Klassert | 53 | 0.77% | 1 | 0.33% |
| Herbert Xu | 37 | 0.54% | 9 | 2.94% |
| Octavian Purdila | 33 | 0.48% | 1 | 0.33% |
| Phil Sutter | 32 | 0.47% | 3 | 0.98% |
| Florian Westphal | 26 | 0.38% | 4 | 1.31% |
| Johannes Berg | 26 | 0.38% | 2 | 0.65% |
| Paul Blakey | 25 | 0.37% | 1 | 0.33% |
| Praveen Kumar Kannoju | 25 | 0.37% | 1 | 0.33% |
| Alexander Aring | 24 | 0.35% | 3 | 0.98% |
| David Decotigny | 20 | 0.29% | 3 | 0.98% |
| Wei Yongjun | 20 | 0.29% | 2 | 0.65% |
| Denys Vlasenko | 19 | 0.28% | 1 | 0.33% |
| Jesus Sanchez-Palencia | 19 | 0.28% | 1 | 0.33% |
| Wang Hai | 15 | 0.22% | 1 | 0.33% |
| Jiri Kosina | 15 | 0.22% | 2 | 0.65% |
| Kees Cook | 14 | 0.20% | 1 | 0.33% |
| Vincent Prince | 13 | 0.19% | 1 | 0.33% |
| Peter P. Waskiewicz Jr | 12 | 0.18% | 1 | 0.33% |
| Lars Persson | 12 | 0.18% | 1 | 0.33% |
| Yajun Deng | 12 | 0.18% | 1 | 0.33% |
| Peilin Ye | 11 | 0.16% | 1 | 0.33% |
| Stefan Rompf | 11 | 0.16% | 1 | 0.33% |
| Vladimir Oltean | 10 | 0.15% | 1 | 0.33% |
| Ahmed S. Darwish | 10 | 0.15% | 3 | 0.98% |
| Jussi Kivilinna | 9 | 0.13% | 2 | 0.65% |
| Kevin Bracey | 8 | 0.12% | 1 | 0.33% |
| Marc Kleine-Budde | 7 | 0.10% | 1 | 0.33% |
| Nikolay Aleksandrov | 7 | 0.10% | 1 | 0.33% |
| Eric W. Biedermann | 7 | 0.10% | 3 | 0.98% |
| Vimalkumar | 6 | 0.09% | 1 | 0.33% |
| Tommy S. Christensen | 6 | 0.09% | 1 | 0.33% |
| Valentin Longchamp | 5 | 0.07% | 1 | 0.33% |
| Tom Herbert | 5 | 0.07% | 1 | 0.33% |
| Arnaldo Carvalho de Melo | 5 | 0.07% | 1 | 0.33% |
| Li RongQing | 4 | 0.06% | 1 | 0.33% |
| Arjan van de Ven | 4 | 0.06% | 2 | 0.65% |
| Victor Nogueira | 4 | 0.06% | 1 | 0.33% |
| Arthur Kepner | 3 | 0.04% | 1 | 0.33% |
| Chris Dion | 3 | 0.04% | 1 | 0.33% |
| Daniel Borkmann | 3 | 0.04% | 1 | 0.33% |
| Venkatesh Pallipadi | 3 | 0.04% | 1 | 0.33% |
| Kuniyuki Iwashima | 3 | 0.04% | 1 | 0.33% |
| Pavel Emelyanov | 2 | 0.03% | 1 | 0.33% |
| Joy Latten | 2 | 0.03% | 1 | 0.33% |
| Michael S. Tsirkin | 2 | 0.03% | 1 | 0.33% |
| Jeff Garzik | 2 | 0.03% | 1 | 0.33% |
| Thomas Gleixner | 2 | 0.03% | 1 | 0.33% |
| Linus Torvalds | 1 | 0.01% | 1 | 0.33% |
| Andi Kleen | 1 | 0.01% | 1 | 0.33% |
| Elena Reshetova | 1 | 0.01% | 1 | 0.33% |
| Jesper Juhl | 1 | 0.01% | 1 | 0.33% |
| Ilpo Järvinen | 1 | 0.01% | 1 | 0.33% |
| Joe Perches | 1 | 0.01% | 1 | 0.33% |
| Matthias Tafelmeier | 1 | 0.01% | 1 | 0.33% |
| Jouke Witteveen | 1 | 0.01% | 1 | 0.33% |
| Adrian Bunk | 1 | 0.01% | 1 | 0.33% |
| Andrew Morton | 1 | 0.01% | 1 | 0.33% |
| Total | 6842 | 306 |
12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625
// SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/sch_generic.c Generic packet scheduler routines. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Jamal Hadi Salim, <hadi@cyberus.ca> 990601 * - Ingress support */ #include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/rcupdate.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/if_vlan.h> #include <linux/skb_array.h> #include <linux/if_macvlan.h> #include <net/sch_generic.h> #include <net/pkt_sched.h> #include <net/dst.h> #include <net/hotdata.h> #include <trace/events/qdisc.h> #include <trace/events/net.h> #include <net/xfrm.h> /* Qdisc to use by default */ const struct Qdisc_ops *default_qdisc_ops = &pfifo_fast_ops; EXPORT_SYMBOL(default_qdisc_ops); static void qdisc_maybe_clear_missed(struct Qdisc *q, const struct netdev_queue *txq) { clear_bit(__QDISC_STATE_MISSED, &q->state); /* Make sure the below netif_xmit_frozen_or_stopped() * checking happens after clearing STATE_MISSED. */ smp_mb__after_atomic(); /* Checking netif_xmit_frozen_or_stopped() again to * make sure STATE_MISSED is set if the STATE_MISSED * set by netif_tx_wake_queue()'s rescheduling of * net_tx_action() is cleared by the above clear_bit(). */ if (!netif_xmit_frozen_or_stopped(txq)) set_bit(__QDISC_STATE_MISSED, &q->state); else set_bit(__QDISC_STATE_DRAINING, &q->state); } /* Main transmission queue. */ /* Modifications to data participating in scheduling must be protected with * qdisc_lock(qdisc) spinlock. * * The idea is the following: * - enqueue, dequeue are serialized via qdisc root lock * - ingress filtering is also serialized via qdisc root lock * - updates to tree and tree walking are only done under the rtnl mutex. */ #define SKB_XOFF_MAGIC ((struct sk_buff *)1UL) static inline struct sk_buff *__skb_dequeue_bad_txq(struct Qdisc *q) { const struct netdev_queue *txq = q->dev_queue; spinlock_t *lock = NULL; struct sk_buff *skb; if (q->flags & TCQ_F_NOLOCK) { lock = qdisc_lock(q); spin_lock(lock); } skb = skb_peek(&q->skb_bad_txq); if (skb) { /* check the reason of requeuing without tx lock first */ txq = skb_get_tx_queue(txq->dev, skb); if (!netif_xmit_frozen_or_stopped(txq)) { skb = __skb_dequeue(&q->skb_bad_txq); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_dec(q, skb); qdisc_qstats_cpu_qlen_dec(q); } else { qdisc_qstats_backlog_dec(q, skb); q->q.qlen--; } } else { skb = SKB_XOFF_MAGIC; qdisc_maybe_clear_missed(q, txq); } } if (lock) spin_unlock(lock); return skb; } static inline struct sk_buff *qdisc_dequeue_skb_bad_txq(struct Qdisc *q) { struct sk_buff *skb = skb_peek(&q->skb_bad_txq); if (unlikely(skb)) skb = __skb_dequeue_bad_txq(q); return skb; } static inline void qdisc_enqueue_skb_bad_txq(struct Qdisc *q, struct sk_buff *skb) { spinlock_t *lock = NULL; if (q->flags & TCQ_F_NOLOCK) { lock = qdisc_lock(q); spin_lock(lock); } __skb_queue_tail(&q->skb_bad_txq, skb); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_inc(q, skb); qdisc_qstats_cpu_qlen_inc(q); } else { qdisc_qstats_backlog_inc(q, skb); q->q.qlen++; } if (lock) spin_unlock(lock); } static inline void dev_requeue_skb(struct sk_buff *skb, struct Qdisc *q) { spinlock_t *lock = NULL; if (q->flags & TCQ_F_NOLOCK) { lock = qdisc_lock(q); spin_lock(lock); } while (skb) { struct sk_buff *next = skb->next; __skb_queue_tail(&q->gso_skb, skb); /* it's still part of the queue */ if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_requeues_inc(q); qdisc_qstats_cpu_backlog_inc(q, skb); qdisc_qstats_cpu_qlen_inc(q); } else { q->qstats.requeues++; qdisc_qstats_backlog_inc(q, skb); q->q.qlen++; } skb = next; } if (lock) { spin_unlock(lock); set_bit(__QDISC_STATE_MISSED, &q->state); } else { __netif_schedule(q); } } static void try_bulk_dequeue_skb(struct Qdisc *q, struct sk_buff *skb, const struct netdev_queue *txq, int *packets) { int bytelimit = qdisc_avail_bulklimit(txq) - skb->len; while (bytelimit > 0) { struct sk_buff *nskb = q->dequeue(q); if (!nskb) break; bytelimit -= nskb->len; /* covers GSO len */ skb->next = nskb; skb = nskb; (*packets)++; /* GSO counts as one pkt */ } skb_mark_not_on_list(skb); } /* This variant of try_bulk_dequeue_skb() makes sure * all skbs in the chain are for the same txq */ static void try_bulk_dequeue_skb_slow(struct Qdisc *q, struct sk_buff *skb, int *packets) { int mapping = skb_get_queue_mapping(skb); struct sk_buff *nskb; int cnt = 0; do { nskb = q->dequeue(q); if (!nskb) break; if (unlikely(skb_get_queue_mapping(nskb) != mapping)) { qdisc_enqueue_skb_bad_txq(q, nskb); break; } skb->next = nskb; skb = nskb; } while (++cnt < 8); (*packets) += cnt; skb_mark_not_on_list(skb); } /* Note that dequeue_skb can possibly return a SKB list (via skb->next). * A requeued skb (via q->gso_skb) can also be a SKB list. */ static struct sk_buff *dequeue_skb(struct Qdisc *q, bool *validate, int *packets) { const struct netdev_queue *txq = q->dev_queue; struct sk_buff *skb = NULL; *packets = 1; if (unlikely(!skb_queue_empty(&q->gso_skb))) { spinlock_t *lock = NULL; if (q->flags & TCQ_F_NOLOCK) { lock = qdisc_lock(q); spin_lock(lock); } skb = skb_peek(&q->gso_skb); /* skb may be null if another cpu pulls gso_skb off in between * empty check and lock. */ if (!skb) { if (lock) spin_unlock(lock); goto validate; } /* skb in gso_skb were already validated */ *validate = false; if (xfrm_offload(skb)) *validate = true; /* check the reason of requeuing without tx lock first */ txq = skb_get_tx_queue(txq->dev, skb); if (!netif_xmit_frozen_or_stopped(txq)) { skb = __skb_dequeue(&q->gso_skb); if (qdisc_is_percpu_stats(q)) { qdisc_qstats_cpu_backlog_dec(q, skb); qdisc_qstats_cpu_qlen_dec(q); } else { qdisc_qstats_backlog_dec(q, skb); q->q.qlen--; } } else { skb = NULL; qdisc_maybe_clear_missed(q, txq); } if (lock) spin_unlock(lock); goto trace; } validate: *validate = true; if ((q->flags & TCQ_F_ONETXQUEUE) && netif_xmit_frozen_or_stopped(txq)) { qdisc_maybe_clear_missed(q, txq); return skb; } skb = qdisc_dequeue_skb_bad_txq(q); if (unlikely(skb)) { if (skb == SKB_XOFF_MAGIC) return NULL; goto bulk; } skb = q->dequeue(q); if (skb) { bulk: if (qdisc_may_bulk(q)) try_bulk_dequeue_skb(q, skb, txq, packets); else try_bulk_dequeue_skb_slow(q, skb, packets); } trace: trace_qdisc_dequeue(q, txq, *packets, skb); return skb; } /* * Transmit possibly several skbs, and handle the return status as * required. Owning qdisc running bit guarantees that only one CPU * can execute this function. * * Returns to the caller: * false - hardware queue frozen backoff * true - feel free to send more pkts */ bool sch_direct_xmit(struct sk_buff *skb, struct Qdisc *q, struct net_device *dev, struct netdev_queue *txq, spinlock_t *root_lock, bool validate) { int ret = NETDEV_TX_BUSY; bool again = false; /* And release qdisc */ if (root_lock) spin_unlock(root_lock); /* Note that we validate skb (GSO, checksum, ...) outside of locks */ if (validate) skb = validate_xmit_skb_list(skb, dev, &again); #ifdef CONFIG_XFRM_OFFLOAD if (unlikely(again)) { if (root_lock) spin_lock(root_lock); dev_requeue_skb(skb, q); return false; } #endif if (likely(skb)) { HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_stopped(txq)) skb = dev_hard_start_xmit(skb, dev, txq, &ret); else qdisc_maybe_clear_missed(q, txq); HARD_TX_UNLOCK(dev, txq); } else { if (root_lock) spin_lock(root_lock); return true; } if (root_lock) spin_lock(root_lock); if (!dev_xmit_complete(ret)) { /* Driver returned NETDEV_TX_BUSY - requeue skb */ if (unlikely(ret != NETDEV_TX_BUSY)) net_warn_ratelimited("BUG %s code %d qlen %d\n", dev->name, ret, q->q.qlen); dev_requeue_skb(skb, q); return false; } return true; } /* * NOTE: Called under qdisc_lock(q) with locally disabled BH. * * running seqcount guarantees only one CPU can process * this qdisc at a time. qdisc_lock(q) serializes queue accesses for * this queue. * * netif_tx_lock serializes accesses to device driver. * * qdisc_lock(q) and netif_tx_lock are mutually exclusive, * if one is grabbed, another must be free. * * Note, that this procedure can be called by a watchdog timer * * Returns to the caller: * 0 - queue is empty or throttled. * >0 - queue is not empty. * */ static inline bool qdisc_restart(struct Qdisc *q, int *packets) { spinlock_t *root_lock = NULL; struct netdev_queue *txq; struct net_device *dev; struct sk_buff *skb; bool validate; /* Dequeue packet */ skb = dequeue_skb(q, &validate, packets); if (unlikely(!skb)) return false; if (!(q->flags & TCQ_F_NOLOCK)) root_lock = qdisc_lock(q); dev = qdisc_dev(q); txq = skb_get_tx_queue(dev, skb); return sch_direct_xmit(skb, q, dev, txq, root_lock, validate); } void __qdisc_run(struct Qdisc *q) { int quota = READ_ONCE(net_hotdata.dev_tx_weight); int packets; while (qdisc_restart(q, &packets)) { quota -= packets; if (quota <= 0) { if (q->flags & TCQ_F_NOLOCK) set_bit(__QDISC_STATE_MISSED, &q->state); else __netif_schedule(q); break; } } } unsigned long dev_trans_start(struct net_device *dev) { unsigned long res = READ_ONCE(netdev_get_tx_queue(dev, 0)->trans_start); unsigned long val; unsigned int i; for (i = 1; i < dev->num_tx_queues; i++) { val = READ_ONCE(netdev_get_tx_queue(dev, i)->trans_start); if (val && time_after(val, res)) res = val; } return res; } EXPORT_SYMBOL(dev_trans_start); static void netif_freeze_queues(struct net_device *dev) { unsigned int i; int cpu; cpu = smp_processor_id(); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); /* We are the only thread of execution doing a * freeze, but we have to grab the _xmit_lock in * order to synchronize with threads which are in * the ->hard_start_xmit() handler and already * checked the frozen bit. */ __netif_tx_lock(txq, cpu); set_bit(__QUEUE_STATE_FROZEN, &txq->state); __netif_tx_unlock(txq); } } void netif_tx_lock(struct net_device *dev) { spin_lock(&dev->tx_global_lock); netif_freeze_queues(dev); } EXPORT_SYMBOL(netif_tx_lock); static void netif_unfreeze_queues(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); /* No need to grab the _xmit_lock here. If the * queue is not stopped for another reason, we * force a schedule. */ clear_bit(__QUEUE_STATE_FROZEN, &txq->state); netif_schedule_queue(txq); } } void netif_tx_unlock(struct net_device *dev) { netif_unfreeze_queues(dev); spin_unlock(&dev->tx_global_lock); } EXPORT_SYMBOL(netif_tx_unlock); static void dev_watchdog(struct timer_list *t) { struct net_device *dev = from_timer(dev, t, watchdog_timer); bool release = true; spin_lock(&dev->tx_global_lock); if (!qdisc_tx_is_noop(dev)) { if (netif_device_present(dev) && netif_running(dev) && netif_carrier_ok(dev)) { unsigned int timedout_ms = 0; unsigned int i; unsigned long trans_start; unsigned long oldest_start = jiffies; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq; txq = netdev_get_tx_queue(dev, i); if (!netif_xmit_stopped(txq)) continue; /* Paired with WRITE_ONCE() + smp_mb...() in * netdev_tx_sent_queue() and netif_tx_stop_queue(). */ smp_mb(); trans_start = READ_ONCE(txq->trans_start); if (time_after(jiffies, trans_start + dev->watchdog_timeo)) { timedout_ms = jiffies_to_msecs(jiffies - trans_start); atomic_long_inc(&txq->trans_timeout); break; } if (time_after(oldest_start, trans_start)) oldest_start = trans_start; } if (unlikely(timedout_ms)) { trace_net_dev_xmit_timeout(dev, i); netdev_crit(dev, "NETDEV WATCHDOG: CPU: %d: transmit queue %u timed out %u ms\n", raw_smp_processor_id(), i, timedout_ms); netif_freeze_queues(dev); dev->netdev_ops->ndo_tx_timeout(dev, i); netif_unfreeze_queues(dev); } if (!mod_timer(&dev->watchdog_timer, round_jiffies(oldest_start + dev->watchdog_timeo))) release = false; } } spin_unlock(&dev->tx_global_lock); if (release) netdev_put(dev, &dev->watchdog_dev_tracker); } void __netdev_watchdog_up(struct net_device *dev) { if (dev->netdev_ops->ndo_tx_timeout) { if (dev->watchdog_timeo <= 0) dev->watchdog_timeo = 5*HZ; if (!mod_timer(&dev->watchdog_timer, round_jiffies(jiffies + dev->watchdog_timeo))) netdev_hold(dev, &dev->watchdog_dev_tracker, GFP_ATOMIC); } } EXPORT_SYMBOL_GPL(__netdev_watchdog_up); static void dev_watchdog_up(struct net_device *dev) { __netdev_watchdog_up(dev); } static void dev_watchdog_down(struct net_device *dev) { netif_tx_lock_bh(dev); if (del_timer(&dev->watchdog_timer)) netdev_put(dev, &dev->watchdog_dev_tracker); netif_tx_unlock_bh(dev); } /** * netif_carrier_on - set carrier * @dev: network device * * Device has detected acquisition of carrier. */ void netif_carrier_on(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_NOCARRIER, &dev->state)) { if (dev->reg_state == NETREG_UNINITIALIZED) return; atomic_inc(&dev->carrier_up_count); linkwatch_fire_event(dev); if (netif_running(dev)) __netdev_watchdog_up(dev); } } EXPORT_SYMBOL(netif_carrier_on); /** * netif_carrier_off - clear carrier * @dev: network device * * Device has detected loss of carrier. */ void netif_carrier_off(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_NOCARRIER, &dev->state)) { if (dev->reg_state == NETREG_UNINITIALIZED) return; atomic_inc(&dev->carrier_down_count); linkwatch_fire_event(dev); } } EXPORT_SYMBOL(netif_carrier_off); /** * netif_carrier_event - report carrier state event * @dev: network device * * Device has detected a carrier event but the carrier state wasn't changed. * Use in drivers when querying carrier state asynchronously, to avoid missing * events (link flaps) if link recovers before it's queried. */ void netif_carrier_event(struct net_device *dev) { if (dev->reg_state == NETREG_UNINITIALIZED) return; atomic_inc(&dev->carrier_up_count); atomic_inc(&dev->carrier_down_count); linkwatch_fire_event(dev); } EXPORT_SYMBOL_GPL(netif_carrier_event); /* "NOOP" scheduler: the best scheduler, recommended for all interfaces under all circumstances. It is difficult to invent anything faster or cheaper. */ static int noop_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, struct sk_buff **to_free) { dev_core_stats_tx_dropped_inc(skb->dev); __qdisc_drop(skb, to_free); return NET_XMIT_CN; } static struct sk_buff *noop_dequeue(struct Qdisc *qdisc) { return NULL; } struct Qdisc_ops noop_qdisc_ops __read_mostly = { .id = "noop", .priv_size = 0, .enqueue = noop_enqueue, .dequeue = noop_dequeue, .peek = noop_dequeue, .owner = THIS_MODULE, }; static struct netdev_queue noop_netdev_queue = { RCU_POINTER_INITIALIZER(qdisc, &noop_qdisc), RCU_POINTER_INITIALIZER(qdisc_sleeping, &noop_qdisc), }; struct Qdisc noop_qdisc = { .enqueue = noop_enqueue, .dequeue = noop_dequeue, .flags = TCQ_F_BUILTIN, .ops = &noop_qdisc_ops, .q.lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.q.lock), .dev_queue = &noop_netdev_queue, .busylock = __SPIN_LOCK_UNLOCKED(noop_qdisc.busylock), .gso_skb = { .next = (struct sk_buff *)&noop_qdisc.gso_skb, .prev = (struct sk_buff *)&noop_qdisc.gso_skb, .qlen = 0, .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.gso_skb.lock), }, .skb_bad_txq = { .next = (struct sk_buff *)&noop_qdisc.skb_bad_txq, .prev = (struct sk_buff *)&noop_qdisc.skb_bad_txq, .qlen = 0, .lock = __SPIN_LOCK_UNLOCKED(noop_qdisc.skb_bad_txq.lock), }, .owner = -1, }; EXPORT_SYMBOL(noop_qdisc); static int noqueue_init(struct Qdisc *qdisc, struct nlattr *opt, struct netlink_ext_ack *extack) { /* register_qdisc() assigns a default of noop_enqueue if unset, * but __dev_queue_xmit() treats noqueue only as such * if this is NULL - so clear it here. */ qdisc->enqueue = NULL; return 0; } struct Qdisc_ops noqueue_qdisc_ops __read_mostly = { .id = "noqueue", .priv_size = 0, .init = noqueue_init, .enqueue = noop_enqueue, .dequeue = noop_dequeue, .peek = noop_dequeue, .owner = THIS_MODULE, }; const u8 sch_default_prio2band[TC_PRIO_MAX + 1] = { 1, 2, 2, 2, 1, 2, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1 }; EXPORT_SYMBOL(sch_default_prio2band); /* 3-band FIFO queue: old style, but should be a bit faster than generic prio+fifo combination. */ #define PFIFO_FAST_BANDS 3 /* * Private data for a pfifo_fast scheduler containing: * - rings for priority bands */ struct pfifo_fast_priv { struct skb_array q[PFIFO_FAST_BANDS]; }; static inline struct skb_array *band2list(struct pfifo_fast_priv *priv, int band) { return &priv->q[band]; } static int pfifo_fast_enqueue(struct sk_buff *skb, struct Qdisc *qdisc, struct sk_buff **to_free) { int band = sch_default_prio2band[skb->priority & TC_PRIO_MAX]; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct skb_array *q = band2list(priv, band); unsigned int pkt_len = qdisc_pkt_len(skb); int err; err = skb_array_produce(q, skb); if (unlikely(err)) { if (qdisc_is_percpu_stats(qdisc)) return qdisc_drop_cpu(skb, qdisc, to_free); else return qdisc_drop(skb, qdisc, to_free); } qdisc_update_stats_at_enqueue(qdisc, pkt_len); return NET_XMIT_SUCCESS; } static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct sk_buff *skb = NULL; bool need_retry = true; int band; retry: for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) { struct skb_array *q = band2list(priv, band); if (__skb_array_empty(q)) continue; skb = __skb_array_consume(q); } if (likely(skb)) { qdisc_update_stats_at_dequeue(qdisc, skb); } else if (need_retry && READ_ONCE(qdisc->state) & QDISC_STATE_NON_EMPTY) { /* Delay clearing the STATE_MISSED here to reduce * the overhead of the second spin_trylock() in * qdisc_run_begin() and __netif_schedule() calling * in qdisc_run_end(). */ clear_bit(__QDISC_STATE_MISSED, &qdisc->state); clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); /* Make sure dequeuing happens after clearing * STATE_MISSED. */ smp_mb__after_atomic(); need_retry = false; goto retry; } return skb; } static struct sk_buff *pfifo_fast_peek(struct Qdisc *qdisc) { struct pfifo_fast_priv *priv = qdisc_priv(qdisc); struct sk_buff *skb = NULL; int band; for (band = 0; band < PFIFO_FAST_BANDS && !skb; band++) { struct skb_array *q = band2list(priv, band); skb = __skb_array_peek(q); } return skb; } static void pfifo_fast_reset(struct Qdisc *qdisc) { int i, band; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); for (band = 0; band < PFIFO_FAST_BANDS; band++) { struct skb_array *q = band2list(priv, band); struct sk_buff *skb; /* NULL ring is possible if destroy path is due to a failed * skb_array_init() in pfifo_fast_init() case. */ if (!q->ring.queue) continue; while ((skb = __skb_array_consume(q)) != NULL) kfree_skb(skb); } if (qdisc_is_percpu_stats(qdisc)) { for_each_possible_cpu(i) { struct gnet_stats_queue *q; q = per_cpu_ptr(qdisc->cpu_qstats, i); q->backlog = 0; q->qlen = 0; } } } static int pfifo_fast_dump(struct Qdisc *qdisc, struct sk_buff *skb) { struct tc_prio_qopt opt = { .bands = PFIFO_FAST_BANDS }; memcpy(&opt.priomap, sch_default_prio2band, TC_PRIO_MAX + 1); if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; return skb->len; nla_put_failure: return -1; } static int pfifo_fast_init(struct Qdisc *qdisc, struct nlattr *opt, struct netlink_ext_ack *extack) { unsigned int qlen = qdisc_dev(qdisc)->tx_queue_len; struct pfifo_fast_priv *priv = qdisc_priv(qdisc); int prio; /* guard against zero length rings */ if (!qlen) return -EINVAL; for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { struct skb_array *q = band2list(priv, prio); int err; err = skb_array_init(q, qlen, GFP_KERNEL); if (err) return -ENOMEM; } /* Can by-pass the queue discipline */ qdisc->flags |= TCQ_F_CAN_BYPASS; return 0; } static void pfifo_fast_destroy(struct Qdisc *sch) { struct pfifo_fast_priv *priv = qdisc_priv(sch); int prio; for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { struct skb_array *q = band2list(priv, prio); /* NULL ring is possible if destroy path is due to a failed * skb_array_init() in pfifo_fast_init() case. */ if (!q->ring.queue) continue; /* Destroy ring but no need to kfree_skb because a call to * pfifo_fast_reset() has already done that work. */ ptr_ring_cleanup(&q->ring, NULL); } } static int pfifo_fast_change_tx_queue_len(struct Qdisc *sch, unsigned int new_len) { struct pfifo_fast_priv *priv = qdisc_priv(sch); struct skb_array *bands[PFIFO_FAST_BANDS]; int prio; for (prio = 0; prio < PFIFO_FAST_BANDS; prio++) { struct skb_array *q = band2list(priv, prio); bands[prio] = q; } return skb_array_resize_multiple(bands, PFIFO_FAST_BANDS, new_len, GFP_KERNEL); } struct Qdisc_ops pfifo_fast_ops __read_mostly = { .id = "pfifo_fast", .priv_size = sizeof(struct pfifo_fast_priv), .enqueue = pfifo_fast_enqueue, .dequeue = pfifo_fast_dequeue, .peek = pfifo_fast_peek, .init = pfifo_fast_init, .destroy = pfifo_fast_destroy, .reset = pfifo_fast_reset, .dump = pfifo_fast_dump, .change_tx_queue_len = pfifo_fast_change_tx_queue_len, .owner = THIS_MODULE, .static_flags = TCQ_F_NOLOCK | TCQ_F_CPUSTATS, }; EXPORT_SYMBOL(pfifo_fast_ops); static struct lock_class_key qdisc_tx_busylock; struct Qdisc *qdisc_alloc(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, struct netlink_ext_ack *extack) { struct Qdisc *sch; unsigned int size = sizeof(*sch) + ops->priv_size; int err = -ENOBUFS; struct net_device *dev; if (!dev_queue) { NL_SET_ERR_MSG(extack, "No device queue given"); err = -EINVAL; goto errout; } dev = dev_queue->dev; sch = kzalloc_node(size, GFP_KERNEL, netdev_queue_numa_node_read(dev_queue)); if (!sch) goto errout; __skb_queue_head_init(&sch->gso_skb); __skb_queue_head_init(&sch->skb_bad_txq); gnet_stats_basic_sync_init(&sch->bstats); lockdep_register_key(&sch->root_lock_key); spin_lock_init(&sch->q.lock); lockdep_set_class(&sch->q.lock, &sch->root_lock_key); if (ops->static_flags & TCQ_F_CPUSTATS) { sch->cpu_bstats = netdev_alloc_pcpu_stats(struct gnet_stats_basic_sync); if (!sch->cpu_bstats) goto errout1; sch->cpu_qstats = alloc_percpu(struct gnet_stats_queue); if (!sch->cpu_qstats) { free_percpu(sch->cpu_bstats); goto errout1; } } spin_lock_init(&sch->busylock); lockdep_set_class(&sch->busylock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); /* seqlock has the same scope of busylock, for NOLOCK qdisc */ spin_lock_init(&sch->seqlock); lockdep_set_class(&sch->seqlock, dev->qdisc_tx_busylock ?: &qdisc_tx_busylock); sch->ops = ops; sch->flags = ops->static_flags; sch->enqueue = ops->enqueue; sch->dequeue = ops->dequeue; sch->dev_queue = dev_queue; sch->owner = -1; netdev_hold(dev, &sch->dev_tracker, GFP_KERNEL); refcount_set(&sch->refcnt, 1); return sch; errout1: lockdep_unregister_key(&sch->root_lock_key); kfree(sch); errout: return ERR_PTR(err); } struct Qdisc *qdisc_create_dflt(struct netdev_queue *dev_queue, const struct Qdisc_ops *ops, unsigned int parentid, struct netlink_ext_ack *extack) { struct Qdisc *sch; if (!try_module_get(ops->owner)) { NL_SET_ERR_MSG(extack, "Failed to increase module reference counter"); return NULL; } sch = qdisc_alloc(dev_queue, ops, extack); if (IS_ERR(sch)) { module_put(ops->owner); return NULL; } sch->parent = parentid; if (!ops->init || ops->init(sch, NULL, extack) == 0) { trace_qdisc_create(ops, dev_queue->dev, parentid); return sch; } qdisc_put(sch); return NULL; } EXPORT_SYMBOL(qdisc_create_dflt); /* Under qdisc_lock(qdisc) and BH! */ void qdisc_reset(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; trace_qdisc_reset(qdisc); if (ops->reset) ops->reset(qdisc); __skb_queue_purge(&qdisc->gso_skb); __skb_queue_purge(&qdisc->skb_bad_txq); qdisc->q.qlen = 0; qdisc->qstats.backlog = 0; } EXPORT_SYMBOL(qdisc_reset); void qdisc_free(struct Qdisc *qdisc) { if (qdisc_is_percpu_stats(qdisc)) { free_percpu(qdisc->cpu_bstats); free_percpu(qdisc->cpu_qstats); } kfree(qdisc); } static void qdisc_free_cb(struct rcu_head *head) { struct Qdisc *q = container_of(head, struct Qdisc, rcu); qdisc_free(q); } static void __qdisc_destroy(struct Qdisc *qdisc) { const struct Qdisc_ops *ops = qdisc->ops; struct net_device *dev = qdisc_dev(qdisc); #ifdef CONFIG_NET_SCHED qdisc_hash_del(qdisc); qdisc_put_stab(rtnl_dereference(qdisc->stab)); #endif gen_kill_estimator(&qdisc->rate_est); qdisc_reset(qdisc); if (ops->destroy) ops->destroy(qdisc); lockdep_unregister_key(&qdisc->root_lock_key); module_put(ops->owner); netdev_put(dev, &qdisc->dev_tracker); trace_qdisc_destroy(qdisc); call_rcu(&qdisc->rcu, qdisc_free_cb); } void qdisc_destroy(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN) return; __qdisc_destroy(qdisc); } void qdisc_put(struct Qdisc *qdisc) { if (!qdisc) return; if (qdisc->flags & TCQ_F_BUILTIN || !refcount_dec_and_test(&qdisc->refcnt)) return; __qdisc_destroy(qdisc); } EXPORT_SYMBOL(qdisc_put); /* Version of qdisc_put() that is called with rtnl mutex unlocked. * Intended to be used as optimization, this function only takes rtnl lock if * qdisc reference counter reached zero. */ void qdisc_put_unlocked(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN || !refcount_dec_and_rtnl_lock(&qdisc->refcnt)) return; __qdisc_destroy(qdisc); rtnl_unlock(); } EXPORT_SYMBOL(qdisc_put_unlocked); /* Attach toplevel qdisc to device queue. */ struct Qdisc *dev_graft_qdisc(struct netdev_queue *dev_queue, struct Qdisc *qdisc) { struct Qdisc *oqdisc = rtnl_dereference(dev_queue->qdisc_sleeping); spinlock_t *root_lock; root_lock = qdisc_lock(oqdisc); spin_lock_bh(root_lock); /* ... and graft new one */ if (qdisc == NULL) qdisc = &noop_qdisc; rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); rcu_assign_pointer(dev_queue->qdisc, &noop_qdisc); spin_unlock_bh(root_lock); return oqdisc; } EXPORT_SYMBOL(dev_graft_qdisc); static void shutdown_scheduler_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc_default) { struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); struct Qdisc *qdisc_default = _qdisc_default; if (qdisc) { rcu_assign_pointer(dev_queue->qdisc, qdisc_default); rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc_default); qdisc_put(qdisc); } } static void attach_one_default_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_unused) { struct Qdisc *qdisc; const struct Qdisc_ops *ops = default_qdisc_ops; if (dev->priv_flags & IFF_NO_QUEUE) ops = &noqueue_qdisc_ops; else if(dev->type == ARPHRD_CAN) ops = &pfifo_fast_ops; qdisc = qdisc_create_dflt(dev_queue, ops, TC_H_ROOT, NULL); if (!qdisc) return; if (!netif_is_multiqueue(dev)) qdisc->flags |= TCQ_F_ONETXQUEUE | TCQ_F_NOPARENT; rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); } static void attach_default_qdiscs(struct net_device *dev) { struct netdev_queue *txq; struct Qdisc *qdisc; txq = netdev_get_tx_queue(dev, 0); if (!netif_is_multiqueue(dev) || dev->priv_flags & IFF_NO_QUEUE) { netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); qdisc = rtnl_dereference(txq->qdisc_sleeping); rcu_assign_pointer(dev->qdisc, qdisc); qdisc_refcount_inc(qdisc); } else { qdisc = qdisc_create_dflt(txq, &mq_qdisc_ops, TC_H_ROOT, NULL); if (qdisc) { rcu_assign_pointer(dev->qdisc, qdisc); qdisc->ops->attach(qdisc); } } qdisc = rtnl_dereference(dev->qdisc); /* Detect default qdisc setup/init failed and fallback to "noqueue" */ if (qdisc == &noop_qdisc) { netdev_warn(dev, "default qdisc (%s) fail, fallback to %s\n", default_qdisc_ops->id, noqueue_qdisc_ops.id); netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); dev->priv_flags |= IFF_NO_QUEUE; netdev_for_each_tx_queue(dev, attach_one_default_qdisc, NULL); qdisc = rtnl_dereference(txq->qdisc_sleeping); rcu_assign_pointer(dev->qdisc, qdisc); qdisc_refcount_inc(qdisc); dev->priv_flags ^= IFF_NO_QUEUE; } #ifdef CONFIG_NET_SCHED if (qdisc != &noop_qdisc) qdisc_hash_add(qdisc, false); #endif } static void transition_one_qdisc(struct net_device *dev, struct netdev_queue *dev_queue, void *_need_watchdog) { struct Qdisc *new_qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); int *need_watchdog_p = _need_watchdog; if (!(new_qdisc->flags & TCQ_F_BUILTIN)) clear_bit(__QDISC_STATE_DEACTIVATED, &new_qdisc->state); rcu_assign_pointer(dev_queue->qdisc, new_qdisc); if (need_watchdog_p) { WRITE_ONCE(dev_queue->trans_start, 0); *need_watchdog_p = 1; } } void dev_activate(struct net_device *dev) { int need_watchdog; /* No queueing discipline is attached to device; * create default one for devices, which need queueing * and noqueue_qdisc for virtual interfaces */ if (rtnl_dereference(dev->qdisc) == &noop_qdisc) attach_default_qdiscs(dev); if (!netif_carrier_ok(dev)) /* Delay activation until next carrier-on event */ return; need_watchdog = 0; netdev_for_each_tx_queue(dev, transition_one_qdisc, &need_watchdog); if (dev_ingress_queue(dev)) transition_one_qdisc(dev, dev_ingress_queue(dev), NULL); if (need_watchdog) { netif_trans_update(dev); dev_watchdog_up(dev); } } EXPORT_SYMBOL(dev_activate); static void qdisc_deactivate(struct Qdisc *qdisc) { if (qdisc->flags & TCQ_F_BUILTIN) return; set_bit(__QDISC_STATE_DEACTIVATED, &qdisc->state); } static void dev_deactivate_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc_default) { struct Qdisc *qdisc_default = _qdisc_default; struct Qdisc *qdisc; qdisc = rtnl_dereference(dev_queue->qdisc); if (qdisc) { qdisc_deactivate(qdisc); rcu_assign_pointer(dev_queue->qdisc, qdisc_default); } } static void dev_reset_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_unused) { struct Qdisc *qdisc; bool nolock; qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); if (!qdisc) return; nolock = qdisc->flags & TCQ_F_NOLOCK; if (nolock) spin_lock_bh(&qdisc->seqlock); spin_lock_bh(qdisc_lock(qdisc)); qdisc_reset(qdisc); spin_unlock_bh(qdisc_lock(qdisc)); if (nolock) { clear_bit(__QDISC_STATE_MISSED, &qdisc->state); clear_bit(__QDISC_STATE_DRAINING, &qdisc->state); spin_unlock_bh(&qdisc->seqlock); } } static bool some_qdisc_is_busy(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *dev_queue; spinlock_t *root_lock; struct Qdisc *q; int val; dev_queue = netdev_get_tx_queue(dev, i); q = rtnl_dereference(dev_queue->qdisc_sleeping); root_lock = qdisc_lock(q); spin_lock_bh(root_lock); val = (qdisc_is_running(q) || test_bit(__QDISC_STATE_SCHED, &q->state)); spin_unlock_bh(root_lock); if (val) return true; } return false; } /** * dev_deactivate_many - deactivate transmissions on several devices * @head: list of devices to deactivate * * This function returns only when all outstanding transmissions * have completed, unless all devices are in dismantle phase. */ void dev_deactivate_many(struct list_head *head) { struct net_device *dev; list_for_each_entry(dev, head, close_list) { netdev_for_each_tx_queue(dev, dev_deactivate_queue, &noop_qdisc); if (dev_ingress_queue(dev)) dev_deactivate_queue(dev, dev_ingress_queue(dev), &noop_qdisc); dev_watchdog_down(dev); } /* Wait for outstanding qdisc-less dev_queue_xmit calls or * outstanding qdisc enqueuing calls. * This is avoided if all devices are in dismantle phase : * Caller will call synchronize_net() for us */ synchronize_net(); list_for_each_entry(dev, head, close_list) { netdev_for_each_tx_queue(dev, dev_reset_queue, NULL); if (dev_ingress_queue(dev)) dev_reset_queue(dev, dev_ingress_queue(dev), NULL); } /* Wait for outstanding qdisc_run calls. */ list_for_each_entry(dev, head, close_list) { while (some_qdisc_is_busy(dev)) { /* wait_event() would avoid this sleep-loop but would * require expensive checks in the fast paths of packet * processing which isn't worth it. */ schedule_timeout_uninterruptible(1); } } } void dev_deactivate(struct net_device *dev) { LIST_HEAD(single); list_add(&dev->close_list, &single); dev_deactivate_many(&single); list_del(&single); } EXPORT_SYMBOL(dev_deactivate); static int qdisc_change_tx_queue_len(struct net_device *dev, struct netdev_queue *dev_queue) { struct Qdisc *qdisc = rtnl_dereference(dev_queue->qdisc_sleeping); const struct Qdisc_ops *ops = qdisc->ops; if (ops->change_tx_queue_len) return ops->change_tx_queue_len(qdisc, dev->tx_queue_len); return 0; } void dev_qdisc_change_real_num_tx(struct net_device *dev, unsigned int new_real_tx) { struct Qdisc *qdisc = rtnl_dereference(dev->qdisc); if (qdisc->ops->change_real_num_tx) qdisc->ops->change_real_num_tx(qdisc, new_real_tx); } void mq_change_real_num_tx(struct Qdisc *sch, unsigned int new_real_tx) { #ifdef CONFIG_NET_SCHED struct net_device *dev = qdisc_dev(sch); struct Qdisc *qdisc; unsigned int i; for (i = new_real_tx; i < dev->real_num_tx_queues; i++) { qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc_sleeping); /* Only update the default qdiscs we created, * qdiscs with handles are always hashed. */ if (qdisc != &noop_qdisc && !qdisc->handle) qdisc_hash_del(qdisc); } for (i = dev->real_num_tx_queues; i < new_real_tx; i++) { qdisc = rtnl_dereference(netdev_get_tx_queue(dev, i)->qdisc_sleeping); if (qdisc != &noop_qdisc && !qdisc->handle) qdisc_hash_add(qdisc, false); } #endif } EXPORT_SYMBOL(mq_change_real_num_tx); int dev_qdisc_change_tx_queue_len(struct net_device *dev) { bool up = dev->flags & IFF_UP; unsigned int i; int ret = 0; if (up) dev_deactivate(dev); for (i = 0; i < dev->num_tx_queues; i++) { ret = qdisc_change_tx_queue_len(dev, &dev->_tx[i]); /* TODO: revert changes on a partial failure */ if (ret) break; } if (up) dev_activate(dev); return ret; } static void dev_init_scheduler_queue(struct net_device *dev, struct netdev_queue *dev_queue, void *_qdisc) { struct Qdisc *qdisc = _qdisc; rcu_assign_pointer(dev_queue->qdisc, qdisc); rcu_assign_pointer(dev_queue->qdisc_sleeping, qdisc); } void dev_init_scheduler(struct net_device *dev) { rcu_assign_pointer(dev->qdisc, &noop_qdisc); netdev_for_each_tx_queue(dev, dev_init_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) dev_init_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); timer_setup(&dev->watchdog_timer, dev_watchdog, 0); } void dev_shutdown(struct net_device *dev) { netdev_for_each_tx_queue(dev, shutdown_scheduler_queue, &noop_qdisc); if (dev_ingress_queue(dev)) shutdown_scheduler_queue(dev, dev_ingress_queue(dev), &noop_qdisc); qdisc_put(rtnl_dereference(dev->qdisc)); rcu_assign_pointer(dev->qdisc, &noop_qdisc); WARN_ON(timer_pending(&dev->watchdog_timer)); } /** * psched_ratecfg_precompute__() - Pre-compute values for reciprocal division * @rate: Rate to compute reciprocal division values of * @mult: Multiplier for reciprocal division * @shift: Shift for reciprocal division * * The multiplier and shift for reciprocal division by rate are stored * in mult and shift. * * The deal here is to replace a divide by a reciprocal one * in fast path (a reciprocal divide is a multiply and a shift) * * Normal formula would be : * time_in_ns = (NSEC_PER_SEC * len) / rate_bps * * We compute mult/shift to use instead : * time_in_ns = (len * mult) >> shift; * * We try to get the highest possible mult value for accuracy, * but have to make sure no overflows will ever happen. * * reciprocal_value() is not used here it doesn't handle 64-bit values. */ static void psched_ratecfg_precompute__(u64 rate, u32 *mult, u8 *shift) { u64 factor = NSEC_PER_SEC; *mult = 1; *shift = 0; if (rate <= 0) return; for (;;) { *mult = div64_u64(factor, rate); if (*mult & (1U << 31) || factor & (1ULL << 63)) break; factor <<= 1; (*shift)++; } } void psched_ratecfg_precompute(struct psched_ratecfg *r, const struct tc_ratespec *conf, u64 rate64) { memset(r, 0, sizeof(*r)); r->overhead = conf->overhead; r->mpu = conf->mpu; r->rate_bytes_ps = max_t(u64, conf->rate, rate64); r->linklayer = (conf->linklayer & TC_LINKLAYER_MASK); psched_ratecfg_precompute__(r->rate_bytes_ps, &r->mult, &r->shift); } EXPORT_SYMBOL(psched_ratecfg_precompute); void psched_ppscfg_precompute(struct psched_pktrate *r, u64 pktrate64) { r->rate_pkts_ps = pktrate64; psched_ratecfg_precompute__(r->rate_pkts_ps, &r->mult, &r->shift); } EXPORT_SYMBOL(psched_ppscfg_precompute); void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, struct tcf_proto *tp_head) { /* Protected with chain0->filter_chain_lock. * Can't access chain directly because tp_head can be NULL. */ struct mini_Qdisc *miniq_old = rcu_dereference_protected(*miniqp->p_miniq, 1); struct mini_Qdisc *miniq; if (!tp_head) { RCU_INIT_POINTER(*miniqp->p_miniq, NULL); } else { miniq = miniq_old != &miniqp->miniq1 ? &miniqp->miniq1 : &miniqp->miniq2; /* We need to make sure that readers won't see the miniq * we are about to modify. So ensure that at least one RCU * grace period has elapsed since the miniq was made * inactive. */ if (IS_ENABLED(CONFIG_PREEMPT_RT)) cond_synchronize_rcu(miniq->rcu_state); else if (!poll_state_synchronize_rcu(miniq->rcu_state)) synchronize_rcu_expedited(); miniq->filter_list = tp_head; rcu_assign_pointer(*miniqp->p_miniq, miniq); } if (miniq_old) /* This is counterpart of the rcu sync above. We need to * block potential new user of miniq_old until all readers * are not seeing it. */ miniq_old->rcu_state = start_poll_synchronize_rcu(); } EXPORT_SYMBOL(mini_qdisc_pair_swap); void mini_qdisc_pair_block_init(struct mini_Qdisc_pair *miniqp, struct tcf_block *block) { miniqp->miniq1.block = block; miniqp->miniq2.block = block; } EXPORT_SYMBOL(mini_qdisc_pair_block_init); void mini_qdisc_pair_init(struct mini_Qdisc_pair *miniqp, struct Qdisc *qdisc, struct mini_Qdisc __rcu **p_miniq) { miniqp->miniq1.cpu_bstats = qdisc->cpu_bstats; miniqp->miniq1.cpu_qstats = qdisc->cpu_qstats; miniqp->miniq2.cpu_bstats = qdisc->cpu_bstats; miniqp->miniq2.cpu_qstats = qdisc->cpu_qstats; miniqp->miniq1.rcu_state = get_state_synchronize_rcu(); miniqp->miniq2.rcu_state = miniqp->miniq1.rcu_state; miniqp->p_miniq = p_miniq; } EXPORT_SYMBOL(mini_qdisc_pair_init);
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with Cregit http://github.com/cregit/cregit
Version 2.0-RC1