| Author | Tokens | Token Proportion | Commits | Commit Proportion |
|---|---|---|---|---|
| Arnaldo Carvalho de Melo | 4251 | 25.43% | 147 | 26.44% |
| Jiri Olsa | 2900 | 17.35% | 104 | 18.71% |
| Ian Rogers | 1784 | 10.67% | 37 | 6.65% |
| Namhyung Kim | 1085 | 6.49% | 28 | 5.04% |
| Adrian Hunter | 1020 | 6.10% | 40 | 7.19% |
| Riccardo Mancini | 861 | 5.15% | 10 | 1.80% |
| Kan Liang | 842 | 5.04% | 21 | 3.78% |
| Andi Kleen | 373 | 2.23% | 23 | 4.14% |
| Peter Zijlstra | 347 | 2.08% | 8 | 1.44% |
| Weilin Wang | 313 | 1.87% | 1 | 0.18% |
| Stéphane Eranian | 289 | 1.73% | 14 | 2.52% |
| David Ahern | 281 | 1.68% | 6 | 1.08% |
| Madhavan Srinivasan | 251 | 1.50% | 1 | 0.18% |
| Jin Yao | 241 | 1.44% | 8 | 1.44% |
| OGAWA Hirofumi | 213 | 1.27% | 1 | 0.18% |
| Song Liu | 194 | 1.16% | 8 | 1.44% |
| Ingo Molnar | 151 | 0.90% | 12 | 2.16% |
| Ze Gao | 141 | 0.84% | 2 | 0.36% |
| Frédéric Weisbecker | 117 | 0.70% | 6 | 1.08% |
| Wang Nan | 102 | 0.61% | 6 | 1.08% |
| German Gomez | 81 | 0.48% | 1 | 0.18% |
| Ravi Bangoria | 78 | 0.47% | 4 | 0.72% |
| Alexey Budankov | 74 | 0.44% | 3 | 0.54% |
| Sandipan Das | 69 | 0.41% | 1 | 0.18% |
| Jaswinder Singh Rajput | 67 | 0.40% | 3 | 0.54% |
| Yang Jihong | 66 | 0.39% | 2 | 0.36% |
| Roberto Agostino Vitillo | 64 | 0.38% | 2 | 0.36% |
| Mengting Zhang | 50 | 0.30% | 1 | 0.18% |
| Florian Fischer | 49 | 0.29% | 2 | 0.36% |
| Mathieu J. Poirier | 34 | 0.20% | 4 | 0.72% |
| Robert Richter | 30 | 0.18% | 4 | 0.72% |
| Leo Yan | 30 | 0.18% | 4 | 0.72% |
| Dominique Martinet | 28 | 0.17% | 1 | 0.18% |
| yuzhoujian | 24 | 0.14% | 1 | 0.18% |
| Masami Hiramatsu | 23 | 0.14% | 2 | 0.36% |
| Kim Phillips | 23 | 0.14% | 3 | 0.54% |
| Vineet Gupta | 21 | 0.13% | 1 | 0.18% |
| Yann Droneaud | 19 | 0.11% | 1 | 0.18% |
| Kirill Smelkov | 13 | 0.08% | 1 | 0.18% |
| Hari Bathini | 12 | 0.07% | 1 | 0.18% |
| Don Zickus | 11 | 0.07% | 1 | 0.18% |
| David Sharp | 10 | 0.06% | 1 | 0.18% |
| Lin Ming | 8 | 0.05% | 1 | 0.18% |
| Anton Blanchard | 7 | 0.04% | 2 | 0.36% |
| Agustin Vega-Frias | 6 | 0.04% | 1 | 0.18% |
| Sergey Senozhatsky | 6 | 0.04% | 1 | 0.18% |
| Simon Kaempflein | 6 | 0.04% | 1 | 0.18% |
| James Clark | 6 | 0.04% | 2 | 0.36% |
| Tzvetomir Stoyanov (VMware) | 6 | 0.04% | 3 | 0.54% |
| Naveen N. Rao | 5 | 0.03% | 1 | 0.18% |
| Hisao Tanabe | 4 | 0.02% | 1 | 0.18% |
| Xiao Guangrong | 3 | 0.02% | 1 | 0.18% |
| John Kacur | 3 | 0.02% | 1 | 0.18% |
| Steven Rostedt | 3 | 0.02% | 1 | 0.18% |
| Andrey Vagin | 2 | 0.01% | 1 | 0.18% |
| Li Zefan | 2 | 0.01% | 1 | 0.18% |
| Changbin Du | 2 | 0.01% | 1 | 0.18% |
| Mao Han | 2 | 0.01% | 1 | 0.18% |
| Thomas Gleixner | 2 | 0.01% | 1 | 0.18% |
| Fengguang Wu | 2 | 0.01% | 1 | 0.18% |
| Yunseong Kim | 1 | 0.01% | 1 | 0.18% |
| Linus Torvalds | 1 | 0.01% | 1 | 0.18% |
| Adam Buchbinder | 1 | 0.01% | 1 | 0.18% |
| Konstantin Khlebnikov | 1 | 0.01% | 1 | 0.18% |
| Borislav Petkov | 1 | 0.01% | 1 | 0.18% |
| Eduard Zingerman | 1 | 0.01% | 1 | 0.18% |
| Ben Hutchings | 1 | 0.01% | 1 | 0.18% |
| Total | 16714 | 556 |
12345678910111213141516171819202122232425262728293031323334353637383940414243444546474849505152535455565758596061626364656667686970717273747576777879808182838485868788899091929394959697989910010110210310410510610710810911011111211311411511611711811912012112212312412512612712812913013113213313413513613713813914014114214314414514614714814915015115215315415515615715815916016116216316416516616716816917017117217317417517617717817918018118218318418518618718818919019119219319419519619719819920020120220320420520620720820921021121221321421521621721821922022122222322422522622722822923023123223323423523623723823924024124224324424524624724824925025125225325425525625725825926026126226326426526626726826927027127227327427527627727827928028128228328428528628728828929029129229329429529629729829930030130230330430530630730830931031131231331431531631731831932032132232332432532632732832933033133233333433533633733833934034134234334434534634734834935035135235335435535635735835936036136236336436536636736836937037137237337437537637737837938038138238338438538638738838939039139239339439539639739839940040140240340440540640740840941041141241341441541641741841942042142242342442542642742842943043143243343443543643743843944044144244344444544644744844945045145245345445545645745845946046146246346446546646746846947047147247347447547647747847948048148248348448548648748848949049149249349449549649749849950050150250350450550650750850951051151251351451551651751851952052152252352452552652752852953053153253353453553653753853954054154254354454554654754854955055155255355455555655755855956056156256356456556656756856957057157257357457557657757857958058158258358458558658758858959059159259359459559659759859960060160260360460560660760860961061161261361461561661761861962062162262362462562662762862963063163263363463563663763863964064164264364464564664764864965065165265365465565665765865966066166266366466566666766866967067167267367467567667767867968068168268368468568668768868969069169269369469569669769869970070170270370470570670770870971071171271371471571671771871972072172272372472572672772872973073173273373473573673773873974074174274374474574674774874975075175275375475575675775875976076176276376476576676776876977077177277377477577677777877978078178278378478578678778878979079179279379479579679779879980080180280380480580680780880981081181281381481581681781881982082182282382482582682782882983083183283383483583683783883984084184284384484584684784884985085185285385485585685785885986086186286386486586686786886987087187287387487587687787887988088188288388488588688788888989089189289389489589689789889990090190290390490590690790890991091191291391491591691791891992092192292392492592692792892993093193293393493593693793893994094194294394494594694794894995095195295395495595695795895996096196296396496596696796896997097197297397497597697797897998098198298398498598698798898999099199299399499599699799899910001001100210031004100510061007100810091010101110121013101410151016101710181019102010211022102310241025102610271028102910301031103210331034103510361037103810391040104110421043104410451046104710481049105010511052105310541055105610571058105910601061106210631064106510661067106810691070107110721073107410751076107710781079108010811082108310841085108610871088108910901091109210931094109510961097109810991100110111021103110411051106110711081109111011111112111311141115111611171118111911201121112211231124112511261127112811291130113111321133113411351136113711381139114011411142114311441145114611471148114911501151115211531154115511561157115811591160116111621163116411651166116711681169117011711172117311741175117611771178117911801181118211831184118511861187118811891190119111921193119411951196119711981199120012011202120312041205120612071208120912101211121212131214121512161217121812191220122112221223122412251226122712281229123012311232123312341235123612371238123912401241124212431244124512461247124812491250125112521253125412551256125712581259126012611262126312641265126612671268126912701271127212731274127512761277127812791280128112821283128412851286128712881289129012911292129312941295129612971298129913001301130213031304130513061307130813091310131113121313131413151316131713181319132013211322132313241325132613271328132913301331133213331334133513361337133813391340134113421343134413451346134713481349135013511352135313541355135613571358135913601361136213631364136513661367136813691370137113721373137413751376137713781379138013811382138313841385138613871388138913901391139213931394139513961397139813991400140114021403140414051406140714081409141014111412141314141415141614171418141914201421142214231424142514261427142814291430143114321433143414351436143714381439144014411442144314441445144614471448144914501451145214531454145514561457145814591460146114621463146414651466146714681469147014711472147314741475147614771478147914801481148214831484148514861487148814891490149114921493149414951496149714981499150015011502150315041505150615071508150915101511151215131514151515161517151815191520152115221523152415251526152715281529153015311532153315341535153615371538153915401541154215431544154515461547154815491550155115521553155415551556155715581559156015611562156315641565156615671568156915701571157215731574157515761577157815791580158115821583158415851586158715881589159015911592159315941595159615971598159916001601160216031604160516061607160816091610161116121613161416151616161716181619162016211622162316241625162616271628162916301631163216331634163516361637163816391640164116421643164416451646164716481649165016511652165316541655165616571658165916601661166216631664166516661667166816691670167116721673167416751676167716781679168016811682168316841685168616871688168916901691169216931694169516961697169816991700170117021703170417051706170717081709171017111712171317141715171617171718171917201721172217231724172517261727172817291730173117321733173417351736173717381739174017411742174317441745174617471748174917501751175217531754175517561757175817591760176117621763176417651766176717681769177017711772177317741775177617771778177917801781178217831784178517861787178817891790179117921793179417951796179717981799180018011802180318041805180618071808180918101811181218131814181518161817181818191820182118221823182418251826182718281829183018311832183318341835183618371838183918401841184218431844184518461847184818491850185118521853185418551856185718581859186018611862186318641865186618671868186918701871187218731874187518761877187818791880188118821883188418851886188718881889189018911892189318941895189618971898189919001901190219031904190519061907190819091910191119121913191419151916191719181919192019211922192319241925192619271928192919301931193219331934193519361937193819391940194119421943194419451946194719481949195019511952195319541955195619571958195919601961196219631964196519661967196819691970197119721973197419751976197719781979198019811982198319841985198619871988198919901991199219931994199519961997199819992000200120022003200420052006200720082009201020112012201320142015201620172018201920202021202220232024202520262027202820292030203120322033203420352036203720382039204020412042204320442045204620472048204920502051205220532054205520562057205820592060206120622063206420652066206720682069207020712072207320742075207620772078207920802081208220832084208520862087208820892090209120922093209420952096209720982099210021012102210321042105210621072108210921102111211221132114211521162117211821192120212121222123212421252126212721282129213021312132213321342135213621372138213921402141214221432144214521462147214821492150215121522153215421552156215721582159216021612162216321642165216621672168216921702171217221732174217521762177217821792180218121822183218421852186218721882189219021912192219321942195219621972198219922002201220222032204220522062207220822092210221122122213221422152216221722182219222022212222222322242225222622272228222922302231223222332234223522362237223822392240224122422243224422452246224722482249225022512252225322542255225622572258225922602261226222632264226522662267226822692270227122722273227422752276227722782279228022812282228322842285228622872288228922902291229222932294229522962297229822992300230123022303230423052306230723082309231023112312231323142315231623172318231923202321232223232324232523262327232823292330233123322333233423352336233723382339234023412342234323442345234623472348234923502351235223532354235523562357235823592360236123622363236423652366236723682369237023712372237323742375237623772378237923802381238223832384238523862387238823892390239123922393239423952396239723982399240024012402240324042405240624072408240924102411241224132414241524162417241824192420242124222423242424252426242724282429243024312432243324342435243624372438243924402441244224432444244524462447244824492450245124522453245424552456245724582459246024612462246324642465246624672468246924702471247224732474247524762477247824792480248124822483248424852486248724882489249024912492249324942495249624972498249925002501250225032504250525062507250825092510251125122513251425152516251725182519252025212522252325242525252625272528252925302531253225332534253525362537253825392540254125422543254425452546254725482549255025512552255325542555255625572558255925602561256225632564256525662567256825692570257125722573257425752576257725782579258025812582258325842585258625872588258925902591259225932594259525962597259825992600260126022603260426052606260726082609261026112612261326142615261626172618261926202621262226232624262526262627262826292630263126322633263426352636263726382639264026412642264326442645264626472648264926502651265226532654265526562657265826592660266126622663266426652666266726682669267026712672267326742675267626772678267926802681268226832684268526862687268826892690269126922693269426952696269726982699270027012702270327042705270627072708270927102711271227132714271527162717271827192720272127222723272427252726272727282729273027312732273327342735273627372738273927402741274227432744274527462747274827492750275127522753275427552756275727582759276027612762276327642765276627672768276927702771277227732774277527762777277827792780278127822783278427852786278727882789279027912792279327942795279627972798279928002801280228032804280528062807280828092810281128122813281428152816281728182819282028212822282328242825282628272828282928302831283228332834283528362837283828392840284128422843284428452846284728482849285028512852285328542855285628572858285928602861286228632864286528662867286828692870287128722873287428752876287728782879288028812882288328842885288628872888288928902891289228932894289528962897289828992900290129022903290429052906290729082909291029112912291329142915291629172918291929202921292229232924292529262927292829292930293129322933293429352936293729382939294029412942294329442945294629472948294929502951295229532954295529562957295829592960296129622963296429652966296729682969297029712972297329742975297629772978297929802981298229832984298529862987298829892990299129922993299429952996299729982999300030013002300330043005300630073008300930103011301230133014301530163017301830193020302130223023302430253026302730283029303030313032303330343035303630373038303930403041304230433044304530463047304830493050305130523053305430553056305730583059306030613062306330643065306630673068306930703071307230733074307530763077307830793080308130823083308430853086308730883089309030913092309330943095309630973098309931003101310231033104310531063107310831093110311131123113311431153116311731183119312031213122312331243125312631273128312931303131313231333134313531363137313831393140314131423143314431453146314731483149315031513152315331543155315631573158315931603161316231633164316531663167316831693170317131723173317431753176317731783179318031813182318331843185318631873188318931903191319231933194319531963197319831993200320132023203320432053206320732083209321032113212321332143215321632173218321932203221322232233224322532263227322832293230323132323233323432353236323732383239324032413242324332443245324632473248324932503251325232533254325532563257325832593260326132623263326432653266326732683269327032713272327332743275327632773278327932803281328232833284328532863287328832893290329132923293329432953296329732983299330033013302330333043305330633073308330933103311331233133314331533163317331833193320332133223323332433253326332733283329333033313332333333343335333633373338333933403341334233433344334533463347334833493350335133523353335433553356335733583359336033613362336333643365336633673368336933703371337233733374337533763377337833793380338133823383338433853386338733883389339033913392339333943395339633973398339934003401340234033404340534063407340834093410341134123413341434153416341734183419342034213422342334243425342634273428342934303431343234333434343534363437343834393440344134423443344434453446344734483449345034513452345334543455345634573458345934603461346234633464346534663467346834693470347134723473347434753476347734783479348034813482348334843485348634873488348934903491349234933494349534963497349834993500350135023503350435053506350735083509351035113512351335143515351635173518351935203521352235233524352535263527352835293530353135323533353435353536
// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2011, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com> * * Parts came from builtin-{top,stat,record}.c, see those files for further * copyright notes. */ #include <byteswap.h> #include <errno.h> #include <inttypes.h> #include <linux/bitops.h> #include <api/io.h> #include <api/fs/fs.h> #include <api/fs/tracing_path.h> #include <linux/hw_breakpoint.h> #include <linux/perf_event.h> #include <linux/compiler.h> #include <linux/err.h> #include <linux/zalloc.h> #include <sys/ioctl.h> #include <sys/resource.h> #include <sys/types.h> #include <dirent.h> #include <stdlib.h> #include <perf/evsel.h> #include "asm/bug.h" #include "bpf_counter.h" #include "callchain.h" #include "cgroup.h" #include "counts.h" #include "event.h" #include "evsel.h" #include "time-utils.h" #include "util/env.h" #include "util/evsel_config.h" #include "util/evsel_fprintf.h" #include "evlist.h" #include <perf/cpumap.h> #include "thread_map.h" #include "target.h" #include "perf_regs.h" #include "record.h" #include "debug.h" #include "trace-event.h" #include "stat.h" #include "string2.h" #include "memswap.h" #include "util.h" #include "util/hashmap.h" #include "off_cpu.h" #include "pmu.h" #include "pmus.h" #include "rlimit.h" #include "../perf-sys.h" #include "util/parse-branch-options.h" #include "util/bpf-filter.h" #include "util/hist.h" #include <internal/xyarray.h> #include <internal/lib.h> #include <internal/threadmap.h> #include "util/intel-tpebs.h" #include <linux/ctype.h> #ifdef HAVE_LIBTRACEEVENT #include <traceevent/event-parse.h> #endif struct perf_missing_features perf_missing_features; static clockid_t clockid; static const char *const perf_tool_event__tool_names[PERF_TOOL_MAX] = { NULL, "duration_time", "user_time", "system_time", }; const char *perf_tool_event__to_str(enum perf_tool_event ev) { if (ev > PERF_TOOL_NONE && ev < PERF_TOOL_MAX) return perf_tool_event__tool_names[ev]; return NULL; } enum perf_tool_event perf_tool_event__from_str(const char *str) { int i; perf_tool_event__for_each_event(i) { if (!strcmp(str, perf_tool_event__tool_names[i])) return i; } return PERF_TOOL_NONE; } static int evsel__no_extra_init(struct evsel *evsel __maybe_unused) { return 0; } void __weak test_attr__ready(void) { } static void evsel__no_extra_fini(struct evsel *evsel __maybe_unused) { } static struct { size_t size; int (*init)(struct evsel *evsel); void (*fini)(struct evsel *evsel); } perf_evsel__object = { .size = sizeof(struct evsel), .init = evsel__no_extra_init, .fini = evsel__no_extra_fini, }; int evsel__object_config(size_t object_size, int (*init)(struct evsel *evsel), void (*fini)(struct evsel *evsel)) { if (object_size == 0) goto set_methods; if (perf_evsel__object.size > object_size) return -EINVAL; perf_evsel__object.size = object_size; set_methods: if (init != NULL) perf_evsel__object.init = init; if (fini != NULL) perf_evsel__object.fini = fini; return 0; } #define FD(e, x, y) (*(int *)xyarray__entry(e->core.fd, x, y)) int __evsel__sample_size(u64 sample_type) { u64 mask = sample_type & PERF_SAMPLE_MASK; int size = 0; int i; for (i = 0; i < 64; i++) { if (mask & (1ULL << i)) size++; } size *= sizeof(u64); return size; } /** * __perf_evsel__calc_id_pos - calculate id_pos. * @sample_type: sample type * * This function returns the position of the event id (PERF_SAMPLE_ID or * PERF_SAMPLE_IDENTIFIER) in a sample event i.e. in the array of struct * perf_record_sample. */ static int __perf_evsel__calc_id_pos(u64 sample_type) { int idx = 0; if (sample_type & PERF_SAMPLE_IDENTIFIER) return 0; if (!(sample_type & PERF_SAMPLE_ID)) return -1; if (sample_type & PERF_SAMPLE_IP) idx += 1; if (sample_type & PERF_SAMPLE_TID) idx += 1; if (sample_type & PERF_SAMPLE_TIME) idx += 1; if (sample_type & PERF_SAMPLE_ADDR) idx += 1; return idx; } /** * __perf_evsel__calc_is_pos - calculate is_pos. * @sample_type: sample type * * This function returns the position (counting backwards) of the event id * (PERF_SAMPLE_ID or PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if * sample_id_all is used there is an id sample appended to non-sample events. */ static int __perf_evsel__calc_is_pos(u64 sample_type) { int idx = 1; if (sample_type & PERF_SAMPLE_IDENTIFIER) return 1; if (!(sample_type & PERF_SAMPLE_ID)) return -1; if (sample_type & PERF_SAMPLE_CPU) idx += 1; if (sample_type & PERF_SAMPLE_STREAM_ID) idx += 1; return idx; } void evsel__calc_id_pos(struct evsel *evsel) { evsel->id_pos = __perf_evsel__calc_id_pos(evsel->core.attr.sample_type); evsel->is_pos = __perf_evsel__calc_is_pos(evsel->core.attr.sample_type); } void __evsel__set_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit) { if (!(evsel->core.attr.sample_type & bit)) { evsel->core.attr.sample_type |= bit; evsel->sample_size += sizeof(u64); evsel__calc_id_pos(evsel); } } void __evsel__reset_sample_bit(struct evsel *evsel, enum perf_event_sample_format bit) { if (evsel->core.attr.sample_type & bit) { evsel->core.attr.sample_type &= ~bit; evsel->sample_size -= sizeof(u64); evsel__calc_id_pos(evsel); } } void evsel__set_sample_id(struct evsel *evsel, bool can_sample_identifier) { if (can_sample_identifier) { evsel__reset_sample_bit(evsel, ID); evsel__set_sample_bit(evsel, IDENTIFIER); } else { evsel__set_sample_bit(evsel, ID); } evsel->core.attr.read_format |= PERF_FORMAT_ID; } /** * evsel__is_function_event - Return whether given evsel is a function * trace event * * @evsel - evsel selector to be tested * * Return %true if event is function trace event */ bool evsel__is_function_event(struct evsel *evsel) { #define FUNCTION_EVENT "ftrace:function" return evsel->name && !strncmp(FUNCTION_EVENT, evsel->name, sizeof(FUNCTION_EVENT)); #undef FUNCTION_EVENT } void evsel__init(struct evsel *evsel, struct perf_event_attr *attr, int idx) { perf_evsel__init(&evsel->core, attr, idx); evsel->tracking = !idx; evsel->unit = strdup(""); evsel->scale = 1.0; evsel->max_events = ULONG_MAX; evsel->evlist = NULL; evsel->bpf_obj = NULL; evsel->bpf_fd = -1; INIT_LIST_HEAD(&evsel->config_terms); INIT_LIST_HEAD(&evsel->bpf_counter_list); INIT_LIST_HEAD(&evsel->bpf_filters); perf_evsel__object.init(evsel); evsel->sample_size = __evsel__sample_size(attr->sample_type); evsel__calc_id_pos(evsel); evsel->cmdline_group_boundary = false; evsel->metric_events = NULL; evsel->per_pkg_mask = NULL; evsel->collect_stat = false; evsel->pmu_name = NULL; evsel->group_pmu_name = NULL; evsel->skippable = false; } struct evsel *evsel__new_idx(struct perf_event_attr *attr, int idx) { struct evsel *evsel = zalloc(perf_evsel__object.size); if (!evsel) return NULL; evsel__init(evsel, attr, idx); if (evsel__is_bpf_output(evsel) && !attr->sample_type) { evsel->core.attr.sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD), evsel->core.attr.sample_period = 1; } if (evsel__is_clock(evsel)) { free((char *)evsel->unit); evsel->unit = strdup("msec"); evsel->scale = 1e-6; } return evsel; } int copy_config_terms(struct list_head *dst, struct list_head *src) { struct evsel_config_term *pos, *tmp; list_for_each_entry(pos, src, list) { tmp = malloc(sizeof(*tmp)); if (tmp == NULL) return -ENOMEM; *tmp = *pos; if (tmp->free_str) { tmp->val.str = strdup(pos->val.str); if (tmp->val.str == NULL) { free(tmp); return -ENOMEM; } } list_add_tail(&tmp->list, dst); } return 0; } static int evsel__copy_config_terms(struct evsel *dst, struct evsel *src) { return copy_config_terms(&dst->config_terms, &src->config_terms); } /** * evsel__clone - create a new evsel copied from @orig * @orig: original evsel * * The assumption is that @orig is not configured nor opened yet. * So we only care about the attributes that can be set while it's parsed. */ struct evsel *evsel__clone(struct evsel *orig) { struct evsel *evsel; BUG_ON(orig->core.fd); BUG_ON(orig->counts); BUG_ON(orig->priv); BUG_ON(orig->per_pkg_mask); /* cannot handle BPF objects for now */ if (orig->bpf_obj) return NULL; evsel = evsel__new(&orig->core.attr); if (evsel == NULL) return NULL; evsel->core.cpus = perf_cpu_map__get(orig->core.cpus); evsel->core.own_cpus = perf_cpu_map__get(orig->core.own_cpus); evsel->core.threads = perf_thread_map__get(orig->core.threads); evsel->core.nr_members = orig->core.nr_members; evsel->core.system_wide = orig->core.system_wide; evsel->core.requires_cpu = orig->core.requires_cpu; evsel->core.is_pmu_core = orig->core.is_pmu_core; if (orig->name) { evsel->name = strdup(orig->name); if (evsel->name == NULL) goto out_err; } if (orig->group_name) { evsel->group_name = strdup(orig->group_name); if (evsel->group_name == NULL) goto out_err; } if (orig->pmu_name) { evsel->pmu_name = strdup(orig->pmu_name); if (evsel->pmu_name == NULL) goto out_err; } if (orig->group_pmu_name) { evsel->group_pmu_name = strdup(orig->group_pmu_name); if (evsel->group_pmu_name == NULL) goto out_err; } if (orig->filter) { evsel->filter = strdup(orig->filter); if (evsel->filter == NULL) goto out_err; } if (orig->metric_id) { evsel->metric_id = strdup(orig->metric_id); if (evsel->metric_id == NULL) goto out_err; } evsel->cgrp = cgroup__get(orig->cgrp); #ifdef HAVE_LIBTRACEEVENT evsel->tp_format = orig->tp_format; #endif evsel->handler = orig->handler; evsel->core.leader = orig->core.leader; evsel->max_events = orig->max_events; evsel->tool_event = orig->tool_event; free((char *)evsel->unit); evsel->unit = strdup(orig->unit); if (evsel->unit == NULL) goto out_err; evsel->scale = orig->scale; evsel->snapshot = orig->snapshot; evsel->per_pkg = orig->per_pkg; evsel->percore = orig->percore; evsel->precise_max = orig->precise_max; evsel->is_libpfm_event = orig->is_libpfm_event; evsel->exclude_GH = orig->exclude_GH; evsel->sample_read = orig->sample_read; evsel->auto_merge_stats = orig->auto_merge_stats; evsel->collect_stat = orig->collect_stat; evsel->weak_group = orig->weak_group; evsel->use_config_name = orig->use_config_name; evsel->pmu = orig->pmu; if (evsel__copy_config_terms(evsel, orig) < 0) goto out_err; return evsel; out_err: evsel__delete(evsel); return NULL; } /* * Returns pointer with encoded error via <linux/err.h> interface. */ #ifdef HAVE_LIBTRACEEVENT struct evsel *evsel__newtp_idx(const char *sys, const char *name, int idx, bool format) { struct evsel *evsel = zalloc(perf_evsel__object.size); int err = -ENOMEM; if (evsel == NULL) { goto out_err; } else { struct perf_event_attr attr = { .type = PERF_TYPE_TRACEPOINT, .sample_type = (PERF_SAMPLE_RAW | PERF_SAMPLE_TIME | PERF_SAMPLE_CPU | PERF_SAMPLE_PERIOD), }; if (asprintf(&evsel->name, "%s:%s", sys, name) < 0) goto out_free; event_attr_init(&attr); if (format) { evsel->tp_format = trace_event__tp_format(sys, name); if (IS_ERR(evsel->tp_format)) { err = PTR_ERR(evsel->tp_format); goto out_free; } attr.config = evsel->tp_format->id; } else { attr.config = (__u64) -1; } attr.sample_period = 1; evsel__init(evsel, &attr, idx); } return evsel; out_free: zfree(&evsel->name); free(evsel); out_err: return ERR_PTR(err); } #endif const char *const evsel__hw_names[PERF_COUNT_HW_MAX] = { "cycles", "instructions", "cache-references", "cache-misses", "branches", "branch-misses", "bus-cycles", "stalled-cycles-frontend", "stalled-cycles-backend", "ref-cycles", }; char *evsel__bpf_counter_events; bool evsel__match_bpf_counter_events(const char *name) { int name_len; bool match; char *ptr; if (!evsel__bpf_counter_events) return false; ptr = strstr(evsel__bpf_counter_events, name); name_len = strlen(name); /* check name matches a full token in evsel__bpf_counter_events */ match = (ptr != NULL) && ((ptr == evsel__bpf_counter_events) || (*(ptr - 1) == ',')) && ((*(ptr + name_len) == ',') || (*(ptr + name_len) == '\0')); return match; } static const char *__evsel__hw_name(u64 config) { if (config < PERF_COUNT_HW_MAX && evsel__hw_names[config]) return evsel__hw_names[config]; return "unknown-hardware"; } static int evsel__add_modifiers(struct evsel *evsel, char *bf, size_t size) { int colon = 0, r = 0; struct perf_event_attr *attr = &evsel->core.attr; bool exclude_guest_default = false; #define MOD_PRINT(context, mod) do { \ if (!attr->exclude_##context) { \ if (!colon) colon = ++r; \ r += scnprintf(bf + r, size - r, "%c", mod); \ } } while(0) if (attr->exclude_kernel || attr->exclude_user || attr->exclude_hv) { MOD_PRINT(kernel, 'k'); MOD_PRINT(user, 'u'); MOD_PRINT(hv, 'h'); exclude_guest_default = true; } if (attr->precise_ip) { if (!colon) colon = ++r; r += scnprintf(bf + r, size - r, "%.*s", attr->precise_ip, "ppp"); exclude_guest_default = true; } if (attr->exclude_host || attr->exclude_guest == exclude_guest_default) { MOD_PRINT(host, 'H'); MOD_PRINT(guest, 'G'); } #undef MOD_PRINT if (colon) bf[colon - 1] = ':'; return r; } int __weak arch_evsel__hw_name(struct evsel *evsel, char *bf, size_t size) { return scnprintf(bf, size, "%s", __evsel__hw_name(evsel->core.attr.config)); } static int evsel__hw_name(struct evsel *evsel, char *bf, size_t size) { int r = arch_evsel__hw_name(evsel, bf, size); return r + evsel__add_modifiers(evsel, bf + r, size - r); } const char *const evsel__sw_names[PERF_COUNT_SW_MAX] = { "cpu-clock", "task-clock", "page-faults", "context-switches", "cpu-migrations", "minor-faults", "major-faults", "alignment-faults", "emulation-faults", "dummy", }; static const char *__evsel__sw_name(u64 config) { if (config < PERF_COUNT_SW_MAX && evsel__sw_names[config]) return evsel__sw_names[config]; return "unknown-software"; } static int evsel__sw_name(struct evsel *evsel, char *bf, size_t size) { int r = scnprintf(bf, size, "%s", __evsel__sw_name(evsel->core.attr.config)); return r + evsel__add_modifiers(evsel, bf + r, size - r); } static int evsel__tool_name(enum perf_tool_event ev, char *bf, size_t size) { return scnprintf(bf, size, "%s", perf_tool_event__to_str(ev)); } static int __evsel__bp_name(char *bf, size_t size, u64 addr, u64 type) { int r; r = scnprintf(bf, size, "mem:0x%" PRIx64 ":", addr); if (type & HW_BREAKPOINT_R) r += scnprintf(bf + r, size - r, "r"); if (type & HW_BREAKPOINT_W) r += scnprintf(bf + r, size - r, "w"); if (type & HW_BREAKPOINT_X) r += scnprintf(bf + r, size - r, "x"); return r; } static int evsel__bp_name(struct evsel *evsel, char *bf, size_t size) { struct perf_event_attr *attr = &evsel->core.attr; int r = __evsel__bp_name(bf, size, attr->bp_addr, attr->bp_type); return r + evsel__add_modifiers(evsel, bf + r, size - r); } const char *const evsel__hw_cache[PERF_COUNT_HW_CACHE_MAX][EVSEL__MAX_ALIASES] = { { "L1-dcache", "l1-d", "l1d", "L1-data", }, { "L1-icache", "l1-i", "l1i", "L1-instruction", }, { "LLC", "L2", }, { "dTLB", "d-tlb", "Data-TLB", }, { "iTLB", "i-tlb", "Instruction-TLB", }, { "branch", "branches", "bpu", "btb", "bpc", }, { "node", }, }; const char *const evsel__hw_cache_op[PERF_COUNT_HW_CACHE_OP_MAX][EVSEL__MAX_ALIASES] = { { "load", "loads", "read", }, { "store", "stores", "write", }, { "prefetch", "prefetches", "speculative-read", "speculative-load", }, }; const char *const evsel__hw_cache_result[PERF_COUNT_HW_CACHE_RESULT_MAX][EVSEL__MAX_ALIASES] = { { "refs", "Reference", "ops", "access", }, { "misses", "miss", }, }; #define C(x) PERF_COUNT_HW_CACHE_##x #define CACHE_READ (1 << C(OP_READ)) #define CACHE_WRITE (1 << C(OP_WRITE)) #define CACHE_PREFETCH (1 << C(OP_PREFETCH)) #define COP(x) (1 << x) /* * cache operation stat * L1I : Read and prefetch only * ITLB and BPU : Read-only */ static const unsigned long evsel__hw_cache_stat[C(MAX)] = { [C(L1D)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), [C(L1I)] = (CACHE_READ | CACHE_PREFETCH), [C(LL)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), [C(DTLB)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), [C(ITLB)] = (CACHE_READ), [C(BPU)] = (CACHE_READ), [C(NODE)] = (CACHE_READ | CACHE_WRITE | CACHE_PREFETCH), }; bool evsel__is_cache_op_valid(u8 type, u8 op) { if (evsel__hw_cache_stat[type] & COP(op)) return true; /* valid */ else return false; /* invalid */ } int __evsel__hw_cache_type_op_res_name(u8 type, u8 op, u8 result, char *bf, size_t size) { if (result) { return scnprintf(bf, size, "%s-%s-%s", evsel__hw_cache[type][0], evsel__hw_cache_op[op][0], evsel__hw_cache_result[result][0]); } return scnprintf(bf, size, "%s-%s", evsel__hw_cache[type][0], evsel__hw_cache_op[op][1]); } static int __evsel__hw_cache_name(u64 config, char *bf, size_t size) { u8 op, result, type = (config >> 0) & 0xff; const char *err = "unknown-ext-hardware-cache-type"; if (type >= PERF_COUNT_HW_CACHE_MAX) goto out_err; op = (config >> 8) & 0xff; err = "unknown-ext-hardware-cache-op"; if (op >= PERF_COUNT_HW_CACHE_OP_MAX) goto out_err; result = (config >> 16) & 0xff; err = "unknown-ext-hardware-cache-result"; if (result >= PERF_COUNT_HW_CACHE_RESULT_MAX) goto out_err; err = "invalid-cache"; if (!evsel__is_cache_op_valid(type, op)) goto out_err; return __evsel__hw_cache_type_op_res_name(type, op, result, bf, size); out_err: return scnprintf(bf, size, "%s", err); } static int evsel__hw_cache_name(struct evsel *evsel, char *bf, size_t size) { int ret = __evsel__hw_cache_name(evsel->core.attr.config, bf, size); return ret + evsel__add_modifiers(evsel, bf + ret, size - ret); } static int evsel__raw_name(struct evsel *evsel, char *bf, size_t size) { int ret = scnprintf(bf, size, "raw 0x%" PRIx64, evsel->core.attr.config); return ret + evsel__add_modifiers(evsel, bf + ret, size - ret); } const char *evsel__name(struct evsel *evsel) { char bf[128]; if (!evsel) goto out_unknown; if (evsel->name) return evsel->name; switch (evsel->core.attr.type) { case PERF_TYPE_RAW: evsel__raw_name(evsel, bf, sizeof(bf)); break; case PERF_TYPE_HARDWARE: evsel__hw_name(evsel, bf, sizeof(bf)); break; case PERF_TYPE_HW_CACHE: evsel__hw_cache_name(evsel, bf, sizeof(bf)); break; case PERF_TYPE_SOFTWARE: if (evsel__is_tool(evsel)) evsel__tool_name(evsel__tool_event(evsel), bf, sizeof(bf)); else evsel__sw_name(evsel, bf, sizeof(bf)); break; case PERF_TYPE_TRACEPOINT: scnprintf(bf, sizeof(bf), "%s", "unknown tracepoint"); break; case PERF_TYPE_BREAKPOINT: evsel__bp_name(evsel, bf, sizeof(bf)); break; default: scnprintf(bf, sizeof(bf), "unknown attr type: %d", evsel->core.attr.type); break; } evsel->name = strdup(bf); if (evsel->name) return evsel->name; out_unknown: return "unknown"; } bool evsel__name_is(struct evsel *evsel, const char *name) { return !strcmp(evsel__name(evsel), name); } const char *evsel__metric_id(const struct evsel *evsel) { if (evsel->metric_id) return evsel->metric_id; if (evsel__is_tool(evsel)) return perf_tool_event__to_str(evsel__tool_event(evsel)); return "unknown"; } const char *evsel__group_name(struct evsel *evsel) { return evsel->group_name ?: "anon group"; } /* * Returns the group details for the specified leader, * with following rules. * * For record -e '{cycles,instructions}' * 'anon group { cycles:u, instructions:u }' * * For record -e 'cycles,instructions' and report --group * 'cycles:u, instructions:u' */ int evsel__group_desc(struct evsel *evsel, char *buf, size_t size) { int ret = 0; bool first = true; struct evsel *pos; const char *group_name = evsel__group_name(evsel); if (!evsel->forced_leader) ret = scnprintf(buf, size, "%s { ", group_name); for_each_group_evsel(pos, evsel) { if (symbol_conf.skip_empty && evsel__hists(pos)->stats.nr_samples == 0) continue; ret += scnprintf(buf + ret, size - ret, "%s%s", first ? "" : ", ", evsel__name(pos)); first = false; } if (!evsel->forced_leader) ret += scnprintf(buf + ret, size - ret, " }"); return ret; } static void __evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, struct callchain_param *param) { bool function = evsel__is_function_event(evsel); struct perf_event_attr *attr = &evsel->core.attr; const char *arch = perf_env__arch(evsel__env(evsel)); evsel__set_sample_bit(evsel, CALLCHAIN); attr->sample_max_stack = param->max_stack; if (opts->kernel_callchains) attr->exclude_callchain_user = 1; if (opts->user_callchains) attr->exclude_callchain_kernel = 1; if (param->record_mode == CALLCHAIN_LBR) { if (!opts->branch_stack) { if (attr->exclude_user) { pr_warning("LBR callstack option is only available " "to get user callchain information. " "Falling back to framepointers.\n"); } else { evsel__set_sample_bit(evsel, BRANCH_STACK); attr->branch_sample_type = PERF_SAMPLE_BRANCH_USER | PERF_SAMPLE_BRANCH_CALL_STACK | PERF_SAMPLE_BRANCH_NO_CYCLES | PERF_SAMPLE_BRANCH_NO_FLAGS | PERF_SAMPLE_BRANCH_HW_INDEX; } } else pr_warning("Cannot use LBR callstack with branch stack. " "Falling back to framepointers.\n"); } if (param->record_mode == CALLCHAIN_DWARF) { if (!function) { evsel__set_sample_bit(evsel, REGS_USER); evsel__set_sample_bit(evsel, STACK_USER); if (opts->sample_user_regs && DWARF_MINIMAL_REGS(arch) != arch__user_reg_mask()) { attr->sample_regs_user |= DWARF_MINIMAL_REGS(arch); pr_warning("WARNING: The use of --call-graph=dwarf may require all the user registers, " "specifying a subset with --user-regs may render DWARF unwinding unreliable, " "so the minimal registers set (IP, SP) is explicitly forced.\n"); } else { attr->sample_regs_user |= arch__user_reg_mask(); } attr->sample_stack_user = param->dump_size; attr->exclude_callchain_user = 1; } else { pr_info("Cannot use DWARF unwind for function trace event," " falling back to framepointers.\n"); } } if (function) { pr_info("Disabling user space callchains for function trace event.\n"); attr->exclude_callchain_user = 1; } } void evsel__config_callchain(struct evsel *evsel, struct record_opts *opts, struct callchain_param *param) { if (param->enabled) return __evsel__config_callchain(evsel, opts, param); } static void evsel__reset_callgraph(struct evsel *evsel, struct callchain_param *param) { struct perf_event_attr *attr = &evsel->core.attr; evsel__reset_sample_bit(evsel, CALLCHAIN); if (param->record_mode == CALLCHAIN_LBR) { evsel__reset_sample_bit(evsel, BRANCH_STACK); attr->branch_sample_type &= ~(PERF_SAMPLE_BRANCH_USER | PERF_SAMPLE_BRANCH_CALL_STACK | PERF_SAMPLE_BRANCH_HW_INDEX); } if (param->record_mode == CALLCHAIN_DWARF) { evsel__reset_sample_bit(evsel, REGS_USER); evsel__reset_sample_bit(evsel, STACK_USER); } } static void evsel__apply_config_terms(struct evsel *evsel, struct record_opts *opts, bool track) { struct evsel_config_term *term; struct list_head *config_terms = &evsel->config_terms; struct perf_event_attr *attr = &evsel->core.attr; /* callgraph default */ struct callchain_param param = { .record_mode = callchain_param.record_mode, }; u32 dump_size = 0; int max_stack = 0; const char *callgraph_buf = NULL; list_for_each_entry(term, config_terms, list) { switch (term->type) { case EVSEL__CONFIG_TERM_PERIOD: if (!(term->weak && opts->user_interval != ULLONG_MAX)) { attr->sample_period = term->val.period; attr->freq = 0; evsel__reset_sample_bit(evsel, PERIOD); } break; case EVSEL__CONFIG_TERM_FREQ: if (!(term->weak && opts->user_freq != UINT_MAX)) { attr->sample_freq = term->val.freq; attr->freq = 1; evsel__set_sample_bit(evsel, PERIOD); } break; case EVSEL__CONFIG_TERM_TIME: if (term->val.time) evsel__set_sample_bit(evsel, TIME); else evsel__reset_sample_bit(evsel, TIME); break; case EVSEL__CONFIG_TERM_CALLGRAPH: callgraph_buf = term->val.str; break; case EVSEL__CONFIG_TERM_BRANCH: if (term->val.str && strcmp(term->val.str, "no")) { evsel__set_sample_bit(evsel, BRANCH_STACK); parse_branch_str(term->val.str, &attr->branch_sample_type); } else evsel__reset_sample_bit(evsel, BRANCH_STACK); break; case EVSEL__CONFIG_TERM_STACK_USER: dump_size = term->val.stack_user; break; case EVSEL__CONFIG_TERM_MAX_STACK: max_stack = term->val.max_stack; break; case EVSEL__CONFIG_TERM_MAX_EVENTS: evsel->max_events = term->val.max_events; break; case EVSEL__CONFIG_TERM_INHERIT: /* * attr->inherit should has already been set by * evsel__config. If user explicitly set * inherit using config terms, override global * opt->no_inherit setting. */ attr->inherit = term->val.inherit ? 1 : 0; break; case EVSEL__CONFIG_TERM_OVERWRITE: attr->write_backward = term->val.overwrite ? 1 : 0; break; case EVSEL__CONFIG_TERM_DRV_CFG: break; case EVSEL__CONFIG_TERM_PERCORE: break; case EVSEL__CONFIG_TERM_AUX_OUTPUT: attr->aux_output = term->val.aux_output ? 1 : 0; break; case EVSEL__CONFIG_TERM_AUX_SAMPLE_SIZE: /* Already applied by auxtrace */ break; case EVSEL__CONFIG_TERM_CFG_CHG: break; default: break; } } /* User explicitly set per-event callgraph, clear the old setting and reset. */ if ((callgraph_buf != NULL) || (dump_size > 0) || max_stack) { bool sample_address = false; if (max_stack) { param.max_stack = max_stack; if (callgraph_buf == NULL) callgraph_buf = "fp"; } /* parse callgraph parameters */ if (callgraph_buf != NULL) { if (!strcmp(callgraph_buf, "no")) { param.enabled = false; param.record_mode = CALLCHAIN_NONE; } else { param.enabled = true; if (parse_callchain_record(callgraph_buf, ¶m)) { pr_err("per-event callgraph setting for %s failed. " "Apply callgraph global setting for it\n", evsel->name); return; } if (param.record_mode == CALLCHAIN_DWARF) sample_address = true; } } if (dump_size > 0) { dump_size = round_up(dump_size, sizeof(u64)); param.dump_size = dump_size; } /* If global callgraph set, clear it */ if (callchain_param.enabled) evsel__reset_callgraph(evsel, &callchain_param); /* set perf-event callgraph */ if (param.enabled) { if (sample_address) { evsel__set_sample_bit(evsel, ADDR); evsel__set_sample_bit(evsel, DATA_SRC); evsel->core.attr.mmap_data = track; } evsel__config_callchain(evsel, opts, ¶m); } } } struct evsel_config_term *__evsel__get_config_term(struct evsel *evsel, enum evsel_term_type type) { struct evsel_config_term *term, *found_term = NULL; list_for_each_entry(term, &evsel->config_terms, list) { if (term->type == type) found_term = term; } return found_term; } void __weak arch_evsel__set_sample_weight(struct evsel *evsel) { evsel__set_sample_bit(evsel, WEIGHT); } void __weak arch__post_evsel_config(struct evsel *evsel __maybe_unused, struct perf_event_attr *attr __maybe_unused) { } static void evsel__set_default_freq_period(struct record_opts *opts, struct perf_event_attr *attr) { if (opts->freq) { attr->freq = 1; attr->sample_freq = opts->freq; } else { attr->sample_period = opts->default_interval; } } static bool evsel__is_offcpu_event(struct evsel *evsel) { return evsel__is_bpf_output(evsel) && evsel__name_is(evsel, OFFCPU_EVENT); } /* * The enable_on_exec/disabled value strategy: * * 1) For any type of traced program: * - all independent events and group leaders are disabled * - all group members are enabled * * Group members are ruled by group leaders. They need to * be enabled, because the group scheduling relies on that. * * 2) For traced programs executed by perf: * - all independent events and group leaders have * enable_on_exec set * - we don't specifically enable or disable any event during * the record command * * Independent events and group leaders are initially disabled * and get enabled by exec. Group members are ruled by group * leaders as stated in 1). * * 3) For traced programs attached by perf (pid/tid): * - we specifically enable or disable all events during * the record command * * When attaching events to already running traced we * enable/disable events specifically, as there's no * initial traced exec call. */ void evsel__config(struct evsel *evsel, struct record_opts *opts, struct callchain_param *callchain) { struct evsel *leader = evsel__leader(evsel); struct perf_event_attr *attr = &evsel->core.attr; int track = evsel->tracking; bool per_cpu = opts->target.default_per_cpu && !opts->target.per_thread; attr->sample_id_all = perf_missing_features.sample_id_all ? 0 : 1; attr->inherit = !opts->no_inherit; attr->write_backward = opts->overwrite ? 1 : 0; attr->read_format = PERF_FORMAT_LOST; evsel__set_sample_bit(evsel, IP); evsel__set_sample_bit(evsel, TID); if (evsel->sample_read) { evsel__set_sample_bit(evsel, READ); /* * We need ID even in case of single event, because * PERF_SAMPLE_READ process ID specific data. */ evsel__set_sample_id(evsel, false); /* * Apply group format only if we belong to group * with more than one members. */ if (leader->core.nr_members > 1) { attr->read_format |= PERF_FORMAT_GROUP; attr->inherit = 0; } } /* * We default some events to have a default interval. But keep * it a weak assumption overridable by the user. */ if ((evsel->is_libpfm_event && !attr->sample_period) || (!evsel->is_libpfm_event && (!attr->sample_period || opts->user_freq != UINT_MAX || opts->user_interval != ULLONG_MAX))) evsel__set_default_freq_period(opts, attr); /* * If attr->freq was set (here or earlier), ask for period * to be sampled. */ if (attr->freq) evsel__set_sample_bit(evsel, PERIOD); if (opts->no_samples) attr->sample_freq = 0; if (opts->inherit_stat) { evsel->core.attr.read_format |= PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING | PERF_FORMAT_ID; attr->inherit_stat = 1; } if (opts->sample_address) { evsel__set_sample_bit(evsel, ADDR); attr->mmap_data = track; } /* * We don't allow user space callchains for function trace * event, due to issues with page faults while tracing page * fault handler and its overall trickiness nature. */ if (evsel__is_function_event(evsel)) evsel->core.attr.exclude_callchain_user = 1; if (callchain && callchain->enabled && !evsel->no_aux_samples) evsel__config_callchain(evsel, opts, callchain); if (opts->sample_intr_regs && !evsel->no_aux_samples && !evsel__is_dummy_event(evsel)) { attr->sample_regs_intr = opts->sample_intr_regs; evsel__set_sample_bit(evsel, REGS_INTR); } if (opts->sample_user_regs && !evsel->no_aux_samples && !evsel__is_dummy_event(evsel)) { attr->sample_regs_user |= opts->sample_user_regs; evsel__set_sample_bit(evsel, REGS_USER); } if (target__has_cpu(&opts->target) || opts->sample_cpu) evsel__set_sample_bit(evsel, CPU); /* * When the user explicitly disabled time don't force it here. */ if (opts->sample_time && (!perf_missing_features.sample_id_all && (!opts->no_inherit || target__has_cpu(&opts->target) || per_cpu || opts->sample_time_set))) evsel__set_sample_bit(evsel, TIME); if (opts->raw_samples && !evsel->no_aux_samples) { evsel__set_sample_bit(evsel, TIME); evsel__set_sample_bit(evsel, RAW); evsel__set_sample_bit(evsel, CPU); } if (opts->sample_address) evsel__set_sample_bit(evsel, DATA_SRC); if (opts->sample_phys_addr) evsel__set_sample_bit(evsel, PHYS_ADDR); if (opts->no_buffering) { attr->watermark = 0; attr->wakeup_events = 1; } if (opts->branch_stack && !evsel->no_aux_samples) { evsel__set_sample_bit(evsel, BRANCH_STACK); attr->branch_sample_type = opts->branch_stack; } if (opts->sample_weight) arch_evsel__set_sample_weight(evsel); attr->task = track; attr->mmap = track; attr->mmap2 = track && !perf_missing_features.mmap2; attr->comm = track; attr->build_id = track && opts->build_id; /* * ksymbol is tracked separately with text poke because it needs to be * system wide and enabled immediately. */ if (!opts->text_poke) attr->ksymbol = track && !perf_missing_features.ksymbol; attr->bpf_event = track && !opts->no_bpf_event && !perf_missing_features.bpf; if (opts->record_namespaces) attr->namespaces = track; if (opts->record_cgroup) { attr->cgroup = track && !perf_missing_features.cgroup; evsel__set_sample_bit(evsel, CGROUP); } if (opts->sample_data_page_size) evsel__set_sample_bit(evsel, DATA_PAGE_SIZE); if (opts->sample_code_page_size) evsel__set_sample_bit(evsel, CODE_PAGE_SIZE); if (opts->record_switch_events) attr->context_switch = track; if (opts->sample_transaction) evsel__set_sample_bit(evsel, TRANSACTION); if (opts->running_time) { evsel->core.attr.read_format |= PERF_FORMAT_TOTAL_TIME_ENABLED | PERF_FORMAT_TOTAL_TIME_RUNNING; } /* * XXX see the function comment above * * Disabling only independent events or group leaders, * keeping group members enabled. */ if (evsel__is_group_leader(evsel)) attr->disabled = 1; /* * Setting enable_on_exec for independent events and * group leaders for traced executed by perf. */ if (target__none(&opts->target) && evsel__is_group_leader(evsel) && !opts->target.initial_delay) attr->enable_on_exec = 1; if (evsel->immediate) { attr->disabled = 0; attr->enable_on_exec = 0; } clockid = opts->clockid; if (opts->use_clockid) { attr->use_clockid = 1; attr->clockid = opts->clockid; } if (evsel->precise_max) attr->precise_ip = 3; if (opts->all_user) { attr->exclude_kernel = 1; attr->exclude_user = 0; } if (opts->all_kernel) { attr->exclude_kernel = 0; attr->exclude_user = 1; } if (evsel->core.own_cpus || evsel->unit) evsel->core.attr.read_format |= PERF_FORMAT_ID; /* * Apply event specific term settings, * it overloads any global configuration. */ evsel__apply_config_terms(evsel, opts, track); evsel->ignore_missing_thread = opts->ignore_missing_thread; /* The --period option takes the precedence. */ if (opts->period_set) { if (opts->period) evsel__set_sample_bit(evsel, PERIOD); else evsel__reset_sample_bit(evsel, PERIOD); } /* * A dummy event never triggers any actual counter and therefore * cannot be used with branch_stack. * * For initial_delay, a dummy event is added implicitly. * The software event will trigger -EOPNOTSUPP error out, * if BRANCH_STACK bit is set. */ if (evsel__is_dummy_event(evsel)) evsel__reset_sample_bit(evsel, BRANCH_STACK); if (evsel__is_offcpu_event(evsel)) evsel->core.attr.sample_type &= OFFCPU_SAMPLE_TYPES; arch__post_evsel_config(evsel, attr); } int evsel__set_filter(struct evsel *evsel, const char *filter) { char *new_filter = strdup(filter); if (new_filter != NULL) { free(evsel->filter); evsel->filter = new_filter; return 0; } return -1; } static int evsel__append_filter(struct evsel *evsel, const char *fmt, const char *filter) { char *new_filter; if (evsel->filter == NULL) return evsel__set_filter(evsel, filter); if (asprintf(&new_filter, fmt, evsel->filter, filter) > 0) { free(evsel->filter); evsel->filter = new_filter; return 0; } return -1; } int evsel__append_tp_filter(struct evsel *evsel, const char *filter) { return evsel__append_filter(evsel, "(%s) && (%s)", filter); } int evsel__append_addr_filter(struct evsel *evsel, const char *filter) { return evsel__append_filter(evsel, "%s,%s", filter); } /* Caller has to clear disabled after going through all CPUs. */ int evsel__enable_cpu(struct evsel *evsel, int cpu_map_idx) { return perf_evsel__enable_cpu(&evsel->core, cpu_map_idx); } int evsel__enable(struct evsel *evsel) { int err = perf_evsel__enable(&evsel->core); if (!err) evsel->disabled = false; return err; } /* Caller has to set disabled after going through all CPUs. */ int evsel__disable_cpu(struct evsel *evsel, int cpu_map_idx) { return perf_evsel__disable_cpu(&evsel->core, cpu_map_idx); } int evsel__disable(struct evsel *evsel) { int err = perf_evsel__disable(&evsel->core); /* * We mark it disabled here so that tools that disable a event can * ignore events after they disable it. I.e. the ring buffer may have * already a few more events queued up before the kernel got the stop * request. */ if (!err) evsel->disabled = true; return err; } void free_config_terms(struct list_head *config_terms) { struct evsel_config_term *term, *h; list_for_each_entry_safe(term, h, config_terms, list) { list_del_init(&term->list); if (term->free_str) zfree(&term->val.str); free(term); } } static void evsel__free_config_terms(struct evsel *evsel) { free_config_terms(&evsel->config_terms); } void evsel__exit(struct evsel *evsel) { assert(list_empty(&evsel->core.node)); assert(evsel->evlist == NULL); bpf_counter__destroy(evsel); perf_bpf_filter__destroy(evsel); evsel__free_counts(evsel); perf_evsel__free_fd(&evsel->core); perf_evsel__free_id(&evsel->core); evsel__free_config_terms(evsel); cgroup__put(evsel->cgrp); perf_cpu_map__put(evsel->core.cpus); perf_cpu_map__put(evsel->core.own_cpus); perf_thread_map__put(evsel->core.threads); zfree(&evsel->group_name); zfree(&evsel->name); zfree(&evsel->filter); zfree(&evsel->pmu_name); zfree(&evsel->group_pmu_name); zfree(&evsel->unit); zfree(&evsel->metric_id); evsel__zero_per_pkg(evsel); hashmap__free(evsel->per_pkg_mask); evsel->per_pkg_mask = NULL; zfree(&evsel->metric_events); perf_evsel__object.fini(evsel); if (evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME || evsel__tool_event(evsel) == PERF_TOOL_USER_TIME) xyarray__delete(evsel->start_times); } void evsel__delete(struct evsel *evsel) { if (!evsel) return; evsel__exit(evsel); free(evsel); } void evsel__compute_deltas(struct evsel *evsel, int cpu_map_idx, int thread, struct perf_counts_values *count) { struct perf_counts_values tmp; if (!evsel->prev_raw_counts) return; tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread); *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count; count->val = count->val - tmp.val; count->ena = count->ena - tmp.ena; count->run = count->run - tmp.run; } static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread) { struct perf_counts_values *count = perf_counts(evsel->counts, cpu_map_idx, thread); return perf_evsel__read(&evsel->core, cpu_map_idx, thread, count); } static int evsel__read_retire_lat(struct evsel *evsel, int cpu_map_idx, int thread) { return tpebs_set_evsel(evsel, cpu_map_idx, thread); } static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread, u64 val, u64 ena, u64 run, u64 lost) { struct perf_counts_values *count; count = perf_counts(counter->counts, cpu_map_idx, thread); if (counter->retire_lat) { evsel__read_retire_lat(counter, cpu_map_idx, thread); perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true); return; } count->val = val; count->ena = ena; count->run = run; count->lost = lost; perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true); } static bool evsel__group_has_tpebs(struct evsel *leader) { struct evsel *evsel; for_each_group_evsel(evsel, leader) { if (evsel__is_retire_lat(evsel)) return true; } return false; } static u64 evsel__group_read_nr_members(struct evsel *leader) { u64 nr = leader->core.nr_members; struct evsel *evsel; for_each_group_evsel(evsel, leader) { if (evsel__is_retire_lat(evsel)) nr--; } return nr; } static u64 evsel__group_read_size(struct evsel *leader) { u64 read_format = leader->core.attr.read_format; int entry = sizeof(u64); /* value */ int size = 0; int nr = 1; if (!evsel__group_has_tpebs(leader)) return perf_evsel__read_size(&leader->core); if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) size += sizeof(u64); if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) size += sizeof(u64); if (read_format & PERF_FORMAT_ID) entry += sizeof(u64); if (read_format & PERF_FORMAT_LOST) entry += sizeof(u64); if (read_format & PERF_FORMAT_GROUP) { nr = evsel__group_read_nr_members(leader); size += sizeof(u64); } size += entry * nr; return size; } static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int thread, u64 *data) { u64 read_format = leader->core.attr.read_format; struct sample_read_value *v; u64 nr, ena = 0, run = 0, lost = 0; nr = *data++; if (nr != evsel__group_read_nr_members(leader)) return -EINVAL; if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) ena = *data++; if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) run = *data++; v = (void *)data; sample_read_group__for_each(v, nr, read_format) { struct evsel *counter; counter = evlist__id2evsel(leader->evlist, v->id); if (!counter) return -EINVAL; if (read_format & PERF_FORMAT_LOST) lost = v->lost; evsel__set_count(counter, cpu_map_idx, thread, v->value, ena, run, lost); } return 0; } static int evsel__read_group(struct evsel *leader, int cpu_map_idx, int thread) { struct perf_stat_evsel *ps = leader->stats; u64 read_format = leader->core.attr.read_format; int size = evsel__group_read_size(leader); u64 *data = ps->group_data; if (!(read_format & PERF_FORMAT_ID)) return -EINVAL; if (!evsel__is_group_leader(leader)) return -EINVAL; if (!data) { data = zalloc(size); if (!data) return -ENOMEM; ps->group_data = data; } if (FD(leader, cpu_map_idx, thread) < 0) return -EINVAL; if (readn(FD(leader, cpu_map_idx, thread), data, size) <= 0) return -errno; return evsel__process_group_data(leader, cpu_map_idx, thread, data); } static bool read_until_char(struct io *io, char e) { int c; do { c = io__get_char(io); if (c == -1) return false; } while (c != e); return true; } static int read_stat_field(int fd, struct perf_cpu cpu, int field, __u64 *val) { char buf[256]; struct io io; int i; io__init(&io, fd, buf, sizeof(buf)); /* Skip lines to relevant CPU. */ for (i = -1; i < cpu.cpu; i++) { if (!read_until_char(&io, '\n')) return -EINVAL; } /* Skip to "cpu". */ if (io__get_char(&io) != 'c') return -EINVAL; if (io__get_char(&io) != 'p') return -EINVAL; if (io__get_char(&io) != 'u') return -EINVAL; /* Skip N of cpuN. */ if (!read_until_char(&io, ' ')) return -EINVAL; i = 1; while (true) { if (io__get_dec(&io, val) != ' ') break; if (field == i) return 0; i++; } return -EINVAL; } static int read_pid_stat_field(int fd, int field, __u64 *val) { char buf[256]; struct io io; int c, i; io__init(&io, fd, buf, sizeof(buf)); if (io__get_dec(&io, val) != ' ') return -EINVAL; if (field == 1) return 0; /* Skip comm. */ if (io__get_char(&io) != '(' || !read_until_char(&io, ')')) return -EINVAL; if (field == 2) return -EINVAL; /* String can't be returned. */ /* Skip state */ if (io__get_char(&io) != ' ' || io__get_char(&io) == -1) return -EINVAL; if (field == 3) return -EINVAL; /* String can't be returned. */ /* Loop over numeric fields*/ if (io__get_char(&io) != ' ') return -EINVAL; i = 4; while (true) { c = io__get_dec(&io, val); if (c == -1) return -EINVAL; if (c == -2) { /* Assume a -ve was read */ c = io__get_dec(&io, val); *val *= -1; } if (c != ' ') return -EINVAL; if (field == i) return 0; i++; } return -EINVAL; } static int evsel__read_tool(struct evsel *evsel, int cpu_map_idx, int thread) { __u64 *start_time, cur_time, delta_start; int fd, err = 0; struct perf_counts_values *count; bool adjust = false; count = perf_counts(evsel->counts, cpu_map_idx, thread); switch (evsel__tool_event(evsel)) { case PERF_TOOL_DURATION_TIME: /* * Pretend duration_time is only on the first CPU and thread, or * else aggregation will scale duration_time by the number of * CPUs/threads. */ start_time = &evsel->start_time; if (cpu_map_idx == 0 && thread == 0) cur_time = rdclock(); else cur_time = *start_time; break; case PERF_TOOL_USER_TIME: case PERF_TOOL_SYSTEM_TIME: { bool system = evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME; start_time = xyarray__entry(evsel->start_times, cpu_map_idx, thread); fd = FD(evsel, cpu_map_idx, thread); lseek(fd, SEEK_SET, 0); if (evsel->pid_stat) { /* The event exists solely on 1 CPU. */ if (cpu_map_idx == 0) err = read_pid_stat_field(fd, system ? 15 : 14, &cur_time); else cur_time = 0; } else { /* The event is for all threads. */ if (thread == 0) { struct perf_cpu cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx); err = read_stat_field(fd, cpu, system ? 3 : 1, &cur_time); } else { cur_time = 0; } } adjust = true; break; } case PERF_TOOL_NONE: case PERF_TOOL_MAX: default: err = -EINVAL; } if (err) return err; delta_start = cur_time - *start_time; if (adjust) { __u64 ticks_per_sec = sysconf(_SC_CLK_TCK); delta_start *= 1000000000 / ticks_per_sec; } count->val = delta_start; count->ena = count->run = delta_start; count->lost = 0; return 0; } int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread) { if (evsel__is_tool(evsel)) return evsel__read_tool(evsel, cpu_map_idx, thread); if (evsel__is_retire_lat(evsel)) return evsel__read_retire_lat(evsel, cpu_map_idx, thread); if (evsel->core.attr.read_format & PERF_FORMAT_GROUP) return evsel__read_group(evsel, cpu_map_idx, thread); return evsel__read_one(evsel, cpu_map_idx, thread); } int __evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread, bool scale) { struct perf_counts_values count; size_t nv = scale ? 3 : 1; if (FD(evsel, cpu_map_idx, thread) < 0) return -EINVAL; if (evsel->counts == NULL && evsel__alloc_counts(evsel) < 0) return -ENOMEM; if (readn(FD(evsel, cpu_map_idx, thread), &count, nv * sizeof(u64)) <= 0) return -errno; evsel__compute_deltas(evsel, cpu_map_idx, thread, &count); perf_counts_values__scale(&count, scale, NULL); *perf_counts(evsel->counts, cpu_map_idx, thread) = count; return 0; } static int evsel__match_other_cpu(struct evsel *evsel, struct evsel *other, int cpu_map_idx) { struct perf_cpu cpu; cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx); return perf_cpu_map__idx(other->core.cpus, cpu); } static int evsel__hybrid_group_cpu_map_idx(struct evsel *evsel, int cpu_map_idx) { struct evsel *leader = evsel__leader(evsel); if ((evsel__is_hybrid(evsel) && !evsel__is_hybrid(leader)) || (!evsel__is_hybrid(evsel) && evsel__is_hybrid(leader))) { return evsel__match_other_cpu(evsel, leader, cpu_map_idx); } return cpu_map_idx; } static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread) { struct evsel *leader = evsel__leader(evsel); int fd; if (evsel__is_group_leader(evsel)) return -1; /* * Leader must be already processed/open, * if not it's a bug. */ BUG_ON(!leader->core.fd); cpu_map_idx = evsel__hybrid_group_cpu_map_idx(evsel, cpu_map_idx); if (cpu_map_idx == -1) return -1; fd = FD(leader, cpu_map_idx, thread); BUG_ON(fd == -1 && !leader->skippable); /* * When the leader has been skipped, return -2 to distinguish from no * group leader case. */ return fd == -1 ? -2 : fd; } static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int thread_idx) { for (int cpu = 0; cpu < nr_cpus; cpu++) for (int thread = thread_idx; thread < nr_threads - 1; thread++) FD(pos, cpu, thread) = FD(pos, cpu, thread + 1); } static int update_fds(struct evsel *evsel, int nr_cpus, int cpu_map_idx, int nr_threads, int thread_idx) { struct evsel *pos; if (cpu_map_idx >= nr_cpus || thread_idx >= nr_threads) return -EINVAL; evlist__for_each_entry(evsel->evlist, pos) { nr_cpus = pos != evsel ? nr_cpus : cpu_map_idx; evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx); /* * Since fds for next evsel has not been created, * there is no need to iterate whole event list. */ if (pos == evsel) break; } return 0; } static bool evsel__ignore_missing_thread(struct evsel *evsel, int nr_cpus, int cpu_map_idx, struct perf_thread_map *threads, int thread, int err) { pid_t ignore_pid = perf_thread_map__pid(threads, thread); if (!evsel->ignore_missing_thread) return false; /* The system wide setup does not work with threads. */ if (evsel->core.system_wide) return false; /* The -ESRCH is perf event syscall errno for pid's not found. */ if (err != -ESRCH) return false; /* If there's only one thread, let it fail. */ if (threads->nr == 1) return false; /* * We should remove fd for missing_thread first * because thread_map__remove() will decrease threads->nr. */ if (update_fds(evsel, nr_cpus, cpu_map_idx, threads->nr, thread)) return false; if (thread_map__remove(threads, thread)) return false; pr_warning("WARNING: Ignored open failure for pid %d\n", ignore_pid); return true; } static int __open_attr__fprintf(FILE *fp, const char *name, const char *val, void *priv __maybe_unused) { return fprintf(fp, " %-32s %s\n", name, val); } static void display_attr(struct perf_event_attr *attr) { if (verbose >= 2 || debug_peo_args) { fprintf(stderr, "%.60s\n", graph_dotted_line); fprintf(stderr, "perf_event_attr:\n"); perf_event_attr__fprintf(stderr, attr, __open_attr__fprintf, NULL); fprintf(stderr, "%.60s\n", graph_dotted_line); } } bool evsel__precise_ip_fallback(struct evsel *evsel) { /* Do not try less precise if not requested. */ if (!evsel->precise_max) return false; /* * We tried all the precise_ip values, and it's * still failing, so leave it to standard fallback. */ if (!evsel->core.attr.precise_ip) { evsel->core.attr.precise_ip = evsel->precise_ip_original; return false; } if (!evsel->precise_ip_original) evsel->precise_ip_original = evsel->core.attr.precise_ip; evsel->core.attr.precise_ip--; pr_debug2_peo("decreasing precise_ip by one (%d)\n", evsel->core.attr.precise_ip); display_attr(&evsel->core.attr); return true; } static struct perf_cpu_map *empty_cpu_map; static struct perf_thread_map *empty_thread_map; static int __evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads) { int nthreads = perf_thread_map__nr(threads); if ((perf_missing_features.write_backward && evsel->core.attr.write_backward) || (perf_missing_features.aux_output && evsel->core.attr.aux_output)) return -EINVAL; if (cpus == NULL) { if (empty_cpu_map == NULL) { empty_cpu_map = perf_cpu_map__new_any_cpu(); if (empty_cpu_map == NULL) return -ENOMEM; } cpus = empty_cpu_map; } if (threads == NULL) { if (empty_thread_map == NULL) { empty_thread_map = thread_map__new_by_tid(-1); if (empty_thread_map == NULL) return -ENOMEM; } threads = empty_thread_map; } if (evsel->core.fd == NULL && perf_evsel__alloc_fd(&evsel->core, perf_cpu_map__nr(cpus), nthreads) < 0) return -ENOMEM; if ((evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME || evsel__tool_event(evsel) == PERF_TOOL_USER_TIME) && !evsel->start_times) { evsel->start_times = xyarray__new(perf_cpu_map__nr(cpus), nthreads, sizeof(__u64)); if (!evsel->start_times) return -ENOMEM; } evsel->open_flags = PERF_FLAG_FD_CLOEXEC; if (evsel->cgrp) evsel->open_flags |= PERF_FLAG_PID_CGROUP; return 0; } static void evsel__disable_missing_features(struct evsel *evsel) { if (perf_missing_features.branch_counters) evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_COUNTERS; if (perf_missing_features.read_lost) evsel->core.attr.read_format &= ~PERF_FORMAT_LOST; if (perf_missing_features.weight_struct) { evsel__set_sample_bit(evsel, WEIGHT); evsel__reset_sample_bit(evsel, WEIGHT_STRUCT); } if (perf_missing_features.clockid_wrong) evsel->core.attr.clockid = CLOCK_MONOTONIC; /* should always work */ if (perf_missing_features.clockid) { evsel->core.attr.use_clockid = 0; evsel->core.attr.clockid = 0; } if (perf_missing_features.cloexec) evsel->open_flags &= ~(unsigned long)PERF_FLAG_FD_CLOEXEC; if (perf_missing_features.mmap2) evsel->core.attr.mmap2 = 0; if (evsel->pmu && evsel->pmu->missing_features.exclude_guest) evsel->core.attr.exclude_guest = evsel->core.attr.exclude_host = 0; if (perf_missing_features.lbr_flags) evsel->core.attr.branch_sample_type &= ~(PERF_SAMPLE_BRANCH_NO_FLAGS | PERF_SAMPLE_BRANCH_NO_CYCLES); if (perf_missing_features.group_read && evsel->core.attr.inherit) evsel->core.attr.read_format &= ~(PERF_FORMAT_GROUP|PERF_FORMAT_ID); if (perf_missing_features.ksymbol) evsel->core.attr.ksymbol = 0; if (perf_missing_features.bpf) evsel->core.attr.bpf_event = 0; if (perf_missing_features.branch_hw_idx) evsel->core.attr.branch_sample_type &= ~PERF_SAMPLE_BRANCH_HW_INDEX; if (perf_missing_features.sample_id_all) evsel->core.attr.sample_id_all = 0; } int evsel__prepare_open(struct evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads) { int err; err = __evsel__prepare_open(evsel, cpus, threads); if (err) return err; evsel__disable_missing_features(evsel); return err; } bool evsel__detect_missing_features(struct evsel *evsel) { /* * Must probe features in the order they were added to the * perf_event_attr interface. */ if (!perf_missing_features.branch_counters && (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_COUNTERS)) { perf_missing_features.branch_counters = true; pr_debug2("switching off branch counters support\n"); return true; } else if (!perf_missing_features.read_lost && (evsel->core.attr.read_format & PERF_FORMAT_LOST)) { perf_missing_features.read_lost = true; pr_debug2("switching off PERF_FORMAT_LOST support\n"); return true; } else if (!perf_missing_features.weight_struct && (evsel->core.attr.sample_type & PERF_SAMPLE_WEIGHT_STRUCT)) { perf_missing_features.weight_struct = true; pr_debug2("switching off weight struct support\n"); return true; } else if (!perf_missing_features.code_page_size && (evsel->core.attr.sample_type & PERF_SAMPLE_CODE_PAGE_SIZE)) { perf_missing_features.code_page_size = true; pr_debug2_peo("Kernel has no PERF_SAMPLE_CODE_PAGE_SIZE support, bailing out\n"); return false; } else if (!perf_missing_features.data_page_size && (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE)) { perf_missing_features.data_page_size = true; pr_debug2_peo("Kernel has no PERF_SAMPLE_DATA_PAGE_SIZE support, bailing out\n"); return false; } else if (!perf_missing_features.cgroup && evsel->core.attr.cgroup) { perf_missing_features.cgroup = true; pr_debug2_peo("Kernel has no cgroup sampling support, bailing out\n"); return false; } else if (!perf_missing_features.branch_hw_idx && (evsel->core.attr.branch_sample_type & PERF_SAMPLE_BRANCH_HW_INDEX)) { perf_missing_features.branch_hw_idx = true; pr_debug2("switching off branch HW index support\n"); return true; } else if (!perf_missing_features.aux_output && evsel->core.attr.aux_output) { perf_missing_features.aux_output = true; pr_debug2_peo("Kernel has no attr.aux_output support, bailing out\n"); return false; } else if (!perf_missing_features.bpf && evsel->core.attr.bpf_event) { perf_missing_features.bpf = true; pr_debug2_peo("switching off bpf_event\n"); return true; } else if (!perf_missing_features.ksymbol && evsel->core.attr.ksymbol) { perf_missing_features.ksymbol = true; pr_debug2_peo("switching off ksymbol\n"); return true; } else if (!perf_missing_features.write_backward && evsel->core.attr.write_backward) { perf_missing_features.write_backward = true; pr_debug2_peo("switching off write_backward\n"); return false; } else if (!perf_missing_features.clockid_wrong && evsel->core.attr.use_clockid) { perf_missing_features.clockid_wrong = true; pr_debug2_peo("switching off clockid\n"); return true; } else if (!perf_missing_features.clockid && evsel->core.attr.use_clockid) { perf_missing_features.clockid = true; pr_debug2_peo("switching off use_clockid\n"); return true; } else if (!perf_missing_features.cloexec && (evsel->open_flags & PERF_FLAG_FD_CLOEXEC)) { perf_missing_features.cloexec = true; pr_debug2_peo("switching off cloexec flag\n"); return true; } else if (!perf_missing_features.mmap2 && evsel->core.attr.mmap2) { perf_missing_features.mmap2 = true; pr_debug2_peo("switching off mmap2\n"); return true; } else if (evsel->core.attr.exclude_guest || evsel->core.attr.exclude_host) { if (evsel->pmu == NULL) evsel->pmu = evsel__find_pmu(evsel); if (evsel->pmu) evsel->pmu->missing_features.exclude_guest = true; else { /* we cannot find PMU, disable attrs now */ evsel->core.attr.exclude_host = false; evsel->core.attr.exclude_guest = false; } if (evsel->exclude_GH) { pr_debug2_peo("PMU has no exclude_host/guest support, bailing out\n"); return false; } if (!perf_missing_features.exclude_guest) { perf_missing_features.exclude_guest = true; pr_debug2_peo("switching off exclude_guest, exclude_host\n"); } return true; } else if (!perf_missing_features.sample_id_all) { perf_missing_features.sample_id_all = true; pr_debug2_peo("switching off sample_id_all\n"); return true; } else if (!perf_missing_features.lbr_flags && (evsel->core.attr.branch_sample_type & (PERF_SAMPLE_BRANCH_NO_CYCLES | PERF_SAMPLE_BRANCH_NO_FLAGS))) { perf_missing_features.lbr_flags = true; pr_debug2_peo("switching off branch sample type no (cycles/flags)\n"); return true; } else if (!perf_missing_features.group_read && evsel->core.attr.inherit && (evsel->core.attr.read_format & PERF_FORMAT_GROUP) && evsel__is_group_leader(evsel)) { perf_missing_features.group_read = true; pr_debug2_peo("switching off group read\n"); return true; } else { return false; } } static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads, int start_cpu_map_idx, int end_cpu_map_idx) { int idx, thread, nthreads; int pid = -1, err, old_errno; enum rlimit_action set_rlimit = NO_CHANGE; if (evsel__tool_event(evsel) == PERF_TOOL_DURATION_TIME) { if (evsel->core.attr.sample_period) /* no sampling */ return -EINVAL; evsel->start_time = rdclock(); return 0; } if (evsel__is_retire_lat(evsel)) return tpebs_start(evsel->evlist); err = __evsel__prepare_open(evsel, cpus, threads); if (err) return err; if (cpus == NULL) cpus = empty_cpu_map; if (threads == NULL) threads = empty_thread_map; nthreads = perf_thread_map__nr(threads); if (evsel->cgrp) pid = evsel->cgrp->fd; fallback_missing_features: evsel__disable_missing_features(evsel); pr_debug3("Opening: %s\n", evsel__name(evsel)); display_attr(&evsel->core.attr); for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) { for (thread = 0; thread < nthreads; thread++) { int fd, group_fd; retry_open: if (thread >= nthreads) break; if (!evsel->cgrp && !evsel->core.system_wide) pid = perf_thread_map__pid(threads, thread); if (evsel__tool_event(evsel) == PERF_TOOL_USER_TIME || evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME) { bool system = evsel__tool_event(evsel) == PERF_TOOL_SYSTEM_TIME; __u64 *start_time = NULL; if (evsel->core.attr.sample_period) { /* no sampling */ err = -EINVAL; goto out_close; } if (pid > -1) { char buf[64]; snprintf(buf, sizeof(buf), "/proc/%d/stat", pid); fd = open(buf, O_RDONLY); evsel->pid_stat = true; } else { fd = open("/proc/stat", O_RDONLY); } FD(evsel, idx, thread) = fd; if (fd < 0) { err = -errno; goto out_close; } start_time = xyarray__entry(evsel->start_times, idx, thread); if (pid > -1) { err = read_pid_stat_field(fd, system ? 15 : 14, start_time); } else { struct perf_cpu cpu; cpu = perf_cpu_map__cpu(evsel->core.cpus, idx); err = read_stat_field(fd, cpu, system ? 3 : 1, start_time); } if (err) goto out_close; continue; } group_fd = get_group_fd(evsel, idx, thread); if (group_fd == -2) { pr_debug("broken group leader for %s\n", evsel->name); err = -EINVAL; goto out_close; } test_attr__ready(); /* Debug message used by test scripts */ pr_debug2_peo("sys_perf_event_open: pid %d cpu %d group_fd %d flags %#lx", pid, perf_cpu_map__cpu(cpus, idx).cpu, group_fd, evsel->open_flags); fd = sys_perf_event_open(&evsel->core.attr, pid, perf_cpu_map__cpu(cpus, idx).cpu, group_fd, evsel->open_flags); FD(evsel, idx, thread) = fd; if (fd < 0) { err = -errno; pr_debug2_peo("\nsys_perf_event_open failed, error %d\n", err); goto try_fallback; } bpf_counter__install_pe(evsel, idx, fd); if (unlikely(test_attr__enabled)) { test_attr__open(&evsel->core.attr, pid, perf_cpu_map__cpu(cpus, idx), fd, group_fd, evsel->open_flags); } /* Debug message used by test scripts */ pr_debug2_peo(" = %d\n", fd); if (evsel->bpf_fd >= 0) { int evt_fd = fd; int bpf_fd = evsel->bpf_fd; err = ioctl(evt_fd, PERF_EVENT_IOC_SET_BPF, bpf_fd); if (err && errno != EEXIST) { pr_err("failed to attach bpf fd %d: %s\n", bpf_fd, strerror(errno)); err = -EINVAL; goto out_close; } } set_rlimit = NO_CHANGE; /* * If we succeeded but had to kill clockid, fail and * have evsel__open_strerror() print us a nice error. */ if (perf_missing_features.clockid || perf_missing_features.clockid_wrong) { err = -EINVAL; goto out_close; } } } return 0; try_fallback: if (evsel__precise_ip_fallback(evsel)) goto retry_open; if (evsel__ignore_missing_thread(evsel, perf_cpu_map__nr(cpus), idx, threads, thread, err)) { /* We just removed 1 thread, so lower the upper nthreads limit. */ nthreads--; /* ... and pretend like nothing have happened. */ err = 0; goto retry_open; } /* * perf stat needs between 5 and 22 fds per CPU. When we run out * of them try to increase the limits. */ if (err == -EMFILE && rlimit__increase_nofile(&set_rlimit)) goto retry_open; if (err != -EINVAL || idx > 0 || thread > 0) goto out_close; if (evsel__detect_missing_features(evsel)) goto fallback_missing_features; out_close: if (err) threads->err_thread = thread; old_errno = errno; do { while (--thread >= 0) { if (FD(evsel, idx, thread) >= 0) close(FD(evsel, idx, thread)); FD(evsel, idx, thread) = -1; } thread = nthreads; } while (--idx >= 0); errno = old_errno; return err; } int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus, struct perf_thread_map *threads) { return evsel__open_cpu(evsel, cpus, threads, 0, perf_cpu_map__nr(cpus)); } void evsel__close(struct evsel *evsel) { if (evsel__is_retire_lat(evsel)) tpebs_delete(); perf_evsel__close(&evsel->core); perf_evsel__free_id(&evsel->core); } int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx) { if (cpu_map_idx == -1) return evsel__open_cpu(evsel, cpus, NULL, 0, perf_cpu_map__nr(cpus)); return evsel__open_cpu(evsel, cpus, NULL, cpu_map_idx, cpu_map_idx + 1); } int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads) { return evsel__open(evsel, NULL, threads); } static int perf_evsel__parse_id_sample(const struct evsel *evsel, const union perf_event *event, struct perf_sample *sample) { u64 type = evsel->core.attr.sample_type; const __u64 *array = event->sample.array; bool swapped = evsel->needs_swap; union u64_swap u; array += ((event->header.size - sizeof(event->header)) / sizeof(u64)) - 1; if (type & PERF_SAMPLE_IDENTIFIER) { sample->id = *array; array--; } if (type & PERF_SAMPLE_CPU) { u.val64 = *array; if (swapped) { /* undo swap of u64, then swap on individual u32s */ u.val64 = bswap_64(u.val64); u.val32[0] = bswap_32(u.val32[0]); } sample->cpu = u.val32[0]; array--; } if (type & PERF_SAMPLE_STREAM_ID) { sample->stream_id = *array; array--; } if (type & PERF_SAMPLE_ID) { sample->id = *array; array--; } if (type & PERF_SAMPLE_TIME) { sample->time = *array; array--; } if (type & PERF_SAMPLE_TID) { u.val64 = *array; if (swapped) { /* undo swap of u64, then swap on individual u32s */ u.val64 = bswap_64(u.val64); u.val32[0] = bswap_32(u.val32[0]); u.val32[1] = bswap_32(u.val32[1]); } sample->pid = u.val32[0]; sample->tid = u.val32[1]; array--; } return 0; } static inline bool overflow(const void *endp, u16 max_size, const void *offset, u64 size) { return size > max_size || offset + size > endp; } #define OVERFLOW_CHECK(offset, size, max_size) \ do { \ if (overflow(endp, (max_size), (offset), (size))) \ return -EFAULT; \ } while (0) #define OVERFLOW_CHECK_u64(offset) \ OVERFLOW_CHECK(offset, sizeof(u64), sizeof(u64)) static int perf_event__check_size(union perf_event *event, unsigned int sample_size) { /* * The evsel's sample_size is based on PERF_SAMPLE_MASK which includes * up to PERF_SAMPLE_PERIOD. After that overflow() must be used to * check the format does not go past the end of the event. */ if (sample_size + sizeof(event->header) > event->header.size) return -EFAULT; return 0; } void __weak arch_perf_parse_sample_weight(struct perf_sample *data, const __u64 *array, u64 type __maybe_unused) { data->weight = *array; } u64 evsel__bitfield_swap_branch_flags(u64 value) { u64 new_val = 0; /* * branch_flags * union { * u64 values; * struct { * mispred:1 //target mispredicted * predicted:1 //target predicted * in_tx:1 //in transaction * abort:1 //transaction abort * cycles:16 //cycle count to last branch * type:4 //branch type * spec:2 //branch speculation info * new_type:4 //additional branch type * priv:3 //privilege level * reserved:31 * } * } * * Avoid bswap64() the entire branch_flag.value, * as it has variable bit-field sizes. Instead the * macro takes the bit-field position/size, * swaps it based on the host endianness. */ if (host_is_bigendian()) { new_val = bitfield_swap(value, 0, 1); new_val |= bitfield_swap(value, 1, 1); new_val |= bitfield_swap(value, 2, 1); new_val |= bitfield_swap(value, 3, 1); new_val |= bitfield_swap(value, 4, 16); new_val |= bitfield_swap(value, 20, 4); new_val |= bitfield_swap(value, 24, 2); new_val |= bitfield_swap(value, 26, 4); new_val |= bitfield_swap(value, 30, 3); new_val |= bitfield_swap(value, 33, 31); } else { new_val = bitfield_swap(value, 63, 1); new_val |= bitfield_swap(value, 62, 1); new_val |= bitfield_swap(value, 61, 1); new_val |= bitfield_swap(value, 60, 1); new_val |= bitfield_swap(value, 44, 16); new_val |= bitfield_swap(value, 40, 4); new_val |= bitfield_swap(value, 38, 2); new_val |= bitfield_swap(value, 34, 4); new_val |= bitfield_swap(value, 31, 3); new_val |= bitfield_swap(value, 0, 31); } return new_val; } static inline bool evsel__has_branch_counters(const struct evsel *evsel) { struct evsel *leader = evsel__leader(evsel); /* The branch counters feature only supports group */ if (!leader || !evsel->evlist) return false; if (evsel->evlist->nr_br_cntr < 0) evlist__update_br_cntr(evsel->evlist); if (leader->br_cntr_nr > 0) return true; return false; } int evsel__parse_sample(struct evsel *evsel, union perf_event *event, struct perf_sample *data) { u64 type = evsel->core.attr.sample_type; bool swapped = evsel->needs_swap; const __u64 *array; u16 max_size = event->header.size; const void *endp = (void *)event + max_size; u64 sz; /* * used for cross-endian analysis. See git commit 65014ab3 * for why this goofiness is needed. */ union u64_swap u; memset(data, 0, sizeof(*data)); data->cpu = data->pid = data->tid = -1; data->stream_id = data->id = data->time = -1ULL; data->period = evsel->core.attr.sample_period; data->cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK; data->misc = event->header.misc; data->data_src = PERF_MEM_DATA_SRC_NONE; data->vcpu = -1; if (event->header.type != PERF_RECORD_SAMPLE) { if (!evsel->core.attr.sample_id_all) return 0; return perf_evsel__parse_id_sample(evsel, event, data); } array = event->sample.array; if (perf_event__check_size(event, evsel->sample_size)) return -EFAULT; if (type & PERF_SAMPLE_IDENTIFIER) { data->id = *array; array++; } if (type & PERF_SAMPLE_IP) { data->ip = *array; array++; } if (type & PERF_SAMPLE_TID) { u.val64 = *array; if (swapped) { /* undo swap of u64, then swap on individual u32s */ u.val64 = bswap_64(u.val64); u.val32[0] = bswap_32(u.val32[0]); u.val32[1] = bswap_32(u.val32[1]); } data->pid = u.val32[0]; data->tid = u.val32[1]; array++; } if (type & PERF_SAMPLE_TIME) { data->time = *array; array++; } if (type & PERF_SAMPLE_ADDR) { data->addr = *array; array++; } if (type & PERF_SAMPLE_ID) { data->id = *array; array++; } if (type & PERF_SAMPLE_STREAM_ID) { data->stream_id = *array; array++; } if (type & PERF_SAMPLE_CPU) { u.val64 = *array; if (swapped) { /* undo swap of u64, then swap on individual u32s */ u.val64 = bswap_64(u.val64); u.val32[0] = bswap_32(u.val32[0]); } data->cpu = u.val32[0]; array++; } if (type & PERF_SAMPLE_PERIOD) { data->period = *array; array++; } if (type & PERF_SAMPLE_READ) { u64 read_format = evsel->core.attr.read_format; OVERFLOW_CHECK_u64(array); if (read_format & PERF_FORMAT_GROUP) data->read.group.nr = *array; else data->read.one.value = *array; array++; if (read_format & PERF_FORMAT_TOTAL_TIME_ENABLED) { OVERFLOW_CHECK_u64(array); data->read.time_enabled = *array; array++; } if (read_format & PERF_FORMAT_TOTAL_TIME_RUNNING) { OVERFLOW_CHECK_u64(array); data->read.time_running = *array; array++; } /* PERF_FORMAT_ID is forced for PERF_SAMPLE_READ */ if (read_format & PERF_FORMAT_GROUP) { const u64 max_group_nr = UINT64_MAX / sizeof(struct sample_read_value); if (data->read.group.nr > max_group_nr) return -EFAULT; sz = data->read.group.nr * sample_read_value_size(read_format); OVERFLOW_CHECK(array, sz, max_size); data->read.group.values = (struct sample_read_value *)array; array = (void *)array + sz; } else { OVERFLOW_CHECK_u64(array); data->read.one.id = *array; array++; if (read_format & PERF_FORMAT_LOST) { OVERFLOW_CHECK_u64(array); data->read.one.lost = *array; array++; } } } if (type & PERF_SAMPLE_CALLCHAIN) { const u64 max_callchain_nr = UINT64_MAX / sizeof(u64); OVERFLOW_CHECK_u64(array); data->callchain = (struct ip_callchain *)array++; if (data->callchain->nr > max_callchain_nr) return -EFAULT; sz = data->callchain->nr * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); array = (void *)array + sz; } if (type & PERF_SAMPLE_RAW) { OVERFLOW_CHECK_u64(array); u.val64 = *array; /* * Undo swap of u64, then swap on individual u32s, * get the size of the raw area and undo all of the * swap. The pevent interface handles endianness by * itself. */ if (swapped) { u.val64 = bswap_64(u.val64); u.val32[0] = bswap_32(u.val32[0]); u.val32[1] = bswap_32(u.val32[1]); } data->raw_size = u.val32[0]; /* * The raw data is aligned on 64bits including the * u32 size, so it's safe to use mem_bswap_64. */ if (swapped) mem_bswap_64((void *) array, data->raw_size); array = (void *)array + sizeof(u32); OVERFLOW_CHECK(array, data->raw_size, max_size); data->raw_data = (void *)array; array = (void *)array + data->raw_size; } if (type & PERF_SAMPLE_BRANCH_STACK) { const u64 max_branch_nr = UINT64_MAX / sizeof(struct branch_entry); struct branch_entry *e; unsigned int i; OVERFLOW_CHECK_u64(array); data->branch_stack = (struct branch_stack *)array++; if (data->branch_stack->nr > max_branch_nr) return -EFAULT; sz = data->branch_stack->nr * sizeof(struct branch_entry); if (evsel__has_branch_hw_idx(evsel)) { sz += sizeof(u64); e = &data->branch_stack->entries[0]; } else { data->no_hw_idx = true; /* * if the PERF_SAMPLE_BRANCH_HW_INDEX is not applied, * only nr and entries[] will be output by kernel. */ e = (struct branch_entry *)&data->branch_stack->hw_idx; } if (swapped) { /* * struct branch_flag does not have endian * specific bit field definition. And bswap * will not resolve the issue, since these * are bit fields. * * evsel__bitfield_swap_branch_flags() uses a * bitfield_swap macro to swap the bit position * based on the host endians. */ for (i = 0; i < data->branch_stack->nr; i++, e++) e->flags.value = evsel__bitfield_swap_branch_flags(e->flags.value); } OVERFLOW_CHECK(array, sz, max_size); array = (void *)array + sz; if (evsel__has_branch_counters(evsel)) { data->branch_stack_cntr = (u64 *)array; sz = data->branch_stack->nr * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); array = (void *)array + sz; } } if (type & PERF_SAMPLE_REGS_USER) { OVERFLOW_CHECK_u64(array); data->user_regs.abi = *array; array++; if (data->user_regs.abi) { u64 mask = evsel->core.attr.sample_regs_user; sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); data->user_regs.mask = mask; data->user_regs.regs = (u64 *)array; array = (void *)array + sz; } } if (type & PERF_SAMPLE_STACK_USER) { OVERFLOW_CHECK_u64(array); sz = *array++; data->user_stack.offset = ((char *)(array - 1) - (char *) event); if (!sz) { data->user_stack.size = 0; } else { OVERFLOW_CHECK(array, sz, max_size); data->user_stack.data = (char *)array; array = (void *)array + sz; OVERFLOW_CHECK_u64(array); data->user_stack.size = *array++; if (WARN_ONCE(data->user_stack.size > sz, "user stack dump failure\n")) return -EFAULT; } } if (type & PERF_SAMPLE_WEIGHT_TYPE) { OVERFLOW_CHECK_u64(array); arch_perf_parse_sample_weight(data, array, type); array++; } if (type & PERF_SAMPLE_DATA_SRC) { OVERFLOW_CHECK_u64(array); data->data_src = *array; array++; } if (type & PERF_SAMPLE_TRANSACTION) { OVERFLOW_CHECK_u64(array); data->transaction = *array; array++; } data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE; if (type & PERF_SAMPLE_REGS_INTR) { OVERFLOW_CHECK_u64(array); data->intr_regs.abi = *array; array++; if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) { u64 mask = evsel->core.attr.sample_regs_intr; sz = hweight64(mask) * sizeof(u64); OVERFLOW_CHECK(array, sz, max_size); data->intr_regs.mask = mask; data->intr_regs.regs = (u64 *)array; array = (void *)array + sz; } } data->phys_addr = 0; if (type & PERF_SAMPLE_PHYS_ADDR) { data->phys_addr = *array; array++; } data->cgroup = 0; if (type & PERF_SAMPLE_CGROUP) { data->cgroup = *array; array++; } data->data_page_size = 0; if (type & PERF_SAMPLE_DATA_PAGE_SIZE) { data->data_page_size = *array; array++; } data->code_page_size = 0; if (type & PERF_SAMPLE_CODE_PAGE_SIZE) { data->code_page_size = *array; array++; } if (type & PERF_SAMPLE_AUX) { OVERFLOW_CHECK_u64(array); sz = *array++; OVERFLOW_CHECK(array, sz, max_size); /* Undo swap of data */ if (swapped) mem_bswap_64((char *)array, sz); data->aux_sample.size = sz; data->aux_sample.data = (char *)array; array = (void *)array + sz; } return 0; } int evsel__parse_sample_timestamp(struct evsel *evsel, union perf_event *event, u64 *timestamp) { u64 type = evsel->core.attr.sample_type; const __u64 *array; if (!(type & PERF_SAMPLE_TIME)) return -1; if (event->header.type != PERF_RECORD_SAMPLE) { struct perf_sample data = { .time = -1ULL, }; if (!evsel->core.attr.sample_id_all) return -1; if (perf_evsel__parse_id_sample(evsel, event, &data)) return -1; *timestamp = data.time; return 0; } array = event->sample.array; if (perf_event__check_size(event, evsel->sample_size)) return -EFAULT; if (type & PERF_SAMPLE_IDENTIFIER) array++; if (type & PERF_SAMPLE_IP) array++; if (type & PERF_SAMPLE_TID) array++; if (type & PERF_SAMPLE_TIME) *timestamp = *array; return 0; } u16 evsel__id_hdr_size(const struct evsel *evsel) { u64 sample_type = evsel->core.attr.sample_type; u16 size = 0; if (sample_type & PERF_SAMPLE_TID) size += sizeof(u64); if (sample_type & PERF_SAMPLE_TIME) size += sizeof(u64); if (sample_type & PERF_SAMPLE_ID) size += sizeof(u64); if (sample_type & PERF_SAMPLE_STREAM_ID) size += sizeof(u64); if (sample_type & PERF_SAMPLE_CPU) size += sizeof(u64); if (sample_type & PERF_SAMPLE_IDENTIFIER) size += sizeof(u64); return size; } #ifdef HAVE_LIBTRACEEVENT struct tep_format_field *evsel__field(struct evsel *evsel, const char *name) { return tep_find_field(evsel->tp_format, name); } struct tep_format_field *evsel__common_field(struct evsel *evsel, const char *name) { return tep_find_common_field(evsel->tp_format, name); } void *evsel__rawptr(struct evsel *evsel, struct perf_sample *sample, const char *name) { struct tep_format_field *field = evsel__field(evsel, name); int offset; if (!field) return NULL; offset = field->offset; if (field->flags & TEP_FIELD_IS_DYNAMIC) { offset = *(int *)(sample->raw_data + field->offset); offset &= 0xffff; if (tep_field_is_relative(field->flags)) offset += field->offset + field->size; } return sample->raw_data + offset; } u64 format_field__intval(struct tep_format_field *field, struct perf_sample *sample, bool needs_swap) { u64 value; void *ptr = sample->raw_data + field->offset; switch (field->size) { case 1: return *(u8 *)ptr; case 2: value = *(u16 *)ptr; break; case 4: value = *(u32 *)ptr; break; case 8: memcpy(&value, ptr, sizeof(u64)); break; default: return 0; } if (!needs_swap) return value; switch (field->size) { case 2: return bswap_16(value); case 4: return bswap_32(value); case 8: return bswap_64(value); default: return 0; } return 0; } u64 evsel__intval(struct evsel *evsel, struct perf_sample *sample, const char *name) { struct tep_format_field *field = evsel__field(evsel, name); return field ? format_field__intval(field, sample, evsel->needs_swap) : 0; } u64 evsel__intval_common(struct evsel *evsel, struct perf_sample *sample, const char *name) { struct tep_format_field *field = evsel__common_field(evsel, name); return field ? format_field__intval(field, sample, evsel->needs_swap) : 0; } char evsel__taskstate(struct evsel *evsel, struct perf_sample *sample, const char *name) { static struct tep_format_field *prev_state_field; static const char *states; struct tep_format_field *field; unsigned long long val; unsigned int bit; char state = '?'; /* '?' denotes unknown task state */ field = evsel__field(evsel, name); if (!field) return state; if (!states || field != prev_state_field) { states = parse_task_states(field); if (!states) return state; prev_state_field = field; } /* * Note since the kernel exposes TASK_REPORT_MAX to userspace * to denote the 'preempted' state, we might as welll report * 'R' for this case, which make senses to users as well. * * We can change this if we have a good reason in the future. */ val = evsel__intval(evsel, sample, name); bit = val ? ffs(val) : 0; state = (!bit || bit > strlen(states)) ? 'R' : states[bit-1]; return state; } #endif bool evsel__fallback(struct evsel *evsel, struct target *target, int err, char *msg, size_t msgsize) { int paranoid; if ((err == ENOENT || err == ENXIO || err == ENODEV) && evsel->core.attr.type == PERF_TYPE_HARDWARE && evsel->core.attr.config == PERF_COUNT_HW_CPU_CYCLES) { /* * If it's cycles then fall back to hrtimer based cpu-clock sw * counter, which is always available even if no PMU support. * * PPC returns ENXIO until 2.6.37 (behavior changed with commit * b0a873e). */ evsel->core.attr.type = PERF_TYPE_SOFTWARE; evsel->core.attr.config = target__has_cpu(target) ? PERF_COUNT_SW_CPU_CLOCK : PERF_COUNT_SW_TASK_CLOCK; scnprintf(msg, msgsize, "The cycles event is not supported, trying to fall back to %s", target__has_cpu(target) ? "cpu-clock" : "task-clock"); zfree(&evsel->name); return true; } else if (err == EACCES && !evsel->core.attr.exclude_kernel && (paranoid = perf_event_paranoid()) > 1) { const char *name = evsel__name(evsel); char *new_name; const char *sep = ":"; /* If event has exclude user then don't exclude kernel. */ if (evsel->core.attr.exclude_user) return false; /* Is there already the separator in the name. */ if (strchr(name, '/') || (strchr(name, ':') && !evsel->is_libpfm_event)) sep = ""; if (asprintf(&new_name, "%s%su", name, sep) < 0) return false; free(evsel->name); evsel->name = new_name; scnprintf(msg, msgsize, "kernel.perf_event_paranoid=%d, trying " "to fall back to excluding kernel and hypervisor " " samples", paranoid); evsel->core.attr.exclude_kernel = 1; evsel->core.attr.exclude_hv = 1; return true; } return false; } static bool find_process(const char *name) { size_t len = strlen(name); DIR *dir; struct dirent *d; int ret = -1; dir = opendir(procfs__mountpoint()); if (!dir) return false; /* Walk through the directory. */ while (ret && (d = readdir(dir)) != NULL) { char path[PATH_MAX]; char *data; size_t size; if ((d->d_type != DT_DIR) || !strcmp(".", d->d_name) || !strcmp("..", d->d_name)) continue; scnprintf(path, sizeof(path), "%s/%s/comm", procfs__mountpoint(), d->d_name); if (filename__read_str(path, &data, &size)) continue; ret = strncmp(name, data, len); free(data); } closedir(dir); return ret ? false : true; } int __weak arch_evsel__open_strerror(struct evsel *evsel __maybe_unused, char *msg __maybe_unused, size_t size __maybe_unused) { return 0; } int evsel__open_strerror(struct evsel *evsel, struct target *target, int err, char *msg, size_t size) { char sbuf[STRERR_BUFSIZE]; int printed = 0, enforced = 0; int ret; switch (err) { case EPERM: case EACCES: printed += scnprintf(msg + printed, size - printed, "Access to performance monitoring and observability operations is limited.\n"); if (!sysfs__read_int("fs/selinux/enforce", &enforced)) { if (enforced) { printed += scnprintf(msg + printed, size - printed, "Enforced MAC policy settings (SELinux) can limit access to performance\n" "monitoring and observability operations. Inspect system audit records for\n" "more perf_event access control information and adjusting the policy.\n"); } } if (err == EPERM) printed += scnprintf(msg, size, "No permission to enable %s event.\n\n", evsel__name(evsel)); return scnprintf(msg + printed, size - printed, "Consider adjusting /proc/sys/kernel/perf_event_paranoid setting to open\n" "access to performance monitoring and observability operations for processes\n" "without CAP_PERFMON, CAP_SYS_PTRACE or CAP_SYS_ADMIN Linux capability.\n" "More information can be found at 'Perf events and tool security' document:\n" "https://www.kernel.org/doc/html/latest/admin-guide/perf-security.html\n" "perf_event_paranoid setting is %d:\n" " -1: Allow use of (almost) all events by all users\n" " Ignore mlock limit after perf_event_mlock_kb without CAP_IPC_LOCK\n" ">= 0: Disallow raw and ftrace function tracepoint access\n" ">= 1: Disallow CPU event access\n" ">= 2: Disallow kernel profiling\n" "To make the adjusted perf_event_paranoid setting permanent preserve it\n" "in /etc/sysctl.conf (e.g. kernel.perf_event_paranoid = <setting>)", perf_event_paranoid()); case ENOENT: return scnprintf(msg, size, "The %s event is not supported.", evsel__name(evsel)); case EMFILE: return scnprintf(msg, size, "%s", "Too many events are opened.\n" "Probably the maximum number of open file descriptors has been reached.\n" "Hint: Try again after reducing the number of events.\n" "Hint: Try increasing the limit with 'ulimit -n <limit>'"); case ENOMEM: if (evsel__has_callchain(evsel) && access("/proc/sys/kernel/perf_event_max_stack", F_OK) == 0) return scnprintf(msg, size, "Not enough memory to setup event with callchain.\n" "Hint: Try tweaking /proc/sys/kernel/perf_event_max_stack\n" "Hint: Current value: %d", sysctl__max_stack()); break; case ENODEV: if (target->cpu_list) return scnprintf(msg, size, "%s", "No such device - did you specify an out-of-range profile CPU?"); break; case EOPNOTSUPP: if (evsel->core.attr.sample_type & PERF_SAMPLE_BRANCH_STACK) return scnprintf(msg, size, "%s: PMU Hardware or event type doesn't support branch stack sampling.", evsel__name(evsel)); if (evsel->core.attr.aux_output) return scnprintf(msg, size, "%s: PMU Hardware doesn't support 'aux_output' feature", evsel__name(evsel)); if (evsel->core.attr.sample_period != 0) return scnprintf(msg, size, "%s: PMU Hardware doesn't support sampling/overflow-interrupts. Try 'perf stat'", evsel__name(evsel)); if (evsel->core.attr.precise_ip) return scnprintf(msg, size, "%s", "\'precise\' request may not be supported. Try removing 'p' modifier."); #if defined(__i386__) || defined(__x86_64__) if (evsel->core.attr.type == PERF_TYPE_HARDWARE) return scnprintf(msg, size, "%s", "No hardware sampling interrupt available.\n"); #endif break; case EBUSY: if (find_process("oprofiled")) return scnprintf(msg, size, "The PMU counters are busy/taken by another profiler.\n" "We found oprofile daemon running, please stop it and try again."); break; case EINVAL: if (evsel->core.attr.sample_type & PERF_SAMPLE_CODE_PAGE_SIZE && perf_missing_features.code_page_size) return scnprintf(msg, size, "Asking for the code page size isn't supported by this kernel."); if (evsel->core.attr.sample_type & PERF_SAMPLE_DATA_PAGE_SIZE && perf_missing_features.data_page_size) return scnprintf(msg, size, "Asking for the data page size isn't supported by this kernel."); if (evsel->core.attr.write_backward && perf_missing_features.write_backward) return scnprintf(msg, size, "Reading from overwrite event is not supported by this kernel."); if (perf_missing_features.clockid) return scnprintf(msg, size, "clockid feature not supported."); if (perf_missing_features.clockid_wrong) return scnprintf(msg, size, "wrong clockid (%d).", clockid); if (perf_missing_features.aux_output) return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel."); if (!target__has_cpu(target)) return scnprintf(msg, size, "Invalid event (%s) in per-thread mode, enable system wide with '-a'.", evsel__name(evsel)); break; case ENODATA: return scnprintf(msg, size, "Cannot collect data source with the load latency event alone. " "Please add an auxiliary event in front of the load latency event."); default: break; } ret = arch_evsel__open_strerror(evsel, msg, size); if (ret) return ret; return scnprintf(msg, size, "The sys_perf_event_open() syscall returned with %d (%s) for event (%s).\n" "/bin/dmesg | grep -i perf may provide additional information.\n", err, str_error_r(err, sbuf, sizeof(sbuf)), evsel__name(evsel)); } struct perf_env *evsel__env(struct evsel *evsel) { if (evsel && evsel->evlist && evsel->evlist->env) return evsel->evlist->env; return &perf_env; } static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist) { int cpu_map_idx, thread; if (evsel__is_retire_lat(evsel)) return 0; for (cpu_map_idx = 0; cpu_map_idx < xyarray__max_x(evsel->core.fd); cpu_map_idx++) { for (thread = 0; thread < xyarray__max_y(evsel->core.fd); thread++) { int fd = FD(evsel, cpu_map_idx, thread); if (perf_evlist__id_add_fd(&evlist->core, &evsel->core, cpu_map_idx, thread, fd) < 0) return -1; } } return 0; } int evsel__store_ids(struct evsel *evsel, struct evlist *evlist) { struct perf_cpu_map *cpus = evsel->core.cpus; struct perf_thread_map *threads = evsel->core.threads; if (perf_evsel__alloc_id(&evsel->core, perf_cpu_map__nr(cpus), threads->nr)) return -ENOMEM; return store_evsel_ids(evsel, evlist); } void evsel__zero_per_pkg(struct evsel *evsel) { struct hashmap_entry *cur; size_t bkt; if (evsel->per_pkg_mask) { hashmap__for_each_entry(evsel->per_pkg_mask, cur, bkt) zfree(&cur->pkey); hashmap__clear(evsel->per_pkg_mask); } } /** * evsel__is_hybrid - does the evsel have a known PMU that is hybrid. Note, this * will be false on hybrid systems for hardware and legacy * cache events. */ bool evsel__is_hybrid(const struct evsel *evsel) { if (perf_pmus__num_core_pmus() == 1) return false; return evsel->core.is_pmu_core; } struct evsel *evsel__leader(const struct evsel *evsel) { return container_of(evsel->core.leader, struct evsel, core); } bool evsel__has_leader(struct evsel *evsel, struct evsel *leader) { return evsel->core.leader == &leader->core; } bool evsel__is_leader(struct evsel *evsel) { return evsel__has_leader(evsel, evsel); } void evsel__set_leader(struct evsel *evsel, struct evsel *leader) { evsel->core.leader = &leader->core; } int evsel__source_count(const struct evsel *evsel) { struct evsel *pos; int count = 0; evlist__for_each_entry(evsel->evlist, pos) { if (pos->metric_leader == evsel) count++; } return count; } bool __weak arch_evsel__must_be_in_group(const struct evsel *evsel __maybe_unused) { return false; } /* * Remove an event from a given group (leader). * Some events, e.g., perf metrics Topdown events, * must always be grouped. Ignore the events. */ void evsel__remove_from_group(struct evsel *evsel, struct evsel *leader) { if (!arch_evsel__must_be_in_group(evsel) && evsel != leader) { evsel__set_leader(evsel, evsel); evsel->core.nr_members = 0; leader->core.nr_members--; } }
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