Something went wrong. Try again.
(I'm so sorry!) Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel os linux
Something went wrong. Try again.
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069// SPDX-License-Identifier: GPL-2.0-only/* * Copyright (C) 2008, 2009 Intel Corporation * Authors: Andi Kleen, Fengguang Wu * * High level machine check handler. Handles pages reported by the * hardware as being corrupted usually due to a multi-bit ECC memory or cache * failure. * * In addition there is a "soft offline" entry point that allows stop using * not-yet-corrupted-by-suspicious pages without killing anything. * * Handles page cache pages in various states. The tricky part * here is that we can access any page asynchronously in respect to * other VM users, because memory failures could happen anytime and * anywhere. This could violate some of their assumptions. This is why * this code has to be extremely careful. Generally it tries to use * normal locking rules, as in get the standard locks, even if that means * the error handling takes potentially a long time. * * It can be very tempting to add handling for obscure cases here. * In general any code for handling new cases should only be added iff: * - You know how to test it. * - You have a test that can be added to mce-test * https://git.kernel.org/cgit/utils/cpu/mce/mce-test.git/ * - The case actually shows up as a frequent (top 10) page state in * tools/mm/page-types when running a real workload. * * There are several operations here with exponential complexity because * of unsuitable VM data structures. For example the operation to map back * from RMAP chains to processes has to walk the complete process list and * has non linear complexity with the number. But since memory corruptions * are rare we hope to get away with this. This avoids impacting the core * VM. */
#define pr_fmt(fmt) "Memory failure: " fmt
#include <linux/kernel.h>#include <linux/mm.h>#include <linux/memory-failure.h>#include <linux/page-flags.h>#include <linux/sched/signal.h>#include <linux/sched/task.h>#include <linux/dax.h>#include <linux/ksm.h>#include <linux/rmap.h>#include <linux/export.h>#include <linux/pagemap.h>#include <linux/swap.h>#include <linux/backing-dev.h>#include <linux/migrate.h>#include <linux/slab.h>#include <linux/leafops.h>#include <linux/hugetlb.h>#include <linux/memory_hotplug.h>#include <linux/mm_inline.h>#include <linux/memremap.h>#include <linux/kfifo.h>#include <linux/ratelimit.h>#include <linux/pagewalk.h>#include <linux/shmem_fs.h>#include <linux/sysctl.h>
#define CREATE_TRACE_POINTS#include <trace/events/memory-failure.h>
#include "swap.h"#include "page_alloc.h"#include "internal.h"
static int sysctl_memory_failure_early_kill __read_mostly;
static int sysctl_memory_failure_recovery __read_mostly = 1;
static int sysctl_enable_soft_offline __read_mostly = 1;
static int sysctl_panic_on_unrecoverable_mf __read_mostly;
atomic_long_t num_poisoned_pages __read_mostly = ATOMIC_LONG_INIT(0);
static bool hw_memory_failure __read_mostly;
static DEFINE_MUTEX(mf_mutex);
void num_poisoned_pages_inc(unsigned long pfn){ atomic_long_inc(&num_poisoned_pages); memblk_nr_poison_inc(pfn);}
void num_poisoned_pages_sub(unsigned long pfn, long i){ atomic_long_sub(i, &num_poisoned_pages); if (pfn != -1UL) memblk_nr_poison_sub(pfn, i);}
/* * Return the first or the last hardware-poisoned online page in [start, * start + size), or PHYS_ADDR_MAX if the range is clean. */static phys_addr_t range_hwpoison(phys_addr_t start, unsigned long size, bool first){ phys_addr_t poison = PHYS_ADDR_MAX; unsigned long pfn, end_pfn;
if (!size || !atomic_long_read(&num_poisoned_pages)) return poison;
end_pfn = PHYS_PFN(start + size - 1); for (pfn = PHYS_PFN(start); pfn <= end_pfn; pfn++) { struct page *page = pfn_to_online_page(pfn);
if (page && is_page_hwpoison(page)) { if (first) return PFN_PHYS(pfn);
poison = PFN_PHYS(pfn); }
cond_resched(); }
return poison;}
phys_addr_t range_first_hwpoison(phys_addr_t start, unsigned long size){ return range_hwpoison(start, size, true);}
phys_addr_t range_last_hwpoison(phys_addr_t start, unsigned long size){ return range_hwpoison(start, size, false);}
/** * MF_ATTR_RO - Create sysfs entry for each memory failure statistics. * @_name: name of the file in the per NUMA sysfs directory. */#define MF_ATTR_RO(_name) \static ssize_t _name##_show(struct device *dev, \ struct device_attribute *attr, \ char *buf) \{ \ struct memory_failure_stats *mf_stats = \ &NODE_DATA(dev->id)->mf_stats; \ return sysfs_emit(buf, "%lu\n", mf_stats->_name); \} \static DEVICE_ATTR_RO(_name)
MF_ATTR_RO(total);MF_ATTR_RO(ignored);MF_ATTR_RO(failed);MF_ATTR_RO(delayed);MF_ATTR_RO(recovered);
static struct attribute *memory_failure_attr[] = { &dev_attr_total.attr, &dev_attr_ignored.attr, &dev_attr_failed.attr, &dev_attr_delayed.attr, &dev_attr_recovered.attr, NULL,};
const struct attribute_group memory_failure_attr_group = { .name = "memory_failure", .attrs = memory_failure_attr,};
static const struct ctl_table memory_failure_table[] = { { .procname = "memory_failure_early_kill", .data = &sysctl_memory_failure_early_kill, .maxlen = sizeof(sysctl_memory_failure_early_kill), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "memory_failure_recovery", .data = &sysctl_memory_failure_recovery, .maxlen = sizeof(sysctl_memory_failure_recovery), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "enable_soft_offline", .data = &sysctl_enable_soft_offline, .maxlen = sizeof(sysctl_enable_soft_offline), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }, { .procname = "panic_on_unrecoverable_memory_failure", .data = &sysctl_panic_on_unrecoverable_mf, .maxlen = sizeof(sysctl_panic_on_unrecoverable_mf), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_ONE, }};
static struct rb_root_cached pfn_space_itree = RB_ROOT_CACHED;
static DEFINE_MUTEX(pfn_space_lock);
/* * Return values: * 1: the page is dissolved (if needed) and taken off from buddy, * 0: the page is dissolved (if needed) and not taken off from buddy, * < 0: failed to dissolve. */static int __page_handle_poison(struct page *page){ int ret;
zone_pcp_disable(page_zone(page)); ret = dissolve_free_hugetlb_folio(page_folio(page)); if (!ret) ret = take_page_off_buddy(page); zone_pcp_enable(page_zone(page));
return ret;}
static bool page_handle_poison(struct page *page, bool hugepage_or_freepage, bool release){ if (hugepage_or_freepage) { /* * Doing this check for free pages is also fine since * dissolve_free_hugetlb_folio() returns 0 for non-hugetlb folios as well. */ if (__page_handle_poison(page) <= 0) /* * We could fail to take off the target page from buddy * for example due to racy page allocation, but that's * acceptable because soft-offlined page is not broken * and if someone really want to use it, they should * take it. */ return false; }
SetPageHWPoison(page); if (release) put_page(page); page_ref_inc(page); num_poisoned_pages_inc(page_to_pfn(page));
return true;}
static hwpoison_filter_func_t __rcu *hwpoison_filter_func __read_mostly;
void hwpoison_filter_register(hwpoison_filter_func_t *filter){ rcu_assign_pointer(hwpoison_filter_func, filter);}EXPORT_SYMBOL_GPL(hwpoison_filter_register);
void hwpoison_filter_unregister(void){ RCU_INIT_POINTER(hwpoison_filter_func, NULL); synchronize_rcu();}EXPORT_SYMBOL_GPL(hwpoison_filter_unregister);
static int hwpoison_filter(struct page *p){ int ret = 0; hwpoison_filter_func_t *filter;
rcu_read_lock(); filter = rcu_dereference(hwpoison_filter_func); if (filter) ret = filter(p); rcu_read_unlock();
return ret;}
/* * Kill all processes that have a poisoned page mapped and then isolate * the page. * * General strategy: * Find all processes having the page mapped and kill them. * But we keep a page reference around so that the page is not * actually freed yet. * Then stash the page away * * There's no convenient way to get back to mapped processes * from the VMAs. So do a brute-force search over all * running processes. * * Remember that machine checks are not common (or rather * if they are common you have other problems), so this shouldn't * be a performance issue. * * Also there are some races possible while we get from the * error detection to actually handle it. */
struct to_kill { struct list_head nd; struct task_struct *tsk; unsigned long addr; short size_shift;};
/* * Send all the processes who have the page mapped a signal. * ``action optional'' if they are not immediately affected by the error * ``action required'' if error happened in current execution context */static int kill_proc(struct to_kill *tk, unsigned long pfn, int flags){ struct task_struct *t = tk->tsk; short addr_lsb = tk->size_shift; int ret = 0;
pr_err("%#lx: Sending SIGBUS to %s:%d due to hardware memory corruption\n", pfn, t->comm, task_pid_nr(t));
if ((flags & MF_ACTION_REQUIRED) && (t == current)) ret = force_sig_mceerr(BUS_MCEERR_AR, (void __user *)tk->addr, addr_lsb); else /* * Signal other processes sharing the page if they have * PF_MCE_EARLY set. * Don't use force here, it's convenient if the signal * can be temporarily blocked. */ ret = send_sig_mceerr(BUS_MCEERR_AO, (void __user *)tk->addr, addr_lsb, t); if (ret < 0) pr_info("Error sending signal to %s:%d: %d\n", t->comm, task_pid_nr(t), ret); return ret;}
/* * Unknown page type encountered. Try to check whether it can turn PageLRU by * lru_add_drain_all. */void shake_folio(struct folio *folio){ if (folio_test_hugetlb(folio)) return; /* * TODO: Could shrink slab caches here if a lightweight range-based * shrinker will be available. */ if (folio_test_slab(folio)) return;
lru_add_drain_all();}EXPORT_SYMBOL_GPL(shake_folio);
static void shake_page(struct page *page){ shake_folio(page_folio(page));}
static unsigned long dev_pagemap_mapping_shift(struct vm_area_struct *vma, unsigned long address){ unsigned long ret = 0; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; pte_t ptent;
VM_BUG_ON_VMA(address == -EFAULT, vma); pgd = pgd_offset(vma->vm_mm, address); if (!pgd_present(*pgd)) return 0; p4d = p4d_offset(pgd, address); if (!p4d_present(*p4d)) return 0; pud = pud_offset(p4d, address); if (!pud_present(*pud)) return 0; if (pud_trans_huge(*pud)) return PUD_SHIFT; pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return 0; if (pmd_trans_huge(*pmd)) return PMD_SHIFT; pte = pte_offset_map(pmd, address); if (!pte) return 0; ptent = ptep_get(pte); if (pte_present(ptent)) ret = PAGE_SHIFT; pte_unmap(pte); return ret;}
/* * Failure handling: if we can't find or can't kill a process there's * not much we can do. We just print a message and ignore otherwise. */
/* * Schedule a process for later kill. * Uses GFP_ATOMIC allocations to avoid potential recursions in the VM. */static void __add_to_kill(struct task_struct *tsk, const struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, unsigned long addr){ struct to_kill *tk;
tk = kmalloc_obj(struct to_kill, GFP_ATOMIC); if (!tk) { pr_err("Out of memory while machine check handling\n"); return; }
tk->addr = addr; if (is_zone_device_page(p)) tk->size_shift = dev_pagemap_mapping_shift(vma, tk->addr); else tk->size_shift = folio_shift(page_folio(p));
/* * Send SIGKILL if "tk->addr == -EFAULT". Also, as * "tk->size_shift" is always non-zero for !is_zone_device_page(), * so "tk->size_shift == 0" effectively checks no mapping on * ZONE_DEVICE. Indeed, when a devdax page is mmapped N times * to a process' address space, it's possible not all N VMAs * contain mappings for the page, but at least one VMA does. * Only deliver SIGBUS with payload derived from the VMA that * has a mapping for the page. */ if (tk->addr == -EFAULT) { pr_info("Unable to find user space address %lx in %s\n", page_to_pfn(p), tsk->comm); } else if (tk->size_shift == 0) { kfree(tk); return; }
get_task_struct(tsk); tk->tsk = tsk; list_add_tail(&tk->nd, to_kill);}
static void add_to_kill_anon_file(struct task_struct *tsk, const struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, unsigned long addr){ if (addr == -EFAULT) return; __add_to_kill(tsk, p, vma, to_kill, addr);}
#ifdef CONFIG_KSMstatic bool task_in_to_kill_list(struct list_head *to_kill, struct task_struct *tsk){ struct to_kill *tk, *next;
list_for_each_entry_safe(tk, next, to_kill, nd) { if (tk->tsk == tsk) return true; }
return false;}
void add_to_kill_ksm(struct task_struct *tsk, const struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, unsigned long addr){ if (!task_in_to_kill_list(to_kill, tsk)) __add_to_kill(tsk, p, vma, to_kill, addr);}#endif/* * Kill the processes that have been collected earlier. * * Only do anything when FORCEKILL is set, otherwise just free the * list (this is used for clean pages which do not need killing) */static void kill_procs(struct list_head *to_kill, bool forcekill, unsigned long pfn, int flags){ struct to_kill *tk, *next;
list_for_each_entry_safe(tk, next, to_kill, nd) { if (forcekill) { if (tk->addr == -EFAULT) { pr_err("%#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", pfn, tk->tsk->comm, task_pid_nr(tk->tsk)); do_send_sig_info(SIGKILL, SEND_SIG_PRIV, tk->tsk, PIDTYPE_PID); }
/* * In theory the process could have mapped * something else on the address in-between. We could * check for that, but we need to tell the * process anyways. */ else if (kill_proc(tk, pfn, flags) < 0) pr_err("%#lx: Cannot send advisory machine check signal to %s:%d\n", pfn, tk->tsk->comm, task_pid_nr(tk->tsk)); } list_del(&tk->nd); put_task_struct(tk->tsk); kfree(tk); }}
/* * Find a dedicated thread which is supposed to handle SIGBUS(BUS_MCEERR_AO) * on behalf of the thread group. Return task_struct of the (first found) * dedicated thread if found, and return NULL otherwise. * * We already hold rcu lock in the caller, so we don't have to call * rcu_read_lock/unlock() in this function. */static struct task_struct *find_early_kill_thread(struct task_struct *tsk){ struct task_struct *t;
for_each_thread(tsk, t) { if (t->flags & PF_MCE_PROCESS) { if (t->flags & PF_MCE_EARLY) return t; } else { if (sysctl_memory_failure_early_kill) return t; } } return NULL;}
/* * Determine whether a given process is "early kill" process which expects * to be signaled when some page under the process is hwpoisoned. * Return task_struct of the dedicated thread (main thread unless explicitly * specified) if the process is "early kill" and otherwise returns NULL. * * Note that the above is true for Action Optional case. For Action Required * case, it's only meaningful to the current thread which need to be signaled * with SIGBUS, this error is Action Optional for other non current * processes sharing the same error page,if the process is "early kill", the * task_struct of the dedicated thread will also be returned. */struct task_struct *task_early_kill(struct task_struct *tsk, int force_early){ if (!tsk->mm) return NULL; /* * Comparing ->mm here because current task might represent * a subthread, while tsk always points to the main thread. */ if (force_early && tsk->mm == current->mm) return current;
return find_early_kill_thread(tsk);}
/* * Collect processes when the error hit an anonymous page. */static void collect_procs_anon(const struct folio *folio, const struct page *page, struct list_head *to_kill, int force_early){ struct task_struct *tsk; struct anon_vma *av; pgoff_t pgoff;
av = folio_lock_anon_vma_read(folio, NULL); if (av == NULL) /* Not actually mapped anymore */ return;
pgoff = page_pgoff(folio, page); rcu_read_lock(); for_each_process(tsk) { struct vm_area_struct *vma; struct anon_vma_chain *vmac; struct task_struct *t = task_early_kill(tsk, force_early); unsigned long addr;
if (!t) continue; anon_rmap_tree_foreach(vmac, av, pgoff, pgoff) { vma = vmac->vma; if (vma->vm_mm != t->mm) continue; addr = page_mapped_in_vma(page, vma); add_to_kill_anon_file(t, page, vma, to_kill, addr); } } rcu_read_unlock(); anon_vma_unlock_read(av);}
/* * Collect processes when the error hit a file mapped page. */static void collect_procs_file(const struct folio *folio, const struct page *page, struct list_head *to_kill, int force_early){ struct vm_area_struct *vma; struct task_struct *tsk; struct address_space *mapping = folio->mapping; pgoff_t pgoff;
i_mmap_lock_read(mapping); rcu_read_lock(); pgoff = page_pgoff(folio, page); for_each_process(tsk) { struct task_struct *t = task_early_kill(tsk, force_early); unsigned long addr;
if (!t) continue; mapping_rmap_tree_foreach(vma, mapping, pgoff, pgoff) { /* * Send early kill signal to tasks where a vma covers * the page but the corrupted page is not necessarily * mapped in its pte. * Assume applications who requested early kill want * to be informed of all such data corruptions. */ if (vma->vm_mm != t->mm) continue; addr = page_address_in_vma(folio, page, vma); add_to_kill_anon_file(t, page, vma, to_kill, addr); } } rcu_read_unlock(); i_mmap_unlock_read(mapping);}
#ifdef CONFIG_FS_DAXstatic void add_to_kill_fsdax(struct task_struct *tsk, const struct page *p, struct vm_area_struct *vma, struct list_head *to_kill, pgoff_t pgoff){ unsigned long addr = vma_filebacked_address(vma, pgoff, 1); __add_to_kill(tsk, p, vma, to_kill, addr);}
/* * Collect processes when the error hit a fsdax page. */static void collect_procs_fsdax(const struct page *page, struct address_space *mapping, pgoff_t pgoff, struct list_head *to_kill, bool pre_remove){ struct vm_area_struct *vma; struct task_struct *tsk;
i_mmap_lock_read(mapping); rcu_read_lock(); for_each_process(tsk) { struct task_struct *t = tsk;
/* * Search for all tasks while MF_MEM_PRE_REMOVE is set, because * the current may not be the one accessing the fsdax page. * Otherwise, search for the current task. */ if (!pre_remove) t = task_early_kill(tsk, true); if (!t) continue; mapping_rmap_tree_foreach(vma, mapping, pgoff, pgoff) { if (vma->vm_mm == t->mm) add_to_kill_fsdax(t, page, vma, to_kill, pgoff); } } rcu_read_unlock(); i_mmap_unlock_read(mapping);}#endif /* CONFIG_FS_DAX */
/* * Collect the processes who have the corrupted page mapped to kill. */static void collect_procs(const struct folio *folio, const struct page *page, struct list_head *tokill, int force_early){ if (!folio->mapping) return; if (unlikely(folio_test_ksm(folio))) collect_procs_ksm(folio, page, tokill, force_early); else if (folio_test_anon(folio)) collect_procs_anon(folio, page, tokill, force_early); else collect_procs_file(folio, page, tokill, force_early);}
struct hwpoison_walk { struct to_kill tk; unsigned long pfn; int flags;};
static void set_to_kill(struct to_kill *tk, unsigned long addr, short shift){ tk->addr = addr; tk->size_shift = shift;}
static int check_hwpoisoned_entry(pte_t pte, unsigned long addr, short shift, unsigned long poisoned_pfn, struct to_kill *tk){ unsigned long pfn = 0; unsigned long hwpoison_vaddr; unsigned long mask;
if (pte_present(pte)) { pfn = pte_pfn(pte); } else { const softleaf_t entry = softleaf_from_pte(pte);
if (softleaf_is_hwpoison(entry)) pfn = softleaf_to_pfn(entry); }
mask = ~((1UL << (shift - PAGE_SHIFT)) - 1); if (!pfn || pfn != (poisoned_pfn & mask)) return 0;
hwpoison_vaddr = addr + ((poisoned_pfn - pfn) << PAGE_SHIFT); set_to_kill(tk, hwpoison_vaddr, shift); return 1;}
#ifdef CONFIG_TRANSPARENT_HUGEPAGEstatic int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr, struct hwpoison_walk *hwp){ pmd_t pmd = *pmdp; unsigned long pfn; unsigned long hwpoison_vaddr;
if (!pmd_present(pmd)) return 0; pfn = pmd_pfn(pmd); if (pfn <= hwp->pfn && hwp->pfn < pfn + HPAGE_PMD_NR) { hwpoison_vaddr = addr + ((hwp->pfn - pfn) << PAGE_SHIFT); set_to_kill(&hwp->tk, hwpoison_vaddr, PAGE_SHIFT); return 1; } return 0;}#elsestatic int check_hwpoisoned_pmd_entry(pmd_t *pmdp, unsigned long addr, struct hwpoison_walk *hwp){ return 0;}#endif
static int hwpoison_pte_range(pmd_t *pmdp, unsigned long addr, unsigned long end, struct mm_walk *walk){ struct hwpoison_walk *hwp = walk->private; int ret = 0; pte_t *ptep, *mapped_pte; spinlock_t *ptl;
ptl = pmd_trans_huge_lock(pmdp, walk->vma); if (ptl) { ret = check_hwpoisoned_pmd_entry(pmdp, addr, hwp); spin_unlock(ptl); goto out; }
mapped_pte = ptep = pte_offset_map_lock(walk->vma->vm_mm, pmdp, addr, &ptl); if (!ptep) goto out;
for (; addr != end; ptep++, addr += PAGE_SIZE) { ret = check_hwpoisoned_entry(ptep_get(ptep), addr, PAGE_SHIFT, hwp->pfn, &hwp->tk); if (ret == 1) break; } pte_unmap_unlock(mapped_pte, ptl);out: cond_resched(); return ret;}
#ifdef CONFIG_HUGETLB_PAGEstatic int hwpoison_hugetlb_range(pte_t *ptep, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk){ struct hwpoison_walk *hwp = walk->private; struct hstate *h = hstate_vma(walk->vma); spinlock_t *ptl; pte_t pte; int ret;
ptl = huge_pte_lock(h, walk->mm, ptep); pte = huge_ptep_get(walk->mm, addr, ptep); ret = check_hwpoisoned_entry(pte, addr, huge_page_shift(h), hwp->pfn, &hwp->tk); spin_unlock(ptl); return ret;}#else#define hwpoison_hugetlb_range NULL#endif
static int hwpoison_test_walk(unsigned long start, unsigned long end, struct mm_walk *walk){ /* We also want to consider pages mapped into VM_PFNMAP. */ return 0;}
static const struct mm_walk_ops hwpoison_walk_ops = { .pmd_entry = hwpoison_pte_range, .hugetlb_entry = hwpoison_hugetlb_range, .test_walk = hwpoison_test_walk, .walk_lock = PGWALK_RDLOCK,};
/* * Sends SIGBUS to the current process with error info. * * This function is intended to handle "Action Required" MCEs on already * hardware poisoned pages. They could happen, for example, when * memory_failure() failed to unmap the error page at the first call, or * when multiple local machine checks happened on different CPUs. * * MCE handler currently has no easy access to the error virtual address, * so this function walks page table to find it. The returned virtual address * is proper in most cases, but it could be wrong when the application * process has multiple entries mapping the error page. */static int kill_accessing_process(struct task_struct *p, unsigned long pfn, int flags){ int ret; struct hwpoison_walk priv = { .pfn = pfn, }; priv.tk.tsk = p;
if (!p->mm) return -EFAULT;
mmap_read_lock(p->mm); ret = walk_page_range(p->mm, 0, TASK_SIZE, &hwpoison_walk_ops, (void *)&priv); /* * ret = 1 when CMCI wins, regardless of whether try_to_unmap() * succeeds or fails, then kill the process with SIGBUS. * ret = 0 when poison page is a clean page and it's dropped, no * SIGBUS is needed. */ if (ret == 1 && priv.tk.addr) kill_proc(&priv.tk, pfn, flags); mmap_read_unlock(p->mm);
return ret > 0 ? -EHWPOISON : 0;}
/* * MF_IGNORED - The m-f() handler marks the page as PG_hwpoison'ed. * But it could not do more to isolate the page from being accessed again, * nor does it kill the process. This is extremely rare and one of the * potential causes is that the page state has been changed due to * underlying race condition. This is the most severe outcomes. * * MF_FAILED - The m-f() handler marks the page as PG_hwpoison'ed. * It should have killed the process, but it can't isolate the page, * due to conditions such as extra pin, unmap failure, etc. Accessing * the page again may trigger another MCE and the process will be killed * by the m-f() handler immediately. * * MF_DELAYED - The m-f() handler marks the page as PG_hwpoison'ed. * It means the page was unmapped and partially isolated (e.g. removed from * file mapping or the LRU) but full cleanup is deferred (e.g. the metadata * for the memory, as in struct page/folio, is still referenced). Any * further access to the page will result in the process being killed. * * MF_RECOVERED - The m-f() handler marks the page as PG_hwpoison'ed. * The page has been completely isolated, that is, unmapped, taken out of * the buddy system, or hole-punched out of the file mapping. */static const char *action_name[] = { [MF_IGNORED] = "Ignored", [MF_FAILED] = "Failed", [MF_DELAYED] = "Delayed", [MF_RECOVERED] = "Recovered",};
static const char * const action_page_types[] = { [MF_MSG_KERNEL] = "reserved kernel page", [MF_MSG_KERNEL_HIGH_ORDER] = "high-order kernel page", [MF_MSG_HUGE] = "huge page", [MF_MSG_FREE_HUGE] = "free huge page", [MF_MSG_GET_HWPOISON] = "get hwpoison page", [MF_MSG_UNMAP_FAILED] = "unmapping failed page", [MF_MSG_DIRTY_SWAPCACHE] = "dirty swapcache page", [MF_MSG_CLEAN_SWAPCACHE] = "clean swapcache page", [MF_MSG_DIRTY_MLOCKED_LRU] = "dirty mlocked LRU page", [MF_MSG_CLEAN_MLOCKED_LRU] = "clean mlocked LRU page", [MF_MSG_DIRTY_UNEVICTABLE_LRU] = "dirty unevictable LRU page", [MF_MSG_CLEAN_UNEVICTABLE_LRU] = "clean unevictable LRU page", [MF_MSG_DIRTY_LRU] = "dirty LRU page", [MF_MSG_CLEAN_LRU] = "clean LRU page", [MF_MSG_TRUNCATED_LRU] = "already truncated LRU page", [MF_MSG_BUDDY] = "free buddy page", [MF_MSG_DAX] = "dax page", [MF_MSG_UNSPLIT_THP] = "unsplit thp", [MF_MSG_ALREADY_POISONED] = "already poisoned page", [MF_MSG_PFN_MAP] = "non struct page pfn", [MF_MSG_UNKNOWN] = "unknown page",};
/* * XXX: It is possible that a page is isolated from LRU cache, * and then kept in swap cache or failed to remove from page cache. * The page count will stop it from being freed by unpoison. * Stress tests should be aware of this memory leak problem. */static int delete_from_lru_cache(struct folio *folio){ if (folio_isolate_lru(folio)) { /* * Clear sensible page flags, so that the buddy system won't * complain when the folio is unpoison-and-freed. */ folio_clear_active(folio); folio_clear_unevictable(folio);
/* * Poisoned page might never drop its ref count to 0 so we have * to uncharge it manually from its memcg. */ mem_cgroup_uncharge(folio);
/* * drop the refcount elevated by folio_isolate_lru() */ folio_put(folio); return 0; } return -EIO;}
static int truncate_error_folio(struct folio *folio, unsigned long pfn, struct address_space *mapping){ int ret = MF_FAILED;
if (mapping->a_ops->error_remove_folio) { int err = mapping->a_ops->error_remove_folio(mapping, folio);
if (err == MF_DELAYED) ret = err; else if (err != 0) pr_info("%#lx: Failed to punch page: %d\n", pfn, err); else if (!filemap_release_folio(folio, GFP_NOIO)) pr_info("%#lx: Failed to release buffers\n", pfn); else ret = MF_RECOVERED; } else { /* * If the file system doesn't support it just invalidate * This fails on dirty or anything with private pages */ if (mapping_evict_folio(mapping, folio)) ret = MF_RECOVERED; else pr_info("%#lx: Failed to invalidate\n", pfn); }
return ret;}
struct page_state { unsigned long mask; unsigned long res; enum mf_action_page_type type;
/* Callback ->action() has to unlock the relevant page inside it. */ int (*action)(struct page_state *ps, struct page *p);};
/* * Return true if page is still referenced by others, otherwise return * false. * * The extra_pins is true when one extra refcount is expected. */static bool has_extra_refcount(struct page_state *ps, struct page *p, bool extra_pins){ int count = page_count(p) - 1;
if (extra_pins) count -= folio_nr_pages(page_folio(p));
if (count > 0) { pr_err("%#lx: %s still referenced by %d users\n", page_to_pfn(p), action_page_types[ps->type], count); return true; }
return false;}
/* * Page in unknown state. Do nothing. * This is a catch-all in case we fail to make sense of the page state. */static int me_unknown(struct page_state *ps, struct page *p){ pr_err("%#lx: Unknown page state\n", page_to_pfn(p)); unlock_page(p); return MF_IGNORED;}
/* * Clean (or cleaned) page cache page. */static int me_pagecache_clean(struct page_state *ps, struct page *p){ struct folio *folio = page_folio(p); int ret; struct address_space *mapping; bool extra_pins;
delete_from_lru_cache(folio);
/* * For anonymous folios the only reference left * should be the one m_f() holds. */ if (folio_test_anon(folio)) { ret = MF_RECOVERED; goto out; }
/* * Now truncate the page in the page cache. This is really * more like a "temporary hole punch" * Don't do this for block devices when someone else * has a reference, because it could be file system metadata * and that's not safe to truncate. */ mapping = folio_mapping(folio); if (!mapping) { /* Folio has been torn down in the meantime */ ret = MF_FAILED; goto out; }
/* * Truncation is a bit tricky. Enable it per file system for now. * * Open: to take i_rwsem or not for this? Right now we don't. */ ret = truncate_error_folio(folio, page_to_pfn(p), mapping);
extra_pins = ret == MF_DELAYED; if (has_extra_refcount(ps, p, extra_pins)) ret = MF_FAILED;
out: folio_unlock(folio);
return ret;}
/* * Dirty pagecache page * Issues: when the error hit a hole page the error is not properly * propagated. */static int me_pagecache_dirty(struct page_state *ps, struct page *p){ struct folio *folio = page_folio(p); struct address_space *mapping = folio_mapping(folio);
/* TBD: print more information about the file. */ if (mapping) { /* * IO error will be reported by write(), fsync(), etc. * who check the mapping. * This way the application knows that something went * wrong with its dirty file data. */ mapping_set_error(mapping, -EIO); }
return me_pagecache_clean(ps, p);}
/* * Clean and dirty swap cache. * * Dirty swap cache page is tricky to handle. The page could live both in page * table and swap cache(ie. page is freshly swapped in). So it could be * referenced concurrently by 2 types of PTEs: * normal PTEs and swap PTEs. We try to handle them consistently by calling * try_to_unmap(!TTU_HWPOISON) to convert the normal PTEs to swap PTEs, * and then * - clear dirty bit to prevent IO * - remove from LRU * - but keep in the swap cache, so that when we return to it on * a later page fault, we know the application is accessing * corrupted data and shall be killed (we installed simple * interception code in do_swap_page to catch it). * * Clean swap cache pages can be directly isolated. A later page fault will * bring in the known good data from disk. */static int me_swapcache_dirty(struct page_state *ps, struct page *p){ struct folio *folio = page_folio(p); int ret; bool extra_pins = false;
folio_clear_dirty(folio); /* Trigger EIO in shmem: */ folio_clear_uptodate(folio);
ret = delete_from_lru_cache(folio) ? MF_FAILED : MF_DELAYED; folio_unlock(folio);
if (ret == MF_DELAYED) extra_pins = true;
if (has_extra_refcount(ps, p, extra_pins)) ret = MF_FAILED;
return ret;}
static int me_swapcache_clean(struct page_state *ps, struct page *p){ struct folio *folio = page_folio(p); int ret;
swap_cache_del_folio(folio);
ret = delete_from_lru_cache(folio) ? MF_FAILED : MF_RECOVERED; folio_unlock(folio);
if (has_extra_refcount(ps, p, false)) ret = MF_FAILED;
return ret;}
/* * Huge pages. Needs work. * Issues: * - Error on hugepage is contained in hugepage unit (not in raw page unit.) * To narrow down kill region to one page, we need to break up pmd. */static int me_huge_page(struct page_state *ps, struct page *p){ struct folio *folio = page_folio(p); int res; struct address_space *mapping; bool extra_pins = false;
mapping = folio_mapping(folio); if (mapping) { res = truncate_error_folio(folio, page_to_pfn(p), mapping); /* The page is kept in page cache. */ extra_pins = true; folio_unlock(folio); } else { folio_unlock(folio); /* * migration entry prevents later access on error hugepage, * so we can free and dissolve it into buddy to save healthy * subpages. */ folio_put(folio); if (__page_handle_poison(p) > 0) { page_ref_inc(p); res = MF_RECOVERED; } else { res = MF_FAILED; } }
if (has_extra_refcount(ps, p, extra_pins)) res = MF_FAILED;
return res;}
/* * Various page states we can handle. * * A page state is defined by its current page->flags bits. * The table matches them in order and calls the right handler. * * This is quite tricky because we can access page at any time * in its live cycle, so all accesses have to be extremely careful. * * This is not complete. More states could be added. * For any missing state don't attempt recovery. */
#define dirty (1UL << PG_dirty)#define sc ((1UL << PG_swapcache) | (1UL << PG_swapbacked))#define unevict (1UL << PG_unevictable)#define mlock (1UL << PG_mlocked)#define lru (1UL << PG_lru)#define head (1UL << PG_head)
static struct page_state error_states[] = { /* * free pages are specially detected outside this table: * PG_buddy pages only make a small fraction of all free pages. */
{ head, head, MF_MSG_HUGE, me_huge_page },
{ sc|dirty, sc|dirty, MF_MSG_DIRTY_SWAPCACHE, me_swapcache_dirty }, { sc|dirty, sc, MF_MSG_CLEAN_SWAPCACHE, me_swapcache_clean },
{ mlock|dirty, mlock|dirty, MF_MSG_DIRTY_MLOCKED_LRU, me_pagecache_dirty }, { mlock|dirty, mlock, MF_MSG_CLEAN_MLOCKED_LRU, me_pagecache_clean },
{ unevict|dirty, unevict|dirty, MF_MSG_DIRTY_UNEVICTABLE_LRU, me_pagecache_dirty }, { unevict|dirty, unevict, MF_MSG_CLEAN_UNEVICTABLE_LRU, me_pagecache_clean },
{ lru|dirty, lru|dirty, MF_MSG_DIRTY_LRU, me_pagecache_dirty }, { lru|dirty, lru, MF_MSG_CLEAN_LRU, me_pagecache_clean },
/* * Catchall entry: must be at end. */ { 0, 0, MF_MSG_UNKNOWN, me_unknown },};
#undef dirty#undef sc#undef unevict#undef mlock#undef lru#undef head
static void update_per_node_mf_stats(unsigned long pfn, enum mf_result result){ int nid = MAX_NUMNODES; struct memory_failure_stats *mf_stats = NULL;
nid = pfn_to_nid(pfn); if (unlikely(nid < 0 || nid >= MAX_NUMNODES)) { WARN_ONCE(1, "Memory failure: pfn=%#lx, invalid nid=%d", pfn, nid); return; }
mf_stats = &NODE_DATA(nid)->mf_stats; switch (result) { case MF_IGNORED: ++mf_stats->ignored; break; case MF_FAILED: ++mf_stats->failed; break; case MF_DELAYED: ++mf_stats->delayed; break; case MF_RECOVERED: ++mf_stats->recovered; break; default: WARN_ONCE(1, "Memory failure: mf_result=%d is not properly handled", result); break; } ++mf_stats->total;}
static bool panic_on_unrecoverable_mf(enum mf_action_page_type type, enum mf_result result){ if (!sysctl_panic_on_unrecoverable_mf) return false;
return type == MF_MSG_KERNEL && result == MF_IGNORED;}
/* * "Dirty/Clean" indication is not 100% accurate due to the possibility of * setting PG_dirty outside page lock. See also comment above set_page_dirty(). */static int action_result(unsigned long pfn, enum mf_action_page_type type, enum mf_result result){ trace_memory_failure_event(pfn, type, result);
if (type != MF_MSG_ALREADY_POISONED && type != MF_MSG_PFN_MAP) { num_poisoned_pages_inc(pfn); update_per_node_mf_stats(pfn, result); }
pr_err("%#lx: recovery action for %s: %s\n", pfn, action_page_types[type], action_name[result]);
if (panic_on_unrecoverable_mf(type, result)) panic("Memory failure: %#lx: unrecoverable page", pfn);
return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY;}
static int page_action(struct page_state *ps, struct page *p, unsigned long pfn){ int result;
/* page p should be unlocked after returning from ps->action(). */ result = ps->action(ps, p);
/* Could do more checks here if page looks ok */ /* * Could adjust zone counters here to correct for the missing page. */
return action_result(pfn, ps->type, result);}
static inline bool PageHWPoisonTakenOff(struct page *page){ return PageHWPoison(page) && page_private(page) == MAGIC_HWPOISON;}
void SetPageHWPoisonTakenOff(struct page *page){ set_page_private(page, MAGIC_HWPOISON);}
void ClearPageHWPoisonTakenOff(struct page *page){ if (PageHWPoison(page)) set_page_private(page, 0);}
/* * Return true if a page type of a given page is supported by hwpoison * mechanism (while handling could fail), otherwise false. This function * does not return true for hugetlb or device memory pages, so it's assumed * to be called only in the context where we never have such pages. */static inline bool HWPoisonHandlable(struct page *page, unsigned long flags){ if (PageSlab(page)) return false;
/* Soft offline could migrate movable_ops pages */ if ((flags & MF_SOFT_OFFLINE) && page_has_movable_ops(page)) return true;
return PageLRU(page) || is_free_buddy_page(page);}
/* * Positive identification of pages the hwpoison handler cannot recover: * pages owned by kernel internals with no userspace mapping to unmap, no * file mapping to invalidate, and no migration target. */static inline bool is_kernel_owned_page(struct page *page){ struct page *head; bool kernel_owned;
/* PG_reserved is a per-page flag, never set on a compound page. */ if (PageReserved(page)) return true;
/* * Page-type bits live only on the head page, so resolve any tail * first. The check takes no refcount; recheck the head afterwards * so a concurrent split or compound free cannot leave us trusting * a stale view. A residual free->alloc->free cannot be closed here * (frozen slab and large-kmalloc pages cannot be pinned), but is * harmless: where a wrong verdict could panic, memory_failure() has * already set PageHWPoison, which bars the page from the allocator. */retry: head = compound_head(page); kernel_owned = PageSlab(head) || PageTable(head) || PageLargeKmalloc(head); if (head != compound_head(page)) goto retry; return kernel_owned;}
static int __get_hwpoison_page(struct page *page, unsigned long flags){ struct folio *folio = page_folio(page); int ret = 0; bool hugetlb = false;
ret = get_hwpoison_hugetlb_folio(folio, &hugetlb, false); if (hugetlb) { /* Make sure hugetlb demotion did not happen from under us. */ if (folio == page_folio(page)) return ret; if (ret > 0) { folio_put(folio); folio = page_folio(page); } }
/* * This check prevents from calling folio_try_get() for any * unsupported type of folio in order to reduce the risk of unexpected * races caused by taking a folio refcount. */ if (!HWPoisonHandlable(&folio->page, flags)) return -EBUSY;
if (folio_try_get(folio)) { if (folio == page_folio(page)) return 1;
pr_info("%#lx cannot catch tail\n", page_to_pfn(page)); folio_put(folio); }
return 0;}
#define GET_PAGE_MAX_RETRY_NUM 3
static int get_any_page(struct page *p, unsigned long flags){ int ret = 0, pass = 0; bool count_increased = false;
if (flags & MF_COUNT_INCREASED) count_increased = true;
/* * Page types we know are kernel-owned and cannot be recovered. * Short-circuit before the shake_page() / retry loop, which * cannot turn any of these into something HWPoisonHandlable(). * Drop the caller's reference if MF_COUNT_INCREASED took one. */ if (is_kernel_owned_page(p)) { if (count_increased) put_page(p); ret = -ENOTRECOVERABLE; goto out; }
try_again: if (!count_increased) { ret = __get_hwpoison_page(p, flags); if (!ret) { if (page_count(p)) { /* We raced with an allocation, retry. */ if (pass++ < GET_PAGE_MAX_RETRY_NUM) goto try_again; ret = -EBUSY; } else if (!PageHuge(p) && !is_free_buddy_page(p)) { /* We raced with put_page, retry. */ if (pass++ < GET_PAGE_MAX_RETRY_NUM) goto try_again; ret = -EIO; } goto out; } else if (ret == -EBUSY) { /* * We raced with (possibly temporary) unhandlable * page, retry. */ if (pass++ < GET_PAGE_MAX_RETRY_NUM) { shake_page(p); goto try_again; } ret = -EIO; goto out; } }
if (PageHuge(p) || HWPoisonHandlable(p, flags)) { ret = 1; } else { /* * A page we cannot handle. Check whether we can turn * it into something we can handle. */ if (pass++ < GET_PAGE_MAX_RETRY_NUM) { put_page(p); shake_page(p); count_increased = false; goto try_again; } put_page(p); ret = -EIO; }out: if (ret == -EIO || ret == -ENOTRECOVERABLE) pr_err("%#lx: unhandlable page.\n", page_to_pfn(p));
return ret;}
static int __get_unpoison_page(struct page *page){ struct folio *folio = page_folio(page); int ret = 0; bool hugetlb = false;
ret = get_hwpoison_hugetlb_folio(folio, &hugetlb, true); if (hugetlb) { /* Make sure hugetlb demotion did not happen from under us. */ if (folio == page_folio(page)) return ret; if (ret > 0) folio_put(folio); }
/* * PageHWPoisonTakenOff pages are not only marked as PG_hwpoison, * but also isolated from buddy freelist, so need to identify the * state and have to cancel both operations to unpoison. */ if (PageHWPoisonTakenOff(page)) return -EHWPOISON;
return get_page_unless_zero(page) ? 1 : 0;}
/** * get_hwpoison_page() - Get refcount for memory error handling * @p: Raw error page (hit by memory error) * @flags: Flags controlling behavior of error handling * * get_hwpoison_page() takes a page refcount of an error page to handle memory * error on it, after checking that the error page is in a well-defined state * (defined as a page-type we can successfully handle the memory error on it, * such as LRU page and hugetlb page). * * Memory error handling could be triggered at any time on any type of page, * so it's prone to race with typical memory management lifecycle (like * allocation and free). So to avoid such races, get_hwpoison_page() takes * extra care for the error page's state (as done in __get_hwpoison_page()), * and has some retry logic in get_any_page(). * * When called from unpoison_memory(), the caller should already ensure that * the given page has PG_hwpoison. So it's never reused for other page * allocations, and __get_unpoison_page() never races with them. * * Return: 0 on failure or free buddy (hugetlb) page, * 1 on success for in-use pages in a well-defined state, * -EIO for pages on which we can not handle memory errors, * -EBUSY when get_hwpoison_page() has raced with page lifecycle * operations like allocation and free, * -EHWPOISON when the page is hwpoisoned and taken off from buddy, * -ENOTRECOVERABLE for kernel-owned pages identified by * is_kernel_owned_page() (PG_reserved, slab, * page-table, large-kmalloc) that the handler cannot recover. */static int get_hwpoison_page(struct page *p, unsigned long flags){ int ret;
zone_pcp_disable(page_zone(p)); if (flags & MF_UNPOISON) ret = __get_unpoison_page(p); else ret = get_any_page(p, flags); zone_pcp_enable(page_zone(p));
return ret;}
/* * The caller must guarantee the folio isn't large folio, except hugetlb. * try_to_unmap() can't handle it. */int unmap_poisoned_folio(struct folio *folio, unsigned long pfn, bool must_kill){ enum ttu_flags ttu = TTU_IGNORE_MLOCK | TTU_SYNC | TTU_HWPOISON; struct address_space *mapping;
if (folio_test_swapcache(folio)) { pr_err("%#lx: keeping poisoned page in swap cache\n", pfn); ttu &= ~TTU_HWPOISON; }
/* * Propagate the dirty bit from PTEs to struct page first, because we * need this to decide if we should kill or just drop the page. * XXX: the dirty test could be racy: set_page_dirty() may not always * be called inside page lock (it's recommended but not enforced). */ mapping = folio_mapping(folio); if (!must_kill && !folio_test_dirty(folio) && mapping && mapping_can_writeback(mapping)) { if (folio_mkclean(folio)) { folio_set_dirty(folio); } else { ttu &= ~TTU_HWPOISON; pr_info("%#lx: corrupted page was clean: dropped without side effects\n", pfn); } }
if (folio_test_hugetlb(folio) && !folio_test_anon(folio)) { /* * For hugetlb folios in shared mappings, try_to_unmap * could potentially call huge_pmd_unshare. Because of * this, take semaphore in write mode here and set * TTU_RMAP_LOCKED to indicate we have taken the lock * at this higher level. */ mapping = hugetlb_folio_mapping_lock_write(folio); if (!mapping) { pr_info("%#lx: could not lock mapping for mapped hugetlb folio\n", folio_pfn(folio)); return -EBUSY; }
try_to_unmap(folio, ttu|TTU_RMAP_LOCKED); i_mmap_unlock_write(mapping); } else { try_to_unmap(folio, ttu); }
return folio_mapped(folio) ? -EBUSY : 0;}
/* * Do all that is necessary to remove user space mappings. Unmap * the pages and send SIGBUS to the processes if the data was dirty. */static bool hwpoison_user_mappings(struct folio *folio, struct page *p, unsigned long pfn, int flags){ LIST_HEAD(tokill); bool unmap_success; bool forcekill; bool mlocked = folio_test_mlocked(folio);
/* * Here we are interested only in user-mapped pages, so skip any * other types of pages. */ if (folio_test_reserved(folio) || folio_test_slab(folio) || folio_test_pgtable(folio) || folio_test_offline(folio)) return true; if (!(folio_test_lru(folio) || folio_test_hugetlb(folio))) return true;
/* * This check implies we don't kill processes if their pages * are in the swap cache early. Those are always late kills. */ if (!folio_mapped(folio)) return true;
/* * First collect all the processes that have the page * mapped in dirty form. This has to be done before try_to_unmap, * because ttu takes the rmap data structures down. */ collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED);
unmap_success = !unmap_poisoned_folio(folio, pfn, flags & MF_MUST_KILL); if (!unmap_success) pr_err("%#lx: failed to unmap page (folio mapcount=%d)\n", pfn, folio_mapcount(folio));
/* * try_to_unmap() might put mlocked page in lru cache, so call * shake_page() again to ensure that it's flushed. */ if (mlocked) shake_folio(folio);
/* * Now that the dirty bit has been propagated to the * struct page and all unmaps done we can decide if * killing is needed or not. Only kill when the page * was dirty or the process is not restartable, * otherwise the tokill list is merely * freed. When there was a problem unmapping earlier * use a more force-full uncatchable kill to prevent * any accesses to the poisoned memory. */ forcekill = folio_test_dirty(folio) || (flags & MF_MUST_KILL) || !unmap_success; kill_procs(&tokill, forcekill, pfn, flags);
return unmap_success;}
static int identify_page_state(unsigned long pfn, struct page *p, unsigned long page_flags){ struct page_state *ps;
/* * The first check uses the current page flags which may not have any * relevant information. The second check with the saved page flags is * carried out only if the first check can't determine the page status. */ for (ps = error_states;; ps++) if ((p->flags.f & ps->mask) == ps->res) break;
page_flags |= (p->flags.f & (1UL << PG_dirty));
if (!ps->mask) for (ps = error_states;; ps++) if ((page_flags & ps->mask) == ps->res) break; return page_action(ps, p, pfn);}
/* * When 'release' is 'false', it means that if thp split has failed, * there is still more to do, hence the page refcount we took earlier * is still needed. */static int try_to_split_thp_page(struct page *page, unsigned int new_order, bool release){ int ret;
lock_page(page); ret = split_huge_page_to_order(page, new_order); unlock_page(page);
if (ret && release) put_page(page);
return ret;}
static void unmap_and_kill(struct list_head *to_kill, unsigned long pfn, struct address_space *mapping, pgoff_t index, int flags){ struct to_kill *tk; unsigned long size = 0;
list_for_each_entry(tk, to_kill, nd) if (tk->size_shift) size = max(size, 1UL << tk->size_shift);
if (size) { /* * Unmap the largest mapping to avoid breaking up device-dax * mappings which are constant size. The actual size of the * mapping being torn down is communicated in siginfo, see * kill_proc() */ loff_t start = ((loff_t)index << PAGE_SHIFT) & ~(size - 1);
unmap_mapping_range(mapping, start, size, 0); }
kill_procs(to_kill, !!(flags & MF_MUST_KILL), pfn, flags);}
/* * Only dev_pagemap pages get here, such as fsdax when the filesystem * either do not claim or fails to claim a hwpoison event, or devdax. * The fsdax pages are initialized per base page, and the devdax pages * could be initialized either as base pages, or as compound pages with * vmemmap optimization enabled. Devdax is simplistic in its dealing with * hwpoison, such that, if a subpage of a compound page is poisoned, * simply mark the compound head page is by far sufficient. */static int mf_generic_kill_procs(unsigned long long pfn, int flags, struct dev_pagemap *pgmap){ struct folio *folio = pfn_folio(pfn); LIST_HEAD(to_kill); dax_entry_t cookie; int rc = 0;
/* * Prevent the inode from being freed while we are interrogating * the address_space, typically this would be handled by * lock_page(), but dax pages do not use the page lock. This * also prevents changes to the mapping of this pfn until * poison signaling is complete. */ cookie = dax_lock_folio(folio); if (!cookie) return -EBUSY;
if (hwpoison_filter(&folio->page)) { rc = -EOPNOTSUPP; goto unlock; }
switch (pgmap->type) { case MEMORY_DEVICE_PRIVATE: case MEMORY_DEVICE_COHERENT: /* * TODO: Handle device pages which may need coordination * with device-side memory. */ rc = -ENXIO; goto unlock; default: break; }
/* * Use this flag as an indication that the dax page has been * remapped UC to prevent speculative consumption of poison. */ SetPageHWPoison(&folio->page);
/* * Unlike System-RAM there is no possibility to swap in a * different physical page at a given virtual address, so all * userspace consumption of ZONE_DEVICE memory necessitates * SIGBUS (i.e. MF_MUST_KILL) */ flags |= MF_ACTION_REQUIRED | MF_MUST_KILL; collect_procs(folio, &folio->page, &to_kill, true);
unmap_and_kill(&to_kill, pfn, folio->mapping, folio->index, flags);unlock: dax_unlock_folio(folio, cookie); return rc;}
#ifdef CONFIG_FS_DAX/** * mf_dax_kill_procs - Collect and kill processes who are using this file range * @mapping: address_space of the file in use * @index: start pgoff of the range within the file * @count: length of the range, in unit of PAGE_SIZE * @mf_flags: memory failure flags */int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index, unsigned long count, int mf_flags){ LIST_HEAD(to_kill); dax_entry_t cookie; struct page *page; size_t end = index + count; bool pre_remove = mf_flags & MF_MEM_PRE_REMOVE;
mf_flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
for (; index < end; index++) { page = NULL; cookie = dax_lock_mapping_entry(mapping, index, &page); if (!cookie) return -EBUSY; if (!page) goto unlock;
if (!pre_remove) SetPageHWPoison(page);
/* * The pre_remove case is revoking access, the memory is still * good and could theoretically be put back into service. */ collect_procs_fsdax(page, mapping, index, &to_kill, pre_remove); unmap_and_kill(&to_kill, page_to_pfn(page), mapping, index, mf_flags);unlock: dax_unlock_mapping_entry(mapping, index, cookie); } return 0;}EXPORT_SYMBOL_GPL(mf_dax_kill_procs);#endif /* CONFIG_FS_DAX */
#ifdef CONFIG_HUGETLB_PAGE
/* * Struct raw_hwp_page represents information about "raw error page", * constructing singly linked list from ->_hugetlb_hwpoison field of folio. */struct raw_hwp_page { struct llist_node node; struct page *page;};
static inline struct llist_head *raw_hwp_list_head(struct folio *folio){ return (struct llist_head *)&folio->_hugetlb_hwpoison;}
bool is_raw_hwpoison_page_in_hugepage(struct page *page){ struct llist_head *raw_hwp_head; struct raw_hwp_page *p; struct folio *folio = page_folio(page); bool ret = false;
if (!folio_test_hwpoison(folio)) return false;
if (!folio_test_hugetlb(folio)) return PageHWPoison(page);
/* * When RawHwpUnreliable is set, kernel lost track of which subpages * are HWPOISON. So return as if ALL subpages are HWPOISONed. */ if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return true;
mutex_lock(&mf_mutex);
raw_hwp_head = raw_hwp_list_head(folio); llist_for_each_entry(p, raw_hwp_head->first, node) { if (page == p->page) { ret = true; break; } }
mutex_unlock(&mf_mutex);
return ret;}
static unsigned long __folio_free_raw_hwp(struct folio *folio, bool move_flag){ struct llist_node *head; struct raw_hwp_page *p, *next; unsigned long count = 0;
head = llist_del_all(raw_hwp_list_head(folio)); llist_for_each_entry_safe(p, next, head, node) { if (move_flag) SetPageHWPoison(p->page); else num_poisoned_pages_sub(page_to_pfn(p->page), 1); kfree(p); count++; } return count;}
#define MF_HUGETLB_FREED 0 /* freed hugepage */#define MF_HUGETLB_IN_USED 1 /* in-use hugepage */#define MF_HUGETLB_NON_HUGEPAGE 2 /* not a hugepage */#define MF_HUGETLB_FOLIO_PRE_POISONED 3 /* folio already poisoned */#define MF_HUGETLB_PAGE_PRE_POISONED 4 /* exact page already poisoned */#define MF_HUGETLB_RETRY 5 /* hugepage is busy, retry *//* * Set hugetlb folio as hwpoisoned, update folio private raw hwpoison list * to keep track of the poisoned pages. */static int hugetlb_update_hwpoison(struct folio *folio, struct page *page){ struct llist_head *head; struct raw_hwp_page *raw_hwp; struct raw_hwp_page *p; int ret = folio_test_set_hwpoison(folio) ? MF_HUGETLB_FOLIO_PRE_POISONED : 0;
/* * Once the hwpoison hugepage has lost reliable raw error info, * there is little meaning to keep additional error info precisely, * so skip to add additional raw error info. */ if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return MF_HUGETLB_FOLIO_PRE_POISONED; head = raw_hwp_list_head(folio); llist_for_each_entry(p, head->first, node) { if (p->page == page) return MF_HUGETLB_PAGE_PRE_POISONED; }
raw_hwp = kmalloc_obj(struct raw_hwp_page, GFP_ATOMIC); if (raw_hwp) { raw_hwp->page = page; llist_add(&raw_hwp->node, head); } else { /* * Failed to save raw error info. We no longer trace all * hwpoisoned subpages, and we need refuse to free/dissolve * this hwpoisoned hugepage. */ folio_set_hugetlb_raw_hwp_unreliable(folio); /* * Once hugetlb_raw_hwp_unreliable is set, raw_hwp_page is not * used any more, so free it. */ __folio_free_raw_hwp(folio, false); } return ret;}
static unsigned long folio_free_raw_hwp(struct folio *folio, bool move_flag){ /* * hugetlb_vmemmap_optimized hugepages can't be freed because struct * pages for tail pages are required but they don't exist. */ if (move_flag && folio_test_hugetlb_vmemmap_optimized(folio)) return 0;
/* * hugetlb_raw_hwp_unreliable hugepages shouldn't be unpoisoned by * definition. */ if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return 0;
return __folio_free_raw_hwp(folio, move_flag);}
void folio_clear_hugetlb_hwpoison(struct folio *folio){ if (folio_test_hugetlb_raw_hwp_unreliable(folio)) return; if (folio_test_hugetlb_vmemmap_optimized(folio)) return; folio_clear_hwpoison(folio); folio_free_raw_hwp(folio, true);}
static int get_huge_page_for_hwpoison(unsigned long pfn, int flags, bool *migratable_cleared){ struct page *page = pfn_to_page(pfn); struct folio *folio; bool count_increased = false; int ret, rc;
spin_lock_irq(&hugetlb_lock); folio = page_folio(page); if (!folio_test_hugetlb(folio)) { ret = MF_HUGETLB_NON_HUGEPAGE; goto out_unlock; } else if (flags & MF_COUNT_INCREASED) { ret = MF_HUGETLB_IN_USED; count_increased = true; } else if (folio_test_hugetlb_freed(folio)) { ret = MF_HUGETLB_FREED; } else if (folio_test_hugetlb_migratable(folio)) { if (folio_try_get(folio)) { ret = MF_HUGETLB_IN_USED; count_increased = true; } else { ret = MF_HUGETLB_FREED; } } else { ret = MF_HUGETLB_RETRY; if (!(flags & MF_NO_RETRY)) goto out_unlock; }
rc = hugetlb_update_hwpoison(folio, page); if (rc >= MF_HUGETLB_FOLIO_PRE_POISONED) { ret = rc; goto out_unlock; }
/* * Clearing hugetlb_migratable for hwpoisoned hugepages to prevent them * from being migrated by memory hotremove. */ if (count_increased && folio_test_hugetlb_migratable(folio)) { folio_clear_hugetlb_migratable(folio); *migratable_cleared = true; }
spin_unlock_irq(&hugetlb_lock); return ret;out_unlock: spin_unlock_irq(&hugetlb_lock); if (count_increased) folio_put(folio); return ret;}
/* * Taking refcount of hugetlb pages needs extra care about race conditions * with basic operations like hugepage allocation/free/demotion. * So some of prechecks for hwpoison (pinning, and testing/setting * PageHWPoison) should be done in single hugetlb_lock range. * Returns: * 0 - recovered * -ENOENT - no hugetlb page * -EBUSY - not recovered * -EOPNOTSUPP - hwpoison_filter'ed * -EHWPOISON - folio or exact page already poisoned * -EFAULT - kill_accessing_process finds current->mm null */static int try_memory_failure_hugetlb(unsigned long pfn, int flags){ int res, rv; struct page *p = pfn_to_page(pfn); struct folio *folio; unsigned long page_flags; bool migratable_cleared = false;
retry: res = get_huge_page_for_hwpoison(pfn, flags, &migratable_cleared); switch (res) { case MF_HUGETLB_NON_HUGEPAGE: /* fallback to normal page handling */ return -ENOENT; case MF_HUGETLB_RETRY: if (!(flags & MF_NO_RETRY)) { flags |= MF_NO_RETRY; goto retry; } return action_result(pfn, MF_MSG_GET_HWPOISON, MF_IGNORED); case MF_HUGETLB_FOLIO_PRE_POISONED: case MF_HUGETLB_PAGE_PRE_POISONED: rv = -EHWPOISON; if (flags & MF_ACTION_REQUIRED) rv = kill_accessing_process(current, pfn, flags); if (res == MF_HUGETLB_PAGE_PRE_POISONED) action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); else action_result(pfn, MF_MSG_HUGE, MF_FAILED); return rv; default: WARN_ON((res != MF_HUGETLB_FREED) && (res != MF_HUGETLB_IN_USED)); break; }
folio = page_folio(p); folio_lock(folio);
if (hwpoison_filter(p)) { folio_clear_hugetlb_hwpoison(folio); if (migratable_cleared) folio_set_hugetlb_migratable(folio); folio_unlock(folio); if (res == MF_HUGETLB_IN_USED) folio_put(folio); return -EOPNOTSUPP; }
/* * Handling free hugepage. The possible race with hugepage allocation * or demotion can be prevented by PageHWPoison flag. */ if (res == MF_HUGETLB_FREED) { folio_unlock(folio); if (__page_handle_poison(p) > 0) { page_ref_inc(p); res = MF_RECOVERED; } else { res = MF_FAILED; } return action_result(pfn, MF_MSG_FREE_HUGE, res); }
page_flags = folio->flags.f;
if (!hwpoison_user_mappings(folio, p, pfn, flags)) { folio_unlock(folio); return action_result(pfn, MF_MSG_UNMAP_FAILED, MF_FAILED); }
return identify_page_state(pfn, p, page_flags);}
#elsestatic inline int try_memory_failure_hugetlb(unsigned long pfn, int flags){ return -ENOENT;}
static inline unsigned long folio_free_raw_hwp(struct folio *folio, bool flag){ return 0;}#endif /* CONFIG_HUGETLB_PAGE */
/* Drop the extra refcount in case we come from madvise() */static void put_ref_page(unsigned long pfn, int flags){ if (!(flags & MF_COUNT_INCREASED)) return;
put_page(pfn_to_page(pfn));}
static int memory_failure_dev_pagemap(unsigned long pfn, int flags, struct dev_pagemap *pgmap){ int rc = -ENXIO;
/* device metadata space is not recoverable */ if (!pgmap_pfn_valid(pgmap, pfn)) goto out;
/* * Call driver's implementation to handle the memory failure, otherwise * fall back to generic handler. */ if (pgmap_has_memory_failure(pgmap)) { rc = pgmap->ops->memory_failure(pgmap, pfn, 1, flags); /* * Fall back to generic handler too if operation is not * supported inside the driver/device/filesystem. */ if (rc != -EOPNOTSUPP) goto out; }
rc = mf_generic_kill_procs(pfn, flags, pgmap);out: /* drop pgmap ref acquired in caller */ put_dev_pagemap(pgmap); if (rc != -EOPNOTSUPP) action_result(pfn, MF_MSG_DAX, rc ? MF_FAILED : MF_RECOVERED); return rc;}
/* * The calling condition is as such: thp split failed, page might have * been RDMA pinned, not much can be done for recovery. * But a SIGBUS should be delivered with vaddr provided so that the user * application has a chance to recover. Also, application processes' * election for MCE early killed will be honored. */static void kill_procs_now(struct page *p, unsigned long pfn, int flags, struct folio *folio){ LIST_HEAD(tokill);
folio_lock(folio); collect_procs(folio, p, &tokill, flags & MF_ACTION_REQUIRED); folio_unlock(folio);
kill_procs(&tokill, true, pfn, flags);}
int register_pfn_address_space(struct pfn_address_space *pfn_space){ guard(mutex)(&pfn_space_lock);
if (!pfn_space->pfn_to_vma_pgoff) return -EINVAL;
if (interval_tree_iter_first(&pfn_space_itree, pfn_space->node.start, pfn_space->node.last)) return -EBUSY;
interval_tree_insert(&pfn_space->node, &pfn_space_itree);
return 0;}EXPORT_SYMBOL_GPL(register_pfn_address_space);
void unregister_pfn_address_space(struct pfn_address_space *pfn_space){ guard(mutex)(&pfn_space_lock);
if (interval_tree_iter_first(&pfn_space_itree, pfn_space->node.start, pfn_space->node.last)) interval_tree_remove(&pfn_space->node, &pfn_space_itree);}EXPORT_SYMBOL_GPL(unregister_pfn_address_space);
static void add_to_kill_pgoff(struct task_struct *tsk, struct vm_area_struct *vma, struct list_head *to_kill, pgoff_t pgoff){ struct to_kill *tk;
tk = kmalloc_obj(*tk, GFP_ATOMIC); if (!tk) { pr_info("Unable to kill proc %d\n", tsk->pid); return; }
/* Check for pgoff not backed by struct page */ tk->addr = vma_filebacked_address(vma, pgoff, 1); tk->size_shift = PAGE_SHIFT;
if (tk->addr == -EFAULT) pr_info("Unable to find address %lx in %s\n", pgoff, tsk->comm);
get_task_struct(tsk); tk->tsk = tsk; list_add_tail(&tk->nd, to_kill);}
/* * Collect processes when the error hit a PFN not backed by struct page. */static void collect_procs_pfn(struct pfn_address_space *pfn_space, unsigned long pfn, struct list_head *to_kill){ struct vm_area_struct *vma; struct task_struct *tsk; struct address_space *mapping = pfn_space->mapping;
i_mmap_lock_read(mapping); rcu_read_lock(); for_each_process(tsk) { struct task_struct *t = tsk;
t = task_early_kill(tsk, true); if (!t) continue; mapping_rmap_tree_foreach(vma, mapping, 0, ULONG_MAX) { pgoff_t pgoff;
if (vma->vm_mm == t->mm && !pfn_space->pfn_to_vma_pgoff(vma, pfn, &pgoff)) add_to_kill_pgoff(t, vma, to_kill, pgoff); } } rcu_read_unlock(); i_mmap_unlock_read(mapping);}
/** * memory_failure_pfn - Handle memory failure on a page not backed by * struct page. * @pfn: Page Number of the corrupted page * @flags: fine tune action taken * * Return: * 0 - success, * -EBUSY - Page PFN does not belong to any address space mapping. */static int memory_failure_pfn(unsigned long pfn, int flags){ struct interval_tree_node *node; LIST_HEAD(tokill);
scoped_guard(mutex, &pfn_space_lock) { bool mf_handled = false;
/* * Modules registers with MM the address space mapping to * the device memory they manage. Iterate to identify * exactly which address space has mapped to this failing * PFN. */ for (node = interval_tree_iter_first(&pfn_space_itree, pfn, pfn); node; node = interval_tree_iter_next(node, pfn, pfn)) { struct pfn_address_space *pfn_space = container_of(node, struct pfn_address_space, node);
collect_procs_pfn(pfn_space, pfn, &tokill);
mf_handled = true; }
if (!mf_handled) return action_result(pfn, MF_MSG_PFN_MAP, MF_IGNORED); }
/* * Unlike System-RAM there is no possibility to swap in a different * physical page at a given virtual address, so all userspace * consumption of direct PFN memory necessitates SIGBUS (i.e. * MF_MUST_KILL) */ flags |= MF_ACTION_REQUIRED | MF_MUST_KILL;
kill_procs(&tokill, true, pfn, flags);
return action_result(pfn, MF_MSG_PFN_MAP, MF_RECOVERED);}
/** * memory_failure - Handle memory failure of a page. * @pfn: Page Number of the corrupted page * @flags: fine tune action taken * * This function is called by the low level machine check code * of an architecture when it detects hardware memory corruption * of a page. It tries its best to recover, which includes * dropping pages, killing processes etc. * * The function is primarily of use for corruptions that * happen outside the current execution context (e.g. when * detected by a background scrubber) * * Must run in process context (e.g. a work queue) with interrupts * enabled and no spinlocks held. * * Return: * 0 - success, * -ENXIO - memory not managed by the kernel * -EOPNOTSUPP - hwpoison_filter() filtered the error event, * -EHWPOISON - the page was already poisoned, potentially * kill process, * other negative values - failure. */int memory_failure(unsigned long pfn, int flags){ struct page *p; struct folio *folio; struct dev_pagemap *pgmap; int res = 0; unsigned long page_flags; bool retry = true;
if (!sysctl_memory_failure_recovery) panic("Memory failure on page %lx", pfn);
mutex_lock(&mf_mutex);
if (!(flags & MF_SW_SIMULATED)) hw_memory_failure = true;
p = pfn_to_online_page(pfn); if (!p) { res = arch_memory_failure(pfn, flags); if (res == 0) goto unlock_mutex;
if (!pfn_valid(pfn) && !arch_is_platform_page(PFN_PHYS(pfn))) { /* * The PFN is not backed by struct page. */ res = memory_failure_pfn(pfn, flags); goto unlock_mutex; }
if (pfn_valid(pfn)) { pgmap = get_dev_pagemap(pfn); put_ref_page(pfn, flags); if (pgmap) { res = memory_failure_dev_pagemap(pfn, flags, pgmap); goto unlock_mutex; } } pr_err("%#lx: memory outside kernel control\n", pfn); res = -ENXIO; goto unlock_mutex; }
try_again: res = try_memory_failure_hugetlb(pfn, flags); /* * -ENOENT means the page we found is not hugetlb, so proceed with normal page handling */ if (res != -ENOENT) goto unlock_mutex;
if (TestSetPageHWPoison(p)) { res = -EHWPOISON; if (flags & MF_ACTION_REQUIRED) res = kill_accessing_process(current, pfn, flags); if (flags & MF_COUNT_INCREASED) put_page(p); action_result(pfn, MF_MSG_ALREADY_POISONED, MF_FAILED); goto unlock_mutex; }
/* * We need/can do nothing about count=0 pages. * 1) it's a free page, and therefore in safe hand: * check_new_page() will be the gate keeper. * 2) it's part of a non-compound high order page. * Implies some kernel user: cannot stop them from * R/W the page; let's pray that the page has been * used and will be freed some time later. * In fact it's dangerous to directly bump up page count from 0, * that may make page_ref_freeze()/page_ref_unfreeze() mismatch. */ res = get_hwpoison_page(p, flags); switch (res) { case 0: if (is_free_buddy_page(p)) { if (take_page_off_buddy(p)) { page_ref_inc(p); res = MF_RECOVERED; } else { /* We lost the race, try again */ if (retry) { ClearPageHWPoison(p); retry = false; goto try_again; } res = MF_FAILED; } res = action_result(pfn, MF_MSG_BUDDY, res); } else { res = action_result(pfn, MF_MSG_KERNEL_HIGH_ORDER, MF_IGNORED); } goto unlock_mutex; case 1: /* Got a refcount on a handlable page. */ break; case -ENOTRECOVERABLE: /* * Stable unhandlable kernel-owned page (PG_reserved, * slab, page tables, large-kmalloc). * No recovery possible. */ res = action_result(pfn, MF_MSG_KERNEL, MF_IGNORED); goto unlock_mutex; default: /* Transient lifecycle race with the page allocator. */ res = action_result(pfn, MF_MSG_GET_HWPOISON, MF_IGNORED); goto unlock_mutex; }
folio = page_folio(p);
/* filter pages that are protected from hwpoison test by users */ folio_lock(folio); if (hwpoison_filter(p)) { ClearPageHWPoison(p); folio_unlock(folio); folio_put(folio); res = -EOPNOTSUPP; goto unlock_mutex; } folio_unlock(folio);
if (folio_test_large(folio)) { const int new_order = min_order_for_split(folio); int err;
/* * The flag must be set after the refcount is bumped * otherwise it may race with THP split. * And the flag can't be set in get_hwpoison_page() since * it is called by soft offline too and it is just called * for !MF_COUNT_INCREASED. So here seems to be the best * place. * * Don't need care about the above error handling paths for * get_hwpoison_page() since they handle either free page * or unhandlable page. The refcount is bumped iff the * page is a valid handlable page. */ folio_set_has_hwpoisoned(folio); err = try_to_split_thp_page(p, new_order, /* release= */ false); /* * If splitting a folio to order-0 fails, kill the process. * Split the folio regardless to minimize unusable pages. * Because the memory failure code cannot handle large * folios, this split is always treated as if it failed. */ if (err || new_order) { /* get folio again in case the original one is split */ folio = page_folio(p); res = -EHWPOISON; kill_procs_now(p, pfn, flags, folio); put_page(p); action_result(pfn, MF_MSG_UNSPLIT_THP, MF_FAILED); goto unlock_mutex; } VM_BUG_ON_PAGE(!page_count(p), p); folio = page_folio(p); }
/* * We ignore non-LRU pages for good reasons. * - PG_locked is only well defined for LRU pages and a few others * - to avoid races with __SetPageLocked() * - to avoid races with __SetPageSlab*() (and more non-atomic ops) * The check (unnecessarily) ignores LRU pages being isolated and * walked by the page reclaim code, however that's not a big loss. */ shake_folio(folio);
folio_lock(folio);
/* * We're only intended to deal with the non-Compound page here. * The page cannot become compound pages again as folio has been * split and extra refcnt is held. */ WARN_ON(folio_test_large(folio));
/* * We use page flags to determine what action should be taken, but * the flags can be modified by the error containment action. One * example is an mlocked page, where PG_mlocked is cleared by * folio_remove_rmap_*() in try_to_unmap_one(). So to determine page * status correctly, we save a copy of the page flags at this time. */ page_flags = folio->flags.f;
/* * __munlock_folio() may clear a writeback folio's LRU flag without * the folio lock. We need to wait for writeback completion for this * folio or it may trigger a vfs BUG while evicting inode. */ if (!folio_test_lru(folio) && !folio_test_writeback(folio)) goto identify_page_state;
/* * It's very difficult to mess with pages currently under IO * and in many cases impossible, so we just avoid it here. */ folio_wait_writeback(folio);
/* * Now take care of user space mappings. * Abort on fail: __filemap_remove_folio() assumes unmapped page. */ if (!hwpoison_user_mappings(folio, p, pfn, flags)) { res = action_result(pfn, MF_MSG_UNMAP_FAILED, MF_FAILED); goto unlock_page; }
/* * Torn down by someone else? */ if (folio_test_lru(folio) && !folio_test_swapcache(folio) && folio->mapping == NULL) { res = action_result(pfn, MF_MSG_TRUNCATED_LRU, MF_IGNORED); goto unlock_page; }
identify_page_state: res = identify_page_state(pfn, p, page_flags); mutex_unlock(&mf_mutex); return res;unlock_page: folio_unlock(folio);unlock_mutex: mutex_unlock(&mf_mutex); return res;}EXPORT_SYMBOL_GPL(memory_failure);
#define MEMORY_FAILURE_FIFO_ORDER 4#define MEMORY_FAILURE_FIFO_SIZE (1 << MEMORY_FAILURE_FIFO_ORDER)
struct memory_failure_entry { unsigned long pfn; int flags;};
struct memory_failure_cpu { DECLARE_KFIFO(fifo, struct memory_failure_entry, MEMORY_FAILURE_FIFO_SIZE); raw_spinlock_t lock; struct work_struct work;};
static DEFINE_PER_CPU(struct memory_failure_cpu, memory_failure_cpu);
/** * memory_failure_queue - Schedule handling memory failure of a page. * @pfn: Page Number of the corrupted page * @flags: Flags for memory failure handling * * This function is called by the low level hardware error handler * when it detects hardware memory corruption of a page. It schedules * the recovering of error page, including dropping pages, killing * processes etc. * * The function is primarily of use for corruptions that * happen outside the current execution context (e.g. when * detected by a background scrubber) * * Can run in IRQ context. */void memory_failure_queue(unsigned long pfn, int flags){ struct memory_failure_cpu *mf_cpu; unsigned long proc_flags; bool buffer_overflow; struct memory_failure_entry entry = { .pfn = pfn, .flags = flags, };
mf_cpu = &get_cpu_var(memory_failure_cpu); raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags); buffer_overflow = !kfifo_put(&mf_cpu->fifo, entry); if (!buffer_overflow) schedule_work_on(smp_processor_id(), &mf_cpu->work); raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); put_cpu_var(memory_failure_cpu); if (buffer_overflow) pr_err("buffer overflow when queuing memory failure at %#lx\n", pfn);}EXPORT_SYMBOL_GPL(memory_failure_queue);
static void memory_failure_work_func(struct work_struct *work){ struct memory_failure_cpu *mf_cpu; struct memory_failure_entry entry = { 0, }; unsigned long proc_flags; int gotten;
mf_cpu = container_of(work, struct memory_failure_cpu, work); for (;;) { raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags); gotten = kfifo_get(&mf_cpu->fifo, &entry); raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); if (!gotten) break; if (entry.flags & MF_SOFT_OFFLINE) soft_offline_page(entry.pfn, entry.flags); else memory_failure(entry.pfn, entry.flags); }}
static int __init memory_failure_init(void){ struct memory_failure_cpu *mf_cpu; int cpu;
for_each_possible_cpu(cpu) { mf_cpu = &per_cpu(memory_failure_cpu, cpu); raw_spin_lock_init(&mf_cpu->lock); INIT_KFIFO(mf_cpu->fifo); INIT_WORK(&mf_cpu->work, memory_failure_work_func); }
register_sysctl_init("vm", memory_failure_table);
return 0;}core_initcall(memory_failure_init);
#undef pr_fmt#define pr_fmt(fmt) "Unpoison: " fmt#define unpoison_pr_info(fmt, pfn, rs) \({ \ if (__ratelimit(rs)) \ pr_info(fmt, pfn); \})
/** * unpoison_memory - Unpoison a previously poisoned page * @pfn: Page number of the to be unpoisoned page * * Software-unpoison a page that has been poisoned by * memory_failure() earlier. * * This is only done on the software-level, so it only works * for linux injected failures, not real hardware failures * * Returns 0 for success, otherwise -errno. */int unpoison_memory(unsigned long pfn){ struct folio *folio; struct page *p; int ret = -EBUSY, ghp; unsigned long count; bool huge = false; static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST);
p = pfn_to_online_page(pfn); if (!p) return -EIO; folio = page_folio(p);
mutex_lock(&mf_mutex);
if (hw_memory_failure) { unpoison_pr_info("%#lx: disabled after HW memory failure\n", pfn, &unpoison_rs); ret = -EOPNOTSUPP; goto unlock_mutex; }
if (is_huge_zero_folio(folio)) { unpoison_pr_info("%#lx: huge zero page is not supported\n", pfn, &unpoison_rs); ret = -EOPNOTSUPP; goto unlock_mutex; }
if (!PageHWPoison(p)) { unpoison_pr_info("%#lx: page was already unpoisoned\n", pfn, &unpoison_rs); goto unlock_mutex; }
if (folio_ref_count(folio) > 1) { unpoison_pr_info("%#lx: someone grabs the hwpoison page\n", pfn, &unpoison_rs); goto unlock_mutex; }
if (folio_test_slab(folio) || folio_test_pgtable(folio) || folio_test_reserved(folio) || folio_test_offline(folio)) goto unlock_mutex;
if (folio_mapped(folio)) { unpoison_pr_info("%#lx: someone maps the hwpoison page\n", pfn, &unpoison_rs); goto unlock_mutex; }
if (folio_mapping(folio)) { unpoison_pr_info("%#lx: the hwpoison page has non-NULL mapping\n", pfn, &unpoison_rs); goto unlock_mutex; }
ghp = get_hwpoison_page(p, MF_UNPOISON); if (!ghp) { if (folio_test_hugetlb(folio)) { huge = true; count = folio_free_raw_hwp(folio, false); if (count == 0) goto unlock_mutex; } ret = folio_test_clear_hwpoison(folio) ? 0 : -EBUSY; } else if (ghp < 0) { if (ghp == -EHWPOISON) { ret = put_page_back_buddy(p) ? 0 : -EBUSY; } else { ret = ghp; unpoison_pr_info("%#lx: failed to grab page\n", pfn, &unpoison_rs); } } else { if (folio_test_hugetlb(folio)) { huge = true; count = folio_free_raw_hwp(folio, false); if (count == 0) { folio_put(folio); goto unlock_mutex; } }
folio_put(folio); if (TestClearPageHWPoison(p)) { folio_put(folio); ret = 0; } }
unlock_mutex: mutex_unlock(&mf_mutex); if (!ret) { if (!huge) num_poisoned_pages_sub(pfn, 1); unpoison_pr_info("%#lx: software-unpoisoned page\n", page_to_pfn(p), &unpoison_rs); } return ret;}EXPORT_SYMBOL(unpoison_memory);
#undef pr_fmt#define pr_fmt(fmt) "Soft offline: " fmt
/* * soft_offline_in_use_page handles hugetlb-pages and non-hugetlb pages. * If the page is a non-dirty unmapped page-cache page, it simply invalidates. * If the page is mapped, it migrates the contents over. */static int soft_offline_in_use_page(struct page *page){ long ret = 0; unsigned long pfn = page_to_pfn(page); struct folio *folio = page_folio(page); char const *msg_page[] = {"page", "hugepage"}; bool huge = folio_test_hugetlb(folio); bool isolated; LIST_HEAD(pagelist); struct migration_target_control mtc = { .nid = NUMA_NO_NODE, .gfp_mask = GFP_USER | __GFP_MOVABLE | __GFP_RETRY_MAYFAIL, .reason = MR_MEMORY_FAILURE, };
if (!huge && folio_test_large(folio)) { const int new_order = min_order_for_split(folio);
/* * If new_order (target split order) is not 0, do not split the * folio at all to retain the still accessible large folio. * NOTE: if minimizing the number of soft offline pages is * preferred, split it to non-zero new_order like it is done in * memory_failure(). */ if (new_order || try_to_split_thp_page(page, /* new_order= */ 0, /* release= */ true)) { pr_info("%#lx: thp split failed\n", pfn); return -EBUSY; } folio = page_folio(page); }
folio_lock(folio); if (!huge) folio_wait_writeback(folio); if (PageHWPoison(page)) { folio_unlock(folio); folio_put(folio); pr_info("%#lx: page already poisoned\n", pfn); return 0; }
if (!huge && folio_test_lru(folio) && !folio_test_swapcache(folio)) /* * Try to invalidate first. This should work for * non dirty unmapped page cache pages. */ ret = mapping_evict_folio(folio_mapping(folio), folio); folio_unlock(folio);
if (ret) { pr_info("%#lx: invalidated\n", pfn); page_handle_poison(page, false, true); return 0; }
isolated = isolate_folio_to_list(folio, &pagelist);
/* * If we succeed to isolate the folio, we grabbed another refcount on * the folio, so we can safely drop the one we got from get_any_page(). * If we failed to isolate the folio, it means that we cannot go further * and we will return an error, so drop the reference we got from * get_any_page() as well. */ folio_put(folio);
if (isolated) { ret = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_MEMORY_FAILURE, NULL); if (!ret) { bool release = !huge;
if (!page_handle_poison(page, huge, release)) ret = -EBUSY; } else { if (!list_empty(&pagelist)) putback_movable_pages(&pagelist);
pr_info("%#lx: %s migration failed %ld, type %pGp\n", pfn, msg_page[huge], ret, &page->flags.f); if (ret > 0) ret = -EBUSY; } } else { pr_info("%#lx: %s isolation failed, page count %d, type %pGp\n", pfn, msg_page[huge], page_count(page), &page->flags.f); ret = -EBUSY; } return ret;}
/** * soft_offline_page - Soft offline a page. * @pfn: pfn to soft-offline * @flags: flags. Same as memory_failure(). * * Returns 0 on success, * -EOPNOTSUPP for hwpoison_filter() filtered the error event, or * disabled by /proc/sys/vm/enable_soft_offline, * < 0 otherwise negated errno. * * Soft offline a page, by migration or invalidation, * without killing anything. This is for the case when * a page is not corrupted yet (so it's still valid to access), * but has had a number of corrected errors and is better taken * out. * * The actual policy on when to do that is maintained by * user space. * * This should never impact any application or cause data loss, * however it might take some time. * * This is not a 100% solution for all memory, but tries to be * ``good enough'' for the majority of memory. */int soft_offline_page(unsigned long pfn, int flags){ int ret; bool try_again = true; struct page *page;
if (!pfn_valid(pfn)) { WARN_ON_ONCE(flags & MF_COUNT_INCREASED); return -ENXIO; }
/* Only online pages can be soft-offlined (esp., not ZONE_DEVICE). */ page = pfn_to_online_page(pfn); if (!page) { put_ref_page(pfn, flags); return -EIO; }
if (!sysctl_enable_soft_offline) { pr_info_once("disabled by /proc/sys/vm/enable_soft_offline\n"); put_ref_page(pfn, flags); return -EOPNOTSUPP; }
mutex_lock(&mf_mutex);
if (PageHWPoison(page)) { pr_info("%#lx: page already poisoned\n", pfn); put_ref_page(pfn, flags); mutex_unlock(&mf_mutex); return 0; }
retry: get_online_mems(); ret = get_hwpoison_page(page, flags | MF_SOFT_OFFLINE); put_online_mems();
if (hwpoison_filter(page)) { if (ret > 0) put_page(page);
mutex_unlock(&mf_mutex); return -EOPNOTSUPP; }
if (ret > 0) { ret = soft_offline_in_use_page(page); } else if (ret == 0) { if (!page_handle_poison(page, true, false)) { if (try_again) { try_again = false; flags &= ~MF_COUNT_INCREASED; goto retry; } ret = -EBUSY; } }
mutex_unlock(&mf_mutex);
return ret;}