123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121212221232124212521262127212821292130213121322133213421352136213721382139214021412142214321442145214621472148214921502151215221532154215521562157215821592160216121622163216421652166216721682169217021712172217321742175217621772178217921802181218221832184218521862187218821892190219121922193219421952196219721982199220022012202220322042205220622072208220922102211221222132214221522162217221822192220222122222223222422252226222722282229223022312232223322342235223622372238223922402241224222432244224522462247224822492250225122522253225422552256225722582259226022612262226322642265226622672268226922702271227222732274227522762277227822792280228122822283228422852286228722882289229022912292229322942295229622972298229923002301230223032304230523062307230823092310231123122313231423152316231723182319232023212322232323242325232623272328232923302331233223332334233523362337233823392340234123422343234423452346234723482349235023512352235323542355235623572358235923602361236223632364236523662367236823692370237123722373237423752376237723782379238023812382238323842385238623872388238923902391239223932394239523962397239823992400240124022403240424052406240724082409241024112412241324142415241624172418241924202421242224232424242524262427242824292430243124322433243424352436243724382439244024412442244324442445244624472448244924502451245224532454245524562457245824592460246124622463246424652466246724682469247024712472247324742475247624772478247924802481248224832484248524862487248824892490249124922493249424952496249724982499250025012502250325042505250625072508250925102511251225132514251525162517251825192520252125222523252425252526252725282529253025312532253325342535253625372538253925402541254225432544254525462547254825492550255125522553255425552556255725582559256025612562256325642565256625672568256925702571257225732574257525762577257825792580258125822583258425852586258725882589259025912592259325942595259625972598259926002601260226032604260526062607260826092610261126122613261426152616261726182619262026212622262326242625262626272628262926302631263226332634263526362637263826392640264126422643264426452646264726482649265026512652265326542655265626572658265926602661266226632664266526662667266826692670267126722673267426752676267726782679268026812682268326842685268626872688268926902691269226932694269526962697269826992700270127022703270427052706270727082709271027112712271327142715271627172718271927202721272227232724272527262727272827292730273127322733273427352736273727382739274027412742274327442745274627472748274927502751275227532754275527562757275827592760276127622763276427652766276727682769277027712772277327742775277627772778277927802781278227832784278527862787278827892790279127922793279427952796279727982799280028012802280328042805280628072808280928102811281228132814281528162817281828192820282128222823282428252826282728282829283028312832283328342835283628372838283928402841284228432844284528462847284828492850285128522853285428552856285728582859286028612862286328642865286628672868286928702871287228732874287528762877287828792880288128822883288428852886288728882889289028912892289328942895289628972898289929002901290229032904290529062907290829092910291129122913291429152916291729182919292029212922292329242925292629272928292929302931293229332934293529362937293829392940294129422943294429452946294729482949295029512952295329542955295629572958295929602961296229632964296529662967296829692970297129722973297429752976297729782979298029812982298329842985298629872988298929902991299229932994299529962997299829993000300130023003300430053006300730083009301030113012301330143015301630173018301930203021302230233024302530263027302830293030303130323033303430353036303730383039304030413042304330443045304630473048304930503051305230533054305530563057305830593060306130623063306430653066306730683069307030713072307330743075307630773078307930803081308230833084308530863087308830893090309130923093309430953096 |
- // SPDX-License-Identifier: GPL-2.0
- /*
- * Memory Migration functionality - linux/mm/migrate.c
- *
- * Copyright (C) 2006 Silicon Graphics, Inc., Christoph Lameter
- *
- * Page migration was first developed in the context of the memory hotplug
- * project. The main authors of the migration code are:
- *
- * IWAMOTO Toshihiro <iwamoto@valinux.co.jp>
- * Hirokazu Takahashi <taka@valinux.co.jp>
- * Dave Hansen <haveblue@us.ibm.com>
- * Christoph Lameter
- */
- #include <linux/migrate.h>
- #include <linux/export.h>
- #include <linux/swap.h>
- #include <linux/swapops.h>
- #include <linux/pagemap.h>
- #include <linux/buffer_head.h>
- #include <linux/mm_inline.h>
- #include <linux/nsproxy.h>
- #include <linux/pagevec.h>
- #include <linux/ksm.h>
- #include <linux/rmap.h>
- #include <linux/topology.h>
- #include <linux/cpu.h>
- #include <linux/cpuset.h>
- #include <linux/writeback.h>
- #include <linux/mempolicy.h>
- #include <linux/vmalloc.h>
- #include <linux/security.h>
- #include <linux/backing-dev.h>
- #include <linux/compaction.h>
- #include <linux/syscalls.h>
- #include <linux/compat.h>
- #include <linux/hugetlb.h>
- #include <linux/hugetlb_cgroup.h>
- #include <linux/gfp.h>
- #include <linux/pagewalk.h>
- #include <linux/pfn_t.h>
- #include <linux/memremap.h>
- #include <linux/userfaultfd_k.h>
- #include <linux/balloon_compaction.h>
- #include <linux/mmu_notifier.h>
- #include <linux/page_idle.h>
- #include <linux/page_owner.h>
- #include <linux/sched/mm.h>
- #include <linux/ptrace.h>
- #include <linux/oom.h>
- #include <asm/tlbflush.h>
- #define CREATE_TRACE_POINTS
- #include <trace/events/migrate.h>
- #include "internal.h"
- int isolate_movable_page(struct page *page, isolate_mode_t mode)
- {
- struct address_space *mapping;
- /*
- * Avoid burning cycles with pages that are yet under __free_pages(),
- * or just got freed under us.
- *
- * In case we 'win' a race for a movable page being freed under us and
- * raise its refcount preventing __free_pages() from doing its job
- * the put_page() at the end of this block will take care of
- * release this page, thus avoiding a nasty leakage.
- */
- if (unlikely(!get_page_unless_zero(page)))
- goto out;
- /*
- * Check PageMovable before holding a PG_lock because page's owner
- * assumes anybody doesn't touch PG_lock of newly allocated page
- * so unconditionally grabbing the lock ruins page's owner side.
- */
- if (unlikely(!__PageMovable(page)))
- goto out_putpage;
- /*
- * As movable pages are not isolated from LRU lists, concurrent
- * compaction threads can race against page migration functions
- * as well as race against the releasing a page.
- *
- * In order to avoid having an already isolated movable page
- * being (wrongly) re-isolated while it is under migration,
- * or to avoid attempting to isolate pages being released,
- * lets be sure we have the page lock
- * before proceeding with the movable page isolation steps.
- */
- if (unlikely(!trylock_page(page)))
- goto out_putpage;
- if (!PageMovable(page) || PageIsolated(page))
- goto out_no_isolated;
- mapping = page_mapping(page);
- VM_BUG_ON_PAGE(!mapping, page);
- if (!mapping->a_ops->isolate_page(page, mode))
- goto out_no_isolated;
- /* Driver shouldn't use PG_isolated bit of page->flags */
- WARN_ON_ONCE(PageIsolated(page));
- SetPageIsolated(page);
- unlock_page(page);
- return 0;
- out_no_isolated:
- unlock_page(page);
- out_putpage:
- put_page(page);
- out:
- return -EBUSY;
- }
- /* It should be called on page which is PG_movable */
- void putback_movable_page(struct page *page)
- {
- struct address_space *mapping;
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- VM_BUG_ON_PAGE(!PageMovable(page), page);
- VM_BUG_ON_PAGE(!PageIsolated(page), page);
- mapping = page_mapping(page);
- mapping->a_ops->putback_page(page);
- ClearPageIsolated(page);
- }
- /*
- * Put previously isolated pages back onto the appropriate lists
- * from where they were once taken off for compaction/migration.
- *
- * This function shall be used whenever the isolated pageset has been
- * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range()
- * and isolate_huge_page().
- */
- void putback_movable_pages(struct list_head *l)
- {
- struct page *page;
- struct page *page2;
- list_for_each_entry_safe(page, page2, l, lru) {
- if (unlikely(PageHuge(page))) {
- putback_active_hugepage(page);
- continue;
- }
- list_del(&page->lru);
- /*
- * We isolated non-lru movable page so here we can use
- * __PageMovable because LRU page's mapping cannot have
- * PAGE_MAPPING_MOVABLE.
- */
- if (unlikely(__PageMovable(page))) {
- VM_BUG_ON_PAGE(!PageIsolated(page), page);
- lock_page(page);
- if (PageMovable(page))
- putback_movable_page(page);
- else
- ClearPageIsolated(page);
- unlock_page(page);
- put_page(page);
- } else {
- mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON +
- page_is_file_lru(page), -thp_nr_pages(page));
- putback_lru_page(page);
- }
- }
- }
- EXPORT_SYMBOL_GPL(putback_movable_pages);
- /*
- * Restore a potential migration pte to a working pte entry
- */
- static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
- unsigned long addr, void *old)
- {
- struct page_vma_mapped_walk pvmw = {
- .page = old,
- .vma = vma,
- .address = addr,
- .flags = PVMW_SYNC | PVMW_MIGRATION,
- };
- struct page *new;
- pte_t pte;
- swp_entry_t entry;
- VM_BUG_ON_PAGE(PageTail(page), page);
- while (page_vma_mapped_walk(&pvmw)) {
- if (PageKsm(page))
- new = page;
- else
- new = page - pvmw.page->index +
- linear_page_index(vma, pvmw.address);
- #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
- /* PMD-mapped THP migration entry */
- if (!pvmw.pte) {
- VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page);
- remove_migration_pmd(&pvmw, new);
- continue;
- }
- #endif
- get_page(new);
- pte = pte_mkold(mk_pte(new, READ_ONCE(vma->vm_page_prot)));
- if (pte_swp_soft_dirty(*pvmw.pte))
- pte = pte_mksoft_dirty(pte);
- /*
- * Recheck VMA as permissions can change since migration started
- */
- entry = pte_to_swp_entry(*pvmw.pte);
- if (is_write_migration_entry(entry))
- pte = maybe_mkwrite(pte, vma->vm_flags);
- else if (pte_swp_uffd_wp(*pvmw.pte))
- pte = pte_mkuffd_wp(pte);
- if (unlikely(is_device_private_page(new))) {
- entry = make_device_private_entry(new, pte_write(pte));
- pte = swp_entry_to_pte(entry);
- if (pte_swp_soft_dirty(*pvmw.pte))
- pte = pte_swp_mksoft_dirty(pte);
- if (pte_swp_uffd_wp(*pvmw.pte))
- pte = pte_swp_mkuffd_wp(pte);
- }
- #ifdef CONFIG_HUGETLB_PAGE
- if (PageHuge(new)) {
- pte = pte_mkhuge(pte);
- pte = arch_make_huge_pte(pte, vma, new, 0);
- set_huge_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
- if (PageAnon(new))
- hugepage_add_anon_rmap(new, vma, pvmw.address);
- else
- page_dup_rmap(new, true);
- } else
- #endif
- {
- set_pte_at(vma->vm_mm, pvmw.address, pvmw.pte, pte);
- if (PageAnon(new))
- page_add_anon_rmap(new, vma, pvmw.address, false);
- else
- page_add_file_rmap(new, false);
- }
- if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new))
- mlock_vma_page(new);
- if (PageTransHuge(page) && PageMlocked(page))
- clear_page_mlock(page);
- /* No need to invalidate - it was non-present before */
- update_mmu_cache(vma, pvmw.address, pvmw.pte);
- }
- return true;
- }
- /*
- * Get rid of all migration entries and replace them by
- * references to the indicated page.
- */
- void remove_migration_ptes(struct page *old, struct page *new, bool locked)
- {
- struct rmap_walk_control rwc = {
- .rmap_one = remove_migration_pte,
- .arg = old,
- };
- if (locked)
- rmap_walk_locked(new, &rwc);
- else
- rmap_walk(new, &rwc);
- }
- /*
- * Something used the pte of a page under migration. We need to
- * get to the page and wait until migration is finished.
- * When we return from this function the fault will be retried.
- */
- void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
- spinlock_t *ptl)
- {
- pte_t pte;
- swp_entry_t entry;
- struct page *page;
- spin_lock(ptl);
- pte = *ptep;
- if (!is_swap_pte(pte))
- goto out;
- entry = pte_to_swp_entry(pte);
- if (!is_migration_entry(entry))
- goto out;
- page = migration_entry_to_page(entry);
- page = compound_head(page);
- /*
- * Once page cache replacement of page migration started, page_count
- * is zero; but we must not call put_and_wait_on_page_locked() without
- * a ref. Use get_page_unless_zero(), and just fault again if it fails.
- */
- if (!get_page_unless_zero(page))
- goto out;
- pte_unmap_unlock(ptep, ptl);
- put_and_wait_on_page_locked(page);
- return;
- out:
- pte_unmap_unlock(ptep, ptl);
- }
- void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd,
- unsigned long address)
- {
- spinlock_t *ptl = pte_lockptr(mm, pmd);
- pte_t *ptep = pte_offset_map(pmd, address);
- __migration_entry_wait(mm, ptep, ptl);
- }
- void migration_entry_wait_huge(struct vm_area_struct *vma,
- struct mm_struct *mm, pte_t *pte)
- {
- spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), mm, pte);
- __migration_entry_wait(mm, pte, ptl);
- }
- #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
- void pmd_migration_entry_wait(struct mm_struct *mm, pmd_t *pmd)
- {
- spinlock_t *ptl;
- struct page *page;
- ptl = pmd_lock(mm, pmd);
- if (!is_pmd_migration_entry(*pmd))
- goto unlock;
- page = migration_entry_to_page(pmd_to_swp_entry(*pmd));
- if (!get_page_unless_zero(page))
- goto unlock;
- spin_unlock(ptl);
- put_and_wait_on_page_locked(page);
- return;
- unlock:
- spin_unlock(ptl);
- }
- #endif
- static int expected_page_refs(struct address_space *mapping, struct page *page)
- {
- int expected_count = 1;
- /*
- * Device private pages have an extra refcount as they are
- * ZONE_DEVICE pages.
- */
- expected_count += is_device_private_page(page);
- if (mapping)
- expected_count += thp_nr_pages(page) + page_has_private(page);
- return expected_count;
- }
- /*
- * Replace the page in the mapping.
- *
- * The number of remaining references must be:
- * 1 for anonymous pages without a mapping
- * 2 for pages with a mapping
- * 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
- */
- int migrate_page_move_mapping(struct address_space *mapping,
- struct page *newpage, struct page *page, int extra_count)
- {
- XA_STATE(xas, &mapping->i_pages, page_index(page));
- struct zone *oldzone, *newzone;
- int dirty;
- int expected_count = expected_page_refs(mapping, page) + extra_count;
- int nr = thp_nr_pages(page);
- if (!mapping) {
- /* Anonymous page without mapping */
- if (page_count(page) != expected_count)
- return -EAGAIN;
- /* No turning back from here */
- newpage->index = page->index;
- newpage->mapping = page->mapping;
- if (PageSwapBacked(page))
- __SetPageSwapBacked(newpage);
- return MIGRATEPAGE_SUCCESS;
- }
- oldzone = page_zone(page);
- newzone = page_zone(newpage);
- xas_lock_irq(&xas);
- if (page_count(page) != expected_count || xas_load(&xas) != page) {
- xas_unlock_irq(&xas);
- return -EAGAIN;
- }
- if (!page_ref_freeze(page, expected_count)) {
- xas_unlock_irq(&xas);
- return -EAGAIN;
- }
- /*
- * Now we know that no one else is looking at the page:
- * no turning back from here.
- */
- newpage->index = page->index;
- newpage->mapping = page->mapping;
- page_ref_add(newpage, nr); /* add cache reference */
- if (PageSwapBacked(page)) {
- __SetPageSwapBacked(newpage);
- if (PageSwapCache(page)) {
- SetPageSwapCache(newpage);
- set_page_private(newpage, page_private(page));
- }
- } else {
- VM_BUG_ON_PAGE(PageSwapCache(page), page);
- }
- /* Move dirty while page refs frozen and newpage not yet exposed */
- dirty = PageDirty(page);
- if (dirty) {
- ClearPageDirty(page);
- SetPageDirty(newpage);
- }
- xas_store(&xas, newpage);
- if (PageTransHuge(page)) {
- int i;
- for (i = 1; i < nr; i++) {
- xas_next(&xas);
- xas_store(&xas, newpage);
- }
- }
- /*
- * Drop cache reference from old page by unfreezing
- * to one less reference.
- * We know this isn't the last reference.
- */
- page_ref_unfreeze(page, expected_count - nr);
- xas_unlock(&xas);
- /* Leave irq disabled to prevent preemption while updating stats */
- /*
- * If moved to a different zone then also account
- * the page for that zone. Other VM counters will be
- * taken care of when we establish references to the
- * new page and drop references to the old page.
- *
- * Note that anonymous pages are accounted for
- * via NR_FILE_PAGES and NR_ANON_MAPPED if they
- * are mapped to swap space.
- */
- if (newzone != oldzone) {
- struct lruvec *old_lruvec, *new_lruvec;
- struct mem_cgroup *memcg;
- memcg = page_memcg(page);
- old_lruvec = mem_cgroup_lruvec(memcg, oldzone->zone_pgdat);
- new_lruvec = mem_cgroup_lruvec(memcg, newzone->zone_pgdat);
- __mod_lruvec_state(old_lruvec, NR_FILE_PAGES, -nr);
- __mod_lruvec_state(new_lruvec, NR_FILE_PAGES, nr);
- if (PageSwapBacked(page) && !PageSwapCache(page)) {
- __mod_lruvec_state(old_lruvec, NR_SHMEM, -nr);
- __mod_lruvec_state(new_lruvec, NR_SHMEM, nr);
- }
- if (dirty && mapping_can_writeback(mapping)) {
- __mod_lruvec_state(old_lruvec, NR_FILE_DIRTY, -nr);
- __mod_zone_page_state(oldzone, NR_ZONE_WRITE_PENDING, -nr);
- __mod_lruvec_state(new_lruvec, NR_FILE_DIRTY, nr);
- __mod_zone_page_state(newzone, NR_ZONE_WRITE_PENDING, nr);
- }
- }
- local_irq_enable();
- return MIGRATEPAGE_SUCCESS;
- }
- EXPORT_SYMBOL(migrate_page_move_mapping);
- /*
- * The expected number of remaining references is the same as that
- * of migrate_page_move_mapping().
- */
- int migrate_huge_page_move_mapping(struct address_space *mapping,
- struct page *newpage, struct page *page)
- {
- XA_STATE(xas, &mapping->i_pages, page_index(page));
- int expected_count;
- xas_lock_irq(&xas);
- expected_count = 2 + page_has_private(page);
- if (page_count(page) != expected_count || xas_load(&xas) != page) {
- xas_unlock_irq(&xas);
- return -EAGAIN;
- }
- if (!page_ref_freeze(page, expected_count)) {
- xas_unlock_irq(&xas);
- return -EAGAIN;
- }
- newpage->index = page->index;
- newpage->mapping = page->mapping;
- get_page(newpage);
- xas_store(&xas, newpage);
- page_ref_unfreeze(page, expected_count - 1);
- xas_unlock_irq(&xas);
- return MIGRATEPAGE_SUCCESS;
- }
- /*
- * Gigantic pages are so large that we do not guarantee that page++ pointer
- * arithmetic will work across the entire page. We need something more
- * specialized.
- */
- static void __copy_gigantic_page(struct page *dst, struct page *src,
- int nr_pages)
- {
- int i;
- struct page *dst_base = dst;
- struct page *src_base = src;
- for (i = 0; i < nr_pages; ) {
- cond_resched();
- copy_highpage(dst, src);
- i++;
- dst = mem_map_next(dst, dst_base, i);
- src = mem_map_next(src, src_base, i);
- }
- }
- static void copy_huge_page(struct page *dst, struct page *src)
- {
- int i;
- int nr_pages;
- if (PageHuge(src)) {
- /* hugetlbfs page */
- struct hstate *h = page_hstate(src);
- nr_pages = pages_per_huge_page(h);
- if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) {
- __copy_gigantic_page(dst, src, nr_pages);
- return;
- }
- } else {
- /* thp page */
- BUG_ON(!PageTransHuge(src));
- nr_pages = thp_nr_pages(src);
- }
- for (i = 0; i < nr_pages; i++) {
- cond_resched();
- copy_highpage(dst + i, src + i);
- }
- }
- /*
- * Copy the page to its new location
- */
- void migrate_page_states(struct page *newpage, struct page *page)
- {
- int cpupid;
- if (PageError(page))
- SetPageError(newpage);
- if (PageReferenced(page))
- SetPageReferenced(newpage);
- if (PageUptodate(page))
- SetPageUptodate(newpage);
- if (TestClearPageActive(page)) {
- VM_BUG_ON_PAGE(PageUnevictable(page), page);
- SetPageActive(newpage);
- } else if (TestClearPageUnevictable(page))
- SetPageUnevictable(newpage);
- if (PageWorkingset(page))
- SetPageWorkingset(newpage);
- if (PageChecked(page))
- SetPageChecked(newpage);
- if (PageMappedToDisk(page))
- SetPageMappedToDisk(newpage);
- /* Move dirty on pages not done by migrate_page_move_mapping() */
- if (PageDirty(page))
- SetPageDirty(newpage);
- if (page_is_young(page))
- set_page_young(newpage);
- if (page_is_idle(page))
- set_page_idle(newpage);
- /*
- * Copy NUMA information to the new page, to prevent over-eager
- * future migrations of this same page.
- */
- cpupid = page_cpupid_xchg_last(page, -1);
- page_cpupid_xchg_last(newpage, cpupid);
- ksm_migrate_page(newpage, page);
- /*
- * Please do not reorder this without considering how mm/ksm.c's
- * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache().
- */
- if (PageSwapCache(page))
- ClearPageSwapCache(page);
- ClearPagePrivate(page);
- set_page_private(page, 0);
- /*
- * If any waiters have accumulated on the new page then
- * wake them up.
- */
- if (PageWriteback(newpage))
- end_page_writeback(newpage);
- /*
- * PG_readahead shares the same bit with PG_reclaim. The above
- * end_page_writeback() may clear PG_readahead mistakenly, so set the
- * bit after that.
- */
- if (PageReadahead(page))
- SetPageReadahead(newpage);
- copy_page_owner(page, newpage);
- if (!PageHuge(page))
- mem_cgroup_migrate(page, newpage);
- }
- EXPORT_SYMBOL(migrate_page_states);
- void migrate_page_copy(struct page *newpage, struct page *page)
- {
- if (PageHuge(page) || PageTransHuge(page))
- copy_huge_page(newpage, page);
- else
- copy_highpage(newpage, page);
- migrate_page_states(newpage, page);
- }
- EXPORT_SYMBOL(migrate_page_copy);
- /************************************************************
- * Migration functions
- ***********************************************************/
- /*
- * Common logic to directly migrate a single LRU page suitable for
- * pages that do not use PagePrivate/PagePrivate2.
- *
- * Pages are locked upon entry and exit.
- */
- int migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page,
- enum migrate_mode mode)
- {
- int rc;
- BUG_ON(PageWriteback(page)); /* Writeback must be complete */
- rc = migrate_page_move_mapping(mapping, newpage, page, 0);
- if (rc != MIGRATEPAGE_SUCCESS)
- return rc;
- if (mode != MIGRATE_SYNC_NO_COPY)
- migrate_page_copy(newpage, page);
- else
- migrate_page_states(newpage, page);
- return MIGRATEPAGE_SUCCESS;
- }
- EXPORT_SYMBOL(migrate_page);
- #ifdef CONFIG_BLOCK
- /* Returns true if all buffers are successfully locked */
- static bool buffer_migrate_lock_buffers(struct buffer_head *head,
- enum migrate_mode mode)
- {
- struct buffer_head *bh = head;
- /* Simple case, sync compaction */
- if (mode != MIGRATE_ASYNC) {
- do {
- lock_buffer(bh);
- bh = bh->b_this_page;
- } while (bh != head);
- return true;
- }
- /* async case, we cannot block on lock_buffer so use trylock_buffer */
- do {
- if (!trylock_buffer(bh)) {
- /*
- * We failed to lock the buffer and cannot stall in
- * async migration. Release the taken locks
- */
- struct buffer_head *failed_bh = bh;
- bh = head;
- while (bh != failed_bh) {
- unlock_buffer(bh);
- bh = bh->b_this_page;
- }
- return false;
- }
- bh = bh->b_this_page;
- } while (bh != head);
- return true;
- }
- static int __buffer_migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page, enum migrate_mode mode,
- bool check_refs)
- {
- struct buffer_head *bh, *head;
- int rc;
- int expected_count;
- if (!page_has_buffers(page))
- return migrate_page(mapping, newpage, page, mode);
- /* Check whether page does not have extra refs before we do more work */
- expected_count = expected_page_refs(mapping, page);
- if (page_count(page) != expected_count)
- return -EAGAIN;
- head = page_buffers(page);
- if (!buffer_migrate_lock_buffers(head, mode))
- return -EAGAIN;
- if (check_refs) {
- bool busy;
- bool invalidated = false;
- recheck_buffers:
- busy = false;
- spin_lock(&mapping->private_lock);
- bh = head;
- do {
- if (atomic_read(&bh->b_count)) {
- busy = true;
- break;
- }
- bh = bh->b_this_page;
- } while (bh != head);
- if (busy) {
- if (invalidated) {
- rc = -EAGAIN;
- goto unlock_buffers;
- }
- spin_unlock(&mapping->private_lock);
- invalidate_bh_lrus();
- invalidated = true;
- goto recheck_buffers;
- }
- }
- rc = migrate_page_move_mapping(mapping, newpage, page, 0);
- if (rc != MIGRATEPAGE_SUCCESS)
- goto unlock_buffers;
- attach_page_private(newpage, detach_page_private(page));
- bh = head;
- do {
- set_bh_page(bh, newpage, bh_offset(bh));
- bh = bh->b_this_page;
- } while (bh != head);
- if (mode != MIGRATE_SYNC_NO_COPY)
- migrate_page_copy(newpage, page);
- else
- migrate_page_states(newpage, page);
- rc = MIGRATEPAGE_SUCCESS;
- unlock_buffers:
- if (check_refs)
- spin_unlock(&mapping->private_lock);
- bh = head;
- do {
- unlock_buffer(bh);
- bh = bh->b_this_page;
- } while (bh != head);
- return rc;
- }
- /*
- * Migration function for pages with buffers. This function can only be used
- * if the underlying filesystem guarantees that no other references to "page"
- * exist. For example attached buffer heads are accessed only under page lock.
- */
- int buffer_migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page, enum migrate_mode mode)
- {
- return __buffer_migrate_page(mapping, newpage, page, mode, false);
- }
- EXPORT_SYMBOL(buffer_migrate_page);
- /*
- * Same as above except that this variant is more careful and checks that there
- * are also no buffer head references. This function is the right one for
- * mappings where buffer heads are directly looked up and referenced (such as
- * block device mappings).
- */
- int buffer_migrate_page_norefs(struct address_space *mapping,
- struct page *newpage, struct page *page, enum migrate_mode mode)
- {
- return __buffer_migrate_page(mapping, newpage, page, mode, true);
- }
- #endif
- /*
- * Writeback a page to clean the dirty state
- */
- static int writeout(struct address_space *mapping, struct page *page)
- {
- struct writeback_control wbc = {
- .sync_mode = WB_SYNC_NONE,
- .nr_to_write = 1,
- .range_start = 0,
- .range_end = LLONG_MAX,
- .for_reclaim = 1
- };
- int rc;
- if (!mapping->a_ops->writepage)
- /* No write method for the address space */
- return -EINVAL;
- if (!clear_page_dirty_for_io(page))
- /* Someone else already triggered a write */
- return -EAGAIN;
- /*
- * A dirty page may imply that the underlying filesystem has
- * the page on some queue. So the page must be clean for
- * migration. Writeout may mean we loose the lock and the
- * page state is no longer what we checked for earlier.
- * At this point we know that the migration attempt cannot
- * be successful.
- */
- remove_migration_ptes(page, page, false);
- rc = mapping->a_ops->writepage(page, &wbc);
- if (rc != AOP_WRITEPAGE_ACTIVATE)
- /* unlocked. Relock */
- lock_page(page);
- return (rc < 0) ? -EIO : -EAGAIN;
- }
- /*
- * Default handling if a filesystem does not provide a migration function.
- */
- static int fallback_migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *page, enum migrate_mode mode)
- {
- if (PageDirty(page)) {
- /* Only writeback pages in full synchronous migration */
- switch (mode) {
- case MIGRATE_SYNC:
- case MIGRATE_SYNC_NO_COPY:
- break;
- default:
- return -EBUSY;
- }
- return writeout(mapping, page);
- }
- /*
- * Buffers may be managed in a filesystem specific way.
- * We must have no buffers or drop them.
- */
- if (page_has_private(page) &&
- !try_to_release_page(page, GFP_KERNEL))
- return mode == MIGRATE_SYNC ? -EAGAIN : -EBUSY;
- return migrate_page(mapping, newpage, page, mode);
- }
- /*
- * Move a page to a newly allocated page
- * The page is locked and all ptes have been successfully removed.
- *
- * The new page will have replaced the old page if this function
- * is successful.
- *
- * Return value:
- * < 0 - error code
- * MIGRATEPAGE_SUCCESS - success
- */
- static int move_to_new_page(struct page *newpage, struct page *page,
- enum migrate_mode mode)
- {
- struct address_space *mapping;
- int rc = -EAGAIN;
- bool is_lru = !__PageMovable(page);
- VM_BUG_ON_PAGE(!PageLocked(page), page);
- VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
- mapping = page_mapping(page);
- if (likely(is_lru)) {
- if (!mapping)
- rc = migrate_page(mapping, newpage, page, mode);
- else if (mapping->a_ops->migratepage)
- /*
- * Most pages have a mapping and most filesystems
- * provide a migratepage callback. Anonymous pages
- * are part of swap space which also has its own
- * migratepage callback. This is the most common path
- * for page migration.
- */
- rc = mapping->a_ops->migratepage(mapping, newpage,
- page, mode);
- else
- rc = fallback_migrate_page(mapping, newpage,
- page, mode);
- } else {
- /*
- * In case of non-lru page, it could be released after
- * isolation step. In that case, we shouldn't try migration.
- */
- VM_BUG_ON_PAGE(!PageIsolated(page), page);
- if (!PageMovable(page)) {
- rc = MIGRATEPAGE_SUCCESS;
- ClearPageIsolated(page);
- goto out;
- }
- rc = mapping->a_ops->migratepage(mapping, newpage,
- page, mode);
- WARN_ON_ONCE(rc == MIGRATEPAGE_SUCCESS &&
- !PageIsolated(page));
- }
- /*
- * When successful, old pagecache page->mapping must be cleared before
- * page is freed; but stats require that PageAnon be left as PageAnon.
- */
- if (rc == MIGRATEPAGE_SUCCESS) {
- if (__PageMovable(page)) {
- VM_BUG_ON_PAGE(!PageIsolated(page), page);
- /*
- * We clear PG_movable under page_lock so any compactor
- * cannot try to migrate this page.
- */
- ClearPageIsolated(page);
- }
- /*
- * Anonymous and movable page->mapping will be cleared by
- * free_pages_prepare so don't reset it here for keeping
- * the type to work PageAnon, for example.
- */
- if (!PageMappingFlags(page))
- page->mapping = NULL;
- if (likely(!is_zone_device_page(newpage)))
- flush_dcache_page(newpage);
- }
- out:
- return rc;
- }
- static int __unmap_and_move(struct page *page, struct page *newpage,
- int force, enum migrate_mode mode)
- {
- int rc = -EAGAIN;
- int page_was_mapped = 0;
- struct anon_vma *anon_vma = NULL;
- bool is_lru = !__PageMovable(page);
- if (!trylock_page(page)) {
- if (!force || mode == MIGRATE_ASYNC)
- goto out;
- /*
- * It's not safe for direct compaction to call lock_page.
- * For example, during page readahead pages are added locked
- * to the LRU. Later, when the IO completes the pages are
- * marked uptodate and unlocked. However, the queueing
- * could be merging multiple pages for one bio (e.g.
- * mpage_readahead). If an allocation happens for the
- * second or third page, the process can end up locking
- * the same page twice and deadlocking. Rather than
- * trying to be clever about what pages can be locked,
- * avoid the use of lock_page for direct compaction
- * altogether.
- */
- if (current->flags & PF_MEMALLOC)
- goto out;
- lock_page(page);
- }
- if (PageWriteback(page)) {
- /*
- * Only in the case of a full synchronous migration is it
- * necessary to wait for PageWriteback. In the async case,
- * the retry loop is too short and in the sync-light case,
- * the overhead of stalling is too much
- */
- switch (mode) {
- case MIGRATE_SYNC:
- case MIGRATE_SYNC_NO_COPY:
- break;
- default:
- rc = -EBUSY;
- goto out_unlock;
- }
- if (!force)
- goto out_unlock;
- wait_on_page_writeback(page);
- }
- /*
- * By try_to_unmap(), page->mapcount goes down to 0 here. In this case,
- * we cannot notice that anon_vma is freed while we migrates a page.
- * This get_anon_vma() delays freeing anon_vma pointer until the end
- * of migration. File cache pages are no problem because of page_lock()
- * File Caches may use write_page() or lock_page() in migration, then,
- * just care Anon page here.
- *
- * Only page_get_anon_vma() understands the subtleties of
- * getting a hold on an anon_vma from outside one of its mms.
- * But if we cannot get anon_vma, then we won't need it anyway,
- * because that implies that the anon page is no longer mapped
- * (and cannot be remapped so long as we hold the page lock).
- */
- if (PageAnon(page) && !PageKsm(page))
- anon_vma = page_get_anon_vma(page);
- /*
- * Block others from accessing the new page when we get around to
- * establishing additional references. We are usually the only one
- * holding a reference to newpage at this point. We used to have a BUG
- * here if trylock_page(newpage) fails, but would like to allow for
- * cases where there might be a race with the previous use of newpage.
- * This is much like races on refcount of oldpage: just don't BUG().
- */
- if (unlikely(!trylock_page(newpage)))
- goto out_unlock;
- if (unlikely(!is_lru)) {
- rc = move_to_new_page(newpage, page, mode);
- goto out_unlock_both;
- }
- /*
- * Corner case handling:
- * 1. When a new swap-cache page is read into, it is added to the LRU
- * and treated as swapcache but it has no rmap yet.
- * Calling try_to_unmap() against a page->mapping==NULL page will
- * trigger a BUG. So handle it here.
- * 2. An orphaned page (see truncate_complete_page) might have
- * fs-private metadata. The page can be picked up due to memory
- * offlining. Everywhere else except page reclaim, the page is
- * invisible to the vm, so the page can not be migrated. So try to
- * free the metadata, so the page can be freed.
- */
- if (!page->mapping) {
- VM_BUG_ON_PAGE(PageAnon(page), page);
- if (page_has_private(page)) {
- try_to_free_buffers(page);
- goto out_unlock_both;
- }
- } else if (page_mapped(page)) {
- /* Establish migration ptes */
- VM_BUG_ON_PAGE(PageAnon(page) && !PageKsm(page) && !anon_vma,
- page);
- try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK);
- page_was_mapped = 1;
- }
- if (!page_mapped(page))
- rc = move_to_new_page(newpage, page, mode);
- if (page_was_mapped)
- remove_migration_ptes(page,
- rc == MIGRATEPAGE_SUCCESS ? newpage : page, false);
- out_unlock_both:
- unlock_page(newpage);
- out_unlock:
- /* Drop an anon_vma reference if we took one */
- if (anon_vma)
- put_anon_vma(anon_vma);
- unlock_page(page);
- out:
- /*
- * If migration is successful, decrease refcount of the newpage
- * which will not free the page because new page owner increased
- * refcounter. As well, if it is LRU page, add the page to LRU
- * list in here. Use the old state of the isolated source page to
- * determine if we migrated a LRU page. newpage was already unlocked
- * and possibly modified by its owner - don't rely on the page
- * state.
- */
- if (rc == MIGRATEPAGE_SUCCESS) {
- if (unlikely(!is_lru))
- put_page(newpage);
- else
- putback_lru_page(newpage);
- }
- return rc;
- }
- /*
- * Obtain the lock on page, remove all ptes and migrate the page
- * to the newly allocated page in newpage.
- */
- static int unmap_and_move(new_page_t get_new_page,
- free_page_t put_new_page,
- unsigned long private, struct page *page,
- int force, enum migrate_mode mode,
- enum migrate_reason reason)
- {
- int rc = MIGRATEPAGE_SUCCESS;
- struct page *newpage = NULL;
- if (!thp_migration_supported() && PageTransHuge(page))
- return -ENOMEM;
- if (page_count(page) == 1) {
- /* page was freed from under us. So we are done. */
- ClearPageActive(page);
- ClearPageUnevictable(page);
- if (unlikely(__PageMovable(page))) {
- lock_page(page);
- if (!PageMovable(page))
- ClearPageIsolated(page);
- unlock_page(page);
- }
- goto out;
- }
- newpage = get_new_page(page, private);
- if (!newpage)
- return -ENOMEM;
- rc = __unmap_and_move(page, newpage, force, mode);
- if (rc == MIGRATEPAGE_SUCCESS)
- set_page_owner_migrate_reason(newpage, reason);
- out:
- if (rc != -EAGAIN) {
- /*
- * A page that has been migrated has all references
- * removed and will be freed. A page that has not been
- * migrated will have kept its references and be restored.
- */
- list_del(&page->lru);
- /*
- * Compaction can migrate also non-LRU pages which are
- * not accounted to NR_ISOLATED_*. They can be recognized
- * as __PageMovable
- */
- if (likely(!__PageMovable(page)))
- mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON +
- page_is_file_lru(page), -thp_nr_pages(page));
- }
- /*
- * If migration is successful, releases reference grabbed during
- * isolation. Otherwise, restore the page to right list unless
- * we want to retry.
- */
- if (rc == MIGRATEPAGE_SUCCESS) {
- if (reason != MR_MEMORY_FAILURE)
- /*
- * We release the page in page_handle_poison.
- */
- put_page(page);
- } else {
- if (rc != -EAGAIN) {
- if (likely(!__PageMovable(page))) {
- putback_lru_page(page);
- goto put_new;
- }
- lock_page(page);
- if (PageMovable(page))
- putback_movable_page(page);
- else
- ClearPageIsolated(page);
- unlock_page(page);
- put_page(page);
- }
- put_new:
- if (put_new_page)
- put_new_page(newpage, private);
- else
- put_page(newpage);
- }
- return rc;
- }
- /*
- * Counterpart of unmap_and_move_page() for hugepage migration.
- *
- * This function doesn't wait the completion of hugepage I/O
- * because there is no race between I/O and migration for hugepage.
- * Note that currently hugepage I/O occurs only in direct I/O
- * where no lock is held and PG_writeback is irrelevant,
- * and writeback status of all subpages are counted in the reference
- * count of the head page (i.e. if all subpages of a 2MB hugepage are
- * under direct I/O, the reference of the head page is 512 and a bit more.)
- * This means that when we try to migrate hugepage whose subpages are
- * doing direct I/O, some references remain after try_to_unmap() and
- * hugepage migration fails without data corruption.
- *
- * There is also no race when direct I/O is issued on the page under migration,
- * because then pte is replaced with migration swap entry and direct I/O code
- * will wait in the page fault for migration to complete.
- */
- static int unmap_and_move_huge_page(new_page_t get_new_page,
- free_page_t put_new_page, unsigned long private,
- struct page *hpage, int force,
- enum migrate_mode mode, int reason)
- {
- int rc = -EAGAIN;
- int page_was_mapped = 0;
- struct page *new_hpage;
- struct anon_vma *anon_vma = NULL;
- struct address_space *mapping = NULL;
- /*
- * Migratability of hugepages depends on architectures and their size.
- * This check is necessary because some callers of hugepage migration
- * like soft offline and memory hotremove don't walk through page
- * tables or check whether the hugepage is pmd-based or not before
- * kicking migration.
- */
- if (!hugepage_migration_supported(page_hstate(hpage))) {
- putback_active_hugepage(hpage);
- return -ENOSYS;
- }
- new_hpage = get_new_page(hpage, private);
- if (!new_hpage)
- return -ENOMEM;
- if (!trylock_page(hpage)) {
- if (!force)
- goto out;
- switch (mode) {
- case MIGRATE_SYNC:
- case MIGRATE_SYNC_NO_COPY:
- break;
- default:
- goto out;
- }
- lock_page(hpage);
- }
- /*
- * Check for pages which are in the process of being freed. Without
- * page_mapping() set, hugetlbfs specific move page routine will not
- * be called and we could leak usage counts for subpools.
- */
- if (page_private(hpage) && !page_mapping(hpage)) {
- rc = -EBUSY;
- goto out_unlock;
- }
- if (PageAnon(hpage))
- anon_vma = page_get_anon_vma(hpage);
- if (unlikely(!trylock_page(new_hpage)))
- goto put_anon;
- if (page_mapped(hpage)) {
- bool mapping_locked = false;
- enum ttu_flags ttu = TTU_MIGRATION|TTU_IGNORE_MLOCK;
- if (!PageAnon(hpage)) {
- /*
- * 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 let lower levels know we have taken the lock.
- */
- mapping = hugetlb_page_mapping_lock_write(hpage);
- if (unlikely(!mapping))
- goto unlock_put_anon;
- mapping_locked = true;
- ttu |= TTU_RMAP_LOCKED;
- }
- try_to_unmap(hpage, ttu);
- page_was_mapped = 1;
- if (mapping_locked)
- i_mmap_unlock_write(mapping);
- }
- if (!page_mapped(hpage))
- rc = move_to_new_page(new_hpage, hpage, mode);
- if (page_was_mapped)
- remove_migration_ptes(hpage,
- rc == MIGRATEPAGE_SUCCESS ? new_hpage : hpage, false);
- unlock_put_anon:
- unlock_page(new_hpage);
- put_anon:
- if (anon_vma)
- put_anon_vma(anon_vma);
- if (rc == MIGRATEPAGE_SUCCESS) {
- move_hugetlb_state(hpage, new_hpage, reason);
- put_new_page = NULL;
- }
- out_unlock:
- unlock_page(hpage);
- out:
- if (rc != -EAGAIN)
- putback_active_hugepage(hpage);
- /*
- * If migration was not successful and there's a freeing callback, use
- * it. Otherwise, put_page() will drop the reference grabbed during
- * isolation.
- */
- if (put_new_page)
- put_new_page(new_hpage, private);
- else
- putback_active_hugepage(new_hpage);
- return rc;
- }
- /*
- * migrate_pages - migrate the pages specified in a list, to the free pages
- * supplied as the target for the page migration
- *
- * @from: The list of pages to be migrated.
- * @get_new_page: The function used to allocate free pages to be used
- * as the target of the page migration.
- * @put_new_page: The function used to free target pages if migration
- * fails, or NULL if no special handling is necessary.
- * @private: Private data to be passed on to get_new_page()
- * @mode: The migration mode that specifies the constraints for
- * page migration, if any.
- * @reason: The reason for page migration.
- *
- * The function returns after 10 attempts or if no pages are movable any more
- * because the list has become empty or no retryable pages exist any more.
- * The caller should call putback_movable_pages() to return pages to the LRU
- * or free list only if ret != 0.
- *
- * Returns the number of pages that were not migrated, or an error code.
- */
- int migrate_pages(struct list_head *from, new_page_t get_new_page,
- free_page_t put_new_page, unsigned long private,
- enum migrate_mode mode, int reason)
- {
- int retry = 1;
- int thp_retry = 1;
- int nr_failed = 0;
- int nr_succeeded = 0;
- int nr_thp_succeeded = 0;
- int nr_thp_failed = 0;
- int nr_thp_split = 0;
- int pass = 0;
- bool is_thp = false;
- struct page *page;
- struct page *page2;
- int swapwrite = current->flags & PF_SWAPWRITE;
- int rc, nr_subpages;
- trace_mm_migrate_pages_start(mode, reason);
- if (!swapwrite)
- current->flags |= PF_SWAPWRITE;
- for (pass = 0; pass < 10 && (retry || thp_retry); pass++) {
- retry = 0;
- thp_retry = 0;
- list_for_each_entry_safe(page, page2, from, lru) {
- retry:
- /*
- * THP statistics is based on the source huge page.
- * Capture required information that might get lost
- * during migration.
- */
- is_thp = PageTransHuge(page) && !PageHuge(page);
- nr_subpages = thp_nr_pages(page);
- cond_resched();
- if (PageHuge(page))
- rc = unmap_and_move_huge_page(get_new_page,
- put_new_page, private, page,
- pass > 2, mode, reason);
- else
- rc = unmap_and_move(get_new_page, put_new_page,
- private, page, pass > 2, mode,
- reason);
- switch(rc) {
- case -ENOMEM:
- /*
- * THP migration might be unsupported or the
- * allocation could've failed so we should
- * retry on the same page with the THP split
- * to base pages.
- *
- * Head page is retried immediately and tail
- * pages are added to the tail of the list so
- * we encounter them after the rest of the list
- * is processed.
- */
- if (is_thp) {
- lock_page(page);
- rc = split_huge_page_to_list(page, from);
- unlock_page(page);
- if (!rc) {
- list_safe_reset_next(page, page2, lru);
- nr_thp_split++;
- goto retry;
- }
- nr_thp_failed++;
- nr_failed += nr_subpages;
- goto out;
- }
- nr_failed++;
- goto out;
- case -EAGAIN:
- if (is_thp) {
- thp_retry++;
- break;
- }
- retry++;
- break;
- case MIGRATEPAGE_SUCCESS:
- if (is_thp) {
- nr_thp_succeeded++;
- nr_succeeded += nr_subpages;
- break;
- }
- nr_succeeded++;
- break;
- default:
- /*
- * Permanent failure (-EBUSY, -ENOSYS, etc.):
- * unlike -EAGAIN case, the failed page is
- * removed from migration page list and not
- * retried in the next outer loop.
- */
- if (is_thp) {
- nr_thp_failed++;
- nr_failed += nr_subpages;
- break;
- }
- nr_failed++;
- break;
- }
- }
- }
- nr_failed += retry + thp_retry;
- nr_thp_failed += thp_retry;
- rc = nr_failed;
- out:
- count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded);
- count_vm_events(PGMIGRATE_FAIL, nr_failed);
- count_vm_events(THP_MIGRATION_SUCCESS, nr_thp_succeeded);
- count_vm_events(THP_MIGRATION_FAIL, nr_thp_failed);
- count_vm_events(THP_MIGRATION_SPLIT, nr_thp_split);
- trace_mm_migrate_pages(nr_succeeded, nr_failed, nr_thp_succeeded,
- nr_thp_failed, nr_thp_split, mode, reason);
- if (!swapwrite)
- current->flags &= ~PF_SWAPWRITE;
- return rc;
- }
- EXPORT_SYMBOL_GPL(migrate_pages);
- struct page *alloc_migration_target(struct page *page, unsigned long private)
- {
- struct migration_target_control *mtc;
- gfp_t gfp_mask;
- unsigned int order = 0;
- struct page *new_page = NULL;
- int nid;
- int zidx;
- mtc = (struct migration_target_control *)private;
- gfp_mask = mtc->gfp_mask;
- nid = mtc->nid;
- if (nid == NUMA_NO_NODE)
- nid = page_to_nid(page);
- if (PageHuge(page)) {
- struct hstate *h = page_hstate(compound_head(page));
- gfp_mask = htlb_modify_alloc_mask(h, gfp_mask);
- return alloc_huge_page_nodemask(h, nid, mtc->nmask, gfp_mask);
- }
- if (PageTransHuge(page)) {
- /*
- * clear __GFP_RECLAIM to make the migration callback
- * consistent with regular THP allocations.
- */
- gfp_mask &= ~__GFP_RECLAIM;
- gfp_mask |= GFP_TRANSHUGE;
- order = HPAGE_PMD_ORDER;
- }
- zidx = zone_idx(page_zone(page));
- if (is_highmem_idx(zidx) || zidx == ZONE_MOVABLE)
- gfp_mask |= __GFP_HIGHMEM;
- new_page = __alloc_pages_nodemask(gfp_mask, order, nid, mtc->nmask);
- if (new_page && PageTransHuge(new_page))
- prep_transhuge_page(new_page);
- return new_page;
- }
- #ifdef CONFIG_NUMA
- static int store_status(int __user *status, int start, int value, int nr)
- {
- while (nr-- > 0) {
- if (put_user(value, status + start))
- return -EFAULT;
- start++;
- }
- return 0;
- }
- static int do_move_pages_to_node(struct mm_struct *mm,
- struct list_head *pagelist, int node)
- {
- int err;
- struct migration_target_control mtc = {
- .nid = node,
- .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE,
- };
- err = migrate_pages(pagelist, alloc_migration_target, NULL,
- (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL);
- if (err)
- putback_movable_pages(pagelist);
- return err;
- }
- /*
- * Resolves the given address to a struct page, isolates it from the LRU and
- * puts it to the given pagelist.
- * Returns:
- * errno - if the page cannot be found/isolated
- * 0 - when it doesn't have to be migrated because it is already on the
- * target node
- * 1 - when it has been queued
- */
- static int add_page_for_migration(struct mm_struct *mm, unsigned long addr,
- int node, struct list_head *pagelist, bool migrate_all)
- {
- struct vm_area_struct *vma;
- struct page *page;
- unsigned int follflags;
- int err;
- mmap_read_lock(mm);
- err = -EFAULT;
- vma = find_vma(mm, addr);
- if (!vma || addr < vma->vm_start || !vma_migratable(vma))
- goto out;
- /* FOLL_DUMP to ignore special (like zero) pages */
- follflags = FOLL_GET | FOLL_DUMP;
- page = follow_page(vma, addr, follflags);
- err = PTR_ERR(page);
- if (IS_ERR(page))
- goto out;
- err = -ENOENT;
- if (!page)
- goto out;
- err = 0;
- if (page_to_nid(page) == node)
- goto out_putpage;
- err = -EACCES;
- if (page_mapcount(page) > 1 && !migrate_all)
- goto out_putpage;
- if (PageHuge(page)) {
- if (PageHead(page)) {
- isolate_huge_page(page, pagelist);
- err = 1;
- }
- } else {
- struct page *head;
- head = compound_head(page);
- err = isolate_lru_page(head);
- if (err)
- goto out_putpage;
- err = 1;
- list_add_tail(&head->lru, pagelist);
- mod_node_page_state(page_pgdat(head),
- NR_ISOLATED_ANON + page_is_file_lru(head),
- thp_nr_pages(head));
- }
- out_putpage:
- /*
- * Either remove the duplicate refcount from
- * isolate_lru_page() or drop the page ref if it was
- * not isolated.
- */
- put_user_page(page);
- out:
- mmap_read_unlock(mm);
- return err;
- }
- static int move_pages_and_store_status(struct mm_struct *mm, int node,
- struct list_head *pagelist, int __user *status,
- int start, int i, unsigned long nr_pages)
- {
- int err;
- if (list_empty(pagelist))
- return 0;
- err = do_move_pages_to_node(mm, pagelist, node);
- if (err) {
- /*
- * Positive err means the number of failed
- * pages to migrate. Since we are going to
- * abort and return the number of non-migrated
- * pages, so need to incude the rest of the
- * nr_pages that have not been attempted as
- * well.
- */
- if (err > 0)
- err += nr_pages - i - 1;
- return err;
- }
- return store_status(status, start, node, i - start);
- }
- /*
- * Migrate an array of page address onto an array of nodes and fill
- * the corresponding array of status.
- */
- static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes,
- unsigned long nr_pages,
- const void __user * __user *pages,
- const int __user *nodes,
- int __user *status, int flags)
- {
- int current_node = NUMA_NO_NODE;
- LIST_HEAD(pagelist);
- int start, i;
- int err = 0, err1;
- lru_cache_disable();
- for (i = start = 0; i < nr_pages; i++) {
- const void __user *p;
- unsigned long addr;
- int node;
- err = -EFAULT;
- if (get_user(p, pages + i))
- goto out_flush;
- if (get_user(node, nodes + i))
- goto out_flush;
- addr = (unsigned long)untagged_addr(p);
- err = -ENODEV;
- if (node < 0 || node >= MAX_NUMNODES)
- goto out_flush;
- if (!node_state(node, N_MEMORY))
- goto out_flush;
- err = -EACCES;
- if (!node_isset(node, task_nodes))
- goto out_flush;
- if (current_node == NUMA_NO_NODE) {
- current_node = node;
- start = i;
- } else if (node != current_node) {
- err = move_pages_and_store_status(mm, current_node,
- &pagelist, status, start, i, nr_pages);
- if (err)
- goto out;
- start = i;
- current_node = node;
- }
- /*
- * Errors in the page lookup or isolation are not fatal and we simply
- * report them via status
- */
- err = add_page_for_migration(mm, addr, current_node,
- &pagelist, flags & MPOL_MF_MOVE_ALL);
- if (err > 0) {
- /* The page is successfully queued for migration */
- continue;
- }
- /*
- * If the page is already on the target node (!err), store the
- * node, otherwise, store the err.
- */
- err = store_status(status, i, err ? : current_node, 1);
- if (err)
- goto out_flush;
- err = move_pages_and_store_status(mm, current_node, &pagelist,
- status, start, i, nr_pages);
- if (err)
- goto out;
- current_node = NUMA_NO_NODE;
- }
- out_flush:
- /* Make sure we do not overwrite the existing error */
- err1 = move_pages_and_store_status(mm, current_node, &pagelist,
- status, start, i, nr_pages);
- if (err >= 0)
- err = err1;
- out:
- lru_cache_enable();
- return err;
- }
- /*
- * Determine the nodes of an array of pages and store it in an array of status.
- */
- static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages,
- const void __user **pages, int *status)
- {
- unsigned long i;
- mmap_read_lock(mm);
- for (i = 0; i < nr_pages; i++) {
- unsigned long addr = (unsigned long)(*pages);
- struct vm_area_struct *vma;
- struct page *page;
- int err = -EFAULT;
- vma = find_vma(mm, addr);
- if (!vma || addr < vma->vm_start)
- goto set_status;
- /* FOLL_DUMP to ignore special (like zero) pages */
- page = follow_page(vma, addr, FOLL_DUMP);
- err = PTR_ERR(page);
- if (IS_ERR(page))
- goto set_status;
- err = page ? page_to_nid(page) : -ENOENT;
- set_status:
- *status = err;
- pages++;
- status++;
- }
- mmap_read_unlock(mm);
- }
- /*
- * Determine the nodes of a user array of pages and store it in
- * a user array of status.
- */
- static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages,
- const void __user * __user *pages,
- int __user *status)
- {
- #define DO_PAGES_STAT_CHUNK_NR 16
- const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR];
- int chunk_status[DO_PAGES_STAT_CHUNK_NR];
- while (nr_pages) {
- unsigned long chunk_nr;
- chunk_nr = nr_pages;
- if (chunk_nr > DO_PAGES_STAT_CHUNK_NR)
- chunk_nr = DO_PAGES_STAT_CHUNK_NR;
- if (copy_from_user(chunk_pages, pages, chunk_nr * sizeof(*chunk_pages)))
- break;
- do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status);
- if (copy_to_user(status, chunk_status, chunk_nr * sizeof(*status)))
- break;
- pages += chunk_nr;
- status += chunk_nr;
- nr_pages -= chunk_nr;
- }
- return nr_pages ? -EFAULT : 0;
- }
- static struct mm_struct *find_mm_struct(pid_t pid, nodemask_t *mem_nodes)
- {
- struct task_struct *task;
- struct mm_struct *mm;
- /*
- * There is no need to check if current process has the right to modify
- * the specified process when they are same.
- */
- if (!pid) {
- mmget(current->mm);
- *mem_nodes = cpuset_mems_allowed(current);
- return current->mm;
- }
- /* Find the mm_struct */
- rcu_read_lock();
- task = find_task_by_vpid(pid);
- if (!task) {
- rcu_read_unlock();
- return ERR_PTR(-ESRCH);
- }
- get_task_struct(task);
- /*
- * Check if this process has the right to modify the specified
- * process. Use the regular "ptrace_may_access()" checks.
- */
- if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) {
- rcu_read_unlock();
- mm = ERR_PTR(-EPERM);
- goto out;
- }
- rcu_read_unlock();
- mm = ERR_PTR(security_task_movememory(task));
- if (IS_ERR(mm))
- goto out;
- *mem_nodes = cpuset_mems_allowed(task);
- mm = get_task_mm(task);
- out:
- put_task_struct(task);
- if (!mm)
- mm = ERR_PTR(-EINVAL);
- return mm;
- }
- /*
- * Move a list of pages in the address space of the currently executing
- * process.
- */
- static int kernel_move_pages(pid_t pid, unsigned long nr_pages,
- const void __user * __user *pages,
- const int __user *nodes,
- int __user *status, int flags)
- {
- struct mm_struct *mm;
- int err;
- nodemask_t task_nodes;
- /* Check flags */
- if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL))
- return -EINVAL;
- if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
- return -EPERM;
- mm = find_mm_struct(pid, &task_nodes);
- if (IS_ERR(mm))
- return PTR_ERR(mm);
- if (nodes)
- err = do_pages_move(mm, task_nodes, nr_pages, pages,
- nodes, status, flags);
- else
- err = do_pages_stat(mm, nr_pages, pages, status);
- mmput(mm);
- return err;
- }
- SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages,
- const void __user * __user *, pages,
- const int __user *, nodes,
- int __user *, status, int, flags)
- {
- return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags);
- }
- #ifdef CONFIG_COMPAT
- COMPAT_SYSCALL_DEFINE6(move_pages, pid_t, pid, compat_ulong_t, nr_pages,
- compat_uptr_t __user *, pages32,
- const int __user *, nodes,
- int __user *, status,
- int, flags)
- {
- const void __user * __user *pages;
- int i;
- pages = compat_alloc_user_space(nr_pages * sizeof(void *));
- for (i = 0; i < nr_pages; i++) {
- compat_uptr_t p;
- if (get_user(p, pages32 + i) ||
- put_user(compat_ptr(p), pages + i))
- return -EFAULT;
- }
- return kernel_move_pages(pid, nr_pages, pages, nodes, status, flags);
- }
- #endif /* CONFIG_COMPAT */
- #ifdef CONFIG_NUMA_BALANCING
- /*
- * Returns true if this is a safe migration target node for misplaced NUMA
- * pages. Currently it only checks the watermarks which crude
- */
- static bool migrate_balanced_pgdat(struct pglist_data *pgdat,
- unsigned long nr_migrate_pages)
- {
- int z;
- for (z = pgdat->nr_zones - 1; z >= 0; z--) {
- struct zone *zone = pgdat->node_zones + z;
- if (!populated_zone(zone))
- continue;
- /* Avoid waking kswapd by allocating pages_to_migrate pages. */
- if (!zone_watermark_ok(zone, 0,
- high_wmark_pages(zone) +
- nr_migrate_pages,
- ZONE_MOVABLE, 0))
- continue;
- return true;
- }
- return false;
- }
- static struct page *alloc_misplaced_dst_page(struct page *page,
- unsigned long data)
- {
- int nid = (int) data;
- struct page *newpage;
- newpage = __alloc_pages_node(nid,
- (GFP_HIGHUSER_MOVABLE |
- __GFP_THISNODE | __GFP_NOMEMALLOC |
- __GFP_NORETRY | __GFP_NOWARN) &
- ~__GFP_RECLAIM, 0);
- return newpage;
- }
- static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
- {
- int page_lru;
- VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page);
- /* Avoid migrating to a node that is nearly full */
- if (!migrate_balanced_pgdat(pgdat, compound_nr(page)))
- return 0;
- if (isolate_lru_page(page))
- return 0;
- /*
- * migrate_misplaced_transhuge_page() skips page migration's usual
- * check on page_count(), so we must do it here, now that the page
- * has been isolated: a GUP pin, or any other pin, prevents migration.
- * The expected page count is 3: 1 for page's mapcount and 1 for the
- * caller's pin and 1 for the reference taken by isolate_lru_page().
- */
- if (PageTransHuge(page) && page_count(page) != 3) {
- putback_lru_page(page);
- return 0;
- }
- page_lru = page_is_file_lru(page);
- mod_node_page_state(page_pgdat(page), NR_ISOLATED_ANON + page_lru,
- thp_nr_pages(page));
- /*
- * Isolating the page has taken another reference, so the
- * caller's reference can be safely dropped without the page
- * disappearing underneath us during migration.
- */
- put_page(page);
- return 1;
- }
- bool pmd_trans_migrating(pmd_t pmd)
- {
- struct page *page = pmd_page(pmd);
- return PageLocked(page);
- }
- /*
- * Attempt to migrate a misplaced page to the specified destination
- * node. Caller is expected to have an elevated reference count on
- * the page that will be dropped by this function before returning.
- */
- int migrate_misplaced_page(struct page *page, struct vm_fault *vmf,
- int node)
- {
- pg_data_t *pgdat = NODE_DATA(node);
- int isolated;
- int nr_remaining;
- LIST_HEAD(migratepages);
- /*
- * Don't migrate file pages that are mapped in multiple processes
- * with execute permissions as they are probably shared libraries.
- */
- if (page_mapcount(page) != 1 && page_is_file_lru(page) &&
- (vmf->vma_flags & VM_EXEC))
- goto out;
- /*
- * Also do not migrate dirty pages as not all filesystems can move
- * dirty pages in MIGRATE_ASYNC mode which is a waste of cycles.
- */
- if (page_is_file_lru(page) && PageDirty(page))
- goto out;
- isolated = numamigrate_isolate_page(pgdat, page);
- if (!isolated)
- goto out;
- list_add(&page->lru, &migratepages);
- nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page,
- NULL, node, MIGRATE_ASYNC,
- MR_NUMA_MISPLACED);
- if (nr_remaining) {
- if (!list_empty(&migratepages)) {
- list_del(&page->lru);
- dec_node_page_state(page, NR_ISOLATED_ANON +
- page_is_file_lru(page));
- putback_lru_page(page);
- }
- isolated = 0;
- } else
- count_vm_numa_event(NUMA_PAGE_MIGRATE);
- BUG_ON(!list_empty(&migratepages));
- return isolated;
- out:
- put_page(page);
- return 0;
- }
- #endif /* CONFIG_NUMA_BALANCING */
- #if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
- /*
- * Migrates a THP to a given target node. page must be locked and is unlocked
- * before returning.
- */
- int migrate_misplaced_transhuge_page(struct mm_struct *mm,
- struct vm_area_struct *vma,
- pmd_t *pmd, pmd_t entry,
- unsigned long address,
- struct page *page, int node)
- {
- spinlock_t *ptl;
- pg_data_t *pgdat = NODE_DATA(node);
- int isolated = 0;
- struct page *new_page = NULL;
- int page_lru = page_is_file_lru(page);
- unsigned long start = address & HPAGE_PMD_MASK;
- new_page = alloc_pages_node(node,
- (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE),
- HPAGE_PMD_ORDER);
- if (!new_page)
- goto out_fail;
- prep_transhuge_page(new_page);
- isolated = numamigrate_isolate_page(pgdat, page);
- if (!isolated) {
- put_page(new_page);
- goto out_fail;
- }
- /* Prepare a page as a migration target */
- __SetPageLocked(new_page);
- if (PageSwapBacked(page))
- __SetPageSwapBacked(new_page);
- /* anon mapping, we can simply copy page->mapping to the new page: */
- new_page->mapping = page->mapping;
- new_page->index = page->index;
- /* flush the cache before copying using the kernel virtual address */
- flush_cache_range(vma, start, start + HPAGE_PMD_SIZE);
- migrate_page_copy(new_page, page);
- WARN_ON(PageLRU(new_page));
- /* Recheck the target PMD */
- ptl = pmd_lock(mm, pmd);
- if (unlikely(!pmd_same(*pmd, entry) || !page_ref_freeze(page, 2))) {
- spin_unlock(ptl);
- /* Reverse changes made by migrate_page_copy() */
- if (TestClearPageActive(new_page))
- SetPageActive(page);
- if (TestClearPageUnevictable(new_page))
- SetPageUnevictable(page);
- unlock_page(new_page);
- put_page(new_page); /* Free it */
- /* Retake the callers reference and putback on LRU */
- get_page(page);
- putback_lru_page(page);
- mod_node_page_state(page_pgdat(page),
- NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
- goto out_unlock;
- }
- entry = mk_huge_pmd(new_page, vma->vm_page_prot);
- entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
- /*
- * Overwrite the old entry under pagetable lock and establish
- * the new PTE. Any parallel GUP will either observe the old
- * page blocking on the page lock, block on the page table
- * lock or observe the new page. The SetPageUptodate on the
- * new page and page_add_new_anon_rmap guarantee the copy is
- * visible before the pagetable update.
- */
- page_add_anon_rmap(new_page, vma, start, true);
- /*
- * At this point the pmd is numa/protnone (i.e. non present) and the TLB
- * has already been flushed globally. So no TLB can be currently
- * caching this non present pmd mapping. There's no need to clear the
- * pmd before doing set_pmd_at(), nor to flush the TLB after
- * set_pmd_at(). Clearing the pmd here would introduce a race
- * condition against MADV_DONTNEED, because MADV_DONTNEED only holds the
- * mmap_lock for reading. If the pmd is set to NULL at any given time,
- * MADV_DONTNEED won't wait on the pmd lock and it'll skip clearing this
- * pmd.
- */
- set_pmd_at(mm, start, pmd, entry);
- update_mmu_cache_pmd(vma, address, &entry);
- page_ref_unfreeze(page, 2);
- mlock_migrate_page(new_page, page);
- page_remove_rmap(page, true);
- set_page_owner_migrate_reason(new_page, MR_NUMA_MISPLACED);
- spin_unlock(ptl);
- /* Take an "isolate" reference and put new page on the LRU. */
- get_page(new_page);
- putback_lru_page(new_page);
- unlock_page(new_page);
- unlock_page(page);
- put_page(page); /* Drop the rmap reference */
- put_page(page); /* Drop the LRU isolation reference */
- count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR);
- count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR);
- mod_node_page_state(page_pgdat(page),
- NR_ISOLATED_ANON + page_lru,
- -HPAGE_PMD_NR);
- return isolated;
- out_fail:
- count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
- ptl = pmd_lock(mm, pmd);
- if (pmd_same(*pmd, entry)) {
- entry = pmd_modify(entry, vma->vm_page_prot);
- set_pmd_at(mm, start, pmd, entry);
- update_mmu_cache_pmd(vma, address, &entry);
- }
- spin_unlock(ptl);
- out_unlock:
- unlock_page(page);
- put_page(page);
- return 0;
- }
- #endif /* CONFIG_NUMA_BALANCING */
- #endif /* CONFIG_NUMA */
- #ifdef CONFIG_DEVICE_PRIVATE
- static int migrate_vma_collect_hole(unsigned long start,
- unsigned long end,
- __always_unused int depth,
- struct mm_walk *walk)
- {
- struct migrate_vma *migrate = walk->private;
- unsigned long addr;
- /* Only allow populating anonymous memory. */
- if (!vma_is_anonymous(walk->vma)) {
- for (addr = start; addr < end; addr += PAGE_SIZE) {
- migrate->src[migrate->npages] = 0;
- migrate->dst[migrate->npages] = 0;
- migrate->npages++;
- }
- return 0;
- }
- for (addr = start; addr < end; addr += PAGE_SIZE) {
- migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE;
- migrate->dst[migrate->npages] = 0;
- migrate->npages++;
- migrate->cpages++;
- }
- return 0;
- }
- static int migrate_vma_collect_skip(unsigned long start,
- unsigned long end,
- struct mm_walk *walk)
- {
- struct migrate_vma *migrate = walk->private;
- unsigned long addr;
- for (addr = start; addr < end; addr += PAGE_SIZE) {
- migrate->dst[migrate->npages] = 0;
- migrate->src[migrate->npages++] = 0;
- }
- return 0;
- }
- static int migrate_vma_collect_pmd(pmd_t *pmdp,
- unsigned long start,
- unsigned long end,
- struct mm_walk *walk)
- {
- struct migrate_vma *migrate = walk->private;
- struct vm_area_struct *vma = walk->vma;
- struct mm_struct *mm = vma->vm_mm;
- unsigned long addr = start, unmapped = 0;
- spinlock_t *ptl;
- pte_t *ptep;
- again:
- if (pmd_none(*pmdp))
- return migrate_vma_collect_hole(start, end, -1, walk);
- if (pmd_trans_huge(*pmdp)) {
- struct page *page;
- ptl = pmd_lock(mm, pmdp);
- if (unlikely(!pmd_trans_huge(*pmdp))) {
- spin_unlock(ptl);
- goto again;
- }
- page = pmd_page(*pmdp);
- if (is_huge_zero_page(page)) {
- spin_unlock(ptl);
- split_huge_pmd(vma, pmdp, addr);
- if (pmd_trans_unstable(pmdp))
- return migrate_vma_collect_skip(start, end,
- walk);
- } else {
- int ret;
- get_page(page);
- spin_unlock(ptl);
- if (unlikely(!trylock_page(page)))
- return migrate_vma_collect_skip(start, end,
- walk);
- ret = split_huge_page(page);
- unlock_page(page);
- put_page(page);
- if (ret)
- return migrate_vma_collect_skip(start, end,
- walk);
- if (pmd_none(*pmdp))
- return migrate_vma_collect_hole(start, end, -1,
- walk);
- }
- }
- if (unlikely(pmd_bad(*pmdp)))
- return migrate_vma_collect_skip(start, end, walk);
- ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
- arch_enter_lazy_mmu_mode();
- for (; addr < end; addr += PAGE_SIZE, ptep++) {
- unsigned long mpfn = 0, pfn;
- struct page *page;
- swp_entry_t entry;
- pte_t pte;
- pte = *ptep;
- if (pte_none(pte)) {
- if (vma_is_anonymous(vma)) {
- mpfn = MIGRATE_PFN_MIGRATE;
- migrate->cpages++;
- }
- goto next;
- }
- if (!pte_present(pte)) {
- /*
- * Only care about unaddressable device page special
- * page table entry. Other special swap entries are not
- * migratable, and we ignore regular swapped page.
- */
- entry = pte_to_swp_entry(pte);
- if (!is_device_private_entry(entry))
- goto next;
- page = device_private_entry_to_page(entry);
- if (!(migrate->flags &
- MIGRATE_VMA_SELECT_DEVICE_PRIVATE) ||
- page->pgmap->owner != migrate->pgmap_owner)
- goto next;
- mpfn = migrate_pfn(page_to_pfn(page)) |
- MIGRATE_PFN_MIGRATE;
- if (is_write_device_private_entry(entry))
- mpfn |= MIGRATE_PFN_WRITE;
- } else {
- if (!(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM))
- goto next;
- pfn = pte_pfn(pte);
- if (is_zero_pfn(pfn)) {
- mpfn = MIGRATE_PFN_MIGRATE;
- migrate->cpages++;
- goto next;
- }
- page = vm_normal_page(migrate->vma, addr, pte);
- mpfn = migrate_pfn(pfn) | MIGRATE_PFN_MIGRATE;
- mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0;
- }
- /* FIXME support THP */
- if (!page || !page->mapping || PageTransCompound(page)) {
- mpfn = 0;
- goto next;
- }
- /*
- * By getting a reference on the page we pin it and that blocks
- * any kind of migration. Side effect is that it "freezes" the
- * pte.
- *
- * We drop this reference after isolating the page from the lru
- * for non device page (device page are not on the lru and thus
- * can't be dropped from it).
- */
- get_page(page);
- migrate->cpages++;
- /*
- * Optimize for the common case where page is only mapped once
- * in one process. If we can lock the page, then we can safely
- * set up a special migration page table entry now.
- */
- if (trylock_page(page)) {
- pte_t swp_pte;
- mpfn |= MIGRATE_PFN_LOCKED;
- ptep_get_and_clear(mm, addr, ptep);
- /* Setup special migration page table entry */
- entry = make_migration_entry(page, mpfn &
- MIGRATE_PFN_WRITE);
- swp_pte = swp_entry_to_pte(entry);
- if (pte_present(pte)) {
- if (pte_soft_dirty(pte))
- swp_pte = pte_swp_mksoft_dirty(swp_pte);
- if (pte_uffd_wp(pte))
- swp_pte = pte_swp_mkuffd_wp(swp_pte);
- } else {
- if (pte_swp_soft_dirty(pte))
- swp_pte = pte_swp_mksoft_dirty(swp_pte);
- if (pte_swp_uffd_wp(pte))
- swp_pte = pte_swp_mkuffd_wp(swp_pte);
- }
- set_pte_at(mm, addr, ptep, swp_pte);
- /*
- * This is like regular unmap: we remove the rmap and
- * drop page refcount. Page won't be freed, as we took
- * a reference just above.
- */
- page_remove_rmap(page, false);
- put_page(page);
- if (pte_present(pte))
- unmapped++;
- }
- next:
- migrate->dst[migrate->npages] = 0;
- migrate->src[migrate->npages++] = mpfn;
- }
- arch_leave_lazy_mmu_mode();
- pte_unmap_unlock(ptep - 1, ptl);
- /* Only flush the TLB if we actually modified any entries */
- if (unmapped)
- flush_tlb_range(walk->vma, start, end);
- return 0;
- }
- static const struct mm_walk_ops migrate_vma_walk_ops = {
- .pmd_entry = migrate_vma_collect_pmd,
- .pte_hole = migrate_vma_collect_hole,
- };
- /*
- * migrate_vma_collect() - collect pages over a range of virtual addresses
- * @migrate: migrate struct containing all migration information
- *
- * This will walk the CPU page table. For each virtual address backed by a
- * valid page, it updates the src array and takes a reference on the page, in
- * order to pin the page until we lock it and unmap it.
- */
- static void migrate_vma_collect(struct migrate_vma *migrate)
- {
- struct mmu_notifier_range range;
- /*
- * Note that the pgmap_owner is passed to the mmu notifier callback so
- * that the registered device driver can skip invalidating device
- * private page mappings that won't be migrated.
- */
- mmu_notifier_range_init_migrate(&range, 0, migrate->vma,
- migrate->vma->vm_mm, migrate->start, migrate->end,
- migrate->pgmap_owner);
- mmu_notifier_invalidate_range_start(&range);
- walk_page_range(migrate->vma->vm_mm, migrate->start, migrate->end,
- &migrate_vma_walk_ops, migrate);
- mmu_notifier_invalidate_range_end(&range);
- migrate->end = migrate->start + (migrate->npages << PAGE_SHIFT);
- }
- /*
- * migrate_vma_check_page() - check if page is pinned or not
- * @page: struct page to check
- *
- * Pinned pages cannot be migrated. This is the same test as in
- * migrate_page_move_mapping(), except that here we allow migration of a
- * ZONE_DEVICE page.
- */
- static bool migrate_vma_check_page(struct page *page)
- {
- /*
- * One extra ref because caller holds an extra reference, either from
- * isolate_lru_page() for a regular page, or migrate_vma_collect() for
- * a device page.
- */
- int extra = 1;
- /*
- * FIXME support THP (transparent huge page), it is bit more complex to
- * check them than regular pages, because they can be mapped with a pmd
- * or with a pte (split pte mapping).
- */
- if (PageCompound(page))
- return false;
- /* Page from ZONE_DEVICE have one extra reference */
- if (is_zone_device_page(page)) {
- /*
- * Private page can never be pin as they have no valid pte and
- * GUP will fail for those. Yet if there is a pending migration
- * a thread might try to wait on the pte migration entry and
- * will bump the page reference count. Sadly there is no way to
- * differentiate a regular pin from migration wait. Hence to
- * avoid 2 racing thread trying to migrate back to CPU to enter
- * infinite loop (one stoping migration because the other is
- * waiting on pte migration entry). We always return true here.
- *
- * FIXME proper solution is to rework migration_entry_wait() so
- * it does not need to take a reference on page.
- */
- return is_device_private_page(page);
- }
- /* For file back page */
- if (page_mapping(page))
- extra += 1 + page_has_private(page);
- if ((page_count(page) - extra) > page_mapcount(page))
- return false;
- return true;
- }
- /*
- * migrate_vma_prepare() - lock pages and isolate them from the lru
- * @migrate: migrate struct containing all migration information
- *
- * This locks pages that have been collected by migrate_vma_collect(). Once each
- * page is locked it is isolated from the lru (for non-device pages). Finally,
- * the ref taken by migrate_vma_collect() is dropped, as locked pages cannot be
- * migrated by concurrent kernel threads.
- */
- static void migrate_vma_prepare(struct migrate_vma *migrate)
- {
- const unsigned long npages = migrate->npages;
- const unsigned long start = migrate->start;
- unsigned long addr, i, restore = 0;
- bool allow_drain = true;
- lru_add_drain();
- for (i = 0; (i < npages) && migrate->cpages; i++) {
- struct page *page = migrate_pfn_to_page(migrate->src[i]);
- bool remap = true;
- if (!page)
- continue;
- if (!(migrate->src[i] & MIGRATE_PFN_LOCKED)) {
- /*
- * Because we are migrating several pages there can be
- * a deadlock between 2 concurrent migration where each
- * are waiting on each other page lock.
- *
- * Make migrate_vma() a best effort thing and backoff
- * for any page we can not lock right away.
- */
- if (!trylock_page(page)) {
- migrate->src[i] = 0;
- migrate->cpages--;
- put_page(page);
- continue;
- }
- remap = false;
- migrate->src[i] |= MIGRATE_PFN_LOCKED;
- }
- /* ZONE_DEVICE pages are not on LRU */
- if (!is_zone_device_page(page)) {
- if (!PageLRU(page) && allow_drain) {
- /* Drain CPU's pagevec */
- lru_add_drain_all();
- allow_drain = false;
- }
- if (isolate_lru_page(page)) {
- if (remap) {
- migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
- migrate->cpages--;
- restore++;
- } else {
- migrate->src[i] = 0;
- unlock_page(page);
- migrate->cpages--;
- put_page(page);
- }
- continue;
- }
- /* Drop the reference we took in collect */
- put_page(page);
- }
- if (!migrate_vma_check_page(page)) {
- if (remap) {
- migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
- migrate->cpages--;
- restore++;
- if (!is_zone_device_page(page)) {
- get_page(page);
- putback_lru_page(page);
- }
- } else {
- migrate->src[i] = 0;
- unlock_page(page);
- migrate->cpages--;
- if (!is_zone_device_page(page))
- putback_lru_page(page);
- else
- put_page(page);
- }
- }
- }
- for (i = 0, addr = start; i < npages && restore; i++, addr += PAGE_SIZE) {
- struct page *page = migrate_pfn_to_page(migrate->src[i]);
- if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE))
- continue;
- remove_migration_pte(page, migrate->vma, addr, page);
- migrate->src[i] = 0;
- unlock_page(page);
- put_page(page);
- restore--;
- }
- }
- /*
- * migrate_vma_unmap() - replace page mapping with special migration pte entry
- * @migrate: migrate struct containing all migration information
- *
- * Replace page mapping (CPU page table pte) with a special migration pte entry
- * and check again if it has been pinned. Pinned pages are restored because we
- * cannot migrate them.
- *
- * This is the last step before we call the device driver callback to allocate
- * destination memory and copy contents of original page over to new page.
- */
- static void migrate_vma_unmap(struct migrate_vma *migrate)
- {
- int flags = TTU_MIGRATION | TTU_IGNORE_MLOCK;
- const unsigned long npages = migrate->npages;
- const unsigned long start = migrate->start;
- unsigned long addr, i, restore = 0;
- for (i = 0; i < npages; i++) {
- struct page *page = migrate_pfn_to_page(migrate->src[i]);
- if (!page || !(migrate->src[i] & MIGRATE_PFN_MIGRATE))
- continue;
- if (page_mapped(page)) {
- try_to_unmap(page, flags);
- if (page_mapped(page))
- goto restore;
- }
- if (migrate_vma_check_page(page))
- continue;
- restore:
- migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
- migrate->cpages--;
- restore++;
- }
- for (addr = start, i = 0; i < npages && restore; addr += PAGE_SIZE, i++) {
- struct page *page = migrate_pfn_to_page(migrate->src[i]);
- if (!page || (migrate->src[i] & MIGRATE_PFN_MIGRATE))
- continue;
- remove_migration_ptes(page, page, false);
- migrate->src[i] = 0;
- unlock_page(page);
- restore--;
- if (is_zone_device_page(page))
- put_page(page);
- else
- putback_lru_page(page);
- }
- }
- /**
- * migrate_vma_setup() - prepare to migrate a range of memory
- * @args: contains the vma, start, and pfns arrays for the migration
- *
- * Returns: negative errno on failures, 0 when 0 or more pages were migrated
- * without an error.
- *
- * Prepare to migrate a range of memory virtual address range by collecting all
- * the pages backing each virtual address in the range, saving them inside the
- * src array. Then lock those pages and unmap them. Once the pages are locked
- * and unmapped, check whether each page is pinned or not. Pages that aren't
- * pinned have the MIGRATE_PFN_MIGRATE flag set (by this function) in the
- * corresponding src array entry. Then restores any pages that are pinned, by
- * remapping and unlocking those pages.
- *
- * The caller should then allocate destination memory and copy source memory to
- * it for all those entries (ie with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE
- * flag set). Once these are allocated and copied, the caller must update each
- * corresponding entry in the dst array with the pfn value of the destination
- * page and with the MIGRATE_PFN_VALID and MIGRATE_PFN_LOCKED flags set
- * (destination pages must have their struct pages locked, via lock_page()).
- *
- * Note that the caller does not have to migrate all the pages that are marked
- * with MIGRATE_PFN_MIGRATE flag in src array unless this is a migration from
- * device memory to system memory. If the caller cannot migrate a device page
- * back to system memory, then it must return VM_FAULT_SIGBUS, which has severe
- * consequences for the userspace process, so it must be avoided if at all
- * possible.
- *
- * For empty entries inside CPU page table (pte_none() or pmd_none() is true) we
- * do set MIGRATE_PFN_MIGRATE flag inside the corresponding source array thus
- * allowing the caller to allocate device memory for those unback virtual
- * address. For this the caller simply has to allocate device memory and
- * properly set the destination entry like for regular migration. Note that
- * this can still fails and thus inside the device driver must check if the
- * migration was successful for those entries after calling migrate_vma_pages()
- * just like for regular migration.
- *
- * After that, the callers must call migrate_vma_pages() to go over each entry
- * in the src array that has the MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag
- * set. If the corresponding entry in dst array has MIGRATE_PFN_VALID flag set,
- * then migrate_vma_pages() to migrate struct page information from the source
- * struct page to the destination struct page. If it fails to migrate the
- * struct page information, then it clears the MIGRATE_PFN_MIGRATE flag in the
- * src array.
- *
- * At this point all successfully migrated pages have an entry in the src
- * array with MIGRATE_PFN_VALID and MIGRATE_PFN_MIGRATE flag set and the dst
- * array entry with MIGRATE_PFN_VALID flag set.
- *
- * Once migrate_vma_pages() returns the caller may inspect which pages were
- * successfully migrated, and which were not. Successfully migrated pages will
- * have the MIGRATE_PFN_MIGRATE flag set for their src array entry.
- *
- * It is safe to update device page table after migrate_vma_pages() because
- * both destination and source page are still locked, and the mmap_lock is held
- * in read mode (hence no one can unmap the range being migrated).
- *
- * Once the caller is done cleaning up things and updating its page table (if it
- * chose to do so, this is not an obligation) it finally calls
- * migrate_vma_finalize() to update the CPU page table to point to new pages
- * for successfully migrated pages or otherwise restore the CPU page table to
- * point to the original source pages.
- */
- int migrate_vma_setup(struct migrate_vma *args)
- {
- long nr_pages = (args->end - args->start) >> PAGE_SHIFT;
- args->start &= PAGE_MASK;
- args->end &= PAGE_MASK;
- if (!args->vma || is_vm_hugetlb_page(args->vma) ||
- (args->vma->vm_flags & VM_SPECIAL) || vma_is_dax(args->vma))
- return -EINVAL;
- if (nr_pages <= 0)
- return -EINVAL;
- if (args->start < args->vma->vm_start ||
- args->start >= args->vma->vm_end)
- return -EINVAL;
- if (args->end <= args->vma->vm_start || args->end > args->vma->vm_end)
- return -EINVAL;
- if (!args->src || !args->dst)
- return -EINVAL;
- memset(args->src, 0, sizeof(*args->src) * nr_pages);
- args->cpages = 0;
- args->npages = 0;
- migrate_vma_collect(args);
- if (args->cpages)
- migrate_vma_prepare(args);
- if (args->cpages)
- migrate_vma_unmap(args);
- /*
- * At this point pages are locked and unmapped, and thus they have
- * stable content and can safely be copied to destination memory that
- * is allocated by the drivers.
- */
- return 0;
- }
- EXPORT_SYMBOL(migrate_vma_setup);
- /*
- * This code closely matches the code in:
- * __handle_mm_fault()
- * handle_pte_fault()
- * do_anonymous_page()
- * to map in an anonymous zero page but the struct page will be a ZONE_DEVICE
- * private page.
- */
- static void migrate_vma_insert_page(struct migrate_vma *migrate,
- unsigned long addr,
- struct page *page,
- unsigned long *src,
- unsigned long *dst)
- {
- struct vm_area_struct *vma = migrate->vma;
- struct mm_struct *mm = vma->vm_mm;
- bool flush = false;
- spinlock_t *ptl;
- pte_t entry;
- pgd_t *pgdp;
- p4d_t *p4dp;
- pud_t *pudp;
- pmd_t *pmdp;
- pte_t *ptep;
- /* Only allow populating anonymous memory */
- if (!vma_is_anonymous(vma))
- goto abort;
- pgdp = pgd_offset(mm, addr);
- p4dp = p4d_alloc(mm, pgdp, addr);
- if (!p4dp)
- goto abort;
- pudp = pud_alloc(mm, p4dp, addr);
- if (!pudp)
- goto abort;
- pmdp = pmd_alloc(mm, pudp, addr);
- if (!pmdp)
- goto abort;
- if (pmd_trans_huge(*pmdp) || pmd_devmap(*pmdp))
- goto abort;
- /*
- * Use pte_alloc() instead of pte_alloc_map(). We can't run
- * pte_offset_map() on pmds where a huge pmd might be created
- * from a different thread.
- *
- * pte_alloc_map() is safe to use under mmap_write_lock(mm) or when
- * parallel threads are excluded by other means.
- *
- * Here we only have mmap_read_lock(mm).
- */
- if (pte_alloc(mm, pmdp))
- goto abort;
- /* See the comment in pte_alloc_one_map() */
- if (unlikely(pmd_trans_unstable(pmdp)))
- goto abort;
- if (unlikely(anon_vma_prepare(vma)))
- goto abort;
- if (mem_cgroup_charge(page, vma->vm_mm, GFP_KERNEL))
- goto abort;
- /*
- * The memory barrier inside __SetPageUptodate makes sure that
- * preceding stores to the page contents become visible before
- * the set_pte_at() write.
- */
- __SetPageUptodate(page);
- if (is_zone_device_page(page)) {
- if (is_device_private_page(page)) {
- swp_entry_t swp_entry;
- swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE);
- entry = swp_entry_to_pte(swp_entry);
- } else {
- /*
- * For now we only support migrating to un-addressable
- * device memory.
- */
- pr_warn_once("Unsupported ZONE_DEVICE page type.\n");
- goto abort;
- }
- } else {
- entry = mk_pte(page, vma->vm_page_prot);
- if (vma->vm_flags & VM_WRITE)
- entry = pte_mkwrite(pte_mkdirty(entry));
- }
- ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
- if (check_stable_address_space(mm))
- goto unlock_abort;
- if (pte_present(*ptep)) {
- unsigned long pfn = pte_pfn(*ptep);
- if (!is_zero_pfn(pfn))
- goto unlock_abort;
- flush = true;
- } else if (!pte_none(*ptep))
- goto unlock_abort;
- /*
- * Check for userfaultfd but do not deliver the fault. Instead,
- * just back off.
- */
- if (userfaultfd_missing(vma))
- goto unlock_abort;
- inc_mm_counter(mm, MM_ANONPAGES);
- page_add_new_anon_rmap(page, vma, addr, false);
- if (!is_zone_device_page(page))
- lru_cache_add_inactive_or_unevictable(page, vma);
- get_page(page);
- if (flush) {
- flush_cache_page(vma, addr, pte_pfn(*ptep));
- ptep_clear_flush_notify(vma, addr, ptep);
- set_pte_at_notify(mm, addr, ptep, entry);
- update_mmu_cache(vma, addr, ptep);
- } else {
- /* No need to invalidate - it was non-present before */
- set_pte_at(mm, addr, ptep, entry);
- update_mmu_cache(vma, addr, ptep);
- }
- pte_unmap_unlock(ptep, ptl);
- *src = MIGRATE_PFN_MIGRATE;
- return;
- unlock_abort:
- pte_unmap_unlock(ptep, ptl);
- abort:
- *src &= ~MIGRATE_PFN_MIGRATE;
- }
- /**
- * migrate_vma_pages() - migrate meta-data from src page to dst page
- * @migrate: migrate struct containing all migration information
- *
- * This migrates struct page meta-data from source struct page to destination
- * struct page. This effectively finishes the migration from source page to the
- * destination page.
- */
- void migrate_vma_pages(struct migrate_vma *migrate)
- {
- const unsigned long npages = migrate->npages;
- const unsigned long start = migrate->start;
- struct mmu_notifier_range range;
- unsigned long addr, i;
- bool notified = false;
- for (i = 0, addr = start; i < npages; addr += PAGE_SIZE, i++) {
- struct page *newpage = migrate_pfn_to_page(migrate->dst[i]);
- struct page *page = migrate_pfn_to_page(migrate->src[i]);
- struct address_space *mapping;
- int r;
- if (!newpage) {
- migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
- continue;
- }
- if (!page) {
- if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE))
- continue;
- if (!notified) {
- notified = true;
- mmu_notifier_range_init(&range,
- MMU_NOTIFY_CLEAR, 0,
- NULL,
- migrate->vma->vm_mm,
- addr, migrate->end);
- mmu_notifier_invalidate_range_start(&range);
- }
- migrate_vma_insert_page(migrate, addr, newpage,
- &migrate->src[i],
- &migrate->dst[i]);
- continue;
- }
- mapping = page_mapping(page);
- if (is_zone_device_page(newpage)) {
- if (is_device_private_page(newpage)) {
- /*
- * For now only support private anonymous when
- * migrating to un-addressable device memory.
- */
- if (mapping) {
- migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
- continue;
- }
- } else {
- /*
- * Other types of ZONE_DEVICE page are not
- * supported.
- */
- migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
- continue;
- }
- }
- r = migrate_page(mapping, newpage, page, MIGRATE_SYNC_NO_COPY);
- if (r != MIGRATEPAGE_SUCCESS)
- migrate->src[i] &= ~MIGRATE_PFN_MIGRATE;
- }
- /*
- * No need to double call mmu_notifier->invalidate_range() callback as
- * the above ptep_clear_flush_notify() inside migrate_vma_insert_page()
- * did already call it.
- */
- if (notified)
- mmu_notifier_invalidate_range_only_end(&range);
- }
- EXPORT_SYMBOL(migrate_vma_pages);
- /**
- * migrate_vma_finalize() - restore CPU page table entry
- * @migrate: migrate struct containing all migration information
- *
- * This replaces the special migration pte entry with either a mapping to the
- * new page if migration was successful for that page, or to the original page
- * otherwise.
- *
- * This also unlocks the pages and puts them back on the lru, or drops the extra
- * refcount, for device pages.
- */
- void migrate_vma_finalize(struct migrate_vma *migrate)
- {
- const unsigned long npages = migrate->npages;
- unsigned long i;
- for (i = 0; i < npages; i++) {
- struct page *newpage = migrate_pfn_to_page(migrate->dst[i]);
- struct page *page = migrate_pfn_to_page(migrate->src[i]);
- if (!page) {
- if (newpage) {
- unlock_page(newpage);
- put_page(newpage);
- }
- continue;
- }
- if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE) || !newpage) {
- if (newpage) {
- unlock_page(newpage);
- put_page(newpage);
- }
- newpage = page;
- }
- remove_migration_ptes(page, newpage, false);
- unlock_page(page);
- if (is_zone_device_page(page))
- put_page(page);
- else
- putback_lru_page(page);
- if (newpage != page) {
- unlock_page(newpage);
- if (is_zone_device_page(newpage))
- put_page(newpage);
- else
- putback_lru_page(newpage);
- }
- }
- }
- EXPORT_SYMBOL(migrate_vma_finalize);
- #endif /* CONFIG_DEVICE_PRIVATE */
|