| Author | Tokens | Token Proportion | Commits | Commit Proportion |
|---|---|---|---|---|
| Martin Schwidefsky | 7465 | 59.83% | 36 | 20.22% |
| Janosch Frank | 1396 | 11.19% | 14 | 7.87% |
| David Hildenbrand | 1305 | 10.46% | 25 | 14.04% |
| Claudio Imbrenda | 606 | 4.86% | 6 | 3.37% |
| Dominik Dingel | 348 | 2.79% | 10 | 5.62% |
| Christian Bornträger | 309 | 2.48% | 14 | 7.87% |
| Heiko Carstens | 293 | 2.35% | 13 | 7.30% |
| Nico Boehr | 120 | 0.96% | 1 | 0.56% |
| Gerald Schaefer | 94 | 0.75% | 8 | 4.49% |
| Linus Torvalds (pre-git) | 83 | 0.67% | 9 | 5.06% |
| John Levon | 66 | 0.53% | 1 | 0.56% |
| Andrew Morton | 57 | 0.46% | 3 | 1.69% |
| Qi Zheng | 45 | 0.36% | 1 | 0.56% |
| Linus Torvalds | 34 | 0.27% | 4 | 2.25% |
| Suren Baghdasaryan | 32 | 0.26% | 3 | 1.69% |
| Michel Lespinasse | 32 | 0.26% | 2 | 1.12% |
| Christoph Hellwig | 31 | 0.25% | 2 | 1.12% |
| Hugh Dickins | 30 | 0.24% | 3 | 1.69% |
| Florian Funke | 24 | 0.19% | 1 | 0.56% |
| Matthew Wilcox | 24 | 0.19% | 1 | 0.56% |
| Carsten Otte | 17 | 0.14% | 2 | 1.12% |
| Jens Freimann | 10 | 0.08% | 1 | 0.56% |
| Peter Xu | 7 | 0.06% | 2 | 1.12% |
| Konstantin Weitz | 7 | 0.06% | 1 | 0.56% |
| Joe Perches | 6 | 0.05% | 1 | 0.56% |
| Steve Capper | 6 | 0.05% | 1 | 0.56% |
| Chuhong Yuan | 5 | 0.04% | 1 | 0.56% |
| Johannes Weiner | 5 | 0.04% | 1 | 0.56% |
| Vincenzo Frascino | 3 | 0.02% | 1 | 0.56% |
| Mike Kravetz | 3 | 0.02% | 1 | 0.56% |
| Anshuman Khandual | 2 | 0.02% | 1 | 0.56% |
| Vasily Gorbik | 2 | 0.02% | 2 | 1.12% |
| Tejun Heo | 2 | 0.02% | 1 | 0.56% |
| Kirill A. Shutemov | 2 | 0.02% | 1 | 0.56% |
| Jeremy Fitzhardinge | 2 | 0.02% | 1 | 0.56% |
| Stefan Roesch | 1 | 0.01% | 1 | 0.56% |
| Mike Rapoport | 1 | 0.01% | 1 | 0.56% |
| Greg Kroah-Hartman | 1 | 0.01% | 1 | 0.56% |
| Total | 12476 | 178 |
1234567891011121314151617181920212223242526272829303132333435363738394041424344454647484950515253545556575859606162636465666768697071727374757677787980818283848586878889909192939495969798991001011021031041051061071081091101111121131141151161171181191201211221231241251261271281291301311321331341351361371381391401411421431441451461471481491501511521531541551561571581591601611621631641651661671681691701711721731741751761771781791801811821831841851861871881891901911921931941951961971981992002012022032042052062072082092102112122132142152162172182192202212222232242252262272282292302312322332342352362372382392402412422432442452462472482492502512522532542552562572582592602612622632642652662672682692702712722732742752762772782792802812822832842852862872882892902912922932942952962972982993003013023033043053063073083093103113123133143153163173183193203213223233243253263273283293303313323333343353363373383393403413423433443453463473483493503513523533543553563573583593603613623633643653663673683693703713723733743753763773783793803813823833843853863873883893903913923933943953963973983994004014024034044054064074084094104114124134144154164174184194204214224234244254264274284294304314324334344354364374384394404414424434444454464474484494504514524534544554564574584594604614624634644654664674684694704714724734744754764774784794804814824834844854864874884894904914924934944954964974984995005015025035045055065075085095105115125135145155165175185195205215225235245255265275285295305315325335345355365375385395405415425435445455465475485495505515525535545555565575585595605615625635645655665675685695705715725735745755765775785795805815825835845855865875885895905915925935945955965975985996006016026036046056066076086096106116126136146156166176186196206216226236246256266276286296306316326336346356366376386396406416426436446456466476486496506516526536546556566576586596606616626636646656666676686696706716726736746756766776786796806816826836846856866876886896906916926936946956966976986997007017027037047057067077087097107117127137147157167177187197207217227237247257267277287297307317327337347357367377387397407417427437447457467477487497507517527537547557567577587597607617627637647657667677687697707717727737747757767777787797807817827837847857867877887897907917927937947957967977987998008018028038048058068078088098108118128138148158168178188198208218228238248258268278288298308318328338348358368378388398408418428438448458468478488498508518528538548558568578588598608618628638648658668678688698708718728738748758768778788798808818828838848858868878888898908918928938948958968978988999009019029039049059069079089099109119129139149159169179189199209219229239249259269279289299309319329339349359369379389399409419429439449459469479489499509519529539549559569579589599609619629639649659669679689699709719729739749759769779789799809819829839849859869879889899909919929939949959969979989991000100110021003100410051006100710081009101010111012101310141015101610171018101910201021102210231024102510261027102810291030103110321033103410351036103710381039104010411042104310441045104610471048104910501051105210531054105510561057105810591060106110621063106410651066106710681069107010711072107310741075107610771078107910801081108210831084108510861087108810891090109110921093109410951096109710981099110011011102110311041105110611071108110911101111111211131114111511161117111811191120112111221123112411251126112711281129113011311132113311341135113611371138113911401141114211431144114511461147114811491150115111521153115411551156115711581159116011611162116311641165116611671168116911701171117211731174117511761177117811791180118111821183118411851186118711881189119011911192119311941195119611971198119912001201120212031204120512061207120812091210121112121213121412151216121712181219122012211222122312241225122612271228122912301231123212331234123512361237123812391240124112421243124412451246124712481249125012511252125312541255125612571258125912601261126212631264126512661267126812691270127112721273127412751276127712781279128012811282128312841285128612871288128912901291129212931294129512961297129812991300130113021303130413051306130713081309131013111312131313141315131613171318131913201321132213231324132513261327132813291330133113321333133413351336133713381339134013411342134313441345134613471348134913501351135213531354135513561357135813591360136113621363136413651366136713681369137013711372137313741375137613771378137913801381138213831384138513861387138813891390139113921393139413951396139713981399140014011402140314041405140614071408140914101411141214131414141514161417141814191420142114221423142414251426142714281429143014311432143314341435143614371438143914401441144214431444144514461447144814491450145114521453145414551456145714581459146014611462146314641465146614671468146914701471147214731474147514761477147814791480148114821483148414851486148714881489149014911492149314941495149614971498149915001501150215031504150515061507150815091510151115121513151415151516151715181519152015211522152315241525152615271528152915301531153215331534153515361537153815391540154115421543154415451546154715481549155015511552155315541555155615571558155915601561156215631564156515661567156815691570157115721573157415751576157715781579158015811582158315841585158615871588158915901591159215931594159515961597159815991600160116021603160416051606160716081609161016111612161316141615161616171618161916201621162216231624162516261627162816291630163116321633163416351636163716381639164016411642164316441645164616471648164916501651165216531654165516561657165816591660166116621663166416651666166716681669167016711672167316741675167616771678167916801681168216831684168516861687168816891690169116921693169416951696169716981699170017011702170317041705170617071708170917101711171217131714171517161717171817191720172117221723172417251726172717281729173017311732173317341735173617371738173917401741174217431744174517461747174817491750175117521753175417551756175717581759176017611762176317641765176617671768176917701771177217731774177517761777177817791780178117821783178417851786178717881789179017911792179317941795179617971798179918001801180218031804180518061807180818091810181118121813181418151816181718181819182018211822182318241825182618271828182918301831183218331834183518361837183818391840184118421843184418451846184718481849185018511852185318541855185618571858185918601861186218631864186518661867186818691870187118721873187418751876187718781879188018811882188318841885188618871888188918901891189218931894189518961897189818991900190119021903190419051906190719081909191019111912191319141915191619171918191919201921192219231924192519261927192819291930193119321933193419351936193719381939194019411942194319441945194619471948194919501951195219531954195519561957195819591960196119621963196419651966196719681969197019711972197319741975197619771978197919801981198219831984198519861987198819891990199119921993199419951996199719981999200020012002200320042005200620072008200920102011201220132014201520162017201820192020202120222023202420252026202720282029203020312032203320342035203620372038203920402041204220432044204520462047204820492050205120522053205420552056205720582059206020612062206320642065206620672068206920702071207220732074207520762077207820792080208120822083208420852086208720882089209020912092209320942095209620972098209921002101210221032104210521062107210821092110211121122113211421152116211721182119212021212122212321242125212621272128212921302131213221332134213521362137213821392140214121422143214421452146214721482149215021512152215321542155215621572158215921602161216221632164216521662167216821692170217121722173217421752176217721782179218021812182218321842185218621872188218921902191219221932194219521962197219821992200220122022203220422052206220722082209221022112212221322142215221622172218221922202221222222232224222522262227222822292230223122322233223422352236223722382239224022412242224322442245224622472248224922502251225222532254225522562257225822592260226122622263226422652266226722682269227022712272227322742275227622772278227922802281228222832284228522862287228822892290229122922293229422952296229722982299230023012302230323042305230623072308230923102311231223132314231523162317231823192320232123222323232423252326232723282329233023312332233323342335233623372338233923402341234223432344234523462347234823492350235123522353235423552356235723582359236023612362236323642365236623672368236923702371237223732374237523762377237823792380238123822383238423852386238723882389239023912392239323942395239623972398239924002401240224032404240524062407240824092410241124122413241424152416241724182419242024212422242324242425242624272428242924302431243224332434243524362437243824392440244124422443244424452446244724482449245024512452245324542455245624572458245924602461246224632464246524662467246824692470247124722473247424752476247724782479248024812482248324842485248624872488248924902491249224932494249524962497249824992500250125022503250425052506250725082509251025112512251325142515251625172518251925202521252225232524252525262527252825292530253125322533253425352536253725382539254025412542254325442545254625472548254925502551255225532554255525562557255825592560256125622563256425652566256725682569257025712572257325742575257625772578257925802581258225832584258525862587258825892590259125922593259425952596259725982599260026012602260326042605260626072608260926102611261226132614261526162617261826192620262126222623262426252626262726282629263026312632263326342635263626372638263926402641264226432644264526462647264826492650265126522653265426552656265726582659266026612662266326642665266626672668266926702671267226732674267526762677267826792680268126822683268426852686268726882689269026912692269326942695269626972698269927002701270227032704270527062707270827092710271127122713271427152716271727182719272027212722272327242725272627272728272927302731273227332734273527362737273827392740274127422743274427452746274727482749275027512752275327542755275627572758275927602761276227632764276527662767276827692770277127722773277427752776277727782779278027812782278327842785278627872788278927902791279227932794279527962797279827992800280128022803280428052806280728082809281028112812281328142815281628172818281928202821282228232824282528262827282828292830283128322833283428352836283728382839284028412842284328442845284628472848284928502851285228532854285528562857285828592860286128622863286428652866286728682869287028712872287328742875287628772878287928802881288228832884288528862887288828892890289128922893289428952896289728982899290029012902290329042905290629072908290929102911291229132914291529162917291829192920292129222923292429252926292729282929293029312932293329342935293629372938293929402941294229432944294529462947294829492950295129522953295429552956295729582959296029612962296329642965296629672968296929702971297229732974297529762977297829792980298129822983298429852986298729882989299029912992299329942995299629972998299930003001300230033004300530063007300830093010301130123013301430153016301730183019302030213022302330243025302630273028302930303031303230333034303530363037
// SPDX-License-Identifier: GPL-2.0 /* * KVM guest address space mapping code * * Copyright IBM Corp. 2007, 2020 * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> * David Hildenbrand <david@redhat.com> * Janosch Frank <frankja@linux.vnet.ibm.com> */ #include <linux/kernel.h> #include <linux/pagewalk.h> #include <linux/swap.h> #include <linux/smp.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/swapops.h> #include <linux/ksm.h> #include <linux/mman.h> #include <linux/pgtable.h> #include <asm/page-states.h> #include <asm/pgalloc.h> #include <asm/gmap.h> #include <asm/page.h> #include <asm/tlb.h> #define GMAP_SHADOW_FAKE_TABLE 1ULL static struct page *gmap_alloc_crst(void) { struct page *page; page = alloc_pages(GFP_KERNEL_ACCOUNT, CRST_ALLOC_ORDER); if (!page) return NULL; __arch_set_page_dat(page_to_virt(page), 1UL << CRST_ALLOC_ORDER); return page; } /** * gmap_alloc - allocate and initialize a guest address space * @limit: maximum address of the gmap address space * * Returns a guest address space structure. */ static struct gmap *gmap_alloc(unsigned long limit) { struct gmap *gmap; struct page *page; unsigned long *table; unsigned long etype, atype; if (limit < _REGION3_SIZE) { limit = _REGION3_SIZE - 1; atype = _ASCE_TYPE_SEGMENT; etype = _SEGMENT_ENTRY_EMPTY; } else if (limit < _REGION2_SIZE) { limit = _REGION2_SIZE - 1; atype = _ASCE_TYPE_REGION3; etype = _REGION3_ENTRY_EMPTY; } else if (limit < _REGION1_SIZE) { limit = _REGION1_SIZE - 1; atype = _ASCE_TYPE_REGION2; etype = _REGION2_ENTRY_EMPTY; } else { limit = -1UL; atype = _ASCE_TYPE_REGION1; etype = _REGION1_ENTRY_EMPTY; } gmap = kzalloc(sizeof(struct gmap), GFP_KERNEL_ACCOUNT); if (!gmap) goto out; INIT_LIST_HEAD(&gmap->crst_list); INIT_LIST_HEAD(&gmap->children); INIT_LIST_HEAD(&gmap->pt_list); INIT_RADIX_TREE(&gmap->guest_to_host, GFP_KERNEL_ACCOUNT); INIT_RADIX_TREE(&gmap->host_to_guest, GFP_ATOMIC | __GFP_ACCOUNT); INIT_RADIX_TREE(&gmap->host_to_rmap, GFP_ATOMIC | __GFP_ACCOUNT); spin_lock_init(&gmap->guest_table_lock); spin_lock_init(&gmap->shadow_lock); refcount_set(&gmap->ref_count, 1); page = gmap_alloc_crst(); if (!page) goto out_free; page->index = 0; list_add(&page->lru, &gmap->crst_list); table = page_to_virt(page); crst_table_init(table, etype); gmap->table = table; gmap->asce = atype | _ASCE_TABLE_LENGTH | _ASCE_USER_BITS | __pa(table); gmap->asce_end = limit; return gmap; out_free: kfree(gmap); out: return NULL; } /** * gmap_create - create a guest address space * @mm: pointer to the parent mm_struct * @limit: maximum size of the gmap address space * * Returns a guest address space structure. */ struct gmap *gmap_create(struct mm_struct *mm, unsigned long limit) { struct gmap *gmap; unsigned long gmap_asce; gmap = gmap_alloc(limit); if (!gmap) return NULL; gmap->mm = mm; spin_lock(&mm->context.lock); list_add_rcu(&gmap->list, &mm->context.gmap_list); if (list_is_singular(&mm->context.gmap_list)) gmap_asce = gmap->asce; else gmap_asce = -1UL; WRITE_ONCE(mm->context.gmap_asce, gmap_asce); spin_unlock(&mm->context.lock); return gmap; } EXPORT_SYMBOL_GPL(gmap_create); static void gmap_flush_tlb(struct gmap *gmap) { if (MACHINE_HAS_IDTE) __tlb_flush_idte(gmap->asce); else __tlb_flush_global(); } static void gmap_radix_tree_free(struct radix_tree_root *root) { struct radix_tree_iter iter; unsigned long indices[16]; unsigned long index; void __rcu **slot; int i, nr; /* A radix tree is freed by deleting all of its entries */ index = 0; do { nr = 0; radix_tree_for_each_slot(slot, root, &iter, index) { indices[nr] = iter.index; if (++nr == 16) break; } for (i = 0; i < nr; i++) { index = indices[i]; radix_tree_delete(root, index); } } while (nr > 0); } static void gmap_rmap_radix_tree_free(struct radix_tree_root *root) { struct gmap_rmap *rmap, *rnext, *head; struct radix_tree_iter iter; unsigned long indices[16]; unsigned long index; void __rcu **slot; int i, nr; /* A radix tree is freed by deleting all of its entries */ index = 0; do { nr = 0; radix_tree_for_each_slot(slot, root, &iter, index) { indices[nr] = iter.index; if (++nr == 16) break; } for (i = 0; i < nr; i++) { index = indices[i]; head = radix_tree_delete(root, index); gmap_for_each_rmap_safe(rmap, rnext, head) kfree(rmap); } } while (nr > 0); } /** * gmap_free - free a guest address space * @gmap: pointer to the guest address space structure * * No locks required. There are no references to this gmap anymore. */ static void gmap_free(struct gmap *gmap) { struct page *page, *next; /* Flush tlb of all gmaps (if not already done for shadows) */ if (!(gmap_is_shadow(gmap) && gmap->removed)) gmap_flush_tlb(gmap); /* Free all segment & region tables. */ list_for_each_entry_safe(page, next, &gmap->crst_list, lru) __free_pages(page, CRST_ALLOC_ORDER); gmap_radix_tree_free(&gmap->guest_to_host); gmap_radix_tree_free(&gmap->host_to_guest); /* Free additional data for a shadow gmap */ if (gmap_is_shadow(gmap)) { struct ptdesc *ptdesc, *n; /* Free all page tables. */ list_for_each_entry_safe(ptdesc, n, &gmap->pt_list, pt_list) page_table_free_pgste(ptdesc); gmap_rmap_radix_tree_free(&gmap->host_to_rmap); /* Release reference to the parent */ gmap_put(gmap->parent); } kfree(gmap); } /** * gmap_get - increase reference counter for guest address space * @gmap: pointer to the guest address space structure * * Returns the gmap pointer */ struct gmap *gmap_get(struct gmap *gmap) { refcount_inc(&gmap->ref_count); return gmap; } EXPORT_SYMBOL_GPL(gmap_get); /** * gmap_put - decrease reference counter for guest address space * @gmap: pointer to the guest address space structure * * If the reference counter reaches zero the guest address space is freed. */ void gmap_put(struct gmap *gmap) { if (refcount_dec_and_test(&gmap->ref_count)) gmap_free(gmap); } EXPORT_SYMBOL_GPL(gmap_put); /** * gmap_remove - remove a guest address space but do not free it yet * @gmap: pointer to the guest address space structure */ void gmap_remove(struct gmap *gmap) { struct gmap *sg, *next; unsigned long gmap_asce; /* Remove all shadow gmaps linked to this gmap */ if (!list_empty(&gmap->children)) { spin_lock(&gmap->shadow_lock); list_for_each_entry_safe(sg, next, &gmap->children, list) { list_del(&sg->list); gmap_put(sg); } spin_unlock(&gmap->shadow_lock); } /* Remove gmap from the pre-mm list */ spin_lock(&gmap->mm->context.lock); list_del_rcu(&gmap->list); if (list_empty(&gmap->mm->context.gmap_list)) gmap_asce = 0; else if (list_is_singular(&gmap->mm->context.gmap_list)) gmap_asce = list_first_entry(&gmap->mm->context.gmap_list, struct gmap, list)->asce; else gmap_asce = -1UL; WRITE_ONCE(gmap->mm->context.gmap_asce, gmap_asce); spin_unlock(&gmap->mm->context.lock); synchronize_rcu(); /* Put reference */ gmap_put(gmap); } EXPORT_SYMBOL_GPL(gmap_remove); /* * gmap_alloc_table is assumed to be called with mmap_lock held */ static int gmap_alloc_table(struct gmap *gmap, unsigned long *table, unsigned long init, unsigned long gaddr) { struct page *page; unsigned long *new; /* since we dont free the gmap table until gmap_free we can unlock */ page = gmap_alloc_crst(); if (!page) return -ENOMEM; new = page_to_virt(page); crst_table_init(new, init); spin_lock(&gmap->guest_table_lock); if (*table & _REGION_ENTRY_INVALID) { list_add(&page->lru, &gmap->crst_list); *table = __pa(new) | _REGION_ENTRY_LENGTH | (*table & _REGION_ENTRY_TYPE_MASK); page->index = gaddr; page = NULL; } spin_unlock(&gmap->guest_table_lock); if (page) __free_pages(page, CRST_ALLOC_ORDER); return 0; } /** * __gmap_segment_gaddr - find virtual address from segment pointer * @entry: pointer to a segment table entry in the guest address space * * Returns the virtual address in the guest address space for the segment */ static unsigned long __gmap_segment_gaddr(unsigned long *entry) { struct page *page; unsigned long offset; offset = (unsigned long) entry / sizeof(unsigned long); offset = (offset & (PTRS_PER_PMD - 1)) * PMD_SIZE; page = pmd_pgtable_page((pmd_t *) entry); return page->index + offset; } /** * __gmap_unlink_by_vmaddr - unlink a single segment via a host address * @gmap: pointer to the guest address space structure * @vmaddr: address in the host process address space * * Returns 1 if a TLB flush is required */ static int __gmap_unlink_by_vmaddr(struct gmap *gmap, unsigned long vmaddr) { unsigned long *entry; int flush = 0; BUG_ON(gmap_is_shadow(gmap)); spin_lock(&gmap->guest_table_lock); entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT); if (entry) { flush = (*entry != _SEGMENT_ENTRY_EMPTY); *entry = _SEGMENT_ENTRY_EMPTY; } spin_unlock(&gmap->guest_table_lock); return flush; } /** * __gmap_unmap_by_gaddr - unmap a single segment via a guest address * @gmap: pointer to the guest address space structure * @gaddr: address in the guest address space * * Returns 1 if a TLB flush is required */ static int __gmap_unmap_by_gaddr(struct gmap *gmap, unsigned long gaddr) { unsigned long vmaddr; vmaddr = (unsigned long) radix_tree_delete(&gmap->guest_to_host, gaddr >> PMD_SHIFT); return vmaddr ? __gmap_unlink_by_vmaddr(gmap, vmaddr) : 0; } /** * gmap_unmap_segment - unmap segment from the guest address space * @gmap: pointer to the guest address space structure * @to: address in the guest address space * @len: length of the memory area to unmap * * Returns 0 if the unmap succeeded, -EINVAL if not. */ int gmap_unmap_segment(struct gmap *gmap, unsigned long to, unsigned long len) { unsigned long off; int flush; BUG_ON(gmap_is_shadow(gmap)); if ((to | len) & (PMD_SIZE - 1)) return -EINVAL; if (len == 0 || to + len < to) return -EINVAL; flush = 0; mmap_write_lock(gmap->mm); for (off = 0; off < len; off += PMD_SIZE) flush |= __gmap_unmap_by_gaddr(gmap, to + off); mmap_write_unlock(gmap->mm); if (flush) gmap_flush_tlb(gmap); return 0; } EXPORT_SYMBOL_GPL(gmap_unmap_segment); /** * gmap_map_segment - map a segment to the guest address space * @gmap: pointer to the guest address space structure * @from: source address in the parent address space * @to: target address in the guest address space * @len: length of the memory area to map * * Returns 0 if the mmap succeeded, -EINVAL or -ENOMEM if not. */ int gmap_map_segment(struct gmap *gmap, unsigned long from, unsigned long to, unsigned long len) { unsigned long off; int flush; BUG_ON(gmap_is_shadow(gmap)); if ((from | to | len) & (PMD_SIZE - 1)) return -EINVAL; if (len == 0 || from + len < from || to + len < to || from + len - 1 > TASK_SIZE_MAX || to + len - 1 > gmap->asce_end) return -EINVAL; flush = 0; mmap_write_lock(gmap->mm); for (off = 0; off < len; off += PMD_SIZE) { /* Remove old translation */ flush |= __gmap_unmap_by_gaddr(gmap, to + off); /* Store new translation */ if (radix_tree_insert(&gmap->guest_to_host, (to + off) >> PMD_SHIFT, (void *) from + off)) break; } mmap_write_unlock(gmap->mm); if (flush) gmap_flush_tlb(gmap); if (off >= len) return 0; gmap_unmap_segment(gmap, to, len); return -ENOMEM; } EXPORT_SYMBOL_GPL(gmap_map_segment); /** * __gmap_translate - translate a guest address to a user space address * @gmap: pointer to guest mapping meta data structure * @gaddr: guest address * * Returns user space address which corresponds to the guest address or * -EFAULT if no such mapping exists. * This function does not establish potentially missing page table entries. * The mmap_lock of the mm that belongs to the address space must be held * when this function gets called. * * Note: Can also be called for shadow gmaps. */ unsigned long __gmap_translate(struct gmap *gmap, unsigned long gaddr) { unsigned long vmaddr; vmaddr = (unsigned long) radix_tree_lookup(&gmap->guest_to_host, gaddr >> PMD_SHIFT); /* Note: guest_to_host is empty for a shadow gmap */ return vmaddr ? (vmaddr | (gaddr & ~PMD_MASK)) : -EFAULT; } EXPORT_SYMBOL_GPL(__gmap_translate); /** * gmap_translate - translate a guest address to a user space address * @gmap: pointer to guest mapping meta data structure * @gaddr: guest address * * Returns user space address which corresponds to the guest address or * -EFAULT if no such mapping exists. * This function does not establish potentially missing page table entries. */ unsigned long gmap_translate(struct gmap *gmap, unsigned long gaddr) { unsigned long rc; mmap_read_lock(gmap->mm); rc = __gmap_translate(gmap, gaddr); mmap_read_unlock(gmap->mm); return rc; } EXPORT_SYMBOL_GPL(gmap_translate); /** * gmap_unlink - disconnect a page table from the gmap shadow tables * @mm: pointer to the parent mm_struct * @table: pointer to the host page table * @vmaddr: vm address associated with the host page table */ void gmap_unlink(struct mm_struct *mm, unsigned long *table, unsigned long vmaddr) { struct gmap *gmap; int flush; rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { flush = __gmap_unlink_by_vmaddr(gmap, vmaddr); if (flush) gmap_flush_tlb(gmap); } rcu_read_unlock(); } static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *old, pmd_t new, unsigned long gaddr); /** * __gmap_link - set up shadow page tables to connect a host to a guest address * @gmap: pointer to guest mapping meta data structure * @gaddr: guest address * @vmaddr: vm address * * Returns 0 on success, -ENOMEM for out of memory conditions, and -EFAULT * if the vm address is already mapped to a different guest segment. * The mmap_lock of the mm that belongs to the address space must be held * when this function gets called. */ int __gmap_link(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr) { struct mm_struct *mm; unsigned long *table; spinlock_t *ptl; pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; u64 unprot; int rc; BUG_ON(gmap_is_shadow(gmap)); /* Create higher level tables in the gmap page table */ table = gmap->table; if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION1) { table += (gaddr & _REGION1_INDEX) >> _REGION1_SHIFT; if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _REGION2_ENTRY_EMPTY, gaddr & _REGION1_MASK)) return -ENOMEM; table = __va(*table & _REGION_ENTRY_ORIGIN); } if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION2) { table += (gaddr & _REGION2_INDEX) >> _REGION2_SHIFT; if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _REGION3_ENTRY_EMPTY, gaddr & _REGION2_MASK)) return -ENOMEM; table = __va(*table & _REGION_ENTRY_ORIGIN); } if ((gmap->asce & _ASCE_TYPE_MASK) >= _ASCE_TYPE_REGION3) { table += (gaddr & _REGION3_INDEX) >> _REGION3_SHIFT; if ((*table & _REGION_ENTRY_INVALID) && gmap_alloc_table(gmap, table, _SEGMENT_ENTRY_EMPTY, gaddr & _REGION3_MASK)) return -ENOMEM; table = __va(*table & _REGION_ENTRY_ORIGIN); } table += (gaddr & _SEGMENT_INDEX) >> _SEGMENT_SHIFT; /* Walk the parent mm page table */ mm = gmap->mm; pgd = pgd_offset(mm, vmaddr); VM_BUG_ON(pgd_none(*pgd)); p4d = p4d_offset(pgd, vmaddr); VM_BUG_ON(p4d_none(*p4d)); pud = pud_offset(p4d, vmaddr); VM_BUG_ON(pud_none(*pud)); /* large puds cannot yet be handled */ if (pud_leaf(*pud)) return -EFAULT; pmd = pmd_offset(pud, vmaddr); VM_BUG_ON(pmd_none(*pmd)); /* Are we allowed to use huge pages? */ if (pmd_leaf(*pmd) && !gmap->mm->context.allow_gmap_hpage_1m) return -EFAULT; /* Link gmap segment table entry location to page table. */ rc = radix_tree_preload(GFP_KERNEL_ACCOUNT); if (rc) return rc; ptl = pmd_lock(mm, pmd); spin_lock(&gmap->guest_table_lock); if (*table == _SEGMENT_ENTRY_EMPTY) { rc = radix_tree_insert(&gmap->host_to_guest, vmaddr >> PMD_SHIFT, table); if (!rc) { if (pmd_leaf(*pmd)) { *table = (pmd_val(*pmd) & _SEGMENT_ENTRY_HARDWARE_BITS_LARGE) | _SEGMENT_ENTRY_GMAP_UC | _SEGMENT_ENTRY; } else *table = pmd_val(*pmd) & _SEGMENT_ENTRY_HARDWARE_BITS; } } else if (*table & _SEGMENT_ENTRY_PROTECT && !(pmd_val(*pmd) & _SEGMENT_ENTRY_PROTECT)) { unprot = (u64)*table; unprot &= ~_SEGMENT_ENTRY_PROTECT; unprot |= _SEGMENT_ENTRY_GMAP_UC; gmap_pmdp_xchg(gmap, (pmd_t *)table, __pmd(unprot), gaddr); } spin_unlock(&gmap->guest_table_lock); spin_unlock(ptl); radix_tree_preload_end(); return rc; } /** * fixup_user_fault_nowait - manually resolve a user page fault without waiting * @mm: mm_struct of target mm * @address: user address * @fault_flags:flags to pass down to handle_mm_fault() * @unlocked: did we unlock the mmap_lock while retrying * * This function behaves similarly to fixup_user_fault(), but it guarantees * that the fault will be resolved without waiting. The function might drop * and re-acquire the mm lock, in which case @unlocked will be set to true. * * The guarantee is that the fault is handled without waiting, but the * function itself might sleep, due to the lock. * * Context: Needs to be called with mm->mmap_lock held in read mode, and will * return with the lock held in read mode; @unlocked will indicate whether * the lock has been dropped and re-acquired. This is the same behaviour as * fixup_user_fault(). * * Return: 0 on success, -EAGAIN if the fault cannot be resolved without * waiting, -EFAULT if the fault cannot be resolved, -ENOMEM if out of * memory. */ static int fixup_user_fault_nowait(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { struct vm_area_struct *vma; unsigned int test_flags; vm_fault_t fault; int rc; fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; test_flags = fault_flags & FAULT_FLAG_WRITE ? VM_WRITE : VM_READ; vma = find_vma(mm, address); if (unlikely(!vma || address < vma->vm_start)) return -EFAULT; if (unlikely(!(vma->vm_flags & test_flags))) return -EFAULT; fault = handle_mm_fault(vma, address, fault_flags, NULL); /* the mm lock has been dropped, take it again */ if (fault & VM_FAULT_COMPLETED) { *unlocked = true; mmap_read_lock(mm); return 0; } /* the mm lock has not been dropped */ if (fault & VM_FAULT_ERROR) { rc = vm_fault_to_errno(fault, 0); BUG_ON(!rc); return rc; } /* the mm lock has not been dropped because of FAULT_FLAG_RETRY_NOWAIT */ if (fault & VM_FAULT_RETRY) return -EAGAIN; /* nothing needed to be done and the mm lock has not been dropped */ return 0; } /** * __gmap_fault - resolve a fault on a guest address * @gmap: pointer to guest mapping meta data structure * @gaddr: guest address * @fault_flags: flags to pass down to handle_mm_fault() * * Context: Needs to be called with mm->mmap_lock held in read mode. Might * drop and re-acquire the lock. Will always return with the lock held. */ static int __gmap_fault(struct gmap *gmap, unsigned long gaddr, unsigned int fault_flags) { unsigned long vmaddr; bool unlocked; int rc = 0; retry: unlocked = false; vmaddr = __gmap_translate(gmap, gaddr); if (IS_ERR_VALUE(vmaddr)) return vmaddr; if (fault_flags & FAULT_FLAG_RETRY_NOWAIT) rc = fixup_user_fault_nowait(gmap->mm, vmaddr, fault_flags, &unlocked); else rc = fixup_user_fault(gmap->mm, vmaddr, fault_flags, &unlocked); if (rc) return rc; /* * In the case that fixup_user_fault unlocked the mmap_lock during * fault-in, redo __gmap_translate() to avoid racing with a * map/unmap_segment. * In particular, __gmap_translate(), fixup_user_fault{,_nowait}(), * and __gmap_link() must all be called atomically in one go; if the * lock had been dropped in between, a retry is needed. */ if (unlocked) goto retry; return __gmap_link(gmap, gaddr, vmaddr); } /** * gmap_fault - resolve a fault on a guest address * @gmap: pointer to guest mapping meta data structure * @gaddr: guest address * @fault_flags: flags to pass down to handle_mm_fault() * * Returns 0 on success, -ENOMEM for out of memory conditions, -EFAULT if the * vm address is already mapped to a different guest segment, and -EAGAIN if * FAULT_FLAG_RETRY_NOWAIT was specified and the fault could not be processed * immediately. */ int gmap_fault(struct gmap *gmap, unsigned long gaddr, unsigned int fault_flags) { int rc; mmap_read_lock(gmap->mm); rc = __gmap_fault(gmap, gaddr, fault_flags); mmap_read_unlock(gmap->mm); return rc; } EXPORT_SYMBOL_GPL(gmap_fault); /* * this function is assumed to be called with mmap_lock held */ void __gmap_zap(struct gmap *gmap, unsigned long gaddr) { struct vm_area_struct *vma; unsigned long vmaddr; spinlock_t *ptl; pte_t *ptep; /* Find the vm address for the guest address */ vmaddr = (unsigned long) radix_tree_lookup(&gmap->guest_to_host, gaddr >> PMD_SHIFT); if (vmaddr) { vmaddr |= gaddr & ~PMD_MASK; vma = vma_lookup(gmap->mm, vmaddr); if (!vma || is_vm_hugetlb_page(vma)) return; /* Get pointer to the page table entry */ ptep = get_locked_pte(gmap->mm, vmaddr, &ptl); if (likely(ptep)) { ptep_zap_unused(gmap->mm, vmaddr, ptep, 0); pte_unmap_unlock(ptep, ptl); } } } EXPORT_SYMBOL_GPL(__gmap_zap); void gmap_discard(struct gmap *gmap, unsigned long from, unsigned long to) { unsigned long gaddr, vmaddr, size; struct vm_area_struct *vma; mmap_read_lock(gmap->mm); for (gaddr = from; gaddr < to; gaddr = (gaddr + PMD_SIZE) & PMD_MASK) { /* Find the vm address for the guest address */ vmaddr = (unsigned long) radix_tree_lookup(&gmap->guest_to_host, gaddr >> PMD_SHIFT); if (!vmaddr) continue; vmaddr |= gaddr & ~PMD_MASK; /* Find vma in the parent mm */ vma = find_vma(gmap->mm, vmaddr); if (!vma) continue; /* * We do not discard pages that are backed by * hugetlbfs, so we don't have to refault them. */ if (is_vm_hugetlb_page(vma)) continue; size = min(to - gaddr, PMD_SIZE - (gaddr & ~PMD_MASK)); zap_page_range_single(vma, vmaddr, size, NULL); } mmap_read_unlock(gmap->mm); } EXPORT_SYMBOL_GPL(gmap_discard); static LIST_HEAD(gmap_notifier_list); static DEFINE_SPINLOCK(gmap_notifier_lock); /** * gmap_register_pte_notifier - register a pte invalidation callback * @nb: pointer to the gmap notifier block */ void gmap_register_pte_notifier(struct gmap_notifier *nb) { spin_lock(&gmap_notifier_lock); list_add_rcu(&nb->list, &gmap_notifier_list); spin_unlock(&gmap_notifier_lock); } EXPORT_SYMBOL_GPL(gmap_register_pte_notifier); /** * gmap_unregister_pte_notifier - remove a pte invalidation callback * @nb: pointer to the gmap notifier block */ void gmap_unregister_pte_notifier(struct gmap_notifier *nb) { spin_lock(&gmap_notifier_lock); list_del_rcu(&nb->list); spin_unlock(&gmap_notifier_lock); synchronize_rcu(); } EXPORT_SYMBOL_GPL(gmap_unregister_pte_notifier); /** * gmap_call_notifier - call all registered invalidation callbacks * @gmap: pointer to guest mapping meta data structure * @start: start virtual address in the guest address space * @end: end virtual address in the guest address space */ static void gmap_call_notifier(struct gmap *gmap, unsigned long start, unsigned long end) { struct gmap_notifier *nb; list_for_each_entry(nb, &gmap_notifier_list, list) nb->notifier_call(gmap, start, end); } /** * gmap_table_walk - walk the gmap page tables * @gmap: pointer to guest mapping meta data structure * @gaddr: virtual address in the guest address space * @level: page table level to stop at * * Returns a table entry pointer for the given guest address and @level * @level=0 : returns a pointer to a page table table entry (or NULL) * @level=1 : returns a pointer to a segment table entry (or NULL) * @level=2 : returns a pointer to a region-3 table entry (or NULL) * @level=3 : returns a pointer to a region-2 table entry (or NULL) * @level=4 : returns a pointer to a region-1 table entry (or NULL) * * Returns NULL if the gmap page tables could not be walked to the * requested level. * * Note: Can also be called for shadow gmaps. */ static inline unsigned long *gmap_table_walk(struct gmap *gmap, unsigned long gaddr, int level) { const int asce_type = gmap->asce & _ASCE_TYPE_MASK; unsigned long *table = gmap->table; if (gmap_is_shadow(gmap) && gmap->removed) return NULL; if (WARN_ON_ONCE(level > (asce_type >> 2) + 1)) return NULL; if (asce_type != _ASCE_TYPE_REGION1 && gaddr & (-1UL << (31 + (asce_type >> 2) * 11))) return NULL; switch (asce_type) { case _ASCE_TYPE_REGION1: table += (gaddr & _REGION1_INDEX) >> _REGION1_SHIFT; if (level == 4) break; if (*table & _REGION_ENTRY_INVALID) return NULL; table = __va(*table & _REGION_ENTRY_ORIGIN); fallthrough; case _ASCE_TYPE_REGION2: table += (gaddr & _REGION2_INDEX) >> _REGION2_SHIFT; if (level == 3) break; if (*table & _REGION_ENTRY_INVALID) return NULL; table = __va(*table & _REGION_ENTRY_ORIGIN); fallthrough; case _ASCE_TYPE_REGION3: table += (gaddr & _REGION3_INDEX) >> _REGION3_SHIFT; if (level == 2) break; if (*table & _REGION_ENTRY_INVALID) return NULL; table = __va(*table & _REGION_ENTRY_ORIGIN); fallthrough; case _ASCE_TYPE_SEGMENT: table += (gaddr & _SEGMENT_INDEX) >> _SEGMENT_SHIFT; if (level == 1) break; if (*table & _REGION_ENTRY_INVALID) return NULL; table = __va(*table & _SEGMENT_ENTRY_ORIGIN); table += (gaddr & _PAGE_INDEX) >> PAGE_SHIFT; } return table; } /** * gmap_pte_op_walk - walk the gmap page table, get the page table lock * and return the pte pointer * @gmap: pointer to guest mapping meta data structure * @gaddr: virtual address in the guest address space * @ptl: pointer to the spinlock pointer * * Returns a pointer to the locked pte for a guest address, or NULL */ static pte_t *gmap_pte_op_walk(struct gmap *gmap, unsigned long gaddr, spinlock_t **ptl) { unsigned long *table; BUG_ON(gmap_is_shadow(gmap)); /* Walk the gmap page table, lock and get pte pointer */ table = gmap_table_walk(gmap, gaddr, 1); /* get segment pointer */ if (!table || *table & _SEGMENT_ENTRY_INVALID) return NULL; return pte_alloc_map_lock(gmap->mm, (pmd_t *) table, gaddr, ptl); } /** * gmap_pte_op_fixup - force a page in and connect the gmap page table * @gmap: pointer to guest mapping meta data structure * @gaddr: virtual address in the guest address space * @vmaddr: address in the host process address space * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE * * Returns 0 if the caller can retry __gmap_translate (might fail again), * -ENOMEM if out of memory and -EFAULT if anything goes wrong while fixing * up or connecting the gmap page table. */ static int gmap_pte_op_fixup(struct gmap *gmap, unsigned long gaddr, unsigned long vmaddr, int prot) { struct mm_struct *mm = gmap->mm; unsigned int fault_flags; bool unlocked = false; BUG_ON(gmap_is_shadow(gmap)); fault_flags = (prot == PROT_WRITE) ? FAULT_FLAG_WRITE : 0; if (fixup_user_fault(mm, vmaddr, fault_flags, &unlocked)) return -EFAULT; if (unlocked) /* lost mmap_lock, caller has to retry __gmap_translate */ return 0; /* Connect the page tables */ return __gmap_link(gmap, gaddr, vmaddr); } /** * gmap_pte_op_end - release the page table lock * @ptep: pointer to the locked pte * @ptl: pointer to the page table spinlock */ static void gmap_pte_op_end(pte_t *ptep, spinlock_t *ptl) { pte_unmap_unlock(ptep, ptl); } /** * gmap_pmd_op_walk - walk the gmap tables, get the guest table lock * and return the pmd pointer * @gmap: pointer to guest mapping meta data structure * @gaddr: virtual address in the guest address space * * Returns a pointer to the pmd for a guest address, or NULL */ static inline pmd_t *gmap_pmd_op_walk(struct gmap *gmap, unsigned long gaddr) { pmd_t *pmdp; BUG_ON(gmap_is_shadow(gmap)); pmdp = (pmd_t *) gmap_table_walk(gmap, gaddr, 1); if (!pmdp) return NULL; /* without huge pages, there is no need to take the table lock */ if (!gmap->mm->context.allow_gmap_hpage_1m) return pmd_none(*pmdp) ? NULL : pmdp; spin_lock(&gmap->guest_table_lock); if (pmd_none(*pmdp)) { spin_unlock(&gmap->guest_table_lock); return NULL; } /* 4k page table entries are locked via the pte (pte_alloc_map_lock). */ if (!pmd_leaf(*pmdp)) spin_unlock(&gmap->guest_table_lock); return pmdp; } /** * gmap_pmd_op_end - release the guest_table_lock if needed * @gmap: pointer to the guest mapping meta data structure * @pmdp: pointer to the pmd */ static inline void gmap_pmd_op_end(struct gmap *gmap, pmd_t *pmdp) { if (pmd_leaf(*pmdp)) spin_unlock(&gmap->guest_table_lock); } /* * gmap_protect_pmd - remove access rights to memory and set pmd notification bits * @pmdp: pointer to the pmd to be protected * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE * @bits: notification bits to set * * Returns: * 0 if successfully protected * -EAGAIN if a fixup is needed * -EINVAL if unsupported notifier bits have been specified * * Expected to be called with sg->mm->mmap_lock in read and * guest_table_lock held. */ static int gmap_protect_pmd(struct gmap *gmap, unsigned long gaddr, pmd_t *pmdp, int prot, unsigned long bits) { int pmd_i = pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID; int pmd_p = pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT; pmd_t new = *pmdp; /* Fixup needed */ if ((pmd_i && (prot != PROT_NONE)) || (pmd_p && (prot == PROT_WRITE))) return -EAGAIN; if (prot == PROT_NONE && !pmd_i) { new = set_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_INVALID)); gmap_pmdp_xchg(gmap, pmdp, new, gaddr); } if (prot == PROT_READ && !pmd_p) { new = clear_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_INVALID)); new = set_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_PROTECT)); gmap_pmdp_xchg(gmap, pmdp, new, gaddr); } if (bits & GMAP_NOTIFY_MPROT) set_pmd(pmdp, set_pmd_bit(*pmdp, __pgprot(_SEGMENT_ENTRY_GMAP_IN))); /* Shadow GMAP protection needs split PMDs */ if (bits & GMAP_NOTIFY_SHADOW) return -EINVAL; return 0; } /* * gmap_protect_pte - remove access rights to memory and set pgste bits * @gmap: pointer to guest mapping meta data structure * @gaddr: virtual address in the guest address space * @pmdp: pointer to the pmd associated with the pte * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE * @bits: notification bits to set * * Returns 0 if successfully protected, -ENOMEM if out of memory and * -EAGAIN if a fixup is needed. * * Expected to be called with sg->mm->mmap_lock in read */ static int gmap_protect_pte(struct gmap *gmap, unsigned long gaddr, pmd_t *pmdp, int prot, unsigned long bits) { int rc; pte_t *ptep; spinlock_t *ptl; unsigned long pbits = 0; if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID) return -EAGAIN; ptep = pte_alloc_map_lock(gmap->mm, pmdp, gaddr, &ptl); if (!ptep) return -ENOMEM; pbits |= (bits & GMAP_NOTIFY_MPROT) ? PGSTE_IN_BIT : 0; pbits |= (bits & GMAP_NOTIFY_SHADOW) ? PGSTE_VSIE_BIT : 0; /* Protect and unlock. */ rc = ptep_force_prot(gmap->mm, gaddr, ptep, prot, pbits); gmap_pte_op_end(ptep, ptl); return rc; } /* * gmap_protect_range - remove access rights to memory and set pgste bits * @gmap: pointer to guest mapping meta data structure * @gaddr: virtual address in the guest address space * @len: size of area * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE * @bits: pgste notification bits to set * * Returns 0 if successfully protected, -ENOMEM if out of memory and * -EFAULT if gaddr is invalid (or mapping for shadows is missing). * * Called with sg->mm->mmap_lock in read. */ static int gmap_protect_range(struct gmap *gmap, unsigned long gaddr, unsigned long len, int prot, unsigned long bits) { unsigned long vmaddr, dist; pmd_t *pmdp; int rc; BUG_ON(gmap_is_shadow(gmap)); while (len) { rc = -EAGAIN; pmdp = gmap_pmd_op_walk(gmap, gaddr); if (pmdp) { if (!pmd_leaf(*pmdp)) { rc = gmap_protect_pte(gmap, gaddr, pmdp, prot, bits); if (!rc) { len -= PAGE_SIZE; gaddr += PAGE_SIZE; } } else { rc = gmap_protect_pmd(gmap, gaddr, pmdp, prot, bits); if (!rc) { dist = HPAGE_SIZE - (gaddr & ~HPAGE_MASK); len = len < dist ? 0 : len - dist; gaddr = (gaddr & HPAGE_MASK) + HPAGE_SIZE; } } gmap_pmd_op_end(gmap, pmdp); } if (rc) { if (rc == -EINVAL) return rc; /* -EAGAIN, fixup of userspace mm and gmap */ vmaddr = __gmap_translate(gmap, gaddr); if (IS_ERR_VALUE(vmaddr)) return vmaddr; rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, prot); if (rc) return rc; } } return 0; } /** * gmap_mprotect_notify - change access rights for a range of ptes and * call the notifier if any pte changes again * @gmap: pointer to guest mapping meta data structure * @gaddr: virtual address in the guest address space * @len: size of area * @prot: indicates access rights: PROT_NONE, PROT_READ or PROT_WRITE * * Returns 0 if for each page in the given range a gmap mapping exists, * the new access rights could be set and the notifier could be armed. * If the gmap mapping is missing for one or more pages -EFAULT is * returned. If no memory could be allocated -ENOMEM is returned. * This function establishes missing page table entries. */ int gmap_mprotect_notify(struct gmap *gmap, unsigned long gaddr, unsigned long len, int prot) { int rc; if ((gaddr & ~PAGE_MASK) || (len & ~PAGE_MASK) || gmap_is_shadow(gmap)) return -EINVAL; if (!MACHINE_HAS_ESOP && prot == PROT_READ) return -EINVAL; mmap_read_lock(gmap->mm); rc = gmap_protect_range(gmap, gaddr, len, prot, GMAP_NOTIFY_MPROT); mmap_read_unlock(gmap->mm); return rc; } EXPORT_SYMBOL_GPL(gmap_mprotect_notify); /** * gmap_read_table - get an unsigned long value from a guest page table using * absolute addressing, without marking the page referenced. * @gmap: pointer to guest mapping meta data structure * @gaddr: virtual address in the guest address space * @val: pointer to the unsigned long value to return * * Returns 0 if the value was read, -ENOMEM if out of memory and -EFAULT * if reading using the virtual address failed. -EINVAL if called on a gmap * shadow. * * Called with gmap->mm->mmap_lock in read. */ int gmap_read_table(struct gmap *gmap, unsigned long gaddr, unsigned long *val) { unsigned long address, vmaddr; spinlock_t *ptl; pte_t *ptep, pte; int rc; if (gmap_is_shadow(gmap)) return -EINVAL; while (1) { rc = -EAGAIN; ptep = gmap_pte_op_walk(gmap, gaddr, &ptl); if (ptep) { pte = *ptep; if (pte_present(pte) && (pte_val(pte) & _PAGE_READ)) { address = pte_val(pte) & PAGE_MASK; address += gaddr & ~PAGE_MASK; *val = *(unsigned long *)__va(address); set_pte(ptep, set_pte_bit(*ptep, __pgprot(_PAGE_YOUNG))); /* Do *NOT* clear the _PAGE_INVALID bit! */ rc = 0; } gmap_pte_op_end(ptep, ptl); } if (!rc) break; vmaddr = __gmap_translate(gmap, gaddr); if (IS_ERR_VALUE(vmaddr)) { rc = vmaddr; break; } rc = gmap_pte_op_fixup(gmap, gaddr, vmaddr, PROT_READ); if (rc) break; } return rc; } EXPORT_SYMBOL_GPL(gmap_read_table); /** * gmap_insert_rmap - add a rmap to the host_to_rmap radix tree * @sg: pointer to the shadow guest address space structure * @vmaddr: vm address associated with the rmap * @rmap: pointer to the rmap structure * * Called with the sg->guest_table_lock */ static inline void gmap_insert_rmap(struct gmap *sg, unsigned long vmaddr, struct gmap_rmap *rmap) { struct gmap_rmap *temp; void __rcu **slot; BUG_ON(!gmap_is_shadow(sg)); slot = radix_tree_lookup_slot(&sg->host_to_rmap, vmaddr >> PAGE_SHIFT); if (slot) { rmap->next = radix_tree_deref_slot_protected(slot, &sg->guest_table_lock); for (temp = rmap->next; temp; temp = temp->next) { if (temp->raddr == rmap->raddr) { kfree(rmap); return; } } radix_tree_replace_slot(&sg->host_to_rmap, slot, rmap); } else { rmap->next = NULL; radix_tree_insert(&sg->host_to_rmap, vmaddr >> PAGE_SHIFT, rmap); } } /** * gmap_protect_rmap - restrict access rights to memory (RO) and create an rmap * @sg: pointer to the shadow guest address space structure * @raddr: rmap address in the shadow gmap * @paddr: address in the parent guest address space * @len: length of the memory area to protect * * Returns 0 if successfully protected and the rmap was created, -ENOMEM * if out of memory and -EFAULT if paddr is invalid. */ static int gmap_protect_rmap(struct gmap *sg, unsigned long raddr, unsigned long paddr, unsigned long len) { struct gmap *parent; struct gmap_rmap *rmap; unsigned long vmaddr; spinlock_t *ptl; pte_t *ptep; int rc; BUG_ON(!gmap_is_shadow(sg)); parent = sg->parent; while (len) { vmaddr = __gmap_translate(parent, paddr); if (IS_ERR_VALUE(vmaddr)) return vmaddr; rmap = kzalloc(sizeof(*rmap), GFP_KERNEL_ACCOUNT); if (!rmap) return -ENOMEM; rmap->raddr = raddr; rc = radix_tree_preload(GFP_KERNEL_ACCOUNT); if (rc) { kfree(rmap); return rc; } rc = -EAGAIN; ptep = gmap_pte_op_walk(parent, paddr, &ptl); if (ptep) { spin_lock(&sg->guest_table_lock); rc = ptep_force_prot(parent->mm, paddr, ptep, PROT_READ, PGSTE_VSIE_BIT); if (!rc) gmap_insert_rmap(sg, vmaddr, rmap); spin_unlock(&sg->guest_table_lock); gmap_pte_op_end(ptep, ptl); } radix_tree_preload_end(); if (rc) { kfree(rmap); rc = gmap_pte_op_fixup(parent, paddr, vmaddr, PROT_READ); if (rc) return rc; continue; } paddr += PAGE_SIZE; len -= PAGE_SIZE; } return 0; } #define _SHADOW_RMAP_MASK 0x7 #define _SHADOW_RMAP_REGION1 0x5 #define _SHADOW_RMAP_REGION2 0x4 #define _SHADOW_RMAP_REGION3 0x3 #define _SHADOW_RMAP_SEGMENT 0x2 #define _SHADOW_RMAP_PGTABLE 0x1 /** * gmap_idte_one - invalidate a single region or segment table entry * @asce: region or segment table *origin* + table-type bits * @vaddr: virtual address to identify the table entry to flush * * The invalid bit of a single region or segment table entry is set * and the associated TLB entries depending on the entry are flushed. * The table-type of the @asce identifies the portion of the @vaddr * that is used as the invalidation index. */ static inline void gmap_idte_one(unsigned long asce, unsigned long vaddr) { asm volatile( " idte %0,0,%1" : : "a" (asce), "a" (vaddr) : "cc", "memory"); } /** * gmap_unshadow_page - remove a page from a shadow page table * @sg: pointer to the shadow guest address space structure * @raddr: rmap address in the shadow guest address space * * Called with the sg->guest_table_lock */ static void gmap_unshadow_page(struct gmap *sg, unsigned long raddr) { unsigned long *table; BUG_ON(!gmap_is_shadow(sg)); table = gmap_table_walk(sg, raddr, 0); /* get page table pointer */ if (!table || *table & _PAGE_INVALID) return; gmap_call_notifier(sg, raddr, raddr + PAGE_SIZE - 1); ptep_unshadow_pte(sg->mm, raddr, (pte_t *) table); } /** * __gmap_unshadow_pgt - remove all entries from a shadow page table * @sg: pointer to the shadow guest address space structure * @raddr: rmap address in the shadow guest address space * @pgt: pointer to the start of a shadow page table * * Called with the sg->guest_table_lock */ static void __gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr, unsigned long *pgt) { int i; BUG_ON(!gmap_is_shadow(sg)); for (i = 0; i < _PAGE_ENTRIES; i++, raddr += PAGE_SIZE) pgt[i] = _PAGE_INVALID; } /** * gmap_unshadow_pgt - remove a shadow page table from a segment entry * @sg: pointer to the shadow guest address space structure * @raddr: address in the shadow guest address space * * Called with the sg->guest_table_lock */ static void gmap_unshadow_pgt(struct gmap *sg, unsigned long raddr) { unsigned long *ste; phys_addr_t sto, pgt; struct ptdesc *ptdesc; BUG_ON(!gmap_is_shadow(sg)); ste = gmap_table_walk(sg, raddr, 1); /* get segment pointer */ if (!ste || !(*ste & _SEGMENT_ENTRY_ORIGIN)) return; gmap_call_notifier(sg, raddr, raddr + _SEGMENT_SIZE - 1); sto = __pa(ste - ((raddr & _SEGMENT_INDEX) >> _SEGMENT_SHIFT)); gmap_idte_one(sto | _ASCE_TYPE_SEGMENT, raddr); pgt = *ste & _SEGMENT_ENTRY_ORIGIN; *ste = _SEGMENT_ENTRY_EMPTY; __gmap_unshadow_pgt(sg, raddr, __va(pgt)); /* Free page table */ ptdesc = page_ptdesc(phys_to_page(pgt)); list_del(&ptdesc->pt_list); page_table_free_pgste(ptdesc); } /** * __gmap_unshadow_sgt - remove all entries from a shadow segment table * @sg: pointer to the shadow guest address space structure * @raddr: rmap address in the shadow guest address space * @sgt: pointer to the start of a shadow segment table * * Called with the sg->guest_table_lock */ static void __gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr, unsigned long *sgt) { struct ptdesc *ptdesc; phys_addr_t pgt; int i; BUG_ON(!gmap_is_shadow(sg)); for (i = 0; i < _CRST_ENTRIES; i++, raddr += _SEGMENT_SIZE) { if (!(sgt[i] & _SEGMENT_ENTRY_ORIGIN)) continue; pgt = sgt[i] & _REGION_ENTRY_ORIGIN; sgt[i] = _SEGMENT_ENTRY_EMPTY; __gmap_unshadow_pgt(sg, raddr, __va(pgt)); /* Free page table */ ptdesc = page_ptdesc(phys_to_page(pgt)); list_del(&ptdesc->pt_list); page_table_free_pgste(ptdesc); } } /** * gmap_unshadow_sgt - remove a shadow segment table from a region-3 entry * @sg: pointer to the shadow guest address space structure * @raddr: rmap address in the shadow guest address space * * Called with the shadow->guest_table_lock */ static void gmap_unshadow_sgt(struct gmap *sg, unsigned long raddr) { unsigned long r3o, *r3e; phys_addr_t sgt; struct page *page; BUG_ON(!gmap_is_shadow(sg)); r3e = gmap_table_walk(sg, raddr, 2); /* get region-3 pointer */ if (!r3e || !(*r3e & _REGION_ENTRY_ORIGIN)) return; gmap_call_notifier(sg, raddr, raddr + _REGION3_SIZE - 1); r3o = (unsigned long) (r3e - ((raddr & _REGION3_INDEX) >> _REGION3_SHIFT)); gmap_idte_one(__pa(r3o) | _ASCE_TYPE_REGION3, raddr); sgt = *r3e & _REGION_ENTRY_ORIGIN; *r3e = _REGION3_ENTRY_EMPTY; __gmap_unshadow_sgt(sg, raddr, __va(sgt)); /* Free segment table */ page = phys_to_page(sgt); list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } /** * __gmap_unshadow_r3t - remove all entries from a shadow region-3 table * @sg: pointer to the shadow guest address space structure * @raddr: address in the shadow guest address space * @r3t: pointer to the start of a shadow region-3 table * * Called with the sg->guest_table_lock */ static void __gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr, unsigned long *r3t) { struct page *page; phys_addr_t sgt; int i; BUG_ON(!gmap_is_shadow(sg)); for (i = 0; i < _CRST_ENTRIES; i++, raddr += _REGION3_SIZE) { if (!(r3t[i] & _REGION_ENTRY_ORIGIN)) continue; sgt = r3t[i] & _REGION_ENTRY_ORIGIN; r3t[i] = _REGION3_ENTRY_EMPTY; __gmap_unshadow_sgt(sg, raddr, __va(sgt)); /* Free segment table */ page = phys_to_page(sgt); list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } } /** * gmap_unshadow_r3t - remove a shadow region-3 table from a region-2 entry * @sg: pointer to the shadow guest address space structure * @raddr: rmap address in the shadow guest address space * * Called with the sg->guest_table_lock */ static void gmap_unshadow_r3t(struct gmap *sg, unsigned long raddr) { unsigned long r2o, *r2e; phys_addr_t r3t; struct page *page; BUG_ON(!gmap_is_shadow(sg)); r2e = gmap_table_walk(sg, raddr, 3); /* get region-2 pointer */ if (!r2e || !(*r2e & _REGION_ENTRY_ORIGIN)) return; gmap_call_notifier(sg, raddr, raddr + _REGION2_SIZE - 1); r2o = (unsigned long) (r2e - ((raddr & _REGION2_INDEX) >> _REGION2_SHIFT)); gmap_idte_one(__pa(r2o) | _ASCE_TYPE_REGION2, raddr); r3t = *r2e & _REGION_ENTRY_ORIGIN; *r2e = _REGION2_ENTRY_EMPTY; __gmap_unshadow_r3t(sg, raddr, __va(r3t)); /* Free region 3 table */ page = phys_to_page(r3t); list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } /** * __gmap_unshadow_r2t - remove all entries from a shadow region-2 table * @sg: pointer to the shadow guest address space structure * @raddr: rmap address in the shadow guest address space * @r2t: pointer to the start of a shadow region-2 table * * Called with the sg->guest_table_lock */ static void __gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr, unsigned long *r2t) { phys_addr_t r3t; struct page *page; int i; BUG_ON(!gmap_is_shadow(sg)); for (i = 0; i < _CRST_ENTRIES; i++, raddr += _REGION2_SIZE) { if (!(r2t[i] & _REGION_ENTRY_ORIGIN)) continue; r3t = r2t[i] & _REGION_ENTRY_ORIGIN; r2t[i] = _REGION2_ENTRY_EMPTY; __gmap_unshadow_r3t(sg, raddr, __va(r3t)); /* Free region 3 table */ page = phys_to_page(r3t); list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } } /** * gmap_unshadow_r2t - remove a shadow region-2 table from a region-1 entry * @sg: pointer to the shadow guest address space structure * @raddr: rmap address in the shadow guest address space * * Called with the sg->guest_table_lock */ static void gmap_unshadow_r2t(struct gmap *sg, unsigned long raddr) { unsigned long r1o, *r1e; struct page *page; phys_addr_t r2t; BUG_ON(!gmap_is_shadow(sg)); r1e = gmap_table_walk(sg, raddr, 4); /* get region-1 pointer */ if (!r1e || !(*r1e & _REGION_ENTRY_ORIGIN)) return; gmap_call_notifier(sg, raddr, raddr + _REGION1_SIZE - 1); r1o = (unsigned long) (r1e - ((raddr & _REGION1_INDEX) >> _REGION1_SHIFT)); gmap_idte_one(__pa(r1o) | _ASCE_TYPE_REGION1, raddr); r2t = *r1e & _REGION_ENTRY_ORIGIN; *r1e = _REGION1_ENTRY_EMPTY; __gmap_unshadow_r2t(sg, raddr, __va(r2t)); /* Free region 2 table */ page = phys_to_page(r2t); list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } /** * __gmap_unshadow_r1t - remove all entries from a shadow region-1 table * @sg: pointer to the shadow guest address space structure * @raddr: rmap address in the shadow guest address space * @r1t: pointer to the start of a shadow region-1 table * * Called with the shadow->guest_table_lock */ static void __gmap_unshadow_r1t(struct gmap *sg, unsigned long raddr, unsigned long *r1t) { unsigned long asce; struct page *page; phys_addr_t r2t; int i; BUG_ON(!gmap_is_shadow(sg)); asce = __pa(r1t) | _ASCE_TYPE_REGION1; for (i = 0; i < _CRST_ENTRIES; i++, raddr += _REGION1_SIZE) { if (!(r1t[i] & _REGION_ENTRY_ORIGIN)) continue; r2t = r1t[i] & _REGION_ENTRY_ORIGIN; __gmap_unshadow_r2t(sg, raddr, __va(r2t)); /* Clear entry and flush translation r1t -> r2t */ gmap_idte_one(asce, raddr); r1t[i] = _REGION1_ENTRY_EMPTY; /* Free region 2 table */ page = phys_to_page(r2t); list_del(&page->lru); __free_pages(page, CRST_ALLOC_ORDER); } } /** * gmap_unshadow - remove a shadow page table completely * @sg: pointer to the shadow guest address space structure * * Called with sg->guest_table_lock */ static void gmap_unshadow(struct gmap *sg) { unsigned long *table; BUG_ON(!gmap_is_shadow(sg)); if (sg->removed) return; sg->removed = 1; gmap_call_notifier(sg, 0, -1UL); gmap_flush_tlb(sg); table = __va(sg->asce & _ASCE_ORIGIN); switch (sg->asce & _ASCE_TYPE_MASK) { case _ASCE_TYPE_REGION1: __gmap_unshadow_r1t(sg, 0, table); break; case _ASCE_TYPE_REGION2: __gmap_unshadow_r2t(sg, 0, table); break; case _ASCE_TYPE_REGION3: __gmap_unshadow_r3t(sg, 0, table); break; case _ASCE_TYPE_SEGMENT: __gmap_unshadow_sgt(sg, 0, table); break; } } /** * gmap_find_shadow - find a specific asce in the list of shadow tables * @parent: pointer to the parent gmap * @asce: ASCE for which the shadow table is created * @edat_level: edat level to be used for the shadow translation * * Returns the pointer to a gmap if a shadow table with the given asce is * already available, ERR_PTR(-EAGAIN) if another one is just being created, * otherwise NULL */ static struct gmap *gmap_find_shadow(struct gmap *parent, unsigned long asce, int edat_level) { struct gmap *sg; list_for_each_entry(sg, &parent->children, list) { if (sg->orig_asce != asce || sg->edat_level != edat_level || sg->removed) continue; if (!sg->initialized) return ERR_PTR(-EAGAIN); refcount_inc(&sg->ref_count); return sg; } return NULL; } /** * gmap_shadow_valid - check if a shadow guest address space matches the * given properties and is still valid * @sg: pointer to the shadow guest address space structure * @asce: ASCE for which the shadow table is requested * @edat_level: edat level to be used for the shadow translation * * Returns 1 if the gmap shadow is still valid and matches the given * properties, the caller can continue using it. Returns 0 otherwise, the * caller has to request a new shadow gmap in this case. * */ int gmap_shadow_valid(struct gmap *sg, unsigned long asce, int edat_level) { if (sg->removed) return 0; return sg->orig_asce == asce && sg->edat_level == edat_level; } EXPORT_SYMBOL_GPL(gmap_shadow_valid); /** * gmap_shadow - create/find a shadow guest address space * @parent: pointer to the parent gmap * @asce: ASCE for which the shadow table is created * @edat_level: edat level to be used for the shadow translation * * The pages of the top level page table referred by the asce parameter * will be set to read-only and marked in the PGSTEs of the kvm process. * The shadow table will be removed automatically on any change to the * PTE mapping for the source table. * * Returns a guest address space structure, ERR_PTR(-ENOMEM) if out of memory, * ERR_PTR(-EAGAIN) if the caller has to retry and ERR_PTR(-EFAULT) if the * parent gmap table could not be protected. */ struct gmap *gmap_shadow(struct gmap *parent, unsigned long asce, int edat_level) { struct gmap *sg, *new; unsigned long limit; int rc; BUG_ON(parent->mm->context.allow_gmap_hpage_1m); BUG_ON(gmap_is_shadow(parent)); spin_lock(&parent->shadow_lock); sg = gmap_find_shadow(parent, asce, edat_level); spin_unlock(&parent->shadow_lock); if (sg) return sg; /* Create a new shadow gmap */ limit = -1UL >> (33 - (((asce & _ASCE_TYPE_MASK) >> 2) * 11)); if (asce & _ASCE_REAL_SPACE) limit = -1UL; new = gmap_alloc(limit); if (!new) return ERR_PTR(-ENOMEM); new->mm = parent->mm; new->parent = gmap_get(parent); new->private = parent->private; new->orig_asce = asce; new->edat_level = edat_level; new->initialized = false; spin_lock(&parent->shadow_lock); /* Recheck if another CPU created the same shadow */ sg = gmap_find_shadow(parent, asce, edat_level); if (sg) { spin_unlock(&parent->shadow_lock); gmap_free(new); return sg; } if (asce & _ASCE_REAL_SPACE) { /* only allow one real-space gmap shadow */ list_for_each_entry(sg, &parent->children, list) { if (sg->orig_asce & _ASCE_REAL_SPACE) { spin_lock(&sg->guest_table_lock); gmap_unshadow(sg); spin_unlock(&sg->guest_table_lock); list_del(&sg->list); gmap_put(sg); break; } } } refcount_set(&new->ref_count, 2); list_add(&new->list, &parent->children); if (asce & _ASCE_REAL_SPACE) { /* nothing to protect, return right away */ new->initialized = true; spin_unlock(&parent->shadow_lock); return new; } spin_unlock(&parent->shadow_lock); /* protect after insertion, so it will get properly invalidated */ mmap_read_lock(parent->mm); rc = gmap_protect_range(parent, asce & _ASCE_ORIGIN, ((asce & _ASCE_TABLE_LENGTH) + 1) * PAGE_SIZE, PROT_READ, GMAP_NOTIFY_SHADOW); mmap_read_unlock(parent->mm); spin_lock(&parent->shadow_lock); new->initialized = true; if (rc) { list_del(&new->list); gmap_free(new); new = ERR_PTR(rc); } spin_unlock(&parent->shadow_lock); return new; } EXPORT_SYMBOL_GPL(gmap_shadow); /** * gmap_shadow_r2t - create an empty shadow region 2 table * @sg: pointer to the shadow guest address space structure * @saddr: faulting address in the shadow gmap * @r2t: parent gmap address of the region 2 table to get shadowed * @fake: r2t references contiguous guest memory block, not a r2t * * The r2t parameter specifies the address of the source table. The * four pages of the source table are made read-only in the parent gmap * address space. A write to the source table area @r2t will automatically * remove the shadow r2 table and all of its descendants. * * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the * shadow table structure is incomplete, -ENOMEM if out of memory and * -EFAULT if an address in the parent gmap could not be resolved. * * Called with sg->mm->mmap_lock in read. */ int gmap_shadow_r2t(struct gmap *sg, unsigned long saddr, unsigned long r2t, int fake) { unsigned long raddr, origin, offset, len; unsigned long *table; phys_addr_t s_r2t; struct page *page; int rc; BUG_ON(!gmap_is_shadow(sg)); /* Allocate a shadow region second table */ page = gmap_alloc_crst(); if (!page) return -ENOMEM; page->index = r2t & _REGION_ENTRY_ORIGIN; if (fake) page->index |= GMAP_SHADOW_FAKE_TABLE; s_r2t = page_to_phys(page); /* Install shadow region second table */ spin_lock(&sg->guest_table_lock); table = gmap_table_walk(sg, saddr, 4); /* get region-1 pointer */ if (!table) { rc = -EAGAIN; /* Race with unshadow */ goto out_free; } if (!(*table & _REGION_ENTRY_INVALID)) { rc = 0; /* Already established */ goto out_free; } else if (*table & _REGION_ENTRY_ORIGIN) { rc = -EAGAIN; /* Race with shadow */ goto out_free; } crst_table_init(__va(s_r2t), _REGION2_ENTRY_EMPTY); /* mark as invalid as long as the parent table is not protected */ *table = s_r2t | _REGION_ENTRY_LENGTH | _REGION_ENTRY_TYPE_R1 | _REGION_ENTRY_INVALID; if (sg->edat_level >= 1) *table |= (r2t & _REGION_ENTRY_PROTECT); list_add(&page->lru, &sg->crst_list); if (fake) { /* nothing to protect for fake tables */ *table &= ~_REGION_ENTRY_INVALID; spin_unlock(&sg->guest_table_lock); return 0; } spin_unlock(&sg->guest_table_lock); /* Make r2t read-only in parent gmap page table */ raddr = (saddr & _REGION1_MASK) | _SHADOW_RMAP_REGION1; origin = r2t & _REGION_ENTRY_ORIGIN; offset = ((r2t & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE; len = ((r2t & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset; rc = gmap_protect_rmap(sg, raddr, origin + offset, len); spin_lock(&sg->guest_table_lock); if (!rc) { table = gmap_table_walk(sg, saddr, 4); if (!table || (*table & _REGION_ENTRY_ORIGIN) != s_r2t) rc = -EAGAIN; /* Race with unshadow */ else *table &= ~_REGION_ENTRY_INVALID; } else { gmap_unshadow_r2t(sg, raddr); } spin_unlock(&sg->guest_table_lock); return rc; out_free: spin_unlock(&sg->guest_table_lock); __free_pages(page, CRST_ALLOC_ORDER); return rc; } EXPORT_SYMBOL_GPL(gmap_shadow_r2t); /** * gmap_shadow_r3t - create a shadow region 3 table * @sg: pointer to the shadow guest address space structure * @saddr: faulting address in the shadow gmap * @r3t: parent gmap address of the region 3 table to get shadowed * @fake: r3t references contiguous guest memory block, not a r3t * * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the * shadow table structure is incomplete, -ENOMEM if out of memory and * -EFAULT if an address in the parent gmap could not be resolved. * * Called with sg->mm->mmap_lock in read. */ int gmap_shadow_r3t(struct gmap *sg, unsigned long saddr, unsigned long r3t, int fake) { unsigned long raddr, origin, offset, len; unsigned long *table; phys_addr_t s_r3t; struct page *page; int rc; BUG_ON(!gmap_is_shadow(sg)); /* Allocate a shadow region second table */ page = gmap_alloc_crst(); if (!page) return -ENOMEM; page->index = r3t & _REGION_ENTRY_ORIGIN; if (fake) page->index |= GMAP_SHADOW_FAKE_TABLE; s_r3t = page_to_phys(page); /* Install shadow region second table */ spin_lock(&sg->guest_table_lock); table = gmap_table_walk(sg, saddr, 3); /* get region-2 pointer */ if (!table) { rc = -EAGAIN; /* Race with unshadow */ goto out_free; } if (!(*table & _REGION_ENTRY_INVALID)) { rc = 0; /* Already established */ goto out_free; } else if (*table & _REGION_ENTRY_ORIGIN) { rc = -EAGAIN; /* Race with shadow */ goto out_free; } crst_table_init(__va(s_r3t), _REGION3_ENTRY_EMPTY); /* mark as invalid as long as the parent table is not protected */ *table = s_r3t | _REGION_ENTRY_LENGTH | _REGION_ENTRY_TYPE_R2 | _REGION_ENTRY_INVALID; if (sg->edat_level >= 1) *table |= (r3t & _REGION_ENTRY_PROTECT); list_add(&page->lru, &sg->crst_list); if (fake) { /* nothing to protect for fake tables */ *table &= ~_REGION_ENTRY_INVALID; spin_unlock(&sg->guest_table_lock); return 0; } spin_unlock(&sg->guest_table_lock); /* Make r3t read-only in parent gmap page table */ raddr = (saddr & _REGION2_MASK) | _SHADOW_RMAP_REGION2; origin = r3t & _REGION_ENTRY_ORIGIN; offset = ((r3t & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE; len = ((r3t & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset; rc = gmap_protect_rmap(sg, raddr, origin + offset, len); spin_lock(&sg->guest_table_lock); if (!rc) { table = gmap_table_walk(sg, saddr, 3); if (!table || (*table & _REGION_ENTRY_ORIGIN) != s_r3t) rc = -EAGAIN; /* Race with unshadow */ else *table &= ~_REGION_ENTRY_INVALID; } else { gmap_unshadow_r3t(sg, raddr); } spin_unlock(&sg->guest_table_lock); return rc; out_free: spin_unlock(&sg->guest_table_lock); __free_pages(page, CRST_ALLOC_ORDER); return rc; } EXPORT_SYMBOL_GPL(gmap_shadow_r3t); /** * gmap_shadow_sgt - create a shadow segment table * @sg: pointer to the shadow guest address space structure * @saddr: faulting address in the shadow gmap * @sgt: parent gmap address of the segment table to get shadowed * @fake: sgt references contiguous guest memory block, not a sgt * * Returns: 0 if successfully shadowed or already shadowed, -EAGAIN if the * shadow table structure is incomplete, -ENOMEM if out of memory and * -EFAULT if an address in the parent gmap could not be resolved. * * Called with sg->mm->mmap_lock in read. */ int gmap_shadow_sgt(struct gmap *sg, unsigned long saddr, unsigned long sgt, int fake) { unsigned long raddr, origin, offset, len; unsigned long *table; phys_addr_t s_sgt; struct page *page; int rc; BUG_ON(!gmap_is_shadow(sg) || (sgt & _REGION3_ENTRY_LARGE)); /* Allocate a shadow segment table */ page = gmap_alloc_crst(); if (!page) return -ENOMEM; page->index = sgt & _REGION_ENTRY_ORIGIN; if (fake) page->index |= GMAP_SHADOW_FAKE_TABLE; s_sgt = page_to_phys(page); /* Install shadow region second table */ spin_lock(&sg->guest_table_lock); table = gmap_table_walk(sg, saddr, 2); /* get region-3 pointer */ if (!table) { rc = -EAGAIN; /* Race with unshadow */ goto out_free; } if (!(*table & _REGION_ENTRY_INVALID)) { rc = 0; /* Already established */ goto out_free; } else if (*table & _REGION_ENTRY_ORIGIN) { rc = -EAGAIN; /* Race with shadow */ goto out_free; } crst_table_init(__va(s_sgt), _SEGMENT_ENTRY_EMPTY); /* mark as invalid as long as the parent table is not protected */ *table = s_sgt | _REGION_ENTRY_LENGTH | _REGION_ENTRY_TYPE_R3 | _REGION_ENTRY_INVALID; if (sg->edat_level >= 1) *table |= sgt & _REGION_ENTRY_PROTECT; list_add(&page->lru, &sg->crst_list); if (fake) { /* nothing to protect for fake tables */ *table &= ~_REGION_ENTRY_INVALID; spin_unlock(&sg->guest_table_lock); return 0; } spin_unlock(&sg->guest_table_lock); /* Make sgt read-only in parent gmap page table */ raddr = (saddr & _REGION3_MASK) | _SHADOW_RMAP_REGION3; origin = sgt & _REGION_ENTRY_ORIGIN; offset = ((sgt & _REGION_ENTRY_OFFSET) >> 6) * PAGE_SIZE; len = ((sgt & _REGION_ENTRY_LENGTH) + 1) * PAGE_SIZE - offset; rc = gmap_protect_rmap(sg, raddr, origin + offset, len); spin_lock(&sg->guest_table_lock); if (!rc) { table = gmap_table_walk(sg, saddr, 2); if (!table || (*table & _REGION_ENTRY_ORIGIN) != s_sgt) rc = -EAGAIN; /* Race with unshadow */ else *table &= ~_REGION_ENTRY_INVALID; } else { gmap_unshadow_sgt(sg, raddr); } spin_unlock(&sg->guest_table_lock); return rc; out_free: spin_unlock(&sg->guest_table_lock); __free_pages(page, CRST_ALLOC_ORDER); return rc; } EXPORT_SYMBOL_GPL(gmap_shadow_sgt); /** * gmap_shadow_pgt_lookup - find a shadow page table * @sg: pointer to the shadow guest address space structure * @saddr: the address in the shadow aguest address space * @pgt: parent gmap address of the page table to get shadowed * @dat_protection: if the pgtable is marked as protected by dat * @fake: pgt references contiguous guest memory block, not a pgtable * * Returns 0 if the shadow page table was found and -EAGAIN if the page * table was not found. * * Called with sg->mm->mmap_lock in read. */ int gmap_shadow_pgt_lookup(struct gmap *sg, unsigned long saddr, unsigned long *pgt, int *dat_protection, int *fake) { unsigned long *table; struct page *page; int rc; BUG_ON(!gmap_is_shadow(sg)); spin_lock(&sg->guest_table_lock); table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */ if (table && !(*table & _SEGMENT_ENTRY_INVALID)) { /* Shadow page tables are full pages (pte+pgste) */ page = pfn_to_page(*table >> PAGE_SHIFT); *pgt = page->index & ~GMAP_SHADOW_FAKE_TABLE; *dat_protection = !!(*table & _SEGMENT_ENTRY_PROTECT); *fake = !!(page->index & GMAP_SHADOW_FAKE_TABLE); rc = 0; } else { rc = -EAGAIN; } spin_unlock(&sg->guest_table_lock); return rc; } EXPORT_SYMBOL_GPL(gmap_shadow_pgt_lookup); /** * gmap_shadow_pgt - instantiate a shadow page table * @sg: pointer to the shadow guest address space structure * @saddr: faulting address in the shadow gmap * @pgt: parent gmap address of the page table to get shadowed * @fake: pgt references contiguous guest memory block, not a pgtable * * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the * shadow table structure is incomplete, -ENOMEM if out of memory, * -EFAULT if an address in the parent gmap could not be resolved and * * Called with gmap->mm->mmap_lock in read */ int gmap_shadow_pgt(struct gmap *sg, unsigned long saddr, unsigned long pgt, int fake) { unsigned long raddr, origin; unsigned long *table; struct ptdesc *ptdesc; phys_addr_t s_pgt; int rc; BUG_ON(!gmap_is_shadow(sg) || (pgt & _SEGMENT_ENTRY_LARGE)); /* Allocate a shadow page table */ ptdesc = page_table_alloc_pgste(sg->mm); if (!ptdesc) return -ENOMEM; ptdesc->pt_index = pgt & _SEGMENT_ENTRY_ORIGIN; if (fake) ptdesc->pt_index |= GMAP_SHADOW_FAKE_TABLE; s_pgt = page_to_phys(ptdesc_page(ptdesc)); /* Install shadow page table */ spin_lock(&sg->guest_table_lock); table = gmap_table_walk(sg, saddr, 1); /* get segment pointer */ if (!table) { rc = -EAGAIN; /* Race with unshadow */ goto out_free; } if (!(*table & _SEGMENT_ENTRY_INVALID)) { rc = 0; /* Already established */ goto out_free; } else if (*table & _SEGMENT_ENTRY_ORIGIN) { rc = -EAGAIN; /* Race with shadow */ goto out_free; } /* mark as invalid as long as the parent table is not protected */ *table = (unsigned long) s_pgt | _SEGMENT_ENTRY | (pgt & _SEGMENT_ENTRY_PROTECT) | _SEGMENT_ENTRY_INVALID; list_add(&ptdesc->pt_list, &sg->pt_list); if (fake) { /* nothing to protect for fake tables */ *table &= ~_SEGMENT_ENTRY_INVALID; spin_unlock(&sg->guest_table_lock); return 0; } spin_unlock(&sg->guest_table_lock); /* Make pgt read-only in parent gmap page table (not the pgste) */ raddr = (saddr & _SEGMENT_MASK) | _SHADOW_RMAP_SEGMENT; origin = pgt & _SEGMENT_ENTRY_ORIGIN & PAGE_MASK; rc = gmap_protect_rmap(sg, raddr, origin, PAGE_SIZE); spin_lock(&sg->guest_table_lock); if (!rc) { table = gmap_table_walk(sg, saddr, 1); if (!table || (*table & _SEGMENT_ENTRY_ORIGIN) != s_pgt) rc = -EAGAIN; /* Race with unshadow */ else *table &= ~_SEGMENT_ENTRY_INVALID; } else { gmap_unshadow_pgt(sg, raddr); } spin_unlock(&sg->guest_table_lock); return rc; out_free: spin_unlock(&sg->guest_table_lock); page_table_free_pgste(ptdesc); return rc; } EXPORT_SYMBOL_GPL(gmap_shadow_pgt); /** * gmap_shadow_page - create a shadow page mapping * @sg: pointer to the shadow guest address space structure * @saddr: faulting address in the shadow gmap * @pte: pte in parent gmap address space to get shadowed * * Returns 0 if successfully shadowed or already shadowed, -EAGAIN if the * shadow table structure is incomplete, -ENOMEM if out of memory and * -EFAULT if an address in the parent gmap could not be resolved. * * Called with sg->mm->mmap_lock in read. */ int gmap_shadow_page(struct gmap *sg, unsigned long saddr, pte_t pte) { struct gmap *parent; struct gmap_rmap *rmap; unsigned long vmaddr, paddr; spinlock_t *ptl; pte_t *sptep, *tptep; int prot; int rc; BUG_ON(!gmap_is_shadow(sg)); parent = sg->parent; prot = (pte_val(pte) & _PAGE_PROTECT) ? PROT_READ : PROT_WRITE; rmap = kzalloc(sizeof(*rmap), GFP_KERNEL_ACCOUNT); if (!rmap) return -ENOMEM; rmap->raddr = (saddr & PAGE_MASK) | _SHADOW_RMAP_PGTABLE; while (1) { paddr = pte_val(pte) & PAGE_MASK; vmaddr = __gmap_translate(parent, paddr); if (IS_ERR_VALUE(vmaddr)) { rc = vmaddr; break; } rc = radix_tree_preload(GFP_KERNEL_ACCOUNT); if (rc) break; rc = -EAGAIN; sptep = gmap_pte_op_walk(parent, paddr, &ptl); if (sptep) { spin_lock(&sg->guest_table_lock); /* Get page table pointer */ tptep = (pte_t *) gmap_table_walk(sg, saddr, 0); if (!tptep) { spin_unlock(&sg->guest_table_lock); gmap_pte_op_end(sptep, ptl); radix_tree_preload_end(); break; } rc = ptep_shadow_pte(sg->mm, saddr, sptep, tptep, pte); if (rc > 0) { /* Success and a new mapping */ gmap_insert_rmap(sg, vmaddr, rmap); rmap = NULL; rc = 0; } gmap_pte_op_end(sptep, ptl); spin_unlock(&sg->guest_table_lock); } radix_tree_preload_end(); if (!rc) break; rc = gmap_pte_op_fixup(parent, paddr, vmaddr, prot); if (rc) break; } kfree(rmap); return rc; } EXPORT_SYMBOL_GPL(gmap_shadow_page); /* * gmap_shadow_notify - handle notifications for shadow gmap * * Called with sg->parent->shadow_lock. */ static void gmap_shadow_notify(struct gmap *sg, unsigned long vmaddr, unsigned long gaddr) { struct gmap_rmap *rmap, *rnext, *head; unsigned long start, end, bits, raddr; BUG_ON(!gmap_is_shadow(sg)); spin_lock(&sg->guest_table_lock); if (sg->removed) { spin_unlock(&sg->guest_table_lock); return; } /* Check for top level table */ start = sg->orig_asce & _ASCE_ORIGIN; end = start + ((sg->orig_asce & _ASCE_TABLE_LENGTH) + 1) * PAGE_SIZE; if (!(sg->orig_asce & _ASCE_REAL_SPACE) && gaddr >= start && gaddr < end) { /* The complete shadow table has to go */ gmap_unshadow(sg); spin_unlock(&sg->guest_table_lock); list_del(&sg->list); gmap_put(sg); return; } /* Remove the page table tree from on specific entry */ head = radix_tree_delete(&sg->host_to_rmap, vmaddr >> PAGE_SHIFT); gmap_for_each_rmap_safe(rmap, rnext, head) { bits = rmap->raddr & _SHADOW_RMAP_MASK; raddr = rmap->raddr ^ bits; switch (bits) { case _SHADOW_RMAP_REGION1: gmap_unshadow_r2t(sg, raddr); break; case _SHADOW_RMAP_REGION2: gmap_unshadow_r3t(sg, raddr); break; case _SHADOW_RMAP_REGION3: gmap_unshadow_sgt(sg, raddr); break; case _SHADOW_RMAP_SEGMENT: gmap_unshadow_pgt(sg, raddr); break; case _SHADOW_RMAP_PGTABLE: gmap_unshadow_page(sg, raddr); break; } kfree(rmap); } spin_unlock(&sg->guest_table_lock); } /** * ptep_notify - call all invalidation callbacks for a specific pte. * @mm: pointer to the process mm_struct * @vmaddr: virtual address in the process address space * @pte: pointer to the page table entry * @bits: bits from the pgste that caused the notify call * * This function is assumed to be called with the page table lock held * for the pte to notify. */ void ptep_notify(struct mm_struct *mm, unsigned long vmaddr, pte_t *pte, unsigned long bits) { unsigned long offset, gaddr = 0; unsigned long *table; struct gmap *gmap, *sg, *next; offset = ((unsigned long) pte) & (255 * sizeof(pte_t)); offset = offset * (PAGE_SIZE / sizeof(pte_t)); rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); table = radix_tree_lookup(&gmap->host_to_guest, vmaddr >> PMD_SHIFT); if (table) gaddr = __gmap_segment_gaddr(table) + offset; spin_unlock(&gmap->guest_table_lock); if (!table) continue; if (!list_empty(&gmap->children) && (bits & PGSTE_VSIE_BIT)) { spin_lock(&gmap->shadow_lock); list_for_each_entry_safe(sg, next, &gmap->children, list) gmap_shadow_notify(sg, vmaddr, gaddr); spin_unlock(&gmap->shadow_lock); } if (bits & PGSTE_IN_BIT) gmap_call_notifier(gmap, gaddr, gaddr + PAGE_SIZE - 1); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(ptep_notify); static void pmdp_notify_gmap(struct gmap *gmap, pmd_t *pmdp, unsigned long gaddr) { set_pmd(pmdp, clear_pmd_bit(*pmdp, __pgprot(_SEGMENT_ENTRY_GMAP_IN))); gmap_call_notifier(gmap, gaddr, gaddr + HPAGE_SIZE - 1); } /** * gmap_pmdp_xchg - exchange a gmap pmd with another * @gmap: pointer to the guest address space structure * @pmdp: pointer to the pmd entry * @new: replacement entry * @gaddr: the affected guest address * * This function is assumed to be called with the guest_table_lock * held. */ static void gmap_pmdp_xchg(struct gmap *gmap, pmd_t *pmdp, pmd_t new, unsigned long gaddr) { gaddr &= HPAGE_MASK; pmdp_notify_gmap(gmap, pmdp, gaddr); new = clear_pmd_bit(new, __pgprot(_SEGMENT_ENTRY_GMAP_IN)); if (MACHINE_HAS_TLB_GUEST) __pmdp_idte(gaddr, (pmd_t *)pmdp, IDTE_GUEST_ASCE, gmap->asce, IDTE_GLOBAL); else if (MACHINE_HAS_IDTE) __pmdp_idte(gaddr, (pmd_t *)pmdp, 0, 0, IDTE_GLOBAL); else __pmdp_csp(pmdp); set_pmd(pmdp, new); } static void gmap_pmdp_clear(struct mm_struct *mm, unsigned long vmaddr, int purge) { pmd_t *pmdp; struct gmap *gmap; unsigned long gaddr; rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); pmdp = (pmd_t *)radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT); if (pmdp) { gaddr = __gmap_segment_gaddr((unsigned long *)pmdp); pmdp_notify_gmap(gmap, pmdp, gaddr); WARN_ON(pmd_val(*pmdp) & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | _SEGMENT_ENTRY_GMAP_UC | _SEGMENT_ENTRY)); if (purge) __pmdp_csp(pmdp); set_pmd(pmdp, __pmd(_SEGMENT_ENTRY_EMPTY)); } spin_unlock(&gmap->guest_table_lock); } rcu_read_unlock(); } /** * gmap_pmdp_invalidate - invalidate all affected guest pmd entries without * flushing * @mm: pointer to the process mm_struct * @vmaddr: virtual address in the process address space */ void gmap_pmdp_invalidate(struct mm_struct *mm, unsigned long vmaddr) { gmap_pmdp_clear(mm, vmaddr, 0); } EXPORT_SYMBOL_GPL(gmap_pmdp_invalidate); /** * gmap_pmdp_csp - csp all affected guest pmd entries * @mm: pointer to the process mm_struct * @vmaddr: virtual address in the process address space */ void gmap_pmdp_csp(struct mm_struct *mm, unsigned long vmaddr) { gmap_pmdp_clear(mm, vmaddr, 1); } EXPORT_SYMBOL_GPL(gmap_pmdp_csp); /** * gmap_pmdp_idte_local - invalidate and clear a guest pmd entry * @mm: pointer to the process mm_struct * @vmaddr: virtual address in the process address space */ void gmap_pmdp_idte_local(struct mm_struct *mm, unsigned long vmaddr) { unsigned long *entry, gaddr; struct gmap *gmap; pmd_t *pmdp; rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT); if (entry) { pmdp = (pmd_t *)entry; gaddr = __gmap_segment_gaddr(entry); pmdp_notify_gmap(gmap, pmdp, gaddr); WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | _SEGMENT_ENTRY_GMAP_UC | _SEGMENT_ENTRY)); if (MACHINE_HAS_TLB_GUEST) __pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE, gmap->asce, IDTE_LOCAL); else if (MACHINE_HAS_IDTE) __pmdp_idte(gaddr, pmdp, 0, 0, IDTE_LOCAL); *entry = _SEGMENT_ENTRY_EMPTY; } spin_unlock(&gmap->guest_table_lock); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(gmap_pmdp_idte_local); /** * gmap_pmdp_idte_global - invalidate and clear a guest pmd entry * @mm: pointer to the process mm_struct * @vmaddr: virtual address in the process address space */ void gmap_pmdp_idte_global(struct mm_struct *mm, unsigned long vmaddr) { unsigned long *entry, gaddr; struct gmap *gmap; pmd_t *pmdp; rcu_read_lock(); list_for_each_entry_rcu(gmap, &mm->context.gmap_list, list) { spin_lock(&gmap->guest_table_lock); entry = radix_tree_delete(&gmap->host_to_guest, vmaddr >> PMD_SHIFT); if (entry) { pmdp = (pmd_t *)entry; gaddr = __gmap_segment_gaddr(entry); pmdp_notify_gmap(gmap, pmdp, gaddr); WARN_ON(*entry & ~(_SEGMENT_ENTRY_HARDWARE_BITS_LARGE | _SEGMENT_ENTRY_GMAP_UC | _SEGMENT_ENTRY)); if (MACHINE_HAS_TLB_GUEST) __pmdp_idte(gaddr, pmdp, IDTE_GUEST_ASCE, gmap->asce, IDTE_GLOBAL); else if (MACHINE_HAS_IDTE) __pmdp_idte(gaddr, pmdp, 0, 0, IDTE_GLOBAL); else __pmdp_csp(pmdp); *entry = _SEGMENT_ENTRY_EMPTY; } spin_unlock(&gmap->guest_table_lock); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(gmap_pmdp_idte_global); /** * gmap_test_and_clear_dirty_pmd - test and reset segment dirty status * @gmap: pointer to guest address space * @pmdp: pointer to the pmd to be tested * @gaddr: virtual address in the guest address space * * This function is assumed to be called with the guest_table_lock * held. */ static bool gmap_test_and_clear_dirty_pmd(struct gmap *gmap, pmd_t *pmdp, unsigned long gaddr) { if (pmd_val(*pmdp) & _SEGMENT_ENTRY_INVALID) return false; /* Already protected memory, which did not change is clean */ if (pmd_val(*pmdp) & _SEGMENT_ENTRY_PROTECT && !(pmd_val(*pmdp) & _SEGMENT_ENTRY_GMAP_UC)) return false; /* Clear UC indication and reset protection */ set_pmd(pmdp, clear_pmd_bit(*pmdp, __pgprot(_SEGMENT_ENTRY_GMAP_UC))); gmap_protect_pmd(gmap, gaddr, pmdp, PROT_READ, 0); return true; } /** * gmap_sync_dirty_log_pmd - set bitmap based on dirty status of segment * @gmap: pointer to guest address space * @bitmap: dirty bitmap for this pmd * @gaddr: virtual address in the guest address space * @vmaddr: virtual address in the host address space * * This function is assumed to be called with the guest_table_lock * held. */ void gmap_sync_dirty_log_pmd(struct gmap *gmap, unsigned long bitmap[4], unsigned long gaddr, unsigned long vmaddr) { int i; pmd_t *pmdp; pte_t *ptep; spinlock_t *ptl; pmdp = gmap_pmd_op_walk(gmap, gaddr); if (!pmdp) return; if (pmd_leaf(*pmdp)) { if (gmap_test_and_clear_dirty_pmd(gmap, pmdp, gaddr)) bitmap_fill(bitmap, _PAGE_ENTRIES); } else { for (i = 0; i < _PAGE_ENTRIES; i++, vmaddr += PAGE_SIZE) { ptep = pte_alloc_map_lock(gmap->mm, pmdp, vmaddr, &ptl); if (!ptep) continue; if (ptep_test_and_clear_uc(gmap->mm, vmaddr, ptep)) set_bit(i, bitmap); pte_unmap_unlock(ptep, ptl); } } gmap_pmd_op_end(gmap, pmdp); } EXPORT_SYMBOL_GPL(gmap_sync_dirty_log_pmd); #ifdef CONFIG_TRANSPARENT_HUGEPAGE static int thp_split_walk_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; split_huge_pmd(vma, pmd, addr); return 0; } static const struct mm_walk_ops thp_split_walk_ops = { .pmd_entry = thp_split_walk_pmd_entry, .walk_lock = PGWALK_WRLOCK_VERIFY, }; static inline void thp_split_mm(struct mm_struct *mm) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); for_each_vma(vmi, vma) { vm_flags_mod(vma, VM_NOHUGEPAGE, VM_HUGEPAGE); walk_page_vma(vma, &thp_split_walk_ops, NULL); } mm->def_flags |= VM_NOHUGEPAGE; } #else static inline void thp_split_mm(struct mm_struct *mm) { } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* * switch on pgstes for its userspace process (for kvm) */ int s390_enable_sie(void) { struct mm_struct *mm = current->mm; /* Do we have pgstes? if yes, we are done */ if (mm_has_pgste(mm)) return 0; /* Fail if the page tables are 2K */ if (!mm_alloc_pgste(mm)) return -EINVAL; mmap_write_lock(mm); mm->context.has_pgste = 1; /* split thp mappings and disable thp for future mappings */ thp_split_mm(mm); mmap_write_unlock(mm); return 0; } EXPORT_SYMBOL_GPL(s390_enable_sie); static int find_zeropage_pte_entry(pte_t *pte, unsigned long addr, unsigned long end, struct mm_walk *walk) { unsigned long *found_addr = walk->private; /* Return 1 of the page is a zeropage. */ if (is_zero_pfn(pte_pfn(*pte))) { /* * Shared zeropage in e.g., a FS DAX mapping? We cannot do the * right thing and likely don't care: FAULT_FLAG_UNSHARE * currently only works in COW mappings, which is also where * mm_forbids_zeropage() is checked. */ if (!is_cow_mapping(walk->vma->vm_flags)) return -EFAULT; *found_addr = addr; return 1; } return 0; } static const struct mm_walk_ops find_zeropage_ops = { .pte_entry = find_zeropage_pte_entry, .walk_lock = PGWALK_WRLOCK, }; /* * Unshare all shared zeropages, replacing them by anonymous pages. Note that * we cannot simply zap all shared zeropages, because this could later * trigger unexpected userfaultfd missing events. * * This must be called after mm->context.allow_cow_sharing was * set to 0, to avoid future mappings of shared zeropages. * * mm contracts with s390, that even if mm were to remove a page table, * and racing with walk_page_range_vma() calling pte_offset_map_lock() * would fail, it will never insert a page table containing empty zero * pages once mm_forbids_zeropage(mm) i.e. * mm->context.allow_cow_sharing is set to 0. */ static int __s390_unshare_zeropages(struct mm_struct *mm) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); unsigned long addr; vm_fault_t fault; int rc; for_each_vma(vmi, vma) { /* * We could only look at COW mappings, but it's more future * proof to catch unexpected zeropages in other mappings and * fail. */ if ((vma->vm_flags & VM_PFNMAP) || is_vm_hugetlb_page(vma)) continue; addr = vma->vm_start; retry: rc = walk_page_range_vma(vma, addr, vma->vm_end, &find_zeropage_ops, &addr); if (rc < 0) return rc; else if (!rc) continue; /* addr was updated by find_zeropage_pte_entry() */ fault = handle_mm_fault(vma, addr, FAULT_FLAG_UNSHARE | FAULT_FLAG_REMOTE, NULL); if (fault & VM_FAULT_OOM) return -ENOMEM; /* * See break_ksm(): even after handle_mm_fault() returned 0, we * must start the lookup from the current address, because * handle_mm_fault() may back out if there's any difficulty. * * VM_FAULT_SIGBUS and VM_FAULT_SIGSEGV are unexpected but * maybe they could trigger in the future on concurrent * truncation. In that case, the shared zeropage would be gone * and we can simply retry and make progress. */ cond_resched(); goto retry; } return 0; } static int __s390_disable_cow_sharing(struct mm_struct *mm) { int rc; if (!mm->context.allow_cow_sharing) return 0; mm->context.allow_cow_sharing = 0; /* Replace all shared zeropages by anonymous pages. */ rc = __s390_unshare_zeropages(mm); /* * Make sure to disable KSM (if enabled for the whole process or * individual VMAs). Note that nothing currently hinders user space * from re-enabling it. */ if (!rc) rc = ksm_disable(mm); if (rc) mm->context.allow_cow_sharing = 1; return rc; } /* * Disable most COW-sharing of memory pages for the whole process: * (1) Disable KSM and unmerge/unshare any KSM pages. * (2) Disallow shared zeropages and unshare any zerpages that are mapped. * * Not that we currently don't bother with COW-shared pages that are shared * with parent/child processes due to fork(). */ int s390_disable_cow_sharing(void) { int rc; mmap_write_lock(current->mm); rc = __s390_disable_cow_sharing(current->mm); mmap_write_unlock(current->mm); return rc; } EXPORT_SYMBOL_GPL(s390_disable_cow_sharing); /* * Enable storage key handling from now on and initialize the storage * keys with the default key. */ static int __s390_enable_skey_pte(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { /* Clear storage key */ ptep_zap_key(walk->mm, addr, pte); return 0; } /* * Give a chance to schedule after setting a key to 256 pages. * We only hold the mm lock, which is a rwsem and the kvm srcu. * Both can sleep. */ static int __s390_enable_skey_pmd(pmd_t *pmd, unsigned long addr, unsigned long next, struct mm_walk *walk) { cond_resched(); return 0; } static int __s390_enable_skey_hugetlb(pte_t *pte, unsigned long addr, unsigned long hmask, unsigned long next, struct mm_walk *walk) { pmd_t *pmd = (pmd_t *)pte; unsigned long start, end; struct folio *folio = page_folio(pmd_page(*pmd)); /* * The write check makes sure we do not set a key on shared * memory. This is needed as the walker does not differentiate * between actual guest memory and the process executable or * shared libraries. */ if (pmd_val(*pmd) & _SEGMENT_ENTRY_INVALID || !(pmd_val(*pmd) & _SEGMENT_ENTRY_WRITE)) return 0; start = pmd_val(*pmd) & HPAGE_MASK; end = start + HPAGE_SIZE; __storage_key_init_range(start, end); set_bit(PG_arch_1, &folio->flags); cond_resched(); return 0; } static const struct mm_walk_ops enable_skey_walk_ops = { .hugetlb_entry = __s390_enable_skey_hugetlb, .pte_entry = __s390_enable_skey_pte, .pmd_entry = __s390_enable_skey_pmd, .walk_lock = PGWALK_WRLOCK, }; int s390_enable_skey(void) { struct mm_struct *mm = current->mm; int rc = 0; mmap_write_lock(mm); if (mm_uses_skeys(mm)) goto out_up; mm->context.uses_skeys = 1; rc = __s390_disable_cow_sharing(mm); if (rc) { mm->context.uses_skeys = 0; goto out_up; } walk_page_range(mm, 0, TASK_SIZE, &enable_skey_walk_ops, NULL); out_up: mmap_write_unlock(mm); return rc; } EXPORT_SYMBOL_GPL(s390_enable_skey); /* * Reset CMMA state, make all pages stable again. */ static int __s390_reset_cmma(pte_t *pte, unsigned long addr, unsigned long next, struct mm_walk *walk) { ptep_zap_unused(walk->mm, addr, pte, 1); return 0; } static const struct mm_walk_ops reset_cmma_walk_ops = { .pte_entry = __s390_reset_cmma, .walk_lock = PGWALK_WRLOCK, }; void s390_reset_cmma(struct mm_struct *mm) { mmap_write_lock(mm); walk_page_range(mm, 0, TASK_SIZE, &reset_cmma_walk_ops, NULL); mmap_write_unlock(mm); } EXPORT_SYMBOL_GPL(s390_reset_cmma); #define GATHER_GET_PAGES 32 struct reset_walk_state { unsigned long next; unsigned long count; unsigned long pfns[GATHER_GET_PAGES]; }; static int s390_gather_pages(pte_t *ptep, unsigned long addr, unsigned long next, struct mm_walk *walk) { struct reset_walk_state *p = walk->private; pte_t pte = READ_ONCE(*ptep); if (pte_present(pte)) { /* we have a reference from the mapping, take an extra one */ get_page(phys_to_page(pte_val(pte))); p->pfns[p->count] = phys_to_pfn(pte_val(pte)); p->next = next; p->count++; } return p->count >= GATHER_GET_PAGES; } static const struct mm_walk_ops gather_pages_ops = { .pte_entry = s390_gather_pages, .walk_lock = PGWALK_RDLOCK, }; /* * Call the Destroy secure page UVC on each page in the given array of PFNs. * Each page needs to have an extra reference, which will be released here. */ void s390_uv_destroy_pfns(unsigned long count, unsigned long *pfns) { struct folio *folio; unsigned long i; for (i = 0; i < count; i++) { folio = pfn_folio(pfns[i]); /* we always have an extra reference */ uv_destroy_folio(folio); /* get rid of the extra reference */ folio_put(folio); cond_resched(); } } EXPORT_SYMBOL_GPL(s390_uv_destroy_pfns); /** * __s390_uv_destroy_range - Call the destroy secure page UVC on each page * in the given range of the given address space. * @mm: the mm to operate on * @start: the start of the range * @end: the end of the range * @interruptible: if not 0, stop when a fatal signal is received * * Walk the given range of the given address space and call the destroy * secure page UVC on each page. Optionally exit early if a fatal signal is * pending. * * Return: 0 on success, -EINTR if the function stopped before completing */ int __s390_uv_destroy_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool interruptible) { struct reset_walk_state state = { .next = start }; int r = 1; while (r > 0) { state.count = 0; mmap_read_lock(mm); r = walk_page_range(mm, state.next, end, &gather_pages_ops, &state); mmap_read_unlock(mm); cond_resched(); s390_uv_destroy_pfns(state.count, state.pfns); if (interruptible && fatal_signal_pending(current)) return -EINTR; } return 0; } EXPORT_SYMBOL_GPL(__s390_uv_destroy_range); /** * s390_unlist_old_asce - Remove the topmost level of page tables from the * list of page tables of the gmap. * @gmap: the gmap whose table is to be removed * * On s390x, KVM keeps a list of all pages containing the page tables of the * gmap (the CRST list). This list is used at tear down time to free all * pages that are now not needed anymore. * * This function removes the topmost page of the tree (the one pointed to by * the ASCE) from the CRST list. * * This means that it will not be freed when the VM is torn down, and needs * to be handled separately by the caller, unless a leak is actually * intended. Notice that this function will only remove the page from the * list, the page will still be used as a top level page table (and ASCE). */ void s390_unlist_old_asce(struct gmap *gmap) { struct page *old; old = virt_to_page(gmap->table); spin_lock(&gmap->guest_table_lock); list_del(&old->lru); /* * Sometimes the topmost page might need to be "removed" multiple * times, for example if the VM is rebooted into secure mode several * times concurrently, or if s390_replace_asce fails after calling * s390_remove_old_asce and is attempted again later. In that case * the old asce has been removed from the list, and therefore it * will not be freed when the VM terminates, but the ASCE is still * in use and still pointed to. * A subsequent call to replace_asce will follow the pointer and try * to remove the same page from the list again. * Therefore it's necessary that the page of the ASCE has valid * pointers, so list_del can work (and do nothing) without * dereferencing stale or invalid pointers. */ INIT_LIST_HEAD(&old->lru); spin_unlock(&gmap->guest_table_lock); } EXPORT_SYMBOL_GPL(s390_unlist_old_asce); /** * s390_replace_asce - Try to replace the current ASCE of a gmap with a copy * @gmap: the gmap whose ASCE needs to be replaced * * If the ASCE is a SEGMENT type then this function will return -EINVAL, * otherwise the pointers in the host_to_guest radix tree will keep pointing * to the wrong pages, causing use-after-free and memory corruption. * If the allocation of the new top level page table fails, the ASCE is not * replaced. * In any case, the old ASCE is always removed from the gmap CRST list. * Therefore the caller has to make sure to save a pointer to it * beforehand, unless a leak is actually intended. */ int s390_replace_asce(struct gmap *gmap) { unsigned long asce; struct page *page; void *table; s390_unlist_old_asce(gmap); /* Replacing segment type ASCEs would cause serious issues */ if ((gmap->asce & _ASCE_TYPE_MASK) == _ASCE_TYPE_SEGMENT) return -EINVAL; page = gmap_alloc_crst(); if (!page) return -ENOMEM; page->index = 0; table = page_to_virt(page); memcpy(table, gmap->table, 1UL << (CRST_ALLOC_ORDER + PAGE_SHIFT)); /* * The caller has to deal with the old ASCE, but here we make sure * the new one is properly added to the CRST list, so that * it will be freed when the VM is torn down. */ spin_lock(&gmap->guest_table_lock); list_add(&page->lru, &gmap->crst_list); spin_unlock(&gmap->guest_table_lock); /* Set new table origin while preserving existing ASCE control bits */ asce = (gmap->asce & ~_ASCE_ORIGIN) | __pa(table); WRITE_ONCE(gmap->asce, asce); WRITE_ONCE(gmap->mm->context.gmap_asce, asce); WRITE_ONCE(gmap->table, table); return 0; } EXPORT_SYMBOL_GPL(s390_replace_asce);
Information contained on this website is for historical information purposes only and does not indicate or represent copyright ownership.
Created with Cregit http://github.com/cregit/cregit
Version 2.0-RC1