123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975976977978979980981982983984985986987988989990991992993994995996997998999100010011002100310041005100610071008100910101011101210131014101510161017101810191020102110221023102410251026102710281029103010311032103310341035103610371038103910401041104210431044104510461047104810491050105110521053105410551056105710581059106010611062106310641065106610671068106910701071107210731074107510761077107810791080108110821083108410851086108710881089109010911092109310941095109610971098109911001101110211031104110511061107110811091110111111121113111411151116111711181119112011211122112311241125112611271128112911301131113211331134113511361137113811391140114111421143114411451146114711481149115011511152115311541155115611571158115911601161116211631164116511661167116811691170117111721173117411751176117711781179118011811182118311841185118611871188118911901191119211931194119511961197119811991200120112021203120412051206120712081209121012111212121312141215121612171218121912201221122212231224122512261227122812291230123112321233123412351236123712381239124012411242124312441245124612471248124912501251125212531254125512561257125812591260126112621263126412651266126712681269127012711272127312741275127612771278127912801281128212831284128512861287128812891290129112921293129412951296129712981299130013011302130313041305130613071308130913101311131213131314131513161317131813191320132113221323132413251326132713281329133013311332133313341335133613371338133913401341134213431344134513461347134813491350135113521353135413551356135713581359136013611362136313641365136613671368136913701371137213731374137513761377137813791380138113821383138413851386138713881389139013911392139313941395139613971398139914001401140214031404140514061407140814091410141114121413141414151416141714181419142014211422142314241425142614271428142914301431143214331434143514361437143814391440144114421443144414451446144714481449145014511452145314541455145614571458145914601461146214631464146514661467146814691470147114721473147414751476147714781479148014811482148314841485148614871488148914901491149214931494149514961497149814991500150115021503150415051506150715081509151015111512151315141515151615171518151915201521152215231524152515261527152815291530153115321533153415351536153715381539154015411542154315441545154615471548154915501551155215531554155515561557155815591560156115621563156415651566156715681569157015711572157315741575157615771578157915801581158215831584158515861587158815891590159115921593159415951596159715981599160016011602160316041605160616071608160916101611161216131614161516161617161816191620162116221623162416251626162716281629163016311632163316341635163616371638163916401641164216431644164516461647164816491650165116521653165416551656165716581659166016611662166316641665166616671668166916701671167216731674167516761677167816791680168116821683168416851686168716881689169016911692169316941695169616971698169917001701170217031704170517061707170817091710171117121713171417151716171717181719172017211722172317241725172617271728172917301731173217331734173517361737173817391740174117421743174417451746174717481749175017511752175317541755175617571758175917601761176217631764176517661767176817691770177117721773177417751776177717781779178017811782178317841785178617871788178917901791179217931794179517961797179817991800180118021803180418051806180718081809181018111812181318141815181618171818181918201821182218231824182518261827182818291830183118321833183418351836183718381839184018411842184318441845184618471848184918501851185218531854185518561857185818591860186118621863186418651866186718681869187018711872187318741875187618771878187918801881188218831884188518861887188818891890189118921893189418951896189718981899190019011902190319041905190619071908190919101911191219131914191519161917191819191920192119221923192419251926192719281929193019311932193319341935193619371938193919401941194219431944194519461947194819491950195119521953195419551956195719581959196019611962196319641965196619671968196919701971197219731974197519761977197819791980198119821983198419851986198719881989199019911992199319941995199619971998199920002001200220032004200520062007200820092010201120122013201420152016201720182019202020212022202320242025202620272028202920302031203220332034203520362037203820392040204120422043204420452046204720482049205020512052205320542055205620572058205920602061206220632064206520662067206820692070207120722073207420752076207720782079208020812082208320842085208620872088208920902091209220932094209520962097209820992100210121022103210421052106210721082109211021112112211321142115211621172118211921202121 |
- // SPDX-License-Identifier: GPL-2.0-only
- /*
- * fs/userfaultfd.c
- *
- * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org>
- * Copyright (C) 2008-2009 Red Hat, Inc.
- * Copyright (C) 2015 Red Hat, Inc.
- *
- * Some part derived from fs/eventfd.c (anon inode setup) and
- * mm/ksm.c (mm hashing).
- */
- #include <linux/list.h>
- #include <linux/hashtable.h>
- #include <linux/sched/signal.h>
- #include <linux/sched/mm.h>
- #include <linux/mm.h>
- #include <linux/mmu_notifier.h>
- #include <linux/poll.h>
- #include <linux/slab.h>
- #include <linux/seq_file.h>
- #include <linux/file.h>
- #include <linux/bug.h>
- #include <linux/anon_inodes.h>
- #include <linux/syscalls.h>
- #include <linux/userfaultfd_k.h>
- #include <linux/mempolicy.h>
- #include <linux/ioctl.h>
- #include <linux/security.h>
- #include <linux/hugetlb.h>
- int sysctl_unprivileged_userfaultfd __read_mostly;
- static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly;
- /*
- * Start with fault_pending_wqh and fault_wqh so they're more likely
- * to be in the same cacheline.
- *
- * Locking order:
- * fd_wqh.lock
- * fault_pending_wqh.lock
- * fault_wqh.lock
- * event_wqh.lock
- *
- * To avoid deadlocks, IRQs must be disabled when taking any of the above locks,
- * since fd_wqh.lock is taken by aio_poll() while it's holding a lock that's
- * also taken in IRQ context.
- */
- struct userfaultfd_ctx {
- /* waitqueue head for the pending (i.e. not read) userfaults */
- wait_queue_head_t fault_pending_wqh;
- /* waitqueue head for the userfaults */
- wait_queue_head_t fault_wqh;
- /* waitqueue head for the pseudo fd to wakeup poll/read */
- wait_queue_head_t fd_wqh;
- /* waitqueue head for events */
- wait_queue_head_t event_wqh;
- /* a refile sequence protected by fault_pending_wqh lock */
- seqcount_spinlock_t refile_seq;
- /* pseudo fd refcounting */
- refcount_t refcount;
- /* userfaultfd syscall flags */
- unsigned int flags;
- /* features requested from the userspace */
- unsigned int features;
- /* released */
- bool released;
- /* memory mappings are changing because of non-cooperative event */
- bool mmap_changing;
- /* mm with one ore more vmas attached to this userfaultfd_ctx */
- struct mm_struct *mm;
- };
- struct userfaultfd_fork_ctx {
- struct userfaultfd_ctx *orig;
- struct userfaultfd_ctx *new;
- struct list_head list;
- };
- struct userfaultfd_unmap_ctx {
- struct userfaultfd_ctx *ctx;
- unsigned long start;
- unsigned long end;
- struct list_head list;
- };
- struct userfaultfd_wait_queue {
- struct uffd_msg msg;
- wait_queue_entry_t wq;
- struct userfaultfd_ctx *ctx;
- bool waken;
- };
- struct userfaultfd_wake_range {
- unsigned long start;
- unsigned long len;
- };
- /* internal indication that UFFD_API ioctl was successfully executed */
- #define UFFD_FEATURE_INITIALIZED (1u << 31)
- static bool userfaultfd_is_initialized(struct userfaultfd_ctx *ctx)
- {
- return ctx->features & UFFD_FEATURE_INITIALIZED;
- }
- static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
- int wake_flags, void *key)
- {
- struct userfaultfd_wake_range *range = key;
- int ret;
- struct userfaultfd_wait_queue *uwq;
- unsigned long start, len;
- uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
- ret = 0;
- /* len == 0 means wake all */
- start = range->start;
- len = range->len;
- if (len && (start > uwq->msg.arg.pagefault.address ||
- start + len <= uwq->msg.arg.pagefault.address))
- goto out;
- WRITE_ONCE(uwq->waken, true);
- /*
- * The Program-Order guarantees provided by the scheduler
- * ensure uwq->waken is visible before the task is woken.
- */
- ret = wake_up_state(wq->private, mode);
- if (ret) {
- /*
- * Wake only once, autoremove behavior.
- *
- * After the effect of list_del_init is visible to the other
- * CPUs, the waitqueue may disappear from under us, see the
- * !list_empty_careful() in handle_userfault().
- *
- * try_to_wake_up() has an implicit smp_mb(), and the
- * wq->private is read before calling the extern function
- * "wake_up_state" (which in turns calls try_to_wake_up).
- */
- list_del_init(&wq->entry);
- }
- out:
- return ret;
- }
- /**
- * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd
- * context.
- * @ctx: [in] Pointer to the userfaultfd context.
- */
- static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx)
- {
- refcount_inc(&ctx->refcount);
- }
- /**
- * userfaultfd_ctx_put - Releases a reference to the internal userfaultfd
- * context.
- * @ctx: [in] Pointer to userfaultfd context.
- *
- * The userfaultfd context reference must have been previously acquired either
- * with userfaultfd_ctx_get() or userfaultfd_ctx_fdget().
- */
- static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx)
- {
- if (refcount_dec_and_test(&ctx->refcount)) {
- VM_BUG_ON(spin_is_locked(&ctx->fault_pending_wqh.lock));
- VM_BUG_ON(waitqueue_active(&ctx->fault_pending_wqh));
- VM_BUG_ON(spin_is_locked(&ctx->fault_wqh.lock));
- VM_BUG_ON(waitqueue_active(&ctx->fault_wqh));
- VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock));
- VM_BUG_ON(waitqueue_active(&ctx->event_wqh));
- VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock));
- VM_BUG_ON(waitqueue_active(&ctx->fd_wqh));
- mmdrop(ctx->mm);
- kmem_cache_free(userfaultfd_ctx_cachep, ctx);
- }
- }
- static inline void msg_init(struct uffd_msg *msg)
- {
- BUILD_BUG_ON(sizeof(struct uffd_msg) != 32);
- /*
- * Must use memset to zero out the paddings or kernel data is
- * leaked to userland.
- */
- memset(msg, 0, sizeof(struct uffd_msg));
- }
- static inline struct uffd_msg userfault_msg(unsigned long address,
- unsigned int flags,
- unsigned long reason,
- unsigned int features)
- {
- struct uffd_msg msg;
- msg_init(&msg);
- msg.event = UFFD_EVENT_PAGEFAULT;
- msg.arg.pagefault.address = address;
- /*
- * These flags indicate why the userfault occurred:
- * - UFFD_PAGEFAULT_FLAG_WP indicates a write protect fault.
- * - UFFD_PAGEFAULT_FLAG_MINOR indicates a minor fault.
- * - Neither of these flags being set indicates a MISSING fault.
- *
- * Separately, UFFD_PAGEFAULT_FLAG_WRITE indicates it was a write
- * fault. Otherwise, it was a read fault.
- */
- if (flags & FAULT_FLAG_WRITE)
- msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE;
- if (reason & VM_UFFD_WP)
- msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP;
- if (reason & VM_UFFD_MINOR)
- msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_MINOR;
- if (features & UFFD_FEATURE_THREAD_ID)
- msg.arg.pagefault.feat.ptid = task_pid_vnr(current);
- return msg;
- }
- #ifdef CONFIG_HUGETLB_PAGE
- /*
- * Same functionality as userfaultfd_must_wait below with modifications for
- * hugepmd ranges.
- */
- static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
- struct vm_area_struct *vma,
- unsigned long address,
- unsigned long flags,
- unsigned long reason)
- {
- struct mm_struct *mm = ctx->mm;
- pte_t *ptep, pte;
- bool ret = true;
- mmap_assert_locked(mm);
- ptep = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
- if (!ptep)
- goto out;
- ret = false;
- pte = huge_ptep_get(ptep);
- /*
- * Lockless access: we're in a wait_event so it's ok if it
- * changes under us.
- */
- if (huge_pte_none(pte))
- ret = true;
- if (!huge_pte_write(pte) && (reason & VM_UFFD_WP))
- ret = true;
- out:
- return ret;
- }
- #else
- static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
- struct vm_area_struct *vma,
- unsigned long address,
- unsigned long flags,
- unsigned long reason)
- {
- return false; /* should never get here */
- }
- #endif /* CONFIG_HUGETLB_PAGE */
- /*
- * Verify the pagetables are still not ok after having reigstered into
- * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any
- * userfault that has already been resolved, if userfaultfd_read and
- * UFFDIO_COPY|ZEROPAGE are being run simultaneously on two different
- * threads.
- */
- static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
- unsigned long address,
- unsigned long flags,
- unsigned long reason)
- {
- struct mm_struct *mm = ctx->mm;
- pgd_t *pgd;
- p4d_t *p4d;
- pud_t *pud;
- pmd_t *pmd, _pmd;
- pte_t *pte;
- bool ret = true;
- mmap_assert_locked(mm);
- pgd = pgd_offset(mm, address);
- if (!pgd_present(*pgd))
- goto out;
- p4d = p4d_offset(pgd, address);
- if (!p4d_present(*p4d))
- goto out;
- pud = pud_offset(p4d, address);
- if (!pud_present(*pud))
- goto out;
- pmd = pmd_offset(pud, address);
- /*
- * READ_ONCE must function as a barrier with narrower scope
- * and it must be equivalent to:
- * _pmd = *pmd; barrier();
- *
- * This is to deal with the instability (as in
- * pmd_trans_unstable) of the pmd.
- */
- _pmd = READ_ONCE(*pmd);
- if (pmd_none(_pmd))
- goto out;
- ret = false;
- if (!pmd_present(_pmd))
- goto out;
- if (pmd_trans_huge(_pmd)) {
- if (!pmd_write(_pmd) && (reason & VM_UFFD_WP))
- ret = true;
- goto out;
- }
- /*
- * the pmd is stable (as in !pmd_trans_unstable) so we can re-read it
- * and use the standard pte_offset_map() instead of parsing _pmd.
- */
- pte = pte_offset_map(pmd, address);
- /*
- * Lockless access: we're in a wait_event so it's ok if it
- * changes under us.
- */
- if (pte_none(*pte))
- ret = true;
- if (!pte_write(*pte) && (reason & VM_UFFD_WP))
- ret = true;
- pte_unmap(pte);
- out:
- return ret;
- }
- static inline long userfaultfd_get_blocking_state(unsigned int flags)
- {
- if (flags & FAULT_FLAG_INTERRUPTIBLE)
- return TASK_INTERRUPTIBLE;
- if (flags & FAULT_FLAG_KILLABLE)
- return TASK_KILLABLE;
- return TASK_UNINTERRUPTIBLE;
- }
- /*
- * The locking rules involved in returning VM_FAULT_RETRY depending on
- * FAULT_FLAG_ALLOW_RETRY, FAULT_FLAG_RETRY_NOWAIT and
- * FAULT_FLAG_KILLABLE are not straightforward. The "Caution"
- * recommendation in __lock_page_or_retry is not an understatement.
- *
- * If FAULT_FLAG_ALLOW_RETRY is set, the mmap_lock must be released
- * before returning VM_FAULT_RETRY only if FAULT_FLAG_RETRY_NOWAIT is
- * not set.
- *
- * If FAULT_FLAG_ALLOW_RETRY is set but FAULT_FLAG_KILLABLE is not
- * set, VM_FAULT_RETRY can still be returned if and only if there are
- * fatal_signal_pending()s, and the mmap_lock must be released before
- * returning it.
- */
- vm_fault_t handle_userfault(struct vm_fault *vmf, unsigned long reason)
- {
- struct mm_struct *mm = vmf->vma->vm_mm;
- struct userfaultfd_ctx *ctx;
- struct userfaultfd_wait_queue uwq;
- vm_fault_t ret = VM_FAULT_SIGBUS;
- bool must_wait;
- long blocking_state;
- /*
- * We don't do userfault handling for the final child pid update.
- *
- * We also don't do userfault handling during
- * coredumping. hugetlbfs has the special
- * follow_hugetlb_page() to skip missing pages in the
- * FOLL_DUMP case, anon memory also checks for FOLL_DUMP with
- * the no_page_table() helper in follow_page_mask(), but the
- * shmem_vm_ops->fault method is invoked even during
- * coredumping without mmap_lock and it ends up here.
- */
- if (current->flags & (PF_EXITING|PF_DUMPCORE))
- goto out;
- /*
- * Coredumping runs without mmap_lock so we can only check that
- * the mmap_lock is held, if PF_DUMPCORE was not set.
- */
- mmap_assert_locked(mm);
- ctx = vmf->vma->vm_userfaultfd_ctx.ctx;
- if (!ctx)
- goto out;
- BUG_ON(ctx->mm != mm);
- /* Any unrecognized flag is a bug. */
- VM_BUG_ON(reason & ~__VM_UFFD_FLAGS);
- /* 0 or > 1 flags set is a bug; we expect exactly 1. */
- VM_BUG_ON(!reason || (reason & (reason - 1)));
- if (ctx->features & UFFD_FEATURE_SIGBUS)
- goto out;
- if ((vmf->flags & FAULT_FLAG_USER) == 0 &&
- ctx->flags & UFFD_USER_MODE_ONLY) {
- printk_once(KERN_WARNING "uffd: Set unprivileged_userfaultfd "
- "sysctl knob to 1 if kernel faults must be handled "
- "without obtaining CAP_SYS_PTRACE capability\n");
- goto out;
- }
- /*
- * If it's already released don't get it. This avoids to loop
- * in __get_user_pages if userfaultfd_release waits on the
- * caller of handle_userfault to release the mmap_lock.
- */
- if (unlikely(READ_ONCE(ctx->released))) {
- /*
- * Don't return VM_FAULT_SIGBUS in this case, so a non
- * cooperative manager can close the uffd after the
- * last UFFDIO_COPY, without risking to trigger an
- * involuntary SIGBUS if the process was starting the
- * userfaultfd while the userfaultfd was still armed
- * (but after the last UFFDIO_COPY). If the uffd
- * wasn't already closed when the userfault reached
- * this point, that would normally be solved by
- * userfaultfd_must_wait returning 'false'.
- *
- * If we were to return VM_FAULT_SIGBUS here, the non
- * cooperative manager would be instead forced to
- * always call UFFDIO_UNREGISTER before it can safely
- * close the uffd.
- */
- ret = VM_FAULT_NOPAGE;
- goto out;
- }
- /*
- * Check that we can return VM_FAULT_RETRY.
- *
- * NOTE: it should become possible to return VM_FAULT_RETRY
- * even if FAULT_FLAG_TRIED is set without leading to gup()
- * -EBUSY failures, if the userfaultfd is to be extended for
- * VM_UFFD_WP tracking and we intend to arm the userfault
- * without first stopping userland access to the memory. For
- * VM_UFFD_MISSING userfaults this is enough for now.
- */
- if (unlikely(!(vmf->flags & FAULT_FLAG_ALLOW_RETRY))) {
- /*
- * Validate the invariant that nowait must allow retry
- * to be sure not to return SIGBUS erroneously on
- * nowait invocations.
- */
- BUG_ON(vmf->flags & FAULT_FLAG_RETRY_NOWAIT);
- #ifdef CONFIG_DEBUG_VM
- if (printk_ratelimit()) {
- printk(KERN_WARNING
- "FAULT_FLAG_ALLOW_RETRY missing %x\n",
- vmf->flags);
- dump_stack();
- }
- #endif
- goto out;
- }
- /*
- * Handle nowait, not much to do other than tell it to retry
- * and wait.
- */
- ret = VM_FAULT_RETRY;
- if (vmf->flags & FAULT_FLAG_RETRY_NOWAIT)
- goto out;
- /* take the reference before dropping the mmap_lock */
- userfaultfd_ctx_get(ctx);
- init_waitqueue_func_entry(&uwq.wq, userfaultfd_wake_function);
- uwq.wq.private = current;
- uwq.msg = userfault_msg(vmf->address, vmf->flags, reason,
- ctx->features);
- uwq.ctx = ctx;
- uwq.waken = false;
- blocking_state = userfaultfd_get_blocking_state(vmf->flags);
- spin_lock_irq(&ctx->fault_pending_wqh.lock);
- /*
- * After the __add_wait_queue the uwq is visible to userland
- * through poll/read().
- */
- __add_wait_queue(&ctx->fault_pending_wqh, &uwq.wq);
- /*
- * The smp_mb() after __set_current_state prevents the reads
- * following the spin_unlock to happen before the list_add in
- * __add_wait_queue.
- */
- set_current_state(blocking_state);
- spin_unlock_irq(&ctx->fault_pending_wqh.lock);
- if (!is_vm_hugetlb_page(vmf->vma))
- must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
- reason);
- else
- must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma,
- vmf->address,
- vmf->flags, reason);
- mmap_read_unlock(mm);
- if (likely(must_wait && !READ_ONCE(ctx->released))) {
- wake_up_poll(&ctx->fd_wqh, EPOLLIN);
- schedule();
- }
- __set_current_state(TASK_RUNNING);
- /*
- * Here we race with the list_del; list_add in
- * userfaultfd_ctx_read(), however because we don't ever run
- * list_del_init() to refile across the two lists, the prev
- * and next pointers will never point to self. list_add also
- * would never let any of the two pointers to point to
- * self. So list_empty_careful won't risk to see both pointers
- * pointing to self at any time during the list refile. The
- * only case where list_del_init() is called is the full
- * removal in the wake function and there we don't re-list_add
- * and it's fine not to block on the spinlock. The uwq on this
- * kernel stack can be released after the list_del_init.
- */
- if (!list_empty_careful(&uwq.wq.entry)) {
- spin_lock_irq(&ctx->fault_pending_wqh.lock);
- /*
- * No need of list_del_init(), the uwq on the stack
- * will be freed shortly anyway.
- */
- list_del(&uwq.wq.entry);
- spin_unlock_irq(&ctx->fault_pending_wqh.lock);
- }
- /*
- * ctx may go away after this if the userfault pseudo fd is
- * already released.
- */
- userfaultfd_ctx_put(ctx);
- out:
- return ret;
- }
- static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
- struct userfaultfd_wait_queue *ewq)
- {
- struct userfaultfd_ctx *release_new_ctx;
- if (WARN_ON_ONCE(current->flags & PF_EXITING))
- goto out;
- ewq->ctx = ctx;
- init_waitqueue_entry(&ewq->wq, current);
- release_new_ctx = NULL;
- spin_lock_irq(&ctx->event_wqh.lock);
- /*
- * After the __add_wait_queue the uwq is visible to userland
- * through poll/read().
- */
- __add_wait_queue(&ctx->event_wqh, &ewq->wq);
- for (;;) {
- set_current_state(TASK_KILLABLE);
- if (ewq->msg.event == 0)
- break;
- if (READ_ONCE(ctx->released) ||
- fatal_signal_pending(current)) {
- /*
- * &ewq->wq may be queued in fork_event, but
- * __remove_wait_queue ignores the head
- * parameter. It would be a problem if it
- * didn't.
- */
- __remove_wait_queue(&ctx->event_wqh, &ewq->wq);
- if (ewq->msg.event == UFFD_EVENT_FORK) {
- struct userfaultfd_ctx *new;
- new = (struct userfaultfd_ctx *)
- (unsigned long)
- ewq->msg.arg.reserved.reserved1;
- release_new_ctx = new;
- }
- break;
- }
- spin_unlock_irq(&ctx->event_wqh.lock);
- wake_up_poll(&ctx->fd_wqh, EPOLLIN);
- schedule();
- spin_lock_irq(&ctx->event_wqh.lock);
- }
- __set_current_state(TASK_RUNNING);
- spin_unlock_irq(&ctx->event_wqh.lock);
- if (release_new_ctx) {
- struct vm_area_struct *vma;
- struct mm_struct *mm = release_new_ctx->mm;
- /* the various vma->vm_userfaultfd_ctx still points to it */
- mmap_write_lock(mm);
- for (vma = mm->mmap; vma; vma = vma->vm_next)
- if (vma->vm_userfaultfd_ctx.ctx == release_new_ctx) {
- vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~__VM_UFFD_FLAGS;
- }
- mmap_write_unlock(mm);
- userfaultfd_ctx_put(release_new_ctx);
- }
- /*
- * ctx may go away after this if the userfault pseudo fd is
- * already released.
- */
- out:
- WRITE_ONCE(ctx->mmap_changing, false);
- userfaultfd_ctx_put(ctx);
- }
- static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx,
- struct userfaultfd_wait_queue *ewq)
- {
- ewq->msg.event = 0;
- wake_up_locked(&ctx->event_wqh);
- __remove_wait_queue(&ctx->event_wqh, &ewq->wq);
- }
- int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
- {
- struct userfaultfd_ctx *ctx = NULL, *octx;
- struct userfaultfd_fork_ctx *fctx;
- octx = vma->vm_userfaultfd_ctx.ctx;
- if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
- vm_write_begin(vma);
- vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- WRITE_ONCE(vma->vm_flags,
- vma->vm_flags & ~__VM_UFFD_FLAGS);
- vm_write_end(vma);
- return 0;
- }
- list_for_each_entry(fctx, fcs, list)
- if (fctx->orig == octx) {
- ctx = fctx->new;
- break;
- }
- if (!ctx) {
- fctx = kmalloc(sizeof(*fctx), GFP_KERNEL);
- if (!fctx)
- return -ENOMEM;
- ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
- if (!ctx) {
- kfree(fctx);
- return -ENOMEM;
- }
- refcount_set(&ctx->refcount, 1);
- ctx->flags = octx->flags;
- ctx->features = octx->features;
- ctx->released = false;
- ctx->mmap_changing = false;
- ctx->mm = vma->vm_mm;
- mmgrab(ctx->mm);
- userfaultfd_ctx_get(octx);
- WRITE_ONCE(octx->mmap_changing, true);
- fctx->orig = octx;
- fctx->new = ctx;
- list_add_tail(&fctx->list, fcs);
- }
- vma->vm_userfaultfd_ctx.ctx = ctx;
- return 0;
- }
- static void dup_fctx(struct userfaultfd_fork_ctx *fctx)
- {
- struct userfaultfd_ctx *ctx = fctx->orig;
- struct userfaultfd_wait_queue ewq;
- msg_init(&ewq.msg);
- ewq.msg.event = UFFD_EVENT_FORK;
- ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new;
- userfaultfd_event_wait_completion(ctx, &ewq);
- }
- void dup_userfaultfd_complete(struct list_head *fcs)
- {
- struct userfaultfd_fork_ctx *fctx, *n;
- list_for_each_entry_safe(fctx, n, fcs, list) {
- dup_fctx(fctx);
- list_del(&fctx->list);
- kfree(fctx);
- }
- }
- void mremap_userfaultfd_prep(struct vm_area_struct *vma,
- struct vm_userfaultfd_ctx *vm_ctx)
- {
- struct userfaultfd_ctx *ctx;
- ctx = vma->vm_userfaultfd_ctx.ctx;
- if (!ctx)
- return;
- if (ctx->features & UFFD_FEATURE_EVENT_REMAP) {
- vm_ctx->ctx = ctx;
- userfaultfd_ctx_get(ctx);
- WRITE_ONCE(ctx->mmap_changing, true);
- } else {
- /* Drop uffd context if remap feature not enabled */
- vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vma->vm_flags &= ~__VM_UFFD_FLAGS;
- }
- }
- void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
- unsigned long from, unsigned long to,
- unsigned long len)
- {
- struct userfaultfd_ctx *ctx = vm_ctx->ctx;
- struct userfaultfd_wait_queue ewq;
- if (!ctx)
- return;
- if (to & ~PAGE_MASK) {
- userfaultfd_ctx_put(ctx);
- return;
- }
- msg_init(&ewq.msg);
- ewq.msg.event = UFFD_EVENT_REMAP;
- ewq.msg.arg.remap.from = from;
- ewq.msg.arg.remap.to = to;
- ewq.msg.arg.remap.len = len;
- userfaultfd_event_wait_completion(ctx, &ewq);
- }
- bool userfaultfd_remove(struct vm_area_struct *vma,
- unsigned long start, unsigned long end)
- {
- struct mm_struct *mm = vma->vm_mm;
- struct userfaultfd_ctx *ctx;
- struct userfaultfd_wait_queue ewq;
- ctx = vma->vm_userfaultfd_ctx.ctx;
- if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE))
- return true;
- userfaultfd_ctx_get(ctx);
- WRITE_ONCE(ctx->mmap_changing, true);
- mmap_read_unlock(mm);
- msg_init(&ewq.msg);
- ewq.msg.event = UFFD_EVENT_REMOVE;
- ewq.msg.arg.remove.start = start;
- ewq.msg.arg.remove.end = end;
- userfaultfd_event_wait_completion(ctx, &ewq);
- return false;
- }
- static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
- unsigned long start, unsigned long end)
- {
- struct userfaultfd_unmap_ctx *unmap_ctx;
- list_for_each_entry(unmap_ctx, unmaps, list)
- if (unmap_ctx->ctx == ctx && unmap_ctx->start == start &&
- unmap_ctx->end == end)
- return true;
- return false;
- }
- int userfaultfd_unmap_prep(struct vm_area_struct *vma,
- unsigned long start, unsigned long end,
- struct list_head *unmaps)
- {
- for ( ; vma && vma->vm_start < end; vma = vma->vm_next) {
- struct userfaultfd_unmap_ctx *unmap_ctx;
- struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
- if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) ||
- has_unmap_ctx(ctx, unmaps, start, end))
- continue;
- unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL);
- if (!unmap_ctx)
- return -ENOMEM;
- userfaultfd_ctx_get(ctx);
- WRITE_ONCE(ctx->mmap_changing, true);
- unmap_ctx->ctx = ctx;
- unmap_ctx->start = start;
- unmap_ctx->end = end;
- list_add_tail(&unmap_ctx->list, unmaps);
- }
- return 0;
- }
- void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf)
- {
- struct userfaultfd_unmap_ctx *ctx, *n;
- struct userfaultfd_wait_queue ewq;
- list_for_each_entry_safe(ctx, n, uf, list) {
- msg_init(&ewq.msg);
- ewq.msg.event = UFFD_EVENT_UNMAP;
- ewq.msg.arg.remove.start = ctx->start;
- ewq.msg.arg.remove.end = ctx->end;
- userfaultfd_event_wait_completion(ctx->ctx, &ewq);
- list_del(&ctx->list);
- kfree(ctx);
- }
- }
- static int userfaultfd_release(struct inode *inode, struct file *file)
- {
- struct userfaultfd_ctx *ctx = file->private_data;
- struct mm_struct *mm = ctx->mm;
- struct vm_area_struct *vma, *prev;
- /* len == 0 means wake all */
- struct userfaultfd_wake_range range = { .len = 0, };
- unsigned long new_flags;
- WRITE_ONCE(ctx->released, true);
- if (!mmget_not_zero(mm))
- goto wakeup;
- /*
- * Flush page faults out of all CPUs. NOTE: all page faults
- * must be retried without returning VM_FAULT_SIGBUS if
- * userfaultfd_ctx_get() succeeds but vma->vma_userfault_ctx
- * changes while handle_userfault released the mmap_lock. So
- * it's critical that released is set to true (above), before
- * taking the mmap_lock for writing.
- */
- mmap_write_lock(mm);
- prev = NULL;
- for (vma = mm->mmap; vma; vma = vma->vm_next) {
- cond_resched();
- BUG_ON(!!vma->vm_userfaultfd_ctx.ctx ^
- !!(vma->vm_flags & __VM_UFFD_FLAGS));
- if (vma->vm_userfaultfd_ctx.ctx != ctx) {
- prev = vma;
- continue;
- }
- new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
- prev = vma_merge(mm, prev, vma->vm_start, vma->vm_end,
- new_flags, vma->anon_vma,
- vma->vm_file, vma->vm_pgoff,
- vma_policy(vma),
- NULL_VM_UFFD_CTX,
- vma_get_anon_name(vma));
- if (prev)
- vma = prev;
- else
- prev = vma;
- vm_write_begin(vma);
- WRITE_ONCE(vma->vm_flags, new_flags);
- vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vm_write_end(vma);
- }
- mmap_write_unlock(mm);
- mmput(mm);
- wakeup:
- /*
- * After no new page faults can wait on this fault_*wqh, flush
- * the last page faults that may have been already waiting on
- * the fault_*wqh.
- */
- spin_lock_irq(&ctx->fault_pending_wqh.lock);
- __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL, &range);
- __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, &range);
- spin_unlock_irq(&ctx->fault_pending_wqh.lock);
- /* Flush pending events that may still wait on event_wqh */
- wake_up_all(&ctx->event_wqh);
- wake_up_poll(&ctx->fd_wqh, EPOLLHUP);
- userfaultfd_ctx_put(ctx);
- return 0;
- }
- /* fault_pending_wqh.lock must be hold by the caller */
- static inline struct userfaultfd_wait_queue *find_userfault_in(
- wait_queue_head_t *wqh)
- {
- wait_queue_entry_t *wq;
- struct userfaultfd_wait_queue *uwq;
- lockdep_assert_held(&wqh->lock);
- uwq = NULL;
- if (!waitqueue_active(wqh))
- goto out;
- /* walk in reverse to provide FIFO behavior to read userfaults */
- wq = list_last_entry(&wqh->head, typeof(*wq), entry);
- uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
- out:
- return uwq;
- }
- static inline struct userfaultfd_wait_queue *find_userfault(
- struct userfaultfd_ctx *ctx)
- {
- return find_userfault_in(&ctx->fault_pending_wqh);
- }
- static inline struct userfaultfd_wait_queue *find_userfault_evt(
- struct userfaultfd_ctx *ctx)
- {
- return find_userfault_in(&ctx->event_wqh);
- }
- static __poll_t userfaultfd_poll(struct file *file, poll_table *wait)
- {
- struct userfaultfd_ctx *ctx = file->private_data;
- __poll_t ret;
- poll_wait(file, &ctx->fd_wqh, wait);
- if (!userfaultfd_is_initialized(ctx))
- return EPOLLERR;
- /*
- * poll() never guarantees that read won't block.
- * userfaults can be waken before they're read().
- */
- if (unlikely(!(file->f_flags & O_NONBLOCK)))
- return EPOLLERR;
- /*
- * lockless access to see if there are pending faults
- * __pollwait last action is the add_wait_queue but
- * the spin_unlock would allow the waitqueue_active to
- * pass above the actual list_add inside
- * add_wait_queue critical section. So use a full
- * memory barrier to serialize the list_add write of
- * add_wait_queue() with the waitqueue_active read
- * below.
- */
- ret = 0;
- smp_mb();
- if (waitqueue_active(&ctx->fault_pending_wqh))
- ret = EPOLLIN;
- else if (waitqueue_active(&ctx->event_wqh))
- ret = EPOLLIN;
- return ret;
- }
- static const struct file_operations userfaultfd_fops;
- static int resolve_userfault_fork(struct userfaultfd_ctx *new,
- struct inode *inode,
- struct uffd_msg *msg)
- {
- int fd;
- fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, new,
- O_RDWR | (new->flags & UFFD_SHARED_FCNTL_FLAGS), inode);
- if (fd < 0)
- return fd;
- msg->arg.reserved.reserved1 = 0;
- msg->arg.fork.ufd = fd;
- return 0;
- }
- static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
- struct uffd_msg *msg, struct inode *inode)
- {
- ssize_t ret;
- DECLARE_WAITQUEUE(wait, current);
- struct userfaultfd_wait_queue *uwq;
- /*
- * Handling fork event requires sleeping operations, so
- * we drop the event_wqh lock, then do these ops, then
- * lock it back and wake up the waiter. While the lock is
- * dropped the ewq may go away so we keep track of it
- * carefully.
- */
- LIST_HEAD(fork_event);
- struct userfaultfd_ctx *fork_nctx = NULL;
- /* always take the fd_wqh lock before the fault_pending_wqh lock */
- spin_lock_irq(&ctx->fd_wqh.lock);
- __add_wait_queue(&ctx->fd_wqh, &wait);
- for (;;) {
- set_current_state(TASK_INTERRUPTIBLE);
- spin_lock(&ctx->fault_pending_wqh.lock);
- uwq = find_userfault(ctx);
- if (uwq) {
- /*
- * Use a seqcount to repeat the lockless check
- * in wake_userfault() to avoid missing
- * wakeups because during the refile both
- * waitqueue could become empty if this is the
- * only userfault.
- */
- write_seqcount_begin(&ctx->refile_seq);
- /*
- * The fault_pending_wqh.lock prevents the uwq
- * to disappear from under us.
- *
- * Refile this userfault from
- * fault_pending_wqh to fault_wqh, it's not
- * pending anymore after we read it.
- *
- * Use list_del() by hand (as
- * userfaultfd_wake_function also uses
- * list_del_init() by hand) to be sure nobody
- * changes __remove_wait_queue() to use
- * list_del_init() in turn breaking the
- * !list_empty_careful() check in
- * handle_userfault(). The uwq->wq.head list
- * must never be empty at any time during the
- * refile, or the waitqueue could disappear
- * from under us. The "wait_queue_head_t"
- * parameter of __remove_wait_queue() is unused
- * anyway.
- */
- list_del(&uwq->wq.entry);
- add_wait_queue(&ctx->fault_wqh, &uwq->wq);
- write_seqcount_end(&ctx->refile_seq);
- /* careful to always initialize msg if ret == 0 */
- *msg = uwq->msg;
- spin_unlock(&ctx->fault_pending_wqh.lock);
- ret = 0;
- break;
- }
- spin_unlock(&ctx->fault_pending_wqh.lock);
- spin_lock(&ctx->event_wqh.lock);
- uwq = find_userfault_evt(ctx);
- if (uwq) {
- *msg = uwq->msg;
- if (uwq->msg.event == UFFD_EVENT_FORK) {
- fork_nctx = (struct userfaultfd_ctx *)
- (unsigned long)
- uwq->msg.arg.reserved.reserved1;
- list_move(&uwq->wq.entry, &fork_event);
- /*
- * fork_nctx can be freed as soon as
- * we drop the lock, unless we take a
- * reference on it.
- */
- userfaultfd_ctx_get(fork_nctx);
- spin_unlock(&ctx->event_wqh.lock);
- ret = 0;
- break;
- }
- userfaultfd_event_complete(ctx, uwq);
- spin_unlock(&ctx->event_wqh.lock);
- ret = 0;
- break;
- }
- spin_unlock(&ctx->event_wqh.lock);
- if (signal_pending(current)) {
- ret = -ERESTARTSYS;
- break;
- }
- if (no_wait) {
- ret = -EAGAIN;
- break;
- }
- spin_unlock_irq(&ctx->fd_wqh.lock);
- schedule();
- spin_lock_irq(&ctx->fd_wqh.lock);
- }
- __remove_wait_queue(&ctx->fd_wqh, &wait);
- __set_current_state(TASK_RUNNING);
- spin_unlock_irq(&ctx->fd_wqh.lock);
- if (!ret && msg->event == UFFD_EVENT_FORK) {
- ret = resolve_userfault_fork(fork_nctx, inode, msg);
- spin_lock_irq(&ctx->event_wqh.lock);
- if (!list_empty(&fork_event)) {
- /*
- * The fork thread didn't abort, so we can
- * drop the temporary refcount.
- */
- userfaultfd_ctx_put(fork_nctx);
- uwq = list_first_entry(&fork_event,
- typeof(*uwq),
- wq.entry);
- /*
- * If fork_event list wasn't empty and in turn
- * the event wasn't already released by fork
- * (the event is allocated on fork kernel
- * stack), put the event back to its place in
- * the event_wq. fork_event head will be freed
- * as soon as we return so the event cannot
- * stay queued there no matter the current
- * "ret" value.
- */
- list_del(&uwq->wq.entry);
- __add_wait_queue(&ctx->event_wqh, &uwq->wq);
- /*
- * Leave the event in the waitqueue and report
- * error to userland if we failed to resolve
- * the userfault fork.
- */
- if (likely(!ret))
- userfaultfd_event_complete(ctx, uwq);
- } else {
- /*
- * Here the fork thread aborted and the
- * refcount from the fork thread on fork_nctx
- * has already been released. We still hold
- * the reference we took before releasing the
- * lock above. If resolve_userfault_fork
- * failed we've to drop it because the
- * fork_nctx has to be freed in such case. If
- * it succeeded we'll hold it because the new
- * uffd references it.
- */
- if (ret)
- userfaultfd_ctx_put(fork_nctx);
- }
- spin_unlock_irq(&ctx->event_wqh.lock);
- }
- return ret;
- }
- static ssize_t userfaultfd_read(struct file *file, char __user *buf,
- size_t count, loff_t *ppos)
- {
- struct userfaultfd_ctx *ctx = file->private_data;
- ssize_t _ret, ret = 0;
- struct uffd_msg msg;
- int no_wait = file->f_flags & O_NONBLOCK;
- struct inode *inode = file_inode(file);
- if (!userfaultfd_is_initialized(ctx))
- return -EINVAL;
- for (;;) {
- if (count < sizeof(msg))
- return ret ? ret : -EINVAL;
- _ret = userfaultfd_ctx_read(ctx, no_wait, &msg, inode);
- if (_ret < 0)
- return ret ? ret : _ret;
- if (copy_to_user((__u64 __user *) buf, &msg, sizeof(msg)))
- return ret ? ret : -EFAULT;
- ret += sizeof(msg);
- buf += sizeof(msg);
- count -= sizeof(msg);
- /*
- * Allow to read more than one fault at time but only
- * block if waiting for the very first one.
- */
- no_wait = O_NONBLOCK;
- }
- }
- static void __wake_userfault(struct userfaultfd_ctx *ctx,
- struct userfaultfd_wake_range *range)
- {
- spin_lock_irq(&ctx->fault_pending_wqh.lock);
- /* wake all in the range and autoremove */
- if (waitqueue_active(&ctx->fault_pending_wqh))
- __wake_up_locked_key(&ctx->fault_pending_wqh, TASK_NORMAL,
- range);
- if (waitqueue_active(&ctx->fault_wqh))
- __wake_up(&ctx->fault_wqh, TASK_NORMAL, 1, range);
- spin_unlock_irq(&ctx->fault_pending_wqh.lock);
- }
- static __always_inline void wake_userfault(struct userfaultfd_ctx *ctx,
- struct userfaultfd_wake_range *range)
- {
- unsigned seq;
- bool need_wakeup;
- /*
- * To be sure waitqueue_active() is not reordered by the CPU
- * before the pagetable update, use an explicit SMP memory
- * barrier here. PT lock release or mmap_read_unlock(mm) still
- * have release semantics that can allow the
- * waitqueue_active() to be reordered before the pte update.
- */
- smp_mb();
- /*
- * Use waitqueue_active because it's very frequent to
- * change the address space atomically even if there are no
- * userfaults yet. So we take the spinlock only when we're
- * sure we've userfaults to wake.
- */
- do {
- seq = read_seqcount_begin(&ctx->refile_seq);
- need_wakeup = waitqueue_active(&ctx->fault_pending_wqh) ||
- waitqueue_active(&ctx->fault_wqh);
- cond_resched();
- } while (read_seqcount_retry(&ctx->refile_seq, seq));
- if (need_wakeup)
- __wake_userfault(ctx, range);
- }
- static __always_inline int validate_range(struct mm_struct *mm,
- __u64 start, __u64 len)
- {
- __u64 task_size = mm->task_size;
- if (start & ~PAGE_MASK)
- return -EINVAL;
- if (len & ~PAGE_MASK)
- return -EINVAL;
- if (!len)
- return -EINVAL;
- if (start < mmap_min_addr)
- return -EINVAL;
- if (start >= task_size)
- return -EINVAL;
- if (len > task_size - start)
- return -EINVAL;
- return 0;
- }
- static inline bool vma_can_userfault(struct vm_area_struct *vma,
- unsigned long vm_flags)
- {
- /* FIXME: add WP support to hugetlbfs and shmem */
- if (vm_flags & VM_UFFD_WP) {
- if (is_vm_hugetlb_page(vma) || vma_is_shmem(vma))
- return false;
- }
- if (vm_flags & VM_UFFD_MINOR) {
- if (!(is_vm_hugetlb_page(vma) || vma_is_shmem(vma)))
- return false;
- }
- return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
- vma_is_shmem(vma);
- }
- static int userfaultfd_register(struct userfaultfd_ctx *ctx,
- unsigned long arg)
- {
- struct mm_struct *mm = ctx->mm;
- struct vm_area_struct *vma, *prev, *cur;
- int ret;
- struct uffdio_register uffdio_register;
- struct uffdio_register __user *user_uffdio_register;
- unsigned long vm_flags, new_flags;
- bool found;
- bool basic_ioctls;
- unsigned long start, end, vma_end;
- user_uffdio_register = (struct uffdio_register __user *) arg;
- ret = -EFAULT;
- if (copy_from_user(&uffdio_register, user_uffdio_register,
- sizeof(uffdio_register)-sizeof(__u64)))
- goto out;
- ret = -EINVAL;
- if (!uffdio_register.mode)
- goto out;
- if (uffdio_register.mode & ~UFFD_API_REGISTER_MODES)
- goto out;
- vm_flags = 0;
- if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MISSING)
- vm_flags |= VM_UFFD_MISSING;
- if (uffdio_register.mode & UFFDIO_REGISTER_MODE_WP)
- vm_flags |= VM_UFFD_WP;
- if (uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR) {
- #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
- goto out;
- #endif
- vm_flags |= VM_UFFD_MINOR;
- }
- ret = validate_range(mm, uffdio_register.range.start,
- uffdio_register.range.len);
- if (ret)
- goto out;
- start = uffdio_register.range.start;
- end = start + uffdio_register.range.len;
- ret = -ENOMEM;
- if (!mmget_not_zero(mm))
- goto out;
- mmap_write_lock(mm);
- vma = find_vma_prev(mm, start, &prev);
- if (!vma)
- goto out_unlock;
- /* check that there's at least one vma in the range */
- ret = -EINVAL;
- if (vma->vm_start >= end)
- goto out_unlock;
- /*
- * If the first vma contains huge pages, make sure start address
- * is aligned to huge page size.
- */
- if (is_vm_hugetlb_page(vma)) {
- unsigned long vma_hpagesize = vma_kernel_pagesize(vma);
- if (start & (vma_hpagesize - 1))
- goto out_unlock;
- }
- /*
- * Search for not compatible vmas.
- */
- found = false;
- basic_ioctls = false;
- for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
- cond_resched();
- BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
- !!(cur->vm_flags & __VM_UFFD_FLAGS));
- /* check not compatible vmas */
- ret = -EINVAL;
- if (!vma_can_userfault(cur, vm_flags))
- goto out_unlock;
- /*
- * UFFDIO_COPY will fill file holes even without
- * PROT_WRITE. This check enforces that if this is a
- * MAP_SHARED, the process has write permission to the backing
- * file. If VM_MAYWRITE is set it also enforces that on a
- * MAP_SHARED vma: there is no F_WRITE_SEAL and no further
- * F_WRITE_SEAL can be taken until the vma is destroyed.
- */
- ret = -EPERM;
- if (unlikely(!(cur->vm_flags & VM_MAYWRITE)))
- goto out_unlock;
- /*
- * If this vma contains ending address, and huge pages
- * check alignment.
- */
- if (is_vm_hugetlb_page(cur) && end <= cur->vm_end &&
- end > cur->vm_start) {
- unsigned long vma_hpagesize = vma_kernel_pagesize(cur);
- ret = -EINVAL;
- if (end & (vma_hpagesize - 1))
- goto out_unlock;
- }
- if ((vm_flags & VM_UFFD_WP) && !(cur->vm_flags & VM_MAYWRITE))
- goto out_unlock;
- /*
- * Check that this vma isn't already owned by a
- * different userfaultfd. We can't allow more than one
- * userfaultfd to own a single vma simultaneously or we
- * wouldn't know which one to deliver the userfaults to.
- */
- ret = -EBUSY;
- if (cur->vm_userfaultfd_ctx.ctx &&
- cur->vm_userfaultfd_ctx.ctx != ctx)
- goto out_unlock;
- /*
- * Note vmas containing huge pages
- */
- if (is_vm_hugetlb_page(cur))
- basic_ioctls = true;
- found = true;
- }
- BUG_ON(!found);
- if (vma->vm_start < start)
- prev = vma;
- ret = 0;
- do {
- cond_resched();
- BUG_ON(!vma_can_userfault(vma, vm_flags));
- BUG_ON(vma->vm_userfaultfd_ctx.ctx &&
- vma->vm_userfaultfd_ctx.ctx != ctx);
- WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
- /*
- * Nothing to do: this vma is already registered into this
- * userfaultfd and with the right tracking mode too.
- */
- if (vma->vm_userfaultfd_ctx.ctx == ctx &&
- (vma->vm_flags & vm_flags) == vm_flags)
- goto skip;
- if (vma->vm_start > start)
- start = vma->vm_start;
- vma_end = min(end, vma->vm_end);
- new_flags = (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags;
- prev = vma_merge(mm, prev, start, vma_end, new_flags,
- vma->anon_vma, vma->vm_file, vma->vm_pgoff,
- vma_policy(vma),
- ((struct vm_userfaultfd_ctx){ ctx }),
- vma_get_anon_name(vma));
- if (prev) {
- vma = prev;
- goto next;
- }
- if (vma->vm_start < start) {
- ret = split_vma(mm, vma, start, 1);
- if (ret)
- break;
- }
- if (vma->vm_end > end) {
- ret = split_vma(mm, vma, end, 0);
- if (ret)
- break;
- }
- next:
- /*
- * In the vma_merge() successful mprotect-like case 8:
- * the next vma was merged into the current one and
- * the current one has not been updated yet.
- */
- vm_write_begin(vma);
- WRITE_ONCE(vma->vm_flags, new_flags);
- vma->vm_userfaultfd_ctx.ctx = ctx;
- vm_write_end(vma);
- if (is_vm_hugetlb_page(vma) && uffd_disable_huge_pmd_share(vma))
- hugetlb_unshare_all_pmds(vma);
- skip:
- prev = vma;
- start = vma->vm_end;
- vma = vma->vm_next;
- } while (vma && vma->vm_start < end);
- out_unlock:
- mmap_write_unlock(mm);
- mmput(mm);
- if (!ret) {
- __u64 ioctls_out;
- ioctls_out = basic_ioctls ? UFFD_API_RANGE_IOCTLS_BASIC :
- UFFD_API_RANGE_IOCTLS;
- /*
- * Declare the WP ioctl only if the WP mode is
- * specified and all checks passed with the range
- */
- if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_WP))
- ioctls_out &= ~((__u64)1 << _UFFDIO_WRITEPROTECT);
- /* CONTINUE ioctl is only supported for MINOR ranges. */
- if (!(uffdio_register.mode & UFFDIO_REGISTER_MODE_MINOR))
- ioctls_out &= ~((__u64)1 << _UFFDIO_CONTINUE);
- /*
- * Now that we scanned all vmas we can already tell
- * userland which ioctls methods are guaranteed to
- * succeed on this range.
- */
- if (put_user(ioctls_out, &user_uffdio_register->ioctls))
- ret = -EFAULT;
- }
- out:
- return ret;
- }
- static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
- unsigned long arg)
- {
- struct mm_struct *mm = ctx->mm;
- struct vm_area_struct *vma, *prev, *cur;
- int ret;
- struct uffdio_range uffdio_unregister;
- unsigned long new_flags;
- bool found;
- unsigned long start, end, vma_end;
- const void __user *buf = (void __user *)arg;
- ret = -EFAULT;
- if (copy_from_user(&uffdio_unregister, buf, sizeof(uffdio_unregister)))
- goto out;
- ret = validate_range(mm, uffdio_unregister.start,
- uffdio_unregister.len);
- if (ret)
- goto out;
- start = uffdio_unregister.start;
- end = start + uffdio_unregister.len;
- ret = -ENOMEM;
- if (!mmget_not_zero(mm))
- goto out;
- mmap_write_lock(mm);
- vma = find_vma_prev(mm, start, &prev);
- if (!vma)
- goto out_unlock;
- /* check that there's at least one vma in the range */
- ret = -EINVAL;
- if (vma->vm_start >= end)
- goto out_unlock;
- /*
- * If the first vma contains huge pages, make sure start address
- * is aligned to huge page size.
- */
- if (is_vm_hugetlb_page(vma)) {
- unsigned long vma_hpagesize = vma_kernel_pagesize(vma);
- if (start & (vma_hpagesize - 1))
- goto out_unlock;
- }
- /*
- * Search for not compatible vmas.
- */
- found = false;
- ret = -EINVAL;
- for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
- cond_resched();
- BUG_ON(!!cur->vm_userfaultfd_ctx.ctx ^
- !!(cur->vm_flags & __VM_UFFD_FLAGS));
- /*
- * Check not compatible vmas, not strictly required
- * here as not compatible vmas cannot have an
- * userfaultfd_ctx registered on them, but this
- * provides for more strict behavior to notice
- * unregistration errors.
- */
- if (!vma_can_userfault(cur, cur->vm_flags))
- goto out_unlock;
- found = true;
- }
- BUG_ON(!found);
- if (vma->vm_start < start)
- prev = vma;
- ret = 0;
- do {
- cond_resched();
- BUG_ON(!vma_can_userfault(vma, vma->vm_flags));
- /*
- * Nothing to do: this vma is already registered into this
- * userfaultfd and with the right tracking mode too.
- */
- if (!vma->vm_userfaultfd_ctx.ctx)
- goto skip;
- WARN_ON(!(vma->vm_flags & VM_MAYWRITE));
- if (vma->vm_start > start)
- start = vma->vm_start;
- vma_end = min(end, vma->vm_end);
- if (userfaultfd_missing(vma)) {
- /*
- * Wake any concurrent pending userfault while
- * we unregister, so they will not hang
- * permanently and it avoids userland to call
- * UFFDIO_WAKE explicitly.
- */
- struct userfaultfd_wake_range range;
- range.start = start;
- range.len = vma_end - start;
- wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range);
- }
- new_flags = vma->vm_flags & ~__VM_UFFD_FLAGS;
- prev = vma_merge(mm, prev, start, vma_end, new_flags,
- vma->anon_vma, vma->vm_file, vma->vm_pgoff,
- vma_policy(vma),
- NULL_VM_UFFD_CTX,
- vma_get_anon_name(vma));
- if (prev) {
- vma = prev;
- goto next;
- }
- if (vma->vm_start < start) {
- ret = split_vma(mm, vma, start, 1);
- if (ret)
- break;
- }
- if (vma->vm_end > end) {
- ret = split_vma(mm, vma, end, 0);
- if (ret)
- break;
- }
- next:
- /*
- * In the vma_merge() successful mprotect-like case 8:
- * the next vma was merged into the current one and
- * the current one has not been updated yet.
- */
- vm_write_begin(vma);
- WRITE_ONCE(vma->vm_flags, new_flags);
- vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
- vm_write_end(vma);
- skip:
- prev = vma;
- start = vma->vm_end;
- vma = vma->vm_next;
- } while (vma && vma->vm_start < end);
- out_unlock:
- mmap_write_unlock(mm);
- mmput(mm);
- out:
- return ret;
- }
- /*
- * userfaultfd_wake may be used in combination with the
- * UFFDIO_*_MODE_DONTWAKE to wakeup userfaults in batches.
- */
- static int userfaultfd_wake(struct userfaultfd_ctx *ctx,
- unsigned long arg)
- {
- int ret;
- struct uffdio_range uffdio_wake;
- struct userfaultfd_wake_range range;
- const void __user *buf = (void __user *)arg;
- ret = -EFAULT;
- if (copy_from_user(&uffdio_wake, buf, sizeof(uffdio_wake)))
- goto out;
- ret = validate_range(ctx->mm, uffdio_wake.start, uffdio_wake.len);
- if (ret)
- goto out;
- range.start = uffdio_wake.start;
- range.len = uffdio_wake.len;
- /*
- * len == 0 means wake all and we don't want to wake all here,
- * so check it again to be sure.
- */
- VM_BUG_ON(!range.len);
- wake_userfault(ctx, &range);
- ret = 0;
- out:
- return ret;
- }
- static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
- unsigned long arg)
- {
- __s64 ret;
- struct uffdio_copy uffdio_copy;
- struct uffdio_copy __user *user_uffdio_copy;
- struct userfaultfd_wake_range range;
- user_uffdio_copy = (struct uffdio_copy __user *) arg;
- ret = -EAGAIN;
- if (READ_ONCE(ctx->mmap_changing))
- goto out;
- ret = -EFAULT;
- if (copy_from_user(&uffdio_copy, user_uffdio_copy,
- /* don't copy "copy" last field */
- sizeof(uffdio_copy)-sizeof(__s64)))
- goto out;
- ret = validate_range(ctx->mm, uffdio_copy.dst, uffdio_copy.len);
- if (ret)
- goto out;
- /*
- * double check for wraparound just in case. copy_from_user()
- * will later check uffdio_copy.src + uffdio_copy.len to fit
- * in the userland range.
- */
- ret = -EINVAL;
- if (uffdio_copy.src + uffdio_copy.len <= uffdio_copy.src)
- goto out;
- if (uffdio_copy.mode & ~(UFFDIO_COPY_MODE_DONTWAKE|UFFDIO_COPY_MODE_WP))
- goto out;
- if (mmget_not_zero(ctx->mm)) {
- ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
- uffdio_copy.len, &ctx->mmap_changing,
- uffdio_copy.mode);
- mmput(ctx->mm);
- } else {
- return -ESRCH;
- }
- if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
- return -EFAULT;
- if (ret < 0)
- goto out;
- BUG_ON(!ret);
- /* len == 0 would wake all */
- range.len = ret;
- if (!(uffdio_copy.mode & UFFDIO_COPY_MODE_DONTWAKE)) {
- range.start = uffdio_copy.dst;
- wake_userfault(ctx, &range);
- }
- ret = range.len == uffdio_copy.len ? 0 : -EAGAIN;
- out:
- return ret;
- }
- static int userfaultfd_zeropage(struct userfaultfd_ctx *ctx,
- unsigned long arg)
- {
- __s64 ret;
- struct uffdio_zeropage uffdio_zeropage;
- struct uffdio_zeropage __user *user_uffdio_zeropage;
- struct userfaultfd_wake_range range;
- user_uffdio_zeropage = (struct uffdio_zeropage __user *) arg;
- ret = -EAGAIN;
- if (READ_ONCE(ctx->mmap_changing))
- goto out;
- ret = -EFAULT;
- if (copy_from_user(&uffdio_zeropage, user_uffdio_zeropage,
- /* don't copy "zeropage" last field */
- sizeof(uffdio_zeropage)-sizeof(__s64)))
- goto out;
- ret = validate_range(ctx->mm, uffdio_zeropage.range.start,
- uffdio_zeropage.range.len);
- if (ret)
- goto out;
- ret = -EINVAL;
- if (uffdio_zeropage.mode & ~UFFDIO_ZEROPAGE_MODE_DONTWAKE)
- goto out;
- if (mmget_not_zero(ctx->mm)) {
- ret = mfill_zeropage(ctx->mm, uffdio_zeropage.range.start,
- uffdio_zeropage.range.len,
- &ctx->mmap_changing);
- mmput(ctx->mm);
- } else {
- return -ESRCH;
- }
- if (unlikely(put_user(ret, &user_uffdio_zeropage->zeropage)))
- return -EFAULT;
- if (ret < 0)
- goto out;
- /* len == 0 would wake all */
- BUG_ON(!ret);
- range.len = ret;
- if (!(uffdio_zeropage.mode & UFFDIO_ZEROPAGE_MODE_DONTWAKE)) {
- range.start = uffdio_zeropage.range.start;
- wake_userfault(ctx, &range);
- }
- ret = range.len == uffdio_zeropage.range.len ? 0 : -EAGAIN;
- out:
- return ret;
- }
- static int userfaultfd_writeprotect(struct userfaultfd_ctx *ctx,
- unsigned long arg)
- {
- int ret;
- struct uffdio_writeprotect uffdio_wp;
- struct uffdio_writeprotect __user *user_uffdio_wp;
- struct userfaultfd_wake_range range;
- bool mode_wp, mode_dontwake;
- if (READ_ONCE(ctx->mmap_changing))
- return -EAGAIN;
- user_uffdio_wp = (struct uffdio_writeprotect __user *) arg;
- if (copy_from_user(&uffdio_wp, user_uffdio_wp,
- sizeof(struct uffdio_writeprotect)))
- return -EFAULT;
- ret = validate_range(ctx->mm, uffdio_wp.range.start,
- uffdio_wp.range.len);
- if (ret)
- return ret;
- if (uffdio_wp.mode & ~(UFFDIO_WRITEPROTECT_MODE_DONTWAKE |
- UFFDIO_WRITEPROTECT_MODE_WP))
- return -EINVAL;
- mode_wp = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_WP;
- mode_dontwake = uffdio_wp.mode & UFFDIO_WRITEPROTECT_MODE_DONTWAKE;
- if (mode_wp && mode_dontwake)
- return -EINVAL;
- if (mmget_not_zero(ctx->mm)) {
- ret = mwriteprotect_range(ctx->mm, uffdio_wp.range.start,
- uffdio_wp.range.len, mode_wp,
- &ctx->mmap_changing);
- mmput(ctx->mm);
- } else {
- return -ESRCH;
- }
- if (ret)
- return ret;
- if (!mode_wp && !mode_dontwake) {
- range.start = uffdio_wp.range.start;
- range.len = uffdio_wp.range.len;
- wake_userfault(ctx, &range);
- }
- return ret;
- }
- static int userfaultfd_continue(struct userfaultfd_ctx *ctx, unsigned long arg)
- {
- __s64 ret;
- struct uffdio_continue uffdio_continue;
- struct uffdio_continue __user *user_uffdio_continue;
- struct userfaultfd_wake_range range;
- user_uffdio_continue = (struct uffdio_continue __user *)arg;
- ret = -EAGAIN;
- if (READ_ONCE(ctx->mmap_changing))
- goto out;
- ret = -EFAULT;
- if (copy_from_user(&uffdio_continue, user_uffdio_continue,
- /* don't copy the output fields */
- sizeof(uffdio_continue) - (sizeof(__s64))))
- goto out;
- ret = validate_range(ctx->mm, uffdio_continue.range.start,
- uffdio_continue.range.len);
- if (ret)
- goto out;
- ret = -EINVAL;
- /* double check for wraparound just in case. */
- if (uffdio_continue.range.start + uffdio_continue.range.len <=
- uffdio_continue.range.start) {
- goto out;
- }
- if (uffdio_continue.mode & ~UFFDIO_CONTINUE_MODE_DONTWAKE)
- goto out;
- if (mmget_not_zero(ctx->mm)) {
- ret = mcopy_continue(ctx->mm, uffdio_continue.range.start,
- uffdio_continue.range.len,
- &ctx->mmap_changing);
- mmput(ctx->mm);
- } else {
- return -ESRCH;
- }
- if (unlikely(put_user(ret, &user_uffdio_continue->mapped)))
- return -EFAULT;
- if (ret < 0)
- goto out;
- /* len == 0 would wake all */
- BUG_ON(!ret);
- range.len = ret;
- if (!(uffdio_continue.mode & UFFDIO_CONTINUE_MODE_DONTWAKE)) {
- range.start = uffdio_continue.range.start;
- wake_userfault(ctx, &range);
- }
- ret = range.len == uffdio_continue.range.len ? 0 : -EAGAIN;
- out:
- return ret;
- }
- static inline unsigned int uffd_ctx_features(__u64 user_features)
- {
- /*
- * For the current set of features the bits just coincide. Set
- * UFFD_FEATURE_INITIALIZED to mark the features as enabled.
- */
- return (unsigned int)user_features | UFFD_FEATURE_INITIALIZED;
- }
- /*
- * userland asks for a certain API version and we return which bits
- * and ioctl commands are implemented in this kernel for such API
- * version or -EINVAL if unknown.
- */
- static int userfaultfd_api(struct userfaultfd_ctx *ctx,
- unsigned long arg)
- {
- struct uffdio_api uffdio_api;
- void __user *buf = (void __user *)arg;
- unsigned int ctx_features;
- int ret;
- __u64 features;
- ret = -EFAULT;
- if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api)))
- goto out;
- features = uffdio_api.features;
- ret = -EINVAL;
- if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES))
- goto err_out;
- ret = -EPERM;
- if ((features & UFFD_FEATURE_EVENT_FORK) && !capable(CAP_SYS_PTRACE))
- goto err_out;
- /* report all available features and ioctls to userland */
- uffdio_api.features = UFFD_API_FEATURES;
- #ifndef CONFIG_HAVE_ARCH_USERFAULTFD_MINOR
- uffdio_api.features &=
- ~(UFFD_FEATURE_MINOR_HUGETLBFS | UFFD_FEATURE_MINOR_SHMEM);
- #endif
- uffdio_api.ioctls = UFFD_API_IOCTLS;
- ret = -EFAULT;
- if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
- goto out;
- /* only enable the requested features for this uffd context */
- ctx_features = uffd_ctx_features(features);
- ret = -EINVAL;
- if (cmpxchg(&ctx->features, 0, ctx_features) != 0)
- goto err_out;
- ret = 0;
- out:
- return ret;
- err_out:
- memset(&uffdio_api, 0, sizeof(uffdio_api));
- if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
- ret = -EFAULT;
- goto out;
- }
- static long userfaultfd_ioctl(struct file *file, unsigned cmd,
- unsigned long arg)
- {
- int ret = -EINVAL;
- struct userfaultfd_ctx *ctx = file->private_data;
- if (cmd != UFFDIO_API && !userfaultfd_is_initialized(ctx))
- return -EINVAL;
- switch(cmd) {
- case UFFDIO_API:
- ret = userfaultfd_api(ctx, arg);
- break;
- case UFFDIO_REGISTER:
- ret = userfaultfd_register(ctx, arg);
- break;
- case UFFDIO_UNREGISTER:
- ret = userfaultfd_unregister(ctx, arg);
- break;
- case UFFDIO_WAKE:
- ret = userfaultfd_wake(ctx, arg);
- break;
- case UFFDIO_COPY:
- ret = userfaultfd_copy(ctx, arg);
- break;
- case UFFDIO_ZEROPAGE:
- ret = userfaultfd_zeropage(ctx, arg);
- break;
- case UFFDIO_WRITEPROTECT:
- ret = userfaultfd_writeprotect(ctx, arg);
- break;
- case UFFDIO_CONTINUE:
- ret = userfaultfd_continue(ctx, arg);
- break;
- }
- return ret;
- }
- #ifdef CONFIG_PROC_FS
- static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f)
- {
- struct userfaultfd_ctx *ctx = f->private_data;
- wait_queue_entry_t *wq;
- unsigned long pending = 0, total = 0;
- spin_lock_irq(&ctx->fault_pending_wqh.lock);
- list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) {
- pending++;
- total++;
- }
- list_for_each_entry(wq, &ctx->fault_wqh.head, entry) {
- total++;
- }
- spin_unlock_irq(&ctx->fault_pending_wqh.lock);
- /*
- * If more protocols will be added, there will be all shown
- * separated by a space. Like this:
- * protocols: aa:... bb:...
- */
- seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n",
- pending, total, UFFD_API, ctx->features,
- UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS);
- }
- #endif
- static const struct file_operations userfaultfd_fops = {
- #ifdef CONFIG_PROC_FS
- .show_fdinfo = userfaultfd_show_fdinfo,
- #endif
- .release = userfaultfd_release,
- .poll = userfaultfd_poll,
- .read = userfaultfd_read,
- .unlocked_ioctl = userfaultfd_ioctl,
- .compat_ioctl = compat_ptr_ioctl,
- .llseek = noop_llseek,
- };
- static void init_once_userfaultfd_ctx(void *mem)
- {
- struct userfaultfd_ctx *ctx = (struct userfaultfd_ctx *) mem;
- init_waitqueue_head(&ctx->fault_pending_wqh);
- init_waitqueue_head(&ctx->fault_wqh);
- init_waitqueue_head(&ctx->event_wqh);
- init_waitqueue_head(&ctx->fd_wqh);
- seqcount_spinlock_init(&ctx->refile_seq, &ctx->fault_pending_wqh.lock);
- }
- SYSCALL_DEFINE1(userfaultfd, int, flags)
- {
- struct userfaultfd_ctx *ctx;
- int fd;
- if (!sysctl_unprivileged_userfaultfd &&
- (flags & UFFD_USER_MODE_ONLY) == 0 &&
- !capable(CAP_SYS_PTRACE)) {
- printk_once(KERN_WARNING "uffd: Set unprivileged_userfaultfd "
- "sysctl knob to 1 if kernel faults must be handled "
- "without obtaining CAP_SYS_PTRACE capability\n");
- return -EPERM;
- }
- BUG_ON(!current->mm);
- /* Check the UFFD_* constants for consistency. */
- BUILD_BUG_ON(UFFD_USER_MODE_ONLY & UFFD_SHARED_FCNTL_FLAGS);
- BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC);
- BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK);
- if (flags & ~(UFFD_SHARED_FCNTL_FLAGS | UFFD_USER_MODE_ONLY))
- return -EINVAL;
- ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
- if (!ctx)
- return -ENOMEM;
- refcount_set(&ctx->refcount, 1);
- ctx->flags = flags;
- ctx->features = 0;
- ctx->released = false;
- ctx->mmap_changing = false;
- ctx->mm = current->mm;
- /* prevent the mm struct to be freed */
- mmgrab(ctx->mm);
- fd = anon_inode_getfd_secure("[userfaultfd]", &userfaultfd_fops, ctx,
- O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS), NULL);
- if (fd < 0) {
- mmdrop(ctx->mm);
- kmem_cache_free(userfaultfd_ctx_cachep, ctx);
- }
- return fd;
- }
- static int __init userfaultfd_init(void)
- {
- userfaultfd_ctx_cachep = kmem_cache_create("userfaultfd_ctx_cache",
- sizeof(struct userfaultfd_ctx),
- 0,
- SLAB_HWCACHE_ALIGN|SLAB_PANIC,
- init_once_userfaultfd_ctx);
- return 0;
- }
- __initcall(userfaultfd_init);
|