/* * fs/userfaultfd.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * Copyright (C) 2008-2009 Red Hat, Inc. * Copyright (C) 2015 Red Hat, Inc. * * This work is licensed under the terms of the GNU GPL, version 2. See * the COPYING file in the top-level directory. * * 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/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> static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; enum userfaultfd_state { UFFD_STATE_WAIT_API, UFFD_STATE_RUNNING,}; /* * Start with fault_pending_wqh and fault_wqh so they're more likely * to be in the same cacheline. */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 */ struct seqcount refile_seq; /* pseudo fd refcounting */ atomic_t refcount; /* userfaultfd syscall flags */ unsigned int flags; /* features requested from the userspace */ unsigned int features; /* state machine */ enum userfaultfd_state state; /* released */ bool released; /* 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;}; 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 implicit smp_mb__before_spinlock in try_to_wake_up() * renders uwq->waken visible to other CPUs before the task is * waken. */ 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__before_spinlock, and the * wq->private is read before calling the extern * function "wake_up_state" (which in turns calls * try_to_wake_up). While the spin_lock;spin_unlock; * wouldn't be enough, the smp_mb__before_spinlock is * enough to avoid an explicit smp_mb() here. */ 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){ if (!atomic_inc_not_zero(&ctx->refcount)) BUG();} /** * 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 (atomic_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){ struct uffd_msg msg; msg_init(&msg); msg.event = UFFD_EVENT_PAGEFAULT; msg.arg.pagefault.address = address; if (flags & FAULT_FLAG_WRITE) /* * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WRITE * was not set in a UFFD_EVENT_PAGEFAULT, it means it * was a read fault, otherwise if set it means it's * a write fault. */ msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE; if (reason & VM_UFFD_WP) /* * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WP was * not set in a UFFD_EVENT_PAGEFAULT, it means it was * a missing fault, otherwise if set it means it's a * write protect fault. */ msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP; 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 *pte; bool ret = true; VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem)); pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); if (!pte) goto out; ret = false; /* * 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;}#elsestatic 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; VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem)); 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_present(_pmd)) goto out; ret = false; if (pmd_trans_huge(_pmd)) 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; pte_unmap(pte); out: return ret;} /* * 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_sem 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_sem must be released before * returning it. */int 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; int ret; bool must_wait, return_to_userland; long blocking_state; ret = VM_FAULT_SIGBUS; /* * 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_sem and it ends up here. */ if (current->flags & (PF_EXITING|PF_DUMPCORE)) goto out; /* * Coredumping runs without mmap_sem so we can only check that * the mmap_sem is held, if PF_DUMPCORE was not set. */ WARN_ON_ONCE(!rwsem_is_locked(&mm->mmap_sem)); ctx = vmf->vma->vm_userfaultfd_ctx.ctx; if (!ctx) goto out; BUG_ON(ctx->mm != mm); VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP)); VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP)); /* * 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_sem. */ if (unlikely(ACCESS_ONCE(ctx->released))) 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_sem */ 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); uwq.ctx = ctx; uwq.waken = false; return_to_userland = (vmf->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) == (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE); blocking_state = return_to_userland ? TASK_INTERRUPTIBLE : TASK_KILLABLE; spin_lock(&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(&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); up_read(&mm->mmap_sem); if (likely(must_wait && !ACCESS_ONCE(ctx->released) && (return_to_userland ? !signal_pending(current) : !fatal_signal_pending(current)))) { wake_up_poll(&ctx->fd_wqh, POLLIN); schedule(); ret |= VM_FAULT_MAJOR; /* * False wakeups can orginate even from rwsem before * up_read() however userfaults will wait either for a * targeted wakeup on the specific uwq waitqueue from * wake_userfault() or for signals or for uffd * release. */ while (!READ_ONCE(uwq.waken)) { /* * This needs the full smp_store_mb() * guarantee as the state write must be * visible to other CPUs before reading * uwq.waken from other CPUs. */ set_current_state(blocking_state); if (READ_ONCE(uwq.waken) || READ_ONCE(ctx->released) || (return_to_userland ? signal_pending(current) : fatal_signal_pending(current))) break; schedule(); } } __set_current_state(TASK_RUNNING); if (return_to_userland) { if (signal_pending(current) && !fatal_signal_pending(current)) { /* * If we got a SIGSTOP or SIGCONT and this is * a normal userland page fault, just let * userland return so the signal will be * handled and gdb debugging works. The page * fault code immediately after we return from * this function is going to release theLines 1–500 of 1890. Load more
/* * fs/userfaultfd.c * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * Copyright (C) 2008-2009 Red Hat, Inc. * Copyright (C) 2015 Red Hat, Inc. * * This work is licensed under the terms of the GNU GPL, version 2. See * the COPYING file in the top-level directory. * * 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/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> static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; enum userfaultfd_state { UFFD_STATE_WAIT_API, UFFD_STATE_RUNNING, }; /* * Start with fault_pending_wqh and fault_wqh so they're more likely * to be in the same cacheline. */ 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 */ struct seqcount refile_seq; /* pseudo fd refcounting */ atomic_t refcount; /* userfaultfd syscall flags */ unsigned int flags; /* features requested from the userspace */ unsigned int features; /* state machine */ enum userfaultfd_state state; /* released */ bool released; /* 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; }; 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 implicit smp_mb__before_spinlock in try_to_wake_up() * renders uwq->waken visible to other CPUs before the task is * waken. */ 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__before_spinlock, and the * wq->private is read before calling the extern * function "wake_up_state" (which in turns calls * try_to_wake_up). While the spin_lock;spin_unlock; * wouldn't be enough, the smp_mb__before_spinlock is * enough to avoid an explicit smp_mb() here. */ 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) { if (!atomic_inc_not_zero(&ctx->refcount)) BUG(); } /** * 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 (atomic_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) { struct uffd_msg msg; msg_init(&msg); msg.event = UFFD_EVENT_PAGEFAULT; msg.arg.pagefault.address = address; if (flags & FAULT_FLAG_WRITE) /* * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WRITE * was not set in a UFFD_EVENT_PAGEFAULT, it means it * was a read fault, otherwise if set it means it's * a write fault. */ msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WRITE; if (reason & VM_UFFD_WP) /* * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WP was * not set in a UFFD_EVENT_PAGEFAULT, it means it was * a missing fault, otherwise if set it means it's a * write protect fault. */ msg.arg.pagefault.flags |= UFFD_PAGEFAULT_FLAG_WP; 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 *pte; bool ret = true; VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem)); pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma)); if (!pte) goto out; ret = false; /* * 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; VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem)); 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_present(_pmd)) goto out; ret = false; if (pmd_trans_huge(_pmd)) 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; pte_unmap(pte); out: return ret; } /* * 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_sem 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_sem must be released before * returning it. */ int 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; int ret; bool must_wait, return_to_userland; long blocking_state; ret = VM_FAULT_SIGBUS; /* * 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_sem and it ends up here. */ if (current->flags & (PF_EXITING|PF_DUMPCORE)) goto out; /* * Coredumping runs without mmap_sem so we can only check that * the mmap_sem is held, if PF_DUMPCORE was not set. */ WARN_ON_ONCE(!rwsem_is_locked(&mm->mmap_sem)); ctx = vmf->vma->vm_userfaultfd_ctx.ctx; if (!ctx) goto out; BUG_ON(ctx->mm != mm); VM_BUG_ON(reason & ~(VM_UFFD_MISSING|VM_UFFD_WP)); VM_BUG_ON(!(reason & VM_UFFD_MISSING) ^ !!(reason & VM_UFFD_WP)); /* * 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_sem. */ if (unlikely(ACCESS_ONCE(ctx->released))) 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_sem */ 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); uwq.ctx = ctx; uwq.waken = false; return_to_userland = (vmf->flags & (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE)) == (FAULT_FLAG_USER|FAULT_FLAG_KILLABLE); blocking_state = return_to_userland ? TASK_INTERRUPTIBLE : TASK_KILLABLE; spin_lock(&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(&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); up_read(&mm->mmap_sem); if (likely(must_wait && !ACCESS_ONCE(ctx->released) && (return_to_userland ? !signal_pending(current) : !fatal_signal_pending(current)))) { wake_up_poll(&ctx->fd_wqh, POLLIN); schedule(); ret |= VM_FAULT_MAJOR; /* * False wakeups can orginate even from rwsem before * up_read() however userfaults will wait either for a * targeted wakeup on the specific uwq waitqueue from * wake_userfault() or for signals or for uffd * release. */ while (!READ_ONCE(uwq.waken)) { /* * This needs the full smp_store_mb() * guarantee as the state write must be * visible to other CPUs before reading * uwq.waken from other CPUs. */ set_current_state(blocking_state); if (READ_ONCE(uwq.waken) || READ_ONCE(ctx->released) || (return_to_userland ? signal_pending(current) : fatal_signal_pending(current))) break; schedule(); } } __set_current_state(TASK_RUNNING); if (return_to_userland) { if (signal_pending(current) && !fatal_signal_pending(current)) { /* * If we got a SIGSTOP or SIGCONT and this is * a normal userland page fault, just let * userland return so the signal will be * handled and gdb debugging works. The page * fault code immediately after we return from * this function is going to release the