/* * Kernel-based Virtual Machine driver for Linux * * This module enables machines with Intel VT-x extensions to run virtual * machines without emulation or binary translation. * * Copyright (C) 2006 Qumranet, Inc. * Copyright 2010 Red Hat, Inc. and/or its affilates. * * Authors: * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> * * This work is licensed under the terms of the GNU GPL, version 2. See * the COPYING file in the top-level directory. * */ #include "iodev.h" #include <linux/kvm_host.h> #include <linux/kvm.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/percpu.h> #include <linux/mm.h> #include <linux/miscdevice.h> #include <linux/vmalloc.h> #include <linux/reboot.h> #include <linux/debugfs.h> #include <linux/highmem.h> #include <linux/file.h> #include <linux/sysdev.h> #include <linux/cpu.h> #include <linux/sched.h> #include <linux/cpumask.h> #include <linux/smp.h> #include <linux/anon_inodes.h> #include <linux/profile.h> #include <linux/kvm_para.h> #include <linux/pagemap.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/compat.h> #include <linux/srcu.h> #include <linux/hugetlb.h> #include <linux/slab.h> #include <asm/processor.h> #include <asm/io.h> #include <asm/uaccess.h> #include <asm/pgtable.h> #include <asm-generic/bitops/le.h> #include "coalesced_mmio.h" #define CREATE_TRACE_POINTS #include <trace/events/kvm.h> MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); /* * Ordering of locks: * * kvm->lock --> kvm->slots_lock --> kvm->irq_lock */ DEFINE_SPINLOCK(kvm_lock); LIST_HEAD(vm_list); static cpumask_var_t cpus_hardware_enabled; static int kvm_usage_count = 0; static atomic_t hardware_enable_failed; struct kmem_cache *kvm_vcpu_cache; EXPORT_SYMBOL_GPL(kvm_vcpu_cache); static __read_mostly struct preempt_ops kvm_preempt_ops; struct dentry *kvm_debugfs_dir; static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); static int hardware_enable_all(void); static void hardware_disable_all(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); static bool kvm_rebooting; static bool largepages_enabled = true; struct page *hwpoison_page; pfn_t hwpoison_pfn; inline int kvm_is_mmio_pfn(pfn_t pfn) { if (pfn_valid(pfn)) { struct page *page = compound_head(pfn_to_page(pfn)); return PageReserved(page); } return true; } /* * Switches to specified vcpu, until a matching vcpu_put() */ void vcpu_load(struct kvm_vcpu *vcpu) { int cpu; mutex_lock(&vcpu->mutex); cpu = get_cpu(); preempt_notifier_register(&vcpu->preempt_notifier); kvm_arch_vcpu_load(vcpu, cpu); put_cpu(); } void vcpu_put(struct kvm_vcpu *vcpu) { preempt_disable(); kvm_arch_vcpu_put(vcpu); preempt_notifier_unregister(&vcpu->preempt_notifier); preempt_enable(); mutex_unlock(&vcpu->mutex); } static void ack_flush(void *_completed) { } static bool make_all_cpus_request(struct kvm *kvm, unsigned int req) { int i, cpu, me; cpumask_var_t cpus; bool called = true; struct kvm_vcpu *vcpu; zalloc_cpumask_var(&cpus, GFP_ATOMIC); raw_spin_lock(&kvm->requests_lock); me = smp_processor_id(); kvm_for_each_vcpu(i, vcpu, kvm) { if (kvm_make_check_request(req, vcpu)) continue; cpu = vcpu->cpu; if (cpus != NULL && cpu != -1 && cpu != me) cpumask_set_cpu(cpu, cpus); } if (unlikely(cpus == NULL)) smp_call_function_many(cpu_online_mask, ack_flush, NULL, 1); else if (!cpumask_empty(cpus)) smp_call_function_many(cpus, ack_flush, NULL, 1); else called = false; raw_spin_unlock(&kvm->requests_lock); free_cpumask_var(cpus); return called; } void kvm_flush_remote_tlbs(struct kvm *kvm) { if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH)) ++kvm->stat.remote_tlb_flush; } void kvm_reload_remote_mmus(struct kvm *kvm) { make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD); } int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) { struct page *page; int r; mutex_init(&vcpu->mutex); vcpu->cpu = -1; vcpu->kvm = kvm; vcpu->vcpu_id = id; init_waitqueue_head(&vcpu->wq); page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!page) { r = -ENOMEM; goto fail; } vcpu->run = page_address(page); r = kvm_arch_vcpu_init(vcpu); if (r < 0) goto fail_free_run; return 0; fail_free_run: free_page((unsigned long)vcpu->run); fail: return r; } EXPORT_SYMBOL_GPL(kvm_vcpu_init); void kvm_vcpu_uninit(struct kvm_vcpu *vcpu) { kvm_arch_vcpu_uninit(vcpu); free_page((unsigned long)vcpu->run); } EXPORT_SYMBOL_GPL(kvm_vcpu_uninit); #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn) { return container_of(mn, struct kvm, mmu_notifier); } static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long address) { struct kvm *kvm = mmu_notifier_to_kvm(mn); int need_tlb_flush, idx; /* * When ->invalidate_page runs, the linux pte has been zapped * already but the page is still allocated until * ->invalidate_page returns. So if we increase the sequence * here the kvm page fault will notice if the spte can't be * established because the page is going to be freed. If * instead the kvm page fault establishes the spte before * ->invalidate_page runs, kvm_unmap_hva will release it * before returning. * * The sequence increase only need to be seen at spin_unlock * time, and not at spin_lock time. * * Increasing the sequence after the spin_unlock would be * unsafe because the kvm page fault could then establish the * pte after kvm_unmap_hva returned, without noticing the page * is going to be freed. */ idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); kvm->mmu_notifier_seq++; need_tlb_flush = kvm_unmap_hva(kvm, address); spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush) kvm_flush_remote_tlbs(kvm); } static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long address, pte_t pte) { struct kvm *kvm = mmu_notifier_to_kvm(mn); int idx; idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); kvm->mmu_notifier_seq++; kvm_set_spte_hva(kvm, address, pte); spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); } static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end) { struct kvm *kvm = mmu_notifier_to_kvm(mn); int need_tlb_flush = 0, idx; idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); /* * The count increase must become visible at unlock time as no * spte can be established without taking the mmu_lock and * count is also read inside the mmu_lock critical section. */ kvm->mmu_notifier_count++; for (; start < end; start += PAGE_SIZE) need_tlb_flush |= kvm_unmap_hva(kvm, start); spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush) kvm_flush_remote_tlbs(kvm); } static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end) { struct kvm *kvm = mmu_notifier_to_kvm(mn); spin_lock(&kvm->mmu_lock); /* * This sequence increase will notify the kvm page fault that * the page that is going to be mapped in the spte could have * been freed. */ kvm->mmu_notifier_seq++; /* * The above sequence increase must be visible before the * below count decrease but both values are read by the kvm * page fault under mmu_lock spinlock so we don't need to add * a smb_wmb() here in between the two. */ kvm->mmu_notifier_count--; spin_unlock(&kvm->mmu_lock); BUG_ON(kvm->mmu_notifier_count < 0); } static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long address) { struct kvm *kvm = mmu_notifier_to_kvm(mn); int young, idx; idx = srcu_read_lock(&kvm->srcu); spin_lock(&kvm->mmu_lock); young = kvm_age_hva(kvm, address); spin_unlock(&kvm->mmu_lock); srcu_read_unlock(&kvm->srcu, idx); if (young) kvm_flush_remote_tlbs(kvm); return young; } static void kvm_mmu_notifier_release(struct mmu_notifier *mn, struct mm_struct *mm) { struct kvm *kvm = mmu_notifier_to_kvm(mn); int idx; idx = srcu_read_lock(&kvm->srcu); kvm_arch_flush_shadow(kvm); srcu_read_unlock(&kvm->srcu, idx); } static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { .invalidate_page = kvm_mmu_notifier_invalidate_page, .invalidate_range_start = kvm_mmu_notifier_invalidate_range_start, .invalidate_range_end = kvm_mmu_notifier_invalidate_range_end, .clear_flush_young = kvm_mmu_notifier_clear_flush_young, .change_pte = kvm_mmu_notifier_change_pte, .release = kvm_mmu_notifier_release, }; static int kvm_init_mmu_notifier(struct kvm *kvm) { kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops; return mmu_notifier_register(&kvm->mmu_notifier, current->mm); } #else /* !(CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER) */ static int kvm_init_mmu_notifier(struct kvm *kvm) { return 0; } #endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */ static struct kvm *kvm_create_vm(void) { int r = 0, i; struct kvm *kvm = kvm_arch_create_vm(); if (IS_ERR(kvm)) goto out; r = hardware_enable_all(); if (r) goto out_err_nodisable; #ifdef CONFIG_HAVE_KVM_IRQCHIP INIT_HLIST_HEAD(&kvm->mask_notifier_list); INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); #endif r = -ENOMEM; kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); if (!kvm->memslots) goto out_err; if (init_srcu_struct(&kvm->srcu)) goto out_err; for (i = 0; i < KVM_NR_BUSES; i++) { kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL); if (!kvm->buses[i]) { cleanup_srcu_struct(&kvm->srcu); goto out_err; } } r = kvm_init_mmu_notifier(kvm); if (r) { cleanup_srcu_struct(&kvm->srcu); goto out_err; } kvm->mm = current->mm; atomic_inc(&kvm->mm->mm_count); spin_lock_init(&kvm->mmu_lock); raw_spin_lock_init(&kvm->requests_lock); kvm_eventfd_init(kvm); mutex_init(&kvm->lock); mutex_init(&kvm->irq_lock); mutex_init(&kvm->slots_lock); atomic_set(&kvm->users_count, 1); spin_lock(&kvm_lock); list_add(&kvm->vm_list, &vm_list); spin_unlock(&kvm_lock); out: return kvm; out_err: hardware_disable_all(); out_err_nodisable: for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm->buses[i]); kfree(kvm->memslots); kfree(kvm); return ERR_PTR(r); } /* * Free any memory in @free but not in @dont. */ static void kvm_free_physmem_slot(struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { int i; if (!dont || free->rmap != dont->rmap) vfree(free->rmap); if (!dont || free->dirty_bitmap != dont->dirty_bitmap) vfree(free->dirty_bitmap); for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) { if (!dont || free->lpage_info[i] != dont->lpage_info[i]) { vfree(free->lpage_info[i]); free->lpage_info[i] = NULL; } } free->npages = 0; free->dirty_bitmap = NULL; free->rmap = NULL; } void kvm_free_physmem(struct kvm *kvm) { int i; struct kvm_memslots *slots = kvm->memslots; for (i = 0; i < slots->nmemslots; ++i) kvm_free_physmem_slot(&slots->memslots[i], NULL); kfree(kvm->memslots); } static void kvm_destroy_vm(struct kvm *kvm) { int i; struct mm_struct *mm = kvm->mm; kvm_arch_sync_events(kvm); spin_lock(&kvm_lock); list_del(&kvm->vm_list); spin_unlock(&kvm_lock); kvm_free_irq_routing(kvm); for (i = 0; i < KVM_NR_BUSES; i++) kvm_io_bus_destroy(kvm->buses[i]); kvm_coalesced_mmio_free(kvm); #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); #else kvm_arch_flush_shadow(kvm); #endif kvm_arch_destroy_vm(kvm); hardware_disable_all(); mmdrop(mm); } void kvm_get_kvm(struct kvm *kvm) { atomic_inc(&kvm->users_count); } EXPORT_SYMBOL_GPL(kvm_get_kvm); void kvm_put_kvm(struct kvm *kvm) { if (atomic_dec_and_test(&kvm->users_count)) kvm_destroy_vm(kvm); } EXPORT_SYMBOL_GPL(kvm_put_kvm); static int kvm_vm_release(struct inode *inode, struct file *filp) { struct kvm *kvm = filp->private_data; kvm_irqfd_release(kvm); kvm_put_kvm(kvm); return 0; } /* * Allocate some memory and give it an address in the guest physical address * space. * * Discontiguous memory is allowed, mostly for framebuffers. * * Must be called holding mmap_sem for write. */ int __kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, int user_alloc) { int r, flush_shadow = 0; gfn_t base_gfn; unsigned long npages; unsigned long i; struct kvm_memory_slot *memslot; struct kvm_memory_slot old, new; struct kvm_memslots *slots, *old_memslots; r = -EINVAL; /* General sanity checks */ if (mem->memory_size & (PAGE_SIZE - 1)) goto out; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) goto out; if (user_alloc && (mem->userspace_addr & (PAGE_SIZE - 1))) goto out; if (mem->slot >= KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS) goto out; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) goto out; memslot = &kvm->memslots->memslots[mem->slot]; base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; npages = mem->memory_size >> PAGE_SHIFT; r = -EINVAL; if (npages > KVM_MEM_MAX_NR_PAGES) goto out; if (!npages) mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES; new = old = *memslot; new.id = mem->slot; new.base_gfn = base_gfn; new.npages = npages; new.flags = mem->flags; /* Disallow changing a memory slot's size. */ r = -EINVAL; if (npages && old.npages && npages != old.npages) goto out_free; /* Check for overlaps */ r = -EEXIST; for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { struct kvm_memory_slot *s = &kvm->memslots->memslots[i]; if (s == memslot || !s->npages) continue; if (!((base_gfn + npages <= s->base_gfn) || (base_gfn >= s->base_gfn + s->npages))) goto out_free; } /* Free page dirty bitmap if unneeded */ if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES)) new.dirty_bitmap = NULL; r = -ENOMEM; /* Allocate if a slot is being created */ #ifndef CONFIG_S390 if (npages && !new.rmap) { new.rmap = vmalloc(npages * sizeof(*new.rmap)); if (!new.rmap) goto out_free; memset(new.rmap, 0, npages * sizeof(*new.rmap)); new.user_alloc = user_alloc; new.userspace_addr = mem->userspace_addr; } if (!npages) goto skip_lpage; for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) { unsigned long ugfn; unsigned long j; int lpages; int level = i + 2; /* Avoid unused variable warning if no large pages */ (void)level; if (new.lpage_info[i]) continue; lpages = 1 + ((base_gfn + npages - 1) >> KVM_HPAGE_GFN_SHIFT(level)); lpages -= base_gfn >> KVM_HPAGE_GFN_SHIFT(level); new.lpage_info[i] = vmalloc(lpages * sizeof(*new.lpage_info[i])); if (!new.lpage_info[i]) goto out_free; memset(new.lpage_info[i], 0, lpages * sizeof(*new.lpage_info[i])); if (base_gfn & (KVM_PAGES_PER_HPAGE(level) - 1)) new.lpage_info[i][0].write_count = 1; if ((base_gfn+npages) & (KVM_PAGES_PER_HPAGE(level) - 1)) new.lpage_info[i][lpages - 1].write_count = 1; ugfn = new.userspace_addr >> PAGE_SHIFT; /* * If the gfn and userspace address are not aligned wrt each * other, or if explicitly asked to, disable large page * support for this slot */ if ((base_gfn ^ ugfn) & (KVM_PAGES_PER_HPAGE(level) - 1) || !largepages_enabled) for (j = 0; j < lpages; ++j) new.lpage_info[i][j].write_count = 1; } skip_lpage: /* Allocate page dirty bitmap if needed */ if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) { unsigned long dirty_bytes = kvm_dirty_bitmap_bytes(&new); new.dirty_bitmap = vmalloc(dirty_bytes); if (!new.dirty_bitmap) goto out_free; memset(new.dirty_bitmap, 0, dirty_bytes); /* destroy any largepage mappings for dirty tracking */ if (old.npages) flush_shadow = 1; } #else /* not defined CONFIG_S390 */ new.user_alloc = user_alloc; if (user_alloc) new.userspace_addr = mem->userspace_addr; #endif /* not defined CONFIG_S390 */ if (!npages) { r = -ENOMEM; slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); if (!slots) goto out_free; memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); if (mem->slot >= slots->nmemslots) slots->nmemslots = mem->slot + 1; slots->memslots[mem->slot].flags |= KVM_MEMSLOT_INVALID; old_memslots = kvm->memslots; rcu_assign_pointer(kvm->memslots, slots); synchronize_srcu_expedited(&kvm->srcu); /* From this point no new shadow pages pointing to a deleted * memslot will be created. * * validation of sp->gfn happens in: * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) * - kvm_is_visible_gfn (mmu_check_roots) */ kvm_arch_flush_shadow(kvm); kfree(old_memslots); } r = kvm_arch_prepare_memory_region(kvm, &new, old, mem, user_alloc); if (r) goto out_free; #ifdef CONFIG_DMAR /* map the pages in iommu page table */ if (npages) { r = kvm_iommu_map_pages(kvm, &new); if (r) goto out_free; } #endif r = -ENOMEM; slots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); if (!slots) goto out_free; memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); if (mem->slot >= slots->nmemslots) slots->nmemslots = mem->slot + 1; /* actual memory is freed via old in kvm_free_physmem_slot below */ if (!npages) { new.rmap = NULL; new.dirty_bitmap = NULL; for (i = 0; i < KVM_NR_PAGE_SIZES - 1; ++i) new.lpage_info[i] = NULL; } slots->memslots[mem->slot] = new; old_memslots = kvm->memslots; rcu_assign_pointer(kvm->memslots, slots); synchronize_srcu_expedited(&kvm->srcu); kvm_arch_commit_memory_region(kvm, mem, old, user_alloc); kvm_free_physmem_slot(&old, &new); kfree(old_memslots); if (flush_shadow) kvm_arch_flush_shadow(kvm); return 0; out_free: kvm_free_physmem_slot(&new, &old); out: return r; } EXPORT_SYMBOL_GPL(__kvm_set_memory_region); int kvm_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, int user_alloc) { int r; mutex_lock(&kvm->slots_lock); r = __kvm_set_memory_region(kvm, mem, user_alloc); mutex_unlock(&kvm->slots_lock); return r; } EXPORT_SYMBOL_GPL(kvm_set_memory_region); int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem, int user_alloc) { if (mem->slot >= KVM_MEMORY_SLOTS) return -EINVAL; return kvm_set_memory_region(kvm, mem, user_alloc); } int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, int *is_dirty) { struct kvm_memory_slot *memslot; int r, i; unsigned long n; unsigned long any = 0; r = -EINVAL; if (log->slot >= KVM_MEMORY_SLOTS) goto out; memslot = &kvm->memslots->memslots[log->slot]; r = -ENOENT; if (!memslot->dirty_bitmap) goto out; n = kvm_dirty_bitmap_bytes(memslot); for (i = 0; !any && i < n/sizeof(long); ++i) any = memslot->dirty_bitmap[i]; r = -EFAULT; if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n)) goto out; if (any) *is_dirty = 1; r = 0; out: return r; } void kvm_disable_largepages(void) { largepages_enabled = false; } EXPORT_SYMBOL_GPL(kvm_disable_largepages); int is_error_page(struct page *page) { return page == bad_page || page == hwpoison_page; } EXPORT_SYMBOL_GPL(is_error_page); int is_error_pfn(pfn_t pfn) { return pfn == bad_pfn || pfn == hwpoison_pfn; } EXPORT_SYMBOL_GPL(is_error_pfn); int is_hwpoison_pfn(pfn_t pfn) { return pfn == hwpoison_pfn; } EXPORT_SYMBOL_GPL(is_hwpoison_pfn); static inline unsigned long bad_hva(void) { return PAGE_OFFSET; } int kvm_is_error_hva(unsigned long addr) { return addr == bad_hva(); } EXPORT_SYMBOL_GPL(kvm_is_error_hva); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { int i; struct kvm_memslots *slots = kvm_memslots(kvm); for (i = 0; i < slots->nmemslots; ++i) { struct kvm_memory_slot *memslot = &slots->memslots[i]; if (gfn >= memslot->base_gfn && gfn < memslot->base_gfn + memslot->npages) return memslot; } return NULL; } EXPORT_SYMBOL_GPL(gfn_to_memslot); int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { int i; struct kvm_memslots *slots = kvm_memslots(kvm); for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { struct kvm_memory_slot *memslot = &slots->memslots[i]; if (memslot->flags & KVM_MEMSLOT_INVALID) continue; if (gfn >= memslot->base_gfn && gfn < memslot->base_gfn + memslot->npages) return 1; } return 0; } EXPORT_SYMBOL_GPL(kvm_is_visible_gfn); unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn) { struct vm_area_struct *vma; unsigned long addr, size; size = PAGE_SIZE; addr = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(addr)) return PAGE_SIZE; down_read(¤t->mm->mmap_sem); vma = find_vma(current->mm, addr); if (!vma) goto out; size = vma_kernel_pagesize(vma); out: up_read(¤t->mm->mmap_sem); return size; } int memslot_id(struct kvm *kvm, gfn_t gfn) { int i; struct kvm_memslots *slots = kvm_memslots(kvm); struct kvm_memory_slot *memslot = NULL; for (i = 0; i < slots->nmemslots; ++i) { memslot = &slots->memslots[i]; if (gfn >= memslot->base_gfn && gfn < memslot->base_gfn + memslot->npages) break; } return memslot - slots->memslots; } static unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { return slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE; } unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *slot; slot = gfn_to_memslot(kvm, gfn); if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return bad_hva(); return gfn_to_hva_memslot(slot, gfn); } EXPORT_SYMBOL_GPL(gfn_to_hva); static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr) { struct page *page[1]; int npages; pfn_t pfn; might_sleep(); npages = get_user_pages_fast(addr, 1, 1, page); if (unlikely(npages != 1)) { struct vm_area_struct *vma; down_read(¤t->mm->mmap_sem); if (is_hwpoison_address(addr)) { up_read(¤t->mm->mmap_sem); get_page(hwpoison_page); return page_to_pfn(hwpoison_page); } vma = find_vma(current->mm, addr); if (vma == NULL || addr < vma->vm_start || !(vma->vm_flags & VM_PFNMAP)) { up_read(¤t->mm->mmap_sem); get_page(bad_page); return page_to_pfn(bad_page); } pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; up_read(¤t->mm->mmap_sem); BUG_ON(!kvm_is_mmio_pfn(pfn)); } else pfn = page_to_pfn(page[0]); return pfn; } pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) { unsigned long addr; addr = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(addr)) { get_page(bad_page); return page_to_pfn(bad_page); } return hva_to_pfn(kvm, addr); } EXPORT_SYMBOL_GPL(gfn_to_pfn); pfn_t gfn_to_pfn_memslot(struct kvm *kvm, struct kvm_memory_slot *slot, gfn_t gfn) { unsigned long addr = gfn_to_hva_memslot(slot, gfn); return hva_to_pfn(kvm, addr); } struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) { pfn_t pfn; pfn = gfn_to_pfn(kvm, gfn); if (!kvm_is_mmio_pfn(pfn)) return pfn_to_page(pfn); WARN_ON(kvm_is_mmio_pfn(pfn)); get_page(bad_page); return bad_page; } EXPORT_SYMBOL_GPL(gfn_to_page); void kvm_release_page_clean(struct page *page) { kvm_release_pfn_clean(page_to_pfn(page)); } EXPORT_SYMBOL_GPL(kvm_release_page_clean); void kvm_release_pfn_clean(pfn_t pfn) { if (!kvm_is_mmio_pfn(pfn)) put_page(pfn_to_page(pfn)); } EXPORT_SYMBOL_GPL(kvm_release_pfn_clean); void kvm_release_page_dirty(struct page *page) { kvm_release_pfn_dirty(page_to_pfn(page)); } EXPORT_SYMBOL_GPL(kvm_release_page_dirty); void kvm_release_pfn_dirty(pfn_t pfn) { kvm_set_pfn_dirty(pfn); kvm_release_pfn_clean(pfn); } EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty); void kvm_set_page_dirty(struct page *page) { kvm_set_pfn_dirty(page_to_pfn(page)); } EXPORT_SYMBOL_GPL(kvm_set_page_dirty); void kvm_set_pfn_dirty(pfn_t pfn) { if (!kvm_is_mmio_pfn(pfn)) { struct page *page = pfn_to_page(pfn); if (!PageReserved(page)) SetPageDirty(page); } } EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty); void kvm_set_pfn_accessed(pfn_t pfn) { if (!kvm_is_mmio_pfn(pfn)) mark_page_accessed(pfn_to_page(pfn)); } EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed); void kvm_get_pfn(pfn_t pfn) { if (!kvm_is_mmio_pfn(pfn)) get_page(pfn_to_page(pfn)); } EXPORT_SYMBOL_GPL(kvm_get_pfn); static int next_segment(unsigned long len, int offset) { if (len > PAGE_SIZE - offset) return PAGE_SIZE - offset; else return len; } int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len) { int r; unsigned long addr; addr = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; r = copy_from_user(data, (void __user *)addr + offset, len); if (r) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(kvm_read_guest_page); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_read_guest_page(kvm, gfn, data, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; data += seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_read_guest); int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len) { int r; unsigned long addr; gfn_t gfn = gpa >> PAGE_SHIFT; int offset = offset_in_page(gpa); addr = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; pagefault_disable(); r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len); pagefault_enable(); if (r) return -EFAULT; return 0; } EXPORT_SYMBOL(kvm_read_guest_atomic); int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len) { int r; unsigned long addr; addr = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; r = copy_to_user((void __user *)addr + offset, data, len); if (r) return -EFAULT; mark_page_dirty(kvm, gfn); return 0; } EXPORT_SYMBOL_GPL(kvm_write_guest_page); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_write_guest_page(kvm, gfn, data, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; data += seg; ++gfn; } return 0; } int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len) { return kvm_write_guest_page(kvm, gfn, empty_zero_page, offset, len); } EXPORT_SYMBOL_GPL(kvm_clear_guest_page); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_clear_guest_page(kvm, gfn, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_clear_guest); void mark_page_dirty(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *memslot; memslot = gfn_to_memslot(kvm, gfn); if (memslot && memslot->dirty_bitmap) { unsigned long rel_gfn = gfn - memslot->base_gfn; generic___set_le_bit(rel_gfn, memslot->dirty_bitmap); } } /* * The vCPU has executed a HLT instruction with in-kernel mode enabled. */ void kvm_vcpu_block(struct kvm_vcpu *vcpu) { DEFINE_WAIT(wait); for (;;) { prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); if (kvm_arch_vcpu_runnable(vcpu)) { kvm_make_request(KVM_REQ_UNHALT, vcpu); break; } if (kvm_cpu_has_pending_timer(vcpu)) break; if (signal_pending(current)) break; schedule(); } finish_wait(&vcpu->wq, &wait); } void kvm_resched(struct kvm_vcpu *vcpu) { if (!need_resched()) return; cond_resched(); } EXPORT_SYMBOL_GPL(kvm_resched); void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu) { ktime_t expires; DEFINE_WAIT(wait); prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); /* Sleep for 100 us, and hope lock-holder got scheduled */ expires = ktime_add_ns(ktime_get(), 100000UL); schedule_hrtimeout(&expires, HRTIMER_MODE_ABS); finish_wait(&vcpu->wq, &wait); } EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct kvm_vcpu *vcpu = vma->vm_file->private_data; struct page *page; if (vmf->pgoff == 0) page = virt_to_page(vcpu->run); #ifdef CONFIG_X86 else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET) page = virt_to_page(vcpu->arch.pio_data); #endif #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET) page = virt_to_page(vcpu->kvm->coalesced_mmio_ring); #endif else return VM_FAULT_SIGBUS; get_page(page); vmf->page = page; return 0; } static const struct vm_operations_struct kvm_vcpu_vm_ops = { .fault = kvm_vcpu_fault, }; static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma) { vma->vm_ops = &kvm_vcpu_vm_ops; return 0; } static int kvm_vcpu_release(struct inode *inode, struct file *filp) { struct kvm_vcpu *vcpu = filp->private_data; kvm_put_kvm(vcpu->kvm); return 0; } static struct file_operations kvm_vcpu_fops = { .release = kvm_vcpu_release, .unlocked_ioctl = kvm_vcpu_ioctl, .compat_ioctl = kvm_vcpu_ioctl, .mmap = kvm_vcpu_mmap, }; /* * Allocates an inode for the vcpu. */ static int create_vcpu_fd(struct kvm_vcpu *vcpu) { return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR); } /* * Creates some virtual cpus. Good luck creating more than one. */ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) { int r; struct kvm_vcpu *vcpu, *v; vcpu = kvm_arch_vcpu_create(kvm, id); if (IS_ERR(vcpu)) return PTR_ERR(vcpu); preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); r = kvm_arch_vcpu_setup(vcpu); if (r) return r; mutex_lock(&kvm->lock); if (atomic_read(&kvm->online_vcpus) == KVM_MAX_VCPUS) { r = -EINVAL; goto vcpu_destroy; } kvm_for_each_vcpu(r, v, kvm) if (v->vcpu_id == id) { r = -EEXIST; goto vcpu_destroy; } BUG_ON(kvm->vcpus[atomic_read(&kvm->online_vcpus)]); /* Now it's all set up, let userspace reach it */ kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); if (r < 0) { kvm_put_kvm(kvm); goto vcpu_destroy; } kvm->vcpus[atomic_read(&kvm->online_vcpus)] = vcpu; smp_wmb(); atomic_inc(&kvm->online_vcpus); #ifdef CONFIG_KVM_APIC_ARCHITECTURE if (kvm->bsp_vcpu_id == id) kvm->bsp_vcpu = vcpu; #endif mutex_unlock(&kvm->lock); return r; vcpu_destroy: mutex_unlock(&kvm->lock); kvm_arch_vcpu_destroy(vcpu); return r; } static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) { if (sigset) { sigdelsetmask(sigset, sigmask(SIGKILL)|sigmask(SIGSTOP)); vcpu->sigset_active = 1; vcpu->sigset = *sigset; } else vcpu->sigset_active = 0; return 0; } static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; int r; struct kvm_fpu *fpu = NULL; struct kvm_sregs *kvm_sregs = NULL; if (vcpu->kvm->mm != current->mm) return -EIO; #if defined(CONFIG_S390) || defined(CONFIG_PPC) /* * Special cases: vcpu ioctls that are asynchronous to vcpu execution, * so vcpu_load() would break it. */ if (ioctl == KVM_S390_INTERRUPT || ioctl == KVM_INTERRUPT) return kvm_arch_vcpu_ioctl(filp, ioctl, arg); #endif vcpu_load(vcpu); switch (ioctl) { case KVM_RUN: r = -EINVAL; if (arg) goto out; r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run); break; case KVM_GET_REGS: { struct kvm_regs *kvm_regs; r = -ENOMEM; kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL); if (!kvm_regs) goto out; r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs); if (r) goto out_free1; r = -EFAULT; if (copy_to_user(argp, kvm_regs, sizeof(struct kvm_regs))) goto out_free1; r = 0; out_free1: kfree(kvm_regs); break; } case KVM_SET_REGS: { struct kvm_regs *kvm_regs; r = -ENOMEM; kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL); if (!kvm_regs) goto out; r = -EFAULT; if (copy_from_user(kvm_regs, argp, sizeof(struct kvm_regs))) goto out_free2; r = kvm_arch_vcpu_ioctl_set_regs(vcpu, kvm_regs); if (r) goto out_free2; r = 0; out_free2: kfree(kvm_regs); break; } case KVM_GET_SREGS: { kvm_sregs = kzalloc(sizeof(struct kvm_sregs), GFP_KERNEL); r = -ENOMEM; if (!kvm_sregs) goto out; r = kvm_arch_vcpu_ioctl_get_sregs(vcpu, kvm_sregs); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, kvm_sregs, sizeof(struct kvm_sregs))) goto out; r = 0; break; } case KVM_SET_SREGS: { kvm_sregs = kmalloc(sizeof(struct kvm_sregs), GFP_KERNEL); r = -ENOMEM; if (!kvm_sregs) goto out; r = -EFAULT; if (copy_from_user(kvm_sregs, argp, sizeof(struct kvm_sregs))) goto out; r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, kvm_sregs); if (r) goto out; r = 0; break; } case KVM_GET_MP_STATE: { struct kvm_mp_state mp_state; r = kvm_arch_vcpu_ioctl_get_mpstate(vcpu, &mp_state); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &mp_state, sizeof mp_state)) goto out; r = 0; break; } case KVM_SET_MP_STATE: { struct kvm_mp_state mp_state; r = -EFAULT; if (copy_from_user(&mp_state, argp, sizeof mp_state)) goto out; r = kvm_arch_vcpu_ioctl_set_mpstate(vcpu, &mp_state); if (r) goto out; r = 0; break; } case KVM_TRANSLATE: { struct kvm_translation tr; r = -EFAULT; if (copy_from_user(&tr, argp, sizeof tr)) goto out; r = kvm_arch_vcpu_ioctl_translate(vcpu, &tr); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &tr, sizeof tr)) goto out; r = 0; break; } case KVM_SET_GUEST_DEBUG: { struct kvm_guest_debug dbg; r = -EFAULT; if (copy_from_user(&dbg, argp, sizeof dbg)) goto out; r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg); if (r) goto out; r = 0; break; } case KVM_SET_SIGNAL_MASK: { struct kvm_signal_mask __user *sigmask_arg = argp; struct kvm_signal_mask kvm_sigmask; sigset_t sigset, *p; p = NULL; if (argp) { r = -EFAULT; if (copy_from_user(&kvm_sigmask, argp, sizeof kvm_sigmask)) goto out; r = -EINVAL; if (kvm_sigmask.len != sizeof sigset) goto out; r = -EFAULT; if (copy_from_user(&sigset, sigmask_arg->sigset, sizeof sigset)) goto out; p = &sigset; } r = kvm_vcpu_ioctl_set_sigmask(vcpu, p); break; } case KVM_GET_FPU: { fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL); r = -ENOMEM; if (!fpu) goto out; r = kvm_arch_vcpu_ioctl_get_fpu(vcpu, fpu); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, fpu, sizeof(struct kvm_fpu))) goto out; r = 0; break; } case KVM_SET_FPU: { fpu = kmalloc(sizeof(struct kvm_fpu), GFP_KERNEL); r = -ENOMEM; if (!fpu) goto out; r = -EFAULT; if (copy_from_user(fpu, argp, sizeof(struct kvm_fpu))) goto out; r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu); if (r) goto out; r = 0; break; } default: r = kvm_arch_vcpu_ioctl(filp, ioctl, arg); } out: vcpu_put(vcpu); kfree(fpu); kfree(kvm_sregs); return r; } static long kvm_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; int r; if (kvm->mm != current->mm) return -EIO; switch (ioctl) { case KVM_CREATE_VCPU: r = kvm_vm_ioctl_create_vcpu(kvm, arg); if (r < 0) goto out; break; case KVM_SET_USER_MEMORY_REGION: { struct kvm_userspace_memory_region kvm_userspace_mem; r = -EFAULT; if (copy_from_user(&kvm_userspace_mem, argp, sizeof kvm_userspace_mem)) goto out; r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 1); if (r) goto out; break; } case KVM_GET_DIRTY_LOG: { struct kvm_dirty_log log; r = -EFAULT; if (copy_from_user(&log, argp, sizeof log)) goto out; r = kvm_vm_ioctl_get_dirty_log(kvm, &log); if (r) goto out; break; } #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET case KVM_REGISTER_COALESCED_MMIO: { struct kvm_coalesced_mmio_zone zone; r = -EFAULT; if (copy_from_user(&zone, argp, sizeof zone)) goto out; r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone); if (r) goto out; r = 0; break; } case KVM_UNREGISTER_COALESCED_MMIO: { struct kvm_coalesced_mmio_zone zone; r = -EFAULT; if (copy_from_user(&zone, argp, sizeof zone)) goto out; r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone); if (r) goto out; r = 0; break; } #endif case KVM_IRQFD: { struct kvm_irqfd data; r = -EFAULT; if (copy_from_user(&data, argp, sizeof data)) goto out; r = kvm_irqfd(kvm, data.fd, data.gsi, data.flags); break; } case KVM_IOEVENTFD: { struct kvm_ioeventfd data; r = -EFAULT; if (copy_from_user(&data, argp, sizeof data)) goto out; r = kvm_ioeventfd(kvm, &data); break; } #ifdef CONFIG_KVM_APIC_ARCHITECTURE case KVM_SET_BOOT_CPU_ID: r = 0; mutex_lock(&kvm->lock); if (atomic_read(&kvm->online_vcpus) != 0) r = -EBUSY; else kvm->bsp_vcpu_id = arg; mutex_unlock(&kvm->lock); break; #endif default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); if (r == -ENOTTY) r = kvm_vm_ioctl_assigned_device(kvm, ioctl, arg); } out: return r; } #ifdef CONFIG_COMPAT struct compat_kvm_dirty_log { __u32 slot; __u32 padding1; union { compat_uptr_t dirty_bitmap; /* one bit per page */ __u64 padding2; }; }; static long kvm_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; int r; if (kvm->mm != current->mm) return -EIO; switch (ioctl) { case KVM_GET_DIRTY_LOG: { struct compat_kvm_dirty_log compat_log; struct kvm_dirty_log log; r = -EFAULT; if (copy_from_user(&compat_log, (void __user *)arg, sizeof(compat_log))) goto out; log.slot = compat_log.slot; log.padding1 = compat_log.padding1; log.padding2 = compat_log.padding2; log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); r = kvm_vm_ioctl_get_dirty_log(kvm, &log); if (r) goto out; break; } default: r = kvm_vm_ioctl(filp, ioctl, arg); } out: return r; } #endif static int kvm_vm_fault(struct vm_area_struct *vma, struct vm_fault *vmf) { struct page *page[1]; unsigned long addr; int npages; gfn_t gfn = vmf->pgoff; struct kvm *kvm = vma->vm_file->private_data; addr = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(addr)) return VM_FAULT_SIGBUS; npages = get_user_pages(current, current->mm, addr, 1, 1, 0, page, NULL); if (unlikely(npages != 1)) return VM_FAULT_SIGBUS; vmf->page = page[0]; return 0; } static const struct vm_operations_struct kvm_vm_vm_ops = { .fault = kvm_vm_fault, }; static int kvm_vm_mmap(struct file *file, struct vm_area_struct *vma) { vma->vm_ops = &kvm_vm_vm_ops; return 0; } static struct file_operations kvm_vm_fops = { .release = kvm_vm_release, .unlocked_ioctl = kvm_vm_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = kvm_vm_compat_ioctl, #endif .mmap = kvm_vm_mmap, }; static int kvm_dev_ioctl_create_vm(void) { int fd, r; struct kvm *kvm; kvm = kvm_create_vm(); if (IS_ERR(kvm)) return PTR_ERR(kvm); #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET r = kvm_coalesced_mmio_init(kvm); if (r < 0) { kvm_put_kvm(kvm); return r; } #endif fd = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR); if (fd < 0) kvm_put_kvm(kvm); return fd; } static long kvm_dev_ioctl_check_extension_generic(long arg) { switch (arg) { case KVM_CAP_USER_MEMORY: case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS: #ifdef CONFIG_KVM_APIC_ARCHITECTURE case KVM_CAP_SET_BOOT_CPU_ID: #endif case KVM_CAP_INTERNAL_ERROR_DATA: return 1; #ifdef CONFIG_HAVE_KVM_IRQCHIP case KVM_CAP_IRQ_ROUTING: return KVM_MAX_IRQ_ROUTES; #endif default: break; } return kvm_dev_ioctl_check_extension(arg); } static long kvm_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { long r = -EINVAL; switch (ioctl) { case KVM_GET_API_VERSION: r = -EINVAL; if (arg) goto out; r = KVM_API_VERSION; break; case KVM_CREATE_VM: r = -EINVAL; if (arg) goto out; r = kvm_dev_ioctl_create_vm(); break; case KVM_CHECK_EXTENSION: r = kvm_dev_ioctl_check_extension_generic(arg); break; case KVM_GET_VCPU_MMAP_SIZE: r = -EINVAL; if (arg) goto out; r = PAGE_SIZE; /* struct kvm_run */ #ifdef CONFIG_X86 r += PAGE_SIZE; /* pio data page */ #endif #ifdef KVM_COALESCED_MMIO_PAGE_OFFSET r += PAGE_SIZE; /* coalesced mmio ring page */ #endif break; case KVM_TRACE_ENABLE: case KVM_TRACE_PAUSE: case KVM_TRACE_DISABLE: r = -EOPNOTSUPP; break; default: return kvm_arch_dev_ioctl(filp, ioctl, arg); } out: return r; } static struct file_operations kvm_chardev_ops = { .unlocked_ioctl = kvm_dev_ioctl, .compat_ioctl = kvm_dev_ioctl, }; static struct miscdevice kvm_dev = { KVM_MINOR, "kvm", &kvm_chardev_ops, }; static void hardware_enable(void *junk) { int cpu = raw_smp_processor_id(); int r; if (cpumask_test_cpu(cpu, cpus_hardware_enabled)) return; cpumask_set_cpu(cpu, cpus_hardware_enabled); r = kvm_arch_hardware_enable(NULL); if (r) { cpumask_clear_cpu(cpu, cpus_hardware_enabled); atomic_inc(&hardware_enable_failed); printk(KERN_INFO "kvm: enabling virtualization on " "CPU%d failed\n", cpu); } } static void hardware_disable(void *junk) { int cpu = raw_smp_processor_id(); if (!cpumask_test_cpu(cpu, cpus_hardware_enabled)) return; cpumask_clear_cpu(cpu, cpus_hardware_enabled); kvm_arch_hardware_disable(NULL); } static void hardware_disable_all_nolock(void) { BUG_ON(!kvm_usage_count); kvm_usage_count--; if (!kvm_usage_count) on_each_cpu(hardware_disable, NULL, 1); } static void hardware_disable_all(void) { spin_lock(&kvm_lock); hardware_disable_all_nolock(); spin_unlock(&kvm_lock); } static int hardware_enable_all(void) { int r = 0; spin_lock(&kvm_lock); kvm_usage_count++; if (kvm_usage_count == 1) { atomic_set(&hardware_enable_failed, 0); on_each_cpu(hardware_enable, NULL, 1); if (atomic_read(&hardware_enable_failed)) { hardware_disable_all_nolock(); r = -EBUSY; } } spin_unlock(&kvm_lock); return r; } static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, void *v) { int cpu = (long)v; if (!kvm_usage_count) return NOTIFY_OK; val &= ~CPU_TASKS_FROZEN; switch (val) { case CPU_DYING: printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n", cpu); hardware_disable(NULL); break; case CPU_ONLINE: printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n", cpu); smp_call_function_single(cpu, hardware_enable, NULL, 1); break; } return NOTIFY_OK; } asmlinkage void kvm_handle_fault_on_reboot(void) { if (kvm_rebooting) /* spin while reset goes on */ while (true) ; /* Fault while not rebooting. We want the trace. */ BUG(); } EXPORT_SYMBOL_GPL(kvm_handle_fault_on_reboot); static int kvm_reboot(struct notifier_block *notifier, unsigned long val, void *v) { /* * Some (well, at least mine) BIOSes hang on reboot if * in vmx root mode. * * And Intel TXT required VMX off for all cpu when system shutdown. */ printk(KERN_INFO "kvm: exiting hardware virtualization\n"); kvm_rebooting = true; on_each_cpu(hardware_disable, NULL, 1); return NOTIFY_OK; } static struct notifier_block kvm_reboot_notifier = { .notifier_call = kvm_reboot, .priority = 0, }; static void kvm_io_bus_destroy(struct kvm_io_bus *bus) { int i; for (i = 0; i < bus->dev_count; i++) { struct kvm_io_device *pos = bus->devs[i]; kvm_iodevice_destructor(pos); } kfree(bus); } /* kvm_io_bus_write - called under kvm->slots_lock */ int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val) { int i; struct kvm_io_bus *bus; bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); for (i = 0; i < bus->dev_count; i++) if (!kvm_iodevice_write(bus->devs[i], addr, len, val)) return 0; return -EOPNOTSUPP; } /* kvm_io_bus_read - called under kvm->slots_lock */ int kvm_io_bus_read(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, void *val) { int i; struct kvm_io_bus *bus; bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); for (i = 0; i < bus->dev_count; i++) if (!kvm_iodevice_read(bus->devs[i], addr, len, val)) return 0; return -EOPNOTSUPP; } /* Caller must hold slots_lock. */ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev) { struct kvm_io_bus *new_bus, *bus; bus = kvm->buses[bus_idx]; if (bus->dev_count > NR_IOBUS_DEVS-1) return -ENOSPC; new_bus = kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL); if (!new_bus) return -ENOMEM; memcpy(new_bus, bus, sizeof(struct kvm_io_bus)); new_bus->devs[new_bus->dev_count++] = dev; rcu_assign_pointer(kvm->buses[bus_idx], new_bus); synchronize_srcu_expedited(&kvm->srcu); kfree(bus); return 0; } /* Caller must hold slots_lock. */ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev) { int i, r; struct kvm_io_bus *new_bus, *bus; new_bus = kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL); if (!new_bus) return -ENOMEM; bus = kvm->buses[bus_idx]; memcpy(new_bus, bus, sizeof(struct kvm_io_bus)); r = -ENOENT; for (i = 0; i < new_bus->dev_count; i++) if (new_bus->devs[i] == dev) { r = 0; new_bus->devs[i] = new_bus->devs[--new_bus->dev_count]; break; } if (r) { kfree(new_bus); return r; } rcu_assign_pointer(kvm->buses[bus_idx], new_bus); synchronize_srcu_expedited(&kvm->srcu); kfree(bus); return r; } static struct notifier_block kvm_cpu_notifier = { .notifier_call = kvm_cpu_hotplug, .priority = 20, /* must be > scheduler priority */ }; static int vm_stat_get(void *_offset, u64 *val) { unsigned offset = (long)_offset; struct kvm *kvm; *val = 0; spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) *val += *(u32 *)((void *)kvm + offset); spin_unlock(&kvm_lock); return 0; } DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, NULL, "%llu\n"); static int vcpu_stat_get(void *_offset, u64 *val) { unsigned offset = (long)_offset; struct kvm *kvm; struct kvm_vcpu *vcpu; int i; *val = 0; spin_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) kvm_for_each_vcpu(i, vcpu, kvm) *val += *(u32 *)((void *)vcpu + offset); spin_unlock(&kvm_lock); return 0; } DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, NULL, "%llu\n"); static const struct file_operations *stat_fops[] = { [KVM_STAT_VCPU] = &vcpu_stat_fops, [KVM_STAT_VM] = &vm_stat_fops, }; static void kvm_init_debug(void) { struct kvm_stats_debugfs_item *p; kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); for (p = debugfs_entries; p->name; ++p) p->dentry = debugfs_create_file(p->name, 0444, kvm_debugfs_dir, (void *)(long)p->offset, stat_fops[p->kind]); } static void kvm_exit_debug(void) { struct kvm_stats_debugfs_item *p; for (p = debugfs_entries; p->name; ++p) debugfs_remove(p->dentry); debugfs_remove(kvm_debugfs_dir); } static int kvm_suspend(struct sys_device *dev, pm_message_t state) { if (kvm_usage_count) hardware_disable(NULL); return 0; } static int kvm_resume(struct sys_device *dev) { if (kvm_usage_count) hardware_enable(NULL); return 0; } static struct sysdev_class kvm_sysdev_class = { .name = "kvm", .suspend = kvm_suspend, .resume = kvm_resume, }; static struct sys_device kvm_sysdev = { .id = 0, .cls = &kvm_sysdev_class, }; struct page *bad_page; pfn_t bad_pfn; static inline struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn) { return container_of(pn, struct kvm_vcpu, preempt_notifier); } static void kvm_sched_in(struct preempt_notifier *pn, int cpu) { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); kvm_arch_vcpu_load(vcpu, cpu); } static void kvm_sched_out(struct preempt_notifier *pn, struct task_struct *next) { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); kvm_arch_vcpu_put(vcpu); } int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, struct module *module) { int r; int cpu; r = kvm_arch_init(opaque); if (r) goto out_fail; bad_page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (bad_page == NULL) { r = -ENOMEM; goto out; } bad_pfn = page_to_pfn(bad_page); hwpoison_page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (hwpoison_page == NULL) { r = -ENOMEM; goto out_free_0; } hwpoison_pfn = page_to_pfn(hwpoison_page); if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) { r = -ENOMEM; goto out_free_0; } r = kvm_arch_hardware_setup(); if (r < 0) goto out_free_0a; for_each_online_cpu(cpu) { smp_call_function_single(cpu, kvm_arch_check_processor_compat, &r, 1); if (r < 0) goto out_free_1; } r = register_cpu_notifier(&kvm_cpu_notifier); if (r) goto out_free_2; register_reboot_notifier(&kvm_reboot_notifier); r = sysdev_class_register(&kvm_sysdev_class); if (r) goto out_free_3; r = sysdev_register(&kvm_sysdev); if (r) goto out_free_4; /* A kmem cache lets us meet the alignment requirements of fx_save. */ if (!vcpu_align) vcpu_align = __alignof__(struct kvm_vcpu); kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size, vcpu_align, 0, NULL); if (!kvm_vcpu_cache) { r = -ENOMEM; goto out_free_5; } kvm_chardev_ops.owner = module; kvm_vm_fops.owner = module; kvm_vcpu_fops.owner = module; r = misc_register(&kvm_dev); if (r) { printk(KERN_ERR "kvm: misc device register failed\n"); goto out_free; } kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out; kvm_init_debug(); return 0; out_free: kmem_cache_destroy(kvm_vcpu_cache); out_free_5: sysdev_unregister(&kvm_sysdev); out_free_4: sysdev_class_unregister(&kvm_sysdev_class); out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); unregister_cpu_notifier(&kvm_cpu_notifier); out_free_2: out_free_1: kvm_arch_hardware_unsetup(); out_free_0a: free_cpumask_var(cpus_hardware_enabled); out_free_0: if (hwpoison_page) __free_page(hwpoison_page); __free_page(bad_page); out: kvm_arch_exit(); out_fail: return r; } EXPORT_SYMBOL_GPL(kvm_init); void kvm_exit(void) { kvm_exit_debug(); misc_deregister(&kvm_dev); kmem_cache_destroy(kvm_vcpu_cache); sysdev_unregister(&kvm_sysdev); sysdev_class_unregister(&kvm_sysdev_class); unregister_reboot_notifier(&kvm_reboot_notifier); unregister_cpu_notifier(&kvm_cpu_notifier); on_each_cpu(hardware_disable, NULL, 1); kvm_arch_hardware_unsetup(); kvm_arch_exit(); free_cpumask_var(cpus_hardware_enabled); __free_page(hwpoison_page); __free_page(bad_page); } EXPORT_SYMBOL_GPL(kvm_exit);