diff options
Diffstat (limited to 'virt/kvm/kvm_main.c')
| -rw-r--r-- | virt/kvm/kvm_main.c | 2247 |
1 files changed, 1666 insertions, 581 deletions
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index a944be392d6..4b6c01b477f 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -5,6 +5,7 @@ * machines without emulation or binary translation. * * Copyright (C) 2006 Qumranet, Inc. + * Copyright 2010 Red Hat, Inc. and/or its affiliates. * * Authors: * Avi Kivity <avi@qumranet.com> @@ -22,7 +23,6 @@ #include <linux/module.h> #include <linux/errno.h> #include <linux/percpu.h> -#include <linux/gfp.h> #include <linux/mm.h> #include <linux/miscdevice.h> #include <linux/vmalloc.h> @@ -30,7 +30,7 @@ #include <linux/debugfs.h> #include <linux/highmem.h> #include <linux/file.h> -#include <linux/sysdev.h> +#include <linux/syscore_ops.h> #include <linux/cpu.h> #include <linux/sched.h> #include <linux/cpumask.h> @@ -44,16 +44,19 @@ #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 <linux/sort.h> +#include <linux/bsearch.h> #include <asm/processor.h> #include <asm/io.h> #include <asm/uaccess.h> #include <asm/pgtable.h> -#include <asm-generic/bitops/le.h> -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET #include "coalesced_mmio.h" -#endif +#include "async_pf.h" #define CREATE_TRACE_POINTS #include <trace/events/kvm.h> @@ -68,6 +71,7 @@ MODULE_LICENSE("GPL"); */ DEFINE_SPINLOCK(kvm_lock); +static DEFINE_RAW_SPINLOCK(kvm_count_lock); LIST_HEAD(vm_list); static cpumask_var_t cpus_hardware_enabled; @@ -83,19 +87,30 @@ struct dentry *kvm_debugfs_dir; static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); +#ifdef CONFIG_COMPAT +static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl, + unsigned long arg); +#endif static int hardware_enable_all(void); static void hardware_disable_all(void); -static bool kvm_rebooting; +static void kvm_io_bus_destroy(struct kvm_io_bus *bus); +static void update_memslots(struct kvm_memslots *slots, + struct kvm_memory_slot *new, u64 last_generation); + +static void kvm_release_pfn_dirty(pfn_t pfn); +static void mark_page_dirty_in_slot(struct kvm *kvm, + struct kvm_memory_slot *memslot, gfn_t gfn); + +__visible bool kvm_rebooting; +EXPORT_SYMBOL_GPL(kvm_rebooting); static bool largepages_enabled = true; -inline int kvm_is_mmio_pfn(pfn_t pfn) +bool kvm_is_mmio_pfn(pfn_t pfn) { - if (pfn_valid(pfn)) { - struct page *page = compound_head(pfn_to_page(pfn)); - return PageReserved(page); - } + if (pfn_valid(pfn)) + return PageReserved(pfn_to_page(pfn)); return true; } @@ -103,15 +118,25 @@ inline int kvm_is_mmio_pfn(pfn_t pfn) /* * Switches to specified vcpu, until a matching vcpu_put() */ -void vcpu_load(struct kvm_vcpu *vcpu) +int vcpu_load(struct kvm_vcpu *vcpu) { int cpu; - mutex_lock(&vcpu->mutex); + if (mutex_lock_killable(&vcpu->mutex)) + return -EINTR; + if (unlikely(vcpu->pid != current->pids[PIDTYPE_PID].pid)) { + /* The thread running this VCPU changed. */ + struct pid *oldpid = vcpu->pid; + struct pid *newpid = get_task_pid(current, PIDTYPE_PID); + rcu_assign_pointer(vcpu->pid, newpid); + synchronize_rcu(); + put_pid(oldpid); + } cpu = get_cpu(); preempt_notifier_register(&vcpu->preempt_notifier); kvm_arch_vcpu_load(vcpu, cpu); put_cpu(); + return 0; } void vcpu_put(struct kvm_vcpu *vcpu) @@ -136,13 +161,16 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req) zalloc_cpumask_var(&cpus, GFP_ATOMIC); - spin_lock(&kvm->requests_lock); - me = smp_processor_id(); + me = get_cpu(); kvm_for_each_vcpu(i, vcpu, kvm) { - if (test_and_set_bit(req, &vcpu->requests)) - continue; + kvm_make_request(req, vcpu); cpu = vcpu->cpu; - if (cpus != NULL && cpu != -1 && cpu != me) + + /* Set ->requests bit before we read ->mode */ + smp_mb(); + + if (cpus != NULL && cpu != -1 && cpu != me && + kvm_vcpu_exiting_guest_mode(vcpu) != OUTSIDE_GUEST_MODE) cpumask_set_cpu(cpu, cpus); } if (unlikely(cpus == NULL)) @@ -151,22 +179,37 @@ static bool make_all_cpus_request(struct kvm *kvm, unsigned int req) smp_call_function_many(cpus, ack_flush, NULL, 1); else called = false; - spin_unlock(&kvm->requests_lock); + put_cpu(); free_cpumask_var(cpus); return called; } void kvm_flush_remote_tlbs(struct kvm *kvm) { + long dirty_count = kvm->tlbs_dirty; + + smp_mb(); if (make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH)) ++kvm->stat.remote_tlb_flush; + cmpxchg(&kvm->tlbs_dirty, dirty_count, 0); } +EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); void kvm_reload_remote_mmus(struct kvm *kvm) { make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD); } +void kvm_make_mclock_inprogress_request(struct kvm *kvm) +{ + make_all_cpus_request(kvm, KVM_REQ_MCLOCK_INPROGRESS); +} + +void kvm_make_scan_ioapic_request(struct kvm *kvm) +{ + make_all_cpus_request(kvm, KVM_REQ_SCAN_IOAPIC); +} + int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) { struct page *page; @@ -176,7 +219,9 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->cpu = -1; vcpu->kvm = kvm; vcpu->vcpu_id = id; + vcpu->pid = NULL; init_waitqueue_head(&vcpu->wq); + kvm_async_pf_vcpu_init(vcpu); page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!page) { @@ -185,6 +230,10 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) } vcpu->run = page_address(page); + kvm_vcpu_set_in_spin_loop(vcpu, false); + kvm_vcpu_set_dy_eligible(vcpu, false); + vcpu->preempted = false; + r = kvm_arch_vcpu_init(vcpu); if (r < 0) goto fail_free_run; @@ -199,6 +248,7 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_init); void kvm_vcpu_uninit(struct kvm_vcpu *vcpu) { + put_pid(vcpu->pid); kvm_arch_vcpu_uninit(vcpu); free_page((unsigned long)vcpu->run); } @@ -215,7 +265,7 @@ static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn, unsigned long address) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - int need_tlb_flush; + int need_tlb_flush, idx; /* * When ->invalidate_page runs, the linux pte has been zapped @@ -235,15 +285,17 @@ static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn, * 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); + kvm->mmu_notifier_seq++; + need_tlb_flush = kvm_unmap_hva(kvm, address) | kvm->tlbs_dirty; /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush) kvm_flush_remote_tlbs(kvm); + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); } static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, @@ -252,11 +304,14 @@ static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn, 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, @@ -265,8 +320,9 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, unsigned long end) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - int need_tlb_flush = 0; + 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 @@ -274,13 +330,14 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, * 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); - + need_tlb_flush = kvm_unmap_hva_range(kvm, start, end); + need_tlb_flush |= kvm->tlbs_dirty; /* we've to flush the tlb before the pages can be freed */ if (need_tlb_flush) kvm_flush_remote_tlbs(kvm); + + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); } static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, @@ -297,11 +354,11 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, * been freed. */ kvm->mmu_notifier_seq++; + smp_wmb(); /* * 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. + * below count decrease, which is ensured by the smp_wmb above + * in conjunction with the smp_rmb in mmu_notifier_retry(). */ kvm->mmu_notifier_count--; spin_unlock(&kvm->mmu_lock); @@ -314,15 +371,34 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn, unsigned long address) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - int young; + 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); + young = kvm_age_hva(kvm, address); if (young) kvm_flush_remote_tlbs(kvm); + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); + + return young; +} + +static int kvm_mmu_notifier_test_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_test_age_hva(kvm, address); + spin_unlock(&kvm->mmu_lock); + srcu_read_unlock(&kvm->srcu, idx); + return young; } @@ -330,7 +406,11 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn, struct mm_struct *mm) { struct kvm *kvm = mmu_notifier_to_kvm(mn); - kvm_arch_flush_shadow(kvm); + int idx; + + idx = srcu_read_lock(&kvm->srcu); + kvm_arch_flush_shadow_all(kvm); + srcu_read_unlock(&kvm->srcu, idx); } static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { @@ -338,121 +418,178 @@ static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { .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, + .test_young = kvm_mmu_notifier_test_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) +static void kvm_init_memslots_id(struct kvm *kvm) { - int r = 0; - struct kvm *kvm = kvm_arch_create_vm(); -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET - struct page *page; -#endif + int i; + struct kvm_memslots *slots = kvm->memslots; - if (IS_ERR(kvm)) - goto out; + for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) + slots->id_to_index[i] = slots->memslots[i].id = i; +} + +static struct kvm *kvm_create_vm(unsigned long type) +{ + int r, i; + struct kvm *kvm = kvm_arch_alloc_vm(); + + if (!kvm) + return ERR_PTR(-ENOMEM); + + r = kvm_arch_init_vm(kvm, type); + if (r) + goto out_err_no_disable; r = hardware_enable_all(); if (r) - goto out_err_nodisable; + goto out_err_no_disable; #ifdef CONFIG_HAVE_KVM_IRQCHIP INIT_HLIST_HEAD(&kvm->mask_notifier_list); INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); #endif -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET - page = alloc_page(GFP_KERNEL | __GFP_ZERO); - if (!page) { - r = -ENOMEM; - goto out_err; - } - kvm->coalesced_mmio_ring = - (struct kvm_coalesced_mmio_ring *)page_address(page); -#endif + BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); -#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER) - { - kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops; - r = mmu_notifier_register(&kvm->mmu_notifier, current->mm); - if (r) { -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET - put_page(page); -#endif + r = -ENOMEM; + kvm->memslots = kzalloc(sizeof(struct kvm_memslots), GFP_KERNEL); + if (!kvm->memslots) + goto out_err_no_srcu; + kvm_init_memslots_id(kvm); + if (init_srcu_struct(&kvm->srcu)) + goto out_err_no_srcu; + if (init_srcu_struct(&kvm->irq_srcu)) + goto out_err_no_irq_srcu; + for (i = 0; i < KVM_NR_BUSES; i++) { + kvm->buses[i] = kzalloc(sizeof(struct kvm_io_bus), + GFP_KERNEL); + if (!kvm->buses[i]) goto out_err; - } } -#endif + spin_lock_init(&kvm->mmu_lock); kvm->mm = current->mm; atomic_inc(&kvm->mm->mm_count); - spin_lock_init(&kvm->mmu_lock); - spin_lock_init(&kvm->requests_lock); - kvm_io_bus_init(&kvm->pio_bus); kvm_eventfd_init(kvm); mutex_init(&kvm->lock); mutex_init(&kvm->irq_lock); - kvm_io_bus_init(&kvm->mmio_bus); - init_rwsem(&kvm->slots_lock); + mutex_init(&kvm->slots_lock); atomic_set(&kvm->users_count, 1); + INIT_LIST_HEAD(&kvm->devices); + + r = kvm_init_mmu_notifier(kvm); + if (r) + goto out_err; + spin_lock(&kvm_lock); list_add(&kvm->vm_list, &vm_list); spin_unlock(&kvm_lock); -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET - kvm_coalesced_mmio_init(kvm); -#endif -out: + return kvm; -#if defined(KVM_COALESCED_MMIO_PAGE_OFFSET) || \ - (defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)) out_err: + cleanup_srcu_struct(&kvm->irq_srcu); +out_err_no_irq_srcu: + cleanup_srcu_struct(&kvm->srcu); +out_err_no_srcu: hardware_disable_all(); -#endif -out_err_nodisable: - kfree(kvm); +out_err_no_disable: + for (i = 0; i < KVM_NR_BUSES; i++) + kfree(kvm->buses[i]); + kfree(kvm->memslots); + kvm_arch_free_vm(kvm); return ERR_PTR(r); } /* + * Avoid using vmalloc for a small buffer. + * Should not be used when the size is statically known. + */ +void *kvm_kvzalloc(unsigned long size) +{ + if (size > PAGE_SIZE) + return vzalloc(size); + else + return kzalloc(size, GFP_KERNEL); +} + +void kvm_kvfree(const void *addr) +{ + if (is_vmalloc_addr(addr)) + vfree(addr); + else + kfree(addr); +} + +static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) +{ + if (!memslot->dirty_bitmap) + return; + + kvm_kvfree(memslot->dirty_bitmap); + memslot->dirty_bitmap = NULL; +} + +/* * Free any memory in @free but not in @dont. */ -static void kvm_free_physmem_slot(struct kvm_memory_slot *free, +static void kvm_free_physmem_slot(struct kvm *kvm, struct kvm_memory_slot *free, struct kvm_memory_slot *dont) { - int i; + if (!dont || free->dirty_bitmap != dont->dirty_bitmap) + kvm_destroy_dirty_bitmap(free); - if (!dont || free->rmap != dont->rmap) - vfree(free->rmap); + kvm_arch_free_memslot(kvm, free, dont); - if (!dont || free->dirty_bitmap != dont->dirty_bitmap) - vfree(free->dirty_bitmap); + free->npages = 0; +} +static void kvm_free_physmem(struct kvm *kvm) +{ + struct kvm_memslots *slots = kvm->memslots; + struct kvm_memory_slot *memslot; - 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; - } - } + kvm_for_each_memslot(memslot, slots) + kvm_free_physmem_slot(kvm, memslot, NULL); - free->npages = 0; - free->dirty_bitmap = NULL; - free->rmap = NULL; + kfree(kvm->memslots); } -void kvm_free_physmem(struct kvm *kvm) +static void kvm_destroy_devices(struct kvm *kvm) { - int i; + struct list_head *node, *tmp; + + list_for_each_safe(node, tmp, &kvm->devices) { + struct kvm_device *dev = + list_entry(node, struct kvm_device, vm_node); - for (i = 0; i < kvm->nmemslots; ++i) - kvm_free_physmem_slot(&kvm->memslots[i], NULL); + list_del(node); + dev->ops->destroy(dev); + } } static void kvm_destroy_vm(struct kvm *kvm) { + int i; struct mm_struct *mm = kvm->mm; kvm_arch_sync_events(kvm); @@ -460,18 +597,20 @@ static void kvm_destroy_vm(struct kvm *kvm) list_del(&kvm->vm_list); spin_unlock(&kvm_lock); kvm_free_irq_routing(kvm); - kvm_io_bus_destroy(&kvm->pio_bus); - kvm_io_bus_destroy(&kvm->mmio_bus); -#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET - if (kvm->coalesced_mmio_ring != NULL) - free_page((unsigned long)kvm->coalesced_mmio_ring); -#endif + 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); + kvm_arch_flush_shadow_all(kvm); #endif kvm_arch_destroy_vm(kvm); + kvm_destroy_devices(kvm); + kvm_free_physmem(kvm); + cleanup_srcu_struct(&kvm->irq_srcu); + cleanup_srcu_struct(&kvm->srcu); + kvm_arch_free_vm(kvm); hardware_disable_all(); mmdrop(mm); } @@ -501,6 +640,96 @@ static int kvm_vm_release(struct inode *inode, struct file *filp) } /* + * Allocation size is twice as large as the actual dirty bitmap size. + * See x86's kvm_vm_ioctl_get_dirty_log() why this is needed. + */ +static int kvm_create_dirty_bitmap(struct kvm_memory_slot *memslot) +{ + unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot); + + memslot->dirty_bitmap = kvm_kvzalloc(dirty_bytes); + if (!memslot->dirty_bitmap) + return -ENOMEM; + + return 0; +} + +static int cmp_memslot(const void *slot1, const void *slot2) +{ + struct kvm_memory_slot *s1, *s2; + + s1 = (struct kvm_memory_slot *)slot1; + s2 = (struct kvm_memory_slot *)slot2; + + if (s1->npages < s2->npages) + return 1; + if (s1->npages > s2->npages) + return -1; + + return 0; +} + +/* + * Sort the memslots base on its size, so the larger slots + * will get better fit. + */ +static void sort_memslots(struct kvm_memslots *slots) +{ + int i; + + sort(slots->memslots, KVM_MEM_SLOTS_NUM, + sizeof(struct kvm_memory_slot), cmp_memslot, NULL); + + for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) + slots->id_to_index[slots->memslots[i].id] = i; +} + +static void update_memslots(struct kvm_memslots *slots, + struct kvm_memory_slot *new, + u64 last_generation) +{ + if (new) { + int id = new->id; + struct kvm_memory_slot *old = id_to_memslot(slots, id); + unsigned long npages = old->npages; + + *old = *new; + if (new->npages != npages) + sort_memslots(slots); + } + + slots->generation = last_generation + 1; +} + +static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) +{ + u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; + +#ifdef KVM_CAP_READONLY_MEM + valid_flags |= KVM_MEM_READONLY; +#endif + + if (mem->flags & ~valid_flags) + return -EINVAL; + + return 0; +} + +static struct kvm_memslots *install_new_memslots(struct kvm *kvm, + struct kvm_memslots *slots, struct kvm_memory_slot *new) +{ + struct kvm_memslots *old_memslots = kvm->memslots; + + update_memslots(slots, new, kvm->memslots->generation); + rcu_assign_pointer(kvm->memslots, slots); + synchronize_srcu_expedited(&kvm->srcu); + + kvm_arch_memslots_updated(kvm); + + return old_memslots; +} + +/* * Allocate some memory and give it an address in the guest physical address * space. * @@ -509,15 +738,19 @@ static int kvm_vm_release(struct inode *inode, struct file *filp) * 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) + struct kvm_userspace_memory_region *mem) { int r; gfn_t base_gfn; unsigned long npages; - unsigned long i; - struct kvm_memory_slot *memslot; + struct kvm_memory_slot *slot; struct kvm_memory_slot old, new; + struct kvm_memslots *slots = NULL, *old_memslots; + enum kvm_mr_change change; + + r = check_memory_region_flags(mem); + if (r) + goto out; r = -EINVAL; /* General sanity checks */ @@ -525,41 +758,71 @@ int __kvm_set_memory_region(struct kvm *kvm, goto out; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) goto out; - if (user_alloc && (mem->userspace_addr & (PAGE_SIZE - 1))) + /* We can read the guest memory with __xxx_user() later on. */ + if ((mem->slot < KVM_USER_MEM_SLOTS) && + ((mem->userspace_addr & (PAGE_SIZE - 1)) || + !access_ok(VERIFY_WRITE, + (void __user *)(unsigned long)mem->userspace_addr, + mem->memory_size))) goto out; - if (mem->slot >= KVM_MEMORY_SLOTS + KVM_PRIVATE_MEM_SLOTS) + if (mem->slot >= KVM_MEM_SLOTS_NUM) goto out; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) goto out; - memslot = &kvm->memslots[mem->slot]; + slot = id_to_memslot(kvm->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 = old = *slot; + 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; + if (npages) { + if (!old.npages) + change = KVM_MR_CREATE; + else { /* Modify an existing slot. */ + if ((mem->userspace_addr != old.userspace_addr) || + (npages != old.npages) || + ((new.flags ^ old.flags) & KVM_MEM_READONLY)) + goto out; - /* Check for overlaps */ - r = -EEXIST; - for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { - struct kvm_memory_slot *s = &kvm->memslots[i]; + if (base_gfn != old.base_gfn) + change = KVM_MR_MOVE; + else if (new.flags != old.flags) + change = KVM_MR_FLAGS_ONLY; + else { /* Nothing to change. */ + r = 0; + goto out; + } + } + } else if (old.npages) { + change = KVM_MR_DELETE; + } else /* Modify a non-existent slot: disallowed. */ + goto out; - if (s == memslot || !s->npages) - continue; - if (!((base_gfn + npages <= s->base_gfn) || - (base_gfn >= s->base_gfn + s->npages))) - goto out_free; + if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { + /* Check for overlaps */ + r = -EEXIST; + kvm_for_each_memslot(slot, kvm->memslots) { + if ((slot->id >= KVM_USER_MEM_SLOTS) || + (slot->id == mem->slot)) + continue; + if (!((base_gfn + npages <= slot->base_gfn) || + (base_gfn >= slot->base_gfn + slot->npages))) + goto out; + } } /* Free page dirty bitmap if unneeded */ @@ -567,151 +830,116 @@ int __kvm_set_memory_region(struct kvm *kvm, new.dirty_bitmap = NULL; r = -ENOMEM; + if (change == KVM_MR_CREATE) { + new.userspace_addr = mem->userspace_addr; - /* Allocate if a slot is being created */ -#ifndef CONFIG_S390 - if (npages && !new.rmap) { - new.rmap = vmalloc(npages * sizeof(struct page *)); - - if (!new.rmap) + if (kvm_arch_create_memslot(kvm, &new, npages)) goto out_free; - - memset(new.rmap, 0, npages * sizeof(*new.rmap)); - - new.user_alloc = user_alloc; - /* - * hva_to_rmmap() serialzies with the mmu_lock and to be - * safe it has to ignore memslots with !user_alloc && - * !userspace_addr. - */ - if (user_alloc) - new.userspace_addr = mem->userspace_addr; - else - new.userspace_addr = 0; } - 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_PAGES_PER_HPAGE(level); - lpages -= base_gfn / KVM_PAGES_PER_HPAGE(level); - - new.lpage_info[i] = vmalloc(lpages * sizeof(*new.lpage_info[i])); - - if (!new.lpage_info[i]) + /* Allocate page dirty bitmap if needed */ + if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) { + if (kvm_create_dirty_bitmap(&new) < 0) goto out_free; + } - memset(new.lpage_info[i], 0, - lpages * sizeof(*new.lpage_info[i])); - - if (base_gfn % KVM_PAGES_PER_HPAGE(level)) - new.lpage_info[i][0].write_count = 1; - if ((base_gfn+npages) % KVM_PAGES_PER_HPAGE(level)) - 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 ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) { + r = -ENOMEM; + slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots), + GFP_KERNEL); + if (!slots) + goto out_free; + slot = id_to_memslot(slots, mem->slot); + slot->flags |= KVM_MEMSLOT_INVALID; + + old_memslots = install_new_memslots(kvm, slots, NULL); + + /* slot was deleted or moved, clear iommu mapping */ + kvm_iommu_unmap_pages(kvm, &old); + /* From this point no new shadow pages pointing to a deleted, + * or moved, 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) */ - 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; + kvm_arch_flush_shadow_memslot(kvm, slot); + slots = old_memslots; } -skip_lpage: - - /* Allocate page dirty bitmap if needed */ - if ((new.flags & KVM_MEM_LOG_DIRTY_PAGES) && !new.dirty_bitmap) { - unsigned dirty_bytes = ALIGN(npages, BITS_PER_LONG) / 8; + r = kvm_arch_prepare_memory_region(kvm, &new, mem, change); + if (r) + goto out_slots; - new.dirty_bitmap = vmalloc(dirty_bytes); - if (!new.dirty_bitmap) + r = -ENOMEM; + /* + * We can re-use the old_memslots from above, the only difference + * from the currently installed memslots is the invalid flag. This + * will get overwritten by update_memslots anyway. + */ + if (!slots) { + slots = kmemdup(kvm->memslots, sizeof(struct kvm_memslots), + GFP_KERNEL); + if (!slots) goto out_free; - memset(new.dirty_bitmap, 0, dirty_bytes); - if (old.npages) - kvm_arch_flush_shadow(kvm); } -#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) - kvm_arch_flush_shadow(kvm); + /* actual memory is freed via old in kvm_free_physmem_slot below */ + if (change == KVM_MR_DELETE) { + new.dirty_bitmap = NULL; + memset(&new.arch, 0, sizeof(new.arch)); + } - spin_lock(&kvm->mmu_lock); - if (mem->slot >= kvm->nmemslots) - kvm->nmemslots = mem->slot + 1; + old_memslots = install_new_memslots(kvm, slots, &new); - *memslot = new; - spin_unlock(&kvm->mmu_lock); + kvm_arch_commit_memory_region(kvm, mem, &old, change); - r = kvm_arch_set_memory_region(kvm, mem, old, user_alloc); - if (r) { - spin_lock(&kvm->mmu_lock); - *memslot = old; - spin_unlock(&kvm->mmu_lock); - goto out_free; + kvm_free_physmem_slot(kvm, &old, &new); + kfree(old_memslots); + + /* + * IOMMU mapping: New slots need to be mapped. Old slots need to be + * un-mapped and re-mapped if their base changes. Since base change + * unmapping is handled above with slot deletion, mapping alone is + * needed here. Anything else the iommu might care about for existing + * slots (size changes, userspace addr changes and read-only flag + * changes) is disallowed above, so any other attribute changes getting + * here can be skipped. + */ + if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { + r = kvm_iommu_map_pages(kvm, &new); + return r; } - kvm_free_physmem_slot(&old, npages ? &new : NULL); - /* Slot deletion case: we have to update the current slot */ - spin_lock(&kvm->mmu_lock); - if (!npages) - *memslot = old; - spin_unlock(&kvm->mmu_lock); -#ifdef CONFIG_DMAR - /* map the pages in iommu page table */ - r = kvm_iommu_map_pages(kvm, base_gfn, npages); - if (r) - goto out; -#endif return 0; +out_slots: + kfree(slots); out_free: - kvm_free_physmem_slot(&new, &old); + kvm_free_physmem_slot(kvm, &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) + struct kvm_userspace_memory_region *mem) { int r; - down_write(&kvm->slots_lock); - r = __kvm_set_memory_region(kvm, mem, user_alloc); - up_write(&kvm->slots_lock); + mutex_lock(&kvm->slots_lock); + r = __kvm_set_memory_region(kvm, mem); + 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) +static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, + struct kvm_userspace_memory_region *mem) { - if (mem->slot >= KVM_MEMORY_SLOTS) + if (mem->slot >= KVM_USER_MEM_SLOTS) return -EINVAL; - return kvm_set_memory_region(kvm, mem, user_alloc); + return kvm_set_memory_region(kvm, mem); } int kvm_get_dirty_log(struct kvm *kvm, @@ -719,19 +947,19 @@ int kvm_get_dirty_log(struct kvm *kvm, { struct kvm_memory_slot *memslot; int r, i; - int n; + unsigned long n; unsigned long any = 0; r = -EINVAL; - if (log->slot >= KVM_MEMORY_SLOTS) + if (log->slot >= KVM_USER_MEM_SLOTS) goto out; - memslot = &kvm->memslots[log->slot]; + memslot = id_to_memslot(kvm->memslots, log->slot); r = -ENOENT; if (!memslot->dirty_bitmap) goto out; - n = ALIGN(memslot->npages, BITS_PER_LONG) / 8; + n = kvm_dirty_bitmap_bytes(memslot); for (i = 0; !any && i < n/sizeof(long); ++i) any = memslot->dirty_bitmap[i]; @@ -747,6 +975,12 @@ int kvm_get_dirty_log(struct kvm *kvm, out: return r; } +EXPORT_SYMBOL_GPL(kvm_get_dirty_log); + +bool kvm_largepages_enabled(void) +{ + return largepages_enabled; +} void kvm_disable_largepages(void) { @@ -754,166 +988,420 @@ void kvm_disable_largepages(void) } EXPORT_SYMBOL_GPL(kvm_disable_largepages); -int is_error_page(struct page *page) +struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { - return page == bad_page; + return __gfn_to_memslot(kvm_memslots(kvm), gfn); } -EXPORT_SYMBOL_GPL(is_error_page); +EXPORT_SYMBOL_GPL(gfn_to_memslot); -int is_error_pfn(pfn_t pfn) +int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { - return pfn == bad_pfn; + struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn); + + if (!memslot || memslot->id >= KVM_USER_MEM_SLOTS || + memslot->flags & KVM_MEMSLOT_INVALID) + return 0; + + return 1; } -EXPORT_SYMBOL_GPL(is_error_pfn); +EXPORT_SYMBOL_GPL(kvm_is_visible_gfn); -static inline unsigned long bad_hva(void) +unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn) { - return PAGE_OFFSET; + 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 kvm_is_error_hva(unsigned long addr) +static bool memslot_is_readonly(struct kvm_memory_slot *slot) { - return addr == bad_hva(); + return slot->flags & KVM_MEM_READONLY; } -EXPORT_SYMBOL_GPL(kvm_is_error_hva); -struct kvm_memory_slot *gfn_to_memslot_unaliased(struct kvm *kvm, gfn_t gfn) +static unsigned long __gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn, + gfn_t *nr_pages, bool write) { - int i; + if (!slot || slot->flags & KVM_MEMSLOT_INVALID) + return KVM_HVA_ERR_BAD; - for (i = 0; i < kvm->nmemslots; ++i) { - struct kvm_memory_slot *memslot = &kvm->memslots[i]; + if (memslot_is_readonly(slot) && write) + return KVM_HVA_ERR_RO_BAD; - if (gfn >= memslot->base_gfn - && gfn < memslot->base_gfn + memslot->npages) - return memslot; - } - return NULL; + if (nr_pages) + *nr_pages = slot->npages - (gfn - slot->base_gfn); + + return __gfn_to_hva_memslot(slot, gfn); } -EXPORT_SYMBOL_GPL(gfn_to_memslot_unaliased); -struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) +static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn, + gfn_t *nr_pages) { - gfn = unalias_gfn(kvm, gfn); - return gfn_to_memslot_unaliased(kvm, gfn); + return __gfn_to_hva_many(slot, gfn, nr_pages, true); } -int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) +unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, + gfn_t gfn) { - int i; + return gfn_to_hva_many(slot, gfn, NULL); +} +EXPORT_SYMBOL_GPL(gfn_to_hva_memslot); - gfn = unalias_gfn(kvm, gfn); - for (i = 0; i < KVM_MEMORY_SLOTS; ++i) { - struct kvm_memory_slot *memslot = &kvm->memslots[i]; +unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) +{ + return gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL); +} +EXPORT_SYMBOL_GPL(gfn_to_hva); - if (gfn >= memslot->base_gfn - && gfn < memslot->base_gfn + memslot->npages) - return 1; - } - return 0; +/* + * If writable is set to false, the hva returned by this function is only + * allowed to be read. + */ +unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable) +{ + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false); + + if (!kvm_is_error_hva(hva) && writable) + *writable = !memslot_is_readonly(slot); + + return hva; } -EXPORT_SYMBOL_GPL(kvm_is_visible_gfn); -unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) +static int kvm_read_hva(void *data, void __user *hva, int len) { - struct kvm_memory_slot *slot; + return __copy_from_user(data, hva, len); +} - gfn = unalias_gfn(kvm, gfn); - slot = gfn_to_memslot_unaliased(kvm, gfn); - if (!slot) - return bad_hva(); - return (slot->userspace_addr + (gfn - slot->base_gfn) * PAGE_SIZE); +static int kvm_read_hva_atomic(void *data, void __user *hva, int len) +{ + return __copy_from_user_inatomic(data, hva, len); } -EXPORT_SYMBOL_GPL(gfn_to_hva); -pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) +static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, int write, struct page **page) +{ + int flags = FOLL_TOUCH | FOLL_NOWAIT | FOLL_HWPOISON | FOLL_GET; + + if (write) + flags |= FOLL_WRITE; + + return __get_user_pages(tsk, mm, start, 1, flags, page, NULL, NULL); +} + +static inline int check_user_page_hwpoison(unsigned long addr) +{ + int rc, flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_WRITE; + + rc = __get_user_pages(current, current->mm, addr, 1, + flags, NULL, NULL, NULL); + return rc == -EHWPOISON; +} + +/* + * The atomic path to get the writable pfn which will be stored in @pfn, + * true indicates success, otherwise false is returned. + */ +static bool hva_to_pfn_fast(unsigned long addr, bool atomic, bool *async, + bool write_fault, bool *writable, pfn_t *pfn) { struct page *page[1]; - unsigned long addr; int npages; - pfn_t pfn; - might_sleep(); + if (!(async || atomic)) + return false; - addr = gfn_to_hva(kvm, gfn); - if (kvm_is_error_hva(addr)) { - get_page(bad_page); - return page_to_pfn(bad_page); + /* + * Fast pin a writable pfn only if it is a write fault request + * or the caller allows to map a writable pfn for a read fault + * request. + */ + if (!(write_fault || writable)) + return false; + + npages = __get_user_pages_fast(addr, 1, 1, page); + if (npages == 1) { + *pfn = page_to_pfn(page[0]); + + if (writable) + *writable = true; + return true; } - npages = get_user_pages_fast(addr, 1, 1, page); + return false; +} - if (unlikely(npages != 1)) { - struct vm_area_struct *vma; +/* + * The slow path to get the pfn of the specified host virtual address, + * 1 indicates success, -errno is returned if error is detected. + */ +static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault, + bool *writable, pfn_t *pfn) +{ + struct page *page[1]; + int npages = 0; - down_read(¤t->mm->mmap_sem); - vma = find_vma(current->mm, addr); + might_sleep(); - 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); - } + if (writable) + *writable = write_fault; - pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; + if (async) { + down_read(¤t->mm->mmap_sem); + npages = get_user_page_nowait(current, current->mm, + addr, write_fault, page); up_read(¤t->mm->mmap_sem); - BUG_ON(!kvm_is_mmio_pfn(pfn)); } else - pfn = page_to_pfn(page[0]); + npages = get_user_pages_fast(addr, 1, write_fault, + page); + if (npages != 1) + return npages; + + /* map read fault as writable if possible */ + if (unlikely(!write_fault) && writable) { + struct page *wpage[1]; + + npages = __get_user_pages_fast(addr, 1, 1, wpage); + if (npages == 1) { + *writable = true; + put_page(page[0]); + page[0] = wpage[0]; + } + npages = 1; + } + *pfn = page_to_pfn(page[0]); + return npages; +} + +static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) +{ + if (unlikely(!(vma->vm_flags & VM_READ))) + return false; + + if (write_fault && (unlikely(!(vma->vm_flags & VM_WRITE)))) + return false; + + return true; +} + +/* + * Pin guest page in memory and return its pfn. + * @addr: host virtual address which maps memory to the guest + * @atomic: whether this function can sleep + * @async: whether this function need to wait IO complete if the + * host page is not in the memory + * @write_fault: whether we should get a writable host page + * @writable: whether it allows to map a writable host page for !@write_fault + * + * The function will map a writable host page for these two cases: + * 1): @write_fault = true + * 2): @write_fault = false && @writable, @writable will tell the caller + * whether the mapping is writable. + */ +static pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async, + bool write_fault, bool *writable) +{ + struct vm_area_struct *vma; + pfn_t pfn = 0; + int npages; + + /* we can do it either atomically or asynchronously, not both */ + BUG_ON(atomic && async); + + if (hva_to_pfn_fast(addr, atomic, async, write_fault, writable, &pfn)) + return pfn; + + if (atomic) + return KVM_PFN_ERR_FAULT; + + npages = hva_to_pfn_slow(addr, async, write_fault, writable, &pfn); + if (npages == 1) + return pfn; + + down_read(¤t->mm->mmap_sem); + if (npages == -EHWPOISON || + (!async && check_user_page_hwpoison(addr))) { + pfn = KVM_PFN_ERR_HWPOISON; + goto exit; + } + + vma = find_vma_intersection(current->mm, addr, addr + 1); + + if (vma == NULL) + pfn = KVM_PFN_ERR_FAULT; + else if ((vma->vm_flags & VM_PFNMAP)) { + pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) + + vma->vm_pgoff; + BUG_ON(!kvm_is_mmio_pfn(pfn)); + } else { + if (async && vma_is_valid(vma, write_fault)) + *async = true; + pfn = KVM_PFN_ERR_FAULT; + } +exit: + up_read(¤t->mm->mmap_sem); return pfn; } +static pfn_t +__gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, + bool *async, bool write_fault, bool *writable) +{ + unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault); + + if (addr == KVM_HVA_ERR_RO_BAD) + return KVM_PFN_ERR_RO_FAULT; + + if (kvm_is_error_hva(addr)) + return KVM_PFN_NOSLOT; + + /* Do not map writable pfn in the readonly memslot. */ + if (writable && memslot_is_readonly(slot)) { + *writable = false; + writable = NULL; + } + + return hva_to_pfn(addr, atomic, async, write_fault, + writable); +} + +static pfn_t __gfn_to_pfn(struct kvm *kvm, gfn_t gfn, bool atomic, bool *async, + bool write_fault, bool *writable) +{ + struct kvm_memory_slot *slot; + + if (async) + *async = false; + + slot = gfn_to_memslot(kvm, gfn); + + return __gfn_to_pfn_memslot(slot, gfn, atomic, async, write_fault, + writable); +} + +pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) +{ + return __gfn_to_pfn(kvm, gfn, true, NULL, true, NULL); +} +EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic); + +pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async, + bool write_fault, bool *writable) +{ + return __gfn_to_pfn(kvm, gfn, false, async, write_fault, writable); +} +EXPORT_SYMBOL_GPL(gfn_to_pfn_async); + +pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) +{ + return __gfn_to_pfn(kvm, gfn, false, NULL, true, NULL); +} EXPORT_SYMBOL_GPL(gfn_to_pfn); +pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, + bool *writable) +{ + return __gfn_to_pfn(kvm, gfn, false, NULL, write_fault, writable); +} +EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); + +pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +{ + return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL); +} + +pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) +{ + return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL); +} +EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic); + +int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages, + int nr_pages) +{ + unsigned long addr; + gfn_t entry; + + addr = gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, &entry); + if (kvm_is_error_hva(addr)) + return -1; + + if (entry < nr_pages) + return 0; + + return __get_user_pages_fast(addr, nr_pages, 1, pages); +} +EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic); + +static struct page *kvm_pfn_to_page(pfn_t pfn) +{ + if (is_error_noslot_pfn(pfn)) + return KVM_ERR_PTR_BAD_PAGE; + + if (kvm_is_mmio_pfn(pfn)) { + WARN_ON(1); + return KVM_ERR_PTR_BAD_PAGE; + } + + return pfn_to_page(pfn); +} + 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; + return kvm_pfn_to_page(pfn); } EXPORT_SYMBOL_GPL(gfn_to_page); void kvm_release_page_clean(struct page *page) { + WARN_ON(is_error_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)) + if (!is_error_noslot_pfn(pfn) && !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) { + WARN_ON(is_error_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) +static 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) { @@ -953,10 +1441,10 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int r; unsigned long addr; - addr = gfn_to_hva(kvm, gfn); + addr = gfn_to_hva_prot(kvm, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; - r = copy_from_user(data, (void __user *)addr + offset, len); + r = kvm_read_hva(data, (void __user *)addr + offset, len); if (r) return -EFAULT; return 0; @@ -991,11 +1479,11 @@ int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, gfn_t gfn = gpa >> PAGE_SHIFT; int offset = offset_in_page(gpa); - addr = gfn_to_hva(kvm, gfn); + addr = gfn_to_hva_prot(kvm, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; pagefault_disable(); - r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len); + r = kvm_read_hva_atomic(data, (void __user *)addr + offset, len); pagefault_enable(); if (r) return -EFAULT; @@ -1012,7 +1500,7 @@ int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, addr = gfn_to_hva(kvm, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; - r = copy_to_user((void __user *)addr + offset, data, len); + r = __copy_to_user((void __user *)addr + offset, data, len); if (r) return -EFAULT; mark_page_dirty(kvm, gfn); @@ -1040,9 +1528,99 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, return 0; } +int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + gpa_t gpa, unsigned long len) +{ + struct kvm_memslots *slots = kvm_memslots(kvm); + int offset = offset_in_page(gpa); + gfn_t start_gfn = gpa >> PAGE_SHIFT; + gfn_t end_gfn = (gpa + len - 1) >> PAGE_SHIFT; + gfn_t nr_pages_needed = end_gfn - start_gfn + 1; + gfn_t nr_pages_avail; + + ghc->gpa = gpa; + ghc->generation = slots->generation; + ghc->len = len; + ghc->memslot = gfn_to_memslot(kvm, start_gfn); + ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail); + if (!kvm_is_error_hva(ghc->hva) && nr_pages_avail >= nr_pages_needed) { + ghc->hva += offset; + } else { + /* + * If the requested region crosses two memslots, we still + * verify that the entire region is valid here. + */ + while (start_gfn <= end_gfn) { + ghc->memslot = gfn_to_memslot(kvm, start_gfn); + ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, + &nr_pages_avail); + if (kvm_is_error_hva(ghc->hva)) + return -EFAULT; + start_gfn += nr_pages_avail; + } + /* Use the slow path for cross page reads and writes. */ + ghc->memslot = NULL; + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init); + +int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + void *data, unsigned long len) +{ + struct kvm_memslots *slots = kvm_memslots(kvm); + int r; + + BUG_ON(len > ghc->len); + + if (slots->generation != ghc->generation) + kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len); + + if (unlikely(!ghc->memslot)) + return kvm_write_guest(kvm, ghc->gpa, data, len); + + if (kvm_is_error_hva(ghc->hva)) + return -EFAULT; + + r = __copy_to_user((void __user *)ghc->hva, data, len); + if (r) + return -EFAULT; + mark_page_dirty_in_slot(kvm, ghc->memslot, ghc->gpa >> PAGE_SHIFT); + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_write_guest_cached); + +int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, + void *data, unsigned long len) +{ + struct kvm_memslots *slots = kvm_memslots(kvm); + int r; + + BUG_ON(len > ghc->len); + + if (slots->generation != ghc->generation) + kvm_gfn_to_hva_cache_init(kvm, ghc, ghc->gpa, ghc->len); + + if (unlikely(!ghc->memslot)) + return kvm_read_guest(kvm, ghc->gpa, data, len); + + if (kvm_is_error_hva(ghc->hva)) + return -EFAULT; + + r = __copy_from_user(data, (void __user *)ghc->hva, len); + if (r) + return -EFAULT; + + return 0; +} +EXPORT_SYMBOL_GPL(kvm_read_guest_cached); + 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); + const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0))); + + return kvm_write_guest_page(kvm, gfn, zero_page, offset, len); } EXPORT_SYMBOL_GPL(kvm_clear_guest_page); @@ -1065,21 +1643,26 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) } EXPORT_SYMBOL_GPL(kvm_clear_guest); -void mark_page_dirty(struct kvm *kvm, gfn_t gfn) +static void mark_page_dirty_in_slot(struct kvm *kvm, + struct kvm_memory_slot *memslot, + gfn_t gfn) { - struct kvm_memory_slot *memslot; - - gfn = unalias_gfn(kvm, gfn); - memslot = gfn_to_memslot_unaliased(kvm, gfn); if (memslot && memslot->dirty_bitmap) { unsigned long rel_gfn = gfn - memslot->base_gfn; - /* avoid RMW */ - if (!generic_test_le_bit(rel_gfn, memslot->dirty_bitmap)) - generic___set_le_bit(rel_gfn, memslot->dirty_bitmap); + set_bit_le(rel_gfn, memslot->dirty_bitmap); } } +void mark_page_dirty(struct kvm *kvm, gfn_t gfn) +{ + struct kvm_memory_slot *memslot; + + memslot = gfn_to_memslot(kvm, gfn); + mark_page_dirty_in_slot(kvm, memslot, gfn); +} +EXPORT_SYMBOL_GPL(mark_page_dirty); + /* * The vCPU has executed a HLT instruction with in-kernel mode enabled. */ @@ -1091,7 +1674,7 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); if (kvm_arch_vcpu_runnable(vcpu)) { - set_bit(KVM_REQ_UNHALT, &vcpu->requests); + kvm_make_request(KVM_REQ_UNHALT, vcpu); break; } if (kvm_cpu_has_pending_timer(vcpu)) @@ -1104,27 +1687,146 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) finish_wait(&vcpu->wq, &wait); } +EXPORT_SYMBOL_GPL(kvm_vcpu_block); -void kvm_resched(struct kvm_vcpu *vcpu) +#ifndef CONFIG_S390 +/* + * Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode. + */ +void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { - if (!need_resched()) - return; - cond_resched(); + int me; + int cpu = vcpu->cpu; + wait_queue_head_t *wqp; + + wqp = kvm_arch_vcpu_wq(vcpu); + if (waitqueue_active(wqp)) { + wake_up_interruptible(wqp); + ++vcpu->stat.halt_wakeup; + } + + me = get_cpu(); + if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) + if (kvm_arch_vcpu_should_kick(vcpu)) + smp_send_reschedule(cpu); + put_cpu(); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_kick); +#endif /* !CONFIG_S390 */ + +int kvm_vcpu_yield_to(struct kvm_vcpu *target) +{ + struct pid *pid; + struct task_struct *task = NULL; + int ret = 0; + + rcu_read_lock(); + pid = rcu_dereference(target->pid); + if (pid) + task = get_pid_task(target->pid, PIDTYPE_PID); + rcu_read_unlock(); + if (!task) + return ret; + if (task->flags & PF_VCPU) { + put_task_struct(task); + return ret; + } + ret = yield_to(task, 1); + put_task_struct(task); + + return ret; } -EXPORT_SYMBOL_GPL(kvm_resched); +EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to); -void kvm_vcpu_on_spin(struct kvm_vcpu *vcpu) +/* + * Helper that checks whether a VCPU is eligible for directed yield. + * Most eligible candidate to yield is decided by following heuristics: + * + * (a) VCPU which has not done pl-exit or cpu relax intercepted recently + * (preempted lock holder), indicated by @in_spin_loop. + * Set at the beiginning and cleared at the end of interception/PLE handler. + * + * (b) VCPU which has done pl-exit/ cpu relax intercepted but did not get + * chance last time (mostly it has become eligible now since we have probably + * yielded to lockholder in last iteration. This is done by toggling + * @dy_eligible each time a VCPU checked for eligibility.) + * + * Yielding to a recently pl-exited/cpu relax intercepted VCPU before yielding + * to preempted lock-holder could result in wrong VCPU selection and CPU + * burning. Giving priority for a potential lock-holder increases lock + * progress. + * + * Since algorithm is based on heuristics, accessing another VCPU data without + * locking does not harm. It may result in trying to yield to same VCPU, fail + * and continue with next VCPU and so on. + */ +static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu) { - ktime_t expires; - DEFINE_WAIT(wait); +#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT + bool eligible; - prepare_to_wait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); + eligible = !vcpu->spin_loop.in_spin_loop || + (vcpu->spin_loop.in_spin_loop && + vcpu->spin_loop.dy_eligible); - /* Sleep for 100 us, and hope lock-holder got scheduled */ - expires = ktime_add_ns(ktime_get(), 100000UL); - schedule_hrtimeout(&expires, HRTIMER_MODE_ABS); + if (vcpu->spin_loop.in_spin_loop) + kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible); - finish_wait(&vcpu->wq, &wait); + return eligible; +#else + return true; +#endif +} + +void kvm_vcpu_on_spin(struct kvm_vcpu *me) +{ + struct kvm *kvm = me->kvm; + struct kvm_vcpu *vcpu; + int last_boosted_vcpu = me->kvm->last_boosted_vcpu; + int yielded = 0; + int try = 3; + int pass; + int i; + + kvm_vcpu_set_in_spin_loop(me, true); + /* + * We boost the priority of a VCPU that is runnable but not + * currently running, because it got preempted by something + * else and called schedule in __vcpu_run. Hopefully that + * VCPU is holding the lock that we need and will release it. + * We approximate round-robin by starting at the last boosted VCPU. + */ + for (pass = 0; pass < 2 && !yielded && try; pass++) { + kvm_for_each_vcpu(i, vcpu, kvm) { + if (!pass && i <= last_boosted_vcpu) { + i = last_boosted_vcpu; + continue; + } else if (pass && i > last_boosted_vcpu) + break; + if (!ACCESS_ONCE(vcpu->preempted)) + continue; + if (vcpu == me) + continue; + if (waitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) + continue; + if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) + continue; + + yielded = kvm_vcpu_yield_to(vcpu); + if (yielded > 0) { + kvm->last_boosted_vcpu = i; + break; + } else if (yielded < 0) { + try--; + if (!try) + break; + } + } + } + kvm_vcpu_set_in_spin_loop(me, false); + + /* Ensure vcpu is not eligible during next spinloop */ + kvm_vcpu_set_dy_eligible(me, false); } EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); @@ -1144,7 +1846,7 @@ static int kvm_vcpu_fault(struct vm_area_struct *vma, struct vm_fault *vmf) page = virt_to_page(vcpu->kvm->coalesced_mmio_ring); #endif else - return VM_FAULT_SIGBUS; + return kvm_arch_vcpu_fault(vcpu, vmf); get_page(page); vmf->page = page; return 0; @@ -1171,8 +1873,11 @@ static int kvm_vcpu_release(struct inode *inode, struct file *filp) static struct file_operations kvm_vcpu_fops = { .release = kvm_vcpu_release, .unlocked_ioctl = kvm_vcpu_ioctl, - .compat_ioctl = kvm_vcpu_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = kvm_vcpu_compat_ioctl, +#endif .mmap = kvm_vcpu_mmap, + .llseek = noop_llseek, }; /* @@ -1180,7 +1885,7 @@ static struct file_operations kvm_vcpu_fops = { */ static int create_vcpu_fd(struct kvm_vcpu *vcpu) { - return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR); + return anon_inode_getfd("kvm-vcpu", &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC); } /* @@ -1191,6 +1896,9 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) int r; struct kvm_vcpu *vcpu, *v; + if (id >= KVM_MAX_VCPUS) + return -EINVAL; + vcpu = kvm_arch_vcpu_create(kvm, id); if (IS_ERR(vcpu)) return PTR_ERR(vcpu); @@ -1199,18 +1907,22 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) r = kvm_arch_vcpu_setup(vcpu); if (r) - return r; + goto vcpu_destroy; mutex_lock(&kvm->lock); + if (!kvm_vcpu_compatible(vcpu)) { + r = -EINVAL; + goto unlock_vcpu_destroy; + } if (atomic_read(&kvm->online_vcpus) == KVM_MAX_VCPUS) { r = -EINVAL; - goto vcpu_destroy; + goto unlock_vcpu_destroy; } kvm_for_each_vcpu(r, v, kvm) if (v->vcpu_id == id) { r = -EEXIST; - goto vcpu_destroy; + goto unlock_vcpu_destroy; } BUG_ON(kvm->vcpus[atomic_read(&kvm->online_vcpus)]); @@ -1220,22 +1932,20 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) r = create_vcpu_fd(vcpu); if (r < 0) { kvm_put_kvm(kvm); - goto vcpu_destroy; + goto unlock_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); + kvm_arch_vcpu_postcreate(vcpu); return r; -vcpu_destroy: +unlock_vcpu_destroy: mutex_unlock(&kvm->lock); +vcpu_destroy: kvm_arch_vcpu_destroy(vcpu); return r; } @@ -1262,12 +1972,27 @@ static long kvm_vcpu_ioctl(struct file *filp, if (vcpu->kvm->mm != current->mm) return -EIO; + +#if defined(CONFIG_S390) || defined(CONFIG_PPC) || defined(CONFIG_MIPS) + /* + * 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 + + + r = vcpu_load(vcpu); + if (r) + return r; switch (ioctl) { case KVM_RUN: r = -EINVAL; if (arg) goto out; r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run); + trace_kvm_userspace_exit(vcpu->run->exit_reason, r); break; case KVM_GET_REGS: { struct kvm_regs *kvm_regs; @@ -1291,17 +2016,12 @@ out_free1: struct kvm_regs *kvm_regs; r = -ENOMEM; - kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL); - if (!kvm_regs) + kvm_regs = memdup_user(argp, sizeof(*kvm_regs)); + if (IS_ERR(kvm_regs)) { + r = PTR_ERR(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; } @@ -1320,17 +2040,13 @@ out_free2: 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))) + kvm_sregs = memdup_user(argp, sizeof(*kvm_sregs)); + if (IS_ERR(kvm_sregs)) { + r = PTR_ERR(kvm_sregs); + kvm_sregs = NULL; goto out; + } r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, kvm_sregs); - if (r) - goto out; - r = 0; break; } case KVM_GET_MP_STATE: { @@ -1352,9 +2068,6 @@ out_free2: 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: { @@ -1379,9 +2092,6 @@ out_free2: 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: { @@ -1404,7 +2114,7 @@ out_free2: goto out; p = &sigset; } - r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset); + r = kvm_vcpu_ioctl_set_sigmask(vcpu, p); break; } case KVM_GET_FPU: { @@ -1422,28 +2132,198 @@ out_free2: 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))) + fpu = memdup_user(argp, sizeof(*fpu)); + if (IS_ERR(fpu)) { + r = PTR_ERR(fpu); + fpu = NULL; 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; } +#ifdef CONFIG_COMPAT +static long kvm_vcpu_compat_ioctl(struct file *filp, + unsigned int ioctl, unsigned long arg) +{ + struct kvm_vcpu *vcpu = filp->private_data; + void __user *argp = compat_ptr(arg); + int r; + + if (vcpu->kvm->mm != current->mm) + return -EIO; + + switch (ioctl) { + case KVM_SET_SIGNAL_MASK: { + struct kvm_signal_mask __user *sigmask_arg = argp; + struct kvm_signal_mask kvm_sigmask; + compat_sigset_t csigset; + sigset_t sigset; + + if (argp) { + r = -EFAULT; + if (copy_from_user(&kvm_sigmask, argp, + sizeof kvm_sigmask)) + goto out; + r = -EINVAL; + if (kvm_sigmask.len != sizeof csigset) + goto out; + r = -EFAULT; + if (copy_from_user(&csigset, sigmask_arg->sigset, + sizeof csigset)) + goto out; + sigset_from_compat(&sigset, &csigset); + r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset); + } else + r = kvm_vcpu_ioctl_set_sigmask(vcpu, NULL); + break; + } + default: + r = kvm_vcpu_ioctl(filp, ioctl, arg); + } + +out: + return r; +} +#endif + +static int kvm_device_ioctl_attr(struct kvm_device *dev, + int (*accessor)(struct kvm_device *dev, + struct kvm_device_attr *attr), + unsigned long arg) +{ + struct kvm_device_attr attr; + + if (!accessor) + return -EPERM; + + if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) + return -EFAULT; + + return accessor(dev, &attr); +} + +static long kvm_device_ioctl(struct file *filp, unsigned int ioctl, + unsigned long arg) +{ + struct kvm_device *dev = filp->private_data; + + switch (ioctl) { + case KVM_SET_DEVICE_ATTR: + return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg); + case KVM_GET_DEVICE_ATTR: + return kvm_device_ioctl_attr(dev, dev->ops->get_attr, arg); + case KVM_HAS_DEVICE_ATTR: + return kvm_device_ioctl_attr(dev, dev->ops->has_attr, arg); + default: + if (dev->ops->ioctl) + return dev->ops->ioctl(dev, ioctl, arg); + + return -ENOTTY; + } +} + +static int kvm_device_release(struct inode *inode, struct file *filp) +{ + struct kvm_device *dev = filp->private_data; + struct kvm *kvm = dev->kvm; + + kvm_put_kvm(kvm); + return 0; +} + +static const struct file_operations kvm_device_fops = { + .unlocked_ioctl = kvm_device_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = kvm_device_ioctl, +#endif + .release = kvm_device_release, +}; + +struct kvm_device *kvm_device_from_filp(struct file *filp) +{ + if (filp->f_op != &kvm_device_fops) + return NULL; + + return filp->private_data; +} + +static int kvm_ioctl_create_device(struct kvm *kvm, + struct kvm_create_device *cd) +{ + struct kvm_device_ops *ops = NULL; + struct kvm_device *dev; + bool test = cd->flags & KVM_CREATE_DEVICE_TEST; + int ret; + + switch (cd->type) { +#ifdef CONFIG_KVM_MPIC + case KVM_DEV_TYPE_FSL_MPIC_20: + case KVM_DEV_TYPE_FSL_MPIC_42: + ops = &kvm_mpic_ops; + break; +#endif +#ifdef CONFIG_KVM_XICS + case KVM_DEV_TYPE_XICS: + ops = &kvm_xics_ops; + break; +#endif +#ifdef CONFIG_KVM_VFIO + case KVM_DEV_TYPE_VFIO: + ops = &kvm_vfio_ops; + break; +#endif +#ifdef CONFIG_KVM_ARM_VGIC + case KVM_DEV_TYPE_ARM_VGIC_V2: + ops = &kvm_arm_vgic_v2_ops; + break; +#endif +#ifdef CONFIG_S390 + case KVM_DEV_TYPE_FLIC: + ops = &kvm_flic_ops; + break; +#endif + default: + return -ENODEV; + } + + if (test) + return 0; + + dev = kzalloc(sizeof(*dev), GFP_KERNEL); + if (!dev) + return -ENOMEM; + + dev->ops = ops; + dev->kvm = kvm; + + ret = ops->create(dev, cd->type); + if (ret < 0) { + kfree(dev); + return ret; + } + + ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); + if (ret < 0) { + ops->destroy(dev); + return ret; + } + + list_add(&dev->vm_node, &kvm->devices); + kvm_get_kvm(kvm); + cd->fd = ret; + return 0; +} + static long kvm_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { @@ -1456,8 +2336,6 @@ static long kvm_vm_ioctl(struct file *filp, 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; @@ -1467,9 +2345,7 @@ static long kvm_vm_ioctl(struct file *filp, sizeof kvm_userspace_mem)) goto out; - r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem, 1); - if (r) - goto out; + r = kvm_vm_ioctl_set_memory_region(kvm, &kvm_userspace_mem); break; } case KVM_GET_DIRTY_LOG: { @@ -1479,8 +2355,6 @@ static long kvm_vm_ioctl(struct file *filp, 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 @@ -1489,11 +2363,7 @@ static long kvm_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&zone, argp, sizeof zone)) goto out; - r = -ENXIO; r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone); - if (r) - goto out; - r = 0; break; } case KVM_UNREGISTER_COALESCED_MMIO: { @@ -1501,11 +2371,7 @@ static long kvm_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&zone, argp, sizeof zone)) goto out; - r = -ENXIO; r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone); - if (r) - goto out; - r = 0; break; } #endif @@ -1515,7 +2381,7 @@ static long kvm_vm_ioctl(struct file *filp, r = -EFAULT; if (copy_from_user(&data, argp, sizeof data)) goto out; - r = kvm_irqfd(kvm, data.fd, data.gsi, data.flags); + r = kvm_irqfd(kvm, &data); break; } case KVM_IOEVENTFD: { @@ -1538,6 +2404,89 @@ static long kvm_vm_ioctl(struct file *filp, mutex_unlock(&kvm->lock); break; #endif +#ifdef CONFIG_HAVE_KVM_MSI + case KVM_SIGNAL_MSI: { + struct kvm_msi msi; + + r = -EFAULT; + if (copy_from_user(&msi, argp, sizeof msi)) + goto out; + r = kvm_send_userspace_msi(kvm, &msi); + break; + } +#endif +#ifdef __KVM_HAVE_IRQ_LINE + case KVM_IRQ_LINE_STATUS: + case KVM_IRQ_LINE: { + struct kvm_irq_level irq_event; + + r = -EFAULT; + if (copy_from_user(&irq_event, argp, sizeof irq_event)) + goto out; + + r = kvm_vm_ioctl_irq_line(kvm, &irq_event, + ioctl == KVM_IRQ_LINE_STATUS); + if (r) + goto out; + + r = -EFAULT; + if (ioctl == KVM_IRQ_LINE_STATUS) { + if (copy_to_user(argp, &irq_event, sizeof irq_event)) + goto out; + } + + r = 0; + break; + } +#endif +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING + case KVM_SET_GSI_ROUTING: { + struct kvm_irq_routing routing; + struct kvm_irq_routing __user *urouting; + struct kvm_irq_routing_entry *entries; + + r = -EFAULT; + if (copy_from_user(&routing, argp, sizeof(routing))) + goto out; + r = -EINVAL; + if (routing.nr >= KVM_MAX_IRQ_ROUTES) + goto out; + if (routing.flags) + goto out; + r = -ENOMEM; + entries = vmalloc(routing.nr * sizeof(*entries)); + if (!entries) + goto out; + r = -EFAULT; + urouting = argp; + if (copy_from_user(entries, urouting->entries, + routing.nr * sizeof(*entries))) + goto out_free_irq_routing; + r = kvm_set_irq_routing(kvm, entries, routing.nr, + routing.flags); + out_free_irq_routing: + vfree(entries); + break; + } +#endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */ + case KVM_CREATE_DEVICE: { + struct kvm_create_device cd; + + r = -EFAULT; + if (copy_from_user(&cd, argp, sizeof(cd))) + goto out; + + r = kvm_ioctl_create_device(kvm, &cd); + if (r) + goto out; + + r = -EFAULT; + if (copy_to_user(argp, &cd, sizeof(cd))) + goto out; + + r = 0; + break; + } default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); if (r == -ENOTTY) @@ -1580,8 +2529,6 @@ static long kvm_vm_compat_ioctl(struct file *filp, log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); r = kvm_vm_ioctl_get_dirty_log(kvm, &log); - if (r) - goto out; break; } default: @@ -1593,59 +2540,35 @@ out: } #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, + .llseek = noop_llseek, }; -static int kvm_dev_ioctl_create_vm(void) +static int kvm_dev_ioctl_create_vm(unsigned long type) { - int fd; + int r; struct kvm *kvm; - kvm = kvm_create_vm(); + kvm = kvm_create_vm(type); if (IS_ERR(kvm)) return PTR_ERR(kvm); - fd = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR); - if (fd < 0) +#ifdef KVM_COALESCED_MMIO_PAGE_OFFSET + r = kvm_coalesced_mmio_init(kvm); + if (r < 0) { + kvm_put_kvm(kvm); + return r; + } +#endif + r = anon_inode_getfd("kvm-vm", &kvm_vm_fops, kvm, O_RDWR | O_CLOEXEC); + if (r < 0) kvm_put_kvm(kvm); - return fd; + return r; } static long kvm_dev_ioctl_check_extension_generic(long arg) @@ -1658,8 +2581,14 @@ static long kvm_dev_ioctl_check_extension_generic(long arg) case KVM_CAP_SET_BOOT_CPU_ID: #endif case KVM_CAP_INTERNAL_ERROR_DATA: +#ifdef CONFIG_HAVE_KVM_MSI + case KVM_CAP_SIGNAL_MSI: +#endif +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING + case KVM_CAP_IRQFD_RESAMPLE: +#endif return 1; -#ifdef CONFIG_HAVE_KVM_IRQCHIP +#ifdef CONFIG_HAVE_KVM_IRQ_ROUTING case KVM_CAP_IRQ_ROUTING: return KVM_MAX_IRQ_ROUTES; #endif @@ -1682,10 +2611,7 @@ static long kvm_dev_ioctl(struct file *filp, r = KVM_API_VERSION; break; case KVM_CREATE_VM: - r = -EINVAL; - if (arg) - goto out; - r = kvm_dev_ioctl_create_vm(); + r = kvm_dev_ioctl_create_vm(arg); break; case KVM_CHECK_EXTENSION: r = kvm_dev_ioctl_check_extension_generic(arg); @@ -1717,6 +2643,7 @@ out: static struct file_operations kvm_chardev_ops = { .unlocked_ioctl = kvm_dev_ioctl, .compat_ioctl = kvm_dev_ioctl, + .llseek = noop_llseek, }; static struct miscdevice kvm_dev = { @@ -1725,7 +2652,7 @@ static struct miscdevice kvm_dev = { &kvm_chardev_ops, }; -static void hardware_enable(void *junk) +static void hardware_enable_nolock(void *junk) { int cpu = raw_smp_processor_id(); int r; @@ -1745,7 +2672,15 @@ static void hardware_enable(void *junk) } } -static void hardware_disable(void *junk) +static void hardware_enable(void) +{ + raw_spin_lock(&kvm_count_lock); + if (kvm_usage_count) + hardware_enable_nolock(NULL); + raw_spin_unlock(&kvm_count_lock); +} + +static void hardware_disable_nolock(void *junk) { int cpu = raw_smp_processor_id(); @@ -1755,32 +2690,40 @@ static void hardware_disable(void *junk) kvm_arch_hardware_disable(NULL); } +static void hardware_disable(void) +{ + raw_spin_lock(&kvm_count_lock); + if (kvm_usage_count) + hardware_disable_nolock(NULL); + raw_spin_unlock(&kvm_count_lock); +} + 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); + on_each_cpu(hardware_disable_nolock, NULL, 1); } static void hardware_disable_all(void) { - spin_lock(&kvm_lock); + raw_spin_lock(&kvm_count_lock); hardware_disable_all_nolock(); - spin_unlock(&kvm_lock); + raw_spin_unlock(&kvm_count_lock); } static int hardware_enable_all(void) { int r = 0; - spin_lock(&kvm_lock); + raw_spin_lock(&kvm_count_lock); kvm_usage_count++; if (kvm_usage_count == 1) { atomic_set(&hardware_enable_failed, 0); - on_each_cpu(hardware_enable, NULL, 1); + on_each_cpu(hardware_enable_nolock, NULL, 1); if (atomic_read(&hardware_enable_failed)) { hardware_disable_all_nolock(); @@ -1788,7 +2731,7 @@ static int hardware_enable_all(void) } } - spin_unlock(&kvm_lock); + raw_spin_unlock(&kvm_count_lock); return r; } @@ -1798,42 +2741,22 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, { 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); + hardware_disable(); break; - case CPU_UP_CANCELED: - printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n", - cpu); - smp_call_function_single(cpu, hardware_disable, NULL, 1); - break; - case CPU_ONLINE: + case CPU_STARTING: printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n", cpu); - smp_call_function_single(cpu, hardware_enable, NULL, 1); + hardware_enable(); 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) { @@ -1845,7 +2768,7 @@ static int kvm_reboot(struct notifier_block *notifier, unsigned long val, */ printk(KERN_INFO "kvm: exiting hardware virtualization\n"); kvm_rebooting = true; - on_each_cpu(hardware_disable, NULL, 1); + on_each_cpu(hardware_disable_nolock, NULL, 1); return NOTIFY_OK; } @@ -1854,92 +2777,239 @@ static struct notifier_block kvm_reboot_notifier = { .priority = 0, }; -void kvm_io_bus_init(struct kvm_io_bus *bus) -{ - memset(bus, 0, sizeof(*bus)); -} - -void kvm_io_bus_destroy(struct kvm_io_bus *bus) +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]; + struct kvm_io_device *pos = bus->range[i].dev; kvm_iodevice_destructor(pos); } + kfree(bus); +} + +static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1, + const struct kvm_io_range *r2) +{ + if (r1->addr < r2->addr) + return -1; + if (r1->addr + r1->len > r2->addr + r2->len) + return 1; + return 0; +} + +static int kvm_io_bus_sort_cmp(const void *p1, const void *p2) +{ + return kvm_io_bus_cmp(p1, p2); +} + +static int kvm_io_bus_insert_dev(struct kvm_io_bus *bus, struct kvm_io_device *dev, + gpa_t addr, int len) +{ + bus->range[bus->dev_count++] = (struct kvm_io_range) { + .addr = addr, + .len = len, + .dev = dev, + }; + + sort(bus->range, bus->dev_count, sizeof(struct kvm_io_range), + kvm_io_bus_sort_cmp, NULL); + + return 0; +} + +static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus, + gpa_t addr, int len) +{ + struct kvm_io_range *range, key; + int off; + + key = (struct kvm_io_range) { + .addr = addr, + .len = len, + }; + + range = bsearch(&key, bus->range, bus->dev_count, + sizeof(struct kvm_io_range), kvm_io_bus_sort_cmp); + if (range == NULL) + return -ENOENT; + + off = range - bus->range; + + while (off > 0 && kvm_io_bus_cmp(&key, &bus->range[off-1]) == 0) + off--; + + return off; +} + +static int __kvm_io_bus_write(struct kvm_io_bus *bus, + struct kvm_io_range *range, const void *val) +{ + int idx; + + idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len); + if (idx < 0) + return -EOPNOTSUPP; + + while (idx < bus->dev_count && + kvm_io_bus_cmp(range, &bus->range[idx]) == 0) { + if (!kvm_iodevice_write(bus->range[idx].dev, range->addr, + range->len, val)) + return idx; + idx++; + } + + return -EOPNOTSUPP; } /* kvm_io_bus_write - called under kvm->slots_lock */ -int kvm_io_bus_write(struct kvm_io_bus *bus, gpa_t addr, +int kvm_io_bus_write(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val) { - int i; - for (i = 0; i < bus->dev_count; i++) - if (!kvm_iodevice_write(bus->devs[i], addr, len, val)) - return 0; - return -EOPNOTSUPP; + struct kvm_io_bus *bus; + struct kvm_io_range range; + int r; + + range = (struct kvm_io_range) { + .addr = addr, + .len = len, + }; + + bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); + r = __kvm_io_bus_write(bus, &range, val); + return r < 0 ? r : 0; } -/* kvm_io_bus_read - called under kvm->slots_lock */ -int kvm_io_bus_read(struct kvm_io_bus *bus, gpa_t addr, int len, void *val) +/* kvm_io_bus_write_cookie - called under kvm->slots_lock */ +int kvm_io_bus_write_cookie(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, + int len, const void *val, long cookie) { - int i; - for (i = 0; i < bus->dev_count; i++) - if (!kvm_iodevice_read(bus->devs[i], addr, len, val)) - return 0; - return -EOPNOTSUPP; + struct kvm_io_bus *bus; + struct kvm_io_range range; + + range = (struct kvm_io_range) { + .addr = addr, + .len = len, + }; + + bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); + + /* First try the device referenced by cookie. */ + if ((cookie >= 0) && (cookie < bus->dev_count) && + (kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0)) + if (!kvm_iodevice_write(bus->range[cookie].dev, addr, len, + val)) + return cookie; + + /* + * cookie contained garbage; fall back to search and return the + * correct cookie value. + */ + return __kvm_io_bus_write(bus, &range, val); } -int kvm_io_bus_register_dev(struct kvm *kvm, struct kvm_io_bus *bus, - struct kvm_io_device *dev) +static int __kvm_io_bus_read(struct kvm_io_bus *bus, struct kvm_io_range *range, + void *val) { - int ret; + int idx; - down_write(&kvm->slots_lock); - ret = __kvm_io_bus_register_dev(bus, dev); - up_write(&kvm->slots_lock); + idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len); + if (idx < 0) + return -EOPNOTSUPP; - return ret; + while (idx < bus->dev_count && + kvm_io_bus_cmp(range, &bus->range[idx]) == 0) { + if (!kvm_iodevice_read(bus->range[idx].dev, range->addr, + range->len, val)) + return idx; + idx++; + } + + return -EOPNOTSUPP; } +EXPORT_SYMBOL_GPL(kvm_io_bus_write); -/* An unlocked version. Caller must have write lock on slots_lock. */ -int __kvm_io_bus_register_dev(struct kvm_io_bus *bus, - struct kvm_io_device *dev) +/* 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) { - if (bus->dev_count > NR_IOBUS_DEVS-1) - return -ENOSPC; + struct kvm_io_bus *bus; + struct kvm_io_range range; + int r; - bus->devs[bus->dev_count++] = dev; + range = (struct kvm_io_range) { + .addr = addr, + .len = len, + }; - return 0; + bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); + r = __kvm_io_bus_read(bus, &range, val); + return r < 0 ? r : 0; } -void kvm_io_bus_unregister_dev(struct kvm *kvm, - struct kvm_io_bus *bus, - struct kvm_io_device *dev) + +/* Caller must hold slots_lock. */ +int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, + int len, struct kvm_io_device *dev) { - down_write(&kvm->slots_lock); - __kvm_io_bus_unregister_dev(bus, dev); - up_write(&kvm->slots_lock); + struct kvm_io_bus *new_bus, *bus; + + bus = kvm->buses[bus_idx]; + /* exclude ioeventfd which is limited by maximum fd */ + if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1) + return -ENOSPC; + + new_bus = kzalloc(sizeof(*bus) + ((bus->dev_count + 1) * + sizeof(struct kvm_io_range)), GFP_KERNEL); + if (!new_bus) + return -ENOMEM; + memcpy(new_bus, bus, sizeof(*bus) + (bus->dev_count * + sizeof(struct kvm_io_range))); + kvm_io_bus_insert_dev(new_bus, dev, addr, len); + rcu_assign_pointer(kvm->buses[bus_idx], new_bus); + synchronize_srcu_expedited(&kvm->srcu); + kfree(bus); + + return 0; } -/* An unlocked version. Caller must have write lock on slots_lock. */ -void __kvm_io_bus_unregister_dev(struct kvm_io_bus *bus, - struct kvm_io_device *dev) +/* 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; + int i, r; + struct kvm_io_bus *new_bus, *bus; + bus = kvm->buses[bus_idx]; + r = -ENOENT; for (i = 0; i < bus->dev_count; i++) - if (bus->devs[i] == dev) { - bus->devs[i] = bus->devs[--bus->dev_count]; + if (bus->range[i].dev == dev) { + r = 0; break; } + + if (r) + return r; + + new_bus = kzalloc(sizeof(*bus) + ((bus->dev_count - 1) * + sizeof(struct kvm_io_range)), GFP_KERNEL); + if (!new_bus) + return -ENOMEM; + + memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range)); + new_bus->dev_count--; + memcpy(new_bus->range + i, bus->range + i + 1, + (new_bus->dev_count - i) * sizeof(struct kvm_io_range)); + + 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) @@ -1981,15 +3051,29 @@ static const struct file_operations *stat_fops[] = { [KVM_STAT_VM] = &vm_stat_fops, }; -static void kvm_init_debug(void) +static int kvm_init_debug(void) { + int r = -EEXIST; struct kvm_stats_debugfs_item *p; kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); - for (p = debugfs_entries; p->name; ++p) + if (kvm_debugfs_dir == NULL) + goto out; + + 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]); + if (p->dentry == NULL) + goto out_dir; + } + + return 0; + +out_dir: + debugfs_remove_recursive(kvm_debugfs_dir); +out: + return r; } static void kvm_exit_debug(void) @@ -2001,34 +3085,26 @@ static void kvm_exit_debug(void) debugfs_remove(kvm_debugfs_dir); } -static int kvm_suspend(struct sys_device *dev, pm_message_t state) +static int kvm_suspend(void) { if (kvm_usage_count) - hardware_disable(NULL); + hardware_disable_nolock(NULL); return 0; } -static int kvm_resume(struct sys_device *dev) +static void kvm_resume(void) { - if (kvm_usage_count) - hardware_enable(NULL); - return 0; + if (kvm_usage_count) { + WARN_ON(raw_spin_is_locked(&kvm_count_lock)); + hardware_enable_nolock(NULL); + } } -static struct sysdev_class kvm_sysdev_class = { - .name = "kvm", +static struct syscore_ops kvm_syscore_ops = { .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) { @@ -2038,6 +3114,8 @@ struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn) static void kvm_sched_in(struct preempt_notifier *pn, int cpu) { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); + if (vcpu->preempted) + vcpu->preempted = false; kvm_arch_vcpu_load(vcpu, cpu); } @@ -2047,10 +3125,12 @@ static void kvm_sched_out(struct preempt_notifier *pn, { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); + if (current->state == TASK_RUNNING) + vcpu->preempted = true; kvm_arch_vcpu_put(vcpu); } -int kvm_init(void *opaque, unsigned int vcpu_size, +int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, struct module *module) { int r; @@ -2060,14 +3140,16 @@ int kvm_init(void *opaque, unsigned int vcpu_size, 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); + /* + * kvm_arch_init makes sure there's at most one caller + * for architectures that support multiple implementations, + * like intel and amd on x86. + * kvm_arch_init must be called before kvm_irqfd_init to avoid creating + * conflicts in case kvm is already setup for another implementation. + */ + r = kvm_irqfd_init(); + if (r) + goto out_irqfd; if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) { r = -ENOMEM; @@ -2091,23 +3173,20 @@ int kvm_init(void *opaque, unsigned int vcpu_size, 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. */ - kvm_vcpu_cache = kmem_cache_create("kvm_vcpu", vcpu_size, - __alignof__(struct kvm_vcpu), + 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; + goto out_free_3; } + r = kvm_async_pf_init(); + if (r) + goto out_free; + kvm_chardev_ops.owner = module; kvm_vm_fops.owner = module; kvm_vcpu_fops.owner = module; @@ -2115,22 +3194,29 @@ int kvm_init(void *opaque, unsigned int vcpu_size, r = misc_register(&kvm_dev); if (r) { printk(KERN_ERR "kvm: misc device register failed\n"); - goto out_free; + goto out_unreg; } + register_syscore_ops(&kvm_syscore_ops); + kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out; - kvm_init_debug(); + r = kvm_init_debug(); + if (r) { + printk(KERN_ERR "kvm: create debugfs files failed\n"); + goto out_undebugfs; + } return 0; +out_undebugfs: + unregister_syscore_ops(&kvm_syscore_ops); + misc_deregister(&kvm_dev); +out_unreg: + kvm_async_pf_deinit(); 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); @@ -2140,8 +3226,8 @@ out_free_1: out_free_0a: free_cpumask_var(cpus_hardware_enabled); out_free_0: - __free_page(bad_page); -out: + kvm_irqfd_exit(); +out_irqfd: kvm_arch_exit(); out_fail: return r; @@ -2150,18 +3236,17 @@ EXPORT_SYMBOL_GPL(kvm_init); void kvm_exit(void) { - tracepoint_synchronize_unregister(); kvm_exit_debug(); misc_deregister(&kvm_dev); kmem_cache_destroy(kvm_vcpu_cache); - sysdev_unregister(&kvm_sysdev); - sysdev_class_unregister(&kvm_sysdev_class); + kvm_async_pf_deinit(); + unregister_syscore_ops(&kvm_syscore_ops); unregister_reboot_notifier(&kvm_reboot_notifier); unregister_cpu_notifier(&kvm_cpu_notifier); - on_each_cpu(hardware_disable, NULL, 1); + on_each_cpu(hardware_disable_nolock, NULL, 1); kvm_arch_hardware_unsetup(); kvm_arch_exit(); + kvm_irqfd_exit(); free_cpumask_var(cpus_hardware_enabled); - __free_page(bad_page); } EXPORT_SYMBOL_GPL(kvm_exit); |