diff options
Diffstat (limited to 'virt/kvm/kvm_main.c')
| -rw-r--r-- | virt/kvm/kvm_main.c | 301 |
1 files changed, 147 insertions, 154 deletions
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 439d3b4cd1a9..72c4e6b39389 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -155,6 +155,8 @@ static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm); static unsigned long long kvm_createvm_count; static unsigned long long kvm_active_vms; +static DEFINE_PER_CPU(cpumask_var_t, cpu_kick_mask); + __weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm, unsigned long start, unsigned long end) { @@ -235,11 +237,8 @@ static void ack_flush(void *_completed) { } -static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait) +static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait) { - if (unlikely(!cpus)) - cpus = cpu_online_mask; - if (cpumask_empty(cpus)) return false; @@ -247,33 +246,55 @@ static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait) return true; } +static void kvm_make_vcpu_request(struct kvm *kvm, struct kvm_vcpu *vcpu, + unsigned int req, struct cpumask *tmp, + int current_cpu) +{ + int cpu; + + kvm_make_request(req, vcpu); + + if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) + return; + + /* + * Note, the vCPU could get migrated to a different pCPU at any point + * after kvm_request_needs_ipi(), which could result in sending an IPI + * to the previous pCPU. But, that's OK because the purpose of the IPI + * is to ensure the vCPU returns to OUTSIDE_GUEST_MODE, which is + * satisfied if the vCPU migrates. Entering READING_SHADOW_PAGE_TABLES + * after this point is also OK, as the requirement is only that KVM wait + * for vCPUs that were reading SPTEs _before_ any changes were + * finalized. See kvm_vcpu_kick() for more details on handling requests. + */ + if (kvm_request_needs_ipi(vcpu, req)) { + cpu = READ_ONCE(vcpu->cpu); + if (cpu != -1 && cpu != current_cpu) + __cpumask_set_cpu(cpu, tmp); + } +} + bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, - struct kvm_vcpu *except, - unsigned long *vcpu_bitmap, cpumask_var_t tmp) + unsigned long *vcpu_bitmap) { - int i, cpu, me; struct kvm_vcpu *vcpu; + struct cpumask *cpus; + int i, me; bool called; me = get_cpu(); - kvm_for_each_vcpu(i, vcpu, kvm) { - if ((vcpu_bitmap && !test_bit(i, vcpu_bitmap)) || - vcpu == except) - continue; - - kvm_make_request(req, vcpu); - cpu = vcpu->cpu; + cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask); + cpumask_clear(cpus); - if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) + for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) { + vcpu = kvm_get_vcpu(kvm, i); + if (!vcpu) continue; - - if (tmp != NULL && cpu != -1 && cpu != me && - kvm_request_needs_ipi(vcpu, req)) - __cpumask_set_cpu(cpu, tmp); + kvm_make_vcpu_request(kvm, vcpu, req, cpus, me); } - called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT)); + called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); put_cpu(); return called; @@ -282,14 +303,25 @@ bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, bool kvm_make_all_cpus_request_except(struct kvm *kvm, unsigned int req, struct kvm_vcpu *except) { - cpumask_var_t cpus; + struct kvm_vcpu *vcpu; + struct cpumask *cpus; bool called; + int i, me; + + me = get_cpu(); - zalloc_cpumask_var(&cpus, GFP_ATOMIC); + cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask); + cpumask_clear(cpus); - called = kvm_make_vcpus_request_mask(kvm, req, except, NULL, cpus); + kvm_for_each_vcpu(i, vcpu, kvm) { + if (vcpu == except) + continue; + kvm_make_vcpu_request(kvm, vcpu, req, cpus, me); + } + + called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); + put_cpu(); - free_cpumask_var(cpus); return called; } @@ -302,13 +334,8 @@ EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request); #ifndef CONFIG_HAVE_KVM_ARCH_TLB_FLUSH_ALL void kvm_flush_remote_tlbs(struct kvm *kvm) { - /* - * Read tlbs_dirty before setting KVM_REQ_TLB_FLUSH in - * kvm_make_all_cpus_request. - */ - long dirty_count = smp_load_acquire(&kvm->tlbs_dirty); - ++kvm->stat.generic.remote_tlb_flush_requests; + /* * We want to publish modifications to the page tables before reading * mode. Pairs with a memory barrier in arch-specific code. @@ -323,7 +350,6 @@ void kvm_flush_remote_tlbs(struct kvm *kvm) if (!kvm_arch_flush_remote_tlb(kvm) || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH)) ++kvm->stat.generic.remote_tlb_flush; - cmpxchg(&kvm->tlbs_dirty, dirty_count, 0); } EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); #endif @@ -528,7 +554,7 @@ static __always_inline int __kvm_handle_hva_range(struct kvm *kvm, } } - if (range->flush_on_ret && (ret || kvm->tlbs_dirty)) + if (range->flush_on_ret && ret) kvm_flush_remote_tlbs(kvm); if (locked) @@ -1505,11 +1531,10 @@ static struct kvm_memslots *kvm_dup_memslots(struct kvm_memslots *old, static int kvm_set_memslot(struct kvm *kvm, const struct kvm_userspace_memory_region *mem, - struct kvm_memory_slot *old, struct kvm_memory_slot *new, int as_id, enum kvm_mr_change change) { - struct kvm_memory_slot *slot; + struct kvm_memory_slot *slot, old; struct kvm_memslots *slots; int r; @@ -1540,7 +1565,7 @@ static int kvm_set_memslot(struct kvm *kvm, * Note, the INVALID flag needs to be in the appropriate entry * in the freshly allocated memslots, not in @old or @new. */ - slot = id_to_memslot(slots, old->id); + slot = id_to_memslot(slots, new->id); slot->flags |= KVM_MEMSLOT_INVALID; /* @@ -1571,6 +1596,26 @@ static int kvm_set_memslot(struct kvm *kvm, kvm_copy_memslots(slots, __kvm_memslots(kvm, as_id)); } + /* + * Make a full copy of the old memslot, the pointer will become stale + * when the memslots are re-sorted by update_memslots(), and the old + * memslot needs to be referenced after calling update_memslots(), e.g. + * to free its resources and for arch specific behavior. This needs to + * happen *after* (re)acquiring slots_arch_lock. + */ + slot = id_to_memslot(slots, new->id); + if (slot) { + old = *slot; + } else { + WARN_ON_ONCE(change != KVM_MR_CREATE); + memset(&old, 0, sizeof(old)); + old.id = new->id; + old.as_id = as_id; + } + + /* Copy the arch-specific data, again after (re)acquiring slots_arch_lock. */ + memcpy(&new->arch, &old.arch, sizeof(old.arch)); + r = kvm_arch_prepare_memory_region(kvm, new, mem, change); if (r) goto out_slots; @@ -1578,14 +1623,18 @@ static int kvm_set_memslot(struct kvm *kvm, update_memslots(slots, new, change); slots = install_new_memslots(kvm, as_id, slots); - kvm_arch_commit_memory_region(kvm, mem, old, new, change); + kvm_arch_commit_memory_region(kvm, mem, &old, new, change); + + /* Free the old memslot's metadata. Note, this is the full copy!!! */ + if (change == KVM_MR_DELETE) + kvm_free_memslot(kvm, &old); kvfree(slots); return 0; out_slots: if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { - slot = id_to_memslot(slots, old->id); + slot = id_to_memslot(slots, new->id); slot->flags &= ~KVM_MEMSLOT_INVALID; slots = install_new_memslots(kvm, as_id, slots); } else { @@ -1600,7 +1649,6 @@ static int kvm_delete_memslot(struct kvm *kvm, struct kvm_memory_slot *old, int as_id) { struct kvm_memory_slot new; - int r; if (!old->npages) return -EINVAL; @@ -1613,12 +1661,7 @@ static int kvm_delete_memslot(struct kvm *kvm, */ new.as_id = as_id; - r = kvm_set_memslot(kvm, mem, old, &new, as_id, KVM_MR_DELETE); - if (r) - return r; - - kvm_free_memslot(kvm, old); - return 0; + return kvm_set_memslot(kvm, mem, &new, as_id, KVM_MR_DELETE); } /* @@ -1646,7 +1689,8 @@ int __kvm_set_memory_region(struct kvm *kvm, id = (u16)mem->slot; /* General sanity checks */ - if (mem->memory_size & (PAGE_SIZE - 1)) + if ((mem->memory_size & (PAGE_SIZE - 1)) || + (mem->memory_size != (unsigned long)mem->memory_size)) return -EINVAL; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) return -EINVAL; @@ -1692,7 +1736,6 @@ int __kvm_set_memory_region(struct kvm *kvm, if (!old.npages) { change = KVM_MR_CREATE; new.dirty_bitmap = NULL; - memset(&new.arch, 0, sizeof(new.arch)); } else { /* Modify an existing slot. */ if ((new.userspace_addr != old.userspace_addr) || (new.npages != old.npages) || @@ -1706,9 +1749,8 @@ int __kvm_set_memory_region(struct kvm *kvm, else /* Nothing to change. */ return 0; - /* Copy dirty_bitmap and arch from the current memslot. */ + /* Copy dirty_bitmap from the current memslot. */ new.dirty_bitmap = old.dirty_bitmap; - memcpy(&new.arch, &old.arch, sizeof(new.arch)); } if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { @@ -1734,7 +1776,7 @@ int __kvm_set_memory_region(struct kvm *kvm, bitmap_set(new.dirty_bitmap, 0, new.npages); } - r = kvm_set_memslot(kvm, mem, &old, &new, as_id, change); + r = kvm_set_memslot(kvm, mem, &new, as_id, change); if (r) goto out_bitmap; @@ -2522,72 +2564,36 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_page); -void kvm_release_pfn(kvm_pfn_t pfn, bool dirty, struct gfn_to_pfn_cache *cache) +void kvm_release_pfn(kvm_pfn_t pfn, bool dirty) { if (pfn == 0) return; - if (cache) - cache->pfn = cache->gfn = 0; - if (dirty) kvm_release_pfn_dirty(pfn); else kvm_release_pfn_clean(pfn); } -static void kvm_cache_gfn_to_pfn(struct kvm_memory_slot *slot, gfn_t gfn, - struct gfn_to_pfn_cache *cache, u64 gen) -{ - kvm_release_pfn(cache->pfn, cache->dirty, cache); - - cache->pfn = gfn_to_pfn_memslot(slot, gfn); - cache->gfn = gfn; - cache->dirty = false; - cache->generation = gen; -} - -static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn, - struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, - bool atomic) +int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map) { kvm_pfn_t pfn; void *hva = NULL; struct page *page = KVM_UNMAPPED_PAGE; - struct kvm_memory_slot *slot = __gfn_to_memslot(slots, gfn); - u64 gen = slots->generation; if (!map) return -EINVAL; - if (cache) { - if (!cache->pfn || cache->gfn != gfn || - cache->generation != gen) { - if (atomic) - return -EAGAIN; - kvm_cache_gfn_to_pfn(slot, gfn, cache, gen); - } - pfn = cache->pfn; - } else { - if (atomic) - return -EAGAIN; - pfn = gfn_to_pfn_memslot(slot, gfn); - } + pfn = gfn_to_pfn(vcpu->kvm, gfn); if (is_error_noslot_pfn(pfn)) return -EINVAL; if (pfn_valid(pfn)) { page = pfn_to_page(pfn); - if (atomic) - hva = kmap_atomic(page); - else - hva = kmap(page); + hva = kmap(page); #ifdef CONFIG_HAS_IOMEM - } else if (!atomic) { - hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB); } else { - return -EINVAL; + hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB); #endif } @@ -2601,27 +2607,9 @@ static int __kvm_map_gfn(struct kvm_memslots *slots, gfn_t gfn, return 0; } - -int kvm_map_gfn(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool atomic) -{ - return __kvm_map_gfn(kvm_memslots(vcpu->kvm), gfn, map, - cache, atomic); -} -EXPORT_SYMBOL_GPL(kvm_map_gfn); - -int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map) -{ - return __kvm_map_gfn(kvm_vcpu_memslots(vcpu), gfn, map, - NULL, false); -} EXPORT_SYMBOL_GPL(kvm_vcpu_map); -static void __kvm_unmap_gfn(struct kvm *kvm, - struct kvm_memory_slot *memslot, - struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, - bool dirty, bool atomic) +void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty) { if (!map) return; @@ -2629,45 +2617,21 @@ static void __kvm_unmap_gfn(struct kvm *kvm, if (!map->hva) return; - if (map->page != KVM_UNMAPPED_PAGE) { - if (atomic) - kunmap_atomic(map->hva); - else - kunmap(map->page); - } + if (map->page != KVM_UNMAPPED_PAGE) + kunmap(map->page); #ifdef CONFIG_HAS_IOMEM - else if (!atomic) - memunmap(map->hva); else - WARN_ONCE(1, "Unexpected unmapping in atomic context"); + memunmap(map->hva); #endif if (dirty) - mark_page_dirty_in_slot(kvm, memslot, map->gfn); + kvm_vcpu_mark_page_dirty(vcpu, map->gfn); - if (cache) - cache->dirty |= dirty; - else - kvm_release_pfn(map->pfn, dirty, NULL); + kvm_release_pfn(map->pfn, dirty); map->hva = NULL; map->page = NULL; } - -int kvm_unmap_gfn(struct kvm_vcpu *vcpu, struct kvm_host_map *map, - struct gfn_to_pfn_cache *cache, bool dirty, bool atomic) -{ - __kvm_unmap_gfn(vcpu->kvm, gfn_to_memslot(vcpu->kvm, map->gfn), map, - cache, dirty, atomic); - return 0; -} -EXPORT_SYMBOL_GPL(kvm_unmap_gfn); - -void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty) -{ - __kvm_unmap_gfn(vcpu->kvm, kvm_vcpu_gfn_to_memslot(vcpu, map->gfn), - map, NULL, dirty, false); -} EXPORT_SYMBOL_GPL(kvm_vcpu_unmap); struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn) @@ -2967,7 +2931,8 @@ int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, int r; gpa_t gpa = ghc->gpa + offset; - BUG_ON(len + offset > ghc->len); + if (WARN_ON_ONCE(len + offset > ghc->len)) + return -EINVAL; if (slots->generation != ghc->generation) { if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) @@ -3004,7 +2969,8 @@ int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, int r; gpa_t gpa = ghc->gpa + offset; - BUG_ON(len + offset > ghc->len); + if (WARN_ON_ONCE(len + offset > ghc->len)) + return -EINVAL; if (slots->generation != ghc->generation) { if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) @@ -3134,15 +3100,19 @@ out: static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu) { - unsigned int old, val, shrink; + unsigned int old, val, shrink, grow_start; old = val = vcpu->halt_poll_ns; shrink = READ_ONCE(halt_poll_ns_shrink); + grow_start = READ_ONCE(halt_poll_ns_grow_start); if (shrink == 0) val = 0; else val /= shrink; + if (val < grow_start) + val = 0; + vcpu->halt_poll_ns = val; trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old); } @@ -3290,16 +3260,24 @@ EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up); */ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { - int me; - int cpu = vcpu->cpu; + int me, cpu; if (kvm_vcpu_wake_up(vcpu)) return; + /* + * Note, the vCPU could get migrated to a different pCPU at any point + * after kvm_arch_vcpu_should_kick(), which could result in sending an + * IPI to the previous pCPU. But, that's ok because the purpose of the + * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the + * vCPU also requires it to leave IN_GUEST_MODE. + */ me = get_cpu(); - if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) - if (kvm_arch_vcpu_should_kick(vcpu)) + if (kvm_arch_vcpu_should_kick(vcpu)) { + cpu = READ_ONCE(vcpu->cpu); + if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) smp_send_reschedule(cpu); + } put_cpu(); } EXPORT_SYMBOL_GPL(kvm_vcpu_kick); @@ -3493,7 +3471,7 @@ static const struct vm_operations_struct kvm_vcpu_vm_ops = { static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma) { struct kvm_vcpu *vcpu = file->private_data; - unsigned long pages = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT; + unsigned long pages = vma_pages(vma); if ((kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff) || kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff + pages - 1)) && @@ -3557,7 +3535,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) struct kvm_vcpu *vcpu; struct page *page; - if (id >= KVM_MAX_VCPU_ID) + if (id >= KVM_MAX_VCPU_IDS) return -EINVAL; mutex_lock(&kvm->lock); @@ -3709,7 +3687,7 @@ static long kvm_vcpu_ioctl(struct file *filp, struct kvm_fpu *fpu = NULL; struct kvm_sregs *kvm_sregs = NULL; - if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged) + if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) @@ -3919,7 +3897,7 @@ static long kvm_vcpu_compat_ioctl(struct file *filp, void __user *argp = compat_ptr(arg); int r; - if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_bugged) + if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; switch (ioctl) { @@ -3985,7 +3963,7 @@ static long kvm_device_ioctl(struct file *filp, unsigned int ioctl, { struct kvm_device *dev = filp->private_data; - if (dev->kvm->mm != current->mm || dev->kvm->vm_bugged) + if (dev->kvm->mm != current->mm || dev->kvm->vm_dead) return -EIO; switch (ioctl) { @@ -4307,7 +4285,7 @@ static long kvm_vm_ioctl(struct file *filp, void __user *argp = (void __user *)arg; int r; - if (kvm->mm != current->mm || kvm->vm_bugged) + if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_CREATE_VCPU: @@ -4518,7 +4496,7 @@ static long kvm_vm_compat_ioctl(struct file *filp, struct kvm *kvm = filp->private_data; int r; - if (kvm->mm != current->mm || kvm->vm_bugged) + if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; switch (ioctl) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT @@ -5513,9 +5491,17 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, goto out_free_3; } + for_each_possible_cpu(cpu) { + if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu), + GFP_KERNEL, cpu_to_node(cpu))) { + r = -ENOMEM; + goto out_free_4; + } + } + r = kvm_async_pf_init(); if (r) - goto out_free; + goto out_free_5; kvm_chardev_ops.owner = module; kvm_vm_fops.owner = module; @@ -5541,7 +5527,10 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align, out_unreg: kvm_async_pf_deinit(); -out_free: +out_free_5: + for_each_possible_cpu(cpu) + free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); +out_free_4: kmem_cache_destroy(kvm_vcpu_cache); out_free_3: unregister_reboot_notifier(&kvm_reboot_notifier); @@ -5561,8 +5550,12 @@ EXPORT_SYMBOL_GPL(kvm_init); void kvm_exit(void) { + int cpu; + debugfs_remove_recursive(kvm_debugfs_dir); misc_deregister(&kvm_dev); + for_each_possible_cpu(cpu) + free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); kvm_async_pf_deinit(); unregister_syscore_ops(&kvm_syscore_ops); |
