diff options
Diffstat (limited to 'kernel/virt/kvm/kvm_main.c')
| -rw-r--r-- | kernel/virt/kvm/kvm_main.c | 597 |
1 files changed, 422 insertions, 175 deletions
diff --git a/kernel/virt/kvm/kvm_main.c b/kernel/virt/kvm/kvm_main.c index de930768a..eeed326be 100644 --- a/kernel/virt/kvm/kvm_main.c +++ b/kernel/virt/kvm/kvm_main.c @@ -66,9 +66,18 @@ MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); -static unsigned int halt_poll_ns; +/* Architectures should define their poll value according to the halt latency */ +static unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT; module_param(halt_poll_ns, uint, S_IRUGO | S_IWUSR); +/* Default doubles per-vcpu halt_poll_ns. */ +static unsigned int halt_poll_ns_grow = 2; +module_param(halt_poll_ns_grow, int, S_IRUGO); + +/* Default resets per-vcpu halt_poll_ns . */ +static unsigned int halt_poll_ns_shrink; +module_param(halt_poll_ns_shrink, int, S_IRUGO); + /* * Ordering of locks: * @@ -103,8 +112,7 @@ static void hardware_disable_all(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); 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); +static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn); __visible bool kvm_rebooting; EXPORT_SYMBOL_GPL(kvm_rebooting); @@ -218,9 +226,12 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) vcpu->kvm = kvm; vcpu->vcpu_id = id; vcpu->pid = NULL; - init_swait_head(&vcpu->wq); + init_swait_queue_head(&vcpu->wq); kvm_async_pf_vcpu_init(vcpu); + vcpu->pre_pcpu = -1; + INIT_LIST_HEAD(&vcpu->blocked_vcpu_list); + page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!page) { r = -ENOMEM; @@ -388,6 +399,36 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn, return young; } +static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn, + struct mm_struct *mm, + unsigned long start, + unsigned long end) +{ + struct kvm *kvm = mmu_notifier_to_kvm(mn); + int young, idx; + + idx = srcu_read_lock(&kvm->srcu); + spin_lock(&kvm->mmu_lock); + /* + * Even though we do not flush TLB, this will still adversely + * affect performance on pre-Haswell Intel EPT, where there is + * no EPT Access Bit to clear so that we have to tear down EPT + * tables instead. If we find this unacceptable, we can always + * add a parameter to kvm_age_hva so that it effectively doesn't + * do anything on clear_young. + * + * Also note that currently we never issue secondary TLB flushes + * from clear_young, leaving this job up to the regular system + * cadence. If we find this inaccurate, we might come up with a + * more sophisticated heuristic later. + */ + young = kvm_age_hva(kvm, start, end); + 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) @@ -420,6 +461,7 @@ 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, + .clear_young = kvm_mmu_notifier_clear_young, .test_young = kvm_mmu_notifier_test_young, .change_pte = kvm_mmu_notifier_change_pte, .release = kvm_mmu_notifier_release, @@ -440,13 +482,60 @@ static int kvm_init_mmu_notifier(struct kvm *kvm) #endif /* CONFIG_MMU_NOTIFIER && KVM_ARCH_WANT_MMU_NOTIFIER */ -static void kvm_init_memslots_id(struct kvm *kvm) +static struct kvm_memslots *kvm_alloc_memslots(void) { int i; - struct kvm_memslots *slots = kvm->memslots; + struct kvm_memslots *slots; + slots = kvm_kvzalloc(sizeof(struct kvm_memslots)); + if (!slots) + return NULL; + + /* + * Init kvm generation close to the maximum to easily test the + * code of handling generation number wrap-around. + */ + slots->generation = -150; for (i = 0; i < KVM_MEM_SLOTS_NUM; i++) slots->id_to_index[i] = slots->memslots[i].id = i; + + return slots; +} + +static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) +{ + if (!memslot->dirty_bitmap) + return; + + kvfree(memslot->dirty_bitmap); + memslot->dirty_bitmap = NULL; +} + +/* + * Free any memory in @free but not in @dont. + */ +static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free, + struct kvm_memory_slot *dont) +{ + if (!dont || free->dirty_bitmap != dont->dirty_bitmap) + kvm_destroy_dirty_bitmap(free); + + kvm_arch_free_memslot(kvm, free, dont); + + free->npages = 0; +} + +static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) +{ + struct kvm_memory_slot *memslot; + + if (!slots) + return; + + kvm_for_each_memslot(memslot, slots) + kvm_free_memslot(kvm, memslot, NULL); + + kvfree(slots); } static struct kvm *kvm_create_vm(unsigned long type) @@ -472,17 +561,12 @@ static struct kvm *kvm_create_vm(unsigned long type) BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); r = -ENOMEM; - kvm->memslots = kvm_kvzalloc(sizeof(struct kvm_memslots)); - if (!kvm->memslots) - goto out_err_no_srcu; - - /* - * Init kvm generation close to the maximum to easily test the - * code of handling generation number wrap-around. - */ - kvm->memslots->generation = -150; + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) { + kvm->memslots[i] = kvm_alloc_memslots(); + if (!kvm->memslots[i]) + 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)) @@ -512,6 +596,8 @@ static struct kvm *kvm_create_vm(unsigned long type) list_add(&kvm->vm_list, &vm_list); spin_unlock(&kvm_lock); + preempt_notifier_inc(); + return kvm; out_err: @@ -523,7 +609,8 @@ out_err_no_srcu: out_err_no_disable: for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm->buses[i]); - kvfree(kvm->memslots); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) + kvm_free_memslots(kvm, kvm->memslots[i]); kvm_arch_free_vm(kvm); return ERR_PTR(r); } @@ -540,40 +627,6 @@ void *kvm_kvzalloc(unsigned long size) return kzalloc(size, GFP_KERNEL); } -static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) -{ - if (!memslot->dirty_bitmap) - return; - - 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 *kvm, struct kvm_memory_slot *free, - struct kvm_memory_slot *dont) -{ - if (!dont || free->dirty_bitmap != dont->dirty_bitmap) - kvm_destroy_dirty_bitmap(free); - - kvm_arch_free_memslot(kvm, free, dont); - - free->npages = 0; -} - -static void kvm_free_physmem(struct kvm *kvm) -{ - struct kvm_memslots *slots = kvm->memslots; - struct kvm_memory_slot *memslot; - - kvm_for_each_memslot(memslot, slots) - kvm_free_physmem_slot(kvm, memslot, NULL); - - kvfree(kvm->memslots); -} - static void kvm_destroy_devices(struct kvm *kvm) { struct list_head *node, *tmp; @@ -607,10 +660,12 @@ static void kvm_destroy_vm(struct kvm *kvm) #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); - kvm_free_physmem(kvm); + for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) + kvm_free_memslots(kvm, kvm->memslots[i]); cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); kvm_arch_free_vm(kvm); + preempt_notifier_dec(); hardware_disable_all(); mmdrop(mm); } @@ -670,8 +725,6 @@ static void update_memslots(struct kvm_memslots *slots, WARN_ON(mslots[i].id != id); if (!new->npages) { WARN_ON(!mslots[i].npages); - new->base_gfn = 0; - new->flags = 0; if (mslots[i].npages) slots->used_slots--; } else { @@ -711,7 +764,7 @@ static void update_memslots(struct kvm_memslots *slots, slots->id_to_index[mslots[i].id] = i; } -static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) +static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem) { u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; @@ -726,9 +779,9 @@ static int check_memory_region_flags(struct kvm_userspace_memory_region *mem) } static struct kvm_memslots *install_new_memslots(struct kvm *kvm, - struct kvm_memslots *slots) + int as_id, struct kvm_memslots *slots) { - struct kvm_memslots *old_memslots = kvm->memslots; + struct kvm_memslots *old_memslots = __kvm_memslots(kvm, as_id); /* * Set the low bit in the generation, which disables SPTE caching @@ -737,7 +790,7 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, WARN_ON(old_memslots->generation & 1); slots->generation = old_memslots->generation + 1; - rcu_assign_pointer(kvm->memslots, slots); + rcu_assign_pointer(kvm->memslots[as_id], slots); synchronize_srcu_expedited(&kvm->srcu); /* @@ -747,7 +800,7 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, */ slots->generation++; - kvm_arch_memslots_updated(kvm); + kvm_arch_memslots_updated(kvm, slots); return old_memslots; } @@ -761,7 +814,7 @@ static struct kvm_memslots *install_new_memslots(struct kvm *kvm, * Must be called holding kvm->slots_lock for write. */ int __kvm_set_memory_region(struct kvm *kvm, - struct kvm_userspace_memory_region *mem) + const struct kvm_userspace_memory_region *mem) { int r; gfn_t base_gfn; @@ -769,6 +822,7 @@ int __kvm_set_memory_region(struct kvm *kvm, struct kvm_memory_slot *slot; struct kvm_memory_slot old, new; struct kvm_memslots *slots = NULL, *old_memslots; + int as_id, id; enum kvm_mr_change change; r = check_memory_region_flags(mem); @@ -776,36 +830,36 @@ int __kvm_set_memory_region(struct kvm *kvm, goto out; r = -EINVAL; + as_id = mem->slot >> 16; + id = (u16)mem->slot; + /* General sanity checks */ if (mem->memory_size & (PAGE_SIZE - 1)) goto out; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) goto out; /* We can read the guest memory with __xxx_user() later on. */ - if ((mem->slot < KVM_USER_MEM_SLOTS) && + if ((id < 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_MEM_SLOTS_NUM) + if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM) goto out; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) goto out; - slot = id_to_memslot(kvm->memslots, mem->slot); + slot = id_to_memslot(__kvm_memslots(kvm, as_id), id); base_gfn = mem->guest_phys_addr >> PAGE_SHIFT; npages = mem->memory_size >> PAGE_SHIFT; if (npages > KVM_MEM_MAX_NR_PAGES) goto out; - if (!npages) - mem->flags &= ~KVM_MEM_LOG_DIRTY_PAGES; - new = old = *slot; - new.id = mem->slot; + new.id = id; new.base_gfn = base_gfn; new.npages = npages; new.flags = mem->flags; @@ -828,17 +882,21 @@ int __kvm_set_memory_region(struct kvm *kvm, goto out; } } - } else if (old.npages) { + } else { + if (!old.npages) + goto out; + change = KVM_MR_DELETE; - } else /* Modify a non-existent slot: disallowed. */ - goto out; + new.base_gfn = 0; + new.flags = 0; + } if ((change == KVM_MR_CREATE) || (change == KVM_MR_MOVE)) { /* Check for overlaps */ r = -EEXIST; - kvm_for_each_memslot(slot, kvm->memslots) { + kvm_for_each_memslot(slot, __kvm_memslots(kvm, as_id)) { if ((slot->id >= KVM_USER_MEM_SLOTS) || - (slot->id == mem->slot)) + (slot->id == id)) continue; if (!((base_gfn + npages <= slot->base_gfn) || (base_gfn >= slot->base_gfn + slot->npages))) @@ -867,13 +925,13 @@ int __kvm_set_memory_region(struct kvm *kvm, slots = kvm_kvzalloc(sizeof(struct kvm_memslots)); if (!slots) goto out_free; - memcpy(slots, kvm->memslots, sizeof(struct kvm_memslots)); + memcpy(slots, __kvm_memslots(kvm, as_id), sizeof(struct kvm_memslots)); if ((change == KVM_MR_DELETE) || (change == KVM_MR_MOVE)) { - slot = id_to_memslot(slots, mem->slot); + slot = id_to_memslot(slots, id); slot->flags |= KVM_MEMSLOT_INVALID; - old_memslots = install_new_memslots(kvm, slots); + old_memslots = install_new_memslots(kvm, as_id, slots); /* slot was deleted or moved, clear iommu mapping */ kvm_iommu_unmap_pages(kvm, &old); @@ -898,18 +956,18 @@ int __kvm_set_memory_region(struct kvm *kvm, if (r) goto out_slots; - /* actual memory is freed via old in kvm_free_physmem_slot below */ + /* actual memory is freed via old in kvm_free_memslot below */ if (change == KVM_MR_DELETE) { new.dirty_bitmap = NULL; memset(&new.arch, 0, sizeof(new.arch)); } update_memslots(slots, &new); - old_memslots = install_new_memslots(kvm, slots); + old_memslots = install_new_memslots(kvm, as_id, slots); - kvm_arch_commit_memory_region(kvm, mem, &old, change); + kvm_arch_commit_memory_region(kvm, mem, &old, &new, change); - kvm_free_physmem_slot(kvm, &old, &new); + kvm_free_memslot(kvm, &old, &new); kvfree(old_memslots); /* @@ -931,14 +989,14 @@ int __kvm_set_memory_region(struct kvm *kvm, out_slots: kvfree(slots); out_free: - kvm_free_physmem_slot(kvm, &new, &old); + kvm_free_memslot(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) + const struct kvm_userspace_memory_region *mem) { int r; @@ -952,24 +1010,29 @@ EXPORT_SYMBOL_GPL(kvm_set_memory_region); static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region *mem) { - if (mem->slot >= KVM_USER_MEM_SLOTS) + if ((u16)mem->slot >= KVM_USER_MEM_SLOTS) return -EINVAL; + return kvm_set_memory_region(kvm, mem); } int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, int *is_dirty) { + struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int r, i; + int r, i, as_id, id; unsigned long n; unsigned long any = 0; r = -EINVAL; - if (log->slot >= KVM_USER_MEM_SLOTS) + as_id = log->slot >> 16; + id = (u16)log->slot; + if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS) goto out; - memslot = id_to_memslot(kvm->memslots, log->slot); + slots = __kvm_memslots(kvm, as_id); + memslot = id_to_memslot(slots, id); r = -ENOENT; if (!memslot->dirty_bitmap) goto out; @@ -1018,17 +1081,21 @@ EXPORT_SYMBOL_GPL(kvm_get_dirty_log); int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log, bool *is_dirty) { + struct kvm_memslots *slots; struct kvm_memory_slot *memslot; - int r, i; + int r, i, as_id, id; unsigned long n; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_buffer; r = -EINVAL; - if (log->slot >= KVM_USER_MEM_SLOTS) + as_id = log->slot >> 16; + id = (u16)log->slot; + if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS) goto out; - memslot = id_to_memslot(kvm->memslots, log->slot); + slots = __kvm_memslots(kvm, as_id); + memslot = id_to_memslot(slots, id); dirty_bitmap = memslot->dirty_bitmap; r = -ENOENT; @@ -1091,6 +1158,11 @@ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_memslot); +struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + return __gfn_to_memslot(kvm_vcpu_memslots(vcpu), gfn); +} + int kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn); @@ -1166,6 +1238,12 @@ unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_hva); +unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + return gfn_to_hva_many(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, NULL); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_hva); + /* * If writable is set to false, the hva returned by this function is only * allowed to be read. @@ -1188,6 +1266,13 @@ unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable) return gfn_to_hva_memslot_prot(slot, gfn, writable); } +unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable) +{ + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + + return gfn_to_hva_memslot_prot(slot, gfn, writable); +} + static int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, int write, struct page **page) { @@ -1355,9 +1440,8 @@ exit: 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) +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); @@ -1376,65 +1460,59 @@ __gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, return hva_to_pfn(addr, atomic, async, write_fault, writable); } +EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot); -static pfn_t __gfn_to_pfn(struct kvm *kvm, gfn_t gfn, bool atomic, bool *async, - bool write_fault, bool *writable) +pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, 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); + return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL, + write_fault, writable); } +EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); -pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) +pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { - return __gfn_to_pfn(kvm, gfn, true, NULL, true, NULL); + return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL); } -EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic); +EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot); -pfn_t gfn_to_pfn_async(struct kvm *kvm, gfn_t gfn, bool *async, - bool write_fault, bool *writable) +pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) { - return __gfn_to_pfn(kvm, gfn, false, async, write_fault, writable); + return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL); } -EXPORT_SYMBOL_GPL(gfn_to_pfn_async); +EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic); -pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) +pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn) { - return __gfn_to_pfn(kvm, gfn, false, NULL, true, NULL); + return gfn_to_pfn_memslot_atomic(gfn_to_memslot(kvm, gfn), gfn); } -EXPORT_SYMBOL_GPL(gfn_to_pfn); +EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic); -pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, - bool *writable) +pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn) { - return __gfn_to_pfn(kvm, gfn, false, NULL, write_fault, writable); + return gfn_to_pfn_memslot_atomic(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn); } -EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); +EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn_atomic); -pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn) +pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) { - return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL); + return gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn); } +EXPORT_SYMBOL_GPL(gfn_to_pfn); -pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn) +pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn) { - return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL); + return gfn_to_pfn_memslot(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn); } -EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic); +EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn); -int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages, - int nr_pages) +int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, 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); + addr = gfn_to_hva_many(slot, gfn, &entry); if (kvm_is_error_hva(addr)) return -1; @@ -1468,6 +1546,16 @@ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) } EXPORT_SYMBOL_GPL(gfn_to_page); +struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + pfn_t pfn; + + pfn = kvm_vcpu_gfn_to_pfn(vcpu, gfn); + + return kvm_pfn_to_page(pfn); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_page); + void kvm_release_page_clean(struct page *page) { WARN_ON(is_error_page(page)); @@ -1530,13 +1618,13 @@ static int next_segment(unsigned long len, int offset) return len; } -int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, - int len) +static int __kvm_read_guest_page(struct kvm_memory_slot *slot, gfn_t gfn, + void *data, int offset, int len) { int r; unsigned long addr; - addr = gfn_to_hva_prot(kvm, gfn, NULL); + addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; r = __copy_from_user(data, (void __user *)addr + offset, len); @@ -1544,8 +1632,25 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, return -EFAULT; return 0; } + +int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, + int len) +{ + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + + return __kvm_read_guest_page(slot, gfn, data, offset, len); +} EXPORT_SYMBOL_GPL(kvm_read_guest_page); +int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, + int offset, int len) +{ + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + + return __kvm_read_guest_page(slot, gfn, data, offset, len); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_page); + int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; @@ -1566,15 +1671,33 @@ int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len) } EXPORT_SYMBOL_GPL(kvm_read_guest); -int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, - unsigned long len) +int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len) { - int r; - unsigned long addr; gfn_t gfn = gpa >> PAGE_SHIFT; + int seg; int offset = offset_in_page(gpa); + int ret; + + while ((seg = next_segment(len, offset)) != 0) { + ret = kvm_vcpu_read_guest_page(vcpu, gfn, data, offset, seg); + if (ret < 0) + return ret; + offset = 0; + len -= seg; + data += seg; + ++gfn; + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest); + +static int __kvm_read_guest_atomic(struct kvm_memory_slot *slot, gfn_t gfn, + void *data, int offset, unsigned long len) +{ + int r; + unsigned long addr; - addr = gfn_to_hva_prot(kvm, gfn, NULL); + addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; pagefault_disable(); @@ -1584,25 +1707,63 @@ int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, return -EFAULT; return 0; } -EXPORT_SYMBOL(kvm_read_guest_atomic); -int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, - int offset, int len) +int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data, + unsigned long len) +{ + gfn_t gfn = gpa >> PAGE_SHIFT; + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + int offset = offset_in_page(gpa); + + return __kvm_read_guest_atomic(slot, gfn, data, offset, len); +} +EXPORT_SYMBOL_GPL(kvm_read_guest_atomic); + +int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, + void *data, unsigned long len) +{ + gfn_t gfn = gpa >> PAGE_SHIFT; + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + int offset = offset_in_page(gpa); + + return __kvm_read_guest_atomic(slot, gfn, data, offset, len); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic); + +static int __kvm_write_guest_page(struct kvm_memory_slot *memslot, gfn_t gfn, + const void *data, int offset, int len) { int r; unsigned long addr; - addr = gfn_to_hva(kvm, gfn); + addr = gfn_to_hva_memslot(memslot, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; r = __copy_to_user((void __user *)addr + offset, data, len); if (r) return -EFAULT; - mark_page_dirty(kvm, gfn); + mark_page_dirty_in_slot(memslot, gfn); return 0; } + +int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, + const void *data, int offset, int len) +{ + struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); + + return __kvm_write_guest_page(slot, gfn, data, offset, len); +} EXPORT_SYMBOL_GPL(kvm_write_guest_page); +int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, + const void *data, int offset, int len) +{ + struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + + return __kvm_write_guest_page(slot, gfn, data, offset, len); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest_page); + int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len) { @@ -1624,6 +1785,27 @@ int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, } EXPORT_SYMBOL_GPL(kvm_write_guest); +int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, + unsigned long len) +{ + gfn_t gfn = gpa >> PAGE_SHIFT; + int seg; + int offset = offset_in_page(gpa); + int ret; + + while ((seg = next_segment(len, offset)) != 0) { + ret = kvm_vcpu_write_guest_page(vcpu, gfn, data, offset, seg); + if (ret < 0) + return ret; + offset = 0; + len -= seg; + data += seg; + ++gfn; + } + return 0; +} +EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest); + int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len) { @@ -1681,7 +1863,7 @@ int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, 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); + mark_page_dirty_in_slot(ghc->memslot, ghc->gpa >> PAGE_SHIFT); return 0; } @@ -1739,8 +1921,7 @@ int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) } EXPORT_SYMBOL_GPL(kvm_clear_guest); -static void mark_page_dirty_in_slot(struct kvm *kvm, - struct kvm_memory_slot *memslot, +static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn) { if (memslot && memslot->dirty_bitmap) { @@ -1755,10 +1936,51 @@ 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); + mark_page_dirty_in_slot(memslot, gfn); } EXPORT_SYMBOL_GPL(mark_page_dirty); +void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn) +{ + struct kvm_memory_slot *memslot; + + memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); + mark_page_dirty_in_slot(memslot, gfn); +} +EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty); + +static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) +{ + int old, val; + + old = val = vcpu->halt_poll_ns; + /* 10us base */ + if (val == 0 && halt_poll_ns_grow) + val = 10000; + else + val *= halt_poll_ns_grow; + + if (val > halt_poll_ns) + val = halt_poll_ns; + + vcpu->halt_poll_ns = val; + trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old); +} + +static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu) +{ + int old, val; + + old = val = vcpu->halt_poll_ns; + if (halt_poll_ns_shrink == 0) + val = 0; + else + val /= halt_poll_ns_shrink; + + vcpu->halt_poll_ns = val; + trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old); +} + static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) { if (kvm_arch_vcpu_runnable(vcpu)) { @@ -1779,13 +2001,15 @@ static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) void kvm_vcpu_block(struct kvm_vcpu *vcpu) { ktime_t start, cur; - DEFINE_SWAITER(wait); + DECLARE_SWAITQUEUE(wait); bool waited = false; + u64 block_ns; start = cur = ktime_get(); - if (halt_poll_ns) { - ktime_t stop = ktime_add_ns(ktime_get(), halt_poll_ns); + if (vcpu->halt_poll_ns) { + ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns); + ++vcpu->stat.halt_attempted_poll; do { /* * This sets KVM_REQ_UNHALT if an interrupt @@ -1799,8 +2023,10 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) } while (single_task_running() && ktime_before(cur, stop)); } + kvm_arch_vcpu_blocking(vcpu); + for (;;) { - swait_prepare(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); + prepare_to_swait(&vcpu->wq, &wait, TASK_INTERRUPTIBLE); if (kvm_vcpu_check_block(vcpu) < 0) break; @@ -1809,11 +2035,27 @@ void kvm_vcpu_block(struct kvm_vcpu *vcpu) schedule(); } - swait_finish(&vcpu->wq, &wait); + finish_swait(&vcpu->wq, &wait); cur = ktime_get(); + kvm_arch_vcpu_unblocking(vcpu); out: - trace_kvm_vcpu_wakeup(ktime_to_ns(cur) - ktime_to_ns(start), waited); + block_ns = ktime_to_ns(cur) - ktime_to_ns(start); + + if (halt_poll_ns) { + if (block_ns <= vcpu->halt_poll_ns) + ; + /* we had a long block, shrink polling */ + else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns) + shrink_halt_poll_ns(vcpu); + /* we had a short halt and our poll time is too small */ + else if (vcpu->halt_poll_ns < halt_poll_ns && + block_ns < halt_poll_ns) + grow_halt_poll_ns(vcpu); + } else + vcpu->halt_poll_ns = 0; + + trace_kvm_vcpu_wakeup(block_ns, waited); } EXPORT_SYMBOL_GPL(kvm_vcpu_block); @@ -1825,11 +2067,11 @@ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { int me; int cpu = vcpu->cpu; - struct swait_head *wqp; + struct swait_queue_head *wqp; wqp = kvm_arch_vcpu_wq(vcpu); - if (swaitqueue_active(wqp)) { - swait_wake_interruptible(wqp); + if (swait_active(wqp)) { + swake_up(wqp); ++vcpu->stat.halt_wakeup; } @@ -1930,7 +2172,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me) continue; if (vcpu == me) continue; - if (swaitqueue_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) + if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu)) continue; if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) continue; @@ -2059,6 +2301,11 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) } kvm->vcpus[atomic_read(&kvm->online_vcpus)] = vcpu; + + /* + * Pairs with smp_rmb() in kvm_get_vcpu. Write kvm->vcpus + * before kvm->online_vcpu's incremented value. + */ smp_wmb(); atomic_inc(&kvm->online_vcpus); @@ -2471,9 +2718,6 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_USER_MEMORY: case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS: -#ifdef CONFIG_KVM_APIC_ARCHITECTURE - case KVM_CAP_SET_BOOT_CPU_ID: -#endif case KVM_CAP_INTERNAL_ERROR_DATA: #ifdef CONFIG_HAVE_KVM_MSI case KVM_CAP_SIGNAL_MSI: @@ -2482,12 +2726,17 @@ static long kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) case KVM_CAP_IRQFD: case KVM_CAP_IRQFD_RESAMPLE: #endif + case KVM_CAP_IOEVENTFD_ANY_LENGTH: case KVM_CAP_CHECK_EXTENSION_VM: return 1; #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING case KVM_CAP_IRQ_ROUTING: return KVM_MAX_IRQ_ROUTES; #endif +#if KVM_ADDRESS_SPACE_NUM > 1 + case KVM_CAP_MULTI_ADDRESS_SPACE: + return KVM_ADDRESS_SPACE_NUM; +#endif default: break; } @@ -2565,17 +2814,6 @@ static long kvm_vm_ioctl(struct file *filp, r = kvm_ioeventfd(kvm, &data); break; } -#ifdef CONFIG_KVM_APIC_ARCHITECTURE - case KVM_SET_BOOT_CPU_ID: - r = 0; - mutex_lock(&kvm->lock); - if (atomic_read(&kvm->online_vcpus) != 0) - r = -EBUSY; - else - kvm->bsp_vcpu_id = arg; - mutex_unlock(&kvm->lock); - break; -#endif #ifdef CONFIG_HAVE_KVM_MSI case KVM_SIGNAL_MSI: { struct kvm_msi msi; @@ -2882,18 +3120,12 @@ static int hardware_enable_all(void) static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val, void *v) { - int cpu = (long)v; - val &= ~CPU_TASKS_FROZEN; switch (val) { case CPU_DYING: - pr_info("kvm: disabling virtualization on CPU%d\n", - cpu); hardware_disable(); break; case CPU_STARTING: - pr_info("kvm: enabling virtualization on CPU%d\n", - cpu); hardware_enable(); break; } @@ -2935,10 +3167,25 @@ static void kvm_io_bus_destroy(struct kvm_io_bus *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) + gpa_t addr1 = r1->addr; + gpa_t addr2 = r2->addr; + + if (addr1 < addr2) return -1; - if (r1->addr + r1->len > r2->addr + r2->len) + + /* If r2->len == 0, match the exact address. If r2->len != 0, + * accept any overlapping write. Any order is acceptable for + * overlapping ranges, because kvm_io_bus_get_first_dev ensures + * we process all of them. + */ + if (r2->len) { + addr1 += r1->len; + addr2 += r2->len; + } + + if (addr1 > addr2) return 1; + return 0; } @@ -3103,7 +3350,7 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1) return -ENOSPC; - new_bus = kzalloc(sizeof(*bus) + ((bus->dev_count + 1) * + new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count + 1) * sizeof(struct kvm_io_range)), GFP_KERNEL); if (!new_bus) return -ENOMEM; @@ -3135,7 +3382,7 @@ int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, if (r) return r; - new_bus = kzalloc(sizeof(*bus) + ((bus->dev_count - 1) * + new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count - 1) * sizeof(struct kvm_io_range)), GFP_KERNEL); if (!new_bus) return -ENOMEM; |