module_param(halt_poll_ns_grow, uint, 0644);
EXPORT_SYMBOL_GPL(halt_poll_ns_grow);
+/* The start value to grow halt_poll_ns from */
+unsigned int halt_poll_ns_grow_start = 10000; /* 10us */
+module_param(halt_poll_ns_grow_start, uint, 0644);
+EXPORT_SYMBOL_GPL(halt_poll_ns_grow_start);
+
/* Default resets per-vcpu halt_poll_ns . */
unsigned int halt_poll_ns_shrink;
module_param(halt_poll_ns_shrink, uint, 0644);
int i;
struct kvm_memslots *slots;
- slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
+ slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL_ACCOUNT);
if (!slots)
return NULL;
kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries,
sizeof(*kvm->debugfs_stat_data),
- GFP_KERNEL);
+ GFP_KERNEL_ACCOUNT);
if (!kvm->debugfs_stat_data)
return -ENOMEM;
for (p = debugfs_entries; p->name; p++) {
- stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL);
+ stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT);
if (!stat_data)
return -ENOMEM;
struct kvm_memslots *slots = kvm_alloc_memslots();
if (!slots)
goto out_err_no_srcu;
- /*
- * Generations must be different for each address space.
- * Init kvm generation close to the maximum to easily test the
- * code of handling generation number wrap-around.
- */
- slots->generation = i * 2 - 150;
+ /* Generations must be different for each address space. */
+ slots->generation = i;
rcu_assign_pointer(kvm->memslots[i], slots);
}
goto out_err_no_irq_srcu;
for (i = 0; i < KVM_NR_BUSES; i++) {
rcu_assign_pointer(kvm->buses[i],
- kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL));
+ kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT));
if (!kvm->buses[i])
goto out_err;
}
{
unsigned long dirty_bytes = 2 * kvm_dirty_bitmap_bytes(memslot);
- memslot->dirty_bitmap = kvzalloc(dirty_bytes, GFP_KERNEL);
+ memslot->dirty_bitmap = kvzalloc(dirty_bytes, GFP_KERNEL_ACCOUNT);
if (!memslot->dirty_bitmap)
return -ENOMEM;
int as_id, struct kvm_memslots *slots)
{
struct kvm_memslots *old_memslots = __kvm_memslots(kvm, as_id);
+ u64 gen = old_memslots->generation;
- /*
- * Set the low bit in the generation, which disables SPTE caching
- * until the end of synchronize_srcu_expedited.
- */
- WARN_ON(old_memslots->generation & 1);
- slots->generation = old_memslots->generation + 1;
+ WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS);
+ slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS;
rcu_assign_pointer(kvm->memslots[as_id], slots);
synchronize_srcu_expedited(&kvm->srcu);
/*
- * Increment the new memslot generation a second time. This prevents
- * vm exits that race with memslot updates from caching a memslot
- * generation that will (potentially) be valid forever.
- *
+ * Increment the new memslot generation a second time, dropping the
+ * update in-progress flag and incrementing then generation based on
+ * the number of address spaces. This provides a unique and easily
+ * identifiable generation number while the memslots are in flux.
+ */
+ gen = slots->generation & ~KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS;
+
+ /*
* Generations must be unique even across address spaces. We do not need
* a global counter for that, instead the generation space is evenly split
* across address spaces. For example, with two address spaces, address
- * space 0 will use generations 0, 4, 8, ... while * address space 1 will
- * use generations 2, 6, 10, 14, ...
+ * space 0 will use generations 0, 2, 4, ... while address space 1 will
+ * use generations 1, 3, 5, ...
*/
- slots->generation += KVM_ADDRESS_SPACE_NUM * 2 - 1;
+ gen += KVM_ADDRESS_SPACE_NUM;
- kvm_arch_memslots_updated(kvm, slots);
+ kvm_arch_memslots_updated(kvm, gen);
+
+ slots->generation = gen;
return old_memslots;
}
goto out_free;
}
- slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
+ slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL_ACCOUNT);
if (!slots)
goto out_free;
memcpy(slots, __kvm_memslots(kvm, as_id), sizeof(struct kvm_memslots));
#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
/**
- * kvm_get_dirty_log_protect - get a snapshot of dirty pages, and if any pages
+ * kvm_get_dirty_log_protect - get a snapshot of dirty pages
* and reenable dirty page tracking for the corresponding pages.
* @kvm: pointer to kvm instance
* @log: slot id and address to which we copy the log
- * @is_dirty: flag set if any page is dirty
+ * @flush: true if TLB flush is needed by caller
*
* We need to keep it in mind that VCPU threads can write to the bitmap
* concurrently. So, to avoid losing track of dirty pages we keep the
mask = xchg(&dirty_bitmap[i], 0);
dirty_bitmap_buffer[i] = mask;
- if (mask) {
- offset = i * BITS_PER_LONG;
- kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
- offset, mask);
- }
+ offset = i * BITS_PER_LONG;
+ kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
+ offset, mask);
}
spin_unlock(&kvm->mmu_lock);
}
* and reenable dirty page tracking for the corresponding pages.
* @kvm: pointer to kvm instance
* @log: slot id and address from which to fetch the bitmap of dirty pages
+ * @flush: true if TLB flush is needed by caller
*/
int kvm_clear_dirty_log_protect(struct kvm *kvm,
struct kvm_clear_dirty_log *log, bool *flush)
if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
return -EINVAL;
- if ((log->first_page & 63) || (log->num_pages & 63))
+ if (log->first_page & 63)
return -EINVAL;
slots = __kvm_memslots(kvm, as_id);
if (!dirty_bitmap)
return -ENOENT;
- n = kvm_dirty_bitmap_bytes(memslot);
+ n = ALIGN(log->num_pages, BITS_PER_LONG) / 8;
if (log->first_page > memslot->npages ||
- log->num_pages > memslot->npages - log->first_page)
- return -EINVAL;
+ log->num_pages > memslot->npages - log->first_page ||
+ (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63)))
+ return -EINVAL;
*flush = false;
dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);
return -EFAULT;
spin_lock(&kvm->mmu_lock);
- for (offset = log->first_page,
- i = offset / BITS_PER_LONG, n = log->num_pages / BITS_PER_LONG; n--;
+ for (offset = log->first_page, i = offset / BITS_PER_LONG,
+ n = DIV_ROUND_UP(log->num_pages, BITS_PER_LONG); n--;
i++, offset += BITS_PER_LONG) {
unsigned long mask = *dirty_bitmap_buffer++;
atomic_long_t *p = (atomic_long_t *) &dirty_bitmap[i];
}
EXPORT_SYMBOL_GPL(gfn_to_page);
+static int __kvm_map_gfn(struct kvm_memory_slot *slot, gfn_t gfn,
+ struct kvm_host_map *map)
+{
+ kvm_pfn_t pfn;
+ void *hva = NULL;
+ struct page *page = KVM_UNMAPPED_PAGE;
+
+ if (!map)
+ return -EINVAL;
+
+ pfn = gfn_to_pfn_memslot(slot, gfn);
+ if (is_error_noslot_pfn(pfn))
+ return -EINVAL;
+
+ if (pfn_valid(pfn)) {
+ page = pfn_to_page(pfn);
+ hva = kmap(page);
+ } else {
+ hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB);
+ }
+
+ if (!hva)
+ return -EFAULT;
+
+ map->page = page;
+ map->hva = hva;
+ map->pfn = pfn;
+ map->gfn = gfn;
+
+ return 0;
+}
+
+int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map)
+{
+ return __kvm_map_gfn(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, map);
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_map);
+
+void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map,
+ bool dirty)
+{
+ if (!map)
+ return;
+
+ if (!map->hva)
+ return;
+
+ if (map->page)
+ kunmap(map->page);
+ else
+ memunmap(map->hva);
+
+ if (dirty) {
+ kvm_vcpu_mark_page_dirty(vcpu, map->gfn);
+ kvm_release_pfn_dirty(map->pfn);
+ } else {
+ kvm_release_pfn_clean(map->pfn);
+ }
+
+ map->hva = NULL;
+ map->page = NULL;
+}
+EXPORT_SYMBOL_GPL(kvm_vcpu_unmap);
+
struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn)
{
kvm_pfn_t pfn;
static void grow_halt_poll_ns(struct kvm_vcpu *vcpu)
{
- unsigned int old, val, grow;
+ unsigned int old, val, grow, grow_start;
old = val = vcpu->halt_poll_ns;
+ grow_start = READ_ONCE(halt_poll_ns_grow_start);
grow = READ_ONCE(halt_poll_ns_grow);
- /* 10us base */
- if (val == 0 && grow)
- val = 10000;
- else
- val *= grow;
+ if (!grow)
+ goto out;
+
+ val *= grow;
+ if (val < grow_start)
+ val = grow_start;
if (val > halt_poll_ns)
val = halt_poll_ns;
vcpu->halt_poll_ns = val;
+out:
trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old);
}
u64 block_ns;
start = cur = ktime_get();
- if (vcpu->halt_poll_ns) {
+ if (vcpu->halt_poll_ns && !kvm_arch_no_poll(vcpu)) {
ktime_t stop = ktime_add_ns(ktime_get(), vcpu->halt_poll_ns);
++vcpu->stat.halt_attempted_poll;
struct kvm_regs *kvm_regs;
r = -ENOMEM;
- kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL);
+ kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL_ACCOUNT);
if (!kvm_regs)
goto out;
r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs);
break;
}
case KVM_GET_SREGS: {
- kvm_sregs = kzalloc(sizeof(struct kvm_sregs), GFP_KERNEL);
+ kvm_sregs = kzalloc(sizeof(struct kvm_sregs),
+ GFP_KERNEL_ACCOUNT);
r = -ENOMEM;
if (!kvm_sregs)
goto out;
break;
}
case KVM_GET_FPU: {
- fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL);
+ fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL_ACCOUNT);
r = -ENOMEM;
if (!fpu)
goto out;
}
#endif
+static int kvm_device_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+ struct kvm_device *dev = filp->private_data;
+
+ if (dev->ops->mmap)
+ return dev->ops->mmap(dev, vma);
+
+ return -ENODEV;
+}
+
static int kvm_device_ioctl_attr(struct kvm_device *dev,
int (*accessor)(struct kvm_device *dev,
struct kvm_device_attr *attr),
{
struct kvm_device *dev = filp->private_data;
+ if (dev->kvm->mm != current->mm)
+ return -EIO;
+
switch (ioctl) {
case KVM_SET_DEVICE_ATTR:
return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg);
struct kvm_device *dev = filp->private_data;
struct kvm *kvm = dev->kvm;
+ if (dev->ops->release) {
+ mutex_lock(&kvm->lock);
+ list_del(&dev->vm_node);
+ dev->ops->release(dev);
+ mutex_unlock(&kvm->lock);
+ }
+
kvm_put_kvm(kvm);
return 0;
}
.unlocked_ioctl = kvm_device_ioctl,
.release = kvm_device_release,
KVM_COMPAT(kvm_device_ioctl),
+ .mmap = kvm_device_mmap,
};
struct kvm_device *kvm_device_from_filp(struct file *filp)
struct kvm_device_ops *ops = NULL;
struct kvm_device *dev;
bool test = cd->flags & KVM_CREATE_DEVICE_TEST;
+ int type;
int ret;
if (cd->type >= ARRAY_SIZE(kvm_device_ops_table))
return -ENODEV;
- ops = kvm_device_ops_table[cd->type];
+ type = array_index_nospec(cd->type, ARRAY_SIZE(kvm_device_ops_table));
+ ops = kvm_device_ops_table[type];
if (ops == NULL)
return -ENODEV;
if (test)
return 0;
- dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL_ACCOUNT);
if (!dev)
return -ENOMEM;
dev->kvm = kvm;
mutex_lock(&kvm->lock);
- ret = ops->create(dev, cd->type);
+ ret = ops->create(dev, type);
if (ret < 0) {
mutex_unlock(&kvm->lock);
kfree(dev);
case KVM_CAP_CHECK_EXTENSION_VM:
case KVM_CAP_ENABLE_CAP_VM:
#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
- case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT:
+ case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2:
#endif
return 1;
#ifdef CONFIG_KVM_MMIO
#endif
case KVM_CAP_MAX_VCPU_ID:
return KVM_MAX_VCPU_ID;
+ case KVM_CAP_NR_MEMSLOTS:
+ return KVM_USER_MEM_SLOTS;
default:
break;
}
{
switch (cap->cap) {
#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
- case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT:
+ case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2:
if (cap->flags || (cap->args[0] & ~1))
return -EINVAL;
kvm->manual_dirty_log_protect = cap->args[0];
r = __kvm_io_bus_write(vcpu, bus, &range, val);
return r < 0 ? r : 0;
}
+EXPORT_SYMBOL_GPL(kvm_io_bus_write);
/* kvm_io_bus_write_cookie - called under kvm->slots_lock */
int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx,
return -EOPNOTSUPP;
}
-EXPORT_SYMBOL_GPL(kvm_io_bus_write);
/* kvm_io_bus_read - called under kvm->slots_lock */
int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr,
return r < 0 ? r : 0;
}
-
/* 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)
if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1)
return -ENOSPC;
- new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count + 1) *
- sizeof(struct kvm_io_range)), GFP_KERNEL);
+ new_bus = kmalloc(struct_size(bus, range, bus->dev_count + 1),
+ GFP_KERNEL_ACCOUNT);
if (!new_bus)
return -ENOMEM;
if (i == bus->dev_count)
return;
- new_bus = kmalloc(sizeof(*bus) + ((bus->dev_count - 1) *
- sizeof(struct kvm_io_range)), GFP_KERNEL);
+ new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1),
+ GFP_KERNEL_ACCOUNT);
if (!new_bus) {
pr_err("kvm: failed to shrink bus, removing it completely\n");
goto broken;
active = kvm_active_vms;
spin_unlock(&kvm_lock);
- env = kzalloc(sizeof(*env), GFP_KERNEL);
+ env = kzalloc(sizeof(*env), GFP_KERNEL_ACCOUNT);
if (!env)
return;
add_uevent_var(env, "PID=%d", kvm->userspace_pid);
if (!IS_ERR_OR_NULL(kvm->debugfs_dentry)) {
- char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL);
+ char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL_ACCOUNT);
if (p) {
tmp = dentry_path_raw(kvm->debugfs_dentry, p, PATH_MAX);