blob: 5ecea812cb6a24056ee5ab42aa585cb7f5ce15ab [file] [log] [blame]
/*
* Kernel-based Virtual Machine driver for Linux
*
* This module enables machines with Intel VT-x extensions to run virtual
* machines without emulation or binary translation.
*
* Copyright (C) 2006 Qumranet, Inc.
* Copyright 2010 Red Hat, Inc. and/or its affiliates.
*
* Authors:
* Avi Kivity <avi@qumranet.com>
* Yaniv Kamay <yaniv@qumranet.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
*/
#include <kvm/iodev.h>
#include <linux/kvm_host.h>
#include <linux/kvm.h>
#include <linux/module.h>
#include <linux/errno.h>
#include <linux/percpu.h>
#include <linux/mm.h>
#include <linux/miscdevice.h>
#include <linux/vmalloc.h>
#include <linux/reboot.h>
#include <linux/debugfs.h>
#include <linux/highmem.h>
#include <linux/file.h>
#include <linux/syscore_ops.h>
#include <linux/cpu.h>
#include <linux/sched/signal.h>
#include <linux/sched/mm.h>
#include <linux/sched/stat.h>
#include <linux/cpumask.h>
#include <linux/smp.h>
#include <linux/anon_inodes.h>
#include <linux/profile.h>
#include <linux/kvm_para.h>
#include <linux/pagemap.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/bitops.h>
#include <linux/spinlock.h>
#include <linux/compat.h>
#include <linux/srcu.h>
#include <linux/hugetlb.h>
#include <linux/slab.h>
#include <linux/sort.h>
#include <linux/bsearch.h>
#include <asm/processor.h>
#include <asm/io.h>
#include <asm/ioctl.h>
#include <linux/uaccess.h>
#include <asm/pgtable.h>
#include "coalesced_mmio.h"
#include "async_pf.h"
#include "vfio.h"
#define CREATE_TRACE_POINTS
#include <trace/events/kvm.h>
/* Worst case buffer size needed for holding an integer. */
#define ITOA_MAX_LEN 12
MODULE_AUTHOR("Qumranet");
MODULE_LICENSE("GPL");
/* Architectures should define their poll value according to the halt latency */
unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT;
module_param(halt_poll_ns, uint, 0644);
EXPORT_SYMBOL_GPL(halt_poll_ns);
/* Default doubles per-vcpu halt_poll_ns. */
unsigned int halt_poll_ns_grow = 2;
module_param(halt_poll_ns_grow, uint, 0644);
EXPORT_SYMBOL_GPL(halt_poll_ns_grow);
/* Default resets per-vcpu halt_poll_ns . */
unsigned int halt_poll_ns_shrink;
module_param(halt_poll_ns_shrink, uint, 0644);
EXPORT_SYMBOL_GPL(halt_poll_ns_shrink);
/*
* Ordering of locks:
*
* kvm->lock --> kvm->slots_lock --> kvm->irq_lock
*/
DEFINE_SPINLOCK(kvm_lock);
static DEFINE_RAW_SPINLOCK(kvm_count_lock);
LIST_HEAD(vm_list);
static cpumask_var_t cpus_hardware_enabled;
static int kvm_usage_count;
static atomic_t hardware_enable_failed;
struct kmem_cache *kvm_vcpu_cache;
EXPORT_SYMBOL_GPL(kvm_vcpu_cache);
static __read_mostly struct preempt_ops kvm_preempt_ops;
struct dentry *kvm_debugfs_dir;
EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
static int kvm_debugfs_num_entries;
static const struct file_operations *stat_fops_per_vm[];
static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg);
#ifdef CONFIG_KVM_COMPAT
static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg);
#define KVM_COMPAT(c) .compat_ioctl = (c)
#else
static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl,
unsigned long arg) { return -EINVAL; }
#define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl
#endif
static int hardware_enable_all(void);
static void hardware_disable_all(void);
static void kvm_io_bus_destroy(struct kvm_io_bus *bus);
static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot, gfn_t gfn);
__visible bool kvm_rebooting;
EXPORT_SYMBOL_GPL(kvm_rebooting);
static bool largepages_enabled = true;
#define KVM_EVENT_CREATE_VM 0
#define KVM_EVENT_DESTROY_VM 1
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;
__weak int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
unsigned long start, unsigned long end, bool blockable)
{
return 0;
}
bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
{
if (pfn_valid(pfn))
return PageReserved(pfn_to_page(pfn));
return true;
}
/*
* Switches to specified vcpu, until a matching vcpu_put()
*/
void vcpu_load(struct kvm_vcpu *vcpu)
{
int cpu = get_cpu();
preempt_notifier_register(&vcpu->preempt_notifier);
kvm_arch_vcpu_load(vcpu, cpu);
put_cpu();
}
EXPORT_SYMBOL_GPL(vcpu_load);
void vcpu_put(struct kvm_vcpu *vcpu)
{
preempt_disable();
kvm_arch_vcpu_put(vcpu);
preempt_notifier_unregister(&vcpu->preempt_notifier);
preempt_enable();
}
EXPORT_SYMBOL_GPL(vcpu_put);
/* TODO: merge with kvm_arch_vcpu_should_kick */
static bool kvm_request_needs_ipi(struct kvm_vcpu *vcpu, unsigned req)
{
int mode = kvm_vcpu_exiting_guest_mode(vcpu);
/*
* We need to wait for the VCPU to reenable interrupts and get out of
* READING_SHADOW_PAGE_TABLES mode.
*/
if (req & KVM_REQUEST_WAIT)
return mode != OUTSIDE_GUEST_MODE;
/*
* Need to kick a running VCPU, but otherwise there is nothing to do.
*/
return mode == IN_GUEST_MODE;
}
static void ack_flush(void *_completed)
{
}
static inline bool kvm_kick_many_cpus(const struct cpumask *cpus, bool wait)
{
if (unlikely(!cpus))
cpus = cpu_online_mask;
if (cpumask_empty(cpus))
return false;
smp_call_function_many(cpus, ack_flush, NULL, wait);
return true;
}
bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req,
unsigned long *vcpu_bitmap, cpumask_var_t tmp)
{
int i, cpu, me;
struct kvm_vcpu *vcpu;
bool called;
me = get_cpu();
kvm_for_each_vcpu(i, vcpu, kvm) {
if (vcpu_bitmap && !test_bit(i, vcpu_bitmap))
continue;
kvm_make_request(req, vcpu);
cpu = vcpu->cpu;
if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu))
continue;
if (tmp != NULL && cpu != -1 && cpu != me &&
kvm_request_needs_ipi(vcpu, req))
__cpumask_set_cpu(cpu, tmp);
}
called = kvm_kick_many_cpus(tmp, !!(req & KVM_REQUEST_WAIT));
put_cpu();
return called;
}
bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req)
{
cpumask_var_t cpus;
bool called;
zalloc_cpumask_var(&cpus, GFP_ATOMIC);
called = kvm_make_vcpus_request_mask(kvm, req, NULL, cpus);
free_cpumask_var(cpus);
return called;
}
#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);
/*
* We want to publish modifications to the page tables before reading
* mode. Pairs with a memory barrier in arch-specific code.
* - x86: smp_mb__after_srcu_read_unlock in vcpu_enter_guest
* and smp_mb in walk_shadow_page_lockless_begin/end.
* - powerpc: smp_mb in kvmppc_prepare_to_enter.
*
* There is already an smp_mb__after_atomic() before
* kvm_make_all_cpus_request() reads vcpu->mode. We reuse that
* barrier here.
*/
if (!kvm_arch_flush_remote_tlb(kvm)
|| kvm_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);
#endif
void kvm_reload_remote_mmus(struct kvm *kvm)
{
kvm_make_all_cpus_request(kvm, KVM_REQ_MMU_RELOAD);
}
int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
{
struct page *page;
int r;
mutex_init(&vcpu->mutex);
vcpu->cpu = -1;
vcpu->kvm = kvm;
vcpu->vcpu_id = id;
vcpu->pid = NULL;
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;
goto fail;
}
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;
return 0;
fail_free_run:
free_page((unsigned long)vcpu->run);
fail:
return r;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_init);
void kvm_vcpu_uninit(struct kvm_vcpu *vcpu)
{
/*
* no need for rcu_read_lock as VCPU_RUN is the only place that
* will change the vcpu->pid pointer and on uninit all file
* descriptors are already gone.
*/
put_pid(rcu_dereference_protected(vcpu->pid, 1));
kvm_arch_vcpu_uninit(vcpu);
free_page((unsigned long)vcpu->run);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_uninit);
#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
{
return container_of(mn, struct kvm, mmu_notifier);
}
static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long address,
pte_t pte)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
int idx;
idx = srcu_read_lock(&kvm->srcu);
spin_lock(&kvm->mmu_lock);
kvm->mmu_notifier_seq++;
if (kvm_set_spte_hva(kvm, address, pte))
kvm_flush_remote_tlbs(kvm);
spin_unlock(&kvm->mmu_lock);
srcu_read_unlock(&kvm->srcu, idx);
}
static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
const struct mmu_notifier_range *range)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
int need_tlb_flush = 0, idx;
int ret;
idx = srcu_read_lock(&kvm->srcu);
spin_lock(&kvm->mmu_lock);
/*
* The count increase must become visible at unlock time as no
* spte can be established without taking the mmu_lock and
* count is also read inside the mmu_lock critical section.
*/
kvm->mmu_notifier_count++;
need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->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);
ret = kvm_arch_mmu_notifier_invalidate_range(kvm, range->start,
range->end, range->blockable);
srcu_read_unlock(&kvm->srcu, idx);
return ret;
}
static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
const struct mmu_notifier_range *range)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
spin_lock(&kvm->mmu_lock);
/*
* This sequence increase will notify the kvm page fault that
* the page that is going to be mapped in the spte could have
* been freed.
*/
kvm->mmu_notifier_seq++;
smp_wmb();
/*
* The above sequence increase must be visible before the
* 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);
BUG_ON(kvm->mmu_notifier_count < 0);
}
static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long 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);
young = kvm_age_hva(kvm, start, end);
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_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)
{
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;
}
static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
struct mm_struct *mm)
{
struct kvm *kvm = mmu_notifier_to_kvm(mn);
int idx;
idx = srcu_read_lock(&kvm->srcu);
kvm_arch_flush_shadow_all(kvm);
srcu_read_unlock(&kvm->srcu, idx);
}
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,
};
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_memslots *kvm_alloc_memslots(void)
{
int i;
struct kvm_memslots *slots;
slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
if (!slots)
return NULL;
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 void kvm_destroy_vm_debugfs(struct kvm *kvm)
{
int i;
if (!kvm->debugfs_dentry)
return;
debugfs_remove_recursive(kvm->debugfs_dentry);
if (kvm->debugfs_stat_data) {
for (i = 0; i < kvm_debugfs_num_entries; i++)
kfree(kvm->debugfs_stat_data[i]);
kfree(kvm->debugfs_stat_data);
}
}
static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
{
char dir_name[ITOA_MAX_LEN * 2];
struct kvm_stat_data *stat_data;
struct kvm_stats_debugfs_item *p;
if (!debugfs_initialized())
return 0;
snprintf(dir_name, sizeof(dir_name), "%d-%d", task_pid_nr(current), fd);
kvm->debugfs_dentry = debugfs_create_dir(dir_name, kvm_debugfs_dir);
kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries,
sizeof(*kvm->debugfs_stat_data),
GFP_KERNEL);
if (!kvm->debugfs_stat_data)
return -ENOMEM;
for (p = debugfs_entries; p->name; p++) {
stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL);
if (!stat_data)
return -ENOMEM;
stat_data->kvm = kvm;
stat_data->offset = p->offset;
kvm->debugfs_stat_data[p - debugfs_entries] = stat_data;
debugfs_create_file(p->name, 0644, kvm->debugfs_dentry,
stat_data, stat_fops_per_vm[p->kind]);
}
return 0;
}
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);
spin_lock_init(&kvm->mmu_lock);
mmgrab(current->mm);
kvm->mm = current->mm;
kvm_eventfd_init(kvm);
mutex_init(&kvm->lock);
mutex_init(&kvm->irq_lock);
mutex_init(&kvm->slots_lock);
refcount_set(&kvm->users_count, 1);
INIT_LIST_HEAD(&kvm->devices);
r = kvm_arch_init_vm(kvm, type);
if (r)
goto out_err_no_disable;
r = hardware_enable_all();
if (r)
goto out_err_no_disable;
#ifdef CONFIG_HAVE_KVM_IRQFD
INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
#endif
BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
r = -ENOMEM;
for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
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;
rcu_assign_pointer(kvm->memslots[i], slots);
}
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++) {
rcu_assign_pointer(kvm->buses[i],
kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL));
if (!kvm->buses[i])
goto out_err;
}
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);
preempt_notifier_inc();
return kvm;
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();
out_err_no_disable:
refcount_set(&kvm->users_count, 0);
for (i = 0; i < KVM_NR_BUSES; i++)
kfree(kvm_get_bus(kvm, i));
for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
kvm_free_memslots(kvm, __kvm_memslots(kvm, i));
kvm_arch_free_vm(kvm);
mmdrop(current->mm);
return ERR_PTR(r);
}
static void kvm_destroy_devices(struct kvm *kvm)
{
struct kvm_device *dev, *tmp;
/*
* We do not need to take the kvm->lock here, because nobody else
* has a reference to the struct kvm at this point and therefore
* cannot access the devices list anyhow.
*/
list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) {
list_del(&dev->vm_node);
dev->ops->destroy(dev);
}
}
static void kvm_destroy_vm(struct kvm *kvm)
{
int i;
struct mm_struct *mm = kvm->mm;
kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm);
kvm_destroy_vm_debugfs(kvm);
kvm_arch_sync_events(kvm);
spin_lock(&kvm_lock);
list_del(&kvm->vm_list);
spin_unlock(&kvm_lock);
kvm_free_irq_routing(kvm);
for (i = 0; i < KVM_NR_BUSES; i++) {
struct kvm_io_bus *bus = kvm_get_bus(kvm, i);
if (bus)
kvm_io_bus_destroy(bus);
kvm->buses[i] = NULL;
}
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_all(kvm);
#endif
kvm_arch_destroy_vm(kvm);
kvm_destroy_devices(kvm);
for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
kvm_free_memslots(kvm, __kvm_memslots(kvm, 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);
}
void kvm_get_kvm(struct kvm *kvm)
{
refcount_inc(&kvm->users_count);
}
EXPORT_SYMBOL_GPL(kvm_get_kvm);
void kvm_put_kvm(struct kvm *kvm)
{
if (refcount_dec_and_test(&kvm->users_count))
kvm_destroy_vm(kvm);
}
EXPORT_SYMBOL_GPL(kvm_put_kvm);
static int kvm_vm_release(struct inode *inode, struct file *filp)
{
struct kvm *kvm = filp->private_data;
kvm_irqfd_release(kvm);
kvm_put_kvm(kvm);
return 0;
}
/*
* 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 = kvzalloc(dirty_bytes, GFP_KERNEL);
if (!memslot->dirty_bitmap)
return -ENOMEM;
return 0;
}
/*
* Insert memslot and re-sort memslots based on their GFN,
* so binary search could be used to lookup GFN.
* Sorting algorithm takes advantage of having initially
* sorted array and known changed memslot position.
*/
static void update_memslots(struct kvm_memslots *slots,
struct kvm_memory_slot *new,
enum kvm_mr_change change)
{
int id = new->id;
int i = slots->id_to_index[id];
struct kvm_memory_slot *mslots = slots->memslots;
WARN_ON(mslots[i].id != id);
switch (change) {
case KVM_MR_CREATE:
slots->used_slots++;
WARN_ON(mslots[i].npages || !new->npages);
break;
case KVM_MR_DELETE:
slots->used_slots--;
WARN_ON(new->npages || !mslots[i].npages);
break;
default:
break;
}
while (i < KVM_MEM_SLOTS_NUM - 1 &&
new->base_gfn <= mslots[i + 1].base_gfn) {
if (!mslots[i + 1].npages)
break;
mslots[i] = mslots[i + 1];
slots->id_to_index[mslots[i].id] = i;
i++;
}
/*
* The ">=" is needed when creating a slot with base_gfn == 0,
* so that it moves before all those with base_gfn == npages == 0.
*
* On the other hand, if new->npages is zero, the above loop has
* already left i pointing to the beginning of the empty part of
* mslots, and the ">=" would move the hole backwards in this
* case---which is wrong. So skip the loop when deleting a slot.
*/
if (new->npages) {
while (i > 0 &&
new->base_gfn >= mslots[i - 1].base_gfn) {
mslots[i] = mslots[i - 1];
slots->id_to_index[mslots[i].id] = i;
i--;
}
} else
WARN_ON_ONCE(i != slots->used_slots);
mslots[i] = *new;
slots->id_to_index[mslots[i].id] = i;
}
static int check_memory_region_flags(const struct kvm_userspace_memory_region *mem)
{
u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
#ifdef __KVM_HAVE_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,
int as_id, struct kvm_memslots *slots)
{
struct kvm_memslots *old_memslots = __kvm_memslots(kvm, as_id);
/*
* 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;
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.
*
* 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, ...
*/
slots->generation += KVM_ADDRESS_SPACE_NUM * 2 - 1;
kvm_arch_memslots_updated(kvm, slots);
return old_memslots;
}
/*
* Allocate some memory and give it an address in the guest physical address
* space.
*
* Discontiguous memory is allowed, mostly for framebuffers.
*
* Must be called holding kvm->slots_lock for write.
*/
int __kvm_set_memory_region(struct kvm *kvm,
const struct kvm_userspace_memory_region *mem)
{
int r;
gfn_t base_gfn;
unsigned long npages;
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);
if (r)
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 ((id < KVM_USER_MEM_SLOTS) &&
((mem->userspace_addr & (PAGE_SIZE - 1)) ||
!access_ok((void __user *)(unsigned long)mem->userspace_addr,
mem->memory_size)))
goto out;
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(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;
new = old = *slot;
new.id = id;
new.base_gfn = base_gfn;
new.npages = npages;
new.flags = mem->flags;
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;
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)
goto out;
change = KVM_MR_DELETE;
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, as_id)) {
if (slot->id == id)
continue;
if (!((base_gfn + npages <= slot->base_gfn) ||
(base_gfn >= slot->base_gfn + slot->npages)))
goto out;
}
}
/* Free page dirty bitmap if unneeded */
if (!(new.flags & KVM_MEM_LOG_DIRTY_PAGES))
new.dirty_bitmap = NULL;
r = -ENOMEM;
if (change == KVM_MR_CREATE) {
new.userspace_addr = mem->userspace_addr;
if (kvm_arch_create_memslot(kvm, &new, npages))
goto out_free;
}
/* 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;
}
slots = kvzalloc(sizeof(struct kvm_memslots), GFP_KERNEL);
if (!slots)
goto out_free;
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, id);
slot->flags |= KVM_MEMSLOT_INVALID;
old_memslots = install_new_memslots(kvm, as_id, slots);
/* 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)
*/
kvm_arch_flush_shadow_memslot(kvm, slot);
/*
* 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.
*/
slots = old_memslots;
}
r = kvm_arch_prepare_memory_region(kvm, &new, mem, change);
if (r)
goto out_slots;
/* 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, change);
old_memslots = install_new_memslots(kvm, as_id, slots);
kvm_arch_commit_memory_region(kvm, mem, &old, &new, change);
kvm_free_memslot(kvm, &old, &new);
kvfree(old_memslots);
return 0;
out_slots:
kvfree(slots);
out_free:
kvm_free_memslot(kvm, &new, &old);
out:
return r;
}
EXPORT_SYMBOL_GPL(__kvm_set_memory_region);
int kvm_set_memory_region(struct kvm *kvm,
const struct kvm_userspace_memory_region *mem)
{
int r;
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);
static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm,
struct kvm_userspace_memory_region *mem)
{
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 i, as_id, id;
unsigned long n;
unsigned long any = 0;
as_id = log->slot >> 16;
id = (u16)log->slot;
if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
return -EINVAL;
slots = __kvm_memslots(kvm, as_id);
memslot = id_to_memslot(slots, id);
if (!memslot->dirty_bitmap)
return -ENOENT;
n = kvm_dirty_bitmap_bytes(memslot);
for (i = 0; !any && i < n/sizeof(long); ++i)
any = memslot->dirty_bitmap[i];
if (copy_to_user(log->dirty_bitmap, memslot->dirty_bitmap, n))
return -EFAULT;
if (any)
*is_dirty = 1;
return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_dirty_log);
#ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT
/**
* kvm_get_dirty_log_protect - get a snapshot of dirty pages, and if any 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
*
* 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
* following order:
*
* 1. Take a snapshot of the bit and clear it if needed.
* 2. Write protect the corresponding page.
* 3. Copy the snapshot to the userspace.
* 4. Upon return caller flushes TLB's if needed.
*
* Between 2 and 4, the guest may write to the page using the remaining TLB
* entry. This is not a problem because the page is reported dirty using
* the snapshot taken before and step 4 ensures that writes done after
* exiting to userspace will be logged for the next call.
*
*/
int kvm_get_dirty_log_protect(struct kvm *kvm,
struct kvm_dirty_log *log, bool *flush)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int i, as_id, id;
unsigned long n;
unsigned long *dirty_bitmap;
unsigned long *dirty_bitmap_buffer;
as_id = log->slot >> 16;
id = (u16)log->slot;
if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
return -EINVAL;
slots = __kvm_memslots(kvm, as_id);
memslot = id_to_memslot(slots, id);
dirty_bitmap = memslot->dirty_bitmap;
if (!dirty_bitmap)
return -ENOENT;
n = kvm_dirty_bitmap_bytes(memslot);
*flush = false;
if (kvm->manual_dirty_log_protect) {
/*
* Unlike kvm_get_dirty_log, we always return false in *flush,
* because no flush is needed until KVM_CLEAR_DIRTY_LOG. There
* is some code duplication between this function and
* kvm_get_dirty_log, but hopefully all architecture
* transition to kvm_get_dirty_log_protect and kvm_get_dirty_log
* can be eliminated.
*/
dirty_bitmap_buffer = dirty_bitmap;
} else {
dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);
memset(dirty_bitmap_buffer, 0, n);
spin_lock(&kvm->mmu_lock);
for (i = 0; i < n / sizeof(long); i++) {
unsigned long mask;
gfn_t offset;
if (!dirty_bitmap[i])
continue;
*flush = true;
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);
}
}
spin_unlock(&kvm->mmu_lock);
}
if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n))
return -EFAULT;
return 0;
}
EXPORT_SYMBOL_GPL(kvm_get_dirty_log_protect);
/**
* kvm_clear_dirty_log_protect - clear dirty bits in the bitmap
* 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
*/
int kvm_clear_dirty_log_protect(struct kvm *kvm,
struct kvm_clear_dirty_log *log, bool *flush)
{
struct kvm_memslots *slots;
struct kvm_memory_slot *memslot;
int as_id, id;
gfn_t offset;
unsigned long i, n;
unsigned long *dirty_bitmap;
unsigned long *dirty_bitmap_buffer;
as_id = log->slot >> 16;
id = (u16)log->slot;
if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_USER_MEM_SLOTS)
return -EINVAL;
if ((log->first_page & 63) || (log->num_pages & 63))
return -EINVAL;
slots = __kvm_memslots(kvm, as_id);
memslot = id_to_memslot(slots, id);
dirty_bitmap = memslot->dirty_bitmap;
if (!dirty_bitmap)
return -ENOENT;
n = kvm_dirty_bitmap_bytes(memslot);
if (log->first_page > memslot->npages ||
log->num_pages > memslot->npages - log->first_page)
return -EINVAL;
*flush = false;
dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot);
if (copy_from_user(dirty_bitmap_buffer, log->dirty_bitmap, n))
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--;
i++, offset += BITS_PER_LONG) {
unsigned long mask = *dirty_bitmap_buffer++;
atomic_long_t *p = (atomic_long_t *) &dirty_bitmap[i];
if (!mask)
continue;
mask &= atomic_long_fetch_andnot(mask, p);
/*
* mask contains the bits that really have been cleared. This
* never includes any bits beyond the length of the memslot (if
* the length is not aligned to 64 pages), therefore it is not
* a problem if userspace sets them in log->dirty_bitmap.
*/
if (mask) {
*flush = true;
kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot,
offset, mask);
}
}
spin_unlock(&kvm->mmu_lock);
return 0;
}
EXPORT_SYMBOL_GPL(kvm_clear_dirty_log_protect);
#endif
bool kvm_largepages_enabled(void)
{
return largepages_enabled;
}
void kvm_disable_largepages(void)
{
largepages_enabled = false;
}
EXPORT_SYMBOL_GPL(kvm_disable_largepages);
struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
{
return __gfn_to_memslot(kvm_memslots(kvm), 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);
}
bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn)
{
struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn);
if (!memslot || memslot->id >= KVM_USER_MEM_SLOTS ||
memslot->flags & KVM_MEMSLOT_INVALID)
return false;
return true;
}
EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
unsigned long kvm_host_page_size(struct kvm *kvm, gfn_t gfn)
{
struct vm_area_struct *vma;
unsigned long addr, size;
size = PAGE_SIZE;
addr = gfn_to_hva(kvm, gfn);
if (kvm_is_error_hva(addr))
return PAGE_SIZE;
down_read(&current->mm->mmap_sem);
vma = find_vma(current->mm, addr);
if (!vma)
goto out;
size = vma_kernel_pagesize(vma);
out:
up_read(&current->mm->mmap_sem);
return size;
}
static bool memslot_is_readonly(struct kvm_memory_slot *slot)
{
return slot->flags & KVM_MEM_READONLY;
}
static unsigned long __gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
gfn_t *nr_pages, bool write)
{
if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
return KVM_HVA_ERR_BAD;
if (memslot_is_readonly(slot) && write)
return KVM_HVA_ERR_RO_BAD;
if (nr_pages)
*nr_pages = slot->npages - (gfn - slot->base_gfn);
return __gfn_to_hva_memslot(slot, gfn);
}
static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
gfn_t *nr_pages)
{
return __gfn_to_hva_many(slot, gfn, nr_pages, true);
}
unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
gfn_t gfn)
{
return gfn_to_hva_many(slot, gfn, NULL);
}
EXPORT_SYMBOL_GPL(gfn_to_hva_memslot);
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);
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);
/*
* Return the hva of a @gfn and the R/W attribute if possible.
*
* @slot: the kvm_memory_slot which contains @gfn
* @gfn: the gfn to be translated
* @writable: used to return the read/write attribute of the @slot if the hva
* is valid and @writable is not NULL
*/
unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot,
gfn_t gfn, bool *writable)
{
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;
}
unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable)
{
struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn);
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 inline int check_user_page_hwpoison(unsigned long addr)
{
int rc, flags = FOLL_HWPOISON | FOLL_WRITE;
rc = get_user_pages(addr, 1, flags, NULL, NULL);
return rc == -EHWPOISON;
}
/*
* The fast path to get the writable pfn which will be stored in @pfn,
* true indicates success, otherwise false is returned. It's also the
* only part that runs if we can are in atomic context.
*/
static bool hva_to_pfn_fast(unsigned long addr, bool write_fault,
bool *writable, kvm_pfn_t *pfn)
{
struct page *page[1];
int npages;
/*
* 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;
}
return false;
}
/*
* 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, kvm_pfn_t *pfn)
{
unsigned int flags = FOLL_HWPOISON;
struct page *page;
int npages = 0;
might_sleep();
if (writable)
*writable = write_fault;
if (write_fault)
flags |= FOLL_WRITE;
if (async)
flags |= FOLL_NOWAIT;
npages = get_user_pages_unlocked(addr, 1, &page, flags);
if (npages != 1)
return npages;
/* map read fault as writable if possible */
if (unlikely(!write_fault) && writable) {
struct page *wpage;
if (__get_user_pages_fast(addr, 1, 1, &wpage) == 1) {
*writable = true;
put_page(page);
page = wpage;
}
}
*pfn = page_to_pfn(page);
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;
}
static int hva_to_pfn_remapped(struct vm_area_struct *vma,
unsigned long addr, bool *async,
bool write_fault, bool *writable,
kvm_pfn_t *p_pfn)
{
unsigned long pfn;
int r;
r = follow_pfn(vma, addr, &pfn);
if (r) {
/*
* get_user_pages fails for VM_IO and VM_PFNMAP vmas and does
* not call the fault handler, so do it here.
*/
bool unlocked = false;
r = fixup_user_fault(current, current->mm, addr,
(write_fault ? FAULT_FLAG_WRITE : 0),
&unlocked);
if (unlocked)
return -EAGAIN;
if (r)
return r;
r = follow_pfn(vma, addr, &pfn);
if (r)
return r;
}
if (writable)
*writable = true;
/*
* Get a reference here because callers of *hva_to_pfn* and
* *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the
* returned pfn. This is only needed if the VMA has VM_MIXEDMAP
* set, but the kvm_get_pfn/kvm_release_pfn_clean pair will
* simply do nothing for reserved pfns.
*
* Whoever called remap_pfn_range is also going to call e.g.
* unmap_mapping_range before the underlying pages are freed,
* causing a call to our MMU notifier.
*/
kvm_get_pfn(pfn);
*p_pfn = pfn;
return 0;
}
/*
* 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 kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
bool write_fault, bool *writable)
{
struct vm_area_struct *vma;
kvm_pfn_t pfn = 0;
int npages, r;
/* we can do it either atomically or asynchronously, not both */
BUG_ON(atomic && async);
if (hva_to_pfn_fast(addr, 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(&current->mm->mmap_sem);
if (npages == -EHWPOISON ||
(!async && check_user_page_hwpoison(addr))) {
pfn = KVM_PFN_ERR_HWPOISON;
goto exit;
}
retry:
vma = find_vma_intersection(current->mm, addr, addr + 1);
if (vma == NULL)
pfn = KVM_PFN_ERR_FAULT;
else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) {
r = hva_to_pfn_remapped(vma, addr, async, write_fault, writable, &pfn);
if (r == -EAGAIN)
goto retry;
if (r < 0)
pfn = KVM_PFN_ERR_FAULT;
} else {
if (async && vma_is_valid(vma, write_fault))
*async = true;
pfn = KVM_PFN_ERR_FAULT;
}
exit:
up_read(&current->mm->mmap_sem);
return pfn;
}
kvm_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) {
if (writable)
*writable = false;
return KVM_PFN_ERR_RO_FAULT;
}
if (kvm_is_error_hva(addr)) {
if (writable)
*writable = false;
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);
}
EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot);
kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
bool *writable)
{
return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, NULL,
write_fault, writable);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
kvm_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);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot);
kvm_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);
kvm_pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn)
{
return gfn_to_pfn_memslot_atomic(gfn_to_memslot(kvm, gfn), gfn);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn_atomic);
kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn)
{
return gfn_to_pfn_memslot_atomic(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn_atomic);
kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn)
{
return gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn);
}
EXPORT_SYMBOL_GPL(gfn_to_pfn);
kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn)
{
return gfn_to_pfn_memslot(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn);
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 = 0;
addr = gfn_to_hva_many(slot, 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(kvm_pfn_t pfn)
{
if (is_error_noslot_pfn(pfn))
return KVM_ERR_PTR_BAD_PAGE;
if (kvm_is_reserved_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)
{
kvm_pfn_t pfn;
pfn = gfn_to_pfn(kvm, gfn);
return kvm_pfn_to_page(pfn);
}
EXPORT_SYMBOL_GPL(gfn_to_page);
struct page *kvm_vcpu_gfn_to_page(struct kvm_vcpu *vcpu, gfn_t gfn)
{
kvm_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));
kvm_release_pfn_clean(page_to_pfn(page));
}
EXPORT_SYMBOL_GPL(kvm_release_page_clean);
void kvm_release_pfn_clean(kvm_pfn_t pfn)
{
if (!is_error_noslot_pfn(pfn) && !kvm_is_reserved_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(kvm_pfn_t pfn)
{
kvm_set_pfn_dirty(pfn);
kvm_release_pfn_clean(pfn);
}
EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
void kvm_set_pfn_dirty(kvm_pfn_t pfn)
{
if (!kvm_is_reserved_pfn(pfn)) {
struct page *page = pfn_to_page(pfn);
if (!PageReserved(page))
SetPageDirty(page);
}
}
EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
void kvm_set_pfn_accessed(kvm_pfn_t pfn)
{
if (!kvm_is_reserved_pfn(pfn))
mark_page_accessed(pfn_to_page(pfn));
}
EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
void kvm_get_pfn(kvm_pfn_t pfn)
{
if (!kvm_is_reserved_pfn(pfn))
get_page(pfn_to_page(pfn));
}
EXPORT_SYMBOL_GPL(kvm_get_pfn);
static int next_segment(unsigned long len, int offset)
{
if (len > PAGE_SIZE - offset)
return PAGE_SIZE - offset;
else
return len;
}
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_memslot_prot(slot, gfn, NULL);
if (kvm_is_error_hva(addr))
return -EFAULT;
r = __copy_from_user(data, (void __user *)addr + offset, len);
if (r)
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;
int seg;
int offset = offset_in_page(gpa);
int ret;
while ((seg = next_segment(len, offset)) != 0) {
ret = kvm_read_guest_page(kvm, gfn, data, offset, seg);
if (ret < 0)
return ret;
offset = 0;
len -= seg;
data += seg;
++gfn;
}
return 0;
}
EXPORT_SYMBOL_GPL(kvm_read_guest);
int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
int seg;
int offset = offset_in_page(gpa);
int ret;
while ((seg = next_segment(len, offset)) != 0) {
ret = kvm_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_memslot_prot(slot, gfn, NULL);
if (kvm_is_error_hva(addr))
return -EFAULT;
pagefault_disable();
r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len);
pagefault_enable();
if (r)
return -EFAULT;
return 0;
}
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_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_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)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
int seg;
int offset = offset_in_page(gpa);
int ret;
while ((seg = next_segment(len, offset)) != 0) {
ret = kvm_write_guest_page(kvm, gfn, data, offset, seg);
if (ret < 0)
return ret;
offset = 0;
len -= seg;
data += seg;
++gfn;
}
return 0;
}
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);
static int __kvm_gfn_to_hva_cache_init(struct kvm_memslots *slots,
struct gfn_to_hva_cache *ghc,
gpa_t gpa, unsigned long len)
{
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;
int r = start_gfn <= end_gfn ? 0 : -EINVAL;
ghc->gpa = gpa;
ghc->generation = slots->generation;
ghc->len = len;
ghc->hva = KVM_HVA_ERR_BAD;
/*
* If the requested region crosses two memslots, we still
* verify that the entire region is valid here.
*/
while (!r && start_gfn <= end_gfn) {
ghc->memslot = __gfn_to_memslot(slots, start_gfn);
ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn,
&nr_pages_avail);
if (kvm_is_error_hva(ghc->hva))
r = -EFAULT;
start_gfn += nr_pages_avail;
}
/* Use the slow path for cross page reads and writes. */
if (!r && nr_pages_needed == 1)
ghc->hva += offset;
else
ghc->memslot = NULL;
return r;
}
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);
return __kvm_gfn_to_hva_cache_init(slots, ghc, gpa, len);
}
EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init);
int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned int offset,
unsigned long len)
{
struct kvm_memslots *slots = kvm_memslots(kvm);
int r;
gpa_t gpa = ghc->gpa + offset;
BUG_ON(len + offset > ghc->len);
if (slots->generation != ghc->generation)
__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len);
if (unlikely(!ghc->memslot))
return kvm_write_guest(kvm, gpa, data, len);
if (kvm_is_error_hva(ghc->hva))
return -EFAULT;
r = __copy_to_user((void __user *)ghc->hva + offset, data, len);
if (r)
return -EFAULT;
mark_page_dirty_in_slot(ghc->memslot, gpa >> PAGE_SHIFT);
return 0;
}
EXPORT_SYMBOL_GPL(kvm_write_guest_offset_cached);
int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
void *data, unsigned long len)
{
return kvm_write_guest_offset_cached(kvm, ghc, data, 0, len);
}
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(slots, 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)
{
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);
int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len)
{
gfn_t gfn = gpa >> PAGE_SHIFT;
int seg;
int offset = offset_in_page(gpa);
int ret;
while ((seg = next_segment(len, offset)) != 0) {
ret = kvm_clear_guest_page(kvm, gfn, offset, seg);
if (ret < 0)
return ret;
offset = 0;
len -= seg;
++gfn;
}
return 0;
}
EXPORT_SYMBOL_GPL(kvm_clear_guest);
static void mark_page_dirty_in_slot(struct kvm_memory_slot *memslot,
gfn_t gfn)
{
if (memslot && memslot->dirty_bitmap) {
unsigned long rel_gfn = gfn - memslot->base_gfn;
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(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);
void kvm_sigset_activate(struct kvm_vcpu *vcpu)
{
if (!vcpu->sigset_active)
return;
/*
* This does a lockless modification of ->real_blocked, which is fine
* because, only current can change ->real_blocked and all readers of
* ->real_blocked don't care as long ->real_blocked is always a subset
* of ->blocked.
*/
sigprocmask(SIG_SETMASK, &vcpu->sigset, &current->real_blocked);
}
void kvm_sigset_deactivate(struct kvm_vcpu *vcpu)
{
if (!vcpu->sigset_active)
return;
sigprocmask(SIG_SETMASK, &current->real_blocked, NULL);
sigemptyset(&current->real_blocked);
}
static void grow_halt_poll_ns(struct kvm_vcpu *vcpu)
{
unsigned int old, val, grow;
old = val = vcpu->halt_poll_ns;
grow = READ_ONCE(halt_poll_ns_grow);
/* 10us base */
if (val == 0 && grow)
val = 10000;
else
val *= 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)
{
unsigned int old, val, shrink;
old = val = vcpu->halt_poll_ns;
shrink = READ_ONCE(halt_poll_ns_shrink);
if (shrink == 0)
val = 0;
else
val /= 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)
{
int ret = -EINTR;
int idx = srcu_read_lock(&vcpu->kvm->srcu);
if (kvm_arch_vcpu_runnable(vcpu)) {
kvm_make_request(KVM_REQ_UNHALT, vcpu);
goto out;
}
if (kvm_cpu_has_pending_timer(vcpu))
goto out;
if (signal_pending(current))
goto out;
ret = 0;
out:
srcu_read_unlock(&vcpu->kvm->srcu, idx);
return ret;
}
/*
* The vCPU has executed a HLT instruction with in-kernel mode enabled.
*/
void kvm_vcpu_block(struct kvm_vcpu *vcpu)
{
ktime_t start, cur;
DECLARE_SWAITQUEUE(wait);
bool waited = false;
u64 block_ns;
start = cur = ktime_get();
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
* arrives.
*/
if (kvm_vcpu_check_block(vcpu) < 0) {
++vcpu->stat.halt_successful_poll;
if (!vcpu_valid_wakeup(vcpu))
++vcpu->stat.halt_poll_invalid;
goto out;
}
cur = ktime_get();
} while (single_task_running() && ktime_before(cur, stop));
}
kvm_arch_vcpu_blocking(vcpu);
for (;;) {
prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
if (kvm_vcpu_check_block(vcpu) < 0)
break;
waited = true;
schedule();
}
finish_swait(&vcpu->wq, &wait);
cur = ktime_get();
kvm_arch_vcpu_unblocking(vcpu);
out:
block_ns = ktime_to_ns(cur) - ktime_to_ns(start);
if (!vcpu_valid_wakeup(vcpu))
shrink_halt_poll_ns(vcpu);
else 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, vcpu_valid_wakeup(vcpu));
kvm_arch_vcpu_block_finish(vcpu);
}
EXPORT_SYMBOL_GPL(kvm_vcpu_block);
bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
{
struct swait_queue_head *wqp;
wqp = kvm_arch_vcpu_wq(vcpu);
if (swq_has_sleeper(wqp)) {
swake_up_one(wqp);
++vcpu->stat.halt_wakeup;
return true;
}
return false;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up);
#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)
{
int me;
int cpu = vcpu->cpu;
if (kvm_vcpu_wake_up(vcpu))
return;
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(pid, PIDTYPE_PID);
rcu_read_unlock();
if (!task)
return ret;
ret = yield_to(task, 1);
put_task_struct(task);
return ret;
}
EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
/*
* 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)
{
#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
bool eligible;
eligible = !vcpu->spin_loop.in_spin_loop ||
vcpu->spin_loop.dy_eligible;
if (vcpu->spin_loop.in_spin_loop)
kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible);
return eligible;
#else
return true;
#endif
}
void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
{
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 (!READ_ONCE(vcpu->preempted))
continue;
if (vcpu == me)
continue;
if (swait_active(&vcpu->wq) && !kvm_arch_vcpu_runnable(vcpu))
continue;
if (yield_to_kernel_mode && !kvm_arch_vcpu_in_kernel(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);
static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf)
{
struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data;
struct page *page;
if (vmf->pgoff == 0)
page = virt_to_page(vcpu->run);
#ifdef CONFIG_X86
else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET)
page = virt_to_page(vcpu->arch.pio_data);
#endif
#ifdef CONFIG_KVM_MMIO
else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET)
page = virt_to_page(vcpu->kvm->coalesced_mmio_ring);
#endif
else
return kvm_arch_vcpu_fault(vcpu, vmf);
get_page(page);
vmf->page = page;
return 0;
}
static const struct vm_operations_struct kvm_vcpu_vm_ops = {
.fault = kvm_vcpu_fault,
};
static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma)
{
vma->vm_ops = &kvm_vcpu_vm_ops;
return 0;
}
static int kvm_vcpu_release(struct inode *inode, struct file *filp)
{
struct kvm_vcpu *vcpu = filp->private_data;
debugfs_remove_recursive(vcpu->debugfs_dentry);
kvm_put_kvm(vcpu->kvm);
return 0;
}
static struct file_operations kvm_vcpu_fops = {
.release = kvm_vcpu_release,
.unlocked_ioctl = kvm_vcpu_ioctl,
.mmap = kvm_vcpu_mmap,
.llseek = noop_llseek,
KVM_COMPAT(kvm_vcpu_compat_ioctl),
};
/*
* Allocates an inode for the vcpu.
*/
static int create_vcpu_fd(struct kvm_vcpu *vcpu)
{
char name[8 + 1 + ITOA_MAX_LEN + 1];
snprintf(name, sizeof(name), "kvm-vcpu:%d", vcpu->vcpu_id);
return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC);
}
static int kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
{
char dir_name[ITOA_MAX_LEN * 2];
int ret;
if (!kvm_arch_has_vcpu_debugfs())
return 0;
if (!debugfs_initialized())
return 0;
snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id);
vcpu->debugfs_dentry = debugfs_create_dir(dir_name,
vcpu->kvm->debugfs_dentry);
if (!vcpu->debugfs_dentry)
return -ENOMEM;
ret = kvm_arch_create_vcpu_debugfs(vcpu);
if (ret < 0) {
debugfs_remove_recursive(vcpu->debugfs_dentry);
return ret;
}
return 0;
}
/*
* Creates some virtual cpus. Good luck creating more than one.
*/
static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
{
int r;
struct kvm_vcpu *vcpu;
if (id >= KVM_MAX_VCPU_ID)
return -EINVAL;
mutex_lock(&kvm->lock);
if (kvm->created_vcpus == KVM_MAX_VCPUS) {
mutex_unlock(&kvm->lock);
return -EINVAL;
}
kvm->created_vcpus++;
mutex_unlock(&kvm->lock);
vcpu = kvm_arch_vcpu_create(kvm, id);
if (IS_ERR(vcpu)) {
r = PTR_ERR(vcpu);
goto vcpu_decrement;
}
preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops);
r = kvm_arch_vcpu_setup(vcpu);
if (r)
goto vcpu_destroy;
r = kvm_create_vcpu_debugfs(vcpu);
if (r)
goto vcpu_destroy;
mutex_lock(&kvm->lock);
if (kvm_get_vcpu_by_id(kvm, id)) {
r = -EEXIST;
goto unlock_vcpu_destroy;
}
BUG_ON(kvm->vcpus[atomic_read(&kvm->online_vcpus)]);
/* Now it's all set up, let userspace reach it */
kvm_get_kvm(kvm);
r = create_vcpu_fd(vcpu);
if (r < 0) {
kvm_put_kvm(kvm);
goto unlock_vcpu_destroy;
}
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);
mutex_unlock(&kvm->lock);
kvm_arch_vcpu_postcreate(vcpu);
return r;
unlock_vcpu_destroy:
mutex_unlock(&kvm->lock);
debugfs_remove_recursive(vcpu->debugfs_dentry);
vcpu_destroy:
kvm_arch_vcpu_destroy(vcpu);
vcpu_decrement:
mutex_lock(&kvm->lock);
kvm->created_vcpus--;
mutex_unlock(&kvm->lock);
return r;
}
static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset)
{
if (sigset) {
sigdelsetmask(sigset, sigmask(SIGKILL)|sigmask(SIGSTOP));
vcpu->sigset_active = 1;
vcpu->sigset = *sigset;
} else
vcpu->sigset_active = 0;
return 0;
}
static long kvm_vcpu_ioctl(struct file *filp,
unsigned int ioctl, unsigned long arg)
{
struct kvm_vcpu *vcpu = filp->private_data;
void __user *argp = (void __user *)arg;
int r;
struct kvm_fpu *fpu = NULL;
struct kvm_sregs *kvm_sregs = NULL;
if (vcpu->kvm->mm != current->mm)
return -EIO;
if (unlikely(_IOC_TYPE(ioctl) != KVMIO))
return -EINVAL;
/*
* Some architectures have vcpu ioctls that are asynchronous to vcpu
* execution; mutex_lock() would break them.
*/
r = kvm_arch_vcpu_async_ioctl(filp, ioctl, arg);
if (r != -ENOIOCTLCMD)
return r;
if (mutex_lock_killable(&vcpu->mutex))
return -EINTR;
switch (ioctl) {
case KVM_RUN: {
struct pid *oldpid;
r = -EINVAL;
if (arg)
goto out;
oldpid = rcu_access_pointer(vcpu->pid);
if (unlikely(oldpid != task_pid(current))) {
/* The thread running this VCPU changed. */
struct pid *newpid;
r = kvm_arch_vcpu_run_pid_change(vcpu);
if (r)
break;
newpid = get_task_pid(current, PIDTYPE_PID);
rcu_assign_pointer(vcpu->pid, newpid);
if (oldpid)
synchronize_rcu();
put_pid(oldpid);
}
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;
r = -ENOMEM;
kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL);
if (!kvm_regs)
goto out;
r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs);
if (r)
goto out_free1;
r = -EFAULT;
if (copy_to_user(argp, kvm_regs, sizeof(struct kvm_regs)))
goto out_free1;
r = 0;
out_free1:
kfree(kvm_regs);
break;
}
case KVM_SET_REGS: {
struct kvm_regs *kvm_regs;
r = -ENOMEM;
kvm_regs = memdup_user(argp, sizeof(*kvm_regs));
if (IS_ERR(kvm_regs)) {
r = PTR_ERR(kvm_regs);
goto out;
}
r = kvm_arch_vcpu_ioctl_set_regs(vcpu, kvm_regs);
kfree(kvm_regs);
break;
}
case KVM_GET_SREGS: {
kvm_sregs = kzalloc(sizeof(struct kvm_sregs), GFP_KERNEL);
r = -ENOMEM;
if (!kvm_sregs)
goto out;
r = kvm_arch_vcpu_ioctl_get_sregs(vcpu, kvm_sregs);
if (r)
goto out;
r = -EFAULT;
if (copy_to_user(argp, kvm_sregs, sizeof(struct kvm_sregs)))
goto out;
r = 0;
break;
}
case KVM_SET_SREGS: {
kvm_sregs = 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);
break;
}
case KVM_GET_MP_STATE: {
struct kvm_mp_state mp_state;
r = kvm_arch_vcpu_ioctl_get_mpstate(vcpu, &mp_state);
if (r)
goto out;
r = -EFAULT;
if (copy_to_user(argp, &mp_state, sizeof(mp_state)))
goto out;
r = 0;
break;
}
case KVM_SET_MP_STATE: {
struct kvm_mp_state mp_state;
r = -EFAULT;
if (copy_from_user(&mp_state, argp, sizeof(mp_state)))
goto out;
r = kvm_arch_vcpu_ioctl_set_mpstate(vcpu, &mp_state);
break;
}
case KVM_TRANSLATE: {
struct kvm_translation tr;
r = -EFAULT;
if (copy_from_user(&tr, argp, sizeof(tr)))
goto out;
r = kvm_arch_vcpu_ioctl_translate(vcpu, &tr);
if (r)
goto out;
r = -EFAULT;
if (copy_to_user(argp, &tr, sizeof(tr)))
goto out;
r = 0;
break;
}
case KVM_SET_GUEST_DEBUG: {
struct kvm_guest_debug dbg;
r = -EFAULT;
if (copy_from_user(&dbg, argp, sizeof(dbg)))
goto out;
r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg);
break;
}
case KVM_SET_SIGNAL_MASK: {
struct kvm_signal_mask __user *sigmask_arg = argp;
struct kvm_signal_mask kvm_sigmask;
sigset_t sigset, *p;
p = NULL;
if (argp) {
r = -EFAULT;
if (copy_from_user(&kvm_sigmask, argp,
sizeof(kvm_sigmask)))
goto out;
r = -EINVAL;
if (kvm_sigmask.len != sizeof(sigset))
goto out;
r = -EFAULT;
if (copy_from_user(&sigset, sigmask_arg->sigset,
sizeof(sigset)))
goto out;
p = &sigset;
}
r = kvm_vcpu_ioctl_set_sigmask(vcpu, p);
break;
}
case KVM_GET_FPU: {
fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL);
r = -ENOMEM;
if (!fpu)
goto out;
r = kvm_arch_vcpu_ioctl_get_fpu(vcpu, fpu);
if (r)
goto out;