#include <asm/processor.h>
#include <asm/ioctl.h>
#include <linux/uaccess.h>
-#include <asm/pgtable.h>
#include "coalesced_mmio.h"
#include "async_pf.h"
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)
+__weak void kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
+ unsigned long start, unsigned long end)
{
- return 0;
}
bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
vcpu->kvm = kvm;
vcpu->vcpu_id = id;
vcpu->pid = NULL;
- init_swait_queue_head(&vcpu->wq);
+ rcuwait_init(&vcpu->wait);
kvm_async_pf_vcpu_init(vcpu);
vcpu->pre_pcpu = -1;
return container_of(mn, struct kvm, mmu_notifier);
}
+static void kvm_mmu_notifier_invalidate_range(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long start, unsigned long end)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ int idx;
+
+ idx = srcu_read_lock(&kvm->srcu);
+ kvm_arch_mmu_notifier_invalidate_range(kvm, start, end);
+ srcu_read_unlock(&kvm->srcu, idx);
+}
+
static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long address,
{
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);
kvm_flush_remote_tlbs(kvm);
spin_unlock(&kvm->mmu_lock);
-
- ret = kvm_arch_mmu_notifier_invalidate_range(kvm, range->start,
- range->end,
- mmu_notifier_range_blockable(range));
-
srcu_read_unlock(&kvm->srcu, idx);
- return ret;
+ return 0;
}
static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
}
static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
+ .invalidate_range = kvm_mmu_notifier_invalidate_range,
.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,
goto out_err_no_arch_destroy_vm;
}
+ kvm->max_halt_poll_ns = halt_poll_ns;
+
r = kvm_arch_init_vm(kvm, type);
if (r)
goto out_err_no_arch_destroy_vm;
if (mem->guest_phys_addr & (PAGE_SIZE - 1))
return -EINVAL;
/* We can read the guest memory with __xxx_user() later on. */
- if ((id < KVM_USER_MEM_SLOTS) &&
- ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
+ if ((mem->userspace_addr & (PAGE_SIZE - 1)) ||
!access_ok((void __user *)(unsigned long)mem->userspace_addr,
- mem->memory_size)))
+ mem->memory_size))
return -EINVAL;
if (as_id >= KVM_ADDRESS_SPACE_NUM || id >= KVM_MEM_SLOTS_NUM)
return -EINVAL;
{
return __gfn_to_memslot(kvm_vcpu_memslots(vcpu), gfn);
}
+EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_memslot);
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;
+ return kvm_is_visible_memslot(memslot);
}
EXPORT_SYMBOL_GPL(kvm_is_visible_gfn);
if (kvm_is_error_hva(addr))
return PAGE_SIZE;
- down_read(¤t->mm->mmap_sem);
+ mmap_read_lock(current->mm);
vma = find_vma(current->mm, addr);
if (!vma)
goto out;
size = vma_kernel_pagesize(vma);
out:
- up_read(¤t->mm->mmap_sem);
+ mmap_read_unlock(current->mm);
return size;
}
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
if (!(write_fault || writable))
return false;
- npages = __get_user_pages_fast(addr, 1, 1, page);
- if (npages == 1) {
+ if (get_user_page_fast_only(addr, FOLL_WRITE, page)) {
*pfn = page_to_pfn(page[0]);
if (writable)
if (unlikely(!write_fault) && writable) {
struct page *wpage;
- if (__get_user_pages_fast(addr, 1, 1, &wpage) == 1) {
+ if (get_user_page_fast_only(addr, FOLL_WRITE, &wpage)) {
*writable = true;
put_page(page);
page = wpage;
if (npages == 1)
return pfn;
- down_read(¤t->mm->mmap_sem);
+ mmap_read_lock(current->mm);
if (npages == -EHWPOISON ||
(!async && check_user_page_hwpoison(addr))) {
pfn = KVM_PFN_ERR_HWPOISON;
pfn = KVM_PFN_ERR_FAULT;
}
exit:
- up_read(¤t->mm->mmap_sem);
+ mmap_read_unlock(current->mm);
return pfn;
}
if (entry < nr_pages)
return 0;
- return __get_user_pages_fast(addr, nr_pages, 1, pages);
+ return get_user_pages_fast_only(addr, nr_pages, FOLL_WRITE, pages);
}
EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);
}
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)
+int kvm_read_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 > ghc->len);
+ BUG_ON(len + offset > ghc->len);
if (slots->generation != ghc->generation) {
if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len))
return -EFAULT;
if (unlikely(!ghc->memslot))
- return kvm_read_guest(kvm, ghc->gpa, data, len);
+ return kvm_read_guest(kvm, gpa, data, len);
- r = __copy_from_user(data, (void __user *)ghc->hva, len);
+ r = __copy_from_user(data, (void __user *)ghc->hva + offset, len);
if (r)
return -EFAULT;
return 0;
}
+EXPORT_SYMBOL_GPL(kvm_read_guest_offset_cached);
+
+int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc,
+ void *data, unsigned long len)
+{
+ return kvm_read_guest_offset_cached(kvm, ghc, data, 0, len);
+}
EXPORT_SYMBOL_GPL(kvm_read_guest_cached);
int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len)
return ret;
}
+static inline void
+update_halt_poll_stats(struct kvm_vcpu *vcpu, u64 poll_ns, bool waited)
+{
+ if (waited)
+ vcpu->stat.halt_poll_fail_ns += poll_ns;
+ else
+ vcpu->stat.halt_poll_success_ns += poll_ns;
+}
+
/*
* 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);
+ ktime_t start, cur, poll_end;
bool waited = false;
u64 block_ns;
kvm_arch_vcpu_blocking(vcpu);
- start = cur = ktime_get();
+ start = cur = poll_end = ktime_get();
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_poll_invalid;
goto out;
}
- cur = ktime_get();
+ poll_end = cur = ktime_get();
} while (single_task_running() && ktime_before(cur, stop));
}
+ prepare_to_rcuwait(&vcpu->wait);
for (;;) {
- prepare_to_swait_exclusive(&vcpu->wq, &wait, TASK_INTERRUPTIBLE);
+ set_current_state(TASK_INTERRUPTIBLE);
if (kvm_vcpu_check_block(vcpu) < 0)
break;
waited = true;
schedule();
}
-
- finish_swait(&vcpu->wq, &wait);
+ finish_rcuwait(&vcpu->wait);
cur = ktime_get();
out:
kvm_arch_vcpu_unblocking(vcpu);
block_ns = ktime_to_ns(cur) - ktime_to_ns(start);
+ update_halt_poll_stats(
+ vcpu, ktime_to_ns(ktime_sub(poll_end, start)), waited);
+
if (!kvm_arch_no_poll(vcpu)) {
if (!vcpu_valid_wakeup(vcpu)) {
shrink_halt_poll_ns(vcpu);
- } else if (halt_poll_ns) {
+ } else if (vcpu->kvm->max_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)
+ else if (vcpu->halt_poll_ns &&
+ block_ns > vcpu->kvm->max_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)
+ else if (vcpu->halt_poll_ns < vcpu->kvm->max_halt_poll_ns &&
+ block_ns < vcpu->kvm->max_halt_poll_ns)
grow_halt_poll_ns(vcpu);
} else {
vcpu->halt_poll_ns = 0;
bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu)
{
- struct swait_queue_head *wqp;
+ struct rcuwait *waitp;
- wqp = kvm_arch_vcpu_wq(vcpu);
- if (swq_has_sleeper(wqp)) {
- swake_up_one(wqp);
+ waitp = kvm_arch_vcpu_get_wait(vcpu);
+ if (rcuwait_wake_up(waitp)) {
WRITE_ONCE(vcpu->ready, true);
++vcpu->stat.halt_wakeup;
return true;
*
* (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.
+ * Set at the beginning 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
continue;
if (vcpu == me)
continue;
- if (swait_active(&vcpu->wq) && !vcpu_dy_runnable(vcpu))
+ if (rcuwait_active(&vcpu->wait) &&
+ !vcpu_dy_runnable(vcpu))
continue;
if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode &&
!kvm_arch_vcpu_in_kernel(vcpu))
{
struct kvm_vcpu *vcpu = filp->private_data;
- debugfs_remove_recursive(vcpu->debugfs_dentry);
kvm_put_kvm(vcpu->kvm);
return 0;
}
static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
{
#ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS
+ struct dentry *debugfs_dentry;
char dir_name[ITOA_MAX_LEN * 2];
if (!debugfs_initialized())
return;
snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id);
- vcpu->debugfs_dentry = debugfs_create_dir(dir_name,
- vcpu->kvm->debugfs_dentry);
+ debugfs_dentry = debugfs_create_dir(dir_name,
+ vcpu->kvm->debugfs_dentry);
- kvm_arch_create_vcpu_debugfs(vcpu);
+ kvm_arch_create_vcpu_debugfs(vcpu, debugfs_dentry);
#endif
}
if (r)
goto vcpu_free_run_page;
- kvm_create_vcpu_debugfs(vcpu);
-
mutex_lock(&kvm->lock);
if (kvm_get_vcpu_by_id(kvm, id)) {
r = -EEXIST;
mutex_unlock(&kvm->lock);
kvm_arch_vcpu_postcreate(vcpu);
+ kvm_create_vcpu_debugfs(vcpu);
return r;
unlock_vcpu_destroy:
mutex_unlock(&kvm->lock);
- debugfs_remove_recursive(vcpu->debugfs_dentry);
kvm_arch_vcpu_destroy(vcpu);
vcpu_free_run_page:
free_page((unsigned long)vcpu->run);
synchronize_rcu();
put_pid(oldpid);
}
- r = kvm_arch_vcpu_ioctl_run(vcpu, vcpu->run);
+ r = kvm_arch_vcpu_ioctl_run(vcpu);
trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
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);
if (kvm_sigmask.len != sizeof(compat_sigset_t))
goto out;
r = -EFAULT;
- if (get_compat_sigset(&sigset, (void *)sigmask_arg->sigset))
+ if (get_compat_sigset(&sigset,
+ (compat_sigset_t __user *)sigmask_arg->sigset))
goto out;
r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset);
} else
case KVM_CAP_IOEVENTFD_ANY_LENGTH:
case KVM_CAP_CHECK_EXTENSION_VM:
case KVM_CAP_ENABLE_CAP_VM:
+ case KVM_CAP_HALT_POLL:
return 1;
#ifdef CONFIG_KVM_MMIO
case KVM_CAP_COALESCED_MMIO:
return 0;
}
#endif
+ case KVM_CAP_HALT_POLL: {
+ if (cap->flags || cap->args[0] != (unsigned int)cap->args[0])
+ return -EINVAL;
+
+ kvm->max_halt_poll_ns = cap->args[0];
+ return 0;
+ }
default:
return kvm_vm_ioctl_enable_cap(kvm, cap);
}
if (routing.flags)
goto out;
if (routing.nr) {
- r = -ENOMEM;
- entries = vmalloc(array_size(sizeof(*entries),
- routing.nr));
- if (!entries)
- goto out;
- r = -EFAULT;
urouting = argp;
- if (copy_from_user(entries, urouting->entries,
- routing.nr * sizeof(*entries)))
- goto out_free_irq_routing;
+ entries = vmemdup_user(urouting->entries,
+ array_size(sizeof(*entries),
+ routing.nr));
+ if (IS_ERR(entries)) {
+ r = PTR_ERR(entries);
+ goto out;
+ }
}
r = kvm_set_irq_routing(kvm, entries, routing.nr,
routing.flags);
-out_free_irq_routing:
- vfree(entries);
+ kvfree(entries);
break;
}
#endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */
return vcpu;
}
+EXPORT_SYMBOL_GPL(kvm_get_running_vcpu);
/**
* kvm_get_running_vcpus - get the per-CPU array of currently running vcpus.