static int handle_test_block(struct kvm_vcpu *vcpu)
{
unsigned long hva;
gpa_t addr;
int reg2;
if (vcpu->arch.sie_block->gpsw.mask & PSW_MASK_PSTATE)
return kvm_s390_inject_program_int(vcpu, PGM_PRIVILEGED_OP);
kvm_s390_get_regs_rre(vcpu, NULL, ®2);
addr = vcpu->run->s.regs.gprs[reg2] & PAGE_MASK;
addr = kvm_s390_real_to_abs(vcpu, addr);
hva = gfn_to_hva(vcpu->kvm, gpa_to_gfn(addr));
if (kvm_is_error_hva(hva))
return kvm_s390_inject_program_int(vcpu, PGM_ADDRESSING);
/*
* We don't expect errors on modern systems, and do not care
* about storage keys (yet), so let's just clear the page.
*/
if (clear_user((void __user *)hva, PAGE_SIZE) != 0)
return -EFAULT;
kvm_s390_set_psw_cc(vcpu, 0);
vcpu->run->s.regs.gprs[0] = 0;
return 0;
}
void kvm_let_guest_timer_more_accurat(struct kvm_vcpu *vcpu)
{
gpa_t gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, vcpu->arch.regs[0]);
gfn_t gfn = gpa >> 12;
u32 hva_tmp = gfn_to_hva(vcpu->kvm, gfn);
struct timeval *tv = hva_tmp | (gpa & ~PAGE_MASK);
extern struct timezone sys_tz;
do_gettimeofday(tv);
if (vcpu->arch.regs[1] != 0) {
gpa = vcpu->arch.mmu.gva_to_gpa(vcpu, vcpu->arch.regs[1]);
gfn = gpa >> 12;
hva_tmp = gfn_to_hva(vcpu->kvm, gfn);
struct timezone *tz = hva_tmp | (gpa & ~PAGE_MASK);
*tz = sys_tz;
}
int kvm_setup_async_pf(struct kvm_vcpu *vcpu, gva_t gva, gfn_t gfn,
struct kvm_arch_async_pf *arch)
{
struct kvm_async_pf *work;
if (vcpu->async_pf.queued >= ASYNC_PF_PER_VCPU)
return 0;
/* setup delayed work */
/*
* do alloc nowait since if we are going to sleep anyway we
* may as well sleep faulting in page
*/
work = kmem_cache_zalloc(async_pf_cache, GFP_NOWAIT);
if (!work)
return 0;
work->wakeup_all = false;
work->vcpu = vcpu;
work->gva = gva;
work->addr = gfn_to_hva(vcpu->kvm, gfn);
work->arch = *arch;
work->mm = current->mm;
atomic_inc(&work->mm->mm_users);
kvm_get_kvm(work->vcpu->kvm);
/* this can't really happen otherwise gfn_to_pfn_async
would succeed */
if (unlikely(kvm_is_error_hva(work->addr)))
goto retry_sync;
INIT_WORK(&work->work, async_pf_execute);
if (!schedule_work(&work->work))
goto retry_sync;
list_add_tail(&work->queue, &vcpu->async_pf.queue);
vcpu->async_pf.queued++;
kvm_arch_async_page_not_present(vcpu, work);
return 1;
retry_sync:
kvm_put_kvm(work->vcpu->kvm);
mmput(work->mm);
kmem_cache_free(async_pf_cache, work);
return 0;
}
static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
struct kvm_memory_slot *memslot,
unsigned long fault_status)
{
int ret;
bool write_fault, writable, hugetlb = false, force_pte = false;
unsigned long mmu_seq;
gfn_t gfn = fault_ipa >> PAGE_SHIFT;
unsigned long hva = gfn_to_hva(vcpu->kvm, gfn);
struct kvm *kvm = vcpu->kvm;
struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
struct vm_area_struct *vma;
pfn_t pfn;
write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu));
if (fault_status == FSC_PERM && !write_fault) {
kvm_err("Unexpected L2 read permission error\n");
return -EFAULT;
}
/* Let's check if we will get back a huge page backed by hugetlbfs */
down_read(¤t->mm->mmap_sem);
vma = find_vma_intersection(current->mm, hva, hva + 1);
if (is_vm_hugetlb_page(vma)) {
hugetlb = true;
gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
} else {
/*
* Pages belonging to memslots that don't have the same
* alignment for userspace and IPA cannot be mapped using
* block descriptors even if the pages belong to a THP for
* the process, because the stage-2 block descriptor will
* cover more than a single THP and we loose atomicity for
* unmapping, updates, and splits of the THP or other pages
* in the stage-2 block range.
*/
if ((memslot->userspace_addr & ~PMD_MASK) !=
static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
gfn_t gfn, struct kvm_memory_slot *memslot,
unsigned long fault_status)
{
pte_t new_pte;
pfn_t pfn;
int ret;
bool write_fault, writable;
unsigned long mmu_seq;
unsigned long hva = gfn_to_hva(vcpu->kvm, gfn);
struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
pgprot_t mem_type = PAGE_S2;
write_fault = kvm_is_write_fault(vcpu);
if (fault_status == FSC_PERM && !write_fault) {
kvm_err("Unexpected L2 read permission error\n");
return -EFAULT;
}
/* We need minimum second+third level pages */
ret = mmu_topup_memory_cache(memcache, 2, KVM_NR_MEM_OBJS);
if (ret)
return ret;
mmu_seq = vcpu->kvm->mmu_notifier_seq;
/*
* Ensure the read of mmu_notifier_seq happens before we call
* gfn_to_pfn_prot (which calls get_user_pages), so that we don't risk
* the page we just got a reference to gets unmapped before we have a
* chance to grab the mmu_lock, which ensure that if the page gets
* unmapped afterwards, the call to kvm_unmap_hva will take it away
* from us again properly. This smp_rmb() interacts with the smp_wmb()
* in kvm_mmu_notifier_invalidate_<page|range_end>.
*/
smp_rmb();
pfn = gfn_to_pfn_prot(vcpu->kvm, gfn, write_fault, &writable);
if (is_error_pfn(pfn))
return -EFAULT;
if (kvm_is_device_pfn(pfn))
mem_type = PAGE_S2_DEVICE;
new_pte = pfn_pte(pfn, mem_type);
coherent_cache_guest_page(vcpu, hva, PAGE_SIZE);
spin_lock(&vcpu->kvm->mmu_lock);
if (mmu_notifier_retry(vcpu->kvm, mmu_seq))
goto out_unlock;
if (writable) {
kvm_set_s2pte_writable(&new_pte);
kvm_set_pfn_dirty(pfn);
}
stage2_set_pte(vcpu->kvm, memcache, fault_ipa, &new_pte,
pgprot_val(mem_type) == pgprot_val(PAGE_S2_DEVICE));
out_unlock:
spin_unlock(&vcpu->kvm->mmu_lock);
kvm_release_pfn_clean(pfn);
return 0;
}
static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
struct kvm_memory_slot *memslot,
unsigned long fault_status)
{
int ret;
bool write_fault, writable, hugetlb = false;
unsigned long mmu_seq;
gfn_t gfn = fault_ipa >> PAGE_SHIFT;
unsigned long hva = gfn_to_hva(vcpu->kvm, gfn);
struct kvm *kvm = vcpu->kvm;
struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache;
struct vm_area_struct *vma;
pfn_t pfn;
write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu));
if (fault_status == FSC_PERM && !write_fault) {
kvm_err("Unexpected L2 read permission error\n");
return -EFAULT;
}
/* Let's check if we will get back a huge page backed by hugetlbfs */
down_read(¤t->mm->mmap_sem);
vma = find_vma_intersection(current->mm, hva, hva + 1);
if (is_vm_hugetlb_page(vma)) {
hugetlb = true;
gfn = (fault_ipa & PMD_MASK) >> PAGE_SHIFT;
}
up_read(¤t->mm->mmap_sem);
/* We need minimum second+third level pages */
ret = mmu_topup_memory_cache(memcache, 2, KVM_NR_MEM_OBJS);
if (ret)
return ret;
mmu_seq = vcpu->kvm->mmu_notifier_seq;
/*
* Ensure the read of mmu_notifier_seq happens before we call
* gfn_to_pfn_prot (which calls get_user_pages), so that we don't risk
* the page we just got a reference to gets unmapped before we have a
* chance to grab the mmu_lock, which ensure that if the page gets
* unmapped afterwards, the call to kvm_unmap_hva will take it away
* from us again properly. This smp_rmb() interacts with the smp_wmb()
* in kvm_mmu_notifier_invalidate_<page|range_end>.
*/
smp_rmb();
pfn = gfn_to_pfn_prot(kvm, gfn, write_fault, &writable);
if (is_error_pfn(pfn))
return -EFAULT;
spin_lock(&kvm->mmu_lock);
if (mmu_notifier_retry(kvm, mmu_seq))
goto out_unlock;
if (hugetlb) {
pmd_t new_pmd = pfn_pmd(pfn, PAGE_S2);
new_pmd = pmd_mkhuge(new_pmd);
if (writable) {
kvm_set_s2pmd_writable(&new_pmd);
kvm_set_pfn_dirty(pfn);
}
coherent_icache_guest_page(kvm, hva & PMD_MASK, PMD_SIZE);
ret = stage2_set_pmd_huge(kvm, memcache, fault_ipa, &new_pmd);
} else {
pte_t new_pte = pfn_pte(pfn, PAGE_S2);
if (writable) {
kvm_set_s2pte_writable(&new_pte);
kvm_set_pfn_dirty(pfn);
}
coherent_icache_guest_page(kvm, hva, PAGE_SIZE);
ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, false);
}
out_unlock:
spin_unlock(&kvm->mmu_lock);
kvm_release_pfn_clean(pfn);
return ret;
}
