add 2nd stage page fault handling during live migration

- added pte_index() to add to pmd pfn

---
 arch/arm/kvm/mmu.c |   31 +++++++++++++++++++++++++++++--
 1 file changed, 29 insertions(+), 2 deletions(-)

index 52d4dd6..61ee812 100644
@@ -924,6 +924,7 @@ static int user_mem_abort(struct kvm_vcpu *vcpu,

phys_addr_t fault_ipa,
struct kvm_mmu_memory_cache *memcache = &vcpu->arch.mmu_page_cache; struct vm_area_struct *vma;
pfn_t pfn;
+ bool migration_active;

write_fault = kvm_is_write_fault(kvm_vcpu_get_hsr(vcpu)); if (fault_status == FSC_PERM && !write_fault) {
@@ -975,12 +976,21 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
return -EFAULT;

spin_lock(&kvm->mmu_lock);
+ /* place inside lock to prevent race condition when whole VM is being
+ * write proteced. Prevent race of huge page install when migration is
+ * active.
+ */
+ migration_active = vcpu->kvm->arch.migration_in_progress;
+
if (mmu_notifier_retry(kvm, mmu_seq))
goto out_unlock;
- if (!hugetlb && !force_pte)
+
+ /* During migration don't rebuild huge pages */
+ if (!hugetlb && !force_pte && !migration_active)
hugetlb = transparent_hugepage_adjust(&pfn, &fault_ipa);

- if (hugetlb) {
+ /* During migration don't install new huge pages */
+ if (hugetlb && !migration_active) {
pmd_t new_pmd = pfn_pmd(pfn, PAGE_S2);
new_pmd = pmd_mkhuge(new_pmd);
if (writable) {
@@ -992,6 +1002,21 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
} else {
pte_t new_pte = pfn_pte(pfn, PAGE_S2);
if (writable) {
+ /* First convert huge page pfn to normal 4k page pfn,
+ * while migration is in progress.
+ * Second in migration mode and rare case where
+ * splitting of huge pages fails check if pmd is
+ * mapping a huge page if it is then clear it so
+ * stage2_set_pte() can map in a small page.
+ */
+ if (migration_active && hugetlb) {
+ pmd_t *pmd;
+ pfn += pte_index(fault_ipa);
+ new_pte = pfn_pte(pfn, PAGE_S2);
+ pmd = stage2_get_pmd(kvm, NULL, fault_ipa);
+ if (pmd && kvm_pmd_huge(*pmd))
+ clear_pmd_entry(kvm, pmd, fault_ipa);
+ }
kvm_set_s2pte_writable(&new_pte); kvm_set_pfn_dirty(pfn);
}
@@ -999,6 +1024,8 @@ static int user_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa,
ret = stage2_set_pte(kvm, memcache, fault_ipa, &new_pte, false);
}

+ if (writable)
+ mark_page_dirty(kvm, gfn);

out_unlock:
spin_unlock(&kvm->mmu_lock);

1.7.9.5