[RFC,3/3] KVM, HWPoison, unpoison address across rebooting

Commit Message

Huang, Ying Dec. 22, 2010, 2:51 a.m. UTC

None

Patch

--- a/include/linux/kvm.h
+++ b/include/linux/kvm.h
@@ -676,6 +676,7 @@  struct kvm_clock_data {
 #define KVM_SET_PIT2              _IOW(KVMIO,  0xa0, struct kvm_pit_state2)
 /* Available with KVM_CAP_PPC_GET_PVINFO */
 #define KVM_PPC_GET_PVINFO	  _IOW(KVMIO,  0xa1, struct kvm_ppc_pvinfo)
+#define KVM_UNPOISON_ADDRESS	  _IO(KVMIO,  0xa2)
 
 /*
  * ioctls for vcpu fds
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1512,6 +1512,14 @@  extern int sysctl_memory_failure_recover
 extern void shake_page(struct page *p, int access);
 extern atomic_long_t mce_bad_pages;
 extern int soft_offline_page(struct page *page, int flags);
+#ifdef CONFIG_MEMORY_FAILURE
+int unpoison_address(unsigned long addr);
+#else
+static inline int unpoison_address(unsigned long addr)
+{
+	return -EINVAL;
+}
+#endif
 
 extern void dump_page(struct page *page);
 
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1433,3 +1433,42 @@  done:
 	/* keep elevated page count for bad page */
 	return ret;
 }
+
+int unpoison_address(unsigned long addr)
+{
+	struct mm_struct *mm;
+	pgd_t *pgdp;
+	pud_t pud, *pudp;
+	pmd_t pmd, *pmdp;
+	pte_t pte, *ptep;
+	spinlock_t *ptl;
+	swp_entry_t entry;
+	int rc;
+
+	mm = current->mm;
+	pgdp = pgd_offset(mm, addr);
+	if (!pgd_present(*pgdp))
+		return -EINVAL;
+	pudp = pud_offset(pgdp, addr);
+	pud = *pudp;
+	if (!pud_present(pud) || pud_large(pud))
+		return -EINVAL;
+	pmdp = pmd_offset(pudp, addr);
+	pmd = *pmdp;
+	/* can not unpoison huge page yet */
+	if (!pmd_present(pmd) || pmd_large(pmd))
+		return -EINVAL;
+	ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl);
+	pte = *ptep;
+	rc = -EINVAL;
+	if (!is_swap_pte(pte))
+		goto out;
+	entry = pte_to_swp_entry(pte);
+	if (!is_hwpoison_entry(entry))
+		goto out;
+	pte_clear(mm, addr, ptep);
+out:
+	pte_unmap_unlock(ptep, ptl);
+	return rc;
+}
+EXPORT_SYMBOL_GPL(unpoison_address);
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -774,6 +774,17 @@  int kvm_vm_ioctl_set_memory_region(struc
 	return kvm_set_memory_region(kvm, mem, user_alloc);
 }
 
+static int kvm_unpoison_address(struct kvm *kvm, unsigned long address)
+{
+	int r;
+
+	down_read(&current->mm->mmap_sem);
+	r = unpoison_address(address);
+	up_read(&current->mm->mmap_sem);
+
+	return r;
+}
+
 int kvm_get_dirty_log(struct kvm *kvm,
 			struct kvm_dirty_log *log, int *is_dirty)
 {
@@ -1728,6 +1739,9 @@  static long kvm_vm_ioctl(struct file *fi
 		mutex_unlock(&kvm->lock);
 		break;
 #endif
+	case KVM_UNPOISON_ADDRESS:
+		r = kvm_unpoison_address(kvm, arg);
+		break;
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 		if (r == -ENOTTY)