HWPOISON, hugetlb: detect hwpoison in hugetlb code

This patch enables to block access to hwpoisoned hugepage and
also enables to block unmapping for it.

Dependency:
  "HWPOISON, hugetlb: enable error handling path for hugepage"

Signed-off-by: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Fengguang Wu <fengguang.wu@intel.com>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andi Kleen <ak@linux.intel.com>

mm/hugetlb.c

@@ -19,6 +19,8 @@
 #include <linux/sysfs.h>
 #include <linux/slab.h>
 #include <linux/rmap.h>
+#include <linux/swap.h>
+#include <linux/swapops.h>
 
 #include <asm/page.h>
 #include <asm/pgtable.h>
@@ -2149,6 +2151,19 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 	return -ENOMEM;
 }
 
+static int is_hugetlb_entry_hwpoisoned(pte_t pte)
+{
+	swp_entry_t swp;
+
+	if (huge_pte_none(pte) || pte_present(pte))
+		return 0;
+	swp = pte_to_swp_entry(pte);
+	if (non_swap_entry(swp) && is_hwpoison_entry(swp)) {
+		return 1;
+	} else
+		return 0;
+}
+
 void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 			    unsigned long end, struct page *ref_page)
 {
@@ -2207,6 +2222,12 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 		if (huge_pte_none(pte))
 			continue;
 
+		/*
+		 * HWPoisoned hugepage is already unmapped and dropped reference
+		 */
+		if (unlikely(is_hugetlb_entry_hwpoisoned(pte)))
+			continue;
+
 		page = pte_page(pte);
 		if (pte_dirty(pte))
 			set_page_dirty(page);
@@ -2490,6 +2511,18 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		page_dup_rmap(page);
 	}
 
+	/*
+	 * Since memory error handler replaces pte into hwpoison swap entry
+	 * at the time of error handling, a process which reserved but not have
+	 * the mapping to the error hugepage does not have hwpoison swap entry.
+	 * So we need to block accesses from such a process by checking
+	 * PG_hwpoison bit here.
+	 */
+	if (unlikely(PageHWPoison(page))) {
+		ret = VM_FAULT_HWPOISON;
+		goto backout_unlocked;
+	}
+
 	/*
 	 * If we are going to COW a private mapping later, we examine the
 	 * pending reservations for this page now. This will ensure that
@@ -2544,6 +2577,13 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	static DEFINE_MUTEX(hugetlb_instantiation_mutex);
 	struct hstate *h = hstate_vma(vma);
 
+	ptep = huge_pte_offset(mm, address);
+	if (ptep) {
+		entry = huge_ptep_get(ptep);
+		if (unlikely(is_hugetlb_entry_hwpoisoned(entry)))
+			return VM_FAULT_HWPOISON;
+	}
+
 	ptep = huge_pte_alloc(mm, address, huge_page_size(h));
 	if (!ptep)
 		return VM_FAULT_OOM;