thp: fix the wrong reported address of hwpoisoned hugepages

When the tail page of THP is poisoned, the head page will be poisoned too.
 And the wrong address, address of head page, will be sent with sigbus
always.

So when the poisoned page is used by Guest OS which is running on KVM,
after the address changing(hva->gpa) by qemu, the unexpected process on
Guest OS will be killed by sigbus.

What we expected is that the process using the poisoned tail page could be
killed on Guest OS, but not that the process using the healthy head page
is killed.

Since it is not good to poison the healthy page, avoid poisoning other
than the page which is really poisoned.
  (While we poison all pages in a huge page in case of hugetlb,
   we can do this for THP thanks to split_huge_page().)

Here we fix two parts:
  1. Isolate the poisoned page only to make sure
     the reported address is the address of poisoned page.
  2. make the poisoned page work as the poisoned regular page.

[akpm@linux-foundation.org: fix spello in comment]
Signed-off-by: Jin Dongming <jin.dongming@np.css.fujitsu.com>
Reviewed-by: Hidetoshi Seto <seto.hidetoshi@jp.fujitsu.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 28 insertions, 6 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index e187454d82f..b6c1ce3c53b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1162,7 +1162,12 @@ static void __split_huge_page_refcount(struct page *page)
 		/* after clearing PageTail the gup refcount can be released */
 		smp_mb();
 
-		page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
+		/*
+		 * retain hwpoison flag of the poisoned tail page:
+		 *   fix for the unsuitable process killed on Guest Machine(KVM)
+		 *   by the memory-failure.
+		 */
+		page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP | __PG_HWPOISON;
 		page_tail->flags |= (page->flags &
 				     ((1L << PG_referenced) |
 				      (1L << PG_swapbacked) |
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 1e9c30b241c..04158d6f44d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -854,6 +854,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	int ret;
 	int kill = 1;
 	struct page *hpage = compound_head(p);
+	struct page *ppage;
 
 	if (PageReserved(p) || PageSlab(p))
 		return SWAP_SUCCESS;
@@ -894,6 +895,14 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 		}
 	}
 
+	/*
+	 * ppage: poisoned page
+	 *   if p is regular page(4k page)
+	 *        ppage == real poisoned page;
+	 *   else p is hugetlb or THP, ppage == head page.
+	 */
+	ppage = hpage;
+
 	if (PageTransHuge(hpage)) {
 		/*
 		 * Verify that this isn't a hugetlbfs head page, the check for
@@ -919,6 +928,8 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 				BUG_ON(!PageHWPoison(p));
 				return SWAP_FAIL;
 			}
+			/* THP is split, so ppage should be the real poisoned page. */
+			ppage = p;
 		}
 	}
 
@@ -931,12 +942,18 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * there's nothing that can be done.
 	 */
 	if (kill)
-		collect_procs(hpage, &tokill);
+		collect_procs(ppage, &tokill);
 
-	ret = try_to_unmap(hpage, ttu);
+	if (hpage != ppage)
+		lock_page_nosync(ppage);
+
+	ret = try_to_unmap(ppage, ttu);
 	if (ret != SWAP_SUCCESS)
 		printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n",
-				pfn, page_mapcount(hpage));
+				pfn, page_mapcount(ppage));
+
+	if (hpage != ppage)
+		unlock_page(ppage);
 
 	/*
 	 * Now that the dirty bit has been propagated to the
@@ -947,7 +964,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * use a more force-full uncatchable kill to prevent
 	 * any accesses to the poisoned memory.
 	 */
-	kill_procs_ao(&tokill, !!PageDirty(hpage), trapno,
+	kill_procs_ao(&tokill, !!PageDirty(ppage), trapno,
 		      ret != SWAP_SUCCESS, p, pfn);
 
 	return ret;
@@ -1090,7 +1107,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
 	 * For error on the tail page, we should set PG_hwpoison
 	 * on the head page to show that the hugepage is hwpoisoned
 	 */
-	if (PageTail(p) && TestSetPageHWPoison(hpage)) {
+	if (PageHuge(p) && PageTail(p) && TestSetPageHWPoison(hpage)) {
 		action_result(pfn, "hugepage already hardware poisoned",
 				IGNORED);
 		unlock_page(hpage);