HWPOISON: detect free buddy pages explicitly

Most free pages in the buddy system have no PG_buddy set.
Introduce is_free_buddy_page() for detecting them reliably.

CC: Nick Piggin <npiggin@suse.de>
CC: Mel Gorman <mel@linux.vnet.ibm.com>
Signed-off-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Andi Kleen <ak@linux.intel.com>

3 files changed, 31 insertions, 2 deletions

diff --git a/mm/internal.h b/mm/internal.h
index 4fe67a162cb4..49b2ff776b78 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -50,6 +50,9 @@ extern void putback_lru_page(struct page *page);
  */
 extern void __free_pages_bootmem(struct page *page, unsigned int order);
 extern void prep_compound_page(struct page *page, unsigned long order);
+#ifdef CONFIG_MEMORY_FAILURE
+extern bool is_free_buddy_page(struct page *page);
+#endif
 
 
 /*
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 676ab394200e..5055b940df5f 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -807,8 +807,13 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
          */
         if (!(flags & MF_COUNT_INCREASED) &&
                 !get_page_unless_zero(compound_head(p))) {
-                action_result(pfn, "free or high order kernel", IGNORED);
-                return PageBuddy(compound_head(p)) ? 0 : -EBUSY;
+                if (is_free_buddy_page(p)) {
+                        action_result(pfn, "free buddy", DELAYED);
+                        return 0;
+                } else {
+                        action_result(pfn, "high order kernel", IGNORED);
+                        return -EBUSY;
+                }
         }
 
         /*
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 59d2e88fb47c..6867b4d391fd 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5081,3 +5081,24 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn)
         spin_unlock_irqrestore(&zone->lock, flags);
 }
 #endif
+
+#ifdef CONFIG_MEMORY_FAILURE
+bool is_free_buddy_page(struct page *page)
+{
+        struct zone *zone = page_zone(page);
+        unsigned long pfn = page_to_pfn(page);
+        unsigned long flags;
+        int order;
+
+        spin_lock_irqsave(&zone->lock, flags);
+        for (order = 0; order < MAX_ORDER; order++) {
+                struct page *page_head = page - (pfn & ((1 << order) - 1));
+
+                if (PageBuddy(page_head) && page_order(page_head) >= order)
+                        break;
+        }
+        spin_unlock_irqrestore(&zone->lock, flags);
+
+        return order < MAX_ORDER;
+}
+#endif