Merge branch 'hwpoison' of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6

* 'hwpoison' of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6:
  hugetlb: add missing unlock in avoidcopy path in hugetlb_cow()
  hwpoison: rename CONFIG
  HWPOISON, hugetlb: support hwpoison injection for hugepage
  HWPOISON, hugetlb: detect hwpoison in hugetlb code
  HWPOISON, hugetlb: isolate corrupted hugepage
  HWPOISON, hugetlb: maintain mce_bad_pages in handling hugepage error
  HWPOISON, hugetlb: set/clear PG_hwpoison bits on hugepage
  HWPOISON, hugetlb: enable error handling path for hugepage
  hugetlb, rmap: add reverse mapping for hugepage
  hugetlb: move definition of is_vm_hugetlb_page() to hugepage_inline.h

Fix up trivial conflicts in mm/memory-failure.c

include/linux/hugetlb.h

@@ -2,6 +2,7 @@
 #define _LINUX_HUGETLB_H
 
 #include <linux/fs.h>
+#include <linux/hugetlb_inline.h>
 
 struct ctl_table;
 struct user_struct;
@@ -14,11 +15,6 @@ struct user_struct;
 
 int PageHuge(struct page *page);
 
-static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
-{
-	return vma->vm_flags & VM_HUGETLB;
-}
-
 void reset_vma_resv_huge_pages(struct vm_area_struct *vma);
 int hugetlb_sysctl_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
 int hugetlb_overcommit_handler(struct ctl_table *, int, void __user *, size_t *, loff_t *);
@@ -47,6 +43,7 @@ int hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						struct vm_area_struct *vma,
 						int acctflags);
 void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed);
+void __isolate_hwpoisoned_huge_page(struct page *page);
 
 extern unsigned long hugepages_treat_as_movable;
 extern const unsigned long hugetlb_zero, hugetlb_infinity;
@@ -77,11 +74,6 @@ static inline int PageHuge(struct page *page)
 	return 0;
 }
 
-static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
-{
-	return 0;
-}
-
 static inline void reset_vma_resv_huge_pages(struct vm_area_struct *vma)
 {
 }
@@ -108,6 +100,8 @@ static inline void hugetlb_report_meminfo(struct seq_file *m)
 #define is_hugepage_only_range(mm, addr, len)	0
 #define hugetlb_free_pgd_range(tlb, addr, end, floor, ceiling) ({BUG(); 0; })
 #define hugetlb_fault(mm, vma, addr, flags)	({ BUG(); 0; })
+#define huge_pte_offset(mm, address)	0
+#define __isolate_hwpoisoned_huge_page(page)	0
 
 #define hugetlb_change_protection(vma, address, end, newprot)
 

include/linux/hugetlb_inline.h

+#ifndef _LINUX_HUGETLB_INLINE_H
+#define _LINUX_HUGETLB_INLINE_H
+
+#ifdef CONFIG_HUGETLB_PAGE
+
+#include <linux/mm.h>
+
+static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
+{
+	return vma->vm_flags & VM_HUGETLB;
+}
+
+#else
+
+static inline int is_vm_hugetlb_page(struct vm_area_struct *vma)
+{
+	return 0;
+}
+
+#endif
+
+#endif

include/linux/pagemap.h

@@ -13,6 +13,7 @@
 #include <linux/gfp.h>
 #include <linux/bitops.h>
 #include <linux/hardirq.h> /* for in_interrupt() */
+#include <linux/hugetlb_inline.h>
 
 /*
  * Bits in mapping->flags.  The lower __GFP_BITS_SHIFT bits are the page
@@ -281,10 +282,16 @@ static inline loff_t page_offset(struct page *page)
 	return ((loff_t)page->index) << PAGE_CACHE_SHIFT;
 }
 
+extern pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
+				     unsigned long address);
+
 static inline pgoff_t linear_page_index(struct vm_area_struct *vma,
 					unsigned long address)
 {
-	pgoff_t pgoff = (address - vma->vm_start) >> PAGE_SHIFT;
+	pgoff_t pgoff;
+	if (unlikely(is_vm_hugetlb_page(vma)))
+		return linear_hugepage_index(vma, address);
+	pgoff = (address - vma->vm_start) >> PAGE_SHIFT;
 	pgoff += vma->vm_pgoff;
 	return pgoff >> (PAGE_CACHE_SHIFT - PAGE_SHIFT);
 }

include/linux/poison.h

@@ -48,15 +48,6 @@
 #define POISON_FREE	0x6b	/* for use-after-free poisoning */
 #define	POISON_END	0xa5	/* end-byte of poisoning */
 
-/********** mm/hugetlb.c **********/
-/*
- * Private mappings of hugetlb pages use this poisoned value for
- * page->mapping. The core VM should not be doing anything with this mapping
- * but futex requires the existence of some page->mapping value even though it
- * is unused if PAGE_MAPPING_ANON is set.
- */
-#define HUGETLB_POISON	((void *)(0x00300300 + POISON_POINTER_DELTA + PAGE_MAPPING_ANON))
-
 /********** arch/$ARCH/mm/init.c **********/
 #define POISON_FREE_INITMEM	0xcc
 

include/linux/rmap.h

@@ -168,6 +168,11 @@ void page_add_new_anon_rmap(struct page *, struct vm_area_struct *, unsigned lon
 void page_add_file_rmap(struct page *);
 void page_remove_rmap(struct page *);
 
+void hugepage_add_anon_rmap(struct page *, struct vm_area_struct *,
+			    unsigned long);
+void hugepage_add_new_anon_rmap(struct page *, struct vm_area_struct *,
+				unsigned long);
+
 static inline void page_dup_rmap(struct page *page)
 {
 	atomic_inc(&page->_mapcount);

mm/hugetlb.c

@@ -18,6 +18,9 @@
 #include <linux/bootmem.h>
 #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>
@@ -220,6 +223,12 @@ static pgoff_t vma_hugecache_offset(struct hstate *h,
 			(vma->vm_pgoff >> huge_page_order(h));
 }
 
+pgoff_t linear_hugepage_index(struct vm_area_struct *vma,
+				     unsigned long address)
+{
+	return vma_hugecache_offset(hstate_vma(vma), vma, address);
+}
+
 /*
  * Return the size of the pages allocated when backing a VMA. In the majority
  * cases this will be same size as used by the page table entries.
@@ -552,6 +561,7 @@ static void free_huge_page(struct page *page)
 	set_page_private(page, 0);
 	page->mapping = NULL;
 	BUG_ON(page_count(page));
+	BUG_ON(page_mapcount(page));
 	INIT_LIST_HEAD(&page->lru);
 
 	spin_lock(&hugetlb_lock);
@@ -605,6 +615,8 @@ int PageHuge(struct page *page)
 	return dtor == free_huge_page;
 }
 
+EXPORT_SYMBOL_GPL(PageHuge);
+
 static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid)
 {
 	struct page *page;
@@ -2129,6 +2141,7 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src,
 			entry = huge_ptep_get(src_pte);
 			ptepage = pte_page(entry);
 			get_page(ptepage);
+			page_dup_rmap(ptepage);
 			set_huge_pte_at(dst, addr, dst_pte, entry);
 		}
 		spin_unlock(&src->page_table_lock);
@@ -2140,6 +2153,19 @@ 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)
 {
@@ -2198,6 +2224,12 @@ 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);
@@ -2207,6 +2239,7 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start,
 	flush_tlb_range(vma, start, end);
 	mmu_notifier_invalidate_range_end(mm, start, end);
 	list_for_each_entry_safe(page, tmp, &page_list, lru) {
+		page_remove_rmap(page);
 		list_del(&page->lru);
 		put_page(page);
 	}
@@ -2272,6 +2305,9 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma,
 	return 1;
 }
 
+/*
+ * Hugetlb_cow() should be called with page lock of the original hugepage held.
+ */
 static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 			unsigned long address, pte_t *ptep, pte_t pte,
 			struct page *pagecache_page)
@@ -2286,8 +2322,13 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 retry_avoidcopy:
 	/* If no-one else is actually using this page, avoid the copy
 	 * and just make the page writable */
-	avoidcopy = (page_count(old_page) == 1);
+	avoidcopy = (page_mapcount(old_page) == 1);
 	if (avoidcopy) {
+		if (!trylock_page(old_page)) {
+			if (PageAnon(old_page))
+				page_move_anon_rmap(old_page, vma, address);
+		} else
+			unlock_page(old_page);
 		set_huge_ptep_writable(vma, address, ptep);
 		return 0;
 	}
@@ -2338,6 +2379,13 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 		return -PTR_ERR(new_page);
 	}
 
+	/*
+	 * When the original hugepage is shared one, it does not have
+	 * anon_vma prepared.
+	 */
+	if (unlikely(anon_vma_prepare(vma)))
+		return VM_FAULT_OOM;
+
 	copy_huge_page(new_page, old_page, address, vma);
 	__SetPageUptodate(new_page);
 
@@ -2355,6 +2403,8 @@ static int hugetlb_cow(struct mm_struct *mm, struct vm_area_struct *vma,
 		huge_ptep_clear_flush(vma, address, ptep);
 		set_huge_pte_at(mm, address, ptep,
 				make_huge_pte(vma, new_page, 1));
+		page_remove_rmap(old_page);
+		hugepage_add_anon_rmap(new_page, vma, address);
 		/* Make the old page be freed below */
 		new_page = old_page;
 		mmu_notifier_invalidate_range_end(mm,
@@ -2458,10 +2508,29 @@ static int hugetlb_no_page(struct mm_struct *mm, struct vm_area_struct *vma,
 			spin_lock(&inode->i_lock);
 			inode->i_blocks += blocks_per_huge_page(h);
 			spin_unlock(&inode->i_lock);
+			page_dup_rmap(page);
 		} else {
 			lock_page(page);
-			page->mapping = HUGETLB_POISON;
+			if (unlikely(anon_vma_prepare(vma))) {
+				ret = VM_FAULT_OOM;
+				goto backout_unlocked;
+			}
+			hugepage_add_new_anon_rmap(page, vma, address);
 		}
+	} else {
+		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;
 	}
 
 	/*
@@ -2513,10 +2582,18 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	pte_t *ptep;
 	pte_t entry;
 	int ret;
+	struct page *page = NULL;
 	struct page *pagecache_page = NULL;
 	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;
@@ -2554,6 +2631,11 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 								vma, address);
 	}
 
+	if (!pagecache_page) {
+		page = pte_page(entry);
+		lock_page(page);
+	}
+
 	spin_lock(&mm->page_table_lock);
 	/* Check for a racing update before calling hugetlb_cow */
 	if (unlikely(!pte_same(entry, huge_ptep_get(ptep))))
@@ -2579,6 +2661,8 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (pagecache_page) {
 		unlock_page(pagecache_page);
 		put_page(pagecache_page);
+	} else {
+		unlock_page(page);
 	}
 
 out_mutex:
@@ -2791,3 +2875,19 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed)
 	hugetlb_put_quota(inode->i_mapping, (chg - freed));
 	hugetlb_acct_memory(h, -(chg - freed));
 }
+
+/*
+ * This function is called from memory failure code.
+ * Assume the caller holds page lock of the head page.
+ */
+void __isolate_hwpoisoned_huge_page(struct page *hpage)
+{
+	struct hstate *h = page_hstate(hpage);
+	int nid = page_to_nid(hpage);
+
+	spin_lock(&hugetlb_lock);
+	list_del(&hpage->lru);
+	h->free_huge_pages--;
+	h->free_huge_pages_node[nid]--;
+	spin_unlock(&hugetlb_lock);
+}

mm/hwpoison-inject.c

@@ -5,6 +5,7 @@
 #include <linux/mm.h>
 #include <linux/swap.h>
 #include <linux/pagemap.h>
+#include <linux/hugetlb.h>
 #include "internal.h"
 
 static struct dentry *hwpoison_dir;
@@ -13,6 +14,7 @@ static int hwpoison_inject(void *data, u64 val)
 {
 	unsigned long pfn = val;
 	struct page *p;
+	struct page *hpage;
 	int err;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -24,18 +26,19 @@ static int hwpoison_inject(void *data, u64 val)
 		return -ENXIO;
 
 	p = pfn_to_page(pfn);
+	hpage = compound_head(p);
 	/*
 	 * This implies unable to support free buddy pages.
 	 */
-	if (!get_page_unless_zero(p))
+	if (!get_page_unless_zero(hpage))
 		return 0;
 
-	if (!PageLRU(p))
+	if (!PageLRU(p) && !PageHuge(p))
 		shake_page(p, 0);
 	/*
 	 * This implies unable to support non-LRU pages.
 	 */
-	if (!PageLRU(p))
+	if (!PageLRU(p) && !PageHuge(p))
 		return 0;
 
 	/*
@@ -44,9 +47,9 @@ static int hwpoison_inject(void *data, u64 val)
 	 * We temporarily take page lock for try_get_mem_cgroup_from_page().
 	 * __memory_failure() will redo the check reliably inside page lock.
 	 */
-	lock_page(p);
-	err = hwpoison_filter(p);
-	unlock_page(p);
+	lock_page(hpage);
+	err = hwpoison_filter(hpage);
+	unlock_page(hpage);
 	if (err)
 		return 0;
 

mm/memory-failure.c

@@ -46,6 +46,7 @@
 #include <linux/suspend.h>
 #include <linux/slab.h>
 #include <linux/swapops.h>
+#include <linux/hugetlb.h>
 #include "internal.h"
 
 int sysctl_memory_failure_early_kill __read_mostly = 0;
@@ -690,17 +691,29 @@ static int me_swapcache_clean(struct page *p, unsigned long pfn)
 /*
  * Huge pages. Needs work.
  * Issues:
- * No rmap support so we cannot find the original mapper. In theory could walk
- * all MMs and look for the mappings, but that would be non atomic and racy.
- * Need rmap for hugepages for this. Alternatively we could employ a heuristic,
- * like just walking the current process and hoping it has it mapped (that
- * should be usually true for the common "shared database cache" case)
- * Should handle free huge pages and dequeue them too, but this needs to
- * handle huge page accounting correctly.
+ * - Error on hugepage is contained in hugepage unit (not in raw page unit.)
+ *   To narrow down kill region to one page, we need to break up pmd.
+ * - To support soft-offlining for hugepage, we need to support hugepage
+ *   migration.
  */
 static int me_huge_page(struct page *p, unsigned long pfn)
 {
-	return FAILED;
+	struct page *hpage = compound_head(p);
+	/*
+	 * We can safely recover from error on free or reserved (i.e.
+	 * not in-use) hugepage by dequeuing it from freelist.
+	 * To check whether a hugepage is in-use or not, we can't use
+	 * page->lru because it can be used in other hugepage operations,
+	 * such as __unmap_hugepage_range() and gather_surplus_pages().
+	 * So instead we use page_mapping() and PageAnon().
+	 * We assume that this function is called with page lock held,
+	 * so there is no race between isolation and mapping/unmapping.
+	 */
+	if (!(page_mapping(hpage) || PageAnon(hpage))) {
+		__isolate_hwpoisoned_huge_page(hpage);
+		return RECOVERED;
+	}
+	return DELAYED;
 }
 
 /*
@@ -838,6 +851,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	int ret;
 	int i;
 	int kill = 1;
+	struct page *hpage = compound_head(p);
 
 	if (PageReserved(p) || PageSlab(p))
 		return SWAP_SUCCESS;
@@ -846,10 +860,10 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * This check implies we don't kill processes if their pages
 	 * are in the swap cache early. Those are always late kills.
 	 */
-	if (!page_mapped(p))
+	if (!page_mapped(hpage))
 		return SWAP_SUCCESS;
 
-	if (PageCompound(p) || PageKsm(p))
+	if (PageKsm(p))
 		return SWAP_FAIL;
 
 	if (PageSwapCache(p)) {
@@ -864,10 +878,11 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * XXX: the dirty test could be racy: set_page_dirty() may not always
 	 * be called inside page lock (it's recommended but not enforced).
 	 */
-	mapping = page_mapping(p);
-	if (!PageDirty(p) && mapping && mapping_cap_writeback_dirty(mapping)) {
-		if (page_mkclean(p)) {
-			SetPageDirty(p);
+	mapping = page_mapping(hpage);
+	if (!PageDirty(hpage) && mapping &&
+	    mapping_cap_writeback_dirty(mapping)) {
+		if (page_mkclean(hpage)) {
+			SetPageDirty(hpage);
 		} else {
 			kill = 0;
 			ttu |= TTU_IGNORE_HWPOISON;
@@ -886,14 +901,14 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 	 * there's nothing that can be done.
 	 */
 	if (kill)
-		collect_procs(p, &tokill);
+		collect_procs(hpage, &tokill);
 
 	/*
 	 * try_to_unmap can fail temporarily due to races.
 	 * Try a few times (RED-PEN better strategy?)
 	 */
 	for (i = 0; i < N_UNMAP_TRIES; i++) {
-		ret = try_to_unmap(p, ttu);
+		ret = try_to_unmap(hpage, ttu);
 		if (ret == SWAP_SUCCESS)
 			break;
 		pr_debug("MCE %#lx: try_to_unmap retry needed %d\n", pfn,  ret);
@@ -901,7 +916,7 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 
 	if (ret != SWAP_SUCCESS)
 		printk(KERN_ERR "MCE %#lx: failed to unmap page (mapcount=%d)\n",
-				pfn, page_mapcount(p));
+				pfn, page_mapcount(hpage));
 
 	/*
 	 * Now that the dirty bit has been propagated to the
@@ -912,17 +927,35 @@ 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(p), trapno,
+	kill_procs_ao(&tokill, !!PageDirty(hpage), trapno,
 		      ret != SWAP_SUCCESS, pfn);
 
 	return ret;
 }
 
+static void set_page_hwpoison_huge_page(struct page *hpage)
+{
+	int i;
+	int nr_pages = 1 << compound_order(hpage);
+	for (i = 0; i < nr_pages; i++)
+		SetPageHWPoison(hpage + i);
+}
+
+static void clear_page_hwpoison_huge_page(struct page *hpage)
+{
+	int i;
+	int nr_pages = 1 << compound_order(hpage);
+	for (i = 0; i < nr_pages; i++)
+		ClearPageHWPoison(hpage + i);
+}
+
 int __memory_failure(unsigned long pfn, int trapno, int flags)
 {
 	struct page_state *ps;
 	struct page *p;
+	struct page *hpage;
 	int res;
+	unsigned int nr_pages;
 
 	if (!sysctl_memory_failure_recovery)
 		panic("Memory failure from trap %d on page %lx", trapno, pfn);
@@ -935,12 +968,14 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
 	}
 
 	p = pfn_to_page(pfn);
+	hpage = compound_head(p);
 	if (TestSetPageHWPoison(p)) {
 		printk(KERN_ERR "MCE %#lx: already hardware poisoned\n", pfn);
 		return 0;
 	}
 
-	atomic_long_add(1, &mce_bad_pages);
+	nr_pages = 1 << compound_order(hpage);
+	atomic_long_add(nr_pages, &mce_bad_pages);
 
 	/*
 	 * We need/can do nothing about count=0 pages.
@@ -954,7 +989,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
 	 * that may make page_freeze_refs()/page_unfreeze_refs() mismatch.
 	 */
 	if (!(flags & MF_COUNT_INCREASED) &&
-		!get_page_unless_zero(compound_head(p))) {
+		!get_page_unless_zero(hpage)) {
 		if (is_free_buddy_page(p)) {
 			action_result(pfn, "free buddy", DELAYED);
 			return 0;
@@ -972,9 +1007,9 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
 	 * The check (unnecessarily) ignores LRU pages being isolated and
 	 * walked by the page reclaim code, however that's not a big loss.
 	 */
-	if (!PageLRU(p))
+	if (!PageLRU(p) && !PageHuge(p))
 		shake_page(p, 0);
-	if (!PageLRU(p)) {
+	if (!PageLRU(p) && !PageHuge(p)) {
 		/*
 		 * shake_page could have turned it free.
 		 */
@@ -992,7 +1027,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
 	 * It's very difficult to mess with pages currently under IO
 	 * and in many cases impossible, so we just avoid it here.
 	 */
-	lock_page_nosync(p);
+	lock_page_nosync(hpage);
 
 	/*
 	 * unpoison always clear PG_hwpoison inside page lock
@@ -1004,11 +1039,31 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
 	}
 	if (hwpoison_filter(p)) {
 		if (TestClearPageHWPoison(p))
-			atomic_long_dec(&mce_bad_pages);
-		unlock_page(p);
-		put_page(p);
+			atomic_long_sub(nr_pages, &mce_bad_pages);
+		unlock_page(hpage);
+		put_page(hpage);
+		return 0;
+	}
+
+	/*
+	 * 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)) {
+		action_result(pfn, "hugepage already hardware poisoned",
+				IGNORED);
+		unlock_page(hpage);
+		put_page(hpage);
 		return 0;
 	}
+	/*
+	 * Set PG_hwpoison on all pages in an error hugepage,
+	 * because containment is done in hugepage unit for now.
+	 * Since we have done TestSetPageHWPoison() for the head page with
+	 * page lock held, we can safely set PG_hwpoison bits on tail pages.
+	 */
+	if (PageHuge(p))
+		set_page_hwpoison_huge_page(hpage);
 
 	wait_on_page_writeback(p);
 
@@ -1039,7 +1094,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags)
 		}
 	}
 out:
-	unlock_page(p);
+	unlock_page(hpage);
 	return res;
 }
 EXPORT_SYMBOL_GPL(__memory_failure);
@@ -1083,6 +1138,7 @@ int unpoison_memory(unsigned long pfn)
 	struct page *page;
 	struct page *p;
 	int freeit = 0;
+	unsigned int nr_pages;
 
 	if (!pfn_valid(pfn))
 		return -ENXIO;
@@ -1095,9 +1151,11 @@ int unpoison_memory(unsigned long pfn)
 		return 0;
 	}
 
+	nr_pages = 1 << compound_order(page);
+
 	if (!get_page_unless_zero(page)) {
 		if (TestClearPageHWPoison(p))
-			atomic_long_dec(&mce_bad_pages);
+			atomic_long_sub(nr_pages, &mce_bad_pages);
 		pr_debug("MCE: Software-unpoisoned free page %#lx\n", pfn);
 		return 0;
 	}
@@ -1109,11 +1167,13 @@ int unpoison_memory(unsigned long pfn)
 	 * the PG_hwpoison page will be caught and isolated on the entrance to
 	 * the free buddy page pool.
 	 */
-	if (TestClearPageHWPoison(p)) {
+	if (TestClearPageHWPoison(page)) {
 		pr_debug("MCE: Software-unpoisoned page %#lx\n", pfn);
-		atomic_long_dec(&mce_bad_pages);
+		atomic_long_sub(nr_pages, &mce_bad_pages);
 		freeit = 1;
 	}
+	if (PageHuge(p))
+		clear_page_hwpoison_huge_page(page);
 	unlock_page(page);
 
 	put_page(page);

mm/rmap.c

@@ -56,6 +56,7 @@
 #include <linux/memcontrol.h>
 #include <linux/mmu_notifier.h>
 #include <linux/migrate.h>
+#include <linux/hugetlb.h>
 
 #include <asm/tlbflush.h>
 
@@ -350,6 +351,8 @@ vma_address(struct page *page, struct vm_area_struct *vma)
 	pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
 	unsigned long address;
 
+	if (unlikely(is_vm_hugetlb_page(vma)))
+		pgoff = page->index << huge_page_order(page_hstate(page));
 	address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
 	if (unlikely(address < vma->vm_start || address >= vma->vm_end)) {
 		/* page should be within @vma mapping range */
@@ -394,6 +397,12 @@ pte_t *page_check_address(struct page *page, struct mm_struct *mm,
 	pte_t *pte;
 	spinlock_t *ptl;
 
+	if (unlikely(PageHuge(page))) {
+		pte = huge_pte_offset(mm, address);
+		ptl = &mm->page_table_lock;
+		goto check;
+	}
+
 	pgd = pgd_offset(mm, address);
 	if (!pgd_present(*pgd))
 		return NULL;
@@ -414,6 +423,7 @@ pte_t *page_check_address(struct page *page, struct mm_struct *mm,
 	}
 
 	ptl = pte_lockptr(mm, pmd);
+check:
 	spin_lock(ptl);
 	if (pte_present(*pte) && page_to_pfn(page) == pte_pfn(*pte)) {
 		*ptlp = ptl;
@@ -916,6 +926,12 @@ void page_remove_rmap(struct page *page)
 		page_clear_dirty(page);
 		set_page_dirty(page);
 	}
+	/*
+	 * Hugepages are not counted in NR_ANON_PAGES nor NR_FILE_MAPPED
+	 * and not charged by memcg for now.
+	 */
+	if (unlikely(PageHuge(page)))
+		return;
 	if (PageAnon(page)) {
 		mem_cgroup_uncharge_page(page);
 		__dec_zone_page_state(page, NR_ANON_PAGES);
@@ -1524,3 +1540,46 @@ int rmap_walk(struct page *page, int (*rmap_one)(struct page *,
 		return rmap_walk_file(page, rmap_one, arg);
 }
 #endif /* CONFIG_MIGRATION */
+
+#ifdef CONFIG_HUGETLB_PAGE
+/*
+ * The following three functions are for anonymous (private mapped) hugepages.
+ * Unlike common anonymous pages, anonymous hugepages have no accounting code
+ * and no lru code, because we handle hugepages differently from common pages.
+ */
+static void __hugepage_set_anon_rmap(struct page *page,
+	struct vm_area_struct *vma, unsigned long address, int exclusive)
+{
+	struct anon_vma *anon_vma = vma->anon_vma;
+	BUG_ON(!anon_vma);
+	if (!exclusive) {
+		struct anon_vma_chain *avc;
+		avc = list_entry(vma->anon_vma_chain.prev,
+				 struct anon_vma_chain, same_vma);
+		anon_vma = avc->anon_vma;
+	}
+	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
+	page->mapping = (struct address_space *) anon_vma;
+	page->index = linear_page_index(vma, address);
+}
+
+void hugepage_add_anon_rmap(struct page *page,
+			    struct vm_area_struct *vma, unsigned long address)
+{
+	struct anon_vma *anon_vma = vma->anon_vma;
+	int first;
+	BUG_ON(!anon_vma);
+	BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+	first = atomic_inc_and_test(&page->_mapcount);
+	if (first)
+		__hugepage_set_anon_rmap(page, vma, address, 0);
+}
+
+void hugepage_add_new_anon_rmap(struct page *page,
+			struct vm_area_struct *vma, unsigned long address)
+{
+	BUG_ON(address < vma->vm_start || address >= vma->vm_end);
+	atomic_set(&page->_mapcount, 0);
+	__hugepage_set_anon_rmap(page, vma, address, 1);
+}
+#endif /* CONFIG_HUGETLB_PAGE */