Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "18 patches.

  Subsystems affected by this patch series: mm (memory-failure, swap,
  slub, hugetlb, memory-failure, slub, thp, sparsemem), and coredump"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm/sparse: fix check_usemap_section_nr warnings
  mm: thp: replace DEBUG_VM BUG with VM_WARN when unmap fails for split
  mm/thp: unmap_mapping_page() to fix THP truncate_cleanup_page()
  mm/thp: fix page_address_in_vma() on file THP tails
  mm/thp: fix vma_address() if virtual address below file offset
  mm/thp: try_to_unmap() use TTU_SYNC for safe splitting
  mm/thp: make is_huge_zero_pmd() safe and quicker
  mm/thp: fix __split_huge_pmd_locked() on shmem migration entry
  mm, thp: use head page in __migration_entry_wait()
  mm/slub.c: include swab.h
  crash_core, vmcoreinfo: append 'SECTION_SIZE_BITS' to vmcoreinfo
  mm/memory-failure: make sure wait for page writeback in memory_failure
  mm/hugetlb: expand restore_reserve_on_error functionality
  mm/slub: actually fix freelist pointer vs redzoning
  mm/slub: fix redzoning for small allocations
  mm/slub: clarify verification reporting
  mm/swap: fix pte_same_as_swp() not removing uffd-wp bit when compare
  mm,hwpoison: fix race with hugetlb page allocation

22 files changed, 386 insertions, 152 deletions

diff --git a/Documentation/vm/slub.rst b/Documentation/vm/slub.rst
index 03f294a638bd..d3028554b1e9 100644
--- a/Documentation/vm/slub.rst
+++ b/Documentation/vm/slub.rst
@@ -181,7 +181,7 @@ SLUB Debug output
 Here is a sample of slub debug output::
 
  ====================================================================
- BUG kmalloc-8: Redzone overwritten
+ BUG kmalloc-8: Right Redzone overwritten
  --------------------------------------------------------------------
 
  INFO: 0xc90f6d28-0xc90f6d2b. First byte 0x00 instead of 0xcc
@@ -189,10 +189,10 @@ Here is a sample of slub debug output::
  INFO: Object 0xc90f6d20 @offset=3360 fp=0xc90f6d58
  INFO: Allocated in get_modalias+0x61/0xf5 age=53 cpu=1 pid=554
 
- Bytes b4 0xc90f6d10:  00 00 00 00 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ
-   Object 0xc90f6d20:  31 30 31 39 2e 30 30 35                         1019.005
-  Redzone 0xc90f6d28:  00 cc cc cc                                     .
-  Padding 0xc90f6d50:  5a 5a 5a 5a 5a 5a 5a 5a                         ZZZZZZZZ
+ Bytes b4 (0xc90f6d10): 00 00 00 00 00 00 00 00 5a 5a 5a 5a 5a 5a 5a 5a ........ZZZZZZZZ
+ Object   (0xc90f6d20): 31 30 31 39 2e 30 30 35                         1019.005
+ Redzone  (0xc90f6d28): 00 cc cc cc                                     .
+ Padding  (0xc90f6d50): 5a 5a 5a 5a 5a 5a 5a 5a                         ZZZZZZZZ
 
    [<c010523d>] dump_trace+0x63/0x1eb
    [<c01053df>] show_trace_log_lvl+0x1a/0x2f
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 55efd3dd04f6..30dee68458c7 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -735,6 +735,7 @@ static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset,
 		__SetPageUptodate(page);
 		error = huge_add_to_page_cache(page, mapping, index);
 		if (unlikely(error)) {
+			restore_reserve_on_error(h, &pseudo_vma, addr, page);
 			put_page(page);
 			mutex_unlock(&hugetlb_fault_mutex_table[hash]);
 			goto out;
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 9626fda5efce..2a8ebe6c222e 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -286,6 +286,7 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
 vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
 
 extern struct page *huge_zero_page;
+extern unsigned long huge_zero_pfn;
 
 static inline bool is_huge_zero_page(struct page *page)
 {
@@ -294,7 +295,7 @@ static inline bool is_huge_zero_page(struct page *page)
 
 static inline bool is_huge_zero_pmd(pmd_t pmd)
 {
-	return is_huge_zero_page(pmd_page(pmd));
+	return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd);
 }
 
 static inline bool is_huge_zero_pud(pud_t pud)
@@ -440,6 +441,11 @@ static inline bool is_huge_zero_page(struct page *page)
 	return false;
 }
 
+static inline bool is_huge_zero_pmd(pmd_t pmd)
+{
+	return false;
+}
+
 static inline bool is_huge_zero_pud(pud_t pud)
 {
 	return false;
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index b92f25ccef58..6504346a1947 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -149,6 +149,7 @@ bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
 long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
 						long freed);
 bool isolate_huge_page(struct page *page, struct list_head *list);
+int get_hwpoison_huge_page(struct page *page, bool *hugetlb);
 void putback_active_hugepage(struct page *page);
 void move_hugetlb_state(struct page *oldpage, struct page *newpage, int reason);
 void free_huge_page(struct page *page);
@@ -339,6 +340,11 @@ static inline bool isolate_huge_page(struct page *page, struct list_head *list)
 	return false;
 }
 
+static inline int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
+{
+	return 0;
+}
+
 static inline void putback_active_hugepage(struct page *page)
 {
 }
@@ -604,6 +610,8 @@ struct page *alloc_huge_page_vma(struct hstate *h, struct vm_area_struct *vma,
 				unsigned long address);
 int huge_add_to_page_cache(struct page *page, struct address_space *mapping,
 			pgoff_t idx);
+void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
+				unsigned long address, struct page *page);
 
 /* arch callback */
 int __init __alloc_bootmem_huge_page(struct hstate *h);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index c274f75efcf9..8ae31622deef 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1719,6 +1719,7 @@ struct zap_details {
 	struct address_space *check_mapping;	/* Check page->mapping if set */
 	pgoff_t	first_index;			/* Lowest page->index to unmap */
 	pgoff_t last_index;			/* Highest page->index to unmap */
+	struct page *single_page;		/* Locked page to be unmapped */
 };
 
 struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
@@ -1766,6 +1767,7 @@ extern vm_fault_t handle_mm_fault(struct vm_area_struct *vma,
 extern int fixup_user_fault(struct mm_struct *mm,
 			    unsigned long address, unsigned int fault_flags,
 			    bool *unlocked);
+void unmap_mapping_page(struct page *page);
 void unmap_mapping_pages(struct address_space *mapping,
 		pgoff_t start, pgoff_t nr, bool even_cows);
 void unmap_mapping_range(struct address_space *mapping,
@@ -1786,6 +1788,7 @@ static inline int fixup_user_fault(struct mm_struct *mm, unsigned long address,
 	BUG();
 	return -EFAULT;
 }
+static inline void unmap_mapping_page(struct page *page) { }
 static inline void unmap_mapping_pages(struct address_space *mapping,
 		pgoff_t start, pgoff_t nr, bool even_cows) { }
 static inline void unmap_mapping_range(struct address_space *mapping,
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index def5c62c93b3..8d04e7deedc6 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -91,6 +91,7 @@ enum ttu_flags {
 
 	TTU_SPLIT_HUGE_PMD	= 0x4,	/* split huge PMD if any */
 	TTU_IGNORE_MLOCK	= 0x8,	/* ignore mlock */
+	TTU_SYNC		= 0x10,	/* avoid racy checks with PVMW_SYNC */
 	TTU_IGNORE_HWPOISON	= 0x20,	/* corrupted page is recoverable */
 	TTU_BATCH_FLUSH		= 0x40,	/* Batch TLB flushes where possible
 					 * and caller guarantees they will
diff --git a/include/linux/swapops.h b/include/linux/swapops.h
index d9b7c9132c2f..6430a94c6981 100644
--- a/include/linux/swapops.h
+++ b/include/linux/swapops.h
@@ -23,6 +23,16 @@
 #define SWP_TYPE_SHIFT	(BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT)
 #define SWP_OFFSET_MASK	((1UL << SWP_TYPE_SHIFT) - 1)
 
+/* Clear all flags but only keep swp_entry_t related information */
+static inline pte_t pte_swp_clear_flags(pte_t pte)
+{
+	if (pte_swp_soft_dirty(pte))
+		pte = pte_swp_clear_soft_dirty(pte);
+	if (pte_swp_uffd_wp(pte))
+		pte = pte_swp_clear_uffd_wp(pte);
+	return pte;
+}
+
 /*
  * Store a type+offset into a swp_entry_t in an arch-independent format
  */
@@ -66,10 +76,7 @@ static inline swp_entry_t pte_to_swp_entry(pte_t pte)
 {
 	swp_entry_t arch_entry;
 
-	if (pte_swp_soft_dirty(pte))
-		pte = pte_swp_clear_soft_dirty(pte);
-	if (pte_swp_uffd_wp(pte))
-		pte = pte_swp_clear_uffd_wp(pte);
+	pte = pte_swp_clear_flags(pte);
 	arch_entry = __pte_to_swp_entry(pte);
 	return swp_entry(__swp_type(arch_entry), __swp_offset(arch_entry));
 }
diff --git a/kernel/crash_core.c b/kernel/crash_core.c
index 825284baaf46..684a6061a13a 100644
--- a/kernel/crash_core.c
+++ b/kernel/crash_core.c
@@ -464,6 +464,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_LENGTH(mem_section, NR_SECTION_ROOTS);
 	VMCOREINFO_STRUCT_SIZE(mem_section);
 	VMCOREINFO_OFFSET(mem_section, section_mem_map);
+	VMCOREINFO_NUMBER(SECTION_SIZE_BITS);
 	VMCOREINFO_NUMBER(MAX_PHYSMEM_BITS);
 #endif
 	VMCOREINFO_STRUCT_SIZE(page);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 63ed6b25deaa..6d2a0119fc58 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -62,6 +62,7 @@ static struct shrinker deferred_split_shrinker;
 
 static atomic_t huge_zero_refcount;
 struct page *huge_zero_page __read_mostly;
+unsigned long huge_zero_pfn __read_mostly = ~0UL;
 
 bool transparent_hugepage_enabled(struct vm_area_struct *vma)
 {
@@ -98,6 +99,7 @@ retry:
 		__free_pages(zero_page, compound_order(zero_page));
 		goto retry;
 	}
+	WRITE_ONCE(huge_zero_pfn, page_to_pfn(zero_page));
 
 	/* We take additional reference here. It will be put back by shrinker */
 	atomic_set(&huge_zero_refcount, 2);
@@ -147,6 +149,7 @@ static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink,
 	if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) {
 		struct page *zero_page = xchg(&huge_zero_page, NULL);
 		BUG_ON(zero_page == NULL);
+		WRITE_ONCE(huge_zero_pfn, ~0UL);
 		__free_pages(zero_page, compound_order(zero_page));
 		return HPAGE_PMD_NR;
 	}
@@ -2044,7 +2047,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	count_vm_event(THP_SPLIT_PMD);
 
 	if (!vma_is_anonymous(vma)) {
-		_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
+		old_pmd = pmdp_huge_clear_flush_notify(vma, haddr, pmd);
 		/*
 		 * We are going to unmap this huge page. So
 		 * just go ahead and zap it
@@ -2053,16 +2056,25 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 			zap_deposited_table(mm, pmd);
 		if (vma_is_special_huge(vma))
 			return;
-		page = pmd_page(_pmd);
-		if (!PageDirty(page) && pmd_dirty(_pmd))
-			set_page_dirty(page);
-		if (!PageReferenced(page) && pmd_young(_pmd))
-			SetPageReferenced(page);
-		page_remove_rmap(page, true);
-		put_page(page);
+		if (unlikely(is_pmd_migration_entry(old_pmd))) {
+			swp_entry_t entry;
+
+			entry = pmd_to_swp_entry(old_pmd);
+			page = migration_entry_to_page(entry);
+		} else {
+			page = pmd_page(old_pmd);
+			if (!PageDirty(page) && pmd_dirty(old_pmd))
+				set_page_dirty(page);
+			if (!PageReferenced(page) && pmd_young(old_pmd))
+				SetPageReferenced(page);
+			page_remove_rmap(page, true);
+			put_page(page);
+		}
 		add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR);
 		return;
-	} else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) {
+	}
+
+	if (is_huge_zero_pmd(*pmd)) {
 		/*
 		 * FIXME: Do we want to invalidate secondary mmu by calling
 		 * mmu_notifier_invalidate_range() see comments below inside
@@ -2338,17 +2350,17 @@ void vma_adjust_trans_huge(struct vm_area_struct *vma,
 
 static void unmap_page(struct page *page)
 {
-	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK |
+	enum ttu_flags ttu_flags = TTU_IGNORE_MLOCK | TTU_SYNC |
 		TTU_RMAP_LOCKED | TTU_SPLIT_HUGE_PMD;
-	bool unmap_success;
 
 	VM_BUG_ON_PAGE(!PageHead(page), page);
 
 	if (PageAnon(page))
 		ttu_flags |= TTU_SPLIT_FREEZE;
 
-	unmap_success = try_to_unmap(page, ttu_flags);
-	VM_BUG_ON_PAGE(!unmap_success, page);
+	try_to_unmap(page, ttu_flags);
+
+	VM_WARN_ON_ONCE_PAGE(page_mapped(page), page);
 }
 
 static void remap_page(struct page *page, unsigned int nr)
@@ -2659,7 +2671,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	struct deferred_split *ds_queue = get_deferred_split_queue(head);
 	struct anon_vma *anon_vma = NULL;
 	struct address_space *mapping = NULL;
-	int count, mapcount, extra_pins, ret;
+	int extra_pins, ret;
 	pgoff_t end;
 
 	VM_BUG_ON_PAGE(is_huge_zero_page(head), head);
@@ -2718,7 +2730,6 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 	}
 
 	unmap_page(head);
-	VM_BUG_ON_PAGE(compound_mapcount(head), head);
 
 	/* block interrupt reentry in xa_lock and spinlock */
 	local_irq_disable();
@@ -2736,9 +2747,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 
 	/* Prevent deferred_split_scan() touching ->_refcount */
 	spin_lock(&ds_queue->split_queue_lock);
-	count = page_count(head);
-	mapcount = total_mapcount(head);
-	if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) {
+	if (page_ref_freeze(head, 1 + extra_pins)) {
 		if (!list_empty(page_deferred_list(head))) {
 			ds_queue->split_queue_len--;
 			list_del(page_deferred_list(head));
@@ -2758,16 +2767,9 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		__split_huge_page(page, list, end);
 		ret = 0;
 	} else {
-		if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
-			pr_alert("total_mapcount: %u, page_count(): %u\n",
-					mapcount, count);
-			if (PageTail(page))
-				dump_page(head, NULL);
-			dump_page(page, "total_mapcount(head) > 0");
-			BUG();
-		}
 		spin_unlock(&ds_queue->split_queue_lock);
-fail:		if (mapping)
+fail:
+		if (mapping)
 			xa_unlock(&mapping->i_pages);
 		local_irq_enable();
 		remap_page(head, thp_nr_pages(head));
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5560b50876fb..e0a5f9cbbece 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2121,12 +2121,18 @@ out:
  * be restored when a newly allocated huge page must be freed.  It is
  * to be called after calling vma_needs_reservation to determine if a
  * reservation exists.
+ *
+ * vma_del_reservation is used in error paths where an entry in the reserve
+ * map was created during huge page allocation and must be removed.  It is to
+ * be called after calling vma_needs_reservation to determine if a reservation
+ * exists.
  */
 enum vma_resv_mode {
 	VMA_NEEDS_RESV,
 	VMA_COMMIT_RESV,
 	VMA_END_RESV,
 	VMA_ADD_RESV,
+	VMA_DEL_RESV,
 };
 static long __vma_reservation_common(struct hstate *h,
 				struct vm_area_struct *vma, unsigned long addr,
@@ -2170,11 +2176,21 @@ static long __vma_reservation_common(struct hstate *h,
 			ret = region_del(resv, idx, idx + 1);
 		}
 		break;
+	case VMA_DEL_RESV:
+		if (vma->vm_flags & VM_MAYSHARE) {
+			region_abort(resv, idx, idx + 1, 1);
+			ret = region_del(resv, idx, idx + 1);
+		} else {
+			ret = region_add(resv, idx, idx + 1, 1, NULL, NULL);
+			/* region_add calls of range 1 should never fail. */
+			VM_BUG_ON(ret < 0);
+		}
+		break;
 	default:
 		BUG();
 	}
 
-	if (vma->vm_flags & VM_MAYSHARE)
+	if (vma->vm_flags & VM_MAYSHARE || mode == VMA_DEL_RESV)
 		return ret;
 	/*
 	 * We know private mapping must have HPAGE_RESV_OWNER set.
@@ -2222,25 +2238,39 @@ static long vma_add_reservation(struct hstate *h,
 	return __vma_reservation_common(h, vma, addr, VMA_ADD_RESV);
 }
 
+static long vma_del_reservation(struct hstate *h,
+			struct vm_area_struct *vma, unsigned long addr)
+{
+	return __vma_reservation_common(h, vma, addr, VMA_DEL_RESV);
+}
+
 /*
- * This routine is called to restore a reservation on error paths.  In the
- * specific error paths, a huge page was allocated (via alloc_huge_page)
- * and is about to be freed.  If a reservation for the page existed,
- * alloc_huge_page would have consumed the reservation and set
- * HPageRestoreReserve in the newly allocated page.  When the page is freed
- * via free_huge_page, the global reservation count will be incremented if
- * HPageRestoreReserve is set.  However, free_huge_page can not adjust the
- * reserve map.  Adjust the reserve map here to be consistent with global
- * reserve count adjustments to be made by free_huge_page.
+ * This routine is called to restore reservation information on error paths.
+ * It should ONLY be called for pages allocated via alloc_huge_page(), and
+ * the hugetlb mutex should remain held when calling this routine.
+ *
+ * It handles two specific cases:
+ * 1) A reservation was in place and the page consumed the reservation.
+ *    HPageRestoreReserve is set in the page.
+ * 2) No reservation was in place for the page, so HPageRestoreReserve is
+ *    not set.  However, alloc_huge_page always updates the reserve map.
+ *
+ * In case 1, free_huge_page later in the error path will increment the
+ * global reserve count.  But, free_huge_page does not have enough context
+ * to adjust the reservation map.  This case deals primarily with private
+ * mappings.  Adjust the reserve map here to be consistent with global
+ * reserve count adjustments to be made by free_huge_page.  Make sure the
+ * reserve map indicates there is a reservation present.
+ *
+ * In case 2, simply undo reserve map modifications done by alloc_huge_page.
  */
-static void restore_reserve_on_error(struct hstate *h,
-			struct vm_area_struct *vma, unsigned long address,
-			struct page *page)
+void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma,
+			unsigned long address, struct page *page)
 {
-	if (unlikely(HPageRestoreReserve(page))) {
-		long rc = vma_needs_reservation(h, vma, address);
+	long rc = vma_needs_reservation(h, vma, address);
 
-		if (unlikely(rc < 0)) {
+	if (HPageRestoreReserve(page)) {
+		if (unlikely(rc < 0))
 			/*
 			 * Rare out of memory condition in reserve map
 			 * manipulation.  Clear HPageRestoreReserve so that
@@ -2253,16 +2283,57 @@ static void restore_reserve_on_error(struct hstate *h,
 			 * accounting of reserve counts.
 			 */
 			ClearHPageRestoreReserve(page);
-		} else if (rc) {
-			rc = vma_add_reservation(h, vma, address);
-			if (unlikely(rc < 0))
+		else if (rc)
+			(void)vma_add_reservation(h, vma, address);
+		else
+			vma_end_reservation(h, vma, address);
+	} else {
+		if (!rc) {
+			/*
+			 * This indicates there is an entry in the reserve map
+			 * added by alloc_huge_page.  We know it was added
+			 * before the alloc_huge_page call, otherwise
+			 * HPageRestoreReserve would be set on the page.
+			 * Remove the entry so that a subsequent allocation
+			 * does not consume a reservation.
+			 */
+			rc = vma_del_reservation(h, vma, address);
+			if (rc < 0)
+				/*
+				 * VERY rare out of memory condition.  Since
+				 * we can not delete the entry, set
+				 * HPageRestoreReserve so that the reserve
+				 * count will be incremented when the page
+				 * is freed.  This reserve will be consumed
+				 * on a subsequent allocation.
+				 */
+				SetHPageRestoreReserve(page);
+		} else if (rc < 0) {
+			/*
+			 * Rare out of memory condition from
+			 * vma_needs_reservation call.  Memory allocation is
+			 * only attempted if a new entry is needed.  Therefore,
+			 * this implies there is not an entry in the
+			 * reserve map.
+			 *
+			 * For shared mappings, no entry in the map indicates
+			 * no reservation.  We are done.
+			 */
+			if (!(vma->vm_flags & VM_MAYSHARE))
 				/*
-				 * See above comment about rare out of
-				 * memory condition.
+				 * For private mappings, no entry indicates
+				 * a reservation is present.  Since we can
+				 * not add an entry, set SetHPageRestoreReserve
+				 * on the page so reserve count will be
+				 * incremented when freed.  This reserve will
+				 * be consumed on a subsequent allocation.
 				 */
-				ClearHPageRestoreReserve(page);
+				SetHPageRestoreReserve(page);
 		} else
-			vma_end_reservation(h, vma, address);
+			/*
+			 * No reservation present, do nothing
+			 */
+			 vma_end_reservation(h, vma, address);
 	}
 }
 
@@ -4037,6 +4108,8 @@ again:
 				spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
 				entry = huge_ptep_get(src_pte);
 				if (!pte_same(src_pte_old, entry)) {
+					restore_reserve_on_error(h, vma, addr,
+								new);
 					put_page(new);
 					/* dst_entry won't change as in child */
 					goto again;
@@ -5006,6 +5079,7 @@ out_release_unlock:
 	if (vm_shared || is_continue)
 		unlock_page(page);
 out_release_nounlock:
+	restore_reserve_on_error(h, dst_vma, dst_addr, page);
 	put_page(page);
 	goto out;
 }
@@ -5857,6 +5931,21 @@ unlock:
 	return ret;
 }
 
+int get_hwpoison_huge_page(struct page *page, bool *hugetlb)
+{
+	int ret = 0;
+
+	*hugetlb = false;
+	spin_lock_irq(&hugetlb_lock);
+	if (PageHeadHuge(page)) {
+		*hugetlb = true;
+		if (HPageFreed(page) || HPageMigratable(page))
+			ret = get_page_unless_zero(page);
+	}
+	spin_unlock_irq(&hugetlb_lock);
+	return ret;
+}
+
 void putback_active_hugepage(struct page *page)
 {
 	spin_lock_irq(&hugetlb_lock);
diff --git a/mm/internal.h b/mm/internal.h
index 2f1182948aa6..e8fdb531f887 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -384,27 +384,52 @@ static inline void mlock_migrate_page(struct page *newpage, struct page *page)
 extern pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma);
 
 /*
- * At what user virtual address is page expected in @vma?
+ * At what user virtual address is page expected in vma?
+ * Returns -EFAULT if all of the page is outside the range of vma.
+ * If page is a compound head, the entire compound page is considered.
  */
 static inline unsigned long
-__vma_address(struct page *page, struct vm_area_struct *vma)
+vma_address(struct page *page, struct vm_area_struct *vma)
 {
-	pgoff_t pgoff = page_to_pgoff(page);
-	return vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+	pgoff_t pgoff;
+	unsigned long address;
+
+	VM_BUG_ON_PAGE(PageKsm(page), page);	/* KSM page->index unusable */
+	pgoff = page_to_pgoff(page);
+	if (pgoff >= vma->vm_pgoff) {
+		address = vma->vm_start +
+			((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+		/* Check for address beyond vma (or wrapped through 0?) */
+		if (address < vma->vm_start || address >= vma->vm_end)
+			address = -EFAULT;
+	} else if (PageHead(page) &&
+		   pgoff + compound_nr(page) - 1 >= vma->vm_pgoff) {
+		/* Test above avoids possibility of wrap to 0 on 32-bit */
+		address = vma->vm_start;
+	} else {
+		address = -EFAULT;
+	}
+	return address;
 }
 
+/*
+ * Then at what user virtual address will none of the page be found in vma?
+ * Assumes that vma_address() already returned a good starting address.
+ * If page is a compound head, the entire compound page is considered.
+ */
 static inline unsigned long
-vma_address(struct page *page, struct vm_area_struct *vma)
+vma_address_end(struct page *page, struct vm_area_struct *vma)
 {
-	unsigned long start, end;
-
-	start = __vma_address(page, vma);
-	end = start + thp_size(page) - PAGE_SIZE;
-
-	/* page should be within @vma mapping range */
-	VM_BUG_ON_VMA(end < vma->vm_start || start >= vma->vm_end, vma);
-
-	return max(start, vma->vm_start);
+	pgoff_t pgoff;
+	unsigned long address;
+
+	VM_BUG_ON_PAGE(PageKsm(page), page);	/* KSM page->index unusable */
+	pgoff = page_to_pgoff(page) + compound_nr(page);
+	address = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT);
+	/* Check for address beyond vma (or wrapped through 0?) */
+	if (address < vma->vm_start || address > vma->vm_end)
+		address = vma->vm_end;
+	return address;
 }
 
 static inline struct file *maybe_unlock_mmap_for_io(struct vm_fault *vmf,
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 85ad98c00fd9..0143d32bc666 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -949,6 +949,17 @@ static int page_action(struct page_state *ps, struct page *p,
 	return (result == MF_RECOVERED || result == MF_DELAYED) ? 0 : -EBUSY;
 }
 
+/*
+ * Return true if a page type of a given page is supported by hwpoison
+ * mechanism (while handling could fail), otherwise false.  This function
+ * does not return true for hugetlb or device memory pages, so it's assumed
+ * to be called only in the context where we never have such pages.
+ */
+static inline bool HWPoisonHandlable(struct page *page)
+{
+	return PageLRU(page) || __PageMovable(page);
+}
+
 /**
  * __get_hwpoison_page() - Get refcount for memory error handling:
  * @page:	raw error page (hit by memory error)
@@ -959,8 +970,22 @@ static int page_action(struct page_state *ps, struct page *p,
 static int __get_hwpoison_page(struct page *page)
 {
 	struct page *head = compound_head(page);
+	int ret = 0;
+	bool hugetlb = false;
+
+	ret = get_hwpoison_huge_page(head, &hugetlb);
+	if (hugetlb)
+		return ret;
 
-	if (!PageHuge(head) && PageTransHuge(head)) {
+	/*
+	 * This check prevents from calling get_hwpoison_unless_zero()
+	 * for any unsupported type of page in order to reduce the risk of
+	 * unexpected races caused by taking a page refcount.
+	 */
+	if (!HWPoisonHandlable(head))
+		return 0;
+
+	if (PageTransHuge(head)) {
 		/*
 		 * Non anonymous thp exists only in allocation/free time. We
 		 * can't handle such a case correctly, so let's give it up.
@@ -1017,7 +1042,7 @@ try_again:
 			ret = -EIO;
 		}
 	} else {
-		if (PageHuge(p) || PageLRU(p) || __PageMovable(p)) {
+		if (PageHuge(p) || HWPoisonHandlable(p)) {
 			ret = 1;
 		} else {
 			/*
@@ -1527,7 +1552,12 @@ try_again:
 		return 0;
 	}
 
-	if (!PageTransTail(p) && !PageLRU(p))
+	/*
+	 * __munlock_pagevec may clear a writeback page's LRU flag without
+	 * page_lock. We need wait writeback completion for this page or it
+	 * may trigger vfs BUG while evict inode.
+	 */
+	if (!PageTransTail(p) && !PageLRU(p) && !PageWriteback(p))
 		goto identify_page_state;
 
 	/*
diff --git a/mm/memory.c b/mm/memory.c
index f3ffab9b9e39..486f4a2874e7 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1361,7 +1361,18 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 			else if (zap_huge_pmd(tlb, vma, pmd, addr))
 				goto next;
 			/* fall through */
+		} else if (details && details->single_page &&
+			   PageTransCompound(details->single_page) &&
+			   next - addr == HPAGE_PMD_SIZE && pmd_none(*pmd)) {
+			spinlock_t *ptl = pmd_lock(tlb->mm, pmd);
+			/*
+			 * Take and drop THP pmd lock so that we cannot return
+			 * prematurely, while zap_huge_pmd() has cleared *pmd,
+			 * but not yet decremented compound_mapcount().
+			 */
+			spin_unlock(ptl);
 		}
+
 		/*
 		 * Here there can be other concurrent MADV_DONTNEED or
 		 * trans huge page faults running, and if the pmd is
@@ -3237,6 +3248,36 @@ static inline void unmap_mapping_range_tree(struct rb_root_cached *root,
 }
 
 /**
+ * unmap_mapping_page() - Unmap single page from processes.
+ * @page: The locked page to be unmapped.
+ *
+ * Unmap this page from any userspace process which still has it mmaped.
+ * Typically, for efficiency, the range of nearby pages has already been
+ * unmapped by unmap_mapping_pages() or unmap_mapping_range().  But once
+ * truncation or invalidation holds the lock on a page, it may find that
+ * the page has been remapped again: and then uses unmap_mapping_page()
+ * to unmap it finally.
+ */
+void unmap_mapping_page(struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	struct zap_details details = { };
+
+	VM_BUG_ON(!PageLocked(page));
+	VM_BUG_ON(PageTail(page));
+
+	details.check_mapping = mapping;
+	details.first_index = page->index;
+	details.last_index = page->index + thp_nr_pages(page) - 1;
+	details.single_page = page;
+
+	i_mmap_lock_write(mapping);
+	if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)))
+		unmap_mapping_range_tree(&mapping->i_mmap, &details);
+	i_mmap_unlock_write(mapping);
+}
+
+/**
  * unmap_mapping_pages() - Unmap pages from processes.
  * @mapping: The address space containing pages to be unmapped.
  * @start: Index of first page to be unmapped.
diff --git a/mm/migrate.c b/mm/migrate.c
index b234c3f3acb7..41ff2c9896c4 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -295,6 +295,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep,
 		goto out;
 
 	page = migration_entry_to_page(entry);
+	page = compound_head(page);
 
 	/*
 	 * Once page cache replacement of page migration started, page_count
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index 2cf01d933f13..e37bd43904af 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -212,23 +212,34 @@ restart:
 			pvmw->ptl = NULL;
 		}
 	} else if (!pmd_present(pmde)) {
+		/*
+		 * If PVMW_SYNC, take and drop THP pmd lock so that we
+		 * cannot return prematurely, while zap_huge_pmd() has
+		 * cleared *pmd but not decremented compound_mapcount().
+		 */
+		if ((pvmw->flags & PVMW_SYNC) &&
+		    PageTransCompound(pvmw->page)) {
+			spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);
+
+			spin_unlock(ptl);
+		}
 		return false;
 	}
 	if (!map_pte(pvmw))
 		goto next_pte;
 	while (1) {
+		unsigned long end;
+
 		if (check_pte(pvmw))
 			return true;
 next_pte:
 		/* Seek to next pte only makes sense for THP */
 		if (!PageTransHuge(pvmw->page) || PageHuge(pvmw->page))
 			return not_found(pvmw);
+		end = vma_address_end(pvmw->page, pvmw->vma);
 		do {
 			pvmw->address += PAGE_SIZE;
-			if (pvmw->address >= pvmw->vma->vm_end ||
-			    pvmw->address >=
-					__vma_address(pvmw->page, pvmw->vma) +
-					thp_size(pvmw-&g