Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "15 fixes"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm, docs: update memory.stat description with workingset* entries
  mm: vmscan: scan until it finds eligible pages
  mm, thp: copying user pages must schedule on collapse
  dax: fix PMD data corruption when fault races with write
  dax: fix data corruption when fault races with write
  ext4: return to starting transaction in ext4_dax_huge_fault()
  mm: fix data corruption due to stale mmap reads
  dax: prevent invalidation of mapped DAX entries
  Tigran has moved
  mm, vmalloc: fix vmalloc users tracking properly
  mm/khugepaged: add missed tracepoint for collapse_huge_page_swapin
  gcov: support GCC 7.1
  mm, vmstat: Remove spurious WARN() during zoneinfo print
  time: delete current_fs_time()
  hwpoison, memcg: forcibly uncharge LRU pages

8 files changed, 63 insertions, 23 deletions

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 7cb9c88bb4a3..945fd1ca49b5 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -612,7 +612,8 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
 				      spinlock_t *ptl)
 {
 	pte_t *_pte;
-	for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++) {
+	for (_pte = pte; _pte < pte + HPAGE_PMD_NR;
+				_pte++, page++, address += PAGE_SIZE) {
 		pte_t pteval = *_pte;
 		struct page *src_page;
 
@@ -651,9 +652,7 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
 			spin_unlock(ptl);
 			free_page_and_swap_cache(src_page);
 		}
-
-		address += PAGE_SIZE;
-		page++;
+		cond_resched();
 	}
 }
 
@@ -907,8 +906,10 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 				return false;
 			}
 			/* check if the pmd is still valid */
-			if (mm_find_pmd(mm, address) != pmd)
+			if (mm_find_pmd(mm, address) != pmd) {
+				trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 				return false;
+			}
 		}
 		if (ret & VM_FAULT_ERROR) {
 			trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ff73899af61a..94172089f52f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -5528,7 +5528,7 @@ static void uncharge_list(struct list_head *page_list)
 		next = page->lru.next;
 
 		VM_BUG_ON_PAGE(PageLRU(page), page);
-		VM_BUG_ON_PAGE(page_count(page), page);
+		VM_BUG_ON_PAGE(!PageHWPoison(page) && page_count(page), page);
 
 		if (!page->mem_cgroup)
 			continue;
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index 73066b80d14a..2527dfeddb00 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -539,6 +539,13 @@ static int delete_from_lru_cache(struct page *p)
 		 */
 		ClearPageActive(p);
 		ClearPageUnevictable(p);
+
+		/*
+		 * Poisoned page might never drop its ref count to 0 so we have
+		 * to uncharge it manually from its memcg.
+		 */
+		mem_cgroup_uncharge(p);
+
 		/*
 		 * drop the page count elevated by isolate_lru_page()
 		 */
diff --git a/mm/truncate.c b/mm/truncate.c
index 83a059e8cd1d..6479ed2afc53 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -67,17 +67,14 @@ static void truncate_exceptional_entry(struct address_space *mapping,
 
 /*
  * Invalidate exceptional entry if easily possible. This handles exceptional
- * entries for invalidate_inode_pages() so for DAX it evicts only unlocked and
- * clean entries.
+ * entries for invalidate_inode_pages().
  */
 static int invalidate_exceptional_entry(struct address_space *mapping,
 					pgoff_t index, void *entry)
 {
-	/* Handled by shmem itself */
-	if (shmem_mapping(mapping))
+	/* Handled by shmem itself, or for DAX we do nothing. */
+	if (shmem_mapping(mapping) || dax_mapping(mapping))
 		return 1;
-	if (dax_mapping(mapping))
-		return dax_invalidate_mapping_entry(mapping, index);
 	clear_shadow_entry(mapping, index, entry);
 	return 1;
 }
@@ -689,7 +686,17 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 		cond_resched();
 		index++;
 	}
-
+	/*
+	 * For DAX we invalidate page tables after invalidating radix tree.  We
+	 * could invalidate page tables while invalidating each entry however
+	 * that would be expensive. And doing range unmapping before doesn't
+	 * work as we have no cheap way to find whether radix tree entry didn't
+	 * get remapped later.
+	 */
+	if (dax_mapping(mapping)) {
+		unmap_mapping_range(mapping, (loff_t)start << PAGE_SHIFT,
+				    (loff_t)(end - start + 1) << PAGE_SHIFT, 0);
+	}
 out:
 	cleancache_invalidate_inode(mapping);
 	return ret;
diff --git a/mm/util.c b/mm/util.c
index 718154debc87..464df3489903 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -382,7 +382,8 @@ void *kvmalloc_node(size_t size, gfp_t flags, int node)
 	if (ret || size <= PAGE_SIZE)
 		return ret;
 
-	return __vmalloc_node_flags(size, node, flags);
+	return __vmalloc_node_flags_caller(size, node, flags,
+			__builtin_return_address(0));
 }
 EXPORT_SYMBOL(kvmalloc_node);
 
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 194c22eccb9d..34a1c3e46ed7 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -1649,6 +1649,9 @@ void *vmap(struct page **pages, unsigned int count,
 }
 EXPORT_SYMBOL(vmap);
 
+static void *__vmalloc_node(unsigned long size, unsigned long align,
+			    gfp_t gfp_mask, pgprot_t prot,
+			    int node, const void *caller);
 static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 				 pgprot_t prot, int node)
 {
@@ -1791,7 +1794,7 @@ fail:
  *	with mm people.
  *
  */
-void *__vmalloc_node(unsigned long size, unsigned long align,
+static void *__vmalloc_node(unsigned long size, unsigned long align,
 			    gfp_t gfp_mask, pgprot_t prot,
 			    int node, const void *caller)
 {
@@ -1806,6 +1809,20 @@ void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
 }
 EXPORT_SYMBOL(__vmalloc);
 
+static inline void *__vmalloc_node_flags(unsigned long size,
+					int node, gfp_t flags)
+{
+	return __vmalloc_node(size, 1, flags, PAGE_KERNEL,
+					node, __builtin_return_address(0));
+}
+
+
+void *__vmalloc_node_flags_caller(unsigned long size, int node, gfp_t flags,
+				  void *caller)
+{
+	return __vmalloc_node(size, 1, flags, PAGE_KERNEL, node, caller);
+}
+
 /**
  *	vmalloc  -  allocate virtually contiguous memory
  *	@size:		allocation size
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 2f45c0520f43..8ad39bbc79e6 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1449,7 +1449,7 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec,
  *
  * Appropriate locks must be held before calling this function.
  *
- * @nr_to_scan:	The number of pages to look through on the list.
+ * @nr_to_scan:	The number of eligible pages to look through on the list.
  * @lruvec:	The LRU vector to pull pages from.
  * @dst:	The temp list to put pages on to.
  * @nr_scanned:	The number of pages that were scanned.
@@ -1469,11 +1469,13 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 	unsigned long nr_zone_taken[MAX_NR_ZONES] = { 0 };
 	unsigned long nr_skipped[MAX_NR_ZONES] = { 0, };
 	unsigned long skipped = 0;
-	unsigned long scan, nr_pages;
+	unsigned long scan, total_scan, nr_pages;
 	LIST_HEAD(pages_skipped);
 
-	for (scan = 0; scan < nr_to_scan && nr_taken < nr_to_scan &&
-					!list_empty(src); scan++) {
+	scan = 0;
+	for (total_scan = 0;
+	     scan < nr_to_scan && nr_taken < nr_to_scan && !list_empty(src);
+	     total_scan++) {
 		struct page *page;
 
 		page = lru_to_page(src);
@@ -1487,6 +1489,13 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 			continue;
 		}
 
+		/*
+		 * Do not count skipped pages because that makes the function
+		 * return with no isolated pages if the LRU mostly contains
+		 * ineligible pages.  This causes the VM to not reclaim any
+		 * pages, triggering a premature OOM.
+		 */
+		scan++;
 		switch (__isolate_lru_page(page, mode)) {
 		case 0:
 			nr_pages = hpage_nr_pages(page);
@@ -1524,9 +1533,9 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan,
 			skipped += nr_skipped[zid];
 		}
 	}
-	*nr_scanned = scan;
+	*nr_scanned = total_scan;
 	trace_mm_vmscan_lru_isolate(sc->reclaim_idx, sc->order, nr_to_scan,
-				    scan, skipped, nr_taken, mode, lru);
+				    total_scan, skipped, nr_taken, mode, lru);
 	update_lru_sizes(lruvec, lru, nr_zone_taken);
 	return nr_taken;
 }
diff --git a/mm/vmstat.c b/mm/vmstat.c
index f5fa1bd1eb16..76f73670200a 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1359,8 +1359,6 @@ static bool is_zone_first_populated(pg_data_t *pgdat, struct zone *zone)
 			return zone == compare;
 	}
 
-	/* The zone must be somewhere! */
-	WARN_ON_ONCE(1);
 	return false;
 }