Backmerge tag 'v4.9-rc8' into drm-next

Linux 4.9-rc8

Daniel requested this so we could apply some follow on fixes cleanly to -next.

10 files changed, 73 insertions, 17 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index cdcd25cb30fe..d4a6e4001512 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1426,11 +1426,12 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 
 bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		  unsigned long new_addr, unsigned long old_end,
-		  pmd_t *old_pmd, pmd_t *new_pmd)
+		  pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush)
 {
 	spinlock_t *old_ptl, *new_ptl;
 	pmd_t pmd;
 	struct mm_struct *mm = vma->vm_mm;
+	bool force_flush = false;
 
 	if ((old_addr & ~HPAGE_PMD_MASK) ||
 	    (new_addr & ~HPAGE_PMD_MASK) ||
@@ -1456,6 +1457,8 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		if (new_ptl != old_ptl)
 			spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
 		pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);
+		if (pmd_present(pmd) && pmd_dirty(pmd))
+			force_flush = true;
 		VM_BUG_ON(!pmd_none(*new_pmd));
 
 		if (pmd_move_must_withdraw(new_ptl, old_ptl) &&
@@ -1467,6 +1470,10 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
 		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
 		if (new_ptl != old_ptl)
 			spin_unlock(new_ptl);
+		if (force_flush)
+			flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
+		else
+			*need_flush = true;
 		spin_unlock(old_ptl);
 		return true;
 	}
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index 70c009741aab..0e9505f66ec1 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -764,6 +764,25 @@ EXPORT_SYMBOL(__asan_storeN_noabort);
 void __asan_handle_no_return(void) {}
 EXPORT_SYMBOL(__asan_handle_no_return);
 
+/* Emitted by compiler to poison large objects when they go out of scope. */
+void __asan_poison_stack_memory(const void *addr, size_t size)
+{
+	/*
+	 * Addr is KASAN_SHADOW_SCALE_SIZE-aligned and the object is surrounded
+	 * by redzones, so we simply round up size to simplify logic.
+	 */
+	kasan_poison_shadow(addr, round_up(size, KASAN_SHADOW_SCALE_SIZE),
+			    KASAN_USE_AFTER_SCOPE);
+}
+EXPORT_SYMBOL(__asan_poison_stack_memory);
+
+/* Emitted by compiler to unpoison large objects when they go into scope. */
+void __asan_unpoison_stack_memory(const void *addr, size_t size)
+{
+	kasan_unpoison_shadow(addr, size);
+}
+EXPORT_SYMBOL(__asan_unpoison_stack_memory);
+
 #ifdef CONFIG_MEMORY_HOTPLUG
 static int kasan_mem_notifier(struct notifier_block *nb,
 			unsigned long action, void *data)
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index e5c2181fee6f..1c260e6b3b3c 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -21,6 +21,7 @@
 #define KASAN_STACK_MID         0xF2
 #define KASAN_STACK_RIGHT       0xF3
 #define KASAN_STACK_PARTIAL     0xF4
+#define KASAN_USE_AFTER_SCOPE   0xF8
 
 /* Don't break randconfig/all*config builds */
 #ifndef KASAN_ABI_VERSION
@@ -53,6 +54,9 @@ struct kasan_global {
 #if KASAN_ABI_VERSION >= 4
 	struct kasan_source_location *location;
 #endif
+#if KASAN_ABI_VERSION >= 5
+	char *odr_indicator;
+#endif
 };
 
 /**
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 24c1211fe9d5..073325aedc68 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -90,6 +90,9 @@ static void print_error_description(struct kasan_access_info *info)
 	case KASAN_KMALLOC_FREE:
 		bug_type = "use-after-free";
 		break;
+	case KASAN_USE_AFTER_SCOPE:
+		bug_type = "use-after-scope";
+		break;
 	}
 
 	pr_err("BUG: KASAN: %s in %pS at addr %p\n",
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 728d7790dc2d..87e1a7ca3846 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -103,6 +103,7 @@ static struct khugepaged_scan khugepaged_scan = {
 	.mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head),
 };
 
+#ifdef CONFIG_SYSFS
 static ssize_t scan_sleep_millisecs_show(struct kobject *kobj,
 					 struct kobj_attribute *attr,
 					 char *buf)
@@ -295,6 +296,7 @@ struct attribute_group khugepaged_attr_group = {
 	.attrs = khugepaged_attr,
 	.name = "khugepaged",
 };
+#endif /* CONFIG_SYSFS */
 
 #define VM_NO_KHUGEPAGED (VM_SPECIAL | VM_HUGETLB)
 
diff --git a/mm/mlock.c b/mm/mlock.c
index 145a4258ddbc..cdbed8aaa426 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -190,10 +190,13 @@ unsigned int munlock_vma_page(struct page *page)
 	 */
 	spin_lock_irq(zone_lru_lock(zone));
 
-	nr_pages = hpage_nr_pages(page);
-	if (!TestClearPageMlocked(page))
+	if (!TestClearPageMlocked(page)) {
+		/* Potentially, PTE-mapped THP: do not skip the rest PTEs */
+		nr_pages = 1;
 		goto unlock_out;
+	}
 
+	nr_pages = hpage_nr_pages(page);
 	__mod_zone_page_state(zone, NR_MLOCK, -nr_pages);
 
 	if (__munlock_isolate_lru_page(page, true)) {
diff --git a/mm/mremap.c b/mm/mremap.c
index da22ad2a5678..30d7d2482eea 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -104,11 +104,13 @@ static pte_t move_soft_dirty_pte(pte_t pte)
 static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 		unsigned long old_addr, unsigned long old_end,
 		struct vm_area_struct *new_vma, pmd_t *new_pmd,
-		unsigned long new_addr, bool need_rmap_locks)
+		unsigned long new_addr, bool need_rmap_locks, bool *need_flush)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *old_pte, *new_pte, pte;
 	spinlock_t *old_ptl, *new_ptl;
+	bool force_flush = false;
+	unsigned long len = old_end - old_addr;
 
 	/*
 	 * When need_rmap_locks is true, we take the i_mmap_rwsem and anon_vma
@@ -146,7 +148,19 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 				   new_pte++, new_addr += PAGE_SIZE) {
 		if (pte_none(*old_pte))
 			continue;
+
 		pte = ptep_get_and_clear(mm, old_addr, old_pte);
+		/*
+		 * If we are remapping a dirty PTE, make sure
+		 * to flush TLB before we drop the PTL for the
+		 * old PTE or we may race with page_mkclean().
+		 *
+		 * This check has to be done after we removed the
+		 * old PTE from page tables or another thread may
+		 * dirty it after the check and before the removal.
+		 */
+		if (pte_present(pte) && pte_dirty(pte))
+			force_flush = true;
 		pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr);
 		pte = move_soft_dirty_pte(pte);
 		set_pte_at(mm, new_addr, new_pte, pte);
@@ -156,6 +170,10 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd,
 	if (new_ptl != old_ptl)
 		spin_unlock(new_ptl);
 	pte_unmap(new_pte - 1);
+	if (force_flush)
+		flush_tlb_range(vma, old_end - len, old_end);
+	else
+		*need_flush = true;
 	pte_unmap_unlock(old_pte - 1, old_ptl);
 	if (need_rmap_locks)
 		drop_rmap_locks(vma);
@@ -201,13 +219,12 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 				if (need_rmap_locks)
 					take_rmap_locks(vma);
 				moved = move_huge_pmd(vma, old_addr, new_addr,
-						    old_end, old_pmd, new_pmd);
+						    old_end, old_pmd, new_pmd,
+						    &need_flush);
 				if (need_rmap_locks)
 					drop_rmap_locks(vma);
-				if (moved) {
-					need_flush = true;
+				if (moved)
 					continue;
-				}
 			}
 			split_huge_pmd(vma, old_pmd, old_addr);
 			if (pmd_trans_unstable(old_pmd))
@@ -220,11 +237,10 @@ unsigned long move_page_tables(struct vm_area_struct *vma,
 			extent = next - new_addr;
 		if (extent > LATENCY_LIMIT)
 			extent = LATENCY_LIMIT;
-		move_ptes(vma, old_pmd, old_addr, old_addr + extent,
-			  new_vma, new_pmd, new_addr, need_rmap_locks);
-		need_flush = true;
+		move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma,
+			  new_pmd, new_addr, need_rmap_locks, &need_flush);
 	}
-	if (likely(need_flush))
+	if (need_flush)
 		flush_tlb_range(vma, old_end-len, old_addr);
 
 	mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end);
diff --git a/mm/truncate.c b/mm/truncate.c
index a01cce450a26..8d8c62d89e6d 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -283,7 +283,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 
 			if (!trylock_page(page))
 				continue;
-			WARN_ON(page_to_pgoff(page) != index);
+			WARN_ON(page_to_index(page) != index);
 			if (PageWriteback(page)) {
 				unlock_page(page);
 				continue;
@@ -371,7 +371,7 @@ void truncate_inode_pages_range(struct address_space *mapping,
 			}
 
 			lock_page(page);
-			WARN_ON(page_to_pgoff(page) != index);
+			WARN_ON(page_to_index(page) != index);
 			wait_on_page_writeback(page);
 			truncate_inode_page(mapping, page);
 			unlock_page(page);
@@ -492,7 +492,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping,
 			if (!trylock_page(page))
 				continue;
 
-			WARN_ON(page_to_pgoff(page) != index);
+			WARN_ON(page_to_index(page) != index);
 
 			/* Middle of THP: skip */
 			if (PageTransTail(page)) {
@@ -612,7 +612,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping,
 			}
 
 			lock_page(page);
-			WARN_ON(page_to_pgoff(page) != index);
+			WARN_ON(page_to_index(page) != index);
 			if (page->mapping != mapping) {
 				unlock_page(page);
 				continue;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 76fda2268148..d75cdf360730 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2354,6 +2354,8 @@ static void shrink_node_memcg(struct pglist_data *pgdat, struct mem_cgroup *memc
 			}
 		}
 
+		cond_resched();
+
 		if (nr_reclaimed < nr_to_reclaim || scan_adjusted)
 			continue;
 
diff --git a/mm/workingset.c b/mm/workingset.c
index 617475f529f4..fb1f9183d89a 100644
--- a/mm/workingset.c
+++ b/mm/workingset.c
@@ -348,7 +348,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker,
 	shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc);
 	local_irq_enable();
 
-	if (memcg_kmem_enabled()) {
+	if (sc->memcg) {
 		pages = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid,
 						     LRU_ALL_FILE);
 	} else {