Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few random little subsystems

 - almost all of the MM patches which are staged ahead of linux-next
   material. I'll trickle to post-linux-next work in as the dependents
   get merged up.

Subsystems affected by this patch series: kthread, kbuild, ide, ntfs,
ocfs2, arch, and mm (slab-generic, slab, slub, dax, debug, pagecache,
gup, swap, shmem, memcg, pagemap, mremap, hmm, vmalloc, documentation,
kasan, pagealloc, memory-failure, hugetlb, vmscan, z3fold, compaction,
oom-kill, migration, cma, page-poison, userfaultfd, zswap, zsmalloc,
uaccess, zram, and cleanups).

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (200 commits)
  mm: cleanup kstrto*() usage
  mm: fix fall-through warnings for Clang
  mm: slub: convert sysfs sprintf family to sysfs_emit/sysfs_emit_at
  mm: shmem: convert shmem_enabled_show to use sysfs_emit_at
  mm:backing-dev: use sysfs_emit in macro defining functions
  mm: huge_memory: convert remaining use of sprintf to sysfs_emit and neatening
  mm: use sysfs_emit for struct kobject * uses
  mm: fix kernel-doc markups
  zram: break the strict dependency from lzo
  zram: add stat to gather incompressible pages since zram set up
  zram: support page writeback
  mm/process_vm_access: remove redundant initialization of iov_r
  mm/zsmalloc.c: rework the list_add code in insert_zspage()
  mm/zswap: move to use crypto_acomp API for hardware acceleration
  mm/zswap: fix passing zero to 'PTR_ERR' warning
  mm/zswap: make struct kernel_param_ops definitions const
  userfaultfd/selftests: hint the test runner on required privilege
  userfaultfd/selftests: fix retval check for userfaultfd_open()
  userfaultfd/selftests: always dump something in modes
  userfaultfd: selftests: make __{s,u}64 format specifiers portable
  ...

1 files changed, 58 insertions, 47 deletions

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 6ae491a8b210..4d88fe5a277a 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -413,10 +413,13 @@ static DEFINE_SPINLOCK(vmap_area_lock);
 static DEFINE_SPINLOCK(free_vmap_area_lock);
 /* Export for kexec only */
 LIST_HEAD(vmap_area_list);
-static LLIST_HEAD(vmap_purge_list);
 static struct rb_root vmap_area_root = RB_ROOT;
 static bool vmap_initialized __read_mostly;
 
+static struct rb_root purge_vmap_area_root = RB_ROOT;
+static LIST_HEAD(purge_vmap_area_list);
+static DEFINE_SPINLOCK(purge_vmap_area_lock);
+
 /*
  * This kmem_cache is used for vmap_area objects. Instead of
  * allocating from slab we reuse an object from this cache to
@@ -820,10 +823,17 @@ insert:
 	if (!merged)
 		link_va(va, root, parent, link, head);
 
-	/*
-	 * Last step is to check and update the tree.
-	 */
-	augment_tree_propagate_from(va);
+	return va;
+}
+
+static __always_inline struct vmap_area *
+merge_or_add_vmap_area_augment(struct vmap_area *va,
+	struct rb_root *root, struct list_head *head)
+{
+	va = merge_or_add_vmap_area(va, root, head);
+	if (va)
+		augment_tree_propagate_from(va);
+
 	return va;
 }
 
@@ -1138,7 +1148,7 @@ static void free_vmap_area(struct vmap_area *va)
 	 * Insert/Merge it back to the free tree/list.
 	 */
 	spin_lock(&free_vmap_area_lock);
-	merge_or_add_vmap_area(va, &free_vmap_area_root, &free_vmap_area_list);
+	merge_or_add_vmap_area_augment(va, &free_vmap_area_root, &free_vmap_area_list);
 	spin_unlock(&free_vmap_area_lock);
 }
 
@@ -1326,32 +1336,32 @@ void set_iounmap_nonlazy(void)
 static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
 {
 	unsigned long resched_threshold;
-	struct llist_node *valist;
-	struct vmap_area *va;
-	struct vmap_area *n_va;
+	struct list_head local_pure_list;
+	struct vmap_area *va, *n_va;
 
 	lockdep_assert_held(&vmap_purge_lock);
 
-	valist = llist_del_all(&vmap_purge_list);
-	if (unlikely(valist == NULL))
+	spin_lock(&purge_vmap_area_lock);
+	purge_vmap_area_root = RB_ROOT;
+	list_replace_init(&purge_vmap_area_list, &local_pure_list);
+	spin_unlock(&purge_vmap_area_lock);
+
+	if (unlikely(list_empty(&local_pure_list)))
 		return false;
 
-	/*
-	 * TODO: to calculate a flush range without looping.
-	 * The list can be up to lazy_max_pages() elements.
-	 */
-	llist_for_each_entry(va, valist, purge_list) {
-		if (va->va_start < start)
-			start = va->va_start;
-		if (va->va_end > end)
-			end = va->va_end;
-	}
+	start = min(start,
+		list_first_entry(&local_pure_list,
+			struct vmap_area, list)->va_start);
+
+	end = max(end,
+		list_last_entry(&local_pure_list,
+			struct vmap_area, list)->va_end);
 
 	flush_tlb_kernel_range(start, end);
 	resched_threshold = lazy_max_pages() << 1;
 
 	spin_lock(&free_vmap_area_lock);
-	llist_for_each_entry_safe(va, n_va, valist, purge_list) {
+	list_for_each_entry_safe(va, n_va, &local_pure_list, list) {
 		unsigned long nr = (va->va_end - va->va_start) >> PAGE_SHIFT;
 		unsigned long orig_start = va->va_start;
 		unsigned long orig_end = va->va_end;
@@ -1361,8 +1371,8 @@ static bool __purge_vmap_area_lazy(unsigned long start, unsigned long end)
 		 * detached and there is no need to "unlink" it from
 		 * anything.
 		 */
-		va = merge_or_add_vmap_area(va, &free_vmap_area_root,
-					    &free_vmap_area_list);
+		va = merge_or_add_vmap_area_augment(va, &free_vmap_area_root,
+				&free_vmap_area_list);
 
 		if (!va)
 			continue;
@@ -1419,9 +1429,15 @@ static void free_vmap_area_noflush(struct vmap_area *va)
 	nr_lazy = atomic_long_add_return((va->va_end - va->va_start) >>
 				PAGE_SHIFT, &vmap_lazy_nr);
 
-	/* After this point, we may free va at any time */
-	llist_add(&va->purge_list, &vmap_purge_list);
+	/*
+	 * Merge or place it to the purge tree/list.
+	 */
+	spin_lock(&purge_vmap_area_lock);
+	merge_or_add_vmap_area(va,
+		&purge_vmap_area_root, &purge_vmap_area_list);
+	spin_unlock(&purge_vmap_area_lock);
 
+	/* After this point, we may free va at any time */
 	if (unlikely(nr_lazy > lazy_max_pages()))
 		try_purge_vmap_area_lazy();
 }
@@ -2256,7 +2272,7 @@ static void __vunmap(const void *addr, int deallocate_pages)
 	debug_check_no_locks_freed(area->addr, get_vm_area_size(area));
 	debug_check_no_obj_freed(area->addr, get_vm_area_size(area));
 
-	kasan_poison_vmalloc(area->addr, area->size);
+	kasan_poison_vmalloc(area->addr, get_vm_area_size(area));
 
 	vm_remove_mappings(area, deallocate_pages);
 
@@ -2275,7 +2291,6 @@ static void __vunmap(const void *addr, int deallocate_pages)
 	}
 
 	kfree(area);
-	return;
 }
 
 static inline void __vfree_deferred(const void *addr)
@@ -2461,9 +2476,11 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 {
 	const gfp_t nested_gfp = (gfp_mask & GFP_RECLAIM_MASK) | __GFP_ZERO;
 	unsigned int nr_pages = get_vm_area_size(area) >> PAGE_SHIFT;
-	unsigned int array_size = nr_pages * sizeof(struct page *), i;
+	unsigned long array_size;
+	unsigned int i;
 	struct page **pages;
 
+	array_size = (unsigned long)nr_pages * sizeof(struct page *);
 	gfp_mask |= __GFP_NOWARN;
 	if (!(gfp_mask & (GFP_DMA | GFP_DMA32)))
 		gfp_mask |= __GFP_HIGHMEM;
@@ -2477,8 +2494,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	}
 
 	if (!pages) {
-		remove_vm_area(area->addr);
-		kfree(area);
+		free_vm_area(area);
 		return NULL;
 	}
 
@@ -3134,6 +3150,7 @@ pvm_find_va_enclose_addr(unsigned long addr)
  * @va:
  *   in - the VA we start the search(reverse order);
  *   out - the VA with the highest aligned end address.
+ * @align: alignment for required highest address
  *
  * Returns: determined end address within vmap_area
  */
@@ -3350,8 +3367,8 @@ recovery:
 	while (area--) {
 		orig_start = vas[area]->va_start;
 		orig_end = vas[area]->va_end;
-		va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root,
-					    &free_vmap_area_list);
+		va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root,
+				&free_vmap_area_list);
 		if (va)
 			kasan_release_vmalloc(orig_start, orig_end,
 				va->va_start, va->va_end);
@@ -3400,8 +3417,8 @@ err_free_shadow:
 	for (area = 0; area < nr_vms; area++) {
 		orig_start = vas[area]->va_start;
 		orig_end = vas[area]->va_end;
-		va = merge_or_add_vmap_area(vas[area], &free_vmap_area_root,
-					    &free_vmap_area_list);
+		va = merge_or_add_vmap_area_augment(vas[area], &free_vmap_area_root,
+				&free_vmap_area_list);
 		if (va)
 			kasan_release_vmalloc(orig_start, orig_end,
 				va->va_start, va->va_end);
@@ -3448,11 +3465,11 @@ static void *s_next(struct seq_file *m, void *p, loff_t *pos)
 }
 
 static void s_stop(struct seq_file *m, void *p)
-	__releases(&vmap_purge_lock)
 	__releases(&vmap_area_lock)
+	__releases(&vmap_purge_lock)
 {
-	mutex_unlock(&vmap_purge_lock);
 	spin_unlock(&vmap_area_lock);
+	mutex_unlock(&vmap_purge_lock);
 }
 
 static void show_numa_info(struct seq_file *m, struct vm_struct *v)
@@ -3481,18 +3498,15 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v)
 
 static void show_purge_info(struct seq_file *m)
 {
-	struct llist_node *head;
 	struct vmap_area *va;
 
-	head = READ_ONCE(vmap_purge_list.first);
-	if (head == NULL)
-		return;
-
-	llist_for_each_entry(va, head, purge_list) {
+	spin_lock(&purge_vmap_area_lock);
+	list_for_each_entry(va, &purge_vmap_area_list, list) {
 		seq_printf(m, "0x%pK-0x%pK %7ld unpurged vm_area\n",
 			(void *)va->va_start, (void *)va->va_end,
 			va->va_end - va->va_start);
 	}
+	spin_unlock(&purge_vmap_area_lock);
 }
 
 static int s_show(struct seq_file *m, void *p)
@@ -3550,10 +3564,7 @@ static int s_show(struct seq_file *m, void *p)
 	seq_putc(m, '\n');
 
 	/*
-	 * As a final step, dump "unpurged" areas. Note,
-	 * that entire "/proc/vmallocinfo" output will not
-	 * be address sorted, because the purge list is not
-	 * sorted.
+	 * As a final step, dump "unpurged" areas.
 	 */
 	if (list_is_last(&va->list, &vmap_area_list))
 		show_purge_info(m);