Merge branch 'akpm' (patches from Andrew)

Merge fixes from Andrew Morton:
 "18 fixes"

[ The 18 fixes turned into 17 commits, because one of the fixes was a
  fix for another patch in the series that I just folded in by editing
  the patch manually - hopefully correctly     - Linus ]

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mm: fix memory leak in copy_huge_pmd()
  drivers/hwspinlock: fix race between radix tree insertion and lookup
  radix-tree: fix race in gang lookup
  mm/vmpressure.c: fix subtree pressure detection
  mm: polish virtual memory accounting
  mm: warn about VmData over RLIMIT_DATA
  Documentation: cgroup-v2: add memory.stat::sock description
  mm: memcontrol: drop superfluous entry in the per-memcg stats array
  drivers/scsi/sg.c: mark VMA as VM_IO to prevent migration
  proc: revert /proc/<pid>/maps [stack:TID] annotation
  numa: fix /proc/<pid>/numa_maps for hugetlbfs on s390
  MAINTAINERS: update Seth email
  ocfs2/cluster: fix memory leak in o2hb_region_release
  lib/test-string_helpers.c: fix and improve string_get_size() tests
  thp: limit number of object to scan on deferred_split_scan()
  thp: change deferred_split_count() to return number of THP in queue
  thp: make split_queue per-node

6 files changed, 103 insertions, 73 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index fd3a07b..36c0701 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -138,9 +138,6 @@ static struct khugepaged_scan khugepaged_scan = {
 	.mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head),
 };
 
-static DEFINE_SPINLOCK(split_queue_lock);
-static LIST_HEAD(split_queue);
-static unsigned long split_queue_len;
 static struct shrinker deferred_split_shrinker;
 
 static void set_recommended_min_free_kbytes(void)
@@ -861,7 +858,8 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm,
 		return false;
 	entry = mk_pmd(zero_page, vma->vm_page_prot);
 	entry = pmd_mkhuge(entry);
-	pgtable_trans_huge_deposit(mm, pmd, pgtable);
+	if (pgtable)
+		pgtable_trans_huge_deposit(mm, pmd, pgtable);
 	set_pmd_at(mm, haddr, pmd, entry);
 	atomic_long_inc(&mm->nr_ptes);
 	return true;
@@ -1039,13 +1037,15 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	spinlock_t *dst_ptl, *src_ptl;
 	struct page *src_page;
 	pmd_t pmd;
-	pgtable_t pgtable;
+	pgtable_t pgtable = NULL;
 	int ret;
 
-	ret = -ENOMEM;
-	pgtable = pte_alloc_one(dst_mm, addr);
-	if (unlikely(!pgtable))
-		goto out;
+	if (!vma_is_dax(vma)) {
+		ret = -ENOMEM;
+		pgtable = pte_alloc_one(dst_mm, addr);
+		if (unlikely(!pgtable))
+			goto out;
+	}
 
 	dst_ptl = pmd_lock(dst_mm, dst_pmd);
 	src_ptl = pmd_lockptr(src_mm, src_pmd);
@@ -1076,7 +1076,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		goto out_unlock;
 	}
 
-	if (pmd_trans_huge(pmd)) {
+	if (!vma_is_dax(vma)) {
 		/* thp accounting separate from pmd_devmap accounting */
 		src_page = pmd_page(pmd);
 		VM_BUG_ON_PAGE(!PageHead(src_page), src_page);
@@ -3358,6 +3358,7 @@ int total_mapcount(struct page *page)
 int split_huge_page_to_list(struct page *page, struct list_head *list)
 {
 	struct page *head = compound_head(page);
+	struct pglist_data *pgdata = NODE_DATA(page_to_nid(head));
 	struct anon_vma *anon_vma;
 	int count, mapcount, ret;
 	bool mlocked;
@@ -3401,19 +3402,19 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		lru_add_drain();
 
 	/* Prevent deferred_split_scan() touching ->_count */
-	spin_lock_irqsave(&split_queue_lock, flags);
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
 	count = page_count(head);
 	mapcount = total_mapcount(head);
 	if (!mapcount && count == 1) {
 		if (!list_empty(page_deferred_list(head))) {
-			split_queue_len--;
+			pgdata->split_queue_len--;
 			list_del(page_deferred_list(head));
 		}
-		spin_unlock_irqrestore(&split_queue_lock, flags);
+		spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 		__split_huge_page(page, list);
 		ret = 0;
 	} else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) {
-		spin_unlock_irqrestore(&split_queue_lock, flags);
+		spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 		pr_alert("total_mapcount: %u, page_count(): %u\n",
 				mapcount, count);
 		if (PageTail(page))
@@ -3421,7 +3422,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
 		dump_page(page, "total_mapcount(head) > 0");
 		BUG();
 	} else {
-		spin_unlock_irqrestore(&split_queue_lock, flags);
+		spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 		unfreeze_page(anon_vma, head);
 		ret = -EBUSY;
 	}
@@ -3436,64 +3437,65 @@ out:
 
 void free_transhuge_page(struct page *page)
 {
+	struct pglist_data *pgdata = NODE_DATA(page_to_nid(page));
 	unsigned long flags;
 
-	spin_lock_irqsave(&split_queue_lock, flags);
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
 	if (!list_empty(page_deferred_list(page))) {
-		split_queue_len--;
+		pgdata->split_queue_len--;
 		list_del(page_deferred_list(page));
 	}
-	spin_unlock_irqrestore(&split_queue_lock, flags);
+	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 	free_compound_page(page);
 }
 
 void deferred_split_huge_page(struct page *page)
 {
+	struct pglist_data *pgdata = NODE_DATA(page_to_nid(page));
 	unsigned long flags;
 
 	VM_BUG_ON_PAGE(!PageTransHuge(page), page);
 
-	spin_lock_irqsave(&split_queue_lock, flags);
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
 	if (list_empty(page_deferred_list(page))) {
-		list_add_tail(page_deferred_list(page), &split_queue);
-		split_queue_len++;
+		list_add_tail(page_deferred_list(page), &pgdata->split_queue);
+		pgdata->split_queue_len++;
 	}
-	spin_unlock_irqrestore(&split_queue_lock, flags);
+	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 }
 
 static unsigned long deferred_split_count(struct shrinker *shrink,
 		struct shrink_control *sc)
 {
-	/*
-	 * Split a page from split_queue will free up at least one page,
-	 * at most HPAGE_PMD_NR - 1. We don't track exact number.
-	 * Let's use HPAGE_PMD_NR / 2 as ballpark.
-	 */
-	return ACCESS_ONCE(split_queue_len) * HPAGE_PMD_NR / 2;
+	struct pglist_data *pgdata = NODE_DATA(sc->nid);
+	return ACCESS_ONCE(pgdata->split_queue_len);
 }
 
 static unsigned long deferred_split_scan(struct shrinker *shrink,
 		struct shrink_control *sc)
 {
+	struct pglist_data *pgdata = NODE_DATA(sc->nid);
 	unsigned long flags;
 	LIST_HEAD(list), *pos, *next;
 	struct page *page;
 	int split = 0;
 
-	spin_lock_irqsave(&split_queue_lock, flags);
-	list_splice_init(&split_queue, &list);
-
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
 	/* Take pin on all head pages to avoid freeing them under us */
 	list_for_each_safe(pos, next, &list) {
 		page = list_entry((void *)pos, struct page, mapping);
 		page = compound_head(page);
-		/* race with put_compound_page() */
-		if (!get_page_unless_zero(page)) {
+		if (get_page_unless_zero(page)) {
+			list_move(page_deferred_list(page), &list);
+		} else {
+			/* We lost race with put_compound_page() */
 			list_del_init(page_deferred_list(page));
-			split_queue_len--;
+			pgdata->split_queue_len--;
 		}
+		if (!--sc->nr_to_scan)
+			break;
 	}
-	spin_unlock_irqrestore(&split_queue_lock, flags);
+	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 
 	list_for_each_safe(pos, next, &list) {
 		page = list_entry((void *)pos, struct page, mapping);
@@ -3505,17 +3507,24 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
 		put_page(page);
 	}
 
-	spin_lock_irqsave(&split_queue_lock, flags);
-	list_splice_tail(&list, &split_queue);
-	spin_unlock_irqrestore(&split_queue_lock, flags);
+	spin_lock_irqsave(&pgdata->split_queue_lock, flags);
+	list_splice_tail(&list, &pgdata->split_queue);
+	spin_unlock_irqrestore(&pgdata->split_queue_lock, flags);
 
-	return split * HPAGE_PMD_NR / 2;
+	/*
+	 * Stop shrinker if we didn't split any page, but the queue is empty.
+	 * This can happen if pages were freed under us.
+	 */
+	if (!split && list_empty(&pgdata->split_queue))
+		return SHRINK_STOP;
+	return split;
 }
 
 static struct shrinker deferred_split_shrinker = {
 	.count_objects = deferred_split_count,
 	.scan_objects = deferred_split_scan,
 	.seeks = DEFAULT_SEEKS,
+	.flags = SHRINKER_NUMA_AWARE,
 };
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/mm/internal.h b/mm/internal.h
index ed8b5ff..a38a21e 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -216,6 +216,37 @@ static inline bool is_cow_mapping(vm_flags_t flags)
 	return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
 }
 
+/*
+ * These three helpers classifies VMAs for virtual memory accounting.
+ */
+
+/*
+ * Executable code area - executable, not writable, not stack
+ */
+static inline bool is_exec_mapping(vm_flags_t flags)
+{
+	return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC;
+}
+
+/*
+ * Stack area - atomatically grows in one direction
+ *
+ * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous:
+ * do_mmap() forbids all other combinations.
+ */
+static inline bool is_stack_mapping(vm_flags_t flags)
+{
+	return (flags & VM_STACK) == VM_STACK;
+}
+
+/*
+ * Data area - private, writable, not stack
+ */
+static inline bool is_data_mapping(vm_flags_t flags)
+{
+	return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE;
+}
+
 /* mm/util.c */
 void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct vm_area_struct *prev, struct rb_node *rb_parent);
diff --git a/mm/mmap.c b/mm/mmap.c
index 84b1262..cfc0cdc 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -42,6 +42,7 @@
 #include <linux/memory.h>
 #include <linux/printk.h>
 #include <linux/userfaultfd_k.h>
+#include <linux/moduleparam.h>
 
 #include <asm/uaccess.h>
 #include <asm/cacheflush.h>
@@ -69,6 +70,8 @@ const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX;
 int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS;
 #endif
 
+static bool ignore_rlimit_data = true;
+core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);
 
 static void unmap_region(struct mm_struct *mm,
 		struct vm_area_struct *vma, struct vm_area_struct *prev,
@@ -2982,9 +2985,17 @@ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages)
 	if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT)
 		return false;
 
-	if ((flags & (VM_WRITE | VM_SHARED | (VM_STACK_FLAGS &
-				(VM_GROWSUP | VM_GROWSDOWN)))) == VM_WRITE)
-		return mm->data_vm + npages <= rlimit(RLIMIT_DATA);
+	if (is_data_mapping(flags) &&
+	    mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) {
+		if (ignore_rlimit_data)
+			pr_warn_once("%s (%d): VmData %lu exceed data ulimit "
+				     "%lu. Will be forbidden soon.\n",
+				     current->comm, current->pid,
+				     (mm->data_vm + npages) << PAGE_SHIFT,
+				     rlimit(RLIMIT_DATA));
+		else
+			return false;
+	}
 
 	return true;
 }
@@ -2993,11 +3004,11 @@ void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages)
 {
 	mm->total_vm += npages;
 
-	if ((flags & (VM_EXEC | VM_WRITE)) == VM_EXEC)
+	if (is_exec_mapping(flags))
 		mm->exec_vm += npages;
-	else if (flags & (VM_STACK_FLAGS & (VM_GROWSUP | VM_GROWSDOWN)))
+	else if (is_stack_mapping(flags))
 		mm->stack_vm += npages;
-	else if ((flags & (VM_WRITE | VM_SHARED)) == VM_WRITE)
+	else if (is_data_mapping(flags))
 		mm->data_vm += npages;
 }
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 63358d9..ea2c4d3 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5210,6 +5210,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 	pgdat->numabalancing_migrate_nr_pages = 0;
 	pgdat->numabalancing_migrate_next_window = jiffies;
 #endif
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	spin_lock_init(&pgdat->split_queue_lock);
+	INIT_LIST_HEAD(&pgdat->split_queue);
+	pgdat->split_queue_len = 0;
+#endif
 	init_waitqueue_head(&pgdat->kswapd_wait);
 	init_waitqueue_head(&pgdat->pfmemalloc_wait);
 	pgdat_page_ext_init(pgdat);
diff --git a/mm/util.c b/mm/util.c
index c108a65..4fb14ca 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -230,36 +230,11 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 }
 
 /* Check if the vma is being used as a stack by this task */
-static int vm_is_stack_for_task(struct task_struct *t,
-				struct vm_area_struct *vma)
+int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t)
 {
 	return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
 }
 
-/*
- * Check if the vma is being used as a stack.
- * If is_group is non-zero, check in the entire thread group or else
- * just check in the current task. Returns the task_struct of the task
- * that the vma is stack for. Must be called under rcu_read_lock().
- */
-struct task_struct *task_of_stack(struct task_struct *task,
-				struct vm_area_struct *vma, bool in_group)
-{
-	if (vm_is_stack_for_task(task, vma))
-		return task;
-
-	if (in_group) {
-		struct task_struct *t;
-
-		for_each_thread(task, t) {
-			if (vm_is_stack_for_task(t, vma))
-				return t;
-		}
-	}
-
-	return NULL;
-}
-
 #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
 void arch_pick_mmap_layout(struct mm_struct *mm)
 {
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index 9a6c070..149fdf6 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -248,9 +248,8 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree,
 
 	if (tree) {
 		spin_lock(&vmpr->sr_lock);
-		vmpr->tree_scanned += scanned;
+		scanned = vmpr->tree_scanned += scanned;
 		vmpr->tree_reclaimed += reclaimed;
-		scanned = vmpr->scanned;
 		spin_unlock(&vmpr->sr_lock);
 
 		if (scanned < vmpressure_win)