Merge branch 'linus' into timers/core

Pick up the latest fixes and refresh the branch.

Signed-off-by: Ingo Molnar <mingo@kernel.org>

15 files changed, 281 insertions, 78 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index eb69f352401d..723bbe04a0b0 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -543,7 +543,7 @@ config ZSWAP
 
 config MEM_SOFT_DIRTY
 	bool "Track memory changes"
-	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY
+	depends on CHECKPOINT_RESTORE && HAVE_ARCH_SOFT_DIRTY && PROC_FS
 	select PROC_PAGE_MONITOR
 	help
 	  This option enables memory changes tracking by introducing a
diff --git a/mm/compaction.c b/mm/compaction.c
index 805165bcd3dd..f58bcd016f43 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -134,6 +134,10 @@ static void update_pageblock_skip(struct compact_control *cc,
 			bool migrate_scanner)
 {
 	struct zone *zone = cc->zone;
+
+	if (cc->ignore_skip_hint)
+		return;
+
 	if (!page)
 		return;
 
diff --git a/mm/fremap.c b/mm/fremap.c
index 5bff08147768..bbc4d660221a 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -208,9 +208,10 @@ get_write_lock:
 		if (mapping_cap_account_dirty(mapping)) {
 			unsigned long addr;
 			struct file *file = get_file(vma->vm_file);
+			/* mmap_region may free vma; grab the info now */
+			vm_flags = vma->vm_flags;
 
-			addr = mmap_region(file, start, size,
-					vma->vm_flags, pgoff);
+			addr = mmap_region(file, start, size, vm_flags, pgoff);
 			fput(file);
 			if (IS_ERR_VALUE(addr)) {
 				err = addr;
@@ -218,7 +219,7 @@ get_write_lock:
 				BUG_ON(addr != start);
 				err = 0;
 			}
-			goto out;
+			goto out_freed;
 		}
 		mutex_lock(&mapping->i_mmap_mutex);
 		flush_dcache_mmap_lock(mapping);
@@ -253,6 +254,7 @@ get_write_lock:
 out:
 	if (vma)
 		vm_flags = vma->vm_flags;
+out_freed:
 	if (likely(!has_write_lock))
 		up_read(&mm->mmap_sem);
 	else
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index bccd5a628ea6..9c0b17295ba0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -882,6 +882,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		ret = 0;
 		goto out_unlock;
 	}
+
 	if (unlikely(pmd_trans_splitting(pmd))) {
 		/* split huge page running from under us */
 		spin_unlock(src_ptl);
@@ -1243,6 +1244,10 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma,
 	if ((flags & FOLL_DUMP) && is_huge_zero_pmd(*pmd))
 		return ERR_PTR(-EFAULT);
 
+	/* Full NUMA hinting faults to serialise migration in fault paths */
+	if ((flags & FOLL_NUMA) && pmd_numa(*pmd))
+		goto out;
+
 	page = pmd_page(*pmd);
 	VM_BUG_ON(!PageHead(page));
 	if (flags & FOLL_TOUCH) {
@@ -1295,6 +1300,17 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (unlikely(!pmd_same(pmd, *pmdp)))
 		goto out_unlock;
 
+	/*
+	 * If there are potential migrations, wait for completion and retry
+	 * without disrupting NUMA hinting information. Do not relock and
+	 * check_same as the page may no longer be mapped.
+	 */
+	if (unlikely(pmd_trans_migrating(*pmdp))) {
+		spin_unlock(ptl);
+		wait_migrate_huge_page(vma->anon_vma, pmdp);
+		goto out;
+	}
+
 	page = pmd_page(pmd);
 	BUG_ON(is_huge_zero_page(page));
 	page_nid = page_to_nid(page);
@@ -1323,23 +1339,22 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		/* If the page was locked, there are no parallel migrations */
 		if (page_locked)
 			goto clear_pmdnuma;
+	}
 
-		/*
-		 * Otherwise wait for potential migrations and retry. We do
-		 * relock and check_same as the page may no longer be mapped.
-		 * As the fault is being retried, do not account for it.
-		 */
+	/* Migration could have started since the pmd_trans_migrating check */
+	if (!page_locked) {
 		spin_unlock(ptl);
 		wait_on_page_locked(page);
 		page_nid = -1;
 		goto out;
 	}
 
-	/* Page is misplaced, serialise migrations and parallel THP splits */
+	/*
+	 * Page is misplaced. Page lock serialises migrations. Acquire anon_vma
+	 * to serialises splits
+	 */
 	get_page(page);
 	spin_unlock(ptl);
-	if (!page_locked)
-		lock_page(page);
 	anon_vma = page_lock_anon_vma_read(page);
 
 	/* Confirm the PMD did not change while page_table_lock was released */
@@ -1351,6 +1366,13 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_unlock;
 	}
 
+	/* Bail if we fail to protect against THP splits for any reason */
+	if (unlikely(!anon_vma)) {
+		put_page(page);
+		page_nid = -1;
+		goto clear_pmdnuma;
+	}
+
 	/*
 	 * Migrate the THP to the requested node, returns with page unlocked
 	 * and pmd_numa cleared.
@@ -1481,8 +1503,18 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma,
 		pmd = pmdp_get_and_clear(mm, old_addr, old_pmd);
 		VM_BUG_ON(!pmd_none(*new_pmd));
 		set_pmd_at(mm, new_addr, new_pmd, pmd_mksoft_dirty(pmd));
-		if (new_ptl != old_ptl)
+		if (new_ptl != old_ptl) {
+			pgtable_t pgtable;
+
+			/*
+			 * Move preallocated PTE page table if new_pmd is on
+			 * different PMD page table.
+			 */
+			pgtable = pgtable_trans_huge_withdraw(mm, old_pmd);
+			pgtable_trans_huge_deposit(mm, new_pmd, pgtable);
+
 			spin_unlock(new_ptl);
+		}
 		spin_unlock(old_ptl);
 	}
 out:
@@ -1507,6 +1539,8 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 		ret = 1;
 		if (!prot_numa) {
 			entry = pmdp_get_and_clear(mm, addr, pmd);
+			if (pmd_numa(entry))
+				entry = pmd_mknonnuma(entry);
 			entry = pmd_modify(entry, newprot);
 			ret = HPAGE_PMD_NR;
 			BUG_ON(pmd_write(entry));
@@ -1521,7 +1555,7 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 			 */
 			if (!is_huge_zero_page(page) &&
 			    !pmd_numa(*pmd)) {
-				entry = pmdp_get_and_clear(mm, addr, pmd);
+				entry = *pmd;
 				entry = pmd_mknuma(entry);
 				ret = HPAGE_PMD_NR;
 			}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index f1a0ae6e11b8..7f1a356153c0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -338,7 +338,7 @@ struct mem_cgroup {
 static size_t memcg_size(void)
 {
 	return sizeof(struct mem_cgroup) +
-		nr_node_ids * sizeof(struct mem_cgroup_per_node);
+		nr_node_ids * sizeof(struct mem_cgroup_per_node *);
 }
 
 /* internal only representation about the status of kmem accounting. */
@@ -2694,7 +2694,10 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 		goto bypass;
 
 	if (unlikely(task_in_memcg_oom(current)))
-		goto bypass;
+		goto nomem;
+
+	if (gfp_mask & __GFP_NOFAIL)
+		oom = false;
 
 	/*
 	 * We always charge the cgroup the mm_struct belongs to.
@@ -6352,6 +6355,42 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css)
 static void mem_cgroup_css_free(struct cgroup_subsys_state *css)
 {
 	struct mem_cgroup *memcg = mem_cgroup_from_css(css);
+	/*
+	 * XXX: css_offline() would be where we should reparent all
+	 * memory to prepare the cgroup for destruction.  However,
+	 * memcg does not do css_tryget() and res_counter charging
+	 * under the same RCU lock region, which means that charging
+	 * could race with offlining.  Offlining only happens to
+	 * cgroups with no tasks in them but charges can show up
+	 * without any tasks from the swapin path when the target
+	 * memcg is looked up from the swapout record and not from the
+	 * current task as it usually is.  A race like this can leak
+	 * charges and put pages with stale cgroup pointers into
+	 * circulation:
+	 *
+	 * #0                        #1
+	 *                           lookup_swap_cgroup_id()
+	 *                           rcu_read_lock()
+	 *                           mem_cgroup_lookup()
+	 *                           css_tryget()
+	 *                           rcu_read_unlock()
+	 * disable css_tryget()
+	 * call_rcu()
+	 *   offline_css()
+	 *     reparent_charges()
+	 *                           res_counter_charge()
+	 *                           css_put()
+	 *                             css_free()
+	 *                           pc->mem_cgroup = dead memcg
+	 *                           add page to lru
+	 *
+	 * The bulk of the charges are still moved in offline_css() to
+	 * avoid pinning a lot of pages in case a long-term reference
+	 * like a swapout record is deferring the css_free() to long
+	 * after offlining.  But this makes sure we catch any charges
+	 * made after offlining:
+	 */
+	mem_cgroup_reparent_charges(memcg);
 
 	memcg_destroy_kmem(memcg);
 	__mem_cgroup_free(memcg);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index b7c171602ba1..fabe55046c1d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -938,6 +938,16 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn,
 				BUG_ON(!PageHWPoison(p));
 				return SWAP_FAIL;
 			}
+			/*
+			 * We pinned the head page for hwpoison handling,
+			 * now we split the thp and we are interested in
+			 * the hwpoisoned raw page, so move the refcount
+			 * to it.
+			 */
+			if (hpage != p) {
+				put_page(hpage);
+				get_page(p);
+			}
 			/* THP is split, so ppage should be the real poisoned page. */
 			ppage = p;
 		}
@@ -1505,10 +1515,16 @@ static int soft_offline_huge_page(struct page *page, int flags)
 		if (ret > 0)
 			ret = -EIO;
 	} else {
-		set_page_hwpoison_huge_page(hpage);
-		dequeue_hwpoisoned_huge_page(hpage);
-		atomic_long_add(1 << compound_order(hpage),
-				&num_poisoned_pages);
+		/* overcommit hugetlb page will be freed to buddy */
+		if (PageHuge(page)) {
+			set_page_hwpoison_huge_page(hpage);
+			dequeue_hwpoisoned_huge_page(hpage);
+			atomic_long_add(1 << compound_order(hpage),
+					&num_poisoned_pages);
+		} else {
+			SetPageHWPoison(page);
+			atomic_long_inc(&num_poisoned_pages);
+		}
 	}
 	return ret;
 }
diff --git a/mm/memory.c b/mm/memory.c
index 5d9025f3b3e1..6768ce9e57d2 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4271,7 +4271,7 @@ void copy_user_huge_page(struct page *dst, struct page *src,
 }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE || CONFIG_HUGETLBFS */
 
-#if USE_SPLIT_PTE_PTLOCKS && BLOATED_SPINLOCKS
+#if USE_SPLIT_PTE_PTLOCKS && ALLOC_SPLIT_PTLOCKS
 bool ptlock_alloc(struct page *page)
 {
 	spinlock_t *ptl;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index eca4a3129129..0cd2c4d4e270 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1197,14 +1197,16 @@ static struct page *new_vma_page(struct page *page, unsigned long private, int *
 			break;
 		vma = vma->vm_next;
 	}
+
+	if (PageHuge(page)) {
+		if (vma)
+			return alloc_huge_page_noerr(vma, address, 1);
+		else
+			return NULL;
+	}
 	/*
-	 * queue_pages_range() confirms that @page belongs to some vma,
-	 * so vma shouldn't be NULL.
+	 * if !vma, alloc_page_vma() will use task or system default policy
 	 */
-	BUG_ON(!vma);
-
-	if (PageHuge(page))
-		return alloc_huge_page_noerr(vma, address, 1);
 	return alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
 }
 #else
@@ -1318,7 +1320,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 		if (nr_failed && (flags & MPOL_MF_STRICT))
 			err = -EIO;
 	} else
-		putback_lru_pages(&pagelist);
+		putback_movable_pages(&pagelist);
 
 	up_write(&mm->mmap_sem);
  mpol_out:
diff --git a/mm/migrate.c b/mm/migrate.c
index bb940045fe85..9194375b2307 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -36,6 +36,7 @@
 #include <linux/hugetlb_cgroup.h>
 #include <linux/gfp.h>
 #include <linux/balloon_compaction.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/tlbflush.h>
 
@@ -316,14 +317,15 @@ static inline bool buffer_migrate_lock_buffers(struct buffer_head *head,
  */
 int migrate_page_move_mapping(struct address_space *mapping,
 		struct page *newpage, struct page *page,
-		struct buffer_head *head, enum migrate_mode mode)
+		struct buffer_head *head, enum migrate_mode mode,
+		int extra_count)
 {
-	int expected_count = 0;
+	int expected_count = 1 + extra_count;
 	void **pslot;
 
 	if (!mapping) {
 		/* Anonymous page without mapping */
-		if (page_count(page) != 1)
+		if (page_count(page) != expected_count)
 			return -EAGAIN;
 		return MIGRATEPAGE_SUCCESS;
 	}
@@ -333,7 +335,7 @@ int migrate_page_move_mapping(struct address_space *mapping,
 	pslot = radix_tree_lookup_slot(&mapping->page_tree,
  					page_index(page));
 
-	expected_count = 2 + page_has_private(page);
+	expected_count += 1 + page_has_private(page);
 	if (page_count(page) != expected_count ||
 		radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) {
 		spin_unlock_irq(&mapping->tree_lock);
@@ -583,7 +585,7 @@ int migrate_page(struct address_space *mapping,
 
 	BUG_ON(PageWriteback(page));	/* Writeback must be complete */
 
-	rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode);
+	rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0);
 
 	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
@@ -610,7 +612,7 @@ int buffer_migrate_page(struct address_space *mapping,
 
 	head = page_buffers(page);
 
-	rc = migrate_page_move_mapping(mapping, newpage, page, head, mode);
+	rc = migrate_page_move_mapping(mapping, newpage, page, head, mode, 0);
 
 	if (rc != MIGRATEPAGE_SUCCESS)
 		return rc;
@@ -1654,6 +1656,18 @@ int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page)
 	return 1;
 }
 
+bool pmd_trans_migrating(pmd_t pmd)
+{
+	struct page *page = pmd_page(pmd);
+	return PageLocked(page);
+}
+
+void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd)
+{
+	struct page *page = pmd_page(*pmd);
+	wait_on_page_locked(page);
+}
+
 /*
  * Attempt to migrate a misplaced page to the specified destination
  * node. Caller is expected to have an elevated reference count on
@@ -1716,12 +1730,14 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 				struct page *page, int node)
 {
 	spinlock_t *ptl;
-	unsigned long haddr = address & HPAGE_PMD_MASK;
 	pg_data_t *pgdat = NODE_DATA(node);
 	int isolated = 0;
 	struct page *new_page = NULL;
 	struct mem_cgroup *memcg = NULL;
 	int page_lru = page_is_file_cache(page);
+	unsigned long mmun_start = address & HPAGE_PMD_MASK;
+	unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE;
+	pmd_t orig_entry;
 
 	/*
 	 * Rate-limit the amount of data that is being migrated to a node.
@@ -1744,6 +1760,9 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		goto out_fail;
 	}
 
+	if (mm_tlb_flush_pending(mm))
+		flush_tlb_range(vma, mmun_start, mmun_end);
+
 	/* Prepare a page as a migration target */
 	__set_page_locked(new_page);
 	SetPageSwapBacked(new_page);
@@ -1755,9 +1774,12 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	WARN_ON(PageLRU(new_page));
 
 	/* Recheck the target PMD */
+	mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end);
 	ptl = pmd_lock(mm, pmd);
-	if (unlikely(!pmd_same(*pmd, entry))) {
+	if (unlikely(!pmd_same(*pmd, entry) || page_count(page) != 2)) {
+fail_putback:
 		spin_unlock(ptl);
+		mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
 		/* Reverse changes made by migrate_page_copy() */
 		if (TestClearPageActive(new_page))
@@ -1774,7 +1796,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 		putback_lru_page(page);
 		mod_zone_page_state(page_zone(page),
 			 NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR);
-		goto out_fail;
+
+		goto out_unlock;
 	}
 
 	/*
@@ -1786,16 +1809,35 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	 */
 	mem_cgroup_prepare_migration(page, new_page, &memcg);
 
+	orig_entry = *pmd;
 	entry = mk_pmd(new_page, vma->vm_page_prot);
-	entry = pmd_mknonnuma(entry);
-	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 	entry = pmd_mkhuge(entry);
+	entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma);
 
-	pmdp_clear_flush(vma, haddr, pmd);
-	set_pmd_at(mm, haddr, pmd, entry);
-	page_add_new_anon_rmap(new_page, vma, haddr);
+	/*
+	 * Clear the old entry under pagetable lock and establish the new PTE.
+	 * Any parallel GUP will either observe the old page blocking on the
+	 * page lock, block on the page table lock or observe the new page.
+	 * The SetPageUptodate on the new page and page_add_new_anon_rmap
+	 * guarantee the copy is visible before the pagetable update.
+	 */
+	flush_cache_range(vma, mmun_start, mmun_end);
+	page_add_new_anon_rmap(new_page, vma, mmun_start);
+	pmdp_clear_flush(vma, mmun_start, pmd);
+	set_pmd_at(mm, mmun_start, pmd, entry);
+	flush_tlb_range(vma, mmun_start, mmun_end);
 	update_mmu_cache_pmd(vma, address, &entry);
+
+	if (page_count(page) != 2) {
+		set_pmd_at(mm, mmun_start, pmd, orig_entry);
+		flush_tlb_range(vma, mmun_start, mmun_end);
+		update_mmu_cache_pmd(vma, address, &entry);
+		page_remove_rmap(new_page);
+		goto fail_putback;
+	}
+
 	page_remove_rmap(page);
+
 	/*
 	 * Finish the charge transaction under the page table lock to
 	 * prevent split_huge_page() from dividing up the charge
@@ -1803,6 +1845,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 	 */
 	mem_cgroup_end_migration(memcg, page, new_page, true);
 	spin_unlock(ptl);
+	mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end);
 
 	unlock_page(new_page);
 	unlock_page(page);
@@ -1820,10 +1863,15 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm,
 out_fail:
 	count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR);
 out_dropref:
-	entry = pmd_mknonnuma(entry);
-	set_pmd_at(mm, haddr, pmd, entry);
-	update_mmu_cache_pmd(vma, address, &entry);
+	ptl = pmd_lock(mm, pmd);
+	if (pmd_same(*pmd, entry)) {
+		entry = pmd_mknonnuma(entry);
+		set_pmd_at(mm, mmun_start, pmd, entry);
+		update_mmu_cache_pmd(vma, address, &entry);
+	}
+	spin_unlock(ptl);
 
+out_unlock:
 	unlock_page(page);
 	put_page(page);
 	return 0;
diff --git a/mm/mlock.c b/mm/mlock.c
index d480cd6fc475..192e6eebe4f2 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -133,7 +133,10 @@ static void __munlock_isolation_failed(struct page *page)
 
 /**
  * munlock_vma_page - munlock a vma page
- * @page - page to be unlocked
+ * @page - page to be unlocked, either a normal page or THP page head
+ *
+ * returns the size of the page as a page mask (0 for normal page,
+ *         HPAGE_PMD_NR - 1 for THP head page)
  *
  * called from munlock()/munmap() path with page supposedly on the LRU.
  * When we munlock a page, because the vma where we found the page is being
@@ -148,21 +151,30 @@ static void __munlock_isolation_failed(struct page *page)
  */
 unsigned int munlock_vma_page(struct page *page)
 {
-	unsigned int page_mask = 0;
+	unsigned int nr_pages;
 
 	BUG_ON(!PageLocked(page));
 
 	if (TestClearPageMlocked(page)) {
-		unsigned int nr_pages = hpage_nr_pages(page);
+		nr_pages = hpage_nr_pages(page);
 		mod_zone_page_state(page_zone(page), NR_MLOCK, -nr_pages);
-		page_mask = nr_pages - 1;
 		if (!isolate_lru_page(page))
 			__munlock_isolated_page(page);
 		else
 			__munlock_isolation_failed(page);
+	} else {
+		nr_pages = hpage_nr_pages(page);
 	}
 
-	return page_mask;
+	/*
+	 * Regardless of the original PageMlocked flag, we determine nr_pages
+	 * after touching the flag. This leaves a possible race with a THP page
+	 * split, such that a whole THP page was munlocked, but nr_pages == 1.
+	 * Returning a smaller mask due to that is OK, the worst that can
+	 * happen is subsequent useless scanning of the former tail pages.
+	 * The NR_MLOCK accounting can however become broken.
+	 */
+	return nr_pages - 1;
 }
 
 /**
@@ -286,10 +298,12 @@ static void __munlock_pagevec(struct pagevec *pvec, struct zone *zone)
 {
 	int i;
 	int nr = pagevec_count(pvec);
-	int delta_munlocked = -nr;
+	int delta_munlocked;
 	struct pagevec pvec_putback;
 	int pgrescued = 0;
 
+	pagevec_init(&pvec_putback, 0);
+
 	/* Phase 1: page isolation */
 	spin_lock_irq(&zone->lru_lock);
 	for (i = 0; i < nr; i++) {
@@ -318,18 +332,21 @@ skip_munlock:
 			/*
 			 * We won't be munlocking this page in the next phase
 			 * but we still need to release the follow_page_mask()
-			 * pin.
+			 * pin. We cannot do it under lru_lock however. If it's
+			 * the last pin, __page_cache_release would deadlock.
 			 */
+			pagevec_add(&pvec_putback, pvec->pages[i]);
 			pvec->pages[i] = NULL;
-			put_page(page);
-			delta_munlocked++;
 		}
 	}
+	delta_munlocked = -nr + pagevec_count(&pvec_putback);
 	__mod_zone_page_state(zone, NR_MLOCK, delta_munlocked);
 	spin_unlock_irq(&zone->lru_lock);
 
+	/* Now we can release pins of pages that we are not munlocking */
+	pagevec_release(&pvec_putback);
+
 	/* Phase 2: page munlock */
-	pagevec_init(&pvec_putback, 0);
 	for (i = 0; i < nr; i++) {
 		struct page *page = pvec->pages[i];
 
@@ -440,7 +457,8 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 
 	while (start < end) {
 		struct page *page = NULL;
-		unsigned int page_mask, page_increm;
+		unsigned int page_mask;
+		unsigned long page_increm;
 		struct pagevec pvec;
 		struct zone *zone;
 		int zoneid;
@@ -490,7 +508,9 @@ void munlock_vma_pages_range(struct vm_area_struct *vma,
 				goto next;
 			}
 		}
-		page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask);
+		/* It's a bug to munlock in the middle of a THP page */
+		VM_BUG_ON((start >> PAGE_SHIFT) & page_mask);
+		page_increm = 1 + page_mask;
 		start += page_increm * PAGE_SIZE;
 next:
 		cond_resched();
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 26667971c824..bb53a6591aea 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -52,17 +52,21 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 			pte_t ptent;
 			bool updated = false;
 
-			ptent = ptep_modify_prot_start(mm, addr, pte);
 			if (!prot_numa) {
+				ptent = ptep_modify_prot_start(mm, addr, pte);
+				if (pte_numa(ptent))
+					ptent = pte_mknonnuma(ptent);
 				ptent = pte_modify(ptent, newprot);
 				updated = true;
 			} else {
 				struct page *page;
 
+				ptent = *pte;
 				page = vm_normal_page(vma, addr, oldpte);
 				if (page) {
 					if (!pte_numa(oldpte)) {
 						ptent = pte_mknuma(ptent);
+						set_pte_at(mm, addr, pte, ptent);
 						updated = true;
 					}
 				}
@@ -79,7 +83,10 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 
 			if (updated)
 				pages++;
-			ptep_modify_prot_commit(mm, addr, pte, ptent);
+
+			/* Only !prot_numa always clears the pte */
+			if (!prot_numa)
+				ptep_modify_prot_commit(mm, addr, pte, ptent);
 		} else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) {
 			swp_entry_t entry = pte_to_swp_entry(oldpte);
 
@@ -181,6 +188,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 	BUG_ON(addr >= end);
 	pgd = pgd_offset(mm, addr);
 	flush_cache_range(vma, addr, end);
+	set_tlb_flush_pending(mm);
 	do {
 		next = pgd_addr_end(addr, end);
 		if (pgd_none_or_clear_bad(pgd))
@@ -192,6 +200,7 @@ static unsigned long change_protection_range(struct vm_area_struct *vma,
 	/* Only flush the TLB if we actually modified any entries: */
 	if (pages)
 		flush_tlb_range(vma, start, end);
+	clear_tlb_flush_pending(mm);
 
 	return pages;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 580a5f075ed0..5248fe070aa4 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1816,7 +1816,7 @@ static void zlc_clear_zones_full(struct zonelist *zonelist)
 
 static bool zone_local(struct zone *local_zone, struct zone *zone)
 {
-	return node_distance(local_zone->node, zone->node) == LOCAL_DISTANCE;
+	return local_zone->node == zone->node;
 }
 
 static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone)
@@ -1913,18 +1913,17 @@ zonelist_scan:
 		 * page was allocated in should have no effect on the
 		 * time the page has in memory before being reclaimed.
 		 *
-		 * When zone_reclaim_mode is enabled, try to stay in
-		 * local zones in the fastpath.  If that fails, the
-		 * slowpath is entered, which will do another pass
-		 * starting with the local zones, but ultimately fall
-		 * back to remote zones that do not partake in the
-		 * fairness round-robin cycle of this zonelist.
+		 * Try to stay in local zones in the fastpath.  If
+		 * that fails, the slowpath is entered, which will do
+		 * another pass starting with the local zones, but
+		 * ultimately fall back to remote zones that do not
+		 * partake in the fairness round-robin cycle of this
+		 * zonelist.
 		 */
 		if (alloc_flags & ALLOC_WMARK_LOW) {
 			if (zone_page_state(zone, NR_ALLOC_BATCH) <= 0)
 				continue;
-			if (zone_reclaim_mode &&
-			    !zone_local(preferred_zone, zone))
+			if (!zone_local(preferred_zone, zone))
 				continue;
 		}
 		/*
@@ -2390,7 +2389,7 @@ static void prepare_slowpath(gfp_t gfp_mask, unsigned int order,
 		 * thrash fairness information for zones that are not
 		 * actually part of this zonelist's round-robin cycle.
 		 */
-		if (zone_reclaim_mode && !zone_local(preferred_zone, zone))
+		if (!zone_local(preferred_zone, zone))
 			continue;
 		mod_zone_page_state(zone, NR_ALLOC_BATCH,
 				    high_wmark_pages(zone) -
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index cbb38545d9d6..a8b919925934 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -110,9 +110,10 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma,
 pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
 		       pte_t *ptep)
 {
+	struct mm_struct *mm = (vma)->vm_mm;
 	pte_t pte;
-	pte = ptep_get_and_clear((vma)->vm_mm, address, ptep);
-	if (pte_accessible(pte))
+	pte = ptep_get_and_clear(mm, address, ptep);
+	if (pte_accessible(mm, pte))
 		flush_tlb_page(vma, address);
 	return pte;
 }
@@ -191,6 +192,9 @@ pgtable_t pgtable_trans_huge_withdraw(struct mm_struct *mm, pmd_t *pmdp)
 void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
+	pmd_t entry = *pmdp;
+	if (pmd_numa(entry))
+		entry = pmd_mknonnuma(entry);
 	set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(*pmdp));
 	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 }
diff --git a/mm/rmap.c b/mm/rmap.c
index 55c8b8dc9ffb..068522d8502a 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -600,7 +600,11 @@ pte_t *__page_check_address(struct page *page, struct mm_struct *mm,
 	spinlock_t *ptl;
 
 	if (unlikely(PageHuge(page))) {
+		/* when pud is not present, pte will be NULL */
 		pte = huge_pte_offset(mm, address);
+		if (!pte)
+			return NULL;
+
 		ptl = huge_pte_lockptr(page_hstate(page), mm, pte);
 		goto check;
 	}
diff --git a/mm/shmem.c b/mm/shmem.c
index 8297623fcaed..902a14842b74 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2918,13 +2918,8 @@ static struct dentry_operations anon_ops = {
 	.d_dname = simple_dname
 };
 
-/**
- * shmem_file_setup - get an unlinked file living in tmpfs
- * @name: name for dentry (to be seen in /proc/<pid>/maps
- * @size: size to be set for the file
- * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
- */
-struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags)
+static struct file *__shmem_file_setup(const char *name, loff_t size,
+				       unsigned long flags, unsigned int i_flags)
 {
 	struct file *res;
 	struct inode *inode;
@@ -2957,6 +2952,7 @@ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags
 	if (!inode)
 		goto put_dentry;
 
+	inode->i_flags |= i_flags;
 	d_instantiate(path.dentry, inode);
 	inode->i_size = size;
 	clear_nlink(inode);	/* It is unlinked */
@@ -2977,6 +2973,32 @@ put_memory:
 	shmem_unacct_size(flags, size);
 	return res;
 }
+
+/**
+ * shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be
+ * 	kernel internal.  There will be NO LSM permission checks against the
+ * 	underlying inode.  So users of this interface must do LSM checks at a
+ * 	higher layer.  The one user is the big_key implementation.  LSM checks
+ * 	are provided at the key level rather than the inode level.
+ * @name: name for dentry (to be seen in /proc/<pid>/maps
+ * @size: size to be set for the file
+ * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
+ */
+struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags)
+{
+	return __shmem_file_setup(name, size, flags, S_PRIVATE);
+}
+
+/**
+ * shmem_file_setup - get an unlinked file living in tmpfs
+ * @name: name for dentry (to be seen in /proc/<pid>/maps
+ * @size: size to be set for the file
+ * @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
+ */
+struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags)
+{
+	return __shmem_file_setup(name, size, flags, 0);
+}
 EXPORT_SYMBOL_GPL(shmem_file_setup);
 
 /**