Merge branch 'timers/urgent' into timers/core, to pick up fix

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

13 files changed, 156 insertions, 111 deletions

diff --git a/mm/debug.c b/mm/debug.c
index 8345bb6e4769..0461df1207cb 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -67,28 +67,31 @@ void __dump_page(struct page *page, const char *reason)
 	 */
 	mapcount = PageSlab(page) ? 0 : page_mapcount(page);
 
-	pr_warn("page:%px refcount:%d mapcount:%d mapping:%px index:%#lx",
-		  page, page_ref_count(page), mapcount,
-		  page->mapping, page_to_pgoff(page));
 	if (PageCompound(page))
-		pr_cont(" compound_mapcount: %d", compound_mapcount(page));
-	pr_cont("\n");
-	if (PageAnon(page))
-		pr_warn("anon ");
-	else if (PageKsm(page))
-		pr_warn("ksm ");
+		pr_warn("page:%px refcount:%d mapcount:%d mapping:%px "
+			"index:%#lx compound_mapcount: %d\n",
+			page, page_ref_count(page), mapcount,
+			page->mapping, page_to_pgoff(page),
+			compound_mapcount(page));
+	else
+		pr_warn("page:%px refcount:%d mapcount:%d mapping:%px index:%#lx\n",
+			page, page_ref_count(page), mapcount,
+			page->mapping, page_to_pgoff(page));
+	if (PageKsm(page))
+		pr_warn("ksm flags: %#lx(%pGp)\n", page->flags, &page->flags);
+	else if (PageAnon(page))
+		pr_warn("anon flags: %#lx(%pGp)\n", page->flags, &page->flags);
 	else if (mapping) {
-		pr_warn("%ps ", mapping->a_ops);
 		if (mapping->host && mapping->host->i_dentry.first) {
 			struct dentry *dentry;
 			dentry = container_of(mapping->host->i_dentry.first, struct dentry, d_u.d_alias);
-			pr_warn("name:\"%pd\" ", dentry);
-		}
+			pr_warn("%ps name:\"%pd\"\n", mapping->a_ops, dentry);
+		} else
+			pr_warn("%ps\n", mapping->a_ops);
+		pr_warn("flags: %#lx(%pGp)\n", page->flags, &page->flags);
 	}
 	BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1);
 
-	pr_warn("flags: %#lx(%pGp)\n", page->flags, &page->flags);
-
 hex_only:
 	print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32,
 			sizeof(unsigned long), page,
diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c
index f1930fa0b445..2ac38bdc18a1 100644
--- a/mm/hugetlb_cgroup.c
+++ b/mm/hugetlb_cgroup.c
@@ -196,7 +196,7 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages,
 again:
 	rcu_read_lock();
 	h_cg = hugetlb_cgroup_from_task(current);
-	if (!css_tryget_online(&h_cg->css)) {
+	if (!css_tryget(&h_cg->css)) {
 		rcu_read_unlock();
 		goto again;
 	}
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 0a1b4b484ac5..a8a57bebb5fa 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1028,12 +1028,13 @@ static void collapse_huge_page(struct mm_struct *mm,
 
 	anon_vma_lock_write(vma->anon_vma);
 
-	pte = pte_offset_map(pmd, address);
-	pte_ptl = pte_lockptr(mm, pmd);
-
 	mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm,
 				address, address + HPAGE_PMD_SIZE);
 	mmu_notifier_invalidate_range_start(&range);
+
+	pte = pte_offset_map(pmd, address);
+	pte_ptl = pte_lockptr(mm, pmd);
+
 	pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */
 	/*
 	 * After this gup_fast can't run anymore. This also removes
@@ -1601,17 +1602,6 @@ static void collapse_file(struct mm_struct *mm,
 					result = SCAN_FAIL;
 					goto xa_unlocked;
 				}
-			} else if (!PageUptodate(page)) {
-				xas_unlock_irq(&xas);
-				wait_on_page_locked(page);
-				if (!trylock_page(page)) {
-					result = SCAN_PAGE_LOCK;
-					goto xa_unlocked;
-				}
-				get_page(page);
-			} else if (PageDirty(page)) {
-				result = SCAN_FAIL;
-				goto xa_locked;
 			} else if (trylock_page(page)) {
 				get_page(page);
 				xas_unlock_irq(&xas);
@@ -1626,7 +1616,12 @@ static void collapse_file(struct mm_struct *mm,
 		 * without racing with truncate.
 		 */
 		VM_BUG_ON_PAGE(!PageLocked(page), page);
-		VM_BUG_ON_PAGE(!PageUptodate(page), page);
+
+		/* make sure the page is up to date */
+		if (unlikely(!PageUptodate(page))) {
+			result = SCAN_FAIL;
+			goto out_unlock;
+		}
 
 		/*
 		 * If file was truncated then extended, or hole-punched, before
@@ -1642,6 +1637,16 @@ static void collapse_file(struct mm_struct *mm,
 			goto out_unlock;
 		}
 
+		if (!is_shmem && PageDirty(page)) {
+			/*
+			 * khugepaged only works on read-only fd, so this
+			 * page is dirty because it hasn't been flushed
+			 * since first write.
+			 */
+			result = SCAN_FAIL;
+			goto out_unlock;
+		}
+
 		if (isolate_lru_page(page)) {
 			result = SCAN_DEL_PAGE_LRU;
 			goto out_unlock;
diff --git a/mm/madvise.c b/mm/madvise.c
index 2be9f3fdb05e..94c343b4c968 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -363,8 +363,12 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd,
 		ClearPageReferenced(page);
 		test_and_clear_page_young(page);
 		if (pageout) {
-			if (!isolate_lru_page(page))
-				list_add(&page->lru, &page_list);
+			if (!isolate_lru_page(page)) {
+				if (PageUnevictable(page))
+					putback_lru_page(page);
+				else
+					list_add(&page->lru, &page_list);
+			}
 		} else
 			deactivate_page(page);
 huge_unlock:
@@ -441,8 +445,12 @@ regular_page:
 		ClearPageReferenced(page);
 		test_and_clear_page_young(page);
 		if (pageout) {
-			if (!isolate_lru_page(page))
-				list_add(&page->lru, &page_list);
+			if (!isolate_lru_page(page)) {
+				if (PageUnevictable(page))
+					putback_lru_page(page);
+				else
+					list_add(&page->lru, &page_list);
+			}
 		} else
 			deactivate_page(page);
 	}
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 363106578876..46ad252e6d6a 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -484,7 +484,7 @@ ino_t page_cgroup_ino(struct page *page)
 	unsigned long ino = 0;
 
 	rcu_read_lock();
-	if (PageHead(page) && PageSlab(page))
+	if (PageSlab(page) && !PageTail(page))
 		memcg = memcg_from_slab_page(page);
 	else
 		memcg = READ_ONCE(page->mem_cgroup);
@@ -960,7 +960,7 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm)
 			if (unlikely(!memcg))
 				memcg = root_mem_cgroup;
 		}
-	} while (!css_tryget_online(&memcg->css));
+	} while (!css_tryget(&memcg->css));
 	rcu_read_unlock();
 	return memcg;
 }
@@ -2535,6 +2535,15 @@ retry:
 	}
 
 	/*
+	 * Memcg doesn't have a dedicated reserve for atomic
+	 * allocations. But like the global atomic pool, we need to
+	 * put the burden of reclaim on regular allocation requests
+	 * and let these go through as privileged allocations.
+	 */
+	if (gfp_mask & __GFP_ATOMIC)
+		goto force;
+
+	/*
 	 * Unlike in global OOM situations, memcg is not in a physical
 	 * memory shortage.  Allow dying and OOM-killed tasks to
 	 * bypass the last charges so that they can exit quickly and
@@ -5014,12 +5023,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	int node;
 
-	/*
-	 * Flush percpu vmstats and vmevents to guarantee the value correctness
-	 * on parent's and all ancestor levels.
-	 */
-	memcg_flush_percpu_vmstats(memcg, false);
-	memcg_flush_percpu_vmevents(memcg);
 	for_each_node(node)
 		free_mem_cgroup_per_node_info(memcg, node);
 	free_percpu(memcg->vmstats_percpu);
@@ -5030,6 +5033,12 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg)
 static void mem_cgroup_free(struct mem_cgroup *memcg)
 {
 	memcg_wb_domain_exit(memcg);
+	/*
+	 * Flush percpu vmstats and vmevents to guarantee the value correctness
+	 * on parent's and all ancestor levels.
+	 */
+	memcg_flush_percpu_vmstats(memcg, false);
+	memcg_flush_percpu_vmevents(memcg);
 	__mem_cgroup_free(memcg);
 }
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index df570e5c71cc..3b62a9ff8ea0 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -447,6 +447,14 @@ static void update_pgdat_span(struct pglist_data *pgdat)
 					     zone->spanned_pages;
 
 		/* No need to lock the zones, they can't change. */
+		if (!zone->spanned_pages)
+			continue;
+		if (!node_end_pfn) {
+			node_start_pfn = zone->zone_start_pfn;
+			node_end_pfn = zone_end_pfn;
+			continue;
+		}
+
 		if (zone_end_pfn > node_end_pfn)
 			node_end_pfn = zone_end_pfn;
 		if (zone->zone_start_pfn < node_start_pfn)
@@ -1638,6 +1646,18 @@ static int check_cpu_on_node(pg_data_t *pgdat)
 	return 0;
 }
 
+static int check_no_memblock_for_node_cb(struct memory_block *mem, void *arg)
+{
+	int nid = *(int *)arg;
+
+	/*
+	 * If a memory block belongs to multiple nodes, the stored nid is not
+	 * reliable. However, such blocks are always online (e.g., cannot get
+	 * offlined) and, therefore, are still spanned by the node.
+	 */
+	return mem->nid == nid ? -EEXIST : 0;
+}
+
 /**
  * try_offline_node
  * @nid: the node ID
@@ -1650,25 +1670,24 @@ static int check_cpu_on_node(pg_data_t *pgdat)
 void try_offline_node(int nid)
 {
 	pg_data_t *pgdat = NODE_DATA(nid);
-	unsigned long start_pfn = pgdat->node_start_pfn;
-	unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
-	unsigned long pfn;
-
-	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
-		unsigned long section_nr = pfn_to_section_nr(pfn);
-
-		if (!present_section_nr(section_nr))
-			continue;
+	int rc;
 
-		if (pfn_to_nid(pfn) != nid)
-			continue;
+	/*
+	 * If the node still spans pages (especially ZONE_DEVICE), don't
+	 * offline it. A node spans memory after move_pfn_range_to_zone(),
+	 * e.g., after the memory block was onlined.
+	 */
+	if (pgdat->node_spanned_pages)
+		return;
 
-		/*
-		 * some memory sections of this node are not removed, and we
-		 * can't offline node now.
-		 */
+	/*
+	 * Especially offline memory blocks might not be spanned by the
+	 * node. They will get spanned by the node once they get onlined.
+	 * However, they link to the node in sysfs and can get onlined later.
+	 */
+	rc = for_each_memory_block(&nid, check_no_memblock_for_node_cb);
+	if (rc)
 		return;
-	}
 
 	if (check_cpu_on_node(pgdat))
 		return;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 4ae967bcf954..e08c94170ae4 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -672,7 +672,9 @@ static const struct mm_walk_ops queue_pages_walk_ops = {
  * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were
  *     specified.
  * 0 - queue pages successfully or no misplaced page.
- * -EIO - there is misplaced page and only MPOL_MF_STRICT was specified.
+ * errno - i.e. misplaced pages with MPOL_MF_STRICT specified (-EIO) or
+ *         memory range specified by nodemask and maxnode points outside
+ *         your accessible address space (-EFAULT)
  */
 static int
 queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
@@ -1286,7 +1288,7 @@ static long do_mbind(unsigned long start, unsigned long len,
 			  flags | MPOL_MF_INVERT, &pagelist);
 
 	if (ret < 0) {
-		err = -EIO;
+		err = ret;
 		goto up_out;
 	}
 
@@ -1305,10 +1307,12 @@ static long do_mbind(unsigned long start, unsigned long len,
 
 		if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT)))
 			err = -EIO;
-	} else
-		putback_movable_pages(&pagelist);
-
+	} else {
 up_out:
+		if (!list_empty(&pagelist))
+			putback_movable_pages(&pagelist);
+	}
+
 	up_write(&mm->mmap_sem);
 mpol_out:
 	mpol_put(new);
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 7fde88695f35..9a889e456168 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -180,7 +180,7 @@ int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range)
 					mn->ops->invalidate_range_start, _ret,
 					!mmu_notifier_range_blockable(range) ? "non-" : "");
 				WARN_ON(mmu_notifier_range_blockable(range) ||
-					ret != -EAGAIN);
+					_ret != -EAGAIN);
 				ret = _ret;
 			}
 		}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ecc3dbad606b..f391c0c4ed1d 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1948,6 +1948,14 @@ void __init page_alloc_init_late(void)
 	wait_for_completion(&pgdat_init_all_done_comp);
 
 	/*
+	 * The number of managed pages has changed due to the initialisation
+	 * so the pcpu batch and high limits needs to be updated or the limits
+	 * will be artificially small.
+	 */
+	for_each_populated_zone(zone)
+		zone_pcp_update(zone);
+
+	/*
 	 * We initialized the rest of the deferred pages.  Permanently disable
 	 * on-demand struct page initialization.
 	 */
@@ -3720,10 +3728,6 @@ try_this_zone:
 static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask)
 {
 	unsigned int filter = SHOW_MEM_FILTER_NODES;
-	static DEFINE_RATELIMIT_STATE(show_mem_rs, HZ, 1);
-
-	if (!__ratelimit(&show_mem_rs))
-		return;
 
 	/*
 	 * This documents exceptions given to allocations in certain
@@ -3744,8 +3748,7 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...)
 {
 	struct va_format vaf;
 	va_list args;
-	static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL,
-				      DEFAULT_RATELIMIT_BURST);
+	static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1);
 
 	if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs))
 		return;
@@ -8514,7 +8517,6 @@ void free_contig_range(unsigned long pfn, unsigned int nr_pages)
 	WARN(count != 0, "%d pages are still in use!\n", count);
 }
 
-#ifdef CONFIG_MEMORY_HOTPLUG
 /*
  * The zone indicated has a new number of managed_pages; batch sizes and percpu
  * page high values need to be recalulated.
@@ -8528,7 +8530,6 @@ void __meminit zone_pcp_update(struct zone *zone)
 				per_cpu_ptr(zone->pageset, cpu));
 	mutex_unlock(&pcp_batch_high_lock);
 }
-#endif
 
 void zone_pcp_reset(struct zone *zone)
 {
diff --git a/mm/page_io.c b/mm/page_io.c
index 24ee600f9131..60a66a58b9bf 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -73,6 +73,7 @@ static void swap_slot_free_notify(struct page *page)
 {
 	struct swap_info_struct *sis;
 	struct gendisk *disk;
+	swp_entry_t entry;
 
 	/*
 	 * There is no guarantee that the page is in swap cache - the software
@@ -104,11 +105,10 @@ static void swap_slot_free_notify(struct page *page)
 	 * we again wish to reclaim it.
 	 */
 	disk = sis->bdev->bd_disk;
-	if (disk->fops->swap_slot_free_notify) {
-		swp_entry_t entry;
+	entry.val = page_private(page);
+	if (disk->fops->swap_slot_free_notify && __swap_count(entry) == 1) {
 		unsigned long offset;
 
-		entry.val = page_private(page);
 		offset = swp_offset(entry);
 
 		SetPageDirty(page);
diff --git a/mm/slab.h b/mm/slab.h
index 68e455f2b698..b2b01694dc43 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -323,8 +323,8 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s)
  * Expects a pointer to a slab page. Please note, that PageSlab() check
  * isn't sufficient, as it returns true also for tail compound slab pages,
  * which do not have slab_cache pointer set.
- * So this function assumes that the page can pass PageHead() and PageSlab()
- * checks.
+ * So this function assumes that the page can pass PageSlab() && !PageTail()
+ * check.
  *
  * The kmem_cache can be reparented asynchronously. The caller must ensure
  * the memcg lifetime, e.g. by taking rcu_read_lock() or cgroup_mutex.
diff --git a/mm/slub.c b/mm/slub.c
index b25c807a111f..e72e802fc569 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1433,12 +1433,15 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s,
 	void *old_tail = *tail ? *tail : *head;
 	int rsize;
 
-	if (slab_want_init_on_free(s)) {
-		void *p = NULL;
+	/* Head and tail of the reconstructed freelist */
+	*head = NULL;
+	*tail = NULL;
 
-		do {
-			object = next;
-			next = get_freepointer(s, object);
+	do {
+		object = next;
+		next = get_freepointer(s, object);
+
+		if (slab_want_init_on_free(s)) {
 			/*
 			 * Clear the object and the metadata, but don't touch
 			 * the redzone.
@@ -1448,29 +1451,8 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s,
 							   : 0;
 			memset((char *)object + s->inuse, 0,
 			       s->size - s->inuse - rsize);
-			set_freepointer(s, object, p);
-			p = object;
-		} while (object != old_tail);
-	}
-
-/*
- * Compiler cannot detect this function can be removed if slab_free_hook()
- * evaluates to nothing.  Thus, catch all relevant config debug options here.
- */
-#if defined(CONFIG_LOCKDEP)	||		\
-	defined(CONFIG_DEBUG_KMEMLEAK) ||	\
-	defined(CONFIG_DEBUG_OBJECTS_FREE) ||	\
-	defined(CONFIG_KASAN)
 
-	next = *head;
-
-	/* Head and tail of the reconstructed freelist */
-	*head = NULL;
-	*tail = NULL;
-
-	do {
-		object = next;
-		next = get_freepointer(s, object);
+		}
 		/* If object's reuse doesn't have to be delayed */
 		if (!slab_free_hook(s, object)) {
 			/* Move object to the new freelist */
@@ -1485,9 +1467,6 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s,
 		*tail = NULL;
 
 	return *head != NULL;
-#else
-	return true;
-#endif
 }
 
 static void *setup_object(struct kmem_cache *s, struct page *page,
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 6afc892a148a..a8222041bd44 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1383,12 +1383,29 @@ static void pagetypeinfo_showfree_print(struct seq_file *m,
 			unsigned long freecount = 0;
 			struct free_area *area;
 			struct list_head *curr;
+			bool overflow = false;
 
 			area = &(zone->free_area[order]);
 
-			list_for_each(curr, &area->free_list[mtype])
-				freecount++;
-			seq_printf(m, "%6lu ", freecount);
+			list_for_each(curr, &area->free_list[mtype]) {
+				/*
+				 * Cap the free_list iteration because it might
+				 * be really large and we are under a spinlock
+				 * so a long time spent here could trigger a
+				 * hard lockup detector. Anyway this is a
+				 * debugging tool so knowing there is a handful
+				 * of pages of this order should be more than
+				 * sufficient.
+				 */
+				if (++freecount >= 100000) {
+					overflow = true;
+					break;
+				}
+			}
+			seq_printf(m, "%s%6lu ", overflow ? ">" : "", freecount);
+			spin_unlock_irq(&zone->lock);
+			cond_resched();
+			spin_lock_irq(&zone->lock);
 		}
 		seq_putc(m, '\n');
 	}
@@ -1972,7 +1989,7 @@ void __init init_mm_internals(void)
 #endif
 #ifdef CONFIG_PROC_FS
 	proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op);
-	proc_create_seq("pagetypeinfo", 0444, NULL, &pagetypeinfo_op);
+	proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op);
 	proc_create_seq("vmstat", 0444, NULL, &vmstat_op);
 	proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op);
 #endif