Merge branch 'linus' into x86/asm, to pick up fixes

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

14 files changed, 65 insertions, 177 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index be0ee11fa0d9..86e3e0e74d20 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -187,7 +187,7 @@ config MEMORY_HOTPLUG
 	bool "Allow for memory hot-add"
 	depends on SPARSEMEM || X86_64_ACPI_NUMA
 	depends on ARCH_ENABLE_MEMORY_HOTPLUG
-	depends on !KASAN
+	depends on COMPILE_TEST || !KASAN
 
 config MEMORY_HOTPLUG_SPARSE
 	def_bool y
diff --git a/mm/filemap.c b/mm/filemap.c
index 849f459ad078..c7fe2f16503f 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -790,9 +790,7 @@ EXPORT_SYMBOL(__page_cache_alloc);
  */
 wait_queue_head_t *page_waitqueue(struct page *page)
 {
-	const struct zone *zone = page_zone(page);
-
-	return &zone->wait_table[hash_ptr(page, zone->wait_table_bits)];
+	return bit_waitqueue(page, 0);
 }
 EXPORT_SYMBOL(page_waitqueue);
 
diff --git a/mm/gup.c b/mm/gup.c
index 7aa113c2d373..ec4f82704b6f 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -526,7 +526,7 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags)
  * instead of __get_user_pages. __get_user_pages should be used only if
  * you need some special @gup_flags.
  */
-long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		unsigned long start, unsigned long nr_pages,
 		unsigned int gup_flags, struct page **pages,
 		struct vm_area_struct **vmas, int *nonblocking)
@@ -631,7 +631,6 @@ next_page:
 	} while (nr_pages);
 	return i;
 }
-EXPORT_SYMBOL(__get_user_pages);
 
 bool vma_permits_fault(struct vm_area_struct *vma, unsigned int fault_flags)
 {
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index a5e453cf05c4..e5355a5b423f 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1453,8 +1453,11 @@ static void kmemleak_scan(void)
 
 		read_lock(&tasklist_lock);
 		do_each_thread(g, p) {
-			scan_block(task_stack_page(p), task_stack_page(p) +
-				   THREAD_SIZE, NULL);
+			void *stack = try_get_task_stack(p);
+			if (stack) {
+				scan_block(stack, stack + THREAD_SIZE, NULL);
+				put_task_stack(p);
+			}
 		} while_each_thread(g, p);
 		read_unlock(&tasklist_lock);
 	}
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 1d05cb9d363d..234676e31edd 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -554,6 +554,8 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware,
 	err = memcg_init_list_lru(lru, memcg_aware);
 	if (err) {
 		kfree(lru->node);
+		/* Do this so a list_lru_destroy() doesn't crash: */
+		lru->node = NULL;
 		goto out;
 	}
 
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ae052b5e3315..0f870ba43942 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1917,6 +1917,15 @@ retry:
 		     current->flags & PF_EXITING))
 		goto force;
 
+	/*
+	 * Prevent unbounded recursion when reclaim operations need to
+	 * allocate memory. This might exceed the limits temporarily,
+	 * but we prefer facilitating memory reclaim and getting back
+	 * under the limit over triggering OOM kills in these cases.
+	 */
+	if (unlikely(current->flags & PF_MEMALLOC))
+		goto force;
+
 	if (unlikely(task_in_memcg_oom(current)))
 		goto nomem;
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 962927309b6e..cad4b9125695 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -268,7 +268,6 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
 	unsigned long i, pfn, end_pfn, nr_pages;
 	int node = pgdat->node_id;
 	struct page *page;
-	struct zone *zone;
 
 	nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
 	page = virt_to_page(pgdat);
@@ -276,19 +275,6 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
 	for (i = 0; i < nr_pages; i++, page++)
 		get_page_bootmem(node, page, NODE_INFO);
 
-	zone = &pgdat->node_zones[0];
-	for (; zone < pgdat->node_zones + MAX_NR_ZONES - 1; zone++) {
-		if (zone_is_initialized(zone)) {
-			nr_pages = zone->wait_table_hash_nr_entries
-				* sizeof(wait_queue_head_t);
-			nr_pages = PAGE_ALIGN(nr_pages) >> PAGE_SHIFT;
-			page = virt_to_page(zone->wait_table);
-
-			for (i = 0; i < nr_pages; i++, page++)
-				get_page_bootmem(node, page, NODE_INFO);
-		}
-	}
-
 	pfn = pgdat->node_start_pfn;
 	end_pfn = pgdat_end_pfn(pgdat);
 
@@ -2131,7 +2117,6 @@ void try_offline_node(int nid)
 	unsigned long start_pfn = pgdat->node_start_pfn;
 	unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
 	unsigned long pfn;
-	int i;
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
 		unsigned long section_nr = pfn_to_section_nr(pfn);
@@ -2158,20 +2143,6 @@ void try_offline_node(int nid)
 	 */
 	node_set_offline(nid);
 	unregister_one_node(nid);
-
-	/* free waittable in each zone */
-	for (i = 0; i < MAX_NR_ZONES; i++) {
-		struct zone *zone = pgdat->node_zones + i;
-
-		/*
-		 * wait_table may be allocated from boot memory,
-		 * here only free if it's allocated by vmalloc.
-		 */
-		if (is_vmalloc_addr(zone->wait_table)) {
-			vfree(zone->wait_table);
-			zone->wait_table = NULL;
-		}
-	}
 }
 EXPORT_SYMBOL(try_offline_node);
 
diff --git a/mm/mprotect.c b/mm/mprotect.c
index bcdbe62f3e6d..11936526b08b 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -25,7 +25,6 @@
 #include <linux/perf_event.h>
 #include <linux/pkeys.h>
 #include <linux/ksm.h>
-#include <linux/pkeys.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
diff --git a/mm/nommu.c b/mm/nommu.c
index db5fd1795298..8b8faaf2a9e9 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -109,7 +109,7 @@ unsigned int kobjsize(const void *objp)
 	return PAGE_SIZE << compound_order(page);
 }
 
-long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
+static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
 		      unsigned long start, unsigned long nr_pages,
 		      unsigned int foll_flags, struct page **pages,
 		      struct vm_area_struct **vmas, int *nonblocking)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 3f639739cab9..2dd614877de2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4224,7 +4224,7 @@ static void show_migration_types(unsigned char type)
 	}
 
 	*p = '\0';
-	printk("(%s) ", tmp);
+	printk(KERN_CONT "(%s) ", tmp);
 }
 
 /*
@@ -4335,7 +4335,8 @@ void show_free_areas(unsigned int filter)
 			free_pcp += per_cpu_ptr(zone->pageset, cpu)->pcp.count;
 
 		show_node(zone);
-		printk("%s"
+		printk(KERN_CONT
+			"%s"
 			" free:%lukB"
 			" min:%lukB"
 			" low:%lukB"
@@ -4382,8 +4383,8 @@ void show_free_areas(unsigned int filter)
 			K(zone_page_state(zone, NR_FREE_CMA_PAGES)));
 		printk("lowmem_reserve[]:");
 		for (i = 0; i < MAX_NR_ZONES; i++)
-			printk(" %ld", zone->lowmem_reserve[i]);
-		printk("\n");
+			printk(KERN_CONT " %ld", zone->lowmem_reserve[i]);
+		printk(KERN_CONT "\n");
 	}
 
 	for_each_populated_zone(zone) {
@@ -4394,7 +4395,7 @@ void show_free_areas(unsigned int filter)
 		if (skip_free_areas_node(filter, zone_to_nid(zone)))
 			continue;
 		show_node(zone);
-		printk("%s: ", zone->name);
+		printk(KERN_CONT "%s: ", zone->name);
 
 		spin_lock_irqsave(&zone->lock, flags);
 		for (order = 0; order < MAX_ORDER; order++) {
@@ -4412,11 +4413,12 @@ void show_free_areas(unsigned int filter)
 		}
 		spin_unlock_irqrestore(&zone->lock, flags);
 		for (order = 0; order < MAX_ORDER; order++) {
-			printk("%lu*%lukB ", nr[order], K(1UL) << order);
+			printk(KERN_CONT "%lu*%lukB ",
+			       nr[order], K(1UL) << order);
 			if (nr[order])
 				show_migration_types(types[order]);
 		}
-		printk("= %lukB\n", K(total));
+		printk(KERN_CONT "= %lukB\n", K(total));
 	}
 
 	hugetlb_show_meminfo();
@@ -4977,72 +4979,6 @@ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone)
 }
 
 /*
- * Helper functions to size the waitqueue hash table.
- * Essentially these want to choose hash table sizes sufficiently
- * large so that collisions trying to wait on pages are rare.
- * But in fact, the number of active page waitqueues on typical
- * systems is ridiculously low, less than 200. So this is even
- * conservative, even though it seems large.
- *
- * The constant PAGES_PER_WAITQUEUE specifies the ratio of pages to
- * waitqueues, i.e. the size of the waitq table given the number of pages.
- */
-#define PAGES_PER_WAITQUEUE	256
-
-#ifndef CONFIG_MEMORY_HOTPLUG
-static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
-{
-	unsigned long size = 1;
-
-	pages /= PAGES_PER_WAITQUEUE;
-
-	while (size < pages)
-		size <<= 1;
-
-	/*
-	 * Once we have dozens or even hundreds of threads sleeping
-	 * on IO we've got bigger problems than wait queue collision.
-	 * Limit the size of the wait table to a reasonable size.
-	 */
-	size = min(size, 4096UL);
-
-	return max(size, 4UL);
-}
-#else
-/*
- * A zone's size might be changed by hot-add, so it is not possible to determine
- * a suitable size for its wait_table.  So we use the maximum size now.
- *
- * The max wait table size = 4096 x sizeof(wait_queue_head_t).   ie:
- *
- *    i386 (preemption config)    : 4096 x 16 = 64Kbyte.
- *    ia64, x86-64 (no preemption): 4096 x 20 = 80Kbyte.
- *    ia64, x86-64 (preemption)   : 4096 x 24 = 96Kbyte.
- *
- * The maximum entries are prepared when a zone's memory is (512K + 256) pages
- * or more by the traditional way. (See above).  It equals:
- *
- *    i386, x86-64, powerpc(4K page size) : =  ( 2G + 1M)byte.
- *    ia64(16K page size)                 : =  ( 8G + 4M)byte.
- *    powerpc (64K page size)             : =  (32G +16M)byte.
- */
-static inline unsigned long wait_table_hash_nr_entries(unsigned long pages)
-{
-	return 4096UL;
-}
-#endif
-
-/*
- * This is an integer logarithm so that shifts can be used later
- * to extract the more random high bits from the multiplicative
- * hash function before the remainder is taken.
- */
-static inline unsigned long wait_table_bits(unsigned long size)
-{
-	return ffz(~size);
-}
-
-/*
  * Initially all pages are reserved - free ones are freed
  * up by free_all_bootmem() once the early boot process is
  * done. Non-atomic initialization, single-pass.
@@ -5304,49 +5240,6 @@ void __init setup_per_cpu_pageset(void)
 			alloc_percpu(struct per_cpu_nodestat);
 }
 
-static noinline __ref
-int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
-{
-	int i;
-	size_t alloc_size;
-
-	/*
-	 * The per-page waitqueue mechanism uses hashed waitqueues
-	 * per zone.
-	 */
-	zone->wait_table_hash_nr_entries =
-		 wait_table_hash_nr_entries(zone_size_pages);
-	zone->wait_table_bits =
-		wait_table_bits(zone->wait_table_hash_nr_entries);
-	alloc_size = zone->wait_table_hash_nr_entries
-					* sizeof(wait_queue_head_t);
-
-	if (!slab_is_available()) {
-		zone->wait_table = (wait_queue_head_t *)
-			memblock_virt_alloc_node_nopanic(
-				alloc_size, zone->zone_pgdat->node_id);
-	} else {
-		/*
-		 * This case means that a zone whose size was 0 gets new memory
-		 * via memory hot-add.
-		 * But it may be the case that a new node was hot-added.  In
-		 * this case vmalloc() will not be able to use this new node's
-		 * memory - this wait_table must be initialized to use this new
-		 * node itself as well.
-		 * To use this new node's memory, further consideration will be
-		 * necessary.
-		 */
-		zone->wait_table = vmalloc(alloc_size);
-	}
-	if (!zone->wait_table)
-		return -ENOMEM;
-
-	for (i = 0; i < zone->wait_table_hash_nr_entries; ++i)
-		init_waitqueue_head(zone->wait_table + i);
-
-	return 0;
-}
-
 static __meminit void zone_pcp_init(struct zone *zone)
 {
 	/*
@@ -5367,10 +5260,7 @@ int __meminit init_currently_empty_zone(struct zone *zone,
 					unsigned long size)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
-	int ret;
-	ret = zone_wait_table_init(zone, size);
-	if (ret)
-		return ret;
+
 	pgdat->nr_zones = zone_idx(zone) + 1;
 
 	zone->zone_start_pfn = zone_start_pfn;
@@ -5382,6 +5272,7 @@ int __meminit init_currently_empty_zone(struct zone *zone,
 			zone_start_pfn, (zone_start_pfn + size));
 
 	zone_init_free_lists(zone);
+	zone->initialized = 1;
 
 	return 0;
 }
diff --git a/mm/slab.c b/mm/slab.c
index 090fb26b3a39..0b0550ca85b4 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -233,6 +233,7 @@ static void kmem_cache_node_init(struct kmem_cache_node *parent)
 	spin_lock_init(&parent->list_lock);
 	parent->free_objects = 0;
 	parent->free_touched = 0;
+	parent->num_slabs = 0;
 }
 
 #define MAKE_LIST(cachep, listp, slab, nodeid)				\
@@ -966,7 +967,7 @@ static int setup_kmem_cache_node(struct kmem_cache *cachep,
 	 * guaranteed to be valid until irq is re-enabled, because it will be
 	 * freed after synchronize_sched().
 	 */
-	if (force_change)
+	if (old_shared && force_change)
 		synchronize_sched();
 
 fail:
@@ -1382,24 +1383,27 @@ slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
 	for_each_kmem_cache_node(cachep, node, n) {
 		unsigned long active_objs = 0, num_objs = 0, free_objects = 0;
 		unsigned long active_slabs = 0, num_slabs = 0;
+		unsigned long num_slabs_partial = 0, num_slabs_free = 0;
+		unsigned long num_slabs_full;
 
 		spin_lock_irqsave(&n->list_lock, flags);
-		list_for_each_entry(page, &n->slabs_full, lru) {
-			active_objs += cachep->num;
-			active_slabs++;
-		}
+		num_slabs = n->num_slabs;
 		list_for_each_entry(page, &n->slabs_partial, lru) {
 			active_objs += page->active;
-			active_slabs++;
+			num_slabs_partial++;
 		}
 		list_for_each_entry(page, &n->slabs_free, lru)
-			num_slabs++;
+			num_slabs_free++;
 
 		free_objects += n->free_objects;
 		spin_unlock_irqrestore(&n->list_lock, flags);
 
-		num_slabs += active_slabs;
 		num_objs = num_slabs * cachep->num;
+		active_slabs = num_slabs - num_slabs_free;
+		num_slabs_full = num_slabs -
+			(num_slabs_partial + num_slabs_free);
+		active_objs += (num_slabs_full * cachep->num);
+
 		pr_warn("  node %d: slabs: %ld/%ld, objs: %ld/%ld, free: %ld\n",
 			node, active_slabs, num_slabs, active_objs, num_objs,
 			free_objects);
@@ -2314,6 +2318,7 @@ static int drain_freelist(struct kmem_cache *cache,
 
 		page = list_entry(p, struct page, lru);
 		list_del(&page->lru);
+		n->num_slabs--;
 		/*
 		 * Safe to drop the lock. The slab is no longer linked
 		 * to the cache.
@@ -2752,6 +2757,8 @@ static void cache_grow_end(struct kmem_cache *cachep, struct page *page)
 		list_add_tail(&page->lru, &(n->slabs_free));
 	else
 		fixup_slab_list(cachep, n, page, &list);
+
+	n->num_slabs++;
 	STATS_INC_GROWN(cachep);
 	n->free_objects += cachep->num - page->active;
 	spin_unlock(&n->list_lock);
@@ -3443,6 +3450,7 @@ static void free_block(struct kmem_cache *cachep, void **objpp,
 
 		page = list_last_entry(&n->slabs_free, struct page, lru);
 		list_move(&page->lru, list);
+		n->num_slabs--;
 	}
 }
 
@@ -4099,6 +4107,8 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
 	unsigned long num_objs;
 	unsigned long active_slabs = 0;
 	unsigned long num_slabs, free_objects = 0, shared_avail = 0;
+	unsigned long num_slabs_partial = 0, num_slabs_free = 0;
+	unsigned long num_slabs_full = 0;
 	const char *name;
 	char *error = NULL;
 	int node;
@@ -4111,33 +4121,34 @@ void get_slabinfo(struct kmem_cache *cachep, struct slabinfo *sinfo)
 		check_irq_on();
 		spin_lock_irq(&n->list_lock);
 
-		list_for_each_entry(page, &n->slabs_full, lru) {
-			if (page->active != cachep->num && !error)
-				error = "slabs_full accounting error";
-			active_objs += cachep->num;
-			active_slabs++;
-		}
+		num_slabs += n->num_slabs;
+
 		list_for_each_entry(page, &n->slabs_partial, lru) {
 			if (page->active == cachep->num && !error)
 				error = "slabs_partial accounting error";
 			if (!page->active && !error)
 				error = "slabs_partial accounting error";
 			active_objs += page->active;
-			active_slabs++;
+			num_slabs_partial++;
 		}
+
 		list_for_each_entry(page, &n->slabs_free, lru) {
 			if (page->active && !error)
 				error = "slabs_free accounting error";
-			num_slabs++;
+			num_slabs_free++;
 		}
+
 		free_objects += n->free_objects;
 		if (n->shared)
 			shared_avail += n->shared->avail;
 
 		spin_unlock_irq(&n->list_lock);
 	}
-	num_slabs += active_slabs;
 	num_objs = num_slabs * cachep->num;
+	active_slabs = num_slabs - num_slabs_free;
+	num_slabs_full = num_slabs - (num_slabs_partial + num_slabs_free);
+	active_objs += (num_slabs_full * cachep->num);
+
 	if (num_objs - active_objs != free_objects && !error)
 		error = "free_objects accounting error";
 
diff --git a/mm/slab.h b/mm/slab.h
index 9653f2e2591a..bc05fdc3edce 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -432,6 +432,7 @@ struct kmem_cache_node {
 	struct list_head slabs_partial;	/* partial list first, better asm code */
 	struct list_head slabs_full;
 	struct list_head slabs_free;
+	unsigned long num_slabs;
 	unsigned long free_objects;
 	unsigned int free_limit;
 	unsigned int colour_next;	/* Per-node cache coloring */
diff --git a/mm/util.c b/mm/util.c
index 952cbe7ad7b7..1a41553db866 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -230,8 +230,10 @@ 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 */
-int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t)
+int vma_is_stack_for_current(struct vm_area_struct *vma)
 {
+	struct task_struct * __maybe_unused t = current;
+
 	return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
 }
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 744f926af442..76fda2268148 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3043,7 +3043,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
 					    sc.gfp_mask,
 					    sc.reclaim_idx);
 
+	current->flags |= PF_MEMALLOC;
 	nr_reclaimed = do_try_to_free_pages(zonelist, &sc);
+	current->flags &= ~PF_MEMALLOC;
 
 	trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed);