Merge branch 'akpm' (patches from Andrew)

Merge yet more updates from Andrew Morton:

 - the rest of ocfs2

 - various hotfixes, mainly MM

 - quite a bit of misc stuff - drivers, fork, exec, signals, etc.

 - printk updates

 - firmware

 - checkpatch

 - nilfs2

 - more kexec stuff than usual

 - rapidio updates

 - w1 things

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (111 commits)
  ipc: delete "nr_ipc_ns"
  kcov: allow more fine-grained coverage instrumentation
  init/Kconfig: add clarification for out-of-tree modules
  config: add android config fragments
  init/Kconfig: ban CONFIG_LOCALVERSION_AUTO with allmodconfig
  relay: add global mode support for buffer-only channels
  init: allow blacklisting of module_init functions
  w1:omap_hdq: fix regression
  w1: add helper macro module_w1_family
  w1: remove need for ida and use PLATFORM_DEVID_AUTO
  rapidio/switches: add driver for IDT gen3 switches
  powerpc/fsl_rio: apply changes for RIO spec rev 3
  rapidio: modify for rev.3 specification changes
  rapidio: change inbound window size type to u64
  rapidio/idt_gen2: fix locking warning
  rapidio: fix error handling in mbox request/release functions
  rapidio/tsi721_dma: advance queue processing from transfer submit call
  rapidio/tsi721: add messaging mbox selector parameter
  rapidio/tsi721: add PCIe MRRS override parameter
  rapidio/tsi721_dma: add channel mask and queue size parameters
  ...

14 files changed, 124 insertions, 103 deletions

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f904246a8fd5..ef968306fd5b 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2216,6 +2216,10 @@ static unsigned long set_max_huge_pages(struct hstate *h, unsigned long count,
 		 * and reducing the surplus.
 		 */
 		spin_unlock(&hugetlb_lock);
+
+		/* yield cpu to avoid soft lockup */
+		cond_resched();
+
 		if (hstate_is_gigantic(h))
 			ret = alloc_fresh_gigantic_page(h, nodes_allowed);
 		else
@@ -4306,7 +4310,7 @@ pte_t *huge_pte_alloc(struct mm_struct *mm,
 				pte = (pte_t *)pmd_alloc(mm, pud, addr);
 		}
 	}
-	BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte));
+	BUG_ON(pte && pte_present(*pte) && !pte_huge(*pte));
 
 	return pte;
 }
diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c
index b6f99e81bfeb..88af13c00d3c 100644
--- a/mm/kasan/kasan.c
+++ b/mm/kasan/kasan.c
@@ -442,11 +442,6 @@ void kasan_poison_object_data(struct kmem_cache *cache, void *object)
 	kasan_poison_shadow(object,
 			round_up(cache->object_size, KASAN_SHADOW_SCALE_SIZE),
 			KASAN_KMALLOC_REDZONE);
-	if (cache->flags & SLAB_KASAN) {
-		struct kasan_alloc_meta *alloc_info =
-			get_alloc_info(cache, object);
-		alloc_info->state = KASAN_STATE_INIT;
-	}
 }
 
 static inline int in_irqentry_text(unsigned long ptr)
@@ -510,6 +505,17 @@ struct kasan_free_meta *get_free_info(struct kmem_cache *cache,
 	return (void *)object + cache->kasan_info.free_meta_offset;
 }
 
+void kasan_init_slab_obj(struct kmem_cache *cache, const void *object)
+{
+	struct kasan_alloc_meta *alloc_info;
+
+	if (!(cache->flags & SLAB_KASAN))
+		return;
+
+	alloc_info = get_alloc_info(cache, object);
+	__memset(alloc_info, 0, sizeof(*alloc_info));
+}
+
 void kasan_slab_alloc(struct kmem_cache *cache, void *object, gfp_t flags)
 {
 	kasan_kmalloc(cache, object, cache->object_size, flags);
@@ -529,34 +535,26 @@ static void kasan_poison_slab_free(struct kmem_cache *cache, void *object)
 
 bool kasan_slab_free(struct kmem_cache *cache, void *object)
 {
+	s8 shadow_byte;
+
 	/* RCU slabs could be legally used after free within the RCU period */
 	if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU))
 		return false;
 
-	if (likely(cache->flags & SLAB_KASAN)) {
-		struct kasan_alloc_meta *alloc_info;
-		struct kasan_free_meta *free_info;
+	shadow_byte = READ_ONCE(*(s8 *)kasan_mem_to_shadow(object));
+	if (shadow_byte < 0 || shadow_byte >= KASAN_SHADOW_SCALE_SIZE) {
+		kasan_report_double_free(cache, object, shadow_byte);
+		return true;
+	}
 
-		alloc_info = get_alloc_info(cache, object);
-		free_info = get_free_info(cache, object);
+	kasan_poison_slab_free(cache, object);
 
-		switch (alloc_info->state) {
-		case KASAN_STATE_ALLOC:
-			alloc_info->state = KASAN_STATE_QUARANTINE;
-			quarantine_put(free_info, cache);
-			set_track(&free_info->track, GFP_NOWAIT);
-			kasan_poison_slab_free(cache, object);
-			return true;
-		case KASAN_STATE_QUARANTINE:
-		case KASAN_STATE_FREE:
-			pr_err("Double free");
-			dump_stack();
-			break;
-		default:
-			break;
-		}
-	}
-	return false;
+	if (unlikely(!(cache->flags & SLAB_KASAN)))
+		return false;
+
+	set_track(&get_alloc_info(cache, object)->free_track, GFP_NOWAIT);
+	quarantine_put(get_free_info(cache, object), cache);
+	return true;
 }
 
 void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size,
@@ -565,7 +563,7 @@ void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size,
 	unsigned long redzone_start;
 	unsigned long redzone_end;
 
-	if (flags & __GFP_RECLAIM)
+	if (gfpflags_allow_blocking(flags))
 		quarantine_reduce();
 
 	if (unlikely(object == NULL))
@@ -579,14 +577,9 @@ void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size,
 	kasan_unpoison_shadow(object, size);
 	kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start,
 		KASAN_KMALLOC_REDZONE);
-	if (cache->flags & SLAB_KASAN) {
-		struct kasan_alloc_meta *alloc_info =
-			get_alloc_info(cache, object);
 
-		alloc_info->state = KASAN_STATE_ALLOC;
-		alloc_info->alloc_size = size;
-		set_track(&alloc_info->track, flags);
-	}
+	if (cache->flags & SLAB_KASAN)
+		set_track(&get_alloc_info(cache, object)->alloc_track, flags);
 }
 EXPORT_SYMBOL(kasan_kmalloc);
 
@@ -596,7 +589,7 @@ void kasan_kmalloc_large(const void *ptr, size_t size, gfp_t flags)
 	unsigned long redzone_start;
 	unsigned long redzone_end;
 
-	if (flags & __GFP_RECLAIM)
+	if (gfpflags_allow_blocking(flags))
 		quarantine_reduce();
 
 	if (unlikely(ptr == NULL))
diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
index 31972cdba433..e5c2181fee6f 100644
--- a/mm/kasan/kasan.h
+++ b/mm/kasan/kasan.h
@@ -59,13 +59,6 @@ struct kasan_global {
  * Structures to keep alloc and free tracks *
  */
 
-enum kasan_state {
-	KASAN_STATE_INIT,
-	KASAN_STATE_ALLOC,
-	KASAN_STATE_QUARANTINE,
-	KASAN_STATE_FREE
-};
-
 #define KASAN_STACK_DEPTH 64
 
 struct kasan_track {
@@ -74,9 +67,8 @@ struct kasan_track {
 };
 
 struct kasan_alloc_meta {
-	struct kasan_track track;
-	u32 state : 2;	/* enum kasan_state */
-	u32 alloc_size : 30;
+	struct kasan_track alloc_track;
+	struct kasan_track free_track;
 };
 
 struct qlist_node {
@@ -87,7 +79,6 @@ struct kasan_free_meta {
 	 * Otherwise it might be used for the allocator freelist.
 	 */
 	struct qlist_node quarantine_link;
-	struct kasan_track track;
 };
 
 struct kasan_alloc_meta *get_alloc_info(struct kmem_cache *cache,
@@ -108,6 +99,8 @@ static inline bool kasan_report_enabled(void)
 
 void kasan_report(unsigned long addr, size_t size,
 		bool is_write, unsigned long ip);
+void kasan_report_double_free(struct kmem_cache *cache, void *object,
+			s8 shadow);
 
 #if defined(CONFIG_SLAB) || defined(CONFIG_SLUB)
 void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache);
diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c
index 65793f150d1f..b6728a33a4ac 100644
--- a/mm/kasan/quarantine.c
+++ b/mm/kasan/quarantine.c
@@ -144,13 +144,15 @@ static void *qlink_to_object(struct qlist_node *qlink, struct kmem_cache *cache)
 static void qlink_free(struct qlist_node *qlink, struct kmem_cache *cache)
 {
 	void *object = qlink_to_object(qlink, cache);
-	struct kasan_alloc_meta *alloc_info = get_alloc_info(cache, object);
 	unsigned long flags;
 
-	local_irq_save(flags);
-	alloc_info->state = KASAN_STATE_FREE;
+	if (IS_ENABLED(CONFIG_SLAB))
+		local_irq_save(flags);
+
 	___cache_free(cache, object, _THIS_IP_);
-	local_irq_restore(flags);
+
+	if (IS_ENABLED(CONFIG_SLAB))
+		local_irq_restore(flags);
 }
 
 static void qlist_free_all(struct qlist_head *q, struct kmem_cache *cache)
@@ -196,7 +198,7 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache)
 
 void quarantine_reduce(void)
 {
-	size_t new_quarantine_size;
+	size_t new_quarantine_size, percpu_quarantines;
 	unsigned long flags;
 	struct qlist_head to_free = QLIST_INIT;
 	size_t size_to_free = 0;
@@ -214,7 +216,12 @@ void quarantine_reduce(void)
 	 */
 	new_quarantine_size = (READ_ONCE(totalram_pages) << PAGE_SHIFT) /
 		QUARANTINE_FRACTION;
-	new_quarantine_size -= QUARANTINE_PERCPU_SIZE * num_online_cpus();
+	percpu_quarantines = QUARANTINE_PERCPU_SIZE * num_online_cpus();
+	if (WARN_ONCE(new_quarantine_size < percpu_quarantines,
+		"Too little memory, disabling global KASAN quarantine.\n"))
+		new_quarantine_size = 0;
+	else
+		new_quarantine_size -= percpu_quarantines;
 	WRITE_ONCE(quarantine_size, new_quarantine_size);
 
 	last = global_quarantine.head;
diff --git a/mm/kasan/report.c b/mm/kasan/report.c
index 861b9776841a..24c1211fe9d5 100644
--- a/mm/kasan/report.c
+++ b/mm/kasan/report.c
@@ -116,6 +116,26 @@ static inline bool init_task_stack_addr(const void *addr)
 			sizeof(init_thread_union.stack));
 }
 
+static DEFINE_SPINLOCK(report_lock);
+
+static void kasan_start_report(unsigned long *flags)
+{
+	/*
+	 * Make sure we don't end up in loop.
+	 */
+	kasan_disable_current();
+	spin_lock_irqsave(&report_lock, *flags);
+	pr_err("==================================================================\n");
+}
+
+static void kasan_end_report(unsigned long *flags)
+{
+	pr_err("==================================================================\n");
+	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
+	spin_unlock_irqrestore(&report_lock, *flags);
+	kasan_enable_current();
+}
+
 static void print_track(struct kasan_track *track)
 {
 	pr_err("PID = %u\n", track->pid);
@@ -129,37 +149,33 @@ static void print_track(struct kasan_track *track)
 	}
 }
 
-static void kasan_object_err(struct kmem_cache *cache, struct page *page,
-				void *object, char *unused_reason)
+static void kasan_object_err(struct kmem_cache *cache, void *object)
 {
 	struct kasan_alloc_meta *alloc_info = get_alloc_info(cache, object);
-	struct kasan_free_meta *free_info;
 
 	dump_stack();
-	pr_err("Object at %p, in cache %s\n", object, cache->name);
+	pr_err("Object at %p, in cache %s size: %d\n", object, cache->name,
+		cache->object_size);
+
 	if (!(cache->flags & SLAB_KASAN))
 		return;
-	switch (alloc_info->state) {
-	case KASAN_STATE_INIT:
-		pr_err("Object not allocated yet\n");
-		break;
-	case KASAN_STATE_ALLOC:
-		pr_err("Object allocated with size %u bytes.\n",
-		       alloc_info->alloc_size);
-		pr_err("Allocation:\n");
-		print_track(&alloc_info->track);
-		break;
-	case KASAN_STATE_FREE:
-	case KASAN_STATE_QUARANTINE:
-		pr_err("Object freed, allocated with size %u bytes\n",
-		       alloc_info->alloc_size);
-		free_info = get_free_info(cache, object);
-		pr_err("Allocation:\n");
-		print_track(&alloc_info->track);
-		pr_err("Deallocation:\n");
-		print_track(&free_info->track);
-		break;
-	}
+
+	pr_err("Allocated:\n");
+	print_track(&alloc_info->alloc_track);
+	pr_err("Freed:\n");
+	print_track(&alloc_info->free_track);
+}
+
+void kasan_report_double_free(struct kmem_cache *cache, void *object,
+			s8 shadow)
+{
+	unsigned long flags;
+
+	kasan_start_report(&flags);
+	pr_err("BUG: Double free or freeing an invalid pointer\n");
+	pr_err("Unexpected shadow byte: 0x%hhX\n", shadow);
+	kasan_object_err(cache, object);
+	kasan_end_report(&flags);
 }
 
 static void print_address_description(struct kasan_access_info *info)
@@ -175,8 +191,7 @@ static void print_address_description(struct kasan_access_info *info)
 			struct kmem_cache *cache = page->slab_cache;
 			object = nearest_obj(cache, page,
 						(void *)info->access_addr);
-			kasan_object_err(cache, page, object,
-					"kasan: bad access detected");
+			kasan_object_err(cache, object);
 			return;
 		}
 		dump_page(page, "kasan: bad access detected");
@@ -241,19 +256,13 @@ static void print_shadow_for_address(const void *addr)
 	}
 }
 
-static DEFINE_SPINLOCK(report_lock);
-
 static void kasan_report_error(struct kasan_access_info *info)
 {
 	unsigned long flags;
 	const char *bug_type;
 
-	/*
-	 * Make sure we don't end up in loop.
-	 */
-	kasan_disable_current();
-	spin_lock_irqsave(&report_lock, flags);
-	pr_err("==================================================================\n");
+	kasan_start_report(&flags);
+
 	if (info->access_addr <
 			kasan_shadow_to_mem((void *)KASAN_SHADOW_START)) {
 		if ((unsigned long)info->access_addr < PAGE_SIZE)
@@ -274,10 +283,8 @@ static void kasan_report_error(struct kasan_access_info *info)
 		print_address_description(info);
 		print_shadow_for_address(info->first_bad_addr);
 	}
-	pr_err("==================================================================\n");
-	add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
-	spin_unlock_irqrestore(&report_lock, flags);
-	kasan_enable_current();
+
+	kasan_end_report(&flags);
 }
 
 void kasan_report(unsigned long addr, size_t size,
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index c265212bec8c..66beca1ad92f 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -2559,6 +2559,15 @@ unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order,
 		return 0;
 
 	mctz = soft_limit_tree_node(pgdat->node_id);
+
+	/*
+	 * Do not even bother to check the largest node if the root
+	 * is empty. Do it lockless to prevent lock bouncing. Races
+	 * are acceptable as soft limit is best effort anyway.
+	 */
+	if (RB_EMPTY_ROOT(&mctz->rb_root))
+		return 0;
+
 	/*
 	 * This loop can run a while, specially if mem_cgroup's continuously
 	 * keep exceeding their soft limit and putting the system under
diff --git a/mm/memory.c b/mm/memory.c
index 4425b6059339..83be99d9d8a1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2642,6 +2642,7 @@ int do_swap_page(struct fault_env *fe, pte_t orig_pte)
 	if (page == swapcache) {
 		do_page_add_anon_rmap(page, vma, fe->address, exclusive);
 		mem_cgroup_commit_charge(page, memcg, true, false);
+		activate_page(page);
 	} else { /* ksm created a completely new copy */
 		page_add_new_anon_rmap(page, vma, fe->address, false);
 		mem_cgroup_commit_charge(page, memcg, false, false);
@@ -3133,6 +3134,8 @@ static int do_fault_around(struct fault_env *fe, pgoff_t start_pgoff)
 
 	if (pmd_none(*fe->pmd)) {
 		fe->prealloc_pte = pte_alloc_one(fe->vma->vm_mm, fe->address);
+		if (!fe->prealloc_pte)
+			goto out;
 		smp_wmb(); /* See comment in __pte_alloc() */
 	}
 
diff --git a/mm/mmap.c b/mm/mmap.c
index d44bee96a5fe..ca9d91bca0d6 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2653,16 +2653,18 @@ static inline void verify_mm_writelocked(struct mm_struct *mm)
  *  anonymous maps.  eventually we may be able to do some
  *  brk-specific accounting here.
  */
-static int do_brk(unsigned long addr, unsigned long len)
+static int do_brk(unsigned long addr, unsigned long request)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma, *prev;
-	unsigned long flags;
+	unsigned long flags, len;
 	struct rb_node **rb_link, *rb_parent;
 	pgoff_t pgoff = addr >> PAGE_SHIFT;
 	int error;
 
-	len = PAGE_ALIGN(len);
+	len = PAGE_ALIGN(request);
+	if (len < request)
+		return -ENOMEM;
 	if (!len)
 		return 0;
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index ea759b935360..39a372a2a1d6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5276,7 +5276,7 @@ void __init setup_per_cpu_pageset(void)
 		setup_zone_pageset(zone);
 }
 
-static noinline __init_refok
+static noinline __ref
 int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages)
 {
 	int i;
@@ -5903,7 +5903,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat)
 	}
 }
 
-static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat)
+static void __ref alloc_node_mem_map(struct pglist_data *pgdat)
 {
 	unsigned long __maybe_unused start = 0;
 	unsigned long __maybe_unused offset = 0;
diff --git a/mm/slab.c b/mm/slab.c
index 09771ed3e693..261147ba156f 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1877,7 +1877,7 @@ static struct array_cache __percpu *alloc_kmem_cache_cpus(
 	return cpu_cache;
 }
 
-static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
+static int __ref setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
 {
 	if (slab_state >= FULL)
 		return enable_cpucache(cachep, gfp);
@@ -2604,9 +2604,11 @@ static void cache_init_objs(struct kmem_cache *cachep,
 	}
 
 	for (i = 0; i < cachep->num; i++) {
+		objp = index_to_obj(cachep, page, i);
+		kasan_init_slab_obj(cachep, objp);
+
 		/* constructor could break poison info */
 		if (DEBUG == 0 && cachep->ctor) {
-			objp = index_to_obj(cachep, page, i);
 			kasan_unpoison_object_data(cachep, objp);
 			cachep->ctor(objp);
 			kasan_poison_object_data(cachep, objp);
diff --git a/mm/slub.c b/mm/slub.c
index 74e7c8c30db8..26eb6a99540e 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -1384,6 +1384,7 @@ static void setup_object(struct kmem_cache *s, struct page *page,
 				void *object)
 {
 	setup_object_debug(s, page, object);
+	kasan_init_slab_obj(s, object);
 	if (unlikely(s->ctor)) {
 		kasan_unpoison_object_data(s, object);
 		s->ctor(object);
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 68885dcbaf40..574c67b663fe 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -36,7 +36,7 @@
  * Uses the main allocators if they are available, else bootmem.
  */
 
-static void * __init_refok __earlyonly_bootmem_alloc(int node,
+static void * __ref __earlyonly_bootmem_alloc(int node,
 				unsigned long size,
 				unsigned long align,
 				unsigned long goal)
diff --git a/mm/sparse.c b/mm/sparse.c
index 36d7bbb80e49..1e168bf2779a 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -59,7 +59,7 @@ static inline void set_section_nid(unsigned long section_nr, int nid)
 #endif
 
 #ifdef CONFIG_SPARSEMEM_EXTREME
-static struct mem_section noinline __init_refok *sparse_index_alloc(int nid)
+static noinline struct mem_section __ref *sparse_index_alloc(int nid)
 {
 	struct mem_section *section = NULL;
 	unsigned long array_size = SECTIONS_PER_ROOT *
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 650d26832569..374d95d04178 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2561,7 +2561,7 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc)
 			shrink_node_memcg(pgdat, memcg, sc, &lru_pages);
 			node_lru_pages += lru_pages;
 
-			if (!global_reclaim(sc))
+			if (memcg)
 				shrink_slab(sc->gfp_mask, pgdat->node_id,
 					    memcg, sc->nr_scanned - scanned,
 					    lru_pages);