Merge branch 'for-4.15/dax' into libnvdimm-for-next

18 files changed, 135 insertions, 46 deletions

diff --git a/mm/compaction.c b/mm/compaction.c
index fb548e4c7bd4..03d31a875341 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1999,17 +1999,14 @@ void wakeup_kcompactd(pg_data_t *pgdat, int order, int classzone_idx)
 	if (pgdat->kcompactd_max_order < order)
 		pgdat->kcompactd_max_order = order;
 
-	/*
-	 * Pairs with implicit barrier in wait_event_freezable()
-	 * such that wakeups are not missed in the lockless
-	 * waitqueue_active() call.
-	 */
-	smp_acquire__after_ctrl_dep();
-
 	if (pgdat->kcompactd_classzone_idx > classzone_idx)
 		pgdat->kcompactd_classzone_idx = classzone_idx;
 
-	if (!waitqueue_active(&pgdat->kcompactd_wait))
+	/*
+	 * Pairs with implicit barrier in wait_event_freezable()
+	 * such that wakeups are not missed.
+	 */
+	if (!wq_has_sleeper(&pgdat->kcompactd_wait))
 		return;
 
 	if (!kcompactd_node_suitable(pgdat))
diff --git a/mm/filemap.c b/mm/filemap.c
index 870971e20967..594d73fef8b4 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -620,6 +620,14 @@ int file_check_and_advance_wb_err(struct file *file)
 		trace_file_check_and_advance_wb_err(file, old);
 		spin_unlock(&file->f_lock);
 	}
+
+	/*
+	 * We're mostly using this function as a drop in replacement for
+	 * filemap_check_errors. Clear AS_EIO/AS_ENOSPC to emulate the effect
+	 * that the legacy code would have had on these flags.
+	 */
+	clear_bit(AS_EIO, &mapping->flags);
+	clear_bit(AS_ENOSPC, &mapping->flags);
 	return err;
 }
 EXPORT_SYMBOL(file_check_and_advance_wb_err);
@@ -2926,9 +2934,15 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from)
 	 * we're writing.  Either one is a pretty crazy thing to do,
 	 * so we don't support it 100%.  If this invalidation
 	 * fails, tough, the write still worked...
+	 *
+	 * Most of the time we do not need this since dio_complete() will do
+	 * the invalidation for us. However there are some file systems that
+	 * do not end up with dio_complete() being called, so let's not break
+	 * them by removing it completely
 	 */
-	invalidate_inode_pages2_range(mapping,
-				pos >> PAGE_SHIFT, end);
+	if (mapping->nrpages)
+		invalidate_inode_pages2_range(mapping,
+					pos >> PAGE_SHIFT, end);
 
 	if (written > 0) {
 		pos += written;
diff --git a/mm/ksm.c b/mm/ksm.c
index 15dd7415f7b3..6cb60f46cce5 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -1990,6 +1990,7 @@ static void stable_tree_append(struct rmap_item *rmap_item,
  */
 static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
 {
+	struct mm_struct *mm = rmap_item->mm;
 	struct rmap_item *tree_rmap_item;
 	struct page *tree_page = NULL;
 	struct stable_node *stable_node;
@@ -2062,9 +2063,11 @@ static void cmp_and_merge_page(struct page *page, struct rmap_item *rmap_item)
 	if (ksm_use_zero_pages && (checksum == zero_checksum)) {
 		struct vm_area_struct *vma;
 
-		vma = find_mergeable_vma(rmap_item->mm, rmap_item->address);
+		down_read(&mm->mmap_sem);
+		vma = find_mergeable_vma(mm, rmap_item->address);
 		err = try_to_merge_one_page(vma, page,
 					    ZERO_PAGE(rmap_item->address));
+		up_read(&mm->mmap_sem);
 		/*
 		 * In case of failure, the page was not really empty, so we
 		 * need to continue. Otherwise we're done.
diff --git a/mm/list_lru.c b/mm/list_lru.c
index 7a40fa2be858..f141f0c80ff3 100644
--- a/mm/list_lru.c
+++ b/mm/list_lru.c
@@ -325,12 +325,12 @@ static int memcg_init_list_lru_node(struct list_lru_node *nlru)
 {
 	int size = memcg_nr_cache_ids;
 
-	nlru->memcg_lrus = kmalloc(size * sizeof(void *), GFP_KERNEL);
+	nlru->memcg_lrus = kvmalloc(size * sizeof(void *), GFP_KERNEL);
 	if (!nlru->memcg_lrus)
 		return -ENOMEM;
 
 	if (__memcg_init_list_lru_node(nlru->memcg_lrus, 0, size)) {
-		kfree(nlru->memcg_lrus);
+		kvfree(nlru->memcg_lrus);
 		return -ENOMEM;
 	}
 
@@ -340,7 +340,7 @@ static int memcg_init_list_lru_node(struct list_lru_node *nlru)
 static void memcg_destroy_list_lru_node(struct list_lru_node *nlru)
 {
 	__memcg_destroy_list_lru_node(nlru->memcg_lrus, 0, memcg_nr_cache_ids);
-	kfree(nlru->memcg_lrus);
+	kvfree(nlru->memcg_lrus);
 }
 
 static int memcg_update_list_lru_node(struct list_lru_node *nlru,
@@ -351,12 +351,12 @@ static int memcg_update_list_lru_node(struct list_lru_node *nlru,
 	BUG_ON(old_size > new_size);
 
 	old = nlru->memcg_lrus;
-	new = kmalloc(new_size * sizeof(void *), GFP_KERNEL);
+	new = kvmalloc(new_size * sizeof(void *), GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
 	if (__memcg_init_list_lru_node(new, old_size, new_size)) {
-		kfree(new);
+		kvfree(new);
 		return -ENOMEM;
 	}
 
@@ -373,7 +373,7 @@ static int memcg_update_list_lru_node(struct list_lru_node *nlru,
 	nlru->memcg_lrus = new;
 	spin_unlock_irq(&nlru->lock);
 
-	kfree(old);
+	kvfree(old);
 	return 0;
 }
 
diff --git a/mm/madvise.c b/mm/madvise.c
index 21261ff0466f..25bade36e9ca 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -625,18 +625,26 @@ static int madvise_inject_error(int behavior,
 {
 	struct page *page;
 	struct zone *zone;
+	unsigned int order;
 
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	for (; start < end; start += PAGE_SIZE <<
-				compound_order(compound_head(page))) {
+
+	for (; start < end; start += PAGE_SIZE << order) {
 		int ret;
 
 		ret = get_user_pages_fast(start, 1, 0, &page);
 		if (ret != 1)
 			return ret;
 
+		/*
+		 * When soft offlining hugepages, after migrating the page
+		 * we dissolve it, therefore in the second loop "page" will
+		 * no longer be a compound page, and order will be 0.
+		 */
+		order = compound_order(compound_head(page));
+
 		if (PageHWPoison(page)) {
 			put_page(page);
 			continue;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 15af3da5af02..d5f3a62887cf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -1777,6 +1777,10 @@ static void drain_local_stock(struct work_struct *dummy)
 	struct memcg_stock_pcp *stock;
 	unsigned long flags;
 
+	/*
+	 * The only protection from memory hotplug vs. drain_stock races is
+	 * that we always operate on local CPU stock here with IRQ disabled
+	 */
 	local_irq_save(flags);
 
 	stock = this_cpu_ptr(&memcg_stock);
@@ -1821,27 +1825,33 @@ static void drain_all_stock(struct mem_cgroup *root_memcg)
 	/* If someone's already draining, avoid adding running more workers. */
 	if (!mutex_trylock(&percpu_charge_mutex))
 		return;
-	/* Notify other cpus that system-wide "drain" is running */
-	get_online_cpus();
+	/*
+	 * Notify other cpus that system-wide "drain" is running
+	 * We do not care about races with the cpu hotplug because cpu down
+	 * as well as workers from this path always operate on the local
+	 * per-cpu data. CPU up doesn't touch memcg_stock at all.
+	 */
 	curcpu = get_cpu();
 	for_each_online_cpu(cpu) {
 		struct memcg_stock_pcp *stock = &per_cpu(memcg_stock, cpu);
 		struct mem_cgroup *memcg;
 
 		memcg = stock->cached;
-		if (!memcg || !stock->nr_pages)
+		if (!memcg || !stock->nr_pages || !css_tryget(&memcg->css))
 			continue;
-		if (!mem_cgroup_is_descendant(memcg, root_memcg))
+		if (!mem_cgroup_is_descendant(memcg, root_memcg)) {
+			css_put(&memcg->css);
 			continue;
+		}
 		if (!test_and_set_bit(FLUSHING_CACHED_CHARGE, &stock->flags)) {
 			if (cpu == curcpu)
 				drain_local_stock(&stock->work);
 			else
 				schedule_work_on(cpu, &stock->work);
 		}
+		css_put(&memcg->css);
 	}
 	put_cpu();
-	put_online_cpus();
 	mutex_unlock(&percpu_charge_mutex);
 }
 
@@ -5648,7 +5658,8 @@ static void uncharge_batch(const struct uncharge_gather *ug)
 static void uncharge_page(struct page *page, struct uncharge_gather *ug)
 {
 	VM_BUG_ON_PAGE(PageLRU(page), page);
-	VM_BUG_ON_PAGE(!PageHWPoison(page) && page_count(page), page);
+	VM_BUG_ON_PAGE(page_count(page) && !is_zone_device_page(page) &&
+			!PageHWPoison(page) , page);
 
 	if (!page->mem_cgroup)
 		return;
diff --git a/mm/memory.c b/mm/memory.c
index ec4e15494901..a728bed16c20 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -845,7 +845,7 @@ struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
 		 * vm_normal_page() so that we do not have to special case all
 		 * call site of vm_normal_page().
 		 */
-		if (likely(pfn < highest_memmap_pfn)) {
+		if (likely(pfn <= highest_memmap_pfn)) {
 			struct page *page = pfn_to_page(pfn);
 
 			if (is_device_public_page(page)) {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e882cb6da994..d4b5f29906b9 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -328,6 +328,7 @@ int __ref __add_pages(int nid, unsigned long phys_start_pfn,
 		if (err && (err != -EEXIST))
 			break;
 		err = 0;
+		cond_resched();
 	}
 	vmemmap_populate_print_last();
 out:
@@ -337,7 +338,7 @@ EXPORT_SYMBOL_GPL(__add_pages);
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
 /* find the smallest valid pfn in the range [start_pfn, end_pfn) */
-static int find_smallest_section_pfn(int nid, struct zone *zone,
+static unsigned long find_smallest_section_pfn(int nid, struct zone *zone,
 				     unsigned long start_pfn,
 				     unsigned long end_pfn)
 {
@@ -362,7 +363,7 @@ static int find_smallest_section_pfn(int nid, struct zone *zone,
 }
 
 /* find the biggest valid pfn in the range [start_pfn, end_pfn). */
-static int find_biggest_section_pfn(int nid, struct zone *zone,
+static unsigned long find_biggest_section_pfn(int nid, struct zone *zone,
 				    unsigned long start_pfn,
 				    unsigned long end_pfn)
 {
@@ -550,7 +551,7 @@ static int __remove_section(struct zone *zone, struct mem_section *ms,
 		return ret;
 
 	scn_nr = __section_nr(ms);
-	start_pfn = section_nr_to_pfn(scn_nr);
+	start_pfn = section_nr_to_pfn((unsigned long)scn_nr);
 	__remove_zone(zone, start_pfn);
 
 	sparse_remove_one_section(zone, ms, map_offset);
diff --git a/mm/mmap.c b/mm/mmap.c
index 680506faceae..924839fac0e6 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1387,9 +1387,24 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 
 	if (file) {
 		struct inode *inode = file_inode(file);
+		unsigned long flags_mask;
+
+		flags_mask = LEGACY_MAP_MASK | file->f_op->mmap_supported_flags;
 
 		switch (flags & MAP_TYPE) {
 		case MAP_SHARED:
+			/*
+			 * Force use of MAP_SHARED_VALIDATE with non-legacy
+			 * flags. E.g. MAP_SYNC is dangerous to use with
+			 * MAP_SHARED as you don't know which consistency model
+			 * you will get. We silently ignore unsupported flags
+			 * with MAP_SHARED to preserve backward compatibility.
+			 */
+			flags &= LEGACY_MAP_MASK;
+			/* fall through */
+		case MAP_SHARED_VALIDATE:
+			if (flags & ~flags_mask)
+				return -EOPNOTSUPP;
 			if ((prot&PROT_WRITE) && !(file->f_mode&FMODE_WRITE))
 				return -EACCES;
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index 99736e026712..dee0f75c3013 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -40,6 +40,7 @@
 #include <linux/ratelimit.h>
 #include <linux/kthread.h>
 #include <linux/init.h>
+#include <linux/mmu_notifier.h>
 
 #include <asm/tlb.h>
 #include "internal.h"
@@ -495,6 +496,21 @@ static bool __oom_reap_task_mm(struct task_struct *tsk, struct mm_struct *mm)
 	}
 
 	/*
+	 * If the mm has notifiers then we would need to invalidate them around
+	 * unmap_page_range and that is risky because notifiers can sleep and
+	 * what they do is basically undeterministic.  So let's have a short
+	 * sleep to give the oom victim some more time.
+	 * TODO: we really want to get rid of this ugly hack and make sure that
+	 * notifiers cannot block for unbounded amount of time and add
+	 * mmu_notifier_invalidate_range_{start,end} around unmap_page_range
+	 */
+	if (mm_has_notifiers(mm)) {
+		up_read(&mm->mmap_sem);
+		schedule_timeout_idle(HZ);
+		goto unlock_oom;
+	}
+
+	/*
 	 * MMF_OOM_SKIP is set by exit_mmap when the OOM reaper can't
 	 * work on the mm anymore. The check for MMF_OOM_SKIP must run
 	 * under mmap_sem for reading because it serializes against the
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c841af88836a..77e4d3c5c57b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1190,7 +1190,7 @@ static void __meminit __init_single_pfn(unsigned long pfn, unsigned long zone,
 }
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-static void init_reserved_page(unsigned long pfn)
+static void __meminit init_reserved_page(unsigned long pfn)
 {
 	pg_data_t *pgdat;
 	int nid, zid;
@@ -5367,6 +5367,7 @@ not_early:
 
 			__init_single_page(page, pfn, zone, nid);
 			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+			cond_resched();
 		} else {
 			__init_single_pfn(pfn, zone, nid);
 		}
diff --git a/mm/percpu-stats.c b/mm/percpu-stats.c
index 6142484e88f7..7a58460bfd27 100644
--- a/mm/percpu-stats.c
+++ b/mm/percpu-stats.c
@@ -73,7 +73,7 @@ static void chunk_map_stats(struct seq_file *m, struct pcpu_chunk *chunk,
 		     last_alloc + 1 : 0;
 
 	as_len = 0;
-	start = chunk->start_offset;
+	start = chunk->start_offset / PCPU_MIN_ALLOC_SIZE;
 
 	/*
 	 * If a bit is set in the allocation map, the bound_map identifies
diff --git a/mm/percpu.c b/mm/percpu.c
index 59d44d61f5f1..aa121cef76de 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -353,6 +353,8 @@ static void pcpu_next_md_free_region(struct pcpu_chunk *chunk, int *bit_off,
 					block->contig_hint_start);
 			return;
 		}
+		/* reset to satisfy the second predicate above */
+		block_off = 0;
 
 		*bits = block->right_free;
 		*bit_off = (i + 1) * PCPU_BITMAP_BLOCK_BITS - block->right_free;
@@ -407,6 +409,8 @@ static void pcpu_next_fit_region(struct pcpu_chunk *chunk, int alloc_bits,
 			*bit_off = pcpu_block_off_to_off(i, block->first_free);
 			return;
 		}
+		/* reset to satisfy the second predicate above */
+		block_off = 0;
 
 		*bit_off = ALIGN(PCPU_BITMAP_BLOCK_BITS - block->right_free,
 				 align);
diff --git a/mm/rodata_test.c b/mm/rodata_test.c
index 6bb4deb12e78..d908c8769b48 100644
--- a/mm/rodata_test.c
+++ b/mm/rodata_test.c
@@ -14,7 +14,7 @@
 #include <linux/uaccess.h>
 #include <asm/sections.h>
 
-const int rodata_test_data = 0xC3;
+static const int rodata_test_data = 0xC3;
 
 void rodata_test(void)
 {
diff --git a/mm/slab_common.c b/mm/slab_common.c
index 904a83be82de..80164599ca5d 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -165,9 +165,9 @@ static int init_memcg_params(struct kmem_cache *s,
 	if (!memcg_nr_cache_ids)
 		return 0;
 
-	arr = kzalloc(sizeof(struct memcg_cache_array) +
-		      memcg_nr_cache_ids * sizeof(void *),
-		      GFP_KERNEL);
+	arr = kvzalloc(sizeof(struct memcg_cache_array) +
+		       memcg_nr_cache_ids * sizeof(void *),
+		       GFP_KERNEL);
 	if (!arr)
 		return -ENOMEM;
 
@@ -178,15 +178,23 @@ static int init_memcg_params(struct kmem_cache *s,
 static void destroy_memcg_params(struct kmem_cache *s)
 {
 	if (is_root_cache(s))
-		kfree(rcu_access_pointer(s->memcg_params.memcg_caches));
+		kvfree(rcu_access_pointer(s->memcg_params.memcg_caches));
+}
+
+static void free_memcg_params(struct rcu_head *rcu)
+{
+	struct memcg_cache_array *old;
+
+	old = container_of(rcu, struct memcg_cache_array, rcu);
+	kvfree(old);
 }
 
 static int update_memcg_params(struct kmem_cache *s, int new_array_size)
 {
 	struct memcg_cache_array *old, *new;
 
-	new = kzalloc(sizeof(struct memcg_cache_array) +
-		      new_array_size * sizeof(void *), GFP_KERNEL);
+	new = kvzalloc(sizeof(struct memcg_cache_array) +
+		       new_array_size * sizeof(void *), GFP_KERNEL);
 	if (!new)
 		return -ENOMEM;
 
@@ -198,7 +206,7 @@ static int update_memcg_params(struct kmem_cache *s, int new_array_size)
 
 	rcu_assign_pointer(s->memcg_params.memcg_caches, new);
 	if (old)
-		kfree_rcu(old, rcu);
+		call_rcu(&old->rcu, free_memcg_params);
 	return 0;
 }
 
diff --git a/mm/swap.c b/mm/swap.c
index 9295ae960d66..a77d68f2c1b6 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -575,7 +575,7 @@ static void lru_lazyfree_fn(struct page *page, struct lruvec *lruvec,
 			    void *arg)
 {
 	if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
-	    !PageUnevictable(page)) {
+	    !PageSwapCache(page) && !PageUnevictable(page)) {
 		bool active = PageActive(page);
 
 		del_page_from_lru_list(page, lruvec,
@@ -665,7 +665,7 @@ void deactivate_file_page(struct page *page)
 void mark_page_lazyfree(struct page *page)
 {
 	if (PageLRU(page) && PageAnon(page) && PageSwapBacked(page) &&
-	    !PageUnevictable(page)) {
+	    !PageSwapCache(page) && !PageUnevictable(page)) {
 		struct pagevec *pvec = &get_cpu_var(lru_lazyfree_pvecs);
 
 		get_page(page);
diff --git a/mm/swap_state.c b/mm/swap_state.c
index 71ce2d1ccbf7..ed91091d1e68 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -242,6 +242,17 @@ int add_to_swap(struct page *page)
 		 * clear SWAP_HAS_CACHE flag.
 		 */
 		goto fail;
+	/*
+	 * Normally the page will be dirtied in unmap because its pte should be
+	 * dirty. A special case is MADV_FREE page. The page'e pte could have
+	 * dirty bit cleared but the page's SwapBacked bit is still set because
+	 * clearing the dirty bit and SwapBacked bit has no lock protected. For
+	 * such page, unmap will not set dirty bit for it, so page reclaim will
+	 * not write the page out. This can cause data corruption when the page
+	 * is swap in later. Always setting the dirty bit for the page solves
+	 * the problem.
+	 */
+	set_page_dirty(page);
 
 	return 1;
 
diff --git a/mm/z3fold.c b/mm/z3fold.c
index 486550df32be..b2ba2ba585f3 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -250,6 +250,7 @@ static void __release_z3fold_page(struct z3fold_header *zhdr, bool locked)
 
 	WARN_ON(!list_empty(&zhdr->buddy));
 	set_bit(PAGE_STALE, &page->private);
+	clear_bit(NEEDS_COMPACTING, &page->private);
 	spin_lock(&pool->lock);
 	if (!list_empty(&page->lru))
 		list_del(&page->lru);
@@ -303,7 +304,6 @@ static void free_pages_work(struct work_struct *w)
 		list_del(&zhdr->buddy);
 		if (WARN_ON(!test_bit(PAGE_STALE, &page->private)))
 			continue;
-		clear_bit(NEEDS_COMPACTING, &page->private);
 		spin_unlock(&pool->stale_lock);
 		cancel_work_sync(&zhdr->work);
 		free_z3fold_page(page);
@@ -624,10 +624,8 @@ lookup:
 	 * stale pages list. cancel_work_sync() can sleep so we must make
 	 * sure it won't be called in case we're in atomic context.
 	 */
-	if (zhdr && (can_sleep || !work_pending(&zhdr->work) ||
-	    !unlikely(work_busy(&zhdr->work)))) {
+	if (zhdr && (can_sleep || !work_pending(&zhdr->work))) {
 		list_del(&zhdr->buddy);
-		clear_bit(NEEDS_COMPACTING, &page->private);
 		spin_unlock(&pool->stale_lock);
 		if (can_sleep)
 			cancel_work_sync(&zhdr->work);
@@ -875,16 +873,18 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries)
 				goto next;
 		}
 next:
+		spin_lock(&pool->lock);
 		if (test_bit(PAGE_HEADLESS, &page->private)) {
 			if (ret == 0) {
+				spin_unlock(&pool->lock);
 				free_z3fold_page(page);
 				return 0;
 			}
 		} else if (kref_put(&zhdr->refcount, release_z3fold_page)) {
 			atomic64_dec(&pool->pages_nr);
+			spin_unlock(&pool->lock);
 			return 0;
 		}
-		spin_lock(&pool->lock);
 
 		/*
 		 * Add to the beginning of LRU.