Merge tag 'v3.9-rc5' into wq/for-3.10

Writeback conversion to workqueue will be based on top of wq/for-3.10
branch to take advantage of custom attrs and NUMA support for unbound
workqueues.  Mainline currently contains two commits which result in
non-trivial merge conflicts with wq/for-3.10 and because
block/for-3.10/core is based on v3.9-rc3 which contains one of the
conflicting commits, we need a pre-merge-window merge anyway.  Let's
pull v3.9-rc5 into wq/for-3.10 so that the block tree doesn't suffer
from workqueue merge conflicts.

The two conflicts and their resolutions:

* e68035fb65 ("workqueue: convert to idr_alloc()") in mainline changes
  worker_pool_assign_id() to use idr_alloc() instead of the old idr
  interface.  worker_pool_assign_id() goes through multiple locking
  changes in wq/for-3.10 causing the following conflict.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

  <<<<<<< HEAD
	  lockdep_assert_held(&wq_pool_mutex);

	  do {
		  if (!idr_pre_get(&worker_pool_idr, GFP_KERNEL))
			  return -ENOMEM;
		  ret = idr_get_new(&worker_pool_idr, pool, &pool->id);
	  } while (ret == -EAGAIN);
  =======
	  mutex_lock(&worker_pool_idr_mutex);
	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0)
		  pool->id = ret;
	  mutex_unlock(&worker_pool_idr_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

	  return ret < 0 ? ret : 0;
  }

  We want locking from the former and idr_alloc() usage from the
  latter, which can be combined to the following.

  static int worker_pool_assign_id(struct worker_pool *pool)
  {
	  int ret;

	  lockdep_assert_held(&wq_pool_mutex);

	  ret = idr_alloc(&worker_pool_idr, pool, 0, 0, GFP_KERNEL);
	  if (ret >= 0) {
		  pool->id = ret;
		  return 0;
	  }
	  return ret;
   }

* eb2834285c ("workqueue: fix possible pool stall bug in
  wq_unbind_fn()") updated wq_unbind_fn() such that it has single
  larger for_each_std_worker_pool() loop instead of two separate loops
  with a schedule() call inbetween.  wq/for-3.10 renamed
  pool->assoc_mutex to pool->manager_mutex causing the following
  conflict (earlier function body and comments omitted for brevity).

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
  <<<<<<< HEAD
		  mutex_unlock(&pool->manager_mutex);
	  }
  =======
		  mutex_unlock(&pool->assoc_mutex);
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89

		  schedule();

  <<<<<<< HEAD
	  for_each_cpu_worker_pool(pool, cpu)
  =======
  >>>>>>> c67bf5361e7e66a0ff1f4caf95f89347d55dfb89
		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

  The resolution is mostly trivial.  We want the control flow of the
  latter with the rename of the former.

  static void wq_unbind_fn(struct work_struct *work)
  {
  ...
		  spin_unlock_irq(&pool->lock);
		  mutex_unlock(&pool->manager_mutex);

		  schedule();

		  atomic_set(&pool->nr_running, 0);

		  spin_lock_irq(&pool->lock);
		  wake_up_worker(pool);
		  spin_unlock_irq(&pool->lock);
	  }
  }

Signed-off-by: Tejun Heo <tj@kernel.org>

10 files changed, 40 insertions, 38 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index ae55c1e04d10..3bea74f1ccfe 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -286,8 +286,12 @@ config NR_QUICK
 	default "1"
 
 config VIRT_TO_BUS
-	def_bool y
-	depends on HAVE_VIRT_TO_BUS
+	bool
+	help
+	  An architecture should select this if it implements the
+	  deprecated interface virt_to_bus().  All new architectures
+	  should probably not select this.
+
 
 config MMU_NOTIFIER
 	bool
diff --git a/mm/fremap.c b/mm/fremap.c
index 0cd4c11488ed..87da3590c61e 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -129,7 +129,7 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
 	struct vm_area_struct *vma;
 	int err = -EINVAL;
 	int has_write_lock = 0;
-	vm_flags_t vm_flags;
+	vm_flags_t vm_flags = 0;
 
 	if (prot)
 		return err;
@@ -204,10 +204,8 @@ get_write_lock:
 			unsigned long addr;
 			struct file *file = get_file(vma->vm_file);
 
-			vm_flags = vma->vm_flags;
-			if (!(flags & MAP_NONBLOCK))
-				vm_flags |= VM_POPULATE;
-			addr = mmap_region(file, start, size, vm_flags, pgoff);
+			addr = mmap_region(file, start, size,
+					vma->vm_flags, pgoff);
 			fput(file);
 			if (IS_ERR_VALUE(addr)) {
 				err = addr;
@@ -226,12 +224,6 @@ get_write_lock:
 		mutex_unlock(&mapping->i_mmap_mutex);
 	}
 
-	if (!(flags & MAP_NONBLOCK) && !(vma->vm_flags & VM_POPULATE)) {
-		if (!has_write_lock)
-			goto get_write_lock;
-		vma->vm_flags |= VM_POPULATE;
-	}
-
 	if (vma->vm_flags & VM_LOCKED) {
 		/*
 		 * drop PG_Mlocked flag for over-mapped range
@@ -254,7 +246,8 @@ get_write_lock:
 	 */
 
 out:
-	vm_flags = vma->vm_flags;
+	if (vma)
+		vm_flags = vma->vm_flags;
 	if (likely(!has_write_lock))
 		up_read(&mm->mmap_sem);
 	else
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 0a0be33bb199..ca9a7c6d7e97 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -2124,8 +2124,12 @@ int hugetlb_report_node_meminfo(int nid, char *buf)
 /* Return the number pages of memory we physically have, in PAGE_SIZE units. */
 unsigned long hugetlb_total_pages(void)
 {
-	struct hstate *h = &default_hstate;
-	return h->nr_huge_pages * pages_per_huge_page(h);
+	struct hstate *h;
+	unsigned long nr_total_pages = 0;
+
+	for_each_hstate(h)
+		nr_total_pages += h->nr_huge_pages * pages_per_huge_page(h);
+	return nr_total_pages;
 }
 
 static int hugetlb_acct_memory(struct hstate *h, long delta)
diff --git a/mm/ksm.c b/mm/ksm.c
index 85bfd4c16346..b6afe0c440d8 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -489,7 +489,7 @@ out:		page = NULL;
  */
 static inline int get_kpfn_nid(unsigned long kpfn)
 {
-	return ksm_merge_across_nodes ? 0 : pfn_to_nid(kpfn);
+	return ksm_merge_across_nodes ? 0 : NUMA(pfn_to_nid(kpfn));
 }
 
 static void remove_node_from_stable_tree(struct stable_node *stable_node)
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 53b8201b31eb..2b552224f5cf 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3012,6 +3012,8 @@ void memcg_update_array_size(int num)
 		memcg_limited_groups_array_size = memcg_caches_array_size(num);
 }
 
+static void kmem_cache_destroy_work_func(struct work_struct *w);
+
 int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
 {
 	struct memcg_cache_params *cur_params = s->memcg_params;
@@ -3031,6 +3033,8 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups)
 			return -ENOMEM;
 		}
 
+		INIT_WORK(&s->memcg_params->destroy,
+				kmem_cache_destroy_work_func);
 		s->memcg_params->is_root_cache = true;
 
 		/*
@@ -3078,6 +3082,8 @@ int memcg_register_cache(struct mem_cgroup *memcg, struct kmem_cache *s,
 	if (!s->memcg_params)
 		return -ENOMEM;
 
+	INIT_WORK(&s->memcg_params->destroy,
+			kmem_cache_destroy_work_func);
 	if (memcg) {
 		s->memcg_params->memcg = memcg;
 		s->memcg_params->root_cache = root_cache;
@@ -3358,8 +3364,6 @@ static void mem_cgroup_destroy_all_caches(struct mem_cgroup *memcg)
 	list_for_each_entry(params, &memcg->memcg_slab_caches, list) {
 		cachep = memcg_params_to_cache(params);
 		cachep->memcg_params->dead = true;
-		INIT_WORK(&cachep->memcg_params->destroy,
-				  kmem_cache_destroy_work_func);
 		schedule_work(&cachep->memcg_params->destroy);
 	}
 	mutex_unlock(&memcg->slab_caches_mutex);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b81a367b9f39..ee3765760818 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1779,7 +1779,11 @@ void try_offline_node(int nid)
 	for (i = 0; i < MAX_NR_ZONES; i++) {
 		struct zone *zone = pgdat->node_zones + i;
 
-		if (zone->wait_table)
+		/*
+		 * 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);
 	}
 
@@ -1801,7 +1805,7 @@ int __ref remove_memory(int nid, u64 start, u64 size)
 	int retry = 1;
 
 	start_pfn = PFN_DOWN(start);
-	end_pfn = start_pfn + PFN_DOWN(size);
+	end_pfn = PFN_UP(start + size - 1);
 
 	/*
 	 * When CONFIG_MEMCG is on, one memory block may be used by other
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 31d26637b658..74310017296e 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2390,9 +2390,9 @@ restart:
 
 				*mpol_new = *n->policy;
 				atomic_set(&mpol_new->refcnt, 1);
-				sp_node_init(n_new, n->end, end, mpol_new);
-				sp_insert(sp, n_new);
+				sp_node_init(n_new, end, n->end, mpol_new);
 				n->end = start;
+				sp_insert(sp, n_new);
 				n_new = NULL;
 				mpol_new = NULL;
 				break;
diff --git a/mm/mlock.c b/mm/mlock.c
index 1c5e33fce639..79b7cf7d1bca 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -358,7 +358,7 @@ static int do_mlock(unsigned long start, size_t len, int on)
 
 		newflags = vma->vm_flags & ~VM_LOCKED;
 		if (on)
-			newflags |= VM_LOCKED | VM_POPULATE;
+			newflags |= VM_LOCKED;
 
 		tmp = vma->vm_end;
 		if (tmp > end)
@@ -418,8 +418,7 @@ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors)
 		 * range with the first VMA. Also, skip undesirable VMA types.
 		 */
 		nend = min(end, vma->vm_end);
-		if ((vma->vm_flags & (VM_IO | VM_PFNMAP | VM_POPULATE)) !=
-		    VM_POPULATE)
+		if (vma->vm_flags & (VM_IO | VM_PFNMAP))
 			continue;
 		if (nstart < vma->vm_start)
 			nstart = vma->vm_start;
@@ -492,9 +491,9 @@ static int do_mlockall(int flags)
 	struct vm_area_struct * vma, * prev = NULL;
 
 	if (flags & MCL_FUTURE)
-		current->mm->def_flags |= VM_LOCKED | VM_POPULATE;
+		current->mm->def_flags |= VM_LOCKED;
 	else
-		current->mm->def_flags &= ~(VM_LOCKED | VM_POPULATE);
+		current->mm->def_flags &= ~VM_LOCKED;
 	if (flags == MCL_FUTURE)
 		goto out;
 
@@ -503,7 +502,7 @@ static int do_mlockall(int flags)
 
 		newflags = vma->vm_flags & ~VM_LOCKED;
 		if (flags & MCL_CURRENT)
-			newflags |= VM_LOCKED | VM_POPULATE;
+			newflags |= VM_LOCKED;
 
 		/* Ignore errors */
 		mlock_fixup(vma, &prev, vma->vm_start, vma->vm_end, newflags);
diff --git a/mm/mmap.c b/mm/mmap.c
index 2664a47cec93..6466699b16cb 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1306,7 +1306,9 @@ unsigned long do_mmap_pgoff(struct file *file, unsigned long addr,
 	}
 
 	addr = mmap_region(file, addr, len, vm_flags, pgoff);
-	if (!IS_ERR_VALUE(addr) && (vm_flags & VM_POPULATE))
+	if (!IS_ERR_VALUE(addr) &&
+	    ((vm_flags & VM_LOCKED) ||
+	     (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE))
 		*populate = len;
 	return addr;
 }
diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c
index 926b46649749..fd26d0433509 100644
--- a/mm/process_vm_access.c
+++ b/mm/process_vm_access.c
@@ -429,12 +429,6 @@ compat_process_vm_rw(compat_pid_t pid,
 	if (flags != 0)
 		return -EINVAL;
 
-	if (!access_ok(VERIFY_READ, lvec, liovcnt * sizeof(*lvec)))
-		goto out;
-
-	if (!access_ok(VERIFY_READ, rvec, riovcnt * sizeof(*rvec)))
-		goto out;
-
 	if (vm_write)
 		rc = compat_rw_copy_check_uvector(WRITE, lvec, liovcnt,
 						  UIO_FASTIOV, iovstack_l,
@@ -459,8 +453,6 @@ free_iovecs:
 		kfree(iov_r);
 	if (iov_l != iovstack_l)
 		kfree(iov_l);
-
-out:
 	return rc;
 }