Merge branch 'akpm' (Andrew's patch-bomb)

Merge first batch of patches from Andrew Morton:
 "A few misc things and all the MM queue"

* emailed from Andrew Morton <akpm@linux-foundation.org>: (92 commits)
  memcg: avoid THP split in task migration
  thp: add HPAGE_PMD_* definitions for !CONFIG_TRANSPARENT_HUGEPAGE
  memcg: clean up existing move charge code
  mm/memcontrol.c: remove unnecessary 'break' in mem_cgroup_read()
  mm/memcontrol.c: remove redundant BUG_ON() in mem_cgroup_usage_unregister_event()
  mm/memcontrol.c: s/stealed/stolen/
  memcg: fix performance of mem_cgroup_begin_update_page_stat()
  memcg: remove PCG_FILE_MAPPED
  memcg: use new logic for page stat accounting
  memcg: remove PCG_MOVE_LOCK flag from page_cgroup
  memcg: simplify move_account() check
  memcg: remove EXPORT_SYMBOL(mem_cgroup_update_page_stat)
  memcg: kill dead prev_priority stubs
  memcg: remove PCG_CACHE page_cgroup flag
  memcg: let css_get_next() rely upon rcu_read_lock()
  cgroup: revert ss_id_lock to spinlock
  idr: make idr_get_next() good for rcu_read_lock()
  memcg: remove unnecessary thp check in page stat accounting
  memcg: remove redundant returns
  memcg: enum lru_list lru
  ...

4 files changed, 37 insertions, 49 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 1ece8e20fdb..f4ea4b6f3cf 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4881,9 +4881,9 @@ void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
 
 	rcu_assign_pointer(id->css, NULL);
 	rcu_assign_pointer(css->id, NULL);
-	write_lock(&ss->id_lock);
+	spin_lock(&ss->id_lock);
 	idr_remove(&ss->idr, id->id);
-	write_unlock(&ss->id_lock);
+	spin_unlock(&ss->id_lock);
 	kfree_rcu(id, rcu_head);
 }
 EXPORT_SYMBOL_GPL(free_css_id);
@@ -4909,10 +4909,10 @@ static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
 		error = -ENOMEM;
 		goto err_out;
 	}
-	write_lock(&ss->id_lock);
+	spin_lock(&ss->id_lock);
 	/* Don't use 0. allocates an ID of 1-65535 */
 	error = idr_get_new_above(&ss->idr, newid, 1, &myid);
-	write_unlock(&ss->id_lock);
+	spin_unlock(&ss->id_lock);
 
 	/* Returns error when there are no free spaces for new ID.*/
 	if (error) {
@@ -4927,9 +4927,9 @@ static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
 	return newid;
 remove_idr:
 	error = -ENOSPC;
-	write_lock(&ss->id_lock);
+	spin_lock(&ss->id_lock);
 	idr_remove(&ss->idr, myid);
-	write_unlock(&ss->id_lock);
+	spin_unlock(&ss->id_lock);
 err_out:
 	kfree(newid);
 	return ERR_PTR(error);
@@ -4941,7 +4941,7 @@ static int __init_or_module cgroup_init_idr(struct cgroup_subsys *ss,
 {
 	struct css_id *newid;
 
-	rwlock_init(&ss->id_lock);
+	spin_lock_init(&ss->id_lock);
 	idr_init(&ss->idr);
 
 	newid = get_new_cssid(ss, 0);
@@ -5029,6 +5029,8 @@ css_get_next(struct cgroup_subsys *ss, int id,
 		return NULL;
 
 	BUG_ON(!ss->use_id);
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
 	/* fill start point for scan */
 	tmpid = id;
 	while (1) {
@@ -5036,10 +5038,7 @@ css_get_next(struct cgroup_subsys *ss, int id,
 		 * scan next entry from bitmap(tree), tmpid is updated after
 		 * idr_get_next().
 		 */
-		read_lock(&ss->id_lock);
 		tmp = idr_get_next(&ss->idr, &tmpid);
-		read_unlock(&ss->id_lock);
-
 		if (!tmp)
 			break;
 		if (tmp->depth >= depth && tmp->stack[depth] == rootid) {
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 5d575836dba..1010cc61931 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -964,7 +964,6 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 {
 	bool need_loop;
 
-repeat:
 	/*
 	 * Allow tasks that have access to memory reserves because they have
 	 * been OOM killed to get memory anywhere.
@@ -983,45 +982,19 @@ repeat:
 	 */
 	need_loop = task_has_mempolicy(tsk) ||
 			!nodes_intersects(*newmems, tsk->mems_allowed);
-	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
-	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
 
-	/*
-	 * ensure checking ->mems_allowed_change_disable after setting all new
-	 * allowed nodes.
-	 *
-	 * the read-side task can see an nodemask with new allowed nodes and
-	 * old allowed nodes. and if it allocates page when cpuset clears newly
-	 * disallowed ones continuous, it can see the new allowed bits.
-	 *
-	 * And if setting all new allowed nodes is after the checking, setting
-	 * all new allowed nodes and clearing newly disallowed ones will be done
-	 * continuous, and the read-side task may find no node to alloc page.
-	 */
-	smp_mb();
+	if (need_loop)
+		write_seqcount_begin(&tsk->mems_allowed_seq);
 
-	/*
-	 * Allocation of memory is very fast, we needn't sleep when waiting
-	 * for the read-side.
-	 */
-	while (need_loop && ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
-		task_unlock(tsk);
-		if (!task_curr(tsk))
-			yield();
-		goto repeat;
-	}
-
-	/*
-	 * ensure checking ->mems_allowed_change_disable before clearing all new
-	 * disallowed nodes.
-	 *
-	 * if clearing newly disallowed bits before the checking, the read-side
-	 * task may find no node to alloc page.
-	 */
-	smp_mb();
+	nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
+	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
 
 	mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
 	tsk->mems_allowed = *newmems;
+
+	if (need_loop)
+		write_seqcount_end(&tsk->mems_allowed_seq);
+
 	task_unlock(tsk);
 }
 
diff --git a/kernel/exit.c b/kernel/exit.c
index 7ad335c3045..16b07bfac22 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -935,7 +935,7 @@ void do_exit(long code)
 	acct_update_integrals(tsk);
 	/* sync mm's RSS info before statistics gathering */
 	if (tsk->mm)
-		sync_mm_rss(tsk, tsk->mm);
+		sync_mm_rss(tsk->mm);
 	group_dead = atomic_dec_and_test(&tsk->signal->live);
 	if (group_dead) {
 		hrtimer_cancel(&tsk->signal->real_timer);
diff --git a/kernel/fork.c b/kernel/fork.c
index 26a7138bb84..37674ec55cd 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -512,6 +512,23 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	return NULL;
 }
 
+static void check_mm(struct mm_struct *mm)
+{
+	int i;
+
+	for (i = 0; i < NR_MM_COUNTERS; i++) {
+		long x = atomic_long_read(&mm->rss_stat.count[i]);
+
+		if (unlikely(x))
+			printk(KERN_ALERT "BUG: Bad rss-counter state "
+					  "mm:%p idx:%d val:%ld\n", mm, i, x);
+	}
+
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	VM_BUG_ON(mm->pmd_huge_pte);
+#endif
+}
+
 /*
  * Allocate and initialize an mm_struct.
  */
@@ -539,9 +556,7 @@ void __mmdrop(struct mm_struct *mm)
 	mm_free_pgd(mm);
 	destroy_context(mm);
 	mmu_notifier_mm_destroy(mm);
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-	VM_BUG_ON(mm->pmd_huge_pte);
-#endif
+	check_mm(mm);
 	free_mm(mm);
 }
 EXPORT_SYMBOL_GPL(__mmdrop);
@@ -1223,6 +1238,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 #ifdef CONFIG_CPUSETS
 	p->cpuset_mem_spread_rotor = NUMA_NO_NODE;
 	p->cpuset_slab_spread_rotor = NUMA_NO_NODE;
+	seqcount_init(&p->mems_allowed_seq);
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	p->irq_events = 0;