Merge tag 'fscache-fixes-for-ceph' into wip-fscache

Patches for Ceph FS-Cache support

11 files changed, 100 insertions, 55 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 781845a013ab..e91963302c0d 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -4480,6 +4480,7 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	struct dentry *d = cgrp->dentry;
 	struct cgroup_event *event, *tmp;
 	struct cgroup_subsys *ss;
+	struct cgroup *child;
 	bool empty;
 
 	lockdep_assert_held(&d->d_inode->i_mutex);
@@ -4490,12 +4491,28 @@ static int cgroup_destroy_locked(struct cgroup *cgrp)
 	 * @cgrp from being removed while __put_css_set() is in progress.
 	 */
 	read_lock(&css_set_lock);
-	empty = list_empty(&cgrp->cset_links) && list_empty(&cgrp->children);
+	empty = list_empty(&cgrp->cset_links);
 	read_unlock(&css_set_lock);
 	if (!empty)
 		return -EBUSY;
 
 	/*
+	 * Make sure there's no live children.  We can't test ->children
+	 * emptiness as dead children linger on it while being destroyed;
+	 * otherwise, "rmdir parent/child parent" may fail with -EBUSY.
+	 */
+	empty = true;
+	rcu_read_lock();
+	list_for_each_entry_rcu(child, &cgrp->children, sibling) {
+		empty = cgroup_is_dead(child);
+		if (!empty)
+			break;
+	}
+	rcu_read_unlock();
+	if (!empty)
+		return -EBUSY;
+
+	/*
 	 * Block new css_tryget() by killing css refcnts.  cgroup core
 	 * guarantees that, by the time ->css_offline() is invoked, no new
 	 * css reference will be given out via css_tryget().  We can't
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index e5657788fedd..ea1966db34f2 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -475,13 +475,17 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
 
 	/*
 	 * Cpusets with tasks - existing or newly being attached - can't
-	 * have empty cpus_allowed or mems_allowed.
+	 * be changed to have empty cpus_allowed or mems_allowed.
 	 */
 	ret = -ENOSPC;
-	if ((cgroup_task_count(cur->css.cgroup) || cur->attach_in_progress) &&
-	    (cpumask_empty(trial->cpus_allowed) &&
-	     nodes_empty(trial->mems_allowed)))
-		goto out;
+	if ((cgroup_task_count(cur->css.cgroup) || cur->attach_in_progress)) {
+		if (!cpumask_empty(cur->cpus_allowed) &&
+		    cpumask_empty(trial->cpus_allowed))
+			goto out;
+		if (!nodes_empty(cur->mems_allowed) &&
+		    nodes_empty(trial->mems_allowed))
+			goto out;
+	}
 
 	ret = 0;
 out:
@@ -1608,11 +1612,13 @@ static int cpuset_write_u64(struct cgroup *cgrp, struct cftype *cft, u64 val)
 {
 	struct cpuset *cs = cgroup_cs(cgrp);
 	cpuset_filetype_t type = cft->private;
-	int retval = -ENODEV;
+	int retval = 0;
 
 	mutex_lock(&cpuset_mutex);
-	if (!is_cpuset_online(cs))
+	if (!is_cpuset_online(cs)) {
+		retval = -ENODEV;
 		goto out_unlock;
+	}
 
 	switch (type) {
 	case FILE_CPU_EXCLUSIVE:
diff --git a/kernel/fork.c b/kernel/fork.c
index e23bb19e2a3e..bf46287c91a4 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1177,7 +1177,8 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 	 * don't allow the creation of threads.
 	 */
 	if ((clone_flags & (CLONE_VM|CLONE_NEWPID)) &&
-	    (task_active_pid_ns(current) != current->nsproxy->pid_ns))
+	    (task_active_pid_ns(current) !=
+	     current->nsproxy->pid_ns_for_children))
 		return ERR_PTR(-EINVAL);
 
 	retval = security_task_create(clone_flags);
@@ -1351,7 +1352,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 
 	if (pid != &init_struct_pid) {
 		retval = -ENOMEM;
-		pid = alloc_pid(p->nsproxy->pid_ns);
+		pid = alloc_pid(p->nsproxy->pid_ns_for_children);
 		if (!pid)
 			goto bad_fork_cleanup_io;
 	}
diff --git a/kernel/nsproxy.c b/kernel/nsproxy.c
index 364ceab15f0c..997cbb951a3b 100644
--- a/kernel/nsproxy.c
+++ b/kernel/nsproxy.c
@@ -29,15 +29,15 @@
 static struct kmem_cache *nsproxy_cachep;
 
 struct nsproxy init_nsproxy = {
-	.count	= ATOMIC_INIT(1),
-	.uts_ns	= &init_uts_ns,
+	.count			= ATOMIC_INIT(1),
+	.uts_ns			= &init_uts_ns,
 #if defined(CONFIG_POSIX_MQUEUE) || defined(CONFIG_SYSVIPC)
-	.ipc_ns	= &init_ipc_ns,
+	.ipc_ns			= &init_ipc_ns,
 #endif
-	.mnt_ns	= NULL,
-	.pid_ns	= &init_pid_ns,
+	.mnt_ns			= NULL,
+	.pid_ns_for_children	= &init_pid_ns,
 #ifdef CONFIG_NET
-	.net_ns	= &init_net,
+	.net_ns			= &init_net,
 #endif
 };
 
@@ -85,9 +85,10 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 		goto out_ipc;
 	}
 
-	new_nsp->pid_ns = copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns);
-	if (IS_ERR(new_nsp->pid_ns)) {
-		err = PTR_ERR(new_nsp->pid_ns);
+	new_nsp->pid_ns_for_children =
+		copy_pid_ns(flags, user_ns, tsk->nsproxy->pid_ns_for_children);
+	if (IS_ERR(new_nsp->pid_ns_for_children)) {
+		err = PTR_ERR(new_nsp->pid_ns_for_children);
 		goto out_pid;
 	}
 
@@ -100,8 +101,8 @@ static struct nsproxy *create_new_namespaces(unsigned long flags,
 	return new_nsp;
 
 out_net:
-	if (new_nsp->pid_ns)
-		put_pid_ns(new_nsp->pid_ns);
+	if (new_nsp->pid_ns_for_children)
+		put_pid_ns(new_nsp->pid_ns_for_children);
 out_pid:
 	if (new_nsp->ipc_ns)
 		put_ipc_ns(new_nsp->ipc_ns);
@@ -174,8 +175,8 @@ void free_nsproxy(struct nsproxy *ns)
 		put_uts_ns(ns->uts_ns);
 	if (ns->ipc_ns)
 		put_ipc_ns(ns->ipc_ns);
-	if (ns->pid_ns)
-		put_pid_ns(ns->pid_ns);
+	if (ns->pid_ns_for_children)
+		put_pid_ns(ns->pid_ns_for_children);
 	put_net(ns->net_ns);
 	kmem_cache_free(nsproxy_cachep, ns);
 }
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index 6917e8edb48e..601bb361c235 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -349,8 +349,8 @@ static int pidns_install(struct nsproxy *nsproxy, void *ns)
 	if (ancestor != active)
 		return -EINVAL;
 
-	put_pid_ns(nsproxy->pid_ns);
-	nsproxy->pid_ns = get_pid_ns(new);
+	put_pid_ns(nsproxy->pid_ns_for_children);
+	nsproxy->pid_ns_for_children = get_pid_ns(new);
 	return 0;
 }
 
diff --git a/kernel/power/qos.c b/kernel/power/qos.c
index 06fe28589e9c..a394297f8b2f 100644
--- a/kernel/power/qos.c
+++ b/kernel/power/qos.c
@@ -296,6 +296,17 @@ int pm_qos_request_active(struct pm_qos_request *req)
 }
 EXPORT_SYMBOL_GPL(pm_qos_request_active);
 
+static void __pm_qos_update_request(struct pm_qos_request *req,
+			   s32 new_value)
+{
+	trace_pm_qos_update_request(req->pm_qos_class, new_value);
+
+	if (new_value != req->node.prio)
+		pm_qos_update_target(
+			pm_qos_array[req->pm_qos_class]->constraints,
+			&req->node, PM_QOS_UPDATE_REQ, new_value);
+}
+
 /**
  * pm_qos_work_fn - the timeout handler of pm_qos_update_request_timeout
  * @work: work struct for the delayed work (timeout)
@@ -308,7 +319,7 @@ static void pm_qos_work_fn(struct work_struct *work)
 						  struct pm_qos_request,
 						  work);
 
-	pm_qos_update_request(req, PM_QOS_DEFAULT_VALUE);
+	__pm_qos_update_request(req, PM_QOS_DEFAULT_VALUE);
 }
 
 /**
@@ -364,12 +375,7 @@ void pm_qos_update_request(struct pm_qos_request *req,
 	}
 
 	cancel_delayed_work_sync(&req->work);
-
-	trace_pm_qos_update_request(req->pm_qos_class, new_value);
-	if (new_value != req->node.prio)
-		pm_qos_update_target(
-			pm_qos_array[req->pm_qos_class]->constraints,
-			&req->node, PM_QOS_UPDATE_REQ, new_value);
+	__pm_qos_update_request(req, new_value);
 }
 EXPORT_SYMBOL_GPL(pm_qos_update_request);
 
diff --git a/kernel/time/sched_clock.c b/kernel/time/sched_clock.c
index a326f27d7f09..0b479a6a22bb 100644
--- a/kernel/time/sched_clock.c
+++ b/kernel/time/sched_clock.c
@@ -121,7 +121,7 @@ void __init setup_sched_clock(u32 (*read)(void), int bits, unsigned long rate)
 	BUG_ON(bits > 32);
 	WARN_ON(!irqs_disabled());
 	read_sched_clock = read;
-	sched_clock_mask = (1 << bits) - 1;
+	sched_clock_mask = (1ULL << bits) - 1;
 	cd.rate = rate;
 
 	/* calculate the mult/shift to convert counter ticks to ns. */
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index e77edc97e036..e8a1516cc0a3 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -182,7 +182,8 @@ static bool can_stop_full_tick(void)
 		 * Don't allow the user to think they can get
 		 * full NO_HZ with this machine.
 		 */
-		WARN_ONCE(1, "NO_HZ FULL will not work with unstable sched clock");
+		WARN_ONCE(have_nohz_full_mask,
+			  "NO_HZ FULL will not work with unstable sched clock");
 		return false;
 	}
 #endif
@@ -343,8 +344,6 @@ static int tick_nohz_init_all(void)
 
 void __init tick_nohz_init(void)
 {
-	int cpu;
-
 	if (!have_nohz_full_mask) {
 		if (tick_nohz_init_all() < 0)
 			return;
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 3bdf28323012..61ed862cdd37 100644
--- a/kernel/time/timer_list.c
+++ b/kernel/time/timer_list.c
@@ -265,10 +265,9 @@ static inline void timer_list_header(struct seq_file *m, u64 now)
 static int timer_list_show(struct seq_file *m, void *v)
 {
 	struct timer_list_iter *iter = v;
-	u64 now = ktime_to_ns(ktime_get());
 
 	if (iter->cpu == -1 && !iter->second_pass)
-		timer_list_header(m, now);
+		timer_list_header(m, iter->now);
 	else if (!iter->second_pass)
 		print_cpu(m, iter->cpu, iter->now);
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
@@ -298,33 +297,41 @@ void sysrq_timer_list_show(void)
 	return;
 }
 
-static void *timer_list_start(struct seq_file *file, loff_t *offset)
+static void *move_iter(struct timer_list_iter *iter, loff_t offset)
 {
-	struct timer_list_iter *iter = file->private;
-
-	if (!*offset) {
-		iter->cpu = -1;
-		iter->now = ktime_to_ns(ktime_get());
-	} else if (iter->cpu >= nr_cpu_ids) {
+	for (; offset; offset--) {
+		iter->cpu = cpumask_next(iter->cpu, cpu_online_mask);
+		if (iter->cpu >= nr_cpu_ids) {
 #ifdef CONFIG_GENERIC_CLOCKEVENTS
-		if (!iter->second_pass) {
-			iter->cpu = -1;
-			iter->second_pass = true;
-		} else
-			return NULL;
+			if (!iter->second_pass) {
+				iter->cpu = -1;
+				iter->second_pass = true;
+			} else
+				return NULL;
 #else
-		return NULL;
+			return NULL;
 #endif
+		}
 	}
 	return iter;
 }
 
+static void *timer_list_start(struct seq_file *file, loff_t *offset)
+{
+	struct timer_list_iter *iter = file->private;
+
+	if (!*offset)
+		iter->now = ktime_to_ns(ktime_get());
+	iter->cpu = -1;
+	iter->second_pass = false;
+	return move_iter(iter, *offset);
+}
+
 static void *timer_list_next(struct seq_file *file, void *v, loff_t *offset)
 {
 	struct timer_list_iter *iter = file->private;
-	iter->cpu = cpumask_next(iter->cpu, cpu_online_mask);
 	++*offset;
-	return timer_list_start(file, offset);
+	return move_iter(iter, 1);
 }
 
 static void timer_list_stop(struct seq_file *seq, void *v)
diff --git a/kernel/wait.c b/kernel/wait.c
index dec68bd4e9d8..d550920e040c 100644
--- a/kernel/wait.c
+++ b/kernel/wait.c
@@ -363,8 +363,7 @@ EXPORT_SYMBOL(out_of_line_wait_on_atomic_t);
 
 /**
  * wake_up_atomic_t - Wake up a waiter on a atomic_t
- * @word: The word being waited on, a kernel virtual address
- * @bit: The bit of the word being waited on
+ * @p: The atomic_t being waited on, a kernel virtual address
  *
  * Wake up anyone waiting for the atomic_t to go to zero.
  *
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 7f5d4be22034..e93f7b9067d8 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2201,6 +2201,15 @@ __acquires(&pool->lock)
 		dump_stack();
 	}
 
+	/*
+	 * The following prevents a kworker from hogging CPU on !PREEMPT
+	 * kernels, where a requeueing work item waiting for something to
+	 * happen could deadlock with stop_machine as such work item could
+	 * indefinitely requeue itself while all other CPUs are trapped in
+	 * stop_machine.
+	 */
+	cond_resched();
+
 	spin_lock_irq(&pool->lock);
 
 	/* clear cpu intensive status */