Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Three sets of overlapping changes.  Nothing serious.

Signed-off-by: David S. Miller <davem@davemloft.net>

5 files changed, 63 insertions, 24 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 5e8dab5bf9ad..d6b729beba49 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -3446,9 +3446,28 @@ static ssize_t cgroup_subtree_control_write(struct kernfs_open_file *of,
 	 * Except for the root, subtree_control must be zero for a cgroup
 	 * with tasks so that child cgroups don't compete against tasks.
 	 */
-	if (enable && cgroup_parent(cgrp) && !list_empty(&cgrp->cset_links)) {
-		ret = -EBUSY;
-		goto out_unlock;
+	if (enable && cgroup_parent(cgrp)) {
+		struct cgrp_cset_link *link;
+
+		/*
+		 * Because namespaces pin csets too, @cgrp->cset_links
+		 * might not be empty even when @cgrp is empty.  Walk and
+		 * verify each cset.
+		 */
+		spin_lock_irq(&css_set_lock);
+
+		ret = 0;
+		list_for_each_entry(link, &cgrp->cset_links, cset_link) {
+			if (css_set_populated(link->cset)) {
+				ret = -EBUSY;
+				break;
+			}
+		}
+
+		spin_unlock_irq(&css_set_lock);
+
+		if (ret)
+			goto out_unlock;
 	}
 
 	/* save and update control masks and prepare csses */
@@ -3899,7 +3918,9 @@ void cgroup_file_notify(struct cgroup_file *cfile)
  * cgroup_task_count - count the number of tasks in a cgroup.
  * @cgrp: the cgroup in question
  *
- * Return the number of tasks in the cgroup.
+ * Return the number of tasks in the cgroup.  The returned number can be
+ * higher than the actual number of tasks due to css_set references from
+ * namespace roots and temporary usages.
  */
 static int cgroup_task_count(const struct cgroup *cgrp)
 {
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index c27e53326bef..2b4c20ab5bbe 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -325,8 +325,7 @@ static struct file_system_type cpuset_fs_type = {
 /*
  * Return in pmask the portion of a cpusets's cpus_allowed that
  * are online.  If none are online, walk up the cpuset hierarchy
- * until we find one that does have some online cpus.  The top
- * cpuset always has some cpus online.
+ * until we find one that does have some online cpus.
  *
  * One way or another, we guarantee to return some non-empty subset
  * of cpu_online_mask.
@@ -335,8 +334,20 @@ static struct file_system_type cpuset_fs_type = {
  */
 static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask)
 {
-	while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask))
+	while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) {
 		cs = parent_cs(cs);
+		if (unlikely(!cs)) {
+			/*
+			 * The top cpuset doesn't have any online cpu as a
+			 * consequence of a race between cpuset_hotplug_work
+			 * and cpu hotplug notifier.  But we know the top
+			 * cpuset's effective_cpus is on its way to to be
+			 * identical to cpu_online_mask.
+			 */
+			cpumask_copy(pmask, cpu_online_mask);
+			return;
+		}
+	}
 	cpumask_and(pmask, cs->effective_cpus, cpu_online_mask);
 }
 
@@ -2074,7 +2085,7 @@ static void cpuset_bind(struct cgroup_subsys_state *root_css)
  * which could have been changed by cpuset just after it inherits the
  * state from the parent and before it sits on the cgroup's task list.
  */
-void cpuset_fork(struct task_struct *task)
+static void cpuset_fork(struct task_struct *task)
 {
 	if (task_css_is_root(task, cpuset_cgrp_id))
 		return;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 9fc3be0c7d01..5c02f6764868 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3929,7 +3929,7 @@ static void exclusive_event_destroy(struct perf_event *event)
 
 static bool exclusive_event_match(struct perf_event *e1, struct perf_event *e2)
 {
-	if ((e1->pmu->capabilities & PERF_PMU_CAP_EXCLUSIVE) &&
+	if ((e1->pmu == e2->pmu) &&
 	    (e1->cpu == e2->cpu ||
 	     e1->cpu == -1 ||
 	     e2->cpu == -1))
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 637389088b3f..26ba5654d9d5 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -820,6 +820,8 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
 	desc->name = name;
 
 	if (handle != handle_bad_irq && is_chained) {
+		unsigned int type = irqd_get_trigger_type(&desc->irq_data);
+
 		/*
 		 * We're about to start this interrupt immediately,
 		 * hence the need to set the trigger configuration.
@@ -828,8 +830,10 @@ __irq_do_set_handler(struct irq_desc *desc, irq_flow_handler_t handle,
 		 * chained interrupt. Reset it immediately because we
 		 * do know better.
 		 */
-		__irq_set_trigger(desc, irqd_get_trigger_type(&desc->irq_data));
-		desc->handle_irq = handle;
+		if (type != IRQ_TYPE_NONE) {
+			__irq_set_trigger(desc, type);
+			desc->handle_irq = handle;
+		}
 
 		irq_settings_set_noprobe(desc);
 		irq_settings_set_norequest(desc);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index dade4c9559cc..7bc56762ca35 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -5124,19 +5124,20 @@ tracing_read_pipe(struct file *filp, char __user *ubuf,
 	struct trace_iterator *iter = filp->private_data;
 	ssize_t sret;
 
-	/* return any leftover data */
-	sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
-	if (sret != -EBUSY)
-		return sret;
-
-	trace_seq_init(&iter->seq);
-
 	/*
 	 * Avoid more than one consumer on a single file descriptor
 	 * This is just a matter of traces coherency, the ring buffer itself
 	 * is protected.
 	 */
 	mutex_lock(&iter->mutex);
+
+	/* return any leftover data */
+	sret = trace_seq_to_user(&iter->seq, ubuf, cnt);
+	if (sret != -EBUSY)
+		goto out;
+
+	trace_seq_init(&iter->seq);
+
 	if (iter->trace->read) {
 		sret = iter->trace->read(iter, filp, ubuf, cnt, ppos);
 		if (sret)
@@ -6163,9 +6164,6 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		return -EBUSY;
 #endif
 
-	if (splice_grow_spd(pipe, &spd))
-		return -ENOMEM;
-
 	if (*ppos & (PAGE_SIZE - 1))
 		return -EINVAL;
 
@@ -6175,6 +6173,9 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 		len &= PAGE_MASK;
 	}
 
+	if (splice_grow_spd(pipe, &spd))
+		return -ENOMEM;
+
  again:
 	trace_access_lock(iter->cpu_file);
 	entries = ring_buffer_entries_cpu(iter->trace_buffer->buffer, iter->cpu_file);
@@ -6232,19 +6233,21 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos,
 	/* did we read anything? */
 	if (!spd.nr_pages) {
 		if (ret)
-			return ret;
+			goto out;
 
+		ret = -EAGAIN;
 		if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK))
-			return -EAGAIN;
+			goto out;
 
 		ret = wait_on_pipe(iter, true);
 		if (ret)
-			return ret;
+			goto out;
 
 		goto again;
 	}
 
 	ret = splice_to_pipe(pipe, &spd);
+out:
 	splice_shrink_spd(&spd);
 
 	return ret;