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

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

9 files changed, 122 insertions, 63 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 7868fc3c0bc5..70776aec2562 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1648,10 +1648,13 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 			 int flags, const char *unused_dev_name,
 			 void *data)
 {
+	struct super_block *pinned_sb = NULL;
+	struct cgroup_subsys *ss;
 	struct cgroup_root *root;
 	struct cgroup_sb_opts opts;
 	struct dentry *dentry;
 	int ret;
+	int i;
 	bool new_sb;
 
 	/*
@@ -1677,6 +1680,27 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 		goto out_unlock;
 	}
 
+	/*
+	 * Destruction of cgroup root is asynchronous, so subsystems may
+	 * still be dying after the previous unmount.  Let's drain the
+	 * dying subsystems.  We just need to ensure that the ones
+	 * unmounted previously finish dying and don't care about new ones
+	 * starting.  Testing ref liveliness is good enough.
+	 */
+	for_each_subsys(ss, i) {
+		if (!(opts.subsys_mask & (1 << i)) ||
+		    ss->root == &cgrp_dfl_root)
+			continue;
+
+		if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) {
+			mutex_unlock(&cgroup_mutex);
+			msleep(10);
+			ret = restart_syscall();
+			goto out_free;
+		}
+		cgroup_put(&ss->root->cgrp);
+	}
+
 	for_each_root(root) {
 		bool name_match = false;
 
@@ -1717,15 +1741,23 @@ static struct dentry *cgroup_mount(struct file_system_type *fs_type,
 		}
 
 		/*
-		 * A root's lifetime is governed by its root cgroup.
-		 * tryget_live failure indicate that the root is being
-		 * destroyed.  Wait for destruction to complete so that the
-		 * subsystems are free.  We can use wait_queue for the wait
-		 * but this path is super cold.  Let's just sleep for a bit
-		 * and retry.
+		 * We want to reuse @root whose lifetime is governed by its
+		 * ->cgrp.  Let's check whether @root is alive and keep it
+		 * that way.  As cgroup_kill_sb() can happen anytime, we
+		 * want to block it by pinning the sb so that @root doesn't
+		 * get killed before mount is complete.
+		 *
+		 * With the sb pinned, tryget_live can reliably indicate
+		 * whether @root can be reused.  If it's being killed,
+		 * drain it.  We can use wait_queue for the wait but this
+		 * path is super cold.  Let's just sleep a bit and retry.
 		 */
-		if (!percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
+		pinned_sb = kernfs_pin_sb(root->kf_root, NULL);
+		if (IS_ERR(pinned_sb) ||
+		    !percpu_ref_tryget_live(&root->cgrp.self.refcnt)) {
 			mutex_unlock(&cgroup_mutex);
+			if (!IS_ERR_OR_NULL(pinned_sb))
+				deactivate_super(pinned_sb);
 			msleep(10);
 			ret = restart_syscall();
 			goto out_free;
@@ -1770,6 +1802,16 @@ out_free:
 				CGROUP_SUPER_MAGIC, &new_sb);
 	if (IS_ERR(dentry) || !new_sb)
 		cgroup_put(&root->cgrp);
+
+	/*
+	 * If @pinned_sb, we're reusing an existing root and holding an
+	 * extra ref on its sb.  Mount is complete.  Put the extra ref.
+	 */
+	if (pinned_sb) {
+		WARN_ON(new_sb);
+		deactivate_super(pinned_sb);
+	}
+
 	return dentry;
 }
 
@@ -3328,7 +3370,7 @@ bool css_has_online_children(struct cgroup_subsys_state *css)
 
 	rcu_read_lock();
 	css_for_each_child(child, css) {
-		if (css->flags & CSS_ONLINE) {
+		if (child->flags & CSS_ONLINE) {
 			ret = true;
 			break;
 		}
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index f6b33c696224..116a4164720a 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1181,7 +1181,13 @@ done:
 
 int current_cpuset_is_being_rebound(void)
 {
-	return task_cs(current) == cpuset_being_rebound;
+	int ret;
+
+	rcu_read_lock();
+	ret = task_cs(current) == cpuset_being_rebound;
+	rcu_read_unlock();
+
+	return ret;
 }
 
 static int update_relax_domain_level(struct cpuset *cs, s64 val)
@@ -1617,7 +1623,17 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	 * resources, wait for the previously scheduled operations before
 	 * proceeding, so that we don't end up keep removing tasks added
 	 * after execution capability is restored.
+	 *
+	 * cpuset_hotplug_work calls back into cgroup core via
+	 * cgroup_transfer_tasks() and waiting for it from a cgroupfs
+	 * operation like this one can lead to a deadlock through kernfs
+	 * active_ref protection.  Let's break the protection.  Losing the
+	 * protection is okay as we check whether @cs is online after
+	 * grabbing cpuset_mutex anyway.  This only happens on the legacy
+	 * hierarchies.
 	 */
+	css_get(&cs->css);
+	kernfs_break_active_protection(of->kn);
 	flush_work(&cpuset_hotplug_work);
 
 	mutex_lock(&cpuset_mutex);
@@ -1645,6 +1661,8 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of,
 	free_trial_cpuset(trialcs);
 out_unlock:
 	mutex_unlock(&cpuset_mutex);
+	kernfs_unbreak_active_protection(of->kn);
+	css_put(&cs->css);
 	return retval ?: nbytes;
 }
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index a33d9a2bcbd7..b0c95f0f06fd 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -2320,7 +2320,7 @@ static void perf_event_context_sched_out(struct task_struct *task, int ctxn,
 	next_parent = rcu_dereference(next_ctx->parent_ctx);
 
 	/* If neither context have a parent context; they cannot be clones. */
-	if (!parent && !next_parent)
+	if (!parent || !next_parent)
 		goto unlock;
 
 	if (next_parent == ctx || next_ctx == parent || next_parent == parent) {
diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
index c445e392e93f..6f3254e8c137 100644
--- a/kernel/events/uprobes.c
+++ b/kernel/events/uprobes.c
@@ -846,7 +846,7 @@ static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *u
 {
 	int err;
 
-	if (!consumer_del(uprobe, uc))	/* WARN? */
+	if (WARN_ON(!consumer_del(uprobe, uc)))
 		return;
 
 	err = register_for_each_vma(uprobe, NULL);
@@ -927,7 +927,7 @@ int uprobe_apply(struct inode *inode, loff_t offset,
 	int ret = -ENOENT;
 
 	uprobe = find_uprobe(inode, offset);
-	if (!uprobe)
+	if (WARN_ON(!uprobe))
 		return ret;
 
 	down_write(&uprobe->register_rwsem);
@@ -952,7 +952,7 @@ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consume
 	struct uprobe *uprobe;
 
 	uprobe = find_uprobe(inode, offset);
-	if (!uprobe)
+	if (WARN_ON(!uprobe))
 		return;
 
 	down_write(&uprobe->register_rwsem);
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 7339e42a85ab..1487a123db5c 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -455,9 +455,9 @@ EXPORT_SYMBOL_GPL(irq_alloc_hwirqs);
  */
 void irq_free_hwirqs(unsigned int from, int cnt)
 {
-	int i;
+	int i, j;
 
-	for (i = from; cnt > 0; i++, cnt--) {
+	for (i = from, j = cnt; j > 0; i++, j--) {
 		irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE);
 		arch_teardown_hwirq(i);
 	}
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index ea2d5f6962ed..13e839dbca07 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -1416,9 +1416,10 @@ static int have_callable_console(void)
 /*
  * Can we actually use the console at this time on this cpu?
  *
- * Console drivers may assume that per-cpu resources have been allocated. So
- * unless they're explicitly marked as being able to cope (CON_ANYTIME) don't
- * call them until this CPU is officially up.
+ * Console drivers may assume that per-cpu resources have
+ * been allocated. So unless they're explicitly marked as
+ * being able to cope (CON_ANYTIME) don't call them until
+ * this CPU is officially up.
  */
 static inline int can_use_console(unsigned int cpu)
 {
@@ -1431,10 +1432,8 @@ static inline int can_use_console(unsigned int cpu)
  * console_lock held, and 'console_locked' set) if it
  * is successful, false otherwise.
  */
-static int console_trylock_for_printk(void)
+static int console_trylock_for_printk(unsigned int cpu)
 {
-	unsigned int cpu = smp_processor_id();
-
 	if (!console_trylock())
 		return 0;
 	/*
@@ -1609,8 +1608,7 @@ asmlinkage int vprintk_emit(int facility, int level,
 		 */
 		if (!oops_in_progress && !lockdep_recursing(current)) {
 			recursion_bug = 1;
-			local_irq_restore(flags);
-			return 0;
+			goto out_restore_irqs;
 		}
 		zap_locks();
 	}
@@ -1718,27 +1716,21 @@ asmlinkage int vprintk_emit(int facility, int level,
 
 	logbuf_cpu = UINT_MAX;
 	raw_spin_unlock(&logbuf_lock);
-	lockdep_on();
-	local_irq_restore(flags);
 
 	/* If called from the scheduler, we can not call up(). */
-	if (in_sched)
-		return printed_len;
-
-	/*
-	 * Disable preemption to avoid being preempted while holding
-	 * console_sem which would prevent anyone from printing to console
-	 */
-	preempt_disable();
-	/*
-	 * Try to acquire and then immediately release the console semaphore.
-	 * The release will print out buffers and wake up /dev/kmsg and syslog()
-	 * users.
-	 */
-	if (console_trylock_for_printk())
-		console_unlock();
-	preempt_enable();
+	if (!in_sched) {
+		/*
+		 * Try to acquire and then immediately release the console
+		 * semaphore.  The release will print out buffers and wake up
+		 * /dev/kmsg and syslog() users.
+		 */
+		if (console_trylock_for_printk(this_cpu))
+			console_unlock();
+	}
 
+	lockdep_on();
+out_restore_irqs:
+	local_irq_restore(flags);
 	return printed_len;
 }
 EXPORT_SYMBOL(vprintk_emit);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 384ede311717..f243444a3772 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1396,7 +1396,6 @@ void tracing_start(void)
 
 	arch_spin_unlock(&global_trace.max_lock);
 
-	ftrace_start();
  out:
 	raw_spin_unlock_irqrestore(&global_trace.start_lock, flags);
 }
@@ -1443,7 +1442,6 @@ void tracing_stop(void)
 	struct ring_buffer *buffer;
 	unsigned long flags;
 
-	ftrace_stop();
 	raw_spin_lock_irqsave(&global_trace.start_lock, flags);
 	if (global_trace.stop_count++)
 		goto out;
diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c
index 04fdb5de823c..3c9b97e6b1f4 100644
--- a/kernel/trace/trace_uprobe.c
+++ b/kernel/trace/trace_uprobe.c
@@ -893,6 +893,9 @@ probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file,
 	int ret;
 
 	if (file) {
+		if (tu->tp.flags & TP_FLAG_PROFILE)
+			return -EINTR;
+
 		link = kmalloc(sizeof(*link), GFP_KERNEL);
 		if (!link)
 			return -ENOMEM;
@@ -901,29 +904,40 @@ probe_event_enable(struct trace_uprobe *tu, struct ftrace_event_file *file,
 		list_add_tail_rcu(&link->list, &tu->tp.files);
 
 		tu->tp.flags |= TP_FLAG_TRACE;
-	} else
-		tu->tp.flags |= TP_FLAG_PROFILE;
+	} else {
+		if (tu->tp.flags & TP_FLAG_TRACE)
+			return -EINTR;
 
-	ret = uprobe_buffer_enable();
-	if (ret < 0)
-		return ret;
+		tu->tp.flags |= TP_FLAG_PROFILE;
+	}
 
 	WARN_ON(!uprobe_filter_is_empty(&tu->filter));
 
 	if (enabled)
 		return 0;
 
+	ret = uprobe_buffer_enable();
+	if (ret)
+		goto err_flags;
+
 	tu->consumer.filter = filter;
 	ret = uprobe_register(tu->inode, tu->offset, &tu->consumer);
-	if (ret) {
-		if (file) {
-			list_del(&link->list);
-			kfree(link);
-			tu->tp.flags &= ~TP_FLAG_TRACE;
-		} else
-			tu->tp.flags &= ~TP_FLAG_PROFILE;
-	}
+	if (ret)
+		goto err_buffer;
 
+	return 0;
+
+ err_buffer:
+	uprobe_buffer_disable();
+
+ err_flags:
+	if (file) {
+		list_del(&link->list);
+		kfree(link);
+		tu->tp.flags &= ~TP_FLAG_TRACE;
+	} else {
+		tu->tp.flags &= ~TP_FLAG_PROFILE;
+	}
 	return ret;
 }
 
@@ -1201,12 +1215,6 @@ static int uprobe_dispatcher(struct uprobe_consumer *con, struct pt_regs *regs)
 
 	current->utask->vaddr = (unsigned long) &udd;
 
-#ifdef CONFIG_PERF_EVENTS
-	if ((tu->tp.flags & TP_FLAG_TRACE) == 0 &&
-	    !uprobe_perf_filter(&tu->consumer, 0, current->mm))
-		return UPROBE_HANDLER_REMOVE;
-#endif
-
 	if (WARN_ON_ONCE(!uprobe_cpu_buffer))
 		return 0;
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 6203d2900877..35974ac69600 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -3284,6 +3284,7 @@ int workqueue_sysfs_register(struct workqueue_struct *wq)
 		}
 	}
 
+	dev_set_uevent_suppress(&wq_dev->dev, false);
 	kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD);
 	return 0;
 }
@@ -4879,7 +4880,7 @@ static void __init wq_numa_init(void)
 	BUG_ON(!tbl);
 
 	for_each_node(node)
-		BUG_ON(!alloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
+		BUG_ON(!zalloc_cpumask_var_node(&tbl[node], GFP_KERNEL,
 				node_online(node) ? node : NUMA_NO_NODE));
 
 	for_each_possible_cpu(cpu) {