cgroup/cpuset: Introduce cpuset_cpus_allowed_locked()

cpuset_cpus_allowed() uses a reader lock that is sleepable under RT,
which means it cannot be called inside raw_spin_lock_t context.

Introduce a new cpuset_cpus_allowed_locked() helper that performs the
same function as cpuset_cpus_allowed() except that the caller must have
acquired the cpuset_mutex so that no further locking will be needed.

Suggested-by: Waiman Long <[email protected]>
Signed-off-by: Pingfan Liu <[email protected]>
Cc: Waiman Long <[email protected]>
Cc: Tejun Heo <[email protected]>
Cc: Johannes Weiner <[email protected]>
Cc: Michal Koutný <[email protected]>
Cc: [email protected]
To: [email protected]
Reviewed-by: Chen Ridong <[email protected]>
Reviewed-by: Waiman Long <[email protected]>
Signed-off-by: Tejun Heo <[email protected]>

Author: Pingfan Liu

include/linux/cpuset.h

@@ -74,6 +74,7 @@ extern void inc_dl_tasks_cs(struct task_struct *task);
 extern void dec_dl_tasks_cs(struct task_struct *task);
 extern void cpuset_lock(void);
 extern void cpuset_unlock(void);
+extern void cpuset_cpus_allowed_locked(struct task_struct *p, struct cpumask *mask);
 extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);
 extern bool cpuset_cpus_allowed_fallback(struct task_struct *p);
 extern bool cpuset_cpu_is_isolated(int cpu);
@@ -195,10 +196,16 @@ static inline void dec_dl_tasks_cs(struct task_struct *task) { }
 static inline void cpuset_lock(void) { }
 static inline void cpuset_unlock(void) { }
 
+static inline void cpuset_cpus_allowed_locked(struct task_struct *p,
+					struct cpumask *mask)
+{
+	cpumask_copy(mask, task_cpu_possible_mask(p));
+}
+
 static inline void cpuset_cpus_allowed(struct task_struct *p,
 				       struct cpumask *mask)
 {
-	cpumask_copy(mask, task_cpu_possible_mask(p));
+	cpuset_cpus_allowed_locked(p, mask);
 }
 
 static inline bool cpuset_cpus_allowed_fallback(struct task_struct *p)

kernel/cgroup/cpuset.c

@@ -4160,24 +4160,13 @@ void __init cpuset_init_smp(void)
 	BUG_ON(!cpuset_migrate_mm_wq);
 }
 
-/**
- * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset.
- * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
- * @pmask: pointer to struct cpumask variable to receive cpus_allowed set.
- *
- * Description: Returns the cpumask_var_t cpus_allowed of the cpuset
- * attached to the specified @tsk.  Guaranteed to return some non-empty
- * subset of cpu_active_mask, even if this means going outside the
- * tasks cpuset, except when the task is in the top cpuset.
- **/
-
-void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
+/*
+ * Return cpus_allowed mask from a task's cpuset.
+ */
+static void __cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask)
 {
-	unsigned long flags;
 	struct cpuset *cs;
 
-	spin_lock_irqsave(&callback_lock, flags);
-
 	cs = task_cs(tsk);
 	if (cs != &top_cpuset)
 		guarantee_active_cpus(tsk, pmask);
@@ -4197,7 +4186,39 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
 		if (!cpumask_intersects(pmask, cpu_active_mask))
 			cpumask_copy(pmask, possible_mask);
 	}
+}
 
+/**
+ * cpuset_cpus_allowed_locked - return cpus_allowed mask from a task's cpuset.
+ * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
+ * @pmask: pointer to struct cpumask variable to receive cpus_allowed set.
+ *
+ * Similir to cpuset_cpus_allowed() except that the caller must have acquired
+ * cpuset_mutex.
+ */
+void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask)
+{
+	lockdep_assert_held(&cpuset_mutex);
+	__cpuset_cpus_allowed_locked(tsk, pmask);
+}
+
+/**
+ * cpuset_cpus_allowed - return cpus_allowed mask from a task's cpuset.
+ * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed.
+ * @pmask: pointer to struct cpumask variable to receive cpus_allowed set.
+ *
+ * Description: Returns the cpumask_var_t cpus_allowed of the cpuset
+ * attached to the specified @tsk.  Guaranteed to return some non-empty
+ * subset of cpu_active_mask, even if this means going outside the
+ * tasks cpuset, except when the task is in the top cpuset.
+ **/
+
+void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&callback_lock, flags);
+	__cpuset_cpus_allowed_locked(tsk, pmask);
 	spin_unlock_irqrestore(&callback_lock, flags);
 }