Donate to e Foundation | Murena handsets with /e/OS | Own a part of Murena! Learn more

Commit 897f0b3c authored by Oleg Nesterov's avatar Oleg Nesterov Committed by Ingo Molnar
Browse files

sched: Kill the broken and deadlockable cpuset_lock/cpuset_cpus_allowed_locked code 



This patch just states the fact the cpusets/cpuhotplug interaction is
broken and removes the deadlockable code which only pretends to work.

- cpuset_lock() doesn't really work. It is needed for
  cpuset_cpus_allowed_locked() but we can't take this lock in
  try_to_wake_up()->select_fallback_rq() path.

- cpuset_lock() is deadlockable. Suppose that a task T bound to CPU takes
  callback_mutex. If cpu_down(CPU) happens before T drops callback_mutex
  stop_machine() preempts T, then migration_call(CPU_DEAD) tries to take
  cpuset_lock() and hangs forever because CPU is already dead and thus
  T can't be scheduled.

- cpuset_cpus_allowed_locked() is deadlockable too. It takes task_lock()
  which is not irq-safe, but try_to_wake_up() can be called from irq.

Kill them, and change select_fallback_rq() to use cpu_possible_mask, like
we currently do without CONFIG_CPUSETS.

Also, with or without this patch, with or without CONFIG_CPUSETS, the
callers of select_fallback_rq() can race with each other or with
set_cpus_allowed() pathes.

The subsequent patches try to to fix these problems.

Signed-off-by: default avatarOleg Nesterov <oleg@redhat.com>
Signed-off-by: default avatarPeter Zijlstra <a.p.zijlstra@chello.nl>
LKML-Reference: <20100315091003.GA9123@redhat.com>
Signed-off-by: default avatarIngo Molnar <mingo@elte.hu>
parent 25c2d55c

include/linux/cpuset.h

+0 −13
Original line number Diff line number Diff line
@@ -21,8 +21,6 @@ extern int number_of_cpusets; /* How many cpusets are defined in system? */ 
extern int cpuset_init(void);

extern void cpuset_init_smp(void);

extern void cpuset_cpus_allowed(struct task_struct *p, struct cpumask *mask);

extern void cpuset_cpus_allowed_locked(struct task_struct *p,

				       struct cpumask *mask);

extern nodemask_t cpuset_mems_allowed(struct task_struct *p);

#define cpuset_current_mems_allowed (current->mems_allowed)

void cpuset_init_current_mems_allowed(void);
@@ -69,9 +67,6 @@ struct seq_file; 
extern void cpuset_task_status_allowed(struct seq_file *m,

					struct task_struct *task);



extern void cpuset_lock(void);

extern void cpuset_unlock(void);



extern int cpuset_mem_spread_node(void);



static inline int cpuset_do_page_mem_spread(void)
@@ -105,11 +100,6 @@ static inline void cpuset_cpus_allowed(struct task_struct *p, 
{

	cpumask_copy(mask, cpu_possible_mask);

}

static inline void cpuset_cpus_allowed_locked(struct task_struct *p,

					      struct cpumask *mask)

{

	cpumask_copy(mask, cpu_possible_mask);

}



static inline nodemask_t cpuset_mems_allowed(struct task_struct *p)

{
@@ -157,9 +147,6 @@ static inline void cpuset_task_status_allowed(struct seq_file *m, 
{

}



static inline void cpuset_lock(void) {}

static inline void cpuset_unlock(void) {}



static inline int cpuset_mem_spread_node(void)

{

	return 0;

kernel/cpuset.c

+1 −26
Original line number Diff line number Diff line
@@ -2182,19 +2182,10 @@ void __init cpuset_init_smp(void) 
void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)

{

	mutex_lock(&callback_mutex);

	cpuset_cpus_allowed_locked(tsk, pmask);

	mutex_unlock(&callback_mutex);

}



/**

 * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset.

 * Must be called with callback_mutex held.

 **/

void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask)

{

	task_lock(tsk);

	guarantee_online_cpus(task_cs(tsk), pmask);

	task_unlock(tsk);

	mutex_unlock(&callback_mutex);

}



void cpuset_init_current_mems_allowed(void)
@@ -2382,22 +2373,6 @@ int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask) 
	return 0;

}



/**

 * cpuset_lock - lock out any changes to cpuset structures

 *

 * The out of memory (oom) code needs to mutex_lock cpusets

 * from being changed while it scans the tasklist looking for a

 * task in an overlapping cpuset.  Expose callback_mutex via this

 * cpuset_lock() routine, so the oom code can lock it, before

 * locking the task list.  The tasklist_lock is a spinlock, so

 * must be taken inside callback_mutex.

 */



void cpuset_lock(void)

{

	mutex_lock(&callback_mutex);

}



/**

 * cpuset_unlock - release lock on cpuset changes

 *

kernel/sched.c

+3 −7
Original line number Diff line number Diff line
@@ -2296,11 +2296,9 @@ static int select_fallback_rq(int cpu, struct task_struct *p) 
		return dest_cpu;



	/* No more Mr. Nice Guy. */

	if (dest_cpu >= nr_cpu_ids) {

		rcu_read_lock();

		cpuset_cpus_allowed_locked(p, &p->cpus_allowed);

		rcu_read_unlock();

		dest_cpu = cpumask_any_and(cpu_active_mask, &p->cpus_allowed);

	if (unlikely(dest_cpu >= nr_cpu_ids)) {

		cpumask_copy(&p->cpus_allowed, cpu_possible_mask);

		dest_cpu = cpumask_any(cpu_active_mask);



		/*

		 * Don't tell them about moving exiting tasks or
@@ -5866,7 +5864,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) 


	case CPU_DEAD:

	case CPU_DEAD_FROZEN:

		cpuset_lock(); /* around calls to cpuset_cpus_allowed_lock() */

		migrate_live_tasks(cpu);

		rq = cpu_rq(cpu);

		kthread_stop(rq->migration_thread);
@@ -5879,7 +5876,6 @@ migration_call(struct notifier_block *nfb, unsigned long action, void *hcpu) 
		rq->idle->sched_class = &idle_sched_class;

		migrate_dead_tasks(cpu);

		raw_spin_unlock_irq(&rq->lock);

		cpuset_unlock();

		migrate_nr_uninterruptible(rq);

		BUG_ON(rq->nr_running != 0);

		calc_global_load_remove(rq);