sched: replace PF_THREAD_BOUND with PF_NO_SETAFFINITY

PF_THREAD_BOUND was originally used to mark kernel threads which were
bound to a specific CPU using kthread_bind() and a task with the flag
set allows cpus_allowed modifications only to itself.  Workqueue is
currently abusing it to prevent userland from meddling with
cpus_allowed of workqueue workers.

What we need is a flag to prevent userland from messing with
cpus_allowed of certain kernel tasks.  In kernel, anyone can
(incorrectly) squash the flag, and, for worker-type usages,
restricting cpus_allowed modification to the task itself doesn't
provide meaningful extra proection as other tasks can inject work
items to the task anyway.

This patch replaces PF_THREAD_BOUND with PF_NO_SETAFFINITY.
sched_setaffinity() checks the flag and return -EINVAL if set.
set_cpus_allowed_ptr() is no longer affected by the flag.

This will allow simplifying workqueue worker CPU affinity management.
Signed-off-by: NTejun Heo <tj@kernel.org>
Acked-by: NIngo Molnar <mingo@kernel.org>
Reviewed-by: NLai Jiangshan <laijs@cn.fujitsu.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>

include/linux/sched.h

@@ -1793,7 +1793,7 @@ extern void thread_group_cputime_adjusted(struct task_struct *p, cputime_t *ut,
 #define PF_SWAPWRITE	0x00800000	/* Allowed to write to swap */
 #define PF_SPREAD_PAGE	0x01000000	/* Spread page cache over cpuset */
 #define PF_SPREAD_SLAB	0x02000000	/* Spread some slab caches over cpuset */
-#define PF_THREAD_BOUND	0x04000000	/* Thread bound to specific cpu */
+#define PF_NO_SETAFFINITY 0x04000000	/* Userland is not allowed to meddle with cpus_allowed */
 #define PF_MCE_EARLY    0x08000000      /* Early kill for mce process policy */
 #define PF_MEMPOLICY	0x10000000	/* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER	0x20000000	/* Thread belongs to the rt mutex tester */

kernel/cgroup.c

@@ -2224,11 +2224,11 @@ retry_find_task:
 		tsk = tsk->group_leader;
 
 	/*
-	 * Workqueue threads may acquire PF_THREAD_BOUND and become
+	 * Workqueue threads may acquire PF_NO_SETAFFINITY and become
 	 * trapped in a cpuset, or RT worker may be born in a cgroup
 	 * with no rt_runtime allocated.  Just say no.
 	 */
-	if (tsk == kthreadd_task || (tsk->flags & PF_THREAD_BOUND)) {
+	if (tsk == kthreadd_task || (tsk->flags & PF_NO_SETAFFINITY)) {
 		ret = -EINVAL;
 		rcu_read_unlock();
 		goto out_unlock_cgroup;

kernel/cpuset.c

@@ -1388,16 +1388,16 @@ static int cpuset_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
 
 	cgroup_taskset_for_each(task, cgrp, tset) {
 		/*
-		 * Kthreads bound to specific cpus cannot be moved to a new
-		 * cpuset; we cannot change their cpu affinity and
-		 * isolating such threads by their set of allowed nodes is
-		 * unnecessary.  Thus, cpusets are not applicable for such
-		 * threads.  This prevents checking for success of
-		 * set_cpus_allowed_ptr() on all attached tasks before
-		 * cpus_allowed may be changed.
+		 * Kthreads which disallow setaffinity shouldn't be moved
+		 * to a new cpuset; we don't want to change their cpu
+		 * affinity and isolating such threads by their set of
+		 * allowed nodes is unnecessary.  Thus, cpusets are not
+		 * applicable for such threads.  This prevents checking for
+		 * success of set_cpus_allowed_ptr() on all attached tasks
+		 * before cpus_allowed may be changed.
 		 */
 		ret = -EINVAL;
-		if (task->flags & PF_THREAD_BOUND)
+		if (task->flags & PF_NO_SETAFFINITY)
 			goto out_unlock;
 		ret = security_task_setscheduler(task);
 		if (ret)

kernel/kthread.c

@@ -260,7 +260,7 @@ static void __kthread_bind(struct task_struct *p, unsigned int cpu)
 {
 	/* It's safe because the task is inactive. */
 	do_set_cpus_allowed(p, cpumask_of(cpu));
-	p->flags |= PF_THREAD_BOUND;
+	p->flags |= PF_NO_SETAFFINITY;
 }
 
 /**

kernel/sched/core.c

@@ -4126,6 +4126,10 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
 	get_task_struct(p);
 	rcu_read_unlock();
 
+	if (p->flags & PF_NO_SETAFFINITY) {
+		retval = -EINVAL;
+		goto out_put_task;
+	}
 	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL)) {
 		retval = -ENOMEM;
 		goto out_put_task;
@@ -4773,11 +4777,6 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 		goto out;
 	}
 
-	if (unlikely((p->flags & PF_THREAD_BOUND) && p != current)) {
-		ret = -EINVAL;
-		goto out;
-	}
-
 	do_set_cpus_allowed(p, new_mask);
 
 	/* Can the task run on the task's current CPU? If so, we're done */

kernel/workqueue.c

@@ -1757,12 +1757,8 @@ static struct worker *create_worker(struct worker_pool *pool)
 	set_user_nice(worker->task, pool->attrs->nice);
 	set_cpus_allowed_ptr(worker->task, pool->attrs->cpumask);
 
-	/*
-	 * %PF_THREAD_BOUND is used to prevent userland from meddling with
-	 * cpumask of workqueue workers.  This is an abuse.  We need
-	 * %PF_NO_SETAFFINITY.
-	 */
-	worker->task->flags |= PF_THREAD_BOUND;
+	/* prevent userland from meddling with cpumask of workqueue workers */
+	worker->task->flags |= PF_NO_SETAFFINITY;
 
 	/*
 	 * The caller is responsible for ensuring %POOL_DISASSOCIATED
@@ -3876,7 +3872,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *fmt,
 		}
 
 		wq->rescuer = rescuer;
-		rescuer->task->flags |= PF_THREAD_BOUND;
+		rescuer->task->flags |= PF_NO_SETAFFINITY;
 		wake_up_process(rescuer->task);
 	}