Commit db3b02ae authored by Will Deacon's avatar Will Deacon Committed by Peter Zijlstra
Browse files

sched: Split the guts of sched_setaffinity() into a helper function 



In preparation for replaying user affinity requests using a saved mask,
split sched_setaffinity() up so that the initial task lookup and
security checks are only performed when the request is coming directly
from userspace.

Signed-off-by: default avatarWill Deacon <will@kernel.org>
Signed-off-by: default avatarPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: default avatarValentin Schneider <Valentin.Schneider@arm.com>
Link: https://lore.kernel.org/r/20210730112443.23245-8-will@kernel.org
parent b90ca8ba

kernel/sched/core.c

+57 −48
Original line number Diff line number Diff line
@@ -7594,53 +7594,22 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr, 
	return retval;

}



long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)

static int

__sched_setaffinity(struct task_struct *p, const struct cpumask *mask)

{

	cpumask_var_t cpus_allowed, new_mask;

	struct task_struct *p;

	int retval;

	cpumask_var_t cpus_allowed, new_mask;



	rcu_read_lock();



	p = find_process_by_pid(pid);

	if (!p) {

		rcu_read_unlock();

		return -ESRCH;

	}



	/* Prevent p going away */

	get_task_struct(p);

	rcu_read_unlock();

	if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL))

		return -ENOMEM;



	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;

	}

	if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {

		retval = -ENOMEM;

		goto out_free_cpus_allowed;

	}

	retval = -EPERM;

	if (!check_same_owner(p)) {

		rcu_read_lock();

		if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {

			rcu_read_unlock();

			goto out_free_new_mask;

		}

		rcu_read_unlock();

	}



	retval = security_task_setscheduler(p);

	if (retval)

		goto out_free_new_mask;





	cpuset_cpus_allowed(p, cpus_allowed);

	cpumask_and(new_mask, in_mask, cpus_allowed);

	cpumask_and(new_mask, mask, cpus_allowed);



	/*

	 * Since bandwidth control happens on root_domain basis,
@@ -7661,23 +7630,63 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) 
#endif

again:

	retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK);

	if (retval)

		goto out_free_new_mask;



	if (!retval) {

	cpuset_cpus_allowed(p, cpus_allowed);

	if (!cpumask_subset(new_mask, cpus_allowed)) {

		/*

			 * We must have raced with a concurrent cpuset

			 * update. Just reset the cpus_allowed to the

			 * cpuset's cpus_allowed

		 * We must have raced with a concurrent cpuset update.

		 * Just reset the cpumask to the cpuset's cpus_allowed.

		 */

		cpumask_copy(new_mask, cpus_allowed);

		goto again;

	}

	}



out_free_new_mask:

	free_cpumask_var(new_mask);

out_free_cpus_allowed:

	free_cpumask_var(cpus_allowed);

	return retval;

}



long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)

{

	struct task_struct *p;

	int retval;



	rcu_read_lock();



	p = find_process_by_pid(pid);

	if (!p) {

		rcu_read_unlock();

		return -ESRCH;

	}



	/* Prevent p going away */

	get_task_struct(p);

	rcu_read_unlock();



	if (p->flags & PF_NO_SETAFFINITY) {

		retval = -EINVAL;

		goto out_put_task;

	}



	if (!check_same_owner(p)) {

		rcu_read_lock();

		if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE)) {

			rcu_read_unlock();

			retval = -EPERM;

			goto out_put_task;

		}

		rcu_read_unlock();

	}



	retval = security_task_setscheduler(p);

	if (retval)

		goto out_put_task;



	retval = __sched_setaffinity(p, in_mask);

out_put_task:

	put_task_struct(p);

	return retval;