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: Tejun Heo <tj@kernel.org>
Acked-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
diff --git a/include/linux/sched.h b/include/linux/sched.h
index d35d2b6..e5c64f7 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1793,7 +1793,7 @@
#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 */
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index a32f943..3852d92 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -2224,11 +2224,11 @@
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;
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 4f9dfe4..f22e947 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1388,16 +1388,16 @@
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)
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 691dc2e..a2fbbb7 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -260,7 +260,7 @@
{
/* 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;
}
/**
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 7f12624a..23606ee 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -4126,6 +4126,10 @@
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 @@
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 */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 969be0b..39a591f 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1757,12 +1757,8 @@
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 @@
}
wq->rescuer = rescuer;
- rescuer->task->flags |= PF_THREAD_BOUND;
+ rescuer->task->flags |= PF_NO_SETAFFINITY;
wake_up_process(rescuer->task);
}