sched: prevent bound kthreads from changing cpus_allowed

Kthreads that have called kthread_bind() are bound to specific cpus, so
other tasks should not be able to change their cpus_allowed from under
them.  Otherwise, it is possible to move kthreads, such as the migration
or software watchdog threads, so they are not allowed access to the cpu
they work on.

Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Menage <menage@google.com>
Cc: Paul Jackson <pj@sgi.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

4 files changed, 21 insertions, 1 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index d25acf600a32..2db1485f865d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1486,6 +1486,7 @@ static inline void put_task_struct(struct task_struct *t)
 #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_MEMPOLICY    0x10000000      /* Non-default NUMA mempolicy */
 #define PF_MUTEX_TESTER 0x20000000      /* Thread belongs to the rt mutex tester */
 #define PF_FREEZER_SKIP 0x40000000      /* Freezer should not count it as freezeable */
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 6090d18b58a9..b84354f4de36 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -1190,6 +1190,15 @@ static int cpuset_can_attach(struct cgroup_subsys *ss,
 
         if (cpus_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
                 return -ENOSPC;
+        if (tsk->flags & PF_THREAD_BOUND) {
+                cpumask_t mask;
+
+                mutex_lock(&callback_mutex);
+                mask = cs->cpus_allowed;
+                mutex_unlock(&callback_mutex);
+                if (!cpus_equal(tsk->cpus_allowed, mask))
+                        return -EINVAL;
+        }
 
         return security_task_setscheduler(tsk, 0, NULL);
 }
@@ -1203,11 +1212,14 @@ static void cpuset_attach(struct cgroup_subsys *ss,
         struct mm_struct *mm;
         struct cpuset *cs = cgroup_cs(cont);
         struct cpuset *oldcs = cgroup_cs(oldcont);
+        int err;
 
         mutex_lock(&callback_mutex);
         guarantee_online_cpus(cs, &cpus);
-        set_cpus_allowed_ptr(tsk, &cpus);
+        err = set_cpus_allowed_ptr(tsk, &cpus);
         mutex_unlock(&callback_mutex);
+        if (err)
+                return;
 
         from = oldcs->mems_allowed;
         to = cs->mems_allowed;
diff --git a/kernel/kthread.c b/kernel/kthread.c
index bd1b9ea024e1..97747cdd37c9 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -180,6 +180,7 @@ void kthread_bind(struct task_struct *k, unsigned int cpu)
         set_task_cpu(k, cpu);
         k->cpus_allowed = cpumask_of_cpu(cpu);
         k->rt.nr_cpus_allowed = 1;
+        k->flags |= PF_THREAD_BOUND;
 }
 EXPORT_SYMBOL(kthread_bind);
 
diff --git a/kernel/sched.c b/kernel/sched.c
index e9c24a128655..164fe7fe0d89 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -5563,6 +5563,12 @@ int set_cpus_allowed_ptr(struct task_struct *p, const cpumask_t *new_mask)
                 goto out;
         }
 
+        if (unlikely((p->flags & PF_THREAD_BOUND) && p != current &&
+                     !cpus_equal(p->cpus_allowed, *new_mask))) {
+                ret = -EINVAL;
+                goto out;
+        }
+
         if (p->sched_class->set_cpus_allowed)
                 p->sched_class->set_cpus_allowed(p, new_mask);
         else {