cpuset: Call set_cpus_allowed_ptr() with appropriate mask for task

set_cpus_allowed_ptr() will fail with -EINVAL if the requested
affinity mask is not a subset of the task_cpu_possible_mask() for the
task being updated. Consequently, on a heterogeneous system with cpusets
spanning the different CPU types, updates to the cgroup hierarchy can
silently fail to update task affinities when the effective affinity
mask for the cpuset is expanded.

For example, consider an arm64 system with 4 CPUs, where CPUs 2-3 are
the only cores capable of executing 32-bit tasks. Attaching a 32-bit
task to a cpuset containing CPUs 0-2 will correctly affine the task to
CPU 2. Extending the cpuset to CPUs 0-3, however, will fail to extend
the affinity mask of the 32-bit task because update_tasks_cpumask() will
pass the full 0-3 mask to set_cpus_allowed_ptr().

Extend update_tasks_cpumask() to take a temporary 'cpumask' paramater
and use it to mask the 'effective_cpus' mask with the possible mask for
each task being updated.

Fixes: 431c69fac05b ("cpuset: Honour task_cpu_possible_mask() in guarantee_online_cpus()")
Signed-off-by: Will Deacon <will@kernel.org>
Acked-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>

diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
index 528285a91499b521a1fe8c4a7ef917d4e73e3604..ca826bd1eba33205963ec14d07d824c651525d85 100644 (file)
--- a/kernel/cgroup/cpuset.c
+++ b/kernel/cgroup/cpuset.c
@@ -1205,12 +1205,13 @@ void rebuild_sched_domains(void)
 /**
  * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset.
  * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed
+ * @new_cpus: the temp variable for the new effective_cpus mask
  *
  * Iterate through each task of @cs updating its cpus_allowed to the
  * effective cpuset's.  As this function is called with cpuset_rwsem held,
  * cpuset membership stays stable.
  */
-static void update_tasks_cpumask(struct cpuset *cs)
+static void update_tasks_cpumask(struct cpuset *cs, struct cpumask *new_cpus)
 {
        struct css_task_iter it;
        struct task_struct *task;
@@ -1224,7 +1225,10 @@ static void update_tasks_cpumask(struct cpuset *cs)
                if (top_cs && (task->flags & PF_KTHREAD) &&
                    kthread_is_per_cpu(task))
                        continue;
-               set_cpus_allowed_ptr(task, cs->effective_cpus);
+
+               cpumask_and(new_cpus, cs->effective_cpus,
+                           task_cpu_possible_mask(task));
+               set_cpus_allowed_ptr(task, new_cpus);
        }
        css_task_iter_end(&it);
 }
@@ -1509,7 +1513,7 @@ static int update_parent_subparts_cpumask(struct cpuset *cs, int cmd,
        spin_unlock_irq(&callback_lock);
 
        if (adding || deleting)
-               update_tasks_cpumask(parent);
+               update_tasks_cpumask(parent, tmp->new_cpus);
 
        /*
         * Set or clear CS_SCHED_LOAD_BALANCE when partcmd_update, if necessary.
@@ -1661,7 +1665,7 @@ update_parent_subparts:
                WARN_ON(!is_in_v2_mode() &&
                        !cpumask_equal(cp->cpus_allowed, cp->effective_cpus));
 
-               update_tasks_cpumask(cp);
+               update_tasks_cpumask(cp, tmp->new_cpus);
 
                /*
                 * On legacy hierarchy, if the effective cpumask of any non-
@@ -2309,7 +2313,7 @@ static int update_prstate(struct cpuset *cs, int new_prs)
                }
        }
 
-       update_tasks_cpumask(parent);
+       update_tasks_cpumask(parent, tmpmask.new_cpus);
 
        if (parent->child_ecpus_count)
                update_sibling_cpumasks(parent, cs, &tmpmask);
@@ -3348,7 +3352,7 @@ hotplug_update_tasks_legacy(struct cpuset *cs,
         * as the tasks will be migrated to an ancestor.
         */
        if (cpus_updated && !cpumask_empty(cs->cpus_allowed))
-               update_tasks_cpumask(cs);
+               update_tasks_cpumask(cs, new_cpus);
        if (mems_updated && !nodes_empty(cs->mems_allowed))
                update_tasks_nodemask(cs);
 
@@ -3385,7 +3389,7 @@ hotplug_update_tasks(struct cpuset *cs,
        spin_unlock_irq(&callback_lock);
 
        if (cpus_updated)
-               update_tasks_cpumask(cs);
+               update_tasks_cpumask(cs, new_cpus);
        if (mems_updated)
                update_tasks_nodemask(cs);
 }