summaryrefslogtreecommitdiff
path: root/kernel/cpuset.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2010-05-18 08:27:54 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2010-05-18 08:27:54 -0700
commitb8ae30ee26d379db436b0b8c8c3ff1b52f69e5d1 (patch)
tree506aa0b4bdbf90f61e7e9261c7db90aa1452dcce /kernel/cpuset.c
parent4d7b4ac22fbec1a03206c6cde353f2fd6942f828 (diff)
parent9c6f7e43b4e02c161b53e97ba913855246876c61 (diff)
Merge branch 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (49 commits) stop_machine: Move local variable closer to the usage site in cpu_stop_cpu_callback() sched, wait: Use wrapper functions sched: Remove a stale comment ondemand: Make the iowait-is-busy time a sysfs tunable ondemand: Solve a big performance issue by counting IOWAIT time as busy sched: Intoduce get_cpu_iowait_time_us() sched: Eliminate the ts->idle_lastupdate field sched: Fold updating of the last_update_time_info into update_ts_time_stats() sched: Update the idle statistics in get_cpu_idle_time_us() sched: Introduce a function to update the idle statistics sched: Add a comment to get_cpu_idle_time_us() cpu_stop: add dummy implementation for UP sched: Remove rq argument to the tracepoints rcu: need barrier() in UP synchronize_sched_expedited() sched: correctly place paranioa memory barriers in synchronize_sched_expedited() sched: kill paranoia check in synchronize_sched_expedited() sched: replace migration_thread with cpu_stop stop_machine: reimplement using cpu_stop cpu_stop: implement stop_cpu[s]() sched: Fix select_idle_sibling() logic in select_task_rq_fair() ...
Diffstat (limited to 'kernel/cpuset.c')
-rw-r--r--kernel/cpuset.c67
1 files changed, 42 insertions, 25 deletions
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index d10946748ec2..9a50c5f6e727 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -2182,19 +2182,52 @@ void __init cpuset_init_smp(void)
void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
{
mutex_lock(&callback_mutex);
- cpuset_cpus_allowed_locked(tsk, pmask);
+ task_lock(tsk);
+ guarantee_online_cpus(task_cs(tsk), pmask);
+ task_unlock(tsk);
mutex_unlock(&callback_mutex);
}
-/**
- * cpuset_cpus_allowed_locked - return cpus_allowed mask from a tasks cpuset.
- * Must be called with callback_mutex held.
- **/
-void cpuset_cpus_allowed_locked(struct task_struct *tsk, struct cpumask *pmask)
+int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
{
- task_lock(tsk);
- guarantee_online_cpus(task_cs(tsk), pmask);
- task_unlock(tsk);
+ const struct cpuset *cs;
+ int cpu;
+
+ rcu_read_lock();
+ cs = task_cs(tsk);
+ if (cs)
+ cpumask_copy(&tsk->cpus_allowed, cs->cpus_allowed);
+ rcu_read_unlock();
+
+ /*
+ * We own tsk->cpus_allowed, nobody can change it under us.
+ *
+ * But we used cs && cs->cpus_allowed lockless and thus can
+ * race with cgroup_attach_task() or update_cpumask() and get
+ * the wrong tsk->cpus_allowed. However, both cases imply the
+ * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr()
+ * which takes task_rq_lock().
+ *
+ * If we are called after it dropped the lock we must see all
+ * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary
+ * set any mask even if it is not right from task_cs() pov,
+ * the pending set_cpus_allowed_ptr() will fix things.
+ */
+
+ cpu = cpumask_any_and(&tsk->cpus_allowed, cpu_active_mask);
+ if (cpu >= nr_cpu_ids) {
+ /*
+ * Either tsk->cpus_allowed is wrong (see above) or it
+ * is actually empty. The latter case is only possible
+ * if we are racing with remove_tasks_in_empty_cpuset().
+ * Like above we can temporary set any mask and rely on
+ * set_cpus_allowed_ptr() as synchronization point.
+ */
+ cpumask_copy(&tsk->cpus_allowed, cpu_possible_mask);
+ cpu = cpumask_any(cpu_active_mask);
+ }
+
+ return cpu;
}
void cpuset_init_current_mems_allowed(void)
@@ -2383,22 +2416,6 @@ int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
}
/**
- * cpuset_lock - lock out any changes to cpuset structures
- *
- * The out of memory (oom) code needs to mutex_lock cpusets
- * from being changed while it scans the tasklist looking for a
- * task in an overlapping cpuset. Expose callback_mutex via this
- * cpuset_lock() routine, so the oom code can lock it, before
- * locking the task list. The tasklist_lock is a spinlock, so
- * must be taken inside callback_mutex.
- */
-
-void cpuset_lock(void)
-{
- mutex_lock(&callback_mutex);
-}
-
-/**
* cpuset_unlock - release lock on cpuset changes
*
* Undo the lock taken in a previous cpuset_lock() call.