struct cpuset, css);
}
+#ifdef CONFIG_NUMA
+static inline bool task_has_mempolicy(struct task_struct *task)
+{
+ return task->mempolicy;
+}
+#else
+static inline bool task_has_mempolicy(struct task_struct *task)
+{
+ return false;
+}
+#endif
+
+
/* bits in struct cpuset flags field */
typedef enum {
CS_CPU_EXCLUSIVE,
* are online. If none are online, walk up the cpuset hierarchy
* until we find one that does have some online cpus. If we get
* all the way to the top and still haven't found any online cpus,
- * return cpu_online_map. Or if passed a NULL cs from an exit'ing
- * task, return cpu_online_map.
+ * return cpu_online_mask. Or if passed a NULL cs from an exit'ing
+ * task, return cpu_online_mask.
*
* One way or another, we guarantee to return some non-empty subset
- * of cpu_online_map.
+ * of cpu_online_mask.
*
* Call with callback_mutex held.
*/
int retval;
int is_load_balanced;
- /* top_cpuset.cpus_allowed tracks cpu_online_map; it's read-only */
+ /* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */
if (cs == &top_cpuset)
return -EACCES;
static void cpuset_change_task_nodemask(struct task_struct *tsk,
nodemask_t *newmems)
{
- bool masks_disjoint = !nodes_intersects(*newmems, tsk->mems_allowed);
+ bool need_loop;
-repeat:
/*
* Allow tasks that have access to memory reserves because they have
* been OOM killed to get memory anywhere.
return;
task_lock(tsk);
- nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
- mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
-
/*
- * ensure checking ->mems_allowed_change_disable after setting all new
- * allowed nodes.
- *
- * the read-side task can see an nodemask with new allowed nodes and
- * old allowed nodes. and if it allocates page when cpuset clears newly
- * disallowed ones continuous, it can see the new allowed bits.
- *
- * And if setting all new allowed nodes is after the checking, setting
- * all new allowed nodes and clearing newly disallowed ones will be done
- * continuous, and the read-side task may find no node to alloc page.
+ * Determine if a loop is necessary if another thread is doing
+ * get_mems_allowed(). If at least one node remains unchanged and
+ * tsk does not have a mempolicy, then an empty nodemask will not be
+ * possible when mems_allowed is larger than a word.
*/
- smp_mb();
+ need_loop = task_has_mempolicy(tsk) ||
+ !nodes_intersects(*newmems, tsk->mems_allowed);
- /*
- * Allocation of memory is very fast, we needn't sleep when waiting
- * for the read-side. No wait is necessary, however, if at least one
- * node remains unchanged.
- */
- while (masks_disjoint &&
- ACCESS_ONCE(tsk->mems_allowed_change_disable)) {
- task_unlock(tsk);
- if (!task_curr(tsk))
- yield();
- goto repeat;
- }
+ if (need_loop)
+ write_seqcount_begin(&tsk->mems_allowed_seq);
- /*
- * ensure checking ->mems_allowed_change_disable before clearing all new
- * disallowed nodes.
- *
- * if clearing newly disallowed bits before the checking, the read-side
- * task may find no node to alloc page.
- */
- smp_mb();
+ nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems);
+ mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP1);
mpol_rebind_task(tsk, newmems, MPOL_REBIND_STEP2);
tsk->mems_allowed = *newmems;
+
+ if (need_loop)
+ write_seqcount_end(&tsk->mems_allowed_seq);
+
task_unlock(tsk);
}
}
/* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */
-static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
- struct cgroup_taskset *tset)
+static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cont,
+ struct task_struct *tsk)
{
- struct cpuset *cs = cgroup_cs(cgrp);
+ struct cpuset *cs = cgroup_cs(cont);
+ if ((current != task) && (!capable(CAP_SYS_ADMIN))) {
+ const struct cred *cred = current_cred(), *tcred;
+
+ if (cred->euid != tcred->uid && cred->euid != tcred->suid)
+ return -EPERM;
+ }
+
if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
return -ENOSPC;
* set_cpus_allowed_ptr() on all attached tasks before cpus_allowed may
* be changed.
*/
- if (cgroup_taskset_first(tset)->flags & PF_THREAD_BOUND)
+ if (tsk->flags & PF_THREAD_BOUND)
return -EINVAL;
return 0;
/*
* Protected by cgroup_lock. The nodemasks must be stored globally because
- * dynamically allocating them is not allowed in pre_attach, and they must
- * persist among pre_attach, attach_task, and attach.
+ * dynamically allocating them is not allowed in can_attach, and they must
+ * persist until attach.
*/
static cpumask_var_t cpus_attach;
static nodemask_t cpuset_attach_nodemask_from;
static nodemask_t cpuset_attach_nodemask_to;
-/* Set-up work for before attaching each task. */
-static void cpuset_pre_attach(struct cgroup *cont)
+/* Called by cgroups to determine if a cpuset is usable; cgroup_mutex held */
+static int cpuset_can_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
{
- struct cpuset *cs = cgroup_cs(cont);
+ struct cpuset *cs = cgroup_cs(cgrp);
+ struct task_struct *task;
+ int ret;
+ if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
+ return -ENOSPC;
+
+ 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.
+ */
+ if (task->flags & PF_THREAD_BOUND)
+ return -EINVAL;
+ if ((ret = security_task_setscheduler(task)))
+ return ret;
+ }
+
+ /* prepare for attach */
if (cs == &top_cpuset)
cpumask_copy(cpus_attach, cpu_possible_mask);
else
guarantee_online_cpus(cs, cpus_attach);
guarantee_online_mems(cs, &cpuset_attach_nodemask_to);
-}
-
-/* Per-thread attachment work. */
-static void cpuset_attach_task(struct cgroup *cont, struct task_struct *tsk)
-{
- int err;
- struct cpuset *cs = cgroup_cs(cont);
-
- /*
- * can_attach beforehand should guarantee that this doesn't fail.
- * TODO: have a better way to handle failure here
- */
- err = set_cpus_allowed_ptr(tsk, cpus_attach);
- WARN_ON_ONCE(err);
- cpuset_change_task_nodemask(tsk, &cpuset_attach_nodemask_to);
- cpuset_update_task_spread_flag(cs, tsk);
+ return 0;
}
-static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
- struct cgroup_taskset *tset)
+static void cpuset_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
{
struct mm_struct *mm;
- struct task_struct *tsk = cgroup_taskset_first(tset);
+ struct task_struct *task;
+ struct task_struct *leader = cgroup_taskset_first(tset);
struct cgroup *oldcgrp = cgroup_taskset_cur_cgroup(tset);
struct cpuset *cs = cgroup_cs(cgrp);
struct cpuset *oldcs = cgroup_cs(oldcgrp);
+ cgroup_taskset_for_each(task, cgrp, tset) {
+ /*
+ * can_attach beforehand should guarantee that this doesn't
+ * fail. TODO: have a better way to handle failure here
+ */
+ WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach));
+
+ cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to);
+ cpuset_update_task_spread_flag(cs, task);
+ }
+
/*
* Change mm, possibly for multiple threads in a threadgroup. This is
* expensive and may sleep.
*/
cpuset_attach_nodemask_from = oldcs->mems_allowed;
cpuset_attach_nodemask_to = cs->mems_allowed;
- mm = get_task_mm(tsk);
+ mm = get_task_mm(leader);
if (mm) {
mpol_rebind_mm(mm, &cpuset_attach_nodemask_to);
if (is_memory_migrate(cs))
* (and likewise for mems) to the new cgroup. Called with cgroup_mutex
* held.
*/
-static void cpuset_post_clone(struct cgroup_subsys *ss,
- struct cgroup *cgroup)
+static void cpuset_post_clone(struct cgroup *cgroup)
{
struct cgroup *parent, *child;
struct cpuset *cs, *parent_cs;
/*
* cpuset_create - create a cpuset
- * ss: cpuset cgroup subsystem
* cont: control group that the new cpuset will be part of
*/
-static struct cgroup_subsys_state *cpuset_create(
- struct cgroup_subsys *ss,
- struct cgroup *cont)
+static struct cgroup_subsys_state *cpuset_create(struct cgroup *cont)
{
struct cpuset *cs;
struct cpuset *parent;
* will call async_rebuild_sched_domains().
*/
-static void cpuset_destroy(struct cgroup_subsys *ss, struct cgroup *cont)
+static void cpuset_destroy(struct cgroup *cont)
{
struct cpuset *cs = cgroup_cs(cont);
.create = cpuset_create,
.destroy = cpuset_destroy,
.can_attach = cpuset_can_attach,
- .can_attach_task = cpuset_can_attach_task,
- .pre_attach = cpuset_pre_attach,
- .attach_task = cpuset_attach_task,
.attach = cpuset_attach,
.populate = cpuset_populate,
.post_clone = cpuset_post_clone,
*
* Description: Returns the cpumask_var_t cpus_allowed of the cpuset
* attached to the specified @tsk. Guaranteed to return some non-empty
- * subset of cpu_online_map, even if this means going outside the
+ * subset of cpu_online_mask, even if this means going outside the
* tasks cpuset.
**/
mutex_unlock(&callback_mutex);
}
-int cpuset_cpus_allowed_fallback(struct task_struct *tsk)
+void cpuset_cpus_allowed_fallback(struct task_struct *tsk)
{
const struct cpuset *cs;
- int cpu;
rcu_read_lock();
cs = task_cs(tsk);
* 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.
+ *
+ * select_fallback_rq() will fix things ups and set cpu_possible_mask
+ * if required.
*/
-
- 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.
- */
- do_set_cpus_allowed(tsk, cpu_possible_mask);
- cpu = cpumask_any(cpu_active_mask);
- }
-
- return cpu;
}
void cpuset_init_current_mems_allowed(void)
Code Review / linux-2.6.git / blobdiff