1 files changed, 27 insertions, 84 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index a09ac2b9a661..2382683617a3 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -964,7 +964,6 @@ static void cpuset_change_task_nodemask(struct task_struct *tsk,
 {
         bool need_loop;
 
-repeat:
         /*
          * Allow tasks that have access to memory reserves because they have
          * been OOM killed to get memory anywhere.
@@ -983,45 +982,19 @@ repeat:
          */
         need_loop = task_has_mempolicy(tsk) ||
                         !nodes_intersects(*newmems, tsk->mems_allowed);
-        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.
-         */
-        smp_mb();
-
-        /*
-         * Allocation of memory is very fast, we needn't sleep when waiting
-         * for the read-side.
-         */
-        while (need_loop && 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);
 }
 
@@ -1399,8 +1372,7 @@ static nodemask_t cpuset_attach_nodemask_from;
 static nodemask_t cpuset_attach_nodemask_to;
 
 /* 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 *cgrp, struct cgroup_taskset *tset)
 {
         struct cpuset *cs = cgroup_cs(cgrp);
         struct task_struct *task;
@@ -1436,8 +1408,7 @@ static int cpuset_can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
         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 *task;
@@ -1794,28 +1765,17 @@ static struct cftype files[] = {
                 .write_u64 = cpuset_write_u64,
                 .private = FILE_SPREAD_SLAB,
         },
-};
 
-static struct cftype cft_memory_pressure_enabled = {
-        .name = "memory_pressure_enabled",
-        .read_u64 = cpuset_read_u64,
-        .write_u64 = cpuset_write_u64,
-        .private = FILE_MEMORY_PRESSURE_ENABLED,
-};
-
-static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont)
-{
-        int err;
+        {
+                .name = "memory_pressure_enabled",
+                .flags = CFTYPE_ONLY_ON_ROOT,
+                .read_u64 = cpuset_read_u64,
+                .write_u64 = cpuset_write_u64,
+                .private = FILE_MEMORY_PRESSURE_ENABLED,
+        },
 
-        err = cgroup_add_files(cont, ss, files, ARRAY_SIZE(files));
-        if (err)
-                return err;
-        /* memory_pressure_enabled is in root cpuset only */
-        if (!cont->parent)
-                err = cgroup_add_file(cont, ss,
-                                      &cft_memory_pressure_enabled);
-        return err;
-}
+        { }     /* terminate */
+};
 
 /*
  * post_clone() is called during cgroup_create() when the
@@ -1833,8 +1793,7 @@ static int cpuset_populate(struct cgroup_subsys *ss, struct cgroup *cont)
  * (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;
@@ -1857,13 +1816,10 @@ static void cpuset_post_clone(struct cgroup_subsys *ss,
 
 /*
  *      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;
@@ -1902,7 +1858,7 @@ static struct cgroup_subsys_state *cpuset_create(
  * 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);
 
@@ -1920,9 +1876,9 @@ struct cgroup_subsys cpuset_subsys = {
         .destroy = cpuset_destroy,
         .can_attach = cpuset_can_attach,
         .attach = cpuset_attach,
-        .populate = cpuset_populate,
         .post_clone = cpuset_post_clone,
         .subsys_id = cpuset_subsys_id,
+        .base_cftypes = files,
         .early_init = 1,
 };
 
@@ -2195,10 +2151,9 @@ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask)
         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);
@@ -2219,22 +2174,10 @@ int cpuset_cpus_allowed_fallback(struct task_struct *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)