Merge branch 'wip-2.6.34' into old-private-masterarchived-private-master

1 files changed, 94 insertions, 57 deletions

diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index b5cb469d2545..d10946748ec2 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -537,8 +537,7 @@ update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *c)
  *      element of the partition (one sched domain) to be passed to
  *      partition_sched_domains().
  */
-/* FIXME: see the FIXME in partition_sched_domains() */
-static int generate_sched_domains(struct cpumask **domains,
+static int generate_sched_domains(cpumask_var_t **domains,
                         struct sched_domain_attr **attributes)
 {
         LIST_HEAD(q);           /* queue of cpusets to be scanned */
@@ -546,7 +545,7 @@ static int generate_sched_domains(struct cpumask **domains,
         struct cpuset **csa;    /* array of all cpuset ptrs */
         int csn;                /* how many cpuset ptrs in csa so far */
         int i, j, k;            /* indices for partition finding loops */
-        struct cpumask *doms;   /* resulting partition; i.e. sched domains */
+        cpumask_var_t *doms;    /* resulting partition; i.e. sched domains */
         struct sched_domain_attr *dattr;  /* attributes for custom domains */
         int ndoms = 0;          /* number of sched domains in result */
         int nslot;              /* next empty doms[] struct cpumask slot */
@@ -557,7 +556,8 @@ static int generate_sched_domains(struct cpumask **domains,
 
         /* Special case for the 99% of systems with one, full, sched domain */
         if (is_sched_load_balance(&top_cpuset)) {
-                doms = kmalloc(cpumask_size(), GFP_KERNEL);
+                ndoms = 1;
+                doms = alloc_sched_domains(ndoms);
                 if (!doms)
                         goto done;
 
@@ -566,9 +566,8 @@ static int generate_sched_domains(struct cpumask **domains,
                         *dattr = SD_ATTR_INIT;
                         update_domain_attr_tree(dattr, &top_cpuset);
                 }
-                cpumask_copy(doms, top_cpuset.cpus_allowed);
+                cpumask_copy(doms[0], top_cpuset.cpus_allowed);
 
-                ndoms = 1;
                 goto done;
         }
 
@@ -636,7 +635,7 @@ restart:
          * Now we know how many domains to create.
          * Convert <csn, csa> to <ndoms, doms> and populate cpu masks.
          */
-        doms = kmalloc(ndoms * cpumask_size(), GFP_KERNEL);
+        doms = alloc_sched_domains(ndoms);
         if (!doms)
                 goto done;
 
@@ -656,7 +655,7 @@ restart:
                         continue;
                 }
 
-                dp = doms + nslot;
+                dp = doms[nslot];
 
                 if (nslot == ndoms) {
                         static int warnings = 10;
@@ -718,7 +717,7 @@ done:
 static void do_rebuild_sched_domains(struct work_struct *unused)
 {
         struct sched_domain_attr *attr;
-        struct cpumask *doms;
+        cpumask_var_t *doms;
         int ndoms;
 
         get_online_cpus();
@@ -738,7 +737,7 @@ static void do_rebuild_sched_domains(struct work_struct *unused)
 {
 }
 
-static int generate_sched_domains(struct cpumask **domains,
+static int generate_sched_domains(cpumask_var_t **domains,
                         struct sched_domain_attr **attributes)
 {
         *domains = NULL;
@@ -873,7 +872,7 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
                 if (retval < 0)
                         return retval;
 
-                if (!cpumask_subset(trialcs->cpus_allowed, cpu_online_mask))
+                if (!cpumask_subset(trialcs->cpus_allowed, cpu_active_mask))
                         return -EINVAL;
         }
         retval = validate_change(cs, trialcs);
@@ -921,9 +920,6 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
  *    call to guarantee_online_mems(), as we know no one is changing
  *    our task's cpuset.
  *
- *    Hold callback_mutex around the two modifications of our tasks
- *    mems_allowed to synchronize with cpuset_mems_allowed().
- *
  *    While the mm_struct we are migrating is typically from some
  *    other task, the task_struct mems_allowed that we are hacking
  *    is for our current task, which must allocate new pages for that
@@ -974,15 +970,20 @@ static void cpuset_change_nodemask(struct task_struct *p,
         struct cpuset *cs;
         int migrate;
         const nodemask_t *oldmem = scan->data;
-        nodemask_t newmems;
+        NODEMASK_ALLOC(nodemask_t, newmems, GFP_KERNEL);
+
+        if (!newmems)
+                return;
 
         cs = cgroup_cs(scan->cg);
-        guarantee_online_mems(cs, &newmems);
+        guarantee_online_mems(cs, newmems);
 
         task_lock(p);
-        cpuset_change_task_nodemask(p, &newmems);
+        cpuset_change_task_nodemask(p, newmems);
         task_unlock(p);
 
+        NODEMASK_FREE(newmems);
+
         mm = get_task_mm(p);
         if (!mm)
                 return;
@@ -1052,16 +1053,21 @@ static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem,
 static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
                            const char *buf)
 {
-        nodemask_t oldmem;
+        NODEMASK_ALLOC(nodemask_t, oldmem, GFP_KERNEL);
         int retval;
         struct ptr_heap heap;
 
+        if (!oldmem)
+                return -ENOMEM;
+
         /*
          * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
          * it's read-only
          */
-        if (cs == &top_cpuset)
-                return -EACCES;
+        if (cs == &top_cpuset) {
+                retval = -EACCES;
+                goto done;
+        }
 
         /*
          * An empty mems_allowed is ok iff there are no tasks in the cpuset.
@@ -1077,11 +1083,13 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
                         goto done;
 
                 if (!nodes_subset(trialcs->mems_allowed,
-                                node_states[N_HIGH_MEMORY]))
-                        return -EINVAL;
+                                node_states[N_HIGH_MEMORY])) {
+                        retval =  -EINVAL;
+                        goto done;
+                }
         }
-        oldmem = cs->mems_allowed;
-        if (nodes_equal(oldmem, trialcs->mems_allowed)) {
+        *oldmem = cs->mems_allowed;
+        if (nodes_equal(*oldmem, trialcs->mems_allowed)) {
                 retval = 0;             /* Too easy - nothing to do */
                 goto done;
         }
@@ -1097,10 +1105,11 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
         cs->mems_allowed = trialcs->mems_allowed;
         mutex_unlock(&callback_mutex);
 
-        update_tasks_nodemask(cs, &oldmem, &heap);
+        update_tasks_nodemask(cs, oldmem, &heap);
 
         heap_free(&heap);
 done:
+        NODEMASK_FREE(oldmem);
         return retval;
 }
 
@@ -1385,40 +1394,47 @@ static void cpuset_attach(struct cgroup_subsys *ss, struct cgroup *cont,
                           struct cgroup *oldcont, struct task_struct *tsk,
                           bool threadgroup)
 {
-        nodemask_t from, to;
         struct mm_struct *mm;
         struct cpuset *cs = cgroup_cs(cont);
         struct cpuset *oldcs = cgroup_cs(oldcont);
+        NODEMASK_ALLOC(nodemask_t, from, GFP_KERNEL);
+        NODEMASK_ALLOC(nodemask_t, to, GFP_KERNEL);
+
+        if (from == NULL || to == NULL)
+                goto alloc_fail;
 
         if (cs == &top_cpuset) {
                 cpumask_copy(cpus_attach, cpu_possible_mask);
-                to = node_possible_map;
         } else {
                 guarantee_online_cpus(cs, cpus_attach);
-                guarantee_online_mems(cs, &to);
         }
+        guarantee_online_mems(cs, to);
 
         /* do per-task migration stuff possibly for each in the threadgroup */
-        cpuset_attach_task(tsk, &to, cs);
+        cpuset_attach_task(tsk, to, cs);
         if (threadgroup) {
                 struct task_struct *c;
                 rcu_read_lock();
                 list_for_each_entry_rcu(c, &tsk->thread_group, thread_group) {
-                        cpuset_attach_task(c, &to, cs);
+                        cpuset_attach_task(c, to, cs);
                 }
                 rcu_read_unlock();
         }
 
         /* change mm; only needs to be done once even if threadgroup */
-        from = oldcs->mems_allowed;
-        to = cs->mems_allowed;
+        *from = oldcs->mems_allowed;
+        *to = cs->mems_allowed;
         mm = get_task_mm(tsk);
         if (mm) {
-                mpol_rebind_mm(mm, &to);
+                mpol_rebind_mm(mm, to);
                 if (is_memory_migrate(cs))
-                        cpuset_migrate_mm(mm, &from, &to);
+                        cpuset_migrate_mm(mm, from, to);
                 mmput(mm);
         }
+
+alloc_fail:
+        NODEMASK_FREE(from);
+        NODEMASK_FREE(to);
 }
 
 /* The various types of files and directories in a cpuset file system */
@@ -1563,13 +1579,21 @@ static int cpuset_sprintf_cpulist(char *page, struct cpuset *cs)
 
 static int cpuset_sprintf_memlist(char *page, struct cpuset *cs)
 {
-        nodemask_t mask;
+        NODEMASK_ALLOC(nodemask_t, mask, GFP_KERNEL);
+        int retval;
+
+        if (mask == NULL)
+                return -ENOMEM;
 
         mutex_lock(&callback_mutex);
-        mask = cs->mems_allowed;
+        *mask = cs->mems_allowed;
         mutex_unlock(&callback_mutex);
 
-        return nodelist_scnprintf(page, PAGE_SIZE, mask);
+        retval = nodelist_scnprintf(page, PAGE_SIZE, *mask);
+
+        NODEMASK_FREE(mask);
+
+        return retval;
 }
 
 static ssize_t cpuset_common_file_read(struct cgroup *cont,
@@ -1998,7 +2022,10 @@ static void scan_for_empty_cpusets(struct cpuset *root)
         struct cpuset *cp;      /* scans cpusets being updated */
         struct cpuset *child;   /* scans child cpusets of cp */
         struct cgroup *cont;
-        nodemask_t oldmems;
+        NODEMASK_ALLOC(nodemask_t, oldmems, GFP_KERNEL);
+
+        if (oldmems == NULL)
+                return;
 
         list_add_tail((struct list_head *)&root->stack_list, &queue);
 
@@ -2011,16 +2038,16 @@ static void scan_for_empty_cpusets(struct cpuset *root)
                 }
 
                 /* Continue past cpusets with all cpus, mems online */
-                if (cpumask_subset(cp->cpus_allowed, cpu_online_mask) &&
+                if (cpumask_subset(cp->cpus_allowed, cpu_active_mask) &&
                     nodes_subset(cp->mems_allowed, node_states[N_HIGH_MEMORY]))
                         continue;
 
-                oldmems = cp->mems_allowed;
+                *oldmems = cp->mems_allowed;
 
                 /* Remove offline cpus and mems from this cpuset. */
                 mutex_lock(&callback_mutex);
                 cpumask_and(cp->cpus_allowed, cp->cpus_allowed,
-                            cpu_online_mask);
+                            cpu_active_mask);
                 nodes_and(cp->mems_allowed, cp->mems_allowed,
                                                 node_states[N_HIGH_MEMORY]);
                 mutex_unlock(&callback_mutex);
@@ -2031,9 +2058,10 @@ static void scan_for_empty_cpusets(struct cpuset *root)
                         remove_tasks_in_empty_cpuset(cp);
                 else {
                         update_tasks_cpumask(cp, NULL);
-                        update_tasks_nodemask(cp, &oldmems, NULL);
+                        update_tasks_nodemask(cp, oldmems, NULL);
                 }
         }
+        NODEMASK_FREE(oldmems);
 }
 
 /*
@@ -2052,14 +2080,16 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
                                 unsigned long phase, void *unused_cpu)
 {
         struct sched_domain_attr *attr;
-        struct cpumask *doms;
+        cpumask_var_t *doms;
         int ndoms;
 
         switch (phase) {
         case CPU_ONLINE:
         case CPU_ONLINE_FROZEN:
-        case CPU_DEAD:
-        case CPU_DEAD_FROZEN:
+        case CPU_DOWN_PREPARE:
+        case CPU_DOWN_PREPARE_FROZEN:
+        case CPU_DOWN_FAILED:
+        case CPU_DOWN_FAILED_FROZEN:
                 break;
 
         default:
@@ -2068,7 +2098,7 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 
         cgroup_lock();
         mutex_lock(&callback_mutex);
-        cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
+        cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
         mutex_unlock(&callback_mutex);
         scan_for_empty_cpusets(&top_cpuset);
         ndoms = generate_sched_domains(&doms, &attr);
@@ -2089,20 +2119,33 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 static int cpuset_track_online_nodes(struct notifier_block *self,
                                 unsigned long action, void *arg)
 {
+        NODEMASK_ALLOC(nodemask_t, oldmems, GFP_KERNEL);
+
+        if (oldmems == NULL)
+                return NOTIFY_DONE;
+
         cgroup_lock();
         switch (action) {
         case MEM_ONLINE:
-        case MEM_OFFLINE:
+                *oldmems = top_cpuset.mems_allowed;
                 mutex_lock(&callback_mutex);
                 top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
                 mutex_unlock(&callback_mutex);
-                if (action == MEM_OFFLINE)
-                        scan_for_empty_cpusets(&top_cpuset);
+                update_tasks_nodemask(&top_cpuset, oldmems, NULL);
+                break;
+        case MEM_OFFLINE:
+                /*
+                 * needn't update top_cpuset.mems_allowed explicitly because
+                 * scan_for_empty_cpusets() will update it.
+                 */
+                scan_for_empty_cpusets(&top_cpuset);
                 break;
         default:
                 break;
         }
         cgroup_unlock();
+
+        NODEMASK_FREE(oldmems);
         return NOTIFY_OK;
 }
 #endif
@@ -2115,7 +2158,7 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
 
 void __init cpuset_init_smp(void)
 {
-        cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
+        cpumask_copy(top_cpuset.cpus_allowed, cpu_active_mask);
         top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
 
         hotcpu_notifier(cpuset_track_online_cpus, 0);
@@ -2537,15 +2580,9 @@ const struct file_operations proc_cpuset_operations = {
 };
 #endif /* CONFIG_PROC_PID_CPUSET */
 
-/* Display task cpus_allowed, mems_allowed in /proc/<pid>/status file. */
+/* Display task mems_allowed in /proc/<pid>/status file. */
 void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task)
 {
-        seq_printf(m, "Cpus_allowed:\t");
-        seq_cpumask(m, &task->cpus_allowed);
-        seq_printf(m, "\n");
-        seq_printf(m, "Cpus_allowed_list:\t");
-        seq_cpumask_list(m, &task->cpus_allowed);
-        seq_printf(m, "\n");
         seq_printf(m, "Mems_allowed:\t");
         seq_nodemask(m, &task->mems_allowed);
         seq_printf(m, "\n");