mem-hotplug: avoid multiple zones sharing same boot strapping boot_pageset

[safe/jmp/linux-2.6] / kernel / cpu.c

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 25bba73..3e8b3ba 100644 (file)
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -164,6 +164,7 @@ static inline void check_for_tasks(int cpu)
 }
 
 struct take_cpu_down_param {
+       struct task_struct *caller;
        unsigned long mod;
        void *hcpu;
 };
@@ -172,6 +173,7 @@ struct take_cpu_down_param {
 static int __ref take_cpu_down(void *_param)
 {
        struct take_cpu_down_param *param = _param;
+       unsigned int cpu = (unsigned long)param->hcpu;
        int err;
 
        /* Ensure this CPU doesn't handle any more interrupts. */
@@ -182,6 +184,8 @@ static int __ref take_cpu_down(void *_param)
        raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
                                param->hcpu);
 
+       if (task_cpu(param->caller) == cpu)
+               move_task_off_dead_cpu(cpu, param->caller);
        /* Force idle task to run as soon as we yield: it should
           immediately notice cpu is offline and die quickly. */
        sched_idle_next();
@@ -192,10 +196,10 @@ static int __ref take_cpu_down(void *_param)
 static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 {
        int err, nr_calls = 0;
-       cpumask_var_t old_allowed;
        void *hcpu = (void *)(long)cpu;
        unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
        struct take_cpu_down_param tcd_param = {
+               .caller = current,
                .mod = mod,
                .hcpu = hcpu,
        };
@@ -206,9 +210,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
        if (!cpu_online(cpu))
                return -EINVAL;
 
-       if (!alloc_cpumask_var(&old_allowed, GFP_KERNEL))
-               return -ENOMEM;
-
        cpu_hotplug_begin();
        set_cpu_active(cpu, false);
        err = __raw_notifier_call_chain(&cpu_chain, CPU_DOWN_PREPARE | mod,
@@ -225,10 +226,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
                goto out_release;
        }
 
-       /* Ensure that we are not runnable on dying cpu */
-       cpumask_copy(old_allowed, &current->cpus_allowed);
-       set_cpus_allowed_ptr(current, cpu_active_mask);
-
        err = __stop_machine(take_cpu_down, &tcd_param, cpumask_of(cpu));
        if (err) {
                set_cpu_active(cpu, true);
@@ -237,7 +234,7 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
                                            hcpu) == NOTIFY_BAD)
                        BUG();
 
-               goto out_allowed;
+               goto out_release;
        }
        BUG_ON(cpu_online(cpu));
 
@@ -255,8 +252,6 @@ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen)
 
        check_for_tasks(cpu);
 
-out_allowed:
-       set_cpus_allowed_ptr(current, old_allowed);
 out_release:
        cpu_hotplug_done();
        if (!err) {
@@ -264,7 +259,6 @@ out_release:
                                            hcpu) == NOTIFY_BAD)
                        BUG();
        }
-       free_cpumask_var(old_allowed);
        return err;
 }
 
@@ -272,9 +266,6 @@ int __ref cpu_down(unsigned int cpu)
 {
        int err;
 
-       err = stop_machine_create();
-       if (err)
-               return err;
        cpu_maps_update_begin();
 
        if (cpu_hotplug_disabled) {
@@ -286,7 +277,6 @@ int __ref cpu_down(unsigned int cpu)
 
 out:
        cpu_maps_update_done();
-       stop_machine_destroy();
        return err;
 }
 EXPORT_SYMBOL(cpu_down);
@@ -336,6 +326,12 @@ out_notify:
 int __cpuinit cpu_up(unsigned int cpu)
 {
        int err = 0;
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+       int nid;
+       pg_data_t       *pgdat;
+#endif
+
        if (!cpu_possible(cpu)) {
                printk(KERN_ERR "can't online cpu %d because it is not "
                        "configured as may-hotadd at boot time\n", cpu);
@@ -346,6 +342,25 @@ int __cpuinit cpu_up(unsigned int cpu)
                return -EINVAL;
        }
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+       nid = cpu_to_node(cpu);
+       if (!node_online(nid)) {
+               err = mem_online_node(nid);
+               if (err)
+                       return err;
+       }
+
+       pgdat = NODE_DATA(nid);
+       if (!pgdat) {
+               printk(KERN_ERR
+                       "Can't online cpu %d due to NULL pgdat\n", cpu);
+               return -ENOMEM;
+       }
+
+       if (pgdat->node_zonelists->_zonerefs->zone == NULL)
+               build_all_zonelists(NULL);
+#endif
+
        cpu_maps_update_begin();
 
        if (cpu_hotplug_disabled) {
@@ -367,9 +382,6 @@ int disable_nonboot_cpus(void)
 {
        int cpu, first_cpu, error;
 
-       error = stop_machine_create();
-       if (error)
-               return error;
        cpu_maps_update_begin();
        first_cpu = cpumask_first(cpu_online_mask);
        /*
@@ -400,7 +412,6 @@ int disable_nonboot_cpus(void)
                printk(KERN_ERR "Non-boot CPUs are not disabled\n");
        }
        cpu_maps_update_done();
-       stop_machine_destroy();
        return error;
 }