x86/mcheck: Move CPU_ONLINE and CPU_DOWN_PREPARE to hotplug state machine

[karo-tx-linux.git] / arch / x86 / kernel / cpu / mcheck / mce.c

diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index a7fdf453d895bab87d785f193471269fba4fbdd0..78955f501ff232f13e6bea6b139d29da3e9edc5c 100644 (file)
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -1745,6 +1745,14 @@ static void mce_start_timer(unsigned int cpu, struct timer_list *t)
        add_timer_on(t, cpu);
 }
 
+static void __mcheck_cpu_setup_timer(void)
+{
+       struct timer_list *t = this_cpu_ptr(&mce_timer);
+       unsigned int cpu = smp_processor_id();
+
+       setup_pinned_timer(t, mce_timer_fn, cpu);
+}
+
 static void __mcheck_cpu_init_timer(void)
 {
        struct timer_list *t = this_cpu_ptr(&mce_timer);
@@ -1796,7 +1804,7 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
        __mcheck_cpu_init_generic();
        __mcheck_cpu_init_vendor(c);
        __mcheck_cpu_init_clear_banks();
-       __mcheck_cpu_init_timer();
+       __mcheck_cpu_setup_timer();
 }
 
 /*
@@ -2255,8 +2263,6 @@ static struct bus_type mce_subsys = {
 
 DEFINE_PER_CPU(struct device *, mce_device);
 
-void (*threshold_cpu_callback)(unsigned long action, unsigned int cpu);
-
 static inline struct mce_bank *attr_to_bank(struct device_attribute *attr)
 {
        return container_of(attr, struct mce_bank, attr);
@@ -2409,6 +2415,10 @@ static int mce_device_create(unsigned int cpu)
        if (!mce_available(&boot_cpu_data))
                return -EIO;
 
+       dev = per_cpu(mce_device, cpu);
+       if (dev)
+               return 0;
+
        dev = kzalloc(sizeof *dev, GFP_KERNEL);
        if (!dev)
                return -ENOMEM;
@@ -2468,28 +2478,25 @@ static void mce_device_remove(unsigned int cpu)
 }
 
 /* Make sure there are no machine checks on offlined CPUs. */
-static void mce_disable_cpu(void *h)
+static void mce_disable_cpu(void)
 {
-       unsigned long action = *(unsigned long *)h;
-
        if (!mce_available(raw_cpu_ptr(&cpu_info)))
                return;
 
-       if (!(action & CPU_TASKS_FROZEN))
+       if (!cpuhp_tasks_frozen)
                cmci_clear();
 
        vendor_disable_error_reporting();
 }
 
-static void mce_reenable_cpu(void *h)
+static void mce_reenable_cpu(void)
 {
-       unsigned long action = *(unsigned long *)h;
        int i;
 
        if (!mce_available(raw_cpu_ptr(&cpu_info)))
                return;
 
-       if (!(action & CPU_TASKS_FROZEN))
+       if (!cpuhp_tasks_frozen)
                cmci_reenable();
        for (i = 0; i < mca_cfg.banks; i++) {
                struct mce_bank *b = &mce_banks[i];
@@ -2504,18 +2511,9 @@ static int
 mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 {
        unsigned int cpu = (unsigned long)hcpu;
-       struct timer_list *t = &per_cpu(mce_timer, cpu);
 
        switch (action & ~CPU_TASKS_FROZEN) {
-       case CPU_ONLINE:
-               mce_device_create(cpu);
-               if (threshold_cpu_callback)
-                       threshold_cpu_callback(action, cpu);
-               break;
        case CPU_DEAD:
-               if (threshold_cpu_callback)
-                       threshold_cpu_callback(action, cpu);
-               mce_device_remove(cpu);
                mce_intel_hcpu_update(cpu);
 
                /* intentionally ignoring frozen here */
@@ -2523,18 +2521,41 @@ mce_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
                        cmci_rediscover();
                break;
        case CPU_DOWN_PREPARE:
-               smp_call_function_single(cpu, mce_disable_cpu, &action, 1);
-               del_timer_sync(t);
-               break;
-       case CPU_DOWN_FAILED:
-               smp_call_function_single(cpu, mce_reenable_cpu, &action, 1);
-               mce_start_timer(cpu, t);
+
                break;
        }
 
        return NOTIFY_OK;
 }
 
+static int mce_cpu_online(unsigned int cpu)
+{
+       struct timer_list *t = &per_cpu(mce_timer, cpu);
+       int ret;
+
+       mce_device_create(cpu);
+
+       ret = mce_threshold_create_device(cpu);
+       if (ret) {
+               mce_device_remove(cpu);
+               return ret;
+       }
+       mce_reenable_cpu();
+       mce_start_timer(cpu, t);
+       return 0;
+}
+
+static int mce_cpu_pre_down(unsigned int cpu)
+{
+       struct timer_list *t = &per_cpu(mce_timer, cpu);
+
+       mce_disable_cpu();
+       del_timer_sync(t);
+       mce_threshold_remove_device(cpu);
+       mce_device_remove(cpu);
+       return 0;
+}
+
 static struct notifier_block mce_cpu_notifier = {
        .notifier_call = mce_cpu_callback,
 };
@@ -2559,8 +2580,8 @@ static __init void mce_init_banks(void)
 
 static __init int mcheck_init_device(void)
 {
+       enum cpuhp_state hp_online;
        int err;
-       int i = 0;
 
        if (!mce_available(&boot_cpu_data)) {
                err = -EIO;
@@ -2578,21 +2599,13 @@ static __init int mcheck_init_device(void)
        if (err)
                goto err_out_mem;
 
-       cpu_notifier_register_begin();
-       for_each_online_cpu(i) {
-               err = mce_device_create(i);
-               if (err) {
-                       /*
-                        * Register notifier anyway (and do not unreg it) so
-                        * that we don't leave undeleted timers, see notifier
-                        * callback above.
-                        */
-                       __register_hotcpu_notifier(&mce_cpu_notifier);
-                       cpu_notifier_register_done();
-                       goto err_device_create;
-               }
-       }
+       err = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/mce:online",
+                               mce_cpu_online, mce_cpu_pre_down);
+       if (err < 0)
+               goto err_out_mem;
+       hp_online = err;
 
+       cpu_notifier_register_begin();
        __register_hotcpu_notifier(&mce_cpu_notifier);
        cpu_notifier_register_done();
 
@@ -2607,16 +2620,7 @@ static __init int mcheck_init_device(void)
 
 err_register:
        unregister_syscore_ops(&mce_syscore_ops);
-
-err_device_create:
-       /*
-        * We didn't keep track of which devices were created above, but
-        * even if we had, the set of online cpus might have changed.
-        * Play safe and remove for every possible cpu, since
-        * mce_device_remove() will do the right thing.
-        */
-       for_each_possible_cpu(i)
-               mce_device_remove(i);
+       cpuhp_remove_state(hp_online);
 
 err_out_mem:
        free_cpumask_var(mce_device_initialized);