HOTPLUG: Add CPU_DYING notifier

KVM wants a notification when a cpu is about to die, so it can disable
hardware extensions, but at a time when user processes cannot be scheduled
on the cpu, so it doesn't try to use virtualization extensions after they
have been disabled.

This adds a CPU_DYING notification.  The notification is called in atomic
context on the doomed cpu.

Signed-off-by: Avi Kivity <avi@qumranet.com>

diff --git a/include/linux/notifier.h b/include/linux/notifier.h
index 9431101bf8769508db8dc6263927049d1cfdb9df..576f2bb34cc80dcc84271c874fc47e0bf16cc50e 100644 (file)
--- a/include/linux/notifier.h
+++ b/include/linux/notifier.h
@@ -196,6 +196,8 @@ extern int __srcu_notifier_call_chain(struct srcu_notifier_head *nh,
 #define CPU_DEAD               0x0007 /* CPU (unsigned)v dead */
 #define CPU_LOCK_ACQUIRE       0x0008 /* Acquire all hotcpu locks */
 #define CPU_LOCK_RELEASE       0x0009 /* Release all hotcpu locks */
+#define CPU_DYING              0x000A /* CPU (unsigned)v not running any task,
+                                       * not handling interrupts, soon dead */
 
 /* Used for CPU hotplug events occuring while tasks are frozen due to a suspend
  * operation in progress
@@ -208,6 +210,7 @@ extern int __srcu_notifier_call_chain(struct srcu_notifier_head *nh,
 #define CPU_DOWN_PREPARE_FROZEN        (CPU_DOWN_PREPARE | CPU_TASKS_FROZEN)
 #define CPU_DOWN_FAILED_FROZEN (CPU_DOWN_FAILED | CPU_TASKS_FROZEN)
 #define CPU_DEAD_FROZEN                (CPU_DEAD | CPU_TASKS_FROZEN)
+#define CPU_DYING_FROZEN       (CPU_DYING | CPU_TASKS_FROZEN)
 
 #endif /* __KERNEL__ */
 #endif /* _LINUX_NOTIFIER_H */

diff --git a/kernel/cpu.c b/kernel/cpu.c
index 208cf3497c10230552e12de042a72a1da61fe955..181ae7086029e0b0eebb60cbc264b01b49f9297d 100644 (file)
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -103,11 +103,19 @@ static inline void check_for_tasks(int cpu)
        write_unlock_irq(&tasklist_lock);
 }
 
+struct take_cpu_down_param {
+       unsigned long mod;
+       void *hcpu;
+};
+
 /* Take this CPU down. */
-static int take_cpu_down(void *unused)
+static int take_cpu_down(void *_param)
 {
+       struct take_cpu_down_param *param = _param;
        int err;
 
+       raw_notifier_call_chain(&cpu_chain, CPU_DYING | param->mod,
+                               param->hcpu);
        /* Ensure this CPU doesn't handle any more interrupts. */
        err = __cpu_disable();
        if (err < 0)
@@ -127,6 +135,10 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
        cpumask_t old_allowed, tmp;
        void *hcpu = (void *)(long)cpu;
        unsigned long mod = tasks_frozen ? CPU_TASKS_FROZEN : 0;
+       struct take_cpu_down_param tcd_param = {
+               .mod = mod,
+               .hcpu = hcpu,
+       };
 
        if (num_online_cpus() == 1)
                return -EBUSY;
@@ -153,7 +165,7 @@ static int _cpu_down(unsigned int cpu, int tasks_frozen)
        set_cpus_allowed(current, tmp);
 
        mutex_lock(&cpu_bitmask_lock);
-       p = __stop_machine_run(take_cpu_down, NULL, cpu);
+       p = __stop_machine_run(take_cpu_down, &tcd_param, cpu);
        mutex_unlock(&cpu_bitmask_lock);
 
        if (IS_ERR(p) || cpu_online(cpu)) {