[RFC v2 PATCH 05/21] KVM: Enable/Disable virtualization on slave CPUs are activated/dying

[Tomoki Sekiyama <tomoki.sekiyama.qu@hitachi.com>]

Enable virtualization when slave CPUs are activated, and disable when
the CPUs are dying using slave CPU notifier call chain.

In x86, TSC kHz must also be initialized by tsc_khz_changed when the
new slave CPUs are activated.

Signed-off-by: Tomoki Sekiyama <tomoki.sekiyama.qu@hitachi.com>
Cc: Avi Kivity <avi@redhat.com>
Cc: Marcelo Tosatti <mtosatti@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
---

 arch/x86/kvm/x86.c  |   16 ++++++++++++++++
 virt/kvm/kvm_main.c |   30 ++++++++++++++++++++++++++++--
 2 files changed, 44 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 148ed66..7501cc4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -61,6 +61,7 @@
 #include <asm/xcr.h>
 #include <asm/pvclock.h>
 #include <asm/div64.h>
+#include <asm/cpu.h>
 
 #define MAX_IO_MSRS 256
 #define KVM_MAX_MCE_BANKS 32
@@ -4782,9 +4783,15 @@ static int kvmclock_cpu_notifier(struct notifier_block *nfb,
 	switch (action) {
 		case CPU_ONLINE:
 		case CPU_DOWN_FAILED:
+#ifdef CONFIG_SLAVE_CPU
+		case CPU_SLAVE_UP:
+#endif
 			smp_call_function_single(cpu, tsc_khz_changed, NULL, 1);
 			break;
 		case CPU_DOWN_PREPARE:
+#ifdef CONFIG_SLAVE_CPU
+		case CPU_SLAVE_DYING:
+#endif
 			smp_call_function_single(cpu, tsc_bad, NULL, 1);
 			break;
 	}
@@ -4796,12 +4803,18 @@ static struct notifier_block kvmclock_cpu_notifier_block = {
 	.priority = -INT_MAX
 };
 
+static struct notifier_block kvmclock_slave_cpu_notifier_block = {
+	.notifier_call  = kvmclock_cpu_notifier,
+	.priority = -INT_MAX
+};
+
 static void kvm_timer_init(void)
 {
 	int cpu;
 
 	max_tsc_khz = tsc_khz;
 	register_hotcpu_notifier(&kvmclock_cpu_notifier_block);
+	register_slave_cpu_notifier(&kvmclock_slave_cpu_notifier_block);
 	if (!boot_cpu_has(X86_FEATURE_CONSTANT_TSC)) {
 #ifdef CONFIG_CPU_FREQ
 		struct cpufreq_policy policy;
@@ -4818,6 +4831,8 @@ static void kvm_timer_init(void)
 	pr_debug("kvm: max_tsc_khz = %ld\n", max_tsc_khz);
 	for_each_online_cpu(cpu)
 		smp_call_function_single(cpu, tsc_khz_changed, NULL, 1);
+	for_each_slave_cpu(cpu)
+		smp_call_function_single(cpu, tsc_khz_changed, NULL, 1);
 }
 
 static DEFINE_PER_CPU(struct kvm_vcpu *, current_vcpu);
@@ -4943,6 +4958,7 @@ void kvm_arch_exit(void)
 		cpufreq_unregister_notifier(&kvmclock_cpufreq_notifier_block,
 					    CPUFREQ_TRANSITION_NOTIFIER);
 	unregister_hotcpu_notifier(&kvmclock_cpu_notifier_block);
+	unregister_slave_cpu_notifier(&kvmclock_slave_cpu_notifier_block);
 	kvm_x86_ops = NULL;
 	kvm_mmu_module_exit();
 }
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d617f69..dc86e9a 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -54,6 +54,9 @@
 #include <asm/io.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
+#ifdef CONFIG_X86
+#include <asm/cpu.h>
+#endif
 
 #include "coalesced_mmio.h"
 #include "async_pf.h"
@@ -2336,11 +2339,17 @@ static void hardware_disable(void *junk)
 
 static void hardware_disable_all_nolock(void)
 {
+	int cpu;
+
 	BUG_ON(!kvm_usage_count);
 
 	kvm_usage_count--;
-	if (!kvm_usage_count)
+	if (!kvm_usage_count) {
 		on_each_cpu(hardware_disable_nolock, NULL, 1);
+		for_each_slave_cpu(cpu)
+			smp_call_function_single(cpu, hardware_disable_nolock,
+						 NULL, 1);
+	}
 }
 
 static void hardware_disable_all(void)
@@ -2353,6 +2362,7 @@ static void hardware_disable_all(void)
 static int hardware_enable_all(void)
 {
 	int r = 0;
+	int cpu;
 
 	raw_spin_lock(&kvm_lock);
 
@@ -2360,6 +2370,9 @@ static int hardware_enable_all(void)
 	if (kvm_usage_count == 1) {
 		atomic_set(&hardware_enable_failed, 0);
 		on_each_cpu(hardware_enable_nolock, NULL, 1);
+		for_each_slave_cpu(cpu)
+			smp_call_function_single(cpu, hardware_enable_nolock,
+						 NULL, 1);
 
 		if (atomic_read(&hardware_enable_failed)) {
 			hardware_disable_all_nolock();
@@ -2383,11 +2396,17 @@ static int kvm_cpu_hotplug(struct notifier_block *notifier, unsigned long val,
 	val &= ~CPU_TASKS_FROZEN;
 	switch (val) {
 	case CPU_DYING:
+#ifdef CONFIG_SLAVE_CPU
+	case CPU_SLAVE_DYING:
+#endif
 		printk(KERN_INFO "kvm: disabling virtualization on CPU%d\n",
 		       cpu);
 		hardware_disable(NULL);
 		break;
 	case CPU_STARTING:
+#ifdef CONFIG_SLAVE_CPU
+	case CPU_SLAVE_UP:
+#endif
 		printk(KERN_INFO "kvm: enabling virtualization on CPU%d\n",
 		       cpu);
 		hardware_enable(NULL);
@@ -2605,6 +2624,10 @@ static struct notifier_block kvm_cpu_notifier = {
 	.notifier_call = kvm_cpu_hotplug,
 };
 
+static struct notifier_block kvm_slave_cpu_notifier = {
+	.notifier_call = kvm_cpu_hotplug,
+};
+
 static int vm_stat_get(void *_offset, u64 *val)
 {
 	unsigned offset = (long)_offset;
@@ -2768,7 +2791,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	if (r < 0)
 		goto out_free_0a;
 
-	for_each_online_cpu(cpu) {
+	for_each_cpu(cpu, cpu_online_or_slave_mask) {
 		smp_call_function_single(cpu,
 				kvm_arch_check_processor_compat,
 				&r, 1);
@@ -2779,6 +2802,7 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	r = register_cpu_notifier(&kvm_cpu_notifier);
 	if (r)
 		goto out_free_2;
+	register_slave_cpu_notifier(&kvm_slave_cpu_notifier);
 	register_reboot_notifier(&kvm_reboot_notifier);
 
 	/* A kmem cache lets us meet the alignment requirements of fx_save. */
@@ -2826,6 +2850,7 @@ out_free:
 	kmem_cache_destroy(kvm_vcpu_cache);
 out_free_3:
 	unregister_reboot_notifier(&kvm_reboot_notifier);
+	unregister_slave_cpu_notifier(&kvm_slave_cpu_notifier);
 	unregister_cpu_notifier(&kvm_cpu_notifier);
 out_free_2:
 out_free_1:
@@ -2853,6 +2878,7 @@ void kvm_exit(void)
 	kvm_async_pf_deinit();
 	unregister_syscore_ops(&kvm_syscore_ops);
 	unregister_reboot_notifier(&kvm_reboot_notifier);
+	unregister_slave_cpu_notifier(&kvm_slave_cpu_notifier);
 	unregister_cpu_notifier(&kvm_cpu_notifier);
 	on_each_cpu(hardware_disable_nolock, NULL, 1);
 	kvm_arch_hardware_unsetup();