x86: vmclear vmcss on all cpus when doing kdump if necessary

The notifier will be registered in vmclear_notifier_list when loading kvm-intel module. And the bitmap indicates whether we should do VMCLEAR operation in kdump. The bits in the bitmap are set/unset according to different conditions.

Signed-off-by Zhang Yanfei <[email protected]>

---
 arch/x86/kvm/vmx.c |   77 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 76 insertions(+), 1 deletions(-)

arch/x86/kvm/vmx.c +60 -1

index 4ff0ab9..eea55b3 100644
@@ -41,6 +41,7 @@
 #include <asm/i387.h>
 #include <asm/xcr.h>
 #include <asm/perf_event.h>
+#include <asm/kexec.h>
 
 #include "trace.h"
 

@@ -963,6 +964,49 @@ static void vmcs_load(struct vmcs *vmcs)
 		       vmcs, phys_addr);
 }
 
+#ifdef CONFIG_KEXEC
+/*
+ * This bitmap is used to indicate whether the vmclear
+ * operation is enabled on all cpus. All disabled by
+ * default.
+ */
+static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE;
+
+static inline void crash_enable_local_vmclear(int cpu)
+{
+	cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap);
+}
+
+static inline void crash_disable_local_vmclear(int cpu)
+{
+	cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap);
+}
+
+static inline int crash_local_vmclear_enabled(int cpu)
+{
+	return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap);
+}
+
+static void vmclear_local_loaded_vmcss(void);
+static int crash_vmclear_local_loaded_vmcss(struct notifier_block *this,
+					    unsigned long val, void *ptr)
+{
+	int cpu = raw_smp_processor_id();
+
+	if (crash_local_vmclear_enabled(cpu))
+		vmclear_local_loaded_vmcss();
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block crash_vmclear_notifier = {
+	.notifier_call = crash_vmclear_local_loaded_vmcss,
+};
+#else
+static inline void crash_enable_local_vmclear(int cpu) { }
+static inline void crash_disable_local_vmclear(int cpu) { }
+#endif /* CONFIG_KEXEC */
+
 static void __loaded_vmcs_clear(void *arg)
 {
 	struct loaded_vmcs *loaded_vmcs = arg;

@@ -972,8 +1016,10 @@ static void __loaded_vmcs_clear(void *arg)
 		return; /* vcpu migration can race with cpu offline */
 	if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs)
 		per_cpu(current_vmcs, cpu) = NULL;
+	crash_disable_local_vmclear(cpu);
 	list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link);
 	loaded_vmcs_init(loaded_vmcs);
+	crash_enable_local_vmclear(cpu);
 }
 
 static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)

@@ -1491,8 +1537,10 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 		local_irq_disable();
+		crash_disable_local_vmclear(cpu);
 		list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link,
 			 &per_cpu(loaded_vmcss_on_cpu, cpu));
+		crash_enable_local_vmclear(cpu);
 		local_irq_enable();
 
 		/*

@@ -2302,6 +2350,18 @@ static int hardware_enable(void *garbage)
 		return -EBUSY;
 
 	INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
+
+	/*
+	 * Now we can enable the vmclear operation in kdump
+	 * since the loaded_vmcss_on_cpu list on this cpu
+	 * has been initialized.
+	 *
+	 * Though the cpu is not in VMX operation now, there
+	 * is no problem to enable the vmclear operation
+	 * for the loaded_vmcss_on_cpu list is empty!
+	 */
+	crash_enable_local_vmclear(cpu);
+
 	rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
 
 	test_bits = FEATURE_CONTROL_LOCKED;

@@ -2335,7 +2395,6 @@ static void vmclear_local_loaded_vmcss(void)
 		__loaded_vmcs_clear(v);
 }
 
-
 /* Just like cpu_vmxoff(), but with the __kvm_handle_fault_on_reboot()
  * tricks.
  */

Quoted 126 lines · Zhang Yanfei

The notifier will be registered in vmclear_notifier_list when loading kvm-intel module. And the bitmap indicates whether we should do VMCLEAR operation in kdump. The bits in the bitmap are set/unset according to different conditions.

Signed-off-by Zhang Yanfei <[email protected]>

---
 arch/x86/kvm/vmx.c |   77 +++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 76 insertions(+), 1 deletions(-)

arch/x86/kvm/vmx.c +61 -1

index 4ff0ab9..eea55b3 100644
@@ -41,6 +41,7 @@
 #include <asm/i387.h>
 #include <asm/xcr.h>
 #include <asm/perf_event.h>
+#include <asm/kexec.h>
 
 #include "trace.h"
 

@@ -963,6 +964,49 @@ static void vmcs_load(struct vmcs *vmcs)
 		       vmcs, phys_addr);
 }
 
+#ifdef CONFIG_KEXEC
+/*
+ * This bitmap is used to indicate whether the vmclear
+ * operation is enabled on all cpus. All disabled by
+ * default.
+ */
+static cpumask_t crash_vmclear_enabled_bitmap = CPU_MASK_NONE;
+
+static inline void crash_enable_local_vmclear(int cpu)
+{
+	cpumask_set_cpu(cpu, &crash_vmclear_enabled_bitmap);
+}
+
+static inline void crash_disable_local_vmclear(int cpu)
+{
+	cpumask_clear_cpu(cpu, &crash_vmclear_enabled_bitmap);
+}
+
+static inline int crash_local_vmclear_enabled(int cpu)
+{
+	return cpumask_test_cpu(cpu, &crash_vmclear_enabled_bitmap);
+}
+
+static void vmclear_local_loaded_vmcss(void);
+static int crash_vmclear_local_loaded_vmcss(struct notifier_block *this,
+					    unsigned long val, void *ptr)
+{
+	int cpu = raw_smp_processor_id();
+
+	if (crash_local_vmclear_enabled(cpu))
+		vmclear_local_loaded_vmcss();
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block crash_vmclear_notifier = {
+	.notifier_call = crash_vmclear_local_loaded_vmcss,
+};
+#else
+static inline void crash_enable_local_vmclear(int cpu) { }
+static inline void crash_disable_local_vmclear(int cpu) { }
+#endif /* CONFIG_KEXEC */
+
 static void __loaded_vmcs_clear(void *arg)
 {
 	struct loaded_vmcs *loaded_vmcs = arg;

@@ -972,8 +1016,10 @@ static void __loaded_vmcs_clear(void *arg)
 		return; /* vcpu migration can race with cpu offline */
 	if (per_cpu(current_vmcs, cpu) == loaded_vmcs->vmcs)
 		per_cpu(current_vmcs, cpu) = NULL;
+	crash_disable_local_vmclear(cpu);
 	list_del(&loaded_vmcs->loaded_vmcss_on_cpu_link);
 	loaded_vmcs_init(loaded_vmcs);
+	crash_enable_local_vmclear(cpu);
 }
 
 static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)

@@ -1491,8 +1537,10 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 		kvm_make_request(KVM_REQ_TLB_FLUSH, vcpu);
 		local_irq_disable();
+		crash_disable_local_vmclear(cpu);
 		list_add(&vmx->loaded_vmcs->loaded_vmcss_on_cpu_link,
 			 &per_cpu(loaded_vmcss_on_cpu, cpu));
+		crash_enable_local_vmclear(cpu);
 		local_irq_enable();
 
 		/*

@@ -2302,6 +2350,18 @@ static int hardware_enable(void *garbage)
 		return -EBUSY;
 
 	INIT_LIST_HEAD(&per_cpu(loaded_vmcss_on_cpu, cpu));
+
+	/*
+	 * Now we can enable the vmclear operation in kdump
+	 * since the loaded_vmcss_on_cpu list on this cpu
+	 * has been initialized.
+	 *
+	 * Though the cpu is not in VMX operation now, there
+	 * is no problem to enable the vmclear operation
+	 * for the loaded_vmcss_on_cpu list is empty!
+	 */
+	crash_enable_local_vmclear(cpu);
+
 	rdmsrl(MSR_IA32_FEATURE_CONTROL, old);
 
 	test_bits = FEATURE_CONTROL_LOCKED;

@@ -2335,7 +2395,6 @@ static void vmclear_local_loaded_vmcss(void)
 		__loaded_vmcs_clear(v);
 }
 
-
 /* Just like cpu_vmxoff(), but with the __kvm_handle_fault_on_reboot()
  * tricks.
  */

@@ -2348,6 +2407,12 @@ static void hardware_disable(void *garbage)
 {
 	if (vmm_exclusive) {
 		vmclear_local_loaded_vmcss();
+		/*

arch/x86/kvm/vmx.c static void hardware_disable(void *garbage) · line 2416

Quoted 6 lines

arch/x86/kvm/vmx.c +5 -0

+		 * vmclear operation in kdump should be disabled here
+		 * because the cpu is going to exit VMX operation
+		 * and the loaded_vmcss_on_cpu list may not be empty!
+		 */
+		crash_disable_local_vmclear(raw_smp_processor_id());
 		kvm_cpu_vmxoff();

How come its not empty? vmclear_local_loaded_vmcss cleared it, didnt it?