KVM: VMX: provide the vmclear function and a bitmap to support VMCLEAR in kdump

The vmclear function will be assigned to the callback function pointer
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 <zhangyanfei@cn.fujitsu.com>
Acked-by: Eric W. Biederman <ebiederm@xmission.com>
Signed-off-by: Gleb Natapov <gleb@redhat.com>

1 files changed, 67 insertions, 0 deletions

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 94833e2fe78c..1a30fd5c3fb2 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -42,6 +42,7 @@
 #include <asm/i387.h>
 #include <asm/xcr.h>
 #include <asm/perf_event.h>
+#include <asm/kexec.h>
 
 #include "trace.h"
 
@@ -987,6 +988,46 @@ 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 crash_vmclear_local_loaded_vmcss(void)
+{
+        int cpu = raw_smp_processor_id();
+        struct loaded_vmcs *v;
+
+        if (!crash_local_vmclear_enabled(cpu))
+                return;
+
+        list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
+                            loaded_vmcss_on_cpu_link)
+                vmcs_clear(v->vmcs);
+}
+#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;
@@ -996,6 +1037,7 @@ 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);
 
         /*
@@ -1007,6 +1049,7 @@ static void __loaded_vmcs_clear(void *arg)
         smp_wmb();
 
         loaded_vmcs_init(loaded_vmcs);
+        crash_enable_local_vmclear(cpu);
 }
 
 static void loaded_vmcs_clear(struct loaded_vmcs *loaded_vmcs)
@@ -1530,6 +1573,7 @@ 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);
 
                 /*
                  * Read loaded_vmcs->cpu should be before fetching
@@ -1540,6 +1584,7 @@ static void vmx_vcpu_load(struct kvm_vcpu *vcpu, int 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();
 
                 /*
@@ -2353,6 +2398,18 @@ 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;
@@ -7383,6 +7440,11 @@ static int __init vmx_init(void)
         if (r)
                 goto out3;
 
+#ifdef CONFIG_KEXEC
+        rcu_assign_pointer(crash_vmclear_loaded_vmcss,
+                           crash_vmclear_local_loaded_vmcss);
+#endif
+
         vmx_disable_intercept_for_msr(MSR_FS_BASE, false);
         vmx_disable_intercept_for_msr(MSR_GS_BASE, false);
         vmx_disable_intercept_for_msr(MSR_KERNEL_GS_BASE, true);
@@ -7420,6 +7482,11 @@ static void __exit vmx_exit(void)
         free_page((unsigned long)vmx_io_bitmap_b);
         free_page((unsigned long)vmx_io_bitmap_a);
 
+#ifdef CONFIG_KEXEC
+        rcu_assign_pointer(crash_vmclear_loaded_vmcss, NULL);
+        synchronize_rcu();
+#endif
+
         kvm_exit();
 }