x86/kexec: VMCLEAR VMCSs loaded on all cpus if necessary

This patch provides a way to VMCLEAR VMCSs related to guests
on all cpus before executing the VMXOFF when doing kdump. This
is used to ensure the VMCSs in the vmcore updated and
non-corrupted.

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>

arch/x86/include/asm/kexec.h

@@ -163,6 +163,8 @@ struct kimage_arch {
 };
 #endif
 
+extern void (*crash_vmclear_loaded_vmcss)(void);
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_X86_KEXEC_H */

arch/x86/kernel/crash.c

@@ -16,6 +16,7 @@
 #include <linux/delay.h>
 #include <linux/elf.h>
 #include <linux/elfcore.h>
+#include <linux/module.h>
 
 #include <asm/processor.h>
 #include <asm/hardirq.h>
@@ -30,6 +31,27 @@
 
 int in_crash_kexec;
 
+/*
+ * This is used to VMCLEAR all VMCSs loaded on the
+ * processor. And when loading kvm_intel module, the
+ * callback function pointer will be assigned.
+ *
+ * protected by rcu.
+ */
+void (*crash_vmclear_loaded_vmcss)(void) = NULL;
+EXPORT_SYMBOL_GPL(crash_vmclear_loaded_vmcss);
+
+static inline void cpu_crash_vmclear_loaded_vmcss(void)
+{
+	void (*do_vmclear_operation)(void) = NULL;
+
+	rcu_read_lock();
+	do_vmclear_operation = rcu_dereference(crash_vmclear_loaded_vmcss);
+	if (do_vmclear_operation)
+		do_vmclear_operation();
+	rcu_read_unlock();
+}
+
 #if defined(CONFIG_SMP) && defined(CONFIG_X86_LOCAL_APIC)
 
 static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
@@ -46,6 +68,11 @@ static void kdump_nmi_callback(int cpu, struct pt_regs *regs)
 #endif
 	crash_save_cpu(regs, cpu);
 
+	/*
+	 * VMCLEAR VMCSs loaded on all cpus if needed.
+	 */
+	cpu_crash_vmclear_loaded_vmcss();
+
 	/* Disable VMX or SVM if needed.
 	 *
 	 * We need to disable virtualization on all CPUs.
@@ -88,6 +115,11 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
 
 	kdump_nmi_shootdown_cpus();
 
+	/*
+	 * VMCLEAR VMCSs loaded on this cpu if needed.
+	 */
+	cpu_crash_vmclear_loaded_vmcss();
+
 	/* Booting kdump kernel with VMX or SVM enabled won't work,
 	 * because (among other limitations) we can't disable paging
 	 * with the virt flags.