On emergency_restart, we may need to use an NMI to disable virtualization
on all CPUs. We do that using nmi_shootdown_cpus() if VMX is enabled.
Finding a proper point to hook the nmi_shootdown_cpus() call isn't
trivial, as the non-emergency machine_restart() (that doesn't need the
NMI tricks) uses machine_emergency_restart() directly.
The solution to make this work without adding a new function or argument
to machine_ops was setting a 'reboot_emergency' flag that tells if
native_machine_emergency_restart() needs to do the virt cleanup or not.
Signed-off-by: Eduardo Habkost <ehabkost at redhat.com>
---
arch/x86/kernel/reboot.c | 63 ++++++++++++++++++++++++++++++++++++++++++++-
1 files changed, 61 insertions(+), 2 deletions(-)
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 6f05a28..a5f8c09 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -12,6 +12,7 @@
#include <asm/proto.h>
#include <asm/reboot_fixups.h>
#include <asm/reboot.h>
+#include <asm/virtext.h>
#ifdef CONFIG_X86_32
# include <linux/dmi.h>
@@ -39,6 +40,13 @@ int reboot_force;
static int reboot_cpu = -1;
#endif
+/* This is set if we need to go through the 'emergency' path.
+ * When machine_emergency_restart() is called, we may be on
+ * an inconsistent state and won't be able to do a clean cleanup
+ */
+static int reboot_emergency;
+
+
/* This is set by the PCI code if either type 1 or type 2 PCI is detected */
bool port_cf9_safe = false;
@@ -359,6 +367,48 @@ static inline void kb_wait(void)
}
}
+static void vmxoff_nmi(int cpu, struct die_args *args)
+{
+ cpu_emergency_vmxoff();
+}
+
+/* Use NMIs as IPIs to tell all CPUs to disable virtualization
+ */
+static void emergency_vmx_disable_all(void)
+{
+ /* Just make sure we won't change CPUs while doing this */
+ local_irq_disable();
+
+ /* We need to disable VMX on all CPUs before rebooting, otherwise
+ * we risk hanging up the machine, because the CPU ignore INIT
+ * signals when VMX is enabled.
+ *
+ * We can't take any locks and we may be on an inconsistent
+ * state, so we use NMIs as IPIs to tell the other CPUs to disable
+ * VMX and halt.
+ *
+ * For safety, we will avoid running the nmi_shootdown_cpus()
+ * stuff unnecessarily, but we don't have a way to check
+ * if other CPUs have VMX enabled. So we will call it only if the
+ * CPU we are running on has VMX enabled.
+ *
+ * We will miss cases where VMX is not enabled on all CPUs. This
+ * shouldn't do much harm because KVM always enable VMX on all
+ * CPUs anyway. But we can miss it on the small window where KVM
+ * is still enabling VMX.
+ */
+ if (cpu_has_vmx() && cpu_vmx_enabled()) {
+ /* Disable VMX on this CPU.
+ */
+ cpu_vmxoff();
+
+ /* Halt and disable VMX on the other CPUs */
+ nmi_shootdown_cpus(vmxoff_nmi);
+
+ }
+}
+
+
void __attribute__((weak)) mach_reboot_fixups(void)
{
}
@@ -367,6 +417,9 @@ static void native_machine_emergency_restart(void)
{
int i;
+ if (reboot_emergency)
+ emergency_vmx_disable_all();
+
/* Tell the BIOS if we want cold or warm reboot */
*((unsigned short *)__va(0x472)) = reboot_mode;
@@ -473,13 +526,19 @@ void native_machine_shutdown(void)
#endif
}
+static void __machine_emergency_restart(int emergency)
+{
+ reboot_emergency = emergency;
+ machine_ops.emergency_restart();
+}
+
static void native_machine_restart(char *__unused)
{
printk("machine restart\n");
if (!reboot_force)
machine_shutdown();
- machine_emergency_restart();
+ __machine_emergency_restart(0);
}
static void native_machine_halt(void)
@@ -523,7 +582,7 @@ void machine_shutdown(void)
void machine_emergency_restart(void)
{
- machine_ops.emergency_restart();
+ __machine_emergency_restart(1);
}
void machine_restart(char *cmd)
--
1.5.5.GIT
