[PATCH] kvm: better MWAIT emulation for guests

[Michael S. Tsirkin]

Some guests call mwait without checking the cpu flags.  We currently
emulate that as a NOP but on VMX we can do better: let guest stop the
CPU until timer or IPI.  CPU will be busy but that isn't any worse than
a NOP emulation.

Note that mwait within guests is not the same as on real hardware
because you must halt if you want to go deep into sleep.  Thus it isn't
a good idea to use the regular MWAIT flag in CPUID for that.  Add a flag
in the hypervisor leaf instead.

Signed-off-by: Michael S. Tsirkin <mst@xxxxxxxxxx>
---
 Documentation/virtual/kvm/cpuid.txt  | 3 +++
 arch/x86/include/uapi/asm/kvm_para.h | 1 +
 arch/x86/kvm/cpuid.c                 | 3 +++
 arch/x86/kvm/vmx.c                   | 4 ----
 4 files changed, 7 insertions(+), 4 deletions(-)

diff --git a/Documentation/virtual/kvm/cpuid.txt b/Documentation/virtual/kvm/cpuid.txt
index 3c65feb..5caa234 100644
--- a/Documentation/virtual/kvm/cpuid.txt
+++ b/Documentation/virtual/kvm/cpuid.txt
@@ -54,6 +54,9 @@ KVM_FEATURE_PV_UNHALT              ||     7 || guest checks this feature bit
                                    ||       || before enabling paravirtualized
                                    ||       || spinlock support.
 ------------------------------------------------------------------------------
+KVM_FEATURE_MWAIT                  ||     8 || guest can use monitor/mwait
+                                   ||       || to halt the VCPU.
+------------------------------------------------------------------------------
 KVM_FEATURE_CLOCKSOURCE_STABLE_BIT ||    24 || host will warn if no guest-side
                                    ||       || per-cpu warps are expected in
                                    ||       || kvmclock.
diff --git a/arch/x86/include/uapi/asm/kvm_para.h b/arch/x86/include/uapi/asm/kvm_para.h
index cff0bb6..9cc77a7 100644
--- a/arch/x86/include/uapi/asm/kvm_para.h
+++ b/arch/x86/include/uapi/asm/kvm_para.h
@@ -24,6 +24,7 @@
 #define KVM_FEATURE_STEAL_TIME		5
 #define KVM_FEATURE_PV_EOI		6
 #define KVM_FEATURE_PV_UNHALT		7
+#define KVM_FEATURE_MWAIT		8
 
 /* The last 8 bits are used to indicate how to interpret the flags field
  * in pvclock structure. If no bits are set, all flags are ignored.
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index efde6cc..fe3d292 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -594,6 +594,9 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function,
 		if (sched_info_on())
 			entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
 
+		if (this_cpu_has(X86_FEATURE_MWAIT))
+			entry->eax = (1 << KVM_FEATURE_MWAIT);
+
 		entry->ebx = 0;
 		entry->ecx = 0;
 		entry->edx = 0;
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 4bfe349..b167aba 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3547,13 +3547,9 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
 	      CPU_BASED_USE_IO_BITMAPS |
 	      CPU_BASED_MOV_DR_EXITING |
 	      CPU_BASED_USE_TSC_OFFSETING |
-	      CPU_BASED_MWAIT_EXITING |
-	      CPU_BASED_MONITOR_EXITING |
 	      CPU_BASED_INVLPG_EXITING |
 	      CPU_BASED_RDPMC_EXITING;
 
-	printk(KERN_ERR "cleared CPU_BASED_MWAIT_EXITING + CPU_BASED_MONITOR_EXITING\n");
-
 	opt = CPU_BASED_TPR_SHADOW |
 	      CPU_BASED_USE_MSR_BITMAPS |
 	      CPU_BASED_ACTIVATE_SECONDARY_CONTROLS;
-- 
MST