[PATCH v2] i386/kvm: add support for KVM_CAP_X86_DISABLE_EXITS

[Wanpeng Li <kernellwp@gmail.com>]

From: Wanpeng Li <wanpengli@tencent.com>

This patch adds support for KVM_CAP_X86_DISABLE_EXITS. Provides userspace with 
per-VM capability(KVM_CAP_X86_DISABLE_EXITS) to not intercept MWAIT/HLT/PAUSE 
in order that to improve latency in some workloads.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com> 
Cc: Eduardo Habkost <ehabkost@redhat.com>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
---
v1 -> v2:
 * disable kvm-hint-dedicated if kvm-pv-unhalt is specified

 linux-headers/linux/kvm.h |  6 +++++-
 target/i386/cpu.h         |  2 ++
 target/i386/kvm.c         | 15 +++++++++++++++
 3 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h
index a167be8..857df15 100644
--- a/linux-headers/linux/kvm.h
+++ b/linux-headers/linux/kvm.h
@@ -925,7 +925,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_GS 140
 #define KVM_CAP_S390_AIS 141
 #define KVM_CAP_SPAPR_TCE_VFIO 142
-#define KVM_CAP_X86_GUEST_MWAIT 143
+#define KVM_CAP_X86_DISABLE_EXITS 143
 #define KVM_CAP_ARM_USER_IRQ 144
 #define KVM_CAP_S390_CMMA_MIGRATION 145
 #define KVM_CAP_PPC_FWNMI 146
@@ -1508,6 +1508,10 @@ struct kvm_assigned_msix_entry {
 #define KVM_X2APIC_API_USE_32BIT_IDS            (1ULL << 0)
 #define KVM_X2APIC_API_DISABLE_BROADCAST_QUIRK  (1ULL << 1)
 
+#define KVM_X86_DISABLE_EXITS_MWAIT          (1 << 0)
+#define KVM_X86_DISABLE_EXITS_HLT            (1 << 1)
+#define KVM_X86_DISABLE_EXITS_PAUSE          (1 << 2)
+
 /* Available with KVM_CAP_ARM_USER_IRQ */
 
 /* Bits for run->s.regs.device_irq_level */
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 1b219fa..965de1b 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -685,6 +685,8 @@ typedef uint32_t FeatureWordArray[FEATURE_WORDS];
 #define CPUID_7_0_EDX_AVX512_4FMAPS (1U << 3) /* AVX512 Multiply Accumulation Single Precision */
 #define CPUID_7_0_EDX_SPEC_CTRL     (1U << 26) /* Speculation Control */
 
+#define KVM_PV_UNHALT (1U << 7)
+
 #define KVM_HINTS_DEDICATED (1U << 0)
 
 #define CPUID_8000_0008_EBX_IBPB    (1U << 12) /* Indirect Branch Prediction Barrier */
diff --git a/target/i386/kvm.c b/target/i386/kvm.c
index 6c49954..9357caa 100644
--- a/target/i386/kvm.c
+++ b/target/i386/kvm.c
@@ -1029,6 +1029,21 @@ int kvm_arch_init_vcpu(CPUState *cs)
         }
     }
 
+    if (env->features[FEAT_KVM_HINTS] & KVM_HINTS_DEDICATED) {
+        int disable_exits = kvm_check_extension(cs->kvm_state, KVM_CAP_X86_DISABLE_EXITS);
+
+        if (disable_exits) {
+            disable_exits &= (KVM_X86_DISABLE_EXITS_MWAIT |
+                              KVM_X86_DISABLE_EXITS_HLT |
+                              KVM_X86_DISABLE_EXITS_PAUSE);
+            if (env->user_features[KVM] & KVM_PV_UNHALT)
+                disable_exits &= ~KVM_X86_DISABLE_EXITS_HLT;
+        }
+        if (kvm_vm_enable_cap(cs->kvm_state, KVM_CAP_X86_DISABLE_EXITS, 0, disable_exits)) {
+            error_report("kvm: DISABLE EXITS not supported");
+        }
+    }
+
     qemu_add_vm_change_state_handler(cpu_update_state, env);
 
     c = cpuid_find_entry(&cpuid_data.cpuid, 1, 0);
-- 
2.7.4