KVM: X86: Provide a capability to disable PAUSE intercepts

Allow to disable pause loop exit/pause filtering on a per VM basis.

If some VMs have dedicated host CPUs, they won't be negatively affected
due to needlessly intercepted PAUSE instructions.

Thanks to Jan H. Schönherr's initial patch.

Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Jan H. Schönherr <jschoenh@amazon.de>
Signed-off-by: Wanpeng Li <wanpengli@tencent.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 31f4186698275cac9acb878acecacba10bbc5fae..8fb60287d987dd64be888a1dddbc61ed65c6e522 100644 (file)
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -813,6 +813,7 @@ struct kvm_arch {
 
        bool mwait_in_guest;
        bool hlt_in_guest;
+       bool pause_in_guest;
 
        bool ept_identity_pagetable_done;
        gpa_t ept_identity_map_addr;

diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
index 0f801d82f49366f3444c404eb649f02379f34f87..9729b7e59cc9d6cf8dddb3400dd9d0a66cab61c4 100644 (file)
--- a/arch/x86/kvm/svm.c
+++ b/arch/x86/kvm/svm.c
@@ -1460,7 +1460,8 @@ static void init_vmcb(struct vcpu_svm *svm)
        svm->nested.vmcb = 0;
        svm->vcpu.arch.hflags = 0;
 
-       if (boot_cpu_has(X86_FEATURE_PAUSEFILTER)) {
+       if (boot_cpu_has(X86_FEATURE_PAUSEFILTER) &&
+           !kvm_pause_in_guest(svm->vcpu.kvm)) {
                control->pause_filter_count = 3000;
                set_intercept(svm, INTERCEPT_PAUSE);
        }

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 65747d1194acf361cf9ee68b138bc2465cf9da50..12473e769b0d5137388c0ca8f57d495d3cc628cd 100644 (file)
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -5595,7 +5595,7 @@ static void vmx_compute_secondary_exec_control(struct vcpu_vmx *vmx)
        }
        if (!enable_unrestricted_guest)
                exec_control &= ~SECONDARY_EXEC_UNRESTRICTED_GUEST;
-       if (!ple_gap)
+       if (kvm_pause_in_guest(vmx->vcpu.kvm))
                exec_control &= ~SECONDARY_EXEC_PAUSE_LOOP_EXITING;
        if (!kvm_vcpu_apicv_active(vcpu))
                exec_control &= ~(SECONDARY_EXEC_APIC_REGISTER_VIRT |
@@ -5758,7 +5758,7 @@ static void vmx_vcpu_setup(struct vcpu_vmx *vmx)
                vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc)));
        }
 
-       if (ple_gap) {
+       if (!kvm_pause_in_guest(vmx->vcpu.kvm)) {
                vmcs_write32(PLE_GAP, ple_gap);
                vmx->ple_window = ple_window;
                vmx->ple_window_dirty = true;
@@ -7207,7 +7207,7 @@ static __exit void hardware_unsetup(void)
  */
 static int handle_pause(struct kvm_vcpu *vcpu)
 {
-       if (ple_gap)
+       if (!kvm_pause_in_guest(vcpu->kvm))
                grow_ple_window(vcpu);
 
        /*
@@ -9903,6 +9903,13 @@ free_vcpu:
        return ERR_PTR(err);
 }
 
+static int vmx_vm_init(struct kvm *kvm)
+{
+       if (!ple_gap)
+               kvm->arch.pause_in_guest = true;
+       return 0;
+}
+
 static void __init vmx_check_processor_compat(void *rtn)
 {
        struct vmcs_config vmcs_conf;
@@ -12052,7 +12059,7 @@ static void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu)
 
 static void vmx_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
-       if (ple_gap)
+       if (!kvm_pause_in_guest(vcpu->kvm))
                shrink_ple_window(vcpu);
 }
 
@@ -12412,6 +12419,8 @@ static struct kvm_x86_ops vmx_x86_ops __ro_after_init = {
        .cpu_has_accelerated_tpr = report_flexpriority,
        .cpu_has_high_real_mode_segbase = vmx_has_high_real_mode_segbase,
 
+       .vm_init = vmx_vm_init,
+
        .vcpu_create = vmx_create_vcpu,
        .vcpu_free = vmx_free_vcpu,
        .vcpu_reset = vmx_vcpu_reset,

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9e6aaf62bf3cd889b5d27be67b67d993d4152005..26a8cd93be0c1353057733122946c02531242041 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2878,7 +2878,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
                r = KVM_CLOCK_TSC_STABLE;
                break;
        case KVM_CAP_X86_DISABLE_EXITS:
-               r |=  KVM_X86_DISABLE_EXITS_HTL;
+               r |=  KVM_X86_DISABLE_EXITS_HTL | KVM_X86_DISABLE_EXITS_PAUSE;
                if(kvm_can_mwait_in_guest())
                        r |= KVM_X86_DISABLE_EXITS_MWAIT;
                break;
@@ -4235,6 +4235,8 @@ split_irqchip_unlock:
                        kvm->arch.mwait_in_guest = true;
                if (cap->args[0] & KVM_X86_DISABLE_EXITS_HTL)
                        kvm->arch.hlt_in_guest = true;
+               if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE)
+                       kvm->arch.pause_in_guest = true;
                r = 0;
                break;
        default:

diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 6d14589c1a910702f58b6b0707d47f5754e23d13..b620cfa8e8d5ccdaf57c4e3cdc96d6b2c088f8e7 100644 (file)
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -266,8 +266,10 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
 
 #define KVM_X86_DISABLE_EXITS_MWAIT          (1 << 0)
 #define KVM_X86_DISABLE_EXITS_HTL            (1 << 1)
+#define KVM_X86_DISABLE_EXITS_PAUSE          (1 << 2)
 #define KVM_X86_DISABLE_VALID_EXITS          (KVM_X86_DISABLE_EXITS_MWAIT | \
-                                              KVM_X86_DISABLE_EXITS_HTL)
+                                              KVM_X86_DISABLE_EXITS_HTL | \
+                                              KVM_X86_DISABLE_EXITS_PAUSE)
 
 static inline bool kvm_mwait_in_guest(struct kvm *kvm)
 {
@@ -279,4 +281,9 @@ static inline bool kvm_hlt_in_guest(struct kvm *kvm)
        return kvm->arch.hlt_in_guest;
 }
 
+static inline bool kvm_pause_in_guest(struct kvm *kvm)
+{
+       return kvm->arch.pause_in_guest;
+}
+
 #endif