[patch 3/3] KVM: x86: frequency change hypercalls

[Marcelo Tosatti]

Implement min/max/up/down frequency change 
KVM hypercalls. To be used by DPDK implementation.

Also allow such hypercalls from guest userspace.

Signed-off-by: Marcelo Tosatti <mtosatti@xxxxxxxxxx>

---
 Documentation/virtual/kvm/hypercalls.txt |   45 +++++++++++++++++++
 arch/x86/kvm/x86.c                       |   71 ++++++++++++++++++++++++++++++-
 include/uapi/linux/kvm_para.h            |    5 ++
 3 files changed, 120 insertions(+), 1 deletion(-)

Index: kvm-pvfreq/arch/x86/kvm/x86.c
===================================================================
--- kvm-pvfreq.orig/arch/x86/kvm/x86.c	2017-02-02 11:17:17.063756725 -0200
+++ kvm-pvfreq/arch/x86/kvm/x86.c	2017-02-02 11:17:17.822752510 -0200
@@ -6219,10 +6219,58 @@
 	kvm_x86_ops->refresh_apicv_exec_ctrl(vcpu);
 }
 
+#ifdef CONFIG_CPU_FREQ_GOV_USERSPACE
+/* call into cpufreq-userspace governor */
+static int kvm_pvfreq_up(struct kvm_vcpu *vcpu)
+{
+	int ret;
+	int cpu = get_cpu();
+
+	ret = cpufreq_userspace_freq_up(cpu);
+	put_cpu();
+
+	return ret;
+}
+
+static int kvm_pvfreq_down(struct kvm_vcpu *vcpu)
+{
+	int ret;
+	int cpu = get_cpu();
+
+	ret = cpufreq_userspace_freq_down(cpu);
+	put_cpu();
+
+	return ret;
+}
+
+static int kvm_pvfreq_max(struct kvm_vcpu *vcpu)
+{
+	int ret;
+	int cpu = get_cpu();
+
+	ret = cpufreq_userspace_freq_max(cpu);
+	put_cpu();
+
+	return ret;
+}
+
+static int kvm_pvfreq_min(struct kvm_vcpu *vcpu)
+{
+	int ret;
+	int cpu = get_cpu();
+
+	ret = cpufreq_userspace_freq_min(cpu);
+	put_cpu();
+
+	return ret;
+}
+#endif
+
 int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
 {
 	unsigned long nr, a0, a1, a2, a3, ret;
 	int op_64_bit, r;
+	bool cpl_check;
 
 	r = kvm_skip_emulated_instruction(vcpu);
 
@@ -6246,7 +6294,13 @@
 		a3 &= 0xFFFFFFFF;
 	}
 
-	if (kvm_x86_ops->get_cpl(vcpu) != 0) {
+	cpl_check = true;
+	if (nr == KVM_HC_FREQ_UP || nr == KVM_HC_FREQ_DOWN ||
+	    nr == KVM_HC_FREQ_MIN || nr == KVM_HC_FREQ_MAX)
+		if (vcpu->arch.allow_freq_hypercall == true)
+			cpl_check = false;
+
+	if (cpl_check == true && kvm_x86_ops->get_cpl(vcpu) != 0) {
 		ret = -KVM_EPERM;
 		goto out;
 	}
@@ -6262,6 +6316,21 @@
 	case KVM_HC_CLOCK_PAIRING:
 		ret = kvm_pv_clock_pairing(vcpu, a0, a1);
 		break;
+#ifdef CONFIG_CPU_FREQ_GOV_USERSPACE
+	case KVM_HC_FREQ_UP:
+		ret = kvm_pvfreq_up(vcpu);
+		break;
+	case KVM_HC_FREQ_DOWN:
+		ret = kvm_pvfreq_down(vcpu);
+		break;
+	case KVM_HC_FREQ_MAX:
+		ret = kvm_pvfreq_max(vcpu);
+		break;
+	case KVM_HC_FREQ_MIN:
+		ret = kvm_pvfreq_min(vcpu);
+		break;
+#endif
+
 	default:
 		ret = -KVM_ENOSYS;
 		break;
Index: kvm-pvfreq/include/uapi/linux/kvm_para.h
===================================================================
--- kvm-pvfreq.orig/include/uapi/linux/kvm_para.h	2017-02-02 10:51:53.741217306 -0200
+++ kvm-pvfreq/include/uapi/linux/kvm_para.h	2017-02-02 11:17:17.824752499 -0200
@@ -25,6 +25,11 @@
 #define KVM_HC_MIPS_EXIT_VM		7
 #define KVM_HC_MIPS_CONSOLE_OUTPUT	8
 #define KVM_HC_CLOCK_PAIRING		9
+#define KVM_HC_FREQ_UP			10
+#define KVM_HC_FREQ_DOWN		11
+#define KVM_HC_FREQ_MAX			12
+#define KVM_HC_FREQ_MIN			13
+
 
 /*
  * hypercalls use architecture specific
Index: kvm-pvfreq/Documentation/virtual/kvm/hypercalls.txt
===================================================================
--- kvm-pvfreq.orig/Documentation/virtual/kvm/hypercalls.txt	2017-02-02 10:51:53.741217306 -0200
+++ kvm-pvfreq/Documentation/virtual/kvm/hypercalls.txt	2017-02-02 15:29:24.401692793 -0200
@@ -116,3 +116,48 @@
 
 Returns KVM_EOPNOTSUPP if the host does not use TSC clocksource,
 or if clock type is different than KVM_CLOCK_PAIRING_WALLCLOCK.
+
+7. KVM_HC_FREQ_UP
+-----------------
+
+Architecture: x86
+Status: active
+Purpose: Hypercall used to increase frequency to the next
+higher frequency.
+Usage example: DPDK power aware applications, that run on
+isolated CPUs. No input argument, returns 0 if success,
+1 if already at lowest frequency, error otherwise.
+
+8. KVM_HC_FREQ_DOWN
+---------------------
+
+Architecture: x86
+Status: active
+Purpose: Hypercall used to decrease frequency to the next
+lower frequency.
+Usage example: DPDK power aware applications, that run on
+isolated CPUs. No input argument, returns 0 if success,
+1 if already at lowest frequency, negative error otherwise.
+
+9. KVM_HC_FREQ_MIN
+-------------------
+
+Architecture: x86
+Status: active
+Purpose: Hypercall used to decrease frequency to the
+minimum frequency.
+Usage example: DPDK power aware applications, that run
+on isolated CPUs. No input argument, returns 0 if success
+error otherwise.
+
+10. KVM_HC_FREQ_MAX
+-------------------
+
+Architecture: x86
+Status: active
+Purpose: Hypercall used to increase frequency to the
+maximum frequency.
+Usage example: DPDK power aware applications, that run
+on isolated CPUs. No input argument, returns 0 if success
+error otherwise.
+