KVM: arm64: Support stolen time reporting via shared structure

Implement the service call for configuring a shared structure between a
VCPU and the hypervisor in which the hypervisor can write the time
stolen from the VCPU's execution time by other tasks on the host.

User space allocates memory which is placed at an IPA also chosen by user
space. The hypervisor then updates the shared structure using
kvm_put_guest() to ensure single copy atomicity of the 64-bit value
reporting the stolen time in nanoseconds.

Whenever stolen time is enabled by the guest, the stolen time counter is
reset.

The stolen time itself is retrieved from the sched_info structure
maintained by the Linux scheduler code. We enable SCHEDSTATS when
selecting KVM Kconfig to ensure this value is meaningful.

Signed-off-by: Steven Price <[email protected]>
Signed-off-by: Marc Zyngier <[email protected]>

Author: Steven Price

arch/arm/include/asm/kvm_host.h

@@ -39,6 +39,7 @@
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
 #define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
+#define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
@@ -329,6 +330,24 @@ static inline long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
 	return SMCCC_RET_NOT_SUPPORTED;
 }
 
+static inline gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
+{
+	return GPA_INVALID;
+}
+
+static inline void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
+{
+}
+
+static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
+{
+}
+
+static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch)
+{
+	return false;
+}
+
 void kvm_mmu_wp_memory_region(struct kvm *kvm, int slot);
 
 struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr);

arch/arm64/include/asm/kvm_host.h

@@ -44,6 +44,7 @@
 	KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_IRQ_PENDING	KVM_ARCH_REQ(1)
 #define KVM_REQ_VCPU_RESET	KVM_ARCH_REQ(2)
+#define KVM_REQ_RECORD_STEAL	KVM_ARCH_REQ(3)
 
 DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use);
 
@@ -338,6 +339,13 @@ struct kvm_vcpu_arch {
 	/* True when deferrable sysregs are loaded on the physical CPU,
 	 * see kvm_vcpu_load_sysregs and kvm_vcpu_put_sysregs. */
 	bool sysregs_loaded_on_cpu;
+
+	/* Guest PV state */
+	struct {
+		u64 steal;
+		u64 last_steal;
+		gpa_t base;
+	} steal;
 };
 
 /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */
@@ -479,6 +487,18 @@ int kvm_perf_init(void);
 int kvm_perf_teardown(void);
 
 long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu);
+gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu);
+void kvm_update_stolen_time(struct kvm_vcpu *vcpu);
+
+static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch)
+{
+	vcpu_arch->steal.base = GPA_INVALID;
+}
+
+static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch)
+{
+	return (vcpu_arch->steal.base != GPA_INVALID);
+}
 
 void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome);
 

arch/arm64/kvm/Kconfig

@@ -39,6 +39,7 @@ config KVM
 	select IRQ_BYPASS_MANAGER
 	select HAVE_KVM_IRQ_BYPASS
 	select HAVE_KVM_VCPU_RUN_PID_CHANGE
+	select SCHEDSTATS
 	---help---
 	  Support hosting virtualized guest machines.
 	  We don't support KVM with 16K page tables yet, due to the multiple

include/linux/kvm_types.h

@@ -35,6 +35,8 @@ typedef unsigned long  gva_t;
 typedef u64            gpa_t;
 typedef u64            gfn_t;
 
+#define GPA_INVALID	(~(gpa_t)0)
+
 typedef unsigned long  hva_t;
 typedef u64            hpa_t;
 typedef u64            hfn_t;

virt/kvm/arm/arm.c

@@ -40,6 +40,10 @@
 #include <asm/kvm_coproc.h>
 #include <asm/sections.h>
 
+#include <kvm/arm_hypercalls.h>
+#include <kvm/arm_pmu.h>
+#include <kvm/arm_psci.h>
+
 #ifdef REQUIRES_VIRT
 __asm__(".arch_extension	virt");
 #endif
@@ -351,6 +355,8 @@ int kvm_arch_vcpu_init(struct kvm_vcpu *vcpu)
 
 	kvm_arm_reset_debug_ptr(vcpu);
 
+	kvm_arm_pvtime_vcpu_init(&vcpu->arch);
+
 	return kvm_vgic_vcpu_init(vcpu);
 }
 
@@ -380,6 +386,8 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 	kvm_vcpu_load_sysregs(vcpu);
 	kvm_arch_vcpu_load_fp(vcpu);
 	kvm_vcpu_pmu_restore_guest(vcpu);
+	if (kvm_arm_is_pvtime_enabled(&vcpu->arch))
+		kvm_make_request(KVM_REQ_RECORD_STEAL, vcpu);
 
 	if (single_task_running())
 		vcpu_clear_wfe_traps(vcpu);
@@ -645,6 +653,9 @@ static void check_vcpu_requests(struct kvm_vcpu *vcpu)
 		 * that a VCPU sees new virtual interrupts.
 		 */
 		kvm_check_request(KVM_REQ_IRQ_PENDING, vcpu);
+
+		if (kvm_check_request(KVM_REQ_RECORD_STEAL, vcpu))
+			kvm_update_stolen_time(vcpu);
 	}
 }
 

virt/kvm/arm/hypercalls.c

@@ -14,6 +14,7 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 	u32 func_id = smccc_get_function(vcpu);
 	long val = SMCCC_RET_NOT_SUPPORTED;
 	u32 feature;
+	gpa_t gpa;
 
 	switch (func_id) {
 	case ARM_SMCCC_VERSION_FUNC_ID:
@@ -56,6 +57,11 @@ int kvm_hvc_call_handler(struct kvm_vcpu *vcpu)
 	case ARM_SMCCC_HV_PV_TIME_FEATURES:
 		val = kvm_hypercall_pv_features(vcpu);
 		break;
+	case ARM_SMCCC_HV_PV_TIME_ST:
+		gpa = kvm_init_stolen_time(vcpu);
+		if (gpa != GPA_INVALID)
+			val = gpa;
+		break;
 	default:
 		return kvm_psci_call(vcpu);
 	}

virt/kvm/arm/pvtime.c

@@ -3,18 +3,70 @@
 
 #include <linux/arm-smccc.h>
 
+#include <asm/pvclock-abi.h>
+
 #include <kvm/arm_hypercalls.h>
 
+void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
+{
+	struct kvm *kvm = vcpu->kvm;
+	u64 steal;
+	__le64 steal_le;
+	u64 offset;
+	int idx;
+	u64 base = vcpu->arch.steal.base;
+
+	if (base == GPA_INVALID)
+		return;
+
+	/* Let's do the local bookkeeping */
+	steal = vcpu->arch.steal.steal;
+	steal += current->sched_info.run_delay - vcpu->arch.steal.last_steal;
+	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
+	vcpu->arch.steal.steal = steal;
+
+	steal_le = cpu_to_le64(steal);
+	idx = srcu_read_lock(&kvm->srcu);
+	offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time);
+	kvm_put_guest(kvm, base + offset, steal_le, u64);
+	srcu_read_unlock(&kvm->srcu, idx);
+}
+
 long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
 {
 	u32 feature = smccc_get_arg1(vcpu);
 	long val = SMCCC_RET_NOT_SUPPORTED;
 
 	switch (feature) {
 	case ARM_SMCCC_HV_PV_TIME_FEATURES:
+	case ARM_SMCCC_HV_PV_TIME_ST:
 		val = SMCCC_RET_SUCCESS;
 		break;
 	}
 
 	return val;
 }
+
+gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu)
+{
+	struct pvclock_vcpu_stolen_time init_values = {};
+	struct kvm *kvm = vcpu->kvm;
+	u64 base = vcpu->arch.steal.base;
+	int idx;
+
+	if (base == GPA_INVALID)
+		return base;
+
+	/*
+	 * Start counting stolen time from the time the guest requests
+	 * the feature enabled.
+	 */
+	vcpu->arch.steal.steal = 0;
+	vcpu->arch.steal.last_steal = current->sched_info.run_delay;
+
+	idx = srcu_read_lock(&kvm->srcu);
+	kvm_write_guest(kvm, base, &init_values, sizeof(init_values));
+	srcu_read_unlock(&kvm->srcu, idx);
+
+	return base;
+}