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 <steven.price@arm.com>
Signed-off-by: Marc Zyngier <maz@kernel.org>

3 files changed, 69 insertions, 0 deletions

diff --git a/virt/kvm/arm/arm.c b/virt/kvm/arm/arm.c
index 86c6aa1cb58e..2aba375dfd13 100644
--- a/virt/kvm/arm/arm.c
+++ b/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);
 	}
 }
 
diff --git a/virt/kvm/arm/hypercalls.c b/virt/kvm/arm/hypercalls.c
index 97ea8b133e77..550dfa3e53cd 100644
--- a/virt/kvm/arm/hypercalls.c
+++ b/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);
 	}
diff --git a/virt/kvm/arm/pvtime.c b/virt/kvm/arm/pvtime.c
index 9fc69fc2d683..b90b3a7bea85 100644
--- a/virt/kvm/arm/pvtime.c
+++ b/virt/kvm/arm/pvtime.c
@@ -3,8 +3,35 @@
 
 #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);
@@ -12,9 +39,34 @@ long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu)
 
 	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;
+}