9 files changed, 93 insertions, 60 deletions

diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index 0c3cbb0915ff..704c2899197e 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -18,7 +18,7 @@ menuconfig VIRTUALIZATION
 if VIRTUALIZATION
 
 config KVM
-	tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)"
+	tristate "Kernel-based Virtual Machine (KVM) support"
 	depends on RISCV_SBI && MMU
 	select HAVE_KVM_IRQCHIP
 	select HAVE_KVM_IRQ_ROUTING
diff --git a/arch/riscv/kvm/aia_device.c b/arch/riscv/kvm/aia_device.c
index 39cd26af5a69..43e472ff3e1a 100644
--- a/arch/riscv/kvm/aia_device.c
+++ b/arch/riscv/kvm/aia_device.c
@@ -526,12 +526,10 @@ int kvm_riscv_vcpu_aia_update(struct kvm_vcpu *vcpu)
 void kvm_riscv_vcpu_aia_reset(struct kvm_vcpu *vcpu)
 {
 	struct kvm_vcpu_aia_csr *csr = &vcpu->arch.aia_context.guest_csr;
-	struct kvm_vcpu_aia_csr *reset_csr =
-				&vcpu->arch.aia_context.guest_reset_csr;
 
 	if (!kvm_riscv_aia_available())
 		return;
-	memcpy(csr, reset_csr, sizeof(*csr));
+	memset(csr, 0, sizeof(*csr));
 
 	/* Proceed only if AIA was initialized successfully */
 	if (!kvm_riscv_aia_initialized(vcpu->kvm))
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 60d684c76c58..e0a01af426ff 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -51,12 +51,33 @@ const struct kvm_stats_header kvm_vcpu_stats_header = {
 		       sizeof(kvm_vcpu_stats_desc),
 };
 
-static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
+static void kvm_riscv_vcpu_context_reset(struct kvm_vcpu *vcpu,
+					 bool kvm_sbi_reset)
 {
 	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
-	struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
 	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
-	struct kvm_cpu_context *reset_cntx = &vcpu->arch.guest_reset_context;
+	void *vector_datap = cntx->vector.datap;
+
+	memset(cntx, 0, sizeof(*cntx));
+	memset(csr, 0, sizeof(*csr));
+	memset(&vcpu->arch.smstateen_csr, 0, sizeof(vcpu->arch.smstateen_csr));
+
+	/* Restore datap as it's not a part of the guest context. */
+	cntx->vector.datap = vector_datap;
+
+	if (kvm_sbi_reset)
+		kvm_riscv_vcpu_sbi_load_reset_state(vcpu);
+
+	/* Setup reset state of shadow SSTATUS and HSTATUS CSRs */
+	cntx->sstatus = SR_SPP | SR_SPIE;
+
+	cntx->hstatus |= HSTATUS_VTW;
+	cntx->hstatus |= HSTATUS_SPVP;
+	cntx->hstatus |= HSTATUS_SPV;
+}
+
+static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu, bool kvm_sbi_reset)
+{
 	bool loaded;
 
 	/**
@@ -71,11 +92,7 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 
 	vcpu->arch.last_exit_cpu = -1;
 
-	memcpy(csr, reset_csr, sizeof(*csr));
-
-	spin_lock(&vcpu->arch.reset_cntx_lock);
-	memcpy(cntx, reset_cntx, sizeof(*cntx));
-	spin_unlock(&vcpu->arch.reset_cntx_lock);
+	kvm_riscv_vcpu_context_reset(vcpu, kvm_sbi_reset);
 
 	kvm_riscv_vcpu_fp_reset(vcpu);
 
@@ -110,8 +127,6 @@ int kvm_arch_vcpu_precreate(struct kvm *kvm, unsigned int id)
 int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 {
 	int rc;
-	struct kvm_cpu_context *cntx;
-	struct kvm_vcpu_csr *reset_csr = &vcpu->arch.guest_reset_csr;
 
 	spin_lock_init(&vcpu->arch.mp_state_lock);
 
@@ -131,24 +146,11 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	/* Setup VCPU hfence queue */
 	spin_lock_init(&vcpu->arch.hfence_lock);
 
-	/* Setup reset state of shadow SSTATUS and HSTATUS CSRs */
-	spin_lock_init(&vcpu->arch.reset_cntx_lock);
+	spin_lock_init(&vcpu->arch.reset_state.lock);
 
-	spin_lock(&vcpu->arch.reset_cntx_lock);
-	cntx = &vcpu->arch.guest_reset_context;
-	cntx->sstatus = SR_SPP | SR_SPIE;
-	cntx->hstatus = 0;
-	cntx->hstatus |= HSTATUS_VTW;
-	cntx->hstatus |= HSTATUS_SPVP;
-	cntx->hstatus |= HSTATUS_SPV;
-	spin_unlock(&vcpu->arch.reset_cntx_lock);
-
-	if (kvm_riscv_vcpu_alloc_vector_context(vcpu, cntx))
+	if (kvm_riscv_vcpu_alloc_vector_context(vcpu))
 		return -ENOMEM;
 
-	/* By default, make CY, TM, and IR counters accessible in VU mode */
-	reset_csr->scounteren = 0x7;
-
 	/* Setup VCPU timer */
 	kvm_riscv_vcpu_timer_init(vcpu);
 
@@ -167,7 +169,7 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	kvm_riscv_vcpu_sbi_init(vcpu);
 
 	/* Reset VCPU */
-	kvm_riscv_reset_vcpu(vcpu);
+	kvm_riscv_reset_vcpu(vcpu, false);
 
 	return 0;
 }
@@ -516,6 +518,12 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
 	case KVM_MP_STATE_STOPPED:
 		__kvm_riscv_vcpu_power_off(vcpu);
 		break;
+	case KVM_MP_STATE_INIT_RECEIVED:
+		if (vcpu->kvm->arch.mp_state_reset)
+			kvm_riscv_reset_vcpu(vcpu, false);
+		else
+			ret = -EINVAL;
+		break;
 	default:
 		ret = -EINVAL;
 	}
@@ -704,7 +712,7 @@ static void kvm_riscv_check_vcpu_requests(struct kvm_vcpu *vcpu)
 		}
 
 		if (kvm_check_request(KVM_REQ_VCPU_RESET, vcpu))
-			kvm_riscv_reset_vcpu(vcpu);
+			kvm_riscv_reset_vcpu(vcpu, true);
 
 		if (kvm_check_request(KVM_REQ_UPDATE_HGATP, vcpu))
 			kvm_riscv_gstage_update_hgatp(vcpu);
diff --git a/arch/riscv/kvm/vcpu_onereg.c b/arch/riscv/kvm/vcpu_onereg.c
index 43ee8e33ba23..2e1b646f0d61 100644
--- a/arch/riscv/kvm/vcpu_onereg.c
+++ b/arch/riscv/kvm/vcpu_onereg.c
@@ -47,8 +47,10 @@ static const unsigned long kvm_isa_ext_arr[] = {
 	KVM_ISA_EXT_ARR(SVNAPOT),
 	KVM_ISA_EXT_ARR(SVPBMT),
 	KVM_ISA_EXT_ARR(SVVPTC),
+	KVM_ISA_EXT_ARR(ZAAMO),
 	KVM_ISA_EXT_ARR(ZABHA),
 	KVM_ISA_EXT_ARR(ZACAS),
+	KVM_ISA_EXT_ARR(ZALRSC),
 	KVM_ISA_EXT_ARR(ZAWRS),
 	KVM_ISA_EXT_ARR(ZBA),
 	KVM_ISA_EXT_ARR(ZBB),
@@ -149,8 +151,10 @@ static bool kvm_riscv_vcpu_isa_disable_allowed(unsigned long ext)
 	case KVM_RISCV_ISA_EXT_SVINVAL:
 	case KVM_RISCV_ISA_EXT_SVNAPOT:
 	case KVM_RISCV_ISA_EXT_SVVPTC:
+	case KVM_RISCV_ISA_EXT_ZAAMO:
 	case KVM_RISCV_ISA_EXT_ZABHA:
 	case KVM_RISCV_ISA_EXT_ZACAS:
+	case KVM_RISCV_ISA_EXT_ZALRSC:
 	case KVM_RISCV_ISA_EXT_ZAWRS:
 	case KVM_RISCV_ISA_EXT_ZBA:
 	case KVM_RISCV_ISA_EXT_ZBB:
diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
index d1c83a77735e..6e09b518a5d1 100644
--- a/arch/riscv/kvm/vcpu_sbi.c
+++ b/arch/riscv/kvm/vcpu_sbi.c
@@ -143,9 +143,9 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu,
 	struct kvm_vcpu *tmp;
 
 	kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
-		spin_lock(&vcpu->arch.mp_state_lock);
+		spin_lock(&tmp->arch.mp_state_lock);
 		WRITE_ONCE(tmp->arch.mp_state.mp_state, KVM_MP_STATE_STOPPED);
-		spin_unlock(&vcpu->arch.mp_state_lock);
+		spin_unlock(&tmp->arch.mp_state_lock);
 	}
 	kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_SLEEP);
 
@@ -156,6 +156,34 @@ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu,
 	run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
 }
 
+void kvm_riscv_vcpu_sbi_request_reset(struct kvm_vcpu *vcpu,
+				      unsigned long pc, unsigned long a1)
+{
+	spin_lock(&vcpu->arch.reset_state.lock);
+	vcpu->arch.reset_state.pc = pc;
+	vcpu->arch.reset_state.a1 = a1;
+	spin_unlock(&vcpu->arch.reset_state.lock);
+
+	kvm_make_request(KVM_REQ_VCPU_RESET, vcpu);
+}
+
+void kvm_riscv_vcpu_sbi_load_reset_state(struct kvm_vcpu *vcpu)
+{
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+	struct kvm_vcpu_reset_state *reset_state = &vcpu->arch.reset_state;
+
+	cntx->a0 = vcpu->vcpu_id;
+
+	spin_lock(&vcpu->arch.reset_state.lock);
+	cntx->sepc = reset_state->pc;
+	cntx->a1 = reset_state->a1;
+	spin_unlock(&vcpu->arch.reset_state.lock);
+
+	cntx->sstatus &= ~SR_SIE;
+	csr->vsatp = 0;
+}
+
 int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run)
 {
 	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
diff --git a/arch/riscv/kvm/vcpu_sbi_hsm.c b/arch/riscv/kvm/vcpu_sbi_hsm.c
index 3070bb31745d..f26207f84bab 100644
--- a/arch/riscv/kvm/vcpu_sbi_hsm.c
+++ b/arch/riscv/kvm/vcpu_sbi_hsm.c
@@ -15,7 +15,6 @@
 
 static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu)
 {
-	struct kvm_cpu_context *reset_cntx;
 	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
 	struct kvm_vcpu *target_vcpu;
 	unsigned long target_vcpuid = cp->a0;
@@ -32,17 +31,7 @@ static int kvm_sbi_hsm_vcpu_start(struct kvm_vcpu *vcpu)
 		goto out;
 	}
 
-	spin_lock(&target_vcpu->arch.reset_cntx_lock);
-	reset_cntx = &target_vcpu->arch.guest_reset_context;
-	/* start address */
-	reset_cntx->sepc = cp->a1;
-	/* target vcpu id to start */
-	reset_cntx->a0 = target_vcpuid;
-	/* private data passed from kernel */
-	reset_cntx->a1 = cp->a2;
-	spin_unlock(&target_vcpu->arch.reset_cntx_lock);
-
-	kvm_make_request(KVM_REQ_VCPU_RESET, target_vcpu);
+	kvm_riscv_vcpu_sbi_request_reset(target_vcpu, cp->a1, cp->a2);
 
 	__kvm_riscv_vcpu_power_on(target_vcpu);
 
diff --git a/arch/riscv/kvm/vcpu_sbi_system.c b/arch/riscv/kvm/vcpu_sbi_system.c
index bc0ebba89003..359be90b0fc5 100644
--- a/arch/riscv/kvm/vcpu_sbi_system.c
+++ b/arch/riscv/kvm/vcpu_sbi_system.c
@@ -13,7 +13,6 @@ static int kvm_sbi_ext_susp_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 				    struct kvm_vcpu_sbi_return *retdata)
 {
 	struct kvm_cpu_context *cp = &vcpu->arch.guest_context;
-	struct kvm_cpu_context *reset_cntx;
 	unsigned long funcid = cp->a6;
 	unsigned long hva, i;
 	struct kvm_vcpu *tmp;
@@ -45,14 +44,7 @@ static int kvm_sbi_ext_susp_handler(struct kvm_vcpu *vcpu, struct kvm_run *run,
 			}
 		}
 
-		spin_lock(&vcpu->arch.reset_cntx_lock);
-		reset_cntx = &vcpu->arch.guest_reset_context;
-		reset_cntx->sepc = cp->a1;
-		reset_cntx->a0 = vcpu->vcpu_id;
-		reset_cntx->a1 = cp->a2;
-		spin_unlock(&vcpu->arch.reset_cntx_lock);
-
-		kvm_make_request(KVM_REQ_VCPU_RESET, vcpu);
+		kvm_riscv_vcpu_sbi_request_reset(vcpu, cp->a1, cp->a2);
 
 		/* userspace provides the suspend implementation */
 		kvm_riscv_vcpu_sbi_forward(vcpu, run);
diff --git a/arch/riscv/kvm/vcpu_vector.c b/arch/riscv/kvm/vcpu_vector.c
index d92d1348045c..a5f88cb717f3 100644
--- a/arch/riscv/kvm/vcpu_vector.c
+++ b/arch/riscv/kvm/vcpu_vector.c
@@ -22,6 +22,9 @@ void kvm_riscv_vcpu_vector_reset(struct kvm_vcpu *vcpu)
 	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
 
 	cntx->sstatus &= ~SR_VS;
+
+	cntx->vector.vlenb = riscv_v_vsize / 32;
+
 	if (riscv_isa_extension_available(isa, v)) {
 		cntx->sstatus |= SR_VS_INITIAL;
 		WARN_ON(!cntx->vector.datap);
@@ -70,13 +73,11 @@ void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cntx)
 		__kvm_riscv_vector_restore(cntx);
 }
 
-int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu,
-					struct kvm_cpu_context *cntx)
+int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu)
 {
-	cntx->vector.datap = kmalloc(riscv_v_vsize, GFP_KERNEL);
-	if (!cntx->vector.datap)
+	vcpu->arch.guest_context.vector.datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
+	if (!vcpu->arch.guest_context.vector.datap)
 		return -ENOMEM;
-	cntx->vector.vlenb = riscv_v_vsize / 32;
 
 	vcpu->arch.host_context.vector.datap = kzalloc(riscv_v_vsize, GFP_KERNEL);
 	if (!vcpu->arch.host_context.vector.datap)
@@ -87,7 +88,7 @@ int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu,
 
 void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu)
 {
-	kfree(vcpu->arch.guest_reset_context.vector.datap);
+	kfree(vcpu->arch.guest_context.vector.datap);
 	kfree(vcpu->arch.host_context.vector.datap);
 }
 #endif
diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c
index 7396b8654f45..b27ec8f96697 100644
--- a/arch/riscv/kvm/vm.c
+++ b/arch/riscv/kvm/vm.c
@@ -209,6 +209,19 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	return r;
 }
 
+int kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap)
+{
+	switch (cap->cap) {
+	case KVM_CAP_RISCV_MP_STATE_RESET:
+		if (cap->flags)
+			return -EINVAL;
+		kvm->arch.mp_state_reset = true;
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 {
 	return -EINVAL;