Merge tag 'kvm-riscv-6.16-1' of https://github.com/kvm-riscv/linux into HEAD

KVM/riscv changes for 6.16

- Add vector registers to get-reg-list selftest
- VCPU reset related improvements
- Remove scounteren initialization from VCPU reset
- Support VCPU reset from userspace using set_mpstate() ioctl

Author: bonzini

Documentation/virt/kvm/api.rst

@@ -8541,6 +8541,17 @@ aforementioned registers before the first KVM_RUN. These registers are VM
 scoped, meaning that the same set of values are presented on all vCPUs in a
 given VM.
 
+7.43 KVM_CAP_RISCV_MP_STATE_RESET
+---------------------------------
+
+:Architectures: riscv
+:Type: VM
+:Parameters: None
+:Returns: 0 on success, -EINVAL if arg[0] is not zero
+
+When this capability is enabled, KVM resets the VCPU when setting
+MP_STATE_INIT_RECEIVED through IOCTL.  The original MP_STATE is preserved.
+
 8. Other capabilities.
 ======================
 

arch/riscv/include/asm/kvm_aia.h

@@ -63,9 +63,6 @@ struct kvm_vcpu_aia {
 	/* CPU AIA CSR context of Guest VCPU */
 	struct kvm_vcpu_aia_csr guest_csr;
 
-	/* CPU AIA CSR context upon Guest VCPU reset */
-	struct kvm_vcpu_aia_csr guest_reset_csr;
-
 	/* Guest physical address of IMSIC for this VCPU */
 	gpa_t		imsic_addr;
 

arch/riscv/include/asm/kvm_host.h

@@ -119,6 +119,9 @@ struct kvm_arch {
 
 	/* AIA Guest/VM context */
 	struct kvm_aia aia;
+
+	/* KVM_CAP_RISCV_MP_STATE_RESET */
+	bool mp_state_reset;
 };
 
 struct kvm_cpu_trap {
@@ -193,6 +196,12 @@ struct kvm_vcpu_smstateen_csr {
 	unsigned long sstateen0;
 };
 
+struct kvm_vcpu_reset_state {
+	spinlock_t lock;
+	unsigned long pc;
+	unsigned long a1;
+};
+
 struct kvm_vcpu_arch {
 	/* VCPU ran at least once */
 	bool ran_atleast_once;
@@ -227,12 +236,8 @@ struct kvm_vcpu_arch {
 	/* CPU Smstateen CSR context of Guest VCPU */
 	struct kvm_vcpu_smstateen_csr smstateen_csr;
 
-	/* CPU context upon Guest VCPU reset */
-	struct kvm_cpu_context guest_reset_context;
-	spinlock_t reset_cntx_lock;
-
-	/* CPU CSR context upon Guest VCPU reset */
-	struct kvm_vcpu_csr guest_reset_csr;
+	/* CPU reset state of Guest VCPU */
+	struct kvm_vcpu_reset_state reset_state;
 
 	/*
 	 * VCPU interrupts

arch/riscv/include/asm/kvm_vcpu_sbi.h

@@ -55,6 +55,9 @@ void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run);
 void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu,
 				     struct kvm_run *run,
 				     u32 type, u64 flags);
+void kvm_riscv_vcpu_sbi_request_reset(struct kvm_vcpu *vcpu,
+				      unsigned long pc, unsigned long a1);
+void kvm_riscv_vcpu_sbi_load_reset_state(struct kvm_vcpu *vcpu);
 int kvm_riscv_vcpu_sbi_return(struct kvm_vcpu *vcpu, struct kvm_run *run);
 int kvm_riscv_vcpu_set_reg_sbi_ext(struct kvm_vcpu *vcpu,
 				   const struct kvm_one_reg *reg);

arch/riscv/include/asm/kvm_vcpu_vector.h

@@ -33,8 +33,7 @@ void kvm_riscv_vcpu_guest_vector_restore(struct kvm_cpu_context *cntx,
 					 unsigned long *isa);
 void kvm_riscv_vcpu_host_vector_save(struct kvm_cpu_context *cntx);
 void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *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);
 void kvm_riscv_vcpu_free_vector_context(struct kvm_vcpu *vcpu);
 #else
 
@@ -62,8 +61,7 @@ static inline void kvm_riscv_vcpu_host_vector_restore(struct kvm_cpu_context *cn
 {
 }
 
-static inline int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu,
-						      struct kvm_cpu_context *cntx)
+static inline int kvm_riscv_vcpu_alloc_vector_context(struct kvm_vcpu *vcpu)
 {
 	return 0;
 }

arch/riscv/kernel/head.S

@@ -131,6 +131,12 @@ secondary_start_sbi:
 	csrw CSR_IE, zero
 	csrw CSR_IP, zero
 
+#ifndef CONFIG_RISCV_M_MODE
+	/* Enable time CSR */
+	li t0, 0x2
+	csrw CSR_SCOUNTEREN, t0
+#endif
+
 	/* Load the global pointer */
 	load_global_pointer
 
@@ -226,6 +232,10 @@ SYM_CODE_START(_start_kernel)
 	 * to hand it to us.
 	 */
 	csrr a0, CSR_MHARTID
+#else
+	/* Enable time CSR */
+	li t0, 0x2
+	csrw CSR_SCOUNTEREN, t0
 #endif /* CONFIG_RISCV_M_MODE */
 
 	/* Load the global pointer */

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

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))

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;
 
 	/**
@@ -71,13 +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);
-
-	memset(&vcpu->arch.smstateen_csr, 0, sizeof(vcpu->arch.smstateen_csr));
+	kvm_riscv_vcpu_context_reset(vcpu, kvm_sbi_reset);
 
 	kvm_riscv_vcpu_fp_reset(vcpu);
 
@@ -112,8 +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);
 
@@ -133,24 +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);
 
@@ -169,7 +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;
 }
@@ -518,6 +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;
 	}
@@ -706,7 +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);

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;