[Backport]: RISC-V: KVM: Add SBI system suspend support

arch/riscv/include/asm/kvm_host.h

@@ -230,6 +230,7 @@ struct kvm_vcpu_arch {
 
 	/* 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;

arch/riscv/include/asm/kvm_vcpu_sbi.h

@@ -97,6 +97,7 @@ extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_rfence;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_srst;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_hsm;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_dbcn;
+extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_susp;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_sta;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_fwft;
 extern const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_experimental;

arch/riscv/include/uapi/asm/kvm.h

@@ -210,6 +210,7 @@ enum KVM_RISCV_SBI_EXT_ID {
 	KVM_RISCV_SBI_EXT_VENDOR,
 	KVM_RISCV_SBI_EXT_DBCN,
 	KVM_RISCV_SBI_EXT_STA,
+	KVM_RISCV_SBI_EXT_SUSP,
 	KVM_RISCV_SBI_EXT_FWFT,
 	KVM_RISCV_SBI_EXT_MAX,
 };

arch/riscv/kvm/Makefile

@@ -31,6 +31,7 @@ kvm-y += vcpu_sbi_hsm.o
 kvm-$(CONFIG_RISCV_PMU_SBI) += vcpu_sbi_pmu.o
 kvm-y += vcpu_sbi_replace.o
 kvm-y += vcpu_sbi_sta.o
+kvm-y += vcpu_sbi_system.o
 kvm-$(CONFIG_RISCV_SBI_V01) += vcpu_sbi_v01.o
 kvm-y += vcpu_switch.o
 kvm-y += vcpu_timer.o

arch/riscv/kvm/vcpu.c

@@ -73,7 +73,9 @@ static void kvm_riscv_reset_vcpu(struct kvm_vcpu *vcpu)
 
 	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));
 
@@ -132,12 +134,16 @@ int kvm_arch_vcpu_create(struct kvm_vcpu *vcpu)
 	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(&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))
 		return -ENOMEM;

arch/riscv/kvm/vcpu_sbi.c

@@ -70,6 +70,10 @@ static const struct kvm_riscv_sbi_extension_entry sbi_ext[] = {
 		.ext_idx = KVM_RISCV_SBI_EXT_DBCN,
 		.ext_ptr = &vcpu_sbi_ext_dbcn,
 	},
+	{
+		.ext_idx = KVM_RISCV_SBI_EXT_SUSP,
+		.ext_ptr = &vcpu_sbi_ext_susp,
+	},
 	{
 		.ext_idx = KVM_RISCV_SBI_EXT_STA,
 		.ext_ptr = &vcpu_sbi_ext_sta,

arch/riscv/kvm/vcpu_sbi_hsm.c

@@ -31,13 +31,16 @@ 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_power_on(target_vcpu);

arch/riscv/kvm/vcpu_sbi_system.c

@@ -0,0 +1,74 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2024 Ventana Micro Systems Inc.
+ */
+
+#include <linux/kvm_host.h>
+#include <linux/wordpart.h>
+
+#include <asm/kvm_vcpu_sbi.h>
+#include <asm/sbi.h>
+
+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;
+
+	switch (funcid) {
+	case SBI_EXT_SUSP_SYSTEM_SUSPEND:
+		if (lower_32_bits(cp->a0) != SBI_SUSP_SLEEP_TYPE_SUSPEND_TO_RAM) {
+			retdata->err_val = SBI_ERR_INVALID_PARAM;
+			return 0;
+		}
+
+		if (!(cp->sstatus & SR_SPP)) {
+			retdata->err_val = SBI_ERR_FAILURE;
+			return 0;
+		}
+
+		hva = kvm_vcpu_gfn_to_hva_prot(vcpu, cp->a1 >> PAGE_SHIFT, NULL);
+		if (kvm_is_error_hva(hva)) {
+			retdata->err_val = SBI_ERR_INVALID_ADDRESS;
+			return 0;
+		}
+
+		kvm_for_each_vcpu(i, tmp, vcpu->kvm) {
+			if (tmp == vcpu)
+				continue;
+			if (!kvm_riscv_vcpu_stopped(tmp)) {
+				retdata->err_val = SBI_ERR_DENIED;
+				return 0;
+			}
+		}
+
+		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);
+
+		/* userspace provides the suspend implementation */
+		kvm_riscv_vcpu_sbi_forward(vcpu, run);
+		retdata->uexit = true;
+		break;
+	default:
+		retdata->err_val = SBI_ERR_NOT_SUPPORTED;
+		break;
+	}
+
+	return 0;
+}
+
+const struct kvm_vcpu_sbi_extension vcpu_sbi_ext_susp = {
+	.extid_start = SBI_EXT_SUSP,
+	.extid_end = SBI_EXT_SUSP,
+	.default_disabled = true,
+	.handler = kvm_sbi_ext_susp_handler,
+};

tools/testing/selftests/kvm/riscv/get-reg-list.c

@@ -102,6 +102,7 @@ bool filter_reg(__u64 reg)
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_HSM:
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_PMU:
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_DBCN:
+	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_SUSP:
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_STA:
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_EXPERIMENTAL:
 	case KVM_REG_RISCV_SBI_EXT | KVM_REG_RISCV_SBI_SINGLE | KVM_RISCV_SBI_EXT_VENDOR:
@@ -428,6 +429,8 @@ static const char *sbi_ext_single_id_to_str(__u64 reg_off)
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_SRST),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_HSM),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_PMU),
+		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_DBCN),
+		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_SUSP),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_STA),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_EXPERIMENTAL),
 		KVM_SBI_EXT_ARR(KVM_RISCV_SBI_EXT_VENDOR),
@@ -850,6 +853,7 @@ KVM_SBI_EXT_SUBLIST_CONFIG(base, BASE);
 KVM_SBI_EXT_SUBLIST_CONFIG(sta, STA);
 KVM_SBI_EXT_SIMPLE_CONFIG(pmu, PMU);
 KVM_SBI_EXT_SIMPLE_CONFIG(dbcn, DBCN);
+KVM_SBI_EXT_SIMPLE_CONFIG(susp, SUSP);
 
 KVM_ISA_EXT_SUBLIST_CONFIG(aia, AIA);
 KVM_ISA_EXT_SUBLIST_CONFIG(fp_f, FP_F);
@@ -879,6 +883,7 @@ struct vcpu_reg_list *vcpu_configs[] = {
 	&config_sbi_sta,
 	&config_sbi_pmu,
 	&config_sbi_dbcn,
+	&config_sbi_susp,
 	&config_aia,
 	&config_fp_f,
 	&config_fp_d,