RISC-V: KVM: Implement KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls

euleros inclusion
category: feature
feature: initial KVM RISC-V support
bugzilla: 46845
CVE: NA

For KVM RISC-V, we use KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls to access
VCPU config and registers from user-space.

We have three types of VCPU registers:
1. CONFIG - these are VCPU config and capabilities
2. CORE   - these are VCPU general purpose registers
3. CSR    - these are VCPU control and status registers

The CONFIG register available to user-space is ISA. The ISA register is
a read and write register where user-space can only write the desired
VCPU ISA capabilities before running the VCPU.

The CORE registers available to user-space are PC, RA, SP, GP, TP, A0-A7,
T0-T6, S0-S11 and MODE. Most of these are RISC-V general registers except
PC and MODE. The PC register represents program counter whereas the MODE
register represent VCPU privilege mode (i.e. S/U-mode).

The CSRs available to user-space are SSTATUS, SIE, STVEC, SSCRATCH, SEPC,
SCAUSE, STVAL, SIP, and SATP. All of these are read/write registers.

In future, more VCPU register types will be added (such as FP) for the
KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls.

Reference: https://gitee.com/openeuler/kernel/issues/I26X9VSigned-off-by: NAnup Patel <anup.patel@wdc.com>
Acked-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NPaolo Bonzini <pbonzini@redhat.com>
Reviewed-by: NYifei Jiang <jiangyifei@huawei.com>
Acked-by: NXie XiuQi <xiexiuqi@huawei.com>
Signed-off-by: NChen Jun <chenjun102@huawei.com>

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

@@ -41,10 +41,61 @@ struct kvm_guest_debug_arch {
 struct kvm_sync_regs {
 };
 
-/* dummy definition */
+/* for KVM_GET_SREGS and KVM_SET_SREGS */
 struct kvm_sregs {
 };
 
+/* CONFIG registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+struct kvm_riscv_config {
+	unsigned long isa;
+};
+
+/* CORE registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+struct kvm_riscv_core {
+	struct user_regs_struct regs;
+	unsigned long mode;
+};
+
+/* Possible privilege modes for kvm_riscv_core */
+#define KVM_RISCV_MODE_S	1
+#define KVM_RISCV_MODE_U	0
+
+/* CSR registers for KVM_GET_ONE_REG and KVM_SET_ONE_REG */
+struct kvm_riscv_csr {
+	unsigned long sstatus;
+	unsigned long sie;
+	unsigned long stvec;
+	unsigned long sscratch;
+	unsigned long sepc;
+	unsigned long scause;
+	unsigned long stval;
+	unsigned long sip;
+	unsigned long satp;
+	unsigned long scounteren;
+};
+
+#define KVM_REG_SIZE(id)		\
+	(1U << (((id) & KVM_REG_SIZE_MASK) >> KVM_REG_SIZE_SHIFT))
+
+/* If you need to interpret the index values, here is the key: */
+#define KVM_REG_RISCV_TYPE_MASK		0x00000000FF000000
+#define KVM_REG_RISCV_TYPE_SHIFT	24
+
+/* Config registers are mapped as type 1 */
+#define KVM_REG_RISCV_CONFIG		(0x01 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_CONFIG_REG(name)	\
+	(offsetof(struct kvm_riscv_config, name) / sizeof(unsigned long))
+
+/* Core registers are mapped as type 2 */
+#define KVM_REG_RISCV_CORE		(0x02 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_CORE_REG(name)	\
+		(offsetof(struct kvm_riscv_core, name) / sizeof(unsigned long))
+
+/* Control and status registers are mapped as type 3 */
+#define KVM_REG_RISCV_CSR		(0x03 << KVM_REG_RISCV_TYPE_SHIFT)
+#define KVM_REG_RISCV_CSR_REG(name)	\
+		(offsetof(struct kvm_riscv_csr, name) / sizeof(unsigned long))
+
 #endif
 
 #endif /* __LINUX_KVM_RISCV_H */

arch/riscv/kvm/vcpu.c

@@ -18,7 +18,6 @@
 #include <linux/fs.h>
 #include <linux/kvm_host.h>
 #include <asm/csr.h>
-#include <asm/delay.h>
 #include <asm/hwcap.h>
 
 struct kvm_stats_debugfs_item debugfs_entries[] = {
@@ -148,6 +147,225 @@ vm_fault_t kvm_arch_vcpu_fault(struct kvm_vcpu *vcpu, struct vm_fault *vmf)
 	return VM_FAULT_SIGBUS;
 }
 
+static int kvm_riscv_vcpu_get_reg_config(struct kvm_vcpu *vcpu,
+					 const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CONFIG);
+	unsigned long reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	switch (reg_num) {
+	case KVM_REG_RISCV_CONFIG_REG(isa):
+		reg_val = vcpu->arch.isa;
+		break;
+	default:
+		return -EINVAL;
+	};
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg_config(struct kvm_vcpu *vcpu,
+					 const struct kvm_one_reg *reg)
+{
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CONFIG);
+	unsigned long reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	switch (reg_num) {
+	case KVM_REG_RISCV_CONFIG_REG(isa):
+		if (!vcpu->arch.ran_atleast_once) {
+			vcpu->arch.isa = reg_val;
+			vcpu->arch.isa &= riscv_isa_extension_base(NULL);
+			vcpu->arch.isa &= KVM_RISCV_ISA_ALLOWED;
+		} else {
+			return -EOPNOTSUPP;
+		}
+		break;
+	default:
+		return -EINVAL;
+	};
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_get_reg_core(struct kvm_vcpu *vcpu,
+				       const struct kvm_one_reg *reg)
+{
+	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CORE);
+	unsigned long reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
+		return -EINVAL;
+
+	if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc))
+		reg_val = cntx->sepc;
+	else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num &&
+		 reg_num <= KVM_REG_RISCV_CORE_REG(regs.t6))
+		reg_val = ((unsigned long *)cntx)[reg_num];
+	else if (reg_num == KVM_REG_RISCV_CORE_REG(mode))
+		reg_val = (cntx->sstatus & SR_SPP) ?
+				KVM_RISCV_MODE_S : KVM_RISCV_MODE_U;
+	else
+		return -EINVAL;
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg_core(struct kvm_vcpu *vcpu,
+				       const struct kvm_one_reg *reg)
+{
+	struct kvm_cpu_context *cntx = &vcpu->arch.guest_context;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CORE);
+	unsigned long reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+	if (reg_num >= sizeof(struct kvm_riscv_core) / sizeof(unsigned long))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	if (reg_num == KVM_REG_RISCV_CORE_REG(regs.pc))
+		cntx->sepc = reg_val;
+	else if (KVM_REG_RISCV_CORE_REG(regs.pc) < reg_num &&
+		 reg_num <= KVM_REG_RISCV_CORE_REG(regs.t6))
+		((unsigned long *)cntx)[reg_num] = reg_val;
+	else if (reg_num == KVM_REG_RISCV_CORE_REG(mode)) {
+		if (reg_val == KVM_RISCV_MODE_S)
+			cntx->sstatus |= SR_SPP;
+		else
+			cntx->sstatus &= ~SR_SPP;
+	} else
+		return -EINVAL;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_get_reg_csr(struct kvm_vcpu *vcpu,
+				      const struct kvm_one_reg *reg)
+{
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CSR);
+	unsigned long reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
+		return -EINVAL;
+
+	if (reg_num == KVM_REG_RISCV_CSR_REG(sip)) {
+		kvm_riscv_vcpu_flush_interrupts(vcpu);
+		reg_val = csr->hvip >> VSIP_TO_HVIP_SHIFT;
+		reg_val = reg_val & VSIP_VALID_MASK;
+	} else if (reg_num == KVM_REG_RISCV_CSR_REG(sie)) {
+		reg_val = csr->hie >> VSIP_TO_HVIP_SHIFT;
+		reg_val = reg_val & VSIP_VALID_MASK;
+	} else
+		reg_val = ((unsigned long *)csr)[reg_num];
+
+	if (copy_to_user(uaddr, &reg_val, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg_csr(struct kvm_vcpu *vcpu,
+				      const struct kvm_one_reg *reg)
+{
+	struct kvm_vcpu_csr *csr = &vcpu->arch.guest_csr;
+	unsigned long __user *uaddr =
+			(unsigned long __user *)(unsigned long)reg->addr;
+	unsigned long reg_num = reg->id & ~(KVM_REG_ARCH_MASK |
+					    KVM_REG_SIZE_MASK |
+					    KVM_REG_RISCV_CSR);
+	unsigned long reg_val;
+
+	if (KVM_REG_SIZE(reg->id) != sizeof(unsigned long))
+		return -EINVAL;
+	if (reg_num >= sizeof(struct kvm_riscv_csr) / sizeof(unsigned long))
+		return -EINVAL;
+
+	if (copy_from_user(&reg_val, uaddr, KVM_REG_SIZE(reg->id)))
+		return -EFAULT;
+
+	if (reg_num == KVM_REG_RISCV_CSR_REG(sip) ||
+	    reg_num == KVM_REG_RISCV_CSR_REG(sie)) {
+		reg_val = reg_val & VSIP_VALID_MASK;
+		reg_val = reg_val << VSIP_TO_HVIP_SHIFT;
+	}
+
+	((unsigned long *)csr)[reg_num] = reg_val;
+
+	if (reg_num == KVM_REG_RISCV_CSR_REG(sip))
+		WRITE_ONCE(vcpu->arch.irqs_pending_mask, 0);
+
+	return 0;
+}
+
+static int kvm_riscv_vcpu_set_reg(struct kvm_vcpu *vcpu,
+				  const struct kvm_one_reg *reg)
+{
+	if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CONFIG)
+		return kvm_riscv_vcpu_set_reg_config(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CORE)
+		return kvm_riscv_vcpu_set_reg_core(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CSR)
+		return kvm_riscv_vcpu_set_reg_csr(vcpu, reg);
+
+	return -EINVAL;
+}
+
+static int kvm_riscv_vcpu_get_reg(struct kvm_vcpu *vcpu,
+				  const struct kvm_one_reg *reg)
+{
+	if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CONFIG)
+		return kvm_riscv_vcpu_get_reg_config(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CORE)
+		return kvm_riscv_vcpu_get_reg_core(vcpu, reg);
+	else if ((reg->id & KVM_REG_RISCV_TYPE_MASK) == KVM_REG_RISCV_CSR)
+		return kvm_riscv_vcpu_get_reg_csr(vcpu, reg);
+
+	return -EINVAL;
+}
+
 long kvm_arch_vcpu_async_ioctl(struct file *filp,
 			       unsigned int ioctl, unsigned long arg)
 {
@@ -172,8 +390,30 @@ long kvm_arch_vcpu_async_ioctl(struct file *filp,
 long kvm_arch_vcpu_ioctl(struct file *filp,
 			 unsigned int ioctl, unsigned long arg)
 {
-	/* TODO: */
-	return -EINVAL;
+	struct kvm_vcpu *vcpu = filp->private_data;
+	void __user *argp = (void __user *)arg;
+	long r = -EINVAL;
+
+	switch (ioctl) {
+	case KVM_SET_ONE_REG:
+	case KVM_GET_ONE_REG: {
+		struct kvm_one_reg reg;
+
+		r = -EFAULT;
+		if (copy_from_user(&reg, argp, sizeof(reg)))
+			break;
+
+		if (ioctl == KVM_SET_ONE_REG)
+			r = kvm_riscv_vcpu_set_reg(vcpu, &reg);
+		else
+			r = kvm_riscv_vcpu_get_reg(vcpu, &reg);
+		break;
+	}
+	default:
+		break;
+	}
+
+	return r;
 }
 
 int kvm_arch_vcpu_ioctl_get_sregs(struct kvm_vcpu *vcpu,