LoongArch: KVM: Enable paravirt feature control from VMM

Export kernel paravirt features to user space, so that VMM can control
each single paravirt feature. By default paravirt features will be the
same with kvm supported features if VMM does not set it.

Also a new feature KVM_FEATURE_VIRT_EXTIOI is added which can be set
from user space. This feature indicates that the virt EIOINTC can route
interrupts to 256 vCPUs, rather than 4 vCPUs like with real HW.
Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

arch/loongarch/include/asm/kvm_host.h

@@ -112,6 +112,8 @@ struct kvm_arch {
 	unsigned int  root_level;
 	spinlock_t    phyid_map_lock;
 	struct kvm_phyid_map  *phyid_map;
+	/* Enabled PV features */
+	unsigned long pv_features;
 
 	s64 time_offset;
 	struct kvm_context __percpu *vmcs;
@@ -143,6 +145,11 @@ enum emulation_result {
 #define KVM_LARCH_SWCSR_LATEST	(0x1 << 5)
 #define KVM_LARCH_HWCSR_USABLE	(0x1 << 6)
 
+#define LOONGARCH_PV_FEAT_UPDATED	BIT_ULL(63)
+#define LOONGARCH_PV_FEAT_MASK		(BIT(KVM_FEATURE_IPI) |		\
+					 BIT(KVM_FEATURE_STEAL_TIME) |	\
+					 BIT(KVM_FEATURE_VIRT_EXTIOI))
+
 struct kvm_vcpu_arch {
 	/*
 	 * Switch pointer-to-function type to unsigned long

arch/loongarch/include/asm/kvm_para.h

@@ -2,6 +2,8 @@
 #ifndef _ASM_LOONGARCH_KVM_PARA_H
 #define _ASM_LOONGARCH_KVM_PARA_H
 
+#include <uapi/asm/kvm_para.h>
+
 /*
  * Hypercall code field
  */

arch/loongarch/include/asm/kvm_vcpu.h

@@ -130,4 +130,9 @@ static inline bool kvm_pvtime_supported(void)
 	return !!sched_info_on();
 }
 
+static inline bool kvm_guest_has_pv_feature(struct kvm_vcpu *vcpu, unsigned int feature)
+{
+	return vcpu->kvm->arch.pv_features & BIT(feature);
+}
+
 #endif /* __ASM_LOONGARCH_KVM_VCPU_H__ */

arch/loongarch/include/asm/loongarch.h

@@ -161,16 +161,8 @@
 
 /*
  * CPUCFG index area: 0x40000000 -- 0x400000ff
- * SW emulation for KVM hypervirsor
+ * SW emulation for KVM hypervirsor, see arch/loongarch/include/uapi/asm/kvm_para.h
  */
-#define CPUCFG_KVM_BASE			0x40000000
-#define CPUCFG_KVM_SIZE			0x100
-
-#define CPUCFG_KVM_SIG			(CPUCFG_KVM_BASE + 0)
-#define  KVM_SIGNATURE			"KVM\0"
-#define CPUCFG_KVM_FEATURE		(CPUCFG_KVM_BASE + 4)
-#define  KVM_FEATURE_IPI		BIT(1)
-#define  KVM_FEATURE_STEAL_TIME		BIT(2)
 
 #ifndef __ASSEMBLY__
 

arch/loongarch/include/uapi/asm/Kbuild

 # SPDX-License-Identifier: GPL-2.0
 syscall-y += unistd_64.h
-
-generic-y += kvm_para.h

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

@@ -92,13 +92,15 @@ struct kvm_fpu {
 #define KVM_IOC_CPUCFG(REG)		LOONGARCH_REG_64(KVM_REG_LOONGARCH_CPUCFG, REG)
 
 /* Device Control API on vm fd */
-#define KVM_LOONGARCH_VM_FEAT_CTRL	0
-#define  KVM_LOONGARCH_VM_FEAT_LSX	0
-#define  KVM_LOONGARCH_VM_FEAT_LASX	1
-#define  KVM_LOONGARCH_VM_FEAT_X86BT	2
-#define  KVM_LOONGARCH_VM_FEAT_ARMBT	3
-#define  KVM_LOONGARCH_VM_FEAT_MIPSBT	4
-#define  KVM_LOONGARCH_VM_FEAT_PMU	5
+#define KVM_LOONGARCH_VM_FEAT_CTRL		0
+#define  KVM_LOONGARCH_VM_FEAT_LSX		0
+#define  KVM_LOONGARCH_VM_FEAT_LASX		1
+#define  KVM_LOONGARCH_VM_FEAT_X86BT		2
+#define  KVM_LOONGARCH_VM_FEAT_ARMBT		3
+#define  KVM_LOONGARCH_VM_FEAT_MIPSBT		4
+#define  KVM_LOONGARCH_VM_FEAT_PMU		5
+#define  KVM_LOONGARCH_VM_FEAT_PV_IPI		6
+#define  KVM_LOONGARCH_VM_FEAT_PV_STEALTIME	7
 
 /* Device Control API on vcpu fd */
 #define KVM_LOONGARCH_VCPU_CPUCFG	0

arch/loongarch/include/uapi/asm/kvm_para.h

+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_ASM_KVM_PARA_H
+#define _UAPI_ASM_KVM_PARA_H
+
+#include <linux/types.h>
+
+/*
+ * CPUCFG index area: 0x40000000 -- 0x400000ff
+ * SW emulation for KVM hypervirsor
+ */
+#define CPUCFG_KVM_BASE			0x40000000
+#define CPUCFG_KVM_SIZE			0x100
+#define CPUCFG_KVM_SIG			(CPUCFG_KVM_BASE + 0)
+#define  KVM_SIGNATURE			"KVM\0"
+#define CPUCFG_KVM_FEATURE		(CPUCFG_KVM_BASE + 4)
+#define  KVM_FEATURE_IPI		1
+#define  KVM_FEATURE_STEAL_TIME		2
+/* BIT 24 - 31 are features configurable by user space vmm */
+#define  KVM_FEATURE_VIRT_EXTIOI	24
+
+#endif /* _UAPI_ASM_KVM_PARA_H */

arch/loongarch/kernel/paravirt.c

@@ -176,7 +176,7 @@ int __init pv_ipi_init(void)
 		return 0;
 
 	feature = read_cpucfg(CPUCFG_KVM_FEATURE);
-	if (!(feature & KVM_FEATURE_IPI))
+	if (!(feature & BIT(KVM_FEATURE_IPI)))
 		return 0;
 
 #ifdef CONFIG_SMP
@@ -207,7 +207,7 @@ static int pv_enable_steal_time(void)
 	}
 
 	addr |= KVM_STEAL_PHYS_VALID;
-	kvm_hypercall2(KVM_HCALL_FUNC_NOTIFY, KVM_FEATURE_STEAL_TIME, addr);
+	kvm_hypercall2(KVM_HCALL_FUNC_NOTIFY, BIT(KVM_FEATURE_STEAL_TIME), addr);
 
 	return 0;
 }
@@ -215,7 +215,7 @@ static int pv_enable_steal_time(void)
 static void pv_disable_steal_time(void)
 {
 	if (has_steal_clock)
-		kvm_hypercall2(KVM_HCALL_FUNC_NOTIFY, KVM_FEATURE_STEAL_TIME, 0);
+		kvm_hypercall2(KVM_HCALL_FUNC_NOTIFY, BIT(KVM_FEATURE_STEAL_TIME), 0);
 }
 
 #ifdef CONFIG_SMP
@@ -267,7 +267,7 @@ int __init pv_time_init(void)
 		return 0;
 
 	feature = read_cpucfg(CPUCFG_KVM_FEATURE);
-	if (!(feature & KVM_FEATURE_STEAL_TIME))
+	if (!(feature & BIT(KVM_FEATURE_STEAL_TIME)))
 		return 0;
 
 	has_steal_clock = 1;

arch/loongarch/kvm/exit.c

@@ -50,9 +50,7 @@ static int kvm_emu_cpucfg(struct kvm_vcpu *vcpu, larch_inst inst)
 		vcpu->arch.gprs[rd] = *(unsigned int *)KVM_SIGNATURE;
 		break;
 	case CPUCFG_KVM_FEATURE:
-		ret = KVM_FEATURE_IPI;
-		if (kvm_pvtime_supported())
-			ret |= KVM_FEATURE_STEAL_TIME;
+		ret = vcpu->kvm->arch.pv_features & LOONGARCH_PV_FEAT_MASK;
 		vcpu->arch.gprs[rd] = ret;
 		break;
 	default:
@@ -705,25 +703,22 @@ static long kvm_save_notify(struct kvm_vcpu *vcpu)
 	id   = kvm_read_reg(vcpu, LOONGARCH_GPR_A1);
 	data = kvm_read_reg(vcpu, LOONGARCH_GPR_A2);
 	switch (id) {
-	case KVM_FEATURE_STEAL_TIME:
-		if (!kvm_pvtime_supported())
-			return KVM_HCALL_INVALID_CODE;
-
+	case BIT(KVM_FEATURE_STEAL_TIME):
 		if (data & ~(KVM_STEAL_PHYS_MASK | KVM_STEAL_PHYS_VALID))
 			return KVM_HCALL_INVALID_PARAMETER;
 
 		vcpu->arch.st.guest_addr = data;
 		if (!(data & KVM_STEAL_PHYS_VALID))
-			break;
+			return 0;
 
 		vcpu->arch.st.last_steal = current->sched_info.run_delay;
 		kvm_make_request(KVM_REQ_STEAL_UPDATE, vcpu);
-		break;
+		return 0;
 	default:
-		break;
+		return KVM_HCALL_INVALID_CODE;
 	};
 
-	return 0;
+	return KVM_HCALL_INVALID_CODE;
 };
 
 /*
@@ -797,19 +792,21 @@ static int kvm_send_pv_ipi(struct kvm_vcpu *vcpu)
  */
 static void kvm_handle_service(struct kvm_vcpu *vcpu)
 {
+	long ret = KVM_HCALL_INVALID_CODE;
 	unsigned long func = kvm_read_reg(vcpu, LOONGARCH_GPR_A0);
-	long ret;
 
 	switch (func) {
 	case KVM_HCALL_FUNC_IPI:
-		kvm_send_pv_ipi(vcpu);
-		ret = KVM_HCALL_SUCCESS;
+		if (kvm_guest_has_pv_feature(vcpu, KVM_FEATURE_IPI)) {
+			kvm_send_pv_ipi(vcpu);
+			ret = KVM_HCALL_SUCCESS;
+		}
 		break;
 	case KVM_HCALL_FUNC_NOTIFY:
-		ret = kvm_save_notify(vcpu);
+		if (kvm_guest_has_pv_feature(vcpu, KVM_FEATURE_STEAL_TIME))
+			ret = kvm_save_notify(vcpu);
 		break;
 	default:
-		ret = KVM_HCALL_INVALID_CODE;
 		break;
 	}
 

arch/loongarch/kvm/vcpu.c

@@ -953,6 +953,8 @@ static int kvm_loongarch_cpucfg_has_attr(struct kvm_vcpu *vcpu,
 	case LOONGARCH_CPUCFG2:
 	case LOONGARCH_CPUCFG6:
 		return 0;
+	case CPUCFG_KVM_FEATURE:
+		return 0;
 	default:
 		return -ENXIO;
 	}
@@ -963,8 +965,8 @@ static int kvm_loongarch_cpucfg_has_attr(struct kvm_vcpu *vcpu,
 static int kvm_loongarch_pvtime_has_attr(struct kvm_vcpu *vcpu,
 					 struct kvm_device_attr *attr)
 {
-	if (!kvm_pvtime_supported() ||
-			attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA)
+	if (!kvm_guest_has_pv_feature(vcpu, KVM_FEATURE_STEAL_TIME)
+			|| attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA)
 		return -ENXIO;
 
 	return 0;
@@ -996,9 +998,18 @@ static int kvm_loongarch_cpucfg_get_attr(struct kvm_vcpu *vcpu,
 	uint64_t val;
 	uint64_t __user *uaddr = (uint64_t __user *)attr->addr;
 
-	ret = _kvm_get_cpucfg_mask(attr->attr, &val);
-	if (ret)
-		return ret;
+	switch (attr->attr) {
+	case 0 ... (KVM_MAX_CPUCFG_REGS - 1):
+		ret = _kvm_get_cpucfg_mask(attr->attr, &val);
+		if (ret)
+			return ret;
+		break;
+	case CPUCFG_KVM_FEATURE:
+		val = vcpu->kvm->arch.pv_features & LOONGARCH_PV_FEAT_MASK;
+		break;
+	default:
+		return -ENXIO;
+	}
 
 	put_user(val, uaddr);
 
@@ -1011,8 +1022,8 @@ static int kvm_loongarch_pvtime_get_attr(struct kvm_vcpu *vcpu,
 	u64 gpa;
 	u64 __user *user = (u64 __user *)attr->addr;
 
-	if (!kvm_pvtime_supported() ||
-			attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA)
+	if (!kvm_guest_has_pv_feature(vcpu, KVM_FEATURE_STEAL_TIME)
+			|| attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA)
 		return -ENXIO;
 
 	gpa = vcpu->arch.st.guest_addr;
@@ -1044,7 +1055,28 @@ static int kvm_loongarch_vcpu_get_attr(struct kvm_vcpu *vcpu,
 static int kvm_loongarch_cpucfg_set_attr(struct kvm_vcpu *vcpu,
 					 struct kvm_device_attr *attr)
 {
-	return -ENXIO;
+	u64 val, valid;
+	u64 __user *user = (u64 __user *)attr->addr;
+	struct kvm *kvm = vcpu->kvm;
+
+	switch (attr->attr) {
+	case CPUCFG_KVM_FEATURE:
+		if (get_user(val, user))
+			return -EFAULT;
+
+		valid = LOONGARCH_PV_FEAT_MASK;
+		if (val & ~valid)
+			return -EINVAL;
+
+		/* All vCPUs need set the same PV features */
+		if ((kvm->arch.pv_features & LOONGARCH_PV_FEAT_UPDATED)
+				&& ((kvm->arch.pv_features & valid) != val))
+			return -EINVAL;
+		kvm->arch.pv_features = val | LOONGARCH_PV_FEAT_UPDATED;
+		return 0;
+	default:
+		return -ENXIO;
+	}
 }
 
 static int kvm_loongarch_pvtime_set_attr(struct kvm_vcpu *vcpu,
@@ -1054,8 +1086,8 @@ static int kvm_loongarch_pvtime_set_attr(struct kvm_vcpu *vcpu,
 	u64 gpa, __user *user = (u64 __user *)attr->addr;
 	struct kvm *kvm = vcpu->kvm;
 
-	if (!kvm_pvtime_supported() ||
-			attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA)
+	if (!kvm_guest_has_pv_feature(vcpu, KVM_FEATURE_STEAL_TIME)
+			|| attr->attr != KVM_LOONGARCH_VCPU_PVTIME_GPA)
 		return -ENXIO;
 
 	if (get_user(gpa, user))

arch/loongarch/kvm/vm.c

@@ -5,6 +5,7 @@
 
 #include <linux/kvm_host.h>
 #include <asm/kvm_mmu.h>
+#include <asm/kvm_vcpu.h>
 
 const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
 	KVM_GENERIC_VM_STATS(),
@@ -39,6 +40,12 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	spin_lock_init(&kvm->arch.phyid_map_lock);
 
 	kvm_init_vmcs(kvm);
+
+	/* Enable all PV features by default */
+	kvm->arch.pv_features = BIT(KVM_FEATURE_IPI);
+	if (kvm_pvtime_supported())
+		kvm->arch.pv_features |= BIT(KVM_FEATURE_STEAL_TIME);
+
 	kvm->arch.gpa_size = BIT(cpu_vabits - 1);
 	kvm->arch.root_level = CONFIG_PGTABLE_LEVELS - 1;
 	kvm->arch.invalid_ptes[0] = 0;
@@ -126,6 +133,12 @@ static int kvm_vm_feature_has_attr(struct kvm *kvm, struct kvm_device_attr *attr
 		if (cpu_has_pmp)
 			return 0;
 		return -ENXIO;
+	case KVM_LOONGARCH_VM_FEAT_PV_IPI:
+		return 0;
+	case KVM_LOONGARCH_VM_FEAT_PV_STEALTIME:
+		if (kvm_pvtime_supported())
+			return 0;
+		return -ENXIO;
 	default:
 		return -ENXIO;
 	}