LoongArch: KVM: Add paravirt preempt feature in hypervisor side

Feature KVM_FEATURE_PREEMPT is added to show whether vCPU is preempted
or not. It is to help guest OS scheduling or lock checking etc. Here
add KVM_FEATURE_PREEMPT feature and use one byte as preempted flag in
the steal time structure.

Signed-off-by: Bibo Mao <maobibo@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

Author: bibo-mao

arch/loongarch/include/asm/kvm_host.h

@@ -165,6 +165,7 @@ enum emulation_result {
 
 #define LOONGARCH_PV_FEAT_UPDATED	BIT_ULL(63)
 #define LOONGARCH_PV_FEAT_MASK		(BIT(KVM_FEATURE_IPI) |		\
+					 BIT(KVM_FEATURE_PREEMPT) |	\
 					 BIT(KVM_FEATURE_STEAL_TIME) |	\
 					 BIT(KVM_FEATURE_USER_HCALL) |	\
 					 BIT(KVM_FEATURE_VIRT_EXTIOI))
@@ -254,6 +255,7 @@ struct kvm_vcpu_arch {
 		u64 guest_addr;
 		u64 last_steal;
 		struct gfn_to_hva_cache cache;
+		u8  preempted;
 	} st;
 };
 

arch/loongarch/include/asm/kvm_para.h

@@ -37,8 +37,10 @@ struct kvm_steal_time {
 	__u64 steal;
 	__u32 version;
 	__u32 flags;
-	__u32 pad[12];
+	__u8  preempted;
+	__u8  pad[47];
 };
+#define KVM_VCPU_PREEMPTED		(1 << 0)
 
 /*
  * Hypercall interface for KVM hypervisor

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

@@ -105,6 +105,7 @@ struct kvm_fpu {
 #define  KVM_LOONGARCH_VM_FEAT_PV_STEALTIME	7
 #define  KVM_LOONGARCH_VM_FEAT_PTW		8
 #define  KVM_LOONGARCH_VM_FEAT_MSGINT		9
+#define  KVM_LOONGARCH_VM_FEAT_PV_PREEMPT	10
 
 /* Device Control API on vcpu fd */
 #define KVM_LOONGARCH_VCPU_CPUCFG	0

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

@@ -15,6 +15,7 @@
 #define CPUCFG_KVM_FEATURE		(CPUCFG_KVM_BASE + 4)
 #define  KVM_FEATURE_IPI		1
 #define  KVM_FEATURE_STEAL_TIME		2
+#define  KVM_FEATURE_PREEMPT		3
 /* BIT 24 - 31 are features configurable by user space vmm */
 #define  KVM_FEATURE_VIRT_EXTIOI	24
 #define  KVM_FEATURE_USER_HCALL		25

arch/loongarch/kvm/vcpu.c

@@ -181,6 +181,11 @@ static void kvm_update_stolen_time(struct kvm_vcpu *vcpu)
 	}
 
 	st = (struct kvm_steal_time __user *)ghc->hva;
+	if (kvm_guest_has_pv_feature(vcpu, KVM_FEATURE_PREEMPT)) {
+		unsafe_put_user(0, &st->preempted, out);
+		vcpu->arch.st.preempted = 0;
+	}
+
 	unsafe_get_user(version, &st->version, out);
 	if (version & 1)
 		version += 1; /* first time write, random junk */
@@ -1795,11 +1800,57 @@ static int _kvm_vcpu_put(struct kvm_vcpu *vcpu, int cpu)
 	return 0;
 }
 
+static void kvm_vcpu_set_pv_preempted(struct kvm_vcpu *vcpu)
+{
+	gpa_t gpa;
+	struct gfn_to_hva_cache *ghc;
+	struct kvm_memslots *slots;
+	struct kvm_steal_time __user *st;
+
+	gpa = vcpu->arch.st.guest_addr;
+	if (!(gpa & KVM_STEAL_PHYS_VALID))
+		return;
+
+	/* vCPU may be preempted for many times */
+	if (vcpu->arch.st.preempted)
+		return;
+
+	/* This happens on process exit */
+	if (unlikely(current->mm != vcpu->kvm->mm))
+		return;
+
+	gpa &= KVM_STEAL_PHYS_MASK;
+	ghc = &vcpu->arch.st.cache;
+	slots = kvm_memslots(vcpu->kvm);
+	if (slots->generation != ghc->generation || gpa != ghc->gpa) {
+		if (kvm_gfn_to_hva_cache_init(vcpu->kvm, ghc, gpa, sizeof(*st))) {
+			ghc->gpa = INVALID_GPA;
+			return;
+		}
+	}
+
+	st = (struct kvm_steal_time __user *)ghc->hva;
+	unsafe_put_user(KVM_VCPU_PREEMPTED, &st->preempted, out);
+	vcpu->arch.st.preempted = KVM_VCPU_PREEMPTED;
+out:
+	mark_page_dirty_in_slot(vcpu->kvm, ghc->memslot, gpa_to_gfn(ghc->gpa));
+}
+
 void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
 {
-	int cpu;
+	int cpu, idx;
 	unsigned long flags;
 
+	if (vcpu->preempted && kvm_guest_has_pv_feature(vcpu, KVM_FEATURE_PREEMPT)) {
+		/*
+		 * Take the srcu lock as memslots will be accessed to check
+		 * the gfn cache generation against the memslots generation.
+		 */
+		idx = srcu_read_lock(&vcpu->kvm->srcu);
+		kvm_vcpu_set_pv_preempted(vcpu);
+		srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	}
+
 	local_irq_save(flags);
 	cpu = smp_processor_id();
 	vcpu->arch.last_sched_cpu = cpu;

arch/loongarch/kvm/vm.c

@@ -52,7 +52,9 @@ static void kvm_vm_init_features(struct kvm *kvm)
 	kvm->arch.pv_features = BIT(KVM_FEATURE_IPI);
 	kvm->arch.kvm_features = BIT(KVM_LOONGARCH_VM_FEAT_PV_IPI);
 	if (kvm_pvtime_supported()) {
+		kvm->arch.pv_features |= BIT(KVM_FEATURE_PREEMPT);
 		kvm->arch.pv_features |= BIT(KVM_FEATURE_STEAL_TIME);
+		kvm->arch.kvm_features |= BIT(KVM_LOONGARCH_VM_FEAT_PV_PREEMPT);
 		kvm->arch.kvm_features |= BIT(KVM_LOONGARCH_VM_FEAT_PV_STEALTIME);
 	}
 }
@@ -154,6 +156,7 @@ static int kvm_vm_feature_has_attr(struct kvm *kvm, struct kvm_device_attr *attr
 	case KVM_LOONGARCH_VM_FEAT_MSGINT:
 	case KVM_LOONGARCH_VM_FEAT_PMU:
 	case KVM_LOONGARCH_VM_FEAT_PV_IPI:
+	case KVM_LOONGARCH_VM_FEAT_PV_PREEMPT:
 	case KVM_LOONGARCH_VM_FEAT_PV_STEALTIME:
 		if (kvm_vm_support(&kvm->arch, attr->attr))
 			return 0;