[RFC PATCH 2/8] KVM: Add KVM_MAP_MEMORY vcpu ioctl to pre-populate guest memory

[isaku . yamahata]

From: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>

Add new ioctl KVM_MAP_MEMORY in the kvm common code. It iterates on the
memory range and call arch specific function.  Add stub function as weak
symbol.

[1] https://lore.kernel.org/kvm/Zbrj5WKVgMsUFDtb@xxxxxxxxxx/
Suggested-by: Sean Christopherson <seanjc@xxxxxxxxxx>
Signed-off-by: Isaku Yamahata <isaku.yamahata@xxxxxxxxx>
---
 include/linux/kvm_host.h |  4 +++
 include/uapi/linux/kvm.h | 15 ++++++++
 virt/kvm/kvm_main.c      | 74 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 93 insertions(+)

diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9807ea98b568..afbed288d625 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2445,4 +2445,8 @@ static inline int kvm_gmem_get_pfn(struct kvm *kvm,
 }
 #endif /* CONFIG_KVM_PRIVATE_MEM */
 
+int kvm_arch_vcpu_pre_map_memory(struct kvm_vcpu *vcpu);
+int kvm_arch_vcpu_map_memory(struct kvm_vcpu *vcpu,
+			     struct kvm_memory_mapping *mapping);
+
 #endif
diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h
index 2190adbe3002..f5d6b481244f 100644
--- a/include/uapi/linux/kvm.h
+++ b/include/uapi/linux/kvm.h
@@ -917,6 +917,7 @@ struct kvm_enable_cap {
 #define KVM_CAP_MEMORY_ATTRIBUTES 233
 #define KVM_CAP_GUEST_MEMFD 234
 #define KVM_CAP_VM_TYPES 235
+#define KVM_CAP_MAP_MEMORY 236
 
 struct kvm_irq_routing_irqchip {
 	__u32 irqchip;
@@ -1548,4 +1549,18 @@ struct kvm_create_guest_memfd {
 	__u64 reserved[6];
 };
 
+#define KVM_MAP_MEMORY	_IOWR(KVMIO, 0xd5, struct kvm_memory_mapping)
+
+#define KVM_MEMORY_MAPPING_FLAG_WRITE	_BITULL(0)
+#define KVM_MEMORY_MAPPING_FLAG_EXEC	_BITULL(1)
+#define KVM_MEMORY_MAPPING_FLAG_USER	_BITULL(2)
+#define KVM_MEMORY_MAPPING_FLAG_PRIVATE	_BITULL(3)
+
+struct kvm_memory_mapping {
+	__u64 base_gfn;
+	__u64 nr_pages;
+	__u64 flags;
+	__u64 source;
+};
+
 #endif /* __LINUX_KVM_H */
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d1fd9cb5d037..d77c9b79d76b 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4419,6 +4419,69 @@ static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu)
 	return fd;
 }
 
+__weak int kvm_arch_vcpu_pre_map_memory(struct kvm_vcpu *vcpu)
+{
+	return -EOPNOTSUPP;
+}
+
+__weak int kvm_arch_vcpu_map_memory(struct kvm_vcpu *vcpu,
+				    struct kvm_memory_mapping *mapping)
+{
+	return -EOPNOTSUPP;
+}
+
+static int kvm_vcpu_map_memory(struct kvm_vcpu *vcpu,
+			       struct kvm_memory_mapping *mapping)
+{
+	bool added = false;
+	int idx, r = 0;
+
+	if (mapping->flags & ~(KVM_MEMORY_MAPPING_FLAG_WRITE |
+			       KVM_MEMORY_MAPPING_FLAG_EXEC |
+			       KVM_MEMORY_MAPPING_FLAG_USER |
+			       KVM_MEMORY_MAPPING_FLAG_PRIVATE))
+		return -EINVAL;
+	if ((mapping->flags & KVM_MEMORY_MAPPING_FLAG_PRIVATE) &&
+	    !kvm_arch_has_private_mem(vcpu->kvm))
+		return -EINVAL;
+
+	/* Sanity check */
+	if (!IS_ALIGNED(mapping->source, PAGE_SIZE) ||
+	    !mapping->nr_pages ||
+	    mapping->base_gfn + mapping->nr_pages <= mapping->base_gfn)
+		return -EINVAL;
+
+	vcpu_load(vcpu);
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+	r = kvm_arch_vcpu_pre_map_memory(vcpu);
+	if (r)
+		return r;
+
+	while (mapping->nr_pages) {
+		if (signal_pending(current)) {
+			r = -ERESTARTSYS;
+			break;
+		}
+
+		if (need_resched())
+			cond_resched();
+
+		r = kvm_arch_vcpu_map_memory(vcpu, mapping);
+		if (r)
+			break;
+
+		added = true;
+	}
+
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	vcpu_put(vcpu);
+
+	if (added && mapping->nr_pages > 0)
+		r = -EAGAIN;
+
+	return r;
+}
+
 static long kvm_vcpu_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -4620,6 +4683,17 @@ static long kvm_vcpu_ioctl(struct file *filp,
 		r = kvm_vcpu_ioctl_get_stats_fd(vcpu);
 		break;
 	}
+	case KVM_MAP_MEMORY: {
+		struct kvm_memory_mapping mapping;
+
+		r = -EFAULT;
+		if (copy_from_user(&mapping, argp, sizeof(mapping)))
+			break;
+		r = kvm_vcpu_map_memory(vcpu, &mapping);
+		if (copy_to_user(argp, &mapping, sizeof(mapping)))
+			r = -EFAULT;
+		break;
+	}
 	default:
 		r = kvm_arch_vcpu_ioctl(filp, ioctl, arg);
 	}
-- 
2.25.1