Merge branch 'kvm-prefault' into HEAD

Pre-population has been requested several times to mitigate KVM page faults
during guest boot or after live migration.  It is also required by TDX
before filling in the initial guest memory with measured contents.
Introduce it as a generic API.

2 files changed, 63 insertions, 0 deletions

diff --git a/virt/kvm/Kconfig b/virt/kvm/Kconfig
index 754c6c923427..b14e14cdbfb9 100644
--- a/virt/kvm/Kconfig
+++ b/virt/kvm/Kconfig
@@ -67,6 +67,9 @@ config HAVE_KVM_INVALID_WAKEUPS
 config KVM_GENERIC_DIRTYLOG_READ_PROTECT
        bool
 
+config KVM_GENERIC_PRE_FAULT_MEMORY
+       bool
+
 config KVM_COMPAT
        def_bool y
        depends on KVM && COMPAT && !(S390 || ARM64 || RISCV)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 8e422c2c9450..f817ec66c85f 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4373,6 +4373,52 @@ static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu)
 	return fd;
 }
 
+#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY
+static int kvm_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
+				     struct kvm_pre_fault_memory *range)
+{
+	int idx;
+	long r;
+	u64 full_size;
+
+	if (range->flags)
+		return -EINVAL;
+
+	if (!PAGE_ALIGNED(range->gpa) ||
+	    !PAGE_ALIGNED(range->size) ||
+	    range->gpa + range->size <= range->gpa)
+		return -EINVAL;
+
+	vcpu_load(vcpu);
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
+	full_size = range->size;
+	do {
+		if (signal_pending(current)) {
+			r = -EINTR;
+			break;
+		}
+
+		r = kvm_arch_vcpu_pre_fault_memory(vcpu, range);
+		if (WARN_ON_ONCE(r == 0 || r == -EIO))
+			break;
+
+		if (r < 0)
+			break;
+
+		range->size -= r;
+		range->gpa += r;
+		cond_resched();
+	} while (range->size);
+
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	vcpu_put(vcpu);
+
+	/* Return success if at least one page was mapped successfully.  */
+	return full_size == range->size ? r : 0;
+}
+#endif
+
 static long kvm_vcpu_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -4573,6 +4619,20 @@ out_free1:
 		r = kvm_vcpu_ioctl_get_stats_fd(vcpu);
 		break;
 	}
+#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY
+	case KVM_PRE_FAULT_MEMORY: {
+		struct kvm_pre_fault_memory range;
+
+		r = -EFAULT;
+		if (copy_from_user(&range, argp, sizeof(range)))
+			break;
+		r = kvm_vcpu_pre_fault_memory(vcpu, &range);
+		/* Pass back leftover range. */
+		if (copy_to_user(argp, &range, sizeof(range)))
+			r = -EFAULT;
+		break;
+	}
+#endif
 	default:
 		r = kvm_arch_vcpu_ioctl(filp, ioctl, arg);
 	}