KVM: Xen PV-on-HVM guest support

Support for Xen PV-on-HVM guests can be implemented almost entirely in
userspace, except for handling one annoying MSR that maps a Xen
hypercall blob into guest address space.

A generic mechanism to delegate MSR writes to userspace seems overkill
and risks encouraging similar MSR abuse in the future.  Thus this patch
adds special support for the Xen HVM MSR.

I implemented a new ioctl, KVM_XEN_HVM_CONFIG, that lets userspace tell
KVM which MSR the guest will write to, as well as the starting address
and size of the hypercall blobs (one each for 32-bit and 64-bit) that
userspace has loaded from files.  When the guest writes to the MSR, KVM
copies one page of the blob from userspace to the guest.

I've tested this patch with a hacked-up version of Gerd's userspace
code, booting a number of guests (CentOS 5.3 i386 and x86_64, and
FreeBSD 8.0-RC1 amd64) and exercising PV network and block devices.

[jan: fix i386 build warning]
[avi: future proof abi with a flags field]
Signed-off-by: Ed Swierk <eswierk@aristanetworks.com>
Signed-off-by: Jan Kiszka <jan.kiszka@siemens.com>
Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>
Signed-off-by: Avi Kivity <avi@redhat.com>

Documentation/kvm/api.txt

@@ -593,6 +593,30 @@ struct kvm_irqchip {
 	} chip;
 };
 
+4.27 KVM_XEN_HVM_CONFIG
+
+Capability: KVM_CAP_XEN_HVM
+Architectures: x86
+Type: vm ioctl
+Parameters: struct kvm_xen_hvm_config (in)
+Returns: 0 on success, -1 on error
+
+Sets the MSR that the Xen HVM guest uses to initialize its hypercall
+page, and provides the starting address and size of the hypercall
+blobs in userspace.  When the guest writes the MSR, kvm copies one
+page of a blob (32- or 64-bit, depending on the vcpu mode) to guest
+memory.
+
+struct kvm_xen_hvm_config {
+	__u32 flags;
+	__u32 msr;
+	__u64 blob_addr_32;
+	__u64 blob_addr_64;
+	__u8 blob_size_32;
+	__u8 blob_size_64;
+	__u8 pad2[30];
+};
+
 5. The kvm_run structure
 
 Application code obtains a pointer to the kvm_run structure by

arch/x86/include/asm/kvm.h

@@ -19,6 +19,7 @@
 #define __KVM_HAVE_MSIX
 #define __KVM_HAVE_MCE
 #define __KVM_HAVE_PIT_STATE2
+#define __KVM_HAVE_XEN_HVM
 
 /* Architectural interrupt line count. */
 #define KVM_NR_INTERRUPTS 256

arch/x86/include/asm/kvm_host.h

@@ -410,6 +410,8 @@ struct kvm_arch{
 
 	unsigned long irq_sources_bitmap;
 	u64 vm_init_tsc;
+
+	struct kvm_xen_hvm_config xen_hvm_config;
 };
 
 struct kvm_vm_stat {

arch/x86/kvm/x86.c

@@ -857,6 +857,38 @@ static int set_msr_mce(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 	return 0;
 }
 
+static int xen_hvm_config(struct kvm_vcpu *vcpu, u64 data)
+{
+	struct kvm *kvm = vcpu->kvm;
+	int lm = is_long_mode(vcpu);
+	u8 *blob_addr = lm ? (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_64
+		: (u8 *)(long)kvm->arch.xen_hvm_config.blob_addr_32;
+	u8 blob_size = lm ? kvm->arch.xen_hvm_config.blob_size_64
+		: kvm->arch.xen_hvm_config.blob_size_32;
+	u32 page_num = data & ~PAGE_MASK;
+	u64 page_addr = data & PAGE_MASK;
+	u8 *page;
+	int r;
+
+	r = -E2BIG;
+	if (page_num >= blob_size)
+		goto out;
+	r = -ENOMEM;
+	page = kzalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!page)
+		goto out;
+	r = -EFAULT;
+	if (copy_from_user(page, blob_addr + (page_num * PAGE_SIZE), PAGE_SIZE))
+		goto out_free;
+	if (kvm_write_guest(kvm, page_addr, page, PAGE_SIZE))
+		goto out_free;
+	r = 0;
+out_free:
+	kfree(page);
+out:
+	return r;
+}
+
 int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 {
 	switch (msr) {
@@ -972,6 +1004,8 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, u32 msr, u64 data)
 			"0x%x data 0x%llx\n", msr, data);
 		break;
 	default:
+		if (msr && (msr == vcpu->kvm->arch.xen_hvm_config.msr))
+			return xen_hvm_config(vcpu, data);
 		if (!ignore_msrs) {
 			pr_unimpl(vcpu, "unhandled wrmsr: 0x%x data %llx\n",
 				msr, data);
@@ -1246,6 +1280,7 @@ int kvm_dev_ioctl_check_extension(long ext)
 	case KVM_CAP_PIT2:
 	case KVM_CAP_PIT_STATE2:
 	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
+	case KVM_CAP_XEN_HVM:
 		r = 1;
 		break;
 	case KVM_CAP_COALESCED_MMIO:
@@ -2441,6 +2476,17 @@ long kvm_arch_vm_ioctl(struct file *filp,
 		r = 0;
 		break;
 	}
+	case KVM_XEN_HVM_CONFIG: {
+		r = -EFAULT;
+		if (copy_from_user(&kvm->arch.xen_hvm_config, argp,
+				   sizeof(struct kvm_xen_hvm_config)))
+			goto out;
+		r = -EINVAL;
+		if (kvm->arch.xen_hvm_config.flags)
+			goto out;
+		r = 0;
+		break;
+	}
 	default:
 		;
 	}

include/linux/kvm.h

@@ -436,6 +436,9 @@ struct kvm_ioeventfd {
 #endif
 #define KVM_CAP_IOEVENTFD 36
 #define KVM_CAP_SET_IDENTITY_MAP_ADDR 37
+#ifdef __KVM_HAVE_XEN_HVM
+#define KVM_CAP_XEN_HVM 38
+#endif
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -488,6 +491,18 @@ struct kvm_x86_mce {
 };
 #endif
 
+#ifdef KVM_CAP_XEN_HVM
+struct kvm_xen_hvm_config {
+	__u32 flags;
+	__u32 msr;
+	__u64 blob_addr_32;
+	__u64 blob_addr_64;
+	__u8 blob_size_32;
+	__u8 blob_size_64;
+	__u8 pad2[30];
+};
+#endif
+
 #define KVM_IRQFD_FLAG_DEASSIGN (1 << 0)
 
 struct kvm_irqfd {
@@ -546,6 +561,7 @@ struct kvm_irqfd {
 #define KVM_CREATE_PIT2		   _IOW(KVMIO, 0x77, struct kvm_pit_config)
 #define KVM_SET_BOOT_CPU_ID        _IO(KVMIO, 0x78)
 #define KVM_IOEVENTFD             _IOW(KVMIO, 0x79, struct kvm_ioeventfd)
+#define KVM_XEN_HVM_CONFIG        _IOW(KVMIO, 0x7a, struct kvm_xen_hvm_config)
 
 /*
  * ioctls for vcpu fds