/**
* intel_gvt_init_host - Load MPT modules and detect if we're running in host
* @gvt: intel gvt device
*
* This function is called at the driver loading stage. If failed to find a
* loadable MPT module or detect currently we're running in a VM, then GVT-g
* will be disabled
*
* Returns:
* Zero on success, negative error code if failed.
*
*/
int intel_gvt_init_host(void)
{
if (intel_gvt_host.initialized)
return 0;
/* Xen DOM U */
if (xen_domain() && !xen_initial_domain())
return -ENODEV;
/* Try to load MPT modules for hypervisors */
if (xen_initial_domain()) {
/* In Xen dom0 */
intel_gvt_host.mpt = try_then_request_module(
symbol_get(xengt_mpt), "xengt");
intel_gvt_host.hypervisor_type = INTEL_GVT_HYPERVISOR_XEN;
} else {
#if IS_ENABLED(CONFIG_DRM_I915_GVT_KVMGT)
/* not in Xen. Try KVMGT */
intel_gvt_host.mpt = try_then_request_module(
symbol_get(kvmgt_mpt), "kvmgt");
intel_gvt_host.hypervisor_type = INTEL_GVT_HYPERVISOR_KVM;
#endif
}
/* Fail to load MPT modules - bail out */
if (!intel_gvt_host.mpt)
return -EINVAL;
gvt_dbg_core("Running with hypervisor %s in host mode\n",
supported_hypervisors[intel_gvt_host.hypervisor_type]);
intel_gvt_host.initialized = true;
return 0;
}
static int
nexus_xen_attach(device_t dev)
{
int error;
device_t acpi_dev = NULL;
nexus_init_resources();
bus_generic_probe(dev);
if (xen_initial_domain()) {
/* Disable some ACPI devices that are not usable by Dom0 */
acpi_cpu_disabled = true;
acpi_hpet_disabled = true;
acpi_timer_disabled = true;
acpi_dev = BUS_ADD_CHILD(dev, 10, "acpi", 0);
if (acpi_dev == NULL)
panic("Unable to add ACPI bus to Xen Dom0");
}
error = bus_generic_attach(dev);
if (xen_initial_domain() && (error == 0))
acpi_install_wakeup_handler(device_get_softc(acpi_dev));
return (error);
}
static void __init xen_filter_cpu_maps(void)
{
int i, rc;
unsigned int subtract = 0;
if (!xen_initial_domain())
return;
num_processors = 0;
disabled_cpus = 0;
for (i = 0; i < nr_cpu_ids; i++) {
rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
if (rc >= 0) {
num_processors++;
set_cpu_possible(i, true);
} else {
set_cpu_possible(i, false);
set_cpu_present(i, false);
subtract++;
}
}
#ifdef CONFIG_HOTPLUG_CPU
if (subtract)
nr_cpu_ids = nr_cpu_ids - subtract;
#endif
}
static void __init xen_init_cpuid_mask(void)
{
unsigned int ax, bx, cx, dx;
unsigned int xsave_mask;
cpuid_leaf1_edx_mask =
~((1 << X86_FEATURE_MCE) | /* disable MCE */
(1 << X86_FEATURE_MCA) | /* disable MCA */
(1 << X86_FEATURE_MTRR) | /* disable MTRR */
(1 << X86_FEATURE_ACC)); /* thermal monitoring */
if (!xen_initial_domain())
cpuid_leaf1_edx_mask &=
~((1 << X86_FEATURE_APIC) | /* disable local APIC */
(1 << X86_FEATURE_ACPI)); /* disable ACPI */
ax = 1;
xen_cpuid(&ax, &bx, &cx, &dx);
xsave_mask =
(1 << (X86_FEATURE_XSAVE % 32)) |
(1 << (X86_FEATURE_OSXSAVE % 32));
/* Xen will set CR4.OSXSAVE if supported and not disabled by force */
if ((cx & xsave_mask) != xsave_mask)
cpuid_leaf1_ecx_mask &= ~xsave_mask; /* disable XSAVE & OSXSAVE */
}
static efi_system_table_t __init *xen_efi_probe(void)
{
struct xen_platform_op op = {
.cmd = XENPF_firmware_info,
.u.firmware_info = {
.type = XEN_FW_EFI_INFO,
.index = XEN_FW_EFI_CONFIG_TABLE
}
};
union xenpf_efi_info *info = &op.u.firmware_info.u.efi_info;
if (!xen_initial_domain() || HYPERVISOR_platform_op(&op) < 0)
return NULL;
/* Here we know that Xen runs on EFI platform. */
efi.get_time = xen_efi_get_time;
efi.set_time = xen_efi_set_time;
efi.get_wakeup_time = xen_efi_get_wakeup_time;
efi.set_wakeup_time = xen_efi_set_wakeup_time;
efi.get_variable = xen_efi_get_variable;
efi.get_next_variable = xen_efi_get_next_variable;
efi.set_variable = xen_efi_set_variable;
efi.query_variable_info = xen_efi_query_variable_info;
efi.update_capsule = xen_efi_update_capsule;
efi.query_capsule_caps = xen_efi_query_capsule_caps;
efi.get_next_high_mono_count = xen_efi_get_next_high_mono_count;
efi.reset_system = xen_efi_reset_system;
efi_systab_xen.tables = info->cfg.addr;
efi_systab_xen.nr_tables = info->cfg.nent;
op.cmd = XENPF_firmware_info;
op.u.firmware_info.type = XEN_FW_EFI_INFO;
op.u.firmware_info.index = XEN_FW_EFI_VENDOR;
info->vendor.bufsz = sizeof(vendor);
set_xen_guest_handle(info->vendor.name, vendor);
if (HYPERVISOR_platform_op(&op) == 0) {
efi_systab_xen.fw_vendor = __pa_symbol(vendor);
efi_systab_xen.fw_revision = info->vendor.revision;
} else
efi_systab_xen.fw_vendor = __pa_symbol(L"UNKNOWN");
op.cmd = XENPF_firmware_info;
op.u.firmware_info.type = XEN_FW_EFI_INFO;
op.u.firmware_info.index = XEN_FW_EFI_VERSION;
if (HYPERVISOR_platform_op(&op) == 0)
efi_systab_xen.hdr.revision = info->version;
op.cmd = XENPF_firmware_info;
op.u.firmware_info.type = XEN_FW_EFI_INFO;
op.u.firmware_info.index = XEN_FW_EFI_RT_VERSION;
if (HYPERVISOR_platform_op(&op) == 0)
efi.runtime_version = info->version;
return &efi_systab_xen;
}
static __init void xen_init_cpuid_mask(void)
{
unsigned int ax, bx, cx, dx;
cpuid_leaf1_edx_mask =
~((1 << X86_FEATURE_MCE) | /* disable MCE */
(1 << X86_FEATURE_MCA) | /* disable MCA */
(1 << X86_FEATURE_ACC)); /* thermal monitoring */
if (!xen_initial_domain())
cpuid_leaf1_edx_mask &=
~((1 << X86_FEATURE_APIC) | /* disable local APIC */
(1 << X86_FEATURE_ACPI)); /* disable ACPI */
ax = 1;
cx = 0;
xen_cpuid(&ax, &bx, &cx, &dx);
/* cpuid claims we support xsave; try enabling it to see what happens */
if (cx & (1 << (X86_FEATURE_XSAVE % 32))) {
unsigned long cr4;
set_in_cr4(X86_CR4_OSXSAVE);
cr4 = read_cr4();
if ((cr4 & X86_CR4_OSXSAVE) == 0)
cpuid_leaf1_ecx_mask &= ~(1 << (X86_FEATURE_XSAVE % 32));
clear_in_cr4(X86_CR4_OSXSAVE);
}
}
static u32 xen_apic_read(u32 reg)
{
struct xen_platform_op op = {
.cmd = XENPF_get_cpuinfo,
.interface_version = XENPF_INTERFACE_VERSION,
.u.pcpu_info.xen_cpuid = 0,
};
int ret = 0;
if (!xen_initial_domain() || smp_processor_id())
return 0;
if (reg == APIC_LVR)
return 0x10;
if (reg != APIC_ID)
return 0;
ret = HYPERVISOR_dom0_op(&op);
if (ret)
return 0;
return op.u.pcpu_info.apic_id << 24;
}
static void xen_apic_write(u32 reg, u32 val)
{
WARN_ON(1);
}
static void __init xen_filter_cpu_maps(void)
{
int i, rc;
unsigned int subtract = 0;
if (!xen_initial_domain())
return;
num_processors = 0;
disabled_cpus = 0;
for (i = 0; i < nr_cpu_ids; i++) {
rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
if (rc >= 0) {
num_processors++;
set_cpu_possible(i, true);
} else {
set_cpu_possible(i, false);
set_cpu_present(i, false);
subtract++;
}
}
#ifdef CONFIG_HOTPLUG_CPU
/* This is akin to using 'nr_cpus' on the Linux command line.
* Which is OK as when we use 'dom0_max_vcpus=X' we can only
* have up to X, while nr_cpu_ids is greater than X. This
* normally is not a problem, except when CPU hotplugging
* is involved and then there might be more than X CPUs
* in the guest - which will not work as there is no
* hypercall to expand the max number of VCPUs an already
* running guest has. So cap it up to X. */
if (subtract)
nr_cpu_ids = nr_cpu_ids - subtract;
#endif
}
static int
xc_attach(device_t dev)
{
int error;
xencons_dev = dev;
xccons = tty_alloc(&xc_ttydevsw, NULL);
tty_makedev(xccons, NULL, "xc%r", 0);
callout_init(&xc_callout, 0);
xencons_ring_init();
cnsl_evt_reg = true;
callout_reset(&xc_callout, XC_POLLTIME, xc_timeout, xccons);
if (xen_initial_domain()) {
error = xen_intr_bind_virq(dev, VIRQ_CONSOLE, 0, NULL,
xencons_priv_interrupt, NULL,
INTR_TYPE_TTY, &xen_intr_handle);
KASSERT(error >= 0, ("can't register console interrupt"));
}
/* register handler to flush console on shutdown */
if ((EVENTHANDLER_REGISTER(shutdown_post_sync, xc_shutdown,
NULL, SHUTDOWN_PRI_DEFAULT)) == NULL)
printf("xencons: shutdown event registration failed!\n");
return (0);
}
static u32 xen_apic_read(u32 reg)
{
struct xen_platform_op op = {
.cmd = XENPF_get_cpuinfo,
.interface_version = XENPF_INTERFACE_VERSION,
.u.pcpu_info.xen_cpuid = 0,
};
int ret = 0;
/* Shouldn't need this as APIC is turned off for PV, and we only
* get called on the bootup processor. But just in case. */
if (!xen_initial_domain() || smp_processor_id())
return 0;
if (reg == APIC_LVR)
return 0x10;
if (reg != APIC_ID)
return 0;
ret = HYPERVISOR_dom0_op(&op);
if (ret)
return 0;
return op.u.pcpu_info.apic_id << 24;
}
static void xen_apic_write(u32 reg, u32 val)
{
/* Warn to see if there's any stray references */
WARN_ON(1);
}
static unsigned long __init xen_get_max_pages(void)
{
unsigned long max_pages, limit;
domid_t domid = DOMID_SELF;
long ret;
limit = xen_get_pages_limit();
max_pages = limit;
/*
* For the initial domain we use the maximum reservation as
* the maximum page.
*
* For guest domains the current maximum reservation reflects
* the current maximum rather than the static maximum. In this
* case the e820 map provided to us will cover the static
* maximum region.
*/
if (xen_initial_domain()) {
ret = HYPERVISOR_memory_op(XENMEM_maximum_reservation, &domid);
if (ret > 0)
max_pages = ret;
}
return min(max_pages, limit);
}
/*
* pci_xen_swiotlb_detect - set xen_swiotlb to 1 if necessary
*
* This returns non-zero if we are forced to use xen_swiotlb (by the boot
* option).
*/
int __init pci_xen_swiotlb_detect(void)
{
if (!xen_pv_domain())
return 0;
/* If running as PV guest, either iommu=soft, or swiotlb=force will
* activate this IOMMU. If running as PV privileged, activate it
* irregardless.
*/
if ((xen_initial_domain() || swiotlb || swiotlb_force))
xen_swiotlb = 1;
/* If we are running under Xen, we MUST disable the native SWIOTLB.
* Don't worry about swiotlb_force flag activating the native, as
* the 'swiotlb' flag is the only one turning it on. */
swiotlb = 0;
#ifdef CONFIG_X86_64
/* pci_swiotlb_detect_4gb turns on native SWIOTLB if no_iommu == 0
* (so no iommu=X command line over-writes).
* Considering that PV guests do not want the *native SWIOTLB* but
* only Xen SWIOTLB it is not useful to us so set no_iommu=1 here.
*/
if (max_pfn > MAX_DMA32_PFN)
no_iommu = 1;
#endif
return xen_swiotlb;
}
static int __init xen_hvc_init(void)
{
struct hvc_struct *hp;
struct hv_ops *ops;
if (!xen_pv_domain())
return -ENODEV;
if (xen_initial_domain()) {
ops = &dom0_hvc_ops;
xencons_irq = bind_virq_to_irq(VIRQ_CONSOLE, 0);
} else {
if (!xen_start_info->console.domU.evtchn)
return -ENODEV;
ops = &domU_hvc_ops;
xencons_irq = bind_evtchn_to_irq(xen_start_info->console.domU.evtchn);
}
if (xencons_irq < 0)
xencons_irq = 0; /* NO_IRQ */
else
irq_set_noprobe(xencons_irq);
hp = hvc_alloc(HVC_COOKIE, xencons_irq, ops, 256);
if (IS_ERR(hp))
return PTR_ERR(hp);
hvc = hp;
console_pfn = mfn_to_pfn(xen_start_info->console.domU.mfn);
return 0;
}
static int __init register_xen_amba_notifier(void)
{
if (!xen_initial_domain() || acpi_disabled)
return 0;
return bus_register_notifier(&amba_bustype, &amba_device_nb);
}
static int __init register_xen_platform_notifier(void)
{
if (!xen_initial_domain() || acpi_disabled)
return 0;
return bus_register_notifier(&platform_bus_type, &platform_device_nb);
}
int xen_stub_processor_init(void)
{
if (!xen_initial_domain())
return -ENODEV;
/* just reserve space for Xen, block native driver loaded */
return acpi_bus_register_driver(&xen_stub_processor_driver);
}
void omx_xenfront_exit(void)
{
/* Never succeed */
if (xen_initial_domain())
return;
xenbus_unregister_driver(&omx_xenfront_driver);
printk_inf("exit\n");
}
static void
xc_cnputc(struct consdev *dev, int c)
{
if (xen_initial_domain())
xc_cnputc_dom0(dev, c);
else
xc_cnputc_domu(dev, c);
}
void __init xen_init_apic(void)
{
x86_io_apic_ops.read = xen_io_apic_read;
/* On PV guests the APIC CPUID bit is disabled so none of the
* routines end up executing. */
if (!xen_initial_domain())
apic = &xen_pv_apic;
x86_platform.apic_post_init = xen_apic_check;
}
static ssize_t capabilities_read(struct file *file, char __user *buf,
size_t size, loff_t *off)
{
char *tmp = "";
if (xen_initial_domain())
tmp = "control_d\n";
return simple_read_from_buffer(buf, size, off, tmp, strlen(tmp));
}
static int __init xenkbd_init(void)
{
if (!xen_domain())
return -ENODEV;
if (xen_initial_domain())
return -ENODEV;
return xenbus_register_frontend(&xenkbd_driver);
}
static int __init xenkbd_init(void)
{
if (!xen_domain())
return -ENODEV;
/* Nothing to do if running in dom0. */
if (xen_initial_domain())
return -ENODEV;
return xenbus_register_frontend(&xenkbd_driver);
}
static int __init xenbus_probe_initcall(void)
{
if (!xen_domain())
return -ENODEV;
if (xen_initial_domain() || xen_hvm_domain())
return 0;
xenbus_probe(NULL);
return 0;
}
static int __init xenbus_backend_init(void)
{
int err;
if (!xen_initial_domain())
return -ENODEV;
err = misc_register(&xenbus_backend_dev);
if (err)
printk(KERN_ERR "Could not register xenbus backend device\n");
return err;
}
static int __init xen_late_init_mcelog(void)
{
/* Only DOM0 is responsible for MCE logging */
if (xen_initial_domain()) {
/* register character device /dev/mcelog for xen mcelog */
if (misc_register(&xen_mce_chrdev_device))
return -ENODEV;
return bind_virq_for_mce();
}
return -ENODEV;
}
static unsigned long __init xen_get_pages_limit(void)
{
unsigned long limit;
#ifdef CONFIG_X86_32
limit = GB(64) / PAGE_SIZE;
#else
limit = MAXMEM / PAGE_SIZE;
if (!xen_initial_domain() && xen_512gb_limit)
limit = GB(512) / PAGE_SIZE;
#endif
return limit;
}
static u32 xen_apic_read(u32 reg)
{
struct xen_platform_op op = {
.cmd = XENPF_get_cpuinfo,
.interface_version = XENPF_INTERFACE_VERSION,
.u.pcpu_info.xen_cpuid = 0,
};
int ret = 0;
/* Shouldn't need this as APIC is turned off for PV, and we only
* get called on the bootup processor. But just in case. */
if (!xen_initial_domain() || smp_processor_id())
return 0;
if (reg == APIC_LVR)
return 0x10;
#ifdef CONFIG_X86_32
if (reg == APIC_LDR)
return SET_APIC_LOGICAL_ID(1UL << smp_processor_id());
#endif
if (reg != APIC_ID)
return 0;
ret = HYPERVISOR_dom0_op(&op);
if (ret)
op.u.pcpu_info.apic_id = BAD_APICID;
return op.u.pcpu_info.apic_id << 24;
}
static void xen_apic_write(u32 reg, u32 val)
{
if (reg == APIC_LVTPC) {
(void)pmu_apic_update(reg);
return;
}
/* Warn to see if there's any stray references */
WARN(1,"register: %x, value: %x\n", reg, val);
}
static u64 xen_apic_icr_read(void)
{
return 0;
}
static void xen_apic_icr_write(u32 low, u32 id)
{
/* Warn to see if there's any stray references */
WARN_ON(1);
}
static void __init xen_fill_possible_map(void)
{
int i, rc;
if (xen_initial_domain())
return;
for (i = 0; i < nr_cpu_ids; i++) {
rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
if (rc >= 0) {
num_processors++;
set_cpu_possible(i, true);
}
}
}
static int xen_cons_init(void)
{
struct hv_ops *ops;
if (!xen_pv_domain())
return 0;
if (xen_initial_domain())
ops = &dom0_hvc_ops;
else
ops = &domU_hvc_ops;
hvc_instantiate(HVC_COOKIE, 0, ops);
return 0;
}
static void __exit xen_acpi_processor_exit(void)
{
if (!xen_initial_domain())
return;
acpi_processor_uninstall_hotplug_notify();
acpi_bus_unregister_driver(&xen_acpi_processor_driver);
/*
* stub reserve space again to prevent any chance of native
* driver loading.
*/
xen_stub_processor_init();
return;
}