ShuriZma
/
xemu
mirror of https://github.com/xemu-project/xemu.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

* bugfixes 

* show machine ACPI support in QAPI
 * Core Xen emulation support for KVM/x86
 -----BEGIN PGP SIGNATURE-----
 
 iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmQAlrYUHHBib256aW5p
 QHJlZGhhdC5jb20ACgkQv/vSX3jHroONWwf/fxDUMcZUvvatNxiVMhNfqEt/cL0F
 Durv1PmbbeVh9PP0W7XFkEXO3LCIRDyR4rtmCs7gHGdmzDOWQ+QIWgQijQ/y7ElQ
 bTVsvs0+s/6H3csP3dJTJaXSHshbQvrAZTsyk5KcAB6xdL1KqulfLUoGvXJhAmRs
 NKZN8un+nuAhFhL0VBWA9eQaP+BVHQI5ItAj8PaoBby4+Q9fNnat6j1/G4iLly8J
 dxIwCnuRHLiB3melWtadwbv6ddLJFeZNa50HUIsynqoItTzmRVr+oXz1yfq087dB
 9uksmoqb+icGEdwqs0iYbQ/dhVnIrMDpn/n2Us28S5VdIMVvxr1JEbEkSQ==
 =0jY8
 -----END PGP SIGNATURE-----

Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging

* bugfixes
* show machine ACPI support in QAPI
* Core Xen emulation support for KVM/x86

# -----BEGIN PGP SIGNATURE-----
#
# iQFIBAABCAAyFiEE8TM4V0tmI4mGbHaCv/vSX3jHroMFAmQAlrYUHHBib256aW5p
# QHJlZGhhdC5jb20ACgkQv/vSX3jHroONWwf/fxDUMcZUvvatNxiVMhNfqEt/cL0F
# Durv1PmbbeVh9PP0W7XFkEXO3LCIRDyR4rtmCs7gHGdmzDOWQ+QIWgQijQ/y7ElQ
# bTVsvs0+s/6H3csP3dJTJaXSHshbQvrAZTsyk5KcAB6xdL1KqulfLUoGvXJhAmRs
# NKZN8un+nuAhFhL0VBWA9eQaP+BVHQI5ItAj8PaoBby4+Q9fNnat6j1/G4iLly8J
# dxIwCnuRHLiB3melWtadwbv6ddLJFeZNa50HUIsynqoItTzmRVr+oXz1yfq087dB
# 9uksmoqb+icGEdwqs0iYbQ/dhVnIrMDpn/n2Us28S5VdIMVvxr1JEbEkSQ==
# =0jY8
# -----END PGP SIGNATURE-----
# gpg: Signature made Thu 02 Mar 2023 12:29:42 GMT
# gpg:                using RSA key F13338574B662389866C7682BFFBD25F78C7AE83
# gpg:                issuer "pbonzini@redhat.com"
# gpg: Good signature from "Paolo Bonzini <bonzini@gnu.org>" [full]
# gpg:                 aka "Paolo Bonzini <pbonzini@redhat.com>" [full]
# Primary key fingerprint: 46F5 9FBD 57D6 12E7 BFD4  E2F7 7E15 100C CD36 69B1
#      Subkey fingerprint: F133 3857 4B66 2389 866C  7682 BFFB D25F 78C7 AE83

* tag 'for-upstream' of https://gitlab.com/bonzini/qemu: (62 commits)
  Makefile: qemu-bundle is a directory
  qapi: Add 'acpi' field to 'query-machines' output
  hw/xen: Subsume xen_be_register_common() into xen_be_init()
  i386/xen: Document Xen HVM emulation
  kvm/i386: Add xen-evtchn-max-pirq property
  hw/xen: Support MSI mapping to PIRQ
  hw/xen: Support GSI mapping to PIRQ
  hw/xen: Implement emulated PIRQ hypercall support
  i386/xen: Implement HYPERVISOR_physdev_op
  hw/xen: Automatically add xen-platform PCI device for emulated Xen guests
  hw/xen: Add basic ring handling to xenstore
  hw/xen: Add xen_xenstore device for xenstore emulation
  hw/xen: Add backend implementation of interdomain event channel support
  i386/xen: handle HVMOP_get_param
  i386/xen: Reserve Xen special pages for console, xenstore rings
  i386/xen: handle PV timer hypercalls
  hw/xen: Implement GNTTABOP_query_size
  i386/xen: Implement HYPERVISOR_grant_table_op and GNTTABOP_[gs]et_verson
  hw/xen: Support mapping grant frames
  hw/xen: Add xen_gnttab device for grant table emulation
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
This commit is contained in:
Peter Maydell 2023-03-02 16:13:45 +00:00
parent 262312d7ba 526947e496
commit c61d1a066c
82 changed files with 13465 additions and 211 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
Makefile
View File

@ -220,7 +220,7 @@ qemu-%.tar.bz2:
distclean: clean recurse-distclean
-$(quiet-@)test -f build.ninja && $(NINJA) $(NINJAFLAGS) -t clean -g || :
rm -f config-host.mak Makefile.prereqs qemu-bundle
rm -f config-host.mak Makefile.prereqs
rm -f tests/tcg/*/config-target.mak tests/tcg/config-host.mak
rm -f config.status
rm -f roms/seabios/config.mak
@ -230,7 +230,7 @@ distclean: clean recurse-distclean
rm -f Makefile.ninja Makefile.mtest build.ninja.stamp meson.stamp
rm -f config.log
rm -f linux-headers/asm
rm -Rf .sdk
rm -Rf .sdk qemu-bundle
find-src-path = find "$(SRC_PATH)" -path "$(SRC_PATH)/meson" -prune -o \
-type l -prune -o \( -name "*.[chsS]" -o -name "*.[ch].inc" \)

3
accel/kvm/kvm-all.c
View File

@ -3703,6 +3703,9 @@ static void kvm_accel_instance_init(Object *obj)
s->kvm_dirty_ring_size = 0;
s->notify_vmexit = NOTIFY_VMEXIT_OPTION_RUN;
s->notify_window = 0;
s->xen_version = 0;
s->xen_gnttab_max_frames = 64;
s->xen_evtchn_max_pirq = 256;
}
/**

2
accel/xen/xen-all.c
View File

@ -171,6 +171,8 @@ static int xen_init(MachineState *ms)
* opt out of system RAM being allocated by generic code
*/
mc->default_ram_id = NULL;
xen_mode = XEN_ATTACH;
return 0;
}

76
docs/system/i386/xen.rst Normal file
View File

@ -0,0 +1,76 @@
Xen HVM guest support
=====================
Description
-----------
KVM has support for hosting Xen guests, intercepting Xen hypercalls and event
channel (Xen PV interrupt) delivery. This allows guests which expect to be
run under Xen to be hosted in QEMU under Linux/KVM instead.
Setup
-----
Xen mode is enabled by setting the ``xen-version`` property of the KVM
accelerator, for example for Xen 4.10:
.. parsed-literal::
|qemu_system| --accel kvm,xen-version=0x4000a
Additionally, virtual APIC support can be advertised to the guest through the
``xen-vapic`` CPU flag:
.. parsed-literal::
|qemu_system| --accel kvm,xen-version=0x4000a --cpu host,+xen_vapic
When Xen support is enabled, QEMU changes hypervisor identification (CPUID
0x40000000..0x4000000A) to Xen. The KVM identification and features are not
advertised to a Xen guest. If Hyper-V is also enabled, the Xen identification
moves to leaves 0x40000100..0x4000010A.
The Xen platform device is enabled automatically for a Xen guest. This allows
a guest to unplug all emulated devices, in order to use Xen PV block and network
drivers instead. Note that until the Xen PV device back ends are enabled to work
with Xen mode in QEMU, that is unlikely to cause significant joy. Linux guests
can be dissuaded from this by adding 'xen_emul_unplug=never' on their command
line, and it can also be noted that AHCI disk controllers are exempt from being
unplugged, as are passthrough VFIO PCI devices.
Properties
----------
The following properties exist on the KVM accelerator object:
``xen-version``
This property contains the Xen version in ``XENVER_version`` form, with the
major version in the top 16 bits and the minor version in the low 16 bits.
Setting this property enables the Xen guest support.
``xen-evtchn-max-pirq``
Xen PIRQs represent an emulated physical interrupt, either GSI or MSI, which
can be routed to an event channel instead of to the emulated I/O or local
APIC. By default, QEMU permits only 256 PIRQs because this allows maximum
compatibility with 32-bit MSI where the higher bits of the PIRQ# would need
to be in the upper 64 bits of the MSI message. For guests with large numbers
of PCI devices (and none which are limited to 32-bit addressing) it may be
desirable to increase this value.
``xen-gnttab-max-frames``
Xen grant tables are the means by which a Xen guest grants access to its
memory for PV back ends (disk, network, etc.). Since QEMU only supports v1
grant tables which are 8 bytes in size, each page (each frame) of the grant
table can reference 512 pages of guest memory. The default number of frames
is 64, allowing for 32768 pages of guest memory to be accessed by PV backends
through simultaneous grants. For guests with large numbers of PV devices and
high throughput, it may be desirable to increase this value.
OS requirements
---------------
The minimal Xen support in the KVM accelerator requires the host to be running
Linux v5.12 or newer. Later versions add optimisations: Linux v5.17 added
acceleration of interrupt delivery via the Xen PIRQ mechanism, and Linux v5.19
accelerated Xen PV timers and inter-processor interrupts (IPIs).

1
docs/system/target-i386.rst
View File

@ -27,6 +27,7 @@ Architectural features
i386/cpu
i386/hyperv
i386/xen
i386/kvm-pv
i386/sgx
i386/amd-memory-encryption

29
hmp-commands.hx
View File

@ -1815,3 +1815,32 @@ SRST
Dump the FDT in dtb format to *filename*.
ERST
#endif
#if defined(CONFIG_XEN_EMU)
{
.name = "xen-event-inject",
.args_type = "port:i",
.params = "port",
.help = "inject event channel",
.cmd = hmp_xen_event_inject,
},
SRST
``xen-event-inject`` *port*
Notify guest via event channel on port *port*.
ERST
{
.name = "xen-event-list",
.args_type = "",
.params = "",
.help = "list event channel state",
.cmd = hmp_xen_event_list,
},
SRST
``xen-event-list``
List event channels in the guest
ERST
#endif

1
hw/Kconfig
View File

@ -41,6 +41,7 @@ source tpm/Kconfig
source usb/Kconfig
source virtio/Kconfig
source vfio/Kconfig
source xen/Kconfig
source watchdog/Kconfig
# arch Kconfig

1
hw/core/machine-qmp-cmds.c
View File

@ -102,6 +102,7 @@ MachineInfoList *qmp_query_machines(Error **errp)
info->hotpluggable_cpus = mc->has_hotpluggable_cpus;
info->numa_mem_supported = mc->numa_mem_supported;
info->deprecated = !!mc->deprecation_reason;
info->acpi = !!object_class_property_find(OBJECT_CLASS(mc), "acpi");
if (mc->default_cpu_type) {
info->default_cpu_type = g_strdup(mc->default_cpu_type);
}

5
hw/i386/Kconfig
View File

@ -136,3 +136,8 @@ config VMPORT
config VMMOUSE
bool
depends on VMPORT
config XEN_EMU
bool
default y
depends on KVM && (I386 || X86_64)

13
hw/i386/kvm/meson.build
View File

@ -4,5 +4,18 @@ i386_kvm_ss.add(when: 'CONFIG_APIC', if_true: files('apic.c'))
i386_kvm_ss.add(when: 'CONFIG_I8254', if_true: files('i8254.c'))
i386_kvm_ss.add(when: 'CONFIG_I8259', if_true: files('i8259.c'))
i386_kvm_ss.add(when: 'CONFIG_IOAPIC', if_true: files('ioapic.c'))
i386_kvm_ss.add(when: 'CONFIG_XEN_EMU', if_true: files(
'xen_overlay.c',
'xen_evtchn.c',
'xen_gnttab.c',
'xen_xenstore.c',
))
i386_ss.add_all(when: 'CONFIG_KVM', if_true: i386_kvm_ss)
xen_stubs_ss = ss.source_set()
xen_stubs_ss.add(when: 'CONFIG_XEN_EMU', if_false: files(
'xen-stubs.c',
))
specific_ss.add_all(when: 'CONFIG_SOFTMMU', if_true: xen_stubs_ss)

5
hw/i386/kvm/trace-events Normal file
View File

@ -0,0 +1,5 @@
kvm_xen_map_pirq(int pirq, int gsi) "pirq %d gsi %d"
kvm_xen_unmap_pirq(int pirq, int gsi) "pirq %d gsi %d"
kvm_xen_get_free_pirq(int pirq, int type) "pirq %d type %d"
kvm_xen_bind_pirq(int pirq, int port) "pirq %d port %d"
kvm_xen_unmask_pirq(int pirq, char *dev, int vector) "pirq %d dev %s vector %d"

1
hw/i386/kvm/trace.h Normal file
View File

@ -0,0 +1 @@
#include "trace/trace-hw_i386_kvm.h"

44
hw/i386/kvm/xen-stubs.c Normal file
View File

@ -0,0 +1,44 @@
/*
* QEMU Xen emulation: QMP stubs
*
* Copyright © 2023 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Authors: David Woodhouse <dwmw2@infradead.org>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "qapi/error.h"
#include "qapi/qapi-commands-misc-target.h"
#include "xen_evtchn.h"
void xen_evtchn_snoop_msi(PCIDevice *dev, bool is_msix, unsigned int vector,
uint64_t addr, uint32_t data, bool is_masked)
{
}
void xen_evtchn_remove_pci_device(PCIDevice *dev)
{
}
bool xen_evtchn_deliver_pirq_msi(uint64_t address, uint32_t data)
{
return false;
}
#ifdef TARGET_I386
EvtchnInfoList *qmp_xen_event_list(Error **errp)
{
error_setg(errp, "Xen event channel emulation not enabled");
return NULL;
}
void qmp_xen_event_inject(uint32_t port, Error **errp)
{
error_setg(errp, "Xen event channel emulation not enabled");
}
#endif

2341
hw/i386/kvm/xen_evtchn.c Normal file
View File

File diff suppressed because it is too large Load Diff

88
hw/i386/kvm/xen_evtchn.h Normal file
View File

@ -0,0 +1,88 @@
/*
* QEMU Xen emulation: Event channel support
*
* Copyright © 2022 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Authors: David Woodhouse <dwmw2@infradead.org>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#ifndef QEMU_XEN_EVTCHN_H
#define QEMU_XEN_EVTCHN_H
#include "hw/sysbus.h"
typedef uint32_t evtchn_port_t;
void xen_evtchn_create(void);
int xen_evtchn_soft_reset(void);
int xen_evtchn_set_callback_param(uint64_t param);
void xen_evtchn_connect_gsis(qemu_irq *system_gsis);
void xen_evtchn_set_callback_level(int level);
int xen_evtchn_set_port(uint16_t port);
bool xen_evtchn_set_gsi(int gsi, int level);
void xen_evtchn_snoop_msi(PCIDevice *dev, bool is_msix, unsigned int vector,
uint64_t addr, uint32_t data, bool is_masked);
void xen_evtchn_remove_pci_device(PCIDevice *dev);
struct kvm_irq_routing_entry;
int xen_evtchn_translate_pirq_msi(struct kvm_irq_routing_entry *route,
uint64_t address, uint32_t data);
bool xen_evtchn_deliver_pirq_msi(uint64_t address, uint32_t data);
/*
* These functions mirror the libxenevtchn library API, providing the QEMU
* backend side of "interdomain" event channels.
*/
struct xenevtchn_handle;
struct xenevtchn_handle *xen_be_evtchn_open(void);
int xen_be_evtchn_bind_interdomain(struct xenevtchn_handle *xc, uint32_t domid,
evtchn_port_t guest_port);
int xen_be_evtchn_unbind(struct xenevtchn_handle *xc, evtchn_port_t port);
int xen_be_evtchn_close(struct xenevtchn_handle *xc);
int xen_be_evtchn_fd(struct xenevtchn_handle *xc);
int xen_be_evtchn_notify(struct xenevtchn_handle *xc, evtchn_port_t port);
int xen_be_evtchn_unmask(struct xenevtchn_handle *xc, evtchn_port_t port);
int xen_be_evtchn_pending(struct xenevtchn_handle *xc);
/* Apart from this which is a local addition */
int xen_be_evtchn_get_guest_port(struct xenevtchn_handle *xc);
struct evtchn_status;
struct evtchn_close;
struct evtchn_unmask;
struct evtchn_bind_virq;
struct evtchn_bind_pirq;
struct evtchn_bind_ipi;
struct evtchn_send;
struct evtchn_alloc_unbound;
struct evtchn_bind_interdomain;
struct evtchn_bind_vcpu;
struct evtchn_reset;
int xen_evtchn_status_op(struct evtchn_status *status);
int xen_evtchn_close_op(struct evtchn_close *close);
int xen_evtchn_unmask_op(struct evtchn_unmask *unmask);
int xen_evtchn_bind_virq_op(struct evtchn_bind_virq *virq);
int xen_evtchn_bind_pirq_op(struct evtchn_bind_pirq *pirq);
int xen_evtchn_bind_ipi_op(struct evtchn_bind_ipi *ipi);
int xen_evtchn_send_op(struct evtchn_send *send);
int xen_evtchn_alloc_unbound_op(struct evtchn_alloc_unbound *alloc);
int xen_evtchn_bind_interdomain_op(struct evtchn_bind_interdomain *interdomain);
int xen_evtchn_bind_vcpu_op(struct evtchn_bind_vcpu *vcpu);
int xen_evtchn_reset_op(struct evtchn_reset *reset);
struct physdev_map_pirq;
struct physdev_unmap_pirq;
struct physdev_eoi;
struct physdev_irq_status_query;
struct physdev_get_free_pirq;
int xen_physdev_map_pirq(struct physdev_map_pirq *map);
int xen_physdev_unmap_pirq(struct physdev_unmap_pirq *unmap);
int xen_physdev_eoi_pirq(struct physdev_eoi *eoi);
int xen_physdev_query_pirq(struct physdev_irq_status_query *query);
int xen_physdev_get_free_pirq(struct physdev_get_free_pirq *get);
#endif /* QEMU_XEN_EVTCHN_H */

232
hw/i386/kvm/xen_gnttab.c Normal file
View File

@ -0,0 +1,232 @@
/*
* QEMU Xen emulation: Grant table support
*
* Copyright © 2022 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Authors: David Woodhouse <dwmw2@infradead.org>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "qemu/host-utils.h"
#include "qemu/module.h"
#include "qemu/lockable.h"
#include "qemu/main-loop.h"
#include "qapi/error.h"
#include "qom/object.h"
#include "exec/target_page.h"
#include "exec/address-spaces.h"
#include "migration/vmstate.h"
#include "hw/sysbus.h"
#include "hw/xen/xen.h"
#include "xen_overlay.h"
#include "xen_gnttab.h"
#include "sysemu/kvm.h"
#include "sysemu/kvm_xen.h"
#include "hw/xen/interface/memory.h"
#include "hw/xen/interface/grant_table.h"
#define TYPE_XEN_GNTTAB "xen-gnttab"
OBJECT_DECLARE_SIMPLE_TYPE(XenGnttabState, XEN_GNTTAB)
#define XEN_PAGE_SHIFT 12
#define XEN_PAGE_SIZE (1ULL << XEN_PAGE_SHIFT)
#define ENTRIES_PER_FRAME_V1 (XEN_PAGE_SIZE / sizeof(grant_entry_v1_t))
struct XenGnttabState {
/*< private >*/
SysBusDevice busdev;
/*< public >*/
QemuMutex gnt_lock;
uint32_t nr_frames;
uint32_t max_frames;
union {
grant_entry_v1_t *v1;
/* Theoretically, v2 support could be added here. */
} entries;
MemoryRegion gnt_frames;
MemoryRegion *gnt_aliases;
uint64_t *gnt_frame_gpas;
};
struct XenGnttabState *xen_gnttab_singleton;
static void xen_gnttab_realize(DeviceState *dev, Error **errp)
{
XenGnttabState *s = XEN_GNTTAB(dev);
int i;
if (xen_mode != XEN_EMULATE) {
error_setg(errp, "Xen grant table support is for Xen emulation");
return;
}
s->nr_frames = 0;
s->max_frames = kvm_xen_get_gnttab_max_frames();
memory_region_init_ram(&s->gnt_frames, OBJECT(dev), "xen:grant_table",
XEN_PAGE_SIZE * s->max_frames, &error_abort);
memory_region_set_enabled(&s->gnt_frames, true);
s->entries.v1 = memory_region_get_ram_ptr(&s->gnt_frames);
memset(s->entries.v1, 0, XEN_PAGE_SIZE * s->max_frames);
/* Create individual page-sizes aliases for overlays */
s->gnt_aliases = (void *)g_new0(MemoryRegion, s->max_frames);
s->gnt_frame_gpas = (void *)g_new(uint64_t, s->max_frames);
for (i = 0; i < s->max_frames; i++) {
memory_region_init_alias(&s->gnt_aliases[i], OBJECT(dev),
NULL, &s->gnt_frames,
i * XEN_PAGE_SIZE, XEN_PAGE_SIZE);
s->gnt_frame_gpas[i] = INVALID_GPA;
}
qemu_mutex_init(&s->gnt_lock);
xen_gnttab_singleton = s;
}
static int xen_gnttab_post_load(void *opaque, int version_id)
{
XenGnttabState *s = XEN_GNTTAB(opaque);
uint32_t i;
for (i = 0; i < s->nr_frames; i++) {
if (s->gnt_frame_gpas[i] != INVALID_GPA) {
xen_overlay_do_map_page(&s->gnt_aliases[i], s->gnt_frame_gpas[i]);
}
}
return 0;
}
static bool xen_gnttab_is_needed(void *opaque)
{
return xen_mode == XEN_EMULATE;
}
static const VMStateDescription xen_gnttab_vmstate = {
.name = "xen_gnttab",
.version_id = 1,
.minimum_version_id = 1,
.needed = xen_gnttab_is_needed,
.post_load = xen_gnttab_post_load,
.fields = (VMStateField[]) {
VMSTATE_UINT32(nr_frames, XenGnttabState),
VMSTATE_VARRAY_UINT32(gnt_frame_gpas, XenGnttabState, nr_frames, 0,
vmstate_info_uint64, uint64_t),
VMSTATE_END_OF_LIST()
}
};
static void xen_gnttab_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
dc->realize = xen_gnttab_realize;
dc->vmsd = &xen_gnttab_vmstate;
}
static const TypeInfo xen_gnttab_info = {
.name = TYPE_XEN_GNTTAB,
.parent = TYPE_SYS_BUS_DEVICE,
.instance_size = sizeof(XenGnttabState),
.class_init = xen_gnttab_class_init,
};
void xen_gnttab_create(void)
{
xen_gnttab_singleton = XEN_GNTTAB(sysbus_create_simple(TYPE_XEN_GNTTAB,
-1, NULL));
}
static void xen_gnttab_register_types(void)
{
type_register_static(&xen_gnttab_info);
}
type_init(xen_gnttab_register_types)
int xen_gnttab_map_page(uint64_t idx, uint64_t gfn)
{
XenGnttabState *s = xen_gnttab_singleton;
uint64_t gpa = gfn << XEN_PAGE_SHIFT;
if (!s) {
return -ENOTSUP;
}
if (idx >= s->max_frames) {
return -EINVAL;
}
QEMU_IOTHREAD_LOCK_GUARD();
QEMU_LOCK_GUARD(&s->gnt_lock);
xen_overlay_do_map_page(&s->gnt_aliases[idx], gpa);
s->gnt_frame_gpas[idx] = gpa;
if (s->nr_frames <= idx) {
s->nr_frames = idx + 1;
}
return 0;
}
int xen_gnttab_set_version_op(struct gnttab_set_version *set)
{
int ret;
switch (set->version) {
case 1:
ret = 0;
break;
case 2:
/* Behave as before set_version was introduced. */
ret = -ENOSYS;
break;
default:
ret = -EINVAL;
}
set->version = 1;
return ret;
}
int xen_gnttab_get_version_op(struct gnttab_get_version *get)
{
if (get->dom != DOMID_SELF && get->dom != xen_domid) {
return -ESRCH;
}
get->version = 1;
return 0;
}
int xen_gnttab_query_size_op(struct gnttab_query_size *size)
{
XenGnttabState *s = xen_gnttab_singleton;
if (!s) {
return -ENOTSUP;
}
if (size->dom != DOMID_SELF && size->dom != xen_domid) {
size->status = GNTST_bad_domain;
return 0;
}
size->status = GNTST_okay;
size->nr_frames = s->nr_frames;
size->max_nr_frames = s->max_frames;
return 0;
}

25
hw/i386/kvm/xen_gnttab.h Normal file
View File

@ -0,0 +1,25 @@
/*
* QEMU Xen emulation: Grant table support
*
* Copyright © 2022 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Authors: David Woodhouse <dwmw2@infradead.org>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#ifndef QEMU_XEN_GNTTAB_H
#define QEMU_XEN_GNTTAB_H
void xen_gnttab_create(void);
int xen_gnttab_map_page(uint64_t idx, uint64_t gfn);
struct gnttab_set_version;
struct gnttab_get_version;
struct gnttab_query_size;
int xen_gnttab_set_version_op(struct gnttab_set_version *set);
int xen_gnttab_get_version_op(struct gnttab_get_version *get);
int xen_gnttab_query_size_op(struct gnttab_query_size *size);
#endif /* QEMU_XEN_GNTTAB_H */

272
hw/i386/kvm/xen_overlay.c Normal file
View File

@ -0,0 +1,272 @@
/*
* QEMU Xen emulation: Shared/overlay pages support
*
* Copyright © 2022 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Authors: David Woodhouse <dwmw2@infradead.org>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "qemu/host-utils.h"
#include "qemu/module.h"
#include "qemu/main-loop.h"
#include "qapi/error.h"
#include "qom/object.h"
#include "exec/target_page.h"
#include "exec/address-spaces.h"
#include "migration/vmstate.h"
#include "hw/sysbus.h"
#include "hw/xen/xen.h"
#include "xen_overlay.h"
#include "sysemu/kvm.h"
#include "sysemu/kvm_xen.h"
#include <linux/kvm.h>
#include "hw/xen/interface/memory.h"
#define TYPE_XEN_OVERLAY "xen-overlay"
OBJECT_DECLARE_SIMPLE_TYPE(XenOverlayState, XEN_OVERLAY)
#define XEN_PAGE_SHIFT 12
#define XEN_PAGE_SIZE (1ULL << XEN_PAGE_SHIFT)
struct XenOverlayState {
/*< private >*/
SysBusDevice busdev;
/*< public >*/
MemoryRegion shinfo_mem;
void *shinfo_ptr;
uint64_t shinfo_gpa;
bool long_mode;
};
struct XenOverlayState *xen_overlay_singleton;
void xen_overlay_do_map_page(MemoryRegion *page, uint64_t gpa)
{
/*
* Xen allows guests to map the same page as many times as it likes
* into guest physical frames. We don't, because it would be hard
* to track and restore them all. One mapping of each page is
* perfectly sufficient for all known guests... and we've tested
* that theory on a few now in other implementations. dwmw2.
*/
if (memory_region_is_mapped(page)) {
if (gpa == INVALID_GPA) {
memory_region_del_subregion(get_system_memory(), page);
} else {
/* Just move it */
memory_region_set_address(page, gpa);
}
} else if (gpa != INVALID_GPA) {
memory_region_add_subregion_overlap(get_system_memory(), gpa, page, 0);
}
}
/* KVM is the only existing back end for now. Let's not overengineer it yet. */
static int xen_overlay_set_be_shinfo(uint64_t gfn)
{
struct kvm_xen_hvm_attr xa = {
.type = KVM_XEN_ATTR_TYPE_SHARED_INFO,
.u.shared_info.gfn = gfn,
};
return kvm_vm_ioctl(kvm_state, KVM_XEN_HVM_SET_ATTR, &xa);
}
static void xen_overlay_realize(DeviceState *dev, Error **errp)
{
XenOverlayState *s = XEN_OVERLAY(dev);
if (xen_mode != XEN_EMULATE) {
error_setg(errp, "Xen overlay page support is for Xen emulation");
return;
}
memory_region_init_ram(&s->shinfo_mem, OBJECT(dev), "xen:shared_info",
XEN_PAGE_SIZE, &error_abort);
memory_region_set_enabled(&s->shinfo_mem, true);
s->shinfo_ptr = memory_region_get_ram_ptr(&s->shinfo_mem);
s->shinfo_gpa = INVALID_GPA;
s->long_mode = false;
memset(s->shinfo_ptr, 0, XEN_PAGE_SIZE);
}
static int xen_overlay_pre_save(void *opaque)
{
/*
* Fetch the kernel's idea of long_mode to avoid the race condition
* where the guest has set the hypercall page up in 64-bit mode but
* not yet made a hypercall by the time migration happens, so qemu
* hasn't yet noticed.
*/
return xen_sync_long_mode();
}
static int xen_overlay_post_load(void *opaque, int version_id)
{
XenOverlayState *s = opaque;
if (s->shinfo_gpa != INVALID_GPA) {
xen_overlay_do_map_page(&s->shinfo_mem, s->shinfo_gpa);
xen_overlay_set_be_shinfo(s->shinfo_gpa >> XEN_PAGE_SHIFT);
}
if (s->long_mode) {
xen_set_long_mode(true);
}
return 0;
}
static bool xen_overlay_is_needed(void *opaque)
{
return xen_mode == XEN_EMULATE;
}
static const VMStateDescription xen_overlay_vmstate = {
.name = "xen_overlay",
.version_id = 1,
.minimum_version_id = 1,
.needed = xen_overlay_is_needed,
.pre_save = xen_overlay_pre_save,
.post_load = xen_overlay_post_load,
.fields = (VMStateField[]) {
VMSTATE_UINT64(shinfo_gpa, XenOverlayState),
VMSTATE_BOOL(long_mode, XenOverlayState),
VMSTATE_END_OF_LIST()
}
};
static void xen_overlay_reset(DeviceState *dev)
{
kvm_xen_soft_reset();
}
static void xen_overlay_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
dc->reset = xen_overlay_reset;
dc->realize = xen_overlay_realize;
dc->vmsd = &xen_overlay_vmstate;
}
static const TypeInfo xen_overlay_info = {
.name = TYPE_XEN_OVERLAY,
.parent = TYPE_SYS_BUS_DEVICE,
.instance_size = sizeof(XenOverlayState),
.class_init = xen_overlay_class_init,
};
void xen_overlay_create(void)
{
xen_overlay_singleton = XEN_OVERLAY(sysbus_create_simple(TYPE_XEN_OVERLAY,
-1, NULL));
/* If xen_domid wasn't explicitly set, at least make sure it isn't zero. */
if (xen_domid == DOMID_QEMU) {
xen_domid = 1;
};
}
static void xen_overlay_register_types(void)
{
type_register_static(&xen_overlay_info);
}
type_init(xen_overlay_register_types)
int xen_overlay_map_shinfo_page(uint64_t gpa)
{
XenOverlayState *s = xen_overlay_singleton;
int ret;
if (!s) {
return -ENOENT;
}
assert(qemu_mutex_iothread_locked());
if (s->shinfo_gpa) {
/* If removing shinfo page, turn the kernel magic off first */
ret = xen_overlay_set_be_shinfo(INVALID_GFN);
if (ret) {
return ret;
}
}
xen_overlay_do_map_page(&s->shinfo_mem, gpa);
if (gpa != INVALID_GPA) {
ret = xen_overlay_set_be_shinfo(gpa >> XEN_PAGE_SHIFT);
if (ret) {
return ret;
}
}
s->shinfo_gpa = gpa;
return 0;
}
void *xen_overlay_get_shinfo_ptr(void)
{
XenOverlayState *s = xen_overlay_singleton;
if (!s) {
return NULL;
}
return s->shinfo_ptr;
}
int xen_sync_long_mode(void)
{
int ret;
struct kvm_xen_hvm_attr xa = {
.type = KVM_XEN_ATTR_TYPE_LONG_MODE,
};
if (!xen_overlay_singleton) {
return -ENOENT;
}
ret = kvm_vm_ioctl(kvm_state, KVM_XEN_HVM_GET_ATTR, &xa);
if (!ret) {
xen_overlay_singleton->long_mode = xa.u.long_mode;
}
return ret;
}
int xen_set_long_mode(bool long_mode)
{
int ret;
struct kvm_xen_hvm_attr xa = {
.type = KVM_XEN_ATTR_TYPE_LONG_MODE,
.u.long_mode = long_mode,
};
if (!xen_overlay_singleton) {
return -ENOENT;
}
ret = kvm_vm_ioctl(kvm_state, KVM_XEN_HVM_SET_ATTR, &xa);
if (!ret) {
xen_overlay_singleton->long_mode = xa.u.long_mode;
}
return ret;
}
bool xen_is_long_mode(void)
{
return xen_overlay_singleton && xen_overlay_singleton->long_mode;
}

26
hw/i386/kvm/xen_overlay.h Normal file
View File

@ -0,0 +1,26 @@
/*
* QEMU Xen emulation: Shared/overlay pages support
*
* Copyright © 2022 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Authors: David Woodhouse <dwmw2@infradead.org>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#ifndef QEMU_XEN_OVERLAY_H
#define QEMU_XEN_OVERLAY_H
void xen_overlay_create(void);
int xen_overlay_map_shinfo_page(uint64_t gpa);
void *xen_overlay_get_shinfo_ptr(void);
int xen_sync_long_mode(void);
int xen_set_long_mode(bool long_mode);
bool xen_is_long_mode(void);
void xen_overlay_do_map_page(MemoryRegion *page, uint64_t gpa);
#endif /* QEMU_XEN_OVERLAY_H */

500
hw/i386/kvm/xen_xenstore.c Normal file
View File

@ -0,0 +1,500 @@
/*
* QEMU Xen emulation: Shared/overlay pages support
*
* Copyright © 2022 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Authors: David Woodhouse <dwmw2@infradead.org>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#include "qemu/osdep.h"
#include "qemu/host-utils.h"
#include "qemu/module.h"
#include "qemu/main-loop.h"
#include "qemu/cutils.h"
#include "qapi/error.h"
#include "qom/object.h"
#include "migration/vmstate.h"
#include "hw/sysbus.h"
#include "hw/xen/xen.h"
#include "xen_overlay.h"
#include "xen_evtchn.h"
#include "xen_xenstore.h"
#include "sysemu/kvm.h"
#include "sysemu/kvm_xen.h"
#include "hw/xen/interface/io/xs_wire.h"
#include "hw/xen/interface/event_channel.h"
#define TYPE_XEN_XENSTORE "xen-xenstore"
OBJECT_DECLARE_SIMPLE_TYPE(XenXenstoreState, XEN_XENSTORE)
#define XEN_PAGE_SHIFT 12
#define XEN_PAGE_SIZE (1ULL << XEN_PAGE_SHIFT)
#define ENTRIES_PER_FRAME_V1 (XEN_PAGE_SIZE / sizeof(grant_entry_v1_t))
#define ENTRIES_PER_FRAME_V2 (XEN_PAGE_SIZE / sizeof(grant_entry_v2_t))
#define XENSTORE_HEADER_SIZE ((unsigned int)sizeof(struct xsd_sockmsg))
struct XenXenstoreState {
/*< private >*/
SysBusDevice busdev;
/*< public >*/
MemoryRegion xenstore_page;
struct xenstore_domain_interface *xs;
uint8_t req_data[XENSTORE_HEADER_SIZE + XENSTORE_PAYLOAD_MAX];
uint8_t rsp_data[XENSTORE_HEADER_SIZE + XENSTORE_PAYLOAD_MAX];
uint32_t req_offset;
uint32_t rsp_offset;
bool rsp_pending;
bool fatal_error;
evtchn_port_t guest_port;
evtchn_port_t be_port;
struct xenevtchn_handle *eh;
};
struct XenXenstoreState *xen_xenstore_singleton;
static void xen_xenstore_event(void *opaque);
static void xen_xenstore_realize(DeviceState *dev, Error **errp)
{
XenXenstoreState *s = XEN_XENSTORE(dev);
if (xen_mode != XEN_EMULATE) {
error_setg(errp, "Xen xenstore support is for Xen emulation");
return;
}
memory_region_init_ram(&s->xenstore_page, OBJECT(dev), "xen:xenstore_page",
XEN_PAGE_SIZE, &error_abort);
memory_region_set_enabled(&s->xenstore_page, true);
s->xs = memory_region_get_ram_ptr(&s->xenstore_page);
memset(s->xs, 0, XEN_PAGE_SIZE);
/* We can't map it this early as KVM isn't ready */
xen_xenstore_singleton = s;
s->eh = xen_be_evtchn_open();
if (!s->eh) {
error_setg(errp, "Xenstore evtchn port init failed");
return;
}
aio_set_fd_handler(qemu_get_aio_context(), xen_be_evtchn_fd(s->eh), true,
xen_xenstore_event, NULL, NULL, NULL, s);
}
static bool xen_xenstore_is_needed(void *opaque)
{
return xen_mode == XEN_EMULATE;
}
static int xen_xenstore_pre_save(void *opaque)
{
XenXenstoreState *s = opaque;
if (s->eh) {
s->guest_port = xen_be_evtchn_get_guest_port(s->eh);
}
return 0;
}
static int xen_xenstore_post_load(void *opaque, int ver)
{
XenXenstoreState *s = opaque;
/*
* As qemu/dom0, rebind to the guest's port. The Windows drivers may
* unbind the XenStore evtchn and rebind to it, having obtained the
* "remote" port through EVTCHNOP_status. In the case that migration
* occurs while it's unbound, the "remote" port needs to be the same
* as before so that the guest can find it, but should remain unbound.
*/
if (s->guest_port) {
int be_port = xen_be_evtchn_bind_interdomain(s->eh, xen_domid,
s->guest_port);
if (be_port < 0) {
return be_port;
}
s->be_port = be_port;
}
return 0;
}
static const VMStateDescription xen_xenstore_vmstate = {
.name = "xen_xenstore",
.version_id = 1,
.minimum_version_id = 1,
.needed = xen_xenstore_is_needed,
.pre_save = xen_xenstore_pre_save,
.post_load = xen_xenstore_post_load,
.fields = (VMStateField[]) {
VMSTATE_UINT8_ARRAY(req_data, XenXenstoreState,
sizeof_field(XenXenstoreState, req_data)),
VMSTATE_UINT8_ARRAY(rsp_data, XenXenstoreState,
sizeof_field(XenXenstoreState, rsp_data)),
VMSTATE_UINT32(req_offset, XenXenstoreState),
VMSTATE_UINT32(rsp_offset, XenXenstoreState),
VMSTATE_BOOL(rsp_pending, XenXenstoreState),
VMSTATE_UINT32(guest_port, XenXenstoreState),
VMSTATE_BOOL(fatal_error, XenXenstoreState),
VMSTATE_END_OF_LIST()
}
};
static void xen_xenstore_class_init(ObjectClass *klass, void *data)
{
DeviceClass *dc = DEVICE_CLASS(klass);
dc->realize = xen_xenstore_realize;
dc->vmsd = &xen_xenstore_vmstate;
}
static const TypeInfo xen_xenstore_info = {
.name = TYPE_XEN_XENSTORE,
.parent = TYPE_SYS_BUS_DEVICE,
.instance_size = sizeof(XenXenstoreState),
.class_init = xen_xenstore_class_init,
};
void xen_xenstore_create(void)
{
DeviceState *dev = sysbus_create_simple(TYPE_XEN_XENSTORE, -1, NULL);
xen_xenstore_singleton = XEN_XENSTORE(dev);
/*
* Defer the init (xen_xenstore_reset()) until KVM is set up and the
* overlay page can be mapped.
*/
}
static void xen_xenstore_register_types(void)
{
type_register_static(&xen_xenstore_info);
}
type_init(xen_xenstore_register_types)
uint16_t xen_xenstore_get_port(void)
{
XenXenstoreState *s = xen_xenstore_singleton;
if (!s) {
return 0;
}
return s->guest_port;
}
static bool req_pending(XenXenstoreState *s)
{
struct xsd_sockmsg *req = (struct xsd_sockmsg *)s->req_data;
return s->req_offset == XENSTORE_HEADER_SIZE + req->len;
}
static void reset_req(XenXenstoreState *s)
{
memset(s->req_data, 0, sizeof(s->req_data));
s->req_offset = 0;
}
static void reset_rsp(XenXenstoreState *s)
{
s->rsp_pending = false;
memset(s->rsp_data, 0, sizeof(s->rsp_data));
s->rsp_offset = 0;
}
static void process_req(XenXenstoreState *s)
{
struct xsd_sockmsg *req = (struct xsd_sockmsg *)s->req_data;
struct xsd_sockmsg *rsp = (struct xsd_sockmsg *)s->rsp_data;
const char enosys[] = "ENOSYS";
assert(req_pending(s));
assert(!s->rsp_pending);
rsp->type = XS_ERROR;
rsp->req_id = req->req_id;
rsp->tx_id = req->tx_id;
rsp->len = sizeof(enosys);
memcpy((void *)&rsp[1], enosys, sizeof(enosys));
s->rsp_pending = true;
reset_req(s);
}
static unsigned int copy_from_ring(XenXenstoreState *s, uint8_t *ptr,
unsigned int len)
{
if (!len) {
return 0;
}
XENSTORE_RING_IDX prod = qatomic_read(&s->xs->req_prod);
XENSTORE_RING_IDX cons = qatomic_read(&s->xs->req_cons);
unsigned int copied = 0;
/* Ensure the ring contents don't cross the req_prod access. */
smp_rmb();
while (len) {
unsigned int avail = prod - cons;
unsigned int offset = MASK_XENSTORE_IDX(cons);
unsigned int copylen = avail;
if (avail > XENSTORE_RING_SIZE) {
error_report("XenStore ring handling error");
s->fatal_error = true;
break;
} else if (avail == 0) {
break;
}
if (copylen > len) {
copylen = len;
}
if (copylen > XENSTORE_RING_SIZE - offset) {
copylen = XENSTORE_RING_SIZE - offset;
}
memcpy(ptr, &s->xs->req[offset], copylen);
copied += copylen;
ptr += copylen;
len -= copylen;
cons += copylen;
}
/*
* Not sure this ever mattered except on Alpha, but this barrier
* is to ensure that the update to req_cons is globally visible
* only after we have consumed all the data from the ring, and we
* don't end up seeing data written to the ring *after* the other
* end sees the update and writes more to the ring. Xen's own
* xenstored has the same barrier here (although with no comment
* at all, obviously, because it's Xen code).
*/
smp_mb();
qatomic_set(&s->xs->req_cons, cons);
return copied;
}
static unsigned int copy_to_ring(XenXenstoreState *s, uint8_t *ptr,
unsigned int len)
{
if (!len) {
return 0;
}
XENSTORE_RING_IDX cons = qatomic_read(&s->xs->rsp_cons);
XENSTORE_RING_IDX prod = qatomic_read(&s->xs->rsp_prod);
unsigned int copied = 0;
/*
* This matches the barrier in copy_to_ring() (or the guest's
* equivalent) betweem writing the data to the ring and updating
* rsp_prod. It protects against the pathological case (which
* again I think never happened except on Alpha) where our
* subsequent writes to the ring could *cross* the read of
* rsp_cons and the guest could see the new data when it was
* intending to read the old.
*/
smp_mb();
while (len) {
unsigned int avail = cons + XENSTORE_RING_SIZE - prod;
unsigned int offset = MASK_XENSTORE_IDX(prod);
unsigned int copylen = len;
if (avail > XENSTORE_RING_SIZE) {
error_report("XenStore ring handling error");
s->fatal_error = true;
break;
} else if (avail == 0) {
break;
}
if (copylen > avail) {
copylen = avail;
}
if (copylen > XENSTORE_RING_SIZE - offset) {
copylen = XENSTORE_RING_SIZE - offset;
}
memcpy(&s->xs->rsp[offset], ptr, copylen);
copied += copylen;
ptr += copylen;
len -= copylen;
prod += copylen;
}
/* Ensure the ring contents are seen before rsp_prod update. */
smp_wmb();
qatomic_set(&s->xs->rsp_prod, prod);
return copied;
}
static unsigned int get_req(XenXenstoreState *s)
{
unsigned int copied = 0;
if (s->fatal_error) {
return 0;
}
assert(!req_pending(s));
if (s->req_offset < XENSTORE_HEADER_SIZE) {
void *ptr = s->req_data + s->req_offset;
unsigned int len = XENSTORE_HEADER_SIZE;
unsigned int copylen = copy_from_ring(s, ptr, len);
copied += copylen;
s->req_offset += copylen;
}
if (s->req_offset >= XENSTORE_HEADER_SIZE) {
struct xsd_sockmsg *req = (struct xsd_sockmsg *)s->req_data;
if (req->len > (uint32_t)XENSTORE_PAYLOAD_MAX) {
error_report("Illegal XenStore request");
s->fatal_error = true;
return 0;
}
void *ptr = s->req_data + s->req_offset;
unsigned int len = XENSTORE_HEADER_SIZE + req->len - s->req_offset;
unsigned int copylen = copy_from_ring(s, ptr, len);
copied += copylen;
s->req_offset += copylen;
}
return copied;
}
static unsigned int put_rsp(XenXenstoreState *s)
{
if (s->fatal_error) {
return 0;
}
assert(s->rsp_pending);
struct xsd_sockmsg *rsp = (struct xsd_sockmsg *)s->rsp_data;
assert(s->rsp_offset < XENSTORE_HEADER_SIZE + rsp->len);
void *ptr = s->rsp_data + s->rsp_offset;
unsigned int len = XENSTORE_HEADER_SIZE + rsp->len - s->rsp_offset;
unsigned int copylen = copy_to_ring(s, ptr, len);
s->rsp_offset += copylen;
/* Have we produced a complete response? */
if (s->rsp_offset == XENSTORE_HEADER_SIZE + rsp->len) {
reset_rsp(s);
}
return copylen;
}
static void xen_xenstore_event(void *opaque)
{
XenXenstoreState *s = opaque;
evtchn_port_t port = xen_be_evtchn_pending(s->eh);
unsigned int copied_to, copied_from;
bool processed, notify = false;
if (port != s->be_port) {
return;
}
/* We know this is a no-op. */
xen_be_evtchn_unmask(s->eh, port);
do {
copied_to = copied_from = 0;
processed = false;
if (s->rsp_pending) {
copied_to = put_rsp(s);
}
if (!req_pending(s)) {
copied_from = get_req(s);
}
if (req_pending(s) && !s->rsp_pending) {
process_req(s);
processed = true;
}
notify |= copied_to || copied_from;
} while (copied_to || copied_from || processed);
if (notify) {
xen_be_evtchn_notify(s->eh, s->be_port);
}
}
static void alloc_guest_port(XenXenstoreState *s)
{
struct evtchn_alloc_unbound alloc = {
.dom = DOMID_SELF,
.remote_dom = DOMID_QEMU,
};
if (!xen_evtchn_alloc_unbound_op(&alloc)) {
s->guest_port = alloc.port;
}
}
int xen_xenstore_reset(void)
{
XenXenstoreState *s = xen_xenstore_singleton;
int err;
if (!s) {
return -ENOTSUP;
}
s->req_offset = s->rsp_offset = 0;
s->rsp_pending = false;
if (!memory_region_is_mapped(&s->xenstore_page)) {
uint64_t gpa = XEN_SPECIAL_PFN(XENSTORE) << TARGET_PAGE_BITS;
xen_overlay_do_map_page(&s->xenstore_page, gpa);
}
alloc_guest_port(s);
/*
* As qemu/dom0, bind to the guest's port. For incoming migration, this
* will be unbound as the guest's evtchn table is overwritten. We then
* rebind to the correct guest port in xen_xenstore_post_load().
*/
err = xen_be_evtchn_bind_interdomain(s->eh, xen_domid, s->guest_port);
if (err < 0) {
return err;
}
s->be_port = err;
return 0;
}

20
hw/i386/kvm/xen_xenstore.h Normal file
View File

@ -0,0 +1,20 @@
/*
* QEMU Xen emulation: Xenstore emulation
*
* Copyright © 2022 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* Authors: David Woodhouse <dwmw2@infradead.org>
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*/
#ifndef QEMU_XEN_XENSTORE_H
#define QEMU_XEN_XENSTORE_H
void xen_xenstore_create(void);
int xen_xenstore_reset(void);
uint16_t xen_xenstore_get_port(void);
#endif /* QEMU_XEN_XENSTORE_H */

26
hw/i386/pc.c
View File

@ -90,6 +90,10 @@
#include "hw/virtio/virtio-iommu.h"
#include "hw/virtio/virtio-pmem-pci.h"
#include "hw/virtio/virtio-mem-pci.h"
#include "hw/i386/kvm/xen_overlay.h"
#include "hw/i386/kvm/xen_evtchn.h"
#include "hw/i386/kvm/xen_gnttab.h"
#include "hw/i386/kvm/xen_xenstore.h"
#include "hw/mem/memory-device.h"
#include "sysemu/replay.h"
#include "target/i386/cpu.h"
@ -1308,6 +1312,15 @@ void pc_basic_device_init(struct PCMachineState *pcms,
}
*rtc_state = ISA_DEVICE(mc146818_rtc_init(isa_bus, 2000, rtc_irq));
#ifdef CONFIG_XEN_EMU
if (xen_mode == XEN_EMULATE) {
xen_evtchn_connect_gsis(gsi);
if (pcms->bus) {
pci_create_simple(pcms->bus, -1, "xen-platform");
}
}
#endif
qemu_register_boot_set(pc_boot_set, *rtc_state);
if (!xen_enabled() &&
@ -1846,6 +1859,19 @@ static void pc_machine_initfn(Object *obj)
cxl_machine_init(obj, &pcms->cxl_devices_state);
}
int pc_machine_kvm_type(MachineState *machine, const char *kvm_type)
{
#ifdef CONFIG_XEN_EMU
if (xen_mode == XEN_EMULATE) {
xen_overlay_create();
xen_evtchn_create();
xen_gnttab_create();
xen_xenstore_create();
}
#endif
return 0;
}
static void pc_machine_reset(MachineState *machine, ShutdownCause reason)
{
CPUState *cs;

16
hw/i386/x86.c
View File

@ -61,6 +61,11 @@
#include CONFIG_DEVICES
#include "kvm/kvm_i386.h"
#ifdef CONFIG_XEN_EMU
#include "hw/xen/xen.h"
#include "hw/i386/kvm/xen_evtchn.h"
#endif
/* Physical Address of PVH entry point read from kernel ELF NOTE */
static size_t pvh_start_addr;
@ -610,6 +615,17 @@ void gsi_handler(void *opaque, int n, int level)
}
/* fall through */
case ISA_NUM_IRQS ... IOAPIC_NUM_PINS - 1:
#ifdef CONFIG_XEN_EMU
/*
* Xen delivers the GSI to the Legacy PIC (not that Legacy PIC
* routing actually works properly under Xen). And then to
* *either* the PIRQ handling or the I/OAPIC depending on
* whether the former wants it.
*/
if (xen_mode == XEN_EMULATE && xen_evtchn_set_gsi(n, level)) {
break;
}
#endif
qemu_set_irq(s->ioapic_irq[n], level);
break;
case IO_APIC_SECONDARY_IRQBASE

5
hw/i386/xen/meson.build
View File

@ -2,6 +2,9 @@ i386_ss.add(when: 'CONFIG_XEN', if_true: files(
'xen-hvm.c',
'xen-mapcache.c',
'xen_apic.c',
'xen_platform.c',
'xen_pvdevice.c',
))
i386_ss.add(when: 'CONFIG_XEN_BUS', if_true: files(
'xen_platform.c',
))

8
hw/i386/xen/xen-hvm.c
View File

@ -1502,13 +1502,7 @@ void xen_hvm_init_pc(PCMachineState *pcms, MemoryRegion **ram_memory)
device_listener_register(&state->device_listener);
xen_bus_init();
/* Initialize backend core & drivers */
if (xen_be_init() != 0) {
error_report("xen backend core setup failed");
goto err;
}
xen_be_register_common();
xen_be_init();
QLIST_INIT(&xen_physmap);
xen_read_physmap(state);

57
hw/i386/xen/xen_platform.c
View File

@ -27,9 +27,9 @@
#include "qapi/error.h"
#include "hw/ide/pci.h"
#include "hw/pci/pci.h"
#include "hw/xen/xen_common.h"
#include "migration/vmstate.h"
#include "hw/xen/xen-legacy-backend.h"
#include "hw/xen/xen.h"
#include "net/net.h"
#include "trace.h"
#include "sysemu/xen.h"
#include "sysemu/block-backend.h"
@ -37,6 +37,11 @@
#include "qemu/module.h"
#include "qom/object.h"
#ifdef CONFIG_XEN
#include "hw/xen/xen_common.h"
#include "hw/xen/xen-legacy-backend.h"
#endif
//#define DEBUG_PLATFORM
#ifdef DEBUG_PLATFORM
@ -108,12 +113,25 @@ static void log_writeb(PCIXenPlatformState *s, char val)
#define _UNPLUG_NVME_DISKS 3
#define UNPLUG_NVME_DISKS (1u << _UNPLUG_NVME_DISKS)
static bool pci_device_is_passthrough(PCIDevice *d)
{
if (!strcmp(d->name, "xen-pci-passthrough")) {
return true;
}
if (xen_mode == XEN_EMULATE && !strcmp(d->name, "vfio-pci")) {
return true;
}
return false;
}
static void unplug_nic(PCIBus *b, PCIDevice *d, void *o)
{
/* We have to ignore passthrough devices */
if (pci_get_word(d->config + PCI_CLASS_DEVICE) ==
PCI_CLASS_NETWORK_ETHERNET
&& strcmp(d->name, "xen-pci-passthrough") != 0) {
&& !pci_device_is_passthrough(d)) {
object_unparent(OBJECT(d));
}
}
@ -186,9 +204,8 @@ static void unplug_disks(PCIBus *b, PCIDevice *d, void *opaque)
!(flags & UNPLUG_IDE_SCSI_DISKS);
/* We have to ignore passthrough devices */
if (!strcmp(d->name, "xen-pci-passthrough")) {
if (pci_device_is_passthrough(d))
return;
}
switch (pci_get_word(d->config + PCI_CLASS_DEVICE)) {
case PCI_CLASS_STORAGE_IDE:
@ -267,18 +284,26 @@ static void platform_fixed_ioport_writeb(void *opaque, uint32_t addr, uint32_t v
PCIXenPlatformState *s = opaque;
switch (addr) {
case 0: /* Platform flags */ {
hvmmem_type_t mem_type = (val & PFFLAG_ROM_LOCK) ?
HVMMEM_ram_ro : HVMMEM_ram_rw;
if (xen_set_mem_type(xen_domid, mem_type, 0xc0, 0x40)) {
DPRINTF("unable to change ro/rw state of ROM memory area!\n");
} else {
case 0: /* Platform flags */
if (xen_mode == XEN_EMULATE) {
/* XX: Use i440gx/q35 PAM setup to do this? */
s->flags = val & PFFLAG_ROM_LOCK;
DPRINTF("changed ro/rw state of ROM memory area. now is %s state.\n",
(mem_type == HVMMEM_ram_ro ? "ro":"rw"));
#ifdef CONFIG_XEN
} else {
hvmmem_type_t mem_type = (val & PFFLAG_ROM_LOCK) ?
HVMMEM_ram_ro : HVMMEM_ram_rw;
if (xen_set_mem_type(xen_domid, mem_type, 0xc0, 0x40)) {
DPRINTF("unable to change ro/rw state of ROM memory area!\n");
} else {
s->flags = val & PFFLAG_ROM_LOCK;
DPRINTF("changed ro/rw state of ROM memory area. now is %s state.\n",
(mem_type == HVMMEM_ram_ro ? "ro" : "rw"));
}
#endif
}
break;
}
case 2:
log_writeb(s, val);
break;
@ -496,8 +521,8 @@ static void xen_platform_realize(PCIDevice *dev, Error **errp)
uint8_t *pci_conf;
/* Device will crash on reset if xen is not initialized */
if (!xen_enabled()) {
error_setg(errp, "xen-platform device requires the Xen accelerator");
if (xen_mode == XEN_DISABLED) {
error_setg(errp, "xen-platform device requires a Xen guest");
return;
}

11
hw/pci/msi.c
View File

@ -24,6 +24,8 @@
#include "qemu/range.h"
#include "qapi/error.h"
#include "hw/i386/kvm/xen_evtchn.h"
/* PCI_MSI_ADDRESS_LO */
#define PCI_MSI_ADDRESS_LO_MASK (~0x3)
@ -414,6 +416,15 @@ void msi_write_config(PCIDevice *dev, uint32_t addr, uint32_t val, int len)
fprintf(stderr, "\n");
#endif
if (xen_mode == XEN_EMULATE) {
for (vector = 0; vector < msi_nr_vectors(flags); vector++) {
MSIMessage msg = msi_prepare_message(dev, vector);
xen_evtchn_snoop_msi(dev, false, vector, msg.address, msg.data,
msi_is_masked(dev, vector));
}
}
if (!(flags & PCI_MSI_FLAGS_ENABLE)) {
return;
}

9
hw/pci/msix.c
View File

@ -26,6 +26,8 @@
#include "qapi/error.h"
#include "trace.h"
#include "hw/i386/kvm/xen_evtchn.h"
/* MSI enable bit and maskall bit are in byte 1 in FLAGS register */
#define MSIX_CONTROL_OFFSET (PCI_MSIX_FLAGS + 1)
#define MSIX_ENABLE_MASK (PCI_MSIX_FLAGS_ENABLE >> 8)
@ -124,6 +126,13 @@ static void msix_handle_mask_update(PCIDevice *dev, int vector, bool was_masked)
{
bool is_masked = msix_is_masked(dev, vector);
if (xen_mode == XEN_EMULATE) {
MSIMessage msg = msix_prepare_message(dev, vector);
xen_evtchn_snoop_msi(dev, true, vector, msg.address, msg.data,
is_masked);
}
if (is_masked == was_masked) {
return;
}

17
hw/pci/pci.c
View File

@ -49,6 +49,9 @@
#include "qemu/cutils.h"
#include "pci-internal.h"
#include "hw/xen/xen.h"
#include "hw/i386/kvm/xen_evtchn.h"
//#define DEBUG_PCI
#ifdef DEBUG_PCI
# define PCI_DPRINTF(format, ...) printf(format, ## __VA_ARGS__)
@ -319,6 +322,17 @@ static void pci_msi_trigger(PCIDevice *dev, MSIMessage msg)
{
MemTxAttrs attrs = {};
/*
* Xen uses the high bits of the address to contain some of the bits
* of the PIRQ#. Therefore we can't just send the write cycle and
* trust that it's caught by the APIC at 0xfee00000 because the
* target of the write might be e.g. 0x0x1000fee46000 for PIRQ#4166.
* So we intercept the delivery here instead of in kvm_send_msi().
*/
if (xen_mode == XEN_EMULATE &&
xen_evtchn_deliver_pirq_msi(msg.address, msg.data)) {
return;
}
attrs.requester_id = pci_requester_id(dev);
address_space_stl_le(&dev->bus_master_as, msg.address, msg.data,
attrs, NULL);
@ -988,6 +1002,9 @@ static void do_pci_unregister_device(PCIDevice *pci_dev)
pci_get_bus(pci_dev)->devices[pci_dev->devfn] = NULL;
pci_config_free(pci_dev);
if (xen_mode == XEN_EMULATE) {
xen_evtchn_remove_pci_device(pci_dev);
}
if (memory_region_is_mapped(&pci_dev->bus_master_enable_region)) {
memory_region_del_subregion(&pci_dev->bus_master_container_region,
&pci_dev->bus_master_enable_region);

3
hw/xen/Kconfig Normal file
View File

@ -0,0 +1,3 @@
config XEN_BUS
bool
default y if (XEN || XEN_EMU)

56
hw/xen/xen-legacy-backend.c
View File

@ -676,21 +676,30 @@ void xenstore_update_fe(char *watch, struct XenLegacyDevice *xendev)
}
/* -------------------------------------------------------------------- */
int xen_be_init(void)
static void xen_set_dynamic_sysbus(void)
{
Object *machine = qdev_get_machine();
ObjectClass *oc = object_get_class(machine);
MachineClass *mc = MACHINE_CLASS(oc);
machine_class_allow_dynamic_sysbus_dev(mc, TYPE_XENSYSDEV);
}
void xen_be_init(void)
{
xengnttab_handle *gnttabdev;
xenstore = xs_daemon_open();
if (!xenstore) {
xen_pv_printf(NULL, 0, "can't connect to xenstored\n");
return -1;
exit(1);
}
qemu_set_fd_handler(xs_fileno(xenstore), xenstore_update, NULL, NULL);
if (xen_xc == NULL || xen_fmem == NULL) {
/* Check if xen_init() have been called */
goto err;
xen_pv_printf(NULL, 0, "Xen operations not set up\n");
exit(1);
}
gnttabdev = xengnttab_open(NULL, 0);
@ -706,23 +715,16 @@ int xen_be_init(void)
xen_sysbus = qbus_new(TYPE_XENSYSBUS, xen_sysdev, "xen-sysbus");
qbus_set_bus_hotplug_handler(xen_sysbus);
return 0;
xen_set_dynamic_sysbus();
err:
qemu_set_fd_handler(xs_fileno(xenstore), NULL, NULL, NULL);
xs_daemon_close(xenstore);
xenstore = NULL;
return -1;
}
static void xen_set_dynamic_sysbus(void)
{
Object *machine = qdev_get_machine();
ObjectClass *oc = object_get_class(machine);
MachineClass *mc = MACHINE_CLASS(oc);
machine_class_allow_dynamic_sysbus_dev(mc, TYPE_XENSYSDEV);
xen_be_register("console", &xen_console_ops);
xen_be_register("vkbd", &xen_kbdmouse_ops);
#ifdef CONFIG_VIRTFS
xen_be_register("9pfs", &xen_9pfs_ops);
#endif
#ifdef CONFIG_USB_LIBUSB
xen_be_register("qusb", &xen_usb_ops);
#endif
}
int xen_be_register(const char *type, struct XenDevOps *ops)
@ -744,20 +746,6 @@ int xen_be_register(const char *type, struct XenDevOps *ops)
return xenstore_scan(type, xen_domid, ops);
}
void xen_be_register_common(void)
{
xen_set_dynamic_sysbus();
xen_be_register("console", &xen_console_ops);
xen_be_register("vkbd", &xen_kbdmouse_ops);
#ifdef CONFIG_VIRTFS
xen_be_register("9pfs", &xen_9pfs_ops);
#endif
#ifdef CONFIG_USB_LIBUSB
xen_be_register("qusb", &xen_usb_ops);
#endif
}
int xen_be_bind_evtchn(struct XenLegacyDevice *xendev)
{
if (xendev->local_port != -1) {

6
hw/xenpv/xen_machine_pv.c
View File

@ -36,10 +36,7 @@ static void xen_init_pv(MachineState *machine)
int i;
/* Initialize backend core & drivers */
if (xen_be_init() != 0) {
error_report("%s: xen backend core setup failed", __func__);
exit(1);
}
xen_be_init();
switch (xen_mode) {
case XEN_ATTACH:
@ -55,7 +52,6 @@ static void xen_init_pv(MachineState *machine)
break;
}
xen_be_register_common();
xen_be_register("vfb", &xen_framebuffer_ops);
xen_be_register("qnic", &xen_netdev_ops);

3
include/hw/i386/pc.h
View File

@ -291,12 +291,15 @@ extern const size_t pc_compat_1_5_len;
extern GlobalProperty pc_compat_1_4[];
extern const size_t pc_compat_1_4_len;
int pc_machine_kvm_type(MachineState *machine, const char *vm_type);
#define DEFINE_PC_MACHINE(suffix, namestr, initfn, optsfn) \
static void pc_machine_##suffix##_class_init(ObjectClass *oc, void *data) \
{ \
MachineClass *mc = MACHINE_CLASS(oc); \
optsfn(mc); \
mc->init = initfn; \
mc->kvm_type = pc_machine_kvm_type; \
} \
static const TypeInfo pc_machine_type_##suffix = { \
.name = namestr TYPE_MACHINE_SUFFIX, \

1
include/hw/pci/msi.h
View File

@ -33,6 +33,7 @@ extern bool msi_nonbroken;
void msi_set_message(PCIDevice *dev, MSIMessage msg);
MSIMessage msi_get_message(PCIDevice *dev, unsigned int vector);
bool msi_enabled(const PCIDevice *dev);
void msi_set_enabled(PCIDevice *dev);
int msi_init(struct PCIDevice *dev, uint8_t offset,
unsigned int nr_vectors, bool msi64bit,
bool msi_per_vector_mask, Error **errp);

510
include/hw/xen/interface/arch-arm.h Normal file
View File

@ -0,0 +1,510 @@
/******************************************************************************
* arch-arm.h
*
* Guest OS interface to ARM Xen.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright 2011 (C) Citrix Systems
*/
#ifndef __XEN_PUBLIC_ARCH_ARM_H__
#define __XEN_PUBLIC_ARCH_ARM_H__
/*
* `incontents 50 arm_abi Hypercall Calling Convention
*
* A hypercall is issued using the ARM HVC instruction.
*
* A hypercall can take up to 5 arguments. These are passed in
* registers, the first argument in x0/r0 (for arm64/arm32 guests
* respectively irrespective of whether the underlying hypervisor is
* 32- or 64-bit), the second argument in x1/r1, the third in x2/r2,
* the forth in x3/r3 and the fifth in x4/r4.
*
* The hypercall number is passed in r12 (arm) or x16 (arm64). In both
* cases the relevant ARM procedure calling convention specifies this
* is an inter-procedure-call scratch register (e.g. for use in linker
* stubs). This use does not conflict with use during a hypercall.
*
* The HVC ISS must contain a Xen specific TAG: XEN_HYPERCALL_TAG.
*
* The return value is in x0/r0.
*
* The hypercall will clobber x16/r12 and the argument registers used
* by that hypercall (except r0 which is the return value) i.e. in
* addition to x16/r12 a 2 argument hypercall will clobber x1/r1 and a
* 4 argument hypercall will clobber x1/r1, x2/r2 and x3/r3.
*
* Parameter structs passed to hypercalls are laid out according to
* the Procedure Call Standard for the ARM Architecture (AAPCS, AKA
* EABI) and Procedure Call Standard for the ARM 64-bit Architecture
* (AAPCS64). Where there is a conflict the 64-bit standard should be
* used regardless of guest type. Structures which are passed as
* hypercall arguments are always little endian.
*
* All memory which is shared with other entities in the system
* (including the hypervisor and other guests) must reside in memory
* which is mapped as Normal Inner Write-Back Outer Write-Back Inner-Shareable.
* This applies to:
* - hypercall arguments passed via a pointer to guest memory.
* - memory shared via the grant table mechanism (including PV I/O
* rings etc).
* - memory shared with the hypervisor (struct shared_info, struct
* vcpu_info, the grant table, etc).
*
* Any cache allocation hints are acceptable.
*/
/*
* `incontents 55 arm_hcall Supported Hypercalls
*
* Xen on ARM makes extensive use of hardware facilities and therefore
* only a subset of the potential hypercalls are required.
*
* Since ARM uses second stage paging any machine/physical addresses
* passed to hypercalls are Guest Physical Addresses (Intermediate
* Physical Addresses) unless otherwise noted.
*
* The following hypercalls (and sub operations) are supported on the
* ARM platform. Other hypercalls should be considered
* unavailable/unsupported.
*
* HYPERVISOR_memory_op
* All generic sub-operations
*
* HYPERVISOR_domctl
* All generic sub-operations, with the exception of:
* * XEN_DOMCTL_irq_permission (not yet implemented)
*
* HYPERVISOR_sched_op
* All generic sub-operations, with the exception of:
* * SCHEDOP_block -- prefer wfi hardware instruction
*
* HYPERVISOR_console_io
* All generic sub-operations
*
* HYPERVISOR_xen_version
* All generic sub-operations
*
* HYPERVISOR_event_channel_op
* All generic sub-operations
*
* HYPERVISOR_physdev_op
* Exactly these sub-operations are supported:
* PHYSDEVOP_pci_device_add
* PHYSDEVOP_pci_device_remove
*
* HYPERVISOR_sysctl
* All generic sub-operations, with the exception of:
* * XEN_SYSCTL_page_offline_op
* * XEN_SYSCTL_get_pmstat
* * XEN_SYSCTL_pm_op
*
* HYPERVISOR_hvm_op
* Exactly these sub-operations are supported:
* * HVMOP_set_param
* * HVMOP_get_param
*
* HYPERVISOR_grant_table_op
* All generic sub-operations
*
* HYPERVISOR_vcpu_op
* Exactly these sub-operations are supported:
* * VCPUOP_register_vcpu_info
* * VCPUOP_register_runstate_memory_area
*
* HYPERVISOR_argo_op
* All generic sub-operations
*
* Other notes on the ARM ABI:
*
* - struct start_info is not exported to ARM guests.
*
* - struct shared_info is mapped by ARM guests using the
* HYPERVISOR_memory_op sub-op XENMEM_add_to_physmap, passing
* XENMAPSPACE_shared_info as space parameter.
*
* - All the per-cpu struct vcpu_info are mapped by ARM guests using the
* HYPERVISOR_vcpu_op sub-op VCPUOP_register_vcpu_info, including cpu0
* struct vcpu_info.
*
* - The grant table is mapped using the HYPERVISOR_memory_op sub-op
* XENMEM_add_to_physmap, passing XENMAPSPACE_grant_table as space
* parameter. The memory range specified under the Xen compatible
* hypervisor node on device tree can be used as target gpfn for the
* mapping.
*
* - Xenstore is initialized by using the two hvm_params
* HVM_PARAM_STORE_PFN and HVM_PARAM_STORE_EVTCHN. They can be read
* with the HYPERVISOR_hvm_op sub-op HVMOP_get_param.
*
* - The paravirtualized console is initialized by using the two
* hvm_params HVM_PARAM_CONSOLE_PFN and HVM_PARAM_CONSOLE_EVTCHN. They
* can be read with the HYPERVISOR_hvm_op sub-op HVMOP_get_param.
*
* - Event channel notifications are delivered using the percpu GIC
* interrupt specified under the Xen compatible hypervisor node on
* device tree.
*
* - The device tree Xen compatible node is fully described under Linux
* at Documentation/devicetree/bindings/arm/xen.txt.
*/
#define XEN_HYPERCALL_TAG 0XEA1
#define int64_aligned_t int64_t __attribute__((aligned(8)))
#define uint64_aligned_t uint64_t __attribute__((aligned(8)))
#ifndef __ASSEMBLY__
#define ___DEFINE_XEN_GUEST_HANDLE(name, type) \
typedef union { type *p; unsigned long q; } \
__guest_handle_ ## name; \
typedef union { type *p; uint64_aligned_t q; } \
__guest_handle_64_ ## name
/*
* XEN_GUEST_HANDLE represents a guest pointer, when passed as a field
* in a struct in memory. On ARM is always 8 bytes sizes and 8 bytes
* aligned.
* XEN_GUEST_HANDLE_PARAM represents a guest pointer, when passed as an
* hypercall argument. It is 4 bytes on aarch32 and 8 bytes on aarch64.
*/
#define __DEFINE_XEN_GUEST_HANDLE(name, type) \
___DEFINE_XEN_GUEST_HANDLE(name, type); \
___DEFINE_XEN_GUEST_HANDLE(const_##name, const type)
#define DEFINE_XEN_GUEST_HANDLE(name) __DEFINE_XEN_GUEST_HANDLE(name, name)
#define __XEN_GUEST_HANDLE(name) __guest_handle_64_ ## name
#define XEN_GUEST_HANDLE(name) __XEN_GUEST_HANDLE(name)
#define XEN_GUEST_HANDLE_PARAM(name) __guest_handle_ ## name
#define set_xen_guest_handle_raw(hnd, val) \
do { \
__typeof__(&(hnd)) _sxghr_tmp = &(hnd); \
_sxghr_tmp->q = 0; \
_sxghr_tmp->p = val; \
} while ( 0 )
#define set_xen_guest_handle(hnd, val) set_xen_guest_handle_raw(hnd, val)
typedef uint64_t xen_pfn_t;
#define PRI_xen_pfn PRIx64
#define PRIu_xen_pfn PRIu64
/*
* Maximum number of virtual CPUs in legacy multi-processor guests.
* Only one. All other VCPUS must use VCPUOP_register_vcpu_info.
*/
#define XEN_LEGACY_MAX_VCPUS 1
typedef uint64_t xen_ulong_t;
#define PRI_xen_ulong PRIx64
#if defined(__XEN__) || defined(__XEN_TOOLS__)
#if defined(__GNUC__) && !defined(__STRICT_ANSI__)
/* Anonymous union includes both 32- and 64-bit names (e.g., r0/x0). */
# define __DECL_REG(n64, n32) union { \
uint64_t n64; \
uint32_t n32; \
}
#else
/* Non-gcc sources must always use the proper 64-bit name (e.g., x0). */
#define __DECL_REG(n64, n32) uint64_t n64
#endif
struct vcpu_guest_core_regs
{
/* Aarch64 Aarch32 */
__DECL_REG(x0, r0_usr);
__DECL_REG(x1, r1_usr);
__DECL_REG(x2, r2_usr);
__DECL_REG(x3, r3_usr);
__DECL_REG(x4, r4_usr);
__DECL_REG(x5, r5_usr);
__DECL_REG(x6, r6_usr);
__DECL_REG(x7, r7_usr);
__DECL_REG(x8, r8_usr);
__DECL_REG(x9, r9_usr);
__DECL_REG(x10, r10_usr);
__DECL_REG(x11, r11_usr);
__DECL_REG(x12, r12_usr);
__DECL_REG(x13, sp_usr);
__DECL_REG(x14, lr_usr);
__DECL_REG(x15, __unused_sp_hyp);
__DECL_REG(x16, lr_irq);
__DECL_REG(x17, sp_irq);
__DECL_REG(x18, lr_svc);
__DECL_REG(x19, sp_svc);
__DECL_REG(x20, lr_abt);
__DECL_REG(x21, sp_abt);
__DECL_REG(x22, lr_und);
__DECL_REG(x23, sp_und);
__DECL_REG(x24, r8_fiq);
__DECL_REG(x25, r9_fiq);
__DECL_REG(x26, r10_fiq);
__DECL_REG(x27, r11_fiq);
__DECL_REG(x28, r12_fiq);
__DECL_REG(x29, sp_fiq);
__DECL_REG(x30, lr_fiq);
/* Return address and mode */
__DECL_REG(pc64, pc32); /* ELR_EL2 */
uint64_t cpsr; /* SPSR_EL2 */
union {
uint64_t spsr_el1; /* AArch64 */
uint32_t spsr_svc; /* AArch32 */
};
/* AArch32 guests only */
uint32_t spsr_fiq, spsr_irq, spsr_und, spsr_abt;
/* AArch64 guests only */
uint64_t sp_el0;
uint64_t sp_el1, elr_el1;
};
typedef struct vcpu_guest_core_regs vcpu_guest_core_regs_t;
DEFINE_XEN_GUEST_HANDLE(vcpu_guest_core_regs_t);
#undef __DECL_REG
struct vcpu_guest_context {
#define _VGCF_online 0
#define VGCF_online (1<<_VGCF_online)
uint32_t flags; /* VGCF_* */
struct vcpu_guest_core_regs user_regs; /* Core CPU registers */
uint64_t sctlr;
uint64_t ttbcr, ttbr0, ttbr1;
};
typedef struct vcpu_guest_context vcpu_guest_context_t;
DEFINE_XEN_GUEST_HANDLE(vcpu_guest_context_t);
/*
* struct xen_arch_domainconfig's ABI is covered by
* XEN_DOMCTL_INTERFACE_VERSION.
*/
#define XEN_DOMCTL_CONFIG_GIC_NATIVE 0
#define XEN_DOMCTL_CONFIG_GIC_V2 1
#define XEN_DOMCTL_CONFIG_GIC_V3 2
#define XEN_DOMCTL_CONFIG_TEE_NONE 0
#define XEN_DOMCTL_CONFIG_TEE_OPTEE 1
struct xen_arch_domainconfig {
/* IN/OUT */
uint8_t gic_version;
/* IN */
uint16_t tee_type;
/* IN */
uint32_t nr_spis;
/*
* OUT
* Based on the property clock-frequency in the DT timer node.
* The property may be present when the bootloader/firmware doesn't
* set correctly CNTFRQ which hold the timer frequency.
*
* As it's not possible to trap this register, we have to replicate
* the value in the guest DT.
*
* = 0 => property not present
* > 0 => Value of the property
*
*/
uint32_t clock_frequency;
};
#endif /* __XEN__ || __XEN_TOOLS__ */
struct arch_vcpu_info {
};
typedef struct arch_vcpu_info arch_vcpu_info_t;
struct arch_shared_info {
};
typedef struct arch_shared_info arch_shared_info_t;
typedef uint64_t xen_callback_t;
#endif
#if defined(__XEN__) || defined(__XEN_TOOLS__)
/* PSR bits (CPSR, SPSR) */
#define PSR_THUMB (1<<5) /* Thumb Mode enable */
#define PSR_FIQ_MASK (1<<6) /* Fast Interrupt mask */
#define PSR_IRQ_MASK (1<<7) /* Interrupt mask */
#define PSR_ABT_MASK (1<<8) /* Asynchronous Abort mask */
#define PSR_BIG_ENDIAN (1<<9) /* arm32: Big Endian Mode */
#define PSR_DBG_MASK (1<<9) /* arm64: Debug Exception mask */
#define PSR_IT_MASK (0x0600fc00) /* Thumb If-Then Mask */
#define PSR_JAZELLE (1<<24) /* Jazelle Mode */
/* 32 bit modes */
#define PSR_MODE_USR 0x10
#define PSR_MODE_FIQ 0x11
#define PSR_MODE_IRQ 0x12
#define PSR_MODE_SVC 0x13
#define PSR_MODE_MON 0x16
#define PSR_MODE_ABT 0x17
#define PSR_MODE_HYP 0x1a
#define PSR_MODE_UND 0x1b
#define PSR_MODE_SYS 0x1f
/* 64 bit modes */
#define PSR_MODE_BIT 0x10 /* Set iff AArch32 */
#define PSR_MODE_EL3h 0x0d
#define PSR_MODE_EL3t 0x0c
#define PSR_MODE_EL2h 0x09
#define PSR_MODE_EL2t 0x08
#define PSR_MODE_EL1h 0x05
#define PSR_MODE_EL1t 0x04
#define PSR_MODE_EL0t 0x00
#define PSR_GUEST32_INIT (PSR_ABT_MASK|PSR_FIQ_MASK|PSR_IRQ_MASK|PSR_MODE_SVC)
#define PSR_GUEST64_INIT (PSR_ABT_MASK|PSR_FIQ_MASK|PSR_IRQ_MASK|PSR_MODE_EL1h)
#define SCTLR_GUEST_INIT xen_mk_ullong(0x00c50078)
/*
* Virtual machine platform (memory layout, interrupts)
*
* These are defined for consistency between the tools and the
* hypervisor. Guests must not rely on these hardcoded values but
* should instead use the FDT.
*/
/* Physical Address Space */
/*
* vGIC mappings: Only one set of mapping is used by the guest.
* Therefore they can overlap.
*/
/* vGIC v2 mappings */
#define GUEST_GICD_BASE xen_mk_ullong(0x03001000)
#define GUEST_GICD_SIZE xen_mk_ullong(0x00001000)
#define GUEST_GICC_BASE xen_mk_ullong(0x03002000)
#define GUEST_GICC_SIZE xen_mk_ullong(0x00002000)
/* vGIC v3 mappings */
#define GUEST_GICV3_GICD_BASE xen_mk_ullong(0x03001000)
#define GUEST_GICV3_GICD_SIZE xen_mk_ullong(0x00010000)
#define GUEST_GICV3_RDIST_REGIONS 1
#define GUEST_GICV3_GICR0_BASE xen_mk_ullong(0x03020000) /* vCPU0..127 */
#define GUEST_GICV3_GICR0_SIZE xen_mk_ullong(0x01000000)
/*
* 256 MB is reserved for VPCI configuration space based on calculation
* 256 buses x 32 devices x 8 functions x 4 KB = 256 MB
*/
#define GUEST_VPCI_ECAM_BASE xen_mk_ullong(0x10000000)
#define GUEST_VPCI_ECAM_SIZE xen_mk_ullong(0x10000000)
/* ACPI tables physical address */
#define GUEST_ACPI_BASE xen_mk_ullong(0x20000000)
#define GUEST_ACPI_SIZE xen_mk_ullong(0x02000000)
/* PL011 mappings */
#define GUEST_PL011_BASE xen_mk_ullong(0x22000000)
#define GUEST_PL011_SIZE xen_mk_ullong(0x00001000)
/* Guest PCI-PCIe memory space where config space and BAR will be available.*/
#define GUEST_VPCI_ADDR_TYPE_MEM xen_mk_ullong(0x02000000)
#define GUEST_VPCI_MEM_ADDR xen_mk_ullong(0x23000000)
#define GUEST_VPCI_MEM_SIZE xen_mk_ullong(0x10000000)
/*
* 16MB == 4096 pages reserved for guest to use as a region to map its
* grant table in.
*/
#define GUEST_GNTTAB_BASE xen_mk_ullong(0x38000000)
#define GUEST_GNTTAB_SIZE xen_mk_ullong(0x01000000)
#define GUEST_MAGIC_BASE xen_mk_ullong(0x39000000)
#define GUEST_MAGIC_SIZE xen_mk_ullong(0x01000000)
#define GUEST_RAM_BANKS 2
/*
* The way to find the extended regions (to be exposed to the guest as unused
* address space) relies on the fact that the regions reserved for the RAM
* below are big enough to also accommodate such regions.
*/
#define GUEST_RAM0_BASE xen_mk_ullong(0x40000000) /* 3GB of low RAM @ 1GB */
#define GUEST_RAM0_SIZE xen_mk_ullong(0xc0000000)
/* 4GB @ 4GB Prefetch Memory for VPCI */
#define GUEST_VPCI_ADDR_TYPE_PREFETCH_MEM xen_mk_ullong(0x42000000)
#define GUEST_VPCI_PREFETCH_MEM_ADDR xen_mk_ullong(0x100000000)
#define GUEST_VPCI_PREFETCH_MEM_SIZE xen_mk_ullong(0x100000000)
#define GUEST_RAM1_BASE xen_mk_ullong(0x0200000000) /* 1016GB of RAM @ 8GB */
#define GUEST_RAM1_SIZE xen_mk_ullong(0xfe00000000)
#define GUEST_RAM_BASE GUEST_RAM0_BASE /* Lowest RAM address */
/* Largest amount of actual RAM, not including holes */
#define GUEST_RAM_MAX (GUEST_RAM0_SIZE + GUEST_RAM1_SIZE)
/* Suitable for e.g. const uint64_t ramfoo[] = GUEST_RAM_BANK_FOOS; */
#define GUEST_RAM_BANK_BASES { GUEST_RAM0_BASE, GUEST_RAM1_BASE }
#define GUEST_RAM_BANK_SIZES { GUEST_RAM0_SIZE, GUEST_RAM1_SIZE }
/* Current supported guest VCPUs */
#define GUEST_MAX_VCPUS 128
/* Interrupts */
#define GUEST_TIMER_VIRT_PPI 27
#define GUEST_TIMER_PHYS_S_PPI 29
#define GUEST_TIMER_PHYS_NS_PPI 30
#define GUEST_EVTCHN_PPI 31
#define GUEST_VPL011_SPI 32
/* PSCI functions */
#define PSCI_cpu_suspend 0
#define PSCI_cpu_off 1
#define PSCI_cpu_on 2
#define PSCI_migrate 3
#endif
#ifndef __ASSEMBLY__
/* Stub definition of PMU structure */
typedef struct xen_pmu_arch { uint8_t dummy; } xen_pmu_arch_t;
#endif
#endif /* __XEN_PUBLIC_ARCH_ARM_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

118
include/hw/xen/interface/arch-x86/cpuid.h Normal file
View File

@ -0,0 +1,118 @@
/******************************************************************************
* arch-x86/cpuid.h
*
* CPUID interface to Xen.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2007 Citrix Systems, Inc.
*
* Authors:
* Keir Fraser <keir@xen.org>
*/
#ifndef __XEN_PUBLIC_ARCH_X86_CPUID_H__
#define __XEN_PUBLIC_ARCH_X86_CPUID_H__
/*
* For compatibility with other hypervisor interfaces, the Xen cpuid leaves
* can be found at the first otherwise unused 0x100 aligned boundary starting
* from 0x40000000.
*
* e.g If viridian extensions are enabled for an HVM domain, the Xen cpuid
* leaves will start at 0x40000100
*/
#define XEN_CPUID_FIRST_LEAF 0x40000000
#define XEN_CPUID_LEAF(i) (XEN_CPUID_FIRST_LEAF + (i))
/*
* Leaf 1 (0x40000x00)
* EAX: Largest Xen-information leaf. All leaves up to an including @EAX
* are supported by the Xen host.
* EBX-EDX: "XenVMMXenVMM" signature, allowing positive identification
* of a Xen host.
*/
#define XEN_CPUID_SIGNATURE_EBX 0x566e6558 /* "XenV" */
#define XEN_CPUID_SIGNATURE_ECX 0x65584d4d /* "MMXe" */
#define XEN_CPUID_SIGNATURE_EDX 0x4d4d566e /* "nVMM" */
/*
* Leaf 2 (0x40000x01)
* EAX[31:16]: Xen major version.
* EAX[15: 0]: Xen minor version.
* EBX-EDX: Reserved (currently all zeroes).
*/
/*
* Leaf 3 (0x40000x02)
* EAX: Number of hypercall transfer pages. This register is always guaranteed
* to specify one hypercall page.
* EBX: Base address of Xen-specific MSRs.
* ECX: Features 1. Unused bits are set to zero.
* EDX: Features 2. Unused bits are set to zero.
*/
/* Does the host support MMU_PT_UPDATE_PRESERVE_AD for this guest? */
#define _XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD 0
#define XEN_CPUID_FEAT1_MMU_PT_UPDATE_PRESERVE_AD (1u<<0)
/*
* Leaf 4 (0x40000x03)
* Sub-leaf 0: EAX: bit 0: emulated tsc
* bit 1: host tsc is known to be reliable
* bit 2: RDTSCP instruction available
* EBX: tsc_mode: 0=default (emulate if necessary), 1=emulate,
* 2=no emulation, 3=no emulation + TSC_AUX support
* ECX: guest tsc frequency in kHz
* EDX: guest tsc incarnation (migration count)
* Sub-leaf 1: EAX: tsc offset low part
* EBX: tsc offset high part
* ECX: multiplicator for tsc->ns conversion
* EDX: shift amount for tsc->ns conversion
* Sub-leaf 2: EAX: host tsc frequency in kHz
*/
/*
* Leaf 5 (0x40000x04)
* HVM-specific features
* Sub-leaf 0: EAX: Features
* Sub-leaf 0: EBX: vcpu id (iff EAX has XEN_HVM_CPUID_VCPU_ID_PRESENT flag)
* Sub-leaf 0: ECX: domain id (iff EAX has XEN_HVM_CPUID_DOMID_PRESENT flag)
*/
#define XEN_HVM_CPUID_APIC_ACCESS_VIRT (1u << 0) /* Virtualized APIC registers */
#define XEN_HVM_CPUID_X2APIC_VIRT (1u << 1) /* Virtualized x2APIC accesses */
/* Memory mapped from other domains has valid IOMMU entries */
#define XEN_HVM_CPUID_IOMMU_MAPPINGS (1u << 2)
#define XEN_HVM_CPUID_VCPU_ID_PRESENT (1u << 3) /* vcpu id is present in EBX */
#define XEN_HVM_CPUID_DOMID_PRESENT (1u << 4) /* domid is present in ECX */
/*
* Leaf 6 (0x40000x05)
* PV-specific parameters
* Sub-leaf 0: EAX: max available sub-leaf
* Sub-leaf 0: EBX: bits 0-7: max machine address width
*/
/* Max. address width in bits taking memory hotplug into account. */
#define XEN_CPUID_MACHINE_ADDRESS_WIDTH_MASK (0xffu << 0)
#define XEN_CPUID_MAX_NUM_LEAVES 5
#endif /* __XEN_PUBLIC_ARCH_X86_CPUID_H__ */

194
include/hw/xen/interface/arch-x86/xen-x86_32.h Normal file
View File

@ -0,0 +1,194 @@
/******************************************************************************
* xen-x86_32.h
*
* Guest OS interface to x86 32-bit Xen.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2004-2007, K A Fraser
*/
#ifndef __XEN_PUBLIC_ARCH_X86_XEN_X86_32_H__
#define __XEN_PUBLIC_ARCH_X86_XEN_X86_32_H__
/*
* Hypercall interface:
* Input: %ebx, %ecx, %edx, %esi, %edi, %ebp (arguments 1-6)
* Output: %eax
* Access is via hypercall page (set up by guest loader or via a Xen MSR):
* call hypercall_page + hypercall-number * 32
* Clobbered: Argument registers (e.g., 2-arg hypercall clobbers %ebx,%ecx)
*/
/*
* These flat segments are in the Xen-private section of every GDT. Since these
* are also present in the initial GDT, many OSes will be able to avoid
* installing their own GDT.
*/
#define FLAT_RING1_CS 0xe019 /* GDT index 259 */
#define FLAT_RING1_DS 0xe021 /* GDT index 260 */
#define FLAT_RING1_SS 0xe021 /* GDT index 260 */
#define FLAT_RING3_CS 0xe02b /* GDT index 261 */
#define FLAT_RING3_DS 0xe033 /* GDT index 262 */
#define FLAT_RING3_SS 0xe033 /* GDT index 262 */
#define FLAT_KERNEL_CS FLAT_RING1_CS
#define FLAT_KERNEL_DS FLAT_RING1_DS
#define FLAT_KERNEL_SS FLAT_RING1_SS
#define FLAT_USER_CS FLAT_RING3_CS
#define FLAT_USER_DS FLAT_RING3_DS
#define FLAT_USER_SS FLAT_RING3_SS
#define __HYPERVISOR_VIRT_START_PAE 0xF5800000
#define __MACH2PHYS_VIRT_START_PAE 0xF5800000
#define __MACH2PHYS_VIRT_END_PAE 0xF6800000
#define HYPERVISOR_VIRT_START_PAE xen_mk_ulong(__HYPERVISOR_VIRT_START_PAE)
#define MACH2PHYS_VIRT_START_PAE xen_mk_ulong(__MACH2PHYS_VIRT_START_PAE)
#define MACH2PHYS_VIRT_END_PAE xen_mk_ulong(__MACH2PHYS_VIRT_END_PAE)
/* Non-PAE bounds are obsolete. */
#define __HYPERVISOR_VIRT_START_NONPAE 0xFC000000
#define __MACH2PHYS_VIRT_START_NONPAE 0xFC000000
#define __MACH2PHYS_VIRT_END_NONPAE 0xFC400000
#define HYPERVISOR_VIRT_START_NONPAE \
xen_mk_ulong(__HYPERVISOR_VIRT_START_NONPAE)
#define MACH2PHYS_VIRT_START_NONPAE \
xen_mk_ulong(__MACH2PHYS_VIRT_START_NONPAE)
#define MACH2PHYS_VIRT_END_NONPAE \
xen_mk_ulong(__MACH2PHYS_VIRT_END_NONPAE)
#define __HYPERVISOR_VIRT_START __HYPERVISOR_VIRT_START_PAE
#define __MACH2PHYS_VIRT_START __MACH2PHYS_VIRT_START_PAE
#define __MACH2PHYS_VIRT_END __MACH2PHYS_VIRT_END_PAE
#ifndef HYPERVISOR_VIRT_START
#define HYPERVISOR_VIRT_START xen_mk_ulong(__HYPERVISOR_VIRT_START)
#endif
#define MACH2PHYS_VIRT_START xen_mk_ulong(__MACH2PHYS_VIRT_START)
#define MACH2PHYS_VIRT_END xen_mk_ulong(__MACH2PHYS_VIRT_END)
#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>2)
#ifndef machine_to_phys_mapping
#define machine_to_phys_mapping ((unsigned long *)MACH2PHYS_VIRT_START)
#endif
/* 32-/64-bit invariability for control interfaces (domctl/sysctl). */
#if defined(__XEN__) || defined(__XEN_TOOLS__)
#undef ___DEFINE_XEN_GUEST_HANDLE
#define ___DEFINE_XEN_GUEST_HANDLE(name, type) \
typedef struct { type *p; } \
__guest_handle_ ## name; \
typedef struct { union { type *p; uint64_aligned_t q; }; } \
__guest_handle_64_ ## name
#undef set_xen_guest_handle_raw
#define set_xen_guest_handle_raw(hnd, val) \
do { if ( sizeof(hnd) == 8 ) *(uint64_t *)&(hnd) = 0; \
(hnd).p = val; \
} while ( 0 )
#define int64_aligned_t int64_t __attribute__((aligned(8)))
#define uint64_aligned_t uint64_t __attribute__((aligned(8)))
#define __XEN_GUEST_HANDLE_64(name) __guest_handle_64_ ## name
#define XEN_GUEST_HANDLE_64(name) __XEN_GUEST_HANDLE_64(name)
#endif
#ifndef __ASSEMBLY__
#if defined(XEN_GENERATING_COMPAT_HEADERS)
/* nothing */
#elif defined(__XEN__) || defined(__XEN_TOOLS__)
/* Anonymous unions include all permissible names (e.g., al/ah/ax/eax). */
#define __DECL_REG_LO8(which) union { \
uint32_t e ## which ## x; \
uint16_t which ## x; \
struct { \
uint8_t which ## l; \
uint8_t which ## h; \
}; \
}
#define __DECL_REG_LO16(name) union { \
uint32_t e ## name, _e ## name; \
uint16_t name; \
}
#else
/* Other sources must always use the proper 32-bit name (e.g., eax). */
#define __DECL_REG_LO8(which) uint32_t e ## which ## x
#define __DECL_REG_LO16(name) uint32_t e ## name
#endif
struct cpu_user_regs {
__DECL_REG_LO8(b);
__DECL_REG_LO8(c);
__DECL_REG_LO8(d);
__DECL_REG_LO16(si);
__DECL_REG_LO16(di);
__DECL_REG_LO16(bp);
__DECL_REG_LO8(a);
uint16_t error_code; /* private */
uint16_t entry_vector; /* private */
__DECL_REG_LO16(ip);
uint16_t cs;
uint8_t saved_upcall_mask;
uint8_t _pad0;
__DECL_REG_LO16(flags); /* eflags.IF == !saved_upcall_mask */
__DECL_REG_LO16(sp);
uint16_t ss, _pad1;
uint16_t es, _pad2;
uint16_t ds, _pad3;
uint16_t fs, _pad4;
uint16_t gs, _pad5;
};
typedef struct cpu_user_regs cpu_user_regs_t;
DEFINE_XEN_GUEST_HANDLE(cpu_user_regs_t);
#undef __DECL_REG_LO8
#undef __DECL_REG_LO16
/*
* Page-directory addresses above 4GB do not fit into architectural %cr3.
* When accessing %cr3, or equivalent field in vcpu_guest_context, guests
* must use the following accessor macros to pack/unpack valid MFNs.
*/
#define xen_pfn_to_cr3(pfn) (((unsigned)(pfn) << 12) | ((unsigned)(pfn) >> 20))
#define xen_cr3_to_pfn(cr3) (((unsigned)(cr3) >> 12) | ((unsigned)(cr3) << 20))
struct arch_vcpu_info {
unsigned long cr2;
unsigned long pad[5]; /* sizeof(vcpu_info_t) == 64 */
};
typedef struct arch_vcpu_info arch_vcpu_info_t;
struct xen_callback {
unsigned long cs;
unsigned long eip;
};
typedef struct xen_callback xen_callback_t;
#endif /* !__ASSEMBLY__ */
#endif /* __XEN_PUBLIC_ARCH_X86_XEN_X86_32_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

241
include/hw/xen/interface/arch-x86/xen-x86_64.h Normal file
View File

@ -0,0 +1,241 @@
/******************************************************************************
* xen-x86_64.h
*
* Guest OS interface to x86 64-bit Xen.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2004-2006, K A Fraser
*/
#ifndef __XEN_PUBLIC_ARCH_X86_XEN_X86_64_H__
#define __XEN_PUBLIC_ARCH_X86_XEN_X86_64_H__
/*
* Hypercall interface:
* Input: %rdi, %rsi, %rdx, %r10, %r8, %r9 (arguments 1-6)
* Output: %rax
* Access is via hypercall page (set up by guest loader or via a Xen MSR):
* call hypercall_page + hypercall-number * 32
* Clobbered: argument registers (e.g., 2-arg hypercall clobbers %rdi,%rsi)
*/
/*
* 64-bit segment selectors
* These flat segments are in the Xen-private section of every GDT. Since these
* are also present in the initial GDT, many OSes will be able to avoid
* installing their own GDT.
*/
#define FLAT_RING3_CS32 0xe023 /* GDT index 260 */
#define FLAT_RING3_CS64 0xe033 /* GDT index 262 */
#define FLAT_RING3_DS32 0xe02b /* GDT index 261 */
#define FLAT_RING3_DS64 0x0000 /* NULL selector */
#define FLAT_RING3_SS32 0xe02b /* GDT index 261 */
#define FLAT_RING3_SS64 0xe02b /* GDT index 261 */
#define FLAT_KERNEL_DS64 FLAT_RING3_DS64
#define FLAT_KERNEL_DS32 FLAT_RING3_DS32
#define FLAT_KERNEL_DS FLAT_KERNEL_DS64
#define FLAT_KERNEL_CS64 FLAT_RING3_CS64
#define FLAT_KERNEL_CS32 FLAT_RING3_CS32
#define FLAT_KERNEL_CS FLAT_KERNEL_CS64
#define FLAT_KERNEL_SS64 FLAT_RING3_SS64
#define FLAT_KERNEL_SS32 FLAT_RING3_SS32
#define FLAT_KERNEL_SS FLAT_KERNEL_SS64
#define FLAT_USER_DS64 FLAT_RING3_DS64
#define FLAT_USER_DS32 FLAT_RING3_DS32
#define FLAT_USER_DS FLAT_USER_DS64
#define FLAT_USER_CS64 FLAT_RING3_CS64
#define FLAT_USER_CS32 FLAT_RING3_CS32
#define FLAT_USER_CS FLAT_USER_CS64
#define FLAT_USER_SS64 FLAT_RING3_SS64
#define FLAT_USER_SS32 FLAT_RING3_SS32
#define FLAT_USER_SS FLAT_USER_SS64
#define __HYPERVISOR_VIRT_START 0xFFFF800000000000
#define __HYPERVISOR_VIRT_END 0xFFFF880000000000
#define __MACH2PHYS_VIRT_START 0xFFFF800000000000
#define __MACH2PHYS_VIRT_END 0xFFFF804000000000
#ifndef HYPERVISOR_VIRT_START
#define HYPERVISOR_VIRT_START xen_mk_ulong(__HYPERVISOR_VIRT_START)
#define HYPERVISOR_VIRT_END xen_mk_ulong(__HYPERVISOR_VIRT_END)
#endif
#define MACH2PHYS_VIRT_START xen_mk_ulong(__MACH2PHYS_VIRT_START)
#define MACH2PHYS_VIRT_END xen_mk_ulong(__MACH2PHYS_VIRT_END)
#define MACH2PHYS_NR_ENTRIES ((MACH2PHYS_VIRT_END-MACH2PHYS_VIRT_START)>>3)
#ifndef machine_to_phys_mapping
#define machine_to_phys_mapping ((unsigned long *)HYPERVISOR_VIRT_START)
#endif
/*
* int HYPERVISOR_set_segment_base(unsigned int which, unsigned long base)
* @which == SEGBASE_* ; @base == 64-bit base address
* Returns 0 on success.
*/
#define SEGBASE_FS 0
#define SEGBASE_GS_USER 1
#define SEGBASE_GS_KERNEL 2
#define SEGBASE_GS_USER_SEL 3 /* Set user %gs specified in base[15:0] */
/*
* int HYPERVISOR_iret(void)
* All arguments are on the kernel stack, in the following format.
* Never returns if successful. Current kernel context is lost.
* The saved CS is mapped as follows:
* RING0 -> RING3 kernel mode.
* RING1 -> RING3 kernel mode.
* RING2 -> RING3 kernel mode.
* RING3 -> RING3 user mode.
* However RING0 indicates that the guest kernel should return to iteself
* directly with
* orb $3,1*8(%rsp)
* iretq
* If flags contains VGCF_in_syscall:
* Restore RAX, RIP, RFLAGS, RSP.
* Discard R11, RCX, CS, SS.
* Otherwise:
* Restore RAX, R11, RCX, CS:RIP, RFLAGS, SS:RSP.
* All other registers are saved on hypercall entry and restored to user.
*/
/* Guest exited in SYSCALL context? Return to guest with SYSRET? */
#define _VGCF_in_syscall 8
#define VGCF_in_syscall (1<<_VGCF_in_syscall)
#define VGCF_IN_SYSCALL VGCF_in_syscall
#ifndef __ASSEMBLY__
struct iret_context {
/* Top of stack (%rsp at point of hypercall). */
uint64_t rax, r11, rcx, flags, rip, cs, rflags, rsp, ss;
/* Bottom of iret stack frame. */
};
#if defined(__XEN__) || defined(__XEN_TOOLS__)
/* Anonymous unions include all permissible names (e.g., al/ah/ax/eax/rax). */
#define __DECL_REG_LOHI(which) union { \
uint64_t r ## which ## x; \
uint32_t e ## which ## x; \
uint16_t which ## x; \
struct { \
uint8_t which ## l; \
uint8_t which ## h; \
}; \
}
#define __DECL_REG_LO8(name) union { \
uint64_t r ## name; \
uint32_t e ## name; \
uint16_t name; \
uint8_t name ## l; \
}
#define __DECL_REG_LO16(name) union { \
uint64_t r ## name; \
uint32_t e ## name; \
uint16_t name; \
}
#define __DECL_REG_HI(num) union { \
uint64_t r ## num; \
uint32_t r ## num ## d; \
uint16_t r ## num ## w; \
uint8_t r ## num ## b; \
}
#elif defined(__GNUC__) && !defined(__STRICT_ANSI__)
/* Anonymous union includes both 32- and 64-bit names (e.g., eax/rax). */
#define __DECL_REG(name) union { \
uint64_t r ## name, e ## name; \
uint32_t _e ## name; \
}
#else
/* Non-gcc sources must always use the proper 64-bit name (e.g., rax). */
#define __DECL_REG(name) uint64_t r ## name
#endif
#ifndef __DECL_REG_LOHI
#define __DECL_REG_LOHI(name) __DECL_REG(name ## x)
#define __DECL_REG_LO8 __DECL_REG
#define __DECL_REG_LO16 __DECL_REG
#define __DECL_REG_HI(num) uint64_t r ## num
#endif
struct cpu_user_regs {
__DECL_REG_HI(15);
__DECL_REG_HI(14);
__DECL_REG_HI(13);
__DECL_REG_HI(12);
__DECL_REG_LO8(bp);
__DECL_REG_LOHI(b);
__DECL_REG_HI(11);
__DECL_REG_HI(10);
__DECL_REG_HI(9);
__DECL_REG_HI(8);
__DECL_REG_LOHI(a);
__DECL_REG_LOHI(c);
__DECL_REG_LOHI(d);
__DECL_REG_LO8(si);
__DECL_REG_LO8(di);
uint32_t error_code; /* private */
uint32_t entry_vector; /* private */
__DECL_REG_LO16(ip);
uint16_t cs, _pad0[1];
uint8_t saved_upcall_mask;
uint8_t _pad1[3];
__DECL_REG_LO16(flags); /* rflags.IF == !saved_upcall_mask */
__DECL_REG_LO8(sp);
uint16_t ss, _pad2[3];
uint16_t es, _pad3[3];
uint16_t ds, _pad4[3];
uint16_t fs, _pad5[3];
uint16_t gs, _pad6[3];
};
typedef struct cpu_user_regs cpu_user_regs_t;
DEFINE_XEN_GUEST_HANDLE(cpu_user_regs_t);
#undef __DECL_REG
#undef __DECL_REG_LOHI
#undef __DECL_REG_LO8
#undef __DECL_REG_LO16
#undef __DECL_REG_HI
#define xen_pfn_to_cr3(pfn) ((unsigned long)(pfn) << 12)
#define xen_cr3_to_pfn(cr3) ((unsigned long)(cr3) >> 12)
struct arch_vcpu_info {
unsigned long cr2;
unsigned long pad; /* sizeof(vcpu_info_t) == 64 */
};
typedef struct arch_vcpu_info arch_vcpu_info_t;
typedef unsigned long xen_callback_t;
#endif /* !__ASSEMBLY__ */
#endif /* __XEN_PUBLIC_ARCH_X86_XEN_X86_64_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

398
include/hw/xen/interface/arch-x86/xen.h Normal file
View File

@ -0,0 +1,398 @@
/******************************************************************************
* arch-x86/xen.h
*
* Guest OS interface to x86 Xen.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2004-2006, K A Fraser
*/
#include "../xen.h"
#ifndef __XEN_PUBLIC_ARCH_X86_XEN_H__
#define __XEN_PUBLIC_ARCH_X86_XEN_H__
/* Structural guest handles introduced in 0x00030201. */
#if __XEN_INTERFACE_VERSION__ >= 0x00030201
#define ___DEFINE_XEN_GUEST_HANDLE(name, type) \
typedef struct { type *p; } __guest_handle_ ## name
#else
#define ___DEFINE_XEN_GUEST_HANDLE(name, type) \
typedef type * __guest_handle_ ## name
#endif
/*
* XEN_GUEST_HANDLE represents a guest pointer, when passed as a field
* in a struct in memory.
* XEN_GUEST_HANDLE_PARAM represent a guest pointer, when passed as an
* hypercall argument.
* XEN_GUEST_HANDLE_PARAM and XEN_GUEST_HANDLE are the same on X86 but
* they might not be on other architectures.
*/
#define __DEFINE_XEN_GUEST_HANDLE(name, type) \
___DEFINE_XEN_GUEST_HANDLE(name, type); \
___DEFINE_XEN_GUEST_HANDLE(const_##name, const type)
#define DEFINE_XEN_GUEST_HANDLE(name) __DEFINE_XEN_GUEST_HANDLE(name, name)
#define __XEN_GUEST_HANDLE(name) __guest_handle_ ## name
#define XEN_GUEST_HANDLE(name) __XEN_GUEST_HANDLE(name)
#define XEN_GUEST_HANDLE_PARAM(name) XEN_GUEST_HANDLE(name)
#define set_xen_guest_handle_raw(hnd, val) do { (hnd).p = val; } while (0)
#define set_xen_guest_handle(hnd, val) set_xen_guest_handle_raw(hnd, val)
#if defined(__i386__)
# ifdef __XEN__
__DeFiNe__ __DECL_REG_LO8(which) uint32_t e ## which ## x
__DeFiNe__ __DECL_REG_LO16(name) union { uint32_t e ## name; }
# endif
#include "xen-x86_32.h"
# ifdef __XEN__
__UnDeF__ __DECL_REG_LO8
__UnDeF__ __DECL_REG_LO16
__DeFiNe__ __DECL_REG_LO8(which) e ## which ## x
__DeFiNe__ __DECL_REG_LO16(name) e ## name
# endif
#elif defined(__x86_64__)
#include "xen-x86_64.h"
#endif
#ifndef __ASSEMBLY__
typedef unsigned long xen_pfn_t;
#define PRI_xen_pfn "lx"
#define PRIu_xen_pfn "lu"
#endif
#define XEN_HAVE_PV_GUEST_ENTRY 1
#define XEN_HAVE_PV_UPCALL_MASK 1
/*
* `incontents 200 segdesc Segment Descriptor Tables
*/
/*
* ` enum neg_errnoval
* ` HYPERVISOR_set_gdt(const xen_pfn_t frames[], unsigned int entries);
* `
*/
/*
* A number of GDT entries are reserved by Xen. These are not situated at the
* start of the GDT because some stupid OSes export hard-coded selector values
* in their ABI. These hard-coded values are always near the start of the GDT,
* so Xen places itself out of the way, at the far end of the GDT.
*
* NB The LDT is set using the MMUEXT_SET_LDT op of HYPERVISOR_mmuext_op
*/
#define FIRST_RESERVED_GDT_PAGE 14
#define FIRST_RESERVED_GDT_BYTE (FIRST_RESERVED_GDT_PAGE * 4096)
#define FIRST_RESERVED_GDT_ENTRY (FIRST_RESERVED_GDT_BYTE / 8)
/*
* ` enum neg_errnoval
* ` HYPERVISOR_update_descriptor(u64 pa, u64 desc);
* `
* ` @pa The machine physical address of the descriptor to
* ` update. Must be either a descriptor page or writable.
* ` @desc The descriptor value to update, in the same format as a
* ` native descriptor table entry.
*/
/* Maximum number of virtual CPUs in legacy multi-processor guests. */
#define XEN_LEGACY_MAX_VCPUS 32
#ifndef __ASSEMBLY__
typedef unsigned long xen_ulong_t;
#define PRI_xen_ulong "lx"
/*
* ` enum neg_errnoval
* ` HYPERVISOR_stack_switch(unsigned long ss, unsigned long esp);
* `
* Sets the stack segment and pointer for the current vcpu.
*/
/*
* ` enum neg_errnoval
* ` HYPERVISOR_set_trap_table(const struct trap_info traps[]);
* `
*/
/*
* Send an array of these to HYPERVISOR_set_trap_table().
* Terminate the array with a sentinel entry, with traps[].address==0.
* The privilege level specifies which modes may enter a trap via a software
* interrupt. On x86/64, since rings 1 and 2 are unavailable, we allocate
* privilege levels as follows:
* Level == 0: Noone may enter
* Level == 1: Kernel may enter
* Level == 2: Kernel may enter
* Level == 3: Everyone may enter
*
* Note: For compatibility with kernels not setting up exception handlers
* early enough, Xen will avoid trying to inject #GP (and hence crash
* the domain) when an RDMSR would require this, but no handler was
* set yet. The precise conditions are implementation specific, and
* new code may not rely on such behavior anyway.
*/
#define TI_GET_DPL(_ti) ((_ti)->flags & 3)
#define TI_GET_IF(_ti) ((_ti)->flags & 4)
#define TI_SET_DPL(_ti,_dpl) ((_ti)->flags |= (_dpl))
#define TI_SET_IF(_ti,_if) ((_ti)->flags |= ((!!(_if))<<2))
struct trap_info {
uint8_t vector; /* exception vector */
uint8_t flags; /* 0-3: privilege level; 4: clear event enable? */
uint16_t cs; /* code selector */
unsigned long address; /* code offset */
};
typedef struct trap_info trap_info_t;
DEFINE_XEN_GUEST_HANDLE(trap_info_t);
typedef uint64_t tsc_timestamp_t; /* RDTSC timestamp */
/*
* The following is all CPU context. Note that the fpu_ctxt block is filled
* in by FXSAVE if the CPU has feature FXSR; otherwise FSAVE is used.
*
* Also note that when calling DOMCTL_setvcpucontext for HVM guests, not all
* information in this structure is updated, the fields read include: fpu_ctxt
* (if VGCT_I387_VALID is set), flags, user_regs and debugreg[*].
*
* Note: VCPUOP_initialise for HVM guests is non-symetric with
* DOMCTL_setvcpucontext, and uses struct vcpu_hvm_context from hvm/hvm_vcpu.h
*/
struct vcpu_guest_context {
/* FPU registers come first so they can be aligned for FXSAVE/FXRSTOR. */
struct { char x[512]; } fpu_ctxt; /* User-level FPU registers */
#define VGCF_I387_VALID (1<<0)
#define VGCF_IN_KERNEL (1<<2)
#define _VGCF_i387_valid 0
#define VGCF_i387_valid (1<<_VGCF_i387_valid)
#define _VGCF_in_kernel 2
#define VGCF_in_kernel (1<<_VGCF_in_kernel)
#define _VGCF_failsafe_disables_events 3
#define VGCF_failsafe_disables_events (1<<_VGCF_failsafe_disables_events)
#define _VGCF_syscall_disables_events 4
#define VGCF_syscall_disables_events (1<<_VGCF_syscall_disables_events)
#define _VGCF_online 5
#define VGCF_online (1<<_VGCF_online)
unsigned long flags; /* VGCF_* flags */
struct cpu_user_regs user_regs; /* User-level CPU registers */
struct trap_info trap_ctxt[256]; /* Virtual IDT */
unsigned long ldt_base, ldt_ents; /* LDT (linear address, # ents) */
unsigned long gdt_frames[16], gdt_ents; /* GDT (machine frames, # ents) */
unsigned long kernel_ss, kernel_sp; /* Virtual TSS (only SS1/SP1) */
/* NB. User pagetable on x86/64 is placed in ctrlreg[1]. */
unsigned long ctrlreg[8]; /* CR0-CR7 (control registers) */
unsigned long debugreg[8]; /* DB0-DB7 (debug registers) */
#ifdef __i386__
unsigned long event_callback_cs; /* CS:EIP of event callback */
unsigned long event_callback_eip;
unsigned long failsafe_callback_cs; /* CS:EIP of failsafe callback */
unsigned long failsafe_callback_eip;
#else
unsigned long event_callback_eip;
unsigned long failsafe_callback_eip;
#ifdef __XEN__
union {
unsigned long syscall_callback_eip;
struct {
unsigned int event_callback_cs; /* compat CS of event cb */
unsigned int failsafe_callback_cs; /* compat CS of failsafe cb */
};
};
#else
unsigned long syscall_callback_eip;
#endif
#endif
unsigned long vm_assist; /* VMASST_TYPE_* bitmap */
#ifdef __x86_64__
/* Segment base addresses. */
uint64_t fs_base;
uint64_t gs_base_kernel;
uint64_t gs_base_user;
#endif
};
typedef struct vcpu_guest_context vcpu_guest_context_t;
DEFINE_XEN_GUEST_HANDLE(vcpu_guest_context_t);
struct arch_shared_info {
/*
* Number of valid entries in the p2m table(s) anchored at
* pfn_to_mfn_frame_list_list and/or p2m_vaddr.
*/
unsigned long max_pfn;
/*
* Frame containing list of mfns containing list of mfns containing p2m.
* A value of 0 indicates it has not yet been set up, ~0 indicates it has
* been set to invalid e.g. due to the p2m being too large for the 3-level
* p2m tree. In this case the linear mapper p2m list anchored at p2m_vaddr
* is to be used.
*/
xen_pfn_t pfn_to_mfn_frame_list_list;
unsigned long nmi_reason;
/*
* Following three fields are valid if p2m_cr3 contains a value different
* from 0.
* p2m_cr3 is the root of the address space where p2m_vaddr is valid.
* p2m_cr3 is in the same format as a cr3 value in the vcpu register state
* and holds the folded machine frame number (via xen_pfn_to_cr3) of a
* L3 or L4 page table.
* p2m_vaddr holds the virtual address of the linear p2m list. All entries
* in the range [0...max_pfn[ are accessible via this pointer.
* p2m_generation will be incremented by the guest before and after each
* change of the mappings of the p2m list. p2m_generation starts at 0 and
* a value with the least significant bit set indicates that a mapping
* update is in progress. This allows guest external software (e.g. in Dom0)
* to verify that read mappings are consistent and whether they have changed
* since the last check.
* Modifying a p2m element in the linear p2m list is allowed via an atomic
* write only.
*/
unsigned long p2m_cr3; /* cr3 value of the p2m address space */
unsigned long p2m_vaddr; /* virtual address of the p2m list */
unsigned long p2m_generation; /* generation count of p2m mapping */
#ifdef __i386__
/* There's no room for this field in the generic structure. */
uint32_t wc_sec_hi;
#endif
};
typedef struct arch_shared_info arch_shared_info_t;
#if defined(__XEN__) || defined(__XEN_TOOLS__)
/*
* struct xen_arch_domainconfig's ABI is covered by
* XEN_DOMCTL_INTERFACE_VERSION.
*/
struct xen_arch_domainconfig {
#define _XEN_X86_EMU_LAPIC 0
#define XEN_X86_EMU_LAPIC (1U<<_XEN_X86_EMU_LAPIC)
#define _XEN_X86_EMU_HPET 1
#define XEN_X86_EMU_HPET (1U<<_XEN_X86_EMU_HPET)
#define _XEN_X86_EMU_PM 2
#define XEN_X86_EMU_PM (1U<<_XEN_X86_EMU_PM)
#define _XEN_X86_EMU_RTC 3
#define XEN_X86_EMU_RTC (1U<<_XEN_X86_EMU_RTC)
#define _XEN_X86_EMU_IOAPIC 4
#define XEN_X86_EMU_IOAPIC (1U<<_XEN_X86_EMU_IOAPIC)
#define _XEN_X86_EMU_PIC 5
#define XEN_X86_EMU_PIC (1U<<_XEN_X86_EMU_PIC)
#define _XEN_X86_EMU_VGA 6
#define XEN_X86_EMU_VGA (1U<<_XEN_X86_EMU_VGA)
#define _XEN_X86_EMU_IOMMU 7
#define XEN_X86_EMU_IOMMU (1U<<_XEN_X86_EMU_IOMMU)
#define _XEN_X86_EMU_PIT 8
#define XEN_X86_EMU_PIT (1U<<_XEN_X86_EMU_PIT)
#define _XEN_X86_EMU_USE_PIRQ 9
#define XEN_X86_EMU_USE_PIRQ (1U<<_XEN_X86_EMU_USE_PIRQ)
#define _XEN_X86_EMU_VPCI 10
#define XEN_X86_EMU_VPCI (1U<<_XEN_X86_EMU_VPCI)
#define XEN_X86_EMU_ALL (XEN_X86_EMU_LAPIC | XEN_X86_EMU_HPET | \
XEN_X86_EMU_PM | XEN_X86_EMU_RTC | \
XEN_X86_EMU_IOAPIC | XEN_X86_EMU_PIC | \
XEN_X86_EMU_VGA | XEN_X86_EMU_IOMMU | \
XEN_X86_EMU_PIT | XEN_X86_EMU_USE_PIRQ |\
XEN_X86_EMU_VPCI)
uint32_t emulation_flags;
/*
* Select whether to use a relaxed behavior for accesses to MSRs not explicitly
* handled by Xen instead of injecting a #GP to the guest. Note this option
* doesn't allow the guest to read or write to the underlying MSR.
*/
#define XEN_X86_MSR_RELAXED (1u << 0)
uint32_t misc_flags;
};
/* Location of online VCPU bitmap. */
#define XEN_ACPI_CPU_MAP 0xaf00
#define XEN_ACPI_CPU_MAP_LEN ((HVM_MAX_VCPUS + 7) / 8)
/* GPE0 bit set during CPU hotplug */
#define XEN_ACPI_GPE0_CPUHP_BIT 2
#endif
/*
* Representations of architectural CPUID and MSR information. Used as the
* serialised version of Xen's internal representation.
*/
typedef struct xen_cpuid_leaf {
#define XEN_CPUID_NO_SUBLEAF 0xffffffffu
uint32_t leaf, subleaf;
uint32_t a, b, c, d;
} xen_cpuid_leaf_t;
DEFINE_XEN_GUEST_HANDLE(xen_cpuid_leaf_t);
typedef struct xen_msr_entry {
uint32_t idx;
uint32_t flags; /* Reserved MBZ. */
uint64_t val;
} xen_msr_entry_t;
DEFINE_XEN_GUEST_HANDLE(xen_msr_entry_t);
#endif /* !__ASSEMBLY__ */
/*
* ` enum neg_errnoval
* ` HYPERVISOR_fpu_taskswitch(int set);
* `
* Sets (if set!=0) or clears (if set==0) CR0.TS.
*/
/*
* ` enum neg_errnoval
* ` HYPERVISOR_set_debugreg(int regno, unsigned long value);
*
* ` unsigned long
* ` HYPERVISOR_get_debugreg(int regno);
* For 0<=reg<=7, returns the debug register value.
* For other values of reg, returns ((unsigned long)-EINVAL).
* (Unfortunately, this interface is defective.)
*/
/*
* Prefix forces emulation of some non-trapping instructions.
* Currently only CPUID.
*/
#ifdef __ASSEMBLY__
#define XEN_EMULATE_PREFIX .byte 0x0f,0x0b,0x78,0x65,0x6e ;
#define XEN_CPUID XEN_EMULATE_PREFIX cpuid
#else
#define XEN_EMULATE_PREFIX ".byte 0x0f,0x0b,0x78,0x65,0x6e ; "
#define XEN_CPUID XEN_EMULATE_PREFIX "cpuid"
#endif
/*
* Debug console IO port, also called "port E9 hack". Each character written
* to this IO port will be printed on the hypervisor console, subject to log
* level restrictions.
*/
#define XEN_HVM_DEBUGCONS_IOPORT 0xe9
#endif /* __XEN_PUBLIC_ARCH_X86_XEN_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

388
include/hw/xen/interface/event_channel.h Normal file
View File

@ -0,0 +1,388 @@
/******************************************************************************
* event_channel.h
*
* Event channels between domains.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2003-2004, K A Fraser.
*/
#ifndef __XEN_PUBLIC_EVENT_CHANNEL_H__
#define __XEN_PUBLIC_EVENT_CHANNEL_H__
#include "xen.h"
/*
* `incontents 150 evtchn Event Channels
*
* Event channels are the basic primitive provided by Xen for event
* notifications. An event is the Xen equivalent of a hardware
* interrupt. They essentially store one bit of information, the event
* of interest is signalled by transitioning this bit from 0 to 1.
*
* Notifications are received by a guest via an upcall from Xen,
* indicating when an event arrives (setting the bit). Further
* notifications are masked until the bit is cleared again (therefore,
* guests must check the value of the bit after re-enabling event
* delivery to ensure no missed notifications).
*
* Event notifications can be masked by setting a flag; this is
* equivalent to disabling interrupts and can be used to ensure
* atomicity of certain operations in the guest kernel.
*
* Event channels are represented by the evtchn_* fields in
* struct shared_info and struct vcpu_info.
*/
/*
* ` enum neg_errnoval
* ` HYPERVISOR_event_channel_op(enum event_channel_op cmd, void *args)
* `
* @cmd == EVTCHNOP_* (event-channel operation).
* @args == struct evtchn_* Operation-specific extra arguments (NULL if none).
*/
/* ` enum event_channel_op { // EVTCHNOP_* => struct evtchn_* */
#define EVTCHNOP_bind_interdomain 0
#define EVTCHNOP_bind_virq 1
#define EVTCHNOP_bind_pirq 2
#define EVTCHNOP_close 3
#define EVTCHNOP_send 4
#define EVTCHNOP_status 5
#define EVTCHNOP_alloc_unbound 6
#define EVTCHNOP_bind_ipi 7
#define EVTCHNOP_bind_vcpu 8
#define EVTCHNOP_unmask 9
#define EVTCHNOP_reset 10
#define EVTCHNOP_init_control 11
#define EVTCHNOP_expand_array 12
#define EVTCHNOP_set_priority 13
#ifdef __XEN__
#define EVTCHNOP_reset_cont 14
#endif
/* ` } */
typedef uint32_t evtchn_port_t;
DEFINE_XEN_GUEST_HANDLE(evtchn_port_t);
/*
* EVTCHNOP_alloc_unbound: Allocate a port in domain <dom> and mark as
* accepting interdomain bindings from domain <remote_dom>. A fresh port
* is allocated in <dom> and returned as <port>.
* NOTES:
* 1. If the caller is unprivileged then <dom> must be DOMID_SELF.
* 2. <remote_dom> may be DOMID_SELF, allowing loopback connections.
*/
struct evtchn_alloc_unbound {
/* IN parameters */
domid_t dom, remote_dom;
/* OUT parameters */
evtchn_port_t port;
};
typedef struct evtchn_alloc_unbound evtchn_alloc_unbound_t;
/*
* EVTCHNOP_bind_interdomain: Construct an interdomain event channel between
* the calling domain and <remote_dom>. <remote_dom,remote_port> must identify
* a port that is unbound and marked as accepting bindings from the calling
* domain. A fresh port is allocated in the calling domain and returned as
* <local_port>.
*
* In case the peer domain has already tried to set our event channel
* pending, before it was bound, EVTCHNOP_bind_interdomain always sets
* the local event channel pending.
*
* The usual pattern of use, in the guest's upcall (or subsequent
* handler) is as follows: (Re-enable the event channel for subsequent
* signalling and then) check for the existence of whatever condition
* is being waited for by other means, and take whatever action is
* needed (if any).
*
* NOTES:
* 1. <remote_dom> may be DOMID_SELF, allowing loopback connections.
*/
struct evtchn_bind_interdomain {
/* IN parameters. */
domid_t remote_dom;
evtchn_port_t remote_port;
/* OUT parameters. */
evtchn_port_t local_port;
};
typedef struct evtchn_bind_interdomain evtchn_bind_interdomain_t;
/*
* EVTCHNOP_bind_virq: Bind a local event channel to VIRQ <irq> on specified
* vcpu.
* NOTES:
* 1. Virtual IRQs are classified as per-vcpu or global. See the VIRQ list
* in xen.h for the classification of each VIRQ.
* 2. Global VIRQs must be allocated on VCPU0 but can subsequently be
* re-bound via EVTCHNOP_bind_vcpu.
* 3. Per-vcpu VIRQs may be bound to at most one event channel per vcpu.
* The allocated event channel is bound to the specified vcpu and the
* binding cannot be changed.
*/
struct evtchn_bind_virq {
/* IN parameters. */
uint32_t virq; /* enum virq */
uint32_t vcpu;
/* OUT parameters. */
evtchn_port_t port;
};
typedef struct evtchn_bind_virq evtchn_bind_virq_t;
/*
* EVTCHNOP_bind_pirq: Bind a local event channel to a real IRQ (PIRQ <irq>).
* NOTES:
* 1. A physical IRQ may be bound to at most one event channel per domain.
* 2. Only a sufficiently-privileged domain may bind to a physical IRQ.
*/
struct evtchn_bind_pirq {
/* IN parameters. */
uint32_t pirq;
#define BIND_PIRQ__WILL_SHARE 1
uint32_t flags; /* BIND_PIRQ__* */
/* OUT parameters. */
evtchn_port_t port;
};
typedef struct evtchn_bind_pirq evtchn_bind_pirq_t;
/*
* EVTCHNOP_bind_ipi: Bind a local event channel to receive events.
* NOTES:
* 1. The allocated event channel is bound to the specified vcpu. The binding
* may not be changed.
*/
struct evtchn_bind_ipi {
uint32_t vcpu;
/* OUT parameters. */
evtchn_port_t port;
};
typedef struct evtchn_bind_ipi evtchn_bind_ipi_t;
/*
* EVTCHNOP_close: Close a local event channel <port>. If the channel is
* interdomain then the remote end is placed in the unbound state
* (EVTCHNSTAT_unbound), awaiting a new connection.
*/
struct evtchn_close {
/* IN parameters. */
evtchn_port_t port;
};
typedef struct evtchn_close evtchn_close_t;
/*
* EVTCHNOP_send: Send an event to the remote end of the channel whose local
* endpoint is <port>.
*/
struct evtchn_send {
/* IN parameters. */
evtchn_port_t port;
};
typedef struct evtchn_send evtchn_send_t;
/*
* EVTCHNOP_status: Get the current status of the communication channel which
* has an endpoint at <dom, port>.
* NOTES:
* 1. <dom> may be specified as DOMID_SELF.
* 2. Only a sufficiently-privileged domain may obtain the status of an event
* channel for which <dom> is not DOMID_SELF.
*/
struct evtchn_status {
/* IN parameters */
domid_t dom;
evtchn_port_t port;
/* OUT parameters */
#define EVTCHNSTAT_closed 0 /* Channel is not in use. */
#define EVTCHNSTAT_unbound 1 /* Channel is waiting interdom connection.*/
#define EVTCHNSTAT_interdomain 2 /* Channel is connected to remote domain. */
#define EVTCHNSTAT_pirq 3 /* Channel is bound to a phys IRQ line. */
#define EVTCHNSTAT_virq 4 /* Channel is bound to a virtual IRQ line */
#define EVTCHNSTAT_ipi 5 /* Channel is bound to a virtual IPI line */
uint32_t status;
uint32_t vcpu; /* VCPU to which this channel is bound. */
union {
struct {
domid_t dom;
} unbound; /* EVTCHNSTAT_unbound */
struct {
domid_t dom;
evtchn_port_t port;
} interdomain; /* EVTCHNSTAT_interdomain */
uint32_t pirq; /* EVTCHNSTAT_pirq */
uint32_t virq; /* EVTCHNSTAT_virq */
} u;
};
typedef struct evtchn_status evtchn_status_t;
/*
* EVTCHNOP_bind_vcpu: Specify which vcpu a channel should notify when an
* event is pending.
* NOTES:
* 1. IPI-bound channels always notify the vcpu specified at bind time.
* This binding cannot be changed.
* 2. Per-VCPU VIRQ channels always notify the vcpu specified at bind time.
* This binding cannot be changed.
* 3. All other channels notify vcpu0 by default. This default is set when
* the channel is allocated (a port that is freed and subsequently reused
* has its binding reset to vcpu0).
*/
struct evtchn_bind_vcpu {
/* IN parameters. */
evtchn_port_t port;
uint32_t vcpu;
};
typedef struct evtchn_bind_vcpu evtchn_bind_vcpu_t;
/*
* EVTCHNOP_unmask: Unmask the specified local event-channel port and deliver
* a notification to the appropriate VCPU if an event is pending.
*/
struct evtchn_unmask {
/* IN parameters. */
evtchn_port_t port;
};
typedef struct evtchn_unmask evtchn_unmask_t;
/*
* EVTCHNOP_reset: Close all event channels associated with specified domain.
* NOTES:
* 1. <dom> may be specified as DOMID_SELF.
* 2. Only a sufficiently-privileged domain may specify other than DOMID_SELF.
* 3. Destroys all control blocks and event array, resets event channel
* operations to 2-level ABI if called with <dom> == DOMID_SELF and FIFO
* ABI was used. Guests should not bind events during EVTCHNOP_reset call
* as these events are likely to be lost.
*/
struct evtchn_reset {
/* IN parameters. */
domid_t dom;
};
typedef struct evtchn_reset evtchn_reset_t;
/*
* EVTCHNOP_init_control: initialize the control block for the FIFO ABI.
*
* Note: any events that are currently pending will not be resent and
* will be lost. Guests should call this before binding any event to
* avoid losing any events.
*/
struct evtchn_init_control {
/* IN parameters. */
uint64_t control_gfn;
uint32_t offset;
uint32_t vcpu;
/* OUT parameters. */
uint8_t link_bits;
uint8_t _pad[7];
};
typedef struct evtchn_init_control evtchn_init_control_t;
/*
* EVTCHNOP_expand_array: add an additional page to the event array.
*/
struct evtchn_expand_array {
/* IN parameters. */
uint64_t array_gfn;
};
typedef struct evtchn_expand_array evtchn_expand_array_t;
/*
* EVTCHNOP_set_priority: set the priority for an event channel.
*/
struct evtchn_set_priority {
/* IN parameters. */
evtchn_port_t port;
uint32_t priority;
};
typedef struct evtchn_set_priority evtchn_set_priority_t;
/*
* ` enum neg_errnoval
* ` HYPERVISOR_event_channel_op_compat(struct evtchn_op *op)
* `
* Superceded by new event_channel_op() hypercall since 0x00030202.
*/
struct evtchn_op {
uint32_t cmd; /* enum event_channel_op */
union {
evtchn_alloc_unbound_t alloc_unbound;
evtchn_bind_interdomain_t bind_interdomain;
evtchn_bind_virq_t bind_virq;
evtchn_bind_pirq_t bind_pirq;
evtchn_bind_ipi_t bind_ipi;
evtchn_close_t close;
evtchn_send_t send;
evtchn_status_t status;
evtchn_bind_vcpu_t bind_vcpu;
evtchn_unmask_t unmask;
} u;
};
typedef struct evtchn_op evtchn_op_t;
DEFINE_XEN_GUEST_HANDLE(evtchn_op_t);
/*
* 2-level ABI
*/
#define EVTCHN_2L_NR_CHANNELS (sizeof(xen_ulong_t) * sizeof(xen_ulong_t) * 64)
/*
* FIFO ABI
*/
/* Events may have priorities from 0 (highest) to 15 (lowest). */
#define EVTCHN_FIFO_PRIORITY_MAX 0
#define EVTCHN_FIFO_PRIORITY_DEFAULT 7
#define EVTCHN_FIFO_PRIORITY_MIN 15
#define EVTCHN_FIFO_MAX_QUEUES (EVTCHN_FIFO_PRIORITY_MIN + 1)
typedef uint32_t event_word_t;
#define EVTCHN_FIFO_PENDING 31
#define EVTCHN_FIFO_MASKED 30
#define EVTCHN_FIFO_LINKED 29
#define EVTCHN_FIFO_BUSY 28
#define EVTCHN_FIFO_LINK_BITS 17
#define EVTCHN_FIFO_LINK_MASK ((1 << EVTCHN_FIFO_LINK_BITS) - 1)
#define EVTCHN_FIFO_NR_CHANNELS (1 << EVTCHN_FIFO_LINK_BITS)
struct evtchn_fifo_control_block {
uint32_t ready;
uint32_t _rsvd;
uint32_t head[EVTCHN_FIFO_MAX_QUEUES];
};
typedef struct evtchn_fifo_control_block evtchn_fifo_control_block_t;
#endif /* __XEN_PUBLIC_EVENT_CHANNEL_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

143
include/hw/xen/interface/features.h Normal file
View File

@ -0,0 +1,143 @@
/******************************************************************************
* features.h
*
* Feature flags, reported by XENVER_get_features.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2006, Keir Fraser <keir@xensource.com>
*/
#ifndef __XEN_PUBLIC_FEATURES_H__
#define __XEN_PUBLIC_FEATURES_H__
/*
* `incontents 200 elfnotes_features XEN_ELFNOTE_FEATURES
*
* The list of all the features the guest supports. They are set by
* parsing the XEN_ELFNOTE_FEATURES and XEN_ELFNOTE_SUPPORTED_FEATURES
* string. The format is the feature names (as given here without the
* "XENFEAT_" prefix) separated by '|' characters.
* If a feature is required for the kernel to function then the feature name
* must be preceded by a '!' character.
*
* Note that if XEN_ELFNOTE_SUPPORTED_FEATURES is used, then in the
* XENFEAT_dom0 MUST be set if the guest is to be booted as dom0,
*/
/*
* If set, the guest does not need to write-protect its pagetables, and can
* update them via direct writes.
*/
#define XENFEAT_writable_page_tables 0
/*
* If set, the guest does not need to write-protect its segment descriptor
* tables, and can update them via direct writes.
*/
#define XENFEAT_writable_descriptor_tables 1
/*
* If set, translation between the guest's 'pseudo-physical' address space
* and the host's machine address space are handled by the hypervisor. In this
* mode the guest does not need to perform phys-to/from-machine translations
* when performing page table operations.
*/
#define XENFEAT_auto_translated_physmap 2
/* If set, the guest is running in supervisor mode (e.g., x86 ring 0). */
#define XENFEAT_supervisor_mode_kernel 3
/*
* If set, the guest does not need to allocate x86 PAE page directories
* below 4GB. This flag is usually implied by auto_translated_physmap.
*/
#define XENFEAT_pae_pgdir_above_4gb 4
/* x86: Does this Xen host support the MMU_PT_UPDATE_PRESERVE_AD hypercall? */
#define XENFEAT_mmu_pt_update_preserve_ad 5
/* x86: Does this Xen host support the MMU_{CLEAR,COPY}_PAGE hypercall? */
#define XENFEAT_highmem_assist 6
/*
* If set, GNTTABOP_map_grant_ref honors flags to be placed into guest kernel
* available pte bits.
*/
#define XENFEAT_gnttab_map_avail_bits 7
/* x86: Does this Xen host support the HVM callback vector type? */
#define XENFEAT_hvm_callback_vector 8
/* x86: pvclock algorithm is safe to use on HVM */
#define XENFEAT_hvm_safe_pvclock 9
/* x86: pirq can be used by HVM guests */
#define XENFEAT_hvm_pirqs 10
/* operation as Dom0 is supported */
#define XENFEAT_dom0 11
/* Xen also maps grant references at pfn = mfn.
* This feature flag is deprecated and should not be used.
#define XENFEAT_grant_map_identity 12
*/
/* Guest can use XENMEMF_vnode to specify virtual node for memory op. */
#define XENFEAT_memory_op_vnode_supported 13
/* arm: Hypervisor supports ARM SMC calling convention. */
#define XENFEAT_ARM_SMCCC_supported 14
/*
* x86/PVH: If set, ACPI RSDP can be placed at any address. Otherwise RSDP
* must be located in lower 1MB, as required by ACPI Specification for IA-PC
* systems.
* This feature flag is only consulted if XEN_ELFNOTE_GUEST_OS contains
* the "linux" string.
*/
#define XENFEAT_linux_rsdp_unrestricted 15
/*
* A direct-mapped (or 1:1 mapped) domain is a domain for which its
* local pages have gfn == mfn. If a domain is direct-mapped,
* XENFEAT_direct_mapped is set; otherwise XENFEAT_not_direct_mapped
* is set.
*
* If neither flag is set (e.g. older Xen releases) the assumptions are:
* - not auto_translated domains (x86 only) are always direct-mapped
* - on x86, auto_translated domains are not direct-mapped
* - on ARM, Dom0 is direct-mapped, DomUs are not
*/
#define XENFEAT_not_direct_mapped 16
#define XENFEAT_direct_mapped 17
#define XENFEAT_NR_SUBMAPS 1
#endif /* __XEN_PUBLIC_FEATURES_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

650
include/hw/xen/interface/grant_table.h
View File

@ -28,9 +28,659 @@
#ifndef __XEN_PUBLIC_GRANT_TABLE_H__
#define __XEN_PUBLIC_GRANT_TABLE_H__
#include "xen.h"
/*
* `incontents 150 gnttab Grant Tables
*
* Xen's grant tables provide a generic mechanism to memory sharing
* between domains. This shared memory interface underpins the split
* device drivers for block and network IO.
*
* Each domain has its own grant table. This is a data structure that
* is shared with Xen; it allows the domain to tell Xen what kind of
* permissions other domains have on its pages. Entries in the grant
* table are identified by grant references. A grant reference is an
* integer, which indexes into the grant table. It acts as a
* capability which the grantee can use to perform operations on the
* granter's memory.
*
* This capability-based system allows shared-memory communications
* between unprivileged domains. A grant reference also encapsulates
* the details of a shared page, removing the need for a domain to
* know the real machine address of a page it is sharing. This makes
* it possible to share memory correctly with domains running in
* fully virtualised memory.
*/
/***********************************
* GRANT TABLE REPRESENTATION
*/
/* Some rough guidelines on accessing and updating grant-table entries
* in a concurrency-safe manner. For more information, Linux contains a
* reference implementation for guest OSes (drivers/xen/grant_table.c, see
* http://git.kernel.org/?p=linux/kernel/git/torvalds/linux.git;a=blob;f=drivers/xen/grant-table.c;hb=HEAD
*
* NB. WMB is a no-op on current-generation x86 processors. However, a
* compiler barrier will still be required.
*
* Introducing a valid entry into the grant table:
* 1. Write ent->domid.
* 2. Write ent->frame:
* GTF_permit_access: Frame to which access is permitted.
* GTF_accept_transfer: Pseudo-phys frame slot being filled by new
* frame, or zero if none.
* 3. Write memory barrier (WMB).
* 4. Write ent->flags, inc. valid type.
*
* Invalidating an unused GTF_permit_access entry:
* 1. flags = ent->flags.
* 2. Observe that !(flags & (GTF_reading|GTF_writing)).
* 3. Check result of SMP-safe CMPXCHG(&ent->flags, flags, 0).
* NB. No need for WMB as reuse of entry is control-dependent on success of
* step 3, and all architectures guarantee ordering of ctrl-dep writes.
*
* Invalidating an in-use GTF_permit_access entry:
* This cannot be done directly. Request assistance from the domain controller
* which can set a timeout on the use of a grant entry and take necessary
* action. (NB. This is not yet implemented!).
*
* Invalidating an unused GTF_accept_transfer entry:
* 1. flags = ent->flags.
* 2. Observe that !(flags & GTF_transfer_committed). [*]
* 3. Check result of SMP-safe CMPXCHG(&ent->flags, flags, 0).
* NB. No need for WMB as reuse of entry is control-dependent on success of
* step 3, and all architectures guarantee ordering of ctrl-dep writes.
* [*] If GTF_transfer_committed is set then the grant entry is 'committed'.
* The guest must /not/ modify the grant entry until the address of the
* transferred frame is written. It is safe for the guest to spin waiting
* for this to occur (detect by observing GTF_transfer_completed in
* ent->flags).
*
* Invalidating a committed GTF_accept_transfer entry:
* 1. Wait for (ent->flags & GTF_transfer_completed).
*
* Changing a GTF_permit_access from writable to read-only:
* Use SMP-safe CMPXCHG to set GTF_readonly, while checking !GTF_writing.
*
* Changing a GTF_permit_access from read-only to writable:
* Use SMP-safe bit-setting instruction.
*/
/*
* Reference to a grant entry in a specified domain's grant table.
*/
typedef uint32_t grant_ref_t;
/*
* A grant table comprises a packed array of grant entries in one or more
* page frames shared between Xen and a guest.
* [XEN]: This field is written by Xen and read by the sharing guest.
* [GST]: This field is written by the guest and read by Xen.
*/
/*
* Version 1 of the grant table entry structure is maintained largely for
* backwards compatibility. New guests are recommended to support using
* version 2 to overcome version 1 limitations, but to default to version 1.
*/
#if __XEN_INTERFACE_VERSION__ < 0x0003020a
#define grant_entry_v1 grant_entry
#define grant_entry_v1_t grant_entry_t
#endif
struct grant_entry_v1 {
/* GTF_xxx: various type and flag information. [XEN,GST] */
uint16_t flags;
/* The domain being granted foreign privileges. [GST] */
domid_t domid;
/*
* GTF_permit_access: GFN that @domid is allowed to map and access. [GST]
* GTF_accept_transfer: GFN that @domid is allowed to transfer into. [GST]
* GTF_transfer_completed: MFN whose ownership transferred by @domid
* (non-translated guests only). [XEN]
*/
uint32_t frame;
};
typedef struct grant_entry_v1 grant_entry_v1_t;
/* The first few grant table entries will be preserved across grant table
* version changes and may be pre-populated at domain creation by tools.
*/
#define GNTTAB_NR_RESERVED_ENTRIES 8
#define GNTTAB_RESERVED_CONSOLE 0
#define GNTTAB_RESERVED_XENSTORE 1
/*
* Type of grant entry.
* GTF_invalid: This grant entry grants no privileges.
* GTF_permit_access: Allow @domid to map/access @frame.
* GTF_accept_transfer: Allow @domid to transfer ownership of one page frame
* to this guest. Xen writes the page number to @frame.
* GTF_transitive: Allow @domid to transitively access a subrange of
* @trans_grant in @trans_domid. No mappings are allowed.
*/
#define GTF_invalid (0U<<0)
#define GTF_permit_access (1U<<0)
#define GTF_accept_transfer (2U<<0)
#define GTF_transitive (3U<<0)
#define GTF_type_mask (3U<<0)
/*
* Subflags for GTF_permit_access and GTF_transitive.
* GTF_readonly: Restrict @domid to read-only mappings and accesses. [GST]
* GTF_reading: Grant entry is currently mapped for reading by @domid. [XEN]
* GTF_writing: Grant entry is currently mapped for writing by @domid. [XEN]
* Further subflags for GTF_permit_access only.
* GTF_PAT, GTF_PWT, GTF_PCD: (x86) cache attribute flags to be used for
* mappings of the grant [GST]
* GTF_sub_page: Grant access to only a subrange of the page. @domid
* will only be allowed to copy from the grant, and not
* map it. [GST]
*/
#define _GTF_readonly (2)
#define GTF_readonly (1U<<_GTF_readonly)
#define _GTF_reading (3)
#define GTF_reading (1U<<_GTF_reading)
#define _GTF_writing (4)
#define GTF_writing (1U<<_GTF_writing)
#define _GTF_PWT (5)
#define GTF_PWT (1U<<_GTF_PWT)
#define _GTF_PCD (6)
#define GTF_PCD (1U<<_GTF_PCD)
#define _GTF_PAT (7)
#define GTF_PAT (1U<<_GTF_PAT)
#define _GTF_sub_page (8)
#define GTF_sub_page (1U<<_GTF_sub_page)
/*
* Subflags for GTF_accept_transfer:
* GTF_transfer_committed: Xen sets this flag to indicate that it is committed
* to transferring ownership of a page frame. When a guest sees this flag
* it must /not/ modify the grant entry until GTF_transfer_completed is
* set by Xen.
* GTF_transfer_completed: It is safe for the guest to spin-wait on this flag
* after reading GTF_transfer_committed. Xen will always write the frame
* address, followed by ORing this flag, in a timely manner.
*/
#define _GTF_transfer_committed (2)
#define GTF_transfer_committed (1U<<_GTF_transfer_committed)
#define _GTF_transfer_completed (3)
#define GTF_transfer_completed (1U<<_GTF_transfer_completed)
/*
* Version 2 grant table entries. These fulfil the same role as
* version 1 entries, but can represent more complicated operations.
* Any given domain will have either a version 1 or a version 2 table,
* and every entry in the table will be the same version.
*
* The interface by which domains use grant references does not depend
* on the grant table version in use by the other domain.
*/
#if __XEN_INTERFACE_VERSION__ >= 0x0003020a
/*
* Version 1 and version 2 grant entries share a common prefix. The
* fields of the prefix are documented as part of struct
* grant_entry_v1.
*/
struct grant_entry_header {
uint16_t flags;
domid_t domid;
};
typedef struct grant_entry_header grant_entry_header_t;
/*
* Version 2 of the grant entry structure.
*/
union grant_entry_v2 {
grant_entry_header_t hdr;
/*
* This member is used for V1-style full page grants, where either:
*
* -- hdr.type is GTF_accept_transfer, or
* -- hdr.type is GTF_permit_access and GTF_sub_page is not set.
*
* In that case, the frame field has the same semantics as the
* field of the same name in the V1 entry structure.
*/
struct {
grant_entry_header_t hdr;
uint32_t pad0;
uint64_t frame;
} full_page;
/*
* If the grant type is GTF_grant_access and GTF_sub_page is set,
* @domid is allowed to access bytes [@page_off,@page_off+@length)
* in frame @frame.
*/
struct {
grant_entry_header_t hdr;
uint16_t page_off;
uint16_t length;
uint64_t frame;
} sub_page;
/*
* If the grant is GTF_transitive, @domid is allowed to use the
* grant @gref in domain @trans_domid, as if it was the local
* domain. Obviously, the transitive access must be compatible
* with the original grant.
*
* The current version of Xen does not allow transitive grants
* to be mapped.
*/
struct {
grant_entry_header_t hdr;
domid_t trans_domid;
uint16_t pad0;
grant_ref_t gref;
} transitive;
uint32_t __spacer[4]; /* Pad to a power of two */
};
typedef union grant_entry_v2 grant_entry_v2_t;
typedef uint16_t grant_status_t;
#endif /* __XEN_INTERFACE_VERSION__ */
/***********************************
* GRANT TABLE QUERIES AND USES
*/
/* ` enum neg_errnoval
* ` HYPERVISOR_grant_table_op(enum grant_table_op cmd,
* ` void *args,
* ` unsigned int count)
* `
*
* @args points to an array of a per-command data structure. The array
* has @count members
*/
/* ` enum grant_table_op { // GNTTABOP_* => struct gnttab_* */
#define GNTTABOP_map_grant_ref 0
#define GNTTABOP_unmap_grant_ref 1
#define GNTTABOP_setup_table 2
#define GNTTABOP_dump_table 3
#define GNTTABOP_transfer 4
#define GNTTABOP_copy 5
#define GNTTABOP_query_size 6
#define GNTTABOP_unmap_and_replace 7
#if __XEN_INTERFACE_VERSION__ >= 0x0003020a
#define GNTTABOP_set_version 8
#define GNTTABOP_get_status_frames 9
#define GNTTABOP_get_version 10
#define GNTTABOP_swap_grant_ref 11
#define GNTTABOP_cache_flush 12
#endif /* __XEN_INTERFACE_VERSION__ */
/* ` } */
/*
* Handle to track a mapping created via a grant reference.
*/
typedef uint32_t grant_handle_t;
/*
* GNTTABOP_map_grant_ref: Map the grant entry (<dom>,<ref>) for access
* by devices and/or host CPUs. If successful, <handle> is a tracking number
* that must be presented later to destroy the mapping(s). On error, <status>
* is a negative status code.
* NOTES:
* 1. If GNTMAP_device_map is specified then <dev_bus_addr> is the address
* via which I/O devices may access the granted frame.
* 2. If GNTMAP_host_map is specified then a mapping will be added at
* either a host virtual address in the current address space, or at
* a PTE at the specified machine address. The type of mapping to
* perform is selected through the GNTMAP_contains_pte flag, and the
* address is specified in <host_addr>.
* 3. Mappings should only be destroyed via GNTTABOP_unmap_grant_ref. If a
* host mapping is destroyed by other means then it is *NOT* guaranteed
* to be accounted to the correct grant reference!
*/
struct gnttab_map_grant_ref {
/* IN parameters. */
uint64_t host_addr;
uint32_t flags; /* GNTMAP_* */
grant_ref_t ref;
domid_t dom;
/* OUT parameters. */
int16_t status; /* => enum grant_status */
grant_handle_t handle;
uint64_t dev_bus_addr;
};
typedef struct gnttab_map_grant_ref gnttab_map_grant_ref_t;
DEFINE_XEN_GUEST_HANDLE(gnttab_map_grant_ref_t);
/*
* GNTTABOP_unmap_grant_ref: Destroy one or more grant-reference mappings
* tracked by <handle>. If <host_addr> or <dev_bus_addr> is zero, that
* field is ignored. If non-zero, they must refer to a device/host mapping
* that is tracked by <handle>
* NOTES:
* 1. The call may fail in an undefined manner if either mapping is not
* tracked by <handle>.
* 3. After executing a batch of unmaps, it is guaranteed that no stale
* mappings will remain in the device or host TLBs.
*/
struct gnttab_unmap_grant_ref {
/* IN parameters. */
uint64_t host_addr;
uint64_t dev_bus_addr;
grant_handle_t handle;
/* OUT parameters. */
int16_t status; /* => enum grant_status */
};
typedef struct gnttab_unmap_grant_ref gnttab_unmap_grant_ref_t;
DEFINE_XEN_GUEST_HANDLE(gnttab_unmap_grant_ref_t);
/*
* GNTTABOP_setup_table: Set up a grant table for <dom> comprising at least
* <nr_frames> pages. The frame addresses are written to the <frame_list>.
* Only <nr_frames> addresses are written, even if the table is larger.
* NOTES:
* 1. <dom> may be specified as DOMID_SELF.
* 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF.
* 3. Xen may not support more than a single grant-table page per domain.
*/
struct gnttab_setup_table {
/* IN parameters. */
domid_t dom;
uint32_t nr_frames;
/* OUT parameters. */
int16_t status; /* => enum grant_status */
#if __XEN_INTERFACE_VERSION__ < 0x00040300
XEN_GUEST_HANDLE(ulong) frame_list;
#else
XEN_GUEST_HANDLE(xen_pfn_t) frame_list;
#endif
};
typedef struct gnttab_setup_table gnttab_setup_table_t;
DEFINE_XEN_GUEST_HANDLE(gnttab_setup_table_t);
/*
* GNTTABOP_dump_table: Dump the contents of the grant table to the
* xen console. Debugging use only.
*/
struct gnttab_dump_table {
/* IN parameters. */
domid_t dom;
/* OUT parameters. */
int16_t status; /* => enum grant_status */
};
typedef struct gnttab_dump_table gnttab_dump_table_t;
DEFINE_XEN_GUEST_HANDLE(gnttab_dump_table_t);
/*
* GNTTABOP_transfer: Transfer <frame> to a foreign domain. The foreign domain
* has previously registered its interest in the transfer via <domid, ref>.
*
* Note that, even if the transfer fails, the specified page no longer belongs
* to the calling domain *unless* the error is GNTST_bad_page.
*
* Note further that only PV guests can use this operation.
*/
struct gnttab_transfer {
/* IN parameters. */
xen_pfn_t mfn;
domid_t domid;
grant_ref_t ref;
/* OUT parameters. */
int16_t status;
};
typedef struct gnttab_transfer gnttab_transfer_t;
DEFINE_XEN_GUEST_HANDLE(gnttab_transfer_t);
/*
* GNTTABOP_copy: Hypervisor based copy
* source and destinations can be eithers MFNs or, for foreign domains,
* grant references. the foreign domain has to grant read/write access
* in its grant table.
*
* The flags specify what type source and destinations are (either MFN
* or grant reference).
*
* Note that this can also be used to copy data between two domains
* via a third party if the source and destination domains had previously
* grant appropriate access to their pages to the third party.
*
* source_offset specifies an offset in the source frame, dest_offset
* the offset in the target frame and len specifies the number of
* bytes to be copied.
*/
#define _GNTCOPY_source_gref (0)
#define GNTCOPY_source_gref (1<<_GNTCOPY_source_gref)
#define _GNTCOPY_dest_gref (1)
#define GNTCOPY_dest_gref (1<<_GNTCOPY_dest_gref)
struct gnttab_copy {
/* IN parameters. */
struct gnttab_copy_ptr {
union {
grant_ref_t ref;
xen_pfn_t gmfn;
} u;
domid_t domid;
uint16_t offset;
} source, dest;
uint16_t len;
uint16_t flags; /* GNTCOPY_* */
/* OUT parameters. */
int16_t status;
};
typedef struct gnttab_copy gnttab_copy_t;
DEFINE_XEN_GUEST_HANDLE(gnttab_copy_t);
/*
* GNTTABOP_query_size: Query the current and maximum sizes of the shared
* grant table.
* NOTES:
* 1. <dom> may be specified as DOMID_SELF.
* 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF.
*/
struct gnttab_query_size {
/* IN parameters. */
domid_t dom;
/* OUT parameters. */
uint32_t nr_frames;
uint32_t max_nr_frames;
int16_t status; /* => enum grant_status */
};
typedef struct gnttab_query_size gnttab_query_size_t;
DEFINE_XEN_GUEST_HANDLE(gnttab_query_size_t);
/*
* GNTTABOP_unmap_and_replace: Destroy one or more grant-reference mappings
* tracked by <handle> but atomically replace the page table entry with one
* pointing to the machine address under <new_addr>. <new_addr> will be
* redirected to the null entry.
* NOTES:
* 1. The call may fail in an undefined manner if either mapping is not
* tracked by <handle>.
* 2. After executing a batch of unmaps, it is guaranteed that no stale
* mappings will remain in the device or host TLBs.
*/
struct gnttab_unmap_and_replace {
/* IN parameters. */
uint64_t host_addr;
uint64_t new_addr;
grant_handle_t handle;
/* OUT parameters. */
int16_t status; /* => enum grant_status */
};
typedef struct gnttab_unmap_and_replace gnttab_unmap_and_replace_t;
DEFINE_XEN_GUEST_HANDLE(gnttab_unmap_and_replace_t);
#if __XEN_INTERFACE_VERSION__ >= 0x0003020a
/*
* GNTTABOP_set_version: Request a particular version of the grant
* table shared table structure. This operation may be used to toggle
* between different versions, but must be performed while no grants
* are active. The only defined versions are 1 and 2.
*/
struct gnttab_set_version {
/* IN/OUT parameters */
uint32_t version;
};
typedef struct gnttab_set_version gnttab_set_version_t;
DEFINE_XEN_GUEST_HANDLE(gnttab_set_version_t);
/*
* GNTTABOP_get_status_frames: Get the list of frames used to store grant
* status for <dom>. In grant format version 2, the status is separated
* from the other shared grant fields to allow more efficient synchronization
* using barriers instead of atomic cmpexch operations.
* <nr_frames> specify the size of vector <frame_list>.
* The frame addresses are returned in the <frame_list>.
* Only <nr_frames> addresses are returned, even if the table is larger.
* NOTES:
* 1. <dom> may be specified as DOMID_SELF.
* 2. Only a sufficiently-privileged domain may specify <dom> != DOMID_SELF.
*/
struct gnttab_get_status_frames {
/* IN parameters. */
uint32_t nr_frames;
domid_t dom;
/* OUT parameters. */
int16_t status; /* => enum grant_status */
XEN_GUEST_HANDLE(uint64_t) frame_list;
};
typedef struct gnttab_get_status_frames gnttab_get_status_frames_t;
DEFINE_XEN_GUEST_HANDLE(gnttab_get_status_frames_t);
/*
* GNTTABOP_get_version: Get the grant table version which is in
* effect for domain <dom>.
*/
struct gnttab_get_version {
/* IN parameters */
domid_t dom;
uint16_t pad;
/* OUT parameters */
uint32_t version;
};
typedef struct gnttab_get_version gnttab_get_version_t;
DEFINE_XEN_GUEST_HANDLE(gnttab_get_version_t);
/*
* GNTTABOP_swap_grant_ref: Swap the contents of two grant entries.
*/
struct gnttab_swap_grant_ref {
/* IN parameters */
grant_ref_t ref_a;
grant_ref_t ref_b;
/* OUT parameters */
int16_t status; /* => enum grant_status */
};
typedef struct gnttab_swap_grant_ref gnttab_swap_grant_ref_t;
DEFINE_XEN_GUEST_HANDLE(gnttab_swap_grant_ref_t);
/*
* Issue one or more cache maintenance operations on a portion of a
* page granted to the calling domain by a foreign domain.
*/
struct gnttab_cache_flush {
union {
uint64_t dev_bus_addr;
grant_ref_t ref;
} a;
uint16_t offset; /* offset from start of grant */
uint16_t length; /* size within the grant */
#define GNTTAB_CACHE_CLEAN (1u<<0)
#define GNTTAB_CACHE_INVAL (1u<<1)
#define GNTTAB_CACHE_SOURCE_GREF (1u<<31)
uint32_t op;
};
typedef struct gnttab_cache_flush gnttab_cache_flush_t;
DEFINE_XEN_GUEST_HANDLE(gnttab_cache_flush_t);
#endif /* __XEN_INTERFACE_VERSION__ */
/*
* Bitfield values for gnttab_map_grant_ref.flags.
*/
/* Map the grant entry for access by I/O devices. */
#define _GNTMAP_device_map (0)
#define GNTMAP_device_map (1<<_GNTMAP_device_map)
/* Map the grant entry for access by host CPUs. */
#define _GNTMAP_host_map (1)
#define GNTMAP_host_map (1<<_GNTMAP_host_map)
/* Accesses to the granted frame will be restricted to read-only access. */
#define _GNTMAP_readonly (2)
#define GNTMAP_readonly (1<<_GNTMAP_readonly)
/*
* GNTMAP_host_map subflag:
* 0 => The host mapping is usable only by the guest OS.
* 1 => The host mapping is usable by guest OS + current application.
*/
#define _GNTMAP_application_map (3)
#define GNTMAP_application_map (1<<_GNTMAP_application_map)
/*
* GNTMAP_contains_pte subflag:
* 0 => This map request contains a host virtual address.
* 1 => This map request contains the machine addess of the PTE to update.
*/
#define _GNTMAP_contains_pte (4)
#define GNTMAP_contains_pte (1<<_GNTMAP_contains_pte)
/*
* Bits to be placed in guest kernel available PTE bits (architecture
* dependent; only supported when XENFEAT_gnttab_map_avail_bits is set).
*/
#define _GNTMAP_guest_avail0 (16)
#define GNTMAP_guest_avail_mask ((uint32_t)~0 << _GNTMAP_guest_avail0)
/*
* Values for error status returns. All errors are -ve.
*/
/* ` enum grant_status { */
#define GNTST_okay (0) /* Normal return. */
#define GNTST_general_error (-1) /* General undefined error. */
#define GNTST_bad_domain (-2) /* Unrecognsed domain id. */
#define GNTST_bad_gntref (-3) /* Unrecognised or inappropriate gntref. */
#define GNTST_bad_handle (-4) /* Unrecognised or inappropriate handle. */
#define GNTST_bad_virt_addr (-5) /* Inappropriate virtual address to map. */
#define GNTST_bad_dev_addr (-6) /* Inappropriate device address to unmap.*/
#define GNTST_no_device_space (-7) /* Out of space in I/O MMU. */
#define GNTST_permission_denied (-8) /* Not enough privilege for operation. */
#define GNTST_bad_page (-9) /* Specified page was invalid for op. */
#define GNTST_bad_copy_arg (-10) /* copy arguments cross page boundary. */
#define GNTST_address_too_big (-11) /* transfer page address too large. */
#define GNTST_eagain (-12) /* Operation not done; try again. */
#define GNTST_no_space (-13) /* Out of space (handles etc). */
/* ` } */
#define GNTTABOP_error_msgs { \
"okay", \
"undefined error", \
"unrecognised domain id", \
"invalid grant reference", \
"invalid mapping handle", \
"invalid virtual address", \
"invalid device address", \
"no spare translation slot in the I/O MMU", \
"permission denied", \
"bad page", \
"copy arguments cross page boundary", \
"page address size too large", \
"operation not done; try again", \
"out of space", \
}
#endif /* __XEN_PUBLIC_GRANT_TABLE_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

395
include/hw/xen/interface/hvm/hvm_op.h Normal file
View File

@ -0,0 +1,395 @@
/*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2007, Keir Fraser
*/
#ifndef __XEN_PUBLIC_HVM_HVM_OP_H__
#define __XEN_PUBLIC_HVM_HVM_OP_H__
#include "../xen.h"
#include "../trace.h"
#include "../event_channel.h"
/* Get/set subcommands: extra argument == pointer to xen_hvm_param struct. */
#define HVMOP_set_param 0
#define HVMOP_get_param 1
struct xen_hvm_param {
domid_t domid; /* IN */
uint16_t pad;
uint32_t index; /* IN */
uint64_t value; /* IN/OUT */
};
typedef struct xen_hvm_param xen_hvm_param_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_param_t);
struct xen_hvm_altp2m_suppress_ve {
uint16_t view;
uint8_t suppress_ve; /* Boolean type. */
uint8_t pad1;
uint32_t pad2;
uint64_t gfn;
};
struct xen_hvm_altp2m_suppress_ve_multi {
uint16_t view;
uint8_t suppress_ve; /* Boolean type. */
uint8_t pad1;
int32_t first_error; /* Should be set to 0. */
uint64_t first_gfn; /* Value may be updated. */
uint64_t last_gfn;
uint64_t first_error_gfn; /* Gfn of the first error. */
};
#if __XEN_INTERFACE_VERSION__ < 0x00040900
/* Set the logical level of one of a domain's PCI INTx wires. */
#define HVMOP_set_pci_intx_level 2
struct xen_hvm_set_pci_intx_level {
/* Domain to be updated. */
domid_t domid;
/* PCI INTx identification in PCI topology (domain:bus:device:intx). */
uint8_t domain, bus, device, intx;
/* Assertion level (0 = unasserted, 1 = asserted). */
uint8_t level;
};
typedef struct xen_hvm_set_pci_intx_level xen_hvm_set_pci_intx_level_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_set_pci_intx_level_t);
/* Set the logical level of one of a domain's ISA IRQ wires. */
#define HVMOP_set_isa_irq_level 3
struct xen_hvm_set_isa_irq_level {
/* Domain to be updated. */
domid_t domid;
/* ISA device identification, by ISA IRQ (0-15). */
uint8_t isa_irq;
/* Assertion level (0 = unasserted, 1 = asserted). */
uint8_t level;
};
typedef struct xen_hvm_set_isa_irq_level xen_hvm_set_isa_irq_level_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_set_isa_irq_level_t);
#define HVMOP_set_pci_link_route 4
struct xen_hvm_set_pci_link_route {
/* Domain to be updated. */
domid_t domid;
/* PCI link identifier (0-3). */
uint8_t link;
/* ISA IRQ (1-15), or 0 (disable link). */
uint8_t isa_irq;
};
typedef struct xen_hvm_set_pci_link_route xen_hvm_set_pci_link_route_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_set_pci_link_route_t);
#endif /* __XEN_INTERFACE_VERSION__ < 0x00040900 */
/* Flushes all VCPU TLBs: @arg must be NULL. */
#define HVMOP_flush_tlbs 5
/*
* hvmmem_type_t should not be defined when generating the corresponding
* compat header. This will ensure that the improperly named HVMMEM_(*)
* values are defined only once.
*/
#ifndef XEN_GENERATING_COMPAT_HEADERS
typedef enum {
HVMMEM_ram_rw, /* Normal read/write guest RAM */
HVMMEM_ram_ro, /* Read-only; writes are discarded */
HVMMEM_mmio_dm, /* Reads and write go to the device model */
#if __XEN_INTERFACE_VERSION__ < 0x00040700
HVMMEM_mmio_write_dm, /* Read-only; writes go to the device model */
#else
HVMMEM_unused, /* Placeholder; setting memory to this type
will fail for code after 4.7.0 */
#endif
HVMMEM_ioreq_server /* Memory type claimed by an ioreq server; type
changes to this value are only allowed after
an ioreq server has claimed its ownership.
Only pages with HVMMEM_ram_rw are allowed to
change to this type; conversely, pages with
this type are only allowed to be changed back
to HVMMEM_ram_rw. */
} hvmmem_type_t;
#endif /* XEN_GENERATING_COMPAT_HEADERS */
/* Hint from PV drivers for pagetable destruction. */
#define HVMOP_pagetable_dying 9
struct xen_hvm_pagetable_dying {
/* Domain with a pagetable about to be destroyed. */
domid_t domid;
uint16_t pad[3]; /* align next field on 8-byte boundary */
/* guest physical address of the toplevel pagetable dying */
uint64_t gpa;
};
typedef struct xen_hvm_pagetable_dying xen_hvm_pagetable_dying_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_pagetable_dying_t);
/* Get the current Xen time, in nanoseconds since system boot. */
#define HVMOP_get_time 10
struct xen_hvm_get_time {
uint64_t now; /* OUT */
};
typedef struct xen_hvm_get_time xen_hvm_get_time_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_get_time_t);
#define HVMOP_xentrace 11
struct xen_hvm_xentrace {
uint16_t event, extra_bytes;
uint8_t extra[TRACE_EXTRA_MAX * sizeof(uint32_t)];
};
typedef struct xen_hvm_xentrace xen_hvm_xentrace_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_xentrace_t);
/* Following tools-only interfaces may change in future. */
#if defined(__XEN__) || defined(__XEN_TOOLS__)
/* Deprecated by XENMEM_access_op_set_access */
#define HVMOP_set_mem_access 12
/* Deprecated by XENMEM_access_op_get_access */
#define HVMOP_get_mem_access 13
#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */
#define HVMOP_get_mem_type 15
/* Return hvmmem_type_t for the specified pfn. */
struct xen_hvm_get_mem_type {
/* Domain to be queried. */
domid_t domid;
/* OUT variable. */
uint16_t mem_type;
uint16_t pad[2]; /* align next field on 8-byte boundary */
/* IN variable. */
uint64_t pfn;
};
typedef struct xen_hvm_get_mem_type xen_hvm_get_mem_type_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_get_mem_type_t);
/* Following tools-only interfaces may change in future. */
#if defined(__XEN__) || defined(__XEN_TOOLS__)
/*
* Definitions relating to DMOP_create_ioreq_server. (Defined here for
* backwards compatibility).
*/
#define HVM_IOREQSRV_BUFIOREQ_OFF 0
#define HVM_IOREQSRV_BUFIOREQ_LEGACY 1
/*
* Use this when read_pointer gets updated atomically and
* the pointer pair gets read atomically:
*/
#define HVM_IOREQSRV_BUFIOREQ_ATOMIC 2
#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */
#if defined(__i386__) || defined(__x86_64__)
/*
* HVMOP_set_evtchn_upcall_vector: Set a <vector> that should be used for event
* channel upcalls on the specified <vcpu>. If set,
* this vector will be used in preference to the
* domain global callback via (see
* HVM_PARAM_CALLBACK_IRQ).
*/
#define HVMOP_set_evtchn_upcall_vector 23
struct xen_hvm_evtchn_upcall_vector {
uint32_t vcpu;
uint8_t vector;
};
typedef struct xen_hvm_evtchn_upcall_vector xen_hvm_evtchn_upcall_vector_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_evtchn_upcall_vector_t);
#endif /* defined(__i386__) || defined(__x86_64__) */
#define HVMOP_guest_request_vm_event 24
/* HVMOP_altp2m: perform altp2m state operations */
#define HVMOP_altp2m 25
#define HVMOP_ALTP2M_INTERFACE_VERSION 0x00000001
struct xen_hvm_altp2m_domain_state {
/* IN or OUT variable on/off */
uint8_t state;
};
typedef struct xen_hvm_altp2m_domain_state xen_hvm_altp2m_domain_state_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_altp2m_domain_state_t);
struct xen_hvm_altp2m_vcpu_enable_notify {
uint32_t vcpu_id;
uint32_t pad;
/* #VE info area gfn */
uint64_t gfn;
};
typedef struct xen_hvm_altp2m_vcpu_enable_notify xen_hvm_altp2m_vcpu_enable_notify_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_altp2m_vcpu_enable_notify_t);
struct xen_hvm_altp2m_vcpu_disable_notify {
uint32_t vcpu_id;
};
typedef struct xen_hvm_altp2m_vcpu_disable_notify xen_hvm_altp2m_vcpu_disable_notify_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_altp2m_vcpu_disable_notify_t);
struct xen_hvm_altp2m_view {
/* IN/OUT variable */
uint16_t view;
uint16_t hvmmem_default_access; /* xenmem_access_t */
};
typedef struct xen_hvm_altp2m_view xen_hvm_altp2m_view_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_altp2m_view_t);
#if __XEN_INTERFACE_VERSION__ < 0x00040a00
struct xen_hvm_altp2m_set_mem_access {
/* view */
uint16_t view;
/* Memory type */
uint16_t access; /* xenmem_access_t */
uint32_t pad;
/* gfn */
uint64_t gfn;
};
typedef struct xen_hvm_altp2m_set_mem_access xen_hvm_altp2m_set_mem_access_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_altp2m_set_mem_access_t);
#endif /* __XEN_INTERFACE_VERSION__ < 0x00040a00 */
struct xen_hvm_altp2m_mem_access {
/* view */
uint16_t view;
/* Memory type */
uint16_t access; /* xenmem_access_t */
uint32_t pad;
/* gfn */
uint64_t gfn;
};
typedef struct xen_hvm_altp2m_mem_access xen_hvm_altp2m_mem_access_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_altp2m_mem_access_t);
struct xen_hvm_altp2m_set_mem_access_multi {
/* view */
uint16_t view;
uint16_t pad;
/* Number of pages */
uint32_t nr;
/*
* Used for continuation purposes.
* Must be set to zero upon initial invocation.
*/
uint64_t opaque;
/* List of pfns to set access for */
XEN_GUEST_HANDLE(const_uint64) pfn_list;
/* Corresponding list of access settings for pfn_list */
XEN_GUEST_HANDLE(const_uint8) access_list;
};
struct xen_hvm_altp2m_change_gfn {
/* view */
uint16_t view;
uint16_t pad1;
uint32_t pad2;
/* old gfn */
uint64_t old_gfn;
/* new gfn, INVALID_GFN (~0UL) means revert */
uint64_t new_gfn;
};
typedef struct xen_hvm_altp2m_change_gfn xen_hvm_altp2m_change_gfn_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_altp2m_change_gfn_t);
struct xen_hvm_altp2m_get_vcpu_p2m_idx {
uint32_t vcpu_id;
uint16_t altp2m_idx;
};
struct xen_hvm_altp2m_set_visibility {
uint16_t altp2m_idx;
uint8_t visible;
uint8_t pad;
};
struct xen_hvm_altp2m_op {
uint32_t version; /* HVMOP_ALTP2M_INTERFACE_VERSION */
uint32_t cmd;
/* Get/set the altp2m state for a domain */
#define HVMOP_altp2m_get_domain_state 1
#define HVMOP_altp2m_set_domain_state 2
/* Set a given VCPU to receive altp2m event notifications */
#define HVMOP_altp2m_vcpu_enable_notify 3
/* Create a new view */
#define HVMOP_altp2m_create_p2m 4
/* Destroy a view */
#define HVMOP_altp2m_destroy_p2m 5
/* Switch view for an entire domain */
#define HVMOP_altp2m_switch_p2m 6
/* Notify that a page of memory is to have specific access types */
#define HVMOP_altp2m_set_mem_access 7
/* Change a p2m entry to have a different gfn->mfn mapping */
#define HVMOP_altp2m_change_gfn 8
/* Set access for an array of pages */
#define HVMOP_altp2m_set_mem_access_multi 9
/* Set the "Suppress #VE" bit on a page */
#define HVMOP_altp2m_set_suppress_ve 10
/* Get the "Suppress #VE" bit of a page */
#define HVMOP_altp2m_get_suppress_ve 11
/* Get the access of a page of memory from a certain view */
#define HVMOP_altp2m_get_mem_access 12
/* Disable altp2m event notifications for a given VCPU */
#define HVMOP_altp2m_vcpu_disable_notify 13
/* Get the active vcpu p2m index */
#define HVMOP_altp2m_get_p2m_idx 14
/* Set the "Supress #VE" bit for a range of pages */
#define HVMOP_altp2m_set_suppress_ve_multi 15
/* Set visibility for a given altp2m view */
#define HVMOP_altp2m_set_visibility 16
domid_t domain;
uint16_t pad1;
uint32_t pad2;
union {
struct xen_hvm_altp2m_domain_state domain_state;
struct xen_hvm_altp2m_vcpu_enable_notify enable_notify;
struct xen_hvm_altp2m_view view;
#if __XEN_INTERFACE_VERSION__ < 0x00040a00
struct xen_hvm_altp2m_set_mem_access set_mem_access;
#endif /* __XEN_INTERFACE_VERSION__ < 0x00040a00 */
struct xen_hvm_altp2m_mem_access mem_access;
struct xen_hvm_altp2m_change_gfn change_gfn;
struct xen_hvm_altp2m_set_mem_access_multi set_mem_access_multi;
struct xen_hvm_altp2m_suppress_ve suppress_ve;
struct xen_hvm_altp2m_suppress_ve_multi suppress_ve_multi;
struct xen_hvm_altp2m_vcpu_disable_notify disable_notify;
struct xen_hvm_altp2m_get_vcpu_p2m_idx get_vcpu_p2m_idx;
struct xen_hvm_altp2m_set_visibility set_visibility;
uint8_t pad[64];
} u;
};
typedef struct xen_hvm_altp2m_op xen_hvm_altp2m_op_t;
DEFINE_XEN_GUEST_HANDLE(xen_hvm_altp2m_op_t);
#endif /* __XEN_PUBLIC_HVM_HVM_OP_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

318
include/hw/xen/interface/hvm/params.h Normal file
View File

@ -0,0 +1,318 @@
/*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2007, Keir Fraser
*/
#ifndef __XEN_PUBLIC_HVM_PARAMS_H__
#define __XEN_PUBLIC_HVM_PARAMS_H__
#include "hvm_op.h"
/* These parameters are deprecated and their meaning is undefined. */
#if defined(__XEN__) || defined(__XEN_TOOLS__)
#define HVM_PARAM_PAE_ENABLED 4
#define HVM_PARAM_DM_DOMAIN 13
#define HVM_PARAM_MEMORY_EVENT_CR0 20
#define HVM_PARAM_MEMORY_EVENT_CR3 21
#define HVM_PARAM_MEMORY_EVENT_CR4 22
#define HVM_PARAM_MEMORY_EVENT_INT3 23
#define HVM_PARAM_NESTEDHVM 24
#define HVM_PARAM_MEMORY_EVENT_SINGLE_STEP 25
#define HVM_PARAM_BUFIOREQ_EVTCHN 26
#define HVM_PARAM_MEMORY_EVENT_MSR 30
#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */
/*
* Parameter space for HVMOP_{set,get}_param.
*/
#define HVM_PARAM_CALLBACK_IRQ 0
#define HVM_PARAM_CALLBACK_IRQ_TYPE_MASK xen_mk_ullong(0xFF00000000000000)
/*
* How should CPU0 event-channel notifications be delivered?
*
* If val == 0 then CPU0 event-channel notifications are not delivered.
* If val != 0, val[63:56] encodes the type, as follows:
*/
#define HVM_PARAM_CALLBACK_TYPE_GSI 0
/*
* val[55:0] is a delivery GSI. GSI 0 cannot be used, as it aliases val == 0,
* and disables all notifications.
*/
#define HVM_PARAM_CALLBACK_TYPE_PCI_INTX 1
/*
* val[55:0] is a delivery PCI INTx line:
* Domain = val[47:32], Bus = val[31:16] DevFn = val[15:8], IntX = val[1:0]
*/
#if defined(__i386__) || defined(__x86_64__)
#define HVM_PARAM_CALLBACK_TYPE_VECTOR 2
/*
* val[7:0] is a vector number. Check for XENFEAT_hvm_callback_vector to know
* if this delivery method is available.
*/
#elif defined(__arm__) || defined(__aarch64__)
#define HVM_PARAM_CALLBACK_TYPE_PPI 2
/*
* val[55:16] needs to be zero.
* val[15:8] is interrupt flag of the PPI used by event-channel:
* bit 8: the PPI is edge(1) or level(0) triggered
* bit 9: the PPI is active low(1) or high(0)
* val[7:0] is a PPI number used by event-channel.
* This is only used by ARM/ARM64 and masking/eoi the interrupt associated to
* the notification is handled by the interrupt controller.
*/
#define HVM_PARAM_CALLBACK_TYPE_PPI_FLAG_MASK 0xFF00
#define HVM_PARAM_CALLBACK_TYPE_PPI_FLAG_LOW_LEVEL 2
#endif
/*
* These are not used by Xen. They are here for convenience of HVM-guest
* xenbus implementations.
*/
#define HVM_PARAM_STORE_PFN 1
#define HVM_PARAM_STORE_EVTCHN 2
#define HVM_PARAM_IOREQ_PFN 5
#define HVM_PARAM_BUFIOREQ_PFN 6
#if defined(__i386__) || defined(__x86_64__)
/*
* Viridian enlightenments
*
* (See http://download.microsoft.com/download/A/B/4/AB43A34E-BDD0-4FA6-BDEF-79EEF16E880B/Hypervisor%20Top%20Level%20Functional%20Specification%20v4.0.docx)
*
* To expose viridian enlightenments to the guest set this parameter
* to the desired feature mask. The base feature set must be present
* in any valid feature mask.
*/
#define HVM_PARAM_VIRIDIAN 9
/* Base+Freq viridian feature sets:
*
* - Hypercall MSRs (HV_X64_MSR_GUEST_OS_ID and HV_X64_MSR_HYPERCALL)
* - APIC access MSRs (HV_X64_MSR_EOI, HV_X64_MSR_ICR and HV_X64_MSR_TPR)
* - Virtual Processor index MSR (HV_X64_MSR_VP_INDEX)
* - Timer frequency MSRs (HV_X64_MSR_TSC_FREQUENCY and
* HV_X64_MSR_APIC_FREQUENCY)
*/
#define _HVMPV_base_freq 0
#define HVMPV_base_freq (1 << _HVMPV_base_freq)
/* Feature set modifications */
/* Disable timer frequency MSRs (HV_X64_MSR_TSC_FREQUENCY and
* HV_X64_MSR_APIC_FREQUENCY).
* This modification restores the viridian feature set to the
* original 'base' set exposed in releases prior to Xen 4.4.
*/
#define _HVMPV_no_freq 1
#define HVMPV_no_freq (1 << _HVMPV_no_freq)
/* Enable Partition Time Reference Counter (HV_X64_MSR_TIME_REF_COUNT) */
#define _HVMPV_time_ref_count 2
#define HVMPV_time_ref_count (1 << _HVMPV_time_ref_count)
/* Enable Reference TSC Page (HV_X64_MSR_REFERENCE_TSC) */
#define _HVMPV_reference_tsc 3
#define HVMPV_reference_tsc (1 << _HVMPV_reference_tsc)
/* Use Hypercall for remote TLB flush */
#define _HVMPV_hcall_remote_tlb_flush 4
#define HVMPV_hcall_remote_tlb_flush (1 << _HVMPV_hcall_remote_tlb_flush)
/* Use APIC assist */
#define _HVMPV_apic_assist 5
#define HVMPV_apic_assist (1 << _HVMPV_apic_assist)
/* Enable crash MSRs */
#define _HVMPV_crash_ctl 6
#define HVMPV_crash_ctl (1 << _HVMPV_crash_ctl)
/* Enable SYNIC MSRs */
#define _HVMPV_synic 7
#define HVMPV_synic (1 << _HVMPV_synic)
/* Enable STIMER MSRs */
#define _HVMPV_stimer 8
#define HVMPV_stimer (1 << _HVMPV_stimer)
/* Use Synthetic Cluster IPI Hypercall */
#define _HVMPV_hcall_ipi 9
#define HVMPV_hcall_ipi (1 << _HVMPV_hcall_ipi)
/* Enable ExProcessorMasks */
#define _HVMPV_ex_processor_masks 10
#define HVMPV_ex_processor_masks (1 << _HVMPV_ex_processor_masks)
/* Allow more than 64 VPs */
#define _HVMPV_no_vp_limit 11
#define HVMPV_no_vp_limit (1 << _HVMPV_no_vp_limit)
/* Enable vCPU hotplug */
#define _HVMPV_cpu_hotplug 12
#define HVMPV_cpu_hotplug (1 << _HVMPV_cpu_hotplug)
#define HVMPV_feature_mask \
(HVMPV_base_freq | \
HVMPV_no_freq | \
HVMPV_time_ref_count | \
HVMPV_reference_tsc | \
HVMPV_hcall_remote_tlb_flush | \
HVMPV_apic_assist | \
HVMPV_crash_ctl | \
HVMPV_synic | \
HVMPV_stimer | \
HVMPV_hcall_ipi | \
HVMPV_ex_processor_masks | \
HVMPV_no_vp_limit | \
HVMPV_cpu_hotplug)
#endif
/*
* Set mode for virtual timers (currently x86 only):
* delay_for_missed_ticks (default):
* Do not advance a vcpu's time beyond the correct delivery time for
* interrupts that have been missed due to preemption. Deliver missed
* interrupts when the vcpu is rescheduled and advance the vcpu's virtual
* time stepwise for each one.
* no_delay_for_missed_ticks:
* As above, missed interrupts are delivered, but guest time always tracks
* wallclock (i.e., real) time while doing so.
* no_missed_ticks_pending:
* No missed interrupts are held pending. Instead, to ensure ticks are
* delivered at some non-zero rate, if we detect missed ticks then the
* internal tick alarm is not disabled if the VCPU is preempted during the
* next tick period.
* one_missed_tick_pending:
* Missed interrupts are collapsed together and delivered as one 'late tick'.
* Guest time always tracks wallclock (i.e., real) time.
*/
#define HVM_PARAM_TIMER_MODE 10
#define HVMPTM_delay_for_missed_ticks 0
#define HVMPTM_no_delay_for_missed_ticks 1
#define HVMPTM_no_missed_ticks_pending 2
#define HVMPTM_one_missed_tick_pending 3
/* Boolean: Enable virtual HPET (high-precision event timer)? (x86-only) */
#define HVM_PARAM_HPET_ENABLED 11
/* Identity-map page directory used by Intel EPT when CR0.PG=0. */
#define HVM_PARAM_IDENT_PT 12
/* ACPI S state: currently support S0 and S3 on x86. */
#define HVM_PARAM_ACPI_S_STATE 14
/* TSS used on Intel when CR0.PE=0. */
#define HVM_PARAM_VM86_TSS 15
/* Boolean: Enable aligning all periodic vpts to reduce interrupts */
#define HVM_PARAM_VPT_ALIGN 16
/* Console debug shared memory ring and event channel */
#define HVM_PARAM_CONSOLE_PFN 17
#define HVM_PARAM_CONSOLE_EVTCHN 18
/*
* Select location of ACPI PM1a and TMR control blocks. Currently two locations
* are supported, specified by version 0 or 1 in this parameter:
* - 0: default, use the old addresses
* PM1A_EVT == 0x1f40; PM1A_CNT == 0x1f44; PM_TMR == 0x1f48
* - 1: use the new default qemu addresses
* PM1A_EVT == 0xb000; PM1A_CNT == 0xb004; PM_TMR == 0xb008
* You can find these address definitions in <hvm/ioreq.h>
*/
#define HVM_PARAM_ACPI_IOPORTS_LOCATION 19
/* Params for the mem event rings */
#define HVM_PARAM_PAGING_RING_PFN 27
#define HVM_PARAM_MONITOR_RING_PFN 28
#define HVM_PARAM_SHARING_RING_PFN 29
/* SHUTDOWN_* action in case of a triple fault */
#define HVM_PARAM_TRIPLE_FAULT_REASON 31
#define HVM_PARAM_IOREQ_SERVER_PFN 32
#define HVM_PARAM_NR_IOREQ_SERVER_PAGES 33
/* Location of the VM Generation ID in guest physical address space. */
#define HVM_PARAM_VM_GENERATION_ID_ADDR 34
/*
* Set mode for altp2m:
* disabled: don't activate altp2m (default)
* mixed: allow access to all altp2m ops for both in-guest and external tools
* external: allow access to external privileged tools only
* limited: guest only has limited access (ie. control VMFUNC and #VE)
*
* Note that 'mixed' mode has not been evaluated for safety from a
* security perspective. Before using this mode in a
* security-critical environment, each subop should be evaluated for
* safety, with unsafe subops blacklisted in XSM.
*/
#define HVM_PARAM_ALTP2M 35
#define XEN_ALTP2M_disabled 0
#define XEN_ALTP2M_mixed 1
#define XEN_ALTP2M_external 2
#define XEN_ALTP2M_limited 3
/*
* Size of the x87 FPU FIP/FDP registers that the hypervisor needs to
* save/restore. This is a workaround for a hardware limitation that
* does not allow the full FIP/FDP and FCS/FDS to be restored.
*
* Valid values are:
*
* 8: save/restore 64-bit FIP/FDP and clear FCS/FDS (default if CPU
* has FPCSDS feature).
*
* 4: save/restore 32-bit FIP/FDP, FCS/FDS, and clear upper 32-bits of
* FIP/FDP.
*
* 0: allow hypervisor to choose based on the value of FIP/FDP
* (default if CPU does not have FPCSDS).
*
* If FPCSDS (bit 13 in CPUID leaf 0x7, subleaf 0x0) is set, the CPU
* never saves FCS/FDS and this parameter should be left at the
* default of 8.
*/
#define HVM_PARAM_X87_FIP_WIDTH 36
/*
* TSS (and its size) used on Intel when CR0.PE=0. The address occupies
* the low 32 bits, while the size is in the high 32 ones.
*/
#define HVM_PARAM_VM86_TSS_SIZED 37
/* Enable MCA capabilities. */
#define HVM_PARAM_MCA_CAP 38
#define XEN_HVM_MCA_CAP_LMCE (xen_mk_ullong(1) << 0)
#define XEN_HVM_MCA_CAP_MASK XEN_HVM_MCA_CAP_LMCE
#define HVM_NR_PARAMS 39
#endif /* __XEN_PUBLIC_HVM_PARAMS_H__ */

14
include/hw/xen/interface/io/blkif.h
View File

@ -118,7 +118,7 @@
*
* The underlying storage is not affected by the direct IO memory
* lifetime bug. See:
* http://lists.xen.org/archives/html/xen-devel/2012-12/msg01154.html
* https://lists.xen.org/archives/html/xen-devel/2012-12/msg01154.html
*
* Therefore this option gives the backend permission to use
* O_DIRECT, notwithstanding that bug.
@ -341,7 +341,7 @@
* access (even when it should be read-only). If the frontend hits the
* maximum number of allowed persistently mapped grants, it can fallback
* to non persistent mode. This will cause a performance degradation,
* since the backend driver will still try to map those grants
* since the the backend driver will still try to map those grants
* persistently. Since the persistent grants protocol is compatible with
* the previous protocol, a frontend driver can choose to work in
* persistent mode even when the backend doesn't support it.
@ -710,3 +710,13 @@ DEFINE_RING_TYPES(blkif, struct blkif_request, struct blkif_response);
#define VDISK_READONLY 0x4
#endif /* __XEN_PUBLIC_IO_BLKIF_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

10
include/hw/xen/interface/io/console.h
View File

@ -44,3 +44,13 @@ DEFINE_XEN_FLEX_RING(xencons);
#endif
#endif /* __XEN_PUBLIC_IO_CONSOLE_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

20
include/hw/xen/interface/io/fbif.h
View File

@ -153,4 +153,24 @@ struct xenfb_page
unsigned long pd[256];
};
/*
* Wart: xenkbd needs to know default resolution. Put it here until a
* better solution is found, but don't leak it to the backend.
*/
#ifdef __KERNEL__
#define XENFB_WIDTH 800
#define XENFB_HEIGHT 600
#define XENFB_DEPTH 32
#endif
#endif
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

10
include/hw/xen/interface/io/kbdif.h
View File

@ -564,3 +564,13 @@ struct xenkbd_page
};
#endif /* __XEN_PUBLIC_IO_KBDIF_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

94
include/hw/xen/interface/io/netif.h
View File

@ -171,7 +171,7 @@
* The ability of the backend to use a control ring is advertised by
* setting:
*
* /local/domain/X/backend/<domid>/<vif>/feature-ctrl-ring = "1"
* /local/domain/X/backend/vif/<domid>/<vif>/feature-ctrl-ring = "1"
*
* The frontend provides a control ring to the backend by setting:
*
@ -190,6 +190,32 @@
* order as requests.
*/
/*
* Link state
* ==========
*
* The backend can advertise its current link (carrier) state to the
* frontend using the /local/domain/X/backend/vif/<domid>/<vif>/carrier
* node. If this node is not present, then the frontend should assume that
* the link is up (for compatibility with backends that do not implement
* this feature). If this node is present, then a value of "0" should be
* interpreted by the frontend as the link being down (no carrier) and a
* value of "1" should be interpreted as the link being up (carrier
* present).
*/
/*
* MTU
* ===
*
* The toolstack may set a value of MTU for the frontend by setting the
* /local/domain/<domid>/device/vif/<vif>/mtu node with the MTU value in
* octets. If this node is absent the frontend should assume an MTU value
* of 1500 octets. A frontend is also at liberty to ignore this value so
* it is only suitable for informing the frontend that a packet payload
* >1500 octets is permitted.
*/
/*
* Hash types
* ==========
@ -267,6 +293,62 @@
#define XEN_NETIF_CTRL_HASH_ALGORITHM_TOEPLITZ 1
/*
* This algorithm uses a 'key' as well as the data buffer itself.
* (Buffer[] and Key[] are treated as shift-registers where the MSB of
* Buffer/Key[0] is considered 'left-most' and the LSB of Buffer/Key[N-1]
* is the 'right-most').
*
* Value = 0
* For number of bits in Buffer[]
* If (left-most bit of Buffer[] is 1)
* Value ^= left-most 32 bits of Key[]
* Key[] << 1
* Buffer[] << 1
*
* The code below is provided for convenience where an operating system
* does not already provide an implementation.
*/
#ifdef XEN_NETIF_DEFINE_TOEPLITZ
static uint32_t xen_netif_toeplitz_hash(const uint8_t *key,
unsigned int keylen,
const uint8_t *buf,
unsigned int buflen)
{
unsigned int keyi, bufi;
uint64_t prefix = 0;
uint64_t hash = 0;
/* Pre-load prefix with the first 8 bytes of the key */
for (keyi = 0; keyi < 8; keyi++) {
prefix <<= 8;
prefix |= (keyi < keylen) ? key[keyi] : 0;
}
for (bufi = 0; bufi < buflen; bufi++) {
uint8_t byte = buf[bufi];
unsigned int bit;
for (bit = 0; bit < 8; bit++) {
if (byte & 0x80)
hash ^= prefix;
prefix <<= 1;
byte <<=1;
}
/*
* 'prefix' has now been left-shifted by 8, so
* OR in the next byte.
*/
prefix |= (keyi < keylen) ? key[keyi] : 0;
keyi++;
}
/* The valid part of the hash is in the upper 32 bits. */
return hash >> 32;
}
#endif /* XEN_NETIF_DEFINE_TOEPLITZ */
/*
* Control requests (struct xen_netif_ctrl_request)
* ================================================
@ -1008,3 +1090,13 @@ DEFINE_RING_TYPES(netif_rx, struct netif_rx_request, struct netif_rx_response);
#define NETIF_RSP_NULL 1
#endif
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

99
include/hw/xen/interface/io/ring.h
View File

@ -1,6 +1,6 @@
/******************************************************************************
* ring.h
*
*
* Shared producer-consumer ring macros.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
@ -33,13 +33,6 @@
* - standard integers types (uint8_t, uint16_t, etc)
* They are provided by stdint.h of the standard headers.
*
* Before using the different macros, you need to provide the following
* macros:
* - xen_mb() a memory barrier
* - xen_rmb() a read memory barrier
* - xen_wmb() a write memory barrier
* Example of those can be found in xenctrl.h.
*
* In addition, if you intend to use the FLEX macros, you also need to
* provide the following, before invoking the FLEX macros:
* - size_t
@ -49,6 +42,14 @@
* and grant_table.h from the Xen public headers.
*/
#include "../xen-compat.h"
#if __XEN_INTERFACE_VERSION__ < 0x00030208
#define xen_mb() mb()
#define xen_rmb() rmb()
#define xen_wmb() wmb()
#endif
typedef unsigned int RING_IDX;
/* Round a 32-bit unsigned constant down to the nearest power of two. */
@ -61,12 +62,12 @@ typedef unsigned int RING_IDX;
/*
* Calculate size of a shared ring, given the total available space for the
* ring and indexes (_sz), and the name tag of the request/response structure.
* A ring contains as many entries as will fit, rounded down to the nearest
* A ring contains as many entries as will fit, rounded down to the nearest
* power of two (so we can mask with (size-1) to loop around).
*/
#define __CONST_RING_SIZE(_s, _sz) \
(__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \
sizeof_field(struct _s##_sring, ring[0])))
sizeof(((struct _s##_sring *)0)->ring[0])))
/*
* The same for passing in an actual pointer instead of a name tag.
*/
@ -75,7 +76,7 @@ typedef unsigned int RING_IDX;
/*
* Macros to make the correct C datatypes for a new kind of ring.
*
*
* To make a new ring datatype, you need to have two message structures,
* let's say request_t, and response_t already defined.
*
@ -85,7 +86,7 @@ typedef unsigned int RING_IDX;
*
* These expand out to give you a set of types, as you can see below.
* The most important of these are:
*
*
* mytag_sring_t - The shared ring.
* mytag_front_ring_t - The 'front' half of the ring.
* mytag_back_ring_t - The 'back' half of the ring.
@ -153,15 +154,15 @@ typedef struct __name##_back_ring __name##_back_ring_t
/*
* Macros for manipulating rings.
*
* FRONT_RING_whatever works on the "front end" of a ring: here
*
* FRONT_RING_whatever works on the "front end" of a ring: here
* requests are pushed on to the ring and responses taken off it.
*
* BACK_RING_whatever works on the "back end" of a ring: here
*
* BACK_RING_whatever works on the "back end" of a ring: here
* requests are taken off the ring and responses put on.
*
* N.B. these macros do NO INTERLOCKS OR FLOW CONTROL.
* This is OK in 1-for-1 request-response situations where the
*
* N.B. these macros do NO INTERLOCKS OR FLOW CONTROL.
* This is OK in 1-for-1 request-response situations where the
* requestor (front end) never has more than RING_SIZE()-1
* outstanding requests.
*/
@ -174,20 +175,24 @@ typedef struct __name##_back_ring __name##_back_ring_t
(void)memset((_s)->__pad, 0, sizeof((_s)->__pad)); \
} while(0)
#define FRONT_RING_INIT(_r, _s, __size) do { \
(_r)->req_prod_pvt = 0; \
(_r)->rsp_cons = 0; \
#define FRONT_RING_ATTACH(_r, _s, _i, __size) do { \
(_r)->req_prod_pvt = (_i); \
(_r)->rsp_cons = (_i); \
(_r)->nr_ents = __RING_SIZE(_s, __size); \
(_r)->sring = (_s); \
} while (0)
#define BACK_RING_INIT(_r, _s, __size) do { \
(_r)->rsp_prod_pvt = 0; \
(_r)->req_cons = 0; \
#define FRONT_RING_INIT(_r, _s, __size) FRONT_RING_ATTACH(_r, _s, 0, __size)
#define BACK_RING_ATTACH(_r, _s, _i, __size) do { \
(_r)->rsp_prod_pvt = (_i); \
(_r)->req_cons = (_i); \
(_r)->nr_ents = __RING_SIZE(_s, __size); \
(_r)->sring = (_s); \
} while (0)
#define BACK_RING_INIT(_r, _s, __size) BACK_RING_ATTACH(_r, _s, 0, __size)
/* How big is this ring? */
#define RING_SIZE(_r) \
((_r)->nr_ents)
@ -206,33 +211,45 @@ typedef struct __name##_back_ring __name##_back_ring_t
#define RING_HAS_UNCONSUMED_RESPONSES(_r) \
((_r)->sring->rsp_prod - (_r)->rsp_cons)
#ifdef __GNUC__
#define RING_HAS_UNCONSUMED_REQUESTS(_r) ({ \
unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \
unsigned int rsp = RING_SIZE(_r) - \
((_r)->req_cons - (_r)->rsp_prod_pvt); \
req < rsp ? req : rsp; \
})
#else
/* Same as above, but without the nice GCC ({ ... }) syntax. */
#define RING_HAS_UNCONSUMED_REQUESTS(_r) \
((((_r)->sring->req_prod - (_r)->req_cons) < \
(RING_SIZE(_r) - ((_r)->req_cons - (_r)->rsp_prod_pvt))) ? \
((_r)->sring->req_prod - (_r)->req_cons) : \
(RING_SIZE(_r) - ((_r)->req_cons - (_r)->rsp_prod_pvt)))
#endif
/* Direct access to individual ring elements, by index. */
#define RING_GET_REQUEST(_r, _idx) \
(&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req))
#define RING_GET_RESPONSE(_r, _idx) \
(&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp))
/*
* Get a local copy of a request.
* Get a local copy of a request/response.
*
* Use this in preference to RING_GET_REQUEST() so all processing is
* Use this in preference to RING_GET_{REQUEST,RESPONSE}() so all processing is
* done on a local copy that cannot be modified by the other end.
*
* Note that https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 may cause this
* to be ineffective where _req is a struct which consists of only bitfields.
* to be ineffective where dest is a struct which consists of only bitfields.
*/
#define RING_COPY_REQUEST(_r, _idx, _req) do { \
/* Use volatile to force the copy into _req. */ \
*(_req) = *(volatile typeof(_req))RING_GET_REQUEST(_r, _idx); \
#define RING_COPY_(type, r, idx, dest) do { \
/* Use volatile to force the copy into dest. */ \
*(dest) = *(volatile __typeof__(dest))RING_GET_##type(r, idx); \
} while (0)
#define RING_GET_RESPONSE(_r, _idx) \
(&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp))
#define RING_COPY_REQUEST(r, idx, req) RING_COPY_(REQUEST, r, idx, req)
#define RING_COPY_RESPONSE(r, idx, rsp) RING_COPY_(RESPONSE, r, idx, rsp)
/* Loop termination condition: Would the specified index overflow the ring? */
#define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \
@ -242,6 +259,10 @@ typedef struct __name##_back_ring __name##_back_ring_t
#define RING_REQUEST_PROD_OVERFLOW(_r, _prod) \
(((_prod) - (_r)->rsp_prod_pvt) > RING_SIZE(_r))
/* Ill-behaved backend determination: Can there be this many responses? */
#define RING_RESPONSE_PROD_OVERFLOW(_r, _prod) \
(((_prod) - (_r)->rsp_cons) > RING_SIZE(_r))
#define RING_PUSH_REQUESTS(_r) do { \
xen_wmb(); /* back sees requests /before/ updated producer index */ \
(_r)->sring->req_prod = (_r)->req_prod_pvt; \
@ -254,26 +275,26 @@ typedef struct __name##_back_ring __name##_back_ring_t
/*
* Notification hold-off (req_event and rsp_event):
*
*
* When queueing requests or responses on a shared ring, it may not always be
* necessary to notify the remote end. For example, if requests are in flight
* in a backend, the front may be able to queue further requests without
* notifying the back (if the back checks for new requests when it queues
* responses).
*
*
* When enqueuing requests or responses:
*
*
* Use RING_PUSH_{REQUESTS,RESPONSES}_AND_CHECK_NOTIFY(). The second argument
* is a boolean return value. True indicates that the receiver requires an
* asynchronous notification.
*
*
* After dequeuing requests or responses (before sleeping the connection):
*
*
* Use RING_FINAL_CHECK_FOR_REQUESTS() or RING_FINAL_CHECK_FOR_RESPONSES().
* The second argument is a boolean return value. True indicates that there
* are pending messages on the ring (i.e., the connection should not be put
* to sleep).
*
*
* These macros will set the req_event/rsp_event field to trigger a
* notification on the very next message that is enqueued. If you want to
* create batches of work (i.e., only receive a notification after several

353
include/hw/xen/interface/io/usbif.h
View File

@ -32,6 +32,34 @@
#include "../grant_table.h"
/*
* Detailed Interface Description
* ==============================
* The pvUSB interface is using a split driver design: a frontend driver in
* the guest and a backend driver in a driver domain (normally dom0) having
* access to the physical USB device(s) being passed to the guest.
*
* The frontend and backend drivers use XenStore to initiate the connection
* between them, the I/O activity is handled via two shared ring pages and an
* event channel. As the interface between frontend and backend is at the USB
* host connector level, multiple (up to 31) physical USB devices can be
* handled by a single connection.
*
* The Xen pvUSB device name is "qusb", so the frontend's XenStore entries are
* to be found under "device/qusb", while the backend's XenStore entries are
* under "backend/<guest-dom-id>/qusb".
*
* When a new pvUSB connection is established, the frontend needs to setup the
* two shared ring pages for communication and the event channel. The ring
* pages need to be made available to the backend via the grant table
* interface.
*
* One of the shared ring pages is used by the backend to inform the frontend
* about USB device plug events (device to be added or removed). This is the
* "conn-ring".
*
* The other ring page is used for USB I/O communication (requests and
* responses). This is the "urb-ring".
*
* Feature and Parameter Negotiation
* =================================
* The two halves of a Xen pvUSB driver utilize nodes within the XenStore to
@ -99,130 +127,273 @@
* The machine ABI rules governing the format of all ring request and
* response structures.
*
* Protocol Description
* ====================
*
*-------------------------- USB device plug events --------------------------
*
* USB device plug events are send via the "conn-ring" shared page. As only
* events are being sent, the respective requests from the frontend to the
* backend are just dummy ones.
* The events sent to the frontend have the following layout:
* 0 1 2 3 octet
* +----------------+----------------+----------------+----------------+
* | id | portnum | speed | 4
* +----------------+----------------+----------------+----------------+
* id - uint16_t, event id (taken from the actual frontend dummy request)
* portnum - uint8_t, port number (1 ... 31)
* speed - uint8_t, device USBIF_SPEED_*, USBIF_SPEED_NONE == unplug
*
* The dummy request:
* 0 1 octet
* +----------------+----------------+
* | id | 2
* +----------------+----------------+
* id - uint16_t, guest supplied value (no need for being unique)
*
*-------------------------- USB I/O request ---------------------------------
*
* A single USB I/O request on the "urb-ring" has the following layout:
* 0 1 2 3 octet
* +----------------+----------------+----------------+----------------+
* | id | nr_buffer_segs | 4
* +----------------+----------------+----------------+----------------+
* | pipe | 8
* +----------------+----------------+----------------+----------------+
* | transfer_flags | buffer_length | 12
* +----------------+----------------+----------------+----------------+
* | request type specific | 16
* | data | 20
* +----------------+----------------+----------------+----------------+
* | seg[0] | 24
* | data | 28
* +----------------+----------------+----------------+----------------+
* |/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/\/|
* +----------------+----------------+----------------+----------------+
* | seg[USBIF_MAX_SEGMENTS_PER_REQUEST - 1] | 144
* | data | 148
* +----------------+----------------+----------------+----------------+
* Bit field bit number 0 is always least significant bit, undefined bits must
* be zero.
* id - uint16_t, guest supplied value
* nr_buffer_segs - uint16_t, number of segment entries in seg[] array
* pipe - uint32_t, bit field with multiple information:
* bits 0-4: port request to send to
* bit 5: unlink request with specified id (cancel I/O) if set (see below)
* bit 7: direction (1 = read from device)
* bits 8-14: device number on port
* bits 15-18: endpoint of device
* bits 30-31: request type: 00 = isochronous, 01 = interrupt,
* 10 = control, 11 = bulk
* transfer_flags - uint16_t, bit field with processing flags:
* bit 0: less data than specified allowed
* buffer_length - uint16_t, total length of data
* request type specific data - 8 bytes, see below
* seg[] - array with 8 byte elements, see below
*
* Request type specific data for isochronous request:
* 0 1 2 3 octet
* +----------------+----------------+----------------+----------------+
* | interval | start_frame | 4
* +----------------+----------------+----------------+----------------+
* | number_of_packets | nr_frame_desc_segs | 8
* +----------------+----------------+----------------+----------------+
* interval - uint16_t, time interval in msecs between frames
* start_frame - uint16_t, start frame number
* number_of_packets - uint16_t, number of packets to transfer
* nr_frame_desc_segs - uint16_t number of seg[] frame descriptors elements
*
* Request type specific data for interrupt request:
* 0 1 2 3 octet
* +----------------+----------------+----------------+----------------+
* | interval | 0 | 4
* +----------------+----------------+----------------+----------------+
* | 0 | 8
* +----------------+----------------+----------------+----------------+
* interval - uint16_t, time in msecs until interruption
*
* Request type specific data for control request:
* 0 1 2 3 octet
* +----------------+----------------+----------------+----------------+
* | data of setup packet | 4
* | | 8
* +----------------+----------------+----------------+----------------+
*
* Request type specific data for bulk request:
* 0 1 2 3 octet
* +----------------+----------------+----------------+----------------+
* | 0 | 4
* | 0 | 8
* +----------------+----------------+----------------+----------------+
*
* Request type specific data for unlink request:
* 0 1 2 3 octet
* +----------------+----------------+----------------+----------------+
* | unlink_id | 0 | 4
* +----------------+----------------+----------------+----------------+
* | 0 | 8
* +----------------+----------------+----------------+----------------+
* unlink_id - uint16_t, request id of request to terminate
*
* seg[] array element layout:
* 0 1 2 3 octet
* +----------------+----------------+----------------+----------------+
* | gref | 4
* +----------------+----------------+----------------+----------------+
* | offset | length | 8
* +----------------+----------------+----------------+----------------+
* gref - uint32_t, grant reference of buffer page
* offset - uint16_t, offset of buffer start in page
* length - uint16_t, length of buffer in page
*
*-------------------------- USB I/O response --------------------------------
*
* 0 1 2 3 octet
* +----------------+----------------+----------------+----------------+
* | id | start_frame | 4
* +----------------+----------------+----------------+----------------+
* | status | 8
* +----------------+----------------+----------------+----------------+
* | actual_length | 12
* +----------------+----------------+----------------+----------------+
* | error_count | 16
* +----------------+----------------+----------------+----------------+
* id - uint16_t, id of the request this response belongs to
* start_frame - uint16_t, start_frame this response (iso requests only)
* status - int32_t, USBIF_STATUS_* (non-iso requests)
* actual_length - uint32_t, actual size of data transferred
* error_count - uint32_t, number of errors (iso requests)
*/
enum usb_spec_version {
USB_VER_UNKNOWN = 0,
USB_VER_USB11,
USB_VER_USB20,
USB_VER_USB30, /* not supported yet */
USB_VER_UNKNOWN = 0,
USB_VER_USB11,
USB_VER_USB20,
USB_VER_USB30, /* not supported yet */
};
/*
* USB pipe in usbif_request
*
* - port number: bits 0-4
* (USB_MAXCHILDREN is 31)
* - port number: bits 0-4
* (USB_MAXCHILDREN is 31)
*
* - operation flag: bit 5
* (0 = submit urb,
* 1 = unlink urb)
* - operation flag: bit 5
* (0 = submit urb,
* 1 = unlink urb)
*
* - direction: bit 7
* (0 = Host-to-Device [Out]
* 1 = Device-to-Host [In])
* - direction: bit 7
* (0 = Host-to-Device [Out]
* 1 = Device-to-Host [In])
*
* - device address: bits 8-14
* - device address: bits 8-14
*
* - endpoint: bits 15-18
* - endpoint: bits 15-18
*
* - pipe type: bits 30-31
* (00 = isochronous, 01 = interrupt,
* 10 = control, 11 = bulk)
* - pipe type: bits 30-31
* (00 = isochronous, 01 = interrupt,
* 10 = control, 11 = bulk)
*/
#define USBIF_PIPE_PORT_MASK 0x0000001f
#define USBIF_PIPE_UNLINK 0x00000020
#define USBIF_PIPE_DIR 0x00000080
#define USBIF_PIPE_DEV_MASK 0x0000007f
#define USBIF_PIPE_DEV_SHIFT 8
#define USBIF_PIPE_EP_MASK 0x0000000f
#define USBIF_PIPE_EP_SHIFT 15
#define USBIF_PIPE_TYPE_MASK 0x00000003
#define USBIF_PIPE_TYPE_SHIFT 30
#define USBIF_PIPE_TYPE_ISOC 0
#define USBIF_PIPE_TYPE_INT 1
#define USBIF_PIPE_TYPE_CTRL 2
#define USBIF_PIPE_TYPE_BULK 3
#define USBIF_PIPE_PORT_MASK 0x0000001f
#define USBIF_PIPE_UNLINK 0x00000020
#define USBIF_PIPE_DIR 0x00000080
#define USBIF_PIPE_DEV_MASK 0x0000007f
#define USBIF_PIPE_DEV_SHIFT 8
#define USBIF_PIPE_EP_MASK 0x0000000f
#define USBIF_PIPE_EP_SHIFT 15
#define USBIF_PIPE_TYPE_MASK 0x00000003
#define USBIF_PIPE_TYPE_SHIFT 30
#define USBIF_PIPE_TYPE_ISOC 0
#define USBIF_PIPE_TYPE_INT 1
#define USBIF_PIPE_TYPE_CTRL 2
#define USBIF_PIPE_TYPE_BULK 3
#define usbif_pipeportnum(pipe) ((pipe) & USBIF_PIPE_PORT_MASK)
#define usbif_setportnum_pipe(pipe, portnum) ((pipe) | (portnum))
#define usbif_pipeportnum(pipe) ((pipe) & USBIF_PIPE_PORT_MASK)
#define usbif_setportnum_pipe(pipe, portnum) ((pipe) | (portnum))
#define usbif_pipeunlink(pipe) ((pipe) & USBIF_PIPE_UNLINK)
#define usbif_pipesubmit(pipe) (!usbif_pipeunlink(pipe))
#define usbif_setunlink_pipe(pipe) ((pipe) | USBIF_PIPE_UNLINK)
#define usbif_pipeunlink(pipe) ((pipe) & USBIF_PIPE_UNLINK)
#define usbif_pipesubmit(pipe) (!usbif_pipeunlink(pipe))
#define usbif_setunlink_pipe(pipe) ((pipe) | USBIF_PIPE_UNLINK)
#define usbif_pipein(pipe) ((pipe) & USBIF_PIPE_DIR)
#define usbif_pipeout(pipe) (!usbif_pipein(pipe))
#define usbif_pipein(pipe) ((pipe) & USBIF_PIPE_DIR)
#define usbif_pipeout(pipe) (!usbif_pipein(pipe))
#define usbif_pipedevice(pipe) \
(((pipe) >> USBIF_PIPE_DEV_SHIFT) & USBIF_PIPE_DEV_MASK)
#define usbif_pipedevice(pipe) \
(((pipe) >> USBIF_PIPE_DEV_SHIFT) & USBIF_PIPE_DEV_MASK)
#define usbif_pipeendpoint(pipe) \
(((pipe) >> USBIF_PIPE_EP_SHIFT) & USBIF_PIPE_EP_MASK)
#define usbif_pipeendpoint(pipe) \
(((pipe) >> USBIF_PIPE_EP_SHIFT) & USBIF_PIPE_EP_MASK)
#define usbif_pipetype(pipe) \
(((pipe) >> USBIF_PIPE_TYPE_SHIFT) & USBIF_PIPE_TYPE_MASK)
#define usbif_pipeisoc(pipe) (usbif_pipetype(pipe) == USBIF_PIPE_TYPE_ISOC)
#define usbif_pipeint(pipe) (usbif_pipetype(pipe) == USBIF_PIPE_TYPE_INT)
#define usbif_pipectrl(pipe) (usbif_pipetype(pipe) == USBIF_PIPE_TYPE_CTRL)
#define usbif_pipebulk(pipe) (usbif_pipetype(pipe) == USBIF_PIPE_TYPE_BULK)
#define usbif_pipetype(pipe) \
(((pipe) >> USBIF_PIPE_TYPE_SHIFT) & USBIF_PIPE_TYPE_MASK)
#define usbif_pipeisoc(pipe) (usbif_pipetype(pipe) == USBIF_PIPE_TYPE_ISOC)
#define usbif_pipeint(pipe) (usbif_pipetype(pipe) == USBIF_PIPE_TYPE_INT)
#define usbif_pipectrl(pipe) (usbif_pipetype(pipe) == USBIF_PIPE_TYPE_CTRL)
#define usbif_pipebulk(pipe) (usbif_pipetype(pipe) == USBIF_PIPE_TYPE_BULK)
#define USBIF_MAX_SEGMENTS_PER_REQUEST (16)
#define USBIF_MAX_PORTNR 31
#define USBIF_RING_SIZE 4096
#define USBIF_MAX_PORTNR 31
#define USBIF_RING_SIZE 4096
/*
* RING for transferring urbs.
*/
struct usbif_request_segment {
grant_ref_t gref;
uint16_t offset;
uint16_t length;
grant_ref_t gref;
uint16_t offset;
uint16_t length;
};
struct usbif_urb_request {
uint16_t id; /* request id */
uint16_t nr_buffer_segs; /* number of urb->transfer_buffer segments */
uint16_t id; /* request id */
uint16_t nr_buffer_segs; /* number of urb->transfer_buffer segments */
/* basic urb parameter */
uint32_t pipe;
uint16_t transfer_flags;
#define USBIF_SHORT_NOT_OK 0x0001
uint16_t buffer_length;
union {
uint8_t ctrl[8]; /* setup_packet (Ctrl) */
/* basic urb parameter */
uint32_t pipe;
uint16_t transfer_flags;
#define USBIF_SHORT_NOT_OK 0x0001
uint16_t buffer_length;
union {
uint8_t ctrl[8]; /* setup_packet (Ctrl) */
struct {
uint16_t interval; /* maximum (1024*8) in usb core */
uint16_t start_frame; /* start frame */
uint16_t number_of_packets; /* number of ISO packet */
uint16_t nr_frame_desc_segs; /* number of iso_frame_desc segments */
} isoc;
struct {
uint16_t interval; /* maximum (1024*8) in usb core */
uint16_t start_frame; /* start frame */
uint16_t number_of_packets; /* number of ISO packet */
uint16_t nr_frame_desc_segs; /* number of iso_frame_desc segments */
} isoc;
struct {
uint16_t interval; /* maximum (1024*8) in usb core */
uint16_t pad[3];
} intr;
struct {
uint16_t interval; /* maximum (1024*8) in usb core */
uint16_t pad[3];
} intr;
struct {
uint16_t unlink_id; /* unlink request id */
uint16_t pad[3];
} unlink;
struct {
uint16_t unlink_id; /* unlink request id */
uint16_t pad[3];
} unlink;
} u;
} u;
/* urb data segments */
struct usbif_request_segment seg[USBIF_MAX_SEGMENTS_PER_REQUEST];
/* urb data segments */
struct usbif_request_segment seg[USBIF_MAX_SEGMENTS_PER_REQUEST];
};
typedef struct usbif_urb_request usbif_urb_request_t;
struct usbif_urb_response {
uint16_t id; /* request id */
uint16_t start_frame; /* start frame (ISO) */
int32_t status; /* status (non-ISO) */
int32_t actual_length; /* actual transfer length */
int32_t error_count; /* number of ISO errors */
uint16_t id; /* request id */
uint16_t start_frame; /* start frame (ISO) */
int32_t status; /* status (non-ISO) */
#define USBIF_STATUS_OK 0
#define USBIF_STATUS_NODEV (-19)
#define USBIF_STATUS_INVAL (-22)
#define USBIF_STATUS_STALL (-32)
#define USBIF_STATUS_IOERROR (-71)
#define USBIF_STATUS_BABBLE (-75)
#define USBIF_STATUS_SHUTDOWN (-108)
int32_t actual_length; /* actual transfer length */
int32_t error_count; /* number of ISO errors */
};
typedef struct usbif_urb_response usbif_urb_response_t;
@ -233,18 +404,18 @@ DEFINE_RING_TYPES(usbif_urb, struct usbif_urb_request, struct usbif_urb_response
* RING for notifying connect/disconnect events to frontend
*/
struct usbif_conn_request {
uint16_t id;
uint16_t id;
};
typedef struct usbif_conn_request usbif_conn_request_t;
struct usbif_conn_response {
uint16_t id; /* request id */
uint8_t portnum; /* port number */
uint8_t speed; /* usb_device_speed */
#define USBIF_SPEED_NONE 0
#define USBIF_SPEED_LOW 1
#define USBIF_SPEED_FULL 2
#define USBIF_SPEED_HIGH 3
uint16_t id; /* request id */
uint8_t portnum; /* port number */
uint8_t speed; /* usb_device_speed */
#define USBIF_SPEED_NONE 0
#define USBIF_SPEED_LOW 1
#define USBIF_SPEED_FULL 2
#define USBIF_SPEED_HIGH 3
};
typedef struct usbif_conn_response usbif_conn_response_t;

10
include/hw/xen/interface/io/xenbus.h
View File

@ -68,3 +68,13 @@ enum xenbus_state {
typedef enum xenbus_state XenbusState;
#endif /* _XEN_PUBLIC_IO_XENBUS_H */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

153
include/hw/xen/interface/io/xs_wire.h Normal file
View File

@ -0,0 +1,153 @@
/*
* Details of the "wire" protocol between Xen Store Daemon and client
* library or guest kernel.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (C) 2005 Rusty Russell IBM Corporation
*/
#ifndef _XS_WIRE_H
#define _XS_WIRE_H
enum xsd_sockmsg_type
{
XS_CONTROL,
#define XS_DEBUG XS_CONTROL
XS_DIRECTORY,
XS_READ,
XS_GET_PERMS,
XS_WATCH,
XS_UNWATCH,
XS_TRANSACTION_START,
XS_TRANSACTION_END,
XS_INTRODUCE,
XS_RELEASE,
XS_GET_DOMAIN_PATH,
XS_WRITE,
XS_MKDIR,
XS_RM,
XS_SET_PERMS,
XS_WATCH_EVENT,
XS_ERROR,
XS_IS_DOMAIN_INTRODUCED,
XS_RESUME,
XS_SET_TARGET,
/* XS_RESTRICT has been removed */
XS_RESET_WATCHES = XS_SET_TARGET + 2,
XS_DIRECTORY_PART,
XS_TYPE_COUNT, /* Number of valid types. */
XS_INVALID = 0xffff /* Guaranteed to remain an invalid type */
};
#define XS_WRITE_NONE "NONE"
#define XS_WRITE_CREATE "CREATE"
#define XS_WRITE_CREATE_EXCL "CREATE|EXCL"
/* We hand errors as strings, for portability. */
struct xsd_errors
{
int errnum;
const char *errstring;
};
#ifdef EINVAL
#define XSD_ERROR(x) { x, #x }
/* LINTED: static unused */
static struct xsd_errors xsd_errors[]
#if defined(__GNUC__)
__attribute__((unused))
#endif
= {
XSD_ERROR(EINVAL),
XSD_ERROR(EACCES),
XSD_ERROR(EEXIST),
XSD_ERROR(EISDIR),
XSD_ERROR(ENOENT),
XSD_ERROR(ENOMEM),
XSD_ERROR(ENOSPC),
XSD_ERROR(EIO),
XSD_ERROR(ENOTEMPTY),
XSD_ERROR(ENOSYS),
XSD_ERROR(EROFS),
XSD_ERROR(EBUSY),
XSD_ERROR(EAGAIN),
XSD_ERROR(EISCONN),
XSD_ERROR(E2BIG)
};
#endif
struct xsd_sockmsg
{
uint32_t type; /* XS_??? */
uint32_t req_id;/* Request identifier, echoed in daemon's response. */
uint32_t tx_id; /* Transaction id (0 if not related to a transaction). */
uint32_t len; /* Length of data following this. */
/* Generally followed by nul-terminated string(s). */
};
enum xs_watch_type
{
XS_WATCH_PATH = 0,
XS_WATCH_TOKEN
};
/*
* `incontents 150 xenstore_struct XenStore wire protocol.
*
* Inter-domain shared memory communications. */
#define XENSTORE_RING_SIZE 1024
typedef uint32_t XENSTORE_RING_IDX;
#define MASK_XENSTORE_IDX(idx) ((idx) & (XENSTORE_RING_SIZE-1))
struct xenstore_domain_interface {
char req[XENSTORE_RING_SIZE]; /* Requests to xenstore daemon. */
char rsp[XENSTORE_RING_SIZE]; /* Replies and async watch events. */
XENSTORE_RING_IDX req_cons, req_prod;
XENSTORE_RING_IDX rsp_cons, rsp_prod;
uint32_t server_features; /* Bitmap of features supported by the server */
uint32_t connection;
};
/* Violating this is very bad. See docs/misc/xenstore.txt. */
#define XENSTORE_PAYLOAD_MAX 4096
/* Violating these just gets you an error back */
#define XENSTORE_ABS_PATH_MAX 3072
#define XENSTORE_REL_PATH_MAX 2048
/* The ability to reconnect a ring */
#define XENSTORE_SERVER_FEATURE_RECONNECTION 1
/* Valid values for the connection field */
#define XENSTORE_CONNECTED 0 /* the steady-state */
#define XENSTORE_RECONNECT 1 /* guest has initiated a reconnect */
#endif /* _XS_WIRE_H */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

754
include/hw/xen/interface/memory.h Normal file
View File

@ -0,0 +1,754 @@
/******************************************************************************
* memory.h
*
* Memory reservation and information.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2005, Keir Fraser <keir@xensource.com>
*/
#ifndef __XEN_PUBLIC_MEMORY_H__
#define __XEN_PUBLIC_MEMORY_H__
#include "xen.h"
#include "physdev.h"
/*
* Increase or decrease the specified domain's memory reservation. Returns the
* number of extents successfully allocated or freed.
* arg == addr of struct xen_memory_reservation.
*/
#define XENMEM_increase_reservation 0
#define XENMEM_decrease_reservation 1
#define XENMEM_populate_physmap 6
#if __XEN_INTERFACE_VERSION__ >= 0x00030209
/*
* Maximum # bits addressable by the user of the allocated region (e.g., I/O
* devices often have a 32-bit limitation even in 64-bit systems). If zero
* then the user has no addressing restriction. This field is not used by
* XENMEM_decrease_reservation.
*/
#define XENMEMF_address_bits(x) (x)
#define XENMEMF_get_address_bits(x) ((x) & 0xffu)
/* NUMA node to allocate from. */
#define XENMEMF_node(x) (((x) + 1) << 8)
#define XENMEMF_get_node(x) ((((x) >> 8) - 1) & 0xffu)
/* Flag to populate physmap with populate-on-demand entries */
#define XENMEMF_populate_on_demand (1<<16)
/* Flag to request allocation only from the node specified */
#define XENMEMF_exact_node_request (1<<17)
#define XENMEMF_exact_node(n) (XENMEMF_node(n) | XENMEMF_exact_node_request)
/* Flag to indicate the node specified is virtual node */
#define XENMEMF_vnode (1<<18)
#endif
struct xen_memory_reservation {
/*
* XENMEM_increase_reservation:
* OUT: MFN (*not* GMFN) bases of extents that were allocated
* XENMEM_decrease_reservation:
* IN: GMFN bases of extents to free
* XENMEM_populate_physmap:
* IN: GPFN bases of extents to populate with memory
* OUT: GMFN bases of extents that were allocated
* (NB. This command also updates the mach_to_phys translation table)
* XENMEM_claim_pages:
* IN: must be zero
*/
XEN_GUEST_HANDLE(xen_pfn_t) extent_start;
/* Number of extents, and size/alignment of each (2^extent_order pages). */
xen_ulong_t nr_extents;
unsigned int extent_order;
#if __XEN_INTERFACE_VERSION__ >= 0x00030209
/* XENMEMF flags. */
unsigned int mem_flags;
#else
unsigned int address_bits;
#endif
/*
* Domain whose reservation is being changed.
* Unprivileged domains can specify only DOMID_SELF.
*/
domid_t domid;
};
typedef struct xen_memory_reservation xen_memory_reservation_t;
DEFINE_XEN_GUEST_HANDLE(xen_memory_reservation_t);
/*
* An atomic exchange of memory pages. If return code is zero then
* @out.extent_list provides GMFNs of the newly-allocated memory.
* Returns zero on complete success, otherwise a negative error code.
* On complete success then always @nr_exchanged == @in.nr_extents.
* On partial success @nr_exchanged indicates how much work was done.
*
* Note that only PV guests can use this operation.
*/
#define XENMEM_exchange 11
struct xen_memory_exchange {
/*
* [IN] Details of memory extents to be exchanged (GMFN bases).
* Note that @in.address_bits is ignored and unused.
*/
struct xen_memory_reservation in;
/*
* [IN/OUT] Details of new memory extents.
* We require that:
* 1. @in.domid == @out.domid
* 2. @in.nr_extents << @in.extent_order ==
* @out.nr_extents << @out.extent_order
* 3. @in.extent_start and @out.extent_start lists must not overlap
* 4. @out.extent_start lists GPFN bases to be populated
* 5. @out.extent_start is overwritten with allocated GMFN bases
*/
struct xen_memory_reservation out;
/*
* [OUT] Number of input extents that were successfully exchanged:
* 1. The first @nr_exchanged input extents were successfully
* deallocated.
* 2. The corresponding first entries in the output extent list correctly
* indicate the GMFNs that were successfully exchanged.
* 3. All other input and output extents are untouched.
* 4. If not all input exents are exchanged then the return code of this
* command will be non-zero.
* 5. THIS FIELD MUST BE INITIALISED TO ZERO BY THE CALLER!
*/
xen_ulong_t nr_exchanged;
};
typedef struct xen_memory_exchange xen_memory_exchange_t;
DEFINE_XEN_GUEST_HANDLE(xen_memory_exchange_t);
/*
* Returns the maximum machine frame number of mapped RAM in this system.
* This command always succeeds (it never returns an error code).
* arg == NULL.
*/
#define XENMEM_maximum_ram_page 2
struct xen_memory_domain {
/* [IN] Domain information is being queried for. */
domid_t domid;
};
/*
* Returns the current or maximum memory reservation, in pages, of the
* specified domain (may be DOMID_SELF). Returns -ve errcode on failure.
* arg == addr of struct xen_memory_domain.
*/
#define XENMEM_current_reservation 3
#define XENMEM_maximum_reservation 4
/*
* Returns the maximum GFN in use by the specified domain (may be DOMID_SELF).
* Returns -ve errcode on failure.
* arg == addr of struct xen_memory_domain.
*/
#define XENMEM_maximum_gpfn 14
/*
* Returns a list of MFN bases of 2MB extents comprising the machine_to_phys
* mapping table. Architectures which do not have a m2p table do not implement
* this command.
* arg == addr of xen_machphys_mfn_list_t.
*/
#define XENMEM_machphys_mfn_list 5
struct xen_machphys_mfn_list {
/*
* Size of the 'extent_start' array. Fewer entries will be filled if the
* machphys table is smaller than max_extents * 2MB.
*/
unsigned int max_extents;
/*
* Pointer to buffer to fill with list of extent starts. If there are
* any large discontiguities in the machine address space, 2MB gaps in
* the machphys table will be represented by an MFN base of zero.
*/
XEN_GUEST_HANDLE(xen_pfn_t) extent_start;
/*
* Number of extents written to the above array. This will be smaller
* than 'max_extents' if the machphys table is smaller than max_e * 2MB.
*/
unsigned int nr_extents;
};
typedef struct xen_machphys_mfn_list xen_machphys_mfn_list_t;
DEFINE_XEN_GUEST_HANDLE(xen_machphys_mfn_list_t);
/*
* For a compat caller, this is identical to XENMEM_machphys_mfn_list.
*
* For a non compat caller, this functions similarly to
* XENMEM_machphys_mfn_list, but returns the mfns making up the compatibility
* m2p table.
*/
#define XENMEM_machphys_compat_mfn_list 25
/*
* Returns the location in virtual address space of the machine_to_phys
* mapping table. Architectures which do not have a m2p table, or which do not
* map it by default into guest address space, do not implement this command.
* arg == addr of xen_machphys_mapping_t.
*/
#define XENMEM_machphys_mapping 12
struct xen_machphys_mapping {
xen_ulong_t v_start, v_end; /* Start and end virtual addresses. */
xen_ulong_t max_mfn; /* Maximum MFN that can be looked up. */
};
typedef struct xen_machphys_mapping xen_machphys_mapping_t;
DEFINE_XEN_GUEST_HANDLE(xen_machphys_mapping_t);
/* Source mapping space. */
/* ` enum phys_map_space { */
#define XENMAPSPACE_shared_info 0 /* shared info page */
#define XENMAPSPACE_grant_table 1 /* grant table page */
#define XENMAPSPACE_gmfn 2 /* GMFN */
#define XENMAPSPACE_gmfn_range 3 /* GMFN range, XENMEM_add_to_physmap only. */
#define XENMAPSPACE_gmfn_foreign 4 /* GMFN from another dom,
* XENMEM_add_to_physmap_batch only. */
#define XENMAPSPACE_dev_mmio 5 /* device mmio region
ARM only; the region is mapped in
Stage-2 using the Normal Memory
Inner/Outer Write-Back Cacheable
memory attribute. */
/* ` } */
/*
* Sets the GPFN at which a particular page appears in the specified guest's
* physical address space (translated guests only).
* arg == addr of xen_add_to_physmap_t.
*/
#define XENMEM_add_to_physmap 7
struct xen_add_to_physmap {
/* Which domain to change the mapping for. */
domid_t domid;
/* Number of pages to go through for gmfn_range */
uint16_t size;
unsigned int space; /* => enum phys_map_space */
#define XENMAPIDX_grant_table_status 0x80000000
/* Index into space being mapped. */
xen_ulong_t idx;
/* GPFN in domid where the source mapping page should appear. */
xen_pfn_t gpfn;
};
typedef struct xen_add_to_physmap xen_add_to_physmap_t;
DEFINE_XEN_GUEST_HANDLE(xen_add_to_physmap_t);
/* A batched version of add_to_physmap. */
#define XENMEM_add_to_physmap_batch 23
struct xen_add_to_physmap_batch {
/* IN */
/* Which domain to change the mapping for. */
domid_t domid;
uint16_t space; /* => enum phys_map_space */
/* Number of pages to go through */
uint16_t size;
#if __XEN_INTERFACE_VERSION__ < 0x00040700
domid_t foreign_domid; /* IFF gmfn_foreign. Should be 0 for other spaces. */
#else
union xen_add_to_physmap_batch_extra {
domid_t foreign_domid; /* gmfn_foreign */
uint16_t res0; /* All the other spaces. Should be 0 */
} u;
#endif
/* Indexes into space being mapped. */
XEN_GUEST_HANDLE(xen_ulong_t) idxs;
/* GPFN in domid where the source mapping page should appear. */
XEN_GUEST_HANDLE(xen_pfn_t) gpfns;
/* OUT */
/* Per index error code. */
XEN_GUEST_HANDLE(int) errs;
};
typedef struct xen_add_to_physmap_batch xen_add_to_physmap_batch_t;
DEFINE_XEN_GUEST_HANDLE(xen_add_to_physmap_batch_t);
#if __XEN_INTERFACE_VERSION__ < 0x00040400
#define XENMEM_add_to_physmap_range XENMEM_add_to_physmap_batch
#define xen_add_to_physmap_range xen_add_to_physmap_batch
typedef struct xen_add_to_physmap_batch xen_add_to_physmap_range_t;
DEFINE_XEN_GUEST_HANDLE(xen_add_to_physmap_range_t);
#endif
/*
* Unmaps the page appearing at a particular GPFN from the specified guest's
* physical address space (translated guests only).
* arg == addr of xen_remove_from_physmap_t.
*/
#define XENMEM_remove_from_physmap 15
struct xen_remove_from_physmap {
/* Which domain to change the mapping for. */
domid_t domid;
/* GPFN of the current mapping of the page. */
xen_pfn_t gpfn;
};
typedef struct xen_remove_from_physmap xen_remove_from_physmap_t;
DEFINE_XEN_GUEST_HANDLE(xen_remove_from_physmap_t);
/*** REMOVED ***/
/*#define XENMEM_translate_gpfn_list 8*/
/*
* Returns the pseudo-physical memory map as it was when the domain
* was started (specified by XENMEM_set_memory_map).
* arg == addr of xen_memory_map_t.
*/
#define XENMEM_memory_map 9
struct xen_memory_map {
/*
* On call the number of entries which can be stored in buffer. On
* return the number of entries which have been stored in
* buffer.
*/
unsigned int nr_entries;
/*
* Entries in the buffer are in the same format as returned by the
* BIOS INT 0x15 EAX=0xE820 call.
*/
XEN_GUEST_HANDLE(void) buffer;
};
typedef struct xen_memory_map xen_memory_map_t;
DEFINE_XEN_GUEST_HANDLE(xen_memory_map_t);
/*
* Returns the real physical memory map. Passes the same structure as
* XENMEM_memory_map.
* Specifying buffer as NULL will return the number of entries required
* to store the complete memory map.
* arg == addr of xen_memory_map_t.
*/
#define XENMEM_machine_memory_map 10
/*
* Set the pseudo-physical memory map of a domain, as returned by
* XENMEM_memory_map.
* arg == addr of xen_foreign_memory_map_t.
*/
#define XENMEM_set_memory_map 13
struct xen_foreign_memory_map {
domid_t domid;
struct xen_memory_map map;
};
typedef struct xen_foreign_memory_map xen_foreign_memory_map_t;
DEFINE_XEN_GUEST_HANDLE(xen_foreign_memory_map_t);
#define XENMEM_set_pod_target 16
#define XENMEM_get_pod_target 17
struct xen_pod_target {
/* IN */
uint64_t target_pages;
/* OUT */
uint64_t tot_pages;
uint64_t pod_cache_pages;
uint64_t pod_entries;
/* IN */
domid_t domid;
};
typedef struct xen_pod_target xen_pod_target_t;
#if defined(__XEN__) || defined(__XEN_TOOLS__)
#ifndef uint64_aligned_t
#define uint64_aligned_t uint64_t
#endif
/*
* Get the number of MFNs saved through memory sharing.
* The call never fails.
*/
#define XENMEM_get_sharing_freed_pages 18
#define XENMEM_get_sharing_shared_pages 19
#define XENMEM_paging_op 20
#define XENMEM_paging_op_nominate 0
#define XENMEM_paging_op_evict 1
#define XENMEM_paging_op_prep 2
struct xen_mem_paging_op {
uint8_t op; /* XENMEM_paging_op_* */
domid_t domain;
/* IN: (XENMEM_paging_op_prep) buffer to immediately fill page from */
XEN_GUEST_HANDLE_64(const_uint8) buffer;
/* IN: gfn of page being operated on */
uint64_aligned_t gfn;
};
typedef struct xen_mem_paging_op xen_mem_paging_op_t;
DEFINE_XEN_GUEST_HANDLE(xen_mem_paging_op_t);
#define XENMEM_access_op 21
#define XENMEM_access_op_set_access 0
#define XENMEM_access_op_get_access 1
/*
* XENMEM_access_op_enable_emulate and XENMEM_access_op_disable_emulate are
* currently unused, but since they have been in use please do not reuse them.
*
* #define XENMEM_access_op_enable_emulate 2
* #define XENMEM_access_op_disable_emulate 3
*/
#define XENMEM_access_op_set_access_multi 4
typedef enum {
XENMEM_access_n,
XENMEM_access_r,
XENMEM_access_w,
XENMEM_access_rw,
XENMEM_access_x,
XENMEM_access_rx,
XENMEM_access_wx,
XENMEM_access_rwx,
/*
* Page starts off as r-x, but automatically
* change to r-w on a write
*/
XENMEM_access_rx2rw,
/*
* Log access: starts off as n, automatically
* goes to rwx, generating an event without
* pausing the vcpu
*/
XENMEM_access_n2rwx,
/* Take the domain default */
XENMEM_access_default
} xenmem_access_t;
struct xen_mem_access_op {
/* XENMEM_access_op_* */
uint8_t op;
/* xenmem_access_t */
uint8_t access;
domid_t domid;
/*
* Number of pages for set op (or size of pfn_list for
* XENMEM_access_op_set_access_multi)
* Ignored on setting default access and other ops
*/
uint32_t nr;
/*
* First pfn for set op
* pfn for get op
* ~0ull is used to set and get the default access for pages
*/
uint64_aligned_t pfn;
/*
* List of pfns to set access for
* Used only with XENMEM_access_op_set_access_multi
*/
XEN_GUEST_HANDLE(const_uint64) pfn_list;
/*
* Corresponding list of access settings for pfn_list
* Used only with XENMEM_access_op_set_access_multi
*/
XEN_GUEST_HANDLE(const_uint8) access_list;
};
typedef struct xen_mem_access_op xen_mem_access_op_t;
DEFINE_XEN_GUEST_HANDLE(xen_mem_access_op_t);
#define XENMEM_sharing_op 22
#define XENMEM_sharing_op_nominate_gfn 0
#define XENMEM_sharing_op_nominate_gref 1
#define XENMEM_sharing_op_share 2
#define XENMEM_sharing_op_debug_gfn 3
#define XENMEM_sharing_op_debug_mfn 4
#define XENMEM_sharing_op_debug_gref 5
#define XENMEM_sharing_op_add_physmap 6
#define XENMEM_sharing_op_audit 7
#define XENMEM_sharing_op_range_share 8
#define XENMEM_sharing_op_fork 9
#define XENMEM_sharing_op_fork_reset 10
#define XENMEM_SHARING_OP_S_HANDLE_INVALID (-10)
#define XENMEM_SHARING_OP_C_HANDLE_INVALID (-9)
/* The following allows sharing of grant refs. This is useful
* for sharing utilities sitting as "filters" in IO backends
* (e.g. memshr + blktap(2)). The IO backend is only exposed
* to grant references, and this allows sharing of the grefs */
#define XENMEM_SHARING_OP_FIELD_IS_GREF_FLAG (xen_mk_ullong(1) << 62)
#define XENMEM_SHARING_OP_FIELD_MAKE_GREF(field, val) \
(field) = (XENMEM_SHARING_OP_FIELD_IS_GREF_FLAG | val)
#define XENMEM_SHARING_OP_FIELD_IS_GREF(field) \
((field) & XENMEM_SHARING_OP_FIELD_IS_GREF_FLAG)
#define XENMEM_SHARING_OP_FIELD_GET_GREF(field) \
((field) & (~XENMEM_SHARING_OP_FIELD_IS_GREF_FLAG))
struct xen_mem_sharing_op {
uint8_t op; /* XENMEM_sharing_op_* */
domid_t domain;
union {
struct mem_sharing_op_nominate { /* OP_NOMINATE_xxx */
union {
uint64_aligned_t gfn; /* IN: gfn to nominate */
uint32_t grant_ref; /* IN: grant ref to nominate */
} u;
uint64_aligned_t handle; /* OUT: the handle */
} nominate;
struct mem_sharing_op_share { /* OP_SHARE/ADD_PHYSMAP */
uint64_aligned_t source_gfn; /* IN: the gfn of the source page */
uint64_aligned_t source_handle; /* IN: handle to the source page */
uint64_aligned_t client_gfn; /* IN: the client gfn */
uint64_aligned_t client_handle; /* IN: handle to the client page */
domid_t client_domain; /* IN: the client domain id */
} share;
struct mem_sharing_op_range { /* OP_RANGE_SHARE */
uint64_aligned_t first_gfn; /* IN: the first gfn */
uint64_aligned_t last_gfn; /* IN: the last gfn */
uint64_aligned_t opaque; /* Must be set to 0 */
domid_t client_domain; /* IN: the client domain id */
uint16_t _pad[3]; /* Must be set to 0 */
} range;
struct mem_sharing_op_debug { /* OP_DEBUG_xxx */
union {
uint64_aligned_t gfn; /* IN: gfn to debug */
uint64_aligned_t mfn; /* IN: mfn to debug */
uint32_t gref; /* IN: gref to debug */
} u;
} debug;
struct mem_sharing_op_fork { /* OP_FORK */
domid_t parent_domain; /* IN: parent's domain id */
/* Only makes sense for short-lived forks */
#define XENMEM_FORK_WITH_IOMMU_ALLOWED (1u << 0)
/* Only makes sense for short-lived forks */
#define XENMEM_FORK_BLOCK_INTERRUPTS (1u << 1)
uint16_t flags; /* IN: optional settings */
uint32_t pad; /* Must be set to 0 */
} fork;
} u;
};
typedef struct xen_mem_sharing_op xen_mem_sharing_op_t;
DEFINE_XEN_GUEST_HANDLE(xen_mem_sharing_op_t);
/*
* Attempt to stake a claim for a domain on a quantity of pages
* of system RAM, but _not_ assign specific pageframes. Only
* arithmetic is performed so the hypercall is very fast and need
* not be preemptible, thus sidestepping time-of-check-time-of-use
* races for memory allocation. Returns 0 if the hypervisor page
* allocator has atomically and successfully claimed the requested
* number of pages, else non-zero.
*
* Any domain may have only one active claim. When sufficient memory
* has been allocated to resolve the claim, the claim silently expires.
* Claiming zero pages effectively resets any outstanding claim and
* is always successful.
*
* Note that a valid claim may be staked even after memory has been
* allocated for a domain. In this case, the claim is not incremental,
* i.e. if the domain's total page count is 3, and a claim is staked
* for 10, only 7 additional pages are claimed.
*
* Caller must be privileged or the hypercall fails.
*/
#define XENMEM_claim_pages 24
/*
* XENMEM_claim_pages flags - the are no flags at this time.
* The zero value is appropriate.
*/
/*
* With some legacy devices, certain guest-physical addresses cannot safely
* be used for other purposes, e.g. to map guest RAM. This hypercall
* enumerates those regions so the toolstack can avoid using them.
*/
#define XENMEM_reserved_device_memory_map 27
struct xen_reserved_device_memory {
xen_pfn_t start_pfn;
xen_ulong_t nr_pages;
};
typedef struct xen_reserved_device_memory xen_reserved_device_memory_t;
DEFINE_XEN_GUEST_HANDLE(xen_reserved_device_memory_t);
struct xen_reserved_device_memory_map {
#define XENMEM_RDM_ALL 1 /* Request all regions (ignore dev union). */
/* IN */
uint32_t flags;
/*
* IN/OUT
*
* Gets set to the required number of entries when too low,
* signaled by error code -ERANGE.
*/
unsigned int nr_entries;
/* OUT */
XEN_GUEST_HANDLE(xen_reserved_device_memory_t) buffer;
/* IN */
union {
physdev_pci_device_t pci;
} dev;
};
typedef struct xen_reserved_device_memory_map xen_reserved_device_memory_map_t;
DEFINE_XEN_GUEST_HANDLE(xen_reserved_device_memory_map_t);
#endif /* defined(__XEN__) || defined(__XEN_TOOLS__) */
/*
* Get the pages for a particular guest resource, so that they can be
* mapped directly by a tools domain.
*/
#define XENMEM_acquire_resource 28
struct xen_mem_acquire_resource {
/* IN - The domain whose resource is to be mapped */
domid_t domid;
/* IN - the type of resource */
uint16_t type;
#define XENMEM_resource_ioreq_server 0
#define XENMEM_resource_grant_table 1
#define XENMEM_resource_vmtrace_buf 2
/*
* IN - a type-specific resource identifier, which must be zero
* unless stated otherwise.
*
* type == XENMEM_resource_ioreq_server -> id == ioreq server id
* type == XENMEM_resource_grant_table -> id defined below
*/
uint32_t id;
#define XENMEM_resource_grant_table_id_shared 0
#define XENMEM_resource_grant_table_id_status 1
/*
* IN/OUT
*
* As an IN parameter number of frames of the resource to be mapped.
* This value may be updated over the course of the operation.
*
* When frame_list is NULL and nr_frames is 0, this is interpreted as a
* request for the size of the resource, which shall be returned in the
* nr_frames field.
*
* The size of a resource will never be zero, but a nonzero result doesn't
* guarantee that a subsequent mapping request will be successful. There
* are further type/id specific constraints which may change between the
* two calls.
*/
uint32_t nr_frames;
uint32_t pad;
/*
* IN - the index of the initial frame to be mapped. This parameter
* is ignored if nr_frames is 0. This value may be updated
* over the course of the operation.
*/
uint64_t frame;
#define XENMEM_resource_ioreq_server_frame_bufioreq 0
#define XENMEM_resource_ioreq_server_frame_ioreq(n) (1 + (n))
/*
* IN/OUT - If the tools domain is PV then, upon return, frame_list
* will be populated with the MFNs of the resource.
* If the tools domain is HVM then it is expected that, on
* entry, frame_list will be populated with a list of GFNs
* that will be mapped to the MFNs of the resource.
* If -EIO is returned then the frame_list has only been
* partially mapped and it is up to the caller to unmap all
* the GFNs.
* This parameter may be NULL if nr_frames is 0. This
* value may be updated over the course of the operation.
*/
XEN_GUEST_HANDLE(xen_pfn_t) frame_list;
};
typedef struct xen_mem_acquire_resource xen_mem_acquire_resource_t;
DEFINE_XEN_GUEST_HANDLE(xen_mem_acquire_resource_t);
/*
* XENMEM_get_vnumainfo used by guest to get
* vNUMA topology from hypervisor.
*/
#define XENMEM_get_vnumainfo 26
/* vNUMA node memory ranges */
struct xen_vmemrange {
uint64_t start, end;
unsigned int flags;
unsigned int nid;
};
typedef struct xen_vmemrange xen_vmemrange_t;
DEFINE_XEN_GUEST_HANDLE(xen_vmemrange_t);
/*
* vNUMA topology specifies vNUMA node number, distance table,
* memory ranges and vcpu mapping provided for guests.
* XENMEM_get_vnumainfo hypercall expects to see from guest
* nr_vnodes, nr_vmemranges and nr_vcpus to indicate available memory.
* After filling guests structures, nr_vnodes, nr_vmemranges and nr_vcpus
* copied back to guest. Domain returns expected values of nr_vnodes,
* nr_vmemranges and nr_vcpus to guest if the values where incorrect.
*/
struct xen_vnuma_topology_info {
/* IN */
domid_t domid;
uint16_t pad;
/* IN/OUT */
unsigned int nr_vnodes;
unsigned int nr_vcpus;
unsigned int nr_vmemranges;
/* OUT */
union {
XEN_GUEST_HANDLE(uint) h;
uint64_t pad;
} vdistance;
union {
XEN_GUEST_HANDLE(uint) h;
uint64_t pad;
} vcpu_to_vnode;
union {
XEN_GUEST_HANDLE(xen_vmemrange_t) h;
uint64_t pad;
} vmemrange;
};
typedef struct xen_vnuma_topology_info xen_vnuma_topology_info_t;
DEFINE_XEN_GUEST_HANDLE(xen_vnuma_topology_info_t);
/* Next available subop number is 29 */
#endif /* __XEN_PUBLIC_MEMORY_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

383
include/hw/xen/interface/physdev.h Normal file
View File

@ -0,0 +1,383 @@
/*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2006, Keir Fraser
*/
#ifndef __XEN_PUBLIC_PHYSDEV_H__
#define __XEN_PUBLIC_PHYSDEV_H__
#include "xen.h"
/*
* Prototype for this hypercall is:
* int physdev_op(int cmd, void *args)
* @cmd == PHYSDEVOP_??? (physdev operation).
* @args == Operation-specific extra arguments (NULL if none).
*/
/*
* Notify end-of-interrupt (EOI) for the specified IRQ.
* @arg == pointer to physdev_eoi structure.
*/
#define PHYSDEVOP_eoi 12
struct physdev_eoi {
/* IN */
uint32_t irq;
};
typedef struct physdev_eoi physdev_eoi_t;
DEFINE_XEN_GUEST_HANDLE(physdev_eoi_t);
/*
* Register a shared page for the hypervisor to indicate whether the guest
* must issue PHYSDEVOP_eoi. The semantics of PHYSDEVOP_eoi change slightly
* once the guest used this function in that the associated event channel
* will automatically get unmasked. The page registered is used as a bit
* array indexed by Xen's PIRQ value.
*/
#define PHYSDEVOP_pirq_eoi_gmfn_v1 17
/*
* Register a shared page for the hypervisor to indicate whether the
* guest must issue PHYSDEVOP_eoi. This hypercall is very similar to
* PHYSDEVOP_pirq_eoi_gmfn_v1 but it doesn't change the semantics of
* PHYSDEVOP_eoi. The page registered is used as a bit array indexed by
* Xen's PIRQ value.
*/
#define PHYSDEVOP_pirq_eoi_gmfn_v2 28
struct physdev_pirq_eoi_gmfn {
/* IN */
xen_pfn_t gmfn;
};
typedef struct physdev_pirq_eoi_gmfn physdev_pirq_eoi_gmfn_t;
DEFINE_XEN_GUEST_HANDLE(physdev_pirq_eoi_gmfn_t);
/*
* Query the status of an IRQ line.
* @arg == pointer to physdev_irq_status_query structure.
*/
#define PHYSDEVOP_irq_status_query 5
struct physdev_irq_status_query {
/* IN */
uint32_t irq;
/* OUT */
uint32_t flags; /* XENIRQSTAT_* */
};
typedef struct physdev_irq_status_query physdev_irq_status_query_t;
DEFINE_XEN_GUEST_HANDLE(physdev_irq_status_query_t);
/* Need to call PHYSDEVOP_eoi when the IRQ has been serviced? */
#define _XENIRQSTAT_needs_eoi (0)
#define XENIRQSTAT_needs_eoi (1U<<_XENIRQSTAT_needs_eoi)
/* IRQ shared by multiple guests? */
#define _XENIRQSTAT_shared (1)
#define XENIRQSTAT_shared (1U<<_XENIRQSTAT_shared)
/*
* Set the current VCPU's I/O privilege level.
* @arg == pointer to physdev_set_iopl structure.
*/
#define PHYSDEVOP_set_iopl 6
struct physdev_set_iopl {
/* IN */
uint32_t iopl;
};
typedef struct physdev_set_iopl physdev_set_iopl_t;
DEFINE_XEN_GUEST_HANDLE(physdev_set_iopl_t);
/*
* Set the current VCPU's I/O-port permissions bitmap.
* @arg == pointer to physdev_set_iobitmap structure.
*/
#define PHYSDEVOP_set_iobitmap 7
struct physdev_set_iobitmap {
/* IN */
#if __XEN_INTERFACE_VERSION__ >= 0x00030205
XEN_GUEST_HANDLE(uint8) bitmap;
#else
uint8_t *bitmap;
#endif
uint32_t nr_ports;
};
typedef struct physdev_set_iobitmap physdev_set_iobitmap_t;
DEFINE_XEN_GUEST_HANDLE(physdev_set_iobitmap_t);
/*
* Read or write an IO-APIC register.
* @arg == pointer to physdev_apic structure.
*/
#define PHYSDEVOP_apic_read 8
#define PHYSDEVOP_apic_write 9
struct physdev_apic {
/* IN */
unsigned long apic_physbase;
uint32_t reg;
/* IN or OUT */
uint32_t value;
};
typedef struct physdev_apic physdev_apic_t;
DEFINE_XEN_GUEST_HANDLE(physdev_apic_t);
/*
* Allocate or free a physical upcall vector for the specified IRQ line.
* @arg == pointer to physdev_irq structure.
*/
#define PHYSDEVOP_alloc_irq_vector 10
#define PHYSDEVOP_free_irq_vector 11
struct physdev_irq {
/* IN */
uint32_t irq;
/* IN or OUT */
uint32_t vector;
};
typedef struct physdev_irq physdev_irq_t;
DEFINE_XEN_GUEST_HANDLE(physdev_irq_t);
#define MAP_PIRQ_TYPE_MSI 0x0
#define MAP_PIRQ_TYPE_GSI 0x1
#define MAP_PIRQ_TYPE_UNKNOWN 0x2
#define MAP_PIRQ_TYPE_MSI_SEG 0x3
#define MAP_PIRQ_TYPE_MULTI_MSI 0x4
#define PHYSDEVOP_map_pirq 13
struct physdev_map_pirq {
domid_t domid;
/* IN */
int type;
/* IN (ignored for ..._MULTI_MSI) */
int index;
/* IN or OUT */
int pirq;
/* IN - high 16 bits hold segment for ..._MSI_SEG and ..._MULTI_MSI */
int bus;
/* IN */
int devfn;
/* IN (also OUT for ..._MULTI_MSI) */
int entry_nr;
/* IN */
uint64_t table_base;
};
typedef struct physdev_map_pirq physdev_map_pirq_t;
DEFINE_XEN_GUEST_HANDLE(physdev_map_pirq_t);
#define PHYSDEVOP_unmap_pirq 14
struct physdev_unmap_pirq {
domid_t domid;
/* IN */
int pirq;
};
typedef struct physdev_unmap_pirq physdev_unmap_pirq_t;
DEFINE_XEN_GUEST_HANDLE(physdev_unmap_pirq_t);
#define PHYSDEVOP_manage_pci_add 15
#define PHYSDEVOP_manage_pci_remove 16
struct physdev_manage_pci {
/* IN */
uint8_t bus;
uint8_t devfn;
};
typedef struct physdev_manage_pci physdev_manage_pci_t;
DEFINE_XEN_GUEST_HANDLE(physdev_manage_pci_t);
#define PHYSDEVOP_restore_msi 19
struct physdev_restore_msi {
/* IN */
uint8_t bus;
uint8_t devfn;
};
typedef struct physdev_restore_msi physdev_restore_msi_t;
DEFINE_XEN_GUEST_HANDLE(physdev_restore_msi_t);
#define PHYSDEVOP_manage_pci_add_ext 20
struct physdev_manage_pci_ext {
/* IN */
uint8_t bus;
uint8_t devfn;
unsigned is_extfn;
unsigned is_virtfn;
struct {
uint8_t bus;
uint8_t devfn;
} physfn;
};
typedef struct physdev_manage_pci_ext physdev_manage_pci_ext_t;
DEFINE_XEN_GUEST_HANDLE(physdev_manage_pci_ext_t);
/*
* Argument to physdev_op_compat() hypercall. Superceded by new physdev_op()
* hypercall since 0x00030202.
*/
struct physdev_op {
uint32_t cmd;
union {
physdev_irq_status_query_t irq_status_query;
physdev_set_iopl_t set_iopl;
physdev_set_iobitmap_t set_iobitmap;
physdev_apic_t apic_op;
physdev_irq_t irq_op;
} u;
};
typedef struct physdev_op physdev_op_t;
DEFINE_XEN_GUEST_HANDLE(physdev_op_t);
#define PHYSDEVOP_setup_gsi 21
struct physdev_setup_gsi {
int gsi;
/* IN */
uint8_t triggering;
/* IN */
uint8_t polarity;
/* IN */
};
typedef struct physdev_setup_gsi physdev_setup_gsi_t;
DEFINE_XEN_GUEST_HANDLE(physdev_setup_gsi_t);
/* leave PHYSDEVOP 22 free */
/* type is MAP_PIRQ_TYPE_GSI or MAP_PIRQ_TYPE_MSI
* the hypercall returns a free pirq */
#define PHYSDEVOP_get_free_pirq 23
struct physdev_get_free_pirq {
/* IN */
int type;
/* OUT */
uint32_t pirq;
};
typedef struct physdev_get_free_pirq physdev_get_free_pirq_t;
DEFINE_XEN_GUEST_HANDLE(physdev_get_free_pirq_t);
#define XEN_PCI_MMCFG_RESERVED 0x1
#define PHYSDEVOP_pci_mmcfg_reserved 24
struct physdev_pci_mmcfg_reserved {
uint64_t address;
uint16_t segment;
uint8_t start_bus;
uint8_t end_bus;
uint32_t flags;
};
typedef struct physdev_pci_mmcfg_reserved physdev_pci_mmcfg_reserved_t;
DEFINE_XEN_GUEST_HANDLE(physdev_pci_mmcfg_reserved_t);
#define XEN_PCI_DEV_EXTFN 0x1
#define XEN_PCI_DEV_VIRTFN 0x2
#define XEN_PCI_DEV_PXM 0x4
#define PHYSDEVOP_pci_device_add 25
struct physdev_pci_device_add {
/* IN */
uint16_t seg;
uint8_t bus;
uint8_t devfn;
uint32_t flags;
struct {
uint8_t bus;
uint8_t devfn;
} physfn;
/*
* Optional parameters array.
* First element ([0]) is PXM domain associated with the device (if
* XEN_PCI_DEV_PXM is set)
*/
uint32_t optarr[XEN_FLEX_ARRAY_DIM];
};
typedef struct physdev_pci_device_add physdev_pci_device_add_t;
DEFINE_XEN_GUEST_HANDLE(physdev_pci_device_add_t);
#define PHYSDEVOP_pci_device_remove 26
#define PHYSDEVOP_restore_msi_ext 27
/*
* Dom0 should use these two to announce MMIO resources assigned to
* MSI-X capable devices won't (prepare) or may (release) change.
*/
#define PHYSDEVOP_prepare_msix 30
#define PHYSDEVOP_release_msix 31
struct physdev_pci_device {
/* IN */
uint16_t seg;
uint8_t bus;
uint8_t devfn;
};
typedef struct physdev_pci_device physdev_pci_device_t;
DEFINE_XEN_GUEST_HANDLE(physdev_pci_device_t);
#define PHYSDEVOP_DBGP_RESET_PREPARE 1
#define PHYSDEVOP_DBGP_RESET_DONE 2
#define PHYSDEVOP_DBGP_BUS_UNKNOWN 0
#define PHYSDEVOP_DBGP_BUS_PCI 1
#define PHYSDEVOP_dbgp_op 29
struct physdev_dbgp_op {
/* IN */
uint8_t op;
uint8_t bus;
union {
physdev_pci_device_t pci;
} u;
};
typedef struct physdev_dbgp_op physdev_dbgp_op_t;
DEFINE_XEN_GUEST_HANDLE(physdev_dbgp_op_t);
/*
* Notify that some PIRQ-bound event channels have been unmasked.
* ** This command is obsolete since interface version 0x00030202 and is **
* ** unsupported by newer versions of Xen. **
*/
#define PHYSDEVOP_IRQ_UNMASK_NOTIFY 4
#if __XEN_INTERFACE_VERSION__ < 0x00040600
/*
* These all-capitals physdev operation names are superceded by the new names
* (defined above) since interface version 0x00030202. The guard above was
* added post-4.5 only though and hence shouldn't check for 0x00030202.
*/
#define PHYSDEVOP_IRQ_STATUS_QUERY PHYSDEVOP_irq_status_query
#define PHYSDEVOP_SET_IOPL PHYSDEVOP_set_iopl
#define PHYSDEVOP_SET_IOBITMAP PHYSDEVOP_set_iobitmap
#define PHYSDEVOP_APIC_READ PHYSDEVOP_apic_read
#define PHYSDEVOP_APIC_WRITE PHYSDEVOP_apic_write
#define PHYSDEVOP_ASSIGN_VECTOR PHYSDEVOP_alloc_irq_vector
#define PHYSDEVOP_FREE_VECTOR PHYSDEVOP_free_irq_vector
#define PHYSDEVOP_IRQ_NEEDS_UNMASK_NOTIFY XENIRQSTAT_needs_eoi
#define PHYSDEVOP_IRQ_SHARED XENIRQSTAT_shared
#endif
#if __XEN_INTERFACE_VERSION__ < 0x00040200
#define PHYSDEVOP_pirq_eoi_gmfn PHYSDEVOP_pirq_eoi_gmfn_v1
#else
#define PHYSDEVOP_pirq_eoi_gmfn PHYSDEVOP_pirq_eoi_gmfn_v2
#endif
#endif /* __XEN_PUBLIC_PHYSDEV_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

202
include/hw/xen/interface/sched.h Normal file
View File

@ -0,0 +1,202 @@
/******************************************************************************
* sched.h
*
* Scheduler state interactions
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2005, Keir Fraser <keir@xensource.com>
*/
#ifndef __XEN_PUBLIC_SCHED_H__
#define __XEN_PUBLIC_SCHED_H__
#include "event_channel.h"
/*
* `incontents 150 sched Guest Scheduler Operations
*
* The SCHEDOP interface provides mechanisms for a guest to interact
* with the scheduler, including yield, blocking and shutting itself
* down.
*/
/*
* The prototype for this hypercall is:
* ` long HYPERVISOR_sched_op(enum sched_op cmd, void *arg, ...)
*
* @cmd == SCHEDOP_??? (scheduler operation).
* @arg == Operation-specific extra argument(s), as described below.
* ... == Additional Operation-specific extra arguments, described below.
*
* Versions of Xen prior to 3.0.2 provided only the following legacy version
* of this hypercall, supporting only the commands yield, block and shutdown:
* long sched_op(int cmd, unsigned long arg)
* @cmd == SCHEDOP_??? (scheduler operation).
* @arg == 0 (SCHEDOP_yield and SCHEDOP_block)
* == SHUTDOWN_* code (SCHEDOP_shutdown)
*
* This legacy version is available to new guests as:
* ` long HYPERVISOR_sched_op_compat(enum sched_op cmd, unsigned long arg)
*/
/* ` enum sched_op { // SCHEDOP_* => struct sched_* */
/*
* Voluntarily yield the CPU.
* @arg == NULL.
*/
#define SCHEDOP_yield 0
/*
* Block execution of this VCPU until an event is received for processing.
* If called with event upcalls masked, this operation will atomically
* reenable event delivery and check for pending events before blocking the
* VCPU. This avoids a "wakeup waiting" race.
* @arg == NULL.
*/
#define SCHEDOP_block 1
/*
* Halt execution of this domain (all VCPUs) and notify the system controller.
* @arg == pointer to sched_shutdown_t structure.
*
* If the sched_shutdown_t reason is SHUTDOWN_suspend then
* x86 PV guests must also set RDX (EDX for 32-bit guests) to the MFN
* of the guest's start info page. RDX/EDX is the third hypercall
* argument.
*
* In addition, which reason is SHUTDOWN_suspend this hypercall
* returns 1 if suspend was cancelled or the domain was merely
* checkpointed, and 0 if it is resuming in a new domain.
*/
#define SCHEDOP_shutdown 2
/*
* Poll a set of event-channel ports. Return when one or more are pending. An
* optional timeout may be specified.
* @arg == pointer to sched_poll_t structure.
*/
#define SCHEDOP_poll 3
/*
* Declare a shutdown for another domain. The main use of this function is
* in interpreting shutdown requests and reasons for fully-virtualized
* domains. A para-virtualized domain may use SCHEDOP_shutdown directly.
* @arg == pointer to sched_remote_shutdown_t structure.
*/
#define SCHEDOP_remote_shutdown 4
/*
* Latch a shutdown code, so that when the domain later shuts down it
* reports this code to the control tools.
* @arg == sched_shutdown_t, as for SCHEDOP_shutdown.
*/
#define SCHEDOP_shutdown_code 5
/*
* Setup, poke and destroy a domain watchdog timer.
* @arg == pointer to sched_watchdog_t structure.
* With id == 0, setup a domain watchdog timer to cause domain shutdown
* after timeout, returns watchdog id.
* With id != 0 and timeout == 0, destroy domain watchdog timer.
* With id != 0 and timeout != 0, poke watchdog timer and set new timeout.
*/
#define SCHEDOP_watchdog 6
/*
* Override the current vcpu affinity by pinning it to one physical cpu or
* undo this override restoring the previous affinity.
* @arg == pointer to sched_pin_override_t structure.
*
* A negative pcpu value will undo a previous pin override and restore the
* previous cpu affinity.
* This call is allowed for the hardware domain only and requires the cpu
* to be part of the domain's cpupool.
*/
#define SCHEDOP_pin_override 7
/* ` } */
struct sched_shutdown {
unsigned int reason; /* SHUTDOWN_* => enum sched_shutdown_reason */
};
typedef struct sched_shutdown sched_shutdown_t;
DEFINE_XEN_GUEST_HANDLE(sched_shutdown_t);
struct sched_poll {
XEN_GUEST_HANDLE(evtchn_port_t) ports;
unsigned int nr_ports;
uint64_t timeout;
};
typedef struct sched_poll sched_poll_t;
DEFINE_XEN_GUEST_HANDLE(sched_poll_t);
struct sched_remote_shutdown {
domid_t domain_id; /* Remote domain ID */
unsigned int reason; /* SHUTDOWN_* => enum sched_shutdown_reason */
};
typedef struct sched_remote_shutdown sched_remote_shutdown_t;
DEFINE_XEN_GUEST_HANDLE(sched_remote_shutdown_t);
struct sched_watchdog {
uint32_t id; /* watchdog ID */
uint32_t timeout; /* timeout */
};
typedef struct sched_watchdog sched_watchdog_t;
DEFINE_XEN_GUEST_HANDLE(sched_watchdog_t);
struct sched_pin_override {
int32_t pcpu;
};
typedef struct sched_pin_override sched_pin_override_t;
DEFINE_XEN_GUEST_HANDLE(sched_pin_override_t);
/*
* Reason codes for SCHEDOP_shutdown. These may be interpreted by control
* software to determine the appropriate action. For the most part, Xen does
* not care about the shutdown code.
*/
/* ` enum sched_shutdown_reason { */
#define SHUTDOWN_poweroff 0 /* Domain exited normally. Clean up and kill. */
#define SHUTDOWN_reboot 1 /* Clean up, kill, and then restart. */
#define SHUTDOWN_suspend 2 /* Clean up, save suspend info, kill. */
#define SHUTDOWN_crash 3 /* Tell controller we've crashed. */
#define SHUTDOWN_watchdog 4 /* Restart because watchdog time expired. */
/*
* Domain asked to perform 'soft reset' for it. The expected behavior is to
* reset internal Xen state for the domain returning it to the point where it
* was created but leaving the domain's memory contents and vCPU contexts
* intact. This will allow the domain to start over and set up all Xen specific
* interfaces again.
*/
#define SHUTDOWN_soft_reset 5
#define SHUTDOWN_MAX 5 /* Maximum valid shutdown reason. */
/* ` } */
#endif /* __XEN_PUBLIC_SCHED_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

341
include/hw/xen/interface/trace.h Normal file
View File

@ -0,0 +1,341 @@
/******************************************************************************
* include/public/trace.h
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Mark Williamson, (C) 2004 Intel Research Cambridge
* Copyright (C) 2005 Bin Ren
*/
#ifndef __XEN_PUBLIC_TRACE_H__
#define __XEN_PUBLIC_TRACE_H__
#define TRACE_EXTRA_MAX 7
#define TRACE_EXTRA_SHIFT 28
/* Trace classes */
#define TRC_CLS_SHIFT 16
#define TRC_GEN 0x0001f000 /* General trace */
#define TRC_SCHED 0x0002f000 /* Xen Scheduler trace */
#define TRC_DOM0OP 0x0004f000 /* Xen DOM0 operation trace */
#define TRC_HVM 0x0008f000 /* Xen HVM trace */
#define TRC_MEM 0x0010f000 /* Xen memory trace */
#define TRC_PV 0x0020f000 /* Xen PV traces */
#define TRC_SHADOW 0x0040f000 /* Xen shadow tracing */
#define TRC_HW 0x0080f000 /* Xen hardware-related traces */
#define TRC_GUEST 0x0800f000 /* Guest-generated traces */
#define TRC_ALL 0x0ffff000
#define TRC_HD_TO_EVENT(x) ((x)&0x0fffffff)
#define TRC_HD_CYCLE_FLAG (1UL<<31)
#define TRC_HD_INCLUDES_CYCLE_COUNT(x) ( !!( (x) & TRC_HD_CYCLE_FLAG ) )
#define TRC_HD_EXTRA(x) (((x)>>TRACE_EXTRA_SHIFT)&TRACE_EXTRA_MAX)
/* Trace subclasses */
#define TRC_SUBCLS_SHIFT 12
/* trace subclasses for SVM */
#define TRC_HVM_ENTRYEXIT 0x00081000 /* VMENTRY and #VMEXIT */
#define TRC_HVM_HANDLER 0x00082000 /* various HVM handlers */
#define TRC_HVM_EMUL 0x00084000 /* emulated devices */
#define TRC_SCHED_MIN 0x00021000 /* Just runstate changes */
#define TRC_SCHED_CLASS 0x00022000 /* Scheduler-specific */
#define TRC_SCHED_VERBOSE 0x00028000 /* More inclusive scheduling */
/*
* The highest 3 bits of the last 12 bits of TRC_SCHED_CLASS above are
* reserved for encoding what scheduler produced the information. The
* actual event is encoded in the last 9 bits.
*
* This means we have 8 scheduling IDs available (which means at most 8
* schedulers generating events) and, in each scheduler, up to 512
* different events.
*/
#define TRC_SCHED_ID_BITS 3
#define TRC_SCHED_ID_SHIFT (TRC_SUBCLS_SHIFT - TRC_SCHED_ID_BITS)
#define TRC_SCHED_ID_MASK (((1UL<<TRC_SCHED_ID_BITS) - 1) << TRC_SCHED_ID_SHIFT)
#define TRC_SCHED_EVT_MASK (~(TRC_SCHED_ID_MASK))
/* Per-scheduler IDs, to identify scheduler specific events */
#define TRC_SCHED_CSCHED 0
#define TRC_SCHED_CSCHED2 1
/* #define XEN_SCHEDULER_SEDF 2 (Removed) */
#define TRC_SCHED_ARINC653 3
#define TRC_SCHED_RTDS 4
#define TRC_SCHED_SNULL 5
/* Per-scheduler tracing */
#define TRC_SCHED_CLASS_EVT(_c, _e) \
( ( TRC_SCHED_CLASS | \
((TRC_SCHED_##_c << TRC_SCHED_ID_SHIFT) & TRC_SCHED_ID_MASK) ) + \
(_e & TRC_SCHED_EVT_MASK) )
/* Trace classes for DOM0 operations */
#define TRC_DOM0_DOMOPS 0x00041000 /* Domains manipulations */
/* Trace classes for Hardware */
#define TRC_HW_PM 0x00801000 /* Power management traces */
#define TRC_HW_IRQ 0x00802000 /* Traces relating to the handling of IRQs */
/* Trace events per class */
#define TRC_LOST_RECORDS (TRC_GEN + 1)
#define TRC_TRACE_WRAP_BUFFER (TRC_GEN + 2)
#define TRC_TRACE_CPU_CHANGE (TRC_GEN + 3)
#define TRC_SCHED_RUNSTATE_CHANGE (TRC_SCHED_MIN + 1)
#define TRC_SCHED_CONTINUE_RUNNING (TRC_SCHED_MIN + 2)
#define TRC_SCHED_DOM_ADD (TRC_SCHED_VERBOSE + 1)
#define TRC_SCHED_DOM_REM (TRC_SCHED_VERBOSE + 2)
#define TRC_SCHED_SLEEP (TRC_SCHED_VERBOSE + 3)
#define TRC_SCHED_WAKE (TRC_SCHED_VERBOSE + 4)
#define TRC_SCHED_YIELD (TRC_SCHED_VERBOSE + 5)
#define TRC_SCHED_BLOCK (TRC_SCHED_VERBOSE + 6)
#define TRC_SCHED_SHUTDOWN (TRC_SCHED_VERBOSE + 7)
#define TRC_SCHED_CTL (TRC_SCHED_VERBOSE + 8)
#define TRC_SCHED_ADJDOM (TRC_SCHED_VERBOSE + 9)
#define TRC_SCHED_SWITCH (TRC_SCHED_VERBOSE + 10)
#define TRC_SCHED_S_TIMER_FN (TRC_SCHED_VERBOSE + 11)
#define TRC_SCHED_T_TIMER_FN (TRC_SCHED_VERBOSE + 12)
#define TRC_SCHED_DOM_TIMER_FN (TRC_SCHED_VERBOSE + 13)
#define TRC_SCHED_SWITCH_INFPREV (TRC_SCHED_VERBOSE + 14)
#define TRC_SCHED_SWITCH_INFNEXT (TRC_SCHED_VERBOSE + 15)
#define TRC_SCHED_SHUTDOWN_CODE (TRC_SCHED_VERBOSE + 16)
#define TRC_SCHED_SWITCH_INFCONT (TRC_SCHED_VERBOSE + 17)
#define TRC_DOM0_DOM_ADD (TRC_DOM0_DOMOPS + 1)
#define TRC_DOM0_DOM_REM (TRC_DOM0_DOMOPS + 2)
#define TRC_MEM_PAGE_GRANT_MAP (TRC_MEM + 1)
#define TRC_MEM_PAGE_GRANT_UNMAP (TRC_MEM + 2)
#define TRC_MEM_PAGE_GRANT_TRANSFER (TRC_MEM + 3)
#define TRC_MEM_SET_P2M_ENTRY (TRC_MEM + 4)
#define TRC_MEM_DECREASE_RESERVATION (TRC_MEM + 5)
#define TRC_MEM_POD_POPULATE (TRC_MEM + 16)
#define TRC_MEM_POD_ZERO_RECLAIM (TRC_MEM + 17)
#define TRC_MEM_POD_SUPERPAGE_SPLINTER (TRC_MEM + 18)
#define TRC_PV_ENTRY 0x00201000 /* Hypervisor entry points for PV guests. */
#define TRC_PV_SUBCALL 0x00202000 /* Sub-call in a multicall hypercall */
#define TRC_PV_HYPERCALL (TRC_PV_ENTRY + 1)
#define TRC_PV_TRAP (TRC_PV_ENTRY + 3)
#define TRC_PV_PAGE_FAULT (TRC_PV_ENTRY + 4)
#define TRC_PV_FORCED_INVALID_OP (TRC_PV_ENTRY + 5)
#define TRC_PV_EMULATE_PRIVOP (TRC_PV_ENTRY + 6)
#define TRC_PV_EMULATE_4GB (TRC_PV_ENTRY + 7)
#define TRC_PV_MATH_STATE_RESTORE (TRC_PV_ENTRY + 8)
#define TRC_PV_PAGING_FIXUP (TRC_PV_ENTRY + 9)
#define TRC_PV_GDT_LDT_MAPPING_FAULT (TRC_PV_ENTRY + 10)
#define TRC_PV_PTWR_EMULATION (TRC_PV_ENTRY + 11)
#define TRC_PV_PTWR_EMULATION_PAE (TRC_PV_ENTRY + 12)
#define TRC_PV_HYPERCALL_V2 (TRC_PV_ENTRY + 13)
#define TRC_PV_HYPERCALL_SUBCALL (TRC_PV_SUBCALL + 14)
/*
* TRC_PV_HYPERCALL_V2 format
*
* Only some of the hypercall argument are recorded. Bit fields A0 to
* A5 in the first extra word are set if the argument is present and
* the arguments themselves are packed sequentially in the following
* words.
*
* The TRC_64_FLAG bit is not set for these events (even if there are
* 64-bit arguments in the record).
*
* Word
* 0 bit 31 30|29 28|27 26|25 24|23 22|21 20|19 ... 0
* A5 |A4 |A3 |A2 |A1 |A0 |Hypercall op
* 1 First 32 bit (or low word of first 64 bit) arg in record
* 2 Second 32 bit (or high word of first 64 bit) arg in record
* ...
*
* A0-A5 bitfield values:
*
* 00b Argument not present
* 01b 32-bit argument present
* 10b 64-bit argument present
* 11b Reserved
*/
#define TRC_PV_HYPERCALL_V2_ARG_32(i) (0x1 << (20 + 2*(i)))
#define TRC_PV_HYPERCALL_V2_ARG_64(i) (0x2 << (20 + 2*(i)))
#define TRC_PV_HYPERCALL_V2_ARG_MASK (0xfff00000)
#define TRC_SHADOW_NOT_SHADOW (TRC_SHADOW + 1)
#define TRC_SHADOW_FAST_PROPAGATE (TRC_SHADOW + 2)
#define TRC_SHADOW_FAST_MMIO (TRC_SHADOW + 3)
#define TRC_SHADOW_FALSE_FAST_PATH (TRC_SHADOW + 4)
#define TRC_SHADOW_MMIO (TRC_SHADOW + 5)
#define TRC_SHADOW_FIXUP (TRC_SHADOW + 6)
#define TRC_SHADOW_DOMF_DYING (TRC_SHADOW + 7)
#define TRC_SHADOW_EMULATE (TRC_SHADOW + 8)
#define TRC_SHADOW_EMULATE_UNSHADOW_USER (TRC_SHADOW + 9)
#define TRC_SHADOW_EMULATE_UNSHADOW_EVTINJ (TRC_SHADOW + 10)
#define TRC_SHADOW_EMULATE_UNSHADOW_UNHANDLED (TRC_SHADOW + 11)
#define TRC_SHADOW_WRMAP_BF (TRC_SHADOW + 12)
#define TRC_SHADOW_PREALLOC_UNPIN (TRC_SHADOW + 13)
#define TRC_SHADOW_RESYNC_FULL (TRC_SHADOW + 14)
#define TRC_SHADOW_RESYNC_ONLY (TRC_SHADOW + 15)
/* trace events per subclass */
#define TRC_HVM_NESTEDFLAG (0x400)
#define TRC_HVM_VMENTRY (TRC_HVM_ENTRYEXIT + 0x01)
#define TRC_HVM_VMEXIT (TRC_HVM_ENTRYEXIT + 0x02)
#define TRC_HVM_VMEXIT64 (TRC_HVM_ENTRYEXIT + TRC_64_FLAG + 0x02)
#define TRC_HVM_PF_XEN (TRC_HVM_HANDLER + 0x01)
#define TRC_HVM_PF_XEN64 (TRC_HVM_HANDLER + TRC_64_FLAG + 0x01)
#define TRC_HVM_PF_INJECT (TRC_HVM_HANDLER + 0x02)
#define TRC_HVM_PF_INJECT64 (TRC_HVM_HANDLER + TRC_64_FLAG + 0x02)
#define TRC_HVM_INJ_EXC (TRC_HVM_HANDLER + 0x03)
#define TRC_HVM_INJ_VIRQ (TRC_HVM_HANDLER + 0x04)
#define TRC_HVM_REINJ_VIRQ (TRC_HVM_HANDLER + 0x05)
#define TRC_HVM_IO_READ (TRC_HVM_HANDLER + 0x06)
#define TRC_HVM_IO_WRITE (TRC_HVM_HANDLER + 0x07)
#define TRC_HVM_CR_READ (TRC_HVM_HANDLER + 0x08)
#define TRC_HVM_CR_READ64 (TRC_HVM_HANDLER + TRC_64_FLAG + 0x08)
#define TRC_HVM_CR_WRITE (TRC_HVM_HANDLER + 0x09)
#define TRC_HVM_CR_WRITE64 (TRC_HVM_HANDLER + TRC_64_FLAG + 0x09)
#define TRC_HVM_DR_READ (TRC_HVM_HANDLER + 0x0A)
#define TRC_HVM_DR_WRITE (TRC_HVM_HANDLER + 0x0B)
#define TRC_HVM_MSR_READ (TRC_HVM_HANDLER + 0x0C)
#define TRC_HVM_MSR_WRITE (TRC_HVM_HANDLER + 0x0D)
#define TRC_HVM_CPUID (TRC_HVM_HANDLER + 0x0E)
#define TRC_HVM_INTR (TRC_HVM_HANDLER + 0x0F)
#define TRC_HVM_NMI (TRC_HVM_HANDLER + 0x10)
#define TRC_HVM_SMI (TRC_HVM_HANDLER + 0x11)
#define TRC_HVM_VMMCALL (TRC_HVM_HANDLER + 0x12)
#define TRC_HVM_HLT (TRC_HVM_HANDLER + 0x13)
#define TRC_HVM_INVLPG (TRC_HVM_HANDLER + 0x14)
#define TRC_HVM_INVLPG64 (TRC_HVM_HANDLER + TRC_64_FLAG + 0x14)
#define TRC_HVM_MCE (TRC_HVM_HANDLER + 0x15)
#define TRC_HVM_IOPORT_READ (TRC_HVM_HANDLER + 0x16)
#define TRC_HVM_IOMEM_READ (TRC_HVM_HANDLER + 0x17)
#define TRC_HVM_CLTS (TRC_HVM_HANDLER + 0x18)
#define TRC_HVM_LMSW (TRC_HVM_HANDLER + 0x19)
#define TRC_HVM_LMSW64 (TRC_HVM_HANDLER + TRC_64_FLAG + 0x19)
#define TRC_HVM_RDTSC (TRC_HVM_HANDLER + 0x1a)
#define TRC_HVM_INTR_WINDOW (TRC_HVM_HANDLER + 0x20)
#define TRC_HVM_NPF (TRC_HVM_HANDLER + 0x21)
#define TRC_HVM_REALMODE_EMULATE (TRC_HVM_HANDLER + 0x22)
#define TRC_HVM_TRAP (TRC_HVM_HANDLER + 0x23)
#define TRC_HVM_TRAP_DEBUG (TRC_HVM_HANDLER + 0x24)
#define TRC_HVM_VLAPIC (TRC_HVM_HANDLER + 0x25)
#define TRC_HVM_XCR_READ64 (TRC_HVM_HANDLER + TRC_64_FLAG + 0x26)
#define TRC_HVM_XCR_WRITE64 (TRC_HVM_HANDLER + TRC_64_FLAG + 0x27)
#define TRC_HVM_IOPORT_WRITE (TRC_HVM_HANDLER + 0x216)
#define TRC_HVM_IOMEM_WRITE (TRC_HVM_HANDLER + 0x217)
/* Trace events for emulated devices */
#define TRC_HVM_EMUL_HPET_START_TIMER (TRC_HVM_EMUL + 0x1)
#define TRC_HVM_EMUL_PIT_START_TIMER (TRC_HVM_EMUL + 0x2)
#define TRC_HVM_EMUL_RTC_START_TIMER (TRC_HVM_EMUL + 0x3)
#define TRC_HVM_EMUL_LAPIC_START_TIMER (TRC_HVM_EMUL + 0x4)
#define TRC_HVM_EMUL_HPET_STOP_TIMER (TRC_HVM_EMUL + 0x5)
#define TRC_HVM_EMUL_PIT_STOP_TIMER (TRC_HVM_EMUL + 0x6)
#define TRC_HVM_EMUL_RTC_STOP_TIMER (TRC_HVM_EMUL + 0x7)
#define TRC_HVM_EMUL_LAPIC_STOP_TIMER (TRC_HVM_EMUL + 0x8)
#define TRC_HVM_EMUL_PIT_TIMER_CB (TRC_HVM_EMUL + 0x9)
#define TRC_HVM_EMUL_LAPIC_TIMER_CB (TRC_HVM_EMUL + 0xA)
#define TRC_HVM_EMUL_PIC_INT_OUTPUT (TRC_HVM_EMUL + 0xB)
#define TRC_HVM_EMUL_PIC_KICK (TRC_HVM_EMUL + 0xC)
#define TRC_HVM_EMUL_PIC_INTACK (TRC_HVM_EMUL + 0xD)
#define TRC_HVM_EMUL_PIC_POSEDGE (TRC_HVM_EMUL + 0xE)
#define TRC_HVM_EMUL_PIC_NEGEDGE (TRC_HVM_EMUL + 0xF)
#define TRC_HVM_EMUL_PIC_PEND_IRQ_CALL (TRC_HVM_EMUL + 0x10)
#define TRC_HVM_EMUL_LAPIC_PIC_INTR (TRC_HVM_EMUL + 0x11)
/* trace events for per class */
#define TRC_PM_FREQ_CHANGE (TRC_HW_PM + 0x01)
#define TRC_PM_IDLE_ENTRY (TRC_HW_PM + 0x02)
#define TRC_PM_IDLE_EXIT (TRC_HW_PM + 0x03)
/* Trace events for IRQs */
#define TRC_HW_IRQ_MOVE_CLEANUP_DELAY (TRC_HW_IRQ + 0x1)
#define TRC_HW_IRQ_MOVE_CLEANUP (TRC_HW_IRQ + 0x2)
#define TRC_HW_IRQ_BIND_VECTOR (TRC_HW_IRQ + 0x3)
#define TRC_HW_IRQ_CLEAR_VECTOR (TRC_HW_IRQ + 0x4)
#define TRC_HW_IRQ_MOVE_FINISH (TRC_HW_IRQ + 0x5)
#define TRC_HW_IRQ_ASSIGN_VECTOR (TRC_HW_IRQ + 0x6)
#define TRC_HW_IRQ_UNMAPPED_VECTOR (TRC_HW_IRQ + 0x7)
#define TRC_HW_IRQ_HANDLED (TRC_HW_IRQ + 0x8)
/*
* Event Flags
*
* Some events (e.g, TRC_PV_TRAP and TRC_HVM_IOMEM_READ) have multiple
* record formats. These event flags distinguish between the
* different formats.
*/
#define TRC_64_FLAG 0x100 /* Addresses are 64 bits (instead of 32 bits) */
/* This structure represents a single trace buffer record. */
struct t_rec {
uint32_t event:28;
uint32_t extra_u32:3; /* # entries in trailing extra_u32[] array */
uint32_t cycles_included:1; /* u.cycles or u.no_cycles? */
union {
struct {
uint32_t cycles_lo, cycles_hi; /* cycle counter timestamp */
uint32_t extra_u32[7]; /* event data items */
} cycles;
struct {
uint32_t extra_u32[7]; /* event data items */
} nocycles;
} u;
};
/*
* This structure contains the metadata for a single trace buffer. The head
* field, indexes into an array of struct t_rec's.
*/
struct t_buf {
/* Assume the data buffer size is X. X is generally not a power of 2.
* CONS and PROD are incremented modulo (2*X):
* 0 <= cons < 2*X
* 0 <= prod < 2*X
* This is done because addition modulo X breaks at 2^32 when X is not a
* power of 2:
* (((2^32 - 1) % X) + 1) % X != (2^32) % X
*/
uint32_t cons; /* Offset of next item to be consumed by control tools. */
uint32_t prod; /* Offset of next item to be produced by Xen. */
/* Records follow immediately after the meta-data header. */
};
/* Structure used to pass MFNs to the trace buffers back to trace consumers.
* Offset is an offset into the mapped structure where the mfn list will be held.
* MFNs will be at ((unsigned long *)(t_info))+(t_info->cpu_offset[cpu]).
*/
struct t_info {
uint16_t tbuf_size; /* Size in pages of each trace buffer */
uint16_t mfn_offset[]; /* Offset within t_info structure of the page list per cpu */
/* MFN lists immediately after the header */
};
#endif /* __XEN_PUBLIC_TRACE_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

248
include/hw/xen/interface/vcpu.h Normal file
View File

@ -0,0 +1,248 @@
/******************************************************************************
* vcpu.h
*
* VCPU initialisation, query, and hotplug.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2005, Keir Fraser <keir@xensource.com>
*/
#ifndef __XEN_PUBLIC_VCPU_H__
#define __XEN_PUBLIC_VCPU_H__
#include "xen.h"
/*
* Prototype for this hypercall is:
* long vcpu_op(int cmd, unsigned int vcpuid, void *extra_args)
* @cmd == VCPUOP_??? (VCPU operation).
* @vcpuid == VCPU to operate on.
* @extra_args == Operation-specific extra arguments (NULL if none).
*/
/*
* Initialise a VCPU. Each VCPU can be initialised only once. A
* newly-initialised VCPU will not run until it is brought up by VCPUOP_up.
*
* @extra_arg == For PV or ARM guests this is a pointer to a vcpu_guest_context
* structure containing the initial state for the VCPU. For x86
* HVM based guests this is a pointer to a vcpu_hvm_context
* structure.
*/
#define VCPUOP_initialise 0
/*
* Bring up a VCPU. This makes the VCPU runnable. This operation will fail
* if the VCPU has not been initialised (VCPUOP_initialise).
*/
#define VCPUOP_up 1
/*
* Bring down a VCPU (i.e., make it non-runnable).
* There are a few caveats that callers should observe:
* 1. This operation may return, and VCPU_is_up may return false, before the
* VCPU stops running (i.e., the command is asynchronous). It is a good
* idea to ensure that the VCPU has entered a non-critical loop before
* bringing it down. Alternatively, this operation is guaranteed
* synchronous if invoked by the VCPU itself.
* 2. After a VCPU is initialised, there is currently no way to drop all its
* references to domain memory. Even a VCPU that is down still holds
* memory references via its pagetable base pointer and GDT. It is good
* practise to move a VCPU onto an 'idle' or default page table, LDT and
* GDT before bringing it down.
*/
#define VCPUOP_down 2
/* Returns 1 if the given VCPU is up. */
#define VCPUOP_is_up 3
/*
* Return information about the state and running time of a VCPU.
* @extra_arg == pointer to vcpu_runstate_info structure.
*/
#define VCPUOP_get_runstate_info 4
struct vcpu_runstate_info {
/* VCPU's current state (RUNSTATE_*). */
int state;
/* When was current state entered (system time, ns)? */
uint64_t state_entry_time;
/*
* Update indicator set in state_entry_time:
* When activated via VMASST_TYPE_runstate_update_flag, set during
* updates in guest memory mapped copy of vcpu_runstate_info.
*/
#define XEN_RUNSTATE_UPDATE (xen_mk_ullong(1) << 63)
/*
* Time spent in each RUNSTATE_* (ns). The sum of these times is
* guaranteed not to drift from system time.
*/
uint64_t time[4];
};
typedef struct vcpu_runstate_info vcpu_runstate_info_t;
DEFINE_XEN_GUEST_HANDLE(vcpu_runstate_info_t);
/* VCPU is currently running on a physical CPU. */
#define RUNSTATE_running 0
/* VCPU is runnable, but not currently scheduled on any physical CPU. */
#define RUNSTATE_runnable 1
/* VCPU is blocked (a.k.a. idle). It is therefore not runnable. */
#define RUNSTATE_blocked 2
/*
* VCPU is not runnable, but it is not blocked.
* This is a 'catch all' state for things like hotplug and pauses by the
* system administrator (or for critical sections in the hypervisor).
* RUNSTATE_blocked dominates this state (it is the preferred state).
*/
#define RUNSTATE_offline 3
/*
* Register a shared memory area from which the guest may obtain its own
* runstate information without needing to execute a hypercall.
* Notes:
* 1. The registered address may be virtual or physical or guest handle,
* depending on the platform. Virtual address or guest handle should be
* registered on x86 systems.
* 2. Only one shared area may be registered per VCPU. The shared area is
* updated by the hypervisor each time the VCPU is scheduled. Thus
* runstate.state will always be RUNSTATE_running and
* runstate.state_entry_time will indicate the system time at which the
* VCPU was last scheduled to run.
* @extra_arg == pointer to vcpu_register_runstate_memory_area structure.
*/
#define VCPUOP_register_runstate_memory_area 5
struct vcpu_register_runstate_memory_area {
union {
XEN_GUEST_HANDLE(vcpu_runstate_info_t) h;
struct vcpu_runstate_info *v;
uint64_t p;
} addr;
};
typedef struct vcpu_register_runstate_memory_area vcpu_register_runstate_memory_area_t;
DEFINE_XEN_GUEST_HANDLE(vcpu_register_runstate_memory_area_t);
/*
* Set or stop a VCPU's periodic timer. Every VCPU has one periodic timer
* which can be set via these commands. Periods smaller than one millisecond
* may not be supported.
*/
#define VCPUOP_set_periodic_timer 6 /* arg == vcpu_set_periodic_timer_t */
#define VCPUOP_stop_periodic_timer 7 /* arg == NULL */
struct vcpu_set_periodic_timer {
uint64_t period_ns;
};
typedef struct vcpu_set_periodic_timer vcpu_set_periodic_timer_t;
DEFINE_XEN_GUEST_HANDLE(vcpu_set_periodic_timer_t);
/*
* Set or stop a VCPU's single-shot timer. Every VCPU has one single-shot
* timer which can be set via these commands.
*/
#define VCPUOP_set_singleshot_timer 8 /* arg == vcpu_set_singleshot_timer_t */
#define VCPUOP_stop_singleshot_timer 9 /* arg == NULL */
struct vcpu_set_singleshot_timer {
uint64_t timeout_abs_ns; /* Absolute system time value in nanoseconds. */
uint32_t flags; /* VCPU_SSHOTTMR_??? */
};
typedef struct vcpu_set_singleshot_timer vcpu_set_singleshot_timer_t;
DEFINE_XEN_GUEST_HANDLE(vcpu_set_singleshot_timer_t);
/* Flags to VCPUOP_set_singleshot_timer. */
/* Require the timeout to be in the future (return -ETIME if it's passed). */
#define _VCPU_SSHOTTMR_future (0)
#define VCPU_SSHOTTMR_future (1U << _VCPU_SSHOTTMR_future)
/*
* Register a memory location in the guest address space for the
* vcpu_info structure. This allows the guest to place the vcpu_info
* structure in a convenient place, such as in a per-cpu data area.
* The pointer need not be page aligned, but the structure must not
* cross a page boundary.
*
* This may be called only once per vcpu.
*/
#define VCPUOP_register_vcpu_info 10 /* arg == vcpu_register_vcpu_info_t */
struct vcpu_register_vcpu_info {
uint64_t mfn; /* mfn of page to place vcpu_info */
uint32_t offset; /* offset within page */
uint32_t rsvd; /* unused */
};
typedef struct vcpu_register_vcpu_info vcpu_register_vcpu_info_t;
DEFINE_XEN_GUEST_HANDLE(vcpu_register_vcpu_info_t);
/* Send an NMI to the specified VCPU. @extra_arg == NULL. */
#define VCPUOP_send_nmi 11
/*
* Get the physical ID information for a pinned vcpu's underlying physical
* processor. The physical ID informmation is architecture-specific.
* On x86: id[31:0]=apic_id, id[63:32]=acpi_id.
* This command returns -EINVAL if it is not a valid operation for this VCPU.
*/
#define VCPUOP_get_physid 12 /* arg == vcpu_get_physid_t */
struct vcpu_get_physid {
uint64_t phys_id;
};
typedef struct vcpu_get_physid vcpu_get_physid_t;
DEFINE_XEN_GUEST_HANDLE(vcpu_get_physid_t);
#define xen_vcpu_physid_to_x86_apicid(physid) ((uint32_t)(physid))
#define xen_vcpu_physid_to_x86_acpiid(physid) ((uint32_t)((physid) >> 32))
/*
* Register a memory location to get a secondary copy of the vcpu time
* parameters. The master copy still exists as part of the vcpu shared
* memory area, and this secondary copy is updated whenever the master copy
* is updated (and using the same versioning scheme for synchronisation).
*
* The intent is that this copy may be mapped (RO) into userspace so
* that usermode can compute system time using the time info and the
* tsc. Usermode will see an array of vcpu_time_info structures, one
* for each vcpu, and choose the right one by an existing mechanism
* which allows it to get the current vcpu number (such as via a
* segment limit). It can then apply the normal algorithm to compute
* system time from the tsc.
*
* @extra_arg == pointer to vcpu_register_time_info_memory_area structure.
*/
#define VCPUOP_register_vcpu_time_memory_area 13
DEFINE_XEN_GUEST_HANDLE(vcpu_time_info_t);
struct vcpu_register_time_memory_area {
union {
XEN_GUEST_HANDLE(vcpu_time_info_t) h;
struct vcpu_time_info *v;
uint64_t p;
} addr;
};
typedef struct vcpu_register_time_memory_area vcpu_register_time_memory_area_t;
DEFINE_XEN_GUEST_HANDLE(vcpu_register_time_memory_area_t);
#endif /* __XEN_PUBLIC_VCPU_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

113
include/hw/xen/interface/version.h Normal file
View File

@ -0,0 +1,113 @@
/******************************************************************************
* version.h
*
* Xen version, type, and compile information.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2005, Nguyen Anh Quynh <aquynh@gmail.com>
* Copyright (c) 2005, Keir Fraser <keir@xensource.com>
*/
#ifndef __XEN_PUBLIC_VERSION_H__
#define __XEN_PUBLIC_VERSION_H__
#include "xen.h"
/* NB. All ops return zero on success, except XENVER_{version,pagesize}
* XENVER_{version,pagesize,build_id} */
/* arg == NULL; returns major:minor (16:16). */
#define XENVER_version 0
/* arg == xen_extraversion_t. */
#define XENVER_extraversion 1
typedef char xen_extraversion_t[16];
#define XEN_EXTRAVERSION_LEN (sizeof(xen_extraversion_t))
/* arg == xen_compile_info_t. */
#define XENVER_compile_info 2
struct xen_compile_info {
char compiler[64];
char compile_by[16];
char compile_domain[32];
char compile_date[32];
};
typedef struct xen_compile_info xen_compile_info_t;
#define XENVER_capabilities 3
typedef char xen_capabilities_info_t[1024];
#define XEN_CAPABILITIES_INFO_LEN (sizeof(xen_capabilities_info_t))
#define XENVER_changeset 4
typedef char xen_changeset_info_t[64];
#define XEN_CHANGESET_INFO_LEN (sizeof(xen_changeset_info_t))
#define XENVER_platform_parameters 5
struct xen_platform_parameters {
xen_ulong_t virt_start;
};
typedef struct xen_platform_parameters xen_platform_parameters_t;
#define XENVER_get_features 6
struct xen_feature_info {
unsigned int submap_idx; /* IN: which 32-bit submap to return */
uint32_t submap; /* OUT: 32-bit submap */
};
typedef struct xen_feature_info xen_feature_info_t;
/* Declares the features reported by XENVER_get_features. */
#include "features.h"
/* arg == NULL; returns host memory page size. */
#define XENVER_pagesize 7
/* arg == xen_domain_handle_t.
*
* The toolstack fills it out for guest consumption. It is intended to hold
* the UUID of the guest.
*/
#define XENVER_guest_handle 8
#define XENVER_commandline 9
typedef char xen_commandline_t[1024];
/*
* Return value is the number of bytes written, or XEN_Exx on error.
* Calling with empty parameter returns the size of build_id.
*/
#define XENVER_build_id 10
struct xen_build_id {
uint32_t len; /* IN: size of buf[]. */
unsigned char buf[XEN_FLEX_ARRAY_DIM];
/* OUT: Variable length buffer with build_id. */
};
typedef struct xen_build_id xen_build_id_t;
#endif /* __XEN_PUBLIC_VERSION_H__ */
/*
* Local variables:
* mode: C
* c-file-style: "BSD"
* c-basic-offset: 4
* tab-width: 4
* indent-tabs-mode: nil
* End:
*/

46
include/hw/xen/interface/xen-compat.h Normal file
View File

@ -0,0 +1,46 @@
/******************************************************************************
* xen-compat.h
*
* Guest OS interface to Xen. Compatibility layer.
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in
* all copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
* DEALINGS IN THE SOFTWARE.
*
* Copyright (c) 2006, Christian Limpach
*/
#ifndef __XEN_PUBLIC_XEN_COMPAT_H__
#define __XEN_PUBLIC_XEN_COMPAT_H__
#define __XEN_LATEST_INTERFACE_VERSION__ 0x00040e00
#if defined(__XEN__) || defined(__XEN_TOOLS__)
/* Xen is built with matching headers and implements the latest interface. */
#define __XEN_INTERFACE_VERSION__ __XEN_LATEST_INTERFACE_VERSION__
#elif !defined(__XEN_INTERFACE_VERSION__)
/* Guests which do not specify a version get the legacy interface. */
#define __XEN_INTERFACE_VERSION__ 0x00000000
#endif
#if __XEN_INTERFACE_VERSION__ > __XEN_LATEST_INTERFACE_VERSION__
#error "These header files do not support the requested interface version."
#endif
#define COMPAT_FLEX_ARRAY_DIM XEN_FLEX_ARRAY_DIM
#endif /* __XEN_PUBLIC_XEN_COMPAT_H__ */

1049
include/hw/xen/interface/xen.h Normal file
View File

File diff suppressed because it is too large Load Diff

3
include/hw/xen/xen-legacy-backend.h
View File

@ -42,8 +42,7 @@ int xenstore_read_fe_uint64(struct XenLegacyDevice *xendev, const char *node,
void xen_be_check_state(struct XenLegacyDevice *xendev);
/* xen backend driver bits */
int xen_be_init(void);
void xen_be_register_common(void);
void xen_be_init(void);
int xen_be_register(const char *type, struct XenDevOps *ops);
int xen_be_set_state(struct XenLegacyDevice *xendev, enum xenbus_state state);
int xen_be_bind_evtchn(struct XenLegacyDevice *xendev);

21
include/hw/xen/xen.h
View File

@ -1,19 +1,30 @@
#ifndef QEMU_HW_XEN_H
#define QEMU_HW_XEN_H
/*
* public xen header
* stuff needed outside xen-*.c, i.e. interfaces to qemu.
* must not depend on any xen headers being present in
* /usr/include/xen, so it can be included unconditionally.
*/
#ifndef QEMU_HW_XEN_H
#define QEMU_HW_XEN_H
/*
* As a temporary measure while the headers are being untangled, define
* __XEN_TOOLS__ here before any Xen headers are included. Otherwise, if
* the Xen toolstack library headers are later included, they will find
* some of the "internal" definitions missing and the build will fail. In
* later commits, we'll end up with a rule that the native libraries have
* to be included first, which will ensure that the libraries get the
* version of Xen libraries that they expect.
*/
#define __XEN_TOOLS__ 1
#include "exec/cpu-common.h"
/* xen-machine.c */
enum xen_mode {
XEN_EMULATE = 0, // xen emulation, using xenner (default)
XEN_ATTACH // attach to xen domain created by libxl
XEN_DISABLED = 0, /* xen support disabled (default) */
XEN_ATTACH, /* attach to xen domain created by libxl */
XEN_EMULATE, /* emulate Xen within QEMU */
};
extern uint32_t xen_domid;

2
include/monitor/hmp.h
View File

@ -114,6 +114,8 @@ void hmp_virtio_status(Monitor *mon, const QDict *qdict);
void hmp_virtio_queue_status(Monitor *mon, const QDict *qdict);
void hmp_vhost_queue_status(Monitor *mon, const QDict *qdict);
void hmp_virtio_queue_element(Monitor *mon, const QDict *qdict);
void hmp_xen_event_inject(Monitor *mon, const QDict *qdict);
void hmp_xen_event_list(Monitor *mon, const QDict *qdict);
void object_add_completion(ReadLineState *rs, int nb_args, const char *str);
void object_del_completion(ReadLineState *rs, int nb_args, const char *str);
void device_add_completion(ReadLineState *rs, int nb_args, const char *str);

4
include/sysemu/kvm_int.h
View File

@ -118,6 +118,10 @@ struct KVMState
struct KVMDirtyRingReaper reaper;
NotifyVmexitOption notify_vmexit;
uint32_t notify_window;
uint32_t xen_version;
uint32_t xen_caps;
uint16_t xen_gnttab_max_frames;
uint16_t xen_evtchn_max_pirq;
};
void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml,

43
include/sysemu/kvm_xen.h Normal file
View File

@ -0,0 +1,43 @@
/*
* Xen HVM emulation support in KVM
*
* Copyright © 2019 Oracle and/or its affiliates. All rights reserved.
* Copyright © 2022 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*
*/
#ifndef QEMU_SYSEMU_KVM_XEN_H
#define QEMU_SYSEMU_KVM_XEN_H
/* The KVM API uses these to indicate "no GPA" or "no GFN" */
#define INVALID_GPA UINT64_MAX
#define INVALID_GFN UINT64_MAX
/* QEMU plays the rôle of dom0 for "interdomain" communication. */
#define DOMID_QEMU 0
int kvm_xen_soft_reset(void);
uint32_t kvm_xen_get_caps(void);
void *kvm_xen_get_vcpu_info_hva(uint32_t vcpu_id);
void kvm_xen_inject_vcpu_callback_vector(uint32_t vcpu_id, int type);
void kvm_xen_set_callback_asserted(void);
int kvm_xen_set_vcpu_virq(uint32_t vcpu_id, uint16_t virq, uint16_t port);
uint16_t kvm_xen_get_gnttab_max_frames(void);
uint16_t kvm_xen_get_evtchn_max_pirq(void);
#define kvm_xen_has_cap(cap) (!!(kvm_xen_get_caps() & \
KVM_XEN_HVM_CONFIG_ ## cap))
#define XEN_SPECIAL_AREA_ADDR 0xfeff8000UL
#define XEN_SPECIAL_AREA_SIZE 0x4000UL
#define XEN_SPECIALPAGE_CONSOLE 0
#define XEN_SPECIALPAGE_XENSTORE 1
#define XEN_SPECIAL_PFN(x) ((XEN_SPECIAL_AREA_ADDR >> TARGET_PAGE_BITS) + \
XEN_SPECIALPAGE_##x)
#endif /* QEMU_SYSEMU_KVM_XEN_H */

2
meson.build
View File

@ -2982,6 +2982,7 @@ if have_system
'hw/i2c',
'hw/i386',
'hw/i386/xen',
'hw/i386/kvm',
'hw/ide',
'hw/input',
'hw/intc',
@ -3881,6 +3882,7 @@ if have_system
if xen.found()
summary_info += {'xen ctrl version': xen.version()}
endif
summary_info += {'Xen emulation': config_all.has_key('CONFIG_XEN_EMU')}
endif
summary_info += {'TCG support': config_all.has_key('CONFIG_TCG')}
if config_all.has_key('CONFIG_TCG')

4
qapi/machine.json
View File

@ -155,6 +155,8 @@
#
# @default-ram-id: the default ID of initial RAM memory backend (since 5.2)
#
# @acpi: machine type supports ACPI (since 8.0)
#
# Since: 1.2
##
{ 'struct': 'MachineInfo',
@ -162,7 +164,7 @@
'*is-default': 'bool', 'cpu-max': 'int',
'hotpluggable-cpus': 'bool', 'numa-mem-supported': 'bool',
'deprecated': 'bool', '*default-cpu-type': 'str',
'*default-ram-id': 'str' } }
'*default-ram-id': 'str', 'acpi': 'bool' } }
##
# @query-machines:

116
qapi/misc-target.json
View File

@ -380,3 +380,119 @@
#
##
{ 'command': 'query-sgx-capabilities', 'returns': 'SGXInfo', 'if': 'TARGET_I386' }
##
# @EvtchnPortType:
#
# An enumeration of Xen event channel port types.
#
# @closed: The port is unused.
#
# @unbound: The port is allocated and ready to be bound.
#
# @interdomain: The port is connected as an interdomain interrupt.
#
# @pirq: The port is bound to a physical IRQ (PIRQ).
#
# @virq: The port is bound to a virtual IRQ (VIRQ).
#
# @ipi: The post is an inter-processor interrupt (IPI).
#
# Since: 8.0
##
{ 'enum': 'EvtchnPortType',
'data': ['closed', 'unbound', 'interdomain', 'pirq', 'virq', 'ipi'],
'if': 'TARGET_I386' }
##
# @EvtchnInfo:
#
# Information about a Xen event channel port
#
# @port: the port number
#
# @vcpu: target vCPU for this port
#
# @type: the port type
#
# @remote-domain: remote domain for interdomain ports
#
# @target: remote port ID, or virq/pirq number
#
# @pending: port is currently active pending delivery
#
# @masked: port is masked
#
# Since: 8.0
##
{ 'struct': 'EvtchnInfo',
'data': {'port': 'uint16',
'vcpu': 'uint32',
'type': 'EvtchnPortType',
'remote-domain': 'str',
'target': 'uint16',
'pending': 'bool',
'masked': 'bool'},
'if': 'TARGET_I386' }
##
# @xen-event-list:
#
# Query the Xen event channels opened by the guest.
#
# Returns: list of open event channel ports.
#
# Since: 8.0
#
# Example:
#
# -> { "execute": "xen-event-list" }
# <- { "return": [
# {
# "pending": false,
# "port": 1,
# "vcpu": 1,
# "remote-domain": "qemu",
# "masked": false,
# "type": "interdomain",
# "target": 1
# },
# {
# "pending": false,
# "port": 2,
# "vcpu": 0,
# "remote-domain": "",
# "masked": false,
# "type": "virq",
# "target": 0
# }
# ]
# }
#
##
{ 'command': 'xen-event-list',
'returns': ['EvtchnInfo'],
'if': 'TARGET_I386' }
##
# @xen-event-inject:
#
# Inject a Xen event channel port (interrupt) to the guest.
#
# @port: The port number
#
# Returns: - Nothing on success.
#
# Since: 8.0
#
# Example:
#
# -> { "execute": "xen-event-inject", "arguments": { "port": 1 } }
# <- { "return": { } }
#
##
{ 'command': 'xen-event-inject',
'data': { 'port': 'uint32' },
'if': 'TARGET_I386' }

2
softmmu/globals.c
View File

@ -63,5 +63,5 @@ QemuUUID qemu_uuid;
bool qemu_uuid_set;
uint32_t xen_domid;
enum xen_mode xen_mode = XEN_EMULATE;
enum xen_mode xen_mode = XEN_DISABLED;
bool xen_domid_restrict;

2
softmmu/vl.c
View File

@ -3360,7 +3360,7 @@ void qemu_init(int argc, char **argv)
has_defaults = 0;
break;
case QEMU_OPTION_xen_domid:
if (!(accel_find("xen"))) {
if (!(accel_find("xen")) && !(accel_find("kvm"))) {
error_report("Option not supported for this target");
exit(1);
}

1
target/i386/cpu.c
View File

@ -7209,6 +7209,7 @@ static Property x86_cpu_properties[] = {
* own cache information (see x86_cpu_load_def()).
*/
DEFINE_PROP_BOOL("legacy-cache", X86CPU, legacy_cache, true),
DEFINE_PROP_BOOL("xen-vapic", X86CPU, xen_vapic, false),
/*
* From "Requirements for Implementing the Microsoft

19
target/i386/cpu.h
View File

@ -26,6 +26,9 @@
#include "exec/cpu-defs.h"
#include "qapi/qapi-types-common.h"
#include "qemu/cpu-float.h"
#include "qemu/timer.h"
#define XEN_NR_VIRQS 24
/* The x86 has a strong memory model with some store-after-load re-ordering */
#define TCG_GUEST_DEFAULT_MO (TCG_MO_ALL & ~TCG_MO_ST_LD)
@ -1799,6 +1802,20 @@ typedef struct CPUArchState {
#endif
#if defined(CONFIG_KVM)
struct kvm_nested_state *nested_state;
MemoryRegion *xen_vcpu_info_mr;
void *xen_vcpu_info_hva;
uint64_t xen_vcpu_info_gpa;
uint64_t xen_vcpu_info_default_gpa;
uint64_t xen_vcpu_time_info_gpa;
uint64_t xen_vcpu_runstate_gpa;
uint8_t xen_vcpu_callback_vector;
bool xen_callback_asserted;
uint16_t xen_virq[XEN_NR_VIRQS];
uint64_t xen_singleshot_timer_ns;
QEMUTimer *xen_singleshot_timer;
uint64_t xen_periodic_timer_period;
QEMUTimer *xen_periodic_timer;
QemuMutex xen_timers_lock;
#endif
#if defined(CONFIG_HVF)
HVFX86LazyFlags hvf_lflags;
@ -1975,6 +1992,8 @@ struct ArchCPU {
int32_t thread_id;
int32_t hv_max_vps;
bool xen_vapic;
};

259
target/i386/kvm/kvm.c
View File

@ -22,6 +22,7 @@
#include <linux/kvm.h>
#include "standard-headers/asm-x86/kvm_para.h"
#include "hw/xen/interface/arch-x86/cpuid.h"
#include "cpu.h"
#include "host-cpu.h"
@ -31,6 +32,7 @@
#include "sysemu/runstate.h"
#include "kvm_i386.h"
#include "sev.h"
#include "xen-emu.h"
#include "hyperv.h"
#include "hyperv-proto.h"
@ -42,6 +44,8 @@
#include "qemu/error-report.h"
#include "qemu/memalign.h"
#include "hw/i386/x86.h"
#include "hw/i386/kvm/xen_evtchn.h"
#include "hw/i386/pc.h"
#include "hw/i386/apic.h"
#include "hw/i386/apic_internal.h"
#include "hw/i386/apic-msidef.h"
@ -49,6 +53,8 @@
#include "hw/i386/x86-iommu.h"
#include "hw/i386/e820_memory_layout.h"
#include "hw/xen/xen.h"
#include "hw/pci/pci.h"
#include "hw/pci/msi.h"
#include "hw/pci/msix.h"
@ -1815,7 +1821,82 @@ int kvm_arch_init_vcpu(CPUState *cs)
has_msr_hv_hypercall = true;
}
if (cpu->expose_kvm) {
if (cs->kvm_state->xen_version) {
#ifdef CONFIG_XEN_EMU
struct kvm_cpuid_entry2 *xen_max_leaf;
memcpy(signature, "XenVMMXenVMM", 12);
xen_max_leaf = c = &cpuid_data.entries[cpuid_i++];
c->function = kvm_base + XEN_CPUID_SIGNATURE;
c->eax = kvm_base + XEN_CPUID_TIME;
c->ebx = signature[0];
c->ecx = signature[1];
c->edx = signature[2];
c = &cpuid_data.entries[cpuid_i++];
c->function = kvm_base + XEN_CPUID_VENDOR;
c->eax = cs->kvm_state->xen_version;
c->ebx = 0;
c->ecx = 0;
c->edx = 0;
c = &cpuid_data.entries[cpuid_i++];
c->function = kvm_base + XEN_CPUID_HVM_MSR;
/* Number of hypercall-transfer pages */
c->eax = 1;
/* Hypercall MSR base address */
if (hyperv_enabled(cpu)) {
c->ebx = XEN_HYPERCALL_MSR_HYPERV;
kvm_xen_init(cs->kvm_state, c->ebx);
} else {
c->ebx = XEN_HYPERCALL_MSR;
}
c->ecx = 0;
c->edx = 0;
c = &cpuid_data.entries[cpuid_i++];
c->function = kvm_base + XEN_CPUID_TIME;
c->eax = ((!!tsc_is_stable_and_known(env) << 1) |
(!!(env->features[FEAT_8000_0001_EDX] & CPUID_EXT2_RDTSCP) << 2));
/* default=0 (emulate if necessary) */
c->ebx = 0;
/* guest tsc frequency */
c->ecx = env->user_tsc_khz;
/* guest tsc incarnation (migration count) */
c->edx = 0;
c = &cpuid_data.entries[cpuid_i++];
c->function = kvm_base + XEN_CPUID_HVM;
xen_max_leaf->eax = kvm_base + XEN_CPUID_HVM;
if (cs->kvm_state->xen_version >= XEN_VERSION(4, 5)) {
c->function = kvm_base + XEN_CPUID_HVM;
if (cpu->xen_vapic) {
c->eax |= XEN_HVM_CPUID_APIC_ACCESS_VIRT;
c->eax |= XEN_HVM_CPUID_X2APIC_VIRT;
}
c->eax |= XEN_HVM_CPUID_IOMMU_MAPPINGS;
if (cs->kvm_state->xen_version >= XEN_VERSION(4, 6)) {
c->eax |= XEN_HVM_CPUID_VCPU_ID_PRESENT;
c->ebx = cs->cpu_index;
}
}
r = kvm_xen_init_vcpu(cs);
if (r) {
return r;
}
kvm_base += 0x100;
#else /* CONFIG_XEN_EMU */
/* This should never happen as kvm_arch_init() would have died first. */
fprintf(stderr, "Cannot enable Xen CPUID without Xen support\n");
abort();
#endif
} else if (cpu->expose_kvm) {
memcpy(signature, "KVMKVMKVM\0\0\0", 12);
c = &cpuid_data.entries[cpuid_i++];
c->function = KVM_CPUID_SIGNATURE | kvm_base;
@ -2529,6 +2610,24 @@ int kvm_arch_init(MachineState *ms, KVMState *s)
}
}
if (s->xen_version) {
#ifdef CONFIG_XEN_EMU
if (!object_dynamic_cast(OBJECT(ms), TYPE_PC_MACHINE)) {
error_report("kvm: Xen support only available in PC machine");
return -ENOTSUP;
}
/* hyperv_enabled() doesn't work yet. */
uint32_t msr = XEN_HYPERCALL_MSR;
ret = kvm_xen_init(s, msr);
if (ret < 0) {
return ret;
}
#else
error_report("kvm: Xen support not enabled in qemu");
return -ENOTSUP;
#endif
}
ret = kvm_get_supported_msrs(s);
if (ret < 0) {
return ret;
@ -4652,6 +4751,15 @@ int kvm_arch_put_registers(CPUState *cpu, int level)
kvm_arch_set_tsc_khz(cpu);
}
#ifdef CONFIG_XEN_EMU
if (xen_mode == XEN_EMULATE && level == KVM_PUT_FULL_STATE) {
ret = kvm_put_xen_state(cpu);
if (ret < 0) {
return ret;
}
}
#endif
ret = kvm_getput_regs(x86_cpu, 1);
if (ret < 0) {
return ret;
@ -4751,6 +4859,14 @@ int kvm_arch_get_registers(CPUState *cs)
if (ret < 0) {
goto out;
}
#ifdef CONFIG_XEN_EMU
if (xen_mode == XEN_EMULATE) {
ret = kvm_get_xen_state(cs);
if (ret < 0) {
goto out;
}
}
#endif
ret = 0;
out:
cpu_sync_bndcs_hflags(&cpu->env);
@ -4875,6 +4991,17 @@ MemTxAttrs kvm_arch_post_run(CPUState *cpu, struct kvm_run *run)
kvm_rate_limit_on_bus_lock();
}
/*
* If the callback is asserted as a GSI (or PCI INTx) then check if
* vcpu_info->evtchn_upcall_pending has been cleared, and deassert
* the callback IRQ if so. Ideally we could hook into the PIC/IOAPIC
* EOI and only resample then, exactly how the VFIO eventfd pairs
* are designed to work for level triggered interrupts.
*/
if (x86_cpu->env.xen_callback_asserted) {
kvm_xen_maybe_deassert_callback(cpu);
}
/* We need to protect the apic state against concurrent accesses from
* different threads in case the userspace irqchip is used. */
if (!kvm_irqchip_in_kernel()) {
@ -5395,6 +5522,11 @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run)
assert(run->msr.reason == KVM_MSR_EXIT_REASON_FILTER);
ret = kvm_handle_wrmsr(cpu, run);
break;
#ifdef CONFIG_XEN_EMU
case KVM_EXIT_XEN:
ret = kvm_xen_handle_exit(cpu, &run->xen);
break;
#endif
default:
fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason);
ret = -1;
@ -5523,6 +5655,20 @@ int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route,
}
}
#ifdef CONFIG_XEN_EMU
if (xen_mode == XEN_EMULATE) {
int handled = xen_evtchn_translate_pirq_msi(route, address, data);
/*
* If it was a PIRQ and successfully routed (handled == 0) or it was
* an error (handled < 0), return. If it wasn't a PIRQ, keep going.
*/
if (handled <= 0) {
return handled;
}
}
#endif
address = kvm_swizzle_msi_ext_dest_id(address);
route->u.msi.address_hi = address >> VTD_MSI_ADDR_HI_SHIFT;
route->u.msi.address_lo = address & VTD_MSI_ADDR_LO_MASK;
@ -5542,8 +5688,8 @@ struct MSIRouteEntry {
static QLIST_HEAD(, MSIRouteEntry) msi_route_list = \
QLIST_HEAD_INITIALIZER(msi_route_list);
static void kvm_update_msi_routes_all(void *private, bool global,
uint32_t index, uint32_t mask)
void kvm_update_msi_routes_all(void *private, bool global,
uint32_t index, uint32_t mask)
{
int cnt = 0, vector;
MSIRouteEntry *entry;
@ -5719,6 +5865,90 @@ static void kvm_arch_set_notify_window(Object *obj, Visitor *v,
s->notify_window = value;
}
static void kvm_arch_get_xen_version(Object *obj, Visitor *v,
const char *name, void *opaque,
Error **errp)
{
KVMState *s = KVM_STATE(obj);
uint32_t value = s->xen_version;
visit_type_uint32(v, name, &value, errp);
}
static void kvm_arch_set_xen_version(Object *obj, Visitor *v,
const char *name, void *opaque,
Error **errp)
{
KVMState *s = KVM_STATE(obj);
Error *error = NULL;
uint32_t value;
visit_type_uint32(v, name, &value, &error);
if (error) {
error_propagate(errp, error);
return;
}
s->xen_version = value;
if (value && xen_mode == XEN_DISABLED) {
xen_mode = XEN_EMULATE;
}
}
static void kvm_arch_get_xen_gnttab_max_frames(Object *obj, Visitor *v,
const char *name, void *opaque,
Error **errp)
{
KVMState *s = KVM_STATE(obj);
uint16_t value = s->xen_gnttab_max_frames;
visit_type_uint16(v, name, &value, errp);
}
static void kvm_arch_set_xen_gnttab_max_frames(Object *obj, Visitor *v,
const char *name, void *opaque,
Error **errp)
{
KVMState *s = KVM_STATE(obj);
Error *error = NULL;
uint16_t value;
visit_type_uint16(v, name, &value, &error);
if (error) {
error_propagate(errp, error);
return;
}
s->xen_gnttab_max_frames = value;
}
static void kvm_arch_get_xen_evtchn_max_pirq(Object *obj, Visitor *v,
const char *name, void *opaque,
Error **errp)
{
KVMState *s = KVM_STATE(obj);
uint16_t value = s->xen_evtchn_max_pirq;
visit_type_uint16(v, name, &value, errp);
}
static void kvm_arch_set_xen_evtchn_max_pirq(Object *obj, Visitor *v,
const char *name, void *opaque,
Error **errp)
{
KVMState *s = KVM_STATE(obj);
Error *error = NULL;
uint16_t value;
visit_type_uint16(v, name, &value, &error);
if (error) {
error_propagate(errp, error);
return;
}
s->xen_evtchn_max_pirq = value;
}
void kvm_arch_accel_class_init(ObjectClass *oc)
{
object_class_property_add_enum(oc, "notify-vmexit", "NotifyVMexitOption",
@ -5735,6 +5965,29 @@ void kvm_arch_accel_class_init(ObjectClass *oc)
object_class_property_set_description(oc, "notify-window",
"Clock cycles without an event window "
"after which a notification VM exit occurs");
object_class_property_add(oc, "xen-version", "uint32",
kvm_arch_get_xen_version,
kvm_arch_set_xen_version,
NULL, NULL);
object_class_property_set_description(oc, "xen-version",
"Xen version to be emulated "
"(in XENVER_version form "
"e.g. 0x4000a for 4.10)");
object_class_property_add(oc, "xen-gnttab-max-frames", "uint16",
kvm_arch_get_xen_gnttab_max_frames,
kvm_arch_set_xen_gnttab_max_frames,
NULL, NULL);
object_class_property_set_description(oc, "xen-gnttab-max-frames",
"Maximum number of grant table frames");
object_class_property_add(oc, "xen-evtchn-max-pirq", "uint16",
kvm_arch_get_xen_evtchn_max_pirq,
kvm_arch_set_xen_evtchn_max_pirq,
NULL, NULL);
object_class_property_set_description(oc, "xen-evtchn-max-pirq",
"Maximum number of Xen PIRQs");
}
void kvm_set_max_apic_id(uint32_t max_apic_id)

2
target/i386/kvm/kvm_i386.h
View File

@ -51,6 +51,8 @@ bool kvm_hv_vpindex_settable(void);
bool kvm_hyperv_expand_features(X86CPU *cpu, Error **errp);
uint64_t kvm_swizzle_msi_ext_dest_id(uint64_t address);
void kvm_update_msi_routes_all(void *private, bool global,
uint32_t index, uint32_t mask);
bool kvm_enable_sgx_provisioning(KVMState *s);
void kvm_request_xsave_components(X86CPU *cpu, uint64_t mask);

2
target/i386/kvm/meson.build
View File

@ -7,6 +7,8 @@ i386_softmmu_kvm_ss.add(files(
'kvm-cpu.c',
))
i386_softmmu_kvm_ss.add(when: 'CONFIG_XEN_EMU', if_true: files('xen-emu.c'))
i386_softmmu_kvm_ss.add(when: 'CONFIG_SEV', if_false: files('sev-stub.c'))
i386_softmmu_ss.add(when: 'CONFIG_HYPERV', if_true: files('hyperv.c'), if_false: files('hyperv-stub.c'))

7
target/i386/kvm/trace-events
View File

@ -5,3 +5,10 @@ kvm_x86_fixup_msi_error(uint32_t gsi) "VT-d failed to remap interrupt for GSI %"
kvm_x86_add_msi_route(int virq) "Adding route entry for virq %d"
kvm_x86_remove_msi_route(int virq) "Removing route entry for virq %d"
kvm_x86_update_msi_routes(int num) "Updated %d MSI routes"
# xen-emu.c
kvm_xen_hypercall(int cpu, uint8_t cpl, uint64_t input, uint64_t a0, uint64_t a1, uint64_t a2, uint64_t ret) "xen_hypercall: cpu %d cpl %d input %" PRIu64 " a0 0x%" PRIx64 " a1 0x%" PRIx64 " a2 0x%" PRIx64" ret 0x%" PRIx64
kvm_xen_soft_reset(void) ""
kvm_xen_set_shared_info(uint64_t gfn) "shared info at gfn 0x%" PRIx64
kvm_xen_set_vcpu_attr(int cpu, int type, uint64_t gpa) "vcpu attr cpu %d type %d gpa 0x%" PRIx64
kvm_xen_set_vcpu_callback(int cpu, int vector) "callback vcpu %d vector %d"

70
target/i386/kvm/xen-compat.h Normal file
View File

@ -0,0 +1,70 @@
/*
* Xen HVM emulation support in KVM
*
* Copyright © 2022 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*
*/
#ifndef QEMU_I386_KVM_XEN_COMPAT_H
#define QEMU_I386_KVM_XEN_COMPAT_H
#include "hw/xen/interface/memory.h"
typedef uint32_t compat_pfn_t;
typedef uint32_t compat_ulong_t;
typedef uint32_t compat_ptr_t;
#define __DEFINE_COMPAT_HANDLE(name, type) \
typedef struct { \
compat_ptr_t c; \
type *_[0] __attribute__((packed)); \
} __compat_handle_ ## name; \
#define DEFINE_COMPAT_HANDLE(name) __DEFINE_COMPAT_HANDLE(name, name)
#define COMPAT_HANDLE(name) __compat_handle_ ## name
DEFINE_COMPAT_HANDLE(compat_pfn_t);
DEFINE_COMPAT_HANDLE(compat_ulong_t);
DEFINE_COMPAT_HANDLE(int);
struct compat_xen_add_to_physmap {
domid_t domid;
uint16_t size;
unsigned int space;
compat_ulong_t idx;
compat_pfn_t gpfn;
};
struct compat_xen_add_to_physmap_batch {
domid_t domid;
uint16_t space;
uint16_t size;
uint16_t extra;
COMPAT_HANDLE(compat_ulong_t) idxs;
COMPAT_HANDLE(compat_pfn_t) gpfns;
COMPAT_HANDLE(int) errs;
};
struct compat_physdev_map_pirq {
domid_t domid;
uint16_t pad;
/* IN */
int type;
/* IN (ignored for ..._MULTI_MSI) */
int index;
/* IN or OUT */
int pirq;
/* IN - high 16 bits hold segment for ..._MSI_SEG and ..._MULTI_MSI */
int bus;
/* IN */
int devfn;
/* IN (also OUT for ..._MULTI_MSI) */
int entry_nr;
/* IN */
uint64_t table_base;
} __attribute__((packed));
#endif /* QEMU_I386_XEN_COMPAT_H */

1897
target/i386/kvm/xen-emu.c Normal file
View File

File diff suppressed because it is too large Load Diff

33
target/i386/kvm/xen-emu.h Normal file
View File

@ -0,0 +1,33 @@
/*
* Xen HVM emulation support in KVM
*
* Copyright © 2019 Oracle and/or its affiliates. All rights reserved.
* Copyright © 2022 Amazon.com, Inc. or its affiliates. All Rights Reserved.
*
* This work is licensed under the terms of the GNU GPL, version 2 or later.
* See the COPYING file in the top-level directory.
*
*/
#ifndef QEMU_I386_KVM_XEN_EMU_H
#define QEMU_I386_KVM_XEN_EMU_H
#define XEN_HYPERCALL_MSR 0x40000000
#define XEN_HYPERCALL_MSR_HYPERV 0x40000200
#define XEN_CPUID_SIGNATURE 0
#define XEN_CPUID_VENDOR 1
#define XEN_CPUID_HVM_MSR 2
#define XEN_CPUID_TIME 3
#define XEN_CPUID_HVM 4
#define XEN_VERSION(maj, min) ((maj) << 16 | (min))
int kvm_xen_init(KVMState *s, uint32_t hypercall_msr);
int kvm_xen_init_vcpu(CPUState *cs);
int kvm_xen_handle_exit(X86CPU *cpu, struct kvm_xen_exit *exit);
int kvm_put_xen_state(CPUState *cs);
int kvm_get_xen_state(CPUState *cs);
void kvm_xen_maybe_deassert_callback(CPUState *cs);
#endif /* QEMU_I386_KVM_XEN_EMU_H */

25
target/i386/machine.c
View File

@ -6,8 +6,10 @@
#include "kvm/hyperv.h"
#include "hw/i386/x86.h"
#include "kvm/kvm_i386.h"
#include "hw/xen/xen.h"
#include "sysemu/kvm.h"
#include "sysemu/kvm_xen.h"
#include "sysemu/tcg.h"
#include "qemu/error-report.h"
@ -1257,6 +1259,28 @@ static const VMStateDescription vmstate_nested_state = {
}
};
static bool xen_vcpu_needed(void *opaque)
{
return (xen_mode == XEN_EMULATE);
}
static const VMStateDescription vmstate_xen_vcpu = {
.name = "cpu/xen_vcpu",
.version_id = 1,
.minimum_version_id = 1,
.needed = xen_vcpu_needed,
.fields = (VMStateField[]) {
VMSTATE_UINT64(env.xen_vcpu_info_gpa, X86CPU),
VMSTATE_UINT64(env.xen_vcpu_info_default_gpa, X86CPU),
VMSTATE_UINT64(env.xen_vcpu_time_info_gpa, X86CPU),
VMSTATE_UINT64(env.xen_vcpu_runstate_gpa, X86CPU),
VMSTATE_UINT8(env.xen_vcpu_callback_vector, X86CPU),
VMSTATE_UINT16_ARRAY(env.xen_virq, X86CPU, XEN_NR_VIRQS),
VMSTATE_UINT64(env.xen_singleshot_timer_ns, X86CPU),
VMSTATE_UINT64(env.xen_periodic_timer_period, X86CPU),
VMSTATE_END_OF_LIST()
}
};
#endif
static bool mcg_ext_ctl_needed(void *opaque)
@ -1716,6 +1740,7 @@ const VMStateDescription vmstate_x86_cpu = {
#endif
#ifdef CONFIG_KVM
&vmstate_nested_state,
&vmstate_xen_vcpu,
#endif
&vmstate_msr_tsx_ctrl,
&vmstate_msr_intel_sgx,

1
tests/qtest/qmp-cmd-test.c
View File

@ -54,6 +54,7 @@ static int query_error_class(const char *cmd)
/* Only valid with accel=tcg */
{ "x-query-jit", ERROR_CLASS_GENERIC_ERROR },
{ "x-query-opcount", ERROR_CLASS_GENERIC_ERROR },
{ "xen-event-list", ERROR_CLASS_GENERIC_ERROR },
{ NULL, -1 }
};
int i;