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>
2026-07-06 00:20:22 -07:00 · 2023-03-02 16:13:45 +00:00
parent 262312d7ba 526947e496
commit c61d1a066c
82 changed files with 13465 additions and 211 deletions
@@ -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 \( -name "*.[chsS]" -o -name "*.[ch].inc" \)
@@ -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;
 }

 /**
@@ -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;
 }

@@ -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).
@@ -27,6 +27,7 @@ Architectural features

   i386/cpu
   i386/hyperv
+   i386/xen
   i386/kvm-pv
   i386/sgx
   i386/amd-memory-encryption
@@ -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
@@ -41,6 +41,7 @@ source tpm/Kconfig
 source usb/Kconfig
 source virtio/Kconfig
 source vfio/Kconfig
+source xen/Kconfig
 source watchdog/Kconfig

 # arch Kconfig
@@ -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);
        }
@@ -136,3 +136,8 @@ config VMPORT
 config VMMOUSE
    bool
    depends on VMPORT
+
+config XEN_EMU
+    bool
+    default y
+    depends on KVM && (I386 || X86_64)
@@ -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)
@@ -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"
@@ -0,0 +1 @@
+#include "trace/trace-hw_i386_kvm.h"
@@ -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
@@ -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 */
@@ -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;
+}
@@ -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 */
@@ -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;
+}
@@ -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 */
--- a/Show More
+++ b/Show More