Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging

pc, pci, virtio: new features, cleanups, fixes

nvdimm label support
cpu acpi hotplug rework
virtio rework
misc cleanups and fixes

Signed-off-by: Michael S. Tsirkin <mst@redhat.com>

# gpg: Signature made Fri 24 Jun 2016 06:50:32 BST
# gpg:                using RSA key 0x281F0DB8D28D5469
# gpg: Good signature from "Michael S. Tsirkin <mst@kernel.org>"
# gpg:                 aka "Michael S. Tsirkin <mst@redhat.com>"
# Primary key fingerprint: 0270 606B 6F3C DF3D 0B17  0970 C350 3912 AFBE 8E67
#      Subkey fingerprint: 5D09 FD08 71C8 F85B 94CA  8A0D 281F 0DB8 D28D 5469

* remotes/mst/tags/for_upstream: (34 commits)
  virtio-bus: remove old set_host_notifier callback
  virtio-mmio: convert to ioeventfd callbacks
  virtio-pci: convert to ioeventfd callbacks
  virtio-ccw: convert to ioeventfd callbacks
  virtio-bus: have callers tolerate new host notifier api
  virtio-bus: common ioeventfd infrastructure
  pc: acpi: drop intermediate PCMachineState.node_cpu
  acpi-test-data: update expected
  pc: use new CPU hotplug interface since 2.7 machine type
  acpi: cpuhp: add cpu._OST handling
  acpi: cpuhp: implement hot-remove parts of CPU hotplug interface
  acpi: cpuhp: implement hot-add parts of CPU hotplug interface
  pc: acpi: introduce AcpiDeviceIfClass.madt_cpu hook
  acpi: cpuhp: add CPU devices AML with _STA method
  pc: piix4/ich9: add 'cpu-hotplug-legacy' property
  docs: update ACPI CPU hotplug spec with new protocol
  i386: pci-assign: Fix MSI-X table size
  docs: add NVDIMM ACPI documentation
  nvdimm acpi: support Set Namespace Label Data function
  nvdimm acpi: support Get Namespace Label Data function
  ...

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

11 files changed, 218 insertions, 4 deletions

diff --git a/include/hw/acpi/acpi_dev_interface.h b/include/hw/acpi/acpi_dev_interface.h
index a0c4a33..da4ef7f 100644
--- a/include/hw/acpi/acpi_dev_interface.h
+++ b/include/hw/acpi/acpi_dev_interface.h
@@ -3,6 +3,7 @@
 
 #include "qom/object.h"
 #include "qapi-types.h"
+#include "hw/boards.h"
 
 /* These values are part of guest ABI, and can not be changed */
 typedef enum {
@@ -37,6 +38,10 @@ void acpi_send_event(DeviceState *dev, AcpiEventStatusBits event);
  * ospm_status: returns status of ACPI device objects, reported
  *              via _OST method if device supports it.
  * send_event: inject a specified event into guest
+ * madt_cpu: fills @entry with Interrupt Controller Structure
+ *           for CPU indexed by @uid in @apic_ids array,
+ *           returned structure types are:
+ *           0 - Local APIC, 9 - Local x2APIC, 0xB - GICC
  *
  * Interface is designed for providing unified interface
  * to generic ACPI functionality that could be used without
@@ -50,5 +55,7 @@ typedef struct AcpiDeviceIfClass {
     /* <public> */
     void (*ospm_status)(AcpiDeviceIf *adev, ACPIOSTInfoList ***list);
     void (*send_event)(AcpiDeviceIf *adev, AcpiEventStatusBits ev);
+    void (*madt_cpu)(AcpiDeviceIf *adev, int uid,
+                     CPUArchIdList *apic_ids, GArray *entry);
 } AcpiDeviceIfClass;
 #endif
diff --git a/include/hw/acpi/aml-build.h b/include/hw/acpi/aml-build.h
index 10c09ca..e7a1a4c 100644
--- a/include/hw/acpi/aml-build.h
+++ b/include/hw/acpi/aml-build.h
@@ -277,6 +277,8 @@ Aml *aml_call1(const char *method, Aml *arg1);
 Aml *aml_call2(const char *method, Aml *arg1, Aml *arg2);
 Aml *aml_call3(const char *method, Aml *arg1, Aml *arg2, Aml *arg3);
 Aml *aml_call4(const char *method, Aml *arg1, Aml *arg2, Aml *arg3, Aml *arg4);
+Aml *aml_call5(const char *method, Aml *arg1, Aml *arg2, Aml *arg3, Aml *arg4,
+               Aml *arg5);
 Aml *aml_gpio_int(AmlConsumerAndProducer con_and_pro,
                   AmlLevelAndEdge edge_level,
                   AmlActiveHighAndLow active_level, AmlShared shared,
@@ -363,6 +365,7 @@ Aml *aml_refof(Aml *arg);
 Aml *aml_derefof(Aml *arg);
 Aml *aml_sizeof(Aml *arg);
 Aml *aml_concatenate(Aml *source1, Aml *source2, Aml *target);
+Aml *aml_object_type(Aml *object);
 
 void
 build_header(BIOSLinker *linker, GArray *table_data,
diff --git a/include/hw/acpi/cpu.h b/include/hw/acpi/cpu.h
new file mode 100644
index 0000000..89ce172
--- /dev/null
+++ b/include/hw/acpi/cpu.h
@@ -0,0 +1,67 @@
+/*
+ * QEMU ACPI hotplug utilities
+ *
+ * Copyright (C) 2016 Red Hat Inc
+ *
+ * Authors:
+ *   Igor Mammedov <imammedo@redhat.com>
+ *
+ * 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 ACPI_CPU_H
+#define ACPI_CPU_H
+
+#include "hw/qdev-core.h"
+#include "hw/acpi/acpi.h"
+#include "hw/acpi/aml-build.h"
+#include "hw/hotplug.h"
+
+typedef struct AcpiCpuStatus {
+    struct CPUState *cpu;
+    uint64_t arch_id;
+    bool is_inserting;
+    bool is_removing;
+    uint32_t ost_event;
+    uint32_t ost_status;
+} AcpiCpuStatus;
+
+typedef struct CPUHotplugState {
+    MemoryRegion ctrl_reg;
+    uint32_t selector;
+    uint8_t command;
+    uint32_t dev_count;
+    AcpiCpuStatus *devs;
+} CPUHotplugState;
+
+void acpi_cpu_plug_cb(HotplugHandler *hotplug_dev,
+                      CPUHotplugState *cpu_st, DeviceState *dev, Error **errp);
+
+void acpi_cpu_unplug_request_cb(HotplugHandler *hotplug_dev,
+                                CPUHotplugState *cpu_st,
+                                DeviceState *dev, Error **errp);
+
+void acpi_cpu_unplug_cb(CPUHotplugState *cpu_st,
+                        DeviceState *dev, Error **errp);
+
+void cpu_hotplug_hw_init(MemoryRegion *as, Object *owner,
+                         CPUHotplugState *state, hwaddr base_addr);
+
+typedef struct CPUHotplugFeatures {
+    bool apci_1_compatible;
+    bool has_legacy_cphp;
+} CPUHotplugFeatures;
+
+void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
+                    hwaddr io_base,
+                    const char *res_root,
+                    const char *event_handler_method);
+
+void acpi_cpu_ospm_status(CPUHotplugState *cpu_st, ACPIOSTInfoList ***list);
+
+extern const VMStateDescription vmstate_cpu_hotplug;
+#define VMSTATE_CPU_HOTPLUG(cpuhp, state) \
+    VMSTATE_STRUCT(cpuhp, state, 1, \
+                   vmstate_cpu_hotplug, CPUHotplugState)
+
+#endif
diff --git a/include/hw/acpi/cpu_hotplug.h b/include/hw/acpi/cpu_hotplug.h
index 6fef67e..b995ef2 100644
--- a/include/hw/acpi/cpu_hotplug.h
+++ b/include/hw/acpi/cpu_hotplug.h
@@ -16,8 +16,10 @@
 #include "hw/acpi/pc-hotplug.h"
 #include "hw/acpi/aml-build.h"
 #include "hw/hotplug.h"
+#include "hw/acpi/cpu.h"
 
 typedef struct AcpiCpuHotplug {
+    Object *device;
     MemoryRegion io;
     uint8_t sts[ACPI_GPE_PROC_LEN];
 } AcpiCpuHotplug;
@@ -28,6 +30,10 @@ void legacy_acpi_cpu_plug_cb(HotplugHandler *hotplug_dev,
 void legacy_acpi_cpu_hotplug_init(MemoryRegion *parent, Object *owner,
                                   AcpiCpuHotplug *gpe_cpu, uint16_t base);
 
+void acpi_switch_to_modern_cphp(AcpiCpuHotplug *gpe_cpu,
+                                CPUHotplugState *cpuhp_state,
+                                uint16_t io_port);
+
 void build_legacy_cpu_hotplug_aml(Aml *ctx, MachineState *machine,
                                   uint16_t io_base);
 #endif
diff --git a/include/hw/acpi/ich9.h b/include/hw/acpi/ich9.h
index bbd657c..a352c94 100644
--- a/include/hw/acpi/ich9.h
+++ b/include/hw/acpi/ich9.h
@@ -23,6 +23,7 @@
 
 #include "hw/acpi/acpi.h"
 #include "hw/acpi/cpu_hotplug.h"
+#include "hw/acpi/cpu.h"
 #include "hw/acpi/memory_hotplug.h"
 #include "hw/acpi/acpi_dev_interface.h"
 #include "hw/acpi/tco.h"
@@ -48,7 +49,9 @@ typedef struct ICH9LPCPMRegs {
     uint32_t pm_io_base;
     Notifier powerdown_notifier;
 
+    bool cpu_hotplug_legacy;
     AcpiCpuHotplug gpe_cpu;
+    CPUHotplugState cpuhp_state;
 
     MemHotplugState acpi_memory_hotplug;
 
diff --git a/include/hw/acpi/ipmi.h b/include/hw/acpi/ipmi.h
new file mode 100644
index 0000000..ab2bb29
--- /dev/null
+++ b/include/hw/acpi/ipmi.h
@@ -0,0 +1,22 @@
+/*
+ * QEMU IPMI ACPI handling
+ *
+ * Copyright (c) 2015,2016 Corey Minyard <cminyard@mvista.com>
+ *
+ * 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 HW_ACPI_IPMI_H
+#define HW_ACPI_IPMI_H
+
+#include "qemu/osdep.h"
+#include "hw/acpi/aml-build.h"
+
+/*
+ * Add ACPI IPMI entries for all registered IPMI devices whose parent
+ * bus matches the given bus.  The resource is the ACPI resource that
+ * contains the IPMI device, this is required for the I2C CRS.
+ */
+void build_acpi_ipmi_devices(Aml *table, BusState *bus);
+
+#endif /* HW_ACPI_IPMI_H */
diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h
index 49566c8..948ed0c 100644
--- a/include/hw/i386/pc.h
+++ b/include/hw/i386/pc.h
@@ -17,6 +17,7 @@
 #include "hw/compat.h"
 #include "hw/mem/pc-dimm.h"
 #include "hw/mem/nvdimm.h"
+#include "hw/acpi/acpi_dev_interface.h"
 
 #define HPET_INTCAP "hpet-intcap"
 
@@ -71,7 +72,6 @@ struct PCMachineState {
     /* NUMA information: */
     uint64_t numa_nodes;
     uint64_t *node_mem;
-    uint64_t *node_cpu;
 };
 
 #define PC_MACHINE_ACPI_DEVICE_PROP "acpi-device"
@@ -136,6 +136,8 @@ struct PCMachineClass {
 
     /* TSC rate migration: */
     bool save_tsc_khz;
+    /* generate legacy CPU hotplug AML */
+    bool legacy_cpu_hotplug;
 };
 
 #define TYPE_PC_MACHINE "generic-pc-machine"
@@ -345,6 +347,10 @@ void pc_system_firmware_init(MemoryRegion *rom_memory,
 /* pvpanic.c */
 uint16_t pvpanic_port(void);
 
+/* acpi-build.c */
+void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid,
+                       CPUArchIdList *apic_ids, GArray *entry);
+
 /* e820 types */
 #define E820_RAM        1
 #define E820_RESERVED   2
diff --git a/include/hw/mem/nvdimm.h b/include/hw/mem/nvdimm.h
index 60ee92b..1cfe9e0 100644
--- a/include/hw/mem/nvdimm.h
+++ b/include/hw/mem/nvdimm.h
@@ -34,7 +34,60 @@
         }                                                     \
     } while (0)
 
-#define TYPE_NVDIMM             "nvdimm"
+/*
+ * The minimum label data size is required by NVDIMM Namespace
+ * specification, see the chapter 2 Namespaces:
+ *   "NVDIMMs following the NVDIMM Block Mode Specification use an area
+ *    at least 128KB in size, which holds around 1000 labels."
+ */
+#define MIN_NAMESPACE_LABEL_SIZE      (128UL << 10)
+
+#define TYPE_NVDIMM      "nvdimm"
+#define NVDIMM(obj)      OBJECT_CHECK(NVDIMMDevice, (obj), TYPE_NVDIMM)
+#define NVDIMM_CLASS(oc) OBJECT_CLASS_CHECK(NVDIMMClass, (oc), TYPE_NVDIMM)
+#define NVDIMM_GET_CLASS(obj) OBJECT_GET_CLASS(NVDIMMClass, (obj), \
+                                               TYPE_NVDIMM)
+struct NVDIMMDevice {
+    /* private */
+    PCDIMMDevice parent_obj;
+
+    /* public */
+
+    /*
+     * the size of label data in NVDIMM device which is presented to
+     * guest via __DSM "Get Namespace Label Size" function.
+     */
+    uint64_t label_size;
+
+    /*
+     * the address of label data which is read by __DSM "Get Namespace
+     * Label Data" function and written by __DSM "Set Namespace Label
+     * Data" function.
+     */
+    void *label_data;
+
+    /*
+     * it's the PMEM region in NVDIMM device, which is presented to
+     * guest via ACPI NFIT and _FIT method if NVDIMM hotplug is supported.
+     */
+    MemoryRegion nvdimm_mr;
+};
+typedef struct NVDIMMDevice NVDIMMDevice;
+
+struct NVDIMMClass {
+    /* private */
+    PCDIMMDeviceClass parent_class;
+
+    /* public */
+
+    /* read @size bytes from NVDIMM label data at @offset into @buf. */
+    void (*read_label_data)(NVDIMMDevice *nvdimm, void *buf,
+                            uint64_t size, uint64_t offset);
+    /* write @size bytes from @buf to NVDIMM label data at @offset. */
+    void (*write_label_data)(NVDIMMDevice *nvdimm, const void *buf,
+                             uint64_t size, uint64_t offset);
+};
+typedef struct NVDIMMClass NVDIMMClass;
 
 #define NVDIMM_DSM_MEM_FILE     "etc/acpi/nvdimm-mem"
 
diff --git a/include/hw/mem/pc-dimm.h b/include/hw/mem/pc-dimm.h
index 67e92d8..1e483f2 100644
--- a/include/hw/mem/pc-dimm.h
+++ b/include/hw/mem/pc-dimm.h
@@ -61,7 +61,9 @@ typedef struct PCDIMMDevice {
  * @realize: called after common dimm is realized so that the dimm based
  * devices get the chance to do specified operations.
  * @get_memory_region: returns #MemoryRegion associated with @dimm which
- * is directly mapped into the physical address space of guest
+ * is directly mapped into the physical address space of guest.
+ * @get_vmstate_memory_region: returns #MemoryRegion which indicates the
+ * memory of @dimm should be kept during live migration.
  */
 typedef struct PCDIMMDeviceClass {
     /* private */
@@ -70,6 +72,7 @@ typedef struct PCDIMMDeviceClass {
     /* public */
     void (*realize)(PCDIMMDevice *dimm, Error **errp);
     MemoryRegion *(*get_memory_region)(PCDIMMDevice *dimm);
+    MemoryRegion *(*get_vmstate_memory_region)(PCDIMMDevice *dimm);
 } PCDIMMDeviceClass;
 
 /**
diff --git a/include/hw/smbios/ipmi.h b/include/hw/smbios/ipmi.h
new file mode 100644
index 0000000..1c9aae3
--- /dev/null
+++ b/include/hw/smbios/ipmi.h
@@ -0,0 +1,15 @@
+/*
+ * IPMI SMBIOS firmware handling
+ *
+ * Copyright (c) 2015,2016 Corey Minyard, MontaVista Software, LLC
+ *
+ * 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_SMBIOS_IPMI_H
+#define QEMU_SMBIOS_IPMI_H
+
+void smbios_build_type_38_table(void);
+
+#endif /* QEMU_SMBIOS_IPMI_H */
diff --git a/include/hw/virtio/virtio-bus.h b/include/hw/virtio/virtio-bus.h
index 3f2c136..f3e5ef3 100644
--- a/include/hw/virtio/virtio-bus.h
+++ b/include/hw/virtio/virtio-bus.h
@@ -52,7 +52,6 @@ typedef struct VirtioBusClass {
     bool (*has_extra_state)(DeviceState *d);
     bool (*query_guest_notifiers)(DeviceState *d);
     int (*set_guest_notifiers)(DeviceState *d, int nvqs, bool assign);
-    int (*set_host_notifier)(DeviceState *d, int n, bool assigned);
     void (*vmstate_change)(DeviceState *d, bool running);
     /*
      * transport independent init function.
@@ -71,6 +70,29 @@ typedef struct VirtioBusClass {
     void (*device_unplugged)(DeviceState *d);
     int (*query_nvectors)(DeviceState *d);
     /*
+     * ioeventfd handling: if the transport implements ioeventfd_started,
+     * it must implement the other ioeventfd callbacks as well
+     */
+    /* Returns true if the ioeventfd has been started for the device. */
+    bool (*ioeventfd_started)(DeviceState *d);
+    /*
+     * Sets the 'ioeventfd started' state after the ioeventfd has been
+     * started/stopped for the device. err signifies whether an error
+     * had occurred.
+     */
+    void (*ioeventfd_set_started)(DeviceState *d, bool started, bool err);
+    /* Returns true if the ioeventfd has been disabled for the device. */
+    bool (*ioeventfd_disabled)(DeviceState *d);
+    /* Sets the 'ioeventfd disabled' state for the device. */
+    void (*ioeventfd_set_disabled)(DeviceState *d, bool disabled);
+    /*
+     * Assigns/deassigns the ioeventfd backing for the transport on
+     * the device for queue number n. Returns an error value on
+     * failure.
+     */
+    int (*ioeventfd_assign)(DeviceState *d, EventNotifier *notifier,
+                            int n, bool assign);
+    /*
      * Does the transport have variable vring alignment?
      * (ie can it ever call virtio_queue_set_align()?)
      * Note that changing this will break migration for this transport.
@@ -111,4 +133,11 @@ static inline VirtIODevice *virtio_bus_get_device(VirtioBusState *bus)
     return (VirtIODevice *)qdev;
 }
 
+/* Start the ioeventfd. */
+void virtio_bus_start_ioeventfd(VirtioBusState *bus);
+/* Stop the ioeventfd. */
+void virtio_bus_stop_ioeventfd(VirtioBusState *bus);
+/* Switch from/to the generic ioeventfd handler */
+int virtio_bus_set_host_notifier(VirtioBusState *bus, int n, bool assign);
+
 #endif /* VIRTIO_BUS_H */