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

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>
 -----BEGIN PGP SIGNATURE-----
 Version: GnuPG v1
 
 iQEcBAABAgAGBQJXbMooAAoJECgfDbjSjVRp0fYIAJ8hWf4im66Y/+Tyk957XJJt
 GZ4axsa21/k6gbVZxrx6jAUwjzWEqLeXKiZ79YMVtE1SIUhSqs1exhfrGhNNXjvn
 t46utHtwMnb6XPb2ru4+bQr1u+NN7RtTmi9Sd3uonWnIGXFrA69QeFejCVcEcSvJ
 uiwjkODmPW0+7gRLa4SP80iS1E6nSA96Z7aOMdbQNMIW1HRVulkiXO2lwg8yz5D0
 QkTqMUk/VK22RFnskDLDnTjXTADSx8L1ipjSkr4D92jTJ06ZLklVe9vijbpmd85k
 ScLRNSgMstkrCe9wuP1CWZeiAG+t7QLBRJWQh7kSk7xWJONP9ShZRX4MbCl7mwI=
 =XqTl
 -----END PGP SIGNATURE-----

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>
This commit is contained in:
Peter Maydell 2016-06-24 11:00:15 +01:00
parent c728876752 21a4d96243
commit a01aef5d2f
53 changed files with 2509 additions and 443 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

94
docs/specs/acpi_cpu_hotplug.txt
View File

@ -4,21 +4,91 @@ QEMU<->ACPI BIOS CPU hotplug interface
QEMU supports CPU hotplug via ACPI. This document
describes the interface between QEMU and the ACPI BIOS.
ACPI GPE block (IO ports 0xafe0-0xafe3, byte access):
-----------------------------------------
Generic ACPI GPE block. Bit 2 (GPE.2) used to notify CPU
hot-add/remove event to ACPI BIOS, via SCI interrupt.
ACPI BIOS GPE.2 handler is dedicated for notifying OS about CPU hot-add
and hot-remove events.
============================================
Legacy ACPI CPU hotplug interface registers:
--------------------------------------------
CPU present bitmap for:
ICH9-LPC (IO port 0x0cd8-0xcf7, 1-byte access)
PIIX-PM (IO port 0xaf00-0xaf1f, 1-byte access)
One bit per CPU. Bit position reflects corresponding CPU APIC ID. Read-only.
The first DWORD in bitmap is used in write mode to switch from legacy
to new CPU hotplug interface, write 0 into it to do switch.
---------------------------------------------------------------
One bit per CPU. Bit position reflects corresponding CPU APIC ID.
Read-only.
QEMU sets corresponding CPU bit on hot-add event and issues SCI
with GPE.2 event set. CPU present map is read by ACPI BIOS GPE.2 handler
to notify OS about CPU hot-add events. CPU hot-remove isn't supported.
CPU hot-add/remove notification:
-----------------------------------------------------
QEMU sets/clears corresponding CPU bit on hot-add/remove event.
CPU present map read by ACPI BIOS GPE.2 handler to notify OS of CPU
hot-(un)plug events.
=====================================
ACPI CPU hotplug interface registers:
-------------------------------------
Register block base address:
ICH9-LPC IO port 0x0cd8
PIIX-PM IO port 0xaf00
Register block size:
ACPI_CPU_HOTPLUG_REG_LEN = 12
read access:
offset:
[0x0-0x3] reserved
[0x4] CPU device status fields: (1 byte access)
bits:
0: Device is enabled and may be used by guest
1: Device insert event, used to distinguish device for which
no device check event to OSPM was issued.
It's valid only when bit 0 is set.
2: Device remove event, used to distinguish device for which
no device eject request to OSPM was issued.
3-7: reserved and should be ignored by OSPM
[0x5-0x7] reserved
[0x8] Command data: (DWORD access)
in case of error or unsupported command reads is 0xFFFFFFFF
current 'Command field' value:
0: returns PXM value corresponding to device
write access:
offset:
[0x0-0x3] CPU selector: (DWORD access)
selects active CPU device. All following accesses to other
registers will read/store data from/to selected CPU.
[0x4] CPU device control fields: (1 byte access)
bits:
0: reserved, OSPM must clear it before writing to register.
1: if set to 1 clears device insert event, set by OSPM
after it has emitted device check event for the
selected CPU device
2: if set to 1 clears device remove event, set by OSPM
after it has emitted device eject request for the
selected CPU device
3: if set to 1 initiates device eject, set by OSPM when it
triggers CPU device removal and calls _EJ0 method
4-7: reserved, OSPM must clear them before writing to register
[0x5] Command field: (1 byte access)
value:
0: selects a CPU device with inserting/removing events and
following reads from 'Command data' register return
selected CPU (CPU selector value). If no CPU with events
found, the current CPU selector doesn't change and
corresponding insert/remove event flags are not set.
1: following writes to 'Command data' register set OST event
register in QEMU
2: following writes to 'Command data' register set OST status
register in QEMU
other values: reserved
[0x6-0x7] reserved
[0x8] Command data: (DWORD access)
current 'Command field' value:
0: OSPM reads value of CPU selector
1: stores value into OST event register
2: stores value into OST status register, triggers
ACPI_DEVICE_OST QMP event from QEMU to external applications
with current values of OST event and status registers.
other values: reserved
Selecting CPU device beyond possible range has no effect on platform:
- write accesses to CPU hot-plug registers not documented above are
ignored
- read accesses to CPU hot-plug registers not documented above return
all bits set to 0.

132
docs/specs/acpi_nvdimm.txt Normal file
View File

@ -0,0 +1,132 @@
QEMU<->ACPI BIOS NVDIMM interface
---------------------------------
QEMU supports NVDIMM via ACPI. This document describes the basic concepts of
NVDIMM ACPI and the interface between QEMU and the ACPI BIOS.
NVDIMM ACPI Background
----------------------
NVDIMM is introduced in ACPI 6.0 which defines an NVDIMM root device under
_SB scope with a _HID of “ACPI0012”. For each NVDIMM present or intended
to be supported by platform, platform firmware also exposes an ACPI
Namespace Device under the root device.
The NVDIMM child devices under the NVDIMM root device are defined with _ADR
corresponding to the NFIT device handle. The NVDIMM root device and the
NVDIMM devices can have device specific methods (_DSM) to provide additional
functions specific to a particular NVDIMM implementation.
This is an example from ACPI 6.0, a platform contains one NVDIMM:
Scope (\_SB){
Device (NVDR) // Root device
{
Name (_HID, “ACPI0012”)
Method (_STA) {...}
Method (_FIT) {...}
Method (_DSM, ...) {...}
Device (NVD)
{
Name(_ADR, h) //where h is NFIT Device Handle for this NVDIMM
Method (_DSM, ...) {...}
}
}
}
Method supported on both NVDIMM root device and NVDIMM device
_DSM (Device Specific Method)
It is a control method that enables devices to provide device specific
control functions that are consumed by the device driver.
The NVDIMM DSM specification can be found at:
http://pmem.io/documents/NVDIMM_DSM_Interface_Example.pdf
Arguments:
Arg0 – A Buffer containing a UUID (16 Bytes)
Arg1 – An Integer containing the Revision ID (4 Bytes)
Arg2 – An Integer containing the Function Index (4 Bytes)
Arg3 – A package containing parameters for the function specified by the
UUID, Revision ID, and Function Index
Return Value:
If Function Index = 0, a Buffer containing a function index bitfield.
Otherwise, the return value and type depends on the UUID, revision ID
and function index which are described in the DSM specification.
Methods on NVDIMM ROOT Device
_FIT(Firmware Interface Table)
It evaluates to a buffer returning data in the format of a series of NFIT
Type Structure.
Arguments: None
Return Value:
A Buffer containing a list of NFIT Type structure entries.
The detailed definition of the structure can be found at ACPI 6.0: 5.2.25
NVDIMM Firmware Interface Table (NFIT).
QEMU NVDIMM Implemention
========================
QEMU uses 4 bytes IO Port starting from 0x0a18 and a RAM-based memory page
for NVDIMM ACPI.
Memory:
QEMU uses BIOS Linker/loader feature to ask BIOS to allocate a memory
page and dynamically patch its into a int32 object named "MEMA" in ACPI.
This page is RAM-based and it is used to transfer data between _DSM
method and QEMU. If ACPI has control, this pages is owned by ACPI which
writes _DSM input data to it, otherwise, it is owned by QEMU which
emulates _DSM access and writes the output data to it.
ACPI writes _DSM Input Data (based on the offset in the page):
[0x0 - 0x3]: 4 bytes, NVDIMM Device Handle, 0 is reserved for NVDIMM
Root device.
[0x4 - 0x7]: 4 bytes, Revision ID, that is the Arg1 of _DSM method.
[0x8 - 0xB]: 4 bytes. Function Index, that is the Arg2 of _DSM method.
[0xC - 0xFFF]: 4084 bytes, the Arg3 of _DSM method.
QEMU Writes Output Data (based on the offset in the page):
[0x0 - 0x3]: 4 bytes, the length of result
[0x4 - 0xFFF]: 4092 bytes, the DSM result filled by QEMU
IO Port 0x0a18 - 0xa1b:
ACPI writes the address of the memory page allocated by BIOS to this
port then QEMU gets the control and fills the result in the memory page.
write Access:
[0x0a18 - 0xa1b]: 4 bytes, the address of the memory page allocated
by BIOS.
_DSM process diagram:
---------------------
"MEMA" indicates the address of memory page allocated by BIOS.
+----------------------+   +-----------------------+
 |   1. OSPM   |      | 2. OSPM |
 | save _DSM input data | | write "MEMA" to | Exit to QEMU
 | to the page +----->| IO port 0x0a18 +------------+
 | indicated by "MEMA" | | | |
 +----------------------+ +-----------------------+ |
  |
  v
 +------------- ----+ +-----------+ +------------------+--------+
 | 5 QEMU | | 4 QEMU | | 3. QEMU |
 | write _DSM result | | emulate | | get _DSM input data from |
| to the page +<------+ _DSM +<-----+ the page indicated by the |
 | | | | | value from the IO port |
+--------+-----------+ +-----------+ +---------------------------+
|
| Enter Guest
|
v
+--------------------------+ +--------------+
| 6 OSPM | | 7 OSPM |
| result size is returned | | _DSM return |
| by reading DSM +----->+ |
| result from the page | | |
+--------------------------+ +--------------+
_FIT implementation
-------------------
TODO (will fill it when nvdimm hotplug is introduced)

2
hw/acpi/Makefile.objs
View File

@ -2,7 +2,9 @@ common-obj-$(CONFIG_ACPI_X86) += core.o piix4.o pcihp.o
common-obj-$(CONFIG_ACPI_X86_ICH) += ich9.o tco.o
common-obj-$(CONFIG_ACPI_CPU_HOTPLUG) += cpu_hotplug.o
common-obj-$(CONFIG_ACPI_MEMORY_HOTPLUG) += memory_hotplug.o memory_hotplug_acpi_table.o
common-obj-$(CONFIG_ACPI_CPU_HOTPLUG) += cpu.o
obj-$(CONFIG_ACPI_NVDIMM) += nvdimm.o
common-obj-$(CONFIG_ACPI) += acpi_interface.o
common-obj-$(CONFIG_ACPI) += bios-linker-loader.o
common-obj-$(CONFIG_ACPI) += aml-build.o
common-obj-$(call land,$(CONFIG_ACPI),$(CONFIG_IPMI)) += ipmi.o

22
hw/acpi/aml-build.c
View File

@ -660,6 +660,20 @@ Aml *aml_call4(const char *method, Aml *arg1, Aml *arg2, Aml *arg3, Aml *arg4)
return var;
}
/* helper to call method with 5 arguments */
Aml *aml_call5(const char *method, Aml *arg1, Aml *arg2, Aml *arg3, Aml *arg4,
Aml *arg5)
{
Aml *var = aml_alloc();
build_append_namestring(var->buf, "%s", method);
aml_append(var, arg1);
aml_append(var, arg2);
aml_append(var, arg3);
aml_append(var, arg4);
aml_append(var, arg5);
return var;
}
/*
* ACPI 5.0: 6.4.3.8.1 GPIO Connection Descriptor
* Type 1, Large Item Name 0xC
@ -1481,6 +1495,14 @@ Aml *aml_concatenate(Aml *source1, Aml *source2, Aml *target)
target);
}
/* ACPI 1.0b: 16.2.5.4 Type 2 Opcodes Encoding: DefObjectType */
Aml *aml_object_type(Aml *object)
{
Aml *var = aml_opcode(0x8E /* ObjectTypeOp */);
aml_append(var, object);
return var;
}
void
build_header(BIOSLinker *linker, GArray *table_data,
AcpiTableHeader *h, const char *sig, int len, uint8_t rev,

561
hw/acpi/cpu.c Normal file
View File

@ -0,0 +1,561 @@
#include "qemu/osdep.h"
#include "hw/boards.h"
#include "hw/acpi/cpu.h"
#include "qapi/error.h"
#include "qapi-event.h"
#include "trace.h"
#define ACPI_CPU_HOTPLUG_REG_LEN 12
#define ACPI_CPU_SELECTOR_OFFSET_WR 0
#define ACPI_CPU_FLAGS_OFFSET_RW 4
#define ACPI_CPU_CMD_OFFSET_WR 5
#define ACPI_CPU_CMD_DATA_OFFSET_RW 8
enum {
CPHP_GET_NEXT_CPU_WITH_EVENT_CMD = 0,
CPHP_OST_EVENT_CMD = 1,
CPHP_OST_STATUS_CMD = 2,
CPHP_CMD_MAX
};
static ACPIOSTInfo *acpi_cpu_device_status(int idx, AcpiCpuStatus *cdev)
{
ACPIOSTInfo *info = g_new0(ACPIOSTInfo, 1);
info->slot_type = ACPI_SLOT_TYPE_CPU;
info->slot = g_strdup_printf("%d", idx);
info->source = cdev->ost_event;
info->status = cdev->ost_status;
if (cdev->cpu) {
DeviceState *dev = DEVICE(cdev->cpu);
if (dev->id) {
info->device = g_strdup(dev->id);
info->has_device = true;
}
}
return info;
}
void acpi_cpu_ospm_status(CPUHotplugState *cpu_st, ACPIOSTInfoList ***list)
{
int i;
for (i = 0; i < cpu_st->dev_count; i++) {
ACPIOSTInfoList *elem = g_new0(ACPIOSTInfoList, 1);
elem->value = acpi_cpu_device_status(i, &cpu_st->devs[i]);
elem->next = NULL;
**list = elem;
*list = &elem->next;
}
}
static uint64_t cpu_hotplug_rd(void *opaque, hwaddr addr, unsigned size)
{
uint64_t val = 0;
CPUHotplugState *cpu_st = opaque;
AcpiCpuStatus *cdev;
if (cpu_st->selector >= cpu_st->dev_count) {
return val;
}
cdev = &cpu_st->devs[cpu_st->selector];
switch (addr) {
case ACPI_CPU_FLAGS_OFFSET_RW: /* pack and return is_* fields */
val |= cdev->cpu ? 1 : 0;
val |= cdev->is_inserting ? 2 : 0;
val |= cdev->is_removing ? 4 : 0;
trace_cpuhp_acpi_read_flags(cpu_st->selector, val);
break;
case ACPI_CPU_CMD_DATA_OFFSET_RW:
switch (cpu_st->command) {
case CPHP_GET_NEXT_CPU_WITH_EVENT_CMD:
val = cpu_st->selector;
break;
default:
break;
}
trace_cpuhp_acpi_read_cmd_data(cpu_st->selector, val);
break;
default:
break;
}
return val;
}
static void cpu_hotplug_wr(void *opaque, hwaddr addr, uint64_t data,
unsigned int size)
{
CPUHotplugState *cpu_st = opaque;
AcpiCpuStatus *cdev;
ACPIOSTInfo *info;
assert(cpu_st->dev_count);
if (addr) {
if (cpu_st->selector >= cpu_st->dev_count) {
trace_cpuhp_acpi_invalid_idx_selected(cpu_st->selector);
return;
}
}
switch (addr) {
case ACPI_CPU_SELECTOR_OFFSET_WR: /* current CPU selector */
cpu_st->selector = data;
trace_cpuhp_acpi_write_idx(cpu_st->selector);
break;
case ACPI_CPU_FLAGS_OFFSET_RW: /* set is_* fields */
cdev = &cpu_st->devs[cpu_st->selector];
if (data & 2) { /* clear insert event */
cdev->is_inserting = false;
trace_cpuhp_acpi_clear_inserting_evt(cpu_st->selector);
} else if (data & 4) { /* clear remove event */
cdev->is_removing = false;
trace_cpuhp_acpi_clear_remove_evt(cpu_st->selector);
} else if (data & 8) {
DeviceState *dev = NULL;
HotplugHandler *hotplug_ctrl = NULL;
if (!cdev->cpu) {
trace_cpuhp_acpi_ejecting_invalid_cpu(cpu_st->selector);
break;
}
trace_cpuhp_acpi_ejecting_cpu(cpu_st->selector);
dev = DEVICE(cdev->cpu);
hotplug_ctrl = qdev_get_hotplug_handler(dev);
hotplug_handler_unplug(hotplug_ctrl, dev, NULL);
}
break;
case ACPI_CPU_CMD_OFFSET_WR:
trace_cpuhp_acpi_write_cmd(cpu_st->selector, data);
if (data < CPHP_CMD_MAX) {
cpu_st->command = data;
if (cpu_st->command == CPHP_GET_NEXT_CPU_WITH_EVENT_CMD) {
uint32_t iter = cpu_st->selector;
do {
cdev = &cpu_st->devs[iter];
if (cdev->is_inserting || cdev->is_removing) {
cpu_st->selector = iter;
trace_cpuhp_acpi_cpu_has_events(cpu_st->selector,
cdev->is_inserting, cdev->is_removing);
break;
}
iter = iter + 1 < cpu_st->dev_count ? iter + 1 : 0;
} while (iter != cpu_st->selector);
}
}
break;
case ACPI_CPU_CMD_DATA_OFFSET_RW:
switch (cpu_st->command) {
case CPHP_OST_EVENT_CMD: {
cdev = &cpu_st->devs[cpu_st->selector];
cdev->ost_event = data;
trace_cpuhp_acpi_write_ost_ev(cpu_st->selector, cdev->ost_event);
break;
}
case CPHP_OST_STATUS_CMD: {
cdev = &cpu_st->devs[cpu_st->selector];
cdev->ost_status = data;
info = acpi_cpu_device_status(cpu_st->selector, cdev);
qapi_event_send_acpi_device_ost(info, &error_abort);
qapi_free_ACPIOSTInfo(info);
trace_cpuhp_acpi_write_ost_status(cpu_st->selector,
cdev->ost_status);
break;
}
default:
break;
}
break;
default:
break;
}
}
static const MemoryRegionOps cpu_hotplug_ops = {
.read = cpu_hotplug_rd,
.write = cpu_hotplug_wr,
.endianness = DEVICE_LITTLE_ENDIAN,
.valid = {
.min_access_size = 1,
.max_access_size = 4,
},
};
void cpu_hotplug_hw_init(MemoryRegion *as, Object *owner,
CPUHotplugState *state, hwaddr base_addr)
{
MachineState *machine = MACHINE(qdev_get_machine());
MachineClass *mc = MACHINE_GET_CLASS(machine);
CPUArchIdList *id_list;
int i;
assert(mc->possible_cpu_arch_ids);
id_list = mc->possible_cpu_arch_ids(machine);
state->dev_count = id_list->len;
state->devs = g_new0(typeof(*state->devs), state->dev_count);
for (i = 0; i < id_list->len; i++) {
state->devs[i].cpu = id_list->cpus[i].cpu;
state->devs[i].arch_id = id_list->cpus[i].arch_id;
}
g_free(id_list);
memory_region_init_io(&state->ctrl_reg, owner, &cpu_hotplug_ops, state,
"acpi-mem-hotplug", ACPI_CPU_HOTPLUG_REG_LEN);
memory_region_add_subregion(as, base_addr, &state->ctrl_reg);
}
static AcpiCpuStatus *get_cpu_status(CPUHotplugState *cpu_st, DeviceState *dev)
{
CPUClass *k = CPU_GET_CLASS(dev);
uint64_t cpu_arch_id = k->get_arch_id(CPU(dev));
int i;
for (i = 0; i < cpu_st->dev_count; i++) {
if (cpu_arch_id == cpu_st->devs[i].arch_id) {
return &cpu_st->devs[i];
}
}
return NULL;
}
void acpi_cpu_plug_cb(HotplugHandler *hotplug_dev,
CPUHotplugState *cpu_st, DeviceState *dev, Error **errp)
{
AcpiCpuStatus *cdev;
cdev = get_cpu_status(cpu_st, dev);
if (!cdev) {
return;
}
cdev->cpu = CPU(dev);
if (dev->hotplugged) {
cdev->is_inserting = true;
acpi_send_event(DEVICE(hotplug_dev), ACPI_CPU_HOTPLUG_STATUS);
}
}
void acpi_cpu_unplug_request_cb(HotplugHandler *hotplug_dev,
CPUHotplugState *cpu_st,
DeviceState *dev, Error **errp)
{
AcpiCpuStatus *cdev;
cdev = get_cpu_status(cpu_st, dev);
if (!cdev) {
return;
}
cdev->is_removing = true;
acpi_send_event(DEVICE(hotplug_dev), ACPI_CPU_HOTPLUG_STATUS);
}
void acpi_cpu_unplug_cb(CPUHotplugState *cpu_st,
DeviceState *dev, Error **errp)
{
AcpiCpuStatus *cdev;
cdev = get_cpu_status(cpu_st, dev);
if (!cdev) {
return;
}
cdev->cpu = NULL;
}
static const VMStateDescription vmstate_cpuhp_sts = {
.name = "CPU hotplug device state",
.version_id = 1,
.minimum_version_id = 1,
.minimum_version_id_old = 1,
.fields = (VMStateField[]) {
VMSTATE_BOOL(is_inserting, AcpiCpuStatus),
VMSTATE_BOOL(is_removing, AcpiCpuStatus),
VMSTATE_UINT32(ost_event, AcpiCpuStatus),
VMSTATE_UINT32(ost_status, AcpiCpuStatus),
VMSTATE_END_OF_LIST()
}
};
const VMStateDescription vmstate_cpu_hotplug = {
.name = "CPU hotplug state",
.version_id = 1,
.minimum_version_id = 1,
.minimum_version_id_old = 1,
.fields = (VMStateField[]) {
VMSTATE_UINT32(selector, CPUHotplugState),
VMSTATE_UINT8(command, CPUHotplugState),
VMSTATE_STRUCT_VARRAY_POINTER_UINT32(devs, CPUHotplugState, dev_count,
vmstate_cpuhp_sts, AcpiCpuStatus),
VMSTATE_END_OF_LIST()
}
};
#define CPU_NAME_FMT "C%.03X"
#define CPUHP_RES_DEVICE "PRES"
#define CPU_LOCK "CPLK"
#define CPU_STS_METHOD "CSTA"
#define CPU_SCAN_METHOD "CSCN"
#define CPU_NOTIFY_METHOD "CTFY"
#define CPU_EJECT_METHOD "CEJ0"
#define CPU_OST_METHOD "COST"
#define CPU_ENABLED "CPEN"
#define CPU_SELECTOR "CSEL"
#define CPU_COMMAND "CCMD"
#define CPU_DATA "CDAT"
#define CPU_INSERT_EVENT "CINS"
#define CPU_REMOVE_EVENT "CRMV"
#define CPU_EJECT_EVENT "CEJ0"
void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts,
hwaddr io_base,
const char *res_root,
const char *event_handler_method)
{
Aml *ifctx;
Aml *field;
Aml *method;
Aml *cpu_ctrl_dev;
Aml *cpus_dev;
Aml *zero = aml_int(0);
Aml *one = aml_int(1);
Aml *sb_scope = aml_scope("_SB");
MachineClass *mc = MACHINE_GET_CLASS(machine);
CPUArchIdList *arch_ids = mc->possible_cpu_arch_ids(machine);
char *cphp_res_path = g_strdup_printf("%s." CPUHP_RES_DEVICE, res_root);
Object *obj = object_resolve_path_type("", TYPE_ACPI_DEVICE_IF, NULL);
AcpiDeviceIfClass *adevc = ACPI_DEVICE_IF_GET_CLASS(obj);
AcpiDeviceIf *adev = ACPI_DEVICE_IF(obj);
cpu_ctrl_dev = aml_device("%s", cphp_res_path);
{
Aml *crs;
aml_append(cpu_ctrl_dev,
aml_name_decl("_HID", aml_eisaid("PNP0A06")));
aml_append(cpu_ctrl_dev,
aml_name_decl("_UID", aml_string("CPU Hotplug resources")));
aml_append(cpu_ctrl_dev, aml_mutex(CPU_LOCK, 0));
crs = aml_resource_template();
aml_append(crs, aml_io(AML_DECODE16, io_base, io_base, 1,
ACPI_CPU_HOTPLUG_REG_LEN));
aml_append(cpu_ctrl_dev, aml_name_decl("_CRS", crs));
/* declare CPU hotplug MMIO region with related access fields */
aml_append(cpu_ctrl_dev,
aml_operation_region("PRST", AML_SYSTEM_IO, aml_int(io_base),
ACPI_CPU_HOTPLUG_REG_LEN));
field = aml_field("PRST", AML_BYTE_ACC, AML_NOLOCK,
AML_WRITE_AS_ZEROS);
aml_append(field, aml_reserved_field(ACPI_CPU_FLAGS_OFFSET_RW * 8));
/* 1 if enabled, read only */
aml_append(field, aml_named_field(CPU_ENABLED, 1));
/* (read) 1 if has a insert event. (write) 1 to clear event */
aml_append(field, aml_named_field(CPU_INSERT_EVENT, 1));
/* (read) 1 if has a remove event. (write) 1 to clear event */
aml_append(field, aml_named_field(CPU_REMOVE_EVENT, 1));
/* initiates device eject, write only */
aml_append(field, aml_named_field(CPU_EJECT_EVENT, 1));
aml_append(field, aml_reserved_field(4));
aml_append(field, aml_named_field(CPU_COMMAND, 8));
aml_append(cpu_ctrl_dev, field);
field = aml_field("PRST", AML_DWORD_ACC, AML_NOLOCK, AML_PRESERVE);
/* CPU selector, write only */
aml_append(field, aml_named_field(CPU_SELECTOR, 32));
/* flags + cmd + 2byte align */
aml_append(field, aml_reserved_field(4 * 8));
aml_append(field, aml_named_field(CPU_DATA, 32));
aml_append(cpu_ctrl_dev, field);
if (opts.has_legacy_cphp) {
method = aml_method("_INI", 0, AML_SERIALIZED);
/* switch off legacy CPU hotplug HW and use new one,
* on reboot system is in new mode and writing 0
* in CPU_SELECTOR selects BSP, which is NOP at
* the time _INI is called */
aml_append(method, aml_store(zero, aml_name(CPU_SELECTOR)));
aml_append(cpu_ctrl_dev, method);
}
}
aml_append(sb_scope, cpu_ctrl_dev);
cpus_dev = aml_device("\\_SB.CPUS");
{
int i;
Aml *ctrl_lock = aml_name("%s.%s", cphp_res_path, CPU_LOCK);
Aml *cpu_selector = aml_name("%s.%s", cphp_res_path, CPU_SELECTOR);
Aml *is_enabled = aml_name("%s.%s", cphp_res_path, CPU_ENABLED);
Aml *cpu_cmd = aml_name("%s.%s", cphp_res_path, CPU_COMMAND);
Aml *cpu_data = aml_name("%s.%s", cphp_res_path, CPU_DATA);
Aml *ins_evt = aml_name("%s.%s", cphp_res_path, CPU_INSERT_EVENT);
Aml *rm_evt = aml_name("%s.%s", cphp_res_path, CPU_REMOVE_EVENT);
Aml *ej_evt = aml_name("%s.%s", cphp_res_path, CPU_EJECT_EVENT);
aml_append(cpus_dev, aml_name_decl("_HID", aml_string("ACPI0010")));
aml_append(cpus_dev, aml_name_decl("_CID", aml_eisaid("PNP0A05")));
method = aml_method(CPU_NOTIFY_METHOD, 2, AML_NOTSERIALIZED);
for (i = 0; i < arch_ids->len; i++) {
Aml *cpu = aml_name(CPU_NAME_FMT, i);
Aml *uid = aml_arg(0);
Aml *event = aml_arg(1);
ifctx = aml_if(aml_equal(uid, aml_int(i)));
{
aml_append(ifctx, aml_notify(cpu, event));
}
aml_append(method, ifctx);
}
aml_append(cpus_dev, method);
method = aml_method(CPU_STS_METHOD, 1, AML_SERIALIZED);
{
Aml *idx = aml_arg(0);
Aml *sta = aml_local(0);
aml_append(method, aml_acquire(ctrl_lock, 0xFFFF));
aml_append(method, aml_store(idx, cpu_selector));
aml_append(method, aml_store(zero, sta));
ifctx = aml_if(aml_equal(is_enabled, one));
{
aml_append(ifctx, aml_store(aml_int(0xF), sta));
}
aml_append(method, ifctx);
aml_append(method, aml_release(ctrl_lock));
aml_append(method, aml_return(sta));
}
aml_append(cpus_dev, method);
method = aml_method(CPU_EJECT_METHOD, 1, AML_SERIALIZED);
{
Aml *idx = aml_arg(0);
aml_append(method, aml_acquire(ctrl_lock, 0xFFFF));
aml_append(method, aml_store(idx, cpu_selector));
aml_append(method, aml_store(one, ej_evt));
aml_append(method, aml_release(ctrl_lock));
}
aml_append(cpus_dev, method);
method = aml_method(CPU_SCAN_METHOD, 0, AML_SERIALIZED);
{
Aml *else_ctx;
Aml *while_ctx;
Aml *has_event = aml_local(0);
Aml *dev_chk = aml_int(1);
Aml *eject_req = aml_int(3);
Aml *next_cpu_cmd = aml_int(CPHP_GET_NEXT_CPU_WITH_EVENT_CMD);
aml_append(method, aml_acquire(ctrl_lock, 0xFFFF));
aml_append(method, aml_store(one, has_event));
while_ctx = aml_while(aml_equal(has_event, one));
{
/* clear loop exit condition, ins_evt/rm_evt checks
* will set it to 1 while next_cpu_cmd returns a CPU
* with events */
aml_append(while_ctx, aml_store(zero, has_event));
aml_append(while_ctx, aml_store(next_cpu_cmd, cpu_cmd));
ifctx = aml_if(aml_equal(ins_evt, one));
{
aml_append(ifctx,
aml_call2(CPU_NOTIFY_METHOD, cpu_data, dev_chk));
aml_append(ifctx, aml_store(one, ins_evt));
aml_append(ifctx, aml_store(one, has_event));
}
aml_append(while_ctx, ifctx);
else_ctx = aml_else();
ifctx = aml_if(aml_equal(rm_evt, one));
{
aml_append(ifctx,
aml_call2(CPU_NOTIFY_METHOD, cpu_data, eject_req));
aml_append(ifctx, aml_store(one, rm_evt));
aml_append(ifctx, aml_store(one, has_event));
}
aml_append(else_ctx, ifctx);
aml_append(while_ctx, else_ctx);
}
aml_append(method, while_ctx);
aml_append(method, aml_release(ctrl_lock));
}
aml_append(cpus_dev, method);
method = aml_method(CPU_OST_METHOD, 4, AML_SERIALIZED);
{
Aml *uid = aml_arg(0);
Aml *ev_cmd = aml_int(CPHP_OST_EVENT_CMD);
Aml *st_cmd = aml_int(CPHP_OST_STATUS_CMD);
aml_append(method, aml_acquire(ctrl_lock, 0xFFFF));
aml_append(method, aml_store(uid, cpu_selector));
aml_append(method, aml_store(ev_cmd, cpu_cmd));
aml_append(method, aml_store(aml_arg(1), cpu_data));
aml_append(method, aml_store(st_cmd, cpu_cmd));
aml_append(method, aml_store(aml_arg(2), cpu_data));
aml_append(method, aml_release(ctrl_lock));
}
aml_append(cpus_dev, method);
/* build Processor object for each processor */
for (i = 0; i < arch_ids->len; i++) {
Aml *dev;
Aml *uid = aml_int(i);
GArray *madt_buf = g_array_new(0, 1, 1);
int arch_id = arch_ids->cpus[i].arch_id;
if (opts.apci_1_compatible && arch_id < 255) {
dev = aml_processor(i, 0, 0, CPU_NAME_FMT, i);
} else {
dev = aml_device(CPU_NAME_FMT, i);
aml_append(dev, aml_name_decl("_HID", aml_string("ACPI0007")));
aml_append(dev, aml_name_decl("_UID", uid));
}
method = aml_method("_STA", 0, AML_SERIALIZED);
aml_append(method, aml_return(aml_call1(CPU_STS_METHOD, uid)));
aml_append(dev, method);
/* build _MAT object */
assert(adevc && adevc->madt_cpu);
adevc->madt_cpu(adev, i, arch_ids, madt_buf);
switch (madt_buf->data[0]) {
case ACPI_APIC_PROCESSOR: {
AcpiMadtProcessorApic *apic = (void *)madt_buf->data;
apic->flags = cpu_to_le32(1);
break;
}
default:
assert(0);
}
aml_append(dev, aml_name_decl("_MAT",
aml_buffer(madt_buf->len, (uint8_t *)madt_buf->data)));
g_array_free(madt_buf, true);
method = aml_method("_EJ0", 1, AML_NOTSERIALIZED);
aml_append(method, aml_call1(CPU_EJECT_METHOD, uid));
aml_append(dev, method);
method = aml_method("_OST", 3, AML_SERIALIZED);
aml_append(method,
aml_call4(CPU_OST_METHOD, uid, aml_arg(0),
aml_arg(1), aml_arg(2))
);
aml_append(dev, method);
aml_append(cpus_dev, dev);
}
}
aml_append(sb_scope, cpus_dev);
aml_append(table, sb_scope);
method = aml_method(event_handler_method, 0, AML_NOTSERIALIZED);
aml_append(method, aml_call0("\\_SB.CPUS." CPU_SCAN_METHOD));
aml_append(table, method);
g_free(cphp_res_path);
g_free(arch_ids);
}

21
hw/acpi/cpu_hotplug.c
View File

@ -34,7 +34,15 @@ static uint64_t cpu_status_read(void *opaque, hwaddr addr, unsigned int size)
static void cpu_status_write(void *opaque, hwaddr addr, uint64_t data,
unsigned int size)
{
/* TODO: implement VCPU removal on guest signal that CPU can be removed */
/* firmware never used to write in CPU present bitmap so use
this fact as means to switch QEMU into modern CPU hotplug
mode by writing 0 at the beginning of legacy CPU bitmap
*/
if (addr == 0 && data == 0) {
AcpiCpuHotplug *cpus = opaque;
object_property_set_bool(cpus->device, false, "cpu-hotplug-legacy",
&error_abort);
}
}
static const MemoryRegionOps AcpiCpuHotplug_ops = {
@ -83,6 +91,17 @@ void legacy_acpi_cpu_hotplug_init(MemoryRegion *parent, Object *owner,
memory_region_init_io(&gpe_cpu->io, owner, &AcpiCpuHotplug_ops,
gpe_cpu, "acpi-cpu-hotplug", ACPI_GPE_PROC_LEN);
memory_region_add_subregion(parent, base, &gpe_cpu->io);
gpe_cpu->device = owner;
}
void acpi_switch_to_modern_cphp(AcpiCpuHotplug *gpe_cpu,
CPUHotplugState *cpuhp_state,
uint16_t io_port)
{
MemoryRegion *parent = pci_address_space_io(PCI_DEVICE(gpe_cpu->device));
memory_region_del_subregion(parent, &gpe_cpu->io);
cpu_hotplug_hw_init(parent, gpe_cpu->device, cpuhp_state, io_port);
}
void build_legacy_cpu_hotplug_aml(Aml *ctx, MachineState *machine,

69
hw/acpi/ich9.c
View File

@ -189,6 +189,33 @@ static const VMStateDescription vmstate_tco_io_state = {
}
};
static bool vmstate_test_use_cpuhp(void *opaque)
{
ICH9LPCPMRegs *s = opaque;
return !s->cpu_hotplug_legacy;
}
static int vmstate_cpuhp_pre_load(void *opaque)
{
ICH9LPCPMRegs *s = opaque;
Object *obj = OBJECT(s->gpe_cpu.device);
object_property_set_bool(obj, false, "cpu-hotplug-legacy", &error_abort);
return 0;
}
static const VMStateDescription vmstate_cpuhp_state = {
.name = "ich9_pm/cpuhp",
.version_id = 1,
.minimum_version_id = 1,
.minimum_version_id_old = 1,
.needed = vmstate_test_use_cpuhp,
.pre_load = vmstate_cpuhp_pre_load,
.fields = (VMStateField[]) {
VMSTATE_CPU_HOTPLUG(cpuhp_state, ICH9LPCPMRegs),
VMSTATE_END_OF_LIST()
}
};
const VMStateDescription vmstate_ich9_pm = {
.name = "ich9_pm",
.version_id = 1,
@ -209,6 +236,7 @@ const VMStateDescription vmstate_ich9_pm = {
.subsections = (const VMStateDescription*[]) {
&vmstate_memhp_state,
&vmstate_tco_io_state,
&vmstate_cpuhp_state,
NULL
}
};
@ -306,6 +334,26 @@ static void ich9_pm_set_memory_hotplug_support(Object *obj, bool value,
s->pm.acpi_memory_hotplug.is_enabled = value;
}
static bool ich9_pm_get_cpu_hotplug_legacy(Object *obj, Error **errp)
{
ICH9LPCState *s = ICH9_LPC_DEVICE(obj);
return s->pm.cpu_hotplug_legacy;
}
static void ich9_pm_set_cpu_hotplug_legacy(Object *obj, bool value,
Error **errp)
{
ICH9LPCState *s = ICH9_LPC_DEVICE(obj);
assert(!value);
if (s->pm.cpu_hotplug_legacy && value == false) {
acpi_switch_to_modern_cphp(&s->pm.gpe_cpu, &s->pm.cpuhp_state,
ICH9_CPU_HOTPLUG_IO_BASE);
}
s->pm.cpu_hotplug_legacy = value;
}
static void ich9_pm_get_disable_s3(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
@ -397,6 +445,7 @@ void ich9_pm_add_properties(Object *obj, ICH9LPCPMRegs *pm, Error **errp)
{
static const uint32_t gpe0_len = ICH9_PMIO_GPE0_LEN;
pm->acpi_memory_hotplug.is_enabled = true;
pm->cpu_hotplug_legacy = true;
pm->disable_s3 = 0;
pm->disable_s4 = 0;
pm->s4_val = 2;
@ -412,6 +461,10 @@ void ich9_pm_add_properties(Object *obj, ICH9LPCPMRegs *pm, Error **errp)
ich9_pm_get_memory_hotplug_support,
ich9_pm_set_memory_hotplug_support,
NULL);
object_property_add_bool(obj, "cpu-hotplug-legacy",
ich9_pm_get_cpu_hotplug_legacy,
ich9_pm_set_cpu_hotplug_legacy,
NULL);
object_property_add(obj, ACPI_PM_PROP_S3_DISABLED, "uint8",
ich9_pm_get_disable_s3,
ich9_pm_set_disable_s3,
@ -440,7 +493,11 @@ void ich9_pm_device_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
acpi_memory_plug_cb(hotplug_dev, &lpc->pm.acpi_memory_hotplug,
dev, errp);
} else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) {
legacy_acpi_cpu_plug_cb(hotplug_dev, &lpc->pm.gpe_cpu, dev, errp);
if (lpc->pm.cpu_hotplug_legacy) {
legacy_acpi_cpu_plug_cb(hotplug_dev, &lpc->pm.gpe_cpu, dev, errp);
} else {
acpi_cpu_plug_cb(hotplug_dev, &lpc->pm.cpuhp_state, dev, errp);
}
} else {
error_setg(errp, "acpi: device plug request for not supported device"
" type: %s", object_get_typename(OBJECT(dev)));
@ -457,6 +514,10 @@ void ich9_pm_device_unplug_request_cb(HotplugHandler *hotplug_dev,
acpi_memory_unplug_request_cb(hotplug_dev,
&lpc->pm.acpi_memory_hotplug, dev,
errp);
} else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU) &&
!lpc->pm.cpu_hotplug_legacy) {
acpi_cpu_unplug_request_cb(hotplug_dev, &lpc->pm.cpuhp_state,
dev, errp);
} else {
error_setg(errp, "acpi: device unplug request for not supported device"
" type: %s", object_get_typename(OBJECT(dev)));
@ -471,6 +532,9 @@ void ich9_pm_device_unplug_cb(HotplugHandler *hotplug_dev, DeviceState *dev,
if (lpc->pm.acpi_memory_hotplug.is_enabled &&
object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
acpi_memory_unplug_cb(&lpc->pm.acpi_memory_hotplug, dev, errp);
} else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU) &&
!lpc->pm.cpu_hotplug_legacy) {
acpi_cpu_unplug_cb(&lpc->pm.cpuhp_state, dev, errp);
} else {
error_setg(errp, "acpi: device unplug for not supported device"
" type: %s", object_get_typename(OBJECT(dev)));
@ -482,4 +546,7 @@ void ich9_pm_ospm_status(AcpiDeviceIf *adev, ACPIOSTInfoList ***list)
ICH9LPCState *s = ICH9_LPC_DEVICE(adev);
acpi_memory_ospm_status(&s->pm.acpi_memory_hotplug, list);
if (!s->pm.cpu_hotplug_legacy) {
acpi_cpu_ospm_status(&s->pm.cpuhp_state, list);
}
}

105
hw/acpi/ipmi.c Normal file
View File

@ -0,0 +1,105 @@
/*
* IPMI ACPI 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.
*/
#include "qemu/osdep.h"
#include "hw/ipmi/ipmi.h"
#include "hw/acpi/aml-build.h"
#include "hw/acpi/acpi.h"
#include "hw/acpi/ipmi.h"
static Aml *aml_ipmi_crs(IPMIFwInfo *info)
{
Aml *crs = aml_resource_template();
/*
* The base address is fixed and cannot change. That may be different
* if someone does PCI, but we aren't there yet.
*/
switch (info->memspace) {
case IPMI_MEMSPACE_IO:
aml_append(crs, aml_io(AML_DECODE16, info->base_address,
info->base_address + info->register_length - 1,
info->register_spacing, info->register_length));
break;
case IPMI_MEMSPACE_MEM32:
aml_append(crs,
aml_dword_memory(AML_POS_DECODE,
AML_MIN_FIXED, AML_MAX_FIXED,
AML_NON_CACHEABLE, AML_READ_WRITE,
0xffffffff,
info->base_address,
info->base_address + info->register_length - 1,
info->register_spacing, info->register_length));
break;
case IPMI_MEMSPACE_MEM64:
aml_append(crs,
aml_qword_memory(AML_POS_DECODE,
AML_MIN_FIXED, AML_MAX_FIXED,
AML_NON_CACHEABLE, AML_READ_WRITE,
0xffffffffffffffffULL,
info->base_address,
info->base_address + info->register_length - 1,
info->register_spacing, info->register_length));
break;
case IPMI_MEMSPACE_SMBUS:
aml_append(crs, aml_return(aml_int(info->base_address)));
break;
default:
abort();
}
if (info->interrupt_number) {
aml_append(crs, aml_irq_no_flags(info->interrupt_number));
}
return crs;
}
static Aml *aml_ipmi_device(IPMIFwInfo *info)
{
Aml *dev;
uint16_t version = ((info->ipmi_spec_major_revision << 8)
| (info->ipmi_spec_minor_revision << 4));
assert(info->ipmi_spec_minor_revision <= 15);
dev = aml_device("MI%d", info->uuid);
aml_append(dev, aml_name_decl("_HID", aml_eisaid("IPI0001")));
aml_append(dev, aml_name_decl("_STR", aml_string("ipmi_%s",
info->interface_name)));
aml_append(dev, aml_name_decl("_UID", aml_int(info->uuid)));
aml_append(dev, aml_name_decl("_CRS", aml_ipmi_crs(info)));
aml_append(dev, aml_name_decl("_IFT", aml_int(info->interface_type)));
aml_append(dev, aml_name_decl("_SRV", aml_int(version)));
return dev;
}
void build_acpi_ipmi_devices(Aml *scope, BusState *bus)
{
BusChild *kid;
QTAILQ_FOREACH(kid, &bus->children, sibling) {
IPMIInterface *ii;
IPMIInterfaceClass *iic;
IPMIFwInfo info;
Object *obj = object_dynamic_cast(OBJECT(kid->child),
TYPE_IPMI_INTERFACE);
if (!obj) {
continue;
}
ii = IPMI_INTERFACE(obj);
iic = IPMI_INTERFACE_GET_CLASS(obj);
iic->get_fwinfo(ii, &info);
aml_append(scope, aml_ipmi_device(&info));
}
}

400
hw/acpi/nvdimm.c
View File

@ -216,6 +216,26 @@ static uint32_t nvdimm_slot_to_dcr_index(int slot)
return nvdimm_slot_to_spa_index(slot) + 1;
}
static NVDIMMDevice *nvdimm_get_device_by_handle(uint32_t handle)
{
NVDIMMDevice *nvdimm = NULL;
GSList *list, *device_list = nvdimm_get_plugged_device_list();
for (list = device_list; list; list = list->next) {
NVDIMMDevice *nvd = list->data;
int slot = object_property_get_int(OBJECT(nvd), PC_DIMM_SLOT_PROP,
NULL);
if (nvdimm_slot_to_handle(slot) == handle) {
nvdimm = nvd;
break;
}
}
g_slist_free(device_list);
return nvdimm;
}
/* ACPI 6.0: 5.2.25.1 System Physical Address Range Structure */
static void
nvdimm_build_structure_spa(GArray *structures, DeviceState *dev)
@ -406,6 +426,282 @@ struct NvdimmDsmFuncNoPayloadOut {
} QEMU_PACKED;
typedef struct NvdimmDsmFuncNoPayloadOut NvdimmDsmFuncNoPayloadOut;
struct NvdimmFuncGetLabelSizeOut {
/* the size of buffer filled by QEMU. */
uint32_t len;
uint32_t func_ret_status; /* return status code. */
uint32_t label_size; /* the size of label data area. */
/*
* Maximum size of the namespace label data length supported by
* the platform in Get/Set Namespace Label Data functions.
*/
uint32_t max_xfer;
} QEMU_PACKED;
typedef struct NvdimmFuncGetLabelSizeOut NvdimmFuncGetLabelSizeOut;
QEMU_BUILD_BUG_ON(sizeof(NvdimmFuncGetLabelSizeOut) > 4096);
struct NvdimmFuncGetLabelDataIn {
uint32_t offset; /* the offset in the namespace label data area. */
uint32_t length; /* the size of data is to be read via the function. */
} QEMU_PACKED;
typedef struct NvdimmFuncGetLabelDataIn NvdimmFuncGetLabelDataIn;
QEMU_BUILD_BUG_ON(sizeof(NvdimmFuncGetLabelDataIn) +
offsetof(NvdimmDsmIn, arg3) > 4096);
struct NvdimmFuncGetLabelDataOut {
/* the size of buffer filled by QEMU. */
uint32_t len;
uint32_t func_ret_status; /* return status code. */
uint8_t out_buf[0]; /* the data got via Get Namesapce Label function. */
} QEMU_PACKED;
typedef struct NvdimmFuncGetLabelDataOut NvdimmFuncGetLabelDataOut;
QEMU_BUILD_BUG_ON(sizeof(NvdimmFuncGetLabelDataOut) > 4096);
struct NvdimmFuncSetLabelDataIn {
uint32_t offset; /* the offset in the namespace label data area. */
uint32_t length; /* the size of data is to be written via the function. */
uint8_t in_buf[0]; /* the data written to label data area. */
} QEMU_PACKED;
typedef struct NvdimmFuncSetLabelDataIn NvdimmFuncSetLabelDataIn;
QEMU_BUILD_BUG_ON(sizeof(NvdimmFuncSetLabelDataIn) +
offsetof(NvdimmDsmIn, arg3) > 4096);
static void
nvdimm_dsm_function0(uint32_t supported_func, hwaddr dsm_mem_addr)
{
NvdimmDsmFunc0Out func0 = {
.len = cpu_to_le32(sizeof(func0)),
.supported_func = cpu_to_le32(supported_func),
};
cpu_physical_memory_write(dsm_mem_addr, &func0, sizeof(func0));
}
static void
nvdimm_dsm_no_payload(uint32_t func_ret_status, hwaddr dsm_mem_addr)
{
NvdimmDsmFuncNoPayloadOut out = {
.len = cpu_to_le32(sizeof(out)),
.func_ret_status = cpu_to_le32(func_ret_status),
};
cpu_physical_memory_write(dsm_mem_addr, &out, sizeof(out));
}
static void nvdimm_dsm_root(NvdimmDsmIn *in, hwaddr dsm_mem_addr)
{
/*
* function 0 is called to inquire which functions are supported by
* OSPM
*/
if (!in->function) {
nvdimm_dsm_function0(0 /* No function supported other than
function 0 */, dsm_mem_addr);
return;
}
/* No function except function 0 is supported yet. */
nvdimm_dsm_no_payload(1 /* Not Supported */, dsm_mem_addr);
}
/*
* the max transfer size is the max size transferred by both a
* 'Get Namespace Label Data' function and a 'Set Namespace Label Data'
* function.
*/
static uint32_t nvdimm_get_max_xfer_label_size(void)
{
uint32_t max_get_size, max_set_size, dsm_memory_size = 4096;
/*
* the max data ACPI can read one time which is transferred by
* the response of 'Get Namespace Label Data' function.
*/
max_get_size = dsm_memory_size - sizeof(NvdimmFuncGetLabelDataOut);
/*
* the max data ACPI can write one time which is transferred by
* 'Set Namespace Label Data' function.
*/
max_set_size = dsm_memory_size - offsetof(NvdimmDsmIn, arg3) -
sizeof(NvdimmFuncSetLabelDataIn);
return MIN(max_get_size, max_set_size);
}
/*
* DSM Spec Rev1 4.4 Get Namespace Label Size (Function Index 4).
*
* It gets the size of Namespace Label data area and the max data size
* that Get/Set Namespace Label Data functions can transfer.
*/
static void nvdimm_dsm_label_size(NVDIMMDevice *nvdimm, hwaddr dsm_mem_addr)
{
NvdimmFuncGetLabelSizeOut label_size_out = {
.len = cpu_to_le32(sizeof(label_size_out)),
};
uint32_t label_size, mxfer;
label_size = nvdimm->label_size;
mxfer = nvdimm_get_max_xfer_label_size();
nvdimm_debug("label_size %#x, max_xfer %#x.\n", label_size, mxfer);
label_size_out.func_ret_status = cpu_to_le32(0 /* Success */);
label_size_out.label_size = cpu_to_le32(label_size);
label_size_out.max_xfer = cpu_to_le32(mxfer);
cpu_physical_memory_write(dsm_mem_addr, &label_size_out,
sizeof(label_size_out));
}
static uint32_t nvdimm_rw_label_data_check(NVDIMMDevice *nvdimm,
uint32_t offset, uint32_t length)
{
uint32_t ret = 3 /* Invalid Input Parameters */;
if (offset + length < offset) {
nvdimm_debug("offset %#x + length %#x is overflow.\n", offset,
length);
return ret;
}
if (nvdimm->label_size < offset + length) {
nvdimm_debug("position %#x is beyond label data (len = %" PRIx64 ").\n",
offset + length, nvdimm->label_size);
return ret;
}
if (length > nvdimm_get_max_xfer_label_size()) {
nvdimm_debug("length (%#x) is larger than max_xfer (%#x).\n",
length, nvdimm_get_max_xfer_label_size());
return ret;
}
return 0 /* Success */;
}
/*
* DSM Spec Rev1 4.5 Get Namespace Label Data (Function Index 5).
*/
static void nvdimm_dsm_get_label_data(NVDIMMDevice *nvdimm, NvdimmDsmIn *in,
hwaddr dsm_mem_addr)
{
NVDIMMClass *nvc = NVDIMM_GET_CLASS(nvdimm);
NvdimmFuncGetLabelDataIn *get_label_data;
NvdimmFuncGetLabelDataOut *get_label_data_out;
uint32_t status;
int size;
get_label_data = (NvdimmFuncGetLabelDataIn *)in->arg3;
le32_to_cpus(&get_label_data->offset);
le32_to_cpus(&get_label_data->length);
nvdimm_debug("Read Label Data: offset %#x length %#x.\n",
get_label_data->offset, get_label_data->length);
status = nvdimm_rw_label_data_check(nvdimm, get_label_data->offset,
get_label_data->length);
if (status != 0 /* Success */) {
nvdimm_dsm_no_payload(status, dsm_mem_addr);
return;
}
size = sizeof(*get_label_data_out) + get_label_data->length;
assert(size <= 4096);
get_label_data_out = g_malloc(size);
get_label_data_out->len = cpu_to_le32(size);
get_label_data_out->func_ret_status = cpu_to_le32(0 /* Success */);
nvc->read_label_data(nvdimm, get_label_data_out->out_buf,
get_label_data->length, get_label_data->offset);
cpu_physical_memory_write(dsm_mem_addr, get_label_data_out, size);
g_free(get_label_data_out);
}
/*
* DSM Spec Rev1 4.6 Set Namespace Label Data (Function Index 6).
*/
static void nvdimm_dsm_set_label_data(NVDIMMDevice *nvdimm, NvdimmDsmIn *in,
hwaddr dsm_mem_addr)
{
NVDIMMClass *nvc = NVDIMM_GET_CLASS(nvdimm);
NvdimmFuncSetLabelDataIn *set_label_data;
uint32_t status;
set_label_data = (NvdimmFuncSetLabelDataIn *)in->arg3;
le32_to_cpus(&set_label_data->offset);
le32_to_cpus(&set_label_data->length);
nvdimm_debug("Write Label Data: offset %#x length %#x.\n",
set_label_data->offset, set_label_data->length);
status = nvdimm_rw_label_data_check(nvdimm, set_label_data->offset,
set_label_data->length);
if (status != 0 /* Success */) {
nvdimm_dsm_no_payload(status, dsm_mem_addr);
return;
}
assert(sizeof(*in) + sizeof(*set_label_data) + set_label_data->length <=
4096);
nvc->write_label_data(nvdimm, set_label_data->in_buf,
set_label_data->length, set_label_data->offset);
nvdimm_dsm_no_payload(0 /* Success */, dsm_mem_addr);
}
static void nvdimm_dsm_device(NvdimmDsmIn *in, hwaddr dsm_mem_addr)
{
NVDIMMDevice *nvdimm = nvdimm_get_device_by_handle(in->handle);
/* See the comments in nvdimm_dsm_root(). */
if (!in->function) {
uint32_t supported_func = 0;
if (nvdimm && nvdimm->label_size) {
supported_func |= 0x1 /* Bit 0 indicates whether there is
support for any functions other
than function 0. */ |
1 << 4 /* Get Namespace Label Size */ |
1 << 5 /* Get Namespace Label Data */ |
1 << 6 /* Set Namespace Label Data */;
}
nvdimm_dsm_function0(supported_func, dsm_mem_addr);
return;
}
if (!nvdimm) {
nvdimm_dsm_no_payload(2 /* Non-Existing Memory Device */,
dsm_mem_addr);
return;
}
/* Encode DSM function according to DSM Spec Rev1. */
switch (in->function) {
case 4 /* Get Namespace Label Size */:
if (nvdimm->label_size) {
nvdimm_dsm_label_size(nvdimm, dsm_mem_addr);
return;
}
break;
case 5 /* Get Namespace Label Data */:
if (nvdimm->label_size) {
nvdimm_dsm_get_label_data(nvdimm, in, dsm_mem_addr);
return;
}
break;
case 0x6 /* Set Namespace Label Data */:
if (nvdimm->label_size) {
nvdimm_dsm_set_label_data(nvdimm, in, dsm_mem_addr);
return;
}
break;
}
nvdimm_dsm_no_payload(1 /* Not Supported */, dsm_mem_addr);
}
static uint64_t
nvdimm_dsm_read(void *opaque, hwaddr addr, unsigned size)
{
@ -436,26 +732,22 @@ nvdimm_dsm_write(void *opaque, hwaddr addr, uint64_t val, unsigned size)
nvdimm_debug("Revision %#x Handler %#x Function %#x.\n", in->revision,
in->handle, in->function);
/*
* function 0 is called to inquire which functions are supported by
* OSPM
*/
if (in->function == 0) {
NvdimmDsmFunc0Out func0 = {
.len = cpu_to_le32(sizeof(func0)),
/* No function supported other than function 0 */
.supported_func = cpu_to_le32(0),
};
cpu_physical_memory_write(dsm_mem_addr, &func0, sizeof func0);
} else {
/* No function except function 0 is supported yet. */
NvdimmDsmFuncNoPayloadOut out = {
.len = cpu_to_le32(sizeof(out)),
.func_ret_status = cpu_to_le32(1) /* Not Supported */,
};
cpu_physical_memory_write(dsm_mem_addr, &out, sizeof(out));
if (in->revision != 0x1 /* Currently we only support DSM Spec Rev1. */) {
nvdimm_debug("Revision %#x is not supported, expect %#x.\n",
in->revision, 0x1);
nvdimm_dsm_no_payload(1 /* Not Supported */, dsm_mem_addr);
goto exit;
}
/* Handle 0 is reserved for NVDIMM Root Device. */
if (!in->handle) {
nvdimm_dsm_root(in, dsm_mem_addr);
goto exit;
}
nvdimm_dsm_device(in, dsm_mem_addr);
exit:
g_free(in);
}
@ -487,18 +779,39 @@ void nvdimm_init_acpi_state(AcpiNVDIMMState *state, MemoryRegion *io,
static void nvdimm_build_common_dsm(Aml *dev)
{
Aml *method, *ifctx, *function, *dsm_mem, *unpatched, *result_size;
Aml *method, *ifctx, *function, *handle, *uuid, *dsm_mem, *result_size;
Aml *elsectx, *unsupport, *unpatched, *expected_uuid, *uuid_invalid;
Aml *pckg, *pckg_index, *pckg_buf;
uint8_t byte_list[1];
method = aml_method(NVDIMM_COMMON_DSM, 4, AML_SERIALIZED);
method = aml_method(NVDIMM_COMMON_DSM, 5, AML_SERIALIZED);
uuid = aml_arg(0);
function = aml_arg(2);
handle = aml_arg(4);
dsm_mem = aml_name(NVDIMM_ACPI_MEM_ADDR);
/*
* do not support any method if DSM memory address has not been
* patched.
*/
unpatched = aml_if(aml_equal(dsm_mem, aml_int(0x0)));
unpatched = aml_equal(dsm_mem, aml_int(0x0));
expected_uuid = aml_local(0);
ifctx = aml_if(aml_equal(handle, aml_int(0x0)));
aml_append(ifctx, aml_store(
aml_touuid("2F10E7A4-9E91-11E4-89D3-123B93F75CBA")
/* UUID for NVDIMM Root Device */, expected_uuid));
aml_append(method, ifctx);
elsectx = aml_else();
aml_append(elsectx, aml_store(
aml_touuid("4309AC30-0D11-11E4-9191-0800200C9A66")
/* UUID for NVDIMM Devices */, expected_uuid));
aml_append(method, elsectx);
uuid_invalid = aml_lnot(aml_equal(uuid, expected_uuid));
unsupport = aml_if(aml_or(unpatched, uuid_invalid, NULL));
/*
* function 0 is called to inquire what functions are supported by
@ -507,23 +820,41 @@ static void nvdimm_build_common_dsm(Aml *dev)
ifctx = aml_if(aml_equal(function, aml_int(0)));
byte_list[0] = 0 /* No function Supported */;
aml_append(ifctx, aml_return(aml_buffer(1, byte_list)));
aml_append(unpatched, ifctx);
aml_append(unsupport, ifctx);
/* No function is supported yet. */
byte_list[0] = 1 /* Not Supported */;
aml_append(unpatched, aml_return(aml_buffer(1, byte_list)));
aml_append(method, unpatched);
aml_append(unsupport, aml_return(aml_buffer(1, byte_list)));
aml_append(method, unsupport);
/*
* The HDLE indicates the DSM function is issued from which device,
* it is not used at this time as no function is supported yet.
* Currently we make it always be 0 for all the devices and will set
* the appropriate value once real function is implemented.
* it reserves 0 for root device and is the handle for NVDIMM devices.
* See the comments in nvdimm_slot_to_handle().
*/
aml_append(method, aml_store(aml_int(0x0), aml_name("HDLE")));
aml_append(method, aml_store(handle, aml_name("HDLE")));
aml_append(method, aml_store(aml_arg(1), aml_name("REVS")));
aml_append(method, aml_store(aml_arg(2), aml_name("FUNC")));
/*
* The fourth parameter (Arg3) of _DSM is a package which contains
* a buffer, the layout of the buffer is specified by UUID (Arg0),
* Revision ID (Arg1) and Function Index (Arg2) which are documented
* in the DSM Spec.
*/
pckg = aml_arg(3);
ifctx = aml_if(aml_and(aml_equal(aml_object_type(pckg),
aml_int(4 /* Package */)) /* It is a Package? */,
aml_equal(aml_sizeof(pckg), aml_int(1)) /* 1 element? */,
NULL));
pckg_index = aml_local(2);
pckg_buf = aml_local(3);
aml_append(ifctx, aml_store(aml_index(pckg, aml_int(0)), pckg_index));
aml_append(ifctx, aml_store(aml_derefof(pckg_index), pckg_buf));
aml_append(ifctx, aml_store(pckg_buf, aml_name("ARG3")));
aml_append(method, ifctx);
/*
* tell QEMU about the real address of DSM memory, then QEMU
* gets the control and fills the result in DSM memory.
@ -542,13 +873,14 @@ static void nvdimm_build_common_dsm(Aml *dev)
aml_append(dev, method);
}
static void nvdimm_build_device_dsm(Aml *dev)
static void nvdimm_build_device_dsm(Aml *dev, uint32_t handle)
{
Aml *method;
method = aml_method("_DSM", 4, AML_NOTSERIALIZED);
aml_append(method, aml_return(aml_call4(NVDIMM_COMMON_DSM, aml_arg(0),
aml_arg(1), aml_arg(2), aml_arg(3))));
aml_append(method, aml_return(aml_call5(NVDIMM_COMMON_DSM, aml_arg(0),
aml_arg(1), aml_arg(2), aml_arg(3),
aml_int(handle))));
aml_append(dev, method);
}
@ -573,7 +905,7 @@ static void nvdimm_build_nvdimm_devices(GSList *device_list, Aml *root_dev)
*/
aml_append(nvdimm_dev, aml_name_decl("_ADR", aml_int(handle)));
nvdimm_build_device_dsm(nvdimm_dev);
nvdimm_build_device_dsm(nvdimm_dev, handle);
aml_append(root_dev, nvdimm_dev);
}
}
@ -665,7 +997,9 @@ static void nvdimm_build_ssdt(GSList *device_list, GArray *table_offsets,
aml_append(dev, field);
nvdimm_build_common_dsm(dev);
nvdimm_build_device_dsm(dev);
/* 0 is reserved for root device. */
nvdimm_build_device_dsm(dev, 0);
nvdimm_build_nvdimm_devices(device_list, dev);

71
hw/acpi/piix4.c
View File

@ -34,6 +34,7 @@
#include "hw/acpi/piix4.h"
#include "hw/acpi/pcihp.h"
#include "hw/acpi/cpu_hotplug.h"
#include "hw/acpi/cpu.h"
#include "hw/hotplug.h"
#include "hw/mem/pc-dimm.h"
#include "hw/acpi/memory_hotplug.h"
@ -86,7 +87,9 @@ typedef struct PIIX4PMState {
uint8_t disable_s4;
uint8_t s4_val;
bool cpu_hotplug_legacy;
AcpiCpuHotplug gpe_cpu;
CPUHotplugState cpuhp_state;
MemHotplugState acpi_memory_hotplug;
} PIIX4PMState;
@ -273,6 +276,32 @@ static const VMStateDescription vmstate_memhp_state = {
}
};
static bool vmstate_test_use_cpuhp(void *opaque)
{
PIIX4PMState *s = opaque;
return !s->cpu_hotplug_legacy;
}
static int vmstate_cpuhp_pre_load(void *opaque)
{
Object *obj = OBJECT(opaque);
object_property_set_bool(obj, false, "cpu-hotplug-legacy", &error_abort);
return 0;
}
static const VMStateDescription vmstate_cpuhp_state = {
.name = "piix4_pm/cpuhp",
.version_id = 1,
.minimum_version_id = 1,
.minimum_version_id_old = 1,
.needed = vmstate_test_use_cpuhp,
.pre_load = vmstate_cpuhp_pre_load,
.fields = (VMStateField[]) {
VMSTATE_CPU_HOTPLUG(cpuhp_state, PIIX4PMState),
VMSTATE_END_OF_LIST()
}
};
/* qemu-kvm 1.2 uses version 3 but advertised as 2
* To support incoming qemu-kvm 1.2 migration, change version_id
* and minimum_version_id to 2 below (which breaks migration from
@ -307,6 +336,7 @@ static const VMStateDescription vmstate_acpi = {
},
.subsections = (const VMStateDescription*[]) {
&vmstate_memhp_state,
&vmstate_cpuhp_state,
NULL
}
};
@ -352,7 +382,11 @@ static void piix4_device_plug_cb(HotplugHandler *hotplug_dev,
} else if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
acpi_pcihp_device_plug_cb(hotplug_dev, &s->acpi_pci_hotplug, dev, errp);
} else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) {
legacy_acpi_cpu_plug_cb(hotplug_dev, &s->gpe_cpu, dev, errp);
if (s->cpu_hotplug_legacy) {
legacy_acpi_cpu_plug_cb(hotplug_dev, &s->gpe_cpu, dev, errp);
} else {
acpi_cpu_plug_cb(hotplug_dev, &s->cpuhp_state, dev, errp);
}
} else {
error_setg(errp, "acpi: device plug request for not supported device"
" type: %s", object_get_typename(OBJECT(dev)));
@ -371,6 +405,9 @@ static void piix4_device_unplug_request_cb(HotplugHandler *hotplug_dev,
} else if (object_dynamic_cast(OBJECT(dev), TYPE_PCI_DEVICE)) {
acpi_pcihp_device_unplug_cb(hotplug_dev, &s->acpi_pci_hotplug, dev,
errp);
} else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU) &&
!s->cpu_hotplug_legacy) {
acpi_cpu_unplug_request_cb(hotplug_dev, &s->cpuhp_state, dev, errp);
} else {
error_setg(errp, "acpi: device unplug request for not supported device"
" type: %s", object_get_typename(OBJECT(dev)));
@ -385,6 +422,9 @@ static void piix4_device_unplug_cb(HotplugHandler *hotplug_dev,
if (s->acpi_memory_hotplug.is_enabled &&
object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
acpi_memory_unplug_cb(&s->acpi_memory_hotplug, dev, errp);
} else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU) &&
!s->cpu_hotplug_legacy) {
acpi_cpu_unplug_cb(&s->cpuhp_state, dev, errp);
} else {
error_setg(errp, "acpi: device unplug for not supported device"
" type: %s", object_get_typename(OBJECT(dev)));
@ -560,6 +600,26 @@ static const MemoryRegionOps piix4_gpe_ops = {
.endianness = DEVICE_LITTLE_ENDIAN,
};
static bool piix4_get_cpu_hotplug_legacy(Object *obj, Error **errp)
{
PIIX4PMState *s = PIIX4_PM(obj);
return s->cpu_hotplug_legacy;
}
static void piix4_set_cpu_hotplug_legacy(Object *obj, bool value, Error **errp)
{
PIIX4PMState *s = PIIX4_PM(obj);
assert(!value);
if (s->cpu_hotplug_legacy && value == false) {
acpi_switch_to_modern_cphp(&s->gpe_cpu, &s->cpuhp_state,
PIIX4_CPU_HOTPLUG_IO_BASE);
}
s->cpu_hotplug_legacy = value;
}
static void piix4_acpi_system_hot_add_init(MemoryRegion *parent,
PCIBus *bus, PIIX4PMState *s)
{
@ -570,6 +630,11 @@ static void piix4_acpi_system_hot_add_init(MemoryRegion *parent,
acpi_pcihp_init(OBJECT(s), &s->acpi_pci_hotplug, bus, parent,
s->use_acpi_pci_hotplug);
s->cpu_hotplug_legacy = true;
object_property_add_bool(OBJECT(s), "cpu-hotplug-legacy",
piix4_get_cpu_hotplug_legacy,
piix4_set_cpu_hotplug_legacy,
NULL);
legacy_acpi_cpu_hotplug_init(parent, OBJECT(s), &s->gpe_cpu,
PIIX4_CPU_HOTPLUG_IO_BASE);
@ -583,6 +648,9 @@ static void piix4_ospm_status(AcpiDeviceIf *adev, ACPIOSTInfoList ***list)
PIIX4PMState *s = PIIX4_PM(adev);
acpi_memory_ospm_status(&s->acpi_memory_hotplug, list);
if (!s->cpu_hotplug_legacy) {
acpi_cpu_ospm_status(&s->cpuhp_state, list);
}
}
static void piix4_send_gpe(AcpiDeviceIf *adev, AcpiEventStatusBits ev)
@ -631,6 +699,7 @@ static void piix4_pm_class_init(ObjectClass *klass, void *data)
hc->unplug = piix4_device_unplug_cb;
adevc->ospm_status = piix4_ospm_status;
adevc->send_event = piix4_send_gpe;
adevc->madt_cpu = pc_madt_cpu_entry;
}
static const TypeInfo piix4_pm_info = {

14
hw/acpi/trace-events
View File

@ -16,3 +16,17 @@ mhp_acpi_clear_insert_evt(uint32_t slot) "slot[0x%"PRIx32"] clear insert event"
mhp_acpi_clear_remove_evt(uint32_t slot) "slot[0x%"PRIx32"] clear remove event"
mhp_acpi_pc_dimm_deleted(uint32_t slot) "slot[0x%"PRIx32"] pc-dimm deleted"
mhp_acpi_pc_dimm_delete_failed(uint32_t slot) "slot[0x%"PRIx32"] pc-dimm delete failed"
# hw/acpi/cpu.c
cpuhp_acpi_invalid_idx_selected(uint32_t idx) "0x%"PRIx32
cpuhp_acpi_read_flags(uint32_t idx, uint8_t flags) "idx[0x%"PRIx32"] flags: 0x%"PRIx8
cpuhp_acpi_write_idx(uint32_t idx) "set active cpu idx: 0x%"PRIx32
cpuhp_acpi_write_cmd(uint32_t idx, uint8_t cmd) "idx[0x%"PRIx32"] cmd: 0x%"PRIx8
cpuhp_acpi_read_cmd_data(uint32_t idx, uint32_t data) "idx[0x%"PRIx32"] data: 0x%"PRIx32
cpuhp_acpi_cpu_has_events(uint32_t idx, bool ins, bool rm) "idx[0x%"PRIx32"] inserting: %d, removing: %d"
cpuhp_acpi_clear_inserting_evt(uint32_t idx) "idx[0x%"PRIx32"]"
cpuhp_acpi_clear_remove_evt(uint32_t idx) "idx[0x%"PRIx32"]"
cpuhp_acpi_ejecting_invalid_cpu(uint32_t idx) "0x%"PRIx32
cpuhp_acpi_ejecting_cpu(uint32_t idx) "0x%"PRIx32
cpuhp_acpi_write_ost_ev(uint32_t slot, uint32_t ev) "idx[0x%"PRIx32"] OST EVENT: 0x%"PRIx32
cpuhp_acpi_write_ost_status(uint32_t slot, uint32_t st) "idx[0x%"PRIx32"] OST STATUS: 0x%"PRIx32

6
hw/block/dataplane/virtio-blk.c
View File

@ -79,7 +79,7 @@ void virtio_blk_data_plane_create(VirtIODevice *vdev, VirtIOBlkConf *conf,
}
/* Don't try if transport does not support notifiers. */
if (!k->set_guest_notifiers || !k->set_host_notifier) {
if (!k->set_guest_notifiers || !k->ioeventfd_started) {
error_setg(errp,
"device is incompatible with dataplane "
"(transport does not support notifiers)");
@ -157,7 +157,7 @@ void virtio_blk_data_plane_start(VirtIOBlockDataPlane *s)
s->guest_notifier = virtio_queue_get_guest_notifier(s->vq);
/* Set up virtqueue notify */
r = k->set_host_notifier(qbus->parent, 0, true);
r = virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), 0, true);
if (r != 0) {
fprintf(stderr, "virtio-blk failed to set host notifier (%d)\n", r);
goto fail_host_notifier;
@ -217,7 +217,7 @@ void virtio_blk_data_plane_stop(VirtIOBlockDataPlane *s)
aio_context_release(s->ctx);
k->set_host_notifier(qbus->parent, 0, false);
virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), 0, false);
/* Clean up guest notifier (irq) */
k->set_guest_notifiers(qbus->parent, 1, false);

80
hw/i386/acpi-build.c
View File

@ -33,6 +33,7 @@
#include "hw/timer/hpet.h"
#include "hw/acpi/acpi-defs.h"
#include "hw/acpi/acpi.h"
#include "hw/acpi/cpu.h"
#include "hw/nvram/fw_cfg.h"
#include "hw/acpi/bios-linker-loader.h"
#include "hw/loader.h"
@ -43,6 +44,7 @@
#include "hw/acpi/tpm.h"
#include "sysemu/tpm_backend.h"
#include "hw/timer/mc146818rtc_regs.h"
#include "sysemu/numa.h"
/* Supported chipsets: */
#include "hw/acpi/piix4.h"
@ -58,6 +60,8 @@
#include "qapi/qmp/qint.h"
#include "qom/qom-qobject.h"
#include "hw/acpi/ipmi.h"
/* These are used to size the ACPI tables for -M pc-i440fx-1.7 and
* -M pc-i440fx-2.0. Even if the actual amount of AML generated grows
* a little bit, there should be plenty of free space since the DSDT
@ -327,12 +331,38 @@ build_fadt(GArray *table_data, BIOSLinker *linker, AcpiPmInfo *pm,
(void *)fadt, "FACP", sizeof(*fadt), 1, oem_id, oem_table_id);
}
void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid,
CPUArchIdList *apic_ids, GArray *entry)
{
int apic_id;
AcpiMadtProcessorApic *apic = acpi_data_push(entry, sizeof *apic);
apic_id = apic_ids->cpus[uid].arch_id;
apic->type = ACPI_APIC_PROCESSOR;
apic->length = sizeof(*apic);
apic->processor_id = uid;
apic->local_apic_id = apic_id;
if (apic_ids->cpus[uid].cpu != NULL) {
apic->flags = cpu_to_le32(1);
} else {
/* ACPI spec says that LAPIC entry for non present
* CPU may be omitted from MADT or it must be marked
* as disabled. However omitting non present CPU from
* MADT breaks hotplug on linux. So possible CPUs
* should be put in MADT but kept disabled.
*/
apic->flags = cpu_to_le32(0);
}
}
static void
build_madt(GArray *table_data, BIOSLinker *linker, PCMachineState *pcms)
{
MachineClass *mc = MACHINE_GET_CLASS(pcms);
CPUArchIdList *apic_ids = mc->possible_cpu_arch_ids(MACHINE(pcms));
int madt_start = table_data->len;
AcpiDeviceIfClass *adevc = ACPI_DEVICE_IF_GET_CLASS(pcms->acpi_dev);
AcpiDeviceIf *adev = ACPI_DEVICE_IF(pcms->acpi_dev);
AcpiMultipleApicTable *madt;
AcpiMadtIoApic *io_apic;
@ -345,24 +375,7 @@ build_madt(GArray *table_data, BIOSLinker *linker, PCMachineState *pcms)
madt->flags = cpu_to_le32(1);
for (i = 0; i < apic_ids->len; i++) {
AcpiMadtProcessorApic *apic = acpi_data_push(table_data, sizeof *apic);
int apic_id = apic_ids->cpus[i].arch_id;
apic->type = ACPI_APIC_PROCESSOR;
apic->length = sizeof(*apic);
apic->processor_id = i;
apic->local_apic_id = apic_id;
if (apic_ids->cpus[i].cpu != NULL) {
apic->flags = cpu_to_le32(1);
} else {
/* ACPI spec says that LAPIC entry for non present
* CPU may be omitted from MADT or it must be marked
* as disabled. However omitting non present CPU from
* MADT breaks hotplug on linux. So possible CPUs
* should be put in MADT but kept disabled.
*/
apic->flags = cpu_to_le32(0);
}
adevc->madt_cpu(adev, i, apic_ids, table_data);
}
g_free(apic_ids);
@ -1334,8 +1347,10 @@ static Aml *build_com_device_aml(uint8_t uid)
static void build_isa_devices_aml(Aml *table)
{
ISADevice *fdc = pc_find_fdc0();
bool ambiguous;
Aml *scope = aml_scope("_SB.PCI0.ISA");
Object *obj = object_resolve_path_type("", TYPE_ISA_BUS, &ambiguous);
aml_append(scope, build_rtc_device_aml());
aml_append(scope, build_kbd_device_aml());
@ -1347,6 +1362,14 @@ static void build_isa_devices_aml(Aml *table)
aml_append(scope, build_com_device_aml(1));
aml_append(scope, build_com_device_aml(2));
if (ambiguous) {
error_report("Multiple ISA busses, unable to define IPMI ACPI data");
} else if (!obj) {
error_report("No ISA bus, unable to define IPMI ACPI data");
} else {
build_acpi_ipmi_devices(scope, BUS(obj));
}
aml_append(table, scope);
}
@ -1874,6 +1897,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,
GPtrArray *mem_ranges = g_ptr_array_new_with_free_func(crs_range_free);
GPtrArray *io_ranges = g_ptr_array_new_with_free_func(crs_range_free);
PCMachineState *pcms = PC_MACHINE(machine);
PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(machine);
uint32_t nr_mem = machine->ram_slots;
int root_bus_limit = 0xFF;
PCIBus *bus = NULL;
@ -1929,7 +1953,15 @@ build_dsdt(GArray *table_data, BIOSLinker *linker,
build_q35_pci0_int(dsdt);
}
build_legacy_cpu_hotplug_aml(dsdt, machine, pm->cpu_hp_io_base);
if (pcmc->legacy_cpu_hotplug) {
build_legacy_cpu_hotplug_aml(dsdt, machine, pm->cpu_hp_io_base);
} else {
CPUHotplugFeatures opts = {
.apci_1_compatible = true, .has_legacy_cphp = true
};
build_cpus_aml(dsdt, machine, opts, pm->cpu_hp_io_base,
"\\_SB.PCI0", "\\_GPE._E02");
}
build_memory_hotplug_aml(dsdt, nr_mem, pm->mem_hp_io_base,
pm->mem_hp_io_len);
@ -2297,7 +2329,6 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
AcpiSratMemoryAffinity *numamem;
int i;
uint64_t curnode;
int srat_start, numa_start, slots;
uint64_t mem_len, mem_base, next_base;
MachineClass *mc = MACHINE_GET_CLASS(machine);
@ -2313,14 +2344,19 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine)
srat->reserved1 = cpu_to_le32(1);
for (i = 0; i < apic_ids->len; i++) {
int j;
int apic_id = apic_ids->cpus[i].arch_id;
core = acpi_data_push(table_data, sizeof *core);
core->type = ACPI_SRAT_PROCESSOR_APIC;
core->length = sizeof(*core);
core->local_apic_id = apic_id;
curnode = pcms->node_cpu[apic_id];
core->proximity_lo = curnode;
for (j = 0; j < nb_numa_nodes; j++) {
if (test_bit(i, numa_info[j].node_cpu)) {
core->proximity_lo = j;
break;
}
}
memset(core->proximity_hi, 0, 3);
core->local_sapic_eid = 0;
core->flags = cpu_to_le32(1);

14
hw/i386/kvm/pci-assign.c
View File

@ -36,8 +36,6 @@
#include "kvm_i386.h"
#include "hw/pci/pci-assign.h"
#define MSIX_PAGE_SIZE 0x1000
/* From linux/ioport.h */
#define IORESOURCE_IO 0x00000100 /* Resource type */
#define IORESOURCE_MEM 0x00000200
@ -122,6 +120,7 @@ typedef struct AssignedDevice {
int *msi_virq;
MSIXTableEntry *msix_table;
hwaddr msix_table_addr;
uint16_t msix_table_size;
uint16_t msix_max;
MemoryRegion mmio;
char *configfd_name;
@ -1310,6 +1309,7 @@ static int assigned_device_pci_cap_init(PCIDevice *pci_dev, Error **errp)
bar_nr = msix_table_entry & PCI_MSIX_FLAGS_BIRMASK;
msix_table_entry &= ~PCI_MSIX_FLAGS_BIRMASK;
dev->msix_table_addr = pci_region[bar_nr].base_addr + msix_table_entry;
dev->msix_table_size = msix_max * sizeof(MSIXTableEntry);
dev->msix_max = msix_max;
}
@ -1633,7 +1633,7 @@ static void assigned_dev_msix_reset(AssignedDevice *dev)
return;
}
memset(dev->msix_table, 0, MSIX_PAGE_SIZE);
memset(dev->msix_table, 0, dev->msix_table_size);
for (i = 0, entry = dev->msix_table; i < dev->msix_max; i++, entry++) {
entry->ctrl = cpu_to_le32(0x1); /* Masked */
@ -1642,8 +1642,8 @@ static void assigned_dev_msix_reset(AssignedDevice *dev)
static void assigned_dev_register_msix_mmio(AssignedDevice *dev, Error **errp)
{
dev->msix_table = mmap(NULL, MSIX_PAGE_SIZE, PROT_READ|PROT_WRITE,
MAP_ANONYMOUS|MAP_PRIVATE, 0, 0);
dev->msix_table = mmap(NULL, dev->msix_table_size, PROT_READ | PROT_WRITE,
MAP_ANONYMOUS | MAP_PRIVATE, 0, 0);
if (dev->msix_table == MAP_FAILED) {
error_setg_errno(errp, errno, "failed to allocate msix_table");
dev->msix_table = NULL;
@ -1653,7 +1653,7 @@ static void assigned_dev_register_msix_mmio(AssignedDevice *dev, Error **errp)
assigned_dev_msix_reset(dev);
memory_region_init_io(&dev->mmio, OBJECT(dev), &assigned_dev_msix_mmio_ops,
dev, "assigned-dev-msix", MSIX_PAGE_SIZE);
dev, "assigned-dev-msix", dev->msix_table_size);
}
static void assigned_dev_unregister_msix_mmio(AssignedDevice *dev)
@ -1662,7 +1662,7 @@ static void assigned_dev_unregister_msix_mmio(AssignedDevice *dev)
return;
}
if (munmap(dev->msix_table, MSIX_PAGE_SIZE) == -1) {
if (munmap(dev->msix_table, dev->msix_table_size) == -1) {
error_report("error unmapping msix_table! %s", strerror(errno));
}
dev->msix_table = NULL;

63
hw/i386/pc.c
View File

@ -1179,7 +1179,7 @@ void pc_machine_done(Notifier *notifier, void *data)
void pc_guest_info_init(PCMachineState *pcms)
{
int i, j;
int i;
pcms->apic_xrupt_override = kvm_allows_irq0_override();
pcms->numa_nodes = nb_numa_nodes;
@ -1189,20 +1189,6 @@ void pc_guest_info_init(PCMachineState *pcms)
pcms->node_mem[i] = numa_info[i].node_mem;
}
pcms->node_cpu = g_malloc0(pcms->apic_id_limit *
sizeof *pcms->node_cpu);
for (i = 0; i < max_cpus; i++) {
unsigned int apic_id = x86_cpu_apic_id_from_index(i);
assert(apic_id < pcms->apic_id_limit);
for (j = 0; j < nb_numa_nodes; j++) {
if (test_bit(i, numa_info[j].node_cpu)) {
pcms->node_cpu[apic_id] = j;
break;
}
}
}
pcms->machine_done.notify = pc_machine_done;
qemu_add_machine_init_done_notifier(&pcms->machine_done);
}
@ -1707,6 +1693,49 @@ static void pc_cpu_plug(HotplugHandler *hotplug_dev,
out:
error_propagate(errp, local_err);
}
static void pc_cpu_unplug_request_cb(HotplugHandler *hotplug_dev,
DeviceState *dev, Error **errp)
{
HotplugHandlerClass *hhc;
Error *local_err = NULL;
PCMachineState *pcms = PC_MACHINE(hotplug_dev);
hhc = HOTPLUG_HANDLER_GET_CLASS(pcms->acpi_dev);
hhc->unplug_request(HOTPLUG_HANDLER(pcms->acpi_dev), dev, &local_err);
if (local_err) {
goto out;
}
out:
error_propagate(errp, local_err);
}
static void pc_cpu_unplug_cb(HotplugHandler *hotplug_dev,
DeviceState *dev, Error **errp)
{
HotplugHandlerClass *hhc;
Error *local_err = NULL;
PCMachineState *pcms = PC_MACHINE(hotplug_dev);
hhc = HOTPLUG_HANDLER_GET_CLASS(pcms->acpi_dev);
hhc->unplug(HOTPLUG_HANDLER(pcms->acpi_dev), dev, &local_err);
if (local_err) {
goto out;
}
/*
* TODO: enable unplug once generic CPU remove bits land
* for now guest will be able to eject CPU ACPI wise but
* it will come back again on machine reset.
*/
/* object_unparent(OBJECT(dev)); */
out:
error_propagate(errp, local_err);
}
static void pc_machine_device_plug_cb(HotplugHandler *hotplug_dev,
DeviceState *dev, Error **errp)
@ -1723,6 +1752,8 @@ static void pc_machine_device_unplug_request_cb(HotplugHandler *hotplug_dev,
{
if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
pc_dimm_unplug_request(hotplug_dev, dev, errp);
} else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) {
pc_cpu_unplug_request_cb(hotplug_dev, dev, errp);
} else {
error_setg(errp, "acpi: device unplug request for not supported device"
" type: %s", object_get_typename(OBJECT(dev)));
@ -1734,6 +1765,8 @@ static void pc_machine_device_unplug_cb(HotplugHandler *hotplug_dev,
{
if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) {
pc_dimm_unplug(hotplug_dev, dev, errp);
} else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) {
pc_cpu_unplug_cb(hotplug_dev, dev, errp);
} else {
error_setg(errp, "acpi: device unplug for not supported device"
" type: %s", object_get_typename(OBJECT(dev)));

2
hw/i386/pc_piix.c
View File

@ -445,9 +445,11 @@ DEFINE_I440FX_MACHINE(v2_7, "pc-i440fx-2.7", NULL,
static void pc_i440fx_2_6_machine_options(MachineClass *m)
{
PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
pc_i440fx_2_7_machine_options(m);
m->is_default = 0;
m->alias = NULL;
pcmc->legacy_cpu_hotplug = true;
SET_MACHINE_COMPAT(m, PC_COMPAT_2_6);
}

2
hw/i386/pc_q35.c
View File

@ -294,8 +294,10 @@ DEFINE_Q35_MACHINE(v2_7, "pc-q35-2.7", NULL,
static void pc_q35_2_6_machine_options(MachineClass *m)
{
PCMachineClass *pcmc = PC_MACHINE_CLASS(m);
pc_q35_2_7_machine_options(m);
m->alias = NULL;
pcmc->legacy_cpu_hotplug = true;
SET_MACHINE_COMPAT(m, PC_COMPAT_2_6);
}

1
hw/isa/lpc_ich9.c
View File

@ -714,6 +714,7 @@ static void ich9_lpc_class_init(ObjectClass *klass, void *data)
hc->unplug = ich9_pm_device_unplug_cb;
adevc->ospm_status = ich9_pm_ospm_status;
adevc->send_event = ich9_send_gpe;
adevc->madt_cpu = pc_madt_cpu_entry;
}
static const TypeInfo ich9_lpc_info = {

132
hw/mem/nvdimm.c
View File

@ -23,20 +23,152 @@
*/
#include "qemu/osdep.h"
#include "qapi/error.h"
#include "qapi/visitor.h"
#include "hw/mem/nvdimm.h"
static void nvdimm_get_label_size(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
NVDIMMDevice *nvdimm = NVDIMM(obj);
uint64_t value = nvdimm->label_size;
visit_type_size(v, name, &value, errp);
}
static void nvdimm_set_label_size(Object *obj, Visitor *v, const char *name,
void *opaque, Error **errp)
{
NVDIMMDevice *nvdimm = NVDIMM(obj);
Error *local_err = NULL;
uint64_t value;
if (memory_region_size(&nvdimm->nvdimm_mr)) {
error_setg(&local_err, "cannot change property value");
goto out;
}
visit_type_size(v, name, &value, &local_err);
if (local_err) {
goto out;
}
if (value < MIN_NAMESPACE_LABEL_SIZE) {
error_setg(&local_err, "Property '%s.%s' (0x%" PRIx64 ") is required"
" at least 0x%lx", object_get_typename(obj),
name, value, MIN_NAMESPACE_LABEL_SIZE);
goto out;
}
nvdimm->label_size = value;
out:
error_propagate(errp, local_err);
}
static void nvdimm_init(Object *obj)
{
object_property_add(obj, "label-size", "int",
nvdimm_get_label_size, nvdimm_set_label_size, NULL,
NULL, NULL);
}
static MemoryRegion *nvdimm_get_memory_region(PCDIMMDevice *dimm)
{
NVDIMMDevice *nvdimm = NVDIMM(dimm);
return &nvdimm->nvdimm_mr;
}
static void nvdimm_realize(PCDIMMDevice *dimm, Error **errp)
{
MemoryRegion *mr = host_memory_backend_get_memory(dimm->hostmem, errp);
NVDIMMDevice *nvdimm = NVDIMM(dimm);
uint64_t align, pmem_size, size = memory_region_size(mr);
align = memory_region_get_alignment(mr);
pmem_size = size - nvdimm->label_size;
nvdimm->label_data = memory_region_get_ram_ptr(mr) + pmem_size;
pmem_size = QEMU_ALIGN_DOWN(pmem_size, align);
if (size <= nvdimm->label_size || !pmem_size) {
HostMemoryBackend *hostmem = dimm->hostmem;
char *path = object_get_canonical_path_component(OBJECT(hostmem));
error_setg(errp, "the size of memdev %s (0x%" PRIx64 ") is too "
"small to contain nvdimm label (0x%" PRIx64 ") and "
"aligned PMEM (0x%" PRIx64 ")",
path, memory_region_size(mr), nvdimm->label_size, align);
return;
}
memory_region_init_alias(&nvdimm->nvdimm_mr, OBJECT(dimm),
"nvdimm-memory", mr, 0, pmem_size);
nvdimm->nvdimm_mr.align = align;
}
/*
* the caller should check the input parameters before calling
* label read/write functions.
*/
static void nvdimm_validate_rw_label_data(NVDIMMDevice *nvdimm, uint64_t size,
uint64_t offset)
{
assert((nvdimm->label_size >= size + offset) && (offset + size > offset));
}
static void nvdimm_read_label_data(NVDIMMDevice *nvdimm, void *buf,
uint64_t size, uint64_t offset)
{
nvdimm_validate_rw_label_data(nvdimm, size, offset);
memcpy(buf, nvdimm->label_data + offset, size);
}
static void nvdimm_write_label_data(NVDIMMDevice *nvdimm, const void *buf,
uint64_t size, uint64_t offset)
{
MemoryRegion *mr;
PCDIMMDevice *dimm = PC_DIMM(nvdimm);
uint64_t backend_offset;
nvdimm_validate_rw_label_data(nvdimm, size, offset);
memcpy(nvdimm->label_data + offset, buf, size);
mr = host_memory_backend_get_memory(dimm->hostmem, &error_abort);
backend_offset = memory_region_size(mr) - nvdimm->label_size + offset;
memory_region_set_dirty(mr, backend_offset, size);
}
static MemoryRegion *nvdimm_get_vmstate_memory_region(PCDIMMDevice *dimm)
{
return host_memory_backend_get_memory(dimm->hostmem, &error_abort);
}
static void nvdimm_class_init(ObjectClass *oc, void *data)
{
DeviceClass *dc = DEVICE_CLASS(oc);
PCDIMMDeviceClass *ddc = PC_DIMM_CLASS(oc);
NVDIMMClass *nvc = NVDIMM_CLASS(oc);
/* nvdimm hotplug has not been supported yet. */
dc->hotpluggable = false;
ddc->realize = nvdimm_realize;
ddc->get_memory_region = nvdimm_get_memory_region;
ddc->get_vmstate_memory_region = nvdimm_get_vmstate_memory_region;
nvc->read_label_data = nvdimm_read_label_data;
nvc->write_label_data = nvdimm_write_label_data;
}
static TypeInfo nvdimm_info = {
.name = TYPE_NVDIMM,
.parent = TYPE_PC_DIMM,
.class_size = sizeof(NVDIMMClass),
.class_init = nvdimm_class_init,
.instance_size = sizeof(NVDIMMDevice),
.instance_init = nvdimm_init,
};
static void nvdimm_register_types(void)

14
hw/mem/pc-dimm.c
View File

@ -40,6 +40,8 @@ void pc_dimm_memory_plug(DeviceState *dev, MemoryHotplugState *hpms,
int slot;
MachineState *machine = MACHINE(qdev_get_machine());
PCDIMMDevice *dimm = PC_DIMM(dev);
PCDIMMDeviceClass *ddc = PC_DIMM_GET_CLASS(dimm);
MemoryRegion *vmstate_mr = ddc->get_vmstate_memory_region(dimm);
Error *local_err = NULL;
uint64_t existing_dimms_capacity = 0;
uint64_t addr;
@ -105,7 +107,7 @@ void pc_dimm_memory_plug(DeviceState *dev, MemoryHotplugState *hpms,
}
memory_region_add_subregion(&hpms->mr, addr - hpms->base, mr);
vmstate_register_ram(mr, dev);
vmstate_register_ram(vmstate_mr, dev);
numa_set_mem_node_id(addr, memory_region_size(mr), dimm->node);
out:
@ -116,10 +118,12 @@ void pc_dimm_memory_unplug(DeviceState *dev, MemoryHotplugState *hpms,
MemoryRegion *mr)
{
PCDIMMDevice *dimm = PC_DIMM(dev);
PCDIMMDeviceClass *ddc = PC_DIMM_GET_CLASS(dimm);
MemoryRegion *vmstate_mr = ddc->get_vmstate_memory_region(dimm);
numa_unset_mem_node_id(dimm->addr, memory_region_size(mr), dimm->node);
memory_region_del_subregion(&hpms->mr, mr);
vmstate_unregister_ram(mr, dev);
vmstate_unregister_ram(vmstate_mr, dev);
}
static int pc_existing_dimms_capacity_internal(Object *obj, void *opaque)
@ -424,6 +428,11 @@ static MemoryRegion *pc_dimm_get_memory_region(PCDIMMDevice *dimm)
return host_memory_backend_get_memory(dimm->hostmem, &error_abort);
}
static MemoryRegion *pc_dimm_get_vmstate_memory_region(PCDIMMDevice *dimm)
{
return host_memory_backend_get_memory(dimm->hostmem, &error_abort);
}
static void pc_dimm_class_init(ObjectClass *oc, void *data)
{
DeviceClass *dc = DEVICE_CLASS(oc);
@ -434,6 +443,7 @@ static void pc_dimm_class_init(ObjectClass *oc, void *data)
dc->desc = "DIMM memory module";
ddc->get_memory_region = pc_dimm_get_memory_region;
ddc->get_vmstate_memory_region = pc_dimm_get_vmstate_memory_region;
}
static TypeInfo pc_dimm_info = {

141
hw/s390x/virtio-ccw.c
View File

@ -69,92 +69,58 @@ VirtIODevice *virtio_ccw_get_vdev(SubchDev *sch)
return vdev;
}
static int virtio_ccw_set_guest2host_notifier(VirtioCcwDevice *dev, int n,
bool assign, bool set_handler)
{
VirtIODevice *vdev = virtio_bus_get_device(&dev->bus);
VirtQueue *vq = virtio_get_queue(vdev, n);
EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
int r = 0;
SubchDev *sch = dev->sch;
uint32_t sch_id = (css_build_subchannel_id(sch) << 16) | sch->schid;
if (assign) {
r = event_notifier_init(notifier, 1);
if (r < 0) {
error_report("%s: unable to init event notifier: %d", __func__, r);
return r;
}
virtio_queue_set_host_notifier_fd_handler(vq, true, set_handler);
r = s390_assign_subch_ioeventfd(notifier, sch_id, n, assign);
if (r < 0) {
error_report("%s: unable to assign ioeventfd: %d", __func__, r);
virtio_queue_set_host_notifier_fd_handler(vq, false, false);
event_notifier_cleanup(notifier);
return r;
}
} else {
virtio_queue_set_host_notifier_fd_handler(vq, false, false);
s390_assign_subch_ioeventfd(notifier, sch_id, n, assign);
event_notifier_cleanup(notifier);
}
return r;
}
static void virtio_ccw_start_ioeventfd(VirtioCcwDevice *dev)
{
VirtIODevice *vdev;
int n, r;
if (!(dev->flags & VIRTIO_CCW_FLAG_USE_IOEVENTFD) ||
dev->ioeventfd_disabled ||
dev->ioeventfd_started) {
return;
}
vdev = virtio_bus_get_device(&dev->bus);
for (n = 0; n < VIRTIO_CCW_QUEUE_MAX; n++) {
if (!virtio_queue_get_num(vdev, n)) {
continue;
}
r = virtio_ccw_set_guest2host_notifier(dev, n, true, true);
if (r < 0) {
goto assign_error;
}
}
dev->ioeventfd_started = true;
return;
assign_error:
while (--n >= 0) {
if (!virtio_queue_get_num(vdev, n)) {
continue;
}
r = virtio_ccw_set_guest2host_notifier(dev, n, false, false);
assert(r >= 0);
}
dev->ioeventfd_started = false;
/* Disable ioeventfd for this device. */
dev->flags &= ~VIRTIO_CCW_FLAG_USE_IOEVENTFD;
error_report("%s: failed. Fallback to userspace (slower).", __func__);
virtio_bus_start_ioeventfd(&dev->bus);
}
static void virtio_ccw_stop_ioeventfd(VirtioCcwDevice *dev)
{
VirtIODevice *vdev;
int n, r;
virtio_bus_stop_ioeventfd(&dev->bus);
}
if (!dev->ioeventfd_started) {
return;
static bool virtio_ccw_ioeventfd_started(DeviceState *d)
{
VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(d);
return dev->ioeventfd_started;
}
static void virtio_ccw_ioeventfd_set_started(DeviceState *d, bool started,
bool err)
{
VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(d);
dev->ioeventfd_started = started;
if (err) {
/* Disable ioeventfd for this device. */
dev->flags &= ~VIRTIO_CCW_FLAG_USE_IOEVENTFD;
}
vdev = virtio_bus_get_device(&dev->bus);
for (n = 0; n < VIRTIO_CCW_QUEUE_MAX; n++) {
if (!virtio_queue_get_num(vdev, n)) {
continue;
}
r = virtio_ccw_set_guest2host_notifier(dev, n, false, false);
assert(r >= 0);
}
dev->ioeventfd_started = false;
}
static bool virtio_ccw_ioeventfd_disabled(DeviceState *d)
{
VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(d);
return dev->ioeventfd_disabled ||
!(dev->flags & VIRTIO_CCW_FLAG_USE_IOEVENTFD);
}
static void virtio_ccw_ioeventfd_set_disabled(DeviceState *d, bool disabled)
{
VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(d);
dev->ioeventfd_disabled = disabled;
}
static int virtio_ccw_ioeventfd_assign(DeviceState *d, EventNotifier *notifier,
int n, bool assign)
{
VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(d);
SubchDev *sch = dev->sch;
uint32_t sch_id = (css_build_subchannel_id(sch) << 16) | sch->schid;
return s390_assign_subch_ioeventfd(notifier, sch_id, n, assign);
}
VirtualCssBus *virtual_css_bus_init(void)
@ -1157,19 +1123,6 @@ static bool virtio_ccw_query_guest_notifiers(DeviceState *d)
return !!(dev->sch->curr_status.pmcw.flags & PMCW_FLAGS_MASK_ENA);
}
static int virtio_ccw_set_host_notifier(DeviceState *d, int n, bool assign)
{
VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(d);
/* Stop using the generic ioeventfd, we are doing eventfd handling
* ourselves below */
dev->ioeventfd_disabled = assign;
if (assign) {
virtio_ccw_stop_ioeventfd(dev);
}
return virtio_ccw_set_guest2host_notifier(dev, n, assign, false);
}
static int virtio_ccw_get_mappings(VirtioCcwDevice *dev)
{
int r;
@ -1798,7 +1751,6 @@ static void virtio_ccw_bus_class_init(ObjectClass *klass, void *data)
k->notify = virtio_ccw_notify;
k->vmstate_change = virtio_ccw_vmstate_change;
k->query_guest_notifiers = virtio_ccw_query_guest_notifiers;
k->set_host_notifier = virtio_ccw_set_host_notifier;
k->set_guest_notifiers = virtio_ccw_set_guest_notifiers;
k->save_queue = virtio_ccw_save_queue;
k->load_queue = virtio_ccw_load_queue;
@ -1807,6 +1759,11 @@ static void virtio_ccw_bus_class_init(ObjectClass *klass, void *data)
k->device_plugged = virtio_ccw_device_plugged;
k->post_plugged = virtio_ccw_post_plugged;
k->device_unplugged = virtio_ccw_device_unplugged;
k->ioeventfd_started = virtio_ccw_ioeventfd_started;
k->ioeventfd_set_started = virtio_ccw_ioeventfd_set_started;
k->ioeventfd_disabled = virtio_ccw_ioeventfd_disabled;
k->ioeventfd_set_disabled = virtio_ccw_ioeventfd_set_disabled;
k->ioeventfd_assign = virtio_ccw_ioeventfd_assign;
}
static const TypeInfo virtio_ccw_bus_info = {

9
hw/scsi/virtio-scsi-dataplane.c
View File

@ -31,7 +31,7 @@ void virtio_scsi_set_iothread(VirtIOSCSI *s, IOThread *iothread)
s->ctx = iothread_get_aio_context(vs->conf.iothread);
/* Don't try if transport does not support notifiers. */
if (!k->set_guest_notifiers || !k->set_host_notifier) {
if (!k->set_guest_notifiers || !k->ioeventfd_started) {
fprintf(stderr, "virtio-scsi: Failed to set iothread "
"(transport does not support notifiers)");
exit(1);
@ -69,11 +69,10 @@ static int virtio_scsi_vring_init(VirtIOSCSI *s, VirtQueue *vq, int n,
void (*fn)(VirtIODevice *vdev, VirtQueue *vq))
{
BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(s)));
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(qbus);
int rc;
/* Set up virtqueue notify */
rc = k->set_host_notifier(qbus->parent, n, true);
rc = virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), n, true);
if (rc != 0) {
fprintf(stderr, "virtio-scsi: Failed to set host notifier (%d)\n",
rc);
@ -159,7 +158,7 @@ fail_vrings:
virtio_scsi_clear_aio(s);
aio_context_release(s->ctx);
for (i = 0; i < vs->conf.num_queues + 2; i++) {
k->set_host_notifier(qbus->parent, i, false);
virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);
}
k->set_guest_notifiers(qbus->parent, vs->conf.num_queues + 2, false);
fail_guest_notifiers:
@ -198,7 +197,7 @@ void virtio_scsi_dataplane_stop(VirtIOSCSI *s)
aio_context_release(s->ctx);
for (i = 0; i < vs->conf.num_queues + 2; i++) {
k->set_host_notifier(qbus->parent, i, false);
virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), i, false);
}
/* Clean up guest notifier (irq) */

1
hw/smbios/Makefile.objs
View File

@ -1 +1,2 @@
common-obj-$(CONFIG_SMBIOS) += smbios.o
common-obj-$(call land,$(CONFIG_SMBIOS),$(CONFIG_IPMI)) += smbios_type_38.o

72
hw/smbios/smbios.c
View File

@ -24,6 +24,8 @@
#include "hw/smbios/smbios.h"
#include "hw/loader.h"
#include "exec/cpu-common.h"
#include "smbios_build.h"
#include "hw/smbios/ipmi.h"
/* legacy structures and constants for <= 2.0 machines */
struct smbios_header {
@ -53,10 +55,10 @@ static bool smbios_uuid_encoded = true;
/* end: legacy structures & constants for <= 2.0 machines */
static uint8_t *smbios_tables;
static size_t smbios_tables_len;
static unsigned smbios_table_max;
static unsigned smbios_table_cnt;
uint8_t *smbios_tables;
size_t smbios_tables_len;
unsigned smbios_table_max;
unsigned smbios_table_cnt;
static SmbiosEntryPointType smbios_ep_type = SMBIOS_ENTRY_POINT_21;
static SmbiosEntryPoint ep;
@ -429,7 +431,7 @@ uint8_t *smbios_get_table_legacy(size_t *length)
/* end: legacy setup functions for <= 2.0 machines */
static bool smbios_skip_table(uint8_t type, bool required_table)
bool smbios_skip_table(uint8_t type, bool required_table)
{
if (test_bit(type, have_binfile_bitmap)) {
return true; /* user provided their own binary blob(s) */
@ -443,65 +445,6 @@ static bool smbios_skip_table(uint8_t type, bool required_table)
return true;
}
#define SMBIOS_BUILD_TABLE_PRE(tbl_type, tbl_handle, tbl_required) \
struct smbios_type_##tbl_type *t; \
size_t t_off; /* table offset into smbios_tables */ \
int str_index = 0; \
do { \
/* should we skip building this table ? */ \
if (smbios_skip_table(tbl_type, tbl_required)) { \
return; \
} \
\
/* use offset of table t within smbios_tables */ \
/* (pointer must be updated after each realloc) */ \
t_off = smbios_tables_len; \
smbios_tables_len += sizeof(*t); \
smbios_tables = g_realloc(smbios_tables, smbios_tables_len); \
t = (struct smbios_type_##tbl_type *)(smbios_tables + t_off); \
\
t->header.type = tbl_type; \
t->header.length = sizeof(*t); \
t->header.handle = cpu_to_le16(tbl_handle); \
} while (0)
#define SMBIOS_TABLE_SET_STR(tbl_type, field, value) \
do { \
int len = (value != NULL) ? strlen(value) + 1 : 0; \
if (len > 1) { \
smbios_tables = g_realloc(smbios_tables, \
smbios_tables_len + len); \
memcpy(smbios_tables + smbios_tables_len, value, len); \
smbios_tables_len += len; \
/* update pointer post-realloc */ \
t = (struct smbios_type_##tbl_type *)(smbios_tables + t_off); \
t->field = ++str_index; \
} else { \
t->field = 0; \
} \
} while (0)
#define SMBIOS_BUILD_TABLE_POST \
do { \
size_t term_cnt, t_size; \
\
/* add '\0' terminator (add two if no strings defined) */ \
term_cnt = (str_index == 0) ? 2 : 1; \
smbios_tables = g_realloc(smbios_tables, \
smbios_tables_len + term_cnt); \
memset(smbios_tables + smbios_tables_len, 0, term_cnt); \
smbios_tables_len += term_cnt; \
\
/* update smbios max. element size */ \
t_size = smbios_tables_len - t_off; \
if (t_size > smbios_table_max) { \
smbios_table_max = t_size; \
} \
\
/* update smbios element count */ \
smbios_table_cnt++; \
} while (0)
static void smbios_build_type_0_table(void)
{
SMBIOS_BUILD_TABLE_PRE(0, 0x000, false); /* optional, leave up to BIOS */
@ -906,6 +849,7 @@ void smbios_get_tables(const struct smbios_phys_mem_area *mem_array,
}
smbios_build_type_32_table();
smbios_build_type_38_table();
smbios_build_type_127_table();
smbios_validate_table();

87
hw/smbios/smbios_build.h Normal file
View File

@ -0,0 +1,87 @@
/*
* SMBIOS Support
*
* Copyright (C) 2009 Hewlett-Packard Development Company, L.P.
* Copyright (C) 2013 Red Hat, Inc.
*
* Authors:
* Alex Williamson <alex.williamson@hp.com>
* Markus Armbruster <armbru@redhat.com>
*
* This work is licensed under the terms of the GNU GPL, version 2. See
* the COPYING file in the top-level directory.
*
* Contributions after 2012-01-13 are licensed under the terms of the
* GNU GPL, version 2 or (at your option) any later version.
*/
#ifndef QEMU_SMBIOS_BUILD_H
#define QEMU_SMBIOS_BUILD_H
bool smbios_skip_table(uint8_t type, bool required_table);
extern uint8_t *smbios_tables;
extern size_t smbios_tables_len;
extern unsigned smbios_table_max;
extern unsigned smbios_table_cnt;
#define SMBIOS_BUILD_TABLE_PRE(tbl_type, tbl_handle, tbl_required) \
struct smbios_type_##tbl_type *t; \
size_t t_off; /* table offset into smbios_tables */ \
int str_index = 0; \
do { \
/* should we skip building this table ? */ \
if (smbios_skip_table(tbl_type, tbl_required)) { \
return; \
} \
\
/* use offset of table t within smbios_tables */ \
/* (pointer must be updated after each realloc) */ \
t_off = smbios_tables_len; \
smbios_tables_len += sizeof(*t); \
smbios_tables = g_realloc(smbios_tables, smbios_tables_len); \
t = (struct smbios_type_##tbl_type *)(smbios_tables + t_off); \
\
t->header.type = tbl_type; \
t->header.length = sizeof(*t); \
t->header.handle = cpu_to_le16(tbl_handle); \
} while (0)
#define SMBIOS_TABLE_SET_STR(tbl_type, field, value) \
do { \
int len = (value != NULL) ? strlen(value) + 1 : 0; \
if (len > 1) { \
smbios_tables = g_realloc(smbios_tables, \
smbios_tables_len + len); \
memcpy(smbios_tables + smbios_tables_len, value, len); \
smbios_tables_len += len; \
/* update pointer post-realloc */ \
t = (struct smbios_type_##tbl_type *)(smbios_tables + t_off); \
t->field = ++str_index; \
} else { \
t->field = 0; \
} \
} while (0)
#define SMBIOS_BUILD_TABLE_POST \
do { \
size_t term_cnt, t_size; \
\
/* add '\0' terminator (add two if no strings defined) */ \
term_cnt = (str_index == 0) ? 2 : 1; \
smbios_tables = g_realloc(smbios_tables, \
smbios_tables_len + term_cnt); \
memset(smbios_tables + smbios_tables_len, 0, term_cnt); \
smbios_tables_len += term_cnt; \
\
/* update smbios max. element size */ \
t_size = smbios_tables_len - t_off; \
if (t_size > smbios_table_max) { \
smbios_table_max = t_size; \
} \
\
/* update smbios element count */ \
smbios_table_cnt++; \
} while (0)
#endif /* QEMU_SMBIOS_BUILD_H */

117
hw/smbios/smbios_type_38.c Normal file
View File

@ -0,0 +1,117 @@
/*
* 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.
*/
#include "qemu/osdep.h"
#include "hw/ipmi/ipmi.h"
#include "hw/smbios/ipmi.h"
#include "hw/smbios/smbios.h"
#include "qemu/error-report.h"
#include "smbios_build.h"
/* SMBIOS type 38 - IPMI */
struct smbios_type_38 {
struct smbios_structure_header header;
uint8_t interface_type;
uint8_t ipmi_spec_revision;
uint8_t i2c_slave_address;
uint8_t nv_storage_device_address;
uint64_t base_address;
uint8_t base_address_modifier;
uint8_t interrupt_number;
} QEMU_PACKED;
static void smbios_build_one_type_38(IPMIFwInfo *info)
{
uint64_t baseaddr = info->base_address;
SMBIOS_BUILD_TABLE_PRE(38, 0x3000, true);
t->interface_type = info->interface_type;
t->ipmi_spec_revision = ((info->ipmi_spec_major_revision << 4)
| info->ipmi_spec_minor_revision);
t->i2c_slave_address = info->i2c_slave_address;
t->nv_storage_device_address = 0;
assert(info->ipmi_spec_minor_revision <= 15);
assert(info->ipmi_spec_major_revision <= 15);
/* or 1 to set it to I/O space */
switch (info->memspace) {
case IPMI_MEMSPACE_IO:
baseaddr |= 1;
break;
case IPMI_MEMSPACE_MEM32:
case IPMI_MEMSPACE_MEM64:
break;
case IPMI_MEMSPACE_SMBUS:
baseaddr <<= 1;
break;
}
t->base_address = cpu_to_le64(baseaddr);
t->base_address_modifier = 0;
if (info->irq_type == IPMI_LEVEL_IRQ) {
t->base_address_modifier |= 1;
}
switch (info->register_spacing) {
case 1:
break;
case 4:
t->base_address_modifier |= 1 << 6;
break;
case 16:
t->base_address_modifier |= 2 << 6;
break;
default:
error_report("IPMI register spacing %d is not compatible with"
" SMBIOS, ignoring this entry.", info->register_spacing);
return;
}
t->interrupt_number = info->interrupt_number;
SMBIOS_BUILD_TABLE_POST;
}
static void smbios_add_ipmi_devices(BusState *bus)
{
BusChild *kid;
QTAILQ_FOREACH(kid, &bus->children, sibling) {
DeviceState *dev = kid->child;
Object *obj = object_dynamic_cast(OBJECT(dev), TYPE_IPMI_INTERFACE);
BusState *childbus;
if (obj) {
IPMIInterface *ii;
IPMIInterfaceClass *iic;
IPMIFwInfo info;
ii = IPMI_INTERFACE(obj);
iic = IPMI_INTERFACE_GET_CLASS(obj);
memset(&info, 0, sizeof(info));
iic->get_fwinfo(ii, &info);
smbios_build_one_type_38(&info);
continue;
}
QLIST_FOREACH(childbus, &dev->child_bus, sibling) {
smbios_add_ipmi_devices(childbus);
}
}
}
void smbios_build_type_38_table(void)
{
BusState *bus;
bus = sysbus_get_default();
if (bus) {
smbios_add_ipmi_devices(bus);
}
}

13
hw/virtio/vhost.c
View File

@ -1110,14 +1110,15 @@ int vhost_dev_enable_notifiers(struct vhost_dev *hdev, VirtIODevice *vdev)
VirtioBusState *vbus = VIRTIO_BUS(qbus);
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus);
int i, r, e;
if (!k->set_host_notifier) {
if (!k->ioeventfd_started) {
fprintf(stderr, "binding does not support host notifiers\n");
r = -ENOSYS;
goto fail;
}
for (i = 0; i < hdev->nvqs; ++i) {
r = k->set_host_notifier(qbus->parent, hdev->vq_index + i, true);
r = virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), hdev->vq_index + i,
true);
if (r < 0) {
fprintf(stderr, "vhost VQ %d notifier binding failed: %d\n", i, -r);
goto fail_vq;
@ -1127,7 +1128,8 @@ int vhost_dev_enable_notifiers(struct vhost_dev *hdev, VirtIODevice *vdev)
return 0;
fail_vq:
while (--i >= 0) {
e = k->set_host_notifier(qbus->parent, hdev->vq_index + i, false);
e = virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), hdev->vq_index + i,
false);
if (e < 0) {
fprintf(stderr, "vhost VQ %d notifier cleanup error: %d\n", i, -r);
fflush(stderr);
@ -1146,12 +1148,11 @@ fail:
void vhost_dev_disable_notifiers(struct vhost_dev *hdev, VirtIODevice *vdev)
{
BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev)));
VirtioBusState *vbus = VIRTIO_BUS(qbus);
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(vbus);
int i, r;
for (i = 0; i < hdev->nvqs; ++i) {
r = k->set_host_notifier(qbus->parent, hdev->vq_index + i, false);
r = virtio_bus_set_host_notifier(VIRTIO_BUS(qbus), hdev->vq_index + i,
false);
if (r < 0) {
fprintf(stderr, "vhost VQ %d notifier cleanup failed: %d\n", i, -r);
fflush(stderr);

132
hw/virtio/virtio-bus.c
View File

@ -146,6 +146,138 @@ void virtio_bus_set_vdev_config(VirtioBusState *bus, uint8_t *config)
}
}
/*
* This function handles both assigning the ioeventfd handler and
* registering it with the kernel.
* assign: register/deregister ioeventfd with the kernel
* set_handler: use the generic ioeventfd handler
*/
static int set_host_notifier_internal(DeviceState *proxy, VirtioBusState *bus,
int n, bool assign, bool set_handler)
{
VirtIODevice *vdev = virtio_bus_get_device(bus);
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
VirtQueue *vq = virtio_get_queue(vdev, n);
EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
int r = 0;
if (assign) {
r = event_notifier_init(notifier, 1);
if (r < 0) {
error_report("%s: unable to init event notifier: %d", __func__, r);
return r;
}
virtio_queue_set_host_notifier_fd_handler(vq, true, set_handler);
r = k->ioeventfd_assign(proxy, notifier, n, assign);
if (r < 0) {
error_report("%s: unable to assign ioeventfd: %d", __func__, r);
virtio_queue_set_host_notifier_fd_handler(vq, false, false);
event_notifier_cleanup(notifier);
return r;
}
} else {
virtio_queue_set_host_notifier_fd_handler(vq, false, false);
k->ioeventfd_assign(proxy, notifier, n, assign);
event_notifier_cleanup(notifier);
}
return r;
}
void virtio_bus_start_ioeventfd(VirtioBusState *bus)
{
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
DeviceState *proxy = DEVICE(BUS(bus)->parent);
VirtIODevice *vdev;
int n, r;
if (!k->ioeventfd_started || k->ioeventfd_started(proxy)) {
return;
}
if (k->ioeventfd_disabled(proxy)) {
return;
}
vdev = virtio_bus_get_device(bus);
for (n = 0; n < VIRTIO_QUEUE_MAX; n++) {
if (!virtio_queue_get_num(vdev, n)) {
continue;
}
r = set_host_notifier_internal(proxy, bus, n, true, true);
if (r < 0) {
goto assign_error;
}
}
k->ioeventfd_set_started(proxy, true, false);
return;
assign_error:
while (--n >= 0) {
if (!virtio_queue_get_num(vdev, n)) {
continue;
}
r = set_host_notifier_internal(proxy, bus, n, false, false);
assert(r >= 0);
}
k->ioeventfd_set_started(proxy, false, true);
error_report("%s: failed. Fallback to userspace (slower).", __func__);
}
void virtio_bus_stop_ioeventfd(VirtioBusState *bus)
{
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
DeviceState *proxy = DEVICE(BUS(bus)->parent);
VirtIODevice *vdev;
int n, r;
if (!k->ioeventfd_started || !k->ioeventfd_started(proxy)) {
return;
}
vdev = virtio_bus_get_device(bus);
for (n = 0; n < VIRTIO_QUEUE_MAX; n++) {
if (!virtio_queue_get_num(vdev, n)) {
continue;
}
r = set_host_notifier_internal(proxy, bus, n, false, false);
assert(r >= 0);
}
k->ioeventfd_set_started(proxy, false, false);
}
/*
* This function switches from/to the generic ioeventfd handler.
* assign==false means 'use generic ioeventfd handler'.
*/
int virtio_bus_set_host_notifier(VirtioBusState *bus, int n, bool assign)
{
VirtioBusClass *k = VIRTIO_BUS_GET_CLASS(bus);
DeviceState *proxy = DEVICE(BUS(bus)->parent);
VirtIODevice *vdev = virtio_bus_get_device(bus);
VirtQueue *vq = virtio_get_queue(vdev, n);
if (!k->ioeventfd_started) {
return -ENOSYS;
}
if (assign) {
/*
* Stop using the generic ioeventfd, we are doing eventfd handling
* ourselves below
*/
k->ioeventfd_set_disabled(proxy, true);
}
/*
* Just switch the handler, don't deassign the ioeventfd.
* Otherwise, there's a window where we don't have an
* ioeventfd and we may end up with a notification where
* we don't expect one.
*/
virtio_queue_set_host_notifier_fd_handler(vq, assign, !assign);
if (!assign) {
/* Use generic ioeventfd handler again. */
k->ioeventfd_set_disabled(proxy, false);
}
return 0;
}
static char *virtio_bus_get_dev_path(DeviceState *dev)
{
BusState *bus = qdev_get_parent_bus(dev);

128
hw/virtio/virtio-mmio.c
View File

@ -93,90 +93,59 @@ typedef struct {
bool ioeventfd_started;
} VirtIOMMIOProxy;
static int virtio_mmio_set_host_notifier_internal(VirtIOMMIOProxy *proxy,
int n, bool assign,
bool set_handler)
static bool virtio_mmio_ioeventfd_started(DeviceState *d)
{
VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
VirtQueue *vq = virtio_get_queue(vdev, n);
EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
int r = 0;
VirtIOMMIOProxy *proxy = VIRTIO_MMIO(d);
return proxy->ioeventfd_started;
}
static void virtio_mmio_ioeventfd_set_started(DeviceState *d, bool started,
bool err)
{
VirtIOMMIOProxy *proxy = VIRTIO_MMIO(d);
proxy->ioeventfd_started = started;
}
static bool virtio_mmio_ioeventfd_disabled(DeviceState *d)
{
VirtIOMMIOProxy *proxy = VIRTIO_MMIO(d);
return !kvm_eventfds_enabled() || proxy->ioeventfd_disabled;
}
static void virtio_mmio_ioeventfd_set_disabled(DeviceState *d, bool disabled)
{
VirtIOMMIOProxy *proxy = VIRTIO_MMIO(d);
proxy->ioeventfd_disabled = disabled;
}
static int virtio_mmio_ioeventfd_assign(DeviceState *d,
EventNotifier *notifier,
int n, bool assign)
{
VirtIOMMIOProxy *proxy = VIRTIO_MMIO(d);
if (assign) {
r = event_notifier_init(notifier, 1);
if (r < 0) {
error_report("%s: unable to init event notifier: %d",
__func__, r);
return r;
}
virtio_queue_set_host_notifier_fd_handler(vq, true, set_handler);
memory_region_add_eventfd(&proxy->iomem, VIRTIO_MMIO_QUEUENOTIFY, 4,
true, n, notifier);
} else {
memory_region_del_eventfd(&proxy->iomem, VIRTIO_MMIO_QUEUENOTIFY, 4,
true, n, notifier);
virtio_queue_set_host_notifier_fd_handler(vq, false, false);
event_notifier_cleanup(notifier);
}
return r;
return 0;
}
static void virtio_mmio_start_ioeventfd(VirtIOMMIOProxy *proxy)
{
VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
int n, r;
if (!kvm_eventfds_enabled() ||
proxy->ioeventfd_disabled ||
proxy->ioeventfd_started) {
return;
}
for (n = 0; n < VIRTIO_QUEUE_MAX; n++) {
if (!virtio_queue_get_num(vdev, n)) {
continue;
}
r = virtio_mmio_set_host_notifier_internal(proxy, n, true, true);
if (r < 0) {
goto assign_error;
}
}
proxy->ioeventfd_started = true;
return;
assign_error:
while (--n >= 0) {
if (!virtio_queue_get_num(vdev, n)) {
continue;
}
r = virtio_mmio_set_host_notifier_internal(proxy, n, false, false);
assert(r >= 0);
}
proxy->ioeventfd_started = false;
error_report("%s: failed. Fallback to a userspace (slower).", __func__);
virtio_bus_start_ioeventfd(&proxy->bus);
}
static void virtio_mmio_stop_ioeventfd(VirtIOMMIOProxy *proxy)
{
int r;
int n;
VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
if (!proxy->ioeventfd_started) {
return;
}
for (n = 0; n < VIRTIO_QUEUE_MAX; n++) {
if (!virtio_queue_get_num(vdev, n)) {
continue;
}
r = virtio_mmio_set_host_notifier_internal(proxy, n, false, false);
assert(r >= 0);
}
proxy->ioeventfd_started = false;
virtio_bus_stop_ioeventfd(&proxy->bus);
}
static uint64_t virtio_mmio_read(void *opaque, hwaddr offset, unsigned size)
@ -498,25 +467,6 @@ assign_error:
return r;
}
static int virtio_mmio_set_host_notifier(DeviceState *opaque, int n,
bool assign)
{
VirtIOMMIOProxy *proxy = VIRTIO_MMIO(opaque);
/* Stop using ioeventfd for virtqueue kick if the device starts using host
* notifiers. This makes it easy to avoid stepping on each others' toes.
*/
proxy->ioeventfd_disabled = assign;
if (assign) {
virtio_mmio_stop_ioeventfd(proxy);
}
/* We don't need to start here: it's not needed because backend
* currently only stops on status change away from ok,
* reset, vmstop and such. If we do add code to start here,
* need to check vmstate, device state etc. */
return virtio_mmio_set_host_notifier_internal(proxy, n, assign, false);
}
/* virtio-mmio device */
static void virtio_mmio_realizefn(DeviceState *d, Error **errp)
@ -558,8 +508,12 @@ static void virtio_mmio_bus_class_init(ObjectClass *klass, void *data)
k->notify = virtio_mmio_update_irq;
k->save_config = virtio_mmio_save_config;
k->load_config = virtio_mmio_load_config;
k->set_host_notifier = virtio_mmio_set_host_notifier;
k->set_guest_notifiers = virtio_mmio_set_guest_notifiers;
k->ioeventfd_started = virtio_mmio_ioeventfd_started;
k->ioeventfd_set_started = virtio_mmio_ioeventfd_set_started;
k->ioeventfd_disabled = virtio_mmio_ioeventfd_disabled;
k->ioeventfd_set_disabled = virtio_mmio_ioeventfd_set_disabled;
k->ioeventfd_assign = virtio_mmio_ioeventfd_assign;
k->has_variable_vring_alignment = true;
bus_class->max_dev = 1;
}

124
hw/virtio/virtio-pci.c
View File

@ -262,14 +262,44 @@ static int virtio_pci_load_queue(DeviceState *d, int n, QEMUFile *f)
return 0;
}
static bool virtio_pci_ioeventfd_started(DeviceState *d)
{
VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
return proxy->ioeventfd_started;
}
static void virtio_pci_ioeventfd_set_started(DeviceState *d, bool started,
bool err)
{
VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
proxy->ioeventfd_started = started;
}
static bool virtio_pci_ioeventfd_disabled(DeviceState *d)
{
VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
return proxy->ioeventfd_disabled ||
!(proxy->flags & VIRTIO_PCI_FLAG_USE_IOEVENTFD);
}
static void virtio_pci_ioeventfd_set_disabled(DeviceState *d, bool disabled)
{
VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
proxy->ioeventfd_disabled = disabled;
}
#define QEMU_VIRTIO_PCI_QUEUE_MEM_MULT 0x1000
static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy,
int n, bool assign, bool set_handler)
static int virtio_pci_ioeventfd_assign(DeviceState *d, EventNotifier *notifier,
int n, bool assign)
{
VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
VirtQueue *vq = virtio_get_queue(vdev, n);
EventNotifier *notifier = virtio_queue_get_host_notifier(vq);
bool legacy = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_LEGACY);
bool modern = !(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_MODERN);
bool fast_mmio = kvm_ioeventfd_any_length_enabled();
@ -280,16 +310,8 @@ static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy,
hwaddr modern_addr = QEMU_VIRTIO_PCI_QUEUE_MEM_MULT *
virtio_get_queue_index(vq);
hwaddr legacy_addr = VIRTIO_PCI_QUEUE_NOTIFY;
int r = 0;
if (assign) {
r = event_notifier_init(notifier, 1);
if (r < 0) {
error_report("%s: unable to init event notifier: %d",
__func__, r);
return r;
}
virtio_queue_set_host_notifier_fd_handler(vq, true, set_handler);
if (modern) {
if (fast_mmio) {
memory_region_add_eventfd(modern_mr, modern_addr, 0,
@ -325,68 +347,18 @@ static int virtio_pci_set_host_notifier_internal(VirtIOPCIProxy *proxy,
memory_region_del_eventfd(legacy_mr, legacy_addr, 2,
true, n, notifier);
}
virtio_queue_set_host_notifier_fd_handler(vq, false, false);
event_notifier_cleanup(notifier);
}
return r;
return 0;
}
static void virtio_pci_start_ioeventfd(VirtIOPCIProxy *proxy)
{
VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
int n, r;
if (!(proxy->flags & VIRTIO_PCI_FLAG_USE_IOEVENTFD) ||
proxy->ioeventfd_disabled ||
proxy->ioeventfd_started) {
return;
}
for (n = 0; n < VIRTIO_QUEUE_MAX; n++) {
if (!virtio_queue_get_num(vdev, n)) {
continue;
}
r = virtio_pci_set_host_notifier_internal(proxy, n, true, true);
if (r < 0) {
goto assign_error;
}
}
proxy->ioeventfd_started = true;
return;
assign_error:
while (--n >= 0) {
if (!virtio_queue_get_num(vdev, n)) {
continue;
}
r = virtio_pci_set_host_notifier_internal(proxy, n, false, false);
assert(r >= 0);
}
proxy->ioeventfd_started = false;
error_report("%s: failed. Fallback to a userspace (slower).", __func__);
virtio_bus_start_ioeventfd(&proxy->bus);
}
static void virtio_pci_stop_ioeventfd(VirtIOPCIProxy *proxy)
{
VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus);
int r;
int n;
if (!proxy->ioeventfd_started) {
return;
}
for (n = 0; n < VIRTIO_QUEUE_MAX; n++) {
if (!virtio_queue_get_num(vdev, n)) {
continue;
}
r = virtio_pci_set_host_notifier_internal(proxy, n, false, false);
assert(r >= 0);
}
proxy->ioeventfd_started = false;
virtio_bus_stop_ioeventfd(&proxy->bus);
}
static void virtio_ioport_write(void *opaque, uint32_t addr, uint32_t val)
@ -1110,24 +1082,6 @@ assign_error:
return r;
}
static int virtio_pci_set_host_notifier(DeviceState *d, int n, bool assign)
{
VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
/* Stop using ioeventfd for virtqueue kick if the device starts using host
* notifiers. This makes it easy to avoid stepping on each others' toes.
*/
proxy->ioeventfd_disabled = assign;
if (assign) {
virtio_pci_stop_ioeventfd(proxy);
}
/* We don't need to start here: it's not needed because backend
* currently only stops on status change away from ok,
* reset, vmstop and such. If we do add code to start here,
* need to check vmstate, device state etc. */
return virtio_pci_set_host_notifier_internal(proxy, n, assign, false);
}
static void virtio_pci_vmstate_change(DeviceState *d, bool running)
{
VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d);
@ -2488,12 +2442,16 @@ static void virtio_pci_bus_class_init(ObjectClass *klass, void *data)
k->load_extra_state = virtio_pci_load_extra_state;
k->has_extra_state = virtio_pci_has_extra_state;
k->query_guest_notifiers = virtio_pci_query_guest_notifiers;
k->set_host_notifier = virtio_pci_set_host_notifier;
k->set_guest_notifiers = virtio_pci_set_guest_notifiers;
k->vmstate_change = virtio_pci_vmstate_change;
k->device_plugged = virtio_pci_device_plugged;
k->device_unplugged = virtio_pci_device_unplugged;
k->query_nvectors = virtio_pci_query_nvectors;
k->ioeventfd_started = virtio_pci_ioeventfd_started;
k->ioeventfd_set_started = virtio_pci_ioeventfd_set_started;
k->ioeventfd_disabled = virtio_pci_ioeventfd_disabled;
k->ioeventfd_set_disabled = virtio_pci_ioeventfd_set_disabled;
k->ioeventfd_assign = virtio_pci_ioeventfd_assign;
}
static const TypeInfo virtio_pci_bus_info = {

7
include/hw/acpi/acpi_dev_interface.h
View File

@ -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

3
include/hw/acpi/aml-build.h
View File

@ -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,

67
include/hw/acpi/cpu.h Normal file
View File

@ -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

6
include/hw/acpi/cpu_hotplug.h
View File

@ -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

3
include/hw/acpi/ich9.h
View File

@ -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;

22
include/hw/acpi/ipmi.h Normal file
View File

@ -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 */

8
include/hw/i386/pc.h
View File

@ -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

55
include/hw/mem/nvdimm.h
View File

@ -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"

5
include/hw/mem/pc-dimm.h
View File

@ -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;
/**

15
include/hw/smbios/ipmi.h Normal file
View File

@ -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 */

31
include/hw/virtio/virtio-bus.h
View File

@ -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.
@ -70,6 +69,29 @@ 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()?)
@ -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 */

3
qapi-schema.json
View File

@ -4079,8 +4079,9 @@
## @ACPISlotType
#
# @DIMM: memory slot
# @CPU: logical CPU slot (since 2.7)
#
{ 'enum': 'ACPISlotType', 'data': [ 'DIMM' ] }
{ 'enum': 'ACPISlotType', 'data': [ 'DIMM', 'CPU' ] }
## @ACPIOSTInfo
#

3
stubs/Makefile.objs
View File

@ -41,3 +41,6 @@ stub-obj-y += target-monitor-defs.o
stub-obj-y += target-get-monitor-def.o
stub-obj-y += vhost.o
stub-obj-y += iohandler.o
stub-obj-y += smbios_type_38.o
stub-obj-y += ipmi.o
stub-obj-y += pc_madt_cpu_entry.o

14
stubs/ipmi.c Normal file
View File

@ -0,0 +1,14 @@
/*
* IPMI ACPI 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.
*/
#include "hw/acpi/ipmi.h"
void build_acpi_ipmi_devices(Aml *table, BusState *bus)
{
}

7
stubs/pc_madt_cpu_entry.c Normal file
View File

@ -0,0 +1,7 @@
#include "qemu/osdep.h"
#include "hw/i386/pc.h"
void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid,
CPUArchIdList *apic_ids, GArray *entry)
{
}

14
stubs/smbios_type_38.c Normal file
View File

@ -0,0 +1,14 @@
/*
* 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.
*/
#include "hw/smbios/ipmi.h"
void smbios_build_type_38_table(void)
{
}

BIN
tests/acpi-test-data/pc/DSDT
View File

Binary file not shown.

BIN
tests/acpi-test-data/pc/DSDT.bridge
View File

Binary file not shown.

BIN
tests/acpi-test-data/pc/DSDT.ipmikcs Normal file
View File

Binary file not shown.

BIN
tests/acpi-test-data/q35/DSDT
View File

Binary file not shown.

BIN
tests/acpi-test-data/q35/DSDT.bridge
View File

Binary file not shown.

BIN
tests/acpi-test-data/q35/DSDT.ipmibt Normal file
View File

Binary file not shown.

60
tests/bios-tables-test.c
View File

@ -49,6 +49,8 @@ typedef struct {
GArray *tables;
uint32_t smbios_ep_addr;
struct smbios_21_entry_point smbios_ep_table;
uint8_t *required_struct_types;
int required_struct_types_len;
} test_data;
#define ACPI_READ_FIELD(field, addr) \
@ -334,7 +336,7 @@ static void test_acpi_tables(test_data *data)
for (i = 0; i < tables_nr; i++) {
AcpiSdtTable ssdt_table;
memset(&ssdt_table, 0 , sizeof(ssdt_table));
memset(&ssdt_table, 0, sizeof(ssdt_table));
uint32_t addr = data->rsdt_tables_addr[i + 1]; /* fadt is first */
test_dst_table(&ssdt_table, addr);
g_array_append_val(data->tables, ssdt_table);
@ -661,7 +663,6 @@ static void test_smbios_structs(test_data *data)
uint32_t addr = ep_table->structure_table_address;
int i, len, max_len = 0;
uint8_t type, prv, crt;
uint8_t required_struct_types[] = {0, 1, 3, 4, 16, 17, 19, 32, 127};
/* walk the smbios tables */
for (i = 0; i < ep_table->number_of_structures; i++) {
@ -701,8 +702,8 @@ static void test_smbios_structs(test_data *data)
g_assert_cmpuint(ep_table->max_structure_size, ==, max_len);
/* required struct types must all be present */
for (i = 0; i < ARRAY_SIZE(required_struct_types); i++) {
g_assert(test_bit(required_struct_types[i], struct_bitmap));
for (i = 0; i < data->required_struct_types_len; i++) {
g_assert(test_bit(data->required_struct_types[i], struct_bitmap));
}
}
@ -742,6 +743,10 @@ static void test_acpi_one(const char *params, test_data *data)
g_free(args);
}
static uint8_t base_required_struct_types[] = {
0, 1, 3, 4, 16, 17, 19, 32, 127
};
static void test_acpi_piix4_tcg(void)
{
test_data data;
@ -751,6 +756,8 @@ static void test_acpi_piix4_tcg(void)
*/
memset(&data, 0, sizeof(data));
data.machine = MACHINE_PC;
data.required_struct_types = base_required_struct_types;
data.required_struct_types_len = ARRAY_SIZE(base_required_struct_types);
test_acpi_one("-machine accel=tcg", &data);
free_test_data(&data);
}
@ -762,6 +769,8 @@ static void test_acpi_piix4_tcg_bridge(void)
memset(&data, 0, sizeof(data));
data.machine = MACHINE_PC;
data.variant = ".bridge";
data.required_struct_types = base_required_struct_types;
data.required_struct_types_len = ARRAY_SIZE(base_required_struct_types);
test_acpi_one("-machine accel=tcg -device pci-bridge,chassis_nr=1", &data);
free_test_data(&data);
}
@ -772,6 +781,8 @@ static void test_acpi_q35_tcg(void)
memset(&data, 0, sizeof(data));
data.machine = MACHINE_Q35;
data.required_struct_types = base_required_struct_types;
data.required_struct_types_len = ARRAY_SIZE(base_required_struct_types);
test_acpi_one("-machine q35,accel=tcg", &data);
free_test_data(&data);
}
@ -783,11 +794,50 @@ static void test_acpi_q35_tcg_bridge(void)
memset(&data, 0, sizeof(data));
data.machine = MACHINE_Q35;
data.variant = ".bridge";
data.required_struct_types = base_required_struct_types;
data.required_struct_types_len = ARRAY_SIZE(base_required_struct_types);
test_acpi_one("-machine q35,accel=tcg -device pci-bridge,chassis_nr=1",
&data);
free_test_data(&data);
}
static uint8_t ipmi_required_struct_types[] = {
0, 1, 3, 4, 16, 17, 19, 32, 38, 127
};
static void test_acpi_q35_tcg_ipmi(void)
{
test_data data;
memset(&data, 0, sizeof(data));
data.machine = MACHINE_Q35;
data.variant = ".ipmibt";
data.required_struct_types = ipmi_required_struct_types;
data.required_struct_types_len = ARRAY_SIZE(ipmi_required_struct_types);
test_acpi_one("-machine q35,accel=tcg -device ipmi-bmc-sim,id=bmc0"
" -device isa-ipmi-bt,bmc=bmc0",
&data);
free_test_data(&data);
}
static void test_acpi_piix4_tcg_ipmi(void)
{
test_data data;
/* Supplying -machine accel argument overrides the default (qtest).
* This is to make guest actually run.
*/
memset(&data, 0, sizeof(data));
data.machine = MACHINE_PC;
data.variant = ".ipmikcs";
data.required_struct_types = ipmi_required_struct_types;
data.required_struct_types_len = ARRAY_SIZE(ipmi_required_struct_types);
test_acpi_one("-machine accel=tcg -device ipmi-bmc-sim,id=bmc0"
" -device isa-ipmi-kcs,irq=0,bmc=bmc0",
&data);
free_test_data(&data);
}
int main(int argc, char *argv[])
{
const char *arch = qtest_get_arch();
@ -804,6 +854,8 @@ int main(int argc, char *argv[])
qtest_add_func("acpi/piix4/tcg/bridge", test_acpi_piix4_tcg_bridge);
qtest_add_func("acpi/q35/tcg", test_acpi_q35_tcg);
qtest_add_func("acpi/q35/tcg/bridge", test_acpi_q35_tcg_bridge);
qtest_add_func("acpi/piix4/tcg/ipmi", test_acpi_piix4_tcg_ipmi);
qtest_add_func("acpi/q35/tcg/ipmi", test_acpi_q35_tcg_ipmi);
}
ret = g_test_run();
boot_sector_cleanup(disk);