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>

5 files changed, 117 insertions, 44 deletions

diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c
index 8ca203211a..5a594be8ee 100644
--- a/hw/i386/acpi-build.c
+++ b/hw/i386/acpi-build.c
@@ -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);
diff --git a/hw/i386/kvm/pci-assign.c b/hw/i386/kvm/pci-assign.c
index f9c901471d..98997d167c 100644
--- a/hw/i386/kvm/pci-assign.c
+++ b/hw/i386/kvm/pci-assign.c
@@ -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;
diff --git a/hw/i386/pc.c b/hw/i386/pc.c
index 7198ed533c..b8fead37e2 100644
--- a/hw/i386/pc.c
+++ b/hw/i386/pc.c
@@ -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)));
diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c
index 53bc968bd0..c7d70af253 100644
--- a/hw/i386/pc_piix.c
+++ b/hw/i386/pc_piix.c
@@ -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);
 }
 
diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c
index e4b541f7b2..97a8835eea 100644
--- a/hw/i386/pc_q35.c
+++ b/hw/i386/pc_q35.c
@@ -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);
 }