diff options
44 files changed, 515 insertions, 190 deletions
diff --git a/default-configs/i386-softmmu.mak b/default-configs/i386-softmmu.mak index ba3fb3ff50..cd5ea391e8 100644 --- a/default-configs/i386-softmmu.mak +++ b/default-configs/i386-softmmu.mak @@ -25,3 +25,4 @@ CONFIG_ISAPC=y CONFIG_I440FX=y CONFIG_Q35=y +CONFIG_ACPI_PCI=y diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig index eca3beed75..7c59cf900b 100644 --- a/hw/acpi/Kconfig +++ b/hw/acpi/Kconfig @@ -23,6 +23,10 @@ config ACPI_NVDIMM bool depends on ACPI +config ACPI_PCI + bool + depends on ACPI && PCI + config ACPI_VMGENID bool default y diff --git a/hw/acpi/Makefile.objs b/hw/acpi/Makefile.objs index 2d46e3789a..661a9b8c2f 100644 --- a/hw/acpi/Makefile.objs +++ b/hw/acpi/Makefile.objs @@ -11,6 +11,7 @@ common-obj-$(call lnot,$(CONFIG_ACPI_X86)) += acpi-stub.o common-obj-y += acpi_interface.o common-obj-y += bios-linker-loader.o common-obj-y += aml-build.o +common-obj-$(CONFIG_ACPI_PCI) += pci.o common-obj-$(CONFIG_TPM) += tpm.o common-obj-$(CONFIG_IPMI) += ipmi.o diff --git a/hw/acpi/pci.c b/hw/acpi/pci.c new file mode 100644 index 0000000000..9510597a19 --- /dev/null +++ b/hw/acpi/pci.c @@ -0,0 +1,61 @@ +/* + * Support for generating PCI related ACPI tables and passing them to Guests + * + * Copyright (C) 2006 Fabrice Bellard + * Copyright (C) 2008-2010 Kevin O'Connor <kevin@koconnor.net> + * Copyright (C) 2013-2019 Red Hat Inc + * Copyright (C) 2019 Intel Corporation + * + * Author: Wei Yang <richardw.yang@linux.intel.com> + * Author: Michael S. Tsirkin <mst@redhat.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "hw/acpi/aml-build.h" +#include "hw/acpi/pci.h" +#include "hw/pci/pcie_host.h" + +void build_mcfg(GArray *table_data, BIOSLinker *linker, AcpiMcfgInfo *info) +{ + int mcfg_start = table_data->len; + + /* + * PCI Firmware Specification, Revision 3.0 + * 4.1.2 MCFG Table Description. + */ + acpi_data_push(table_data, sizeof(AcpiTableHeader)); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 8); + + /* + * Memory Mapped Enhanced Configuration Space Base Address Allocation + * Structure + */ + /* Base address, processor-relative */ + build_append_int_noprefix(table_data, info->base, 8); + /* PCI segment group number */ + build_append_int_noprefix(table_data, 0, 2); + /* Starting PCI Bus number */ + build_append_int_noprefix(table_data, 0, 1); + /* Final PCI Bus number */ + build_append_int_noprefix(table_data, PCIE_MMCFG_BUS(info->size - 1), 1); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 4); + + build_header(linker, table_data, (void *)(table_data->data + mcfg_start), + "MCFG", table_data->len - mcfg_start, 1, NULL, NULL); +} + diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index af8cffde9c..9aced9d54d 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -19,6 +19,7 @@ config ARM_VIRT select PLATFORM_BUS select SMBIOS select VIRTIO_MMIO + select ACPI_PCI config CHEETAH bool diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index e7c96d658e..4a64f9985c 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -546,23 +546,6 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) "SRAT", table_data->len - srat_start, 3, NULL, NULL); } -static void -build_mcfg(GArray *table_data, BIOSLinker *linker, AcpiMcfgInfo *info) -{ - AcpiTableMcfg *mcfg; - int len = sizeof(*mcfg) + sizeof(mcfg->allocation[0]); - - mcfg = acpi_data_push(table_data, len); - mcfg->allocation[0].address = cpu_to_le64(info->base); - - /* Only a single allocation so no need to play with segments */ - mcfg->allocation[0].pci_segment = cpu_to_le16(0); - mcfg->allocation[0].start_bus_number = 0; - mcfg->allocation[0].end_bus_number = PCIE_MMCFG_BUS(info->size - 1); - - build_header(linker, table_data, (void *)mcfg, "MCFG", len, 1, NULL, NULL); -} - /* GTDT */ static void build_gtdt(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index 0d78d73894..85dc1640bc 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -2405,22 +2405,6 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) table_data->len - srat_start, 1, NULL, NULL); } -static void -build_mcfg_q35(GArray *table_data, BIOSLinker *linker, AcpiMcfgInfo *info) -{ - AcpiTableMcfg *mcfg; - int len = sizeof(*mcfg) + 1 * sizeof(mcfg->allocation[0]); - - mcfg = acpi_data_push(table_data, len); - mcfg->allocation[0].address = cpu_to_le64(info->base); - /* Only a single allocation so no need to play with segments */ - mcfg->allocation[0].pci_segment = cpu_to_le16(0); - mcfg->allocation[0].start_bus_number = 0; - mcfg->allocation[0].end_bus_number = PCIE_MMCFG_BUS(info->size - 1); - - build_header(linker, table_data, (void *)mcfg, "MCFG", len, 1, NULL, NULL); -} - /* * VT-d spec 8.1 DMA Remapping Reporting Structure * (version Oct. 2014 or later) @@ -2690,7 +2674,7 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) } if (acpi_get_mcfg(&mcfg)) { acpi_add_table(table_offsets, tables_blob); - build_mcfg_q35(tables_blob, tables->linker, &mcfg); + build_mcfg(tables_blob, tables->linker, &mcfg); } if (x86_iommu_get_default()) { IommuType IOMMUType = x86_iommu_get_type(); diff --git a/hw/pci-bridge/dec.c b/hw/pci-bridge/dec.c index 8484bfd434..ca40253730 100644 --- a/hw/pci-bridge/dec.c +++ b/hw/pci-bridge/dec.c @@ -68,7 +68,7 @@ static void dec_21154_pci_bridge_class_init(ObjectClass *klass, void *data) k->vendor_id = PCI_VENDOR_ID_DEC; k->device_id = PCI_DEVICE_ID_DEC_21154; k->config_write = pci_bridge_write_config; - k->is_bridge = 1; + k->is_bridge = true; dc->desc = "DEC 21154 PCI-PCI bridge"; dc->reset = pci_bridge_reset; dc->vmsd = &vmstate_pci_device; @@ -129,7 +129,7 @@ static void dec_21154_pci_host_class_init(ObjectClass *klass, void *data) k->device_id = PCI_DEVICE_ID_DEC_21154; k->revision = 0x02; k->class_id = PCI_CLASS_BRIDGE_PCI; - k->is_bridge = 1; + k->is_bridge = true; /* * PCI-facing part of the host bridge, not usable without the * host-facing part, which can't be device_add'ed, yet. diff --git a/hw/pci-bridge/i82801b11.c b/hw/pci-bridge/i82801b11.c index 10e590e5c6..6d8b0f54a7 100644 --- a/hw/pci-bridge/i82801b11.c +++ b/hw/pci-bridge/i82801b11.c @@ -90,7 +90,7 @@ static void i82801b11_bridge_class_init(ObjectClass *klass, void *data) PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); DeviceClass *dc = DEVICE_CLASS(klass); - k->is_bridge = 1; + k->is_bridge = true; k->vendor_id = PCI_VENDOR_ID_INTEL; k->device_id = PCI_DEVICE_ID_INTEL_82801BA_11; k->revision = ICH9_D2P_A2_REVISION; diff --git a/hw/pci-bridge/pci_bridge_dev.c b/hw/pci-bridge/pci_bridge_dev.c index ff6b8323da..c56ed1f52f 100644 --- a/hw/pci-bridge/pci_bridge_dev.c +++ b/hw/pci-bridge/pci_bridge_dev.c @@ -253,7 +253,7 @@ static void pci_bridge_dev_class_init(ObjectClass *klass, void *data) k->vendor_id = PCI_VENDOR_ID_REDHAT; k->device_id = PCI_DEVICE_ID_REDHAT_BRIDGE; k->class_id = PCI_CLASS_BRIDGE_PCI; - k->is_bridge = 1, + k->is_bridge = true; dc->desc = "Standard PCI Bridge"; dc->reset = qdev_pci_bridge_dev_reset; dc->props = pci_bridge_dev_properties; diff --git a/hw/pci-bridge/pcie_pci_bridge.c b/hw/pci-bridge/pcie_pci_bridge.c index d491b40d04..9a4fba413a 100644 --- a/hw/pci-bridge/pcie_pci_bridge.c +++ b/hw/pci-bridge/pcie_pci_bridge.c @@ -143,7 +143,7 @@ static void pcie_pci_bridge_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(klass); - k->is_bridge = 1; + k->is_bridge = true; k->vendor_id = PCI_VENDOR_ID_REDHAT; k->device_id = PCI_DEVICE_ID_REDHAT_PCIE_BRIDGE; k->realize = pcie_pci_bridge_realize; diff --git a/hw/pci-bridge/pcie_root_port.c b/hw/pci-bridge/pcie_root_port.c index e94d918b6d..be3f4d5e03 100644 --- a/hw/pci-bridge/pcie_root_port.c +++ b/hw/pci-bridge/pcie_root_port.c @@ -162,7 +162,7 @@ static void rp_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); - k->is_bridge = 1; + k->is_bridge = true; k->config_write = rp_write_config; k->realize = rp_realize; k->exit = rp_exit; diff --git a/hw/pci-bridge/simba.c b/hw/pci-bridge/simba.c index dea4c8c5e7..7cf0d6e047 100644 --- a/hw/pci-bridge/simba.c +++ b/hw/pci-bridge/simba.c @@ -76,7 +76,7 @@ static void simba_pci_bridge_class_init(ObjectClass *klass, void *data) k->device_id = PCI_DEVICE_ID_SUN_SIMBA; k->revision = 0x11; k->config_write = pci_bridge_write_config; - k->is_bridge = 1; + k->is_bridge = true; set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); dc->reset = pci_bridge_reset; dc->vmsd = &vmstate_pci_device; diff --git a/hw/pci-bridge/xio3130_downstream.c b/hw/pci-bridge/xio3130_downstream.c index 467bbabe4c..ab2a51e15d 100644 --- a/hw/pci-bridge/xio3130_downstream.c +++ b/hw/pci-bridge/xio3130_downstream.c @@ -152,7 +152,7 @@ static void xio3130_downstream_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); - k->is_bridge = 1; + k->is_bridge = true; k->config_write = xio3130_downstream_write_config; k->realize = xio3130_downstream_realize; k->exit = xio3130_downstream_exitfn; diff --git a/hw/pci-bridge/xio3130_upstream.c b/hw/pci-bridge/xio3130_upstream.c index b524908cf1..1d41a49ab0 100644 --- a/hw/pci-bridge/xio3130_upstream.c +++ b/hw/pci-bridge/xio3130_upstream.c @@ -126,7 +126,7 @@ static void xio3130_upstream_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); - k->is_bridge = 1; + k->is_bridge = true; k->config_write = xio3130_upstream_write_config; k->realize = xio3130_upstream_realize; k->exit = xio3130_upstream_exitfn; diff --git a/hw/pci/pci.c b/hw/pci/pci.c index b386777045..d3893bdfe1 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -120,6 +120,27 @@ static void pci_bus_realize(BusState *qbus, Error **errp) vmstate_register(NULL, -1, &vmstate_pcibus, bus); } +static void pcie_bus_realize(BusState *qbus, Error **errp) +{ + PCIBus *bus = PCI_BUS(qbus); + + pci_bus_realize(qbus, errp); + + /* + * A PCI-E bus can support extended config space if it's the root + * bus, or if the bus/bridge above it does as well + */ + if (pci_bus_is_root(bus)) { + bus->flags |= PCI_BUS_EXTENDED_CONFIG_SPACE; + } else { + PCIBus *parent_bus = pci_get_bus(bus->parent_dev); + + if (pci_bus_allows_extended_config_space(parent_bus)) { + bus->flags |= PCI_BUS_EXTENDED_CONFIG_SPACE; + } + } +} + static void pci_bus_unrealize(BusState *qbus, Error **errp) { PCIBus *bus = PCI_BUS(qbus); @@ -142,11 +163,6 @@ static uint16_t pcibus_numa_node(PCIBus *bus) return NUMA_NODE_UNASSIGNED; } -static bool pcibus_allows_extended_config_space(PCIBus *bus) -{ - return false; -} - static void pci_bus_class_init(ObjectClass *klass, void *data) { BusClass *k = BUS_CLASS(klass); @@ -161,7 +177,6 @@ static void pci_bus_class_init(ObjectClass *klass, void *data) pbc->bus_num = pcibus_num; pbc->numa_node = pcibus_numa_node; - pbc->allows_extended_config_space = pcibus_allows_extended_config_space; } static const TypeInfo pci_bus_info = { @@ -182,16 +197,11 @@ static const TypeInfo conventional_pci_interface_info = { .parent = TYPE_INTERFACE, }; -static bool pciebus_allows_extended_config_space(PCIBus *bus) -{ - return true; -} - static void pcie_bus_class_init(ObjectClass *klass, void *data) { - PCIBusClass *pbc = PCI_BUS_CLASS(klass); + BusClass *k = BUS_CLASS(klass); - pbc->allows_extended_config_space = pciebus_allows_extended_config_space; + k->realize = pcie_bus_realize; } static const TypeInfo pcie_bus_info = { @@ -410,11 +420,6 @@ bool pci_bus_is_express(PCIBus *bus) return object_dynamic_cast(OBJECT(bus), TYPE_PCIE_BUS); } -bool pci_bus_allows_extended_config_space(PCIBus *bus) -{ - return PCI_BUS_GET_CLASS(bus)->allows_extended_config_space(bus); -} - void pci_root_bus_new_inplace(PCIBus *bus, size_t bus_size, DeviceState *parent, const char *name, MemoryRegion *address_space_mem, @@ -718,37 +723,6 @@ static int pci_parse_devaddr(const char *addr, int *domp, int *busp, return 0; } -static PCIBus *pci_get_bus_devfn(int *devfnp, PCIBus *root, - const char *devaddr) -{ - int dom, bus; - unsigned slot; - - if (!root) { - fprintf(stderr, "No primary PCI bus\n"); - return NULL; - } - - assert(!root->parent_dev); - - if (!devaddr) { - *devfnp = -1; - return pci_find_bus_nr(root, 0); - } - - if (pci_parse_devaddr(devaddr, &dom, &bus, &slot, NULL) < 0) { - return NULL; - } - - if (dom != 0) { - fprintf(stderr, "No support for non-zero PCI domains\n"); - return NULL; - } - - *devfnp = PCI_DEVFN(slot, 0); - return pci_find_bus_nr(root, bus); -} - static void pci_init_cmask(PCIDevice *dev) { pci_set_word(dev->cmask + PCI_VENDOR_ID, 0xffff); @@ -1890,6 +1864,8 @@ PCIDevice *pci_nic_init_nofail(NICInfo *nd, PCIBus *rootbus, DeviceState *dev; int devfn; int i; + int dom, busnr; + unsigned slot; if (nd->model && !strcmp(nd->model, "virtio")) { g_free(nd->model); @@ -1923,7 +1899,32 @@ PCIDevice *pci_nic_init_nofail(NICInfo *nd, PCIBus *rootbus, exit(1); } - bus = pci_get_bus_devfn(&devfn, rootbus, devaddr); + if (!rootbus) { + error_report("No primary PCI bus"); + exit(1); + } + + assert(!rootbus->parent_dev); + + if (!devaddr) { + devfn = -1; + busnr = 0; + } else { + if (pci_parse_devaddr(devaddr, &dom, &busnr, &slot, NULL) < 0) { + error_report("Invalid PCI device address %s for device %s", + devaddr, nd->model); + exit(1); + } + + if (dom != 0) { + error_report("No support for non-zero PCI domains"); + exit(1); + } + + devfn = PCI_DEVFN(slot, 0); + } + + bus = pci_find_bus_nr(rootbus, busnr); if (!bus) { error_report("Invalid PCI device address %s for device %s", devaddr, nd->model); diff --git a/hw/pci/pci_host.c b/hw/pci/pci_host.c index 9d64b2e12f..5f3497256c 100644 --- a/hw/pci/pci_host.c +++ b/hw/pci/pci_host.c @@ -53,16 +53,9 @@ static inline PCIDevice *pci_dev_find_by_addr(PCIBus *bus, uint32_t addr) static void pci_adjust_config_limit(PCIBus *bus, uint32_t *limit) { - if (*limit > PCI_CONFIG_SPACE_SIZE) { - if (!pci_bus_allows_extended_config_space(bus)) { - *limit = PCI_CONFIG_SPACE_SIZE; - return; - } - - if (!pci_bus_is_root(bus)) { - PCIDevice *bridge = pci_bridge_get_device(bus); - pci_adjust_config_limit(pci_get_bus(bridge), limit); - } + if ((*limit > PCI_CONFIG_SPACE_SIZE) && + !pci_bus_allows_extended_config_space(bus)) { + *limit = PCI_CONFIG_SPACE_SIZE; } } diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c index 97961b0128..9cf2c41b8c 100644 --- a/hw/ppc/spapr_pci.c +++ b/hw/ppc/spapr_pci.c @@ -1626,28 +1626,6 @@ static void spapr_phb_unrealize(DeviceState *dev, Error **errp) memory_region_del_subregion(get_system_memory(), &sphb->mem32window); } -static bool spapr_phb_allows_extended_config_space(PCIBus *bus) -{ - SpaprPhbState *sphb = SPAPR_PCI_HOST_BRIDGE(BUS(bus)->parent); - - return sphb->pcie_ecs; -} - -static void spapr_phb_root_bus_class_init(ObjectClass *klass, void *data) -{ - PCIBusClass *pbc = PCI_BUS_CLASS(klass); - - pbc->allows_extended_config_space = spapr_phb_allows_extended_config_space; -} - -#define TYPE_SPAPR_PHB_ROOT_BUS "pci" - -static const TypeInfo spapr_phb_root_bus_info = { - .name = TYPE_SPAPR_PHB_ROOT_BUS, - .parent = TYPE_PCI_BUS, - .class_init = spapr_phb_root_bus_class_init, -}; - static void spapr_phb_realize(DeviceState *dev, Error **errp) { /* We don't use SPAPR_MACHINE() in order to exit gracefully if the user @@ -1753,7 +1731,16 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) pci_spapr_set_irq, pci_swizzle_map_irq_fn, sphb, &sphb->memspace, &sphb->iospace, PCI_DEVFN(0, 0), PCI_NUM_PINS, - TYPE_SPAPR_PHB_ROOT_BUS); + TYPE_PCI_BUS); + + /* + * Despite resembling a vanilla PCI bus in most ways, the PAPR + * para-virtualized PCI bus *does* permit PCI-E extended config + * space access + */ + if (sphb->pcie_ecs) { + bus->flags |= PCI_BUS_EXTENDED_CONFIG_SPACE; + } phb->bus = bus; qbus_set_hotplug_handler(BUS(phb->bus), OBJECT(sphb), NULL); @@ -2348,7 +2335,6 @@ void spapr_pci_rtas_init(void) static void spapr_pci_register_types(void) { type_register_static(&spapr_phb_info); - type_register_static(&spapr_phb_root_bus_info); } type_init(spapr_pci_register_types) diff --git a/hw/scsi/vhost-scsi.c b/hw/scsi/vhost-scsi.c index 61e2e57da9..6b01accf61 100644 --- a/hw/scsi/vhost-scsi.c +++ b/hw/scsi/vhost-scsi.c @@ -114,6 +114,10 @@ static void vhost_scsi_set_status(VirtIODevice *vdev, uint8_t val) VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s); bool start = (val & VIRTIO_CONFIG_S_DRIVER_OK); + if (!vdev->vm_running) { + start = false; + } + if (vsc->dev.started == start) { return; } @@ -135,6 +139,28 @@ static void vhost_dummy_handle_output(VirtIODevice *vdev, VirtQueue *vq) { } +static int vhost_scsi_pre_save(void *opaque) +{ + VHostSCSICommon *vsc = opaque; + + /* At this point, backend must be stopped, otherwise + * it might keep writing to memory. */ + assert(!vsc->dev.started); + + return 0; +} + +static const VMStateDescription vmstate_virtio_vhost_scsi = { + .name = "virtio-vhost_scsi", + .minimum_version_id = 1, + .version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_VIRTIO_DEVICE, + VMSTATE_END_OF_LIST() + }, + .pre_save = vhost_scsi_pre_save, +}; + static void vhost_scsi_realize(DeviceState *dev, Error **errp) { VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev); @@ -173,13 +199,18 @@ static void vhost_scsi_realize(DeviceState *dev, Error **errp) goto close_fd; } - error_setg(&vsc->migration_blocker, - "vhost-scsi does not support migration"); - migrate_add_blocker(vsc->migration_blocker, &err); - if (err) { - error_propagate(errp, err); - error_free(vsc->migration_blocker); - goto close_fd; + if (!vsc->migratable) { + error_setg(&vsc->migration_blocker, + "vhost-scsi does not support migration in all cases. " + "When external environment supports it (Orchestrator migrates " + "target SCSI device state or use shared storage over network), " + "set 'migratable' property to true to enable migration."); + migrate_add_blocker(vsc->migration_blocker, &err); + if (err) { + error_propagate(errp, err); + error_free(vsc->migration_blocker); + goto close_fd; + } } vsc->dev.nvqs = VHOST_SCSI_VQ_NUM_FIXED + vs->conf.num_queues; @@ -204,7 +235,9 @@ static void vhost_scsi_realize(DeviceState *dev, Error **errp) return; free_vqs: - migrate_del_blocker(vsc->migration_blocker); + if (!vsc->migratable) { + migrate_del_blocker(vsc->migration_blocker); + } g_free(vsc->dev.vqs); close_fd: close(vhostfd); @@ -217,8 +250,10 @@ static void vhost_scsi_unrealize(DeviceState *dev, Error **errp) VHostSCSICommon *vsc = VHOST_SCSI_COMMON(dev); struct vhost_virtqueue *vqs = vsc->dev.vqs; - migrate_del_blocker(vsc->migration_blocker); - error_free(vsc->migration_blocker); + if (!vsc->migratable) { + migrate_del_blocker(vsc->migration_blocker); + error_free(vsc->migration_blocker); + } /* This will stop vhost backend. */ vhost_scsi_set_status(vdev, 0); @@ -242,6 +277,7 @@ static Property vhost_scsi_properties[] = { DEFINE_PROP_BIT64("t10_pi", VHostSCSICommon, host_features, VIRTIO_SCSI_F_T10_PI, false), + DEFINE_PROP_BOOL("migratable", VHostSCSICommon, migratable, false), DEFINE_PROP_END_OF_LIST(), }; @@ -252,6 +288,7 @@ static void vhost_scsi_class_init(ObjectClass *klass, void *data) FWPathProviderClass *fwc = FW_PATH_PROVIDER_CLASS(klass); dc->props = vhost_scsi_properties; + dc->vmsd = &vmstate_virtio_vhost_scsi; set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); vdc->realize = vhost_scsi_realize; vdc->unrealize = vhost_scsi_unrealize; diff --git a/hw/scsi/vhost-user-scsi.c b/hw/scsi/vhost-user-scsi.c index 8b1e6876db..a9fd8ea305 100644 --- a/hw/scsi/vhost-user-scsi.c +++ b/hw/scsi/vhost-user-scsi.c @@ -69,6 +69,7 @@ static void vhost_user_scsi_realize(DeviceState *dev, Error **errp) VirtIOSCSICommon *vs = VIRTIO_SCSI_COMMON(dev); VHostUserSCSI *s = VHOST_USER_SCSI(dev); VHostSCSICommon *vsc = VHOST_SCSI_COMMON(s); + struct vhost_virtqueue *vqs = NULL; Error *err = NULL; int ret; @@ -93,6 +94,7 @@ static void vhost_user_scsi_realize(DeviceState *dev, Error **errp) vsc->dev.vqs = g_new(struct vhost_virtqueue, vsc->dev.nvqs); vsc->dev.vq_index = 0; vsc->dev.backend_features = 0; + vqs = vsc->dev.vqs; ret = vhost_dev_init(&vsc->dev, &s->vhost_user, VHOST_BACKEND_TYPE_USER, 0); @@ -100,6 +102,7 @@ static void vhost_user_scsi_realize(DeviceState *dev, Error **errp) error_setg(errp, "vhost-user-scsi: vhost initialization failed: %s", strerror(-ret)); vhost_user_cleanup(&s->vhost_user); + g_free(vqs); return; } diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index 286bb27c65..60747a6f93 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -1650,7 +1650,6 @@ fail_vq: hdev->vqs + i, hdev->vq_index + i); } - i = hdev->nvqs; fail_mem: fail_features: diff --git a/include/hw/acpi/acpi-defs.h b/include/hw/acpi/acpi-defs.h index f9aa4bd398..57a3f58b0c 100644 --- a/include/hw/acpi/acpi-defs.h +++ b/include/hw/acpi/acpi-defs.h @@ -449,24 +449,6 @@ struct AcpiSratProcessorGiccAffinity { typedef struct AcpiSratProcessorGiccAffinity AcpiSratProcessorGiccAffinity; -/* PCI fw r3.0 MCFG table. */ -/* Subtable */ -struct AcpiMcfgAllocation { - uint64_t address; /* Base address, processor-relative */ - uint16_t pci_segment; /* PCI segment group number */ - uint8_t start_bus_number; /* Starting PCI Bus number */ - uint8_t end_bus_number; /* Final PCI Bus number */ - uint32_t reserved; -} QEMU_PACKED; -typedef struct AcpiMcfgAllocation AcpiMcfgAllocation; - -struct AcpiTableMcfg { - ACPI_TABLE_HEADER_DEF; - uint8_t reserved[8]; - AcpiMcfgAllocation allocation[0]; -} QEMU_PACKED; -typedef struct AcpiTableMcfg AcpiTableMcfg; - /* * TCPA Description Table * diff --git a/include/hw/acpi/pci.h b/include/hw/acpi/pci.h index 124af7d32a..8bbd32cf45 100644 --- a/include/hw/acpi/pci.h +++ b/include/hw/acpi/pci.h @@ -30,4 +30,5 @@ typedef struct AcpiMcfgInfo { uint32_t size; } AcpiMcfgInfo; +void build_mcfg(GArray *table_data, BIOSLinker *linker, AcpiMcfgInfo *info); #endif diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h index edf44de21d..d082707dfa 100644 --- a/include/hw/pci/pci.h +++ b/include/hw/pci/pci.h @@ -234,7 +234,7 @@ typedef struct PCIDeviceClass { * This doesn't mean pci host switch. * When card bus bridge is supported, this would be enhanced. */ - int is_bridge; + bool is_bridge; /* rom bar */ const char *romfile; @@ -395,7 +395,6 @@ typedef PCIINTxRoute (*pci_route_irq_fn)(void *opaque, int pin); #define TYPE_PCIE_BUS "PCIE" bool pci_bus_is_express(PCIBus *bus); -bool pci_bus_allows_extended_config_space(PCIBus *bus); void pci_root_bus_new_inplace(PCIBus *bus, size_t bus_size, DeviceState *parent, const char *name, diff --git a/include/hw/pci/pci_bus.h b/include/hw/pci/pci_bus.h index aea98d5040..0714f578af 100644 --- a/include/hw/pci/pci_bus.h +++ b/include/hw/pci/pci_bus.h @@ -17,12 +17,13 @@ typedef struct PCIBusClass { int (*bus_num)(PCIBus *bus); uint16_t (*numa_node)(PCIBus *bus); - bool (*allows_extended_config_space)(PCIBus *bus); } PCIBusClass; enum PCIBusFlags { /* This bus is the root of a PCI domain */ PCI_BUS_IS_ROOT = 0x0001, + /* PCIe extended configuration space is accessible on this bus */ + PCI_BUS_EXTENDED_CONFIG_SPACE = 0x0002, }; struct PCIBus { @@ -57,4 +58,9 @@ static inline bool pci_bus_is_root(PCIBus *bus) return !!(bus->flags & PCI_BUS_IS_ROOT); } +static inline bool pci_bus_allows_extended_config_space(PCIBus *bus) +{ + return !!(bus->flags & PCI_BUS_EXTENDED_CONFIG_SPACE); +} + #endif /* QEMU_PCI_BUS_H */ diff --git a/include/hw/virtio/vhost-scsi-common.h b/include/hw/virtio/vhost-scsi-common.h index 57fb1d87b5..4eab767ee8 100644 --- a/include/hw/virtio/vhost-scsi-common.h +++ b/include/hw/virtio/vhost-scsi-common.h @@ -36,6 +36,7 @@ typedef struct VHostSCSICommon { int target; int lun; uint64_t host_features; + bool migratable; } VHostSCSICommon; int vhost_scsi_common_start(VHostSCSICommon *vsc); diff --git a/migration/fd.c b/migration/fd.c index a7c13df4ad..0a29ecdebf 100644 --- a/migration/fd.c +++ b/migration/fd.c @@ -52,12 +52,14 @@ static gboolean fd_accept_incoming_migration(QIOChannel *ioc, return G_SOURCE_REMOVE; } -void fd_start_incoming_migration(const char *infd, Error **errp) +void fd_start_incoming_migration(const char *fdname, Error **errp) { QIOChannel *ioc; - int fd; + int fd = monitor_fd_param(cur_mon, fdname, errp); + if (fd == -1) { + return; + } - fd = strtol(infd, NULL, 0); trace_migration_fd_incoming(fd); ioc = qio_channel_new_fd(fd, errp); diff --git a/migration/fd.h b/migration/fd.h index a14a63ce2e..b901bc014e 100644 --- a/migration/fd.h +++ b/migration/fd.h @@ -16,7 +16,7 @@ #ifndef QEMU_MIGRATION_FD_H #define QEMU_MIGRATION_FD_H -void fd_start_incoming_migration(const char *path, Error **errp); +void fd_start_incoming_migration(const char *fdname, Error **errp); void fd_start_outgoing_migration(MigrationState *s, const char *fdname, Error **errp); diff --git a/migration/ram.c b/migration/ram.c index 359dc8f1bc..908517fc2b 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -661,8 +661,6 @@ typedef struct { uint64_t num_packets; /* pages sent through this channel */ uint64_t num_pages; - /* syncs main thread and channels */ - QemuSemaphore sem_sync; } MultiFDSendParams; typedef struct { @@ -894,8 +892,6 @@ static int multifd_recv_unfill_packet(MultiFDRecvParams *p, Error **errp) struct { MultiFDSendParams *params; - /* number of created threads */ - int count; /* array of pages to sent */ MultiFDPages_t *pages; /* syncs main thread and channels */ @@ -1027,7 +1023,6 @@ void multifd_save_cleanup(void) p->c = NULL; qemu_mutex_destroy(&p->mutex); qemu_sem_destroy(&p->sem); - qemu_sem_destroy(&p->sem_sync); g_free(p->name); p->name = NULL; multifd_pages_clear(p->pages); @@ -1174,8 +1169,6 @@ static void multifd_new_send_channel_async(QIOTask *task, gpointer opaque) p->running = true; qemu_thread_create(&p->thread, p->name, multifd_send_thread, p, QEMU_THREAD_JOINABLE); - - atomic_inc(&multifd_send_state->count); } } @@ -1191,7 +1184,6 @@ int multifd_save_setup(void) thread_count = migrate_multifd_channels(); multifd_send_state = g_malloc0(sizeof(*multifd_send_state)); multifd_send_state->params = g_new0(MultiFDSendParams, thread_count); - atomic_set(&multifd_send_state->count, 0); multifd_send_state->pages = multifd_pages_init(page_count); qemu_sem_init(&multifd_send_state->sem_sync, 0); qemu_sem_init(&multifd_send_state->channels_ready, 0); @@ -1201,7 +1193,6 @@ int multifd_save_setup(void) qemu_mutex_init(&p->mutex); qemu_sem_init(&p->sem, 0); - qemu_sem_init(&p->sem_sync, 0); p->quit = false; p->pending_job = 0; p->id = i; @@ -3182,11 +3173,11 @@ static int ram_state_init(RAMState **rsp) QSIMPLEQ_INIT(&(*rsp)->src_page_requests); /* - * Count the total number of pages used by ram blocks not including any - * gaps due to alignment or unplugs. + * This must match with the initial values of dirty bitmap. + * Currently we initialize the dirty bitmap to all zeros so + * here the total dirty page count is zero. */ - (*rsp)->migration_dirty_pages = ram_bytes_total() >> TARGET_PAGE_BITS; - + (*rsp)->migration_dirty_pages = 0; ram_state_reset(*rsp); return 0; @@ -3201,8 +3192,16 @@ static void ram_list_init_bitmaps(void) if (ram_bytes_total()) { RAMBLOCK_FOREACH_NOT_IGNORED(block) { pages = block->max_length >> TARGET_PAGE_BITS; + /* + * The initial dirty bitmap for migration must be set with all + * ones to make sure we'll migrate every guest RAM page to + * destination. + * Here we didn't set RAMBlock.bmap simply because it is already + * set in ram_list.dirty_memory[DIRTY_MEMORY_MIGRATION] in + * ram_block_add, and that's where we'll sync the dirty bitmaps. + * Here setting RAMBlock.bmap would be fine too but not necessary. + */ block->bmap = bitmap_new(pages); - bitmap_set(block->bmap, 0, pages); if (migrate_postcopy_ram()) { block->unsentmap = bitmap_new(pages); bitmap_set(block->unsentmap, 0, pages); diff --git a/qemu-options.hx b/qemu-options.hx index 39dc170429..0d8beb4afd 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -2080,7 +2080,7 @@ Specify SMBIOS type 0 fields @item -smbios type=1[,manufacturer=@var{str}][,product=@var{str}][,version=@var{str}][,serial=@var{str}][,uuid=@var{uuid}][,sku=@var{str}][,family=@var{str}] Specify SMBIOS type 1 fields -@item -smbios type=2[,manufacturer=@var{str}][,product=@var{str}][,version=@var{str}][,serial=@var{str}][,asset=@var{str}][,location=@var{str}][,family=@var{str}] +@item -smbios type=2[,manufacturer=@var{str}][,product=@var{str}][,version=@var{str}][,serial=@var{str}][,asset=@var{str}][,location=@var{str}] Specify SMBIOS type 2 fields @item -smbios type=3[,manufacturer=@var{str}][,version=@var{str}][,serial=@var{str}][,asset=@var{str}][,sku=@var{str}] diff --git a/tests/Makefile.include b/tests/Makefile.include index 34df040583..0cd5f465b7 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -264,6 +264,10 @@ check-qtest-arm-y += tests/hexloader-test$(EXESUF) check-qtest-aarch64-y = tests/numa-test$(EXESUF) check-qtest-aarch64-y += tests/boot-serial-test$(EXESUF) check-qtest-aarch64-y += tests/migration-test$(EXESUF) +# TODO: once aarch64 TCG is fixed on ARM 32 bit host, make test unconditional +ifneq ($(ARCH),arm) +check-qtest-aarch64-y += tests/bios-tables-test$(EXESUF) +endif check-qtest-microblazeel-y += $(check-qtest-microblaze-y) diff --git a/tests/bios-tables-test-allowed-diff.h b/tests/bios-tables-test-allowed-diff.h new file mode 100644 index 0000000000..dfb8523c8b --- /dev/null +++ b/tests/bios-tables-test-allowed-diff.h @@ -0,0 +1 @@ +/* List of comma-separated changed AML files to ignore */ diff --git a/tests/bios-tables-test.c b/tests/bios-tables-test.c index 11e07be093..0ce55182f2 100644 --- a/tests/bios-tables-test.c +++ b/tests/bios-tables-test.c @@ -342,13 +342,29 @@ try_again: return exp_tables; } +static bool test_acpi_find_diff_allowed(AcpiSdtTable *sdt) +{ + const gchar *allowed_diff_file[] = { +#include "bios-tables-test-allowed-diff.h" + NULL + }; + const gchar **f; + + for (f = allowed_diff_file; *f; ++f) { + if (!g_strcmp0(sdt->aml_file, *f)) { + return true; + } + } + return false; +} + /* test the list of tables in @data->tables against reference tables */ static void test_acpi_asl(test_data *data) { int i; AcpiSdtTable *sdt, *exp_sdt; test_data exp_data; - gboolean exp_err, err; + gboolean exp_err, err, all_tables_match = true; memset(&exp_data, 0, sizeof(exp_data)); exp_data.tables = load_expected_aml(data); @@ -359,6 +375,20 @@ static void test_acpi_asl(test_data *data) sdt = &g_array_index(data->tables, AcpiSdtTable, i); exp_sdt = &g_array_index(exp_data.tables, AcpiSdtTable, i); + if (sdt->aml_len == exp_sdt->aml_len && + !memcmp(sdt->aml, exp_sdt->aml, sdt->aml_len)) { + /* Identical table binaries: no need to disassemble. */ + continue; + } + + fprintf(stderr, + "acpi-test: Warning! %.4s binary file mismatch. " + "Actual [aml:%s], Expected [aml:%s].\n", + exp_sdt->aml, sdt->aml_file, exp_sdt->aml_file); + + all_tables_match = all_tables_match && + test_acpi_find_diff_allowed(exp_sdt); + err = load_asl(data->tables, sdt); asl = normalize_asl(sdt->asl); @@ -396,11 +426,12 @@ static void test_acpi_asl(test_data *data) "see ASL difference."); } } - } + } } g_string_free(asl, true); g_string_free(exp_asl, true); } + g_assert(all_tables_match); free_test_data(&exp_data); } @@ -813,6 +844,22 @@ static void test_acpi_piix4_tcg_dimm_pxm(void) test_acpi_tcg_dimm_pxm(MACHINE_PC); } +static void test_acpi_virt_tcg(void) +{ + test_data data = { + .machine = "virt", + .accel = "tcg", + .uefi_fl1 = "pc-bios/edk2-aarch64-code.fd", + .uefi_fl2 = "pc-bios/edk2-arm-vars.fd", + .cd = "tests/data/uefi-boot-images/bios-tables-test.aarch64.iso.qcow2", + .ram_start = 0x40000000ULL, + .scan_len = 128ULL * 1024 * 1024, + }; + + test_acpi_one("-cpu cortex-a57", &data); + free_test_data(&data); +} + int main(int argc, char *argv[]) { const char *arch = qtest_get_arch(); @@ -841,6 +888,8 @@ int main(int argc, char *argv[]) qtest_add_func("acpi/q35/numamem", test_acpi_q35_tcg_numamem); qtest_add_func("acpi/piix4/dimmpxm", test_acpi_piix4_tcg_dimm_pxm); qtest_add_func("acpi/q35/dimmpxm", test_acpi_q35_tcg_dimm_pxm); + } else if (strcmp(arch, "aarch64") == 0) { + qtest_add_func("acpi/virt", test_acpi_virt_tcg); } ret = g_test_run(); boot_sector_cleanup(disk); diff --git a/tests/data/acpi/rebuild-expected-aml.sh b/tests/data/acpi/rebuild-expected-aml.sh index ff7e62249d..d2853218dd 100755 --- a/tests/data/acpi/rebuild-expected-aml.sh +++ b/tests/data/acpi/rebuild-expected-aml.sh @@ -12,7 +12,7 @@ # This work is licensed under the terms of the GNU GPLv2. # See the COPYING.LIB file in the top-level directory. -qemu_bins="x86_64-softmmu/qemu-system-x86_64" +qemu_bins="x86_64-softmmu/qemu-system-x86_64 aarch64-softmmu/qemu-system-aarch64" if [ ! -e "tests/bios-tables-test" ]; then echo "Test: bios-tables-test is required! Run make check before this script." diff --git a/tests/data/acpi/virt/APIC b/tests/data/acpi/virt/APIC new file mode 100644 index 0000000000..797dfde284 --- /dev/null +++ b/tests/data/acpi/virt/APIC Binary files differdiff --git a/tests/data/acpi/virt/DSDT b/tests/data/acpi/virt/DSDT new file mode 100644 index 0000000000..20e85c7f89 --- /dev/null +++ b/tests/data/acpi/virt/DSDT Binary files differdiff --git a/tests/data/acpi/virt/FACP b/tests/data/acpi/virt/FACP new file mode 100644 index 0000000000..27de99f51b --- /dev/null +++ b/tests/data/acpi/virt/FACP Binary files differdiff --git a/tests/data/acpi/virt/GTDT b/tests/data/acpi/virt/GTDT new file mode 100644 index 0000000000..10107a65e9 --- /dev/null +++ b/tests/data/acpi/virt/GTDT Binary files differdiff --git a/tests/data/acpi/virt/MCFG b/tests/data/acpi/virt/MCFG new file mode 100644 index 0000000000..e8987e1af0 --- /dev/null +++ b/tests/data/acpi/virt/MCFG Binary files differdiff --git a/tests/data/acpi/virt/SPCR b/tests/data/acpi/virt/SPCR new file mode 100644 index 0000000000..377271a0e7 --- /dev/null +++ b/tests/data/acpi/virt/SPCR Binary files differdiff --git a/tests/libqtest.c b/tests/libqtest.c index 546a875913..9b9b5f37fc 100644 --- a/tests/libqtest.c +++ b/tests/libqtest.c @@ -32,6 +32,7 @@ #define MAX_IRQ 256 #define SOCKET_TIMEOUT 50 +#define SOCKET_MAX_FDS 16 QTestState *global_qtest; @@ -391,6 +392,40 @@ static void GCC_FMT_ATTR(2, 3) qtest_sendf(QTestState *s, const char *fmt, ...) va_end(ap); } +/* Sends a message and file descriptors to the socket. + * It's needed for qmp-commands like getfd/add-fd */ +static void socket_send_fds(int socket_fd, int *fds, size_t fds_num, + const char *buf, size_t buf_size) +{ + ssize_t ret; + struct msghdr msg = { 0 }; + char control[CMSG_SPACE(sizeof(int) * SOCKET_MAX_FDS)] = { 0 }; + size_t fdsize = sizeof(int) * fds_num; + struct cmsghdr *cmsg; + struct iovec iov = { .iov_base = (char *)buf, .iov_len = buf_size }; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + if (fds && fds_num > 0) { + g_assert_cmpuint(fds_num, <, SOCKET_MAX_FDS); + + msg.msg_control = control; + msg.msg_controllen = CMSG_SPACE(fdsize); + + cmsg = CMSG_FIRSTHDR(&msg); + cmsg->cmsg_len = CMSG_LEN(fdsize); + cmsg->cmsg_level = SOL_SOCKET; + cmsg->cmsg_type = SCM_RIGHTS; + memcpy(CMSG_DATA(cmsg), fds, fdsize); + } + + do { + ret = sendmsg(socket_fd, &msg, 0); + } while (ret < 0 && errno == EINTR); + g_assert_cmpint(ret, >, 0); +} + static GString *qtest_recv_line(QTestState *s) { GString *line; @@ -545,7 +580,8 @@ QDict *qtest_qmp_receive(QTestState *s) * in the case that they choose to discard all replies up until * a particular EVENT is received. */ -void qmp_fd_vsend(int fd, const char *fmt, va_list ap) +void qmp_fd_vsend_fds(int fd, int *fds, size_t fds_num, + const char *fmt, va_list ap) { QObject *qobj; @@ -569,25 +605,49 @@ void qmp_fd_vsend(int fd, const char *fmt, va_list ap) fprintf(stderr, "%s", str); } /* Send QMP request */ - socket_send(fd, str, qstring_get_length(qstr)); + if (fds && fds_num > 0) { + socket_send_fds(fd, fds, fds_num, str, qstring_get_length(qstr)); + } else { + socket_send(fd, str, qstring_get_length(qstr)); + } qobject_unref(qstr); qobject_unref(qobj); } } +void qmp_fd_vsend(int fd, const char *fmt, va_list ap) +{ + qmp_fd_vsend_fds(fd, NULL, 0, fmt, ap); +} + +void qtest_qmp_vsend_fds(QTestState *s, int *fds, size_t fds_num, + const char *fmt, va_list ap) +{ + qmp_fd_vsend_fds(s->qmp_fd, fds, fds_num, fmt, ap); +} + void qtest_qmp_vsend(QTestState *s, const char *fmt, va_list ap) { - qmp_fd_vsend(s->qmp_fd, fmt, ap); + qmp_fd_vsend_fds(s->qmp_fd, NULL, 0, fmt, ap); } QDict *qmp_fdv(int fd, const char *fmt, va_list ap) { - qmp_fd_vsend(fd, fmt, ap); + qmp_fd_vsend_fds(fd, NULL, 0, fmt, ap); return qmp_fd_receive(fd); } +QDict *qtest_vqmp_fds(QTestState *s, int *fds, size_t fds_num, + const char *fmt, va_list ap) +{ + qtest_qmp_vsend_fds(s, fds, fds_num, fmt, ap); + + /* Receive reply */ + return qtest_qmp_receive(s); +} + QDict *qtest_vqmp(QTestState *s, const char *fmt, va_list ap) { qtest_qmp_vsend(s, fmt, ap); @@ -616,6 +676,18 @@ void qmp_fd_send(int fd, const char *fmt, ...) va_end(ap); } +QDict *qtest_qmp_fds(QTestState *s, int *fds, size_t fds_num, + const char *fmt, ...) +{ + va_list ap; + QDict *response; + + va_start(ap, fmt); + response = qtest_vqmp_fds(s, fds, fds_num, fmt, ap); + va_end(ap); + return response; +} + QDict *qtest_qmp(QTestState *s, const char *fmt, ...) { va_list ap; diff --git a/tests/libqtest.h b/tests/libqtest.h index 32d927755d..cadf1d4a03 100644 --- a/tests/libqtest.h +++ b/tests/libqtest.h @@ -85,6 +85,21 @@ QTestState *qtest_init_with_serial(const char *extra_args, int *sock_fd); void qtest_quit(QTestState *s); /** + * qtest_qmp_fds: + * @s: #QTestState instance to operate on. + * @fds: array of file descriptors + * @fds_num: number of elements in @fds + * @fmt...: QMP message to send to qemu, formatted like + * qobject_from_jsonf_nofail(). See parse_escape() for what's + * supported after '%'. + * + * Sends a QMP message to QEMU with fds and returns the response. + */ +QDict *qtest_qmp_fds(QTestState *s, int *fds, size_t fds_num, + const char *fmt, ...) + GCC_FMT_ATTR(4, 5); + +/** * qtest_qmp: * @s: #QTestState instance to operate on. * @fmt...: QMP message to send to qemu, formatted like @@ -120,7 +135,23 @@ void qtest_qmp_send_raw(QTestState *s, const char *fmt, ...) GCC_FMT_ATTR(2, 3); /** - * qtest_qmpv: + * qtest_vqmp_fds: + * @s: #QTestState instance to operate on. + * @fds: array of file descriptors + * @fds_num: number of elements in @fds + * @fmt: QMP message to send to QEMU, formatted like + * qobject_from_jsonf_nofail(). See parse_escape() for what's + * supported after '%'. + * @ap: QMP message arguments + * + * Sends a QMP message to QEMU with fds and returns the response. + */ +QDict *qtest_vqmp_fds(QTestState *s, int *fds, size_t fds_num, + const char *fmt, va_list ap) + GCC_FMT_ATTR(4, 0); + +/** + * qtest_vqmp: * @s: #QTestState instance to operate on. * @fmt: QMP message to send to QEMU, formatted like * qobject_from_jsonf_nofail(). See parse_escape() for what's @@ -133,6 +164,22 @@ QDict *qtest_vqmp(QTestState *s, const char *fmt, va_list ap) GCC_FMT_ATTR(2, 0); /** + * qtest_qmp_vsend_fds: + * @s: #QTestState instance to operate on. + * @fds: array of file descriptors + * @fds_num: number of elements in @fds + * @fmt: QMP message to send to QEMU, formatted like + * qobject_from_jsonf_nofail(). See parse_escape() for what's + * supported after '%'. + * @ap: QMP message arguments + * + * Sends a QMP message to QEMU and leaves the response in the stream. + */ +void qtest_qmp_vsend_fds(QTestState *s, int *fds, size_t fds_num, + const char *fmt, va_list ap) + GCC_FMT_ATTR(4, 0); + +/** * qtest_qmp_vsend: * @s: #QTestState instance to operate on. * @fmt: QMP message to send to QEMU, formatted like @@ -888,6 +935,8 @@ static inline int64_t clock_step(int64_t step) } QDict *qmp_fd_receive(int fd); +void qmp_fd_vsend_fds(int fd, int *fds, size_t fds_num, + const char *fmt, va_list ap) GCC_FMT_ATTR(4, 0); void qmp_fd_vsend(int fd, const char *fmt, va_list ap) GCC_FMT_ATTR(2, 0); void qmp_fd_send(int fd, const char *fmt, ...) GCC_FMT_ATTR(2, 3); void qmp_fd_send_raw(int fd, const char *fmt, ...) GCC_FMT_ATTR(2, 3); diff --git a/tests/migration-test.c b/tests/migration-test.c index bd3f5c3125..e0407576cb 100644 --- a/tests/migration-test.c +++ b/tests/migration-test.c @@ -177,6 +177,21 @@ static void stop_cb(void *opaque, const char *name, QDict *data) /* * Events can get in the way of responses we are actually waiting for. */ +GCC_FMT_ATTR(3, 4) +static QDict *wait_command_fd(QTestState *who, int fd, const char *command, ...) +{ + va_list ap; + + va_start(ap, command); + qtest_qmp_vsend_fds(who, &fd, 1, command, ap); + va_end(ap); + + return qtest_qmp_receive_success(who, stop_cb, NULL); +} + +/* + * Events can get in the way of responses we are actually waiting for. + */ GCC_FMT_ATTR(2, 3) static QDict *wait_command(QTestState *who, const char *command, ...) { @@ -480,6 +495,7 @@ static void migrate(QTestState *who, const char *uri, const char *fmt, ...) qdict_put_str(args, "uri", uri); rsp = qmp("{ 'execute': 'migrate', 'arguments': %p}", args); + g_assert(qdict_haskey(rsp, "return")); qobject_unref(rsp); } @@ -1027,6 +1043,90 @@ static void test_precopy_tcp(void) g_free(uri); } +static void test_migrate_fd_proto(void) +{ + QTestState *from, *to; + int ret; + int pair[2]; + QDict *rsp; + const char *error_desc; + + if (test_migrate_start(&from, &to, "defer", false, false)) { + return; + } + + /* + * We want to pick a speed slow enough that the test completes + * quickly, but that it doesn't complete precopy even on a slow + * machine, so also set the downtime. + */ + /* 1 ms should make it not converge */ + migrate_set_parameter(from, "downtime-limit", 1); + /* 1GB/s */ + migrate_set_parameter(from, "max-bandwidth", 1000000000); + + /* Wait for the first serial output from the source */ + wait_for_serial("src_serial"); + + /* Create two connected sockets for migration */ + ret = socketpair(PF_LOCAL, SOCK_STREAM, 0, pair); + g_assert_cmpint(ret, ==, 0); + + /* Send the 1st socket to the target */ + rsp = wait_command_fd(to, pair[0], + "{ 'execute': 'getfd'," + " 'arguments': { 'fdname': 'fd-mig' }}"); + qobject_unref(rsp); + close(pair[0]); + + /* Start incoming migration from the 1st socket */ + rsp = wait_command(to, "{ 'execute': 'migrate-incoming'," + " 'arguments': { 'uri': 'fd:fd-mig' }}"); + qobject_unref(rsp); + + /* Send the 2nd socket to the target */ + rsp = wait_command_fd(from, pair[1], + "{ 'execute': 'getfd'," + " 'arguments': { 'fdname': 'fd-mig' }}"); + qobject_unref(rsp); + close(pair[1]); + + /* Start migration to the 2nd socket*/ + migrate(from, "fd:fd-mig", "{}"); + + wait_for_migration_pass(from); + + /* 300ms should converge */ + migrate_set_parameter(from, "downtime-limit", 300); + + if (!got_stop) { + qtest_qmp_eventwait(from, "STOP"); + } + qtest_qmp_eventwait(to, "RESUME"); + + /* Test closing fds */ + /* We assume, that QEMU removes named fd from its list, + * so this should fail */ + rsp = qtest_qmp(from, "{ 'execute': 'closefd'," + " 'arguments': { 'fdname': 'fd-mig' }}"); + g_assert_true(qdict_haskey(rsp, "error")); + error_desc = qdict_get_str(qdict_get_qdict(rsp, "error"), "desc"); + g_assert_cmpstr(error_desc, ==, "File descriptor named 'fd-mig' not found"); + qobject_unref(rsp); + + rsp = qtest_qmp(to, "{ 'execute': 'closefd'," + " 'arguments': { 'fdname': 'fd-mig' }}"); + g_assert_true(qdict_haskey(rsp, "error")); + error_desc = qdict_get_str(qdict_get_qdict(rsp, "error"), "desc"); + g_assert_cmpstr(error_desc, ==, "File descriptor named 'fd-mig' not found"); + qobject_unref(rsp); + + /* Complete migration */ + wait_for_serial("dest_serial"); + wait_for_migration_complete(from); + test_migrate_end(from, to, true); +} + int main(int argc, char **argv) { char template[] = "/tmp/migration-test-XXXXXX"; @@ -1081,6 +1181,7 @@ int main(int argc, char **argv) qtest_add_func("/migration/precopy/tcp", test_precopy_tcp); /* qtest_add_func("/migration/ignore_shared", test_ignore_shared); */ qtest_add_func("/migration/xbzrle/unix", test_xbzrle_unix); + qtest_add_func("/migration/fd_proto", test_migrate_fd_proto); ret = g_test_run(); diff --git a/vl.c b/vl.c index f023a8ca73..cd1fbc4cdc 100644 --- a/vl.c +++ b/vl.c @@ -2751,20 +2751,25 @@ static bool object_create_initial(const char *type, QemuOpts *opts) exit(0); } - if (g_str_equal(type, "rng-egd") || - g_str_has_prefix(type, "pr-manager-")) { + /* + * Objects should not be made "delayed" without a reason. If you + * add one, state the reason in a comment! + */ + + /* Reason: rng-egd property "chardev" */ + if (g_str_equal(type, "rng-egd")) { return false; } #if defined(CONFIG_VHOST_USER) && defined(CONFIG_LINUX) + /* Reason: cryptodev-vhost-user property "chardev" */ if (g_str_equal(type, "cryptodev-vhost-user")) { return false; } #endif /* - * return false for concrete netfilters since - * they depend on netdevs already existing + * Reason: filter-* property "netdev" etc. */ if (g_str_equal(type, "filter-buffer") || g_str_equal(type, "filter-dump") || |