diff options
Diffstat (limited to 'hw')
| -rw-r--r-- | hw/acpi/Kconfig | 4 | ||||
| -rw-r--r-- | hw/acpi/meson.build | 1 | ||||
| -rw-r--r-- | hw/acpi/viot.c | 114 | ||||
| -rw-r--r-- | hw/acpi/viot.h | 13 | ||||
| -rw-r--r-- | hw/i386/Kconfig | 1 | ||||
| -rw-r--r-- | hw/i386/acpi-build.c | 33 | ||||
| -rw-r--r-- | hw/i386/amd_iommu.c | 2 | ||||
| -rw-r--r-- | hw/i386/intel_iommu.c | 3 | ||||
| -rw-r--r-- | hw/i386/pc.c | 26 | ||||
| -rw-r--r-- | hw/i386/vmmouse.c | 1 | ||||
| -rw-r--r-- | hw/i386/x86-iommu-stub.c | 5 | ||||
| -rw-r--r-- | hw/i386/x86-iommu.c | 31 | ||||
| -rw-r--r-- | hw/i386/xen/xen-hvm.c | 4 | ||||
| -rw-r--r-- | hw/ide/core.c | 8 | ||||
| -rw-r--r-- | hw/pci/pci.c | 26 | ||||
| -rw-r--r-- | hw/pci/pcie.c | 4 | ||||
| -rw-r--r-- | hw/ppc/spapr_pci.c | 12 | ||||
| -rw-r--r-- | hw/ppc/spapr_pci_nvlink2.c | 7 | ||||
| -rw-r--r-- | hw/ppc/spapr_pci_vfio.c | 4 | ||||
| -rw-r--r-- | hw/s390x/s390-pci-bus.c | 5 | ||||
| -rw-r--r-- | hw/usb/hcd-uhci.c | 14 | ||||
| -rw-r--r-- | hw/usb/hcd-uhci.h | 3 | ||||
| -rw-r--r-- | hw/usb/vt82c686-uhci-pci.c | 15 | ||||
| -rw-r--r-- | hw/vfio/common.c | 7 | ||||
| -rw-r--r-- | hw/vfio/pci.c | 19 | ||||
| -rw-r--r-- | hw/virtio/vhost-vdpa.c | 13 | ||||
| -rw-r--r-- | hw/virtio/virtio-mem.c | 92 | ||||
| -rw-r--r-- | hw/xen/xen_pt.c | 4 |
28 files changed, 339 insertions, 132 deletions
diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig index 3b5e118c54..622b0b50b7 100644 --- a/hw/acpi/Kconfig +++ b/hw/acpi/Kconfig @@ -51,6 +51,10 @@ config ACPI_VMGENID default y depends on PC +config ACPI_VIOT + bool + depends on ACPI + config ACPI_HW_REDUCED bool select ACPI diff --git a/hw/acpi/meson.build b/hw/acpi/meson.build index 7d8c0eb43e..adf6347bc4 100644 --- a/hw/acpi/meson.build +++ b/hw/acpi/meson.build @@ -20,6 +20,7 @@ acpi_ss.add(when: 'CONFIG_ACPI_APEI', if_true: files('ghes.c'), if_false: files( acpi_ss.add(when: 'CONFIG_ACPI_PIIX4', if_true: files('piix4.c')) acpi_ss.add(when: 'CONFIG_ACPI_PCIHP', if_true: files('pcihp.c')) acpi_ss.add(when: 'CONFIG_ACPI_PCIHP', if_false: files('acpi-pci-hotplug-stub.c')) +acpi_ss.add(when: 'CONFIG_ACPI_VIOT', if_true: files('viot.c')) acpi_ss.add(when: 'CONFIG_ACPI_X86_ICH', if_true: files('ich9.c', 'tco.c')) acpi_ss.add(when: 'CONFIG_IPMI', if_true: files('ipmi.c'), if_false: files('ipmi-stub.c')) acpi_ss.add(when: 'CONFIG_PC', if_false: files('acpi-x86-stub.c')) diff --git a/hw/acpi/viot.c b/hw/acpi/viot.c new file mode 100644 index 0000000000..c1af75206e --- /dev/null +++ b/hw/acpi/viot.c @@ -0,0 +1,114 @@ +/* + * ACPI Virtual I/O Translation table implementation + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#include "qemu/osdep.h" +#include "hw/acpi/acpi.h" +#include "hw/acpi/aml-build.h" +#include "hw/acpi/viot.h" +#include "hw/pci/pci.h" +#include "hw/pci/pci_host.h" + +struct viot_pci_ranges { + GArray *blob; + size_t count; + uint16_t output_node; +}; + +/* Build PCI range for a given PCI host bridge */ +static int build_pci_range_node(Object *obj, void *opaque) +{ + struct viot_pci_ranges *pci_ranges = opaque; + GArray *blob = pci_ranges->blob; + + if (object_dynamic_cast(obj, TYPE_PCI_HOST_BRIDGE)) { + PCIBus *bus = PCI_HOST_BRIDGE(obj)->bus; + + if (bus && !pci_bus_bypass_iommu(bus)) { + int min_bus, max_bus; + + pci_bus_range(bus, &min_bus, &max_bus); + + /* Type */ + build_append_int_noprefix(blob, 1 /* PCI range */, 1); + /* Reserved */ + build_append_int_noprefix(blob, 0, 1); + /* Length */ + build_append_int_noprefix(blob, 24, 2); + /* Endpoint start */ + build_append_int_noprefix(blob, PCI_BUILD_BDF(min_bus, 0), 4); + /* PCI Segment start */ + build_append_int_noprefix(blob, 0, 2); + /* PCI Segment end */ + build_append_int_noprefix(blob, 0, 2); + /* PCI BDF start */ + build_append_int_noprefix(blob, PCI_BUILD_BDF(min_bus, 0), 2); + /* PCI BDF end */ + build_append_int_noprefix(blob, PCI_BUILD_BDF(max_bus, 0xff), 2); + /* Output node */ + build_append_int_noprefix(blob, pci_ranges->output_node, 2); + /* Reserved */ + build_append_int_noprefix(blob, 0, 6); + + pci_ranges->count++; + } + } + + return 0; +} + +/* + * Generate a VIOT table with one PCI-based virtio-iommu that manages PCI + * endpoints. + * + * Defined in the ACPI Specification (Version TBD) + */ +void build_viot(MachineState *ms, GArray *table_data, BIOSLinker *linker, + uint16_t virtio_iommu_bdf, const char *oem_id, + const char *oem_table_id) +{ + /* The virtio-iommu node follows the 48-bytes header */ + int viommu_off = 48; + AcpiTable table = { .sig = "VIOT", .rev = 0, + .oem_id = oem_id, .oem_table_id = oem_table_id }; + struct viot_pci_ranges pci_ranges = { + .output_node = viommu_off, + .blob = g_array_new(false, true /* clear */, 1), + }; + + /* Build the list of PCI ranges that this viommu manages */ + object_child_foreach_recursive(OBJECT(ms), build_pci_range_node, + &pci_ranges); + + /* ACPI table header */ + acpi_table_begin(&table, table_data); + /* Node count */ + build_append_int_noprefix(table_data, pci_ranges.count + 1, 2); + /* Node offset */ + build_append_int_noprefix(table_data, viommu_off, 2); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 8); + + /* Virtio-iommu node */ + /* Type */ + build_append_int_noprefix(table_data, 3 /* virtio-pci IOMMU */, 1); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 1); + /* Length */ + build_append_int_noprefix(table_data, 16, 2); + /* PCI Segment */ + build_append_int_noprefix(table_data, 0, 2); + /* PCI BDF number */ + build_append_int_noprefix(table_data, virtio_iommu_bdf, 2); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 8); + + /* PCI ranges found above */ + g_array_append_vals(table_data, pci_ranges.blob->data, + pci_ranges.blob->len); + g_array_free(pci_ranges.blob, true); + + acpi_table_end(linker, &table); +} + diff --git a/hw/acpi/viot.h b/hw/acpi/viot.h new file mode 100644 index 0000000000..9fe565bb87 --- /dev/null +++ b/hw/acpi/viot.h @@ -0,0 +1,13 @@ +/* + * ACPI Virtual I/O Translation Table implementation + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#ifndef VIOT_H +#define VIOT_H + +void build_viot(MachineState *ms, GArray *table_data, BIOSLinker *linker, + uint16_t virtio_iommu_bdf, const char *oem_id, + const char *oem_table_id); + +#endif /* VIOT_H */ diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig index 962d2c981b..d22ac4a4b9 100644 --- a/hw/i386/Kconfig +++ b/hw/i386/Kconfig @@ -59,6 +59,7 @@ config PC_ACPI select ACPI_X86 select ACPI_CPU_HOTPLUG select ACPI_MEMORY_HOTPLUG + select ACPI_VIOT select SMBUS_EEPROM select PFLASH_CFI01 depends on ACPI_SMBUS diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index 81418b7911..a3ad6abd33 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -68,9 +68,11 @@ #include "qom/qom-qobject.h" #include "hw/i386/amd_iommu.h" #include "hw/i386/intel_iommu.h" +#include "hw/virtio/virtio-iommu.h" #include "hw/acpi/ipmi.h" #include "hw/acpi/hmat.h" +#include "hw/acpi/viot.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 @@ -2132,8 +2134,7 @@ dmar_host_bridges(Object *obj, void *opaque) PCIBus *bus = PCI_HOST_BRIDGE(obj)->bus; if (bus && !pci_bus_bypass_iommu(bus)) { - pci_for_each_device(bus, pci_bus_num(bus), insert_scope, - scope_blob); + pci_for_each_device_under_bus(bus, insert_scope, scope_blob); } } @@ -2339,7 +2340,7 @@ ivrs_host_bridges(Object *obj, void *opaque) PCIBus *bus = PCI_HOST_BRIDGE(obj)->bus; if (bus && !pci_bus_bypass_iommu(bus)) { - pci_for_each_device(bus, pci_bus_num(bus), insert_ivhd, ivhd_blob); + pci_for_each_device_under_bus(bus, insert_ivhd, ivhd_blob); } } @@ -2488,6 +2489,7 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) PCMachineState *pcms = PC_MACHINE(machine); PCMachineClass *pcmc = PC_MACHINE_GET_CLASS(pcms); X86MachineState *x86ms = X86_MACHINE(machine); + DeviceState *iommu = pcms->iommu; GArray *table_offsets; unsigned facs, dsdt, rsdt, fadt; AcpiPmInfo pm; @@ -2604,17 +2606,20 @@ void acpi_build(AcpiBuildTables *tables, MachineState *machine) build_mcfg(tables_blob, tables->linker, &mcfg, x86ms->oem_id, x86ms->oem_table_id); } - if (x86_iommu_get_default()) { - IommuType IOMMUType = x86_iommu_get_type(); - if (IOMMUType == TYPE_AMD) { - acpi_add_table(table_offsets, tables_blob); - build_amd_iommu(tables_blob, tables->linker, x86ms->oem_id, - x86ms->oem_table_id); - } else if (IOMMUType == TYPE_INTEL) { - acpi_add_table(table_offsets, tables_blob); - build_dmar_q35(tables_blob, tables->linker, x86ms->oem_id, - x86ms->oem_table_id); - } + if (object_dynamic_cast(OBJECT(iommu), TYPE_AMD_IOMMU_DEVICE)) { + acpi_add_table(table_offsets, tables_blob); + build_amd_iommu(tables_blob, tables->linker, x86ms->oem_id, + x86ms->oem_table_id); + } else if (object_dynamic_cast(OBJECT(iommu), TYPE_INTEL_IOMMU_DEVICE)) { + acpi_add_table(table_offsets, tables_blob); + build_dmar_q35(tables_blob, tables->linker, x86ms->oem_id, + x86ms->oem_table_id); + } else if (object_dynamic_cast(OBJECT(iommu), TYPE_VIRTIO_IOMMU_PCI)) { + PCIDevice *pdev = PCI_DEVICE(iommu); + + acpi_add_table(table_offsets, tables_blob); + build_viot(machine, tables_blob, tables->linker, pci_get_bdf(pdev), + x86ms->oem_id, x86ms->oem_table_id); } if (machine->nvdimms_state->is_enabled) { nvdimm_build_acpi(table_offsets, tables_blob, tables->linker, diff --git a/hw/i386/amd_iommu.c b/hw/i386/amd_iommu.c index 9242a0d3ed..91fe34ae58 100644 --- a/hw/i386/amd_iommu.c +++ b/hw/i386/amd_iommu.c @@ -1538,7 +1538,6 @@ static void amdvi_sysbus_realize(DeviceState *dev, Error **errp) { int ret = 0; AMDVIState *s = AMD_IOMMU_DEVICE(dev); - X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(dev); MachineState *ms = MACHINE(qdev_get_machine()); PCMachineState *pcms = PC_MACHINE(ms); X86MachineState *x86ms = X86_MACHINE(ms); @@ -1548,7 +1547,6 @@ static void amdvi_sysbus_realize(DeviceState *dev, Error **errp) amdvi_uint64_equal, g_free, g_free); /* This device should take care of IOMMU PCI properties */ - x86_iommu->type = TYPE_AMD; if (!qdev_realize(DEVICE(&s->pci), &bus->qbus, errp)) { return; } diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index 75f075547f..c27b20090e 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -3806,9 +3806,6 @@ static void vtd_realize(DeviceState *dev, Error **errp) X86MachineState *x86ms = X86_MACHINE(ms); PCIBus *bus = pcms->bus; IntelIOMMUState *s = INTEL_IOMMU_DEVICE(dev); - X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(dev); - - x86_iommu->type = TYPE_INTEL; if (!vtd_decide_config(s, errp)) { return; diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 86223acfd3..e99017e662 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -83,6 +83,7 @@ #include "hw/i386/intel_iommu.h" #include "hw/net/ne2000-isa.h" #include "standard-headers/asm-x86/bootparam.h" +#include "hw/virtio/virtio-iommu.h" #include "hw/virtio/virtio-pmem-pci.h" #include "hw/virtio/virtio-mem-pci.h" #include "hw/mem/memory-device.h" @@ -1330,6 +1331,27 @@ static void pc_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev, } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { pc_virtio_md_pci_pre_plug(hotplug_dev, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) { + /* Declare the APIC range as the reserved MSI region */ + char *resv_prop_str = g_strdup_printf("0xfee00000:0xfeefffff:%d", + VIRTIO_IOMMU_RESV_MEM_T_MSI); + + object_property_set_uint(OBJECT(dev), "len-reserved-regions", 1, errp); + object_property_set_str(OBJECT(dev), "reserved-regions[0]", + resv_prop_str, errp); + g_free(resv_prop_str); + } + + if (object_dynamic_cast(OBJECT(dev), TYPE_X86_IOMMU_DEVICE) || + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) { + PCMachineState *pcms = PC_MACHINE(hotplug_dev); + + if (pcms->iommu) { + error_setg(errp, "QEMU does not support multiple vIOMMUs " + "for x86 yet."); + return; + } + pcms->iommu = dev; } } @@ -1384,7 +1406,9 @@ static HotplugHandler *pc_get_hotplug_handler(MachineState *machine, if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) || object_dynamic_cast(OBJECT(dev), TYPE_CPU) || object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || - object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI) || + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI) || + object_dynamic_cast(OBJECT(dev), TYPE_X86_IOMMU_DEVICE)) { return HOTPLUG_HANDLER(machine); } diff --git a/hw/i386/vmmouse.c b/hw/i386/vmmouse.c index df4798f502..3d66368286 100644 --- a/hw/i386/vmmouse.c +++ b/hw/i386/vmmouse.c @@ -158,6 +158,7 @@ static void vmmouse_read_id(VMMouseState *s) s->queue[s->nb_queue++] = VMMOUSE_VERSION; s->status = 0; + vmmouse_update_handler(s, s->absolute); } static void vmmouse_request_relative(VMMouseState *s) diff --git a/hw/i386/x86-iommu-stub.c b/hw/i386/x86-iommu-stub.c index c5ba077f9d..781b5ff922 100644 --- a/hw/i386/x86-iommu-stub.c +++ b/hw/i386/x86-iommu-stub.c @@ -36,8 +36,3 @@ bool x86_iommu_ir_supported(X86IOMMUState *s) { return false; } - -IommuType x86_iommu_get_type(void) -{ - abort(); -} diff --git a/hw/i386/x86-iommu.c b/hw/i386/x86-iommu.c index 86ad03972e..01d11325a6 100644 --- a/hw/i386/x86-iommu.c +++ b/hw/i386/x86-iommu.c @@ -77,30 +77,17 @@ void x86_iommu_irq_to_msi_message(X86IOMMUIrq *irq, MSIMessage *msg_out) msg_out->data = msg.msi_data; } -/* Default X86 IOMMU device */ -static X86IOMMUState *x86_iommu_default = NULL; - -static void x86_iommu_set_default(X86IOMMUState *x86_iommu) -{ - assert(x86_iommu); - - if (x86_iommu_default) { - error_report("QEMU does not support multiple vIOMMUs " - "for x86 yet."); - exit(1); - } - - x86_iommu_default = x86_iommu; -} - X86IOMMUState *x86_iommu_get_default(void) { - return x86_iommu_default; -} + MachineState *ms = MACHINE(qdev_get_machine()); + PCMachineState *pcms = + PC_MACHINE(object_dynamic_cast(OBJECT(ms), TYPE_PC_MACHINE)); -IommuType x86_iommu_get_type(void) -{ - return x86_iommu_default->type; + if (pcms && + object_dynamic_cast(OBJECT(pcms->iommu), TYPE_X86_IOMMU_DEVICE)) { + return X86_IOMMU_DEVICE(pcms->iommu); + } + return NULL; } static void x86_iommu_realize(DeviceState *dev, Error **errp) @@ -136,8 +123,6 @@ static void x86_iommu_realize(DeviceState *dev, Error **errp) if (x86_class->realize) { x86_class->realize(dev, errp); } - - x86_iommu_set_default(X86_IOMMU_DEVICE(dev)); } static Property x86_iommu_properties[] = { diff --git a/hw/i386/xen/xen-hvm.c b/hw/i386/xen/xen-hvm.c index e3d3d5cf89..482be95415 100644 --- a/hw/i386/xen/xen-hvm.c +++ b/hw/i386/xen/xen-hvm.c @@ -1613,8 +1613,8 @@ void xen_hvm_modified_memory(ram_addr_t start, ram_addr_t length) void qmp_xen_set_global_dirty_log(bool enable, Error **errp) { if (enable) { - memory_global_dirty_log_start(); + memory_global_dirty_log_start(GLOBAL_DIRTY_MIGRATION); } else { - memory_global_dirty_log_stop(); + memory_global_dirty_log_stop(GLOBAL_DIRTY_MIGRATION); } } diff --git a/hw/ide/core.c b/hw/ide/core.c index fd69ca3167..e28f8aad61 100644 --- a/hw/ide/core.c +++ b/hw/ide/core.c @@ -98,8 +98,12 @@ static void put_le16(uint16_t *p, unsigned int v) static void ide_identify_size(IDEState *s) { uint16_t *p = (uint16_t *)s->identify_data; - put_le16(p + 60, s->nb_sectors); - put_le16(p + 61, s->nb_sectors >> 16); + int64_t nb_sectors_lba28 = s->nb_sectors; + if (nb_sectors_lba28 >= 1 << 28) { + nb_sectors_lba28 = (1 << 28) - 1; + } + put_le16(p + 60, nb_sectors_lba28); + put_le16(p + 61, nb_sectors_lba28 >> 16); put_le16(p + 100, s->nb_sectors); put_le16(p + 101, s->nb_sectors >> 16); put_le16(p + 102, s->nb_sectors >> 32); diff --git a/hw/pci/pci.c b/hw/pci/pci.c index 186758ee11..4a84e478ce 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -1654,11 +1654,9 @@ static const pci_class_desc pci_class_descriptions[] = { 0, NULL} }; -static void pci_for_each_device_under_bus_reverse(PCIBus *bus, - void (*fn)(PCIBus *b, - PCIDevice *d, - void *opaque), - void *opaque) +void pci_for_each_device_under_bus_reverse(PCIBus *bus, + pci_bus_dev_fn fn, + void *opaque) { PCIDevice *d; int devfn; @@ -1672,8 +1670,7 @@ static void pci_for_each_device_under_bus_reverse(PCIBus *bus, } void pci_for_each_device_reverse(PCIBus *bus, int bus_num, - void (*fn)(PCIBus *b, PCIDevice *d, void *opaque), - void *opaque) + pci_bus_dev_fn fn, void *opaque) { bus = pci_find_bus_nr(bus, bus_num); @@ -1682,10 +1679,8 @@ void pci_for_each_device_reverse(PCIBus *bus, int bus_num, } } -static void pci_for_each_device_under_bus(PCIBus *bus, - void (*fn)(PCIBus *b, PCIDevice *d, - void *opaque), - void *opaque) +void pci_for_each_device_under_bus(PCIBus *bus, + pci_bus_dev_fn fn, void *opaque) { PCIDevice *d; int devfn; @@ -1699,8 +1694,7 @@ static void pci_for_each_device_under_bus(PCIBus *bus, } void pci_for_each_device(PCIBus *bus, int bus_num, - void (*fn)(PCIBus *b, PCIDevice *d, void *opaque), - void *opaque) + pci_bus_dev_fn fn, void *opaque) { bus = pci_find_bus_nr(bus, bus_num); @@ -2078,10 +2072,8 @@ static PCIBus *pci_find_bus_nr(PCIBus *bus, int bus_num) return NULL; } -void pci_for_each_bus_depth_first(PCIBus *bus, - void *(*begin)(PCIBus *bus, void *parent_state), - void (*end)(PCIBus *bus, void *state), - void *parent_state) +void pci_for_each_bus_depth_first(PCIBus *bus, pci_bus_ret_fn begin, + pci_bus_fn end, void *parent_state) { PCIBus *sec; void *state; diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c index 6e95d82903..914a9bf3d1 100644 --- a/hw/pci/pcie.c +++ b/hw/pci/pcie.c @@ -694,9 +694,7 @@ void pcie_cap_slot_write_config(PCIDevice *dev, (!(old_slt_ctl & PCI_EXP_SLTCTL_PCC) || (old_slt_ctl & PCI_EXP_SLTCTL_PIC_OFF) != PCI_EXP_SLTCTL_PIC_OFF)) { PCIBus *sec_bus = pci_bridge_get_sec_bus(PCI_BRIDGE(dev)); - pci_for_each_device(sec_bus, pci_bus_num(sec_bus), - pcie_unplug_device, NULL); - + pci_for_each_device_under_bus(sec_bus, pcie_unplug_device, NULL); pci_word_test_and_clear_mask(exp_cap + PCI_EXP_SLTSTA, PCI_EXP_SLTSTA_PDS); if (dev->cap_present & QEMU_PCIE_LNKSTA_DLLLA || diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c index 7430bd6314..5bfd4aa9e5 100644 --- a/hw/ppc/spapr_pci.c +++ b/hw/ppc/spapr_pci.c @@ -1317,8 +1317,7 @@ static int spapr_dt_pci_bus(SpaprPhbState *sphb, PCIBus *bus, RESOURCE_CELLS_SIZE)); assert(bus); - pci_for_each_device_reverse(bus, pci_bus_num(bus), - spapr_dt_pci_device_cb, &cbinfo); + pci_for_each_device_under_bus_reverse(bus, spapr_dt_pci_device_cb, &cbinfo); if (cbinfo.err) { return cbinfo.err; } @@ -2306,8 +2305,8 @@ static void spapr_phb_pci_enumerate_bridge(PCIBus *bus, PCIDevice *pdev, return; } - pci_for_each_device(sec_bus, pci_bus_num(sec_bus), - spapr_phb_pci_enumerate_bridge, bus_no); + pci_for_each_device_under_bus(sec_bus, spapr_phb_pci_enumerate_bridge, + bus_no); pci_default_write_config(pdev, PCI_SUBORDINATE_BUS, *bus_no, 1); } @@ -2316,9 +2315,8 @@ static void spapr_phb_pci_enumerate(SpaprPhbState *phb) PCIBus *bus = PCI_HOST_BRIDGE(phb)->bus; unsigned int bus_no = 0; - pci_for_each_device(bus, pci_bus_num(bus), - spapr_phb_pci_enumerate_bridge, - &bus_no); + pci_for_each_device_under_bus(bus, spapr_phb_pci_enumerate_bridge, + &bus_no); } diff --git a/hw/ppc/spapr_pci_nvlink2.c b/hw/ppc/spapr_pci_nvlink2.c index 8ef9b40a18..7fb0cf4d04 100644 --- a/hw/ppc/spapr_pci_nvlink2.c +++ b/hw/ppc/spapr_pci_nvlink2.c @@ -164,8 +164,7 @@ static void spapr_phb_pci_collect_nvgpu(PCIBus *bus, PCIDevice *pdev, return; } - pci_for_each_device(sec_bus, pci_bus_num(sec_bus), - spapr_phb_pci_collect_nvgpu, opaque); + pci_for_each_device_under_bus(sec_bus, spapr_phb_pci_collect_nvgpu, opaque); } void spapr_phb_nvgpu_setup(SpaprPhbState *sphb, Error **errp) @@ -183,8 +182,8 @@ void spapr_phb_nvgpu_setup(SpaprPhbState *sphb, Error **errp) sphb->nvgpus->nv2_atsd_current = sphb->nv2_atsd_win_addr; bus = PCI_HOST_BRIDGE(sphb)->bus; - pci_for_each_device(bus, pci_bus_num(bus), - spapr_phb_pci_collect_nvgpu, sphb->nvgpus); + pci_for_each_device_under_bus(bus, spapr_phb_pci_collect_nvgpu, + sphb->nvgpus); if (sphb->nvgpus->err) { error_propagate(errp, sphb->nvgpus->err); diff --git a/hw/ppc/spapr_pci_vfio.c b/hw/ppc/spapr_pci_vfio.c index f3b37df8ea..2a76b4e0b5 100644 --- a/hw/ppc/spapr_pci_vfio.c +++ b/hw/ppc/spapr_pci_vfio.c @@ -164,8 +164,8 @@ static void spapr_phb_vfio_eeh_clear_dev_msix(PCIBus *bus, static void spapr_phb_vfio_eeh_clear_bus_msix(PCIBus *bus, void *opaque) { - pci_for_each_device(bus, pci_bus_num(bus), - spapr_phb_vfio_eeh_clear_dev_msix, NULL); + pci_for_each_device_under_bus(bus, spapr_phb_vfio_eeh_clear_dev_msix, + NULL); } static void spapr_phb_vfio_eeh_pre_reset(SpaprPhbState *sphb) diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c index 6fafffb029..1b51a72838 100644 --- a/hw/s390x/s390-pci-bus.c +++ b/hw/s390x/s390-pci-bus.c @@ -1163,8 +1163,7 @@ static void s390_pci_enumerate_bridge(PCIBus *bus, PCIDevice *pdev, } /* Assign numbers to all child bridges. The last is the highest number. */ - pci_for_each_device(sec_bus, pci_bus_num(sec_bus), - s390_pci_enumerate_bridge, s); + pci_for_each_device_under_bus(sec_bus, s390_pci_enumerate_bridge, s); pci_default_write_config(pdev, PCI_SUBORDINATE_BUS, s->bus_no, 1); } @@ -1193,7 +1192,7 @@ static void s390_pcihost_reset(DeviceState *dev) * on every system reset, we also have to reassign numbers. */ s->bus_no = 0; - pci_for_each_device(bus, pci_bus_num(bus), s390_pci_enumerate_bridge, s); + pci_for_each_device_under_bus(bus, s390_pci_enumerate_bridge, s); } static void s390_pcihost_class_init(ObjectClass *klass, void *data) diff --git a/hw/usb/hcd-uhci.c b/hw/usb/hcd-uhci.c index 0cb02a6432..d1b5657d72 100644 --- a/hw/usb/hcd-uhci.c +++ b/hw/usb/hcd-uhci.c @@ -31,6 +31,7 @@ #include "hw/usb/uhci-regs.h" #include "migration/vmstate.h" #include "hw/pci/pci.h" +#include "hw/irq.h" #include "hw/qdev-properties.h" #include "qapi/error.h" #include "qemu/timer.h" @@ -290,7 +291,7 @@ static UHCIAsync *uhci_async_find_td(UHCIState *s, uint32_t td_addr) static void uhci_update_irq(UHCIState *s) { - int level; + int level = 0; if (((s->status2 & 1) && (s->intr & (1 << 2))) || ((s->status2 & 2) && (s->intr & (1 << 3))) || ((s->status & UHCI_STS_USBERR) && (s->intr & (1 << 0))) || @@ -298,10 +299,8 @@ static void uhci_update_irq(UHCIState *s) (s->status & UHCI_STS_HSERR) || (s->status & UHCI_STS_HCPERR)) { level = 1; - } else { - level = 0; } - pci_set_irq(&s->dev, level); + qemu_set_irq(s->irq, level); } static void uhci_reset(DeviceState *dev) @@ -1170,9 +1169,9 @@ void usb_uhci_common_realize(PCIDevice *dev, Error **errp) pci_conf[PCI_CLASS_PROG] = 0x00; /* TODO: reset value should be 0. */ - pci_conf[USB_SBRN] = USB_RELEASE_1; // release number - + pci_conf[USB_SBRN] = USB_RELEASE_1; /* release number */ pci_config_set_interrupt_pin(pci_conf, u->info.irq_pin + 1); + s->irq = pci_allocate_irq(dev); if (s->masterbus) { USBPort *ports[NB_PORTS]; @@ -1285,6 +1284,9 @@ void uhci_data_class_init(ObjectClass *klass, void *data) } else { device_class_set_props(dc, uhci_properties_standalone); } + if (info->notuser) { + dc->user_creatable = false; + } u->info = *info; } diff --git a/hw/usb/hcd-uhci.h b/hw/usb/hcd-uhci.h index e61d8fcb19..c85ab7868e 100644 --- a/hw/usb/hcd-uhci.h +++ b/hw/usb/hcd-uhci.h @@ -60,7 +60,7 @@ typedef struct UHCIState { uint32_t frame_bandwidth; bool completions_only; UHCIPort ports[NB_PORTS]; - + qemu_irq irq; /* Interrupts that should be raised at the end of the current frame. */ uint32_t pending_int_mask; @@ -85,6 +85,7 @@ typedef struct UHCIInfo { uint8_t irq_pin; void (*realize)(PCIDevice *dev, Error **errp); bool unplug; + bool notuser; /* disallow user_creatable */ } UHCIInfo; void uhci_data_class_init(ObjectClass *klass, void *data); diff --git a/hw/usb/vt82c686-uhci-pci.c b/hw/usb/vt82c686-uhci-pci.c index b109c21603..0bf2b72ff0 100644 --- a/hw/usb/vt82c686-uhci-pci.c +++ b/hw/usb/vt82c686-uhci-pci.c @@ -1,6 +1,17 @@ #include "qemu/osdep.h" +#include "hw/irq.h" +#include "hw/isa/vt82c686.h" #include "hcd-uhci.h" +static void uhci_isa_set_irq(void *opaque, int irq_num, int level) +{ + UHCIState *s = opaque; + uint8_t irq = pci_get_byte(s->dev.config + PCI_INTERRUPT_LINE); + if (irq > 0 && irq < 15) { + via_isa_set_irq(pci_get_function_0(&s->dev), irq, level); + } +} + static void usb_uhci_vt82c686b_realize(PCIDevice *dev, Error **errp) { UHCIState *s = UHCI(dev); @@ -14,6 +25,8 @@ static void usb_uhci_vt82c686b_realize(PCIDevice *dev, Error **errp) pci_set_long(pci_conf + 0xc0, 0x00002000); usb_uhci_common_realize(dev, errp); + object_unref(s->irq); + s->irq = qemu_allocate_irq(uhci_isa_set_irq, s, 0); } static UHCIInfo uhci_info[] = { @@ -25,6 +38,8 @@ static UHCIInfo uhci_info[] = { .irq_pin = 3, .realize = usb_uhci_vt82c686b_realize, .unplug = true, + /* Reason: only works as USB function of VT82xx superio chips */ + .notuser = true, } }; diff --git a/hw/vfio/common.c b/hw/vfio/common.c index a784b219e6..dd387b0d39 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -893,6 +893,13 @@ static void vfio_listener_region_add(MemoryListener *listener, llend = int128_and(llend, int128_exts64(qemu_real_host_page_mask)); if (int128_ge(int128_make64(iova), llend)) { + if (memory_region_is_ram_device(section->mr)) { + trace_vfio_listener_region_add_no_dma_map( + memory_region_name(section->mr), + section->offset_within_address_space, + int128_getlo(section->size), + qemu_real_host_page_size); + } return; } end = int128_get64(int128_sub(llend, int128_one())); diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 5cdf1d4298..7b45353ce2 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -2453,7 +2453,12 @@ static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f) { VFIOPCIDevice *vdev = container_of(vbasedev, VFIOPCIDevice, vbasedev); PCIDevice *pdev = &vdev->pdev; - int ret; + pcibus_t old_addr[PCI_NUM_REGIONS - 1]; + int bar, ret; + + for (bar = 0; bar < PCI_ROM_SLOT; bar++) { + old_addr[bar] = pdev->io_regions[bar].addr; + } ret = vmstate_load_state(f, &vmstate_vfio_pci_config, vdev, 1); if (ret) { @@ -2463,6 +2468,18 @@ static int vfio_pci_load_config(VFIODevice *vbasedev, QEMUFile *f) vfio_pci_write_config(pdev, PCI_COMMAND, pci_get_word(pdev->config + PCI_COMMAND), 2); + for (bar = 0; bar < PCI_ROM_SLOT; bar++) { + /* + * The address may not be changed in some scenarios + * (e.g. the VF driver isn't loaded in VM). + */ + if (old_addr[bar] != pdev->io_regions[bar].addr && + vdev->bars[bar].region.size > 0 && + vdev->bars[bar].region.size < qemu_real_host_page_size) { + vfio_sub_page_bar_update_mapping(pdev, bar); + } + } + if (msi_enabled(pdev)) { vfio_msi_enable(vdev); } else if (msix_enabled(pdev)) { diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c index 12661fd5b1..0d8051426c 100644 --- a/hw/virtio/vhost-vdpa.c +++ b/hw/virtio/vhost-vdpa.c @@ -331,6 +331,17 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) struct vhost_vdpa *v; assert(dev->vhost_ops->backend_type == VHOST_BACKEND_TYPE_VDPA); trace_vhost_vdpa_init(dev, opaque); + int ret; + + /* + * Similar to VFIO, we end up pinning all guest memory and have to + * disable discarding of RAM. + */ + ret = ram_block_discard_disable(true); + if (ret) { + error_report("Cannot set discarding of RAM broken"); + return ret; + } v = opaque; v->dev = dev; @@ -442,6 +453,8 @@ static int vhost_vdpa_cleanup(struct vhost_dev *dev) memory_listener_unregister(&v->listener); dev->opaque = NULL; + ram_block_discard_disable(false); + return 0; } diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c index df91e454b2..d5a578142b 100644 --- a/hw/virtio/virtio-mem.c +++ b/hw/virtio/virtio-mem.c @@ -228,6 +228,38 @@ static int virtio_mem_for_each_plugged_section(const VirtIOMEM *vmem, return ret; } +static int virtio_mem_for_each_unplugged_section(const VirtIOMEM *vmem, + MemoryRegionSection *s, + void *arg, + virtio_mem_section_cb cb) +{ + unsigned long first_bit, last_bit; + uint64_t offset, size; + int ret = 0; + + first_bit = s->offset_within_region / vmem->bitmap_size; + first_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size, first_bit); + while (first_bit < vmem->bitmap_size) { + MemoryRegionSection tmp = *s; + + offset = first_bit * vmem->block_size; + last_bit = find_next_bit(vmem->bitmap, vmem->bitmap_size, + first_bit + 1) - 1; + size = (last_bit - first_bit + 1) * vmem->block_size; + + if (!virito_mem_intersect_memory_section(&tmp, offset, size)) { + break; + } + ret = cb(&tmp, arg); + if (ret) { + break; + } + first_bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size, + last_bit + 2); + } + return ret; +} + static int virtio_mem_notify_populate_cb(MemoryRegionSection *s, void *arg) { RamDiscardListener *rdl = arg; @@ -744,7 +776,6 @@ static void virtio_mem_device_realize(DeviceState *dev, Error **errp) host_memory_backend_set_mapped(vmem->memdev, true); vmstate_register_ram(&vmem->memdev->mr, DEVICE(vmem)); qemu_register_reset(virtio_mem_system_reset, vmem); - precopy_add_notifier(&vmem->precopy_notifier); /* * Set ourselves as RamDiscardManager before the plug handler maps the @@ -764,7 +795,6 @@ static void virtio_mem_device_unrealize(DeviceState *dev) * found via an address space anymore. Unset ourselves. */ memory_region_set_ram_discard_manager(&vmem->memdev->mr, NULL); - precopy_remove_notifier(&vmem->precopy_notifier); qemu_unregister_reset(virtio_mem_system_reset, vmem); vmstate_unregister_ram(&vmem->memdev->mr, DEVICE(vmem)); host_memory_backend_set_mapped(vmem->memdev, false); @@ -1057,43 +1087,11 @@ static void virtio_mem_set_block_size(Object *obj, Visitor *v, const char *name, vmem->block_size = value; } -static int virtio_mem_precopy_exclude_range_cb(const VirtIOMEM *vmem, void *arg, - uint64_t offset, uint64_t size) -{ - void * const host = qemu_ram_get_host_addr(vmem->memdev->mr.ram_block); - - qemu_guest_free_page_hint(host + offset, size); - return 0; -} - -static void virtio_mem_precopy_exclude_unplugged(VirtIOMEM *vmem) -{ - virtio_mem_for_each_unplugged_range(vmem, NULL, - virtio_mem_precopy_exclude_range_cb); -} - -static int virtio_mem_precopy_notify(NotifierWithReturn *n, void *data) -{ - VirtIOMEM *vmem = container_of(n, VirtIOMEM, precopy_notifier); - PrecopyNotifyData *pnd = data; - - switch (pnd->reason) { - case PRECOPY_NOTIFY_AFTER_BITMAP_SYNC: - virtio_mem_precopy_exclude_unplugged(vmem); - break; - default: - break; - } - - return 0; -} - static void virtio_mem_instance_init(Object *obj) { VirtIOMEM *vmem = VIRTIO_MEM(obj); notifier_list_init(&vmem->size_change_notifiers); - vmem->precopy_notifier.notify = virtio_mem_precopy_notify; QLIST_INIT(&vmem->rdl_list); object_property_add(obj, VIRTIO_MEM_SIZE_PROP, "size", virtio_mem_get_size, @@ -1170,6 +1168,31 @@ static int virtio_mem_rdm_replay_populated(const RamDiscardManager *rdm, virtio_mem_rdm_replay_populated_cb); } +static int virtio_mem_rdm_replay_discarded_cb(MemoryRegionSection *s, + void *arg) +{ + struct VirtIOMEMReplayData *data = arg; + + ((ReplayRamDiscard)data->fn)(s, data->opaque); + return 0; +} + +static void virtio_mem_rdm_replay_discarded(const RamDiscardManager *rdm, + MemoryRegionSection *s, + ReplayRamDiscard replay_fn, + void *opaque) +{ + const VirtIOMEM *vmem = VIRTIO_MEM(rdm); + struct VirtIOMEMReplayData data = { + .fn = replay_fn, + .opaque = opaque, + }; + + g_assert(s->mr == &vmem->memdev->mr); + virtio_mem_for_each_unplugged_section(vmem, s, &data, + virtio_mem_rdm_replay_discarded_cb); +} + static void virtio_mem_rdm_register_listener(RamDiscardManager *rdm, RamDiscardListener *rdl, MemoryRegionSection *s) @@ -1234,6 +1257,7 @@ static void virtio_mem_class_init(ObjectClass *klass, void *data) rdmc->get_min_granularity = virtio_mem_rdm_get_min_granularity; rdmc->is_populated = virtio_mem_rdm_is_populated; rdmc->replay_populated = virtio_mem_rdm_replay_populated; + rdmc->replay_discarded = virtio_mem_rdm_replay_discarded; rdmc->register_listener = virtio_mem_rdm_register_listener; rdmc->unregister_listener = virtio_mem_rdm_unregister_listener; } diff --git a/hw/xen/xen_pt.c b/hw/xen/xen_pt.c index ca0a98187e..027190fa44 100644 --- a/hw/xen/xen_pt.c +++ b/hw/xen/xen_pt.c @@ -615,8 +615,8 @@ static void xen_pt_region_update(XenPCIPassthroughState *s, } args.type = d->io_regions[bar].type; - pci_for_each_device(pci_get_bus(d), pci_dev_bus_num(d), - xen_pt_check_bar_overlap, &args); + pci_for_each_device_under_bus(pci_get_bus(d), + xen_pt_check_bar_overlap, &args); if (args.rc) { XEN_PT_WARN(d, "Region: %d (addr: 0x%"FMT_PCIBUS ", len: 0x%"FMT_PCIBUS") is overlapped.\n", |