diff options
Diffstat (limited to 'hw')
42 files changed, 1151 insertions, 714 deletions
diff --git a/hw/arm/meson.build b/hw/arm/meson.build index 5098795..d90be8f 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -8,7 +8,7 @@ arm_common_ss.add(when: 'CONFIG_HIGHBANK', if_true: files('highbank.c')) arm_common_ss.add(when: 'CONFIG_INTEGRATOR', if_true: files('integratorcp.c')) arm_common_ss.add(when: 'CONFIG_MICROBIT', if_true: files('microbit.c')) arm_common_ss.add(when: 'CONFIG_MPS3R', if_true: files('mps3r.c')) -arm_common_ss.add(when: 'CONFIG_MUSICPAL', if_true: [pixman, files('musicpal.c')]) +arm_common_ss.add(when: 'CONFIG_MUSICPAL', if_true: [files('musicpal.c')]) arm_common_ss.add(when: 'CONFIG_NETDUINOPLUS2', if_true: files('netduinoplus2.c')) arm_common_ss.add(when: 'CONFIG_OLIMEX_STM32_H405', if_true: files('olimex-stm32-h405.c')) arm_common_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx.c', 'npcm7xx_boards.c')) @@ -79,7 +79,7 @@ arm_common_ss.add(when: 'CONFIG_SX1', if_true: files('omap_sx1.c')) arm_common_ss.add(when: 'CONFIG_VERSATILE', if_true: files('versatilepb.c')) arm_common_ss.add(when: 'CONFIG_VEXPRESS', if_true: files('vexpress.c')) -arm_common_ss.add(fdt, files('boot.c')) +arm_common_ss.add(files('boot.c')) hw_arch += {'arm': arm_ss} hw_common_arch += {'arm': arm_common_ss} diff --git a/hw/core/loader.c b/hw/core/loader.c index b792a54..e7056ba 100644 --- a/hw/core/loader.c +++ b/hw/core/loader.c @@ -1333,20 +1333,6 @@ void rom_set_fw(FWCfgState *f) fw_cfg = f; } -void rom_set_order_override(int order) -{ - if (!fw_cfg) - return; - fw_cfg_set_order_override(fw_cfg, order); -} - -void rom_reset_order_override(void) -{ - if (!fw_cfg) - return; - fw_cfg_reset_order_override(fw_cfg); -} - void rom_transaction_begin(void) { Rom *rom; diff --git a/hw/core/machine.c b/hw/core/machine.c index c3f3a50..e869821 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -285,24 +285,6 @@ GlobalProperty hw_compat_2_6[] = { }; const size_t hw_compat_2_6_len = G_N_ELEMENTS(hw_compat_2_6); -GlobalProperty hw_compat_2_5[] = { - { "isa-fdc", "fallback", "144" }, - { "pvscsi", "x-old-pci-configuration", "on" }, - { "pvscsi", "x-disable-pcie", "on" }, - { "vmxnet3", "x-old-msi-offsets", "on" }, - { "vmxnet3", "x-disable-pcie", "on" }, -}; -const size_t hw_compat_2_5_len = G_N_ELEMENTS(hw_compat_2_5); - -GlobalProperty hw_compat_2_4[] = { - { "e1000", "extra_mac_registers", "off" }, - { "virtio-pci", "x-disable-pcie", "on" }, - { "virtio-pci", "migrate-extra", "off" }, - { "fw_cfg_mem", "dma_enabled", "off" }, - { "fw_cfg_io", "dma_enabled", "off" } -}; -const size_t hw_compat_2_4_len = G_N_ELEMENTS(hw_compat_2_4); - MachineState *current_machine; static char *machine_get_kernel(Object *obj, Error **errp) diff --git a/hw/core/meson.build b/hw/core/meson.build index 547de65..b5a545a 100644 --- a/hw/core/meson.build +++ b/hw/core/meson.build @@ -26,7 +26,7 @@ system_ss.add(when: 'CONFIG_XILINX_AXI', if_true: files('stream.c')) system_ss.add(when: 'CONFIG_PLATFORM_BUS', if_true: files('sysbus-fdt.c')) system_ss.add(when: 'CONFIG_EIF', if_true: [files('eif.c'), zlib, libcbor, gnutls]) -libsystem_ss.add(files( +system_ss.add(files( 'cpu-system.c', 'fw-path-provider.c', 'gpio.c', @@ -46,7 +46,7 @@ libsystem_ss.add(files( 'vm-change-state-handler.c', 'clock-vmstate.c', )) -libuser_ss.add(files( +user_ss.add(files( 'cpu-user.c', 'qdev-user.c', )) diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c index 8e11e63..24e145d 100644 --- a/hw/core/qdev-properties-system.c +++ b/hw/core/qdev-properties-system.c @@ -145,6 +145,7 @@ static void set_drive_helper(Object *obj, Visitor *v, const char *name, if (ctx != bdrv_get_aio_context(bs)) { error_setg(errp, "Different aio context is not supported for new " "node"); + return; } blk_replace_bs(blk, bs, errp); diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig index d34ce07..eb65bda 100644 --- a/hw/i386/Kconfig +++ b/hw/i386/Kconfig @@ -10,6 +10,11 @@ config SGX bool depends on KVM +config TDX + bool + select X86_FW_OVMF + depends on KVM + config PC bool imply APPLESMC @@ -26,6 +31,7 @@ config PC imply QXL imply SEV imply SGX + imply TDX imply TEST_DEVICES imply TPM_CRB imply TPM_TIS_ISA diff --git a/hw/i386/amd_iommu.c b/hw/i386/amd_iommu.c index 0775c8f..963aa24 100644 --- a/hw/i386/amd_iommu.c +++ b/hw/i386/amd_iommu.c @@ -1426,7 +1426,6 @@ static AddressSpace *amdvi_host_dma_iommu(PCIBus *bus, void *opaque, int devfn) AMDVIState *s = opaque; AMDVIAddressSpace **iommu_as, *amdvi_dev_as; int bus_num = pci_bus_num(bus); - X86IOMMUState *x86_iommu = X86_IOMMU_DEVICE(s); iommu_as = s->address_spaces[bus_num]; @@ -1486,15 +1485,8 @@ static AddressSpace *amdvi_host_dma_iommu(PCIBus *bus, void *opaque, int devfn) AMDVI_INT_ADDR_FIRST, &amdvi_dev_as->iommu_ir, 1); - if (!x86_iommu->pt_supported) { - memory_region_set_enabled(&amdvi_dev_as->iommu_nodma, false); - memory_region_set_enabled(MEMORY_REGION(&amdvi_dev_as->iommu), - true); - } else { - memory_region_set_enabled(MEMORY_REGION(&amdvi_dev_as->iommu), - false); - memory_region_set_enabled(&amdvi_dev_as->iommu_nodma, true); - } + memory_region_set_enabled(&amdvi_dev_as->iommu_nodma, false); + memory_region_set_enabled(MEMORY_REGION(&amdvi_dev_as->iommu), true); } return &iommu_as[devfn]->as; } @@ -1723,6 +1715,14 @@ static void amdvi_sysbus_realize(DeviceState *dev, Error **errp) exit(EXIT_FAILURE); } + if (s->xtsup) { + if (kvm_irqchip_is_split() && !kvm_enable_x2apic()) { + error_report("AMD IOMMU xtsup=on requires x2APIC support on " + "the KVM side"); + exit(EXIT_FAILURE); + } + } + pci_setup_iommu(bus, &amdvi_iommu_ops, s); amdvi_init(s); } diff --git a/hw/i386/kvm/apic.c b/hw/i386/kvm/apic.c index 39035db..1be9bfe 100644 --- a/hw/i386/kvm/apic.c +++ b/hw/i386/kvm/apic.c @@ -17,6 +17,7 @@ #include "system/hw_accel.h" #include "system/kvm.h" #include "kvm/kvm_i386.h" +#include "kvm/tdx.h" static inline void kvm_apic_set_reg(struct kvm_lapic_state *kapic, int reg_id, uint32_t val) @@ -141,6 +142,10 @@ static void kvm_apic_put(CPUState *cs, run_on_cpu_data data) struct kvm_lapic_state kapic; int ret; + if (is_tdx_vm()) { + return; + } + kvm_put_apicbase(s->cpu, s->apicbase); kvm_put_apic_state(s, &kapic); diff --git a/hw/i386/meson.build b/hw/i386/meson.build index 10bdfde..7896f34 100644 --- a/hw/i386/meson.build +++ b/hw/i386/meson.build @@ -32,6 +32,7 @@ i386_ss.add(when: 'CONFIG_PC', if_true: files( 'port92.c')) i386_ss.add(when: 'CONFIG_X86_FW_OVMF', if_true: files('pc_sysfw_ovmf.c'), if_false: files('pc_sysfw_ovmf-stubs.c')) +i386_ss.add(when: 'CONFIG_TDX', if_true: files('tdvf.c', 'tdvf-hob.c')) subdir('kvm') subdir('xen') diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 7065615..b211633 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -44,6 +44,7 @@ #include "system/xen.h" #include "system/reset.h" #include "kvm/kvm_i386.h" +#include "kvm/tdx.h" #include "hw/xen/xen.h" #include "qobject/qlist.h" #include "qemu/error-report.h" @@ -259,28 +260,6 @@ GlobalProperty pc_compat_2_6[] = { }; const size_t pc_compat_2_6_len = G_N_ELEMENTS(pc_compat_2_6); -GlobalProperty pc_compat_2_5[] = {}; -const size_t pc_compat_2_5_len = G_N_ELEMENTS(pc_compat_2_5); - -GlobalProperty pc_compat_2_4[] = { - PC_CPU_MODEL_IDS("2.4.0") - { "Haswell-" TYPE_X86_CPU, "abm", "off" }, - { "Haswell-noTSX-" TYPE_X86_CPU, "abm", "off" }, - { "Broadwell-" TYPE_X86_CPU, "abm", "off" }, - { "Broadwell-noTSX-" TYPE_X86_CPU, "abm", "off" }, - { "host" "-" TYPE_X86_CPU, "host-cache-info", "on" }, - { TYPE_X86_CPU, "check", "off" }, - { "qemu64" "-" TYPE_X86_CPU, "sse4a", "on" }, - { "qemu64" "-" TYPE_X86_CPU, "abm", "on" }, - { "qemu64" "-" TYPE_X86_CPU, "popcnt", "on" }, - { "qemu32" "-" TYPE_X86_CPU, "popcnt", "on" }, - { "Opteron_G2" "-" TYPE_X86_CPU, "rdtscp", "on" }, - { "Opteron_G3" "-" TYPE_X86_CPU, "rdtscp", "on" }, - { "Opteron_G4" "-" TYPE_X86_CPU, "rdtscp", "on" }, - { "Opteron_G5" "-" TYPE_X86_CPU, "rdtscp", "on", } -}; -const size_t pc_compat_2_4_len = G_N_ELEMENTS(pc_compat_2_4); - /* * @PC_FW_DATA: * Size of the chunk of memory at the top of RAM for the BIOS ACPI tables @@ -976,21 +955,23 @@ void pc_memory_init(PCMachineState *pcms, /* Initialize PC system firmware */ pc_system_firmware_init(pcms, rom_memory); - option_rom_mr = g_malloc(sizeof(*option_rom_mr)); - if (machine_require_guest_memfd(machine)) { - memory_region_init_ram_guest_memfd(option_rom_mr, NULL, "pc.rom", - PC_ROM_SIZE, &error_fatal); - } else { - memory_region_init_ram(option_rom_mr, NULL, "pc.rom", PC_ROM_SIZE, - &error_fatal); - if (pcmc->pci_enabled) { - memory_region_set_readonly(option_rom_mr, true); + if (!is_tdx_vm()) { + option_rom_mr = g_malloc(sizeof(*option_rom_mr)); + if (machine_require_guest_memfd(machine)) { + memory_region_init_ram_guest_memfd(option_rom_mr, NULL, "pc.rom", + PC_ROM_SIZE, &error_fatal); + } else { + memory_region_init_ram(option_rom_mr, NULL, "pc.rom", PC_ROM_SIZE, + &error_fatal); + if (pcmc->pci_enabled) { + memory_region_set_readonly(option_rom_mr, true); + } } + memory_region_add_subregion_overlap(rom_memory, + PC_ROM_MIN_VGA, + option_rom_mr, + 1); } - memory_region_add_subregion_overlap(rom_memory, - PC_ROM_MIN_VGA, - option_rom_mr, - 1); fw_cfg = fw_cfg_arch_create(machine, x86ms->boot_cpus, x86ms->apic_id_limit); @@ -999,14 +980,13 @@ void pc_memory_init(PCMachineState *pcms, if (machine->device_memory) { uint64_t *val = g_malloc(sizeof(*val)); - uint64_t res_mem_end = machine->device_memory->base; - - if (!pcmc->broken_reserved_end) { - res_mem_end += memory_region_size(&machine->device_memory->mr); - } + uint64_t res_mem_end; if (pcms->cxl_devices_state.is_enabled) { res_mem_end = cxl_resv_end; + } else { + res_mem_end = machine->device_memory->base + + memory_region_size(&machine->device_memory->mr); } *val = cpu_to_le64(ROUND_UP(res_mem_end, 1 * GiB)); fw_cfg_add_file(fw_cfg, "etc/reserved-memory-end", val, sizeof(*val)); @@ -1044,9 +1024,7 @@ uint64_t pc_pci_hole64_start(void) hole64_start = pc_get_cxl_range_end(pcms); } else if (pcmc->has_reserved_memory && (ms->ram_size < ms->maxram_size)) { pc_get_device_memory_range(pcms, &hole64_start, &size); - if (!pcmc->broken_reserved_end) { - hole64_start += size; - } + hole64_start += size; } else { hole64_start = pc_above_4g_end(pcms); } @@ -1058,7 +1036,6 @@ DeviceState *pc_vga_init(ISABus *isa_bus, PCIBus *pci_bus) { DeviceState *dev = NULL; - rom_set_order_override(FW_CFG_ORDER_OVERRIDE_VGA); if (pci_bus) { PCIDevice *pcidev = pci_vga_init(pci_bus); dev = pcidev ? &pcidev->qdev : NULL; @@ -1066,7 +1043,7 @@ DeviceState *pc_vga_init(ISABus *isa_bus, PCIBus *pci_bus) ISADevice *isadev = isa_vga_init(isa_bus); dev = isadev ? DEVICE(isadev) : NULL; } - rom_reset_order_override(); + return dev; } @@ -1256,8 +1233,6 @@ void pc_nic_init(PCMachineClass *pcmc, ISABus *isa_bus, PCIBus *pci_bus) bool default_is_ne2k = g_str_equal(mc->default_nic, TYPE_ISA_NE2000); NICInfo *nd; - rom_set_order_override(FW_CFG_ORDER_OVERRIDE_NIC); - while ((nd = qemu_find_nic_info(TYPE_ISA_NE2000, default_is_ne2k, NULL))) { pc_init_ne2k_isa(isa_bus, nd, &error_fatal); } @@ -1266,8 +1241,6 @@ void pc_nic_init(PCMachineClass *pcmc, ISABus *isa_bus, PCIBus *pci_bus) if (pci_bus) { pci_init_nic_devices(pci_bus, mc->default_nic); } - - rom_reset_order_override(); } void pc_i8259_create(ISABus *isa_bus, qemu_irq *i8259_irqs) diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 0dce512..ea7572e 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -285,6 +285,8 @@ static void pc_init1(MachineState *machine, const char *pci_type) pcms->idebus[0] = qdev_get_child_bus(dev, "ide.0"); pcms->idebus[1] = qdev_get_child_bus(dev, "ide.1"); } else { + uint32_t irq; + isa_bus = isa_bus_new(NULL, system_memory, system_io, &error_abort); isa_bus_register_input_irqs(isa_bus, x86ms->gsi); @@ -292,6 +294,9 @@ static void pc_init1(MachineState *machine, const char *pci_type) x86ms->rtc = isa_new(TYPE_MC146818_RTC); qdev_prop_set_int32(DEVICE(x86ms->rtc), "base_year", 2000); isa_realize_and_unref(x86ms->rtc, isa_bus, &error_fatal); + irq = object_property_get_uint(OBJECT(x86ms->rtc), "irq", + &error_fatal); + isa_connect_gpio_out(ISA_DEVICE(x86ms->rtc), 0, irq); i8257_dma_init(OBJECT(machine), isa_bus, 0); pcms->hpet_enabled = false; @@ -778,32 +783,6 @@ static void pc_i440fx_machine_2_6_options(MachineClass *m) DEFINE_I440FX_MACHINE(2, 6); -static void pc_i440fx_machine_2_5_options(MachineClass *m) -{ - X86MachineClass *x86mc = X86_MACHINE_CLASS(m); - - pc_i440fx_machine_2_6_options(m); - x86mc->save_tsc_khz = false; - m->legacy_fw_cfg_order = 1; - compat_props_add(m->compat_props, hw_compat_2_5, hw_compat_2_5_len); - compat_props_add(m->compat_props, pc_compat_2_5, pc_compat_2_5_len); -} - -DEFINE_I440FX_MACHINE(2, 5); - -static void pc_i440fx_machine_2_4_options(MachineClass *m) -{ - PCMachineClass *pcmc = PC_MACHINE_CLASS(m); - - pc_i440fx_machine_2_5_options(m); - m->hw_version = "2.4.0"; - pcmc->broken_reserved_end = true; - compat_props_add(m->compat_props, hw_compat_2_4, hw_compat_2_4_len); - compat_props_add(m->compat_props, pc_compat_2_4, pc_compat_2_4_len); -} - -DEFINE_I440FX_MACHINE(2, 4); - #ifdef CONFIG_ISAPC static void isapc_machine_options(MachineClass *m) { diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index c538b3d..33211b1 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -672,29 +672,3 @@ static void pc_q35_machine_2_6_options(MachineClass *m) } DEFINE_Q35_MACHINE(2, 6); - -static void pc_q35_machine_2_5_options(MachineClass *m) -{ - X86MachineClass *x86mc = X86_MACHINE_CLASS(m); - - pc_q35_machine_2_6_options(m); - x86mc->save_tsc_khz = false; - m->legacy_fw_cfg_order = 1; - compat_props_add(m->compat_props, hw_compat_2_5, hw_compat_2_5_len); - compat_props_add(m->compat_props, pc_compat_2_5, pc_compat_2_5_len); -} - -DEFINE_Q35_MACHINE(2, 5); - -static void pc_q35_machine_2_4_options(MachineClass *m) -{ - PCMachineClass *pcmc = PC_MACHINE_CLASS(m); - - pc_q35_machine_2_5_options(m); - m->hw_version = "2.4.0"; - pcmc->broken_reserved_end = true; - compat_props_add(m->compat_props, hw_compat_2_4, hw_compat_2_4_len); - compat_props_add(m->compat_props, pc_compat_2_4, pc_compat_2_4_len); -} - -DEFINE_Q35_MACHINE(2, 4); diff --git a/hw/i386/pc_sysfw.c b/hw/i386/pc_sysfw.c index 1eeb58a..821396c 100644 --- a/hw/i386/pc_sysfw.c +++ b/hw/i386/pc_sysfw.c @@ -37,6 +37,7 @@ #include "hw/block/flash.h" #include "system/kvm.h" #include "target/i386/sev.h" +#include "kvm/tdx.h" #define FLASH_SECTOR_SIZE 4096 @@ -280,5 +281,11 @@ void x86_firmware_configure(hwaddr gpa, void *ptr, int size) } sev_encrypt_flash(gpa, ptr, size, &error_fatal); + } else if (is_tdx_vm()) { + ret = tdx_parse_tdvf(ptr, size); + if (ret) { + error_report("failed to parse TDVF for TDX VM"); + exit(1); + } } } diff --git a/hw/i386/tdvf-hob.c b/hw/i386/tdvf-hob.c new file mode 100644 index 0000000..782b3d1 --- /dev/null +++ b/hw/i386/tdvf-hob.c @@ -0,0 +1,130 @@ +/* + * Copyright (c) 2025 Intel Corporation + * Author: Isaku Yamahata <isaku.yamahata at gmail.com> + * <isaku.yamahata at intel.com> + * Xiaoyao Li <xiaoyao.li@intel.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu/error-report.h" +#include "standard-headers/uefi/uefi.h" +#include "hw/pci/pcie_host.h" +#include "tdvf-hob.h" + +typedef struct TdvfHob { + hwaddr hob_addr; + void *ptr; + int size; + + /* working area */ + void *current; + void *end; +} TdvfHob; + +static uint64_t tdvf_current_guest_addr(const TdvfHob *hob) +{ + return hob->hob_addr + (hob->current - hob->ptr); +} + +static void tdvf_align(TdvfHob *hob, size_t align) +{ + hob->current = QEMU_ALIGN_PTR_UP(hob->current, align); +} + +static void *tdvf_get_area(TdvfHob *hob, uint64_t size) +{ + void *ret; + + if (hob->current + size > hob->end) { + error_report("TD_HOB overrun, size = 0x%" PRIx64, size); + exit(1); + } + + ret = hob->current; + hob->current += size; + tdvf_align(hob, 8); + return ret; +} + +static void tdvf_hob_add_memory_resources(TdxGuest *tdx, TdvfHob *hob) +{ + EFI_HOB_RESOURCE_DESCRIPTOR *region; + EFI_RESOURCE_ATTRIBUTE_TYPE attr; + EFI_RESOURCE_TYPE resource_type; + + TdxRamEntry *e; + int i; + + for (i = 0; i < tdx->nr_ram_entries; i++) { + e = &tdx->ram_entries[i]; + + if (e->type == TDX_RAM_UNACCEPTED) { + resource_type = EFI_RESOURCE_MEMORY_UNACCEPTED; + attr = EFI_RESOURCE_ATTRIBUTE_TDVF_UNACCEPTED; + } else if (e->type == TDX_RAM_ADDED) { + resource_type = EFI_RESOURCE_SYSTEM_MEMORY; + attr = EFI_RESOURCE_ATTRIBUTE_TDVF_PRIVATE; + } else { + error_report("unknown TDX_RAM_ENTRY type %d", e->type); + exit(1); + } + + region = tdvf_get_area(hob, sizeof(*region)); + *region = (EFI_HOB_RESOURCE_DESCRIPTOR) { + .Header = { + .HobType = EFI_HOB_TYPE_RESOURCE_DESCRIPTOR, + .HobLength = cpu_to_le16(sizeof(*region)), + .Reserved = cpu_to_le32(0), + }, + .Owner = EFI_HOB_OWNER_ZERO, + .ResourceType = cpu_to_le32(resource_type), + .ResourceAttribute = cpu_to_le32(attr), + .PhysicalStart = cpu_to_le64(e->address), + .ResourceLength = cpu_to_le64(e->length), + }; + } +} + +void tdvf_hob_create(TdxGuest *tdx, TdxFirmwareEntry *td_hob) +{ + TdvfHob hob = { + .hob_addr = td_hob->address, + .size = td_hob->size, + .ptr = td_hob->mem_ptr, + + .current = td_hob->mem_ptr, + .end = td_hob->mem_ptr + td_hob->size, + }; + + EFI_HOB_GENERIC_HEADER *last_hob; + EFI_HOB_HANDOFF_INFO_TABLE *hit; + + /* Note, Efi{Free}Memory{Bottom,Top} are ignored, leave 'em zeroed. */ + hit = tdvf_get_area(&hob, sizeof(*hit)); + *hit = (EFI_HOB_HANDOFF_INFO_TABLE) { + .Header = { + .HobType = EFI_HOB_TYPE_HANDOFF, + .HobLength = cpu_to_le16(sizeof(*hit)), + .Reserved = cpu_to_le32(0), + }, + .Version = cpu_to_le32(EFI_HOB_HANDOFF_TABLE_VERSION), + .BootMode = cpu_to_le32(0), + .EfiMemoryTop = cpu_to_le64(0), + .EfiMemoryBottom = cpu_to_le64(0), + .EfiFreeMemoryTop = cpu_to_le64(0), + .EfiFreeMemoryBottom = cpu_to_le64(0), + .EfiEndOfHobList = cpu_to_le64(0), /* initialized later */ + }; + + tdvf_hob_add_memory_resources(tdx, &hob); + + last_hob = tdvf_get_area(&hob, sizeof(*last_hob)); + *last_hob = (EFI_HOB_GENERIC_HEADER) { + .HobType = EFI_HOB_TYPE_END_OF_HOB_LIST, + .HobLength = cpu_to_le16(sizeof(*last_hob)), + .Reserved = cpu_to_le32(0), + }; + hit->EfiEndOfHobList = tdvf_current_guest_addr(&hob); +} diff --git a/hw/i386/tdvf-hob.h b/hw/i386/tdvf-hob.h new file mode 100644 index 0000000..4fc6a37 --- /dev/null +++ b/hw/i386/tdvf-hob.h @@ -0,0 +1,26 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ + +#ifndef HW_I386_TD_HOB_H +#define HW_I386_TD_HOB_H + +#include "hw/i386/tdvf.h" +#include "target/i386/kvm/tdx.h" + +void tdvf_hob_create(TdxGuest *tdx, TdxFirmwareEntry *td_hob); + +#define EFI_RESOURCE_ATTRIBUTE_TDVF_PRIVATE \ + (EFI_RESOURCE_ATTRIBUTE_PRESENT | \ + EFI_RESOURCE_ATTRIBUTE_INITIALIZED | \ + EFI_RESOURCE_ATTRIBUTE_TESTED) + +#define EFI_RESOURCE_ATTRIBUTE_TDVF_UNACCEPTED \ + (EFI_RESOURCE_ATTRIBUTE_PRESENT | \ + EFI_RESOURCE_ATTRIBUTE_INITIALIZED | \ + EFI_RESOURCE_ATTRIBUTE_TESTED) + +#define EFI_RESOURCE_ATTRIBUTE_TDVF_MMIO \ + (EFI_RESOURCE_ATTRIBUTE_PRESENT | \ + EFI_RESOURCE_ATTRIBUTE_INITIALIZED | \ + EFI_RESOURCE_ATTRIBUTE_UNCACHEABLE) + +#endif diff --git a/hw/i386/tdvf.c b/hw/i386/tdvf.c new file mode 100644 index 0000000..645d9d1 --- /dev/null +++ b/hw/i386/tdvf.c @@ -0,0 +1,189 @@ +/* + * Copyright (c) 2025 Intel Corporation + * Author: Isaku Yamahata <isaku.yamahata at gmail.com> + * <isaku.yamahata at intel.com> + * Xiaoyao Li <xiaoyao.li@intel.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu/error-report.h" + +#include "hw/i386/pc.h" +#include "hw/i386/tdvf.h" +#include "system/kvm.h" + +#define TDX_METADATA_OFFSET_GUID "e47a6535-984a-4798-865e-4685a7bf8ec2" +#define TDX_METADATA_VERSION 1 +#define TDVF_SIGNATURE 0x46564454 /* TDVF as little endian */ +#define TDVF_ALIGNMENT 4096 + +/* + * the raw structs read from TDVF keeps the name convention in + * TDVF Design Guide spec. + */ +typedef struct { + uint32_t DataOffset; + uint32_t RawDataSize; + uint64_t MemoryAddress; + uint64_t MemoryDataSize; + uint32_t Type; + uint32_t Attributes; +} TdvfSectionEntry; + +typedef struct { + uint32_t Signature; + uint32_t Length; + uint32_t Version; + uint32_t NumberOfSectionEntries; + TdvfSectionEntry SectionEntries[]; +} TdvfMetadata; + +struct tdx_metadata_offset { + uint32_t offset; +}; + +static TdvfMetadata *tdvf_get_metadata(void *flash_ptr, int size) +{ + TdvfMetadata *metadata; + uint32_t offset = 0; + uint8_t *data; + + if ((uint32_t) size != size) { + return NULL; + } + + if (pc_system_ovmf_table_find(TDX_METADATA_OFFSET_GUID, &data, NULL)) { + offset = size - le32_to_cpu(((struct tdx_metadata_offset *)data)->offset); + + if (offset + sizeof(*metadata) > size) { + return NULL; + } + } else { + error_report("Cannot find TDX_METADATA_OFFSET_GUID"); + return NULL; + } + + metadata = flash_ptr + offset; + + /* Finally, verify the signature to determine if this is a TDVF image. */ + metadata->Signature = le32_to_cpu(metadata->Signature); + if (metadata->Signature != TDVF_SIGNATURE) { + error_report("Invalid TDVF signature in metadata!"); + return NULL; + } + + /* Sanity check that the TDVF doesn't overlap its own metadata. */ + metadata->Length = le32_to_cpu(metadata->Length); + if (offset + metadata->Length > size) { + return NULL; + } + + /* Only version 1 is supported/defined. */ + metadata->Version = le32_to_cpu(metadata->Version); + if (metadata->Version != TDX_METADATA_VERSION) { + return NULL; + } + + return metadata; +} + +static int tdvf_parse_and_check_section_entry(const TdvfSectionEntry *src, + TdxFirmwareEntry *entry) +{ + entry->data_offset = le32_to_cpu(src->DataOffset); + entry->data_len = le32_to_cpu(src->RawDataSize); + entry->address = le64_to_cpu(src->MemoryAddress); + entry->size = le64_to_cpu(src->MemoryDataSize); + entry->type = le32_to_cpu(src->Type); + entry->attributes = le32_to_cpu(src->Attributes); + + /* sanity check */ + if (entry->size < entry->data_len) { + error_report("Broken metadata RawDataSize 0x%x MemoryDataSize 0x%"PRIx64, + entry->data_len, entry->size); + return -1; + } + if (!QEMU_IS_ALIGNED(entry->address, TDVF_ALIGNMENT)) { + error_report("MemoryAddress 0x%"PRIx64" not page aligned", entry->address); + return -1; + } + if (!QEMU_IS_ALIGNED(entry->size, TDVF_ALIGNMENT)) { + error_report("MemoryDataSize 0x%"PRIx64" not page aligned", entry->size); + return -1; + } + + switch (entry->type) { + case TDVF_SECTION_TYPE_BFV: + case TDVF_SECTION_TYPE_CFV: + /* The sections that must be copied from firmware image to TD memory */ + if (entry->data_len == 0) { + error_report("%d section with RawDataSize == 0", entry->type); + return -1; + } + break; + case TDVF_SECTION_TYPE_TD_HOB: + case TDVF_SECTION_TYPE_TEMP_MEM: + /* The sections that no need to be copied from firmware image */ + if (entry->data_len != 0) { + error_report("%d section with RawDataSize 0x%x != 0", + entry->type, entry->data_len); + return -1; + } + break; + default: + error_report("TDVF contains unsupported section type %d", entry->type); + return -1; + } + + return 0; +} + +int tdvf_parse_metadata(TdxFirmware *fw, void *flash_ptr, int size) +{ + g_autofree TdvfSectionEntry *sections = NULL; + TdvfMetadata *metadata; + ssize_t entries_size; + int i; + + metadata = tdvf_get_metadata(flash_ptr, size); + if (!metadata) { + return -EINVAL; + } + + /* load and parse metadata entries */ + fw->nr_entries = le32_to_cpu(metadata->NumberOfSectionEntries); + if (fw->nr_entries < 2) { + error_report("Invalid number of fw entries (%u) in TDVF Metadata", + fw->nr_entries); + return -EINVAL; + } + + entries_size = fw->nr_entries * sizeof(TdvfSectionEntry); + if (metadata->Length != sizeof(*metadata) + entries_size) { + error_report("TDVF metadata len (0x%x) mismatch, expected (0x%x)", + metadata->Length, + (uint32_t)(sizeof(*metadata) + entries_size)); + return -EINVAL; + } + + fw->entries = g_new(TdxFirmwareEntry, fw->nr_entries); + sections = g_new(TdvfSectionEntry, fw->nr_entries); + + memcpy(sections, (void *)metadata + sizeof(*metadata), entries_size); + + for (i = 0; i < fw->nr_entries; i++) { + if (tdvf_parse_and_check_section_entry(§ions[i], &fw->entries[i])) { + goto err; + } + } + + fw->mem_ptr = flash_ptr; + return 0; + +err: + fw->entries = 0; + g_free(fw->entries); + return -EINVAL; +} diff --git a/hw/i386/x86-common.c b/hw/i386/x86-common.c index 1b0671c..b1b5f11 100644 --- a/hw/i386/x86-common.c +++ b/hw/i386/x86-common.c @@ -44,6 +44,7 @@ #include "standard-headers/asm-x86/bootparam.h" #include CONFIG_DEVICES #include "kvm/kvm_i386.h" +#include "kvm/tdx.h" #ifdef CONFIG_XEN_EMU #include "hw/xen/xen.h" @@ -1035,11 +1036,14 @@ void x86_bios_rom_init(X86MachineState *x86ms, const char *default_firmware, if (machine_require_guest_memfd(MACHINE(x86ms))) { memory_region_init_ram_guest_memfd(&x86ms->bios, NULL, "pc.bios", bios_size, &error_fatal); + if (is_tdx_vm()) { + tdx_set_tdvf_region(&x86ms->bios); + } } else { memory_region_init_ram(&x86ms->bios, NULL, "pc.bios", bios_size, &error_fatal); } - if (sev_enabled()) { + if (sev_enabled() || is_tdx_vm()) { /* * The concept of a "reset" simply doesn't exist for * confidential computing guests, we have to destroy and diff --git a/hw/i386/x86.c b/hw/i386/x86.c index e2d0409..f80533d 100644 --- a/hw/i386/x86.c +++ b/hw/i386/x86.c @@ -382,7 +382,6 @@ static void x86_machine_class_init(ObjectClass *oc, const void *data) mc->get_default_cpu_node_id = x86_get_default_cpu_node_id; mc->possible_cpu_arch_ids = x86_possible_cpu_arch_ids; mc->kvm_type = x86_kvm_type; - x86mc->save_tsc_khz = true; x86mc->fwcfg_dma_enabled = true; nc->nmi_monitor_handler = x86_nmi; diff --git a/hw/microblaze/petalogix_ml605_mmu.c b/hw/microblaze/petalogix_ml605_mmu.c index bea6b68..6e923c4 100644 --- a/hw/microblaze/petalogix_ml605_mmu.c +++ b/hw/microblaze/petalogix_ml605_mmu.c @@ -80,8 +80,6 @@ petalogix_ml605_init(MachineState *machine) MemoryRegion *phys_lmb_bram = g_new(MemoryRegion, 1); MemoryRegion *phys_ram = g_new(MemoryRegion, 1); qemu_irq irq[32]; - EndianMode endianness = TARGET_BIG_ENDIAN ? ENDIAN_MODE_BIG - : ENDIAN_MODE_LITTLE; /* init CPUs */ cpu = MICROBLAZE_CPU(object_new(TYPE_MICROBLAZE_CPU)); @@ -113,7 +111,7 @@ petalogix_ml605_init(MachineState *machine) dev = qdev_new("xlnx.xps-intc"); - qdev_prop_set_enum(dev, "endianness", endianness); + qdev_prop_set_enum(dev, "endianness", ENDIAN_MODE_LITTLE); qdev_prop_set_uint32(dev, "kind-of-intr", 1 << TIMER_IRQ); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, INTC_BASEADDR); @@ -129,7 +127,7 @@ petalogix_ml605_init(MachineState *machine) /* 2 timers at irq 2 @ 100 Mhz. */ dev = qdev_new("xlnx.xps-timer"); - qdev_prop_set_enum(dev, "endianness", endianness); + qdev_prop_set_enum(dev, "endianness", ENDIAN_MODE_LITTLE); qdev_prop_set_uint32(dev, "one-timer-only", 0); qdev_prop_set_uint32(dev, "clock-frequency", 100 * 1000000); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); @@ -177,7 +175,7 @@ petalogix_ml605_init(MachineState *machine) SSIBus *spi; dev = qdev_new("xlnx.xps-spi"); - qdev_prop_set_enum(dev, "endianness", endianness); + qdev_prop_set_enum(dev, "endianness", ENDIAN_MODE_LITTLE); qdev_prop_set_uint8(dev, "num-ss-bits", NUM_SPI_FLASHES); busdev = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(busdev, &error_fatal); @@ -218,12 +216,7 @@ petalogix_ml605_init(MachineState *machine) static void petalogix_ml605_machine_init(MachineClass *mc) { - if (TARGET_BIG_ENDIAN) { - mc->desc = "PetaLogix linux refdesign for xilinx ml605 (big endian)"; - mc->deprecation_reason = "big endian support is not tested"; - } else { - mc->desc = "PetaLogix linux refdesign for xilinx ml605 (little endian)"; - } + mc->desc = "PetaLogix linux refdesign for xilinx ml605 (little endian)"; mc->init = petalogix_ml605_init; } diff --git a/hw/microblaze/petalogix_s3adsp1800_mmu.c b/hw/microblaze/petalogix_s3adsp1800_mmu.c index 032f6f7..e8d0ddf 100644 --- a/hw/microblaze/petalogix_s3adsp1800_mmu.c +++ b/hw/microblaze/petalogix_s3adsp1800_mmu.c @@ -58,9 +58,20 @@ #define TYPE_PETALOGIX_S3ADSP1800_MACHINE \ MACHINE_TYPE_NAME("petalogix-s3adsp1800") +struct S3Adsp1800MachineState { + MachineState parent_class; + + EndianMode endianness; +}; + +OBJECT_DECLARE_TYPE(S3Adsp1800MachineState, MachineClass, + PETALOGIX_S3ADSP1800_MACHINE) + + static void petalogix_s3adsp1800_init(MachineState *machine) { + S3Adsp1800MachineState *psms = PETALOGIX_S3ADSP1800_MACHINE(machine); ram_addr_t ram_size = machine->ram_size; DeviceState *dev; MicroBlazeCPU *cpu; @@ -71,13 +82,12 @@ petalogix_s3adsp1800_init(MachineState *machine) MemoryRegion *phys_ram = g_new(MemoryRegion, 1); qemu_irq irq[32]; MemoryRegion *sysmem = get_system_memory(); - EndianMode endianness = TARGET_BIG_ENDIAN ? ENDIAN_MODE_BIG - : ENDIAN_MODE_LITTLE; + EndianMode endianness = psms->endianness; cpu = MICROBLAZE_CPU(object_new(TYPE_MICROBLAZE_CPU)); object_property_set_str(OBJECT(cpu), "version", "7.10.d", &error_abort); object_property_set_bool(OBJECT(cpu), "little-endian", - !TARGET_BIG_ENDIAN, &error_abort); + endianness == ENDIAN_MODE_LITTLE, &error_abort); qdev_realize(DEVICE(cpu), NULL, &error_abort); /* Attach emulated BRAM through the LMB. */ @@ -135,20 +145,41 @@ petalogix_s3adsp1800_init(MachineState *machine) create_unimplemented_device("xps_gpio", GPIO_BASEADDR, 0x10000); - microblaze_load_kernel(cpu, !TARGET_BIG_ENDIAN, ddr_base, ram_size, - machine->initrd_filename, + microblaze_load_kernel(cpu, endianness == ENDIAN_MODE_LITTLE, ddr_base, + ram_size, machine->initrd_filename, BINARY_DEVICE_TREE_FILE, NULL); } +static int machine_get_endianness(Object *obj, Error **errp G_GNUC_UNUSED) +{ + S3Adsp1800MachineState *ms = PETALOGIX_S3ADSP1800_MACHINE(obj); + return ms->endianness; +} + +static void machine_set_endianness(Object *obj, int endianness, Error **errp) +{ + S3Adsp1800MachineState *ms = PETALOGIX_S3ADSP1800_MACHINE(obj); + ms->endianness = endianness; +} + static void petalogix_s3adsp1800_machine_class_init(ObjectClass *oc, const void *data) { MachineClass *mc = MACHINE_CLASS(oc); + ObjectProperty *prop; mc->desc = "PetaLogix linux refdesign for xilinx Spartan 3ADSP1800"; mc->init = petalogix_s3adsp1800_init; mc->is_default = true; + + prop = object_class_property_add_enum(oc, "endianness", "EndianMode", + &EndianMode_lookup, + machine_get_endianness, + machine_set_endianness); + object_property_set_default_str(prop, TARGET_BIG_ENDIAN ? "big" : "little"); + object_class_property_set_description(oc, "endianness", + "Defines whether the machine runs in big or little endian mode"); } static const TypeInfo petalogix_s3adsp1800_machine_types[] = { @@ -156,6 +187,7 @@ static const TypeInfo petalogix_s3adsp1800_machine_types[] = { .name = TYPE_PETALOGIX_S3ADSP1800_MACHINE, .parent = TYPE_MACHINE, .class_init = petalogix_s3adsp1800_machine_class_init, + .instance_size = sizeof(S3Adsp1800MachineState), }, }; diff --git a/hw/microblaze/xlnx-zynqmp-pmu.c b/hw/microblaze/xlnx-zynqmp-pmu.c index ed40b5f..e909802 100644 --- a/hw/microblaze/xlnx-zynqmp-pmu.c +++ b/hw/microblaze/xlnx-zynqmp-pmu.c @@ -181,12 +181,7 @@ static void xlnx_zynqmp_pmu_init(MachineState *machine) static void xlnx_zynqmp_pmu_machine_init(MachineClass *mc) { - if (TARGET_BIG_ENDIAN) { - mc->desc = "Xilinx ZynqMP PMU machine (big endian)"; - mc->deprecation_reason = "big endian support is not tested"; - } else { - mc->desc = "Xilinx ZynqMP PMU machine (little endian)"; - } + mc->desc = "Xilinx ZynqMP PMU machine (little endian)"; mc->init = xlnx_zynqmp_pmu_init; } diff --git a/hw/net/e1000.c b/hw/net/e1000.c index cba4999..a80a7b0 100644 --- a/hw/net/e1000.c +++ b/hw/net/e1000.c @@ -127,10 +127,8 @@ struct E1000State_st { QEMUTimer *flush_queue_timer; /* Compatibility flags for migration to/from qemu 1.3.0 and older */ -#define E1000_FLAG_MAC_BIT 2 #define E1000_FLAG_TSO_BIT 3 #define E1000_FLAG_VET_BIT 4 -#define E1000_FLAG_MAC (1 << E1000_FLAG_MAC_BIT) #define E1000_FLAG_TSO (1 << E1000_FLAG_TSO_BIT) #define E1000_FLAG_VET (1 << E1000_FLAG_VET_BIT) @@ -1212,52 +1210,51 @@ enum { NWRITEOPS = ARRAY_SIZE(macreg_writeops) }; enum { MAC_ACCESS_PARTIAL = 1, MAC_ACCESS_FLAG_NEEDED = 2 }; -#define markflag(x) ((E1000_FLAG_##x << 2) | MAC_ACCESS_FLAG_NEEDED) /* In the array below the meaning of the bits is: [f|f|f|f|f|f|n|p] * f - flag bits (up to 6 possible flags) * n - flag needed - * p - partially implenented */ + * p - partially implemented */ static const uint8_t mac_reg_access[0x8000] = { - [IPAV] = markflag(MAC), [WUC] = markflag(MAC), - [IP6AT] = markflag(MAC), [IP4AT] = markflag(MAC), - [FFVT] = markflag(MAC), [WUPM] = markflag(MAC), - [ECOL] = markflag(MAC), [MCC] = markflag(MAC), - [DC] = markflag(MAC), [TNCRS] = markflag(MAC), - [RLEC] = markflag(MAC), [XONRXC] = markflag(MAC), - [XOFFTXC] = markflag(MAC), [RFC] = markflag(MAC), - [TSCTFC] = markflag(MAC), [MGTPRC] = markflag(MAC), - [WUS] = markflag(MAC), [AIT] = markflag(MAC), - [FFLT] = markflag(MAC), [FFMT] = markflag(MAC), - [SCC] = markflag(MAC), [FCRUC] = markflag(MAC), - [LATECOL] = markflag(MAC), [COLC] = markflag(MAC), - [SEQEC] = markflag(MAC), [CEXTERR] = markflag(MAC), - [XONTXC] = markflag(MAC), [XOFFRXC] = markflag(MAC), - [RJC] = markflag(MAC), [RNBC] = markflag(MAC), - [MGTPDC] = markflag(MAC), [MGTPTC] = markflag(MAC), - [RUC] = markflag(MAC), [ROC] = markflag(MAC), - [GORCL] = markflag(MAC), [GORCH] = markflag(MAC), - [GOTCL] = markflag(MAC), [GOTCH] = markflag(MAC), - [BPRC] = markflag(MAC), [MPRC] = markflag(MAC), - [TSCTC] = markflag(MAC), [PRC64] = markflag(MAC), - [PRC127] = markflag(MAC), [PRC255] = markflag(MAC), - [PRC511] = markflag(MAC), [PRC1023] = markflag(MAC), - [PRC1522] = markflag(MAC), [PTC64] = markflag(MAC), - [PTC127] = markflag(MAC), [PTC255] = markflag(MAC), - [PTC511] = markflag(MAC), [PTC1023] = markflag(MAC), - [PTC1522] = markflag(MAC), [MPTC] = markflag(MAC), - [BPTC] = markflag(MAC), - - [TDFH] = markflag(MAC) | MAC_ACCESS_PARTIAL, - [TDFT] = markflag(MAC) | MAC_ACCESS_PARTIAL, - [TDFHS] = markflag(MAC) | MAC_ACCESS_PARTIAL, - [TDFTS] = markflag(MAC) | MAC_ACCESS_PARTIAL, - [TDFPC] = markflag(MAC) | MAC_ACCESS_PARTIAL, - [RDFH] = markflag(MAC) | MAC_ACCESS_PARTIAL, - [RDFT] = markflag(MAC) | MAC_ACCESS_PARTIAL, - [RDFHS] = markflag(MAC) | MAC_ACCESS_PARTIAL, - [RDFTS] = markflag(MAC) | MAC_ACCESS_PARTIAL, - [RDFPC] = markflag(MAC) | MAC_ACCESS_PARTIAL, - [PBM] = markflag(MAC) | MAC_ACCESS_PARTIAL, + [IPAV] = MAC_ACCESS_FLAG_NEEDED, [WUC] = MAC_ACCESS_FLAG_NEEDED, + [IP6AT] = MAC_ACCESS_FLAG_NEEDED, [IP4AT] = MAC_ACCESS_FLAG_NEEDED, + [FFVT] = MAC_ACCESS_FLAG_NEEDED, [WUPM] = MAC_ACCESS_FLAG_NEEDED, + [ECOL] = MAC_ACCESS_FLAG_NEEDED, [MCC] = MAC_ACCESS_FLAG_NEEDED, + [DC] = MAC_ACCESS_FLAG_NEEDED, [TNCRS] = MAC_ACCESS_FLAG_NEEDED, + [RLEC] = MAC_ACCESS_FLAG_NEEDED, [XONRXC] = MAC_ACCESS_FLAG_NEEDED, + [XOFFTXC] = MAC_ACCESS_FLAG_NEEDED, [RFC] = MAC_ACCESS_FLAG_NEEDED, + [TSCTFC] = MAC_ACCESS_FLAG_NEEDED, [MGTPRC] = MAC_ACCESS_FLAG_NEEDED, + [WUS] = MAC_ACCESS_FLAG_NEEDED, [AIT] = MAC_ACCESS_FLAG_NEEDED, + [FFLT] = MAC_ACCESS_FLAG_NEEDED, [FFMT] = MAC_ACCESS_FLAG_NEEDED, + [SCC] = MAC_ACCESS_FLAG_NEEDED, [FCRUC] = MAC_ACCESS_FLAG_NEEDED, + [LATECOL] = MAC_ACCESS_FLAG_NEEDED, [COLC] = MAC_ACCESS_FLAG_NEEDED, + [SEQEC] = MAC_ACCESS_FLAG_NEEDED, [CEXTERR] = MAC_ACCESS_FLAG_NEEDED, + [XONTXC] = MAC_ACCESS_FLAG_NEEDED, [XOFFRXC] = MAC_ACCESS_FLAG_NEEDED, + [RJC] = MAC_ACCESS_FLAG_NEEDED, [RNBC] = MAC_ACCESS_FLAG_NEEDED, + [MGTPDC] = MAC_ACCESS_FLAG_NEEDED, [MGTPTC] = MAC_ACCESS_FLAG_NEEDED, + [RUC] = MAC_ACCESS_FLAG_NEEDED, [ROC] = MAC_ACCESS_FLAG_NEEDED, + [GORCL] = MAC_ACCESS_FLAG_NEEDED, [GORCH] = MAC_ACCESS_FLAG_NEEDED, + [GOTCL] = MAC_ACCESS_FLAG_NEEDED, [GOTCH] = MAC_ACCESS_FLAG_NEEDED, + [BPRC] = MAC_ACCESS_FLAG_NEEDED, [MPRC] = MAC_ACCESS_FLAG_NEEDED, + [TSCTC] = MAC_ACCESS_FLAG_NEEDED, [PRC64] = MAC_ACCESS_FLAG_NEEDED, + [PRC127] = MAC_ACCESS_FLAG_NEEDED, [PRC255] = MAC_ACCESS_FLAG_NEEDED, + [PRC511] = MAC_ACCESS_FLAG_NEEDED, [PRC1023] = MAC_ACCESS_FLAG_NEEDED, + [PRC1522] = MAC_ACCESS_FLAG_NEEDED, [PTC64] = MAC_ACCESS_FLAG_NEEDED, + [PTC127] = MAC_ACCESS_FLAG_NEEDED, [PTC255] = MAC_ACCESS_FLAG_NEEDED, + [PTC511] = MAC_ACCESS_FLAG_NEEDED, [PTC1023] = MAC_ACCESS_FLAG_NEEDED, + [PTC1522] = MAC_ACCESS_FLAG_NEEDED, [MPTC] = MAC_ACCESS_FLAG_NEEDED, + [BPTC] = MAC_ACCESS_FLAG_NEEDED, + + [TDFH] = MAC_ACCESS_FLAG_NEEDED | MAC_ACCESS_PARTIAL, + [TDFT] = MAC_ACCESS_FLAG_NEEDED | MAC_ACCESS_PARTIAL, + [TDFHS] = MAC_ACCESS_FLAG_NEEDED | MAC_ACCESS_PARTIAL, + [TDFTS] = MAC_ACCESS_FLAG_NEEDED | MAC_ACCESS_PARTIAL, + [TDFPC] = MAC_ACCESS_FLAG_NEEDED | MAC_ACCESS_PARTIAL, + [RDFH] = MAC_ACCESS_FLAG_NEEDED | MAC_ACCESS_PARTIAL, + [RDFT] = MAC_ACCESS_FLAG_NEEDED | MAC_ACCESS_PARTIAL, + [RDFHS] = MAC_ACCESS_FLAG_NEEDED | MAC_ACCESS_PARTIAL, + [RDFTS] = MAC_ACCESS_FLAG_NEEDED | MAC_ACCESS_PARTIAL, + [RDFPC] = MAC_ACCESS_FLAG_NEEDED | MAC_ACCESS_PARTIAL, + [PBM] = MAC_ACCESS_FLAG_NEEDED | MAC_ACCESS_PARTIAL, }; static void @@ -1419,13 +1416,6 @@ static int e1000_tx_tso_post_load(void *opaque, int version_id) return 0; } -static bool e1000_full_mac_needed(void *opaque) -{ - E1000State *s = opaque; - - return chkflag(MAC); -} - static bool e1000_tso_state_needed(void *opaque) { E1000State *s = opaque; @@ -1451,7 +1441,6 @@ static const VMStateDescription vmstate_e1000_full_mac_state = { .name = "e1000/full_mac_state", .version_id = 1, .minimum_version_id = 1, - .needed = e1000_full_mac_needed, .fields = (const VMStateField[]) { VMSTATE_UINT32_ARRAY(mac_reg, E1000State, 0x8000), VMSTATE_END_OF_LIST() @@ -1679,8 +1668,6 @@ static void pci_e1000_realize(PCIDevice *pci_dev, Error **errp) static const Property e1000_properties[] = { DEFINE_NIC_PROPERTIES(E1000State, conf), - DEFINE_PROP_BIT("extra_mac_registers", E1000State, - compat_flags, E1000_FLAG_MAC_BIT, true), DEFINE_PROP_BIT("migrate_tso_props", E1000State, compat_flags, E1000_FLAG_TSO_BIT, true), DEFINE_PROP_BIT("init-vet", E1000State, diff --git a/hw/net/rocker/rocker.h b/hw/net/rocker/rocker.h index 6e0962f..ae06c1c 100644 --- a/hw/net/rocker/rocker.h +++ b/hw/net/rocker/rocker.h @@ -36,15 +36,7 @@ static inline G_GNUC_PRINTF(1, 2) int DPRINTF(const char *fmt, ...) } #endif -#define __le16 uint16_t -#define __le32 uint32_t -#define __le64 uint64_t - -#define __be16 uint16_t -#define __be32 uint32_t -#define __be64 uint64_t - -static inline bool ipv4_addr_is_multicast(__be32 addr) +static inline bool ipv4_addr_is_multicast(uint32_t addr) { return (addr & htonl(0xf0000000)) == htonl(0xe0000000); } @@ -52,8 +44,8 @@ static inline bool ipv4_addr_is_multicast(__be32 addr) typedef struct ipv6_addr { union { uint8_t addr8[16]; - __be16 addr16[8]; - __be32 addr32[4]; + uint16_t addr16[8]; + uint32_t addr32[4]; }; } Ipv6Addr; diff --git a/hw/net/rocker/rocker_hw.h b/hw/net/rocker/rocker_hw.h index 1786323..7ec6bfb 100644 --- a/hw/net/rocker/rocker_hw.h +++ b/hw/net/rocker/rocker_hw.h @@ -9,10 +9,6 @@ #ifndef ROCKER_HW_H #define ROCKER_HW_H -#define __le16 uint16_t -#define __le32 uint32_t -#define __le64 uint64_t - /* * Return codes */ @@ -124,12 +120,12 @@ enum { */ typedef struct rocker_desc { - __le64 buf_addr; + uint64_t buf_addr; uint64_t cookie; - __le16 buf_size; - __le16 tlv_size; - __le16 rsvd[5]; /* pad to 32 bytes */ - __le16 comp_err; + uint16_t buf_size; + uint16_t tlv_size; + uint16_t rsvd[5]; /* pad to 32 bytes */ + uint16_t comp_err; } __attribute__((packed, aligned(8))) RockerDesc; /* @@ -137,9 +133,9 @@ typedef struct rocker_desc { */ typedef struct rocker_tlv { - __le32 type; - __le16 len; - __le16 rsvd; + uint32_t type; + uint16_t len; + uint16_t rsvd; } __attribute__((packed, aligned(8))) RockerTlv; /* cmd msg */ diff --git a/hw/net/rocker/rocker_of_dpa.c b/hw/net/rocker/rocker_of_dpa.c index 3378f63..4aed178 100644 --- a/hw/net/rocker/rocker_of_dpa.c +++ b/hw/net/rocker/rocker_of_dpa.c @@ -52,10 +52,10 @@ typedef struct of_dpa_flow_key { uint32_t tunnel_id; /* overlay tunnel id */ uint32_t tbl_id; /* table id */ struct { - __be16 vlan_id; /* 0 if no VLAN */ + uint16_t vlan_id; /* 0 if no VLAN */ MACAddr src; /* ethernet source address */ MACAddr dst; /* ethernet destination address */ - __be16 type; /* ethernet frame type */ + uint16_t type; /* ethernet frame type */ } eth; struct { uint8_t proto; /* IP protocol or ARP opcode */ @@ -66,14 +66,14 @@ typedef struct of_dpa_flow_key { union { struct { struct { - __be32 src; /* IP source address */ - __be32 dst; /* IP destination address */ + uint32_t src; /* IP source address */ + uint32_t dst; /* IP destination address */ } addr; union { struct { - __be16 src; /* TCP/UDP/SCTP source port */ - __be16 dst; /* TCP/UDP/SCTP destination port */ - __be16 flags; /* TCP flags */ + uint16_t src; /* TCP/UDP/SCTP source port */ + uint16_t dst; /* TCP/UDP/SCTP destination port */ + uint16_t flags; /* TCP flags */ } tp; struct { MACAddr sha; /* ARP source hardware address */ @@ -86,11 +86,11 @@ typedef struct of_dpa_flow_key { Ipv6Addr src; /* IPv6 source address */ Ipv6Addr dst; /* IPv6 destination address */ } addr; - __be32 label; /* IPv6 flow label */ + uint32_t label; /* IPv6 flow label */ struct { - __be16 src; /* TCP/UDP/SCTP source port */ - __be16 dst; /* TCP/UDP/SCTP destination port */ - __be16 flags; /* TCP flags */ + uint16_t src; /* TCP/UDP/SCTP source port */ + uint16_t dst; /* TCP/UDP/SCTP destination port */ + uint16_t flags; /* TCP flags */ } tp; struct { Ipv6Addr target; /* ND target address */ @@ -112,13 +112,13 @@ typedef struct of_dpa_flow_action { struct { uint32_t group_id; uint32_t tun_log_lport; - __be16 vlan_id; + uint16_t vlan_id; } write; struct { - __be16 new_vlan_id; + uint16_t new_vlan_id; uint32_t out_pport; uint8_t copy_to_cpu; - __be16 vlan_id; + uint16_t vlan_id; } apply; } OfDpaFlowAction; @@ -143,7 +143,7 @@ typedef struct of_dpa_flow { typedef struct of_dpa_flow_pkt_fields { uint32_t tunnel_id; struct eth_header *ethhdr; - __be16 *h_proto; + uint16_t *h_proto; struct vlan_header *vlanhdr; struct ip_header *ipv4hdr; struct ip6_header *ipv6hdr; @@ -180,7 +180,7 @@ typedef struct of_dpa_group { uint32_t group_id; MACAddr src_mac; MACAddr dst_mac; - __be16 vlan_id; + uint16_t vlan_id; } l2_rewrite; struct { uint16_t group_count; @@ -190,13 +190,13 @@ typedef struct of_dpa_group { uint32_t group_id; MACAddr src_mac; MACAddr dst_mac; - __be16 vlan_id; + uint16_t vlan_id; uint8_t ttl_check; } l3_unicast; }; } OfDpaGroup; -static int of_dpa_mask2prefix(__be32 mask) +static int of_dpa_mask2prefix(uint32_t mask) { int i; int count = 32; @@ -451,7 +451,7 @@ static void of_dpa_flow_pkt_parse(OfDpaFlowContext *fc, fc->iovcnt = iovcnt + 2; } -static void of_dpa_flow_pkt_insert_vlan(OfDpaFlowContext *fc, __be16 vlan_id) +static void of_dpa_flow_pkt_insert_vlan(OfDpaFlowContext *fc, uint16_t vlan_id) { OfDpaFlowPktFields *fields = &fc->fields; uint16_t h_proto = fields->ethhdr->h_proto; @@ -486,7 +486,7 @@ static void of_dpa_flow_pkt_strip_vlan(OfDpaFlowContext *fc) static void of_dpa_flow_pkt_hdr_rewrite(OfDpaFlowContext *fc, uint8_t *src_mac, uint8_t *dst_mac, - __be16 vlan_id) + uint16_t vlan_id) { OfDpaFlowPktFields *fields = &fc->fields; diff --git a/hw/net/vmxnet3.c b/hw/net/vmxnet3.c index 83d942a..7c0ca56 100644 --- a/hw/net/vmxnet3.c +++ b/hw/net/vmxnet3.c @@ -41,19 +41,9 @@ #define PCI_DEVICE_ID_VMWARE_VMXNET3_REVISION 0x1 #define VMXNET3_MSIX_BAR_SIZE 0x2000 -/* Compatibility flags for migration */ -#define VMXNET3_COMPAT_FLAG_OLD_MSI_OFFSETS_BIT 0 -#define VMXNET3_COMPAT_FLAG_OLD_MSI_OFFSETS \ - (1 << VMXNET3_COMPAT_FLAG_OLD_MSI_OFFSETS_BIT) -#define VMXNET3_COMPAT_FLAG_DISABLE_PCIE_BIT 1 -#define VMXNET3_COMPAT_FLAG_DISABLE_PCIE \ - (1 << VMXNET3_COMPAT_FLAG_DISABLE_PCIE_BIT) - #define VMXNET3_EXP_EP_OFFSET (0x48) -#define VMXNET3_MSI_OFFSET(s) \ - ((s)->compat_flags & VMXNET3_COMPAT_FLAG_OLD_MSI_OFFSETS ? 0x50 : 0x84) -#define VMXNET3_MSIX_OFFSET(s) \ - ((s)->compat_flags & VMXNET3_COMPAT_FLAG_OLD_MSI_OFFSETS ? 0 : 0x9c) +#define VMXNET3_MSI_OFFSET (0x84) +#define VMXNET3_MSIX_OFFSET (0x9c) #define VMXNET3_DSN_OFFSET (0x100) #define VMXNET3_BAR0_IDX (0) @@ -61,8 +51,7 @@ #define VMXNET3_MSIX_BAR_IDX (2) #define VMXNET3_OFF_MSIX_TABLE (0x000) -#define VMXNET3_OFF_MSIX_PBA(s) \ - ((s)->compat_flags & VMXNET3_COMPAT_FLAG_OLD_MSI_OFFSETS ? 0x800 : 0x1000) +#define VMXNET3_OFF_MSIX_PBA (0x1000) /* Link speed in Mbps should be shifted by 16 */ #define VMXNET3_LINK_SPEED (1000 << 16) @@ -2122,8 +2111,8 @@ vmxnet3_init_msix(VMXNET3State *s) &s->msix_bar, VMXNET3_MSIX_BAR_IDX, VMXNET3_OFF_MSIX_TABLE, &s->msix_bar, - VMXNET3_MSIX_BAR_IDX, VMXNET3_OFF_MSIX_PBA(s), - VMXNET3_MSIX_OFFSET(s), NULL); + VMXNET3_MSIX_BAR_IDX, VMXNET3_OFF_MSIX_PBA, + VMXNET3_MSIX_OFFSET, NULL); if (0 > res) { VMW_WRPRN("Failed to initialize MSI-X, error %d", res); @@ -2221,7 +2210,7 @@ static void vmxnet3_pci_realize(PCIDevice *pci_dev, Error **errp) /* Interrupt pin A */ pci_dev->config[PCI_INTERRUPT_PIN] = 0x01; - ret = msi_init(pci_dev, VMXNET3_MSI_OFFSET(s), VMXNET3_MAX_NMSIX_INTRS, + ret = msi_init(pci_dev, VMXNET3_MSI_OFFSET, VMXNET3_MAX_NMSIX_INTRS, VMXNET3_USE_64BIT, VMXNET3_PER_VECTOR_MASK, NULL); /* Any error other than -ENOTSUP(board's MSI support is broken) * is a programming error. Fall back to INTx silently on -ENOTSUP */ @@ -2249,6 +2238,7 @@ static void vmxnet3_instance_init(Object *obj) device_add_bootindex_property(obj, &s->conf.bootindex, "bootindex", "/ethernet-phy@0", DEVICE(obj)); + PCI_DEVICE(obj)->cap_present |= QEMU_PCI_CAP_EXPRESS; } static void vmxnet3_pci_uninit(PCIDevice *pci_dev) @@ -2472,30 +2462,12 @@ static const VMStateDescription vmstate_vmxnet3 = { static const Property vmxnet3_properties[] = { DEFINE_NIC_PROPERTIES(VMXNET3State, conf), - DEFINE_PROP_BIT("x-old-msi-offsets", VMXNET3State, compat_flags, - VMXNET3_COMPAT_FLAG_OLD_MSI_OFFSETS_BIT, false), - DEFINE_PROP_BIT("x-disable-pcie", VMXNET3State, compat_flags, - VMXNET3_COMPAT_FLAG_DISABLE_PCIE_BIT, false), }; -static void vmxnet3_realize(DeviceState *qdev, Error **errp) -{ - VMXNET3Class *vc = VMXNET3_DEVICE_GET_CLASS(qdev); - PCIDevice *pci_dev = PCI_DEVICE(qdev); - VMXNET3State *s = VMXNET3(qdev); - - if (!(s->compat_flags & VMXNET3_COMPAT_FLAG_DISABLE_PCIE)) { - pci_dev->cap_present |= QEMU_PCI_CAP_EXPRESS; - } - - vc->parent_dc_realize(qdev, errp); -} - static void vmxnet3_class_init(ObjectClass *class, const void *data) { DeviceClass *dc = DEVICE_CLASS(class); PCIDeviceClass *c = PCI_DEVICE_CLASS(class); - VMXNET3Class *vc = VMXNET3_DEVICE_CLASS(class); c->realize = vmxnet3_pci_realize; c->exit = vmxnet3_pci_uninit; @@ -2506,8 +2478,6 @@ static void vmxnet3_class_init(ObjectClass *class, const void *data) c->class_id = PCI_CLASS_NETWORK_ETHERNET; c->subsystem_vendor_id = PCI_VENDOR_ID_VMWARE; c->subsystem_id = PCI_DEVICE_ID_VMWARE_VMXNET3; - device_class_set_parent_realize(dc, vmxnet3_realize, - &vc->parent_dc_realize); dc->desc = "VMWare Paravirtualized Ethernet v3"; device_class_set_legacy_reset(dc, vmxnet3_qdev_reset); dc->vmsd = &vmstate_vmxnet3; diff --git a/hw/nvram/fw_cfg.c b/hw/nvram/fw_cfg.c index 237b9f7..aa24050 100644 --- a/hw/nvram/fw_cfg.c +++ b/hw/nvram/fw_cfg.c @@ -817,62 +817,6 @@ void fw_cfg_modify_i64(FWCfgState *s, uint16_t key, uint64_t value) g_free(old); } -void fw_cfg_set_order_override(FWCfgState *s, int order) -{ - assert(s->fw_cfg_order_override == 0); - s->fw_cfg_order_override = order; -} - -void fw_cfg_reset_order_override(FWCfgState *s) -{ - assert(s->fw_cfg_order_override != 0); - s->fw_cfg_order_override = 0; -} - -/* - * This is the legacy order list. For legacy systems, files are in - * the fw_cfg in the order defined below, by the "order" value. Note - * that some entries (VGA ROMs, NIC option ROMS, etc.) go into a - * specific area, but there may be more than one and they occur in the - * order that the user specifies them on the command line. Those are - * handled in a special manner, using the order override above. - * - * For non-legacy, the files are sorted by filename to avoid this kind - * of complexity in the future. - * - * This is only for x86, other arches don't implement versioning so - * they won't set legacy mode. - */ -static struct { - const char *name; - int order; -} fw_cfg_order[] = { - { "etc/boot-menu-wait", 10 }, - { "bootsplash.jpg", 11 }, - { "bootsplash.bmp", 12 }, - { "etc/boot-fail-wait", 15 }, - { "etc/smbios/smbios-tables", 20 }, - { "etc/smbios/smbios-anchor", 30 }, - { "etc/e820", 40 }, - { "etc/reserved-memory-end", 50 }, - { "genroms/kvmvapic.bin", 55 }, - { "genroms/linuxboot.bin", 60 }, - { }, /* VGA ROMs from pc_vga_init come here, 70. */ - { }, /* NIC option ROMs from pc_nic_init come here, 80. */ - { "etc/system-states", 90 }, - { }, /* User ROMs come here, 100. */ - { }, /* Device FW comes here, 110. */ - { "etc/extra-pci-roots", 120 }, - { "etc/acpi/tables", 130 }, - { "etc/table-loader", 140 }, - { "etc/tpm/log", 150 }, - { "etc/acpi/rsdp", 160 }, - { "bootorder", 170 }, - { "etc/msr_feature_control", 180 }, - -#define FW_CFG_ORDER_OVERRIDE_LAST 200 -}; - /* * Any sub-page size update to these table MRs will be lost during migration, * as we use aligned size in ram_load_precopy() -> qemu_ram_resize() path. @@ -890,29 +834,6 @@ static void fw_cfg_acpi_mr_save(FWCfgState *s, const char *filename, size_t len) } } -static int get_fw_cfg_order(FWCfgState *s, const char *name) -{ - int i; - - if (s->fw_cfg_order_override > 0) { - return s->fw_cfg_order_override; - } - - for (i = 0; i < ARRAY_SIZE(fw_cfg_order); i++) { - if (fw_cfg_order[i].name == NULL) { - continue; - } - - if (strcmp(name, fw_cfg_order[i].name) == 0) { - return fw_cfg_order[i].order; - } - } - - /* Stick unknown stuff at the end. */ - warn_report("Unknown firmware file in legacy mode: %s", name); - return FW_CFG_ORDER_OVERRIDE_LAST; -} - void fw_cfg_add_file_callback(FWCfgState *s, const char *filename, FWCfgCallback select_cb, FWCfgWriteCallback write_cb, @@ -921,7 +842,6 @@ void fw_cfg_add_file_callback(FWCfgState *s, const char *filename, { int i, index, count; size_t dsize; - MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine()); int order = 0; if (!s->files) { @@ -933,22 +853,11 @@ void fw_cfg_add_file_callback(FWCfgState *s, const char *filename, count = be32_to_cpu(s->files->count); assert(count < fw_cfg_file_slots(s)); - /* Find the insertion point. */ - if (mc->legacy_fw_cfg_order) { - /* - * Sort by order. For files with the same order, we keep them - * in the sequence in which they were added. - */ - order = get_fw_cfg_order(s, filename); - for (index = count; - index > 0 && order < s->entry_order[index - 1]; - index--); - } else { - /* Sort by file name. */ - for (index = count; - index > 0 && strcmp(filename, s->files->f[index - 1].name) < 0; - index--); - } + /* Find the insertion point, sorting by file name. */ + for (index = count; + index > 0 && strcmp(filename, s->files->f[index - 1].name) < 0; + index--) + ; /* * Move all the entries from the index point and after down one @@ -1058,7 +967,6 @@ bool fw_cfg_add_file_from_generator(FWCfgState *s, static void fw_cfg_machine_reset(void *opaque) { - MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine()); FWCfgState *s = opaque; void *ptr; size_t len; @@ -1068,11 +976,9 @@ static void fw_cfg_machine_reset(void *opaque) ptr = fw_cfg_modify_file(s, "bootorder", (uint8_t *)buf, len); g_free(ptr); - if (!mc->legacy_fw_cfg_order) { - buf = get_boot_devices_lchs_list(&len); - ptr = fw_cfg_modify_file(s, "bios-geometry", (uint8_t *)buf, len); - g_free(ptr); - } + buf = get_boot_devices_lchs_list(&len); + ptr = fw_cfg_modify_file(s, "bios-geometry", (uint8_t *)buf, len); + g_free(ptr); } static void fw_cfg_machine_ready(struct Notifier *n, void *data) diff --git a/hw/pci/pci.c b/hw/pci/pci.c index f5ab510..9b4bf48 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -128,6 +128,12 @@ static GSequence *pci_acpi_index_list(void) return used_acpi_index_list; } +static void pci_set_master(PCIDevice *d, bool enable) +{ + memory_region_set_enabled(&d->bus_master_enable_region, enable); + d->is_master = enable; /* cache the status */ +} + static void pci_init_bus_master(PCIDevice *pci_dev) { AddressSpace *dma_as = pci_device_iommu_address_space(pci_dev); @@ -135,7 +141,7 @@ static void pci_init_bus_master(PCIDevice *pci_dev) memory_region_init_alias(&pci_dev->bus_master_enable_region, OBJECT(pci_dev), "bus master", dma_as->root, 0, memory_region_size(dma_as->root)); - memory_region_set_enabled(&pci_dev->bus_master_enable_region, false); + pci_set_master(pci_dev, false); memory_region_add_subregion(&pci_dev->bus_master_container_region, 0, &pci_dev->bus_master_enable_region); } @@ -804,9 +810,8 @@ static int get_pci_config_device(QEMUFile *f, void *pv, size_t size, pci_bridge_update_mappings(PCI_BRIDGE(s)); } - memory_region_set_enabled(&s->bus_master_enable_region, - pci_get_word(s->config + PCI_COMMAND) - & PCI_COMMAND_MASTER); + pci_set_master(s, pci_get_word(s->config + PCI_COMMAND) + & PCI_COMMAND_MASTER); g_free(config); return 0; @@ -1725,7 +1730,7 @@ static void pci_update_mappings(PCIDevice *d) pci_update_vga(d); } -static inline int pci_irq_disabled(PCIDevice *d) +int pci_irq_disabled(PCIDevice *d) { return pci_get_word(d->config + PCI_COMMAND) & PCI_COMMAND_INTX_DISABLE; } @@ -1787,9 +1792,8 @@ void pci_default_write_config(PCIDevice *d, uint32_t addr, uint32_t val_in, int if (ranges_overlap(addr, l, PCI_COMMAND, 2)) { pci_update_irq_disabled(d, was_irq_disabled); - memory_region_set_enabled(&d->bus_master_enable_region, - (pci_get_word(d->config + PCI_COMMAND) - & PCI_COMMAND_MASTER) && d->enabled); + pci_set_master(d, (pci_get_word(d->config + PCI_COMMAND) & + PCI_COMMAND_MASTER) && d->enabled); } msi_write_config(d, addr, val_in, l); @@ -2935,6 +2939,23 @@ AddressSpace *pci_device_iommu_address_space(PCIDevice *dev) return &address_space_memory; } +int pci_iommu_init_iotlb_notifier(PCIDevice *dev, IOMMUNotifier *n, + IOMMUNotify fn, void *opaque) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->init_iotlb_notifier) { + iommu_bus->iommu_ops->init_iotlb_notifier(bus, iommu_bus->iommu_opaque, + devfn, n, fn, opaque); + return 0; + } + + return -ENODEV; +} + bool pci_device_set_iommu_device(PCIDevice *dev, HostIOMMUDevice *hiod, Error **errp) { @@ -2966,6 +2987,170 @@ void pci_device_unset_iommu_device(PCIDevice *dev) } } +int pci_pri_request_page(PCIDevice *dev, uint32_t pasid, bool priv_req, + bool exec_req, hwaddr addr, bool lpig, + uint16_t prgi, bool is_read, bool is_write) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + if (!dev->is_master || + ((pasid != PCI_NO_PASID) && !pcie_pasid_enabled(dev))) { + return -EPERM; + } + + if (!pcie_pri_enabled(dev)) { + return -EPERM; + } + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->pri_request_page) { + return iommu_bus->iommu_ops->pri_request_page(bus, + iommu_bus->iommu_opaque, + devfn, pasid, priv_req, + exec_req, addr, lpig, prgi, + is_read, is_write); + } + + return -ENODEV; +} + +int pci_pri_register_notifier(PCIDevice *dev, uint32_t pasid, + IOMMUPRINotifier *notifier) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + if (!dev->is_master || + ((pasid != PCI_NO_PASID) && !pcie_pasid_enabled(dev))) { + return -EPERM; + } + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->pri_register_notifier) { + iommu_bus->iommu_ops->pri_register_notifier(bus, + iommu_bus->iommu_opaque, + devfn, pasid, notifier); + return 0; + } + + return -ENODEV; +} + +void pci_pri_unregister_notifier(PCIDevice *dev, uint32_t pasid) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->pri_unregister_notifier) { + iommu_bus->iommu_ops->pri_unregister_notifier(bus, + iommu_bus->iommu_opaque, + devfn, pasid); + } +} + +ssize_t pci_ats_request_translation(PCIDevice *dev, uint32_t pasid, + bool priv_req, bool exec_req, + hwaddr addr, size_t length, + bool no_write, IOMMUTLBEntry *result, + size_t result_length, + uint32_t *err_count) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + if (!dev->is_master || + ((pasid != PCI_NO_PASID) && !pcie_pasid_enabled(dev))) { + return -EPERM; + } + + if (result_length == 0) { + return -ENOSPC; + } + + if (!pcie_ats_enabled(dev)) { + return -EPERM; + } + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->ats_request_translation) { + return iommu_bus->iommu_ops->ats_request_translation(bus, + iommu_bus->iommu_opaque, + devfn, pasid, priv_req, + exec_req, addr, length, + no_write, result, + result_length, err_count); + } + + return -ENODEV; +} + +int pci_iommu_register_iotlb_notifier(PCIDevice *dev, uint32_t pasid, + IOMMUNotifier *n) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + if ((pasid != PCI_NO_PASID) && !pcie_pasid_enabled(dev)) { + return -EPERM; + } + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->register_iotlb_notifier) { + iommu_bus->iommu_ops->register_iotlb_notifier(bus, + iommu_bus->iommu_opaque, devfn, + pasid, n); + return 0; + } + + return -ENODEV; +} + +int pci_iommu_unregister_iotlb_notifier(PCIDevice *dev, uint32_t pasid, + IOMMUNotifier *n) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + if ((pasid != PCI_NO_PASID) && !pcie_pasid_enabled(dev)) { + return -EPERM; + } + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->unregister_iotlb_notifier) { + iommu_bus->iommu_ops->unregister_iotlb_notifier(bus, + iommu_bus->iommu_opaque, + devfn, pasid, n); + return 0; + } + + return -ENODEV; +} + +int pci_iommu_get_iotlb_info(PCIDevice *dev, uint8_t *addr_width, + uint32_t *min_page_size) +{ + PCIBus *bus; + PCIBus *iommu_bus; + int devfn; + + pci_device_get_iommu_bus_devfn(dev, &bus, &iommu_bus, &devfn); + if (iommu_bus && iommu_bus->iommu_ops->get_iotlb_info) { + iommu_bus->iommu_ops->get_iotlb_info(iommu_bus->iommu_opaque, + addr_width, min_page_size); + return 0; + } + + return -ENODEV; +} + void pci_setup_iommu(PCIBus *bus, const PCIIOMMUOps *ops, void *opaque) { /* @@ -3100,9 +3285,8 @@ void pci_set_enabled(PCIDevice *d, bool state) d->enabled = state; pci_update_mappings(d); - memory_region_set_enabled(&d->bus_master_enable_region, - (pci_get_word(d->config + PCI_COMMAND) - & PCI_COMMAND_MASTER) && d->enabled); + pci_set_master(d, (pci_get_word(d->config + PCI_COMMAND) + & PCI_COMMAND_MASTER) && d->enabled); if (qdev_is_realized(&d->qdev)) { pci_device_reset(d); } diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c index 1b12db6..eaeb688 100644 --- a/hw/pci/pcie.c +++ b/hw/pci/pcie.c @@ -1214,3 +1214,81 @@ void pcie_acs_reset(PCIDevice *dev) pci_set_word(dev->config + dev->exp.acs_cap + PCI_ACS_CTRL, 0); } } + +/* PASID */ +void pcie_pasid_init(PCIDevice *dev, uint16_t offset, uint8_t pasid_width, + bool exec_perm, bool priv_mod) +{ + static const uint16_t control_reg_rw_mask = 0x07; + uint16_t capability_reg; + + assert(pasid_width <= PCI_EXT_CAP_PASID_MAX_WIDTH); + + pcie_add_capability(dev, PCI_EXT_CAP_ID_PASID, PCI_PASID_VER, offset, + PCI_EXT_CAP_PASID_SIZEOF); + + capability_reg = ((uint16_t)pasid_width) << PCI_PASID_CAP_WIDTH_SHIFT; + capability_reg |= exec_perm ? PCI_PASID_CAP_EXEC : 0; + capability_reg |= priv_mod ? PCI_PASID_CAP_PRIV : 0; + pci_set_word(dev->config + offset + PCI_PASID_CAP, capability_reg); + + /* Everything is disabled by default */ + pci_set_word(dev->config + offset + PCI_PASID_CTRL, 0); + + pci_set_word(dev->wmask + offset + PCI_PASID_CTRL, control_reg_rw_mask); + + dev->exp.pasid_cap = offset; +} + +/* PRI */ +void pcie_pri_init(PCIDevice *dev, uint16_t offset, uint32_t outstanding_pr_cap, + bool prg_response_pasid_req) +{ + static const uint16_t control_reg_rw_mask = 0x3; + static const uint16_t status_reg_rw1_mask = 0x3; + static const uint32_t pr_alloc_reg_rw_mask = 0xffffffff; + uint16_t status_reg; + + status_reg = prg_response_pasid_req ? PCI_PRI_STATUS_PASID : 0; + status_reg |= PCI_PRI_STATUS_STOPPED; /* Stopped by default */ + + pcie_add_capability(dev, PCI_EXT_CAP_ID_PRI, PCI_PRI_VER, offset, + PCI_EXT_CAP_PRI_SIZEOF); + /* Disabled by default */ + + pci_set_word(dev->config + offset + PCI_PRI_STATUS, status_reg); + pci_set_long(dev->config + offset + PCI_PRI_MAX_REQ, outstanding_pr_cap); + + pci_set_word(dev->wmask + offset + PCI_PRI_CTRL, control_reg_rw_mask); + pci_set_word(dev->w1cmask + offset + PCI_PRI_STATUS, status_reg_rw1_mask); + pci_set_long(dev->wmask + offset + PCI_PRI_ALLOC_REQ, pr_alloc_reg_rw_mask); + + dev->exp.pri_cap = offset; +} + +bool pcie_pri_enabled(const PCIDevice *dev) +{ + if (!pci_is_express(dev) || !dev->exp.pri_cap) { + return false; + } + return (pci_get_word(dev->config + dev->exp.pri_cap + PCI_PRI_CTRL) & + PCI_PRI_CTRL_ENABLE) != 0; +} + +bool pcie_pasid_enabled(const PCIDevice *dev) +{ + if (!pci_is_express(dev) || !dev->exp.pasid_cap) { + return false; + } + return (pci_get_word(dev->config + dev->exp.pasid_cap + PCI_PASID_CTRL) & + PCI_PASID_CTRL_ENABLE) != 0; +} + +bool pcie_ats_enabled(const PCIDevice *dev) +{ + if (!pci_is_express(dev) || !dev->exp.ats_cap) { + return false; + } + return (pci_get_word(dev->config + dev->exp.ats_cap + PCI_ATS_CTRL) & + PCI_ATS_CTRL_ENABLE) != 0; +} diff --git a/hw/scsi/vmw_pvscsi.c b/hw/scsi/vmw_pvscsi.c index d5825b6..7c98b1b 100644 --- a/hw/scsi/vmw_pvscsi.c +++ b/hw/scsi/vmw_pvscsi.c @@ -68,18 +68,7 @@ struct PVSCSIClass { OBJECT_DECLARE_TYPE(PVSCSIState, PVSCSIClass, PVSCSI) -/* Compatibility flags for migration */ -#define PVSCSI_COMPAT_OLD_PCI_CONFIGURATION_BIT 0 -#define PVSCSI_COMPAT_OLD_PCI_CONFIGURATION \ - (1 << PVSCSI_COMPAT_OLD_PCI_CONFIGURATION_BIT) -#define PVSCSI_COMPAT_DISABLE_PCIE_BIT 1 -#define PVSCSI_COMPAT_DISABLE_PCIE \ - (1 << PVSCSI_COMPAT_DISABLE_PCIE_BIT) - -#define PVSCSI_USE_OLD_PCI_CONFIGURATION(s) \ - ((s)->compat_flags & PVSCSI_COMPAT_OLD_PCI_CONFIGURATION) -#define PVSCSI_MSI_OFFSET(s) \ - (PVSCSI_USE_OLD_PCI_CONFIGURATION(s) ? 0x50 : 0x7c) +#define PVSCSI_MSI_OFFSET (0x7c) #define PVSCSI_EXP_EP_OFFSET (0x40) typedef struct PVSCSIRingInfo { @@ -129,8 +118,6 @@ struct PVSCSIState { uint8_t msi_used; /* For migration compatibility */ PVSCSIRingInfo rings; /* Data transfer rings manager */ uint32_t resetting; /* Reset in progress */ - - uint32_t compat_flags; }; typedef struct PVSCSIRequest { @@ -1110,7 +1097,7 @@ pvscsi_init_msi(PVSCSIState *s) int res; PCIDevice *d = PCI_DEVICE(s); - res = msi_init(d, PVSCSI_MSI_OFFSET(s), PVSCSI_MSIX_NUM_VECTORS, + res = msi_init(d, PVSCSI_MSI_OFFSET, PVSCSI_MSIX_NUM_VECTORS, PVSCSI_USE_64BIT, PVSCSI_PER_VECTOR_MASK, NULL); if (res < 0) { trace_pvscsi_init_msi_fail(res); @@ -1158,15 +1145,11 @@ pvscsi_realizefn(PCIDevice *pci_dev, Error **errp) trace_pvscsi_state("init"); /* PCI subsystem ID, subsystem vendor ID, revision */ - if (PVSCSI_USE_OLD_PCI_CONFIGURATION(s)) { - pci_set_word(pci_dev->config + PCI_SUBSYSTEM_ID, 0x1000); - } else { - pci_set_word(pci_dev->config + PCI_SUBSYSTEM_VENDOR_ID, - PCI_VENDOR_ID_VMWARE); - pci_set_word(pci_dev->config + PCI_SUBSYSTEM_ID, - PCI_DEVICE_ID_VMWARE_PVSCSI); - pci_config_set_revision(pci_dev->config, 0x2); - } + pci_set_word(pci_dev->config + PCI_SUBSYSTEM_VENDOR_ID, + PCI_VENDOR_ID_VMWARE); + pci_set_word(pci_dev->config + PCI_SUBSYSTEM_ID, + PCI_DEVICE_ID_VMWARE_PVSCSI); + pci_config_set_revision(pci_dev->config, 0x2); /* PCI latency timer = 255 */ pci_dev->config[PCI_LATENCY_TIMER] = 0xff; @@ -1234,21 +1217,8 @@ pvscsi_post_load(void *opaque, int version_id) return 0; } -static bool pvscsi_vmstate_need_pcie_device(void *opaque) -{ - PVSCSIState *s = PVSCSI(opaque); - - return !(s->compat_flags & PVSCSI_COMPAT_DISABLE_PCIE); -} - -static bool pvscsi_vmstate_test_pci_device(void *opaque, int version_id) -{ - return !pvscsi_vmstate_need_pcie_device(opaque); -} - static const VMStateDescription vmstate_pvscsi_pcie_device = { .name = "pvscsi/pcie", - .needed = pvscsi_vmstate_need_pcie_device, .fields = (const VMStateField[]) { VMSTATE_PCI_DEVICE(parent_obj, PVSCSIState), VMSTATE_END_OF_LIST() @@ -1262,9 +1232,6 @@ static const VMStateDescription vmstate_pvscsi = { .pre_save = pvscsi_pre_save, .post_load = pvscsi_post_load, .fields = (const VMStateField[]) { - VMSTATE_STRUCT_TEST(parent_obj, PVSCSIState, - pvscsi_vmstate_test_pci_device, 0, - vmstate_pci_device, PCIDevice), VMSTATE_UINT8(msi_used, PVSCSIState), VMSTATE_UINT32(resetting, PVSCSIState), VMSTATE_UINT64(reg_interrupt_status, PVSCSIState), @@ -1298,30 +1265,17 @@ static const VMStateDescription vmstate_pvscsi = { static const Property pvscsi_properties[] = { DEFINE_PROP_UINT8("use_msg", PVSCSIState, use_msg, 1), - DEFINE_PROP_BIT("x-old-pci-configuration", PVSCSIState, compat_flags, - PVSCSI_COMPAT_OLD_PCI_CONFIGURATION_BIT, false), - DEFINE_PROP_BIT("x-disable-pcie", PVSCSIState, compat_flags, - PVSCSI_COMPAT_DISABLE_PCIE_BIT, false), }; -static void pvscsi_realize(DeviceState *qdev, Error **errp) +static void pvscsi_instance_init(Object *obj) { - PVSCSIClass *pvs_c = PVSCSI_GET_CLASS(qdev); - PCIDevice *pci_dev = PCI_DEVICE(qdev); - PVSCSIState *s = PVSCSI(qdev); - - if (!(s->compat_flags & PVSCSI_COMPAT_DISABLE_PCIE)) { - pci_dev->cap_present |= QEMU_PCI_CAP_EXPRESS; - } - - pvs_c->parent_dc_realize(qdev, errp); + PCI_DEVICE(obj)->cap_present |= QEMU_PCI_CAP_EXPRESS; } static void pvscsi_class_init(ObjectClass *klass, const void *data) { DeviceClass *dc = DEVICE_CLASS(klass); PCIDeviceClass *k = PCI_DEVICE_CLASS(klass); - PVSCSIClass *pvs_k = PVSCSI_CLASS(klass); HotplugHandlerClass *hc = HOTPLUG_HANDLER_CLASS(klass); k->realize = pvscsi_realizefn; @@ -1330,8 +1284,6 @@ static void pvscsi_class_init(ObjectClass *klass, const void *data) k->device_id = PCI_DEVICE_ID_VMWARE_PVSCSI; k->class_id = PCI_CLASS_STORAGE_SCSI; k->subsystem_id = 0x1000; - device_class_set_parent_realize(dc, pvscsi_realize, - &pvs_k->parent_dc_realize); device_class_set_legacy_reset(dc, pvscsi_reset); dc->vmsd = &vmstate_pvscsi; device_class_set_props(dc, pvscsi_properties); @@ -1346,6 +1298,7 @@ static const TypeInfo pvscsi_info = { .class_size = sizeof(PVSCSIClass), .instance_size = sizeof(PVSCSIState), .class_init = pvscsi_class_init, + .instance_init = pvscsi_instance_init, .interfaces = (const InterfaceInfo[]) { { TYPE_HOTPLUG_HANDLER }, { INTERFACE_PCIE_DEVICE }, diff --git a/hw/timer/hpet.c b/hw/timer/hpet.c index d1b7bc5..0fd1337 100644 --- a/hw/timer/hpet.c +++ b/hw/timer/hpet.c @@ -426,30 +426,11 @@ static uint64_t hpet_ram_read(void *opaque, hwaddr addr, uint64_t cur_tick; trace_hpet_ram_read(addr); + addr &= ~4; - /*address range of all TN regs*/ - if (addr >= 0x100 && addr <= 0x3ff) { - uint8_t timer_id = (addr - 0x100) / 0x20; - HPETTimer *timer = &s->timer[timer_id]; - - if (timer_id > s->num_timers) { - trace_hpet_timer_id_out_of_range(timer_id); - return 0; - } - - switch (addr & 0x18) { - case HPET_TN_CFG: // including interrupt capabilities - return timer->config >> shift; - case HPET_TN_CMP: // comparator register - return timer->cmp >> shift; - case HPET_TN_ROUTE: - return timer->fsb >> shift; - default: - trace_hpet_ram_read_invalid(); - break; - } - } else { - switch (addr & ~4) { + /*address range of all global regs*/ + if (addr <= 0xff) { + switch (addr) { case HPET_ID: // including HPET_PERIOD return s->capability >> shift; case HPET_CFG: @@ -468,6 +449,26 @@ static uint64_t hpet_ram_read(void *opaque, hwaddr addr, trace_hpet_ram_read_invalid(); break; } + } else { + uint8_t timer_id = (addr - 0x100) / 0x20; + HPETTimer *timer = &s->timer[timer_id]; + + if (timer_id > s->num_timers) { + trace_hpet_timer_id_out_of_range(timer_id); + return 0; + } + + switch (addr & 0x1f) { + case HPET_TN_CFG: // including interrupt capabilities + return timer->config >> shift; + case HPET_TN_CMP: // comparator register + return timer->cmp >> shift; + case HPET_TN_ROUTE: + return timer->fsb >> shift; + default: + trace_hpet_ram_read_invalid(); + break; + } } return 0; } @@ -482,9 +483,67 @@ static void hpet_ram_write(void *opaque, hwaddr addr, uint64_t old_val, new_val, cleared; trace_hpet_ram_write(addr, value); + addr &= ~4; - /*address range of all TN regs*/ - if (addr >= 0x100 && addr <= 0x3ff) { + /*address range of all global regs*/ + if (addr <= 0xff) { + switch (addr) { + case HPET_ID: + return; + case HPET_CFG: + old_val = s->config; + new_val = deposit64(old_val, shift, len, value); + new_val = hpet_fixup_reg(new_val, old_val, HPET_CFG_WRITE_MASK); + s->config = new_val; + if (activating_bit(old_val, new_val, HPET_CFG_ENABLE)) { + /* Enable main counter and interrupt generation. */ + s->hpet_offset = + ticks_to_ns(s->hpet_counter) - qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + for (i = 0; i < s->num_timers; i++) { + if (timer_enabled(&s->timer[i]) && (s->isr & (1 << i))) { + update_irq(&s->timer[i], 1); + } + hpet_set_timer(&s->timer[i]); + } + } else if (deactivating_bit(old_val, new_val, HPET_CFG_ENABLE)) { + /* Halt main counter and disable interrupt generation. */ + s->hpet_counter = hpet_get_ticks(s); + for (i = 0; i < s->num_timers; i++) { + hpet_del_timer(&s->timer[i]); + } + } + /* i8254 and RTC output pins are disabled + * when HPET is in legacy mode */ + if (activating_bit(old_val, new_val, HPET_CFG_LEGACY)) { + qemu_set_irq(s->pit_enabled, 0); + qemu_irq_lower(s->irqs[0]); + qemu_irq_lower(s->irqs[RTC_ISA_IRQ]); + } else if (deactivating_bit(old_val, new_val, HPET_CFG_LEGACY)) { + qemu_irq_lower(s->irqs[0]); + qemu_set_irq(s->pit_enabled, 1); + qemu_set_irq(s->irqs[RTC_ISA_IRQ], s->rtc_irq_level); + } + break; + case HPET_STATUS: + new_val = value << shift; + cleared = new_val & s->isr; + for (i = 0; i < s->num_timers; i++) { + if (cleared & (1 << i)) { + update_irq(&s->timer[i], 0); + } + } + break; + case HPET_COUNTER: + if (hpet_enabled(s)) { + trace_hpet_ram_write_counter_write_while_enabled(); + } + s->hpet_counter = deposit64(s->hpet_counter, shift, len, value); + break; + default: + trace_hpet_ram_write_invalid(); + break; + } + } else { uint8_t timer_id = (addr - 0x100) / 0x20; HPETTimer *timer = &s->timer[timer_id]; @@ -550,63 +609,6 @@ static void hpet_ram_write(void *opaque, hwaddr addr, break; } return; - } else { - switch (addr & ~4) { - case HPET_ID: - return; - case HPET_CFG: - old_val = s->config; - new_val = deposit64(old_val, shift, len, value); - new_val = hpet_fixup_reg(new_val, old_val, HPET_CFG_WRITE_MASK); - s->config = new_val; - if (activating_bit(old_val, new_val, HPET_CFG_ENABLE)) { - /* Enable main counter and interrupt generation. */ - s->hpet_offset = - ticks_to_ns(s->hpet_counter) - qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - for (i = 0; i < s->num_timers; i++) { - if (timer_enabled(&s->timer[i]) && (s->isr & (1 << i))) { - update_irq(&s->timer[i], 1); - } - hpet_set_timer(&s->timer[i]); - } - } else if (deactivating_bit(old_val, new_val, HPET_CFG_ENABLE)) { - /* Halt main counter and disable interrupt generation. */ - s->hpet_counter = hpet_get_ticks(s); - for (i = 0; i < s->num_timers; i++) { - hpet_del_timer(&s->timer[i]); - } - } - /* i8254 and RTC output pins are disabled - * when HPET is in legacy mode */ - if (activating_bit(old_val, new_val, HPET_CFG_LEGACY)) { - qemu_set_irq(s->pit_enabled, 0); - qemu_irq_lower(s->irqs[0]); - qemu_irq_lower(s->irqs[RTC_ISA_IRQ]); - } else if (deactivating_bit(old_val, new_val, HPET_CFG_LEGACY)) { - qemu_irq_lower(s->irqs[0]); - qemu_set_irq(s->pit_enabled, 1); - qemu_set_irq(s->irqs[RTC_ISA_IRQ], s->rtc_irq_level); - } - break; - case HPET_STATUS: - new_val = value << shift; - cleared = new_val & s->isr; - for (i = 0; i < s->num_timers; i++) { - if (cleared & (1 << i)) { - update_irq(&s->timer[i], 0); - } - } - break; - case HPET_COUNTER: - if (hpet_enabled(s)) { - trace_hpet_ram_write_counter_write_while_enabled(); - } - s->hpet_counter = deposit64(s->hpet_counter, shift, len, value); - break; - default: - trace_hpet_ram_write_invalid(); - break; - } } } diff --git a/hw/vfio/container-base.c b/hw/vfio/container-base.c index 1c6ca94..d834bd4 100644 --- a/hw/vfio/container-base.c +++ b/hw/vfio/container-base.c @@ -75,12 +75,12 @@ void vfio_address_space_insert(VFIOAddressSpace *space, int vfio_container_dma_map(VFIOContainerBase *bcontainer, hwaddr iova, ram_addr_t size, - void *vaddr, bool readonly) + void *vaddr, bool readonly, MemoryRegion *mr) { VFIOIOMMUClass *vioc = VFIO_IOMMU_GET_CLASS(bcontainer); g_assert(vioc->dma_map); - return vioc->dma_map(bcontainer, iova, size, vaddr, readonly); + return vioc->dma_map(bcontainer, iova, size, vaddr, readonly, mr); } int vfio_container_dma_unmap(VFIOContainerBase *bcontainer, diff --git a/hw/vfio/container.c b/hw/vfio/container.c index a9f0dba..0f948d0 100644 --- a/hw/vfio/container.c +++ b/hw/vfio/container.c @@ -33,8 +33,8 @@ #include "qapi/error.h" #include "pci.h" #include "hw/vfio/vfio-container.h" +#include "hw/vfio/vfio-cpr.h" #include "vfio-helpers.h" -#include "vfio-cpr.h" #include "vfio-listener.h" #define TYPE_HOST_IOMMU_DEVICE_LEGACY_VFIO TYPE_HOST_IOMMU_DEVICE "-legacy-vfio" @@ -207,7 +207,8 @@ static int vfio_legacy_dma_unmap(const VFIOContainerBase *bcontainer, } static int vfio_legacy_dma_map(const VFIOContainerBase *bcontainer, hwaddr iova, - ram_addr_t size, void *vaddr, bool readonly) + ram_addr_t size, void *vaddr, bool readonly, + MemoryRegion *mr) { const VFIOContainer *container = container_of(bcontainer, VFIOContainer, bcontainer); diff --git a/hw/vfio/cpr.c b/hw/vfio/cpr.c index 3214184..0210e76 100644 --- a/hw/vfio/cpr.c +++ b/hw/vfio/cpr.c @@ -8,9 +8,9 @@ #include "qemu/osdep.h" #include "hw/vfio/vfio-device.h" #include "migration/misc.h" +#include "hw/vfio/vfio-cpr.h" #include "qapi/error.h" #include "system/runstate.h" -#include "vfio-cpr.h" static int vfio_cpr_reboot_notifier(NotifierWithReturn *notifier, MigrationEvent *e, Error **errp) diff --git a/hw/vfio/igd.c b/hw/vfio/igd.c index e7952d1..e7a9d1f 100644 --- a/hw/vfio/igd.c +++ b/hw/vfio/igd.c @@ -187,23 +187,21 @@ static bool vfio_pci_igd_opregion_init(VFIOPCIDevice *vdev, } static bool vfio_pci_igd_opregion_detect(VFIOPCIDevice *vdev, - struct vfio_region_info **opregion, - Error **errp) + struct vfio_region_info **opregion) { int ret; - /* Hotplugging is not supported for opregion access */ - if (vdev->pdev.qdev.hotplugged) { - error_setg(errp, "IGD OpRegion is not supported on hotplugged device"); - return false; - } - ret = vfio_device_get_region_info_type(&vdev->vbasedev, VFIO_REGION_TYPE_PCI_VENDOR_TYPE | PCI_VENDOR_ID_INTEL, VFIO_REGION_SUBTYPE_INTEL_IGD_OPREGION, opregion); if (ret) { - error_setg_errno(errp, -ret, - "Device does not supports IGD OpRegion feature"); + return false; + } + + /* Hotplugging is not supported for opregion access */ + if (vdev->pdev.qdev.hotplugged) { + warn_report("IGD device detected, but OpRegion is not supported " + "on hotplugged device."); return false; } @@ -524,7 +522,7 @@ static bool vfio_pci_igd_config_quirk(VFIOPCIDevice *vdev, Error **errp) } /* IGD device always comes with OpRegion */ - if (!vfio_pci_igd_opregion_detect(vdev, &opregion, errp)) { + if (!vfio_pci_igd_opregion_detect(vdev, &opregion)) { return true; } info_report("OpRegion detected on Intel display %x.", vdev->device_id); @@ -695,7 +693,7 @@ static bool vfio_pci_kvmgt_config_quirk(VFIOPCIDevice *vdev, Error **errp) return true; } - if (!vfio_pci_igd_opregion_detect(vdev, &opregion, errp)) { + if (!vfio_pci_igd_opregion_detect(vdev, &opregion)) { /* Should never reach here, KVMGT always emulates OpRegion */ return false; } diff --git a/hw/vfio/iommufd.c b/hw/vfio/iommufd.c index af1c7ab..d3efef7 100644 --- a/hw/vfio/iommufd.c +++ b/hw/vfio/iommufd.c @@ -21,20 +21,21 @@ #include "qapi/error.h" #include "system/iommufd.h" #include "hw/qdev-core.h" +#include "hw/vfio/vfio-cpr.h" #include "system/reset.h" #include "qemu/cutils.h" #include "qemu/chardev_open.h" #include "pci.h" #include "vfio-iommufd.h" #include "vfio-helpers.h" -#include "vfio-cpr.h" #include "vfio-listener.h" #define TYPE_HOST_IOMMU_DEVICE_IOMMUFD_VFIO \ TYPE_HOST_IOMMU_DEVICE_IOMMUFD "-vfio" static int iommufd_cdev_map(const VFIOContainerBase *bcontainer, hwaddr iova, - ram_addr_t size, void *vaddr, bool readonly) + ram_addr_t size, void *vaddr, bool readonly, + MemoryRegion *mr) { const VFIOIOMMUFDContainer *container = container_of(bcontainer, VFIOIOMMUFDContainer, bcontainer); @@ -592,6 +593,10 @@ found_container: goto err_listener_register; } + /* + * Do not move this code before attachment! The nested IOMMU support + * needs device and hwpt id which are generated only after attachment. + */ if (!vfio_device_hiod_create_and_realize(vbasedev, TYPE_HOST_IOMMU_DEVICE_IOMMUFD_VFIO, errp)) { goto err_listener_register; @@ -810,21 +815,38 @@ static void vfio_iommu_iommufd_class_init(ObjectClass *klass, const void *data) vioc->query_dirty_bitmap = iommufd_query_dirty_bitmap; }; +static bool +host_iommu_device_iommufd_vfio_attach_hwpt(HostIOMMUDeviceIOMMUFD *idev, + uint32_t hwpt_id, Error **errp) +{ + VFIODevice *vbasedev = HOST_IOMMU_DEVICE(idev)->agent; + + return !iommufd_cdev_attach_ioas_hwpt(vbasedev, hwpt_id, errp); +} + +static bool +host_iommu_device_iommufd_vfio_detach_hwpt(HostIOMMUDeviceIOMMUFD *idev, + Error **errp) +{ + VFIODevice *vbasedev = HOST_IOMMU_DEVICE(idev)->agent; + + return iommufd_cdev_detach_ioas_hwpt(vbasedev, errp); +} + static bool hiod_iommufd_vfio_realize(HostIOMMUDevice *hiod, void *opaque, Error **errp) { VFIODevice *vdev = opaque; + HostIOMMUDeviceIOMMUFD *idev; HostIOMMUDeviceCaps *caps = &hiod->caps; + VendorCaps *vendor_caps = &caps->vendor_caps; enum iommu_hw_info_type type; - union { - struct iommu_hw_info_vtd vtd; - } data; uint64_t hw_caps; hiod->agent = opaque; - if (!iommufd_backend_get_device_info(vdev->iommufd, vdev->devid, - &type, &data, sizeof(data), + if (!iommufd_backend_get_device_info(vdev->iommufd, vdev->devid, &type, + vendor_caps, sizeof(*vendor_caps), &hw_caps, errp)) { return false; } @@ -833,6 +855,11 @@ static bool hiod_iommufd_vfio_realize(HostIOMMUDevice *hiod, void *opaque, caps->type = type; caps->hw_caps = hw_caps; + idev = HOST_IOMMU_DEVICE_IOMMUFD(hiod); + idev->iommufd = vdev->iommufd; + idev->devid = vdev->devid; + idev->hwpt_id = vdev->hwpt->hwpt_id; + return true; } @@ -858,10 +885,14 @@ hiod_iommufd_vfio_get_page_size_mask(HostIOMMUDevice *hiod) static void hiod_iommufd_vfio_class_init(ObjectClass *oc, const void *data) { HostIOMMUDeviceClass *hiodc = HOST_IOMMU_DEVICE_CLASS(oc); + HostIOMMUDeviceIOMMUFDClass *idevc = HOST_IOMMU_DEVICE_IOMMUFD_CLASS(oc); hiodc->realize = hiod_iommufd_vfio_realize; hiodc->get_iova_ranges = hiod_iommufd_vfio_get_iova_ranges; hiodc->get_page_size_mask = hiod_iommufd_vfio_get_page_size_mask; + + idevc->attach_hwpt = host_iommu_device_iommufd_vfio_attach_hwpt; + idevc->detach_hwpt = host_iommu_device_iommufd_vfio_detach_hwpt; }; static const TypeInfo types[] = { diff --git a/hw/vfio/listener.c b/hw/vfio/listener.c index bfacb3d..203ed03 100644 --- a/hw/vfio/listener.c +++ b/hw/vfio/listener.c @@ -90,16 +90,17 @@ static bool vfio_listener_skipped_section(MemoryRegionSection *section) section->offset_within_address_space & (1ULL << 63); } -/* Called with rcu_read_lock held. */ -static bool vfio_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr, - ram_addr_t *ram_addr, bool *read_only, - Error **errp) +/* + * Called with rcu_read_lock held. + * The returned MemoryRegion must not be accessed after calling rcu_read_unlock. + */ +static MemoryRegion *vfio_translate_iotlb(IOMMUTLBEntry *iotlb, hwaddr *xlat_p, + Error **errp) { - bool ret, mr_has_discard_manager; + MemoryRegion *mr; - ret = memory_get_xlat_addr(iotlb, vaddr, ram_addr, read_only, - &mr_has_discard_manager, errp); - if (ret && mr_has_discard_manager) { + mr = memory_translate_iotlb(iotlb, xlat_p, errp); + if (mr && memory_region_has_ram_discard_manager(mr)) { /* * Malicious VMs might trigger discarding of IOMMU-mapped memory. The * pages will remain pinned inside vfio until unmapped, resulting in a @@ -118,7 +119,7 @@ static bool vfio_get_xlat_addr(IOMMUTLBEntry *iotlb, void **vaddr, " intended via an IOMMU. It's possible to mitigate " " by setting/adjusting RLIMIT_MEMLOCK."); } - return ret; + return mr; } static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) @@ -126,6 +127,8 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) VFIOGuestIOMMU *giommu = container_of(n, VFIOGuestIOMMU, n); VFIOContainerBase *bcontainer = giommu->bcontainer; hwaddr iova = iotlb->iova + giommu->iommu_offset; + MemoryRegion *mr; + hwaddr xlat; void *vaddr; int ret; Error *local_err = NULL; @@ -150,10 +153,14 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) { bool read_only; - if (!vfio_get_xlat_addr(iotlb, &vaddr, NULL, &read_only, &local_err)) { + mr = vfio_translate_iotlb(iotlb, &xlat, &local_err); + if (!mr) { error_report_err(local_err); goto out; } + vaddr = memory_region_get_ram_ptr(mr) + xlat; + read_only = !(iotlb->perm & IOMMU_WO) || mr->readonly; + /* * vaddr is only valid until rcu_read_unlock(). But after * vfio_dma_map has set up the mapping the pages will be @@ -163,7 +170,7 @@ static void vfio_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) */ ret = vfio_container_dma_map(bcontainer, iova, iotlb->addr_mask + 1, vaddr, - read_only); + read_only, mr); if (ret) { error_report("vfio_container_dma_map(%p, 0x%"HWADDR_PRIx", " "0x%"HWADDR_PRIx", %p) = %d (%s)", @@ -233,7 +240,7 @@ static int vfio_ram_discard_notify_populate(RamDiscardListener *rdl, vaddr = memory_region_get_ram_ptr(section->mr) + start; ret = vfio_container_dma_map(bcontainer, iova, next - start, - vaddr, section->readonly); + vaddr, section->readonly, section->mr); if (ret) { /* Rollback */ vfio_ram_discard_notify_discard(rdl, section); @@ -449,6 +456,26 @@ static void vfio_device_error_append(VFIODevice *vbasedev, Error **errp) } } +VFIORamDiscardListener *vfio_find_ram_discard_listener( + VFIOContainerBase *bcontainer, MemoryRegionSection *section) +{ + VFIORamDiscardListener *vrdl = NULL; + + QLIST_FOREACH(vrdl, &bcontainer->vrdl_list, next) { + if (vrdl->mr == section->mr && + vrdl->offset_within_address_space == + section->offset_within_address_space) { + break; + } + } + + if (!vrdl) { + hw_error("vfio: Trying to sync missing RAM discard listener"); + /* does not return */ + } + return vrdl; +} + static void vfio_listener_region_add(MemoryListener *listener, MemoryRegionSection *section) { @@ -557,7 +584,7 @@ static void vfio_listener_region_add(MemoryListener *listener, } ret = vfio_container_dma_map(bcontainer, iova, int128_get64(llsize), - vaddr, section->readonly); + vaddr, section->readonly, section->mr); if (ret) { error_setg(&err, "vfio_container_dma_map(%p, 0x%"HWADDR_PRIx", " "0x%"HWADDR_PRIx", %p) = %d (%s)", @@ -1010,6 +1037,8 @@ static void vfio_iommu_map_dirty_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) ram_addr_t translated_addr; Error *local_err = NULL; int ret = -EINVAL; + MemoryRegion *mr; + hwaddr xlat; trace_vfio_iommu_map_dirty_notify(iova, iova + iotlb->addr_mask); @@ -1021,9 +1050,11 @@ static void vfio_iommu_map_dirty_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) } rcu_read_lock(); - if (!vfio_get_xlat_addr(iotlb, NULL, &translated_addr, NULL, &local_err)) { + mr = vfio_translate_iotlb(iotlb, &xlat, &local_err); + if (!mr) { goto out_unlock; } + translated_addr = memory_region_get_ram_addr(mr) + xlat; ret = vfio_container_query_dirty_bitmap(bcontainer, iova, iotlb->addr_mask + 1, translated_addr, &local_err); @@ -1075,19 +1106,8 @@ vfio_sync_ram_discard_listener_dirty_bitmap(VFIOContainerBase *bcontainer, MemoryRegionSection *section) { RamDiscardManager *rdm = memory_region_get_ram_discard_manager(section->mr); - VFIORamDiscardListener *vrdl = NULL; - - QLIST_FOREACH(vrdl, &bcontainer->vrdl_list, next) { - if (vrdl->mr == section->mr && - vrdl->offset_within_address_space == - section->offset_within_address_space) { - break; - } - } - - if (!vrdl) { - hw_error("vfio: Trying to sync missing RAM discard listener"); - } + VFIORamDiscardListener *vrdl = + vfio_find_ram_discard_listener(bcontainer, section); /* * We only want/can synchronize the bitmap for actually mapped parts - diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index a1bfdfe..b1250d8 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -511,6 +511,25 @@ static void vfio_update_kvm_msi_virq(VFIOMSIVector *vector, MSIMessage msg, kvm_irqchip_commit_routes(kvm_state); } +static void set_irq_signalling(VFIODevice *vbasedev, VFIOMSIVector *vector, + unsigned int nr) +{ + Error *err = NULL; + int32_t fd; + + if (vector->virq >= 0) { + fd = event_notifier_get_fd(&vector->kvm_interrupt); + } else { + fd = event_notifier_get_fd(&vector->interrupt); + } + + if (!vfio_device_irq_set_signaling(vbasedev, VFIO_PCI_MSIX_IRQ_INDEX, nr, + VFIO_IRQ_SET_ACTION_TRIGGER, + fd, &err)) { + error_reportf_err(err, VFIO_MSG_PREFIX, vbasedev->name); + } +} + static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, MSIMessage *msg, IOHandler *handler) { @@ -583,21 +602,7 @@ static int vfio_msix_vector_do_use(PCIDevice *pdev, unsigned int nr, strerror(-ret)); } } else { - Error *err = NULL; - int32_t fd; - - if (vector->virq >= 0) { - fd = event_notifier_get_fd(&vector->kvm_interrupt); - } else { - fd = event_notifier_get_fd(&vector->interrupt); - } - - if (!vfio_device_irq_set_signaling(&vdev->vbasedev, - VFIO_PCI_MSIX_IRQ_INDEX, nr, - VFIO_IRQ_SET_ACTION_TRIGGER, fd, - &err)) { - error_reportf_err(err, VFIO_MSG_PREFIX, vdev->vbasedev.name); - } + set_irq_signalling(&vdev->vbasedev, vector, nr); } } @@ -2854,6 +2859,18 @@ static bool vfio_populate_device(VFIOPCIDevice *vdev, Error **errp) static void vfio_pci_put_device(VFIOPCIDevice *vdev) { + vfio_display_finalize(vdev); + vfio_bars_finalize(vdev); + g_free(vdev->emulated_config_bits); + g_free(vdev->rom); + /* + * XXX Leaking igd_opregion is not an oversight, we can't remove the + * fw_cfg entry therefore leaking this allocation seems like the safest + * option. + * + * g_free(vdev->igd_opregion); + */ + vfio_device_detach(&vdev->vbasedev); g_free(vdev->vbasedev.name); @@ -3005,6 +3022,19 @@ static bool vfio_pci_config_setup(VFIOPCIDevice *vdev, Error **errp) { PCIDevice *pdev = &vdev->pdev; VFIODevice *vbasedev = &vdev->vbasedev; + uint32_t config_space_size; + int ret; + + config_space_size = MIN(pci_config_size(&vdev->pdev), vdev->config_size); + + /* Get a copy of config space */ + ret = vfio_pci_config_space_read(vdev, 0, config_space_size, + vdev->pdev.config); + if (ret < (int)config_space_size) { + ret = ret < 0 ? -ret : EFAULT; + error_setg_errno(errp, ret, "failed to read device config space"); + return false; + } /* vfio emulates a lot for us, but some bits need extra love */ vdev->emulated_config_bits = g_malloc0(vdev->config_size); @@ -3126,15 +3156,14 @@ static bool vfio_interrupt_setup(VFIOPCIDevice *vdev, Error **errp) return true; } -static void vfio_realize(PCIDevice *pdev, Error **errp) +static void vfio_pci_realize(PCIDevice *pdev, Error **errp) { ERRP_GUARD(); VFIOPCIDevice *vdev = VFIO_PCI_BASE(pdev); VFIODevice *vbasedev = &vdev->vbasedev; - int i, ret; + int i; char uuid[UUID_STR_LEN]; g_autofree char *name = NULL; - uint32_t config_space_size; if (vbasedev->fd < 0 && !vbasedev->sysfsdev) { if (!(~vdev->host.domain || ~vdev->host.bus || @@ -3189,17 +3218,6 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) goto error; } - config_space_size = MIN(pci_config_size(&vdev->pdev), vdev->config_size); - - /* Get a copy of config space */ - ret = vfio_pci_config_space_read(vdev, 0, config_space_size, - vdev->pdev.config); - if (ret < (int)config_space_size) { - ret = ret < 0 ? -ret : EFAULT; - error_setg_errno(errp, ret, "failed to read device config space"); - goto error; - } - if (!vfio_pci_config_setup(vdev, errp)) { goto error; } @@ -3302,17 +3320,6 @@ static void vfio_instance_finalize(Object *obj) { VFIOPCIDevice *vdev = VFIO_PCI_BASE(obj); - vfio_display_finalize(vdev); - vfio_bars_finalize(vdev); - g_free(vdev->emulated_config_bits); - g_free(vdev->rom); - /* - * XXX Leaking igd_opregion is not an oversight, we can't remove the - * fw_cfg entry therefore leaking this allocation seems like the safest - * option. - * - * g_free(vdev->igd_opregion); - */ vfio_pci_put_device(vdev); } @@ -3514,7 +3521,7 @@ static void vfio_pci_dev_class_init(ObjectClass *klass, const void *data) object_class_property_add_str(klass, "fd", NULL, vfio_pci_set_fd); #endif dc->desc = "VFIO-based PCI device assignment"; - pdc->realize = vfio_realize; + pdc->realize = vfio_pci_realize; object_class_property_set_description(klass, /* 1.3 */ "host", diff --git a/hw/vfio/vfio-cpr.h b/hw/vfio/vfio-cpr.h deleted file mode 100644 index 134b83a..0000000 --- a/hw/vfio/vfio-cpr.h +++ /dev/null @@ -1,15 +0,0 @@ -/* - * VFIO CPR - * - * Copyright (c) 2025 Oracle and/or its affiliates. - * - * SPDX-License-Identifier: GPL-2.0-or-later - */ - -#ifndef HW_VFIO_CPR_H -#define HW_VFIO_CPR_H - -bool vfio_cpr_register_container(VFIOContainerBase *bcontainer, Error **errp); -void vfio_cpr_unregister_container(VFIOContainerBase *bcontainer); - -#endif /* HW_VFIO_CPR_H */ diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c index 1ab2c11..7061b6e 100644 --- a/hw/virtio/vhost-vdpa.c +++ b/hw/virtio/vhost-vdpa.c @@ -209,6 +209,8 @@ static void vhost_vdpa_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) int ret; Int128 llend; Error *local_err = NULL; + MemoryRegion *mr; + hwaddr xlat; if (iotlb->target_as != &address_space_memory) { error_report("Wrong target AS \"%s\", only system memory is allowed", @@ -228,11 +230,14 @@ static void vhost_vdpa_iommu_map_notify(IOMMUNotifier *n, IOMMUTLBEntry *iotlb) if ((iotlb->perm & IOMMU_RW) != IOMMU_NONE) { bool read_only; - if (!memory_get_xlat_addr(iotlb, &vaddr, NULL, &read_only, NULL, - &local_err)) { + mr = memory_translate_iotlb(iotlb, &xlat, &local_err); + if (!mr) { error_report_err(local_err); return; } + vaddr = memory_region_get_ram_ptr(mr) + xlat; + read_only = !(iotlb->perm & IOMMU_WO) || mr->readonly; + ret = vhost_vdpa_dma_map(s, VHOST_VDPA_GUEST_PA_ASID, iova, iotlb->addr_mask + 1, vaddr, read_only); if (ret) { @@ -594,6 +599,36 @@ static void vhost_vdpa_init_svq(struct vhost_dev *hdev, struct vhost_vdpa *v) v->shadow_vqs = g_steal_pointer(&shadow_vqs); } +static int vhost_vdpa_set_backend_cap(struct vhost_dev *dev) +{ + struct vhost_vdpa *v = dev->opaque; + + uint64_t features; + uint64_t f = 0x1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2 | + 0x1ULL << VHOST_BACKEND_F_IOTLB_BATCH | + 0x1ULL << VHOST_BACKEND_F_IOTLB_ASID | + 0x1ULL << VHOST_BACKEND_F_SUSPEND; + int r; + + if (vhost_vdpa_call(dev, VHOST_GET_BACKEND_FEATURES, &features)) { + return -EFAULT; + } + + features &= f; + + if (vhost_vdpa_first_dev(dev)) { + r = vhost_vdpa_call(dev, VHOST_SET_BACKEND_FEATURES, &features); + if (r) { + return -EFAULT; + } + } + + dev->backend_cap = features; + v->shared->backend_cap = features; + + return 0; +} + static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) { struct vhost_vdpa *v = opaque; @@ -603,7 +638,12 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) v->dev = dev; dev->opaque = opaque ; - v->shared->listener = vhost_vdpa_memory_listener; + + ret = vhost_vdpa_set_backend_cap(dev); + if (unlikely(ret != 0)) { + return ret; + } + vhost_vdpa_init_svq(dev, v); error_propagate(&dev->migration_blocker, v->migration_blocker); @@ -639,6 +679,7 @@ static int vhost_vdpa_init(struct vhost_dev *dev, void *opaque, Error **errp) vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE | VIRTIO_CONFIG_S_DRIVER); + v->shared->listener = vhost_vdpa_memory_listener; return 0; } @@ -841,36 +882,6 @@ static int vhost_vdpa_set_features(struct vhost_dev *dev, return vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_FEATURES_OK); } -static int vhost_vdpa_set_backend_cap(struct vhost_dev *dev) -{ - struct vhost_vdpa *v = dev->opaque; - - uint64_t features; - uint64_t f = 0x1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2 | - 0x1ULL << VHOST_BACKEND_F_IOTLB_BATCH | - 0x1ULL << VHOST_BACKEND_F_IOTLB_ASID | - 0x1ULL << VHOST_BACKEND_F_SUSPEND; - int r; - - if (vhost_vdpa_call(dev, VHOST_GET_BACKEND_FEATURES, &features)) { - return -EFAULT; - } - - features &= f; - - if (vhost_vdpa_first_dev(dev)) { - r = vhost_vdpa_call(dev, VHOST_SET_BACKEND_FEATURES, &features); - if (r) { - return -EFAULT; - } - } - - dev->backend_cap = features; - v->shared->backend_cap = features; - - return 0; -} - static int vhost_vdpa_get_device_id(struct vhost_dev *dev, uint32_t *device_id) { @@ -888,8 +899,14 @@ static int vhost_vdpa_reset_device(struct vhost_dev *dev) ret = vhost_vdpa_call(dev, VHOST_VDPA_SET_STATUS, &status); trace_vhost_vdpa_reset_device(dev); + if (ret) { + return ret; + } + + memory_listener_unregister(&v->shared->listener); + v->shared->listener_registered = false; v->suspended = false; - return ret; + return 0; } static int vhost_vdpa_get_vq_index(struct vhost_dev *dev, int idx) @@ -1373,7 +1390,15 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) "IOMMU and try again"); return -1; } - memory_listener_register(&v->shared->listener, dev->vdev->dma_as); + if (v->shared->listener_registered && + dev->vdev->dma_as != v->shared->listener.address_space) { + memory_listener_unregister(&v->shared->listener); + v->shared->listener_registered = false; + } + if (!v->shared->listener_registered) { + memory_listener_register(&v->shared->listener, dev->vdev->dma_as); + v->shared->listener_registered = true; + } return vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_DRIVER_OK); } @@ -1383,8 +1408,6 @@ static int vhost_vdpa_dev_start(struct vhost_dev *dev, bool started) static void vhost_vdpa_reset_status(struct vhost_dev *dev) { - struct vhost_vdpa *v = dev->opaque; - if (!vhost_vdpa_last_dev(dev)) { return; } @@ -1392,7 +1415,6 @@ static void vhost_vdpa_reset_status(struct vhost_dev *dev) vhost_vdpa_reset_device(dev); vhost_vdpa_add_status(dev, VIRTIO_CONFIG_S_ACKNOWLEDGE | VIRTIO_CONFIG_S_DRIVER); - memory_listener_unregister(&v->shared->listener); } static int vhost_vdpa_set_log_base(struct vhost_dev *dev, uint64_t base, @@ -1526,12 +1548,27 @@ static int vhost_vdpa_get_features(struct vhost_dev *dev, static int vhost_vdpa_set_owner(struct vhost_dev *dev) { + int r; + struct vhost_vdpa *v; + if (!vhost_vdpa_first_dev(dev)) { return 0; } trace_vhost_vdpa_set_owner(dev); - return vhost_vdpa_call(dev, VHOST_SET_OWNER, NULL); + r = vhost_vdpa_call(dev, VHOST_SET_OWNER, NULL); + if (unlikely(r < 0)) { + return r; + } + + /* + * Being optimistic and listening address space memory. If the device + * uses vIOMMU, it is changed at vhost_vdpa_dev_start. + */ + v = dev->opaque; + memory_listener_register(&v->shared->listener, &address_space_memory); + v->shared->listener_registered = true; + return 0; } static int vhost_vdpa_vq_get_addr(struct vhost_dev *dev, @@ -1563,7 +1600,6 @@ const VhostOps vdpa_ops = { .vhost_set_vring_kick = vhost_vdpa_set_vring_kick, .vhost_set_vring_call = vhost_vdpa_set_vring_call, .vhost_get_features = vhost_vdpa_get_features, - .vhost_set_backend_cap = vhost_vdpa_set_backend_cap, .vhost_set_owner = vhost_vdpa_set_owner, .vhost_set_vring_endian = NULL, .vhost_backend_memslots_limit = vhost_vdpa_memslots_limit, diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index 9b48aa8..fba2372 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -146,9 +146,7 @@ static const VMStateDescription vmstate_virtio_pci = { static bool virtio_pci_has_extra_state(DeviceState *d) { - VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d); - - return proxy->flags & VIRTIO_PCI_FLAG_MIGRATE_EXTRA; + return true; } static void virtio_pci_save_extra_state(DeviceState *d, QEMUFile *f) @@ -1215,7 +1213,12 @@ static int virtio_pci_set_guest_notifier(DeviceState *d, int n, bool assign, static bool virtio_pci_query_guest_notifiers(DeviceState *d) { VirtIOPCIProxy *proxy = to_virtio_pci_proxy(d); - return msix_enabled(&proxy->pci_dev); + + if (msix_enabled(&proxy->pci_dev)) { + return true; + } else { + return pci_irq_disabled(&proxy->pci_dev); + } } static int virtio_pci_set_guest_notifiers(DeviceState *d, int nvqs, bool assign) @@ -2363,12 +2366,8 @@ static void virtio_pci_bus_reset_hold(Object *obj, ResetType type) static const Property virtio_pci_properties[] = { DEFINE_PROP_BIT("virtio-pci-bus-master-bug-migration", VirtIOPCIProxy, flags, VIRTIO_PCI_FLAG_BUS_MASTER_BUG_MIGRATION_BIT, false), - DEFINE_PROP_BIT("migrate-extra", VirtIOPCIProxy, flags, - VIRTIO_PCI_FLAG_MIGRATE_EXTRA_BIT, true), DEFINE_PROP_BIT("modern-pio-notify", VirtIOPCIProxy, flags, VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY_BIT, false), - DEFINE_PROP_BIT("x-disable-pcie", VirtIOPCIProxy, flags, - VIRTIO_PCI_FLAG_DISABLE_PCIE_BIT, false), DEFINE_PROP_BIT("page-per-vq", VirtIOPCIProxy, flags, VIRTIO_PCI_FLAG_PAGE_PER_VQ_BIT, false), DEFINE_PROP_BOOL("x-ignore-backend-features", VirtIOPCIProxy, @@ -2397,8 +2396,7 @@ static void virtio_pci_dc_realize(DeviceState *qdev, Error **errp) VirtIOPCIProxy *proxy = VIRTIO_PCI(qdev); PCIDevice *pci_dev = &proxy->pci_dev; - if (!(proxy->flags & VIRTIO_PCI_FLAG_DISABLE_PCIE) && - virtio_pci_modern(proxy)) { + if (virtio_pci_modern(proxy)) { pci_dev->cap_present |= QEMU_PCI_CAP_EXPRESS; } diff --git a/hw/virtio/virtio.c b/hw/virtio/virtio.c index 2e98cec..5534251 100644 --- a/hw/virtio/virtio.c +++ b/hw/virtio/virtio.c @@ -205,6 +205,15 @@ static const char *virtio_id_to_name(uint16_t device_id) return name; } +static void virtio_check_indirect_feature(VirtIODevice *vdev) +{ + if (!virtio_vdev_has_feature(vdev, VIRTIO_RING_F_INDIRECT_DESC)) { + qemu_log_mask(LOG_GUEST_ERROR, + "Device %s: indirect_desc was not negotiated!\n", + vdev->name); + } +} + /* Called within call_rcu(). */ static void virtio_free_region_cache(VRingMemoryRegionCaches *caches) { @@ -1733,6 +1742,7 @@ static void *virtqueue_split_pop(VirtQueue *vq, size_t sz) virtio_error(vdev, "Invalid size for indirect buffer table"); goto done; } + virtio_check_indirect_feature(vdev); /* loop over the indirect descriptor table */ len = address_space_cache_init(&indirect_desc_cache, vdev->dma_as, @@ -1870,6 +1880,7 @@ static void *virtqueue_packed_pop(VirtQueue *vq, size_t sz) virtio_error(vdev, "Invalid size for indirect buffer table"); goto done; } + virtio_check_indirect_feature(vdev); /* loop over the indirect descriptor table */ len = address_space_cache_init(&indirect_desc_cache, vdev->dma_as, |