diff --git a/MAINTAINERS b/MAINTAINERS index 56460c886d..38d1ac8803 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1819,7 +1819,6 @@ F: docs/specs/acpi_hw_reduced_hotplug.rst ACPI/VIOT M: Jean-Philippe Brucker -R: Ani Sinha S: Supported F: hw/acpi/viot.c F: hw/acpi/viot.h diff --git a/configure b/configure index 81618708e4..886000346a 100755 --- a/configure +++ b/configure @@ -1659,8 +1659,8 @@ fi # vhost interdependencies and host support # vhost backends -if test "$vhost_user" = "yes" && test "$linux" != "yes"; then - error_exit "vhost-user is only available on Linux" +if test "$vhost_user" = "yes" && test "$mingw32" = "yes"; then + error_exit "vhost-user is not available on Windows" fi test "$vhost_vdpa" = "" && vhost_vdpa=$linux if test "$vhost_vdpa" = "yes" && test "$linux" != "yes"; then diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index 85773db631..cf02ef6821 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -324,6 +324,14 @@ machine is hardly emulated at all (e.g. neither the LCD nor the USB part had been implemented), so there is not much value added by this board. Use the ``ref405ep`` machine instead. +``pc-i440fx-1.4`` up to ``pc-i440fx-1.7`` (since 7.0) +''''''''''''''''''''''''''''''''''''''''''''''''''''' + +These old machine types are quite neglected nowadays and thus might have +various pitfalls with regards to live migration. Use a newer machine type +instead. + + Backend options --------------- diff --git a/docs/interop/vhost-user.rst b/docs/interop/vhost-user.rst index edc3ad84a3..4dbc84fd00 100644 --- a/docs/interop/vhost-user.rst +++ b/docs/interop/vhost-user.rst @@ -38,6 +38,26 @@ conventions `. *Master* and *slave* can be either a client (i.e. connecting) or server (listening) in the socket communication. +Support for platforms other than Linux +-------------------------------------- + +While vhost-user was initially developed targeting Linux, nowadays it +is supported on any platform that provides the following features: + +- A way for requesting shared memory represented by a file descriptor + so it can be passed over a UNIX domain socket and then mapped by the + other process. + +- AF_UNIX sockets with SCM_RIGHTS, so QEMU and the other process can + exchange messages through it, including ancillary data when needed. + +- Either eventfd or pipe/pipe2. On platforms where eventfd is not + available, QEMU will automatically fall back to pipe2 or, as a last + resort, pipe. Each file descriptor will be used for receiving or + sending events by reading or writing (respectively) an 8-byte value + to the corresponding it. The 8-value itself has no meaning and + should not be interpreted. + Message Specification ===================== diff --git a/docs/pcie_sriov.txt b/docs/pcie_sriov.txt new file mode 100644 index 0000000000..f5e891e1d4 --- /dev/null +++ b/docs/pcie_sriov.txt @@ -0,0 +1,115 @@ +PCI SR/IOV EMULATION SUPPORT +============================ + +Description +=========== +SR/IOV (Single Root I/O Virtualization) is an optional extended capability +of a PCI Express device. It allows a single physical function (PF) to appear as multiple +virtual functions (VFs) for the main purpose of eliminating software +overhead in I/O from virtual machines. + +Qemu now implements the basic common functionality to enable an emulated device +to support SR/IOV. Yet no fully implemented devices exists in Qemu, but a +proof-of-concept hack of the Intel igb can be found here: + +git://github.com/knuto/qemu.git sriov_patches_v5 + +Implementation +============== +Implementing emulation of an SR/IOV capable device typically consists of +implementing support for two types of device classes; the "normal" physical device +(PF) and the virtual device (VF). From Qemu's perspective, the VFs are just +like other devices, except that some of their properties are derived from +the PF. + +A virtual function is different from a physical function in that the BAR +space for all VFs are defined by the BAR registers in the PFs SR/IOV +capability. All VFs have the same BARs and BAR sizes. + +Accesses to these virtual BARs then is computed as + + + * + + +From our emulation perspective this means that there is a separate call for +setting up a BAR for a VF. + +1) To enable SR/IOV support in the PF, it must be a PCI Express device so + you would need to add a PCI Express capability in the normal PCI + capability list. You might also want to add an ARI (Alternative + Routing-ID Interpretation) capability to indicate that your device + supports functions beyond it's "own" function space (0-7), + which is necessary to support more than 7 functions, or + if functions extends beyond offset 7 because they are placed at an + offset > 1 or have stride > 1. + + ... + #include "hw/pci/pcie.h" + #include "hw/pci/pcie_sriov.h" + + pci_your_pf_dev_realize( ... ) + { + ... + int ret = pcie_endpoint_cap_init(d, 0x70); + ... + pcie_ari_init(d, 0x100, 1); + ... + + /* Add and initialize the SR/IOV capability */ + pcie_sriov_pf_init(d, 0x200, "your_virtual_dev", + vf_devid, initial_vfs, total_vfs, + fun_offset, stride); + + /* Set up individual VF BARs (parameters as for normal BARs) */ + pcie_sriov_pf_init_vf_bar( ... ) + ... + } + + For cleanup, you simply call: + + pcie_sriov_pf_exit(device); + + which will delete all the virtual functions and associated resources. + +2) Similarly in the implementation of the virtual function, you need to + make it a PCI Express device and add a similar set of capabilities + except for the SR/IOV capability. Then you need to set up the VF BARs as + subregions of the PFs SR/IOV VF BARs by calling + pcie_sriov_vf_register_bar() instead of the normal pci_register_bar() call: + + pci_your_vf_dev_realize( ... ) + { + ... + int ret = pcie_endpoint_cap_init(d, 0x60); + ... + pcie_ari_init(d, 0x100, 1); + ... + memory_region_init(mr, ... ) + pcie_sriov_vf_register_bar(d, bar_nr, mr); + ... + } + +Testing on Linux guest +====================== +The easiest is if your device driver supports sysfs based SR/IOV +enabling. Support for this was added in kernel v.3.8, so not all drivers +support it yet. + +To enable 4 VFs for a device at 01:00.0: + + modprobe yourdriver + echo 4 > /sys/bus/pci/devices/0000:01:00.0/sriov_numvfs + +You should now see 4 VFs with lspci. +To turn SR/IOV off again - the standard requires you to turn it off before you can enable +another VF count, and the emulation enforces this: + + echo 0 > /sys/bus/pci/devices/0000:01:00.0/sriov_numvfs + +Older drivers typically provide a max_vfs module parameter +to enable it at load time: + + modprobe yourdriver max_vfs=4 + +To disable the VFs again then, you simply have to unload the driver: + + rmmod yourdriver diff --git a/docs/specs/acpi_erst.rst b/docs/specs/acpi_erst.rst new file mode 100644 index 0000000000..a8a9d22d25 --- /dev/null +++ b/docs/specs/acpi_erst.rst @@ -0,0 +1,200 @@ +ACPI ERST DEVICE +================ + +The ACPI ERST device is utilized to support the ACPI Error Record +Serialization Table, ERST, functionality. This feature is designed for +storing error records in persistent storage for future reference +and/or debugging. + +The ACPI specification[1], in Chapter "ACPI Platform Error Interfaces +(APEI)", and specifically subsection "Error Serialization", outlines a +method for storing error records into persistent storage. + +The format of error records is described in the UEFI specification[2], +in Appendix N "Common Platform Error Record". + +While the ACPI specification allows for an NVRAM "mode" (see +GET_ERROR_LOG_ADDRESS_RANGE_ATTRIBUTES) where non-volatile RAM is +directly exposed for direct access by the OS/guest, this device +implements the non-NVRAM "mode". This non-NVRAM "mode" is what is +implemented by most BIOS (since flash memory requires programming +operations in order to update its contents). Furthermore, as of the +time of this writing, Linux only supports the non-NVRAM "mode". + + +Background/Motivation +--------------------- + +Linux uses the persistent storage filesystem, pstore, to record +information (eg. dmesg tail) upon panics and shutdowns. Pstore is +independent of, and runs before, kdump. In certain scenarios (ie. +hosts/guests with root filesystems on NFS/iSCSI where networking +software and/or hardware fails, and thus kdump fails), pstore may +contain information available for post-mortem debugging. + +Two common storage backends for the pstore filesystem are ACPI ERST +and UEFI. Most BIOS implement ACPI ERST. UEFI is not utilized in all +guests. With QEMU supporting ACPI ERST, it becomes a viable pstore +storage backend for virtual machines (as it is now for bare metal +machines). + +Enabling support for ACPI ERST facilitates a consistent method to +capture kernel panic information in a wide range of guests: from +resource-constrained microvms to very large guests, and in particular, +in direct-boot environments (which would lack UEFI run-time services). + +Note that Microsoft Windows also utilizes the ACPI ERST for certain +crash information, if available[3]. + + +Configuration|Usage +------------------- + +To use ACPI ERST, a memory-backend-file object and acpi-erst device +can be created, for example: + + qemu ... + -object memory-backend-file,id=erstnvram,mem-path=acpi-erst.backing,size=0x10000,share=on \ + -device acpi-erst,memdev=erstnvram + +For proper operation, the ACPI ERST device needs a memory-backend-file +object with the following parameters: + + - id: The id of the memory-backend-file object is used to associate + this memory with the acpi-erst device. + - size: The size of the ACPI ERST backing storage. This parameter is + required. + - mem-path: The location of the ACPI ERST backing storage file. This + parameter is also required. + - share: The share=on parameter is required so that updates to the + ERST backing store are written to the file. + +and ERST device: + + - memdev: Is the object id of the memory-backend-file. + - record_size: Specifies the size of the records (or slots) in the + backend storage. Must be a power of two value greater than or + equal to 4096 (PAGE_SIZE). + + +PCI Interface +------------- + +The ERST device is a PCI device with two BARs, one for accessing the +programming registers, and the other for accessing the record exchange +buffer. + +BAR0 contains the programming interface consisting of ACTION and VALUE +64-bit registers. All ERST actions/operations/side effects happen on +the write to the ACTION, by design. Any data needed by the action must +be placed into VALUE prior to writing ACTION. Reading the VALUE +simply returns the register contents, which can be updated by a +previous ACTION. + +BAR1 contains the 8KiB record exchange buffer, which is the +implemented maximum record size. + + +Backend Storage Format +---------------------- + +The backend storage is divided into fixed size "slots", 8KiB in +length, with each slot storing a single record. Not all slots need to +be occupied, and they need not be occupied in a contiguous fashion. +The ability to clear/erase specific records allows for the formation +of unoccupied slots. + +Slot 0 contains a backend storage header that identifies the contents +as ERST and also facilitates efficient access to the records. +Depending upon the size of the backend storage, additional slots will +be designated to be a part of the slot 0 header. For example, at 8KiB, +the slot 0 header can accomodate 1021 records. Thus a storage size +of 8MiB (8KiB * 1024) requires an additional slot for use by the +header. In this scenario, slot 0 and slot 1 form the backend storage +header, and records can be stored starting at slot 2. + +Below is an example layout of the backend storage format (for storage +size less than 8MiB). The size of the storage is a multiple of 8KiB, +and contains N number of slots to store records. The example below +shows two records (in CPER format) in the backend storage, while the +remaining slots are empty/available. + +:: + + Slot Record + <------------------ 8KiB --------------------> + +--------------------------------------------+ + 0 | storage header | + +--------------------------------------------+ + 1 | empty/available | + +--------------------------------------------+ + 2 | CPER | + +--------------------------------------------+ + 3 | CPER | + +--------------------------------------------+ + ... | | + +--------------------------------------------+ + N | empty/available | + +--------------------------------------------+ + +The storage header consists of some basic information and an array +of CPER record_id's to efficiently access records in the backend +storage. + +All fields in the header are stored in little endian format. + +:: + + +--------------------------------------------+ + | magic | 0x0000 + +--------------------------------------------+ + | record_offset | record_size | 0x0008 + +--------------------------------------------+ + | record_count | reserved | version | 0x0010 + +--------------------------------------------+ + | record_id[0] | 0x0018 + +--------------------------------------------+ + | record_id[1] | 0x0020 + +--------------------------------------------+ + | record_id[...] | + +--------------------------------------------+ + | record_id[N] | 0x1FF8 + +--------------------------------------------+ + +The 'magic' field contains the value 0x524F545354535245. + +The 'record_size' field contains the value 0x2000, 8KiB. + +The 'record_offset' field points to the first record_id in the array, +0x0018. + +The 'version' field contains 0x0100, the first version. + +The 'record_count' field contains the number of valid records in the +backend storage. + +The 'record_id' array fields are the 64-bit record identifiers of the +CPER record in the corresponding slot. Stated differently, the +location of a CPER record_id in the record_id[] array provides the +slot index for the corresponding record in the backend storage. + +Note that, for example, with a backend storage less than 8MiB, slot 0 +contains the header, so the record_id[0] will never contain a valid +CPER record_id. Instead slot 1 is the first available slot and thus +record_id_[1] may contain a CPER. + +A 'record_id' of all 0s or all 1s indicates an invalid record (ie. the +slot is available). + + +References +---------- + +[1] "Advanced Configuration and Power Interface Specification", + version 4.0, June 2009. + +[2] "Unified Extensible Firmware Interface Specification", + version 2.1, October 2008. + +[3] "Windows Hardware Error Architecture", specfically + "Error Record Persistence Mechanism". diff --git a/docs/specs/index.rst b/docs/specs/index.rst index 2a35700fb3..e10684bf53 100644 --- a/docs/specs/index.rst +++ b/docs/specs/index.rst @@ -18,4 +18,5 @@ guest hardware that is specific to QEMU. acpi_mem_hotplug acpi_pci_hotplug acpi_nvdimm + acpi_erst sev-guest-firmware diff --git a/docs/specs/pci-ids.txt b/docs/specs/pci-ids.txt index 5e407a6f32..dd6859d039 100644 --- a/docs/specs/pci-ids.txt +++ b/docs/specs/pci-ids.txt @@ -65,6 +65,7 @@ PCI devices (other than virtio): 1b36:000f mdpy (mdev sample device), linux/samples/vfio-mdev/mdpy.c 1b36:0010 PCIe NVMe device (-device nvme) 1b36:0011 PCI PVPanic device (-device pvpanic-pci) +1b36:0012 PCI ACPI ERST device (-device acpi-erst) All these devices are documented in docs/specs. diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c index 8966e16320..1773cf55f1 100644 --- a/hw/acpi/aml-build.c +++ b/hw/acpi/aml-build.c @@ -2152,7 +2152,13 @@ void build_fadt(GArray *tbl, BIOSLinker *linker, const AcpiFadtData *f, build_append_int_noprefix(tbl, 0, 1); /* DAY_ALRM */ build_append_int_noprefix(tbl, 0, 1); /* MON_ALRM */ build_append_int_noprefix(tbl, f->rtc_century, 1); /* CENTURY */ - build_append_int_noprefix(tbl, 0, 2); /* IAPC_BOOT_ARCH */ + /* IAPC_BOOT_ARCH */ + if (f->rev == 1) { + build_append_int_noprefix(tbl, 0, 2); + } else { + /* since ACPI v2.0 */ + build_append_int_noprefix(tbl, f->iapc_boot_arch, 2); + } build_append_int_noprefix(tbl, 0, 1); /* Reserved */ build_append_int_noprefix(tbl, f->flags, 4); /* Flags */ diff --git a/hw/acpi/erst.c b/hw/acpi/erst.c index c0a23cf467..de509c2b48 100644 --- a/hw/acpi/erst.c +++ b/hw/acpi/erst.c @@ -80,11 +80,6 @@ #define UEFI_CPER_RECORD_MIN_SIZE 128U #define UEFI_CPER_RECORD_LENGTH_OFFSET 20U #define UEFI_CPER_RECORD_ID_OFFSET 96U -#define IS_UEFI_CPER_RECORD(ptr) \ - (((ptr)[0] == 'C') && \ - ((ptr)[1] == 'P') && \ - ((ptr)[2] == 'E') && \ - ((ptr)[3] == 'R')) /* * NOTE that when accessing CPER fields within a record, memcpy() diff --git a/hw/acpi/pcihp.c b/hw/acpi/pcihp.c index 6befd23e16..6351bd3424 100644 --- a/hw/acpi/pcihp.c +++ b/hw/acpi/pcihp.c @@ -32,6 +32,7 @@ #include "hw/pci/pci_bridge.h" #include "hw/pci/pci_host.h" #include "hw/pci/pcie_port.h" +#include "hw/pci-bridge/xio3130_downstream.h" #include "hw/i386/acpi-build.h" #include "hw/acpi/acpi.h" #include "hw/pci/pci_bus.h" @@ -336,6 +337,8 @@ void acpi_pcihp_device_plug_cb(HotplugHandler *hotplug_dev, AcpiPciHpState *s, { PCIDevice *pdev = PCI_DEVICE(dev); int slot = PCI_SLOT(pdev->devfn); + PCIDevice *bridge; + PCIBus *bus; int bsel; /* Don't send event when device is enabled during qemu machine creation: @@ -365,7 +368,14 @@ void acpi_pcihp_device_plug_cb(HotplugHandler *hotplug_dev, AcpiPciHpState *s, return; } - bsel = acpi_pcihp_get_bsel(pci_get_bus(pdev)); + bus = pci_get_bus(pdev); + bridge = pci_bridge_get_device(bus); + if (object_dynamic_cast(OBJECT(bridge), TYPE_PCIE_ROOT_PORT) || + object_dynamic_cast(OBJECT(bridge), TYPE_XIO3130_DOWNSTREAM)) { + pcie_cap_slot_enable_power(bridge); + } + + bsel = acpi_pcihp_get_bsel(bus); g_assert(bsel >= 0); s->acpi_pcihp_pci_status[bsel].up |= (1U << slot); acpi_send_event(DEVICE(hotplug_dev), ACPI_PCI_HOTPLUG_STATUS); diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index ebd47aa26f..4ad4d7286c 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -38,6 +38,7 @@ #include "hw/nvram/fw_cfg.h" #include "hw/acpi/bios-linker-loader.h" #include "hw/isa/isa.h" +#include "hw/input/i8042.h" #include "hw/block/fdc.h" #include "hw/acpi/memory_hotplug.h" #include "sysemu/tpm.h" @@ -192,6 +193,13 @@ static void init_common_fadt_data(MachineState *ms, Object *o, .address = object_property_get_uint(o, ACPI_PM_PROP_GPE0_BLK, NULL) }, }; + + /* + * ACPI v2, Table 5-10 - Fixed ACPI Description Table Boot Architecture + * Flags, bit offset 1 - 8042. + */ + fadt.iapc_boot_arch = iapc_boot_arch_8042(); + *data = fadt; } diff --git a/hw/i386/acpi-microvm.c b/hw/i386/acpi-microvm.c index 68ca7e7fc2..fb09185cbd 100644 --- a/hw/i386/acpi-microvm.c +++ b/hw/i386/acpi-microvm.c @@ -37,6 +37,7 @@ #include "hw/pci/pcie_host.h" #include "hw/usb/xhci.h" #include "hw/virtio/virtio-mmio.h" +#include "hw/input/i8042.h" #include "acpi-common.h" #include "acpi-microvm.h" @@ -187,6 +188,11 @@ static void acpi_build_microvm(AcpiBuildTables *tables, .address = GED_MMIO_BASE_REGS + ACPI_GED_REG_RESET, }, .reset_val = ACPI_GED_RESET_VALUE, + /* + * ACPI v2, Table 5-10 - Fixed ACPI Description Table Boot Architecture + * Flags, bit offset 1 - 8042. + */ + .iapc_boot_arch = iapc_boot_arch_8042(), }; table_offsets = g_array_new(false, true /* clear */, diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index 4c6c016388..32471a44cb 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -3030,6 +3030,13 @@ static int vtd_iommu_notify_flag_changed(IOMMUMemoryRegion *iommu, VTDAddressSpace *vtd_as = container_of(iommu, VTDAddressSpace, iommu); IntelIOMMUState *s = vtd_as->iommu_state; + /* TODO: add support for VFIO and vhost users */ + if (s->snoop_control) { + error_setg_errno(errp, -ENOTSUP, + "Snoop Control with vhost or VFIO is not supported"); + return -ENOTSUP; + } + /* Update per-address-space notifier flags */ vtd_as->notifier_flags = new; @@ -3113,6 +3120,7 @@ static Property vtd_properties[] = { VTD_HOST_ADDRESS_WIDTH), DEFINE_PROP_BOOL("caching-mode", IntelIOMMUState, caching_mode, FALSE), DEFINE_PROP_BOOL("x-scalable-mode", IntelIOMMUState, scalable_mode, FALSE), + DEFINE_PROP_BOOL("snoop-control", IntelIOMMUState, snoop_control, false), DEFINE_PROP_BOOL("dma-drain", IntelIOMMUState, dma_drain, true), DEFINE_PROP_END_OF_LIST(), }; @@ -3643,7 +3651,7 @@ static void vtd_init(IntelIOMMUState *s) vtd_spte_rsvd_large[3] = VTD_SPTE_LPAGE_L3_RSVD_MASK(s->aw_bits, x86_iommu->dt_supported); - if (s->scalable_mode) { + if (s->scalable_mode || s->snoop_control) { vtd_spte_rsvd[1] &= ~VTD_SPTE_SNP; vtd_spte_rsvd_large[2] &= ~VTD_SPTE_SNP; vtd_spte_rsvd_large[3] &= ~VTD_SPTE_SNP; @@ -3674,6 +3682,10 @@ static void vtd_init(IntelIOMMUState *s) s->ecap |= VTD_ECAP_SMTS | VTD_ECAP_SRS | VTD_ECAP_SLTS; } + if (s->snoop_control) { + s->ecap |= VTD_ECAP_SC; + } + vtd_reset_caches(s); /* Define registers with default values and bit semantics */ diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h index a6c788049b..1ff13b40f9 100644 --- a/hw/i386/intel_iommu_internal.h +++ b/hw/i386/intel_iommu_internal.h @@ -188,6 +188,7 @@ #define VTD_ECAP_IR (1ULL << 3) #define VTD_ECAP_EIM (1ULL << 4) #define VTD_ECAP_PT (1ULL << 6) +#define VTD_ECAP_SC (1ULL << 7) #define VTD_ECAP_MHMV (15ULL << 20) #define VTD_ECAP_SRS (1ULL << 31) #define VTD_ECAP_SMTS (1ULL << 43) diff --git a/hw/i386/pc.c b/hw/i386/pc.c index c8696ac01e..fd55fc725c 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -318,8 +318,6 @@ GlobalProperty pc_compat_2_0[] = { { "pci-serial-4x", "prog_if", "0" }, { "virtio-net-pci", "guest_announce", "off" }, { "ICH9-LPC", "memory-hotplug-support", "off" }, - { "xio3130-downstream", COMPAT_PROP_PCP, "off" }, - { "ioh3420", COMPAT_PROP_PCP, "off" }, }; const size_t pc_compat_2_0_len = G_N_ELEMENTS(pc_compat_2_0); @@ -1014,7 +1012,8 @@ static const MemoryRegionOps ioportF0_io_ops = { }, }; -static void pc_superio_init(ISABus *isa_bus, bool create_fdctrl, bool no_vmport) +static void pc_superio_init(ISABus *isa_bus, bool create_fdctrl, + bool create_i8042, bool no_vmport) { int i; DriveInfo *fd[MAX_FD]; @@ -1036,6 +1035,10 @@ static void pc_superio_init(ISABus *isa_bus, bool create_fdctrl, bool no_vmport) } } + if (!create_i8042) { + return; + } + i8042 = isa_create_simple(isa_bus, "i8042"); if (!no_vmport) { isa_create_simple(isa_bus, TYPE_VMPORT); @@ -1131,7 +1134,8 @@ void pc_basic_device_init(struct PCMachineState *pcms, i8257_dma_init(isa_bus, 0); /* Super I/O */ - pc_superio_init(isa_bus, create_fdctrl, pcms->vmport != ON_OFF_AUTO_ON); + pc_superio_init(isa_bus, create_fdctrl, pcms->i8042_enabled, + pcms->vmport != ON_OFF_AUTO_ON); } void pc_nic_init(PCMachineClass *pcmc, ISABus *isa_bus, PCIBus *pci_bus) @@ -1512,6 +1516,20 @@ static void pc_machine_set_hpet(Object *obj, bool value, Error **errp) pcms->hpet_enabled = value; } +static bool pc_machine_get_i8042(Object *obj, Error **errp) +{ + PCMachineState *pcms = PC_MACHINE(obj); + + return pcms->i8042_enabled; +} + +static void pc_machine_set_i8042(Object *obj, bool value, Error **errp) +{ + PCMachineState *pcms = PC_MACHINE(obj); + + pcms->i8042_enabled = value; +} + static bool pc_machine_get_default_bus_bypass_iommu(Object *obj, Error **errp) { PCMachineState *pcms = PC_MACHINE(obj); @@ -1641,6 +1659,7 @@ static void pc_machine_initfn(Object *obj) pcms->smbus_enabled = true; pcms->sata_enabled = true; pcms->pit_enabled = true; + pcms->i8042_enabled = true; pcms->max_fw_size = 8 * MiB; #ifdef CONFIG_HPET pcms->hpet_enabled = true; @@ -1777,6 +1796,9 @@ static void pc_machine_class_init(ObjectClass *oc, void *data) object_class_property_set_description(oc, "hpet", "Enable/disable high precision event timer emulation"); + object_class_property_add_bool(oc, PC_MACHINE_I8042, + pc_machine_get_i8042, pc_machine_set_i8042); + object_class_property_add_bool(oc, "default-bus-bypass-iommu", pc_machine_get_default_bus_bypass_iommu, pc_machine_set_default_bus_bypass_iommu); diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index 8d33cf689d..b72c03d0a6 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -757,6 +757,7 @@ static void pc_i440fx_1_7_machine_options(MachineClass *m) m->hw_version = "1.7.0"; m->default_machine_opts = NULL; m->option_rom_has_mr = true; + m->deprecation_reason = "old and unattended - use a newer version instead"; compat_props_add(m->compat_props, pc_compat_1_7, pc_compat_1_7_len); pcmc->smbios_defaults = false; pcmc->gigabyte_align = false; diff --git a/hw/i386/x86.c b/hw/i386/x86.c index b84840a1bb..4cf107baea 100644 --- a/hw/i386/x86.c +++ b/hw/i386/x86.c @@ -83,24 +83,11 @@ inline void init_topo_info(X86CPUTopoInfo *topo_info, uint32_t x86_cpu_apic_id_from_index(X86MachineState *x86ms, unsigned int cpu_index) { - X86MachineClass *x86mc = X86_MACHINE_GET_CLASS(x86ms); X86CPUTopoInfo topo_info; - uint32_t correct_id; - static bool warned; init_topo_info(&topo_info, x86ms); - correct_id = x86_apicid_from_cpu_idx(&topo_info, cpu_index); - if (x86mc->compat_apic_id_mode) { - if (cpu_index != correct_id && !warned && !qtest_enabled()) { - error_report("APIC IDs set in compatibility mode, " - "CPU topology won't match the configuration"); - warned = true; - } - return cpu_index; - } else { - return correct_id; - } + return x86_apicid_from_cpu_idx(&topo_info, cpu_index); } @@ -1330,7 +1317,6 @@ static void x86_machine_class_init(ObjectClass *oc, void *data) mc->cpu_index_to_instance_props = x86_cpu_index_to_props; mc->get_default_cpu_node_id = x86_get_default_cpu_node_id; mc->possible_cpu_arch_ids = x86_possible_cpu_arch_ids; - x86mc->compat_apic_id_mode = false; x86mc->save_tsc_khz = true; x86mc->fwcfg_dma_enabled = true; nc->nmi_monitor_handler = x86_nmi; diff --git a/hw/misc/pvpanic-isa.c b/hw/misc/pvpanic-isa.c index a39fcdd1fc..b84d4d458d 100644 --- a/hw/misc/pvpanic-isa.c +++ b/hw/misc/pvpanic-isa.c @@ -21,6 +21,7 @@ #include "hw/misc/pvpanic.h" #include "qom/object.h" #include "hw/isa/isa.h" +#include "standard-headers/linux/pvpanic.h" OBJECT_DECLARE_SIMPLE_TYPE(PVPanicISAState, PVPANIC_ISA_DEVICE) @@ -64,7 +65,8 @@ static void pvpanic_isa_realizefn(DeviceState *dev, Error **errp) static Property pvpanic_isa_properties[] = { DEFINE_PROP_UINT16(PVPANIC_IOPORT_PROP, PVPanicISAState, ioport, 0x505), - DEFINE_PROP_UINT8("events", PVPanicISAState, pvpanic.events, PVPANIC_PANICKED | PVPANIC_CRASHLOADED), + DEFINE_PROP_UINT8("events", PVPanicISAState, pvpanic.events, + PVPANIC_PANICKED | PVPANIC_CRASH_LOADED), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/misc/pvpanic-pci.c b/hw/misc/pvpanic-pci.c index 62e1be68c1..99cf7e2041 100644 --- a/hw/misc/pvpanic-pci.c +++ b/hw/misc/pvpanic-pci.c @@ -21,6 +21,7 @@ #include "hw/misc/pvpanic.h" #include "qom/object.h" #include "hw/pci/pci.h" +#include "standard-headers/linux/pvpanic.h" OBJECT_DECLARE_SIMPLE_TYPE(PVPanicPCIState, PVPANIC_PCI_DEVICE) @@ -53,7 +54,8 @@ static void pvpanic_pci_realizefn(PCIDevice *dev, Error **errp) } static Property pvpanic_pci_properties[] = { - DEFINE_PROP_UINT8("events", PVPanicPCIState, pvpanic.events, PVPANIC_PANICKED | PVPANIC_CRASHLOADED), + DEFINE_PROP_UINT8("events", PVPanicPCIState, pvpanic.events, + PVPANIC_PANICKED | PVPANIC_CRASH_LOADED), DEFINE_PROP_END_OF_LIST(), }; diff --git a/hw/misc/pvpanic.c b/hw/misc/pvpanic.c index e2cb4a5d28..1540e9091a 100644 --- a/hw/misc/pvpanic.c +++ b/hw/misc/pvpanic.c @@ -21,12 +21,13 @@ #include "hw/qdev-properties.h" #include "hw/misc/pvpanic.h" #include "qom/object.h" +#include "standard-headers/linux/pvpanic.h" static void handle_event(int event) { static bool logged; - if (event & ~(PVPANIC_PANICKED | PVPANIC_CRASHLOADED) && !logged) { + if (event & ~(PVPANIC_PANICKED | PVPANIC_CRASH_LOADED) && !logged) { qemu_log_mask(LOG_GUEST_ERROR, "pvpanic: unknown event %#x.\n", event); logged = true; } @@ -36,7 +37,7 @@ static void handle_event(int event) return; } - if (event & PVPANIC_CRASHLOADED) { + if (event & PVPANIC_CRASH_LOADED) { qemu_system_guest_crashloaded(NULL); return; } diff --git a/hw/net/virtio-net.c b/hw/net/virtio-net.c index cf8ab0f8af..b02a0632df 100644 --- a/hw/net/virtio-net.c +++ b/hw/net/virtio-net.c @@ -628,17 +628,20 @@ static int virtio_net_max_tx_queue_size(VirtIONet *n) NetClientState *peer = n->nic_conf.peers.ncs[0]; /* - * Backends other than vhost-user don't support max queue size. + * Backends other than vhost-user or vhost-vdpa don't support max queue + * size. */ if (!peer) { return VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE; } - if (peer->info->type != NET_CLIENT_DRIVER_VHOST_USER) { + switch(peer->info->type) { + case NET_CLIENT_DRIVER_VHOST_USER: + case NET_CLIENT_DRIVER_VHOST_VDPA: + return VIRTQUEUE_MAX_SIZE; + default: return VIRTIO_NET_TX_QUEUE_DEFAULT_SIZE; - } - - return VIRTQUEUE_MAX_SIZE; + }; } static int peer_attach(VirtIONet *n, int index) diff --git a/hw/pci-bridge/pci_expander_bridge.c b/hw/pci-bridge/pci_expander_bridge.c index 10e6e7c2ab..de932286b5 100644 --- a/hw/pci-bridge/pci_expander_bridge.c +++ b/hw/pci-bridge/pci_expander_bridge.c @@ -192,6 +192,12 @@ static int pxb_map_irq_fn(PCIDevice *pci_dev, int pin) { PCIDevice *pxb = pci_get_bus(pci_dev)->parent_dev; + /* + * First carry out normal swizzle to handle + * multple root ports on a pxb instance. + */ + pin = pci_swizzle_map_irq_fn(pci_dev, pin); + /* * The bios does not index the pxb slot number when * it computes the IRQ because it resides on bus 0 diff --git a/hw/pci-bridge/xio3130_downstream.c b/hw/pci-bridge/xio3130_downstream.c index 04aae72cd6..05e2b06c0c 100644 --- a/hw/pci-bridge/xio3130_downstream.c +++ b/hw/pci-bridge/xio3130_downstream.c @@ -28,6 +28,7 @@ #include "migration/vmstate.h" #include "qapi/error.h" #include "qemu/module.h" +#include "hw/pci-bridge/xio3130_downstream.h" #define PCI_DEVICE_ID_TI_XIO3130D 0x8233 /* downstream port */ #define XIO3130_REVISION 0x1 @@ -84,7 +85,7 @@ static void xio3130_downstream_realize(PCIDevice *d, Error **errp) XIO3130_SSVID_SVID, XIO3130_SSVID_SSID, errp); if (rc < 0) { - goto err_bridge; + goto err_msi; } rc = pcie_cap_init(d, XIO3130_EXP_OFFSET, PCI_EXP_TYPE_DOWNSTREAM, @@ -173,7 +174,7 @@ static void xio3130_downstream_class_init(ObjectClass *klass, void *data) } static const TypeInfo xio3130_downstream_info = { - .name = "xio3130-downstream", + .name = TYPE_XIO3130_DOWNSTREAM, .parent = TYPE_PCIE_SLOT, .class_init = xio3130_downstream_class_init, .interfaces = (InterfaceInfo[]) { diff --git a/hw/pci-bridge/xio3130_upstream.c b/hw/pci-bridge/xio3130_upstream.c index 5cd3af4fbc..5ff46ef050 100644 --- a/hw/pci-bridge/xio3130_upstream.c +++ b/hw/pci-bridge/xio3130_upstream.c @@ -75,7 +75,7 @@ static void xio3130_upstream_realize(PCIDevice *d, Error **errp) XIO3130_SSVID_SVID, XIO3130_SSVID_SSID, errp); if (rc < 0) { - goto err_bridge; + goto err_msi; } rc = pcie_cap_init(d, XIO3130_EXP_OFFSET, PCI_EXP_TYPE_UPSTREAM, diff --git a/hw/pci/meson.build b/hw/pci/meson.build index 5c4bbac817..bcc9c75919 100644 --- a/hw/pci/meson.build +++ b/hw/pci/meson.build @@ -5,6 +5,7 @@ pci_ss.add(files( 'pci.c', 'pci_bridge.c', 'pci_host.c', + 'pcie_sriov.c', 'shpc.c', 'slotid_cap.c' )) diff --git a/hw/pci/pci.c b/hw/pci/pci.c index 5d30f9ca60..5cb1232e27 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -239,6 +239,9 @@ int pci_bar(PCIDevice *d, int reg) { uint8_t type; + /* PCIe virtual functions do not have their own BARs */ + assert(!pci_is_vf(d)); + if (reg != PCI_ROM_SLOT) return PCI_BASE_ADDRESS_0 + reg * 4; @@ -304,10 +307,30 @@ void pci_device_deassert_intx(PCIDevice *dev) } } -static void pci_do_device_reset(PCIDevice *dev) +static void pci_reset_regions(PCIDevice *dev) { int r; + if (pci_is_vf(dev)) { + return; + } + for (r = 0; r < PCI_NUM_REGIONS; ++r) { + PCIIORegion *region = &dev->io_regions[r]; + if (!region->size) { + continue; + } + + if (!(region->type & PCI_BASE_ADDRESS_SPACE_IO) && + region->type & PCI_BASE_ADDRESS_MEM_TYPE_64) { + pci_set_quad(dev->config + pci_bar(dev, r), region->type); + } else { + pci_set_long(dev->config + pci_bar(dev, r), region->type); + } + } +} + +static void pci_do_device_reset(PCIDevice *dev) +{ pci_device_deassert_intx(dev); assert(dev->irq_state == 0); @@ -323,19 +346,7 @@ static void pci_do_device_reset(PCIDevice *dev) pci_get_word(dev->wmask + PCI_INTERRUPT_LINE) | pci_get_word(dev->w1cmask + PCI_INTERRUPT_LINE)); dev->config[PCI_CACHE_LINE_SIZE] = 0x0; - for (r = 0; r < PCI_NUM_REGIONS; ++r) { - PCIIORegion *region = &dev->io_regions[r]; - if (!region->size) { - continue; - } - - if (!(region->type & PCI_BASE_ADDRESS_SPACE_IO) && - region->type & PCI_BASE_ADDRESS_MEM_TYPE_64) { - pci_set_quad(dev->config + pci_bar(dev, r), region->type); - } else { - pci_set_long(dev->config + pci_bar(dev, r), region->type); - } - } + pci_reset_regions(dev); pci_update_mappings(dev); msi_reset(dev); @@ -884,6 +895,16 @@ static void pci_init_multifunction(PCIBus *bus, PCIDevice *dev, Error **errp) dev->config[PCI_HEADER_TYPE] |= PCI_HEADER_TYPE_MULTI_FUNCTION; } + /* + * With SR/IOV and ARI, a device at function 0 need not be a multifunction + * device, as it may just be a VF that ended up with function 0 in + * the legacy PCI interpretation. Avoid failing in such cases: + */ + if (pci_is_vf(dev) && + dev->exp.sriov_vf.pf->cap_present & QEMU_PCI_CAP_MULTIFUNCTION) { + return; + } + /* * multifunction bit is interpreted in two ways as follows. * - all functions must set the bit to 1. @@ -1078,11 +1099,12 @@ static PCIDevice *do_pci_register_device(PCIDevice *pci_dev, return NULL; } else if (!pci_bus_devfn_available(bus, devfn)) { error_setg(errp, "PCI: slot %d function %d not available for %s," - " in use by %s", + " in use by %s,id=%s", PCI_SLOT(devfn), PCI_FUNC(devfn), name, - bus->devices[devfn]->name); + bus->devices[devfn]->name, bus->devices[devfn]->qdev.id); return NULL; } else if (dev->hotplugged && + !pci_is_vf(pci_dev) && pci_get_function_0(pci_dev)) { error_setg(errp, "PCI: slot %d function 0 already occupied by %s," " new func %s cannot be exposed to guest.", @@ -1191,6 +1213,7 @@ void pci_register_bar(PCIDevice *pci_dev, int region_num, pcibus_t size = memory_region_size(memory); uint8_t hdr_type; + assert(!pci_is_vf(pci_dev)); /* VFs must use pcie_sriov_vf_register_bar */ assert(region_num >= 0); assert(region_num < PCI_NUM_REGIONS); assert(is_power_of_2(size)); @@ -1294,11 +1317,45 @@ pcibus_t pci_get_bar_addr(PCIDevice *pci_dev, int region_num) return pci_dev->io_regions[region_num].addr; } -static pcibus_t pci_bar_address(PCIDevice *d, - int reg, uint8_t type, pcibus_t size) +static pcibus_t pci_config_get_bar_addr(PCIDevice *d, int reg, + uint8_t type, pcibus_t size) +{ + pcibus_t new_addr; + if (!pci_is_vf(d)) { + int bar = pci_bar(d, reg); + if (type & PCI_BASE_ADDRESS_MEM_TYPE_64) { + new_addr = pci_get_quad(d->config + bar); + } else { + new_addr = pci_get_long(d->config + bar); + } + } else { + PCIDevice *pf = d->exp.sriov_vf.pf; + uint16_t sriov_cap = pf->exp.sriov_cap; + int bar = sriov_cap + PCI_SRIOV_BAR + reg * 4; + uint16_t vf_offset = + pci_get_word(pf->config + sriov_cap + PCI_SRIOV_VF_OFFSET); + uint16_t vf_stride = + pci_get_word(pf->config + sriov_cap + PCI_SRIOV_VF_STRIDE); + uint32_t vf_num = (d->devfn - (pf->devfn + vf_offset)) / vf_stride; + + if (type & PCI_BASE_ADDRESS_MEM_TYPE_64) { + new_addr = pci_get_quad(pf->config + bar); + } else { + new_addr = pci_get_long(pf->config + bar); + } + new_addr += vf_num * size; + } + /* The ROM slot has a specific enable bit, keep it intact */ + if (reg != PCI_ROM_SLOT) { + new_addr &= ~(size - 1); + } + return new_addr; +} + +pcibus_t pci_bar_address(PCIDevice *d, + int reg, uint8_t type, pcibus_t size) { pcibus_t new_addr, last_addr; - int bar = pci_bar(d, reg); uint16_t cmd = pci_get_word(d->config + PCI_COMMAND); Object *machine = qdev_get_machine(); ObjectClass *oc = object_get_class(machine); @@ -1309,7 +1366,7 @@ static pcibus_t pci_bar_address(PCIDevice *d, if (!(cmd & PCI_COMMAND_IO)) { return PCI_BAR_UNMAPPED; } - new_addr = pci_get_long(d->config + bar) & ~(size - 1); + new_addr = pci_config_get_bar_addr(d, reg, type, size); last_addr = new_addr + size - 1; /* Check if 32 bit BAR wraps around explicitly. * TODO: make priorities correct and remove this work around. @@ -1324,11 +1381,7 @@ static pcibus_t pci_bar_address(PCIDevice *d, if (!(cmd & PCI_COMMAND_MEMORY)) { return PCI_BAR_UNMAPPED; } - if (type & PCI_BASE_ADDRESS_MEM_TYPE_64) { - new_addr = pci_get_quad(d->config + bar); - } else { - new_addr = pci_get_long(d->config + bar); - } + new_addr = pci_config_get_bar_addr(d, reg, type, size); /* the ROM slot has a specific enable bit */ if (reg == PCI_ROM_SLOT && !(new_addr & PCI_ROM_ADDRESS_ENABLE)) { return PCI_BAR_UNMAPPED; @@ -1473,6 +1526,7 @@ void pci_default_write_config(PCIDevice *d, uint32_t addr, uint32_t val_in, int msi_write_config(d, addr, val_in, l); msix_write_config(d, addr, val_in, l); + pcie_sriov_config_write(d, addr, val_in, l); } /***********************************************************/ diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c index d7d73a31e4..67a5d67372 100644 --- a/hw/pci/pcie.c +++ b/hw/pci/pcie.c @@ -366,6 +366,17 @@ static void hotplug_event_clear(PCIDevice *dev) } } +void pcie_cap_slot_enable_power(PCIDevice *dev) +{ + uint8_t *exp_cap = dev->config + dev->exp.exp_cap; + uint32_t sltcap = pci_get_long(exp_cap + PCI_EXP_SLTCAP); + + if (sltcap & PCI_EXP_SLTCAP_PCP) { + pci_set_word_by_mask(exp_cap + PCI_EXP_SLTCTL, + PCI_EXP_SLTCTL_PCC, PCI_EXP_SLTCTL_PWR_ON); + } +} + static void pcie_set_power_device(PCIBus *bus, PCIDevice *dev, void *opaque) { bool *power = opaque; @@ -446,6 +457,11 @@ void pcie_cap_slot_plug_cb(HotplugHandler *hotplug_dev, DeviceState *dev, PCIDevice *pci_dev = PCI_DEVICE(dev); uint32_t lnkcap = pci_get_long(exp_cap + PCI_EXP_LNKCAP); + if (pci_is_vf(pci_dev)) { + /* Virtual function cannot be physically disconnected */ + return; + } + /* Don't send event when device is enabled during qemu machine creation: * it is present on boot, no hotplug event is necessary. We do send an * event when the device is disabled later. */ diff --git a/hw/pci/pcie_sriov.c b/hw/pci/pcie_sriov.c new file mode 100644 index 0000000000..87abad6ac8 --- /dev/null +++ b/hw/pci/pcie_sriov.c @@ -0,0 +1,302 @@ +/* + * pcie_sriov.c: + * + * Implementation of SR/IOV emulation support. + * + * Copyright (c) 2015-2017 Knut Omang + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#include "qemu/osdep.h" +#include "hw/pci/pci.h" +#include "hw/pci/pcie.h" +#include "hw/pci/pci_bus.h" +#include "hw/qdev-properties.h" +#include "qemu/error-report.h" +#include "qemu/range.h" +#include "qapi/error.h" +#include "trace.h" + +static PCIDevice *register_vf(PCIDevice *pf, int devfn, + const char *name, uint16_t vf_num); +static void unregister_vfs(PCIDevice *dev); + +void pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset, + const char *vfname, uint16_t vf_dev_id, + uint16_t init_vfs, uint16_t total_vfs, + uint16_t vf_offset, uint16_t vf_stride) +{ + uint8_t *cfg = dev->config + offset; + uint8_t *wmask; + + pcie_add_capability(dev, PCI_EXT_CAP_ID_SRIOV, 1, + offset, PCI_EXT_CAP_SRIOV_SIZEOF); + dev->exp.sriov_cap = offset; + dev->exp.sriov_pf.num_vfs = 0; + dev->exp.sriov_pf.vfname = g_strdup(vfname); + dev->exp.sriov_pf.vf = NULL; + + pci_set_word(cfg + PCI_SRIOV_VF_OFFSET, vf_offset); + pci_set_word(cfg + PCI_SRIOV_VF_STRIDE, vf_stride); + + /* + * Mandatory page sizes to support. + * Device implementations can call pcie_sriov_pf_add_sup_pgsize() + * to set more bits: + */ + pci_set_word(cfg + PCI_SRIOV_SUP_PGSIZE, SRIOV_SUP_PGSIZE_MINREQ); + + /* + * Default is to use 4K pages, software can modify it + * to any of the supported bits + */ + pci_set_word(cfg + PCI_SRIOV_SYS_PGSIZE, 0x1); + + /* Set up device ID and initial/total number of VFs available */ + pci_set_word(cfg + PCI_SRIOV_VF_DID, vf_dev_id); + pci_set_word(cfg + PCI_SRIOV_INITIAL_VF, init_vfs); + pci_set_word(cfg + PCI_SRIOV_TOTAL_VF, total_vfs); + pci_set_word(cfg + PCI_SRIOV_NUM_VF, 0); + + /* Write enable control bits */ + wmask = dev->wmask + offset; + pci_set_word(wmask + PCI_SRIOV_CTRL, + PCI_SRIOV_CTRL_VFE | PCI_SRIOV_CTRL_MSE | PCI_SRIOV_CTRL_ARI); + pci_set_word(wmask + PCI_SRIOV_NUM_VF, 0xffff); + pci_set_word(wmask + PCI_SRIOV_SYS_PGSIZE, 0x553); + + qdev_prop_set_bit(&dev->qdev, "multifunction", true); +} + +void pcie_sriov_pf_exit(PCIDevice *dev) +{ + unregister_vfs(dev); + g_free((char *)dev->exp.sriov_pf.vfname); + dev->exp.sriov_pf.vfname = NULL; +} + +void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num, + uint8_t type, dma_addr_t size) +{ + uint32_t addr; + uint64_t wmask; + uint16_t sriov_cap = dev->exp.sriov_cap; + + assert(sriov_cap > 0); + assert(region_num >= 0); + assert(region_num < PCI_NUM_REGIONS); + assert(region_num != PCI_ROM_SLOT); + + wmask = ~(size - 1); + addr = sriov_cap + PCI_SRIOV_BAR + region_num * 4; + + pci_set_long(dev->config + addr, type); + if (!(type & PCI_BASE_ADDRESS_SPACE_IO) && + type & PCI_BASE_ADDRESS_MEM_TYPE_64) { + pci_set_quad(dev->wmask + addr, wmask); + pci_set_quad(dev->cmask + addr, ~0ULL); + } else { + pci_set_long(dev->wmask + addr, wmask & 0xffffffff); + pci_set_long(dev->cmask + addr, 0xffffffff); + } + dev->exp.sriov_pf.vf_bar_type[region_num] = type; +} + +void pcie_sriov_vf_register_bar(PCIDevice *dev, int region_num, + MemoryRegion *memory) +{ + PCIIORegion *r; + PCIBus *bus = pci_get_bus(dev); + uint8_t type; + pcibus_t size = memory_region_size(memory); + + assert(pci_is_vf(dev)); /* PFs must use pci_register_bar */ + assert(region_num >= 0); + assert(region_num < PCI_NUM_REGIONS); + type = dev->exp.sriov_vf.pf->exp.sriov_pf.vf_bar_type[region_num]; + + if (!is_power_of_2(size)) { + error_report("%s: PCI region size must be a power" + " of two - type=0x%x, size=0x%"FMT_PCIBUS, + __func__, type, size); + exit(1); + } + + r = &dev->io_regions[region_num]; + r->memory = memory; + r->address_space = + type & PCI_BASE_ADDRESS_SPACE_IO + ? bus->address_space_io + : bus->address_space_mem; + r->size = size; + r->type = type; + + r->addr = pci_bar_address(dev, region_num, r->type, r->size); + if (r->addr != PCI_BAR_UNMAPPED) { + memory_region_add_subregion_overlap(r->address_space, + r->addr, r->memory, 1); + } +} + +static PCIDevice *register_vf(PCIDevice *pf, int devfn, const char *name, + uint16_t vf_num) +{ + PCIDevice *dev = pci_new(devfn, name); + dev->exp.sriov_vf.pf = pf; + dev->exp.sriov_vf.vf_number = vf_num; + PCIBus *bus = pci_get_bus(pf); + Error *local_err = NULL; + + qdev_realize(&dev->qdev, &bus->qbus, &local_err); + if (local_err) { + error_report_err(local_err); + return NULL; + } + + /* set vid/did according to sr/iov spec - they are not used */ + pci_config_set_vendor_id(dev->config, 0xffff); + pci_config_set_device_id(dev->config, 0xffff); + + return dev; +} + +static void register_vfs(PCIDevice *dev) +{ + uint16_t num_vfs; + uint16_t i; + uint16_t sriov_cap = dev->exp.sriov_cap; + uint16_t vf_offset = + pci_get_word(dev->config + sriov_cap + PCI_SRIOV_VF_OFFSET); + uint16_t vf_stride = + pci_get_word(dev->config + sriov_cap + PCI_SRIOV_VF_STRIDE); + int32_t devfn = dev->devfn + vf_offset; + + assert(sriov_cap > 0); + num_vfs = pci_get_word(dev->config + sriov_cap + PCI_SRIOV_NUM_VF); + + dev->exp.sriov_pf.vf = g_malloc(sizeof(PCIDevice *) * num_vfs); + assert(dev->exp.sriov_pf.vf); + + trace_sriov_register_vfs(dev->name, PCI_SLOT(dev->devfn), + PCI_FUNC(dev->devfn), num_vfs); + for (i = 0; i < num_vfs; i++) { + dev->exp.sriov_pf.vf[i] = register_vf(dev, devfn, + dev->exp.sriov_pf.vfname, i); + if (!dev->exp.sriov_pf.vf[i]) { + num_vfs = i; + break; + } + devfn += vf_stride; + } + dev->exp.sriov_pf.num_vfs = num_vfs; +} + +static void unregister_vfs(PCIDevice *dev) +{ + Error *local_err = NULL; + uint16_t num_vfs = dev->exp.sriov_pf.num_vfs; + uint16_t i; + + trace_sriov_unregister_vfs(dev->name, PCI_SLOT(dev->devfn), + PCI_FUNC(dev->devfn), num_vfs); + for (i = 0; i < num_vfs; i++) { + PCIDevice *vf = dev->exp.sriov_pf.vf[i]; + object_property_set_bool(OBJECT(vf), "realized", false, &local_err); + if (local_err) { + fprintf(stderr, "Failed to unplug: %s\n", + error_get_pretty(local_err)); + error_free(local_err); + } + object_unparent(OBJECT(vf)); + } + g_free(dev->exp.sriov_pf.vf); + dev->exp.sriov_pf.vf = NULL; + dev->exp.sriov_pf.num_vfs = 0; + pci_set_word(dev->config + dev->exp.sriov_cap + PCI_SRIOV_NUM_VF, 0); +} + +void pcie_sriov_config_write(PCIDevice *dev, uint32_t address, + uint32_t val, int len) +{ + uint32_t off; + uint16_t sriov_cap = dev->exp.sriov_cap; + + if (!sriov_cap || address < sriov_cap) { + return; + } + off = address - sriov_cap; + if (off >= PCI_EXT_CAP_SRIOV_SIZEOF) { + return; + } + + trace_sriov_config_write(dev->name, PCI_SLOT(dev->devfn), + PCI_FUNC(dev->devfn), off, val, len); + + if (range_covers_byte(off, len, PCI_SRIOV_CTRL)) { + if (dev->exp.sriov_pf.num_vfs) { + if (!(val & PCI_SRIOV_CTRL_VFE)) { + unregister_vfs(dev); + } + } else { + if (val & PCI_SRIOV_CTRL_VFE) { + register_vfs(dev); + } + } + } +} + + +/* Reset SR/IOV VF Enable bit to trigger an unregister of all VFs */ +void pcie_sriov_pf_disable_vfs(PCIDevice *dev) +{ + uint16_t sriov_cap = dev->exp.sriov_cap; + if (sriov_cap) { + uint32_t val = pci_get_byte(dev->config + sriov_cap + PCI_SRIOV_CTRL); + if (val & PCI_SRIOV_CTRL_VFE) { + val &= ~PCI_SRIOV_CTRL_VFE; + pcie_sriov_config_write(dev, sriov_cap + PCI_SRIOV_CTRL, val, 1); + } + } +} + +/* Add optional supported page sizes to the mask of supported page sizes */ +void pcie_sriov_pf_add_sup_pgsize(PCIDevice *dev, uint16_t opt_sup_pgsize) +{ + uint8_t *cfg = dev->config + dev->exp.sriov_cap; + uint8_t *wmask = dev->wmask + dev->exp.sriov_cap; + + uint16_t sup_pgsize = pci_get_word(cfg + PCI_SRIOV_SUP_PGSIZE); + + sup_pgsize |= opt_sup_pgsize; + + /* + * Make sure the new bits are set, and that system page size + * also can be set to any of the new values according to spec: + */ + pci_set_word(cfg + PCI_SRIOV_SUP_PGSIZE, sup_pgsize); + pci_set_word(wmask + PCI_SRIOV_SYS_PGSIZE, sup_pgsize); +} + + +uint16_t pcie_sriov_vf_number(PCIDevice *dev) +{ + assert(pci_is_vf(dev)); + return dev->exp.sriov_vf.vf_number; +} + +PCIDevice *pcie_sriov_get_pf(PCIDevice *dev) +{ + return dev->exp.sriov_vf.pf; +} + +PCIDevice *pcie_sriov_get_vf_at_index(PCIDevice *dev, int n) +{ + assert(!pci_is_vf(dev)); + if (n < dev->exp.sriov_pf.num_vfs) { + return dev->exp.sriov_pf.vf[n]; + } + return NULL; +} diff --git a/hw/pci/trace-events b/hw/pci/trace-events index 7570752c40..aaf46bc92d 100644 --- a/hw/pci/trace-events +++ b/hw/pci/trace-events @@ -10,3 +10,8 @@ pci_cfg_write(const char *dev, uint32_t bus, uint32_t slot, uint32_t func, unsig # msix.c msix_write_config(char *name, bool enabled, bool masked) "dev %s enabled %d masked %d" + +# hw/pci/pcie_sriov.c +sriov_register_vfs(const char *name, int slot, int function, int num_vfs) "%s %02x:%x: creating %d vf devs" +sriov_unregister_vfs(const char *name, int slot, int function, int num_vfs) "%s %02x:%x: Unregistering %d vf devs" +sriov_config_write(const char *name, int slot, int fun, uint32_t offset, uint32_t val, uint32_t len) "%s %02x:%x: sriov offset 0x%x val 0x%x len %d" diff --git a/hw/smbios/smbios.c b/hw/smbios/smbios.c index 6013df1698..60349ee402 100644 --- a/hw/smbios/smbios.c +++ b/hw/smbios/smbios.c @@ -104,9 +104,11 @@ static struct { const char *sock_pfx, *manufacturer, *version, *serial, *asset, *part; uint64_t max_speed; uint64_t current_speed; + uint64_t processor_id; } type4 = { .max_speed = DEFAULT_CPU_SPEED, - .current_speed = DEFAULT_CPU_SPEED + .current_speed = DEFAULT_CPU_SPEED, + .processor_id = 0, }; static struct { @@ -327,6 +329,10 @@ static const QemuOptDesc qemu_smbios_type4_opts[] = { .name = "part", .type = QEMU_OPT_STRING, .help = "part number", + }, { + .name = "processor-id", + .type = QEMU_OPT_NUMBER, + .help = "processor id", }, { /* end of list */ } }; @@ -549,9 +555,23 @@ bool smbios_skip_table(uint8_t type, bool required_table) return true; } +#define T0_BASE 0x000 +#define T1_BASE 0x100 +#define T2_BASE 0x200 +#define T3_BASE 0x300 +#define T4_BASE 0x400 +#define T11_BASE 0xe00 + +#define T16_BASE 0x1000 +#define T17_BASE 0x1100 +#define T19_BASE 0x1300 +#define T32_BASE 0x2000 +#define T41_BASE 0x2900 +#define T127_BASE 0x7F00 + static void smbios_build_type_0_table(void) { - SMBIOS_BUILD_TABLE_PRE(0, 0x000, false); /* optional, leave up to BIOS */ + SMBIOS_BUILD_TABLE_PRE(0, T0_BASE, false); /* optional, leave up to BIOS */ SMBIOS_TABLE_SET_STR(0, vendor_str, type0.vendor); SMBIOS_TABLE_SET_STR(0, bios_version_str, type0.version); @@ -599,7 +619,7 @@ static void smbios_encode_uuid(struct smbios_uuid *uuid, QemuUUID *in) static void smbios_build_type_1_table(void) { - SMBIOS_BUILD_TABLE_PRE(1, 0x100, true); /* required */ + SMBIOS_BUILD_TABLE_PRE(1, T1_BASE, true); /* required */ SMBIOS_TABLE_SET_STR(1, manufacturer_str, type1.manufacturer); SMBIOS_TABLE_SET_STR(1, product_name_str, type1.product); @@ -619,7 +639,7 @@ static void smbios_build_type_1_table(void) static void smbios_build_type_2_table(void) { - SMBIOS_BUILD_TABLE_PRE(2, 0x200, false); /* optional */ + SMBIOS_BUILD_TABLE_PRE(2, T2_BASE, false); /* optional */ SMBIOS_TABLE_SET_STR(2, manufacturer_str, type2.manufacturer); SMBIOS_TABLE_SET_STR(2, product_str, type2.product); @@ -637,7 +657,7 @@ static void smbios_build_type_2_table(void) static void smbios_build_type_3_table(void) { - SMBIOS_BUILD_TABLE_PRE(3, 0x300, true); /* required */ + SMBIOS_BUILD_TABLE_PRE(3, T3_BASE, true); /* required */ SMBIOS_TABLE_SET_STR(3, manufacturer_str, type3.manufacturer); t->type = 0x01; /* Other */ @@ -662,15 +682,20 @@ static void smbios_build_type_4_table(MachineState *ms, unsigned instance) { char sock_str[128]; - SMBIOS_BUILD_TABLE_PRE(4, 0x400 + instance, true); /* required */ + SMBIOS_BUILD_TABLE_PRE(4, T4_BASE + instance, true); /* required */ snprintf(sock_str, sizeof(sock_str), "%s%2x", type4.sock_pfx, instance); SMBIOS_TABLE_SET_STR(4, socket_designation_str, sock_str); t->processor_type = 0x03; /* CPU */ t->processor_family = 0x01; /* Other */ SMBIOS_TABLE_SET_STR(4, processor_manufacturer_str, type4.manufacturer); - t->processor_id[0] = cpu_to_le32(smbios_cpuid_version); - t->processor_id[1] = cpu_to_le32(smbios_cpuid_features); + if (type4.processor_id == 0) { + t->processor_id[0] = cpu_to_le32(smbios_cpuid_version); + t->processor_id[1] = cpu_to_le32(smbios_cpuid_features); + } else { + t->processor_id[0] = cpu_to_le32((uint32_t)type4.processor_id); + t->processor_id[1] = cpu_to_le32(type4.processor_id >> 32); + } SMBIOS_TABLE_SET_STR(4, processor_version_str, type4.version); t->voltage = 0; t->external_clock = cpu_to_le16(0); /* Unknown */ @@ -702,7 +727,7 @@ static void smbios_build_type_11_table(void) return; } - SMBIOS_BUILD_TABLE_PRE(11, 0xe00, true); /* required */ + SMBIOS_BUILD_TABLE_PRE(11, T11_BASE, true); /* required */ snprintf(count_str, sizeof(count_str), "%zu", type11.nvalues); t->count = type11.nvalues; @@ -722,7 +747,7 @@ static void smbios_build_type_16_table(unsigned dimm_cnt) { uint64_t size_kb; - SMBIOS_BUILD_TABLE_PRE(16, 0x1000, true); /* required */ + SMBIOS_BUILD_TABLE_PRE(16, T16_BASE, true); /* required */ t->location = 0x01; /* Other */ t->use = 0x03; /* System memory */ @@ -749,7 +774,7 @@ static void smbios_build_type_17_table(unsigned instance, uint64_t size) char loc_str[128]; uint64_t size_mb; - SMBIOS_BUILD_TABLE_PRE(17, 0x1100 + instance, true); /* required */ + SMBIOS_BUILD_TABLE_PRE(17, T17_BASE + instance, true); /* required */ t->physical_memory_array_handle = cpu_to_le16(0x1000); /* Type 16 above */ t->memory_error_information_handle = cpu_to_le16(0xFFFE); /* Not provided */ @@ -785,12 +810,13 @@ static void smbios_build_type_17_table(unsigned instance, uint64_t size) SMBIOS_BUILD_TABLE_POST; } -static void smbios_build_type_19_table(unsigned instance, +static void smbios_build_type_19_table(unsigned instance, unsigned offset, uint64_t start, uint64_t size) { uint64_t end, start_kb, end_kb; - SMBIOS_BUILD_TABLE_PRE(19, 0x1300 + instance, true); /* required */ + SMBIOS_BUILD_TABLE_PRE(19, T19_BASE + offset + instance, + true); /* required */ end = start + size - 1; assert(end > start); @@ -814,7 +840,7 @@ static void smbios_build_type_19_table(unsigned instance, static void smbios_build_type_32_table(void) { - SMBIOS_BUILD_TABLE_PRE(32, 0x2000, true); /* required */ + SMBIOS_BUILD_TABLE_PRE(32, T32_BASE, true); /* required */ memset(t->reserved, 0, 6); t->boot_status = 0; /* No errors detected */ @@ -828,7 +854,7 @@ static void smbios_build_type_41_table(Error **errp) struct type41_instance *t41; QTAILQ_FOREACH(t41, &type41, next) { - SMBIOS_BUILD_TABLE_PRE(41, 0x2900 + instance, true); + SMBIOS_BUILD_TABLE_PRE(41, T41_BASE + instance, true); SMBIOS_TABLE_SET_STR(41, reference_designation_str, t41->designation); t->device_type = t41->kind; @@ -871,7 +897,7 @@ static void smbios_build_type_41_table(Error **errp) static void smbios_build_type_127_table(void) { - SMBIOS_BUILD_TABLE_PRE(127, 0x7F00, true); /* required */ + SMBIOS_BUILD_TABLE_PRE(127, T127_BASE, true); /* required */ SMBIOS_BUILD_TABLE_POST; } @@ -982,7 +1008,7 @@ void smbios_get_tables(MachineState *ms, uint8_t **anchor, size_t *anchor_len, Error **errp) { - unsigned i, dimm_cnt; + unsigned i, dimm_cnt, offset; if (smbios_legacy) { *tables = *anchor = NULL; @@ -1012,6 +1038,16 @@ void smbios_get_tables(MachineState *ms, dimm_cnt = QEMU_ALIGN_UP(current_machine->ram_size, MAX_DIMM_SZ) / MAX_DIMM_SZ; + /* + * The offset determines if we need to keep additional space betweeen + * table 17 and table 19 header handle numbers so that they do + * not overlap. For example, for a VM with larger than 8 TB guest + * memory and DIMM like chunks of 16 GiB, the default space between + * the two tables (T19_BASE - T17_BASE = 512) is not enough. + */ + offset = (dimm_cnt > (T19_BASE - T17_BASE)) ? \ + dimm_cnt - (T19_BASE - T17_BASE) : 0; + smbios_build_type_16_table(dimm_cnt); for (i = 0; i < dimm_cnt; i++) { @@ -1019,10 +1055,16 @@ void smbios_get_tables(MachineState *ms, } for (i = 0; i < mem_array_size; i++) { - smbios_build_type_19_table(i, mem_array[i].address, + smbios_build_type_19_table(i, offset, mem_array[i].address, mem_array[i].length); } + /* + * make sure 16 bit handle numbers in the headers of tables 19 + * and 32 do not overlap. + */ + assert((mem_array_size + offset) < (T32_BASE - T19_BASE)); + smbios_build_type_32_table(); smbios_build_type_38_table(); smbios_build_type_41_table(errp); @@ -1292,6 +1334,8 @@ void smbios_entry_add(QemuOpts *opts, Error **errp) save_opt(&type4.serial, opts, "serial"); save_opt(&type4.asset, opts, "asset"); save_opt(&type4.part, opts, "part"); + /* If the value is 0, it will take the value from the CPU model. */ + type4.processor_id = qemu_opt_get_number(opts, "processor-id", 0); type4.max_speed = qemu_opt_get_number(opts, "max-speed", DEFAULT_CPU_SPEED); type4.current_speed = qemu_opt_get_number(opts, "current-speed", diff --git a/hw/virtio/trace-events b/hw/virtio/trace-events index f7ad6be5fb..a5102eac9e 100644 --- a/hw/virtio/trace-events +++ b/hw/virtio/trace-events @@ -89,9 +89,11 @@ virtio_mmio_setting_irq(int level) "virtio_mmio setting IRQ %d" # virtio-iommu.c virtio_iommu_device_reset(void) "reset!" +virtio_iommu_system_reset(void) "system reset!" virtio_iommu_get_features(uint64_t features) "device supports features=0x%"PRIx64 virtio_iommu_device_status(uint8_t status) "driver status = %d" -virtio_iommu_get_config(uint64_t page_size_mask, uint64_t start, uint64_t end, uint32_t domain_start, uint32_t domain_end, uint32_t probe_size) "page_size_mask=0x%"PRIx64" input range start=0x%"PRIx64" input range end=0x%"PRIx64" domain range start=%d domain range end=%d probe_size=0x%x" +virtio_iommu_get_config(uint64_t page_size_mask, uint64_t start, uint64_t end, uint32_t domain_start, uint32_t domain_end, uint32_t probe_size, uint8_t bypass) "page_size_mask=0x%"PRIx64" input range start=0x%"PRIx64" input range end=0x%"PRIx64" domain range start=%d domain range end=%d probe_size=0x%x bypass=0x%x" +virtio_iommu_set_config(uint8_t bypass) "bypass=0x%x" virtio_iommu_attach(uint32_t domain_id, uint32_t ep_id) "domain=%d endpoint=%d" virtio_iommu_detach(uint32_t domain_id, uint32_t ep_id) "domain=%d endpoint=%d" virtio_iommu_map(uint32_t domain_id, uint64_t virt_start, uint64_t virt_end, uint64_t phys_start, uint32_t flags) "domain=%d virt_start=0x%"PRIx64" virt_end=0x%"PRIx64 " phys_start=0x%"PRIx64" flags=%d" diff --git a/hw/virtio/vhost-user-i2c.c b/hw/virtio/vhost-user-i2c.c index d172632bb0..42c7f6d9e5 100644 --- a/hw/virtio/vhost-user-i2c.c +++ b/hw/virtio/vhost-user-i2c.c @@ -19,6 +19,11 @@ #define VIRTIO_ID_I2C_ADAPTER 34 #endif +static const int feature_bits[] = { + VIRTIO_I2C_F_ZERO_LENGTH_REQUEST, + VHOST_INVALID_FEATURE_BIT +}; + static void vu_i2c_start(VirtIODevice *vdev) { BusState *qbus = BUS(qdev_get_parent_bus(DEVICE(vdev))); @@ -113,8 +118,10 @@ static void vu_i2c_set_status(VirtIODevice *vdev, uint8_t status) static uint64_t vu_i2c_get_features(VirtIODevice *vdev, uint64_t requested_features, Error **errp) { - /* No feature bits used yet */ - return requested_features; + VHostUserI2C *i2c = VHOST_USER_I2C(vdev); + + virtio_add_feature(&requested_features, VIRTIO_I2C_F_ZERO_LENGTH_REQUEST); + return vhost_get_features(&i2c->vhost_dev, feature_bits, requested_features); } static void vu_i2c_handle_output(VirtIODevice *vdev, VirtQueue *vq) diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 662853513e..6abbc9da32 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -25,6 +25,7 @@ #include "migration/migration.h" #include "migration/postcopy-ram.h" #include "trace.h" +#include "exec/ramblock.h" #include #include @@ -1162,37 +1163,32 @@ static int vhost_user_set_vring_num(struct vhost_dev *dev, return vhost_set_vring(dev, VHOST_USER_SET_VRING_NUM, ring); } -static void vhost_user_host_notifier_restore(struct vhost_dev *dev, - int queue_idx) +static void vhost_user_host_notifier_free(VhostUserHostNotifier *n) { - struct vhost_user *u = dev->opaque; - VhostUserHostNotifier *n = &u->user->notifier[queue_idx]; - VirtIODevice *vdev = dev->vdev; - - if (n->addr && !n->set) { - virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, true); - n->set = true; - } + assert(n && n->unmap_addr); + munmap(n->unmap_addr, qemu_real_host_page_size); + n->unmap_addr = NULL; } -static void vhost_user_host_notifier_remove(struct vhost_dev *dev, - int queue_idx) +static void vhost_user_host_notifier_remove(VhostUserState *user, + VirtIODevice *vdev, int queue_idx) { - struct vhost_user *u = dev->opaque; - VhostUserHostNotifier *n = &u->user->notifier[queue_idx]; - VirtIODevice *vdev = dev->vdev; + VhostUserHostNotifier *n = &user->notifier[queue_idx]; - if (n->addr && n->set) { - virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, false); - n->set = false; + if (n->addr) { + if (vdev) { + virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, false); + } + assert(!n->unmap_addr); + n->unmap_addr = n->addr; + n->addr = NULL; + call_rcu(n, vhost_user_host_notifier_free, rcu); } } static int vhost_user_set_vring_base(struct vhost_dev *dev, struct vhost_vring_state *ring) { - vhost_user_host_notifier_restore(dev, ring->index); - return vhost_set_vring(dev, VHOST_USER_SET_VRING_BASE, ring); } @@ -1235,8 +1231,9 @@ static int vhost_user_get_vring_base(struct vhost_dev *dev, .payload.state = *ring, .hdr.size = sizeof(msg.payload.state), }; + struct vhost_user *u = dev->opaque; - vhost_user_host_notifier_remove(dev, ring->index); + vhost_user_host_notifier_remove(u->user, dev->vdev, ring->index); ret = vhost_user_write(dev, &msg, NULL, 0); if (ret < 0) { @@ -1522,12 +1519,7 @@ static int vhost_user_slave_handle_vring_host_notifier(struct vhost_dev *dev, n = &user->notifier[queue_idx]; - if (n->addr) { - virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, false); - object_unparent(OBJECT(&n->mr)); - munmap(n->addr, page_size); - n->addr = NULL; - } + vhost_user_host_notifier_remove(user, vdev, queue_idx); if (area->u64 & VHOST_USER_VRING_NOFD_MASK) { return 0; @@ -1546,9 +1538,12 @@ static int vhost_user_slave_handle_vring_host_notifier(struct vhost_dev *dev, name = g_strdup_printf("vhost-user/host-notifier@%p mmaps[%d]", user, queue_idx); - if (!n->mr.ram) /* Don't init again after suspend. */ + if (!n->mr.ram) { /* Don't init again after suspend. */ memory_region_init_ram_device_ptr(&n->mr, OBJECT(vdev), name, page_size, addr); + } else { + n->mr.ram_block->host = addr; + } g_free(name); if (virtio_queue_set_host_notifier_mr(vdev, queue_idx, &n->mr, true)) { @@ -1558,7 +1553,6 @@ static int vhost_user_slave_handle_vring_host_notifier(struct vhost_dev *dev, } n->addr = addr; - n->set = true; return 0; } @@ -2522,17 +2516,16 @@ bool vhost_user_init(VhostUserState *user, CharBackend *chr, Error **errp) void vhost_user_cleanup(VhostUserState *user) { int i; + VhostUserHostNotifier *n; if (!user->chr) { return; } memory_region_transaction_begin(); for (i = 0; i < VIRTIO_QUEUE_MAX; i++) { - if (user->notifier[i].addr) { - object_unparent(OBJECT(&user->notifier[i].mr)); - munmap(user->notifier[i].addr, qemu_real_host_page_size); - user->notifier[i].addr = NULL; - } + n = &user->notifier[i]; + vhost_user_host_notifier_remove(user, NULL, i); + object_unparent(OBJECT(&n->mr)); } memory_region_transaction_commit(); user->chr = NULL; diff --git a/hw/virtio/vhost-vdpa.c b/hw/virtio/vhost-vdpa.c index 04ea43704f..6c67d5f034 100644 --- a/hw/virtio/vhost-vdpa.c +++ b/hw/virtio/vhost-vdpa.c @@ -395,15 +395,6 @@ static void vhost_vdpa_host_notifier_uninit(struct vhost_dev *dev, } } -static void vhost_vdpa_host_notifiers_uninit(struct vhost_dev *dev, int n) -{ - int i; - - for (i = 0; i < n; i++) { - vhost_vdpa_host_notifier_uninit(dev, i); - } -} - static int vhost_vdpa_host_notifier_init(struct vhost_dev *dev, int queue_index) { size_t page_size = qemu_real_host_page_size; @@ -431,6 +422,7 @@ static int vhost_vdpa_host_notifier_init(struct vhost_dev *dev, int queue_index) g_free(name); if (virtio_queue_set_host_notifier_mr(vdev, queue_index, &n->mr, true)) { + object_unparent(OBJECT(&n->mr)); munmap(addr, page_size); goto err; } @@ -442,6 +434,15 @@ err: return -1; } +static void vhost_vdpa_host_notifiers_uninit(struct vhost_dev *dev, int n) +{ + int i; + + for (i = dev->vq_index; i < dev->vq_index + n; i++) { + vhost_vdpa_host_notifier_uninit(dev, i); + } +} + static void vhost_vdpa_host_notifiers_init(struct vhost_dev *dev) { int i; @@ -455,7 +456,7 @@ static void vhost_vdpa_host_notifiers_init(struct vhost_dev *dev) return; err: - vhost_vdpa_host_notifiers_uninit(dev, i); + vhost_vdpa_host_notifiers_uninit(dev, i - dev->vq_index); return; } diff --git a/hw/virtio/vhost-vsock-common.c b/hw/virtio/vhost-vsock-common.c index 3f3771274e..ed706681ac 100644 --- a/hw/virtio/vhost-vsock-common.c +++ b/hw/virtio/vhost-vsock-common.c @@ -153,19 +153,23 @@ static void vhost_vsock_common_send_transport_reset(VHostVSockCommon *vvc) if (elem->out_num) { error_report("invalid vhost-vsock event virtqueue element with " "out buffers"); - goto out; + goto err; } if (iov_from_buf(elem->in_sg, elem->in_num, 0, &event, sizeof(event)) != sizeof(event)) { error_report("vhost-vsock event virtqueue element is too short"); - goto out; + goto err; } virtqueue_push(vq, elem, sizeof(event)); virtio_notify(VIRTIO_DEVICE(vvc), vq); -out: + g_free(elem); + return; + +err: + virtqueue_detach_element(vq, elem, 0); g_free(elem); } diff --git a/hw/virtio/vhost.c b/hw/virtio/vhost.c index 7b03efccec..b643f42ea4 100644 --- a/hw/virtio/vhost.c +++ b/hw/virtio/vhost.c @@ -1287,7 +1287,7 @@ static int vhost_virtqueue_init(struct vhost_dev *dev, return r; } - file.fd = event_notifier_get_fd(&vq->masked_notifier); + file.fd = event_notifier_get_wfd(&vq->masked_notifier); r = dev->vhost_ops->vhost_set_vring_call(dev, &file); if (r) { VHOST_OPS_DEBUG(r, "vhost_set_vring_call failed"); @@ -1542,9 +1542,9 @@ void vhost_virtqueue_mask(struct vhost_dev *hdev, VirtIODevice *vdev, int n, if (mask) { assert(vdev->use_guest_notifier_mask); - file.fd = event_notifier_get_fd(&hdev->vqs[index].masked_notifier); + file.fd = event_notifier_get_wfd(&hdev->vqs[index].masked_notifier); } else { - file.fd = event_notifier_get_fd(virtio_queue_get_guest_notifier(vvq)); + file.fd = event_notifier_get_wfd(virtio_queue_get_guest_notifier(vvq)); } file.index = hdev->vhost_ops->vhost_get_vq_index(hdev, n); diff --git a/hw/virtio/virtio-bus.c b/hw/virtio/virtio-bus.c index d23db98c56..0f69d1c742 100644 --- a/hw/virtio/virtio-bus.c +++ b/hw/virtio/virtio-bus.c @@ -48,6 +48,7 @@ void virtio_bus_device_plugged(VirtIODevice *vdev, Error **errp) VirtioBusClass *klass = VIRTIO_BUS_GET_CLASS(bus); VirtioDeviceClass *vdc = VIRTIO_DEVICE_GET_CLASS(vdev); bool has_iommu = virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM); + bool vdev_has_iommu; Error *local_err = NULL; DPRINTF("%s: plug device.\n", qbus->name); @@ -69,11 +70,6 @@ void virtio_bus_device_plugged(VirtIODevice *vdev, Error **errp) return; } - if (has_iommu && !virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM)) { - error_setg(errp, "iommu_platform=true is not supported by the device"); - return; - } - if (klass->device_plugged != NULL) { klass->device_plugged(qbus->parent, &local_err); } @@ -82,9 +78,15 @@ void virtio_bus_device_plugged(VirtIODevice *vdev, Error **errp) return; } + vdev_has_iommu = virtio_host_has_feature(vdev, VIRTIO_F_IOMMU_PLATFORM); if (klass->get_dma_as != NULL && has_iommu) { virtio_add_feature(&vdev->host_features, VIRTIO_F_IOMMU_PLATFORM); vdev->dma_as = klass->get_dma_as(qbus->parent); + if (!vdev_has_iommu && vdev->dma_as != &address_space_memory) { + error_setg(errp, + "iommu_platform=true is not supported by the device"); + return; + } } else { vdev->dma_as = &address_space_memory; } diff --git a/hw/virtio/virtio-iommu.c b/hw/virtio/virtio-iommu.c index aa9c16a17b..239fe97b12 100644 --- a/hw/virtio/virtio-iommu.c +++ b/hw/virtio/virtio-iommu.c @@ -24,6 +24,7 @@ #include "hw/qdev-properties.h" #include "hw/virtio/virtio.h" #include "sysemu/kvm.h" +#include "sysemu/reset.h" #include "qapi/error.h" #include "qemu/error-report.h" #include "trace.h" @@ -42,6 +43,7 @@ typedef struct VirtIOIOMMUDomain { uint32_t id; + bool bypass; GTree *mappings; QLIST_HEAD(, VirtIOIOMMUEndpoint) endpoint_list; } VirtIOIOMMUDomain; @@ -257,12 +259,16 @@ static void virtio_iommu_put_endpoint(gpointer data) } static VirtIOIOMMUDomain *virtio_iommu_get_domain(VirtIOIOMMU *s, - uint32_t domain_id) + uint32_t domain_id, + bool bypass) { VirtIOIOMMUDomain *domain; domain = g_tree_lookup(s->domains, GUINT_TO_POINTER(domain_id)); if (domain) { + if (domain->bypass != bypass) { + return NULL; + } return domain; } domain = g_malloc0(sizeof(*domain)); @@ -270,6 +276,7 @@ static VirtIOIOMMUDomain *virtio_iommu_get_domain(VirtIOIOMMU *s, domain->mappings = g_tree_new_full((GCompareDataFunc)interval_cmp, NULL, (GDestroyNotify)g_free, (GDestroyNotify)g_free); + domain->bypass = bypass; g_tree_insert(s->domains, GUINT_TO_POINTER(domain_id), domain); QLIST_INIT(&domain->endpoint_list); trace_virtio_iommu_get_domain(domain_id); @@ -333,11 +340,16 @@ static int virtio_iommu_attach(VirtIOIOMMU *s, { uint32_t domain_id = le32_to_cpu(req->domain); uint32_t ep_id = le32_to_cpu(req->endpoint); + uint32_t flags = le32_to_cpu(req->flags); VirtIOIOMMUDomain *domain; VirtIOIOMMUEndpoint *ep; trace_virtio_iommu_attach(domain_id, ep_id); + if (flags & ~VIRTIO_IOMMU_ATTACH_F_BYPASS) { + return VIRTIO_IOMMU_S_INVAL; + } + ep = virtio_iommu_get_endpoint(s, ep_id); if (!ep) { return VIRTIO_IOMMU_S_NOENT; @@ -355,7 +367,12 @@ static int virtio_iommu_attach(VirtIOIOMMU *s, } } - domain = virtio_iommu_get_domain(s, domain_id); + domain = virtio_iommu_get_domain(s, domain_id, + flags & VIRTIO_IOMMU_ATTACH_F_BYPASS); + if (!domain) { + /* Incompatible bypass flag */ + return VIRTIO_IOMMU_S_INVAL; + } QLIST_INSERT_HEAD(&domain->endpoint_list, ep, next); ep->domain = domain; @@ -418,6 +435,10 @@ static int virtio_iommu_map(VirtIOIOMMU *s, return VIRTIO_IOMMU_S_NOENT; } + if (domain->bypass) { + return VIRTIO_IOMMU_S_INVAL; + } + interval = g_malloc0(sizeof(*interval)); interval->low = virt_start; @@ -463,6 +484,11 @@ static int virtio_iommu_unmap(VirtIOIOMMU *s, if (!domain) { return VIRTIO_IOMMU_S_NOENT; } + + if (domain->bypass) { + return VIRTIO_IOMMU_S_INVAL; + } + interval.low = virt_start; interval.high = virt_end; @@ -728,8 +754,7 @@ static IOMMUTLBEntry virtio_iommu_translate(IOMMUMemoryRegion *mr, hwaddr addr, .perm = IOMMU_NONE, }; - bypass_allowed = virtio_vdev_has_feature(&s->parent_obj, - VIRTIO_IOMMU_F_BYPASS); + bypass_allowed = s->config.bypass; sid = virtio_iommu_get_bdf(sdev); @@ -780,6 +805,9 @@ static IOMMUTLBEntry virtio_iommu_translate(IOMMUMemoryRegion *mr, hwaddr addr, entry.perm = flag; } goto unlock; + } else if (ep->domain->bypass) { + entry.perm = flag; + goto unlock; } found = g_tree_lookup_extended(ep->domain->mappings, (gpointer)(&interval), @@ -831,13 +859,37 @@ static void virtio_iommu_get_config(VirtIODevice *vdev, uint8_t *config_data) out_config->domain_range.start = cpu_to_le32(dev_config->domain_range.start); out_config->domain_range.end = cpu_to_le32(dev_config->domain_range.end); out_config->probe_size = cpu_to_le32(dev_config->probe_size); + out_config->bypass = dev_config->bypass; trace_virtio_iommu_get_config(dev_config->page_size_mask, dev_config->input_range.start, dev_config->input_range.end, dev_config->domain_range.start, dev_config->domain_range.end, - dev_config->probe_size); + dev_config->probe_size, + dev_config->bypass); +} + +static void virtio_iommu_set_config(VirtIODevice *vdev, + const uint8_t *config_data) +{ + VirtIOIOMMU *dev = VIRTIO_IOMMU(vdev); + struct virtio_iommu_config *dev_config = &dev->config; + const struct virtio_iommu_config *in_config = (void *)config_data; + + if (in_config->bypass != dev_config->bypass) { + if (!virtio_vdev_has_feature(vdev, VIRTIO_IOMMU_F_BYPASS_CONFIG)) { + virtio_error(vdev, "cannot set config.bypass"); + return; + } else if (in_config->bypass != 0 && in_config->bypass != 1) { + virtio_error(vdev, "invalid config.bypass value '%u'", + in_config->bypass); + return; + } + dev_config->bypass = in_config->bypass; + } + + trace_virtio_iommu_set_config(in_config->bypass); } static uint64_t virtio_iommu_get_features(VirtIODevice *vdev, uint64_t f, @@ -963,6 +1015,19 @@ static int virtio_iommu_set_page_size_mask(IOMMUMemoryRegion *mr, return 0; } +static void virtio_iommu_system_reset(void *opaque) +{ + VirtIOIOMMU *s = opaque; + + trace_virtio_iommu_system_reset(); + + /* + * config.bypass is sticky across device reset, but should be restored on + * system reset + */ + s->config.bypass = s->boot_bypass; +} + static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) { VirtIODevice *vdev = VIRTIO_DEVICE(dev); @@ -988,9 +1053,9 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) virtio_add_feature(&s->features, VIRTIO_IOMMU_F_INPUT_RANGE); virtio_add_feature(&s->features, VIRTIO_IOMMU_F_DOMAIN_RANGE); virtio_add_feature(&s->features, VIRTIO_IOMMU_F_MAP_UNMAP); - virtio_add_feature(&s->features, VIRTIO_IOMMU_F_BYPASS); virtio_add_feature(&s->features, VIRTIO_IOMMU_F_MMIO); virtio_add_feature(&s->features, VIRTIO_IOMMU_F_PROBE); + virtio_add_feature(&s->features, VIRTIO_IOMMU_F_BYPASS_CONFIG); qemu_mutex_init(&s->mutex); @@ -1001,6 +1066,8 @@ static void virtio_iommu_device_realize(DeviceState *dev, Error **errp) } else { error_setg(errp, "VIRTIO-IOMMU is not attached to any PCI bus!"); } + + qemu_register_reset(virtio_iommu_system_reset, s); } static void virtio_iommu_device_unrealize(DeviceState *dev) @@ -1008,6 +1075,8 @@ static void virtio_iommu_device_unrealize(DeviceState *dev) VirtIODevice *vdev = VIRTIO_DEVICE(dev); VirtIOIOMMU *s = VIRTIO_IOMMU(dev); + qemu_unregister_reset(virtio_iommu_system_reset, s); + g_hash_table_destroy(s->as_by_busptr); if (s->domains) { g_tree_destroy(s->domains); @@ -1098,8 +1167,8 @@ static const VMStateDescription vmstate_endpoint = { static const VMStateDescription vmstate_domain = { .name = "domain", - .version_id = 1, - .minimum_version_id = 1, + .version_id = 2, + .minimum_version_id = 2, .pre_load = domain_preload, .fields = (VMStateField[]) { VMSTATE_UINT32(id, VirtIOIOMMUDomain), @@ -1108,6 +1177,7 @@ static const VMStateDescription vmstate_domain = { VirtIOIOMMUInterval, VirtIOIOMMUMapping), VMSTATE_QLIST_V(endpoint_list, VirtIOIOMMUDomain, 1, vmstate_endpoint, VirtIOIOMMUEndpoint, next), + VMSTATE_BOOL_V(bypass, VirtIOIOMMUDomain, 2), VMSTATE_END_OF_LIST() } }; @@ -1141,21 +1211,22 @@ static int iommu_post_load(void *opaque, int version_id) static const VMStateDescription vmstate_virtio_iommu_device = { .name = "virtio-iommu-device", - .minimum_version_id = 1, - .version_id = 1, + .minimum_version_id = 2, + .version_id = 2, .post_load = iommu_post_load, .fields = (VMStateField[]) { - VMSTATE_GTREE_DIRECT_KEY_V(domains, VirtIOIOMMU, 1, + VMSTATE_GTREE_DIRECT_KEY_V(domains, VirtIOIOMMU, 2, &vmstate_domain, VirtIOIOMMUDomain), + VMSTATE_UINT8_V(config.bypass, VirtIOIOMMU, 2), VMSTATE_END_OF_LIST() }, }; static const VMStateDescription vmstate_virtio_iommu = { .name = "virtio-iommu", - .minimum_version_id = 1, + .minimum_version_id = 2, .priority = MIG_PRI_IOMMU, - .version_id = 1, + .version_id = 2, .fields = (VMStateField[]) { VMSTATE_VIRTIO_DEVICE, VMSTATE_END_OF_LIST() @@ -1164,6 +1235,7 @@ static const VMStateDescription vmstate_virtio_iommu = { static Property virtio_iommu_properties[] = { DEFINE_PROP_LINK("primary-bus", VirtIOIOMMU, primary_bus, "PCI", PCIBus *), + DEFINE_PROP_BOOL("boot-bypass", VirtIOIOMMU, boot_bypass, true), DEFINE_PROP_END_OF_LIST(), }; @@ -1180,6 +1252,7 @@ static void virtio_iommu_class_init(ObjectClass *klass, void *data) vdc->unrealize = virtio_iommu_device_unrealize; vdc->reset = virtio_iommu_device_reset; vdc->get_config = virtio_iommu_get_config; + vdc->set_config = virtio_iommu_set_config; vdc->get_features = virtio_iommu_get_features; vdc->set_status = virtio_iommu_set_status; vdc->vmsd = &vmstate_virtio_iommu_device; diff --git a/include/hw/acpi/acpi-defs.h b/include/hw/acpi/acpi-defs.h index c97e8633ad..2b42e4192b 100644 --- a/include/hw/acpi/acpi-defs.h +++ b/include/hw/acpi/acpi-defs.h @@ -77,6 +77,7 @@ typedef struct AcpiFadtData { uint16_t plvl2_lat; /* P_LVL2_LAT */ uint16_t plvl3_lat; /* P_LVL3_LAT */ uint16_t arm_boot_arch; /* ARM_BOOT_ARCH */ + uint16_t iapc_boot_arch; /* IAPC_BOOT_ARCH */ uint8_t minor_ver; /* FADT Minor Version */ /* diff --git a/include/hw/i386/intel_iommu.h b/include/hw/i386/intel_iommu.h index 41783ee46d..3b5ac869db 100644 --- a/include/hw/i386/intel_iommu.h +++ b/include/hw/i386/intel_iommu.h @@ -228,6 +228,7 @@ struct IntelIOMMUState { bool caching_mode; /* RO - is cap CM enabled? */ bool scalable_mode; /* RO - is Scalable Mode supported? */ + bool snoop_control; /* RO - is SNP filed supported? */ dma_addr_t root; /* Current root table pointer */ bool root_scalable; /* Type of root table (scalable or not) */ diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index 9c9f4ac748..1a27de9c8b 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -48,6 +48,7 @@ typedef struct PCMachineState { bool sata_enabled; bool pit_enabled; bool hpet_enabled; + bool i8042_enabled; bool default_bus_bypass_iommu; uint64_t max_fw_size; @@ -64,6 +65,7 @@ typedef struct PCMachineState { #define PC_MACHINE_SMBUS "smbus" #define PC_MACHINE_SATA "sata" #define PC_MACHINE_PIT "pit" +#define PC_MACHINE_I8042 "i8042" #define PC_MACHINE_MAX_FW_SIZE "max-fw-size" #define PC_MACHINE_SMBIOS_EP "smbios-entry-point-type" diff --git a/include/hw/i386/x86.h b/include/hw/i386/x86.h index a145a30370..916cc325ee 100644 --- a/include/hw/i386/x86.h +++ b/include/hw/i386/x86.h @@ -35,8 +35,6 @@ struct X86MachineClass { /* TSC rate migration: */ bool save_tsc_khz; - /* Enables contiguous-apic-ID mode */ - bool compat_apic_id_mode; /* use DMA capable linuxboot option rom */ bool fwcfg_dma_enabled; }; diff --git a/include/hw/input/i8042.h b/include/hw/input/i8042.h index 1d90432dae..e070f546e4 100644 --- a/include/hw/input/i8042.h +++ b/include/hw/input/i8042.h @@ -23,4 +23,19 @@ void i8042_mm_init(qemu_irq kbd_irq, qemu_irq mouse_irq, void i8042_isa_mouse_fake_event(ISAKBDState *isa); void i8042_setup_a20_line(ISADevice *dev, qemu_irq a20_out); +static inline bool i8042_present(void) +{ + bool amb = false; + return object_resolve_path_type("", TYPE_I8042, &amb) || amb; +} + +/* + * ACPI v2, Table 5-10 - Fixed ACPI Description Table Boot Architecture + * Flags, bit offset 1 - 8042. + */ +static inline uint16_t iapc_boot_arch_8042(void) +{ + return i8042_present() ? 0x1 << 1 : 0x0 ; +} + #endif /* HW_INPUT_I8042_H */ diff --git a/include/hw/misc/pvpanic.h b/include/hw/misc/pvpanic.h index ca3c5bb533..7f16cc9b16 100644 --- a/include/hw/misc/pvpanic.h +++ b/include/hw/misc/pvpanic.h @@ -22,14 +22,6 @@ #define PVPANIC_IOPORT_PROP "ioport" -/* The bit of supported pv event, TODO: include uapi header and remove this */ -#define PVPANIC_F_PANICKED 0 -#define PVPANIC_F_CRASHLOADED 1 - -/* The pv event value */ -#define PVPANIC_PANICKED (1 << PVPANIC_F_PANICKED) -#define PVPANIC_CRASHLOADED (1 << PVPANIC_F_CRASHLOADED) - /* * PVPanicState for any device type */ diff --git a/include/hw/pci-bridge/xio3130_downstream.h b/include/hw/pci-bridge/xio3130_downstream.h new file mode 100644 index 0000000000..1d10139aea --- /dev/null +++ b/include/hw/pci-bridge/xio3130_downstream.h @@ -0,0 +1,15 @@ +/* + * TI X3130 pci express downstream port switch + * + * Copyright (C) 2022 Igor Mammedov + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_PCI_BRIDGE_XIO3130_DOWNSTREAM_H +#define HW_PCI_BRIDGE_XIO3130_DOWNSTREAM_H + +#define TYPE_XIO3130_DOWNSTREAM "xio3130-downstream" + +#endif + diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h index c3f3c90473..3a32b8dd40 100644 --- a/include/hw/pci/pci.h +++ b/include/hw/pci/pci.h @@ -7,9 +7,6 @@ /* PCI includes legacy ISA access. */ #include "hw/isa/isa.h" -#include "hw/pci/pcie.h" -#include "qom/object.h" - extern bool pci_available; /* PCI bus */ @@ -157,6 +154,7 @@ enum { #define QEMU_PCI_VGA_IO_HI_SIZE 0x20 #include "hw/pci/pci_regs.h" +#include "hw/pci/pcie.h" /* PCI HEADER_TYPE */ #define PCI_HEADER_TYPE_MULTI_FUNCTION 0x80 @@ -499,6 +497,9 @@ typedef AddressSpace *(*PCIIOMMUFunc)(PCIBus *, void *, int); AddressSpace *pci_device_iommu_address_space(PCIDevice *dev); void pci_setup_iommu(PCIBus *bus, PCIIOMMUFunc fn, void *opaque); +pcibus_t pci_bar_address(PCIDevice *d, + int reg, uint8_t type, pcibus_t size); + static inline void pci_set_byte(uint8_t *config, uint8_t val) { @@ -779,6 +780,11 @@ static inline int pci_is_express_downstream_port(const PCIDevice *d) return type == PCI_EXP_TYPE_DOWNSTREAM || type == PCI_EXP_TYPE_ROOT_PORT; } +static inline int pci_is_vf(const PCIDevice *d) +{ + return d->exp.sriov_vf.pf != NULL; +} + static inline uint32_t pci_config_size(const PCIDevice *d) { return pci_is_express(d) ? PCIE_CONFIG_SPACE_SIZE : PCI_CONFIG_SPACE_SIZE; diff --git a/include/hw/pci/pci_regs.h b/include/hw/pci/pci_regs.h index 77ba64b931..a590140962 100644 --- a/include/hw/pci/pci_regs.h +++ b/include/hw/pci/pci_regs.h @@ -4,5 +4,6 @@ #include "standard-headers/linux/pci_regs.h" #define PCI_PM_CAP_VER_1_1 0x0002 /* PCI PM spec ver. 1.1 */ +#define PCI_PM_CAP_VER_1_2 0x0003 /* PCI PM spec ver. 1.2 */ #endif diff --git a/include/hw/pci/pcie.h b/include/hw/pci/pcie.h index 6063bee0ec..798a262a0a 100644 --- a/include/hw/pci/pcie.h +++ b/include/hw/pci/pcie.h @@ -24,6 +24,7 @@ #include "hw/pci/pci_regs.h" #include "hw/pci/pcie_regs.h" #include "hw/pci/pcie_aer.h" +#include "hw/pci/pcie_sriov.h" #include "hw/hotplug.h" typedef enum { @@ -81,6 +82,11 @@ struct PCIExpressDevice { /* ACS */ uint16_t acs_cap; + + /* SR/IOV */ + uint16_t sriov_cap; + PCIESriovPF sriov_pf; + PCIESriovVF sriov_vf; }; #define COMPAT_PROP_PCP "power_controller_present" @@ -112,6 +118,7 @@ void pcie_cap_slot_write_config(PCIDevice *dev, uint32_t addr, uint32_t val, int len); int pcie_cap_slot_post_load(void *opaque, int version_id); void pcie_cap_slot_push_attention_button(PCIDevice *dev); +void pcie_cap_slot_enable_power(PCIDevice *dev); void pcie_cap_root_init(PCIDevice *dev); void pcie_cap_root_reset(PCIDevice *dev); diff --git a/include/hw/pci/pcie_sriov.h b/include/hw/pci/pcie_sriov.h new file mode 100644 index 0000000000..80f5c84e75 --- /dev/null +++ b/include/hw/pci/pcie_sriov.h @@ -0,0 +1,77 @@ +/* + * pcie_sriov.h: + * + * Implementation of SR/IOV emulation support. + * + * Copyright (c) 2015 Knut Omang + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + */ + +#ifndef QEMU_PCIE_SRIOV_H +#define QEMU_PCIE_SRIOV_H + +struct PCIESriovPF { + uint16_t num_vfs; /* Number of virtual functions created */ + uint8_t vf_bar_type[PCI_NUM_REGIONS]; /* Store type for each VF bar */ + const char *vfname; /* Reference to the device type used for the VFs */ + PCIDevice **vf; /* Pointer to an array of num_vfs VF devices */ +}; + +struct PCIESriovVF { + PCIDevice *pf; /* Pointer back to owner physical function */ + uint16_t vf_number; /* Logical VF number of this function */ +}; + +void pcie_sriov_pf_init(PCIDevice *dev, uint16_t offset, + const char *vfname, uint16_t vf_dev_id, + uint16_t init_vfs, uint16_t total_vfs, + uint16_t vf_offset, uint16_t vf_stride); +void pcie_sriov_pf_exit(PCIDevice *dev); + +/* Set up a VF bar in the SR/IOV bar area */ +void pcie_sriov_pf_init_vf_bar(PCIDevice *dev, int region_num, + uint8_t type, dma_addr_t size); + +/* Instantiate a bar for a VF */ +void pcie_sriov_vf_register_bar(PCIDevice *dev, int region_num, + MemoryRegion *memory); + +/* + * Default (minimal) page size support values + * as required by the SR/IOV standard: + * 0x553 << 12 = 0x553000 = 4K + 8K + 64K + 256K + 1M + 4M + */ +#define SRIOV_SUP_PGSIZE_MINREQ 0x553 + +/* + * Optionally add supported page sizes to the mask of supported page sizes + * Page size values are interpreted as opt_sup_pgsize << 12. + */ +void pcie_sriov_pf_add_sup_pgsize(PCIDevice *dev, uint16_t opt_sup_pgsize); + +/* SR/IOV capability config write handler */ +void pcie_sriov_config_write(PCIDevice *dev, uint32_t address, + uint32_t val, int len); + +/* Reset SR/IOV VF Enable bit to unregister all VFs */ +void pcie_sriov_pf_disable_vfs(PCIDevice *dev); + +/* Get logical VF number of a VF - only valid for VFs */ +uint16_t pcie_sriov_vf_number(PCIDevice *dev); + +/* + * Get the physical function that owns this VF. + * Returns NULL if dev is not a virtual function + */ +PCIDevice *pcie_sriov_get_pf(PCIDevice *dev); + +/* + * Get the n-th VF of this physical function - only valid for PF. + * Returns NULL if index is invalid + */ +PCIDevice *pcie_sriov_get_vf_at_index(PCIDevice *dev, int n); + +#endif /* QEMU_PCIE_SRIOV_H */ diff --git a/include/hw/virtio/vhost-user-i2c.h b/include/hw/virtio/vhost-user-i2c.h index deae47a76d..d8372f3b43 100644 --- a/include/hw/virtio/vhost-user-i2c.h +++ b/include/hw/virtio/vhost-user-i2c.h @@ -25,4 +25,7 @@ struct VHostUserI2C { bool connected; }; +/* Virtio Feature bits */ +#define VIRTIO_I2C_F_ZERO_LENGTH_REQUEST 0 + #endif /* _QEMU_VHOST_USER_I2C_H */ diff --git a/include/hw/virtio/vhost-user.h b/include/hw/virtio/vhost-user.h index a9abca3288..e44a41bb70 100644 --- a/include/hw/virtio/vhost-user.h +++ b/include/hw/virtio/vhost-user.h @@ -12,9 +12,10 @@ #include "hw/virtio/virtio.h" typedef struct VhostUserHostNotifier { + struct rcu_head rcu; MemoryRegion mr; void *addr; - bool set; + void *unmap_addr; } VhostUserHostNotifier; typedef struct VhostUserState { diff --git a/include/hw/virtio/virtio-iommu.h b/include/hw/virtio/virtio-iommu.h index e2339e5b72..84391f8448 100644 --- a/include/hw/virtio/virtio-iommu.h +++ b/include/hw/virtio/virtio-iommu.h @@ -58,6 +58,7 @@ struct VirtIOIOMMU { GTree *domains; QemuMutex mutex; GTree *endpoints; + bool boot_bypass; }; #endif diff --git a/include/qemu/event_notifier.h b/include/qemu/event_notifier.h index b79add035d..8a4ff308e1 100644 --- a/include/qemu/event_notifier.h +++ b/include/qemu/event_notifier.h @@ -38,6 +38,7 @@ int event_notifier_test_and_clear(EventNotifier *); #ifdef CONFIG_POSIX void event_notifier_init_fd(EventNotifier *, int fd); int event_notifier_get_fd(const EventNotifier *); +int event_notifier_get_wfd(const EventNotifier *); #else HANDLE event_notifier_get_handle(EventNotifier *); #endif diff --git a/include/qemu/typedefs.h b/include/qemu/typedefs.h index c564f54c11..42f4ceb701 100644 --- a/include/qemu/typedefs.h +++ b/include/qemu/typedefs.h @@ -88,6 +88,8 @@ typedef struct PCIDevice PCIDevice; typedef struct PCIEAERErr PCIEAERErr; typedef struct PCIEAERLog PCIEAERLog; typedef struct PCIEAERMsg PCIEAERMsg; +typedef struct PCIESriovPF PCIESriovPF; +typedef struct PCIESriovVF PCIESriovVF; typedef struct PCIEPort PCIEPort; typedef struct PCIESlot PCIESlot; typedef struct PCIExpressDevice PCIExpressDevice; diff --git a/include/standard-headers/linux/pvpanic.h b/include/standard-headers/linux/pvpanic.h new file mode 100644 index 0000000000..54b7485390 --- /dev/null +++ b/include/standard-headers/linux/pvpanic.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +#ifndef __PVPANIC_H__ +#define __PVPANIC_H__ + +#define PVPANIC_PANICKED (1 << 0) +#define PVPANIC_CRASH_LOADED (1 << 1) + +#endif /* __PVPANIC_H__ */ diff --git a/meson.build b/meson.build index 0763c3b6a0..2d6601467f 100644 --- a/meson.build +++ b/meson.build @@ -2725,7 +2725,7 @@ if have_system or have_user endif vhost_user = not_found -if 'CONFIG_VHOST_USER' in config_host +if targetos == 'linux' and 'CONFIG_VHOST_USER' in config_host libvhost_user = subproject('libvhost-user') vhost_user = libvhost_user.get_variable('vhost_user_dep') endif diff --git a/qemu-options.hx b/qemu-options.hx index 094a6c1d7c..5ce0ada75e 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -2537,6 +2537,7 @@ DEF("smbios", HAS_ARG, QEMU_OPTION_smbios, " specify SMBIOS type 3 fields\n" "-smbios type=4[,sock_pfx=str][,manufacturer=str][,version=str][,serial=str]\n" " [,asset=str][,part=str][,max-speed=%d][,current-speed=%d]\n" + " [,processor-id=%d]\n" " specify SMBIOS type 4 fields\n" "-smbios type=11[,value=str][,path=filename]\n" " specify SMBIOS type 11 fields\n" @@ -2562,7 +2563,7 @@ SRST ``-smbios type=3[,manufacturer=str][,version=str][,serial=str][,asset=str][,sku=str]`` Specify SMBIOS type 3 fields -``-smbios type=4[,sock_pfx=str][,manufacturer=str][,version=str][,serial=str][,asset=str][,part=str]`` +``-smbios type=4[,sock_pfx=str][,manufacturer=str][,version=str][,serial=str][,asset=str][,part=str][,processor-id=%d]`` Specify SMBIOS type 4 fields ``-smbios type=11[,value=str][,path=filename]`` diff --git a/qom/object.c b/qom/object.c index 4048a2fef1..d34608558e 100644 --- a/qom/object.c +++ b/qom/object.c @@ -1168,10 +1168,14 @@ GSList *object_class_get_list_sorted(const char *implements_type, Object *object_ref(void *objptr) { Object *obj = OBJECT(objptr); + uint32_t ref; + if (!obj) { return NULL; } - qatomic_inc(&obj->ref); + ref = qatomic_fetch_inc(&obj->ref); + /* Assert waaay before the integer overflows */ + g_assert(ref < INT_MAX); return obj; } diff --git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers.sh index fe850763c5..839a5ec614 100755 --- a/scripts/update-linux-headers.sh +++ b/scripts/update-linux-headers.sh @@ -214,7 +214,8 @@ for i in "$tmpdir"/include/linux/*virtio*.h \ "$tmpdir/include/linux/const.h" \ "$tmpdir/include/linux/kernel.h" \ "$tmpdir/include/linux/vhost_types.h" \ - "$tmpdir/include/linux/sysinfo.h"; do + "$tmpdir/include/linux/sysinfo.h" \ + "$tmpdir/include/misc/pvpanic.h"; do cp_portable "$i" "$output/include/standard-headers/linux" done mkdir -p "$output/include/standard-headers/drm" diff --git a/tests/data/acpi/q35/FACP b/tests/data/acpi/q35/FACP index f6a864cc86..a8f6a89611 100644 Binary files a/tests/data/acpi/q35/FACP and b/tests/data/acpi/q35/FACP differ diff --git a/tests/data/acpi/q35/FACP.nosmm b/tests/data/acpi/q35/FACP.nosmm index 6a9aa5f370..c4e6d18ee5 100644 Binary files a/tests/data/acpi/q35/FACP.nosmm and b/tests/data/acpi/q35/FACP.nosmm differ diff --git a/tests/data/acpi/q35/FACP.slic b/tests/data/acpi/q35/FACP.slic index 15986e095c..48bbb1cf5a 100644 Binary files a/tests/data/acpi/q35/FACP.slic and b/tests/data/acpi/q35/FACP.slic differ diff --git a/tests/data/acpi/q35/FACP.xapic b/tests/data/acpi/q35/FACP.xapic index 2d3659c9c6..31fa5dd19c 100644 Binary files a/tests/data/acpi/q35/FACP.xapic and b/tests/data/acpi/q35/FACP.xapic differ diff --git a/tests/qtest/virtio-iommu-test.c b/tests/qtest/virtio-iommu-test.c index 47e68388a0..068e7a9e6c 100644 --- a/tests/qtest/virtio-iommu-test.c +++ b/tests/qtest/virtio-iommu-test.c @@ -31,11 +31,13 @@ static void pci_config(void *obj, void *data, QGuestAllocator *t_alloc) uint64_t input_range_end = qvirtio_config_readq(dev, 16); uint32_t domain_range_start = qvirtio_config_readl(dev, 24); uint32_t domain_range_end = qvirtio_config_readl(dev, 28); + uint8_t bypass = qvirtio_config_readb(dev, 36); g_assert_cmpint(input_range_start, ==, 0); g_assert_cmphex(input_range_end, ==, UINT64_MAX); g_assert_cmpint(domain_range_start, ==, 0); g_assert_cmpint(domain_range_end, ==, UINT32_MAX); + g_assert_cmpint(bypass, ==, 1); } static int read_tail_status(struct virtio_iommu_req_tail *buffer) diff --git a/util/event_notifier-posix.c b/util/event_notifier-posix.c index 8307013c5d..16294e98d4 100644 --- a/util/event_notifier-posix.c +++ b/util/event_notifier-posix.c @@ -99,6 +99,11 @@ int event_notifier_get_fd(const EventNotifier *e) return e->rfd; } +int event_notifier_get_wfd(const EventNotifier *e) +{ + return e->wfd; +} + int event_notifier_set(EventNotifier *e) { static const uint64_t value = 1;