diff options
Diffstat (limited to 'hw')
61 files changed, 1642 insertions, 1167 deletions
diff --git a/hw/acpi/acpi_generic_initiator.c b/hw/acpi/acpi_generic_initiator.c deleted file mode 100644 index 17b9a052f5..0000000000 --- a/hw/acpi/acpi_generic_initiator.c +++ /dev/null @@ -1,148 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* - * Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES. All rights reserved - */ - -#include "qemu/osdep.h" -#include "hw/acpi/acpi_generic_initiator.h" -#include "hw/acpi/aml-build.h" -#include "hw/boards.h" -#include "hw/pci/pci_device.h" -#include "qemu/error-report.h" - -typedef struct AcpiGenericInitiatorClass { - ObjectClass parent_class; -} AcpiGenericInitiatorClass; - -OBJECT_DEFINE_TYPE_WITH_INTERFACES(AcpiGenericInitiator, acpi_generic_initiator, - ACPI_GENERIC_INITIATOR, OBJECT, - { TYPE_USER_CREATABLE }, - { NULL }) - -OBJECT_DECLARE_SIMPLE_TYPE(AcpiGenericInitiator, ACPI_GENERIC_INITIATOR) - -static void acpi_generic_initiator_init(Object *obj) -{ - AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj); - - gi->node = MAX_NODES; - gi->pci_dev = NULL; -} - -static void acpi_generic_initiator_finalize(Object *obj) -{ - AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj); - - g_free(gi->pci_dev); -} - -static void acpi_generic_initiator_set_pci_device(Object *obj, const char *val, - Error **errp) -{ - AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj); - - gi->pci_dev = g_strdup(val); -} - -static void acpi_generic_initiator_set_node(Object *obj, Visitor *v, - const char *name, void *opaque, - Error **errp) -{ - AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj); - MachineState *ms = MACHINE(qdev_get_machine()); - uint32_t value; - - if (!visit_type_uint32(v, name, &value, errp)) { - return; - } - - if (value >= MAX_NODES) { - error_printf("%s: Invalid NUMA node specified\n", - TYPE_ACPI_GENERIC_INITIATOR); - exit(1); - } - - gi->node = value; - ms->numa_state->nodes[gi->node].has_gi = true; -} - -static void acpi_generic_initiator_class_init(ObjectClass *oc, void *data) -{ - object_class_property_add_str(oc, "pci-dev", NULL, - acpi_generic_initiator_set_pci_device); - object_class_property_add(oc, "node", "int", NULL, - acpi_generic_initiator_set_node, NULL, NULL); -} - -/* - * ACPI 6.3: - * Table 5-78 Generic Initiator Affinity Structure - */ -static void -build_srat_generic_pci_initiator_affinity(GArray *table_data, int node, - PCIDeviceHandle *handle) -{ - uint8_t index; - - build_append_int_noprefix(table_data, 5, 1); /* Type */ - build_append_int_noprefix(table_data, 32, 1); /* Length */ - build_append_int_noprefix(table_data, 0, 1); /* Reserved */ - build_append_int_noprefix(table_data, 1, 1); /* Device Handle Type: PCI */ - build_append_int_noprefix(table_data, node, 4); /* Proximity Domain */ - - /* Device Handle - PCI */ - build_append_int_noprefix(table_data, handle->segment, 2); - build_append_int_noprefix(table_data, handle->bdf, 2); - for (index = 0; index < 12; index++) { - build_append_int_noprefix(table_data, 0, 1); - } - - build_append_int_noprefix(table_data, GEN_AFFINITY_ENABLED, 4); /* Flags */ - build_append_int_noprefix(table_data, 0, 4); /* Reserved */ -} - -static int build_all_acpi_generic_initiators(Object *obj, void *opaque) -{ - MachineState *ms = MACHINE(qdev_get_machine()); - AcpiGenericInitiator *gi; - GArray *table_data = opaque; - PCIDeviceHandle dev_handle; - PCIDevice *pci_dev; - Object *o; - - if (!object_dynamic_cast(obj, TYPE_ACPI_GENERIC_INITIATOR)) { - return 0; - } - - gi = ACPI_GENERIC_INITIATOR(obj); - if (gi->node >= ms->numa_state->num_nodes) { - error_printf("%s: Specified node %d is invalid.\n", - TYPE_ACPI_GENERIC_INITIATOR, gi->node); - exit(1); - } - - o = object_resolve_path_type(gi->pci_dev, TYPE_PCI_DEVICE, NULL); - if (!o) { - error_printf("%s: Specified device must be a PCI device.\n", - TYPE_ACPI_GENERIC_INITIATOR); - exit(1); - } - - pci_dev = PCI_DEVICE(o); - - dev_handle.segment = 0; - dev_handle.bdf = PCI_BUILD_BDF(pci_bus_num(pci_get_bus(pci_dev)), - pci_dev->devfn); - - build_srat_generic_pci_initiator_affinity(table_data, - gi->node, &dev_handle); - - return 0; -} - -void build_srat_generic_pci_initiator(GArray *table_data) -{ - object_child_foreach_recursive(object_get_root(), - build_all_acpi_generic_initiators, - table_data); -} diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c index 34e0ddbde8..6a76626177 100644 --- a/hw/acpi/aml-build.c +++ b/hw/acpi/aml-build.c @@ -1938,6 +1938,89 @@ void build_srat_memory(GArray *table_data, uint64_t base, } /* + * ACPI Spec Revision 6.3 + * Table 5-80 Device Handle - PCI + */ +static void build_append_srat_pci_device_handle(GArray *table_data, + uint16_t segment, + uint8_t bus, uint8_t devfn) +{ + /* PCI segment number */ + build_append_int_noprefix(table_data, segment, 2); + /* PCI Bus Device Function */ + build_append_int_noprefix(table_data, bus, 1); + build_append_int_noprefix(table_data, devfn, 1); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 12); +} + +static void build_append_srat_acpi_device_handle(GArray *table_data, + const char *hid, + uint32_t uid) +{ + assert(strlen(hid) == 8); + /* Device Handle - ACPI */ + for (int i = 0; i < sizeof(hid); i++) { + build_append_int_noprefix(table_data, hid[i], 1); + } + build_append_int_noprefix(table_data, uid, 4); + build_append_int_noprefix(table_data, 0, 4); +} + +/* + * ACPI spec, Revision 6.3 + * 5.2.16.6 Generic Initiator Affinity Structure + * With PCI Device Handle. + */ +void build_srat_pci_generic_initiator(GArray *table_data, uint32_t node, + uint16_t segment, uint8_t bus, + uint8_t devfn) +{ + /* Type */ + build_append_int_noprefix(table_data, 5, 1); + /* Length */ + build_append_int_noprefix(table_data, 32, 1); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 1); + /* Device Handle Type: PCI */ + build_append_int_noprefix(table_data, 1, 1); + /* Proximity Domain */ + build_append_int_noprefix(table_data, node, 4); + /* Device Handle */ + build_append_srat_pci_device_handle(table_data, segment, bus, devfn); + /* Flags - GI Enabled */ + build_append_int_noprefix(table_data, 1, 4); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 4); +} + +/* + * ACPI spec, Revision 6.5 + * 5.2.16.7 Generic Port Affinity Structure + * With ACPI Device Handle. + */ +void build_srat_acpi_generic_port(GArray *table_data, uint32_t node, + const char *hid, uint32_t uid) +{ + /* Type */ + build_append_int_noprefix(table_data, 6, 1); + /* Length */ + build_append_int_noprefix(table_data, 32, 1); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 1); + /* Device Handle Type: ACPI */ + build_append_int_noprefix(table_data, 0, 1); + /* Proximity Domain */ + build_append_int_noprefix(table_data, node, 4); + /* Device Handle */ + build_append_srat_acpi_device_handle(table_data, hid, uid); + /* Flags - GP Enabled */ + build_append_int_noprefix(table_data, 1, 4); + /* Reserved */ + build_append_int_noprefix(table_data, 0, 4); +} + +/* * ACPI spec 5.2.17 System Locality Distance Information Table * (Revision 2.0 or later) */ diff --git a/hw/acpi/cpu.c b/hw/acpi/cpu.c index 5cb60ca8bc..23443f09a5 100644 --- a/hw/acpi/cpu.c +++ b/hw/acpi/cpu.c @@ -50,6 +50,18 @@ void acpi_cpu_ospm_status(CPUHotplugState *cpu_st, ACPIOSTInfoList ***list) } } +static bool check_cpu_enabled_status(DeviceState *dev) +{ + CPUClass *k = dev ? CPU_GET_CLASS(dev) : NULL; + CPUState *cpu = CPU(dev); + + if (cpu && (!k->cpu_enabled_status || k->cpu_enabled_status(cpu))) { + return true; + } + + return false; +} + static uint64_t cpu_hotplug_rd(void *opaque, hwaddr addr, unsigned size) { uint64_t val = 0; @@ -63,10 +75,11 @@ static uint64_t cpu_hotplug_rd(void *opaque, hwaddr addr, unsigned size) cdev = &cpu_st->devs[cpu_st->selector]; switch (addr) { case ACPI_CPU_FLAGS_OFFSET_RW: /* pack and return is_* fields */ - val |= cdev->cpu ? 1 : 0; + val |= check_cpu_enabled_status(DEVICE(cdev->cpu)) ? 1 : 0; val |= cdev->is_inserting ? 2 : 0; val |= cdev->is_removing ? 4 : 0; val |= cdev->fw_remove ? 16 : 0; + val |= cdev->cpu ? 32 : 0; trace_cpuhp_acpi_read_flags(cpu_st->selector, val); break; case ACPI_CPU_CMD_DATA_OFFSET_RW: @@ -233,6 +246,17 @@ void cpu_hotplug_hw_init(MemoryRegion *as, Object *owner, memory_region_add_subregion(as, base_addr, &state->ctrl_reg); } +static bool should_remain_acpi_present(DeviceState *dev) +{ + CPUClass *k = CPU_GET_CLASS(dev); + /* + * A system may contain CPUs that are always present on one die, NUMA node, + * or socket, yet may be non-present on another simultaneously. Check from + * architecture specific code. + */ + return k->cpu_persistent_status && k->cpu_persistent_status(CPU(dev)); +} + static AcpiCpuStatus *get_cpu_status(CPUHotplugState *cpu_st, DeviceState *dev) { CPUClass *k = CPU_GET_CLASS(dev); @@ -289,7 +313,9 @@ void acpi_cpu_unplug_cb(CPUHotplugState *cpu_st, return; } - cdev->cpu = NULL; + if (!should_remain_acpi_present(dev)) { + cdev->cpu = NULL; + } } static const VMStateDescription vmstate_cpuhp_sts = { @@ -336,6 +362,7 @@ const VMStateDescription vmstate_cpu_hotplug = { #define CPU_REMOVE_EVENT "CRMV" #define CPU_EJECT_EVENT "CEJ0" #define CPU_FW_EJECT_EVENT "CEJF" +#define CPU_PRESENT "CPRS" void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, build_madt_cpu_fn build_madt_cpu, hwaddr base_addr, @@ -396,7 +423,9 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, aml_append(field, aml_named_field(CPU_EJECT_EVENT, 1)); /* tell firmware to do device eject, write only */ aml_append(field, aml_named_field(CPU_FW_EJECT_EVENT, 1)); - aml_append(field, aml_reserved_field(3)); + /* 1 if present, read only */ + aml_append(field, aml_named_field(CPU_PRESENT, 1)); + aml_append(field, aml_reserved_field(2)); aml_append(field, aml_named_field(CPU_COMMAND, 8)); aml_append(cpu_ctrl_dev, field); @@ -426,6 +455,7 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, Aml *ctrl_lock = aml_name("%s.%s", cphp_res_path, CPU_LOCK); Aml *cpu_selector = aml_name("%s.%s", cphp_res_path, CPU_SELECTOR); Aml *is_enabled = aml_name("%s.%s", cphp_res_path, CPU_ENABLED); + Aml *is_present = aml_name("%s.%s", cphp_res_path, CPU_PRESENT); Aml *cpu_cmd = aml_name("%s.%s", cphp_res_path, CPU_COMMAND); Aml *cpu_data = aml_name("%s.%s", cphp_res_path, CPU_DATA); Aml *ins_evt = aml_name("%s.%s", cphp_res_path, CPU_INSERT_EVENT); @@ -454,13 +484,26 @@ void build_cpus_aml(Aml *table, MachineState *machine, CPUHotplugFeatures opts, { Aml *idx = aml_arg(0); Aml *sta = aml_local(0); + Aml *ifctx2; + Aml *else_ctx; aml_append(method, aml_acquire(ctrl_lock, 0xFFFF)); aml_append(method, aml_store(idx, cpu_selector)); aml_append(method, aml_store(zero, sta)); - ifctx = aml_if(aml_equal(is_enabled, one)); + ifctx = aml_if(aml_equal(is_present, one)); { - aml_append(ifctx, aml_store(aml_int(0xF), sta)); + ifctx2 = aml_if(aml_equal(is_enabled, one)); + { + /* cpu is present and enabled */ + aml_append(ifctx2, aml_store(aml_int(0xF), sta)); + } + aml_append(ifctx, ifctx2); + else_ctx = aml_else(); + { + /* cpu is present but disabled */ + aml_append(else_ctx, aml_store(aml_int(0xD), sta)); + } + aml_append(ifctx, else_ctx); } aml_append(method, ifctx); aml_append(method, aml_release(ctrl_lock)); diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c index d00f5a6c1c..663d9cb093 100644 --- a/hw/acpi/generic_event_device.c +++ b/hw/acpi/generic_event_device.c @@ -331,6 +331,24 @@ static const VMStateDescription vmstate_memhp_state = { } }; +static bool cpuhp_needed(void *opaque) +{ + MachineClass *mc = MACHINE_GET_CLASS(qdev_get_machine()); + + return mc->has_hotpluggable_cpus; +} + +static const VMStateDescription vmstate_cpuhp_state = { + .name = "acpi-ged/cpuhp", + .version_id = 1, + .minimum_version_id = 1, + .needed = cpuhp_needed, + .fields = (VMStateField[]) { + VMSTATE_CPU_HOTPLUG(cpuhp_state, AcpiGedState), + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_ged_state = { .name = "acpi-ged-state", .version_id = 1, @@ -379,6 +397,7 @@ static const VMStateDescription vmstate_acpi_ged = { }, .subsections = (const VMStateDescription * const []) { &vmstate_memhp_state, + &vmstate_cpuhp_state, &vmstate_ghes_state, NULL } diff --git a/hw/acpi/meson.build b/hw/acpi/meson.build index 7f8ccc9b7a..c8854f4d48 100644 --- a/hw/acpi/meson.build +++ b/hw/acpi/meson.build @@ -1,6 +1,5 @@ acpi_ss = ss.source_set() acpi_ss.add(files( - 'acpi_generic_initiator.c', 'acpi_interface.c', 'aml-build.c', 'bios-linker-loader.c', diff --git a/hw/acpi/pci.c b/hw/acpi/pci.c index 20b70dcd81..f88f450af3 100644 --- a/hw/acpi/pci.c +++ b/hw/acpi/pci.c @@ -24,8 +24,14 @@ */ #include "qemu/osdep.h" +#include "qemu/error-report.h" +#include "qom/object_interfaces.h" +#include "qapi/error.h" +#include "hw/boards.h" #include "hw/acpi/aml-build.h" #include "hw/acpi/pci.h" +#include "hw/pci/pci_bridge.h" +#include "hw/pci/pci_device.h" #include "hw/pci/pcie_host.h" /* @@ -59,3 +65,239 @@ void build_mcfg(GArray *table_data, BIOSLinker *linker, AcpiMcfgInfo *info, acpi_table_end(linker, &table); } + +typedef struct AcpiGenericInitiator { + /* private */ + Object parent; + + /* public */ + char *pci_dev; + uint32_t node; +} AcpiGenericInitiator; + +typedef struct AcpiGenericInitiatorClass { + ObjectClass parent_class; +} AcpiGenericInitiatorClass; + +#define TYPE_ACPI_GENERIC_INITIATOR "acpi-generic-initiator" + +OBJECT_DEFINE_TYPE_WITH_INTERFACES(AcpiGenericInitiator, acpi_generic_initiator, + ACPI_GENERIC_INITIATOR, OBJECT, + { TYPE_USER_CREATABLE }, + { NULL }) + +OBJECT_DECLARE_SIMPLE_TYPE(AcpiGenericInitiator, ACPI_GENERIC_INITIATOR) + +static void acpi_generic_initiator_init(Object *obj) +{ + AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj); + + gi->node = MAX_NODES; + gi->pci_dev = NULL; +} + +static void acpi_generic_initiator_finalize(Object *obj) +{ + AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj); + + g_free(gi->pci_dev); +} + +static void acpi_generic_initiator_set_pci_device(Object *obj, const char *val, + Error **errp) +{ + AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj); + + gi->pci_dev = g_strdup(val); +} + +static void acpi_generic_initiator_set_node(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + AcpiGenericInitiator *gi = ACPI_GENERIC_INITIATOR(obj); + MachineState *ms = MACHINE(qdev_get_machine()); + uint32_t value; + + if (!visit_type_uint32(v, name, &value, errp)) { + return; + } + + if (value >= MAX_NODES) { + error_printf("%s: Invalid NUMA node specified\n", + TYPE_ACPI_GENERIC_INITIATOR); + exit(1); + } + + gi->node = value; + ms->numa_state->nodes[gi->node].has_gi = true; +} + +static void acpi_generic_initiator_class_init(ObjectClass *oc, void *data) +{ + object_class_property_add_str(oc, "pci-dev", NULL, + acpi_generic_initiator_set_pci_device); + object_class_property_set_description(oc, "pci-dev", + "PCI device to associate with the node"); + object_class_property_add(oc, "node", "int", NULL, + acpi_generic_initiator_set_node, NULL, NULL); + object_class_property_set_description(oc, "node", + "NUMA node associated with the PCI device"); +} + +static int build_acpi_generic_initiator(Object *obj, void *opaque) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + AcpiGenericInitiator *gi; + GArray *table_data = opaque; + int32_t devfn; + uint8_t bus; + Object *o; + + if (!object_dynamic_cast(obj, TYPE_ACPI_GENERIC_INITIATOR)) { + return 0; + } + + gi = ACPI_GENERIC_INITIATOR(obj); + if (gi->node >= ms->numa_state->num_nodes) { + error_printf("%s: Specified node %d is invalid.\n", + TYPE_ACPI_GENERIC_INITIATOR, gi->node); + exit(1); + } + + o = object_resolve_path_type(gi->pci_dev, TYPE_PCI_DEVICE, NULL); + if (!o) { + error_printf("%s: Specified device must be a PCI device.\n", + TYPE_ACPI_GENERIC_INITIATOR); + exit(1); + } + + bus = object_property_get_uint(o, "busnr", &error_fatal); + devfn = object_property_get_uint(o, "addr", &error_fatal); + /* devfn is constrained in PCI to be 8 bit but storage is an int32_t */ + assert(devfn >= 0 && devfn < PCI_DEVFN_MAX); + + build_srat_pci_generic_initiator(table_data, gi->node, 0, bus, devfn); + + return 0; +} + +typedef struct AcpiGenericPort { + /* private */ + Object parent; + + /* public */ + char *pci_bus; + uint32_t node; +} AcpiGenericPort; + +typedef struct AcpiGenericPortClass { + ObjectClass parent_class; +} AcpiGenericPortClass; + +#define TYPE_ACPI_GENERIC_PORT "acpi-generic-port" + +OBJECT_DEFINE_TYPE_WITH_INTERFACES(AcpiGenericPort, acpi_generic_port, + ACPI_GENERIC_PORT, OBJECT, + { TYPE_USER_CREATABLE }, + { NULL }) + +OBJECT_DECLARE_SIMPLE_TYPE(AcpiGenericPort, ACPI_GENERIC_PORT) + +static void acpi_generic_port_init(Object *obj) +{ + AcpiGenericPort *gp = ACPI_GENERIC_PORT(obj); + + gp->node = MAX_NODES; + gp->pci_bus = NULL; +} + +static void acpi_generic_port_finalize(Object *obj) +{ + AcpiGenericPort *gp = ACPI_GENERIC_PORT(obj); + + g_free(gp->pci_bus); +} + +static void acpi_generic_port_set_pci_bus(Object *obj, const char *val, + Error **errp) +{ + AcpiGenericPort *gp = ACPI_GENERIC_PORT(obj); + + gp->pci_bus = g_strdup(val); +} + +static void acpi_generic_port_set_node(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + AcpiGenericPort *gp = ACPI_GENERIC_PORT(obj); + uint32_t value; + + if (!visit_type_uint32(v, name, &value, errp)) { + return; + } + + if (value >= MAX_NODES) { + error_printf("%s: Invalid NUMA node specified\n", + TYPE_ACPI_GENERIC_INITIATOR); + exit(1); + } + + gp->node = value; +} + +static void acpi_generic_port_class_init(ObjectClass *oc, void *data) +{ + object_class_property_add_str(oc, "pci-bus", NULL, + acpi_generic_port_set_pci_bus); + object_class_property_set_description(oc, "pci-bus", + "PCI Bus of the host bridge associated with this GP affinity structure"); + object_class_property_add(oc, "node", "int", NULL, + acpi_generic_port_set_node, NULL, NULL); + object_class_property_set_description(oc, "node", + "The NUMA node like ID to index HMAT/SLIT NUMA properties involving GP"); +} + +static int build_acpi_generic_port(Object *obj, void *opaque) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + const char *hid = "ACPI0016"; + GArray *table_data = opaque; + AcpiGenericPort *gp; + uint32_t uid; + Object *o; + + if (!object_dynamic_cast(obj, TYPE_ACPI_GENERIC_PORT)) { + return 0; + } + + gp = ACPI_GENERIC_PORT(obj); + + if (gp->node >= ms->numa_state->num_nodes) { + error_printf("%s: node %d is invalid.\n", + TYPE_ACPI_GENERIC_PORT, gp->node); + exit(1); + } + + o = object_resolve_path_type(gp->pci_bus, TYPE_PXB_CXL_BUS, NULL); + if (!o) { + error_printf("%s: device must be a CXL host bridge.\n", + TYPE_ACPI_GENERIC_PORT); + exit(1); + } + + uid = object_property_get_uint(o, "acpi_uid", &error_fatal); + build_srat_acpi_generic_port(table_data, gp->node, hid, uid); + + return 0; +} + +void build_srat_generic_affinity_structures(GArray *table_data) +{ + object_child_foreach_recursive(object_get_root(), + build_acpi_generic_initiator, + table_data); + object_child_foreach_recursive(object_get_root(), build_acpi_generic_port, + table_data); +} diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index e7fd9338d1..1b25e73578 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -539,6 +539,7 @@ config ASPEED_SOC select PMBUS select MAX31785 select FSI_APB2OPB_ASPEED + select AT24C config MPS2 bool diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index b4b1ce9efb..6ca145362c 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -338,10 +338,20 @@ static void sdhci_attach_drive(SDHCIState *sdhci, DriveInfo *dinfo, bool emmc, return; } card = qdev_new(emmc ? TYPE_EMMC : TYPE_SD_CARD); - if (emmc) { + + /* + * Force the boot properties of the eMMC device only when the + * machine is strapped to boot from eMMC. Without these + * settings, the machine would not boot. + * + * This also allows the machine to use an eMMC device without + * boot areas when booting from the flash device (or -kernel) + * Ideally, the device and its properties should be defined on + * the command line. + */ + if (emmc && boot_emmc) { qdev_prop_set_uint64(card, "boot-partition-size", 1 * MiB); - qdev_prop_set_uint8(card, "boot-config", - boot_emmc ? 0x1 << 3 : 0x0); + qdev_prop_set_uint8(card, "boot-config", 0x1 << 3); } qdev_prop_set_drive_err(card, "drive", blk_by_legacy_dinfo(dinfo), &error_fatal); @@ -1594,18 +1604,20 @@ static void aspeed_minibmc_machine_init(MachineState *machine) connect_serial_hds_to_uarts(bmc); qdev_realize(DEVICE(bmc->soc), NULL, &error_abort); - aspeed_board_init_flashes(&bmc->soc->fmc, - bmc->fmc_model ? bmc->fmc_model : amc->fmc_model, - amc->num_cs, - 0); + if (defaults_enabled()) { + aspeed_board_init_flashes(&bmc->soc->fmc, + bmc->fmc_model ? bmc->fmc_model : amc->fmc_model, + amc->num_cs, + 0); - aspeed_board_init_flashes(&bmc->soc->spi[0], - bmc->spi_model ? bmc->spi_model : amc->spi_model, - amc->num_cs, amc->num_cs); + aspeed_board_init_flashes(&bmc->soc->spi[0], + bmc->spi_model ? bmc->spi_model : amc->spi_model, + amc->num_cs, amc->num_cs); - aspeed_board_init_flashes(&bmc->soc->spi[1], - bmc->spi_model ? bmc->spi_model : amc->spi_model, - amc->num_cs, (amc->num_cs * 2)); + aspeed_board_init_flashes(&bmc->soc->spi[1], + bmc->spi_model ? bmc->spi_model : amc->spi_model, + amc->num_cs, (amc->num_cs * 2)); + } if (amc->i2c_init) { amc->i2c_init(bmc); diff --git a/hw/arm/aspeed_ast27x0.c b/hw/arm/aspeed_ast27x0.c index dca660eb6b..63d1fcb086 100644 --- a/hw/arm/aspeed_ast27x0.c +++ b/hw/arm/aspeed_ast27x0.c @@ -13,6 +13,7 @@ #include "qapi/error.h" #include "hw/misc/unimp.h" #include "hw/arm/aspeed_soc.h" +#include "hw/arm/bsa.h" #include "qemu/module.h" #include "qemu/error-report.h" #include "hw/i2c/aspeed_i2c.h" @@ -63,9 +64,10 @@ static const hwaddr aspeed_soc_ast2700_memmap[] = { [ASPEED_DEV_ADC] = 0x14C00000, [ASPEED_DEV_I2C] = 0x14C0F000, [ASPEED_DEV_GPIO] = 0x14C0B000, + [ASPEED_DEV_RTC] = 0x12C0F000, }; -#define AST2700_MAX_IRQ 288 +#define AST2700_MAX_IRQ 256 /* Shared Peripheral Interrupt values below are offset by -32 from datasheet */ static const int aspeed_soc_ast2700_irqmap[] = { @@ -376,6 +378,8 @@ static void aspeed_soc_ast2700_init(Object *obj) snprintf(typename, sizeof(typename), "aspeed.gpio-%s", socname); object_initialize_child(obj, "gpio", &s->gpio, typename); + + object_initialize_child(obj, "rtc", &s->rtc, TYPE_ASPEED_RTC); } /* @@ -402,7 +406,7 @@ static bool aspeed_soc_ast2700_gic_realize(DeviceState *dev, Error **errp) gicdev = DEVICE(&a->gic); qdev_prop_set_uint32(gicdev, "revision", 3); qdev_prop_set_uint32(gicdev, "num-cpu", sc->num_cpus); - qdev_prop_set_uint32(gicdev, "num-irq", AST2700_MAX_IRQ); + qdev_prop_set_uint32(gicdev, "num-irq", AST2700_MAX_IRQ + GIC_INTERNAL); redist_region_count = qlist_new(); qlist_append_int(redist_region_count, sc->num_cpus); @@ -416,28 +420,27 @@ static bool aspeed_soc_ast2700_gic_realize(DeviceState *dev, Error **errp) for (i = 0; i < sc->num_cpus; i++) { DeviceState *cpudev = DEVICE(&a->cpu[i]); - int NUM_IRQS = 256, ARCH_GIC_MAINT_IRQ = 9, VIRTUAL_PMU_IRQ = 7; - int ppibase = NUM_IRQS + i * GIC_INTERNAL + GIC_NR_SGIS; + int intidbase = AST2700_MAX_IRQ + i * GIC_INTERNAL; const int timer_irq[] = { - [GTIMER_PHYS] = 14, - [GTIMER_VIRT] = 11, - [GTIMER_HYP] = 10, - [GTIMER_SEC] = 13, + [GTIMER_PHYS] = ARCH_TIMER_NS_EL1_IRQ, + [GTIMER_VIRT] = ARCH_TIMER_VIRT_IRQ, + [GTIMER_HYP] = ARCH_TIMER_NS_EL2_IRQ, + [GTIMER_SEC] = ARCH_TIMER_S_EL1_IRQ, }; int j; for (j = 0; j < ARRAY_SIZE(timer_irq); j++) { qdev_connect_gpio_out(cpudev, j, - qdev_get_gpio_in(gicdev, ppibase + timer_irq[j])); + qdev_get_gpio_in(gicdev, intidbase + timer_irq[j])); } qemu_irq irq = qdev_get_gpio_in(gicdev, - ppibase + ARCH_GIC_MAINT_IRQ); + intidbase + ARCH_GIC_MAINT_IRQ); qdev_connect_gpio_out_named(cpudev, "gicv3-maintenance-interrupt", 0, irq); qdev_connect_gpio_out_named(cpudev, "pmu-interrupt", 0, - qdev_get_gpio_in(gicdev, ppibase + VIRTUAL_PMU_IRQ)); + qdev_get_gpio_in(gicdev, intidbase + VIRTUAL_PMU_IRQ)); sysbus_connect_irq(gicbusdev, i, qdev_get_gpio_in(cpudev, ARM_CPU_IRQ)); sysbus_connect_irq(gicbusdev, i + sc->num_cpus, @@ -670,6 +673,14 @@ static void aspeed_soc_ast2700_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio), 0, aspeed_soc_get_irq(s, ASPEED_DEV_GPIO)); + /* RTC */ + if (!sysbus_realize(SYS_BUS_DEVICE(&s->rtc), errp)) { + return; + } + aspeed_mmio_map(s, SYS_BUS_DEVICE(&s->rtc), 0, sc->memmap[ASPEED_DEV_RTC]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->rtc), 0, + aspeed_soc_get_irq(s, ASPEED_DEV_RTC)); + create_unimplemented_device("ast2700.dpmcu", 0x11000000, 0x40000); create_unimplemented_device("ast2700.iomem0", 0x12000000, 0x01000000); create_unimplemented_device("ast2700.iomem1", 0x14000000, 0x01000000); diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index f76fb117ad..620992c92c 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -57,7 +57,6 @@ #include "migration/vmstate.h" #include "hw/acpi/ghes.h" #include "hw/acpi/viot.h" -#include "hw/acpi/acpi_generic_initiator.h" #include "hw/virtio/virtio-acpi.h" #include "target/arm/multiprocessing.h" @@ -511,7 +510,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) } } - build_srat_generic_pci_initiator(table_data); + build_srat_generic_affinity_structures(table_data); if (ms->nvdimms_state->is_enabled) { nvdimm_build_srat(table_data); diff --git a/hw/block/vhost-user-blk.c b/hw/block/vhost-user-blk.c index 5b7f46bbb0..7996e49821 100644 --- a/hw/block/vhost-user-blk.c +++ b/hw/block/vhost-user-blk.c @@ -90,27 +90,39 @@ static void vhost_user_blk_set_config(VirtIODevice *vdev, const uint8_t *config) s->blkcfg.wce = blkcfg->wce; } +static int vhost_user_blk_sync_config(DeviceState *dev, Error **errp) +{ + int ret; + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VHostUserBlk *s = VHOST_USER_BLK(vdev); + + ret = vhost_dev_get_config(&s->dev, (uint8_t *)&s->blkcfg, + vdev->config_len, errp); + if (ret < 0) { + return ret; + } + + memcpy(vdev->config, &s->blkcfg, vdev->config_len); + virtio_notify_config(vdev); + + return 0; +} + static int vhost_user_blk_handle_config_change(struct vhost_dev *dev) { int ret; - VirtIODevice *vdev = dev->vdev; - VHostUserBlk *s = VHOST_USER_BLK(dev->vdev); Error *local_err = NULL; if (!dev->started) { return 0; } - ret = vhost_dev_get_config(dev, (uint8_t *)&s->blkcfg, - vdev->config_len, &local_err); + ret = vhost_user_blk_sync_config(DEVICE(dev->vdev), &local_err); if (ret < 0) { error_report_err(local_err); return ret; } - memcpy(dev->vdev->config, &s->blkcfg, vdev->config_len); - virtio_notify_config(dev->vdev); - return 0; } @@ -579,6 +591,7 @@ static void vhost_user_blk_class_init(ObjectClass *klass, void *data) device_class_set_props(dc, vhost_user_blk_properties); dc->vmsd = &vmstate_vhost_user_blk; + dc->sync_config = vhost_user_blk_sync_config; set_bit(DEVICE_CATEGORY_STORAGE, dc->categories); vdc->realize = vhost_user_blk_device_realize; vdc->unrealize = vhost_user_blk_device_unrealize; diff --git a/hw/core/machine.c b/hw/core/machine.c index 222799bc46..c1893fe255 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -34,7 +34,9 @@ #include "hw/virtio/virtio-iommu.h" #include "audio/audio.h" -GlobalProperty hw_compat_9_1[] = {}; +GlobalProperty hw_compat_9_1[] = { + { TYPE_PCI_DEVICE, "x-pcie-ext-tag", "false" }, +}; const size_t hw_compat_9_1_len = G_N_ELEMENTS(hw_compat_9_1); GlobalProperty hw_compat_9_0[] = { @@ -281,33 +283,6 @@ GlobalProperty hw_compat_2_4[] = { }; const size_t hw_compat_2_4_len = G_N_ELEMENTS(hw_compat_2_4); -GlobalProperty hw_compat_2_3[] = { - { "virtio-blk-pci", "any_layout", "off" }, - { "virtio-balloon-pci", "any_layout", "off" }, - { "virtio-serial-pci", "any_layout", "off" }, - { "virtio-9p-pci", "any_layout", "off" }, - { "virtio-rng-pci", "any_layout", "off" }, - { TYPE_PCI_DEVICE, "x-pcie-lnksta-dllla", "off" }, - { "migration", "send-configuration", "off" }, - { "migration", "send-section-footer", "off" }, - { "migration", "store-global-state", "off" }, -}; -const size_t hw_compat_2_3_len = G_N_ELEMENTS(hw_compat_2_3); - -GlobalProperty hw_compat_2_2[] = {}; -const size_t hw_compat_2_2_len = G_N_ELEMENTS(hw_compat_2_2); - -GlobalProperty hw_compat_2_1[] = { - { "intel-hda", "old_msi_addr", "on" }, - { "VGA", "qemu-extended-regs", "off" }, - { "secondary-vga", "qemu-extended-regs", "off" }, - { "virtio-scsi-pci", "any_layout", "off" }, - { "usb-mouse", "usb_version", "1" }, - { "usb-kbd", "usb_version", "1" }, - { "virtio-pci", "virtio-pci-bus-master-bug-migration", "on" }, -}; -const size_t hw_compat_2_1_len = G_N_ELEMENTS(hw_compat_2_1); - MachineState *current_machine; static char *machine_get_kernel(Object *obj, Error **errp) diff --git a/hw/cxl/cxl-mailbox-utils.c b/hw/cxl/cxl-mailbox-utils.c index 9258e48f95..2d4d62c454 100644 --- a/hw/cxl/cxl-mailbox-utils.c +++ b/hw/cxl/cxl-mailbox-utils.c @@ -151,6 +151,9 @@ static CXLRetCode cmd_tunnel_management_cmd(const struct cxl_cmd *cmd, in = (void *)payload_in; out = (void *)payload_out; + if (len_in < sizeof(*in)) { + return CXL_MBOX_INVALID_PAYLOAD_LENGTH; + } /* Enough room for minimum sized message - no payload */ if (in->size < sizeof(in->ccimessage)) { return CXL_MBOX_INVALID_PAYLOAD_LENGTH; @@ -266,6 +269,12 @@ static CXLRetCode cmd_events_clear_records(const struct cxl_cmd *cmd, CXLClearEventPayload *pl; pl = (CXLClearEventPayload *)payload_in; + + if (len_in < sizeof(*pl) || + len_in < sizeof(*pl) + sizeof(*pl->handle) * pl->nr_recs) { + return CXL_MBOX_INVALID_PAYLOAD_LENGTH; + } + *len_out = 0; return cxl_event_clear_records(cxlds, pl); } @@ -374,7 +383,7 @@ static CXLRetCode cmd_infostat_identify(const struct cxl_cmd *cmd, uint16_t pcie_subsys_vid; uint16_t pcie_subsys_id; uint64_t sn; - uint8_t max_message_size; + uint8_t max_message_size; uint8_t component_type; } QEMU_PACKED *is_identify; QEMU_BUILD_BUG_ON(sizeof(*is_identify) != 18); @@ -521,6 +530,9 @@ static CXLRetCode cmd_get_physical_port_state(const struct cxl_cmd *cmd, in = (struct cxl_fmapi_get_phys_port_state_req_pl *)payload_in; out = (struct cxl_fmapi_get_phys_port_state_resp_pl *)payload_out; + if (len_in < sizeof(*in)) { + return CXL_MBOX_INVALID_PAYLOAD_LENGTH; + } /* Check if what was requested can fit */ if (sizeof(*out) + sizeof(*out->ports) * in->num_ports > cci->payload_max) { return CXL_MBOX_INVALID_INPUT; @@ -649,9 +661,9 @@ static CXLRetCode cmd_firmware_update_get_info(const struct cxl_cmd *cmd, } QEMU_PACKED *fw_info; QEMU_BUILD_BUG_ON(sizeof(*fw_info) != 0x50); - if ((cxl_dstate->vmem_size < CXL_CAPACITY_MULTIPLIER) || - (cxl_dstate->pmem_size < CXL_CAPACITY_MULTIPLIER) || - (ct3d->dc.total_capacity < CXL_CAPACITY_MULTIPLIER)) { + if (!QEMU_IS_ALIGNED(cxl_dstate->vmem_size, CXL_CAPACITY_MULTIPLIER) || + !QEMU_IS_ALIGNED(cxl_dstate->pmem_size, CXL_CAPACITY_MULTIPLIER) || + !QEMU_IS_ALIGNED(ct3d->dc.total_capacity, CXL_CAPACITY_MULTIPLIER)) { return CXL_MBOX_INTERNAL_ERROR; } @@ -699,6 +711,10 @@ static CXLRetCode cmd_firmware_update_transfer(const struct cxl_cmd *cmd, } QEMU_PACKED *fw_transfer = (void *)payload_in; size_t offset, length; + if (len < sizeof(*fw_transfer)) { + return CXL_MBOX_INVALID_PAYLOAD_LENGTH; + } + if (fw_transfer->action == CXL_FW_XFER_ACTION_ABORT) { /* * At this point there aren't any on-going transfers @@ -927,24 +943,28 @@ static CXLRetCode cmd_logs_get_log(const struct cxl_cmd *cmd, get_log = (void *)payload_in; + if (get_log->length > cci->payload_max) { + return CXL_MBOX_INVALID_INPUT; + } + + if (!qemu_uuid_is_equal(&get_log->uuid, &cel_uuid)) { + return CXL_MBOX_INVALID_LOG; + } + /* * CXL r3.1 Section 8.2.9.5.2: Get Log (Opcode 0401h) * The device shall return Invalid Input if the Offset or Length * fields attempt to access beyond the size of the log as reported by Get - * Supported Logs. + * Supported Log. * - * The CEL buffer is large enough to fit all commands in the emulation, so - * the only possible failure would be if the mailbox itself isn't big - * enough. + * Only valid for there to be one entry per opcode, but the length + offset + * may still be greater than that if the inputs are not valid and so access + * beyond the end of cci->cel_log. */ - if (get_log->offset + get_log->length > cci->payload_max) { + if ((uint64_t)get_log->offset + get_log->length >= sizeof(cci->cel_log)) { return CXL_MBOX_INVALID_INPUT; } - if (!qemu_uuid_is_equal(&get_log->uuid, &cel_uuid)) { - return CXL_MBOX_INVALID_LOG; - } - /* Store off everything to local variables so we can wipe out the payload */ *len_out = get_log->length; @@ -1133,10 +1153,8 @@ static CXLRetCode cmd_features_get_supported(const struct cxl_cmd *cmd, (struct CXLSupportedFeatureEntry) { .uuid = ecs_uuid, .feat_index = index, - .get_feat_size = CXL_ECS_NUM_MEDIA_FRUS * - sizeof(CXLMemECSReadAttrs), - .set_feat_size = CXL_ECS_NUM_MEDIA_FRUS * - sizeof(CXLMemECSWriteAttrs), + .get_feat_size = sizeof(CXLMemECSReadAttrs), + .set_feat_size = sizeof(CXLMemECSWriteAttrs), .attr_flags = CXL_FEAT_ENTRY_ATTR_FLAG_CHANGABLE, .get_feat_version = CXL_ECS_GET_FEATURE_VERSION, .set_feat_version = CXL_ECS_SET_FEATURE_VERSION, @@ -1204,13 +1222,10 @@ static CXLRetCode cmd_features_get_feature(const struct cxl_cmd *cmd, (uint8_t *)&ct3d->patrol_scrub_attrs + get_feature->offset, bytes_to_copy); } else if (qemu_uuid_is_equal(&get_feature->uuid, &ecs_uuid)) { - if (get_feature->offset >= CXL_ECS_NUM_MEDIA_FRUS * - sizeof(CXLMemECSReadAttrs)) { + if (get_feature->offset >= sizeof(CXLMemECSReadAttrs)) { return CXL_MBOX_INVALID_INPUT; } - bytes_to_copy = CXL_ECS_NUM_MEDIA_FRUS * - sizeof(CXLMemECSReadAttrs) - - get_feature->offset; + bytes_to_copy = sizeof(CXLMemECSReadAttrs) - get_feature->offset; bytes_to_copy = MIN(bytes_to_copy, get_feature->count); memcpy(payload_out, (uint8_t *)&ct3d->ecs_attrs + get_feature->offset, @@ -1243,6 +1258,9 @@ static CXLRetCode cmd_features_set_feature(const struct cxl_cmd *cmd, CXLType3Dev *ct3d; uint16_t count; + if (len_in < sizeof(*hdr)) { + return CXL_MBOX_INVALID_PAYLOAD_LENGTH; + } if (!object_dynamic_cast(OBJECT(cci->d), TYPE_CXL_TYPE3)) { return CXL_MBOX_UNSUPPORTED; @@ -1277,6 +1295,11 @@ static CXLRetCode cmd_features_set_feature(const struct cxl_cmd *cmd, ps_set_feature = (void *)payload_in; ps_write_attrs = &ps_set_feature->feat_data; + + if ((uint32_t)hdr->offset + bytes_to_copy > + sizeof(ct3d->patrol_scrub_wr_attrs)) { + return CXL_MBOX_INVALID_PAYLOAD_LENGTH; + } memcpy((uint8_t *)&ct3d->patrol_scrub_wr_attrs + hdr->offset, ps_write_attrs, bytes_to_copy); @@ -1299,18 +1322,22 @@ static CXLRetCode cmd_features_set_feature(const struct cxl_cmd *cmd, ecs_set_feature = (void *)payload_in; ecs_write_attrs = ecs_set_feature->feat_data; - memcpy((uint8_t *)ct3d->ecs_wr_attrs + hdr->offset, + + if ((uint32_t)hdr->offset + bytes_to_copy > + sizeof(ct3d->ecs_wr_attrs)) { + return CXL_MBOX_INVALID_PAYLOAD_LENGTH; + } + memcpy((uint8_t *)&ct3d->ecs_wr_attrs + hdr->offset, ecs_write_attrs, bytes_to_copy); set_feat_info->data_size += bytes_to_copy; if (data_transfer_flag == CXL_SET_FEATURE_FLAG_FULL_DATA_TRANSFER || data_transfer_flag == CXL_SET_FEATURE_FLAG_FINISH_DATA_TRANSFER) { + ct3d->ecs_attrs.ecs_log_cap = ct3d->ecs_wr_attrs.ecs_log_cap; for (count = 0; count < CXL_ECS_NUM_MEDIA_FRUS; count++) { - ct3d->ecs_attrs[count].ecs_log_cap = - ct3d->ecs_wr_attrs[count].ecs_log_cap; - ct3d->ecs_attrs[count].ecs_config = - ct3d->ecs_wr_attrs[count].ecs_config & 0x1F; + ct3d->ecs_attrs.fru_attrs[count].ecs_config = + ct3d->ecs_wr_attrs.fru_attrs[count].ecs_config & 0x1F; } } } else { @@ -1324,7 +1351,7 @@ static CXLRetCode cmd_features_set_feature(const struct cxl_cmd *cmd, if (qemu_uuid_is_equal(&hdr->uuid, &patrol_scrub_uuid)) { memset(&ct3d->patrol_scrub_wr_attrs, 0, set_feat_info->data_size); } else if (qemu_uuid_is_equal(&hdr->uuid, &ecs_uuid)) { - memset(ct3d->ecs_wr_attrs, 0, set_feat_info->data_size); + memset(&ct3d->ecs_wr_attrs, 0, set_feat_info->data_size); } set_feat_info->data_transfer_flag = 0; set_feat_info->data_saved_across_reset = false; @@ -1445,7 +1472,7 @@ static CXLRetCode cmd_ccls_get_lsa(const struct cxl_cmd *cmd, } QEMU_PACKED *get_lsa; CXLType3Dev *ct3d = CXL_TYPE3(cci->d); CXLType3Class *cvc = CXL_TYPE3_GET_CLASS(ct3d); - uint32_t offset, length; + uint64_t offset, length; get_lsa = (void *)payload_in; offset = get_lsa->offset; @@ -1479,8 +1506,8 @@ static CXLRetCode cmd_ccls_set_lsa(const struct cxl_cmd *cmd, const size_t hdr_len = offsetof(struct set_lsa_pl, data); *len_out = 0; - if (!len_in) { - return CXL_MBOX_SUCCESS; + if (len_in < hdr_len) { + return CXL_MBOX_INVALID_PAYLOAD_LENGTH; } if (set_lsa_payload->offset + len_in > cvc->get_lsa_size(ct3d) + hdr_len) { @@ -2233,6 +2260,7 @@ static CXLRetCode cmd_dcd_get_dyn_cap_ext_list(const struct cxl_cmd *cmd, stw_le_p(&out_rec->shared_seq, ent->shared_seq); record_done++; + out_rec++; if (record_done == record_count) { break; } @@ -2470,11 +2498,20 @@ static CXLRetCode cmd_dcd_add_dyn_cap_rsp(const struct cxl_cmd *cmd, uint64_t dpa, len; CXLRetCode ret; + if (len_in < sizeof(*in)) { + return CXL_MBOX_INVALID_PAYLOAD_LENGTH; + } + if (in->num_entries_updated == 0) { cxl_extent_group_list_delete_front(&ct3d->dc.extents_pending); return CXL_MBOX_SUCCESS; } + if (len_in < + sizeof(*in) + sizeof(*in->updated_entries) * in->num_entries_updated) { + return CXL_MBOX_INVALID_PAYLOAD_LENGTH; + } + /* Adding extents causes exceeding device's extent tracking ability. */ if (in->num_entries_updated + ct3d->dc.total_extent_count > CXL_NUM_EXTENTS_SUPPORTED) { @@ -2629,10 +2666,19 @@ static CXLRetCode cmd_dcd_release_dyn_cap(const struct cxl_cmd *cmd, uint32_t updated_list_size; CXLRetCode ret; + if (len_in < sizeof(*in)) { + return CXL_MBOX_INVALID_PAYLOAD_LENGTH; + } + if (in->num_entries_updated == 0) { return CXL_MBOX_INVALID_INPUT; } + if (len_in < + sizeof(*in) + sizeof(*in->updated_entries) * in->num_entries_updated) { + return CXL_MBOX_INVALID_PAYLOAD_LENGTH; + } + ret = cxl_detect_malformed_extent_list(ct3d, in); if (ret != CXL_MBOX_SUCCESS) { return ret; @@ -2879,7 +2925,8 @@ static void bg_timercb(void *opaque) } } else { /* estimate only */ - cci->bg.complete_pct = 100 * now / total_time; + cci->bg.complete_pct = + 100 * (now - cci->bg.starttime) / cci->bg.runtime; timer_mod(cci->bg.timer, now + CXL_MBOX_BG_UPDATE_FREQ); } diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index 4967aa7459..9fcc2897b8 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -68,7 +68,6 @@ #include "hw/acpi/utils.h" #include "hw/acpi/pci.h" #include "hw/acpi/cxl.h" -#include "hw/acpi/acpi_generic_initiator.h" #include "qom/qom-qobject.h" #include "hw/i386/amd_iommu.h" @@ -741,7 +740,8 @@ static Aml *build_prt(bool is_pci0_prt) int pin; method = aml_method("_PRT", 0, AML_NOTSERIALIZED); - rt_pkg = aml_varpackage(nroutes); + assert(nroutes < 256); + rt_pkg = aml_package(nroutes); for (pin = 0; pin < nroutes; pin++) { Aml *pkg = aml_package(4); @@ -1476,6 +1476,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, QLIST_FOREACH(bus, &bus->child, sibling) { uint8_t bus_num = pci_bus_num(bus); uint8_t numa_node = pci_bus_numa_node(bus); + uint32_t uid; /* look only for expander root buses */ if (!pci_bus_is_root(bus)) { @@ -1486,6 +1487,8 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, root_bus_limit = bus_num - 1; } + uid = object_property_get_uint(OBJECT(bus), "acpi_uid", + &error_fatal); scope = aml_scope("\\_SB"); if (pci_bus_is_cxl(bus)) { @@ -1493,7 +1496,7 @@ build_dsdt(GArray *table_data, BIOSLinker *linker, } else { dev = aml_device("PC%.02X", bus_num); } - aml_append(dev, aml_name_decl("_UID", aml_int(bus_num))); + aml_append(dev, aml_name_decl("_UID", aml_int(uid))); aml_append(dev, aml_name_decl("_BBN", aml_int(bus_num))); if (pci_bus_is_cxl(bus)) { struct Aml *aml_pkg = aml_package(2); @@ -1971,7 +1974,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) build_srat_memory(table_data, 0, 0, 0, MEM_AFFINITY_NOFLAGS); } - build_srat_generic_pci_initiator(table_data); + build_srat_generic_affinity_structures(table_data); /* * Entry is required for Windows to enable memory hotplug in OS @@ -2321,7 +2324,7 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker, const char *oem_id, /* Capability offset */ build_append_int_noprefix(table_data, s->pci.capab_offset, 2); /* IOMMU base address */ - build_append_int_noprefix(table_data, s->mmio.addr, 8); + build_append_int_noprefix(table_data, s->mr_mmio.addr, 8); /* PCI Segment Group */ build_append_int_noprefix(table_data, 0, 2); /* IOMMU info */ @@ -2356,7 +2359,7 @@ build_amd_iommu(GArray *table_data, BIOSLinker *linker, const char *oem_id, /* Capability offset */ build_append_int_noprefix(table_data, s->pci.capab_offset, 2); /* IOMMU base address */ - build_append_int_noprefix(table_data, s->mmio.addr, 8); + build_append_int_noprefix(table_data, s->mr_mmio.addr, 8); /* PCI Segment Group */ build_append_int_noprefix(table_data, 0, 2); /* IOMMU info */ diff --git a/hw/i386/amd_iommu.c b/hw/i386/amd_iommu.c index 464f0b666e..13af7211e1 100644 --- a/hw/i386/amd_iommu.c +++ b/hw/i386/amd_iommu.c @@ -32,6 +32,7 @@ #include "trace.h" #include "hw/i386/apic-msidef.h" #include "hw/qdev-properties.h" +#include "kvm/kvm_i386.h" /* used AMD-Vi MMIO registers */ const char *amdvi_mmio_low[] = { @@ -60,8 +61,9 @@ struct AMDVIAddressSpace { uint8_t bus_num; /* bus number */ uint8_t devfn; /* device function */ AMDVIState *iommu_state; /* AMDVI - one per machine */ - MemoryRegion root; /* AMDVI Root memory map region */ + MemoryRegion root; /* AMDVI Root memory map region */ IOMMUMemoryRegion iommu; /* Device's address translation region */ + MemoryRegion iommu_nodma; /* Alias of shared nodma memory region */ MemoryRegion iommu_ir; /* Device's interrupt remapping region */ AddressSpace as; /* device's corresponding address space */ }; @@ -430,6 +432,12 @@ static void amdvi_complete_ppr(AMDVIState *s, uint64_t *cmd) trace_amdvi_ppr_exec(); } +static void amdvi_intremap_inval_notify_all(AMDVIState *s, bool global, + uint32_t index, uint32_t mask) +{ + x86_iommu_iec_notify_all(X86_IOMMU_DEVICE(s), global, index, mask); +} + static void amdvi_inval_all(AMDVIState *s, uint64_t *cmd) { if (extract64(cmd[0], 0, 60) || cmd[1]) { @@ -437,6 +445,9 @@ static void amdvi_inval_all(AMDVIState *s, uint64_t *cmd) s->cmdbuf + s->cmdbuf_head); } + /* Notify global invalidation */ + amdvi_intremap_inval_notify_all(s, true, 0, 0); + amdvi_iotlb_reset(s); trace_amdvi_all_inval(); } @@ -485,6 +496,9 @@ static void amdvi_inval_inttable(AMDVIState *s, uint64_t *cmd) return; } + /* Notify global invalidation */ + amdvi_intremap_inval_notify_all(s, true, 0, 0); + trace_amdvi_intr_inval(); } @@ -1412,6 +1426,7 @@ 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]; @@ -1436,13 +1451,13 @@ static AddressSpace *amdvi_host_dma_iommu(PCIBus *bus, void *opaque, int devfn) * Memory region relationships looks like (Address range shows * only lower 32 bits to make it short in length...): * - * |-----------------+-------------------+----------| - * | Name | Address range | Priority | - * |-----------------+-------------------+----------+ - * | amdvi_root | 00000000-ffffffff | 0 | - * | amdvi_iommu | 00000000-ffffffff | 1 | - * | amdvi_iommu_ir | fee00000-feefffff | 64 | - * |-----------------+-------------------+----------| + * |--------------------+-------------------+----------| + * | Name | Address range | Priority | + * |--------------------+-------------------+----------+ + * | amdvi-root | 00000000-ffffffff | 0 | + * | amdvi-iommu_nodma | 00000000-ffffffff | 0 | + * | amdvi-iommu_ir | fee00000-feefffff | 1 | + * |--------------------+-------------------+----------| */ memory_region_init_iommu(&amdvi_dev_as->iommu, sizeof(amdvi_dev_as->iommu), @@ -1452,16 +1467,34 @@ static AddressSpace *amdvi_host_dma_iommu(PCIBus *bus, void *opaque, int devfn) memory_region_init(&amdvi_dev_as->root, OBJECT(s), "amdvi_root", UINT64_MAX); address_space_init(&amdvi_dev_as->as, &amdvi_dev_as->root, name); - memory_region_init_io(&amdvi_dev_as->iommu_ir, OBJECT(s), - &amdvi_ir_ops, s, "amd_iommu_ir", - AMDVI_INT_ADDR_SIZE); - memory_region_add_subregion_overlap(&amdvi_dev_as->root, - AMDVI_INT_ADDR_FIRST, - &amdvi_dev_as->iommu_ir, - 64); memory_region_add_subregion_overlap(&amdvi_dev_as->root, 0, MEMORY_REGION(&amdvi_dev_as->iommu), - 1); + 0); + + /* Build the DMA Disabled alias to shared memory */ + memory_region_init_alias(&amdvi_dev_as->iommu_nodma, OBJECT(s), + "amdvi-sys", &s->mr_sys, 0, + memory_region_size(&s->mr_sys)); + memory_region_add_subregion_overlap(&amdvi_dev_as->root, 0, + &amdvi_dev_as->iommu_nodma, + 0); + /* Build the Interrupt Remapping alias to shared memory */ + memory_region_init_alias(&amdvi_dev_as->iommu_ir, OBJECT(s), + "amdvi-ir", &s->mr_ir, 0, + memory_region_size(&s->mr_ir)); + memory_region_add_subregion_overlap(MEMORY_REGION(&amdvi_dev_as->iommu), + 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); + } } return &iommu_as[devfn]->as; } @@ -1598,10 +1631,37 @@ static void amdvi_sysbus_realize(DeviceState *dev, Error **errp) x86ms->ioapic_as = amdvi_host_dma_iommu(bus, s, AMDVI_IOAPIC_SB_DEVID); /* set up MMIO */ - memory_region_init_io(&s->mmio, OBJECT(s), &mmio_mem_ops, s, "amdvi-mmio", - AMDVI_MMIO_SIZE); + memory_region_init_io(&s->mr_mmio, OBJECT(s), &mmio_mem_ops, s, + "amdvi-mmio", AMDVI_MMIO_SIZE); memory_region_add_subregion(get_system_memory(), AMDVI_BASE_ADDR, - &s->mmio); + &s->mr_mmio); + + /* Create the share memory regions by all devices */ + memory_region_init(&s->mr_sys, OBJECT(s), "amdvi-sys", UINT64_MAX); + + /* set up the DMA disabled memory region */ + memory_region_init_alias(&s->mr_nodma, OBJECT(s), + "amdvi-nodma", get_system_memory(), 0, + memory_region_size(get_system_memory())); + memory_region_add_subregion_overlap(&s->mr_sys, 0, + &s->mr_nodma, 0); + + /* set up the Interrupt Remapping memory region */ + memory_region_init_io(&s->mr_ir, OBJECT(s), &amdvi_ir_ops, + s, "amdvi-ir", AMDVI_INT_ADDR_SIZE); + memory_region_add_subregion_overlap(&s->mr_sys, AMDVI_INT_ADDR_FIRST, + &s->mr_ir, 1); + + /* AMD IOMMU with x2APIC mode requires xtsup=on */ + if (x86ms->apic_id_limit > 255 && !s->xtsup) { + error_report("AMD IOMMU with x2APIC confguration requires xtsup=on"); + exit(EXIT_FAILURE); + } + if (s->xtsup && kvm_irqchip_is_split() && !kvm_enable_x2apic()) { + error_report("AMD IOMMU xtsup=on requires support on the KVM side"); + exit(EXIT_FAILURE); + } + pci_setup_iommu(bus, &amdvi_iommu_ops, s); amdvi_init(s); } diff --git a/hw/i386/amd_iommu.h b/hw/i386/amd_iommu.h index 73619fe9ea..e0dac4d9a9 100644 --- a/hw/i386/amd_iommu.h +++ b/hw/i386/amd_iommu.h @@ -353,7 +353,10 @@ struct AMDVIState { uint32_t pprlog_head; /* ppr log head */ uint32_t pprlog_tail; /* ppr log tail */ - MemoryRegion mmio; /* MMIO region */ + MemoryRegion mr_mmio; /* MMIO region */ + MemoryRegion mr_sys; + MemoryRegion mr_nodma; + MemoryRegion mr_ir; uint8_t mmior[AMDVI_MMIO_SIZE]; /* read/write MMIO */ uint8_t w1cmask[AMDVI_MMIO_SIZE]; /* read/write 1 clear mask */ uint8_t romask[AMDVI_MMIO_SIZE]; /* MMIO read/only mask */ diff --git a/hw/i386/intel_iommu.c b/hw/i386/intel_iommu.c index 08fe218935..4c0d1d7d47 100644 --- a/hw/i386/intel_iommu.c +++ b/hw/i386/intel_iommu.c @@ -2532,15 +2532,51 @@ static bool vtd_get_inv_desc(IntelIOMMUState *s, return true; } +static bool vtd_inv_desc_reserved_check(IntelIOMMUState *s, + VTDInvDesc *inv_desc, + uint64_t mask[4], bool dw, + const char *func_name, + const char *desc_type) +{ + if (s->iq_dw) { + if (inv_desc->val[0] & mask[0] || inv_desc->val[1] & mask[1] || + inv_desc->val[2] & mask[2] || inv_desc->val[3] & mask[3]) { + error_report("%s: invalid %s desc val[3]: 0x%"PRIx64 + " val[2]: 0x%"PRIx64" val[1]=0x%"PRIx64 + " val[0]=0x%"PRIx64" (reserved nonzero)", + func_name, desc_type, inv_desc->val[3], + inv_desc->val[2], inv_desc->val[1], + inv_desc->val[0]); + return false; + } + } else { + if (dw) { + error_report("%s: 256-bit %s desc in 128-bit invalidation queue", + func_name, desc_type); + return false; + } + + if (inv_desc->lo & mask[0] || inv_desc->hi & mask[1]) { + error_report("%s: invalid %s desc: hi=%"PRIx64", lo=%"PRIx64 + " (reserved nonzero)", func_name, desc_type, + inv_desc->hi, inv_desc->lo); + return false; + } + } + + return true; +} + static bool vtd_process_wait_desc(IntelIOMMUState *s, VTDInvDesc *inv_desc) { - if ((inv_desc->hi & VTD_INV_DESC_WAIT_RSVD_HI) || - (inv_desc->lo & VTD_INV_DESC_WAIT_RSVD_LO)) { - error_report_once("%s: invalid wait desc: hi=%"PRIx64", lo=%"PRIx64 - " (reserved nonzero)", __func__, inv_desc->hi, - inv_desc->lo); + uint64_t mask[4] = {VTD_INV_DESC_WAIT_RSVD_LO, VTD_INV_DESC_WAIT_RSVD_HI, + VTD_INV_DESC_ALL_ONE, VTD_INV_DESC_ALL_ONE}; + + if (!vtd_inv_desc_reserved_check(s, inv_desc, mask, false, + __func__, "wait")) { return false; } + if (inv_desc->lo & VTD_INV_DESC_WAIT_SW) { /* Status Write */ uint32_t status_data = (uint32_t)(inv_desc->lo >> @@ -2574,13 +2610,14 @@ static bool vtd_process_context_cache_desc(IntelIOMMUState *s, VTDInvDesc *inv_desc) { uint16_t sid, fmask; + uint64_t mask[4] = {VTD_INV_DESC_CC_RSVD, VTD_INV_DESC_ALL_ONE, + VTD_INV_DESC_ALL_ONE, VTD_INV_DESC_ALL_ONE}; - if ((inv_desc->lo & VTD_INV_DESC_CC_RSVD) || inv_desc->hi) { - error_report_once("%s: invalid cc inv desc: hi=%"PRIx64", lo=%"PRIx64 - " (reserved nonzero)", __func__, inv_desc->hi, - inv_desc->lo); + if (!vtd_inv_desc_reserved_check(s, inv_desc, mask, false, + __func__, "cc inv")) { return false; } + switch (inv_desc->lo & VTD_INV_DESC_CC_G) { case VTD_INV_DESC_CC_DOMAIN: trace_vtd_inv_desc_cc_domain( @@ -2610,12 +2647,11 @@ static bool vtd_process_iotlb_desc(IntelIOMMUState *s, VTDInvDesc *inv_desc) uint16_t domain_id; uint8_t am; hwaddr addr; + uint64_t mask[4] = {VTD_INV_DESC_IOTLB_RSVD_LO, VTD_INV_DESC_IOTLB_RSVD_HI, + VTD_INV_DESC_ALL_ONE, VTD_INV_DESC_ALL_ONE}; - if ((inv_desc->lo & VTD_INV_DESC_IOTLB_RSVD_LO) || - (inv_desc->hi & VTD_INV_DESC_IOTLB_RSVD_HI)) { - error_report_once("%s: invalid iotlb inv desc: hi=0x%"PRIx64 - ", lo=0x%"PRIx64" (reserved bits unzero)", - __func__, inv_desc->hi, inv_desc->lo); + if (!vtd_inv_desc_reserved_check(s, inv_desc, mask, false, + __func__, "iotlb inv")) { return false; } @@ -2656,6 +2692,14 @@ static bool vtd_process_iotlb_desc(IntelIOMMUState *s, VTDInvDesc *inv_desc) static bool vtd_process_inv_iec_desc(IntelIOMMUState *s, VTDInvDesc *inv_desc) { + uint64_t mask[4] = {VTD_INV_DESC_IEC_RSVD, VTD_INV_DESC_ALL_ONE, + VTD_INV_DESC_ALL_ONE, VTD_INV_DESC_ALL_ONE}; + + if (!vtd_inv_desc_reserved_check(s, inv_desc, mask, false, + __func__, "iec inv")) { + return false; + } + trace_vtd_inv_desc_iec(inv_desc->iec.granularity, inv_desc->iec.index, inv_desc->iec.index_mask); @@ -2705,19 +2749,19 @@ static bool vtd_process_device_iotlb_desc(IntelIOMMUState *s, hwaddr addr; uint16_t sid; bool size; + uint64_t mask[4] = {VTD_INV_DESC_DEVICE_IOTLB_RSVD_LO, + VTD_INV_DESC_DEVICE_IOTLB_RSVD_HI, + VTD_INV_DESC_ALL_ONE, VTD_INV_DESC_ALL_ONE}; + + if (!vtd_inv_desc_reserved_check(s, inv_desc, mask, false, + __func__, "dev-iotlb inv")) { + return false; + } addr = VTD_INV_DESC_DEVICE_IOTLB_ADDR(inv_desc->hi); sid = VTD_INV_DESC_DEVICE_IOTLB_SID(inv_desc->lo); size = VTD_INV_DESC_DEVICE_IOTLB_SIZE(inv_desc->hi); - if ((inv_desc->lo & VTD_INV_DESC_DEVICE_IOTLB_RSVD_LO) || - (inv_desc->hi & VTD_INV_DESC_DEVICE_IOTLB_RSVD_HI)) { - error_report_once("%s: invalid dev-iotlb inv desc: hi=%"PRIx64 - ", lo=%"PRIx64" (reserved nonzero)", __func__, - inv_desc->hi, inv_desc->lo); - return false; - } - /* * Using sid is OK since the guest should have finished the * initialization of both the bus and device. @@ -2847,6 +2891,7 @@ static void vtd_handle_iqt_write(IntelIOMMUState *s) if (s->iq_dw && (val & VTD_IQT_QT_256_RSV_BIT)) { error_report_once("%s: RSV bit is set: val=0x%"PRIx64, __func__, val); + vtd_handle_inv_queue_error(s); return; } s->iq_tail = VTD_IQT_QT(s->iq_dw, val); @@ -3372,6 +3417,7 @@ static Property vtd_properties[] = { DEFINE_PROP_BOOL("x-pasid-mode", IntelIOMMUState, pasid, false), DEFINE_PROP_BOOL("dma-drain", IntelIOMMUState, dma_drain, true), DEFINE_PROP_BOOL("dma-translation", IntelIOMMUState, dma_translation, true), + DEFINE_PROP_BOOL("stale-tm", IntelIOMMUState, stale_tm, false), DEFINE_PROP_END_OF_LIST(), }; @@ -4138,15 +4184,15 @@ static void vtd_init(IntelIOMMUState *s) */ vtd_spte_rsvd[0] = ~0ULL; vtd_spte_rsvd[1] = VTD_SPTE_PAGE_L1_RSVD_MASK(s->aw_bits, - x86_iommu->dt_supported); + x86_iommu->dt_supported && s->stale_tm); vtd_spte_rsvd[2] = VTD_SPTE_PAGE_L2_RSVD_MASK(s->aw_bits); vtd_spte_rsvd[3] = VTD_SPTE_PAGE_L3_RSVD_MASK(s->aw_bits); vtd_spte_rsvd[4] = VTD_SPTE_PAGE_L4_RSVD_MASK(s->aw_bits); vtd_spte_rsvd_large[2] = VTD_SPTE_LPAGE_L2_RSVD_MASK(s->aw_bits, - x86_iommu->dt_supported); + x86_iommu->dt_supported && s->stale_tm); vtd_spte_rsvd_large[3] = VTD_SPTE_LPAGE_L3_RSVD_MASK(s->aw_bits, - x86_iommu->dt_supported); + x86_iommu->dt_supported && s->stale_tm); if (s->scalable_mode || s->snoop_control) { vtd_spte_rsvd[1] &= ~VTD_SPTE_SNP; diff --git a/hw/i386/intel_iommu_internal.h b/hw/i386/intel_iommu_internal.h index 13d5d129ae..4323fc5d6d 100644 --- a/hw/i386/intel_iommu_internal.h +++ b/hw/i386/intel_iommu_internal.h @@ -356,6 +356,7 @@ union VTDInvDesc { typedef union VTDInvDesc VTDInvDesc; /* Masks for struct VTDInvDesc */ +#define VTD_INV_DESC_ALL_ONE -1ULL #define VTD_INV_DESC_TYPE(val) ((((val) >> 5) & 0x70ULL) | \ ((val) & 0xfULL)) #define VTD_INV_DESC_CC 0x1 /* Context-cache Invalidate Desc */ @@ -409,11 +410,14 @@ typedef union VTDInvDesc VTDInvDesc; #define VTD_INV_DESC_DEVICE_IOTLB_RSVD_HI 0xffeULL #define VTD_INV_DESC_DEVICE_IOTLB_RSVD_LO 0xffff0000ffe0f1f0 +/* Masks for Interrupt Entry Invalidate Descriptor */ +#define VTD_INV_DESC_IEC_RSVD 0xffff000007fff1e0ULL + /* Rsvd field masks for spte */ #define VTD_SPTE_SNP 0x800ULL -#define VTD_SPTE_PAGE_L1_RSVD_MASK(aw, dt_supported) \ - dt_supported ? \ +#define VTD_SPTE_PAGE_L1_RSVD_MASK(aw, stale_tm) \ + stale_tm ? \ (0x800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM | VTD_SL_TM)) : \ (0x800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM)) #define VTD_SPTE_PAGE_L2_RSVD_MASK(aw) \ @@ -423,12 +427,12 @@ typedef union VTDInvDesc VTDInvDesc; #define VTD_SPTE_PAGE_L4_RSVD_MASK(aw) \ (0x880ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM)) -#define VTD_SPTE_LPAGE_L2_RSVD_MASK(aw, dt_supported) \ - dt_supported ? \ +#define VTD_SPTE_LPAGE_L2_RSVD_MASK(aw, stale_tm) \ + stale_tm ? \ (0x1ff800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM | VTD_SL_TM)) : \ (0x1ff800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM)) -#define VTD_SPTE_LPAGE_L3_RSVD_MASK(aw, dt_supported) \ - dt_supported ? \ +#define VTD_SPTE_LPAGE_L3_RSVD_MASK(aw, stale_tm) \ + stale_tm ? \ (0x3ffff800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM | VTD_SL_TM)) : \ (0x3ffff800ULL | ~(VTD_HAW_MASK(aw) | VTD_SL_IGN_COM)) diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 2047633e4c..830614d930 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -82,6 +82,7 @@ GlobalProperty pc_compat_9_1[] = { { "ICH9-LPC", "x-smi-swsmi-timer", "off" }, { "ICH9-LPC", "x-smi-periodic-timer", "off" }, + { TYPE_INTEL_IOMMU_DEVICE, "stale-tm", "on" }, }; const size_t pc_compat_9_1_len = G_N_ELEMENTS(pc_compat_9_1); diff --git a/hw/intc/pnv_xive2.c b/hw/intc/pnv_xive2.c index 78609105a8..834d32287b 100644 --- a/hw/intc/pnv_xive2.c +++ b/hw/intc/pnv_xive2.c @@ -490,6 +490,23 @@ static int pnv_xive2_write_nvp(Xive2Router *xrtr, uint8_t blk, uint32_t idx, word_number); } +static int pnv_xive2_get_nvgc(Xive2Router *xrtr, bool crowd, + uint8_t blk, uint32_t idx, + Xive2Nvgc *nvgc) +{ + return pnv_xive2_vst_read(PNV_XIVE2(xrtr), crowd ? VST_NVC : VST_NVG, + blk, idx, nvgc); +} + +static int pnv_xive2_write_nvgc(Xive2Router *xrtr, bool crowd, + uint8_t blk, uint32_t idx, + Xive2Nvgc *nvgc) +{ + return pnv_xive2_vst_write(PNV_XIVE2(xrtr), crowd ? VST_NVC : VST_NVG, + blk, idx, nvgc, + XIVE_VST_WORD_ALL); +} + static int pnv_xive2_nxc_to_table_type(uint8_t nxc_type, uint32_t *table_type) { switch (nxc_type) { @@ -2407,6 +2424,8 @@ static void pnv_xive2_class_init(ObjectClass *klass, void *data) xrc->write_end = pnv_xive2_write_end; xrc->get_nvp = pnv_xive2_get_nvp; xrc->write_nvp = pnv_xive2_write_nvp; + xrc->get_nvgc = pnv_xive2_get_nvgc; + xrc->write_nvgc = pnv_xive2_write_nvgc; xrc->get_config = pnv_xive2_get_config; xrc->get_block_id = pnv_xive2_get_block_id; @@ -2497,8 +2516,9 @@ void pnv_xive2_pic_print_info(PnvXive2 *xive, GString *buf) Xive2Eas eas; Xive2End end; Xive2Nvp nvp; + Xive2Nvgc nvgc; int i; - uint64_t xive_nvp_per_subpage; + uint64_t entries_per_subpage; g_string_append_printf(buf, "XIVE[%x] Source %08x .. %08x\n", blk, srcno0, srcno0 + nr_esbs - 1); @@ -2530,10 +2550,28 @@ void pnv_xive2_pic_print_info(PnvXive2 *xive, GString *buf) g_string_append_printf(buf, "XIVE[%x] #%d NVPT %08x .. %08x\n", chip_id, blk, 0, XIVE2_NVP_COUNT - 1); - xive_nvp_per_subpage = pnv_xive2_vst_per_subpage(xive, VST_NVP); - for (i = 0; i < XIVE2_NVP_COUNT; i += xive_nvp_per_subpage) { + entries_per_subpage = pnv_xive2_vst_per_subpage(xive, VST_NVP); + for (i = 0; i < XIVE2_NVP_COUNT; i += entries_per_subpage) { while (!xive2_router_get_nvp(xrtr, blk, i, &nvp)) { xive2_nvp_pic_print_info(&nvp, i++, buf); } } + + g_string_append_printf(buf, "XIVE[%x] #%d NVGT %08x .. %08x\n", + chip_id, blk, 0, XIVE2_NVP_COUNT - 1); + entries_per_subpage = pnv_xive2_vst_per_subpage(xive, VST_NVG); + for (i = 0; i < XIVE2_NVP_COUNT; i += entries_per_subpage) { + while (!xive2_router_get_nvgc(xrtr, false, blk, i, &nvgc)) { + xive2_nvgc_pic_print_info(&nvgc, i++, buf); + } + } + + g_string_append_printf(buf, "XIVE[%x] #%d NVCT %08x .. %08x\n", + chip_id, blk, 0, XIVE2_NVP_COUNT - 1); + entries_per_subpage = pnv_xive2_vst_per_subpage(xive, VST_NVC); + for (i = 0; i < XIVE2_NVP_COUNT; i += entries_per_subpage) { + while (!xive2_router_get_nvgc(xrtr, true, blk, i, &nvgc)) { + xive2_nvgc_pic_print_info(&nvgc, i++, buf); + } + } } diff --git a/hw/intc/spapr_xive_kvm.c b/hw/intc/spapr_xive_kvm.c index 5789062379..7a86197fc9 100644 --- a/hw/intc/spapr_xive_kvm.c +++ b/hw/intc/spapr_xive_kvm.c @@ -720,7 +720,7 @@ int kvmppc_xive_connect(SpaprInterruptController *intc, uint32_t nr_servers, { SpaprXive *xive = SPAPR_XIVE(intc); XiveSource *xsrc = &xive->source; - size_t esb_len = xive_source_esb_len(xsrc); + uint64_t esb_len = xive_source_esb_len(xsrc); size_t tima_len = 4ull << TM_SHIFT; CPUState *cs; int fd; @@ -824,7 +824,7 @@ void kvmppc_xive_disconnect(SpaprInterruptController *intc) { SpaprXive *xive = SPAPR_XIVE(intc); XiveSource *xsrc; - size_t esb_len; + uint64_t esb_len; assert(xive->fd != -1); diff --git a/hw/intc/xics.c b/hw/intc/xics.c index 6f4d5271ea..e893363dc9 100644 --- a/hw/intc/xics.c +++ b/hw/intc/xics.c @@ -335,22 +335,6 @@ static void icp_realize(DeviceState *dev, Error **errp) return; } } - /* - * The way that pre_2_10_icp is handling is really, really hacky. - * We used to have here this call: - * - * vmstate_register(NULL, icp->cs->cpu_index, &vmstate_icp_server, icp); - * - * But we were doing: - * pre_2_10_vmstate_register_dummy_icp() - * this vmstate_register() - * pre_2_10_vmstate_unregister_dummy_icp() - * - * So for a short amount of time we had to vmstate entries with - * the same name. This fixes it. - */ - vmstate_replace_hack_for_ppc(NULL, icp->cs->cpu_index, - &vmstate_icp_server, icp); } static void icp_unrealize(DeviceState *dev) diff --git a/hw/intc/xive.c b/hw/intc/xive.c index 5a02dd8e02..245e4d181a 100644 --- a/hw/intc/xive.c +++ b/hw/intc/xive.c @@ -74,33 +74,48 @@ static uint64_t xive_tctx_accept(XiveTCTX *tctx, uint8_t ring) if (regs[TM_NSR] & mask) { uint8_t cppr = regs[TM_PIPR]; + uint8_t alt_ring; + uint8_t *alt_regs; + + /* POOL interrupt uses IPB in QW2, POOL ring */ + if ((ring == TM_QW3_HV_PHYS) && (nsr & (TM_QW3_NSR_HE_POOL << 6))) { + alt_ring = TM_QW2_HV_POOL; + } else { + alt_ring = ring; + } + alt_regs = &tctx->regs[alt_ring]; regs[TM_CPPR] = cppr; /* Reset the pending buffer bit */ - regs[TM_IPB] &= ~xive_priority_to_ipb(cppr); - regs[TM_PIPR] = ipb_to_pipr(regs[TM_IPB]); + alt_regs[TM_IPB] &= ~xive_priority_to_ipb(cppr); /* Drop Exception bit */ regs[TM_NSR] &= ~mask; - trace_xive_tctx_accept(tctx->cs->cpu_index, ring, - regs[TM_IPB], regs[TM_PIPR], + trace_xive_tctx_accept(tctx->cs->cpu_index, alt_ring, + alt_regs[TM_IPB], regs[TM_PIPR], regs[TM_CPPR], regs[TM_NSR]); } - return (nsr << 8) | regs[TM_CPPR]; + return ((uint64_t)nsr << 8) | regs[TM_CPPR]; } static void xive_tctx_notify(XiveTCTX *tctx, uint8_t ring) { + /* HV_POOL ring uses HV_PHYS NSR, CPPR and PIPR registers */ + uint8_t alt_ring = (ring == TM_QW2_HV_POOL) ? TM_QW3_HV_PHYS : ring; + uint8_t *alt_regs = &tctx->regs[alt_ring]; uint8_t *regs = &tctx->regs[ring]; - if (regs[TM_PIPR] < regs[TM_CPPR]) { + if (alt_regs[TM_PIPR] < alt_regs[TM_CPPR]) { switch (ring) { case TM_QW1_OS: regs[TM_NSR] |= TM_QW1_NSR_EO; break; + case TM_QW2_HV_POOL: + alt_regs[TM_NSR] = (TM_QW3_NSR_HE_POOL << 6); + break; case TM_QW3_HV_PHYS: regs[TM_NSR] |= (TM_QW3_NSR_HE_PHYS << 6); break; @@ -108,26 +123,27 @@ static void xive_tctx_notify(XiveTCTX *tctx, uint8_t ring) g_assert_not_reached(); } trace_xive_tctx_notify(tctx->cs->cpu_index, ring, - regs[TM_IPB], regs[TM_PIPR], - regs[TM_CPPR], regs[TM_NSR]); + regs[TM_IPB], alt_regs[TM_PIPR], + alt_regs[TM_CPPR], alt_regs[TM_NSR]); qemu_irq_raise(xive_tctx_output(tctx, ring)); } } -void xive_tctx_reset_os_signal(XiveTCTX *tctx) +void xive_tctx_reset_signal(XiveTCTX *tctx, uint8_t ring) { /* - * Lower the External interrupt. Used when pulling an OS - * context. It is necessary to avoid catching it in the hypervisor - * context. It should be raised again when re-pushing the OS - * context. + * Lower the External interrupt. Used when pulling a context. It is + * necessary to avoid catching it in the higher privilege context. It + * should be raised again when re-pushing the lower privilege context. */ - qemu_irq_lower(xive_tctx_output(tctx, TM_QW1_OS)); + qemu_irq_lower(xive_tctx_output(tctx, ring)); } static void xive_tctx_set_cppr(XiveTCTX *tctx, uint8_t ring, uint8_t cppr) { uint8_t *regs = &tctx->regs[ring]; + uint8_t pipr_min; + uint8_t ring_min; trace_xive_tctx_set_cppr(tctx->cs->cpu_index, ring, regs[TM_IPB], regs[TM_PIPR], @@ -139,8 +155,37 @@ static void xive_tctx_set_cppr(XiveTCTX *tctx, uint8_t ring, uint8_t cppr) tctx->regs[ring + TM_CPPR] = cppr; + /* + * Recompute the PIPR based on local pending interrupts. The PHYS + * ring must take the minimum of both the PHYS and POOL PIPR values. + */ + pipr_min = ipb_to_pipr(regs[TM_IPB]); + ring_min = ring; + + /* PHYS updates also depend on POOL values */ + if (ring == TM_QW3_HV_PHYS) { + uint8_t *pool_regs = &tctx->regs[TM_QW2_HV_POOL]; + + /* POOL values only matter if POOL ctx is valid */ + if (pool_regs[TM_WORD2] & 0x80) { + + uint8_t pool_pipr = ipb_to_pipr(pool_regs[TM_IPB]); + + /* + * Determine highest priority interrupt and + * remember which ring has it. + */ + if (pool_pipr < pipr_min) { + pipr_min = pool_pipr; + ring_min = TM_QW2_HV_POOL; + } + } + } + + regs[TM_PIPR] = pipr_min; + /* CPPR has changed, check if we need to raise a pending exception */ - xive_tctx_notify(tctx, ring); + xive_tctx_notify(tctx, ring_min); } void xive_tctx_ipb_update(XiveTCTX *tctx, uint8_t ring, uint8_t ipb) @@ -179,6 +224,17 @@ static uint64_t xive_tm_pull_pool_ctx(XivePresenter *xptr, XiveTCTX *tctx, return qw2w2; } +static uint64_t xive_tm_pull_phys_ctx(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, unsigned size) +{ + uint8_t qw3b8_prev = tctx->regs[TM_QW3_HV_PHYS + TM_WORD2]; + uint8_t qw3b8; + + qw3b8 = qw3b8_prev & ~TM_QW3B8_VT; + tctx->regs[TM_QW3_HV_PHYS + TM_WORD2] = qw3b8; + return qw3b8; +} + static void xive_tm_vt_push(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset, uint64_t value, unsigned size) { @@ -207,14 +263,14 @@ static uint64_t xive_tm_vt_poll(XivePresenter *xptr, XiveTCTX *tctx, static const uint8_t xive_tm_hw_view[] = { 3, 0, 0, 0, 0, 0, 0, 0, 3, 3, 3, 3, 0, 0, 0, 0, /* QW-0 User */ 3, 3, 3, 3, 3, 3, 0, 2, 3, 3, 3, 3, 0, 0, 0, 0, /* QW-1 OS */ - 0, 0, 3, 3, 0, 0, 0, 0, 3, 3, 3, 3, 0, 0, 0, 0, /* QW-2 POOL */ + 0, 0, 3, 3, 0, 3, 3, 0, 3, 3, 3, 3, 0, 0, 0, 0, /* QW-2 POOL */ 3, 3, 3, 3, 0, 3, 0, 2, 3, 0, 0, 3, 3, 3, 3, 0, /* QW-3 PHYS */ }; static const uint8_t xive_tm_hv_view[] = { 3, 0, 0, 0, 0, 0, 0, 0, 3, 3, 3, 3, 0, 0, 0, 0, /* QW-0 User */ 3, 3, 3, 3, 3, 3, 0, 2, 3, 3, 3, 3, 0, 0, 0, 0, /* QW-1 OS */ - 0, 0, 3, 3, 0, 0, 0, 0, 0, 3, 3, 3, 0, 0, 0, 0, /* QW-2 POOL */ + 0, 0, 3, 3, 0, 3, 3, 0, 0, 3, 3, 3, 0, 0, 0, 0, /* QW-2 POOL */ 3, 3, 3, 3, 0, 3, 0, 2, 3, 0, 0, 3, 0, 0, 0, 0, /* QW-3 PHYS */ }; @@ -341,6 +397,19 @@ static void xive_tm_set_os_cppr(XivePresenter *xptr, XiveTCTX *tctx, xive_tctx_set_cppr(tctx, TM_QW1_OS, value & 0xff); } +static void xive_tctx_set_lgs(XiveTCTX *tctx, uint8_t ring, uint8_t lgs) +{ + uint8_t *regs = &tctx->regs[ring]; + + regs[TM_LGS] = lgs; +} + +static void xive_tm_set_os_lgs(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, uint64_t value, unsigned size) +{ + xive_tctx_set_lgs(tctx, TM_QW1_OS, value & 0xff); +} + /* * Adjust the IPB to allow a CPU to process event queues of other * priorities during one physical interrupt cycle. @@ -400,7 +469,7 @@ static uint64_t xive_tm_pull_os_ctx(XivePresenter *xptr, XiveTCTX *tctx, qw1w2_new = xive_set_field32(TM_QW1W2_VO, qw1w2, 0); xive_tctx_set_os_cam(tctx, qw1w2_new); - xive_tctx_reset_os_signal(tctx); + xive_tctx_reset_signal(tctx, TM_QW1_OS); return qw1w2; } @@ -488,20 +557,34 @@ static const XiveTmOp xive_tm_operations[] = { * MMIOs below 2K : raw values and special operations without side * effects */ - { XIVE_TM_OS_PAGE, TM_QW1_OS + TM_CPPR, 1, xive_tm_set_os_cppr, NULL }, - { XIVE_TM_HV_PAGE, TM_QW1_OS + TM_WORD2, 4, xive_tm_push_os_ctx, NULL }, - { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_CPPR, 1, xive_tm_set_hv_cppr, NULL }, - { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_WORD2, 1, xive_tm_vt_push, NULL }, - { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_WORD2, 1, NULL, xive_tm_vt_poll }, + { XIVE_TM_OS_PAGE, TM_QW1_OS + TM_CPPR, 1, xive_tm_set_os_cppr, + NULL }, + { XIVE_TM_HV_PAGE, TM_QW1_OS + TM_WORD2, 4, xive_tm_push_os_ctx, + NULL }, + { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_CPPR, 1, xive_tm_set_hv_cppr, + NULL }, + { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_WORD2, 1, xive_tm_vt_push, + NULL }, + { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_WORD2, 1, NULL, + xive_tm_vt_poll }, /* MMIOs above 2K : special operations with side effects */ - { XIVE_TM_OS_PAGE, TM_SPC_ACK_OS_REG, 2, NULL, xive_tm_ack_os_reg }, - { XIVE_TM_OS_PAGE, TM_SPC_SET_OS_PENDING, 1, xive_tm_set_os_pending, NULL }, - { XIVE_TM_HV_PAGE, TM_SPC_PULL_OS_CTX, 4, NULL, xive_tm_pull_os_ctx }, - { XIVE_TM_HV_PAGE, TM_SPC_PULL_OS_CTX, 8, NULL, xive_tm_pull_os_ctx }, - { XIVE_TM_HV_PAGE, TM_SPC_ACK_HV_REG, 2, NULL, xive_tm_ack_hv_reg }, - { XIVE_TM_HV_PAGE, TM_SPC_PULL_POOL_CTX, 4, NULL, xive_tm_pull_pool_ctx }, - { XIVE_TM_HV_PAGE, TM_SPC_PULL_POOL_CTX, 8, NULL, xive_tm_pull_pool_ctx }, + { XIVE_TM_OS_PAGE, TM_SPC_ACK_OS_REG, 2, NULL, + xive_tm_ack_os_reg }, + { XIVE_TM_OS_PAGE, TM_SPC_SET_OS_PENDING, 1, xive_tm_set_os_pending, + NULL }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_OS_CTX, 4, NULL, + xive_tm_pull_os_ctx }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_OS_CTX, 8, NULL, + xive_tm_pull_os_ctx }, + { XIVE_TM_HV_PAGE, TM_SPC_ACK_HV_REG, 2, NULL, + xive_tm_ack_hv_reg }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_POOL_CTX, 4, NULL, + xive_tm_pull_pool_ctx }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_POOL_CTX, 8, NULL, + xive_tm_pull_pool_ctx }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_PHYS_CTX, 1, NULL, + xive_tm_pull_phys_ctx }, }; static const XiveTmOp xive2_tm_operations[] = { @@ -509,20 +592,50 @@ static const XiveTmOp xive2_tm_operations[] = { * MMIOs below 2K : raw values and special operations without side * effects */ - { XIVE_TM_OS_PAGE, TM_QW1_OS + TM_CPPR, 1, xive_tm_set_os_cppr, NULL }, - { XIVE_TM_HV_PAGE, TM_QW1_OS + TM_WORD2, 4, xive2_tm_push_os_ctx, NULL }, - { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_CPPR, 1, xive_tm_set_hv_cppr, NULL }, - { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_WORD2, 1, xive_tm_vt_push, NULL }, - { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_WORD2, 1, NULL, xive_tm_vt_poll }, + { XIVE_TM_OS_PAGE, TM_QW1_OS + TM_CPPR, 1, xive_tm_set_os_cppr, + NULL }, + { XIVE_TM_HV_PAGE, TM_QW1_OS + TM_WORD2, 4, xive2_tm_push_os_ctx, + NULL }, + { XIVE_TM_HV_PAGE, TM_QW1_OS + TM_WORD2, 8, xive2_tm_push_os_ctx, + NULL }, + { XIVE_TM_OS_PAGE, TM_QW1_OS + TM_LGS, 1, xive_tm_set_os_lgs, + NULL }, + { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_CPPR, 1, xive_tm_set_hv_cppr, + NULL }, + { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_WORD2, 1, xive_tm_vt_push, + NULL }, + { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_WORD2, 1, NULL, + xive_tm_vt_poll }, + { XIVE_TM_HV_PAGE, TM_QW3_HV_PHYS + TM_T, 1, xive2_tm_set_hv_target, + NULL }, /* MMIOs above 2K : special operations with side effects */ - { XIVE_TM_OS_PAGE, TM_SPC_ACK_OS_REG, 2, NULL, xive_tm_ack_os_reg }, - { XIVE_TM_OS_PAGE, TM_SPC_SET_OS_PENDING, 1, xive_tm_set_os_pending, NULL }, - { XIVE_TM_HV_PAGE, TM_SPC_PULL_OS_CTX, 4, NULL, xive2_tm_pull_os_ctx }, - { XIVE_TM_HV_PAGE, TM_SPC_PULL_OS_CTX, 8, NULL, xive2_tm_pull_os_ctx }, - { XIVE_TM_HV_PAGE, TM_SPC_ACK_HV_REG, 2, NULL, xive_tm_ack_hv_reg }, - { XIVE_TM_HV_PAGE, TM_SPC_PULL_POOL_CTX, 4, NULL, xive_tm_pull_pool_ctx }, - { XIVE_TM_HV_PAGE, TM_SPC_PULL_POOL_CTX, 8, NULL, xive_tm_pull_pool_ctx }, + { XIVE_TM_OS_PAGE, TM_SPC_ACK_OS_REG, 2, NULL, + xive_tm_ack_os_reg }, + { XIVE_TM_OS_PAGE, TM_SPC_SET_OS_PENDING, 1, xive_tm_set_os_pending, + NULL }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_OS_CTX_G2, 4, NULL, + xive2_tm_pull_os_ctx }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_OS_CTX, 4, NULL, + xive2_tm_pull_os_ctx }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_OS_CTX, 8, NULL, + xive2_tm_pull_os_ctx }, + { XIVE_TM_HV_PAGE, TM_SPC_ACK_HV_REG, 2, NULL, + xive_tm_ack_hv_reg }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_POOL_CTX_G2, 4, NULL, + xive_tm_pull_pool_ctx }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_POOL_CTX, 4, NULL, + xive_tm_pull_pool_ctx }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_POOL_CTX, 8, NULL, + xive_tm_pull_pool_ctx }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_OS_CTX_OL, 1, xive2_tm_pull_os_ctx_ol, + NULL }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_PHYS_CTX_G2, 4, NULL, + xive_tm_pull_phys_ctx }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_PHYS_CTX, 1, NULL, + xive_tm_pull_phys_ctx }, + { XIVE_TM_HV_PAGE, TM_SPC_PULL_PHYS_CTX_OL, 1, xive2_tm_pull_phys_ctx_ol, + NULL }, }; static const XiveTmOp *xive_tm_find_op(XivePresenter *xptr, hwaddr offset, @@ -718,6 +831,10 @@ void xive_tctx_reset(XiveTCTX *tctx) tctx->regs[TM_QW1_OS + TM_LSMFB] = 0xFF; tctx->regs[TM_QW1_OS + TM_ACK_CNT] = 0xFF; tctx->regs[TM_QW1_OS + TM_AGE] = 0xFF; + if (!(xive_presenter_get_config(tctx->xptr) & + XIVE_PRESENTER_GEN1_TIMA_OS)) { + tctx->regs[TM_QW1_OS + TM_OGEN] = 2; + } /* * Initialize PIPR to 0xFF to avoid phantom interrupts when the @@ -1242,7 +1359,7 @@ static void xive_source_reset(void *dev) static void xive_source_realize(DeviceState *dev, Error **errp) { XiveSource *xsrc = XIVE_SOURCE(dev); - size_t esb_len = xive_source_esb_len(xsrc); + uint64_t esb_len = xive_source_esb_len(xsrc); assert(xsrc->xive); diff --git a/hw/intc/xive2.c b/hw/intc/xive2.c index 1f150685bf..d1df35e9b3 100644 --- a/hw/intc/xive2.c +++ b/hw/intc/xive2.c @@ -26,6 +26,43 @@ uint32_t xive2_router_get_config(Xive2Router *xrtr) return xrc->get_config(xrtr); } +static int xive2_router_get_block_id(Xive2Router *xrtr) +{ + Xive2RouterClass *xrc = XIVE2_ROUTER_GET_CLASS(xrtr); + + return xrc->get_block_id(xrtr); +} + +static uint64_t xive2_nvp_reporting_addr(Xive2Nvp *nvp) +{ + uint64_t cache_addr; + + cache_addr = xive_get_field32(NVP2_W6_REPORTING_LINE, nvp->w6) << 24 | + xive_get_field32(NVP2_W7_REPORTING_LINE, nvp->w7); + cache_addr <<= 8; /* aligned on a cache line pair */ + return cache_addr; +} + +static uint32_t xive2_nvgc_get_backlog(Xive2Nvgc *nvgc, uint8_t priority) +{ + uint32_t val = 0; + uint8_t *ptr, i; + + if (priority > 7) { + return 0; + } + + /* + * The per-priority backlog counters are 24-bit and the structure + * is stored in big endian + */ + ptr = (uint8_t *)&nvgc->w2 + priority * 3; + for (i = 0; i < 3; i++, ptr++) { + val = (val << 8) + *ptr; + } + return val; +} + void xive2_eas_pic_print_info(Xive2Eas *eas, uint32_t lisn, GString *buf) { if (!xive2_eas_is_valid(eas)) { @@ -144,14 +181,20 @@ void xive2_nvp_pic_print_info(Xive2Nvp *nvp, uint32_t nvp_idx, GString *buf) { uint8_t eq_blk = xive_get_field32(NVP2_W5_VP_END_BLOCK, nvp->w5); uint32_t eq_idx = xive_get_field32(NVP2_W5_VP_END_INDEX, nvp->w5); + uint64_t cache_line = xive2_nvp_reporting_addr(nvp); if (!xive2_nvp_is_valid(nvp)) { return; } - g_string_append_printf(buf, " %08x end:%02x/%04x IPB:%02x", + g_string_append_printf(buf, " %08x end:%02x/%04x IPB:%02x PGoFirst:%02x", nvp_idx, eq_blk, eq_idx, - xive_get_field32(NVP2_W2_IPB, nvp->w2)); + xive_get_field32(NVP2_W2_IPB, nvp->w2), + xive_get_field32(NVP2_W0_PGOFIRST, nvp->w0)); + if (cache_line) { + g_string_append_printf(buf, " reporting CL:%016"PRIx64, cache_line); + } + /* * When the NVP is HW controlled, more fields are updated */ @@ -166,6 +209,23 @@ void xive2_nvp_pic_print_info(Xive2Nvp *nvp, uint32_t nvp_idx, GString *buf) g_string_append_c(buf, '\n'); } +void xive2_nvgc_pic_print_info(Xive2Nvgc *nvgc, uint32_t nvgc_idx, GString *buf) +{ + uint8_t i; + + if (!xive2_nvgc_is_valid(nvgc)) { + return; + } + + g_string_append_printf(buf, " %08x PGoNext:%02x bklog: ", nvgc_idx, + xive_get_field32(NVGC2_W0_PGONEXT, nvgc->w0)); + for (i = 0; i <= XIVE_PRIORITY_MAX; i++) { + g_string_append_printf(buf, "[%d]=0x%x ", + i, xive2_nvgc_get_backlog(nvgc, i)); + } + g_string_append_printf(buf, "\n"); +} + static void xive2_end_enqueue(Xive2End *end, uint32_t data) { uint64_t qaddr_base = xive2_end_qaddr(end); @@ -210,13 +270,14 @@ static void xive2_end_enqueue(Xive2End *end, uint32_t data) * the NVP by changing the H bit while the context is enabled */ -static void xive2_tctx_save_os_ctx(Xive2Router *xrtr, XiveTCTX *tctx, - uint8_t nvp_blk, uint32_t nvp_idx) +static void xive2_tctx_save_ctx(Xive2Router *xrtr, XiveTCTX *tctx, + uint8_t nvp_blk, uint32_t nvp_idx, + uint8_t ring) { CPUPPCState *env = &POWERPC_CPU(tctx->cs)->env; uint32_t pir = env->spr_cb[SPR_PIR].default_value; Xive2Nvp nvp; - uint8_t *regs = &tctx->regs[TM_QW1_OS]; + uint8_t *regs = &tctx->regs[ring]; if (xive2_router_get_nvp(xrtr, nvp_blk, nvp_idx, &nvp)) { qemu_log_mask(LOG_GUEST_ERROR, "XIVE: No NVP %x/%x\n", @@ -261,44 +322,190 @@ static void xive2_tctx_save_os_ctx(Xive2Router *xrtr, XiveTCTX *tctx, xive2_router_write_nvp(xrtr, nvp_blk, nvp_idx, &nvp, 1); } -static void xive2_os_cam_decode(uint32_t cam, uint8_t *nvp_blk, - uint32_t *nvp_idx, bool *vo, bool *ho) +static void xive2_cam_decode(uint32_t cam, uint8_t *nvp_blk, + uint32_t *nvp_idx, bool *valid, bool *hw) { *nvp_blk = xive2_nvp_blk(cam); *nvp_idx = xive2_nvp_idx(cam); - *vo = !!(cam & TM2_QW1W2_VO); - *ho = !!(cam & TM2_QW1W2_HO); + *valid = !!(cam & TM2_W2_VALID); + *hw = !!(cam & TM2_W2_HW); } -uint64_t xive2_tm_pull_os_ctx(XivePresenter *xptr, XiveTCTX *tctx, - hwaddr offset, unsigned size) +/* + * Encode the HW CAM line with 7bit or 8bit thread id. The thread id + * width and block id width is configurable at the IC level. + * + * chipid << 24 | 0000 0000 0000 0000 1 threadid (7Bit) + * chipid << 24 | 0000 0000 0000 0001 threadid (8Bit) + */ +static uint32_t xive2_tctx_hw_cam_line(XivePresenter *xptr, XiveTCTX *tctx) { Xive2Router *xrtr = XIVE2_ROUTER(xptr); - uint32_t qw1w2 = xive_tctx_word2(&tctx->regs[TM_QW1_OS]); - uint32_t qw1w2_new; - uint32_t cam = be32_to_cpu(qw1w2); + CPUPPCState *env = &POWERPC_CPU(tctx->cs)->env; + uint32_t pir = env->spr_cb[SPR_PIR].default_value; + uint8_t blk = xive2_router_get_block_id(xrtr); + uint8_t tid_shift = + xive2_router_get_config(xrtr) & XIVE2_THREADID_8BITS ? 8 : 7; + uint8_t tid_mask = (1 << tid_shift) - 1; + + return xive2_nvp_cam_line(blk, 1 << tid_shift | (pir & tid_mask)); +} + +static uint64_t xive2_tm_pull_ctx(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, unsigned size, uint8_t ring) +{ + Xive2Router *xrtr = XIVE2_ROUTER(xptr); + uint32_t target_ringw2 = xive_tctx_word2(&tctx->regs[ring]); + uint32_t cam = be32_to_cpu(target_ringw2); uint8_t nvp_blk; uint32_t nvp_idx; - bool vo; + uint8_t cur_ring; + bool valid; bool do_save; - xive2_os_cam_decode(cam, &nvp_blk, &nvp_idx, &vo, &do_save); + xive2_cam_decode(cam, &nvp_blk, &nvp_idx, &valid, &do_save); - if (!vo) { + if (!valid) { qemu_log_mask(LOG_GUEST_ERROR, "XIVE: pulling invalid NVP %x/%x !?\n", nvp_blk, nvp_idx); } - /* Invalidate CAM line */ - qw1w2_new = xive_set_field32(TM2_QW1W2_VO, qw1w2, 0); - memcpy(&tctx->regs[TM_QW1_OS + TM_WORD2], &qw1w2_new, 4); + /* Invalidate CAM line of requested ring and all lower rings */ + for (cur_ring = TM_QW0_USER; cur_ring <= ring; + cur_ring += XIVE_TM_RING_SIZE) { + uint32_t ringw2 = xive_tctx_word2(&tctx->regs[cur_ring]); + uint32_t ringw2_new = xive_set_field32(TM2_QW1W2_VO, ringw2, 0); + memcpy(&tctx->regs[cur_ring + TM_WORD2], &ringw2_new, 4); + } if (xive2_router_get_config(xrtr) & XIVE2_VP_SAVE_RESTORE && do_save) { - xive2_tctx_save_os_ctx(xrtr, tctx, nvp_blk, nvp_idx); + xive2_tctx_save_ctx(xrtr, tctx, nvp_blk, nvp_idx, ring); + } + + /* + * Lower external interrupt line of requested ring and below except for + * USER, which doesn't exist. + */ + for (cur_ring = TM_QW1_OS; cur_ring <= ring; + cur_ring += XIVE_TM_RING_SIZE) { + xive_tctx_reset_signal(tctx, cur_ring); + } + return target_ringw2; +} + +uint64_t xive2_tm_pull_os_ctx(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, unsigned size) +{ + return xive2_tm_pull_ctx(xptr, tctx, offset, size, TM_QW1_OS); +} + +#define REPORT_LINE_GEN1_SIZE 16 + +static void xive2_tm_report_line_gen1(XiveTCTX *tctx, uint8_t *data, + uint8_t size) +{ + uint8_t *regs = tctx->regs; + + g_assert(size == REPORT_LINE_GEN1_SIZE); + memset(data, 0, size); + /* + * See xive architecture for description of what is saved. It is + * hand-picked information to fit in 16 bytes. + */ + data[0x0] = regs[TM_QW3_HV_PHYS + TM_NSR]; + data[0x1] = regs[TM_QW3_HV_PHYS + TM_CPPR]; + data[0x2] = regs[TM_QW3_HV_PHYS + TM_IPB]; + data[0x3] = regs[TM_QW2_HV_POOL + TM_IPB]; + data[0x4] = regs[TM_QW1_OS + TM_ACK_CNT]; + data[0x5] = regs[TM_QW3_HV_PHYS + TM_LGS]; + data[0x6] = 0xFF; + data[0x7] = regs[TM_QW3_HV_PHYS + TM_WORD2] & 0x80; + data[0x7] |= (regs[TM_QW2_HV_POOL + TM_WORD2] & 0x80) >> 1; + data[0x7] |= (regs[TM_QW1_OS + TM_WORD2] & 0x80) >> 2; + data[0x7] |= (regs[TM_QW3_HV_PHYS + TM_WORD2] & 0x3); + data[0x8] = regs[TM_QW1_OS + TM_NSR]; + data[0x9] = regs[TM_QW1_OS + TM_CPPR]; + data[0xA] = regs[TM_QW1_OS + TM_IPB]; + data[0xB] = regs[TM_QW1_OS + TM_LGS]; + if (regs[TM_QW0_USER + TM_WORD2] & 0x80) { + /* + * Logical server extension, except VU bit replaced by EB bit + * from NSR + */ + data[0xC] = regs[TM_QW0_USER + TM_WORD2]; + data[0xC] &= ~0x80; + data[0xC] |= regs[TM_QW0_USER + TM_NSR] & 0x80; + data[0xD] = regs[TM_QW0_USER + TM_WORD2 + 1]; + data[0xE] = regs[TM_QW0_USER + TM_WORD2 + 2]; + data[0xF] = regs[TM_QW0_USER + TM_WORD2 + 3]; } +} + +static void xive2_tm_pull_ctx_ol(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, uint64_t value, + unsigned size, uint8_t ring) +{ + Xive2Router *xrtr = XIVE2_ROUTER(xptr); + uint32_t hw_cam, nvp_idx, xive2_cfg, reserved; + uint8_t nvp_blk; + Xive2Nvp nvp; + uint64_t phys_addr; + MemTxResult result; - xive_tctx_reset_os_signal(tctx); - return qw1w2; + hw_cam = xive2_tctx_hw_cam_line(xptr, tctx); + nvp_blk = xive2_nvp_blk(hw_cam); + nvp_idx = xive2_nvp_idx(hw_cam); + + if (xive2_router_get_nvp(xrtr, nvp_blk, nvp_idx, &nvp)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: No NVP %x/%x\n", + nvp_blk, nvp_idx); + return; + } + + if (!xive2_nvp_is_valid(&nvp)) { + qemu_log_mask(LOG_GUEST_ERROR, "XIVE: invalid NVP %x/%x\n", + nvp_blk, nvp_idx); + return; + } + + xive2_cfg = xive2_router_get_config(xrtr); + + phys_addr = xive2_nvp_reporting_addr(&nvp) + 0x80; /* odd line */ + if (xive2_cfg & XIVE2_GEN1_TIMA_OS) { + uint8_t pull_ctxt[REPORT_LINE_GEN1_SIZE]; + + xive2_tm_report_line_gen1(tctx, pull_ctxt, REPORT_LINE_GEN1_SIZE); + result = dma_memory_write(&address_space_memory, phys_addr, + pull_ctxt, REPORT_LINE_GEN1_SIZE, + MEMTXATTRS_UNSPECIFIED); + assert(result == MEMTX_OK); + } else { + result = dma_memory_write(&address_space_memory, phys_addr, + &tctx->regs, sizeof(tctx->regs), + MEMTXATTRS_UNSPECIFIED); + assert(result == MEMTX_OK); + reserved = 0xFFFFFFFF; + result = dma_memory_write(&address_space_memory, phys_addr + 12, + &reserved, sizeof(reserved), + MEMTXATTRS_UNSPECIFIED); + assert(result == MEMTX_OK); + } + + /* the rest is similar to pull context to registers */ + xive2_tm_pull_ctx(xptr, tctx, offset, size, ring); +} + +void xive2_tm_pull_os_ctx_ol(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, uint64_t value, unsigned size) +{ + xive2_tm_pull_ctx_ol(xptr, tctx, offset, value, size, TM_QW1_OS); +} + + +void xive2_tm_pull_phys_ctx_ol(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, uint64_t value, unsigned size) +{ + xive2_tm_pull_ctx_ol(xptr, tctx, offset, value, size, TM_QW3_HV_PHYS); } static uint8_t xive2_tctx_restore_os_ctx(Xive2Router *xrtr, XiveTCTX *tctx, @@ -390,17 +597,31 @@ static void xive2_tctx_need_resend(Xive2Router *xrtr, XiveTCTX *tctx, void xive2_tm_push_os_ctx(XivePresenter *xptr, XiveTCTX *tctx, hwaddr offset, uint64_t value, unsigned size) { - uint32_t cam = value; - uint32_t qw1w2 = cpu_to_be32(cam); + uint32_t cam; + uint32_t qw1w2; + uint64_t qw1dw1; uint8_t nvp_blk; uint32_t nvp_idx; bool vo; bool do_restore; - xive2_os_cam_decode(cam, &nvp_blk, &nvp_idx, &vo, &do_restore); - /* First update the thead context */ - memcpy(&tctx->regs[TM_QW1_OS + TM_WORD2], &qw1w2, 4); + switch (size) { + case 4: + cam = value; + qw1w2 = cpu_to_be32(cam); + memcpy(&tctx->regs[TM_QW1_OS + TM_WORD2], &qw1w2, 4); + break; + case 8: + cam = value >> 32; + qw1dw1 = cpu_to_be64(value); + memcpy(&tctx->regs[TM_QW1_OS + TM_WORD2], &qw1dw1, 8); + break; + default: + g_assert_not_reached(); + } + + xive2_cam_decode(cam, &nvp_blk, &nvp_idx, &vo, &do_restore); /* Check the interrupt pending bits */ if (vo) { @@ -409,6 +630,19 @@ void xive2_tm_push_os_ctx(XivePresenter *xptr, XiveTCTX *tctx, } } +static void xive2_tctx_set_target(XiveTCTX *tctx, uint8_t ring, uint8_t target) +{ + uint8_t *regs = &tctx->regs[ring]; + + regs[TM_T] = target; +} + +void xive2_tm_set_hv_target(XivePresenter *xptr, XiveTCTX *tctx, + hwaddr offset, uint64_t value, unsigned size) +{ + xive2_tctx_set_target(tctx, TM_QW3_HV_PHYS, value & 0xff); +} + /* * XIVE Router (aka. Virtualization Controller or IVRE) */ @@ -471,31 +705,22 @@ int xive2_router_write_nvp(Xive2Router *xrtr, uint8_t nvp_blk, uint32_t nvp_idx, return xrc->write_nvp(xrtr, nvp_blk, nvp_idx, nvp, word_number); } -static int xive2_router_get_block_id(Xive2Router *xrtr) +int xive2_router_get_nvgc(Xive2Router *xrtr, bool crowd, + uint8_t nvgc_blk, uint32_t nvgc_idx, + Xive2Nvgc *nvgc) { Xive2RouterClass *xrc = XIVE2_ROUTER_GET_CLASS(xrtr); - return xrc->get_block_id(xrtr); + return xrc->get_nvgc(xrtr, crowd, nvgc_blk, nvgc_idx, nvgc); } -/* - * Encode the HW CAM line with 7bit or 8bit thread id. The thread id - * width and block id width is configurable at the IC level. - * - * chipid << 24 | 0000 0000 0000 0000 1 threadid (7Bit) - * chipid << 24 | 0000 0000 0000 0001 threadid (8Bit) - */ -static uint32_t xive2_tctx_hw_cam_line(XivePresenter *xptr, XiveTCTX *tctx) +int xive2_router_write_nvgc(Xive2Router *xrtr, bool crowd, + uint8_t nvgc_blk, uint32_t nvgc_idx, + Xive2Nvgc *nvgc) { - Xive2Router *xrtr = XIVE2_ROUTER(xptr); - CPUPPCState *env = &POWERPC_CPU(tctx->cs)->env; - uint32_t pir = env->spr_cb[SPR_PIR].default_value; - uint8_t blk = xive2_router_get_block_id(xrtr); - uint8_t tid_shift = - xive2_router_get_config(xrtr) & XIVE2_THREADID_8BITS ? 8 : 7; - uint8_t tid_mask = (1 << tid_shift) - 1; + Xive2RouterClass *xrc = XIVE2_ROUTER_GET_CLASS(xrtr); - return xive2_nvp_cam_line(blk, 1 << tid_shift | (pir & tid_mask)); + return xrc->write_nvgc(xrtr, crowd, nvgc_blk, nvgc_idx, nvgc); } /* diff --git a/hw/m68k/next-cube.c b/hw/m68k/next-cube.c index 9832213e7e..08886d432c 100644 --- a/hw/m68k/next-cube.c +++ b/hw/m68k/next-cube.c @@ -404,7 +404,7 @@ static void next_scr_writefn(void *opaque, hwaddr addr, uint64_t val, switch (addr) { case 0x14108: - DPRINTF("FDCSR Write: %x\n", value); + DPRINTF("FDCSR Write: %"PRIx64 "\n", val); if (val == 0x0) { /* qemu_irq_raise(s->fd_irq[0]); */ } @@ -468,15 +468,15 @@ static void next_scr_writefn(void *opaque, hwaddr addr, uint64_t val, /* int_mask |= 0x1000; */ /* s->scsi_csr_1 |= 0x80; */ } - DPRINTF("SCSICSR Write: %x\n", val); + DPRINTF("SCSICSR Write: %"PRIx64 "\n", val); /* s->scsi_csr_1 = val; */ break; /* Hardware timer latch - not implemented yet */ case 0x1a000: default: - DPRINTF("BMAP Write @ 0x%x with 0x%x size %u\n", (unsigned int)addr, - val, size); + DPRINTF("BMAP Write @ 0x%x with 0x%"PRIx64 " size %u\n", + (unsigned int)addr, val, size); } } @@ -585,7 +585,7 @@ static void next_dma_write(void *opaque, hwaddr addr, uint64_t val, break; default: - DPRINTF("DMA write @ %x w/ %x\n", (unsigned)addr, (unsigned)value); + DPRINTF("DMA write @ %x w/ %x\n", (unsigned)addr, (unsigned)val); } } @@ -828,7 +828,7 @@ static void nextscsi_write(void *opaque, uint8_t *buf, int size) nextdma_write(opaque, buf, size, NEXTDMA_SCSI); } -static void next_scsi_init(DeviceState *pcdev, M68kCPU *cpu) +static void next_scsi_init(DeviceState *pcdev) { struct NeXTPC *next_pc = NEXT_PC(pcdev); DeviceState *dev; @@ -1050,7 +1050,7 @@ static void next_cube_init(MachineState *machine) /* TODO: */ /* Network */ /* SCSI */ - next_scsi_init(pcdev, cpu); + next_scsi_init(pcdev); /* DMA */ memory_region_init_io(&m->dmamem, NULL, &next_dma_ops, machine, diff --git a/hw/mem/cxl_type3.c b/hw/mem/cxl_type3.c index 235ac40aeb..5cf754b38f 100644 --- a/hw/mem/cxl_type3.c +++ b/hw/mem/cxl_type3.c @@ -17,6 +17,7 @@ #include "hw/mem/pc-dimm.h" #include "hw/pci/pci.h" #include "hw/qdev-properties.h" +#include "hw/qdev-properties-system.h" #include "qapi/error.h" #include "qemu/log.h" #include "qemu/module.h" @@ -919,16 +920,15 @@ static void ct3_realize(PCIDevice *pci_dev, Error **errp) ct3d->patrol_scrub_attrs.scrub_flags = CXL_MEMDEV_PS_ENABLE_DEFAULT; /* Set default value for DDR5 ECS read attributes */ + ct3d->ecs_attrs.ecs_log_cap = CXL_ECS_LOG_ENTRY_TYPE_DEFAULT; for (count = 0; count < CXL_ECS_NUM_MEDIA_FRUS; count++) { - ct3d->ecs_attrs[count].ecs_log_cap = - CXL_ECS_LOG_ENTRY_TYPE_DEFAULT; - ct3d->ecs_attrs[count].ecs_cap = + ct3d->ecs_attrs.fru_attrs[count].ecs_cap = CXL_ECS_REALTIME_REPORT_CAP_DEFAULT; - ct3d->ecs_attrs[count].ecs_config = + ct3d->ecs_attrs.fru_attrs[count].ecs_config = CXL_ECS_THRESHOLD_COUNT_DEFAULT | (CXL_ECS_MODE_DEFAULT << 3); /* Reserved */ - ct3d->ecs_attrs[count].ecs_flags = 0; + ct3d->ecs_attrs.fru_attrs[count].ecs_flags = 0; } return; @@ -1200,6 +1200,7 @@ static void ct3d_reset(DeviceState *dev) uint32_t *reg_state = ct3d->cxl_cstate.crb.cache_mem_registers; uint32_t *write_msk = ct3d->cxl_cstate.crb.cache_mem_regs_write_mask; + pcie_cap_fill_link_ep_usp(PCI_DEVICE(dev), ct3d->width, ct3d->speed); cxl_component_register_init_common(reg_state, write_msk, CXL2_TYPE3_DEVICE); cxl_device_register_init_t3(ct3d); @@ -1229,6 +1230,10 @@ static Property ct3_props[] = { DEFINE_PROP_UINT8("num-dc-regions", CXLType3Dev, dc.num_regions, 0), DEFINE_PROP_LINK("volatile-dc-memdev", CXLType3Dev, dc.host_dc, TYPE_MEMORY_BACKEND, HostMemoryBackend *), + DEFINE_PROP_PCIE_LINK_SPEED("x-speed", CXLType3Dev, + speed, PCIE_LINK_SPEED_32), + DEFINE_PROP_PCIE_LINK_WIDTH("x-width", CXLType3Dev, + width, PCIE_LINK_WIDTH_16), DEFINE_PROP_END_OF_LIST(), }; @@ -1375,9 +1380,7 @@ void qmp_cxl_inject_poison(const char *path, uint64_t start, uint64_t length, ct3d = CXL_TYPE3(obj); QLIST_FOREACH(p, &ct3d->poison_list, node) { - if (((start >= p->start) && (start < p->start + p->length)) || - ((start + length > p->start) && - (start + length <= p->start + p->length))) { + if ((start < p->start + p->length) && (start + length > p->start)) { error_setg(errp, "Overlap with existing poisoned region not supported"); return; @@ -2060,11 +2063,11 @@ static void qmp_cxl_process_dynamic_capacity_prescriptive(const char *path, stw_le_p(&dCap.host_id, hid); /* only valid for DC_REGION_CONFIG_UPDATED event */ dCap.updated_region_id = 0; - dCap.flags = 0; for (i = 0; i < num_extents; i++) { memcpy(&dCap.dynamic_capacity_extent, &extents[i], sizeof(CXLDCExtentRaw)); + dCap.flags = 0; if (i < num_extents - 1) { /* Set "More" flag */ dCap.flags |= BIT(0); diff --git a/hw/nvme/ctrl.c b/hw/nvme/ctrl.c index f4e89203c1..8e4612e035 100644 --- a/hw/nvme/ctrl.c +++ b/hw/nvme/ctrl.c @@ -5692,6 +5692,33 @@ static uint16_t nvme_identify_sec_ctrl_list(NvmeCtrl *n, NvmeRequest *req) return nvme_c2h(n, (uint8_t *)&list, sizeof(list), req); } +static uint16_t nvme_identify_ns_ind(NvmeCtrl *n, NvmeRequest *req, bool alloc) +{ + NvmeNamespace *ns; + NvmeIdentify *c = (NvmeIdentify *)&req->cmd; + uint32_t nsid = le32_to_cpu(c->nsid); + + trace_pci_nvme_identify_ns_ind(nsid); + + if (!nvme_nsid_valid(n, nsid) || nsid == NVME_NSID_BROADCAST) { + return NVME_INVALID_NSID | NVME_DNR; + } + + ns = nvme_ns(n, nsid); + if (unlikely(!ns)) { + if (alloc) { + ns = nvme_subsys_ns(n->subsys, nsid); + if (!ns) { + return nvme_rpt_empty_id_struct(n, req); + } + } else { + return nvme_rpt_empty_id_struct(n, req); + } + } + + return nvme_c2h(n, (uint8_t *)&ns->id_ns_ind, sizeof(NvmeIdNsInd), req); +} + static uint16_t nvme_identify_ns_csi(NvmeCtrl *n, NvmeRequest *req, bool active) { @@ -5946,6 +5973,10 @@ static uint16_t nvme_identify(NvmeCtrl *n, NvmeRequest *req) return nvme_identify_sec_ctrl_list(n, req); case NVME_ID_CNS_CS_NS: return nvme_identify_ns_csi(n, req, true); + case NVME_ID_CNS_CS_IND_NS: + return nvme_identify_ns_ind(n, req, false); + case NVME_ID_CNS_CS_IND_NS_ALLOCATED: + return nvme_identify_ns_ind(n, req, true); case NVME_ID_CNS_CS_NS_PRESENT: return nvme_identify_ns_csi(n, req, false); case NVME_ID_CNS_CTRL: diff --git a/hw/nvme/dif.c b/hw/nvme/dif.c index 01b19c3373..2805128498 100644 --- a/hw/nvme/dif.c +++ b/hw/nvme/dif.c @@ -575,11 +575,6 @@ uint16_t nvme_dif_rw(NvmeCtrl *n, NvmeRequest *req) uint8_t *mbuf, *end; int16_t pil = ns->lbaf.ms - nvme_pi_tuple_size(ns); - status = nvme_check_prinfo(ns, prinfo, slba, reftag); - if (status) { - goto err; - } - flags = 0; ctx->mdata.bounce = g_malloc0(mlen); diff --git a/hw/nvme/ns.c b/hw/nvme/ns.c index ea8db175db..526e15aa80 100644 --- a/hw/nvme/ns.c +++ b/hw/nvme/ns.c @@ -30,6 +30,7 @@ void nvme_ns_init_format(NvmeNamespace *ns) { NvmeIdNs *id_ns = &ns->id_ns; + NvmeIdNsNvm *id_ns_nvm = &ns->id_ns_nvm; BlockDriverInfo bdi; int npdg, ret; int64_t nlbas; @@ -55,6 +56,8 @@ void nvme_ns_init_format(NvmeNamespace *ns) } id_ns->npda = id_ns->npdg = npdg - 1; + id_ns_nvm->npdal = npdg; + id_ns_nvm->npdgl = npdg; } static int nvme_ns_init(NvmeNamespace *ns, Error **errp) @@ -62,6 +65,7 @@ static int nvme_ns_init(NvmeNamespace *ns, Error **errp) static uint64_t ns_count; NvmeIdNs *id_ns = &ns->id_ns; NvmeIdNsNvm *id_ns_nvm = &ns->id_ns_nvm; + NvmeIdNsInd *id_ns_ind = &ns->id_ns_ind; uint8_t ds; uint16_t ms; int i; @@ -72,10 +76,12 @@ static int nvme_ns_init(NvmeNamespace *ns, Error **errp) ns->id_ns.dlfeat = 0x1; /* support DULBE and I/O optimization fields */ - id_ns->nsfeat |= (0x4 | 0x10); + id_ns->nsfeat |= (NVME_ID_NS_NSFEAT_DAE | NVME_ID_NS_NSFEAT_OPTPERF_ALL); if (ns->params.shared) { - id_ns->nmic |= NVME_NMIC_NS_SHARED; + id_ns->nmic |= NVME_ID_NS_IND_NMIC_SHRNS; + id_ns_ind->nmic = NVME_ID_NS_IND_NMIC_SHRNS; + id_ns_ind->nstat = NVME_ID_NS_IND_NSTAT_NRDY; } /* Substitute a missing EUI-64 by an autogenerated one */ @@ -770,6 +776,7 @@ static void nvme_ns_realize(DeviceState *dev, Error **errp) subsys->namespaces[nsid] = ns; ns->id_ns.endgid = cpu_to_le16(0x1); + ns->id_ns_ind.endgrpid = cpu_to_le16(0x1); if (ns->params.detached) { return; diff --git a/hw/nvme/nvme.h b/hw/nvme/nvme.h index 7566b316d1..7242206910 100644 --- a/hw/nvme/nvme.h +++ b/hw/nvme/nvme.h @@ -233,6 +233,7 @@ typedef struct NvmeNamespace { int64_t moff; NvmeIdNs id_ns; NvmeIdNsNvm id_ns_nvm; + NvmeIdNsInd id_ns_ind; NvmeLBAF lbaf; unsigned int nlbaf; size_t lbasz; diff --git a/hw/nvme/trace-events b/hw/nvme/trace-events index 3a67680c6a..6be0bfa1c1 100644 --- a/hw/nvme/trace-events +++ b/hw/nvme/trace-events @@ -56,6 +56,7 @@ pci_nvme_identify(uint16_t cid, uint8_t cns, uint16_t ctrlid, uint8_t csi) "cid pci_nvme_identify_ctrl(void) "identify controller" pci_nvme_identify_ctrl_csi(uint8_t csi) "identify controller, csi=0x%"PRIx8"" pci_nvme_identify_ns(uint32_t ns) "nsid %"PRIu32"" +pci_nvme_identify_ns_ind(uint32_t nsid) "nsid %"PRIu32"" pci_nvme_identify_ctrl_list(uint8_t cns, uint16_t cntid) "cns 0x%"PRIx8" cntid %"PRIu16"" pci_nvme_identify_pri_ctrl_cap(uint16_t cntlid) "identify primary controller capabilities cntlid=%"PRIu16"" pci_nvme_identify_sec_ctrl_list(uint16_t cntlid, uint8_t numcntl) "identify secondary controller list cntlid=%"PRIu16" numcntl=%"PRIu8"" diff --git a/hw/pci-bridge/cxl_downstream.c b/hw/pci-bridge/cxl_downstream.c index 4b42984360..c347ac06f3 100644 --- a/hw/pci-bridge/cxl_downstream.c +++ b/hw/pci-bridge/cxl_downstream.c @@ -13,6 +13,8 @@ #include "hw/pci/msi.h" #include "hw/pci/pcie.h" #include "hw/pci/pcie_port.h" +#include "hw/qdev-properties.h" +#include "hw/qdev-properties-system.h" #include "hw/cxl/cxl.h" #include "qapi/error.h" @@ -210,24 +212,20 @@ static void cxl_dsp_exitfn(PCIDevice *d) pci_bridge_exitfn(d); } -static void cxl_dsp_instance_post_init(Object *obj) -{ - PCIESlot *s = PCIE_SLOT(obj); - - if (!s->speed) { - s->speed = QEMU_PCI_EXP_LNK_2_5GT; - } - - if (!s->width) { - s->width = QEMU_PCI_EXP_LNK_X1; - } -} +static Property cxl_dsp_props[] = { + DEFINE_PROP_PCIE_LINK_SPEED("x-speed", PCIESlot, + speed, PCIE_LINK_SPEED_64), + DEFINE_PROP_PCIE_LINK_WIDTH("x-width", PCIESlot, + width, PCIE_LINK_WIDTH_16), + DEFINE_PROP_END_OF_LIST() +}; static void cxl_dsp_class_init(ObjectClass *oc, void *data) { DeviceClass *dc = DEVICE_CLASS(oc); PCIDeviceClass *k = PCI_DEVICE_CLASS(oc); + device_class_set_props(dc, cxl_dsp_props); k->config_write = cxl_dsp_config_write; k->realize = cxl_dsp_realize; k->exit = cxl_dsp_exitfn; @@ -243,7 +241,6 @@ static const TypeInfo cxl_dsp_info = { .name = TYPE_CXL_DSP, .instance_size = sizeof(CXLDownstreamPort), .parent = TYPE_PCIE_SLOT, - .instance_post_init = cxl_dsp_instance_post_init, .class_init = cxl_dsp_class_init, .interfaces = (InterfaceInfo[]) { { INTERFACE_PCIE_DEVICE }, diff --git a/hw/pci-bridge/cxl_root_port.c b/hw/pci-bridge/cxl_root_port.c index 2dd10239bd..5e2156d7ba 100644 --- a/hw/pci-bridge/cxl_root_port.c +++ b/hw/pci-bridge/cxl_root_port.c @@ -24,6 +24,7 @@ #include "hw/pci/pcie_port.h" #include "hw/pci/msi.h" #include "hw/qdev-properties.h" +#include "hw/qdev-properties-system.h" #include "hw/sysbus.h" #include "qapi/error.h" #include "hw/cxl/cxl.h" @@ -206,6 +207,10 @@ static Property gen_rp_props[] = { -1), DEFINE_PROP_SIZE("pref64-reserve", CXLRootPort, res_reserve.mem_pref_64, -1), + DEFINE_PROP_PCIE_LINK_SPEED("x-speed", PCIESlot, + speed, PCIE_LINK_SPEED_64), + DEFINE_PROP_PCIE_LINK_WIDTH("x-width", PCIESlot, + width, PCIE_LINK_WIDTH_32), DEFINE_PROP_END_OF_LIST() }; diff --git a/hw/pci-bridge/cxl_upstream.c b/hw/pci-bridge/cxl_upstream.c index a5a39cc524..55f8b0053f 100644 --- a/hw/pci-bridge/cxl_upstream.c +++ b/hw/pci-bridge/cxl_upstream.c @@ -11,6 +11,7 @@ #include "qemu/osdep.h" #include "qemu/log.h" #include "hw/qdev-properties.h" +#include "hw/qdev-properties-system.h" #include "hw/pci/msi.h" #include "hw/pci/pcie.h" #include "hw/pci/pcie_port.h" @@ -100,6 +101,7 @@ static void cxl_usp_reset(DeviceState *qdev) pci_bridge_reset(qdev); pcie_cap_deverr_reset(d); + pcie_cap_fill_link_ep_usp(d, usp->width, usp->speed); latch_registers(usp); } @@ -363,6 +365,10 @@ static void cxl_usp_exitfn(PCIDevice *d) static Property cxl_upstream_props[] = { DEFINE_PROP_UINT64("sn", CXLUpstreamPort, sn, UI64_NULL), DEFINE_PROP_STRING("cdat", CXLUpstreamPort, cxl_cstate.cdat.filename), + DEFINE_PROP_PCIE_LINK_SPEED("x-speed", CXLUpstreamPort, + speed, PCIE_LINK_SPEED_32), + DEFINE_PROP_PCIE_LINK_WIDTH("x-width", CXLUpstreamPort, + width, PCIE_LINK_WIDTH_16), DEFINE_PROP_END_OF_LIST() }; diff --git a/hw/pci-bridge/pci_expander_bridge.c b/hw/pci-bridge/pci_expander_bridge.c index dfaea6cbf4..07d411cff5 100644 --- a/hw/pci-bridge/pci_expander_bridge.c +++ b/hw/pci-bridge/pci_expander_bridge.c @@ -38,7 +38,6 @@ DECLARE_INSTANCE_CHECKER(PXBBus, PXB_BUS, DECLARE_INSTANCE_CHECKER(PXBBus, PXB_PCIE_BUS, TYPE_PXB_PCIE_BUS) -#define TYPE_PXB_CXL_BUS "pxb-cxl-bus" DECLARE_INSTANCE_CHECKER(PXBBus, PXB_CXL_BUS, TYPE_PXB_CXL_BUS) @@ -85,12 +84,25 @@ static uint16_t pxb_bus_numa_node(PCIBus *bus) return pxb->numa_node; } +static void prop_pxb_uid_get(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + uint32_t uid = pci_bus_num(PCI_BUS(obj)); + + visit_type_uint32(v, name, &uid, errp); +} + static void pxb_bus_class_init(ObjectClass *class, void *data) { PCIBusClass *pbc = PCI_BUS_CLASS(class); pbc->bus_num = pxb_bus_num; pbc->numa_node = pxb_bus_numa_node; + + object_class_property_add(class, "acpi_uid", "uint32", + prop_pxb_uid_get, NULL, NULL, NULL); + object_class_property_set_description(class, "acpi_uid", + "ACPI Unique ID used to distinguish this PCI Host Bridge / ACPI00016"); } static const TypeInfo pxb_bus_info = { @@ -318,7 +330,7 @@ static gint pxb_compare(gconstpointer a, gconstpointer b) 0; } -static void pxb_dev_realize_common(PCIDevice *dev, enum BusType type, +static bool pxb_dev_realize_common(PCIDevice *dev, enum BusType type, Error **errp) { PXBDev *pxb = PXB_DEV(dev); @@ -330,13 +342,13 @@ static void pxb_dev_realize_common(PCIDevice *dev, enum BusType type, if (ms->numa_state == NULL) { error_setg(errp, "NUMA is not supported by this machine-type"); - return; + return false; } if (pxb->numa_node != NUMA_NODE_UNASSIGNED && pxb->numa_node >= ms->numa_state->num_nodes) { error_setg(errp, "Illegal numa node %d", pxb->numa_node); - return; + return false; } if (dev->qdev.id && *dev->qdev.id) { @@ -382,12 +394,13 @@ static void pxb_dev_realize_common(PCIDevice *dev, enum BusType type, pci_config_set_class(dev->config, PCI_CLASS_BRIDGE_HOST); pxb_dev_list = g_list_insert_sorted(pxb_dev_list, pxb, pxb_compare); - return; + return true; err_register_bus: object_unref(OBJECT(bds)); object_unparent(OBJECT(bus)); object_unref(OBJECT(ds)); + return false; } static void pxb_dev_realize(PCIDevice *dev, Error **errp) @@ -488,7 +501,9 @@ static void pxb_cxl_dev_realize(PCIDevice *dev, Error **errp) return; } - pxb_dev_realize_common(dev, CXL, errp); + if (!pxb_dev_realize_common(dev, CXL, errp)) { + return; + } pxb_cxl_dev_reset(DEVICE(dev)); } diff --git a/hw/pci-host/gpex-acpi.c b/hw/pci-host/gpex-acpi.c index 391fabb8a8..e8b4c64c5f 100644 --- a/hw/pci-host/gpex-acpi.c +++ b/hw/pci-host/gpex-acpi.c @@ -141,6 +141,7 @@ void acpi_dsdt_add_gpex(Aml *scope, struct GPEXConfig *cfg) QLIST_FOREACH(bus, &bus->child, sibling) { uint8_t bus_num = pci_bus_num(bus); uint8_t numa_node = pci_bus_numa_node(bus); + uint32_t uid; bool is_cxl = pci_bus_is_cxl(bus); if (!pci_bus_is_root(bus)) { @@ -156,6 +157,8 @@ void acpi_dsdt_add_gpex(Aml *scope, struct GPEXConfig *cfg) nr_pcie_buses = bus_num; } + uid = object_property_get_uint(OBJECT(bus), "acpi_uid", + &error_fatal); dev = aml_device("PC%.02X", bus_num); if (is_cxl) { struct Aml *pkg = aml_package(2); @@ -168,7 +171,7 @@ void acpi_dsdt_add_gpex(Aml *scope, struct GPEXConfig *cfg) aml_append(dev, aml_name_decl("_CID", aml_string("PNP0A03"))); } aml_append(dev, aml_name_decl("_BBN", aml_int(bus_num))); - aml_append(dev, aml_name_decl("_UID", aml_int(bus_num))); + aml_append(dev, aml_name_decl("_UID", aml_int(uid))); aml_append(dev, aml_name_decl("_STR", aml_unicode("pxb Device"))); aml_append(dev, aml_name_decl("_CCA", aml_int(1))); if (numa_node != NUMA_NODE_UNASSIGNED) { diff --git a/hw/pci/pci.c b/hw/pci/pci.c index 87da35ca9b..1416ae202c 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -67,6 +67,19 @@ static char *pcibus_get_fw_dev_path(DeviceState *dev); static void pcibus_reset_hold(Object *obj, ResetType type); static bool pcie_has_upstream_port(PCIDevice *dev); +static void prop_pci_busnr_get(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + uint8_t busnr = pci_dev_bus_num(PCI_DEVICE(obj)); + + visit_type_uint8(v, name, &busnr, errp); +} + +static const PropertyInfo prop_pci_busnr = { + .name = "busnr", + .get = prop_pci_busnr_get, +}; + static Property pci_props[] = { DEFINE_PROP_PCI_DEVFN("addr", PCIDevice, devfn, -1), DEFINE_PROP_STRING("romfile", PCIDevice, romfile), @@ -87,6 +100,9 @@ static Property pci_props[] = { QEMU_PCIE_ARI_NEXTFN_1_BITNR, false), DEFINE_PROP_SIZE32("x-max-bounce-buffer-size", PCIDevice, max_bounce_buffer_size, DEFAULT_MAX_BOUNCE_BUFFER_SIZE), + DEFINE_PROP_BIT("x-pcie-ext-tag", PCIDevice, cap_present, + QEMU_PCIE_EXT_TAG_BITNR, true), + { .name = "busnr", .info = &prop_pci_busnr }, DEFINE_PROP_END_OF_LIST() }; diff --git a/hw/pci/pci_bridge.c b/hw/pci/pci_bridge.c index 6a4e38856d..2c7bb1a525 100644 --- a/hw/pci/pci_bridge.c +++ b/hw/pci/pci_bridge.c @@ -380,9 +380,12 @@ void pci_bridge_initfn(PCIDevice *dev, const char *typename) sec_bus->map_irq = br->map_irq ? br->map_irq : pci_swizzle_map_irq_fn; sec_bus->address_space_mem = &br->address_space_mem; memory_region_init(&br->address_space_mem, OBJECT(br), "pci_bridge_pci", UINT64_MAX); + address_space_init(&br->as_mem, &br->address_space_mem, + "pci_bridge_pci_mem"); sec_bus->address_space_io = &br->address_space_io; memory_region_init(&br->address_space_io, OBJECT(br), "pci_bridge_io", 4 * GiB); + address_space_init(&br->as_io, &br->address_space_io, "pci_bridge_pci_io"); pci_bridge_region_init(br); QLIST_INIT(&sec_bus->child); QLIST_INSERT_HEAD(&parent->child, sec_bus, sibling); @@ -399,6 +402,8 @@ void pci_bridge_exitfn(PCIDevice *pci_dev) PCIBridge *s = PCI_BRIDGE(pci_dev); assert(QLIST_EMPTY(&s->sec_bus.child)); QLIST_REMOVE(&s->sec_bus, sibling); + address_space_destroy(&s->as_mem); + address_space_destroy(&s->as_io); pci_bridge_region_del(s, &s->windows); pci_bridge_region_cleanup(s, &s->windows); /* object_unparent() is called automatically during device deletion */ diff --git a/hw/pci/pcie.c b/hw/pci/pcie.c index 4b2f0805c6..0b455c8654 100644 --- a/hw/pci/pcie.c +++ b/hw/pci/pcie.c @@ -86,7 +86,13 @@ pcie_cap_v1_fill(PCIDevice *dev, uint8_t port, uint8_t type, uint8_t version) * Specification, Revision 1.1., or subsequent PCI Express Base * Specification revisions. */ - pci_set_long(exp_cap + PCI_EXP_DEVCAP, PCI_EXP_DEVCAP_RBER); + uint32_t devcap = PCI_EXP_DEVCAP_RBER; + + if (dev->cap_present & QEMU_PCIE_EXT_TAG) { + devcap = PCI_EXP_DEVCAP_RBER | PCI_EXP_DEVCAP_EXT_TAG; + } + + pci_set_long(exp_cap + PCI_EXP_DEVCAP, devcap); pci_set_long(exp_cap + PCI_EXP_LNKCAP, (port << PCI_EXP_LNKCAP_PN_SHIFT) | @@ -105,46 +111,18 @@ pcie_cap_v1_fill(PCIDevice *dev, uint8_t port, uint8_t type, uint8_t version) pci_set_word(cmask + PCI_EXP_LNKSTA, 0); } -static void pcie_cap_fill_slot_lnk(PCIDevice *dev) +/* Includes setting the target speed default */ +static void pcie_cap_fill_lnk(uint8_t *exp_cap, PCIExpLinkWidth width, + PCIExpLinkSpeed speed) { - PCIESlot *s = (PCIESlot *)object_dynamic_cast(OBJECT(dev), TYPE_PCIE_SLOT); - uint8_t *exp_cap = dev->config + dev->exp.exp_cap; - - /* Skip anything that isn't a PCIESlot */ - if (!s) { - return; - } - /* Clear and fill LNKCAP from what was configured above */ pci_long_test_and_clear_mask(exp_cap + PCI_EXP_LNKCAP, PCI_EXP_LNKCAP_MLW | PCI_EXP_LNKCAP_SLS); pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP, - QEMU_PCI_EXP_LNKCAP_MLW(s->width) | - QEMU_PCI_EXP_LNKCAP_MLS(s->speed)); - - /* - * Link bandwidth notification is required for all root ports and - * downstream ports supporting links wider than x1 or multiple link - * speeds. - */ - if (s->width > QEMU_PCI_EXP_LNK_X1 || - s->speed > QEMU_PCI_EXP_LNK_2_5GT) { - pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP, - PCI_EXP_LNKCAP_LBNC); - } - - if (s->speed > QEMU_PCI_EXP_LNK_2_5GT) { - /* - * Hot-plug capable downstream ports and downstream ports supporting - * link speeds greater than 5GT/s must hardwire PCI_EXP_LNKCAP_DLLLARC - * to 1b. PCI_EXP_LNKCAP_DLLLARC implies PCI_EXP_LNKSTA_DLLLA, which - * we also hardwire to 1b here. 2.5GT/s hot-plug slots should also - * technically implement this, but it's not done here for compatibility. - */ - pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP, - PCI_EXP_LNKCAP_DLLLARC); - /* the PCI_EXP_LNKSTA_DLLLA will be set in the hotplug function */ + QEMU_PCI_EXP_LNKCAP_MLW(width) | + QEMU_PCI_EXP_LNKCAP_MLS(speed)); + if (speed > QEMU_PCI_EXP_LNK_2_5GT) { /* * Target Link Speed defaults to the highest link speed supported by * the component. 2.5GT/s devices are permitted to hardwire to zero. @@ -152,7 +130,7 @@ static void pcie_cap_fill_slot_lnk(PCIDevice *dev) pci_word_test_and_clear_mask(exp_cap + PCI_EXP_LNKCTL2, PCI_EXP_LNKCTL2_TLS); pci_word_test_and_set_mask(exp_cap + PCI_EXP_LNKCTL2, - QEMU_PCI_EXP_LNKCAP_MLS(s->speed) & + QEMU_PCI_EXP_LNKCAP_MLS(speed) & PCI_EXP_LNKCTL2_TLS); } @@ -161,27 +139,82 @@ static void pcie_cap_fill_slot_lnk(PCIDevice *dev) * actually a reference to the highest bit supported in this register. * We assume the device supports all link speeds. */ - if (s->speed > QEMU_PCI_EXP_LNK_5GT) { + if (speed > QEMU_PCI_EXP_LNK_5GT) { pci_long_test_and_clear_mask(exp_cap + PCI_EXP_LNKCAP2, ~0U); pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP2, PCI_EXP_LNKCAP2_SLS_2_5GB | PCI_EXP_LNKCAP2_SLS_5_0GB | PCI_EXP_LNKCAP2_SLS_8_0GB); - if (s->speed > QEMU_PCI_EXP_LNK_8GT) { + if (speed > QEMU_PCI_EXP_LNK_8GT) { pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP2, PCI_EXP_LNKCAP2_SLS_16_0GB); } - if (s->speed > QEMU_PCI_EXP_LNK_16GT) { + if (speed > QEMU_PCI_EXP_LNK_16GT) { pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP2, PCI_EXP_LNKCAP2_SLS_32_0GB); } - if (s->speed > QEMU_PCI_EXP_LNK_32GT) { + if (speed > QEMU_PCI_EXP_LNK_32GT) { pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP2, PCI_EXP_LNKCAP2_SLS_64_0GB); } } } +void pcie_cap_fill_link_ep_usp(PCIDevice *dev, PCIExpLinkWidth width, + PCIExpLinkSpeed speed) +{ + uint8_t *exp_cap = dev->config + dev->exp.exp_cap; + + /* + * For an end point or USP need to set the current status as well + * as the capabilities. + */ + pci_long_test_and_clear_mask(exp_cap + PCI_EXP_LNKSTA, + PCI_EXP_LNKSTA_CLS | PCI_EXP_LNKSTA_NLW); + pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKSTA, + QEMU_PCI_EXP_LNKSTA_NLW(width) | + QEMU_PCI_EXP_LNKSTA_CLS(speed)); + + pcie_cap_fill_lnk(exp_cap, width, speed); +} + +static void pcie_cap_fill_slot_lnk(PCIDevice *dev) +{ + PCIESlot *s = (PCIESlot *)object_dynamic_cast(OBJECT(dev), TYPE_PCIE_SLOT); + uint8_t *exp_cap = dev->config + dev->exp.exp_cap; + + /* Skip anything that isn't a PCIESlot */ + if (!s) { + return; + } + + /* + * Link bandwidth notification is required for all root ports and + * downstream ports supporting links wider than x1 or multiple link + * speeds. + */ + if (s->width > QEMU_PCI_EXP_LNK_X1 || + s->speed > QEMU_PCI_EXP_LNK_2_5GT) { + pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP, + PCI_EXP_LNKCAP_LBNC); + } + + if (s->speed > QEMU_PCI_EXP_LNK_2_5GT) { + /* + * Hot-plug capable downstream ports and downstream ports supporting + * link speeds greater than 5GT/s must hardwire PCI_EXP_LNKCAP_DLLLARC + * to 1b. PCI_EXP_LNKCAP_DLLLARC implies PCI_EXP_LNKSTA_DLLLA, which + * we also hardwire to 1b here. 2.5GT/s hot-plug slots should also + * technically implement this, but it's not done here for compatibility. + */ + pci_long_test_and_set_mask(exp_cap + PCI_EXP_LNKCAP, + PCI_EXP_LNKCAP_DLLLARC); + /* the PCI_EXP_LNKSTA_DLLLA will be set in the hotplug function */ + } + + pcie_cap_fill_lnk(exp_cap, s->width, s->speed); +} + int pcie_cap_init(PCIDevice *dev, uint8_t offset, uint8_t type, uint8_t port, Error **errp) diff --git a/hw/ppc/e500.c b/hw/ppc/e500.c index b760c6d6a2..6433348072 100644 --- a/hw/ppc/e500.c +++ b/hw/ppc/e500.c @@ -721,11 +721,21 @@ static int ppce500_prep_device_tree(PPCE500MachineState *machine, kernel_base, kernel_size, true); } -hwaddr booke206_page_size_to_tlb(uint64_t size) +static hwaddr booke206_page_size_to_tlb(uint64_t size) { return 63 - clz64(size / KiB); } +void booke206_set_tlb(ppcmas_tlb_t *tlb, target_ulong va, hwaddr pa, + hwaddr len) +{ + tlb->mas1 = booke206_page_size_to_tlb(len) << MAS1_TSIZE_SHIFT; + tlb->mas1 |= MAS1_VALID; + tlb->mas2 = va & TARGET_PAGE_MASK; + tlb->mas7_3 = pa & TARGET_PAGE_MASK; + tlb->mas7_3 |= MAS3_UR | MAS3_UW | MAS3_UX | MAS3_SR | MAS3_SW | MAS3_SX; +} + static int booke206_initial_map_tsize(CPUPPCState *env) { struct boot_info *bi = env->load_info; @@ -751,25 +761,6 @@ static uint64_t mmubooke_initial_mapsize(CPUPPCState *env) return (1ULL << 10 << tsize); } -/* Create -kernel TLB entries for BookE. */ -static void mmubooke_create_initial_mapping(CPUPPCState *env) -{ - ppcmas_tlb_t *tlb = booke206_get_tlbm(env, 1, 0, 0); - hwaddr size; - int ps; - - ps = booke206_initial_map_tsize(env); - size = (ps << MAS1_TSIZE_SHIFT); - tlb->mas1 = MAS1_VALID | size; - tlb->mas2 = 0; - tlb->mas7_3 = 0; - tlb->mas7_3 |= MAS3_UR | MAS3_UW | MAS3_UX | MAS3_SR | MAS3_SW | MAS3_SX; - -#ifdef CONFIG_KVM - env->tlb_dirty = true; -#endif -} - static void ppce500_cpu_reset_sec(void *opaque) { PowerPCCPU *cpu = opaque; @@ -786,6 +777,8 @@ static void ppce500_cpu_reset(void *opaque) CPUState *cs = CPU(cpu); CPUPPCState *env = &cpu->env; struct boot_info *bi = env->load_info; + uint64_t map_size = mmubooke_initial_mapsize(env); + ppcmas_tlb_t *tlb = booke206_get_tlbm(env, 1, 0, 0); cpu_reset(cs); @@ -796,11 +789,15 @@ static void ppce500_cpu_reset(void *opaque) env->gpr[4] = 0; env->gpr[5] = 0; env->gpr[6] = EPAPR_MAGIC; - env->gpr[7] = mmubooke_initial_mapsize(env); + env->gpr[7] = map_size; env->gpr[8] = 0; env->gpr[9] = 0; env->nip = bi->entry; - mmubooke_create_initial_mapping(env); + /* create initial mapping */ + booke206_set_tlb(tlb, 0, 0, map_size); +#ifdef CONFIG_KVM + env->tlb_dirty = true; +#endif } static DeviceState *ppce500_init_mpic_qemu(PPCE500MachineState *pms, diff --git a/hw/ppc/e500.h b/hw/ppc/e500.h index 8c09ef92e4..01db102625 100644 --- a/hw/ppc/e500.h +++ b/hw/ppc/e500.h @@ -41,8 +41,6 @@ struct PPCE500MachineClass { void ppce500_init(MachineState *machine); -hwaddr booke206_page_size_to_tlb(uint64_t size); - #define TYPE_PPCE500_MACHINE "ppce500-base-machine" OBJECT_DECLARE_TYPE(PPCE500MachineState, PPCE500MachineClass, PPCE500_MACHINE) diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c index 795acc289f..f0f0d7567d 100644 --- a/hw/ppc/pnv.c +++ b/hw/ppc/pnv.c @@ -736,21 +736,27 @@ static void pnv_reset(MachineState *machine, ResetType type) } } - fdt = pnv_dt_create(machine); - - /* Pack resulting tree */ - _FDT((fdt_pack(fdt))); + if (machine->fdt) { + fdt = machine->fdt; + } else { + fdt = pnv_dt_create(machine); + /* Pack resulting tree */ + _FDT((fdt_pack(fdt))); + } qemu_fdt_dumpdtb(fdt, fdt_totalsize(fdt)); cpu_physical_memory_write(PNV_FDT_ADDR, fdt, fdt_totalsize(fdt)); - /* - * Set machine->fdt for 'dumpdtb' QMP/HMP command. Free - * the existing machine->fdt to avoid leaking it during - * a reset. - */ - g_free(machine->fdt); - machine->fdt = fdt; + /* Update machine->fdt with latest fdt */ + if (machine->fdt != fdt) { + /* + * Set machine->fdt for 'dumpdtb' QMP/HMP command. Free + * the existing machine->fdt to avoid leaking it during + * a reset. + */ + g_free(machine->fdt); + machine->fdt = fdt; + } } static ISABus *pnv_chip_power8_isa_create(PnvChip *chip, Error **errp) @@ -952,6 +958,14 @@ static void pnv_init(MachineState *machine) g_free(sz); exit(EXIT_FAILURE); } + + /* checks for invalid option combinations */ + if (machine->dtb && (strlen(machine->kernel_cmdline) != 0)) { + error_report("-append and -dtb cannot be used together, as passed" + " command line is ignored in case of custom dtb"); + exit(EXIT_FAILURE); + } + memory_region_add_subregion(get_system_memory(), 0, machine->ram); /* @@ -1003,6 +1017,21 @@ static void pnv_init(MachineState *machine) } } + /* load dtb if passed */ + if (machine->dtb) { + int fdt_size; + + warn_report("with manually passed dtb, some options like '-append'" + " will get ignored and the dtb passed will be used as-is"); + + /* read the file 'machine->dtb', and load it into 'fdt' buffer */ + machine->fdt = load_device_tree(machine->dtb, &fdt_size); + if (!machine->fdt) { + error_report("Could not load dtb '%s'", machine->dtb); + exit(1); + } + } + /* MSIs are supported on this platform */ msi_nonbroken = true; diff --git a/hw/ppc/pnv_adu.c b/hw/ppc/pnv_adu.c index 81b7d6e526..f636dedf79 100644 --- a/hw/ppc/pnv_adu.c +++ b/hw/ppc/pnv_adu.c @@ -116,6 +116,12 @@ static void pnv_adu_xscom_write(void *opaque, hwaddr addr, uint64_t val, uint32_t lpc_size = lpc_cmd_size(adu); uint64_t data = 0; + if (!is_power_of_2(lpc_size) || lpc_size > sizeof(data)) { + qemu_log_mask(LOG_GUEST_ERROR, "ADU: Unsupported LPC access " + "size:%" PRId32 "\n", lpc_size); + break; + } + pnv_lpc_opb_read(adu->lpc, lpc_addr, (void *)&data, lpc_size); /* @@ -135,6 +141,12 @@ static void pnv_adu_xscom_write(void *opaque, hwaddr addr, uint64_t val, uint32_t lpc_size = lpc_cmd_size(adu); uint64_t data; + if (!is_power_of_2(lpc_size) || lpc_size > sizeof(data)) { + qemu_log_mask(LOG_GUEST_ERROR, "ADU: Unsupported LPC access " + "size:%" PRId32 "\n", lpc_size); + break; + } + data = cpu_to_be64(val) >> ((lpc_addr & 7) * 8); /* See above */ pnv_lpc_opb_write(adu->lpc, lpc_addr, (void *)&data, lpc_size); } diff --git a/hw/ppc/pnv_lpc.c b/hw/ppc/pnv_lpc.c index f8aad955b5..8c203d2059 100644 --- a/hw/ppc/pnv_lpc.c +++ b/hw/ppc/pnv_lpc.c @@ -427,21 +427,27 @@ static void pnv_lpc_eval_serirq_routes(PnvLpcController *lpc) int irq; if (!lpc->psi_has_serirq) { - if ((lpc->opb_irq_route0 & PPC_BITMASK(8, 13)) || - (lpc->opb_irq_route1 & PPC_BITMASK(4, 31))) { + if ((lpc->opb_irq_route0 & PPC_BITMASK32(8, 13)) || + (lpc->opb_irq_route1 & PPC_BITMASK32(4, 31))) { qemu_log_mask(LOG_GUEST_ERROR, "OPB: setting serirq routing on POWER8 system, ignoring.\n"); } return; } + /* + * Each of the ISA irqs is routed to one of the 4 SERIRQ irqs with 2 + * bits, split across 2 OPB registers. + */ for (irq = 0; irq <= 13; irq++) { - int serirq = (lpc->opb_irq_route1 >> (31 - 5 - (irq * 2))) & 0x3; + int serirq = extract32(lpc->opb_irq_route1, + PPC_BIT32_NR(5 + irq * 2), 2); lpc->irq_to_serirq_route[irq] = serirq; } for (irq = 14; irq < ISA_NUM_IRQS; irq++) { - int serirq = (lpc->opb_irq_route0 >> (31 - 9 - (irq * 2))) & 0x3; + int serirq = extract32(lpc->opb_irq_route0, + PPC_BIT32_NR(9 + (irq - 14) * 2), 2); lpc->irq_to_serirq_route[irq] = serirq; } } diff --git a/hw/ppc/ppc.c b/hw/ppc/ppc.c index fde4619412..b86b5847de 100644 --- a/hw/ppc/ppc.c +++ b/hw/ppc/ppc.c @@ -728,7 +728,9 @@ static inline int64_t __cpu_ppc_load_decr(CPUPPCState *env, int64_t now, int64_t decr; n = ns_to_tb(tb_env->decr_freq, now); - if (next > n && tb_env->flags & PPC_TIMER_BOOKE) { + + /* BookE timers stop when reaching 0. */ + if (next < n && tb_env->flags & PPC_TIMER_BOOKE) { decr = 0; } else { decr = next - n; diff --git a/hw/ppc/ppc440_bamboo.c b/hw/ppc/ppc440_bamboo.c index 96d9ce65c2..a55f108434 100644 --- a/hw/ppc/ppc440_bamboo.c +++ b/hw/ppc/ppc440_bamboo.c @@ -110,29 +110,6 @@ static int bamboo_load_device_tree(MachineState *machine, return 0; } -/* Create reset TLB entries for BookE, spanning the 32bit addr space. */ -static void mmubooke_create_initial_mapping(CPUPPCState *env, - target_ulong va, - hwaddr pa) -{ - ppcemb_tlb_t *tlb = &env->tlb.tlbe[0]; - - tlb->attr = 0; - tlb->prot = PAGE_VALID | ((PAGE_READ | PAGE_WRITE | PAGE_EXEC) << 4); - tlb->size = 1U << 31; /* up to 0x80000000 */ - tlb->EPN = va & TARGET_PAGE_MASK; - tlb->RPN = pa & TARGET_PAGE_MASK; - tlb->PID = 0; - - tlb = &env->tlb.tlbe[1]; - tlb->attr = 0; - tlb->prot = PAGE_VALID | ((PAGE_READ | PAGE_WRITE | PAGE_EXEC) << 4); - tlb->size = 1U << 31; /* up to 0xffffffff */ - tlb->EPN = 0x80000000 & TARGET_PAGE_MASK; - tlb->RPN = 0x80000000 & TARGET_PAGE_MASK; - tlb->PID = 0; -} - static void main_cpu_reset(void *opaque) { PowerPCCPU *cpu = opaque; @@ -143,8 +120,9 @@ static void main_cpu_reset(void *opaque) env->gpr[3] = FDT_ADDR; env->nip = entry; - /* Create a mapping for the kernel. */ - mmubooke_create_initial_mapping(env, 0, 0); + /* Create a mapping spanning the 32bit addr space. */ + booke_set_tlb(&env->tlb.tlbe[0], 0, 0, 1U << 31); + booke_set_tlb(&env->tlb.tlbe[1], 0x80000000, 0x80000000, 1U << 31); } static void bamboo_init(MachineState *machine) diff --git a/hw/ppc/ppc_booke.c b/hw/ppc/ppc_booke.c index ca22da196a..c8849e66ff 100644 --- a/hw/ppc/ppc_booke.c +++ b/hw/ppc/ppc_booke.c @@ -31,6 +31,16 @@ #include "hw/loader.h" #include "kvm_ppc.h" +void booke_set_tlb(ppcemb_tlb_t *tlb, target_ulong va, hwaddr pa, + target_ulong size) +{ + tlb->attr = 0; + tlb->prot = PAGE_RWX << 4 | PAGE_VALID; + tlb->size = size; + tlb->EPN = va & TARGET_PAGE_MASK; + tlb->RPN = pa & TARGET_PAGE_MASK; + tlb->PID = 0; +} /* Timer Control Register */ diff --git a/hw/ppc/ppce500_spin.c b/hw/ppc/ppce500_spin.c index e08739a443..93b16320d4 100644 --- a/hw/ppc/ppce500_spin.c +++ b/hw/ppc/ppce500_spin.c @@ -33,6 +33,7 @@ #include "hw/hw.h" #include "hw/sysbus.h" #include "sysemu/hw_accel.h" +#include "hw/ppc/ppc.h" #include "e500.h" #include "qom/object.h" @@ -70,30 +71,12 @@ static void spin_reset(DeviceState *dev) } } -static void mmubooke_create_initial_mapping(CPUPPCState *env, - target_ulong va, - hwaddr pa, - hwaddr len) -{ - ppcmas_tlb_t *tlb = booke206_get_tlbm(env, 1, 0, 1); - hwaddr size; - - size = (booke206_page_size_to_tlb(len) << MAS1_TSIZE_SHIFT); - tlb->mas1 = MAS1_VALID | size; - tlb->mas2 = (va & TARGET_PAGE_MASK) | MAS2_M; - tlb->mas7_3 = pa & TARGET_PAGE_MASK; - tlb->mas7_3 |= MAS3_UR | MAS3_UW | MAS3_UX | MAS3_SR | MAS3_SW | MAS3_SX; -#ifdef CONFIG_KVM - env->tlb_dirty = true; -#endif -} - static void spin_kick(CPUState *cs, run_on_cpu_data data) { CPUPPCState *env = cpu_env(cs); SpinInfo *curspin = data.host_ptr; - hwaddr map_size = 64 * MiB; - hwaddr map_start; + hwaddr map_start, map_size = 64 * MiB; + ppcmas_tlb_t *tlb = booke206_get_tlbm(env, 1, 0, 1); cpu_synchronize_state(cs); stl_p(&curspin->pir, env->spr[SPR_BOOKE_PIR]); @@ -107,7 +90,12 @@ static void spin_kick(CPUState *cs, run_on_cpu_data data) env->gpr[9] = 0; map_start = ldq_p(&curspin->addr) & ~(map_size - 1); - mmubooke_create_initial_mapping(env, 0, map_start, map_size); + /* create initial mapping */ + booke206_set_tlb(tlb, 0, map_start, map_size); + tlb->mas2 |= MAS2_M; +#ifdef CONFIG_KVM + env->tlb_dirty = true; +#endif cs->halted = 0; cs->exception_index = -1; diff --git a/hw/ppc/sam460ex.c b/hw/ppc/sam460ex.c index 1fce093ac8..78e2a46e75 100644 --- a/hw/ppc/sam460ex.c +++ b/hw/ppc/sam460ex.c @@ -213,38 +213,6 @@ static int sam460ex_load_device_tree(MachineState *machine, return fdt_size; } -/* Create reset TLB entries for BookE, mapping only the flash memory. */ -static void mmubooke_create_initial_mapping_uboot(CPUPPCState *env) -{ - ppcemb_tlb_t *tlb = &env->tlb.tlbe[0]; - - /* on reset the flash is mapped by a shadow TLB, - * but since we don't implement them we need to use - * the same values U-Boot will use to avoid a fault. - */ - tlb->attr = 0; - tlb->prot = PAGE_VALID | ((PAGE_READ | PAGE_WRITE | PAGE_EXEC) << 4); - tlb->size = 0x10000000; /* up to 0xffffffff */ - tlb->EPN = 0xf0000000 & TARGET_PAGE_MASK; - tlb->RPN = (0xf0000000 & TARGET_PAGE_MASK) | 0x4; - tlb->PID = 0; -} - -/* Create reset TLB entries for BookE, spanning the 32bit addr space. */ -static void mmubooke_create_initial_mapping(CPUPPCState *env, - target_ulong va, - hwaddr pa) -{ - ppcemb_tlb_t *tlb = &env->tlb.tlbe[0]; - - tlb->attr = 0; - tlb->prot = PAGE_VALID | ((PAGE_READ | PAGE_WRITE | PAGE_EXEC) << 4); - tlb->size = 1 << 31; /* up to 0x80000000 */ - tlb->EPN = va & TARGET_PAGE_MASK; - tlb->RPN = pa & TARGET_PAGE_MASK; - tlb->PID = 0; -} - static void main_cpu_reset(void *opaque) { PowerPCCPU *cpu = opaque; @@ -253,20 +221,27 @@ static void main_cpu_reset(void *opaque) cpu_reset(CPU(cpu)); - /* either we have a kernel to boot or we jump to U-Boot */ + /* + * On reset the flash is mapped by a shadow TLB, but since we + * don't implement them we need to use the same values U-Boot + * will use to avoid a fault. + * either we have a kernel to boot or we jump to U-Boot + */ if (bi->entry != UBOOT_ENTRY) { env->gpr[1] = (16 * MiB) - 8; env->gpr[3] = FDT_ADDR; env->nip = bi->entry; /* Create a mapping for the kernel. */ - mmubooke_create_initial_mapping(env, 0, 0); + booke_set_tlb(&env->tlb.tlbe[0], 0, 0, 1 << 31); env->gpr[6] = tswap32(EPAPR_MAGIC); env->gpr[7] = (16 * MiB) - 8; /* bi->ima_size; */ } else { env->nip = UBOOT_ENTRY; - mmubooke_create_initial_mapping_uboot(env); + /* Create a mapping for U-Boot. */ + booke_set_tlb(&env->tlb.tlbe[0], 0xf0000000, 0xf0000000, 0x10000000); + env->tlb.tlbe[0].RPN |= 4; } } diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index 2c10a70a48..5c02037c56 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -132,61 +132,6 @@ static bool spapr_is_thread0_in_vcore(SpaprMachineState *spapr, return spapr_get_vcpu_id(cpu) % spapr->vsmt == 0; } -static bool pre_2_10_vmstate_dummy_icp_needed(void *opaque) -{ - /* Dummy entries correspond to unused ICPState objects in older QEMUs, - * and newer QEMUs don't even have them. In both cases, we don't want - * to send anything on the wire. - */ - return false; -} - -static const VMStateDescription pre_2_10_vmstate_dummy_icp = { - /* - * Hack ahead. We can't have two devices with the same name and - * instance id. So I rename this to pass make check. - * Real help from people who knows the hardware is needed. - */ - .name = "icp/server", - .version_id = 1, - .minimum_version_id = 1, - .needed = pre_2_10_vmstate_dummy_icp_needed, - .fields = (const VMStateField[]) { - VMSTATE_UNUSED(4), /* uint32_t xirr */ - VMSTATE_UNUSED(1), /* uint8_t pending_priority */ - VMSTATE_UNUSED(1), /* uint8_t mfrr */ - VMSTATE_END_OF_LIST() - }, -}; - -/* - * See comment in hw/intc/xics.c:icp_realize() - * - * You have to remove vmstate_replace_hack_for_ppc() when you remove - * the machine types that need the following function. - */ -static void pre_2_10_vmstate_register_dummy_icp(int i) -{ - vmstate_register(NULL, i, &pre_2_10_vmstate_dummy_icp, - (void *)(uintptr_t) i); -} - -/* - * See comment in hw/intc/xics.c:icp_realize() - * - * You have to remove vmstate_replace_hack_for_ppc() when you remove - * the machine types that need the following function. - */ -static void pre_2_10_vmstate_unregister_dummy_icp(int i) -{ - /* - * This used to be: - * - * vmstate_unregister(NULL, &pre_2_10_vmstate_dummy_icp, - * (void *)(uintptr_t) i); - */ -} - int spapr_max_server_number(SpaprMachineState *spapr) { MachineState *ms = MACHINE(spapr); @@ -682,7 +627,6 @@ static int spapr_dt_dynamic_reconfiguration_memory(SpaprMachineState *spapr, static int spapr_dt_memory(SpaprMachineState *spapr, void *fdt) { MachineState *machine = MACHINE(spapr); - SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr); hwaddr mem_start, node_size; int i, nb_nodes = machine->numa_state->num_nodes; NodeInfo *nodes = machine->numa_state->nodes; @@ -724,7 +668,6 @@ static int spapr_dt_memory(SpaprMachineState *spapr, void *fdt) if (spapr_ovec_test(spapr->ov5_cas, OV5_DRCONF_MEMORY)) { int ret; - g_assert(smc->dr_lmb_enabled); ret = spapr_dt_dynamic_reconfiguration_memory(spapr, fdt); if (ret) { return ret; @@ -1307,9 +1250,7 @@ void *spapr_build_fdt(SpaprMachineState *spapr, bool reset, size_t space) spapr_dt_cpus(fdt, spapr); /* ibm,drc-indexes and friends */ - if (smc->dr_lmb_enabled) { - root_drc_type_mask |= SPAPR_DR_CONNECTOR_TYPE_LMB; - } + root_drc_type_mask |= SPAPR_DR_CONNECTOR_TYPE_LMB; if (smc->dr_phb_enabled) { root_drc_type_mask |= SPAPR_DR_CONNECTOR_TYPE_PHB; } @@ -2715,7 +2656,6 @@ static void spapr_init_cpus(SpaprMachineState *spapr) { MachineState *machine = MACHINE(spapr); MachineClass *mc = MACHINE_GET_CLASS(machine); - SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(machine); const char *type = spapr_get_cpu_core_type(machine->cpu_type); const CPUArchIdList *possible_cpus; unsigned int smp_cpus = machine->smp.cpus; @@ -2744,15 +2684,6 @@ static void spapr_init_cpus(SpaprMachineState *spapr) boot_cores_nr = possible_cpus->len; } - if (smc->pre_2_10_has_unused_icps) { - for (i = 0; i < spapr_max_server_number(spapr); i++) { - /* Dummy entries get deregistered when real ICPState objects - * are registered during CPU core hotplug. - */ - pre_2_10_vmstate_register_dummy_icp(i); - } - } - for (i = 0; i < possible_cpus->len; i++) { int core_id = i * smp_threads; @@ -2929,10 +2860,8 @@ static void spapr_machine_init(MachineState *machine) spapr->ov5 = spapr_ovec_new(); spapr->ov5_cas = spapr_ovec_new(); - if (smc->dr_lmb_enabled) { - spapr_ovec_set(spapr->ov5, OV5_DRCONF_MEMORY); - spapr_validate_node_memory(machine, &error_fatal); - } + spapr_ovec_set(spapr->ov5, OV5_DRCONF_MEMORY); + spapr_validate_node_memory(machine, &error_fatal); spapr_ovec_set(spapr->ov5, OV5_FORM1_AFFINITY); @@ -3016,9 +2945,7 @@ static void spapr_machine_init(MachineState *machine) machine_memory_devices_init(machine, device_mem_base, device_mem_size); } - if (smc->dr_lmb_enabled) { - spapr_create_lmb_dr_connectors(spapr); - } + spapr_create_lmb_dr_connectors(spapr); if (mc->nvdimm_supported) { spapr_create_nvdimm_dr_connectors(spapr); @@ -3078,11 +3005,7 @@ static void spapr_machine_init(MachineState *machine) } if (machine->usb) { - if (smc->use_ohci_by_default) { - pci_create_simple(phb->bus, -1, "pci-ohci"); - } else { - pci_create_simple(phb->bus, -1, "nec-usb-xhci"); - } + pci_create_simple(phb->bus, -1, "nec-usb-xhci"); if (has_vga) { USBBus *usb_bus; @@ -3662,7 +3585,6 @@ static void spapr_memory_plug(HotplugHandler *hotplug_dev, DeviceState *dev) static void spapr_memory_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { - const SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(hotplug_dev); SpaprMachineState *spapr = SPAPR_MACHINE(hotplug_dev); bool is_nvdimm = object_dynamic_cast(OBJECT(dev), TYPE_NVDIMM); PCDIMMDevice *dimm = PC_DIMM(dev); @@ -3671,11 +3593,6 @@ static void spapr_memory_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev, Object *memdev; hwaddr pagesize; - if (!smc->dr_lmb_enabled) { - error_setg(errp, "Memory hotplug not supported for this machine"); - return; - } - size = memory_device_get_region_size(MEMORY_DEVICE(dimm), &local_err); if (local_err) { error_propagate(errp, local_err); @@ -3932,21 +3849,9 @@ void spapr_core_release(DeviceState *dev) static void spapr_core_unplug(HotplugHandler *hotplug_dev, DeviceState *dev) { MachineState *ms = MACHINE(hotplug_dev); - SpaprMachineClass *smc = SPAPR_MACHINE_GET_CLASS(ms); CPUCore *cc = CPU_CORE(dev); CPUArchId *core_slot = spapr_find_cpu_slot(ms, cc->core_id, NULL); - if (smc->pre_2_10_has_unused_icps) { - SpaprCpuCore *sc = SPAPR_CPU_CORE(OBJECT(dev)); - int i; - - for (i = 0; i < cc->nr_threads; i++) { - CPUState *cs = CPU(sc->threads[i]); - - pre_2_10_vmstate_register_dummy_icp(cs->cpu_index); - } - } - assert(core_slot); core_slot->cpu = NULL; qdev_unrealize(dev); @@ -4027,7 +3932,6 @@ static void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev) { SpaprMachineState *spapr = SPAPR_MACHINE(OBJECT(hotplug_dev)); MachineClass *mc = MACHINE_GET_CLASS(spapr); - SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); SpaprCpuCore *core = SPAPR_CPU_CORE(OBJECT(dev)); CPUCore *cc = CPU_CORE(dev); SpaprDrc *drc; @@ -4077,12 +3981,6 @@ static void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev) } } - if (smc->pre_2_10_has_unused_icps) { - for (i = 0; i < cc->nr_threads; i++) { - CPUState *cs = CPU(core->threads[i]); - pre_2_10_vmstate_unregister_dummy_icp(cs->cpu_index); - } - } } static void spapr_core_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev, @@ -4713,7 +4611,6 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) hc->unplug_request = spapr_machine_device_unplug_request; hc->unplug = spapr_machine_device_unplug; - smc->dr_lmb_enabled = true; smc->update_dt_enabled = true; mc->default_cpu_type = POWERPC_CPU_TYPE_NAME("power10_v2.0"); mc->has_hotpluggable_cpus = true; @@ -4834,8 +4731,6 @@ static void spapr_machine_latest_class_options(MachineClass *mc) DEFINE_SPAPR_MACHINE_IMPL(true, major, minor) #define DEFINE_SPAPR_MACHINE(major, minor) \ DEFINE_SPAPR_MACHINE_IMPL(false, major, minor) -#define DEFINE_SPAPR_MACHINE_TAGGED(major, minor, tag) \ - DEFINE_SPAPR_MACHINE_IMPL(false, major, minor, _, tag) /* * pseries-9.2 @@ -5120,278 +5015,6 @@ static void spapr_machine_3_0_class_options(MachineClass *mc) DEFINE_SPAPR_MACHINE(3, 0); -/* - * pseries-2.12 - */ -static void spapr_machine_2_12_class_options(MachineClass *mc) -{ - SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); - static GlobalProperty compat[] = { - { TYPE_POWERPC_CPU, "pre-3.0-migration", "on" }, - { TYPE_SPAPR_CPU_CORE, "pre-3.0-migration", "on" }, - }; - - spapr_machine_3_0_class_options(mc); - compat_props_add(mc->compat_props, hw_compat_2_12, hw_compat_2_12_len); - compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); - - /* We depend on kvm_enabled() to choose a default value for the - * hpt-max-page-size capability. Of course we can't do it here - * because this is too early and the HW accelerator isn't initialized - * yet. Postpone this to machine init (see default_caps_with_cpu()). - */ - smc->default_caps.caps[SPAPR_CAP_HPT_MAXPAGESIZE] = 0; -} - -DEFINE_SPAPR_MACHINE(2, 12); - -static void spapr_machine_2_12_sxxm_class_options(MachineClass *mc) -{ - SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); - - spapr_machine_2_12_class_options(mc); - smc->default_caps.caps[SPAPR_CAP_CFPC] = SPAPR_CAP_WORKAROUND; - smc->default_caps.caps[SPAPR_CAP_SBBC] = SPAPR_CAP_WORKAROUND; - smc->default_caps.caps[SPAPR_CAP_IBS] = SPAPR_CAP_FIXED_CCD; -} - -DEFINE_SPAPR_MACHINE_TAGGED(2, 12, sxxm); - -/* - * pseries-2.11 - */ - -static void spapr_machine_2_11_class_options(MachineClass *mc) -{ - SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); - - spapr_machine_2_12_class_options(mc); - smc->default_caps.caps[SPAPR_CAP_HTM] = SPAPR_CAP_ON; - compat_props_add(mc->compat_props, hw_compat_2_11, hw_compat_2_11_len); -} - -DEFINE_SPAPR_MACHINE(2, 11); - -/* - * pseries-2.10 - */ - -static void spapr_machine_2_10_class_options(MachineClass *mc) -{ - spapr_machine_2_11_class_options(mc); - compat_props_add(mc->compat_props, hw_compat_2_10, hw_compat_2_10_len); -} - -DEFINE_SPAPR_MACHINE(2, 10); - -/* - * pseries-2.9 - */ - -static void spapr_machine_2_9_class_options(MachineClass *mc) -{ - SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); - static GlobalProperty compat[] = { - { TYPE_POWERPC_CPU, "pre-2.10-migration", "on" }, - }; - - spapr_machine_2_10_class_options(mc); - compat_props_add(mc->compat_props, hw_compat_2_9, hw_compat_2_9_len); - compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); - smc->pre_2_10_has_unused_icps = true; - smc->resize_hpt_default = SPAPR_RESIZE_HPT_DISABLED; -} - -DEFINE_SPAPR_MACHINE(2, 9); - -/* - * pseries-2.8 - */ - -static void spapr_machine_2_8_class_options(MachineClass *mc) -{ - static GlobalProperty compat[] = { - { TYPE_SPAPR_PCI_HOST_BRIDGE, "pcie-extended-configuration-space", "off" }, - }; - - spapr_machine_2_9_class_options(mc); - compat_props_add(mc->compat_props, hw_compat_2_8, hw_compat_2_8_len); - compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); - mc->numa_mem_align_shift = 23; -} - -DEFINE_SPAPR_MACHINE(2, 8); - -/* - * pseries-2.7 - */ - -static bool phb_placement_2_7(SpaprMachineState *spapr, uint32_t index, - uint64_t *buid, hwaddr *pio, - hwaddr *mmio32, hwaddr *mmio64, - unsigned n_dma, uint32_t *liobns, Error **errp) -{ - /* Legacy PHB placement for pseries-2.7 and earlier machine types */ - const uint64_t base_buid = 0x800000020000000ULL; - const hwaddr phb_spacing = 0x1000000000ULL; /* 64 GiB */ - const hwaddr mmio_offset = 0xa0000000; /* 2 GiB + 512 MiB */ - const hwaddr pio_offset = 0x80000000; /* 2 GiB */ - const uint32_t max_index = 255; - const hwaddr phb0_alignment = 0x10000000000ULL; /* 1 TiB */ - - uint64_t ram_top = MACHINE(spapr)->ram_size; - hwaddr phb0_base, phb_base; - int i; - - /* Do we have device memory? */ - if (MACHINE(spapr)->device_memory) { - /* Can't just use maxram_size, because there may be an - * alignment gap between normal and device memory regions - */ - ram_top = MACHINE(spapr)->device_memory->base + - memory_region_size(&MACHINE(spapr)->device_memory->mr); - } - - phb0_base = QEMU_ALIGN_UP(ram_top, phb0_alignment); - - if (index > max_index) { - error_setg(errp, "\"index\" for PAPR PHB is too large (max %u)", - max_index); - return false; - } - - *buid = base_buid + index; - for (i = 0; i < n_dma; ++i) { - liobns[i] = SPAPR_PCI_LIOBN(index, i); - } - - phb_base = phb0_base + index * phb_spacing; - *pio = phb_base + pio_offset; - *mmio32 = phb_base + mmio_offset; - /* - * We don't set the 64-bit MMIO window, relying on the PHB's - * fallback behaviour of automatically splitting a large "32-bit" - * window into contiguous 32-bit and 64-bit windows - */ - - return true; -} - -static void spapr_machine_2_7_class_options(MachineClass *mc) -{ - SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); - static GlobalProperty compat[] = { - { TYPE_SPAPR_PCI_HOST_BRIDGE, "mem_win_size", "0xf80000000", }, - { TYPE_SPAPR_PCI_HOST_BRIDGE, "mem64_win_size", "0", }, - { TYPE_POWERPC_CPU, "pre-2.8-migration", "on", }, - { TYPE_SPAPR_PCI_HOST_BRIDGE, "pre-2.8-migration", "on", }, - }; - - spapr_machine_2_8_class_options(mc); - mc->default_cpu_type = POWERPC_CPU_TYPE_NAME("power7_v2.3"); - mc->default_machine_opts = "modern-hotplug-events=off"; - compat_props_add(mc->compat_props, hw_compat_2_7, hw_compat_2_7_len); - compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); - smc->phb_placement = phb_placement_2_7; -} - -DEFINE_SPAPR_MACHINE(2, 7); - -/* - * pseries-2.6 - */ - -static void spapr_machine_2_6_class_options(MachineClass *mc) -{ - static GlobalProperty compat[] = { - { TYPE_SPAPR_PCI_HOST_BRIDGE, "ddw", "off" }, - }; - - spapr_machine_2_7_class_options(mc); - mc->has_hotpluggable_cpus = false; - compat_props_add(mc->compat_props, hw_compat_2_6, hw_compat_2_6_len); - compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); -} - -DEFINE_SPAPR_MACHINE(2, 6); - -/* - * pseries-2.5 - */ - -static void spapr_machine_2_5_class_options(MachineClass *mc) -{ - SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); - static GlobalProperty compat[] = { - { "spapr-vlan", "use-rx-buffer-pools", "off" }, - }; - - spapr_machine_2_6_class_options(mc); - smc->use_ohci_by_default = true; - compat_props_add(mc->compat_props, hw_compat_2_5, hw_compat_2_5_len); - compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); -} - -DEFINE_SPAPR_MACHINE(2, 5); - -/* - * pseries-2.4 - */ - -static void spapr_machine_2_4_class_options(MachineClass *mc) -{ - SpaprMachineClass *smc = SPAPR_MACHINE_CLASS(mc); - - spapr_machine_2_5_class_options(mc); - smc->dr_lmb_enabled = false; - compat_props_add(mc->compat_props, hw_compat_2_4, hw_compat_2_4_len); -} - -DEFINE_SPAPR_MACHINE(2, 4); - -/* - * pseries-2.3 - */ - -static void spapr_machine_2_3_class_options(MachineClass *mc) -{ - static GlobalProperty compat[] = { - { "spapr-pci-host-bridge", "dynamic-reconfiguration", "off" }, - }; - spapr_machine_2_4_class_options(mc); - compat_props_add(mc->compat_props, hw_compat_2_3, hw_compat_2_3_len); - compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); -} -DEFINE_SPAPR_MACHINE(2, 3); - -/* - * pseries-2.2 - */ - -static void spapr_machine_2_2_class_options(MachineClass *mc) -{ - static GlobalProperty compat[] = { - { TYPE_SPAPR_PCI_HOST_BRIDGE, "mem_win_size", "0x20000000" }, - }; - - spapr_machine_2_3_class_options(mc); - compat_props_add(mc->compat_props, hw_compat_2_2, hw_compat_2_2_len); - compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); - mc->default_machine_opts = "modern-hotplug-events=off,suppress-vmdesc=on"; -} -DEFINE_SPAPR_MACHINE(2, 2); - -/* - * pseries-2.1 - */ - -static void spapr_machine_2_1_class_options(MachineClass *mc) -{ - spapr_machine_2_2_class_options(mc); - compat_props_add(mc->compat_props, hw_compat_2_1, hw_compat_2_1_len); -} -DEFINE_SPAPR_MACHINE(2, 1); - static void spapr_machine_register_types(void) { type_register_static(&spapr_machine_info); diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c index 4642245168..ada439e831 100644 --- a/hw/ppc/spapr_cpu_core.c +++ b/hw/ppc/spapr_cpu_core.c @@ -197,9 +197,7 @@ static void spapr_unrealize_vcpu(PowerPCCPU *cpu, SpaprCpuCore *sc) { CPUPPCState *env = &cpu->env; - if (!sc->pre_3_0_migration) { - vmstate_unregister(NULL, &vmstate_spapr_cpu_state, cpu->machine_data); - } + vmstate_unregister(NULL, &vmstate_spapr_cpu_state, cpu->machine_data); spapr_irq_cpu_intc_destroy(SPAPR_MACHINE(qdev_get_machine()), cpu); cpu_ppc_tb_free(env); qdev_unrealize(DEVICE(cpu)); @@ -285,10 +283,8 @@ static bool spapr_realize_vcpu(PowerPCCPU *cpu, SpaprMachineState *spapr, return false; } - if (!sc->pre_3_0_migration) { - vmstate_register(NULL, cs->cpu_index, &vmstate_spapr_cpu_state, - cpu->machine_data); - } + vmstate_register(NULL, cs->cpu_index, &vmstate_spapr_cpu_state, + cpu->machine_data); return true; } @@ -366,8 +362,6 @@ static void spapr_cpu_core_realize(DeviceState *dev, Error **errp) static Property spapr_cpu_core_properties[] = { DEFINE_PROP_INT32("node-id", SpaprCpuCore, node_id, CPU_UNSET_NUMA_NODE_ID), - DEFINE_PROP_BOOL("pre-3.0-migration", SpaprCpuCore, pre_3_0_migration, - false), DEFINE_PROP_END_OF_LIST() }; @@ -411,6 +405,7 @@ static const TypeInfo spapr_cpu_core_type_infos[] = { DEFINE_SPAPR_CPU_CORE_TYPE("power9_v2.0"), DEFINE_SPAPR_CPU_CORE_TYPE("power9_v2.2"), DEFINE_SPAPR_CPU_CORE_TYPE("power10_v2.0"), + DEFINE_SPAPR_CPU_CORE_TYPE("power11_v2.0"), #ifdef CONFIG_KVM DEFINE_SPAPR_CPU_CORE_TYPE("host"), #endif diff --git a/hw/ppc/spapr_nested.c b/hw/ppc/spapr_nested.c index c02785756c..7def8eb73b 100644 --- a/hw/ppc/spapr_nested.c +++ b/hw/ppc/spapr_nested.c @@ -771,6 +771,7 @@ static void copy_logical_pvr(void *a, void *b, bool set) if (*pvr_logical_ptr) { switch (*pvr_logical_ptr) { + case CPU_POWERPC_LOGICAL_3_10_P11: case CPU_POWERPC_LOGICAL_3_10: pcr = PCR_COMPAT_3_10 | PCR_COMPAT_3_00; break; @@ -982,6 +983,7 @@ struct guest_state_element_type guest_state_element_types[] = { GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_FSCR, fscr), GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_PSPB, pspb), GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_CTRL, ctrl), + GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_DPDES, dpdes), GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_VRSAVE, vrsave), GUEST_STATE_ELEMENT_ENV_DW(GSB_VCPU_SPR_DAR, dar), GUEST_STATE_ELEMENT_ENV_W(GSB_VCPU_SPR_DSISR, dsisr), @@ -1184,6 +1186,12 @@ static target_ulong h_guest_get_capabilities(PowerPCCPU *cpu, return H_PARAMETER; } + /* P11 capabilities */ + if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_10_P11, 0, + spapr->max_compat_pvr)) { + env->gpr[4] |= H_GUEST_CAPABILITIES_P11_MODE; + } + /* P10 capabilities */ if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_10, 0, spapr->max_compat_pvr)) { @@ -1226,7 +1234,10 @@ static target_ulong h_guest_set_capabilities(PowerPCCPU *cpu, env->gpr[4] = 1; /* set R5 to the first supported Power Processor Mode */ - if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_10, 0, + if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_10_P11, 0, + spapr->max_compat_pvr)) { + env->gpr[5] = H_GUEST_CAP_P11_MODE_BMAP; + } else if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_10, 0, spapr->max_compat_pvr)) { env->gpr[5] = H_GUEST_CAP_P10_MODE_BMAP; } else if (ppc_check_compat(cpu, CPU_POWERPC_LOGICAL_3_00, 0, diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c index 5c0024bef9..7e24084673 100644 --- a/hw/ppc/spapr_pci.c +++ b/hw/ppc/spapr_pci.c @@ -1237,10 +1237,6 @@ static void add_drcs(SpaprPhbState *phb, PCIBus *bus) int i; uint8_t chassis; - if (!phb->dr_enabled) { - return; - } - chassis = chassis_from_bus(bus); if (pci_bus_is_root(bus)) { @@ -1260,10 +1256,6 @@ static void remove_drcs(SpaprPhbState *phb, PCIBus *bus) int i; uint8_t chassis; - if (!phb->dr_enabled) { - return; - } - chassis = chassis_from_bus(bus); for (i = PCI_SLOT_MAX * PCI_FUNC_MAX - 1; i >= 0; i--) { @@ -1548,17 +1540,6 @@ static void spapr_pci_pre_plug(HotplugHandler *plug_handler, PCIBus *bus = PCI_BUS(qdev_get_parent_bus(DEVICE(pdev))); uint32_t slotnr = PCI_SLOT(pdev->devfn); - if (!phb->dr_enabled) { - /* if this is a hotplug operation initiated by the user - * we need to let them know it's not enabled - */ - if (plugged_dev->hotplugged) { - error_setg(errp, "Bus '%s' does not support hotplugging", - phb->parent_obj.bus->qbus.name); - return; - } - } - if (IS_PCI_BRIDGE(plugged_dev)) { if (!bridge_has_valid_chassis_nr(OBJECT(plugged_dev), errp)) { return; @@ -1591,14 +1572,6 @@ static void spapr_pci_plug(HotplugHandler *plug_handler, SpaprDrc *drc = drc_from_dev(phb, pdev); uint32_t slotnr = PCI_SLOT(pdev->devfn); - /* - * If DR is disabled we don't need to do anything in the case of - * hotplug or coldplug callbacks. - */ - if (!phb->dr_enabled) { - return; - } - g_assert(drc); if (IS_PCI_BRIDGE(plugged_dev)) { @@ -1673,12 +1646,6 @@ static void spapr_pci_unplug_request(HotplugHandler *plug_handler, PCIDevice *pdev = PCI_DEVICE(plugged_dev); SpaprDrc *drc = drc_from_dev(phb, pdev); - if (!phb->dr_enabled) { - error_setg(errp, "Bus '%s' does not support hotplugging", - phb->parent_obj.bus->qbus.name); - return; - } - g_assert(drc); g_assert(drc->dev == plugged_dev); @@ -1847,30 +1814,15 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) assert(sphb->index != (uint32_t)-1); /* checked in spapr_phb_pre_plug() */ - if (sphb->mem64_win_size != 0) { - if (sphb->mem_win_size > SPAPR_PCI_MEM32_WIN_SIZE) { - error_setg(errp, "32-bit memory window of size 0x%"HWADDR_PRIx - " (max 2 GiB)", sphb->mem_win_size); - return; - } - - /* 64-bit window defaults to identity mapping */ - sphb->mem64_win_pciaddr = sphb->mem64_win_addr; - } else if (sphb->mem_win_size > SPAPR_PCI_MEM32_WIN_SIZE) { - /* - * For compatibility with old configuration, if no 64-bit MMIO - * window is specified, but the ordinary (32-bit) memory - * window is specified as > 2GiB, we treat it as a 2GiB 32-bit - * window, with a 64-bit MMIO window following on immediately - * afterwards - */ - sphb->mem64_win_size = sphb->mem_win_size - SPAPR_PCI_MEM32_WIN_SIZE; - sphb->mem64_win_addr = sphb->mem_win_addr + SPAPR_PCI_MEM32_WIN_SIZE; - sphb->mem64_win_pciaddr = - SPAPR_PCI_MEM_WIN_BUS_OFFSET + SPAPR_PCI_MEM32_WIN_SIZE; - sphb->mem_win_size = SPAPR_PCI_MEM32_WIN_SIZE; + if (sphb->mem_win_size > SPAPR_PCI_MEM32_WIN_SIZE) { + error_setg(errp, "32-bit memory window of size 0x%"HWADDR_PRIx + " (max 2 GiB)", sphb->mem_win_size); + return; } + /* 64-bit window defaults to identity mapping */ + sphb->mem64_win_pciaddr = sphb->mem64_win_addr; + if (spapr_pci_find_phb(spapr, sphb->buid)) { SpaprPhbState *s; @@ -2089,8 +2041,6 @@ static Property spapr_phb_properties[] = { SPAPR_PCI_MEM64_WIN_SIZE), DEFINE_PROP_UINT64("io_win_size", SpaprPhbState, io_win_size, SPAPR_PCI_IO_WIN_SIZE), - DEFINE_PROP_BOOL("dynamic-reconfiguration", SpaprPhbState, dr_enabled, - true), /* Default DMA window is 0..1GB */ DEFINE_PROP_UINT64("dma_win_addr", SpaprPhbState, dma_win_addr, 0), DEFINE_PROP_UINT64("dma_win_size", SpaprPhbState, dma_win_size, 0x40000000), @@ -2101,8 +2051,6 @@ static Property spapr_phb_properties[] = { (1ULL << 12) | (1ULL << 16) | (1ULL << 21) | (1ULL << 24)), DEFINE_PROP_UINT32("numa_node", SpaprPhbState, numa_node, -1), - DEFINE_PROP_BOOL("pre-2.8-migration", SpaprPhbState, - pre_2_8_migration, false), DEFINE_PROP_BOOL("pcie-extended-configuration-space", SpaprPhbState, pcie_ecs, true), DEFINE_PROP_BOOL("pre-5.1-associativity", SpaprPhbState, @@ -2140,20 +2088,6 @@ static int spapr_pci_pre_save(void *opaque) gpointer key, value; int i; - if (sphb->pre_2_8_migration) { - sphb->mig_liobn = sphb->dma_liobn[0]; - sphb->mig_mem_win_addr = sphb->mem_win_addr; - sphb->mig_mem_win_size = sphb->mem_win_size; - sphb->mig_io_win_addr = sphb->io_win_addr; - sphb->mig_io_win_size = sphb->io_win_size; - - if ((sphb->mem64_win_size != 0) - && (sphb->mem64_win_addr - == (sphb->mem_win_addr + sphb->mem_win_size))) { - sphb->mig_mem_win_size += sphb->mem64_win_size; - } - } - g_free(sphb->msi_devs); sphb->msi_devs = NULL; sphb->msi_devs_num = g_hash_table_size(sphb->msi); @@ -2200,13 +2134,6 @@ static int spapr_pci_post_load(void *opaque, int version_id) return 0; } -static bool pre_2_8_migration(void *opaque, int version_id) -{ - SpaprPhbState *sphb = opaque; - - return sphb->pre_2_8_migration; -} - static const VMStateDescription vmstate_spapr_pci = { .name = "spapr_pci", .version_id = 2, @@ -2216,11 +2143,6 @@ static const VMStateDescription vmstate_spapr_pci = { .post_load = spapr_pci_post_load, .fields = (const VMStateField[]) { VMSTATE_UINT64_EQUAL(buid, SpaprPhbState, NULL), - VMSTATE_UINT32_TEST(mig_liobn, SpaprPhbState, pre_2_8_migration), - VMSTATE_UINT64_TEST(mig_mem_win_addr, SpaprPhbState, pre_2_8_migration), - VMSTATE_UINT64_TEST(mig_mem_win_size, SpaprPhbState, pre_2_8_migration), - VMSTATE_UINT64_TEST(mig_io_win_addr, SpaprPhbState, pre_2_8_migration), - VMSTATE_UINT64_TEST(mig_io_win_size, SpaprPhbState, pre_2_8_migration), VMSTATE_STRUCT_ARRAY(lsi_table, SpaprPhbState, PCI_NUM_PINS, 0, vmstate_spapr_pci_lsi, SpaprPciLsi), VMSTATE_INT32(msi_devs_num, SpaprPhbState), diff --git a/hw/ppc/virtex_ml507.c b/hw/ppc/virtex_ml507.c index 235281e939..f378e5c4a9 100644 --- a/hw/ppc/virtex_ml507.c +++ b/hw/ppc/virtex_ml507.c @@ -67,29 +67,6 @@ static struct boot_info void *vfdt; } boot_info; -/* Create reset TLB entries for BookE, spanning the 32bit addr space. */ -static void mmubooke_create_initial_mapping(CPUPPCState *env, - target_ulong va, - hwaddr pa) -{ - ppcemb_tlb_t *tlb = &env->tlb.tlbe[0]; - - tlb->attr = 0; - tlb->prot = PAGE_VALID | ((PAGE_READ | PAGE_WRITE | PAGE_EXEC) << 4); - tlb->size = 1U << 31; /* up to 0x80000000 */ - tlb->EPN = va & TARGET_PAGE_MASK; - tlb->RPN = pa & TARGET_PAGE_MASK; - tlb->PID = 0; - - tlb = &env->tlb.tlbe[1]; - tlb->attr = 0; - tlb->prot = PAGE_VALID | ((PAGE_READ | PAGE_WRITE | PAGE_EXEC) << 4); - tlb->size = 1U << 31; /* up to 0xffffffff */ - tlb->EPN = 0x80000000 & TARGET_PAGE_MASK; - tlb->RPN = 0x80000000 & TARGET_PAGE_MASK; - tlb->PID = 0; -} - static PowerPCCPU *ppc440_init_xilinx(const char *cpu_type, uint32_t sysclk) { PowerPCCPU *cpu; @@ -139,8 +116,9 @@ static void main_cpu_reset(void *opaque) env->gpr[3] = bi->fdt; env->nip = bi->bootstrap_pc; - /* Create a mapping for the kernel. */ - mmubooke_create_initial_mapping(env, 0, 0); + /* Create a mapping spanning the 32bit addr space. */ + booke_set_tlb(&env->tlb.tlbe[0], 0, 0, 1U << 31); + booke_set_tlb(&env->tlb.tlbe[1], 0x80000000, 0x80000000, 1U << 31); env->gpr[6] = tswap32(EPAPR_MAGIC); env->gpr[7] = bi->ima_size; } diff --git a/hw/s390x/Kconfig b/hw/s390x/Kconfig index 3bbf4ae56e..82afdaa9dc 100644 --- a/hw/s390x/Kconfig +++ b/hw/s390x/Kconfig @@ -7,6 +7,7 @@ config S390_CCW_VIRTIO imply VFIO_AP imply VFIO_CCW imply WDT_DIAG288 + imply PCI_BRIDGE imply PCIE_DEVICES imply IOMMUFD select PCI_EXPRESS diff --git a/hw/sd/aspeed_sdhci.c b/hw/sd/aspeed_sdhci.c index 427e5336a8..98d5460905 100644 --- a/hw/sd/aspeed_sdhci.c +++ b/hw/sd/aspeed_sdhci.c @@ -24,8 +24,10 @@ #define ASPEED_SDHCI_DEBOUNCE_RESET 0x00000005 #define ASPEED_SDHCI_BUS 0x08 #define ASPEED_SDHCI_SDIO_140 0x10 +#define ASPEED_SDHCI_SDIO_144 0x14 #define ASPEED_SDHCI_SDIO_148 0x18 #define ASPEED_SDHCI_SDIO_240 0x20 +#define ASPEED_SDHCI_SDIO_244 0x24 #define ASPEED_SDHCI_SDIO_248 0x28 #define ASPEED_SDHCI_WP_POL 0xec #define ASPEED_SDHCI_CARD_DET 0xf0 @@ -35,21 +37,27 @@ static uint64_t aspeed_sdhci_read(void *opaque, hwaddr addr, unsigned int size) { - uint32_t val = 0; + uint64_t val = 0; AspeedSDHCIState *sdhci = opaque; switch (addr) { case ASPEED_SDHCI_SDIO_140: - val = (uint32_t)sdhci->slots[0].capareg; + val = extract64(sdhci->slots[0].capareg, 0, 32); + break; + case ASPEED_SDHCI_SDIO_144: + val = extract64(sdhci->slots[0].capareg, 32, 32); break; case ASPEED_SDHCI_SDIO_148: - val = (uint32_t)sdhci->slots[0].maxcurr; + val = extract64(sdhci->slots[0].maxcurr, 0, 32); break; case ASPEED_SDHCI_SDIO_240: - val = (uint32_t)sdhci->slots[1].capareg; + val = extract64(sdhci->slots[1].capareg, 0, 32); + break; + case ASPEED_SDHCI_SDIO_244: + val = extract64(sdhci->slots[1].capareg, 32, 32); break; case ASPEED_SDHCI_SDIO_248: - val = (uint32_t)sdhci->slots[1].maxcurr; + val = extract64(sdhci->slots[1].maxcurr, 0, 32); break; default: if (addr < ASPEED_SDHCI_REG_SIZE) { @@ -61,9 +69,9 @@ static uint64_t aspeed_sdhci_read(void *opaque, hwaddr addr, unsigned int size) } } - trace_aspeed_sdhci_read(addr, size, (uint64_t) val); + trace_aspeed_sdhci_read(addr, size, val); - return (uint64_t)val; + return val; } static void aspeed_sdhci_write(void *opaque, hwaddr addr, uint64_t val, @@ -79,16 +87,26 @@ static void aspeed_sdhci_write(void *opaque, hwaddr addr, uint64_t val, sdhci->regs[TO_REG(addr)] = (uint32_t)val & ~ASPEED_SDHCI_INFO_RESET; break; case ASPEED_SDHCI_SDIO_140: - sdhci->slots[0].capareg = (uint64_t)(uint32_t)val; + sdhci->slots[0].capareg = deposit64(sdhci->slots[0].capareg, 0, 32, val); + break; + case ASPEED_SDHCI_SDIO_144: + sdhci->slots[0].capareg = deposit64(sdhci->slots[0].capareg, 32, 32, val); break; case ASPEED_SDHCI_SDIO_148: - sdhci->slots[0].maxcurr = (uint64_t)(uint32_t)val; + sdhci->slots[0].maxcurr = deposit64(sdhci->slots[0].maxcurr, + 0, 32, val); break; case ASPEED_SDHCI_SDIO_240: - sdhci->slots[1].capareg = (uint64_t)(uint32_t)val; + sdhci->slots[1].capareg = deposit64(sdhci->slots[1].capareg, + 0, 32, val); + break; + case ASPEED_SDHCI_SDIO_244: + sdhci->slots[1].capareg = deposit64(sdhci->slots[1].capareg, + 32, 32, val); break; case ASPEED_SDHCI_SDIO_248: - sdhci->slots[1].maxcurr = (uint64_t)(uint32_t)val; + sdhci->slots[1].maxcurr = deposit64(sdhci->slots[0].maxcurr, + 0, 32, val); break; default: if (addr < ASPEED_SDHCI_REG_SIZE) { diff --git a/hw/sd/sd.c b/hw/sd/sd.c index b2e2d58e01..f9bd03f3fd 100644 --- a/hw/sd/sd.c +++ b/hw/sd/sd.c @@ -834,7 +834,9 @@ static void sd_reset(DeviceState *dev) sect = 0; } size = sect << HWBLOCK_SHIFT; - size -= sd_bootpart_offset(sd); + if (sd_is_emmc(sd)) { + size -= sd->boot_part_size * 2; + } sect = sd_addr_to_wpnum(size) + 1; diff --git a/hw/ssi/pnv_spi.c b/hw/ssi/pnv_spi.c index 9e7207bf7c..c21b2ebb3c 100644 --- a/hw/ssi/pnv_spi.c +++ b/hw/ssi/pnv_spi.c @@ -53,8 +53,8 @@ static PnvXferBuffer *pnv_spi_xfer_buffer_new(void) static void pnv_spi_xfer_buffer_free(PnvXferBuffer *payload) { - free(payload->data); - free(payload); + g_free(payload->data); + g_free(payload); } static uint8_t *pnv_spi_xfer_buffer_write_ptr(PnvXferBuffer *payload, @@ -217,6 +217,9 @@ static void transfer(PnvSpi *s, PnvXferBuffer *payload) PnvXferBuffer *rsp_payload = NULL; rsp_payload = pnv_spi_xfer_buffer_new(); + if (!rsp_payload) { + return; + } for (int offset = 0; offset < payload->len; offset += s->transfer_len) { tx = 0; for (int i = 0; i < s->transfer_len; i++) { @@ -235,9 +238,8 @@ static void transfer(PnvSpi *s, PnvXferBuffer *payload) (rx >> (8 * (s->transfer_len - 1) - i * 8)) & 0xFF; } } - if (rsp_payload != NULL) { - spi_response(s, s->N1_bits, rsp_payload); - } + spi_response(s, s->N1_bits, rsp_payload); + pnv_spi_xfer_buffer_free(rsp_payload); } static inline uint8_t get_seq_index(PnvSpi *s) diff --git a/hw/timer/aspeed_timer.c b/hw/timer/aspeed_timer.c index b1f860ecfb..149f7cc5a6 100644 --- a/hw/timer/aspeed_timer.c +++ b/hw/timer/aspeed_timer.c @@ -276,7 +276,8 @@ static void aspeed_timer_set_value(AspeedTimerCtrlState *s, int timer, int reg, old_reload = t->reload; t->reload = calculate_min_ticks(t, value); - /* If the reload value was not previously set, or zero, and + /* + * If the reload value was not previously set, or zero, and * the current value is valid, try to start the timer if it is * enabled. */ @@ -312,7 +313,8 @@ static void aspeed_timer_set_value(AspeedTimerCtrlState *s, int timer, int reg, } } -/* Control register operations are broken out into helpers that can be +/* + * Control register operations are broken out into helpers that can be * explicitly called on aspeed_timer_reset(), but also from * aspeed_timer_ctrl_op(). */ @@ -396,7 +398,8 @@ static void aspeed_timer_set_ctrl(AspeedTimerCtrlState *s, uint32_t reg) AspeedTimer *t; const uint8_t enable_mask = BIT(op_enable); - /* Handle a dependency between the 'enable' and remaining three + /* + * Handle a dependency between the 'enable' and remaining three * configuration bits - i.e. if more than one bit in the control set has * changed, including the 'enable' bit, then we want either disable the * timer and perform configuration, or perform configuration and then @@ -577,12 +580,11 @@ static void aspeed_2600_timer_write(AspeedTimerCtrlState *s, hwaddr offset, switch (offset) { case 0x34: - s->irq_sts &= tv; + s->irq_sts &= ~tv; break; case 0x3C: aspeed_timer_set_ctrl(s, s->ctrl & ~tv); break; - case 0x38: default: qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset 0x%" HWADDR_PRIx "\n", @@ -623,7 +625,8 @@ static void aspeed_timer_reset(DeviceState *dev) for (i = 0; i < ASPEED_TIMER_NR_TIMERS; i++) { AspeedTimer *t = &s->timers[i]; - /* Explicitly call helpers to avoid any conditional behaviour through + /* + * Explicitly call helpers to avoid any conditional behaviour through * aspeed_timer_set_ctrl(). */ aspeed_timer_ctrl_enable(t, false); diff --git a/hw/virtio/vhost-user.c b/hw/virtio/vhost-user.c index 00561daa06..f170f0b25b 100644 --- a/hw/virtio/vhost-user.c +++ b/hw/virtio/vhost-user.c @@ -1185,9 +1185,16 @@ static int vhost_user_set_vring_num(struct vhost_dev *dev, static void vhost_user_host_notifier_free(VhostUserHostNotifier *n) { - assert(n && n->unmap_addr); - munmap(n->unmap_addr, qemu_real_host_page_size()); - n->unmap_addr = NULL; + if (n->unmap_addr) { + munmap(n->unmap_addr, qemu_real_host_page_size()); + n->unmap_addr = NULL; + } + if (n->destroy) { + memory_region_transaction_begin(); + object_unparent(OBJECT(&n->mr)); + memory_region_transaction_commit(); + g_free(n); + } } /* @@ -1195,17 +1202,28 @@ static void vhost_user_host_notifier_free(VhostUserHostNotifier *n) * under rcu. */ static void vhost_user_host_notifier_remove(VhostUserHostNotifier *n, - VirtIODevice *vdev) + VirtIODevice *vdev, bool destroy) { + /* + * if destroy == false and n->addr == NULL, we have nothing to do. + * so, just return. + */ + if (!n || (!destroy && !n->addr)) { + return; + } + if (n->addr) { if (vdev) { + memory_region_transaction_begin(); virtio_queue_set_host_notifier_mr(vdev, n->idx, &n->mr, false); + memory_region_transaction_commit(); } assert(!n->unmap_addr); n->unmap_addr = n->addr; n->addr = NULL; - call_rcu(n, vhost_user_host_notifier_free, rcu); } + n->destroy = destroy; + call_rcu(n, vhost_user_host_notifier_free, rcu); } static int vhost_user_set_vring_base(struct vhost_dev *dev, @@ -1279,9 +1297,7 @@ static int vhost_user_get_vring_base(struct vhost_dev *dev, struct vhost_user *u = dev->opaque; VhostUserHostNotifier *n = fetch_notifier(u->user, ring->index); - if (n) { - vhost_user_host_notifier_remove(n, dev->vdev); - } + vhost_user_host_notifier_remove(n, dev->vdev, false); ret = vhost_user_write(dev, &msg, NULL, 0); if (ret < 0) { @@ -1562,7 +1578,7 @@ static int vhost_user_backend_handle_vring_host_notifier(struct vhost_dev *dev, * new mapped address. */ n = fetch_or_create_notifier(user, queue_idx); - vhost_user_host_notifier_remove(n, vdev); + vhost_user_host_notifier_remove(n, vdev, false); if (area->u64 & VHOST_USER_VRING_NOFD_MASK) { return 0; @@ -1607,9 +1623,14 @@ vhost_user_backend_handle_shared_object_add(struct vhost_dev *dev, QemuUUID uuid; memcpy(uuid.data, object->uuid, sizeof(object->uuid)); - return virtio_add_vhost_device(&uuid, dev); + return !virtio_add_vhost_device(&uuid, dev); } +/* + * Handle VHOST_USER_BACKEND_SHARED_OBJECT_REMOVE backend requests. + * + * Return: 0 on success, 1 on error. + */ static int vhost_user_backend_handle_shared_object_remove(struct vhost_dev *dev, VhostUserShared *object) @@ -1623,16 +1644,16 @@ vhost_user_backend_handle_shared_object_remove(struct vhost_dev *dev, struct vhost_dev *owner = virtio_lookup_vhost_device(&uuid); if (dev != owner) { /* Not allowed to remove non-owned entries */ - return 0; + return 1; } break; } default: /* Not allowed to remove non-owned entries */ - return 0; + return 1; } - return virtio_remove_resource(&uuid); + return !virtio_remove_resource(&uuid); } static bool vhost_user_send_resp(QIOChannel *ioc, VhostUserHeader *hdr, @@ -2736,15 +2757,7 @@ static int vhost_user_set_inflight_fd(struct vhost_dev *dev, static void vhost_user_state_destroy(gpointer data) { VhostUserHostNotifier *n = (VhostUserHostNotifier *) data; - if (n) { - vhost_user_host_notifier_remove(n, NULL); - object_unparent(OBJECT(&n->mr)); - /* - * We can't free until vhost_user_host_notifier_remove has - * done it's thing so schedule the free with RCU. - */ - g_free_rcu(n, rcu); - } + vhost_user_host_notifier_remove(n, NULL, true); } bool vhost_user_init(VhostUserState *user, CharBackend *chr, Error **errp) @@ -2765,9 +2778,7 @@ void vhost_user_cleanup(VhostUserState *user) if (!user->chr) { return; } - memory_region_transaction_begin(); user->notifiers = (GPtrArray *) g_ptr_array_free(user->notifiers, true); - memory_region_transaction_commit(); user->chr = NULL; } diff --git a/hw/virtio/virtio-pci.c b/hw/virtio/virtio-pci.c index 4d832fe845..5a394821da 100644 --- a/hw/virtio/virtio-pci.c +++ b/hw/virtio/virtio-pci.c @@ -2057,6 +2057,8 @@ static void virtio_pci_device_plugged(DeviceState *d, Error **errp) if (modern_pio) { memory_region_init(&proxy->io_bar, OBJECT(proxy), "virtio-pci-io", 0x4); + address_space_init(&proxy->modern_cfg_io_as, &proxy->io_bar, + "virtio-pci-cfg-io-as"); pci_register_bar(&proxy->pci_dev, proxy->modern_io_bar_idx, PCI_BASE_ADDRESS_SPACE_IO, &proxy->io_bar); @@ -2180,6 +2182,9 @@ static void virtio_pci_realize(PCIDevice *pci_dev, Error **errp) /* PCI BAR regions must be powers of 2 */ pow2ceil(proxy->notify.offset + proxy->notify.size)); + address_space_init(&proxy->modern_cfg_mem_as, &proxy->modern_bar, + "virtio-pci-cfg-mem-as"); + if (proxy->disable_legacy == ON_OFF_AUTO_AUTO) { proxy->disable_legacy = pcie_port ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF; } @@ -2269,12 +2274,17 @@ static void virtio_pci_exit(PCIDevice *pci_dev) VirtIOPCIProxy *proxy = VIRTIO_PCI(pci_dev); bool pcie_port = pci_bus_is_express(pci_get_bus(pci_dev)) && !pci_bus_is_root(pci_get_bus(pci_dev)); + bool modern_pio = proxy->flags & VIRTIO_PCI_FLAG_MODERN_PIO_NOTIFY; msix_uninit_exclusive_bar(pci_dev); if (proxy->flags & VIRTIO_PCI_FLAG_AER && pcie_port && pci_is_express(pci_dev)) { pcie_aer_exit(pci_dev); } + address_space_destroy(&proxy->modern_cfg_mem_as); + if (modern_pio) { + address_space_destroy(&proxy->modern_cfg_io_as); + } } static void virtio_pci_reset(DeviceState *qdev) @@ -2385,6 +2395,14 @@ static void virtio_pci_dc_realize(DeviceState *qdev, Error **errp) vpciklass->parent_dc_realize(qdev, errp); } +static int virtio_pci_sync_config(DeviceState *dev, Error **errp) +{ + VirtIOPCIProxy *proxy = VIRTIO_PCI(dev); + VirtIODevice *vdev = virtio_bus_get_device(&proxy->bus); + + return qdev_sync_config(DEVICE(vdev), errp); +} + static void virtio_pci_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); @@ -2401,6 +2419,7 @@ static void virtio_pci_class_init(ObjectClass *klass, void *data) device_class_set_parent_realize(dc, virtio_pci_dc_realize, &vpciklass->parent_dc_realize); rc->phases.hold = virtio_pci_bus_reset_hold; + dc->sync_config = virtio_pci_sync_config; } static const TypeInfo virtio_pci_info = { |