diff options
Diffstat (limited to 'hw/core')
| -rw-r--r-- | hw/core/Makefile.objs | 5 | ||||
| -rw-r--r-- | hw/core/machine-hmp-cmds.c | 167 | ||||
| -rw-r--r-- | hw/core/machine-qmp-cmds.c | 330 | ||||
| -rw-r--r-- | hw/core/machine.c | 89 | ||||
| -rw-r--r-- | hw/core/numa.c | 613 | ||||
| -rw-r--r-- | hw/core/qdev.c | 2 | ||||
| -rw-r--r-- | hw/core/vm-change-state-handler.c | 61 |
7 files changed, 1266 insertions, 1 deletions
diff --git a/hw/core/Makefile.objs b/hw/core/Makefile.objs index a799c83815..f8481d959f 100644 --- a/hw/core/Makefile.objs +++ b/hw/core/Makefile.objs @@ -7,6 +7,7 @@ common-obj-$(CONFIG_SOFTMMU) += fw-path-provider.o common-obj-y += irq.o common-obj-y += hotplug.o common-obj-$(CONFIG_SOFTMMU) += nmi.o +common-obj-$(CONFIG_SOFTMMU) += vm-change-state-handler.o common-obj-$(CONFIG_EMPTY_SLOT) += empty_slot.o common-obj-$(CONFIG_XILINX_AXI) += stream.o @@ -22,3 +23,7 @@ common-obj-$(CONFIG_SOFTMMU) += split-irq.o common-obj-$(CONFIG_PLATFORM_BUS) += platform-bus.o common-obj-$(CONFIG_SOFTMMU) += generic-loader.o common-obj-$(CONFIG_SOFTMMU) += null-machine.o + +obj-$(CONFIG_SOFTMMU) += machine-qmp-cmds.o +obj-$(CONFIG_SOFTMMU) += numa.o +common-obj-$(CONFIG_SOFTMMU) += machine-hmp-cmds.o diff --git a/hw/core/machine-hmp-cmds.c b/hw/core/machine-hmp-cmds.c new file mode 100644 index 0000000000..1f66bda346 --- /dev/null +++ b/hw/core/machine-hmp-cmds.c @@ -0,0 +1,167 @@ +/* + * HMP commands related to machines and CPUs + * + * Copyright IBM, Corp. 2011 + * + * Authors: + * Anthony Liguori <aliguori@us.ibm.com> + * + * This work is licensed under the terms of the GNU GPL, version 2. See + * the COPYING file in the top-level directory. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu/osdep.h" +#include "monitor/hmp.h" +#include "monitor/monitor.h" +#include "qapi/error.h" +#include "qapi/qapi-builtin-visit.h" +#include "qapi/qapi-commands-machine.h" +#include "qapi/qmp/qdict.h" +#include "qapi/string-output-visitor.h" +#include "qemu/error-report.h" +#include "sysemu/numa.h" + +void hmp_info_cpus(Monitor *mon, const QDict *qdict) +{ + CpuInfoFastList *cpu_list, *cpu; + + cpu_list = qmp_query_cpus_fast(NULL); + + for (cpu = cpu_list; cpu; cpu = cpu->next) { + int active = ' '; + + if (cpu->value->cpu_index == monitor_get_cpu_index()) { + active = '*'; + } + + monitor_printf(mon, "%c CPU #%" PRId64 ":", active, + cpu->value->cpu_index); + monitor_printf(mon, " thread_id=%" PRId64 "\n", cpu->value->thread_id); + } + + qapi_free_CpuInfoFastList(cpu_list); +} + +void hmp_cpu_add(Monitor *mon, const QDict *qdict) +{ + int cpuid; + Error *err = NULL; + + error_report("cpu_add is deprecated, please use device_add instead"); + + cpuid = qdict_get_int(qdict, "id"); + qmp_cpu_add(cpuid, &err); + hmp_handle_error(mon, &err); +} + +void hmp_hotpluggable_cpus(Monitor *mon, const QDict *qdict) +{ + Error *err = NULL; + HotpluggableCPUList *l = qmp_query_hotpluggable_cpus(&err); + HotpluggableCPUList *saved = l; + CpuInstanceProperties *c; + + if (err != NULL) { + hmp_handle_error(mon, &err); + return; + } + + monitor_printf(mon, "Hotpluggable CPUs:\n"); + while (l) { + monitor_printf(mon, " type: \"%s\"\n", l->value->type); + monitor_printf(mon, " vcpus_count: \"%" PRIu64 "\"\n", + l->value->vcpus_count); + if (l->value->has_qom_path) { + monitor_printf(mon, " qom_path: \"%s\"\n", l->value->qom_path); + } + + c = l->value->props; + monitor_printf(mon, " CPUInstance Properties:\n"); + if (c->has_node_id) { + monitor_printf(mon, " node-id: \"%" PRIu64 "\"\n", c->node_id); + } + if (c->has_socket_id) { + monitor_printf(mon, " socket-id: \"%" PRIu64 "\"\n", c->socket_id); + } + if (c->has_die_id) { + monitor_printf(mon, " die-id: \"%" PRIu64 "\"\n", c->die_id); + } + if (c->has_core_id) { + monitor_printf(mon, " core-id: \"%" PRIu64 "\"\n", c->core_id); + } + if (c->has_thread_id) { + monitor_printf(mon, " thread-id: \"%" PRIu64 "\"\n", c->thread_id); + } + + l = l->next; + } + + qapi_free_HotpluggableCPUList(saved); +} + +void hmp_info_memdev(Monitor *mon, const QDict *qdict) +{ + Error *err = NULL; + MemdevList *memdev_list = qmp_query_memdev(&err); + MemdevList *m = memdev_list; + Visitor *v; + char *str; + + while (m) { + v = string_output_visitor_new(false, &str); + visit_type_uint16List(v, NULL, &m->value->host_nodes, NULL); + monitor_printf(mon, "memory backend: %s\n", m->value->id); + monitor_printf(mon, " size: %" PRId64 "\n", m->value->size); + monitor_printf(mon, " merge: %s\n", + m->value->merge ? "true" : "false"); + monitor_printf(mon, " dump: %s\n", + m->value->dump ? "true" : "false"); + monitor_printf(mon, " prealloc: %s\n", + m->value->prealloc ? "true" : "false"); + monitor_printf(mon, " policy: %s\n", + HostMemPolicy_str(m->value->policy)); + visit_complete(v, &str); + monitor_printf(mon, " host nodes: %s\n", str); + + g_free(str); + visit_free(v); + m = m->next; + } + + monitor_printf(mon, "\n"); + + qapi_free_MemdevList(memdev_list); + hmp_handle_error(mon, &err); +} + +void hmp_info_numa(Monitor *mon, const QDict *qdict) +{ + int i; + NumaNodeMem *node_mem; + CpuInfoList *cpu_list, *cpu; + + cpu_list = qmp_query_cpus(&error_abort); + node_mem = g_new0(NumaNodeMem, nb_numa_nodes); + + query_numa_node_mem(node_mem); + monitor_printf(mon, "%d nodes\n", nb_numa_nodes); + for (i = 0; i < nb_numa_nodes; i++) { + monitor_printf(mon, "node %d cpus:", i); + for (cpu = cpu_list; cpu; cpu = cpu->next) { + if (cpu->value->has_props && cpu->value->props->has_node_id && + cpu->value->props->node_id == i) { + monitor_printf(mon, " %" PRIi64, cpu->value->CPU); + } + } + monitor_printf(mon, "\n"); + monitor_printf(mon, "node %d size: %" PRId64 " MB\n", i, + node_mem[i].node_mem >> 20); + monitor_printf(mon, "node %d plugged: %" PRId64 " MB\n", i, + node_mem[i].node_plugged_mem >> 20); + } + qapi_free_CpuInfoList(cpu_list); + g_free(node_mem); +} diff --git a/hw/core/machine-qmp-cmds.c b/hw/core/machine-qmp-cmds.c new file mode 100644 index 0000000000..5bd95b8ab0 --- /dev/null +++ b/hw/core/machine-qmp-cmds.c @@ -0,0 +1,330 @@ +/* + * QMP commands related to machines and CPUs + * + * Copyright (C) 2014 Red Hat Inc + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "cpu.h" +#include "hw/boards.h" +#include "qapi/error.h" +#include "qapi/qapi-commands-machine.h" +#include "qapi/qmp/qerror.h" +#include "sysemu/hostmem.h" +#include "sysemu/hw_accel.h" +#include "sysemu/numa.h" +#include "sysemu/sysemu.h" + +CpuInfoList *qmp_query_cpus(Error **errp) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + MachineClass *mc = MACHINE_GET_CLASS(ms); + CpuInfoList *head = NULL, *cur_item = NULL; + CPUState *cpu; + + CPU_FOREACH(cpu) { + CpuInfoList *info; +#if defined(TARGET_I386) + X86CPU *x86_cpu = X86_CPU(cpu); + CPUX86State *env = &x86_cpu->env; +#elif defined(TARGET_PPC) + PowerPCCPU *ppc_cpu = POWERPC_CPU(cpu); + CPUPPCState *env = &ppc_cpu->env; +#elif defined(TARGET_SPARC) + SPARCCPU *sparc_cpu = SPARC_CPU(cpu); + CPUSPARCState *env = &sparc_cpu->env; +#elif defined(TARGET_RISCV) + RISCVCPU *riscv_cpu = RISCV_CPU(cpu); + CPURISCVState *env = &riscv_cpu->env; +#elif defined(TARGET_MIPS) + MIPSCPU *mips_cpu = MIPS_CPU(cpu); + CPUMIPSState *env = &mips_cpu->env; +#elif defined(TARGET_TRICORE) + TriCoreCPU *tricore_cpu = TRICORE_CPU(cpu); + CPUTriCoreState *env = &tricore_cpu->env; +#elif defined(TARGET_S390X) + S390CPU *s390_cpu = S390_CPU(cpu); + CPUS390XState *env = &s390_cpu->env; +#endif + + cpu_synchronize_state(cpu); + + info = g_malloc0(sizeof(*info)); + info->value = g_malloc0(sizeof(*info->value)); + info->value->CPU = cpu->cpu_index; + info->value->current = (cpu == first_cpu); + info->value->halted = cpu->halted; + info->value->qom_path = object_get_canonical_path(OBJECT(cpu)); + info->value->thread_id = cpu->thread_id; +#if defined(TARGET_I386) + info->value->arch = CPU_INFO_ARCH_X86; + info->value->u.x86.pc = env->eip + env->segs[R_CS].base; +#elif defined(TARGET_PPC) + info->value->arch = CPU_INFO_ARCH_PPC; + info->value->u.ppc.nip = env->nip; +#elif defined(TARGET_SPARC) + info->value->arch = CPU_INFO_ARCH_SPARC; + info->value->u.q_sparc.pc = env->pc; + info->value->u.q_sparc.npc = env->npc; +#elif defined(TARGET_MIPS) + info->value->arch = CPU_INFO_ARCH_MIPS; + info->value->u.q_mips.PC = env->active_tc.PC; +#elif defined(TARGET_TRICORE) + info->value->arch = CPU_INFO_ARCH_TRICORE; + info->value->u.tricore.PC = env->PC; +#elif defined(TARGET_S390X) + info->value->arch = CPU_INFO_ARCH_S390; + info->value->u.s390.cpu_state = env->cpu_state; +#elif defined(TARGET_RISCV) + info->value->arch = CPU_INFO_ARCH_RISCV; + info->value->u.riscv.pc = env->pc; +#else + info->value->arch = CPU_INFO_ARCH_OTHER; +#endif + info->value->has_props = !!mc->cpu_index_to_instance_props; + if (info->value->has_props) { + CpuInstanceProperties *props; + props = g_malloc0(sizeof(*props)); + *props = mc->cpu_index_to_instance_props(ms, cpu->cpu_index); + info->value->props = props; + } + + /* XXX: waiting for the qapi to support GSList */ + if (!cur_item) { + head = cur_item = info; + } else { + cur_item->next = info; + cur_item = info; + } + } + + return head; +} + +static CpuInfoArch sysemu_target_to_cpuinfo_arch(SysEmuTarget target) +{ + /* + * The @SysEmuTarget -> @CpuInfoArch mapping below is based on the + * TARGET_ARCH -> TARGET_BASE_ARCH mapping in the "configure" script. + */ + switch (target) { + case SYS_EMU_TARGET_I386: + case SYS_EMU_TARGET_X86_64: + return CPU_INFO_ARCH_X86; + + case SYS_EMU_TARGET_PPC: + case SYS_EMU_TARGET_PPC64: + return CPU_INFO_ARCH_PPC; + + case SYS_EMU_TARGET_SPARC: + case SYS_EMU_TARGET_SPARC64: + return CPU_INFO_ARCH_SPARC; + + case SYS_EMU_TARGET_MIPS: + case SYS_EMU_TARGET_MIPSEL: + case SYS_EMU_TARGET_MIPS64: + case SYS_EMU_TARGET_MIPS64EL: + return CPU_INFO_ARCH_MIPS; + + case SYS_EMU_TARGET_TRICORE: + return CPU_INFO_ARCH_TRICORE; + + case SYS_EMU_TARGET_S390X: + return CPU_INFO_ARCH_S390; + + case SYS_EMU_TARGET_RISCV32: + case SYS_EMU_TARGET_RISCV64: + return CPU_INFO_ARCH_RISCV; + + default: + return CPU_INFO_ARCH_OTHER; + } +} + +static void cpustate_to_cpuinfo_s390(CpuInfoS390 *info, const CPUState *cpu) +{ +#ifdef TARGET_S390X + S390CPU *s390_cpu = S390_CPU(cpu); + CPUS390XState *env = &s390_cpu->env; + + info->cpu_state = env->cpu_state; +#else + abort(); +#endif +} + +/* + * fast means: we NEVER interrupt vCPU threads to retrieve + * information from KVM. + */ +CpuInfoFastList *qmp_query_cpus_fast(Error **errp) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + MachineClass *mc = MACHINE_GET_CLASS(ms); + CpuInfoFastList *head = NULL, *cur_item = NULL; + SysEmuTarget target = qapi_enum_parse(&SysEmuTarget_lookup, TARGET_NAME, + -1, &error_abort); + CPUState *cpu; + + CPU_FOREACH(cpu) { + CpuInfoFastList *info = g_malloc0(sizeof(*info)); + info->value = g_malloc0(sizeof(*info->value)); + + info->value->cpu_index = cpu->cpu_index; + info->value->qom_path = object_get_canonical_path(OBJECT(cpu)); + info->value->thread_id = cpu->thread_id; + + info->value->has_props = !!mc->cpu_index_to_instance_props; + if (info->value->has_props) { + CpuInstanceProperties *props; + props = g_malloc0(sizeof(*props)); + *props = mc->cpu_index_to_instance_props(ms, cpu->cpu_index); + info->value->props = props; + } + + info->value->arch = sysemu_target_to_cpuinfo_arch(target); + info->value->target = target; + if (target == SYS_EMU_TARGET_S390X) { + cpustate_to_cpuinfo_s390(&info->value->u.s390x, cpu); + } + + if (!cur_item) { + head = cur_item = info; + } else { + cur_item->next = info; + cur_item = info; + } + } + + return head; +} + +MachineInfoList *qmp_query_machines(Error **errp) +{ + GSList *el, *machines = object_class_get_list(TYPE_MACHINE, false); + MachineInfoList *mach_list = NULL; + + for (el = machines; el; el = el->next) { + MachineClass *mc = el->data; + MachineInfoList *entry; + MachineInfo *info; + + info = g_malloc0(sizeof(*info)); + if (mc->is_default) { + info->has_is_default = true; + info->is_default = true; + } + + if (mc->alias) { + info->has_alias = true; + info->alias = g_strdup(mc->alias); + } + + info->name = g_strdup(mc->name); + info->cpu_max = !mc->max_cpus ? 1 : mc->max_cpus; + info->hotpluggable_cpus = mc->has_hotpluggable_cpus; + info->numa_mem_supported = mc->numa_mem_supported; + info->deprecated = !!mc->deprecation_reason; + + entry = g_malloc0(sizeof(*entry)); + entry->value = info; + entry->next = mach_list; + mach_list = entry; + } + + g_slist_free(machines); + return mach_list; +} + +CurrentMachineParams *qmp_query_current_machine(Error **errp) +{ + CurrentMachineParams *params = g_malloc0(sizeof(*params)); + params->wakeup_suspend_support = qemu_wakeup_suspend_enabled(); + + return params; +} + +HotpluggableCPUList *qmp_query_hotpluggable_cpus(Error **errp) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + MachineClass *mc = MACHINE_GET_CLASS(ms); + + if (!mc->has_hotpluggable_cpus) { + error_setg(errp, QERR_FEATURE_DISABLED, "query-hotpluggable-cpus"); + return NULL; + } + + return machine_query_hotpluggable_cpus(ms); +} + +void qmp_cpu_add(int64_t id, Error **errp) +{ + MachineClass *mc; + + mc = MACHINE_GET_CLASS(current_machine); + if (mc->hot_add_cpu) { + mc->hot_add_cpu(current_machine, id, errp); + } else { + error_setg(errp, "Not supported"); + } +} + +void qmp_set_numa_node(NumaOptions *cmd, Error **errp) +{ + if (!runstate_check(RUN_STATE_PRECONFIG)) { + error_setg(errp, "The command is permitted only in '%s' state", + RunState_str(RUN_STATE_PRECONFIG)); + return; + } + + set_numa_options(MACHINE(qdev_get_machine()), cmd, errp); +} + +static int query_memdev(Object *obj, void *opaque) +{ + MemdevList **list = opaque; + MemdevList *m = NULL; + + if (object_dynamic_cast(obj, TYPE_MEMORY_BACKEND)) { + m = g_malloc0(sizeof(*m)); + + m->value = g_malloc0(sizeof(*m->value)); + + m->value->id = object_get_canonical_path_component(obj); + m->value->has_id = !!m->value->id; + + m->value->size = object_property_get_uint(obj, "size", + &error_abort); + m->value->merge = object_property_get_bool(obj, "merge", + &error_abort); + m->value->dump = object_property_get_bool(obj, "dump", + &error_abort); + m->value->prealloc = object_property_get_bool(obj, + "prealloc", + &error_abort); + m->value->policy = object_property_get_enum(obj, + "policy", + "HostMemPolicy", + &error_abort); + object_property_get_uint16List(obj, "host-nodes", + &m->value->host_nodes, + &error_abort); + + m->next = *list; + *list = m; + } + + return 0; +} + +MemdevList *qmp_query_memdev(Error **errp) +{ + Object *obj = object_get_objects_root(); + MemdevList *list = NULL; + + object_child_foreach(obj, query_memdev, &list); + return list; +} diff --git a/hw/core/machine.c b/hw/core/machine.c index ea5a01aa49..2be19ec0cd 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -11,6 +11,9 @@ */ #include "qemu/osdep.h" +#include "qemu/option.h" +#include "qapi/qmp/qerror.h" +#include "sysemu/replay.h" #include "qemu/units.h" #include "hw/boards.h" #include "qapi/error.h" @@ -30,6 +33,7 @@ GlobalProperty hw_compat_4_0[] = { { "bochs-display", "edid", "false" }, { "virtio-vga", "edid", "false" }, { "virtio-gpu-pci", "edid", "false" }, + { "virtio-device", "use-started", "false" }, }; const size_t hw_compat_4_0_len = G_N_ELEMENTS(hw_compat_4_0); @@ -682,6 +686,11 @@ void machine_set_cpu_numa_node(MachineState *machine, return; } + if (props->has_die_id && !slot->props.has_die_id) { + error_setg(errp, "die-id is not supported"); + return; + } + /* skip slots with explicit mismatch */ if (props->has_thread_id && props->thread_id != slot->props.thread_id) { continue; @@ -691,6 +700,10 @@ void machine_set_cpu_numa_node(MachineState *machine, continue; } + if (props->has_die_id && props->die_id != slot->props.die_id) { + continue; + } + if (props->has_socket_id && props->socket_id != slot->props.socket_id) { continue; } @@ -716,6 +729,78 @@ void machine_set_cpu_numa_node(MachineState *machine, } } +static void smp_parse(MachineState *ms, QemuOpts *opts) +{ + if (opts) { + unsigned cpus = qemu_opt_get_number(opts, "cpus", 0); + unsigned sockets = qemu_opt_get_number(opts, "sockets", 0); + unsigned cores = qemu_opt_get_number(opts, "cores", 0); + unsigned threads = qemu_opt_get_number(opts, "threads", 0); + + /* compute missing values, prefer sockets over cores over threads */ + if (cpus == 0 || sockets == 0) { + cores = cores > 0 ? cores : 1; + threads = threads > 0 ? threads : 1; + if (cpus == 0) { + sockets = sockets > 0 ? sockets : 1; + cpus = cores * threads * sockets; + } else { + ms->smp.max_cpus = + qemu_opt_get_number(opts, "maxcpus", cpus); + sockets = ms->smp.max_cpus / (cores * threads); + } + } else if (cores == 0) { + threads = threads > 0 ? threads : 1; + cores = cpus / (sockets * threads); + cores = cores > 0 ? cores : 1; + } else if (threads == 0) { + threads = cpus / (cores * sockets); + threads = threads > 0 ? threads : 1; + } else if (sockets * cores * threads < cpus) { + error_report("cpu topology: " + "sockets (%u) * cores (%u) * threads (%u) < " + "smp_cpus (%u)", + sockets, cores, threads, cpus); + exit(1); + } + + ms->smp.max_cpus = + qemu_opt_get_number(opts, "maxcpus", cpus); + + if (ms->smp.max_cpus < cpus) { + error_report("maxcpus must be equal to or greater than smp"); + exit(1); + } + + if (sockets * cores * threads > ms->smp.max_cpus) { + error_report("cpu topology: " + "sockets (%u) * cores (%u) * threads (%u) > " + "maxcpus (%u)", + sockets, cores, threads, + ms->smp.max_cpus); + exit(1); + } + + if (sockets * cores * threads != ms->smp.max_cpus) { + warn_report("Invalid CPU topology deprecated: " + "sockets (%u) * cores (%u) * threads (%u) " + "!= maxcpus (%u)", + sockets, cores, threads, + ms->smp.max_cpus); + } + + ms->smp.cpus = cpus; + ms->smp.cores = cores; + ms->smp.threads = threads; + } + + if (ms->smp.cpus > 1) { + Error *blocker = NULL; + error_setg(&blocker, QERR_REPLAY_NOT_SUPPORTED, "smp"); + replay_add_blocker(blocker); + } +} + static void machine_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); @@ -723,6 +808,7 @@ static void machine_class_init(ObjectClass *oc, void *data) /* Default 128 MB as guest ram size */ mc->default_ram_size = 128 * MiB; mc->rom_file_has_mr = true; + mc->smp_parse = smp_parse; /* numa node memory size aligned on 8MB by default. * On Linux, each node's border has to be 8MB aligned @@ -948,6 +1034,9 @@ static char *cpu_slot_to_string(const CPUArchId *cpu) if (cpu->props.has_socket_id) { g_string_append_printf(s, "socket-id: %"PRId64, cpu->props.socket_id); } + if (cpu->props.has_die_id) { + g_string_append_printf(s, "die-id: %"PRId64, cpu->props.die_id); + } if (cpu->props.has_core_id) { if (s->len) { g_string_append_printf(s, ", "); diff --git a/hw/core/numa.c b/hw/core/numa.c new file mode 100644 index 0000000000..a11431483c --- /dev/null +++ b/hw/core/numa.c @@ -0,0 +1,613 @@ +/* + * NUMA parameter parsing routines + * + * Copyright (c) 2014 Fujitsu Ltd. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "sysemu/numa.h" +#include "exec/cpu-common.h" +#include "exec/ramlist.h" +#include "qemu/bitmap.h" +#include "qemu/error-report.h" +#include "qapi/error.h" +#include "qapi/opts-visitor.h" +#include "qapi/qapi-visit-machine.h" +#include "sysemu/qtest.h" +#include "hw/mem/pc-dimm.h" +#include "hw/mem/memory-device.h" +#include "qemu/option.h" +#include "qemu/config-file.h" +#include "qemu/cutils.h" + +QemuOptsList qemu_numa_opts = { + .name = "numa", + .implied_opt_name = "type", + .head = QTAILQ_HEAD_INITIALIZER(qemu_numa_opts.head), + .desc = { { 0 } } /* validated with OptsVisitor */ +}; + +static int have_memdevs; +static int have_mem; +static int max_numa_nodeid; /* Highest specified NUMA node ID, plus one. + * For all nodes, nodeid < max_numa_nodeid + */ +int nb_numa_nodes; +bool have_numa_distance; +NodeInfo numa_info[MAX_NODES]; + + +static void parse_numa_node(MachineState *ms, NumaNodeOptions *node, + Error **errp) +{ + Error *err = NULL; + uint16_t nodenr; + uint16List *cpus = NULL; + MachineClass *mc = MACHINE_GET_CLASS(ms); + unsigned int max_cpus = ms->smp.max_cpus; + + if (node->has_nodeid) { + nodenr = node->nodeid; + } else { + nodenr = nb_numa_nodes; + } + + if (nodenr >= MAX_NODES) { + error_setg(errp, "Max number of NUMA nodes reached: %" + PRIu16 "", nodenr); + return; + } + + if (numa_info[nodenr].present) { + error_setg(errp, "Duplicate NUMA nodeid: %" PRIu16, nodenr); + return; + } + + if (!mc->cpu_index_to_instance_props || !mc->get_default_cpu_node_id) { + error_setg(errp, "NUMA is not supported by this machine-type"); + return; + } + for (cpus = node->cpus; cpus; cpus = cpus->next) { + CpuInstanceProperties props; + if (cpus->value >= max_cpus) { + error_setg(errp, + "CPU index (%" PRIu16 ")" + " should be smaller than maxcpus (%d)", + cpus->value, max_cpus); + return; + } + props = mc->cpu_index_to_instance_props(ms, cpus->value); + props.node_id = nodenr; + props.has_node_id = true; + machine_set_cpu_numa_node(ms, &props, &err); + if (err) { + error_propagate(errp, err); + return; + } + } + + have_memdevs = have_memdevs ? : node->has_memdev; + have_mem = have_mem ? : node->has_mem; + if ((node->has_mem && have_memdevs) || (node->has_memdev && have_mem)) { + error_setg(errp, "numa configuration should use either mem= or memdev=," + "mixing both is not allowed"); + return; + } + + if (node->has_mem) { + numa_info[nodenr].node_mem = node->mem; + if (!qtest_enabled()) { + warn_report("Parameter -numa node,mem is deprecated," + " use -numa node,memdev instead"); + } + } + if (node->has_memdev) { + Object *o; + o = object_resolve_path_type(node->memdev, TYPE_MEMORY_BACKEND, NULL); + if (!o) { + error_setg(errp, "memdev=%s is ambiguous", node->memdev); + return; + } + + object_ref(o); + numa_info[nodenr].node_mem = object_property_get_uint(o, "size", NULL); + numa_info[nodenr].node_memdev = MEMORY_BACKEND(o); + } + numa_info[nodenr].present = true; + max_numa_nodeid = MAX(max_numa_nodeid, nodenr + 1); + nb_numa_nodes++; +} + +static void parse_numa_distance(NumaDistOptions *dist, Error **errp) +{ + uint16_t src = dist->src; + uint16_t dst = dist->dst; + uint8_t val = dist->val; + + if (src >= MAX_NODES || dst >= MAX_NODES) { + error_setg(errp, "Parameter '%s' expects an integer between 0 and %d", + src >= MAX_NODES ? "src" : "dst", MAX_NODES - 1); + return; + } + + if (!numa_info[src].present || !numa_info[dst].present) { + error_setg(errp, "Source/Destination NUMA node is missing. " + "Please use '-numa node' option to declare it first."); + return; + } + + if (val < NUMA_DISTANCE_MIN) { + error_setg(errp, "NUMA distance (%" PRIu8 ") is invalid, " + "it shouldn't be less than %d.", + val, NUMA_DISTANCE_MIN); + return; + } + + if (src == dst && val != NUMA_DISTANCE_MIN) { + error_setg(errp, "Local distance of node %d should be %d.", + src, NUMA_DISTANCE_MIN); + return; + } + + numa_info[src].distance[dst] = val; + have_numa_distance = true; +} + +void set_numa_options(MachineState *ms, NumaOptions *object, Error **errp) +{ + Error *err = NULL; + + switch (object->type) { + case NUMA_OPTIONS_TYPE_NODE: + parse_numa_node(ms, &object->u.node, &err); + if (err) { + goto end; + } + break; + case NUMA_OPTIONS_TYPE_DIST: + parse_numa_distance(&object->u.dist, &err); + if (err) { + goto end; + } + break; + case NUMA_OPTIONS_TYPE_CPU: + if (!object->u.cpu.has_node_id) { + error_setg(&err, "Missing mandatory node-id property"); + goto end; + } + if (!numa_info[object->u.cpu.node_id].present) { + error_setg(&err, "Invalid node-id=%" PRId64 ", NUMA node must be " + "defined with -numa node,nodeid=ID before it's used with " + "-numa cpu,node-id=ID", object->u.cpu.node_id); + goto end; + } + + machine_set_cpu_numa_node(ms, qapi_NumaCpuOptions_base(&object->u.cpu), + &err); + break; + default: + abort(); + } + +end: + error_propagate(errp, err); +} + +static int parse_numa(void *opaque, QemuOpts *opts, Error **errp) +{ + NumaOptions *object = NULL; + MachineState *ms = MACHINE(opaque); + Error *err = NULL; + Visitor *v = opts_visitor_new(opts); + + visit_type_NumaOptions(v, NULL, &object, &err); + visit_free(v); + if (err) { + goto end; + } + + /* Fix up legacy suffix-less format */ + if ((object->type == NUMA_OPTIONS_TYPE_NODE) && object->u.node.has_mem) { + const char *mem_str = qemu_opt_get(opts, "mem"); + qemu_strtosz_MiB(mem_str, NULL, &object->u.node.mem); + } + + set_numa_options(ms, object, &err); + +end: + qapi_free_NumaOptions(object); + if (err) { + error_propagate(errp, err); + return -1; + } + + return 0; +} + +/* If all node pair distances are symmetric, then only distances + * in one direction are enough. If there is even one asymmetric + * pair, though, then all distances must be provided. The + * distance from a node to itself is always NUMA_DISTANCE_MIN, + * so providing it is never necessary. + */ +static void validate_numa_distance(void) +{ + int src, dst; + bool is_asymmetrical = false; + + for (src = 0; src < nb_numa_nodes; src++) { + for (dst = src; dst < nb_numa_nodes; dst++) { + if (numa_info[src].distance[dst] == 0 && + numa_info[dst].distance[src] == 0) { + if (src != dst) { + error_report("The distance between node %d and %d is " + "missing, at least one distance value " + "between each nodes should be provided.", + src, dst); + exit(EXIT_FAILURE); + } + } + + if (numa_info[src].distance[dst] != 0 && + numa_info[dst].distance[src] != 0 && + numa_info[src].distance[dst] != + numa_info[dst].distance[src]) { + is_asymmetrical = true; + } + } + } + + if (is_asymmetrical) { + for (src = 0; src < nb_numa_nodes; src++) { + for (dst = 0; dst < nb_numa_nodes; dst++) { + if (src != dst && numa_info[src].distance[dst] == 0) { + error_report("At least one asymmetrical pair of " + "distances is given, please provide distances " + "for both directions of all node pairs."); + exit(EXIT_FAILURE); + } + } + } + } +} + +static void complete_init_numa_distance(void) +{ + int src, dst; + + /* Fixup NUMA distance by symmetric policy because if it is an + * asymmetric distance table, it should be a complete table and + * there would not be any missing distance except local node, which + * is verified by validate_numa_distance above. + */ + for (src = 0; src < nb_numa_nodes; src++) { + for (dst = 0; dst < nb_numa_nodes; dst++) { + if (numa_info[src].distance[dst] == 0) { + if (src == dst) { + numa_info[src].distance[dst] = NUMA_DISTANCE_MIN; + } else { + numa_info[src].distance[dst] = numa_info[dst].distance[src]; + } + } + } + } +} + +void numa_legacy_auto_assign_ram(MachineClass *mc, NodeInfo *nodes, + int nb_nodes, ram_addr_t size) +{ + int i; + uint64_t usedmem = 0; + + /* Align each node according to the alignment + * requirements of the machine class + */ + + for (i = 0; i < nb_nodes - 1; i++) { + nodes[i].node_mem = (size / nb_nodes) & + ~((1 << mc->numa_mem_align_shift) - 1); + usedmem += nodes[i].node_mem; + } + nodes[i].node_mem = size - usedmem; +} + +void numa_default_auto_assign_ram(MachineClass *mc, NodeInfo *nodes, + int nb_nodes, ram_addr_t size) +{ + int i; + uint64_t usedmem = 0, node_mem; + uint64_t granularity = size / nb_nodes; + uint64_t propagate = 0; + + for (i = 0; i < nb_nodes - 1; i++) { + node_mem = (granularity + propagate) & + ~((1 << mc->numa_mem_align_shift) - 1); + propagate = granularity + propagate - node_mem; + nodes[i].node_mem = node_mem; + usedmem += node_mem; + } + nodes[i].node_mem = size - usedmem; +} + +void numa_complete_configuration(MachineState *ms) +{ + int i; + MachineClass *mc = MACHINE_GET_CLASS(ms); + + /* + * If memory hotplug is enabled (slots > 0) but without '-numa' + * options explicitly on CLI, guestes will break. + * + * Windows: won't enable memory hotplug without SRAT table at all + * + * Linux: if QEMU is started with initial memory all below 4Gb + * and no SRAT table present, guest kernel will use nommu DMA ops, + * which breaks 32bit hw drivers when memory is hotplugged and + * guest tries to use it with that drivers. + * + * Enable NUMA implicitly by adding a new NUMA node automatically. + */ + if (ms->ram_slots > 0 && nb_numa_nodes == 0 && + mc->auto_enable_numa_with_memhp) { + NumaNodeOptions node = { }; + parse_numa_node(ms, &node, &error_abort); + } + + assert(max_numa_nodeid <= MAX_NODES); + + /* No support for sparse NUMA node IDs yet: */ + for (i = max_numa_nodeid - 1; i >= 0; i--) { + /* Report large node IDs first, to make mistakes easier to spot */ + if (!numa_info[i].present) { + error_report("numa: Node ID missing: %d", i); + exit(1); + } + } + + /* This must be always true if all nodes are present: */ + assert(nb_numa_nodes == max_numa_nodeid); + + if (nb_numa_nodes > 0) { + uint64_t numa_total; + + if (nb_numa_nodes > MAX_NODES) { + nb_numa_nodes = MAX_NODES; + } + + /* If no memory size is given for any node, assume the default case + * and distribute the available memory equally across all nodes + */ + for (i = 0; i < nb_numa_nodes; i++) { + if (numa_info[i].node_mem != 0) { + break; + } + } + if (i == nb_numa_nodes) { + assert(mc->numa_auto_assign_ram); + mc->numa_auto_assign_ram(mc, numa_info, nb_numa_nodes, ram_size); + if (!qtest_enabled()) { + warn_report("Default splitting of RAM between nodes is deprecated," + " Use '-numa node,memdev' to explictly define RAM" + " allocation per node"); + } + } + + numa_total = 0; + for (i = 0; i < nb_numa_nodes; i++) { + numa_total += numa_info[i].node_mem; + } + if (numa_total != ram_size) { + error_report("total memory for NUMA nodes (0x%" PRIx64 ")" + " should equal RAM size (0x" RAM_ADDR_FMT ")", + numa_total, ram_size); + exit(1); + } + + /* QEMU needs at least all unique node pair distances to build + * the whole NUMA distance table. QEMU treats the distance table + * as symmetric by default, i.e. distance A->B == distance B->A. + * Thus, QEMU is able to complete the distance table + * initialization even though only distance A->B is provided and + * distance B->A is not. QEMU knows the distance of a node to + * itself is always 10, so A->A distances may be omitted. When + * the distances of two nodes of a pair differ, i.e. distance + * A->B != distance B->A, then that means the distance table is + * asymmetric. In this case, the distances for both directions + * of all node pairs are required. + */ + if (have_numa_distance) { + /* Validate enough NUMA distance information was provided. */ + validate_numa_distance(); + + /* Validation succeeded, now fill in any missing distances. */ + complete_init_numa_distance(); + } + } +} + +void parse_numa_opts(MachineState *ms) +{ + qemu_opts_foreach(qemu_find_opts("numa"), parse_numa, ms, &error_fatal); +} + +void numa_cpu_pre_plug(const CPUArchId *slot, DeviceState *dev, Error **errp) +{ + int node_id = object_property_get_int(OBJECT(dev), "node-id", &error_abort); + + if (node_id == CPU_UNSET_NUMA_NODE_ID) { + /* due to bug in libvirt, it doesn't pass node-id from props on + * device_add as expected, so we have to fix it up here */ + if (slot->props.has_node_id) { + object_property_set_int(OBJECT(dev), slot->props.node_id, + "node-id", errp); + } + } else if (node_id != slot->props.node_id) { + error_setg(errp, "invalid node-id, must be %"PRId64, + slot->props.node_id); + } +} + +static void allocate_system_memory_nonnuma(MemoryRegion *mr, Object *owner, + const char *name, + uint64_t ram_size) +{ + if (mem_path) { +#ifdef __linux__ + Error *err = NULL; + memory_region_init_ram_from_file(mr, owner, name, ram_size, 0, 0, + mem_path, &err); + if (err) { + error_report_err(err); + if (mem_prealloc) { + exit(1); + } + warn_report("falling back to regular RAM allocation"); + error_printf("This is deprecated. Make sure that -mem-path " + " specified path has sufficient resources to allocate" + " -m specified RAM amount"); + /* Legacy behavior: if allocation failed, fall back to + * regular RAM allocation. + */ + mem_path = NULL; + memory_region_init_ram_nomigrate(mr, owner, name, ram_size, &error_fatal); + } +#else + fprintf(stderr, "-mem-path not supported on this host\n"); + exit(1); +#endif + } else { + memory_region_init_ram_nomigrate(mr, owner, name, ram_size, &error_fatal); + } + vmstate_register_ram_global(mr); +} + +void memory_region_allocate_system_memory(MemoryRegion *mr, Object *owner, + const char *name, + uint64_t ram_size) +{ + uint64_t addr = 0; + int i; + + if (nb_numa_nodes == 0 || !have_memdevs) { + allocate_system_memory_nonnuma(mr, owner, name, ram_size); + return; + } + + memory_region_init(mr, owner, name, ram_size); + for (i = 0; i < nb_numa_nodes; i++) { + uint64_t size = numa_info[i].node_mem; + HostMemoryBackend *backend = numa_info[i].node_memdev; + if (!backend) { + continue; + } + MemoryRegion *seg = host_memory_backend_get_memory(backend); + + if (memory_region_is_mapped(seg)) { + char *path = object_get_canonical_path_component(OBJECT(backend)); + error_report("memory backend %s is used multiple times. Each " + "-numa option must use a different memdev value.", + path); + g_free(path); + exit(1); + } + + host_memory_backend_set_mapped(backend, true); + memory_region_add_subregion(mr, addr, seg); + vmstate_register_ram_global(seg); + addr += size; + } +} + +static void numa_stat_memory_devices(NumaNodeMem node_mem[]) +{ + MemoryDeviceInfoList *info_list = qmp_memory_device_list(); + MemoryDeviceInfoList *info; + PCDIMMDeviceInfo *pcdimm_info; + VirtioPMEMDeviceInfo *vpi; + + for (info = info_list; info; info = info->next) { + MemoryDeviceInfo *value = info->value; + + if (value) { + switch (value->type) { + case MEMORY_DEVICE_INFO_KIND_DIMM: + case MEMORY_DEVICE_INFO_KIND_NVDIMM: + pcdimm_info = value->type == MEMORY_DEVICE_INFO_KIND_DIMM ? + value->u.dimm.data : value->u.nvdimm.data; + node_mem[pcdimm_info->node].node_mem += pcdimm_info->size; + node_mem[pcdimm_info->node].node_plugged_mem += + pcdimm_info->size; + break; + case MEMORY_DEVICE_INFO_KIND_VIRTIO_PMEM: + vpi = value->u.virtio_pmem.data; + /* TODO: once we support numa, assign to right node */ + node_mem[0].node_mem += vpi->size; + node_mem[0].node_plugged_mem += vpi->size; + break; + default: + g_assert_not_reached(); + } + } + } + qapi_free_MemoryDeviceInfoList(info_list); +} + +void query_numa_node_mem(NumaNodeMem node_mem[]) +{ + int i; + + if (nb_numa_nodes <= 0) { + return; + } + + numa_stat_memory_devices(node_mem); + for (i = 0; i < nb_numa_nodes; i++) { + node_mem[i].node_mem += numa_info[i].node_mem; + } +} + +void ram_block_notifier_add(RAMBlockNotifier *n) +{ + QLIST_INSERT_HEAD(&ram_list.ramblock_notifiers, n, next); +} + +void ram_block_notifier_remove(RAMBlockNotifier *n) +{ + QLIST_REMOVE(n, next); +} + +void ram_block_notify_add(void *host, size_t size) +{ + RAMBlockNotifier *notifier; + + QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) { + notifier->ram_block_added(notifier, host, size); + } +} + +void ram_block_notify_remove(void *host, size_t size) +{ + RAMBlockNotifier *notifier; + + QLIST_FOREACH(notifier, &ram_list.ramblock_notifiers, next) { + notifier->ram_block_removed(notifier, host, size); + } +} diff --git a/hw/core/qdev.c b/hw/core/qdev.c index f9b6efe509..94ebc0a4a1 100644 --- a/hw/core/qdev.c +++ b/hw/core/qdev.c @@ -29,7 +29,7 @@ #include "hw/qdev.h" #include "sysemu/sysemu.h" #include "qapi/error.h" -#include "qapi/qapi-events-misc.h" +#include "qapi/qapi-events-qdev.h" #include "qapi/qmp/qerror.h" #include "qapi/visitor.h" #include "qemu/error-report.h" diff --git a/hw/core/vm-change-state-handler.c b/hw/core/vm-change-state-handler.c new file mode 100644 index 0000000000..f814813bdd --- /dev/null +++ b/hw/core/vm-change-state-handler.c @@ -0,0 +1,61 @@ +/* + * qdev vm change state handlers + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, + * or (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "hw/qdev.h" + +static int qdev_get_dev_tree_depth(DeviceState *dev) +{ + int depth; + + for (depth = 0; dev; depth++) { + BusState *bus = dev->parent_bus; + + if (!bus) { + break; + } + + dev = bus->parent; + } + + return depth; +} + +/** + * qdev_add_vm_change_state_handler: + * @dev: the device that owns this handler + * @cb: the callback function to be invoked + * @opaque: user data passed to the callback function + * + * This function works like qemu_add_vm_change_state_handler() except callbacks + * are invoked in qdev tree depth order. Ordering is desirable when callbacks + * of children depend on their parent's callback having completed first. + * + * For example, when qdev_add_vm_change_state_handler() is used, a host + * controller's callback is invoked before the children on its bus when the VM + * starts running. The order is reversed when the VM stops running. + * + * Returns: an entry to be freed with qemu_del_vm_change_state_handler() + */ +VMChangeStateEntry *qdev_add_vm_change_state_handler(DeviceState *dev, + VMChangeStateHandler *cb, + void *opaque) +{ + int depth = qdev_get_dev_tree_depth(dev); + + return qemu_add_vm_change_state_handler_prio(cb, opaque, depth); +} |