diff options
47 files changed, 1437 insertions, 731 deletions
@@ -921,6 +921,15 @@ void cpu_synchronize_all_post_init(void) } } +void cpu_synchronize_all_pre_loadvm(void) +{ + CPUState *cpu; + + CPU_FOREACH(cpu) { + cpu_synchronize_pre_loadvm(cpu); + } +} + static int do_vm_stop(RunState state) { int ret = 0; diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index 2079828c22..3d78ff68e6 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -496,12 +496,10 @@ build_srat(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) srat->reserved1 = cpu_to_le32(1); for (i = 0; i < cpu_list->len; ++i) { - int node_id = cpu_list->cpus[i].props.has_node_id ? - cpu_list->cpus[i].props.node_id : 0; core = acpi_data_push(table_data, sizeof(*core)); core->type = ACPI_SRAT_PROCESSOR_GICC; core->length = sizeof(*core); - core->proximity = cpu_to_le32(node_id); + core->proximity = cpu_to_le32(cpu_list->cpus[i].props.node_id); core->acpi_processor_uid = cpu_to_le32(i); core->flags = cpu_to_le32(1); } diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 4db2d4207c..010f7244bf 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -1372,7 +1372,6 @@ static void machvirt_init(MachineState *machine) for (n = 0; n < possible_cpus->len; n++) { Object *cpuobj; CPUState *cs; - int node_id; if (n >= smp_cpus) { break; @@ -1385,19 +1384,8 @@ static void machvirt_init(MachineState *machine) cs = CPU(cpuobj); cs->cpu_index = n; - node_id = possible_cpus->cpus[cs->cpu_index].props.node_id; - if (!possible_cpus->cpus[cs->cpu_index].props.has_node_id) { - /* by default CPUState::numa_node was 0 if it's not set via CLI - * keep it this way for now but in future we probably should - * refuse to start up with incomplete numa mapping */ - node_id = 0; - } - if (cs->numa_node == CPU_UNSET_NUMA_NODE_ID) { - cs->numa_node = node_id; - } else { - /* CPU isn't device_add compatible yet, this shouldn't happen */ - error_setg(&error_abort, "user set node-id not implemented"); - } + numa_cpu_pre_plug(&possible_cpus->cpus[cs->cpu_index], DEVICE(cpuobj), + &error_fatal); if (!vms->secure) { object_property_set_bool(cpuobj, false, "has_el3", NULL); diff --git a/hw/core/machine.c b/hw/core/machine.c index 3adebf14c4..2e7e9778cd 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -701,26 +701,43 @@ static char *cpu_slot_to_string(const CPUArchId *cpu) return g_string_free(s, false); } -static void machine_numa_validate(MachineState *machine) +static void machine_numa_finish_init(MachineState *machine) { int i; + bool default_mapping; GString *s = g_string_new(NULL); MachineClass *mc = MACHINE_GET_CLASS(machine); const CPUArchIdList *possible_cpus = mc->possible_cpu_arch_ids(machine); assert(nb_numa_nodes); for (i = 0; i < possible_cpus->len; i++) { + if (possible_cpus->cpus[i].props.has_node_id) { + break; + } + } + default_mapping = (i == possible_cpus->len); + + for (i = 0; i < possible_cpus->len; i++) { const CPUArchId *cpu_slot = &possible_cpus->cpus[i]; - /* at this point numa mappings are initilized by CLI options - * or with default mappings so it's sufficient to list - * all not yet mapped CPUs here */ - /* TODO: make it hard error in future */ if (!cpu_slot->props.has_node_id) { - char *cpu_str = cpu_slot_to_string(cpu_slot); - g_string_append_printf(s, "%sCPU %d [%s]", s->len ? ", " : "", i, - cpu_str); - g_free(cpu_str); + /* fetch default mapping from board and enable it */ + CpuInstanceProperties props = cpu_slot->props; + + if (!default_mapping) { + /* record slots with not set mapping, + * TODO: make it hard error in future */ + char *cpu_str = cpu_slot_to_string(cpu_slot); + g_string_append_printf(s, "%sCPU %d [%s]", + s->len ? ", " : "", i, cpu_str); + g_free(cpu_str); + + /* non mapped cpus used to fallback to node 0 */ + props.node_id = 0; + } + + props.has_node_id = true; + machine_set_cpu_numa_node(machine, &props, &error_fatal); } } if (s->len && !qtest_enabled()) { @@ -738,7 +755,7 @@ void machine_run_board_init(MachineState *machine) MachineClass *machine_class = MACHINE_GET_CLASS(machine); if (nb_numa_nodes) { - machine_numa_validate(machine); + machine_numa_finish_init(machine); } machine_class->init(machine); } diff --git a/hw/i386/acpi-build.c b/hw/i386/acpi-build.c index 82bd44f38e..ce74c84460 100644 --- a/hw/i386/acpi-build.c +++ b/hw/i386/acpi-build.c @@ -2335,8 +2335,7 @@ build_srat(GArray *table_data, BIOSLinker *linker, MachineState *machine) srat->reserved1 = cpu_to_le32(1); for (i = 0; i < apic_ids->len; i++) { - int node_id = apic_ids->cpus[i].props.has_node_id ? - apic_ids->cpus[i].props.node_id : 0; + int node_id = apic_ids->cpus[i].props.node_id; uint32_t apic_id = apic_ids->cpus[i].arch_id; if (apic_id < 255) { diff --git a/hw/i386/pc.c b/hw/i386/pc.c index 107a34125b..5b8c6fbbea 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -788,9 +788,7 @@ static FWCfgState *bochs_bios_init(AddressSpace *as, PCMachineState *pcms) for (i = 0; i < cpus->len; i++) { unsigned int apic_id = cpus->cpus[i].arch_id; assert(apic_id < pcms->apic_id_limit); - if (cpus->cpus[i].props.has_node_id) { - numa_fw_cfg[apic_id + 1] = cpu_to_le64(cpus->cpus[i].props.node_id); - } + numa_fw_cfg[apic_id + 1] = cpu_to_le64(cpus->cpus[i].props.node_id); } for (i = 0; i < nb_numa_nodes; i++) { numa_fw_cfg[pcms->apic_id_limit + 1 + i] = @@ -1893,7 +1891,6 @@ static void pc_cpu_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { int idx; - int node_id; CPUState *cs; CPUArchId *cpu_slot; X86CPUTopoInfo topo; @@ -1984,21 +1981,7 @@ static void pc_cpu_pre_plug(HotplugHandler *hotplug_dev, cs = CPU(cpu); cs->cpu_index = idx; - node_id = cpu_slot->props.node_id; - if (!cpu_slot->props.has_node_id) { - /* by default CPUState::numa_node was 0 if it's not set via CLI - * keep it this way for now but in future we probably should - * refuse to start up with incomplete numa mapping */ - node_id = 0; - } - if (cs->numa_node == CPU_UNSET_NUMA_NODE_ID) { - cs->numa_node = node_id; - } else if (cs->numa_node != node_id) { - error_setg(errp, "node-id %d must match numa node specified" - "with -numa option for cpu-index %d", - cs->numa_node, cs->cpu_index); - return; - } + numa_cpu_pre_plug(cpu_slot, dev, errp); } static void pc_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev, diff --git a/hw/intc/openpic.c b/hw/intc/openpic.c index 4349e45e04..f966d0604a 100644 --- a/hw/intc/openpic.c +++ b/hw/intc/openpic.c @@ -796,27 +796,24 @@ static uint64_t openpic_gbl_read(void *opaque, hwaddr addr, unsigned len) } static void openpic_tmr_write(void *opaque, hwaddr addr, uint64_t val, - unsigned len) + unsigned len) { OpenPICState *opp = opaque; int idx; - addr += 0x10f0; - DPRINTF("%s: addr %#" HWADDR_PRIx " <= %08" PRIx64 "\n", - __func__, addr, val); + __func__, (addr + 0x10f0), val); if (addr & 0xF) { return; } - if (addr == 0x10f0) { + if (addr == 0) { /* TFRR */ opp->tfrr = val; return; } - + addr -= 0x10; /* correct for TFRR */ idx = (addr >> 6) & 0x3; - addr = addr & 0x30; switch (addr & 0x30) { case 0x00: /* TCCR */ @@ -844,16 +841,17 @@ static uint64_t openpic_tmr_read(void *opaque, hwaddr addr, unsigned len) uint32_t retval = -1; int idx; - DPRINTF("%s: addr %#" HWADDR_PRIx "\n", __func__, addr); + DPRINTF("%s: addr %#" HWADDR_PRIx "\n", __func__, addr + 0x10f0); if (addr & 0xF) { goto out; } - idx = (addr >> 6) & 0x3; - if (addr == 0x0) { + if (addr == 0) { /* TFRR */ retval = opp->tfrr; goto out; } + addr -= 0x10; /* correct for TFRR */ + idx = (addr >> 6) & 0x3; switch (addr & 0x30) { case 0x00: /* TCCR */ retval = opp->timers[idx].tccr; @@ -861,10 +859,10 @@ static uint64_t openpic_tmr_read(void *opaque, hwaddr addr, unsigned len) case 0x10: /* TBCR */ retval = opp->timers[idx].tbcr; break; - case 0x20: /* TIPV */ + case 0x20: /* TVPR */ retval = read_IRQreg_ivpr(opp, opp->irq_tim0 + idx); break; - case 0x30: /* TIDE (TIDR) */ + case 0x30: /* TDR */ retval = read_IRQreg_idr(opp, opp->irq_tim0 + idx); break; } diff --git a/hw/net/vmxnet3.c b/hw/net/vmxnet3.c index 8b1fab24fd..4df31101ec 100644 --- a/hw/net/vmxnet3.c +++ b/hw/net/vmxnet3.c @@ -2262,6 +2262,11 @@ static const MemoryRegionOps b1_ops = { }, }; +static SaveVMHandlers savevm_vmxnet3_msix = { + .save_state = vmxnet3_msix_save, + .load_state = vmxnet3_msix_load, +}; + static uint64_t vmxnet3_device_serial_num(VMXNET3State *s) { uint64_t dsn_payload; @@ -2331,8 +2336,7 @@ static void vmxnet3_pci_realize(PCIDevice *pci_dev, Error **errp) vmxnet3_device_serial_num(s)); } - register_savevm(dev, "vmxnet3-msix", -1, 1, - vmxnet3_msix_save, vmxnet3_msix_load, s); + register_savevm_live(dev, "vmxnet3-msix", -1, 1, &savevm_vmxnet3_msix, s); } static void vmxnet3_instance_init(Object *obj) diff --git a/hw/nvram/spapr_nvram.c b/hw/nvram/spapr_nvram.c index aa5d2c1f5f..bc355a4348 100644 --- a/hw/nvram/spapr_nvram.c +++ b/hw/nvram/spapr_nvram.c @@ -144,7 +144,15 @@ static void spapr_nvram_realize(VIOsPAPRDevice *dev, Error **errp) int ret; if (nvram->blk) { - nvram->size = blk_getlength(nvram->blk); + int64_t len = blk_getlength(nvram->blk); + + if (len < 0) { + error_setg_errno(errp, -len, + "could not get length of backing image"); + return; + } + + nvram->size = len; ret = blk_set_perm(nvram->blk, BLK_PERM_CONSISTENT_READ | BLK_PERM_WRITE, diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c index 231ed9735b..89b6801f67 100644 --- a/hw/ppc/pnv.c +++ b/hw/ppc/pnv.c @@ -378,8 +378,9 @@ static void powernv_populate_ipmi_bt(ISADevice *d, void *fdt, int lpc_off) _FDT(node); g_free(name); - fdt_setprop(fdt, node, "reg", io_regs, sizeof(io_regs)); - fdt_setprop(fdt, node, "compatible", compatible, sizeof(compatible)); + _FDT((fdt_setprop(fdt, node, "reg", io_regs, sizeof(io_regs)))); + _FDT((fdt_setprop(fdt, node, "compatible", compatible, + sizeof(compatible)))); /* Mark it as reserved to avoid Linux trying to claim it */ _FDT((fdt_setprop_string(fdt, node, "status", "reserved"))); diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index ab3aab1279..91b4057933 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -57,6 +57,7 @@ #include "hw/pci/pci.h" #include "hw/scsi/scsi.h" #include "hw/virtio/virtio-scsi.h" +#include "hw/virtio/vhost-scsi-common.h" #include "exec/address-spaces.h" #include "hw/usb.h" @@ -182,25 +183,19 @@ static int spapr_fixup_cpu_smt_dt(void *fdt, int offset, PowerPCCPU *cpu, return ret; } -static int spapr_fixup_cpu_numa_dt(void *fdt, int offset, CPUState *cs) +static int spapr_fixup_cpu_numa_dt(void *fdt, int offset, PowerPCCPU *cpu) { - int ret = 0; - PowerPCCPU *cpu = POWERPC_CPU(cs); int index = ppc_get_vcpu_dt_id(cpu); uint32_t associativity[] = {cpu_to_be32(0x5), cpu_to_be32(0x0), cpu_to_be32(0x0), cpu_to_be32(0x0), - cpu_to_be32(cs->numa_node), + cpu_to_be32(cpu->node_id), cpu_to_be32(index)}; /* Advertise NUMA via ibm,associativity */ - if (nb_numa_nodes > 1) { - ret = fdt_setprop(fdt, offset, "ibm,associativity", associativity, + return fdt_setprop(fdt, offset, "ibm,associativity", associativity, sizeof(associativity)); - } - - return ret; } /* Populate the "ibm,pa-features" property */ @@ -325,9 +320,11 @@ static int spapr_fixup_cpu_dt(void *fdt, sPAPRMachineState *spapr) return ret; } - ret = spapr_fixup_cpu_numa_dt(fdt, offset, cs); - if (ret < 0) { - return ret; + if (nb_numa_nodes > 1) { + ret = spapr_fixup_cpu_numa_dt(fdt, offset, cpu); + if (ret < 0) { + return ret; + } } ret = spapr_fixup_cpu_smt_dt(fdt, offset, cpu, compat_smt); @@ -456,15 +453,13 @@ static void spapr_populate_cpu_dt(CPUState *cs, void *fdt, int offset, uint32_t pft_size_prop[] = {0, cpu_to_be32(spapr->htab_shift)}; int compat_smt = MIN(smp_threads, ppc_compat_max_threads(cpu)); sPAPRDRConnector *drc; - sPAPRDRConnectorClass *drck; int drc_index; uint32_t radix_AP_encodings[PPC_PAGE_SIZES_MAX_SZ]; int i; - drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_CPU, index); + drc = spapr_drc_by_id(TYPE_SPAPR_DRC_CPU, index); if (drc) { - drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); - drc_index = drck->get_index(drc); + drc_index = spapr_drc_index(drc); _FDT((fdt_setprop_cell(fdt, offset, "ibm,my-drc-index", drc_index))); } @@ -542,7 +537,9 @@ static void spapr_populate_cpu_dt(CPUState *cs, void *fdt, int offset, _FDT((fdt_setprop(fdt, offset, "ibm,pft-size", pft_size_prop, sizeof(pft_size_prop)))); - _FDT(spapr_fixup_cpu_numa_dt(fdt, offset, cs)); + if (nb_numa_nodes > 1) { + _FDT(spapr_fixup_cpu_numa_dt(fdt, offset, cpu)); + } _FDT(spapr_fixup_cpu_smt_dt(fdt, offset, cpu, compat_smt)); @@ -654,15 +651,13 @@ static int spapr_populate_drconf_memory(sPAPRMachineState *spapr, void *fdt) if (i >= hotplug_lmb_start) { sPAPRDRConnector *drc; - sPAPRDRConnectorClass *drck; - drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_LMB, i); + drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, i); g_assert(drc); - drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); dynamic_memory[0] = cpu_to_be32(addr >> 32); dynamic_memory[1] = cpu_to_be32(addr & 0xffffffff); - dynamic_memory[2] = cpu_to_be32(drck->get_index(drc)); + dynamic_memory[2] = cpu_to_be32(spapr_drc_index(drc)); dynamic_memory[3] = cpu_to_be32(0); /* reserved */ dynamic_memory[4] = cpu_to_be32(numa_get_node(addr, NULL)); if (memory_region_present(get_system_memory(), addr)) { @@ -1915,7 +1910,7 @@ static void spapr_create_lmb_dr_connectors(sPAPRMachineState *spapr) uint64_t addr; addr = i * lmb_size + spapr->hotplug_memory.base; - drc = spapr_dr_connector_new(OBJECT(spapr), SPAPR_DR_CONNECTOR_TYPE_LMB, + drc = spapr_dr_connector_new(OBJECT(spapr), TYPE_SPAPR_DRC_LMB, addr/lmb_size); qemu_register_reset(spapr_drc_reset, drc); } @@ -2012,8 +2007,7 @@ static void spapr_init_cpus(sPAPRMachineState *spapr) if (mc->has_hotpluggable_cpus) { sPAPRDRConnector *drc = - spapr_dr_connector_new(OBJECT(spapr), - SPAPR_DR_CONNECTOR_TYPE_CPU, + spapr_dr_connector_new(OBJECT(spapr), TYPE_SPAPR_DRC_CPU, (core_id / smp_threads) * smt); qemu_register_reset(spapr_drc_reset, drc); @@ -2344,10 +2338,6 @@ static void ppc_spapr_init(MachineState *machine) register_savevm_live(NULL, "spapr/htab", -1, 1, &savevm_htab_handlers, spapr); - /* used by RTAS */ - QTAILQ_INIT(&spapr->ccs_list); - qemu_register_reset(spapr_ccs_reset_hook, spapr); - qemu_register_boot_set(spapr_boot_set, spapr); if (kvm_enabled()) { @@ -2388,6 +2378,7 @@ static char *spapr_get_fw_dev_path(FWPathProvider *p, BusState *bus, ((type *)object_dynamic_cast(OBJECT(obj), (name))) SCSIDevice *d = CAST(SCSIDevice, dev, TYPE_SCSI_DEVICE); sPAPRPHBState *phb = CAST(sPAPRPHBState, dev, TYPE_SPAPR_PCI_HOST_BRIDGE); + VHostSCSICommon *vsc = CAST(VHostSCSICommon, dev, TYPE_VHOST_SCSI_COMMON); if (d) { void *spapr = CAST(void, bus->parent, "spapr-vscsi"); @@ -2444,6 +2435,12 @@ static char *spapr_get_fw_dev_path(FWPathProvider *p, BusState *bus, return g_strdup_printf("pci@%"PRIX64, phb->buid); } + if (vsc) { + /* Same logic as virtio above */ + unsigned id = 0x1000000 | (vsc->target << 16) | vsc->lun; + return g_strdup_printf("disk@%"PRIX64, (uint64_t)id << 32); + } + return NULL; } @@ -2533,8 +2530,8 @@ static void spapr_add_lmbs(DeviceState *dev, uint64_t addr_start, uint64_t size, uint64_t addr = addr_start; for (i = 0; i < nr_lmbs; i++) { - drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_LMB, - addr/SPAPR_MEMORY_BLOCK_SIZE); + drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, + addr / SPAPR_MEMORY_BLOCK_SIZE); g_assert(drc); fdt = create_device_tree(&fdt_size); @@ -2555,12 +2552,12 @@ static void spapr_add_lmbs(DeviceState *dev, uint64_t addr_start, uint64_t size, */ if (dev->hotplugged) { if (dedicated_hp_event_source) { - drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_LMB, - addr_start / SPAPR_MEMORY_BLOCK_SIZE); + drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, + addr_start / SPAPR_MEMORY_BLOCK_SIZE); drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); spapr_hotplug_req_add_by_count_indexed(SPAPR_DR_CONNECTOR_TYPE_LMB, nr_lmbs, - drck->get_index(drc)); + spapr_drc_index(drc)); } else { spapr_hotplug_req_add_by_count(SPAPR_DR_CONNECTOR_TYPE_LMB, nr_lmbs); @@ -2673,8 +2670,8 @@ static sPAPRDIMMState *spapr_recover_pending_dimm_state(sPAPRMachineState *ms, addr = addr_start; for (i = 0; i < nr_lmbs; i++) { - drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_LMB, - addr / SPAPR_MEMORY_BLOCK_SIZE); + drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, + addr / SPAPR_MEMORY_BLOCK_SIZE); g_assert(drc); if (drc->indicator_state != SPAPR_DR_INDICATOR_STATE_INACTIVE) { avail_lmbs++; @@ -2757,8 +2754,8 @@ static void spapr_memory_unplug_request(HotplugHandler *hotplug_dev, addr = addr_start; for (i = 0; i < nr_lmbs; i++) { - drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_LMB, - addr / SPAPR_MEMORY_BLOCK_SIZE); + drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, + addr / SPAPR_MEMORY_BLOCK_SIZE); g_assert(drc); drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); @@ -2766,12 +2763,11 @@ static void spapr_memory_unplug_request(HotplugHandler *hotplug_dev, addr += SPAPR_MEMORY_BLOCK_SIZE; } - drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_LMB, - addr_start / SPAPR_MEMORY_BLOCK_SIZE); + drc = spapr_drc_by_id(TYPE_SPAPR_DRC_LMB, + addr_start / SPAPR_MEMORY_BLOCK_SIZE); drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); spapr_hotplug_req_remove_by_count_indexed(SPAPR_DR_CONNECTOR_TYPE_LMB, - nr_lmbs, - drck->get_index(drc)); + nr_lmbs, spapr_drc_index(drc)); out: error_propagate(errp, local_err); } @@ -2839,7 +2835,7 @@ void spapr_core_unplug_request(HotplugHandler *hotplug_dev, DeviceState *dev, return; } - drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_CPU, index * smt); + drc = spapr_drc_by_id(TYPE_SPAPR_DRC_CPU, index * smt); g_assert(drc); drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); @@ -2874,7 +2870,7 @@ static void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev, cc->core_id); return; } - drc = spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_CPU, index * smt); + drc = spapr_drc_by_id(TYPE_SPAPR_DRC_CPU, index * smt); g_assert(drc || !mc->has_hotpluggable_cpus); @@ -2922,11 +2918,9 @@ static void spapr_core_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev, MachineClass *mc = MACHINE_GET_CLASS(hotplug_dev); Error *local_err = NULL; CPUCore *cc = CPU_CORE(dev); - sPAPRCPUCore *sc = SPAPR_CPU_CORE(dev); char *base_core_type = spapr_get_cpu_core_type(machine->cpu_model); const char *type = object_get_typename(OBJECT(dev)); CPUArchId *core_slot; - int node_id; int index; if (dev->hotplugged && !mc->has_hotpluggable_cpus) { @@ -2967,20 +2961,7 @@ static void spapr_core_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev, goto out; } - node_id = core_slot->props.node_id; - if (!core_slot->props.has_node_id) { - /* by default CPUState::numa_node was 0 if it's not set via CLI - * keep it this way for now but in future we probably should - * refuse to start up with incomplete numa mapping */ - node_id = 0; - } - if (sc->node_id == CPU_UNSET_NUMA_NODE_ID) { - sc->node_id = node_id; - } else if (sc->node_id != node_id) { - error_setg(&local_err, "node-id %d must match numa node specified" - "with -numa option for cpu-index %d", sc->node_id, cc->core_id); - goto out; - } + numa_cpu_pre_plug(core_slot, dev, &local_err); out: g_free(base_core_type); diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c index ff7058ecc0..029a14120e 100644 --- a/hw/ppc/spapr_cpu_core.c +++ b/hw/ppc/spapr_cpu_core.c @@ -184,15 +184,17 @@ static void spapr_cpu_core_realize(DeviceState *dev, Error **errp) for (i = 0; i < cc->nr_threads; i++) { char id[32]; CPUState *cs; + PowerPCCPU *cpu; obj = sc->threads + i * size; object_initialize(obj, size, typename); cs = CPU(obj); + cpu = POWERPC_CPU(cs); cs->cpu_index = cc->core_id + i; /* Set NUMA node for the threads belonged to core */ - cs->numa_node = sc->node_id; + cpu->node_id = sc->node_id; snprintf(id, sizeof(id), "thread[%d]", i); object_property_add_child(OBJECT(sc), id, obj, &local_err); diff --git a/hw/ppc/spapr_drc.c b/hw/ppc/spapr_drc.c index cc2400bcd5..39e7f3080a 100644 --- a/hw/ppc/spapr_drc.c +++ b/hw/ppc/spapr_drc.c @@ -27,29 +27,23 @@ #define DRC_INDEX_TYPE_SHIFT 28 #define DRC_INDEX_ID_MASK ((1ULL << DRC_INDEX_TYPE_SHIFT) - 1) -static sPAPRDRConnectorTypeShift get_type_shift(sPAPRDRConnectorType type) +sPAPRDRConnectorType spapr_drc_type(sPAPRDRConnector *drc) { - uint32_t shift = 0; - - /* make sure this isn't SPAPR_DR_CONNECTOR_TYPE_ANY, or some - * other wonky value. - */ - g_assert(is_power_of_2(type)); + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); - while (type != (1 << shift)) { - shift++; - } - return shift; + return 1 << drck->typeshift; } -static uint32_t get_index(sPAPRDRConnector *drc) +uint32_t spapr_drc_index(sPAPRDRConnector *drc) { + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + /* no set format for a drc index: it only needs to be globally * unique. this is how we encode the DRC type on bare-metal * however, so might as well do that here */ - return (get_type_shift(drc->type) << DRC_INDEX_TYPE_SHIFT) | - (drc->id & DRC_INDEX_ID_MASK); + return (drck->typeshift << DRC_INDEX_TYPE_SHIFT) + | (drc->id & DRC_INDEX_ID_MASK); } static uint32_t set_isolation_state(sPAPRDRConnector *drc, @@ -57,7 +51,17 @@ static uint32_t set_isolation_state(sPAPRDRConnector *drc, { sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); - trace_spapr_drc_set_isolation_state(get_index(drc), state); + trace_spapr_drc_set_isolation_state(spapr_drc_index(drc), state); + + /* if the guest is configuring a device attached to this DRC, we + * should reset the configuration state at this point since it may + * no longer be reliable (guest released device and needs to start + * over, or unplug occurred so the FDT is no longer valid) + */ + if (state == SPAPR_DR_ISOLATION_STATE_ISOLATED) { + g_free(drc->ccs); + drc->ccs = NULL; + } if (state == SPAPR_DR_ISOLATION_STATE_UNISOLATED) { /* cannot unisolate a non-existent resource, and, or resources @@ -79,7 +83,7 @@ static uint32_t set_isolation_state(sPAPRDRConnector *drc, * If the LMB being removed doesn't belong to a DIMM device that is * actually being unplugged, fail the isolation request here. */ - if (drc->type == SPAPR_DR_CONNECTOR_TYPE_LMB) { + if (spapr_drc_type(drc) == SPAPR_DR_CONNECTOR_TYPE_LMB) { if ((state == SPAPR_DR_ISOLATION_STATE_ISOLATED) && !drc->awaiting_release) { return RTAS_OUT_HW_ERROR; @@ -98,11 +102,12 @@ static uint32_t set_isolation_state(sPAPRDRConnector *drc, * PAPR+ 2.7, 13.4 */ if (drc->awaiting_release) { + uint32_t drc_index = spapr_drc_index(drc); if (drc->configured) { - trace_spapr_drc_set_isolation_state_finalizing(get_index(drc)); + trace_spapr_drc_set_isolation_state_finalizing(drc_index); drck->detach(drc, DEVICE(drc->dev), NULL); } else { - trace_spapr_drc_set_isolation_state_deferring(get_index(drc)); + trace_spapr_drc_set_isolation_state_deferring(drc_index); } } drc->configured = false; @@ -114,7 +119,7 @@ static uint32_t set_isolation_state(sPAPRDRConnector *drc, static uint32_t set_indicator_state(sPAPRDRConnector *drc, sPAPRDRIndicatorState state) { - trace_spapr_drc_set_indicator_state(get_index(drc), state); + trace_spapr_drc_set_indicator_state(spapr_drc_index(drc), state); drc->indicator_state = state; return RTAS_OUT_SUCCESS; } @@ -124,7 +129,7 @@ static uint32_t set_allocation_state(sPAPRDRConnector *drc, { sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); - trace_spapr_drc_set_allocation_state(get_index(drc), state); + trace_spapr_drc_set_allocation_state(spapr_drc_index(drc), state); if (state == SPAPR_DR_ALLOCATION_STATE_USABLE) { /* if there's no resource/device associated with the DRC, there's @@ -148,11 +153,12 @@ static uint32_t set_allocation_state(sPAPRDRConnector *drc, } } - if (drc->type != SPAPR_DR_CONNECTOR_TYPE_PCI) { + if (spapr_drc_type(drc) != SPAPR_DR_CONNECTOR_TYPE_PCI) { drc->allocation_state = state; if (drc->awaiting_release && drc->allocation_state == SPAPR_DR_ALLOCATION_STATE_UNUSABLE) { - trace_spapr_drc_set_allocation_state_finalizing(get_index(drc)); + uint32_t drc_index = spapr_drc_index(drc); + trace_spapr_drc_set_allocation_state_finalizing(drc_index); drck->detach(drc, DEVICE(drc->dev), NULL); } else if (drc->allocation_state == SPAPR_DR_ALLOCATION_STATE_USABLE) { drc->awaiting_allocation = false; @@ -161,36 +167,11 @@ static uint32_t set_allocation_state(sPAPRDRConnector *drc, return RTAS_OUT_SUCCESS; } -static uint32_t get_type(sPAPRDRConnector *drc) -{ - return drc->type; -} - static const char *get_name(sPAPRDRConnector *drc) { return drc->name; } -static const void *get_fdt(sPAPRDRConnector *drc, int *fdt_start_offset) -{ - if (fdt_start_offset) { - *fdt_start_offset = drc->fdt_start_offset; - } - return drc->fdt; -} - -static void set_configured(sPAPRDRConnector *drc) -{ - trace_spapr_drc_set_configured(get_index(drc)); - - if (drc->isolation_state != SPAPR_DR_ISOLATION_STATE_UNISOLATED) { - /* guest should be not configuring an isolated device */ - trace_spapr_drc_set_configured_skipping(get_index(drc)); - return; - } - drc->configured = true; -} - /* has the guest been notified of device attachment? */ static void set_signalled(sPAPRDRConnector *drc) { @@ -207,7 +188,7 @@ static void set_signalled(sPAPRDRConnector *drc) static uint32_t entity_sense(sPAPRDRConnector *drc, sPAPRDREntitySense *state) { if (drc->dev) { - if (drc->type != SPAPR_DR_CONNECTOR_TYPE_PCI && + if (spapr_drc_type(drc) != SPAPR_DR_CONNECTOR_TYPE_PCI && drc->allocation_state == SPAPR_DR_ALLOCATION_STATE_UNUSABLE) { /* for logical DR, we return a state of UNUSABLE * iff the allocation state UNUSABLE. @@ -225,7 +206,7 @@ static uint32_t entity_sense(sPAPRDRConnector *drc, sPAPRDREntitySense *state) *state = SPAPR_DR_ENTITY_SENSE_PRESENT; } } else { - if (drc->type == SPAPR_DR_CONNECTOR_TYPE_PCI) { + if (spapr_drc_type(drc) == SPAPR_DR_CONNECTOR_TYPE_PCI) { /* PCI devices, and only PCI devices, use EMPTY * in cases where we'd otherwise use UNUSABLE */ @@ -235,7 +216,7 @@ static uint32_t entity_sense(sPAPRDRConnector *drc, sPAPRDREntitySense *state) } } - trace_spapr_drc_entity_sense(get_index(drc), *state); + trace_spapr_drc_entity_sense(spapr_drc_index(drc), *state); return RTAS_OUT_SUCCESS; } @@ -243,17 +224,7 @@ static void prop_get_index(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) { sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(obj); - sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); - uint32_t value = (uint32_t)drck->get_index(drc); - visit_type_uint32(v, name, &value, errp); -} - -static void prop_get_type(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(obj); - sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); - uint32_t value = (uint32_t)drck->get_type(drc); + uint32_t value = spapr_drc_index(drc); visit_type_uint32(v, name, &value, errp); } @@ -264,17 +235,6 @@ static char *prop_get_name(Object *obj, Error **errp) return g_strdup(drck->get_name(drc)); } -static void prop_get_entity_sense(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(obj); - sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); - uint32_t value; - - drck->entity_sense(drc, &value); - visit_type_uint32(v, name, &value, errp); -} - static void prop_get_fdt(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) { @@ -354,13 +314,13 @@ static void prop_get_fdt(Object *obj, Visitor *v, const char *name, static void attach(sPAPRDRConnector *drc, DeviceState *d, void *fdt, int fdt_start_offset, bool coldplug, Error **errp) { - trace_spapr_drc_attach(get_index(drc)); + trace_spapr_drc_attach(spapr_drc_index(drc)); if (drc->isolation_state != SPAPR_DR_ISOLATION_STATE_ISOLATED) { error_setg(errp, "an attached device is still awaiting release"); return; } - if (drc->type == SPAPR_DR_CONNECTOR_TYPE_PCI) { + if (spapr_drc_type(drc) == SPAPR_DR_CONNECTOR_TYPE_PCI) { g_assert(drc->allocation_state == SPAPR_DR_ALLOCATION_STATE_USABLE); } g_assert(fdt || coldplug); @@ -372,7 +332,7 @@ static void attach(sPAPRDRConnector *drc, DeviceState *d, void *fdt, * may be accessing the device, we can easily crash the guest, so we * we defer completion of removal in such cases to the reset() hook. */ - if (drc->type == SPAPR_DR_CONNECTOR_TYPE_PCI) { + if (spapr_drc_type(drc) == SPAPR_DR_CONNECTOR_TYPE_PCI) { drc->isolation_state = SPAPR_DR_ISOLATION_STATE_UNISOLATED; } drc->indicator_state = SPAPR_DR_INDICATOR_STATE_ACTIVE; @@ -390,10 +350,10 @@ static void attach(sPAPRDRConnector *drc, DeviceState *d, void *fdt, * 'physical' DR resources such as PCI where each device/resource is * signalled individually. */ - drc->signalled = (drc->type != SPAPR_DR_CONNECTOR_TYPE_PCI) + drc->signalled = (spapr_drc_type(drc) != SPAPR_DR_CONNECTOR_TYPE_PCI) ? true : coldplug; - if (drc->type != SPAPR_DR_CONNECTOR_TYPE_PCI) { + if (spapr_drc_type(drc) != SPAPR_DR_CONNECTOR_TYPE_PCI) { drc->awaiting_allocation = true; } @@ -405,7 +365,7 @@ static void attach(sPAPRDRConnector *drc, DeviceState *d, void *fdt, static void detach(sPAPRDRConnector *drc, DeviceState *d, Error **errp) { - trace_spapr_drc_detach(get_index(drc)); + trace_spapr_drc_detach(spapr_drc_index(drc)); /* if we've signalled device presence to the guest, or if the guest * has gone ahead and configured the device (via manually-executed @@ -428,14 +388,14 @@ static void detach(sPAPRDRConnector *drc, DeviceState *d, Error **errp) } if (drc->isolation_state != SPAPR_DR_ISOLATION_STATE_ISOLATED) { - trace_spapr_drc_awaiting_isolated(get_index(drc)); + trace_spapr_drc_awaiting_isolated(spapr_drc_index(drc)); drc->awaiting_release = true; return; } - if (drc->type != SPAPR_DR_CONNECTOR_TYPE_PCI && + if (spapr_drc_type(drc) != SPAPR_DR_CONNECTOR_TYPE_PCI && drc->allocation_state != SPAPR_DR_ALLOCATION_STATE_UNUSABLE) { - trace_spapr_drc_awaiting_unusable(get_index(drc)); + trace_spapr_drc_awaiting_unusable(spapr_drc_index(drc)); drc->awaiting_release = true; return; } @@ -443,15 +403,15 @@ static void detach(sPAPRDRConnector *drc, DeviceState *d, Error **errp) if (drc->awaiting_allocation) { if (!drc->awaiting_allocation_skippable) { drc->awaiting_release = true; - trace_spapr_drc_awaiting_allocation(get_index(drc)); + trace_spapr_drc_awaiting_allocation(spapr_drc_index(drc)); return; } } drc->indicator_state = SPAPR_DR_INDICATOR_STATE_INACTIVE; - /* Calling release callbacks based on drc->type. */ - switch (drc->type) { + /* Calling release callbacks based on spapr_drc_type(drc). */ + switch (spapr_drc_type(drc)) { case SPAPR_DR_CONNECTOR_TYPE_CPU: spapr_core_release(drc->dev); break; @@ -487,7 +447,11 @@ static void reset(DeviceState *d) sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); sPAPRDREntitySense state; - trace_spapr_drc_reset(drck->get_index(drc)); + trace_spapr_drc_reset(spapr_drc_index(drc)); + + g_free(drc->ccs); + drc->ccs = NULL; + /* immediately upon reset we can safely assume DRCs whose devices * are pending removal can be safely removed, and that they will * subsequently be left in an ISOLATED state. move the DRC to this @@ -507,7 +471,7 @@ static void reset(DeviceState *d) } /* non-PCI devices may be awaiting a transition to UNUSABLE */ - if (drc->type != SPAPR_DR_CONNECTOR_TYPE_PCI && + if (spapr_drc_type(drc) != SPAPR_DR_CONNECTOR_TYPE_PCI && drc->awaiting_release) { drck->set_allocation_state(drc, SPAPR_DR_ALLOCATION_STATE_UNUSABLE); } @@ -536,22 +500,18 @@ static bool spapr_drc_needed(void *opaque) * If there is dev plugged in, we need to migrate the DRC state when * it is different from cold-plugged state */ - switch (drc->type) { + switch (spapr_drc_type(drc)) { case SPAPR_DR_CONNECTOR_TYPE_PCI: - rc = !((drc->isolation_state == SPAPR_DR_ISOLATION_STATE_UNISOLATED) && - (drc->allocation_state == SPAPR_DR_ALLOCATION_STATE_USABLE) && - drc->configured && drc->signalled && !drc->awaiting_release); - break; case SPAPR_DR_CONNECTOR_TYPE_CPU: case SPAPR_DR_CONNECTOR_TYPE_LMB: - rc = !((drc->isolation_state == SPAPR_DR_ISOLATION_STATE_ISOLATED) && - (drc->allocation_state == SPAPR_DR_ALLOCATION_STATE_UNUSABLE) && + rc = !((drc->isolation_state == SPAPR_DR_ISOLATION_STATE_UNISOLATED) && + (drc->allocation_state == SPAPR_DR_ALLOCATION_STATE_USABLE) && drc->configured && drc->signalled && !drc->awaiting_release); break; case SPAPR_DR_CONNECTOR_TYPE_PHB: case SPAPR_DR_CONNECTOR_TYPE_VIO: default: - g_assert(false); + g_assert_not_reached(); } return rc; } @@ -576,13 +536,12 @@ static const VMStateDescription vmstate_spapr_drc = { static void realize(DeviceState *d, Error **errp) { sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(d); - sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); Object *root_container; char link_name[256]; gchar *child_name; Error *err = NULL; - trace_spapr_drc_realize(drck->get_index(drc)); + trace_spapr_drc_realize(spapr_drc_index(drc)); /* NOTE: we do this as part of realize/unrealize due to the fact * that the guest will communicate with the DRC via RTAS calls * referencing the global DRC index. By unlinking the DRC @@ -591,9 +550,9 @@ static void realize(DeviceState *d, Error **errp) * existing in the composition tree */ root_container = container_get(object_get_root(), DRC_CONTAINER_PATH); - snprintf(link_name, sizeof(link_name), "%x", drck->get_index(drc)); + snprintf(link_name, sizeof(link_name), "%x", spapr_drc_index(drc)); child_name = object_get_canonical_path_component(OBJECT(drc)); - trace_spapr_drc_realize_child(drck->get_index(drc), child_name); + trace_spapr_drc_realize_child(spapr_drc_index(drc), child_name); object_property_add_alias(root_container, link_name, drc->owner, child_name, &err); if (err) { @@ -601,22 +560,21 @@ static void realize(DeviceState *d, Error **errp) object_unref(OBJECT(drc)); } g_free(child_name); - vmstate_register(DEVICE(drc), drck->get_index(drc), &vmstate_spapr_drc, + vmstate_register(DEVICE(drc), spapr_drc_index(drc), &vmstate_spapr_drc, drc); - trace_spapr_drc_realize_complete(drck->get_index(drc)); + trace_spapr_drc_realize_complete(spapr_drc_index(drc)); } static void unrealize(DeviceState *d, Error **errp) { sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(d); - sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); Object *root_container; char name[256]; Error *err = NULL; - trace_spapr_drc_unrealize(drck->get_index(drc)); + trace_spapr_drc_unrealize(spapr_drc_index(drc)); root_container = container_get(object_get_root(), DRC_CONTAINER_PATH); - snprintf(name, sizeof(name), "%x", drck->get_index(drc)); + snprintf(name, sizeof(name), "%x", spapr_drc_index(drc)); object_property_del(root_container, name, &err); if (err) { error_report_err(err); @@ -624,20 +582,16 @@ static void unrealize(DeviceState *d, Error **errp) } } -sPAPRDRConnector *spapr_dr_connector_new(Object *owner, - sPAPRDRConnectorType type, +sPAPRDRConnector *spapr_dr_connector_new(Object *owner, const char *type, uint32_t id) { - sPAPRDRConnector *drc = - SPAPR_DR_CONNECTOR(object_new(TYPE_SPAPR_DR_CONNECTOR)); + sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(object_new(type)); char *prop_name; - g_assert(type); - - drc->type = type; drc->id = id; drc->owner = owner; - prop_name = g_strdup_printf("dr-connector[%"PRIu32"]", get_index(drc)); + prop_name = g_strdup_printf("dr-connector[%"PRIu32"]", + spapr_drc_index(drc)); object_property_add_child(owner, prop_name, OBJECT(drc), NULL); object_property_set_bool(OBJECT(drc), true, "realized", NULL); g_free(prop_name); @@ -663,7 +617,7 @@ sPAPRDRConnector *spapr_dr_connector_new(Object *owner, * DRC names as documented by PAPR+ v2.7, 13.5.2.4 * location codes as documented by PAPR+ v2.7, 12.3.1.5 */ - switch (drc->type) { + switch (spapr_drc_type(drc)) { case SPAPR_DR_CONNECTOR_TYPE_CPU: drc->name = g_strdup_printf("CPU %d", id); break; @@ -682,7 +636,7 @@ sPAPRDRConnector *spapr_dr_connector_new(Object *owner, } /* PCI slot always start in a USABLE state, and stay there */ - if (drc->type == SPAPR_DR_CONNECTOR_TYPE_PCI) { + if (spapr_drc_type(drc) == SPAPR_DR_CONNECTOR_TYPE_PCI) { drc->allocation_state = SPAPR_DR_ALLOCATION_STATE_USABLE; } @@ -693,20 +647,10 @@ static void spapr_dr_connector_instance_init(Object *obj) { sPAPRDRConnector *drc = SPAPR_DR_CONNECTOR(obj); - object_property_add_uint32_ptr(obj, "isolation-state", - &drc->isolation_state, NULL); - object_property_add_uint32_ptr(obj, "indicator-state", - &drc->indicator_state, NULL); - object_property_add_uint32_ptr(obj, "allocation-state", - &drc->allocation_state, NULL); object_property_add_uint32_ptr(obj, "id", &drc->id, NULL); object_property_add(obj, "index", "uint32", prop_get_index, NULL, NULL, NULL, NULL); - object_property_add(obj, "connector_type", "uint32", prop_get_type, - NULL, NULL, NULL, NULL); object_property_add_str(obj, "name", prop_get_name, NULL, NULL); - object_property_add(obj, "entity-sense", "uint32", prop_get_entity_sense, - NULL, NULL, NULL, NULL); object_property_add(obj, "fdt", "struct", prop_get_fdt, NULL, NULL, NULL, NULL); } @@ -722,11 +666,7 @@ static void spapr_dr_connector_class_init(ObjectClass *k, void *data) drck->set_isolation_state = set_isolation_state; drck->set_indicator_state = set_indicator_state; drck->set_allocation_state = set_allocation_state; - drck->get_index = get_index; - drck->get_type = get_type; drck->get_name = get_name; - drck->get_fdt = get_fdt; - drck->set_configured = set_configured; drck->entity_sense = entity_sense; drck->attach = attach; drck->detach = detach; @@ -738,6 +678,30 @@ static void spapr_dr_connector_class_init(ObjectClass *k, void *data) dk->user_creatable = false; } +static void spapr_drc_cpu_class_init(ObjectClass *k, void *data) +{ + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_CLASS(k); + + drck->typeshift = SPAPR_DR_CONNECTOR_TYPE_SHIFT_CPU; + drck->typename = "CPU"; +} + +static void spapr_drc_pci_class_init(ObjectClass *k, void *data) +{ + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_CLASS(k); + + drck->typeshift = SPAPR_DR_CONNECTOR_TYPE_SHIFT_PCI; + drck->typename = "28"; +} + +static void spapr_drc_lmb_class_init(ObjectClass *k, void *data) +{ + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_CLASS(k); + + drck->typeshift = SPAPR_DR_CONNECTOR_TYPE_SHIFT_LMB; + drck->typename = "MEM"; +} + static const TypeInfo spapr_dr_connector_info = { .name = TYPE_SPAPR_DR_CONNECTOR, .parent = TYPE_DEVICE, @@ -745,18 +709,47 @@ static const TypeInfo spapr_dr_connector_info = { .instance_init = spapr_dr_connector_instance_init, .class_size = sizeof(sPAPRDRConnectorClass), .class_init = spapr_dr_connector_class_init, + .abstract = true, }; -static void spapr_drc_register_types(void) -{ - type_register_static(&spapr_dr_connector_info); -} +static const TypeInfo spapr_drc_physical_info = { + .name = TYPE_SPAPR_DRC_PHYSICAL, + .parent = TYPE_SPAPR_DR_CONNECTOR, + .instance_size = sizeof(sPAPRDRConnector), + .abstract = true, +}; -type_init(spapr_drc_register_types) +static const TypeInfo spapr_drc_logical_info = { + .name = TYPE_SPAPR_DRC_LOGICAL, + .parent = TYPE_SPAPR_DR_CONNECTOR, + .instance_size = sizeof(sPAPRDRConnector), + .abstract = true, +}; + +static const TypeInfo spapr_drc_cpu_info = { + .name = TYPE_SPAPR_DRC_CPU, + .parent = TYPE_SPAPR_DRC_LOGICAL, + .instance_size = sizeof(sPAPRDRConnector), + .class_init = spapr_drc_cpu_class_init, +}; + +static const TypeInfo spapr_drc_pci_info = { + .name = TYPE_SPAPR_DRC_PCI, + .parent = TYPE_SPAPR_DRC_PHYSICAL, + .instance_size = sizeof(sPAPRDRConnector), + .class_init = spapr_drc_pci_class_init, +}; + +static const TypeInfo spapr_drc_lmb_info = { + .name = TYPE_SPAPR_DRC_LMB, + .parent = TYPE_SPAPR_DRC_LOGICAL, + .instance_size = sizeof(sPAPRDRConnector), + .class_init = spapr_drc_lmb_class_init, +}; /* helper functions for external users */ -sPAPRDRConnector *spapr_dr_connector_by_index(uint32_t index) +sPAPRDRConnector *spapr_drc_by_index(uint32_t index) { Object *obj; char name[256]; @@ -767,37 +760,13 @@ sPAPRDRConnector *spapr_dr_connector_by_index(uint32_t index) return !obj ? NULL : SPAPR_DR_CONNECTOR(obj); } -sPAPRDRConnector *spapr_dr_connector_by_id(sPAPRDRConnectorType type, - uint32_t id) +sPAPRDRConnector *spapr_drc_by_id(const char *type, uint32_t id) { - return spapr_dr_connector_by_index( - (get_type_shift(type) << DRC_INDEX_TYPE_SHIFT) | - (id & DRC_INDEX_ID_MASK)); -} - -/* generate a string the describes the DRC to encode into the - * device tree. - * - * as documented by PAPR+ v2.7, 13.5.2.6 and C.6.1 - */ -static const char *spapr_drc_get_type_str(sPAPRDRConnectorType type) -{ - switch (type) { - case SPAPR_DR_CONNECTOR_TYPE_CPU: - return "CPU"; - case SPAPR_DR_CONNECTOR_TYPE_PHB: - return "PHB"; - case SPAPR_DR_CONNECTOR_TYPE_VIO: - return "SLOT"; - case SPAPR_DR_CONNECTOR_TYPE_PCI: - return "28"; - case SPAPR_DR_CONNECTOR_TYPE_LMB: - return "MEM"; - default: - g_assert(false); - } + sPAPRDRConnectorClass *drck + = SPAPR_DR_CONNECTOR_CLASS(object_class_by_name(type)); - return NULL; + return spapr_drc_by_index(drck->typeshift << DRC_INDEX_TYPE_SHIFT + | (id & DRC_INDEX_ID_MASK)); } /** @@ -862,14 +831,14 @@ int spapr_drc_populate_dt(void *fdt, int fdt_offset, Object *owner, continue; } - if ((drc->type & drc_type_mask) == 0) { + if ((spapr_drc_type(drc) & drc_type_mask) == 0) { continue; } drc_count++; /* ibm,drc-indexes */ - drc_index = cpu_to_be32(drck->get_index(drc)); + drc_index = cpu_to_be32(spapr_drc_index(drc)); g_array_append_val(drc_indexes, drc_index); /* ibm,drc-power-domains */ @@ -881,8 +850,7 @@ int spapr_drc_populate_dt(void *fdt, int fdt_offset, Object *owner, drc_names = g_string_insert_len(drc_names, -1, "\0", 1); /* ibm,drc-types */ - drc_types = g_string_append(drc_types, - spapr_drc_get_type_str(drc->type)); + drc_types = g_string_append(drc_types, drck->typename); drc_types = g_string_insert_len(drc_types, -1, "\0", 1); } @@ -932,3 +900,276 @@ out: return ret; } + +/* + * RTAS calls + */ + +static bool sensor_type_is_dr(uint32_t sensor_type) +{ + switch (sensor_type) { + case RTAS_SENSOR_TYPE_ISOLATION_STATE: + case RTAS_SENSOR_TYPE_DR: + case RTAS_SENSOR_TYPE_ALLOCATION_STATE: + return true; + } + + return false; +} + +static void rtas_set_indicator(PowerPCCPU *cpu, sPAPRMachineState *spapr, + uint32_t token, uint32_t nargs, + target_ulong args, uint32_t nret, + target_ulong rets) +{ + uint32_t sensor_type; + uint32_t sensor_index; + uint32_t sensor_state; + uint32_t ret = RTAS_OUT_SUCCESS; + sPAPRDRConnector *drc; + sPAPRDRConnectorClass *drck; + + if (nargs != 3 || nret != 1) { + ret = RTAS_OUT_PARAM_ERROR; + goto out; + } + + sensor_type = rtas_ld(args, 0); + sensor_index = rtas_ld(args, 1); + sensor_state = rtas_ld(args, 2); + + if (!sensor_type_is_dr(sensor_type)) { + goto out_unimplemented; + } + + /* if this is a DR sensor we can assume sensor_index == drc_index */ + drc = spapr_drc_by_index(sensor_index); + if (!drc) { + trace_spapr_rtas_set_indicator_invalid(sensor_index); + ret = RTAS_OUT_PARAM_ERROR; + goto out; + } + drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + + switch (sensor_type) { + case RTAS_SENSOR_TYPE_ISOLATION_STATE: + ret = drck->set_isolation_state(drc, sensor_state); + break; + case RTAS_SENSOR_TYPE_DR: + ret = drck->set_indicator_state(drc, sensor_state); + break; + case RTAS_SENSOR_TYPE_ALLOCATION_STATE: + ret = drck->set_allocation_state(drc, sensor_state); + break; + default: + goto out_unimplemented; + } + +out: + rtas_st(rets, 0, ret); + return; + +out_unimplemented: + /* currently only DR-related sensors are implemented */ + trace_spapr_rtas_set_indicator_not_supported(sensor_index, sensor_type); + rtas_st(rets, 0, RTAS_OUT_NOT_SUPPORTED); +} + +static void rtas_get_sensor_state(PowerPCCPU *cpu, sPAPRMachineState *spapr, + uint32_t token, uint32_t nargs, + target_ulong args, uint32_t nret, + target_ulong rets) +{ + uint32_t sensor_type; + uint32_t sensor_index; + uint32_t sensor_state = 0; + sPAPRDRConnector *drc; + sPAPRDRConnectorClass *drck; + uint32_t ret = RTAS_OUT_SUCCESS; + + if (nargs != 2 || nret != 2) { + ret = RTAS_OUT_PARAM_ERROR; + goto out; + } + + sensor_type = rtas_ld(args, 0); + sensor_index = rtas_ld(args, 1); + + if (sensor_type != RTAS_SENSOR_TYPE_ENTITY_SENSE) { + /* currently only DR-related sensors are implemented */ + trace_spapr_rtas_get_sensor_state_not_supported(sensor_index, + sensor_type); + ret = RTAS_OUT_NOT_SUPPORTED; + goto out; + } + + drc = spapr_drc_by_index(sensor_index); + if (!drc) { + trace_spapr_rtas_get_sensor_state_invalid(sensor_index); + ret = RTAS_OUT_PARAM_ERROR; + goto out; + } + drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + ret = drck->entity_sense(drc, &sensor_state); + +out: + rtas_st(rets, 0, ret); + rtas_st(rets, 1, sensor_state); +} + +/* configure-connector work area offsets, int32_t units for field + * indexes, bytes for field offset/len values. + * + * as documented by PAPR+ v2.7, 13.5.3.5 + */ +#define CC_IDX_NODE_NAME_OFFSET 2 +#define CC_IDX_PROP_NAME_OFFSET 2 +#define CC_IDX_PROP_LEN 3 +#define CC_IDX_PROP_DATA_OFFSET 4 +#define CC_VAL_DATA_OFFSET ((CC_IDX_PROP_DATA_OFFSET + 1) * 4) +#define CC_WA_LEN 4096 + +static void configure_connector_st(target_ulong addr, target_ulong offset, + const void *buf, size_t len) +{ + cpu_physical_memory_write(ppc64_phys_to_real(addr + offset), + buf, MIN(len, CC_WA_LEN - offset)); +} + +static void rtas_ibm_configure_connector(PowerPCCPU *cpu, + sPAPRMachineState *spapr, + uint32_t token, uint32_t nargs, + target_ulong args, uint32_t nret, + target_ulong rets) +{ + uint64_t wa_addr; + uint64_t wa_offset; + uint32_t drc_index; + sPAPRDRConnector *drc; + sPAPRConfigureConnectorState *ccs; + sPAPRDRCCResponse resp = SPAPR_DR_CC_RESPONSE_CONTINUE; + int rc; + + if (nargs != 2 || nret != 1) { + rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); + return; + } + + wa_addr = ((uint64_t)rtas_ld(args, 1) << 32) | rtas_ld(args, 0); + + drc_index = rtas_ld(wa_addr, 0); + drc = spapr_drc_by_index(drc_index); + if (!drc) { + trace_spapr_rtas_ibm_configure_connector_invalid(drc_index); + rc = RTAS_OUT_PARAM_ERROR; + goto out; + } + + if (!drc->fdt) { + trace_spapr_rtas_ibm_configure_connector_missing_fdt(drc_index); + rc = SPAPR_DR_CC_RESPONSE_NOT_CONFIGURABLE; + goto out; + } + + ccs = drc->ccs; + if (!ccs) { + ccs = g_new0(sPAPRConfigureConnectorState, 1); + ccs->fdt_offset = drc->fdt_start_offset; + drc->ccs = ccs; + } + + do { + uint32_t tag; + const char *name; + const struct fdt_property *prop; + int fdt_offset_next, prop_len; + + tag = fdt_next_tag(drc->fdt, ccs->fdt_offset, &fdt_offset_next); + + switch (tag) { + case FDT_BEGIN_NODE: + ccs->fdt_depth++; + name = fdt_get_name(drc->fdt, ccs->fdt_offset, NULL); + + /* provide the name of the next OF node */ + wa_offset = CC_VAL_DATA_OFFSET; + rtas_st(wa_addr, CC_IDX_NODE_NAME_OFFSET, wa_offset); + configure_connector_st(wa_addr, wa_offset, name, strlen(name) + 1); + resp = SPAPR_DR_CC_RESPONSE_NEXT_CHILD; + break; + case FDT_END_NODE: + ccs->fdt_depth--; + if (ccs->fdt_depth == 0) { + sPAPRDRIsolationState state = drc->isolation_state; + uint32_t drc_index = spapr_drc_index(drc); + /* done sending the device tree, don't need to track + * the state anymore + */ + trace_spapr_drc_set_configured(drc_index); + if (state == SPAPR_DR_ISOLATION_STATE_UNISOLATED) { + drc->configured = true; + } else { + /* guest should be not configuring an isolated device */ + trace_spapr_drc_set_configured_skipping(drc_index); + } + g_free(ccs); + drc->ccs = NULL; + ccs = NULL; + resp = SPAPR_DR_CC_RESPONSE_SUCCESS; + } else { + resp = SPAPR_DR_CC_RESPONSE_PREV_PARENT; + } + break; + case FDT_PROP: + prop = fdt_get_property_by_offset(drc->fdt, ccs->fdt_offset, + &prop_len); + name = fdt_string(drc->fdt, fdt32_to_cpu(prop->nameoff)); + + /* provide the name of the next OF property */ + wa_offset = CC_VAL_DATA_OFFSET; + rtas_st(wa_addr, CC_IDX_PROP_NAME_OFFSET, wa_offset); + configure_connector_st(wa_addr, wa_offset, name, strlen(name) + 1); + + /* provide the length and value of the OF property. data gets + * placed immediately after NULL terminator of the OF property's + * name string + */ + wa_offset += strlen(name) + 1, + rtas_st(wa_addr, CC_IDX_PROP_LEN, prop_len); + rtas_st(wa_addr, CC_IDX_PROP_DATA_OFFSET, wa_offset); + configure_connector_st(wa_addr, wa_offset, prop->data, prop_len); + resp = SPAPR_DR_CC_RESPONSE_NEXT_PROPERTY; + break; + case FDT_END: + resp = SPAPR_DR_CC_RESPONSE_ERROR; + default: + /* keep seeking for an actionable tag */ + break; + } + if (ccs) { + ccs->fdt_offset = fdt_offset_next; + } + } while (resp == SPAPR_DR_CC_RESPONSE_CONTINUE); + + rc = resp; +out: + rtas_st(rets, 0, rc); +} + +static void spapr_drc_register_types(void) +{ + type_register_static(&spapr_dr_connector_info); + type_register_static(&spapr_drc_physical_info); + type_register_static(&spapr_drc_logical_info); + type_register_static(&spapr_drc_cpu_info); + type_register_static(&spapr_drc_pci_info); + type_register_static(&spapr_drc_lmb_info); + + spapr_rtas_register(RTAS_SET_INDICATOR, "set-indicator", + rtas_set_indicator); + spapr_rtas_register(RTAS_GET_SENSOR_STATE, "get-sensor-state", + rtas_get_sensor_state); + spapr_rtas_register(RTAS_IBM_CONFIGURE_CONNECTOR, "ibm,configure-connector", + rtas_ibm_configure_connector); +} +type_init(spapr_drc_register_types) diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c index 57acd85a87..171aedc7e0 100644 --- a/hw/ppc/spapr_events.c +++ b/hw/ppc/spapr_events.c @@ -477,7 +477,7 @@ static void spapr_powerdown_req(Notifier *n, void *opaque) static void spapr_hotplug_set_signalled(uint32_t drc_index) { - sPAPRDRConnector *drc = spapr_dr_connector_by_index(drc_index); + sPAPRDRConnector *drc = spapr_drc_by_index(drc_index); sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); drck->set_signalled(drc); } @@ -570,22 +570,20 @@ static void spapr_hotplug_req_event(uint8_t hp_id, uint8_t hp_action, void spapr_hotplug_req_add_by_index(sPAPRDRConnector *drc) { - sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); - sPAPRDRConnectorType drc_type = drck->get_type(drc); + sPAPRDRConnectorType drc_type = spapr_drc_type(drc); union drc_identifier drc_id; - drc_id.index = drck->get_index(drc); + drc_id.index = spapr_drc_index(drc); spapr_hotplug_req_event(RTAS_LOG_V6_HP_ID_DRC_INDEX, RTAS_LOG_V6_HP_ACTION_ADD, drc_type, &drc_id); } void spapr_hotplug_req_remove_by_index(sPAPRDRConnector *drc) { - sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); - sPAPRDRConnectorType drc_type = drck->get_type(drc); + sPAPRDRConnectorType drc_type = spapr_drc_type(drc); union drc_identifier drc_id; - drc_id.index = drck->get_index(drc); + drc_id.index = spapr_drc_index(drc); spapr_hotplug_req_event(RTAS_LOG_V6_HP_ID_DRC_INDEX, RTAS_LOG_V6_HP_ACTION_REMOVE, drc_type, &drc_id); } diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c index aae5a62a61..aa1ffea9e5 100644 --- a/hw/ppc/spapr_hcall.c +++ b/hw/ppc/spapr_hcall.c @@ -992,9 +992,10 @@ static target_ulong h_register_process_table(PowerPCCPU *cpu, /* Update the UPRT and GTSE bits in the LPCR for all cpus */ CPU_FOREACH(cs) { - set_spr(cs, SPR_LPCR, LPCR_UPRT | LPCR_GTSE, + set_spr(cs, SPR_LPCR, ((flags & (FLAG_RADIX | FLAG_HASH_PROC_TBL)) ? LPCR_UPRT : 0) | - ((flags & FLAG_GTSE) ? LPCR_GTSE : 0)); + ((flags & FLAG_GTSE) ? LPCR_GTSE : 0), + LPCR_UPRT | LPCR_GTSE); } if (kvm_enabled()) { diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c index e4daf8d5f1..0c181bbca5 100644 --- a/hw/ppc/spapr_pci.c +++ b/hw/ppc/spapr_pci.c @@ -1400,10 +1400,8 @@ static sPAPRDRConnector *spapr_phb_get_pci_func_drc(sPAPRPHBState *phb, uint32_t busnr, int32_t devfn) { - return spapr_dr_connector_by_id(SPAPR_DR_CONNECTOR_TYPE_PCI, - (phb->index << 16) | - (busnr << 8) | - devfn); + return spapr_drc_by_id(TYPE_SPAPR_DRC_PCI, + (phb->index << 16) | (busnr << 8) | devfn); } static sPAPRDRConnector *spapr_phb_get_pci_drc(sPAPRPHBState *phb, @@ -1417,14 +1415,12 @@ static uint32_t spapr_phb_get_pci_drc_index(sPAPRPHBState *phb, PCIDevice *pdev) { sPAPRDRConnector *drc = spapr_phb_get_pci_drc(phb, pdev); - sPAPRDRConnectorClass *drck; if (!drc) { return 0; } - drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); - return drck->get_index(drc); + return spapr_drc_index(drc); } static void spapr_phb_hot_plug_child(HotplugHandler *plug_handler, @@ -1763,8 +1759,7 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) /* allocate connectors for child PCI devices */ if (sphb->dr_enabled) { for (i = 0; i < PCI_SLOT_MAX * 8; i++) { - spapr_dr_connector_new(OBJECT(phb), - SPAPR_DR_CONNECTOR_TYPE_PCI, + spapr_dr_connector_new(OBJECT(phb), TYPE_SPAPR_DRC_PCI, (sphb->index << 16) | i); } } diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c index b666a4c15c..707c4d4936 100644 --- a/hw/ppc/spapr_rtas.c +++ b/hw/ppc/spapr_rtas.c @@ -47,44 +47,6 @@ #include "trace.h" #include "hw/ppc/fdt.h" -static sPAPRConfigureConnectorState *spapr_ccs_find(sPAPRMachineState *spapr, - uint32_t drc_index) -{ - sPAPRConfigureConnectorState *ccs = NULL; - - QTAILQ_FOREACH(ccs, &spapr->ccs_list, next) { - if (ccs->drc_index == drc_index) { - break; - } - } - - return ccs; -} - -static void spapr_ccs_add(sPAPRMachineState *spapr, - sPAPRConfigureConnectorState *ccs) -{ - g_assert(!spapr_ccs_find(spapr, ccs->drc_index)); - QTAILQ_INSERT_HEAD(&spapr->ccs_list, ccs, next); -} - -static void spapr_ccs_remove(sPAPRMachineState *spapr, - sPAPRConfigureConnectorState *ccs) -{ - QTAILQ_REMOVE(&spapr->ccs_list, ccs, next); - g_free(ccs); -} - -void spapr_ccs_reset_hook(void *opaque) -{ - sPAPRMachineState *spapr = opaque; - sPAPRConfigureConnectorState *ccs, *ccs_tmp; - - QTAILQ_FOREACH_SAFE(ccs, &spapr->ccs_list, next, ccs_tmp) { - spapr_ccs_remove(spapr, ccs); - } -} - static void rtas_display_character(PowerPCCPU *cpu, sPAPRMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, @@ -389,266 +351,6 @@ static void rtas_get_power_level(PowerPCCPU *cpu, sPAPRMachineState *spapr, rtas_st(rets, 1, 100); } -static bool sensor_type_is_dr(uint32_t sensor_type) -{ - switch (sensor_type) { - case RTAS_SENSOR_TYPE_ISOLATION_STATE: - case RTAS_SENSOR_TYPE_DR: - case RTAS_SENSOR_TYPE_ALLOCATION_STATE: - return true; - } - - return false; -} - -static void rtas_set_indicator(PowerPCCPU *cpu, sPAPRMachineState *spapr, - uint32_t token, uint32_t nargs, - target_ulong args, uint32_t nret, - target_ulong rets) -{ - uint32_t sensor_type; - uint32_t sensor_index; - uint32_t sensor_state; - uint32_t ret = RTAS_OUT_SUCCESS; - sPAPRDRConnector *drc; - sPAPRDRConnectorClass *drck; - - if (nargs != 3 || nret != 1) { - ret = RTAS_OUT_PARAM_ERROR; - goto out; - } - - sensor_type = rtas_ld(args, 0); - sensor_index = rtas_ld(args, 1); - sensor_state = rtas_ld(args, 2); - - if (!sensor_type_is_dr(sensor_type)) { - goto out_unimplemented; - } - - /* if this is a DR sensor we can assume sensor_index == drc_index */ - drc = spapr_dr_connector_by_index(sensor_index); - if (!drc) { - trace_spapr_rtas_set_indicator_invalid(sensor_index); - ret = RTAS_OUT_PARAM_ERROR; - goto out; - } - drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); - - switch (sensor_type) { - case RTAS_SENSOR_TYPE_ISOLATION_STATE: - /* if the guest is configuring a device attached to this - * DRC, we should reset the configuration state at this - * point since it may no longer be reliable (guest released - * device and needs to start over, or unplug occurred so - * the FDT is no longer valid) - */ - if (sensor_state == SPAPR_DR_ISOLATION_STATE_ISOLATED) { - sPAPRConfigureConnectorState *ccs = spapr_ccs_find(spapr, - sensor_index); - if (ccs) { - spapr_ccs_remove(spapr, ccs); - } - } - ret = drck->set_isolation_state(drc, sensor_state); - break; - case RTAS_SENSOR_TYPE_DR: - ret = drck->set_indicator_state(drc, sensor_state); - break; - case RTAS_SENSOR_TYPE_ALLOCATION_STATE: - ret = drck->set_allocation_state(drc, sensor_state); - break; - default: - goto out_unimplemented; - } - -out: - rtas_st(rets, 0, ret); - return; - -out_unimplemented: - /* currently only DR-related sensors are implemented */ - trace_spapr_rtas_set_indicator_not_supported(sensor_index, sensor_type); - rtas_st(rets, 0, RTAS_OUT_NOT_SUPPORTED); -} - -static void rtas_get_sensor_state(PowerPCCPU *cpu, sPAPRMachineState *spapr, - uint32_t token, uint32_t nargs, - target_ulong args, uint32_t nret, - target_ulong rets) -{ - uint32_t sensor_type; - uint32_t sensor_index; - uint32_t sensor_state = 0; - sPAPRDRConnector *drc; - sPAPRDRConnectorClass *drck; - uint32_t ret = RTAS_OUT_SUCCESS; - - if (nargs != 2 || nret != 2) { - ret = RTAS_OUT_PARAM_ERROR; - goto out; - } - - sensor_type = rtas_ld(args, 0); - sensor_index = rtas_ld(args, 1); - - if (sensor_type != RTAS_SENSOR_TYPE_ENTITY_SENSE) { - /* currently only DR-related sensors are implemented */ - trace_spapr_rtas_get_sensor_state_not_supported(sensor_index, - sensor_type); - ret = RTAS_OUT_NOT_SUPPORTED; - goto out; - } - - drc = spapr_dr_connector_by_index(sensor_index); - if (!drc) { - trace_spapr_rtas_get_sensor_state_invalid(sensor_index); - ret = RTAS_OUT_PARAM_ERROR; - goto out; - } - drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); - ret = drck->entity_sense(drc, &sensor_state); - -out: - rtas_st(rets, 0, ret); - rtas_st(rets, 1, sensor_state); -} - -/* configure-connector work area offsets, int32_t units for field - * indexes, bytes for field offset/len values. - * - * as documented by PAPR+ v2.7, 13.5.3.5 - */ -#define CC_IDX_NODE_NAME_OFFSET 2 -#define CC_IDX_PROP_NAME_OFFSET 2 -#define CC_IDX_PROP_LEN 3 -#define CC_IDX_PROP_DATA_OFFSET 4 -#define CC_VAL_DATA_OFFSET ((CC_IDX_PROP_DATA_OFFSET + 1) * 4) -#define CC_WA_LEN 4096 - -static void configure_connector_st(target_ulong addr, target_ulong offset, - const void *buf, size_t len) -{ - cpu_physical_memory_write(ppc64_phys_to_real(addr + offset), - buf, MIN(len, CC_WA_LEN - offset)); -} - -static void rtas_ibm_configure_connector(PowerPCCPU *cpu, - sPAPRMachineState *spapr, - uint32_t token, uint32_t nargs, - target_ulong args, uint32_t nret, - target_ulong rets) -{ - uint64_t wa_addr; - uint64_t wa_offset; - uint32_t drc_index; - sPAPRDRConnector *drc; - sPAPRDRConnectorClass *drck; - sPAPRConfigureConnectorState *ccs; - sPAPRDRCCResponse resp = SPAPR_DR_CC_RESPONSE_CONTINUE; - int rc; - const void *fdt; - - if (nargs != 2 || nret != 1) { - rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); - return; - } - - wa_addr = ((uint64_t)rtas_ld(args, 1) << 32) | rtas_ld(args, 0); - - drc_index = rtas_ld(wa_addr, 0); - drc = spapr_dr_connector_by_index(drc_index); - if (!drc) { - trace_spapr_rtas_ibm_configure_connector_invalid(drc_index); - rc = RTAS_OUT_PARAM_ERROR; - goto out; - } - - drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); - fdt = drck->get_fdt(drc, NULL); - if (!fdt) { - trace_spapr_rtas_ibm_configure_connector_missing_fdt(drc_index); - rc = SPAPR_DR_CC_RESPONSE_NOT_CONFIGURABLE; - goto out; - } - - ccs = spapr_ccs_find(spapr, drc_index); - if (!ccs) { - ccs = g_new0(sPAPRConfigureConnectorState, 1); - (void)drck->get_fdt(drc, &ccs->fdt_offset); - ccs->drc_index = drc_index; - spapr_ccs_add(spapr, ccs); - } - - do { - uint32_t tag; - const char *name; - const struct fdt_property *prop; - int fdt_offset_next, prop_len; - - tag = fdt_next_tag(fdt, ccs->fdt_offset, &fdt_offset_next); - - switch (tag) { - case FDT_BEGIN_NODE: - ccs->fdt_depth++; - name = fdt_get_name(fdt, ccs->fdt_offset, NULL); - - /* provide the name of the next OF node */ - wa_offset = CC_VAL_DATA_OFFSET; - rtas_st(wa_addr, CC_IDX_NODE_NAME_OFFSET, wa_offset); - configure_connector_st(wa_addr, wa_offset, name, strlen(name) + 1); - resp = SPAPR_DR_CC_RESPONSE_NEXT_CHILD; - break; - case FDT_END_NODE: - ccs->fdt_depth--; - if (ccs->fdt_depth == 0) { - /* done sending the device tree, don't need to track - * the state anymore - */ - drck->set_configured(drc); - spapr_ccs_remove(spapr, ccs); - ccs = NULL; - resp = SPAPR_DR_CC_RESPONSE_SUCCESS; - } else { - resp = SPAPR_DR_CC_RESPONSE_PREV_PARENT; - } - break; - case FDT_PROP: - prop = fdt_get_property_by_offset(fdt, ccs->fdt_offset, - &prop_len); - name = fdt_string(fdt, fdt32_to_cpu(prop->nameoff)); - - /* provide the name of the next OF property */ - wa_offset = CC_VAL_DATA_OFFSET; - rtas_st(wa_addr, CC_IDX_PROP_NAME_OFFSET, wa_offset); - configure_connector_st(wa_addr, wa_offset, name, strlen(name) + 1); - - /* provide the length and value of the OF property. data gets - * placed immediately after NULL terminator of the OF property's - * name string - */ - wa_offset += strlen(name) + 1, - rtas_st(wa_addr, CC_IDX_PROP_LEN, prop_len); - rtas_st(wa_addr, CC_IDX_PROP_DATA_OFFSET, wa_offset); - configure_connector_st(wa_addr, wa_offset, prop->data, prop_len); - resp = SPAPR_DR_CC_RESPONSE_NEXT_PROPERTY; - break; - case FDT_END: - resp = SPAPR_DR_CC_RESPONSE_ERROR; - default: - /* keep seeking for an actionable tag */ - break; - } - if (ccs) { - ccs->fdt_offset = fdt_offset_next; - } - } while (resp == SPAPR_DR_CC_RESPONSE_CONTINUE); - - rc = resp; -out: - rtas_st(rets, 0, rc); -} - static struct rtas_call { const char *name; spapr_rtas_fn fn; @@ -790,12 +492,6 @@ static void core_rtas_register_types(void) rtas_set_power_level); spapr_rtas_register(RTAS_GET_POWER_LEVEL, "get-power-level", rtas_get_power_level); - spapr_rtas_register(RTAS_SET_INDICATOR, "set-indicator", - rtas_set_indicator); - spapr_rtas_register(RTAS_GET_SENSOR_STATE, "get-sensor-state", - rtas_get_sensor_state); - spapr_rtas_register(RTAS_IBM_CONFIGURE_CONNECTOR, "ibm,configure-connector", - rtas_ibm_configure_connector); } type_init(core_rtas_register_types) diff --git a/hw/s390x/s390-skeys.c b/hw/s390x/s390-skeys.c index 619152cc37..35e7f6316f 100644 --- a/hw/s390x/s390-skeys.c +++ b/hw/s390x/s390-skeys.c @@ -362,6 +362,11 @@ static inline bool s390_skeys_get_migration_enabled(Object *obj, Error **errp) return ss->migration_enabled; } +static SaveVMHandlers savevm_s390_storage_keys = { + .save_state = s390_storage_keys_save, + .load_state = s390_storage_keys_load, +}; + static inline void s390_skeys_set_migration_enabled(Object *obj, bool value, Error **errp) { @@ -375,8 +380,8 @@ static inline void s390_skeys_set_migration_enabled(Object *obj, bool value, ss->migration_enabled = value; if (ss->migration_enabled) { - register_savevm(NULL, TYPE_S390_SKEYS, 0, 1, s390_storage_keys_save, - s390_storage_keys_load, ss); + register_savevm_live(NULL, TYPE_S390_SKEYS, 0, 1, + &savevm_s390_storage_keys, ss); } else { unregister_savevm(DEVICE(ss), TYPE_S390_SKEYS, ss); } diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index c9021f2fa9..a806345276 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -104,6 +104,11 @@ void s390_memory_init(ram_addr_t mem_size) s390_skeys_init(); } +static SaveVMHandlers savevm_gtod = { + .save_state = gtod_save, + .load_state = gtod_load, +}; + static void ccw_init(MachineState *machine) { int ret; @@ -151,8 +156,7 @@ static void ccw_init(MachineState *machine) s390_create_virtio_net(BUS(css_bus), "virtio-net-ccw"); /* Register savevm handler for guest TOD clock */ - register_savevm(NULL, "todclock", 0, 1, - gtod_save, gtod_load, kvm_state); + register_savevm_live(NULL, "todclock", 0, 1, &savevm_gtod, kvm_state); } static void s390_cpu_plug(HotplugHandler *hotplug_dev, diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index e447f5d8f4..d071c9c0e9 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -566,75 +566,75 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *); .value = "off",\ },{\ .driver = "qemu64" "-" TYPE_X86_CPU,\ - .property = "level",\ + .property = "min-level",\ .value = stringify(4),\ },{\ .driver = "kvm64" "-" TYPE_X86_CPU,\ - .property = "level",\ + .property = "min-level",\ .value = stringify(5),\ },{\ .driver = "pentium3" "-" TYPE_X86_CPU,\ - .property = "level",\ + .property = "min-level",\ .value = stringify(2),\ },{\ .driver = "n270" "-" TYPE_X86_CPU,\ - .property = "level",\ + .property = "min-level",\ .value = stringify(5),\ },{\ .driver = "Conroe" "-" TYPE_X86_CPU,\ - .property = "level",\ + .property = "min-level",\ .value = stringify(4),\ },{\ .driver = "Penryn" "-" TYPE_X86_CPU,\ - .property = "level",\ + .property = "min-level",\ .value = stringify(4),\ },{\ .driver = "Nehalem" "-" TYPE_X86_CPU,\ - .property = "level",\ + .property = "min-level",\ .value = stringify(4),\ },{\ .driver = "n270" "-" TYPE_X86_CPU,\ - .property = "xlevel",\ + .property = "min-xlevel",\ .value = stringify(0x8000000a),\ },{\ .driver = "Penryn" "-" TYPE_X86_CPU,\ - .property = "xlevel",\ + .property = "min-xlevel",\ .value = stringify(0x8000000a),\ },{\ .driver = "Conroe" "-" TYPE_X86_CPU,\ - .property = "xlevel",\ + .property = "min-xlevel",\ .value = stringify(0x8000000a),\ },{\ .driver = "Nehalem" "-" TYPE_X86_CPU,\ - .property = "xlevel",\ + .property = "min-xlevel",\ .value = stringify(0x8000000a),\ },{\ .driver = "Westmere" "-" TYPE_X86_CPU,\ - .property = "xlevel",\ + .property = "min-xlevel",\ .value = stringify(0x8000000a),\ },{\ .driver = "SandyBridge" "-" TYPE_X86_CPU,\ - .property = "xlevel",\ + .property = "min-xlevel",\ .value = stringify(0x8000000a),\ },{\ .driver = "IvyBridge" "-" TYPE_X86_CPU,\ - .property = "xlevel",\ + .property = "min-xlevel",\ .value = stringify(0x8000000a),\ },{\ .driver = "Haswell" "-" TYPE_X86_CPU,\ - .property = "xlevel",\ + .property = "min-xlevel",\ .value = stringify(0x8000000a),\ },{\ .driver = "Haswell-noTSX" "-" TYPE_X86_CPU,\ - .property = "xlevel",\ + .property = "min-xlevel",\ .value = stringify(0x8000000a),\ },{\ .driver = "Broadwell" "-" TYPE_X86_CPU,\ - .property = "xlevel",\ + .property = "min-xlevel",\ .value = stringify(0x8000000a),\ },{\ .driver = "Broadwell-noTSX" "-" TYPE_X86_CPU,\ - .property = "xlevel",\ + .property = "min-xlevel",\ .value = stringify(0x8000000a),\ },{\ .driver = TYPE_X86_CPU,\ @@ -860,7 +860,7 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *); .value = stringify(2),\ },{\ .driver = "Conroe-" TYPE_X86_CPU,\ - .property = "level",\ + .property = "min-level",\ .value = stringify(2),\ },{\ .driver = "Penryn-" TYPE_X86_CPU,\ @@ -868,7 +868,7 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *); .value = stringify(2),\ },{\ .driver = "Penryn-" TYPE_X86_CPU,\ - .property = "level",\ + .property = "min-level",\ .value = stringify(2),\ },{\ .driver = "Nehalem-" TYPE_X86_CPU,\ @@ -876,7 +876,7 @@ bool e820_get_entry(int, uint32_t, uint64_t *, uint64_t *); .value = stringify(2),\ },{\ .driver = "Nehalem-" TYPE_X86_CPU,\ - .property = "level",\ + .property = "min-level",\ .value = stringify(2),\ },{\ .driver = "virtio-net-pci",\ diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h index 98fb78b012..f973b02845 100644 --- a/include/hw/ppc/spapr.h +++ b/include/hw/ppc/spapr.h @@ -11,7 +11,6 @@ struct VIOsPAPRBus; struct sPAPRPHBState; struct sPAPRNVRAM; -typedef struct sPAPRConfigureConnectorState sPAPRConfigureConnectorState; typedef struct sPAPREventLogEntry sPAPREventLogEntry; typedef struct sPAPREventSource sPAPREventSource; @@ -102,9 +101,6 @@ struct sPAPRMachineState { bool htab_first_pass; int htab_fd; - /* RTAS state */ - QTAILQ_HEAD(, sPAPRConfigureConnectorState) ccs_list; - /* Pending DIMM unplug cache. It is populated when a LMB * unplug starts. It can be regenerated if a migration * occurs during the unplug process. */ @@ -646,16 +642,6 @@ void *spapr_populate_hotplug_cpu_dt(CPUState *cs, int *fdt_offset, void spapr_core_release(DeviceState *dev); void spapr_lmb_release(DeviceState *dev); -/* rtas-configure-connector state */ -struct sPAPRConfigureConnectorState { - uint32_t drc_index; - int fdt_offset; - int fdt_depth; - QTAILQ_ENTRY(sPAPRConfigureConnectorState) next; -}; - -void spapr_ccs_reset_hook(void *opaque); - void spapr_rtc_read(sPAPRRTCState *rtc, struct tm *tm, uint32_t *ns); int spapr_rtc_import_offset(sPAPRRTCState *rtc, int64_t legacy_offset); diff --git a/include/hw/ppc/spapr_drc.h b/include/hw/ppc/spapr_drc.h index 813b9ffd60..c88e1beed4 100644 --- a/include/hw/ppc/spapr_drc.h +++ b/include/hw/ppc/spapr_drc.h @@ -26,6 +26,48 @@ #define SPAPR_DR_CONNECTOR(obj) OBJECT_CHECK(sPAPRDRConnector, (obj), \ TYPE_SPAPR_DR_CONNECTOR) +#define TYPE_SPAPR_DRC_PHYSICAL "spapr-drc-physical" +#define SPAPR_DRC_PHYSICAL_GET_CLASS(obj) \ + OBJECT_GET_CLASS(sPAPRDRConnectorClass, obj, TYPE_SPAPR_DRC_PHYSICAL) +#define SPAPR_DRC_PHYSICAL_CLASS(klass) \ + OBJECT_CLASS_CHECK(sPAPRDRConnectorClass, klass, \ + TYPE_SPAPR_DRC_PHYSICAL) +#define SPAPR_DRC_PHYSICAL(obj) OBJECT_CHECK(sPAPRDRConnector, (obj), \ + TYPE_SPAPR_DRC_PHYSICAL) + +#define TYPE_SPAPR_DRC_LOGICAL "spapr-drc-logical" +#define SPAPR_DRC_LOGICAL_GET_CLASS(obj) \ + OBJECT_GET_CLASS(sPAPRDRConnectorClass, obj, TYPE_SPAPR_DRC_LOGICAL) +#define SPAPR_DRC_LOGICAL_CLASS(klass) \ + OBJECT_CLASS_CHECK(sPAPRDRConnectorClass, klass, \ + TYPE_SPAPR_DRC_LOGICAL) +#define SPAPR_DRC_LOGICAL(obj) OBJECT_CHECK(sPAPRDRConnector, (obj), \ + TYPE_SPAPR_DRC_LOGICAL) + +#define TYPE_SPAPR_DRC_CPU "spapr-drc-cpu" +#define SPAPR_DRC_CPU_GET_CLASS(obj) \ + OBJECT_GET_CLASS(sPAPRDRConnectorClass, obj, TYPE_SPAPR_DRC_CPU) +#define SPAPR_DRC_CPU_CLASS(klass) \ + OBJECT_CLASS_CHECK(sPAPRDRConnectorClass, klass, TYPE_SPAPR_DRC_CPU) +#define SPAPR_DRC_CPU(obj) OBJECT_CHECK(sPAPRDRConnector, (obj), \ + TYPE_SPAPR_DRC_CPU) + +#define TYPE_SPAPR_DRC_PCI "spapr-drc-pci" +#define SPAPR_DRC_PCI_GET_CLASS(obj) \ + OBJECT_GET_CLASS(sPAPRDRConnectorClass, obj, TYPE_SPAPR_DRC_PCI) +#define SPAPR_DRC_PCI_CLASS(klass) \ + OBJECT_CLASS_CHECK(sPAPRDRConnectorClass, klass, TYPE_SPAPR_DRC_PCI) +#define SPAPR_DRC_PCI(obj) OBJECT_CHECK(sPAPRDRConnector, (obj), \ + TYPE_SPAPR_DRC_PCI) + +#define TYPE_SPAPR_DRC_LMB "spapr-drc-lmb" +#define SPAPR_DRC_LMB_GET_CLASS(obj) \ + OBJECT_GET_CLASS(sPAPRDRConnectorClass, obj, TYPE_SPAPR_DRC_LMB) +#define SPAPR_DRC_LMB_CLASS(klass) \ + OBJECT_CLASS_CHECK(sPAPRDRConnectorClass, klass, TYPE_SPAPR_DRC_LMB) +#define SPAPR_DRC_LMB(obj) OBJECT_CHECK(sPAPRDRConnector, (obj), \ + TYPE_SPAPR_DRC_LMB) + /* * Various hotplug types managed by sPAPRDRConnector * @@ -130,11 +172,16 @@ typedef enum { SPAPR_DR_CC_RESPONSE_NOT_CONFIGURABLE = -9003, } sPAPRDRCCResponse; +/* rtas-configure-connector state */ +typedef struct sPAPRConfigureConnectorState { + int fdt_offset; + int fdt_depth; +} sPAPRConfigureConnectorState; + typedef struct sPAPRDRConnector { /*< private >*/ DeviceState parent; - sPAPRDRConnectorType type; uint32_t id; Object *owner; const char *name; @@ -148,6 +195,7 @@ typedef struct sPAPRDRConnector { void *fdt; int fdt_start_offset; bool configured; + sPAPRConfigureConnectorState *ccs; bool awaiting_release; bool signalled; @@ -163,6 +211,8 @@ typedef struct sPAPRDRConnectorClass { DeviceClass parent; /*< public >*/ + sPAPRDRConnectorTypeShift typeshift; + const char *typename; /* used in device tree, PAPR 13.5.2.6 & C.6.1 */ /* accessors for guest-visible (generally via RTAS) DR state */ uint32_t (*set_isolation_state)(sPAPRDRConnector *drc, @@ -171,16 +221,10 @@ typedef struct sPAPRDRConnectorClass { sPAPRDRIndicatorState state); uint32_t (*set_allocation_state)(sPAPRDRConnector *drc, sPAPRDRAllocationState state); - uint32_t (*get_index)(sPAPRDRConnector *drc); - uint32_t (*get_type)(sPAPRDRConnector *drc); const char *(*get_name)(sPAPRDRConnector *drc); uint32_t (*entity_sense)(sPAPRDRConnector *drc, sPAPRDREntitySense *state); - /* QEMU interfaces for managing FDT/configure-connector */ - const void *(*get_fdt)(sPAPRDRConnector *drc, int *fdt_start_offset); - void (*set_configured)(sPAPRDRConnector *drc); - /* QEMU interfaces for managing hotplug operations */ void (*attach)(sPAPRDRConnector *drc, DeviceState *d, void *fdt, int fdt_start_offset, bool coldplug, Error **errp); @@ -189,12 +233,13 @@ typedef struct sPAPRDRConnectorClass { void (*set_signalled)(sPAPRDRConnector *drc); } sPAPRDRConnectorClass; -sPAPRDRConnector *spapr_dr_connector_new(Object *owner, - sPAPRDRConnectorType type, +uint32_t spapr_drc_index(sPAPRDRConnector *drc); +sPAPRDRConnectorType spapr_drc_type(sPAPRDRConnector *drc); + +sPAPRDRConnector *spapr_dr_connector_new(Object *owner, const char *type, uint32_t id); -sPAPRDRConnector *spapr_dr_connector_by_index(uint32_t index); -sPAPRDRConnector *spapr_dr_connector_by_id(sPAPRDRConnectorType type, - uint32_t id); +sPAPRDRConnector *spapr_drc_by_index(uint32_t index); +sPAPRDRConnector *spapr_drc_by_id(const char *type, uint32_t id); int spapr_drc_populate_dt(void *fdt, int fdt_offset, Object *owner, uint32_t drc_type_mask); diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h index 66895623da..8a3e9e6088 100644 --- a/include/migration/vmstate.h +++ b/include/migration/vmstate.h @@ -59,14 +59,6 @@ typedef struct SaveVMHandlers { LoadStateHandler *load_state; } SaveVMHandlers; -int register_savevm(DeviceState *dev, - const char *idstr, - int instance_id, - int version_id, - SaveStateHandler *save_state, - LoadStateHandler *load_state, - void *opaque); - int register_savevm_live(DeviceState *dev, const char *idstr, int instance_id, diff --git a/include/qom/cpu.h b/include/qom/cpu.h index 55214ce131..89ddb686fb 100644 --- a/include/qom/cpu.h +++ b/include/qom/cpu.h @@ -265,7 +265,6 @@ struct qemu_work_item; * @cpu_index: CPU index (informative). * @nr_cores: Number of cores within this CPU package. * @nr_threads: Number of threads within this CPU. - * @numa_node: NUMA node this CPU is belonging to. * @host_tid: Host thread ID. * @running: #true if CPU is currently running (lockless). * @has_waiter: #true if a CPU is currently waiting for the cpu_exec_end; @@ -314,7 +313,6 @@ struct CPUState { int nr_cores; int nr_threads; - int numa_node; struct QemuThread *thread; #ifdef _WIN32 diff --git a/include/sysemu/cpus.h b/include/sysemu/cpus.h index a8053f1715..731756d948 100644 --- a/include/sysemu/cpus.h +++ b/include/sysemu/cpus.h @@ -27,6 +27,7 @@ void qemu_timer_notify_cb(void *opaque, QEMUClockType type); void cpu_synchronize_all_states(void); void cpu_synchronize_all_post_reset(void); void cpu_synchronize_all_post_init(void); +void cpu_synchronize_all_pre_loadvm(void); void qtest_clock_warp(int64_t dest); diff --git a/include/sysemu/hax.h b/include/sysemu/hax.h index d9f023918e..232a68ab1b 100644 --- a/include/sysemu/hax.h +++ b/include/sysemu/hax.h @@ -33,6 +33,7 @@ int hax_populate_ram(uint64_t va, uint32_t size); void hax_cpu_synchronize_state(CPUState *cpu); void hax_cpu_synchronize_post_reset(CPUState *cpu); void hax_cpu_synchronize_post_init(CPUState *cpu); +void hax_cpu_synchronize_pre_loadvm(CPUState *cpu); #ifdef CONFIG_HAX diff --git a/include/sysemu/hw_accel.h b/include/sysemu/hw_accel.h index c9b3105bc7..469ffda460 100644 --- a/include/sysemu/hw_accel.h +++ b/include/sysemu/hw_accel.h @@ -45,4 +45,14 @@ static inline void cpu_synchronize_post_init(CPUState *cpu) } } +static inline void cpu_synchronize_pre_loadvm(CPUState *cpu) +{ + if (kvm_enabled()) { + kvm_cpu_synchronize_pre_loadvm(cpu); + } + if (hax_enabled()) { + hax_cpu_synchronize_pre_loadvm(cpu); + } +} + #endif /* QEMU_HW_ACCEL_H */ diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h index 5cc83f2003..a45c145560 100644 --- a/include/sysemu/kvm.h +++ b/include/sysemu/kvm.h @@ -459,6 +459,7 @@ int kvm_physical_memory_addr_from_host(KVMState *s, void *ram_addr, void kvm_cpu_synchronize_state(CPUState *cpu); void kvm_cpu_synchronize_post_reset(CPUState *cpu); void kvm_cpu_synchronize_post_init(CPUState *cpu); +void kvm_cpu_synchronize_pre_loadvm(CPUState *cpu); void kvm_init_cpu_signals(CPUState *cpu); diff --git a/include/sysemu/numa.h b/include/sysemu/numa.h index 7ffde5b119..610eece211 100644 --- a/include/sysemu/numa.h +++ b/include/sysemu/numa.h @@ -35,4 +35,5 @@ void numa_legacy_auto_assign_ram(MachineClass *mc, NodeInfo *nodes, int nb_nodes, ram_addr_t size); void numa_default_auto_assign_ram(MachineClass *mc, NodeInfo *nodes, int nb_nodes, ram_addr_t size); +void numa_cpu_pre_plug(const CPUArchId *slot, DeviceState *dev, Error **errp); #endif @@ -1896,6 +1896,16 @@ void kvm_cpu_synchronize_post_init(CPUState *cpu) run_on_cpu(cpu, do_kvm_cpu_synchronize_post_init, RUN_ON_CPU_NULL); } +static void do_kvm_cpu_synchronize_pre_loadvm(CPUState *cpu, run_on_cpu_data arg) +{ + cpu->kvm_vcpu_dirty = true; +} + +void kvm_cpu_synchronize_pre_loadvm(CPUState *cpu) +{ + run_on_cpu(cpu, do_kvm_cpu_synchronize_pre_loadvm, RUN_ON_CPU_NULL); +} + #ifdef KVM_HAVE_MCE_INJECTION static __thread void *pending_sigbus_addr; static __thread int pending_sigbus_code; diff --git a/migration/savevm.c b/migration/savevm.c index 9c320f59d0..1993ca23fe 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -645,21 +645,6 @@ int register_savevm_live(DeviceState *dev, return 0; } -int register_savevm(DeviceState *dev, - const char *idstr, - int instance_id, - int version_id, - SaveStateHandler *save_state, - LoadStateHandler *load_state, - void *opaque) -{ - SaveVMHandlers *ops = g_new0(SaveVMHandlers, 1); - ops->save_state = save_state; - ops->load_state = load_state; - return register_savevm_live(dev, idstr, instance_id, version_id, - ops, opaque); -} - void unregister_savevm(DeviceState *dev, const char *idstr, void *opaque) { SaveStateEntry *se, *new_se; @@ -679,7 +664,6 @@ void unregister_savevm(DeviceState *dev, const char *idstr, void *opaque) if (strcmp(se->idstr, id) == 0 && se->opaque == opaque) { QTAILQ_REMOVE(&savevm_state.handlers, se, entry); g_free(se->compat); - g_free(se->ops); g_free(se); } } @@ -2015,6 +1999,8 @@ int qemu_loadvm_state(QEMUFile *f) } } + cpu_synchronize_all_pre_loadvm(); + ret = qemu_loadvm_state_main(f, mis); qemu_event_set(&mis->main_thread_load_event); @@ -1696,23 +1696,26 @@ static void hmp_info_mtree(Monitor *mon, const QDict *qdict) static void hmp_info_numa(Monitor *mon, const QDict *qdict) { int i; - CPUState *cpu; uint64_t *node_mem; + CpuInfoList *cpu_list, *cpu; + cpu_list = qmp_query_cpus(&error_abort); node_mem = g_new0(uint64_t, 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); - CPU_FOREACH(cpu) { - if (cpu->numa_node == i) { - monitor_printf(mon, " %d", cpu->cpu_index); + 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] >> 20); } + qapi_free_CpuInfoList(cpu_list); g_free(node_mem); } @@ -426,7 +426,6 @@ void numa_default_auto_assign_ram(MachineClass *mc, NodeInfo *nodes, void parse_numa_opts(MachineState *ms) { int i; - const CPUArchIdList *possible_cpus; MachineClass *mc = MACHINE_GET_CLASS(ms); if (qemu_opts_foreach(qemu_find_opts("numa"), parse_numa, ms, NULL)) { @@ -484,31 +483,6 @@ void parse_numa_opts(MachineState *ms) numa_set_mem_ranges(); - /* assign CPUs to nodes using board provided default mapping */ - if (!mc->cpu_index_to_instance_props || !mc->possible_cpu_arch_ids) { - error_report("default CPUs to NUMA node mapping isn't supported"); - exit(1); - } - - possible_cpus = mc->possible_cpu_arch_ids(ms); - for (i = 0; i < possible_cpus->len; i++) { - if (possible_cpus->cpus[i].props.has_node_id) { - break; - } - } - - /* no CPUs are assigned to NUMA nodes */ - if (i == possible_cpus->len) { - for (i = 0; i < max_cpus; i++) { - CpuInstanceProperties props; - /* fetch default mapping from board and enable it */ - props = mc->cpu_index_to_instance_props(ms, i); - props.has_node_id = true; - - machine_set_cpu_numa_node(ms, &props, &error_fatal); - } - } - /* 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. @@ -533,6 +507,23 @@ void parse_numa_opts(MachineState *ms) } } +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, "node-id=%d must match numa node specified " + "with -numa option", node_id); + } +} + static void allocate_system_memory_nonnuma(MemoryRegion *mr, Object *owner, const char *name, uint64_t ram_size) diff --git a/qapi/block-core.json b/qapi/block-core.json index 88a7471a23..f85c2235c7 100644 --- a/qapi/block-core.json +++ b/qapi/block-core.json @@ -449,7 +449,8 @@ # # @io-status: @BlockDeviceIoStatus. Only present if the device # supports it and the VM is configured to stop on errors -# (supported device models: virtio-blk, ide, scsi-disk) +# (supported device models: virtio-blk, IDE, SCSI except +# scsi-generic) # # @inserted: @BlockDeviceInfo describing the device if media is # present diff --git a/qom/object_interfaces.c b/qom/object_interfaces.c index d4253a88de..ff27e0669e 100644 --- a/qom/object_interfaces.c +++ b/qom/object_interfaces.c @@ -4,6 +4,7 @@ #include "qemu/module.h" #include "qapi-visit.h" #include "qapi/opts-visitor.h" +#include "qemu/config-file.h" void user_creatable_complete(Object *obj, Error **errp) { @@ -181,6 +182,14 @@ void user_creatable_del(const char *id, Error **errp) error_setg(errp, "object '%s' is in use, can not be deleted", id); return; } + + /* + * if object was defined on the command-line, remove its corresponding + * option group entry + */ + qemu_opts_del(qemu_opts_find(qemu_find_opts_err("object", &error_abort), + id)); + object_unparent(obj); } diff --git a/scripts/device-crash-test b/scripts/device-crash-test new file mode 100755 index 0000000000..5f90e9bb54 --- /dev/null +++ b/scripts/device-crash-test @@ -0,0 +1,624 @@ +#!/usr/bin/env python2.7 +# +# Copyright (c) 2017 Red Hat Inc +# +# Author: +# Eduardo Habkost <ehabkost@redhat.com> +# +# 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, write to the Free Software Foundation, Inc., +# 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA. + +""" +Run QEMU with all combinations of -machine and -device types, +check for crashes and unexpected errors. +""" + +import sys +import os +import glob +import logging +import traceback +import re +import random +import argparse +from itertools import chain + +sys.path.append(os.path.join(os.path.dirname(__file__), '..', 'scripts')) +from qemu import QEMUMachine + +logger = logging.getLogger('device-crash-test') +dbg = logger.debug + + +# Purposes of the following whitelist: +# * Avoiding verbose log messages when we find known non-fatal +# (exitcode=1) errors +# * Avoiding fatal errors when we find known crashes +# * Skipping machines/devices that are known not to work out of +# the box, when running in --quick mode +# +# Keeping the whitelist updated is desirable, but not required, +# because unexpected cases where QEMU exits with exitcode=1 will +# just trigger a INFO message. + +# Valid whitelist entry keys: +# * accel: regexp, full match only +# * machine: regexp, full match only +# * device: regexp, full match only +# * log: regexp, partial match allowed +# * exitcode: if not present, defaults to 1. If None, matches any exitcode +# * warn: if True, matching failures will be logged as warnings +# * expected: if True, QEMU is expected to always fail every time +# when testing the corresponding test case +# * loglevel: log level of log output when there's a match. +ERROR_WHITELIST = [ + # Machines that won't work out of the box: + # MACHINE | ERROR MESSAGE + {'machine':'niagara', 'expected':True}, # Unable to load a firmware for -M niagara + {'machine':'boston', 'expected':True}, # Please provide either a -kernel or -bios argument + {'machine':'leon3_generic', 'expected':True}, # Can't read bios image (null) + + # devices that don't work out of the box because they require extra options to "-device DEV": + # DEVICE | ERROR MESSAGE + {'device':'.*-(i386|x86_64)-cpu', 'expected':True}, # CPU socket-id is not set + {'device':'ARM,bitband-memory', 'expected':True}, # source-memory property not set + {'device':'arm.cortex-a9-global-timer', 'expected':True}, # a9_gtimer_realize: num-cpu must be between 1 and 4 + {'device':'arm_mptimer', 'expected':True}, # num-cpu must be between 1 and 4 + {'device':'armv7m', 'expected':True}, # memory property was not set + {'device':'aspeed.scu', 'expected':True}, # Unknown silicon revision: 0x0 + {'device':'aspeed.sdmc', 'expected':True}, # Unknown silicon revision: 0x0 + {'device':'bcm2835-dma', 'expected':True}, # bcm2835_dma_realize: required dma-mr link not found: Property '.dma-mr' not found + {'device':'bcm2835-fb', 'expected':True}, # bcm2835_fb_realize: required vcram-base property not set + {'device':'bcm2835-mbox', 'expected':True}, # bcm2835_mbox_realize: required mbox-mr link not found: Property '.mbox-mr' not found + {'device':'bcm2835-peripherals', 'expected':True}, # bcm2835_peripherals_realize: required ram link not found: Property '.ram' not found + {'device':'bcm2835-property', 'expected':True}, # bcm2835_property_realize: required fb link not found: Property '.fb' not found + {'device':'bcm2835_gpio', 'expected':True}, # bcm2835_gpio_realize: required sdhci link not found: Property '.sdbus-sdhci' not found + {'device':'bcm2836', 'expected':True}, # bcm2836_realize: required ram link not found: Property '.ram' not found + {'device':'cfi.pflash01', 'expected':True}, # attribute "sector-length" not specified or zero. + {'device':'cfi.pflash02', 'expected':True}, # attribute "sector-length" not specified or zero. + {'device':'icp', 'expected':True}, # icp_realize: required link 'xics' not found: Property '.xics' not found + {'device':'ics', 'expected':True}, # ics_base_realize: required link 'xics' not found: Property '.xics' not found + # "-device ide-cd" does work on more recent QEMU versions, so it doesn't have expected=True + {'device':'ide-cd'}, # No drive specified + {'device':'ide-drive', 'expected':True}, # No drive specified + {'device':'ide-hd', 'expected':True}, # No drive specified + {'device':'ipmi-bmc-extern', 'expected':True}, # IPMI external bmc requires chardev attribute + {'device':'isa-debugcon', 'expected':True}, # Can't create serial device, empty char device + {'device':'isa-ipmi-bt', 'expected':True}, # IPMI device requires a bmc attribute to be set + {'device':'isa-ipmi-kcs', 'expected':True}, # IPMI device requires a bmc attribute to be set + {'device':'isa-parallel', 'expected':True}, # Can't create serial device, empty char device + {'device':'isa-serial', 'expected':True}, # Can't create serial device, empty char device + {'device':'ivshmem', 'expected':True}, # You must specify either 'shm' or 'chardev' + {'device':'ivshmem-doorbell', 'expected':True}, # You must specify a 'chardev' + {'device':'ivshmem-plain', 'expected':True}, # You must specify a 'memdev' + {'device':'kvm-pci-assign', 'expected':True}, # no host device specified + {'device':'loader', 'expected':True}, # please include valid arguments + {'device':'nand', 'expected':True}, # Unsupported NAND block size 0x1 + {'device':'nvdimm', 'expected':True}, # 'memdev' property is not set + {'device':'nvme', 'expected':True}, # Device initialization failed + {'device':'pc-dimm', 'expected':True}, # 'memdev' property is not set + {'device':'pci-bridge', 'expected':True}, # Bridge chassis not specified. Each bridge is required to be assigned a unique chassis id > 0. + {'device':'pci-bridge-seat', 'expected':True}, # Bridge chassis not specified. Each bridge is required to be assigned a unique chassis id > 0. + {'device':'pci-serial', 'expected':True}, # Can't create serial device, empty char device + {'device':'pci-serial-2x', 'expected':True}, # Can't create serial device, empty char device + {'device':'pci-serial-4x', 'expected':True}, # Can't create serial device, empty char device + {'device':'pxa2xx-dma', 'expected':True}, # channels value invalid + {'device':'pxb', 'expected':True}, # Bridge chassis not specified. Each bridge is required to be assigned a unique chassis id > 0. + {'device':'scsi-block', 'expected':True}, # drive property not set + {'device':'scsi-disk', 'expected':True}, # drive property not set + {'device':'scsi-generic', 'expected':True}, # drive property not set + {'device':'scsi-hd', 'expected':True}, # drive property not set + {'device':'spapr-pci-host-bridge', 'expected':True}, # BUID not specified for PHB + {'device':'spapr-pci-vfio-host-bridge', 'expected':True}, # BUID not specified for PHB + {'device':'spapr-rng', 'expected':True}, # spapr-rng needs an RNG backend! + {'device':'spapr-vty', 'expected':True}, # chardev property not set + {'device':'tpm-tis', 'expected':True}, # tpm_tis: backend driver with id (null) could not be found + {'device':'unimplemented-device', 'expected':True}, # property 'size' not specified or zero + {'device':'usb-braille', 'expected':True}, # Property chardev is required + {'device':'usb-mtp', 'expected':True}, # x-root property must be configured + {'device':'usb-redir', 'expected':True}, # Parameter 'chardev' is missing + {'device':'usb-serial', 'expected':True}, # Property chardev is required + {'device':'usb-storage', 'expected':True}, # drive property not set + {'device':'vfio-amd-xgbe', 'expected':True}, # -device vfio-amd-xgbe: vfio error: wrong host device name + {'device':'vfio-calxeda-xgmac', 'expected':True}, # -device vfio-calxeda-xgmac: vfio error: wrong host device name + {'device':'vfio-pci', 'expected':True}, # No provided host device + {'device':'vfio-pci-igd-lpc-bridge', 'expected':True}, # VFIO dummy ISA/LPC bridge must have address 1f.0 + {'device':'vhost-scsi.*', 'expected':True}, # vhost-scsi: missing wwpn + {'device':'vhost-vsock-device', 'expected':True}, # guest-cid property must be greater than 2 + {'device':'vhost-vsock-pci', 'expected':True}, # guest-cid property must be greater than 2 + {'device':'virtio-9p-ccw', 'expected':True}, # 9pfs device couldn't find fsdev with the id = NULL + {'device':'virtio-9p-device', 'expected':True}, # 9pfs device couldn't find fsdev with the id = NULL + {'device':'virtio-9p-pci', 'expected':True}, # 9pfs device couldn't find fsdev with the id = NULL + {'device':'virtio-blk-ccw', 'expected':True}, # drive property not set + {'device':'virtio-blk-device', 'expected':True}, # drive property not set + {'device':'virtio-blk-device', 'expected':True}, # drive property not set + {'device':'virtio-blk-pci', 'expected':True}, # drive property not set + {'device':'virtio-crypto-ccw', 'expected':True}, # 'cryptodev' parameter expects a valid object + {'device':'virtio-crypto-device', 'expected':True}, # 'cryptodev' parameter expects a valid object + {'device':'virtio-crypto-pci', 'expected':True}, # 'cryptodev' parameter expects a valid object + {'device':'virtio-input-host-device', 'expected':True}, # evdev property is required + {'device':'virtio-input-host-pci', 'expected':True}, # evdev property is required + {'device':'xen-pvdevice', 'expected':True}, # Device ID invalid, it must always be supplied + {'device':'vhost-vsock-ccw', 'expected':True}, # guest-cid property must be greater than 2 + {'device':'ALTR.timer', 'expected':True}, # "clock-frequency" property must be provided + {'device':'zpci', 'expected':True}, # target must be defined + {'device':'pnv-(occ|icp|lpc)', 'expected':True}, # required link 'xics' not found: Property '.xics' not found + {'device':'powernv-cpu-.*', 'expected':True}, # pnv_core_realize: required link 'xics' not found: Property '.xics' not found + + # ioapic devices are already created by pc and will fail: + {'machine':'q35|pc.*', 'device':'kvm-ioapic', 'expected':True}, # Only 1 ioapics allowed + {'machine':'q35|pc.*', 'device':'ioapic', 'expected':True}, # Only 1 ioapics allowed + + # KVM-specific devices shouldn't be tried without accel=kvm: + {'accel':'(?!kvm).*', 'device':'kvmclock', 'expected':True}, + {'accel':'(?!kvm).*', 'device':'kvm-pci-assign', 'expected':True}, + + # xen-specific machines and devices: + {'accel':'(?!xen).*', 'machine':'xen.*', 'expected':True}, + {'accel':'(?!xen).*', 'device':'xen-.*', 'expected':True}, + + # this fails on some machine-types, but not all, so they don't have expected=True: + {'device':'vmgenid'}, # vmgenid requires DMA write support in fw_cfg, which this machine type does not provide + + # Silence INFO messages for errors that are common on multiple + # devices/machines: + {'log':r"No '[\w-]+' bus found for device '[\w-]+'"}, + {'log':r"images* must be given with the 'pflash' parameter"}, + {'log':r"(Guest|ROM|Flash|Kernel) image must be specified"}, + {'log':r"[cC]ould not load [\w ]+ (BIOS|bios) '[\w-]+\.bin'"}, + {'log':r"Couldn't find rom image '[\w-]+\.bin'"}, + {'log':r"speed mismatch trying to attach usb device"}, + {'log':r"Can't create a second ISA bus"}, + {'log':r"duplicate fw_cfg file name"}, + # sysbus-related error messages: most machines reject most dynamic sysbus devices: + {'log':r"Option '-device [\w.,-]+' cannot be handled by this machine"}, + {'log':r"Device [\w.,-]+ is not supported by this machine yet"}, + {'log':r"Device [\w.,-]+ can not be dynamically instantiated"}, + {'log':r"Platform Bus: Can not fit MMIO region of size "}, + # other more specific errors we will ignore: + {'device':'allwinner-a10', 'log':"Unsupported NIC model:"}, + {'device':'.*-spapr-cpu-core', 'log':r"CPU core type should be"}, + {'log':r"MSI(-X)? is not supported by interrupt controller"}, + {'log':r"pxb-pcie? devices cannot reside on a PCIe? bus"}, + {'log':r"Ignoring smp_cpus value"}, + {'log':r"sd_init failed: Drive 'sd0' is already in use because it has been automatically connected to another device"}, + {'log':r"This CPU requires a smaller page size than the system is using"}, + {'log':r"MSI-X support is mandatory in the S390 architecture"}, + {'log':r"rom check and register reset failed"}, + {'log':r"Unable to initialize GIC, CPUState for CPU#0 not valid"}, + {'log':r"Multiple VT220 operator consoles are not supported"}, + {'log':r"core 0 already populated"}, + {'log':r"could not find stage1 bootloader"}, + + # other exitcode=1 failures not listed above will just generate INFO messages: + {'exitcode':1, 'loglevel':logging.INFO}, + + # KNOWN CRASHES: + # Known crashes will generate error messages, but won't be fatal. + # Those entries must be removed once we fix the crashes. + {'exitcode':-6, 'log':r"Device 'serial0' is in use", 'loglevel':logging.ERROR}, + {'exitcode':-6, 'log':r"spapr_rtas_register: Assertion .*rtas_table\[token\]\.name.* failed", 'loglevel':logging.ERROR}, + {'exitcode':-6, 'log':r"qemu_net_client_setup: Assertion `!peer->peer' failed", 'loglevel':logging.ERROR}, + {'exitcode':-6, 'log':r'RAMBlock "[\w.-]+" already registered', 'loglevel':logging.ERROR}, + {'exitcode':-6, 'log':r"find_ram_offset: Assertion `size != 0' failed.", 'loglevel':logging.ERROR}, + {'exitcode':-6, 'log':r"puv3_load_kernel: Assertion `kernel_filename != NULL' failed", 'loglevel':logging.ERROR}, + {'exitcode':-6, 'log':r"add_cpreg_to_hashtable: code should not be reached", 'loglevel':logging.ERROR}, + {'exitcode':-6, 'log':r"qemu_alloc_display: Assertion `surface->image != NULL' failed", 'loglevel':logging.ERROR}, + {'exitcode':-6, 'log':r"Unexpected error in error_set_from_qdev_prop_error", 'loglevel':logging.ERROR}, + {'exitcode':-6, 'log':r"Object .* is not an instance of type spapr-machine", 'loglevel':logging.ERROR}, + {'exitcode':-6, 'log':r"Object .* is not an instance of type generic-pc-machine", 'loglevel':logging.ERROR}, + {'exitcode':-6, 'log':r"Object .* is not an instance of type e500-ccsr", 'loglevel':logging.ERROR}, + {'exitcode':-6, 'log':r"vmstate_register_with_alias_id: Assertion `!se->compat || se->instance_id == 0' failed", 'loglevel':logging.ERROR}, + {'exitcode':-11, 'device':'stm32f205-soc', 'loglevel':logging.ERROR, 'expected':True}, + {'exitcode':-11, 'device':'xlnx,zynqmp', 'loglevel':logging.ERROR, 'expected':True}, + {'exitcode':-11, 'device':'mips-cps', 'loglevel':logging.ERROR, 'expected':True}, + {'exitcode':-11, 'device':'gus', 'loglevel':logging.ERROR, 'expected':True}, + {'exitcode':-11, 'device':'a9mpcore_priv', 'loglevel':logging.ERROR, 'expected':True}, + {'exitcode':-11, 'device':'a15mpcore_priv', 'loglevel':logging.ERROR, 'expected':True}, + {'exitcode':-11, 'device':'isa-serial', 'loglevel':logging.ERROR, 'expected':True}, + {'exitcode':-11, 'device':'sb16', 'loglevel':logging.ERROR, 'expected':True}, + {'exitcode':-11, 'device':'cs4231a', 'loglevel':logging.ERROR, 'expected':True}, + {'exitcode':-11, 'device':'arm-gicv3', 'loglevel':logging.ERROR, 'expected':True}, + {'exitcode':-11, 'machine':'isapc', 'device':'.*-iommu', 'loglevel':logging.ERROR, 'expected':True}, + + # everything else (including SIGABRT and SIGSEGV) will be a fatal error: + {'exitcode':None, 'fatal':True, 'loglevel':logging.FATAL}, +] + + +def whitelistTestCaseMatch(wl, t): + """Check if a test case specification can match a whitelist entry + + This only checks if a whitelist entry is a candidate match + for a given test case, it won't check if the test case + results/output match the entry. See whitelistResultMatch(). + """ + return (('machine' not in wl or + 'machine' not in t or + re.match(wl['machine'] + '$', t['machine'])) and + ('accel' not in wl or + 'accel' not in t or + re.match(wl['accel'] + '$', t['accel'])) and + ('device' not in wl or + 'device' not in t or + re.match(wl['device'] + '$', t['device']))) + + +def whitelistCandidates(t): + """Generate the list of candidates that can match a test case""" + for i, wl in enumerate(ERROR_WHITELIST): + if whitelistTestCaseMatch(wl, t): + yield (i, wl) + + +def findExpectedResult(t): + """Check if there's an expected=True whitelist entry for a test case + + Returns (i, wl) tuple, where i is the index in + ERROR_WHITELIST and wl is the whitelist entry itself. + """ + for i, wl in whitelistCandidates(t): + if wl.get('expected'): + return (i, wl) + + +def whitelistResultMatch(wl, r): + """Check if test case results/output match a whitelist entry + + It is valid to call this function only if + whitelistTestCaseMatch() is True for the entry (e.g. on + entries returned by whitelistCandidates()) + """ + assert whitelistTestCaseMatch(wl, r['testcase']) + return ((wl.get('exitcode', 1) is None or + r['exitcode'] == wl.get('exitcode', 1)) and + ('log' not in wl or + re.search(wl['log'], r['log'], re.MULTILINE))) + + +def checkResultWhitelist(r): + """Look up whitelist entry for a given test case result + + Returns (i, wl) tuple, where i is the index in + ERROR_WHITELIST and wl is the whitelist entry itself. + """ + for i, wl in whitelistCandidates(r['testcase']): + if whitelistResultMatch(wl, r): + return i, wl + + raise Exception("this should never happen") + + +def qemuOptsEscape(s): + """Escape option value QemuOpts""" + return s.replace(",", ",,") + + +def formatTestCase(t): + """Format test case info as "key=value key=value" for prettier logging output""" + return ' '.join('%s=%s' % (k, v) for k, v in t.items()) + + +def qomListTypeNames(vm, **kwargs): + """Run qom-list-types QMP command, return type names""" + types = vm.command('qom-list-types', **kwargs) + return [t['name'] for t in types] + + +def infoQDM(vm): + """Parse 'info qdm' output""" + args = {'command-line': 'info qdm'} + devhelp = vm.command('human-monitor-command', **args) + for l in devhelp.split('\n'): + l = l.strip() + if l == '' or l.endswith(':'): + continue + d = {'name': re.search(r'name "([^"]+)"', l).group(1), + 'no-user': (re.search(', no-user', l) is not None)} + yield d + + +class QemuBinaryInfo(object): + def __init__(self, binary, devtype): + if devtype is None: + devtype = 'device' + + self.binary = binary + self._machine_info = {} + + dbg("devtype: %r", devtype) + args = ['-S', '-machine', 'none,accel=kvm:tcg'] + dbg("querying info for QEMU binary: %s", binary) + vm = QEMUMachine(binary=binary, args=args) + vm.launch() + try: + self.alldevs = set(qomListTypeNames(vm, implements=devtype, abstract=False)) + # there's no way to query DeviceClass::user_creatable using QMP, + # so use 'info qdm': + self.no_user_devs = set([d['name'] for d in infoQDM(vm, ) if d['no-user']]) + self.machines = list(m['name'] for m in vm.command('query-machines')) + self.user_devs = self.alldevs.difference(self.no_user_devs) + self.kvm_available = vm.command('query-kvm')['enabled'] + finally: + vm.shutdown() + + def machineInfo(self, machine): + """Query for information on a specific machine-type + + Results are cached internally, in case the same machine- + type is queried multiple times. + """ + if machine in self._machine_info: + return self._machine_info[machine] + + mi = {} + args = ['-S', '-machine', '%s' % (machine)] + dbg("querying machine info for binary=%s machine=%s", self.binary, machine) + vm = QEMUMachine(binary=self.binary, args=args) + try: + vm.launch() + mi['runnable'] = True + except KeyboardInterrupt: + raise + except: + dbg("exception trying to run binary=%s machine=%s", self.binary, machine, exc_info=sys.exc_info()) + dbg("log: %r", vm.get_log()) + mi['runnable'] = False + + vm.shutdown() + self._machine_info[machine] = mi + return mi + + +BINARY_INFO = {} + + +def getBinaryInfo(args, binary): + if binary not in BINARY_INFO: + BINARY_INFO[binary] = QemuBinaryInfo(binary, args.devtype) + return BINARY_INFO[binary] + + +def checkOneCase(args, testcase): + """Check one specific case + + Returns a dictionary containing failure information on error, + or None on success + """ + binary = testcase['binary'] + accel = testcase['accel'] + machine = testcase['machine'] + device = testcase['device'] + + dbg("will test: %r", testcase) + + args = ['-S', '-machine', '%s,accel=%s' % (machine, accel), + '-device', qemuOptsEscape(device)] + cmdline = ' '.join([binary] + args) + dbg("will launch QEMU: %s", cmdline) + vm = QEMUMachine(binary=binary, args=args) + + exc_traceback = None + try: + vm.launch() + except KeyboardInterrupt: + raise + except: + exc_traceback = traceback.format_exc() + dbg("Exception while running test case") + finally: + vm.shutdown() + ec = vm.exitcode() + log = vm.get_log() + + if exc_traceback is not None or ec != 0: + return {'exc_traceback':exc_traceback, + 'exitcode':ec, + 'log':log, + 'testcase':testcase, + 'cmdline':cmdline} + + +def binariesToTest(args, testcase): + if args.qemu: + r = args.qemu + else: + r = glob.glob('./*-softmmu/qemu-system-*') + return r + + +def accelsToTest(args, testcase): + if getBinaryInfo(args, testcase['binary']).kvm_available: + yield 'kvm' + yield 'tcg' + + +def machinesToTest(args, testcase): + return getBinaryInfo(args, testcase['binary']).machines + + +def devicesToTest(args, testcase): + return getBinaryInfo(args, testcase['binary']).user_devs + + +TESTCASE_VARIABLES = [ + ('binary', binariesToTest), + ('accel', accelsToTest), + ('machine', machinesToTest), + ('device', devicesToTest), +] + + +def genCases1(args, testcases, var, fn): + """Generate new testcases for one variable + + If an existing item already has a variable set, don't + generate new items and just return it directly. This + allows the "-t" command-line option to be used to choose + a specific test case. + """ + for testcase in testcases: + if var in testcase: + yield testcase.copy() + else: + for i in fn(args, testcase): + t = testcase.copy() + t[var] = i + yield t + + +def genCases(args, testcase): + """Generate test cases for all variables + """ + cases = [testcase.copy()] + for var, fn in TESTCASE_VARIABLES: + dbg("var: %r, fn: %r", var, fn) + cases = genCases1(args, cases, var, fn) + return cases + + +def casesToTest(args, testcase): + cases = genCases(args, testcase) + if args.random: + cases = list(cases) + cases = random.sample(cases, min(args.random, len(cases))) + if args.debug: + cases = list(cases) + dbg("%d test cases to test", len(cases)) + if args.shuffle: + cases = list(cases) + random.shuffle(cases) + return cases + + +def logFailure(f, level): + t = f['testcase'] + logger.log(level, "failed: %s", formatTestCase(t)) + logger.log(level, "cmdline: %s", f['cmdline']) + for l in f['log'].strip().split('\n'): + logger.log(level, "log: %s", l) + logger.log(level, "exit code: %r", f['exitcode']) + if f['exc_traceback']: + logger.log(level, "exception:") + for l in f['exc_traceback'].split('\n'): + logger.log(level, " %s", l.rstrip('\n')) + + +def main(): + parser = argparse.ArgumentParser(description="QEMU -device crash test") + parser.add_argument('-t', metavar='KEY=VALUE', nargs='*', + help="Limit test cases to KEY=VALUE", + action='append', dest='testcases', default=[]) + parser.add_argument('-d', '--debug', action='store_true', + help='debug output') + parser.add_argument('-v', '--verbose', action='store_true', default=True, + help='verbose output') + parser.add_argument('-q', '--quiet', dest='verbose', action='store_false', + help='non-verbose output') + parser.add_argument('-r', '--random', type=int, metavar='COUNT', + help='run a random sample of COUNT test cases', + default=0) + parser.add_argument('--shuffle', action='store_true', + help='Run test cases in random order') + parser.add_argument('--dry-run', action='store_true', + help="Don't run any tests, just generate list") + parser.add_argument('-D', '--devtype', metavar='TYPE', + help="Test only device types that implement TYPE") + parser.add_argument('-Q', '--quick', action='store_true', default=True, + help="Quick mode: skip test cases that are expected to fail") + parser.add_argument('-F', '--full', action='store_false', dest='quick', + help="Full mode: test cases that are expected to fail") + parser.add_argument('--strict', action='store_true', dest='strict', + help="Treat all warnings as fatal") + parser.add_argument('qemu', nargs='*', metavar='QEMU', + help='QEMU binary to run') + args = parser.parse_args() + + if args.debug: + lvl = logging.DEBUG + elif args.verbose: + lvl = logging.INFO + else: + lvl = logging.WARN + logging.basicConfig(stream=sys.stdout, level=lvl, format='%(levelname)s: %(message)s') + + fatal_failures = [] + wl_stats = {} + skipped = 0 + total = 0 + + tc = {} + dbg("testcases: %r", args.testcases) + if args.testcases: + for t in chain(*args.testcases): + for kv in t.split(): + k, v = kv.split('=', 1) + tc[k] = v + + if len(binariesToTest(args, tc)) == 0: + print >>sys.stderr, "No QEMU binary found" + parser.print_usage(sys.stderr) + return 1 + + for t in casesToTest(args, tc): + logger.info("running test case: %s", formatTestCase(t)) + total += 1 + + expected_match = findExpectedResult(t) + if (args.quick and + (expected_match or + not getBinaryInfo(args, t['binary']).machineInfo(t['machine'])['runnable'])): + dbg("skipped: %s", formatTestCase(t)) + skipped += 1 + continue + + if args.dry_run: + continue + + try: + f = checkOneCase(args, t) + except KeyboardInterrupt: + break + + if f: + i, wl = checkResultWhitelist(f) + dbg("testcase: %r, whitelist match: %r", t, wl) + wl_stats.setdefault(i, []).append(f) + level = wl.get('loglevel', logging.DEBUG) + logFailure(f, level) + if wl.get('fatal') or (args.strict and level >= logging.WARN): + fatal_failures.append(f) + else: + dbg("success: %s", formatTestCase(t)) + if expected_match: + logger.warn("Didn't fail as expected: %s", formatTestCase(t)) + + logger.info("Total: %d test cases", total) + if skipped: + logger.info("Skipped %d test cases", skipped) + + if args.debug: + stats = sorted([(len(wl_stats.get(i, [])), wl) for i, wl in enumerate(ERROR_WHITELIST)]) + for count, wl in stats: + dbg("whitelist entry stats: %d: %r", count, wl) + + if fatal_failures: + for f in fatal_failures: + t = f['testcase'] + logger.error("Fatal failure: %s", formatTestCase(t)) + logger.error("Fatal failures on some machine/device combinations") + return 1 + +if __name__ == '__main__': + sys.exit(main()) diff --git a/scripts/qemu.py b/scripts/qemu.py index 6d1b6230b7..880e3e8219 100644 --- a/scripts/qemu.py +++ b/scripts/qemu.py @@ -85,8 +85,16 @@ class QEMUMachine(object): return raise + def is_running(self): + return self._popen and (self._popen.returncode is None) + + def exitcode(self): + if self._popen is None: + return None + return self._popen.returncode + def get_pid(self): - if not self._popen: + if not self.is_running(): return None return self._popen.pid @@ -128,16 +136,16 @@ class QEMUMachine(object): stderr=subprocess.STDOUT, shell=False) self._post_launch() except: - if self._popen: + if self.is_running(): self._popen.kill() + self._popen.wait() self._load_io_log() self._post_shutdown() - self._popen = None raise def shutdown(self): '''Terminate the VM and clean up''' - if not self._popen is None: + if self.is_running(): try: self._qmp.cmd('quit') self._qmp.close() @@ -149,7 +157,6 @@ class QEMUMachine(object): sys.stderr.write('qemu received signal %i: %s\n' % (-exitcode, ' '.join(self._args))) self._load_io_log() self._post_shutdown() - self._popen = None underscore_to_dash = string.maketrans('_', '-') def qmp(self, cmd, conv_keys=True, **args): diff --git a/slirp/slirp.c b/slirp/slirp.c index e79345bdfc..23864938f7 100644 --- a/slirp/slirp.c +++ b/slirp/slirp.c @@ -272,6 +272,11 @@ static void slirp_init_once(void) static void slirp_state_save(QEMUFile *f, void *opaque); static int slirp_state_load(QEMUFile *f, void *opaque, int version_id); +static SaveVMHandlers savevm_slirp_state = { + .save_state = slirp_state_save, + .load_state = slirp_state_load, +}; + Slirp *slirp_init(int restricted, bool in_enabled, struct in_addr vnetwork, struct in_addr vnetmask, struct in_addr vhost, bool in6_enabled, @@ -321,8 +326,7 @@ Slirp *slirp_init(int restricted, bool in_enabled, struct in_addr vnetwork, slirp->opaque = opaque; - register_savevm(NULL, "slirp", 0, 4, - slirp_state_save, slirp_state_load, slirp); + register_savevm_live(NULL, "slirp", 0, 4, &savevm_slirp_state, slirp); QTAILQ_INSERT_TAIL(&slirp_instances, slirp, entry); diff --git a/target/arm/cpu.c b/target/arm/cpu.c index 04a3fea03f..28a9141298 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -1589,7 +1589,7 @@ static Property arm_cpu_properties[] = { DEFINE_PROP_UINT32("midr", ARMCPU, midr, 0), DEFINE_PROP_UINT64("mp-affinity", ARMCPU, mp_affinity, ARM64_AFFINITY_INVALID), - DEFINE_PROP_INT32("node-id", CPUState, numa_node, CPU_UNSET_NUMA_NODE_ID), + DEFINE_PROP_INT32("node-id", ARMCPU, node_id, CPU_UNSET_NUMA_NODE_ID), DEFINE_PROP_END_OF_LIST() }; diff --git a/target/arm/cpu.h b/target/arm/cpu.h index 13da5036bc..16a1e59615 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -704,6 +704,8 @@ struct ARMCPU { ARMELChangeHook *el_change_hook; void *el_change_hook_opaque; + + int32_t node_id; /* NUMA node this CPU belongs to */ }; static inline ARMCPU *arm_env_get_cpu(CPUARMState *env) diff --git a/target/i386/cpu.c b/target/i386/cpu.c index a41d595c23..ffb5267162 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -3986,7 +3986,7 @@ static Property x86_cpu_properties[] = { DEFINE_PROP_INT32("core-id", X86CPU, core_id, -1), DEFINE_PROP_INT32("socket-id", X86CPU, socket_id, -1), #endif - DEFINE_PROP_INT32("node-id", CPUState, numa_node, CPU_UNSET_NUMA_NODE_ID), + DEFINE_PROP_INT32("node-id", X86CPU, node_id, CPU_UNSET_NUMA_NODE_ID), DEFINE_PROP_BOOL("pmu", X86CPU, enable_pmu, false), { .name = "hv-spinlocks", .info = &qdev_prop_spinlocks }, DEFINE_PROP_BOOL("hv-relaxed", X86CPU, hyperv_relaxed_timing, false), diff --git a/target/i386/cpu.h b/target/i386/cpu.h index c4602ca80d..cfe825f0a4 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -1275,6 +1275,7 @@ struct X86CPU { struct kvm_msrs *kvm_msr_buf; + int32_t node_id; /* NUMA node this CPU belongs to */ int32_t socket_id; int32_t core_id; int32_t thread_id; diff --git a/target/i386/hax-all.c b/target/i386/hax-all.c index 73469311d6..097db5cae1 100644 --- a/target/i386/hax-all.c +++ b/target/i386/hax-all.c @@ -635,6 +635,16 @@ void hax_cpu_synchronize_post_init(CPUState *cpu) run_on_cpu(cpu, do_hax_cpu_synchronize_post_init, RUN_ON_CPU_NULL); } +static void do_hax_cpu_synchronize_pre_loadvm(CPUState *cpu, run_on_cpu_data arg) +{ + cpu->hax_vcpu_dirty = true; +} + +void hax_cpu_synchronize_pre_loadvm(CPUState *cpu) +{ + run_on_cpu(cpu, do_hax_cpu_synchronize_pre_loadvm, RUN_ON_CPU_NULL); +} + int hax_smp_cpu_exec(CPUState *cpu) { CPUArchState *env = (CPUArchState *) (cpu->env_ptr); diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index 401e10e7da..d10808d9f4 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -1205,6 +1205,7 @@ struct PowerPCCPU { uint32_t compat_pvr; PPCVirtualHypervisor *vhyp; Object *intc; + int32_t node_id; /* NUMA node this CPU belongs to */ /* Fields related to migration compatibility hacks */ bool pre_2_8_migration; diff --git a/tests/check-qom-proplist.c b/tests/check-qom-proplist.c index a16cefca73..8e432e9ab6 100644 --- a/tests/check-qom-proplist.c +++ b/tests/check-qom-proplist.c @@ -23,6 +23,9 @@ #include "qapi/error.h" #include "qom/object.h" #include "qemu/module.h" +#include "qemu/option.h" +#include "qemu/config-file.h" +#include "qom/object_interfaces.h" #define TYPE_DUMMY "qemu-dummy" @@ -162,6 +165,10 @@ static const TypeInfo dummy_info = { .instance_finalize = dummy_finalize, .class_size = sizeof(DummyObjectClass), .class_init = dummy_class_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_USER_CREATABLE }, + { } + } }; @@ -320,6 +327,14 @@ static const TypeInfo dummy_backend_info = { .class_size = sizeof(DummyBackendClass), }; +static QemuOptsList qemu_object_opts = { + .name = "object", + .implied_opt_name = "qom-type", + .head = QTAILQ_HEAD_INITIALIZER(qemu_object_opts.head), + .desc = { + { } + }, +}; static void test_dummy_createv(void) @@ -388,6 +403,46 @@ static void test_dummy_createlist(void) object_unparent(OBJECT(dobj)); } +static void test_dummy_createcmdl(void) +{ + QemuOpts *opts; + DummyObject *dobj; + Error *err = NULL; + const char *params = TYPE_DUMMY \ + ",id=dev0," \ + "bv=yes,sv=Hiss hiss hiss,av=platypus"; + + qemu_add_opts(&qemu_object_opts); + opts = qemu_opts_parse(&qemu_object_opts, params, true, &err); + g_assert(err == NULL); + g_assert(opts); + + dobj = DUMMY_OBJECT(user_creatable_add_opts(opts, &err)); + g_assert(err == NULL); + g_assert(dobj); + g_assert_cmpstr(dobj->sv, ==, "Hiss hiss hiss"); + g_assert(dobj->bv == true); + g_assert(dobj->av == DUMMY_PLATYPUS); + + user_creatable_del("dev0", &err); + g_assert(err == NULL); + error_free(err); + + /* + * cmdline-parsing via qemu_opts_parse() results in a QemuOpts entry + * corresponding to the Object's ID to be added to the QemuOptsList + * for objects. To avoid having this entry conflict with future + * Objects using the same ID (which can happen in cases where + * qemu_opts_parse() is used to parse the object params, such as + * with hmp_object_add() at the time of this comment), we need to + * check for this in user_creatable_del() and remove the QemuOpts if + * it is present. + * + * The below check ensures this works as expected. + */ + g_assert_null(qemu_opts_find(&qemu_object_opts, "dev0")); +} + static void test_dummy_badenum(void) { Error *err = NULL; @@ -525,6 +580,7 @@ int main(int argc, char **argv) g_test_add_func("/qom/proplist/createlist", test_dummy_createlist); g_test_add_func("/qom/proplist/createv", test_dummy_createv); + g_test_add_func("/qom/proplist/createcmdline", test_dummy_createcmdl); g_test_add_func("/qom/proplist/badenum", test_dummy_badenum); g_test_add_func("/qom/proplist/getenum", test_dummy_getenum); g_test_add_func("/qom/proplist/iterator", test_dummy_iterator); diff --git a/tests/test-x86-cpuid-compat.c b/tests/test-x86-cpuid-compat.c index 6c71e46391..4166ce54b7 100644 --- a/tests/test-x86-cpuid-compat.c +++ b/tests/test-x86-cpuid-compat.c @@ -313,6 +313,44 @@ int main(int argc, char **argv) add_cpuid_test("x86/cpuid/auto-xlevel2/pc-2.7", "-machine pc-i440fx-2.7 -cpu 486,+xstore", "xlevel2", 0); + /* + * QEMU 1.4.0 had auto-level enabled for CPUID[7], already, + * and the compat code that sets default level shouldn't + * disable the auto-level=7 code: + */ + add_cpuid_test("x86/cpuid/auto-level7/pc-i440fx-1.4/off", + "-machine pc-i440fx-1.4 -cpu Nehalem", + "level", 2); + add_cpuid_test("x86/cpuid/auto-level7/pc-i440fx-1.5/on", + "-machine pc-i440fx-1.4 -cpu Nehalem,+smap", + "level", 7); + add_cpuid_test("x86/cpuid/auto-level7/pc-i440fx-2.3/off", + "-machine pc-i440fx-2.3 -cpu Penryn", + "level", 4); + add_cpuid_test("x86/cpuid/auto-level7/pc-i440fx-2.3/on", + "-machine pc-i440fx-2.3 -cpu Penryn,+erms", + "level", 7); + add_cpuid_test("x86/cpuid/auto-level7/pc-i440fx-2.9/off", + "-machine pc-i440fx-2.9 -cpu Conroe", + "level", 10); + add_cpuid_test("x86/cpuid/auto-level7/pc-i440fx-2.9/on", + "-machine pc-i440fx-2.9 -cpu Conroe,+erms", + "level", 10); + + /* + * xlevel doesn't have any feature that triggers auto-level + * code on old machine-types. Just check that the compat code + * is working correctly: + */ + add_cpuid_test("x86/cpuid/xlevel-compat/pc-i440fx-2.3", + "-machine pc-i440fx-2.3 -cpu SandyBridge", + "xlevel", 0x8000000a); + add_cpuid_test("x86/cpuid/xlevel-compat/pc-i440fx-2.4/npt-off", + "-machine pc-i440fx-2.4 -cpu SandyBridge,", + "xlevel", 0x80000008); + add_cpuid_test("x86/cpuid/xlevel-compat/pc-i440fx-2.4/npt-on", + "-machine pc-i440fx-2.4 -cpu SandyBridge,+npt", + "xlevel", 0x80000008); /* Test feature parsing */ add_feature_test("x86/cpuid/features/plus", diff --git a/tests/virtio-scsi-test.c b/tests/virtio-scsi-test.c index 8b0f77a63e..eff71df81f 100644 --- a/tests/virtio-scsi-test.c +++ b/tests/virtio-scsi-test.c @@ -149,7 +149,7 @@ static QVirtIOSCSI *qvirtio_scsi_pci_init(int slot) vs->qs = qvirtio_scsi_start("-drive file=blkdebug::null-co://," "if=none,id=dr1,format=raw,file.align=4k " - "-device scsi-disk,drive=dr1,lun=0,scsi-id=1"); + "-device scsi-hd,drive=dr1,lun=0,scsi-id=1"); dev = qvirtio_pci_device_find(vs->qs->pcibus, VIRTIO_ID_SCSI); vs->dev = (QVirtioDevice *)dev; g_assert(dev != NULL); |