diff options
43 files changed, 1362 insertions, 362 deletions
@@ -1333,6 +1333,7 @@ static void *qemu_dummy_cpu_thread_fn(void *arg) qemu_wait_io_event(cpu); } while (!cpu->unplug); + qemu_mutex_unlock_iothread(); rcu_unregister_thread(); return NULL; #endif diff --git a/hw/intc/spapr_xive.c b/hw/intc/spapr_xive.c index 290a290e43..e0e5cb5d8e 100644 --- a/hw/intc/spapr_xive.c +++ b/hw/intc/spapr_xive.c @@ -244,13 +244,12 @@ static void spapr_xive_instance_init(Object *obj) { sPAPRXive *xive = SPAPR_XIVE(obj); - object_initialize(&xive->source, sizeof(xive->source), TYPE_XIVE_SOURCE); - object_property_add_child(obj, "source", OBJECT(&xive->source), NULL); + object_initialize_child(obj, "source", &xive->source, sizeof(xive->source), + TYPE_XIVE_SOURCE, &error_abort, NULL); - object_initialize(&xive->end_source, sizeof(xive->end_source), - TYPE_XIVE_END_SOURCE); - object_property_add_child(obj, "end_source", OBJECT(&xive->end_source), - NULL); + object_initialize_child(obj, "end_source", &xive->end_source, + sizeof(xive->end_source), TYPE_XIVE_END_SOURCE, + &error_abort, NULL); } static void spapr_xive_realize(DeviceState *dev, Error **errp) @@ -317,6 +316,9 @@ static void spapr_xive_realize(DeviceState *dev, Error **errp) /* Map all regions */ spapr_xive_map_mmio(xive); + xive->nodename = g_strdup_printf("interrupt-controller@%" PRIx64, + xive->tm_base + XIVE_TM_USER_PAGE * (1 << TM_SHIFT)); + qemu_register_reset(spapr_xive_reset, dev); } @@ -1448,7 +1450,6 @@ void spapr_dt_xive(sPAPRMachineState *spapr, uint32_t nr_servers, void *fdt, cpu_to_be32(7), /* start */ cpu_to_be32(0xf8), /* count */ }; - gchar *nodename; /* Thread Interrupt Management Area : User (ring 3) and OS (ring 2) */ timas[0] = cpu_to_be64(xive->tm_base + @@ -1458,10 +1459,7 @@ void spapr_dt_xive(sPAPRMachineState *spapr, uint32_t nr_servers, void *fdt, XIVE_TM_OS_PAGE * (1ull << TM_SHIFT)); timas[3] = cpu_to_be64(1ull << TM_SHIFT); - nodename = g_strdup_printf("interrupt-controller@%" PRIx64, - xive->tm_base + XIVE_TM_USER_PAGE * (1 << TM_SHIFT)); - _FDT(node = fdt_add_subnode(fdt, 0, nodename)); - g_free(nodename); + _FDT(node = fdt_add_subnode(fdt, 0, xive->nodename)); _FDT(fdt_setprop_string(fdt, node, "device_type", "power-ivpe")); _FDT(fdt_setprop(fdt, node, "reg", timas, sizeof(timas))); diff --git a/hw/intc/xics.c b/hw/intc/xics.c index 3009fa7472..af7dc709ab 100644 --- a/hw/intc/xics.c +++ b/hw/intc/xics.c @@ -338,6 +338,9 @@ static void icp_realize(DeviceState *dev, Error **errp) case PPC_FLAGS_INPUT_POWER7: icp->output = env->irq_inputs[POWER7_INPUT_INT]; break; + case PPC_FLAGS_INPUT_POWER9: /* For SPAPR xics emulation */ + icp->output = env->irq_inputs[POWER9_INPUT_INT]; + break; case PPC_FLAGS_INPUT_970: icp->output = env->irq_inputs[PPC970_INPUT_INT]; @@ -755,6 +758,10 @@ void ics_set_irq_type(ICSState *ics, int srcno, bool lsi) ics->irqs[srcno].flags |= lsi ? XICS_FLAGS_IRQ_LSI : XICS_FLAGS_IRQ_MSI; + + if (kvm_irqchip_in_kernel()) { + ics_set_kvm_state_one(ics, srcno); + } } static void xics_register_types(void) diff --git a/hw/intc/xics_kvm.c b/hw/intc/xics_kvm.c index a00d0a7962..c6e1b630a4 100644 --- a/hw/intc/xics_kvm.c +++ b/hw/intc/xics_kvm.c @@ -213,45 +213,57 @@ void ics_synchronize_state(ICSState *ics) ics_get_kvm_state(ics); } -int ics_set_kvm_state(ICSState *ics) +int ics_set_kvm_state_one(ICSState *ics, int srcno) { uint64_t state; - int i; Error *local_err = NULL; + ICSIRQState *irq = &ics->irqs[srcno]; + int ret; - for (i = 0; i < ics->nr_irqs; i++) { - ICSIRQState *irq = &ics->irqs[i]; - int ret; - - state = irq->server; - state |= (uint64_t)(irq->saved_priority & KVM_XICS_PRIORITY_MASK) - << KVM_XICS_PRIORITY_SHIFT; - if (irq->priority != irq->saved_priority) { - assert(irq->priority == 0xff); - state |= KVM_XICS_MASKED; - } + state = irq->server; + state |= (uint64_t)(irq->saved_priority & KVM_XICS_PRIORITY_MASK) + << KVM_XICS_PRIORITY_SHIFT; + if (irq->priority != irq->saved_priority) { + assert(irq->priority == 0xff); + state |= KVM_XICS_MASKED; + } - if (ics->irqs[i].flags & XICS_FLAGS_IRQ_LSI) { - state |= KVM_XICS_LEVEL_SENSITIVE; - if (irq->status & XICS_STATUS_ASSERTED) { - state |= KVM_XICS_PENDING; - } - } else { - if (irq->status & XICS_STATUS_MASKED_PENDING) { - state |= KVM_XICS_PENDING; - } + if (irq->flags & XICS_FLAGS_IRQ_LSI) { + state |= KVM_XICS_LEVEL_SENSITIVE; + if (irq->status & XICS_STATUS_ASSERTED) { + state |= KVM_XICS_PENDING; } - if (irq->status & XICS_STATUS_PRESENTED) { - state |= KVM_XICS_PRESENTED; - } - if (irq->status & XICS_STATUS_QUEUED) { - state |= KVM_XICS_QUEUED; + } else { + if (irq->status & XICS_STATUS_MASKED_PENDING) { + state |= KVM_XICS_PENDING; } + } + if (irq->status & XICS_STATUS_PRESENTED) { + state |= KVM_XICS_PRESENTED; + } + if (irq->status & XICS_STATUS_QUEUED) { + state |= KVM_XICS_QUEUED; + } + + ret = kvm_device_access(kernel_xics_fd, KVM_DEV_XICS_GRP_SOURCES, + srcno + ics->offset, &state, true, &local_err); + if (local_err) { + error_report_err(local_err); + return ret; + } + + return 0; +} + +int ics_set_kvm_state(ICSState *ics) +{ + int i; + + for (i = 0; i < ics->nr_irqs; i++) { + int ret; - ret = kvm_device_access(kernel_xics_fd, KVM_DEV_XICS_GRP_SOURCES, - i + ics->offset, &state, true, &local_err); - if (local_err) { - error_report_err(local_err); + ret = ics_set_kvm_state_one(ics, i); + if (ret) { return ret; } } diff --git a/hw/intc/xics_spapr.c b/hw/intc/xics_spapr.c index e2d8b38183..53bda6661b 100644 --- a/hw/intc/xics_spapr.c +++ b/hw/intc/xics_spapr.c @@ -254,7 +254,7 @@ void spapr_dt_xics(sPAPRMachineState *spapr, uint32_t nr_servers, void *fdt, }; int node; - _FDT(node = fdt_add_subnode(fdt, 0, "interrupt-controller")); + _FDT(node = fdt_add_subnode(fdt, 0, XICS_NODENAME)); _FDT(fdt_setprop_string(fdt, node, "device_type", "PowerPC-External-Interrupt-Presentation")); diff --git a/hw/intc/xive.c b/hw/intc/xive.c index 2e9b8efd43..daa7badc84 100644 --- a/hw/intc/xive.c +++ b/hw/intc/xive.c @@ -481,8 +481,8 @@ static void xive_tctx_realize(DeviceState *dev, Error **errp) env = &cpu->env; switch (PPC_INPUT(env)) { - case PPC_FLAGS_INPUT_POWER7: - tctx->output = env->irq_inputs[POWER7_INPUT_INT]; + case PPC_FLAGS_INPUT_POWER9: + tctx->output = env->irq_inputs[POWER9_INPUT_INT]; break; default: diff --git a/hw/ppc/pnv.c b/hw/ppc/pnv.c index da540860a2..3d5dfef220 100644 --- a/hw/ppc/pnv.c +++ b/hw/ppc/pnv.c @@ -47,14 +47,16 @@ #include <libfdt.h> -#define FDT_MAX_SIZE 0x00100000 +#define FDT_MAX_SIZE (1 * MiB) #define FW_FILE_NAME "skiboot.lid" #define FW_LOAD_ADDR 0x0 -#define FW_MAX_SIZE 0x00400000 +#define FW_MAX_SIZE (4 * MiB) #define KERNEL_LOAD_ADDR 0x20000000 +#define KERNEL_MAX_SIZE (256 * MiB) #define INITRD_LOAD_ADDR 0x60000000 +#define INITRD_MAX_SIZE (256 * MiB) static const char *pnv_chip_core_typename(const PnvChip *o) { @@ -588,7 +590,7 @@ static void pnv_init(MachineState *machine) long kernel_size; kernel_size = load_image_targphys(machine->kernel_filename, - KERNEL_LOAD_ADDR, 0x2000000); + KERNEL_LOAD_ADDR, KERNEL_MAX_SIZE); if (kernel_size < 0) { error_report("Could not load kernel '%s'", machine->kernel_filename); @@ -600,7 +602,7 @@ static void pnv_init(MachineState *machine) if (machine->initrd_filename) { pnv->initrd_base = INITRD_LOAD_ADDR; pnv->initrd_size = load_image_targphys(machine->initrd_filename, - pnv->initrd_base, 0x10000000); /* 128MB max */ + pnv->initrd_base, INITRD_MAX_SIZE); if (pnv->initrd_size < 0) { error_report("Could not load initial ram disk '%s'", machine->initrd_filename); @@ -736,18 +738,18 @@ static void pnv_chip_power8_instance_init(Object *obj) { Pnv8Chip *chip8 = PNV8_CHIP(obj); - object_initialize(&chip8->psi, sizeof(chip8->psi), TYPE_PNV_PSI); - object_property_add_child(obj, "psi", OBJECT(&chip8->psi), NULL); + object_initialize_child(obj, "psi", &chip8->psi, sizeof(chip8->psi), + TYPE_PNV_PSI, &error_abort, NULL); object_property_add_const_link(OBJECT(&chip8->psi), "xics", OBJECT(qdev_get_machine()), &error_abort); - object_initialize(&chip8->lpc, sizeof(chip8->lpc), TYPE_PNV_LPC); - object_property_add_child(obj, "lpc", OBJECT(&chip8->lpc), NULL); + object_initialize_child(obj, "lpc", &chip8->lpc, sizeof(chip8->lpc), + TYPE_PNV_LPC, &error_abort, NULL); object_property_add_const_link(OBJECT(&chip8->lpc), "psi", OBJECT(&chip8->psi), &error_abort); - object_initialize(&chip8->occ, sizeof(chip8->occ), TYPE_PNV_OCC); - object_property_add_child(obj, "occ", OBJECT(&chip8->occ), NULL); + object_initialize_child(obj, "occ", &chip8->occ, sizeof(chip8->occ), + TYPE_PNV_OCC, &error_abort, NULL); object_property_add_const_link(OBJECT(&chip8->occ), "psi", OBJECT(&chip8->psi), &error_abort); } diff --git a/hw/ppc/pnv_psi.c b/hw/ppc/pnv_psi.c index 8ced095063..44bc0cbf58 100644 --- a/hw/ppc/pnv_psi.c +++ b/hw/ppc/pnv_psi.c @@ -444,8 +444,8 @@ static void pnv_psi_init(Object *obj) { PnvPsi *psi = PNV_PSI(obj); - object_initialize(&psi->ics, sizeof(psi->ics), TYPE_ICS_SIMPLE); - object_property_add_child(obj, "ics-psi", OBJECT(&psi->ics), NULL); + object_initialize_child(obj, "ics-psi", &psi->ics, sizeof(psi->ics), + TYPE_ICS_SIMPLE, &error_abort, NULL); } static const uint8_t irq_to_xivr[] = { diff --git a/hw/ppc/ppc.c b/hw/ppc/ppc.c index cffdc3914a..d1e3d4cd20 100644 --- a/hw/ppc/ppc.c +++ b/hw/ppc/ppc.c @@ -306,6 +306,48 @@ void ppcPOWER7_irq_init(PowerPCCPU *cpu) env->irq_inputs = (void **)qemu_allocate_irqs(&power7_set_irq, cpu, POWER7_INPUT_NB); } + +/* POWER9 internal IRQ controller */ +static void power9_set_irq(void *opaque, int pin, int level) +{ + PowerPCCPU *cpu = opaque; + CPUPPCState *env = &cpu->env; + + LOG_IRQ("%s: env %p pin %d level %d\n", __func__, + env, pin, level); + + switch (pin) { + case POWER9_INPUT_INT: + /* Level sensitive - active high */ + LOG_IRQ("%s: set the external IRQ state to %d\n", + __func__, level); + ppc_set_irq(cpu, PPC_INTERRUPT_EXT, level); + break; + case POWER9_INPUT_HINT: + /* Level sensitive - active high */ + LOG_IRQ("%s: set the external IRQ state to %d\n", + __func__, level); + ppc_set_irq(cpu, PPC_INTERRUPT_HVIRT, level); + break; + default: + /* Unknown pin - do nothing */ + LOG_IRQ("%s: unknown IRQ pin %d\n", __func__, pin); + return; + } + if (level) { + env->irq_input_state |= 1 << pin; + } else { + env->irq_input_state &= ~(1 << pin); + } +} + +void ppcPOWER9_irq_init(PowerPCCPU *cpu) +{ + CPUPPCState *env = &cpu->env; + + env->irq_inputs = (void **)qemu_allocate_irqs(&power9_set_irq, cpu, + POWER9_INPUT_NB); +} #endif /* defined(TARGET_PPC64) */ void ppc40x_core_reset(PowerPCCPU *cpu) @@ -776,7 +818,7 @@ static inline void cpu_ppc_hdecr_excp(PowerPCCPU *cpu) * interrupts in a PM state. Not only they don't cause a * wakeup but they also get effectively discarded. */ - if (!env->in_pm_state) { + if (!env->resume_as_sreset) { ppc_set_irq(cpu, PPC_INTERRUPT_HDECR, 1); } } diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index abf9ebce59..b6a571b6f1 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -1247,13 +1247,30 @@ static void *spapr_build_fdt(sPAPRMachineState *spapr) * Add info to guest to indentify which host is it being run on * and what is the uuid of the guest */ - if (kvmppc_get_host_model(&buf)) { - _FDT(fdt_setprop_string(fdt, 0, "host-model", buf)); - g_free(buf); + if (spapr->host_model && !g_str_equal(spapr->host_model, "none")) { + if (g_str_equal(spapr->host_model, "passthrough")) { + /* -M host-model=passthrough */ + if (kvmppc_get_host_model(&buf)) { + _FDT(fdt_setprop_string(fdt, 0, "host-model", buf)); + g_free(buf); + } + } else { + /* -M host-model=<user-string> */ + _FDT(fdt_setprop_string(fdt, 0, "host-model", spapr->host_model)); + } } - if (kvmppc_get_host_serial(&buf)) { - _FDT(fdt_setprop_string(fdt, 0, "host-serial", buf)); - g_free(buf); + + if (spapr->host_serial && !g_str_equal(spapr->host_serial, "none")) { + if (g_str_equal(spapr->host_serial, "passthrough")) { + /* -M host-serial=passthrough */ + if (kvmppc_get_host_serial(&buf)) { + _FDT(fdt_setprop_string(fdt, 0, "host-serial", buf)); + g_free(buf); + } + } else { + /* -M host-serial=<user-string> */ + _FDT(fdt_setprop_string(fdt, 0, "host-serial", spapr->host_serial)); + } } buf = qemu_uuid_unparse_strdup(&qemu_uuid); @@ -1295,7 +1312,7 @@ static void *spapr_build_fdt(sPAPRMachineState *spapr) QLIST_FOREACH(phb, &spapr->phbs, list) { ret = spapr_populate_pci_dt(phb, PHANDLE_INTC, fdt, - spapr->irq->nr_msis); + spapr->irq->nr_msis, NULL); if (ret < 0) { error_report("couldn't setup PCI devices in fdt"); exit(1); @@ -1348,6 +1365,14 @@ static void *spapr_build_fdt(sPAPRMachineState *spapr) exit(1); } + if (smc->dr_phb_enabled) { + ret = spapr_drc_populate_dt(fdt, 0, NULL, SPAPR_DR_CONNECTOR_TYPE_PHB); + if (ret < 0) { + error_report("Couldn't set up PHB DR device tree properties"); + exit(1); + } + } + return fdt; } @@ -1372,11 +1397,44 @@ static void emulate_spapr_hypercall(PPCVirtualHypervisor *vhyp, } } -static uint64_t spapr_get_patbe(PPCVirtualHypervisor *vhyp) +struct LPCRSyncState { + target_ulong value; + target_ulong mask; +}; + +static void do_lpcr_sync(CPUState *cs, run_on_cpu_data arg) +{ + struct LPCRSyncState *s = arg.host_ptr; + PowerPCCPU *cpu = POWERPC_CPU(cs); + CPUPPCState *env = &cpu->env; + target_ulong lpcr; + + cpu_synchronize_state(cs); + lpcr = env->spr[SPR_LPCR]; + lpcr &= ~s->mask; + lpcr |= s->value; + ppc_store_lpcr(cpu, lpcr); +} + +void spapr_set_all_lpcrs(target_ulong value, target_ulong mask) +{ + CPUState *cs; + struct LPCRSyncState s = { + .value = value, + .mask = mask + }; + CPU_FOREACH(cs) { + run_on_cpu(cs, do_lpcr_sync, RUN_ON_CPU_HOST_PTR(&s)); + } +} + +static void spapr_get_pate(PPCVirtualHypervisor *vhyp, ppc_v3_pate_t *entry) { sPAPRMachineState *spapr = SPAPR_MACHINE(vhyp); - return spapr->patb_entry; + /* Copy PATE1:GR into PATE0:HR */ + entry->dw0 = spapr->patb_entry & PATE0_HR; + entry->dw1 = spapr->patb_entry; } #define HPTE(_table, _i) (void *)(((uint64_t *)(_table)) + ((_i) * 2)) @@ -1476,8 +1534,25 @@ static void spapr_store_hpte(PPCVirtualHypervisor *vhyp, hwaddr ptex, if (!spapr->htab) { kvmppc_write_hpte(ptex, pte0, pte1); } else { - stq_p(spapr->htab + offset, pte0); - stq_p(spapr->htab + offset + HASH_PTE_SIZE_64 / 2, pte1); + if (pte0 & HPTE64_V_VALID) { + stq_p(spapr->htab + offset + HASH_PTE_SIZE_64 / 2, pte1); + /* + * When setting valid, we write PTE1 first. This ensures + * proper synchronization with the reading code in + * ppc_hash64_pteg_search() + */ + smp_wmb(); + stq_p(spapr->htab + offset, pte0); + } else { + stq_p(spapr->htab + offset, pte0); + /* + * When clearing it we set PTE0 first. This ensures proper + * synchronization with the reading code in + * ppc_hash64_pteg_search() + */ + smp_wmb(); + stq_p(spapr->htab + offset + HASH_PTE_SIZE_64 / 2, pte1); + } } } @@ -1548,7 +1623,7 @@ void spapr_reallocate_hpt(sPAPRMachineState *spapr, int shift, } } /* We're setting up a hash table, so that means we're not radix */ - spapr->patb_entry = 0; + spapr_set_all_lpcrs(0, LPCR_HR | LPCR_UPRT); } void spapr_setup_hpt_and_vrma(sPAPRMachineState *spapr) @@ -1602,16 +1677,21 @@ static void spapr_machine_reset(void) if (kvm_enabled() && kvmppc_has_cap_mmu_radix() && ppc_type_check_compat(machine->cpu_type, CPU_POWERPC_LOGICAL_3_00, 0, spapr->max_compat_pvr)) { - /* If using KVM with radix mode available, VCPUs can be started + /* + * If using KVM with radix mode available, VCPUs can be started * without a HPT because KVM will start them in radix mode. - * Set the GR bit in PATB so that we know there is no HPT. */ - spapr->patb_entry = PATBE1_GR; + * Set the GR bit in PATE so that we know there is no HPT. + */ + spapr->patb_entry = PATE1_GR; + spapr_set_all_lpcrs(LPCR_HR | LPCR_UPRT, LPCR_HR | LPCR_UPRT); } else { spapr_setup_hpt_and_vrma(spapr); } - /* if this reset wasn't generated by CAS, we should reset our - * negotiated options and start from scratch */ + /* + * If this reset wasn't generated by CAS, we should reset our + * negotiated options and start from scratch + */ if (!spapr->cas_reboot) { spapr_ovec_cleanup(spapr->ov5_cas); spapr->ov5_cas = spapr_ovec_new(); @@ -1696,9 +1776,9 @@ static void spapr_create_nvram(sPAPRMachineState *spapr) static void spapr_rtc_create(sPAPRMachineState *spapr) { - object_initialize(&spapr->rtc, sizeof(spapr->rtc), TYPE_SPAPR_RTC); - object_property_add_child(OBJECT(spapr), "rtc", OBJECT(&spapr->rtc), - &error_fatal); + object_initialize_child(OBJECT(spapr), "rtc", + &spapr->rtc, sizeof(spapr->rtc), TYPE_SPAPR_RTC, + &error_fatal, NULL); object_property_set_bool(OBJECT(&spapr->rtc), true, "realized", &error_fatal); object_property_add_alias(OBJECT(spapr), "rtc-time", OBJECT(&spapr->rtc), @@ -1761,9 +1841,16 @@ static int spapr_post_load(void *opaque, int version_id) if (kvm_enabled() && spapr->patb_entry) { PowerPCCPU *cpu = POWERPC_CPU(first_cpu); - bool radix = !!(spapr->patb_entry & PATBE1_GR); + bool radix = !!(spapr->patb_entry & PATE1_GR); bool gtse = !!(cpu->env.spr[SPR_LPCR] & LPCR_GTSE); + /* + * Update LPCR:HR and UPRT as they may not be set properly in + * the stream + */ + spapr_set_all_lpcrs(radix ? (LPCR_HR | LPCR_UPRT) : 0, + LPCR_HR | LPCR_UPRT); + err = kvmppc_configure_v3_mmu(cpu, radix, gtse, spapr->patb_entry); if (err) { error_report("Process table config unsupported by the host"); @@ -2796,6 +2883,19 @@ static void spapr_machine_init(MachineState *machine) /* We always have at least the nvram device on VIO */ spapr_create_nvram(spapr); + /* + * Setup hotplug / dynamic-reconfiguration connectors. top-level + * connectors (described in root DT node's "ibm,drc-types" property) + * are pre-initialized here. additional child connectors (such as + * connectors for a PHBs PCI slots) are added as needed during their + * parent's realization. + */ + if (smc->dr_phb_enabled) { + for (i = 0; i < SPAPR_MAX_PHBS; i++) { + spapr_dr_connector_new(OBJECT(machine), TYPE_SPAPR_DRC_PHB, i); + } + } + /* Set up PCI */ spapr_pci_rtas_init(); @@ -2909,6 +3009,9 @@ static void spapr_machine_init(MachineState *machine) register_savevm_live(NULL, "spapr/htab", -1, 1, &savevm_htab_handlers, spapr); + qbus_set_hotplug_handler(sysbus_get_default(), OBJECT(machine), + &error_fatal); + qemu_register_boot_set(spapr_boot_set, spapr); if (kvm_enabled()) { @@ -3144,6 +3247,36 @@ static void spapr_set_ic_mode(Object *obj, const char *value, Error **errp) } } +static char *spapr_get_host_model(Object *obj, Error **errp) +{ + sPAPRMachineState *spapr = SPAPR_MACHINE(obj); + + return g_strdup(spapr->host_model); +} + +static void spapr_set_host_model(Object *obj, const char *value, Error **errp) +{ + sPAPRMachineState *spapr = SPAPR_MACHINE(obj); + + g_free(spapr->host_model); + spapr->host_model = g_strdup(value); +} + +static char *spapr_get_host_serial(Object *obj, Error **errp) +{ + sPAPRMachineState *spapr = SPAPR_MACHINE(obj); + + return g_strdup(spapr->host_serial); +} + +static void spapr_set_host_serial(Object *obj, const char *value, Error **errp) +{ + sPAPRMachineState *spapr = SPAPR_MACHINE(obj); + + g_free(spapr->host_serial); + spapr->host_serial = g_strdup(value); +} + static void spapr_instance_init(Object *obj) { sPAPRMachineState *spapr = SPAPR_MACHINE(obj); @@ -3189,6 +3322,17 @@ static void spapr_instance_init(Object *obj) object_property_set_description(obj, "ic-mode", "Specifies the interrupt controller mode (xics, xive, dual)", NULL); + + object_property_add_str(obj, "host-model", + spapr_get_host_model, spapr_set_host_model, + &error_abort); + object_property_set_description(obj, "host-model", + "Set host's model-id to use - none|passthrough|string", &error_abort); + object_property_add_str(obj, "host-serial", + spapr_get_host_serial, spapr_set_host_serial, + &error_abort); + object_property_set_description(obj, "host-serial", + "Set host's system-id to use - none|passthrough|string", &error_abort); } static void spapr_machine_finalizefn(Object *obj) @@ -3213,14 +3357,26 @@ static void spapr_nmi(NMIState *n, int cpu_index, Error **errp) } } +int spapr_lmb_dt_populate(sPAPRDRConnector *drc, sPAPRMachineState *spapr, + void *fdt, int *fdt_start_offset, Error **errp) +{ + uint64_t addr; + uint32_t node; + + addr = spapr_drc_index(drc) * SPAPR_MEMORY_BLOCK_SIZE; + node = object_property_get_uint(OBJECT(drc->dev), PC_DIMM_NODE_PROP, + &error_abort); + *fdt_start_offset = spapr_populate_memory_node(fdt, node, addr, + SPAPR_MEMORY_BLOCK_SIZE); + return 0; +} + static void spapr_add_lmbs(DeviceState *dev, uint64_t addr_start, uint64_t size, - uint32_t node, bool dedicated_hp_event_source, - Error **errp) + bool dedicated_hp_event_source, Error **errp) { sPAPRDRConnector *drc; uint32_t nr_lmbs = size/SPAPR_MEMORY_BLOCK_SIZE; - int i, fdt_offset, fdt_size; - void *fdt; + int i; uint64_t addr = addr_start; bool hotplugged = spapr_drc_hotplugged(dev); Error *local_err = NULL; @@ -3230,11 +3386,7 @@ static void spapr_add_lmbs(DeviceState *dev, uint64_t addr_start, uint64_t size, addr / SPAPR_MEMORY_BLOCK_SIZE); g_assert(drc); - fdt = create_device_tree(&fdt_size); - fdt_offset = spapr_populate_memory_node(fdt, node, addr, - SPAPR_MEMORY_BLOCK_SIZE); - - spapr_drc_attach(drc, dev, fdt, fdt_offset, &local_err); + spapr_drc_attach(drc, dev, &local_err); if (local_err) { while (addr > addr_start) { addr -= SPAPR_MEMORY_BLOCK_SIZE; @@ -3242,7 +3394,6 @@ static void spapr_add_lmbs(DeviceState *dev, uint64_t addr_start, uint64_t size, addr / SPAPR_MEMORY_BLOCK_SIZE); spapr_drc_detach(drc); } - g_free(fdt); error_propagate(errp, local_err); return; } @@ -3275,7 +3426,6 @@ static void spapr_memory_plug(HotplugHandler *hotplug_dev, DeviceState *dev, sPAPRMachineState *ms = SPAPR_MACHINE(hotplug_dev); PCDIMMDevice *dimm = PC_DIMM(dev); uint64_t size, addr; - uint32_t node; size = memory_device_get_region_size(MEMORY_DEVICE(dev), &error_abort); @@ -3290,10 +3440,7 @@ static void spapr_memory_plug(HotplugHandler *hotplug_dev, DeviceState *dev, goto out_unplug; } - node = object_property_get_uint(OBJECT(dev), PC_DIMM_NODE_PROP, - &error_abort); - spapr_add_lmbs(dev, addr, size, node, - spapr_ovec_test(ms->ov5_cas, OV5_HP_EVT), + spapr_add_lmbs(dev, addr, size, spapr_ovec_test(ms->ov5_cas, OV5_HP_EVT), &local_err); if (local_err) { goto out_unplug; @@ -3513,27 +3660,6 @@ out: error_propagate(errp, local_err); } -static void *spapr_populate_hotplug_cpu_dt(CPUState *cs, int *fdt_offset, - sPAPRMachineState *spapr) -{ - PowerPCCPU *cpu = POWERPC_CPU(cs); - DeviceClass *dc = DEVICE_GET_CLASS(cs); - int id = spapr_get_vcpu_id(cpu); - void *fdt; - int offset, fdt_size; - char *nodename; - - fdt = create_device_tree(&fdt_size); - nodename = g_strdup_printf("%s@%x", dc->fw_name, id); - offset = fdt_add_subnode(fdt, 0, nodename); - - spapr_populate_cpu_dt(cs, fdt, offset, spapr); - g_free(nodename); - - *fdt_offset = offset; - return fdt; -} - /* Callback to be called during DRC release. */ void spapr_core_release(DeviceState *dev) { @@ -3594,6 +3720,27 @@ void spapr_core_unplug_request(HotplugHandler *hotplug_dev, DeviceState *dev, spapr_hotplug_req_remove_by_index(drc); } +int spapr_core_dt_populate(sPAPRDRConnector *drc, sPAPRMachineState *spapr, + void *fdt, int *fdt_start_offset, Error **errp) +{ + sPAPRCPUCore *core = SPAPR_CPU_CORE(drc->dev); + CPUState *cs = CPU(core->threads[0]); + PowerPCCPU *cpu = POWERPC_CPU(cs); + DeviceClass *dc = DEVICE_GET_CLASS(cs); + int id = spapr_get_vcpu_id(cpu); + char *nodename; + int offset; + + nodename = g_strdup_printf("%s@%x", dc->fw_name, id); + offset = fdt_add_subnode(fdt, 0, nodename); + g_free(nodename); + + spapr_populate_cpu_dt(cs, fdt, offset, spapr); + + *fdt_start_offset = offset; + return 0; +} + static void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { @@ -3602,7 +3749,7 @@ static void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev, sPAPRMachineClass *smc = SPAPR_MACHINE_CLASS(mc); sPAPRCPUCore *core = SPAPR_CPU_CORE(OBJECT(dev)); CPUCore *cc = CPU_CORE(dev); - CPUState *cs = CPU(core->threads[0]); + CPUState *cs; sPAPRDRConnector *drc; Error *local_err = NULL; CPUArchId *core_slot; @@ -3621,14 +3768,8 @@ static void spapr_core_plug(HotplugHandler *hotplug_dev, DeviceState *dev, g_assert(drc || !mc->has_hotpluggable_cpus); if (drc) { - void *fdt; - int fdt_offset; - - fdt = spapr_populate_hotplug_cpu_dt(cs, &fdt_offset, spapr); - - spapr_drc_attach(drc, dev, fdt, fdt_offset, &local_err); + spapr_drc_attach(drc, dev, &local_err); if (local_err) { - g_free(fdt); error_propagate(errp, local_err); return; } @@ -3712,6 +3853,115 @@ out: error_propagate(errp, local_err); } +int spapr_phb_dt_populate(sPAPRDRConnector *drc, sPAPRMachineState *spapr, + void *fdt, int *fdt_start_offset, Error **errp) +{ + sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(drc->dev); + int intc_phandle; + + intc_phandle = spapr_irq_get_phandle(spapr, spapr->fdt_blob, errp); + if (intc_phandle <= 0) { + return -1; + } + + if (spapr_populate_pci_dt(sphb, intc_phandle, fdt, spapr->irq->nr_msis, + fdt_start_offset)) { + error_setg(errp, "unable to create FDT node for PHB %d", sphb->index); + return -1; + } + + /* generally SLOF creates these, for hotplug it's up to QEMU */ + _FDT(fdt_setprop_string(fdt, *fdt_start_offset, "name", "pci")); + + return 0; +} + +static void spapr_phb_pre_plug(HotplugHandler *hotplug_dev, DeviceState *dev, + Error **errp) +{ + sPAPRMachineState *spapr = SPAPR_MACHINE(OBJECT(hotplug_dev)); + sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(dev); + sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr); + const unsigned windows_supported = spapr_phb_windows_supported(sphb); + + if (dev->hotplugged && !smc->dr_phb_enabled) { + error_setg(errp, "PHB hotplug not supported for this machine"); + return; + } + + if (sphb->index == (uint32_t)-1) { + error_setg(errp, "\"index\" for PAPR PHB is mandatory"); + return; + } + + /* + * This will check that sphb->index doesn't exceed the maximum number of + * PHBs for the current machine type. + */ + smc->phb_placement(spapr, sphb->index, + &sphb->buid, &sphb->io_win_addr, + &sphb->mem_win_addr, &sphb->mem64_win_addr, + windows_supported, sphb->dma_liobn, errp); +} + +static void spapr_phb_plug(HotplugHandler *hotplug_dev, DeviceState *dev, + Error **errp) +{ + sPAPRMachineState *spapr = SPAPR_MACHINE(OBJECT(hotplug_dev)); + sPAPRMachineClass *smc = SPAPR_MACHINE_GET_CLASS(spapr); + sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(dev); + sPAPRDRConnector *drc; + bool hotplugged = spapr_drc_hotplugged(dev); + Error *local_err = NULL; + + if (!smc->dr_phb_enabled) { + return; + } + + drc = spapr_drc_by_id(TYPE_SPAPR_DRC_PHB, sphb->index); + /* hotplug hooks should check it's enabled before getting this far */ + assert(drc); + + spapr_drc_attach(drc, DEVICE(dev), &local_err); + if (local_err) { + error_propagate(errp, local_err); + return; + } + + if (hotplugged) { + spapr_hotplug_req_add_by_index(drc); + } else { + spapr_drc_reset(drc); + } +} + +void spapr_phb_release(DeviceState *dev) +{ + HotplugHandler *hotplug_ctrl = qdev_get_hotplug_handler(dev); + + hotplug_handler_unplug(hotplug_ctrl, dev, &error_abort); +} + +static void spapr_phb_unplug(HotplugHandler *hotplug_dev, DeviceState *dev) +{ + object_unparent(OBJECT(dev)); +} + +static void spapr_phb_unplug_request(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) +{ + sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(dev); + sPAPRDRConnector *drc; + + drc = spapr_drc_by_id(TYPE_SPAPR_DRC_PHB, sphb->index); + assert(drc); + + if (!spapr_drc_unplug_requested(drc)) { + spapr_drc_detach(drc); + spapr_hotplug_req_remove_by_index(drc); + } +} + static void spapr_machine_device_plug(HotplugHandler *hotplug_dev, DeviceState *dev, Error **errp) { @@ -3719,6 +3969,8 @@ static void spapr_machine_device_plug(HotplugHandler *hotplug_dev, spapr_memory_plug(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE)) { spapr_core_plug(hotplug_dev, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_PCI_HOST_BRIDGE)) { + spapr_phb_plug(hotplug_dev, dev, errp); } } @@ -3729,6 +3981,8 @@ static void spapr_machine_device_unplug(HotplugHandler *hotplug_dev, spapr_memory_unplug(hotplug_dev, dev); } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE)) { spapr_core_unplug(hotplug_dev, dev); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_PCI_HOST_BRIDGE)) { + spapr_phb_unplug(hotplug_dev, dev); } } @@ -3737,6 +3991,7 @@ static void spapr_machine_device_unplug_request(HotplugHandler *hotplug_dev, { sPAPRMachineState *sms = SPAPR_MACHINE(OBJECT(hotplug_dev)); MachineClass *mc = MACHINE_GET_CLASS(sms); + sPAPRMachineClass *smc = SPAPR_MACHINE_CLASS(mc); if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM)) { if (spapr_ovec_test(sms->ov5_cas, OV5_HP_EVT)) { @@ -3756,6 +4011,12 @@ static void spapr_machine_device_unplug_request(HotplugHandler *hotplug_dev, return; } spapr_core_unplug_request(hotplug_dev, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_PCI_HOST_BRIDGE)) { + if (!smc->dr_phb_enabled) { + error_setg(errp, "PHB hot unplug not supported on this machine"); + return; + } + spapr_phb_unplug_request(hotplug_dev, dev, errp); } } @@ -3766,6 +4027,8 @@ static void spapr_machine_device_pre_plug(HotplugHandler *hotplug_dev, spapr_memory_pre_plug(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE)) { spapr_core_pre_plug(hotplug_dev, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_PCI_HOST_BRIDGE)) { + spapr_phb_pre_plug(hotplug_dev, dev, errp); } } @@ -3773,7 +4036,8 @@ static HotplugHandler *spapr_get_hotplug_handler(MachineState *machine, DeviceState *dev) { if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) || - object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE)) { + object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_CPU_CORE) || + object_dynamic_cast(OBJECT(dev), TYPE_SPAPR_PCI_HOST_BRIDGE)) { return HOTPLUG_HANDLER(machine); } return NULL; @@ -4004,7 +4268,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) vhc->map_hptes = spapr_map_hptes; vhc->unmap_hptes = spapr_unmap_hptes; vhc->store_hpte = spapr_store_hpte; - vhc->get_patbe = spapr_get_patbe; + vhc->get_pate = spapr_get_pate; vhc->encode_hpt_for_kvm_pr = spapr_encode_hpt_for_kvm_pr; xic->ics_get = spapr_ics_get; xic->ics_resend = spapr_ics_resend; @@ -4026,6 +4290,7 @@ static void spapr_machine_class_init(ObjectClass *oc, void *data) smc->default_caps.caps[SPAPR_CAP_NESTED_KVM_HV] = SPAPR_CAP_OFF; spapr_caps_add_properties(smc, &error_abort); smc->irq = &spapr_irq_xics; + smc->dr_phb_enabled = true; } static const TypeInfo spapr_machine_info = { @@ -4086,11 +4351,18 @@ DEFINE_SPAPR_MACHINE(4_0, "4.0", true); static void spapr_machine_3_1_class_options(MachineClass *mc) { sPAPRMachineClass *smc = SPAPR_MACHINE_CLASS(mc); + static GlobalProperty compat[] = { + { TYPE_SPAPR_MACHINE, "host-model", "passthrough" }, + { TYPE_SPAPR_MACHINE, "host-serial", "passthrough" }, + }; spapr_machine_4_0_class_options(mc); compat_props_add(mc->compat_props, hw_compat_3_1, hw_compat_3_1_len); + compat_props_add(mc->compat_props, compat, G_N_ELEMENTS(compat)); + mc->default_cpu_type = POWERPC_CPU_TYPE_NAME("power8_v2.0"); smc->update_dt_enabled = false; + smc->dr_phb_enabled = false; } DEFINE_SPAPR_MACHINE(3_1, "3.1", false); diff --git a/hw/ppc/spapr_drc.c b/hw/ppc/spapr_drc.c index 2edb7d1e9c..2943cf47d4 100644 --- a/hw/ppc/spapr_drc.c +++ b/hw/ppc/spapr_drc.c @@ -22,6 +22,7 @@ #include "qemu/error-report.h" #include "hw/ppc/spapr.h" /* for RTAS return codes */ #include "hw/pci-host/spapr.h" /* spapr_phb_remove_pci_device_cb callback */ +#include "sysemu/device_tree.h" #include "trace.h" #define DRC_CONTAINER_PATH "/dr-connector" @@ -373,8 +374,7 @@ static void prop_get_fdt(Object *obj, Visitor *v, const char *name, } while (fdt_depth != 0); } -void spapr_drc_attach(sPAPRDRConnector *drc, DeviceState *d, void *fdt, - int fdt_start_offset, Error **errp) +void spapr_drc_attach(sPAPRDRConnector *drc, DeviceState *d, Error **errp) { trace_spapr_drc_attach(spapr_drc_index(drc)); @@ -384,11 +384,8 @@ void spapr_drc_attach(sPAPRDRConnector *drc, DeviceState *d, void *fdt, } g_assert((drc->state == SPAPR_DRC_STATE_LOGICAL_UNUSABLE) || (drc->state == SPAPR_DRC_STATE_PHYSICAL_POWERON)); - g_assert(fdt); drc->dev = d; - drc->fdt = fdt; - drc->fdt_start_offset = fdt_start_offset; object_property_add_link(OBJECT(drc), "device", object_get_typename(OBJECT(drc->dev)), @@ -674,6 +671,7 @@ static void spapr_drc_cpu_class_init(ObjectClass *k, void *data) drck->typename = "CPU"; drck->drc_name_prefix = "CPU "; drck->release = spapr_core_release; + drck->dt_populate = spapr_core_dt_populate; } static void spapr_drc_pci_class_init(ObjectClass *k, void *data) @@ -684,6 +682,7 @@ static void spapr_drc_pci_class_init(ObjectClass *k, void *data) drck->typename = "28"; drck->drc_name_prefix = "C"; drck->release = spapr_phb_remove_pci_device_cb; + drck->dt_populate = spapr_pci_dt_populate; } static void spapr_drc_lmb_class_init(ObjectClass *k, void *data) @@ -694,6 +693,18 @@ static void spapr_drc_lmb_class_init(ObjectClass *k, void *data) drck->typename = "MEM"; drck->drc_name_prefix = "LMB "; drck->release = spapr_lmb_release; + drck->dt_populate = spapr_lmb_dt_populate; +} + +static void spapr_drc_phb_class_init(ObjectClass *k, void *data) +{ + sPAPRDRConnectorClass *drck = SPAPR_DR_CONNECTOR_CLASS(k); + + drck->typeshift = SPAPR_DR_CONNECTOR_TYPE_SHIFT_PHB; + drck->typename = "PHB"; + drck->drc_name_prefix = "PHB "; + drck->release = spapr_phb_release; + drck->dt_populate = spapr_phb_dt_populate; } static const TypeInfo spapr_dr_connector_info = { @@ -739,6 +750,13 @@ static const TypeInfo spapr_drc_lmb_info = { .class_init = spapr_drc_lmb_class_init, }; +static const TypeInfo spapr_drc_phb_info = { + .name = TYPE_SPAPR_DRC_PHB, + .parent = TYPE_SPAPR_DRC_LOGICAL, + .instance_size = sizeof(sPAPRDRConnector), + .class_init = spapr_drc_phb_class_init, +}; + /* helper functions for external users */ sPAPRDRConnector *spapr_drc_by_index(uint32_t index) @@ -1102,10 +1120,28 @@ static void rtas_ibm_configure_connector(PowerPCCPU *cpu, goto out; } - g_assert(drc->fdt); - drck = SPAPR_DR_CONNECTOR_GET_CLASS(drc); + if (!drc->fdt) { + Error *local_err = NULL; + void *fdt; + int fdt_size; + + fdt = create_device_tree(&fdt_size); + + if (drck->dt_populate(drc, spapr, fdt, &drc->fdt_start_offset, + &local_err)) { + g_free(fdt); + error_free(local_err); + rc = SPAPR_DR_CC_RESPONSE_ERROR; + goto out; + } + + drc->fdt = fdt; + drc->ccs_offset = drc->fdt_start_offset; + drc->ccs_depth = 0; + } + do { uint32_t tag; const char *name; @@ -1189,6 +1225,7 @@ static void spapr_drc_register_types(void) type_register_static(&spapr_drc_cpu_info); type_register_static(&spapr_drc_pci_info); type_register_static(&spapr_drc_lmb_info); + type_register_static(&spapr_drc_phb_info); spapr_rtas_register(RTAS_SET_INDICATOR, "set-indicator", rtas_set_indicator); diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c index b9c7ecb9e9..ab9a1f0063 100644 --- a/hw/ppc/spapr_events.c +++ b/hw/ppc/spapr_events.c @@ -526,6 +526,9 @@ static void spapr_hotplug_req_event(uint8_t hp_id, uint8_t hp_action, case SPAPR_DR_CONNECTOR_TYPE_CPU: hp->hotplug_type = RTAS_LOG_V6_HP_TYPE_CPU; break; + case SPAPR_DR_CONNECTOR_TYPE_PHB: + hp->hotplug_type = RTAS_LOG_V6_HP_TYPE_PHB; + break; default: /* we shouldn't be signaling hotplug events for resources * that don't support them diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c index 17bcaa3822..476bad6271 100644 --- a/hw/ppc/spapr_hcall.c +++ b/hw/ppc/spapr_hcall.c @@ -17,37 +17,6 @@ #include "mmu-book3s-v3.h" #include "hw/mem/memory-device.h" -struct LPCRSyncState { - target_ulong value; - target_ulong mask; -}; - -static void do_lpcr_sync(CPUState *cs, run_on_cpu_data arg) -{ - struct LPCRSyncState *s = arg.host_ptr; - PowerPCCPU *cpu = POWERPC_CPU(cs); - CPUPPCState *env = &cpu->env; - target_ulong lpcr; - - cpu_synchronize_state(cs); - lpcr = env->spr[SPR_LPCR]; - lpcr &= ~s->mask; - lpcr |= s->value; - ppc_store_lpcr(cpu, lpcr); -} - -static void set_all_lpcrs(target_ulong value, target_ulong mask) -{ - CPUState *cs; - struct LPCRSyncState s = { - .value = value, - .mask = mask - }; - CPU_FOREACH(cs) { - run_on_cpu(cs, do_lpcr_sync, RUN_ON_CPU_HOST_PTR(&s)); - } -} - static bool has_spr(PowerPCCPU *cpu, int spr) { /* We can test whether the SPR is defined by checking for a valid name */ @@ -1255,12 +1224,12 @@ static target_ulong h_set_mode_resource_le(PowerPCCPU *cpu, switch (mflags) { case H_SET_MODE_ENDIAN_BIG: - set_all_lpcrs(0, LPCR_ILE); + spapr_set_all_lpcrs(0, LPCR_ILE); spapr_pci_switch_vga(true); return H_SUCCESS; case H_SET_MODE_ENDIAN_LITTLE: - set_all_lpcrs(LPCR_ILE, LPCR_ILE); + spapr_set_all_lpcrs(LPCR_ILE, LPCR_ILE); spapr_pci_switch_vga(false); return H_SUCCESS; } @@ -1289,7 +1258,7 @@ static target_ulong h_set_mode_resource_addr_trans_mode(PowerPCCPU *cpu, return H_UNSUPPORTED_FLAG; } - set_all_lpcrs(mflags << LPCR_AIL_SHIFT, LPCR_AIL); + spapr_set_all_lpcrs(mflags << LPCR_AIL_SHIFT, LPCR_AIL); return H_SUCCESS; } @@ -1342,12 +1311,12 @@ static void spapr_check_setup_free_hpt(sPAPRMachineState *spapr, * later and so assumed radix and now it's called H_REG_PROC_TBL */ - if ((patbe_old & PATBE1_GR) == (patbe_new & PATBE1_GR)) { + if ((patbe_old & PATE1_GR) == (patbe_new & PATE1_GR)) { /* We assume RADIX, so this catches all the "Do Nothing" cases */ - } else if (!(patbe_old & PATBE1_GR)) { + } else if (!(patbe_old & PATE1_GR)) { /* HASH->RADIX : Free HPT */ spapr_free_hpt(spapr); - } else if (!(patbe_new & PATBE1_GR)) { + } else if (!(patbe_new & PATE1_GR)) { /* RADIX->HASH || NOTHING->HASH : Allocate HPT */ spapr_setup_hpt_and_vrma(spapr); } @@ -1385,7 +1354,7 @@ static target_ulong h_register_process_table(PowerPCCPU *cpu, } else if (table_size > 24) { return H_P4; } - cproc = PATBE1_GR | proc_tbl | table_size; + cproc = PATE1_GR | proc_tbl | table_size; } else { /* Register new HPT process table */ if (flags & FLAG_HASH_PROC_TBL) { /* Hash with Segment Tables */ /* TODO - Not Supported */ @@ -1404,13 +1373,15 @@ static target_ulong h_register_process_table(PowerPCCPU *cpu, } } else { /* Deregister current process table */ - /* Set to benign value: (current GR) | 0. This allows - * deregistration in KVM to succeed even if the radix bit in flags - * doesn't match the radix bit in the old PATB. */ - cproc = spapr->patb_entry & PATBE1_GR; + /* + * Set to benign value: (current GR) | 0. This allows + * deregistration in KVM to succeed even if the radix bit + * in flags doesn't match the radix bit in the old PATE. + */ + cproc = spapr->patb_entry & PATE1_GR; } } else { /* Maintain current registration */ - if (!(flags & FLAG_RADIX) != !(spapr->patb_entry & PATBE1_GR)) { + if (!(flags & FLAG_RADIX) != !(spapr->patb_entry & PATE1_GR)) { /* Technically caused by flag bits => H_PARAMETER */ return H_PARAMETER; /* Existing Process Table Mismatch */ } @@ -1422,10 +1393,11 @@ static target_ulong h_register_process_table(PowerPCCPU *cpu, spapr->patb_entry = cproc; /* Save new process table */ - /* Update the UPRT and GTSE bits in the LPCR for all cpus */ - set_all_lpcrs(((flags & (FLAG_RADIX | FLAG_HASH_PROC_TBL)) ? LPCR_UPRT : 0) | - ((flags & FLAG_GTSE) ? LPCR_GTSE : 0), - LPCR_UPRT | LPCR_GTSE); + /* Update the UPRT, HR and GTSE bits in the LPCR for all cpus */ + spapr_set_all_lpcrs(((flags & (FLAG_RADIX | FLAG_HASH_PROC_TBL)) ? + (LPCR_UPRT | LPCR_HR) : 0) | + ((flags & FLAG_GTSE) ? LPCR_GTSE : 0), + LPCR_UPRT | LPCR_HR | LPCR_GTSE); if (kvm_enabled()) { return kvmppc_configure_v3_mmu(cpu, flags & FLAG_RADIX, @@ -1646,7 +1618,7 @@ static target_ulong h_client_architecture_support(PowerPCCPU *cpu, if (!spapr->cas_reboot) { /* If spapr_machine_reset() did not set up a HPT but one is necessary * (because the guest isn't going to use radix) then set it up here. */ - if ((spapr->patb_entry & PATBE1_GR) && !guest_radix) { + if ((spapr->patb_entry & PATE1_GR) && !guest_radix) { /* legacy hash or new hash: */ spapr_setup_hpt_and_vrma(spapr); } diff --git a/hw/ppc/spapr_irq.c b/hw/ppc/spapr_irq.c index 4297eed600..4145079d7f 100644 --- a/hw/ppc/spapr_irq.c +++ b/hw/ppc/spapr_irq.c @@ -230,6 +230,11 @@ static void spapr_irq_reset_xics(sPAPRMachineState *spapr, Error **errp) /* TODO: create the KVM XICS device */ } +static const char *spapr_irq_get_nodename_xics(sPAPRMachineState *spapr) +{ + return XICS_NODENAME; +} + #define SPAPR_IRQ_XICS_NR_IRQS 0x1000 #define SPAPR_IRQ_XICS_NR_MSIS \ (XICS_IRQ_BASE + SPAPR_IRQ_XICS_NR_IRQS - SPAPR_IRQ_MSI) @@ -249,6 +254,7 @@ sPAPRIrq spapr_irq_xics = { .post_load = spapr_irq_post_load_xics, .reset = spapr_irq_reset_xics, .set_irq = spapr_irq_set_irq_xics, + .get_nodename = spapr_irq_get_nodename_xics, }; /* @@ -384,6 +390,11 @@ static void spapr_irq_set_irq_xive(void *opaque, int srcno, int val) xive_source_set_irq(&spapr->xive->source, srcno, val); } +static const char *spapr_irq_get_nodename_xive(sPAPRMachineState *spapr) +{ + return spapr->xive->nodename; +} + /* * XIVE uses the full IRQ number space. Set it to 8K to be compatible * with XICS. @@ -407,6 +418,7 @@ sPAPRIrq spapr_irq_xive = { .post_load = spapr_irq_post_load_xive, .reset = spapr_irq_reset_xive, .set_irq = spapr_irq_set_irq_xive, + .get_nodename = spapr_irq_get_nodename_xive, }; /* @@ -541,6 +553,11 @@ static void spapr_irq_set_irq_dual(void *opaque, int srcno, int val) spapr_irq_current(spapr)->set_irq(spapr, srcno, val); } +static const char *spapr_irq_get_nodename_dual(sPAPRMachineState *spapr) +{ + return spapr_irq_current(spapr)->get_nodename(spapr); +} + /* * Define values in sync with the XIVE and XICS backend */ @@ -561,7 +578,8 @@ sPAPRIrq spapr_irq_dual = { .cpu_intc_create = spapr_irq_cpu_intc_create_dual, .post_load = spapr_irq_post_load_dual, .reset = spapr_irq_reset_dual, - .set_irq = spapr_irq_set_irq_dual + .set_irq = spapr_irq_set_irq_dual, + .get_nodename = spapr_irq_get_nodename_dual, }; /* @@ -620,6 +638,27 @@ void spapr_irq_reset(sPAPRMachineState *spapr, Error **errp) } } +int spapr_irq_get_phandle(sPAPRMachineState *spapr, void *fdt, Error **errp) +{ + const char *nodename = spapr->irq->get_nodename(spapr); + int offset, phandle; + + offset = fdt_subnode_offset(fdt, 0, nodename); + if (offset < 0) { + error_setg(errp, "Can't find node \"%s\": %s", nodename, + fdt_strerror(offset)); + return -1; + } + + phandle = fdt_get_phandle(fdt, offset); + if (!phandle) { + error_setg(errp, "Can't get phandle of node \"%s\"", nodename); + return -1; + } + + return phandle; +} + /* * XICS legacy routines - to deprecate one day */ @@ -691,4 +730,5 @@ sPAPRIrq spapr_irq_xics_legacy = { .cpu_intc_create = spapr_irq_cpu_intc_create_xics, .post_load = spapr_irq_post_load_xics, .set_irq = spapr_irq_set_irq_xics, + .get_nodename = spapr_irq_get_nodename_xics, }; diff --git a/hw/ppc/spapr_ovec.c b/hw/ppc/spapr_ovec.c index 318bf33de4..12510b236a 100644 --- a/hw/ppc/spapr_ovec.c +++ b/hw/ppc/spapr_ovec.c @@ -16,6 +16,7 @@ #include "qemu/bitmap.h" #include "exec/address-spaces.h" #include "qemu/error-report.h" +#include "sysemu/qtest.h" #include "trace.h" #include <libfdt.h> @@ -131,6 +132,11 @@ bool spapr_ovec_test(sPAPROptionVector *ov, long bitnr) g_assert(ov); g_assert(bitnr < OV_MAXBITS); + /* support memory unplug for qtest */ + if (qtest_enabled() && bitnr == OV5_HP_EVT) { + return true; + } + return test_bit(bitnr, ov->bitmap) ? true : false; } diff --git a/hw/ppc/spapr_pci.c b/hw/ppc/spapr_pci.c index 60777b2355..06a5ffd281 100644 --- a/hw/ppc/spapr_pci.c +++ b/hw/ppc/spapr_pci.c @@ -1408,6 +1408,17 @@ static uint32_t spapr_phb_get_pci_drc_index(sPAPRPHBState *phb, return spapr_drc_index(drc); } +int spapr_pci_dt_populate(sPAPRDRConnector *drc, sPAPRMachineState *spapr, + void *fdt, int *fdt_start_offset, Error **errp) +{ + HotplugHandler *plug_handler = qdev_get_hotplug_handler(drc->dev); + sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(plug_handler); + PCIDevice *pdev = PCI_DEVICE(drc->dev); + + *fdt_start_offset = spapr_create_pci_child_dt(sphb, pdev, fdt, 0); + return 0; +} + static void spapr_pci_plug(HotplugHandler *plug_handler, DeviceState *plugged_dev, Error **errp) { @@ -1417,8 +1428,6 @@ static void spapr_pci_plug(HotplugHandler *plug_handler, Error *local_err = NULL; PCIBus *bus = PCI_BUS(qdev_get_parent_bus(DEVICE(pdev))); uint32_t slotnr = PCI_SLOT(pdev->devfn); - void *fdt = NULL; - int fdt_start_offset, fdt_size; /* if DR is disabled we don't need to do anything in the case of * hotplug or coldplug callbacks @@ -1448,10 +1457,7 @@ static void spapr_pci_plug(HotplugHandler *plug_handler, goto out; } - fdt = create_device_tree(&fdt_size); - fdt_start_offset = spapr_create_pci_child_dt(phb, pdev, fdt, 0); - - spapr_drc_attach(drc, DEVICE(pdev), fdt, fdt_start_offset, &local_err); + spapr_drc_attach(drc, DEVICE(pdev), &local_err); if (local_err) { goto out; } @@ -1483,7 +1489,6 @@ static void spapr_pci_plug(HotplugHandler *plug_handler, out: if (local_err) { error_propagate(errp, local_err); - g_free(fdt); } } @@ -1565,6 +1570,75 @@ static void spapr_pci_unplug_request(HotplugHandler *plug_handler, } } +static void spapr_phb_finalizefn(Object *obj) +{ + sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(obj); + + g_free(sphb->dtbusname); + sphb->dtbusname = NULL; +} + +static void spapr_phb_unrealize(DeviceState *dev, Error **errp) +{ + sPAPRMachineState *spapr = SPAPR_MACHINE(qdev_get_machine()); + SysBusDevice *s = SYS_BUS_DEVICE(dev); + PCIHostState *phb = PCI_HOST_BRIDGE(s); + sPAPRPHBState *sphb = SPAPR_PCI_HOST_BRIDGE(phb); + sPAPRTCETable *tcet; + int i; + const unsigned windows_supported = spapr_phb_windows_supported(sphb); + + if (sphb->msi) { + g_hash_table_unref(sphb->msi); + sphb->msi = NULL; + } + + /* + * Remove IO/MMIO subregions and aliases, rest should get cleaned + * via PHB's unrealize->object_finalize + */ + for (i = windows_supported - 1; i >= 0; i--) { + tcet = spapr_tce_find_by_liobn(sphb->dma_liobn[i]); + if (tcet) { + memory_region_del_subregion(&sphb->iommu_root, + spapr_tce_get_iommu(tcet)); + } + } + + if (sphb->dr_enabled) { + for (i = PCI_SLOT_MAX * 8 - 1; i >= 0; i--) { + sPAPRDRConnector *drc = spapr_drc_by_id(TYPE_SPAPR_DRC_PCI, + (sphb->index << 16) | i); + + if (drc) { + object_unparent(OBJECT(drc)); + } + } + } + + for (i = PCI_NUM_PINS - 1; i >= 0; i--) { + if (sphb->lsi_table[i].irq) { + spapr_irq_free(spapr, sphb->lsi_table[i].irq, 1); + sphb->lsi_table[i].irq = 0; + } + } + + QLIST_REMOVE(sphb, list); + + memory_region_del_subregion(&sphb->iommu_root, &sphb->msiwindow); + + address_space_destroy(&sphb->iommu_as); + + qbus_set_hotplug_handler(BUS(phb->bus), NULL, &error_abort); + pci_unregister_root_bus(phb->bus); + + memory_region_del_subregion(get_system_memory(), &sphb->iowindow); + if (sphb->mem64_win_pciaddr != (hwaddr)-1) { + memory_region_del_subregion(get_system_memory(), &sphb->mem64window); + } + memory_region_del_subregion(get_system_memory(), &sphb->mem32window); +} + static void spapr_phb_realize(DeviceState *dev, Error **errp) { /* We don't use SPAPR_MACHINE() in order to exit gracefully if the user @@ -1582,29 +1656,14 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) PCIBus *bus; uint64_t msi_window_size = 4096; sPAPRTCETable *tcet; - const unsigned windows_supported = - sphb->ddw_enabled ? SPAPR_PCI_DMA_MAX_WINDOWS : 1; + const unsigned windows_supported = spapr_phb_windows_supported(sphb); if (!spapr) { error_setg(errp, TYPE_SPAPR_PCI_HOST_BRIDGE " needs a pseries machine"); return; } - if (sphb->index != (uint32_t)-1) { - Error *local_err = NULL; - - smc->phb_placement(spapr, sphb->index, - &sphb->buid, &sphb->io_win_addr, - &sphb->mem_win_addr, &sphb->mem64_win_addr, - windows_supported, sphb->dma_liobn, &local_err); - if (local_err) { - error_propagate(errp, local_err); - return; - } - } else { - error_setg(errp, "\"index\" for PAPR PHB is mandatory"); - return; - } + assert(sphb->index != (uint32_t)-1); /* checked in spapr_phb_pre_plug() */ if (sphb->mem64_win_size != 0) { if (sphb->mem_win_size > SPAPR_PCI_MEM32_WIN_SIZE) { @@ -1740,6 +1799,10 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) if (local_err) { error_propagate_prepend(errp, local_err, "can't allocate LSIs: "); + /* + * Older machines will never support PHB hotplug, ie, this is an + * init only path and QEMU will terminate. No need to rollback. + */ return; } } @@ -1747,7 +1810,7 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) spapr_irq_claim(spapr, irq, true, &local_err); if (local_err) { error_propagate_prepend(errp, local_err, "can't allocate LSIs: "); - return; + goto unrealize; } sphb->lsi_table[i].irq = irq; @@ -1767,13 +1830,17 @@ static void spapr_phb_realize(DeviceState *dev, Error **errp) if (!tcet) { error_setg(errp, "Creating window#%d failed for %s", i, sphb->dtbusname); - return; + goto unrealize; } memory_region_add_subregion(&sphb->iommu_root, 0, spapr_tce_get_iommu(tcet)); } sphb->msi = g_hash_table_new_full(g_int_hash, g_int_equal, g_free, g_free); + return; + +unrealize: + spapr_phb_unrealize(dev, NULL); } static int spapr_phb_children_reset(Object *child, void *opaque) @@ -1972,6 +2039,7 @@ static void spapr_phb_class_init(ObjectClass *klass, void *data) hc->root_bus_path = spapr_phb_root_bus_path; dc->realize = spapr_phb_realize; + dc->unrealize = spapr_phb_unrealize; dc->props = spapr_phb_properties; dc->reset = spapr_phb_reset; dc->vmsd = &vmstate_spapr_pci; @@ -1987,6 +2055,7 @@ static const TypeInfo spapr_phb_info = { .name = TYPE_SPAPR_PCI_HOST_BRIDGE, .parent = TYPE_PCI_HOST_BRIDGE, .instance_size = sizeof(sPAPRPHBState), + .instance_finalize = spapr_phb_finalizefn, .class_init = spapr_phb_class_init, .interfaces = (InterfaceInfo[]) { { TYPE_HOTPLUG_HANDLER }, @@ -2070,7 +2139,7 @@ static void spapr_phb_pci_enumerate(sPAPRPHBState *phb) } int spapr_populate_pci_dt(sPAPRPHBState *phb, uint32_t intc_phandle, void *fdt, - uint32_t nr_msis) + uint32_t nr_msis, int *node_offset) { int bus_off, i, j, ret; gchar *nodename; @@ -2120,11 +2189,15 @@ int spapr_populate_pci_dt(sPAPRPHBState *phb, uint32_t intc_phandle, void *fdt, sPAPRTCETable *tcet; PCIBus *bus = PCI_HOST_BRIDGE(phb)->bus; sPAPRFDT s_fdt; + sPAPRDRConnector *drc; /* Start populating the FDT */ nodename = g_strdup_printf("pci@%" PRIx64, phb->buid); _FDT(bus_off = fdt_add_subnode(fdt, 0, nodename)); g_free(nodename); + if (node_offset) { + *node_offset = bus_off; + } /* Write PHB properties */ _FDT(fdt_setprop_string(fdt, bus_off, "device_type", "pci")); @@ -2183,6 +2256,14 @@ int spapr_populate_pci_dt(sPAPRPHBState *phb, uint32_t intc_phandle, void *fdt, tcet->liobn, tcet->bus_offset, tcet->nb_table << tcet->page_shift); + drc = spapr_drc_by_id(TYPE_SPAPR_DRC_PHB, phb->index); + if (drc) { + uint32_t drc_index = cpu_to_be32(spapr_drc_index(drc)); + + _FDT(fdt_setprop(fdt, bus_off, "ibm,my-drc-index", &drc_index, + sizeof(drc_index))); + } + /* Walk the bridges and program the bus numbers*/ spapr_phb_pci_enumerate(phb); _FDT(fdt_setprop_cell(fdt, bus_off, "qemu,phb-enumerated", 0x1)); diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c index d6a0952154..7a2cb786a3 100644 --- a/hw/ppc/spapr_rtas.c +++ b/hw/ppc/spapr_rtas.c @@ -172,10 +172,10 @@ static void rtas_start_cpu(PowerPCCPU *callcpu, sPAPRMachineState *spapr, * New cpus are expected to start in the same radix/hash mode * as the existing CPUs */ - if (ppc64_radix_guest(callcpu)) { - lpcr |= LPCR_UPRT | LPCR_GTSE; + if (ppc64_v3_radix(callcpu)) { + lpcr |= LPCR_UPRT | LPCR_GTSE | LPCR_HR; } else { - lpcr &= ~(LPCR_UPRT | LPCR_GTSE); + lpcr &= ~(LPCR_UPRT | LPCR_GTSE | LPCR_HR); } } ppc_store_lpcr(newcpu, lpcr); diff --git a/include/hw/pci-host/spapr.h b/include/hw/pci-host/spapr.h index 51d81c4b7c..ab0e3a0a6f 100644 --- a/include/hw/pci-host/spapr.h +++ b/include/hw/pci-host/spapr.h @@ -113,7 +113,7 @@ static inline qemu_irq spapr_phb_lsi_qirq(struct sPAPRPHBState *phb, int pin) } int spapr_populate_pci_dt(sPAPRPHBState *phb, uint32_t intc_phandle, void *fdt, - uint32_t nr_msis); + uint32_t nr_msis, int *node_offset); void spapr_pci_rtas_init(void); @@ -121,8 +121,10 @@ sPAPRPHBState *spapr_pci_find_phb(sPAPRMachineState *spapr, uint64_t buid); PCIDevice *spapr_pci_find_dev(sPAPRMachineState *spapr, uint64_t buid, uint32_t config_addr); -/* PCI release callback. */ +/* DRC callbacks */ void spapr_phb_remove_pci_device_cb(DeviceState *dev); +int spapr_pci_dt_populate(sPAPRDRConnector *drc, sPAPRMachineState *spapr, + void *fdt, int *fdt_start_offset, Error **errp); /* VFIO EEH hooks */ #ifdef CONFIG_LINUX @@ -163,4 +165,9 @@ static inline void spapr_phb_vfio_reset(DeviceState *qdev) void spapr_phb_dma_reset(sPAPRPHBState *sphb); +static inline unsigned spapr_phb_windows_supported(sPAPRPHBState *sphb) +{ + return sphb->ddw_enabled ? SPAPR_PCI_DMA_MAX_WINDOWS : 1; +} + #endif /* PCI_HOST_SPAPR_H */ diff --git a/include/hw/ppc/ppc.h b/include/hw/ppc/ppc.h index 298ec354a8..746170f635 100644 --- a/include/hw/ppc/ppc.h +++ b/include/hw/ppc/ppc.h @@ -73,6 +73,7 @@ static inline void ppc40x_irq_init(PowerPCCPU *cpu) {} static inline void ppc6xx_irq_init(PowerPCCPU *cpu) {} static inline void ppc970_irq_init(PowerPCCPU *cpu) {} static inline void ppcPOWER7_irq_init(PowerPCCPU *cpu) {} +static inline void ppcPOWER9_irq_init(PowerPCCPU *cpu) {} static inline void ppce500_irq_init(PowerPCCPU *cpu) {} #else void ppc40x_irq_init(PowerPCCPU *cpu); @@ -80,6 +81,7 @@ void ppce500_irq_init(PowerPCCPU *cpu); void ppc6xx_irq_init(PowerPCCPU *cpu); void ppc970_irq_init(PowerPCCPU *cpu); void ppcPOWER7_irq_init(PowerPCCPU *cpu); +void ppcPOWER9_irq_init(PowerPCCPU *cpu); #endif /* PPC machines for OpenBIOS */ diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h index 631fc5103b..59073a7579 100644 --- a/include/hw/ppc/spapr.h +++ b/include/hw/ppc/spapr.h @@ -104,6 +104,7 @@ struct sPAPRMachineClass { /*< public >*/ bool dr_lmb_enabled; /* enable dynamic-reconfig/hotplug of LMBs */ + bool dr_phb_enabled; /* enable dynamic-reconfig/hotplug of PHBs */ bool update_dt_enabled; /* enable KVMPPC_H_UPDATE_DT */ bool use_ohci_by_default; /* use USB-OHCI instead of XHCI */ bool pre_2_10_has_unused_icps; @@ -177,6 +178,8 @@ struct sPAPRMachineState { /*< public >*/ char *kvm_type; + char *host_model; + char *host_serial; int32_t irq_map_nr; unsigned long *irq_map; @@ -762,9 +765,16 @@ void spapr_reallocate_hpt(sPAPRMachineState *spapr, int shift, void spapr_clear_pending_events(sPAPRMachineState *spapr); int spapr_max_server_number(sPAPRMachineState *spapr); -/* CPU and LMB DRC release callbacks. */ +/* DRC callbacks. */ void spapr_core_release(DeviceState *dev); +int spapr_core_dt_populate(sPAPRDRConnector *drc, sPAPRMachineState *spapr, + void *fdt, int *fdt_start_offset, Error **errp); void spapr_lmb_release(DeviceState *dev); +int spapr_lmb_dt_populate(sPAPRDRConnector *drc, sPAPRMachineState *spapr, + void *fdt, int *fdt_start_offset, Error **errp); +void spapr_phb_release(DeviceState *dev); +int spapr_phb_dt_populate(sPAPRDRConnector *drc, sPAPRMachineState *spapr, + void *fdt, int *fdt_start_offset, Error **errp); void spapr_rtc_read(sPAPRRTCState *rtc, struct tm *tm, uint32_t *ns); int spapr_rtc_import_offset(sPAPRRTCState *rtc, int64_t legacy_offset); @@ -839,4 +849,5 @@ void spapr_check_pagesize(sPAPRMachineState *spapr, hwaddr pagesize, #define SPAPR_OV5_XIVE_EXPLOIT 0x40 #define SPAPR_OV5_XIVE_BOTH 0x80 /* Only to advertise on the platform */ +void spapr_set_all_lpcrs(target_ulong value, target_ulong mask); #endif /* HW_SPAPR_H */ diff --git a/include/hw/ppc/spapr_drc.h b/include/hw/ppc/spapr_drc.h index f6ff32e7e2..46b0f6216d 100644 --- a/include/hw/ppc/spapr_drc.h +++ b/include/hw/ppc/spapr_drc.h @@ -18,6 +18,7 @@ #include "qom/object.h" #include "sysemu/sysemu.h" #include "hw/qdev.h" +#include "qapi/error.h" #define TYPE_SPAPR_DR_CONNECTOR "spapr-dr-connector" #define SPAPR_DR_CONNECTOR_GET_CLASS(obj) \ @@ -70,6 +71,14 @@ #define SPAPR_DRC_LMB(obj) OBJECT_CHECK(sPAPRDRConnector, (obj), \ TYPE_SPAPR_DRC_LMB) +#define TYPE_SPAPR_DRC_PHB "spapr-drc-phb" +#define SPAPR_DRC_PHB_GET_CLASS(obj) \ + OBJECT_GET_CLASS(sPAPRDRConnectorClass, obj, TYPE_SPAPR_DRC_PHB) +#define SPAPR_DRC_PHB_CLASS(klass) \ + OBJECT_CLASS_CHECK(sPAPRDRConnectorClass, klass, TYPE_SPAPR_DRC_PHB) +#define SPAPR_DRC_PHB(obj) OBJECT_CHECK(sPAPRDRConnector, (obj), \ + TYPE_SPAPR_DRC_PHB) + /* * Various hotplug types managed by sPAPRDRConnector * @@ -213,6 +222,8 @@ typedef struct sPAPRDRConnector { int fdt_start_offset; } sPAPRDRConnector; +struct sPAPRMachineState; + typedef struct sPAPRDRConnectorClass { /*< private >*/ DeviceClass parent; @@ -228,6 +239,9 @@ typedef struct sPAPRDRConnectorClass { uint32_t (*isolate)(sPAPRDRConnector *drc); uint32_t (*unisolate)(sPAPRDRConnector *drc); void (*release)(DeviceState *dev); + + int (*dt_populate)(sPAPRDRConnector *drc, struct sPAPRMachineState *spapr, + void *fdt, int *fdt_start_offset, Error **errp); } sPAPRDRConnectorClass; typedef struct sPAPRDRCPhysical { @@ -255,8 +269,7 @@ 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); -void spapr_drc_attach(sPAPRDRConnector *drc, DeviceState *d, void *fdt, - int fdt_start_offset, Error **errp); +void spapr_drc_attach(sPAPRDRConnector *drc, DeviceState *d, Error **errp); void spapr_drc_detach(sPAPRDRConnector *drc); bool spapr_drc_needed(void *opaque); diff --git a/include/hw/ppc/spapr_irq.h b/include/hw/ppc/spapr_irq.h index 488511c3d8..ec1ee64fa6 100644 --- a/include/hw/ppc/spapr_irq.h +++ b/include/hw/ppc/spapr_irq.h @@ -47,6 +47,7 @@ typedef struct sPAPRIrq { int (*post_load)(sPAPRMachineState *spapr, int version_id); void (*reset)(sPAPRMachineState *spapr, Error **errp); void (*set_irq)(void *opaque, int srcno, int val); + const char *(*get_nodename)(sPAPRMachineState *spapr); } sPAPRIrq; extern sPAPRIrq spapr_irq_xics; @@ -60,6 +61,7 @@ void spapr_irq_free(sPAPRMachineState *spapr, int irq, int num); qemu_irq spapr_qirq(sPAPRMachineState *spapr, int irq); int spapr_irq_post_load(sPAPRMachineState *spapr, int version_id); void spapr_irq_reset(sPAPRMachineState *spapr, Error **errp); +int spapr_irq_get_phandle(sPAPRMachineState *spapr, void *fdt, Error **errp); /* * XICS legacy routines diff --git a/include/hw/ppc/spapr_xive.h b/include/hw/ppc/spapr_xive.h index 9bec9192e4..2d31f24e3b 100644 --- a/include/hw/ppc/spapr_xive.h +++ b/include/hw/ppc/spapr_xive.h @@ -26,6 +26,9 @@ typedef struct sPAPRXive { XiveENDSource end_source; hwaddr end_base; + /* DT */ + gchar *nodename; + /* Routing table */ XiveEAS *eat; uint32_t nr_irqs; diff --git a/include/hw/ppc/xics.h b/include/hw/ppc/xics.h index d36bbe11ee..eb65ad7e43 100644 --- a/include/hw/ppc/xics.h +++ b/include/hw/ppc/xics.h @@ -195,6 +195,7 @@ void icp_synchronize_state(ICPState *icp); void icp_kvm_realize(DeviceState *dev, Error **errp); void ics_get_kvm_state(ICSState *ics); +int ics_set_kvm_state_one(ICSState *ics, int srcno); int ics_set_kvm_state(ICSState *ics); void ics_synchronize_state(ICSState *ics); void ics_kvm_set_irq(ICSState *ics, int srcno, int val); diff --git a/include/hw/ppc/xics_spapr.h b/include/hw/ppc/xics_spapr.h index b1ab27d022..b8d924baf4 100644 --- a/include/hw/ppc/xics_spapr.h +++ b/include/hw/ppc/xics_spapr.h @@ -29,6 +29,8 @@ #include "hw/ppc/spapr.h" +#define XICS_NODENAME "interrupt-controller" + void spapr_dt_xics(sPAPRMachineState *spapr, uint32_t nr_servers, void *fdt, uint32_t phandle); int xics_kvm_init(sPAPRMachineState *spapr, Error **errp); diff --git a/target/ppc/cpu-qom.h b/target/ppc/cpu-qom.h index 3130802304..ae51fe754e 100644 --- a/target/ppc/cpu-qom.h +++ b/target/ppc/cpu-qom.h @@ -113,6 +113,8 @@ enum powerpc_excp_t { POWERPC_EXCP_POWER7, /* POWER8 exception model */ POWERPC_EXCP_POWER8, + /* POWER9 exception model */ + POWERPC_EXCP_POWER9, }; /*****************************************************************************/ @@ -122,6 +124,7 @@ typedef enum { PPC_PM_NAP, PPC_PM_SLEEP, PPC_PM_RVWINKLE, + PPC_PM_STOP, } powerpc_pm_insn_t; /*****************************************************************************/ @@ -139,6 +142,8 @@ enum powerpc_input_t { PPC_FLAGS_INPUT_970, /* PowerPC POWER7 bus */ PPC_FLAGS_INPUT_POWER7, + /* PowerPC POWER9 bus */ + PPC_FLAGS_INPUT_POWER9, /* PowerPC 401 bus */ PPC_FLAGS_INPUT_401, /* Freescale RCPU bus */ diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index 325ebbeb98..26604ddf98 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -160,8 +160,10 @@ enum { /* Server doorbell variants */ POWERPC_EXCP_SDOOR = 99, POWERPC_EXCP_SDOOR_HV = 100, + /* ISA 3.00 additions */ + POWERPC_EXCP_HVIRT = 101, /* EOL */ - POWERPC_EXCP_NB = 101, + POWERPC_EXCP_NB = 102, /* QEMU exceptions: used internally during code translation */ POWERPC_EXCP_STOP = 0x200, /* stop translation */ POWERPC_EXCP_BRANCH = 0x201, /* branch instruction */ @@ -318,6 +320,10 @@ struct ppc_slb_t { #define SEGMENT_SHIFT_1T 40 #define SEGMENT_MASK_1T (~((1ULL << SEGMENT_SHIFT_1T) - 1)) +typedef struct ppc_v3_pate_t { + uint64_t dw0; + uint64_t dw1; +} ppc_v3_pate_t; /*****************************************************************************/ /* Machine state register bits definition */ @@ -386,6 +392,7 @@ struct ppc_slb_t { #define LPCR_AIL (3ull << LPCR_AIL_SHIFT) #define LPCR_UPRT PPC_BIT(41) /* Use Process Table */ #define LPCR_EVIRT PPC_BIT(42) /* Enhanced Virtualisation */ +#define LPCR_HR PPC_BIT(43) /* Host Radix */ #define LPCR_ONL PPC_BIT(45) #define LPCR_LD PPC_BIT(46) /* Large Decrementer */ #define LPCR_P7_PECE0 PPC_BIT(49) @@ -414,6 +421,10 @@ struct ppc_slb_t { #define LPCR_HVICE PPC_BIT(62) /* HV Virtualisation Int Enable */ #define LPCR_HDICE PPC_BIT(63) +/* PSSCR bits */ +#define PSSCR_ESL PPC_BIT(42) /* Enable State Loss */ +#define PSSCR_EC PPC_BIT(43) /* Exit Criterion */ + #define msr_sf ((env->msr >> MSR_SF) & 1) #define msr_isf ((env->msr >> MSR_ISF) & 1) #define msr_shv ((env->msr >> MSR_SHV) & 1) @@ -1110,11 +1121,13 @@ struct CPUPPCState { * instructions and SPRs are diallowed if MSR:HV is 0 */ bool has_hv_mode; - /* On P7/P8, set when in PM state, we need to handle resume - * in a special way (such as routing some resume causes to - * 0x100), so flag this here. + + /* + * On P7/P8/P9, set when in PM state, we need to handle resume in + * a special way (such as routing some resume causes to 0x100, ie, + * sreset), so flag this here. */ - bool in_pm_state; + bool resume_as_sreset; #endif /* Those resources are used only during code translation */ @@ -1239,7 +1252,7 @@ struct PPCVirtualHypervisorClass { hwaddr ptex, int n); void (*store_hpte)(PPCVirtualHypervisor *vhyp, hwaddr ptex, uint64_t pte0, uint64_t pte1); - uint64_t (*get_patbe)(PPCVirtualHypervisor *vhyp); + void (*get_pate)(PPCVirtualHypervisor *vhyp, ppc_v3_pate_t *entry); target_ulong (*encode_hpt_for_kvm_pr)(PPCVirtualHypervisor *vhyp); }; @@ -2319,6 +2332,13 @@ enum { * them */ POWER7_INPUT_NB, }; + +enum { + /* POWER9 input pins */ + POWER9_INPUT_INT = 0, + POWER9_INPUT_HINT = 1, + POWER9_INPUT_NB, +}; #endif /* Hardware exceptions definitions */ @@ -2343,6 +2363,7 @@ enum { PPC_INTERRUPT_PERFM, /* Performance monitor interrupt */ PPC_INTERRUPT_HMI, /* Hypervisor Maintainance interrupt */ PPC_INTERRUPT_HDOORBELL, /* Hypervisor Doorbell interrupt */ + PPC_INTERRUPT_HVIRT, /* Hypervisor virtualization interrupt */ }; /* Processor Compatibility mask (PCR) */ diff --git a/target/ppc/excp_helper.c b/target/ppc/excp_helper.c index 751d759fcc..39bedbb11d 100644 --- a/target/ppc/excp_helper.c +++ b/target/ppc/excp_helper.c @@ -65,6 +65,49 @@ static inline void dump_syscall(CPUPPCState *env) ppc_dump_gpr(env, 6), env->nip); } +static int powerpc_reset_wakeup(CPUState *cs, CPUPPCState *env, int excp, + target_ulong *msr) +{ + /* We no longer are in a PM state */ + env->resume_as_sreset = false; + + /* Pretend to be returning from doze always as we don't lose state */ + *msr |= (0x1ull << (63 - 47)); + + /* Machine checks are sent normally */ + if (excp == POWERPC_EXCP_MCHECK) { + return excp; + } + switch (excp) { + case POWERPC_EXCP_RESET: + *msr |= 0x4ull << (63 - 45); + break; + case POWERPC_EXCP_EXTERNAL: + *msr |= 0x8ull << (63 - 45); + break; + case POWERPC_EXCP_DECR: + *msr |= 0x6ull << (63 - 45); + break; + case POWERPC_EXCP_SDOOR: + *msr |= 0x5ull << (63 - 45); + break; + case POWERPC_EXCP_SDOOR_HV: + *msr |= 0x3ull << (63 - 45); + break; + case POWERPC_EXCP_HV_MAINT: + *msr |= 0xaull << (63 - 45); + break; + case POWERPC_EXCP_HVIRT: + *msr |= 0x9ull << (63 - 45); + break; + default: + cpu_abort(cs, "Unsupported exception %d in Power Save mode\n", + excp); + } + return POWERPC_EXCP_RESET; +} + + /* Note that this function should be greatly optimized * when called with a constant excp, from ppc_hw_interrupt */ @@ -97,47 +140,17 @@ static inline void powerpc_excp(PowerPCCPU *cpu, int excp_model, int excp) asrr0 = -1; asrr1 = -1; - /* check for special resume at 0x100 from doze/nap/sleep/winkle on P7/P8 */ - if (env->in_pm_state) { - env->in_pm_state = false; - - /* Pretend to be returning from doze always as we don't lose state */ - msr |= (0x1ull << (63 - 47)); - - /* Non-machine check are routed to 0x100 with a wakeup cause - * encoded in SRR1 - */ - if (excp != POWERPC_EXCP_MCHECK) { - switch (excp) { - case POWERPC_EXCP_RESET: - msr |= 0x4ull << (63 - 45); - break; - case POWERPC_EXCP_EXTERNAL: - msr |= 0x8ull << (63 - 45); - break; - case POWERPC_EXCP_DECR: - msr |= 0x6ull << (63 - 45); - break; - case POWERPC_EXCP_SDOOR: - msr |= 0x5ull << (63 - 45); - break; - case POWERPC_EXCP_SDOOR_HV: - msr |= 0x3ull << (63 - 45); - break; - case POWERPC_EXCP_HV_MAINT: - msr |= 0xaull << (63 - 45); - break; - default: - cpu_abort(cs, "Unsupported exception %d in Power Save mode\n", - excp); - } - excp = POWERPC_EXCP_RESET; - } + /* + * check for special resume at 0x100 from doze/nap/sleep/winkle on + * P7/P8/P9 + */ + if (env->resume_as_sreset) { + excp = powerpc_reset_wakeup(cs, env, excp, &msr); } /* Exception targetting modifiers * - * LPES0 is supported on POWER7/8 + * LPES0 is supported on POWER7/8/9 * LPES1 is not supported (old iSeries mode) * * On anything else, we behave as if LPES0 is 1 @@ -148,9 +161,10 @@ static inline void powerpc_excp(PowerPCCPU *cpu, int excp_model, int excp) */ #if defined(TARGET_PPC64) if (excp_model == POWERPC_EXCP_POWER7 || - excp_model == POWERPC_EXCP_POWER8) { + excp_model == POWERPC_EXCP_POWER8 || + excp_model == POWERPC_EXCP_POWER9) { lpes0 = !!(env->spr[SPR_LPCR] & LPCR_LPES0); - if (excp_model == POWERPC_EXCP_POWER8) { + if (excp_model != POWERPC_EXCP_POWER7) { ail = (env->spr[SPR_LPCR] & LPCR_AIL) >> LPCR_AIL_SHIFT; } else { ail = 0; @@ -416,6 +430,7 @@ static inline void powerpc_excp(PowerPCCPU *cpu, int excp_model, int excp) case POWERPC_EXCP_HISEG: /* Hypervisor instruction segment exception */ case POWERPC_EXCP_SDOOR_HV: /* Hypervisor Doorbell interrupt */ case POWERPC_EXCP_HV_EMU: + case POWERPC_EXCP_HVIRT: /* Hypervisor virtualization */ srr0 = SPR_HSRR0; srr1 = SPR_HSRR1; new_msr |= (target_ulong)MSR_HVB; @@ -652,7 +667,15 @@ static inline void powerpc_excp(PowerPCCPU *cpu, int excp_model, int excp) } } else if (excp_model == POWERPC_EXCP_POWER8) { if (new_msr & MSR_HVB) { - if (env->spr[SPR_HID0] & (HID0_HILE | HID0_POWER9_HILE)) { + if (env->spr[SPR_HID0] & HID0_HILE) { + new_msr |= (target_ulong)1 << MSR_LE; + } + } else if (env->spr[SPR_LPCR] & LPCR_ILE) { + new_msr |= (target_ulong)1 << MSR_LE; + } + } else if (excp_model == POWERPC_EXCP_POWER9) { + if (new_msr & MSR_HVB) { + if (env->spr[SPR_HID0] & HID0_POWER9_HILE) { new_msr |= (target_ulong)1 << MSR_LE; } } else if (env->spr[SPR_LPCR] & LPCR_ILE) { @@ -748,6 +771,7 @@ void ppc_cpu_do_interrupt(CPUState *cs) static void ppc_hw_interrupt(CPUPPCState *env) { PowerPCCPU *cpu = ppc_env_get_cpu(env); + bool async_deliver; /* External reset */ if (env->pending_interrupts & (1 << PPC_INTERRUPT_RESET)) { @@ -769,21 +793,44 @@ static void ppc_hw_interrupt(CPUPPCState *env) return; } #endif + + /* + * For interrupts that gate on MSR:EE, we need to do something a + * bit more subtle, as we need to let them through even when EE is + * clear when coming out of some power management states (in order + * for them to become a 0x100). + */ + async_deliver = (msr_ee != 0) || env->resume_as_sreset; + /* Hypervisor decrementer exception */ if (env->pending_interrupts & (1 << PPC_INTERRUPT_HDECR)) { /* LPCR will be clear when not supported so this will work */ bool hdice = !!(env->spr[SPR_LPCR] & LPCR_HDICE); - if ((msr_ee != 0 || msr_hv == 0) && hdice) { + if ((async_deliver || msr_hv == 0) && hdice) { /* HDEC clears on delivery */ env->pending_interrupts &= ~(1 << PPC_INTERRUPT_HDECR); powerpc_excp(cpu, env->excp_model, POWERPC_EXCP_HDECR); return; } } - /* Extermal interrupt can ignore MSR:EE under some circumstances */ + + /* Hypervisor virtualization interrupt */ + if (env->pending_interrupts & (1 << PPC_INTERRUPT_HVIRT)) { + /* LPCR will be clear when not supported so this will work */ + bool hvice = !!(env->spr[SPR_LPCR] & LPCR_HVICE); + if ((async_deliver || msr_hv == 0) && hvice) { + powerpc_excp(cpu, env->excp_model, POWERPC_EXCP_HVIRT); + return; + } + } + + /* External interrupt can ignore MSR:EE under some circumstances */ if (env->pending_interrupts & (1 << PPC_INTERRUPT_EXT)) { bool lpes0 = !!(env->spr[SPR_LPCR] & LPCR_LPES0); - if (msr_ee != 0 || (env->has_hv_mode && msr_hv == 0 && !lpes0)) { + bool heic = !!(env->spr[SPR_LPCR] & LPCR_HEIC); + /* HEIC blocks delivery to the hypervisor */ + if ((async_deliver && !(heic && msr_hv && !msr_pr)) || + (env->has_hv_mode && msr_hv == 0 && !lpes0)) { powerpc_excp(cpu, env->excp_model, POWERPC_EXCP_EXTERNAL); return; } @@ -795,7 +842,7 @@ static void ppc_hw_interrupt(CPUPPCState *env) return; } } - if (msr_ee != 0) { + if (async_deliver != 0) { /* Watchdog timer on embedded PowerPC */ if (env->pending_interrupts & (1 << PPC_INTERRUPT_WDT)) { env->pending_interrupts &= ~(1 << PPC_INTERRUPT_WDT); @@ -849,6 +896,22 @@ static void ppc_hw_interrupt(CPUPPCState *env) return; } } + + if (env->resume_as_sreset) { + /* + * This is a bug ! It means that has_work took us out of halt without + * anything to deliver while in a PM state that requires getting + * out via a 0x100 + * + * This means we will incorrectly execute past the power management + * instruction instead of triggering a reset. + * + * It generally means a discrepancy between the wakup conditions in the + * processor has_work implementation and the logic in this function. + */ + cpu_abort(CPU(ppc_env_get_cpu(env)), + "Wakeup from PM state but interrupt Undelivered"); + } } void ppc_cpu_do_system_reset(CPUState *cs) @@ -943,22 +1006,15 @@ void helper_pminsn(CPUPPCState *env, powerpc_pm_insn_t insn) cs = CPU(ppc_env_get_cpu(env)); cs->halted = 1; - env->in_pm_state = true; /* The architecture specifies that HDEC interrupts are * discarded in PM states */ env->pending_interrupts &= ~(1 << PPC_INTERRUPT_HDECR); - /* Technically, nap doesn't set EE, but if we don't set it - * then ppc_hw_interrupt() won't deliver. We could add some - * other tests there based on LPCR but it's simpler to just - * whack EE in. It will be cleared by the 0x100 at wakeup - * anyway. It will still be observable by the guest in SRR1 - * but this doesn't seem to be a problem. - */ - env->msr |= (1ull << MSR_EE); - raise_exception(env, EXCP_HLT); + /* Condition for waking up at 0x100 */ + env->resume_as_sreset = (insn != PPC_PM_STOP) || + (env->spr[SPR_PSSCR] & PSSCR_EC); } #endif /* defined(TARGET_PPC64) */ diff --git a/target/ppc/helper.h b/target/ppc/helper.h index 18910d18a4..638a6e99c4 100644 --- a/target/ppc/helper.h +++ b/target/ppc/helper.h @@ -689,6 +689,7 @@ DEF_HELPER_2(store_ptcr, void, env, tl) #endif DEF_HELPER_2(store_sdr1, void, env, tl) DEF_HELPER_2(store_pidr, void, env, tl) +DEF_HELPER_2(store_lpidr, void, env, tl) DEF_HELPER_FLAGS_2(store_tbl, TCG_CALL_NO_RWG, void, env, tl) DEF_HELPER_FLAGS_2(store_tbu, TCG_CALL_NO_RWG, void, env, tl) DEF_HELPER_FLAGS_2(store_atbl, TCG_CALL_NO_RWG, void, env, tl) diff --git a/target/ppc/helper_regs.h b/target/ppc/helper_regs.h index 5efd18049e..a2205e1044 100644 --- a/target/ppc/helper_regs.h +++ b/target/ppc/helper_regs.h @@ -174,26 +174,19 @@ static inline int hreg_store_msr(CPUPPCState *env, target_ulong value, static inline void check_tlb_flush(CPUPPCState *env, bool global) { CPUState *cs = CPU(ppc_env_get_cpu(env)); - if (env->tlb_need_flush & TLB_NEED_LOCAL_FLUSH) { - tlb_flush(cs); - env->tlb_need_flush &= ~TLB_NEED_LOCAL_FLUSH; - } - /* Propagate TLB invalidations to other CPUs when the guest uses broadcast - * TLB invalidation instructions. - */ + /* Handle global flushes first */ if (global && (env->tlb_need_flush & TLB_NEED_GLOBAL_FLUSH)) { - CPUState *other_cs; - CPU_FOREACH(other_cs) { - if (other_cs != cs) { - PowerPCCPU *cpu = POWERPC_CPU(other_cs); - CPUPPCState *other_env = &cpu->env; - - other_env->tlb_need_flush &= ~TLB_NEED_LOCAL_FLUSH; - tlb_flush(other_cs); - } - } env->tlb_need_flush &= ~TLB_NEED_GLOBAL_FLUSH; + env->tlb_need_flush &= ~TLB_NEED_LOCAL_FLUSH; + tlb_flush_all_cpus_synced(cs); + return; + } + + /* Then handle local ones */ + if (env->tlb_need_flush & TLB_NEED_LOCAL_FLUSH) { + env->tlb_need_flush &= ~TLB_NEED_LOCAL_FLUSH; + tlb_flush(cs); } } #else diff --git a/target/ppc/misc_helper.c b/target/ppc/misc_helper.c index b884930096..c65d1ade15 100644 --- a/target/ppc/misc_helper.c +++ b/target/ppc/misc_helper.c @@ -117,6 +117,21 @@ void helper_store_pidr(CPUPPCState *env, target_ulong val) tlb_flush(CPU(cpu)); } +void helper_store_lpidr(CPUPPCState *env, target_ulong val) +{ + PowerPCCPU *cpu = ppc_env_get_cpu(env); + + env->spr[SPR_LPIDR] = val; + + /* + * We need to flush the TLB on LPID changes as we only tag HV vs + * guest in TCG TLB. Also the quadrants means the HV will + * potentially access and cache entries for the current LPID as + * well. + */ + tlb_flush(CPU(cpu)); +} + void helper_store_hid0_601(CPUPPCState *env, target_ulong val) { target_ulong hid0; diff --git a/target/ppc/mmu-book3s-v3.c b/target/ppc/mmu-book3s-v3.c index b60df4408f..32b8c166b5 100644 --- a/target/ppc/mmu-book3s-v3.c +++ b/target/ppc/mmu-book3s-v3.c @@ -26,9 +26,36 @@ int ppc64_v3_handle_mmu_fault(PowerPCCPU *cpu, vaddr eaddr, int rwx, int mmu_idx) { - if (ppc64_radix_guest(cpu)) { /* Guest uses radix */ + if (ppc64_v3_radix(cpu)) { /* Guest uses radix */ return ppc_radix64_handle_mmu_fault(cpu, eaddr, rwx, mmu_idx); } else { /* Guest uses hash */ return ppc_hash64_handle_mmu_fault(cpu, eaddr, rwx, mmu_idx); } } + +hwaddr ppc64_v3_get_phys_page_debug(PowerPCCPU *cpu, vaddr eaddr) +{ + if (ppc64_v3_radix(cpu)) { + return ppc_radix64_get_phys_page_debug(cpu, eaddr); + } else { + return ppc_hash64_get_phys_page_debug(cpu, eaddr); + } +} + +bool ppc64_v3_get_pate(PowerPCCPU *cpu, target_ulong lpid, ppc_v3_pate_t *entry) +{ + uint64_t patb = cpu->env.spr[SPR_PTCR] & PTCR_PATB; + uint64_t pats = cpu->env.spr[SPR_PTCR] & PTCR_PATS; + + /* Calculate number of entries */ + pats = 1ull << (pats + 12 - 4); + if (pats <= lpid) { + return false; + } + + /* Grab entry */ + patb += 16 * lpid; + entry->dw0 = ldq_phys(CPU(cpu)->as, patb); + entry->dw1 = ldq_phys(CPU(cpu)->as, patb + 8); + return true; +} diff --git a/target/ppc/mmu-book3s-v3.h b/target/ppc/mmu-book3s-v3.h index fdf80987d7..ee8288e32d 100644 --- a/target/ppc/mmu-book3s-v3.h +++ b/target/ppc/mmu-book3s-v3.h @@ -17,8 +17,10 @@ * License along with this library; if not, see <http://www.gnu.org/licenses/>. */ -#ifndef MMU_H -#define MMU_H +#ifndef MMU_BOOOK3S_V3_H +#define MMU_BOOOK3S_V3_H + +#include "mmu-hash64.h" #ifndef CONFIG_USER_ONLY @@ -29,7 +31,16 @@ #define PTCR_PATS 0x000000000000001FULL /* Partition Table Size */ /* Partition Table Entry Fields */ -#define PATBE1_GR 0x8000000000000000 +#define PATE0_HR 0x8000000000000000 + +/* + * WARNING: This field doesn't actually exist in the final version of + * the architecture and is unused by hardware. However, qemu uses it + * as an indication of a radix guest in the pseudo-PATB entry that it + * maintains for SPAPR guests and in the migration stream, so we need + * to keep it around + */ +#define PATE1_GR 0x8000000000000000 /* Process Table Entry */ struct prtb_entry { @@ -43,19 +54,68 @@ static inline bool ppc64_use_proc_tbl(PowerPCCPU *cpu) return !!(cpu->env.spr[SPR_LPCR] & LPCR_UPRT); } -static inline bool ppc64_radix_guest(PowerPCCPU *cpu) -{ - PPCVirtualHypervisorClass *vhc = - PPC_VIRTUAL_HYPERVISOR_GET_CLASS(cpu->vhyp); +bool ppc64_v3_get_pate(PowerPCCPU *cpu, target_ulong lpid, + ppc_v3_pate_t *entry); - return !!(vhc->get_patbe(cpu->vhyp) & PATBE1_GR); +/* + * The LPCR:HR bit is a shortcut that avoids having to + * dig out the partition table in the fast path. This is + * also how the HW uses it. + */ +static inline bool ppc64_v3_radix(PowerPCCPU *cpu) +{ + return !!(cpu->env.spr[SPR_LPCR] & LPCR_HR); } +hwaddr ppc64_v3_get_phys_page_debug(PowerPCCPU *cpu, vaddr eaddr); + int ppc64_v3_handle_mmu_fault(PowerPCCPU *cpu, vaddr eaddr, int rwx, int mmu_idx); +static inline hwaddr ppc_hash64_hpt_base(PowerPCCPU *cpu) +{ + uint64_t base; + + if (cpu->vhyp) { + return 0; + } + if (cpu->env.mmu_model == POWERPC_MMU_3_00) { + ppc_v3_pate_t pate; + + if (!ppc64_v3_get_pate(cpu, cpu->env.spr[SPR_LPIDR], &pate)) { + return 0; + } + base = pate.dw0; + } else { + base = cpu->env.spr[SPR_SDR1]; + } + return base & SDR_64_HTABORG; +} + +static inline hwaddr ppc_hash64_hpt_mask(PowerPCCPU *cpu) +{ + uint64_t base; + + if (cpu->vhyp) { + PPCVirtualHypervisorClass *vhc = + PPC_VIRTUAL_HYPERVISOR_GET_CLASS(cpu->vhyp); + return vhc->hpt_mask(cpu->vhyp); + } + if (cpu->env.mmu_model == POWERPC_MMU_3_00) { + ppc_v3_pate_t pate; + + if (!ppc64_v3_get_pate(cpu, cpu->env.spr[SPR_LPIDR], &pate)) { + return 0; + } + base = pate.dw0; + } else { + base = cpu->env.spr[SPR_SDR1]; + } + return (1ULL << ((base & SDR_64_HTABSIZE) + 18 - 7)) - 1; +} + #endif /* TARGET_PPC64 */ #endif /* CONFIG_USER_ONLY */ -#endif /* MMU_H */ +#endif /* MMU_BOOOK3S_V3_H */ diff --git a/target/ppc/mmu-hash32.c b/target/ppc/mmu-hash32.c index 03ae3c1279..e8562a7c87 100644 --- a/target/ppc/mmu-hash32.c +++ b/target/ppc/mmu-hash32.c @@ -319,6 +319,12 @@ static hwaddr ppc_hash32_pteg_search(PowerPCCPU *cpu, hwaddr pteg_off, for (i = 0; i < HPTES_PER_GROUP; i++) { pte0 = ppc_hash32_load_hpte0(cpu, pte_offset); + /* + * pte0 contains the valid bit and must be read before pte1, + * otherwise we might see an old pte1 with a new valid bit and + * thus an inconsistent hpte value + */ + smp_rmb(); pte1 = ppc_hash32_load_hpte1(cpu, pte_offset); if ((pte0 & HPTE32_V_VALID) diff --git a/target/ppc/mmu-hash64.c b/target/ppc/mmu-hash64.c index 276d9015e7..c431303eff 100644 --- a/target/ppc/mmu-hash64.c +++ b/target/ppc/mmu-hash64.c @@ -417,7 +417,7 @@ const ppc_hash_pte64_t *ppc_hash64_map_hptes(PowerPCCPU *cpu, hwaddr ptex, int n) { hwaddr pte_offset = ptex * HASH_PTE_SIZE_64; - hwaddr base = ppc_hash64_hpt_base(cpu); + hwaddr base; hwaddr plen = n * HASH_PTE_SIZE_64; const ppc_hash_pte64_t *hptes; @@ -426,6 +426,7 @@ const ppc_hash_pte64_t *ppc_hash64_map_hptes(PowerPCCPU *cpu, PPC_VIRTUAL_HYPERVISOR_GET_CLASS(cpu->vhyp); return vhc->map_hptes(cpu->vhyp, ptex, n); } + base = ppc_hash64_hpt_base(cpu); if (!base) { return NULL; @@ -490,6 +491,18 @@ static unsigned hpte_page_shift(const PPCHash64SegmentPageSizes *sps, return 0; /* Bad page size encoding */ } +static void ppc64_v3_new_to_old_hpte(target_ulong *pte0, target_ulong *pte1) +{ + /* Insert B into pte0 */ + *pte0 = (*pte0 & HPTE64_V_COMMON_BITS) | + ((*pte1 & HPTE64_R_3_0_SSIZE_MASK) << + (HPTE64_V_SSIZE_SHIFT - HPTE64_R_3_0_SSIZE_SHIFT)); + + /* Remove B from pte1 */ + *pte1 = *pte1 & ~HPTE64_R_3_0_SSIZE_MASK; +} + + static hwaddr ppc_hash64_pteg_search(PowerPCCPU *cpu, hwaddr hash, const PPCHash64SegmentPageSizes *sps, target_ulong ptem, @@ -507,8 +520,19 @@ static hwaddr ppc_hash64_pteg_search(PowerPCCPU *cpu, hwaddr hash, } for (i = 0; i < HPTES_PER_GROUP; i++) { pte0 = ppc_hash64_hpte0(cpu, pteg, i); + /* + * pte0 contains the valid bit and must be read before pte1, + * otherwise we might see an old pte1 with a new valid bit and + * thus an inconsistent hpte value + */ + smp_rmb(); pte1 = ppc_hash64_hpte1(cpu, pteg, i); + /* Convert format if necessary */ + if (cpu->env.mmu_model == POWERPC_MMU_3_00 && !cpu->vhyp) { + ppc64_v3_new_to_old_hpte(&pte0, &pte1); + } + /* This compares V, B, H (secondary) and the AVPN */ if (HPTE64_V_COMPARE(pte0, ptem)) { *pshift = hpte_page_shift(sps, pte0, pte1); @@ -918,7 +942,7 @@ hwaddr ppc_hash64_get_phys_page_debug(PowerPCCPU *cpu, target_ulong addr) void ppc_hash64_store_hpte(PowerPCCPU *cpu, hwaddr ptex, uint64_t pte0, uint64_t pte1) { - hwaddr base = ppc_hash64_hpt_base(cpu); + hwaddr base; hwaddr offset = ptex * HASH_PTE_SIZE_64; if (cpu->vhyp) { @@ -927,6 +951,7 @@ void ppc_hash64_store_hpte(PowerPCCPU *cpu, hwaddr ptex, vhc->store_hpte(cpu->vhyp, ptex, pte0, pte1); return; } + base = ppc_hash64_hpt_base(cpu); stq_phys(CPU(cpu)->as, base + offset, pte0); stq_phys(CPU(cpu)->as, base + offset + HASH_PTE_SIZE_64 / 2, pte1); @@ -1084,10 +1109,18 @@ void ppc_store_lpcr(PowerPCCPU *cpu, target_ulong val) case POWERPC_MMU_3_00: /* P9 */ lpcr = val & (LPCR_VPM1 | LPCR_ISL | LPCR_KBV | LPCR_DPFD | (LPCR_PECE_U_MASK & LPCR_HVEE) | LPCR_ILE | LPCR_AIL | - LPCR_UPRT | LPCR_EVIRT | LPCR_ONL | + LPCR_UPRT | LPCR_EVIRT | LPCR_ONL | LPCR_HR | (LPCR_PECE_L_MASK & (LPCR_PDEE | LPCR_HDEE | LPCR_EEE | LPCR_DEE | LPCR_OEE)) | LPCR_MER | LPCR_GTSE | LPCR_TC | LPCR_HEIC | LPCR_LPES0 | LPCR_HVICE | LPCR_HDICE); + /* + * If we have a virtual hypervisor, we need to bring back RMLS. It + * doesn't exist on an actual P9 but that's all we know how to + * configure with softmmu at the moment + */ + if (cpu->vhyp) { + lpcr |= (val & LPCR_RMLS); + } break; default: ; diff --git a/target/ppc/mmu-hash64.h b/target/ppc/mmu-hash64.h index f11efc9cbc..6b555b7220 100644 --- a/target/ppc/mmu-hash64.h +++ b/target/ppc/mmu-hash64.h @@ -63,6 +63,7 @@ void ppc_hash64_filter_pagesizes(PowerPCCPU *cpu, #define SDR_64_HTABORG 0x0FFFFFFFFFFC0000ULL #define SDR_64_HTABSIZE 0x000000000000001FULL +#define PATE0_HTABORG 0x0FFFFFFFFFFC0000ULL #define HPTES_PER_GROUP 8 #define HASH_PTE_SIZE_64 16 #define HASH_PTEG_SIZE_64 (HASH_PTE_SIZE_64 * HPTES_PER_GROUP) @@ -102,23 +103,10 @@ void ppc_hash64_filter_pagesizes(PowerPCCPU *cpu, #define HPTE64_V_1TB_SEG 0x4000000000000000ULL #define HPTE64_V_VRMA_MASK 0x4001ffffff000000ULL -static inline hwaddr ppc_hash64_hpt_base(PowerPCCPU *cpu) -{ - if (cpu->vhyp) { - return 0; - } - return cpu->env.spr[SPR_SDR1] & SDR_64_HTABORG; -} - -static inline hwaddr ppc_hash64_hpt_mask(PowerPCCPU *cpu) -{ - if (cpu->vhyp) { - PPCVirtualHypervisorClass *vhc = - PPC_VIRTUAL_HYPERVISOR_GET_CLASS(cpu->vhyp); - return vhc->hpt_mask(cpu->vhyp); - } - return (1ULL << ((cpu->env.spr[SPR_SDR1] & SDR_64_HTABSIZE) + 18 - 7)) - 1; -} +/* Format changes for ARCH v3 */ +#define HPTE64_V_COMMON_BITS 0x000fffffffffffffULL +#define HPTE64_R_3_0_SSIZE_SHIFT 58 +#define HPTE64_R_3_0_SSIZE_MASK (3ULL << HPTE64_R_3_0_SSIZE_SHIFT) struct ppc_hash_pte64 { uint64_t pte0, pte1; diff --git a/target/ppc/mmu-radix64.c b/target/ppc/mmu-radix64.c index ab76cbc835..ca1fb2673f 100644 --- a/target/ppc/mmu-radix64.c +++ b/target/ppc/mmu-radix64.c @@ -31,10 +31,26 @@ static bool ppc_radix64_get_fully_qualified_addr(CPUPPCState *env, vaddr eaddr, uint64_t *lpid, uint64_t *pid) { - /* We don't have HV support yet and shouldn't get here with it set anyway */ - assert(!msr_hv); - - if (!msr_hv) { /* !MSR[HV] -> Guest */ + if (msr_hv) { /* MSR[HV] -> Hypervisor/bare metal */ + switch (eaddr & R_EADDR_QUADRANT) { + case R_EADDR_QUADRANT0: + *lpid = 0; + *pid = env->spr[SPR_BOOKS_PID]; + break; + case R_EADDR_QUADRANT1: + *lpid = env->spr[SPR_LPIDR]; + *pid = env->spr[SPR_BOOKS_PID]; + break; + case R_EADDR_QUADRANT2: + *lpid = env->spr[SPR_LPIDR]; + *pid = 0; + break; + case R_EADDR_QUADRANT3: + *lpid = 0; + *pid = 0; + break; + } + } else { /* !MSR[HV] -> Guest */ switch (eaddr & R_EADDR_QUADRANT) { case R_EADDR_QUADRANT0: /* Guest application */ *lpid = env->spr[SPR_LPIDR]; @@ -186,20 +202,32 @@ static uint64_t ppc_radix64_walk_tree(PowerPCCPU *cpu, vaddr eaddr, raddr, psize, fault_cause, pte_addr); } +static bool validate_pate(PowerPCCPU *cpu, uint64_t lpid, ppc_v3_pate_t *pate) +{ + CPUPPCState *env = &cpu->env; + + if (!(pate->dw0 & PATE0_HR)) { + return false; + } + if (lpid == 0 && !msr_hv) { + return false; + } + /* More checks ... */ + return true; +} + int ppc_radix64_handle_mmu_fault(PowerPCCPU *cpu, vaddr eaddr, int rwx, int mmu_idx) { CPUState *cs = CPU(cpu); CPUPPCState *env = &cpu->env; - PPCVirtualHypervisorClass *vhc = - PPC_VIRTUAL_HYPERVISOR_GET_CLASS(cpu->vhyp); + PPCVirtualHypervisorClass *vhc; hwaddr raddr, pte_addr; - uint64_t lpid = 0, pid = 0, offset, size, patbe, prtbe0, pte; + uint64_t lpid = 0, pid = 0, offset, size, prtbe0, pte; int page_size, prot, fault_cause = 0; + ppc_v3_pate_t pate; assert((rwx == 0) || (rwx == 1) || (rwx == 2)); - assert(!msr_hv); /* For now there is no Radix PowerNV Support */ - assert(cpu->vhyp); assert(ppc64_use_proc_tbl(cpu)); /* Real Mode Access */ @@ -220,17 +248,33 @@ int ppc_radix64_handle_mmu_fault(PowerPCCPU *cpu, vaddr eaddr, int rwx, } /* Get Process Table */ - patbe = vhc->get_patbe(cpu->vhyp); + if (cpu->vhyp) { + vhc = PPC_VIRTUAL_HYPERVISOR_GET_CLASS(cpu->vhyp); + vhc->get_pate(cpu->vhyp, &pate); + } else { + if (!ppc64_v3_get_pate(cpu, lpid, &pate)) { + ppc_radix64_raise_si(cpu, rwx, eaddr, DSISR_NOPTE); + return 1; + } + if (!validate_pate(cpu, lpid, &pate)) { + ppc_radix64_raise_si(cpu, rwx, eaddr, DSISR_R_BADCONFIG); + } + /* We don't support guest mode yet */ + if (lpid != 0) { + error_report("PowerNV guest support Unimplemented"); + exit(1); + } + } /* Index Process Table by PID to Find Corresponding Process Table Entry */ offset = pid * sizeof(struct prtb_entry); - size = 1ULL << ((patbe & PATBE1_R_PRTS) + 12); + size = 1ULL << ((pate.dw1 & PATE1_R_PRTS) + 12); if (offset >= size) { /* offset exceeds size of the process table */ ppc_radix64_raise_si(cpu, rwx, eaddr, DSISR_NOPTE); return 1; } - prtbe0 = ldq_phys(cs->as, (patbe & PATBE1_R_PRTB) + offset); + prtbe0 = ldq_phys(cs->as, (pate.dw1 & PATE1_R_PRTB) + offset); /* Walk Radix Tree from Process Table Entry to Convert EA to RA */ page_size = PRTBE_R_GET_RTS(prtbe0); @@ -255,11 +299,11 @@ hwaddr ppc_radix64_get_phys_page_debug(PowerPCCPU *cpu, target_ulong eaddr) { CPUState *cs = CPU(cpu); CPUPPCState *env = &cpu->env; - PPCVirtualHypervisorClass *vhc = - PPC_VIRTUAL_HYPERVISOR_GET_CLASS(cpu->vhyp); + PPCVirtualHypervisorClass *vhc; hwaddr raddr, pte_addr; - uint64_t lpid = 0, pid = 0, offset, size, patbe, prtbe0, pte; + uint64_t lpid = 0, pid = 0, offset, size, prtbe0, pte; int page_size, fault_cause = 0; + ppc_v3_pate_t pate; /* Handle Real Mode */ if (msr_dr == 0) { @@ -273,16 +317,31 @@ hwaddr ppc_radix64_get_phys_page_debug(PowerPCCPU *cpu, target_ulong eaddr) } /* Get Process Table */ - patbe = vhc->get_patbe(cpu->vhyp); + if (cpu->vhyp) { + vhc = PPC_VIRTUAL_HYPERVISOR_GET_CLASS(cpu->vhyp); + vhc->get_pate(cpu->vhyp, &pate); + } else { + if (!ppc64_v3_get_pate(cpu, lpid, &pate)) { + return -1; + } + if (!validate_pate(cpu, lpid, &pate)) { + return -1; + } + /* We don't support guest mode yet */ + if (lpid != 0) { + error_report("PowerNV guest support Unimplemented"); + exit(1); + } + } /* Index Process Table by PID to Find Corresponding Process Table Entry */ offset = pid * sizeof(struct prtb_entry); - size = 1ULL << ((patbe & PATBE1_R_PRTS) + 12); + size = 1ULL << ((pate.dw1 & PATE1_R_PRTS) + 12); if (offset >= size) { /* offset exceeds size of the process table */ return -1; } - prtbe0 = ldq_phys(cs->as, (patbe & PATBE1_R_PRTB) + offset); + prtbe0 = ldq_phys(cs->as, (pate.dw1 & PATE1_R_PRTB) + offset); /* Walk Radix Tree from Process Table Entry to Convert EA to RA */ page_size = PRTBE_R_GET_RTS(prtbe0); diff --git a/target/ppc/mmu-radix64.h b/target/ppc/mmu-radix64.h index 0ecf063a17..96228546aa 100644 --- a/target/ppc/mmu-radix64.h +++ b/target/ppc/mmu-radix64.h @@ -12,8 +12,8 @@ #define R_EADDR_QUADRANT3 0xC000000000000000 /* Radix Partition Table Entry Fields */ -#define PATBE1_R_PRTB 0x0FFFFFFFFFFFF000 -#define PATBE1_R_PRTS 0x000000000000001F +#define PATE1_R_PRTB 0x0FFFFFFFFFFFF000 +#define PATE1_R_PRTS 0x000000000000001F /* Radix Process Table Entry Fields */ #define PRTBE_R_GET_RTS(rts) \ diff --git a/target/ppc/mmu_helper.c b/target/ppc/mmu_helper.c index bcf19da61d..4a6be4d63b 100644 --- a/target/ppc/mmu_helper.c +++ b/target/ppc/mmu_helper.c @@ -1342,7 +1342,7 @@ void dump_mmu(FILE *f, fprintf_function cpu_fprintf, CPUPPCState *env) dump_slb(f, cpu_fprintf, ppc_env_get_cpu(env)); break; case POWERPC_MMU_3_00: - if (ppc64_radix_guest(ppc_env_get_cpu(env))) { + if (ppc64_v3_radix(ppc_env_get_cpu(env))) { /* TODO - Unsupported */ } else { dump_slb(f, cpu_fprintf, ppc_env_get_cpu(env)); @@ -1489,12 +1489,7 @@ hwaddr ppc_cpu_get_phys_page_debug(CPUState *cs, vaddr addr) case POWERPC_MMU_2_07: return ppc_hash64_get_phys_page_debug(cpu, addr); case POWERPC_MMU_3_00: - if (ppc64_radix_guest(ppc_env_get_cpu(env))) { - return ppc_radix64_get_phys_page_debug(cpu, addr); - } else { - return ppc_hash64_get_phys_page_debug(cpu, addr); - } - break; + return ppc64_v3_get_phys_page_debug(cpu, addr); #endif case POWERPC_MMU_32B: diff --git a/target/ppc/translate.c b/target/ppc/translate.c index f4d70e725a..819221f246 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -3566,7 +3566,8 @@ static void gen_doze(DisasContext *ctx) t = tcg_const_i32(PPC_PM_DOZE); gen_helper_pminsn(cpu_env, t); tcg_temp_free_i32(t); - gen_stop_exception(ctx); + /* Stop translation, as the CPU is supposed to sleep from now */ + gen_exception_nip(ctx, EXCP_HLT, ctx->base.pc_next); #endif /* defined(CONFIG_USER_ONLY) */ } @@ -3581,13 +3582,25 @@ static void gen_nap(DisasContext *ctx) t = tcg_const_i32(PPC_PM_NAP); gen_helper_pminsn(cpu_env, t); tcg_temp_free_i32(t); - gen_stop_exception(ctx); + /* Stop translation, as the CPU is supposed to sleep from now */ + gen_exception_nip(ctx, EXCP_HLT, ctx->base.pc_next); #endif /* defined(CONFIG_USER_ONLY) */ } static void gen_stop(DisasContext *ctx) { - gen_nap(ctx); +#if defined(CONFIG_USER_ONLY) + GEN_PRIV; +#else + TCGv_i32 t; + + CHK_HV; + t = tcg_const_i32(PPC_PM_STOP); + gen_helper_pminsn(cpu_env, t); + tcg_temp_free_i32(t); + /* Stop translation, as the CPU is supposed to sleep from now */ + gen_exception_nip(ctx, EXCP_HLT, ctx->base.pc_next); +#endif /* defined(CONFIG_USER_ONLY) */ } static void gen_sleep(DisasContext *ctx) @@ -3601,7 +3614,8 @@ static void gen_sleep(DisasContext *ctx) t = tcg_const_i32(PPC_PM_SLEEP); gen_helper_pminsn(cpu_env, t); tcg_temp_free_i32(t); - gen_stop_exception(ctx); + /* Stop translation, as the CPU is supposed to sleep from now */ + gen_exception_nip(ctx, EXCP_HLT, ctx->base.pc_next); #endif /* defined(CONFIG_USER_ONLY) */ } @@ -3616,7 +3630,8 @@ static void gen_rvwinkle(DisasContext *ctx) t = tcg_const_i32(PPC_PM_RVWINKLE); gen_helper_pminsn(cpu_env, t); tcg_temp_free_i32(t); - gen_stop_exception(ctx); + /* Stop translation, as the CPU is supposed to sleep from now */ + gen_exception_nip(ctx, EXCP_HLT, ctx->base.pc_next); #endif /* defined(CONFIG_USER_ONLY) */ } #endif /* #if defined(TARGET_PPC64) */ @@ -7466,7 +7481,8 @@ void ppc_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf, #if defined(TARGET_PPC64) if (env->excp_model == POWERPC_EXCP_POWER7 || - env->excp_model == POWERPC_EXCP_POWER8) { + env->excp_model == POWERPC_EXCP_POWER8 || + env->excp_model == POWERPC_EXCP_POWER9) { cpu_fprintf(f, "HSRR0 " TARGET_FMT_lx " HSRR1 " TARGET_FMT_lx "\n", env->spr[SPR_HSRR0], env->spr[SPR_HSRR1]); } diff --git a/target/ppc/translate_init.inc.c b/target/ppc/translate_init.inc.c index d884906004..58542c0fe0 100644 --- a/target/ppc/translate_init.inc.c +++ b/target/ppc/translate_init.inc.c @@ -408,6 +408,11 @@ static void spr_write_pidr(DisasContext *ctx, int sprn, int gprn) gen_helper_store_pidr(cpu_env, cpu_gpr[gprn]); } +static void spr_write_lpidr(DisasContext *ctx, int sprn, int gprn) +{ + gen_helper_store_lpidr(cpu_env, cpu_gpr[gprn]); +} + static void spr_read_hior(DisasContext *ctx, int gprn, int sprn) { tcg_gen_ld_tl(cpu_gpr[gprn], cpu_env, offsetof(CPUPPCState, excp_prefix)); @@ -3313,6 +3318,15 @@ static void init_excp_POWER8(CPUPPCState *env) #endif } +static void init_excp_POWER9(CPUPPCState *env) +{ + init_excp_POWER8(env); + +#if !defined(CONFIG_USER_ONLY) + env->excp_vectors[POWERPC_EXCP_HVIRT] = 0x00000EA0; +#endif +} + #endif /*****************************************************************************/ @@ -7876,7 +7890,7 @@ static void gen_spr_book3s_ids(CPUPPCState *env) spr_register_hv(env, SPR_LPIDR, "LPIDR", SPR_NOACCESS, SPR_NOACCESS, SPR_NOACCESS, SPR_NOACCESS, - &spr_read_generic, &spr_write_generic, + &spr_read_generic, &spr_write_lpidr, 0x00000000); spr_register_hv(env, SPR_HFSCR, "HFSCR", SPR_NOACCESS, SPR_NOACCESS, @@ -8783,8 +8797,8 @@ static void init_proc_POWER9(CPUPPCState *env) env->icache_line_size = 128; /* Allocate hardware IRQ controller */ - init_excp_POWER8(env); - ppcPOWER7_irq_init(ppc_env_get_cpu(env)); + init_excp_POWER9(env); + ppcPOWER9_irq_init(ppc_env_get_cpu(env)); } static bool ppc_pvr_match_power9(PowerPCCPUClass *pcc, uint32_t pvr) @@ -8801,13 +8815,23 @@ static bool cpu_has_work_POWER9(CPUState *cs) CPUPPCState *env = &cpu->env; if (cs->halted) { + uint64_t psscr = env->spr[SPR_PSSCR]; + if (!(cs->interrupt_request & CPU_INTERRUPT_HARD)) { return false; } + + /* If EC is clear, just return true on any pending interrupt */ + if (!(psscr & PSSCR_EC)) { + return true; + } /* External Exception */ if ((env->pending_interrupts & (1u << PPC_INTERRUPT_EXT)) && (env->spr[SPR_LPCR] & LPCR_EEE)) { - return true; + bool heic = !!(env->spr[SPR_LPCR] & LPCR_HEIC); + if (heic == 0 || !msr_hv || msr_pr) { + return true; + } } /* Decrementer Exception */ if ((env->pending_interrupts & (1u << PPC_INTERRUPT_DECR)) && @@ -8829,6 +8853,11 @@ static bool cpu_has_work_POWER9(CPUState *cs) (env->spr[SPR_LPCR] & LPCR_HDEE)) { return true; } + /* Hypervisor virtualization exception */ + if ((env->pending_interrupts & (1u << PPC_INTERRUPT_HVIRT)) && + (env->spr[SPR_LPCR] & LPCR_HVEE)) { + return true; + } if (env->pending_interrupts & (1u << PPC_INTERRUPT_RESET)) { return true; } @@ -8898,8 +8927,8 @@ POWERPC_FAMILY(POWER9)(ObjectClass *oc, void *data) pcc->hash64_opts = &ppc_hash64_opts_POWER7; pcc->radix_page_info = &POWER9_radix_page_info; #endif - pcc->excp_model = POWERPC_EXCP_POWER8; - pcc->bus_model = PPC_FLAGS_INPUT_POWER7; + pcc->excp_model = POWERPC_EXCP_POWER9; + pcc->bus_model = PPC_FLAGS_INPUT_POWER9; pcc->bfd_mach = bfd_mach_ppc64; pcc->flags = POWERPC_FLAG_VRE | POWERPC_FLAG_SE | POWERPC_FLAG_BE | POWERPC_FLAG_PMM | diff --git a/tests/Makefile.include b/tests/Makefile.include index 370de59974..c28502f7c6 100644 --- a/tests/Makefile.include +++ b/tests/Makefile.include @@ -198,6 +198,7 @@ check-qtest-i386-$(CONFIG_ISA_IPMI_KCS) += tests/ipmi-kcs-test$(EXESUF) # check-qtest-i386-$(CONFIG_ISA_IPMI_BT) += tests/ipmi-bt-test$(EXESUF) check-qtest-i386-y += tests/i440fx-test$(EXESUF) check-qtest-i386-y += tests/fw_cfg-test$(EXESUF) +check-qtest-i386-y += tests/device-plug-test$(EXESUF) check-qtest-i386-y += tests/drive_del-test$(EXESUF) check-qtest-i386-$(CONFIG_WDT_IB700) += tests/wdt_ib700-test$(EXESUF) check-qtest-i386-y += tests/tco-test$(EXESUF) @@ -262,6 +263,7 @@ check-qtest-ppc-$(CONFIG_M48T59) += tests/m48t59-test$(EXESUF) check-qtest-ppc64-y += $(check-qtest-ppc-y) check-qtest-ppc64-$(CONFIG_PSERIES) += tests/spapr-phb-test$(EXESUF) +check-qtest-ppc64-$(CONFIG_PSERIES) += tests/device-plug-test$(EXESUF) check-qtest-ppc64-$(CONFIG_POWERNV) += tests/pnv-xscom-test$(EXESUF) check-qtest-ppc64-y += tests/migration-test$(EXESUF) check-qtest-ppc64-$(CONFIG_PSERIES) += tests/rtas-test$(EXESUF) @@ -316,6 +318,7 @@ check-qtest-s390x-$(CONFIG_SLIRP) += tests/test-netfilter$(EXESUF) check-qtest-s390x-$(CONFIG_POSIX) += tests/test-filter-mirror$(EXESUF) check-qtest-s390x-$(CONFIG_POSIX) += tests/test-filter-redirector$(EXESUF) check-qtest-s390x-y += tests/drive_del-test$(EXESUF) +check-qtest-s390x-y += tests/device-plug-test$(EXESUF) check-qtest-s390x-y += tests/virtio-ccw-test$(EXESUF) check-qtest-s390x-y += tests/cpu-plug-test$(EXESUF) check-qtest-s390x-y += tests/migration-test$(EXESUF) @@ -764,6 +767,7 @@ tests/ipoctal232-test$(EXESUF): tests/ipoctal232-test.o tests/qom-test$(EXESUF): tests/qom-test.o tests/test-hmp$(EXESUF): tests/test-hmp.o tests/machine-none-test$(EXESUF): tests/machine-none-test.o +tests/device-plug-test$(EXESUF): tests/device-plug-test.o tests/drive_del-test$(EXESUF): tests/drive_del-test.o $(libqos-virtio-obj-y) tests/nvme-test$(EXESUF): tests/nvme-test.o $(libqos-pc-obj-y) tests/pvpanic-test$(EXESUF): tests/pvpanic-test.o diff --git a/tests/device-plug-test.c b/tests/device-plug-test.c new file mode 100644 index 0000000000..318e422d51 --- /dev/null +++ b/tests/device-plug-test.c @@ -0,0 +1,178 @@ +/* + * QEMU device plug/unplug handling + * + * Copyright (C) 2019 Red Hat Inc. + * + * Authors: + * David Hildenbrand <david@redhat.com> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "libqtest.h" +#include "qapi/qmp/qdict.h" +#include "qapi/qmp/qstring.h" + +static void device_del_start(QTestState *qtest, const char *id) +{ + qtest_qmp_send(qtest, + "{'execute': 'device_del', 'arguments': { 'id': %s } }", id); +} + +static void device_del_finish(QTestState *qtest) +{ + QDict *resp = qtest_qmp_receive(qtest); + + g_assert(qdict_haskey(resp, "return")); + qobject_unref(resp); +} + +static void device_del_request(QTestState *qtest, const char *id) +{ + device_del_start(qtest, id); + device_del_finish(qtest); +} + +static void system_reset(QTestState *qtest) +{ + QDict *resp; + + resp = qtest_qmp(qtest, "{'execute': 'system_reset'}"); + g_assert(qdict_haskey(resp, "return")); + qobject_unref(resp); +} + +static void wait_device_deleted_event(QTestState *qtest, const char *id) +{ + QDict *resp, *data; + QString *qstr; + + /* + * Other devices might get removed along with the removed device. Skip + * these. The device of interest will be the last one. + */ + for (;;) { + resp = qtest_qmp_eventwait_ref(qtest, "DEVICE_DELETED"); + data = qdict_get_qdict(resp, "data"); + if (!data || !qdict_get(data, "device")) { + qobject_unref(resp); + continue; + } + qstr = qobject_to(QString, qdict_get(data, "device")); + g_assert(qstr); + if (!strcmp(qstring_get_str(qstr), id)) { + qobject_unref(resp); + break; + } + qobject_unref(resp); + } +} + +static void test_pci_unplug_request(void) +{ + QTestState *qtest = qtest_initf("-device virtio-mouse-pci,id=dev0"); + + /* + * Request device removal. As the guest is not running, the request won't + * be processed. However during system reset, the removal will be + * handled, removing the device. + */ + device_del_request(qtest, "dev0"); + system_reset(qtest); + wait_device_deleted_event(qtest, "dev0"); + + qtest_quit(qtest); +} + +static void test_ccw_unplug(void) +{ + QTestState *qtest = qtest_initf("-device virtio-balloon-ccw,id=dev0"); + + /* + * The DEVICE_DELETED events will be sent before the command + * completes. + */ + device_del_start(qtest, "dev0"); + wait_device_deleted_event(qtest, "dev0"); + device_del_finish(qtest); + + qtest_quit(qtest); +} + +static void test_spapr_cpu_unplug_request(void) +{ + QTestState *qtest; + + qtest = qtest_initf("-cpu power9_v2.0 -smp 1,maxcpus=2 " + "-device power9_v2.0-spapr-cpu-core,core-id=1,id=dev0"); + + /* similar to test_pci_unplug_request */ + device_del_request(qtest, "dev0"); + system_reset(qtest); + wait_device_deleted_event(qtest, "dev0"); + + qtest_quit(qtest); +} + +static void test_spapr_memory_unplug_request(void) +{ + QTestState *qtest; + + qtest = qtest_initf("-m 256M,slots=1,maxmem=768M " + "-object memory-backend-ram,id=mem0,size=512M " + "-device pc-dimm,id=dev0,memdev=mem0"); + + /* similar to test_pci_unplug_request */ + device_del_request(qtest, "dev0"); + system_reset(qtest); + wait_device_deleted_event(qtest, "dev0"); + + qtest_quit(qtest); +} + +static void test_spapr_phb_unplug_request(void) +{ + QTestState *qtest; + + qtest = qtest_initf("-device spapr-pci-host-bridge,index=1,id=dev0"); + + /* similar to test_pci_unplug_request */ + device_del_request(qtest, "dev0"); + system_reset(qtest); + wait_device_deleted_event(qtest, "dev0"); + + qtest_quit(qtest); +} + +int main(int argc, char **argv) +{ + const char *arch = qtest_get_arch(); + + g_test_init(&argc, &argv, NULL); + + /* + * We need a system that will process unplug requests during system resets + * and does not do PCI surprise removal. This holds for x86 ACPI, + * s390x and spapr. + */ + qtest_add_func("/device-plug/pci-unplug-request", + test_pci_unplug_request); + + if (!strcmp(arch, "s390x")) { + qtest_add_func("/device-plug/ccw-unplug", + test_ccw_unplug); + } + + if (!strcmp(arch, "ppc64")) { + qtest_add_func("/device-plug/spapr-cpu-unplug-request", + test_spapr_cpu_unplug_request); + qtest_add_func("/device-plug/spapr-memory-unplug-request", + test_spapr_memory_unplug_request); + qtest_add_func("/device-plug/spapr-phb-unplug-request", + test_spapr_phb_unplug_request); + } + + return g_test_run(); +} |