diff options
83 files changed, 1084 insertions, 874 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 24b70169bc..459e3594e1 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -909,7 +909,7 @@ X86 Machines ------------ PC M: Michael S. Tsirkin <mst@redhat.com> -M: Marcel Apfelbaum <marcel@redhat.com> +M: Marcel Apfelbaum <marcel.apfelbaum@gmail.com> S: Supported F: include/hw/i386/ F: hw/i386/ @@ -959,7 +959,7 @@ F: include/hw/timer/mc146818rtc* Machine core M: Eduardo Habkost <ehabkost@redhat.com> -M: Marcel Apfelbaum <marcel@redhat.com> +M: Marcel Apfelbaum <marcel.apfelbaum@gmail.com> S: Supported F: hw/core/machine.c F: hw/core/null-machine.c @@ -1033,7 +1033,7 @@ F: hw/ipack/ PCI M: Michael S. Tsirkin <mst@redhat.com> -M: Marcel Apfelbaum <marcel@redhat.com> +M: Marcel Apfelbaum <marcel.apfelbaum@gmail.com> S: Supported F: include/hw/pci/* F: hw/misc/pci-testdev.c @@ -2075,7 +2075,7 @@ F: docs/block-replication.txt PVRDMA M: Yuval Shaia <yuval.shaia@oracle.com> -M: Marcel Apfelbaum <marcel@redhat.com> +M: Marcel Apfelbaum <marcel.apfelbaum@gmail.com> S: Maintained F: hw/rdma/* F: hw/rdma/vmw/* diff --git a/hw/misc/macio/macio.c b/hw/misc/macio/macio.c index dac7bcd15e..79621eb879 100644 --- a/hw/misc/macio/macio.c +++ b/hw/misc/macio/macio.c @@ -279,11 +279,10 @@ static void macio_newworld_realize(PCIDevice *d, Error **errp) { MacIOState *s = MACIO(d); NewWorldMacIOState *ns = NEWWORLD_MACIO(d); + DeviceState *pic_dev = DEVICE(ns->pic); Error *err = NULL; SysBusDevice *sysbus_dev; MemoryRegion *timer_memory = NULL; - int i; - int cur_irq = 0; macio_common_realize(d, &err); if (err) { @@ -292,11 +291,14 @@ static void macio_newworld_realize(PCIDevice *d, Error **errp) } sysbus_dev = SYS_BUS_DEVICE(&s->cuda); - sysbus_connect_irq(sysbus_dev, 0, ns->irqs[cur_irq++]); + sysbus_connect_irq(sysbus_dev, 0, qdev_get_gpio_in(pic_dev, + NEWWORLD_CUDA_IRQ)); sysbus_dev = SYS_BUS_DEVICE(&s->escc); - sysbus_connect_irq(sysbus_dev, 0, ns->irqs[cur_irq++]); - sysbus_connect_irq(sysbus_dev, 1, ns->irqs[cur_irq++]); + sysbus_connect_irq(sysbus_dev, 0, qdev_get_gpio_in(pic_dev, + NEWWORLD_ESCCB_IRQ)); + sysbus_connect_irq(sysbus_dev, 1, qdev_get_gpio_in(pic_dev, + NEWWORLD_ESCCA_IRQ)); /* OpenPIC */ sysbus_dev = SYS_BUS_DEVICE(ns->pic); @@ -304,15 +306,22 @@ static void macio_newworld_realize(PCIDevice *d, Error **errp) sysbus_mmio_get_region(sysbus_dev, 0)); /* IDE buses */ - for (i = 0; i < ARRAY_SIZE(ns->ide); i++) { - qemu_irq irq0 = ns->irqs[cur_irq++]; - qemu_irq irq1 = ns->irqs[cur_irq++]; - - macio_realize_ide(s, &ns->ide[i], irq0, irq1, 0x16 + (i * 4), &err); - if (err) { - error_propagate(errp, err); - return; - } + macio_realize_ide(s, &ns->ide[0], + qdev_get_gpio_in(pic_dev, NEWWORLD_IDE0_IRQ), + qdev_get_gpio_in(pic_dev, NEWWORLD_IDE0_DMA_IRQ), + 0x16, &err); + if (err) { + error_propagate(errp, err); + return; + } + + macio_realize_ide(s, &ns->ide[1], + qdev_get_gpio_in(pic_dev, NEWWORLD_IDE1_IRQ), + qdev_get_gpio_in(pic_dev, NEWWORLD_IDE1_DMA_IRQ), + 0x1a, &err); + if (err) { + error_propagate(errp, err); + return; } /* Timer */ @@ -328,8 +337,6 @@ static void macio_newworld_init(Object *obj) NewWorldMacIOState *ns = NEWWORLD_MACIO(obj); int i; - qdev_init_gpio_out(DEVICE(obj), ns->irqs, ARRAY_SIZE(ns->irqs)); - object_property_add_link(obj, "pic", TYPE_OPENPIC, (Object **) &ns->pic, qdev_prop_allow_set_link_before_realize, diff --git a/hw/pci-host/trace-events b/hw/pci-host/trace-events index 341a87a702..dd7a398e96 100644 --- a/hw/pci-host/trace-events +++ b/hw/pci-host/trace-events @@ -18,3 +18,5 @@ unin_set_irq(int irq_num, int level) "setting INT %d = %d" unin_get_config_reg(uint32_t reg, uint32_t addr, uint32_t retval) "converted config space accessor 0x%"PRIx32 "/0x%"PRIx32 " -> 0x%"PRIx32 unin_data_write(uint64_t addr, unsigned len, uint64_t val) "write addr 0x%"PRIx64 " len %d val 0x%"PRIx64 unin_data_read(uint64_t addr, unsigned len, uint64_t val) "read addr 0x%"PRIx64 " len %d val 0x%"PRIx64 +unin_write(uint64_t addr, uint64_t value) "addr=0x%" PRIx64 " val=0x%"PRIx64 +unin_read(uint64_t addr, uint64_t value) "addr=0x%" PRIx64 " val=0x%"PRIx64 diff --git a/hw/pci-host/uninorth.c b/hw/pci-host/uninorth.c index fada0ffd5f..ba76b84dbc 100644 --- a/hw/pci-host/uninorth.c +++ b/hw/pci-host/uninorth.c @@ -519,6 +519,62 @@ static const TypeInfo pci_unin_internal_info = { .class_init = pci_unin_internal_class_init, }; +/* UniN device */ +static void unin_write(void *opaque, hwaddr addr, uint64_t value, + unsigned size) +{ + trace_unin_write(addr, value); + if (addr == 0x0) { + *(int *)opaque = value; + } +} + +static uint64_t unin_read(void *opaque, hwaddr addr, unsigned size) +{ + uint32_t value; + + value = 0; + switch (addr) { + case 0: + value = *(int *)opaque; + } + + trace_unin_read(addr, value); + + return value; +} + +static const MemoryRegionOps unin_ops = { + .read = unin_read, + .write = unin_write, + .endianness = DEVICE_BIG_ENDIAN, +}; + +static void unin_init(Object *obj) +{ + UNINState *s = UNI_NORTH(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + + memory_region_init_io(&s->mem, obj, &unin_ops, &s->token, "unin", 0x1000); + + sysbus_init_mmio(sbd, &s->mem); +} + +static void unin_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + set_bit(DEVICE_CATEGORY_BRIDGE, dc->categories); +} + +static const TypeInfo unin_info = { + .name = TYPE_UNI_NORTH, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(UNINState), + .instance_init = unin_init, + .class_init = unin_class_init, +}; + static void unin_register_types(void) { type_register_static(&unin_main_pci_host_info); @@ -530,6 +586,8 @@ static void unin_register_types(void) type_register_static(&pci_u3_agp_info); type_register_static(&pci_unin_agp_info); type_register_static(&pci_unin_internal_info); + + type_register_static(&unin_info); } type_init(unin_register_types) diff --git a/hw/ppc/mac.h b/hw/ppc/mac.h index 892dd03789..22a7efbed6 100644 --- a/hw/ppc/mac.h +++ b/hw/ppc/mac.h @@ -56,6 +56,15 @@ #define OLDWORLD_IDE1_IRQ 0xe #define OLDWORLD_IDE1_DMA_IRQ 0x3 +/* New World IRQs */ +#define NEWWORLD_CUDA_IRQ 0x19 +#define NEWWORLD_ESCCB_IRQ 0x24 +#define NEWWORLD_ESCCA_IRQ 0x25 +#define NEWWORLD_IDE0_IRQ 0xd +#define NEWWORLD_IDE0_DMA_IRQ 0x2 +#define NEWWORLD_IDE1_IRQ 0xe +#define NEWWORLD_IDE1_DMA_IRQ 0x3 + /* MacIO */ #define TYPE_MACIO_IDE "macio-ide" #define MACIO_IDE(obj) OBJECT_CHECK(MACIOIDEState, (obj), TYPE_MACIO_IDE) diff --git a/hw/ppc/mac_newworld.c b/hw/ppc/mac_newworld.c index 29bd3838bf..744acdfd2e 100644 --- a/hw/ppc/mac_newworld.c +++ b/hw/ppc/mac_newworld.c @@ -82,36 +82,6 @@ #define NDRV_VGA_FILENAME "qemu_vga.ndrv" -/* UniN device */ -static void unin_write(void *opaque, hwaddr addr, uint64_t value, - unsigned size) -{ - trace_mac99_uninorth_write(addr, value); - if (addr == 0x0) { - *(int*)opaque = value; - } -} - -static uint64_t unin_read(void *opaque, hwaddr addr, unsigned size) -{ - uint32_t value; - - value = 0; - switch (addr) { - case 0: - value = *(int*)opaque; - } - - trace_mac99_uninorth_read(addr, value); - - return value; -} - -static const MemoryRegionOps unin_ops = { - .read = unin_read, - .write = unin_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; static void fw_cfg_boot_set(void *opaque, const char *boot_device, Error **errp) @@ -144,8 +114,7 @@ static void ppc_core99_init(MachineState *machine) PowerPCCPU *cpu = NULL; CPUPPCState *env = NULL; char *filename; - qemu_irq *pic, **openpic_irqs; - MemoryRegion *unin_memory = g_new(MemoryRegion, 1); + qemu_irq **openpic_irqs; int linux_boot, i, j, k; MemoryRegion *ram = g_new(MemoryRegion, 1), *bios = g_new(MemoryRegion, 1); hwaddr kernel_base, initrd_base, cmdline_base = 0; @@ -164,7 +133,6 @@ static void ppc_core99_init(MachineState *machine) int machine_arch; SysBusDevice *s; DeviceState *dev, *pic_dev; - int *token = g_new(int, 1); hwaddr nvram_addr = 0xFFF04000; uint64_t tbfreq; @@ -272,9 +240,12 @@ static void ppc_core99_init(MachineState *machine) } } - /* UniN init: XXX should be a real device */ - memory_region_init_io(unin_memory, NULL, &unin_ops, token, "unin", 0x1000); - memory_region_add_subregion(get_system_memory(), 0xf8000000, unin_memory); + /* UniN init */ + dev = qdev_create(NULL, TYPE_UNI_NORTH); + qdev_init_nofail(dev); + s = SYS_BUS_DEVICE(dev); + memory_region_add_subregion(get_system_memory(), 0xf8000000, + sysbus_mmio_get_region(s, 0)); openpic_irqs = g_malloc0(smp_cpus * sizeof(qemu_irq *)); openpic_irqs[0] = @@ -320,8 +291,6 @@ static void ppc_core99_init(MachineState *machine) } } - pic = g_new0(qemu_irq, 64); - pic_dev = qdev_create(NULL, TYPE_OPENPIC); qdev_prop_set_uint32(pic_dev, "model", OPENPIC_MODEL_KEYLARGO); qdev_init_nofail(pic_dev); @@ -333,10 +302,6 @@ static void ppc_core99_init(MachineState *machine) } } - for (i = 0; i < 64; i++) { - pic[i] = qdev_get_gpio_in(pic_dev, i); - } - if (PPC_INPUT(env) == PPC_FLAGS_INPUT_970) { /* 970 gets a U3 bus */ /* Uninorth AGP bus */ @@ -410,13 +375,6 @@ static void ppc_core99_init(MachineState *machine) /* MacIO */ macio = NEWWORLD_MACIO(pci_create(pci_bus, -1, TYPE_NEWWORLD_MACIO)); dev = DEVICE(macio); - qdev_connect_gpio_out(dev, 0, pic[0x19]); /* CUDA */ - qdev_connect_gpio_out(dev, 1, pic[0x24]); /* ESCC-B */ - qdev_connect_gpio_out(dev, 2, pic[0x25]); /* ESCC-A */ - qdev_connect_gpio_out(dev, 3, pic[0x0d]); /* IDE */ - qdev_connect_gpio_out(dev, 4, pic[0x02]); /* IDE DMA */ - qdev_connect_gpio_out(dev, 5, pic[0x0e]); /* IDE */ - qdev_connect_gpio_out(dev, 6, pic[0x03]); /* IDE DMA */ qdev_prop_set_uint64(dev, "frequency", tbfreq); object_property_set_link(OBJECT(macio), OBJECT(pic_dev), "pic", &error_abort); diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index b35aff5d81..32ab3c43b6 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -1668,10 +1668,8 @@ static void spapr_machine_reset(void) g_free(fdt); /* Set up the entry state */ - first_ppc_cpu->env.gpr[3] = fdt_addr; + spapr_cpu_set_entry_state(first_ppc_cpu, SPAPR_ENTRY_POINT, fdt_addr); first_ppc_cpu->env.gpr[5] = 0; - first_cpu->halted = 0; - first_ppc_cpu->env.nip = SPAPR_ENTRY_POINT; spapr->cas_reboot = false; } @@ -1851,10 +1849,12 @@ static bool spapr_ov5_cas_needed(void *opaque) * * Thus, for any cases where the set of available CAS-negotiatable * options extends beyond OV5_FORM1_AFFINITY and OV5_DRCONF_MEMORY, we - * include the CAS-negotiated options in the migration stream. + * include the CAS-negotiated options in the migration stream, unless + * if they affect boot time behaviour only. */ spapr_ovec_set(ov5_mask, OV5_FORM1_AFFINITY); spapr_ovec_set(ov5_mask, OV5_DRCONF_MEMORY); + spapr_ovec_set(ov5_mask, OV5_DRMEM_V2); /* spapr_ovec_diff returns true if bits were removed. we avoid using * the mask itself since in the future it's possible "legacy" bits may be @@ -2508,13 +2508,11 @@ static void spapr_machine_init(MachineState *machine) int i; MemoryRegion *sysmem = get_system_memory(); MemoryRegion *ram = g_new(MemoryRegion, 1); - MemoryRegion *rma_region; - void *rma = NULL; - hwaddr rma_alloc_size; hwaddr node0_size = spapr_node0_size(machine); long load_limit, fw_size; char *filename; Error *resize_hpt_err = NULL; + PowerPCCPU *first_ppc_cpu; msi_nonbroken = true; @@ -2549,40 +2547,28 @@ static void spapr_machine_init(MachineState *machine) exit(1); } - /* Allocate RMA if necessary */ - rma_alloc_size = kvmppc_alloc_rma(&rma); + spapr->rma_size = node0_size; - if (rma_alloc_size == -1) { - error_report("Unable to create RMA"); - exit(1); + /* With KVM, we don't actually know whether KVM supports an + * unbounded RMA (PR KVM) or is limited by the hash table size + * (HV KVM using VRMA), so we always assume the latter + * + * In that case, we also limit the initial allocations for RTAS + * etc... to 256M since we have no way to know what the VRMA size + * is going to be as it depends on the size of the hash table + * which isn't determined yet. + */ + if (kvm_enabled()) { + spapr->vrma_adjust = 1; + spapr->rma_size = MIN(spapr->rma_size, 0x10000000); } - if (rma_alloc_size && (rma_alloc_size < node0_size)) { - spapr->rma_size = rma_alloc_size; - } else { - spapr->rma_size = node0_size; - - /* With KVM, we don't actually know whether KVM supports an - * unbounded RMA (PR KVM) or is limited by the hash table size - * (HV KVM using VRMA), so we always assume the latter - * - * In that case, we also limit the initial allocations for RTAS - * etc... to 256M since we have no way to know what the VRMA size - * is going to be as it depends on the size of the hash table - * isn't determined yet. - */ - if (kvm_enabled()) { - spapr->vrma_adjust = 1; - spapr->rma_size = MIN(spapr->rma_size, 0x10000000); - } - - /* Actually we don't support unbounded RMA anymore since we - * added proper emulation of HV mode. The max we can get is - * 16G which also happens to be what we configure for PAPR - * mode so make sure we don't do anything bigger than that - */ - spapr->rma_size = MIN(spapr->rma_size, 0x400000000ull); - } + /* Actually we don't support unbounded RMA anymore since we added + * proper emulation of HV mode. The max we can get is 16G which + * also happens to be what we configure for PAPR mode so make sure + * we don't do anything bigger than that + */ + spapr->rma_size = MIN(spapr->rma_size, 0x400000000ull); if (spapr->rma_size > node0_size) { error_report("Numa node 0 has to span the RMA (%#08"HWADDR_PRIx")", @@ -2607,11 +2593,6 @@ static void spapr_machine_init(MachineState *machine) } spapr_ovec_set(spapr->ov5, OV5_FORM1_AFFINITY); - if (!kvm_enabled() || kvmppc_has_cap_mmu_radix()) { - /* KVM and TCG always allow GTSE with radix... */ - spapr_ovec_set(spapr->ov5, OV5_MMU_RADIX_GTSE); - } - /* ... but not with hash (currently). */ /* advertise support for dedicated HP event source to guests */ if (spapr->use_hotplug_event_source) { @@ -2629,6 +2610,15 @@ static void spapr_machine_init(MachineState *machine) /* init CPUs */ spapr_init_cpus(spapr); + first_ppc_cpu = POWERPC_CPU(first_cpu); + if ((!kvm_enabled() || kvmppc_has_cap_mmu_radix()) && + ppc_check_compat(first_ppc_cpu, CPU_POWERPC_LOGICAL_3_00, 0, + spapr->max_compat_pvr)) { + /* KVM and TCG always allow GTSE with radix... */ + spapr_ovec_set(spapr->ov5, OV5_MMU_RADIX_GTSE); + } + /* ... but not with hash (currently). */ + if (kvm_enabled()) { /* Enable H_LOGICAL_CI_* so SLOF can talk to in-kernel devices */ kvmppc_enable_logical_ci_hcalls(); @@ -2643,14 +2633,6 @@ static void spapr_machine_init(MachineState *machine) machine->ram_size); memory_region_add_subregion(sysmem, 0, ram); - if (rma_alloc_size && rma) { - rma_region = g_new(MemoryRegion, 1); - memory_region_init_ram_ptr(rma_region, NULL, "ppc_spapr.rma", - rma_alloc_size, rma); - vmstate_register_ram_global(rma_region); - memory_region_add_subregion(sysmem, 0, rma_region); - } - /* initialize hotplug memory address space */ if (machine->ram_size < machine->maxram_size) { ram_addr_t hotplug_mem_size = machine->maxram_size - machine->ram_size; diff --git a/hw/ppc/spapr_cpu_core.c b/hw/ppc/spapr_cpu_core.c index 01dbc69424..f3e9b879b2 100644 --- a/hw/ppc/spapr_cpu_core.c +++ b/hw/ppc/spapr_cpu_core.c @@ -28,6 +28,7 @@ static void spapr_cpu_reset(void *opaque) CPUState *cs = CPU(cpu); CPUPPCState *env = &cpu->env; PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu); + target_ulong lpcr; cpu_reset(cs); @@ -43,13 +44,43 @@ static void spapr_cpu_reset(void *opaque) env->spr[SPR_HIOR] = 0; - /* Disable Power-saving mode Exit Cause exceptions for the CPU. - * This can cause issues when rebooting the guest if a secondary - * is awaken */ - if (cs != first_cpu) { - env->spr[SPR_LPCR] &= ~pcc->lpcr_pm; - } + lpcr = env->spr[SPR_LPCR]; + + /* Set emulated LPCR to not send interrupts to hypervisor. Note that + * under KVM, the actual HW LPCR will be set differently by KVM itself, + * the settings below ensure proper operations with TCG in absence of + * a real hypervisor. + * + * Clearing VPM0 will also cause us to use RMOR in mmu-hash64.c for + * real mode accesses, which thankfully defaults to 0 and isn't + * accessible in guest mode. + * + * Disable Power-saving mode Exit Cause exceptions for the CPU, so + * we don't get spurious wakups before an RTAS start-cpu call. + */ + lpcr &= ~(LPCR_VPM0 | LPCR_VPM1 | LPCR_ISL | LPCR_KBV | pcc->lpcr_pm); + lpcr |= LPCR_LPES0 | LPCR_LPES1; + + /* Set RMLS to the max (ie, 16G) */ + lpcr &= ~LPCR_RMLS; + lpcr |= 1ull << LPCR_RMLS_SHIFT; + + ppc_store_lpcr(cpu, lpcr); + + /* Set a full AMOR so guest can use the AMR as it sees fit */ + env->spr[SPR_AMOR] = 0xffffffffffffffffull; +} + +void spapr_cpu_set_entry_state(PowerPCCPU *cpu, target_ulong nip, target_ulong r3) +{ + PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu); + CPUPPCState *env = &cpu->env; + env->nip = nip; + env->gpr[3] = r3; + CPU(cpu)->halted = 0; + /* Enable Power-saving mode Exit Cause exceptions */ + ppc_store_lpcr(cpu, env->spr[SPR_LPCR] | pcc->lpcr_pm); } static void spapr_cpu_destroy(PowerPCCPU *cpu) @@ -65,8 +96,8 @@ static void spapr_cpu_init(sPAPRMachineState *spapr, PowerPCCPU *cpu, /* Set time-base frequency to 512 MHz */ cpu_ppc_tb_init(env, SPAPR_TIMEBASE_FREQ); - /* Enable PAPR mode in TCG or KVM */ - cpu_ppc_set_papr(cpu, PPC_VIRTUAL_HYPERVISOR(spapr)); + cpu_ppc_set_vhyp(cpu, PPC_VIRTUAL_HYPERVISOR(spapr)); + kvmppc_set_papr(cpu); qemu_register_reset(spapr_cpu_reset, cpu); spapr_cpu_reset(cpu); diff --git a/hw/ppc/spapr_hcall.c b/hw/ppc/spapr_hcall.c index 16bccdd5c0..ca9702e667 100644 --- a/hw/ppc/spapr_hcall.c +++ b/hw/ppc/spapr_hcall.c @@ -15,32 +15,35 @@ #include "hw/ppc/spapr_ovec.h" #include "mmu-book3s-v3.h" -struct SPRSyncState { - int spr; +struct LPCRSyncState { target_ulong value; target_ulong mask; }; -static void do_spr_sync(CPUState *cs, run_on_cpu_data arg) +static void do_lpcr_sync(CPUState *cs, run_on_cpu_data arg) { - struct SPRSyncState *s = arg.host_ptr; + struct LPCRSyncState *s = arg.host_ptr; PowerPCCPU *cpu = POWERPC_CPU(cs); CPUPPCState *env = &cpu->env; + target_ulong lpcr; cpu_synchronize_state(cs); - env->spr[s->spr] &= ~s->mask; - env->spr[s->spr] |= s->value; + lpcr = env->spr[SPR_LPCR]; + lpcr &= ~s->mask; + lpcr |= s->value; + ppc_store_lpcr(cpu, lpcr); } -static void set_spr(CPUState *cs, int spr, target_ulong value, - target_ulong mask) +static void set_all_lpcrs(target_ulong value, target_ulong mask) { - struct SPRSyncState s = { - .spr = spr, + CPUState *cs; + struct LPCRSyncState s = { .value = value, .mask = mask }; - run_on_cpu(cs, do_spr_sync, RUN_ON_CPU_HOST_PTR(&s)); + CPU_FOREACH(cs) { + run_on_cpu(cs, do_lpcr_sync, RUN_ON_CPU_HOST_PTR(&s)); + } } static bool has_spr(PowerPCCPU *cpu, int spr) @@ -1235,8 +1238,6 @@ static target_ulong h_set_mode_resource_le(PowerPCCPU *cpu, target_ulong value1, target_ulong value2) { - CPUState *cs; - if (value1) { return H_P3; } @@ -1246,16 +1247,12 @@ static target_ulong h_set_mode_resource_le(PowerPCCPU *cpu, switch (mflags) { case H_SET_MODE_ENDIAN_BIG: - CPU_FOREACH(cs) { - set_spr(cs, SPR_LPCR, 0, LPCR_ILE); - } + set_all_lpcrs(0, LPCR_ILE); spapr_pci_switch_vga(true); return H_SUCCESS; case H_SET_MODE_ENDIAN_LITTLE: - CPU_FOREACH(cs) { - set_spr(cs, SPR_LPCR, LPCR_ILE, LPCR_ILE); - } + set_all_lpcrs(LPCR_ILE, LPCR_ILE); spapr_pci_switch_vga(false); return H_SUCCESS; } @@ -1268,7 +1265,6 @@ static target_ulong h_set_mode_resource_addr_trans_mode(PowerPCCPU *cpu, target_ulong value1, target_ulong value2) { - CPUState *cs; PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu); if (!(pcc->insns_flags2 & PPC2_ISA207S)) { @@ -1285,9 +1281,7 @@ static target_ulong h_set_mode_resource_addr_trans_mode(PowerPCCPU *cpu, return H_UNSUPPORTED_FLAG; } - CPU_FOREACH(cs) { - set_spr(cs, SPR_LPCR, mflags << LPCR_AIL_SHIFT, LPCR_AIL); - } + set_all_lpcrs(mflags << LPCR_AIL_SHIFT, LPCR_AIL); return H_SUCCESS; } @@ -1364,7 +1358,6 @@ static target_ulong h_register_process_table(PowerPCCPU *cpu, target_ulong opcode, target_ulong *args) { - CPUState *cs; target_ulong flags = args[0]; target_ulong proc_tbl = args[1]; target_ulong page_size = args[2]; @@ -1422,12 +1415,9 @@ 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 */ - CPU_FOREACH(cs) { - set_spr(cs, SPR_LPCR, - ((flags & (FLAG_RADIX | FLAG_HASH_PROC_TBL)) ? LPCR_UPRT : 0) | - ((flags & FLAG_GTSE) ? LPCR_GTSE : 0), - LPCR_UPRT | LPCR_GTSE); - } + set_all_lpcrs(((flags & (FLAG_RADIX | FLAG_HASH_PROC_TBL)) ? LPCR_UPRT : 0) | + ((flags & FLAG_GTSE) ? LPCR_GTSE : 0), + LPCR_UPRT | LPCR_GTSE); if (kvm_enabled()) { return kvmppc_configure_v3_mmu(cpu, flags & FLAG_RADIX, diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c index 0ec5fa4cfe..7f9738daed 100644 --- a/hw/ppc/spapr_rtas.c +++ b/hw/ppc/spapr_rtas.c @@ -32,11 +32,12 @@ #include "hw/qdev.h" #include "sysemu/device_tree.h" #include "sysemu/cpus.h" -#include "sysemu/kvm.h" +#include "sysemu/hw_accel.h" #include "hw/ppc/spapr.h" #include "hw/ppc/spapr_vio.h" #include "hw/ppc/spapr_rtas.h" +#include "hw/ppc/spapr_cpu_core.h" #include "hw/ppc/ppc.h" #include "hw/boards.h" @@ -45,6 +46,8 @@ #include "qemu/cutils.h" #include "trace.h" #include "hw/ppc/fdt.h" +#include "target/ppc/mmu-hash64.h" +#include "target/ppc/mmu-book3s-v3.h" static void rtas_display_character(PowerPCCPU *cpu, sPAPRMachineState *spapr, uint32_t token, uint32_t nargs, @@ -119,34 +122,16 @@ static void rtas_query_cpu_stopped_state(PowerPCCPU *cpu_, rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); } -/* - * Set the timebase offset of the CPU to that of first CPU. - * This helps hotplugged CPU to have the correct timebase offset. - */ -static void spapr_cpu_update_tb_offset(PowerPCCPU *cpu) -{ - PowerPCCPU *fcpu = POWERPC_CPU(first_cpu); - - cpu->env.tb_env->tb_offset = fcpu->env.tb_env->tb_offset; -} - -static void spapr_cpu_set_endianness(PowerPCCPU *cpu) -{ - PowerPCCPU *fcpu = POWERPC_CPU(first_cpu); - PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(fcpu); - - if (!pcc->interrupts_big_endian(fcpu)) { - cpu->env.spr[SPR_LPCR] |= LPCR_ILE; - } -} - -static void rtas_start_cpu(PowerPCCPU *cpu_, sPAPRMachineState *spapr, +static void rtas_start_cpu(PowerPCCPU *callcpu, sPAPRMachineState *spapr, uint32_t token, uint32_t nargs, target_ulong args, uint32_t nret, target_ulong rets) { target_ulong id, start, r3; - PowerPCCPU *cpu; + PowerPCCPU *newcpu; + CPUPPCState *env; + PowerPCCPUClass *pcc; + target_ulong lpcr; if (nargs != 3 || nret != 1) { rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); @@ -157,41 +142,55 @@ static void rtas_start_cpu(PowerPCCPU *cpu_, sPAPRMachineState *spapr, start = rtas_ld(args, 1); r3 = rtas_ld(args, 2); - cpu = spapr_find_cpu(id); - if (cpu != NULL) { - CPUState *cs = CPU(cpu); - CPUPPCState *env = &cpu->env; - PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu); + newcpu = spapr_find_cpu(id); + if (!newcpu) { + /* Didn't find a matching cpu */ + rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); + return; + } - if (!cs->halted) { - rtas_st(rets, 0, RTAS_OUT_HW_ERROR); - return; - } + env = &newcpu->env; + pcc = POWERPC_CPU_GET_CLASS(newcpu); + + if (!CPU(newcpu)->halted) { + rtas_st(rets, 0, RTAS_OUT_HW_ERROR); + return; + } - /* This will make sure qemu state is up to date with kvm, and - * mark it dirty so our changes get flushed back before the - * new cpu enters */ - kvm_cpu_synchronize_state(cs); + cpu_synchronize_state(CPU(newcpu)); - env->msr = (1ULL << MSR_SF) | (1ULL << MSR_ME); + env->msr = (1ULL << MSR_SF) | (1ULL << MSR_ME); - /* Enable Power-saving mode Exit Cause exceptions for the new CPU */ - env->spr[SPR_LPCR] |= pcc->lpcr_pm; + /* Enable Power-saving mode Exit Cause exceptions for the new CPU */ + lpcr = env->spr[SPR_LPCR]; + if (!pcc->interrupts_big_endian(callcpu)) { + lpcr |= LPCR_ILE; + } + if (env->mmu_model == POWERPC_MMU_3_00) { + /* + * 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; + } else { + lpcr &= ~(LPCR_UPRT | LPCR_GTSE); + } + } + ppc_store_lpcr(newcpu, lpcr); - env->nip = start; - env->gpr[3] = r3; - cs->halted = 0; - spapr_cpu_set_endianness(cpu); - spapr_cpu_update_tb_offset(cpu); + /* + * Set the timebase offset of the new CPU to that of the invoking + * CPU. This helps hotplugged CPU to have the correct timebase + * offset. + */ + newcpu->env.tb_env->tb_offset = callcpu->env.tb_env->tb_offset; - qemu_cpu_kick(cs); + spapr_cpu_set_entry_state(newcpu, start, r3); - rtas_st(rets, 0, RTAS_OUT_SUCCESS); - return; - } + qemu_cpu_kick(CPU(newcpu)); - /* Didn't find a matching cpu */ - rtas_st(rets, 0, RTAS_OUT_PARAM_ERROR); + rtas_st(rets, 0, RTAS_OUT_SUCCESS); } static void rtas_stop_self(PowerPCCPU *cpu, sPAPRMachineState *spapr, @@ -203,13 +202,12 @@ static void rtas_stop_self(PowerPCCPU *cpu, sPAPRMachineState *spapr, CPUPPCState *env = &cpu->env; PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu); - cs->halted = 1; - qemu_cpu_kick(cs); - /* Disable Power-saving mode Exit Cause exceptions for the CPU. * This could deliver an interrupt on a dying CPU and crash the * guest */ - env->spr[SPR_LPCR] &= ~pcc->lpcr_pm; + ppc_store_lpcr(cpu, env->spr[SPR_LPCR] & ~pcc->lpcr_pm); + cs->halted = 1; + qemu_cpu_kick(cs); } static inline int sysparm_st(target_ulong addr, target_ulong len, diff --git a/hw/ppc/trace-events b/hw/ppc/trace-events index 66ec7eda6e..dc5e65aee9 100644 --- a/hw/ppc/trace-events +++ b/hw/ppc/trace-events @@ -92,10 +92,6 @@ rs6000mc_size_read(uint32_t addr, uint32_t val) "read addr=0x%x val=0x%x" rs6000mc_size_write(uint32_t addr, uint32_t val) "write addr=0x%x val=0x%x" rs6000mc_parity_read(uint32_t addr, uint32_t val) "read addr=0x%x val=0x%x" -# hw/ppc/mac_newworld.c -mac99_uninorth_write(uint64_t addr, uint64_t value) "addr=0x%" PRIx64 " val=0x%"PRIx64 -mac99_uninorth_read(uint64_t addr, uint64_t value) "addr=0x%" PRIx64 " val=0x%"PRIx64 - # hw/ppc/ppc4xx_pci.c ppc4xx_pci_map_irq(int32_t devfn, int irq_num, int slot) "devfn 0x%x irq %d -> %d" ppc4xx_pci_set_irq(int irq_num) "PCI irq %d" diff --git a/hw/rdma/rdma_backend.c b/hw/rdma/rdma_backend.c index 5c7b3d8949..e9ced6f9ef 100644 --- a/hw/rdma/rdma_backend.c +++ b/hw/rdma/rdma_backend.c @@ -774,7 +774,7 @@ int rdma_backend_init(RdmaBackendDev *backend_dev, goto out_destroy_comm_channel; } - if (backend_dev->backend_gid_idx > port_attr.gid_tbl_len) { + if (backend_dev->backend_gid_idx >= port_attr.gid_tbl_len) { error_setg(errp, "Invalid backend_gid_idx, should be less than %d", port_attr.gid_tbl_len); goto out_destroy_comm_channel; diff --git a/hw/rdma/rdma_rm.c b/hw/rdma/rdma_rm.c index 51a47d7292..415da15efe 100644 --- a/hw/rdma/rdma_rm.c +++ b/hw/rdma/rdma_rm.c @@ -21,8 +21,6 @@ #include "rdma_backend.h" #include "rdma_rm.h" -#define MAX_RM_TBL_NAME 16 - /* Page directory and page tables */ #define PG_DIR_SZ { TARGET_PAGE_SIZE / sizeof(__u64) } #define PG_TBL_SZ { TARGET_PAGE_SIZE / sizeof(__u64) } diff --git a/hw/rdma/rdma_rm_defs.h b/hw/rdma/rdma_rm_defs.h index fc646da61f..226011176d 100644 --- a/hw/rdma/rdma_rm_defs.h +++ b/hw/rdma/rdma_rm_defs.h @@ -20,9 +20,9 @@ #define MAX_PORTS 1 #define MAX_PORT_GIDS 1 +#define MAX_GIDS MAX_PORT_GIDS #define MAX_PORT_PKEYS 1 -#define MAX_PKEYS 1 -#define MAX_GIDS 2048 +#define MAX_PKEYS MAX_PORT_PKEYS #define MAX_UCS 512 #define MAX_MR_SIZE (1UL << 27) #define MAX_QP 1024 @@ -34,9 +34,9 @@ #define MAX_QP_INIT_RD_ATOM 16 #define MAX_AH 64 -#define MAX_RMRESTBL_NAME_SZ 16 +#define MAX_RM_TBL_NAME 16 typedef struct RdmaRmResTbl { - char name[MAX_RMRESTBL_NAME_SZ]; + char name[MAX_RM_TBL_NAME]; QemuMutex lock; unsigned long *bitmap; size_t tbl_sz; @@ -87,7 +87,6 @@ typedef struct RdmaRmQP { typedef struct RdmaRmPort { union ibv_gid gid_tbl[MAX_PORT_GIDS]; enum ibv_port_state state; - int *pkey_tbl; /* TODO: Not yet supported */ } RdmaRmPort; typedef struct RdmaDeviceResources { diff --git a/hw/rdma/vmw/pvrdma.h b/hw/rdma/vmw/pvrdma.h index 8c173cb824..0b46dc5a9b 100644 --- a/hw/rdma/vmw/pvrdma.h +++ b/hw/rdma/vmw/pvrdma.h @@ -31,7 +31,7 @@ #define RDMA_REG_BAR_IDX 1 #define RDMA_UAR_BAR_IDX 2 #define RDMA_BAR0_MSIX_SIZE (16 * 1024) -#define RDMA_BAR1_REGS_SIZE 256 +#define RDMA_BAR1_REGS_SIZE 64 #define RDMA_BAR2_UAR_SIZE (0x1000 * MAX_UCS) /* each uc gets page */ /* MSIX */ @@ -86,7 +86,7 @@ static inline int get_reg_val(PVRDMADev *dev, hwaddr addr, uint32_t *val) { int idx = addr >> 2; - if (idx > RDMA_BAR1_REGS_SIZE) { + if (idx >= RDMA_BAR1_REGS_SIZE) { return -EINVAL; } @@ -99,7 +99,7 @@ static inline int set_reg_val(PVRDMADev *dev, hwaddr addr, uint32_t val) { int idx = addr >> 2; - if (idx > RDMA_BAR1_REGS_SIZE) { + if (idx >= RDMA_BAR1_REGS_SIZE) { return -EINVAL; } diff --git a/hw/rdma/vmw/pvrdma_cmd.c b/hw/rdma/vmw/pvrdma_cmd.c index 99019d8741..14255d609f 100644 --- a/hw/rdma/vmw/pvrdma_cmd.c +++ b/hw/rdma/vmw/pvrdma_cmd.c @@ -232,7 +232,7 @@ static int create_mr(PVRDMADev *dev, union pvrdma_cmd_req *req, cmd->start, cmd->length, host_virt, cmd->access_flags, &resp->mr_handle, &resp->lkey, &resp->rkey); - if (!resp->hdr.err) { + if (host_virt && !resp->hdr.err) { munmap(host_virt, cmd->length); } @@ -576,7 +576,7 @@ static int create_bind(PVRDMADev *dev, union pvrdma_cmd_req *req, pr_dbg("index=%d\n", cmd->index); - if (cmd->index > MAX_PORT_GIDS) { + if (cmd->index >= MAX_PORT_GIDS) { return -EINVAL; } @@ -603,7 +603,11 @@ static int destroy_bind(PVRDMADev *dev, union pvrdma_cmd_req *req, { struct pvrdma_cmd_destroy_bind *cmd = &req->destroy_bind; - pr_dbg("clear index %d\n", cmd->index); + pr_dbg("index=%d\n", cmd->index); + + if (cmd->index >= MAX_PORT_GIDS) { + return -EINVAL; + } memset(dev->rdma_dev_res.ports[0].gid_tbl[cmd->index].raw, 0, sizeof(dev->rdma_dev_res.ports[0].gid_tbl[cmd->index].raw)); diff --git a/hw/rdma/vmw/pvrdma_main.c b/hw/rdma/vmw/pvrdma_main.c index c552248c90..3ed7409763 100644 --- a/hw/rdma/vmw/pvrdma_main.c +++ b/hw/rdma/vmw/pvrdma_main.c @@ -275,15 +275,6 @@ static void init_dsr_dev_caps(PVRDMADev *dev) pr_dbg("Initialized\n"); } -static void free_ports(PVRDMADev *dev) -{ - int i; - - for (i = 0; i < MAX_PORTS; i++) { - g_free(dev->rdma_dev_res.ports[i].gid_tbl); - } -} - static void init_ports(PVRDMADev *dev, Error **errp) { int i; @@ -292,10 +283,6 @@ static void init_ports(PVRDMADev *dev, Error **errp) for (i = 0; i < MAX_PORTS; i++) { dev->rdma_dev_res.ports[i].state = IBV_PORT_DOWN; - - dev->rdma_dev_res.ports[i].pkey_tbl = - g_malloc0(sizeof(*dev->rdma_dev_res.ports[i].pkey_tbl) * - MAX_PORT_PKEYS); } } @@ -462,14 +449,14 @@ static void init_bars(PCIDevice *pdev) /* BAR 1 - Registers */ memset(&dev->regs_data, 0, sizeof(dev->regs_data)); memory_region_init_io(&dev->regs, OBJECT(dev), ®s_ops, dev, - "pvrdma-regs", RDMA_BAR1_REGS_SIZE); + "pvrdma-regs", sizeof(dev->regs_data)); pci_register_bar(pdev, RDMA_REG_BAR_IDX, PCI_BASE_ADDRESS_SPACE_MEMORY, &dev->regs); /* BAR 2 - UAR */ memset(&dev->uar_data, 0, sizeof(dev->uar_data)); memory_region_init_io(&dev->uar, OBJECT(dev), &uar_ops, dev, "rdma-uar", - RDMA_BAR2_UAR_SIZE); + sizeof(dev->uar_data)); pci_register_bar(pdev, RDMA_UAR_BAR_IDX, PCI_BASE_ADDRESS_SPACE_MEMORY, &dev->uar); } @@ -622,8 +609,6 @@ static void pvrdma_exit(PCIDevice *pdev) pvrdma_qp_ops_fini(); - free_ports(dev); - rdma_rm_fini(&dev->rdma_dev_res); rdma_backend_fini(&dev->backend_dev); diff --git a/hw/rdma/vmw/pvrdma_qp_ops.c b/hw/rdma/vmw/pvrdma_qp_ops.c index 750ade6c31..99bb51111e 100644 --- a/hw/rdma/vmw/pvrdma_qp_ops.c +++ b/hw/rdma/vmw/pvrdma_qp_ops.c @@ -216,6 +216,7 @@ void pvrdma_cq_poll(RdmaDeviceResources *dev_res, uint32_t cq_handle) cq = rdma_rm_get_cq(dev_res, cq_handle); if (!cq) { pr_dbg("Invalid CQ# %d\n", cq_handle); + return; } rdma_backend_poll_cq(dev_res, &cq->backend_cq); diff --git a/hw/s390x/event-facility.c b/hw/s390x/event-facility.c index 9c24bc6f7c..ee5b83448b 100644 --- a/hw/s390x/event-facility.c +++ b/hw/s390x/event-facility.c @@ -26,11 +26,23 @@ typedef struct SCLPEventsBus { BusState qbus; } SCLPEventsBus; +/* we need to save 32 bit chunks for compatibility */ +#ifdef HOST_WORDS_BIGENDIAN +#define RECV_MASK_LOWER 1 +#define RECV_MASK_UPPER 0 +#else /* little endian host */ +#define RECV_MASK_LOWER 0 +#define RECV_MASK_UPPER 1 +#endif + struct SCLPEventFacility { SysBusDevice parent_obj; SCLPEventsBus sbus; /* guest's receive mask */ - sccb_mask_t receive_mask; + union { + uint32_t receive_mask_pieces[2]; + sccb_mask_t receive_mask; + }; /* * when false, we keep the same broken, backwards compatible behaviour as * before, allowing only masks of size exactly 4; when true, we implement @@ -262,7 +274,7 @@ static void read_event_data(SCLPEventFacility *ef, SCCB *sccb) case SCLP_SELECTIVE_READ: copy_mask((uint8_t *)&sclp_active_selection_mask, (uint8_t *)&red->mask, sizeof(sclp_active_selection_mask), ef->mask_length); - sclp_active_selection_mask = be32_to_cpu(sclp_active_selection_mask); + sclp_active_selection_mask = be64_to_cpu(sclp_active_selection_mask); if (!sclp_cp_receive_mask || (sclp_active_selection_mask & ~sclp_cp_receive_mask)) { sccb->h.response_code = @@ -294,21 +306,22 @@ static void write_event_mask(SCLPEventFacility *ef, SCCB *sccb) } /* - * Note: We currently only support masks up to 4 byte length; - * the remainder is filled up with zeroes. Linux uses - * a 4 byte mask length. + * Note: We currently only support masks up to 8 byte length; + * the remainder is filled up with zeroes. Older Linux + * kernels use a 4 byte mask length, newer ones can use both + * 8 or 4 depending on what is available on the host. */ /* keep track of the guest's capability masks */ copy_mask((uint8_t *)&tmp_mask, WEM_CP_RECEIVE_MASK(we_mask, mask_length), sizeof(tmp_mask), mask_length); - ef->receive_mask = be32_to_cpu(tmp_mask); + ef->receive_mask = be64_to_cpu(tmp_mask); /* return the SCLP's capability masks to the guest */ - tmp_mask = cpu_to_be32(get_host_receive_mask(ef)); + tmp_mask = cpu_to_be64(get_host_receive_mask(ef)); copy_mask(WEM_RECEIVE_MASK(we_mask, mask_length), (uint8_t *)&tmp_mask, mask_length, sizeof(tmp_mask)); - tmp_mask = cpu_to_be32(get_host_send_mask(ef)); + tmp_mask = cpu_to_be64(get_host_send_mask(ef)); copy_mask(WEM_SEND_MASK(we_mask, mask_length), (uint8_t *)&tmp_mask, mask_length, sizeof(tmp_mask)); @@ -369,6 +382,13 @@ static void command_handler(SCLPEventFacility *ef, SCCB *sccb, uint64_t code) } } +static bool vmstate_event_facility_mask64_needed(void *opaque) +{ + SCLPEventFacility *ef = opaque; + + return (ef->receive_mask & 0xFFFFFFFF) != 0; +} + static bool vmstate_event_facility_mask_length_needed(void *opaque) { SCLPEventFacility *ef = opaque; @@ -376,6 +396,17 @@ static bool vmstate_event_facility_mask_length_needed(void *opaque) return ef->allow_all_mask_sizes; } +static const VMStateDescription vmstate_event_facility_mask64 = { + .name = "vmstate-event-facility/mask64", + .version_id = 0, + .minimum_version_id = 0, + .needed = vmstate_event_facility_mask64_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT32(receive_mask_pieces[RECV_MASK_LOWER], SCLPEventFacility), + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_event_facility_mask_length = { .name = "vmstate-event-facility/mask_length", .version_id = 0, @@ -392,10 +423,11 @@ static const VMStateDescription vmstate_event_facility = { .version_id = 0, .minimum_version_id = 0, .fields = (VMStateField[]) { - VMSTATE_UINT32(receive_mask, SCLPEventFacility), + VMSTATE_UINT32(receive_mask_pieces[RECV_MASK_UPPER], SCLPEventFacility), VMSTATE_END_OF_LIST() }, .subsections = (const VMStateDescription * []) { + &vmstate_event_facility_mask64, &vmstate_event_facility_mask_length, NULL } @@ -511,3 +543,17 @@ static void register_types(void) } type_init(register_types) + +BusState *sclp_get_event_facility_bus(void) +{ + Object *busobj; + SCLPEventsBus *sbus; + + busobj = object_resolve_path_type("", TYPE_SCLP_EVENTS_BUS, NULL); + sbus = OBJECT_CHECK(SCLPEventsBus, busobj, TYPE_SCLP_EVENTS_BUS); + if (!sbus) { + return NULL; + } + + return &sbus->qbus; +} diff --git a/hw/s390x/ipl.c b/hw/s390x/ipl.c index fb554ab156..150f6c0582 100644 --- a/hw/s390x/ipl.c +++ b/hw/s390x/ipl.c @@ -373,6 +373,10 @@ int s390_ipl_set_loadparm(uint8_t *loadparm) loadparm[i] = ascii2ebcdic[(uint8_t) lp[i]]; } + if (i < 8) { + memset(loadparm + i, 0x40, 8 - i); /* fill with EBCDIC spaces */ + } + g_free(lp); return 0; } diff --git a/hw/s390x/s390-pci-inst.c b/hw/s390x/s390-pci-inst.c index 3fcc330fe3..02a815fd31 100644 --- a/hw/s390x/s390-pci-inst.c +++ b/hw/s390x/s390-pci-inst.c @@ -155,8 +155,6 @@ int clp_service_call(S390CPU *cpu, uint8_t r2, uintptr_t ra) S390pciState *s = s390_get_phb(); int i; - cpu_synchronize_state(CPU(cpu)); - if (env->psw.mask & PSW_MASK_PSTATE) { s390_program_interrupt(env, PGM_PRIVILEGED, 4, ra); return 0; @@ -389,8 +387,6 @@ int pcilg_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) uint32_t fh; uint8_t pcias; - cpu_synchronize_state(CPU(cpu)); - if (env->psw.mask & PSW_MASK_PSTATE) { s390_program_interrupt(env, PGM_PRIVILEGED, 4, ra); return 0; @@ -487,8 +483,6 @@ int pcistg_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) uint32_t fh; uint8_t pcias; - cpu_synchronize_state(CPU(cpu)); - if (env->psw.mask & PSW_MASK_PSTATE) { s390_program_interrupt(env, PGM_PRIVILEGED, 4, ra); return 0; @@ -620,8 +614,6 @@ int rpcit_service_call(S390CPU *cpu, uint8_t r1, uint8_t r2, uintptr_t ra) S390IOTLBEntry entry; hwaddr start, end; - cpu_synchronize_state(CPU(cpu)); - if (env->psw.mask & PSW_MASK_PSTATE) { s390_program_interrupt(env, PGM_PRIVILEGED, 4, ra); return 0; diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index 435f7c99e7..100dfdc96d 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -288,6 +288,15 @@ static void s390_create_virtio_net(BusState *bus, const char *name) } } +static void s390_create_sclpconsole(const char *type, Chardev *chardev) +{ + DeviceState *dev; + + dev = qdev_create(sclp_get_event_facility_bus(), type); + qdev_prop_set_chr(dev, "chardev", chardev); + qdev_init_nofail(dev); +} + static void ccw_init(MachineState *machine) { int ret; @@ -346,6 +355,14 @@ static void ccw_init(MachineState *machine) /* Create VirtIO network adapters */ s390_create_virtio_net(BUS(css_bus), "virtio-net-ccw"); + /* init consoles */ + if (serial_hd(0)) { + s390_create_sclpconsole("sclpconsole", serial_hd(0)); + } + if (serial_hd(1)) { + s390_create_sclpconsole("sclplmconsole", serial_hd(1)); + } + /* Register savevm handler for guest TOD clock */ register_savevm_live(NULL, "todclock", 0, 1, &savevm_gtod, NULL); } @@ -470,10 +487,8 @@ static void ccw_machine_class_init(ObjectClass *oc, void *data) mc->block_default_type = IF_VIRTIO; mc->no_cdrom = 1; mc->no_floppy = 1; - mc->no_serial = 1; mc->no_parallel = 1; mc->no_sdcard = 1; - mc->use_sclp = 1; mc->max_cpus = S390_MAX_CPUS; mc->has_hotpluggable_cpus = true; mc->get_hotplug_handler = s390_get_hotplug_handler; @@ -671,6 +686,9 @@ bool css_migration_enabled(void) } \ type_init(ccw_machine_register_##suffix) +#define CCW_COMPAT_2_12 \ + HW_COMPAT_2_12 + #define CCW_COMPAT_2_11 \ HW_COMPAT_2_11 \ {\ @@ -756,14 +774,26 @@ bool css_migration_enabled(void) .value = "0",\ }, +static void ccw_machine_2_13_instance_options(MachineState *machine) +{ +} + +static void ccw_machine_2_13_class_options(MachineClass *mc) +{ +} +DEFINE_CCW_MACHINE(2_13, "2.13", true); + static void ccw_machine_2_12_instance_options(MachineState *machine) { + ccw_machine_2_13_instance_options(machine); } static void ccw_machine_2_12_class_options(MachineClass *mc) { + ccw_machine_2_13_class_options(mc); + SET_MACHINE_COMPAT(mc, CCW_COMPAT_2_12); } -DEFINE_CCW_MACHINE(2_12, "2.12", true); +DEFINE_CCW_MACHINE(2_12, "2.12", false); static void ccw_machine_2_11_instance_options(MachineState *machine) { diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c index fe34b50769..e67392c5f9 100644 --- a/hw/vfio/ccw.c +++ b/hw/vfio/ccw.c @@ -292,12 +292,43 @@ static void vfio_ccw_put_region(VFIOCCWDevice *vcdev) g_free(vcdev->io_region); } -static void vfio_put_device(VFIOCCWDevice *vcdev) +static void vfio_ccw_put_device(VFIOCCWDevice *vcdev) { g_free(vcdev->vdev.name); vfio_put_base_device(&vcdev->vdev); } +static void vfio_ccw_get_device(VFIOGroup *group, VFIOCCWDevice *vcdev, + Error **errp) +{ + char *name = g_strdup_printf("%x.%x.%04x", vcdev->cdev.hostid.cssid, + vcdev->cdev.hostid.ssid, + vcdev->cdev.hostid.devid); + VFIODevice *vbasedev; + + QLIST_FOREACH(vbasedev, &group->device_list, next) { + if (strcmp(vbasedev->name, name) == 0) { + error_setg(errp, "vfio: subchannel %s has already been attached", + name); + goto out_err; + } + } + + if (vfio_get_device(group, vcdev->cdev.mdevid, &vcdev->vdev, errp)) { + goto out_err; + } + + vcdev->vdev.ops = &vfio_ccw_ops; + vcdev->vdev.type = VFIO_DEVICE_TYPE_CCW; + vcdev->vdev.name = name; + vcdev->vdev.dev = &vcdev->cdev.parent_obj.parent_obj; + + return; + +out_err: + g_free(name); +} + static VFIOGroup *vfio_ccw_get_group(S390CCWDevice *cdev, Error **errp) { char *tmp, group_path[PATH_MAX]; @@ -327,7 +358,6 @@ static VFIOGroup *vfio_ccw_get_group(S390CCWDevice *cdev, Error **errp) static void vfio_ccw_realize(DeviceState *dev, Error **errp) { - VFIODevice *vbasedev; VFIOGroup *group; CcwDevice *ccw_dev = DO_UPCAST(CcwDevice, parent_obj, dev); S390CCWDevice *cdev = DO_UPCAST(S390CCWDevice, parent_obj, ccw_dev); @@ -348,22 +378,8 @@ static void vfio_ccw_realize(DeviceState *dev, Error **errp) goto out_group_err; } - vcdev->vdev.ops = &vfio_ccw_ops; - vcdev->vdev.type = VFIO_DEVICE_TYPE_CCW; - vcdev->vdev.name = g_strdup_printf("%x.%x.%04x", cdev->hostid.cssid, - cdev->hostid.ssid, cdev->hostid.devid); - vcdev->vdev.dev = dev; - QLIST_FOREACH(vbasedev, &group->device_list, next) { - if (strcmp(vbasedev->name, vcdev->vdev.name) == 0) { - error_setg(&err, "vfio: subchannel %s has already been attached", - vcdev->vdev.name); - g_free(vcdev->vdev.name); - goto out_device_err; - } - } - - if (vfio_get_device(group, cdev->mdevid, &vcdev->vdev, &err)) { - g_free(vcdev->vdev.name); + vfio_ccw_get_device(group, vcdev, &err); + if (err) { goto out_device_err; } @@ -382,7 +398,7 @@ static void vfio_ccw_realize(DeviceState *dev, Error **errp) out_notifier_err: vfio_ccw_put_region(vcdev); out_region_err: - vfio_put_device(vcdev); + vfio_ccw_put_device(vcdev); out_device_err: vfio_put_group(group); out_group_err: @@ -403,7 +419,7 @@ static void vfio_ccw_unrealize(DeviceState *dev, Error **errp) vfio_ccw_unregister_io_notifier(vcdev); vfio_ccw_put_region(vcdev); - vfio_put_device(vcdev); + vfio_ccw_put_device(vcdev); vfio_put_group(group); if (cdc->unrealize) { diff --git a/include/elf.h b/include/elf.h index c0dc9bb5fd..934dbbd6b3 100644 --- a/include/elf.h +++ b/include/elf.h @@ -1483,6 +1483,7 @@ typedef struct elf64_shdr { #define ELFOSABI_TRU64 10 /* Compaq TRU64 UNIX. */ #define ELFOSABI_MODESTO 11 /* Novell Modesto. */ #define ELFOSABI_OPENBSD 12 /* OpenBSD. */ +#define ELFOSABI_ARM_FDPIC 65 /* ARM FDPIC */ #define ELFOSABI_ARM 97 /* ARM */ #define ELFOSABI_STANDALONE 255 /* Standalone (embedded) application */ diff --git a/include/exec/user/abitypes.h b/include/exec/user/abitypes.h index ba188608c2..743b8bb9ea 100644 --- a/include/exec/user/abitypes.h +++ b/include/exec/user/abitypes.h @@ -15,7 +15,7 @@ #define ABI_LLONG_ALIGNMENT 2 #endif -#if defined(TARGET_I386) && !defined(TARGET_X86_64) +#if (defined(TARGET_I386) && !defined(TARGET_X86_64)) || defined(TARGET_SH4) #define ABI_LLONG_ALIGNMENT 4 #endif diff --git a/include/hw/boards.h b/include/hw/boards.h index a609239112..5c5eee55e6 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -180,7 +180,6 @@ struct MachineClass { unsigned int no_serial:1, no_parallel:1, use_virtcon:1, - use_sclp:1, no_floppy:1, no_cdrom:1, no_sdcard:1, diff --git a/include/hw/misc/macio/macio.h b/include/hw/misc/macio/macio.h index 64a2584a77..838eaf1db0 100644 --- a/include/hw/misc/macio/macio.h +++ b/include/hw/misc/macio/macio.h @@ -71,7 +71,6 @@ typedef struct NewWorldMacIOState { /*< public >*/ OpenPICState *pic; - qemu_irq irqs[7]; MACIOIDEState ide[2]; } NewWorldMacIOState; diff --git a/include/hw/pci-host/uninorth.h b/include/hw/pci-host/uninorth.h index f0e6836c76..f6654bad9b 100644 --- a/include/hw/pci-host/uninorth.h +++ b/include/hw/pci-host/uninorth.h @@ -53,4 +53,15 @@ typedef struct UNINHostState { MemoryRegion pci_io; } UNINHostState; +typedef struct UNINState { + SysBusDevice parent_obj; + + MemoryRegion mem; + int token[1]; +} UNINState; + +#define TYPE_UNI_NORTH "uni-north" +#define UNI_NORTH(obj) \ + OBJECT_CHECK(UNINState, (obj), TYPE_UNI_NORTH) + #endif /* UNINORTH_H */ diff --git a/include/hw/ppc/spapr_cpu_core.h b/include/hw/ppc/spapr_cpu_core.h index 1129f344aa..47dcfda12b 100644 --- a/include/hw/ppc/spapr_cpu_core.h +++ b/include/hw/ppc/spapr_cpu_core.h @@ -12,6 +12,7 @@ #include "hw/qdev.h" #include "hw/cpu/core.h" #include "target/ppc/cpu-qom.h" +#include "target/ppc/cpu.h" #define TYPE_SPAPR_CPU_CORE "spapr-cpu-core" #define SPAPR_CPU_CORE(obj) \ @@ -38,4 +39,6 @@ typedef struct sPAPRCPUCoreClass { } sPAPRCPUCoreClass; const char *spapr_get_cpu_core_type(const char *cpu_type); +void spapr_cpu_set_entry_state(PowerPCCPU *cpu, target_ulong nip, target_ulong r3); + #endif diff --git a/include/hw/s390x/event-facility.h b/include/hw/s390x/event-facility.h index 5698e5e96c..6cf71cec38 100644 --- a/include/hw/s390x/event-facility.h +++ b/include/hw/s390x/event-facility.h @@ -73,7 +73,7 @@ typedef struct WriteEventMask { #define WEM_RECEIVE_MASK(wem, mask_len) ((wem)->masks + 2 * (mask_len)) #define WEM_SEND_MASK(wem, mask_len) ((wem)->masks + 3 * (mask_len)) -typedef uint32_t sccb_mask_t; +typedef uint64_t sccb_mask_t; typedef struct EventBufferHeader { uint16_t length; @@ -210,4 +210,6 @@ typedef struct SCLPEventFacilityClass { bool (*event_pending)(SCLPEventFacility *ef); } SCLPEventFacilityClass; +BusState *sclp_get_event_facility_bus(void); + #endif diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index d90e10a113..f95dc61dfb 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -120,9 +120,7 @@ static void target_setup_general_frame(struct target_rt_sigframe *sf, __put_user(0, &sf->uc.tuc_flags); __put_user(0, &sf->uc.tuc_link); - __put_user(target_sigaltstack_used.ss_sp, &sf->uc.tuc_stack.ss_sp); - __put_user(sas_ss_flags(env->xregs[31]), &sf->uc.tuc_stack.ss_flags); - __put_user(target_sigaltstack_used.ss_size, &sf->uc.tuc_stack.ss_size); + target_save_altstack(&sf->uc.tuc_stack, env); for (i = 0; i < 31; i++) { __put_user(env->xregs[i], &sf->uc.tuc_mcontext.regs[i]); @@ -372,14 +370,7 @@ static abi_ulong get_sigframe(struct target_sigaction *ka, { abi_ulong sp; - sp = env->xregs[31]; - - /* - * This is the X/Open sanctioned signal stack switching. - */ - if ((ka->sa_flags & TARGET_SA_ONSTACK) && !sas_ss_flags(sp)) { - sp = target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; - } + sp = target_sigsp(get_sp_from_cpustate(env), ka); sp = (sp - size) & ~15; diff --git a/linux-user/alpha/signal.c b/linux-user/alpha/signal.c index a8c718f2c6..f24de02c6f 100644 --- a/linux-user/alpha/signal.c +++ b/linux-user/alpha/signal.c @@ -117,12 +117,10 @@ static inline abi_ulong get_sigframe(struct target_sigaction *sa, CPUAlphaState *env, unsigned long framesize) { - abi_ulong sp = env->ir[IR_SP]; + abi_ulong sp; + + sp = target_sigsp(get_sp_from_cpustate(env), sa); - /* This is the X/Open sanctioned signal stack switching. */ - if ((sa->sa_flags & TARGET_SA_ONSTACK) != 0 && !sas_ss_flags(sp)) { - sp = target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; - } return (sp - framesize) & -32; } @@ -187,12 +185,9 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, __put_user(0, &frame->uc.tuc_flags); __put_user(0, &frame->uc.tuc_link); __put_user(set->sig[0], &frame->uc.tuc_osf_sigmask); - __put_user(target_sigaltstack_used.ss_sp, - &frame->uc.tuc_stack.ss_sp); - __put_user(sas_ss_flags(env->ir[IR_SP]), - &frame->uc.tuc_stack.ss_flags); - __put_user(target_sigaltstack_used.ss_size, - &frame->uc.tuc_stack.ss_size); + + target_save_altstack(&frame->uc.tuc_stack, env); + setup_sigcontext(&frame->uc.tuc_mcontext, env, frame_addr, set); for (i = 0; i < TARGET_NSIG_WORDS; ++i) { __put_user(set->sig[i], &frame->uc.tuc_sigmask.sig[i]); diff --git a/linux-user/arm/signal.c b/linux-user/arm/signal.c index 0c1ec53025..59b5b65ed1 100644 --- a/linux-user/arm/signal.c +++ b/linux-user/arm/signal.c @@ -102,13 +102,13 @@ struct sigframe_v1 { struct target_sigcontext sc; abi_ulong extramask[TARGET_NSIG_WORDS-1]; - abi_ulong retcode; + abi_ulong retcode[4]; }; struct sigframe_v2 { struct target_ucontext_v2 uc; - abi_ulong retcode; + abi_ulong retcode[4]; }; struct rt_sigframe_v1 @@ -117,14 +117,14 @@ struct rt_sigframe_v1 abi_ulong puc; struct target_siginfo info; struct target_ucontext_v1 uc; - abi_ulong retcode; + abi_ulong retcode[4]; }; struct rt_sigframe_v2 { struct target_siginfo info; struct target_ucontext_v2 uc; - abi_ulong retcode; + abi_ulong retcode[4]; }; #define TARGET_CONFIG_CPU_32 1 @@ -147,6 +147,21 @@ static const abi_ulong retcodes[4] = { SWI_SYS_RT_SIGRETURN, SWI_THUMB_RT_SIGRETURN }; +/* + * Stub needed to make sure the FD register (r9) contains the right + * value. + */ +static const unsigned long sigreturn_fdpic_codes[3] = { + 0xe59fc004, /* ldr r12, [pc, #4] to read function descriptor */ + 0xe59c9004, /* ldr r9, [r12, #4] to setup GOT */ + 0xe59cf000 /* ldr pc, [r12] to jump into restorer */ +}; + +static const unsigned long sigreturn_fdpic_thumb_codes[3] = { + 0xc008f8df, /* ldr r12, [pc, #8] to read function descriptor */ + 0x9004f8dc, /* ldr r9, [r12, #4] to setup GOT */ + 0xf000f8dc /* ldr pc, [r12] to jump into restorer */ +}; static inline int valid_user_regs(CPUARMState *regs) { @@ -186,27 +201,42 @@ setup_sigcontext(struct target_sigcontext *sc, /*struct _fpstate *fpstate,*/ static inline abi_ulong get_sigframe(struct target_sigaction *ka, CPUARMState *regs, int framesize) { - unsigned long sp = regs->regs[13]; + unsigned long sp; - /* - * This is the X/Open sanctioned signal stack switching. - */ - if ((ka->sa_flags & TARGET_SA_ONSTACK) && !sas_ss_flags(sp)) { - sp = target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; - } + sp = target_sigsp(get_sp_from_cpustate(regs), ka); /* * ATPCS B01 mandates 8-byte alignment */ return (sp - framesize) & ~7; } -static void +static int setup_return(CPUARMState *env, struct target_sigaction *ka, abi_ulong *rc, abi_ulong frame_addr, int usig, abi_ulong rc_addr) { - abi_ulong handler = ka->_sa_handler; + abi_ulong handler = 0; + abi_ulong handler_fdpic_GOT = 0; abi_ulong retcode; - int thumb = handler & 1; + + int thumb; + int is_fdpic = info_is_fdpic(((TaskState *)thread_cpu->opaque)->info); + + if (is_fdpic) { + /* In FDPIC mode, ka->_sa_handler points to a function + * descriptor (FD). The first word contains the address of the + * handler. The second word contains the value of the PIC + * register (r9). */ + abi_ulong funcdesc_ptr = ka->_sa_handler; + if (get_user_ual(handler, funcdesc_ptr) + || get_user_ual(handler_fdpic_GOT, funcdesc_ptr + 4)) { + return 1; + } + } else { + handler = ka->_sa_handler; + } + + thumb = handler & 1; + uint32_t cpsr = cpsr_read(env); cpsr &= ~CPSR_IT; @@ -217,7 +247,28 @@ setup_return(CPUARMState *env, struct target_sigaction *ka, } if (ka->sa_flags & TARGET_SA_RESTORER) { - retcode = ka->sa_restorer; + if (is_fdpic) { + /* For FDPIC we ensure that the restorer is called with a + * correct r9 value. For that we need to write code on + * the stack that sets r9 and jumps back to restorer + * value. + */ + if (thumb) { + __put_user(sigreturn_fdpic_thumb_codes[0], rc); + __put_user(sigreturn_fdpic_thumb_codes[1], rc + 1); + __put_user(sigreturn_fdpic_thumb_codes[2], rc + 2); + __put_user((abi_ulong)ka->sa_restorer, rc + 3); + } else { + __put_user(sigreturn_fdpic_codes[0], rc); + __put_user(sigreturn_fdpic_codes[1], rc + 1); + __put_user(sigreturn_fdpic_codes[2], rc + 2); + __put_user((abi_ulong)ka->sa_restorer, rc + 3); + } + + retcode = rc_addr + thumb; + } else { + retcode = ka->sa_restorer; + } } else { unsigned int idx = thumb; @@ -231,10 +282,15 @@ setup_return(CPUARMState *env, struct target_sigaction *ka, } env->regs[0] = usig; + if (is_fdpic) { + env->regs[9] = handler_fdpic_GOT; + } env->regs[13] = frame_addr; env->regs[14] = retcode; env->regs[15] = handler & (thumb ? ~1 : ~3); cpsr_write(env, cpsr, CPSR_IT | CPSR_T, CPSRWriteByInstr); + + return 0; } static abi_ulong *setup_sigframe_v2_vfp(abi_ulong *regspace, CPUARMState *env) @@ -285,9 +341,7 @@ static void setup_sigframe_v2(struct target_ucontext_v2 *uc, memset(uc, 0, offsetof(struct target_ucontext_v2, tuc_mcontext)); memset(&stack, 0, sizeof(stack)); - __put_user(target_sigaltstack_used.ss_sp, &stack.ss_sp); - __put_user(target_sigaltstack_used.ss_size, &stack.ss_size); - __put_user(sas_ss_flags(get_sp_from_cpustate(env)), &stack.ss_flags); + target_save_altstack(&stack, env); memcpy(&uc->tuc_stack, &stack, sizeof(stack)); setup_sigcontext(&uc->tuc_mcontext, env, set->sig[0]); @@ -327,12 +381,15 @@ static void setup_frame_v1(int usig, struct target_sigaction *ka, __put_user(set->sig[i], &frame->extramask[i - 1]); } - setup_return(regs, ka, &frame->retcode, frame_addr, usig, - frame_addr + offsetof(struct sigframe_v1, retcode)); + if (setup_return(regs, ka, frame->retcode, frame_addr, usig, + frame_addr + offsetof(struct sigframe_v1, retcode))) { + goto sigsegv; + } unlock_user_struct(frame, frame_addr, 1); return; sigsegv: + unlock_user_struct(frame, frame_addr, 1); force_sigsegv(usig); } @@ -349,12 +406,15 @@ static void setup_frame_v2(int usig, struct target_sigaction *ka, setup_sigframe_v2(&frame->uc, set, regs); - setup_return(regs, ka, &frame->retcode, frame_addr, usig, - frame_addr + offsetof(struct sigframe_v2, retcode)); + if (setup_return(regs, ka, frame->retcode, frame_addr, usig, + frame_addr + offsetof(struct sigframe_v2, retcode))) { + goto sigsegv; + } unlock_user_struct(frame, frame_addr, 1); return; sigsegv: + unlock_user_struct(frame, frame_addr, 1); force_sigsegv(usig); } @@ -394,9 +454,7 @@ static void setup_rt_frame_v1(int usig, struct target_sigaction *ka, memset(&frame->uc, 0, offsetof(struct target_ucontext_v1, tuc_mcontext)); memset(&stack, 0, sizeof(stack)); - __put_user(target_sigaltstack_used.ss_sp, &stack.ss_sp); - __put_user(target_sigaltstack_used.ss_size, &stack.ss_size); - __put_user(sas_ss_flags(get_sp_from_cpustate(env)), &stack.ss_flags); + target_save_altstack(&stack, env); memcpy(&frame->uc.tuc_stack, &stack, sizeof(stack)); setup_sigcontext(&frame->uc.tuc_mcontext, env, set->sig[0]); @@ -404,8 +462,10 @@ static void setup_rt_frame_v1(int usig, struct target_sigaction *ka, __put_user(set->sig[i], &frame->uc.tuc_sigmask.sig[i]); } - setup_return(env, ka, &frame->retcode, frame_addr, usig, - frame_addr + offsetof(struct rt_sigframe_v1, retcode)); + if (setup_return(env, ka, frame->retcode, frame_addr, usig, + frame_addr + offsetof(struct rt_sigframe_v1, retcode))) { + goto sigsegv; + } env->regs[1] = info_addr; env->regs[2] = uc_addr; @@ -413,6 +473,7 @@ static void setup_rt_frame_v1(int usig, struct target_sigaction *ka, unlock_user_struct(frame, frame_addr, 1); return; sigsegv: + unlock_user_struct(frame, frame_addr, 1); force_sigsegv(usig); } @@ -435,8 +496,10 @@ static void setup_rt_frame_v2(int usig, struct target_sigaction *ka, setup_sigframe_v2(&frame->uc, set, env); - setup_return(env, ka, &frame->retcode, frame_addr, usig, - frame_addr + offsetof(struct rt_sigframe_v2, retcode)); + if (setup_return(env, ka, frame->retcode, frame_addr, usig, + frame_addr + offsetof(struct rt_sigframe_v2, retcode))) { + goto sigsegv; + } env->regs[1] = info_addr; env->regs[2] = uc_addr; @@ -444,6 +507,7 @@ static void setup_rt_frame_v2(int usig, struct target_sigaction *ka, unlock_user_struct(frame, frame_addr, 1); return; sigsegv: + unlock_user_struct(frame, frame_addr, 1); force_sigsegv(usig); } diff --git a/linux-user/arm/target_structs.h b/linux-user/arm/target_structs.h index 0bf034cc25..9a3dbce03d 100644 --- a/linux-user/arm/target_structs.h +++ b/linux-user/arm/target_structs.h @@ -49,4 +49,11 @@ struct target_shmid_ds { abi_ulong __unused5; }; +struct target_oabi_flock64 { + abi_short l_type; + abi_short l_whence; + abi_llong l_start; + abi_llong l_len; + abi_int l_pid; +} QEMU_PACKED; #endif diff --git a/linux-user/elfload.c b/linux-user/elfload.c index c77ed1bb01..36d52194bc 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -78,6 +78,11 @@ enum { */ #define personality(pers) (pers & PER_MASK) +int info_is_fdpic(struct image_info *info) +{ + return info->personality == PER_LINUX_FDPIC; +} + /* this flag is uneffective under linux too, should be deleted */ #ifndef MAP_DENYWRITE #define MAP_DENYWRITE 0 @@ -287,6 +292,25 @@ static inline void init_thread(struct target_pt_regs *regs, /* For uClinux PIC binaries. */ /* XXX: Linux does this only on ARM with no MMU (do we care ?) */ regs->uregs[10] = infop->start_data; + + /* Support ARM FDPIC. */ + if (info_is_fdpic(infop)) { + /* As described in the ABI document, r7 points to the loadmap info + * prepared by the kernel. If an interpreter is needed, r8 points + * to the interpreter loadmap and r9 points to the interpreter + * PT_DYNAMIC info. If no interpreter is needed, r8 is zero, and + * r9 points to the main program PT_DYNAMIC info. + */ + regs->uregs[7] = infop->loadmap_addr; + if (infop->interpreter_loadmap_addr) { + /* Executable is dynamically loaded. */ + regs->uregs[8] = infop->interpreter_loadmap_addr; + regs->uregs[9] = infop->interpreter_pt_dynamic_addr; + } else { + regs->uregs[8] = 0; + regs->uregs[9] = infop->pt_dynamic_addr; + } + } } #define ELF_NREG 18 @@ -1681,7 +1705,19 @@ static void zero_bss(abi_ulong elf_bss, abi_ulong last_bss, int prot) } } -#ifdef CONFIG_USE_FDPIC +#ifdef TARGET_ARM +static int elf_is_fdpic(struct elfhdr *exec) +{ + return exec->e_ident[EI_OSABI] == ELFOSABI_ARM_FDPIC; +} +#else +/* Default implementation, always false. */ +static int elf_is_fdpic(struct elfhdr *exec) +{ + return 0; +} +#endif + static abi_ulong loader_build_fdpic_loadmap(struct image_info *info, abi_ulong sp) { uint16_t n; @@ -1706,7 +1742,6 @@ static abi_ulong loader_build_fdpic_loadmap(struct image_info *info, abi_ulong s return sp; } -#endif static abi_ulong create_elf_tables(abi_ulong p, int argc, int envc, struct elfhdr *exec, @@ -1725,7 +1760,6 @@ static abi_ulong create_elf_tables(abi_ulong p, int argc, int envc, sp = p; -#ifdef CONFIG_USE_FDPIC /* Needs to be before we load the env/argc/... */ if (elf_is_fdpic(exec)) { /* Need 4 byte alignment for these structs */ @@ -1735,9 +1769,13 @@ static abi_ulong create_elf_tables(abi_ulong p, int argc, int envc, if (interp_info) { interp_info->other_info = info; sp = loader_build_fdpic_loadmap(interp_info, sp); + info->interpreter_loadmap_addr = interp_info->loadmap_addr; + info->interpreter_pt_dynamic_addr = interp_info->pt_dynamic_addr; + } else { + info->interpreter_loadmap_addr = 0; + info->interpreter_pt_dynamic_addr = 0; } } -#endif u_platform = 0; k_platform = ELF_PLATFORM; @@ -2153,10 +2191,8 @@ static void load_elf_image(const char *image_name, int image_fd, } bswap_phdr(phdr, ehdr->e_phnum); -#ifdef CONFIG_USE_FDPIC info->nsegs = 0; info->pt_dynamic_addr = 0; -#endif mmap_lock(); @@ -2173,9 +2209,7 @@ static void load_elf_image(const char *image_name, int image_fd, if (a > hiaddr) { hiaddr = a; } -#ifdef CONFIG_USE_FDPIC ++info->nsegs; -#endif } } @@ -2200,8 +2234,7 @@ static void load_elf_image(const char *image_name, int image_fd, } load_bias = load_addr - loaddr; -#ifdef CONFIG_USE_FDPIC - { + if (elf_is_fdpic(ehdr)) { struct elf32_fdpic_loadseg *loadsegs = info->loadsegs = g_malloc(sizeof(*loadsegs) * info->nsegs); @@ -2219,7 +2252,6 @@ static void load_elf_image(const char *image_name, int image_fd, } } } -#endif info->load_bias = load_bias; info->load_addr = load_addr; diff --git a/linux-user/hppa/signal.c b/linux-user/hppa/signal.c index 585af3a37f..6e7a295aee 100644 --- a/linux-user/hppa/signal.c +++ b/linux-user/hppa/signal.c @@ -113,11 +113,9 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, struct target_rt_sigframe *frame; int i; - sp = env->gr[30]; - if (ka->sa_flags & TARGET_SA_ONSTACK) { - if (sas_ss_flags(sp) == 0) { - sp = (target_sigaltstack_used.ss_sp + 0x7f) & ~0x3f; - } + sp = get_sp_from_cpustate(env); + if ((ka->sa_flags & TARGET_SA_ONSTACK) && !sas_ss_flags(sp)) { + sp = (target_sigaltstack_used.ss_sp + 0x7f) & ~0x3f; } frame_addr = QEMU_ALIGN_UP(sp, 64); sp = frame_addr + PARISC_RT_SIGFRAME_SIZE32; @@ -132,11 +130,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, frame->uc.tuc_flags = 0; frame->uc.tuc_link = 0; - __put_user(target_sigaltstack_used.ss_sp, &frame->uc.tuc_stack.ss_sp); - __put_user(sas_ss_flags(get_sp_from_cpustate(env)), - &frame->uc.tuc_stack.ss_flags); - __put_user(target_sigaltstack_used.ss_size, - &frame->uc.tuc_stack.ss_size); + target_save_altstack(&frame->uc.tuc_stack, env); for (i = 0; i < TARGET_NSIG_WORDS; i++) { __put_user(set->sig[i], &frame->uc.tuc_sigmask.sig[i]); diff --git a/linux-user/i386/signal.c b/linux-user/i386/signal.c index 4a190e6435..e9a23a2dec 100644 --- a/linux-user/i386/signal.c +++ b/linux-user/i386/signal.c @@ -283,16 +283,14 @@ get_sigframe(struct target_sigaction *ka, CPUX86State *env, size_t frame_size) unsigned long esp; /* Default to using normal stack */ - esp = env->regs[R_ESP]; + esp = get_sp_from_cpustate(env); #ifdef TARGET_X86_64 esp -= 128; /* this is the redzone */ #endif /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa_flags & TARGET_SA_ONSTACK) { - if (sas_ss_flags(esp) == 0) { - esp = target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; - } + esp = target_sigsp(esp, ka); } else { #ifndef TARGET_X86_64 /* This is the legacy signal stack switching. */ @@ -404,11 +402,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, /* Create the ucontext. */ __put_user(0, &frame->uc.tuc_flags); __put_user(0, &frame->uc.tuc_link); - __put_user(target_sigaltstack_used.ss_sp, &frame->uc.tuc_stack.ss_sp); - __put_user(sas_ss_flags(get_sp_from_cpustate(env)), - &frame->uc.tuc_stack.ss_flags); - __put_user(target_sigaltstack_used.ss_size, - &frame->uc.tuc_stack.ss_size); + target_save_altstack(&frame->uc.tuc_stack, env); setup_sigcontext(&frame->uc.tuc_mcontext, &frame->fpstate, env, set->sig[0], frame_addr + offsetof(struct rt_sigframe, fpstate)); diff --git a/linux-user/m68k/signal.c b/linux-user/m68k/signal.c index fc72468a81..5dd8bb5f99 100644 --- a/linux-user/m68k/signal.c +++ b/linux-user/m68k/signal.c @@ -117,14 +117,10 @@ static inline abi_ulong get_sigframe(struct target_sigaction *ka, CPUM68KState *regs, size_t frame_size) { - unsigned long sp; + abi_ulong sp; - sp = regs->aregs[7]; + sp = target_sigsp(get_sp_from_cpustate(regs), ka); - /* This is the X/Open sanctioned signal stack switching. */ - if ((ka->sa_flags & TARGET_SA_ONSTACK) && (sas_ss_flags (sp) == 0)) { - sp = target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; - } return ((sp - frame_size) & -8UL); } @@ -318,12 +314,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, __put_user(0, &frame->uc.tuc_flags); __put_user(0, &frame->uc.tuc_link); - __put_user(target_sigaltstack_used.ss_sp, - &frame->uc.tuc_stack.ss_sp); - __put_user(sas_ss_flags(env->aregs[7]), - &frame->uc.tuc_stack.ss_flags); - __put_user(target_sigaltstack_used.ss_size, - &frame->uc.tuc_stack.ss_size); + target_save_altstack(&frame->uc.tuc_stack, env); err |= target_rt_setup_ucontext(&frame->uc, env); if (err) diff --git a/linux-user/microblaze/signal.c b/linux-user/microblaze/signal.c index 5572baa7dc..fada0f1495 100644 --- a/linux-user/microblaze/signal.c +++ b/linux-user/microblaze/signal.c @@ -133,9 +133,7 @@ static abi_ulong get_sigframe(struct target_sigaction *ka, { abi_ulong sp = env->regs[1]; - if ((ka->sa_flags & TARGET_SA_ONSTACK) != 0 && !on_sig_stack(sp)) { - sp = target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; - } + sp = target_sigsp(sp, ka); return ((sp - frame_size) & -8UL); } diff --git a/linux-user/mips/signal.c b/linux-user/mips/signal.c index adeb5a4241..ed9849c7f6 100644 --- a/linux-user/mips/signal.c +++ b/linux-user/mips/signal.c @@ -179,20 +179,12 @@ get_sigframe(struct target_sigaction *ka, CPUMIPSState *regs, size_t frame_size) { unsigned long sp; - /* Default to using normal stack */ - sp = regs->active_tc.gpr[29]; - /* * FPU emulator may have its own trampoline active just * above the user stack, 16-bytes before the next lowest * 16 byte boundary. Try to avoid trashing it. */ - sp -= 32; - - /* This is the X/Open sanctioned signal stack switching. */ - if ((ka->sa_flags & TARGET_SA_ONSTACK) && (sas_ss_flags (sp) == 0)) { - sp = target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; - } + sp = target_sigsp(get_sp_from_cpustate(regs) - 32, ka); return (sp - frame_size) & ~7; } @@ -323,10 +315,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, __put_user(0, &frame->rs_uc.tuc_flags); __put_user(0, &frame->rs_uc.tuc_link); - __put_user(target_sigaltstack_used.ss_sp, &frame->rs_uc.tuc_stack.ss_sp); - __put_user(target_sigaltstack_used.ss_size, &frame->rs_uc.tuc_stack.ss_size); - __put_user(sas_ss_flags(get_sp_from_cpustate(env)), - &frame->rs_uc.tuc_stack.ss_flags); + target_save_altstack(&frame->rs_uc.tuc_stack, env); setup_sigcontext(env, &frame->rs_uc.tuc_mcontext); diff --git a/linux-user/nios2/signal.c b/linux-user/nios2/signal.c index 816eed90f1..9a0b36e5ad 100644 --- a/linux-user/nios2/signal.c +++ b/linux-user/nios2/signal.c @@ -42,18 +42,6 @@ struct target_rt_sigframe { struct target_ucontext uc; }; -static unsigned long sigsp(unsigned long sp, struct target_sigaction *ka) -{ - if (unlikely((ka->sa_flags & SA_ONSTACK)) && !sas_ss_flags(sp)) { -#ifdef CONFIG_STACK_GROWSUP - return target_sigaltstack_used.ss_sp; -#else - return target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; -#endif - } - return sp; -} - static int rt_setup_ucontext(struct target_ucontext *uc, CPUNios2State *env) { unsigned long *gregs = uc->tuc_mcontext.gregs; @@ -158,11 +146,8 @@ static void *get_sigframe(struct target_sigaction *ka, CPUNios2State *env, { unsigned long usp; - /* Default to using normal stack. */ - usp = env->regs[R_SP]; - /* This is the X/Open sanctioned signal stack switching. */ - usp = sigsp(usp, ka); + usp = target_sigsp(get_sp_from_cpustate(env), ka); /* Verify, is it 32 or 64 bit aligned */ return (void *)((usp - frame_size) & -8UL); @@ -185,9 +170,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, /* Create the ucontext. */ __put_user(0, &frame->uc.tuc_flags); __put_user(0, &frame->uc.tuc_link); - __put_user(target_sigaltstack_used.ss_sp, &frame->uc.tuc_stack.ss_sp); - __put_user(sas_ss_flags(env->regs[R_SP]), &frame->uc.tuc_stack.ss_flags); - __put_user(target_sigaltstack_used.ss_size, &frame->uc.tuc_stack.ss_size); + target_save_altstack(&frame->uc.tuc_stack, env); err |= rt_setup_ucontext(&frame->uc, env); for (i = 0; i < TARGET_NSIG_WORDS; i++) { __put_user((abi_ulong)set->sig[i], diff --git a/linux-user/openrisc/signal.c b/linux-user/openrisc/signal.c index 0276808b59..ecf2897ccd 100644 --- a/linux-user/openrisc/signal.c +++ b/linux-user/openrisc/signal.c @@ -124,14 +124,11 @@ static inline abi_ulong get_sigframe(struct target_sigaction *ka, CPUOpenRISCState *regs, size_t frame_size) { - unsigned long sp = cpu_get_gpr(regs, 1); + unsigned long sp = get_sp_from_cpustate(regs); int onsigstack = on_sig_stack(sp); /* redzone */ - /* This is the X/Open sanctioned signal stack switching. */ - if ((ka->sa_flags & TARGET_SA_ONSTACK) != 0 && !onsigstack) { - sp = target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; - } + sp = target_sigsp(sp, ka); sp = align_sigframe(sp - frame_size); @@ -175,12 +172,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, /*err |= __clear_user(&frame->uc, offsetof(ucontext_t, uc_mcontext));*/ __put_user(0, &frame->uc.tuc_flags); __put_user(0, &frame->uc.tuc_link); - __put_user(target_sigaltstack_used.ss_sp, - &frame->uc.tuc_stack.ss_sp); - __put_user(sas_ss_flags(cpu_get_gpr(env, 1)), - &frame->uc.tuc_stack.ss_flags); - __put_user(target_sigaltstack_used.ss_size, - &frame->uc.tuc_stack.ss_size); + target_save_altstack(&frame->uc.tuc_stack, env); setup_sigcontext(&frame->sc, env, set->sig[0]); /*err |= copy_to_user(frame->uc.tuc_sigmask, set, sizeof(*set));*/ diff --git a/linux-user/ppc/signal.c b/linux-user/ppc/signal.c index 15148d54a9..cacc9afb5a 100644 --- a/linux-user/ppc/signal.c +++ b/linux-user/ppc/signal.c @@ -217,13 +217,7 @@ static target_ulong get_sigframe(struct target_sigaction *ka, { target_ulong oldsp; - oldsp = env->gpr[1]; - - if ((ka->sa_flags & TARGET_SA_ONSTACK) && - (sas_ss_flags(oldsp) == 0)) { - oldsp = (target_sigaltstack_used.ss_sp - + target_sigaltstack_used.ss_size); - } + oldsp = target_sigsp(get_sp_from_cpustate(env), ka); return (oldsp - frame_size) & ~0xFUL; } @@ -515,12 +509,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, __put_user(0, &rt_sf->uc.tuc_flags); __put_user(0, &rt_sf->uc.tuc_link); - __put_user((target_ulong)target_sigaltstack_used.ss_sp, - &rt_sf->uc.tuc_stack.ss_sp); - __put_user(sas_ss_flags(env->gpr[1]), - &rt_sf->uc.tuc_stack.ss_flags); - __put_user(target_sigaltstack_used.ss_size, - &rt_sf->uc.tuc_stack.ss_size); + target_save_altstack(&rt_sf->uc.tuc_stack, env); #if !defined(TARGET_PPC64) __put_user(h2g (&rt_sf->uc.tuc_mcontext), &rt_sf->uc.tuc_regs); diff --git a/linux-user/qemu.h b/linux-user/qemu.h index 192a0d2fef..c55c8e294b 100644 --- a/linux-user/qemu.h +++ b/linux-user/qemu.h @@ -51,13 +51,15 @@ struct image_info { abi_ulong file_string; uint32_t elf_flags; int personality; -#ifdef CONFIG_USE_FDPIC + + /* The fields below are used in FDPIC mode. */ abi_ulong loadmap_addr; uint16_t nsegs; void *loadsegs; abi_ulong pt_dynamic_addr; + abi_ulong interpreter_loadmap_addr; + abi_ulong interpreter_pt_dynamic_addr; struct image_info *other_info; -#endif }; #ifdef TARGET_I386 @@ -183,6 +185,13 @@ int loader_exec(int fdexec, const char *filename, char **argv, char **envp, struct target_pt_regs * regs, struct image_info *infop, struct linux_binprm *); +/* Returns true if the image uses the FDPIC ABI. If this is the case, + * we have to provide some information (loadmap, pt_dynamic_info) such + * that the program can be relocated adequately. This is also useful + * when handling signals. + */ +int info_is_fdpic(struct image_info *info); + uint32_t get_elf_eflags(int fd); int load_elf_binary(struct linux_binprm *bprm, struct image_info *info); int load_flt_binary(struct linux_binprm *bprm, struct image_info *info); diff --git a/linux-user/riscv/signal.c b/linux-user/riscv/signal.c index 718f3a5679..ef599e319a 100644 --- a/linux-user/riscv/signal.c +++ b/linux-user/riscv/signal.c @@ -54,24 +54,20 @@ struct target_rt_sigframe { static abi_ulong get_sigframe(struct target_sigaction *ka, CPURISCVState *regs, size_t framesize) { - abi_ulong sp = regs->gpr[xSP]; - int onsigstack = on_sig_stack(sp); - - /* redzone */ - /* This is the X/Open sanctioned signal stack switching. */ - if ((ka->sa_flags & TARGET_SA_ONSTACK) != 0 && !onsigstack) { - sp = target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; - } - - sp -= framesize; - sp &= ~3UL; /* align sp on 4-byte boundary */ + abi_ulong sp = get_sp_from_cpustate(regs); /* If we are on the alternate signal stack and would overflow it, don't. Return an always-bogus address instead so we will die with SIGSEGV. */ - if (onsigstack && !likely(on_sig_stack(sp))) { + if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize))) { return -1L; } + /* This is the X/Open sanctioned signal stack switching. */ + sp = target_sigsp(sp, ka) - framesize; + + /* XXX: kernel aligns with 0xf ? */ + sp &= ~3UL; /* align sp on 4-byte boundary */ + return sp; } @@ -95,16 +91,10 @@ static void setup_sigcontext(struct target_sigcontext *sc, CPURISCVState *env) static void setup_ucontext(struct target_ucontext *uc, CPURISCVState *env, target_sigset_t *set) { - abi_ulong ss_sp = (target_ulong)target_sigaltstack_used.ss_sp; - abi_ulong ss_flags = sas_ss_flags(env->gpr[xSP]); - abi_ulong ss_size = target_sigaltstack_used.ss_size; - __put_user(0, &(uc->uc_flags)); __put_user(0, &(uc->uc_link)); - __put_user(ss_sp, &(uc->uc_stack.ss_sp)); - __put_user(ss_flags, &(uc->uc_stack.ss_flags)); - __put_user(ss_size, &(uc->uc_stack.ss_size)); + target_save_altstack(&uc->uc_stack, env); int i; for (i = 0; i < TARGET_NSIG_WORDS; i++) { diff --git a/linux-user/s390x/signal.c b/linux-user/s390x/signal.c index a204a85e4a..e35cbe6870 100644 --- a/linux-user/s390x/signal.c +++ b/linux-user/s390x/signal.c @@ -86,14 +86,11 @@ get_sigframe(struct target_sigaction *ka, CPUS390XState *env, size_t frame_size) abi_ulong sp; /* Default to using normal stack */ - sp = env->regs[15]; + sp = get_sp_from_cpustate(env); /* This is the X/Open sanctioned signal stack switching. */ if (ka->sa_flags & TARGET_SA_ONSTACK) { - if (!sas_ss_flags(sp)) { - sp = target_sigaltstack_used.ss_sp + - target_sigaltstack_used.ss_size; - } + sp = target_sigsp(sp, ka); } /* This is the legacy signal stack switching. */ @@ -205,10 +202,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, /* Create the ucontext. */ __put_user(0, &frame->uc.tuc_flags); __put_user((abi_ulong)0, (abi_ulong *)&frame->uc.tuc_link); - __put_user(target_sigaltstack_used.ss_sp, &frame->uc.tuc_stack.ss_sp); - __put_user(sas_ss_flags(get_sp_from_cpustate(env)), - &frame->uc.tuc_stack.ss_flags); - __put_user(target_sigaltstack_used.ss_size, &frame->uc.tuc_stack.ss_size); + target_save_altstack(&frame->uc.tuc_stack, env); save_sigregs(env, &frame->uc.tuc_mcontext); for (i = 0; i < TARGET_NSIG_WORDS; i++) { __put_user((abi_ulong)set->sig[i], diff --git a/linux-user/sh4/signal.c b/linux-user/sh4/signal.c index 5ce182aff7..2a5378e16e 100644 --- a/linux-user/sh4/signal.c +++ b/linux-user/sh4/signal.c @@ -78,9 +78,7 @@ struct target_rt_sigframe static abi_ulong get_sigframe(struct target_sigaction *ka, unsigned long sp, size_t frame_size) { - if ((ka->sa_flags & TARGET_SA_ONSTACK) && (sas_ss_flags(sp) == 0)) { - sp = target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; - } + sp = target_sigsp(sp, ka); return (sp - frame_size) & -8ul; } @@ -238,12 +236,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, /* Create the ucontext. */ __put_user(0, &frame->uc.tuc_flags); __put_user(0, (unsigned long *)&frame->uc.tuc_link); - __put_user((unsigned long)target_sigaltstack_used.ss_sp, - &frame->uc.tuc_stack.ss_sp); - __put_user(sas_ss_flags(regs->gregs[15]), - &frame->uc.tuc_stack.ss_flags); - __put_user(target_sigaltstack_used.ss_size, - &frame->uc.tuc_stack.ss_size); + target_save_altstack(&frame->uc.tuc_stack, regs); setup_sigcontext(&frame->uc.tuc_mcontext, regs, set->sig[0]); for(i = 0; i < TARGET_NSIG_WORDS; i++) { diff --git a/linux-user/signal-common.h b/linux-user/signal-common.h index fbb8d4365c..51030a9306 100644 --- a/linux-user/signal-common.h +++ b/linux-user/signal-common.h @@ -21,17 +21,10 @@ #define SIGNAL_COMMON_H extern struct target_sigaltstack target_sigaltstack_used; -static inline int on_sig_stack(unsigned long sp) -{ - return (sp - target_sigaltstack_used.ss_sp - < target_sigaltstack_used.ss_size); -} - -static inline int sas_ss_flags(unsigned long sp) -{ - return (target_sigaltstack_used.ss_size == 0 ? SS_DISABLE - : on_sig_stack(sp) ? SS_ONSTACK : 0); -} +int on_sig_stack(unsigned long sp); +int sas_ss_flags(unsigned long sp); +abi_ulong target_sigsp(abi_ulong sp, struct target_sigaction *ka); +void target_save_altstack(target_stack_t *uss, CPUArchState *env); static inline void target_sigemptyset(target_sigset_t *set) { diff --git a/linux-user/signal.c b/linux-user/signal.c index a3022c2f04..01de433e3a 100644 --- a/linux-user/signal.c +++ b/linux-user/signal.c @@ -249,6 +249,38 @@ void set_sigmask(const sigset_t *set) } #endif +/* sigaltstack management */ + +int on_sig_stack(unsigned long sp) +{ + return (sp - target_sigaltstack_used.ss_sp + < target_sigaltstack_used.ss_size); +} + +int sas_ss_flags(unsigned long sp) +{ + return (target_sigaltstack_used.ss_size == 0 ? SS_DISABLE + : on_sig_stack(sp) ? SS_ONSTACK : 0); +} + +abi_ulong target_sigsp(abi_ulong sp, struct target_sigaction *ka) +{ + /* + * This is the X/Open sanctioned signal stack switching. + */ + if ((ka->sa_flags & TARGET_SA_ONSTACK) && !sas_ss_flags(sp)) { + return target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; + } + return sp; +} + +void target_save_altstack(target_stack_t *uss, CPUArchState *env) +{ + __put_user(target_sigaltstack_used.ss_sp, &uss->ss_sp); + __put_user(sas_ss_flags(get_sp_from_cpustate(env)), &uss->ss_flags); + __put_user(target_sigaltstack_used.ss_size, &uss->ss_size); +} + /* siginfo conversion */ static inline void host_to_target_siginfo_noswap(target_siginfo_t *tinfo, diff --git a/linux-user/sparc/signal.c b/linux-user/sparc/signal.c index c823e61cee..45e922f328 100644 --- a/linux-user/sparc/signal.c +++ b/linux-user/sparc/signal.c @@ -123,18 +123,28 @@ static inline abi_ulong get_sigframe(struct target_sigaction *sa, CPUSPARCState *env, unsigned long framesize) { - abi_ulong sp; + abi_ulong sp = get_sp_from_cpustate(env); - sp = env->regwptr[UREG_FP]; + /* + * If we are on the alternate signal stack and would overflow it, don't. + * Return an always-bogus address instead so we will die with SIGSEGV. + */ + if (on_sig_stack(sp) && !likely(on_sig_stack(sp - framesize))) { + return -1; + } /* This is the X/Open sanctioned signal stack switching. */ - if (sa->sa_flags & TARGET_SA_ONSTACK) { - if (!on_sig_stack(sp) - && !((target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size) & 7)) { - sp = target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; - } - } - return sp - framesize; + sp = target_sigsp(sp, sa) - framesize; + + /* Always align the stack frame. This handles two cases. First, + * sigaltstack need not be mindful of platform specific stack + * alignment. Second, if we took this signal because the stack + * is not aligned properly, we'd like to take the signal cleanly + * and report that. + */ + sp &= ~15UL; + + return sp; } static int diff --git a/linux-user/syscall.c b/linux-user/syscall.c index 404be44ad5..e4825747f9 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -6600,10 +6600,10 @@ typedef abi_long from_flock64_fn(struct flock64 *fl, abi_ulong target_addr); typedef abi_long to_flock64_fn(abi_ulong target_addr, const struct flock64 *fl); #if defined(TARGET_ARM) && TARGET_ABI_BITS == 32 -static inline abi_long copy_from_user_eabi_flock64(struct flock64 *fl, +static inline abi_long copy_from_user_oabi_flock64(struct flock64 *fl, abi_ulong target_flock_addr) { - struct target_eabi_flock64 *target_fl; + struct target_oabi_flock64 *target_fl; short l_type; if (!lock_user_struct(VERIFY_READ, target_fl, target_flock_addr, 1)) { @@ -6620,10 +6620,10 @@ static inline abi_long copy_from_user_eabi_flock64(struct flock64 *fl, return 0; } -static inline abi_long copy_to_user_eabi_flock64(abi_ulong target_flock_addr, +static inline abi_long copy_to_user_oabi_flock64(abi_ulong target_flock_addr, const struct flock64 *fl) { - struct target_eabi_flock64 *target_fl; + struct target_oabi_flock64 *target_fl; short l_type; if (!lock_user_struct(VERIFY_WRITE, target_fl, target_flock_addr, 0)) { @@ -11629,9 +11629,9 @@ abi_long do_syscall(void *cpu_env, int num, abi_long arg1, to_flock64_fn *copyto = copy_to_user_flock64; #ifdef TARGET_ARM - if (((CPUARMState *)cpu_env)->eabi) { - copyfrom = copy_from_user_eabi_flock64; - copyto = copy_to_user_eabi_flock64; + if (!((CPUARMState *)cpu_env)->eabi) { + copyfrom = copy_from_user_oabi_flock64; + copyto = copy_to_user_oabi_flock64; } #endif diff --git a/linux-user/syscall_defs.h b/linux-user/syscall_defs.h index 23f5bccf0e..361bb83a29 100644 --- a/linux-user/syscall_defs.h +++ b/linux-user/syscall_defs.h @@ -2649,29 +2649,12 @@ struct target_flock { }; struct target_flock64 { - short l_type; - short l_whence; -#if defined(TARGET_PPC) || defined(TARGET_X86_64) || defined(TARGET_MIPS) \ - || defined(TARGET_SPARC) || defined(TARGET_HPPA) \ - || defined(TARGET_MICROBLAZE) || defined(TARGET_TILEGX) \ - || defined(TARGET_XTENSA) - int __pad; -#endif - abi_llong l_start; - abi_llong l_len; - int l_pid; -} QEMU_PACKED; - -#ifdef TARGET_ARM -struct target_eabi_flock64 { - short l_type; - short l_whence; - int __pad; + abi_short l_type; + abi_short l_whence; abi_llong l_start; abi_llong l_len; - int l_pid; -} QEMU_PACKED; -#endif + abi_int l_pid; +}; struct target_f_owner_ex { int type; /* Owner type of ID. */ diff --git a/linux-user/tilegx/signal.c b/linux-user/tilegx/signal.c index 8f54f54f95..d0ed3de569 100644 --- a/linux-user/tilegx/signal.c +++ b/linux-user/tilegx/signal.c @@ -86,17 +86,13 @@ static void restore_sigcontext(CPUTLGState *env, struct target_sigcontext *sc) static abi_ulong get_sigframe(struct target_sigaction *ka, CPUArchState *env, size_t frame_size) { - unsigned long sp = env->regs[TILEGX_R_SP]; + unsigned long sp = get_sp_from_cpustate(env); if (on_sig_stack(sp) && !likely(on_sig_stack(sp - frame_size))) { return -1UL; } - if ((ka->sa_flags & SA_ONSTACK) && !sas_ss_flags(sp)) { - sp = target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; - } - - sp -= frame_size; + sp = target_sigsp(sp, ka) - frame_size; sp &= -16UL; return sp; } @@ -127,10 +123,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, /* Create the ucontext. */ __put_user(0, &frame->uc.tuc_flags); __put_user(0, &frame->uc.tuc_link); - __put_user(target_sigaltstack_used.ss_sp, &frame->uc.tuc_stack.ss_sp); - __put_user(sas_ss_flags(env->regs[TILEGX_R_SP]), - &frame->uc.tuc_stack.ss_flags); - __put_user(target_sigaltstack_used.ss_size, &frame->uc.tuc_stack.ss_size); + target_save_altstack(&frame->uc.tuc_stack, env); setup_sigcontext(&frame->uc.tuc_mcontext, env, info->si_signo); if (ka->sa_flags & TARGET_SA_RESTORER) { diff --git a/linux-user/xtensa/signal.c b/linux-user/xtensa/signal.c index 1e98910c1b..3e483efc61 100644 --- a/linux-user/xtensa/signal.c +++ b/linux-user/xtensa/signal.c @@ -55,12 +55,10 @@ static abi_ulong get_sigframe(struct target_sigaction *sa, CPUXtensaState *env, unsigned long framesize) { - abi_ulong sp = env->regs[1]; + abi_ulong sp; + + sp = target_sigsp(get_sp_from_cpustate(env), sa); - /* This is the X/Open sanctioned signal stack switching. */ - if ((sa->sa_flags & TARGET_SA_ONSTACK) != 0 && !sas_ss_flags(sp)) { - sp = target_sigaltstack_used.ss_sp + target_sigaltstack_used.ss_size; - } return (sp - framesize) & -16; } @@ -152,12 +150,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, __put_user(0, &frame->uc.tuc_flags); __put_user(0, &frame->uc.tuc_link); - __put_user(target_sigaltstack_used.ss_sp, - &frame->uc.tuc_stack.ss_sp); - __put_user(sas_ss_flags(env->regs[1]), - &frame->uc.tuc_stack.ss_flags); - __put_user(target_sigaltstack_used.ss_size, - &frame->uc.tuc_stack.ss_size); + target_save_altstack(&frame->uc.tuc_stack, env); if (!setup_sigcontext(frame, env)) { unlock_user_struct(frame, frame_addr, 0); goto give_sigsegv; diff --git a/pc-bios/s390-ccw.img b/pc-bios/s390-ccw.img Binary files differindex fdd6809c70..450a076dc0 100644 --- a/pc-bios/s390-ccw.img +++ b/pc-bios/s390-ccw.img diff --git a/pc-bios/s390-ccw/Makefile b/pc-bios/s390-ccw/Makefile index 1712c2d95d..439e3cc9c9 100644 --- a/pc-bios/s390-ccw/Makefile +++ b/pc-bios/s390-ccw/Makefile @@ -9,7 +9,9 @@ $(call set-vpath, $(SRC_PATH)/pc-bios/s390-ccw) .PHONY : all clean build-all -OBJECTS = start.o main.o bootmap.o sclp.o virtio.o virtio-scsi.o virtio-blkdev.o libc.o menu.o +OBJECTS = start.o main.o bootmap.o jump2ipl.o sclp.o menu.o \ + virtio.o virtio-scsi.o virtio-blkdev.o libc.o + QEMU_CFLAGS := $(filter -W%, $(QEMU_CFLAGS)) QEMU_CFLAGS += -ffreestanding -fno-delete-null-pointer-checks -msoft-float QEMU_CFLAGS += -march=z900 -fPIE -fno-strict-aliasing diff --git a/pc-bios/s390-ccw/bootmap.c b/pc-bios/s390-ccw/bootmap.c index 9287b7a70f..7aef65ab67 100644 --- a/pc-bios/s390-ccw/bootmap.c +++ b/pc-bios/s390-ccw/bootmap.c @@ -29,14 +29,6 @@ /* Scratch space */ static uint8_t sec[MAX_SECTOR_SIZE*4] __attribute__((__aligned__(PAGE_SIZE))); -typedef struct ResetInfo { - uint32_t ipl_mask; - uint32_t ipl_addr; - uint32_t ipl_continue; -} ResetInfo; - -static ResetInfo save; - const uint8_t el_torito_magic[] = "EL TORITO SPECIFICATION" "\0\0\0\0\0\0\0\0\0\0\0\0\0\0\0"; @@ -57,53 +49,6 @@ static inline bool is_iso_vd_valid(IsoVolDesc *vd) vd->type <= VOL_DESC_TYPE_PARTITION; } -static void jump_to_IPL_2(void) -{ - ResetInfo *current = 0; - - void (*ipl)(void) = (void *) (uint64_t) current->ipl_continue; - *current = save; - ipl(); /* should not return */ -} - -static void jump_to_IPL_code(uint64_t address) -{ - /* store the subsystem information _after_ the bootmap was loaded */ - write_subsystem_identification(); - - /* prevent unknown IPL types in the guest */ - if (iplb.pbt == S390_IPL_TYPE_QEMU_SCSI) { - iplb.pbt = S390_IPL_TYPE_CCW; - set_iplb(&iplb); - } - - /* - * The IPL PSW is at address 0. We also must not overwrite the - * content of non-BIOS memory after we loaded the guest, so we - * save the original content and restore it in jump_to_IPL_2. - */ - ResetInfo *current = 0; - - save = *current; - current->ipl_addr = (uint32_t) (uint64_t) &jump_to_IPL_2; - current->ipl_continue = address & 0x7fffffff; - - debug_print_int("set IPL addr to", current->ipl_continue); - - /* Ensure the guest output starts fresh */ - sclp_print("\n"); - - /* - * HACK ALERT. - * We use the load normal reset to keep r15 unchanged. jump_to_IPL_2 - * can then use r15 as its stack pointer. - */ - asm volatile("lghi 1,1\n\t" - "diag 1,1,0x308\n\t" - : : : "1", "memory"); - panic("\n! IPL returns !\n"); -} - /*********************************************************************** * IPL an ECKD DASD (CDL or LDL/CMS format) */ @@ -297,7 +242,7 @@ static void run_eckd_boot_script(block_number_t bmt_block_nr, } debug_print_int("loadparm", loadparm); - IPL_assert(loadparm <= MAX_TABLE_ENTRIES, "loadparm value greater than" + IPL_assert(loadparm < MAX_BOOT_ENTRIES, "loadparm value greater than" " maximum number of boot entries allowed"); memset(sec, FREE_SPACE_FILLER, sizeof(sec)); @@ -565,6 +510,8 @@ static void ipl_scsi(void) int program_table_entries = 0; BootMapTable *prog_table = (void *)sec; unsigned int loadparm = get_loadparm_index(); + bool valid_entries[MAX_BOOT_ENTRIES] = {false}; + size_t i; /* Grab the MBR */ memset(sec, FREE_SPACE_FILLER, sizeof(sec)); @@ -585,22 +532,22 @@ static void ipl_scsi(void) read_block(mbr->pt.blockno, sec, "Error reading Program Table"); IPL_assert(magic_match(sec, ZIPL_MAGIC), "No zIPL magic in PT"); - while (program_table_entries <= MAX_TABLE_ENTRIES) { - if (!prog_table->entry[program_table_entries].scsi.blockno) { - break; + for (i = 0; i < MAX_BOOT_ENTRIES; i++) { + if (prog_table->entry[i].scsi.blockno) { + valid_entries[i] = true; + program_table_entries++; } - program_table_entries++; } debug_print_int("program table entries", program_table_entries); IPL_assert(program_table_entries != 0, "Empty Program Table"); if (menu_is_enabled_enum()) { - loadparm = menu_get_enum_boot_index(program_table_entries); + loadparm = menu_get_enum_boot_index(valid_entries); } debug_print_int("loadparm", loadparm); - IPL_assert(loadparm <= MAX_TABLE_ENTRIES, "loadparm value greater than" + IPL_assert(loadparm < MAX_BOOT_ENTRIES, "loadparm value greater than" " maximum number of boot entries allowed"); zipl_run(&prog_table->entry[loadparm].scsi); /* no return */ @@ -727,13 +674,7 @@ static void load_iso_bc_entry(IsoBcSection *load) (void *)((uint64_t)bswap16(s.load_segment)), blks_to_load); - /* Trying to get PSW at zero address */ - if (*((uint64_t *)0) & IPL_PSW_MASK) { - jump_to_IPL_code((*((uint64_t *)0)) & 0x7fffffff); - } - - /* Try default linux start address */ - jump_to_IPL_code(KERN_IMAGE_START); + jump_to_low_kernel(); } static uint32_t find_iso_bc(void) diff --git a/pc-bios/s390-ccw/bootmap.h b/pc-bios/s390-ccw/bootmap.h index 07eb600b00..a085212077 100644 --- a/pc-bios/s390-ccw/bootmap.h +++ b/pc-bios/s390-ccw/bootmap.h @@ -57,8 +57,6 @@ typedef union BootMapPointer { ExtEckdBlockPtr xeckd; } __attribute__ ((packed)) BootMapPointer; -#define MAX_TABLE_ENTRIES 30 - /* aka Program Table */ typedef struct BootMapTable { uint8_t magic[4]; @@ -355,10 +353,6 @@ static inline uint32_t iso_733_to_u32(uint64_t x) #define ISO_SECTOR_SIZE 2048 /* El Torito specifies boot image size in 512 byte blocks */ #define ET_SECTOR_SHIFT 2 -#define KERN_IMAGE_START 0x010000UL -#define PSW_MASK_64 0x0000000100000000ULL -#define PSW_MASK_32 0x0000000080000000ULL -#define IPL_PSW_MASK (PSW_MASK_32 | PSW_MASK_64) #define ISO_PRIMARY_VD_SECTOR 16 diff --git a/pc-bios/s390-ccw/iplb.h b/pc-bios/s390-ccw/iplb.h index 5357a36d51..ded20c834e 100644 --- a/pc-bios/s390-ccw/iplb.h +++ b/pc-bios/s390-ccw/iplb.h @@ -101,10 +101,11 @@ static inline bool manage_iplb(IplParameterBlock *iplb, bool store) { register unsigned long addr asm("0") = (unsigned long) iplb; register unsigned long rc asm("1") = 0; + unsigned long subcode = store ? 6 : 5; asm volatile ("diag %0,%2,0x308\n" : "+d" (addr), "+d" (rc) - : "d" (store ? 6 : 5) + : "d" (subcode) : "memory", "cc"); return rc == 0x01; } diff --git a/pc-bios/s390-ccw/jump2ipl.c b/pc-bios/s390-ccw/jump2ipl.c new file mode 100644 index 0000000000..266f1502b9 --- /dev/null +++ b/pc-bios/s390-ccw/jump2ipl.c @@ -0,0 +1,91 @@ +/* + * QEMU s390-ccw firmware - jump to IPL code + * + * This work is licensed under the terms of the GNU GPL, version 2 or (at + * your option) any later version. See the COPYING file in the top-level + * directory. + */ + +#include "libc.h" +#include "s390-ccw.h" + +#define KERN_IMAGE_START 0x010000UL +#define PSW_MASK_64 0x0000000100000000ULL +#define PSW_MASK_32 0x0000000080000000ULL +#define IPL_PSW_MASK (PSW_MASK_32 | PSW_MASK_64) + +typedef struct ResetInfo { + uint32_t ipl_mask; + uint32_t ipl_addr; + uint32_t ipl_continue; +} ResetInfo; + +static ResetInfo save; + +static void jump_to_IPL_2(void) +{ + ResetInfo *current = 0; + + void (*ipl)(void) = (void *) (uint64_t) current->ipl_continue; + *current = save; + ipl(); /* should not return */ +} + +void jump_to_IPL_code(uint64_t address) +{ + /* store the subsystem information _after_ the bootmap was loaded */ + write_subsystem_identification(); + + /* prevent unknown IPL types in the guest */ + if (iplb.pbt == S390_IPL_TYPE_QEMU_SCSI) { + iplb.pbt = S390_IPL_TYPE_CCW; + set_iplb(&iplb); + } + + /* + * The IPL PSW is at address 0. We also must not overwrite the + * content of non-BIOS memory after we loaded the guest, so we + * save the original content and restore it in jump_to_IPL_2. + */ + ResetInfo *current = 0; + + save = *current; + current->ipl_addr = (uint32_t) (uint64_t) &jump_to_IPL_2; + current->ipl_continue = address & 0x7fffffff; + + debug_print_int("set IPL addr to", current->ipl_continue); + + /* Ensure the guest output starts fresh */ + sclp_print("\n"); + + /* + * HACK ALERT. + * We use the load normal reset to keep r15 unchanged. jump_to_IPL_2 + * can then use r15 as its stack pointer. + */ + asm volatile("lghi 1,1\n\t" + "diag 1,1,0x308\n\t" + : : : "1", "memory"); + panic("\n! IPL returns !\n"); +} + +void jump_to_low_kernel(void) +{ + /* + * If it looks like a Linux binary, i.e. there is the "S390EP" magic from + * arch/s390/kernel/head.S here, then let's jump to the well-known Linux + * kernel start address (when jumping to the PSW-at-zero address instead, + * the kernel startup code fails when we booted from a network device). + */ + if (!memcmp((char *)0x10008, "S390EP", 6)) { + jump_to_IPL_code(KERN_IMAGE_START); + } + + /* Trying to get PSW at zero address */ + if (*((uint64_t *)0) & IPL_PSW_MASK) { + jump_to_IPL_code((*((uint64_t *)0)) & 0x7fffffff); + } + + /* No other option left, so use the Linux kernel start address */ + jump_to_IPL_code(KERN_IMAGE_START); +} diff --git a/pc-bios/s390-ccw/libc.c b/pc-bios/s390-ccw/libc.c index 38ea77d7aa..a786566c4c 100644 --- a/pc-bios/s390-ccw/libc.c +++ b/pc-bios/s390-ccw/libc.c @@ -63,7 +63,7 @@ uint64_t atoui(const char *str) */ char *uitoa(uint64_t num, char *str, size_t len) { - size_t num_idx = 1; /* account for NUL */ + long num_idx = 1; /* account for NUL */ uint64_t tmp = num; IPL_assert(str != NULL, "uitoa: no space allocated to store string"); diff --git a/pc-bios/s390-ccw/libc.h b/pc-bios/s390-ccw/libc.h index 63ece70c6b..818517ff5d 100644 --- a/pc-bios/s390-ccw/libc.h +++ b/pc-bios/s390-ccw/libc.h @@ -12,7 +12,7 @@ #ifndef S390_CCW_LIBC_H #define S390_CCW_LIBC_H -typedef long size_t; +typedef unsigned long size_t; typedef int bool; typedef unsigned char uint8_t; typedef unsigned short uint16_t; diff --git a/pc-bios/s390-ccw/main.c b/pc-bios/s390-ccw/main.c index 9d9f8cf4d3..26f9adf84a 100644 --- a/pc-bios/s390-ccw/main.c +++ b/pc-bios/s390-ccw/main.c @@ -15,11 +15,11 @@ char stack[PAGE_SIZE * 8] __attribute__((__aligned__(PAGE_SIZE))); static SubChannelId blk_schid = { .one = 1 }; IplParameterBlock iplb __attribute__((__aligned__(PAGE_SIZE))); -static char loadparm[8] = { 0, 0, 0, 0, 0, 0, 0, 0 }; +static char loadparm_str[9] = { 0, 0, 0, 0, 0, 0, 0, 0, 0 }; QemuIplParameters qipl; #define LOADPARM_PROMPT "PROMPT " -#define LOADPARM_EMPTY "........" +#define LOADPARM_EMPTY " " #define BOOT_MENU_FLAG_MASK (QIPL_FLAG_BM_OPTS_CMD | QIPL_FLAG_BM_OPTS_ZIPL) /* @@ -45,7 +45,7 @@ void panic(const char *string) unsigned int get_loadparm_index(void) { - return atoui(loadparm); + return atoui(loadparm_str); } static bool find_dev(Schib *schib, int dev_no) @@ -80,13 +80,13 @@ static bool find_dev(Schib *schib, int dev_no) static void menu_setup(void) { - if (memcmp(loadparm, LOADPARM_PROMPT, 8) == 0) { + if (memcmp(loadparm_str, LOADPARM_PROMPT, 8) == 0) { menu_set_parms(QIPL_FLAG_BM_OPTS_CMD, 0); return; } /* If loadparm was set to any other value, then do not enable menu */ - if (memcmp(loadparm, LOADPARM_EMPTY, 8) != 0) { + if (memcmp(loadparm_str, LOADPARM_EMPTY, 8) != 0) { return; } @@ -116,8 +116,8 @@ static void virtio_setup(void) */ enable_mss_facility(); - sclp_get_loadparm_ascii(loadparm); - memcpy(ldp + 10, loadparm, 8); + sclp_get_loadparm_ascii(loadparm_str); + memcpy(ldp + 10, loadparm_str, 8); sclp_print(ldp); memcpy(&qipl, early_qipl, sizeof(QemuIplParameters)); diff --git a/pc-bios/s390-ccw/menu.c b/pc-bios/s390-ccw/menu.c index 96eec81e84..82a4ae6315 100644 --- a/pc-bios/s390-ccw/menu.c +++ b/pc-bios/s390-ccw/menu.c @@ -158,7 +158,7 @@ static void boot_menu_prompt(bool retry) } } -static int get_boot_index(int entries) +static int get_boot_index(bool *valid_entries) { int boot_index; bool retry = false; @@ -168,7 +168,8 @@ static int get_boot_index(int entries) boot_menu_prompt(retry); boot_index = get_index(); retry = true; - } while (boot_index < 0 || boot_index >= entries); + } while (boot_index < 0 || boot_index >= MAX_BOOT_ENTRIES || + !valid_entries[boot_index]); sclp_print("\nBooting entry #"); sclp_print(uitoa(boot_index, tmp, sizeof(tmp))); @@ -176,7 +177,8 @@ static int get_boot_index(int entries) return boot_index; } -static void zipl_println(const char *data, size_t len) +/* Returns the entry number that was printed */ +static int zipl_print_entry(const char *data, size_t len) { char buf[len + 2]; @@ -185,12 +187,15 @@ static void zipl_println(const char *data, size_t len) buf[len + 1] = '\0'; sclp_print(buf); + + return buf[0] == ' ' ? atoui(buf + 1) : atoui(buf); } int menu_get_zipl_boot_index(const char *menu_data) { size_t len; - int entries; + int entry; + bool valid_entries[MAX_BOOT_ENTRIES] = {false}; uint16_t zipl_flag = *(uint16_t *)(menu_data - ZIPL_FLAG_OFFSET); uint16_t zipl_timeout = *(uint16_t *)(menu_data - ZIPL_TIMEOUT_OFFSET); @@ -202,34 +207,51 @@ int menu_get_zipl_boot_index(const char *menu_data) timeout = zipl_timeout * 1000; } - /* Print and count all menu items, including the banner */ - for (entries = 0; *menu_data; entries++) { + /* Print banner */ + sclp_print("s390-ccw zIPL Boot Menu\n\n"); + menu_data += strlen(menu_data) + 1; + + /* Print entries */ + while (*menu_data) { len = strlen(menu_data); - zipl_println(menu_data, len); + entry = zipl_print_entry(menu_data, len); menu_data += len + 1; - if (entries < 2) { + valid_entries[entry] = true; + + if (entry == 0) { sclp_print("\n"); } } sclp_print("\n"); - return get_boot_index(entries - 1); /* subtract 1 to exclude banner */ + return get_boot_index(valid_entries); } - -int menu_get_enum_boot_index(int entries) +int menu_get_enum_boot_index(bool *valid_entries) { - char tmp[4]; + char tmp[3]; + int i; - sclp_print("s390x Enumerated Boot Menu.\n\n"); + sclp_print("s390-ccw Enumerated Boot Menu.\n\n"); - sclp_print(uitoa(entries, tmp, sizeof(tmp))); - sclp_print(" entries detected. Select from boot index 0 to "); - sclp_print(uitoa(entries - 1, tmp, sizeof(tmp))); - sclp_print(".\n\n"); + for (i = 0; i < MAX_BOOT_ENTRIES; i++) { + if (valid_entries[i]) { + if (i < 10) { + sclp_print(" "); + } + sclp_print("["); + sclp_print(uitoa(i, tmp, sizeof(tmp))); + sclp_print("]"); + if (i == 0) { + sclp_print(" default\n"); + } + sclp_print("\n"); + } + } - return get_boot_index(entries); + sclp_print("\n"); + return get_boot_index(valid_entries); } void menu_set_parms(uint8_t boot_menu_flag, uint32_t boot_menu_timeout) diff --git a/pc-bios/s390-ccw/netboot.mak b/pc-bios/s390-ccw/netboot.mak index a25d238144..4f64128c6c 100644 --- a/pc-bios/s390-ccw/netboot.mak +++ b/pc-bios/s390-ccw/netboot.mak @@ -1,7 +1,8 @@ SLOF_DIR := $(SRC_PATH)/roms/SLOF -NETOBJS := start.o sclp.o virtio.o virtio-net.o netmain.o libnet.a libc.a +NETOBJS := start.o sclp.o virtio.o virtio-net.o jump2ipl.o netmain.o \ + libnet.a libc.a LIBC_INC := -nostdinc -I$(SLOF_DIR)/lib/libc/include LIBNET_INC := -I$(SLOF_DIR)/lib/libnet diff --git a/pc-bios/s390-ccw/netmain.c b/pc-bios/s390-ccw/netmain.c index d86d46b03f..600024155b 100644 --- a/pc-bios/s390-ccw/netmain.c +++ b/pc-bios/s390-ccw/netmain.c @@ -39,8 +39,12 @@ extern char _start[]; +#define KERNEL_ADDR ((void *)0L) +#define KERNEL_MAX_SIZE ((long)_start) + char stack[PAGE_SIZE * 8] __attribute__((aligned(PAGE_SIZE))); IplParameterBlock iplb __attribute__((aligned(PAGE_SIZE))); +static char cfgbuf[2048]; static SubChannelId net_schid = { .one = 1 }; static int ip_version = 4; @@ -128,17 +132,23 @@ static void seed_rng(uint8_t mac[]) srand(seed); } -static int tftp_load(filename_ip_t *fnip, void *buffer, int len, - unsigned int retries, int ip_vers) +static int tftp_load(filename_ip_t *fnip, void *buffer, int len) { tftp_err_t tftp_err; int rc; - rc = tftp(fnip, buffer, len, retries, &tftp_err, 1, 1428, ip_vers); + rc = tftp(fnip, buffer, len, DEFAULT_TFTP_RETRIES, &tftp_err, 1, 1428, + ip_version); - if (rc > 0) { - printf(" TFTP: Received %s (%d KBytes)\n", fnip->filename, - rc / 1024); + if (rc < 0) { + /* Make sure that error messages are put into a new line */ + printf("\n "); + } + + if (rc > 1024) { + printf(" TFTP: Received %s (%d KBytes)\n", fnip->filename, rc / 1024); + } else if (rc > 0) { + printf(" TFTP: Received %s (%d Bytes)\n", fnip->filename, rc); } else if (rc == -1) { puts("unknown TFTP error"); } else if (rc == -2) { @@ -199,20 +209,19 @@ static int tftp_load(filename_ip_t *fnip, void *buffer, int len, return rc; } -static int net_load(char *buffer, int len) +static int net_init(filename_ip_t *fn_ip) { - filename_ip_t fn_ip; uint8_t mac[6]; int rc; - memset(&fn_ip, 0, sizeof(filename_ip_t)); + memset(fn_ip, 0, sizeof(filename_ip_t)); rc = virtio_net_init(mac); if (rc < 0) { puts("Could not initialize network device"); return -101; } - fn_ip.fd = rc; + fn_ip->fd = rc; printf(" Using MAC address: %02x:%02x:%02x:%02x:%02x:%02x\n", mac[0], mac[1], mac[2], mac[3], mac[4], mac[5]); @@ -220,10 +229,10 @@ static int net_load(char *buffer, int len) set_mac_address(mac); /* init ethernet layer */ seed_rng(mac); - rc = dhcp(&fn_ip, DEFAULT_BOOT_RETRIES); + rc = dhcp(fn_ip, DEFAULT_BOOT_RETRIES); if (rc >= 0) { if (ip_version == 4) { - set_ipv4_address(fn_ip.own_ip); + set_ipv4_address(fn_ip->own_ip); } } else { puts("Could not get IP address"); @@ -232,18 +241,18 @@ static int net_load(char *buffer, int len) if (ip_version == 4) { printf(" Using IPv4 address: %d.%d.%d.%d\n", - (fn_ip.own_ip >> 24) & 0xFF, (fn_ip.own_ip >> 16) & 0xFF, - (fn_ip.own_ip >> 8) & 0xFF, fn_ip.own_ip & 0xFF); + (fn_ip->own_ip >> 24) & 0xFF, (fn_ip->own_ip >> 16) & 0xFF, + (fn_ip->own_ip >> 8) & 0xFF, fn_ip->own_ip & 0xFF); } else if (ip_version == 6) { char ip6_str[40]; - ipv6_to_str(fn_ip.own_ip6.addr, ip6_str); + ipv6_to_str(fn_ip->own_ip6.addr, ip6_str); printf(" Using IPv6 address: %s\n", ip6_str); } if (rc == -2) { printf("ARP request to TFTP server (%d.%d.%d.%d) failed\n", - (fn_ip.server_ip >> 24) & 0xFF, (fn_ip.server_ip >> 16) & 0xFF, - (fn_ip.server_ip >> 8) & 0xFF, fn_ip.server_ip & 0xFF); + (fn_ip->server_ip >> 24) & 0xFF, (fn_ip->server_ip >> 16) & 0xFF, + (fn_ip->server_ip >> 8) & 0xFF, fn_ip->server_ip & 0xFF); return -102; } if (rc == -4 || rc == -3) { @@ -251,28 +260,108 @@ static int net_load(char *buffer, int len) return -107; } + printf(" Using TFTP server: "); if (ip_version == 4) { - printf(" Requesting file \"%s\" via TFTP from %d.%d.%d.%d\n", - fn_ip.filename, - (fn_ip.server_ip >> 24) & 0xFF, (fn_ip.server_ip >> 16) & 0xFF, - (fn_ip.server_ip >> 8) & 0xFF, fn_ip.server_ip & 0xFF); + printf("%d.%d.%d.%d\n", + (fn_ip->server_ip >> 24) & 0xFF, (fn_ip->server_ip >> 16) & 0xFF, + (fn_ip->server_ip >> 8) & 0xFF, fn_ip->server_ip & 0xFF); } else if (ip_version == 6) { char ip6_str[40]; - printf(" Requesting file \"%s\" via TFTP from ", fn_ip.filename); - ipv6_to_str(fn_ip.server_ip6.addr, ip6_str); + ipv6_to_str(fn_ip->server_ip6.addr, ip6_str); printf("%s\n", ip6_str); } - /* Do the TFTP load and print error message if necessary */ - rc = tftp_load(&fn_ip, buffer, len, DEFAULT_TFTP_RETRIES, ip_version); + if (strlen((char *)fn_ip->filename) > 0) { + printf(" Bootfile name: '%s'\n", fn_ip->filename); + } + return rc; +} + +static void net_release(filename_ip_t *fn_ip) +{ if (ip_version == 4) { - dhcp_send_release(fn_ip.fd); + dhcp_send_release(fn_ip->fd); + } +} + +/** + * Load via information from a .INS file (which can be found on CD-ROMs + * for example) + */ +static int handle_ins_cfg(filename_ip_t *fn_ip, char *cfg, int cfgsize) +{ + char *ptr; + int rc = -1, llen; + void *destaddr; + char *insbuf = cfg; + + ptr = strchr(insbuf, '\n'); + if (!ptr) { + puts("Does not seem to be a valid .INS file"); + return -1; + } + + *ptr = 0; + printf("\nParsing .INS file:\n %s\n", &insbuf[2]); + + insbuf = ptr + 1; + while (*insbuf && insbuf < cfg + cfgsize) { + ptr = strchr(insbuf, '\n'); + if (ptr) { + *ptr = 0; + } + llen = strlen(insbuf); + if (!llen) { + insbuf = ptr + 1; + continue; + } + ptr = strchr(insbuf, ' '); + if (!ptr) { + puts("Missing space separator in .INS file"); + return -1; + } + *ptr = 0; + strncpy((char *)fn_ip->filename, insbuf, sizeof(fn_ip->filename)); + destaddr = (char *)atol(ptr + 1); + rc = tftp_load(fn_ip, destaddr, (long)_start - (long)destaddr); + if (rc <= 0) { + break; + } + insbuf += llen + 1; } return rc; } +static int net_try_direct_tftp_load(filename_ip_t *fn_ip) +{ + int rc; + void *loadaddr = (void *)0x2000; /* Load right after the low-core */ + + rc = tftp_load(fn_ip, loadaddr, KERNEL_MAX_SIZE - (long)loadaddr); + if (rc < 0) { + return rc; + } else if (rc < 8) { + printf("'%s' is too small (%i bytes only).\n", fn_ip->filename, rc); + return -1; + } + + /* Check whether it is a configuration file instead of a kernel */ + if (rc < sizeof(cfgbuf) - 1) { + memcpy(cfgbuf, loadaddr, rc); + cfgbuf[rc] = 0; /* Make sure that it is NUL-terminated */ + if (!strncmp("* ", cfgbuf, 2)) { + return handle_ins_cfg(fn_ip, cfgbuf, rc); + } + } + + /* Move kernel to right location */ + memmove(KERNEL_ADDR, loadaddr, rc); + + return rc; +} + void panic(const char *string) { sclp_print(string); @@ -281,6 +370,15 @@ void panic(const char *string) } } +void write_subsystem_identification(void) +{ + SubChannelId *schid = (SubChannelId *) 184; + uint32_t *zeroes = (uint32_t *) 188; + + *schid = net_schid; + *zeroes = 0; +} + static bool find_net_dev(Schib *schib, int dev_no) { int i, r; @@ -344,17 +442,29 @@ static void virtio_setup(void) void main(void) { - int rc; + filename_ip_t fn_ip; + int rc, fnlen; sclp_setup(); sclp_print("Network boot starting...\n"); virtio_setup(); - rc = net_load(NULL, (long)_start); + rc = net_init(&fn_ip); + if (rc) { + panic("Network initialization failed. Halting.\n"); + } + + fnlen = strlen((char *)fn_ip.filename); + if (fnlen > 0 && fn_ip.filename[fnlen - 1] != '/') { + rc = net_try_direct_tftp_load(&fn_ip); + } + + net_release(&fn_ip); + if (rc > 0) { sclp_print("Network loading done, starting kernel...\n"); - asm volatile (" lpsw 0(%0) " : : "r"(0) : "memory"); + jump_to_low_kernel(); } panic("Failed to load OS from network\n"); diff --git a/pc-bios/s390-ccw/s390-ccw.h b/pc-bios/s390-ccw/s390-ccw.h index fd18da22c6..9828aa233d 100644 --- a/pc-bios/s390-ccw/s390-ccw.h +++ b/pc-bios/s390-ccw/s390-ccw.h @@ -87,13 +87,19 @@ ulong get_second(void); /* bootmap.c */ void zipl_load(void); +/* jump2ipl.c */ +void jump_to_IPL_code(uint64_t address); +void jump_to_low_kernel(void); + /* menu.c */ void menu_set_parms(uint8_t boot_menu_flag, uint32_t boot_menu_timeout); int menu_get_zipl_boot_index(const char *menu_data); bool menu_is_enabled_zipl(void); -int menu_get_enum_boot_index(int entries); +int menu_get_enum_boot_index(bool *valid_entries); bool menu_is_enabled_enum(void); +#define MAX_BOOT_ENTRIES 31 + static inline void fill_hex(char *out, unsigned char val) { const char hex[] = "0123456789abcdef"; diff --git a/pc-bios/s390-netboot.img b/pc-bios/s390-netboot.img Binary files differindex 31f3d141cd..ef561efd2e 100644 --- a/pc-bios/s390-netboot.img +++ b/pc-bios/s390-netboot.img diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index 8c9e03f54d..7ccd2f460e 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -1295,6 +1295,7 @@ int ppc_cpu_handle_mmu_fault(CPUState *cpu, vaddr address, int size, int rw, #if !defined(CONFIG_USER_ONLY) void ppc_store_sdr1 (CPUPPCState *env, target_ulong value); +void ppc_store_ptcr(CPUPPCState *env, target_ulong value); #endif /* !defined(CONFIG_USER_ONLY) */ void ppc_store_msr (CPUPPCState *env, target_ulong value); @@ -1331,7 +1332,7 @@ void store_booke_tcr (CPUPPCState *env, target_ulong val); void store_booke_tsr (CPUPPCState *env, target_ulong val); void ppc_tlb_invalidate_all (CPUPPCState *env); void ppc_tlb_invalidate_one (CPUPPCState *env, target_ulong addr); -void cpu_ppc_set_papr(PowerPCCPU *cpu, PPCVirtualHypervisor *vhyp); +void cpu_ppc_set_vhyp(PowerPCCPU *cpu, PPCVirtualHypervisor *vhyp); #endif #endif @@ -1585,6 +1586,7 @@ void ppc_compat_add_property(Object *obj, const char *name, #define SPR_BOOKE_GIVOR13 (0x1BC) #define SPR_BOOKE_GIVOR14 (0x1BD) #define SPR_TIR (0x1BE) +#define SPR_PTCR (0x1D0) #define SPR_BOOKE_SPEFSCR (0x200) #define SPR_Exxx_BBEAR (0x201) #define SPR_Exxx_BBTAR (0x202) diff --git a/target/ppc/helper.h b/target/ppc/helper.h index 5b739179b8..19453c6813 100644 --- a/target/ppc/helper.h +++ b/target/ppc/helper.h @@ -709,6 +709,7 @@ DEF_HELPER_FLAGS_1(load_601_rtcu, TCG_CALL_NO_RWG, tl, env) #if !defined(CONFIG_USER_ONLY) #if defined(TARGET_PPC64) DEF_HELPER_FLAGS_1(load_purr, TCG_CALL_NO_RWG, tl, env) +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) diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c index 6de59c5b21..cbe13b18d1 100644 --- a/target/ppc/kvm.c +++ b/target/ppc/kvm.c @@ -72,7 +72,6 @@ static int cap_segstate; static int cap_booke_sregs; static int cap_ppc_smt; static int cap_ppc_smt_possible; -static int cap_ppc_rma; static int cap_spapr_tce; static int cap_spapr_tce_64; static int cap_spapr_multitce; @@ -133,7 +132,6 @@ int kvm_arch_init(MachineState *ms, KVMState *s) cap_segstate = kvm_check_extension(s, KVM_CAP_PPC_SEGSTATE); cap_booke_sregs = kvm_check_extension(s, KVM_CAP_PPC_BOOKE_SREGS); cap_ppc_smt_possible = kvm_vm_check_extension(s, KVM_CAP_PPC_SMT_POSSIBLE); - cap_ppc_rma = kvm_check_extension(s, KVM_CAP_PPC_RMA); cap_spapr_tce = kvm_check_extension(s, KVM_CAP_SPAPR_TCE); cap_spapr_tce_64 = kvm_check_extension(s, KVM_CAP_SPAPR_TCE_64); cap_spapr_multitce = kvm_check_extension(s, KVM_CAP_SPAPR_MULTITCE); @@ -2090,6 +2088,10 @@ void kvmppc_set_papr(PowerPCCPU *cpu) CPUState *cs = CPU(cpu); int ret; + if (!kvm_enabled()) { + return; + } + ret = kvm_vcpu_enable_cap(cs, KVM_CAP_PPC_PAPR, 0); if (ret) { error_report("This vCPU type or KVM version does not support PAPR"); @@ -2159,52 +2161,12 @@ void kvmppc_hint_smt_possible(Error **errp) #ifdef TARGET_PPC64 -off_t kvmppc_alloc_rma(void **rma) -{ - off_t size; - int fd; - struct kvm_allocate_rma ret; - - /* If cap_ppc_rma == 0, contiguous RMA allocation is not supported - * if cap_ppc_rma == 1, contiguous RMA allocation is supported, but - * not necessary on this hardware - * if cap_ppc_rma == 2, contiguous RMA allocation is needed on this hardware - * - * FIXME: We should allow the user to force contiguous RMA - * allocation in the cap_ppc_rma==1 case. - */ - if (cap_ppc_rma < 2) { - return 0; - } - - fd = kvm_vm_ioctl(kvm_state, KVM_ALLOCATE_RMA, &ret); - if (fd < 0) { - fprintf(stderr, "KVM: Error on KVM_ALLOCATE_RMA: %s\n", - strerror(errno)); - return -1; - } - - size = MIN(ret.rma_size, 256ul << 20); - - *rma = mmap(NULL, size, PROT_READ|PROT_WRITE, MAP_SHARED, fd, 0); - if (*rma == MAP_FAILED) { - fprintf(stderr, "KVM: Error mapping RMA: %s\n", strerror(errno)); - return -1; - }; - - return size; -} - uint64_t kvmppc_rma_size(uint64_t current_size, unsigned int hash_shift) { struct kvm_ppc_smmu_info info; long rampagesize, best_page_shift; int i; - if (cap_ppc_rma >= 2) { - return current_size; - } - /* Find the largest hardware supported page size that's less than * or equal to the (logical) backing page size of guest RAM */ kvm_get_smmu_info(POWERPC_CPU(first_cpu), &info); diff --git a/target/ppc/kvm_ppc.h b/target/ppc/kvm_ppc.h index 4d2789eef6..e2840e1d33 100644 --- a/target/ppc/kvm_ppc.h +++ b/target/ppc/kvm_ppc.h @@ -37,7 +37,6 @@ target_ulong kvmppc_configure_v3_mmu(PowerPCCPU *cpu, bool radix, bool gtse, uint64_t proc_tbl); #ifndef CONFIG_USER_ONLY -off_t kvmppc_alloc_rma(void **rma); bool kvmppc_spapr_use_multitce(void); int kvmppc_spapr_enable_inkernel_multitce(void); void *kvmppc_create_spapr_tce(uint32_t liobn, uint32_t page_shift, @@ -188,11 +187,6 @@ static inline target_ulong kvmppc_configure_v3_mmu(PowerPCCPU *cpu, } #ifndef CONFIG_USER_ONLY -static inline off_t kvmppc_alloc_rma(void **rma) -{ - return 0; -} - static inline bool kvmppc_spapr_use_multitce(void) { return false; diff --git a/target/ppc/machine.c b/target/ppc/machine.c index 3d6434a006..ba1b9e531f 100644 --- a/target/ppc/machine.c +++ b/target/ppc/machine.c @@ -212,6 +212,11 @@ static int cpu_pre_save(void *opaque) ; cpu->mig_msr_mask = env->msr_mask & ~metamask; cpu->mig_insns_flags = env->insns_flags & insns_compat_mask; + /* CPU models supported by old machines all have PPC_MEM_TLBIE, + * so we set it unconditionally to allow backward migration from + * a POWER9 host to a POWER8 host. + */ + cpu->mig_insns_flags |= PPC_MEM_TLBIE; cpu->mig_insns_flags2 = env->insns_flags2 & insns_compat_mask2; cpu->mig_nb_BATs = env->nb_BATs; } diff --git a/target/ppc/misc_helper.c b/target/ppc/misc_helper.c index 0e4217821b..8c8cba5cc6 100644 --- a/target/ppc/misc_helper.c +++ b/target/ppc/misc_helper.c @@ -88,6 +88,18 @@ void helper_store_sdr1(CPUPPCState *env, target_ulong val) } } +#if defined(TARGET_PPC64) +void helper_store_ptcr(CPUPPCState *env, target_ulong val) +{ + PowerPCCPU *cpu = ppc_env_get_cpu(env); + + if (env->spr[SPR_PTCR] != val) { + ppc_store_ptcr(env, val); + tlb_flush(CPU(cpu)); + } +} +#endif /* defined(TARGET_PPC64) */ + void helper_store_pidr(CPUPPCState *env, target_ulong val) { PowerPCCPU *cpu = ppc_env_get_cpu(env); diff --git a/target/ppc/mmu-book3s-v3.h b/target/ppc/mmu-book3s-v3.h index 56095dab52..fdf80987d7 100644 --- a/target/ppc/mmu-book3s-v3.h +++ b/target/ppc/mmu-book3s-v3.h @@ -22,6 +22,12 @@ #ifndef CONFIG_USER_ONLY +/* + * Partition table definitions + */ +#define PTCR_PATB 0x0FFFFFFFFFFFF000ULL /* Partition Table Base */ +#define PTCR_PATS 0x000000000000001FULL /* Partition Table Size */ + /* Partition Table Entry Fields */ #define PATBE1_GR 0x8000000000000000 diff --git a/target/ppc/mmu-hash64.c b/target/ppc/mmu-hash64.c index 7e0adecfd9..a1db20e3a8 100644 --- a/target/ppc/mmu-hash64.c +++ b/target/ppc/mmu-hash64.c @@ -942,7 +942,7 @@ void ppc_hash64_tlb_flush_hpte(PowerPCCPU *cpu, target_ulong ptex, cpu->env.tlb_need_flush = TLB_NEED_GLOBAL_FLUSH | TLB_NEED_LOCAL_FLUSH; } -void ppc_hash64_update_rmls(PowerPCCPU *cpu) +static void ppc_hash64_update_rmls(PowerPCCPU *cpu) { CPUPPCState *env = &cpu->env; uint64_t lpcr = env->spr[SPR_LPCR]; @@ -977,7 +977,7 @@ void ppc_hash64_update_rmls(PowerPCCPU *cpu) } } -void ppc_hash64_update_vrma(PowerPCCPU *cpu) +static void ppc_hash64_update_vrma(PowerPCCPU *cpu) { CPUPPCState *env = &cpu->env; const PPCHash64SegmentPageSizes *sps = NULL; @@ -1028,9 +1028,9 @@ void ppc_hash64_update_vrma(PowerPCCPU *cpu) slb->sps = sps; } -void helper_store_lpcr(CPUPPCState *env, target_ulong val) +void ppc_store_lpcr(PowerPCCPU *cpu, target_ulong val) { - PowerPCCPU *cpu = ppc_env_get_cpu(env); + CPUPPCState *env = &cpu->env; uint64_t lpcr = 0; /* Filter out bits */ @@ -1096,6 +1096,13 @@ void helper_store_lpcr(CPUPPCState *env, target_ulong val) ppc_hash64_update_vrma(cpu); } +void helper_store_lpcr(CPUPPCState *env, target_ulong val) +{ + PowerPCCPU *cpu = ppc_env_get_cpu(env); + + ppc_store_lpcr(cpu, val); +} + void ppc_hash64_init(PowerPCCPU *cpu) { CPUPPCState *env = &cpu->env; diff --git a/target/ppc/mmu-hash64.h b/target/ppc/mmu-hash64.h index d5fc03441d..53dcec5b93 100644 --- a/target/ppc/mmu-hash64.h +++ b/target/ppc/mmu-hash64.h @@ -17,8 +17,7 @@ void ppc_hash64_tlb_flush_hpte(PowerPCCPU *cpu, target_ulong pte0, target_ulong pte1); unsigned ppc_hash64_hpte_page_shift_noslb(PowerPCCPU *cpu, uint64_t pte0, uint64_t pte1); -void ppc_hash64_update_vrma(PowerPCCPU *cpu); -void ppc_hash64_update_rmls(PowerPCCPU *cpu); +void ppc_store_lpcr(PowerPCCPU *cpu, target_ulong val); void ppc_hash64_init(PowerPCCPU *cpu); void ppc_hash64_finalize(PowerPCCPU *cpu); #endif @@ -102,6 +101,9 @@ void ppc_hash64_finalize(PowerPCCPU *cpu); static inline hwaddr ppc_hash64_hpt_base(PowerPCCPU *cpu) { + if (cpu->vhyp) { + return 0; + } return cpu->env.spr[SPR_SDR1] & SDR_64_HTABORG; } diff --git a/target/ppc/mmu_helper.c b/target/ppc/mmu_helper.c index 8075b7149a..98ce17985b 100644 --- a/target/ppc/mmu_helper.c +++ b/target/ppc/mmu_helper.c @@ -2028,6 +2028,35 @@ void ppc_store_sdr1(CPUPPCState *env, target_ulong value) env->spr[SPR_SDR1] = value; } +#if defined(TARGET_PPC64) +void ppc_store_ptcr(CPUPPCState *env, target_ulong value) +{ + PowerPCCPU *cpu = ppc_env_get_cpu(env); + target_ulong ptcr_mask = PTCR_PATB | PTCR_PATS; + target_ulong patbsize = value & PTCR_PATS; + + qemu_log_mask(CPU_LOG_MMU, "%s: " TARGET_FMT_lx "\n", __func__, value); + + assert(!cpu->vhyp); + assert(env->mmu_model & POWERPC_MMU_3_00); + + if (value & ~ptcr_mask) { + error_report("Invalid bits 0x"TARGET_FMT_lx" set in PTCR", + value & ~ptcr_mask); + value &= ptcr_mask; + } + + if (patbsize > 24) { + error_report("Invalid Partition Table size 0x" TARGET_FMT_lx + " stored in PTCR", patbsize); + return; + } + + env->spr[SPR_PTCR] = value; +} + +#endif /* defined(TARGET_PPC64) */ + /* Segment registers load and store */ target_ulong helper_load_sr(CPUPPCState *env, target_ulong sr_num) { diff --git a/target/ppc/translate.c b/target/ppc/translate.c index 3beaa1e2f0..2a4140f420 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -7136,6 +7136,9 @@ void ppc_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf, if (env->spr_cb[SPR_SDR1].name) { /* SDR1 Exists */ cpu_fprintf(f, " SDR1 " TARGET_FMT_lx " ", env->spr[SPR_SDR1]); } + if (env->spr_cb[SPR_PTCR].name) { /* PTCR Exists */ + cpu_fprintf(f, " PTCR " TARGET_FMT_lx " ", env->spr[SPR_PTCR]); + } cpu_fprintf(f, " DAR " TARGET_FMT_lx " DSISR " TARGET_FMT_lx "\n", env->spr[SPR_DAR], env->spr[SPR_DSISR]); break; diff --git a/target/ppc/translate_init.c b/target/ppc/translate_init.c index 85708fe3bb..a72be6d121 100644 --- a/target/ppc/translate_init.c +++ b/target/ppc/translate_init.c @@ -420,6 +420,11 @@ static void spr_write_hior(DisasContext *ctx, int sprn, int gprn) tcg_gen_st_tl(t0, cpu_env, offsetof(CPUPPCState, excp_prefix)); tcg_temp_free(t0); } +static void spr_write_ptcr(DisasContext *ctx, int sprn, int gprn) +{ + gen_helper_store_ptcr(cpu_env, cpu_gpr[gprn]); +} + #endif #endif @@ -8167,6 +8172,18 @@ static void gen_spr_power8_rpr(CPUPPCState *env) #endif } +static void gen_spr_power9_mmu(CPUPPCState *env) +{ +#if !defined(CONFIG_USER_ONLY) + /* Partition Table Control */ + spr_register_hv(env, SPR_PTCR, "PTCR", + SPR_NOACCESS, SPR_NOACCESS, + SPR_NOACCESS, SPR_NOACCESS, + &spr_read_generic, &spr_write_ptcr, + 0x00000000); +#endif +} + static void init_proc_book3s_common(CPUPPCState *env) { gen_spr_ne_601(env); @@ -8719,6 +8736,7 @@ static void init_proc_POWER9(CPUPPCState *env) gen_spr_power8_ic(env); gen_spr_power8_book4(env); gen_spr_power8_rpr(env); + gen_spr_power9_mmu(env); /* POWER9 Specific registers */ spr_register_kvm(env, SPR_TIDR, "TIDR", NULL, NULL, @@ -8864,13 +8882,9 @@ POWERPC_FAMILY(POWER9)(ObjectClass *oc, void *data) } #if !defined(CONFIG_USER_ONLY) -void cpu_ppc_set_papr(PowerPCCPU *cpu, PPCVirtualHypervisor *vhyp) +void cpu_ppc_set_vhyp(PowerPCCPU *cpu, PPCVirtualHypervisor *vhyp) { - PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu); CPUPPCState *env = &cpu->env; - ppc_spr_t *lpcr = &env->spr_cb[SPR_LPCR]; - ppc_spr_t *amor = &env->spr_cb[SPR_AMOR]; - CPUState *cs = CPU(cpu); cpu->vhyp = vhyp; @@ -8879,62 +8893,6 @@ void cpu_ppc_set_papr(PowerPCCPU *cpu, PPCVirtualHypervisor *vhyp) * hypervisor mode itself */ env->msr_mask &= ~MSR_HVB; - - /* Set emulated LPCR to not send interrupts to hypervisor. Note that - * under KVM, the actual HW LPCR will be set differently by KVM itself, - * the settings below ensure proper operations with TCG in absence of - * a real hypervisor. - * - * Clearing VPM0 will also cause us to use RMOR in mmu-hash64.c for - * real mode accesses, which thankfully defaults to 0 and isn't - * accessible in guest mode. - */ - lpcr->default_value &= ~(LPCR_VPM0 | LPCR_VPM1 | LPCR_ISL | LPCR_KBV); - lpcr->default_value |= LPCR_LPES0 | LPCR_LPES1; - - /* Set RMLS to the max (ie, 16G) */ - lpcr->default_value &= ~LPCR_RMLS; - lpcr->default_value |= 1ull << LPCR_RMLS_SHIFT; - - if (env->mmu_model == POWERPC_MMU_3_00) { - /* By default we choose legacy mode and switch to new hash or radix - * when a register process table hcall is made. So disable process - * tables and guest translation shootdown by default - * - * Hot-plugged CPUs inherit from the guest radix setting under - * KVM but not under TCG. Update the default LPCR to keep new - * CPUs in sync when radix is enabled. - */ - if (ppc64_radix_guest(cpu)) { - lpcr->default_value |= LPCR_UPRT | LPCR_GTSE; - } else { - lpcr->default_value &= ~(LPCR_UPRT | LPCR_GTSE); - } - } - - /* Only enable Power-saving mode Exit Cause exceptions on the boot - * CPU. The RTAS command start-cpu will enable them on secondaries. - */ - if (cs == first_cpu) { - lpcr->default_value |= pcc->lpcr_pm; - } - - /* We should be followed by a CPU reset but update the active value - * just in case... - */ - env->spr[SPR_LPCR] = lpcr->default_value; - - /* Set a full AMOR so guest can use the AMR as it sees fit */ - env->spr[SPR_AMOR] = amor->default_value = 0xffffffffffffffffull; - - /* Update some env bits based on new LPCR value */ - ppc_hash64_update_rmls(cpu); - ppc_hash64_update_vrma(cpu); - - /* Tell KVM that we're in PAPR mode */ - if (kvm_enabled()) { - kvmppc_set_papr(cpu); - } } #endif /* !defined(CONFIG_USER_ONLY) */ diff --git a/target/s390x/kvm.c b/target/s390x/kvm.c index fb59d92def..12b90cf5c5 100644 --- a/target/s390x/kvm.c +++ b/target/s390x/kvm.c @@ -1081,7 +1081,6 @@ static int kvm_sclp_service_call(S390CPU *cpu, struct kvm_run *run, uint32_t code; int r = 0; - cpu_synchronize_state(CPU(cpu)); sccb = env->regs[ipbh0 & 0xf]; code = env->regs[(ipbh0 & 0xf0) >> 4]; @@ -1101,8 +1100,6 @@ static int handle_b2(S390CPU *cpu, struct kvm_run *run, uint8_t ipa1) int rc = 0; uint16_t ipbh0 = (run->s390_sieic.ipb & 0xffff0000) >> 16; - cpu_synchronize_state(CPU(cpu)); - switch (ipa1) { case PRIV_B2_XSCH: ioinst_handle_xsch(cpu, env->regs[1], RA_IGNORED); @@ -1248,7 +1245,6 @@ static int kvm_stpcifc_service_call(S390CPU *cpu, struct kvm_run *run) uint8_t ar; if (s390_has_feat(S390_FEAT_ZPCI)) { - cpu_synchronize_state(CPU(cpu)); fiba = get_base_disp_rxy(cpu, run, &ar); return stpcifc_service_call(cpu, r1, fiba, ar, RA_IGNORED); @@ -1266,7 +1262,6 @@ static int kvm_sic_service_call(S390CPU *cpu, struct kvm_run *run) uint16_t mode; int r; - cpu_synchronize_state(CPU(cpu)); mode = env->regs[r1] & 0xffff; isc = (env->regs[r3] >> 27) & 0x7; r = css_do_sic(env, isc, mode); @@ -1297,7 +1292,6 @@ static int kvm_pcistb_service_call(S390CPU *cpu, struct kvm_run *run) uint8_t ar; if (s390_has_feat(S390_FEAT_ZPCI)) { - cpu_synchronize_state(CPU(cpu)); gaddr = get_base_disp_rsy(cpu, run, &ar); return pcistb_service_call(cpu, r1, r3, gaddr, ar, RA_IGNORED); @@ -1313,7 +1307,6 @@ static int kvm_mpcifc_service_call(S390CPU *cpu, struct kvm_run *run) uint8_t ar; if (s390_has_feat(S390_FEAT_ZPCI)) { - cpu_synchronize_state(CPU(cpu)); fiba = get_base_disp_rxy(cpu, run, &ar); return mpcifc_service_call(cpu, r1, fiba, ar, RA_IGNORED); @@ -1401,7 +1394,6 @@ static int handle_hypercall(S390CPU *cpu, struct kvm_run *run) CPUS390XState *env = &cpu->env; int ret; - cpu_synchronize_state(CPU(cpu)); ret = s390_virtio_hypercall(env); if (ret == -EINVAL) { kvm_s390_program_interrupt(cpu, PGM_SPECIFICATION); @@ -1416,7 +1408,6 @@ static void kvm_handle_diag_288(S390CPU *cpu, struct kvm_run *run) uint64_t r1, r3; int rc; - cpu_synchronize_state(CPU(cpu)); r1 = (run->s390_sieic.ipa & 0x00f0) >> 4; r3 = run->s390_sieic.ipa & 0x000f; rc = handle_diag_288(&cpu->env, r1, r3); @@ -1429,7 +1420,6 @@ static void kvm_handle_diag_308(S390CPU *cpu, struct kvm_run *run) { uint64_t r1, r3; - cpu_synchronize_state(CPU(cpu)); r1 = (run->s390_sieic.ipa & 0x00f0) >> 4; r3 = run->s390_sieic.ipa & 0x000f; handle_diag_308(&cpu->env, r1, r3, RA_IGNORED); @@ -1440,8 +1430,6 @@ static int handle_sw_breakpoint(S390CPU *cpu, struct kvm_run *run) CPUS390XState *env = &cpu->env; unsigned long pc; - cpu_synchronize_state(CPU(cpu)); - pc = env->psw.addr - sw_bp_ilen; if (kvm_find_sw_breakpoint(CPU(cpu), pc)) { env->psw.addr = pc; @@ -1493,8 +1481,6 @@ static int kvm_s390_handle_sigp(S390CPU *cpu, uint8_t ipa1, uint32_t ipb) int ret; uint8_t order; - cpu_synchronize_state(CPU(cpu)); - /* get order code */ order = decode_basedisp_rs(env, ipb, NULL) & SIGP_ORDER_MASK; @@ -1556,7 +1542,6 @@ static int handle_oper_loop(S390CPU *cpu, struct kvm_run *run) CPUState *cs = CPU(cpu); PSW oldpsw, newpsw; - cpu_synchronize_state(cs); newpsw.mask = ldq_phys(cs->as, cpu->env.psa + offsetof(LowCore, program_new_psw)); newpsw.addr = ldq_phys(cs->as, cpu->env.psa + @@ -1609,7 +1594,6 @@ static int handle_intercept(S390CPU *cpu) break; case ICPT_WAITPSW: /* disabled wait, since enabled wait is handled in kernel */ - cpu_synchronize_state(cs); s390_handle_wait(cpu); r = EXCP_HALTED; break; @@ -1651,8 +1635,6 @@ static int handle_tsch(S390CPU *cpu) struct kvm_run *run = cs->kvm_run; int ret; - cpu_synchronize_state(cs); - ret = ioinst_handle_tsch(cpu, cpu->env.regs[1], run->s390_tsch.ipb, RA_IGNORED); if (ret < 0) { @@ -1778,7 +1760,7 @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run) qemu_mutex_lock_iothread(); - cpu_synchronize_state(cs); + kvm_cpu_synchronize_state(cs); switch (run->exit_reason) { case KVM_EXIT_S390_SIEIC: diff --git a/tests/boot-serial-test.c b/tests/boot-serial-test.c index 011525d8cf..4d6815c3e0 100644 --- a/tests/boot-serial-test.c +++ b/tests/boot-serial-test.c @@ -96,8 +96,7 @@ static testdef_t tests[] = { { "sparc", "SS-4", "", "MB86904" }, { "sparc", "SS-600MP", "", "TMS390Z55" }, { "sparc64", "sun4u", "", "UltraSPARC" }, - { "s390x", "s390-ccw-virtio", - "-nodefaults -device sclpconsole,chardev=serial0", "virtio device" }, + { "s390x", "s390-ccw-virtio", "", "virtio device" }, { "m68k", "mcf5208evb", "", "TT", sizeof(kernel_mcf5208), kernel_mcf5208 }, { "microblaze", "petalogix-s3adsp1800", "", "TT", sizeof(kernel_pls3adsp1800), kernel_pls3adsp1800 }, @@ -133,7 +133,6 @@ int main(int argc, char **argv) #include "sysemu/iothread.h" #define MAX_VIRTIO_CONSOLES 1 -#define MAX_SCLP_CONSOLES 1 static const char *data_dir[16]; static int data_dir_idx; @@ -158,7 +157,6 @@ static int num_serial_hds = 0; static Chardev **serial_hds = NULL; Chardev *parallel_hds[MAX_PARALLEL_PORTS]; Chardev *virtcon_hds[MAX_VIRTIO_CONSOLES]; -Chardev *sclp_hds[MAX_SCLP_CONSOLES]; int win2k_install_hack = 0; int singlestep = 0; int smp_cpus; @@ -210,7 +208,6 @@ static int has_defaults = 1; static int default_serial = 1; static int default_parallel = 1; static int default_virtcon = 1; -static int default_sclp = 1; static int default_monitor = 1; static int default_floppy = 1; static int default_cdrom = 1; @@ -2588,39 +2585,6 @@ static int virtcon_parse(const char *devname) return 0; } -static int sclp_parse(const char *devname) -{ - QemuOptsList *device = qemu_find_opts("device"); - static int index = 0; - char label[32]; - QemuOpts *dev_opts; - - if (strcmp(devname, "none") == 0) { - return 0; - } - if (index == MAX_SCLP_CONSOLES) { - error_report("too many sclp consoles"); - exit(1); - } - - assert(arch_type == QEMU_ARCH_S390X); - - dev_opts = qemu_opts_create(device, NULL, 0, NULL); - qemu_opt_set(dev_opts, "driver", "sclpconsole", &error_abort); - - snprintf(label, sizeof(label), "sclpcon%d", index); - sclp_hds[index] = qemu_chr_new(label, devname); - if (!sclp_hds[index]) { - error_report("could not connect sclp console" - " to character backend '%s'", devname); - return -1; - } - qemu_opt_set(dev_opts, "chardev", label, &error_abort); - - index++; - return 0; -} - static int debugcon_parse(const char *devname) { QemuOpts *opts; @@ -4254,9 +4218,6 @@ int main(int argc, char **argv, char **envp) if (!has_defaults || !machine_class->use_virtcon) { default_virtcon = 0; } - if (!has_defaults || !machine_class->use_sclp) { - default_sclp = 0; - } if (!has_defaults || machine_class->no_floppy) { default_floppy = 0; } @@ -4303,16 +4264,11 @@ int main(int argc, char **argv, char **envp) add_device_config(DEV_SERIAL, "mon:stdio"); } else if (default_virtcon && default_monitor) { add_device_config(DEV_VIRTCON, "mon:stdio"); - } else if (default_sclp && default_monitor) { - add_device_config(DEV_SCLP, "mon:stdio"); } else { if (default_serial) add_device_config(DEV_SERIAL, "stdio"); if (default_virtcon) add_device_config(DEV_VIRTCON, "stdio"); - if (default_sclp) { - add_device_config(DEV_SCLP, "stdio"); - } if (default_monitor) monitor_parse("stdio", "readline", false); } @@ -4325,9 +4281,6 @@ int main(int argc, char **argv, char **envp) monitor_parse("vc:80Cx24C", "readline", false); if (default_virtcon) add_device_config(DEV_VIRTCON, "vc:80Cx24C"); - if (default_sclp) { - add_device_config(DEV_SCLP, "vc:80Cx24C"); - } } #if defined(CONFIG_VNC) @@ -4577,9 +4530,6 @@ int main(int argc, char **argv, char **envp) exit(1); if (foreach_device_config(DEV_VIRTCON, virtcon_parse) < 0) exit(1); - if (foreach_device_config(DEV_SCLP, sclp_parse) < 0) { - exit(1); - } if (foreach_device_config(DEV_DEBUGCON, debugcon_parse) < 0) exit(1); |