diff options
72 files changed, 1152 insertions, 2795 deletions
diff --git a/bsd-user/arm/target_arch_elf.h b/bsd-user/arm/target_arch_elf.h index b1c0fd2..b54bf5f 100644 --- a/bsd-user/arm/target_arch_elf.h +++ b/bsd-user/arm/target_arch_elf.h @@ -86,7 +86,6 @@ static uint32_t get_elf_hwcap(void) /* probe for the extra features */ /* EDSP is in v5TE and above */ GET_FEATURE(ARM_FEATURE_V5, ARM_HWCAP_ARM_EDSP); - GET_FEATURE(ARM_FEATURE_IWMMXT, ARM_HWCAP_ARM_IWMMXT); GET_FEATURE(ARM_FEATURE_THUMB2EE, ARM_HWCAP_ARM_THUMBEE); GET_FEATURE(ARM_FEATURE_NEON, ARM_HWCAP_ARM_NEON); GET_FEATURE(ARM_FEATURE_V6K, ARM_HWCAP_ARM_TLS); @@ -1839,6 +1839,12 @@ for target in $target_list; do echo "GDB=$gdb_bin" >> $config_target_mak fi + if test "${gdb_arches#*$arch}" != "$gdb_arches" && version_ge $gdb_version 14.1; then + echo "GDB_HAS_SME_TILES=y" >> $config_target_mak + else + echo "GDB_HAS_SME_TILES=n" >> $config_target_mak + fi + if test "${gdb_arches#*aarch64}" != "$gdb_arches" && version_ge $gdb_version 15.1; then echo "GDB_HAS_MTE=y" >> $config_target_mak fi diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index 2fa2c47..aa300bb 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -68,19 +68,6 @@ configurations (e.g. -smp drawers=1,books=1,clusters=1 for x86 PC machine) is marked deprecated since 9.0, users have to ensure that all the topology members described with -smp are supported by the target machine. -``-old-param`` option for booting Arm kernels via param_struct (since 10.0) -''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' - -The ``-old-param`` command line option is specific to Arm targets: -it is used when directly booting a guest kernel to pass it the -command line and other information via the old ``param_struct`` ABI, -rather than the newer ATAGS or DTB mechanisms. This option was only -ever needed to support ancient kernels on some old board types -like the ``akita`` or ``terrier``; it has been deprecated in the -kernel since 2001. None of the board types QEMU supports need -``param_struct`` support, so this option has been deprecated and will -be removed in a future QEMU version. - QEMU Machine Protocol (QMP) commands ------------------------------------ @@ -236,27 +223,6 @@ Keeping 32-bit host support alive is a substantial burden for the QEMU project. Thus QEMU will in future drop the support for all 32-bit host systems. -linux-user mode CPUs --------------------- - -iwMMXt emulation and the ``pxa`` CPUs (since 10.0) -'''''''''''''''''''''''''''''''''''''''''''''''''' - -The ``pxa`` CPU family (``pxa250``, ``pxa255``, ``pxa260``, -``pxa261``, ``pxa262``, ``pxa270-a0``, ``pxa270-a1``, ``pxa270``, -``pxa270-b0``, ``pxa270-b1``, ``pxa270-c0``, ``pxa270-c5``) are no -longer used in system emulation, because all the machine types which -used these CPUs were removed in the QEMU 9.2 release. These CPUs can -now only be used in linux-user mode, and to do that you would have to -explicitly select one of these CPUs with the ``-cpu`` command line -option or the ``QEMU_CPU`` environment variable. - -We don't believe that anybody is using the iwMMXt emulation, and we do -not have any tests to validate it or any real hardware or similar -known-good implementation to test against. GCC is in the process of -dropping their support for iwMMXt codegen. These CPU types are -therefore deprecated in QEMU, and will be removed in a future release. - System emulator CPUs -------------------- diff --git a/docs/about/removed-features.rst b/docs/about/removed-features.rst index 2d3a684..a5338e4 100644 --- a/docs/about/removed-features.rst +++ b/docs/about/removed-features.rst @@ -560,6 +560,18 @@ the options along with the machine models they were intended for. Use ``-run-with user=..`` instead. +``-old-param`` option for booting Arm kernels via param_struct (removed in 10.2) +'''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The ``-old-param`` command line option was specific to Arm targets: +it was used when directly booting a guest kernel to pass it the +command line and other information via the old ``param_struct`` ABI, +rather than the newer ATAGS or DTB mechanisms. This option was only +ever needed to support ancient kernels on some old board types +like the ``akita`` or ``terrier``; it has been deprecated in the +kernel since 2001. None of the board types QEMU supports need +``param_struct`` support, so this option has been removed. + User-mode emulator command line arguments ----------------------------------------- @@ -1138,6 +1150,20 @@ reason the maintainers strongly suspected no one actually used it. QEMU Nios II architecture was orphan; Intel has EOL'ed the Nios II processor IP (see `Intel discontinuance notification`_). +iwMMXt emulation and the ``pxa`` CPUs (removed in 10.2) +''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The ``pxa`` CPU family (``pxa250``, ``pxa255``, ``pxa260``, +``pxa261``, ``pxa262``, ``pxa270-a0``, ``pxa270-a1``, ``pxa270``, +``pxa270-b0``, ``pxa270-b1``, ``pxa270-c0``, ``pxa270-c5``) were +not available in system emulation, because all the machine types which +used these CPUs were removed in the QEMU 9.2 release. We don't +believe that anybody was using the iwMMXt emulation (which you +would have to explicitly enable on the command line), and we did +not have any tests to validate it or any real hardware or similar +known-good implementation to test against. These CPUs have +therefore been removed in linux-user mode as well. + TCG introspection features -------------------------- diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index 4e8aca8..6b04c96 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -23,6 +23,7 @@ the following architecture extensions: - FEAT_AFP (Alternate floating-point behavior) - FEAT_Armv9_Crypto (Armv9 Cryptographic Extension) - FEAT_ASID16 (16 bit ASID) +- FEAT_ATS1A (Address Translation operations that ignore stage 1 permissions) - FEAT_BBM at level 2 (Translation table break-before-make levels) - FEAT_BF16 (AArch64 BFloat16 instructions) - FEAT_BTI (Branch Target Identification) diff --git a/gdbstub/internals.h b/gdbstub/internals.h index bf5a5c6..92466b2 100644 --- a/gdbstub/internals.h +++ b/gdbstub/internals.h @@ -11,7 +11,27 @@ #include "exec/cpu-common.h" -#define MAX_PACKET_LENGTH 4096 +/* + * Most "large" transfers (e.g. memory reads, feature XML + * transfer) have mechanisms in the gdb protocol for splitting + * them. However, register values in particular cannot currently + * be split. This packet size must therefore be at least big enough + * for the worst-case register size. Currently that is Arm SME + * ZA storage with a 256x256 byte value. We also must account + * for the conversion from raw data to hex in gdb_memtohex(), + * which writes 2 * size bytes, and for other protocol overhead + * including command, register number and checksum which add + * another 4 bytes of overhead. However, to be consistent with + * the changes made in gdbserver to address this same requirement, + * we add a total of 32 bytes to account for protocol overhead + * (unclear why specifically 32 bytes), bringing the value of + * MAX_PACKET_LENGTH to 2 * 256 * 256 + 32 = 131104. + * + * The commit making this change for gdbserver can be found here: + * https://sourceware.org/git/?p=binutils-gdb.git;a=commit;h= + * b816042e88583f280ad186ff124ab84d31fb592b + */ +#define MAX_PACKET_LENGTH 131104 /* * Shared structures and definitions diff --git a/hw/arm/boot.c b/hw/arm/boot.c index d084030..e77d867 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -337,81 +337,6 @@ static void set_kernel_args(const struct arm_boot_info *info, AddressSpace *as) WRITE_WORD(p, 0); } -static void set_kernel_args_old(const struct arm_boot_info *info, - AddressSpace *as) -{ - hwaddr p; - const char *s; - int initrd_size = info->initrd_size; - hwaddr base = info->loader_start; - - /* see linux/include/asm-arm/setup.h */ - p = base + KERNEL_ARGS_ADDR; - /* page_size */ - WRITE_WORD(p, 4096); - /* nr_pages */ - WRITE_WORD(p, info->ram_size / 4096); - /* ramdisk_size */ - WRITE_WORD(p, 0); -#define FLAG_READONLY 1 -#define FLAG_RDLOAD 4 -#define FLAG_RDPROMPT 8 - /* flags */ - WRITE_WORD(p, FLAG_READONLY | FLAG_RDLOAD | FLAG_RDPROMPT); - /* rootdev */ - WRITE_WORD(p, (31 << 8) | 0); /* /dev/mtdblock0 */ - /* video_num_cols */ - WRITE_WORD(p, 0); - /* video_num_rows */ - WRITE_WORD(p, 0); - /* video_x */ - WRITE_WORD(p, 0); - /* video_y */ - WRITE_WORD(p, 0); - /* memc_control_reg */ - WRITE_WORD(p, 0); - /* unsigned char sounddefault */ - /* unsigned char adfsdrives */ - /* unsigned char bytes_per_char_h */ - /* unsigned char bytes_per_char_v */ - WRITE_WORD(p, 0); - /* pages_in_bank[4] */ - WRITE_WORD(p, 0); - WRITE_WORD(p, 0); - WRITE_WORD(p, 0); - WRITE_WORD(p, 0); - /* pages_in_vram */ - WRITE_WORD(p, 0); - /* initrd_start */ - if (initrd_size) { - WRITE_WORD(p, info->initrd_start); - } else { - WRITE_WORD(p, 0); - } - /* initrd_size */ - WRITE_WORD(p, initrd_size); - /* rd_start */ - WRITE_WORD(p, 0); - /* system_rev */ - WRITE_WORD(p, 0); - /* system_serial_low */ - WRITE_WORD(p, 0); - /* system_serial_high */ - WRITE_WORD(p, 0); - /* mem_fclk_21285 */ - WRITE_WORD(p, 0); - /* zero unused fields */ - while (p < base + KERNEL_ARGS_ADDR + 256 + 1024) { - WRITE_WORD(p, 0); - } - s = info->kernel_cmdline; - if (s) { - address_space_write(as, p, MEMTXATTRS_UNSPECIFIED, s, strlen(s) + 1); - } else { - WRITE_WORD(p, 0); - } -} - static int fdt_add_memory_node(void *fdt, uint32_t acells, hwaddr mem_base, uint32_t scells, hwaddr mem_len, int numa_node_id) @@ -802,11 +727,7 @@ static void do_cpu_reset(void *opaque) cpu_set_pc(cs, info->loader_start); if (!have_dtb(info)) { - if (old_param) { - set_kernel_args_old(info, as); - } else { - set_kernel_args(info, as); - } + set_kernel_args(info, as); } } else if (info->secondary_cpu_reset_hook) { info->secondary_cpu_reset_hook(cpu, info); diff --git a/hw/arm/raspi4b.c b/hw/arm/raspi4b.c index 20082d5..4df951a 100644 --- a/hw/arm/raspi4b.c +++ b/hw/arm/raspi4b.c @@ -36,9 +36,8 @@ struct Raspi4bMachineState { * (see https://datasheets.raspberrypi.com/bcm2711/bcm2711-peripherals.pdf * 1.2 Address Map) */ -static int raspi_add_memory_node(void *fdt, hwaddr mem_base, hwaddr mem_len) +static void raspi_add_memory_node(void *fdt, hwaddr mem_base, hwaddr mem_len) { - int ret; uint32_t acells, scells; char *nodename = g_strdup_printf("/memory@%" PRIx64, mem_base); @@ -46,19 +45,16 @@ static int raspi_add_memory_node(void *fdt, hwaddr mem_base, hwaddr mem_len) NULL, &error_fatal); scells = qemu_fdt_getprop_cell(fdt, "/", "#size-cells", NULL, &error_fatal); - if (acells == 0 || scells == 0) { - fprintf(stderr, "dtb file invalid (#address-cells or #size-cells 0)\n"); - ret = -1; - } else { - qemu_fdt_add_subnode(fdt, nodename); - qemu_fdt_setprop_string(fdt, nodename, "device_type", "memory"); - ret = qemu_fdt_setprop_sized_cells(fdt, nodename, "reg", - acells, mem_base, - scells, mem_len); - } + /* validated by arm_load_dtb */ + g_assert(acells && scells); + + qemu_fdt_add_subnode(fdt, nodename); + qemu_fdt_setprop_string(fdt, nodename, "device_type", "memory"); + qemu_fdt_setprop_sized_cells(fdt, nodename, "reg", + acells, mem_base, + scells, mem_len); g_free(nodename); - return ret; } static void raspi4_modify_dtb(const struct arm_boot_info *info, void *fdt) diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c index 0dcaf2f..62a7612 100644 --- a/hw/arm/smmu-common.c +++ b/hw/arm/smmu-common.c @@ -20,6 +20,7 @@ #include "trace.h" #include "exec/target_page.h" #include "hw/core/cpu.h" +#include "hw/pci/pci_bridge.h" #include "hw/qdev-properties.h" #include "qapi/error.h" #include "qemu/jhash.h" @@ -925,6 +926,7 @@ static void smmu_base_realize(DeviceState *dev, Error **errp) { SMMUState *s = ARM_SMMU(dev); SMMUBaseClass *sbc = ARM_SMMU_GET_CLASS(dev); + PCIBus *pci_bus = s->primary_bus; Error *local_err = NULL; sbc->parent_realize(dev, &local_err); @@ -937,11 +939,39 @@ static void smmu_base_realize(DeviceState *dev, Error **errp) g_free, g_free); s->smmu_pcibus_by_busptr = g_hash_table_new(NULL, NULL); - if (s->primary_bus) { - pci_setup_iommu(s->primary_bus, &smmu_ops, s); - } else { + if (!pci_bus) { error_setg(errp, "SMMU is not attached to any PCI bus!"); + return; + } + + /* + * We only allow default PCIe Root Complex(pcie.0) or pxb-pcie based extra + * root complexes to be associated with SMMU. + */ + if (pci_bus_is_express(pci_bus) && pci_bus_is_root(pci_bus) && + object_dynamic_cast(OBJECT(pci_bus)->parent, TYPE_PCI_HOST_BRIDGE)) { + /* + * This condition matches either the default pcie.0, pxb-pcie, or + * pxb-cxl. For both pxb-pcie and pxb-cxl, parent_dev will be set. + * Currently, we don't allow pxb-cxl as it requires further + * verification. Therefore, make sure this is indeed pxb-pcie. + */ + if (pci_bus->parent_dev) { + if (!object_dynamic_cast(OBJECT(pci_bus), TYPE_PXB_PCIE_BUS)) { + goto out_err; + } + } + + if (s->smmu_per_bus) { + pci_setup_iommu_per_bus(pci_bus, &smmu_ops, s); + } else { + pci_setup_iommu(pci_bus, &smmu_ops, s); + } + return; } +out_err: + error_setg(errp, "SMMU should be attached to a default PCIe root complex" + "(pcie.0) or a pxb-pcie based root complex"); } /* @@ -961,6 +991,7 @@ static void smmu_base_reset_exit(Object *obj, ResetType type) static const Property smmu_dev_properties[] = { DEFINE_PROP_UINT8("bus_num", SMMUState, bus_num, 0), + DEFINE_PROP_BOOL("smmu_per_bus", SMMUState, smmu_per_bus, false), DEFINE_PROP_LINK("primary-bus", SMMUState, primary_bus, TYPE_PCI_BUS, PCIBus *), }; diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index ab67972..bcf8af8 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -1996,6 +1996,8 @@ static void smmuv3_class_init(ObjectClass *klass, const void *data) device_class_set_parent_realize(dc, smmu_realize, &c->parent_realize); device_class_set_props(dc, smmuv3_properties); + dc->hotpluggable = false; + dc->user_creatable = true; } static int smmuv3_notify_flag_changed(IOMMUMemoryRegion *iommu, diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index b01fc4f..96830f7 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -45,6 +45,7 @@ #include "hw/acpi/generic_event_device.h" #include "hw/acpi/tpm.h" #include "hw/acpi/hmat.h" +#include "hw/arm/smmuv3.h" #include "hw/cxl/cxl.h" #include "hw/pci/pcie_host.h" #include "hw/pci/pci.h" @@ -305,29 +306,126 @@ static int iort_idmap_compare(gconstpointer a, gconstpointer b) return idmap_a->input_base - idmap_b->input_base; } -/* Compute ID ranges (RIDs) from RC that are directed to the ITS Group node */ -static void create_rc_its_idmaps(GArray *its_idmaps, GArray *smmu_idmaps) +typedef struct AcpiIortSMMUv3Dev { + int irq; + hwaddr base; + GArray *rc_smmu_idmaps; + /* Offset of the SMMUv3 IORT Node relative to the start of the IORT */ + size_t offset; +} AcpiIortSMMUv3Dev; + +/* + * Populate the struct AcpiIortSMMUv3Dev for the legacy SMMUv3 and + * return the total number of associated idmaps. + */ +static int populate_smmuv3_legacy_dev(GArray *sdev_blob) { - AcpiIortIdMapping *idmap; - AcpiIortIdMapping next_range = {0}; + VirtMachineState *vms = VIRT_MACHINE(qdev_get_machine()); + AcpiIortSMMUv3Dev sdev; + sdev.rc_smmu_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping)); + object_child_foreach_recursive(object_get_root(), iort_host_bridges, + sdev.rc_smmu_idmaps); /* - * Based on the RID ranges that are directed to the SMMU, determine the - * bypassed RID ranges, i.e., the ones that are directed to the ITS Group - * node and do not pass through the SMMU, by subtracting the SMMU-bound - * ranges from the full RID range (0x0000–0xFFFF). + * There can be only one legacy SMMUv3("iommu=smmuv3") as it is a machine + * wide one. Since it may cover multiple PCIe RCs(based on "bypass_iommu" + * property), may have multiple SMMUv3 idmaps. Sort it by input_base. */ - for (int i = 0; i < smmu_idmaps->len; i++) { - idmap = &g_array_index(smmu_idmaps, AcpiIortIdMapping, i); + g_array_sort(sdev.rc_smmu_idmaps, iort_idmap_compare); - if (next_range.input_base < idmap->input_base) { - next_range.id_count = idmap->input_base - next_range.input_base; - g_array_append_val(its_idmaps, next_range); - } + sdev.base = vms->memmap[VIRT_SMMU].base; + sdev.irq = vms->irqmap[VIRT_SMMU] + ARM_SPI_BASE; + g_array_append_val(sdev_blob, sdev); + return sdev.rc_smmu_idmaps->len; +} + +static int smmuv3_dev_idmap_compare(gconstpointer a, gconstpointer b) +{ + AcpiIortSMMUv3Dev *sdev_a = (AcpiIortSMMUv3Dev *)a; + AcpiIortSMMUv3Dev *sdev_b = (AcpiIortSMMUv3Dev *)b; + AcpiIortIdMapping *map_a = &g_array_index(sdev_a->rc_smmu_idmaps, + AcpiIortIdMapping, 0); + AcpiIortIdMapping *map_b = &g_array_index(sdev_b->rc_smmu_idmaps, + AcpiIortIdMapping, 0); + return map_a->input_base - map_b->input_base; +} - next_range.input_base = idmap->input_base + idmap->id_count; +static int iort_smmuv3_devices(Object *obj, void *opaque) +{ + VirtMachineState *vms = VIRT_MACHINE(qdev_get_machine()); + GArray *sdev_blob = opaque; + AcpiIortIdMapping idmap; + PlatformBusDevice *pbus; + AcpiIortSMMUv3Dev sdev; + int min_bus, max_bus; + SysBusDevice *sbdev; + PCIBus *bus; + + if (!object_dynamic_cast(obj, TYPE_ARM_SMMUV3)) { + return 0; } + bus = PCI_BUS(object_property_get_link(obj, "primary-bus", &error_abort)); + pbus = PLATFORM_BUS_DEVICE(vms->platform_bus_dev); + sbdev = SYS_BUS_DEVICE(obj); + sdev.base = platform_bus_get_mmio_addr(pbus, sbdev, 0); + sdev.base += vms->memmap[VIRT_PLATFORM_BUS].base; + sdev.irq = platform_bus_get_irqn(pbus, sbdev, 0); + sdev.irq += vms->irqmap[VIRT_PLATFORM_BUS]; + sdev.irq += ARM_SPI_BASE; + + pci_bus_range(bus, &min_bus, &max_bus); + sdev.rc_smmu_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping)); + idmap.input_base = min_bus << 8, + idmap.id_count = (max_bus - min_bus + 1) << 8, + g_array_append_val(sdev.rc_smmu_idmaps, idmap); + g_array_append_val(sdev_blob, sdev); + return 0; +} + +/* + * Populate the struct AcpiIortSMMUv3Dev for all SMMUv3 devices and + * return the total number of idmaps. + */ +static int populate_smmuv3_dev(GArray *sdev_blob) +{ + object_child_foreach_recursive(object_get_root(), + iort_smmuv3_devices, sdev_blob); + /* Sort the smmuv3 devices(if any) by smmu idmap input_base */ + g_array_sort(sdev_blob, smmuv3_dev_idmap_compare); + /* + * Since each SMMUv3 dev is assocaited with specific host bridge, + * total number of idmaps equals to total number of smmuv3 devices. + */ + return sdev_blob->len; +} + +/* Compute ID ranges (RIDs) from RC that are directed to the ITS Group node */ +static void create_rc_its_idmaps(GArray *its_idmaps, GArray *smmuv3_devs) +{ + AcpiIortIdMapping *idmap; + AcpiIortIdMapping next_range = {0}; + AcpiIortSMMUv3Dev *sdev; + + for (int i = 0; i < smmuv3_devs->len; i++) { + sdev = &g_array_index(smmuv3_devs, AcpiIortSMMUv3Dev, i); + /* + * Based on the RID ranges that are directed to the SMMU, determine the + * bypassed RID ranges, i.e., the ones that are directed to the ITS + * Group node and do not pass through the SMMU, by subtracting the + * SMMU-bound ranges from the full RID range (0x0000–0xFFFF). + */ + for (int j = 0; j < sdev->rc_smmu_idmaps->len; j++) { + idmap = &g_array_index(sdev->rc_smmu_idmaps, AcpiIortIdMapping, j); + + if (next_range.input_base < idmap->input_base) { + next_range.id_count = idmap->input_base - next_range.input_base; + g_array_append_val(its_idmaps, next_range); + } + + next_range.input_base = idmap->input_base + idmap->id_count; + } + } /* * Append the last RC -> ITS ID mapping. * @@ -341,7 +439,6 @@ static void create_rc_its_idmaps(GArray *its_idmaps, GArray *smmu_idmaps) } } - /* * Input Output Remapping Table (IORT) * Conforms to "IO Remapping Table System Software on ARM Platforms", @@ -351,9 +448,12 @@ static void build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) { int i, nb_nodes, rc_mapping_count; - size_t node_size, smmu_offset = 0; + AcpiIortSMMUv3Dev *sdev; + size_t node_size; + int num_smmus = 0; uint32_t id = 0; - GArray *rc_smmu_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping)); + int rc_smmu_idmaps_len = 0; + GArray *smmuv3_devs = g_array_new(false, true, sizeof(AcpiIortSMMUv3Dev)); GArray *rc_its_idmaps = g_array_new(false, true, sizeof(AcpiIortIdMapping)); AcpiTable table = { .sig = "IORT", .rev = 3, .oem_id = vms->oem_id, @@ -361,22 +461,23 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) /* Table 2 The IORT */ acpi_table_begin(&table, table_data); - if (vms->iommu == VIRT_IOMMU_SMMUV3) { - object_child_foreach_recursive(object_get_root(), - iort_host_bridges, rc_smmu_idmaps); - - /* Sort the smmu idmap by input_base */ - g_array_sort(rc_smmu_idmaps, iort_idmap_compare); + if (vms->legacy_smmuv3_present) { + rc_smmu_idmaps_len = populate_smmuv3_legacy_dev(smmuv3_devs); + } else { + rc_smmu_idmaps_len = populate_smmuv3_dev(smmuv3_devs); + } - nb_nodes = 2; /* RC and SMMUv3 */ - rc_mapping_count = rc_smmu_idmaps->len; + num_smmus = smmuv3_devs->len; + if (num_smmus) { + nb_nodes = num_smmus + 1; /* RC and SMMUv3 */ + rc_mapping_count = rc_smmu_idmaps_len; if (vms->its) { /* * Knowing the ID ranges from the RC to the SMMU, it's possible to * determine the ID ranges from RC that go directly to ITS. */ - create_rc_its_idmaps(rc_its_idmaps, rc_smmu_idmaps); + create_rc_its_idmaps(rc_its_idmaps, smmuv3_devs); nb_nodes++; /* ITS */ rc_mapping_count += rc_its_idmaps->len; @@ -411,9 +512,10 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) build_append_int_noprefix(table_data, 0 /* MADT translation_id */, 4); } - if (vms->iommu == VIRT_IOMMU_SMMUV3) { - int irq = vms->irqmap[VIRT_SMMU] + ARM_SPI_BASE; + for (i = 0; i < num_smmus; i++) { + sdev = &g_array_index(smmuv3_devs, AcpiIortSMMUv3Dev, i); int smmu_mapping_count, offset_to_id_array; + int irq = sdev->irq; if (vms->its) { smmu_mapping_count = 1; /* ITS Group node */ @@ -422,7 +524,7 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) smmu_mapping_count = 0; /* No ID mappings */ offset_to_id_array = 0; /* No ID mappings array */ } - smmu_offset = table_data->len - table.table_offset; + sdev->offset = table_data->len - table.table_offset; /* Table 9 SMMUv3 Format */ build_append_int_noprefix(table_data, 4 /* SMMUv3 */, 1); /* Type */ node_size = SMMU_V3_ENTRY_SIZE + @@ -435,7 +537,7 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) /* Reference to ID Array */ build_append_int_noprefix(table_data, offset_to_id_array, 4); /* Base address */ - build_append_int_noprefix(table_data, vms->memmap[VIRT_SMMU].base, 8); + build_append_int_noprefix(table_data, sdev->base, 8); /* Flags */ build_append_int_noprefix(table_data, 1 /* COHACC Override */, 4); build_append_int_noprefix(table_data, 0, 4); /* Reserved */ @@ -486,21 +588,26 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) build_append_int_noprefix(table_data, 0, 3); /* Reserved */ /* Output Reference */ - if (vms->iommu == VIRT_IOMMU_SMMUV3) { + if (num_smmus) { AcpiIortIdMapping *range; - /* - * Map RIDs (input) from RC to SMMUv3 nodes: RC -> SMMUv3. - * - * N.B.: The mapping from SMMUv3 to ITS Group node (SMMUv3 -> ITS) is - * defined in the SMMUv3 table, where all SMMUv3 IDs are mapped to the - * ITS Group node, if ITS is available. - */ - for (i = 0; i < rc_smmu_idmaps->len; i++) { - range = &g_array_index(rc_smmu_idmaps, AcpiIortIdMapping, i); - /* Output IORT node is the SMMUv3 node. */ - build_iort_id_mapping(table_data, range->input_base, - range->id_count, smmu_offset); + for (i = 0; i < num_smmus; i++) { + sdev = &g_array_index(smmuv3_devs, AcpiIortSMMUv3Dev, i); + + /* + * Map RIDs (input) from RC to SMMUv3 nodes: RC -> SMMUv3. + * + * N.B.: The mapping from SMMUv3 to ITS Group node (SMMUv3 -> ITS) + * is defined in the SMMUv3 table, where all SMMUv3 IDs are mapped + * to the ITS Group node, if ITS is available. + */ + for (int j = 0; j < sdev->rc_smmu_idmaps->len; j++) { + range = &g_array_index(sdev->rc_smmu_idmaps, + AcpiIortIdMapping, j); + /* Output IORT node is the SMMUv3 node. */ + build_iort_id_mapping(table_data, range->input_base, + range->id_count, sdev->offset); + } } if (vms->its) { @@ -525,8 +632,12 @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) } acpi_table_end(linker, &table); - g_array_free(rc_smmu_idmaps, true); g_array_free(rc_its_idmaps, true); + for (i = 0; i < num_smmus; i++) { + sdev = &g_array_index(smmuv3_devs, AcpiIortSMMUv3Dev, i); + g_array_free(sdev->rc_smmu_idmaps, true); + } + g_array_free(smmuv3_devs, true); } /* diff --git a/hw/arm/virt.c b/hw/arm/virt.c index 6f01746..02209fa 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -55,6 +55,7 @@ #include "qemu/cutils.h" #include "qemu/error-report.h" #include "qemu/module.h" +#include "hw/pci/pci_bus.h" #include "hw/pci-host/gpex.h" #include "hw/pci-bridge/pci_expander_bridge.h" #include "hw/virtio/virtio-pci.h" @@ -149,6 +150,9 @@ static void arm_virt_compat_set(MachineClass *mc) #define LEGACY_RAMLIMIT_GB 255 #define LEGACY_RAMLIMIT_BYTES (LEGACY_RAMLIMIT_GB * GiB) +/* MMIO region size for SMMUv3 */ +#define SMMU_IO_LEN 0x20000 + /* Addresses and sizes of our components. * 0..128MB is space for a flash device so we can run bootrom code such as UEFI. * 128MB..256MB is used for miscellaneous device I/O. @@ -180,7 +184,7 @@ static const MemMapEntry base_memmap[] = { [VIRT_FW_CFG] = { 0x09020000, 0x00000018 }, [VIRT_GPIO] = { 0x09030000, 0x00001000 }, [VIRT_UART1] = { 0x09040000, 0x00001000 }, - [VIRT_SMMU] = { 0x09050000, 0x00020000 }, + [VIRT_SMMU] = { 0x09050000, SMMU_IO_LEN }, [VIRT_PCDIMM_ACPI] = { 0x09070000, MEMORY_HOTPLUG_IO_LEN }, [VIRT_ACPI_GED] = { 0x09080000, ACPI_GED_EVT_SEL_LEN }, [VIRT_NVDIMM_ACPI] = { 0x09090000, NVDIMM_ACPI_IO_LEN}, @@ -1442,19 +1446,66 @@ static void create_pcie_irq_map(const MachineState *ms, 0x7 /* PCI irq */); } +static void create_smmuv3_dt_bindings(const VirtMachineState *vms, hwaddr base, + hwaddr size, int irq) +{ + char *node; + const char compat[] = "arm,smmu-v3"; + const char irq_names[] = "eventq\0priq\0cmdq-sync\0gerror"; + MachineState *ms = MACHINE(vms); + + node = g_strdup_printf("/smmuv3@%" PRIx64, base); + qemu_fdt_add_subnode(ms->fdt, node); + qemu_fdt_setprop(ms->fdt, node, "compatible", compat, sizeof(compat)); + qemu_fdt_setprop_sized_cells(ms->fdt, node, "reg", 2, base, 2, size); + + qemu_fdt_setprop_cells(ms->fdt, node, "interrupts", + GIC_FDT_IRQ_TYPE_SPI, irq , GIC_FDT_IRQ_FLAGS_EDGE_LO_HI, + GIC_FDT_IRQ_TYPE_SPI, irq + 1, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI, + GIC_FDT_IRQ_TYPE_SPI, irq + 2, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI, + GIC_FDT_IRQ_TYPE_SPI, irq + 3, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI); + + qemu_fdt_setprop(ms->fdt, node, "interrupt-names", irq_names, + sizeof(irq_names)); + + qemu_fdt_setprop(ms->fdt, node, "dma-coherent", NULL, 0); + qemu_fdt_setprop_cell(ms->fdt, node, "#iommu-cells", 1); + qemu_fdt_setprop_cell(ms->fdt, node, "phandle", vms->iommu_phandle); + g_free(node); +} + +static void create_smmuv3_dev_dtb(VirtMachineState *vms, + DeviceState *dev, PCIBus *bus) +{ + PlatformBusDevice *pbus = PLATFORM_BUS_DEVICE(vms->platform_bus_dev); + SysBusDevice *sbdev = SYS_BUS_DEVICE(dev); + int irq = platform_bus_get_irqn(pbus, sbdev, 0); + hwaddr base = platform_bus_get_mmio_addr(pbus, sbdev, 0); + MachineState *ms = MACHINE(vms); + + if (!(vms->bootinfo.firmware_loaded && virt_is_acpi_enabled(vms)) && + strcmp("pcie.0", bus->qbus.name)) { + warn_report("SMMUv3 device only supported with pcie.0 for DT"); + return; + } + base += vms->memmap[VIRT_PLATFORM_BUS].base; + irq += vms->irqmap[VIRT_PLATFORM_BUS]; + + vms->iommu_phandle = qemu_fdt_alloc_phandle(ms->fdt); + create_smmuv3_dt_bindings(vms, base, SMMU_IO_LEN, irq); + qemu_fdt_setprop_cells(ms->fdt, vms->pciehb_nodename, "iommu-map", + 0x0, vms->iommu_phandle, 0x0, 0x10000); +} + static void create_smmu(const VirtMachineState *vms, PCIBus *bus) { VirtMachineClass *vmc = VIRT_MACHINE_GET_CLASS(vms); - char *node; - const char compat[] = "arm,smmu-v3"; int irq = vms->irqmap[VIRT_SMMU]; int i; hwaddr base = vms->memmap[VIRT_SMMU].base; hwaddr size = vms->memmap[VIRT_SMMU].size; - const char irq_names[] = "eventq\0priq\0cmdq-sync\0gerror"; DeviceState *dev; - MachineState *ms = MACHINE(vms); if (vms->iommu != VIRT_IOMMU_SMMUV3 || !vms->iommu_phandle) { return; @@ -1473,27 +1524,7 @@ static void create_smmu(const VirtMachineState *vms, sysbus_connect_irq(SYS_BUS_DEVICE(dev), i, qdev_get_gpio_in(vms->gic, irq + i)); } - - node = g_strdup_printf("/smmuv3@%" PRIx64, base); - qemu_fdt_add_subnode(ms->fdt, node); - qemu_fdt_setprop(ms->fdt, node, "compatible", compat, sizeof(compat)); - qemu_fdt_setprop_sized_cells(ms->fdt, node, "reg", 2, base, 2, size); - - qemu_fdt_setprop_cells(ms->fdt, node, "interrupts", - GIC_FDT_IRQ_TYPE_SPI, irq , GIC_FDT_IRQ_FLAGS_EDGE_LO_HI, - GIC_FDT_IRQ_TYPE_SPI, irq + 1, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI, - GIC_FDT_IRQ_TYPE_SPI, irq + 2, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI, - GIC_FDT_IRQ_TYPE_SPI, irq + 3, GIC_FDT_IRQ_FLAGS_EDGE_LO_HI); - - qemu_fdt_setprop(ms->fdt, node, "interrupt-names", irq_names, - sizeof(irq_names)); - - qemu_fdt_setprop(ms->fdt, node, "dma-coherent", NULL, 0); - - qemu_fdt_setprop_cell(ms->fdt, node, "#iommu-cells", 1); - - qemu_fdt_setprop_cell(ms->fdt, node, "phandle", vms->iommu_phandle); - g_free(node); + create_smmuv3_dt_bindings(vms, base, size, irq); } static void create_virtio_iommu_dt_bindings(VirtMachineState *vms) @@ -1649,6 +1680,7 @@ static void create_pcie(VirtMachineState *vms) qemu_fdt_setprop_cells(ms->fdt, nodename, "iommu-map", 0x0, vms->iommu_phandle, 0x0, 0x10000); } + vms->legacy_smmuv3_present = true; break; default: g_assert_not_reached(); @@ -2996,6 +3028,16 @@ static void virt_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev, qlist_append_str(reserved_regions, resv_prop_str); qdev_prop_set_array(dev, "reserved-regions", reserved_regions); g_free(resv_prop_str); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_ARM_SMMUV3)) { + if (vms->legacy_smmuv3_present || vms->iommu == VIRT_IOMMU_VIRTIO) { + error_setg(errp, "virt machine already has %s set. " + "Doesn't support incompatible iommus", + (vms->legacy_smmuv3_present) ? + "iommu=smmuv3" : "virtio-iommu"); + } else if (vms->iommu == VIRT_IOMMU_NONE) { + /* The new SMMUv3 device is specific to the PCI bus */ + object_property_set_bool(OBJECT(dev), "smmu_per_bus", true, NULL); + } } } @@ -3019,6 +3061,22 @@ static void virt_machine_device_plug_cb(HotplugHandler *hotplug_dev, virtio_md_pci_plug(VIRTIO_MD_PCI(dev), MACHINE(hotplug_dev), errp); } + if (object_dynamic_cast(OBJECT(dev), TYPE_ARM_SMMUV3)) { + if (!vms->legacy_smmuv3_present && vms->platform_bus_dev) { + PCIBus *bus; + + bus = PCI_BUS(object_property_get_link(OBJECT(dev), "primary-bus", + &error_abort)); + if (pci_bus_bypass_iommu(bus)) { + error_setg(errp, "Bypass option cannot be set for SMMUv3 " + "associated PCIe RC"); + return; + } + + create_smmuv3_dev_dtb(vms, dev, bus); + } + } + if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_IOMMU_PCI)) { PCIDevice *pdev = PCI_DEVICE(dev); @@ -3218,6 +3276,7 @@ static void virt_machine_class_init(ObjectClass *oc, const void *data) mc->max_cpus = 512; machine_class_allow_dynamic_sysbus_dev(mc, TYPE_RAMFB_DEVICE); machine_class_allow_dynamic_sysbus_dev(mc, TYPE_UEFI_VARS_SYSBUS); + machine_class_allow_dynamic_sysbus_dev(mc, TYPE_ARM_SMMUV3); #ifdef CONFIG_TPM machine_class_allow_dynamic_sysbus_dev(mc, TYPE_TPM_TIS_SYSBUS); #endif diff --git a/hw/core/sysbus-fdt.c b/hw/core/sysbus-fdt.c index 0711736..59f1d17 100644 --- a/hw/core/sysbus-fdt.c +++ b/hw/core/sysbus-fdt.c @@ -31,6 +31,7 @@ #include "qemu/error-report.h" #include "system/device_tree.h" #include "system/tpm.h" +#include "hw/arm/smmuv3.h" #include "hw/platform-bus.h" #include "hw/display/ramfb.h" #include "hw/uefi/var-service-api.h" @@ -135,6 +136,8 @@ static const BindingEntry bindings[] = { #ifdef CONFIG_TPM TYPE_BINDING(TYPE_TPM_TIS_SYSBUS, add_tpm_tis_fdt_node), #endif + /* No generic DT support for smmuv3 dev. Support added for arm virt only */ + TYPE_BINDING(TYPE_ARM_SMMUV3, no_fdt_node), TYPE_BINDING(TYPE_RAMFB_DEVICE, no_fdt_node), TYPE_BINDING(TYPE_UEFI_VARS_SYSBUS, add_uefi_vars_node), TYPE_BINDING("", NULL), /* last element */ diff --git a/hw/pci-bridge/pci_expander_bridge.c b/hw/pci-bridge/pci_expander_bridge.c index 3a29dfe..1bccedd 100644 --- a/hw/pci-bridge/pci_expander_bridge.c +++ b/hw/pci-bridge/pci_expander_bridge.c @@ -34,7 +34,6 @@ typedef struct PXBBus PXBBus; DECLARE_INSTANCE_CHECKER(PXBBus, PXB_BUS, TYPE_PXB_BUS) -#define TYPE_PXB_PCIE_BUS "pxb-pcie-bus" DECLARE_INSTANCE_CHECKER(PXBBus, PXB_PCIE_BUS, TYPE_PXB_PCIE_BUS) diff --git a/hw/pci/pci.c b/hw/pci/pci.c index 297196b..c3df9d6 100644 --- a/hw/pci/pci.c +++ b/hw/pci/pci.c @@ -2912,6 +2912,19 @@ static void pci_device_get_iommu_bus_devfn(PCIDevice *dev, } } + /* + * When multiple PCI Express Root Buses are defined using pxb-pcie, + * the IOMMU configuration may be specific to each root bus. However, + * pxb-pcie acts as a special root complex whose parent is effectively + * the default root complex(pcie.0). Ensure that we retrieve the + * correct IOMMU ops(if any) in such cases. + */ + if (pci_bus_is_express(iommu_bus) && pci_bus_is_root(iommu_bus)) { + if (parent_bus->iommu_per_bus) { + break; + } + } + iommu_bus = parent_bus; } @@ -3172,6 +3185,24 @@ void pci_setup_iommu(PCIBus *bus, const PCIIOMMUOps *ops, void *opaque) bus->iommu_opaque = opaque; } +/* + * Similar to pci_setup_iommu(), but sets iommu_per_bus to true, + * indicating that the IOMMU is specific to this bus. This is used by + * IOMMU implementations that are tied to a specific PCIe root complex. + * + * In QEMU, pxb-pcie behaves as a special root complex whose parent is + * effectively the default root complex (pcie.0). The iommu_per_bus + * is checked in pci_device_get_iommu_bus_devfn() to ensure the correct + * IOMMU ops are returned, avoiding the use of the parent’s IOMMU when + * it's not appropriate. + */ +void pci_setup_iommu_per_bus(PCIBus *bus, const PCIIOMMUOps *ops, + void *opaque) +{ + pci_setup_iommu(bus, ops, opaque); + bus->iommu_per_bus = true; +} + static void pci_dev_get_w64(PCIBus *b, PCIDevice *dev, void *opaque) { Range *range = opaque; diff --git a/hw/usb/dev-network.c b/hw/usb/dev-network.c index 81cc09d..1df2454 100644 --- a/hw/usb/dev-network.c +++ b/hw/usb/dev-network.c @@ -1383,7 +1383,7 @@ static void usb_net_realize(USBDevice *dev, Error **errp) qemu_format_nic_info_str(qemu_get_queue(s->nic), s->conf.macaddr.a); snprintf(s->usbstring_mac, sizeof(s->usbstring_mac), "%02x%02x%02x%02x%02x%02x", - 0x40, + s->conf.macaddr.a[0], s->conf.macaddr.a[1], s->conf.macaddr.a[2], s->conf.macaddr.a[3], diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h index e5e2d09..80d0fec 100644 --- a/include/hw/arm/smmu-common.h +++ b/include/hw/arm/smmu-common.h @@ -161,6 +161,7 @@ struct SMMUState { QLIST_HEAD(, SMMUDevice) devices_with_notifiers; uint8_t bus_num; PCIBus *primary_bus; + bool smmu_per_bus; /* SMMU is specific to the primary_bus */ }; struct SMMUBaseClass { diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index 365a28b..ea2cff0 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -179,6 +179,7 @@ struct VirtMachineState { char *oem_table_id; bool ns_el2_virt_timer_irq; CXLState cxl_devices_state; + bool legacy_smmuv3_present; }; #define VIRT_ECAM_ID(high) (high ? VIRT_HIGH_PCIE_ECAM : VIRT_PCIE_ECAM) diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h index 6b7d3ac..6bccb25 100644 --- a/include/hw/pci/pci.h +++ b/include/hw/pci/pci.h @@ -773,6 +773,8 @@ int pci_iommu_unregister_iotlb_notifier(PCIDevice *dev, uint32_t pasid, */ void pci_setup_iommu(PCIBus *bus, const PCIIOMMUOps *ops, void *opaque); +void pci_setup_iommu_per_bus(PCIBus *bus, const PCIIOMMUOps *ops, void *opaque); + pcibus_t pci_bar_address(PCIDevice *d, int reg, uint8_t type, pcibus_t size); diff --git a/include/hw/pci/pci_bridge.h b/include/hw/pci/pci_bridge.h index 8cdacbc..a055fd8 100644 --- a/include/hw/pci/pci_bridge.h +++ b/include/hw/pci/pci_bridge.h @@ -104,6 +104,7 @@ typedef struct PXBPCIEDev { PXBDev parent_obj; } PXBPCIEDev; +#define TYPE_PXB_PCIE_BUS "pxb-pcie-bus" #define TYPE_PXB_CXL_BUS "pxb-cxl-bus" #define TYPE_PXB_DEV "pxb" OBJECT_DECLARE_SIMPLE_TYPE(PXBDev, PXB_DEV) diff --git a/include/hw/pci/pci_bus.h b/include/hw/pci/pci_bus.h index 2261312..c738446 100644 --- a/include/hw/pci/pci_bus.h +++ b/include/hw/pci/pci_bus.h @@ -35,6 +35,7 @@ struct PCIBus { enum PCIBusFlags flags; const PCIIOMMUOps *iommu_ops; void *iommu_opaque; + bool iommu_per_bus; uint8_t devfn_min; uint32_t slot_reserved_mask; pci_set_irq_fn set_irq; diff --git a/include/system/system.h b/include/system/system.h index a7effe7..03a2d0e 100644 --- a/include/system/system.h +++ b/include/system/system.h @@ -42,7 +42,6 @@ extern int graphic_height; extern int graphic_depth; extern int display_opengl; extern const char *keyboard_layout; -extern int old_param; extern uint8_t *boot_splash_filedata; extern bool enable_cpu_pm; extern QEMUClockType rtc_clock; diff --git a/linux-user/aarch64/cpu_loop.c b/linux-user/aarch64/cpu_loop.c index 4c49211..6060572 100644 --- a/linux-user/aarch64/cpu_loop.c +++ b/linux-user/aarch64/cpu_loop.c @@ -27,11 +27,132 @@ #include "target/arm/syndrome.h" #include "target/arm/cpu-features.h" +/* Use the exception syndrome to map a cpu exception to a signal. */ +static void signal_for_exception(CPUARMState *env, vaddr addr) +{ + uint32_t syn = env->exception.syndrome; + int si_code, si_signo; + + /* Let signal delivery see that ESR is live. */ + env->cp15.esr_el[1] = syn; + + switch (syn_get_ec(syn)) { + case EC_DATAABORT: + case EC_INSNABORT: + /* Both EC have the same format for FSC, or close enough. */ + switch (extract32(syn, 0, 6)) { + case 0x04 ... 0x07: /* Translation fault, level {0-3} */ + si_signo = TARGET_SIGSEGV; + si_code = TARGET_SEGV_MAPERR; + break; + case 0x09 ... 0x0b: /* Access flag fault, level {1-3} */ + case 0x0d ... 0x0f: /* Permission fault, level {1-3} */ + si_signo = TARGET_SIGSEGV; + si_code = TARGET_SEGV_ACCERR; + break; + case 0x11: /* Synchronous Tag Check Fault */ + si_signo = TARGET_SIGSEGV; + si_code = TARGET_SEGV_MTESERR; + break; + case 0x21: /* Alignment fault */ + si_signo = TARGET_SIGBUS; + si_code = TARGET_BUS_ADRALN; + break; + default: + g_assert_not_reached(); + } + break; + + case EC_PCALIGNMENT: + si_signo = TARGET_SIGBUS; + si_code = TARGET_BUS_ADRALN; + break; + + case EC_UNCATEGORIZED: /* E.g. undefined instruction */ + case EC_SYSTEMREGISTERTRAP: /* E.g. inaccessible register */ + case EC_SMETRAP: /* E.g. invalid insn in streaming state */ + case EC_BTITRAP: /* E.g. invalid guarded branch target */ + case EC_ILLEGALSTATE: + /* + * Illegal state happens via an ERET from a privileged mode, + * so is not normally possible from user-only. However, gdbstub + * is not prevented from writing CPSR_IL, aka PSTATE.IL, which + * would generate a trap from the next translated block. + * In the kernel, default case -> el0_inv -> bad_el0_sync. + */ + si_signo = TARGET_SIGILL; + si_code = TARGET_ILL_ILLOPC; + break; + + case EC_PACFAIL: + si_signo = TARGET_SIGILL; + si_code = TARGET_ILL_ILLOPN; + break; + + case EC_MOP: + /* + * FIXME: The kernel fixes up wrong-option exceptions. + * For QEMU linux-user mode, you can only get these if + * the process is doing something silly (not executing + * the MOPS instructions in the required P/M/E sequence), + * so it is not a problem in practice that we do not. + * + * We ought ideally to implement the same "rewind to the + * start of the sequence" logic that the kernel does in + * arm64_mops_reset_regs(). In the meantime, deliver + * the guest a SIGILL, with the same ILLOPN si_code + * we've always used for this. + */ + si_signo = TARGET_SIGILL; + si_code = TARGET_ILL_ILLOPN; + break; + + case EC_WFX_TRAP: /* user-only WFI implemented as NOP */ + case EC_CP15RTTRAP: /* AArch32 */ + case EC_CP15RRTTRAP: /* AArch32 */ + case EC_CP14RTTRAP: /* AArch32 */ + case EC_CP14DTTRAP: /* AArch32 */ + case EC_ADVSIMDFPACCESSTRAP: /* user-only does not disable fpu */ + case EC_FPIDTRAP: /* AArch32 */ + case EC_PACTRAP: /* user-only does not disable pac regs */ + case EC_BXJTRAP: /* AArch32 */ + case EC_CP14RRTTRAP: /* AArch32 */ + case EC_AA32_SVC: /* AArch32 */ + case EC_AA32_HVC: /* AArch32 */ + case EC_AA32_SMC: /* AArch32 */ + case EC_AA64_SVC: /* generates EXCP_SWI */ + case EC_AA64_HVC: /* user-only generates EC_UNCATEGORIZED */ + case EC_AA64_SMC: /* user-only generates EC_UNCATEGORIZED */ + case EC_SVEACCESSTRAP: /* user-only does not disable sve */ + case EC_ERETTRAP: /* user-only generates EC_UNCATEGORIZED */ + case EC_GPC: /* user-only has no EL3 gpc tables */ + case EC_INSNABORT_SAME_EL: /* el0 cannot trap to el0 */ + case EC_DATAABORT_SAME_EL: /* el0 cannot trap to el0 */ + case EC_SPALIGNMENT: /* sp alignment checks not implemented */ + case EC_AA32_FPTRAP: /* fp exceptions not implemented */ + case EC_AA64_FPTRAP: /* fp exceptions not implemented */ + case EC_SERROR: /* user-only does not have hw faults */ + case EC_BREAKPOINT: /* user-only does not have hw debug */ + case EC_BREAKPOINT_SAME_EL: /* user-only does not have hw debug */ + case EC_SOFTWARESTEP: /* user-only does not have hw debug */ + case EC_SOFTWARESTEP_SAME_EL: /* user-only does not have hw debug */ + case EC_WATCHPOINT: /* user-only does not have hw debug */ + case EC_WATCHPOINT_SAME_EL: /* user-only does not have hw debug */ + case EC_AA32_BKPT: /* AArch32 */ + case EC_VECTORCATCH: /* AArch32 */ + case EC_AA64_BKPT: /* generates EXCP_BKPT */ + default: + g_assert_not_reached(); + } + + force_sig_fault(si_signo, si_code, addr); +} + /* AArch64 main loop */ void cpu_loop(CPUARMState *env) { CPUState *cs = env_cpu(env); - int trapnr, ec, fsc, si_code, si_signo; + int trapnr; abi_long ret; for (;;) { @@ -63,46 +184,11 @@ void cpu_loop(CPUARMState *env) /* just indicate that signals should be handled asap */ break; case EXCP_UDEF: - force_sig_fault(TARGET_SIGILL, TARGET_ILL_ILLOPN, env->pc); + signal_for_exception(env, env->pc); break; case EXCP_PREFETCH_ABORT: case EXCP_DATA_ABORT: - ec = syn_get_ec(env->exception.syndrome); - switch (ec) { - case EC_DATAABORT: - case EC_INSNABORT: - /* Both EC have the same format for FSC, or close enough. */ - fsc = extract32(env->exception.syndrome, 0, 6); - switch (fsc) { - case 0x04 ... 0x07: /* Translation fault, level {0-3} */ - si_signo = TARGET_SIGSEGV; - si_code = TARGET_SEGV_MAPERR; - break; - case 0x09 ... 0x0b: /* Access flag fault, level {1-3} */ - case 0x0d ... 0x0f: /* Permission fault, level {1-3} */ - si_signo = TARGET_SIGSEGV; - si_code = TARGET_SEGV_ACCERR; - break; - case 0x11: /* Synchronous Tag Check Fault */ - si_signo = TARGET_SIGSEGV; - si_code = TARGET_SEGV_MTESERR; - break; - case 0x21: /* Alignment fault */ - si_signo = TARGET_SIGBUS; - si_code = TARGET_BUS_ADRALN; - break; - default: - g_assert_not_reached(); - } - break; - case EC_PCALIGNMENT: - si_signo = TARGET_SIGBUS; - si_code = TARGET_BUS_ADRALN; - break; - default: - g_assert_not_reached(); - } - force_sig_fault(si_signo, si_code, env->exception.vaddress); + signal_for_exception(env, env->exception.vaddress); break; case EXCP_DEBUG: case EXCP_BKPT: diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index 668353b..ef97be3 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -65,6 +65,13 @@ struct target_fpsimd_context { uint64_t vregs[32 * 2]; /* really uint128_t vregs[32] */ }; +#define TARGET_ESR_MAGIC 0x45535201 + +struct target_esr_context { + struct target_aarch64_ctx head; + uint64_t esr; +}; + #define TARGET_EXTRA_MAGIC 0x45585401 struct target_extra_context { @@ -201,6 +208,14 @@ static void target_setup_fpsimd_record(struct target_fpsimd_context *fpsimd, } } +static void target_setup_esr_record(struct target_esr_context *ctx, + CPUARMState *env) +{ + __put_user(TARGET_ESR_MAGIC, &ctx->head.magic); + __put_user(sizeof(*ctx), &ctx->head.size); + __put_user(env->cp15.esr_el[1], &ctx->esr); +} + static void target_setup_extra_record(struct target_extra_context *extra, uint64_t datap, uint32_t extra_size) { @@ -531,6 +546,9 @@ static int target_restore_sigframe(CPUARMState *env, fpsimd = (struct target_fpsimd_context *)ctx; break; + case TARGET_ESR_MAGIC: + break; /* ignore */ + case TARGET_SVE_MAGIC: if (sve || size < sizeof(struct target_sve_context)) { goto err; @@ -683,7 +701,7 @@ static void target_setup_frame(int usig, struct target_sigaction *ka, uc.tuc_mcontext.__reserved), }; int fpsimd_ofs, fr_ofs, sve_ofs = 0, za_ofs = 0, tpidr2_ofs = 0; - int zt_ofs = 0; + int zt_ofs = 0, esr_ofs = 0; int sve_size = 0, za_size = 0, tpidr2_size = 0, zt_size = 0; struct target_rt_sigframe *frame; struct target_rt_frame_record *fr; @@ -693,6 +711,15 @@ static void target_setup_frame(int usig, struct target_sigaction *ka, fpsimd_ofs = alloc_sigframe_space(sizeof(struct target_fpsimd_context), &layout); + /* + * In user mode, ESR_EL1 is only set by cpu_loop while queueing the + * signal, and it's only valid for the one sync insn. + */ + if (env->cp15.esr_el[1]) { + esr_ofs = alloc_sigframe_space(sizeof(struct target_esr_context), + &layout); + } + /* SVE state needs saving only if it exists. */ if (cpu_isar_feature(aa64_sve, env_archcpu(env)) || cpu_isar_feature(aa64_sme, env_archcpu(env))) { @@ -754,6 +781,11 @@ static void target_setup_frame(int usig, struct target_sigaction *ka, target_setup_general_frame(frame, env, set); target_setup_fpsimd_record((void *)frame + fpsimd_ofs, env); + if (esr_ofs) { + target_setup_esr_record((void *)frame + esr_ofs, env); + /* Leave ESR_EL1 clear while it's not relevant. */ + env->cp15.esr_el[1] = 0; + } target_setup_end_record((void *)frame + layout.std_end_ofs); if (layout.extra_ofs) { target_setup_extra_record((void *)frame + layout.extra_ofs, diff --git a/linux-user/arm/elfload.c b/linux-user/arm/elfload.c index 308ed23..b1a4db4 100644 --- a/linux-user/arm/elfload.c +++ b/linux-user/arm/elfload.c @@ -76,7 +76,6 @@ abi_ulong get_elf_hwcap(CPUState *cs) /* EDSP is in v5TE and above, but all our v5 CPUs are v5TE */ GET_FEATURE(ARM_FEATURE_V5, ARM_HWCAP_ARM_EDSP); - GET_FEATURE(ARM_FEATURE_IWMMXT, ARM_HWCAP_ARM_IWMMXT); GET_FEATURE(ARM_FEATURE_THUMB2EE, ARM_HWCAP_ARM_THUMBEE); GET_FEATURE(ARM_FEATURE_NEON, ARM_HWCAP_ARM_NEON); GET_FEATURE(ARM_FEATURE_V6K, ARM_HWCAP_ARM_TLS); diff --git a/linux-user/arm/signal.c b/linux-user/arm/signal.c index 8db1c4b..3b387cd 100644 --- a/linux-user/arm/signal.c +++ b/linux-user/arm/signal.c @@ -76,21 +76,7 @@ struct target_vfp_sigframe { struct target_user_vfp_exc ufp_exc; } __attribute__((__aligned__(8))); -struct target_iwmmxt_sigframe { - abi_ulong magic; - abi_ulong size; - uint64_t regs[16]; - /* Note that not all the coprocessor control registers are stored here */ - uint32_t wcssf; - uint32_t wcasf; - uint32_t wcgr0; - uint32_t wcgr1; - uint32_t wcgr2; - uint32_t wcgr3; -} __attribute__((__aligned__(8))); - #define TARGET_VFP_MAGIC 0x56465001 -#define TARGET_IWMMXT_MAGIC 0x12ef842a struct sigframe { @@ -267,25 +253,6 @@ static abi_ulong *setup_sigframe_vfp(abi_ulong *regspace, CPUARMState *env) return (abi_ulong*)(vfpframe+1); } -static abi_ulong *setup_sigframe_iwmmxt(abi_ulong *regspace, CPUARMState *env) -{ - int i; - struct target_iwmmxt_sigframe *iwmmxtframe; - iwmmxtframe = (struct target_iwmmxt_sigframe *)regspace; - __put_user(TARGET_IWMMXT_MAGIC, &iwmmxtframe->magic); - __put_user(sizeof(*iwmmxtframe), &iwmmxtframe->size); - for (i = 0; i < 16; i++) { - __put_user(env->iwmmxt.regs[i], &iwmmxtframe->regs[i]); - } - __put_user(env->vfp.xregs[ARM_IWMMXT_wCSSF], &iwmmxtframe->wcssf); - __put_user(env->vfp.xregs[ARM_IWMMXT_wCASF], &iwmmxtframe->wcssf); - __put_user(env->vfp.xregs[ARM_IWMMXT_wCGR0], &iwmmxtframe->wcgr0); - __put_user(env->vfp.xregs[ARM_IWMMXT_wCGR1], &iwmmxtframe->wcgr1); - __put_user(env->vfp.xregs[ARM_IWMMXT_wCGR2], &iwmmxtframe->wcgr2); - __put_user(env->vfp.xregs[ARM_IWMMXT_wCGR3], &iwmmxtframe->wcgr3); - return (abi_ulong*)(iwmmxtframe+1); -} - static void setup_sigframe(struct target_ucontext *uc, target_sigset_t *set, CPUARMState *env) { @@ -306,9 +273,6 @@ static void setup_sigframe(struct target_ucontext *uc, if (cpu_isar_feature(aa32_vfp_simd, env_archcpu(env))) { regspace = setup_sigframe_vfp(regspace, env); } - if (arm_feature(env, ARM_FEATURE_IWMMXT)) { - regspace = setup_sigframe_iwmmxt(regspace, env); - } /* Write terminating magic word */ __put_user(0, regspace); @@ -435,31 +399,6 @@ static abi_ulong *restore_sigframe_vfp(CPUARMState *env, abi_ulong *regspace) return (abi_ulong*)(vfpframe + 1); } -static abi_ulong *restore_sigframe_iwmmxt(CPUARMState *env, - abi_ulong *regspace) -{ - int i; - abi_ulong magic, sz; - struct target_iwmmxt_sigframe *iwmmxtframe; - iwmmxtframe = (struct target_iwmmxt_sigframe *)regspace; - - __get_user(magic, &iwmmxtframe->magic); - __get_user(sz, &iwmmxtframe->size); - if (magic != TARGET_IWMMXT_MAGIC || sz != sizeof(*iwmmxtframe)) { - return 0; - } - for (i = 0; i < 16; i++) { - __get_user(env->iwmmxt.regs[i], &iwmmxtframe->regs[i]); - } - __get_user(env->vfp.xregs[ARM_IWMMXT_wCSSF], &iwmmxtframe->wcssf); - __get_user(env->vfp.xregs[ARM_IWMMXT_wCASF], &iwmmxtframe->wcssf); - __get_user(env->vfp.xregs[ARM_IWMMXT_wCGR0], &iwmmxtframe->wcgr0); - __get_user(env->vfp.xregs[ARM_IWMMXT_wCGR1], &iwmmxtframe->wcgr1); - __get_user(env->vfp.xregs[ARM_IWMMXT_wCGR2], &iwmmxtframe->wcgr2); - __get_user(env->vfp.xregs[ARM_IWMMXT_wCGR3], &iwmmxtframe->wcgr3); - return (abi_ulong*)(iwmmxtframe + 1); -} - static int do_sigframe_return(CPUARMState *env, target_ulong context_addr, struct target_ucontext *uc) @@ -482,12 +421,6 @@ static int do_sigframe_return(CPUARMState *env, return 1; } } - if (arm_feature(env, ARM_FEATURE_IWMMXT)) { - regspace = restore_sigframe_iwmmxt(env, regspace); - if (!regspace) { - return 1; - } - } target_restore_altstack(&uc->tuc_stack, env); diff --git a/qemu-options.hx b/qemu-options.hx index ab23f14..075f4be 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -1231,6 +1231,13 @@ SRST ``aw-bits=val`` (val between 32 and 64, default depends on machine) This decides the address width of the IOVA address space. +``-device arm-smmuv3,primary-bus=id`` + This is only supported by ``-machine virt`` (ARM). + + ``primary-bus=id`` + Accepts either the default root complex (pcie.0) or a + pxb-pcie based root complex. + ERST DEF("name", HAS_ARG, QEMU_OPTION_name, @@ -5347,13 +5354,6 @@ SRST specified, the former is passed to semihosting as it always takes precedence. ERST -DEF("old-param", 0, QEMU_OPTION_old_param, - "-old-param old param mode\n", QEMU_ARCH_ARM) -SRST -``-old-param`` - Old param mode (ARM only). -ERST - DEF("sandbox", HAS_ARG, QEMU_OPTION_sandbox, \ "-sandbox on[,obsolete=allow|deny][,elevateprivileges=allow|deny|children]\n" \ " [,spawn=allow|deny][,resourcecontrol=allow|deny]\n" \ diff --git a/scripts/userfaultfd-wrlat.py b/scripts/userfaultfd-wrlat.py index 0684be4..a61a9ab 100755 --- a/scripts/userfaultfd-wrlat.py +++ b/scripts/userfaultfd-wrlat.py @@ -17,7 +17,6 @@ # This work is licensed under the terms of the GNU GPL, version 2 or # later. See the COPYING file in the top-level directory. -from __future__ import print_function from bcc import BPF from ctypes import c_ushort, c_int, c_ulonglong from time import sleep diff --git a/system/globals.c b/system/globals.c index 9640c95..98f9876 100644 --- a/system/globals.c +++ b/system/globals.c @@ -52,7 +52,6 @@ bool vga_interface_created; Chardev *parallel_hds[MAX_PARALLEL_PORTS]; QEMUOptionRom option_rom[MAX_OPTION_ROMS]; int nb_option_roms; -int old_param; const char *qemu_name; unsigned int nb_prom_envs; const char *prom_envs[MAX_PROM_ENVS]; diff --git a/system/vl.c b/system/vl.c index 3b7057e..00f3694 100644 --- a/system/vl.c +++ b/system/vl.c @@ -3524,10 +3524,6 @@ void qemu_init(int argc, char **argv) prom_envs[nb_prom_envs] = optarg; nb_prom_envs++; break; - case QEMU_OPTION_old_param: - warn_report("-old-param is deprecated"); - old_param = 1; - break; case QEMU_OPTION_rtc: opts = qemu_opts_parse_noisily(qemu_find_opts("rtc"), optarg, false); diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index c9506aa..2a4826f 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -408,10 +408,19 @@ FIELD(HFGRTR_EL2, ERXPFGCTL_EL1, 47, 1) FIELD(HFGRTR_EL2, ERXPFGCDN_EL1, 48, 1) FIELD(HFGRTR_EL2, ERXADDR_EL1, 49, 1) FIELD(HFGRTR_EL2, NACCDATA_EL1, 50, 1) -/* 51-53: RES0 */ +/* 51: RES0 */ +FIELD(HFGRTR_EL2, NGCS_EL0, 52, 1) +FIELD(HFGRTR_EL2, NGCS_EL1, 53, 1) FIELD(HFGRTR_EL2, NSMPRI_EL1, 54, 1) FIELD(HFGRTR_EL2, NTPIDR2_EL0, 55, 1) -/* 56-63: RES0 */ +FIELD(HFGRTR_EL2, NRCWMASK_EL1, 56, 1) +FIELD(HFGRTR_EL2, NPIRE0_EL1, 57, 1) +FIELD(HFGRTR_EL2, NPIR_EL1, 58, 1) +FIELD(HFGRTR_EL2, NPOR_EL0, 59, 1) +FIELD(HFGRTR_EL2, NPOR_EL1, 60, 1) +FIELD(HFGRTR_EL2, NS2POR_EL1, 61, 1) +FIELD(HFGRTR_EL2, NMAIR2_EL1, 62, 1) +FIELD(HFGRTR_EL2, NAMAIR2_EL1, 63, 1) /* These match HFGRTR but bits for RO registers are RES0 */ FIELD(HFGWTR_EL2, AFSR0_EL1, 0, 1) @@ -452,8 +461,18 @@ FIELD(HFGWTR_EL2, ERXPFGCTL_EL1, 47, 1) FIELD(HFGWTR_EL2, ERXPFGCDN_EL1, 48, 1) FIELD(HFGWTR_EL2, ERXADDR_EL1, 49, 1) FIELD(HFGWTR_EL2, NACCDATA_EL1, 50, 1) +FIELD(HFGWTR_EL2, NGCS_EL0, 52, 1) +FIELD(HFGWTR_EL2, NGCS_EL1, 53, 1) FIELD(HFGWTR_EL2, NSMPRI_EL1, 54, 1) FIELD(HFGWTR_EL2, NTPIDR2_EL0, 55, 1) +FIELD(HFGWTR_EL2, NRCWMASK_EL1, 56, 1) +FIELD(HFGWTR_EL2, NPIRE0_EL1, 57, 1) +FIELD(HFGWTR_EL2, NPIR_EL1, 58, 1) +FIELD(HFGWTR_EL2, NPOR_EL0, 59, 1) +FIELD(HFGWTR_EL2, NPOR_EL1, 60, 1) +FIELD(HFGWTR_EL2, NS2POR_EL1, 61, 1) +FIELD(HFGWTR_EL2, NMAIR2_EL1, 62, 1) +FIELD(HFGWTR_EL2, NAMAIR2_EL1, 63, 1) FIELD(HFGITR_EL2, ICIALLUIS, 0, 1) FIELD(HFGITR_EL2, ICIALLU, 1, 1) @@ -512,6 +531,11 @@ FIELD(HFGITR_EL2, SVC_EL1, 53, 1) FIELD(HFGITR_EL2, DCCVAC, 54, 1) FIELD(HFGITR_EL2, NBRBINJ, 55, 1) FIELD(HFGITR_EL2, NBRBIALL, 56, 1) +FIELD(HFGITR_EL2, NGCSPUSHM_EL1, 57, 1) +FIELD(HFGITR_EL2, NGCSSTR_EL1, 58, 1) +FIELD(HFGITR_EL2, NGCSEPP, 59, 1) +FIELD(HFGITR_EL2, COSPRCTX, 60, 1) +FIELD(HFGITR_EL2, ATS1E1A, 62, 1) FIELD(HDFGRTR_EL2, DBGBCRN_EL1, 0, 1) FIELD(HDFGRTR_EL2, DBGBVRN_EL1, 1, 1) @@ -830,6 +854,7 @@ typedef enum FGTBit { DO_BIT(HFGITR, DVPRCTX), DO_BIT(HFGITR, CPPRCTX), DO_BIT(HFGITR, DCCVAC), + DO_BIT(HFGITR, ATS1E1A), } FGTBit; #undef DO_BIT diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h index e49e0ae..512eeaf 100644 --- a/target/arm/cpu-features.h +++ b/target/arm/cpu-features.h @@ -619,6 +619,11 @@ static inline bool isar_feature_aa64_lut(const ARMISARegisters *id) return FIELD_EX64_IDREG(id, ID_AA64ISAR2, LUT); } +static inline bool isar_feature_aa64_ats1a(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64ISAR2, ATS1A); +} + static inline bool isar_feature_aa64_fp_simd(const ARMISARegisters *id) { /* We always set the AdvSIMD and FP fields identically. */ diff --git a/target/arm/cpu.c b/target/arm/cpu.c index d0f6fcd..02e2a31 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -247,10 +247,6 @@ static void arm_cpu_reset_hold(Object *obj, ResetType type) cpu->power_state = cs->start_powered_off ? PSCI_OFF : PSCI_ON; - if (arm_feature(env, ARM_FEATURE_IWMMXT)) { - env->iwmmxt.cregs[ARM_IWMMXT_wCID] = 0x69051000 | 'Q'; - } - if (arm_feature(env, ARM_FEATURE_AARCH64)) { /* 64 bit CPUs always start in 64 bit mode */ env->aarch64 = true; @@ -349,11 +345,6 @@ static void arm_cpu_reset_hold(Object *obj, ResetType type) env->uncached_cpsr = ARM_CPU_MODE_USR; /* For user mode we must enable access to coprocessors */ env->vfp.xregs[ARM_VFP_FPEXC] = 1 << 30; - if (arm_feature(env, ARM_FEATURE_IWMMXT)) { - env->cp15.c15_cpar = 3; - } else if (arm_feature(env, ARM_FEATURE_XSCALE)) { - env->cp15.c15_cpar = 1; - } #else /* @@ -2259,14 +2250,6 @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) } - /* - * We rely on no XScale CPU having VFP so we can use the same bits in the - * TB flags field for VECSTRIDE and XSCALE_CPAR. - */ - assert(arm_feature(env, ARM_FEATURE_AARCH64) || - !cpu_isar_feature(aa32_vfp_simd, cpu) || - !arm_feature(env, ARM_FEATURE_XSCALE)); - #ifndef CONFIG_USER_ONLY { int pagebits; @@ -2623,14 +2606,10 @@ static const Property arm_cpu_properties[] = { static const gchar *arm_gdb_arch_name(CPUState *cs) { ARMCPU *cpu = ARM_CPU(cs); - CPUARMState *env = &cpu->env; if (arm_gdbstub_is_aarch64(cpu)) { return "aarch64"; } - if (arm_feature(env, ARM_FEATURE_IWMMXT)) { - return "iwmmxt"; - } return "arm"; } diff --git a/target/arm/cpu.h b/target/arm/cpu.h index c15d79a..1c0deb7 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -341,7 +341,6 @@ typedef struct CPUArchState { uint64_t vsctlr; /* Virtualization System control register. */ uint64_t cpacr_el1; /* Architectural feature access control register */ uint64_t cptr_el[4]; /* ARMv8 feature trap registers */ - uint32_t c1_xscaleauxcr; /* XScale auxiliary control register. */ uint64_t sder; /* Secure debug enable register. */ uint32_t nsacr; /* Non-secure access control register. */ union { /* MMU translation table base 0. */ @@ -513,7 +512,6 @@ typedef struct CPUArchState { uint64_t cntvoff_el2; /* Counter Virtual Offset register */ uint64_t cntpoff_el2; /* Counter Physical Offset register */ ARMGenericTimer c14_timer[NUM_GTIMERS]; - uint32_t c15_cpar; /* XScale Coprocessor Access Register */ uint32_t c15_ticonfig; /* TI925T configuration byte. */ uint32_t c15_i_max; /* Maximum D-cache dirty line index. */ uint32_t c15_i_min; /* Minimum D-cache dirty line index. */ @@ -699,14 +697,6 @@ typedef struct CPUArchState { */ uint64_t exclusive_high; - /* iwMMXt coprocessor state. */ - struct { - uint64_t regs[16]; - uint64_t val; - - uint32_t cregs[16]; - } iwmmxt; - struct { ARMPACKey apia; ARMPACKey apib; @@ -935,6 +925,7 @@ struct ArchCPU { DynamicGDBFeatureInfo dyn_sysreg_feature; DynamicGDBFeatureInfo dyn_svereg_feature; + DynamicGDBFeatureInfo dyn_smereg_feature; DynamicGDBFeatureInfo dyn_m_systemreg_feature; DynamicGDBFeatureInfo dyn_m_secextreg_feature; @@ -1865,16 +1856,6 @@ enum arm_cpu_mode { /* QEMU-internal value meaning "FPSCR, but we care only about NZCV" */ #define QEMU_VFP_FPSCR_NZCV 0xffff -/* iwMMXt coprocessor control registers. */ -#define ARM_IWMMXT_wCID 0 -#define ARM_IWMMXT_wCon 1 -#define ARM_IWMMXT_wCSSF 2 -#define ARM_IWMMXT_wCASF 3 -#define ARM_IWMMXT_wCGR0 8 -#define ARM_IWMMXT_wCGR1 9 -#define ARM_IWMMXT_wCGR2 10 -#define ARM_IWMMXT_wCGR3 11 - /* V7M CCR bits */ FIELD(V7M_CCR, NONBASETHRDENA, 0, 1) FIELD(V7M_CCR, USERSETMPEND, 1, 1) @@ -2444,8 +2425,6 @@ QEMU_BUILD_BUG_ON(ARRAY_SIZE(((ARMCPU *)0)->ccsidr) <= R_V7M_CSSELR_INDEX_MASK); */ enum arm_features { ARM_FEATURE_AUXCR, /* ARM1026 Auxiliary control register. */ - ARM_FEATURE_XSCALE, /* Intel XScale extensions. */ - ARM_FEATURE_IWMMXT, /* Intel iwMMXt extension. */ ARM_FEATURE_V6, ARM_FEATURE_V6K, ARM_FEATURE_V7, @@ -3025,13 +3004,6 @@ FIELD(TBFLAG_AM32, THUMB, 23, 1) /* Not cached. */ */ FIELD(TBFLAG_A32, VECLEN, 0, 3) /* Not cached. */ FIELD(TBFLAG_A32, VECSTRIDE, 3, 2) /* Not cached. */ -/* - * We store the bottom two bits of the CPAR as TB flags and handle - * checks on the other bits at runtime. This shares the same bits as - * VECSTRIDE, which is OK as no XScale CPU has VFP. - * Not cached, because VECLEN+VECSTRIDE are not cached. - */ -FIELD(TBFLAG_A32, XSCALE_CPAR, 5, 2) FIELD(TBFLAG_A32, VFPEN, 7, 1) /* Partially cached, minus FPEXC. */ FIELD(TBFLAG_A32, SCTLR__B, 8, 1) /* Cannot overlap with SCTLR_B */ FIELD(TBFLAG_A32, HSTR_ACTIVE, 9, 1) diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c index ce4497a..2d331ff 100644 --- a/target/arm/gdbstub.c +++ b/target/arm/gdbstub.c @@ -527,7 +527,8 @@ void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu) * registers so we don't need to include both. */ #ifdef TARGET_AARCH64 - if (isar_feature_aa64_sve(&cpu->isar)) { + if (isar_feature_aa64_sve(&cpu->isar) || + isar_feature_aa64_sme(&cpu->isar)) { GDBFeature *feature = arm_gen_dynamic_svereg_feature(cs, cs->gdb_num_regs); gdb_register_coprocessor(cs, aarch64_gdb_get_sve_reg, aarch64_gdb_set_sve_reg, feature, 0); @@ -537,6 +538,13 @@ void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu) gdb_find_static_feature("aarch64-fpu.xml"), 0); } + + if (isar_feature_aa64_sme(&cpu->isar)) { + GDBFeature *sme_feature = + arm_gen_dynamic_smereg_feature(cs, cs->gdb_num_regs); + gdb_register_coprocessor(cs, aarch64_gdb_get_sme_reg, + aarch64_gdb_set_sme_reg, sme_feature, 0); + } /* * Note that we report pauth information via the feature name * org.gnu.gdb.aarch64.pauth_v2, not org.gnu.gdb.aarch64.pauth. diff --git a/target/arm/gdbstub64.c b/target/arm/gdbstub64.c index 08e2858..3bccde2 100644 --- a/target/arm/gdbstub64.c +++ b/target/arm/gdbstub64.c @@ -249,6 +249,90 @@ int aarch64_gdb_set_sve_reg(CPUState *cs, uint8_t *buf, int reg) return 0; } +int aarch64_gdb_get_sme_reg(CPUState *cs, GByteArray *buf, int reg) +{ + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; + + switch (reg) { + case 0: /* svg register */ + { + int vq = 0; + if (FIELD_EX64(env->svcr, SVCR, SM)) { + vq = sve_vqm1_for_el_sm(env, arm_current_el(env), + FIELD_EX64(env->svcr, SVCR, SM)) + 1; + } + /* svg = vector granules (2 * vector quardwords) in streaming mode */ + return gdb_get_reg64(buf, vq * 2); + } + case 1: /* svcr register */ + return gdb_get_reg64(buf, env->svcr); + case 2: /* za register */ + { + int len = 0; + int vq = cpu->sme_max_vq; + int svl = vq * 16; + for (int i = 0; i < svl; i++) { + for (int q = 0; q < vq; q++) { + len += gdb_get_reg128(buf, + env->za_state.za[i].d[q * 2 + 1], + env->za_state.za[i].d[q * 2]); + } + } + return len; + } + default: + /* gdbstub asked for something out of range */ + qemu_log_mask(LOG_UNIMP, "%s: out of range register %d", __func__, reg); + break; + } + + return 0; +} + +int aarch64_gdb_set_sme_reg(CPUState *cs, uint8_t *buf, int reg) +{ + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; + + switch (reg) { + case 0: /* svg register */ + /* cannot set svg via gdbstub */ + return 8; + case 1: /* svcr register */ + aarch64_set_svcr(env, ldq_le_p(buf), + R_SVCR_SM_MASK | R_SVCR_ZA_MASK); + return 8; + case 2: /* za register */ + { + int len = 0; + int vq = cpu->sme_max_vq; + int svl = vq * 16; + for (int i = 0; i < svl; i++) { + for (int q = 0; q < vq; q++) { + if (target_big_endian()) { + env->za_state.za[i].d[q * 2 + 1] = ldq_p(buf); + buf += 8; + env->za_state.za[i].d[q * 2] = ldq_p(buf); + } else{ + env->za_state.za[i].d[q * 2] = ldq_p(buf); + buf += 8; + env->za_state.za[i].d[q * 2 + 1] = ldq_p(buf); + } + buf += 8; + len += 16; + } + } + return len; + } + default: + /* gdbstub asked for something out of range */ + break; + } + + return 0; +} + int aarch64_gdb_get_pauth_reg(CPUState *cs, GByteArray *buf, int reg) { ARMCPU *cpu = ARM_CPU(cs); @@ -413,6 +497,41 @@ GDBFeature *arm_gen_dynamic_svereg_feature(CPUState *cs, int base_reg) return &cpu->dyn_svereg_feature.desc; } +GDBFeature *arm_gen_dynamic_smereg_feature(CPUState *cs, int base_reg) +{ + ARMCPU *cpu = ARM_CPU(cs); + int vq = cpu->sme_max_vq; + int svl = vq * 16; + GDBFeatureBuilder builder; + int reg = 0; + + gdb_feature_builder_init(&builder, &cpu->dyn_smereg_feature.desc, + "org.gnu.gdb.aarch64.sme", "sme-registers.xml", + base_reg); + + + /* Create the sme_bv vector type. */ + gdb_feature_builder_append_tag( + &builder, "<vector id=\"sme_bv\" type=\"uint8\" count=\"%d\"/>", + svl); + + /* Create the sme_bvv vector type. */ + gdb_feature_builder_append_tag( + &builder, "<vector id=\"sme_bvv\" type=\"sme_bv\" count=\"%d\"/>", + svl); + + /* Define the svg, svcr, and za registers. */ + + gdb_feature_builder_append_reg(&builder, "svg", 64, reg++, "int", NULL); + gdb_feature_builder_append_reg(&builder, "svcr", 64, reg++, "int", NULL); + gdb_feature_builder_append_reg(&builder, "za", svl * svl * 8, reg++, + "sme_bvv", NULL); + + gdb_feature_builder_end(&builder); + + return &cpu->dyn_smereg_feature.desc; +} + #ifdef CONFIG_USER_ONLY int aarch64_gdb_get_tag_ctl_reg(CPUState *cs, GByteArray *buf, int reg) { diff --git a/target/arm/helper.c b/target/arm/helper.c index 19637e7..fa8dfac 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -2923,39 +2923,6 @@ static const ARMCPRegInfo omap_cp_reginfo[] = { .type = ARM_CP_CONST | ARM_CP_OVERRIDE, .resetvalue = 0 }, }; -static void xscale_cpar_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - env->cp15.c15_cpar = value & 0x3fff; -} - -static const ARMCPRegInfo xscale_cp_reginfo[] = { - { .name = "XSCALE_CPAR", - .cp = 15, .crn = 15, .crm = 1, .opc1 = 0, .opc2 = 0, .access = PL1_RW, - .fieldoffset = offsetof(CPUARMState, cp15.c15_cpar), .resetvalue = 0, - .writefn = xscale_cpar_write, }, - { .name = "XSCALE_AUXCR", - .cp = 15, .crn = 1, .crm = 0, .opc1 = 0, .opc2 = 1, .access = PL1_RW, - .fieldoffset = offsetof(CPUARMState, cp15.c1_xscaleauxcr), - .resetvalue = 0, }, - /* - * XScale specific cache-lockdown: since we have no cache we NOP these - * and hope the guest does not really rely on cache behaviour. - */ - { .name = "XSCALE_LOCK_ICACHE_LINE", - .cp = 15, .opc1 = 0, .crn = 9, .crm = 1, .opc2 = 0, - .access = PL1_W, .type = ARM_CP_NOP }, - { .name = "XSCALE_UNLOCK_ICACHE", - .cp = 15, .opc1 = 0, .crn = 9, .crm = 1, .opc2 = 1, - .access = PL1_W, .type = ARM_CP_NOP }, - { .name = "XSCALE_DCACHE_LOCK", - .cp = 15, .opc1 = 0, .crn = 9, .crm = 2, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_NOP }, - { .name = "XSCALE_UNLOCK_DCACHE", - .cp = 15, .opc1 = 0, .crn = 9, .crm = 2, .opc2 = 1, - .access = PL1_W, .type = ARM_CP_NOP }, -}; - static const ARMCPRegInfo dummy_c15_cp_reginfo[] = { /* * RAZ/WI the whole crn=15 space, when we don't have a more specific @@ -3346,16 +3313,6 @@ static void sctlr_write(CPUARMState *env, const ARMCPRegInfo *ri, /* This may enable/disable the MMU, so do a TLB flush. */ tlb_flush(CPU(cpu)); - - if (tcg_enabled() && ri->type & ARM_CP_SUPPRESS_TB_END) { - /* - * Normally we would always end the TB on an SCTLR write; see the - * comment in ARMCPRegInfo sctlr initialization below for why Xscale - * is special. Setting ARM_CP_SUPPRESS_TB_END also stops the rebuild - * of hflags from the translator, so do it here. - */ - arm_rebuild_hflags(env); - } } static void mdcr_el3_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -4563,11 +4520,6 @@ static void define_arm_vh_e2h_redirects_aliases(ARMCPU *cpu) { K(3, 0, 14, 1, 0), K(3, 4, 14, 1, 0), K(3, 5, 14, 1, 0), "CNTKCTL", "CNTHCTL_EL2", "CNTKCTL_EL12" }, - /* - * Note that redirection of ZCR is mentioned in the description - * of ZCR_EL2, and aliasing in the description of ZCR_EL1, but - * not in the summary table. - */ { K(3, 0, 1, 2, 0), K(3, 4, 1, 2, 0), K(3, 5, 1, 2, 0), "ZCR_EL1", "ZCR_EL2", "ZCR_EL12", isar_feature_aa64_sve }, { K(3, 0, 1, 2, 6), K(3, 4, 1, 2, 6), K(3, 5, 1, 2, 6), @@ -6899,9 +6851,6 @@ void register_cp_regs_for_features(ARMCPU *cpu) if (arm_feature(env, ARM_FEATURE_STRONGARM)) { define_arm_cp_regs(cpu, strongarm_cp_reginfo); } - if (arm_feature(env, ARM_FEATURE_XSCALE)) { - define_arm_cp_regs(cpu, xscale_cp_reginfo); - } if (arm_feature(env, ARM_FEATURE_DUMMY_C15_REGS)) { define_arm_cp_regs(cpu, dummy_c15_cp_reginfo); } @@ -7250,14 +7199,6 @@ void register_cp_regs_for_features(ARMCPU *cpu) .writefn = sctlr_write, .resetvalue = cpu->reset_sctlr, .raw_writefn = raw_write, }; - if (arm_feature(env, ARM_FEATURE_XSCALE)) { - /* - * Normally we would always end the TB on an SCTLR write, but Linux - * arch/arm/mach-pxa/sleep.S expects two instructions following - * an MMU enable to execute from cache. Imitate this behaviour. - */ - sctlr.type |= ARM_CP_SUPPRESS_TB_END; - } define_one_arm_cp_reg(cpu, &sctlr); if (arm_feature(env, ARM_FEATURE_PMSA) && diff --git a/target/arm/internals.h b/target/arm/internals.h index f5a1e75..532fabc 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -1602,30 +1602,27 @@ bool get_phys_addr(CPUARMState *env, vaddr address, __attribute__((nonnull)); /** - * get_phys_addr_with_space_nogpc: get the physical address for a virtual - * address + * get_phys_addr_for_at: * @env: CPUARMState * @address: virtual address to get physical address for - * @access_type: 0 for read, 1 for write, 2 for execute - * @memop: memory operation feeding this access, or 0 for none + * @prot_check: PAGE_{READ,WRITE,EXEC}, or 0 * @mmu_idx: MMU index indicating required translation regime * @space: security space for the access * @result: set on translation success. * @fi: set to fault info if the translation fails * - * Similar to get_phys_addr, but use the given security space and don't perform - * a Granule Protection Check on the resulting address. - */ -bool get_phys_addr_with_space_nogpc(CPUARMState *env, vaddr address, - MMUAccessType access_type, MemOp memop, - ARMMMUIdx mmu_idx, ARMSecuritySpace space, - GetPhysAddrResult *result, - ARMMMUFaultInfo *fi) + * Similar to get_phys_addr, but for use by AccessType_AT, i.e. + * system instructions for address translation. + */ +bool get_phys_addr_for_at(CPUARMState *env, vaddr address, unsigned prot_check, + ARMMMUIdx mmu_idx, ARMSecuritySpace space, + GetPhysAddrResult *result, ARMMMUFaultInfo *fi) __attribute__((nonnull)); bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, - MMUAccessType access_type, ARMMMUIdx mmu_idx, - bool is_secure, GetPhysAddrResult *result, + MMUAccessType access_type, unsigned prot_check, + ARMMMUIdx mmu_idx, bool is_secure, + GetPhysAddrResult *result, ARMMMUFaultInfo *fi, uint32_t *mregion); void arm_log_exception(CPUState *cs); @@ -1820,8 +1817,11 @@ static inline uint64_t pmu_counter_mask(CPUARMState *env) } GDBFeature *arm_gen_dynamic_svereg_feature(CPUState *cpu, int base_reg); +GDBFeature *arm_gen_dynamic_smereg_feature(CPUState *cpu, int base_reg); int aarch64_gdb_get_sve_reg(CPUState *cs, GByteArray *buf, int reg); int aarch64_gdb_set_sve_reg(CPUState *cs, uint8_t *buf, int reg); +int aarch64_gdb_get_sme_reg(CPUState *cs, GByteArray *buf, int reg); +int aarch64_gdb_set_sme_reg(CPUState *cs, uint8_t *buf, int reg); int aarch64_gdb_get_fpu_reg(CPUState *cs, GByteArray *buf, int reg); int aarch64_gdb_set_fpu_reg(CPUState *cs, uint8_t *buf, int reg); int aarch64_gdb_get_pauth_reg(CPUState *cs, GByteArray *buf, int reg); diff --git a/target/arm/kvm.c b/target/arm/kvm.c index 6672344..c1ec665 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -900,6 +900,58 @@ bool write_kvmstate_to_list(ARMCPU *cpu) return ok; } +/* pretty-print a KVM register */ +#define CP_REG_ARM64_SYSREG_OP(_reg, _op) \ + ((uint8_t)((_reg & CP_REG_ARM64_SYSREG_ ## _op ## _MASK) >> \ + CP_REG_ARM64_SYSREG_ ## _op ## _SHIFT)) + +static gchar *kvm_print_sve_register_name(uint64_t regidx) +{ + uint16_t sve_reg = regidx & 0x000000000000ffff; + + if (regidx == KVM_REG_ARM64_SVE_VLS) { + return g_strdup_printf("SVE VLS"); + } + /* zreg, preg, ffr */ + switch (sve_reg & 0xfc00) { + case 0: + return g_strdup_printf("SVE zreg n:%d slice:%d", + (sve_reg & 0x03e0) >> 5, sve_reg & 0x001f); + case 0x04: + return g_strdup_printf("SVE preg n:%d slice:%d", + (sve_reg & 0x01e0) >> 5, sve_reg & 0x001f); + case 0x06: + return g_strdup_printf("SVE ffr slice:%d", sve_reg & 0x001f); + default: + return g_strdup_printf("SVE ???"); + } +} + +static gchar *kvm_print_register_name(uint64_t regidx) +{ + switch ((regidx & KVM_REG_ARM_COPROC_MASK)) { + case KVM_REG_ARM_CORE: + return g_strdup_printf("core reg %"PRIx64, regidx); + case KVM_REG_ARM_DEMUX: + return g_strdup_printf("demuxed reg %"PRIx64, regidx); + case KVM_REG_ARM64_SYSREG: + return g_strdup_printf("op0:%d op1:%d crn:%d crm:%d op2:%d", + CP_REG_ARM64_SYSREG_OP(regidx, OP0), + CP_REG_ARM64_SYSREG_OP(regidx, OP1), + CP_REG_ARM64_SYSREG_OP(regidx, CRN), + CP_REG_ARM64_SYSREG_OP(regidx, CRM), + CP_REG_ARM64_SYSREG_OP(regidx, OP2)); + case KVM_REG_ARM_FW: + return g_strdup_printf("fw reg %d", (int)(regidx & 0xffff)); + case KVM_REG_ARM64_SVE: + return kvm_print_sve_register_name(regidx); + case KVM_REG_ARM_FW_FEAT_BMAP: + return g_strdup_printf("fw feat reg %d", (int)(regidx & 0xffff)); + default: + return g_strdup_printf("%"PRIx64, regidx); + } +} + bool write_list_to_kvmstate(ARMCPU *cpu, int level) { CPUState *cs = CPU(cpu); @@ -927,11 +979,45 @@ bool write_list_to_kvmstate(ARMCPU *cpu, int level) g_assert_not_reached(); } if (ret) { + gchar *reg_str = kvm_print_register_name(regidx); + /* We might fail for "unknown register" and also for * "you tried to set a register which is constant with * a different value from what it actually contains". */ ok = false; + switch (ret) { + case -ENOENT: + error_report("Could not set register %s: unknown to KVM", + reg_str); + break; + case -EINVAL: + if ((regidx & KVM_REG_SIZE_MASK) == KVM_REG_SIZE_U32) { + if (!kvm_get_one_reg(cs, regidx, &v32)) { + error_report("Could not set register %s to %x (is %x)", + reg_str, (uint32_t)cpu->cpreg_values[i], + v32); + } else { + error_report("Could not set register %s to %x", + reg_str, (uint32_t)cpu->cpreg_values[i]); + } + } else /* U64 */ { + uint64_t v64; + + if (!kvm_get_one_reg(cs, regidx, &v64)) { + error_report("Could not set register %s to %"PRIx64" (is %"PRIx64")", + reg_str, cpu->cpreg_values[i], v64); + } else { + error_report("Could not set register %s to %"PRIx64, + reg_str, cpu->cpreg_values[i]); + } + } + break; + default: + error_report("Could not set register %s: %s", + reg_str, strerror(-ret)); + } + g_free(reg_str); } } return ok; diff --git a/target/arm/machine.c b/target/arm/machine.c index 6986915..6666a0c 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -221,26 +221,6 @@ static const VMStateDescription vmstate_vfp = { } }; -static bool iwmmxt_needed(void *opaque) -{ - ARMCPU *cpu = opaque; - CPUARMState *env = &cpu->env; - - return arm_feature(env, ARM_FEATURE_IWMMXT); -} - -static const VMStateDescription vmstate_iwmmxt = { - .name = "cpu/iwmmxt", - .version_id = 1, - .minimum_version_id = 1, - .needed = iwmmxt_needed, - .fields = (const VMStateField[]) { - VMSTATE_UINT64_ARRAY(env.iwmmxt.regs, ARMCPU, 16), - VMSTATE_UINT32_ARRAY(env.iwmmxt.cregs, ARMCPU, 16), - VMSTATE_END_OF_LIST() - } -}; - /* The expression ARM_MAX_VQ - 2 is 0 for pure AArch32 build, * and ARMPredicateReg is actively empty. This triggers errors * in the expansion of the VMSTATE macros. @@ -1102,7 +1082,6 @@ const VMStateDescription vmstate_arm_cpu = { }, .subsections = (const VMStateDescription * const []) { &vmstate_vfp, - &vmstate_iwmmxt, &vmstate_m, &vmstate_thumb2ee, /* pmsav7_rnr must come before pmsav7 so that we have the diff --git a/target/arm/ptw.c b/target/arm/ptw.c index ed5c728..6344971 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -59,11 +59,23 @@ typedef struct S1Translate { */ bool in_debug; /* + * in_at: is this AccessType_AT? + * This is also set for debug, because at heart that is also + * an address translation, and simplifies a test. + */ + bool in_at; + /* * If this is stage 2 of a stage 1+2 page table walk, then this must * be true if stage 1 is an EL0 access; otherwise this is ignored. * Stage 2 is indicated by in_mmu_idx set to ARMMMUIdx_Stage2{,_S}. */ bool in_s1_is_el0; + /* + * The set of PAGE_* bits to be use in the permission check. + * This is normally directly related to the access_type, but + * may be suppressed for debug or AT insns. + */ + uint8_t in_prot_check; bool out_rw; bool out_be; ARMSecuritySpace out_space; @@ -581,6 +593,7 @@ static bool S1_ptw_translate(CPUARMState *env, S1Translate *ptw, .in_ptw_idx = ptw_idx_for_stage_2(env, s2_mmu_idx), .in_space = s2_space, .in_debug = true, + .in_prot_check = PAGE_READ, }; GetPhysAddrResult s2 = { }; @@ -1061,11 +1074,10 @@ static bool get_phys_addr_v5(CPUARMState *env, S1Translate *ptw, ap = (desc >> (4 + ((address >> 9) & 6))) & 3; result->f.lg_page_size = 12; break; - case 3: /* 1k page, or ARMv6/XScale "extended small (4k) page" */ + case 3: /* 1k page, or ARMv6 "extended small (4k) page" */ if (type == 1) { - /* ARMv6/XScale extended small page format */ - if (arm_feature(env, ARM_FEATURE_XSCALE) - || arm_feature(env, ARM_FEATURE_V6)) { + /* ARMv6 extended small page format */ + if (arm_feature(env, ARM_FEATURE_V6)) { phys_addr = (desc & 0xfffff000) | (address & 0xfff); result->f.lg_page_size = 12; } else { @@ -1089,7 +1101,7 @@ static bool get_phys_addr_v5(CPUARMState *env, S1Translate *ptw, } result->f.prot = ap_to_rw_prot(env, ptw->in_mmu_idx, ap, domain_prot); result->f.prot |= result->f.prot ? PAGE_EXEC : 0; - if (!(result->f.prot & (1 << access_type))) { + if (ptw->in_prot_check & ~result->f.prot) { /* Access permission fault. */ fi->type = ARMFault_Permission; goto do_fault; @@ -1243,7 +1255,7 @@ static bool get_phys_addr_v6(CPUARMState *env, S1Translate *ptw, result->f.prot = get_S1prot(env, mmu_idx, false, user_rw, prot_rw, xn, pxn, result->f.attrs.space, out_space); - if (!(result->f.prot & (1 << access_type))) { + if (ptw->in_prot_check & ~result->f.prot) { /* Access permission fault. */ fi->type = ARMFault_Permission; goto do_fault; @@ -1922,7 +1934,12 @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, descaddr &= ~(hwaddr)(page_size - 1); descaddr |= (address & (page_size - 1)); - if (likely(!ptw->in_debug)) { + /* + * For AccessType_AT, DB is not updated (AArch64.SetDirtyFlag), + * and it is IMPLEMENTATION DEFINED whether AF is updated + * (AArch64.SetAccessFlag; qemu chooses to not update). + */ + if (likely(!ptw->in_at)) { /* * Access flag. * If HA is enabled, prepare to update the descriptor below. @@ -2123,7 +2140,7 @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, result->f.tlb_fill_flags = 0; } - if (!(result->f.prot & (1 << access_type))) { + if (ptw->in_prot_check & ~result->f.prot) { fi->type = ARMFault_Permission; goto do_fault; } @@ -2537,7 +2554,7 @@ static bool get_phys_addr_pmsav7(CPUARMState *env, fi->type = ARMFault_Permission; fi->level = 1; - return !(result->f.prot & (1 << access_type)); + return (ptw->in_prot_check & ~result->f.prot) != 0; } static uint32_t *regime_rbar(CPUARMState *env, ARMMMUIdx mmu_idx, @@ -2561,8 +2578,9 @@ static uint32_t *regime_rlar(CPUARMState *env, ARMMMUIdx mmu_idx, } bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, - MMUAccessType access_type, ARMMMUIdx mmu_idx, - bool secure, GetPhysAddrResult *result, + MMUAccessType access_type, unsigned prot_check, + ARMMMUIdx mmu_idx, bool secure, + GetPhysAddrResult *result, ARMMMUFaultInfo *fi, uint32_t *mregion) { /* @@ -2750,7 +2768,7 @@ bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, if (arm_feature(env, ARM_FEATURE_M)) { fi->level = 1; } - return !(result->f.prot & (1 << access_type)); + return (prot_check & ~result->f.prot) != 0; } static bool v8m_is_sau_exempt(CPUARMState *env, @@ -2952,8 +2970,8 @@ static bool get_phys_addr_pmsav8(CPUARMState *env, } } - ret = pmsav8_mpu_lookup(env, address, access_type, mmu_idx, secure, - result, fi, NULL); + ret = pmsav8_mpu_lookup(env, address, access_type, ptw->in_prot_check, + mmu_idx, secure, result, fi, NULL); if (sattrs.subpage) { result->f.lg_page_size = 0; } @@ -3537,18 +3555,26 @@ static bool get_phys_addr_gpc(CPUARMState *env, S1Translate *ptw, return false; } -bool get_phys_addr_with_space_nogpc(CPUARMState *env, vaddr address, - MMUAccessType access_type, MemOp memop, - ARMMMUIdx mmu_idx, ARMSecuritySpace space, - GetPhysAddrResult *result, - ARMMMUFaultInfo *fi) +bool get_phys_addr_for_at(CPUARMState *env, vaddr address, + unsigned prot_check, ARMMMUIdx mmu_idx, + ARMSecuritySpace space, GetPhysAddrResult *result, + ARMMMUFaultInfo *fi) { S1Translate ptw = { .in_mmu_idx = mmu_idx, .in_space = space, + .in_at = true, + .in_prot_check = prot_check, }; - return get_phys_addr_nogpc(env, &ptw, address, access_type, - memop, result, fi); + /* + * I_MXTJT: Granule protection checks are not performed on the final + * address of a successful translation. This is a translation not a + * memory reference, so MMU_DATA_LOAD is arbitrary (the exact protection + * check is handled or bypassed by .in_prot_check) and "memop = MO_8" + * bypasses any alignment check. + */ + return get_phys_addr_nogpc(env, &ptw, address, + MMU_DATA_LOAD, MO_8, result, fi); } static ARMSecuritySpace @@ -3624,6 +3650,7 @@ bool get_phys_addr(CPUARMState *env, vaddr address, S1Translate ptw = { .in_mmu_idx = mmu_idx, .in_space = arm_mmu_idx_to_security_space(env, mmu_idx), + .in_prot_check = 1 << access_type, }; return get_phys_addr_gpc(env, &ptw, address, access_type, @@ -3637,6 +3664,8 @@ static hwaddr arm_cpu_get_phys_page(CPUARMState *env, vaddr addr, .in_mmu_idx = mmu_idx, .in_space = arm_mmu_idx_to_security_space(env, mmu_idx), .in_debug = true, + .in_at = true, + .in_prot_check = 0, }; GetPhysAddrResult res = {}; ARMMMUFaultInfo fi = {}; diff --git a/target/arm/tcg/cpregs-at.c b/target/arm/tcg/cpregs-at.c index 398a61d..0e8f229 100644 --- a/target/arm/tcg/cpregs-at.c +++ b/target/arm/tcg/cpregs-at.c @@ -24,22 +24,15 @@ static int par_el1_shareability(GetPhysAddrResult *res) } static uint64_t do_ats_write(CPUARMState *env, uint64_t value, - MMUAccessType access_type, ARMMMUIdx mmu_idx, + unsigned prot_check, ARMMMUIdx mmu_idx, ARMSecuritySpace ss) { - bool ret; uint64_t par64; bool format64 = false; ARMMMUFaultInfo fi = {}; GetPhysAddrResult res = {}; - - /* - * I_MXTJT: Granule protection checks are not performed on the final - * address of a successful translation. This is a translation not a - * memory reference, so "memop = none = 0". - */ - ret = get_phys_addr_with_space_nogpc(env, value, access_type, 0, - mmu_idx, ss, &res, &fi); + bool ret = get_phys_addr_for_at(env, value, prot_check, + mmu_idx, ss, &res, &fi); /* * ATS operations only do S1 or S1+S2 translations, so we never @@ -198,7 +191,7 @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value, static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { - MMUAccessType access_type = ri->opc2 & 1 ? MMU_DATA_STORE : MMU_DATA_LOAD; + unsigned access_perm = ri->opc2 & 1 ? PAGE_WRITE : PAGE_READ; uint64_t par64; ARMMMUIdx mmu_idx; int el = arm_current_el(env); @@ -260,7 +253,7 @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) g_assert_not_reached(); } - par64 = do_ats_write(env, value, access_type, mmu_idx, ss); + par64 = do_ats_write(env, value, access_perm, mmu_idx, ss); A32_BANKED_CURRENT_REG_SET(env, par, par64); } @@ -268,11 +261,11 @@ static void ats_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) static void ats1h_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { - MMUAccessType access_type = ri->opc2 & 1 ? MMU_DATA_STORE : MMU_DATA_LOAD; + unsigned access_perm = ri->opc2 & 1 ? PAGE_WRITE : PAGE_READ; uint64_t par64; /* There is no SecureEL2 for AArch32. */ - par64 = do_ats_write(env, value, access_type, ARMMMUIdx_E2, + par64 = do_ats_write(env, value, access_perm, ARMMMUIdx_E2, ARMSS_NonSecure); A32_BANKED_CURRENT_REG_SET(env, par, par64); @@ -316,7 +309,7 @@ static CPAccessResult at_s1e01_access(CPUARMState *env, const ARMCPRegInfo *ri, static void ats_write64(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { - MMUAccessType access_type = ri->opc2 & 1 ? MMU_DATA_STORE : MMU_DATA_LOAD; + unsigned access_perm = ri->opc2 & 1 ? PAGE_WRITE : PAGE_READ; ARMMMUIdx mmu_idx; uint64_t hcr_el2 = arm_hcr_el2_eff(env); bool regime_e20 = (hcr_el2 & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE); @@ -359,7 +352,7 @@ static void ats_write64(CPUARMState *env, const ARMCPRegInfo *ri, } ss = for_el3 ? arm_security_space(env) : arm_security_space_below_el3(env); - env->cp15.par_el[1] = do_ats_write(env, value, access_type, mmu_idx, ss); + env->cp15.par_el[1] = do_ats_write(env, value, access_perm, mmu_idx, ss); } static CPAccessResult ats_access(CPUARMState *env, const ARMCPRegInfo *ri, @@ -495,6 +488,47 @@ static const ARMCPRegInfo ats1cp_reginfo[] = { .writefn = ats_write }, }; +static void ats_s1e1a(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) +{ + uint64_t hcr_el2 = arm_hcr_el2_eff(env); + bool regime_e20 = (hcr_el2 & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE); + ARMMMUIdx mmu_idx = regime_e20 ? ARMMMUIdx_E20_2 : ARMMMUIdx_Stage1_E1; + ARMSecuritySpace ss = arm_security_space_below_el3(env); + + env->cp15.par_el[1] = do_ats_write(env, value, 0, mmu_idx, ss); +} + +static void ats_s1e2a(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) +{ + uint64_t hcr_el2 = arm_hcr_el2_eff(env); + ARMMMUIdx mmu_idx = hcr_el2 & HCR_E2H ? ARMMMUIdx_E20_2 : ARMMMUIdx_E2; + ARMSecuritySpace ss = arm_security_space_below_el3(env); + + env->cp15.par_el[1] = do_ats_write(env, value, 0, mmu_idx, ss); +} + +static void ats_s1e3a(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) +{ + env->cp15.par_el[1] = do_ats_write(env, value, 0, ARMMMUIdx_E3, + arm_security_space(env)); +} + +static const ARMCPRegInfo ats1a_reginfo[] = { + { .name = "AT_S1E1A", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 7, .crm = 9, .opc2 = 2, + .access = PL1_W, .type = ARM_CP_NO_RAW | ARM_CP_RAISES_EXC, + .fgt = FGT_ATS1E1A, + .accessfn = at_s1e01_access, .writefn = ats_s1e1a }, + { .name = "AT_S1E2A", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 7, .crm = 9, .opc2 = 2, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_RAISES_EXC, + .accessfn = at_s1e2_access, .writefn = ats_s1e2a }, + { .name = "AT_S1E3A", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 7, .crm = 9, .opc2 = 2, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_RAISES_EXC, + .writefn = ats_s1e3a }, +}; + void define_at_insn_regs(ARMCPU *cpu) { CPUARMState *env = &cpu->env; @@ -516,4 +550,7 @@ void define_at_insn_regs(ARMCPU *cpu) if (cpu_isar_feature(aa32_ats1e1, cpu)) { define_arm_cp_regs(cpu, ats1cp_reginfo); } + if (cpu_isar_feature(aa64_ats1a, cpu)) { + define_arm_cp_regs(cpu, ats1a_reginfo); + } } diff --git a/target/arm/tcg/cpu32.c b/target/arm/tcg/cpu32.c index a2a23ea..f076141 100644 --- a/target/arm/tcg/cpu32.c +++ b/target/arm/tcg/cpu32.c @@ -807,144 +807,6 @@ static void sa1110_initfn(Object *obj) cpu->reset_sctlr = 0x00000070; } -static void pxa250_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "marvell,xscale"; - set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_XSCALE); - cpu->midr = 0x69052100; - cpu->ctr = 0xd172172; - cpu->reset_sctlr = 0x00000078; -} - -static void pxa255_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "marvell,xscale"; - set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_XSCALE); - cpu->midr = 0x69052d00; - cpu->ctr = 0xd172172; - cpu->reset_sctlr = 0x00000078; -} - -static void pxa260_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "marvell,xscale"; - set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_XSCALE); - cpu->midr = 0x69052903; - cpu->ctr = 0xd172172; - cpu->reset_sctlr = 0x00000078; -} - -static void pxa261_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "marvell,xscale"; - set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_XSCALE); - cpu->midr = 0x69052d05; - cpu->ctr = 0xd172172; - cpu->reset_sctlr = 0x00000078; -} - -static void pxa262_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "marvell,xscale"; - set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_XSCALE); - cpu->midr = 0x69052d06; - cpu->ctr = 0xd172172; - cpu->reset_sctlr = 0x00000078; -} - -static void pxa270a0_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "marvell,xscale"; - set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_XSCALE); - set_feature(&cpu->env, ARM_FEATURE_IWMMXT); - cpu->midr = 0x69054110; - cpu->ctr = 0xd172172; - cpu->reset_sctlr = 0x00000078; -} - -static void pxa270a1_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "marvell,xscale"; - set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_XSCALE); - set_feature(&cpu->env, ARM_FEATURE_IWMMXT); - cpu->midr = 0x69054111; - cpu->ctr = 0xd172172; - cpu->reset_sctlr = 0x00000078; -} - -static void pxa270b0_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "marvell,xscale"; - set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_XSCALE); - set_feature(&cpu->env, ARM_FEATURE_IWMMXT); - cpu->midr = 0x69054112; - cpu->ctr = 0xd172172; - cpu->reset_sctlr = 0x00000078; -} - -static void pxa270b1_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "marvell,xscale"; - set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_XSCALE); - set_feature(&cpu->env, ARM_FEATURE_IWMMXT); - cpu->midr = 0x69054113; - cpu->ctr = 0xd172172; - cpu->reset_sctlr = 0x00000078; -} - -static void pxa270c0_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "marvell,xscale"; - set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_XSCALE); - set_feature(&cpu->env, ARM_FEATURE_IWMMXT); - cpu->midr = 0x69054114; - cpu->ctr = 0xd172172; - cpu->reset_sctlr = 0x00000078; -} - -static void pxa270c5_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "marvell,xscale"; - set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_XSCALE); - set_feature(&cpu->env, ARM_FEATURE_IWMMXT); - cpu->midr = 0x69054117; - cpu->ctr = 0xd172172; - cpu->reset_sctlr = 0x00000078; -} - #ifndef TARGET_AARCH64 /* * -cpu max: a CPU with as many features enabled as our emulation supports. @@ -1032,31 +894,6 @@ static const ARMCPUInfo arm_tcg_cpus[] = { { .name = "ti925t", .initfn = ti925t_initfn }, { .name = "sa1100", .initfn = sa1100_initfn }, { .name = "sa1110", .initfn = sa1110_initfn }, - { .name = "pxa250", .initfn = pxa250_initfn, - .deprecation_note = "iwMMXt CPUs are no longer supported", }, - { .name = "pxa255", .initfn = pxa255_initfn, - .deprecation_note = "iwMMXt CPUs are no longer supported", }, - { .name = "pxa260", .initfn = pxa260_initfn, - .deprecation_note = "iwMMXt CPUs are no longer supported", }, - { .name = "pxa261", .initfn = pxa261_initfn, - .deprecation_note = "iwMMXt CPUs are no longer supported", }, - { .name = "pxa262", .initfn = pxa262_initfn, - .deprecation_note = "iwMMXt CPUs are no longer supported", }, - /* "pxa270" is an alias for "pxa270-a0" */ - { .name = "pxa270", .initfn = pxa270a0_initfn, - .deprecation_note = "iwMMXt CPUs are no longer supported", }, - { .name = "pxa270-a0", .initfn = pxa270a0_initfn, - .deprecation_note = "iwMMXt CPUs are no longer supported", }, - { .name = "pxa270-a1", .initfn = pxa270a1_initfn, - .deprecation_note = "iwMMXt CPUs are no longer supported", }, - { .name = "pxa270-b0", .initfn = pxa270b0_initfn, - .deprecation_note = "iwMMXt CPUs are no longer supported", }, - { .name = "pxa270-b1", .initfn = pxa270b1_initfn, - .deprecation_note = "iwMMXt CPUs are no longer supported", }, - { .name = "pxa270-c0", .initfn = pxa270c0_initfn, - .deprecation_note = "iwMMXt CPUs are no longer supported", }, - { .name = "pxa270-c5", .initfn = pxa270c5_initfn, - .deprecation_note = "iwMMXt CPUs are no longer supported", }, #ifndef TARGET_AARCH64 { .name = "max", .initfn = arm_max_initfn }, #endif diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index b8b1981..abef6a2 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -1179,6 +1179,7 @@ void aarch64_max_tcg_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64ISAR2, BC, 1); /* FEAT_HBC */ t = FIELD_DP64(t, ID_AA64ISAR2, WFXT, 2); /* FEAT_WFxT */ t = FIELD_DP64(t, ID_AA64ISAR2, CSSC, 1); /* FEAT_CSSC */ + t = FIELD_DP64(t, ID_AA64ISAR2, ATS1A, 1); /* FEAT_ATS1A */ SET_IDREG(isar, ID_AA64ISAR2, t); t = GET_IDREG(isar, ID_AA64PFR0); diff --git a/target/arm/tcg/helper.h b/target/arm/tcg/helper.h index 4da32db..4636d1b 100644 --- a/target/arm/tcg/helper.h +++ b/target/arm/tcg/helper.h @@ -444,101 +444,6 @@ DEF_HELPER_3(neon_acgt_f32, i32, i32, i32, fpst) DEF_HELPER_3(neon_acge_f64, i64, i64, i64, fpst) DEF_HELPER_3(neon_acgt_f64, i64, i64, i64, fpst) -/* iwmmxt_helper.c */ -DEF_HELPER_2(iwmmxt_maddsq, i64, i64, i64) -DEF_HELPER_2(iwmmxt_madduq, i64, i64, i64) -DEF_HELPER_2(iwmmxt_sadb, i64, i64, i64) -DEF_HELPER_2(iwmmxt_sadw, i64, i64, i64) -DEF_HELPER_2(iwmmxt_mulslw, i64, i64, i64) -DEF_HELPER_2(iwmmxt_mulshw, i64, i64, i64) -DEF_HELPER_2(iwmmxt_mululw, i64, i64, i64) -DEF_HELPER_2(iwmmxt_muluhw, i64, i64, i64) -DEF_HELPER_2(iwmmxt_macsw, i64, i64, i64) -DEF_HELPER_2(iwmmxt_macuw, i64, i64, i64) -DEF_HELPER_1(iwmmxt_setpsr_nz, i32, i64) - -#define DEF_IWMMXT_HELPER_SIZE_ENV(name) \ -DEF_HELPER_3(iwmmxt_##name##b, i64, env, i64, i64) \ -DEF_HELPER_3(iwmmxt_##name##w, i64, env, i64, i64) \ -DEF_HELPER_3(iwmmxt_##name##l, i64, env, i64, i64) \ - -DEF_IWMMXT_HELPER_SIZE_ENV(unpackl) -DEF_IWMMXT_HELPER_SIZE_ENV(unpackh) - -DEF_HELPER_2(iwmmxt_unpacklub, i64, env, i64) -DEF_HELPER_2(iwmmxt_unpackluw, i64, env, i64) -DEF_HELPER_2(iwmmxt_unpacklul, i64, env, i64) -DEF_HELPER_2(iwmmxt_unpackhub, i64, env, i64) -DEF_HELPER_2(iwmmxt_unpackhuw, i64, env, i64) -DEF_HELPER_2(iwmmxt_unpackhul, i64, env, i64) -DEF_HELPER_2(iwmmxt_unpacklsb, i64, env, i64) -DEF_HELPER_2(iwmmxt_unpacklsw, i64, env, i64) -DEF_HELPER_2(iwmmxt_unpacklsl, i64, env, i64) -DEF_HELPER_2(iwmmxt_unpackhsb, i64, env, i64) -DEF_HELPER_2(iwmmxt_unpackhsw, i64, env, i64) -DEF_HELPER_2(iwmmxt_unpackhsl, i64, env, i64) - -DEF_IWMMXT_HELPER_SIZE_ENV(cmpeq) -DEF_IWMMXT_HELPER_SIZE_ENV(cmpgtu) -DEF_IWMMXT_HELPER_SIZE_ENV(cmpgts) - -DEF_IWMMXT_HELPER_SIZE_ENV(mins) -DEF_IWMMXT_HELPER_SIZE_ENV(minu) -DEF_IWMMXT_HELPER_SIZE_ENV(maxs) -DEF_IWMMXT_HELPER_SIZE_ENV(maxu) - -DEF_IWMMXT_HELPER_SIZE_ENV(subn) -DEF_IWMMXT_HELPER_SIZE_ENV(addn) -DEF_IWMMXT_HELPER_SIZE_ENV(subu) -DEF_IWMMXT_HELPER_SIZE_ENV(addu) -DEF_IWMMXT_HELPER_SIZE_ENV(subs) -DEF_IWMMXT_HELPER_SIZE_ENV(adds) - -DEF_HELPER_3(iwmmxt_avgb0, i64, env, i64, i64) -DEF_HELPER_3(iwmmxt_avgb1, i64, env, i64, i64) -DEF_HELPER_3(iwmmxt_avgw0, i64, env, i64, i64) -DEF_HELPER_3(iwmmxt_avgw1, i64, env, i64, i64) - -DEF_HELPER_3(iwmmxt_align, i64, i64, i64, i32) -DEF_HELPER_4(iwmmxt_insr, i64, i64, i32, i32, i32) - -DEF_HELPER_1(iwmmxt_bcstb, i64, i32) -DEF_HELPER_1(iwmmxt_bcstw, i64, i32) -DEF_HELPER_1(iwmmxt_bcstl, i64, i32) - -DEF_HELPER_1(iwmmxt_addcb, i64, i64) -DEF_HELPER_1(iwmmxt_addcw, i64, i64) -DEF_HELPER_1(iwmmxt_addcl, i64, i64) - -DEF_HELPER_1(iwmmxt_msbb, i32, i64) -DEF_HELPER_1(iwmmxt_msbw, i32, i64) -DEF_HELPER_1(iwmmxt_msbl, i32, i64) - -DEF_HELPER_3(iwmmxt_srlw, i64, env, i64, i32) -DEF_HELPER_3(iwmmxt_srll, i64, env, i64, i32) -DEF_HELPER_3(iwmmxt_srlq, i64, env, i64, i32) -DEF_HELPER_3(iwmmxt_sllw, i64, env, i64, i32) -DEF_HELPER_3(iwmmxt_slll, i64, env, i64, i32) -DEF_HELPER_3(iwmmxt_sllq, i64, env, i64, i32) -DEF_HELPER_3(iwmmxt_sraw, i64, env, i64, i32) -DEF_HELPER_3(iwmmxt_sral, i64, env, i64, i32) -DEF_HELPER_3(iwmmxt_sraq, i64, env, i64, i32) -DEF_HELPER_3(iwmmxt_rorw, i64, env, i64, i32) -DEF_HELPER_3(iwmmxt_rorl, i64, env, i64, i32) -DEF_HELPER_3(iwmmxt_rorq, i64, env, i64, i32) -DEF_HELPER_3(iwmmxt_shufh, i64, env, i64, i32) - -DEF_HELPER_3(iwmmxt_packuw, i64, env, i64, i64) -DEF_HELPER_3(iwmmxt_packul, i64, env, i64, i64) -DEF_HELPER_3(iwmmxt_packuq, i64, env, i64, i64) -DEF_HELPER_3(iwmmxt_packsw, i64, env, i64, i64) -DEF_HELPER_3(iwmmxt_packsl, i64, env, i64, i64) -DEF_HELPER_3(iwmmxt_packsq, i64, env, i64, i64) - -DEF_HELPER_3(iwmmxt_muladdsl, i64, i64, i32, i32) -DEF_HELPER_3(iwmmxt_muladdsw, i64, i64, i32, i32) -DEF_HELPER_3(iwmmxt_muladdswl, i64, i64, i32, i32) - DEF_HELPER_FLAGS_2(neon_unzip8, TCG_CALL_NO_RWG, void, ptr, ptr) DEF_HELPER_FLAGS_2(neon_unzip16, TCG_CALL_NO_RWG, void, ptr, ptr) DEF_HELPER_FLAGS_2(neon_qunzip8, TCG_CALL_NO_RWG, void, ptr, ptr) diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c index 59ab526..0189422 100644 --- a/target/arm/tcg/hflags.c +++ b/target/arm/tcg/hflags.c @@ -624,16 +624,9 @@ TCGTBCPUState arm_get_tb_cpu_state(CPUState *cs) DP_TBFLAG_M32(flags, MVE_NO_PRED, 1); } } else { - /* - * Note that XSCALE_CPAR shares bits with VECSTRIDE. - * Note that VECLEN+VECSTRIDE are RES0 for M-profile. - */ - if (arm_feature(env, ARM_FEATURE_XSCALE)) { - DP_TBFLAG_A32(flags, XSCALE_CPAR, env->cp15.c15_cpar); - } else { - DP_TBFLAG_A32(flags, VECLEN, env->vfp.vec_len); - DP_TBFLAG_A32(flags, VECSTRIDE, env->vfp.vec_stride); - } + /* Note that VECLEN+VECSTRIDE are RES0 for M-profile. */ + DP_TBFLAG_A32(flags, VECLEN, env->vfp.vec_len); + DP_TBFLAG_A32(flags, VECSTRIDE, env->vfp.vec_stride); if (env->vfp.xregs[ARM_VFP_FPEXC] & (1 << 30)) { DP_TBFLAG_A32(flags, VFPEN, 1); } diff --git a/target/arm/tcg/iwmmxt_helper.c b/target/arm/tcg/iwmmxt_helper.c deleted file mode 100644 index ba054b6..0000000 --- a/target/arm/tcg/iwmmxt_helper.c +++ /dev/null @@ -1,672 +0,0 @@ -/* - * iwMMXt micro operations for XScale. - * - * Copyright (c) 2007 OpenedHand, Ltd. - * Written by Andrzej Zaborowski <andrew@openedhand.com> - * Copyright (c) 2008 CodeSourcery - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" - -#include "cpu.h" - -#define HELPER_H "tcg/helper.h" -#include "exec/helper-proto.h.inc" - -/* iwMMXt macros extracted from GNU gdb. */ - -/* Set the SIMD wCASF flags for 8, 16, 32 or 64-bit operations. */ -#define SIMD8_SET(v, n, b) ((v != 0) << ((((b) + 1) * 4) + (n))) -#define SIMD16_SET(v, n, h) ((v != 0) << ((((h) + 1) * 8) + (n))) -#define SIMD32_SET(v, n, w) ((v != 0) << ((((w) + 1) * 16) + (n))) -#define SIMD64_SET(v, n) ((v != 0) << (32 + (n))) -/* Flags to pass as "n" above. */ -#define SIMD_NBIT -1 -#define SIMD_ZBIT -2 -#define SIMD_CBIT -3 -#define SIMD_VBIT -4 -/* Various status bit macros. */ -#define NBIT8(x) ((x) & 0x80) -#define NBIT16(x) ((x) & 0x8000) -#define NBIT32(x) ((x) & 0x80000000) -#define NBIT64(x) ((x) & 0x8000000000000000ULL) -#define ZBIT8(x) (((x) & 0xff) == 0) -#define ZBIT16(x) (((x) & 0xffff) == 0) -#define ZBIT32(x) (((x) & 0xffffffff) == 0) -#define ZBIT64(x) (x == 0) -/* Sign extension macros. */ -#define EXTEND8H(a) ((uint16_t) (int8_t) (a)) -#define EXTEND8(a) ((uint32_t) (int8_t) (a)) -#define EXTEND16(a) ((uint32_t) (int16_t) (a)) -#define EXTEND16S(a) ((int32_t) (int16_t) (a)) -#define EXTEND32(a) ((uint64_t) (int32_t) (a)) - -uint64_t HELPER(iwmmxt_maddsq)(uint64_t a, uint64_t b) -{ - a = (( - EXTEND16S((a >> 0) & 0xffff) * EXTEND16S((b >> 0) & 0xffff) + - EXTEND16S((a >> 16) & 0xffff) * EXTEND16S((b >> 16) & 0xffff) - ) & 0xffffffff) | ((uint64_t) ( - EXTEND16S((a >> 32) & 0xffff) * EXTEND16S((b >> 32) & 0xffff) + - EXTEND16S((a >> 48) & 0xffff) * EXTEND16S((b >> 48) & 0xffff) - ) << 32); - return a; -} - -uint64_t HELPER(iwmmxt_madduq)(uint64_t a, uint64_t b) -{ - a = (( - ((a >> 0) & 0xffff) * ((b >> 0) & 0xffff) + - ((a >> 16) & 0xffff) * ((b >> 16) & 0xffff) - ) & 0xffffffff) | (( - ((a >> 32) & 0xffff) * ((b >> 32) & 0xffff) + - ((a >> 48) & 0xffff) * ((b >> 48) & 0xffff) - ) << 32); - return a; -} - -uint64_t HELPER(iwmmxt_sadb)(uint64_t a, uint64_t b) -{ -#define abs(x) (((x) >= 0) ? x : -x) -#define SADB(SHR) abs((int) ((a >> SHR) & 0xff) - (int) ((b >> SHR) & 0xff)) - return - SADB(0) + SADB(8) + SADB(16) + SADB(24) + - SADB(32) + SADB(40) + SADB(48) + SADB(56); -#undef SADB -} - -uint64_t HELPER(iwmmxt_sadw)(uint64_t a, uint64_t b) -{ -#define SADW(SHR) \ - abs((int) ((a >> SHR) & 0xffff) - (int) ((b >> SHR) & 0xffff)) - return SADW(0) + SADW(16) + SADW(32) + SADW(48); -#undef SADW -} - -uint64_t HELPER(iwmmxt_mulslw)(uint64_t a, uint64_t b) -{ -#define MULS(SHR) ((uint64_t) ((( \ - EXTEND16S((a >> SHR) & 0xffff) * EXTEND16S((b >> SHR) & 0xffff) \ - ) >> 0) & 0xffff) << SHR) - return MULS(0) | MULS(16) | MULS(32) | MULS(48); -#undef MULS -} - -uint64_t HELPER(iwmmxt_mulshw)(uint64_t a, uint64_t b) -{ -#define MULS(SHR) ((uint64_t) ((( \ - EXTEND16S((a >> SHR) & 0xffff) * EXTEND16S((b >> SHR) & 0xffff) \ - ) >> 16) & 0xffff) << SHR) - return MULS(0) | MULS(16) | MULS(32) | MULS(48); -#undef MULS -} - -uint64_t HELPER(iwmmxt_mululw)(uint64_t a, uint64_t b) -{ -#define MULU(SHR) ((uint64_t) ((( \ - ((a >> SHR) & 0xffff) * ((b >> SHR) & 0xffff) \ - ) >> 0) & 0xffff) << SHR) - return MULU(0) | MULU(16) | MULU(32) | MULU(48); -#undef MULU -} - -uint64_t HELPER(iwmmxt_muluhw)(uint64_t a, uint64_t b) -{ -#define MULU(SHR) ((uint64_t) ((( \ - ((a >> SHR) & 0xffff) * ((b >> SHR) & 0xffff) \ - ) >> 16) & 0xffff) << SHR) - return MULU(0) | MULU(16) | MULU(32) | MULU(48); -#undef MULU -} - -uint64_t HELPER(iwmmxt_macsw)(uint64_t a, uint64_t b) -{ -#define MACS(SHR) ( \ - EXTEND16((a >> SHR) & 0xffff) * EXTEND16S((b >> SHR) & 0xffff)) - return (int64_t) (MACS(0) + MACS(16) + MACS(32) + MACS(48)); -#undef MACS -} - -uint64_t HELPER(iwmmxt_macuw)(uint64_t a, uint64_t b) -{ -#define MACU(SHR) ( \ - (uint32_t) ((a >> SHR) & 0xffff) * \ - (uint32_t) ((b >> SHR) & 0xffff)) - return MACU(0) + MACU(16) + MACU(32) + MACU(48); -#undef MACU -} - -#define NZBIT8(x, i) \ - SIMD8_SET(NBIT8((x) & 0xff), SIMD_NBIT, i) | \ - SIMD8_SET(ZBIT8((x) & 0xff), SIMD_ZBIT, i) -#define NZBIT16(x, i) \ - SIMD16_SET(NBIT16((x) & 0xffff), SIMD_NBIT, i) | \ - SIMD16_SET(ZBIT16((x) & 0xffff), SIMD_ZBIT, i) -#define NZBIT32(x, i) \ - SIMD32_SET(NBIT32((x) & 0xffffffff), SIMD_NBIT, i) | \ - SIMD32_SET(ZBIT32((x) & 0xffffffff), SIMD_ZBIT, i) -#define NZBIT64(x) \ - SIMD64_SET(NBIT64(x), SIMD_NBIT) | \ - SIMD64_SET(ZBIT64(x), SIMD_ZBIT) -#define IWMMXT_OP_UNPACK(S, SH0, SH1, SH2, SH3) \ -uint64_t HELPER(glue(iwmmxt_unpack, glue(S, b)))(CPUARMState *env, \ - uint64_t a, uint64_t b) \ -{ \ - a = \ - (((a >> SH0) & 0xff) << 0) | (((b >> SH0) & 0xff) << 8) | \ - (((a >> SH1) & 0xff) << 16) | (((b >> SH1) & 0xff) << 24) | \ - (((a >> SH2) & 0xff) << 32) | (((b >> SH2) & 0xff) << 40) | \ - (((a >> SH3) & 0xff) << 48) | (((b >> SH3) & 0xff) << 56); \ - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = \ - NZBIT8(a >> 0, 0) | NZBIT8(a >> 8, 1) | \ - NZBIT8(a >> 16, 2) | NZBIT8(a >> 24, 3) | \ - NZBIT8(a >> 32, 4) | NZBIT8(a >> 40, 5) | \ - NZBIT8(a >> 48, 6) | NZBIT8(a >> 56, 7); \ - return a; \ -} \ -uint64_t HELPER(glue(iwmmxt_unpack, glue(S, w)))(CPUARMState *env, \ - uint64_t a, uint64_t b) \ -{ \ - a = \ - (((a >> SH0) & 0xffff) << 0) | \ - (((b >> SH0) & 0xffff) << 16) | \ - (((a >> SH2) & 0xffff) << 32) | \ - (((b >> SH2) & 0xffff) << 48); \ - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = \ - NZBIT8(a >> 0, 0) | NZBIT8(a >> 16, 1) | \ - NZBIT8(a >> 32, 2) | NZBIT8(a >> 48, 3); \ - return a; \ -} \ -uint64_t HELPER(glue(iwmmxt_unpack, glue(S, l)))(CPUARMState *env, \ - uint64_t a, uint64_t b) \ -{ \ - a = \ - (((a >> SH0) & 0xffffffff) << 0) | \ - (((b >> SH0) & 0xffffffff) << 32); \ - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = \ - NZBIT32(a >> 0, 0) | NZBIT32(a >> 32, 1); \ - return a; \ -} \ -uint64_t HELPER(glue(iwmmxt_unpack, glue(S, ub)))(CPUARMState *env, \ - uint64_t x) \ -{ \ - x = \ - (((x >> SH0) & 0xff) << 0) | \ - (((x >> SH1) & 0xff) << 16) | \ - (((x >> SH2) & 0xff) << 32) | \ - (((x >> SH3) & 0xff) << 48); \ - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = \ - NZBIT16(x >> 0, 0) | NZBIT16(x >> 16, 1) | \ - NZBIT16(x >> 32, 2) | NZBIT16(x >> 48, 3); \ - return x; \ -} \ -uint64_t HELPER(glue(iwmmxt_unpack, glue(S, uw)))(CPUARMState *env, \ - uint64_t x) \ -{ \ - x = \ - (((x >> SH0) & 0xffff) << 0) | \ - (((x >> SH2) & 0xffff) << 32); \ - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = \ - NZBIT32(x >> 0, 0) | NZBIT32(x >> 32, 1); \ - return x; \ -} \ -uint64_t HELPER(glue(iwmmxt_unpack, glue(S, ul)))(CPUARMState *env, \ - uint64_t x) \ -{ \ - x = (((x >> SH0) & 0xffffffff) << 0); \ - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = NZBIT64(x >> 0); \ - return x; \ -} \ -uint64_t HELPER(glue(iwmmxt_unpack, glue(S, sb)))(CPUARMState *env, \ - uint64_t x) \ -{ \ - x = \ - ((uint64_t) EXTEND8H((x >> SH0) & 0xff) << 0) | \ - ((uint64_t) EXTEND8H((x >> SH1) & 0xff) << 16) | \ - ((uint64_t) EXTEND8H((x >> SH2) & 0xff) << 32) | \ - ((uint64_t) EXTEND8H((x >> SH3) & 0xff) << 48); \ - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = \ - NZBIT16(x >> 0, 0) | NZBIT16(x >> 16, 1) | \ - NZBIT16(x >> 32, 2) | NZBIT16(x >> 48, 3); \ - return x; \ -} \ -uint64_t HELPER(glue(iwmmxt_unpack, glue(S, sw)))(CPUARMState *env, \ - uint64_t x) \ -{ \ - x = \ - ((uint64_t) EXTEND16((x >> SH0) & 0xffff) << 0) | \ - ((uint64_t) EXTEND16((x >> SH2) & 0xffff) << 32); \ - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = \ - NZBIT32(x >> 0, 0) | NZBIT32(x >> 32, 1); \ - return x; \ -} \ -uint64_t HELPER(glue(iwmmxt_unpack, glue(S, sl)))(CPUARMState *env, \ - uint64_t x) \ -{ \ - x = EXTEND32((x >> SH0) & 0xffffffff); \ - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = NZBIT64(x >> 0); \ - return x; \ -} -IWMMXT_OP_UNPACK(l, 0, 8, 16, 24) -IWMMXT_OP_UNPACK(h, 32, 40, 48, 56) - -#define IWMMXT_OP_CMP(SUFF, Tb, Tw, Tl, O) \ -uint64_t HELPER(glue(iwmmxt_, glue(SUFF, b)))(CPUARMState *env, \ - uint64_t a, uint64_t b) \ -{ \ - a = \ - CMP(0, Tb, O, 0xff) | CMP(8, Tb, O, 0xff) | \ - CMP(16, Tb, O, 0xff) | CMP(24, Tb, O, 0xff) | \ - CMP(32, Tb, O, 0xff) | CMP(40, Tb, O, 0xff) | \ - CMP(48, Tb, O, 0xff) | CMP(56, Tb, O, 0xff); \ - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = \ - NZBIT8(a >> 0, 0) | NZBIT8(a >> 8, 1) | \ - NZBIT8(a >> 16, 2) | NZBIT8(a >> 24, 3) | \ - NZBIT8(a >> 32, 4) | NZBIT8(a >> 40, 5) | \ - NZBIT8(a >> 48, 6) | NZBIT8(a >> 56, 7); \ - return a; \ -} \ -uint64_t HELPER(glue(iwmmxt_, glue(SUFF, w)))(CPUARMState *env, \ - uint64_t a, uint64_t b) \ -{ \ - a = CMP(0, Tw, O, 0xffff) | CMP(16, Tw, O, 0xffff) | \ - CMP(32, Tw, O, 0xffff) | CMP(48, Tw, O, 0xffff); \ - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = \ - NZBIT16(a >> 0, 0) | NZBIT16(a >> 16, 1) | \ - NZBIT16(a >> 32, 2) | NZBIT16(a >> 48, 3); \ - return a; \ -} \ -uint64_t HELPER(glue(iwmmxt_, glue(SUFF, l)))(CPUARMState *env, \ - uint64_t a, uint64_t b) \ -{ \ - a = CMP(0, Tl, O, 0xffffffff) | \ - CMP(32, Tl, O, 0xffffffff); \ - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = \ - NZBIT32(a >> 0, 0) | NZBIT32(a >> 32, 1); \ - return a; \ -} -#define CMP(SHR, TYPE, OPER, MASK) ((((TYPE) ((a >> SHR) & MASK) OPER \ - (TYPE) ((b >> SHR) & MASK)) ? (uint64_t) MASK : 0) << SHR) -IWMMXT_OP_CMP(cmpeq, uint8_t, uint16_t, uint32_t, ==) -IWMMXT_OP_CMP(cmpgts, int8_t, int16_t, int32_t, >) -IWMMXT_OP_CMP(cmpgtu, uint8_t, uint16_t, uint32_t, >) -#undef CMP -#define CMP(SHR, TYPE, OPER, MASK) ((((TYPE) ((a >> SHR) & MASK) OPER \ - (TYPE) ((b >> SHR) & MASK)) ? a : b) & ((uint64_t) MASK << SHR)) -IWMMXT_OP_CMP(mins, int8_t, int16_t, int32_t, <) -IWMMXT_OP_CMP(minu, uint8_t, uint16_t, uint32_t, <) -IWMMXT_OP_CMP(maxs, int8_t, int16_t, int32_t, >) -IWMMXT_OP_CMP(maxu, uint8_t, uint16_t, uint32_t, >) -#undef CMP -#define CMP(SHR, TYPE, OPER, MASK) ((uint64_t) (((TYPE) ((a >> SHR) & MASK) \ - OPER (TYPE) ((b >> SHR) & MASK)) & MASK) << SHR) -IWMMXT_OP_CMP(subn, uint8_t, uint16_t, uint32_t, -) -IWMMXT_OP_CMP(addn, uint8_t, uint16_t, uint32_t, +) -#undef CMP -/* TODO Signed- and Unsigned-Saturation */ -#define CMP(SHR, TYPE, OPER, MASK) ((uint64_t) (((TYPE) ((a >> SHR) & MASK) \ - OPER (TYPE) ((b >> SHR) & MASK)) & MASK) << SHR) -IWMMXT_OP_CMP(subu, uint8_t, uint16_t, uint32_t, -) -IWMMXT_OP_CMP(addu, uint8_t, uint16_t, uint32_t, +) -IWMMXT_OP_CMP(subs, int8_t, int16_t, int32_t, -) -IWMMXT_OP_CMP(adds, int8_t, int16_t, int32_t, +) -#undef CMP -#undef IWMMXT_OP_CMP - -#define AVGB(SHR) ((( \ - ((a >> SHR) & 0xff) + ((b >> SHR) & 0xff) + round) >> 1) << SHR) -#define IWMMXT_OP_AVGB(r) \ -uint64_t HELPER(iwmmxt_avgb##r)(CPUARMState *env, uint64_t a, uint64_t b) \ -{ \ - const int round = r; \ - a = AVGB(0) | AVGB(8) | AVGB(16) | AVGB(24) | \ - AVGB(32) | AVGB(40) | AVGB(48) | AVGB(56); \ - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = \ - SIMD8_SET(ZBIT8((a >> 0) & 0xff), SIMD_ZBIT, 0) | \ - SIMD8_SET(ZBIT8((a >> 8) & 0xff), SIMD_ZBIT, 1) | \ - SIMD8_SET(ZBIT8((a >> 16) & 0xff), SIMD_ZBIT, 2) | \ - SIMD8_SET(ZBIT8((a >> 24) & 0xff), SIMD_ZBIT, 3) | \ - SIMD8_SET(ZBIT8((a >> 32) & 0xff), SIMD_ZBIT, 4) | \ - SIMD8_SET(ZBIT8((a >> 40) & 0xff), SIMD_ZBIT, 5) | \ - SIMD8_SET(ZBIT8((a >> 48) & 0xff), SIMD_ZBIT, 6) | \ - SIMD8_SET(ZBIT8((a >> 56) & 0xff), SIMD_ZBIT, 7); \ - return a; \ -} -IWMMXT_OP_AVGB(0) -IWMMXT_OP_AVGB(1) -#undef IWMMXT_OP_AVGB -#undef AVGB - -#define AVGW(SHR) ((( \ - ((a >> SHR) & 0xffff) + ((b >> SHR) & 0xffff) + round) >> 1) << SHR) -#define IWMMXT_OP_AVGW(r) \ -uint64_t HELPER(iwmmxt_avgw##r)(CPUARMState *env, uint64_t a, uint64_t b) \ -{ \ - const int round = r; \ - a = AVGW(0) | AVGW(16) | AVGW(32) | AVGW(48); \ - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = \ - SIMD16_SET(ZBIT16((a >> 0) & 0xffff), SIMD_ZBIT, 0) | \ - SIMD16_SET(ZBIT16((a >> 16) & 0xffff), SIMD_ZBIT, 1) | \ - SIMD16_SET(ZBIT16((a >> 32) & 0xffff), SIMD_ZBIT, 2) | \ - SIMD16_SET(ZBIT16((a >> 48) & 0xffff), SIMD_ZBIT, 3); \ - return a; \ -} -IWMMXT_OP_AVGW(0) -IWMMXT_OP_AVGW(1) -#undef IWMMXT_OP_AVGW -#undef AVGW - -uint64_t HELPER(iwmmxt_align)(uint64_t a, uint64_t b, uint32_t n) -{ - a >>= n << 3; - a |= b << (64 - (n << 3)); - return a; -} - -uint64_t HELPER(iwmmxt_insr)(uint64_t x, uint32_t a, uint32_t b, uint32_t n) -{ - x &= ~((uint64_t) b << n); - x |= (uint64_t) (a & b) << n; - return x; -} - -uint32_t HELPER(iwmmxt_setpsr_nz)(uint64_t x) -{ - return SIMD64_SET((x == 0), SIMD_ZBIT) | - SIMD64_SET((x & (1ULL << 63)), SIMD_NBIT); -} - -uint64_t HELPER(iwmmxt_bcstb)(uint32_t arg) -{ - arg &= 0xff; - return - ((uint64_t) arg << 0 ) | ((uint64_t) arg << 8 ) | - ((uint64_t) arg << 16) | ((uint64_t) arg << 24) | - ((uint64_t) arg << 32) | ((uint64_t) arg << 40) | - ((uint64_t) arg << 48) | ((uint64_t) arg << 56); -} - -uint64_t HELPER(iwmmxt_bcstw)(uint32_t arg) -{ - arg &= 0xffff; - return - ((uint64_t) arg << 0 ) | ((uint64_t) arg << 16) | - ((uint64_t) arg << 32) | ((uint64_t) arg << 48); -} - -uint64_t HELPER(iwmmxt_bcstl)(uint32_t arg) -{ - return arg | ((uint64_t) arg << 32); -} - -uint64_t HELPER(iwmmxt_addcb)(uint64_t x) -{ - return - ((x >> 0) & 0xff) + ((x >> 8) & 0xff) + - ((x >> 16) & 0xff) + ((x >> 24) & 0xff) + - ((x >> 32) & 0xff) + ((x >> 40) & 0xff) + - ((x >> 48) & 0xff) + ((x >> 56) & 0xff); -} - -uint64_t HELPER(iwmmxt_addcw)(uint64_t x) -{ - return - ((x >> 0) & 0xffff) + ((x >> 16) & 0xffff) + - ((x >> 32) & 0xffff) + ((x >> 48) & 0xffff); -} - -uint64_t HELPER(iwmmxt_addcl)(uint64_t x) -{ - return (x & 0xffffffff) + (x >> 32); -} - -uint32_t HELPER(iwmmxt_msbb)(uint64_t x) -{ - return - ((x >> 7) & 0x01) | ((x >> 14) & 0x02) | - ((x >> 21) & 0x04) | ((x >> 28) & 0x08) | - ((x >> 35) & 0x10) | ((x >> 42) & 0x20) | - ((x >> 49) & 0x40) | ((x >> 56) & 0x80); -} - -uint32_t HELPER(iwmmxt_msbw)(uint64_t x) -{ - return - ((x >> 15) & 0x01) | ((x >> 30) & 0x02) | - ((x >> 45) & 0x04) | ((x >> 52) & 0x08); -} - -uint32_t HELPER(iwmmxt_msbl)(uint64_t x) -{ - return ((x >> 31) & 0x01) | ((x >> 62) & 0x02); -} - -/* FIXME: Split wCASF setting into a separate op to avoid env use. */ -uint64_t HELPER(iwmmxt_srlw)(CPUARMState *env, uint64_t x, uint32_t n) -{ - x = (((x & (0xffffll << 0)) >> n) & (0xffffll << 0)) | - (((x & (0xffffll << 16)) >> n) & (0xffffll << 16)) | - (((x & (0xffffll << 32)) >> n) & (0xffffll << 32)) | - (((x & (0xffffll << 48)) >> n) & (0xffffll << 48)); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT16(x >> 0, 0) | NZBIT16(x >> 16, 1) | - NZBIT16(x >> 32, 2) | NZBIT16(x >> 48, 3); - return x; -} - -uint64_t HELPER(iwmmxt_srll)(CPUARMState *env, uint64_t x, uint32_t n) -{ - x = ((x & (0xffffffffll << 0)) >> n) | - ((x >> n) & (0xffffffffll << 32)); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT32(x >> 0, 0) | NZBIT32(x >> 32, 1); - return x; -} - -uint64_t HELPER(iwmmxt_srlq)(CPUARMState *env, uint64_t x, uint32_t n) -{ - x >>= n; - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = NZBIT64(x); - return x; -} - -uint64_t HELPER(iwmmxt_sllw)(CPUARMState *env, uint64_t x, uint32_t n) -{ - x = (((x & (0xffffll << 0)) << n) & (0xffffll << 0)) | - (((x & (0xffffll << 16)) << n) & (0xffffll << 16)) | - (((x & (0xffffll << 32)) << n) & (0xffffll << 32)) | - (((x & (0xffffll << 48)) << n) & (0xffffll << 48)); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT16(x >> 0, 0) | NZBIT16(x >> 16, 1) | - NZBIT16(x >> 32, 2) | NZBIT16(x >> 48, 3); - return x; -} - -uint64_t HELPER(iwmmxt_slll)(CPUARMState *env, uint64_t x, uint32_t n) -{ - x = ((x << n) & (0xffffffffll << 0)) | - ((x & (0xffffffffll << 32)) << n); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT32(x >> 0, 0) | NZBIT32(x >> 32, 1); - return x; -} - -uint64_t HELPER(iwmmxt_sllq)(CPUARMState *env, uint64_t x, uint32_t n) -{ - x <<= n; - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = NZBIT64(x); - return x; -} - -uint64_t HELPER(iwmmxt_sraw)(CPUARMState *env, uint64_t x, uint32_t n) -{ - x = ((uint64_t) ((EXTEND16(x >> 0) >> n) & 0xffff) << 0) | - ((uint64_t) ((EXTEND16(x >> 16) >> n) & 0xffff) << 16) | - ((uint64_t) ((EXTEND16(x >> 32) >> n) & 0xffff) << 32) | - ((uint64_t) ((EXTEND16(x >> 48) >> n) & 0xffff) << 48); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT16(x >> 0, 0) | NZBIT16(x >> 16, 1) | - NZBIT16(x >> 32, 2) | NZBIT16(x >> 48, 3); - return x; -} - -uint64_t HELPER(iwmmxt_sral)(CPUARMState *env, uint64_t x, uint32_t n) -{ - x = (((EXTEND32(x >> 0) >> n) & 0xffffffff) << 0) | - (((EXTEND32(x >> 32) >> n) & 0xffffffff) << 32); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT32(x >> 0, 0) | NZBIT32(x >> 32, 1); - return x; -} - -uint64_t HELPER(iwmmxt_sraq)(CPUARMState *env, uint64_t x, uint32_t n) -{ - x = (int64_t) x >> n; - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = NZBIT64(x); - return x; -} - -uint64_t HELPER(iwmmxt_rorw)(CPUARMState *env, uint64_t x, uint32_t n) -{ - x = ((((x & (0xffffll << 0)) >> n) | - ((x & (0xffffll << 0)) << (16 - n))) & (0xffffll << 0)) | - ((((x & (0xffffll << 16)) >> n) | - ((x & (0xffffll << 16)) << (16 - n))) & (0xffffll << 16)) | - ((((x & (0xffffll << 32)) >> n) | - ((x & (0xffffll << 32)) << (16 - n))) & (0xffffll << 32)) | - ((((x & (0xffffll << 48)) >> n) | - ((x & (0xffffll << 48)) << (16 - n))) & (0xffffll << 48)); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT16(x >> 0, 0) | NZBIT16(x >> 16, 1) | - NZBIT16(x >> 32, 2) | NZBIT16(x >> 48, 3); - return x; -} - -uint64_t HELPER(iwmmxt_rorl)(CPUARMState *env, uint64_t x, uint32_t n) -{ - x = ((x & (0xffffffffll << 0)) >> n) | - ((x >> n) & (0xffffffffll << 32)) | - ((x << (32 - n)) & (0xffffffffll << 0)) | - ((x & (0xffffffffll << 32)) << (32 - n)); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT32(x >> 0, 0) | NZBIT32(x >> 32, 1); - return x; -} - -uint64_t HELPER(iwmmxt_rorq)(CPUARMState *env, uint64_t x, uint32_t n) -{ - x = ror64(x, n); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = NZBIT64(x); - return x; -} - -uint64_t HELPER(iwmmxt_shufh)(CPUARMState *env, uint64_t x, uint32_t n) -{ - x = (((x >> ((n << 4) & 0x30)) & 0xffff) << 0) | - (((x >> ((n << 2) & 0x30)) & 0xffff) << 16) | - (((x >> ((n << 0) & 0x30)) & 0xffff) << 32) | - (((x >> ((n >> 2) & 0x30)) & 0xffff) << 48); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT16(x >> 0, 0) | NZBIT16(x >> 16, 1) | - NZBIT16(x >> 32, 2) | NZBIT16(x >> 48, 3); - return x; -} - -/* TODO: Unsigned-Saturation */ -uint64_t HELPER(iwmmxt_packuw)(CPUARMState *env, uint64_t a, uint64_t b) -{ - a = (((a >> 0) & 0xff) << 0) | (((a >> 16) & 0xff) << 8) | - (((a >> 32) & 0xff) << 16) | (((a >> 48) & 0xff) << 24) | - (((b >> 0) & 0xff) << 32) | (((b >> 16) & 0xff) << 40) | - (((b >> 32) & 0xff) << 48) | (((b >> 48) & 0xff) << 56); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT8(a >> 0, 0) | NZBIT8(a >> 8, 1) | - NZBIT8(a >> 16, 2) | NZBIT8(a >> 24, 3) | - NZBIT8(a >> 32, 4) | NZBIT8(a >> 40, 5) | - NZBIT8(a >> 48, 6) | NZBIT8(a >> 56, 7); - return a; -} - -uint64_t HELPER(iwmmxt_packul)(CPUARMState *env, uint64_t a, uint64_t b) -{ - a = (((a >> 0) & 0xffff) << 0) | (((a >> 32) & 0xffff) << 16) | - (((b >> 0) & 0xffff) << 32) | (((b >> 32) & 0xffff) << 48); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT16(a >> 0, 0) | NZBIT16(a >> 16, 1) | - NZBIT16(a >> 32, 2) | NZBIT16(a >> 48, 3); - return a; -} - -uint64_t HELPER(iwmmxt_packuq)(CPUARMState *env, uint64_t a, uint64_t b) -{ - a = (a & 0xffffffff) | ((b & 0xffffffff) << 32); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT32(a >> 0, 0) | NZBIT32(a >> 32, 1); - return a; -} - -/* TODO: Signed-Saturation */ -uint64_t HELPER(iwmmxt_packsw)(CPUARMState *env, uint64_t a, uint64_t b) -{ - a = (((a >> 0) & 0xff) << 0) | (((a >> 16) & 0xff) << 8) | - (((a >> 32) & 0xff) << 16) | (((a >> 48) & 0xff) << 24) | - (((b >> 0) & 0xff) << 32) | (((b >> 16) & 0xff) << 40) | - (((b >> 32) & 0xff) << 48) | (((b >> 48) & 0xff) << 56); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT8(a >> 0, 0) | NZBIT8(a >> 8, 1) | - NZBIT8(a >> 16, 2) | NZBIT8(a >> 24, 3) | - NZBIT8(a >> 32, 4) | NZBIT8(a >> 40, 5) | - NZBIT8(a >> 48, 6) | NZBIT8(a >> 56, 7); - return a; -} - -uint64_t HELPER(iwmmxt_packsl)(CPUARMState *env, uint64_t a, uint64_t b) -{ - a = (((a >> 0) & 0xffff) << 0) | (((a >> 32) & 0xffff) << 16) | - (((b >> 0) & 0xffff) << 32) | (((b >> 32) & 0xffff) << 48); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT16(a >> 0, 0) | NZBIT16(a >> 16, 1) | - NZBIT16(a >> 32, 2) | NZBIT16(a >> 48, 3); - return a; -} - -uint64_t HELPER(iwmmxt_packsq)(CPUARMState *env, uint64_t a, uint64_t b) -{ - a = (a & 0xffffffff) | ((b & 0xffffffff) << 32); - env->iwmmxt.cregs[ARM_IWMMXT_wCASF] = - NZBIT32(a >> 0, 0) | NZBIT32(a >> 32, 1); - return a; -} - -uint64_t HELPER(iwmmxt_muladdsl)(uint64_t c, uint32_t a, uint32_t b) -{ - return c + ((int32_t) EXTEND32(a) * (int32_t) EXTEND32(b)); -} - -uint64_t HELPER(iwmmxt_muladdsw)(uint64_t c, uint32_t a, uint32_t b) -{ - c += EXTEND32(EXTEND16S((a >> 0) & 0xffff) * - EXTEND16S((b >> 0) & 0xffff)); - c += EXTEND32(EXTEND16S((a >> 16) & 0xffff) * - EXTEND16S((b >> 16) & 0xffff)); - return c; -} - -uint64_t HELPER(iwmmxt_muladdswl)(uint64_t c, uint32_t a, uint32_t b) -{ - return c + (EXTEND32(EXTEND16S(a & 0xffff) * - EXTEND16S(b & 0xffff))); -} diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index 28307b5..d856e3b 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -2829,8 +2829,8 @@ uint32_t HELPER(v7m_tt)(CPUARMState *env, uint32_t addr, uint32_t op) ARMMMUFaultInfo fi = {}; /* We can ignore the return value as prot is always set */ - pmsav8_mpu_lookup(env, addr, MMU_DATA_LOAD, mmu_idx, targetsec, - &res, &fi, &mregion); + pmsav8_mpu_lookup(env, addr, MMU_DATA_LOAD, PAGE_READ, mmu_idx, + targetsec, &res, &fi, &mregion); if (mregion == -1) { mrvalid = false; mregion = 0; diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build index 895facd..1b11565 100644 --- a/target/arm/tcg/meson.build +++ b/target/arm/tcg/meson.build @@ -66,7 +66,6 @@ arm_common_ss.add(files( arm_common_system_ss.add(files( 'cpregs-at.c', 'hflags.c', - 'iwmmxt_helper.c', 'neon_helper.c', 'tlb_helper.c', 'tlb-insns.c', @@ -74,7 +73,6 @@ arm_common_system_ss.add(files( )) arm_user_ss.add(files( 'hflags.c', - 'iwmmxt_helper.c', 'neon_helper.c', 'tlb_helper.c', 'vfp_helper.c', diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c index 575e566..5373e0e 100644 --- a/target/arm/tcg/op_helper.c +++ b/target/arm/tcg/op_helper.c @@ -768,12 +768,6 @@ const void *HELPER(access_check_cp_reg)(CPUARMState *env, uint32_t key, assert(ri != NULL); - if (arm_feature(env, ARM_FEATURE_XSCALE) && ri->cp < 14 - && extract32(env->cp15.c15_cpar, ri->cp, 1) == 0) { - res = CP_ACCESS_UNDEFINED; - goto fail; - } - if (ri->accessfn) { res = ri->accessfn(env, ri, isread); } diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index f7d6d8c..e62dcc5 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -44,8 +44,6 @@ #define ENABLE_ARCH_7 arm_dc_feature(s, ARM_FEATURE_V7) #define ENABLE_ARCH_8 arm_dc_feature(s, ARM_FEATURE_V8) -/* These are TCG temporaries used only by the legacy iwMMXt decoder */ -static TCGv_i64 cpu_V0, cpu_V1, cpu_M0; /* These are TCG globals which alias CPUARMState fields */ static TCGv_i32 cpu_R[16]; TCGv_i32 cpu_CF, cpu_NF, cpu_VF, cpu_ZF; @@ -1252,1263 +1250,6 @@ void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) } } -#define ARM_CP_RW_BIT (1 << 20) - -static inline void iwmmxt_load_reg(TCGv_i64 var, int reg) -{ - tcg_gen_ld_i64(var, tcg_env, offsetof(CPUARMState, iwmmxt.regs[reg])); -} - -static inline void iwmmxt_store_reg(TCGv_i64 var, int reg) -{ - tcg_gen_st_i64(var, tcg_env, offsetof(CPUARMState, iwmmxt.regs[reg])); -} - -static inline TCGv_i32 iwmmxt_load_creg(int reg) -{ - TCGv_i32 var = tcg_temp_new_i32(); - tcg_gen_ld_i32(var, tcg_env, offsetof(CPUARMState, iwmmxt.cregs[reg])); - return var; -} - -static inline void iwmmxt_store_creg(int reg, TCGv_i32 var) -{ - tcg_gen_st_i32(var, tcg_env, offsetof(CPUARMState, iwmmxt.cregs[reg])); -} - -static inline void gen_op_iwmmxt_movq_wRn_M0(int rn) -{ - iwmmxt_store_reg(cpu_M0, rn); -} - -static inline void gen_op_iwmmxt_movq_M0_wRn(int rn) -{ - iwmmxt_load_reg(cpu_M0, rn); -} - -static inline void gen_op_iwmmxt_orq_M0_wRn(int rn) -{ - iwmmxt_load_reg(cpu_V1, rn); - tcg_gen_or_i64(cpu_M0, cpu_M0, cpu_V1); -} - -static inline void gen_op_iwmmxt_andq_M0_wRn(int rn) -{ - iwmmxt_load_reg(cpu_V1, rn); - tcg_gen_and_i64(cpu_M0, cpu_M0, cpu_V1); -} - -static inline void gen_op_iwmmxt_xorq_M0_wRn(int rn) -{ - iwmmxt_load_reg(cpu_V1, rn); - tcg_gen_xor_i64(cpu_M0, cpu_M0, cpu_V1); -} - -#define IWMMXT_OP(name) \ -static inline void gen_op_iwmmxt_##name##_M0_wRn(int rn) \ -{ \ - iwmmxt_load_reg(cpu_V1, rn); \ - gen_helper_iwmmxt_##name(cpu_M0, cpu_M0, cpu_V1); \ -} - -#define IWMMXT_OP_ENV(name) \ -static inline void gen_op_iwmmxt_##name##_M0_wRn(int rn) \ -{ \ - iwmmxt_load_reg(cpu_V1, rn); \ - gen_helper_iwmmxt_##name(cpu_M0, tcg_env, cpu_M0, cpu_V1); \ -} - -#define IWMMXT_OP_ENV_SIZE(name) \ -IWMMXT_OP_ENV(name##b) \ -IWMMXT_OP_ENV(name##w) \ -IWMMXT_OP_ENV(name##l) - -#define IWMMXT_OP_ENV1(name) \ -static inline void gen_op_iwmmxt_##name##_M0(void) \ -{ \ - gen_helper_iwmmxt_##name(cpu_M0, tcg_env, cpu_M0); \ -} - -IWMMXT_OP(maddsq) -IWMMXT_OP(madduq) -IWMMXT_OP(sadb) -IWMMXT_OP(sadw) -IWMMXT_OP(mulslw) -IWMMXT_OP(mulshw) -IWMMXT_OP(mululw) -IWMMXT_OP(muluhw) -IWMMXT_OP(macsw) -IWMMXT_OP(macuw) - -IWMMXT_OP_ENV_SIZE(unpackl) -IWMMXT_OP_ENV_SIZE(unpackh) - -IWMMXT_OP_ENV1(unpacklub) -IWMMXT_OP_ENV1(unpackluw) -IWMMXT_OP_ENV1(unpacklul) -IWMMXT_OP_ENV1(unpackhub) -IWMMXT_OP_ENV1(unpackhuw) -IWMMXT_OP_ENV1(unpackhul) -IWMMXT_OP_ENV1(unpacklsb) -IWMMXT_OP_ENV1(unpacklsw) -IWMMXT_OP_ENV1(unpacklsl) -IWMMXT_OP_ENV1(unpackhsb) -IWMMXT_OP_ENV1(unpackhsw) -IWMMXT_OP_ENV1(unpackhsl) - -IWMMXT_OP_ENV_SIZE(cmpeq) -IWMMXT_OP_ENV_SIZE(cmpgtu) -IWMMXT_OP_ENV_SIZE(cmpgts) - -IWMMXT_OP_ENV_SIZE(mins) -IWMMXT_OP_ENV_SIZE(minu) -IWMMXT_OP_ENV_SIZE(maxs) -IWMMXT_OP_ENV_SIZE(maxu) - -IWMMXT_OP_ENV_SIZE(subn) -IWMMXT_OP_ENV_SIZE(addn) -IWMMXT_OP_ENV_SIZE(subu) -IWMMXT_OP_ENV_SIZE(addu) -IWMMXT_OP_ENV_SIZE(subs) -IWMMXT_OP_ENV_SIZE(adds) - -IWMMXT_OP_ENV(avgb0) -IWMMXT_OP_ENV(avgb1) -IWMMXT_OP_ENV(avgw0) -IWMMXT_OP_ENV(avgw1) - -IWMMXT_OP_ENV(packuw) -IWMMXT_OP_ENV(packul) -IWMMXT_OP_ENV(packuq) -IWMMXT_OP_ENV(packsw) -IWMMXT_OP_ENV(packsl) -IWMMXT_OP_ENV(packsq) - -static void gen_op_iwmmxt_set_mup(void) -{ - TCGv_i32 tmp; - tmp = load_cpu_field(iwmmxt.cregs[ARM_IWMMXT_wCon]); - tcg_gen_ori_i32(tmp, tmp, 2); - store_cpu_field(tmp, iwmmxt.cregs[ARM_IWMMXT_wCon]); -} - -static void gen_op_iwmmxt_set_cup(void) -{ - TCGv_i32 tmp; - tmp = load_cpu_field(iwmmxt.cregs[ARM_IWMMXT_wCon]); - tcg_gen_ori_i32(tmp, tmp, 1); - store_cpu_field(tmp, iwmmxt.cregs[ARM_IWMMXT_wCon]); -} - -static void gen_op_iwmmxt_setpsr_nz(void) -{ - TCGv_i32 tmp = tcg_temp_new_i32(); - gen_helper_iwmmxt_setpsr_nz(tmp, cpu_M0); - store_cpu_field(tmp, iwmmxt.cregs[ARM_IWMMXT_wCASF]); -} - -static inline void gen_op_iwmmxt_addl_M0_wRn(int rn) -{ - iwmmxt_load_reg(cpu_V1, rn); - tcg_gen_ext32u_i64(cpu_V1, cpu_V1); - tcg_gen_add_i64(cpu_M0, cpu_M0, cpu_V1); -} - -static inline int gen_iwmmxt_address(DisasContext *s, uint32_t insn, - TCGv_i32 dest) -{ - int rd; - uint32_t offset; - TCGv_i32 tmp; - - rd = (insn >> 16) & 0xf; - tmp = load_reg(s, rd); - - offset = (insn & 0xff) << ((insn >> 7) & 2); - if (insn & (1 << 24)) { - /* Pre indexed */ - if (insn & (1 << 23)) - tcg_gen_addi_i32(tmp, tmp, offset); - else - tcg_gen_addi_i32(tmp, tmp, -offset); - tcg_gen_mov_i32(dest, tmp); - if (insn & (1 << 21)) { - store_reg(s, rd, tmp); - } - } else if (insn & (1 << 21)) { - /* Post indexed */ - tcg_gen_mov_i32(dest, tmp); - if (insn & (1 << 23)) - tcg_gen_addi_i32(tmp, tmp, offset); - else - tcg_gen_addi_i32(tmp, tmp, -offset); - store_reg(s, rd, tmp); - } else if (!(insn & (1 << 23))) - return 1; - return 0; -} - -static inline int gen_iwmmxt_shift(uint32_t insn, uint32_t mask, TCGv_i32 dest) -{ - int rd = (insn >> 0) & 0xf; - TCGv_i32 tmp; - - if (insn & (1 << 8)) { - if (rd < ARM_IWMMXT_wCGR0 || rd > ARM_IWMMXT_wCGR3) { - return 1; - } else { - tmp = iwmmxt_load_creg(rd); - } - } else { - tmp = tcg_temp_new_i32(); - iwmmxt_load_reg(cpu_V0, rd); - tcg_gen_extrl_i64_i32(tmp, cpu_V0); - } - tcg_gen_andi_i32(tmp, tmp, mask); - tcg_gen_mov_i32(dest, tmp); - return 0; -} - -/* Disassemble an iwMMXt instruction. Returns nonzero if an error occurred - (ie. an undefined instruction). */ -static int disas_iwmmxt_insn(DisasContext *s, uint32_t insn) -{ - int rd, wrd; - int rdhi, rdlo, rd0, rd1, i; - TCGv_i32 addr; - TCGv_i32 tmp, tmp2, tmp3; - - if ((insn & 0x0e000e00) == 0x0c000000) { - if ((insn & 0x0fe00ff0) == 0x0c400000) { - wrd = insn & 0xf; - rdlo = (insn >> 12) & 0xf; - rdhi = (insn >> 16) & 0xf; - if (insn & ARM_CP_RW_BIT) { /* TMRRC */ - iwmmxt_load_reg(cpu_V0, wrd); - tcg_gen_extrl_i64_i32(cpu_R[rdlo], cpu_V0); - tcg_gen_extrh_i64_i32(cpu_R[rdhi], cpu_V0); - } else { /* TMCRR */ - tcg_gen_concat_i32_i64(cpu_V0, cpu_R[rdlo], cpu_R[rdhi]); - iwmmxt_store_reg(cpu_V0, wrd); - gen_op_iwmmxt_set_mup(); - } - return 0; - } - - wrd = (insn >> 12) & 0xf; - addr = tcg_temp_new_i32(); - if (gen_iwmmxt_address(s, insn, addr)) { - return 1; - } - if (insn & ARM_CP_RW_BIT) { - if ((insn >> 28) == 0xf) { /* WLDRW wCx */ - tmp = tcg_temp_new_i32(); - gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); - iwmmxt_store_creg(wrd, tmp); - } else { - i = 1; - if (insn & (1 << 8)) { - if (insn & (1 << 22)) { /* WLDRD */ - gen_aa32_ld64(s, cpu_M0, addr, get_mem_index(s)); - i = 0; - } else { /* WLDRW wRd */ - tmp = tcg_temp_new_i32(); - gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); - } - } else { - tmp = tcg_temp_new_i32(); - if (insn & (1 << 22)) { /* WLDRH */ - gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); - } else { /* WLDRB */ - gen_aa32_ld8u(s, tmp, addr, get_mem_index(s)); - } - } - if (i) { - tcg_gen_extu_i32_i64(cpu_M0, tmp); - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - } - } else { - if ((insn >> 28) == 0xf) { /* WSTRW wCx */ - tmp = iwmmxt_load_creg(wrd); - gen_aa32_st32(s, tmp, addr, get_mem_index(s)); - } else { - gen_op_iwmmxt_movq_M0_wRn(wrd); - tmp = tcg_temp_new_i32(); - if (insn & (1 << 8)) { - if (insn & (1 << 22)) { /* WSTRD */ - gen_aa32_st64(s, cpu_M0, addr, get_mem_index(s)); - } else { /* WSTRW wRd */ - tcg_gen_extrl_i64_i32(tmp, cpu_M0); - gen_aa32_st32(s, tmp, addr, get_mem_index(s)); - } - } else { - if (insn & (1 << 22)) { /* WSTRH */ - tcg_gen_extrl_i64_i32(tmp, cpu_M0); - gen_aa32_st16(s, tmp, addr, get_mem_index(s)); - } else { /* WSTRB */ - tcg_gen_extrl_i64_i32(tmp, cpu_M0); - gen_aa32_st8(s, tmp, addr, get_mem_index(s)); - } - } - } - } - return 0; - } - - if ((insn & 0x0f000000) != 0x0e000000) - return 1; - - switch (((insn >> 12) & 0xf00) | ((insn >> 4) & 0xff)) { - case 0x000: /* WOR */ - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 0) & 0xf; - rd1 = (insn >> 16) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - gen_op_iwmmxt_orq_M0_wRn(rd1); - gen_op_iwmmxt_setpsr_nz(); - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x011: /* TMCR */ - if (insn & 0xf) - return 1; - rd = (insn >> 12) & 0xf; - wrd = (insn >> 16) & 0xf; - switch (wrd) { - case ARM_IWMMXT_wCID: - case ARM_IWMMXT_wCASF: - break; - case ARM_IWMMXT_wCon: - gen_op_iwmmxt_set_cup(); - /* Fall through. */ - case ARM_IWMMXT_wCSSF: - tmp = iwmmxt_load_creg(wrd); - tmp2 = load_reg(s, rd); - tcg_gen_andc_i32(tmp, tmp, tmp2); - iwmmxt_store_creg(wrd, tmp); - break; - case ARM_IWMMXT_wCGR0: - case ARM_IWMMXT_wCGR1: - case ARM_IWMMXT_wCGR2: - case ARM_IWMMXT_wCGR3: - gen_op_iwmmxt_set_cup(); - tmp = load_reg(s, rd); - iwmmxt_store_creg(wrd, tmp); - break; - default: - return 1; - } - break; - case 0x100: /* WXOR */ - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 0) & 0xf; - rd1 = (insn >> 16) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - gen_op_iwmmxt_xorq_M0_wRn(rd1); - gen_op_iwmmxt_setpsr_nz(); - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x111: /* TMRC */ - if (insn & 0xf) - return 1; - rd = (insn >> 12) & 0xf; - wrd = (insn >> 16) & 0xf; - tmp = iwmmxt_load_creg(wrd); - store_reg(s, rd, tmp); - break; - case 0x300: /* WANDN */ - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 0) & 0xf; - rd1 = (insn >> 16) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - tcg_gen_neg_i64(cpu_M0, cpu_M0); - gen_op_iwmmxt_andq_M0_wRn(rd1); - gen_op_iwmmxt_setpsr_nz(); - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x200: /* WAND */ - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 0) & 0xf; - rd1 = (insn >> 16) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - gen_op_iwmmxt_andq_M0_wRn(rd1); - gen_op_iwmmxt_setpsr_nz(); - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x810: case 0xa10: /* WMADD */ - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 0) & 0xf; - rd1 = (insn >> 16) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - if (insn & (1 << 21)) - gen_op_iwmmxt_maddsq_M0_wRn(rd1); - else - gen_op_iwmmxt_madduq_M0_wRn(rd1); - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - break; - case 0x10e: case 0x50e: case 0x90e: case 0xd0e: /* WUNPCKIL */ - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - switch ((insn >> 22) & 3) { - case 0: - gen_op_iwmmxt_unpacklb_M0_wRn(rd1); - break; - case 1: - gen_op_iwmmxt_unpacklw_M0_wRn(rd1); - break; - case 2: - gen_op_iwmmxt_unpackll_M0_wRn(rd1); - break; - case 3: - return 1; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x10c: case 0x50c: case 0x90c: case 0xd0c: /* WUNPCKIH */ - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - switch ((insn >> 22) & 3) { - case 0: - gen_op_iwmmxt_unpackhb_M0_wRn(rd1); - break; - case 1: - gen_op_iwmmxt_unpackhw_M0_wRn(rd1); - break; - case 2: - gen_op_iwmmxt_unpackhl_M0_wRn(rd1); - break; - case 3: - return 1; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x012: case 0x112: case 0x412: case 0x512: /* WSAD */ - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - if (insn & (1 << 22)) - gen_op_iwmmxt_sadw_M0_wRn(rd1); - else - gen_op_iwmmxt_sadb_M0_wRn(rd1); - if (!(insn & (1 << 20))) - gen_op_iwmmxt_addl_M0_wRn(wrd); - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - break; - case 0x010: case 0x110: case 0x210: case 0x310: /* WMUL */ - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - if (insn & (1 << 21)) { - if (insn & (1 << 20)) - gen_op_iwmmxt_mulshw_M0_wRn(rd1); - else - gen_op_iwmmxt_mulslw_M0_wRn(rd1); - } else { - if (insn & (1 << 20)) - gen_op_iwmmxt_muluhw_M0_wRn(rd1); - else - gen_op_iwmmxt_mululw_M0_wRn(rd1); - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - break; - case 0x410: case 0x510: case 0x610: case 0x710: /* WMAC */ - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - if (insn & (1 << 21)) - gen_op_iwmmxt_macsw_M0_wRn(rd1); - else - gen_op_iwmmxt_macuw_M0_wRn(rd1); - if (!(insn & (1 << 20))) { - iwmmxt_load_reg(cpu_V1, wrd); - tcg_gen_add_i64(cpu_M0, cpu_M0, cpu_V1); - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - break; - case 0x006: case 0x406: case 0x806: case 0xc06: /* WCMPEQ */ - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - switch ((insn >> 22) & 3) { - case 0: - gen_op_iwmmxt_cmpeqb_M0_wRn(rd1); - break; - case 1: - gen_op_iwmmxt_cmpeqw_M0_wRn(rd1); - break; - case 2: - gen_op_iwmmxt_cmpeql_M0_wRn(rd1); - break; - case 3: - return 1; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x800: case 0x900: case 0xc00: case 0xd00: /* WAVG2 */ - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - if (insn & (1 << 22)) { - if (insn & (1 << 20)) - gen_op_iwmmxt_avgw1_M0_wRn(rd1); - else - gen_op_iwmmxt_avgw0_M0_wRn(rd1); - } else { - if (insn & (1 << 20)) - gen_op_iwmmxt_avgb1_M0_wRn(rd1); - else - gen_op_iwmmxt_avgb0_M0_wRn(rd1); - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x802: case 0x902: case 0xa02: case 0xb02: /* WALIGNR */ - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - tmp = iwmmxt_load_creg(ARM_IWMMXT_wCGR0 + ((insn >> 20) & 3)); - tcg_gen_andi_i32(tmp, tmp, 7); - iwmmxt_load_reg(cpu_V1, rd1); - gen_helper_iwmmxt_align(cpu_M0, cpu_M0, cpu_V1, tmp); - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - break; - case 0x601: case 0x605: case 0x609: case 0x60d: /* TINSR */ - if (((insn >> 6) & 3) == 3) - return 1; - rd = (insn >> 12) & 0xf; - wrd = (insn >> 16) & 0xf; - tmp = load_reg(s, rd); - gen_op_iwmmxt_movq_M0_wRn(wrd); - switch ((insn >> 6) & 3) { - case 0: - tmp2 = tcg_constant_i32(0xff); - tmp3 = tcg_constant_i32((insn & 7) << 3); - break; - case 1: - tmp2 = tcg_constant_i32(0xffff); - tmp3 = tcg_constant_i32((insn & 3) << 4); - break; - case 2: - tmp2 = tcg_constant_i32(0xffffffff); - tmp3 = tcg_constant_i32((insn & 1) << 5); - break; - default: - g_assert_not_reached(); - } - gen_helper_iwmmxt_insr(cpu_M0, cpu_M0, tmp, tmp2, tmp3); - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - break; - case 0x107: case 0x507: case 0x907: case 0xd07: /* TEXTRM */ - rd = (insn >> 12) & 0xf; - wrd = (insn >> 16) & 0xf; - if (rd == 15 || ((insn >> 22) & 3) == 3) - return 1; - gen_op_iwmmxt_movq_M0_wRn(wrd); - tmp = tcg_temp_new_i32(); - switch ((insn >> 22) & 3) { - case 0: - tcg_gen_shri_i64(cpu_M0, cpu_M0, (insn & 7) << 3); - tcg_gen_extrl_i64_i32(tmp, cpu_M0); - if (insn & 8) { - tcg_gen_ext8s_i32(tmp, tmp); - } else { - tcg_gen_andi_i32(tmp, tmp, 0xff); - } - break; - case 1: - tcg_gen_shri_i64(cpu_M0, cpu_M0, (insn & 3) << 4); - tcg_gen_extrl_i64_i32(tmp, cpu_M0); - if (insn & 8) { - tcg_gen_ext16s_i32(tmp, tmp); - } else { - tcg_gen_andi_i32(tmp, tmp, 0xffff); - } - break; - case 2: - tcg_gen_shri_i64(cpu_M0, cpu_M0, (insn & 1) << 5); - tcg_gen_extrl_i64_i32(tmp, cpu_M0); - break; - } - store_reg(s, rd, tmp); - break; - case 0x117: case 0x517: case 0x917: case 0xd17: /* TEXTRC */ - if ((insn & 0x000ff008) != 0x0003f000 || ((insn >> 22) & 3) == 3) - return 1; - tmp = iwmmxt_load_creg(ARM_IWMMXT_wCASF); - switch ((insn >> 22) & 3) { - case 0: - tcg_gen_shri_i32(tmp, tmp, ((insn & 7) << 2) + 0); - break; - case 1: - tcg_gen_shri_i32(tmp, tmp, ((insn & 3) << 3) + 4); - break; - case 2: - tcg_gen_shri_i32(tmp, tmp, ((insn & 1) << 4) + 12); - break; - } - tcg_gen_shli_i32(tmp, tmp, 28); - gen_set_nzcv(tmp); - break; - case 0x401: case 0x405: case 0x409: case 0x40d: /* TBCST */ - if (((insn >> 6) & 3) == 3) - return 1; - rd = (insn >> 12) & 0xf; - wrd = (insn >> 16) & 0xf; - tmp = load_reg(s, rd); - switch ((insn >> 6) & 3) { - case 0: - gen_helper_iwmmxt_bcstb(cpu_M0, tmp); - break; - case 1: - gen_helper_iwmmxt_bcstw(cpu_M0, tmp); - break; - case 2: - gen_helper_iwmmxt_bcstl(cpu_M0, tmp); - break; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - break; - case 0x113: case 0x513: case 0x913: case 0xd13: /* TANDC */ - if ((insn & 0x000ff00f) != 0x0003f000 || ((insn >> 22) & 3) == 3) - return 1; - tmp = iwmmxt_load_creg(ARM_IWMMXT_wCASF); - tmp2 = tcg_temp_new_i32(); - tcg_gen_mov_i32(tmp2, tmp); - switch ((insn >> 22) & 3) { - case 0: - for (i = 0; i < 7; i ++) { - tcg_gen_shli_i32(tmp2, tmp2, 4); - tcg_gen_and_i32(tmp, tmp, tmp2); - } - break; - case 1: - for (i = 0; i < 3; i ++) { - tcg_gen_shli_i32(tmp2, tmp2, 8); - tcg_gen_and_i32(tmp, tmp, tmp2); - } - break; - case 2: - tcg_gen_shli_i32(tmp2, tmp2, 16); - tcg_gen_and_i32(tmp, tmp, tmp2); - break; - } - gen_set_nzcv(tmp); - break; - case 0x01c: case 0x41c: case 0x81c: case 0xc1c: /* WACC */ - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - switch ((insn >> 22) & 3) { - case 0: - gen_helper_iwmmxt_addcb(cpu_M0, cpu_M0); - break; - case 1: - gen_helper_iwmmxt_addcw(cpu_M0, cpu_M0); - break; - case 2: - gen_helper_iwmmxt_addcl(cpu_M0, cpu_M0); - break; - case 3: - return 1; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - break; - case 0x115: case 0x515: case 0x915: case 0xd15: /* TORC */ - if ((insn & 0x000ff00f) != 0x0003f000 || ((insn >> 22) & 3) == 3) - return 1; - tmp = iwmmxt_load_creg(ARM_IWMMXT_wCASF); - tmp2 = tcg_temp_new_i32(); - tcg_gen_mov_i32(tmp2, tmp); - switch ((insn >> 22) & 3) { - case 0: - for (i = 0; i < 7; i ++) { - tcg_gen_shli_i32(tmp2, tmp2, 4); - tcg_gen_or_i32(tmp, tmp, tmp2); - } - break; - case 1: - for (i = 0; i < 3; i ++) { - tcg_gen_shli_i32(tmp2, tmp2, 8); - tcg_gen_or_i32(tmp, tmp, tmp2); - } - break; - case 2: - tcg_gen_shli_i32(tmp2, tmp2, 16); - tcg_gen_or_i32(tmp, tmp, tmp2); - break; - } - gen_set_nzcv(tmp); - break; - case 0x103: case 0x503: case 0x903: case 0xd03: /* TMOVMSK */ - rd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - if ((insn & 0xf) != 0 || ((insn >> 22) & 3) == 3) - return 1; - gen_op_iwmmxt_movq_M0_wRn(rd0); - tmp = tcg_temp_new_i32(); - switch ((insn >> 22) & 3) { - case 0: - gen_helper_iwmmxt_msbb(tmp, cpu_M0); - break; - case 1: - gen_helper_iwmmxt_msbw(tmp, cpu_M0); - break; - case 2: - gen_helper_iwmmxt_msbl(tmp, cpu_M0); - break; - } - store_reg(s, rd, tmp); - break; - case 0x106: case 0x306: case 0x506: case 0x706: /* WCMPGT */ - case 0x906: case 0xb06: case 0xd06: case 0xf06: - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - switch ((insn >> 22) & 3) { - case 0: - if (insn & (1 << 21)) - gen_op_iwmmxt_cmpgtsb_M0_wRn(rd1); - else - gen_op_iwmmxt_cmpgtub_M0_wRn(rd1); - break; - case 1: - if (insn & (1 << 21)) - gen_op_iwmmxt_cmpgtsw_M0_wRn(rd1); - else - gen_op_iwmmxt_cmpgtuw_M0_wRn(rd1); - break; - case 2: - if (insn & (1 << 21)) - gen_op_iwmmxt_cmpgtsl_M0_wRn(rd1); - else - gen_op_iwmmxt_cmpgtul_M0_wRn(rd1); - break; - case 3: - return 1; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x00e: case 0x20e: case 0x40e: case 0x60e: /* WUNPCKEL */ - case 0x80e: case 0xa0e: case 0xc0e: case 0xe0e: - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - switch ((insn >> 22) & 3) { - case 0: - if (insn & (1 << 21)) - gen_op_iwmmxt_unpacklsb_M0(); - else - gen_op_iwmmxt_unpacklub_M0(); - break; - case 1: - if (insn & (1 << 21)) - gen_op_iwmmxt_unpacklsw_M0(); - else - gen_op_iwmmxt_unpackluw_M0(); - break; - case 2: - if (insn & (1 << 21)) - gen_op_iwmmxt_unpacklsl_M0(); - else - gen_op_iwmmxt_unpacklul_M0(); - break; - case 3: - return 1; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x00c: case 0x20c: case 0x40c: case 0x60c: /* WUNPCKEH */ - case 0x80c: case 0xa0c: case 0xc0c: case 0xe0c: - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - switch ((insn >> 22) & 3) { - case 0: - if (insn & (1 << 21)) - gen_op_iwmmxt_unpackhsb_M0(); - else - gen_op_iwmmxt_unpackhub_M0(); - break; - case 1: - if (insn & (1 << 21)) - gen_op_iwmmxt_unpackhsw_M0(); - else - gen_op_iwmmxt_unpackhuw_M0(); - break; - case 2: - if (insn & (1 << 21)) - gen_op_iwmmxt_unpackhsl_M0(); - else - gen_op_iwmmxt_unpackhul_M0(); - break; - case 3: - return 1; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x204: case 0x604: case 0xa04: case 0xe04: /* WSRL */ - case 0x214: case 0x614: case 0xa14: case 0xe14: - if (((insn >> 22) & 3) == 0) - return 1; - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - tmp = tcg_temp_new_i32(); - if (gen_iwmmxt_shift(insn, 0xff, tmp)) { - return 1; - } - switch ((insn >> 22) & 3) { - case 1: - gen_helper_iwmmxt_srlw(cpu_M0, tcg_env, cpu_M0, tmp); - break; - case 2: - gen_helper_iwmmxt_srll(cpu_M0, tcg_env, cpu_M0, tmp); - break; - case 3: - gen_helper_iwmmxt_srlq(cpu_M0, tcg_env, cpu_M0, tmp); - break; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x004: case 0x404: case 0x804: case 0xc04: /* WSRA */ - case 0x014: case 0x414: case 0x814: case 0xc14: - if (((insn >> 22) & 3) == 0) - return 1; - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - tmp = tcg_temp_new_i32(); - if (gen_iwmmxt_shift(insn, 0xff, tmp)) { - return 1; - } - switch ((insn >> 22) & 3) { - case 1: - gen_helper_iwmmxt_sraw(cpu_M0, tcg_env, cpu_M0, tmp); - break; - case 2: - gen_helper_iwmmxt_sral(cpu_M0, tcg_env, cpu_M0, tmp); - break; - case 3: - gen_helper_iwmmxt_sraq(cpu_M0, tcg_env, cpu_M0, tmp); - break; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x104: case 0x504: case 0x904: case 0xd04: /* WSLL */ - case 0x114: case 0x514: case 0x914: case 0xd14: - if (((insn >> 22) & 3) == 0) - return 1; - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - tmp = tcg_temp_new_i32(); - if (gen_iwmmxt_shift(insn, 0xff, tmp)) { - return 1; - } - switch ((insn >> 22) & 3) { - case 1: - gen_helper_iwmmxt_sllw(cpu_M0, tcg_env, cpu_M0, tmp); - break; - case 2: - gen_helper_iwmmxt_slll(cpu_M0, tcg_env, cpu_M0, tmp); - break; - case 3: - gen_helper_iwmmxt_sllq(cpu_M0, tcg_env, cpu_M0, tmp); - break; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x304: case 0x704: case 0xb04: case 0xf04: /* WROR */ - case 0x314: case 0x714: case 0xb14: case 0xf14: - if (((insn >> 22) & 3) == 0) - return 1; - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - tmp = tcg_temp_new_i32(); - switch ((insn >> 22) & 3) { - case 1: - if (gen_iwmmxt_shift(insn, 0xf, tmp)) { - return 1; - } - gen_helper_iwmmxt_rorw(cpu_M0, tcg_env, cpu_M0, tmp); - break; - case 2: - if (gen_iwmmxt_shift(insn, 0x1f, tmp)) { - return 1; - } - gen_helper_iwmmxt_rorl(cpu_M0, tcg_env, cpu_M0, tmp); - break; - case 3: - if (gen_iwmmxt_shift(insn, 0x3f, tmp)) { - return 1; - } - gen_helper_iwmmxt_rorq(cpu_M0, tcg_env, cpu_M0, tmp); - break; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x116: case 0x316: case 0x516: case 0x716: /* WMIN */ - case 0x916: case 0xb16: case 0xd16: case 0xf16: - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - switch ((insn >> 22) & 3) { - case 0: - if (insn & (1 << 21)) - gen_op_iwmmxt_minsb_M0_wRn(rd1); - else - gen_op_iwmmxt_minub_M0_wRn(rd1); - break; - case 1: - if (insn & (1 << 21)) - gen_op_iwmmxt_minsw_M0_wRn(rd1); - else - gen_op_iwmmxt_minuw_M0_wRn(rd1); - break; - case 2: - if (insn & (1 << 21)) - gen_op_iwmmxt_minsl_M0_wRn(rd1); - else - gen_op_iwmmxt_minul_M0_wRn(rd1); - break; - case 3: - return 1; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - break; - case 0x016: case 0x216: case 0x416: case 0x616: /* WMAX */ - case 0x816: case 0xa16: case 0xc16: case 0xe16: - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - switch ((insn >> 22) & 3) { - case 0: - if (insn & (1 << 21)) - gen_op_iwmmxt_maxsb_M0_wRn(rd1); - else - gen_op_iwmmxt_maxub_M0_wRn(rd1); - break; - case 1: - if (insn & (1 << 21)) - gen_op_iwmmxt_maxsw_M0_wRn(rd1); - else - gen_op_iwmmxt_maxuw_M0_wRn(rd1); - break; - case 2: - if (insn & (1 << 21)) - gen_op_iwmmxt_maxsl_M0_wRn(rd1); - else - gen_op_iwmmxt_maxul_M0_wRn(rd1); - break; - case 3: - return 1; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - break; - case 0x002: case 0x102: case 0x202: case 0x302: /* WALIGNI */ - case 0x402: case 0x502: case 0x602: case 0x702: - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - iwmmxt_load_reg(cpu_V1, rd1); - gen_helper_iwmmxt_align(cpu_M0, cpu_M0, cpu_V1, - tcg_constant_i32((insn >> 20) & 3)); - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - break; - case 0x01a: case 0x11a: case 0x21a: case 0x31a: /* WSUB */ - case 0x41a: case 0x51a: case 0x61a: case 0x71a: - case 0x81a: case 0x91a: case 0xa1a: case 0xb1a: - case 0xc1a: case 0xd1a: case 0xe1a: case 0xf1a: - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - switch ((insn >> 20) & 0xf) { - case 0x0: - gen_op_iwmmxt_subnb_M0_wRn(rd1); - break; - case 0x1: - gen_op_iwmmxt_subub_M0_wRn(rd1); - break; - case 0x3: - gen_op_iwmmxt_subsb_M0_wRn(rd1); - break; - case 0x4: - gen_op_iwmmxt_subnw_M0_wRn(rd1); - break; - case 0x5: - gen_op_iwmmxt_subuw_M0_wRn(rd1); - break; - case 0x7: - gen_op_iwmmxt_subsw_M0_wRn(rd1); - break; - case 0x8: - gen_op_iwmmxt_subnl_M0_wRn(rd1); - break; - case 0x9: - gen_op_iwmmxt_subul_M0_wRn(rd1); - break; - case 0xb: - gen_op_iwmmxt_subsl_M0_wRn(rd1); - break; - default: - return 1; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x01e: case 0x11e: case 0x21e: case 0x31e: /* WSHUFH */ - case 0x41e: case 0x51e: case 0x61e: case 0x71e: - case 0x81e: case 0x91e: case 0xa1e: case 0xb1e: - case 0xc1e: case 0xd1e: case 0xe1e: case 0xf1e: - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - tmp = tcg_constant_i32(((insn >> 16) & 0xf0) | (insn & 0x0f)); - gen_helper_iwmmxt_shufh(cpu_M0, tcg_env, cpu_M0, tmp); - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x018: case 0x118: case 0x218: case 0x318: /* WADD */ - case 0x418: case 0x518: case 0x618: case 0x718: - case 0x818: case 0x918: case 0xa18: case 0xb18: - case 0xc18: case 0xd18: case 0xe18: case 0xf18: - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - switch ((insn >> 20) & 0xf) { - case 0x0: - gen_op_iwmmxt_addnb_M0_wRn(rd1); - break; - case 0x1: - gen_op_iwmmxt_addub_M0_wRn(rd1); - break; - case 0x3: - gen_op_iwmmxt_addsb_M0_wRn(rd1); - break; - case 0x4: - gen_op_iwmmxt_addnw_M0_wRn(rd1); - break; - case 0x5: - gen_op_iwmmxt_adduw_M0_wRn(rd1); - break; - case 0x7: - gen_op_iwmmxt_addsw_M0_wRn(rd1); - break; - case 0x8: - gen_op_iwmmxt_addnl_M0_wRn(rd1); - break; - case 0x9: - gen_op_iwmmxt_addul_M0_wRn(rd1); - break; - case 0xb: - gen_op_iwmmxt_addsl_M0_wRn(rd1); - break; - default: - return 1; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x008: case 0x108: case 0x208: case 0x308: /* WPACK */ - case 0x408: case 0x508: case 0x608: case 0x708: - case 0x808: case 0x908: case 0xa08: case 0xb08: - case 0xc08: case 0xd08: case 0xe08: case 0xf08: - if (!(insn & (1 << 20)) || ((insn >> 22) & 3) == 0) - return 1; - wrd = (insn >> 12) & 0xf; - rd0 = (insn >> 16) & 0xf; - rd1 = (insn >> 0) & 0xf; - gen_op_iwmmxt_movq_M0_wRn(rd0); - switch ((insn >> 22) & 3) { - case 1: - if (insn & (1 << 21)) - gen_op_iwmmxt_packsw_M0_wRn(rd1); - else - gen_op_iwmmxt_packuw_M0_wRn(rd1); - break; - case 2: - if (insn & (1 << 21)) - gen_op_iwmmxt_packsl_M0_wRn(rd1); - else - gen_op_iwmmxt_packul_M0_wRn(rd1); - break; - case 3: - if (insn & (1 << 21)) - gen_op_iwmmxt_packsq_M0_wRn(rd1); - else - gen_op_iwmmxt_packuq_M0_wRn(rd1); - break; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - gen_op_iwmmxt_set_cup(); - break; - case 0x201: case 0x203: case 0x205: case 0x207: - case 0x209: case 0x20b: case 0x20d: case 0x20f: - case 0x211: case 0x213: case 0x215: case 0x217: - case 0x219: case 0x21b: case 0x21d: case 0x21f: - wrd = (insn >> 5) & 0xf; - rd0 = (insn >> 12) & 0xf; - rd1 = (insn >> 0) & 0xf; - if (rd0 == 0xf || rd1 == 0xf) - return 1; - gen_op_iwmmxt_movq_M0_wRn(wrd); - tmp = load_reg(s, rd0); - tmp2 = load_reg(s, rd1); - switch ((insn >> 16) & 0xf) { - case 0x0: /* TMIA */ - gen_helper_iwmmxt_muladdsl(cpu_M0, cpu_M0, tmp, tmp2); - break; - case 0x8: /* TMIAPH */ - gen_helper_iwmmxt_muladdsw(cpu_M0, cpu_M0, tmp, tmp2); - break; - case 0xc: case 0xd: case 0xe: case 0xf: /* TMIAxy */ - if (insn & (1 << 16)) - tcg_gen_shri_i32(tmp, tmp, 16); - if (insn & (1 << 17)) - tcg_gen_shri_i32(tmp2, tmp2, 16); - gen_helper_iwmmxt_muladdswl(cpu_M0, cpu_M0, tmp, tmp2); - break; - default: - return 1; - } - gen_op_iwmmxt_movq_wRn_M0(wrd); - gen_op_iwmmxt_set_mup(); - break; - default: - return 1; - } - - return 0; -} - -/* Disassemble an XScale DSP instruction. Returns nonzero if an error occurred - (ie. an undefined instruction). */ -static int disas_dsp_insn(DisasContext *s, uint32_t insn) -{ - int acc, rd0, rd1, rdhi, rdlo; - TCGv_i32 tmp, tmp2; - - if ((insn & 0x0ff00f10) == 0x0e200010) { - /* Multiply with Internal Accumulate Format */ - rd0 = (insn >> 12) & 0xf; - rd1 = insn & 0xf; - acc = (insn >> 5) & 7; - - if (acc != 0) - return 1; - - tmp = load_reg(s, rd0); - tmp2 = load_reg(s, rd1); - switch ((insn >> 16) & 0xf) { - case 0x0: /* MIA */ - gen_helper_iwmmxt_muladdsl(cpu_M0, cpu_M0, tmp, tmp2); - break; - case 0x8: /* MIAPH */ - gen_helper_iwmmxt_muladdsw(cpu_M0, cpu_M0, tmp, tmp2); - break; - case 0xc: /* MIABB */ - case 0xd: /* MIABT */ - case 0xe: /* MIATB */ - case 0xf: /* MIATT */ - if (insn & (1 << 16)) - tcg_gen_shri_i32(tmp, tmp, 16); - if (insn & (1 << 17)) - tcg_gen_shri_i32(tmp2, tmp2, 16); - gen_helper_iwmmxt_muladdswl(cpu_M0, cpu_M0, tmp, tmp2); - break; - default: - return 1; - } - - gen_op_iwmmxt_movq_wRn_M0(acc); - return 0; - } - - if ((insn & 0x0fe00ff8) == 0x0c400000) { - /* Internal Accumulator Access Format */ - rdhi = (insn >> 16) & 0xf; - rdlo = (insn >> 12) & 0xf; - acc = insn & 7; - - if (acc != 0) - return 1; - - if (insn & ARM_CP_RW_BIT) { /* MRA */ - iwmmxt_load_reg(cpu_V0, acc); - tcg_gen_extrl_i64_i32(cpu_R[rdlo], cpu_V0); - tcg_gen_extrh_i64_i32(cpu_R[rdhi], cpu_V0); - tcg_gen_andi_i32(cpu_R[rdhi], cpu_R[rdhi], (1 << (40 - 32)) - 1); - } else { /* MAR */ - tcg_gen_concat_i32_i64(cpu_V0, cpu_R[rdlo], cpu_R[rdhi]); - iwmmxt_store_reg(cpu_V0, acc); - } - return 0; - } - - return 1; -} - static void gen_goto_ptr(void) { tcg_gen_lookup_and_goto_ptr(); @@ -3048,13 +1789,10 @@ static void do_coproc_insn(DisasContext *s, int cpnum, int is64, } if ((s->hstr_active && s->current_el == 0) || ri->accessfn || - (ri->fgt && s->fgt_active) || - (arm_dc_feature(s, ARM_FEATURE_XSCALE) && cpnum < 14)) { + (ri->fgt && s->fgt_active)) { /* * Emit code to perform further access permissions checks at * runtime; this may result in an exception. - * Note that on XScale all cp0..c13 registers do an access check - * call in order to handle c15_cpar. */ gen_set_condexec(s); gen_update_pc(s, 0); @@ -3192,24 +1930,6 @@ static void do_coproc_insn(DisasContext *s, int cpnum, int is64, } } -/* Decode XScale DSP or iWMMXt insn (in the copro space, cp=0 or 1) */ -static void disas_xscale_insn(DisasContext *s, uint32_t insn) -{ - int cpnum = (insn >> 8) & 0xf; - - if (extract32(s->c15_cpar, cpnum, 1) == 0) { - unallocated_encoding(s); - } else if (arm_dc_feature(s, ARM_FEATURE_IWMMXT)) { - if (disas_iwmmxt_insn(s, insn)) { - unallocated_encoding(s); - } - } else if (arm_dc_feature(s, ARM_FEATURE_XSCALE)) { - if (disas_dsp_insn(s, insn)) { - unallocated_encoding(s); - } - } -} - /* Store a 64-bit value to a register pair. Clobbers val. */ static void gen_storeq_reg(DisasContext *s, int rlow, int rhigh, TCGv_i64 val) { @@ -3569,14 +2289,7 @@ static bool valid_cp(DisasContext *s, int cp) * only cp14 and cp15 are valid, and other values aren't considered * to be in the coprocessor-instruction space at all. v8M still * permits coprocessors 0..7. - * For XScale, we must not decode the XScale cp0, cp1 space as - * a standard coprocessor insn, because we want to fall through to - * the legacy disas_xscale_insn() decoder after decodetree is done. */ - if (arm_dc_feature(s, ARM_FEATURE_XSCALE) && (cp == 0 || cp == 1)) { - return false; - } - if (arm_dc_feature(s, ARM_FEATURE_V8) && !arm_dc_feature(s, ARM_FEATURE_M)) { return cp >= 14; @@ -7343,18 +6056,6 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) disas_neon_shared(s, insn)) { return; } - /* fall back to legacy decoder */ - - if ((insn & 0x0e000f00) == 0x0c000100) { - if (arm_dc_feature(s, ARM_FEATURE_IWMMXT)) { - /* iWMMXt register transfer. */ - if (extract32(s->c15_cpar, 1, 1)) { - if (!disas_iwmmxt_insn(s, insn)) { - return; - } - } - } - } goto illegal_op; } if (cond != 0xe) { @@ -7368,16 +6069,7 @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) disas_vfp(s, insn)) { return; } - /* fall back to legacy decoder */ - /* TODO: convert xscale/iwmmxt decoder to decodetree ?? */ - if (arm_dc_feature(s, ARM_FEATURE_XSCALE)) { - if (((insn & 0x0c000e00) == 0x0c000000) - && ((insn & 0x03000000) != 0x03000000)) { - /* Coprocessor insn, coprocessor 0 or 1 */ - disas_xscale_insn(s, insn); - return; - } - } + /* We didn't match anything in the decoder: UNDEF */ illegal_op: unallocated_encoding(s); @@ -7606,12 +6298,8 @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) dc->hstr_active = EX_TBFLAG_A32(tb_flags, HSTR_ACTIVE); dc->ns = EX_TBFLAG_A32(tb_flags, NS); dc->vfp_enabled = EX_TBFLAG_A32(tb_flags, VFPEN); - if (arm_feature(env, ARM_FEATURE_XSCALE)) { - dc->c15_cpar = EX_TBFLAG_A32(tb_flags, XSCALE_CPAR); - } else { - dc->vec_len = EX_TBFLAG_A32(tb_flags, VECLEN); - dc->vec_stride = EX_TBFLAG_A32(tb_flags, VECSTRIDE); - } + dc->vec_len = EX_TBFLAG_A32(tb_flags, VECLEN); + dc->vec_stride = EX_TBFLAG_A32(tb_flags, VECSTRIDE); dc->sme_trap_nonstreaming = EX_TBFLAG_A32(tb_flags, SME_TRAP_NONSTREAMING); } @@ -7651,10 +6339,6 @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) int bound = -(dc->base.pc_first | TARGET_PAGE_MASK) / 4; dc->base.max_insns = MIN(dc->base.max_insns, bound); } - - cpu_V0 = tcg_temp_new_i64(); - cpu_V1 = tcg_temp_new_i64(); - cpu_M0 = tcg_temp_new_i64(); } static void arm_tr_tb_start(DisasContextBase *dcbase, CPUState *cpu) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index f974996..ec4755a 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -175,8 +175,6 @@ typedef struct DisasContext { uint8_t gm_blocksize; /* True if the current insn_start has been updated. */ bool insn_start_updated; - /* Bottom two bits of XScale c15_cpar coprocessor access control reg */ - int c15_cpar; /* Offset from VNCR_EL2 when FEAT_NV2 redirects this reg to memory */ uint32_t nv2_redirect_offset; } DisasContext; diff --git a/tests/data/acpi/aarch64/virt/DSDT.smmuv3-dev b/tests/data/acpi/aarch64/virt/DSDT.smmuv3-dev Binary files differnew file mode 100644 index 0000000..53d4c07 --- /dev/null +++ b/tests/data/acpi/aarch64/virt/DSDT.smmuv3-dev diff --git a/tests/data/acpi/aarch64/virt/DSDT.smmuv3-legacy b/tests/data/acpi/aarch64/virt/DSDT.smmuv3-legacy Binary files differnew file mode 100644 index 0000000..53d4c07 --- /dev/null +++ b/tests/data/acpi/aarch64/virt/DSDT.smmuv3-legacy diff --git a/tests/data/acpi/aarch64/virt/IORT.smmuv3-dev b/tests/data/acpi/aarch64/virt/IORT.smmuv3-dev Binary files differnew file mode 100644 index 0000000..67be268 --- /dev/null +++ b/tests/data/acpi/aarch64/virt/IORT.smmuv3-dev diff --git a/tests/data/acpi/aarch64/virt/IORT.smmuv3-legacy b/tests/data/acpi/aarch64/virt/IORT.smmuv3-legacy Binary files differnew file mode 100644 index 0000000..41981a4 --- /dev/null +++ b/tests/data/acpi/aarch64/virt/IORT.smmuv3-legacy diff --git a/tests/guest-debug/test_gdbstub.py b/tests/guest-debug/test_gdbstub.py index 4f08089..e017ccb 100644 --- a/tests/guest-debug/test_gdbstub.py +++ b/tests/guest-debug/test_gdbstub.py @@ -1,7 +1,6 @@ """Helper functions for gdbstub testing """ -from __future__ import print_function import argparse import gdb import os diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c index e7e6926..4fa8ac5 100644 --- a/tests/qtest/bios-tables-test.c +++ b/tests/qtest/bios-tables-test.c @@ -2337,6 +2337,86 @@ static void test_acpi_aarch64_virt_viot(void) free_test_data(&data); } +static void test_acpi_aarch64_virt_smmuv3_legacy(void) +{ + test_data data = { + .machine = "virt", + .arch = "aarch64", + .tcg_only = true, + .uefi_fl1 = "pc-bios/edk2-aarch64-code.fd", + .uefi_fl2 = "pc-bios/edk2-arm-vars.fd", + .ram_start = 0x40000000ULL, + .scan_len = 128ULL * MiB, + }; + + /* + * cdrom is plugged into scsi controller to avoid conflict + * with pxb-pcie. See comments in test_acpi_aarch64_virt_tcg_pxb() for + * details. + * + * The setup includes three PCIe root complexes, one of which has + * bypass_iommu enabled. The generated IORT table contains a single + * SMMUv3 node and a Root Complex node with three ID mappings. Two + * of the ID mappings have output references pointing to the SMMUv3 + * node and the remaining one points to ITS. + */ + data.variant = ".smmuv3-legacy"; + test_acpi_one(" -device pcie-root-port,chassis=1,id=pci.1" + " -device virtio-scsi-pci,id=scsi0,bus=pci.1" + " -drive file=" + "tests/data/uefi-boot-images/bios-tables-test.aarch64.iso.qcow2," + "if=none,media=cdrom,id=drive-scsi0-0-0-1,readonly=on" + " -device scsi-cd,bus=scsi0.0,scsi-id=0," + "drive=drive-scsi0-0-0-1,id=scsi0-0-0-1,bootindex=1" + " -cpu cortex-a57" + " -M iommu=smmuv3" + " -device pxb-pcie,id=pcie.1,bus=pcie.0,bus_nr=0x10" + " -device pxb-pcie,id=pcie.2,bus=pcie.0,bus_nr=0x20,bypass_iommu=on", + &data); + free_test_data(&data); +} + +static void test_acpi_aarch64_virt_smmuv3_dev(void) +{ + test_data data = { + .machine = "virt", + .arch = "aarch64", + .tcg_only = true, + .uefi_fl1 = "pc-bios/edk2-aarch64-code.fd", + .uefi_fl2 = "pc-bios/edk2-arm-vars.fd", + .ram_start = 0x40000000ULL, + .scan_len = 128ULL * MiB, + }; + + /* + * cdrom is plugged into scsi controller to avoid conflict + * with pxb-pcie. See comments in test_acpi_aarch64_virt_tcg_pxb() + * for details. + * + * The setup includes three PCie root complexes, two of which are + * connected to separate SMMUv3 devices. The resulting IORT table + * contains two SMMUv3 nodes and a Root Complex node with ID mappings + * of which two of the ID mappings have output references pointing + * to two different SMMUv3 nodes and the remaining ones pointing to + * ITS. + */ + data.variant = ".smmuv3-dev"; + test_acpi_one(" -device pcie-root-port,chassis=1,id=pci.1" + " -device virtio-scsi-pci,id=scsi0,bus=pci.1" + " -drive file=" + "tests/data/uefi-boot-images/bios-tables-test.aarch64.iso.qcow2," + "if=none,media=cdrom,id=drive-scsi0-0-0-1,readonly=on" + " -device scsi-cd,bus=scsi0.0,scsi-id=0," + "drive=drive-scsi0-0-0-1,id=scsi0-0-0-1,bootindex=1" + " -cpu cortex-a57" + " -device arm-smmuv3,primary-bus=pcie.0,id=smmuv3.0" + " -device pxb-pcie,id=pcie.1,bus=pcie.0,bus_nr=0x10" + " -device arm-smmuv3,primary-bus=pcie.1,id=smmuv3.1" + " -device pxb-pcie,id=pcie.2,bus=pcie.0,bus_nr=0x20", + &data); + free_test_data(&data); +} + #ifndef _WIN32 # define DEV_NULL "/dev/null" #else @@ -2768,6 +2848,12 @@ int main(int argc, char *argv[]) if (qtest_has_device("virtio-iommu-pci")) { qtest_add_func("acpi/virt/viot", test_acpi_aarch64_virt_viot); } + qtest_add_func("acpi/virt/smmuv3-legacy", + test_acpi_aarch64_virt_smmuv3_legacy); + if (qtest_has_device("arm-smmuv3")) { + qtest_add_func("acpi/virt/smmuv3-dev", + test_acpi_aarch64_virt_smmuv3_dev); + } } } else if (strcmp(arch, "riscv64") == 0) { if (has_tcg && qtest_has_device("virtio-blk-pci")) { diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target index 16ddcf4..1755874 100644 --- a/tests/tcg/aarch64/Makefile.target +++ b/tests/tcg/aarch64/Makefile.target @@ -134,6 +134,35 @@ run-gdbstub-sve-ioctls: sve-ioctls EXTRA_RUNS += run-gdbstub-sysregs run-gdbstub-sve-ioctls +ifneq ($(CROSS_AS_HAS_ARMV9_SME),) +# SME gdbstub tests + +run-gdbstub-sysregs-sme: sysregs + $(call run-test, $@, $(GDB_SCRIPT) \ + --gdb $(GDB) \ + --qemu $(QEMU) --qargs "$(QEMU_OPTS)" \ + --bin $< --test $(AARCH64_SRC)/gdbstub/test-sme.py \ + -- test_sme --gdb_basic_za_test, \ + basic gdbstub SME support) + +ifeq ($(GDB_HAS_SME_TILES),y) +run-gdbstub-sysregs-sme-tile-slice: sysregs + $(call run-test, $@, $(GDB_SCRIPT) \ + --gdb $(GDB) \ + --qemu $(QEMU) --qargs "$(QEMU_OPTS)" \ + --bin $< --test $(AARCH64_SRC)/gdbstub/test-sme.py \ + -- test_sme --gdb_tile_slice_test, \ + gdbstub SME ZA tile slice support) +else +run-gdbstub-sysregs-sme-tile-slice: sysregs + $(call skip-test,"gdbstub SME ZA tile slice support", \ + "selected gdb ($(GDB)) does not support SME ZA tile slices") +endif + +EXTRA_RUNS += run-gdbstub-sysregs-sme run-gdbstub-sysregs-sme-tile-slice + +endif + ifeq ($(GDB_HAS_MTE),y) run-gdbstub-mte: mte-8 $(call run-test, $@, $(GDB_SCRIPT) \ diff --git a/tests/tcg/aarch64/gdbstub/test-mte.py b/tests/tcg/aarch64/gdbstub/test-mte.py index 9ad98e7..f4a7d7b 100644 --- a/tests/tcg/aarch64/gdbstub/test-mte.py +++ b/tests/tcg/aarch64/gdbstub/test-mte.py @@ -1,4 +1,3 @@ -from __future__ import print_function # # Test GDB memory-tag commands that exercise the stubs for the qIsAddressTagged, # qMemTag, and QMemTag packets, which are used for manipulating allocation tags. diff --git a/tests/tcg/aarch64/gdbstub/test-sme.py b/tests/tcg/aarch64/gdbstub/test-sme.py new file mode 100644 index 0000000..ec03189 --- /dev/null +++ b/tests/tcg/aarch64/gdbstub/test-sme.py @@ -0,0 +1,117 @@ +# +# Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries. +# +# SPDX-License-Identifier: GPL-2.0-or-later + +# +# Test the SME registers are visible and changeable via gdbstub +# +# This is launched via tests/guest-debug/run-test.py +# + +import argparse +import gdb +from test_gdbstub import main, report + +MAGIC = 0x01020304 +BASIC_ZA_TEST = 0 +TILE_SLICE_TEST = 0 + + +def run_test(): + """Run the requested test(s) for SME ZA gdbstub support""" + + if BASIC_ZA_TEST: + run_basic_sme_za_gdbstub_support_test() + if TILE_SLICE_TEST: + run_basic_sme_za_tile_slice_gdbstub_support_test() + + +def run_basic_sme_za_gdbstub_support_test(): + """Test reads and writes to the SME ZA register at the byte level""" + + frame = gdb.selected_frame() + rname = "za" + za = frame.read_register(rname) + report(True, "Reading %s" % rname) + + # Writing to the ZA register, byte by byte. + for i in range(0, 16): + for j in range(0, 16): + cmd = "set $za[%d][%d] = 0x01" % (i, j) + gdb.execute(cmd) + report(True, "%s" % cmd) + + # Reading from the ZA register, byte by byte. + for i in range(0, 16): + for j in range(0, 16): + reg = "$za[%d][%d]" % (i, j) + v = gdb.parse_and_eval(reg) + report(str(v.type) == "uint8_t", "size of %s" % (reg)) + report(v == 0x1, "%s is 0x%x" % (reg, 0x1)) + + +def run_basic_sme_za_tile_slice_gdbstub_support_test(): + """Test reads and writes of SME ZA horizontal and vertical tile slices + + Test if SME ZA tile slices, both horizontal and vertical, + can be correctly read and written to. The sizes to test + are quadwords and doublewords. + """ + + sizes = {} + sizes["q"] = "uint128_t" + sizes["d"] = "uint64_t" + + # Accessing requested sizes of elements of ZA + for size in sizes: + + # Accessing various ZA tiles + for i in range(0, 4): + + # Accessing various horizontal slices for each ZA tile + for j in range(0, 4): + # Writing to various elements in each tile slice + for k in range(0, 4): + cmd = "set $za%dh%c%d[%d] = 0x%x" % (i, size, j, k, MAGIC) + gdb.execute(cmd) + report(True, "%s" % cmd) + + # Reading from the written elements in each tile slice + for k in range(0, 4): + reg = "$za%dh%c%d[%d]" % (i, size, j, k) + v = gdb.parse_and_eval(reg) + report(str(v.type) == sizes[size], "size of %s" % (reg)) + report(v == MAGIC, "%s is 0x%x" % (reg, MAGIC)) + + # Accessing various vertical slices for each ZA tile + for j in range(0, 4): + # Writing to various elements in each tile slice + for k in range(0, 4): + cmd = "set $za%dv%c%d[%d] = 0x%x" % (i, size, j, k, MAGIC) + gdb.execute(cmd) + report(True, "%s" % cmd) + + # Reading from the written elements in each tile slice + for k in range(0, 4): + reg = "$za%dv%c%d[%d]" % (i, size, j, k) + v = gdb.parse_and_eval(reg) + report(str(v.type) == sizes[size], "size of %s" % (reg)) + report(v == MAGIC, "%s is 0x%x" % (reg, MAGIC)) + + +parser = argparse.ArgumentParser(description="A gdbstub test for SME support") +parser.add_argument("--gdb_basic_za_test", + help="Enable test for basic SME ZA support", + action="store_true") +parser.add_argument("--gdb_tile_slice_test", + help="Enable test for ZA tile slice support", + action="store_true") +args = parser.parse_args() + +if args.gdb_basic_za_test: + BASIC_ZA_TEST = 1 +if args.gdb_tile_slice_test: + TILE_SLICE_TEST = 1 + +main(run_test, expected_arch="aarch64") diff --git a/tests/tcg/aarch64/gdbstub/test-sve-ioctl.py b/tests/tcg/aarch64/gdbstub/test-sve-ioctl.py index a78a3a2..2c5c218 100644 --- a/tests/tcg/aarch64/gdbstub/test-sve-ioctl.py +++ b/tests/tcg/aarch64/gdbstub/test-sve-ioctl.py @@ -1,4 +1,3 @@ -from __future__ import print_function # # Test the SVE ZReg reports the right amount of data. It uses the # sve-ioctl test and examines the register data each time the diff --git a/tests/tcg/aarch64/gdbstub/test-sve.py b/tests/tcg/aarch64/gdbstub/test-sve.py index 84cdcd4..7b0489a 100644 --- a/tests/tcg/aarch64/gdbstub/test-sve.py +++ b/tests/tcg/aarch64/gdbstub/test-sve.py @@ -1,4 +1,3 @@ -from __future__ import print_function # # Test the SVE registers are visible and changeable via gdbstub # diff --git a/tests/tcg/multiarch/gdbstub/interrupt.py b/tests/tcg/multiarch/gdbstub/interrupt.py index 2d5654d..4eccdb4 100644 --- a/tests/tcg/multiarch/gdbstub/interrupt.py +++ b/tests/tcg/multiarch/gdbstub/interrupt.py @@ -1,4 +1,3 @@ -from __future__ import print_function # # Test some of the system debug features with the multiarch memory # test. It is a port of the original vmlinux focused test case but diff --git a/tests/tcg/multiarch/gdbstub/memory.py b/tests/tcg/multiarch/gdbstub/memory.py index 532b92e..76d75e5 100644 --- a/tests/tcg/multiarch/gdbstub/memory.py +++ b/tests/tcg/multiarch/gdbstub/memory.py @@ -1,4 +1,3 @@ -from __future__ import print_function # # Test some of the system debug features with the multiarch memory # test. It is a port of the original vmlinux focused test case but diff --git a/tests/tcg/multiarch/gdbstub/sha1.py b/tests/tcg/multiarch/gdbstub/sha1.py index 1ce711a..3403b82 100644 --- a/tests/tcg/multiarch/gdbstub/sha1.py +++ b/tests/tcg/multiarch/gdbstub/sha1.py @@ -1,4 +1,3 @@ -from __future__ import print_function # # A very simple smoke test for debugging the SHA1 userspace test on # each target. diff --git a/tests/tcg/multiarch/gdbstub/test-proc-mappings.py b/tests/tcg/multiarch/gdbstub/test-proc-mappings.py index 6eb6ebf..796dca7 100644 --- a/tests/tcg/multiarch/gdbstub/test-proc-mappings.py +++ b/tests/tcg/multiarch/gdbstub/test-proc-mappings.py @@ -1,7 +1,6 @@ """Test that gdbstub has access to proc mappings. This runs as a sourced script (via -x, via run-test.py).""" -from __future__ import print_function import gdb from test_gdbstub import gdb_exit, main, report diff --git a/tests/tcg/multiarch/gdbstub/test-qxfer-auxv-read.py b/tests/tcg/multiarch/gdbstub/test-qxfer-auxv-read.py index 00c26ab..fa36c94 100644 --- a/tests/tcg/multiarch/gdbstub/test-qxfer-auxv-read.py +++ b/tests/tcg/multiarch/gdbstub/test-qxfer-auxv-read.py @@ -1,4 +1,3 @@ -from __future__ import print_function # # Test auxiliary vector is loaded via gdbstub # diff --git a/tests/tcg/multiarch/gdbstub/test-qxfer-siginfo-read.py b/tests/tcg/multiarch/gdbstub/test-qxfer-siginfo-read.py index 862596b..b18fa12 100644 --- a/tests/tcg/multiarch/gdbstub/test-qxfer-siginfo-read.py +++ b/tests/tcg/multiarch/gdbstub/test-qxfer-siginfo-read.py @@ -1,4 +1,3 @@ -from __future__ import print_function # # Test gdbstub Xfer:siginfo:read stub. # diff --git a/tests/tcg/multiarch/gdbstub/test-thread-breakpoint.py b/tests/tcg/multiarch/gdbstub/test-thread-breakpoint.py index 4d6b6b9..49cbc35 100644 --- a/tests/tcg/multiarch/gdbstub/test-thread-breakpoint.py +++ b/tests/tcg/multiarch/gdbstub/test-thread-breakpoint.py @@ -1,4 +1,3 @@ -from __future__ import print_function # # Test auxiliary vector is loaded via gdbstub # diff --git a/tests/tcg/s390x/gdbstub/test-signals-s390x.py b/tests/tcg/s390x/gdbstub/test-signals-s390x.py index b6b7b39..398ad53 100644 --- a/tests/tcg/s390x/gdbstub/test-signals-s390x.py +++ b/tests/tcg/s390x/gdbstub/test-signals-s390x.py @@ -1,4 +1,3 @@ -from __future__ import print_function # # Test that signals and debugging mix well together on s390x. diff --git a/tests/tcg/s390x/gdbstub/test-svc.py b/tests/tcg/s390x/gdbstub/test-svc.py index 17210b4..29a0aa0 100644 --- a/tests/tcg/s390x/gdbstub/test-svc.py +++ b/tests/tcg/s390x/gdbstub/test-svc.py @@ -1,7 +1,6 @@ """Test single-stepping SVC. This runs as a sourced script (via -x, via run-test.py).""" -from __future__ import print_function import gdb from test_gdbstub import main, report |