diff options
| -rw-r--r-- | docs/devel/migration.rst | 15 | ||||
| -rw-r--r-- | fsdev/Makefile.objs | 7 | ||||
| -rw-r--r-- | hmp.c | 16 | ||||
| -rw-r--r-- | hw/mips/mips_malta.c | 212 | ||||
| -rw-r--r-- | include/elf.h | 2 | ||||
| -rw-r--r-- | include/hw/elf_ops.h | 8 | ||||
| -rw-r--r-- | include/qemu/queue.h | 1 | ||||
| -rw-r--r-- | linux-user/elfload.c | 2 | ||||
| -rw-r--r-- | linux-user/mips/cpu_loop.c | 28 | ||||
| -rw-r--r-- | migration/colo.c | 2 | ||||
| -rw-r--r-- | migration/migration.c | 49 | ||||
| -rw-r--r-- | migration/migration.h | 2 | ||||
| -rw-r--r-- | migration/postcopy-ram.c | 2 | ||||
| -rw-r--r-- | migration/qemu-file-channel.c | 12 | ||||
| -rw-r--r-- | migration/qemu-file.c | 8 | ||||
| -rw-r--r-- | migration/ram.c | 202 | ||||
| -rw-r--r-- | migration/rdma.c | 423 | ||||
| -rw-r--r-- | migration/savevm.c | 3 | ||||
| -rw-r--r-- | migration/vmstate.c | 6 | ||||
| -rw-r--r-- | qapi/migration.json | 64 | ||||
| -rw-r--r-- | target/mips/cpu.h | 2 | ||||
| -rw-r--r-- | target/mips/helper.c | 16 | ||||
| -rw-r--r-- | target/mips/helper.h | 2 | ||||
| -rw-r--r-- | target/mips/mips-defs.h | 4 | ||||
| -rw-r--r-- | target/mips/op_helper.c | 98 | ||||
| -rw-r--r-- | target/mips/translate.c | 4899 | ||||
| -rw-r--r-- | target/mips/translate_init.inc.c | 39 |
27 files changed, 5959 insertions, 165 deletions
diff --git a/docs/devel/migration.rst b/docs/devel/migration.rst index 6ed3fce061..687570754d 100644 --- a/docs/devel/migration.rst +++ b/docs/devel/migration.rst @@ -240,10 +240,13 @@ should succeed even with the data missing. To support this the subsection can be connected to a device property and from there to a versioned machine type. -One important note is that the post_load() function is called "after" -loading all subsections, because a newer subsection could change same -value that it uses. A flag, and the combination of pre_load and post_load -can be used to detect whether a subsection was loaded, and to +The 'pre_load' and 'post_load' functions on subsections are only +called if the subsection is loaded. + +One important note is that the outer post_load() function is called "after" +loading all subsections, because a newer subsection could change the same +value that it uses. A flag, and the combination of outer pre_load and +post_load can be used to detect whether a subsection was loaded, and to fall back on default behaviour when the subsection isn't present. Example: @@ -315,8 +318,8 @@ For example: the property to false. c) Add a static bool support_foo function that tests the property. d) Add a subsection with a .needed set to the support_foo function - e) (potentially) Add a pre_load that sets up a default value for 'foo' - to be used if the subsection isn't loaded. + e) (potentially) Add an outer pre_load that sets up a default value + for 'foo' to be used if the subsection isn't loaded. Now that subsection will not be generated when using an older machine type and the migration stream will be accepted by older diff --git a/fsdev/Makefile.objs b/fsdev/Makefile.objs index fb38017c0b..24bbb3e75c 100644 --- a/fsdev/Makefile.objs +++ b/fsdev/Makefile.objs @@ -1,7 +1,10 @@ # Lots of the fsdev/9pcode is pulled in by vl.c via qemu_fsdev_add. # only pull in the actual 9p backend if we also enabled virtio or xen. -common-obj-$(call land,$(CONFIG_VIRTFS),$(call lor,$(CONFIG_VIRTIO),$(CONFIG_XEN))) = qemu-fsdev.o 9p-marshal.o 9p-iov-marshal.o -common-obj-$(call lnot,$(call land,$(CONFIG_VIRTFS),$(call lor,$(CONFIG_VIRTIO),$(CONFIG_XEN)))) = qemu-fsdev-dummy.o +ifeq ($(call land,$(CONFIG_VIRTFS),$(call lor,$(CONFIG_VIRTIO_9P),$(CONFIG_XEN))),y) +common-obj-y = qemu-fsdev.o 9p-marshal.o 9p-iov-marshal.o +else +common-obj-y = qemu-fsdev-dummy.o +endif common-obj-y += qemu-fsdev-opts.o qemu-fsdev-throttle.o # Toplevel always builds this; targets without virtio will put it in diff --git a/hmp.c b/hmp.c index d94a47f7c7..4975fa56b0 100644 --- a/hmp.c +++ b/hmp.c @@ -327,6 +327,10 @@ void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict) monitor_printf(mon, "%s: %u\n", MigrationParameter_str(MIGRATION_PARAMETER_COMPRESS_THREADS), params->compress_threads); + assert(params->has_compress_wait_thread); + monitor_printf(mon, "%s: %s\n", + MigrationParameter_str(MIGRATION_PARAMETER_COMPRESS_WAIT_THREAD), + params->compress_wait_thread ? "on" : "off"); assert(params->has_decompress_threads); monitor_printf(mon, "%s: %u\n", MigrationParameter_str(MIGRATION_PARAMETER_DECOMPRESS_THREADS), @@ -339,6 +343,10 @@ void hmp_info_migrate_parameters(Monitor *mon, const QDict *qdict) monitor_printf(mon, "%s: %u\n", MigrationParameter_str(MIGRATION_PARAMETER_CPU_THROTTLE_INCREMENT), params->cpu_throttle_increment); + assert(params->has_max_cpu_throttle); + monitor_printf(mon, "%s: %u\n", + MigrationParameter_str(MIGRATION_PARAMETER_MAX_CPU_THROTTLE), + params->max_cpu_throttle); assert(params->has_tls_creds); monitor_printf(mon, "%s: '%s'\n", MigrationParameter_str(MIGRATION_PARAMETER_TLS_CREDS), @@ -1647,6 +1655,10 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict) p->has_compress_threads = true; visit_type_int(v, param, &p->compress_threads, &err); break; + case MIGRATION_PARAMETER_COMPRESS_WAIT_THREAD: + p->has_compress_wait_thread = true; + visit_type_bool(v, param, &p->compress_wait_thread, &err); + break; case MIGRATION_PARAMETER_DECOMPRESS_THREADS: p->has_decompress_threads = true; visit_type_int(v, param, &p->decompress_threads, &err); @@ -1659,6 +1671,10 @@ void hmp_migrate_set_parameter(Monitor *mon, const QDict *qdict) p->has_cpu_throttle_increment = true; visit_type_int(v, param, &p->cpu_throttle_increment, &err); break; + case MIGRATION_PARAMETER_MAX_CPU_THROTTLE: + p->has_max_cpu_throttle = true; + visit_type_int(v, param, &p->max_cpu_throttle, &err); + break; case MIGRATION_PARAMETER_TLS_CREDS: p->has_tls_creds = true; p->tls_creds = g_new0(StrOrNull, 1); diff --git a/hw/mips/mips_malta.c b/hw/mips/mips_malta.c index 3467451482..40041d5ec0 100644 --- a/hw/mips/mips_malta.c +++ b/hw/mips/mips_malta.c @@ -599,6 +599,208 @@ static void network_init(PCIBus *pci_bus) } } +static void write_bootloader_nanomips(uint8_t *base, int64_t run_addr, + int64_t kernel_entry) +{ + uint16_t *p; + + /* Small bootloader */ + p = (uint16_t *)base; + +#define NM_HI1(VAL) (((VAL) >> 16) & 0x1f) +#define NM_HI2(VAL) \ + (((VAL) & 0xf000) | (((VAL) >> 19) & 0xffc) | (((VAL) >> 31) & 0x1)) +#define NM_LO(VAL) ((VAL) & 0xfff) + + stw_p(p++, 0x2800); stw_p(p++, 0x001c); + /* bc to_here */ + stw_p(p++, 0x8000); stw_p(p++, 0xc000); + /* nop */ + stw_p(p++, 0x8000); stw_p(p++, 0xc000); + /* nop */ + stw_p(p++, 0x8000); stw_p(p++, 0xc000); + /* nop */ + stw_p(p++, 0x8000); stw_p(p++, 0xc000); + /* nop */ + stw_p(p++, 0x8000); stw_p(p++, 0xc000); + /* nop */ + stw_p(p++, 0x8000); stw_p(p++, 0xc000); + /* nop */ + stw_p(p++, 0x8000); stw_p(p++, 0xc000); + /* nop */ + + /* to_here: */ + if (semihosting_get_argc()) { + /* Preserve a0 content as arguments have been passed */ + stw_p(p++, 0x8000); stw_p(p++, 0xc000); + /* nop */ + } else { + stw_p(p++, 0x0080); stw_p(p++, 0x0002); + /* li a0,2 */ + } + + stw_p(p++, 0xe3a0 | NM_HI1(ENVP_ADDR - 64)); + + stw_p(p++, NM_HI2(ENVP_ADDR - 64)); + /* lui sp,%hi(ENVP_ADDR - 64) */ + + stw_p(p++, 0x83bd); stw_p(p++, NM_LO(ENVP_ADDR - 64)); + /* ori sp,sp,%lo(ENVP_ADDR - 64) */ + + stw_p(p++, 0xe0a0 | NM_HI1(ENVP_ADDR)); + + stw_p(p++, NM_HI2(ENVP_ADDR)); + /* lui a1,%hi(ENVP_ADDR) */ + + stw_p(p++, 0x80a5); stw_p(p++, NM_LO(ENVP_ADDR)); + /* ori a1,a1,%lo(ENVP_ADDR) */ + + stw_p(p++, 0xe0c0 | NM_HI1(ENVP_ADDR + 8)); + + stw_p(p++, NM_HI2(ENVP_ADDR + 8)); + /* lui a2,%hi(ENVP_ADDR + 8) */ + + stw_p(p++, 0x80c6); stw_p(p++, NM_LO(ENVP_ADDR + 8)); + /* ori a2,a2,%lo(ENVP_ADDR + 8) */ + + stw_p(p++, 0xe0e0 | NM_HI1(loaderparams.ram_low_size)); + + stw_p(p++, NM_HI2(loaderparams.ram_low_size)); + /* lui a3,%hi(loaderparams.ram_low_size) */ + + stw_p(p++, 0x80e7); stw_p(p++, NM_LO(loaderparams.ram_low_size)); + /* ori a3,a3,%lo(loaderparams.ram_low_size) */ + + /* + * Load BAR registers as done by YAMON: + * + * - set up PCI0 I/O BARs from 0x18000000 to 0x181fffff + * - set up PCI0 MEM0 at 0x10000000, size 0x8000000 + * - set up PCI0 MEM1 at 0x18200000, size 0xbe00000 + * + */ + stw_p(p++, 0xe040); stw_p(p++, 0x0681); + /* lui t1, %hi(0xb4000000) */ + +#ifdef TARGET_WORDS_BIGENDIAN + + stw_p(p++, 0xe020); stw_p(p++, 0x0be1); + /* lui t0, %hi(0xdf000000) */ + + /* 0x68 corresponds to GT_ISD (from hw/mips/gt64xxx_pci.c) */ + stw_p(p++, 0x8422); stw_p(p++, 0x9068); + /* sw t0, 0x68(t1) */ + + stw_p(p++, 0xe040); stw_p(p++, 0x077d); + /* lui t1, %hi(0xbbe00000) */ + + stw_p(p++, 0xe020); stw_p(p++, 0x0801); + /* lui t0, %hi(0xc0000000) */ + + /* 0x48 corresponds to GT_PCI0IOLD */ + stw_p(p++, 0x8422); stw_p(p++, 0x9048); + /* sw t0, 0x48(t1) */ + + stw_p(p++, 0xe020); stw_p(p++, 0x0800); + /* lui t0, %hi(0x40000000) */ + + /* 0x50 corresponds to GT_PCI0IOHD */ + stw_p(p++, 0x8422); stw_p(p++, 0x9050); + /* sw t0, 0x50(t1) */ + + stw_p(p++, 0xe020); stw_p(p++, 0x0001); + /* lui t0, %hi(0x80000000) */ + + /* 0x58 corresponds to GT_PCI0M0LD */ + stw_p(p++, 0x8422); stw_p(p++, 0x9058); + /* sw t0, 0x58(t1) */ + + stw_p(p++, 0xe020); stw_p(p++, 0x07e0); + /* lui t0, %hi(0x3f000000) */ + + /* 0x60 corresponds to GT_PCI0M0HD */ + stw_p(p++, 0x8422); stw_p(p++, 0x9060); + /* sw t0, 0x60(t1) */ + + stw_p(p++, 0xe020); stw_p(p++, 0x0821); + /* lui t0, %hi(0xc1000000) */ + + /* 0x80 corresponds to GT_PCI0M1LD */ + stw_p(p++, 0x8422); stw_p(p++, 0x9080); + /* sw t0, 0x80(t1) */ + + stw_p(p++, 0xe020); stw_p(p++, 0x0bc0); + /* lui t0, %hi(0x5e000000) */ + +#else + + stw_p(p++, 0x0020); stw_p(p++, 0x00df); + /* addiu[32] t0, $0, 0xdf */ + + /* 0x68 corresponds to GT_ISD */ + stw_p(p++, 0x8422); stw_p(p++, 0x9068); + /* sw t0, 0x68(t1) */ + + /* Use kseg2 remapped address 0x1be00000 */ + stw_p(p++, 0xe040); stw_p(p++, 0x077d); + /* lui t1, %hi(0xbbe00000) */ + + stw_p(p++, 0x0020); stw_p(p++, 0x00c0); + /* addiu[32] t0, $0, 0xc0 */ + + /* 0x48 corresponds to GT_PCI0IOLD */ + stw_p(p++, 0x8422); stw_p(p++, 0x9048); + /* sw t0, 0x48(t1) */ + + stw_p(p++, 0x0020); stw_p(p++, 0x0040); + /* addiu[32] t0, $0, 0x40 */ + + /* 0x50 corresponds to GT_PCI0IOHD */ + stw_p(p++, 0x8422); stw_p(p++, 0x9050); + /* sw t0, 0x50(t1) */ + + stw_p(p++, 0x0020); stw_p(p++, 0x0080); + /* addiu[32] t0, $0, 0x80 */ + + /* 0x58 corresponds to GT_PCI0M0LD */ + stw_p(p++, 0x8422); stw_p(p++, 0x9058); + /* sw t0, 0x58(t1) */ + + stw_p(p++, 0x0020); stw_p(p++, 0x003f); + /* addiu[32] t0, $0, 0x3f */ + + /* 0x60 corresponds to GT_PCI0M0HD */ + stw_p(p++, 0x8422); stw_p(p++, 0x9060); + /* sw t0, 0x60(t1) */ + + stw_p(p++, 0x0020); stw_p(p++, 0x00c1); + /* addiu[32] t0, $0, 0xc1 */ + + /* 0x80 corresponds to GT_PCI0M1LD */ + stw_p(p++, 0x8422); stw_p(p++, 0x9080); + /* sw t0, 0x80(t1) */ + + stw_p(p++, 0x0020); stw_p(p++, 0x005e); + /* addiu[32] t0, $0, 0x5e */ + +#endif + + /* 0x88 corresponds to GT_PCI0M1HD */ + stw_p(p++, 0x8422); stw_p(p++, 0x9088); + /* sw t0, 0x88(t1) */ + + stw_p(p++, 0xe320 | NM_HI1(kernel_entry)); + + stw_p(p++, NM_HI2(kernel_entry)); + /* lui t9,%hi(kernel_entry) */ + + stw_p(p++, 0x8339); stw_p(p++, NM_LO(kernel_entry)); + /* ori t9,t9,%lo(kernel_entry) */ + + stw_p(p++, 0x4bf9); stw_p(p++, 0x0000); + /* jalrc t8 */ +} + /* ROM and pseudo bootloader The following code implements a very very simple bootloader. It first @@ -620,7 +822,6 @@ static void network_init(PCIBus *pci_bus) a2 - 32-bit address of the environment variables table a3 - RAM size in bytes */ - static void write_bootloader(uint8_t *base, int64_t run_addr, int64_t kernel_entry) { @@ -1096,8 +1297,13 @@ void mips_malta_init(MachineState *machine) loaderparams.initrd_filename = initrd_filename; kernel_entry = load_kernel(); - write_bootloader(memory_region_get_ram_ptr(bios), - bootloader_run_addr, kernel_entry); + if (!cpu_supports_isa(machine->cpu_type, ISA_NANOMIPS32)) { + write_bootloader(memory_region_get_ram_ptr(bios), + bootloader_run_addr, kernel_entry); + } else { + write_bootloader_nanomips(memory_region_get_ram_ptr(bios), + bootloader_run_addr, kernel_entry); + } if (kvm_enabled()) { /* Write the bootloader code @ the end of RAM, 1MB reserved */ write_bootloader(memory_region_get_ram_ptr(ram_low_preio) + diff --git a/include/elf.h b/include/elf.h index 28a5a638e0..312f68af81 100644 --- a/include/elf.h +++ b/include/elf.h @@ -143,6 +143,8 @@ typedef int64_t Elf64_Sxword; #define EM_RISCV 243 /* RISC-V */ +#define EM_NANOMIPS 249 /* Wave Computing nanoMIPS */ + /* * This is an interim value that we will use until the committee comes * up with a final number. diff --git a/include/hw/elf_ops.h b/include/hw/elf_ops.h index b6e19e35d0..81cecaf27e 100644 --- a/include/hw/elf_ops.h +++ b/include/hw/elf_ops.h @@ -327,6 +327,14 @@ static int glue(load_elf, SZ)(const char *name, int fd, } } break; + case EM_MIPS: + case EM_NANOMIPS: + if ((ehdr.e_machine != EM_MIPS) && + (ehdr.e_machine != EM_NANOMIPS)) { + ret = ELF_LOAD_WRONG_ARCH; + goto fail; + } + break; default: if (elf_machine != ehdr.e_machine) { ret = ELF_LOAD_WRONG_ARCH; diff --git a/include/qemu/queue.h b/include/qemu/queue.h index 59fd1203a1..ac418efc43 100644 --- a/include/qemu/queue.h +++ b/include/qemu/queue.h @@ -341,6 +341,7 @@ struct { \ /* * Simple queue access methods. */ +#define QSIMPLEQ_EMPTY_ATOMIC(head) (atomic_read(&((head)->sqh_first)) == NULL) #define QSIMPLEQ_EMPTY(head) ((head)->sqh_first == NULL) #define QSIMPLEQ_FIRST(head) ((head)->sqh_first) #define QSIMPLEQ_NEXT(elm, field) ((elm)->field.sqe_next) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index df07055361..8638612aec 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -853,6 +853,8 @@ static void elf_core_copy_regs(target_elf_gregset_t *regs, const CPUPPCState *en #endif #define ELF_ARCH EM_MIPS +#define elf_check_arch(x) ((x) == EM_MIPS || (x) == EM_NANOMIPS) + static inline void init_thread(struct target_pt_regs *regs, struct image_info *infop) { diff --git a/linux-user/mips/cpu_loop.c b/linux-user/mips/cpu_loop.c index 084ad6a041..c9c20cf8b7 100644 --- a/linux-user/mips/cpu_loop.c +++ b/linux-user/mips/cpu_loop.c @@ -397,10 +397,13 @@ static int do_store_exclusive(CPUMIPSState *env) target_ulong addr; target_ulong page_addr; target_ulong val; + uint32_t val_wp = 0; + uint32_t llnewval_wp = 0; int flags; int segv = 0; int reg; int d; + int wp; addr = env->lladdr; page_addr = addr & TARGET_PAGE_MASK; @@ -412,19 +415,31 @@ static int do_store_exclusive(CPUMIPSState *env) } else { reg = env->llreg & 0x1f; d = (env->llreg & 0x20) != 0; - if (d) { - segv = get_user_s64(val, addr); + wp = (env->llreg & 0x40) != 0; + if (!wp) { + if (d) { + segv = get_user_s64(val, addr); + } else { + segv = get_user_s32(val, addr); + } } else { segv = get_user_s32(val, addr); + segv |= get_user_s32(val_wp, addr); + llnewval_wp = env->llnewval_wp; } if (!segv) { - if (val != env->llval) { + if (val != env->llval && val_wp == llnewval_wp) { env->active_tc.gpr[reg] = 0; } else { - if (d) { - segv = put_user_u64(env->llnewval, addr); + if (!wp) { + if (d) { + segv = put_user_u64(env->llnewval, addr); + } else { + segv = put_user_u32(env->llnewval, addr); + } } else { segv = put_user_u32(env->llnewval, addr); + segv |= put_user_u32(env->llnewval_wp, addr + 4); } if (!segv) { env->active_tc.gpr[reg] = 1; @@ -732,6 +747,9 @@ void target_cpu_copy_regs(CPUArchState *env, struct target_pt_regs *regs) if (regs->cp0_epc & 1) { env->hflags |= MIPS_HFLAG_M16; } + if (env->insn_flags & ISA_NANOMIPS32) { + return; + } if (((info->elf_flags & EF_MIPS_NAN2008) != 0) != ((env->active_fpu.fcr31 & (1 << FCR31_NAN2008)) != 0)) { if ((env->active_fpu.fcr31_rw_bitmask & diff --git a/migration/colo.c b/migration/colo.c index 4381067ed4..88936f5962 100644 --- a/migration/colo.c +++ b/migration/colo.c @@ -534,6 +534,7 @@ void *colo_process_incoming_thread(void *opaque) uint64_t value; Error *local_err = NULL; + rcu_register_thread(); qemu_sem_init(&mis->colo_incoming_sem, 0); migrate_set_state(&mis->state, MIGRATION_STATUS_ACTIVE, @@ -666,5 +667,6 @@ out: } migration_incoming_exit_colo(); + rcu_unregister_thread(); return NULL; } diff --git a/migration/migration.c b/migration/migration.c index b7d9854bda..4b316ec343 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -71,6 +71,7 @@ /* Define default autoconverge cpu throttle migration parameters */ #define DEFAULT_MIGRATE_CPU_THROTTLE_INITIAL 20 #define DEFAULT_MIGRATE_CPU_THROTTLE_INCREMENT 10 +#define DEFAULT_MIGRATE_MAX_CPU_THROTTLE 99 /* Migration XBZRLE default cache size */ #define DEFAULT_MIGRATE_XBZRLE_CACHE_SIZE (64 * 1024 * 1024) @@ -389,6 +390,7 @@ static void process_incoming_migration_co(void *opaque) int ret; assert(mis->from_src_file); + mis->migration_incoming_co = qemu_coroutine_self(); mis->largest_page_size = qemu_ram_pagesize_largest(); postcopy_state_set(POSTCOPY_INCOMING_NONE); migrate_set_state(&mis->state, MIGRATION_STATUS_NONE, @@ -418,7 +420,6 @@ static void process_incoming_migration_co(void *opaque) /* we get COLO info, and know if we are in COLO mode */ if (!ret && migration_incoming_enable_colo()) { - mis->migration_incoming_co = qemu_coroutine_self(); qemu_thread_create(&mis->colo_incoming_thread, "COLO incoming", colo_process_incoming_thread, mis, QEMU_THREAD_JOINABLE); mis->have_colo_incoming_thread = true; @@ -442,6 +443,7 @@ static void process_incoming_migration_co(void *opaque) } mis->bh = qemu_bh_new(process_incoming_migration_bh, mis); qemu_bh_schedule(mis->bh); + mis->migration_incoming_co = NULL; } static void migration_incoming_setup(QEMUFile *f) @@ -671,6 +673,8 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp) params->compress_level = s->parameters.compress_level; params->has_compress_threads = true; params->compress_threads = s->parameters.compress_threads; + params->has_compress_wait_thread = true; + params->compress_wait_thread = s->parameters.compress_wait_thread; params->has_decompress_threads = true; params->decompress_threads = s->parameters.decompress_threads; params->has_cpu_throttle_initial = true; @@ -697,6 +701,8 @@ MigrationParameters *qmp_query_migrate_parameters(Error **errp) params->xbzrle_cache_size = s->parameters.xbzrle_cache_size; params->has_max_postcopy_bandwidth = true; params->max_postcopy_bandwidth = s->parameters.max_postcopy_bandwidth; + params->has_max_cpu_throttle = true; + params->max_cpu_throttle = s->parameters.max_cpu_throttle; return params; } @@ -1043,6 +1049,15 @@ static bool migrate_params_check(MigrationParameters *params, Error **errp) return false; } + if (params->has_max_cpu_throttle && + (params->max_cpu_throttle < params->cpu_throttle_initial || + params->max_cpu_throttle > 99)) { + error_setg(errp, QERR_INVALID_PARAMETER_VALUE, + "max_cpu_throttle", + "an integer in the range of cpu_throttle_initial to 99"); + return false; + } + return true; } @@ -1061,6 +1076,10 @@ static void migrate_params_test_apply(MigrateSetParameters *params, dest->compress_threads = params->compress_threads; } + if (params->has_compress_wait_thread) { + dest->compress_wait_thread = params->compress_wait_thread; + } + if (params->has_decompress_threads) { dest->decompress_threads = params->decompress_threads; } @@ -1110,6 +1129,9 @@ static void migrate_params_test_apply(MigrateSetParameters *params, if (params->has_max_postcopy_bandwidth) { dest->max_postcopy_bandwidth = params->max_postcopy_bandwidth; } + if (params->has_max_cpu_throttle) { + dest->max_cpu_throttle = params->max_cpu_throttle; + } } static void migrate_params_apply(MigrateSetParameters *params, Error **errp) @@ -1126,6 +1148,10 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp) s->parameters.compress_threads = params->compress_threads; } + if (params->has_compress_wait_thread) { + s->parameters.compress_wait_thread = params->compress_wait_thread; + } + if (params->has_decompress_threads) { s->parameters.decompress_threads = params->decompress_threads; } @@ -1185,6 +1211,9 @@ static void migrate_params_apply(MigrateSetParameters *params, Error **errp) if (params->has_max_postcopy_bandwidth) { s->parameters.max_postcopy_bandwidth = params->max_postcopy_bandwidth; } + if (params->has_max_cpu_throttle) { + s->parameters.max_cpu_throttle = params->max_cpu_throttle; + } } void qmp_migrate_set_parameters(MigrateSetParameters *params, Error **errp) @@ -1871,6 +1900,15 @@ int migrate_compress_threads(void) return s->parameters.compress_threads; } +int migrate_compress_wait_thread(void) +{ + MigrationState *s; + + s = migrate_get_current(); + + return s->parameters.compress_wait_thread; +} + int migrate_decompress_threads(void) { MigrationState *s; @@ -1962,7 +2000,6 @@ static int64_t migrate_max_postcopy_bandwidth(void) return s->parameters.max_postcopy_bandwidth; } - bool migrate_use_block(void) { MigrationState *s; @@ -2104,6 +2141,7 @@ static void *source_return_path_thread(void *opaque) int res; trace_source_return_path_thread_entry(); + rcu_register_thread(); retry: while (!ms->rp_state.error && !qemu_file_get_error(rp) && @@ -2243,6 +2281,7 @@ out: trace_source_return_path_thread_end(); ms->rp_state.from_dst_file = NULL; qemu_fclose(rp); + rcu_unregister_thread(); return NULL; } @@ -3131,6 +3170,8 @@ static Property migration_properties[] = { DEFINE_PROP_UINT8("x-compress-threads", MigrationState, parameters.compress_threads, DEFAULT_MIGRATE_COMPRESS_THREAD_COUNT), + DEFINE_PROP_BOOL("x-compress-wait-thread", MigrationState, + parameters.compress_wait_thread, true), DEFINE_PROP_UINT8("x-decompress-threads", MigrationState, parameters.decompress_threads, DEFAULT_MIGRATE_DECOMPRESS_THREAD_COUNT), @@ -3160,6 +3201,9 @@ static Property migration_properties[] = { DEFINE_PROP_SIZE("max-postcopy-bandwidth", MigrationState, parameters.max_postcopy_bandwidth, DEFAULT_MIGRATE_MAX_POSTCOPY_BANDWIDTH), + DEFINE_PROP_UINT8("max-cpu-throttle", MigrationState, + parameters.max_cpu_throttle, + DEFAULT_MIGRATE_MAX_CPU_THROTTLE), /* Migration capabilities */ DEFINE_PROP_MIG_CAP("x-xbzrle", MIGRATION_CAPABILITY_XBZRLE), @@ -3230,6 +3274,7 @@ static void migration_instance_init(Object *obj) params->has_x_multifd_page_count = true; params->has_xbzrle_cache_size = true; params->has_max_postcopy_bandwidth = true; + params->has_max_cpu_throttle = true; qemu_sem_init(&ms->postcopy_pause_sem, 0); qemu_sem_init(&ms->postcopy_pause_rp_sem, 0); diff --git a/migration/migration.h b/migration/migration.h index 64a7b33735..f7813f8261 100644 --- a/migration/migration.h +++ b/migration/migration.h @@ -266,11 +266,13 @@ bool migrate_colo_enabled(void); bool migrate_use_block(void); bool migrate_use_block_incremental(void); +int migrate_max_cpu_throttle(void); bool migrate_use_return_path(void); bool migrate_use_compression(void); int migrate_compress_level(void); int migrate_compress_threads(void); +int migrate_compress_wait_thread(void); int migrate_decompress_threads(void); bool migrate_use_events(void); bool migrate_postcopy_blocktime(void); diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c index 932f188949..3952d78e6b 100644 --- a/migration/postcopy-ram.c +++ b/migration/postcopy-ram.c @@ -853,6 +853,7 @@ static void *postcopy_ram_fault_thread(void *opaque) RAMBlock *rb = NULL; trace_postcopy_ram_fault_thread_entry(); + rcu_register_thread(); mis->last_rb = NULL; /* last RAMBlock we sent part of */ qemu_sem_post(&mis->fault_thread_sem); @@ -1059,6 +1060,7 @@ retry: } } } + rcu_unregister_thread(); trace_postcopy_ram_fault_thread_exit(); g_free(pfd); return NULL; diff --git a/migration/qemu-file-channel.c b/migration/qemu-file-channel.c index e202d73834..8e639eb496 100644 --- a/migration/qemu-file-channel.c +++ b/migration/qemu-file-channel.c @@ -49,7 +49,11 @@ static ssize_t channel_writev_buffer(void *opaque, ssize_t len; len = qio_channel_writev(ioc, local_iov, nlocal_iov, NULL); if (len == QIO_CHANNEL_ERR_BLOCK) { - qio_channel_wait(ioc, G_IO_OUT); + if (qemu_in_coroutine()) { + qio_channel_yield(ioc, G_IO_OUT); + } else { + qio_channel_wait(ioc, G_IO_OUT); + } continue; } if (len < 0) { @@ -80,7 +84,11 @@ static ssize_t channel_get_buffer(void *opaque, ret = qio_channel_read(ioc, (char *)buf, size, NULL); if (ret < 0) { if (ret == QIO_CHANNEL_ERR_BLOCK) { - qio_channel_yield(ioc, G_IO_IN); + if (qemu_in_coroutine()) { + qio_channel_yield(ioc, G_IO_IN); + } else { + qio_channel_wait(ioc, G_IO_IN); + } } else { /* XXX handle Error * object */ return -EIO; diff --git a/migration/qemu-file.c b/migration/qemu-file.c index 0463f4c321..977b9ae07c 100644 --- a/migration/qemu-file.c +++ b/migration/qemu-file.c @@ -253,8 +253,12 @@ size_t ram_control_save_page(QEMUFile *f, ram_addr_t block_offset, if (f->hooks && f->hooks->save_page) { int ret = f->hooks->save_page(f, f->opaque, block_offset, offset, size, bytes_sent); - f->bytes_xfer += size; - if (ret != RAM_SAVE_CONTROL_DELAYED) { + if (ret != RAM_SAVE_CONTROL_NOT_SUPP) { + f->bytes_xfer += size; + } + + if (ret != RAM_SAVE_CONTROL_DELAYED && + ret != RAM_SAVE_CONTROL_NOT_SUPP) { if (bytes_sent && *bytes_sent > 0) { qemu_update_position(f, *bytes_sent); } else if (ret < 0) { diff --git a/migration/ram.c b/migration/ram.c index fa79d0a5b9..79c89425a3 100644 --- a/migration/ram.c +++ b/migration/ram.c @@ -341,6 +341,7 @@ typedef struct PageSearchStatus PageSearchStatus; struct CompressParam { bool done; bool quit; + bool zero_page; QEMUFile *file; QemuMutex mutex; QemuCond cond; @@ -382,14 +383,15 @@ static QemuThread *decompress_threads; static QemuMutex decomp_done_lock; static QemuCond decomp_done_cond; -static int do_compress_ram_page(QEMUFile *f, z_stream *stream, RAMBlock *block, - ram_addr_t offset, uint8_t *source_buf); +static bool do_compress_ram_page(QEMUFile *f, z_stream *stream, RAMBlock *block, + ram_addr_t offset, uint8_t *source_buf); static void *do_data_compress(void *opaque) { CompressParam *param = opaque; RAMBlock *block; ram_addr_t offset; + bool zero_page; qemu_mutex_lock(¶m->mutex); while (!param->quit) { @@ -399,11 +401,12 @@ static void *do_data_compress(void *opaque) param->block = NULL; qemu_mutex_unlock(¶m->mutex); - do_compress_ram_page(param->file, ¶m->stream, block, offset, - param->originbuf); + zero_page = do_compress_ram_page(param->file, ¶m->stream, + block, offset, param->originbuf); qemu_mutex_lock(&comp_done_lock); param->done = true; + param->zero_page = zero_page; qemu_cond_signal(&comp_done_cond); qemu_mutex_unlock(&comp_done_lock); @@ -989,6 +992,7 @@ static void *multifd_send_thread(void *opaque) int ret; trace_multifd_send_thread_start(p->id); + rcu_register_thread(); if (multifd_send_initial_packet(p, &local_err) < 0) { goto out; @@ -1051,6 +1055,7 @@ out: p->running = false; qemu_mutex_unlock(&p->mutex); + rcu_unregister_thread(); trace_multifd_send_thread_end(p->id, p->num_packets, p->num_pages); return NULL; @@ -1220,6 +1225,7 @@ static void *multifd_recv_thread(void *opaque) int ret; trace_multifd_recv_thread_start(p->id); + rcu_register_thread(); while (true) { uint32_t used; @@ -1266,6 +1272,7 @@ static void *multifd_recv_thread(void *opaque) p->running = false; qemu_mutex_unlock(&p->mutex); + rcu_unregister_thread(); trace_multifd_recv_thread_end(p->id, p->num_packets, p->num_pages); return NULL; @@ -1391,13 +1398,15 @@ static void mig_throttle_guest_down(void) MigrationState *s = migrate_get_current(); uint64_t pct_initial = s->parameters.cpu_throttle_initial; uint64_t pct_icrement = s->parameters.cpu_throttle_increment; + int pct_max = s->parameters.max_cpu_throttle; /* We have not started throttling yet. Let's start it. */ if (!cpu_throttle_active()) { cpu_throttle_set(pct_initial); } else { /* Throttling already on, just increase the rate */ - cpu_throttle_set(cpu_throttle_get_percentage() + pct_icrement); + cpu_throttle_set(MIN(cpu_throttle_get_percentage() + pct_icrement, + pct_max)); } } @@ -1666,6 +1675,31 @@ static void migration_bitmap_sync(RAMState *rs) } /** + * save_zero_page_to_file: send the zero page to the file + * + * Returns the size of data written to the file, 0 means the page is not + * a zero page + * + * @rs: current RAM state + * @file: the file where the data is saved + * @block: block that contains the page we want to send + * @offset: offset inside the block for the page + */ +static int save_zero_page_to_file(RAMState *rs, QEMUFile *file, + RAMBlock *block, ram_addr_t offset) +{ + uint8_t *p = block->host + offset; + int len = 0; + + if (is_zero_range(p, TARGET_PAGE_SIZE)) { + len += save_page_header(rs, file, block, offset | RAM_SAVE_FLAG_ZERO); + qemu_put_byte(file, 0); + len += 1; + } + return len; +} + +/** * save_zero_page: send the zero page to the stream * * Returns the number of pages written. @@ -1676,19 +1710,14 @@ static void migration_bitmap_sync(RAMState *rs) */ static int save_zero_page(RAMState *rs, RAMBlock *block, ram_addr_t offset) { - uint8_t *p = block->host + offset; - int pages = -1; + int len = save_zero_page_to_file(rs, rs->f, block, offset); - if (is_zero_range(p, TARGET_PAGE_SIZE)) { + if (len) { ram_counters.duplicate++; - ram_counters.transferred += - save_page_header(rs, rs->f, block, offset | RAM_SAVE_FLAG_ZERO); - qemu_put_byte(rs->f, 0); - ram_counters.transferred += 1; - pages = 1; + ram_counters.transferred += len; + return 1; } - - return pages; + return -1; } static void ram_release_pages(const char *rbname, uint64_t offset, int pages) @@ -1823,15 +1852,20 @@ static int ram_save_multifd_page(RAMState *rs, RAMBlock *block, return 1; } -static int do_compress_ram_page(QEMUFile *f, z_stream *stream, RAMBlock *block, - ram_addr_t offset, uint8_t *source_buf) +static bool do_compress_ram_page(QEMUFile *f, z_stream *stream, RAMBlock *block, + ram_addr_t offset, uint8_t *source_buf) { RAMState *rs = ram_state; - int bytes_sent, blen; uint8_t *p = block->host + (offset & TARGET_PAGE_MASK); + bool zero_page = false; + int ret; + + if (save_zero_page_to_file(rs, f, block, offset)) { + zero_page = true; + goto exit; + } - bytes_sent = save_page_header(rs, f, block, offset | - RAM_SAVE_FLAG_COMPRESS_PAGE); + save_page_header(rs, f, block, offset | RAM_SAVE_FLAG_COMPRESS_PAGE); /* * copy it to a internal buffer to avoid it being modified by VM @@ -1839,17 +1873,25 @@ static int do_compress_ram_page(QEMUFile *f, z_stream *stream, RAMBlock *block, * decompression */ memcpy(source_buf, p, TARGET_PAGE_SIZE); - blen = qemu_put_compression_data(f, stream, source_buf, TARGET_PAGE_SIZE); - if (blen < 0) { - bytes_sent = 0; - qemu_file_set_error(migrate_get_current()->to_dst_file, blen); + ret = qemu_put_compression_data(f, stream, source_buf, TARGET_PAGE_SIZE); + if (ret < 0) { + qemu_file_set_error(migrate_get_current()->to_dst_file, ret); error_report("compressed data failed!"); - } else { - bytes_sent += blen; - ram_release_pages(block->idstr, offset & TARGET_PAGE_MASK, 1); + return false; } - return bytes_sent; +exit: + ram_release_pages(block->idstr, offset & TARGET_PAGE_MASK, 1); + return zero_page; +} + +static void +update_compress_thread_counts(const CompressParam *param, int bytes_xmit) +{ + if (param->zero_page) { + ram_counters.duplicate++; + } + ram_counters.transferred += bytes_xmit; } static void flush_compressed_data(RAMState *rs) @@ -1873,7 +1915,12 @@ static void flush_compressed_data(RAMState *rs) qemu_mutex_lock(&comp_param[idx].mutex); if (!comp_param[idx].quit) { len = qemu_put_qemu_file(rs->f, comp_param[idx].file); - ram_counters.transferred += len; + /* + * it's safe to fetch zero_page without holding comp_done_lock + * as there is no further request submitted to the thread, + * i.e, the thread should be waiting for a request at this point. + */ + update_compress_thread_counts(&comp_param[idx], len); } qemu_mutex_unlock(&comp_param[idx].mutex); } @@ -1890,30 +1937,33 @@ static int compress_page_with_multi_thread(RAMState *rs, RAMBlock *block, ram_addr_t offset) { int idx, thread_count, bytes_xmit = -1, pages = -1; + bool wait = migrate_compress_wait_thread(); thread_count = migrate_compress_threads(); qemu_mutex_lock(&comp_done_lock); - while (true) { - for (idx = 0; idx < thread_count; idx++) { - if (comp_param[idx].done) { - comp_param[idx].done = false; - bytes_xmit = qemu_put_qemu_file(rs->f, comp_param[idx].file); - qemu_mutex_lock(&comp_param[idx].mutex); - set_compress_params(&comp_param[idx], block, offset); - qemu_cond_signal(&comp_param[idx].cond); - qemu_mutex_unlock(&comp_param[idx].mutex); - pages = 1; - ram_counters.normal++; - ram_counters.transferred += bytes_xmit; - break; - } - } - if (pages > 0) { +retry: + for (idx = 0; idx < thread_count; idx++) { + if (comp_param[idx].done) { + comp_param[idx].done = false; + bytes_xmit = qemu_put_qemu_file(rs->f, comp_param[idx].file); + qemu_mutex_lock(&comp_param[idx].mutex); + set_compress_params(&comp_param[idx], block, offset); + qemu_cond_signal(&comp_param[idx].cond); + qemu_mutex_unlock(&comp_param[idx].mutex); + pages = 1; + update_compress_thread_counts(&comp_param[idx], bytes_xmit); break; - } else { - qemu_cond_wait(&comp_done_cond, &comp_done_lock); } } + + /* + * wait for the free thread if the user specifies 'compress-wait-thread', + * otherwise we will post the page out in the main thread as normal page. + */ + if (pages < 0 && wait) { + qemu_cond_wait(&comp_done_cond, &comp_done_lock); + goto retry; + } qemu_mutex_unlock(&comp_done_lock); return pages; @@ -1983,6 +2033,10 @@ static RAMBlock *unqueue_page(RAMState *rs, ram_addr_t *offset) { RAMBlock *block = NULL; + if (QSIMPLEQ_EMPTY_ATOMIC(&rs->src_page_requests)) { + return NULL; + } + qemu_mutex_lock(&rs->src_page_req_mutex); if (!QSIMPLEQ_EMPTY(&rs->src_page_requests)) { struct RAMSrcPageRequest *entry = @@ -2175,6 +2229,39 @@ static bool save_page_use_compression(RAMState *rs) return false; } +/* + * try to compress the page before posting it out, return true if the page + * has been properly handled by compression, otherwise needs other + * paths to handle it + */ +static bool save_compress_page(RAMState *rs, RAMBlock *block, ram_addr_t offset) +{ + if (!save_page_use_compression(rs)) { + return false; + } + + /* + * When starting the process of a new block, the first page of + * the block should be sent out before other pages in the same + * block, and all the pages in last block should have been sent + * out, keeping this order is important, because the 'cont' flag + * is used to avoid resending the block name. + * + * We post the fist page as normal page as compression will take + * much CPU resource. + */ + if (block != rs->last_sent_block) { + flush_compressed_data(rs); + return false; + } + + if (compress_page_with_multi_thread(rs, block, offset) > 0) { + return true; + } + + return false; +} + /** * ram_save_target_page: save one target page * @@ -2195,15 +2282,8 @@ static int ram_save_target_page(RAMState *rs, PageSearchStatus *pss, return res; } - /* - * When starting the process of a new block, the first page of - * the block should be sent out before other pages in the same - * block, and all the pages in last block should have been sent - * out, keeping this order is important, because the 'cont' flag - * is used to avoid resending the block name. - */ - if (block != rs->last_sent_block && save_page_use_compression(rs)) { - flush_compressed_data(rs); + if (save_compress_page(rs, block, offset)) { + return 1; } res = save_zero_page(rs, block, offset); @@ -2221,14 +2301,10 @@ static int ram_save_target_page(RAMState *rs, PageSearchStatus *pss, } /* - * Make sure the first page is sent out before other pages. - * - * we post it as normal page as compression will take much - * CPU resource. + * do not use multifd for compression as the first page in the new + * block should be posted out before sending the compressed page */ - if (block == rs->last_sent_block && save_page_use_compression(rs)) { - return compress_page_with_multi_thread(rs, block, offset); - } else if (migrate_use_multifd()) { + if (!save_page_use_compression(rs) && migrate_use_multifd()) { return ram_save_multifd_page(rs, block, offset); } diff --git a/migration/rdma.c b/migration/rdma.c index 8bd7159059..ae07515e83 100644 --- a/migration/rdma.c +++ b/migration/rdma.c @@ -86,6 +86,7 @@ static uint32_t known_capabilities = RDMA_CAPABILITY_PIN_ALL; " to abort!"); \ rdma->error_reported = 1; \ } \ + rcu_read_unlock(); \ return rdma->error_state; \ } \ } while (0) @@ -387,6 +388,10 @@ typedef struct RDMAContext { uint64_t unregistrations[RDMA_SIGNALED_SEND_MAX]; GHashTable *blockmap; + + /* the RDMAContext for return path */ + struct RDMAContext *return_path; + bool is_return_path; } RDMAContext; #define TYPE_QIO_CHANNEL_RDMA "qio-channel-rdma" @@ -398,7 +403,8 @@ typedef struct QIOChannelRDMA QIOChannelRDMA; struct QIOChannelRDMA { QIOChannel parent; - RDMAContext *rdma; + RDMAContext *rdmain; + RDMAContext *rdmaout; QEMUFile *file; bool blocking; /* XXX we don't actually honour this yet */ }; @@ -1483,27 +1489,56 @@ static uint64_t qemu_rdma_poll(RDMAContext *rdma, uint64_t *wr_id_out, */ static int qemu_rdma_wait_comp_channel(RDMAContext *rdma) { + struct rdma_cm_event *cm_event; + int ret = -1; + /* * Coroutine doesn't start until migration_fd_process_incoming() * so don't yield unless we know we're running inside of a coroutine. */ - if (rdma->migration_started_on_destination) { + if (rdma->migration_started_on_destination && + migration_incoming_get_current()->state == MIGRATION_STATUS_ACTIVE) { yield_until_fd_readable(rdma->comp_channel->fd); } else { /* This is the source side, we're in a separate thread * or destination prior to migration_fd_process_incoming() + * after postcopy, the destination also in a seprate thread. * we can't yield; so we have to poll the fd. * But we need to be able to handle 'cancel' or an error * without hanging forever. */ while (!rdma->error_state && !rdma->received_error) { - GPollFD pfds[1]; + GPollFD pfds[2]; pfds[0].fd = rdma->comp_channel->fd; pfds[0].events = G_IO_IN | G_IO_HUP | G_IO_ERR; + pfds[0].revents = 0; + + pfds[1].fd = rdma->channel->fd; + pfds[1].events = G_IO_IN | G_IO_HUP | G_IO_ERR; + pfds[1].revents = 0; + /* 0.1s timeout, should be fine for a 'cancel' */ - switch (qemu_poll_ns(pfds, 1, 100 * 1000 * 1000)) { + switch (qemu_poll_ns(pfds, 2, 100 * 1000 * 1000)) { + case 2: case 1: /* fd active */ - return 0; + if (pfds[0].revents) { + return 0; + } + + if (pfds[1].revents) { + ret = rdma_get_cm_event(rdma->channel, &cm_event); + if (!ret) { + rdma_ack_cm_event(cm_event); + } + + error_report("receive cm event while wait comp channel," + "cm event is %d", cm_event->event); + if (cm_event->event == RDMA_CM_EVENT_DISCONNECTED || + cm_event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) { + return -EPIPE; + } + } + break; case 0: /* Timeout, go around again */ break; @@ -2323,10 +2358,22 @@ static void qemu_rdma_cleanup(RDMAContext *rdma) rdma_destroy_id(rdma->cm_id); rdma->cm_id = NULL; } + + /* the destination side, listen_id and channel is shared */ if (rdma->listen_id) { - rdma_destroy_id(rdma->listen_id); + if (!rdma->is_return_path) { + rdma_destroy_id(rdma->listen_id); + } rdma->listen_id = NULL; + + if (rdma->channel) { + if (!rdma->is_return_path) { + rdma_destroy_event_channel(rdma->channel); + } + rdma->channel = NULL; + } } + if (rdma->channel) { rdma_destroy_event_channel(rdma->channel); rdma->channel = NULL; @@ -2555,6 +2602,25 @@ err_dest_init_create_listen_id: } +static void qemu_rdma_return_path_dest_init(RDMAContext *rdma_return_path, + RDMAContext *rdma) +{ + int idx; + + for (idx = 0; idx < RDMA_WRID_MAX; idx++) { + rdma_return_path->wr_data[idx].control_len = 0; + rdma_return_path->wr_data[idx].control_curr = NULL; + } + + /*the CM channel and CM id is shared*/ + rdma_return_path->channel = rdma->channel; + rdma_return_path->listen_id = rdma->listen_id; + + rdma->return_path = rdma_return_path; + rdma_return_path->return_path = rdma; + rdma_return_path->is_return_path = true; +} + static void *qemu_rdma_data_init(const char *host_port, Error **errp) { RDMAContext *rdma = NULL; @@ -2595,12 +2661,20 @@ static ssize_t qio_channel_rdma_writev(QIOChannel *ioc, { QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc); QEMUFile *f = rioc->file; - RDMAContext *rdma = rioc->rdma; + RDMAContext *rdma; int ret; ssize_t done = 0; size_t i; size_t len = 0; + rcu_read_lock(); + rdma = atomic_rcu_read(&rioc->rdmaout); + + if (!rdma) { + rcu_read_unlock(); + return -EIO; + } + CHECK_ERROR_STATE(); /* @@ -2610,6 +2684,7 @@ static ssize_t qio_channel_rdma_writev(QIOChannel *ioc, ret = qemu_rdma_write_flush(f, rdma); if (ret < 0) { rdma->error_state = ret; + rcu_read_unlock(); return ret; } @@ -2629,6 +2704,7 @@ static ssize_t qio_channel_rdma_writev(QIOChannel *ioc, if (ret < 0) { rdma->error_state = ret; + rcu_read_unlock(); return ret; } @@ -2637,6 +2713,7 @@ static ssize_t qio_channel_rdma_writev(QIOChannel *ioc, } } + rcu_read_unlock(); return done; } @@ -2670,12 +2747,20 @@ static ssize_t qio_channel_rdma_readv(QIOChannel *ioc, Error **errp) { QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc); - RDMAContext *rdma = rioc->rdma; + RDMAContext *rdma; RDMAControlHeader head; int ret = 0; ssize_t i; size_t done = 0; + rcu_read_lock(); + rdma = atomic_rcu_read(&rioc->rdmain); + + if (!rdma) { + rcu_read_unlock(); + return -EIO; + } + CHECK_ERROR_STATE(); for (i = 0; i < niov; i++) { @@ -2687,7 +2772,7 @@ static ssize_t qio_channel_rdma_readv(QIOChannel *ioc, * were given and dish out the bytes until we run * out of bytes. */ - ret = qemu_rdma_fill(rioc->rdma, data, want, 0); + ret = qemu_rdma_fill(rdma, data, want, 0); done += ret; want -= ret; /* Got what we needed, so go to next iovec */ @@ -2709,25 +2794,28 @@ static ssize_t qio_channel_rdma_readv(QIOChannel *ioc, if (ret < 0) { rdma->error_state = ret; + rcu_read_unlock(); return ret; } /* * SEND was received with new bytes, now try again. */ - ret = qemu_rdma_fill(rioc->rdma, data, want, 0); + ret = qemu_rdma_fill(rdma, data, want, 0); done += ret; want -= ret; /* Still didn't get enough, so lets just return */ if (want) { if (done == 0) { + rcu_read_unlock(); return QIO_CHANNEL_ERR_BLOCK; } else { break; } } } + rcu_read_unlock(); return done; } @@ -2779,15 +2867,29 @@ qio_channel_rdma_source_prepare(GSource *source, gint *timeout) { QIOChannelRDMASource *rsource = (QIOChannelRDMASource *)source; - RDMAContext *rdma = rsource->rioc->rdma; + RDMAContext *rdma; GIOCondition cond = 0; *timeout = -1; + rcu_read_lock(); + if (rsource->condition == G_IO_IN) { + rdma = atomic_rcu_read(&rsource->rioc->rdmain); + } else { + rdma = atomic_rcu_read(&rsource->rioc->rdmaout); + } + + if (!rdma) { + error_report("RDMAContext is NULL when prepare Gsource"); + rcu_read_unlock(); + return FALSE; + } + if (rdma->wr_data[0].control_len) { cond |= G_IO_IN; } cond |= G_IO_OUT; + rcu_read_unlock(); return cond & rsource->condition; } @@ -2795,14 +2897,28 @@ static gboolean qio_channel_rdma_source_check(GSource *source) { QIOChannelRDMASource *rsource = (QIOChannelRDMASource *)source; - RDMAContext *rdma = rsource->rioc->rdma; + RDMAContext *rdma; GIOCondition cond = 0; + rcu_read_lock(); + if (rsource->condition == G_IO_IN) { + rdma = atomic_rcu_read(&rsource->rioc->rdmain); + } else { + rdma = atomic_rcu_read(&rsource->rioc->rdmaout); + } + + if (!rdma) { + error_report("RDMAContext is NULL when check Gsource"); + rcu_read_unlock(); + return FALSE; + } + if (rdma->wr_data[0].control_len) { cond |= G_IO_IN; } cond |= G_IO_OUT; + rcu_read_unlock(); return cond & rsource->condition; } @@ -2813,14 +2929,28 @@ qio_channel_rdma_source_dispatch(GSource *source, { QIOChannelFunc func = (QIOChannelFunc)callback; QIOChannelRDMASource *rsource = (QIOChannelRDMASource *)source; - RDMAContext *rdma = rsource->rioc->rdma; + RDMAContext *rdma; GIOCondition cond = 0; + rcu_read_lock(); + if (rsource->condition == G_IO_IN) { + rdma = atomic_rcu_read(&rsource->rioc->rdmain); + } else { + rdma = atomic_rcu_read(&rsource->rioc->rdmaout); + } + + if (!rdma) { + error_report("RDMAContext is NULL when dispatch Gsource"); + rcu_read_unlock(); + return FALSE; + } + if (rdma->wr_data[0].control_len) { cond |= G_IO_IN; } cond |= G_IO_OUT; + rcu_read_unlock(); return (*func)(QIO_CHANNEL(rsource->rioc), (cond & rsource->condition), user_data); @@ -2860,20 +2990,91 @@ static GSource *qio_channel_rdma_create_watch(QIOChannel *ioc, return source; } +static void qio_channel_rdma_set_aio_fd_handler(QIOChannel *ioc, + AioContext *ctx, + IOHandler *io_read, + IOHandler *io_write, + void *opaque) +{ + QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc); + if (io_read) { + aio_set_fd_handler(ctx, rioc->rdmain->comp_channel->fd, + false, io_read, io_write, NULL, opaque); + } else { + aio_set_fd_handler(ctx, rioc->rdmaout->comp_channel->fd, + false, io_read, io_write, NULL, opaque); + } +} static int qio_channel_rdma_close(QIOChannel *ioc, Error **errp) { QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc); + RDMAContext *rdmain, *rdmaout; trace_qemu_rdma_close(); - if (rioc->rdma) { - if (!rioc->rdma->error_state) { - rioc->rdma->error_state = qemu_file_get_error(rioc->file); + + rdmain = rioc->rdmain; + if (rdmain) { + atomic_rcu_set(&rioc->rdmain, NULL); + } + + rdmaout = rioc->rdmaout; + if (rdmaout) { + atomic_rcu_set(&rioc->rdmaout, NULL); + } + + synchronize_rcu(); + + if (rdmain) { + qemu_rdma_cleanup(rdmain); + } + + if (rdmaout) { + qemu_rdma_cleanup(rdmaout); + } + + g_free(rdmain); + g_free(rdmaout); + + return 0; +} + +static int +qio_channel_rdma_shutdown(QIOChannel *ioc, + QIOChannelShutdown how, + Error **errp) +{ + QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(ioc); + RDMAContext *rdmain, *rdmaout; + + rcu_read_lock(); + + rdmain = atomic_rcu_read(&rioc->rdmain); + rdmaout = atomic_rcu_read(&rioc->rdmain); + + switch (how) { + case QIO_CHANNEL_SHUTDOWN_READ: + if (rdmain) { + rdmain->error_state = -1; + } + break; + case QIO_CHANNEL_SHUTDOWN_WRITE: + if (rdmaout) { + rdmaout->error_state = -1; } - qemu_rdma_cleanup(rioc->rdma); - g_free(rioc->rdma); - rioc->rdma = NULL; + break; + case QIO_CHANNEL_SHUTDOWN_BOTH: + default: + if (rdmain) { + rdmain->error_state = -1; + } + if (rdmaout) { + rdmaout->error_state = -1; + } + break; } + + rcu_read_unlock(); return 0; } @@ -2916,11 +3117,24 @@ static size_t qemu_rdma_save_page(QEMUFile *f, void *opaque, size_t size, uint64_t *bytes_sent) { QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(opaque); - RDMAContext *rdma = rioc->rdma; + RDMAContext *rdma; int ret; + rcu_read_lock(); + rdma = atomic_rcu_read(&rioc->rdmaout); + + if (!rdma) { + rcu_read_unlock(); + return -EIO; + } + CHECK_ERROR_STATE(); + if (migrate_get_current()->state == MIGRATION_STATUS_POSTCOPY_ACTIVE) { + rcu_read_unlock(); + return RAM_SAVE_CONTROL_NOT_SUPP; + } + qemu_fflush(f); if (size > 0) { @@ -3002,12 +3216,45 @@ static size_t qemu_rdma_save_page(QEMUFile *f, void *opaque, } } + rcu_read_unlock(); return RAM_SAVE_CONTROL_DELAYED; err: rdma->error_state = ret; + rcu_read_unlock(); return ret; } +static void rdma_accept_incoming_migration(void *opaque); + +static void rdma_cm_poll_handler(void *opaque) +{ + RDMAContext *rdma = opaque; + int ret; + struct rdma_cm_event *cm_event; + MigrationIncomingState *mis = migration_incoming_get_current(); + + ret = rdma_get_cm_event(rdma->channel, &cm_event); + if (ret) { + error_report("get_cm_event failed %d", errno); + return; + } + rdma_ack_cm_event(cm_event); + + if (cm_event->event == RDMA_CM_EVENT_DISCONNECTED || + cm_event->event == RDMA_CM_EVENT_DEVICE_REMOVAL) { + error_report("receive cm event, cm event is %d", cm_event->event); + rdma->error_state = -EPIPE; + if (rdma->return_path) { + rdma->return_path->error_state = -EPIPE; + } + + if (mis->migration_incoming_co) { + qemu_coroutine_enter(mis->migration_incoming_co); + } + return; + } +} + static int qemu_rdma_accept(RDMAContext *rdma) { RDMACapabilities cap; @@ -3102,7 +3349,15 @@ static int qemu_rdma_accept(RDMAContext *rdma) } } - qemu_set_fd_handler(rdma->channel->fd, NULL, NULL, NULL); + /* Accept the second connection request for return path */ + if (migrate_postcopy() && !rdma->is_return_path) { + qemu_set_fd_handler(rdma->channel->fd, rdma_accept_incoming_migration, + NULL, + (void *)(intptr_t)rdma->return_path); + } else { + qemu_set_fd_handler(rdma->channel->fd, rdma_cm_poll_handler, + NULL, rdma); + } ret = rdma_accept(rdma->cm_id, &conn_param); if (ret) { @@ -3171,8 +3426,8 @@ static int qemu_rdma_registration_handle(QEMUFile *f, void *opaque) RDMAControlHeader blocks = { .type = RDMA_CONTROL_RAM_BLOCKS_RESULT, .repeat = 1 }; QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(opaque); - RDMAContext *rdma = rioc->rdma; - RDMALocalBlocks *local = &rdma->local_ram_blocks; + RDMAContext *rdma; + RDMALocalBlocks *local; RDMAControlHeader head; RDMARegister *reg, *registers; RDMACompress *comp; @@ -3185,8 +3440,17 @@ static int qemu_rdma_registration_handle(QEMUFile *f, void *opaque) int count = 0; int i = 0; + rcu_read_lock(); + rdma = atomic_rcu_read(&rioc->rdmain); + + if (!rdma) { + rcu_read_unlock(); + return -EIO; + } + CHECK_ERROR_STATE(); + local = &rdma->local_ram_blocks; do { trace_qemu_rdma_registration_handle_wait(); @@ -3420,6 +3684,7 @@ out: if (ret < 0) { rdma->error_state = ret; } + rcu_read_unlock(); return ret; } @@ -3433,10 +3698,18 @@ out: static int rdma_block_notification_handle(QIOChannelRDMA *rioc, const char *name) { - RDMAContext *rdma = rioc->rdma; + RDMAContext *rdma; int curr; int found = -1; + rcu_read_lock(); + rdma = atomic_rcu_read(&rioc->rdmain); + + if (!rdma) { + rcu_read_unlock(); + return -EIO; + } + /* Find the matching RAMBlock in our local list */ for (curr = 0; curr < rdma->local_ram_blocks.nb_blocks; curr++) { if (!strcmp(rdma->local_ram_blocks.block[curr].block_name, name)) { @@ -3447,6 +3720,7 @@ rdma_block_notification_handle(QIOChannelRDMA *rioc, const char *name) if (found == -1) { error_report("RAMBlock '%s' not found on destination", name); + rcu_read_unlock(); return -ENOENT; } @@ -3454,6 +3728,7 @@ rdma_block_notification_handle(QIOChannelRDMA *rioc, const char *name) trace_rdma_block_notification_handle(name, rdma->next_src_index); rdma->next_src_index++; + rcu_read_unlock(); return 0; } @@ -3476,14 +3751,27 @@ static int qemu_rdma_registration_start(QEMUFile *f, void *opaque, uint64_t flags, void *data) { QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(opaque); - RDMAContext *rdma = rioc->rdma; + RDMAContext *rdma; + + rcu_read_lock(); + rdma = atomic_rcu_read(&rioc->rdmaout); + if (!rdma) { + rcu_read_unlock(); + return -EIO; + } CHECK_ERROR_STATE(); + if (migrate_get_current()->state == MIGRATION_STATUS_POSTCOPY_ACTIVE) { + rcu_read_unlock(); + return 0; + } + trace_qemu_rdma_registration_start(flags); qemu_put_be64(f, RAM_SAVE_FLAG_HOOK); qemu_fflush(f); + rcu_read_unlock(); return 0; } @@ -3496,12 +3784,24 @@ static int qemu_rdma_registration_stop(QEMUFile *f, void *opaque, { Error *local_err = NULL, **errp = &local_err; QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(opaque); - RDMAContext *rdma = rioc->rdma; + RDMAContext *rdma; RDMAControlHeader head = { .len = 0, .repeat = 1 }; int ret = 0; + rcu_read_lock(); + rdma = atomic_rcu_read(&rioc->rdmaout); + if (!rdma) { + rcu_read_unlock(); + return -EIO; + } + CHECK_ERROR_STATE(); + if (migrate_get_current()->state == MIGRATION_STATUS_POSTCOPY_ACTIVE) { + rcu_read_unlock(); + return 0; + } + qemu_fflush(f); ret = qemu_rdma_drain_cq(f, rdma); @@ -3530,6 +3830,7 @@ static int qemu_rdma_registration_stop(QEMUFile *f, void *opaque, qemu_rdma_reg_whole_ram_blocks : NULL); if (ret < 0) { ERROR(errp, "receiving remote info!"); + rcu_read_unlock(); return ret; } @@ -3553,6 +3854,7 @@ static int qemu_rdma_registration_stop(QEMUFile *f, void *opaque, "not identical on both the source and destination.", local->nb_blocks, nb_dest_blocks); rdma->error_state = -EINVAL; + rcu_read_unlock(); return -EINVAL; } @@ -3569,6 +3871,7 @@ static int qemu_rdma_registration_stop(QEMUFile *f, void *opaque, local->block[i].length, rdma->dest_blocks[i].length); rdma->error_state = -EINVAL; + rcu_read_unlock(); return -EINVAL; } local->block[i].remote_host_addr = @@ -3586,9 +3889,11 @@ static int qemu_rdma_registration_stop(QEMUFile *f, void *opaque, goto err; } + rcu_read_unlock(); return 0; err: rdma->error_state = ret; + rcu_read_unlock(); return ret; } @@ -3606,10 +3911,15 @@ static const QEMUFileHooks rdma_write_hooks = { static void qio_channel_rdma_finalize(Object *obj) { QIOChannelRDMA *rioc = QIO_CHANNEL_RDMA(obj); - if (rioc->rdma) { - qemu_rdma_cleanup(rioc->rdma); - g_free(rioc->rdma); - rioc->rdma = NULL; + if (rioc->rdmain) { + qemu_rdma_cleanup(rioc->rdmain); + g_free(rioc->rdmain); + rioc->rdmain = NULL; + } + if (rioc->rdmaout) { + qemu_rdma_cleanup(rioc->rdmaout); + g_free(rioc->rdmaout); + rioc->rdmaout = NULL; } } @@ -3623,6 +3933,8 @@ static void qio_channel_rdma_class_init(ObjectClass *klass, ioc_klass->io_set_blocking = qio_channel_rdma_set_blocking; ioc_klass->io_close = qio_channel_rdma_close; ioc_klass->io_create_watch = qio_channel_rdma_create_watch; + ioc_klass->io_set_aio_fd_handler = qio_channel_rdma_set_aio_fd_handler; + ioc_klass->io_shutdown = qio_channel_rdma_shutdown; } static const TypeInfo qio_channel_rdma_info = { @@ -3649,13 +3961,16 @@ static QEMUFile *qemu_fopen_rdma(RDMAContext *rdma, const char *mode) } rioc = QIO_CHANNEL_RDMA(object_new(TYPE_QIO_CHANNEL_RDMA)); - rioc->rdma = rdma; if (mode[0] == 'w') { rioc->file = qemu_fopen_channel_output(QIO_CHANNEL(rioc)); + rioc->rdmaout = rdma; + rioc->rdmain = rdma->return_path; qemu_file_set_hooks(rioc->file, &rdma_write_hooks); } else { rioc->file = qemu_fopen_channel_input(QIO_CHANNEL(rioc)); + rioc->rdmain = rdma; + rioc->rdmaout = rdma->return_path; qemu_file_set_hooks(rioc->file, &rdma_read_hooks); } @@ -3679,6 +3994,10 @@ static void rdma_accept_incoming_migration(void *opaque) trace_qemu_rdma_accept_incoming_migration_accepted(); + if (rdma->is_return_path) { + return; + } + f = qemu_fopen_rdma(rdma, "rb"); if (f == NULL) { ERROR(errp, "could not qemu_fopen_rdma!"); @@ -3693,7 +4012,7 @@ static void rdma_accept_incoming_migration(void *opaque) void rdma_start_incoming_migration(const char *host_port, Error **errp) { int ret; - RDMAContext *rdma; + RDMAContext *rdma, *rdma_return_path; Error *local_err = NULL; trace_rdma_start_incoming_migration(); @@ -3720,12 +4039,24 @@ void rdma_start_incoming_migration(const char *host_port, Error **errp) trace_rdma_start_incoming_migration_after_rdma_listen(); + /* initialize the RDMAContext for return path */ + if (migrate_postcopy()) { + rdma_return_path = qemu_rdma_data_init(host_port, &local_err); + + if (rdma_return_path == NULL) { + goto err; + } + + qemu_rdma_return_path_dest_init(rdma_return_path, rdma); + } + qemu_set_fd_handler(rdma->channel->fd, rdma_accept_incoming_migration, NULL, (void *)(intptr_t)rdma); return; err: error_propagate(errp, local_err); g_free(rdma); + g_free(rdma_return_path); } void rdma_start_outgoing_migration(void *opaque, @@ -3733,6 +4064,7 @@ void rdma_start_outgoing_migration(void *opaque, { MigrationState *s = opaque; RDMAContext *rdma = qemu_rdma_data_init(host_port, errp); + RDMAContext *rdma_return_path = NULL; int ret = 0; if (rdma == NULL) { @@ -3753,6 +4085,32 @@ void rdma_start_outgoing_migration(void *opaque, goto err; } + /* RDMA postcopy need a seprate queue pair for return path */ + if (migrate_postcopy()) { + rdma_return_path = qemu_rdma_data_init(host_port, errp); + + if (rdma_return_path == NULL) { + goto err; + } + + ret = qemu_rdma_source_init(rdma_return_path, + s->enabled_capabilities[MIGRATION_CAPABILITY_RDMA_PIN_ALL], errp); + + if (ret) { + goto err; + } + + ret = qemu_rdma_connect(rdma_return_path, errp); + + if (ret) { + goto err; + } + + rdma->return_path = rdma_return_path; + rdma_return_path->return_path = rdma; + rdma_return_path->is_return_path = true; + } + trace_rdma_start_outgoing_migration_after_rdma_connect(); s->to_dst_file = qemu_fopen_rdma(rdma, "wb"); @@ -3760,4 +4118,5 @@ void rdma_start_outgoing_migration(void *opaque, return; err: g_free(rdma); + g_free(rdma_return_path); } diff --git a/migration/savevm.c b/migration/savevm.c index 7f92567a10..13e51f0e34 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -1622,6 +1622,7 @@ static void *postcopy_ram_listen_thread(void *opaque) qemu_sem_post(&mis->listen_thread_sem); trace_postcopy_ram_listen_thread_start(); + rcu_register_thread(); /* * Because we're a thread and not a coroutine we can't yield * in qemu_file, and thus we must be blocking now. @@ -1662,6 +1663,7 @@ static void *postcopy_ram_listen_thread(void *opaque) * to leave the guest running and fire MCEs for pages that never * arrived as a desperate recovery step. */ + rcu_unregister_thread(); exit(EXIT_FAILURE); } @@ -1676,6 +1678,7 @@ static void *postcopy_ram_listen_thread(void *opaque) migration_incoming_state_destroy(); qemu_loadvm_state_cleanup(); + rcu_unregister_thread(); return NULL; } diff --git a/migration/vmstate.c b/migration/vmstate.c index 6b9079bb51..0bc240a317 100644 --- a/migration/vmstate.c +++ b/migration/vmstate.c @@ -418,7 +418,7 @@ int vmstate_save_state_v(QEMUFile *f, const VMStateDescription *vmsd, static const VMStateDescription * vmstate_get_subsection(const VMStateDescription **sub, char *idstr) { - while (sub && *sub && (*sub)->needed) { + while (sub && *sub) { if (strcmp(idstr, (*sub)->name) == 0) { return *sub; } @@ -486,8 +486,8 @@ static int vmstate_subsection_save(QEMUFile *f, const VMStateDescription *vmsd, int ret = 0; trace_vmstate_subsection_save_top(vmsd->name); - while (sub && *sub && (*sub)->needed) { - if ((*sub)->needed(opaque)) { + while (sub && *sub) { + if (vmstate_save_needed(*sub, opaque)) { const VMStateDescription *vmsdsub = *sub; uint8_t len; diff --git a/qapi/migration.json b/qapi/migration.json index 186e8a7303..f62d3f9a4b 100644 --- a/qapi/migration.json +++ b/qapi/migration.json @@ -212,13 +212,13 @@ # -> { "execute": "query-migrate" } # <- { "return": { # "status": "completed", +# "total-time":12345, +# "setup-time":12345, +# "downtime":12345, # "ram":{ # "transferred":123, # "remaining":123, # "total":246, -# "total-time":12345, -# "setup-time":12345, -# "downtime":12345, # "duplicate":123, # "normal":123, # "normal-bytes":123456, @@ -238,13 +238,13 @@ # <- { # "return":{ # "status":"active", +# "total-time":12345, +# "setup-time":12345, +# "expected-downtime":12345, # "ram":{ # "transferred":123, # "remaining":123, # "total":246, -# "total-time":12345, -# "setup-time":12345, -# "expected-downtime":12345, # "duplicate":123, # "normal":123, # "normal-bytes":123456, @@ -259,13 +259,13 @@ # <- { # "return":{ # "status":"active", +# "total-time":12345, +# "setup-time":12345, +# "expected-downtime":12345, # "ram":{ # "total":1057024, # "remaining":1053304, # "transferred":3720, -# "total-time":12345, -# "setup-time":12345, -# "expected-downtime":12345, # "duplicate":123, # "normal":123, # "normal-bytes":123456, @@ -285,14 +285,13 @@ # <- { # "return":{ # "status":"active", -# "capabilities" : [ { "capability": "xbzrle", "state" : true } ], +# "total-time":12345, +# "setup-time":12345, +# "expected-downtime":12345, # "ram":{ # "total":1057024, # "remaining":1053304, # "transferred":3720, -# "total-time":12345, -# "setup-time":12345, -# "expected-downtime":12345, # "duplicate":10, # "normal":3333, # "normal-bytes":3412992, @@ -462,6 +461,11 @@ # @compress-threads: Set compression thread count to be used in live migration, # the compression thread count is an integer between 1 and 255. # +# @compress-wait-thread: Controls behavior when all compression threads are +# currently busy. If true (default), wait for a free +# compression thread to become available; otherwise, +# send the page uncompressed. (Since 3.1) +# # @decompress-threads: Set decompression thread count to be used in live # migration, the decompression thread count is an integer between 1 # and 255. Usually, decompression is at least 4 times as fast as @@ -523,15 +527,20 @@ # @max-postcopy-bandwidth: Background transfer bandwidth during postcopy. # Defaults to 0 (unlimited). In bytes per second. # (Since 3.0) +# +# @max-cpu-throttle: maximum cpu throttle percentage. +# Defaults to 99. (Since 3.1) # Since: 2.4 ## { 'enum': 'MigrationParameter', 'data': ['compress-level', 'compress-threads', 'decompress-threads', + 'compress-wait-thread', 'cpu-throttle-initial', 'cpu-throttle-increment', 'tls-creds', 'tls-hostname', 'max-bandwidth', 'downtime-limit', 'x-checkpoint-delay', 'block-incremental', 'x-multifd-channels', 'x-multifd-page-count', - 'xbzrle-cache-size', 'max-postcopy-bandwidth' ] } + 'xbzrle-cache-size', 'max-postcopy-bandwidth', + 'max-cpu-throttle' ] } ## # @MigrateSetParameters: @@ -540,6 +549,11 @@ # # @compress-threads: compression thread count # +# @compress-wait-thread: Controls behavior when all compression threads are +# currently busy. If true (default), wait for a free +# compression thread to become available; otherwise, +# send the page uncompressed. (Since 3.1) +# # @decompress-threads: decompression thread count # # @cpu-throttle-initial: Initial percentage of time guest cpus are @@ -603,6 +617,10 @@ # @max-postcopy-bandwidth: Background transfer bandwidth during postcopy. # Defaults to 0 (unlimited). In bytes per second. # (Since 3.0) +# +# @max-cpu-throttle: maximum cpu throttle percentage. +# The default value is 99. (Since 3.1) +# # Since: 2.4 ## # TODO either fuse back into MigrationParameters, or make @@ -610,6 +628,7 @@ { 'struct': 'MigrateSetParameters', 'data': { '*compress-level': 'int', '*compress-threads': 'int', + '*compress-wait-thread': 'bool', '*decompress-threads': 'int', '*cpu-throttle-initial': 'int', '*cpu-throttle-increment': 'int', @@ -622,7 +641,8 @@ '*x-multifd-channels': 'int', '*x-multifd-page-count': 'int', '*xbzrle-cache-size': 'size', - '*max-postcopy-bandwidth': 'size' } } + '*max-postcopy-bandwidth': 'size', + '*max-cpu-throttle': 'int' } } ## # @migrate-set-parameters: @@ -649,6 +669,11 @@ # # @compress-threads: compression thread count # +# @compress-wait-thread: Controls behavior when all compression threads are +# currently busy. If true (default), wait for a free +# compression thread to become available; otherwise, +# send the page uncompressed. (Since 3.1) +# # @decompress-threads: decompression thread count # # @cpu-throttle-initial: Initial percentage of time guest cpus are @@ -709,11 +734,17 @@ # @max-postcopy-bandwidth: Background transfer bandwidth during postcopy. # Defaults to 0 (unlimited). In bytes per second. # (Since 3.0) +# +# @max-cpu-throttle: maximum cpu throttle percentage. +# Defaults to 99. +# (Since 3.1) +# # Since: 2.4 ## { 'struct': 'MigrationParameters', 'data': { '*compress-level': 'uint8', '*compress-threads': 'uint8', + '*compress-wait-thread': 'bool', '*decompress-threads': 'uint8', '*cpu-throttle-initial': 'uint8', '*cpu-throttle-increment': 'uint8', @@ -726,7 +757,8 @@ '*x-multifd-channels': 'uint8', '*x-multifd-page-count': 'uint32', '*xbzrle-cache-size': 'size', - '*max-postcopy-bandwidth': 'size' } } + '*max-postcopy-bandwidth': 'size', + '*max-cpu-throttle':'uint8'} } ## # @query-migrate-parameters: diff --git a/target/mips/cpu.h b/target/mips/cpu.h index 009202cf64..28af4d191c 100644 --- a/target/mips/cpu.h +++ b/target/mips/cpu.h @@ -506,6 +506,8 @@ struct CPUMIPSState { uint64_t lladdr; target_ulong llval; target_ulong llnewval; + uint64_t llval_wp; + uint32_t llnewval_wp; target_ulong llreg; uint64_t CP0_LLAddr_rw_bitmask; int CP0_LLAddr_shift; diff --git a/target/mips/helper.c b/target/mips/helper.c index e215af9a41..f0c268b83c 100644 --- a/target/mips/helper.c +++ b/target/mips/helper.c @@ -682,6 +682,22 @@ static void set_hflags_for_handler (CPUMIPSState *env) static inline void set_badinstr_registers(CPUMIPSState *env) { + if (env->insn_flags & ISA_NANOMIPS32) { + if (env->CP0_Config3 & (1 << CP0C3_BI)) { + uint32_t instr = (cpu_lduw_code(env, env->active_tc.PC)) << 16; + if ((instr & 0x10000000) == 0) { + instr |= cpu_lduw_code(env, env->active_tc.PC + 2); + } + env->CP0_BadInstr = instr; + + if ((instr & 0xFC000000) == 0x60000000) { + instr = cpu_lduw_code(env, env->active_tc.PC + 4) << 16; + env->CP0_BadInstrX = instr; + } + } + return; + } + if (env->hflags & MIPS_HFLAG_M16) { /* TODO: add BadInstr support for microMIPS */ return; diff --git a/target/mips/helper.h b/target/mips/helper.h index 5f492348dd..b2a780a6f2 100644 --- a/target/mips/helper.h +++ b/target/mips/helper.h @@ -40,6 +40,8 @@ DEF_HELPER_FLAGS_1(bitswap, TCG_CALL_NO_RWG_SE, tl, tl) DEF_HELPER_FLAGS_1(dbitswap, TCG_CALL_NO_RWG_SE, tl, tl) #endif +DEF_HELPER_FLAGS_4(rotx, TCG_CALL_NO_RWG_SE, tl, tl, i32, i32, i32) + #ifndef CONFIG_USER_ONLY /* CP0 helpers */ DEF_HELPER_1(mfc0_mvpcontrol, tl, env) diff --git a/target/mips/mips-defs.h b/target/mips/mips-defs.h index d239069975..c8e99791ad 100644 --- a/target/mips/mips-defs.h +++ b/target/mips/mips-defs.h @@ -39,6 +39,7 @@ #define ISA_MIPS64R5 0x00001000 #define ISA_MIPS32R6 0x00002000 #define ISA_MIPS64R6 0x00004000 +#define ISA_NANOMIPS32 0x00008000 /* MIPS ASEs. */ #define ASE_MIPS16 0x00010000 @@ -87,6 +88,9 @@ #define CPU_MIPS32R6 (CPU_MIPS32R5 | ISA_MIPS32R6) #define CPU_MIPS64R6 (CPU_MIPS64R5 | CPU_MIPS32R6 | ISA_MIPS64R6) +/* Wave Computing: "nanoMIPS" */ +#define CPU_NANOMIPS32 (CPU_MIPS32R6 | ISA_NANOMIPS32) + /* Strictly follow the architecture standard: - Disallow "special" instruction handling for PMON/SPIM. Note that we still maintain Count/Compare to match the host clock. */ diff --git a/target/mips/op_helper.c b/target/mips/op_helper.c index 0b2663b73a..c148b310cd 100644 --- a/target/mips/op_helper.c +++ b/target/mips/op_helper.c @@ -249,6 +249,100 @@ target_ulong helper_bitswap(target_ulong rt) return (int32_t)bitswap(rt); } +target_ulong helper_rotx(target_ulong rs, uint32_t shift, uint32_t shiftx, + uint32_t stripe) +{ + int i; + uint64_t tmp0 = ((uint64_t)rs) << 32 | ((uint64_t)rs & 0xffffffff); + uint64_t tmp1 = tmp0; + for (i = 0; i <= 46; i++) { + int s; + if (i & 0x8) { + s = shift; + } else { + s = shiftx; + } + + if (stripe != 0 && !(i & 0x4)) { + s = ~s; + } + if (s & 0x10) { + if (tmp0 & (1LL << (i + 16))) { + tmp1 |= 1LL << i; + } else { + tmp1 &= ~(1LL << i); + } + } + } + + uint64_t tmp2 = tmp1; + for (i = 0; i <= 38; i++) { + int s; + if (i & 0x4) { + s = shift; + } else { + s = shiftx; + } + + if (s & 0x8) { + if (tmp1 & (1LL << (i + 8))) { + tmp2 |= 1LL << i; + } else { + tmp2 &= ~(1LL << i); + } + } + } + + uint64_t tmp3 = tmp2; + for (i = 0; i <= 34; i++) { + int s; + if (i & 0x2) { + s = shift; + } else { + s = shiftx; + } + if (s & 0x4) { + if (tmp2 & (1LL << (i + 4))) { + tmp3 |= 1LL << i; + } else { + tmp3 &= ~(1LL << i); + } + } + } + + uint64_t tmp4 = tmp3; + for (i = 0; i <= 32; i++) { + int s; + if (i & 0x1) { + s = shift; + } else { + s = shiftx; + } + if (s & 0x2) { + if (tmp3 & (1LL << (i + 2))) { + tmp4 |= 1LL << i; + } else { + tmp4 &= ~(1LL << i); + } + } + } + + uint64_t tmp5 = tmp4; + for (i = 0; i <= 31; i++) { + int s; + s = shift; + if (s & 0x1) { + if (tmp4 & (1LL << (i + 1))) { + tmp5 |= 1LL << i; + } else { + tmp5 &= ~(1LL << i); + } + } + } + + return (int64_t)(int32_t)(uint32_t)tmp5; +} + #ifndef CONFIG_USER_ONLY static inline hwaddr do_translate_address(CPUMIPSState *env, @@ -2333,10 +2427,12 @@ void helper_eretnc(CPUMIPSState *env) void helper_deret(CPUMIPSState *env) { debug_pre_eret(env); - set_pc(env, env->CP0_DEPC); env->hflags &= ~MIPS_HFLAG_DM; compute_hflags(env); + + set_pc(env, env->CP0_DEPC); + debug_post_eret(env); } #endif /* !CONFIG_USER_ONLY */ diff --git a/target/mips/translate.c b/target/mips/translate.c index bdd880bb77..ab16cdb911 100644 --- a/target/mips/translate.c +++ b/target/mips/translate.c @@ -1449,6 +1449,8 @@ typedef struct DisasContext { uint32_t opcode; int insn_flags; int32_t CP0_Config1; + int32_t CP0_Config3; + int32_t CP0_Config5; /* Routine used to access memory */ int mem_idx; TCGMemOp default_tcg_memop_mask; @@ -1746,6 +1748,18 @@ static inline void gen_op_addr_add (DisasContext *ctx, TCGv ret, TCGv arg0, TCGv #endif } +static inline void gen_op_addr_addi(DisasContext *ctx, TCGv ret, TCGv base, + target_long ofs) +{ + tcg_gen_addi_tl(ret, base, ofs); + +#if defined(TARGET_MIPS64) + if (ctx->hflags & MIPS_HFLAG_AWRAP) { + tcg_gen_ext32s_i64(ret, ret); + } +#endif +} + /* Addresses computation (translation time) */ static target_long addr_add(DisasContext *ctx, target_long base, target_long offset) @@ -1902,6 +1916,59 @@ static inline void check_mvh(DisasContext *ctx) } #endif +/* + * This code generates a "reserved instruction" exception if the + * Config5 XNP bit is set. + */ +static inline void check_xnp(DisasContext *ctx) +{ + if (unlikely(ctx->CP0_Config5 & (1 << CP0C5_XNP))) { + generate_exception_end(ctx, EXCP_RI); + } +} + +/* + * This code generates a "reserved instruction" exception if the + * Config3 MT bit is NOT set. + */ +static inline void check_mt(DisasContext *ctx) +{ + if (unlikely(!(ctx->CP0_Config3 & (1 << CP0C3_MT)))) { + generate_exception_end(ctx, EXCP_RI); + } +} + +#ifndef CONFIG_USER_ONLY +/* + * This code generates a "coprocessor unusable" exception if CP0 is not + * available, and, if that is not the case, generates a "reserved instruction" + * exception if the Config5 MT bit is NOT set. This is needed for availability + * control of some of MT ASE instructions. + */ +static inline void check_cp0_mt(DisasContext *ctx) +{ + if (unlikely(!(ctx->hflags & MIPS_HFLAG_CP0))) { + generate_exception_err(ctx, EXCP_CpU, 0); + } else { + if (unlikely(!(ctx->CP0_Config3 & (1 << CP0C3_MT)))) { + generate_exception_err(ctx, EXCP_RI, 0); + } + } +} +#endif + +/* + * This code generates a "reserved instruction" exception if the + * Config5 NMS bit is set. + */ +static inline void check_nms(DisasContext *ctx) +{ + if (unlikely(ctx->CP0_Config5 & (1 << CP0C5_NMS))) { + generate_exception_end(ctx, EXCP_RI); + } +} + + /* Define small wrappers for gen_load_fpr* so that we have a uniform calling interface for 32 and 64-bit FPRs. No sense in changing all callers for gen_load_fpr32 when we need the CTX parameter for @@ -2348,6 +2415,31 @@ static void gen_ld(DisasContext *ctx, uint32_t opc, tcg_temp_free(t0); } +static void gen_llwp(DisasContext *ctx, uint32_t base, int16_t offset, + uint32_t reg1, uint32_t reg2) +{ + TCGv taddr = tcg_temp_new(); + TCGv_i64 tval = tcg_temp_new_i64(); + TCGv tmp1 = tcg_temp_new(); + TCGv tmp2 = tcg_temp_new(); + + gen_base_offset_addr(ctx, taddr, base, offset); + tcg_gen_qemu_ld64(tval, taddr, ctx->mem_idx); +#ifdef TARGET_WORDS_BIGENDIAN + tcg_gen_extr_i64_tl(tmp2, tmp1, tval); +#else + tcg_gen_extr_i64_tl(tmp1, tmp2, tval); +#endif + gen_store_gpr(tmp1, reg1); + tcg_temp_free(tmp1); + gen_store_gpr(tmp2, reg2); + tcg_temp_free(tmp2); + tcg_gen_st_i64(tval, cpu_env, offsetof(CPUMIPSState, llval_wp)); + tcg_temp_free_i64(tval); + tcg_gen_st_tl(taddr, cpu_env, offsetof(CPUMIPSState, lladdr)); + tcg_temp_free(taddr); +} + /* Store */ static void gen_st (DisasContext *ctx, uint32_t opc, int rt, int base, int offset) @@ -2444,6 +2536,51 @@ static void gen_st_cond (DisasContext *ctx, uint32_t opc, int rt, tcg_temp_free(t0); } +static void gen_scwp(DisasContext *ctx, uint32_t base, int16_t offset, + uint32_t reg1, uint32_t reg2) +{ + TCGv taddr = tcg_temp_local_new(); + TCGv lladdr = tcg_temp_local_new(); + TCGv_i64 tval = tcg_temp_new_i64(); + TCGv_i64 llval = tcg_temp_new_i64(); + TCGv_i64 val = tcg_temp_new_i64(); + TCGv tmp1 = tcg_temp_new(); + TCGv tmp2 = tcg_temp_new(); + TCGLabel *lab_fail = gen_new_label(); + TCGLabel *lab_done = gen_new_label(); + + gen_base_offset_addr(ctx, taddr, base, offset); + + tcg_gen_ld_tl(lladdr, cpu_env, offsetof(CPUMIPSState, lladdr)); + tcg_gen_brcond_tl(TCG_COND_NE, taddr, lladdr, lab_fail); + + gen_load_gpr(tmp1, reg1); + gen_load_gpr(tmp2, reg2); + +#ifdef TARGET_WORDS_BIGENDIAN + tcg_gen_concat_tl_i64(tval, tmp2, tmp1); +#else + tcg_gen_concat_tl_i64(tval, tmp1, tmp2); +#endif + + tcg_gen_ld_i64(llval, cpu_env, offsetof(CPUMIPSState, llval_wp)); + tcg_gen_atomic_cmpxchg_i64(val, taddr, llval, tval, + ctx->mem_idx, MO_64); + if (reg1 != 0) { + tcg_gen_movi_tl(cpu_gpr[reg1], 1); + } + tcg_gen_brcond_i64(TCG_COND_EQ, val, llval, lab_done); + + gen_set_label(lab_fail); + + if (reg1 != 0) { + tcg_gen_movi_tl(cpu_gpr[reg1], 0); + } + gen_set_label(lab_done); + tcg_gen_movi_tl(lladdr, -1); + tcg_gen_st_tl(lladdr, cpu_env, offsetof(CPUMIPSState, lladdr)); +} + /* Load and store */ static void gen_flt_ldst (DisasContext *ctx, uint32_t opc, int ft, TCGv t0) @@ -4564,6 +4701,128 @@ static void gen_compute_branch (DisasContext *ctx, uint32_t opc, tcg_temp_free(t1); } + +/* nanoMIPS Branches */ +static void gen_compute_branch_nm(DisasContext *ctx, uint32_t opc, + int insn_bytes, + int rs, int rt, int32_t offset) +{ + target_ulong btgt = -1; + int bcond_compute = 0; + TCGv t0 = tcg_temp_new(); + TCGv t1 = tcg_temp_new(); + + /* Load needed operands */ + switch (opc) { + case OPC_BEQ: + case OPC_BNE: + /* Compare two registers */ + if (rs != rt) { + gen_load_gpr(t0, rs); + gen_load_gpr(t1, rt); + bcond_compute = 1; + } + btgt = ctx->base.pc_next + insn_bytes + offset; + break; + case OPC_BGEZAL: + /* Compare to zero */ + if (rs != 0) { + gen_load_gpr(t0, rs); + bcond_compute = 1; + } + btgt = ctx->base.pc_next + insn_bytes + offset; + break; + case OPC_BPOSGE32: + tcg_gen_andi_tl(t0, cpu_dspctrl, 0x3F); + bcond_compute = 1; + btgt = ctx->base.pc_next + insn_bytes + offset; + break; + case OPC_JR: + case OPC_JALR: + /* Jump to register */ + if (offset != 0 && offset != 16) { + /* Hint = 0 is JR/JALR, hint 16 is JR.HB/JALR.HB, the + others are reserved. */ + MIPS_INVAL("jump hint"); + generate_exception_end(ctx, EXCP_RI); + goto out; + } + gen_load_gpr(btarget, rs); + break; + default: + MIPS_INVAL("branch/jump"); + generate_exception_end(ctx, EXCP_RI); + goto out; + } + if (bcond_compute == 0) { + /* No condition to be computed */ + switch (opc) { + case OPC_BEQ: /* rx == rx */ + /* Always take */ + ctx->hflags |= MIPS_HFLAG_B; + break; + case OPC_BGEZAL: /* 0 >= 0 */ + /* Always take and link */ + tcg_gen_movi_tl(cpu_gpr[31], + ctx->base.pc_next + insn_bytes); + ctx->hflags |= MIPS_HFLAG_B; + break; + case OPC_BNE: /* rx != rx */ + tcg_gen_movi_tl(cpu_gpr[31], ctx->base.pc_next + 8); + /* Skip the instruction in the delay slot */ + ctx->base.pc_next += 4; + goto out; + case OPC_JR: + ctx->hflags |= MIPS_HFLAG_BR; + break; + case OPC_JALR: + if (rt > 0) { + tcg_gen_movi_tl(cpu_gpr[rt], + ctx->base.pc_next + insn_bytes); + } + ctx->hflags |= MIPS_HFLAG_BR; + break; + default: + MIPS_INVAL("branch/jump"); + generate_exception_end(ctx, EXCP_RI); + goto out; + } + } else { + switch (opc) { + case OPC_BEQ: + tcg_gen_setcond_tl(TCG_COND_EQ, bcond, t0, t1); + goto not_likely; + case OPC_BNE: + tcg_gen_setcond_tl(TCG_COND_NE, bcond, t0, t1); + goto not_likely; + case OPC_BGEZAL: + tcg_gen_setcondi_tl(TCG_COND_GE, bcond, t0, 0); + tcg_gen_movi_tl(cpu_gpr[31], + ctx->base.pc_next + insn_bytes); + goto not_likely; + case OPC_BPOSGE32: + tcg_gen_setcondi_tl(TCG_COND_GE, bcond, t0, 32); + not_likely: + ctx->hflags |= MIPS_HFLAG_BC; + break; + default: + MIPS_INVAL("conditional branch/jump"); + generate_exception_end(ctx, EXCP_RI); + goto out; + } + } + + ctx->btarget = btgt; + + out: + if (insn_bytes == 2) { + ctx->hflags |= MIPS_HFLAG_B16; + } + tcg_temp_free(t0); + tcg_temp_free(t1); +} + + /* special3 bitfield operations */ static void gen_bitops (DisasContext *ctx, uint32_t opc, int rt, int rs, int lsb, int msb) @@ -4736,8 +4995,8 @@ static void gen_lsa(DisasContext *ctx, int opc, int rd, int rs, int rt, return; } -static void gen_align(DisasContext *ctx, int opc, int rd, int rs, int rt, - int bp) +static void gen_align_bits(DisasContext *ctx, int wordsz, int rd, int rs, + int rt, int bits) { TCGv t0; if (rd == 0) { @@ -4745,35 +5004,40 @@ static void gen_align(DisasContext *ctx, int opc, int rd, int rs, int rt, return; } t0 = tcg_temp_new(); - gen_load_gpr(t0, rt); - if (bp == 0) { - switch (opc) { - case OPC_ALIGN: + if (bits == 0 || bits == wordsz) { + if (bits == 0) { + gen_load_gpr(t0, rt); + } else { + gen_load_gpr(t0, rs); + } + switch (wordsz) { + case 32: tcg_gen_ext32s_tl(cpu_gpr[rd], t0); break; #if defined(TARGET_MIPS64) - case OPC_DALIGN: + case 64: tcg_gen_mov_tl(cpu_gpr[rd], t0); break; #endif } } else { TCGv t1 = tcg_temp_new(); + gen_load_gpr(t0, rt); gen_load_gpr(t1, rs); - switch (opc) { - case OPC_ALIGN: + switch (wordsz) { + case 32: { TCGv_i64 t2 = tcg_temp_new_i64(); tcg_gen_concat_tl_i64(t2, t1, t0); - tcg_gen_shri_i64(t2, t2, 8 * (4 - bp)); + tcg_gen_shri_i64(t2, t2, 32 - bits); gen_move_low32(cpu_gpr[rd], t2); tcg_temp_free_i64(t2); } break; #if defined(TARGET_MIPS64) - case OPC_DALIGN: - tcg_gen_shli_tl(t0, t0, 8 * bp); - tcg_gen_shri_tl(t1, t1, 8 * (8 - bp)); + case 64: + tcg_gen_shli_tl(t0, t0, bits); + tcg_gen_shri_tl(t1, t1, 64 - bits); tcg_gen_or_tl(cpu_gpr[rd], t1, t0); break; #endif @@ -4784,6 +5048,18 @@ static void gen_align(DisasContext *ctx, int opc, int rd, int rs, int rt, tcg_temp_free(t0); } +static void gen_align(DisasContext *ctx, int wordsz, int rd, int rs, int rt, + int bp) +{ + gen_align_bits(ctx, wordsz, rd, rs, rt, bp * 8); +} + +static void gen_ext(DisasContext *ctx, int wordsz, int rd, int rs, int rt, + int shift) +{ + gen_align_bits(ctx, wordsz, rd, rs, rt, wordsz - shift); +} + static void gen_bitswap(DisasContext *ctx, int opc, int rd, int rt) { TCGv t0; @@ -8360,7 +8636,7 @@ static void gen_cp0 (CPUMIPSState *env, DisasContext *ctx, uint32_t opc, int rt, opn = "mthc0"; break; case OPC_MFTR: - check_insn(ctx, ASE_MT); + check_cp0_enabled(ctx); if (rd == 0) { /* Treat as NOP. */ return; @@ -8370,7 +8646,7 @@ static void gen_cp0 (CPUMIPSState *env, DisasContext *ctx, uint32_t opc, int rt, opn = "mftr"; break; case OPC_MTTR: - check_insn(ctx, ASE_MT); + check_cp0_enabled(ctx); gen_mttr(env, ctx, rd, rt, (ctx->opcode >> 5) & 1, ctx->opcode & 0x7, (ctx->opcode >> 4) & 1); opn = "mttr"; @@ -14276,8 +14552,7 @@ static void decode_micromips32_opc(CPUMIPSState *env, DisasContext *ctx) break; case ALIGN: check_insn(ctx, ISA_MIPS32R6); - gen_align(ctx, OPC_ALIGN, rd, rs, rt, - extract32(ctx->opcode, 9, 2)); + gen_align(ctx, 32, rd, rs, rt, extract32(ctx->opcode, 9, 2)); break; case EXT: gen_bitops(ctx, OPC_EXT, rt, rs, rr, rd); @@ -15701,6 +15976,4569 @@ static int decode_micromips_opc (CPUMIPSState *env, DisasContext *ctx) return 2; } +/* + * + * nanoMIPS opcodes + * + */ + +/* MAJOR, P16, and P32 pools opcodes */ +enum { + NM_P_ADDIU = 0x00, + NM_ADDIUPC = 0x01, + NM_MOVE_BALC = 0x02, + NM_P16_MV = 0x04, + NM_LW16 = 0x05, + NM_BC16 = 0x06, + NM_P16_SR = 0x07, + + NM_POOL32A = 0x08, + NM_P_BAL = 0x0a, + NM_P16_SHIFT = 0x0c, + NM_LWSP16 = 0x0d, + NM_BALC16 = 0x0e, + NM_P16_4X4 = 0x0f, + + NM_P_GP_W = 0x10, + NM_P_GP_BH = 0x11, + NM_P_J = 0x12, + NM_P16C = 0x14, + NM_LWGP16 = 0x15, + NM_P16_LB = 0x17, + + NM_P48I = 0x18, + NM_P16_A1 = 0x1c, + NM_LW4X4 = 0x1d, + NM_P16_LH = 0x1f, + + NM_P_U12 = 0x20, + NM_P_LS_U12 = 0x21, + NM_P_BR1 = 0x22, + NM_P16_A2 = 0x24, + NM_SW16 = 0x25, + NM_BEQZC16 = 0x26, + + NM_POOL32F = 0x28, + NM_P_LS_S9 = 0x29, + NM_P_BR2 = 0x2a, + + NM_P16_ADDU = 0x2c, + NM_SWSP16 = 0x2d, + NM_BNEZC16 = 0x2e, + NM_MOVEP = 0x2f, + + NM_POOL32S = 0x30, + NM_P_BRI = 0x32, + NM_LI16 = 0x34, + NM_SWGP16 = 0x35, + NM_P16_BR = 0x36, + + NM_P_LUI = 0x38, + NM_ANDI16 = 0x3c, + NM_SW4X4 = 0x3d, + NM_MOVEPREV = 0x3f, +}; + +/* POOL32A instruction pool */ +enum { + NM_POOL32A0 = 0x00, + NM_SPECIAL2 = 0x01, + NM_COP2_1 = 0x02, + NM_UDI = 0x03, + NM_POOL32A5 = 0x05, + NM_POOL32A7 = 0x07, +}; + +/* P.GP.W instruction pool */ +enum { + NM_ADDIUGP_W = 0x00, + NM_LWGP = 0x02, + NM_SWGP = 0x03, +}; + +/* P48I instruction pool */ +enum { + NM_LI48 = 0x00, + NM_ADDIU48 = 0x01, + NM_ADDIUGP48 = 0x02, + NM_ADDIUPC48 = 0x03, + NM_LWPC48 = 0x0b, + NM_SWPC48 = 0x0f, +}; + +/* P.U12 instruction pool */ +enum { + NM_ORI = 0x00, + NM_XORI = 0x01, + NM_ANDI = 0x02, + NM_P_SR = 0x03, + NM_SLTI = 0x04, + NM_SLTIU = 0x05, + NM_SEQI = 0x06, + NM_ADDIUNEG = 0x08, + NM_P_SHIFT = 0x0c, + NM_P_ROTX = 0x0d, + NM_P_INS = 0x0e, + NM_P_EXT = 0x0f, +}; + +/* POOL32F instruction pool */ +enum { + NM_POOL32F_0 = 0x00, + NM_POOL32F_3 = 0x03, + NM_POOL32F_5 = 0x05, +}; + +/* POOL32S instruction pool */ +enum { + NM_POOL32S_0 = 0x00, + NM_POOL32S_4 = 0x04, +}; + +/* P.LUI instruction pool */ +enum { + NM_LUI = 0x00, + NM_ALUIPC = 0x01, +}; + +/* P.GP.BH instruction pool */ +enum { + NM_LBGP = 0x00, + NM_SBGP = 0x01, + NM_LBUGP = 0x02, + NM_ADDIUGP_B = 0x03, + NM_P_GP_LH = 0x04, + NM_P_GP_SH = 0x05, + NM_P_GP_CP1 = 0x06, +}; + +/* P.LS.U12 instruction pool */ +enum { + NM_LB = 0x00, + NM_SB = 0x01, + NM_LBU = 0x02, + NM_P_PREFU12 = 0x03, + NM_LH = 0x04, + NM_SH = 0x05, + NM_LHU = 0x06, + NM_LWU = 0x07, + NM_LW = 0x08, + NM_SW = 0x09, + NM_LWC1 = 0x0a, + NM_SWC1 = 0x0b, + NM_LDC1 = 0x0e, + NM_SDC1 = 0x0f, +}; + +/* P.LS.S9 instruction pool */ +enum { + NM_P_LS_S0 = 0x00, + NM_P_LS_S1 = 0x01, + NM_P_LS_E0 = 0x02, + NM_P_LS_WM = 0x04, + NM_P_LS_UAWM = 0x05, +}; + +/* P.BAL instruction pool */ +enum { + NM_BC = 0x00, + NM_BALC = 0x01, +}; + +/* P.J instruction pool */ +enum { + NM_JALRC = 0x00, + NM_JALRC_HB = 0x01, + NM_P_BALRSC = 0x08, +}; + +/* P.BR1 instruction pool */ +enum { + NM_BEQC = 0x00, + NM_P_BR3A = 0x01, + NM_BGEC = 0x02, + NM_BGEUC = 0x03, +}; + +/* P.BR2 instruction pool */ +enum { + NM_BNEC = 0x00, + NM_BLTC = 0x02, + NM_BLTUC = 0x03, +}; + +/* P.BRI instruction pool */ +enum { + NM_BEQIC = 0x00, + NM_BBEQZC = 0x01, + NM_BGEIC = 0x02, + NM_BGEIUC = 0x03, + NM_BNEIC = 0x04, + NM_BBNEZC = 0x05, + NM_BLTIC = 0x06, + NM_BLTIUC = 0x07, +}; + +/* P16.SHIFT instruction pool */ +enum { + NM_SLL16 = 0x00, + NM_SRL16 = 0x01, +}; + +/* POOL16C instruction pool */ +enum { + NM_POOL16C_0 = 0x00, + NM_LWXS16 = 0x01, +}; + +/* P16.A1 instruction pool */ +enum { + NM_ADDIUR1SP = 0x01, +}; + +/* P16.A2 instruction pool */ +enum { + NM_ADDIUR2 = 0x00, + NM_P_ADDIURS5 = 0x01, +}; + +/* P16.ADDU instruction pool */ +enum { + NM_ADDU16 = 0x00, + NM_SUBU16 = 0x01, +}; + +/* P16.SR instruction pool */ +enum { + NM_SAVE16 = 0x00, + NM_RESTORE_JRC16 = 0x01, +}; + +/* P16.4X4 instruction pool */ +enum { + NM_ADDU4X4 = 0x00, + NM_MUL4X4 = 0x01, +}; + +/* P16.LB instruction pool */ +enum { + NM_LB16 = 0x00, + NM_SB16 = 0x01, + NM_LBU16 = 0x02, +}; + +/* P16.LH instruction pool */ +enum { + NM_LH16 = 0x00, + NM_SH16 = 0x01, + NM_LHU16 = 0x02, +}; + +/* P.RI instruction pool */ +enum { + NM_SIGRIE = 0x00, + NM_P_SYSCALL = 0x01, + NM_BREAK = 0x02, + NM_SDBBP = 0x03, +}; + +/* POOL32A0 instruction pool */ +enum { + NM_P_TRAP = 0x00, + NM_SEB = 0x01, + NM_SLLV = 0x02, + NM_MUL = 0x03, + NM_MFC0 = 0x06, + NM_MFHC0 = 0x07, + NM_SEH = 0x09, + NM_SRLV = 0x0a, + NM_MUH = 0x0b, + NM_MTC0 = 0x0e, + NM_MTHC0 = 0x0f, + NM_SRAV = 0x12, + NM_MULU = 0x13, + NM_ROTRV = 0x1a, + NM_MUHU = 0x1b, + NM_ADD = 0x22, + NM_DIV = 0x23, + NM_ADDU = 0x2a, + NM_MOD = 0x2b, + NM_SUB = 0x32, + NM_DIVU = 0x33, + NM_RDHWR = 0x38, + NM_SUBU = 0x3a, + NM_MODU = 0x3b, + NM_P_CMOVE = 0x42, + NM_FORK = 0x45, + NM_MFTR = 0x46, + NM_MFHTR = 0x47, + NM_AND = 0x4a, + NM_YIELD = 0x4d, + NM_MTTR = 0x4e, + NM_MTHTR = 0x4f, + NM_OR = 0x52, + NM_D_E_MT_VPE = 0x56, + NM_NOR = 0x5a, + NM_XOR = 0x62, + NM_SLT = 0x6a, + NM_P_SLTU = 0x72, + NM_SOV = 0x7a, +}; + +/* POOL32A5 instruction pool */ +enum { + NM_CMP_EQ_PH = 0x00, + NM_CMP_LT_PH = 0x08, + NM_CMP_LE_PH = 0x10, + NM_CMPGU_EQ_QB = 0x18, + NM_CMPGU_LT_QB = 0x20, + NM_CMPGU_LE_QB = 0x28, + NM_CMPGDU_EQ_QB = 0x30, + NM_CMPGDU_LT_QB = 0x38, + NM_CMPGDU_LE_QB = 0x40, + NM_CMPU_EQ_QB = 0x48, + NM_CMPU_LT_QB = 0x50, + NM_CMPU_LE_QB = 0x58, + NM_ADDQ_S_W = 0x60, + NM_SUBQ_S_W = 0x68, + NM_ADDSC = 0x70, + NM_ADDWC = 0x78, + + NM_ADDQ_S_PH = 0x01, + NM_ADDQH_R_PH = 0x09, + NM_ADDQH_R_W = 0x11, + NM_ADDU_S_QB = 0x19, + NM_ADDU_S_PH = 0x21, + NM_ADDUH_R_QB = 0x29, + NM_SHRAV_R_PH = 0x31, + NM_SHRAV_R_QB = 0x39, + NM_SUBQ_S_PH = 0x41, + NM_SUBQH_R_PH = 0x49, + NM_SUBQH_R_W = 0x51, + NM_SUBU_S_QB = 0x59, + NM_SUBU_S_PH = 0x61, + NM_SUBUH_R_QB = 0x69, + NM_SHLLV_S_PH = 0x71, + NM_PRECR_SRA_R_PH_W = 0x79, + + NM_MULEU_S_PH_QBL = 0x12, + NM_MULEU_S_PH_QBR = 0x1a, + NM_MULQ_RS_PH = 0x22, + NM_MULQ_S_PH = 0x2a, + NM_MULQ_RS_W = 0x32, + NM_MULQ_S_W = 0x3a, + NM_APPEND = 0x42, + NM_MODSUB = 0x52, + NM_SHRAV_R_W = 0x5a, + NM_SHRLV_PH = 0x62, + NM_SHRLV_QB = 0x6a, + NM_SHLLV_QB = 0x72, + NM_SHLLV_S_W = 0x7a, + + NM_SHILO = 0x03, + + NM_MULEQ_S_W_PHL = 0x04, + NM_MULEQ_S_W_PHR = 0x0c, + + NM_MUL_S_PH = 0x05, + NM_PRECR_QB_PH = 0x0d, + NM_PRECRQ_QB_PH = 0x15, + NM_PRECRQ_PH_W = 0x1d, + NM_PRECRQ_RS_PH_W = 0x25, + NM_PRECRQU_S_QB_PH = 0x2d, + NM_PACKRL_PH = 0x35, + NM_PICK_QB = 0x3d, + NM_PICK_PH = 0x45, + + NM_SHRA_R_W = 0x5e, + NM_SHRA_R_PH = 0x66, + NM_SHLL_S_PH = 0x76, + NM_SHLL_S_W = 0x7e, + + NM_REPL_PH = 0x07 +}; + +/* POOL32A7 instruction pool */ +enum { + NM_P_LSX = 0x00, + NM_LSA = 0x01, + NM_EXTW = 0x03, + NM_POOL32AXF = 0x07, +}; + +/* P.SR instruction pool */ +enum { + NM_PP_SR = 0x00, + NM_P_SR_F = 0x01, +}; + +/* P.SHIFT instruction pool */ +enum { + NM_P_SLL = 0x00, + NM_SRL = 0x02, + NM_SRA = 0x04, + NM_ROTR = 0x06, +}; + +/* P.ROTX instruction pool */ +enum { + NM_ROTX = 0x00, +}; + +/* P.INS instruction pool */ +enum { + NM_INS = 0x00, +}; + +/* P.EXT instruction pool */ +enum { + NM_EXT = 0x00, +}; + +/* POOL32F_0 (fmt) instruction pool */ +enum { + NM_RINT_S = 0x04, + NM_RINT_D = 0x44, + NM_ADD_S = 0x06, + NM_SELEQZ_S = 0x07, + NM_SELEQZ_D = 0x47, + NM_CLASS_S = 0x0c, + NM_CLASS_D = 0x4c, + NM_SUB_S = 0x0e, + NM_SELNEZ_S = 0x0f, + NM_SELNEZ_D = 0x4f, + NM_MUL_S = 0x16, + NM_SEL_S = 0x17, + NM_SEL_D = 0x57, + NM_DIV_S = 0x1e, + NM_ADD_D = 0x26, + NM_SUB_D = 0x2e, + NM_MUL_D = 0x36, + NM_MADDF_S = 0x37, + NM_MADDF_D = 0x77, + NM_DIV_D = 0x3e, + NM_MSUBF_S = 0x3f, + NM_MSUBF_D = 0x7f, +}; + +/* POOL32F_3 instruction pool */ +enum { + NM_MIN_FMT = 0x00, + NM_MAX_FMT = 0x01, + NM_MINA_FMT = 0x04, + NM_MAXA_FMT = 0x05, + NM_POOL32FXF = 0x07, +}; + +/* POOL32F_5 instruction pool */ +enum { + NM_CMP_CONDN_S = 0x00, + NM_CMP_CONDN_D = 0x02, +}; + +/* P.GP.LH instruction pool */ +enum { + NM_LHGP = 0x00, + NM_LHUGP = 0x01, +}; + +/* P.GP.SH instruction pool */ +enum { + NM_SHGP = 0x00, +}; + +/* P.GP.CP1 instruction pool */ +enum { + NM_LWC1GP = 0x00, + NM_SWC1GP = 0x01, + NM_LDC1GP = 0x02, + NM_SDC1GP = 0x03, +}; + +/* P.LS.S0 instruction pool */ +enum { + NM_LBS9 = 0x00, + NM_LHS9 = 0x04, + NM_LWS9 = 0x08, + NM_LDS9 = 0x0c, + + NM_SBS9 = 0x01, + NM_SHS9 = 0x05, + NM_SWS9 = 0x09, + NM_SDS9 = 0x0d, + + NM_LBUS9 = 0x02, + NM_LHUS9 = 0x06, + NM_LWC1S9 = 0x0a, + NM_LDC1S9 = 0x0e, + + NM_P_PREFS9 = 0x03, + NM_LWUS9 = 0x07, + NM_SWC1S9 = 0x0b, + NM_SDC1S9 = 0x0f, +}; + +/* P.LS.S1 instruction pool */ +enum { + NM_ASET_ACLR = 0x02, + NM_UALH = 0x04, + NM_UASH = 0x05, + NM_CACHE = 0x07, + NM_P_LL = 0x0a, + NM_P_SC = 0x0b, +}; + +/* P.LS.WM instruction pool */ +enum { + NM_LWM = 0x00, + NM_SWM = 0x01, +}; + +/* P.LS.UAWM instruction pool */ +enum { + NM_UALWM = 0x00, + NM_UASWM = 0x01, +}; + +/* P.BR3A instruction pool */ +enum { + NM_BC1EQZC = 0x00, + NM_BC1NEZC = 0x01, + NM_BC2EQZC = 0x02, + NM_BC2NEZC = 0x03, + NM_BPOSGE32C = 0x04, +}; + +/* P16.RI instruction pool */ +enum { + NM_P16_SYSCALL = 0x01, + NM_BREAK16 = 0x02, + NM_SDBBP16 = 0x03, +}; + +/* POOL16C_0 instruction pool */ +enum { + NM_POOL16C_00 = 0x00, +}; + +/* P16.JRC instruction pool */ +enum { + NM_JRC = 0x00, + NM_JALRC16 = 0x01, +}; + +/* P.SYSCALL instruction pool */ +enum { + NM_SYSCALL = 0x00, + NM_HYPCALL = 0x01, +}; + +/* P.TRAP instruction pool */ +enum { + NM_TEQ = 0x00, + NM_TNE = 0x01, +}; + +/* P.CMOVE instruction pool */ +enum { + NM_MOVZ = 0x00, + NM_MOVN = 0x01, +}; + +/* POOL32Axf instruction pool */ +enum { + NM_POOL32AXF_1 = 0x01, + NM_POOL32AXF_2 = 0x02, + NM_POOL32AXF_4 = 0x04, + NM_POOL32AXF_5 = 0x05, + NM_POOL32AXF_7 = 0x07, +}; + +/* POOL32Axf_1 instruction pool */ +enum { + NM_POOL32AXF_1_0 = 0x00, + NM_POOL32AXF_1_1 = 0x01, + NM_POOL32AXF_1_3 = 0x03, + NM_POOL32AXF_1_4 = 0x04, + NM_POOL32AXF_1_5 = 0x05, + NM_POOL32AXF_1_7 = 0x07, +}; + +/* POOL32Axf_2 instruction pool */ +enum { + NM_POOL32AXF_2_0_7 = 0x00, + NM_POOL32AXF_2_8_15 = 0x01, + NM_POOL32AXF_2_16_23 = 0x02, + NM_POOL32AXF_2_24_31 = 0x03, +}; + +/* POOL32Axf_7 instruction pool */ +enum { + NM_SHRA_R_QB = 0x0, + NM_SHRL_PH = 0x1, + NM_REPL_QB = 0x2, +}; + +/* POOL32Axf_1_0 instruction pool */ +enum { + NM_MFHI = 0x0, + NM_MFLO = 0x1, + NM_MTHI = 0x2, + NM_MTLO = 0x3, +}; + +/* POOL32Axf_1_1 instruction pool */ +enum { + NM_MTHLIP = 0x0, + NM_SHILOV = 0x1, +}; + +/* POOL32Axf_1_3 instruction pool */ +enum { + NM_RDDSP = 0x0, + NM_WRDSP = 0x1, + NM_EXTP = 0x2, + NM_EXTPDP = 0x3, +}; + +/* POOL32Axf_1_4 instruction pool */ +enum { + NM_SHLL_QB = 0x0, + NM_SHRL_QB = 0x1, +}; + +/* POOL32Axf_1_5 instruction pool */ +enum { + NM_MAQ_S_W_PHR = 0x0, + NM_MAQ_S_W_PHL = 0x1, + NM_MAQ_SA_W_PHR = 0x2, + NM_MAQ_SA_W_PHL = 0x3, +}; + +/* POOL32Axf_1_7 instruction pool */ +enum { + NM_EXTR_W = 0x0, + NM_EXTR_R_W = 0x1, + NM_EXTR_RS_W = 0x2, + NM_EXTR_S_H = 0x3, +}; + +/* POOL32Axf_2_0_7 instruction pool */ +enum { + NM_DPA_W_PH = 0x0, + NM_DPAQ_S_W_PH = 0x1, + NM_DPS_W_PH = 0x2, + NM_DPSQ_S_W_PH = 0x3, + NM_BALIGN = 0x4, + NM_MADD = 0x5, + NM_MULT = 0x6, + NM_EXTRV_W = 0x7, +}; + +/* POOL32Axf_2_8_15 instruction pool */ +enum { + NM_DPAX_W_PH = 0x0, + NM_DPAQ_SA_L_W = 0x1, + NM_DPSX_W_PH = 0x2, + NM_DPSQ_SA_L_W = 0x3, + NM_MADDU = 0x5, + NM_MULTU = 0x6, + NM_EXTRV_R_W = 0x7, +}; + +/* POOL32Axf_2_16_23 instruction pool */ +enum { + NM_DPAU_H_QBL = 0x0, + NM_DPAQX_S_W_PH = 0x1, + NM_DPSU_H_QBL = 0x2, + NM_DPSQX_S_W_PH = 0x3, + NM_EXTPV = 0x4, + NM_MSUB = 0x5, + NM_MULSA_W_PH = 0x6, + NM_EXTRV_RS_W = 0x7, +}; + +/* POOL32Axf_2_24_31 instruction pool */ +enum { + NM_DPAU_H_QBR = 0x0, + NM_DPAQX_SA_W_PH = 0x1, + NM_DPSU_H_QBR = 0x2, + NM_DPSQX_SA_W_PH = 0x3, + NM_EXTPDPV = 0x4, + NM_MSUBU = 0x5, + NM_MULSAQ_S_W_PH = 0x6, + NM_EXTRV_S_H = 0x7, +}; + +/* POOL32Axf_{4, 5} instruction pool */ +enum { + NM_CLO = 0x25, + NM_CLZ = 0x2d, + + NM_TLBP = 0x01, + NM_TLBR = 0x09, + NM_TLBWI = 0x11, + NM_TLBWR = 0x19, + NM_TLBINV = 0x03, + NM_TLBINVF = 0x0b, + NM_DI = 0x23, + NM_EI = 0x2b, + NM_RDPGPR = 0x70, + NM_WRPGPR = 0x78, + NM_WAIT = 0x61, + NM_DERET = 0x71, + NM_ERETX = 0x79, + + /* nanoMIPS DSP instructions */ + NM_ABSQ_S_QB = 0x00, + NM_ABSQ_S_PH = 0x08, + NM_ABSQ_S_W = 0x10, + NM_PRECEQ_W_PHL = 0x28, + NM_PRECEQ_W_PHR = 0x30, + NM_PRECEQU_PH_QBL = 0x38, + NM_PRECEQU_PH_QBR = 0x48, + NM_PRECEU_PH_QBL = 0x58, + NM_PRECEU_PH_QBR = 0x68, + NM_PRECEQU_PH_QBLA = 0x39, + NM_PRECEQU_PH_QBRA = 0x49, + NM_PRECEU_PH_QBLA = 0x59, + NM_PRECEU_PH_QBRA = 0x69, + NM_REPLV_PH = 0x01, + NM_REPLV_QB = 0x09, + NM_BITREV = 0x18, + NM_INSV = 0x20, + NM_RADDU_W_QB = 0x78, + + NM_BITSWAP = 0x05, + NM_WSBH = 0x3d, +}; + +/* PP.SR instruction pool */ +enum { + NM_SAVE = 0x00, + NM_RESTORE = 0x02, + NM_RESTORE_JRC = 0x03, +}; + +/* P.SR.F instruction pool */ +enum { + NM_SAVEF = 0x00, + NM_RESTOREF = 0x01, +}; + +/* P16.SYSCALL instruction pool */ +enum { + NM_SYSCALL16 = 0x00, + NM_HYPCALL16 = 0x01, +}; + +/* POOL16C_00 instruction pool */ +enum { + NM_NOT16 = 0x00, + NM_XOR16 = 0x01, + NM_AND16 = 0x02, + NM_OR16 = 0x03, +}; + +/* PP.LSX and PP.LSXS instruction pool */ +enum { + NM_LBX = 0x00, + NM_LHX = 0x04, + NM_LWX = 0x08, + NM_LDX = 0x0c, + + NM_SBX = 0x01, + NM_SHX = 0x05, + NM_SWX = 0x09, + NM_SDX = 0x0d, + + NM_LBUX = 0x02, + NM_LHUX = 0x06, + NM_LWC1X = 0x0a, + NM_LDC1X = 0x0e, + + NM_LWUX = 0x07, + NM_SWC1X = 0x0b, + NM_SDC1X = 0x0f, + + NM_LHXS = 0x04, + NM_LWXS = 0x08, + NM_LDXS = 0x0c, + + NM_SHXS = 0x05, + NM_SWXS = 0x09, + NM_SDXS = 0x0d, + + NM_LHUXS = 0x06, + NM_LWC1XS = 0x0a, + NM_LDC1XS = 0x0e, + + NM_LWUXS = 0x07, + NM_SWC1XS = 0x0b, + NM_SDC1XS = 0x0f, +}; + +/* ERETx instruction pool */ +enum { + NM_ERET = 0x00, + NM_ERETNC = 0x01, +}; + +/* POOL32FxF_{0, 1} insturction pool */ +enum { + NM_CFC1 = 0x40, + NM_CTC1 = 0x60, + NM_MFC1 = 0x80, + NM_MTC1 = 0xa0, + NM_MFHC1 = 0xc0, + NM_MTHC1 = 0xe0, + + NM_CVT_S_PL = 0x84, + NM_CVT_S_PU = 0xa4, + + NM_CVT_L_S = 0x004, + NM_CVT_L_D = 0x104, + NM_CVT_W_S = 0x024, + NM_CVT_W_D = 0x124, + + NM_RSQRT_S = 0x008, + NM_RSQRT_D = 0x108, + + NM_SQRT_S = 0x028, + NM_SQRT_D = 0x128, + + NM_RECIP_S = 0x048, + NM_RECIP_D = 0x148, + + NM_FLOOR_L_S = 0x00c, + NM_FLOOR_L_D = 0x10c, + + NM_FLOOR_W_S = 0x02c, + NM_FLOOR_W_D = 0x12c, + + NM_CEIL_L_S = 0x04c, + NM_CEIL_L_D = 0x14c, + NM_CEIL_W_S = 0x06c, + NM_CEIL_W_D = 0x16c, + NM_TRUNC_L_S = 0x08c, + NM_TRUNC_L_D = 0x18c, + NM_TRUNC_W_S = 0x0ac, + NM_TRUNC_W_D = 0x1ac, + NM_ROUND_L_S = 0x0cc, + NM_ROUND_L_D = 0x1cc, + NM_ROUND_W_S = 0x0ec, + NM_ROUND_W_D = 0x1ec, + + NM_MOV_S = 0x01, + NM_MOV_D = 0x81, + NM_ABS_S = 0x0d, + NM_ABS_D = 0x8d, + NM_NEG_S = 0x2d, + NM_NEG_D = 0xad, + NM_CVT_D_S = 0x04d, + NM_CVT_D_W = 0x0cd, + NM_CVT_D_L = 0x14d, + NM_CVT_S_D = 0x06d, + NM_CVT_S_W = 0x0ed, + NM_CVT_S_L = 0x16d, +}; + +/* P.LL instruction pool */ +enum { + NM_LL = 0x00, + NM_LLWP = 0x01, +}; + +/* P.SC instruction pool */ +enum { + NM_SC = 0x00, + NM_SCWP = 0x01, +}; + +/* P.DVP instruction pool */ +enum { + NM_DVP = 0x00, + NM_EVP = 0x01, +}; + + +/* + * + * nanoMIPS decoding engine + * + */ + + +/* extraction utilities */ + +#define NANOMIPS_EXTRACT_RD(op) ((op >> 7) & 0x7) +#define NANOMIPS_EXTRACT_RS(op) ((op >> 4) & 0x7) +#define NANOMIPS_EXTRACT_RS2(op) uMIPS_RS(op) +#define NANOMIPS_EXTRACT_RS1(op) ((op >> 1) & 0x7) +#define NANOMIPS_EXTRACT_RD5(op) ((op >> 5) & 0x1f) +#define NANOMIPS_EXTRACT_RS5(op) (op & 0x1f) + +/* Implement nanoMIPS pseudocode decode_gpr(encoded_gpr, 'gpr3'). */ +static inline int decode_gpr_gpr3(int r) +{ + static const int map[] = { 16, 17, 18, 19, 4, 5, 6, 7 }; + + return map[r & 0x7]; +} + +/* Implement nanoMIPS pseudocode decode_gpr(encoded_gpr, 'gpr3.src.store'). */ +static inline int decode_gpr_gpr3_src_store(int r) +{ + static const int map[] = { 0, 17, 18, 19, 4, 5, 6, 7 }; + + return map[r & 0x7]; +} + +/* Implement nanoMIPS pseudocode decode_gpr(encoded_gpr, 'gpr4'). */ +static inline int decode_gpr_gpr4(int r) +{ + static const int map[] = { 8, 9, 10, 11, 4, 5, 6, 7, + 16, 17, 18, 19, 20, 21, 22, 23 }; + + return map[r & 0xf]; +} + +/* Implement nanoMIPS pseudocode decode_gpr(encoded_gpr, 'gpr4.zero'). */ +static inline int decode_gpr_gpr4_zero(int r) +{ + static const int map[] = { 8, 9, 10, 0, 4, 5, 6, 7, + 16, 17, 18, 19, 20, 21, 22, 23 }; + + return map[r & 0xf]; +} + + +/* extraction utilities */ + +#define NANOMIPS_EXTRACT_RD(op) ((op >> 7) & 0x7) +#define NANOMIPS_EXTRACT_RS(op) ((op >> 4) & 0x7) +#define NANOMIPS_EXTRACT_RS2(op) uMIPS_RS(op) +#define NANOMIPS_EXTRACT_RS1(op) ((op >> 1) & 0x7) +#define NANOMIPS_EXTRACT_RD5(op) ((op >> 5) & 0x1f) +#define NANOMIPS_EXTRACT_RS5(op) (op & 0x1f) + + +static void gen_adjust_sp(DisasContext *ctx, int u) +{ + gen_op_addr_addi(ctx, cpu_gpr[29], cpu_gpr[29], u); +} + +static void gen_save(DisasContext *ctx, uint8_t rt, uint8_t count, + uint8_t gp, uint16_t u) +{ + int counter = 0; + TCGv va = tcg_temp_new(); + TCGv t0 = tcg_temp_new(); + + while (counter != count) { + bool use_gp = gp && (counter == count - 1); + int this_rt = use_gp ? 28 : (rt & 0x10) | ((rt + counter) & 0x1f); + int this_offset = -((counter + 1) << 2); + gen_base_offset_addr(ctx, va, 29, this_offset); + gen_load_gpr(t0, this_rt); + tcg_gen_qemu_st_tl(t0, va, ctx->mem_idx, + (MO_TEUL | ctx->default_tcg_memop_mask)); + counter++; + } + + /* adjust stack pointer */ + gen_adjust_sp(ctx, -u); + + tcg_temp_free(t0); + tcg_temp_free(va); +} + +static void gen_restore(DisasContext *ctx, uint8_t rt, uint8_t count, + uint8_t gp, uint16_t u) +{ + int counter = 0; + TCGv va = tcg_temp_new(); + TCGv t0 = tcg_temp_new(); + + while (counter != count) { + bool use_gp = gp && (counter == count - 1); + int this_rt = use_gp ? 28 : (rt & 0x10) | ((rt + counter) & 0x1f); + int this_offset = u - ((counter + 1) << 2); + gen_base_offset_addr(ctx, va, 29, this_offset); + tcg_gen_qemu_ld_tl(t0, va, ctx->mem_idx, MO_TESL | + ctx->default_tcg_memop_mask); + tcg_gen_ext32s_tl(t0, t0); + gen_store_gpr(t0, this_rt); + counter++; + } + + /* adjust stack pointer */ + gen_adjust_sp(ctx, u); + + tcg_temp_free(t0); + tcg_temp_free(va); +} + +static void gen_pool16c_nanomips_insn(DisasContext *ctx) +{ + int rt = decode_gpr_gpr3(NANOMIPS_EXTRACT_RD(ctx->opcode)); + int rs = decode_gpr_gpr3(NANOMIPS_EXTRACT_RS(ctx->opcode)); + + switch (extract32(ctx->opcode, 2, 2)) { + case NM_NOT16: + gen_logic(ctx, OPC_NOR, rt, rs, 0); + break; + case NM_AND16: + gen_logic(ctx, OPC_AND, rt, rt, rs); + break; + case NM_XOR16: + gen_logic(ctx, OPC_XOR, rt, rt, rs); + break; + case NM_OR16: + gen_logic(ctx, OPC_OR, rt, rt, rs); + break; + } +} + +static void gen_pool32a0_nanomips_insn(CPUMIPSState *env, DisasContext *ctx) +{ + int rt = extract32(ctx->opcode, 21, 5); + int rs = extract32(ctx->opcode, 16, 5); + int rd = extract32(ctx->opcode, 11, 5); + + switch (extract32(ctx->opcode, 3, 7)) { + case NM_P_TRAP: + switch (extract32(ctx->opcode, 10, 1)) { + case NM_TEQ: + check_nms(ctx); + gen_trap(ctx, OPC_TEQ, rs, rt, -1); + break; + case NM_TNE: + check_nms(ctx); + gen_trap(ctx, OPC_TNE, rs, rt, -1); + break; + } + break; + case NM_RDHWR: + check_nms(ctx); + gen_rdhwr(ctx, rt, rs, extract32(ctx->opcode, 11, 3)); + break; + case NM_SEB: + check_nms(ctx); + gen_bshfl(ctx, OPC_SEB, rs, rt); + break; + case NM_SEH: + gen_bshfl(ctx, OPC_SEH, rs, rt); + break; + case NM_SLLV: + gen_shift(ctx, OPC_SLLV, rd, rt, rs); + break; + case NM_SRLV: + gen_shift(ctx, OPC_SRLV, rd, rt, rs); + break; + case NM_SRAV: + gen_shift(ctx, OPC_SRAV, rd, rt, rs); + break; + case NM_ROTRV: + gen_shift(ctx, OPC_ROTRV, rd, rt, rs); + break; + case NM_ADD: + gen_arith(ctx, OPC_ADD, rd, rs, rt); + break; + case NM_ADDU: + gen_arith(ctx, OPC_ADDU, rd, rs, rt); + break; + case NM_SUB: + check_nms(ctx); + gen_arith(ctx, OPC_SUB, rd, rs, rt); + break; + case NM_SUBU: + gen_arith(ctx, OPC_SUBU, rd, rs, rt); + break; + case NM_P_CMOVE: + switch (extract32(ctx->opcode, 10, 1)) { + case NM_MOVZ: + gen_cond_move(ctx, OPC_MOVZ, rd, rs, rt); + break; + case NM_MOVN: + gen_cond_move(ctx, OPC_MOVN, rd, rs, rt); + break; + } + break; + case NM_AND: + gen_logic(ctx, OPC_AND, rd, rs, rt); + break; + case NM_OR: + gen_logic(ctx, OPC_OR, rd, rs, rt); + break; + case NM_NOR: + gen_logic(ctx, OPC_NOR, rd, rs, rt); + break; + case NM_XOR: + gen_logic(ctx, OPC_XOR, rd, rs, rt); + break; + case NM_SLT: + gen_slt(ctx, OPC_SLT, rd, rs, rt); + break; + case NM_P_SLTU: + if (rd == 0) { + /* P_DVP */ +#ifndef CONFIG_USER_ONLY + TCGv t0 = tcg_temp_new(); + switch (extract32(ctx->opcode, 10, 1)) { + case NM_DVP: + if (ctx->vp) { + check_cp0_enabled(ctx); + gen_helper_dvp(t0, cpu_env); + gen_store_gpr(t0, rt); + } + break; + case NM_EVP: + if (ctx->vp) { + check_cp0_enabled(ctx); + gen_helper_evp(t0, cpu_env); + gen_store_gpr(t0, rt); + } + break; + } + tcg_temp_free(t0); +#endif + } else { + gen_slt(ctx, OPC_SLTU, rd, rs, rt); + } + break; + case NM_SOV: + { + TCGv t0 = tcg_temp_new(); + TCGv t1 = tcg_temp_new(); + TCGv t2 = tcg_temp_new(); + + gen_load_gpr(t1, rs); + gen_load_gpr(t2, rt); + tcg_gen_add_tl(t0, t1, t2); + tcg_gen_ext32s_tl(t0, t0); + tcg_gen_xor_tl(t1, t1, t2); + tcg_gen_xor_tl(t2, t0, t2); + tcg_gen_andc_tl(t1, t2, t1); + + /* operands of same sign, result different sign */ + tcg_gen_setcondi_tl(TCG_COND_LT, t0, t1, 0); + gen_store_gpr(t0, rd); + + tcg_temp_free(t0); + tcg_temp_free(t1); + tcg_temp_free(t2); + } + break; + case NM_MUL: + gen_r6_muldiv(ctx, R6_OPC_MUL, rd, rs, rt); + break; + case NM_MUH: + gen_r6_muldiv(ctx, R6_OPC_MUH, rd, rs, rt); + break; + case NM_MULU: + gen_r6_muldiv(ctx, R6_OPC_MULU, rd, rs, rt); + break; + case NM_MUHU: + gen_r6_muldiv(ctx, R6_OPC_MUHU, rd, rs, rt); + break; + case NM_DIV: + gen_r6_muldiv(ctx, R6_OPC_DIV, rd, rs, rt); + break; + case NM_MOD: + gen_r6_muldiv(ctx, R6_OPC_MOD, rd, rs, rt); + break; + case NM_DIVU: + gen_r6_muldiv(ctx, R6_OPC_DIVU, rd, rs, rt); + break; + case NM_MODU: + gen_r6_muldiv(ctx, R6_OPC_MODU, rd, rs, rt); + break; +#ifndef CONFIG_USER_ONLY + case NM_MFC0: + check_cp0_enabled(ctx); + if (rt == 0) { + /* Treat as NOP. */ + break; + } + gen_mfc0(ctx, cpu_gpr[rt], rs, extract32(ctx->opcode, 11, 3)); + break; + case NM_MTC0: + check_cp0_enabled(ctx); + { + TCGv t0 = tcg_temp_new(); + + gen_load_gpr(t0, rt); + gen_mtc0(ctx, t0, rs, extract32(ctx->opcode, 11, 3)); + tcg_temp_free(t0); + } + break; + case NM_D_E_MT_VPE: + { + uint8_t sc = extract32(ctx->opcode, 10, 1); + TCGv t0 = tcg_temp_new(); + + switch (sc) { + case 0: + if (rs == 1) { + /* DMT */ + check_cp0_mt(ctx); + gen_helper_dmt(t0); + gen_store_gpr(t0, rt); + } else if (rs == 0) { + /* DVPE */ + check_cp0_mt(ctx); + gen_helper_dvpe(t0, cpu_env); + gen_store_gpr(t0, rt); + } else { + generate_exception_end(ctx, EXCP_RI); + } + break; + case 1: + if (rs == 1) { + /* EMT */ + check_cp0_mt(ctx); + gen_helper_emt(t0); + gen_store_gpr(t0, rt); + } else if (rs == 0) { + /* EVPE */ + check_cp0_mt(ctx); + gen_helper_evpe(t0, cpu_env); + gen_store_gpr(t0, rt); + } else { + generate_exception_end(ctx, EXCP_RI); + } + break; + } + + tcg_temp_free(t0); + } + break; + case NM_FORK: + check_mt(ctx); + { + TCGv t0 = tcg_temp_new(); + TCGv t1 = tcg_temp_new(); + + gen_load_gpr(t0, rt); + gen_load_gpr(t1, rs); + gen_helper_fork(t0, t1); + tcg_temp_free(t0); + tcg_temp_free(t1); + } + break; + case NM_MFTR: + case NM_MFHTR: + check_cp0_enabled(ctx); + if (rd == 0) { + /* Treat as NOP. */ + return; + } + gen_mftr(env, ctx, rs, rt, extract32(ctx->opcode, 10, 1), + extract32(ctx->opcode, 11, 5), extract32(ctx->opcode, 3, 1)); + break; + case NM_MTTR: + case NM_MTHTR: + check_cp0_enabled(ctx); + gen_mttr(env, ctx, rs, rt, extract32(ctx->opcode, 10, 1), + extract32(ctx->opcode, 11, 5), extract32(ctx->opcode, 3, 1)); + break; + case NM_YIELD: + check_mt(ctx); + { + TCGv t0 = tcg_temp_new(); + + gen_load_gpr(t0, rs); + gen_helper_yield(t0, cpu_env, t0); + gen_store_gpr(t0, rt); + tcg_temp_free(t0); + } + break; +#endif + default: + generate_exception_end(ctx, EXCP_RI); + break; + } +} + +/* dsp */ +static void gen_pool32axf_1_5_nanomips_insn(DisasContext *ctx, uint32_t opc, + int ret, int v1, int v2) +{ + TCGv_i32 t0; + TCGv v0_t; + TCGv v1_t; + + t0 = tcg_temp_new_i32(); + + v0_t = tcg_temp_new(); + v1_t = tcg_temp_new(); + + tcg_gen_movi_i32(t0, v2 >> 3); + + gen_load_gpr(v0_t, ret); + gen_load_gpr(v1_t, v1); + + switch (opc) { + case NM_MAQ_S_W_PHR: + check_dsp(ctx); + gen_helper_maq_s_w_phr(t0, v1_t, v0_t, cpu_env); + break; + case NM_MAQ_S_W_PHL: + check_dsp(ctx); + gen_helper_maq_s_w_phl(t0, v1_t, v0_t, cpu_env); + break; + case NM_MAQ_SA_W_PHR: + check_dsp(ctx); + gen_helper_maq_sa_w_phr(t0, v1_t, v0_t, cpu_env); + break; + case NM_MAQ_SA_W_PHL: + check_dsp(ctx); + gen_helper_maq_sa_w_phl(t0, v1_t, v0_t, cpu_env); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + + tcg_temp_free_i32(t0); + + tcg_temp_free(v0_t); + tcg_temp_free(v1_t); +} + + +static void gen_pool32axf_1_nanomips_insn(DisasContext *ctx, uint32_t opc, + int ret, int v1, int v2) +{ + int16_t imm; + TCGv t0 = tcg_temp_new(); + TCGv t1 = tcg_temp_new(); + TCGv v0_t = tcg_temp_new(); + + gen_load_gpr(v0_t, v1); + + switch (opc) { + case NM_POOL32AXF_1_0: + check_dsp(ctx); + switch (extract32(ctx->opcode, 12, 2)) { + case NM_MFHI: + gen_HILO(ctx, OPC_MFHI, v2 >> 3, ret); + break; + case NM_MFLO: + gen_HILO(ctx, OPC_MFLO, v2 >> 3, ret); + break; + case NM_MTHI: + gen_HILO(ctx, OPC_MTHI, v2 >> 3, v1); + break; + case NM_MTLO: + gen_HILO(ctx, OPC_MTLO, v2 >> 3, v1); + break; + } + break; + case NM_POOL32AXF_1_1: + check_dsp(ctx); + switch (extract32(ctx->opcode, 12, 2)) { + case NM_MTHLIP: + tcg_gen_movi_tl(t0, v2); + gen_helper_mthlip(t0, v0_t, cpu_env); + break; + case NM_SHILOV: + tcg_gen_movi_tl(t0, v2 >> 3); + gen_helper_shilo(t0, v0_t, cpu_env); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_POOL32AXF_1_3: + check_dsp(ctx); + imm = extract32(ctx->opcode, 14, 7); + switch (extract32(ctx->opcode, 12, 2)) { + case NM_RDDSP: + tcg_gen_movi_tl(t0, imm); + gen_helper_rddsp(t0, t0, cpu_env); + gen_store_gpr(t0, ret); + break; + case NM_WRDSP: + gen_load_gpr(t0, ret); + tcg_gen_movi_tl(t1, imm); + gen_helper_wrdsp(t0, t1, cpu_env); + break; + case NM_EXTP: + tcg_gen_movi_tl(t0, v2 >> 3); + tcg_gen_movi_tl(t1, v1); + gen_helper_extp(t0, t0, t1, cpu_env); + gen_store_gpr(t0, ret); + break; + case NM_EXTPDP: + tcg_gen_movi_tl(t0, v2 >> 3); + tcg_gen_movi_tl(t1, v1); + gen_helper_extpdp(t0, t0, t1, cpu_env); + gen_store_gpr(t0, ret); + break; + } + break; + case NM_POOL32AXF_1_4: + check_dsp(ctx); + tcg_gen_movi_tl(t0, v2 >> 2); + switch (extract32(ctx->opcode, 12, 1)) { + case NM_SHLL_QB: + gen_helper_shll_qb(t0, t0, v0_t, cpu_env); + gen_store_gpr(t0, ret); + break; + case NM_SHRL_QB: + gen_helper_shrl_qb(t0, t0, v0_t); + gen_store_gpr(t0, ret); + break; + } + break; + case NM_POOL32AXF_1_5: + opc = extract32(ctx->opcode, 12, 2); + gen_pool32axf_1_5_nanomips_insn(ctx, opc, ret, v1, v2); + break; + case NM_POOL32AXF_1_7: + check_dsp(ctx); + tcg_gen_movi_tl(t0, v2 >> 3); + tcg_gen_movi_tl(t1, v1); + switch (extract32(ctx->opcode, 12, 2)) { + case NM_EXTR_W: + gen_helper_extr_w(t0, t0, t1, cpu_env); + gen_store_gpr(t0, ret); + break; + case NM_EXTR_R_W: + gen_helper_extr_r_w(t0, t0, t1, cpu_env); + gen_store_gpr(t0, ret); + break; + case NM_EXTR_RS_W: + gen_helper_extr_rs_w(t0, t0, t1, cpu_env); + gen_store_gpr(t0, ret); + break; + case NM_EXTR_S_H: + gen_helper_extr_s_h(t0, t0, t1, cpu_env); + gen_store_gpr(t0, ret); + break; + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + + tcg_temp_free(t0); + tcg_temp_free(t1); + tcg_temp_free(v0_t); +} + +static void gen_pool32axf_2_multiply(DisasContext *ctx, uint32_t opc, + TCGv v0, TCGv v1, int rd) +{ + TCGv_i32 t0; + + t0 = tcg_temp_new_i32(); + + tcg_gen_movi_i32(t0, rd >> 3); + + switch (opc) { + case NM_POOL32AXF_2_0_7: + switch (extract32(ctx->opcode, 9, 3)) { + case NM_DPA_W_PH: + check_dspr2(ctx); + gen_helper_dpa_w_ph(t0, v1, v0, cpu_env); + break; + case NM_DPAQ_S_W_PH: + check_dsp(ctx); + gen_helper_dpaq_s_w_ph(t0, v1, v0, cpu_env); + break; + case NM_DPS_W_PH: + check_dspr2(ctx); + gen_helper_dps_w_ph(t0, v1, v0, cpu_env); + break; + case NM_DPSQ_S_W_PH: + check_dsp(ctx); + gen_helper_dpsq_s_w_ph(t0, v1, v0, cpu_env); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_POOL32AXF_2_8_15: + switch (extract32(ctx->opcode, 9, 3)) { + case NM_DPAX_W_PH: + check_dspr2(ctx); + gen_helper_dpax_w_ph(t0, v0, v1, cpu_env); + break; + case NM_DPAQ_SA_L_W: + check_dsp(ctx); + gen_helper_dpaq_sa_l_w(t0, v0, v1, cpu_env); + break; + case NM_DPSX_W_PH: + check_dspr2(ctx); + gen_helper_dpsx_w_ph(t0, v0, v1, cpu_env); + break; + case NM_DPSQ_SA_L_W: + check_dsp(ctx); + gen_helper_dpsq_sa_l_w(t0, v0, v1, cpu_env); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_POOL32AXF_2_16_23: + switch (extract32(ctx->opcode, 9, 3)) { + case NM_DPAU_H_QBL: + check_dsp(ctx); + gen_helper_dpau_h_qbl(t0, v0, v1, cpu_env); + break; + case NM_DPAQX_S_W_PH: + check_dspr2(ctx); + gen_helper_dpaqx_s_w_ph(t0, v0, v1, cpu_env); + break; + case NM_DPSU_H_QBL: + check_dsp(ctx); + gen_helper_dpsu_h_qbl(t0, v0, v1, cpu_env); + break; + case NM_DPSQX_S_W_PH: + check_dspr2(ctx); + gen_helper_dpsqx_s_w_ph(t0, v0, v1, cpu_env); + break; + case NM_MULSA_W_PH: + check_dspr2(ctx); + gen_helper_mulsa_w_ph(t0, v0, v1, cpu_env); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_POOL32AXF_2_24_31: + switch (extract32(ctx->opcode, 9, 3)) { + case NM_DPAU_H_QBR: + check_dsp(ctx); + gen_helper_dpau_h_qbr(t0, v1, v0, cpu_env); + break; + case NM_DPAQX_SA_W_PH: + check_dspr2(ctx); + gen_helper_dpaqx_sa_w_ph(t0, v1, v0, cpu_env); + break; + case NM_DPSU_H_QBR: + check_dsp(ctx); + gen_helper_dpsu_h_qbr(t0, v1, v0, cpu_env); + break; + case NM_DPSQX_SA_W_PH: + check_dspr2(ctx); + gen_helper_dpsqx_sa_w_ph(t0, v1, v0, cpu_env); + break; + case NM_MULSAQ_S_W_PH: + check_dsp(ctx); + gen_helper_mulsaq_s_w_ph(t0, v1, v0, cpu_env); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + + tcg_temp_free_i32(t0); +} + +static void gen_pool32axf_2_nanomips_insn(DisasContext *ctx, uint32_t opc, + int rt, int rs, int rd) +{ + int ret = rt; + TCGv t0 = tcg_temp_new(); + TCGv t1 = tcg_temp_new(); + TCGv v0_t = tcg_temp_new(); + TCGv v1_t = tcg_temp_new(); + + gen_load_gpr(v0_t, rt); + gen_load_gpr(v1_t, rs); + + switch (opc) { + case NM_POOL32AXF_2_0_7: + switch (extract32(ctx->opcode, 9, 3)) { + case NM_DPA_W_PH: + case NM_DPAQ_S_W_PH: + case NM_DPS_W_PH: + case NM_DPSQ_S_W_PH: + gen_pool32axf_2_multiply(ctx, opc, v0_t, v1_t, rd); + break; + case NM_BALIGN: + check_dspr2(ctx); + if (rt != 0) { + gen_load_gpr(t0, rs); + rd &= 3; + if (rd != 0 && rd != 2) { + tcg_gen_shli_tl(cpu_gpr[ret], cpu_gpr[ret], 8 * rd); + tcg_gen_ext32u_tl(t0, t0); + tcg_gen_shri_tl(t0, t0, 8 * (4 - rd)); + tcg_gen_or_tl(cpu_gpr[ret], cpu_gpr[ret], t0); + } + tcg_gen_ext32s_tl(cpu_gpr[ret], cpu_gpr[ret]); + } + break; + case NM_MADD: + check_dsp(ctx); + { + int acc = extract32(ctx->opcode, 14, 2); + TCGv_i64 t2 = tcg_temp_new_i64(); + TCGv_i64 t3 = tcg_temp_new_i64(); + + gen_load_gpr(t0, rt); + gen_load_gpr(t1, rs); + tcg_gen_ext_tl_i64(t2, t0); + tcg_gen_ext_tl_i64(t3, t1); + tcg_gen_mul_i64(t2, t2, t3); + tcg_gen_concat_tl_i64(t3, cpu_LO[acc], cpu_HI[acc]); + tcg_gen_add_i64(t2, t2, t3); + tcg_temp_free_i64(t3); + gen_move_low32(cpu_LO[acc], t2); + gen_move_high32(cpu_HI[acc], t2); + tcg_temp_free_i64(t2); + } + break; + case NM_MULT: + check_dsp(ctx); + { + int acc = extract32(ctx->opcode, 14, 2); + TCGv_i32 t2 = tcg_temp_new_i32(); + TCGv_i32 t3 = tcg_temp_new_i32(); + + gen_load_gpr(t0, rs); + gen_load_gpr(t1, rt); + tcg_gen_trunc_tl_i32(t2, t0); + tcg_gen_trunc_tl_i32(t3, t1); + tcg_gen_muls2_i32(t2, t3, t2, t3); + tcg_gen_ext_i32_tl(cpu_LO[acc], t2); + tcg_gen_ext_i32_tl(cpu_HI[acc], t3); + tcg_temp_free_i32(t2); + tcg_temp_free_i32(t3); + } + break; + case NM_EXTRV_W: + check_dsp(ctx); + gen_load_gpr(v1_t, rs); + tcg_gen_movi_tl(t0, rd >> 3); + gen_helper_extr_w(t0, t0, v1_t, cpu_env); + gen_store_gpr(t0, ret); + break; + } + break; + case NM_POOL32AXF_2_8_15: + switch (extract32(ctx->opcode, 9, 3)) { + case NM_DPAX_W_PH: + case NM_DPAQ_SA_L_W: + case NM_DPSX_W_PH: + case NM_DPSQ_SA_L_W: + gen_pool32axf_2_multiply(ctx, opc, v0_t, v1_t, rd); + break; + case NM_MADDU: + check_dsp(ctx); + { + int acc = extract32(ctx->opcode, 14, 2); + TCGv_i64 t2 = tcg_temp_new_i64(); + TCGv_i64 t3 = tcg_temp_new_i64(); + + gen_load_gpr(t0, rs); + gen_load_gpr(t1, rt); + tcg_gen_ext32u_tl(t0, t0); + tcg_gen_ext32u_tl(t1, t1); + tcg_gen_extu_tl_i64(t2, t0); + tcg_gen_extu_tl_i64(t3, t1); + tcg_gen_mul_i64(t2, t2, t3); + tcg_gen_concat_tl_i64(t3, cpu_LO[acc], cpu_HI[acc]); + tcg_gen_add_i64(t2, t2, t3); + tcg_temp_free_i64(t3); + gen_move_low32(cpu_LO[acc], t2); + gen_move_high32(cpu_HI[acc], t2); + tcg_temp_free_i64(t2); + } + break; + case NM_MULTU: + check_dsp(ctx); + { + int acc = extract32(ctx->opcode, 14, 2); + TCGv_i32 t2 = tcg_temp_new_i32(); + TCGv_i32 t3 = tcg_temp_new_i32(); + + gen_load_gpr(t0, rs); + gen_load_gpr(t1, rt); + tcg_gen_trunc_tl_i32(t2, t0); + tcg_gen_trunc_tl_i32(t3, t1); + tcg_gen_mulu2_i32(t2, t3, t2, t3); + tcg_gen_ext_i32_tl(cpu_LO[acc], t2); + tcg_gen_ext_i32_tl(cpu_HI[acc], t3); + tcg_temp_free_i32(t2); + tcg_temp_free_i32(t3); + } + break; + case NM_EXTRV_R_W: + check_dsp(ctx); + tcg_gen_movi_tl(t0, rd >> 3); + gen_helper_extr_r_w(t0, t0, v1_t, cpu_env); + gen_store_gpr(t0, ret); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_POOL32AXF_2_16_23: + switch (extract32(ctx->opcode, 9, 3)) { + case NM_DPAU_H_QBL: + case NM_DPAQX_S_W_PH: + case NM_DPSU_H_QBL: + case NM_DPSQX_S_W_PH: + case NM_MULSA_W_PH: + gen_pool32axf_2_multiply(ctx, opc, v0_t, v1_t, rd); + break; + case NM_EXTPV: + check_dsp(ctx); + tcg_gen_movi_tl(t0, rd >> 3); + gen_helper_extp(t0, t0, v1_t, cpu_env); + gen_store_gpr(t0, ret); + break; + case NM_MSUB: + check_dsp(ctx); + { + int acc = extract32(ctx->opcode, 14, 2); + TCGv_i64 t2 = tcg_temp_new_i64(); + TCGv_i64 t3 = tcg_temp_new_i64(); + + gen_load_gpr(t0, rs); + gen_load_gpr(t1, rt); + tcg_gen_ext_tl_i64(t2, t0); + tcg_gen_ext_tl_i64(t3, t1); + tcg_gen_mul_i64(t2, t2, t3); + tcg_gen_concat_tl_i64(t3, cpu_LO[acc], cpu_HI[acc]); + tcg_gen_sub_i64(t2, t3, t2); + tcg_temp_free_i64(t3); + gen_move_low32(cpu_LO[acc], t2); + gen_move_high32(cpu_HI[acc], t2); + tcg_temp_free_i64(t2); + } + break; + case NM_EXTRV_RS_W: + check_dsp(ctx); + tcg_gen_movi_tl(t0, rd >> 3); + gen_helper_extr_rs_w(t0, t0, v1_t, cpu_env); + gen_store_gpr(t0, ret); + break; + } + break; + case NM_POOL32AXF_2_24_31: + switch (extract32(ctx->opcode, 9, 3)) { + case NM_DPAU_H_QBR: + case NM_DPAQX_SA_W_PH: + case NM_DPSU_H_QBR: + case NM_DPSQX_SA_W_PH: + case NM_MULSAQ_S_W_PH: + gen_pool32axf_2_multiply(ctx, opc, v0_t, v1_t, rd); + break; + case NM_EXTPDPV: + check_dsp(ctx); + tcg_gen_movi_tl(t0, rd >> 3); + gen_helper_extpdp(t0, t0, v1_t, cpu_env); + gen_store_gpr(t0, ret); + break; + case NM_MSUBU: + check_dsp(ctx); + { + int acc = extract32(ctx->opcode, 14, 2); + TCGv_i64 t2 = tcg_temp_new_i64(); + TCGv_i64 t3 = tcg_temp_new_i64(); + + gen_load_gpr(t0, rs); + gen_load_gpr(t1, rt); + tcg_gen_ext32u_tl(t0, t0); + tcg_gen_ext32u_tl(t1, t1); + tcg_gen_extu_tl_i64(t2, t0); + tcg_gen_extu_tl_i64(t3, t1); + tcg_gen_mul_i64(t2, t2, t3); + tcg_gen_concat_tl_i64(t3, cpu_LO[acc], cpu_HI[acc]); + tcg_gen_sub_i64(t2, t3, t2); + tcg_temp_free_i64(t3); + gen_move_low32(cpu_LO[acc], t2); + gen_move_high32(cpu_HI[acc], t2); + tcg_temp_free_i64(t2); + } + break; + case NM_EXTRV_S_H: + check_dsp(ctx); + tcg_gen_movi_tl(t0, rd >> 3); + gen_helper_extr_s_h(t0, t0, v0_t, cpu_env); + gen_store_gpr(t0, ret); + break; + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + + tcg_temp_free(t0); + tcg_temp_free(t1); + + tcg_temp_free(v0_t); + tcg_temp_free(v1_t); +} + +static void gen_pool32axf_4_nanomips_insn(DisasContext *ctx, uint32_t opc, + int rt, int rs) +{ + int ret = rt; + TCGv t0 = tcg_temp_new(); + TCGv v0_t = tcg_temp_new(); + + gen_load_gpr(v0_t, rs); + + switch (opc) { + case NM_ABSQ_S_QB: + check_dspr2(ctx); + gen_helper_absq_s_qb(v0_t, v0_t, cpu_env); + gen_store_gpr(v0_t, ret); + break; + case NM_ABSQ_S_PH: + check_dsp(ctx); + gen_helper_absq_s_ph(v0_t, v0_t, cpu_env); + gen_store_gpr(v0_t, ret); + break; + case NM_ABSQ_S_W: + check_dsp(ctx); + gen_helper_absq_s_w(v0_t, v0_t, cpu_env); + gen_store_gpr(v0_t, ret); + break; + case NM_PRECEQ_W_PHL: + check_dsp(ctx); + tcg_gen_andi_tl(v0_t, v0_t, 0xFFFF0000); + tcg_gen_ext32s_tl(v0_t, v0_t); + gen_store_gpr(v0_t, ret); + break; + case NM_PRECEQ_W_PHR: + check_dsp(ctx); + tcg_gen_andi_tl(v0_t, v0_t, 0x0000FFFF); + tcg_gen_shli_tl(v0_t, v0_t, 16); + tcg_gen_ext32s_tl(v0_t, v0_t); + gen_store_gpr(v0_t, ret); + break; + case NM_PRECEQU_PH_QBL: + check_dsp(ctx); + gen_helper_precequ_ph_qbl(v0_t, v0_t); + gen_store_gpr(v0_t, ret); + break; + case NM_PRECEQU_PH_QBR: + check_dsp(ctx); + gen_helper_precequ_ph_qbr(v0_t, v0_t); + gen_store_gpr(v0_t, ret); + break; + case NM_PRECEQU_PH_QBLA: + check_dsp(ctx); + gen_helper_precequ_ph_qbla(v0_t, v0_t); + gen_store_gpr(v0_t, ret); + break; + case NM_PRECEQU_PH_QBRA: + check_dsp(ctx); + gen_helper_precequ_ph_qbra(v0_t, v0_t); + gen_store_gpr(v0_t, ret); + break; + case NM_PRECEU_PH_QBL: + check_dsp(ctx); + gen_helper_preceu_ph_qbl(v0_t, v0_t); + gen_store_gpr(v0_t, ret); + break; + case NM_PRECEU_PH_QBR: + check_dsp(ctx); + gen_helper_preceu_ph_qbr(v0_t, v0_t); + gen_store_gpr(v0_t, ret); + break; + case NM_PRECEU_PH_QBLA: + check_dsp(ctx); + gen_helper_preceu_ph_qbla(v0_t, v0_t); + gen_store_gpr(v0_t, ret); + break; + case NM_PRECEU_PH_QBRA: + check_dsp(ctx); + gen_helper_preceu_ph_qbra(v0_t, v0_t); + gen_store_gpr(v0_t, ret); + break; + case NM_REPLV_PH: + check_dsp(ctx); + tcg_gen_ext16u_tl(v0_t, v0_t); + tcg_gen_shli_tl(t0, v0_t, 16); + tcg_gen_or_tl(v0_t, v0_t, t0); + tcg_gen_ext32s_tl(v0_t, v0_t); + gen_store_gpr(v0_t, ret); + break; + case NM_REPLV_QB: + check_dsp(ctx); + tcg_gen_ext8u_tl(v0_t, v0_t); + tcg_gen_shli_tl(t0, v0_t, 8); + tcg_gen_or_tl(v0_t, v0_t, t0); + tcg_gen_shli_tl(t0, v0_t, 16); + tcg_gen_or_tl(v0_t, v0_t, t0); + tcg_gen_ext32s_tl(v0_t, v0_t); + gen_store_gpr(v0_t, ret); + break; + case NM_BITREV: + check_dsp(ctx); + gen_helper_bitrev(v0_t, v0_t); + gen_store_gpr(v0_t, ret); + break; + case NM_INSV: + check_dsp(ctx); + { + TCGv tv0 = tcg_temp_new(); + + gen_load_gpr(tv0, rt); + gen_helper_insv(v0_t, cpu_env, v0_t, tv0); + gen_store_gpr(v0_t, ret); + tcg_temp_free(tv0); + } + break; + case NM_RADDU_W_QB: + check_dsp(ctx); + gen_helper_raddu_w_qb(v0_t, v0_t); + gen_store_gpr(v0_t, ret); + break; + case NM_BITSWAP: + gen_bitswap(ctx, OPC_BITSWAP, ret, rs); + break; + case NM_CLO: + check_nms(ctx); + gen_cl(ctx, OPC_CLO, ret, rs); + break; + case NM_CLZ: + check_nms(ctx); + gen_cl(ctx, OPC_CLZ, ret, rs); + break; + case NM_WSBH: + gen_bshfl(ctx, OPC_WSBH, ret, rs); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + + tcg_temp_free(v0_t); + tcg_temp_free(t0); +} + +static void gen_pool32axf_7_nanomips_insn(DisasContext *ctx, uint32_t opc, + int rt, int rs, int rd) +{ + TCGv t0 = tcg_temp_new(); + TCGv rs_t = tcg_temp_new(); + + gen_load_gpr(rs_t, rs); + + switch (opc) { + case NM_SHRA_R_QB: + check_dspr2(ctx); + tcg_gen_movi_tl(t0, rd >> 2); + switch (extract32(ctx->opcode, 12, 1)) { + case 0: + /* NM_SHRA_QB */ + gen_helper_shra_qb(t0, t0, rs_t); + gen_store_gpr(t0, rt); + break; + case 1: + /* NM_SHRA_R_QB */ + gen_helper_shra_r_qb(t0, t0, rs_t); + gen_store_gpr(t0, rt); + break; + } + break; + case NM_SHRL_PH: + check_dspr2(ctx); + tcg_gen_movi_tl(t0, rd >> 1); + gen_helper_shrl_ph(t0, t0, rs_t); + gen_store_gpr(t0, rt); + break; + case NM_REPL_QB: + check_dsp(ctx); + { + int16_t imm; + target_long result; + imm = extract32(ctx->opcode, 13, 8); + result = (uint32_t)imm << 24 | + (uint32_t)imm << 16 | + (uint32_t)imm << 8 | + (uint32_t)imm; + result = (int32_t)result; + tcg_gen_movi_tl(t0, result); + gen_store_gpr(t0, rt); + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + tcg_temp_free(t0); + tcg_temp_free(rs_t); +} + + +static void gen_pool32axf_nanomips_insn(CPUMIPSState *env, DisasContext *ctx) +{ + int rt = extract32(ctx->opcode, 21, 5); + int rs = extract32(ctx->opcode, 16, 5); + int rd = extract32(ctx->opcode, 11, 5); + + switch (extract32(ctx->opcode, 6, 3)) { + case NM_POOL32AXF_1: + { + int32_t op1 = extract32(ctx->opcode, 9, 3); + gen_pool32axf_1_nanomips_insn(ctx, op1, rt, rs, rd); + } + break; + case NM_POOL32AXF_2: + { + int32_t op1 = extract32(ctx->opcode, 12, 2); + gen_pool32axf_2_nanomips_insn(ctx, op1, rt, rs, rd); + } + break; + case NM_POOL32AXF_4: + { + int32_t op1 = extract32(ctx->opcode, 9, 7); + gen_pool32axf_4_nanomips_insn(ctx, op1, rt, rs); + } + break; + case NM_POOL32AXF_5: + switch (extract32(ctx->opcode, 9, 7)) { +#ifndef CONFIG_USER_ONLY + case NM_TLBP: + gen_cp0(env, ctx, OPC_TLBP, 0, 0); + break; + case NM_TLBR: + gen_cp0(env, ctx, OPC_TLBR, 0, 0); + break; + case NM_TLBWI: + gen_cp0(env, ctx, OPC_TLBWI, 0, 0); + break; + case NM_TLBWR: + gen_cp0(env, ctx, OPC_TLBWR, 0, 0); + break; + case NM_TLBINV: + gen_cp0(env, ctx, OPC_TLBINV, 0, 0); + break; + case NM_TLBINVF: + gen_cp0(env, ctx, OPC_TLBINVF, 0, 0); + break; + case NM_DI: + check_cp0_enabled(ctx); + { + TCGv t0 = tcg_temp_new(); + + save_cpu_state(ctx, 1); + gen_helper_di(t0, cpu_env); + gen_store_gpr(t0, rt); + /* Stop translation as we may have switched the execution mode */ + ctx->base.is_jmp = DISAS_STOP; + tcg_temp_free(t0); + } + break; + case NM_EI: + check_cp0_enabled(ctx); + { + TCGv t0 = tcg_temp_new(); + + save_cpu_state(ctx, 1); + gen_helper_ei(t0, cpu_env); + gen_store_gpr(t0, rt); + /* Stop translation as we may have switched the execution mode */ + ctx->base.is_jmp = DISAS_STOP; + tcg_temp_free(t0); + } + break; + case NM_RDPGPR: + gen_load_srsgpr(rs, rt); + break; + case NM_WRPGPR: + gen_store_srsgpr(rs, rt); + break; + case NM_WAIT: + gen_cp0(env, ctx, OPC_WAIT, 0, 0); + break; + case NM_DERET: + gen_cp0(env, ctx, OPC_DERET, 0, 0); + break; + case NM_ERETX: + gen_cp0(env, ctx, OPC_ERET, 0, 0); + break; +#endif + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_POOL32AXF_7: + { + int32_t op1 = extract32(ctx->opcode, 9, 3); + gen_pool32axf_7_nanomips_insn(ctx, op1, rt, rs, rd); + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } +} + +/* Immediate Value Compact Branches */ +static void gen_compute_imm_branch(DisasContext *ctx, uint32_t opc, + int rt, int32_t imm, int32_t offset) +{ + TCGCond cond; + int bcond_compute = 0; + TCGv t0 = tcg_temp_new(); + TCGv t1 = tcg_temp_new(); + + gen_load_gpr(t0, rt); + tcg_gen_movi_tl(t1, imm); + ctx->btarget = addr_add(ctx, ctx->base.pc_next + 4, offset); + + /* Load needed operands and calculate btarget */ + switch (opc) { + case NM_BEQIC: + if (rt == 0 && imm == 0) { + /* Unconditional branch */ + } else if (rt == 0 && imm != 0) { + /* Treat as NOP */ + goto out; + } else { + bcond_compute = 1; + cond = TCG_COND_EQ; + } + break; + case NM_BBEQZC: + case NM_BBNEZC: + check_nms(ctx); + if (imm >= 32 && !(ctx->hflags & MIPS_HFLAG_64)) { + generate_exception_end(ctx, EXCP_RI); + goto out; + } else if (rt == 0 && opc == NM_BBEQZC) { + /* Unconditional branch */ + } else if (rt == 0 && opc == NM_BBNEZC) { + /* Treat as NOP */ + goto out; + } else { + tcg_gen_shri_tl(t0, t0, imm); + tcg_gen_andi_tl(t0, t0, 1); + tcg_gen_movi_tl(t1, 0); + bcond_compute = 1; + if (opc == NM_BBEQZC) { + cond = TCG_COND_EQ; + } else { + cond = TCG_COND_NE; + } + } + break; + case NM_BNEIC: + if (rt == 0 && imm == 0) { + /* Treat as NOP */ + goto out; + } else if (rt == 0 && imm != 0) { + /* Unconditional branch */ + } else { + bcond_compute = 1; + cond = TCG_COND_NE; + } + break; + case NM_BGEIC: + if (rt == 0 && imm == 0) { + /* Unconditional branch */ + } else { + bcond_compute = 1; + cond = TCG_COND_GE; + } + break; + case NM_BLTIC: + bcond_compute = 1; + cond = TCG_COND_LT; + break; + case NM_BGEIUC: + if (rt == 0 && imm == 0) { + /* Unconditional branch */ + } else { + bcond_compute = 1; + cond = TCG_COND_GEU; + } + break; + case NM_BLTIUC: + bcond_compute = 1; + cond = TCG_COND_LTU; + break; + default: + MIPS_INVAL("Immediate Value Compact branch"); + generate_exception_end(ctx, EXCP_RI); + goto out; + } + + if (bcond_compute == 0) { + /* Uncoditional compact branch */ + gen_goto_tb(ctx, 0, ctx->btarget); + } else { + /* Conditional compact branch */ + TCGLabel *fs = gen_new_label(); + + tcg_gen_brcond_tl(tcg_invert_cond(cond), t0, t1, fs); + + gen_goto_tb(ctx, 1, ctx->btarget); + gen_set_label(fs); + + gen_goto_tb(ctx, 0, ctx->base.pc_next + 4); + } + +out: + tcg_temp_free(t0); + tcg_temp_free(t1); +} + +/* P.BALRSC type nanoMIPS R6 branches: BALRSC and BRSC */ +static void gen_compute_nanomips_pbalrsc_branch(DisasContext *ctx, int rs, + int rt) +{ + TCGv t0 = tcg_temp_new(); + TCGv t1 = tcg_temp_new(); + + /* load rs */ + gen_load_gpr(t0, rs); + + /* link */ + if (rt != 0) { + tcg_gen_movi_tl(cpu_gpr[rt], ctx->base.pc_next + 4); + } + + /* calculate btarget */ + tcg_gen_shli_tl(t0, t0, 1); + tcg_gen_movi_tl(t1, ctx->base.pc_next + 4); + gen_op_addr_add(ctx, btarget, t1, t0); + + /* unconditional branch to register */ + tcg_gen_mov_tl(cpu_PC, btarget); + tcg_gen_lookup_and_goto_ptr(); + + tcg_temp_free(t0); + tcg_temp_free(t1); +} + +/* nanoMIPS Branches */ +static void gen_compute_compact_branch_nm(DisasContext *ctx, uint32_t opc, + int rs, int rt, int32_t offset) +{ + int bcond_compute = 0; + TCGv t0 = tcg_temp_new(); + TCGv t1 = tcg_temp_new(); + + /* Load needed operands and calculate btarget */ + switch (opc) { + /* compact branch */ + case OPC_BGEC: + case OPC_BLTC: + gen_load_gpr(t0, rs); + gen_load_gpr(t1, rt); + bcond_compute = 1; + ctx->btarget = addr_add(ctx, ctx->base.pc_next + 4, offset); + break; + case OPC_BGEUC: + case OPC_BLTUC: + if (rs == 0 || rs == rt) { + /* OPC_BLEZALC, OPC_BGEZALC */ + /* OPC_BGTZALC, OPC_BLTZALC */ + tcg_gen_movi_tl(cpu_gpr[31], ctx->base.pc_next + 4); + } + gen_load_gpr(t0, rs); + gen_load_gpr(t1, rt); + bcond_compute = 1; + ctx->btarget = addr_add(ctx, ctx->base.pc_next + 4, offset); + break; + case OPC_BC: + ctx->btarget = addr_add(ctx, ctx->base.pc_next + 4, offset); + break; + case OPC_BEQZC: + if (rs != 0) { + /* OPC_BEQZC, OPC_BNEZC */ + gen_load_gpr(t0, rs); + bcond_compute = 1; + ctx->btarget = addr_add(ctx, ctx->base.pc_next + 4, offset); + } else { + /* OPC_JIC, OPC_JIALC */ + TCGv tbase = tcg_temp_new(); + TCGv toffset = tcg_temp_new(); + + gen_load_gpr(tbase, rt); + tcg_gen_movi_tl(toffset, offset); + gen_op_addr_add(ctx, btarget, tbase, toffset); + tcg_temp_free(tbase); + tcg_temp_free(toffset); + } + break; + default: + MIPS_INVAL("Compact branch/jump"); + generate_exception_end(ctx, EXCP_RI); + goto out; + } + + if (bcond_compute == 0) { + /* Uncoditional compact branch */ + switch (opc) { + case OPC_BC: + gen_goto_tb(ctx, 0, ctx->btarget); + break; + default: + MIPS_INVAL("Compact branch/jump"); + generate_exception_end(ctx, EXCP_RI); + goto out; + } + } else { + /* Conditional compact branch */ + TCGLabel *fs = gen_new_label(); + + switch (opc) { + case OPC_BGEUC: + if (rs == 0 && rt != 0) { + /* OPC_BLEZALC */ + tcg_gen_brcondi_tl(tcg_invert_cond(TCG_COND_LE), t1, 0, fs); + } else if (rs != 0 && rt != 0 && rs == rt) { + /* OPC_BGEZALC */ + tcg_gen_brcondi_tl(tcg_invert_cond(TCG_COND_GE), t1, 0, fs); + } else { + /* OPC_BGEUC */ + tcg_gen_brcond_tl(tcg_invert_cond(TCG_COND_GEU), t0, t1, fs); + } + break; + case OPC_BLTUC: + if (rs == 0 && rt != 0) { + /* OPC_BGTZALC */ + tcg_gen_brcondi_tl(tcg_invert_cond(TCG_COND_GT), t1, 0, fs); + } else if (rs != 0 && rt != 0 && rs == rt) { + /* OPC_BLTZALC */ + tcg_gen_brcondi_tl(tcg_invert_cond(TCG_COND_LT), t1, 0, fs); + } else { + /* OPC_BLTUC */ + tcg_gen_brcond_tl(tcg_invert_cond(TCG_COND_LTU), t0, t1, fs); + } + break; + case OPC_BGEC: + if (rs == 0 && rt != 0) { + /* OPC_BLEZC */ + tcg_gen_brcondi_tl(tcg_invert_cond(TCG_COND_LE), t1, 0, fs); + } else if (rs != 0 && rt != 0 && rs == rt) { + /* OPC_BGEZC */ + tcg_gen_brcondi_tl(tcg_invert_cond(TCG_COND_GE), t1, 0, fs); + } else { + /* OPC_BGEC */ + tcg_gen_brcond_tl(tcg_invert_cond(TCG_COND_GE), t0, t1, fs); + } + break; + case OPC_BLTC: + if (rs == 0 && rt != 0) { + /* OPC_BGTZC */ + tcg_gen_brcondi_tl(tcg_invert_cond(TCG_COND_GT), t1, 0, fs); + } else if (rs != 0 && rt != 0 && rs == rt) { + /* OPC_BLTZC */ + tcg_gen_brcondi_tl(tcg_invert_cond(TCG_COND_LT), t1, 0, fs); + } else { + /* OPC_BLTC */ + tcg_gen_brcond_tl(tcg_invert_cond(TCG_COND_LT), t0, t1, fs); + } + break; + case OPC_BEQZC: + tcg_gen_brcondi_tl(tcg_invert_cond(TCG_COND_EQ), t0, 0, fs); + break; + default: + MIPS_INVAL("Compact conditional branch/jump"); + generate_exception_end(ctx, EXCP_RI); + goto out; + } + + /* Generating branch here as compact branches don't have delay slot */ + gen_goto_tb(ctx, 1, ctx->btarget); + gen_set_label(fs); + + gen_goto_tb(ctx, 0, ctx->base.pc_next + 4); + } + +out: + tcg_temp_free(t0); + tcg_temp_free(t1); +} + + +/* nanoMIPS CP1 Branches */ +static void gen_compute_branch_cp1_nm(DisasContext *ctx, uint32_t op, + int32_t ft, int32_t offset) +{ + target_ulong btarget; + TCGv_i64 t0 = tcg_temp_new_i64(); + + gen_load_fpr64(ctx, t0, ft); + tcg_gen_andi_i64(t0, t0, 1); + + btarget = addr_add(ctx, ctx->base.pc_next + 4, offset); + + switch (op) { + case NM_BC1EQZC: + tcg_gen_xori_i64(t0, t0, 1); + ctx->hflags |= MIPS_HFLAG_BC; + break; + case NM_BC1NEZC: + /* t0 already set */ + ctx->hflags |= MIPS_HFLAG_BC; + break; + default: + MIPS_INVAL("cp1 cond branch"); + generate_exception_end(ctx, EXCP_RI); + goto out; + } + + tcg_gen_trunc_i64_tl(bcond, t0); + + ctx->btarget = btarget; + +out: + tcg_temp_free_i64(t0); +} + + +static void gen_p_lsx(DisasContext *ctx, int rd, int rs, int rt) +{ + TCGv t0, t1; + t0 = tcg_temp_new(); + t1 = tcg_temp_new(); + + gen_load_gpr(t0, rs); + gen_load_gpr(t1, rt); + + if ((extract32(ctx->opcode, 6, 1)) == 1) { + /* PP.LSXS instructions require shifting */ + switch (extract32(ctx->opcode, 7, 4)) { + case NM_SHXS: + check_nms(ctx); + case NM_LHXS: + case NM_LHUXS: + tcg_gen_shli_tl(t0, t0, 1); + break; + case NM_SWXS: + check_nms(ctx); + case NM_LWXS: + case NM_LWC1XS: + case NM_SWC1XS: + tcg_gen_shli_tl(t0, t0, 2); + break; + case NM_LDC1XS: + case NM_SDC1XS: + tcg_gen_shli_tl(t0, t0, 3); + break; + } + } + gen_op_addr_add(ctx, t0, t0, t1); + + switch (extract32(ctx->opcode, 7, 4)) { + case NM_LBX: + tcg_gen_qemu_ld_tl(t0, t0, ctx->mem_idx, + MO_SB); + gen_store_gpr(t0, rd); + break; + case NM_LHX: + /*case NM_LHXS:*/ + tcg_gen_qemu_ld_tl(t0, t0, ctx->mem_idx, + MO_TESW); + gen_store_gpr(t0, rd); + break; + case NM_LWX: + /*case NM_LWXS:*/ + tcg_gen_qemu_ld_tl(t0, t0, ctx->mem_idx, + MO_TESL); + gen_store_gpr(t0, rd); + break; + case NM_LBUX: + tcg_gen_qemu_ld_tl(t0, t0, ctx->mem_idx, + MO_UB); + gen_store_gpr(t0, rd); + break; + case NM_LHUX: + /*case NM_LHUXS:*/ + tcg_gen_qemu_ld_tl(t0, t0, ctx->mem_idx, + MO_TEUW); + gen_store_gpr(t0, rd); + break; + case NM_SBX: + check_nms(ctx); + gen_load_gpr(t1, rd); + tcg_gen_qemu_st_tl(t1, t0, ctx->mem_idx, + MO_8); + break; + case NM_SHX: + /*case NM_SHXS:*/ + check_nms(ctx); + gen_load_gpr(t1, rd); + tcg_gen_qemu_st_tl(t1, t0, ctx->mem_idx, + MO_TEUW); + break; + case NM_SWX: + /*case NM_SWXS:*/ + check_nms(ctx); + gen_load_gpr(t1, rd); + tcg_gen_qemu_st_tl(t1, t0, ctx->mem_idx, + MO_TEUL); + break; + case NM_LWC1X: + /*case NM_LWC1XS:*/ + case NM_LDC1X: + /*case NM_LDC1XS:*/ + case NM_SWC1X: + /*case NM_SWC1XS:*/ + case NM_SDC1X: + /*case NM_SDC1XS:*/ + if (ctx->CP0_Config1 & (1 << CP0C1_FP)) { + check_cp1_enabled(ctx); + switch (extract32(ctx->opcode, 7, 4)) { + case NM_LWC1X: + /*case NM_LWC1XS:*/ + gen_flt_ldst(ctx, OPC_LWC1, rd, t0); + break; + case NM_LDC1X: + /*case NM_LDC1XS:*/ + gen_flt_ldst(ctx, OPC_LDC1, rd, t0); + break; + case NM_SWC1X: + /*case NM_SWC1XS:*/ + gen_flt_ldst(ctx, OPC_SWC1, rd, t0); + break; + case NM_SDC1X: + /*case NM_SDC1XS:*/ + gen_flt_ldst(ctx, OPC_SDC1, rd, t0); + break; + } + } else { + generate_exception_err(ctx, EXCP_CpU, 1); + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + + tcg_temp_free(t0); + tcg_temp_free(t1); +} + +static void gen_pool32f_nanomips_insn(DisasContext *ctx) +{ + int rt, rs, rd; + + rt = extract32(ctx->opcode, 21, 5); + rs = extract32(ctx->opcode, 16, 5); + rd = extract32(ctx->opcode, 11, 5); + + if (!(ctx->CP0_Config1 & (1 << CP0C1_FP))) { + generate_exception_end(ctx, EXCP_RI); + return; + } + check_cp1_enabled(ctx); + switch (extract32(ctx->opcode, 0, 3)) { + case NM_POOL32F_0: + switch (extract32(ctx->opcode, 3, 7)) { + case NM_RINT_S: + gen_farith(ctx, OPC_RINT_S, 0, rt, rs, 0); + break; + case NM_RINT_D: + gen_farith(ctx, OPC_RINT_D, 0, rt, rs, 0); + break; + case NM_CLASS_S: + gen_farith(ctx, OPC_CLASS_S, 0, rt, rs, 0); + break; + case NM_CLASS_D: + gen_farith(ctx, OPC_CLASS_D, 0, rt, rs, 0); + break; + case NM_ADD_S: + gen_farith(ctx, OPC_ADD_S, rt, rs, rd, 0); + break; + case NM_ADD_D: + gen_farith(ctx, OPC_ADD_D, rt, rs, rd, 0); + break; + case NM_SUB_S: + gen_farith(ctx, OPC_SUB_S, rt, rs, rd, 0); + break; + case NM_SUB_D: + gen_farith(ctx, OPC_SUB_D, rt, rs, rd, 0); + break; + case NM_MUL_S: + gen_farith(ctx, OPC_MUL_S, rt, rs, rd, 0); + break; + case NM_MUL_D: + gen_farith(ctx, OPC_MUL_D, rt, rs, rd, 0); + break; + case NM_DIV_S: + gen_farith(ctx, OPC_DIV_S, rt, rs, rd, 0); + break; + case NM_DIV_D: + gen_farith(ctx, OPC_DIV_D, rt, rs, rd, 0); + break; + case NM_SELEQZ_S: + gen_sel_s(ctx, OPC_SELEQZ_S, rd, rt, rs); + break; + case NM_SELEQZ_D: + gen_sel_d(ctx, OPC_SELEQZ_D, rd, rt, rs); + break; + case NM_SELNEZ_S: + gen_sel_s(ctx, OPC_SELNEZ_S, rd, rt, rs); + break; + case NM_SELNEZ_D: + gen_sel_d(ctx, OPC_SELNEZ_D, rd, rt, rs); + break; + case NM_SEL_S: + gen_sel_s(ctx, OPC_SEL_S, rd, rt, rs); + break; + case NM_SEL_D: + gen_sel_d(ctx, OPC_SEL_D, rd, rt, rs); + break; + case NM_MADDF_S: + gen_farith(ctx, OPC_MADDF_S, rt, rs, rd, 0); + break; + case NM_MADDF_D: + gen_farith(ctx, OPC_MADDF_D, rt, rs, rd, 0); + break; + case NM_MSUBF_S: + gen_farith(ctx, OPC_MSUBF_S, rt, rs, rd, 0); + break; + case NM_MSUBF_D: + gen_farith(ctx, OPC_MSUBF_D, rt, rs, rd, 0); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_POOL32F_3: + switch (extract32(ctx->opcode, 3, 3)) { + case NM_MIN_FMT: + switch (extract32(ctx->opcode, 9, 1)) { + case FMT_SDPS_S: + gen_farith(ctx, OPC_MIN_S, rt, rs, rd, 0); + break; + case FMT_SDPS_D: + gen_farith(ctx, OPC_MIN_D, rt, rs, rd, 0); + break; + } + break; + case NM_MAX_FMT: + switch (extract32(ctx->opcode, 9, 1)) { + case FMT_SDPS_S: + gen_farith(ctx, OPC_MAX_S, rt, rs, rd, 0); + break; + case FMT_SDPS_D: + gen_farith(ctx, OPC_MAX_D, rt, rs, rd, 0); + break; + } + break; + case NM_MINA_FMT: + switch (extract32(ctx->opcode, 9, 1)) { + case FMT_SDPS_S: + gen_farith(ctx, OPC_MINA_S, rt, rs, rd, 0); + break; + case FMT_SDPS_D: + gen_farith(ctx, OPC_MINA_D, rt, rs, rd, 0); + break; + } + break; + case NM_MAXA_FMT: + switch (extract32(ctx->opcode, 9, 1)) { + case FMT_SDPS_S: + gen_farith(ctx, OPC_MAXA_S, rt, rs, rd, 0); + break; + case FMT_SDPS_D: + gen_farith(ctx, OPC_MAXA_D, rt, rs, rd, 0); + break; + } + break; + case NM_POOL32FXF: + switch (extract32(ctx->opcode, 6, 8)) { + case NM_CFC1: + gen_cp1(ctx, OPC_CFC1, rt, rs); + break; + case NM_CTC1: + gen_cp1(ctx, OPC_CTC1, rt, rs); + break; + case NM_MFC1: + gen_cp1(ctx, OPC_MFC1, rt, rs); + break; + case NM_MTC1: + gen_cp1(ctx, OPC_MTC1, rt, rs); + break; + case NM_MFHC1: + gen_cp1(ctx, OPC_MFHC1, rt, rs); + break; + case NM_MTHC1: + gen_cp1(ctx, OPC_MTHC1, rt, rs); + break; + case NM_CVT_S_PL: + gen_farith(ctx, OPC_CVT_S_PL, -1, rs, rt, 0); + break; + case NM_CVT_S_PU: + gen_farith(ctx, OPC_CVT_S_PU, -1, rs, rt, 0); + break; + default: + switch (extract32(ctx->opcode, 6, 9)) { + case NM_CVT_L_S: + gen_farith(ctx, OPC_CVT_L_S, -1, rs, rt, 0); + break; + case NM_CVT_L_D: + gen_farith(ctx, OPC_CVT_L_D, -1, rs, rt, 0); + break; + case NM_CVT_W_S: + gen_farith(ctx, OPC_CVT_W_S, -1, rs, rt, 0); + break; + case NM_CVT_W_D: + gen_farith(ctx, OPC_CVT_W_D, -1, rs, rt, 0); + break; + case NM_RSQRT_S: + gen_farith(ctx, OPC_RSQRT_S, -1, rs, rt, 0); + break; + case NM_RSQRT_D: + gen_farith(ctx, OPC_RSQRT_D, -1, rs, rt, 0); + break; + case NM_SQRT_S: + gen_farith(ctx, OPC_SQRT_S, -1, rs, rt, 0); + break; + case NM_SQRT_D: + gen_farith(ctx, OPC_SQRT_D, -1, rs, rt, 0); + break; + case NM_RECIP_S: + gen_farith(ctx, OPC_RECIP_S, -1, rs, rt, 0); + break; + case NM_RECIP_D: + gen_farith(ctx, OPC_RECIP_D, -1, rs, rt, 0); + break; + case NM_FLOOR_L_S: + gen_farith(ctx, OPC_FLOOR_L_S, -1, rs, rt, 0); + break; + case NM_FLOOR_L_D: + gen_farith(ctx, OPC_FLOOR_L_D, -1, rs, rt, 0); + break; + case NM_FLOOR_W_S: + gen_farith(ctx, OPC_FLOOR_W_S, -1, rs, rt, 0); + break; + case NM_FLOOR_W_D: + gen_farith(ctx, OPC_FLOOR_W_D, -1, rs, rt, 0); + break; + case NM_CEIL_L_S: + gen_farith(ctx, OPC_CEIL_L_S, -1, rs, rt, 0); + break; + case NM_CEIL_L_D: + gen_farith(ctx, OPC_CEIL_L_D, -1, rs, rt, 0); + break; + case NM_CEIL_W_S: + gen_farith(ctx, OPC_CEIL_W_S, -1, rs, rt, 0); + break; + case NM_CEIL_W_D: + gen_farith(ctx, OPC_CEIL_W_D, -1, rs, rt, 0); + break; + case NM_TRUNC_L_S: + gen_farith(ctx, OPC_TRUNC_L_S, -1, rs, rt, 0); + break; + case NM_TRUNC_L_D: + gen_farith(ctx, OPC_TRUNC_L_D, -1, rs, rt, 0); + break; + case NM_TRUNC_W_S: + gen_farith(ctx, OPC_TRUNC_W_S, -1, rs, rt, 0); + break; + case NM_TRUNC_W_D: + gen_farith(ctx, OPC_TRUNC_W_D, -1, rs, rt, 0); + break; + case NM_ROUND_L_S: + gen_farith(ctx, OPC_ROUND_L_S, -1, rs, rt, 0); + break; + case NM_ROUND_L_D: + gen_farith(ctx, OPC_ROUND_L_D, -1, rs, rt, 0); + break; + case NM_ROUND_W_S: + gen_farith(ctx, OPC_ROUND_W_S, -1, rs, rt, 0); + break; + case NM_ROUND_W_D: + gen_farith(ctx, OPC_ROUND_W_D, -1, rs, rt, 0); + break; + case NM_MOV_S: + gen_farith(ctx, OPC_MOV_S, -1, rs, rt, 0); + break; + case NM_MOV_D: + gen_farith(ctx, OPC_MOV_D, -1, rs, rt, 0); + break; + case NM_ABS_S: + gen_farith(ctx, OPC_ABS_S, -1, rs, rt, 0); + break; + case NM_ABS_D: + gen_farith(ctx, OPC_ABS_D, -1, rs, rt, 0); + break; + case NM_NEG_S: + gen_farith(ctx, OPC_NEG_S, -1, rs, rt, 0); + break; + case NM_NEG_D: + gen_farith(ctx, OPC_NEG_D, -1, rs, rt, 0); + break; + case NM_CVT_D_S: + gen_farith(ctx, OPC_CVT_D_S, -1, rs, rt, 0); + break; + case NM_CVT_D_W: + gen_farith(ctx, OPC_CVT_D_W, -1, rs, rt, 0); + break; + case NM_CVT_D_L: + gen_farith(ctx, OPC_CVT_D_L, -1, rs, rt, 0); + break; + case NM_CVT_S_D: + gen_farith(ctx, OPC_CVT_S_D, -1, rs, rt, 0); + break; + case NM_CVT_S_W: + gen_farith(ctx, OPC_CVT_S_W, -1, rs, rt, 0); + break; + case NM_CVT_S_L: + gen_farith(ctx, OPC_CVT_S_L, -1, rs, rt, 0); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + } + break; + } + break; + case NM_POOL32F_5: + switch (extract32(ctx->opcode, 3, 3)) { + case NM_CMP_CONDN_S: + gen_r6_cmp_s(ctx, extract32(ctx->opcode, 6, 5), rt, rs, rd); + break; + case NM_CMP_CONDN_D: + gen_r6_cmp_d(ctx, extract32(ctx->opcode, 6, 5), rt, rs, rd); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } +} + +static void gen_pool32a5_nanomips_insn(DisasContext *ctx, int opc, + int rd, int rs, int rt) +{ + int ret = rd; + TCGv t0 = tcg_temp_new(); + TCGv v1_t = tcg_temp_new(); + TCGv v2_t = tcg_temp_new(); + + gen_load_gpr(v1_t, rs); + gen_load_gpr(v2_t, rt); + + switch (opc) { + case NM_CMP_EQ_PH: + check_dsp(ctx); + gen_helper_cmp_eq_ph(v1_t, v2_t, cpu_env); + break; + case NM_CMP_LT_PH: + check_dsp(ctx); + gen_helper_cmp_lt_ph(v1_t, v2_t, cpu_env); + break; + case NM_CMP_LE_PH: + check_dsp(ctx); + gen_helper_cmp_le_ph(v1_t, v2_t, cpu_env); + break; + case NM_CMPU_EQ_QB: + check_dsp(ctx); + gen_helper_cmpu_eq_qb(v1_t, v2_t, cpu_env); + break; + case NM_CMPU_LT_QB: + check_dsp(ctx); + gen_helper_cmpu_lt_qb(v1_t, v2_t, cpu_env); + break; + case NM_CMPU_LE_QB: + check_dsp(ctx); + gen_helper_cmpu_le_qb(v1_t, v2_t, cpu_env); + break; + case NM_CMPGU_EQ_QB: + check_dsp(ctx); + gen_helper_cmpgu_eq_qb(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case NM_CMPGU_LT_QB: + check_dsp(ctx); + gen_helper_cmpgu_lt_qb(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case NM_CMPGU_LE_QB: + check_dsp(ctx); + gen_helper_cmpgu_le_qb(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case NM_CMPGDU_EQ_QB: + check_dspr2(ctx); + gen_helper_cmpgu_eq_qb(v1_t, v1_t, v2_t); + tcg_gen_deposit_tl(cpu_dspctrl, cpu_dspctrl, v1_t, 24, 4); + gen_store_gpr(v1_t, ret); + break; + case NM_CMPGDU_LT_QB: + check_dspr2(ctx); + gen_helper_cmpgu_lt_qb(v1_t, v1_t, v2_t); + tcg_gen_deposit_tl(cpu_dspctrl, cpu_dspctrl, v1_t, 24, 4); + gen_store_gpr(v1_t, ret); + break; + case NM_CMPGDU_LE_QB: + check_dspr2(ctx); + gen_helper_cmpgu_le_qb(v1_t, v1_t, v2_t); + tcg_gen_deposit_tl(cpu_dspctrl, cpu_dspctrl, v1_t, 24, 4); + gen_store_gpr(v1_t, ret); + break; + case NM_PACKRL_PH: + check_dsp(ctx); + gen_helper_packrl_ph(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case NM_PICK_QB: + check_dsp(ctx); + gen_helper_pick_qb(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_PICK_PH: + check_dsp(ctx); + gen_helper_pick_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_ADDQ_S_W: + check_dsp(ctx); + gen_helper_addq_s_w(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_SUBQ_S_W: + check_dsp(ctx); + gen_helper_subq_s_w(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_ADDSC: + check_dsp(ctx); + gen_helper_addsc(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_ADDWC: + check_dsp(ctx); + gen_helper_addwc(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_ADDQ_S_PH: + check_dsp(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* ADDQ_PH */ + gen_helper_addq_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* ADDQ_S_PH */ + gen_helper_addq_s_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_ADDQH_R_PH: + check_dspr2(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* ADDQH_PH */ + gen_helper_addqh_ph(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* ADDQH_R_PH */ + gen_helper_addqh_r_ph(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_ADDQH_R_W: + check_dspr2(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* ADDQH_W */ + gen_helper_addqh_w(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* ADDQH_R_W */ + gen_helper_addqh_r_w(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_ADDU_S_QB: + check_dsp(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* ADDU_QB */ + gen_helper_addu_qb(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* ADDU_S_QB */ + gen_helper_addu_s_qb(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_ADDU_S_PH: + check_dspr2(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* ADDU_PH */ + gen_helper_addu_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* ADDU_S_PH */ + gen_helper_addu_s_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_ADDUH_R_QB: + check_dspr2(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* ADDUH_QB */ + gen_helper_adduh_qb(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* ADDUH_R_QB */ + gen_helper_adduh_r_qb(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_SHRAV_R_PH: + check_dsp(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* SHRAV_PH */ + gen_helper_shra_ph(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* SHRAV_R_PH */ + gen_helper_shra_r_ph(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_SHRAV_R_QB: + check_dspr2(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* SHRAV_QB */ + gen_helper_shra_qb(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* SHRAV_R_QB */ + gen_helper_shra_r_qb(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_SUBQ_S_PH: + check_dsp(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* SUBQ_PH */ + gen_helper_subq_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* SUBQ_S_PH */ + gen_helper_subq_s_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_SUBQH_R_PH: + check_dspr2(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* SUBQH_PH */ + gen_helper_subqh_ph(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* SUBQH_R_PH */ + gen_helper_subqh_r_ph(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_SUBQH_R_W: + check_dspr2(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* SUBQH_W */ + gen_helper_subqh_w(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* SUBQH_R_W */ + gen_helper_subqh_r_w(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_SUBU_S_QB: + check_dsp(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* SUBU_QB */ + gen_helper_subu_qb(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* SUBU_S_QB */ + gen_helper_subu_s_qb(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_SUBU_S_PH: + check_dspr2(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* SUBU_PH */ + gen_helper_subu_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* SUBU_S_PH */ + gen_helper_subu_s_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_SUBUH_R_QB: + check_dspr2(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* SUBUH_QB */ + gen_helper_subuh_qb(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* SUBUH_R_QB */ + gen_helper_subuh_r_qb(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_SHLLV_S_PH: + check_dsp(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* SHLLV_PH */ + gen_helper_shll_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* SHLLV_S_PH */ + gen_helper_shll_s_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_PRECR_SRA_R_PH_W: + check_dspr2(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* PRECR_SRA_PH_W */ + { + TCGv_i32 sa_t = tcg_const_i32(rd); + gen_helper_precr_sra_ph_w(v1_t, sa_t, v1_t, + cpu_gpr[rt]); + gen_store_gpr(v1_t, rt); + tcg_temp_free_i32(sa_t); + } + break; + case 1: + /* PRECR_SRA_R_PH_W */ + { + TCGv_i32 sa_t = tcg_const_i32(rd); + gen_helper_precr_sra_r_ph_w(v1_t, sa_t, v1_t, + cpu_gpr[rt]); + gen_store_gpr(v1_t, rt); + tcg_temp_free_i32(sa_t); + } + break; + } + break; + case NM_MULEU_S_PH_QBL: + check_dsp(ctx); + gen_helper_muleu_s_ph_qbl(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_MULEU_S_PH_QBR: + check_dsp(ctx); + gen_helper_muleu_s_ph_qbr(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_MULQ_RS_PH: + check_dsp(ctx); + gen_helper_mulq_rs_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_MULQ_S_PH: + check_dspr2(ctx); + gen_helper_mulq_s_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_MULQ_RS_W: + check_dspr2(ctx); + gen_helper_mulq_rs_w(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_MULQ_S_W: + check_dspr2(ctx); + gen_helper_mulq_s_w(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_APPEND: + check_dspr2(ctx); + gen_load_gpr(t0, rs); + if (rd != 0) { + tcg_gen_deposit_tl(cpu_gpr[rt], t0, cpu_gpr[rt], rd, 32 - rd); + } + tcg_gen_ext32s_tl(cpu_gpr[rt], cpu_gpr[rt]); + break; + case NM_MODSUB: + check_dsp(ctx); + gen_helper_modsub(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case NM_SHRAV_R_W: + check_dsp(ctx); + gen_helper_shra_r_w(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case NM_SHRLV_PH: + check_dspr2(ctx); + gen_helper_shrl_ph(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case NM_SHRLV_QB: + check_dsp(ctx); + gen_helper_shrl_qb(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case NM_SHLLV_QB: + check_dsp(ctx); + gen_helper_shll_qb(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_SHLLV_S_W: + check_dsp(ctx); + gen_helper_shll_s_w(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_SHILO: + check_dsp(ctx); + { + TCGv tv0 = tcg_temp_new(); + TCGv tv1 = tcg_temp_new(); + int16_t imm = extract32(ctx->opcode, 16, 7); + + tcg_gen_movi_tl(tv0, rd >> 3); + tcg_gen_movi_tl(tv1, imm); + gen_helper_shilo(tv0, tv1, cpu_env); + } + break; + case NM_MULEQ_S_W_PHL: + check_dsp(ctx); + gen_helper_muleq_s_w_phl(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_MULEQ_S_W_PHR: + check_dsp(ctx); + gen_helper_muleq_s_w_phr(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_MUL_S_PH: + check_dspr2(ctx); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* MUL_PH */ + gen_helper_mul_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case 1: + /* MUL_S_PH */ + gen_helper_mul_s_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + } + break; + case NM_PRECR_QB_PH: + check_dspr2(ctx); + gen_helper_precr_qb_ph(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case NM_PRECRQ_QB_PH: + check_dsp(ctx); + gen_helper_precrq_qb_ph(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case NM_PRECRQ_PH_W: + check_dsp(ctx); + gen_helper_precrq_ph_w(v1_t, v1_t, v2_t); + gen_store_gpr(v1_t, ret); + break; + case NM_PRECRQ_RS_PH_W: + check_dsp(ctx); + gen_helper_precrq_rs_ph_w(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_PRECRQU_S_QB_PH: + check_dsp(ctx); + gen_helper_precrqu_s_qb_ph(v1_t, v1_t, v2_t, cpu_env); + gen_store_gpr(v1_t, ret); + break; + case NM_SHRA_R_W: + check_dsp(ctx); + tcg_gen_movi_tl(t0, rd); + gen_helper_shra_r_w(v1_t, t0, v1_t); + gen_store_gpr(v1_t, rt); + break; + case NM_SHRA_R_PH: + check_dsp(ctx); + tcg_gen_movi_tl(t0, rd >> 1); + switch (extract32(ctx->opcode, 10, 1)) { + case 0: + /* SHRA_PH */ + gen_helper_shra_ph(v1_t, t0, v1_t); + break; + gen_store_gpr(v1_t, rt); + case 1: + /* SHRA_R_PH */ + gen_helper_shra_r_ph(v1_t, t0, v1_t); + gen_store_gpr(v1_t, rt); + break; + } + break; + case NM_SHLL_S_PH: + check_dsp(ctx); + tcg_gen_movi_tl(t0, rd >> 1); + switch (extract32(ctx->opcode, 10, 2)) { + case 0: + /* SHLL_PH */ + gen_helper_shll_ph(v1_t, t0, v1_t, cpu_env); + gen_store_gpr(v1_t, rt); + break; + case 2: + /* SHLL_S_PH */ + gen_helper_shll_s_ph(v1_t, t0, v1_t, cpu_env); + gen_store_gpr(v1_t, rt); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_SHLL_S_W: + check_dsp(ctx); + tcg_gen_movi_tl(t0, rd); + gen_helper_shll_s_w(v1_t, t0, v1_t, cpu_env); + gen_store_gpr(v1_t, rt); + break; + case NM_REPL_PH: + check_dsp(ctx); + { + int16_t imm; + imm = sextract32(ctx->opcode, 11, 11); + imm = (int16_t)(imm << 6) >> 6; + if (rt != 0) { + tcg_gen_movi_tl(cpu_gpr[rt], dup_const(MO_16, imm)); + } + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } +} + +static int decode_nanomips_32_48_opc(CPUMIPSState *env, DisasContext *ctx) +{ + uint16_t insn; + uint32_t op; + int rt, rs, rd; + int offset; + int imm; + + insn = cpu_lduw_code(env, ctx->base.pc_next + 2); + ctx->opcode = (ctx->opcode << 16) | insn; + + rt = extract32(ctx->opcode, 21, 5); + rs = extract32(ctx->opcode, 16, 5); + rd = extract32(ctx->opcode, 11, 5); + + op = extract32(ctx->opcode, 26, 6); + switch (op) { + case NM_P_ADDIU: + if (rt == 0) { + /* P.RI */ + switch (extract32(ctx->opcode, 19, 2)) { + case NM_SIGRIE: + default: + generate_exception_end(ctx, EXCP_RI); + break; + case NM_P_SYSCALL: + if ((extract32(ctx->opcode, 18, 1)) == NM_SYSCALL) { + generate_exception_end(ctx, EXCP_SYSCALL); + } else { + generate_exception_end(ctx, EXCP_RI); + } + break; + case NM_BREAK: + generate_exception_end(ctx, EXCP_BREAK); + break; + case NM_SDBBP: + if (is_uhi(extract32(ctx->opcode, 0, 19))) { + gen_helper_do_semihosting(cpu_env); + } else { + if (ctx->hflags & MIPS_HFLAG_SBRI) { + generate_exception_end(ctx, EXCP_RI); + } else { + generate_exception_end(ctx, EXCP_DBp); + } + } + break; + } + } else { + /* NM_ADDIU */ + imm = extract32(ctx->opcode, 0, 16); + if (rs != 0) { + tcg_gen_addi_tl(cpu_gpr[rt], cpu_gpr[rs], imm); + } else { + tcg_gen_movi_tl(cpu_gpr[rt], imm); + } + tcg_gen_ext32s_tl(cpu_gpr[rt], cpu_gpr[rt]); + } + break; + case NM_ADDIUPC: + if (rt != 0) { + offset = sextract32(ctx->opcode, 0, 1) << 21 | + extract32(ctx->opcode, 1, 20) << 1; + target_long addr = addr_add(ctx, ctx->base.pc_next + 4, offset); + tcg_gen_movi_tl(cpu_gpr[rt], addr); + } + break; + case NM_POOL32A: + switch (ctx->opcode & 0x07) { + case NM_POOL32A0: + gen_pool32a0_nanomips_insn(env, ctx); + break; + case NM_POOL32A5: + { + int32_t op1 = extract32(ctx->opcode, 3, 7); + gen_pool32a5_nanomips_insn(ctx, op1, rd, rs, rt); + } + break; + case NM_POOL32A7: + switch (extract32(ctx->opcode, 3, 3)) { + case NM_P_LSX: + gen_p_lsx(ctx, rd, rs, rt); + break; + case NM_LSA: + /* In nanoMIPS, the shift field directly encodes the shift + * amount, meaning that the supported shift values are in + * the range 0 to 3 (instead of 1 to 4 in MIPSR6). */ + gen_lsa(ctx, OPC_LSA, rd, rs, rt, + extract32(ctx->opcode, 9, 2) - 1); + break; + case NM_EXTW: + gen_ext(ctx, 32, rd, rs, rt, extract32(ctx->opcode, 6, 5)); + break; + case NM_POOL32AXF: + gen_pool32axf_nanomips_insn(env, ctx); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_P_GP_W: + switch (ctx->opcode & 0x03) { + case NM_ADDIUGP_W: + if (rt != 0) { + offset = extract32(ctx->opcode, 0, 21); + gen_op_addr_addi(ctx, cpu_gpr[rt], cpu_gpr[28], offset); + } + break; + case NM_LWGP: + gen_ld(ctx, OPC_LW, rt, 28, extract32(ctx->opcode, 2, 19) << 2); + break; + case NM_SWGP: + gen_st(ctx, OPC_SW, rt, 28, extract32(ctx->opcode, 2, 19) << 2); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_P48I: + { + insn = cpu_lduw_code(env, ctx->base.pc_next + 4); + target_long addr_off = extract32(ctx->opcode, 0, 16) | insn << 16; + switch (extract32(ctx->opcode, 16, 5)) { + case NM_LI48: + check_nms(ctx); + if (rt != 0) { + tcg_gen_movi_tl(cpu_gpr[rt], addr_off); + } + break; + case NM_ADDIU48: + check_nms(ctx); + if (rt != 0) { + tcg_gen_addi_tl(cpu_gpr[rt], cpu_gpr[rt], addr_off); + tcg_gen_ext32s_tl(cpu_gpr[rt], cpu_gpr[rt]); + } + break; + case NM_ADDIUGP48: + check_nms(ctx); + if (rt != 0) { + gen_op_addr_addi(ctx, cpu_gpr[rt], cpu_gpr[28], addr_off); + } + break; + case NM_ADDIUPC48: + check_nms(ctx); + if (rt != 0) { + target_long addr = addr_add(ctx, ctx->base.pc_next + 6, + addr_off); + + tcg_gen_movi_tl(cpu_gpr[rt], addr); + } + break; + case NM_LWPC48: + check_nms(ctx); + if (rt != 0) { + TCGv t0; + t0 = tcg_temp_new(); + + target_long addr = addr_add(ctx, ctx->base.pc_next + 6, + addr_off); + + tcg_gen_movi_tl(t0, addr); + tcg_gen_qemu_ld_tl(cpu_gpr[rt], t0, ctx->mem_idx, MO_TESL); + tcg_temp_free(t0); + } + break; + case NM_SWPC48: + check_nms(ctx); + { + TCGv t0, t1; + t0 = tcg_temp_new(); + t1 = tcg_temp_new(); + + target_long addr = addr_add(ctx, ctx->base.pc_next + 6, + addr_off); + + tcg_gen_movi_tl(t0, addr); + gen_load_gpr(t1, rt); + + tcg_gen_qemu_st_tl(t1, t0, ctx->mem_idx, MO_TEUL); + + tcg_temp_free(t0); + tcg_temp_free(t1); + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + return 6; + } + case NM_P_U12: + switch (extract32(ctx->opcode, 12, 4)) { + case NM_ORI: + gen_logic_imm(ctx, OPC_ORI, rt, rs, extract32(ctx->opcode, 0, 12)); + break; + case NM_XORI: + gen_logic_imm(ctx, OPC_XORI, rt, rs, extract32(ctx->opcode, 0, 12)); + break; + case NM_ANDI: + gen_logic_imm(ctx, OPC_ANDI, rt, rs, extract32(ctx->opcode, 0, 12)); + break; + case NM_P_SR: + switch (extract32(ctx->opcode, 20, 1)) { + case NM_PP_SR: + switch (ctx->opcode & 3) { + case NM_SAVE: + gen_save(ctx, rt, extract32(ctx->opcode, 16, 4), + extract32(ctx->opcode, 2, 1), + extract32(ctx->opcode, 3, 9) << 3); + break; + case NM_RESTORE: + case NM_RESTORE_JRC: + gen_restore(ctx, rt, extract32(ctx->opcode, 16, 4), + extract32(ctx->opcode, 2, 1), + extract32(ctx->opcode, 3, 9) << 3); + if ((ctx->opcode & 3) == NM_RESTORE_JRC) { + gen_compute_branch_nm(ctx, OPC_JR, 2, 31, 0, 0); + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_P_SR_F: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_SLTI: + gen_slt_imm(ctx, OPC_SLTI, rt, rs, extract32(ctx->opcode, 0, 12)); + break; + case NM_SLTIU: + gen_slt_imm(ctx, OPC_SLTIU, rt, rs, extract32(ctx->opcode, 0, 12)); + break; + case NM_SEQI: + { + TCGv t0 = tcg_temp_new(); + + imm = extract32(ctx->opcode, 0, 12); + gen_load_gpr(t0, rs); + tcg_gen_setcondi_tl(TCG_COND_EQ, t0, t0, imm); + gen_store_gpr(t0, rt); + + tcg_temp_free(t0); + } + break; + case NM_ADDIUNEG: + imm = (int16_t) extract32(ctx->opcode, 0, 12); + gen_arith_imm(ctx, OPC_ADDIU, rt, rs, -imm); + break; + case NM_P_SHIFT: + { + int shift = extract32(ctx->opcode, 0, 5); + switch (extract32(ctx->opcode, 5, 4)) { + case NM_P_SLL: + if (rt == 0 && shift == 0) { + /* NOP */ + } else if (rt == 0 && shift == 3) { + /* EHB - treat as NOP */ + } else if (rt == 0 && shift == 5) { + /* PAUSE - treat as NOP */ + } else if (rt == 0 && shift == 6) { + /* SYNC */ + gen_sync(extract32(ctx->opcode, 16, 5)); + } else { + /* SLL */ + gen_shift_imm(ctx, OPC_SLL, rt, rs, + extract32(ctx->opcode, 0, 5)); + } + break; + case NM_SRL: + gen_shift_imm(ctx, OPC_SRL, rt, rs, + extract32(ctx->opcode, 0, 5)); + break; + case NM_SRA: + gen_shift_imm(ctx, OPC_SRA, rt, rs, + extract32(ctx->opcode, 0, 5)); + break; + case NM_ROTR: + gen_shift_imm(ctx, OPC_ROTR, rt, rs, + extract32(ctx->opcode, 0, 5)); + break; + } + } + break; + case NM_P_ROTX: + check_nms(ctx); + if (rt != 0) { + TCGv t0 = tcg_temp_new(); + TCGv_i32 shift = tcg_const_i32(extract32(ctx->opcode, 0, 5)); + TCGv_i32 shiftx = tcg_const_i32(extract32(ctx->opcode, 7, 4) + << 1); + TCGv_i32 stripe = tcg_const_i32(extract32(ctx->opcode, 6, 1)); + + gen_load_gpr(t0, rs); + gen_helper_rotx(cpu_gpr[rt], t0, shift, shiftx, stripe); + tcg_temp_free(t0); + + tcg_temp_free_i32(shift); + tcg_temp_free_i32(shiftx); + tcg_temp_free_i32(stripe); + } + break; + case NM_P_INS: + switch (((ctx->opcode >> 10) & 2) | + (extract32(ctx->opcode, 5, 1))) { + case NM_INS: + check_nms(ctx); + gen_bitops(ctx, OPC_INS, rt, rs, extract32(ctx->opcode, 0, 5), + extract32(ctx->opcode, 6, 5)); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_P_EXT: + switch (((ctx->opcode >> 10) & 2) | + (extract32(ctx->opcode, 5, 1))) { + case NM_EXT: + check_nms(ctx); + gen_bitops(ctx, OPC_EXT, rt, rs, extract32(ctx->opcode, 0, 5), + extract32(ctx->opcode, 6, 5)); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_POOL32F: + gen_pool32f_nanomips_insn(ctx); + break; + case NM_POOL32S: + break; + case NM_P_LUI: + switch (extract32(ctx->opcode, 1, 1)) { + case NM_LUI: + if (rt != 0) { + tcg_gen_movi_tl(cpu_gpr[rt], + sextract32(ctx->opcode, 0, 1) << 31 | + extract32(ctx->opcode, 2, 10) << 21 | + extract32(ctx->opcode, 12, 9) << 12); + } + break; + case NM_ALUIPC: + if (rt != 0) { + offset = sextract32(ctx->opcode, 0, 1) << 31 | + extract32(ctx->opcode, 2, 10) << 21 | + extract32(ctx->opcode, 12, 9) << 12; + target_long addr; + addr = ~0xFFF & addr_add(ctx, ctx->base.pc_next + 4, offset); + tcg_gen_movi_tl(cpu_gpr[rt], addr); + } + break; + } + break; + case NM_P_GP_BH: + { + uint32_t u = extract32(ctx->opcode, 0, 18); + + switch (extract32(ctx->opcode, 18, 3)) { + case NM_LBGP: + gen_ld(ctx, OPC_LB, rt, 28, u); + break; + case NM_SBGP: + gen_st(ctx, OPC_SB, rt, 28, u); + break; + case NM_LBUGP: + gen_ld(ctx, OPC_LBU, rt, 28, u); + break; + case NM_ADDIUGP_B: + if (rt != 0) { + gen_op_addr_addi(ctx, cpu_gpr[rt], cpu_gpr[28], u); + } + break; + case NM_P_GP_LH: + u &= ~1; + switch (ctx->opcode & 1) { + case NM_LHGP: + gen_ld(ctx, OPC_LH, rt, 28, u); + break; + case NM_LHUGP: + gen_ld(ctx, OPC_LHU, rt, 28, u); + break; + } + break; + case NM_P_GP_SH: + u &= ~1; + switch (ctx->opcode & 1) { + case NM_SHGP: + gen_st(ctx, OPC_SH, rt, 28, u); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_P_GP_CP1: + u &= ~0x3; + switch (ctx->opcode & 0x3) { + case NM_LWC1GP: + gen_cop1_ldst(ctx, OPC_LWC1, rt, 28, u); + break; + case NM_LDC1GP: + gen_cop1_ldst(ctx, OPC_LDC1, rt, 28, u); + break; + case NM_SWC1GP: + gen_cop1_ldst(ctx, OPC_SWC1, rt, 28, u); + break; + case NM_SDC1GP: + gen_cop1_ldst(ctx, OPC_SDC1, rt, 28, u); + break; + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + } + break; + case NM_P_LS_U12: + { + uint32_t u = extract32(ctx->opcode, 0, 12); + + switch (extract32(ctx->opcode, 12, 4)) { + case NM_P_PREFU12: + if (rt == 31) { + /* SYNCI */ + /* Break the TB to be able to sync copied instructions + immediately */ + ctx->base.is_jmp = DISAS_STOP; + } else { + /* PREF */ + /* Treat as NOP. */ + } + break; + case NM_LB: + gen_ld(ctx, OPC_LB, rt, rs, u); + break; + case NM_LH: + gen_ld(ctx, OPC_LH, rt, rs, u); + break; + case NM_LW: + gen_ld(ctx, OPC_LW, rt, rs, u); + break; + case NM_LBU: + gen_ld(ctx, OPC_LBU, rt, rs, u); + break; + case NM_LHU: + gen_ld(ctx, OPC_LHU, rt, rs, u); + break; + case NM_SB: + gen_st(ctx, OPC_SB, rt, rs, u); + break; + case NM_SH: + gen_st(ctx, OPC_SH, rt, rs, u); + break; + case NM_SW: + gen_st(ctx, OPC_SW, rt, rs, u); + break; + case NM_LWC1: + gen_cop1_ldst(ctx, OPC_LWC1, rt, rs, u); + break; + case NM_LDC1: + gen_cop1_ldst(ctx, OPC_LDC1, rt, rs, u); + break; + case NM_SWC1: + gen_cop1_ldst(ctx, OPC_SWC1, rt, rs, u); + break; + case NM_SDC1: + gen_cop1_ldst(ctx, OPC_SDC1, rt, rs, u); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + } + break; + case NM_P_LS_S9: + { + int32_t s = (sextract32(ctx->opcode, 15, 1) << 8) | + extract32(ctx->opcode, 0, 8); + + switch (extract32(ctx->opcode, 8, 3)) { + case NM_P_LS_S0: + switch (extract32(ctx->opcode, 11, 4)) { + case NM_LBS9: + gen_ld(ctx, OPC_LB, rt, rs, s); + break; + case NM_LHS9: + gen_ld(ctx, OPC_LH, rt, rs, s); + break; + case NM_LWS9: + gen_ld(ctx, OPC_LW, rt, rs, s); + break; + case NM_LBUS9: + gen_ld(ctx, OPC_LBU, rt, rs, s); + break; + case NM_LHUS9: + gen_ld(ctx, OPC_LHU, rt, rs, s); + break; + case NM_SBS9: + gen_st(ctx, OPC_SB, rt, rs, s); + break; + case NM_SHS9: + gen_st(ctx, OPC_SH, rt, rs, s); + break; + case NM_SWS9: + gen_st(ctx, OPC_SW, rt, rs, s); + break; + case NM_LWC1S9: + gen_cop1_ldst(ctx, OPC_LWC1, rt, rs, s); + break; + case NM_LDC1S9: + gen_cop1_ldst(ctx, OPC_LDC1, rt, rs, s); + break; + case NM_SWC1S9: + gen_cop1_ldst(ctx, OPC_SWC1, rt, rs, s); + break; + case NM_SDC1S9: + gen_cop1_ldst(ctx, OPC_SDC1, rt, rs, s); + break; + case NM_P_PREFS9: + if (rt == 31) { + /* SYNCI */ + /* Break the TB to be able to sync copied instructions + immediately */ + ctx->base.is_jmp = DISAS_STOP; + } else { + /* PREF */ + /* Treat as NOP. */ + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_P_LS_S1: + switch (extract32(ctx->opcode, 11, 4)) { + case NM_UALH: + case NM_UASH: + check_nms(ctx); + { + TCGv t0 = tcg_temp_new(); + TCGv t1 = tcg_temp_new(); + + gen_base_offset_addr(ctx, t0, rs, s); + + switch (extract32(ctx->opcode, 11, 4)) { + case NM_UALH: + tcg_gen_qemu_ld_tl(t0, t0, ctx->mem_idx, MO_TESW | + MO_UNALN); + gen_store_gpr(t0, rt); + break; + case NM_UASH: + gen_load_gpr(t1, rt); + tcg_gen_qemu_st_tl(t1, t0, ctx->mem_idx, MO_TEUW | + MO_UNALN); + break; + } + tcg_temp_free(t0); + tcg_temp_free(t1); + } + break; + case NM_P_LL: + switch (ctx->opcode & 0x03) { + case NM_LL: + gen_ld(ctx, OPC_LL, rt, rs, s); + break; + case NM_LLWP: + check_xnp(ctx); + gen_llwp(ctx, rs, 0, rt, extract32(ctx->opcode, 3, 5)); + break; + } + break; + case NM_P_SC: + switch (ctx->opcode & 0x03) { + case NM_SC: + gen_st_cond(ctx, OPC_SC, rt, rs, s); + break; + case NM_SCWP: + check_xnp(ctx); + gen_scwp(ctx, rs, 0, rt, extract32(ctx->opcode, 3, 5)); + break; + } + break; + case NM_CACHE: + check_cp0_enabled(ctx); + if (ctx->hflags & MIPS_HFLAG_ITC_CACHE) { + gen_cache_operation(ctx, rt, rs, s); + } + break; + } + break; + case NM_P_LS_WM: + case NM_P_LS_UAWM: + check_nms(ctx); + { + int count = extract32(ctx->opcode, 12, 3); + int counter = 0; + + offset = sextract32(ctx->opcode, 15, 1) << 8 | + extract32(ctx->opcode, 0, 8); + TCGv va = tcg_temp_new(); + TCGv t1 = tcg_temp_new(); + TCGMemOp memop = (extract32(ctx->opcode, 8, 3)) == + NM_P_LS_UAWM ? MO_UNALN : 0; + + count = (count == 0) ? 8 : count; + while (counter != count) { + int this_rt = ((rt + counter) & 0x1f) | (rt & 0x10); + int this_offset = offset + (counter << 2); + + gen_base_offset_addr(ctx, va, rs, this_offset); + + switch (extract32(ctx->opcode, 11, 1)) { + case NM_LWM: + tcg_gen_qemu_ld_tl(t1, va, ctx->mem_idx, + memop | MO_TESL); + gen_store_gpr(t1, this_rt); + if ((this_rt == rs) && + (counter != (count - 1))) { + /* UNPREDICTABLE */ + } + break; + case NM_SWM: + this_rt = (rt == 0) ? 0 : this_rt; + gen_load_gpr(t1, this_rt); + tcg_gen_qemu_st_tl(t1, va, ctx->mem_idx, + memop | MO_TEUL); + break; + } + counter++; + } + tcg_temp_free(va); + tcg_temp_free(t1); + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + } + break; + case NM_MOVE_BALC: + check_nms(ctx); + { + TCGv t0 = tcg_temp_new(); + int32_t s = sextract32(ctx->opcode, 0, 1) << 21 | + extract32(ctx->opcode, 1, 20) << 1; + rd = (extract32(ctx->opcode, 24, 1)) == 0 ? 4 : 5; + rt = decode_gpr_gpr4_zero(extract32(ctx->opcode, 25, 1) << 3 | + extract32(ctx->opcode, 21, 3)); + gen_load_gpr(t0, rt); + tcg_gen_mov_tl(cpu_gpr[rd], t0); + gen_compute_branch_nm(ctx, OPC_BGEZAL, 4, 0, 0, s); + tcg_temp_free(t0); + } + break; + case NM_P_BAL: + { + int32_t s = sextract32(ctx->opcode, 0, 1) << 25 | + extract32(ctx->opcode, 1, 24) << 1; + + if ((extract32(ctx->opcode, 25, 1)) == 0) { + /* BC */ + gen_compute_branch_nm(ctx, OPC_BEQ, 4, 0, 0, s); + } else { + /* BALC */ + gen_compute_branch_nm(ctx, OPC_BGEZAL, 4, 0, 0, s); + } + } + break; + case NM_P_J: + switch (extract32(ctx->opcode, 12, 4)) { + case NM_JALRC: + case NM_JALRC_HB: + gen_compute_branch_nm(ctx, OPC_JALR, 4, rs, rt, 0); + break; + case NM_P_BALRSC: + gen_compute_nanomips_pbalrsc_branch(ctx, rs, rt); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_P_BR1: + { + int32_t s = sextract32(ctx->opcode, 0, 1) << 14 | + extract32(ctx->opcode, 1, 13) << 1; + switch (extract32(ctx->opcode, 14, 2)) { + case NM_BEQC: + check_nms(ctx); + gen_compute_branch_nm(ctx, OPC_BEQ, 4, rs, rt, s); + break; + case NM_P_BR3A: + s = sextract32(ctx->opcode, 0, 1) << 14 | + extract32(ctx->opcode, 1, 13) << 1; + check_cp1_enabled(ctx); + switch (extract32(ctx->opcode, 16, 5)) { + case NM_BC1EQZC: + gen_compute_branch_cp1_nm(ctx, OPC_BC1EQZ, rt, s); + break; + case NM_BC1NEZC: + gen_compute_branch_cp1_nm(ctx, OPC_BC1NEZ, rt, s); + break; + case NM_BPOSGE32C: + check_dspr2(ctx); + { + int32_t imm = extract32(ctx->opcode, 1, 13) | + extract32(ctx->opcode, 0, 1) << 13; + + gen_compute_branch_nm(ctx, OPC_BPOSGE32, 4, -1, -2, + imm); + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_BGEC: + if (rs == rt) { + gen_compute_compact_branch_nm(ctx, OPC_BC, rs, rt, s); + } else { + gen_compute_compact_branch_nm(ctx, OPC_BGEC, rs, rt, s); + } + break; + case NM_BGEUC: + if (rs == rt || rt == 0) { + gen_compute_compact_branch_nm(ctx, OPC_BC, 0, 0, s); + } else if (rs == 0) { + gen_compute_compact_branch_nm(ctx, OPC_BEQZC, rt, 0, s); + } else { + gen_compute_compact_branch_nm(ctx, OPC_BGEUC, rs, rt, s); + } + break; + } + } + break; + case NM_P_BR2: + { + int32_t s = sextract32(ctx->opcode, 0, 1) << 14 | + extract32(ctx->opcode, 1, 13) << 1; + switch (extract32(ctx->opcode, 14, 2)) { + case NM_BNEC: + check_nms(ctx); + gen_compute_branch_nm(ctx, OPC_BNE, 4, rs, rt, s); + break; + case NM_BLTC: + if (rs != 0 && rt != 0 && rs == rt) { + /* NOP */ + ctx->hflags |= MIPS_HFLAG_FBNSLOT; + } else { + gen_compute_compact_branch_nm(ctx, OPC_BLTC, rs, rt, s); + } + break; + case NM_BLTUC: + if (rs == 0 || rs == rt) { + /* NOP */ + ctx->hflags |= MIPS_HFLAG_FBNSLOT; + } else { + gen_compute_compact_branch_nm(ctx, OPC_BLTUC, rs, rt, s); + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + } + break; + case NM_P_BRI: + { + int32_t s = sextract32(ctx->opcode, 0, 1) << 11 | + extract32(ctx->opcode, 1, 10) << 1; + uint32_t u = extract32(ctx->opcode, 11, 7); + + gen_compute_imm_branch(ctx, extract32(ctx->opcode, 18, 3), + rt, u, s); + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + return 4; +} + +static int decode_nanomips_opc(CPUMIPSState *env, DisasContext *ctx) +{ + uint32_t op; + int rt = decode_gpr_gpr3(NANOMIPS_EXTRACT_RD(ctx->opcode)); + int rs = decode_gpr_gpr3(NANOMIPS_EXTRACT_RS(ctx->opcode)); + int rd = decode_gpr_gpr3(NANOMIPS_EXTRACT_RS1(ctx->opcode)); + int offset; + int imm; + + /* make sure instructions are on a halfword boundary */ + if (ctx->base.pc_next & 0x1) { + TCGv tmp = tcg_const_tl(ctx->base.pc_next); + tcg_gen_st_tl(tmp, cpu_env, offsetof(CPUMIPSState, CP0_BadVAddr)); + tcg_temp_free(tmp); + generate_exception_end(ctx, EXCP_AdEL); + return 2; + } + + op = extract32(ctx->opcode, 10, 6); + switch (op) { + case NM_P16_MV: + rt = NANOMIPS_EXTRACT_RD5(ctx->opcode); + if (rt != 0) { + /* MOVE */ + rs = NANOMIPS_EXTRACT_RS5(ctx->opcode); + gen_arith(ctx, OPC_ADDU, rt, rs, 0); + } else { + /* P16.RI */ + switch (extract32(ctx->opcode, 3, 2)) { + case NM_P16_SYSCALL: + if (extract32(ctx->opcode, 2, 1) == 0) { + generate_exception_end(ctx, EXCP_SYSCALL); + } else { + generate_exception_end(ctx, EXCP_RI); + } + break; + case NM_BREAK16: + generate_exception_end(ctx, EXCP_BREAK); + break; + case NM_SDBBP16: + if (is_uhi(extract32(ctx->opcode, 0, 3))) { + gen_helper_do_semihosting(cpu_env); + } else { + if (ctx->hflags & MIPS_HFLAG_SBRI) { + generate_exception_end(ctx, EXCP_RI); + } else { + generate_exception_end(ctx, EXCP_DBp); + } + } + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + } + break; + case NM_P16_SHIFT: + { + int shift = extract32(ctx->opcode, 0, 3); + uint32_t opc = 0; + shift = (shift == 0) ? 8 : shift; + + switch (extract32(ctx->opcode, 3, 1)) { + case NM_SLL16: + opc = OPC_SLL; + break; + case NM_SRL16: + opc = OPC_SRL; + break; + } + gen_shift_imm(ctx, opc, rt, rs, shift); + } + break; + case NM_P16C: + switch (ctx->opcode & 1) { + case NM_POOL16C_0: + gen_pool16c_nanomips_insn(ctx); + break; + case NM_LWXS16: + gen_ldxs(ctx, rt, rs, rd); + break; + } + break; + case NM_P16_A1: + switch (extract32(ctx->opcode, 6, 1)) { + case NM_ADDIUR1SP: + imm = extract32(ctx->opcode, 0, 6) << 2; + gen_arith_imm(ctx, OPC_ADDIU, rt, 29, imm); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_P16_A2: + switch (extract32(ctx->opcode, 3, 1)) { + case NM_ADDIUR2: + imm = extract32(ctx->opcode, 0, 3) << 2; + gen_arith_imm(ctx, OPC_ADDIU, rt, rs, imm); + break; + case NM_P_ADDIURS5: + rt = extract32(ctx->opcode, 5, 5); + if (rt != 0) { + /* imm = sign_extend(s[3] . s[2:0] , from_nbits = 4) */ + imm = (sextract32(ctx->opcode, 4, 1) << 3) | + (extract32(ctx->opcode, 0, 3)); + gen_arith_imm(ctx, OPC_ADDIU, rt, rt, imm); + } + break; + } + break; + case NM_P16_ADDU: + switch (ctx->opcode & 0x1) { + case NM_ADDU16: + gen_arith(ctx, OPC_ADDU, rd, rs, rt); + break; + case NM_SUBU16: + gen_arith(ctx, OPC_SUBU, rd, rs, rt); + break; + } + break; + case NM_P16_4X4: + rt = (extract32(ctx->opcode, 9, 1) << 3) | + extract32(ctx->opcode, 5, 3); + rs = (extract32(ctx->opcode, 4, 1) << 3) | + extract32(ctx->opcode, 0, 3); + rt = decode_gpr_gpr4(rt); + rs = decode_gpr_gpr4(rs); + switch ((extract32(ctx->opcode, 7, 2) & 0x2) | + (extract32(ctx->opcode, 3, 1))) { + case NM_ADDU4X4: + check_nms(ctx); + gen_arith(ctx, OPC_ADDU, rt, rs, rt); + break; + case NM_MUL4X4: + check_nms(ctx); + gen_r6_muldiv(ctx, R6_OPC_MUL, rt, rs, rt); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_LI16: + { + int imm = extract32(ctx->opcode, 0, 7); + imm = (imm == 0x7f ? -1 : imm); + if (rt != 0) { + tcg_gen_movi_tl(cpu_gpr[rt], imm); + } + } + break; + case NM_ANDI16: + { + uint32_t u = extract32(ctx->opcode, 0, 4); + u = (u == 12) ? 0xff : + (u == 13) ? 0xffff : u; + gen_logic_imm(ctx, OPC_ANDI, rt, rs, u); + } + break; + case NM_P16_LB: + offset = extract32(ctx->opcode, 0, 2); + switch (extract32(ctx->opcode, 2, 2)) { + case NM_LB16: + gen_ld(ctx, OPC_LB, rt, rs, offset); + break; + case NM_SB16: + rt = decode_gpr_gpr3_src_store( + NANOMIPS_EXTRACT_RD(ctx->opcode)); + gen_st(ctx, OPC_SB, rt, rs, offset); + break; + case NM_LBU16: + gen_ld(ctx, OPC_LBU, rt, rs, offset); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_P16_LH: + offset = extract32(ctx->opcode, 1, 2) << 1; + switch ((extract32(ctx->opcode, 3, 1) << 1) | (ctx->opcode & 1)) { + case NM_LH16: + gen_ld(ctx, OPC_LH, rt, rs, offset); + break; + case NM_SH16: + rt = decode_gpr_gpr3_src_store( + NANOMIPS_EXTRACT_RD(ctx->opcode)); + gen_st(ctx, OPC_SH, rt, rs, offset); + break; + case NM_LHU16: + gen_ld(ctx, OPC_LHU, rt, rs, offset); + break; + default: + generate_exception_end(ctx, EXCP_RI); + break; + } + break; + case NM_LW16: + offset = extract32(ctx->opcode, 0, 4) << 2; + gen_ld(ctx, OPC_LW, rt, rs, offset); + break; + case NM_LWSP16: + rt = NANOMIPS_EXTRACT_RD5(ctx->opcode); + offset = extract32(ctx->opcode, 0, 5) << 2; + gen_ld(ctx, OPC_LW, rt, 29, offset); + break; + case NM_LW4X4: + check_nms(ctx); + rt = (extract32(ctx->opcode, 9, 1) << 3) | + extract32(ctx->opcode, 5, 3); + rs = (extract32(ctx->opcode, 4, 1) << 3) | + extract32(ctx->opcode, 0, 3); + offset = (extract32(ctx->opcode, 3, 1) << 3) | + (extract32(ctx->opcode, 8, 1) << 2); + rt = decode_gpr_gpr4(rt); + rs = decode_gpr_gpr4(rs); + gen_ld(ctx, OPC_LW, rt, rs, offset); + break; + case NM_SW4X4: + check_nms(ctx); + rt = (extract32(ctx->opcode, 9, 1) << 3) | + extract32(ctx->opcode, 5, 3); + rs = (extract32(ctx->opcode, 4, 1) << 3) | + extract32(ctx->opcode, 0, 3); + offset = (extract32(ctx->opcode, 3, 1) << 3) | + (extract32(ctx->opcode, 8, 1) << 2); + rt = decode_gpr_gpr4_zero(rt); + rs = decode_gpr_gpr4(rs); + gen_st(ctx, OPC_SW, rt, rs, offset); + break; + case NM_LWGP16: + offset = extract32(ctx->opcode, 0, 7) << 2; + gen_ld(ctx, OPC_LW, rt, 28, offset); + break; + case NM_SWSP16: + rt = NANOMIPS_EXTRACT_RD5(ctx->opcode); + offset = extract32(ctx->opcode, 0, 5) << 2; + gen_st(ctx, OPC_SW, rt, 29, offset); + break; + case NM_SW16: + rt = decode_gpr_gpr3_src_store( + NANOMIPS_EXTRACT_RD(ctx->opcode)); + rs = decode_gpr_gpr3(NANOMIPS_EXTRACT_RS(ctx->opcode)); + offset = extract32(ctx->opcode, 0, 4) << 2; + gen_st(ctx, OPC_SW, rt, rs, offset); + break; + case NM_SWGP16: + rt = decode_gpr_gpr3_src_store( + NANOMIPS_EXTRACT_RD(ctx->opcode)); + offset = extract32(ctx->opcode, 0, 7) << 2; + gen_st(ctx, OPC_SW, rt, 28, offset); + break; + case NM_BC16: + gen_compute_branch_nm(ctx, OPC_BEQ, 2, 0, 0, + (sextract32(ctx->opcode, 0, 1) << 10) | + (extract32(ctx->opcode, 1, 9) << 1)); + break; + case NM_BALC16: + gen_compute_branch_nm(ctx, OPC_BGEZAL, 2, 0, 0, + (sextract32(ctx->opcode, 0, 1) << 10) | + (extract32(ctx->opcode, 1, 9) << 1)); + break; + case NM_BEQZC16: + gen_compute_branch_nm(ctx, OPC_BEQ, 2, rt, 0, + (sextract32(ctx->opcode, 0, 1) << 7) | + (extract32(ctx->opcode, 1, 6) << 1)); + break; + case NM_BNEZC16: + gen_compute_branch_nm(ctx, OPC_BNE, 2, rt, 0, + (sextract32(ctx->opcode, 0, 1) << 7) | + (extract32(ctx->opcode, 1, 6) << 1)); + break; + case NM_P16_BR: + switch (ctx->opcode & 0xf) { + case 0: + /* P16.JRC */ + switch (extract32(ctx->opcode, 4, 1)) { + case NM_JRC: + gen_compute_branch_nm(ctx, OPC_JR, 2, + extract32(ctx->opcode, 5, 5), 0, 0); + break; + case NM_JALRC16: + gen_compute_branch_nm(ctx, OPC_JALR, 2, + extract32(ctx->opcode, 5, 5), 31, 0); + break; + } + break; + default: + { + /* P16.BRI */ + uint32_t opc = extract32(ctx->opcode, 4, 3) < + extract32(ctx->opcode, 7, 3) ? OPC_BEQ : OPC_BNE; + gen_compute_branch_nm(ctx, opc, 2, rs, rt, + extract32(ctx->opcode, 0, 4) << 1); + } + break; + } + break; + case NM_P16_SR: + { + int count = extract32(ctx->opcode, 0, 4); + int u = extract32(ctx->opcode, 4, 4) << 4; + + rt = 30 + extract32(ctx->opcode, 9, 1); + switch (extract32(ctx->opcode, 8, 1)) { + case NM_SAVE16: + gen_save(ctx, rt, count, 0, u); + break; + case NM_RESTORE_JRC16: + gen_restore(ctx, rt, count, 0, u); + gen_compute_branch_nm(ctx, OPC_JR, 2, 31, 0, 0); + break; + } + } + break; + case NM_MOVEP: + case NM_MOVEPREV: + check_nms(ctx); + { + static const int gpr2reg1[] = {4, 5, 6, 7}; + static const int gpr2reg2[] = {5, 6, 7, 8}; + int re; + int rd2 = extract32(ctx->opcode, 3, 1) << 1 | + extract32(ctx->opcode, 8, 1); + int r1 = gpr2reg1[rd2]; + int r2 = gpr2reg2[rd2]; + int r3 = extract32(ctx->opcode, 4, 1) << 3 | + extract32(ctx->opcode, 0, 3); + int r4 = extract32(ctx->opcode, 9, 1) << 3 | + extract32(ctx->opcode, 5, 3); + TCGv t0 = tcg_temp_new(); + TCGv t1 = tcg_temp_new(); + if (op == NM_MOVEP) { + rd = r1; + re = r2; + rs = decode_gpr_gpr4_zero(r3); + rt = decode_gpr_gpr4_zero(r4); + } else { + rd = decode_gpr_gpr4(r3); + re = decode_gpr_gpr4(r4); + rs = r1; + rt = r2; + } + gen_load_gpr(t0, rs); + gen_load_gpr(t1, rt); + tcg_gen_mov_tl(cpu_gpr[rd], t0); + tcg_gen_mov_tl(cpu_gpr[re], t1); + tcg_temp_free(t0); + tcg_temp_free(t1); + } + break; + default: + return decode_nanomips_32_48_opc(env, ctx); + } + + return 2; +} + + /* SmartMIPS extension to MIPS32 */ #if defined(TARGET_MIPS64) @@ -17901,7 +22739,7 @@ static void decode_opc_special3_r6(CPUMIPSState *env, DisasContext *ctx) switch (op2) { case OPC_ALIGN: case OPC_ALIGN_END: - gen_align(ctx, OPC_ALIGN, rd, rs, rt, sa & 3); + gen_align(ctx, 32, rd, rs, rt, sa & 3); break; case OPC_BITSWAP: gen_bitswap(ctx, op2, rd, rt); @@ -17927,7 +22765,7 @@ static void decode_opc_special3_r6(CPUMIPSState *env, DisasContext *ctx) switch (op2) { case OPC_DALIGN: case OPC_DALIGN_END: - gen_align(ctx, OPC_DALIGN, rd, rs, rt, sa & 7); + gen_align(ctx, 64, rd, rs, rt, sa & 7); break; case OPC_DBITSWAP: gen_bitswap(ctx, op2, rd, rt); @@ -18586,7 +23424,7 @@ static void decode_opc_special3(CPUMIPSState *env, DisasContext *ctx) gen_rdhwr(ctx, rt, rd, extract32(ctx->opcode, 6, 3)); break; case OPC_FORK: - check_insn(ctx, ASE_MT); + check_mt(ctx); { TCGv t0 = tcg_temp_new(); TCGv t1 = tcg_temp_new(); @@ -18599,7 +23437,7 @@ static void decode_opc_special3(CPUMIPSState *env, DisasContext *ctx) } break; case OPC_YIELD: - check_insn(ctx, ASE_MT); + check_mt(ctx); { TCGv t0 = tcg_temp_new(); @@ -19896,22 +24734,22 @@ static void decode_opc(CPUMIPSState *env, DisasContext *ctx) op2 = MASK_MFMC0(ctx->opcode); switch (op2) { case OPC_DMT: - check_insn(ctx, ASE_MT); + check_cp0_mt(ctx); gen_helper_dmt(t0); gen_store_gpr(t0, rt); break; case OPC_EMT: - check_insn(ctx, ASE_MT); + check_cp0_mt(ctx); gen_helper_emt(t0); gen_store_gpr(t0, rt); break; case OPC_DVPE: - check_insn(ctx, ASE_MT); + check_cp0_mt(ctx); gen_helper_dvpe(t0, cpu_env); gen_store_gpr(t0, rt); break; case OPC_EVPE: - check_insn(ctx, ASE_MT); + check_cp0_mt(ctx); gen_helper_evpe(t0, cpu_env); gen_store_gpr(t0, rt); break; @@ -20447,6 +25285,8 @@ static void mips_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) ctx->saved_pc = -1; ctx->insn_flags = env->insn_flags; ctx->CP0_Config1 = env->CP0_Config1; + ctx->CP0_Config3 = env->CP0_Config3; + ctx->CP0_Config5 = env->CP0_Config5; ctx->btarget = 0; ctx->kscrexist = (env->CP0_Config4 >> CP0C4_KScrExist) & 0xff; ctx->rxi = (env->CP0_Config3 >> CP0C3_RXI) & 1; @@ -20517,7 +25357,10 @@ static void mips_tr_translate_insn(DisasContextBase *dcbase, CPUState *cs) int is_slot; is_slot = ctx->hflags & MIPS_HFLAG_BMASK; - if (!(ctx->hflags & MIPS_HFLAG_M16)) { + if (ctx->insn_flags & ISA_NANOMIPS32) { + ctx->opcode = cpu_lduw_code(env, ctx->base.pc_next); + insn_bytes = decode_nanomips_opc(env, ctx); + } else if (!(ctx->hflags & MIPS_HFLAG_M16)) { ctx->opcode = cpu_ldl_code(env, ctx->base.pc_next); insn_bytes = 4; decode_opc(env, ctx); @@ -20956,8 +25799,8 @@ void cpu_state_reset(CPUMIPSState *env) env->CP0_Status |= (1 << CP0St_FR); } - if (env->CP0_Config3 & (1 << CP0C3_ISA)) { - /* microMIPS on reset when Config3.ISA == {1, 3} */ + if (env->CP0_Config3 & (1 << CP0C3_ISA) & (1 << (CP0C3_ISA + 1))) { + /* microMIPS on reset when Config3.ISA is 3 */ env->hflags |= MIPS_HFLAG_M16; } diff --git a/target/mips/translate_init.inc.c b/target/mips/translate_init.inc.c index c7ba6ee5f9..b3320b9dc7 100644 --- a/target/mips/translate_init.inc.c +++ b/target/mips/translate_init.inc.c @@ -449,6 +449,45 @@ const mips_def_t mips_defs[] = .insn_flags = CPU_MIPS32R6 | ASE_MICROMIPS, .mmu_type = MMU_TYPE_R4000, }, + { + .name = "I7200", + .CP0_PRid = 0x00010000, + .CP0_Config0 = MIPS_CONFIG0 | (1 << CP0C0_MM) | (0x2 << CP0C0_AR) | + (MMU_TYPE_R4000 << CP0C0_MT), + .CP0_Config1 = (1U << CP0C1_M) | (15 << CP0C1_MMU) | (2 << CP0C1_IS) | + (4 << CP0C1_IL) | (3 << CP0C1_IA) | (2 << CP0C1_DS) | + (4 << CP0C1_DL) | (3 << CP0C1_DA) | (1 << CP0C1_PC) | + (1 << CP0C1_EP), + .CP0_Config2 = MIPS_CONFIG2, + .CP0_Config3 = MIPS_CONFIG3 | (1U << CP0C3_M) | (1 << CP0C3_CMGCR) | + (1 << CP0C3_BI) | (1 << CP0C3_SC) | (3 << CP0C3_MMAR) | + (1 << CP0C3_ISA_ON_EXC) | (1 << CP0C3_ISA) | + (1 << CP0C3_ULRI) | (1 << CP0C3_RXI) | + (1 << CP0C3_DSP2P) | (1 << CP0C3_DSPP) | + (1 << CP0C3_CTXTC) | (1 << CP0C3_VInt) | + (1 << CP0C3_CDMM) | (1 << CP0C3_MT) | (1 << CP0C3_TL), + .CP0_Config4 = MIPS_CONFIG4 | (0xfc << CP0C4_KScrExist) | + (2 << CP0C4_IE) | (1U << CP0C4_M), + .CP0_Config5 = MIPS_CONFIG5 | (1 << CP0C5_MVH) | (1 << CP0C5_LLB), + .CP0_Config5_rw_bitmask = (1 << CP0C5_SBRI) | (1 << CP0C5_FRE) | + (1 << CP0C5_UFE), + .CP0_LLAddr_rw_bitmask = 0, + .CP0_LLAddr_shift = 0, + .SYNCI_Step = 32, + .CCRes = 2, + .CP0_Status_rw_bitmask = 0x3158FF1F, + .CP0_PageGrain = (1 << CP0PG_IEC) | (1 << CP0PG_XIE) | + (1U << CP0PG_RIE), + .CP0_PageGrain_rw_bitmask = 0, + .CP1_fcr0 = (1 << FCR0_FREP) | (1 << FCR0_HAS2008) | (1 << FCR0_F64) | + (1 << FCR0_L) | (1 << FCR0_W) | (1 << FCR0_D) | + (1 << FCR0_S) | (0x02 << FCR0_PRID) | (0x0 << FCR0_REV), + .CP1_fcr31 = (1 << FCR31_ABS2008) | (1 << FCR31_NAN2008), + .SEGBITS = 32, + .PABITS = 32, + .insn_flags = CPU_NANOMIPS32 | ASE_DSP | ASE_DSPR2 | ASE_MT, + .mmu_type = MMU_TYPE_R4000, + }, #if defined(TARGET_MIPS64) { .name = "R4000", |