diff options
30 files changed, 1626 insertions, 596 deletions
@@ -5424,7 +5424,7 @@ if test "$cpu" = "s390x" ; then write_c_skeleton compile_prog "-march=z900" "" has_z900=$? - if [ $has_z900 = 0 ] || compile_prog "-march=z10" ""; then + if [ $has_z900 = 0 ] || compile_object "-march=z10 -msoft-float -Werror"; then if [ $has_z900 != 0 ]; then echo "WARNING: Your compiler does not support the z900!" echo " The s390-ccw bios will only work with guest CPUs >= z10." diff --git a/hw/s390x/3270-ccw.c b/hw/s390x/3270-ccw.c index 13e93d8..69e6783 100644 --- a/hw/s390x/3270-ccw.c +++ b/hw/s390x/3270-ccw.c @@ -129,6 +129,7 @@ static void emulated_ccw_3270_realize(DeviceState *ds, Error **errp) EMULATED_CCW_3270_CHPID_TYPE); sch->do_subchannel_work = do_subchannel_work_virtual; sch->ccw_cb = emulated_ccw_3270_cb; + sch->irb_cb = build_irb_virtual; ck->init(dev, &err); if (err) { diff --git a/hw/s390x/css.c b/hw/s390x/css.c index bed46f5..133ddea 100644 --- a/hw/s390x/css.c +++ b/hw/s390x/css.c @@ -1335,6 +1335,14 @@ static void copy_schib_to_guest(SCHIB *dest, const SCHIB *src) } } +void copy_esw_to_guest(ESW *dest, const ESW *src) +{ + dest->word0 = cpu_to_be32(src->word0); + dest->erw = cpu_to_be32(src->erw); + dest->word2 = cpu_to_be64(src->word2); + dest->word4 = cpu_to_be32(src->word4); +} + IOInstEnding css_do_stsch(SubchDev *sch, SCHIB *schib) { int ret; @@ -1604,9 +1612,8 @@ static void copy_irb_to_guest(IRB *dest, const IRB *src, const PMCW *pmcw, copy_scsw_to_guest(&dest->scsw, &src->scsw); - for (i = 0; i < ARRAY_SIZE(dest->esw); i++) { - dest->esw[i] = cpu_to_be32(src->esw[i]); - } + copy_esw_to_guest(&dest->esw, &src->esw); + for (i = 0; i < ARRAY_SIZE(dest->ecw); i++) { dest->ecw[i] = cpu_to_be32(src->ecw[i]); } @@ -1632,6 +1639,55 @@ static void copy_irb_to_guest(IRB *dest, const IRB *src, const PMCW *pmcw, *irb_len = sizeof(*dest); } +static void build_irb_sense_data(SubchDev *sch, IRB *irb) +{ + int i; + + /* Attention: sense_data is already BE! */ + memcpy(irb->ecw, sch->sense_data, sizeof(sch->sense_data)); + for (i = 0; i < ARRAY_SIZE(irb->ecw); i++) { + irb->ecw[i] = be32_to_cpu(irb->ecw[i]); + } +} + +void build_irb_passthrough(SubchDev *sch, IRB *irb) +{ + /* Copy ESW from hardware */ + irb->esw = sch->esw; + + /* + * If (irb->esw.erw & ESW_ERW_SENSE) is true, then the contents + * of the ECW is sense data. If false, then it is model-dependent + * information. Either way, copy it into the IRB for the guest to + * read/decide what to do with. + */ + build_irb_sense_data(sch, irb); +} + +void build_irb_virtual(SubchDev *sch, IRB *irb) +{ + SCHIB *schib = &sch->curr_status; + uint16_t stctl = schib->scsw.ctrl & SCSW_CTRL_MASK_STCTL; + + if (stctl & SCSW_STCTL_STATUS_PEND) { + if (schib->scsw.cstat & (SCSW_CSTAT_DATA_CHECK | + SCSW_CSTAT_CHN_CTRL_CHK | + SCSW_CSTAT_INTF_CTRL_CHK)) { + irb->scsw.flags |= SCSW_FLAGS_MASK_ESWF; + irb->esw.word0 = 0x04804000; + } else { + irb->esw.word0 = 0x00800000; + } + /* If a unit check is pending, copy sense data. */ + if ((schib->scsw.dstat & SCSW_DSTAT_UNIT_CHECK) && + (schib->pmcw.chars & PMCW_CHARS_MASK_CSENSE)) { + irb->scsw.flags |= SCSW_FLAGS_MASK_ESWF | SCSW_FLAGS_MASK_ECTL; + build_irb_sense_data(sch, irb); + irb->esw.erw = ESW_ERW_SENSE | (sizeof(sch->sense_data) << 8); + } + } +} + int css_do_tsch_get_irb(SubchDev *sch, IRB *target_irb, int *irb_len) { SCHIB *schib = &sch->curr_status; @@ -1650,29 +1706,12 @@ int css_do_tsch_get_irb(SubchDev *sch, IRB *target_irb, int *irb_len) /* Copy scsw from current status. */ irb.scsw = schib->scsw; - if (stctl & SCSW_STCTL_STATUS_PEND) { - if (schib->scsw.cstat & (SCSW_CSTAT_DATA_CHECK | - SCSW_CSTAT_CHN_CTRL_CHK | - SCSW_CSTAT_INTF_CTRL_CHK)) { - irb.scsw.flags |= SCSW_FLAGS_MASK_ESWF; - irb.esw[0] = 0x04804000; - } else { - irb.esw[0] = 0x00800000; - } - /* If a unit check is pending, copy sense data. */ - if ((schib->scsw.dstat & SCSW_DSTAT_UNIT_CHECK) && - (schib->pmcw.chars & PMCW_CHARS_MASK_CSENSE)) { - int i; - irb.scsw.flags |= SCSW_FLAGS_MASK_ESWF | SCSW_FLAGS_MASK_ECTL; - /* Attention: sense_data is already BE! */ - memcpy(irb.ecw, sch->sense_data, sizeof(sch->sense_data)); - for (i = 0; i < ARRAY_SIZE(irb.ecw); i++) { - irb.ecw[i] = be32_to_cpu(irb.ecw[i]); - } - irb.esw[1] = 0x01000000 | (sizeof(sch->sense_data) << 8); - } + /* Build other IRB data, if necessary */ + if (sch->irb_cb) { + sch->irb_cb(sch, &irb); } + /* Store the irb to the guest. */ p = schib->pmcw; copy_irb_to_guest(target_irb, &irb, &p, irb_len); diff --git a/hw/s390x/s390-ccw.c b/hw/s390x/s390-ccw.c index c227c77..2fc8bb9 100644 --- a/hw/s390x/s390-ccw.c +++ b/hw/s390x/s390-ccw.c @@ -124,6 +124,7 @@ static void s390_ccw_realize(S390CCWDevice *cdev, char *sysfsdev, Error **errp) } sch->driver_data = cdev; sch->do_subchannel_work = do_subchannel_work_passthrough; + sch->irb_cb = build_irb_passthrough; ccw_dev->sch = sch; ret = css_sch_build_schib(sch, &cdev->hostid); diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index 7af27ca..e4b18ae 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -802,7 +802,10 @@ DEFINE_CCW_MACHINE(6_1, "6.1", true); static void ccw_machine_6_0_instance_options(MachineState *machine) { + static const S390FeatInit qemu_cpu_feat = { S390_FEAT_LIST_QEMU_V6_0 }; + ccw_machine_6_1_instance_options(machine); + s390_set_qemu_cpu_model(0x2964, 13, 2, qemu_cpu_feat); } static void ccw_machine_6_0_class_options(MachineClass *mc) diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c index 220b9ef..d68888f 100644 --- a/hw/s390x/virtio-ccw.c +++ b/hw/s390x/virtio-ccw.c @@ -753,6 +753,7 @@ static void virtio_ccw_device_realize(VirtioCcwDevice *dev, Error **errp) sch->id.reserved = 0xff; sch->id.cu_type = VIRTIO_CCW_CU_TYPE; sch->do_subchannel_work = do_subchannel_work_virtual; + sch->irb_cb = build_irb_virtual; ccw_dev->sch = sch; dev->indicators = NULL; dev->revision = -1; diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c index 139a3d9..000992f 100644 --- a/hw/vfio/ccw.c +++ b/hw/vfio/ccw.c @@ -321,6 +321,7 @@ static void vfio_ccw_io_notifier_handler(void *opaque) SCHIB *schib = &sch->curr_status; SCSW s; IRB irb; + ESW esw; int size; if (!event_notifier_test_and_clear(&vcdev->io_notifier)) { @@ -371,6 +372,9 @@ static void vfio_ccw_io_notifier_handler(void *opaque) copy_scsw_to_guest(&s, &irb.scsw); schib->scsw = s; + copy_esw_to_guest(&esw, &irb.esw); + sch->esw = esw; + /* If a uint check is pending, copy sense data. */ if ((schib->scsw.dstat & SCSW_DSTAT_UNIT_CHECK) && (schib->pmcw.chars & PMCW_CHARS_MASK_CSENSE)) { diff --git a/include/elf.h b/include/elf.h index 033bcc9..811bf4a 100644 --- a/include/elf.h +++ b/include/elf.h @@ -605,6 +605,13 @@ typedef struct { #define HWCAP_S390_HIGH_GPRS 512 #define HWCAP_S390_TE 1024 #define HWCAP_S390_VXRS 2048 +#define HWCAP_S390_VXRS_BCD 4096 +#define HWCAP_S390_VXRS_EXT 8192 +#define HWCAP_S390_GS 16384 +#define HWCAP_S390_VXRS_EXT2 32768 +#define HWCAP_S390_VXRS_PDE 65536 +#define HWCAP_S390_SORT 131072 +#define HWCAP_S390_DFLT 262144 /* M68K specific definitions. */ /* We use the top 24 bits to encode information about the diff --git a/include/hw/s390x/css.h b/include/hw/s390x/css.h index bba7593..10ed1df 100644 --- a/include/hw/s390x/css.h +++ b/include/hw/s390x/css.h @@ -138,8 +138,10 @@ struct SubchDev { int (*ccw_cb) (SubchDev *, CCW1); void (*disable_cb)(SubchDev *); IOInstEnding (*do_subchannel_work) (SubchDev *); + void (*irb_cb)(SubchDev *, IRB *); SenseId id; void *driver_data; + ESW esw; }; static inline void sch_gen_unit_exception(SubchDev *sch) @@ -201,6 +203,7 @@ int css_sch_build_schib(SubchDev *sch, CssDevId *dev_id); unsigned int css_find_free_chpid(uint8_t cssid); uint16_t css_build_subchannel_id(SubchDev *sch); void copy_scsw_to_guest(SCSW *dest, const SCSW *src); +void copy_esw_to_guest(ESW *dest, const ESW *src); void css_inject_io_interrupt(SubchDev *sch); void css_reset(void); void css_reset_sch(SubchDev *sch); @@ -215,6 +218,8 @@ void css_clear_sei_pending(void); IOInstEnding s390_ccw_cmd_request(SubchDev *sch); IOInstEnding do_subchannel_work_virtual(SubchDev *sub); IOInstEnding do_subchannel_work_passthrough(SubchDev *sub); +void build_irb_passthrough(SubchDev *sch, IRB *irb); +void build_irb_virtual(SubchDev *sch, IRB *irb); int s390_ccw_halt(SubchDev *sch); int s390_ccw_clear(SubchDev *sch); diff --git a/include/hw/s390x/ioinst.h b/include/hw/s390x/ioinst.h index c6737a3..3771fff 100644 --- a/include/hw/s390x/ioinst.h +++ b/include/hw/s390x/ioinst.h @@ -123,10 +123,20 @@ typedef struct SCHIB { uint8_t mda[4]; } QEMU_PACKED SCHIB; +/* format-0 extended-status word */ +typedef struct ESW { + uint32_t word0; /* subchannel logout for format 0 */ + uint32_t erw; + uint64_t word2; /* failing-storage address for format 0 */ + uint32_t word4; /* secondary-CCW address for format 0 */ +} QEMU_PACKED ESW; + +#define ESW_ERW_SENSE 0x01000000 + /* interruption response block */ typedef struct IRB { SCSW scsw; - uint32_t esw[5]; + ESW esw; uint32_t ecw[8]; uint32_t emw[8]; } IRB; diff --git a/linux-user/elfload.c b/linux-user/elfload.c index 17ab06f..4b01723 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -1376,6 +1376,7 @@ static uint32_t get_elf_hwcap(void) hwcap |= HWCAP_S390_ETF3EH; } GET_FEATURE(S390_FEAT_VECTOR, HWCAP_S390_VXRS); + GET_FEATURE(S390_FEAT_VECTOR_ENH, HWCAP_S390_VXRS_EXT); return hwcap; } diff --git a/linux-user/s390x/signal.c b/linux-user/s390x/signal.c index ef136da..bf8a8fb 100644 --- a/linux-user/s390x/signal.c +++ b/linux-user/s390x/signal.c @@ -112,15 +112,23 @@ get_sigframe(struct target_sigaction *ka, CPUS390XState *env, size_t frame_size) return (sp - frame_size) & -8ul; } +#define PSW_USER_BITS (PSW_MASK_DAT | PSW_MASK_IO | PSW_MASK_EXT | \ + PSW_MASK_MCHECK | PSW_MASK_PSTATE | PSW_ASC_PRIMARY) +#define PSW_MASK_USER (PSW_MASK_ASC | PSW_MASK_CC | PSW_MASK_PM | \ + PSW_MASK_64 | PSW_MASK_32) + static void save_sigregs(CPUS390XState *env, target_sigregs *sregs) { + uint64_t psw_mask = s390_cpu_get_psw_mask(env); int i; /* * Copy a 'clean' PSW mask to the user to avoid leaking * information about whether PER is currently on. + * TODO: qemu does not support PSW_MASK_RI; it will never be set. */ - __put_user(env->psw.mask, &sregs->regs.psw.mask); + psw_mask = PSW_USER_BITS | (psw_mask & PSW_MASK_USER); + __put_user(psw_mask, &sregs->regs.psw.mask); __put_user(env->psw.addr, &sregs->regs.psw.addr); for (i = 0; i < 16; i++) { @@ -289,7 +297,7 @@ void setup_rt_frame(int sig, struct target_sigaction *ka, static void restore_sigregs(CPUS390XState *env, target_sigregs *sc) { - target_ulong prev_addr; + uint64_t prev_addr, prev_mask, mask, addr; int i; for (i = 0; i < 16; i++) { @@ -297,9 +305,28 @@ static void restore_sigregs(CPUS390XState *env, target_sigregs *sc) } prev_addr = env->psw.addr; - __get_user(env->psw.mask, &sc->regs.psw.mask); - __get_user(env->psw.addr, &sc->regs.psw.addr); - trace_user_s390x_restore_sigregs(env, env->psw.addr, prev_addr); + __get_user(mask, &sc->regs.psw.mask); + __get_user(addr, &sc->regs.psw.addr); + trace_user_s390x_restore_sigregs(env, addr, prev_addr); + + /* + * Use current psw.mask to preserve PER bit. + * TODO: + * if (!is_ri_task(current) && (user_sregs.regs.psw.mask & PSW_MASK_RI)) + * return -EINVAL; + * Simply do not allow it to be set in mask. + */ + prev_mask = s390_cpu_get_psw_mask(env); + mask = (prev_mask & ~PSW_MASK_USER) | (mask & PSW_MASK_USER); + /* Check for invalid user address space control. */ + if ((mask & PSW_MASK_ASC) == PSW_ASC_HOME) { + mask = (mask & ~PSW_MASK_ASC) | PSW_ASC_PRIMARY; + } + /* Check for invalid amode. */ + if (mask & PSW_MASK_64) { + mask |= PSW_MASK_32; + } + s390_cpu_set_psw(env, mask, addr); for (i = 0; i < 16; i++) { __get_user(env->aregs[i], &sc->regs.acrs[i]); diff --git a/target/s390x/cc_helper.c b/target/s390x/cc_helper.c index e7039d0..e7a74d6 100644 --- a/target/s390x/cc_helper.c +++ b/target/s390x/cc_helper.c @@ -509,7 +509,7 @@ uint32_t HELPER(calc_cc)(CPUS390XState *env, uint32_t cc_op, uint64_t src, #ifndef CONFIG_USER_ONLY void HELPER(load_psw)(CPUS390XState *env, uint64_t mask, uint64_t addr) { - load_psw(env, mask, addr); + s390_cpu_set_psw(env, mask, addr); cpu_loop_exit(env_cpu(env)); } diff --git a/target/s390x/cpu.h b/target/s390x/cpu.h index 2464d40..b26ae8f 100644 --- a/target/s390x/cpu.h +++ b/target/s390x/cpu.h @@ -845,6 +845,9 @@ int s390_cpu_pv_mem_rw(S390CPU *cpu, unsigned int offset, void *hostbuf, int s390_cpu_restart(S390CPU *cpu); void s390_init_sigp(void); +/* helper.c */ +void s390_cpu_set_psw(CPUS390XState *env, uint64_t mask, uint64_t addr); +uint64_t s390_cpu_get_psw_mask(CPUS390XState *env); /* outside of target/s390x/ */ S390CPU *s390_cpu_addr2state(uint16_t cpu_addr); diff --git a/target/s390x/cpu_models.c b/target/s390x/cpu_models.c index 050dcf2..94090a6 100644 --- a/target/s390x/cpu_models.c +++ b/target/s390x/cpu_models.c @@ -90,8 +90,8 @@ static S390CPUDef s390_cpu_defs[] = { CPUDEF_INIT(0x8562, 15, 1, 47, 0x08000000U, "gen15b", "IBM z15 T02 GA1"), }; -#define QEMU_MAX_CPU_TYPE 0x2964 -#define QEMU_MAX_CPU_GEN 13 +#define QEMU_MAX_CPU_TYPE 0x3906 +#define QEMU_MAX_CPU_GEN 14 #define QEMU_MAX_CPU_EC_GA 2 static const S390FeatInit qemu_max_cpu_feat_init = { S390_FEAT_LIST_QEMU_MAX }; static S390FeatBitmap qemu_max_cpu_feat; diff --git a/target/s390x/excp_helper.c b/target/s390x/excp_helper.c index 20625c2..9c36142 100644 --- a/target/s390x/excp_helper.c +++ b/target/s390x/excp_helper.c @@ -252,7 +252,7 @@ static void do_program_interrupt(CPUS390XState *env) lowcore->pgm_ilen = cpu_to_be16(ilen); lowcore->pgm_code = cpu_to_be16(env->int_pgm_code); - lowcore->program_old_psw.mask = cpu_to_be64(get_psw_mask(env)); + lowcore->program_old_psw.mask = cpu_to_be64(s390_cpu_get_psw_mask(env)); lowcore->program_old_psw.addr = cpu_to_be64(env->psw.addr); mask = be64_to_cpu(lowcore->program_new_psw.mask); addr = be64_to_cpu(lowcore->program_new_psw.addr); @@ -260,7 +260,7 @@ static void do_program_interrupt(CPUS390XState *env) cpu_unmap_lowcore(lowcore); - load_psw(env, mask, addr); + s390_cpu_set_psw(env, mask, addr); } static void do_svc_interrupt(CPUS390XState *env) @@ -272,14 +272,14 @@ static void do_svc_interrupt(CPUS390XState *env) lowcore->svc_code = cpu_to_be16(env->int_svc_code); lowcore->svc_ilen = cpu_to_be16(env->int_svc_ilen); - lowcore->svc_old_psw.mask = cpu_to_be64(get_psw_mask(env)); + lowcore->svc_old_psw.mask = cpu_to_be64(s390_cpu_get_psw_mask(env)); lowcore->svc_old_psw.addr = cpu_to_be64(env->psw.addr + env->int_svc_ilen); mask = be64_to_cpu(lowcore->svc_new_psw.mask); addr = be64_to_cpu(lowcore->svc_new_psw.addr); cpu_unmap_lowcore(lowcore); - load_psw(env, mask, addr); + s390_cpu_set_psw(env, mask, addr); /* When a PER event is pending, the PER exception has to happen immediately after the SERVICE CALL one. */ @@ -348,12 +348,12 @@ static void do_ext_interrupt(CPUS390XState *env) mask = be64_to_cpu(lowcore->external_new_psw.mask); addr = be64_to_cpu(lowcore->external_new_psw.addr); - lowcore->external_old_psw.mask = cpu_to_be64(get_psw_mask(env)); + lowcore->external_old_psw.mask = cpu_to_be64(s390_cpu_get_psw_mask(env)); lowcore->external_old_psw.addr = cpu_to_be64(env->psw.addr); cpu_unmap_lowcore(lowcore); - load_psw(env, mask, addr); + s390_cpu_set_psw(env, mask, addr); } static void do_io_interrupt(CPUS390XState *env) @@ -373,7 +373,7 @@ static void do_io_interrupt(CPUS390XState *env) lowcore->subchannel_nr = cpu_to_be16(io->nr); lowcore->io_int_parm = cpu_to_be32(io->parm); lowcore->io_int_word = cpu_to_be32(io->word); - lowcore->io_old_psw.mask = cpu_to_be64(get_psw_mask(env)); + lowcore->io_old_psw.mask = cpu_to_be64(s390_cpu_get_psw_mask(env)); lowcore->io_old_psw.addr = cpu_to_be64(env->psw.addr); mask = be64_to_cpu(lowcore->io_new_psw.mask); addr = be64_to_cpu(lowcore->io_new_psw.addr); @@ -381,7 +381,7 @@ static void do_io_interrupt(CPUS390XState *env) cpu_unmap_lowcore(lowcore); g_free(io); - load_psw(env, mask, addr); + s390_cpu_set_psw(env, mask, addr); } typedef struct MchkExtSaveArea { @@ -457,14 +457,14 @@ static void do_mchk_interrupt(CPUS390XState *env) lowcore->clock_comp_save_area = cpu_to_be64(env->ckc >> 8); lowcore->mcic = cpu_to_be64(mcic); - lowcore->mcck_old_psw.mask = cpu_to_be64(get_psw_mask(env)); + lowcore->mcck_old_psw.mask = cpu_to_be64(s390_cpu_get_psw_mask(env)); lowcore->mcck_old_psw.addr = cpu_to_be64(env->psw.addr); mask = be64_to_cpu(lowcore->mcck_new_psw.mask); addr = be64_to_cpu(lowcore->mcck_new_psw.addr); cpu_unmap_lowcore(lowcore); - load_psw(env, mask, addr); + s390_cpu_set_psw(env, mask, addr); } void s390_cpu_do_interrupt(CPUState *cs) @@ -592,9 +592,11 @@ void s390x_cpu_debug_excp_handler(CPUState *cs) and MVCS instrutions are not used. */ env->per_perc_atmid |= env->psw.mask & (PSW_MASK_ASC) >> 46; - /* Remove all watchpoints to re-execute the code. A PER exception - will be triggered, it will call load_psw which will recompute - the watchpoints. */ + /* + * Remove all watchpoints to re-execute the code. A PER exception + * will be triggered, it will call s390_cpu_set_psw which will + * recompute the watchpoints. + */ cpu_watchpoint_remove_all(cs, BP_CPU); cpu_loop_exit_noexc(cs); } diff --git a/target/s390x/fpu_helper.c b/target/s390x/fpu_helper.c index f155bc0..13af158 100644 --- a/target/s390x/fpu_helper.c +++ b/target/s390x/fpu_helper.c @@ -509,6 +509,9 @@ uint64_t HELPER(cgeb)(CPUS390XState *env, uint64_t v2, uint32_t m34) s390_restore_bfp_rounding_mode(env, old_mode); handle_exceptions(env, xxc_from_m34(m34), GETPC()); + if (float32_is_any_nan(v2)) { + return INT64_MIN; + } return ret; } @@ -520,6 +523,9 @@ uint64_t HELPER(cgdb)(CPUS390XState *env, uint64_t v2, uint32_t m34) s390_restore_bfp_rounding_mode(env, old_mode); handle_exceptions(env, xxc_from_m34(m34), GETPC()); + if (float64_is_any_nan(v2)) { + return INT64_MIN; + } return ret; } @@ -532,6 +538,9 @@ uint64_t HELPER(cgxb)(CPUS390XState *env, uint64_t h, uint64_t l, uint32_t m34) s390_restore_bfp_rounding_mode(env, old_mode); handle_exceptions(env, xxc_from_m34(m34), GETPC()); + if (float128_is_any_nan(v2)) { + return INT64_MIN; + } return ret; } @@ -543,6 +552,9 @@ uint64_t HELPER(cfeb)(CPUS390XState *env, uint64_t v2, uint32_t m34) s390_restore_bfp_rounding_mode(env, old_mode); handle_exceptions(env, xxc_from_m34(m34), GETPC()); + if (float32_is_any_nan(v2)) { + return INT32_MIN; + } return ret; } @@ -554,6 +566,9 @@ uint64_t HELPER(cfdb)(CPUS390XState *env, uint64_t v2, uint32_t m34) s390_restore_bfp_rounding_mode(env, old_mode); handle_exceptions(env, xxc_from_m34(m34), GETPC()); + if (float64_is_any_nan(v2)) { + return INT32_MIN; + } return ret; } @@ -566,6 +581,9 @@ uint64_t HELPER(cfxb)(CPUS390XState *env, uint64_t h, uint64_t l, uint32_t m34) s390_restore_bfp_rounding_mode(env, old_mode); handle_exceptions(env, xxc_from_m34(m34), GETPC()); + if (float128_is_any_nan(v2)) { + return INT32_MIN; + } return ret; } @@ -573,12 +591,12 @@ uint64_t HELPER(cfxb)(CPUS390XState *env, uint64_t h, uint64_t l, uint32_t m34) uint64_t HELPER(clgeb)(CPUS390XState *env, uint64_t v2, uint32_t m34) { int old_mode = s390_swap_bfp_rounding_mode(env, round_from_m34(m34)); - uint64_t ret; - - v2 = float32_to_float64(v2, &env->fpu_status); - ret = float64_to_uint64(v2, &env->fpu_status); + uint64_t ret = float32_to_uint64(v2, &env->fpu_status); s390_restore_bfp_rounding_mode(env, old_mode); handle_exceptions(env, xxc_from_m34(m34), GETPC()); + if (float32_is_any_nan(v2)) { + return 0; + } return ret; } @@ -590,6 +608,9 @@ uint64_t HELPER(clgdb)(CPUS390XState *env, uint64_t v2, uint32_t m34) s390_restore_bfp_rounding_mode(env, old_mode); handle_exceptions(env, xxc_from_m34(m34), GETPC()); + if (float64_is_any_nan(v2)) { + return 0; + } return ret; } @@ -601,6 +622,9 @@ uint64_t HELPER(clgxb)(CPUS390XState *env, uint64_t h, uint64_t l, uint32_t m34) s390_restore_bfp_rounding_mode(env, old_mode); handle_exceptions(env, xxc_from_m34(m34), GETPC()); + if (float128_is_any_nan(make_float128(h, l))) { + return 0; + } return ret; } @@ -612,6 +636,9 @@ uint64_t HELPER(clfeb)(CPUS390XState *env, uint64_t v2, uint32_t m34) s390_restore_bfp_rounding_mode(env, old_mode); handle_exceptions(env, xxc_from_m34(m34), GETPC()); + if (float32_is_any_nan(v2)) { + return 0; + } return ret; } @@ -623,6 +650,9 @@ uint64_t HELPER(clfdb)(CPUS390XState *env, uint64_t v2, uint32_t m34) s390_restore_bfp_rounding_mode(env, old_mode); handle_exceptions(env, xxc_from_m34(m34), GETPC()); + if (float64_is_any_nan(v2)) { + return 0; + } return ret; } @@ -634,6 +664,9 @@ uint64_t HELPER(clfxb)(CPUS390XState *env, uint64_t h, uint64_t l, uint32_t m34) s390_restore_bfp_rounding_mode(env, old_mode); handle_exceptions(env, xxc_from_m34(m34), GETPC()); + if (float128_is_any_nan(make_float128(h, l))) { + return 0; + } return ret; } diff --git a/target/s390x/gdbstub.c b/target/s390x/gdbstub.c index d6fce5f..5b4e38a 100644 --- a/target/s390x/gdbstub.c +++ b/target/s390x/gdbstub.c @@ -31,18 +31,10 @@ int s390_cpu_gdb_read_register(CPUState *cs, GByteArray *mem_buf, int n) { S390CPU *cpu = S390_CPU(cs); CPUS390XState *env = &cpu->env; - uint64_t val; - int cc_op; switch (n) { case S390_PSWM_REGNUM: - if (tcg_enabled()) { - cc_op = calc_cc(env, env->cc_op, env->cc_src, env->cc_dst, - env->cc_vr); - val = deposit64(env->psw.mask, 44, 2, cc_op); - return gdb_get_regl(mem_buf, val); - } - return gdb_get_regl(mem_buf, env->psw.mask); + return gdb_get_regl(mem_buf, s390_cpu_get_psw_mask(env)); case S390_PSWA_REGNUM: return gdb_get_regl(mem_buf, env->psw.addr); case S390_R0_REGNUM ... S390_R15_REGNUM: @@ -59,10 +51,7 @@ int s390_cpu_gdb_write_register(CPUState *cs, uint8_t *mem_buf, int n) switch (n) { case S390_PSWM_REGNUM: - env->psw.mask = tmpl; - if (tcg_enabled()) { - env->cc_op = extract64(tmpl, 44, 2); - } + s390_cpu_set_psw(env, tmpl, env->psw.addr); break; case S390_PSWA_REGNUM: env->psw.addr = tmpl; diff --git a/target/s390x/gen-features.c b/target/s390x/gen-features.c index a6ec918..242c95e 100644 --- a/target/s390x/gen-features.c +++ b/target/s390x/gen-features.c @@ -706,20 +706,23 @@ static uint16_t qemu_V4_1[] = { S390_FEAT_VECTOR, }; -static uint16_t qemu_LATEST[] = { +static uint16_t qemu_V6_0[] = { S390_FEAT_ACCESS_EXCEPTION_FS_INDICATION, S390_FEAT_SIDE_EFFECT_ACCESS_ESOP2, S390_FEAT_ESOP, }; +static uint16_t qemu_LATEST[] = { + S390_FEAT_INSTRUCTION_EXEC_PROT, + S390_FEAT_MISC_INSTRUCTION_EXT2, + S390_FEAT_MSA_EXT_8, + S390_FEAT_VECTOR_ENH, +}; + /* add all new definitions before this point */ static uint16_t qemu_MAX[] = { /* generates a dependency warning, leave it out for now */ S390_FEAT_MSA_EXT_5, - /* features introduced after the z13 */ - S390_FEAT_INSTRUCTION_EXEC_PROT, - S390_FEAT_MISC_INSTRUCTION_EXT2, - S390_FEAT_MSA_EXT_8, }; /****** END FEATURE DEFS ******/ @@ -838,6 +841,7 @@ static FeatGroupDefSpec QemuFeatDef[] = { QEMU_FEAT_INITIALIZER(V3_1), QEMU_FEAT_INITIALIZER(V4_0), QEMU_FEAT_INITIALIZER(V4_1), + QEMU_FEAT_INITIALIZER(V6_0), QEMU_FEAT_INITIALIZER(LATEST), QEMU_FEAT_INITIALIZER(MAX), }; diff --git a/target/s390x/helper.c b/target/s390x/helper.c index 7678994..1445b74 100644 --- a/target/s390x/helper.c +++ b/target/s390x/helper.c @@ -104,44 +104,6 @@ void s390_handle_wait(S390CPU *cpu) } } -void load_psw(CPUS390XState *env, uint64_t mask, uint64_t addr) -{ - uint64_t old_mask = env->psw.mask; - - env->psw.addr = addr; - env->psw.mask = mask; - - /* KVM will handle all WAITs and trigger a WAIT exit on disabled_wait */ - if (!tcg_enabled()) { - return; - } - env->cc_op = (mask >> 44) & 3; - - if ((old_mask ^ mask) & PSW_MASK_PER) { - s390_cpu_recompute_watchpoints(env_cpu(env)); - } - - if (mask & PSW_MASK_WAIT) { - s390_handle_wait(env_archcpu(env)); - } -} - -uint64_t get_psw_mask(CPUS390XState *env) -{ - uint64_t r = env->psw.mask; - - if (tcg_enabled()) { - env->cc_op = calc_cc(env, env->cc_op, env->cc_src, env->cc_dst, - env->cc_vr); - - r &= ~PSW_MASK_CC; - assert(!(env->cc_op & ~3)); - r |= (uint64_t)env->cc_op << 44; - } - - return r; -} - LowCore *cpu_map_lowcore(CPUS390XState *env) { LowCore *lowcore; @@ -168,7 +130,7 @@ void do_restart_interrupt(CPUS390XState *env) lowcore = cpu_map_lowcore(env); - lowcore->restart_old_psw.mask = cpu_to_be64(get_psw_mask(env)); + lowcore->restart_old_psw.mask = cpu_to_be64(s390_cpu_get_psw_mask(env)); lowcore->restart_old_psw.addr = cpu_to_be64(env->psw.addr); mask = be64_to_cpu(lowcore->restart_new_psw.mask); addr = be64_to_cpu(lowcore->restart_new_psw.addr); @@ -176,7 +138,7 @@ void do_restart_interrupt(CPUS390XState *env) cpu_unmap_lowcore(lowcore); env->pending_int &= ~INTERRUPT_RESTART; - load_psw(env, mask, addr); + s390_cpu_set_psw(env, mask, addr); } void s390_cpu_recompute_watchpoints(CPUState *cs) @@ -266,7 +228,7 @@ int s390_store_status(S390CPU *cpu, hwaddr addr, bool store_arch) sa->grs[i] = cpu_to_be64(cpu->env.regs[i]); } sa->psw.addr = cpu_to_be64(cpu->env.psw.addr); - sa->psw.mask = cpu_to_be64(get_psw_mask(&cpu->env)); + sa->psw.mask = cpu_to_be64(s390_cpu_get_psw_mask(&cpu->env)); sa->prefix = cpu_to_be32(cpu->env.psa); sa->fpc = cpu_to_be32(cpu->env.fpc); sa->todpr = cpu_to_be32(cpu->env.todpr); @@ -323,20 +285,67 @@ int s390_store_adtl_status(S390CPU *cpu, hwaddr addr, hwaddr len) cpu_physical_memory_unmap(sa, len, 1, len); return 0; } +#else +/* For user-only, tcg is always enabled. */ +#define tcg_enabled() true #endif /* CONFIG_USER_ONLY */ +void s390_cpu_set_psw(CPUS390XState *env, uint64_t mask, uint64_t addr) +{ +#ifndef CONFIG_USER_ONLY + uint64_t old_mask = env->psw.mask; +#endif + + env->psw.addr = addr; + env->psw.mask = mask; + + /* KVM will handle all WAITs and trigger a WAIT exit on disabled_wait */ + if (!tcg_enabled()) { + return; + } + env->cc_op = (mask >> 44) & 3; + +#ifndef CONFIG_USER_ONLY + if ((old_mask ^ mask) & PSW_MASK_PER) { + s390_cpu_recompute_watchpoints(env_cpu(env)); + } + + if (mask & PSW_MASK_WAIT) { + s390_handle_wait(env_archcpu(env)); + } +#endif +} + +uint64_t s390_cpu_get_psw_mask(CPUS390XState *env) +{ + uint64_t r = env->psw.mask; + + if (tcg_enabled()) { + uint64_t cc = calc_cc(env, env->cc_op, env->cc_src, + env->cc_dst, env->cc_vr); + + assert(cc <= 3); + r &= ~PSW_MASK_CC; + r |= cc << 44; + } + + return r; +} + void s390_cpu_dump_state(CPUState *cs, FILE *f, int flags) { S390CPU *cpu = S390_CPU(cs); CPUS390XState *env = &cpu->env; int i; - if (env->cc_op > 3) { - qemu_fprintf(f, "PSW=mask %016" PRIx64 " addr %016" PRIx64 " cc %15s\n", - env->psw.mask, env->psw.addr, cc_name(env->cc_op)); + qemu_fprintf(f, "PSW=mask %016" PRIx64 " addr %016" PRIx64, + s390_cpu_get_psw_mask(env), env->psw.addr); + if (!tcg_enabled()) { + qemu_fprintf(f, "\n"); + } else if (env->cc_op > 3) { + qemu_fprintf(f, " cc %15s\n", cc_name(env->cc_op)); } else { - qemu_fprintf(f, "PSW=mask %016" PRIx64 " addr %016" PRIx64 " cc %02x\n", - env->psw.mask, env->psw.addr, env->cc_op); + qemu_fprintf(f, " cc %02x\n", env->cc_op); } for (i = 0; i < 16; i++) { diff --git a/target/s390x/helper.h b/target/s390x/helper.h index d4e4f33..ba045f5 100644 --- a/target/s390x/helper.h +++ b/target/s390x/helper.h @@ -126,6 +126,7 @@ DEF_HELPER_FLAGS_1(stck, TCG_CALL_NO_RWG_SE, i64, env) DEF_HELPER_FLAGS_3(probe_write_access, TCG_CALL_NO_WG, void, env, i64, i64) /* === Vector Support Instructions === */ +DEF_HELPER_FLAGS_4(gvec_vbperm, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32) DEF_HELPER_FLAGS_4(vll, TCG_CALL_NO_WG, void, env, ptr, i64, i64) DEF_HELPER_FLAGS_4(gvec_vpk16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32) DEF_HELPER_FLAGS_4(gvec_vpk32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32) @@ -246,50 +247,77 @@ DEF_HELPER_6(gvec_vstrc_cc_rt16, void, ptr, cptr, cptr, cptr, env, i32) DEF_HELPER_6(gvec_vstrc_cc_rt32, void, ptr, cptr, cptr, cptr, env, i32) /* === Vector Floating-Point Instructions */ +DEF_HELPER_FLAGS_5(gvec_vfa32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) DEF_HELPER_FLAGS_5(gvec_vfa64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) -DEF_HELPER_FLAGS_5(gvec_vfa64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfa128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_4(gvec_wfc32, void, cptr, cptr, env, i32) +DEF_HELPER_4(gvec_wfk32, void, cptr, cptr, env, i32) DEF_HELPER_4(gvec_wfc64, void, cptr, cptr, env, i32) DEF_HELPER_4(gvec_wfk64, void, cptr, cptr, env, i32) +DEF_HELPER_4(gvec_wfc128, void, cptr, cptr, env, i32) +DEF_HELPER_4(gvec_wfk128, void, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfce32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_5(gvec_vfce32_cc, void, ptr, cptr, cptr, env, i32) DEF_HELPER_FLAGS_5(gvec_vfce64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) -DEF_HELPER_FLAGS_5(gvec_vfce64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) DEF_HELPER_5(gvec_vfce64_cc, void, ptr, cptr, cptr, env, i32) -DEF_HELPER_5(gvec_vfce64s_cc, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfce128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_5(gvec_vfce128_cc, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfch32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_5(gvec_vfch32_cc, void, ptr, cptr, cptr, env, i32) DEF_HELPER_FLAGS_5(gvec_vfch64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) -DEF_HELPER_FLAGS_5(gvec_vfch64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) DEF_HELPER_5(gvec_vfch64_cc, void, ptr, cptr, cptr, env, i32) -DEF_HELPER_5(gvec_vfch64s_cc, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfch128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_5(gvec_vfch128_cc, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfche32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_5(gvec_vfche32_cc, void, ptr, cptr, cptr, env, i32) DEF_HELPER_FLAGS_5(gvec_vfche64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) -DEF_HELPER_FLAGS_5(gvec_vfche64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) DEF_HELPER_5(gvec_vfche64_cc, void, ptr, cptr, cptr, env, i32) -DEF_HELPER_5(gvec_vfche64s_cc, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfche128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_5(gvec_vfche128_cc, void, ptr, cptr, cptr, env, i32) DEF_HELPER_FLAGS_4(gvec_vcdg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) -DEF_HELPER_FLAGS_4(gvec_vcdg64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) DEF_HELPER_FLAGS_4(gvec_vcdlg64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) -DEF_HELPER_FLAGS_4(gvec_vcdlg64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) DEF_HELPER_FLAGS_4(gvec_vcgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) -DEF_HELPER_FLAGS_4(gvec_vcgd64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) DEF_HELPER_FLAGS_4(gvec_vclgd64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) -DEF_HELPER_FLAGS_4(gvec_vclgd64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfd32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) DEF_HELPER_FLAGS_5(gvec_vfd64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) -DEF_HELPER_FLAGS_5(gvec_vfd64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfd128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_4(gvec_vfi32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) DEF_HELPER_FLAGS_4(gvec_vfi64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) -DEF_HELPER_FLAGS_4(gvec_vfi64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) +DEF_HELPER_FLAGS_4(gvec_vfi128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) DEF_HELPER_FLAGS_4(gvec_vfll32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) -DEF_HELPER_FLAGS_4(gvec_vfll32s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) +DEF_HELPER_FLAGS_4(gvec_vfll64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) DEF_HELPER_FLAGS_4(gvec_vflr64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) -DEF_HELPER_FLAGS_4(gvec_vflr64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) +DEF_HELPER_FLAGS_4(gvec_vflr128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfm32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) DEF_HELPER_FLAGS_5(gvec_vfm64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) -DEF_HELPER_FLAGS_5(gvec_vfm64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfm128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfmax32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfmax64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfmax128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfmin32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfmin64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfmin128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_6(gvec_vfma32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32) DEF_HELPER_FLAGS_6(gvec_vfma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32) -DEF_HELPER_FLAGS_6(gvec_vfma64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_6(gvec_vfma128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_6(gvec_vfms32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32) DEF_HELPER_FLAGS_6(gvec_vfms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32) -DEF_HELPER_FLAGS_6(gvec_vfms64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_6(gvec_vfms128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_6(gvec_vfnma32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_6(gvec_vfnma64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_6(gvec_vfnma128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_6(gvec_vfnms32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_6(gvec_vfnms64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_6(gvec_vfnms128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_4(gvec_vfsq32, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) DEF_HELPER_FLAGS_4(gvec_vfsq64, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) -DEF_HELPER_FLAGS_4(gvec_vfsq64s, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) +DEF_HELPER_FLAGS_4(gvec_vfsq128, TCG_CALL_NO_WG, void, ptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfs32, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) DEF_HELPER_FLAGS_5(gvec_vfs64, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) -DEF_HELPER_FLAGS_5(gvec_vfs64s, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_FLAGS_5(gvec_vfs128, TCG_CALL_NO_WG, void, ptr, cptr, cptr, env, i32) +DEF_HELPER_4(gvec_vftci32, void, ptr, cptr, env, i32) DEF_HELPER_4(gvec_vftci64, void, ptr, cptr, env, i32) -DEF_HELPER_4(gvec_vftci64s, void, ptr, cptr, env, i32) +DEF_HELPER_4(gvec_vftci128, void, ptr, cptr, env, i32) #ifndef CONFIG_USER_ONLY DEF_HELPER_3(servc, i32, env, i64, i64) diff --git a/target/s390x/insn-data.def b/target/s390x/insn-data.def index 0bb1886..3e55942 100644 --- a/target/s390x/insn-data.def +++ b/target/s390x/insn-data.def @@ -989,6 +989,8 @@ /* === Vector Support Instructions === */ +/* VECTOR BIT PERMUTE */ + E(0xe785, VBPERM, VRR_c, VE, 0, 0, 0, 0, vbperm, 0, 0, IF_VEC) /* VECTOR GATHER ELEMENT */ E(0xe713, VGEF, VRV, V, la2, 0, 0, 0, vge, 0, ES_32, IF_VEC) E(0xe712, VGEG, VRV, V, la2, 0, 0, 0, vge, 0, ES_64, IF_VEC) @@ -1149,6 +1151,8 @@ F(0xe7a7, VMO, VRR_c, V, 0, 0, 0, 0, vm, 0, IF_VEC) /* VECTOR MULTIPLY LOGICAL ODD */ F(0xe7a5, VMLO, VRR_c, V, 0, 0, 0, 0, vm, 0, IF_VEC) +/* VECTOR MULTIPLY SUM LOGICAL */ + F(0xe7b8, VMSL, VRR_d, VE, 0, 0, 0, 0, vmsl, 0, IF_VEC) /* VECTOR NAND */ F(0xe76e, VNN, VRR_c, VE, 0, 0, 0, 0, vnn, 0, IF_VEC) /* VECTOR NOR */ @@ -1245,16 +1249,24 @@ F(0xe7e5, VFD, VRR_c, V, 0, 0, 0, 0, vfa, 0, IF_VEC) /* VECTOR LOAD FP INTEGER */ F(0xe7c7, VFI, VRR_a, V, 0, 0, 0, 0, vcdg, 0, IF_VEC) -/* VECTOR LOAD LENGTHENED */ +/* VECTOR FP LOAD LENGTHENED */ F(0xe7c4, VFLL, VRR_a, V, 0, 0, 0, 0, vfll, 0, IF_VEC) -/* VECTOR LOAD ROUNDED */ +/* VECTOR FP LOAD ROUNDED */ F(0xe7c5, VFLR, VRR_a, V, 0, 0, 0, 0, vcdg, 0, IF_VEC) +/* VECTOR FP MAXIMUM */ + F(0xe7ef, VFMAX, VRR_c, VE, 0, 0, 0, 0, vfmax, 0, IF_VEC) +/* VECTOR FP MINIMUM */ + F(0xe7ee, VFMIN, VRR_c, VE, 0, 0, 0, 0, vfmax, 0, IF_VEC) /* VECTOR FP MULTIPLY */ F(0xe7e7, VFM, VRR_c, V, 0, 0, 0, 0, vfa, 0, IF_VEC) /* VECTOR FP MULTIPLY AND ADD */ F(0xe78f, VFMA, VRR_e, V, 0, 0, 0, 0, vfma, 0, IF_VEC) /* VECTOR FP MULTIPLY AND SUBTRACT */ F(0xe78e, VFMS, VRR_e, V, 0, 0, 0, 0, vfma, 0, IF_VEC) +/* VECTOR FP NEGATIVE MULTIPLY AND ADD */ + F(0xe79f, VFNMA, VRR_e, VE, 0, 0, 0, 0, vfma, 0, IF_VEC) +/* VECTOR FP NEGATIVE MULTIPLY AND SUBTRACT */ + F(0xe79e, VFNMS, VRR_e, VE, 0, 0, 0, 0, vfma, 0, IF_VEC) /* VECTOR FP PERFORM SIGN OPERATION */ F(0xe7cc, VFPSO, VRR_a, V, 0, 0, 0, 0, vfpso, 0, IF_VEC) /* VECTOR FP SQUARE ROOT */ diff --git a/target/s390x/internal.h b/target/s390x/internal.h index 11515bb..9256275 100644 --- a/target/s390x/internal.h +++ b/target/s390x/internal.h @@ -235,10 +235,6 @@ int s390_cpu_write_elf64_note(WriteCoreDumpFunction f, CPUState *cs, const char *cc_name(enum cc_op cc_op); uint32_t calc_cc(CPUS390XState *env, uint32_t cc_op, uint64_t src, uint64_t dst, uint64_t vr); -#ifndef CONFIG_USER_ONLY -void load_psw(CPUS390XState *env, uint64_t mask, uint64_t addr); -#endif /* CONFIG_USER_ONLY */ - /* cpu.c */ #ifndef CONFIG_USER_ONLY @@ -288,6 +284,15 @@ uint8_t s390_softfloat_exc_to_ieee(unsigned int exc); int s390_swap_bfp_rounding_mode(CPUS390XState *env, int m3); void s390_restore_bfp_rounding_mode(CPUS390XState *env, int old_mode); int float_comp_to_cc(CPUS390XState *env, int float_compare); + +#define DCMASK_ZERO 0x0c00 +#define DCMASK_NORMAL 0x0300 +#define DCMASK_SUBNORMAL 0x00c0 +#define DCMASK_INFINITY 0x0030 +#define DCMASK_QUIET_NAN 0x000c +#define DCMASK_SIGNALING_NAN 0x0003 +#define DCMASK_NAN 0x000f +#define DCMASK_NEGATIVE 0x0555 uint16_t float32_dcmask(CPUS390XState *env, float32 f1); uint16_t float64_dcmask(CPUS390XState *env, float64 f1); uint16_t float128_dcmask(CPUS390XState *env, float128 f1); @@ -303,7 +308,6 @@ void s390_cpu_gdb_init(CPUState *cs); void s390_cpu_dump_state(CPUState *cpu, FILE *f, int flags); void do_restart_interrupt(CPUS390XState *env); #ifndef CONFIG_USER_ONLY -uint64_t get_psw_mask(CPUS390XState *env); void s390_cpu_recompute_watchpoints(CPUState *cs); void s390x_tod_timer(void *opaque); void s390x_cpu_timer(void *opaque); diff --git a/target/s390x/kvm-stub.c b/target/s390x/kvm-stub.c index 9970b5a..8a308cf 100644 --- a/target/s390x/kvm-stub.c +++ b/target/s390x/kvm-stub.c @@ -49,11 +49,6 @@ int kvm_s390_get_ri(void) return 0; } -int kvm_s390_get_gs(void) -{ - return 0; -} - int kvm_s390_get_clock(uint8_t *tod_high, uint64_t *tod_low) { return -ENOSYS; diff --git a/target/s390x/kvm.c b/target/s390x/kvm.c index 4fb3bbf..2388924 100644 --- a/target/s390x/kvm.c +++ b/target/s390x/kvm.c @@ -154,7 +154,6 @@ static int cap_async_pf; static int cap_mem_op; static int cap_s390_irq; static int cap_ri; -static int cap_gs; static int cap_hpage_1m; static int cap_vcpu_resets; static int cap_protected; @@ -369,9 +368,7 @@ int kvm_arch_init(MachineState *ms, KVMState *s) } } if (cpu_model_allowed()) { - if (kvm_vm_enable_cap(s, KVM_CAP_S390_GS, 0) == 0) { - cap_gs = 1; - } + kvm_vm_enable_cap(s, KVM_CAP_S390_GS, 0); } /* @@ -2039,11 +2036,6 @@ int kvm_s390_get_ri(void) return cap_ri; } -int kvm_s390_get_gs(void) -{ - return cap_gs; -} - int kvm_s390_set_cpu_state(S390CPU *cpu, uint8_t cpu_state) { struct kvm_mp_state mp_state = {}; diff --git a/target/s390x/kvm_s390x.h b/target/s390x/kvm_s390x.h index 25bbe98..05a5e1e 100644 --- a/target/s390x/kvm_s390x.h +++ b/target/s390x/kvm_s390x.h @@ -27,7 +27,6 @@ void kvm_s390_vcpu_interrupt_pre_save(S390CPU *cpu); int kvm_s390_vcpu_interrupt_post_load(S390CPU *cpu); int kvm_s390_get_hpage_1m(void); int kvm_s390_get_ri(void); -int kvm_s390_get_gs(void); int kvm_s390_get_clock(uint8_t *tod_high, uint64_t *tod_clock); int kvm_s390_get_clock_ext(uint8_t *tod_high, uint64_t *tod_clock); int kvm_s390_set_clock(uint8_t tod_high, uint64_t tod_clock); diff --git a/target/s390x/sigp.c b/target/s390x/sigp.c index c604f17..c2d5cdf 100644 --- a/target/s390x/sigp.c +++ b/target/s390x/sigp.c @@ -235,7 +235,8 @@ static void sigp_restart(CPUState *cs, run_on_cpu_data arg) cpu_synchronize_state(cs); /* * Set OPERATING (and unhalting) before loading the restart PSW. - * load_psw() will then properly halt the CPU again if necessary (TCG). + * s390_cpu_set_psw() will then properly halt the CPU again if + * necessary (TCG). */ s390_cpu_set_state(S390_CPU_STATE_OPERATING, cpu); do_restart_interrupt(&cpu->env); diff --git a/target/s390x/translate_vx.c.inc b/target/s390x/translate_vx.c.inc index eb767f5..a9d51b1 100644 --- a/target/s390x/translate_vx.c.inc +++ b/target/s390x/translate_vx.c.inc @@ -327,6 +327,14 @@ static void gen_addi2_i64(TCGv_i64 dl, TCGv_i64 dh, TCGv_i64 al, TCGv_i64 ah, tcg_temp_free_i64(bh); } +static DisasJumpType op_vbperm(DisasContext *s, DisasOps *o) +{ + gen_gvec_3_ool(get_field(s, v1), get_field(s, v2), get_field(s, v3), 0, + gen_helper_gvec_vbperm); + + return DISAS_NEXT; +} + static DisasJumpType op_vge(DisasContext *s, DisasOps *o) { const uint8_t es = s->insn->data; @@ -1771,6 +1779,56 @@ static DisasJumpType op_vm(DisasContext *s, DisasOps *o) return DISAS_NEXT; } +static DisasJumpType op_vmsl(DisasContext *s, DisasOps *o) +{ + TCGv_i64 l1, h1, l2, h2; + + if (get_field(s, m4) != ES_64) { + gen_program_exception(s, PGM_SPECIFICATION); + return DISAS_NORETURN; + } + + l1 = tcg_temp_new_i64(); + h1 = tcg_temp_new_i64(); + l2 = tcg_temp_new_i64(); + h2 = tcg_temp_new_i64(); + + /* Multipy both even elements from v2 and v3 */ + read_vec_element_i64(l1, get_field(s, v2), 0, ES_64); + read_vec_element_i64(h1, get_field(s, v3), 0, ES_64); + tcg_gen_mulu2_i64(l1, h1, l1, h1); + /* Shift result left by one (x2) if requested */ + if (extract32(get_field(s, m6), 3, 1)) { + tcg_gen_add2_i64(l1, h1, l1, h1, l1, h1); + } + + /* Multipy both odd elements from v2 and v3 */ + read_vec_element_i64(l2, get_field(s, v2), 1, ES_64); + read_vec_element_i64(h2, get_field(s, v3), 1, ES_64); + tcg_gen_mulu2_i64(l2, h2, l2, h2); + /* Shift result left by one (x2) if requested */ + if (extract32(get_field(s, m6), 2, 1)) { + tcg_gen_add2_i64(l2, h2, l2, h2, l2, h2); + } + + /* Add both intermediate results */ + tcg_gen_add2_i64(l1, h1, l1, h1, l2, h2); + /* Add whole v4 */ + read_vec_element_i64(h2, get_field(s, v4), 0, ES_64); + read_vec_element_i64(l2, get_field(s, v4), 1, ES_64); + tcg_gen_add2_i64(l1, h1, l1, h1, l2, h2); + + /* Store final result into v1. */ + write_vec_element_i64(h1, get_field(s, v1), 0, ES_64); + write_vec_element_i64(l1, get_field(s, v1), 1, ES_64); + + tcg_temp_free_i64(l1); + tcg_temp_free_i64(h1); + tcg_temp_free_i64(l2); + tcg_temp_free_i64(h2); + return DISAS_NEXT; +} + static DisasJumpType op_vnn(DisasContext *s, DisasOps *o) { gen_gvec_fn_3(nand, ES_8, get_field(s, v1), @@ -2443,32 +2501,96 @@ static DisasJumpType op_vfa(DisasContext *s, DisasOps *o) { const uint8_t fpf = get_field(s, m4); const uint8_t m5 = get_field(s, m5); - const bool se = extract32(m5, 3, 1); - gen_helper_gvec_3_ptr *fn; - - if (fpf != FPF_LONG || extract32(m5, 0, 3)) { - gen_program_exception(s, PGM_SPECIFICATION); - return DISAS_NORETURN; - } + gen_helper_gvec_3_ptr *fn = NULL; switch (s->fields.op2) { case 0xe3: - fn = se ? gen_helper_gvec_vfa64s : gen_helper_gvec_vfa64; + switch (fpf) { + case FPF_SHORT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfa32; + } + break; + case FPF_LONG: + fn = gen_helper_gvec_vfa64; + break; + case FPF_EXT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfa128; + } + break; + default: + break; + } break; case 0xe5: - fn = se ? gen_helper_gvec_vfd64s : gen_helper_gvec_vfd64; + switch (fpf) { + case FPF_SHORT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfd32; + } + break; + case FPF_LONG: + fn = gen_helper_gvec_vfd64; + break; + case FPF_EXT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfd128; + } + break; + default: + break; + } break; case 0xe7: - fn = se ? gen_helper_gvec_vfm64s : gen_helper_gvec_vfm64; + switch (fpf) { + case FPF_SHORT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfm32; + } + break; + case FPF_LONG: + fn = gen_helper_gvec_vfm64; + break; + case FPF_EXT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfm128; + } + break; + default: + break; + } break; case 0xe2: - fn = se ? gen_helper_gvec_vfs64s : gen_helper_gvec_vfs64; + switch (fpf) { + case FPF_SHORT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfs32; + } + break; + case FPF_LONG: + fn = gen_helper_gvec_vfs64; + break; + case FPF_EXT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfs128; + } + break; + default: + break; + } break; default: g_assert_not_reached(); } + + if (!fn || extract32(m5, 0, 3)) { + gen_program_exception(s, PGM_SPECIFICATION); + return DISAS_NORETURN; + } + gen_gvec_3_ptr(get_field(s, v1), get_field(s, v2), - get_field(s, v3), cpu_env, 0, fn); + get_field(s, v3), cpu_env, m5, fn); return DISAS_NEXT; } @@ -2476,19 +2598,41 @@ static DisasJumpType op_wfc(DisasContext *s, DisasOps *o) { const uint8_t fpf = get_field(s, m3); const uint8_t m4 = get_field(s, m4); + gen_helper_gvec_2_ptr *fn = NULL; - if (fpf != FPF_LONG || m4) { + switch (fpf) { + case FPF_SHORT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_wfk32; + if (s->fields.op2 == 0xcb) { + fn = gen_helper_gvec_wfc32; + } + } + break; + case FPF_LONG: + fn = gen_helper_gvec_wfk64; + if (s->fields.op2 == 0xcb) { + fn = gen_helper_gvec_wfc64; + } + break; + case FPF_EXT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_wfk128; + if (s->fields.op2 == 0xcb) { + fn = gen_helper_gvec_wfc128; + } + } + break; + default: + break; + }; + + if (!fn || m4) { gen_program_exception(s, PGM_SPECIFICATION); return DISAS_NORETURN; } - if (s->fields.op2 == 0xcb) { - gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), - cpu_env, 0, gen_helper_gvec_wfc64); - } else { - gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), - cpu_env, 0, gen_helper_gvec_wfk64); - } + gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, 0, fn); set_cc_static(s); return DISAS_NEXT; } @@ -2498,46 +2642,68 @@ static DisasJumpType op_vfc(DisasContext *s, DisasOps *o) const uint8_t fpf = get_field(s, m4); const uint8_t m5 = get_field(s, m5); const uint8_t m6 = get_field(s, m6); - const bool se = extract32(m5, 3, 1); const bool cs = extract32(m6, 0, 1); - gen_helper_gvec_3_ptr *fn; + const bool sq = extract32(m5, 2, 1); + gen_helper_gvec_3_ptr *fn = NULL; - if (fpf != FPF_LONG || extract32(m5, 0, 3) || extract32(m6, 1, 3)) { - gen_program_exception(s, PGM_SPECIFICATION); - return DISAS_NORETURN; - } - - if (cs) { - switch (s->fields.op2) { - case 0xe8: - fn = se ? gen_helper_gvec_vfce64s_cc : gen_helper_gvec_vfce64_cc; + switch (s->fields.op2) { + case 0xe8: + switch (fpf) { + case FPF_SHORT: + fn = cs ? gen_helper_gvec_vfce32_cc : gen_helper_gvec_vfce32; break; - case 0xeb: - fn = se ? gen_helper_gvec_vfch64s_cc : gen_helper_gvec_vfch64_cc; + case FPF_LONG: + fn = cs ? gen_helper_gvec_vfce64_cc : gen_helper_gvec_vfce64; break; - case 0xea: - fn = se ? gen_helper_gvec_vfche64s_cc : gen_helper_gvec_vfche64_cc; + case FPF_EXT: + fn = cs ? gen_helper_gvec_vfce128_cc : gen_helper_gvec_vfce128; break; default: - g_assert_not_reached(); + break; } - } else { - switch (s->fields.op2) { - case 0xe8: - fn = se ? gen_helper_gvec_vfce64s : gen_helper_gvec_vfce64; + break; + case 0xeb: + switch (fpf) { + case FPF_SHORT: + fn = cs ? gen_helper_gvec_vfch32_cc : gen_helper_gvec_vfch32; break; - case 0xeb: - fn = se ? gen_helper_gvec_vfch64s : gen_helper_gvec_vfch64; + case FPF_LONG: + fn = cs ? gen_helper_gvec_vfch64_cc : gen_helper_gvec_vfch64; break; - case 0xea: - fn = se ? gen_helper_gvec_vfche64s : gen_helper_gvec_vfche64; + case FPF_EXT: + fn = cs ? gen_helper_gvec_vfch128_cc : gen_helper_gvec_vfch128; break; default: - g_assert_not_reached(); + break; + } + break; + case 0xea: + switch (fpf) { + case FPF_SHORT: + fn = cs ? gen_helper_gvec_vfche32_cc : gen_helper_gvec_vfche32; + break; + case FPF_LONG: + fn = cs ? gen_helper_gvec_vfche64_cc : gen_helper_gvec_vfche64; + break; + case FPF_EXT: + fn = cs ? gen_helper_gvec_vfche128_cc : gen_helper_gvec_vfche128; + break; + default: + break; } + break; + default: + g_assert_not_reached(); } - gen_gvec_3_ptr(get_field(s, v1), get_field(s, v2), - get_field(s, v3), cpu_env, 0, fn); + + if (!fn || extract32(m5, 0, 2) || extract32(m6, 1, 3) || + (!s390_has_feat(S390_FEAT_VECTOR_ENH) && (fpf != FPF_LONG || sq))) { + gen_program_exception(s, PGM_SPECIFICATION); + return DISAS_NORETURN; + } + + gen_gvec_3_ptr(get_field(s, v1), get_field(s, v2), get_field(s, v3), + cpu_env, m5, fn); if (cs) { set_cc_static(s); } @@ -2549,36 +2715,72 @@ static DisasJumpType op_vcdg(DisasContext *s, DisasOps *o) const uint8_t fpf = get_field(s, m3); const uint8_t m4 = get_field(s, m4); const uint8_t erm = get_field(s, m5); - const bool se = extract32(m4, 3, 1); - gen_helper_gvec_2_ptr *fn; + gen_helper_gvec_2_ptr *fn = NULL; - if (fpf != FPF_LONG || extract32(m4, 0, 2) || erm > 7 || erm == 2) { - gen_program_exception(s, PGM_SPECIFICATION); - return DISAS_NORETURN; - } switch (s->fields.op2) { case 0xc3: - fn = se ? gen_helper_gvec_vcdg64s : gen_helper_gvec_vcdg64; + if (fpf == FPF_LONG) { + fn = gen_helper_gvec_vcdg64; + } break; case 0xc1: - fn = se ? gen_helper_gvec_vcdlg64s : gen_helper_gvec_vcdlg64; + if (fpf == FPF_LONG) { + fn = gen_helper_gvec_vcdlg64; + } break; case 0xc2: - fn = se ? gen_helper_gvec_vcgd64s : gen_helper_gvec_vcgd64; + if (fpf == FPF_LONG) { + fn = gen_helper_gvec_vcgd64; + } break; case 0xc0: - fn = se ? gen_helper_gvec_vclgd64s : gen_helper_gvec_vclgd64; + if (fpf == FPF_LONG) { + fn = gen_helper_gvec_vclgd64; + } break; case 0xc7: - fn = se ? gen_helper_gvec_vfi64s : gen_helper_gvec_vfi64; + switch (fpf) { + case FPF_SHORT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfi32; + } + break; + case FPF_LONG: + fn = gen_helper_gvec_vfi64; + break; + case FPF_EXT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfi128; + } + break; + default: + break; + } break; case 0xc5: - fn = se ? gen_helper_gvec_vflr64s : gen_helper_gvec_vflr64; + switch (fpf) { + case FPF_LONG: + fn = gen_helper_gvec_vflr64; + break; + case FPF_EXT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vflr128; + } + break; + default: + break; + } break; default: g_assert_not_reached(); } + + if (!fn || extract32(m4, 0, 2) || erm > 7 || erm == 2) { + gen_program_exception(s, PGM_SPECIFICATION); + return DISAS_NORETURN; + } + gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, deposit32(m4, 4, 4, erm), fn); return DISAS_NEXT; @@ -2588,18 +2790,71 @@ static DisasJumpType op_vfll(DisasContext *s, DisasOps *o) { const uint8_t fpf = get_field(s, m3); const uint8_t m4 = get_field(s, m4); - gen_helper_gvec_2_ptr *fn = gen_helper_gvec_vfll32; + gen_helper_gvec_2_ptr *fn = NULL; - if (fpf != FPF_SHORT || extract32(m4, 0, 3)) { + switch (fpf) { + case FPF_SHORT: + fn = gen_helper_gvec_vfll32; + break; + case FPF_LONG: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfll64; + } + break; + default: + break; + } + + if (!fn || extract32(m4, 0, 3)) { gen_program_exception(s, PGM_SPECIFICATION); return DISAS_NORETURN; } - if (extract32(m4, 3, 1)) { - fn = gen_helper_gvec_vfll32s; + gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, m4, fn); + return DISAS_NEXT; +} + +static DisasJumpType op_vfmax(DisasContext *s, DisasOps *o) +{ + const uint8_t fpf = get_field(s, m4); + const uint8_t m6 = get_field(s, m6); + const uint8_t m5 = get_field(s, m5); + gen_helper_gvec_3_ptr *fn; + + if (m6 == 5 || m6 == 6 || m6 == 7 || m6 > 13) { + gen_program_exception(s, PGM_SPECIFICATION); + return DISAS_NORETURN; } - gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, - 0, fn); + + switch (fpf) { + case FPF_SHORT: + if (s->fields.op2 == 0xef) { + fn = gen_helper_gvec_vfmax32; + } else { + fn = gen_helper_gvec_vfmin32; + } + break; + case FPF_LONG: + if (s->fields.op2 == 0xef) { + fn = gen_helper_gvec_vfmax64; + } else { + fn = gen_helper_gvec_vfmin64; + } + break; + case FPF_EXT: + if (s->fields.op2 == 0xef) { + fn = gen_helper_gvec_vfmax128; + } else { + fn = gen_helper_gvec_vfmin128; + } + break; + default: + gen_program_exception(s, PGM_SPECIFICATION); + return DISAS_NORETURN; + } + + gen_gvec_3_ptr(get_field(s, v1), get_field(s, v2), get_field(s, v3), + cpu_env, deposit32(m5, 4, 4, m6), fn); return DISAS_NEXT; } @@ -2607,22 +2862,88 @@ static DisasJumpType op_vfma(DisasContext *s, DisasOps *o) { const uint8_t m5 = get_field(s, m5); const uint8_t fpf = get_field(s, m6); - const bool se = extract32(m5, 3, 1); - gen_helper_gvec_4_ptr *fn; + gen_helper_gvec_4_ptr *fn = NULL; - if (fpf != FPF_LONG || extract32(m5, 0, 3)) { + switch (s->fields.op2) { + case 0x8f: + switch (fpf) { + case FPF_SHORT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfma32; + } + break; + case FPF_LONG: + fn = gen_helper_gvec_vfma64; + break; + case FPF_EXT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfma128; + } + break; + default: + break; + } + break; + case 0x8e: + switch (fpf) { + case FPF_SHORT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfms32; + } + break; + case FPF_LONG: + fn = gen_helper_gvec_vfms64; + break; + case FPF_EXT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfms128; + } + break; + default: + break; + } + break; + case 0x9f: + switch (fpf) { + case FPF_SHORT: + fn = gen_helper_gvec_vfnma32; + break; + case FPF_LONG: + fn = gen_helper_gvec_vfnma64; + break; + case FPF_EXT: + fn = gen_helper_gvec_vfnma128; + break; + default: + break; + } + break; + case 0x9e: + switch (fpf) { + case FPF_SHORT: + fn = gen_helper_gvec_vfnms32; + break; + case FPF_LONG: + fn = gen_helper_gvec_vfnms64; + break; + case FPF_EXT: + fn = gen_helper_gvec_vfnms128; + break; + default: + break; + } + break; + default: + g_assert_not_reached(); + } + + if (!fn || extract32(m5, 0, 3)) { gen_program_exception(s, PGM_SPECIFICATION); return DISAS_NORETURN; } - if (s->fields.op2 == 0x8f) { - fn = se ? gen_helper_gvec_vfma64s : gen_helper_gvec_vfma64; - } else { - fn = se ? gen_helper_gvec_vfms64s : gen_helper_gvec_vfms64; - } gen_gvec_4_ptr(get_field(s, v1), get_field(s, v2), - get_field(s, v3), get_field(s, v4), cpu_env, - 0, fn); + get_field(s, v3), get_field(s, v4), cpu_env, m5, fn); return DISAS_NEXT; } @@ -2633,48 +2954,88 @@ static DisasJumpType op_vfpso(DisasContext *s, DisasOps *o) const uint8_t fpf = get_field(s, m3); const uint8_t m4 = get_field(s, m4); const uint8_t m5 = get_field(s, m5); + const bool se = extract32(m4, 3, 1); TCGv_i64 tmp; - if (fpf != FPF_LONG || extract32(m4, 0, 3) || m5 > 2) { + if ((fpf != FPF_LONG && !s390_has_feat(S390_FEAT_VECTOR_ENH)) || + extract32(m4, 0, 3) || m5 > 2) { gen_program_exception(s, PGM_SPECIFICATION); return DISAS_NORETURN; } - if (extract32(m4, 3, 1)) { - tmp = tcg_temp_new_i64(); - read_vec_element_i64(tmp, v2, 0, ES_64); - switch (m5) { - case 0: - /* sign bit is inverted (complement) */ - tcg_gen_xori_i64(tmp, tmp, 1ull << 63); - break; - case 1: - /* sign bit is set to one (negative) */ - tcg_gen_ori_i64(tmp, tmp, 1ull << 63); - break; - case 2: - /* sign bit is set to zero (positive) */ - tcg_gen_andi_i64(tmp, tmp, (1ull << 63) - 1); - break; + switch (fpf) { + case FPF_SHORT: + if (!se) { + switch (m5) { + case 0: + /* sign bit is inverted (complement) */ + gen_gvec_fn_2i(xori, ES_32, v1, v2, 1ull << 31); + break; + case 1: + /* sign bit is set to one (negative) */ + gen_gvec_fn_2i(ori, ES_32, v1, v2, 1ull << 31); + break; + case 2: + /* sign bit is set to zero (positive) */ + gen_gvec_fn_2i(andi, ES_32, v1, v2, (1ull << 31) - 1); + break; + } + return DISAS_NEXT; } - write_vec_element_i64(tmp, v1, 0, ES_64); - tcg_temp_free_i64(tmp); - } else { - switch (m5) { - case 0: - /* sign bit is inverted (complement) */ - gen_gvec_fn_2i(xori, ES_64, v1, v2, 1ull << 63); - break; - case 1: - /* sign bit is set to one (negative) */ - gen_gvec_fn_2i(ori, ES_64, v1, v2, 1ull << 63); - break; - case 2: - /* sign bit is set to zero (positive) */ - gen_gvec_fn_2i(andi, ES_64, v1, v2, (1ull << 63) - 1); - break; + break; + case FPF_LONG: + if (!se) { + switch (m5) { + case 0: + /* sign bit is inverted (complement) */ + gen_gvec_fn_2i(xori, ES_64, v1, v2, 1ull << 63); + break; + case 1: + /* sign bit is set to one (negative) */ + gen_gvec_fn_2i(ori, ES_64, v1, v2, 1ull << 63); + break; + case 2: + /* sign bit is set to zero (positive) */ + gen_gvec_fn_2i(andi, ES_64, v1, v2, (1ull << 63) - 1); + break; + } + return DISAS_NEXT; } + break; + case FPF_EXT: + /* Only a single element. */ + break; + default: + gen_program_exception(s, PGM_SPECIFICATION); + return DISAS_NORETURN; + } + + /* With a single element, we are only interested in bit 0. */ + tmp = tcg_temp_new_i64(); + read_vec_element_i64(tmp, v2, 0, ES_64); + switch (m5) { + case 0: + /* sign bit is inverted (complement) */ + tcg_gen_xori_i64(tmp, tmp, 1ull << 63); + break; + case 1: + /* sign bit is set to one (negative) */ + tcg_gen_ori_i64(tmp, tmp, 1ull << 63); + break; + case 2: + /* sign bit is set to zero (positive) */ + tcg_gen_andi_i64(tmp, tmp, (1ull << 63) - 1); + break; } + write_vec_element_i64(tmp, v1, 0, ES_64); + + if (fpf == FPF_EXT) { + read_vec_element_i64(tmp, v2, 1, ES_64); + write_vec_element_i64(tmp, v1, 1, ES_64); + } + + tcg_temp_free_i64(tmp); + return DISAS_NEXT; } @@ -2682,18 +3043,32 @@ static DisasJumpType op_vfsq(DisasContext *s, DisasOps *o) { const uint8_t fpf = get_field(s, m3); const uint8_t m4 = get_field(s, m4); - gen_helper_gvec_2_ptr *fn = gen_helper_gvec_vfsq64; + gen_helper_gvec_2_ptr *fn = NULL; - if (fpf != FPF_LONG || extract32(m4, 0, 3)) { + switch (fpf) { + case FPF_SHORT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfsq32; + } + break; + case FPF_LONG: + fn = gen_helper_gvec_vfsq64; + break; + case FPF_EXT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vfsq128; + } + break; + default: + break; + } + + if (!fn || extract32(m4, 0, 3)) { gen_program_exception(s, PGM_SPECIFICATION); return DISAS_NORETURN; } - if (extract32(m4, 3, 1)) { - fn = gen_helper_gvec_vfsq64s; - } - gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, - 0, fn); + gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, m4, fn); return DISAS_NEXT; } @@ -2702,17 +3077,33 @@ static DisasJumpType op_vftci(DisasContext *s, DisasOps *o) const uint16_t i3 = get_field(s, i3); const uint8_t fpf = get_field(s, m4); const uint8_t m5 = get_field(s, m5); - gen_helper_gvec_2_ptr *fn = gen_helper_gvec_vftci64; + gen_helper_gvec_2_ptr *fn = NULL; + + switch (fpf) { + case FPF_SHORT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vftci32; + } + break; + case FPF_LONG: + fn = gen_helper_gvec_vftci64; + break; + case FPF_EXT: + if (s390_has_feat(S390_FEAT_VECTOR_ENH)) { + fn = gen_helper_gvec_vftci128; + } + break; + default: + break; + } - if (fpf != FPF_LONG || extract32(m5, 0, 3)) { + if (!fn || extract32(m5, 0, 3)) { gen_program_exception(s, PGM_SPECIFICATION); return DISAS_NORETURN; } - if (extract32(m5, 3, 1)) { - fn = gen_helper_gvec_vftci64s; - } - gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, i3, fn); + gen_gvec_2_ptr(get_field(s, v1), get_field(s, v2), cpu_env, + deposit32(m5, 4, 12, i3), fn); set_cc_static(s); return DISAS_NEXT; } diff --git a/target/s390x/vec_fpu_helper.c b/target/s390x/vec_fpu_helper.c index c1564e8..8e2b274 100644 --- a/target/s390x/vec_fpu_helper.c +++ b/target/s390x/vec_fpu_helper.c @@ -78,9 +78,41 @@ static void handle_ieee_exc(CPUS390XState *env, uint8_t vxc, uint8_t vec_exc, } } -typedef uint64_t (*vop64_2_fn)(uint64_t a, float_status *s); -static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env, - bool s, bool XxC, uint8_t erm, vop64_2_fn fn, +static float32 s390_vec_read_float32(const S390Vector *v, uint8_t enr) +{ + return make_float32(s390_vec_read_element32(v, enr)); +} + +static float64 s390_vec_read_float64(const S390Vector *v, uint8_t enr) +{ + return make_float64(s390_vec_read_element64(v, enr)); +} + +static float128 s390_vec_read_float128(const S390Vector *v) +{ + return make_float128(s390_vec_read_element64(v, 0), + s390_vec_read_element64(v, 1)); +} + +static void s390_vec_write_float32(S390Vector *v, uint8_t enr, float32 data) +{ + return s390_vec_write_element32(v, enr, data); +} + +static void s390_vec_write_float64(S390Vector *v, uint8_t enr, float64 data) +{ + return s390_vec_write_element64(v, enr, data); +} + +static void s390_vec_write_float128(S390Vector *v, float128 data) +{ + s390_vec_write_element64(v, 0, data.high); + s390_vec_write_element64(v, 1, data.low); +} + +typedef float32 (*vop32_2_fn)(float32 a, float_status *s); +static void vop32_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env, + bool s, bool XxC, uint8_t erm, vop32_2_fn fn, uintptr_t retaddr) { uint8_t vxc, vec_exc = 0; @@ -88,10 +120,10 @@ static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env, int i, old_mode; old_mode = s390_swap_bfp_rounding_mode(env, erm); - for (i = 0; i < 2; i++) { - const uint64_t a = s390_vec_read_element64(v2, i); + for (i = 0; i < 4; i++) { + const float32 a = s390_vec_read_float32(v2, i); - s390_vec_write_element64(&tmp, i, fn(a, &env->fpu_status)); + s390_vec_write_float32(&tmp, i, fn(a, &env->fpu_status)); vxc = check_ieee_exc(env, i, XxC, &vec_exc); if (s || vxc) { break; @@ -102,317 +134,374 @@ static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env, *v1 = tmp; } -typedef uint64_t (*vop64_3_fn)(uint64_t a, uint64_t b, float_status *s); -static void vop64_3(S390Vector *v1, const S390Vector *v2, const S390Vector *v3, - CPUS390XState *env, bool s, vop64_3_fn fn, +typedef float64 (*vop64_2_fn)(float64 a, float_status *s); +static void vop64_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env, + bool s, bool XxC, uint8_t erm, vop64_2_fn fn, uintptr_t retaddr) { uint8_t vxc, vec_exc = 0; S390Vector tmp = {}; - int i; + int i, old_mode; + old_mode = s390_swap_bfp_rounding_mode(env, erm); for (i = 0; i < 2; i++) { - const uint64_t a = s390_vec_read_element64(v2, i); - const uint64_t b = s390_vec_read_element64(v3, i); + const float64 a = s390_vec_read_float64(v2, i); - s390_vec_write_element64(&tmp, i, fn(a, b, &env->fpu_status)); - vxc = check_ieee_exc(env, i, false, &vec_exc); + s390_vec_write_float64(&tmp, i, fn(a, &env->fpu_status)); + vxc = check_ieee_exc(env, i, XxC, &vec_exc); if (s || vxc) { break; } } + s390_restore_bfp_rounding_mode(env, old_mode); handle_ieee_exc(env, vxc, vec_exc, retaddr); *v1 = tmp; } -static uint64_t vfa64(uint64_t a, uint64_t b, float_status *s) +typedef float128 (*vop128_2_fn)(float128 a, float_status *s); +static void vop128_2(S390Vector *v1, const S390Vector *v2, CPUS390XState *env, + bool s, bool XxC, uint8_t erm, vop128_2_fn fn, + uintptr_t retaddr) { - return float64_add(a, b, s); + const float128 a = s390_vec_read_float128(v2); + uint8_t vxc, vec_exc = 0; + S390Vector tmp = {}; + int old_mode; + + old_mode = s390_swap_bfp_rounding_mode(env, erm); + s390_vec_write_float128(&tmp, fn(a, &env->fpu_status)); + vxc = check_ieee_exc(env, 0, XxC, &vec_exc); + s390_restore_bfp_rounding_mode(env, old_mode); + handle_ieee_exc(env, vxc, vec_exc, retaddr); + *v1 = tmp; } -void HELPER(gvec_vfa64)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) +static float64 vcdg64(float64 a, float_status *s) { - vop64_3(v1, v2, v3, env, false, vfa64, GETPC()); + return int64_to_float64(a, s); } -void HELPER(gvec_vfa64s)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) +static float64 vcdlg64(float64 a, float_status *s) { - vop64_3(v1, v2, v3, env, true, vfa64, GETPC()); + return uint64_to_float64(a, s); } -static int wfc64(const S390Vector *v1, const S390Vector *v2, - CPUS390XState *env, bool signal, uintptr_t retaddr) +static float64 vcgd64(float64 a, float_status *s) { - /* only the zero-indexed elements are compared */ - const float64 a = s390_vec_read_element64(v1, 0); - const float64 b = s390_vec_read_element64(v2, 0); - uint8_t vxc, vec_exc = 0; - int cmp; + const float64 tmp = float64_to_int64(a, s); - if (signal) { - cmp = float64_compare(a, b, &env->fpu_status); - } else { - cmp = float64_compare_quiet(a, b, &env->fpu_status); - } - vxc = check_ieee_exc(env, 0, false, &vec_exc); - handle_ieee_exc(env, vxc, vec_exc, retaddr); - - return float_comp_to_cc(env, cmp); + return float64_is_any_nan(a) ? INT64_MIN : tmp; } -void HELPER(gvec_wfc64)(const void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) +static float64 vclgd64(float64 a, float_status *s) { - env->cc_op = wfc64(v1, v2, env, false, GETPC()); + const float64 tmp = float64_to_uint64(a, s); + + return float64_is_any_nan(a) ? 0 : tmp; } -void HELPER(gvec_wfk64)(const void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) -{ - env->cc_op = wfc64(v1, v2, env, true, GETPC()); +#define DEF_GVEC_VOP2_FN(NAME, FN, BITS) \ +void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, CPUS390XState *env, \ + uint32_t desc) \ +{ \ + const uint8_t erm = extract32(simd_data(desc), 4, 4); \ + const bool se = extract32(simd_data(desc), 3, 1); \ + const bool XxC = extract32(simd_data(desc), 2, 1); \ + \ + vop##BITS##_2(v1, v2, env, se, XxC, erm, FN, GETPC()); \ } -typedef bool (*vfc64_fn)(float64 a, float64 b, float_status *status); -static int vfc64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3, - CPUS390XState *env, bool s, vfc64_fn fn, uintptr_t retaddr) +#define DEF_GVEC_VOP2_64(NAME) \ +DEF_GVEC_VOP2_FN(NAME, NAME##64, 64) + +#define DEF_GVEC_VOP2(NAME, OP) \ +DEF_GVEC_VOP2_FN(NAME, float32_##OP, 32) \ +DEF_GVEC_VOP2_FN(NAME, float64_##OP, 64) \ +DEF_GVEC_VOP2_FN(NAME, float128_##OP, 128) + +DEF_GVEC_VOP2_64(vcdg) +DEF_GVEC_VOP2_64(vcdlg) +DEF_GVEC_VOP2_64(vcgd) +DEF_GVEC_VOP2_64(vclgd) +DEF_GVEC_VOP2(vfi, round_to_int) +DEF_GVEC_VOP2(vfsq, sqrt) + +typedef float32 (*vop32_3_fn)(float32 a, float32 b, float_status *s); +static void vop32_3(S390Vector *v1, const S390Vector *v2, const S390Vector *v3, + CPUS390XState *env, bool s, vop32_3_fn fn, + uintptr_t retaddr) { uint8_t vxc, vec_exc = 0; S390Vector tmp = {}; - int match = 0; int i; - for (i = 0; i < 2; i++) { - const float64 a = s390_vec_read_element64(v2, i); - const float64 b = s390_vec_read_element64(v3, i); + for (i = 0; i < 4; i++) { + const float32 a = s390_vec_read_float32(v2, i); + const float32 b = s390_vec_read_float32(v3, i); - /* swap the order of the parameters, so we can use existing functions */ - if (fn(b, a, &env->fpu_status)) { - match++; - s390_vec_write_element64(&tmp, i, -1ull); - } + s390_vec_write_float32(&tmp, i, fn(a, b, &env->fpu_status)); vxc = check_ieee_exc(env, i, false, &vec_exc); if (s || vxc) { break; } } - handle_ieee_exc(env, vxc, vec_exc, retaddr); *v1 = tmp; - if (match) { - return s || match == 2 ? 0 : 1; - } - return 3; -} - -void HELPER(gvec_vfce64)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - vfc64(v1, v2, v3, env, false, float64_eq_quiet, GETPC()); } -void HELPER(gvec_vfce64s)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - vfc64(v1, v2, v3, env, true, float64_eq_quiet, GETPC()); -} - -void HELPER(gvec_vfce64_cc)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - env->cc_op = vfc64(v1, v2, v3, env, false, float64_eq_quiet, GETPC()); -} - -void HELPER(gvec_vfce64s_cc)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - env->cc_op = vfc64(v1, v2, v3, env, true, float64_eq_quiet, GETPC()); -} - -void HELPER(gvec_vfch64)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - vfc64(v1, v2, v3, env, false, float64_lt_quiet, GETPC()); -} - -void HELPER(gvec_vfch64s)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) +typedef float64 (*vop64_3_fn)(float64 a, float64 b, float_status *s); +static void vop64_3(S390Vector *v1, const S390Vector *v2, const S390Vector *v3, + CPUS390XState *env, bool s, vop64_3_fn fn, + uintptr_t retaddr) { - vfc64(v1, v2, v3, env, true, float64_lt_quiet, GETPC()); -} + uint8_t vxc, vec_exc = 0; + S390Vector tmp = {}; + int i; -void HELPER(gvec_vfch64_cc)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - env->cc_op = vfc64(v1, v2, v3, env, false, float64_lt_quiet, GETPC()); -} + for (i = 0; i < 2; i++) { + const float64 a = s390_vec_read_float64(v2, i); + const float64 b = s390_vec_read_float64(v3, i); -void HELPER(gvec_vfch64s_cc)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - env->cc_op = vfc64(v1, v2, v3, env, true, float64_lt_quiet, GETPC()); + s390_vec_write_float64(&tmp, i, fn(a, b, &env->fpu_status)); + vxc = check_ieee_exc(env, i, false, &vec_exc); + if (s || vxc) { + break; + } + } + handle_ieee_exc(env, vxc, vec_exc, retaddr); + *v1 = tmp; } -void HELPER(gvec_vfche64)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) +typedef float128 (*vop128_3_fn)(float128 a, float128 b, float_status *s); +static void vop128_3(S390Vector *v1, const S390Vector *v2, const S390Vector *v3, + CPUS390XState *env, bool s, vop128_3_fn fn, + uintptr_t retaddr) { - vfc64(v1, v2, v3, env, false, float64_le_quiet, GETPC()); -} + const float128 a = s390_vec_read_float128(v2); + const float128 b = s390_vec_read_float128(v3); + uint8_t vxc, vec_exc = 0; + S390Vector tmp = {}; -void HELPER(gvec_vfche64s)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - vfc64(v1, v2, v3, env, true, float64_le_quiet, GETPC()); + s390_vec_write_float128(&tmp, fn(a, b, &env->fpu_status)); + vxc = check_ieee_exc(env, 0, false, &vec_exc); + handle_ieee_exc(env, vxc, vec_exc, retaddr); + *v1 = tmp; } -void HELPER(gvec_vfche64_cc)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - env->cc_op = vfc64(v1, v2, v3, env, false, float64_le_quiet, GETPC()); +#define DEF_GVEC_VOP3_B(NAME, OP, BITS) \ +void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, const void *v3, \ + CPUS390XState *env, uint32_t desc) \ +{ \ + const bool se = extract32(simd_data(desc), 3, 1); \ + \ + vop##BITS##_3(v1, v2, v3, env, se, float##BITS##_##OP, GETPC()); \ } -void HELPER(gvec_vfche64s_cc)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - env->cc_op = vfc64(v1, v2, v3, env, true, float64_le_quiet, GETPC()); -} +#define DEF_GVEC_VOP3(NAME, OP) \ +DEF_GVEC_VOP3_B(NAME, OP, 32) \ +DEF_GVEC_VOP3_B(NAME, OP, 64) \ +DEF_GVEC_VOP3_B(NAME, OP, 128) -static uint64_t vcdg64(uint64_t a, float_status *s) -{ - return int64_to_float64(a, s); -} +DEF_GVEC_VOP3(vfa, add) +DEF_GVEC_VOP3(vfs, sub) +DEF_GVEC_VOP3(vfd, div) +DEF_GVEC_VOP3(vfm, mul) -void HELPER(gvec_vcdg64)(void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) +static int wfc32(const S390Vector *v1, const S390Vector *v2, + CPUS390XState *env, bool signal, uintptr_t retaddr) { - const uint8_t erm = extract32(simd_data(desc), 4, 4); - const bool XxC = extract32(simd_data(desc), 2, 1); - - vop64_2(v1, v2, env, false, XxC, erm, vcdg64, GETPC()); -} + /* only the zero-indexed elements are compared */ + const float32 a = s390_vec_read_float32(v1, 0); + const float32 b = s390_vec_read_float32(v2, 0); + uint8_t vxc, vec_exc = 0; + int cmp; -void HELPER(gvec_vcdg64s)(void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) -{ - const uint8_t erm = extract32(simd_data(desc), 4, 4); - const bool XxC = extract32(simd_data(desc), 2, 1); + if (signal) { + cmp = float32_compare(a, b, &env->fpu_status); + } else { + cmp = float32_compare_quiet(a, b, &env->fpu_status); + } + vxc = check_ieee_exc(env, 0, false, &vec_exc); + handle_ieee_exc(env, vxc, vec_exc, retaddr); - vop64_2(v1, v2, env, true, XxC, erm, vcdg64, GETPC()); + return float_comp_to_cc(env, cmp); } -static uint64_t vcdlg64(uint64_t a, float_status *s) +static int wfc64(const S390Vector *v1, const S390Vector *v2, + CPUS390XState *env, bool signal, uintptr_t retaddr) { - return uint64_to_float64(a, s); -} + /* only the zero-indexed elements are compared */ + const float64 a = s390_vec_read_float64(v1, 0); + const float64 b = s390_vec_read_float64(v2, 0); + uint8_t vxc, vec_exc = 0; + int cmp; -void HELPER(gvec_vcdlg64)(void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) -{ - const uint8_t erm = extract32(simd_data(desc), 4, 4); - const bool XxC = extract32(simd_data(desc), 2, 1); + if (signal) { + cmp = float64_compare(a, b, &env->fpu_status); + } else { + cmp = float64_compare_quiet(a, b, &env->fpu_status); + } + vxc = check_ieee_exc(env, 0, false, &vec_exc); + handle_ieee_exc(env, vxc, vec_exc, retaddr); - vop64_2(v1, v2, env, false, XxC, erm, vcdlg64, GETPC()); + return float_comp_to_cc(env, cmp); } -void HELPER(gvec_vcdlg64s)(void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) +static int wfc128(const S390Vector *v1, const S390Vector *v2, + CPUS390XState *env, bool signal, uintptr_t retaddr) { - const uint8_t erm = extract32(simd_data(desc), 4, 4); - const bool XxC = extract32(simd_data(desc), 2, 1); + /* only the zero-indexed elements are compared */ + const float128 a = s390_vec_read_float128(v1); + const float128 b = s390_vec_read_float128(v2); + uint8_t vxc, vec_exc = 0; + int cmp; - vop64_2(v1, v2, env, true, XxC, erm, vcdlg64, GETPC()); -} + if (signal) { + cmp = float128_compare(a, b, &env->fpu_status); + } else { + cmp = float128_compare_quiet(a, b, &env->fpu_status); + } + vxc = check_ieee_exc(env, 0, false, &vec_exc); + handle_ieee_exc(env, vxc, vec_exc, retaddr); -static uint64_t vcgd64(uint64_t a, float_status *s) -{ - return float64_to_int64(a, s); + return float_comp_to_cc(env, cmp); } -void HELPER(gvec_vcgd64)(void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) -{ - const uint8_t erm = extract32(simd_data(desc), 4, 4); - const bool XxC = extract32(simd_data(desc), 2, 1); - - vop64_2(v1, v2, env, false, XxC, erm, vcgd64, GETPC()); +#define DEF_GVEC_WFC_B(NAME, SIGNAL, BITS) \ +void HELPER(gvec_##NAME##BITS)(const void *v1, const void *v2, \ + CPUS390XState *env, uint32_t desc) \ +{ \ + env->cc_op = wfc##BITS(v1, v2, env, SIGNAL, GETPC()); \ } -void HELPER(gvec_vcgd64s)(void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) -{ - const uint8_t erm = extract32(simd_data(desc), 4, 4); - const bool XxC = extract32(simd_data(desc), 2, 1); - - vop64_2(v1, v2, env, true, XxC, erm, vcgd64, GETPC()); -} +#define DEF_GVEC_WFC(NAME, SIGNAL) \ + DEF_GVEC_WFC_B(NAME, SIGNAL, 32) \ + DEF_GVEC_WFC_B(NAME, SIGNAL, 64) \ + DEF_GVEC_WFC_B(NAME, SIGNAL, 128) -static uint64_t vclgd64(uint64_t a, float_status *s) -{ - return float64_to_uint64(a, s); -} +DEF_GVEC_WFC(wfc, false) +DEF_GVEC_WFC(wfk, true) -void HELPER(gvec_vclgd64)(void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) +typedef bool (*vfc32_fn)(float32 a, float32 b, float_status *status); +static int vfc32(S390Vector *v1, const S390Vector *v2, const S390Vector *v3, + CPUS390XState *env, bool s, vfc32_fn fn, uintptr_t retaddr) { - const uint8_t erm = extract32(simd_data(desc), 4, 4); - const bool XxC = extract32(simd_data(desc), 2, 1); + uint8_t vxc, vec_exc = 0; + S390Vector tmp = {}; + int match = 0; + int i; - vop64_2(v1, v2, env, false, XxC, erm, vclgd64, GETPC()); -} + for (i = 0; i < 4; i++) { + const float32 a = s390_vec_read_float32(v2, i); + const float32 b = s390_vec_read_float32(v3, i); -void HELPER(gvec_vclgd64s)(void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) -{ - const uint8_t erm = extract32(simd_data(desc), 4, 4); - const bool XxC = extract32(simd_data(desc), 2, 1); + /* swap the order of the parameters, so we can use existing functions */ + if (fn(b, a, &env->fpu_status)) { + match++; + s390_vec_write_element32(&tmp, i, -1u); + } + vxc = check_ieee_exc(env, i, false, &vec_exc); + if (s || vxc) { + break; + } + } - vop64_2(v1, v2, env, true, XxC, erm, vclgd64, GETPC()); + handle_ieee_exc(env, vxc, vec_exc, retaddr); + *v1 = tmp; + if (match) { + return s || match == 4 ? 0 : 1; + } + return 3; } -static uint64_t vfd64(uint64_t a, uint64_t b, float_status *s) +typedef bool (*vfc64_fn)(float64 a, float64 b, float_status *status); +static int vfc64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3, + CPUS390XState *env, bool s, vfc64_fn fn, uintptr_t retaddr) { - return float64_div(a, b, s); -} + uint8_t vxc, vec_exc = 0; + S390Vector tmp = {}; + int match = 0; + int i; -void HELPER(gvec_vfd64)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - vop64_3(v1, v2, v3, env, false, vfd64, GETPC()); -} + for (i = 0; i < 2; i++) { + const float64 a = s390_vec_read_float64(v2, i); + const float64 b = s390_vec_read_float64(v3, i); -void HELPER(gvec_vfd64s)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - vop64_3(v1, v2, v3, env, true, vfd64, GETPC()); -} + /* swap the order of the parameters, so we can use existing functions */ + if (fn(b, a, &env->fpu_status)) { + match++; + s390_vec_write_element64(&tmp, i, -1ull); + } + vxc = check_ieee_exc(env, i, false, &vec_exc); + if (s || vxc) { + break; + } + } -static uint64_t vfi64(uint64_t a, float_status *s) -{ - return float64_round_to_int(a, s); + handle_ieee_exc(env, vxc, vec_exc, retaddr); + *v1 = tmp; + if (match) { + return s || match == 2 ? 0 : 1; + } + return 3; } -void HELPER(gvec_vfi64)(void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) +typedef bool (*vfc128_fn)(float128 a, float128 b, float_status *status); +static int vfc128(S390Vector *v1, const S390Vector *v2, const S390Vector *v3, + CPUS390XState *env, bool s, vfc128_fn fn, uintptr_t retaddr) { - const uint8_t erm = extract32(simd_data(desc), 4, 4); - const bool XxC = extract32(simd_data(desc), 2, 1); + const float128 a = s390_vec_read_float128(v2); + const float128 b = s390_vec_read_float128(v3); + uint8_t vxc, vec_exc = 0; + S390Vector tmp = {}; + bool match = false; - vop64_2(v1, v2, env, false, XxC, erm, vfi64, GETPC()); -} + /* swap the order of the parameters, so we can use existing functions */ + if (fn(b, a, &env->fpu_status)) { + match = true; + s390_vec_write_element64(&tmp, 0, -1ull); + s390_vec_write_element64(&tmp, 1, -1ull); + } + vxc = check_ieee_exc(env, 0, false, &vec_exc); + handle_ieee_exc(env, vxc, vec_exc, retaddr); + *v1 = tmp; + return match ? 0 : 3; +} + +#define DEF_GVEC_VFC_B(NAME, OP, BITS) \ +void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, const void *v3, \ + CPUS390XState *env, uint32_t desc) \ +{ \ + const bool se = extract32(simd_data(desc), 3, 1); \ + const bool sq = extract32(simd_data(desc), 2, 1); \ + vfc##BITS##_fn fn = sq ? float##BITS##_##OP : float##BITS##_##OP##_quiet; \ + \ + vfc##BITS(v1, v2, v3, env, se, fn, GETPC()); \ +} \ + \ +void HELPER(gvec_##NAME##BITS##_cc)(void *v1, const void *v2, const void *v3, \ + CPUS390XState *env, uint32_t desc) \ +{ \ + const bool se = extract32(simd_data(desc), 3, 1); \ + const bool sq = extract32(simd_data(desc), 2, 1); \ + vfc##BITS##_fn fn = sq ? float##BITS##_##OP : float##BITS##_##OP##_quiet; \ + \ + env->cc_op = vfc##BITS(v1, v2, v3, env, se, fn, GETPC()); \ +} + +#define DEF_GVEC_VFC(NAME, OP) \ +DEF_GVEC_VFC_B(NAME, OP, 32) \ +DEF_GVEC_VFC_B(NAME, OP, 64) \ +DEF_GVEC_VFC_B(NAME, OP, 128) \ + +DEF_GVEC_VFC(vfce, eq) +DEF_GVEC_VFC(vfch, lt) +DEF_GVEC_VFC(vfche, le) -void HELPER(gvec_vfi64s)(void *v1, const void *v2, CPUS390XState *env, +void HELPER(gvec_vfll32)(void *v1, const void *v2, CPUS390XState *env, uint32_t desc) { - const uint8_t erm = extract32(simd_data(desc), 4, 4); - const bool XxC = extract32(simd_data(desc), 2, 1); - - vop64_2(v1, v2, env, true, XxC, erm, vfi64, GETPC()); -} - -static void vfll32(S390Vector *v1, const S390Vector *v2, CPUS390XState *env, - bool s, uintptr_t retaddr) -{ + const bool s = extract32(simd_data(desc), 3, 1); uint8_t vxc, vec_exc = 0; S390Vector tmp = {}; int i; @@ -429,25 +518,29 @@ static void vfll32(S390Vector *v1, const S390Vector *v2, CPUS390XState *env, break; } } - handle_ieee_exc(env, vxc, vec_exc, retaddr); - *v1 = tmp; + handle_ieee_exc(env, vxc, vec_exc, GETPC()); + *(S390Vector *)v1 = tmp; } -void HELPER(gvec_vfll32)(void *v1, const void *v2, CPUS390XState *env, +void HELPER(gvec_vfll64)(void *v1, const void *v2, CPUS390XState *env, uint32_t desc) { - vfll32(v1, v2, env, false, GETPC()); -} + /* load from even element */ + const float128 ret = float64_to_float128(s390_vec_read_float64(v2, 0), + &env->fpu_status); + uint8_t vxc, vec_exc = 0; -void HELPER(gvec_vfll32s)(void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) -{ - vfll32(v1, v2, env, true, GETPC()); + vxc = check_ieee_exc(env, 0, false, &vec_exc); + handle_ieee_exc(env, vxc, vec_exc, GETPC()); + s390_vec_write_float128(v1, ret); } -static void vflr64(S390Vector *v1, const S390Vector *v2, CPUS390XState *env, - bool s, bool XxC, uint8_t erm, uintptr_t retaddr) +void HELPER(gvec_vflr64)(void *v1, const void *v2, CPUS390XState *env, + uint32_t desc) { + const uint8_t erm = extract32(simd_data(desc), 4, 4); + const bool s = extract32(simd_data(desc), 3, 1); + const bool XxC = extract32(simd_data(desc), 2, 1); uint8_t vxc, vec_exc = 0; S390Vector tmp = {}; int i, old_mode; @@ -466,43 +559,51 @@ static void vflr64(S390Vector *v1, const S390Vector *v2, CPUS390XState *env, } } s390_restore_bfp_rounding_mode(env, old_mode); - handle_ieee_exc(env, vxc, vec_exc, retaddr); - *v1 = tmp; -} - -void HELPER(gvec_vflr64)(void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) -{ - const uint8_t erm = extract32(simd_data(desc), 4, 4); - const bool XxC = extract32(simd_data(desc), 2, 1); - - vflr64(v1, v2, env, false, XxC, erm, GETPC()); + handle_ieee_exc(env, vxc, vec_exc, GETPC()); + *(S390Vector *)v1 = tmp; } -void HELPER(gvec_vflr64s)(void *v1, const void *v2, CPUS390XState *env, +void HELPER(gvec_vflr128)(void *v1, const void *v2, CPUS390XState *env, uint32_t desc) { const uint8_t erm = extract32(simd_data(desc), 4, 4); const bool XxC = extract32(simd_data(desc), 2, 1); + uint8_t vxc, vec_exc = 0; + int old_mode; + float64 ret; - vflr64(v1, v2, env, true, XxC, erm, GETPC()); -} + old_mode = s390_swap_bfp_rounding_mode(env, erm); + ret = float128_to_float64(s390_vec_read_float128(v2), &env->fpu_status); + vxc = check_ieee_exc(env, 0, XxC, &vec_exc); + s390_restore_bfp_rounding_mode(env, old_mode); + handle_ieee_exc(env, vxc, vec_exc, GETPC()); -static uint64_t vfm64(uint64_t a, uint64_t b, float_status *s) -{ - return float64_mul(a, b, s); + /* place at even element, odd element is unpredictable */ + s390_vec_write_float64(v1, 0, ret); } -void HELPER(gvec_vfm64)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) +static void vfma32(S390Vector *v1, const S390Vector *v2, const S390Vector *v3, + const S390Vector *v4, CPUS390XState *env, bool s, int flags, + uintptr_t retaddr) { - vop64_3(v1, v2, v3, env, false, vfm64, GETPC()); -} + uint8_t vxc, vec_exc = 0; + S390Vector tmp = {}; + int i; -void HELPER(gvec_vfm64s)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - vop64_3(v1, v2, v3, env, true, vfm64, GETPC()); + for (i = 0; i < 4; i++) { + const float32 a = s390_vec_read_float32(v2, i); + const float32 b = s390_vec_read_float32(v3, i); + const float32 c = s390_vec_read_float32(v4, i); + float32 ret = float32_muladd(a, b, c, flags, &env->fpu_status); + + s390_vec_write_float32(&tmp, i, ret); + vxc = check_ieee_exc(env, i, false, &vec_exc); + if (s || vxc) { + break; + } + } + handle_ieee_exc(env, vxc, vec_exc, retaddr); + *v1 = tmp; } static void vfma64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3, @@ -514,12 +615,12 @@ static void vfma64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3, int i; for (i = 0; i < 2; i++) { - const uint64_t a = s390_vec_read_element64(v2, i); - const uint64_t b = s390_vec_read_element64(v3, i); - const uint64_t c = s390_vec_read_element64(v4, i); - uint64_t ret = float64_muladd(a, b, c, flags, &env->fpu_status); + const float64 a = s390_vec_read_float64(v2, i); + const float64 b = s390_vec_read_float64(v3, i); + const float64 c = s390_vec_read_float64(v4, i); + const float64 ret = float64_muladd(a, b, c, flags, &env->fpu_status); - s390_vec_write_element64(&tmp, i, ret); + s390_vec_write_float64(&tmp, i, ret); vxc = check_ieee_exc(env, i, false, &vec_exc); if (s || vxc) { break; @@ -529,71 +630,81 @@ static void vfma64(S390Vector *v1, const S390Vector *v2, const S390Vector *v3, *v1 = tmp; } -void HELPER(gvec_vfma64)(void *v1, const void *v2, const void *v3, - const void *v4, CPUS390XState *env, uint32_t desc) +static void vfma128(S390Vector *v1, const S390Vector *v2, const S390Vector *v3, + const S390Vector *v4, CPUS390XState *env, bool s, int flags, + uintptr_t retaddr) { - vfma64(v1, v2, v3, v4, env, false, 0, GETPC()); -} + const float128 a = s390_vec_read_float128(v2); + const float128 b = s390_vec_read_float128(v3); + const float128 c = s390_vec_read_float128(v4); + uint8_t vxc, vec_exc = 0; + float128 ret; -void HELPER(gvec_vfma64s)(void *v1, const void *v2, const void *v3, - const void *v4, CPUS390XState *env, uint32_t desc) -{ - vfma64(v1, v2, v3, v4, env, true, 0, GETPC()); + ret = float128_muladd(a, b, c, flags, &env->fpu_status); + vxc = check_ieee_exc(env, 0, false, &vec_exc); + handle_ieee_exc(env, vxc, vec_exc, retaddr); + s390_vec_write_float128(v1, ret); } -void HELPER(gvec_vfms64)(void *v1, const void *v2, const void *v3, - const void *v4, CPUS390XState *env, uint32_t desc) -{ - vfma64(v1, v2, v3, v4, env, false, float_muladd_negate_c, GETPC()); +#define DEF_GVEC_VFMA_B(NAME, FLAGS, BITS) \ +void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, const void *v3, \ + const void *v4, CPUS390XState *env, \ + uint32_t desc) \ +{ \ + const bool se = extract32(simd_data(desc), 3, 1); \ + \ + vfma##BITS(v1, v2, v3, v4, env, se, FLAGS, GETPC()); \ } -void HELPER(gvec_vfms64s)(void *v1, const void *v2, const void *v3, - const void *v4, CPUS390XState *env, uint32_t desc) -{ - vfma64(v1, v2, v3, v4, env, true, float_muladd_negate_c, GETPC()); -} +#define DEF_GVEC_VFMA(NAME, FLAGS) \ + DEF_GVEC_VFMA_B(NAME, FLAGS, 32) \ + DEF_GVEC_VFMA_B(NAME, FLAGS, 64) \ + DEF_GVEC_VFMA_B(NAME, FLAGS, 128) -static uint64_t vfsq64(uint64_t a, float_status *s) -{ - return float64_sqrt(a, s); -} +DEF_GVEC_VFMA(vfma, 0) +DEF_GVEC_VFMA(vfms, float_muladd_negate_c) +DEF_GVEC_VFMA(vfnma, float_muladd_negate_result) +DEF_GVEC_VFMA(vfnms, float_muladd_negate_c | float_muladd_negate_result) -void HELPER(gvec_vfsq64)(void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) -{ - vop64_2(v1, v2, env, false, false, 0, vfsq64, GETPC()); -} - -void HELPER(gvec_vfsq64s)(void *v1, const void *v2, CPUS390XState *env, +void HELPER(gvec_vftci32)(void *v1, const void *v2, CPUS390XState *env, uint32_t desc) { - vop64_2(v1, v2, env, true, false, 0, vfsq64, GETPC()); -} + uint16_t i3 = extract32(simd_data(desc), 4, 12); + bool s = extract32(simd_data(desc), 3, 1); + int i, match = 0; -static uint64_t vfs64(uint64_t a, uint64_t b, float_status *s) -{ - return float64_sub(a, b, s); -} + for (i = 0; i < 4; i++) { + float32 a = s390_vec_read_float32(v2, i); -void HELPER(gvec_vfs64)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - vop64_3(v1, v2, v3, env, false, vfs64, GETPC()); -} + if (float32_dcmask(env, a) & i3) { + match++; + s390_vec_write_element32(v1, i, -1u); + } else { + s390_vec_write_element32(v1, i, 0); + } + if (s) { + break; + } + } -void HELPER(gvec_vfs64s)(void *v1, const void *v2, const void *v3, - CPUS390XState *env, uint32_t desc) -{ - vop64_3(v1, v2, v3, env, true, vfs64, GETPC()); + if (match == 4 || (s && match)) { + env->cc_op = 0; + } else if (match) { + env->cc_op = 1; + } else { + env->cc_op = 3; + } } -static int vftci64(S390Vector *v1, const S390Vector *v2, CPUS390XState *env, - bool s, uint16_t i3) +void HELPER(gvec_vftci64)(void *v1, const void *v2, CPUS390XState *env, + uint32_t desc) { + const uint16_t i3 = extract32(simd_data(desc), 4, 12); + const bool s = extract32(simd_data(desc), 3, 1); int i, match = 0; for (i = 0; i < 2; i++) { - float64 a = s390_vec_read_element64(v2, i); + const float64 a = s390_vec_read_float64(v2, i); if (float64_dcmask(env, a) & i3) { match++; @@ -606,20 +717,356 @@ static int vftci64(S390Vector *v1, const S390Vector *v2, CPUS390XState *env, } } - if (match) { - return s || match == 2 ? 0 : 1; + if (match == 2 || (s && match)) { + env->cc_op = 0; + } else if (match) { + env->cc_op = 1; + } else { + env->cc_op = 3; } - return 3; } -void HELPER(gvec_vftci64)(void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) +void HELPER(gvec_vftci128)(void *v1, const void *v2, CPUS390XState *env, + uint32_t desc) { - env->cc_op = vftci64(v1, v2, env, false, simd_data(desc)); + const float128 a = s390_vec_read_float128(v2); + uint16_t i3 = extract32(simd_data(desc), 4, 12); + + if (float128_dcmask(env, a) & i3) { + env->cc_op = 0; + s390_vec_write_element64(v1, 0, -1ull); + s390_vec_write_element64(v1, 1, -1ull); + } else { + env->cc_op = 3; + s390_vec_write_element64(v1, 0, 0); + s390_vec_write_element64(v1, 1, 0); + } } -void HELPER(gvec_vftci64s)(void *v1, const void *v2, CPUS390XState *env, - uint32_t desc) +typedef enum S390MinMaxType { + S390_MINMAX_TYPE_IEEE = 0, + S390_MINMAX_TYPE_JAVA, + S390_MINMAX_TYPE_C_MACRO, + S390_MINMAX_TYPE_CPP, + S390_MINMAX_TYPE_F, +} S390MinMaxType; + +typedef enum S390MinMaxRes { + S390_MINMAX_RES_MINMAX = 0, + S390_MINMAX_RES_A, + S390_MINMAX_RES_B, + S390_MINMAX_RES_SILENCE_A, + S390_MINMAX_RES_SILENCE_B, +} S390MinMaxRes; + +static S390MinMaxRes vfmin_res(uint16_t dcmask_a, uint16_t dcmask_b, + S390MinMaxType type, float_status *s) +{ + const bool neg_a = dcmask_a & DCMASK_NEGATIVE; + const bool nan_a = dcmask_a & DCMASK_NAN; + const bool nan_b = dcmask_b & DCMASK_NAN; + + g_assert(type > S390_MINMAX_TYPE_IEEE && type <= S390_MINMAX_TYPE_F); + + if (unlikely((dcmask_a | dcmask_b) & DCMASK_NAN)) { + const bool sig_a = dcmask_a & DCMASK_SIGNALING_NAN; + const bool sig_b = dcmask_b & DCMASK_SIGNALING_NAN; + + if ((dcmask_a | dcmask_b) & DCMASK_SIGNALING_NAN) { + s->float_exception_flags |= float_flag_invalid; + } + switch (type) { + case S390_MINMAX_TYPE_JAVA: + if (sig_a) { + return S390_MINMAX_RES_SILENCE_A; + } else if (sig_b) { + return S390_MINMAX_RES_SILENCE_B; + } + return nan_a ? S390_MINMAX_RES_A : S390_MINMAX_RES_B; + case S390_MINMAX_TYPE_F: + return nan_b ? S390_MINMAX_RES_A : S390_MINMAX_RES_B; + case S390_MINMAX_TYPE_C_MACRO: + s->float_exception_flags |= float_flag_invalid; + return S390_MINMAX_RES_B; + case S390_MINMAX_TYPE_CPP: + s->float_exception_flags |= float_flag_invalid; + return S390_MINMAX_RES_A; + default: + g_assert_not_reached(); + } + } else if (unlikely(dcmask_a & dcmask_b & DCMASK_ZERO)) { + switch (type) { + case S390_MINMAX_TYPE_JAVA: + return neg_a ? S390_MINMAX_RES_A : S390_MINMAX_RES_B; + case S390_MINMAX_TYPE_C_MACRO: + return S390_MINMAX_RES_B; + case S390_MINMAX_TYPE_F: + return !neg_a ? S390_MINMAX_RES_B : S390_MINMAX_RES_A; + case S390_MINMAX_TYPE_CPP: + return S390_MINMAX_RES_A; + default: + g_assert_not_reached(); + } + } + return S390_MINMAX_RES_MINMAX; +} + +static S390MinMaxRes vfmax_res(uint16_t dcmask_a, uint16_t dcmask_b, + S390MinMaxType type, float_status *s) +{ + g_assert(type > S390_MINMAX_TYPE_IEEE && type <= S390_MINMAX_TYPE_F); + + if (unlikely((dcmask_a | dcmask_b) & DCMASK_NAN)) { + const bool sig_a = dcmask_a & DCMASK_SIGNALING_NAN; + const bool sig_b = dcmask_b & DCMASK_SIGNALING_NAN; + const bool nan_a = dcmask_a & DCMASK_NAN; + const bool nan_b = dcmask_b & DCMASK_NAN; + + if ((dcmask_a | dcmask_b) & DCMASK_SIGNALING_NAN) { + s->float_exception_flags |= float_flag_invalid; + } + switch (type) { + case S390_MINMAX_TYPE_JAVA: + if (sig_a) { + return S390_MINMAX_RES_SILENCE_A; + } else if (sig_b) { + return S390_MINMAX_RES_SILENCE_B; + } + return nan_a ? S390_MINMAX_RES_A : S390_MINMAX_RES_B; + case S390_MINMAX_TYPE_F: + return nan_b ? S390_MINMAX_RES_A : S390_MINMAX_RES_B; + case S390_MINMAX_TYPE_C_MACRO: + s->float_exception_flags |= float_flag_invalid; + return S390_MINMAX_RES_B; + case S390_MINMAX_TYPE_CPP: + s->float_exception_flags |= float_flag_invalid; + return S390_MINMAX_RES_A; + default: + g_assert_not_reached(); + } + } else if (unlikely(dcmask_a & dcmask_b & DCMASK_ZERO)) { + const bool neg_a = dcmask_a & DCMASK_NEGATIVE; + + switch (type) { + case S390_MINMAX_TYPE_JAVA: + case S390_MINMAX_TYPE_F: + return neg_a ? S390_MINMAX_RES_B : S390_MINMAX_RES_A; + case S390_MINMAX_TYPE_C_MACRO: + return S390_MINMAX_RES_B; + case S390_MINMAX_TYPE_CPP: + return S390_MINMAX_RES_A; + default: + g_assert_not_reached(); + } + } + return S390_MINMAX_RES_MINMAX; +} + +static S390MinMaxRes vfminmax_res(uint16_t dcmask_a, uint16_t dcmask_b, + S390MinMaxType type, bool is_min, + float_status *s) +{ + return is_min ? vfmin_res(dcmask_a, dcmask_b, type, s) : + vfmax_res(dcmask_a, dcmask_b, type, s); +} + +static void vfminmax32(S390Vector *v1, const S390Vector *v2, + const S390Vector *v3, CPUS390XState *env, + S390MinMaxType type, bool is_min, bool is_abs, bool se, + uintptr_t retaddr) +{ + float_status *s = &env->fpu_status; + uint8_t vxc, vec_exc = 0; + S390Vector tmp = {}; + int i; + + for (i = 0; i < 4; i++) { + float32 a = s390_vec_read_float32(v2, i); + float32 b = s390_vec_read_float32(v3, i); + float32 result; + + if (type != S390_MINMAX_TYPE_IEEE) { + S390MinMaxRes res; + + if (is_abs) { + a = float32_abs(a); + b = float32_abs(b); + } + + res = vfminmax_res(float32_dcmask(env, a), float32_dcmask(env, b), + type, is_min, s); + switch (res) { + case S390_MINMAX_RES_MINMAX: + result = is_min ? float32_min(a, b, s) : float32_max(a, b, s); + break; + case S390_MINMAX_RES_A: + result = a; + break; + case S390_MINMAX_RES_B: + result = b; + break; + case S390_MINMAX_RES_SILENCE_A: + result = float32_silence_nan(a, s); + break; + case S390_MINMAX_RES_SILENCE_B: + result = float32_silence_nan(b, s); + break; + default: + g_assert_not_reached(); + } + } else if (!is_abs) { + result = is_min ? float32_minnum(a, b, &env->fpu_status) : + float32_maxnum(a, b, &env->fpu_status); + } else { + result = is_min ? float32_minnummag(a, b, &env->fpu_status) : + float32_maxnummag(a, b, &env->fpu_status); + } + + s390_vec_write_float32(&tmp, i, result); + vxc = check_ieee_exc(env, i, false, &vec_exc); + if (se || vxc) { + break; + } + } + handle_ieee_exc(env, vxc, vec_exc, retaddr); + *v1 = tmp; +} + +static void vfminmax64(S390Vector *v1, const S390Vector *v2, + const S390Vector *v3, CPUS390XState *env, + S390MinMaxType type, bool is_min, bool is_abs, bool se, + uintptr_t retaddr) { - env->cc_op = vftci64(v1, v2, env, true, simd_data(desc)); + float_status *s = &env->fpu_status; + uint8_t vxc, vec_exc = 0; + S390Vector tmp = {}; + int i; + + for (i = 0; i < 2; i++) { + float64 a = s390_vec_read_float64(v2, i); + float64 b = s390_vec_read_float64(v3, i); + float64 result; + + if (type != S390_MINMAX_TYPE_IEEE) { + S390MinMaxRes res; + + if (is_abs) { + a = float64_abs(a); + b = float64_abs(b); + } + + res = vfminmax_res(float64_dcmask(env, a), float64_dcmask(env, b), + type, is_min, s); + switch (res) { + case S390_MINMAX_RES_MINMAX: + result = is_min ? float64_min(a, b, s) : float64_max(a, b, s); + break; + case S390_MINMAX_RES_A: + result = a; + break; + case S390_MINMAX_RES_B: + result = b; + break; + case S390_MINMAX_RES_SILENCE_A: + result = float64_silence_nan(a, s); + break; + case S390_MINMAX_RES_SILENCE_B: + result = float64_silence_nan(b, s); + break; + default: + g_assert_not_reached(); + } + } else if (!is_abs) { + result = is_min ? float64_minnum(a, b, &env->fpu_status) : + float64_maxnum(a, b, &env->fpu_status); + } else { + result = is_min ? float64_minnummag(a, b, &env->fpu_status) : + float64_maxnummag(a, b, &env->fpu_status); + } + + s390_vec_write_float64(&tmp, i, result); + vxc = check_ieee_exc(env, i, false, &vec_exc); + if (se || vxc) { + break; + } + } + handle_ieee_exc(env, vxc, vec_exc, retaddr); + *v1 = tmp; } + +static void vfminmax128(S390Vector *v1, const S390Vector *v2, + const S390Vector *v3, CPUS390XState *env, + S390MinMaxType type, bool is_min, bool is_abs, bool se, + uintptr_t retaddr) +{ + float128 a = s390_vec_read_float128(v2); + float128 b = s390_vec_read_float128(v3); + float_status *s = &env->fpu_status; + uint8_t vxc, vec_exc = 0; + float128 result; + + if (type != S390_MINMAX_TYPE_IEEE) { + S390MinMaxRes res; + + if (is_abs) { + a = float128_abs(a); + b = float128_abs(b); + } + + res = vfminmax_res(float128_dcmask(env, a), float128_dcmask(env, b), + type, is_min, s); + switch (res) { + case S390_MINMAX_RES_MINMAX: + result = is_min ? float128_min(a, b, s) : float128_max(a, b, s); + break; + case S390_MINMAX_RES_A: + result = a; + break; + case S390_MINMAX_RES_B: + result = b; + break; + case S390_MINMAX_RES_SILENCE_A: + result = float128_silence_nan(a, s); + break; + case S390_MINMAX_RES_SILENCE_B: + result = float128_silence_nan(b, s); + break; + default: + g_assert_not_reached(); + } + } else if (!is_abs) { + result = is_min ? float128_minnum(a, b, &env->fpu_status) : + float128_maxnum(a, b, &env->fpu_status); + } else { + result = is_min ? float128_minnummag(a, b, &env->fpu_status) : + float128_maxnummag(a, b, &env->fpu_status); + } + + vxc = check_ieee_exc(env, 0, false, &vec_exc); + handle_ieee_exc(env, vxc, vec_exc, retaddr); + s390_vec_write_float128(v1, result); +} + +#define DEF_GVEC_VFMINMAX_B(NAME, IS_MIN, BITS) \ +void HELPER(gvec_##NAME##BITS)(void *v1, const void *v2, const void *v3, \ + CPUS390XState *env, uint32_t desc) \ +{ \ + const bool se = extract32(simd_data(desc), 3, 1); \ + uint8_t type = extract32(simd_data(desc), 4, 4); \ + bool is_abs = false; \ + \ + if (type >= 8) { \ + is_abs = true; \ + type -= 8; \ + } \ + \ + vfminmax##BITS(v1, v2, v3, env, type, IS_MIN, is_abs, se, GETPC()); \ +} + +#define DEF_GVEC_VFMINMAX(NAME, IS_MIN) \ + DEF_GVEC_VFMINMAX_B(NAME, IS_MIN, 32) \ + DEF_GVEC_VFMINMAX_B(NAME, IS_MIN, 64) \ + DEF_GVEC_VFMINMAX_B(NAME, IS_MIN, 128) + +DEF_GVEC_VFMINMAX(vfmax, false) +DEF_GVEC_VFMINMAX(vfmin, true) diff --git a/target/s390x/vec_helper.c b/target/s390x/vec_helper.c index 986e7cc..599bab0 100644 --- a/target/s390x/vec_helper.c +++ b/target/s390x/vec_helper.c @@ -19,6 +19,28 @@ #include "exec/cpu_ldst.h" #include "exec/exec-all.h" +void HELPER(gvec_vbperm)(void *v1, const void *v2, const void *v3, + uint32_t desc) +{ + S390Vector tmp = {}; + uint16_t result = 0; + int i; + + for (i = 0; i < 16; i++) { + const uint8_t bit_nr = s390_vec_read_element8(v3, i); + uint16_t bit; + + if (bit_nr >= 128) { + continue; + } + bit = (s390_vec_read_element8(v2, bit_nr / 8) + >> (7 - (bit_nr % 8))) & 1; + result |= (bit << (15 - i)); + } + s390_vec_write_element16(&tmp, 3, result); + *(S390Vector *)v1 = tmp; +} + void HELPER(vll)(CPUS390XState *env, void *v1, uint64_t addr, uint64_t bytes) { if (likely(bytes >= 16)) { |