diff options
author | Peter Maydell <peter.maydell@linaro.org> | 2017-02-02 18:48:06 +0000 |
---|---|---|
committer | Peter Maydell <peter.maydell@linaro.org> | 2017-02-02 18:48:06 +0000 |
commit | 5459ef3bff961bc462ac89460ab6b08a14624c8d (patch) | |
tree | 9308ed3504343e7bc9b4fc1b71a2b8fa7ae68592 /target | |
parent | 4e9f5244e1945b2852b9ddcd7f023a7d19c9ecd7 (diff) | |
parent | 7c6e8797337c24520b48d8b50a900a747e50f974 (diff) |
Merge remote-tracking branch 'remotes/dgibson/tags/ppc-for-2.9-20170202' into staging
ppc patch queue 2017-02-02
This obsoletes ppc-for-2.9-20170112, which had a MacOS build bug.
This is a long overdue ppc pull request for qemu-2.9. It's been a
long time coming due to some holidays and inconveniently timed
problems with testing. So, there's a lot in here:
* More POWER9 instruction implementations for TCG
* The simpler parts of my CPU compatibility mode cleanup
* This changes behaviour to prefer compatibility modes over
"raW" mode for new machine type versions
* New "40p" machine type which is essentially a modernized and
cleaned up "prep". The intention is that it will replace "prep"
once it has some more testing and polish.
* Add pseries-2.9 machine type
* Implement H_SIGNAL_SYS_RESET hypercall
* Consolidate the two alternate CPU init paths in pseries by
making it always go through CPU core objects to initialize CPU
* A number of bugfixes and cleanups
* Stop the guest timebase when the guest is stopped under KVM.
This makes the guest system clock also stop when paused, which
matches the x86 behaviour.
* Some preliminary cleanups leading towards implementation of the
POWER9 MMU.
There are also some changes not strictly related to ppc code, but for
its benefit:
* Limit the pxi-expander-bridge (PXB) device to x86 guests only
(it's essentially a hack to work around historical x86
limitations)
* Some additions to the 128-bit math in host_utils, necessary for
some of the new instructions.
* Revise a number of qtests and enable them for ppc
# gpg: Signature made Thu 02 Feb 2017 01:40:16 GMT
# gpg: using RSA key 0x6C38CACA20D9B392
# gpg: Good signature from "David Gibson <david@gibson.dropbear.id.au>"
# gpg: aka "David Gibson (Red Hat) <dgibson@redhat.com>"
# gpg: aka "David Gibson (ozlabs.org) <dgibson@ozlabs.org>"
# gpg: aka "David Gibson (kernel.org) <dwg@kernel.org>"
# Primary key fingerprint: 75F4 6586 AE61 A66C C44E 87DC 6C38 CACA 20D9 B392
* remotes/dgibson/tags/ppc-for-2.9-20170202: (107 commits)
hw/ppc/pnv: Use error_report instead of hw_error if a ROM file can't be found
ppc/kvm: Handle the "family" CPU via alias instead of registering new types
target/ppc/mmu_hash64: Fix incorrect shift value in amr calculation
target/ppc/mmu_hash64: Fix printing unsigned as signed int
tcg/POWER9: NOOP the cp_abort instruction
target/ppc/debug: Print LPCR register value if register exists
target-ppc: Add xststdc[sp, dp, qp] instructions
target-ppc: Add xvtstdc[sp,dp] instructions
target-ppc: Add MMU model check for booke machines
ppc: switch to constants within BUILD_BUG_ON
target/ppc/cpu-models: Fix/remove bad CPU aliases
target/ppc: Remove unused POWERPC_FAMILY(POWER)
spapr: clock should count only if vm is running
ppc: Remove unused function cpu_ppc601_rtc_init()
target/ppc: Add pcr_supported to POWER9 cpu class definition
powerpc/cpu-models: rename ISAv3.00 logical PVR definition
target-ppc: Add xvcv[hpsp, sphp] instructions
target-ppc: Add xsmulqp instruction
target-ppc: Add xsdivqp instruction
target-ppc: Add xscvsdqp and xscvudqp instructions
...
# Conflicts:
# hw/pci-bridge/Makefile.objs
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Diffstat (limited to 'target')
-rw-r--r-- | target/ppc/Makefile.objs | 2 | ||||
-rw-r--r-- | target/ppc/compat.c | 185 | ||||
-rw-r--r-- | target/ppc/cpu-models.c | 22 | ||||
-rw-r--r-- | target/ppc/cpu-models.h | 2 | ||||
-rw-r--r-- | target/ppc/cpu-qom.h | 3 | ||||
-rw-r--r-- | target/ppc/cpu.h | 67 | ||||
-rw-r--r-- | target/ppc/excp_helper.c | 11 | ||||
-rw-r--r-- | target/ppc/fpu_helper.c | 756 | ||||
-rw-r--r-- | target/ppc/helper.h | 50 | ||||
-rw-r--r-- | target/ppc/int_helper.c | 473 | ||||
-rw-r--r-- | target/ppc/internal.h | 202 | ||||
-rw-r--r-- | target/ppc/kvm.c | 40 | ||||
-rw-r--r-- | target/ppc/kvm_ppc.h | 4 | ||||
-rw-r--r-- | target/ppc/mem_helper.c | 66 | ||||
-rw-r--r-- | target/ppc/mmu-hash64.c | 4 | ||||
-rw-r--r-- | target/ppc/mmu-hash64.h | 2 | ||||
-rw-r--r-- | target/ppc/translate.c | 244 | ||||
-rw-r--r-- | target/ppc/translate/fp-impl.inc.c | 20 | ||||
-rw-r--r-- | target/ppc/translate/fp-ops.inc.c | 2 | ||||
-rw-r--r-- | target/ppc/translate/vmx-impl.inc.c | 64 | ||||
-rw-r--r-- | target/ppc/translate/vmx-ops.inc.c | 23 | ||||
-rw-r--r-- | target/ppc/translate/vsx-impl.inc.c | 484 | ||||
-rw-r--r-- | target/ppc/translate/vsx-ops.inc.c | 74 | ||||
-rw-r--r-- | target/ppc/translate_init.c | 97 |
24 files changed, 2421 insertions, 476 deletions
diff --git a/target/ppc/Makefile.objs b/target/ppc/Makefile.objs index e667e69701..a8c7a30cde 100644 --- a/target/ppc/Makefile.objs +++ b/target/ppc/Makefile.objs @@ -2,7 +2,7 @@ obj-y += cpu-models.o obj-y += translate.o ifeq ($(CONFIG_SOFTMMU),y) obj-y += machine.o mmu_helper.o mmu-hash32.o monitor.o -obj-$(TARGET_PPC64) += mmu-hash64.o arch_dump.o +obj-$(TARGET_PPC64) += mmu-hash64.o arch_dump.o compat.o endif obj-$(CONFIG_KVM) += kvm.o obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o diff --git a/target/ppc/compat.c b/target/ppc/compat.c new file mode 100644 index 0000000000..458da262be --- /dev/null +++ b/target/ppc/compat.c @@ -0,0 +1,185 @@ +/* + * PowerPC CPU initialization for qemu. + * + * Copyright 2016, David Gibson, Red Hat Inc. <dgibson@redhat.com> + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "sysemu/hw_accel.h" +#include "sysemu/kvm.h" +#include "kvm_ppc.h" +#include "sysemu/cpus.h" +#include "qemu/error-report.h" +#include "qapi/error.h" +#include "cpu-models.h" + +typedef struct { + uint32_t pvr; + uint64_t pcr; + uint64_t pcr_level; + int max_threads; +} CompatInfo; + +static const CompatInfo compat_table[] = { + /* + * Ordered from oldest to newest - the code relies on this + */ + { /* POWER6, ISA2.05 */ + .pvr = CPU_POWERPC_LOGICAL_2_05, + .pcr = PCR_COMPAT_2_07 | PCR_COMPAT_2_06 | PCR_COMPAT_2_05 + | PCR_TM_DIS | PCR_VSX_DIS, + .pcr_level = PCR_COMPAT_2_05, + .max_threads = 2, + }, + { /* POWER7, ISA2.06 */ + .pvr = CPU_POWERPC_LOGICAL_2_06, + .pcr = PCR_COMPAT_2_07 | PCR_COMPAT_2_06 | PCR_TM_DIS, + .pcr_level = PCR_COMPAT_2_06, + .max_threads = 4, + }, + { + .pvr = CPU_POWERPC_LOGICAL_2_06_PLUS, + .pcr = PCR_COMPAT_2_07 | PCR_COMPAT_2_06 | PCR_TM_DIS, + .pcr_level = PCR_COMPAT_2_06, + .max_threads = 4, + }, + { /* POWER8, ISA2.07 */ + .pvr = CPU_POWERPC_LOGICAL_2_07, + .pcr = PCR_COMPAT_2_07, + .pcr_level = PCR_COMPAT_2_07, + .max_threads = 8, + }, +}; + +static const CompatInfo *compat_by_pvr(uint32_t pvr) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(compat_table); i++) { + if (compat_table[i].pvr == pvr) { + return &compat_table[i]; + } + } + return NULL; +} + +bool ppc_check_compat(PowerPCCPU *cpu, uint32_t compat_pvr, + uint32_t min_compat_pvr, uint32_t max_compat_pvr) +{ + PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu); + const CompatInfo *compat = compat_by_pvr(compat_pvr); + const CompatInfo *min = compat_by_pvr(min_compat_pvr); + const CompatInfo *max = compat_by_pvr(max_compat_pvr); + +#if !defined(CONFIG_USER_ONLY) + g_assert(cpu->vhyp); +#endif + g_assert(!min_compat_pvr || min); + g_assert(!max_compat_pvr || max); + + if (!compat) { + /* Not a recognized logical PVR */ + return false; + } + if ((min && (compat < min)) || (max && (compat > max))) { + /* Outside specified range */ + return false; + } + if (!(pcc->pcr_supported & compat->pcr_level)) { + /* Not supported by this CPU */ + return false; + } + return true; +} + +void ppc_set_compat(PowerPCCPU *cpu, uint32_t compat_pvr, Error **errp) +{ + const CompatInfo *compat = compat_by_pvr(compat_pvr); + CPUPPCState *env = &cpu->env; + PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu); + uint64_t pcr; + + if (!compat_pvr) { + pcr = 0; + } else if (!compat) { + error_setg(errp, "Unknown compatibility PVR 0x%08"PRIx32, compat_pvr); + return; + } else if (!ppc_check_compat(cpu, compat_pvr, 0, 0)) { + error_setg(errp, "Compatibility PVR 0x%08"PRIx32" not valid for CPU", + compat_pvr); + return; + } else { + pcr = compat->pcr; + } + + cpu_synchronize_state(CPU(cpu)); + + cpu->compat_pvr = compat_pvr; + env->spr[SPR_PCR] = pcr & pcc->pcr_mask; + + if (kvm_enabled()) { + int ret = kvmppc_set_compat(cpu, cpu->compat_pvr); + if (ret < 0) { + error_setg_errno(errp, -ret, + "Unable to set CPU compatibility mode in KVM"); + } + } +} + +typedef struct { + uint32_t compat_pvr; + Error *err; +} SetCompatState; + +static void do_set_compat(CPUState *cs, run_on_cpu_data arg) +{ + PowerPCCPU *cpu = POWERPC_CPU(cs); + SetCompatState *s = arg.host_ptr; + + ppc_set_compat(cpu, s->compat_pvr, &s->err); +} + +void ppc_set_compat_all(uint32_t compat_pvr, Error **errp) +{ + CPUState *cs; + + CPU_FOREACH(cs) { + SetCompatState s = { + .compat_pvr = compat_pvr, + .err = NULL, + }; + + run_on_cpu(cs, do_set_compat, RUN_ON_CPU_HOST_PTR(&s)); + + if (s.err) { + error_propagate(errp, s.err); + return; + } + } +} + +int ppc_compat_max_threads(PowerPCCPU *cpu) +{ + const CompatInfo *compat = compat_by_pvr(cpu->compat_pvr); + int n_threads = CPU(cpu)->nr_threads; + + if (cpu->compat_pvr) { + g_assert(compat); + n_threads = MIN(n_threads, compat->max_threads); + } + + return n_threads; +} diff --git a/target/ppc/cpu-models.c b/target/ppc/cpu-models.c index 506dee1ee8..4d3e6354cf 100644 --- a/target/ppc/cpu-models.c +++ b/target/ppc/cpu-models.c @@ -1375,19 +1375,15 @@ PowerPCCPUAlias ppc_cpu_aliases[] = { { "7445", "7445_v3.2" }, { "7455", "7455_v3.2" }, { "Apollo6", "7455" }, - { "7447", "7447_v1.2" }, + { "7447", "7447_v1.1" }, { "7457", "7457_v1.2" }, { "Apollo7", "7457" }, { "7447A", "7447A_v1.2" }, { "7457A", "7457A_v1.2" }, { "Apollo7PM", "7457A_v1.0" }, #if defined(TARGET_PPC64) - { "Trident", "620" }, { "POWER3", "630" }, - { "Boxer", "POWER3" }, - { "Dino", "POWER3" }, { "POWER3+", "631" }, - { "POWER5gr", "POWER5" }, { "POWER5+", "POWER5+_v2.1" }, { "POWER5gs", "POWER5+_v2.1" }, { "POWER7", "POWER7_v2.3" }, @@ -1399,21 +1395,7 @@ PowerPCCPUAlias ppc_cpu_aliases[] = { { "970", "970_v2.2" }, { "970fx", "970fx_v3.1" }, { "970mp", "970mp_v1.1" }, - { "Apache", "RS64" }, - { "A35", "RS64" }, - { "NorthStar", "RS64-II" }, - { "A50", "RS64-II" }, - { "Pulsar", "RS64-III" }, - { "IceStar", "RS64-IV" }, - { "IStar", "RS64-IV" }, - { "SStar", "RS64-IV" }, -#endif - { "RIOS", "POWER" }, - { "RSC", "POWER" }, - { "RSC3308", "POWER" }, - { "RSC4608", "POWER" }, - { "RSC2", "POWER2" }, - { "P2SC", "POWER2" }, +#endif /* Generic PowerPCs */ #if defined(TARGET_PPC64) diff --git a/target/ppc/cpu-models.h b/target/ppc/cpu-models.h index aafbbd7d5d..d587e69bbc 100644 --- a/target/ppc/cpu-models.h +++ b/target/ppc/cpu-models.h @@ -601,7 +601,7 @@ enum { CPU_POWERPC_LOGICAL_2_06 = 0x0F000003, CPU_POWERPC_LOGICAL_2_06_PLUS = 0x0F100003, CPU_POWERPC_LOGICAL_2_07 = 0x0F000004, - CPU_POWERPC_LOGICAL_2_08 = 0x0F000005, + CPU_POWERPC_LOGICAL_3_00 = 0x0F000005, }; /* System version register (used on MPC 8xxx) */ diff --git a/target/ppc/cpu-qom.h b/target/ppc/cpu-qom.h index d46c31a15d..b7977bad18 100644 --- a/target/ppc/cpu-qom.h +++ b/target/ppc/cpu-qom.h @@ -214,6 +214,9 @@ extern const struct VMStateDescription vmstate_ppc_timebase; .flags = VMS_STRUCT, \ .offset = vmstate_offset_value(_state, _field, PPCTimebase), \ } + +void cpu_ppc_clock_vm_state_change(void *opaque, int running, + RunState state); #endif #endif diff --git a/target/ppc/cpu.h b/target/ppc/cpu.h index 2a50c43689..bc2a2ce431 100644 --- a/target/ppc/cpu.h +++ b/target/ppc/cpu.h @@ -21,6 +21,7 @@ #define PPC_CPU_H #include "qemu-common.h" +#include "qemu/int128.h" //#define PPC_EMULATE_32BITS_HYPV @@ -262,6 +263,7 @@ union ppc_avr_t { #ifdef CONFIG_INT128 __uint128_t u128; #endif + Int128 s128; }; #if !defined(CONFIG_USER_ONLY) @@ -1148,12 +1150,15 @@ do { \ env->wdt_period[3] = (d_); \ } while (0) +typedef struct PPCVirtualHypervisor PPCVirtualHypervisor; +typedef struct PPCVirtualHypervisorClass PPCVirtualHypervisorClass; + /** * PowerPCCPU: * @env: #CPUPPCState * @cpu_dt_id: CPU index used in the device tree. KVM uses this index too * @max_compat: Maximal supported logical PVR from the command line - * @cpu_version: Current logical PVR, zero if in "raw" mode + * @compat_pvr: Current logical PVR, zero if in "raw" mode * * A PowerPC CPU. */ @@ -1165,7 +1170,8 @@ struct PowerPCCPU { CPUPPCState env; int cpu_dt_id; uint32_t max_compat; - uint32_t cpu_version; + uint32_t compat_pvr; + PPCVirtualHypervisor *vhyp; /* Fields related to migration compatibility hacks */ bool pre_2_8_migration; @@ -1187,6 +1193,25 @@ static inline PowerPCCPU *ppc_env_get_cpu(CPUPPCState *env) PowerPCCPUClass *ppc_cpu_class_by_pvr(uint32_t pvr); PowerPCCPUClass *ppc_cpu_class_by_pvr_mask(uint32_t pvr); +struct PPCVirtualHypervisor { + Object parent; +}; + +struct PPCVirtualHypervisorClass { + InterfaceClass parent; + void (*hypercall)(PPCVirtualHypervisor *vhyp, PowerPCCPU *cpu); +}; + +#define TYPE_PPC_VIRTUAL_HYPERVISOR "ppc-virtual-hypervisor" +#define PPC_VIRTUAL_HYPERVISOR(obj) \ + OBJECT_CHECK(PPCVirtualHypervisor, (obj), TYPE_PPC_VIRTUAL_HYPERVISOR) +#define PPC_VIRTUAL_HYPERVISOR_CLASS(klass) \ + OBJECT_CLASS_CHECK(PPCVirtualHypervisorClass, (klass), \ + TYPE_PPC_VIRTUAL_HYPERVISOR) +#define PPC_VIRTUAL_HYPERVISOR_GET_CLASS(obj) \ + OBJECT_GET_CLASS(PPCVirtualHypervisorClass, (obj), \ + TYPE_PPC_VIRTUAL_HYPERVISOR) + void ppc_cpu_do_interrupt(CPUState *cpu); bool ppc_cpu_exec_interrupt(CPUState *cpu, int int_req); void ppc_cpu_dump_state(CPUState *cpu, FILE *f, fprintf_function cpu_fprintf, @@ -1225,9 +1250,7 @@ void ppc_store_sdr1 (CPUPPCState *env, target_ulong value); void ppc_store_msr (CPUPPCState *env, target_ulong value); void ppc_cpu_list (FILE *f, fprintf_function cpu_fprintf); -int ppc_get_compat_smt_threads(PowerPCCPU *cpu); #if defined(TARGET_PPC64) -void ppc_set_compat(PowerPCCPU *cpu, uint32_t cpu_version, Error **errp); #endif /* Time-base and decrementer management */ @@ -1259,6 +1282,7 @@ void store_booke_tcr (CPUPPCState *env, target_ulong val); void store_booke_tsr (CPUPPCState *env, target_ulong val); void ppc_tlb_invalidate_all (CPUPPCState *env); void ppc_tlb_invalidate_one (CPUPPCState *env, target_ulong addr); +void cpu_ppc_set_vhyp(PowerPCCPU *cpu, PPCVirtualHypervisor *vhyp); void cpu_ppc_set_papr(PowerPCCPU *cpu); #endif #endif @@ -1297,18 +1321,34 @@ static inline int cpu_mmu_index (CPUPPCState *env, bool ifetch) return ifetch ? env->immu_idx : env->dmmu_idx; } +/* Compatibility modes */ +#if defined(TARGET_PPC64) +bool ppc_check_compat(PowerPCCPU *cpu, uint32_t compat_pvr, + uint32_t min_compat_pvr, uint32_t max_compat_pvr); +void ppc_set_compat(PowerPCCPU *cpu, uint32_t compat_pvr, Error **errp); +#if !defined(CONFIG_USER_ONLY) +void ppc_set_compat_all(uint32_t compat_pvr, Error **errp); +#endif +int ppc_compat_max_threads(PowerPCCPU *cpu); +#endif /* defined(TARGET_PPC64) */ + #include "exec/cpu-all.h" /*****************************************************************************/ /* CRF definitions */ -#define CRF_LT 3 -#define CRF_GT 2 -#define CRF_EQ 1 -#define CRF_SO 0 -#define CRF_CH (1 << CRF_LT) -#define CRF_CL (1 << CRF_GT) -#define CRF_CH_OR_CL (1 << CRF_EQ) -#define CRF_CH_AND_CL (1 << CRF_SO) +#define CRF_LT_BIT 3 +#define CRF_GT_BIT 2 +#define CRF_EQ_BIT 1 +#define CRF_SO_BIT 0 +#define CRF_LT (1 << CRF_LT_BIT) +#define CRF_GT (1 << CRF_GT_BIT) +#define CRF_EQ (1 << CRF_EQ_BIT) +#define CRF_SO (1 << CRF_SO_BIT) +/* For SPE extensions */ +#define CRF_CH (1 << CRF_LT_BIT) +#define CRF_CL (1 << CRF_GT_BIT) +#define CRF_CH_OR_CL (1 << CRF_EQ_BIT) +#define CRF_CH_AND_CL (1 << CRF_SO_BIT) /* XER definitions */ #define XER_SO 31 @@ -2250,6 +2290,7 @@ enum { PCR_COMPAT_2_05 = 1ull << (63-62), PCR_COMPAT_2_06 = 1ull << (63-61), PCR_COMPAT_2_07 = 1ull << (63-60), + PCR_COMPAT_3_00 = 1ull << (63-59), PCR_VEC_DIS = 1ull << (63-0), /* Vec. disable (bit NA since POWER8) */ PCR_VSX_DIS = 1ull << (63-1), /* VSX disable (bit NA since POWER8) */ PCR_TM_DIS = 1ull << (63-2), /* Trans. memory disable (POWER8) */ @@ -2428,8 +2469,6 @@ static inline bool lsw_reg_in_range(int start, int nregs, int rx) (start + nregs > 32 && (rx >= start || rx < start + nregs - 32)); } -extern void (*cpu_ppc_hypercall)(PowerPCCPU *); - void dump_mmu(FILE *f, fprintf_function cpu_fprintf, CPUPPCState *env); /** diff --git a/target/ppc/excp_helper.c b/target/ppc/excp_helper.c index 93369d4fe5..f4ee7aacd2 100644 --- a/target/ppc/excp_helper.c +++ b/target/ppc/excp_helper.c @@ -35,11 +35,6 @@ #endif /*****************************************************************************/ -/* PowerPC Hypercall emulation */ - -void (*cpu_ppc_hypercall)(PowerPCCPU *); - -/*****************************************************************************/ /* Exception processing */ #if defined(CONFIG_USER_ONLY) void ppc_cpu_do_interrupt(CPUState *cs) @@ -318,8 +313,10 @@ static inline void powerpc_excp(PowerPCCPU *cpu, int excp_model, int excp) env->nip += 4; /* "PAPR mode" built-in hypercall emulation */ - if ((lev == 1) && cpu_ppc_hypercall) { - cpu_ppc_hypercall(cpu); + if ((lev == 1) && cpu->vhyp) { + PPCVirtualHypervisorClass *vhc = + PPC_VIRTUAL_HYPERVISOR_GET_CLASS(cpu->vhyp); + vhc->hypercall(cpu->vhyp, cpu); return; } if (lev == 1) { diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c index 8a389e19af..9f5cafd5ba 100644 --- a/target/ppc/fpu_helper.c +++ b/target/ppc/fpu_helper.c @@ -20,9 +20,20 @@ #include "cpu.h" #include "exec/helper-proto.h" #include "exec/exec-all.h" +#include "internal.h" + +static inline float128 float128_snan_to_qnan(float128 x) +{ + float128 r; + + r.high = x.high | 0x0000800000000000; + r.low = x.low; + return r; +} #define float64_snan_to_qnan(x) ((x) | 0x0008000000000000ULL) #define float32_snan_to_qnan(x) ((x) | 0x00400000) +#define float16_snan_to_qnan(x) ((x) | 0x0200) /*****************************************************************************/ /* Floating point operations helpers */ @@ -46,15 +57,6 @@ uint32_t helper_float64_to_float32(CPUPPCState *env, uint64_t arg) return f.l; } -static inline int isden(float64 d) -{ - CPU_DoubleU u; - - u.d = d; - - return ((u.ll >> 52) & 0x7FF) == 0; -} - static inline int ppc_float32_get_unbiased_exp(float32 f) { return ((f >> 23) & 0xFF) - 127; @@ -65,56 +67,60 @@ static inline int ppc_float64_get_unbiased_exp(float64 f) return ((f >> 52) & 0x7FF) - 1023; } -void helper_compute_fprf(CPUPPCState *env, uint64_t arg) -{ - CPU_DoubleU farg; - int isneg; - int fprf; - - farg.ll = arg; - isneg = float64_is_neg(farg.d); - if (unlikely(float64_is_any_nan(farg.d))) { - if (float64_is_signaling_nan(farg.d, &env->fp_status)) { - /* Signaling NaN: flags are undefined */ - fprf = 0x00; - } else { - /* Quiet NaN */ - fprf = 0x11; - } - } else if (unlikely(float64_is_infinity(farg.d))) { - /* +/- infinity */ - if (isneg) { - fprf = 0x09; - } else { - fprf = 0x05; - } - } else { - if (float64_is_zero(farg.d)) { - /* +/- zero */ - if (isneg) { - fprf = 0x12; - } else { - fprf = 0x02; - } - } else { - if (isden(farg.d)) { - /* Denormalized numbers */ - fprf = 0x10; - } else { - /* Normalized numbers */ - fprf = 0x00; - } - if (isneg) { - fprf |= 0x08; - } else { - fprf |= 0x04; - } - } - } - /* We update FPSCR_FPRF */ - env->fpscr &= ~(0x1F << FPSCR_FPRF); - env->fpscr |= fprf << FPSCR_FPRF; -} +#define COMPUTE_FPRF(tp) \ +void helper_compute_fprf_##tp(CPUPPCState *env, tp arg) \ +{ \ + int isneg; \ + int fprf; \ + \ + isneg = tp##_is_neg(arg); \ + if (unlikely(tp##_is_any_nan(arg))) { \ + if (tp##_is_signaling_nan(arg, &env->fp_status)) { \ + /* Signaling NaN: flags are undefined */ \ + fprf = 0x00; \ + } else { \ + /* Quiet NaN */ \ + fprf = 0x11; \ + } \ + } else if (unlikely(tp##_is_infinity(arg))) { \ + /* +/- infinity */ \ + if (isneg) { \ + fprf = 0x09; \ + } else { \ + fprf = 0x05; \ + } \ + } else { \ + if (tp##_is_zero(arg)) { \ + /* +/- zero */ \ + if (isneg) { \ + fprf = 0x12; \ + } else { \ + fprf = 0x02; \ + } \ + } else { \ + if (tp##_is_zero_or_denormal(arg)) { \ + /* Denormalized numbers */ \ + fprf = 0x10; \ + } else { \ + /* Normalized numbers */ \ + fprf = 0x00; \ + } \ + if (isneg) { \ + fprf |= 0x08; \ + } else { \ + fprf |= 0x04; \ + } \ + } \ + } \ + /* We update FPSCR_FPRF */ \ + env->fpscr &= ~(0x1F << FPSCR_FPRF); \ + env->fpscr |= fprf << FPSCR_FPRF; \ +} + +COMPUTE_FPRF(float16) +COMPUTE_FPRF(float32) +COMPUTE_FPRF(float64) +COMPUTE_FPRF(float128) /* Floating-point invalid operations exception */ static inline __attribute__((__always_inline__)) @@ -1776,53 +1782,6 @@ uint32_t helper_efdcmpeq(CPUPPCState *env, uint64_t op1, uint64_t op2) return helper_efdtsteq(env, op1, op2); } -#define DECODE_SPLIT(opcode, shift1, nb1, shift2, nb2) \ - (((((opcode) >> (shift1)) & ((1 << (nb1)) - 1)) << nb2) | \ - (((opcode) >> (shift2)) & ((1 << (nb2)) - 1))) - -#define xT(opcode) DECODE_SPLIT(opcode, 0, 1, 21, 5) -#define xA(opcode) DECODE_SPLIT(opcode, 2, 1, 16, 5) -#define xB(opcode) DECODE_SPLIT(opcode, 1, 1, 11, 5) -#define xC(opcode) DECODE_SPLIT(opcode, 3, 1, 6, 5) -#define BF(opcode) (((opcode) >> (31-8)) & 7) - -typedef union _ppc_vsr_t { - uint64_t u64[2]; - uint32_t u32[4]; - float32 f32[4]; - float64 f64[2]; -} ppc_vsr_t; - -#if defined(HOST_WORDS_BIGENDIAN) -#define VsrW(i) u32[i] -#define VsrD(i) u64[i] -#else -#define VsrW(i) u32[3-(i)] -#define VsrD(i) u64[1-(i)] -#endif - -static void getVSR(int n, ppc_vsr_t *vsr, CPUPPCState *env) -{ - if (n < 32) { - vsr->VsrD(0) = env->fpr[n]; - vsr->VsrD(1) = env->vsr[n]; - } else { - vsr->u64[0] = env->avr[n-32].u64[0]; - vsr->u64[1] = env->avr[n-32].u64[1]; - } -} - -static void putVSR(int n, ppc_vsr_t *vsr, CPUPPCState *env) -{ - if (n < 32) { - env->fpr[n] = vsr->VsrD(0); - env->vsr[n] = vsr->VsrD(1); - } else { - env->avr[n-32].u64[0] = vsr->u64[0]; - env->avr[n-32].u64[1] = vsr->u64[1]; - } -} - #define float64_to_float64(x, env) x @@ -1865,7 +1824,7 @@ void helper_##name(CPUPPCState *env, uint32_t opcode) \ } \ \ if (sfprf) { \ - helper_compute_fprf(env, xt.fld); \ + helper_compute_fprf_float64(env, xt.fld); \ } \ } \ putVSR(xT(opcode), &xt, env); \ @@ -1881,6 +1840,41 @@ VSX_ADD_SUB(xssubsp, sub, 1, float64, VsrD(0), 1, 1) VSX_ADD_SUB(xvsubdp, sub, 2, float64, VsrD(i), 0, 0) VSX_ADD_SUB(xvsubsp, sub, 4, float32, VsrW(i), 0, 0) +void helper_xsaddqp(CPUPPCState *env, uint32_t opcode) +{ + ppc_vsr_t xt, xa, xb; + float_status tstat; + + getVSR(rA(opcode) + 32, &xa, env); + getVSR(rB(opcode) + 32, &xb, env); + getVSR(rD(opcode) + 32, &xt, env); + helper_reset_fpstatus(env); + + if (unlikely(Rc(opcode) != 0)) { + /* TODO: Support xsadddpo after round-to-odd is implemented */ + abort(); + } + + tstat = env->fp_status; + set_float_exception_flags(0, &tstat); + xt.f128 = float128_add(xa.f128, xb.f128, &tstat); + env->fp_status.float_exception_flags |= tstat.float_exception_flags; + + if (unlikely(tstat.float_exception_flags & float_flag_invalid)) { + if (float128_is_infinity(xa.f128) && float128_is_infinity(xb.f128)) { + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXISI, 1); + } else if (float128_is_signaling_nan(xa.f128, &tstat) || + float128_is_signaling_nan(xb.f128, &tstat)) { + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1); + } + } + + helper_compute_fprf_float128(env, xt.f128); + + putVSR(rD(opcode) + 32, &xt, env); + float_check_status(env); +} + /* VSX_MUL - VSX floating point multiply * op - instruction mnemonic * nels - number of elements (1, 2 or 4) @@ -1920,7 +1914,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ } \ \ if (sfprf) { \ - helper_compute_fprf(env, xt.fld); \ + helper_compute_fprf_float64(env, xt.fld); \ } \ } \ \ @@ -1933,6 +1927,41 @@ VSX_MUL(xsmulsp, 1, float64, VsrD(0), 1, 1) VSX_MUL(xvmuldp, 2, float64, VsrD(i), 0, 0) VSX_MUL(xvmulsp, 4, float32, VsrW(i), 0, 0) +void helper_xsmulqp(CPUPPCState *env, uint32_t opcode) +{ + ppc_vsr_t xt, xa, xb; + + getVSR(rA(opcode) + 32, &xa, env); + getVSR(rB(opcode) + 32, &xb, env); + getVSR(rD(opcode) + 32, &xt, env); + + if (unlikely(Rc(opcode) != 0)) { + /* TODO: Support xsmulpo after round-to-odd is implemented */ + abort(); + } + + helper_reset_fpstatus(env); + + float_status tstat = env->fp_status; + set_float_exception_flags(0, &tstat); + xt.f128 = float128_mul(xa.f128, xb.f128, &tstat); + env->fp_status.float_exception_flags |= tstat.float_exception_flags; + + if (unlikely(tstat.float_exception_flags & float_flag_invalid)) { + if ((float128_is_infinity(xa.f128) && float128_is_zero(xb.f128)) || + (float128_is_infinity(xb.f128) && float128_is_zero(xa.f128))) { + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXIMZ, 1); + } else if (float128_is_signaling_nan(xa.f128, &tstat) || + float128_is_signaling_nan(xb.f128, &tstat)) { + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1); + } + } + helper_compute_fprf_float128(env, xt.f128); + + putVSR(rD(opcode) + 32, &xt, env); + float_check_status(env); +} + /* VSX_DIV - VSX floating point divide * op - instruction mnemonic * nels - number of elements (1, 2 or 4) @@ -1974,7 +2003,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ } \ \ if (sfprf) { \ - helper_compute_fprf(env, xt.fld); \ + helper_compute_fprf_float64(env, xt.fld); \ } \ } \ \ @@ -1987,6 +2016,42 @@ VSX_DIV(xsdivsp, 1, float64, VsrD(0), 1, 1) VSX_DIV(xvdivdp, 2, float64, VsrD(i), 0, 0) VSX_DIV(xvdivsp, 4, float32, VsrW(i), 0, 0) +void helper_xsdivqp(CPUPPCState *env, uint32_t opcode) +{ + ppc_vsr_t xt, xa, xb; + + getVSR(rA(opcode) + 32, &xa, env); + getVSR(rB(opcode) + 32, &xb, env); + getVSR(rD(opcode) + 32, &xt, env); + + if (unlikely(Rc(opcode) != 0)) { + /* TODO: Support xsdivqpo after round-to-odd is implemented */ + abort(); + } + + helper_reset_fpstatus(env); + float_status tstat = env->fp_status; + set_float_exception_flags(0, &tstat); + xt.f128 = float128_div(xa.f128, xb.f128, &tstat); + env->fp_status.float_exception_flags |= tstat.float_exception_flags; + + if (unlikely(tstat.float_exception_flags & float_flag_invalid)) { + if (float128_is_infinity(xa.f128) && float128_is_infinity(xb.f128)) { + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXIDI, 1); + } else if (float128_is_zero(xa.f128) && + float128_is_zero(xb.f128)) { + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXZDZ, 1); + } else if (float128_is_signaling_nan(xa.f128, &tstat) || + float128_is_signaling_nan(xb.f128, &tstat)) { + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 1); + } + } + + helper_compute_fprf_float128(env, xt.f128); + putVSR(rD(opcode) + 32, &xt, env); + float_check_status(env); +} + /* VSX_RE - VSX floating point reciprocal estimate * op - instruction mnemonic * nels - number of elements (1, 2 or 4) @@ -2015,7 +2080,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ } \ \ if (sfprf) { \ - helper_compute_fprf(env, xt.fld); \ + helper_compute_fprf_float64(env, xt.fld); \ } \ } \ \ @@ -2064,7 +2129,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ } \ \ if (sfprf) { \ - helper_compute_fprf(env, xt.fld); \ + helper_compute_fprf_float64(env, xt.fld); \ } \ } \ \ @@ -2114,7 +2179,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ } \ \ if (sfprf) { \ - helper_compute_fprf(env, xt.fld); \ + helper_compute_fprf_float64(env, xt.fld); \ } \ } \ \ @@ -2314,7 +2379,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ } \ \ if (sfprf) { \ - helper_compute_fprf(env, xt_out.fld); \ + helper_compute_fprf_float64(env, xt_out.fld); \ } \ } \ putVSR(xT(opcode), &xt_out, env); \ @@ -2414,34 +2479,108 @@ VSX_SCALAR_CMP_DP(xscmpgedp, le, 1, 1) VSX_SCALAR_CMP_DP(xscmpgtdp, lt, 1, 1) VSX_SCALAR_CMP_DP(xscmpnedp, eq, 0, 0) +void helper_xscmpexpdp(CPUPPCState *env, uint32_t opcode) +{ + ppc_vsr_t xa, xb; + int64_t exp_a, exp_b; + uint32_t cc; + + getVSR(xA(opcode), &xa, env); + getVSR(xB(opcode), &xb, env); + + exp_a = extract64(xa.VsrD(0), 52, 11); + exp_b = extract64(xb.VsrD(0), 52, 11); + + if (unlikely(float64_is_any_nan(xa.VsrD(0)) || + float64_is_any_nan(xb.VsrD(0)))) { + cc = CRF_SO; + } else { + if (exp_a < exp_b) { + cc = CRF_LT; + } else if (exp_a > exp_b) { + cc = CRF_GT; + } else { + cc = CRF_EQ; + } + } + + env->fpscr &= ~(0x0F << FPSCR_FPRF); + env->fpscr |= cc << FPSCR_FPRF; + env->crf[BF(opcode)] = cc; + + helper_float_check_status(env); +} + +void helper_xscmpexpqp(CPUPPCState *env, uint32_t opcode) +{ + ppc_vsr_t xa, xb; + int64_t exp_a, exp_b; + uint32_t cc; + + getVSR(rA(opcode) + 32, &xa, env); + getVSR(rB(opcode) + 32, &xb, env); + + exp_a = extract64(xa.VsrD(0), 48, 15); + exp_b = extract64(xb.VsrD(0), 48, 15); + + if (unlikely(float128_is_any_nan(xa.f128) || + float128_is_any_nan(xb.f128))) { + cc = CRF_SO; + } else { + if (exp_a < exp_b) { + cc = CRF_LT; + } else if (exp_a > exp_b) { + cc = CRF_GT; + } else { + cc = CRF_EQ; + } + } + + env->fpscr &= ~(0x0F << FPSCR_FPRF); + env->fpscr |= cc << FPSCR_FPRF; + env->crf[BF(opcode)] = cc; + + helper_float_check_status(env); +} + #define VSX_SCALAR_CMP(op, ordered) \ void helper_##op(CPUPPCState *env, uint32_t opcode) \ { \ ppc_vsr_t xa, xb; \ uint32_t cc = 0; \ + bool vxsnan_flag = false, vxvc_flag = false; \ \ + helper_reset_fpstatus(env); \ getVSR(xA(opcode), &xa, env); \ getVSR(xB(opcode), &xb, env); \ \ - if (unlikely(float64_is_any_nan(xa.VsrD(0)) || \ - float64_is_any_nan(xb.VsrD(0)))) { \ - if (float64_is_signaling_nan(xa.VsrD(0), &env->fp_status) || \ - float64_is_signaling_nan(xb.VsrD(0), &env->fp_status)) { \ - float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0); \ + if (float64_is_signaling_nan(xa.VsrD(0), &env->fp_status) || \ + float64_is_signaling_nan(xb.VsrD(0), &env->fp_status)) { \ + vxsnan_flag = true; \ + cc = CRF_SO; \ + if (fpscr_ve == 0 && ordered) { \ + vxvc_flag = true; \ } \ + } else if (float64_is_quiet_nan(xa.VsrD(0), &env->fp_status) || \ + float64_is_quiet_nan(xb.VsrD(0), &env->fp_status)) { \ + cc = CRF_SO; \ if (ordered) { \ - float_invalid_op_excp(env, POWERPC_EXCP_FP_VXVC, 0); \ + vxvc_flag = true; \ } \ - cc = 1; \ + } \ + if (vxsnan_flag) { \ + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0); \ + } \ + if (vxvc_flag) { \ + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXVC, 0); \ + } \ + \ + if (float64_lt(xa.VsrD(0), xb.VsrD(0), &env->fp_status)) { \ + cc |= CRF_LT; \ + } else if (!float64_le(xa.VsrD(0), xb.VsrD(0), &env->fp_status)) { \ + cc |= CRF_GT; \ } else { \ - if (float64_lt(xa.VsrD(0), xb.VsrD(0), &env->fp_status)) { \ - cc = 8; \ - } else if (!float64_le(xa.VsrD(0), xb.VsrD(0), \ - &env->fp_status)) { \ - cc = 4; \ - } else { \ - cc = 2; \ - } \ + cc |= CRF_EQ; \ } \ \ env->fpscr &= ~(0x0F << FPSCR_FPRF); \ @@ -2454,6 +2593,56 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ VSX_SCALAR_CMP(xscmpodp, 1) VSX_SCALAR_CMP(xscmpudp, 0) +#define VSX_SCALAR_CMPQ(op, ordered) \ +void helper_##op(CPUPPCState *env, uint32_t opcode) \ +{ \ + ppc_vsr_t xa, xb; \ + uint32_t cc = 0; \ + bool vxsnan_flag = false, vxvc_flag = false; \ + \ + helper_reset_fpstatus(env); \ + getVSR(rA(opcode) + 32, &xa, env); \ + getVSR(rB(opcode) + 32, &xb, env); \ + \ + if (float128_is_signaling_nan(xa.f128, &env->fp_status) || \ + float128_is_signaling_nan(xb.f128, &env->fp_status)) { \ + vxsnan_flag = true; \ + cc = CRF_SO; \ + if (fpscr_ve == 0 && ordered) { \ + vxvc_flag = true; \ + } \ + } else if (float128_is_quiet_nan(xa.f128, &env->fp_status) || \ + float128_is_quiet_nan(xb.f128, &env->fp_status)) { \ + cc = CRF_SO; \ + if (ordered) { \ + vxvc_flag = true; \ + } \ + } \ + if (vxsnan_flag) { \ + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0); \ + } \ + if (vxvc_flag) { \ + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXVC, 0); \ + } \ + \ + if (float128_lt(xa.f128, xb.f128, &env->fp_status)) { \ + cc |= CRF_LT; \ + } else if (!float128_le(xa.f128, xb.f128, &env->fp_status)) { \ + cc |= CRF_GT; \ + } else { \ + cc |= CRF_EQ; \ + } \ + \ + env->fpscr &= ~(0x0F << FPSCR_FPRF); \ + env->fpscr |= cc << FPSCR_FPRF; \ + env->crf[BF(opcode)] = cc; \ + \ + float_check_status(env); \ +} + +VSX_SCALAR_CMPQ(xscmpoqp, 1) +VSX_SCALAR_CMPQ(xscmpuqp, 0) + /* VSX_MAX_MIN - VSX floating point maximum/minimum * name - instruction mnemonic * op - operation (max or min) @@ -2576,8 +2765,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ xt.tfld = ttp##_snan_to_qnan(xt.tfld); \ } \ if (sfprf) { \ - helper_compute_fprf(env, ttp##_to_float64(xt.tfld, \ - &env->fp_status)); \ + helper_compute_fprf_##ttp(env, xt.tfld); \ } \ } \ \ @@ -2590,6 +2778,110 @@ VSX_CVT_FP_TO_FP(xscvspdp, 1, float32, float64, VsrW(0), VsrD(0), 1) VSX_CVT_FP_TO_FP(xvcvdpsp, 2, float64, float32, VsrD(i), VsrW(2*i), 0) VSX_CVT_FP_TO_FP(xvcvspdp, 2, float32, float64, VsrW(2*i), VsrD(i), 0) +/* VSX_CVT_FP_TO_FP_VECTOR - VSX floating point/floating point conversion + * op - instruction mnemonic + * nels - number of elements (1, 2 or 4) + * stp - source type (float32 or float64) + * ttp - target type (float32 or float64) + * sfld - source vsr_t field + * tfld - target vsr_t field (f32 or f64) + * sfprf - set FPRF + */ +#define VSX_CVT_FP_TO_FP_VECTOR(op, nels, stp, ttp, sfld, tfld, sfprf) \ +void helper_##op(CPUPPCState *env, uint32_t opcode) \ +{ \ + ppc_vsr_t xt, xb; \ + int i; \ + \ + getVSR(rB(opcode) + 32, &xb, env); \ + getVSR(rD(opcode) + 32, &xt, env); \ + \ + for (i = 0; i < nels; i++) { \ + xt.tfld = stp##_to_##ttp(xb.sfld, &env->fp_status); \ + if (unlikely(stp##_is_signaling_nan(xb.sfld, \ + &env->fp_status))) { \ + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0); \ + xt.tfld = ttp##_snan_to_qnan(xt.tfld); \ + } \ + if (sfprf) { \ + helper_compute_fprf_##ttp(env, xt.tfld); \ + } \ + } \ + \ + putVSR(rD(opcode) + 32, &xt, env); \ + float_check_status(env); \ +} + +VSX_CVT_FP_TO_FP_VECTOR(xscvdpqp, 1, float64, float128, VsrD(0), f128, 1) + +/* VSX_CVT_FP_TO_FP_HP - VSX floating point/floating point conversion + * involving one half precision value + * op - instruction mnemonic + * nels - number of elements (1, 2 or 4) + * stp - source type + * ttp - target type + * sfld - source vsr_t field + * tfld - target vsr_t field + * sfprf - set FPRF + */ +#define VSX_CVT_FP_TO_FP_HP(op, nels, stp, ttp, sfld, tfld, sfprf) \ +void helper_##op(CPUPPCState *env, uint32_t opcode) \ +{ \ + ppc_vsr_t xt, xb; \ + int i; \ + \ + getVSR(xB(opcode), &xb, env); \ + memset(&xt, 0, sizeof(xt)); \ + \ + for (i = 0; i < nels; i++) { \ + xt.tfld = stp##_to_##ttp(xb.sfld, 1, &env->fp_status); \ + if (unlikely(stp##_is_signaling_nan(xb.sfld, \ + &env->fp_status))) { \ + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0); \ + xt.tfld = ttp##_snan_to_qnan(xt.tfld); \ + } \ + if (sfprf) { \ + helper_compute_fprf_##ttp(env, xt.tfld); \ + } \ + } \ + \ + putVSR(xT(opcode), &xt, env); \ + float_check_status(env); \ +} + +VSX_CVT_FP_TO_FP_HP(xscvdphp, 1, float64, float16, VsrD(0), VsrH(3), 1) +VSX_CVT_FP_TO_FP_HP(xscvhpdp, 1, float16, float64, VsrH(3), VsrD(0), 1) +VSX_CVT_FP_TO_FP_HP(xvcvsphp, 4, float32, float16, VsrW(i), VsrH(2 * i + 1), 0) +VSX_CVT_FP_TO_FP_HP(xvcvhpsp, 4, float16, float32, VsrH(2 * i + 1), VsrW(i), 0) + +/* + * xscvqpdp isn't using VSX_CVT_FP_TO_FP() because xscvqpdpo will be + * added to this later. + */ +void helper_xscvqpdp(CPUPPCState *env, uint32_t opcode) +{ + ppc_vsr_t xt, xb; + + getVSR(rB(opcode) + 32, &xb, env); + memset(&xt, 0, sizeof(xt)); + + if (unlikely(Rc(opcode) != 0)) { + /* TODO: Support xscvqpdpo after round-to-odd is implemented */ + abort(); + } + + xt.VsrD(0) = float128_to_float64(xb.f128, &env->fp_status); + if (unlikely(float128_is_signaling_nan(xb.f128, + &env->fp_status))) { + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0); + xt.VsrD(0) = float64_snan_to_qnan(xt.VsrD(0)); + } + helper_compute_fprf_float64(env, xt.VsrD(0)); + + putVSR(rD(opcode) + 32, &xt, env); + float_check_status(env); +} + uint64_t helper_xscvdpspn(CPUPPCState *env, uint64_t xb) { float_status tstat = env->fp_status; @@ -2662,6 +2954,46 @@ VSX_CVT_FP_TO_INT(xvcvspsxws, 4, float32, int32, VsrW(i), VsrW(i), 0x80000000U) VSX_CVT_FP_TO_INT(xvcvspuxds, 2, float32, uint64, VsrW(2*i), VsrD(i), 0ULL) VSX_CVT_FP_TO_INT(xvcvspuxws, 4, float32, uint32, VsrW(i), VsrW(i), 0U) +/* VSX_CVT_FP_TO_INT_VECTOR - VSX floating point to integer conversion + * op - instruction mnemonic + * stp - source type (float32 or float64) + * ttp - target type (int32, uint32, int64 or uint64) + * sfld - source vsr_t field + * tfld - target vsr_t field + * rnan - resulting NaN + */ +#define VSX_CVT_FP_TO_INT_VECTOR(op, stp, ttp, sfld, tfld, rnan) \ +void helper_##op(CPUPPCState *env, uint32_t opcode) \ +{ \ + ppc_vsr_t xt, xb; \ + \ + getVSR(rB(opcode) + 32, &xb, env); \ + memset(&xt, 0, sizeof(xt)); \ + \ + if (unlikely(stp##_is_any_nan(xb.sfld))) { \ + if (stp##_is_signaling_nan(xb.sfld, &env->fp_status)) { \ + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXSNAN, 0); \ + } \ + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI, 0); \ + xt.tfld = rnan; \ + } else { \ + xt.tfld = stp##_to_##ttp##_round_to_zero(xb.sfld, \ + &env->fp_status); \ + if (env->fp_status.float_exception_flags & float_flag_invalid) { \ + float_invalid_op_excp(env, POWERPC_EXCP_FP_VXCVI, 0); \ + } \ + } \ + \ + putVSR(rD(opcode) + 32, &xt, env); \ + float_check_status(env); \ +} + +VSX_CVT_FP_TO_INT_VECTOR(xscvqpsdz, float128, int64, f128, VsrD(0), \ + 0x8000000000000000ULL) + +VSX_CVT_FP_TO_INT_VECTOR(xscvqpswz, float128, int32, f128, VsrD(0), \ + 0xffffffff80000000ULL) + /* VSX_CVT_INT_TO_FP - VSX integer to floating point conversion * op - instruction mnemonic * nels - number of elements (1, 2 or 4) @@ -2687,7 +3019,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ xt.tfld = helper_frsp(env, xt.tfld); \ } \ if (sfprf) { \ - helper_compute_fprf(env, xt.tfld); \ + helper_compute_fprf_float64(env, xt.tfld); \ } \ } \ \ @@ -2708,6 +3040,31 @@ VSX_CVT_INT_TO_FP(xvcvuxdsp, 2, uint64, float32, VsrD(i), VsrW(2*i), 0, 0) VSX_CVT_INT_TO_FP(xvcvsxwsp, 4, int32, float32, VsrW(i), VsrW(i), 0, 0) VSX_CVT_INT_TO_FP(xvcvuxwsp, 4, uint32, float32, VsrW(i), VsrW(i), 0, 0) +/* VSX_CVT_INT_TO_FP_VECTOR - VSX integer to floating point conversion + * op - instruction mnemonic + * stp - source type (int32, uint32, int64 or uint64) + * ttp - target type (float32 or float64) + * sfld - source vsr_t field + * tfld - target vsr_t field + */ +#define VSX_CVT_INT_TO_FP_VECTOR(op, stp, ttp, sfld, tfld) \ +void helper_##op(CPUPPCState *env, uint32_t opcode) \ +{ \ + ppc_vsr_t xt, xb; \ + \ + getVSR(rB(opcode) + 32, &xb, env); \ + getVSR(rD(opcode) + 32, &xt, env); \ + \ + xt.tfld = stp##_to_##ttp(xb.sfld, &env->fp_status); \ + helper_compute_fprf_##ttp(env, xt.tfld); \ + \ + putVSR(xT(opcode) + 32, &xt, env); \ + float_check_status(env); \ +} + +VSX_CVT_INT_TO_FP_VECTOR(xscvsdqp, int64, float128, VsrD(0), f128) +VSX_CVT_INT_TO_FP_VECTOR(xscvudqp, uint64, float128, VsrD(0), f128) + /* For "use current rounding mode", define a value that will not be one of * the existing rounding model enums. */ @@ -2743,7 +3100,7 @@ void helper_##op(CPUPPCState *env, uint32_t opcode) \ xt.fld = tp##_round_to_int(xb.fld, &env->fp_status); \ } \ if (sfprf) { \ - helper_compute_fprf(env, xt.fld); \ + helper_compute_fprf_float64(env, xt.fld); \ } \ } \ \ @@ -2783,7 +3140,140 @@ uint64_t helper_xsrsp(CPUPPCState *env, uint64_t xb) uint64_t xt = helper_frsp(env, xb); - helper_compute_fprf(env, xt); + helper_compute_fprf_float64(env, xt); float_check_status(env); return xt; } + +#define VSX_XXPERM(op, indexed) \ +void helper_##op(CPUPPCState *env, uint32_t opcode) \ +{ \ + ppc_vsr_t xt, xa, pcv, xto; \ + int i, idx; \ + \ + getVSR(xA(opcode), &xa, env); \ + getVSR(xT(opcode), &xt, env); \ + getVSR(xB(opcode), &pcv, env); \ + \ + for (i = 0; i < 16; i++) { \ + idx = pcv.VsrB(i) & 0x1F; \ + if (indexed) { \ + idx = 31 - idx; \ + } \ + xto.VsrB(i) = (idx <= 15) ? xa.VsrB(idx) : xt.VsrB(idx - 16); \ + } \ + putVSR(xT(opcode), &xto, env); \ +} + +VSX_XXPERM(xxperm, 0) +VSX_XXPERM(xxpermr, 1) + +void helper_xvxsigsp(CPUPPCState *env, uint32_t opcode) +{ + ppc_vsr_t xt, xb; + uint32_t exp, i, fraction; + + getVSR(xB(opcode), &xb, env); + memset(&xt, 0, sizeof(xt)); + + for (i = 0; i < 4; i++) { + exp = (xb.VsrW(i) >> 23) & 0xFF; + fraction = xb.VsrW(i) & 0x7FFFFF; + if (exp != 0 && exp != 255) { + xt.VsrW(i) = fraction | 0x00800000; + } else { + xt.VsrW(i) = fraction; + } + } + putVSR(xT(opcode), &xt, env); +} + +/* VSX_TEST_DC - VSX floating point test data class + * op - instruction mnemonic + * nels - number of elements (1, 2 or 4) + * xbn - VSR register number + * tp - type (float32 or float64) + * fld - vsr_t field (VsrD(*) or VsrW(*)) + * tfld - target vsr_t field (VsrD(*) or VsrW(*)) + * fld_max - target field max + * scrf - set result in CR and FPCC + */ +#define VSX_TEST_DC(op, nels, xbn, tp, fld, tfld, fld_max, scrf) \ +void helper_##op(CPUPPCState *env, uint32_t opcode) \ +{ \ + ppc_vsr_t xt, xb; \ + uint32_t i, sign, dcmx; \ + uint32_t cc, match = 0; \ + \ + getVSR(xbn, &xb, env); \ + if (!scrf) { \ + memset(&xt, 0, sizeof(xt)); \ + dcmx = DCMX_XV(opcode); \ + } else { \ + dcmx = DCMX(opcode); \ + } \ + \ + for (i = 0; i < nels; i++) { \ + sign = tp##_is_neg(xb.fld); \ + if (tp##_is_any_nan(xb.fld)) { \ + match = extract32(dcmx, 6, 1); \ + } else if (tp##_is_infinity(xb.fld)) { \ + match = extract32(dcmx, 4 + !sign, 1); \ + } else if (tp##_is_zero(xb.fld)) { \ + match = extract32(dcmx, 2 + !sign, 1); \ + } else if (tp##_is_zero_or_denormal(xb.fld)) { \ + match = extract32(dcmx, 0 + !sign, 1); \ + } \ + \ + if (scrf) { \ + cc = sign << CRF_LT_BIT | match << CRF_EQ_BIT; \ + env->fpscr &= ~(0x0F << FPSCR_FPRF); \ + env->fpscr |= cc << FPSCR_FPRF; \ + env->crf[BF(opcode)] = cc; \ + } else { \ + xt.tfld = match ? fld_max : 0; \ + } \ + match = 0; \ + } \ + if (!scrf) { \ + putVSR(xT(opcode), &xt, env); \ + } \ +} + +VSX_TEST_DC(xvtstdcdp, 2, xB(opcode), float64, VsrD(i), VsrD(i), UINT64_MAX, 0) +VSX_TEST_DC(xvtstdcsp, 4, xB(opcode), float32, VsrW(i), VsrW(i), UINT32_MAX, 0) +VSX_TEST_DC(xststdcdp, 1, xB(opcode), float64, VsrD(0), VsrD(0), 0, 1) +VSX_TEST_DC(xststdcqp, 1, (rB(opcode) + 32), float128, f128, VsrD(0), 0, 1) + +void helper_xststdcsp(CPUPPCState *env, uint32_t opcode) +{ + ppc_vsr_t xb; + uint32_t dcmx, sign, exp; + uint32_t cc, match = 0, not_sp = 0; + + getVSR(xB(opcode), &xb, env); + dcmx = DCMX(opcode); + exp = (xb.VsrD(0) >> 52) & 0x7FF; + + sign = float64_is_neg(xb.VsrD(0)); + if (float64_is_any_nan(xb.VsrD(0))) { + match = extract32(dcmx, 6, 1); + } else if (float64_is_infinity(xb.VsrD(0))) { + match = extract32(dcmx, 4 + !sign, 1); + } else if (float64_is_zero(xb.VsrD(0))) { + match = extract32(dcmx, 2 + !sign, 1); + } else if (float64_is_zero_or_denormal(xb.VsrD(0)) || + (exp > 0 && exp < 0x381)) { + match = extract32(dcmx, 0 + !sign, 1); + } + + not_sp = !float64_eq(xb.VsrD(0), + float32_to_float64( + float64_to_float32(xb.VsrD(0), &env->fp_status), + &env->fp_status), &env->fp_status); + + cc = sign << CRF_LT_BIT | match << CRF_EQ_BIT | not_sp << CRF_SO_BIT; + env->fpscr &= ~(0x0F << FPSCR_FPRF); + env->fpscr |= cc << FPSCR_FPRF; + env->crf[BF(opcode)] = cc; +} diff --git a/target/ppc/helper.h b/target/ppc/helper.h index 0a8fbba3c5..85af9df36d 100644 --- a/target/ppc/helper.h +++ b/target/ppc/helper.h @@ -56,7 +56,7 @@ DEF_HELPER_FLAGS_2(brinc, TCG_CALL_NO_RWG_SE, tl, tl, tl) DEF_HELPER_1(float_check_status, void, env) DEF_HELPER_1(reset_fpstatus, void, env) -DEF_HELPER_2(compute_fprf, void, env, i64) +DEF_HELPER_2(compute_fprf_float64, void, env, i64) DEF_HELPER_3(store_fpscr, void, env, i64, i32) DEF_HELPER_2(fpscr_clrbit, void, env, i32) DEF_HELPER_2(fpscr_setbit, void, env, i32) @@ -312,6 +312,12 @@ DEF_HELPER_3(lvewx, void, env, avr, tl) DEF_HELPER_3(stvebx, void, env, avr, tl) DEF_HELPER_3(stvehx, void, env, avr, tl) DEF_HELPER_3(stvewx, void, env, avr, tl) +#if defined(TARGET_PPC64) +DEF_HELPER_4(lxvl, void, env, tl, tl, tl) +DEF_HELPER_4(lxvll, void, env, tl, tl, tl) +DEF_HELPER_4(stxvl, void, env, tl, tl, tl) +DEF_HELPER_4(stxvll, void, env, tl, tl, tl) +#endif DEF_HELPER_4(vsumsws, void, env, avr, avr, avr) DEF_HELPER_4(vsum2sws, void, env, avr, avr, avr) DEF_HELPER_4(vsum4sbs, void, env, avr, avr, avr) @@ -361,6 +367,12 @@ DEF_HELPER_3(vpmsumb, void, avr, avr, avr) DEF_HELPER_3(vpmsumh, void, avr, avr, avr) DEF_HELPER_3(vpmsumw, void, avr, avr, avr) DEF_HELPER_3(vpmsumd, void, avr, avr, avr) +DEF_HELPER_2(vextublx, tl, tl, avr) +DEF_HELPER_2(vextuhlx, tl, tl, avr) +DEF_HELPER_2(vextuwlx, tl, tl, avr) +DEF_HELPER_2(vextubrx, tl, tl, avr) +DEF_HELPER_2(vextuhrx, tl, tl, avr) +DEF_HELPER_2(vextuwrx, tl, tl, avr) DEF_HELPER_2(vsbox, void, avr, avr) DEF_HELPER_3(vcipher, void, avr, avr, avr) @@ -377,11 +389,23 @@ DEF_HELPER_3(bcdcfn, i32, avr, avr, i32) DEF_HELPER_3(bcdctn, i32, avr, avr, i32) DEF_HELPER_3(bcdcfz, i32, avr, avr, i32) DEF_HELPER_3(bcdctz, i32, avr, avr, i32) +DEF_HELPER_3(bcdcfsq, i32, avr, avr, i32) +DEF_HELPER_3(bcdctsq, i32, avr, avr, i32) +DEF_HELPER_4(bcdcpsgn, i32, avr, avr, avr, i32) +DEF_HELPER_3(bcdsetsgn, i32, avr, avr, i32) +DEF_HELPER_4(bcds, i32, avr, avr, avr, i32) +DEF_HELPER_4(bcdus, i32, avr, avr, avr, i32) +DEF_HELPER_4(bcdsr, i32, avr, avr, avr, i32) +DEF_HELPER_4(bcdtrunc, i32, avr, avr, avr, i32) +DEF_HELPER_4(bcdutrunc, i32, avr, avr, avr, i32) DEF_HELPER_2(xsadddp, void, env, i32) +DEF_HELPER_2(xsaddqp, void, env, i32) DEF_HELPER_2(xssubdp, void, env, i32) DEF_HELPER_2(xsmuldp, void, env, i32) +DEF_HELPER_2(xsmulqp, void, env, i32) DEF_HELPER_2(xsdivdp, void, env, i32) +DEF_HELPER_2(xsdivqp, void, env, i32) DEF_HELPER_2(xsredp, void, env, i32) DEF_HELPER_2(xssqrtdp, void, env, i32) DEF_HELPER_2(xsrsqrtedp, void, env, i32) @@ -399,12 +423,23 @@ DEF_HELPER_2(xscmpeqdp, void, env, i32) DEF_HELPER_2(xscmpgtdp, void, env, i32) DEF_HELPER_2(xscmpgedp, void, env, i32) DEF_HELPER_2(xscmpnedp, void, env, i32) +DEF_HELPER_2(xscmpexpdp, void, env, i32) +DEF_HELPER_2(xscmpexpqp, void, env, i32) DEF_HELPER_2(xscmpodp, void, env, i32) DEF_HELPER_2(xscmpudp, void, env, i32) +DEF_HELPER_2(xscmpoqp, void, env, i32) +DEF_HELPER_2(xscmpuqp, void, env, i32) DEF_HELPER_2(xsmaxdp, void, env, i32) DEF_HELPER_2(xsmindp, void, env, i32) +DEF_HELPER_2(xscvdphp, void, env, i32) +DEF_HELPER_2(xscvdpqp, void, env, i32) DEF_HELPER_2(xscvdpsp, void, env, i32) DEF_HELPER_2(xscvdpspn, i64, env, i64) +DEF_HELPER_2(xscvqpdp, void, env, i32) +DEF_HELPER_2(xscvqpsdz, void, env, i32) +DEF_HELPER_2(xscvqpswz, void, env, i32) +DEF_HELPER_2(xscvhpdp, void, env, i32) +DEF_HELPER_2(xscvsdqp, void, env, i32) DEF_HELPER_2(xscvspdp, void, env, i32) DEF_HELPER_2(xscvspdpn, i64, env, i64) DEF_HELPER_2(xscvdpsxds, void, env, i32) @@ -414,7 +449,11 @@ DEF_HELPER_2(xscvdpuxws, void, env, i32) DEF_HELPER_2(xscvsxddp, void, env, i32) DEF_HELPER_2(xscvuxdsp, void, env, i32) DEF_HELPER_2(xscvsxdsp, void, env, i32) +DEF_HELPER_2(xscvudqp, void, env, i32) DEF_HELPER_2(xscvuxddp, void, env, i32) +DEF_HELPER_2(xststdcsp, void, env, i32) +DEF_HELPER_2(xststdcdp, void, env, i32) +DEF_HELPER_2(xststdcqp, void, env, i32) DEF_HELPER_2(xsrdpi, void, env, i32) DEF_HELPER_2(xsrdpic, void, env, i32) DEF_HELPER_2(xsrdpim, void, env, i32) @@ -500,6 +539,8 @@ DEF_HELPER_2(xvcmpgesp, void, env, i32) DEF_HELPER_2(xvcmpgtsp, void, env, i32) DEF_HELPER_2(xvcmpnesp, void, env, i32) DEF_HELPER_2(xvcvspdp, void, env, i32) +DEF_HELPER_2(xvcvsphp, void, env, i32) +DEF_HELPER_2(xvcvhpsp, void, env, i32) DEF_HELPER_2(xvcvspsxds, void, env, i32) DEF_HELPER_2(xvcvspsxws, void, env, i32) DEF_HELPER_2(xvcvspuxds, void, env, i32) @@ -508,11 +549,18 @@ DEF_HELPER_2(xvcvsxdsp, void, env, i32) DEF_HELPER_2(xvcvuxdsp, void, env, i32) DEF_HELPER_2(xvcvsxwsp, void, env, i32) DEF_HELPER_2(xvcvuxwsp, void, env, i32) +DEF_HELPER_2(xvtstdcsp, void, env, i32) +DEF_HELPER_2(xvtstdcdp, void, env, i32) DEF_HELPER_2(xvrspi, void, env, i32) DEF_HELPER_2(xvrspic, void, env, i32) DEF_HELPER_2(xvrspim, void, env, i32) DEF_HELPER_2(xvrspip, void, env, i32) DEF_HELPER_2(xvrspiz, void, env, i32) +DEF_HELPER_2(xxperm, void, env, i32) +DEF_HELPER_2(xxpermr, void, env, i32) +DEF_HELPER_4(xxextractuw, void, env, tl, tl, i32) +DEF_HELPER_4(xxinsertw, void, env, tl, tl, i32) +DEF_HELPER_2(xvxsigsp, void, env, i32) DEF_HELPER_2(efscfsi, i32, env, i32) DEF_HELPER_2(efscfui, i32, env, i32) diff --git a/target/ppc/int_helper.c b/target/ppc/int_helper.c index 1871792ff6..dd0a8929b3 100644 --- a/target/ppc/int_helper.c +++ b/target/ppc/int_helper.c @@ -157,7 +157,7 @@ uint64_t helper_divde(CPUPPCState *env, uint64_t rau, uint64_t rbu, uint32_t oe) uint32_t helper_cmpeqb(target_ulong ra, target_ulong rb) { - return hasvalue(rb, ra) ? 1 << CRF_GT : 0; + return hasvalue(rb, ra) ? CRF_GT : 0; } #undef pattern @@ -1773,6 +1773,42 @@ void helper_vlogefp(CPUPPCState *env, ppc_avr_t *r, ppc_avr_t *b) } } +#if defined(HOST_WORDS_BIGENDIAN) +#define VEXTU_X_DO(name, size, left) \ + target_ulong glue(helper_, name)(target_ulong a, ppc_avr_t *b) \ + { \ + int index; \ + if (left) { \ + index = (a & 0xf) * 8; \ + } else { \ + index = ((15 - (a & 0xf) + 1) * 8) - size; \ + } \ + return int128_getlo(int128_rshift(b->s128, index)) & \ + MAKE_64BIT_MASK(0, size); \ + } +#else +#define VEXTU_X_DO(name, size, left) \ + target_ulong glue(helper_, name)(target_ulong a, ppc_avr_t *b) \ + { \ + int index; \ + if (left) { \ + index = ((15 - (a & 0xf) + 1) * 8) - size; \ + } else { \ + index = (a & 0xf) * 8; \ + } \ + return int128_getlo(int128_rshift(b->s128, index)) & \ + MAKE_64BIT_MASK(0, size); \ + } +#endif + +VEXTU_X_DO(vextublx, 8, 1) +VEXTU_X_DO(vextuhlx, 16, 1) +VEXTU_X_DO(vextuwlx, 32, 1) +VEXTU_X_DO(vextubrx, 8, 0) +VEXTU_X_DO(vextuhrx, 16, 0) +VEXTU_X_DO(vextuwrx, 32, 0) +#undef VEXTU_X_DO + /* The specification says that the results are undefined if all of the * shift counts are not identical. We check to make sure that they are * to conform to what real hardware appears to do. */ @@ -1965,6 +2001,57 @@ VEXTRACT(uw, u32) VEXTRACT(d, u64) #undef VEXTRACT +void helper_xxextractuw(CPUPPCState *env, target_ulong xtn, + target_ulong xbn, uint32_t index) +{ + ppc_vsr_t xt, xb; + size_t es = sizeof(uint32_t); + uint32_t ext_index; + int i; + + getVSR(xbn, &xb, env); + memset(&xt, 0, sizeof(xt)); + +#if defined(HOST_WORDS_BIGENDIAN) + ext_index = index; + for (i = 0; i < es; i++, ext_index++) { + xt.u8[8 - es + i] = xb.u8[ext_index % 16]; + } +#else + ext_index = 15 - index; + for (i = es - 1; i >= 0; i--, ext_index--) { + xt.u8[8 + i] = xb.u8[ext_index % 16]; + } +#endif + + putVSR(xtn, &xt, env); +} + +void helper_xxinsertw(CPUPPCState *env, target_ulong xtn, + target_ulong xbn, uint32_t index) +{ + ppc_vsr_t xt, xb; + size_t es = sizeof(uint32_t); + int ins_index, i = 0; + + getVSR(xbn, &xb, env); + getVSR(xtn, &xt, env); + +#if defined(HOST_WORDS_BIGENDIAN) + ins_index = index; + for (i = 0; i < es && ins_index < 16; i++, ins_index++) { + xt.u8[ins_index] = xb.u8[8 - es + i]; + } +#else + ins_index = 15 - index; + for (i = es - 1; i >= 0 && ins_index >= 0; i--, ins_index--) { + xt.u8[ins_index] = xb.u8[8 + i]; + } +#endif + + putVSR(xtn, &xt, env); +} + #define VEXT_SIGNED(name, element, mask, cast, recast) \ void helper_##name(ppc_avr_t *r, ppc_avr_t *b) \ { \ @@ -2464,9 +2551,9 @@ void helper_vsubecuq(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, ppc_avr_t *c) #define NATIONAL_NEG 0x2D #if defined(HOST_WORDS_BIGENDIAN) -#define BCD_DIG_BYTE(n) (15 - (n/2)) +#define BCD_DIG_BYTE(n) (15 - ((n) / 2)) #else -#define BCD_DIG_BYTE(n) (n/2) +#define BCD_DIG_BYTE(n) ((n) / 2) #endif static int bcd_get_sgn(ppc_avr_t *bcd) @@ -2528,12 +2615,30 @@ static void bcd_put_digit(ppc_avr_t *bcd, uint8_t digit, int n) } } +static bool bcd_is_valid(ppc_avr_t *bcd) +{ + int i; + int invalid = 0; + + if (bcd_get_sgn(bcd) == 0) { + return false; + } + + for (i = 1; i < 32; i++) { + bcd_get_digit(bcd, i, &invalid); + if (unlikely(invalid)) { + return false; + } + } + return true; +} + static int bcd_cmp_zero(ppc_avr_t *bcd) { if (bcd->u64[HI_IDX] == 0 && (bcd->u64[LO_IDX] >> 4) == 0) { - return 1 << CRF_EQ; + return CRF_EQ; } else { - return (bcd_get_sgn(bcd) == 1) ? 1 << CRF_GT : 1 << CRF_LT; + return (bcd_get_sgn(bcd) == 1) ? CRF_GT : CRF_LT; } } @@ -2645,25 +2750,25 @@ uint32_t helper_bcdadd(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, uint32_t ps) if (sgna == sgnb) { result.u8[BCD_DIG_BYTE(0)] = bcd_preferred_sgn(sgna, ps); zero = bcd_add_mag(&result, a, b, &invalid, &overflow); - cr = (sgna > 0) ? 1 << CRF_GT : 1 << CRF_LT; + cr = (sgna > 0) ? CRF_GT : CRF_LT; } else if (bcd_cmp_mag(a, b) > 0) { result.u8[BCD_DIG_BYTE(0)] = bcd_preferred_sgn(sgna, ps); zero = bcd_sub_mag(&result, a, b, &invalid, &overflow); - cr = (sgna > 0) ? 1 << CRF_GT : 1 << CRF_LT; + cr = (sgna > 0) ? CRF_GT : CRF_LT; } else { result.u8[BCD_DIG_BYTE(0)] = bcd_preferred_sgn(sgnb, ps); zero = bcd_sub_mag(&result, b, a, &invalid, &overflow); - cr = (sgnb > 0) ? 1 << CRF_GT : 1 << CRF_LT; + cr = (sgnb > 0) ? CRF_GT : CRF_LT; } } if (unlikely(invalid)) { result.u64[HI_IDX] = result.u64[LO_IDX] = -1; - cr = 1 << CRF_SO; + cr = CRF_SO; } else if (overflow) { - cr |= 1 << CRF_SO; + cr |= CRF_SO; } else if (zero) { - cr = 1 << CRF_EQ; + cr = CRF_EQ; } *r = result; @@ -2713,7 +2818,7 @@ uint32_t helper_bcdcfn(ppc_avr_t *r, ppc_avr_t *b, uint32_t ps) cr = bcd_cmp_zero(&ret); if (unlikely(invalid)) { - cr = 1 << CRF_SO; + cr = CRF_SO; } *r = ret; @@ -2743,11 +2848,11 @@ uint32_t helper_bcdctn(ppc_avr_t *r, ppc_avr_t *b, uint32_t ps) cr = bcd_cmp_zero(b); if (ox_flag) { - cr |= 1 << CRF_SO; + cr |= CRF_SO; } if (unlikely(invalid)) { - cr = 1 << CRF_SO; + cr = CRF_SO; } *r = ret; @@ -2771,7 +2876,7 @@ uint32_t helper_bcdcfz(ppc_avr_t *r, ppc_avr_t *b, uint32_t ps) } for (i = 0; i < 16; i++) { - zone_digit = (i * 2) ? b->u8[BCD_DIG_BYTE(i * 2)] >> 4 : zone_lead; + zone_digit = i ? b->u8[BCD_DIG_BYTE(i * 2)] >> 4 : zone_lead; digit = b->u8[BCD_DIG_BYTE(i * 2)] & 0xF; if (unlikely(zone_digit != zone_lead || digit > 0x9)) { invalid = 1; @@ -2791,7 +2896,7 @@ uint32_t helper_bcdcfz(ppc_avr_t *r, ppc_avr_t *b, uint32_t ps) cr = bcd_cmp_zero(&ret); if (unlikely(invalid)) { - cr = 1 << CRF_SO; + cr = CRF_SO; } *r = ret; @@ -2830,18 +2935,350 @@ uint32_t helper_bcdctz(ppc_avr_t *r, ppc_avr_t *b, uint32_t ps) cr = bcd_cmp_zero(b); if (ox_flag) { - cr |= 1 << CRF_SO; + cr |= CRF_SO; } if (unlikely(invalid)) { - cr = 1 << CRF_SO; + cr = CRF_SO; + } + + *r = ret; + + return cr; +} + +uint32_t helper_bcdcfsq(ppc_avr_t *r, ppc_avr_t *b, uint32_t ps) +{ + int i; + int cr = 0; + uint64_t lo_value; + uint64_t hi_value; + ppc_avr_t ret = { .u64 = { 0, 0 } }; + + if (b->s64[HI_IDX] < 0) { + lo_value = -b->s64[LO_IDX]; + hi_value = ~b->u64[HI_IDX] + !lo_value; + bcd_put_digit(&ret, 0xD, 0); + } else { + lo_value = b->u64[LO_IDX]; + hi_value = b->u64[HI_IDX]; + bcd_put_digit(&ret, bcd_preferred_sgn(0, ps), 0); + } + + if (divu128(&lo_value, &hi_value, 1000000000000000ULL) || + lo_value > 9999999999999999ULL) { + cr = CRF_SO; + } + + for (i = 1; i < 16; hi_value /= 10, i++) { + bcd_put_digit(&ret, hi_value % 10, i); + } + + for (; i < 32; lo_value /= 10, i++) { + bcd_put_digit(&ret, lo_value % 10, i); } + cr |= bcd_cmp_zero(&ret); + *r = ret; return cr; } +uint32_t helper_bcdctsq(ppc_avr_t *r, ppc_avr_t *b, uint32_t ps) +{ + uint8_t i; + int cr; + uint64_t carry; + uint64_t unused; + uint64_t lo_value; + uint64_t hi_value = 0; + int sgnb = bcd_get_sgn(b); + int invalid = (sgnb == 0); + + lo_value = bcd_get_digit(b, 31, &invalid); + for (i = 30; i > 0; i--) { + mulu64(&lo_value, &carry, lo_value, 10ULL); + mulu64(&hi_value, &unused, hi_value, 10ULL); + lo_value += bcd_get_digit(b, i, &invalid); + hi_value += carry; + + if (unlikely(invalid)) { + break; + } + } + + if (sgnb == -1) { + r->s64[LO_IDX] = -lo_value; + r->s64[HI_IDX] = ~hi_value + !r->s64[LO_IDX]; + } else { + r->s64[LO_IDX] = lo_value; + r->s64[HI_IDX] = hi_value; + } + + cr = bcd_cmp_zero(b); + + if (unlikely(invalid)) { + cr = CRF_SO; + } + + return cr; +} + +uint32_t helper_bcdcpsgn(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, uint32_t ps) +{ + int i; + int invalid = 0; + + if (bcd_get_sgn(a) == 0 || bcd_get_sgn(b) == 0) { + return CRF_SO; + } + + *r = *a; + bcd_put_digit(r, b->u8[BCD_DIG_BYTE(0)] & 0xF, 0); + + for (i = 1; i < 32; i++) { + bcd_get_digit(a, i, &invalid); + bcd_get_digit(b, i, &invalid); + if (unlikely(invalid)) { + return CRF_SO; + } + } + + return bcd_cmp_zero(r); +} + +uint32_t helper_bcdsetsgn(ppc_avr_t *r, ppc_avr_t *b, uint32_t ps) +{ + int sgnb = bcd_get_sgn(b); + + *r = *b; + bcd_put_digit(r, bcd_preferred_sgn(sgnb, ps), 0); + + if (bcd_is_valid(b) == false) { + return CRF_SO; + } + + return bcd_cmp_zero(r); +} + +uint32_t helper_bcds(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, uint32_t ps) +{ + int cr; +#if defined(HOST_WORDS_BIGENDIAN) + int i = a->s8[7]; +#else + int i = a->s8[8]; +#endif + bool ox_flag = false; + int sgnb = bcd_get_sgn(b); + ppc_avr_t ret = *b; + ret.u64[LO_IDX] &= ~0xf; + + if (bcd_is_valid(b) == false) { + return CRF_SO; + } + + if (unlikely(i > 31)) { + i = 31; + } else if (unlikely(i < -31)) { + i = -31; + } + + if (i > 0) { + ulshift(&ret.u64[LO_IDX], &ret.u64[HI_IDX], i * 4, &ox_flag); + } else { + urshift(&ret.u64[LO_IDX], &ret.u64[HI_IDX], -i * 4); + } + bcd_put_digit(&ret, bcd_preferred_sgn(sgnb, ps), 0); + + *r = ret; + + cr = bcd_cmp_zero(r); + if (ox_flag) { + cr |= CRF_SO; + } + + return cr; +} + +uint32_t helper_bcdus(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, uint32_t ps) +{ + int cr; + int i; + int invalid = 0; + bool ox_flag = false; + ppc_avr_t ret = *b; + + for (i = 0; i < 32; i++) { + bcd_get_digit(b, i, &invalid); + + if (unlikely(invalid)) { + return CRF_SO; + } + } + +#if defined(HOST_WORDS_BIGENDIAN) + i = a->s8[7]; +#else + i = a->s8[8]; +#endif + if (i >= 32) { + ox_flag = true; + ret.u64[LO_IDX] = ret.u64[HI_IDX] = 0; + } else if (i <= -32) { + ret.u64[LO_IDX] = ret.u64[HI_IDX] = 0; + } else if (i > 0) { + ulshift(&ret.u64[LO_IDX], &ret.u64[HI_IDX], i * 4, &ox_flag); + } else { + urshift(&ret.u64[LO_IDX], &ret.u64[HI_IDX], -i * 4); + } + *r = ret; + + cr = bcd_cmp_zero(r); + if (ox_flag) { + cr |= CRF_SO; + } + + return cr; +} + +uint32_t helper_bcdsr(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, uint32_t ps) +{ + int cr; + int unused = 0; + int invalid = 0; + bool ox_flag = false; + int sgnb = bcd_get_sgn(b); + ppc_avr_t ret = *b; + ret.u64[LO_IDX] &= ~0xf; + +#if defined(HOST_WORDS_BIGENDIAN) + int i = a->s8[7]; + ppc_avr_t bcd_one = { .u64 = { 0, 0x10 } }; +#else + int i = a->s8[8]; + ppc_avr_t bcd_one = { .u64 = { 0x10, 0 } }; +#endif + + if (bcd_is_valid(b) == false) { + return CRF_SO; + } + + if (unlikely(i > 31)) { + i = 31; + } else if (unlikely(i < -31)) { + i = -31; + } + + if (i > 0) { + ulshift(&ret.u64[LO_IDX], &ret.u64[HI_IDX], i * 4, &ox_flag); + } else { + urshift(&ret.u64[LO_IDX], &ret.u64[HI_IDX], -i * 4); + + if (bcd_get_digit(&ret, 0, &invalid) >= 5) { + bcd_add_mag(&ret, &ret, &bcd_one, &invalid, &unused); + } + } + bcd_put_digit(&ret, bcd_preferred_sgn(sgnb, ps), 0); + + cr = bcd_cmp_zero(&ret); + if (ox_flag) { + cr |= CRF_SO; + } + *r = ret; + + return cr; +} + +uint32_t helper_bcdtrunc(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, uint32_t ps) +{ + uint64_t mask; + uint32_t ox_flag = 0; +#if defined(HOST_WORDS_BIGENDIAN) + int i = a->s16[3] + 1; +#else + int i = a->s16[4] + 1; +#endif + ppc_avr_t ret = *b; + + if (bcd_is_valid(b) == false) { + return CRF_SO; + } + + if (i > 16 && i < 32) { + mask = (uint64_t)-1 >> (128 - i * 4); + if (ret.u64[HI_IDX] & ~mask) { + ox_flag = CRF_SO; + } + + ret.u64[HI_IDX] &= mask; + } else if (i >= 0 && i <= 16) { + mask = (uint64_t)-1 >> (64 - i * 4); + if (ret.u64[HI_IDX] || (ret.u64[LO_IDX] & ~mask)) { + ox_flag = CRF_SO; + } + + ret.u64[LO_IDX] &= mask; + ret.u64[HI_IDX] = 0; + } + bcd_put_digit(&ret, bcd_preferred_sgn(bcd_get_sgn(b), ps), 0); + *r = ret; + + return bcd_cmp_zero(&ret) | ox_flag; +} + +uint32_t helper_bcdutrunc(ppc_avr_t *r, ppc_avr_t *a, ppc_avr_t *b, uint32_t ps) +{ + int i; + uint64_t mask; + uint32_t ox_flag = 0; + int invalid = 0; + ppc_avr_t ret = *b; + + for (i = 0; i < 32; i++) { + bcd_get_digit(b, i, &invalid); + + if (unlikely(invalid)) { + return CRF_SO; + } + } + +#if defined(HOST_WORDS_BIGENDIAN) + i = a->s16[3]; +#else + i = a->s16[4]; +#endif + if (i > 16 && i < 33) { + mask = (uint64_t)-1 >> (128 - i * 4); + if (ret.u64[HI_IDX] & ~mask) { + ox_flag = CRF_SO; + } + + ret.u64[HI_IDX] &= mask; + } else if (i > 0 && i <= 16) { + mask = (uint64_t)-1 >> (64 - i * 4); + if (ret.u64[HI_IDX] || (ret.u64[LO_IDX] & ~mask)) { + ox_flag = CRF_SO; + } + + ret.u64[LO_IDX] &= mask; + ret.u64[HI_IDX] = 0; + } else if (i == 0) { + if (ret.u64[HI_IDX] || ret.u64[LO_IDX]) { + ox_flag = CRF_SO; + } + ret.u64[HI_IDX] = ret.u64[LO_IDX] = 0; + } + + *r = ret; + if (r->u64[HI_IDX] == 0 && r->u64[LO_IDX] == 0) { + return ox_flag | CRF_EQ; + } + + return ox_flag | CRF_GT; +} + void helper_vsbox(ppc_avr_t *r, ppc_avr_t *a) { int i; diff --git a/target/ppc/internal.h b/target/ppc/internal.h index 1ff4896c45..5a2fd68427 100644 --- a/target/ppc/internal.h +++ b/target/ppc/internal.h @@ -47,4 +47,206 @@ FUNC_MASK(MASK, target_ulong, 32, UINT32_MAX); FUNC_MASK(mask_u32, uint32_t, 32, UINT32_MAX); FUNC_MASK(mask_u64, uint64_t, 64, UINT64_MAX); +/*****************************************************************************/ +/*** Instruction decoding ***/ +#define EXTRACT_HELPER(name, shift, nb) \ +static inline uint32_t name(uint32_t opcode) \ +{ \ + return (opcode >> (shift)) & ((1 << (nb)) - 1); \ +} + +#define EXTRACT_SHELPER(name, shift, nb) \ +static inline int32_t name(uint32_t opcode) \ +{ \ + return (int16_t)((opcode >> (shift)) & ((1 << (nb)) - 1)); \ +} + +#define EXTRACT_HELPER_SPLIT(name, shift1, nb1, shift2, nb2) \ +static inline uint32_t name(uint32_t opcode) \ +{ \ + return (((opcode >> (shift1)) & ((1 << (nb1)) - 1)) << nb2) | \ + ((opcode >> (shift2)) & ((1 << (nb2)) - 1)); \ +} + +#define EXTRACT_HELPER_SPLIT_3(name, \ + d0_bits, shift_op_d0, shift_d0, \ + d1_bits, shift_op_d1, shift_d1, \ + d2_bits, shift_op_d2, shift_d2) \ +static inline int16_t name(uint32_t opcode) \ +{ \ + return \ + (((opcode >> (shift_op_d0)) & ((1 << (d0_bits)) - 1)) << (shift_d0)) | \ + (((opcode >> (shift_op_d1)) & ((1 << (d1_bits)) - 1)) << (shift_d1)) | \ + (((opcode >> (shift_op_d2)) & ((1 << (d2_bits)) - 1)) << (shift_d2)); \ +} + + +/* Opcode part 1 */ +EXTRACT_HELPER(opc1, 26, 6); +/* Opcode part 2 */ +EXTRACT_HELPER(opc2, 1, 5); +/* Opcode part 3 */ +EXTRACT_HELPER(opc3, 6, 5); +/* Opcode part 4 */ +EXTRACT_HELPER(opc4, 16, 5); +/* Update Cr0 flags */ +EXTRACT_HELPER(Rc, 0, 1); +/* Update Cr6 flags (Altivec) */ +EXTRACT_HELPER(Rc21, 10, 1); +/* Destination */ +EXTRACT_HELPER(rD, 21, 5); +/* Source */ +EXTRACT_HELPER(rS, 21, 5); +/* First operand */ +EXTRACT_HELPER(rA, 16, 5); +/* Second operand */ +EXTRACT_HELPER(rB, 11, 5); +/* Third operand */ +EXTRACT_HELPER(rC, 6, 5); +/*** Get CRn ***/ +EXTRACT_HELPER(crfD, 23, 3); +EXTRACT_HELPER(BF, 23, 3); +EXTRACT_HELPER(crfS, 18, 3); +EXTRACT_HELPER(crbD, 21, 5); +EXTRACT_HELPER(crbA, 16, 5); +EXTRACT_HELPER(crbB, 11, 5); +/* SPR / TBL */ +EXTRACT_HELPER(_SPR, 11, 10); +static inline uint32_t SPR(uint32_t opcode) +{ + uint32_t sprn = _SPR(opcode); + + return ((sprn >> 5) & 0x1F) | ((sprn & 0x1F) << 5); +} +/*** Get constants ***/ +/* 16 bits signed immediate value */ +EXTRACT_SHELPER(SIMM, 0, 16); +/* 16 bits unsigned immediate value */ +EXTRACT_HELPER(UIMM, 0, 16); +/* 5 bits signed immediate value */ +EXTRACT_HELPER(SIMM5, 16, 5); +/* 5 bits signed immediate value */ +EXTRACT_HELPER(UIMM5, 16, 5); +/* 4 bits unsigned immediate value */ +EXTRACT_HELPER(UIMM4, 16, 4); +/* Bit count */ +EXTRACT_HELPER(NB, 11, 5); +/* Shift count */ +EXTRACT_HELPER(SH, 11, 5); +/* Vector shift count */ +EXTRACT_HELPER(VSH, 6, 4); +/* Mask start */ +EXTRACT_HELPER(MB, 6, 5); +/* Mask end */ +EXTRACT_HELPER(ME, 1, 5); +/* Trap operand */ +EXTRACT_HELPER(TO, 21, 5); + +EXTRACT_HELPER(CRM, 12, 8); + +#ifndef CONFIG_USER_ONLY +EXTRACT_HELPER(SR, 16, 4); +#endif + +/* mtfsf/mtfsfi */ +EXTRACT_HELPER(FPBF, 23, 3); +EXTRACT_HELPER(FPIMM, 12, 4); +EXTRACT_HELPER(FPL, 25, 1); +EXTRACT_HELPER(FPFLM, 17, 8); +EXTRACT_HELPER(FPW, 16, 1); + +/* addpcis */ +EXTRACT_HELPER_SPLIT_3(DX, 10, 6, 6, 5, 16, 1, 1, 0, 0) +#if defined(TARGET_PPC64) +/* darn */ +EXTRACT_HELPER(L, 16, 2); +#endif + +/*** Jump target decoding ***/ +/* Immediate address */ +static inline target_ulong LI(uint32_t opcode) +{ + return (opcode >> 0) & 0x03FFFFFC; +} + +static inline uint32_t BD(uint32_t opcode) +{ + return (opcode >> 0) & 0xFFFC; +} + +EXTRACT_HELPER(BO, 21, 5); +EXTRACT_HELPER(BI, 16, 5); +/* Absolute/relative address */ +EXTRACT_HELPER(AA, 1, 1); +/* Link */ +EXTRACT_HELPER(LK, 0, 1); + +/* DFP Z22-form */ +EXTRACT_HELPER(DCM, 10, 6) + +/* DFP Z23-form */ +EXTRACT_HELPER(RMC, 9, 2) + +EXTRACT_HELPER_SPLIT(DQxT, 3, 1, 21, 5); +EXTRACT_HELPER_SPLIT(xT, 0, 1, 21, 5); +EXTRACT_HELPER_SPLIT(xS, 0, 1, 21, 5); +EXTRACT_HELPER_SPLIT(xA, 2, 1, 16, 5); +EXTRACT_HELPER_SPLIT(xB, 1, 1, 11, 5); +EXTRACT_HELPER_SPLIT(xC, 3, 1, 6, 5); +EXTRACT_HELPER(DM, 8, 2); +EXTRACT_HELPER(UIM, 16, 2); +EXTRACT_HELPER(SHW, 8, 2); +EXTRACT_HELPER(SP, 19, 2); +EXTRACT_HELPER(IMM8, 11, 8); +EXTRACT_HELPER(DCMX, 16, 7); +EXTRACT_HELPER_SPLIT_3(DCMX_XV, 5, 16, 0, 1, 2, 5, 1, 6, 6); + +typedef union _ppc_vsr_t { + uint8_t u8[16]; + uint16_t u16[8]; + uint32_t u32[4]; + uint64_t u64[2]; + float32 f32[4]; + float64 f64[2]; + float128 f128; + Int128 s128; +} ppc_vsr_t; + +#if defined(HOST_WORDS_BIGENDIAN) +#define VsrB(i) u8[i] +#define VsrH(i) u16[i] +#define VsrW(i) u32[i] +#define VsrD(i) u64[i] +#else +#define VsrB(i) u8[15 - (i)] +#define VsrH(i) u16[7 - (i)] +#define VsrW(i) u32[3 - (i)] +#define VsrD(i) u64[1 - (i)] +#endif + +static inline void getVSR(int n, ppc_vsr_t *vsr, CPUPPCState *env) +{ + if (n < 32) { + vsr->VsrD(0) = env->fpr[n]; + vsr->VsrD(1) = env->vsr[n]; + } else { + vsr->u64[0] = env->avr[n - 32].u64[0]; + vsr->u64[1] = env->avr[n - 32].u64[1]; + } +} + +static inline void putVSR(int n, ppc_vsr_t *vsr, CPUPPCState *env) +{ + if (n < 32) { + env->fpr[n] = vsr->VsrD(0); + env->vsr[n] = vsr->VsrD(1); + } else { + env->avr[n - 32].u64[0] = vsr->u64[0]; + env->avr[n - 32].u64[1] = vsr->u64[1]; + } +} + +void helper_compute_fprf_float16(CPUPPCState *env, float16 arg); +void helper_compute_fprf_float32(CPUPPCState *env, float32 arg); +void helper_compute_fprf_float128(CPUPPCState *env, float128 arg); #endif /* PPC_INTERNAL_H */ diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c index ec92c64159..663d2e79c9 100644 --- a/target/ppc/kvm.c +++ b/target/ppc/kvm.c @@ -24,6 +24,7 @@ #include "qemu-common.h" #include "qemu/error-report.h" #include "cpu.h" +#include "cpu-models.h" #include "qemu/timer.h" #include "sysemu/sysemu.h" #include "sysemu/hw_accel.h" @@ -2108,9 +2109,9 @@ void kvmppc_set_papr(PowerPCCPU *cpu) cap_papr = 1; } -int kvmppc_set_compat(PowerPCCPU *cpu, uint32_t cpu_version) +int kvmppc_set_compat(PowerPCCPU *cpu, uint32_t compat_pvr) { - return kvm_set_one_reg(CPU(cpu), KVM_REG_PPC_ARCH_COMPAT, &cpu_version); + return kvm_set_one_reg(CPU(cpu), KVM_REG_PPC_ARCH_COMPAT, &compat_pvr); } void kvmppc_set_mpic_proxy(PowerPCCPU *cpu, int mpic_proxy) @@ -2412,6 +2413,7 @@ static int kvm_ppc_register_host_cpu_type(void) }; PowerPCCPUClass *pvr_pcc; DeviceClass *dc; + int i; pvr_pcc = kvm_ppc_get_host_cpu_class(); if (pvr_pcc == NULL) { @@ -2420,13 +2422,6 @@ static int kvm_ppc_register_host_cpu_type(void) type_info.parent = object_class_get_name(OBJECT_CLASS(pvr_pcc)); type_register(&type_info); - /* Register generic family CPU class for a family */ - pvr_pcc = ppc_cpu_get_family_class(pvr_pcc); - dc = DEVICE_CLASS(pvr_pcc); - type_info.parent = object_class_get_name(OBJECT_CLASS(pvr_pcc)); - type_info.name = g_strdup_printf("%s-"TYPE_POWERPC_CPU, dc->desc); - type_register(&type_info); - #if defined(TARGET_PPC64) type_info.name = g_strdup_printf("%s-"TYPE_SPAPR_CPU_CORE, "host"); type_info.parent = TYPE_SPAPR_CPU_CORE, @@ -2436,14 +2431,29 @@ static int kvm_ppc_register_host_cpu_type(void) type_info.class_data = (void *) "host"; type_register(&type_info); g_free((void *)type_info.name); - - /* Register generic spapr CPU family class for current host CPU type */ - type_info.name = g_strdup_printf("%s-"TYPE_SPAPR_CPU_CORE, dc->desc); - type_info.class_data = (void *) dc->desc; - type_register(&type_info); - g_free((void *)type_info.name); #endif + /* + * Update generic CPU family class alias (e.g. on a POWER8NVL host, + * we want "POWER8" to be a "family" alias that points to the current + * host CPU type, too) + */ + dc = DEVICE_CLASS(ppc_cpu_get_family_class(pvr_pcc)); + for (i = 0; ppc_cpu_aliases[i].alias != NULL; i++) { + if (strcmp(ppc_cpu_aliases[i].alias, dc->desc) == 0) { + ObjectClass *oc = OBJECT_CLASS(pvr_pcc); + char *suffix; + + ppc_cpu_aliases[i].model = g_strdup(object_class_get_name(oc)); + suffix = strstr(ppc_cpu_aliases[i].model, "-"TYPE_POWERPC_CPU); + if (suffix) { + *suffix = 0; + } + ppc_cpu_aliases[i].oc = oc; + break; + } + } + return 0; } diff --git a/target/ppc/kvm_ppc.h b/target/ppc/kvm_ppc.h index 4b43283913..151c00bac7 100644 --- a/target/ppc/kvm_ppc.h +++ b/target/ppc/kvm_ppc.h @@ -26,7 +26,7 @@ void kvmppc_enable_logical_ci_hcalls(void); void kvmppc_enable_set_mode_hcall(void); void kvmppc_enable_clear_ref_mod_hcalls(void); void kvmppc_set_papr(PowerPCCPU *cpu); -int kvmppc_set_compat(PowerPCCPU *cpu, uint32_t cpu_version); +int kvmppc_set_compat(PowerPCCPU *cpu, uint32_t compat_pvr); void kvmppc_set_mpic_proxy(PowerPCCPU *cpu, int mpic_proxy); int kvmppc_smt_threads(void); int kvmppc_clear_tsr_bits(PowerPCCPU *cpu, uint32_t tsr_bits); @@ -123,7 +123,7 @@ static inline void kvmppc_set_papr(PowerPCCPU *cpu) { } -static inline int kvmppc_set_compat(PowerPCCPU *cpu, uint32_t cpu_version) +static inline int kvmppc_set_compat(PowerPCCPU *cpu, uint32_t compat_pvr) { return 0; } diff --git a/target/ppc/mem_helper.c b/target/ppc/mem_helper.c index 1ab8a6eab4..e6383c6bfa 100644 --- a/target/ppc/mem_helper.c +++ b/target/ppc/mem_helper.c @@ -24,6 +24,7 @@ #include "helper_regs.h" #include "exec/cpu_ldst.h" +#include "internal.h" //#define DEBUG_OP @@ -284,6 +285,71 @@ STVE(stvewx, cpu_stl_data_ra, bswap32, u32) #undef I #undef LVE +#ifdef TARGET_PPC64 +#define GET_NB(rb) ((rb >> 56) & 0xFF) + +#define VSX_LXVL(name, lj) \ +void helper_##name(CPUPPCState *env, target_ulong addr, \ + target_ulong xt_num, target_ulong rb) \ +{ \ + int i; \ + ppc_vsr_t xt; \ + uint64_t nb = GET_NB(rb); \ + \ + xt.s128 = int128_zero(); \ + if (nb) { \ + nb = (nb >= 16) ? 16 : nb; \ + if (msr_le && !lj) { \ + for (i = 16; i > 16 - nb; i--) { \ + xt.VsrB(i - 1) = cpu_ldub_data_ra(env, addr, GETPC()); \ + addr = addr_add(env, addr, 1); \ + } \ + } else { \ + for (i = 0; i < nb; i++) { \ + xt.VsrB(i) = cpu_ldub_data_ra(env, addr, GETPC()); \ + addr = addr_add(env, addr, 1); \ + } \ + } \ + } \ + putVSR(xt_num, &xt, env); \ +} + +VSX_LXVL(lxvl, 0) +VSX_LXVL(lxvll, 1) +#undef VSX_LXVL + +#define VSX_STXVL(name, lj) \ +void helper_##name(CPUPPCState *env, target_ulong addr, \ + target_ulong xt_num, target_ulong rb) \ +{ \ + int i; \ + ppc_vsr_t xt; \ + target_ulong nb = GET_NB(rb); \ + \ + if (!nb) { \ + return; \ + } \ + getVSR(xt_num, &xt, env); \ + nb = (nb >= 16) ? 16 : nb; \ + if (msr_le && !lj) { \ + for (i = 16; i > 16 - nb; i--) { \ + cpu_stb_data_ra(env, addr, xt.VsrB(i - 1), GETPC()); \ + addr = addr_add(env, addr, 1); \ + } \ + } else { \ + for (i = 0; i < nb; i++) { \ + cpu_stb_data_ra(env, addr, xt.VsrB(i), GETPC()); \ + addr = addr_add(env, addr, 1); \ + } \ + } \ +} + +VSX_STXVL(stxvl, 0) +VSX_STXVL(stxvll, 1) +#undef VSX_STXVL +#undef GET_NB +#endif /* TARGET_PPC64 */ + #undef HI_IDX #undef LO_IDX diff --git a/target/ppc/mmu-hash64.c b/target/ppc/mmu-hash64.c index 0efc8c63fa..bb78fb5497 100644 --- a/target/ppc/mmu-hash64.c +++ b/target/ppc/mmu-hash64.c @@ -181,8 +181,8 @@ int ppc_store_slb(PowerPCCPU *cpu, target_ulong slot, slb->vsid = vsid; slb->sps = sps; - LOG_SLB("%s: %d " TARGET_FMT_lx " - " TARGET_FMT_lx " => %016" PRIx64 - " %016" PRIx64 "\n", __func__, slot, esid, vsid, + LOG_SLB("%s: " TARGET_FMT_lu " " TARGET_FMT_lx " - " TARGET_FMT_lx + " => %016" PRIx64 " %016" PRIx64 "\n", __func__, slot, esid, vsid, slb->esid, slb->vsid); return 0; diff --git a/target/ppc/mmu-hash64.h b/target/ppc/mmu-hash64.h index ab5d347a53..7a0b7fca41 100644 --- a/target/ppc/mmu-hash64.h +++ b/target/ppc/mmu-hash64.h @@ -85,7 +85,7 @@ void ppc_hash64_update_rmls(CPUPPCState *env); #define HPTE64_R_C 0x0000000000000080ULL #define HPTE64_R_R 0x0000000000000100ULL #define HPTE64_R_KEY_LO 0x0000000000000e00ULL -#define HPTE64_R_KEY(x) ((((x) & HPTE64_R_KEY_HI) >> 60) | \ +#define HPTE64_R_KEY(x) ((((x) & HPTE64_R_KEY_HI) >> 57) | \ (((x) & HPTE64_R_KEY_LO) >> 9)) #define HPTE64_V_1TB_SEG 0x4000000000000000ULL diff --git a/target/ppc/translate.c b/target/ppc/translate.c index 121218087f..b48abaedfb 100644 --- a/target/ppc/translate.c +++ b/target/ppc/translate.c @@ -422,157 +422,6 @@ typedef struct opcode_t { #define CHK_NONE - -/*****************************************************************************/ -/*** Instruction decoding ***/ -#define EXTRACT_HELPER(name, shift, nb) \ -static inline uint32_t name(uint32_t opcode) \ -{ \ - return (opcode >> (shift)) & ((1 << (nb)) - 1); \ -} - -#define EXTRACT_SHELPER(name, shift, nb) \ -static inline int32_t name(uint32_t opcode) \ -{ \ - return (int16_t)((opcode >> (shift)) & ((1 << (nb)) - 1)); \ -} - -#define EXTRACT_HELPER_SPLIT(name, shift1, nb1, shift2, nb2) \ -static inline uint32_t name(uint32_t opcode) \ -{ \ - return (((opcode >> (shift1)) & ((1 << (nb1)) - 1)) << nb2) | \ - ((opcode >> (shift2)) & ((1 << (nb2)) - 1)); \ -} - -#define EXTRACT_HELPER_DXFORM(name, \ - d0_bits, shift_op_d0, shift_d0, \ - d1_bits, shift_op_d1, shift_d1, \ - d2_bits, shift_op_d2, shift_d2) \ -static inline int16_t name(uint32_t opcode) \ -{ \ - return \ - (((opcode >> (shift_op_d0)) & ((1 << (d0_bits)) - 1)) << (shift_d0)) | \ - (((opcode >> (shift_op_d1)) & ((1 << (d1_bits)) - 1)) << (shift_d1)) | \ - (((opcode >> (shift_op_d2)) & ((1 << (d2_bits)) - 1)) << (shift_d2)); \ -} - - -/* Opcode part 1 */ -EXTRACT_HELPER(opc1, 26, 6); -/* Opcode part 2 */ -EXTRACT_HELPER(opc2, 1, 5); -/* Opcode part 3 */ -EXTRACT_HELPER(opc3, 6, 5); -/* Opcode part 4 */ -EXTRACT_HELPER(opc4, 16, 5); -/* Update Cr0 flags */ -EXTRACT_HELPER(Rc, 0, 1); -/* Update Cr6 flags (Altivec) */ -EXTRACT_HELPER(Rc21, 10, 1); -/* Destination */ -EXTRACT_HELPER(rD, 21, 5); -/* Source */ -EXTRACT_HELPER(rS, 21, 5); -/* First operand */ -EXTRACT_HELPER(rA, 16, 5); -/* Second operand */ -EXTRACT_HELPER(rB, 11, 5); -/* Third operand */ -EXTRACT_HELPER(rC, 6, 5); -/*** Get CRn ***/ -EXTRACT_HELPER(crfD, 23, 3); -EXTRACT_HELPER(crfS, 18, 3); -EXTRACT_HELPER(crbD, 21, 5); -EXTRACT_HELPER(crbA, 16, 5); -EXTRACT_HELPER(crbB, 11, 5); -/* SPR / TBL */ -EXTRACT_HELPER(_SPR, 11, 10); -static inline uint32_t SPR(uint32_t opcode) -{ - uint32_t sprn = _SPR(opcode); - - return ((sprn >> 5) & 0x1F) | ((sprn & 0x1F) << 5); -} -/*** Get constants ***/ -/* 16 bits signed immediate value */ -EXTRACT_SHELPER(SIMM, 0, 16); -/* 16 bits unsigned immediate value */ -EXTRACT_HELPER(UIMM, 0, 16); -/* 5 bits signed immediate value */ -EXTRACT_HELPER(SIMM5, 16, 5); -/* 5 bits signed immediate value */ -EXTRACT_HELPER(UIMM5, 16, 5); -/* 4 bits unsigned immediate value */ -EXTRACT_HELPER(UIMM4, 16, 4); -/* Bit count */ -EXTRACT_HELPER(NB, 11, 5); -/* Shift count */ -EXTRACT_HELPER(SH, 11, 5); -/* Vector shift count */ -EXTRACT_HELPER(VSH, 6, 4); -/* Mask start */ -EXTRACT_HELPER(MB, 6, 5); -/* Mask end */ -EXTRACT_HELPER(ME, 1, 5); -/* Trap operand */ -EXTRACT_HELPER(TO, 21, 5); - -EXTRACT_HELPER(CRM, 12, 8); - -#ifndef CONFIG_USER_ONLY -EXTRACT_HELPER(SR, 16, 4); -#endif - -/* mtfsf/mtfsfi */ -EXTRACT_HELPER(FPBF, 23, 3); -EXTRACT_HELPER(FPIMM, 12, 4); -EXTRACT_HELPER(FPL, 25, 1); -EXTRACT_HELPER(FPFLM, 17, 8); -EXTRACT_HELPER(FPW, 16, 1); - -/* addpcis */ -EXTRACT_HELPER_DXFORM(DX, 10, 6, 6, 5, 16, 1, 1, 0, 0) -#if defined(TARGET_PPC64) -/* darn */ -EXTRACT_HELPER(L, 16, 2); -#endif - -/*** Jump target decoding ***/ -/* Immediate address */ -static inline target_ulong LI(uint32_t opcode) -{ - return (opcode >> 0) & 0x03FFFFFC; -} - -static inline uint32_t BD(uint32_t opcode) -{ - return (opcode >> 0) & 0xFFFC; -} - -EXTRACT_HELPER(BO, 21, 5); -EXTRACT_HELPER(BI, 16, 5); -/* Absolute/relative address */ -EXTRACT_HELPER(AA, 1, 1); -/* Link */ -EXTRACT_HELPER(LK, 0, 1); - -/* DFP Z22-form */ -EXTRACT_HELPER(DCM, 10, 6) - -/* DFP Z23-form */ -EXTRACT_HELPER(RMC, 9, 2) - -EXTRACT_HELPER_SPLIT(xT, 0, 1, 21, 5); -EXTRACT_HELPER_SPLIT(xS, 0, 1, 21, 5); -EXTRACT_HELPER_SPLIT(xA, 2, 1, 16, 5); -EXTRACT_HELPER_SPLIT(xB, 1, 1, 11, 5); -EXTRACT_HELPER_SPLIT(xC, 3, 1, 6, 5); -EXTRACT_HELPER(DM, 8, 2); -EXTRACT_HELPER(UIM, 16, 2); -EXTRACT_HELPER(SHW, 8, 2); -EXTRACT_HELPER(SP, 19, 2); -EXTRACT_HELPER(IMM8, 11, 8); - /*****************************************************************************/ /* PowerPC instructions table */ @@ -763,17 +612,17 @@ static inline void gen_op_cmp(TCGv arg0, TCGv arg1, int s, int crf) tcg_gen_setcond_tl((s ? TCG_COND_LT: TCG_COND_LTU), t0, arg0, arg1); tcg_gen_trunc_tl_i32(t1, t0); - tcg_gen_shli_i32(t1, t1, CRF_LT); + tcg_gen_shli_i32(t1, t1, CRF_LT_BIT); tcg_gen_or_i32(cpu_crf[crf], cpu_crf[crf], t1); tcg_gen_setcond_tl((s ? TCG_COND_GT: TCG_COND_GTU), t0, arg0, arg1); tcg_gen_trunc_tl_i32(t1, t0); - tcg_gen_shli_i32(t1, t1, CRF_GT); + tcg_gen_shli_i32(t1, t1, CRF_GT_BIT); tcg_gen_or_i32(cpu_crf[crf], cpu_crf[crf], t1); tcg_gen_setcond_tl(TCG_COND_EQ, t0, arg0, arg1); tcg_gen_trunc_tl_i32(t1, t0); - tcg_gen_shli_i32(t1, t1, CRF_EQ); + tcg_gen_shli_i32(t1, t1, CRF_EQ_BIT); tcg_gen_or_i32(cpu_crf[crf], cpu_crf[crf], t1); tcg_temp_free(t0); @@ -899,7 +748,7 @@ static void gen_cmprb(DisasContext *ctx) tcg_gen_and_i32(src2lo, src2lo, src2hi); tcg_gen_or_i32(crf, crf, src2lo); } - tcg_gen_shli_i32(crf, crf, CRF_GT); + tcg_gen_shli_i32(crf, crf, CRF_GT_BIT); tcg_temp_free_i32(src1); tcg_temp_free_i32(src2); tcg_temp_free_i32(src2lo); @@ -3148,7 +2997,7 @@ static void gen_conditional_store(DisasContext *ctx, TCGv EA, tcg_gen_trunc_tl_i32(cpu_crf[0], cpu_so); l1 = gen_new_label(); tcg_gen_brcond_tl(TCG_COND_NE, EA, cpu_reserve, l1); - tcg_gen_ori_i32(cpu_crf[0], cpu_crf[0], 1 << CRF_EQ); + tcg_gen_ori_i32(cpu_crf[0], cpu_crf[0], CRF_EQ); tcg_gen_qemu_st_tl(cpu_gpr[reg], EA, ctx->mem_idx, memop); gen_set_label(l1); tcg_gen_movi_tl(cpu_reserve, -1); @@ -3242,7 +3091,7 @@ static void gen_stqcx_(DisasContext *ctx) tcg_gen_trunc_tl_i32(cpu_crf[0], cpu_so); l1 = gen_new_label(); tcg_gen_brcond_tl(TCG_COND_NE, EA, cpu_reserve, l1); - tcg_gen_ori_i32(cpu_crf[0], cpu_crf[0], 1 << CRF_EQ); + tcg_gen_ori_i32(cpu_crf[0], cpu_crf[0], CRF_EQ); if (unlikely(ctx->le_mode)) { gpr1 = cpu_gpr[reg + 1]; @@ -3323,6 +3172,11 @@ static void gen_nap(DisasContext *ctx) #endif /* defined(CONFIG_USER_ONLY) */ } +static void gen_stop(DisasContext *ctx) +{ + gen_nap(ctx); +} + static void gen_sleep(DisasContext *ctx) { #if defined(CONFIG_USER_ONLY) @@ -4423,7 +4277,7 @@ static void gen_slbfee_(DisasContext *ctx) l2 = gen_new_label(); tcg_gen_trunc_tl_i32(cpu_crf[0], cpu_so); tcg_gen_brcondi_tl(TCG_COND_EQ, cpu_gpr[rS(ctx->opcode)], -1, l1); - tcg_gen_ori_i32(cpu_crf[0], cpu_crf[0], 1 << CRF_EQ); + tcg_gen_ori_i32(cpu_crf[0], cpu_crf[0], CRF_EQ); tcg_gen_br(l2); gen_set_label(l1); tcg_gen_movi_tl(cpu_gpr[rS(ctx->opcode)], 0); @@ -6166,6 +6020,10 @@ GEN_TM_NOOP(tabortwci); GEN_TM_NOOP(tabortdc); GEN_TM_NOOP(tabortdci); GEN_TM_NOOP(tsr); +static inline void gen_cp_abort(DisasContext *ctx) +{ + // Do Nothing +} static void gen_tcheck(DisasContext *ctx) { @@ -6223,6 +6081,67 @@ GEN_TM_PRIV_NOOP(trechkpt); #include "translate/spe-impl.inc.c" +/* Handles lfdp, lxsd, lxssp */ +static void gen_dform39(DisasContext *ctx) +{ + switch (ctx->opcode & 0x3) { + case 0: /* lfdp */ + if (ctx->insns_flags2 & PPC2_ISA205) { + return gen_lfdp(ctx); + } + break; + case 2: /* lxsd */ + if (ctx->insns_flags2 & PPC2_ISA300) { + return gen_lxsd(ctx); + } + break; + case 3: /* lxssp */ + if (ctx->insns_flags2 & PPC2_ISA300) { + return gen_lxssp(ctx); + } + break; + } + return gen_invalid(ctx); +} + +/* handles stfdp, lxv, stxsd, stxssp lxvx */ +static void gen_dform3D(DisasContext *ctx) +{ + if ((ctx->opcode & 3) == 1) { /* DQ-FORM */ + switch (ctx->opcode & 0x7) { + case 1: /* lxv */ + if (ctx->insns_flags2 & PPC2_ISA300) { + return gen_lxv(ctx); + } + break; + case 5: /* stxv */ + if (ctx->insns_flags2 & PPC2_ISA300) { + return gen_stxv(ctx); + } + break; + } + } else { /* DS-FORM */ + switch (ctx->opcode & 0x3) { + case 0: /* stfdp */ + if (ctx->insns_flags2 & PPC2_ISA205) { + return gen_stfdp(ctx); + } + break; + case 2: /* stxsd */ + if (ctx->insns_flags2 & PPC2_ISA300) { + return gen_stxsd(ctx); + } + break; + case 3: /* stxssp */ + if (ctx->insns_flags2 & PPC2_ISA300) { + return gen_stxssp(ctx); + } + break; + } + } + return gen_invalid(ctx); +} + static opcode_t opcodes[] = { GEN_HANDLER(invalid, 0x00, 0x00, 0x00, 0xFFFFFFFF, PPC_NONE), GEN_HANDLER(cmp, 0x1F, 0x00, 0x00, 0x00400000, PPC_INTEGER), @@ -6255,6 +6174,7 @@ GEN_HANDLER2(andi_, "andi.", 0x1C, 0xFF, 0xFF, 0x00000000, PPC_INTEGER), GEN_HANDLER2(andis_, "andis.", 0x1D, 0xFF, 0xFF, 0x00000000, PPC_INTEGER), GEN_HANDLER(cntlzw, 0x1F, 0x1A, 0x00, 0x00000000, PPC_INTEGER), GEN_HANDLER_E(cnttzw, 0x1F, 0x1A, 0x10, 0x00000000, PPC_NONE, PPC2_ISA300), +GEN_HANDLER_E(cp_abort, 0x1F, 0x06, 0x1A, 0x03FFF801, PPC_NONE, PPC2_ISA300), GEN_HANDLER(or, 0x1F, 0x1C, 0x0D, 0x00000000, PPC_INTEGER), GEN_HANDLER(xor, 0x1F, 0x1C, 0x09, 0x00000000, PPC_INTEGER), GEN_HANDLER(ori, 0x18, 0xFF, 0xFF, 0x00000000, PPC_INTEGER), @@ -6295,6 +6215,10 @@ GEN_HANDLER(ld, 0x3A, 0xFF, 0xFF, 0x00000000, PPC_64B), GEN_HANDLER(lq, 0x38, 0xFF, 0xFF, 0x00000000, PPC_64BX), GEN_HANDLER(std, 0x3E, 0xFF, 0xFF, 0x00000000, PPC_64B), #endif +/* handles lfdp, lxsd, lxssp */ +GEN_HANDLER_E(dform39, 0x39, 0xFF, 0xFF, 0x00000000, PPC_NONE, PPC2_ISA205), +/* handles stfdp, lxv, stxsd, stxssp, stxv */ +GEN_HANDLER_E(dform3D, 0x3D, 0xFF, 0xFF, 0x00000000, PPC_NONE, PPC2_ISA205), GEN_HANDLER(lmw, 0x2E, 0xFF, 0xFF, 0x00000000, PPC_INTEGER), GEN_HANDLER(stmw, 0x2F, 0xFF, 0xFF, 0x00000000, PPC_INTEGER), GEN_HANDLER(lswi, 0x1F, 0x15, 0x12, 0x00000001, PPC_STRING), @@ -6326,6 +6250,7 @@ GEN_HANDLER(mcrf, 0x13, 0x00, 0xFF, 0x00000001, PPC_INTEGER), GEN_HANDLER(rfi, 0x13, 0x12, 0x01, 0x03FF8001, PPC_FLOW), #if defined(TARGET_PPC64) GEN_HANDLER(rfid, 0x13, 0x12, 0x00, 0x03FF8001, PPC_64B), +GEN_HANDLER_E(stop, 0x13, 0x12, 0x0b, 0x03FFF801, PPC_NONE, PPC2_ISA300), GEN_HANDLER_E(doze, 0x13, 0x12, 0x0c, 0x03FFF801, PPC_NONE, PPC2_PM_ISA206), GEN_HANDLER_E(nap, 0x13, 0x12, 0x0d, 0x03FFF801, PPC_NONE, PPC2_PM_ISA206), GEN_HANDLER_E(sleep, 0x13, 0x12, 0x0e, 0x03FFF801, PPC_NONE, PPC2_PM_ISA206), @@ -6910,6 +6835,9 @@ void ppc_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf, } #endif + if (env->spr_cb[SPR_LPCR].name) + cpu_fprintf(f, " LPCR " TARGET_FMT_lx "\n", env->spr[SPR_LPCR]); + switch (env->mmu_model) { case POWERPC_MMU_32B: case POWERPC_MMU_601: diff --git a/target/ppc/translate/fp-impl.inc.c b/target/ppc/translate/fp-impl.inc.c index 872af7b56f..2fbd4d4f38 100644 --- a/target/ppc/translate/fp-impl.inc.c +++ b/target/ppc/translate/fp-impl.inc.c @@ -9,9 +9,9 @@ static inline void gen_reset_fpstatus(void) gen_helper_reset_fpstatus(cpu_env); } -static inline void gen_compute_fprf(TCGv_i64 arg) +static inline void gen_compute_fprf_float64(TCGv_i64 arg) { - gen_helper_compute_fprf(cpu_env, arg); + gen_helper_compute_fprf_float64(cpu_env, arg); gen_helper_float_check_status(cpu_env); } @@ -47,7 +47,7 @@ static void gen_f##name(DisasContext *ctx) \ cpu_fpr[rD(ctx->opcode)]); \ } \ if (set_fprf) { \ - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); \ + gen_compute_fprf_float64(cpu_fpr[rD(ctx->opcode)]); \ } \ if (unlikely(Rc(ctx->opcode) != 0)) { \ gen_set_cr1_from_fpscr(ctx); \ @@ -74,7 +74,7 @@ static void gen_f##name(DisasContext *ctx) \ cpu_fpr[rD(ctx->opcode)]); \ } \ if (set_fprf) { \ - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); \ + gen_compute_fprf_float64(cpu_fpr[rD(ctx->opcode)]); \ } \ if (unlikely(Rc(ctx->opcode) != 0)) { \ gen_set_cr1_from_fpscr(ctx); \ @@ -100,7 +100,7 @@ static void gen_f##name(DisasContext *ctx) \ cpu_fpr[rD(ctx->opcode)]); \ } \ if (set_fprf) { \ - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); \ + gen_compute_fprf_float64(cpu_fpr[rD(ctx->opcode)]); \ } \ if (unlikely(Rc(ctx->opcode) != 0)) { \ gen_set_cr1_from_fpscr(ctx); \ @@ -121,7 +121,7 @@ static void gen_f##name(DisasContext *ctx) \ gen_helper_f##name(cpu_fpr[rD(ctx->opcode)], cpu_env, \ cpu_fpr[rB(ctx->opcode)]); \ if (set_fprf) { \ - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); \ + gen_compute_fprf_float64(cpu_fpr[rD(ctx->opcode)]); \ } \ if (unlikely(Rc(ctx->opcode) != 0)) { \ gen_set_cr1_from_fpscr(ctx); \ @@ -139,7 +139,7 @@ static void gen_f##name(DisasContext *ctx) \ gen_helper_f##name(cpu_fpr[rD(ctx->opcode)], cpu_env, \ cpu_fpr[rB(ctx->opcode)]); \ if (set_fprf) { \ - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); \ + gen_compute_fprf_float64(cpu_fpr[rD(ctx->opcode)]); \ } \ if (unlikely(Rc(ctx->opcode) != 0)) { \ gen_set_cr1_from_fpscr(ctx); \ @@ -174,7 +174,7 @@ static void gen_frsqrtes(DisasContext *ctx) cpu_fpr[rB(ctx->opcode)]); gen_helper_frsp(cpu_fpr[rD(ctx->opcode)], cpu_env, cpu_fpr[rD(ctx->opcode)]); - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); + gen_compute_fprf_float64(cpu_fpr[rD(ctx->opcode)]); if (unlikely(Rc(ctx->opcode) != 0)) { gen_set_cr1_from_fpscr(ctx); } @@ -196,7 +196,7 @@ static void gen_fsqrt(DisasContext *ctx) gen_reset_fpstatus(); gen_helper_fsqrt(cpu_fpr[rD(ctx->opcode)], cpu_env, cpu_fpr[rB(ctx->opcode)]); - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); + gen_compute_fprf_float64(cpu_fpr[rD(ctx->opcode)]); if (unlikely(Rc(ctx->opcode) != 0)) { gen_set_cr1_from_fpscr(ctx); } @@ -213,7 +213,7 @@ static void gen_fsqrts(DisasContext *ctx) cpu_fpr[rB(ctx->opcode)]); gen_helper_frsp(cpu_fpr[rD(ctx->opcode)], cpu_env, cpu_fpr[rD(ctx->opcode)]); - gen_compute_fprf(cpu_fpr[rD(ctx->opcode)]); + gen_compute_fprf_float64(cpu_fpr[rD(ctx->opcode)]); if (unlikely(Rc(ctx->opcode) != 0)) { gen_set_cr1_from_fpscr(ctx); } diff --git a/target/ppc/translate/fp-ops.inc.c b/target/ppc/translate/fp-ops.inc.c index d36ab4ecc3..3c6d05a074 100644 --- a/target/ppc/translate/fp-ops.inc.c +++ b/target/ppc/translate/fp-ops.inc.c @@ -68,7 +68,6 @@ GEN_LDFS(lfd, ld64, 0x12, PPC_FLOAT) GEN_LDFS(lfs, ld32fs, 0x10, PPC_FLOAT) GEN_HANDLER_E(lfiwax, 0x1f, 0x17, 0x1a, 0x00000001, PPC_NONE, PPC2_ISA205), GEN_HANDLER_E(lfiwzx, 0x1f, 0x17, 0x1b, 0x1, PPC_NONE, PPC2_FP_CVT_ISA206), -GEN_HANDLER_E(lfdp, 0x39, 0xFF, 0xFF, 0x00200003, PPC_NONE, PPC2_ISA205), GEN_HANDLER_E(lfdpx, 0x1F, 0x17, 0x18, 0x00200001, PPC_NONE, PPC2_ISA205), #define GEN_STF(name, stop, opc, type) \ @@ -88,7 +87,6 @@ GEN_STXF(name, stop, 0x17, op | 0x00, type) GEN_STFS(stfd, st64_i64, 0x16, PPC_FLOAT) GEN_STFS(stfs, st32fs, 0x14, PPC_FLOAT) GEN_STXF(stfiw, st32fiw, 0x17, 0x1E, PPC_FLOAT_STFIWX) -GEN_HANDLER_E(stfdp, 0x3D, 0xFF, 0xFF, 0x00200003, PPC_NONE, PPC2_ISA205), GEN_HANDLER_E(stfdpx, 0x1F, 0x17, 0x1C, 0x00200001, PPC_NONE, PPC2_ISA205), GEN_HANDLER(frsqrtes, 0x3B, 0x1A, 0xFF, 0x001F07C0, PPC_FLOAT_FRSQRTES), diff --git a/target/ppc/translate/vmx-impl.inc.c b/target/ppc/translate/vmx-impl.inc.c index 7143eb3a39..3cb6fc2926 100644 --- a/target/ppc/translate/vmx-impl.inc.c +++ b/target/ppc/translate/vmx-impl.inc.c @@ -340,6 +340,19 @@ static void glue(gen_, name0##_##name1)(DisasContext *ctx) \ } \ } +#define GEN_VXFORM_HETRO(name, opc2, opc3) \ +static void glue(gen_, name)(DisasContext *ctx) \ +{ \ + TCGv_ptr rb; \ + if (unlikely(!ctx->altivec_enabled)) { \ + gen_exception(ctx, POWERPC_EXCP_VPU); \ + return; \ + } \ + rb = gen_avr_ptr(rB(ctx->opcode)); \ + gen_helper_##name(cpu_gpr[rD(ctx->opcode)], cpu_gpr[rA(ctx->opcode)], rb); \ + tcg_temp_free_ptr(rb); \ +} + GEN_VXFORM(vaddubm, 0, 0); GEN_VXFORM_DUAL_EXT(vaddubm, PPC_ALTIVEC, PPC_NONE, 0, \ vmul10cuq, PPC_NONE, PPC2_ISA300, 0x0000F800) @@ -525,6 +538,16 @@ GEN_VXFORM_ENV(vaddfp, 5, 0); GEN_VXFORM_ENV(vsubfp, 5, 1); GEN_VXFORM_ENV(vmaxfp, 5, 16); GEN_VXFORM_ENV(vminfp, 5, 17); +GEN_VXFORM_HETRO(vextublx, 6, 24) +GEN_VXFORM_HETRO(vextuhlx, 6, 25) +GEN_VXFORM_HETRO(vextuwlx, 6, 26) +GEN_VXFORM_DUAL(vmrgow, PPC_NONE, PPC2_ALTIVEC_207, + vextuwlx, PPC_NONE, PPC2_ISA300) +GEN_VXFORM_HETRO(vextubrx, 6, 28) +GEN_VXFORM_HETRO(vextuhrx, 6, 29) +GEN_VXFORM_HETRO(vextuwrx, 6, 30) +GEN_VXFORM_DUAL(vmrgew, PPC_NONE, PPC2_ALTIVEC_207, \ + vextuwrx, PPC_NONE, PPC2_ISA300) #define GEN_VXRFORM1(opname, name, str, opc2, opc3) \ static void glue(gen_, name)(DisasContext *ctx) \ @@ -989,10 +1012,25 @@ GEN_BCD2(bcdcfn) GEN_BCD2(bcdctn) GEN_BCD2(bcdcfz) GEN_BCD2(bcdctz) +GEN_BCD2(bcdcfsq) +GEN_BCD2(bcdctsq) +GEN_BCD2(bcdsetsgn) +GEN_BCD(bcdcpsgn); +GEN_BCD(bcds); +GEN_BCD(bcdus); +GEN_BCD(bcdsr); +GEN_BCD(bcdtrunc); +GEN_BCD(bcdutrunc); static void gen_xpnd04_1(DisasContext *ctx) { switch (opc4(ctx->opcode)) { + case 0: + gen_bcdctsq(ctx); + break; + case 2: + gen_bcdcfsq(ctx); + break; case 4: gen_bcdctz(ctx); break; @@ -1005,6 +1043,9 @@ static void gen_xpnd04_1(DisasContext *ctx) case 7: gen_bcdcfn(ctx); break; + case 31: + gen_bcdsetsgn(ctx); + break; default: gen_invalid(ctx); break; @@ -1014,6 +1055,12 @@ static void gen_xpnd04_1(DisasContext *ctx) static void gen_xpnd04_2(DisasContext *ctx) { switch (opc4(ctx->opcode)) { + case 0: + gen_bcdctsq(ctx); + break; + case 2: + gen_bcdcfsq(ctx); + break; case 4: gen_bcdctz(ctx); break; @@ -1023,12 +1070,16 @@ static void gen_xpnd04_2(DisasContext *ctx) case 7: gen_bcdcfn(ctx); break; + case 31: + gen_bcdsetsgn(ctx); + break; default: gen_invalid(ctx); break; } } + GEN_VXFORM_DUAL(vsubcuw, PPC_ALTIVEC, PPC_NONE, \ xpnd04_1, PPC_NONE, PPC2_ISA300) GEN_VXFORM_DUAL(vsubsws, PPC_ALTIVEC, PPC_NONE, \ @@ -1042,6 +1093,19 @@ GEN_VXFORM_DUAL(vsubuhm, PPC_ALTIVEC, PPC_NONE, \ bcdsub, PPC_NONE, PPC2_ALTIVEC_207) GEN_VXFORM_DUAL(vsubuhs, PPC_ALTIVEC, PPC_NONE, \ bcdsub, PPC_NONE, PPC2_ALTIVEC_207) +GEN_VXFORM_DUAL(vaddshs, PPC_ALTIVEC, PPC_NONE, \ + bcdcpsgn, PPC_NONE, PPC2_ISA300) +GEN_VXFORM_DUAL(vsubudm, PPC2_ALTIVEC_207, PPC_NONE, \ + bcds, PPC_NONE, PPC2_ISA300) +GEN_VXFORM_DUAL(vsubuwm, PPC_ALTIVEC, PPC_NONE, \ + bcdus, PPC_NONE, PPC2_ISA300) +GEN_VXFORM_DUAL(vsubsbs, PPC_ALTIVEC, PPC_NONE, \ + bcdtrunc, PPC_NONE, PPC2_ISA300) +GEN_VXFORM_DUAL(vsubuqm, PPC2_ALTIVEC_207, PPC_NONE, \ + bcdtrunc, PPC_NONE, PPC2_ISA300) +GEN_VXFORM_DUAL(vsubcuq, PPC2_ALTIVEC_207, PPC_NONE, \ + bcdutrunc, PPC_NONE, PPC2_ISA300) + static void gen_vsbox(DisasContext *ctx) { diff --git a/target/ppc/translate/vmx-ops.inc.c b/target/ppc/translate/vmx-ops.inc.c index f02b3bed50..139f80cb24 100644 --- a/target/ppc/translate/vmx-ops.inc.c +++ b/target/ppc/translate/vmx-ops.inc.c @@ -61,8 +61,9 @@ GEN_VXFORM(vadduwm, 0, 2), GEN_VXFORM_207(vaddudm, 0, 3), GEN_VXFORM_DUAL(vsububm, bcdadd, 0, 16, PPC_ALTIVEC, PPC_NONE), GEN_VXFORM_DUAL(vsubuhm, bcdsub, 0, 17, PPC_ALTIVEC, PPC_NONE), -GEN_VXFORM(vsubuwm, 0, 18), -GEN_VXFORM_207(vsubudm, 0, 19), +GEN_VXFORM_DUAL(vsubuwm, bcdus, 0, 18, PPC_ALTIVEC, PPC2_ISA300), +GEN_VXFORM_DUAL(vsubudm, bcds, 0, 19, PPC2_ALTIVEC_207, PPC2_ISA300), +GEN_VXFORM_300(bcds, 0, 27), GEN_VXFORM(vmaxub, 1, 0), GEN_VXFORM(vmaxuh, 1, 1), GEN_VXFORM(vmaxuw, 1, 2), @@ -91,8 +92,12 @@ GEN_VXFORM(vmrghw, 6, 2), GEN_VXFORM(vmrglb, 6, 4), GEN_VXFORM(vmrglh, 6, 5), GEN_VXFORM(vmrglw, 6, 6), -GEN_VXFORM_207(vmrgew, 6, 30), -GEN_VXFORM_207(vmrgow, 6, 26), +GEN_VXFORM_300(vextublx, 6, 24), +GEN_VXFORM_300(vextuhlx, 6, 25), +GEN_VXFORM_DUAL(vmrgow, vextuwlx, 6, 26, PPC_NONE, PPC2_ALTIVEC_207), +GEN_VXFORM_300(vextubrx, 6, 28), +GEN_VXFORM_300(vextuhrx, 6, 29), +GEN_VXFORM_DUAL(vmrgew, vextuwrx, 6, 30, PPC_NONE, PPC2_ALTIVEC_207), GEN_VXFORM(vmuloub, 4, 0), GEN_VXFORM(vmulouh, 4, 1), GEN_VXFORM_DUAL(vmulouw, vmuluwm, 4, 2, PPC_ALTIVEC, PPC_NONE), @@ -127,23 +132,25 @@ GEN_HANDLER_E_2(vprtybd, 0x4, 0x1, 0x18, 9, 0, PPC_NONE, PPC2_ISA300), GEN_HANDLER_E_2(vprtybq, 0x4, 0x1, 0x18, 10, 0, PPC_NONE, PPC2_ISA300), GEN_VXFORM_DUAL(vsubcuw, xpnd04_1, 0, 22, PPC_ALTIVEC, PPC_NONE), +GEN_VXFORM_300(bcdsr, 0, 23), +GEN_VXFORM_300(bcdsr, 0, 31), GEN_VXFORM_DUAL(vaddubs, vmul10uq, 0, 8, PPC_ALTIVEC, PPC_NONE), GEN_VXFORM_DUAL(vadduhs, vmul10euq, 0, 9, PPC_ALTIVEC, PPC_NONE), GEN_VXFORM(vadduws, 0, 10), GEN_VXFORM(vaddsbs, 0, 12), -GEN_VXFORM(vaddshs, 0, 13), +GEN_VXFORM_DUAL(vaddshs, bcdcpsgn, 0, 13, PPC_ALTIVEC, PPC_NONE), GEN_VXFORM(vaddsws, 0, 14), GEN_VXFORM_DUAL(vsububs, bcdadd, 0, 24, PPC_ALTIVEC, PPC_NONE), GEN_VXFORM_DUAL(vsubuhs, bcdsub, 0, 25, PPC_ALTIVEC, PPC_NONE), GEN_VXFORM(vsubuws, 0, 26), -GEN_VXFORM(vsubsbs, 0, 28), +GEN_VXFORM_DUAL(vsubsbs, bcdtrunc, 0, 28, PPC_NONE, PPC2_ISA300), GEN_VXFORM(vsubshs, 0, 29), GEN_VXFORM_DUAL(vsubsws, xpnd04_2, 0, 30, PPC_ALTIVEC, PPC_NONE), GEN_VXFORM_207(vadduqm, 0, 4), GEN_VXFORM_207(vaddcuq, 0, 5), GEN_VXFORM_DUAL(vaddeuqm, vaddecuq, 30, 0xFF, PPC_NONE, PPC2_ALTIVEC_207), -GEN_VXFORM_207(vsubuqm, 0, 20), -GEN_VXFORM_207(vsubcuq, 0, 21), +GEN_VXFORM_DUAL(vsubuqm, bcdtrunc, 0, 20, PPC2_ALTIVEC_207, PPC2_ISA300), +GEN_VXFORM_DUAL(vsubcuq, bcdutrunc, 0, 21, PPC2_ALTIVEC_207, PPC2_ISA300), GEN_VXFORM_DUAL(vsubeuqm, vsubecuq, 31, 0xFF, PPC_NONE, PPC2_ALTIVEC_207), GEN_VXFORM(vrlb, 2, 0), GEN_VXFORM(vrlh, 2, 1), diff --git a/target/ppc/translate/vsx-impl.inc.c b/target/ppc/translate/vsx-impl.inc.c index 5a27be4bd4..a44c0034a8 100644 --- a/target/ppc/translate/vsx-impl.inc.c +++ b/target/ppc/translate/vsx-impl.inc.c @@ -190,6 +190,109 @@ static void gen_lxvb16x(DisasContext *ctx) tcg_temp_free(EA); } +#define VSX_VECTOR_LOAD_STORE(name, op, indexed) \ +static void gen_##name(DisasContext *ctx) \ +{ \ + int xt; \ + TCGv EA; \ + TCGv_i64 xth, xtl; \ + \ + if (indexed) { \ + xt = xT(ctx->opcode); \ + } else { \ + xt = DQxT(ctx->opcode); \ + } \ + xth = cpu_vsrh(xt); \ + xtl = cpu_vsrl(xt); \ + \ + if (xt < 32) { \ + if (unlikely(!ctx->vsx_enabled)) { \ + gen_exception(ctx, POWERPC_EXCP_VSXU); \ + return; \ + } \ + } else { \ + if (unlikely(!ctx->altivec_enabled)) { \ + gen_exception(ctx, POWERPC_EXCP_VPU); \ + return; \ + } \ + } \ + gen_set_access_type(ctx, ACCESS_INT); \ + EA = tcg_temp_new(); \ + if (indexed) { \ + gen_addr_reg_index(ctx, EA); \ + } else { \ + gen_addr_imm_index(ctx, EA, 0x0F); \ + } \ + if (ctx->le_mode) { \ + tcg_gen_qemu_##op(xtl, EA, ctx->mem_idx, MO_LEQ); \ + tcg_gen_addi_tl(EA, EA, 8); \ + tcg_gen_qemu_##op(xth, EA, ctx->mem_idx, MO_LEQ); \ + } else { \ + tcg_gen_qemu_##op(xth, EA, ctx->mem_idx, MO_BEQ); \ + tcg_gen_addi_tl(EA, EA, 8); \ + tcg_gen_qemu_##op(xtl, EA, ctx->mem_idx, MO_BEQ); \ + } \ + tcg_temp_free(EA); \ +} + +VSX_VECTOR_LOAD_STORE(lxv, ld_i64, 0) +VSX_VECTOR_LOAD_STORE(stxv, st_i64, 0) +VSX_VECTOR_LOAD_STORE(lxvx, ld_i64, 1) +VSX_VECTOR_LOAD_STORE(stxvx, st_i64, 1) + +#ifdef TARGET_PPC64 +#define VSX_VECTOR_LOAD_STORE_LENGTH(name) \ +static void gen_##name(DisasContext *ctx) \ +{ \ + TCGv EA, xt; \ + \ + if (xT(ctx->opcode) < 32) { \ + if (unlikely(!ctx->vsx_enabled)) { \ + gen_exception(ctx, POWERPC_EXCP_VSXU); \ + return; \ + } \ + } else { \ + if (unlikely(!ctx->altivec_enabled)) { \ + gen_exception(ctx, POWERPC_EXCP_VPU); \ + return; \ + } \ + } \ + EA = tcg_temp_new(); \ + xt = tcg_const_tl(xT(ctx->opcode)); \ + gen_set_access_type(ctx, ACCESS_INT); \ + gen_addr_register(ctx, EA); \ + gen_helper_##name(cpu_env, EA, xt, cpu_gpr[rB(ctx->opcode)]); \ + tcg_temp_free(EA); \ + tcg_temp_free(xt); \ +} + +VSX_VECTOR_LOAD_STORE_LENGTH(lxvl) +VSX_VECTOR_LOAD_STORE_LENGTH(lxvll) +VSX_VECTOR_LOAD_STORE_LENGTH(stxvl) +VSX_VECTOR_LOAD_STORE_LENGTH(stxvll) +#endif + +#define VSX_LOAD_SCALAR_DS(name, operation) \ +static void gen_##name(DisasContext *ctx) \ +{ \ + TCGv EA; \ + TCGv_i64 xth = cpu_vsrh(rD(ctx->opcode) + 32); \ + \ + if (unlikely(!ctx->altivec_enabled)) { \ + gen_exception(ctx, POWERPC_EXCP_VPU); \ + return; \ + } \ + gen_set_access_type(ctx, ACCESS_INT); \ + EA = tcg_temp_new(); \ + gen_addr_imm_index(ctx, EA, 0x03); \ + gen_qemu_##operation(ctx, xth, EA); \ + /* NOTE: cpu_vsrl is undefined */ \ + tcg_temp_free(EA); \ +} + +VSX_LOAD_SCALAR_DS(lxsd, ld64_i64) +VSX_LOAD_SCALAR_DS(lxssp, ld32fs) + #define VSX_STORE_SCALAR(name, operation) \ static void gen_##name(DisasContext *ctx) \ { \ @@ -311,6 +414,27 @@ static void gen_stxvb16x(DisasContext *ctx) tcg_temp_free(EA); } +#define VSX_STORE_SCALAR_DS(name, operation) \ +static void gen_##name(DisasContext *ctx) \ +{ \ + TCGv EA; \ + TCGv_i64 xth = cpu_vsrh(rD(ctx->opcode) + 32); \ + \ + if (unlikely(!ctx->altivec_enabled)) { \ + gen_exception(ctx, POWERPC_EXCP_VPU); \ + return; \ + } \ + gen_set_access_type(ctx, ACCESS_INT); \ + EA = tcg_temp_new(); \ + gen_addr_imm_index(ctx, EA, 0x03); \ + gen_qemu_##operation(ctx, xth, EA); \ + /* NOTE: cpu_vsrl is undefined */ \ + tcg_temp_free(EA); \ +} + +VSX_LOAD_SCALAR_DS(stxsd, st64_i64) +VSX_LOAD_SCALAR_DS(stxssp, st32fs) + #define MV_VSRW(name, tcgop1, tcgop2, target, source) \ static void gen_##name(DisasContext *ctx) \ { \ @@ -517,6 +641,55 @@ VSX_SCALAR_MOVE(xsnabsdp, OP_NABS, SGN_MASK_DP) VSX_SCALAR_MOVE(xsnegdp, OP_NEG, SGN_MASK_DP) VSX_SCALAR_MOVE(xscpsgndp, OP_CPSGN, SGN_MASK_DP) +#define VSX_SCALAR_MOVE_QP(name, op, sgn_mask) \ +static void glue(gen_, name)(DisasContext *ctx) \ +{ \ + int xa; \ + int xt = rD(ctx->opcode) + 32; \ + int xb = rB(ctx->opcode) + 32; \ + TCGv_i64 xah, xbh, xbl, sgm; \ + \ + if (unlikely(!ctx->vsx_enabled)) { \ + gen_exception(ctx, POWERPC_EXCP_VSXU); \ + return; \ + } \ + xbh = tcg_temp_new_i64(); \ + xbl = tcg_temp_new_i64(); \ + sgm = tcg_temp_new_i64(); \ + tcg_gen_mov_i64(xbh, cpu_vsrh(xb)); \ + tcg_gen_mov_i64(xbl, cpu_vsrl(xb)); \ + tcg_gen_movi_i64(sgm, sgn_mask); \ + switch (op) { \ + case OP_ABS: \ + tcg_gen_andc_i64(xbh, xbh, sgm); \ + break; \ + case OP_NABS: \ + tcg_gen_or_i64(xbh, xbh, sgm); \ + break; \ + case OP_NEG: \ + tcg_gen_xor_i64(xbh, xbh, sgm); \ + break; \ + case OP_CPSGN: \ + xah = tcg_temp_new_i64(); \ + xa = rA(ctx->opcode) + 32; \ + tcg_gen_and_i64(xah, cpu_vsrh(xa), sgm); \ + tcg_gen_andc_i64(xbh, xbh, sgm); \ + tcg_gen_or_i64(xbh, xbh, xah); \ + tcg_temp_free_i64(xah); \ + break; \ + } \ + tcg_gen_mov_i64(cpu_vsrh(xt), xbh); \ + tcg_gen_mov_i64(cpu_vsrl(xt), xbl); \ + tcg_temp_free_i64(xbl); \ + tcg_temp_free_i64(xbh); \ + tcg_temp_free_i64(sgm); \ +} + +VSX_SCALAR_MOVE_QP(xsabsqp, OP_ABS, SGN_MASK_DP) +VSX_SCALAR_MOVE_QP(xsnabsqp, OP_NABS, SGN_MASK_DP) +VSX_SCALAR_MOVE_QP(xsnegqp, OP_NEG, SGN_MASK_DP) +VSX_SCALAR_MOVE_QP(xscpsgnqp, OP_CPSGN, SGN_MASK_DP) + #define VSX_VECTOR_MOVE(name, op, sgn_mask) \ static void glue(gen_, name)(DisasContext * ctx) \ { \ @@ -604,9 +777,12 @@ static void gen_##name(DisasContext * ctx) \ } GEN_VSX_HELPER_2(xsadddp, 0x00, 0x04, 0, PPC2_VSX) +GEN_VSX_HELPER_2(xsaddqp, 0x04, 0x00, 0, PPC2_ISA300) GEN_VSX_HELPER_2(xssubdp, 0x00, 0x05, 0, PPC2_VSX) GEN_VSX_HELPER_2(xsmuldp, 0x00, 0x06, 0, PPC2_VSX) +GEN_VSX_HELPER_2(xsmulqp, 0x04, 0x01, 0, PPC2_ISA300) GEN_VSX_HELPER_2(xsdivdp, 0x00, 0x07, 0, PPC2_VSX) +GEN_VSX_HELPER_2(xsdivqp, 0x04, 0x11, 0, PPC2_ISA300) GEN_VSX_HELPER_2(xsredp, 0x14, 0x05, 0, PPC2_VSX) GEN_VSX_HELPER_2(xssqrtdp, 0x16, 0x04, 0, PPC2_VSX) GEN_VSX_HELPER_2(xsrsqrtedp, 0x14, 0x04, 0, PPC2_VSX) @@ -624,12 +800,23 @@ GEN_VSX_HELPER_2(xscmpeqdp, 0x0C, 0x00, 0, PPC2_ISA300) GEN_VSX_HELPER_2(xscmpgtdp, 0x0C, 0x01, 0, PPC2_ISA300) GEN_VSX_HELPER_2(xscmpgedp, 0x0C, 0x02, 0, PPC2_ISA300) GEN_VSX_HELPER_2(xscmpnedp, 0x0C, 0x03, 0, PPC2_ISA300) +GEN_VSX_HELPER_2(xscmpexpdp, 0x0C, 0x07, 0, PPC2_ISA300) +GEN_VSX_HELPER_2(xscmpexpqp, 0x04, 0x05, 0, PPC2_ISA300) GEN_VSX_HELPER_2(xscmpodp, 0x0C, 0x05, 0, PPC2_VSX) GEN_VSX_HELPER_2(xscmpudp, 0x0C, 0x04, 0, PPC2_VSX) +GEN_VSX_HELPER_2(xscmpoqp, 0x04, 0x04, 0, PPC2_VSX) +GEN_VSX_HELPER_2(xscmpuqp, 0x04, 0x14, 0, PPC2_VSX) GEN_VSX_HELPER_2(xsmaxdp, 0x00, 0x14, 0, PPC2_VSX) GEN_VSX_HELPER_2(xsmindp, 0x00, 0x15, 0, PPC2_VSX) +GEN_VSX_HELPER_2(xscvdphp, 0x16, 0x15, 0x11, PPC2_ISA300) GEN_VSX_HELPER_2(xscvdpsp, 0x12, 0x10, 0, PPC2_VSX) +GEN_VSX_HELPER_2(xscvdpqp, 0x04, 0x1A, 0x16, PPC2_ISA300) GEN_VSX_HELPER_XT_XB_ENV(xscvdpspn, 0x16, 0x10, 0, PPC2_VSX207) +GEN_VSX_HELPER_2(xscvqpdp, 0x04, 0x1A, 0x14, PPC2_ISA300) +GEN_VSX_HELPER_2(xscvqpsdz, 0x04, 0x1A, 0x19, PPC2_ISA300) +GEN_VSX_HELPER_2(xscvqpswz, 0x04, 0x1A, 0x09, PPC2_ISA300) +GEN_VSX_HELPER_2(xscvhpdp, 0x16, 0x15, 0x10, PPC2_ISA300) +GEN_VSX_HELPER_2(xscvsdqp, 0x04, 0x1A, 0x0A, PPC2_ISA300) GEN_VSX_HELPER_2(xscvspdp, 0x12, 0x14, 0, PPC2_VSX) GEN_VSX_HELPER_XT_XB_ENV(xscvspdpn, 0x16, 0x14, 0, PPC2_VSX207) GEN_VSX_HELPER_2(xscvdpsxds, 0x10, 0x15, 0, PPC2_VSX) @@ -637,6 +824,7 @@ GEN_VSX_HELPER_2(xscvdpsxws, 0x10, 0x05, 0, PPC2_VSX) GEN_VSX_HELPER_2(xscvdpuxds, 0x10, 0x14, 0, PPC2_VSX) GEN_VSX_HELPER_2(xscvdpuxws, 0x10, 0x04, 0, PPC2_VSX) GEN_VSX_HELPER_2(xscvsxddp, 0x10, 0x17, 0, PPC2_VSX) +GEN_VSX_HELPER_2(xscvudqp, 0x04, 0x1A, 0x02, PPC2_ISA300) GEN_VSX_HELPER_2(xscvuxddp, 0x10, 0x16, 0, PPC2_VSX) GEN_VSX_HELPER_2(xsrdpi, 0x12, 0x04, 0, PPC2_VSX) GEN_VSX_HELPER_2(xsrdpic, 0x16, 0x06, 0, PPC2_VSX) @@ -662,6 +850,9 @@ GEN_VSX_HELPER_2(xsnmsubasp, 0x04, 0x12, 0, PPC2_VSX207) GEN_VSX_HELPER_2(xsnmsubmsp, 0x04, 0x13, 0, PPC2_VSX207) GEN_VSX_HELPER_2(xscvsxdsp, 0x10, 0x13, 0, PPC2_VSX207) GEN_VSX_HELPER_2(xscvuxdsp, 0x10, 0x12, 0, PPC2_VSX207) +GEN_VSX_HELPER_2(xststdcsp, 0x14, 0x12, 0, PPC2_ISA300) +GEN_VSX_HELPER_2(xststdcdp, 0x14, 0x16, 0, PPC2_ISA300) +GEN_VSX_HELPER_2(xststdcqp, 0x04, 0x16, 0, PPC2_ISA300) GEN_VSX_HELPER_2(xvadddp, 0x00, 0x0C, 0, PPC2_VSX) GEN_VSX_HELPER_2(xvsubdp, 0x00, 0x0D, 0, PPC2_VSX) @@ -725,6 +916,8 @@ GEN_VSX_HELPER_2(xvcmpgtsp, 0x0C, 0x09, 0, PPC2_VSX) GEN_VSX_HELPER_2(xvcmpgesp, 0x0C, 0x0A, 0, PPC2_VSX) GEN_VSX_HELPER_2(xvcmpnesp, 0x0C, 0x0B, 0, PPC2_VSX) GEN_VSX_HELPER_2(xvcvspdp, 0x12, 0x1C, 0, PPC2_VSX) +GEN_VSX_HELPER_2(xvcvhpsp, 0x16, 0x1D, 0x18, PPC2_ISA300) +GEN_VSX_HELPER_2(xvcvsphp, 0x16, 0x1D, 0x19, PPC2_ISA300) GEN_VSX_HELPER_2(xvcvspsxds, 0x10, 0x19, 0, PPC2_VSX) GEN_VSX_HELPER_2(xvcvspsxws, 0x10, 0x09, 0, PPC2_VSX) GEN_VSX_HELPER_2(xvcvspuxds, 0x10, 0x18, 0, PPC2_VSX) @@ -738,6 +931,10 @@ GEN_VSX_HELPER_2(xvrspic, 0x16, 0x0A, 0, PPC2_VSX) GEN_VSX_HELPER_2(xvrspim, 0x12, 0x0B, 0, PPC2_VSX) GEN_VSX_HELPER_2(xvrspip, 0x12, 0x0A, 0, PPC2_VSX) GEN_VSX_HELPER_2(xvrspiz, 0x12, 0x09, 0, PPC2_VSX) +GEN_VSX_HELPER_2(xvtstdcsp, 0x14, 0x1A, 0, PPC2_VSX) +GEN_VSX_HELPER_2(xvtstdcdp, 0x14, 0x1E, 0, PPC2_VSX) +GEN_VSX_HELPER_2(xxperm, 0x08, 0x03, 0, PPC2_ISA300) +GEN_VSX_HELPER_2(xxpermr, 0x08, 0x07, 0, PPC2_ISA300) static void gen_xxbrd(DisasContext *ctx) { @@ -1001,6 +1198,293 @@ static void gen_xxsldwi(DisasContext *ctx) tcg_temp_free_i64(xtl); } +#define VSX_EXTRACT_INSERT(name) \ +static void gen_##name(DisasContext *ctx) \ +{ \ + TCGv xt, xb; \ + TCGv_i32 t0 = tcg_temp_new_i32(); \ + uint8_t uimm = UIMM4(ctx->opcode); \ + \ + if (unlikely(!ctx->vsx_enabled)) { \ + gen_exception(ctx, POWERPC_EXCP_VSXU); \ + return; \ + } \ + xt = tcg_const_tl(xT(ctx->opcode)); \ + xb = tcg_const_tl(xB(ctx->opcode)); \ + /* uimm > 15 out of bound and for \ + * uimm > 12 handle as per hardware in helper \ + */ \ + if (uimm > 15) { \ + tcg_gen_movi_i64(cpu_vsrh(xT(ctx->opcode)), 0); \ + tcg_gen_movi_i64(cpu_vsrl(xT(ctx->opcode)), 0); \ + return; \ + } \ + tcg_gen_movi_i32(t0, uimm); \ + gen_helper_##name(cpu_env, xt, xb, t0); \ + tcg_temp_free(xb); \ + tcg_temp_free(xt); \ + tcg_temp_free_i32(t0); \ +} + +VSX_EXTRACT_INSERT(xxextractuw) +VSX_EXTRACT_INSERT(xxinsertw) + +#ifdef TARGET_PPC64 +static void gen_xsxexpdp(DisasContext *ctx) +{ + TCGv rt = cpu_gpr[rD(ctx->opcode)]; + if (unlikely(!ctx->vsx_enabled)) { + gen_exception(ctx, POWERPC_EXCP_VSXU); + return; + } + tcg_gen_shri_i64(rt, cpu_vsrh(xB(ctx->opcode)), 52); + tcg_gen_andi_i64(rt, rt, 0x7FF); +} + +static void gen_xsxexpqp(DisasContext *ctx) +{ + TCGv_i64 xth = cpu_vsrh(rD(ctx->opcode) + 32); + TCGv_i64 xtl = cpu_vsrl(rD(ctx->opcode) + 32); + TCGv_i64 xbh = cpu_vsrh(rB(ctx->opcode) + 32); + + if (unlikely(!ctx->vsx_enabled)) { + gen_exception(ctx, POWERPC_EXCP_VSXU); + return; + } + tcg_gen_shri_i64(xth, xbh, 48); + tcg_gen_andi_i64(xth, xth, 0x7FFF); + tcg_gen_movi_i64(xtl, 0); +} + +static void gen_xsiexpdp(DisasContext *ctx) +{ + TCGv_i64 xth = cpu_vsrh(xT(ctx->opcode)); + TCGv ra = cpu_gpr[rA(ctx->opcode)]; + TCGv rb = cpu_gpr[rB(ctx->opcode)]; + TCGv_i64 t0; + + if (unlikely(!ctx->vsx_enabled)) { + gen_exception(ctx, POWERPC_EXCP_VSXU); + return; + } + t0 = tcg_temp_new_i64(); + tcg_gen_andi_i64(xth, ra, 0x800FFFFFFFFFFFFF); + tcg_gen_andi_i64(t0, rb, 0x7FF); + tcg_gen_shli_i64(t0, t0, 52); + tcg_gen_or_i64(xth, xth, t0); + /* dword[1] is undefined */ + tcg_temp_free_i64(t0); +} + +static void gen_xsiexpqp(DisasContext *ctx) +{ + TCGv_i64 xth = cpu_vsrh(rD(ctx->opcode) + 32); + TCGv_i64 xtl = cpu_vsrl(rD(ctx->opcode) + 32); + TCGv_i64 xah = cpu_vsrh(rA(ctx->opcode) + 32); + TCGv_i64 xal = cpu_vsrl(rA(ctx->opcode) + 32); + TCGv_i64 xbh = cpu_vsrh(rB(ctx->opcode) + 32); + TCGv_i64 t0; + + if (unlikely(!ctx->vsx_enabled)) { + gen_exception(ctx, POWERPC_EXCP_VSXU); + return; + } + t0 = tcg_temp_new_i64(); + tcg_gen_andi_i64(xth, xah, 0x8000FFFFFFFFFFFF); + tcg_gen_andi_i64(t0, xbh, 0x7FFF); + tcg_gen_shli_i64(t0, t0, 48); + tcg_gen_or_i64(xth, xth, t0); + tcg_gen_mov_i64(xtl, xal); + tcg_temp_free_i64(t0); +} + +static void gen_xsxsigdp(DisasContext *ctx) +{ + TCGv rt = cpu_gpr[rD(ctx->opcode)]; + TCGv_i64 t0, zr, nan, exp; + + if (unlikely(!ctx->vsx_enabled)) { + gen_exception(ctx, POWERPC_EXCP_VSXU); + return; + } + exp = tcg_temp_new_i64(); + t0 = tcg_temp_new_i64(); + zr = tcg_const_i64(0); + nan = tcg_const_i64(2047); + + tcg_gen_shri_i64(exp, cpu_vsrh(xB(ctx->opcode)), 52); + tcg_gen_andi_i64(exp, exp, 0x7FF); + tcg_gen_movi_i64(t0, 0x0010000000000000); + tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, zr, zr, t0); + tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, nan, zr, t0); + tcg_gen_andi_i64(rt, cpu_vsrh(xB(ctx->opcode)), 0x000FFFFFFFFFFFFF); + tcg_gen_or_i64(rt, rt, t0); + + tcg_temp_free_i64(t0); + tcg_temp_free_i64(exp); + tcg_temp_free_i64(zr); + tcg_temp_free_i64(nan); +} + +static void gen_xsxsigqp(DisasContext *ctx) +{ + TCGv_i64 t0, zr, nan, exp; + TCGv_i64 xth = cpu_vsrh(rD(ctx->opcode) + 32); + TCGv_i64 xtl = cpu_vsrl(rD(ctx->opcode) + 32); + + if (unlikely(!ctx->vsx_enabled)) { + gen_exception(ctx, POWERPC_EXCP_VSXU); + return; + } + exp = tcg_temp_new_i64(); + t0 = tcg_temp_new_i64(); + zr = tcg_const_i64(0); + nan = tcg_const_i64(32767); + + tcg_gen_shri_i64(exp, cpu_vsrh(rB(ctx->opcode) + 32), 48); + tcg_gen_andi_i64(exp, exp, 0x7FFF); + tcg_gen_movi_i64(t0, 0x0001000000000000); + tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, zr, zr, t0); + tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, nan, zr, t0); + tcg_gen_andi_i64(xth, cpu_vsrh(rB(ctx->opcode) + 32), 0x0000FFFFFFFFFFFF); + tcg_gen_or_i64(xth, xth, t0); + tcg_gen_mov_i64(xtl, cpu_vsrl(rB(ctx->opcode) + 32)); + + tcg_temp_free_i64(t0); + tcg_temp_free_i64(exp); + tcg_temp_free_i64(zr); + tcg_temp_free_i64(nan); +} +#endif + +static void gen_xviexpsp(DisasContext *ctx) +{ + TCGv_i64 xth = cpu_vsrh(xT(ctx->opcode)); + TCGv_i64 xtl = cpu_vsrl(xT(ctx->opcode)); + TCGv_i64 xah = cpu_vsrh(xA(ctx->opcode)); + TCGv_i64 xal = cpu_vsrl(xA(ctx->opcode)); + TCGv_i64 xbh = cpu_vsrh(xB(ctx->opcode)); + TCGv_i64 xbl = cpu_vsrl(xB(ctx->opcode)); + TCGv_i64 t0; + + if (unlikely(!ctx->vsx_enabled)) { + gen_exception(ctx, POWERPC_EXCP_VSXU); + return; + } + t0 = tcg_temp_new_i64(); + tcg_gen_andi_i64(xth, xah, 0x807FFFFF807FFFFF); + tcg_gen_andi_i64(t0, xbh, 0xFF000000FF); + tcg_gen_shli_i64(t0, t0, 23); + tcg_gen_or_i64(xth, xth, t0); + tcg_gen_andi_i64(xtl, xal, 0x807FFFFF807FFFFF); + tcg_gen_andi_i64(t0, xbl, 0xFF000000FF); + tcg_gen_shli_i64(t0, t0, 23); + tcg_gen_or_i64(xtl, xtl, t0); + tcg_temp_free_i64(t0); +} + +static void gen_xviexpdp(DisasContext *ctx) +{ + TCGv_i64 xth = cpu_vsrh(xT(ctx->opcode)); + TCGv_i64 xtl = cpu_vsrl(xT(ctx->opcode)); + TCGv_i64 xah = cpu_vsrh(xA(ctx->opcode)); + TCGv_i64 xal = cpu_vsrl(xA(ctx->opcode)); + TCGv_i64 xbh = cpu_vsrh(xB(ctx->opcode)); + TCGv_i64 xbl = cpu_vsrl(xB(ctx->opcode)); + TCGv_i64 t0; + + if (unlikely(!ctx->vsx_enabled)) { + gen_exception(ctx, POWERPC_EXCP_VSXU); + return; + } + t0 = tcg_temp_new_i64(); + tcg_gen_andi_i64(xth, xah, 0x800FFFFFFFFFFFFF); + tcg_gen_andi_i64(t0, xbh, 0x7FF); + tcg_gen_shli_i64(t0, t0, 52); + tcg_gen_or_i64(xth, xth, t0); + tcg_gen_andi_i64(xtl, xal, 0x800FFFFFFFFFFFFF); + tcg_gen_andi_i64(t0, xbl, 0x7FF); + tcg_gen_shli_i64(t0, t0, 52); + tcg_gen_or_i64(xtl, xtl, t0); + tcg_temp_free_i64(t0); +} + +static void gen_xvxexpsp(DisasContext *ctx) +{ + TCGv_i64 xth = cpu_vsrh(xT(ctx->opcode)); + TCGv_i64 xtl = cpu_vsrl(xT(ctx->opcode)); + TCGv_i64 xbh = cpu_vsrh(xB(ctx->opcode)); + TCGv_i64 xbl = cpu_vsrl(xB(ctx->opcode)); + + if (unlikely(!ctx->vsx_enabled)) { + gen_exception(ctx, POWERPC_EXCP_VSXU); + return; + } + tcg_gen_shri_i64(xth, xbh, 23); + tcg_gen_andi_i64(xth, xth, 0xFF000000FF); + tcg_gen_shri_i64(xtl, xbl, 23); + tcg_gen_andi_i64(xtl, xtl, 0xFF000000FF); +} + +static void gen_xvxexpdp(DisasContext *ctx) +{ + TCGv_i64 xth = cpu_vsrh(xT(ctx->opcode)); + TCGv_i64 xtl = cpu_vsrl(xT(ctx->opcode)); + TCGv_i64 xbh = cpu_vsrh(xB(ctx->opcode)); + TCGv_i64 xbl = cpu_vsrl(xB(ctx->opcode)); + + if (unlikely(!ctx->vsx_enabled)) { + gen_exception(ctx, POWERPC_EXCP_VSXU); + return; + } + tcg_gen_shri_i64(xth, xbh, 52); + tcg_gen_andi_i64(xth, xth, 0x7FF); + tcg_gen_shri_i64(xtl, xbl, 52); + tcg_gen_andi_i64(xtl, xtl, 0x7FF); +} + +GEN_VSX_HELPER_2(xvxsigsp, 0x00, 0x04, 0, PPC2_ISA300) + +static void gen_xvxsigdp(DisasContext *ctx) +{ + TCGv_i64 xth = cpu_vsrh(xT(ctx->opcode)); + TCGv_i64 xtl = cpu_vsrl(xT(ctx->opcode)); + TCGv_i64 xbh = cpu_vsrh(xB(ctx->opcode)); + TCGv_i64 xbl = cpu_vsrl(xB(ctx->opcode)); + + TCGv_i64 t0, zr, nan, exp; + + if (unlikely(!ctx->vsx_enabled)) { + gen_exception(ctx, POWERPC_EXCP_VSXU); + return; + } + exp = tcg_temp_new_i64(); + t0 = tcg_temp_new_i64(); + zr = tcg_const_i64(0); + nan = tcg_const_i64(2047); + + tcg_gen_shri_i64(exp, xbh, 52); + tcg_gen_andi_i64(exp, exp, 0x7FF); + tcg_gen_movi_i64(t0, 0x0010000000000000); + tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, zr, zr, t0); + tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, nan, zr, t0); + tcg_gen_andi_i64(xth, xbh, 0x000FFFFFFFFFFFFF); + tcg_gen_or_i64(xth, xth, t0); + + tcg_gen_shri_i64(exp, xbl, 52); + tcg_gen_andi_i64(exp, exp, 0x7FF); + tcg_gen_movi_i64(t0, 0x0010000000000000); + tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, zr, zr, t0); + tcg_gen_movcond_i64(TCG_COND_EQ, t0, exp, nan, zr, t0); + tcg_gen_andi_i64(xtl, xbl, 0x000FFFFFFFFFFFFF); + tcg_gen_or_i64(xtl, xtl, t0); + + tcg_temp_free_i64(t0); + tcg_temp_free_i64(exp); + tcg_temp_free_i64(zr); + tcg_temp_free_i64(nan); +} + #undef GEN_XX2FORM #undef GEN_XX3FORM #undef GEN_XX2IFORM diff --git a/target/ppc/translate/vsx-ops.inc.c b/target/ppc/translate/vsx-ops.inc.c index 3d9104155a..7dc9f6f477 100644 --- a/target/ppc/translate/vsx-ops.inc.c +++ b/target/ppc/translate/vsx-ops.inc.c @@ -9,6 +9,11 @@ GEN_HANDLER_E(lxvdsx, 0x1F, 0x0C, 0x0A, 0, PPC_NONE, PPC2_VSX), GEN_HANDLER_E(lxvw4x, 0x1F, 0x0C, 0x18, 0, PPC_NONE, PPC2_VSX), GEN_HANDLER_E(lxvh8x, 0x1F, 0x0C, 0x19, 0, PPC_NONE, PPC2_ISA300), GEN_HANDLER_E(lxvb16x, 0x1F, 0x0C, 0x1B, 0, PPC_NONE, PPC2_ISA300), +GEN_HANDLER_E(lxvx, 0x1F, 0x0C, 0x08, 0x00000040, PPC_NONE, PPC2_ISA300), +#if defined(TARGET_PPC64) +GEN_HANDLER_E(lxvl, 0x1F, 0x0D, 0x08, 0, PPC_NONE, PPC2_ISA300), +GEN_HANDLER_E(lxvll, 0x1F, 0x0D, 0x09, 0, PPC_NONE, PPC2_ISA300), +#endif GEN_HANDLER_E(stxsdx, 0x1F, 0xC, 0x16, 0, PPC_NONE, PPC2_VSX), GEN_HANDLER_E(stxsibx, 0x1F, 0xD, 0x1C, 0, PPC_NONE, PPC2_ISA300), @@ -19,6 +24,11 @@ GEN_HANDLER_E(stxvd2x, 0x1F, 0xC, 0x1E, 0, PPC_NONE, PPC2_VSX), GEN_HANDLER_E(stxvw4x, 0x1F, 0xC, 0x1C, 0, PPC_NONE, PPC2_VSX), GEN_HANDLER_E(stxvh8x, 0x1F, 0x0C, 0x1D, 0, PPC_NONE, PPC2_ISA300), GEN_HANDLER_E(stxvb16x, 0x1F, 0x0C, 0x1F, 0, PPC_NONE, PPC2_ISA300), +GEN_HANDLER_E(stxvx, 0x1F, 0x0C, 0x0C, 0, PPC_NONE, PPC2_ISA300), +#if defined(TARGET_PPC64) +GEN_HANDLER_E(stxvl, 0x1F, 0x0D, 0x0C, 0, PPC_NONE, PPC2_ISA300), +GEN_HANDLER_E(stxvll, 0x1F, 0x0D, 0x0D, 0, PPC_NONE, PPC2_ISA300), +#endif GEN_HANDLER_E(mfvsrwz, 0x1F, 0x13, 0x03, 0x0000F800, PPC_NONE, PPC2_VSX207), GEN_HANDLER_E(mtvsrwa, 0x1F, 0x13, 0x06, 0x0000F800, PPC_NONE, PPC2_VSX207), @@ -39,6 +49,10 @@ GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 1, opc3, 0, PPC_NONE, fl2) GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0, opc3, 0, PPC_NONE, fl2), \ GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 1, opc3, 0, PPC_NONE, fl2) +#define GEN_XX2FORM_EXT(name, opc2, opc3, fl2) \ +GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 0, opc3, 0x00100000, PPC_NONE, fl2), \ +GEN_HANDLER2_E(name, #name, 0x3C, opc2 | 1, opc3, 0x00100000, PPC_NONE, fl2) + #define GEN_XX2FORM_EO(name, opc2, opc3, opc4, fl2) \ GEN_HANDLER2_E_2(name, #name, 0x3C, opc2 | 0, opc3, opc4, 0, PPC_NONE, fl2), \ GEN_HANDLER2_E_2(name, #name, 0x3C, opc2 | 1, opc3, opc4, 0, PPC_NONE, fl2) @@ -83,11 +97,54 @@ GEN_HANDLER2_E(name, #name, 0x3C, opc2|0x01, opc3|0x0C, 0, PPC_NONE, PPC2_VSX),\ GEN_HANDLER2_E(name, #name, 0x3C, opc2|0x02, opc3|0x0C, 0, PPC_NONE, PPC2_VSX),\ GEN_HANDLER2_E(name, #name, 0x3C, opc2|0x03, opc3|0x0C, 0, PPC_NONE, PPC2_VSX) +#define GEN_VSX_XFORM_300(name, opc2, opc3, inval) \ +GEN_HANDLER_E(name, 0x3F, opc2, opc3, inval, PPC_NONE, PPC2_ISA300) + +#define GEN_VSX_XFORM_300_EO(name, opc2, opc3, opc4, inval) \ +GEN_HANDLER_E_2(name, 0x3F, opc2, opc3, opc4, inval, PPC_NONE, PPC2_ISA300) + GEN_XX2FORM(xsabsdp, 0x12, 0x15, PPC2_VSX), GEN_XX2FORM(xsnabsdp, 0x12, 0x16, PPC2_VSX), GEN_XX2FORM(xsnegdp, 0x12, 0x17, PPC2_VSX), GEN_XX3FORM(xscpsgndp, 0x00, 0x16, PPC2_VSX), +GEN_VSX_XFORM_300_EO(xsabsqp, 0x04, 0x19, 0x00, 0x00000001), +GEN_VSX_XFORM_300_EO(xsnabsqp, 0x04, 0x19, 0x08, 0x00000001), +GEN_VSX_XFORM_300_EO(xsnegqp, 0x04, 0x19, 0x10, 0x00000001), +GEN_VSX_XFORM_300(xscpsgnqp, 0x04, 0x03, 0x00000001), +GEN_VSX_XFORM_300_EO(xscvdpqp, 0x04, 0x1A, 0x16, 0x00000001), +GEN_VSX_XFORM_300_EO(xscvqpdp, 0x04, 0x1A, 0x14, 0x0), +GEN_VSX_XFORM_300_EO(xscvqpsdz, 0x04, 0x1A, 0x19, 0x00000001), +GEN_VSX_XFORM_300_EO(xscvqpswz, 0x04, 0x1A, 0x09, 0x00000001), + +#ifdef TARGET_PPC64 +GEN_XX2FORM_EO(xsxexpdp, 0x16, 0x15, 0x00, PPC2_ISA300), +GEN_VSX_XFORM_300_EO(xsxexpqp, 0x04, 0x19, 0x02, 0x00000001), +GEN_XX2FORM_EO(xsxsigdp, 0x16, 0x15, 0x01, PPC2_ISA300), +GEN_VSX_XFORM_300_EO(xsxsigqp, 0x04, 0x19, 0x12, 0x00000001), +GEN_HANDLER_E(xsiexpdp, 0x3C, 0x16, 0x1C, 0, PPC_NONE, PPC2_ISA300), +GEN_VSX_XFORM_300(xsiexpqp, 0x4, 0x1B, 0x00000001), +#endif + +GEN_XX2FORM(xststdcdp, 0x14, 0x16, PPC2_ISA300), +GEN_XX2FORM(xststdcsp, 0x14, 0x12, PPC2_ISA300), +GEN_VSX_XFORM_300(xststdcqp, 0x04, 0x16, 0x00000001), + +GEN_XX3FORM(xviexpsp, 0x00, 0x1B, PPC2_ISA300), +GEN_XX3FORM(xviexpdp, 0x00, 0x1F, PPC2_ISA300), +GEN_XX2FORM_EO(xvxexpdp, 0x16, 0x1D, 0x00, PPC2_ISA300), +GEN_XX2FORM_EO(xvxsigdp, 0x16, 0x1D, 0x01, PPC2_ISA300), +GEN_XX2FORM_EO(xvxexpsp, 0x16, 0x1D, 0x08, PPC2_ISA300), +GEN_XX2FORM_EO(xvxsigsp, 0x16, 0x1D, 0x09, PPC2_ISA300), + +/* DCMX = bit[25] << 6 | bit[29] << 5 | bit[11:15] */ +#define GEN_XX2FORM_DCMX(name, opc2, opc3, fl2) \ +GEN_XX3FORM(name, opc2, opc3 | 0, fl2), \ +GEN_XX3FORM(name, opc2, opc3 | 1, fl2) + +GEN_XX2FORM_DCMX(xvtstdcdp, 0x14, 0x1E, PPC2_ISA300), +GEN_XX2FORM_DCMX(xvtstdcsp, 0x14, 0x1A, PPC2_ISA300), + GEN_XX2FORM(xvabsdp, 0x12, 0x1D, PPC2_VSX), GEN_XX2FORM(xvnabsdp, 0x12, 0x1E, PPC2_VSX), GEN_XX2FORM(xvnegdp, 0x12, 0x1F, PPC2_VSX), @@ -98,8 +155,10 @@ GEN_XX2FORM(xvnegsp, 0x12, 0x1B, PPC2_VSX), GEN_XX3FORM(xvcpsgnsp, 0x00, 0x1A, PPC2_VSX), GEN_XX3FORM(xsadddp, 0x00, 0x04, PPC2_VSX), +GEN_VSX_XFORM_300(xsaddqp, 0x04, 0x00, 0x0), GEN_XX3FORM(xssubdp, 0x00, 0x05, PPC2_VSX), GEN_XX3FORM(xsmuldp, 0x00, 0x06, PPC2_VSX), +GEN_VSX_XFORM_300(xsmulqp, 0x04, 0x01, 0x0), GEN_XX3FORM(xsdivdp, 0x00, 0x07, PPC2_VSX), GEN_XX2FORM(xsredp, 0x14, 0x05, PPC2_VSX), GEN_XX2FORM(xssqrtdp, 0x16, 0x04, PPC2_VSX), @@ -118,12 +177,19 @@ GEN_XX3FORM(xscmpeqdp, 0x0C, 0x00, PPC2_ISA300), GEN_XX3FORM(xscmpgtdp, 0x0C, 0x01, PPC2_ISA300), GEN_XX3FORM(xscmpgedp, 0x0C, 0x02, PPC2_ISA300), GEN_XX3FORM(xscmpnedp, 0x0C, 0x03, PPC2_ISA300), +GEN_XX3FORM(xscmpexpdp, 0x0C, 0x07, PPC2_ISA300), +GEN_VSX_XFORM_300(xscmpexpqp, 0x04, 0x05, 0x00600001), GEN_XX2IFORM(xscmpodp, 0x0C, 0x05, PPC2_VSX), GEN_XX2IFORM(xscmpudp, 0x0C, 0x04, PPC2_VSX), +GEN_VSX_XFORM_300(xscmpoqp, 0x04, 0x04, 0x00600001), +GEN_VSX_XFORM_300(xscmpuqp, 0x04, 0x14, 0x00600001), GEN_XX3FORM(xsmaxdp, 0x00, 0x14, PPC2_VSX), GEN_XX3FORM(xsmindp, 0x00, 0x15, PPC2_VSX), +GEN_XX2FORM_EO(xscvdphp, 0x16, 0x15, 0x11, PPC2_ISA300), GEN_XX2FORM(xscvdpsp, 0x12, 0x10, PPC2_VSX), GEN_XX2FORM(xscvdpspn, 0x16, 0x10, PPC2_VSX207), +GEN_XX2FORM_EO(xscvhpdp, 0x16, 0x15, 0x10, PPC2_ISA300), +GEN_VSX_XFORM_300_EO(xscvsdqp, 0x04, 0x1A, 0x0A, 0x00000001), GEN_XX2FORM(xscvspdp, 0x12, 0x14, PPC2_VSX), GEN_XX2FORM(xscvspdpn, 0x16, 0x14, PPC2_VSX207), GEN_XX2FORM(xscvdpsxds, 0x10, 0x15, PPC2_VSX), @@ -131,6 +197,7 @@ GEN_XX2FORM(xscvdpsxws, 0x10, 0x05, PPC2_VSX), GEN_XX2FORM(xscvdpuxds, 0x10, 0x14, PPC2_VSX), GEN_XX2FORM(xscvdpuxws, 0x10, 0x04, PPC2_VSX), GEN_XX2FORM(xscvsxddp, 0x10, 0x17, PPC2_VSX), +GEN_VSX_XFORM_300_EO(xscvudqp, 0x04, 0x1A, 0x02, 0x00000001), GEN_XX2FORM(xscvuxddp, 0x10, 0x16, PPC2_VSX), GEN_XX2FORM(xsrdpi, 0x12, 0x04, PPC2_VSX), GEN_XX2FORM(xsrdpic, 0x16, 0x06, PPC2_VSX), @@ -142,6 +209,7 @@ GEN_XX3FORM(xsaddsp, 0x00, 0x00, PPC2_VSX207), GEN_XX3FORM(xssubsp, 0x00, 0x01, PPC2_VSX207), GEN_XX3FORM(xsmulsp, 0x00, 0x02, PPC2_VSX207), GEN_XX3FORM(xsdivsp, 0x00, 0x03, PPC2_VSX207), +GEN_VSX_XFORM_300(xsdivqp, 0x04, 0x11, 0x0), GEN_XX2FORM(xsresp, 0x14, 0x01, PPC2_VSX207), GEN_XX2FORM(xsrsp, 0x12, 0x11, PPC2_VSX207), GEN_XX2FORM(xssqrtsp, 0x16, 0x00, PPC2_VSX207), @@ -235,6 +303,8 @@ GEN_XX2FORM(xvrspiz, 0x12, 0x09, PPC2_VSX), GEN_XX2FORM_EO(xxbrh, 0x16, 0x1D, 0x07, PPC2_ISA300), GEN_XX2FORM_EO(xxbrw, 0x16, 0x1D, 0x0F, PPC2_ISA300), GEN_XX2FORM_EO(xxbrd, 0x16, 0x1D, 0x17, PPC2_ISA300), +GEN_XX2FORM_EO(xvcvhpsp, 0x16, 0x1D, 0x18, PPC2_ISA300), +GEN_XX2FORM_EO(xvcvsphp, 0x16, 0x1D, 0x19, PPC2_ISA300), GEN_XX2FORM_EO(xxbrq, 0x16, 0x1D, 0x1F, PPC2_ISA300), #define VSX_LOGICAL(name, opc2, opc3, fl2) \ @@ -250,9 +320,13 @@ VSX_LOGICAL(xxlnand, 0x8, 0x16, PPC2_VSX207), VSX_LOGICAL(xxlorc, 0x8, 0x15, PPC2_VSX207), GEN_XX3FORM(xxmrghw, 0x08, 0x02, PPC2_VSX), GEN_XX3FORM(xxmrglw, 0x08, 0x06, PPC2_VSX), +GEN_XX3FORM(xxperm, 0x08, 0x03, PPC2_ISA300), +GEN_XX3FORM(xxpermr, 0x08, 0x07, PPC2_ISA300), GEN_XX2FORM(xxspltw, 0x08, 0x0A, PPC2_VSX), GEN_XX1FORM(xxspltib, 0x08, 0x0B, PPC2_ISA300), GEN_XX3FORM_DM(xxsldwi, 0x08, 0x00), +GEN_XX2FORM_EXT(xxextractuw, 0x0A, 0x0A, PPC2_ISA300), +GEN_XX2FORM_EXT(xxinsertw, 0x0A, 0x0B, PPC2_ISA300), #define GEN_XXSEL_ROW(opc3) \ GEN_HANDLER2_E(xxsel, "xxsel", 0x3C, 0x18, opc3, 0, PPC_NONE, PPC2_VSX), \ diff --git a/target/ppc/translate_init.c b/target/ppc/translate_init.c index 94dfcd7afc..76f79fa77b 100644 --- a/target/ppc/translate_init.c +++ b/target/ppc/translate_init.c @@ -5217,28 +5217,6 @@ POWERPC_FAMILY(e5500)(ObjectClass *oc, void *data) /* Non-embedded PowerPC */ -/* POWER : same as 601, without mfmsr, mfsr */ -POWERPC_FAMILY(POWER)(ObjectClass *oc, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(oc); - PowerPCCPUClass *pcc = POWERPC_CPU_CLASS(oc); - - dc->desc = "POWER"; - /* pcc->insns_flags = XXX_TODO; */ - /* POWER RSC (from RAD6000) */ - pcc->msr_mask = (1ull << MSR_EE) | - (1ull << MSR_PR) | - (1ull << MSR_FP) | - (1ull << MSR_ME) | - (1ull << MSR_FE0) | - (1ull << MSR_SE) | - (1ull << MSR_DE) | - (1ull << MSR_AL) | - (1ull << MSR_EP) | - (1ull << MSR_IR) | - (1ull << MSR_DR); -} - #define POWERPC_MSRR_601 (0x0000000000001040ULL) static void init_proc_601 (CPUPPCState *env) @@ -8797,6 +8775,8 @@ POWERPC_FAMILY(POWER9)(ObjectClass *oc, void *data) dc->props = powerpc_servercpu_properties; pcc->pvr_match = ppc_pvr_match_power9; pcc->pcr_mask = PCR_COMPAT_2_05 | PCR_COMPAT_2_06 | PCR_COMPAT_2_07; + pcc->pcr_supported = PCR_COMPAT_3_00 | PCR_COMPAT_2_07 | PCR_COMPAT_2_06 | + PCR_COMPAT_2_05; pcc->init_proc = init_proc_POWER9; pcc->check_pow = check_pow_nocheck; pcc->insns_flags = PPC_INSNS_BASE | PPC_ISEL | PPC_STRING | PPC_MFTB | @@ -8857,6 +8837,11 @@ POWERPC_FAMILY(POWER9)(ObjectClass *oc, void *data) #if !defined(CONFIG_USER_ONLY) +void cpu_ppc_set_vhyp(PowerPCCPU *cpu, PPCVirtualHypervisor *vhyp) +{ + cpu->vhyp = vhyp; +} + void cpu_ppc_set_papr(PowerPCCPU *cpu) { CPUPPCState *env = &cpu->env; @@ -9947,67 +9932,6 @@ static void ppc_cpu_unrealizefn(DeviceState *dev, Error **errp) } } -int ppc_get_compat_smt_threads(PowerPCCPU *cpu) -{ - CPUState *cs = CPU(cpu); - int ret = MIN(cs->nr_threads, kvmppc_smt_threads()); - - switch (cpu->cpu_version) { - case CPU_POWERPC_LOGICAL_2_05: - ret = MIN(ret, 2); - break; - case CPU_POWERPC_LOGICAL_2_06: - ret = MIN(ret, 4); - break; - case CPU_POWERPC_LOGICAL_2_07: - ret = MIN(ret, 8); - break; - } - - return ret; -} - -#ifdef TARGET_PPC64 -void ppc_set_compat(PowerPCCPU *cpu, uint32_t cpu_version, Error **errp) -{ - int ret = 0; - CPUPPCState *env = &cpu->env; - PowerPCCPUClass *host_pcc; - - cpu->cpu_version = cpu_version; - - switch (cpu_version) { - case CPU_POWERPC_LOGICAL_2_05: - env->spr[SPR_PCR] = PCR_TM_DIS | PCR_VSX_DIS | PCR_COMPAT_2_07 | - PCR_COMPAT_2_06 | PCR_COMPAT_2_05; - break; - case CPU_POWERPC_LOGICAL_2_06: - case CPU_POWERPC_LOGICAL_2_06_PLUS: - env->spr[SPR_PCR] = PCR_TM_DIS | PCR_COMPAT_2_07 | PCR_COMPAT_2_06; - break; - case CPU_POWERPC_LOGICAL_2_07: - env->spr[SPR_PCR] = PCR_COMPAT_2_07; - break; - default: - env->spr[SPR_PCR] = 0; - break; - } - - host_pcc = kvm_ppc_get_host_cpu_class(); - if (host_pcc) { - env->spr[SPR_PCR] &= host_pcc->pcr_mask; - } - - if (kvm_enabled()) { - ret = kvmppc_set_compat(cpu, cpu->cpu_version); - if (ret < 0) { - error_setg_errno(errp, -ret, - "Unable to set CPU compatibility mode in KVM"); - } - } -} -#endif - static gint ppc_cpu_compare_class_pvr(gconstpointer a, gconstpointer b) { ObjectClass *oc = (ObjectClass *)a; @@ -10591,9 +10515,16 @@ static const TypeInfo ppc_cpu_type_info = { .class_init = ppc_cpu_class_init, }; +static const TypeInfo ppc_vhyp_type_info = { + .name = TYPE_PPC_VIRTUAL_HYPERVISOR, + .parent = TYPE_INTERFACE, + .class_size = sizeof(PPCVirtualHypervisorClass), +}; + static void ppc_cpu_register_types(void) { type_register_static(&ppc_cpu_type_info); + type_register_static(&ppc_vhyp_type_info); } type_init(ppc_cpu_register_types) |