The following changes since commit 0d3e41d5efd638a0c5682f6813b26448c3c51624: Merge remote-tracking branch 'remotes/vivier2/tags/trivial-branch-pull-request' into staging (2019-02-14 17:42:25 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20190214 for you to fetch changes up to 497bc12b1b374ecd62903bf062229bd93f8924af: gdbstub: Send a reply to the vKill packet. (2019-02-14 18:45:49 +0000) ---------------------------------------------------------------- target-arm queue: * gdbstub: Send a reply to the vKill packet * Improve codegen for neon min/max and saturating arithmetic * Fix a bug in clearing FPSCR exception status bits * hw/arm/armsse: Fix miswiring of expansion IRQs * hw/intc/armv7m_nvic: Allow byte accesses to SHPR1 * MAINTAINERS: Remove Peter Crosthwaite from various entries * arm: Allow system registers for KVM guests to be changed by QEMU code * linux-user: support HWCAP_CPUID which exposes ID registers to user code * Fix bug in 128-bit cmpxchg for BE Arm guests * Implement (no-op) HACR_EL2 * Fix CRn to be 14 for PMEVTYPER/PMEVCNTR ---------------------------------------------------------------- Aaron Lindsay OS (1): target/arm: Fix CRn to be 14 for PMEVTYPER/PMEVCNTR Alex Bennée (5): target/arm: relax permission checks for HWCAP_CPUID registers target/arm: expose CPUID registers to userspace target/arm: expose MPIDR_EL1 to userspace target/arm: expose remaining CPUID registers as RAZ linux-user/elfload: enable HWCAP_CPUID for AArch64 Catherine Ho (1): target/arm: Fix int128_make128 lo, hi order in paired_cmpxchg64_be Peter Maydell (5): target/arm: Implement HACR_EL2 arm: Allow system registers for KVM guests to be changed by QEMU code MAINTAINERS: Remove Peter Crosthwaite from various entries hw/intc/armv7m_nvic: Allow byte accesses to SHPR1 hw/arm/armsse: Fix miswiring of expansion IRQs Richard Henderson (14): target/arm: Force result size into dp after operation target/arm: Restructure disas_fp_int_conv target/arm: Rely on optimization within tcg_gen_gvec_or target/arm: Use vector minmax expanders for aarch64 target/arm: Use vector minmax expanders for aarch32 target/arm: Use tcg integer min/max primitives for neon target/arm: Remove neon min/max helpers target/arm: Fix vfp_gdb_get/set_reg vs FPSCR target/arm: Fix arm_cpu_dump_state vs FPSCR target/arm: Split out flags setting from vfp compares target/arm: Fix set of bits kept in xregs[ARM_VFP_FPSCR] target/arm: Split out FPSCR.QC to a vector field target/arm: Use vector operations for saturation target/arm: Add missing clear_tail calls Sandra Loosemore (1): gdbstub: Send a reply to the vKill packet. target/arm/cpu.h | 50 ++++++++- target/arm/helper.h | 45 +++++--- target/arm/translate.h | 4 + gdbstub.c | 1 + hw/arm/armsse.c | 2 +- hw/intc/armv7m_nvic.c | 4 +- linux-user/elfload.c | 1 + target/arm/helper-a64.c | 4 +- target/arm/helper.c | 228 ++++++++++++++++++++++++++++++++-------- target/arm/kvm32.c | 20 +--- target/arm/kvm64.c | 2 + target/arm/machine.c | 2 +- target/arm/neon_helper.c | 14 +-- target/arm/translate-a64.c | 171 +++++++++++++++--------------- target/arm/translate-sve.c | 6 +- target/arm/translate.c | 251 ++++++++++++++++++++++++++++++++++----------- target/arm/vec_helper.c | 134 +++++++++++++++++++++++- MAINTAINERS | 4 - 18 files changed, 687 insertions(+), 256 deletions(-) From: Aaron Lindsay OS <aaron@os.amperecomputing.com> This bug was introduced in: commit 5ecdd3e47cadae83a62dc92b472f1fe163b56f59 target/arm: Finish implementation of PM[X]EVCNTR and PM[X]EVTYPER Signed-off-by: Aaron Lindsay <aaron@os.amperecomputing.com> Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Reviewed-by: Laurent Desnogues <laurent.desnogues@gmail.com> Message-id: 20190205135129.19338-1-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) char *pmevtyper_name = g_strdup_printf("PMEVTYPER%d", i); char *pmevtyper_el0_name = g_strdup_printf("PMEVTYPER%d_EL0", i); ARMCPRegInfo pmev_regs[] = { - { .name = pmevcntr_name, .cp = 15, .crn = 15, + { .name = pmevcntr_name, .cp = 15, .crn = 14, .crm = 8 | (3 & (i >> 3)), .opc1 = 0, .opc2 = i & 7, .access = PL0_RW, .type = ARM_CP_IO | ARM_CP_ALIAS, .readfn = pmevcntr_readfn, .writefn = pmevcntr_writefn, .accessfn = pmreg_access }, { .name = pmevcntr_el0_name, .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 3, .crn = 15, .crm = 8 | (3 & (i >> 3)), + .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 8 | (3 & (i >> 3)), .opc2 = i & 7, .access = PL0_RW, .accessfn = pmreg_access, .type = ARM_CP_IO, .readfn = pmevcntr_readfn, .writefn = pmevcntr_writefn, .raw_readfn = pmevcntr_rawread, .raw_writefn = pmevcntr_rawwrite }, - { .name = pmevtyper_name, .cp = 15, .crn = 15, + { .name = pmevtyper_name, .cp = 15, .crn = 14, .crm = 12 | (3 & (i >> 3)), .opc1 = 0, .opc2 = i & 7, .access = PL0_RW, .type = ARM_CP_IO | ARM_CP_ALIAS, .readfn = pmevtyper_readfn, .writefn = pmevtyper_writefn, .accessfn = pmreg_access }, { .name = pmevtyper_el0_name, .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 3, .crn = 15, .crm = 12 | (3 & (i >> 3)), + .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 12 | (3 & (i >> 3)), .opc2 = i & 7, .access = PL0_RW, .accessfn = pmreg_access, .type = ARM_CP_IO, .readfn = pmevtyper_readfn, .writefn = pmevtyper_writefn, -- 2.20.1 HACR_EL2 is a register with IMPDEF behaviour, which allows implementation specific trapping to EL2. Implement it as RAZ/WI, since QEMU's implementation has no extra traps. This also matches what h/w implementations like Cortex-A53 and A57 do. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190205181218.8995-1-peter.maydell@linaro.org --- target/arm/helper.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo el3_no_el2_cp_reginfo[] = { .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 0, .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "HACR_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 7, + .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, { .name = "ESR_EL2", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 4, .crn = 5, .crm = 2, .opc2 = 0, .access = PL2_RW, @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo el2_cp_reginfo[] = { .cp = 15, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 0, .access = PL2_RW, .fieldoffset = offsetof(CPUARMState, cp15.hcr_el2), .writefn = hcr_writelow }, + { .name = "HACR_EL2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 7, + .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, { .name = "ELR_EL2", .state = ARM_CP_STATE_AA64, .type = ARM_CP_ALIAS, .opc0 = 3, .opc1 = 4, .crn = 4, .crm = 0, .opc2 = 1, -- 2.20.1 From: Catherine Ho <catherine.hecx@gmail.com> The lo,hi order is different from the comments. And in commit 1ec182c33379 ("target/arm: Convert to HAVE_CMPXCHG128"), it changes the original code logic. So just restore the old code logic before this commit: do_paired_cmpxchg64_be(): cmpv = int128_make128(env->exclusive_high, env->exclusive_val); newv = int128_make128(new_hi, new_lo); This fixes a bug that would only be visible for big-endian AArch64 guest code. Fixes: 1ec182c33379 ("target/arm: Convert to HAVE_CMPXCHG128") Signed-off-by: Catherine Ho <catherine.hecx@gmail.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 1548985244-24523-1-git-send-email-catherine.hecx@gmail.com [PMM: added note that bug only affects BE guests] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(paired_cmpxchg64_be)(CPUARMState *env, uint64_t addr, * High and low need to be switched here because this is not actually a * 128bit store but two doublewords stored consecutively */ - Int128 cmpv = int128_make128(env->exclusive_val, env->exclusive_high); - Int128 newv = int128_make128(new_lo, new_hi); + Int128 cmpv = int128_make128(env->exclusive_high, env->exclusive_val); + Int128 newv = int128_make128(new_hi, new_lo); Int128 oldv; uintptr_t ra = GETPC(); uint64_t o0, o1; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Rather than a complex set of cases testing for writeback, adjust DP after performing the operation. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190206052857.5077-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) tcg_gen_or_i32(tmp, tmp, tmp2); tcg_temp_free_i32(tmp2); gen_vfp_msr(tmp); + dp = 0; /* always a single precision result */ break; } case 7: /* vcvtt.f16.f32, vcvtt.f16.f64 */ @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) tcg_gen_or_i32(tmp, tmp, tmp2); tcg_temp_free_i32(tmp2); gen_vfp_msr(tmp); + dp = 0; /* always a single precision result */ break; } case 8: /* cmp */ gen_vfp_cmp(dp); + dp = -1; /* no write back */ break; case 9: /* cmpe */ gen_vfp_cmpe(dp); + dp = -1; /* no write back */ break; case 10: /* cmpz */ gen_vfp_cmp(dp); + dp = -1; /* no write back */ break; case 11: /* cmpez */ gen_vfp_F1_ld0(dp); gen_vfp_cmpe(dp); + dp = -1; /* no write back */ break; case 12: /* vrintr */ { @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) break; } case 15: /* single<->double conversion */ - if (dp) + if (dp) { gen_helper_vfp_fcvtsd(cpu_F0s, cpu_F0d, cpu_env); - else + } else { gen_helper_vfp_fcvtds(cpu_F0d, cpu_F0s, cpu_env); + } + dp = !dp; /* result size is opposite */ break; case 16: /* fuito */ gen_vfp_uito(dp, 0); @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) break; case 24: /* ftoui */ gen_vfp_toui(dp, 0); + dp = 0; /* always an integer result */ break; case 25: /* ftouiz */ gen_vfp_touiz(dp, 0); + dp = 0; /* always an integer result */ break; case 26: /* ftosi */ gen_vfp_tosi(dp, 0); + dp = 0; /* always an integer result */ break; case 27: /* ftosiz */ gen_vfp_tosiz(dp, 0); + dp = 0; /* always an integer result */ break; case 28: /* ftosh */ if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) return 1; } - /* Write back the result. */ - if (op == 15 && (rn >= 8 && rn <= 11)) { - /* Comparison, do nothing. */ - } else if (op == 15 && dp && ((rn & 0x1c) == 0x18 || - (rn & 0x1e) == 0x6)) { - /* VCVT double to int: always integer result. - * VCVT double to half precision is always a single - * precision result. - */ - gen_mov_vreg_F0(0, rd); - } else if (op == 15 && rn == 15) { - /* conversion */ - gen_mov_vreg_F0(!dp, rd); - } else { + /* Write back the result, if any. */ + if (dp >= 0) { gen_mov_vreg_F0(dp, rd); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> For opcodes 0-5, move some if conditions into the structure of a switch statement. For opcodes 6 & 7, decode everything at once with a second switch. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190206052857.5077-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 94 ++++++++++++++++++++------------------ 1 file changed, 49 insertions(+), 45 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) int type = extract32(insn, 22, 2); bool sbit = extract32(insn, 29, 1); bool sf = extract32(insn, 31, 1); + bool itof = false; if (sbit) { - unallocated_encoding(s); - return; + goto do_unallocated; } - if (opcode > 5) { - /* FMOV */ - bool itof = opcode & 1; - - if (rmode >= 2) { - unallocated_encoding(s); - return; - } - - switch (sf << 3 | type << 1 | rmode) { - case 0x0: /* 32 bit */ - case 0xa: /* 64 bit */ - case 0xd: /* 64 bit to top half of quad */ - break; - case 0x6: /* 16-bit float, 32-bit int */ - case 0xe: /* 16-bit float, 64-bit int */ - if (dc_isar_feature(aa64_fp16, s)) { - break; - } - /* fallthru */ - default: - /* all other sf/type/rmode combinations are invalid */ - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - handle_fmov(s, rd, rn, type, itof); - } else { - /* actual FP conversions */ - bool itof = extract32(opcode, 1, 1); - - if (rmode != 0 && opcode > 1) { - unallocated_encoding(s); - return; + switch (opcode) { + case 2: /* SCVTF */ + case 3: /* UCVTF */ + itof = true; + /* fallthru */ + case 4: /* FCVTAS */ + case 5: /* FCVTAU */ + if (rmode != 0) { + goto do_unallocated; } + /* fallthru */ + case 0: /* FCVT[NPMZ]S */ + case 1: /* FCVT[NPMZ]U */ switch (type) { case 0: /* float32 */ case 1: /* float64 */ break; case 3: /* float16 */ - if (dc_isar_feature(aa64_fp16, s)) { - break; + if (!dc_isar_feature(aa64_fp16, s)) { + goto do_unallocated; } - /* fallthru */ + break; default: - unallocated_encoding(s); - return; + goto do_unallocated; } - if (!fp_access_check(s)) { return; } handle_fpfpcvt(s, rd, rn, opcode, itof, rmode, 64, sf, type); + break; + + default: + switch (sf << 7 | type << 5 | rmode << 3 | opcode) { + case 0b01100110: /* FMOV half <-> 32-bit int */ + case 0b01100111: + case 0b11100110: /* FMOV half <-> 64-bit int */ + case 0b11100111: + if (!dc_isar_feature(aa64_fp16, s)) { + goto do_unallocated; + } + /* fallthru */ + case 0b00000110: /* FMOV 32-bit */ + case 0b00000111: + case 0b10100110: /* FMOV 64-bit */ + case 0b10100111: + case 0b11001110: /* FMOV top half of 128-bit */ + case 0b11001111: + if (!fp_access_check(s)) { + return; + } + itof = opcode & 1; + handle_fmov(s, rd, rn, type, itof); + break; + + default: + do_unallocated: + unallocated_encoding(s); + return; + } + break; } } -- 2.20.1 From: Alex Bennée <alex.bennee@linaro.org> Although technically not visible to userspace the kernel does make them visible via a trap and emulate ABI. We provide a new permission mask (PL0U_R) which maps to PL0_R for CONFIG_USER builds and adjust the minimum permission check accordingly. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20190205190224.2198-2-alex.bennee@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 12 ++++++++++++ target/arm/helper.c | 6 +++++- 2 files changed, 17 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool cptype_valid(int cptype) #define PL0_R (0x02 | PL1_R) #define PL0_W (0x01 | PL1_W) +/* + * For user-mode some registers are accessible to EL0 via a kernel + * trap-and-emulate ABI. In this case we define the read permissions + * as actually being PL0_R. However some bits of any given register + * may still be masked. + */ +#ifdef CONFIG_USER_ONLY +#define PL0U_R PL0_R +#else +#define PL0U_R PL1_R +#endif + #define PL3_RW (PL3_R | PL3_W) #define PL2_RW (PL2_R | PL2_W) #define PL1_RW (PL1_R | PL1_W) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void define_one_arm_cp_reg_with_opaque(ARMCPU *cpu, if (r->state != ARM_CP_STATE_AA32) { int mask = 0; switch (r->opc1) { - case 0: case 1: case 2: + case 0: + /* min_EL EL1, but some accessible to EL0 via kernel ABI */ + mask = PL0U_R | PL1_RW; + break; + case 1: case 2: /* min_EL EL1 */ mask = PL1_RW; break; -- 2.20.1 From: Alex Bennée <alex.bennee@linaro.org> A number of CPUID registers are exposed to userspace by modern Linux kernels thanks to the "ARM64 CPU Feature Registers" ABI. For QEMU's user-mode emulation we don't need to emulate the kernels trap but just return the value the trap would have done. To avoid too much #ifdef hackery we process ARMCPRegInfo with a new helper (modify_arm_cp_regs) before defining the registers. The modify routine is driven by a simple data structure which describes which bits are exported and which are fixed. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20190205190224.2198-3-alex.bennee@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 21 ++++++++++++++++ target/arm/helper.c | 59 +++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 80 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline void define_one_arm_cp_reg(ARMCPU *cpu, const ARMCPRegInfo *regs) } const ARMCPRegInfo *get_arm_cp_reginfo(GHashTable *cpregs, uint32_t encoded_cp); +/* + * Definition of an ARM co-processor register as viewed from + * userspace. This is used for presenting sanitised versions of + * registers to userspace when emulating the Linux AArch64 CPU + * ID/feature ABI (advertised as HWCAP_CPUID). + */ +typedef struct ARMCPRegUserSpaceInfo { + /* Name of register */ + const char *name; + + /* Only some bits are exported to user space */ + uint64_t exported_bits; + + /* Fixed bits are applied after the mask */ + uint64_t fixed_bits; +} ARMCPRegUserSpaceInfo; + +#define REGUSERINFO_SENTINEL { .name = NULL } + +void modify_arm_cp_regs(ARMCPRegInfo *regs, const ARMCPRegUserSpaceInfo *mods); + /* CPWriteFn that can be used to implement writes-ignored behaviour */ void arm_cp_write_ignore(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value); diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) .resetvalue = cpu->pmceid1 }, REGINFO_SENTINEL }; +#ifdef CONFIG_USER_ONLY + ARMCPRegUserSpaceInfo v8_user_idregs[] = { + { .name = "ID_AA64PFR0_EL1", + .exported_bits = 0x000f000f00ff0000, + .fixed_bits = 0x0000000000000011 }, + { .name = "ID_AA64PFR1_EL1", + .exported_bits = 0x00000000000000f0 }, + { .name = "ID_AA64ZFR0_EL1" }, + { .name = "ID_AA64MMFR0_EL1", + .fixed_bits = 0x00000000ff000000 }, + { .name = "ID_AA64MMFR1_EL1" }, + { .name = "ID_AA64DFR0_EL1", + .fixed_bits = 0x0000000000000006 }, + { .name = "ID_AA64DFR1_EL1" }, + { .name = "ID_AA64AFR0_EL1" }, + { .name = "ID_AA64AFR1_EL1" }, + { .name = "ID_AA64ISAR0_EL1", + .exported_bits = 0x00fffffff0fffff0 }, + { .name = "ID_AA64ISAR1_EL1", + .exported_bits = 0x000000f0ffffffff }, + REGUSERINFO_SENTINEL + }; + modify_arm_cp_regs(v8_idregs, v8_user_idregs); +#endif /* RVBAR_EL1 is only implemented if EL1 is the highest EL */ if (!arm_feature(env, ARM_FEATURE_EL3) && !arm_feature(env, ARM_FEATURE_EL2)) { @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) .opc1 = CP_ANY, .opc2 = CP_ANY, .access = PL1_W, .type = ARM_CP_NOP | ARM_CP_OVERRIDE }; +#ifdef CONFIG_USER_ONLY + ARMCPRegUserSpaceInfo id_v8_user_midr_cp_reginfo[] = { + { .name = "MIDR_EL1", + .exported_bits = 0x00000000ffffffff }, + { .name = "REVIDR_EL1" }, + REGUSERINFO_SENTINEL + }; + modify_arm_cp_regs(id_v8_midr_cp_reginfo, id_v8_user_midr_cp_reginfo); +#endif if (arm_feature(env, ARM_FEATURE_OMAPCP) || arm_feature(env, ARM_FEATURE_STRONGARM)) { ARMCPRegInfo *r; @@ -XXX,XX +XXX,XX @@ void define_arm_cp_regs_with_opaque(ARMCPU *cpu, } } +/* + * Modify ARMCPRegInfo for access from userspace. + * + * This is a data driven modification directed by + * ARMCPRegUserSpaceInfo. All registers become ARM_CP_CONST as + * user-space cannot alter any values and dynamic values pertaining to + * execution state are hidden from user space view anyway. + */ +void modify_arm_cp_regs(ARMCPRegInfo *regs, const ARMCPRegUserSpaceInfo *mods) +{ + const ARMCPRegUserSpaceInfo *m; + ARMCPRegInfo *r; + + for (m = mods; m->name; m++) { + for (r = regs; r->type != ARM_CP_SENTINEL; r++) { + if (strcmp(r->name, m->name) == 0) { + r->type = ARM_CP_CONST; + r->access = PL0U_R; + r->resetvalue &= m->exported_bits; + r->resetvalue |= m->fixed_bits; + break; + } + } + } +} + const ARMCPRegInfo *get_arm_cp_reginfo(GHashTable *cpregs, uint32_t encoded_cp) { return g_hash_table_lookup(cpregs, &encoded_cp); -- 2.20.1 From: Alex Bennée <alex.bennee@linaro.org> As this is a single register we could expose it with a simple ifdef but we use the existing modify_arm_cp_regs mechanism for consistency. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20190205190224.2198-4-alex.bennee@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 21 ++++++++++++++------- 1 file changed, 14 insertions(+), 7 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t mpidr_read(CPUARMState *env, const ARMCPRegInfo *ri) return mpidr_read_val(env); } -static const ARMCPRegInfo mpidr_cp_reginfo[] = { - { .name = "MPIDR", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .crn = 0, .crm = 0, .opc1 = 0, .opc2 = 5, - .access = PL1_R, .readfn = mpidr_read, .type = ARM_CP_NO_RAW }, - REGINFO_SENTINEL -}; - static const ARMCPRegInfo lpae_cp_reginfo[] = { /* NOP AMAIR0/1 */ { .name = "AMAIR0", .state = ARM_CP_STATE_BOTH, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) } if (arm_feature(env, ARM_FEATURE_MPIDR)) { + ARMCPRegInfo mpidr_cp_reginfo[] = { + { .name = "MPIDR_EL1", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .crn = 0, .crm = 0, .opc1 = 0, .opc2 = 5, + .access = PL1_R, .readfn = mpidr_read, .type = ARM_CP_NO_RAW }, + REGINFO_SENTINEL + }; +#ifdef CONFIG_USER_ONLY + ARMCPRegUserSpaceInfo mpidr_user_cp_reginfo[] = { + { .name = "MPIDR_EL1", + .fixed_bits = 0x0000000080000000 }, + REGUSERINFO_SENTINEL + }; + modify_arm_cp_regs(mpidr_cp_reginfo, mpidr_user_cp_reginfo); +#endif define_arm_cp_regs(cpu, mpidr_cp_reginfo); } -- 2.20.1 From: Alex Bennée <alex.bennee@linaro.org> There are a whole bunch more registers in the CPUID space which are currently not used but are exposed as RAZ. To avoid too much duplication we expand ARMCPRegUserSpaceInfo to understand glob patterns so we only need one entry to tweak whole ranges of registers. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20190205190224.2198-5-alex.bennee@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 3 +++ target/arm/helper.c | 26 +++++++++++++++++++++++--- 2 files changed, 26 insertions(+), 3 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct ARMCPRegUserSpaceInfo { /* Name of register */ const char *name; + /* Is the name actually a glob pattern */ + bool is_glob; + /* Only some bits are exported to user space */ uint64_t exported_bits; diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) .fixed_bits = 0x0000000000000011 }, { .name = "ID_AA64PFR1_EL1", .exported_bits = 0x00000000000000f0 }, + { .name = "ID_AA64PFR*_EL1_RESERVED", + .is_glob = true }, { .name = "ID_AA64ZFR0_EL1" }, { .name = "ID_AA64MMFR0_EL1", .fixed_bits = 0x00000000ff000000 }, { .name = "ID_AA64MMFR1_EL1" }, + { .name = "ID_AA64MMFR*_EL1_RESERVED", + .is_glob = true }, { .name = "ID_AA64DFR0_EL1", .fixed_bits = 0x0000000000000006 }, { .name = "ID_AA64DFR1_EL1" }, - { .name = "ID_AA64AFR0_EL1" }, - { .name = "ID_AA64AFR1_EL1" }, + { .name = "ID_AA64DFR*_EL1_RESERVED", + .is_glob = true }, + { .name = "ID_AA64AFR*", + .is_glob = true }, { .name = "ID_AA64ISAR0_EL1", .exported_bits = 0x00fffffff0fffff0 }, { .name = "ID_AA64ISAR1_EL1", .exported_bits = 0x000000f0ffffffff }, + { .name = "ID_AA64ISAR*_EL1_RESERVED", + .is_glob = true }, REGUSERINFO_SENTINEL }; modify_arm_cp_regs(v8_idregs, v8_user_idregs); @@ -XXX,XX +XXX,XX @@ void modify_arm_cp_regs(ARMCPRegInfo *regs, const ARMCPRegUserSpaceInfo *mods) ARMCPRegInfo *r; for (m = mods; m->name; m++) { + GPatternSpec *pat = NULL; + if (m->is_glob) { + pat = g_pattern_spec_new(m->name); + } for (r = regs; r->type != ARM_CP_SENTINEL; r++) { - if (strcmp(r->name, m->name) == 0) { + if (pat && g_pattern_match_string(pat, r->name)) { + r->type = ARM_CP_CONST; + r->access = PL0U_R; + r->resetvalue = 0; + /* continue */ + } else if (strcmp(r->name, m->name) == 0) { r->type = ARM_CP_CONST; r->access = PL0U_R; r->resetvalue &= m->exported_bits; @@ -XXX,XX +XXX,XX @@ void modify_arm_cp_regs(ARMCPRegInfo *regs, const ARMCPRegUserSpaceInfo *mods) break; } } + if (pat) { + g_pattern_spec_free(pat); + } } } -- 2.20.1 From: Alex Bennée <alex.bennee@linaro.org> Userspace programs should (in theory) query the ELF HWCAP before probing these registers. Now we have implemented them all make it public. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190205190224.2198-6-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/elfload.c | 1 + 1 file changed, 1 insertion(+) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) hwcaps |= ARM_HWCAP_A64_FP; hwcaps |= ARM_HWCAP_A64_ASIMD; + hwcaps |= ARM_HWCAP_A64_CPUID; /* probe for the extra features */ #define GET_FEATURE_ID(feat, hwcap) \ -- 2.20.1 At the moment the Arm implementations of kvm_arch_{get,put}_registers() don't support having QEMU change the values of system registers (aka coprocessor registers for AArch32). This is because although kvm_arch_get_registers() calls write_list_to_cpustate() to update the CPU state struct fields (so QEMU code can read the values in the usual way), kvm_arch_put_registers() does not call write_cpustate_to_list(), meaning that any changes to the CPU state struct fields will not be passed back to KVM. The rationale for this design is documented in a comment in the AArch32 kvm_arch_put_registers() -- writing the values in the cpregs list into the CPU state struct is "lossy" because the write of a register might not succeed, and so if we blindly copy the CPU state values back again we will incorrectly change register values for the guest. The assumption was that no QEMU code would need to write to the registers. However, when we implemented debug support for KVM guests, we broke that assumption: the code to handle "set the guest up to take a breakpoint exception" does so by updating various guest registers including ESR_EL1. Support this by making kvm_arch_put_registers() synchronize CPU state back into the list. We sync only those registers where the initial write succeeds, which should be sufficient. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Dongjiu Geng <gengdongjiu@huawei.com> --- target/arm/cpu.h | 9 ++++++++- target/arm/helper.c | 27 +++++++++++++++++++++++++-- target/arm/kvm32.c | 20 ++------------------ target/arm/kvm64.c | 2 ++ target/arm/machine.c | 2 +- 5 files changed, 38 insertions(+), 22 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ bool write_list_to_cpustate(ARMCPU *cpu); /** * write_cpustate_to_list: * @cpu: ARMCPU + * @kvm_sync: true if this is for syncing back to KVM * * For each register listed in the ARMCPU cpreg_indexes list, write * its value from the ARMCPUState structure into the cpreg_values list. * This is used to copy info from TCG's working data structures into * KVM or for outbound migration. * + * @kvm_sync is true if we are doing this in order to sync the + * register state back to KVM. In this case we will only update + * values in the list if the previous list->cpustate sync actually + * successfully wrote the CPU state. Otherwise we will keep the value + * that is in the list. + * * Returns: true if all register values were read correctly, * false if some register was unknown or could not be read. * Note that we do not stop early on failure -- we will attempt * reading all registers in the list. */ -bool write_cpustate_to_list(ARMCPU *cpu); +bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync); #define ARM_CPUID_TI915T 0x54029152 #define ARM_CPUID_TI925T 0x54029252 diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static bool raw_accessors_invalid(const ARMCPRegInfo *ri) return true; } -bool write_cpustate_to_list(ARMCPU *cpu) +bool write_cpustate_to_list(ARMCPU *cpu, bool kvm_sync) { /* Write the coprocessor state from cpu->env to the (index,value) list. */ int i; @@ -XXX,XX +XXX,XX @@ bool write_cpustate_to_list(ARMCPU *cpu) for (i = 0; i < cpu->cpreg_array_len; i++) { uint32_t regidx = kvm_to_cpreg_id(cpu->cpreg_indexes[i]); const ARMCPRegInfo *ri; + uint64_t newval; ri = get_arm_cp_reginfo(cpu->cp_regs, regidx); if (!ri) { @@ -XXX,XX +XXX,XX @@ bool write_cpustate_to_list(ARMCPU *cpu) if (ri->type & ARM_CP_NO_RAW) { continue; } - cpu->cpreg_values[i] = read_raw_cp_reg(&cpu->env, ri); + + newval = read_raw_cp_reg(&cpu->env, ri); + if (kvm_sync) { + /* + * Only sync if the previous list->cpustate sync succeeded. + * Rather than tracking the success/failure state for every + * item in the list, we just recheck "does the raw write we must + * have made in write_list_to_cpustate() read back OK" here. + */ + uint64_t oldval = cpu->cpreg_values[i]; + + if (oldval == newval) { + continue; + } + + write_raw_cp_reg(&cpu->env, ri, oldval); + if (read_raw_cp_reg(&cpu->env, ri) != oldval) { + continue; + } + + write_raw_cp_reg(&cpu->env, ri, newval); + } + cpu->cpreg_values[i] = newval; } return ok; } diff --git a/target/arm/kvm32.c b/target/arm/kvm32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm32.c +++ b/target/arm/kvm32.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) return ret; } - /* Note that we do not call write_cpustate_to_list() - * here, so we are only writing the tuple list back to - * KVM. This is safe because nothing can change the - * CPUARMState cp15 fields (in particular gdb accesses cannot) - * and so there are no changes to sync. In fact syncing would - * be wrong at this point: for a constant register where TCG and - * KVM disagree about its value, the preceding write_list_to_cpustate() - * would not have had any effect on the CPUARMState value (since the - * register is read-only), and a write_cpustate_to_list() here would - * then try to write the TCG value back into KVM -- this would either - * fail or incorrectly change the value the guest sees. - * - * If we ever want to allow the user to modify cp15 registers via - * the gdb stub, we would need to be more clever here (for instance - * tracking the set of registers kvm_arch_get_registers() successfully - * managed to update the CPUARMState with, and only allowing those - * to be written back up into the kernel). - */ + write_cpustate_to_list(cpu, true); + if (!write_list_to_kvmstate(cpu, level)) { return EINVAL; } diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) return ret; } + write_cpustate_to_list(cpu, true); + if (!write_list_to_kvmstate(cpu, level)) { return EINVAL; } diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static int cpu_pre_save(void *opaque) abort(); } } else { - if (!write_cpustate_to_list(cpu)) { + if (!write_cpustate_to_list(cpu, false)) { /* This should never fail. */ abort(); } -- 2.20.1 Peter Crosthwaite hasn't had the bandwidth to do code review or other QEMU work for some time now -- remove his email address from MAINTAINERS file entries so we don't bombard him with patch emails. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190207181422.4907-1-peter.maydell@linaro.org --- MAINTAINERS | 4 ---- 1 file changed, 4 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ Guest CPU cores (TCG): ---------------------- Overall L: qemu-devel@nongnu.org -M: Peter Crosthwaite <crosthwaite.peter@gmail.com> M: Richard Henderson <rth@twiddle.net> R: Paolo Bonzini <pbonzini@redhat.com> S: Maintained @@ -XXX,XX +XXX,XX @@ F: tests/virtio-scsi-test.c T: git https://github.com/bonzini/qemu.git scsi-next SSI -M: Peter Crosthwaite <crosthwaite.peter@gmail.com> M: Alistair Francis <alistair@alistair23.me> S: Maintained F: hw/ssi/* @@ -XXX,XX +XXX,XX @@ F: tests/m25p80-test.c Xilinx SPI M: Alistair Francis <alistair@alistair23.me> -M: Peter Crosthwaite <crosthwaite.peter@gmail.com> S: Maintained F: hw/ssi/xilinx_* @@ -XXX,XX +XXX,XX @@ F: qom/cpu.c F: include/qom/cpu.h Device Tree -M: Peter Crosthwaite <crosthwaite.peter@gmail.com> M: Alexander Graf <agraf@suse.de> S: Maintained F: device_tree.c -- 2.20.1 The code for handling the NVIC SHPR1 register intends to permit byte and halfword accesses (as the architecture requires). However the 'case' line for it only lists the base address of the register, so attempts to access bytes other than the first one end up in the "bad write" default logic. This bug was added accidentally when we split out the SHPR1 logic from SHPR2 and SHPR3 to support v6M. Fixes: 7c9140afd594 ("nvic: Handle ARMv6-M SCS reserved registers") Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> --- The Zephyr RTOS happens to access SHPR1 byte at a time, which is how I spotted this. --- hw/intc/armv7m_nvic.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_read(void *opaque, hwaddr addr, } } break; - case 0xd18: /* System Handler Priority (SHPR1) */ + case 0xd18 ... 0xd1b: /* System Handler Priority (SHPR1) */ if (!arm_feature(&s->cpu->env, ARM_FEATURE_M_MAIN)) { val = 0; break; @@ -XXX,XX +XXX,XX @@ static MemTxResult nvic_sysreg_write(void *opaque, hwaddr addr, } nvic_irq_update(s); return MEMTX_OK; - case 0xd18: /* System Handler Priority (SHPR1) */ + case 0xd18 ... 0xd1b: /* System Handler Priority (SHPR1) */ if (!arm_feature(&s->cpu->env, ARM_FEATURE_M_MAIN)) { return MEMTX_OK; } -- 2.20.1 In commit 91c1e9fcbd7548db368 where we added dual-CPU support to the ARMSSE, we set up the wiring of the expansion IRQs via nested loops: the outer loop on 'i' loops for each CPU, and the inner loop on 'j' loops for each interrupt. Fix a typo which meant we were wiring every expansion IRQ line to external IRQ 0 on CPU 0 and to external IRQ 1 on CPU 1. Fixes: 91c1e9fcbd7548db368 ("hw/arm/armsse: Support dual-CPU configuration") Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> --- hw/arm/armsse.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armsse.c +++ b/hw/arm/armsse.c @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) /* Connect EXP_IRQ/EXP_CPUn_IRQ GPIOs to the NVIC's lines 32 and up */ s->exp_irqs[i] = g_new(qemu_irq, s->exp_numirq); for (j = 0; j < s->exp_numirq; j++) { - s->exp_irqs[i][j] = qdev_get_gpio_in(cpudev, i + 32); + s->exp_irqs[i][j] = qdev_get_gpio_in(cpudev, j + 32); } if (i == 0) { gpioname = g_strdup("EXP_IRQ"); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Since we're now handling a == b generically, we no longer need to do it by hand within target/arm/. Reviewed-by: David Gibson <david@gibson.dropbear.id.au> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190209033847.9014-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 6 +----- target/arm/translate-sve.c | 6 +----- target/arm/translate.c | 12 +++--------- 3 files changed, 5 insertions(+), 19 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_logic(DisasContext *s, uint32_t insn) gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_andc, 0); return; case 2: /* ORR */ - if (rn == rm) { /* MOV */ - gen_gvec_fn2(s, is_q, rd, rn, tcg_gen_gvec_mov, 0); - } else { - gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_or, 0); - } + gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_or, 0); return; case 3: /* ORN */ gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_orc, 0); diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_AND_zzz(DisasContext *s, arg_rrr_esz *a) static bool trans_ORR_zzz(DisasContext *s, arg_rrr_esz *a) { - if (a->rn == a->rm) { /* MOV */ - return do_mov_z(s, a->rd, a->rn); - } else { - return do_vector3_z(s, tcg_gen_gvec_or, 0, a->rd, a->rn, a->rm); - } + return do_vector3_z(s, tcg_gen_gvec_or, 0, a->rd, a->rn, a->rm); } static bool trans_EOR_zzz(DisasContext *s, arg_rrr_esz *a) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_gen_gvec_andc(0, rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); break; - case 2: - if (rn == rm) { - /* VMOV */ - tcg_gen_gvec_mov(0, rd_ofs, rn_ofs, vec_size, vec_size); - } else { - /* VORR */ - tcg_gen_gvec_or(0, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - } + case 2: /* VORR */ + tcg_gen_gvec_or(0, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); break; case 3: /* VORN */ tcg_gen_gvec_orc(0, rd_ofs, rn_ofs, rm_ofs, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190209033847.9014-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 35 ++++++++++++++--------------------- 1 file changed, 14 insertions(+), 21 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { + case 0x0c: /* SMAX, UMAX */ + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_smax, size); + } + return; + case 0x0d: /* SMIN, UMIN */ + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umin, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_smin, size); + } + return; case 0x10: /* ADD, SUB */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_sub, size); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genenvfn = fns[size][u]; break; } - case 0xc: /* SMAX, UMAX */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_max_s8, gen_helper_neon_max_u8 }, - { gen_helper_neon_max_s16, gen_helper_neon_max_u16 }, - { tcg_gen_smax_i32, tcg_gen_umax_i32 }, - }; - genfn = fns[size][u]; - break; - } - - case 0xd: /* SMIN, UMIN */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_min_s8, gen_helper_neon_min_u8 }, - { gen_helper_neon_min_s16, gen_helper_neon_min_u16 }, - { tcg_gen_smin_i32, tcg_gen_umin_i32 }, - }; - genfn = fns[size][u]; - break; - } case 0xe: /* SABD, UABD */ case 0xf: /* SABA, UABA */ { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190209033847.9014-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 25 +++++++++++++++++++------ 1 file changed, 19 insertions(+), 6 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_gen_gvec_cmp(u ? TCG_COND_GEU : TCG_COND_GE, size, rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); return 0; + + case NEON_3R_VMAX: + if (u) { + tcg_gen_gvec_umax(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } else { + tcg_gen_gvec_smax(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } + return 0; + case NEON_3R_VMIN: + if (u) { + tcg_gen_gvec_umin(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } else { + tcg_gen_gvec_smin(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } + return 0; } if (size == 3) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VQRSHL: GEN_NEON_INTEGER_OP_ENV(qrshl); break; - case NEON_3R_VMAX: - GEN_NEON_INTEGER_OP(max); - break; - case NEON_3R_VMIN: - GEN_NEON_INTEGER_OP(min); - break; case NEON_3R_VABD: GEN_NEON_INTEGER_OP(abd); break; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The 32-bit PMIN/PMAX has been decomposed to scalars, and so can be trivially expanded inline. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190209033847.9014-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void gen_neon_rsb(int size, TCGv_i32 t0, TCGv_i32 t1) } /* 32-bit pairwise ops end up the same as the elementwise versions. */ -#define gen_helper_neon_pmax_s32 gen_helper_neon_max_s32 -#define gen_helper_neon_pmax_u32 gen_helper_neon_max_u32 -#define gen_helper_neon_pmin_s32 gen_helper_neon_min_s32 -#define gen_helper_neon_pmin_u32 gen_helper_neon_min_u32 +#define gen_helper_neon_pmax_s32 tcg_gen_smax_i32 +#define gen_helper_neon_pmax_u32 tcg_gen_umax_i32 +#define gen_helper_neon_pmin_s32 tcg_gen_smin_i32 +#define gen_helper_neon_pmin_u32 tcg_gen_umin_i32 #define GEN_NEON_INTEGER_OP_ENV(name) do { \ switch ((size << 1) | u) { \ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> These are now unused. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190209033847.9014-6-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 12 ------------ target/arm/neon_helper.c | 12 ------------ 2 files changed, 24 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(neon_cge_s16, i32, i32, i32) DEF_HELPER_2(neon_cge_u32, i32, i32, i32) DEF_HELPER_2(neon_cge_s32, i32, i32, i32) -DEF_HELPER_2(neon_min_u8, i32, i32, i32) -DEF_HELPER_2(neon_min_s8, i32, i32, i32) -DEF_HELPER_2(neon_min_u16, i32, i32, i32) -DEF_HELPER_2(neon_min_s16, i32, i32, i32) -DEF_HELPER_2(neon_min_u32, i32, i32, i32) -DEF_HELPER_2(neon_min_s32, i32, i32, i32) -DEF_HELPER_2(neon_max_u8, i32, i32, i32) -DEF_HELPER_2(neon_max_s8, i32, i32, i32) -DEF_HELPER_2(neon_max_u16, i32, i32, i32) -DEF_HELPER_2(neon_max_s16, i32, i32, i32) -DEF_HELPER_2(neon_max_u32, i32, i32, i32) -DEF_HELPER_2(neon_max_s32, i32, i32, i32) DEF_HELPER_2(neon_pmin_u8, i32, i32, i32) DEF_HELPER_2(neon_pmin_s8, i32, i32, i32) DEF_HELPER_2(neon_pmin_u16, i32, i32, i32) diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon_helper.c +++ b/target/arm/neon_helper.c @@ -XXX,XX +XXX,XX @@ NEON_VOP(cge_u32, neon_u32, 1) #undef NEON_FN #define NEON_FN(dest, src1, src2) dest = (src1 < src2) ? src1 : src2 -NEON_VOP(min_s8, neon_s8, 4) -NEON_VOP(min_u8, neon_u8, 4) -NEON_VOP(min_s16, neon_s16, 2) -NEON_VOP(min_u16, neon_u16, 2) -NEON_VOP(min_s32, neon_s32, 1) -NEON_VOP(min_u32, neon_u32, 1) NEON_POP(pmin_s8, neon_s8, 4) NEON_POP(pmin_u8, neon_u8, 4) NEON_POP(pmin_s16, neon_s16, 2) @@ -XXX,XX +XXX,XX @@ NEON_POP(pmin_u16, neon_u16, 2) #undef NEON_FN #define NEON_FN(dest, src1, src2) dest = (src1 > src2) ? src1 : src2 -NEON_VOP(max_s8, neon_s8, 4) -NEON_VOP(max_u8, neon_u8, 4) -NEON_VOP(max_s16, neon_s16, 2) -NEON_VOP(max_u16, neon_u16, 2) -NEON_VOP(max_s32, neon_s32, 1) -NEON_VOP(max_u32, neon_u32, 1) NEON_POP(pmax_s8, neon_s8, 4) NEON_POP(pmax_u8, neon_u8, 4) NEON_POP(pmax_s16, neon_s16, 2) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The components of this register is stored in several different locations. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190209033847.9014-7-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static int vfp_gdb_get_reg(CPUARMState *env, uint8_t *buf, int reg) } switch (reg - nregs) { case 0: stl_p(buf, env->vfp.xregs[ARM_VFP_FPSID]); return 4; - case 1: stl_p(buf, env->vfp.xregs[ARM_VFP_FPSCR]); return 4; + case 1: stl_p(buf, vfp_get_fpscr(env)); return 4; case 2: stl_p(buf, env->vfp.xregs[ARM_VFP_FPEXC]); return 4; } return 0; @@ -XXX,XX +XXX,XX @@ static int vfp_gdb_set_reg(CPUARMState *env, uint8_t *buf, int reg) } switch (reg - nregs) { case 0: env->vfp.xregs[ARM_VFP_FPSID] = ldl_p(buf); return 4; - case 1: env->vfp.xregs[ARM_VFP_FPSCR] = ldl_p(buf); return 4; + case 1: vfp_set_fpscr(env, ldl_p(buf)); return 4; case 2: env->vfp.xregs[ARM_VFP_FPEXC] = ldl_p(buf) & (1 << 30); return 4; } return 0; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190209033847.9014-8-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf, i * 2 + 1, (uint32_t)(v >> 32), i, v); } - cpu_fprintf(f, "FPSCR: %08x\n", (int)env->vfp.xregs[ARM_VFP_FPSCR]); + cpu_fprintf(f, "FPSCR: %08x\n", vfp_get_fpscr(env)); } } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Minimize the code within a macro by splitting out a helper function. Use deposit32 instead of manual bit manipulation. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190209033847.9014-9-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 45 +++++++++++++++++++++++++++------------------ 1 file changed, 27 insertions(+), 18 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ float64 VFP_HELPER(sqrt, d)(float64 a, CPUARMState *env) return float64_sqrt(a, &env->vfp.fp_status); } +static void softfloat_to_vfp_compare(CPUARMState *env, int cmp) +{ + uint32_t flags; + switch (cmp) { + case float_relation_equal: + flags = 0x6; + break; + case float_relation_less: + flags = 0x8; + break; + case float_relation_greater: + flags = 0x2; + break; + case float_relation_unordered: + flags = 0x3; + break; + default: + g_assert_not_reached(); + } + env->vfp.xregs[ARM_VFP_FPSCR] = + deposit32(env->vfp.xregs[ARM_VFP_FPSCR], 28, 4, flags); +} + /* XXX: check quiet/signaling case */ #define DO_VFP_cmp(p, type) \ void VFP_HELPER(cmp, p)(type a, type b, CPUARMState *env) \ { \ - uint32_t flags; \ - switch(type ## _compare_quiet(a, b, &env->vfp.fp_status)) { \ - case 0: flags = 0x6; break; \ - case -1: flags = 0x8; break; \ - case 1: flags = 0x2; break; \ - default: case 2: flags = 0x3; break; \ - } \ - env->vfp.xregs[ARM_VFP_FPSCR] = (flags << 28) \ - | (env->vfp.xregs[ARM_VFP_FPSCR] & 0x0fffffff); \ + softfloat_to_vfp_compare(env, \ + type ## _compare_quiet(a, b, &env->vfp.fp_status)); \ } \ void VFP_HELPER(cmpe, p)(type a, type b, CPUARMState *env) \ { \ - uint32_t flags; \ - switch(type ## _compare(a, b, &env->vfp.fp_status)) { \ - case 0: flags = 0x6; break; \ - case -1: flags = 0x8; break; \ - case 1: flags = 0x2; break; \ - default: case 2: flags = 0x3; break; \ - } \ - env->vfp.xregs[ARM_VFP_FPSCR] = (flags << 28) \ - | (env->vfp.xregs[ARM_VFP_FPSCR] & 0x0fffffff); \ + softfloat_to_vfp_compare(env, \ + type ## _compare(a, b, &env->vfp.fp_status)); \ } DO_VFP_cmp(s, float32) DO_VFP_cmp(d, float64) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Given that we mask bits properly on set, there is no reason to mask them again on get. We failed to clear the exception status bits, 0x9f, which means that the wrong value would be returned on get. Except in the (probably normal) case in which the set clears all of the bits. Simplify the code in set to also clear the RES0 bits. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190209033847.9014-10-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 15 ++++++++------- 1 file changed, 8 insertions(+), 7 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env) int i; uint32_t fpscr; - fpscr = (env->vfp.xregs[ARM_VFP_FPSCR] & 0xffc8ffff) + fpscr = env->vfp.xregs[ARM_VFP_FPSCR] | (env->vfp.vec_len << 16) | (env->vfp.vec_stride << 20); @@ -XXX,XX +XXX,XX @@ static inline int vfp_exceptbits_to_host(int target_bits) void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) { int i; - uint32_t changed; + uint32_t changed = env->vfp.xregs[ARM_VFP_FPSCR]; /* When ARMv8.2-FP16 is not supported, FZ16 is RES0. */ if (!cpu_isar_feature(aa64_fp16, arm_env_get_cpu(env))) { @@ -XXX,XX +XXX,XX @@ void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) /* * We don't implement trapped exception handling, so the - * trap enable bits are all RAZ/WI (not RES0!) + * trap enable bits, IDE|IXE|UFE|OFE|DZE|IOE are all RAZ/WI (not RES0!) + * + * If we exclude the exception flags, IOC|DZC|OFC|UFC|IXC|IDC + * (which are stored in fp_status), and the other RES0 bits + * in between, then we clear all of the low 16 bits. */ - val &= ~(FPCR_IDE | FPCR_IXE | FPCR_UFE | FPCR_OFE | FPCR_DZE | FPCR_IOE); - - changed = env->vfp.xregs[ARM_VFP_FPSCR]; - env->vfp.xregs[ARM_VFP_FPSCR] = (val & 0xffc8ffff); + env->vfp.xregs[ARM_VFP_FPSCR] = val & 0xffc80000; env->vfp.vec_len = (val >> 16) & 7; env->vfp.vec_stride = (val >> 20) & 3; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Change the representation of this field such that it is easy to set from vector code. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190209033847.9014-11-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 5 ++++- target/arm/helper.c | 19 +++++++++++++++---- target/arm/neon_helper.c | 2 +- target/arm/vec_helper.c | 2 +- 4 files changed, 21 insertions(+), 7 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUARMState { ARMPredicateReg preg_tmp; #endif - uint32_t xregs[16]; /* We store these fpcsr fields separately for convenience. */ + uint32_t qc[4] QEMU_ALIGNED(16); int vec_len; int vec_stride; + uint32_t xregs[16]; + /* Scratch space for aa32 neon expansion. */ uint32_t scratch[8]; @@ -XXX,XX +XXX,XX @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val); #define FPCR_FZ16 (1 << 19) /* ARMv8.2+, FP16 flush-to-zero */ #define FPCR_FZ (1 << 24) /* Flush-to-zero enable bit */ #define FPCR_DN (1 << 25) /* Default NaN enable bit */ +#define FPCR_QC (1 << 27) /* Cumulative saturation bit */ static inline uint32_t vfp_get_fpsr(CPUARMState *env) { diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static inline int vfp_exceptbits_from_host(int host_bits) uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env) { - int i; - uint32_t fpscr; + uint32_t i, fpscr; fpscr = env->vfp.xregs[ARM_VFP_FPSCR] | (env->vfp.vec_len << 16) @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env) /* FZ16 does not generate an input denormal exception. */ i |= (get_float_exception_flags(&env->vfp.fp_status_f16) & ~float_flag_input_denormal); - fpscr |= vfp_exceptbits_from_host(i); + + i = env->vfp.qc[0] | env->vfp.qc[1] | env->vfp.qc[2] | env->vfp.qc[3]; + fpscr |= i ? FPCR_QC : 0; + return fpscr; } @@ -XXX,XX +XXX,XX @@ void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) * (which are stored in fp_status), and the other RES0 bits * in between, then we clear all of the low 16 bits. */ - env->vfp.xregs[ARM_VFP_FPSCR] = val & 0xffc80000; + env->vfp.xregs[ARM_VFP_FPSCR] = val & 0xf7c80000; env->vfp.vec_len = (val >> 16) & 7; env->vfp.vec_stride = (val >> 20) & 3; + /* + * The bit we set within fpscr_q is arbitrary; the register as a + * whole being zero/non-zero is what counts. + */ + env->vfp.qc[0] = val & FPCR_QC; + env->vfp.qc[1] = 0; + env->vfp.qc[2] = 0; + env->vfp.qc[3] = 0; + changed ^= val; if (changed & (3 << 22)) { i = (val >> 22) & 3; diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon_helper.c +++ b/target/arm/neon_helper.c @@ -XXX,XX +XXX,XX @@ #define SIGNBIT (uint32_t)0x80000000 #define SIGNBIT64 ((uint64_t)1 << 63) -#define SET_QC() env->vfp.xregs[ARM_VFP_FPSCR] |= CPSR_Q +#define SET_QC() env->vfp.qc[0] = 1 #define NEON_TYPE1(name, type) \ typedef struct \ diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ #define H4(x) (x) #endif -#define SET_QC() env->vfp.xregs[ARM_VFP_FPSCR] |= CPSR_Q +#define SET_QC() env->vfp.qc[0] = 1 static void clear_tail(void *vd, uintptr_t opr_sz, uintptr_t max_sz) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> For same-sign saturation, we have tcg vector operations. We can compute the QC bit by comparing the saturated value against the unsaturated value. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190209033847.9014-12-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 33 +++++++ target/arm/translate.h | 4 + target/arm/translate-a64.c | 36 ++++---- target/arm/translate.c | 172 +++++++++++++++++++++++++++++++------ target/arm/vec_helper.c | 130 ++++++++++++++++++++++++++++ 5 files changed, 331 insertions(+), 44 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_6(gvec_fmla_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uqadd_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uqadd_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uqadd_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uqadd_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sqadd_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sqadd_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sqadd_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sqadd_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uqsub_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uqsub_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uqsub_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uqsub_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sqsub_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sqsub_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sqsub_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sqsub_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ extern const GVecGen2i ssra_op[4]; extern const GVecGen2i usra_op[4]; extern const GVecGen2i sri_op[4]; extern const GVecGen2i sli_op[4]; +extern const GVecGen4 uqadd_op[4]; +extern const GVecGen4 sqadd_op[4]; +extern const GVecGen4 uqsub_op[4]; +extern const GVecGen4 sqsub_op[4]; void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); /* diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) } switch (opcode) { + case 0x01: /* SQADD, UQADD */ + tcg_gen_gvec_4(vec_full_reg_offset(s, rd), + offsetof(CPUARMState, vfp.qc), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + is_q ? 16 : 8, vec_full_reg_size(s), + (u ? uqadd_op : sqadd_op) + size); + return; + case 0x05: /* SQSUB, UQSUB */ + tcg_gen_gvec_4(vec_full_reg_offset(s, rd), + offsetof(CPUARMState, vfp.qc), + vec_full_reg_offset(s, rn), + vec_full_reg_offset(s, rm), + is_q ? 16 : 8, vec_full_reg_size(s), + (u ? uqsub_op : sqsub_op) + size); + return; case 0x0c: /* SMAX, UMAX */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_umax, size); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genfn = fns[size][u]; break; } - case 0x1: /* SQADD, UQADD */ - { - static NeonGenTwoOpEnvFn * const fns[3][2] = { - { gen_helper_neon_qadd_s8, gen_helper_neon_qadd_u8 }, - { gen_helper_neon_qadd_s16, gen_helper_neon_qadd_u16 }, - { gen_helper_neon_qadd_s32, gen_helper_neon_qadd_u32 }, - }; - genenvfn = fns[size][u]; - break; - } case 0x2: /* SRHADD, URHADD */ { static NeonGenTwoOpFn * const fns[3][2] = { @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genfn = fns[size][u]; break; } - case 0x5: /* SQSUB, UQSUB */ - { - static NeonGenTwoOpEnvFn * const fns[3][2] = { - { gen_helper_neon_qsub_s8, gen_helper_neon_qsub_u8 }, - { gen_helper_neon_qsub_s16, gen_helper_neon_qsub_u16 }, - { gen_helper_neon_qsub_s32, gen_helper_neon_qsub_u32 }, - }; - genenvfn = fns[size][u]; - break; - } case 0x8: /* SSHL, USHL */ { static NeonGenTwoOpFn * const fns[3][2] = { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ const GVecGen3 cmtst_op[4] = { .vece = MO_64 }, }; +static void gen_uqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, + TCGv_vec a, TCGv_vec b) +{ + TCGv_vec x = tcg_temp_new_vec_matching(t); + tcg_gen_add_vec(vece, x, a, b); + tcg_gen_usadd_vec(vece, t, a, b); + tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); + tcg_gen_or_vec(vece, sat, sat, x); + tcg_temp_free_vec(x); +} + +const GVecGen4 uqadd_op[4] = { + { .fniv = gen_uqadd_vec, + .fno = gen_helper_gvec_uqadd_b, + .opc = INDEX_op_usadd_vec, + .write_aofs = true, + .vece = MO_8 }, + { .fniv = gen_uqadd_vec, + .fno = gen_helper_gvec_uqadd_h, + .opc = INDEX_op_usadd_vec, + .write_aofs = true, + .vece = MO_16 }, + { .fniv = gen_uqadd_vec, + .fno = gen_helper_gvec_uqadd_s, + .opc = INDEX_op_usadd_vec, + .write_aofs = true, + .vece = MO_32 }, + { .fniv = gen_uqadd_vec, + .fno = gen_helper_gvec_uqadd_d, + .opc = INDEX_op_usadd_vec, + .write_aofs = true, + .vece = MO_64 }, +}; + +static void gen_sqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, + TCGv_vec a, TCGv_vec b) +{ + TCGv_vec x = tcg_temp_new_vec_matching(t); + tcg_gen_add_vec(vece, x, a, b); + tcg_gen_ssadd_vec(vece, t, a, b); + tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); + tcg_gen_or_vec(vece, sat, sat, x); + tcg_temp_free_vec(x); +} + +const GVecGen4 sqadd_op[4] = { + { .fniv = gen_sqadd_vec, + .fno = gen_helper_gvec_sqadd_b, + .opc = INDEX_op_ssadd_vec, + .write_aofs = true, + .vece = MO_8 }, + { .fniv = gen_sqadd_vec, + .fno = gen_helper_gvec_sqadd_h, + .opc = INDEX_op_ssadd_vec, + .write_aofs = true, + .vece = MO_16 }, + { .fniv = gen_sqadd_vec, + .fno = gen_helper_gvec_sqadd_s, + .opc = INDEX_op_ssadd_vec, + .write_aofs = true, + .vece = MO_32 }, + { .fniv = gen_sqadd_vec, + .fno = gen_helper_gvec_sqadd_d, + .opc = INDEX_op_ssadd_vec, + .write_aofs = true, + .vece = MO_64 }, +}; + +static void gen_uqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, + TCGv_vec a, TCGv_vec b) +{ + TCGv_vec x = tcg_temp_new_vec_matching(t); + tcg_gen_sub_vec(vece, x, a, b); + tcg_gen_ussub_vec(vece, t, a, b); + tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); + tcg_gen_or_vec(vece, sat, sat, x); + tcg_temp_free_vec(x); +} + +const GVecGen4 uqsub_op[4] = { + { .fniv = gen_uqsub_vec, + .fno = gen_helper_gvec_uqsub_b, + .opc = INDEX_op_ussub_vec, + .write_aofs = true, + .vece = MO_8 }, + { .fniv = gen_uqsub_vec, + .fno = gen_helper_gvec_uqsub_h, + .opc = INDEX_op_ussub_vec, + .write_aofs = true, + .vece = MO_16 }, + { .fniv = gen_uqsub_vec, + .fno = gen_helper_gvec_uqsub_s, + .opc = INDEX_op_ussub_vec, + .write_aofs = true, + .vece = MO_32 }, + { .fniv = gen_uqsub_vec, + .fno = gen_helper_gvec_uqsub_d, + .opc = INDEX_op_ussub_vec, + .write_aofs = true, + .vece = MO_64 }, +}; + +static void gen_sqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, + TCGv_vec a, TCGv_vec b) +{ + TCGv_vec x = tcg_temp_new_vec_matching(t); + tcg_gen_sub_vec(vece, x, a, b); + tcg_gen_sssub_vec(vece, t, a, b); + tcg_gen_cmp_vec(TCG_COND_NE, vece, x, x, t); + tcg_gen_or_vec(vece, sat, sat, x); + tcg_temp_free_vec(x); +} + +const GVecGen4 sqsub_op[4] = { + { .fniv = gen_sqsub_vec, + .fno = gen_helper_gvec_sqsub_b, + .opc = INDEX_op_sssub_vec, + .write_aofs = true, + .vece = MO_8 }, + { .fniv = gen_sqsub_vec, + .fno = gen_helper_gvec_sqsub_h, + .opc = INDEX_op_sssub_vec, + .write_aofs = true, + .vece = MO_16 }, + { .fniv = gen_sqsub_vec, + .fno = gen_helper_gvec_sqsub_s, + .opc = INDEX_op_sssub_vec, + .write_aofs = true, + .vece = MO_32 }, + { .fniv = gen_sqsub_vec, + .fno = gen_helper_gvec_sqsub_d, + .opc = INDEX_op_sssub_vec, + .write_aofs = true, + .vece = MO_64 }, +}; + /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. We process data in a mixture of 32-bit and 64-bit chunks. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } return 0; + case NEON_3R_VQADD: + tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), + rn_ofs, rm_ofs, vec_size, vec_size, + (u ? uqadd_op : sqadd_op) + size); + break; + + case NEON_3R_VQSUB: + tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), + rn_ofs, rm_ofs, vec_size, vec_size, + (u ? uqsub_op : sqsub_op) + size); + break; + case NEON_3R_VMUL: /* VMUL */ if (u) { /* Polynomial case allows only P8 and is handled below. */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) neon_load_reg64(cpu_V0, rn + pass); neon_load_reg64(cpu_V1, rm + pass); switch (op) { - case NEON_3R_VQADD: - if (u) { - gen_helper_neon_qadd_u64(cpu_V0, cpu_env, - cpu_V0, cpu_V1); - } else { - gen_helper_neon_qadd_s64(cpu_V0, cpu_env, - cpu_V0, cpu_V1); - } - break; - case NEON_3R_VQSUB: - if (u) { - gen_helper_neon_qsub_u64(cpu_V0, cpu_env, - cpu_V0, cpu_V1); - } else { - gen_helper_neon_qsub_s64(cpu_V0, cpu_env, - cpu_V0, cpu_V1); - } - break; case NEON_3R_VSHL: if (u) { gen_helper_neon_shl_u64(cpu_V0, cpu_V1, cpu_V0); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VHADD: GEN_NEON_INTEGER_OP(hadd); break; - case NEON_3R_VQADD: - GEN_NEON_INTEGER_OP_ENV(qadd); - break; case NEON_3R_VRHADD: GEN_NEON_INTEGER_OP(rhadd); break; case NEON_3R_VHSUB: GEN_NEON_INTEGER_OP(hsub); break; - case NEON_3R_VQSUB: - GEN_NEON_INTEGER_OP_ENV(qsub); - break; case NEON_3R_VSHL: GEN_NEON_INTEGER_OP(shl); break; diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ DO_FMLA_IDX(gvec_fmla_idx_s, float32, H4) DO_FMLA_IDX(gvec_fmla_idx_d, float64, ) #undef DO_FMLA_IDX + +#define DO_SAT(NAME, WTYPE, TYPEN, TYPEM, OP, MIN, MAX) \ +void HELPER(NAME)(void *vd, void *vq, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + TYPEN *d = vd, *n = vn; TYPEM *m = vm; \ + bool q = false; \ + for (i = 0; i < oprsz / sizeof(TYPEN); i++) { \ + WTYPE dd = (WTYPE)n[i] OP m[i]; \ + if (dd < MIN) { \ + dd = MIN; \ + q = true; \ + } else if (dd > MAX) { \ + dd = MAX; \ + q = true; \ + } \ + d[i] = dd; \ + } \ + if (q) { \ + uint32_t *qc = vq; \ + qc[0] = 1; \ + } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ +} + +DO_SAT(gvec_uqadd_b, int, uint8_t, uint8_t, +, 0, UINT8_MAX) +DO_SAT(gvec_uqadd_h, int, uint16_t, uint16_t, +, 0, UINT16_MAX) +DO_SAT(gvec_uqadd_s, int64_t, uint32_t, uint32_t, +, 0, UINT32_MAX) + +DO_SAT(gvec_sqadd_b, int, int8_t, int8_t, +, INT8_MIN, INT8_MAX) +DO_SAT(gvec_sqadd_h, int, int16_t, int16_t, +, INT16_MIN, INT16_MAX) +DO_SAT(gvec_sqadd_s, int64_t, int32_t, int32_t, +, INT32_MIN, INT32_MAX) + +DO_SAT(gvec_uqsub_b, int, uint8_t, uint8_t, -, 0, UINT8_MAX) +DO_SAT(gvec_uqsub_h, int, uint16_t, uint16_t, -, 0, UINT16_MAX) +DO_SAT(gvec_uqsub_s, int64_t, uint32_t, uint32_t, -, 0, UINT32_MAX) + +DO_SAT(gvec_sqsub_b, int, int8_t, int8_t, -, INT8_MIN, INT8_MAX) +DO_SAT(gvec_sqsub_h, int, int16_t, int16_t, -, INT16_MIN, INT16_MAX) +DO_SAT(gvec_sqsub_s, int64_t, int32_t, int32_t, -, INT32_MIN, INT32_MAX) + +#undef DO_SAT + +void HELPER(gvec_uqadd_d)(void *vd, void *vq, void *vn, + void *vm, uint32_t desc) +{ + intptr_t i, oprsz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn, *m = vm; + bool q = false; + + for (i = 0; i < oprsz / 8; i++) { + uint64_t nn = n[i], mm = m[i], dd = nn + mm; + if (dd < nn) { + dd = UINT64_MAX; + q = true; + } + d[i] = dd; + } + if (q) { + uint32_t *qc = vq; + qc[0] = 1; + } + clear_tail(d, oprsz, simd_maxsz(desc)); +} + +void HELPER(gvec_uqsub_d)(void *vd, void *vq, void *vn, + void *vm, uint32_t desc) +{ + intptr_t i, oprsz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn, *m = vm; + bool q = false; + + for (i = 0; i < oprsz / 8; i++) { + uint64_t nn = n[i], mm = m[i], dd = nn - mm; + if (nn < mm) { + dd = 0; + q = true; + } + d[i] = dd; + } + if (q) { + uint32_t *qc = vq; + qc[0] = 1; + } + clear_tail(d, oprsz, simd_maxsz(desc)); +} + +void HELPER(gvec_sqadd_d)(void *vd, void *vq, void *vn, + void *vm, uint32_t desc) +{ + intptr_t i, oprsz = simd_oprsz(desc); + int64_t *d = vd, *n = vn, *m = vm; + bool q = false; + + for (i = 0; i < oprsz / 8; i++) { + int64_t nn = n[i], mm = m[i], dd = nn + mm; + if (((dd ^ nn) & ~(nn ^ mm)) & INT64_MIN) { + dd = (nn >> 63) ^ ~INT64_MIN; + q = true; + } + d[i] = dd; + } + if (q) { + uint32_t *qc = vq; + qc[0] = 1; + } + clear_tail(d, oprsz, simd_maxsz(desc)); +} + +void HELPER(gvec_sqsub_d)(void *vd, void *vq, void *vn, + void *vm, uint32_t desc) +{ + intptr_t i, oprsz = simd_oprsz(desc); + int64_t *d = vd, *n = vn, *m = vm; + bool q = false; + + for (i = 0; i < oprsz / 8; i++) { + int64_t nn = n[i], mm = m[i], dd = nn - mm; + if (((dd ^ nn) & (nn ^ mm)) & INT64_MIN) { + dd = (nn >> 63) ^ ~INT64_MIN; + q = true; + } + d[i] = dd; + } + if (q) { + uint32_t *qc = vq; + qc[0] = 1; + } + clear_tail(d, oprsz, simd_maxsz(desc)); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Fortunately, the functions affected are so far only called from SVE, so there is no tail to be cleared. But as we convert more of AdvSIMD to gvec, this will matter. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190209033847.9014-13-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/vec_helper.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ d[i] = FUNC(n[i], stat); \ } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ } DO_2OP(gvec_frecpe_h, helper_recpe_f16, float16) @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ d[i] = FUNC(n[i], m[i], stat); \ } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ } DO_3OP(gvec_fadd_h, float16_add, float16) -- 2.20.1 From: Sandra Loosemore <sandra@codesourcery.com> Per the GDB remote protocol documentation https://sourceware.org/gdb/current/onlinedocs/gdb/Packets.html#index-vKill-packet the debug stub is expected to send a reply to the 'vKill' packet. At least some versions of GDB crash if the gdb stub simply exits without sending a reply. This patch fixes QEMU's gdb stub to conform to the expected behavior. Note that QEMU's existing handling of the legacy 'k' packet is correct: in that case GDB does not expect a reply, and QEMU does not send one. Signed-off-by: Sandra Loosemore <sandra@codesourcery.com> Message-id: 1550008033-26540-1-git-send-email-sandra@codesourcery.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- gdbstub.c | 1 + 1 file changed, 1 insertion(+) diff --git a/gdbstub.c b/gdbstub.c index XXXXXXX..XXXXXXX 100644 --- a/gdbstub.c +++ b/gdbstub.c @@ -XXX,XX +XXX,XX @@ static int gdb_handle_packet(GDBState *s, const char *line_buf) break; } else if (strncmp(p, "Kill;", 5) == 0) { /* Kill the target */ + put_packet(s, "OK"); error_report("QEMU: Terminated via GDBstub"); exit(0); } else { -- 2.20.1 Hi; this is one last arm pullreq before the end of the year. Mostly minor cleanups, and also implementation of the FEAT_XS architectural feature. thanks -- PMM The following changes since commit 8032c78e556cd0baec111740a6c636863f9bd7c8: Merge tag 'firmware-20241216-pull-request' of https://gitlab.com/kraxel/qemu into staging (2024-12-16 14:20:33 -0500) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20241217 for you to fetch changes up to e91254250acb8570bd7b8a8f89d30e6d18291d02: tests/functional: update sbsa-ref firmware used in test (2024-12-17 15:21:06 +0000) ---------------------------------------------------------------- target-arm queue: * remove a line of redundant code * convert various TCG helper fns to use 'fpst' alias * Use float_status in helper_fcvtx_f64_to_f32 * Use float_status in helper_vfp_fcvt{ds,sd} * Implement FEAT_XS * hw/intc/arm_gicv3_its: Zero initialize local DTEntry etc structs * tests/functional: update sbsa-ref firmware used in test ---------------------------------------------------------------- Denis Rastyogin (1): target/arm: remove redundant code Manos Pitsidianakis (3): target/arm: Add decodetree entry for DSB nXS variant target/arm: Enable FEAT_XS for the max cpu tests/tcg/aarch64: add system test for FEAT_XS Marcin Juszkiewicz (1): tests/functional: update sbsa-ref firmware used in test Peter Maydell (4): target/arm: Implement fine-grained-trap handling for FEAT_XS target/arm: Add ARM_CP_ADD_TLBI_NXS type flag for NXS insns target/arm: Add ARM_CP_ADD_TLBI_NXS type flag to TLBI insns hw/intc/arm_gicv3_its: Zero initialize local DTEntry etc structs Richard Henderson (10): target/arm: Convert vfp_helper.c to fpst alias target/arm: Convert helper-a64.c to fpst alias target/arm: Convert vec_helper.c to fpst alias target/arm: Convert neon_helper.c to fpst alias target/arm: Convert sve_helper.c to fpst alias target/arm: Convert sme_helper.c to fpst alias target/arm: Convert vec_helper.c to use env alias target/arm: Convert neon_helper.c to use env alias target/arm: Use float_status in helper_fcvtx_f64_to_f32 target/arm: Use float_status in helper_vfp_fcvt{ds,sd} docs/system/arm/emulation.rst | 1 + target/arm/cpregs.h | 80 ++-- target/arm/cpu-features.h | 5 + target/arm/helper.h | 638 +++++++++++++++---------------- target/arm/tcg/helper-a64.h | 116 +++--- target/arm/tcg/helper-sme.h | 4 +- target/arm/tcg/helper-sve.h | 426 ++++++++++----------- target/arm/tcg/a64.decode | 3 + hw/intc/arm_gicv3_its.c | 44 +-- target/arm/helper.c | 30 +- target/arm/tcg/cpu64.c | 1 + target/arm/tcg/helper-a64.c | 101 ++--- target/arm/tcg/neon_helper.c | 27 +- target/arm/tcg/op_helper.c | 11 +- target/arm/tcg/sme_helper.c | 8 +- target/arm/tcg/sve_helper.c | 96 ++--- target/arm/tcg/tlb-insns.c | 202 ++++++---- target/arm/tcg/translate-a64.c | 26 +- target/arm/tcg/translate-vfp.c | 4 +- target/arm/tcg/vec_helper.c | 81 ++-- target/arm/vfp_helper.c | 130 +++---- tests/tcg/aarch64/system/feat-xs.c | 27 ++ tests/functional/test_aarch64_sbsaref.py | 20 +- 23 files changed, 1083 insertions(+), 998 deletions(-) create mode 100644 tests/tcg/aarch64/system/feat-xs.c From: Denis Rastyogin <gerben@altlinux.org> This call is redundant as it only retrieves a value that is not used further. Found by Linux Verification Center (linuxtesting.org) with SVACE. Signed-off-by: Denis Rastyogin <gerben@altlinux.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241212120618.518369-1-gerben@altlinux.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/vfp_helper.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ float64 HELPER(rintd)(float64 x, void *fp_status) ret = float64_round_to_int(x, fp_status); - new_flags = get_float_exception_flags(fp_status); - /* Suppress any inexact exceptions the conversion produced */ if (!(old_flags & float_flag_inexact)) { new_flags = get_float_exception_flags(fp_status); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241206031224.78525-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 268 ++++++++++++++++++++-------------------- target/arm/vfp_helper.c | 120 ++++++++---------- 2 files changed, 186 insertions(+), 202 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(probe_access, TCG_CALL_NO_WG, void, env, tl, i32, i32, i32) DEF_HELPER_1(vfp_get_fpscr, i32, env) DEF_HELPER_2(vfp_set_fpscr, void, env, i32) -DEF_HELPER_3(vfp_addh, f16, f16, f16, ptr) -DEF_HELPER_3(vfp_adds, f32, f32, f32, ptr) -DEF_HELPER_3(vfp_addd, f64, f64, f64, ptr) -DEF_HELPER_3(vfp_subh, f16, f16, f16, ptr) -DEF_HELPER_3(vfp_subs, f32, f32, f32, ptr) -DEF_HELPER_3(vfp_subd, f64, f64, f64, ptr) -DEF_HELPER_3(vfp_mulh, f16, f16, f16, ptr) -DEF_HELPER_3(vfp_muls, f32, f32, f32, ptr) -DEF_HELPER_3(vfp_muld, f64, f64, f64, ptr) -DEF_HELPER_3(vfp_divh, f16, f16, f16, ptr) -DEF_HELPER_3(vfp_divs, f32, f32, f32, ptr) -DEF_HELPER_3(vfp_divd, f64, f64, f64, ptr) -DEF_HELPER_3(vfp_maxh, f16, f16, f16, ptr) -DEF_HELPER_3(vfp_maxs, f32, f32, f32, ptr) -DEF_HELPER_3(vfp_maxd, f64, f64, f64, ptr) -DEF_HELPER_3(vfp_minh, f16, f16, f16, ptr) -DEF_HELPER_3(vfp_mins, f32, f32, f32, ptr) -DEF_HELPER_3(vfp_mind, f64, f64, f64, ptr) -DEF_HELPER_3(vfp_maxnumh, f16, f16, f16, ptr) -DEF_HELPER_3(vfp_maxnums, f32, f32, f32, ptr) -DEF_HELPER_3(vfp_maxnumd, f64, f64, f64, ptr) -DEF_HELPER_3(vfp_minnumh, f16, f16, f16, ptr) -DEF_HELPER_3(vfp_minnums, f32, f32, f32, ptr) -DEF_HELPER_3(vfp_minnumd, f64, f64, f64, ptr) -DEF_HELPER_2(vfp_sqrth, f16, f16, ptr) -DEF_HELPER_2(vfp_sqrts, f32, f32, ptr) -DEF_HELPER_2(vfp_sqrtd, f64, f64, ptr) +DEF_HELPER_3(vfp_addh, f16, f16, f16, fpst) +DEF_HELPER_3(vfp_adds, f32, f32, f32, fpst) +DEF_HELPER_3(vfp_addd, f64, f64, f64, fpst) +DEF_HELPER_3(vfp_subh, f16, f16, f16, fpst) +DEF_HELPER_3(vfp_subs, f32, f32, f32, fpst) +DEF_HELPER_3(vfp_subd, f64, f64, f64, fpst) +DEF_HELPER_3(vfp_mulh, f16, f16, f16, fpst) +DEF_HELPER_3(vfp_muls, f32, f32, f32, fpst) +DEF_HELPER_3(vfp_muld, f64, f64, f64, fpst) +DEF_HELPER_3(vfp_divh, f16, f16, f16, fpst) +DEF_HELPER_3(vfp_divs, f32, f32, f32, fpst) +DEF_HELPER_3(vfp_divd, f64, f64, f64, fpst) +DEF_HELPER_3(vfp_maxh, f16, f16, f16, fpst) +DEF_HELPER_3(vfp_maxs, f32, f32, f32, fpst) +DEF_HELPER_3(vfp_maxd, f64, f64, f64, fpst) +DEF_HELPER_3(vfp_minh, f16, f16, f16, fpst) +DEF_HELPER_3(vfp_mins, f32, f32, f32, fpst) +DEF_HELPER_3(vfp_mind, f64, f64, f64, fpst) +DEF_HELPER_3(vfp_maxnumh, f16, f16, f16, fpst) +DEF_HELPER_3(vfp_maxnums, f32, f32, f32, fpst) +DEF_HELPER_3(vfp_maxnumd, f64, f64, f64, fpst) +DEF_HELPER_3(vfp_minnumh, f16, f16, f16, fpst) +DEF_HELPER_3(vfp_minnums, f32, f32, f32, fpst) +DEF_HELPER_3(vfp_minnumd, f64, f64, f64, fpst) +DEF_HELPER_2(vfp_sqrth, f16, f16, fpst) +DEF_HELPER_2(vfp_sqrts, f32, f32, fpst) +DEF_HELPER_2(vfp_sqrtd, f64, f64, fpst) DEF_HELPER_3(vfp_cmph, void, f16, f16, env) DEF_HELPER_3(vfp_cmps, void, f32, f32, env) DEF_HELPER_3(vfp_cmpd, void, f64, f64, env) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_cmped, void, f64, f64, env) DEF_HELPER_2(vfp_fcvtds, f64, f32, env) DEF_HELPER_2(vfp_fcvtsd, f32, f64, env) -DEF_HELPER_FLAGS_2(bfcvt, TCG_CALL_NO_RWG, i32, f32, ptr) -DEF_HELPER_FLAGS_2(bfcvt_pair, TCG_CALL_NO_RWG, i32, i64, ptr) +DEF_HELPER_FLAGS_2(bfcvt, TCG_CALL_NO_RWG, i32, f32, fpst) +DEF_HELPER_FLAGS_2(bfcvt_pair, TCG_CALL_NO_RWG, i32, i64, fpst) -DEF_HELPER_2(vfp_uitoh, f16, i32, ptr) -DEF_HELPER_2(vfp_uitos, f32, i32, ptr) -DEF_HELPER_2(vfp_uitod, f64, i32, ptr) -DEF_HELPER_2(vfp_sitoh, f16, i32, ptr) -DEF_HELPER_2(vfp_sitos, f32, i32, ptr) -DEF_HELPER_2(vfp_sitod, f64, i32, ptr) +DEF_HELPER_2(vfp_uitoh, f16, i32, fpst) +DEF_HELPER_2(vfp_uitos, f32, i32, fpst) +DEF_HELPER_2(vfp_uitod, f64, i32, fpst) +DEF_HELPER_2(vfp_sitoh, f16, i32, fpst) +DEF_HELPER_2(vfp_sitos, f32, i32, fpst) +DEF_HELPER_2(vfp_sitod, f64, i32, fpst) -DEF_HELPER_2(vfp_touih, i32, f16, ptr) -DEF_HELPER_2(vfp_touis, i32, f32, ptr) -DEF_HELPER_2(vfp_touid, i32, f64, ptr) -DEF_HELPER_2(vfp_touizh, i32, f16, ptr) -DEF_HELPER_2(vfp_touizs, i32, f32, ptr) -DEF_HELPER_2(vfp_touizd, i32, f64, ptr) -DEF_HELPER_2(vfp_tosih, s32, f16, ptr) -DEF_HELPER_2(vfp_tosis, s32, f32, ptr) -DEF_HELPER_2(vfp_tosid, s32, f64, ptr) -DEF_HELPER_2(vfp_tosizh, s32, f16, ptr) -DEF_HELPER_2(vfp_tosizs, s32, f32, ptr) -DEF_HELPER_2(vfp_tosizd, s32, f64, ptr) +DEF_HELPER_2(vfp_touih, i32, f16, fpst) +DEF_HELPER_2(vfp_touis, i32, f32, fpst) +DEF_HELPER_2(vfp_touid, i32, f64, fpst) +DEF_HELPER_2(vfp_touizh, i32, f16, fpst) +DEF_HELPER_2(vfp_touizs, i32, f32, fpst) +DEF_HELPER_2(vfp_touizd, i32, f64, fpst) +DEF_HELPER_2(vfp_tosih, s32, f16, fpst) +DEF_HELPER_2(vfp_tosis, s32, f32, fpst) +DEF_HELPER_2(vfp_tosid, s32, f64, fpst) +DEF_HELPER_2(vfp_tosizh, s32, f16, fpst) +DEF_HELPER_2(vfp_tosizs, s32, f32, fpst) +DEF_HELPER_2(vfp_tosizd, s32, f64, fpst) -DEF_HELPER_3(vfp_toshh_round_to_zero, i32, f16, i32, ptr) -DEF_HELPER_3(vfp_toslh_round_to_zero, i32, f16, i32, ptr) -DEF_HELPER_3(vfp_touhh_round_to_zero, i32, f16, i32, ptr) -DEF_HELPER_3(vfp_toulh_round_to_zero, i32, f16, i32, ptr) -DEF_HELPER_3(vfp_toshs_round_to_zero, i32, f32, i32, ptr) -DEF_HELPER_3(vfp_tosls_round_to_zero, i32, f32, i32, ptr) -DEF_HELPER_3(vfp_touhs_round_to_zero, i32, f32, i32, ptr) -DEF_HELPER_3(vfp_touls_round_to_zero, i32, f32, i32, ptr) -DEF_HELPER_3(vfp_toshd_round_to_zero, i64, f64, i32, ptr) -DEF_HELPER_3(vfp_tosld_round_to_zero, i64, f64, i32, ptr) -DEF_HELPER_3(vfp_tosqd_round_to_zero, i64, f64, i32, ptr) -DEF_HELPER_3(vfp_touhd_round_to_zero, i64, f64, i32, ptr) -DEF_HELPER_3(vfp_tould_round_to_zero, i64, f64, i32, ptr) -DEF_HELPER_3(vfp_touqd_round_to_zero, i64, f64, i32, ptr) -DEF_HELPER_3(vfp_touhh, i32, f16, i32, ptr) -DEF_HELPER_3(vfp_toshh, i32, f16, i32, ptr) -DEF_HELPER_3(vfp_toulh, i32, f16, i32, ptr) -DEF_HELPER_3(vfp_toslh, i32, f16, i32, ptr) -DEF_HELPER_3(vfp_touqh, i64, f16, i32, ptr) -DEF_HELPER_3(vfp_tosqh, i64, f16, i32, ptr) -DEF_HELPER_3(vfp_toshs, i32, f32, i32, ptr) -DEF_HELPER_3(vfp_tosls, i32, f32, i32, ptr) -DEF_HELPER_3(vfp_tosqs, i64, f32, i32, ptr) -DEF_HELPER_3(vfp_touhs, i32, f32, i32, ptr) -DEF_HELPER_3(vfp_touls, i32, f32, i32, ptr) -DEF_HELPER_3(vfp_touqs, i64, f32, i32, ptr) -DEF_HELPER_3(vfp_toshd, i64, f64, i32, ptr) -DEF_HELPER_3(vfp_tosld, i64, f64, i32, ptr) -DEF_HELPER_3(vfp_tosqd, i64, f64, i32, ptr) -DEF_HELPER_3(vfp_touhd, i64, f64, i32, ptr) -DEF_HELPER_3(vfp_tould, i64, f64, i32, ptr) -DEF_HELPER_3(vfp_touqd, i64, f64, i32, ptr) -DEF_HELPER_3(vfp_shtos, f32, i32, i32, ptr) -DEF_HELPER_3(vfp_sltos, f32, i32, i32, ptr) -DEF_HELPER_3(vfp_sqtos, f32, i64, i32, ptr) -DEF_HELPER_3(vfp_uhtos, f32, i32, i32, ptr) -DEF_HELPER_3(vfp_ultos, f32, i32, i32, ptr) -DEF_HELPER_3(vfp_uqtos, f32, i64, i32, ptr) -DEF_HELPER_3(vfp_shtod, f64, i64, i32, ptr) -DEF_HELPER_3(vfp_sltod, f64, i64, i32, ptr) -DEF_HELPER_3(vfp_sqtod, f64, i64, i32, ptr) -DEF_HELPER_3(vfp_uhtod, f64, i64, i32, ptr) -DEF_HELPER_3(vfp_ultod, f64, i64, i32, ptr) -DEF_HELPER_3(vfp_uqtod, f64, i64, i32, ptr) -DEF_HELPER_3(vfp_shtoh, f16, i32, i32, ptr) -DEF_HELPER_3(vfp_uhtoh, f16, i32, i32, ptr) -DEF_HELPER_3(vfp_sltoh, f16, i32, i32, ptr) -DEF_HELPER_3(vfp_ultoh, f16, i32, i32, ptr) -DEF_HELPER_3(vfp_sqtoh, f16, i64, i32, ptr) -DEF_HELPER_3(vfp_uqtoh, f16, i64, i32, ptr) +DEF_HELPER_3(vfp_toshh_round_to_zero, i32, f16, i32, fpst) +DEF_HELPER_3(vfp_toslh_round_to_zero, i32, f16, i32, fpst) +DEF_HELPER_3(vfp_touhh_round_to_zero, i32, f16, i32, fpst) +DEF_HELPER_3(vfp_toulh_round_to_zero, i32, f16, i32, fpst) +DEF_HELPER_3(vfp_toshs_round_to_zero, i32, f32, i32, fpst) +DEF_HELPER_3(vfp_tosls_round_to_zero, i32, f32, i32, fpst) +DEF_HELPER_3(vfp_touhs_round_to_zero, i32, f32, i32, fpst) +DEF_HELPER_3(vfp_touls_round_to_zero, i32, f32, i32, fpst) +DEF_HELPER_3(vfp_toshd_round_to_zero, i64, f64, i32, fpst) +DEF_HELPER_3(vfp_tosld_round_to_zero, i64, f64, i32, fpst) +DEF_HELPER_3(vfp_tosqd_round_to_zero, i64, f64, i32, fpst) +DEF_HELPER_3(vfp_touhd_round_to_zero, i64, f64, i32, fpst) +DEF_HELPER_3(vfp_tould_round_to_zero, i64, f64, i32, fpst) +DEF_HELPER_3(vfp_touqd_round_to_zero, i64, f64, i32, fpst) +DEF_HELPER_3(vfp_touhh, i32, f16, i32, fpst) +DEF_HELPER_3(vfp_toshh, i32, f16, i32, fpst) +DEF_HELPER_3(vfp_toulh, i32, f16, i32, fpst) +DEF_HELPER_3(vfp_toslh, i32, f16, i32, fpst) +DEF_HELPER_3(vfp_touqh, i64, f16, i32, fpst) +DEF_HELPER_3(vfp_tosqh, i64, f16, i32, fpst) +DEF_HELPER_3(vfp_toshs, i32, f32, i32, fpst) +DEF_HELPER_3(vfp_tosls, i32, f32, i32, fpst) +DEF_HELPER_3(vfp_tosqs, i64, f32, i32, fpst) +DEF_HELPER_3(vfp_touhs, i32, f32, i32, fpst) +DEF_HELPER_3(vfp_touls, i32, f32, i32, fpst) +DEF_HELPER_3(vfp_touqs, i64, f32, i32, fpst) +DEF_HELPER_3(vfp_toshd, i64, f64, i32, fpst) +DEF_HELPER_3(vfp_tosld, i64, f64, i32, fpst) +DEF_HELPER_3(vfp_tosqd, i64, f64, i32, fpst) +DEF_HELPER_3(vfp_touhd, i64, f64, i32, fpst) +DEF_HELPER_3(vfp_tould, i64, f64, i32, fpst) +DEF_HELPER_3(vfp_touqd, i64, f64, i32, fpst) +DEF_HELPER_3(vfp_shtos, f32, i32, i32, fpst) +DEF_HELPER_3(vfp_sltos, f32, i32, i32, fpst) +DEF_HELPER_3(vfp_sqtos, f32, i64, i32, fpst) +DEF_HELPER_3(vfp_uhtos, f32, i32, i32, fpst) +DEF_HELPER_3(vfp_ultos, f32, i32, i32, fpst) +DEF_HELPER_3(vfp_uqtos, f32, i64, i32, fpst) +DEF_HELPER_3(vfp_shtod, f64, i64, i32, fpst) +DEF_HELPER_3(vfp_sltod, f64, i64, i32, fpst) +DEF_HELPER_3(vfp_sqtod, f64, i64, i32, fpst) +DEF_HELPER_3(vfp_uhtod, f64, i64, i32, fpst) +DEF_HELPER_3(vfp_ultod, f64, i64, i32, fpst) +DEF_HELPER_3(vfp_uqtod, f64, i64, i32, fpst) +DEF_HELPER_3(vfp_shtoh, f16, i32, i32, fpst) +DEF_HELPER_3(vfp_uhtoh, f16, i32, i32, fpst) +DEF_HELPER_3(vfp_sltoh, f16, i32, i32, fpst) +DEF_HELPER_3(vfp_ultoh, f16, i32, i32, fpst) +DEF_HELPER_3(vfp_sqtoh, f16, i64, i32, fpst) +DEF_HELPER_3(vfp_uqtoh, f16, i64, i32, fpst) -DEF_HELPER_3(vfp_shtos_round_to_nearest, f32, i32, i32, ptr) -DEF_HELPER_3(vfp_sltos_round_to_nearest, f32, i32, i32, ptr) -DEF_HELPER_3(vfp_uhtos_round_to_nearest, f32, i32, i32, ptr) -DEF_HELPER_3(vfp_ultos_round_to_nearest, f32, i32, i32, ptr) -DEF_HELPER_3(vfp_shtod_round_to_nearest, f64, i64, i32, ptr) -DEF_HELPER_3(vfp_sltod_round_to_nearest, f64, i64, i32, ptr) -DEF_HELPER_3(vfp_uhtod_round_to_nearest, f64, i64, i32, ptr) -DEF_HELPER_3(vfp_ultod_round_to_nearest, f64, i64, i32, ptr) -DEF_HELPER_3(vfp_shtoh_round_to_nearest, f16, i32, i32, ptr) -DEF_HELPER_3(vfp_uhtoh_round_to_nearest, f16, i32, i32, ptr) -DEF_HELPER_3(vfp_sltoh_round_to_nearest, f16, i32, i32, ptr) -DEF_HELPER_3(vfp_ultoh_round_to_nearest, f16, i32, i32, ptr) +DEF_HELPER_3(vfp_shtos_round_to_nearest, f32, i32, i32, fpst) +DEF_HELPER_3(vfp_sltos_round_to_nearest, f32, i32, i32, fpst) +DEF_HELPER_3(vfp_uhtos_round_to_nearest, f32, i32, i32, fpst) +DEF_HELPER_3(vfp_ultos_round_to_nearest, f32, i32, i32, fpst) +DEF_HELPER_3(vfp_shtod_round_to_nearest, f64, i64, i32, fpst) +DEF_HELPER_3(vfp_sltod_round_to_nearest, f64, i64, i32, fpst) +DEF_HELPER_3(vfp_uhtod_round_to_nearest, f64, i64, i32, fpst) +DEF_HELPER_3(vfp_ultod_round_to_nearest, f64, i64, i32, fpst) +DEF_HELPER_3(vfp_shtoh_round_to_nearest, f16, i32, i32, fpst) +DEF_HELPER_3(vfp_uhtoh_round_to_nearest, f16, i32, i32, fpst) +DEF_HELPER_3(vfp_sltoh_round_to_nearest, f16, i32, i32, fpst) +DEF_HELPER_3(vfp_ultoh_round_to_nearest, f16, i32, i32, fpst) -DEF_HELPER_FLAGS_2(set_rmode, TCG_CALL_NO_RWG, i32, i32, ptr) +DEF_HELPER_FLAGS_2(set_rmode, TCG_CALL_NO_RWG, i32, i32, fpst) -DEF_HELPER_FLAGS_3(vfp_fcvt_f16_to_f32, TCG_CALL_NO_RWG, f32, f16, ptr, i32) -DEF_HELPER_FLAGS_3(vfp_fcvt_f32_to_f16, TCG_CALL_NO_RWG, f16, f32, ptr, i32) -DEF_HELPER_FLAGS_3(vfp_fcvt_f16_to_f64, TCG_CALL_NO_RWG, f64, f16, ptr, i32) -DEF_HELPER_FLAGS_3(vfp_fcvt_f64_to_f16, TCG_CALL_NO_RWG, f16, f64, ptr, i32) +DEF_HELPER_FLAGS_3(vfp_fcvt_f16_to_f32, TCG_CALL_NO_RWG, f32, f16, fpst, i32) +DEF_HELPER_FLAGS_3(vfp_fcvt_f32_to_f16, TCG_CALL_NO_RWG, f16, f32, fpst, i32) +DEF_HELPER_FLAGS_3(vfp_fcvt_f16_to_f64, TCG_CALL_NO_RWG, f64, f16, fpst, i32) +DEF_HELPER_FLAGS_3(vfp_fcvt_f64_to_f16, TCG_CALL_NO_RWG, f16, f64, fpst, i32) -DEF_HELPER_4(vfp_muladdd, f64, f64, f64, f64, ptr) -DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, ptr) -DEF_HELPER_4(vfp_muladdh, f16, f16, f16, f16, ptr) +DEF_HELPER_4(vfp_muladdd, f64, f64, f64, f64, fpst) +DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, fpst) +DEF_HELPER_4(vfp_muladdh, f16, f16, f16, f16, fpst) -DEF_HELPER_FLAGS_2(recpe_f16, TCG_CALL_NO_RWG, f16, f16, ptr) -DEF_HELPER_FLAGS_2(recpe_f32, TCG_CALL_NO_RWG, f32, f32, ptr) -DEF_HELPER_FLAGS_2(recpe_f64, TCG_CALL_NO_RWG, f64, f64, ptr) -DEF_HELPER_FLAGS_2(rsqrte_f16, TCG_CALL_NO_RWG, f16, f16, ptr) -DEF_HELPER_FLAGS_2(rsqrte_f32, TCG_CALL_NO_RWG, f32, f32, ptr) -DEF_HELPER_FLAGS_2(rsqrte_f64, TCG_CALL_NO_RWG, f64, f64, ptr) +DEF_HELPER_FLAGS_2(recpe_f16, TCG_CALL_NO_RWG, f16, f16, fpst) +DEF_HELPER_FLAGS_2(recpe_f32, TCG_CALL_NO_RWG, f32, f32, fpst) +DEF_HELPER_FLAGS_2(recpe_f64, TCG_CALL_NO_RWG, f64, f64, fpst) +DEF_HELPER_FLAGS_2(rsqrte_f16, TCG_CALL_NO_RWG, f16, f16, fpst) +DEF_HELPER_FLAGS_2(rsqrte_f32, TCG_CALL_NO_RWG, f32, f32, fpst) +DEF_HELPER_FLAGS_2(rsqrte_f64, TCG_CALL_NO_RWG, f64, f64, fpst) DEF_HELPER_FLAGS_1(recpe_u32, TCG_CALL_NO_RWG, i32, i32) DEF_HELPER_FLAGS_1(rsqrte_u32, TCG_CALL_NO_RWG, i32, i32) DEF_HELPER_FLAGS_4(neon_tbl, TCG_CALL_NO_RWG, i64, env, i32, i64, i64) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(shr_cc, i32, env, i32, i32) DEF_HELPER_3(sar_cc, i32, env, i32, i32) DEF_HELPER_3(ror_cc, i32, env, i32, i32) -DEF_HELPER_FLAGS_2(rinth_exact, TCG_CALL_NO_RWG, f16, f16, ptr) -DEF_HELPER_FLAGS_2(rints_exact, TCG_CALL_NO_RWG, f32, f32, ptr) -DEF_HELPER_FLAGS_2(rintd_exact, TCG_CALL_NO_RWG, f64, f64, ptr) -DEF_HELPER_FLAGS_2(rinth, TCG_CALL_NO_RWG, f16, f16, ptr) -DEF_HELPER_FLAGS_2(rints, TCG_CALL_NO_RWG, f32, f32, ptr) -DEF_HELPER_FLAGS_2(rintd, TCG_CALL_NO_RWG, f64, f64, ptr) +DEF_HELPER_FLAGS_2(rinth_exact, TCG_CALL_NO_RWG, f16, f16, fpst) +DEF_HELPER_FLAGS_2(rints_exact, TCG_CALL_NO_RWG, f32, f32, fpst) +DEF_HELPER_FLAGS_2(rintd_exact, TCG_CALL_NO_RWG, f64, f64, fpst) +DEF_HELPER_FLAGS_2(rinth, TCG_CALL_NO_RWG, f16, f16, fpst) +DEF_HELPER_FLAGS_2(rints, TCG_CALL_NO_RWG, f32, f32, fpst) +DEF_HELPER_FLAGS_2(rintd, TCG_CALL_NO_RWG, f64, f64, fpst) DEF_HELPER_FLAGS_2(vjcvt, TCG_CALL_NO_RWG, i32, f64, env) -DEF_HELPER_FLAGS_2(fjcvtzs, TCG_CALL_NO_RWG, i64, f64, ptr) +DEF_HELPER_FLAGS_2(fjcvtzs, TCG_CALL_NO_RWG, i64, f64, fpst) DEF_HELPER_FLAGS_3(check_hcr_el2_trap, TCG_CALL_NO_WG, void, env, i32, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fmlal_idx_a32, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_fmlal_idx_a64, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_2(frint32_s, TCG_CALL_NO_RWG, f32, f32, ptr) -DEF_HELPER_FLAGS_2(frint64_s, TCG_CALL_NO_RWG, f32, f32, ptr) -DEF_HELPER_FLAGS_2(frint32_d, TCG_CALL_NO_RWG, f64, f64, ptr) -DEF_HELPER_FLAGS_2(frint64_d, TCG_CALL_NO_RWG, f64, f64, ptr) +DEF_HELPER_FLAGS_2(frint32_s, TCG_CALL_NO_RWG, f32, f32, fpst) +DEF_HELPER_FLAGS_2(frint64_s, TCG_CALL_NO_RWG, f32, f32, fpst) +DEF_HELPER_FLAGS_2(frint32_d, TCG_CALL_NO_RWG, f64, f64, fpst) +DEF_HELPER_FLAGS_2(frint64_d, TCG_CALL_NO_RWG, f64, f64, fpst) DEF_HELPER_FLAGS_3(gvec_ceq0_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_ceq0_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val) #define VFP_HELPER(name, p) HELPER(glue(glue(vfp_,name),p)) #define VFP_BINOP(name) \ -dh_ctype_f16 VFP_HELPER(name, h)(dh_ctype_f16 a, dh_ctype_f16 b, void *fpstp) \ +dh_ctype_f16 VFP_HELPER(name, h)(dh_ctype_f16 a, dh_ctype_f16 b, float_status *fpst) \ { \ - float_status *fpst = fpstp; \ return float16_ ## name(a, b, fpst); \ } \ -float32 VFP_HELPER(name, s)(float32 a, float32 b, void *fpstp) \ +float32 VFP_HELPER(name, s)(float32 a, float32 b, float_status *fpst) \ { \ - float_status *fpst = fpstp; \ return float32_ ## name(a, b, fpst); \ } \ -float64 VFP_HELPER(name, d)(float64 a, float64 b, void *fpstp) \ +float64 VFP_HELPER(name, d)(float64 a, float64 b, float_status *fpst) \ { \ - float_status *fpst = fpstp; \ return float64_ ## name(a, b, fpst); \ } VFP_BINOP(add) @@ -XXX,XX +XXX,XX @@ VFP_BINOP(minnum) VFP_BINOP(maxnum) #undef VFP_BINOP -dh_ctype_f16 VFP_HELPER(sqrt, h)(dh_ctype_f16 a, void *fpstp) +dh_ctype_f16 VFP_HELPER(sqrt, h)(dh_ctype_f16 a, float_status *fpst) { - return float16_sqrt(a, fpstp); + return float16_sqrt(a, fpst); } -float32 VFP_HELPER(sqrt, s)(float32 a, void *fpstp) +float32 VFP_HELPER(sqrt, s)(float32 a, float_status *fpst) { - return float32_sqrt(a, fpstp); + return float32_sqrt(a, fpst); } -float64 VFP_HELPER(sqrt, d)(float64 a, void *fpstp) +float64 VFP_HELPER(sqrt, d)(float64 a, float_status *fpst) { - return float64_sqrt(a, fpstp); + return float64_sqrt(a, fpst); } static void softfloat_to_vfp_compare(CPUARMState *env, FloatRelation cmp) @@ -XXX,XX +XXX,XX @@ DO_VFP_cmp(d, float64, float64, fp_status) /* Integer to float and float to integer conversions */ #define CONV_ITOF(name, ftype, fsz, sign) \ -ftype HELPER(name)(uint32_t x, void *fpstp) \ +ftype HELPER(name)(uint32_t x, float_status *fpst) \ { \ - float_status *fpst = fpstp; \ return sign##int32_to_##float##fsz((sign##int32_t)x, fpst); \ } #define CONV_FTOI(name, ftype, fsz, sign, round) \ -sign##int32_t HELPER(name)(ftype x, void *fpstp) \ +sign##int32_t HELPER(name)(ftype x, float_status *fpst) \ { \ - float_status *fpst = fpstp; \ if (float##fsz##_is_any_nan(x)) { \ float_raise(float_flag_invalid, fpst); \ return 0; \ @@ -XXX,XX +XXX,XX @@ float32 VFP_HELPER(fcvts, d)(float64 x, CPUARMState *env) return float64_to_float32(x, &env->vfp.fp_status); } -uint32_t HELPER(bfcvt)(float32 x, void *status) +uint32_t HELPER(bfcvt)(float32 x, float_status *status) { return float32_to_bfloat16(x, status); } -uint32_t HELPER(bfcvt_pair)(uint64_t pair, void *status) +uint32_t HELPER(bfcvt_pair)(uint64_t pair, float_status *status) { bfloat16 lo = float32_to_bfloat16(extract64(pair, 0, 32), status); bfloat16 hi = float32_to_bfloat16(extract64(pair, 32, 32), status); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(bfcvt_pair)(uint64_t pair, void *status) */ #define VFP_CONV_FIX_FLOAT(name, p, fsz, ftype, isz, itype) \ ftype HELPER(vfp_##name##to##p)(uint##isz##_t x, uint32_t shift, \ - void *fpstp) \ -{ return itype##_to_##float##fsz##_scalbn(x, -shift, fpstp); } + float_status *fpst) \ +{ return itype##_to_##float##fsz##_scalbn(x, -shift, fpst); } #define VFP_CONV_FIX_FLOAT_ROUND(name, p, fsz, ftype, isz, itype) \ ftype HELPER(vfp_##name##to##p##_round_to_nearest)(uint##isz##_t x, \ uint32_t shift, \ - void *fpstp) \ + float_status *fpst) \ { \ ftype ret; \ - float_status *fpst = fpstp; \ FloatRoundMode oldmode = fpst->float_rounding_mode; \ fpst->float_rounding_mode = float_round_nearest_even; \ - ret = itype##_to_##float##fsz##_scalbn(x, -shift, fpstp); \ + ret = itype##_to_##float##fsz##_scalbn(x, -shift, fpst); \ fpst->float_rounding_mode = oldmode; \ return ret; \ } #define VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, ROUND, suff) \ uint##isz##_t HELPER(vfp_to##name##p##suff)(ftype x, uint32_t shift, \ - void *fpst) \ + float_status *fpst) \ { \ if (unlikely(float##fsz##_is_any_nan(x))) { \ float_raise(float_flag_invalid, fpst); \ @@ -XXX,XX +XXX,XX @@ VFP_CONV_FLOAT_FIX_ROUND(uq, d, 64, float64, 64, uint64, /* Set the current fp rounding mode and return the old one. * The argument is a softfloat float_round_ value. */ -uint32_t HELPER(set_rmode)(uint32_t rmode, void *fpstp) +uint32_t HELPER(set_rmode)(uint32_t rmode, float_status *fp_status) { - float_status *fp_status = fpstp; - uint32_t prev_rmode = get_float_rounding_mode(fp_status); set_float_rounding_mode(rmode, fp_status); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(set_rmode)(uint32_t rmode, void *fpstp) } /* Half precision conversions. */ -float32 HELPER(vfp_fcvt_f16_to_f32)(uint32_t a, void *fpstp, uint32_t ahp_mode) +float32 HELPER(vfp_fcvt_f16_to_f32)(uint32_t a, float_status *fpst, + uint32_t ahp_mode) { /* Squash FZ16 to 0 for the duration of conversion. In this case, * it would affect flushing input denormals. */ - float_status *fpst = fpstp; bool save = get_flush_inputs_to_zero(fpst); set_flush_inputs_to_zero(false, fpst); float32 r = float16_to_float32(a, !ahp_mode, fpst); @@ -XXX,XX +XXX,XX @@ float32 HELPER(vfp_fcvt_f16_to_f32)(uint32_t a, void *fpstp, uint32_t ahp_mode) return r; } -uint32_t HELPER(vfp_fcvt_f32_to_f16)(float32 a, void *fpstp, uint32_t ahp_mode) +uint32_t HELPER(vfp_fcvt_f32_to_f16)(float32 a, float_status *fpst, + uint32_t ahp_mode) { /* Squash FZ16 to 0 for the duration of conversion. In this case, * it would affect flushing output denormals. */ - float_status *fpst = fpstp; bool save = get_flush_to_zero(fpst); set_flush_to_zero(false, fpst); float16 r = float32_to_float16(a, !ahp_mode, fpst); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(vfp_fcvt_f32_to_f16)(float32 a, void *fpstp, uint32_t ahp_mode) return r; } -float64 HELPER(vfp_fcvt_f16_to_f64)(uint32_t a, void *fpstp, uint32_t ahp_mode) +float64 HELPER(vfp_fcvt_f16_to_f64)(uint32_t a, float_status *fpst, + uint32_t ahp_mode) { /* Squash FZ16 to 0 for the duration of conversion. In this case, * it would affect flushing input denormals. */ - float_status *fpst = fpstp; bool save = get_flush_inputs_to_zero(fpst); set_flush_inputs_to_zero(false, fpst); float64 r = float16_to_float64(a, !ahp_mode, fpst); @@ -XXX,XX +XXX,XX @@ float64 HELPER(vfp_fcvt_f16_to_f64)(uint32_t a, void *fpstp, uint32_t ahp_mode) return r; } -uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode) +uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, float_status *fpst, + uint32_t ahp_mode) { /* Squash FZ16 to 0 for the duration of conversion. In this case, * it would affect flushing output denormals. */ - float_status *fpst = fpstp; bool save = get_flush_to_zero(fpst); set_flush_to_zero(false, fpst); float16 r = float64_to_float16(a, !ahp_mode, fpst); @@ -XXX,XX +XXX,XX @@ static bool round_to_inf(float_status *fpst, bool sign_bit) } } -uint32_t HELPER(recpe_f16)(uint32_t input, void *fpstp) +uint32_t HELPER(recpe_f16)(uint32_t input, float_status *fpst) { - float_status *fpst = fpstp; float16 f16 = float16_squash_input_denormal(input, fpst); uint32_t f16_val = float16_val(f16); uint32_t f16_sign = float16_is_neg(f16); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(recpe_f16)(uint32_t input, void *fpstp) return make_float16(f16_val); } -float32 HELPER(recpe_f32)(float32 input, void *fpstp) +float32 HELPER(recpe_f32)(float32 input, float_status *fpst) { - float_status *fpst = fpstp; float32 f32 = float32_squash_input_denormal(input, fpst); uint32_t f32_val = float32_val(f32); bool f32_sign = float32_is_neg(f32); @@ -XXX,XX +XXX,XX @@ float32 HELPER(recpe_f32)(float32 input, void *fpstp) return make_float32(f32_val); } -float64 HELPER(recpe_f64)(float64 input, void *fpstp) +float64 HELPER(recpe_f64)(float64 input, float_status *fpst) { - float_status *fpst = fpstp; float64 f64 = float64_squash_input_denormal(input, fpst); uint64_t f64_val = float64_val(f64); bool f64_sign = float64_is_neg(f64); @@ -XXX,XX +XXX,XX @@ static uint64_t recip_sqrt_estimate(int *exp , int exp_off, uint64_t frac) return extract64(estimate, 0, 8) << 44; } -uint32_t HELPER(rsqrte_f16)(uint32_t input, void *fpstp) +uint32_t HELPER(rsqrte_f16)(uint32_t input, float_status *s) { - float_status *s = fpstp; float16 f16 = float16_squash_input_denormal(input, s); uint16_t val = float16_val(f16); bool f16_sign = float16_is_neg(f16); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(rsqrte_f16)(uint32_t input, void *fpstp) if (float16_is_signaling_nan(f16, s)) { float_raise(float_flag_invalid, s); if (!s->default_nan_mode) { - nan = float16_silence_nan(f16, fpstp); + nan = float16_silence_nan(f16, s); } } if (s->default_nan_mode) { @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(rsqrte_f16)(uint32_t input, void *fpstp) return make_float16(val); } -float32 HELPER(rsqrte_f32)(float32 input, void *fpstp) +float32 HELPER(rsqrte_f32)(float32 input, float_status *s) { - float_status *s = fpstp; float32 f32 = float32_squash_input_denormal(input, s); uint32_t val = float32_val(f32); uint32_t f32_sign = float32_is_neg(f32); @@ -XXX,XX +XXX,XX @@ float32 HELPER(rsqrte_f32)(float32 input, void *fpstp) if (float32_is_signaling_nan(f32, s)) { float_raise(float_flag_invalid, s); if (!s->default_nan_mode) { - nan = float32_silence_nan(f32, fpstp); + nan = float32_silence_nan(f32, s); } } if (s->default_nan_mode) { @@ -XXX,XX +XXX,XX @@ float32 HELPER(rsqrte_f32)(float32 input, void *fpstp) return make_float32(val); } -float64 HELPER(rsqrte_f64)(float64 input, void *fpstp) +float64 HELPER(rsqrte_f64)(float64 input, float_status *s) { - float_status *s = fpstp; float64 f64 = float64_squash_input_denormal(input, s); uint64_t val = float64_val(f64); bool f64_sign = float64_is_neg(f64); @@ -XXX,XX +XXX,XX @@ float64 HELPER(rsqrte_f64)(float64 input, void *fpstp) if (float64_is_signaling_nan(f64, s)) { float_raise(float_flag_invalid, s); if (!s->default_nan_mode) { - nan = float64_silence_nan(f64, fpstp); + nan = float64_silence_nan(f64, s); } } if (s->default_nan_mode) { @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(rsqrte_u32)(uint32_t a) /* VFPv4 fused multiply-accumulate */ dh_ctype_f16 VFP_HELPER(muladd, h)(dh_ctype_f16 a, dh_ctype_f16 b, - dh_ctype_f16 c, void *fpstp) + dh_ctype_f16 c, float_status *fpst) { - float_status *fpst = fpstp; return float16_muladd(a, b, c, 0, fpst); } -float32 VFP_HELPER(muladd, s)(float32 a, float32 b, float32 c, void *fpstp) +float32 VFP_HELPER(muladd, s)(float32 a, float32 b, float32 c, + float_status *fpst) { - float_status *fpst = fpstp; return float32_muladd(a, b, c, 0, fpst); } -float64 VFP_HELPER(muladd, d)(float64 a, float64 b, float64 c, void *fpstp) +float64 VFP_HELPER(muladd, d)(float64 a, float64 b, float64 c, + float_status *fpst) { - float_status *fpst = fpstp; return float64_muladd(a, b, c, 0, fpst); } /* ARMv8 round to integral */ -dh_ctype_f16 HELPER(rinth_exact)(dh_ctype_f16 x, void *fp_status) +dh_ctype_f16 HELPER(rinth_exact)(dh_ctype_f16 x, float_status *fp_status) { return float16_round_to_int(x, fp_status); } -float32 HELPER(rints_exact)(float32 x, void *fp_status) +float32 HELPER(rints_exact)(float32 x, float_status *fp_status) { return float32_round_to_int(x, fp_status); } -float64 HELPER(rintd_exact)(float64 x, void *fp_status) +float64 HELPER(rintd_exact)(float64 x, float_status *fp_status) { return float64_round_to_int(x, fp_status); } -dh_ctype_f16 HELPER(rinth)(dh_ctype_f16 x, void *fp_status) +dh_ctype_f16 HELPER(rinth)(dh_ctype_f16 x, float_status *fp_status) { int old_flags = get_float_exception_flags(fp_status), new_flags; float16 ret; @@ -XXX,XX +XXX,XX @@ dh_ctype_f16 HELPER(rinth)(dh_ctype_f16 x, void *fp_status) return ret; } -float32 HELPER(rints)(float32 x, void *fp_status) +float32 HELPER(rints)(float32 x, float_status *fp_status) { int old_flags = get_float_exception_flags(fp_status), new_flags; float32 ret; @@ -XXX,XX +XXX,XX @@ float32 HELPER(rints)(float32 x, void *fp_status) return ret; } -float64 HELPER(rintd)(float64 x, void *fp_status) +float64 HELPER(rintd)(float64 x, float_status *fp_status) { int old_flags = get_float_exception_flags(fp_status), new_flags; float64 ret; @@ -XXX,XX +XXX,XX @@ const FloatRoundMode arm_rmode_to_sf_map[] = { * Implement float64 to int32_t conversion without saturation; * the result is supplied modulo 2^32. */ -uint64_t HELPER(fjcvtzs)(float64 value, void *vstatus) +uint64_t HELPER(fjcvtzs)(float64 value, float_status *status) { - float_status *status = vstatus; uint32_t frac, e_old, e_new; bool inexact; @@ -XXX,XX +XXX,XX @@ static float32 frint_s(float32 f, float_status *fpst, int intsize) return (0x100u + 126u + intsize) << 23; } -float32 HELPER(frint32_s)(float32 f, void *fpst) +float32 HELPER(frint32_s)(float32 f, float_status *fpst) { return frint_s(f, fpst, 32); } -float32 HELPER(frint64_s)(float32 f, void *fpst) +float32 HELPER(frint64_s)(float32 f, float_status *fpst) { return frint_s(f, fpst, 64); } @@ -XXX,XX +XXX,XX @@ static float64 frint_d(float64 f, float_status *fpst, int intsize) return (uint64_t)(0x800 + 1022 + intsize) << 52; } -float64 HELPER(frint32_d)(float64 f, void *fpst) +float64 HELPER(frint32_d)(float64 f, float_status *fpst) { return frint_d(f, fpst, 32); } -float64 HELPER(frint64_d)(float64 f, void *fpst) +float64 HELPER(frint64_d)(float64 f, float_status *fpst) { return frint_d(f, fpst, 64); } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241206031224.78525-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-a64.h | 94 +++++++++++++++++------------------ target/arm/tcg/helper-a64.c | 98 +++++++++++++------------------------ 2 files changed, 80 insertions(+), 112 deletions(-) diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(msr_i_spsel, void, env, i32) DEF_HELPER_2(msr_i_daifset, void, env, i32) DEF_HELPER_2(msr_i_daifclear, void, env, i32) DEF_HELPER_1(msr_set_allint_el1, void, env) -DEF_HELPER_3(vfp_cmph_a64, i64, f16, f16, ptr) -DEF_HELPER_3(vfp_cmpeh_a64, i64, f16, f16, ptr) -DEF_HELPER_3(vfp_cmps_a64, i64, f32, f32, ptr) -DEF_HELPER_3(vfp_cmpes_a64, i64, f32, f32, ptr) -DEF_HELPER_3(vfp_cmpd_a64, i64, f64, f64, ptr) -DEF_HELPER_3(vfp_cmped_a64, i64, f64, f64, ptr) +DEF_HELPER_3(vfp_cmph_a64, i64, f16, f16, fpst) +DEF_HELPER_3(vfp_cmpeh_a64, i64, f16, f16, fpst) +DEF_HELPER_3(vfp_cmps_a64, i64, f32, f32, fpst) +DEF_HELPER_3(vfp_cmpes_a64, i64, f32, f32, fpst) +DEF_HELPER_3(vfp_cmpd_a64, i64, f64, f64, fpst) +DEF_HELPER_3(vfp_cmped_a64, i64, f64, f64, fpst) DEF_HELPER_FLAGS_4(simd_tblx, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_3(vfp_mulxs, TCG_CALL_NO_RWG, f32, f32, f32, ptr) -DEF_HELPER_FLAGS_3(vfp_mulxd, TCG_CALL_NO_RWG, f64, f64, f64, ptr) -DEF_HELPER_FLAGS_3(neon_ceq_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr) -DEF_HELPER_FLAGS_3(neon_cge_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr) -DEF_HELPER_FLAGS_3(neon_cgt_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr) -DEF_HELPER_FLAGS_3(recpsf_f16, TCG_CALL_NO_RWG, f16, f16, f16, ptr) -DEF_HELPER_FLAGS_3(recpsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, ptr) -DEF_HELPER_FLAGS_3(recpsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr) -DEF_HELPER_FLAGS_3(rsqrtsf_f16, TCG_CALL_NO_RWG, f16, f16, f16, ptr) -DEF_HELPER_FLAGS_3(rsqrtsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, ptr) -DEF_HELPER_FLAGS_3(rsqrtsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr) -DEF_HELPER_FLAGS_2(frecpx_f64, TCG_CALL_NO_RWG, f64, f64, ptr) -DEF_HELPER_FLAGS_2(frecpx_f32, TCG_CALL_NO_RWG, f32, f32, ptr) -DEF_HELPER_FLAGS_2(frecpx_f16, TCG_CALL_NO_RWG, f16, f16, ptr) +DEF_HELPER_FLAGS_3(vfp_mulxs, TCG_CALL_NO_RWG, f32, f32, f32, fpst) +DEF_HELPER_FLAGS_3(vfp_mulxd, TCG_CALL_NO_RWG, f64, f64, f64, fpst) +DEF_HELPER_FLAGS_3(neon_ceq_f64, TCG_CALL_NO_RWG, i64, i64, i64, fpst) +DEF_HELPER_FLAGS_3(neon_cge_f64, TCG_CALL_NO_RWG, i64, i64, i64, fpst) +DEF_HELPER_FLAGS_3(neon_cgt_f64, TCG_CALL_NO_RWG, i64, i64, i64, fpst) +DEF_HELPER_FLAGS_3(recpsf_f16, TCG_CALL_NO_RWG, f16, f16, f16, fpst) +DEF_HELPER_FLAGS_3(recpsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, fpst) +DEF_HELPER_FLAGS_3(recpsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, fpst) +DEF_HELPER_FLAGS_3(rsqrtsf_f16, TCG_CALL_NO_RWG, f16, f16, f16, fpst) +DEF_HELPER_FLAGS_3(rsqrtsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, fpst) +DEF_HELPER_FLAGS_3(rsqrtsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, fpst) +DEF_HELPER_FLAGS_2(frecpx_f64, TCG_CALL_NO_RWG, f64, f64, fpst) +DEF_HELPER_FLAGS_2(frecpx_f32, TCG_CALL_NO_RWG, f32, f32, fpst) +DEF_HELPER_FLAGS_2(frecpx_f16, TCG_CALL_NO_RWG, f16, f16, fpst) DEF_HELPER_FLAGS_2(fcvtx_f64_to_f32, TCG_CALL_NO_RWG, f32, f64, env) DEF_HELPER_FLAGS_3(crc32_64, TCG_CALL_NO_RWG_SE, i64, i64, i64, i32) DEF_HELPER_FLAGS_3(crc32c_64, TCG_CALL_NO_RWG_SE, i64, i64, i64, i32) -DEF_HELPER_FLAGS_3(advsimd_maxh, TCG_CALL_NO_RWG, f16, f16, f16, ptr) -DEF_HELPER_FLAGS_3(advsimd_minh, TCG_CALL_NO_RWG, f16, f16, f16, ptr) -DEF_HELPER_FLAGS_3(advsimd_maxnumh, TCG_CALL_NO_RWG, f16, f16, f16, ptr) -DEF_HELPER_FLAGS_3(advsimd_minnumh, TCG_CALL_NO_RWG, f16, f16, f16, ptr) -DEF_HELPER_3(advsimd_addh, f16, f16, f16, ptr) -DEF_HELPER_3(advsimd_subh, f16, f16, f16, ptr) -DEF_HELPER_3(advsimd_mulh, f16, f16, f16, ptr) -DEF_HELPER_3(advsimd_divh, f16, f16, f16, ptr) -DEF_HELPER_3(advsimd_ceq_f16, i32, f16, f16, ptr) -DEF_HELPER_3(advsimd_cge_f16, i32, f16, f16, ptr) -DEF_HELPER_3(advsimd_cgt_f16, i32, f16, f16, ptr) -DEF_HELPER_3(advsimd_acge_f16, i32, f16, f16, ptr) -DEF_HELPER_3(advsimd_acgt_f16, i32, f16, f16, ptr) -DEF_HELPER_3(advsimd_mulxh, f16, f16, f16, ptr) -DEF_HELPER_4(advsimd_muladdh, f16, f16, f16, f16, ptr) -DEF_HELPER_3(advsimd_add2h, i32, i32, i32, ptr) -DEF_HELPER_3(advsimd_sub2h, i32, i32, i32, ptr) -DEF_HELPER_3(advsimd_mul2h, i32, i32, i32, ptr) -DEF_HELPER_3(advsimd_div2h, i32, i32, i32, ptr) -DEF_HELPER_3(advsimd_max2h, i32, i32, i32, ptr) -DEF_HELPER_3(advsimd_min2h, i32, i32, i32, ptr) -DEF_HELPER_3(advsimd_maxnum2h, i32, i32, i32, ptr) -DEF_HELPER_3(advsimd_minnum2h, i32, i32, i32, ptr) -DEF_HELPER_3(advsimd_mulx2h, i32, i32, i32, ptr) -DEF_HELPER_4(advsimd_muladd2h, i32, i32, i32, i32, ptr) -DEF_HELPER_2(advsimd_rinth_exact, f16, f16, ptr) -DEF_HELPER_2(advsimd_rinth, f16, f16, ptr) +DEF_HELPER_FLAGS_3(advsimd_maxh, TCG_CALL_NO_RWG, f16, f16, f16, fpst) +DEF_HELPER_FLAGS_3(advsimd_minh, TCG_CALL_NO_RWG, f16, f16, f16, fpst) +DEF_HELPER_FLAGS_3(advsimd_maxnumh, TCG_CALL_NO_RWG, f16, f16, f16, fpst) +DEF_HELPER_FLAGS_3(advsimd_minnumh, TCG_CALL_NO_RWG, f16, f16, f16, fpst) +DEF_HELPER_3(advsimd_addh, f16, f16, f16, fpst) +DEF_HELPER_3(advsimd_subh, f16, f16, f16, fpst) +DEF_HELPER_3(advsimd_mulh, f16, f16, f16, fpst) +DEF_HELPER_3(advsimd_divh, f16, f16, f16, fpst) +DEF_HELPER_3(advsimd_ceq_f16, i32, f16, f16, fpst) +DEF_HELPER_3(advsimd_cge_f16, i32, f16, f16, fpst) +DEF_HELPER_3(advsimd_cgt_f16, i32, f16, f16, fpst) +DEF_HELPER_3(advsimd_acge_f16, i32, f16, f16, fpst) +DEF_HELPER_3(advsimd_acgt_f16, i32, f16, f16, fpst) +DEF_HELPER_3(advsimd_mulxh, f16, f16, f16, fpst) +DEF_HELPER_4(advsimd_muladdh, f16, f16, f16, f16, fpst) +DEF_HELPER_3(advsimd_add2h, i32, i32, i32, fpst) +DEF_HELPER_3(advsimd_sub2h, i32, i32, i32, fpst) +DEF_HELPER_3(advsimd_mul2h, i32, i32, i32, fpst) +DEF_HELPER_3(advsimd_div2h, i32, i32, i32, fpst) +DEF_HELPER_3(advsimd_max2h, i32, i32, i32, fpst) +DEF_HELPER_3(advsimd_min2h, i32, i32, i32, fpst) +DEF_HELPER_3(advsimd_maxnum2h, i32, i32, i32, fpst) +DEF_HELPER_3(advsimd_minnum2h, i32, i32, i32, fpst) +DEF_HELPER_3(advsimd_mulx2h, i32, i32, i32, fpst) +DEF_HELPER_4(advsimd_muladd2h, i32, i32, i32, i32, fpst) +DEF_HELPER_2(advsimd_rinth_exact, f16, f16, fpst) +DEF_HELPER_2(advsimd_rinth, f16, f16, fpst) DEF_HELPER_2(exception_return, void, env, i64) DEF_HELPER_FLAGS_2(dc_zva, TCG_CALL_NO_WG, void, env, i64) diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t float_rel_to_flags(int res) return flags; } -uint64_t HELPER(vfp_cmph_a64)(uint32_t x, uint32_t y, void *fp_status) +uint64_t HELPER(vfp_cmph_a64)(uint32_t x, uint32_t y, float_status *fp_status) { return float_rel_to_flags(float16_compare_quiet(x, y, fp_status)); } -uint64_t HELPER(vfp_cmpeh_a64)(uint32_t x, uint32_t y, void *fp_status) +uint64_t HELPER(vfp_cmpeh_a64)(uint32_t x, uint32_t y, float_status *fp_status) { return float_rel_to_flags(float16_compare(x, y, fp_status)); } -uint64_t HELPER(vfp_cmps_a64)(float32 x, float32 y, void *fp_status) +uint64_t HELPER(vfp_cmps_a64)(float32 x, float32 y, float_status *fp_status) { return float_rel_to_flags(float32_compare_quiet(x, y, fp_status)); } -uint64_t HELPER(vfp_cmpes_a64)(float32 x, float32 y, void *fp_status) +uint64_t HELPER(vfp_cmpes_a64)(float32 x, float32 y, float_status *fp_status) { return float_rel_to_flags(float32_compare(x, y, fp_status)); } -uint64_t HELPER(vfp_cmpd_a64)(float64 x, float64 y, void *fp_status) +uint64_t HELPER(vfp_cmpd_a64)(float64 x, float64 y, float_status *fp_status) { return float_rel_to_flags(float64_compare_quiet(x, y, fp_status)); } -uint64_t HELPER(vfp_cmped_a64)(float64 x, float64 y, void *fp_status) +uint64_t HELPER(vfp_cmped_a64)(float64 x, float64 y, float_status *fp_status) { return float_rel_to_flags(float64_compare(x, y, fp_status)); } -float32 HELPER(vfp_mulxs)(float32 a, float32 b, void *fpstp) +float32 HELPER(vfp_mulxs)(float32 a, float32 b, float_status *fpst) { - float_status *fpst = fpstp; - a = float32_squash_input_denormal(a, fpst); b = float32_squash_input_denormal(b, fpst); @@ -XXX,XX +XXX,XX @@ float32 HELPER(vfp_mulxs)(float32 a, float32 b, void *fpstp) return float32_mul(a, b, fpst); } -float64 HELPER(vfp_mulxd)(float64 a, float64 b, void *fpstp) +float64 HELPER(vfp_mulxd)(float64 a, float64 b, float_status *fpst) { - float_status *fpst = fpstp; - a = float64_squash_input_denormal(a, fpst); b = float64_squash_input_denormal(b, fpst); @@ -XXX,XX +XXX,XX @@ float64 HELPER(vfp_mulxd)(float64 a, float64 b, void *fpstp) } /* 64bit/double versions of the neon float compare functions */ -uint64_t HELPER(neon_ceq_f64)(float64 a, float64 b, void *fpstp) +uint64_t HELPER(neon_ceq_f64)(float64 a, float64 b, float_status *fpst) { - float_status *fpst = fpstp; return -float64_eq_quiet(a, b, fpst); } -uint64_t HELPER(neon_cge_f64)(float64 a, float64 b, void *fpstp) +uint64_t HELPER(neon_cge_f64)(float64 a, float64 b, float_status *fpst) { - float_status *fpst = fpstp; return -float64_le(b, a, fpst); } -uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp) +uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, float_status *fpst) { - float_status *fpst = fpstp; return -float64_lt(b, a, fpst); } @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp) * multiply-add-and-halve. */ -uint32_t HELPER(recpsf_f16)(uint32_t a, uint32_t b, void *fpstp) +uint32_t HELPER(recpsf_f16)(uint32_t a, uint32_t b, float_status *fpst) { - float_status *fpst = fpstp; - a = float16_squash_input_denormal(a, fpst); b = float16_squash_input_denormal(b, fpst); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(recpsf_f16)(uint32_t a, uint32_t b, void *fpstp) return float16_muladd(a, b, float16_two, 0, fpst); } -float32 HELPER(recpsf_f32)(float32 a, float32 b, void *fpstp) +float32 HELPER(recpsf_f32)(float32 a, float32 b, float_status *fpst) { - float_status *fpst = fpstp; - a = float32_squash_input_denormal(a, fpst); b = float32_squash_input_denormal(b, fpst); @@ -XXX,XX +XXX,XX @@ float32 HELPER(recpsf_f32)(float32 a, float32 b, void *fpstp) return float32_muladd(a, b, float32_two, 0, fpst); } -float64 HELPER(recpsf_f64)(float64 a, float64 b, void *fpstp) +float64 HELPER(recpsf_f64)(float64 a, float64 b, float_status *fpst) { - float_status *fpst = fpstp; - a = float64_squash_input_denormal(a, fpst); b = float64_squash_input_denormal(b, fpst); @@ -XXX,XX +XXX,XX @@ float64 HELPER(recpsf_f64)(float64 a, float64 b, void *fpstp) return float64_muladd(a, b, float64_two, 0, fpst); } -uint32_t HELPER(rsqrtsf_f16)(uint32_t a, uint32_t b, void *fpstp) +uint32_t HELPER(rsqrtsf_f16)(uint32_t a, uint32_t b, float_status *fpst) { - float_status *fpst = fpstp; - a = float16_squash_input_denormal(a, fpst); b = float16_squash_input_denormal(b, fpst); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(rsqrtsf_f16)(uint32_t a, uint32_t b, void *fpstp) return float16_muladd(a, b, float16_three, float_muladd_halve_result, fpst); } -float32 HELPER(rsqrtsf_f32)(float32 a, float32 b, void *fpstp) +float32 HELPER(rsqrtsf_f32)(float32 a, float32 b, float_status *fpst) { - float_status *fpst = fpstp; - a = float32_squash_input_denormal(a, fpst); b = float32_squash_input_denormal(b, fpst); @@ -XXX,XX +XXX,XX @@ float32 HELPER(rsqrtsf_f32)(float32 a, float32 b, void *fpstp) return float32_muladd(a, b, float32_three, float_muladd_halve_result, fpst); } -float64 HELPER(rsqrtsf_f64)(float64 a, float64 b, void *fpstp) +float64 HELPER(rsqrtsf_f64)(float64 a, float64 b, float_status *fpst) { - float_status *fpst = fpstp; - a = float64_squash_input_denormal(a, fpst); b = float64_squash_input_denormal(b, fpst); @@ -XXX,XX +XXX,XX @@ float64 HELPER(rsqrtsf_f64)(float64 a, float64 b, void *fpstp) } /* Floating-point reciprocal exponent - see FPRecpX in ARM ARM */ -uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp) +uint32_t HELPER(frecpx_f16)(uint32_t a, float_status *fpst) { - float_status *fpst = fpstp; uint16_t val16, sbit; int16_t exp; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp) } } -float32 HELPER(frecpx_f32)(float32 a, void *fpstp) +float32 HELPER(frecpx_f32)(float32 a, float_status *fpst) { - float_status *fpst = fpstp; uint32_t val32, sbit; int32_t exp; @@ -XXX,XX +XXX,XX @@ float32 HELPER(frecpx_f32)(float32 a, void *fpstp) } } -float64 HELPER(frecpx_f64)(float64 a, void *fpstp) +float64 HELPER(frecpx_f64)(float64 a, float_status *fpst) { - float_status *fpst = fpstp; uint64_t val64, sbit; int64_t exp; @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(crc32c_64)(uint64_t acc, uint64_t val, uint32_t bytes) #define ADVSIMD_HELPER(name, suffix) HELPER(glue(glue(advsimd_, name), suffix)) #define ADVSIMD_HALFOP(name) \ -uint32_t ADVSIMD_HELPER(name, h)(uint32_t a, uint32_t b, void *fpstp) \ +uint32_t ADVSIMD_HELPER(name, h)(uint32_t a, uint32_t b, float_status *fpst) \ { \ - float_status *fpst = fpstp; \ return float16_ ## name(a, b, fpst); \ } @@ -XXX,XX +XXX,XX @@ ADVSIMD_HALFOP(minnum) ADVSIMD_HALFOP(maxnum) #define ADVSIMD_TWOHALFOP(name) \ -uint32_t ADVSIMD_HELPER(name, 2h)(uint32_t two_a, uint32_t two_b, void *fpstp) \ +uint32_t ADVSIMD_HELPER(name, 2h)(uint32_t two_a, uint32_t two_b, \ + float_status *fpst) \ { \ float16 a1, a2, b1, b2; \ uint32_t r1, r2; \ - float_status *fpst = fpstp; \ a1 = extract32(two_a, 0, 16); \ a2 = extract32(two_a, 16, 16); \ b1 = extract32(two_b, 0, 16); \ @@ -XXX,XX +XXX,XX @@ ADVSIMD_TWOHALFOP(minnum) ADVSIMD_TWOHALFOP(maxnum) /* Data processing - scalar floating-point and advanced SIMD */ -static float16 float16_mulx(float16 a, float16 b, void *fpstp) +static float16 float16_mulx(float16 a, float16 b, float_status *fpst) { - float_status *fpst = fpstp; - a = float16_squash_input_denormal(a, fpst); b = float16_squash_input_denormal(b, fpst); @@ -XXX,XX +XXX,XX @@ ADVSIMD_TWOHALFOP(mulx) /* fused multiply-accumulate */ uint32_t HELPER(advsimd_muladdh)(uint32_t a, uint32_t b, uint32_t c, - void *fpstp) + float_status *fpst) { - float_status *fpst = fpstp; return float16_muladd(a, b, c, 0, fpst); } uint32_t HELPER(advsimd_muladd2h)(uint32_t two_a, uint32_t two_b, - uint32_t two_c, void *fpstp) + uint32_t two_c, float_status *fpst) { - float_status *fpst = fpstp; float16 a1, a2, b1, b2, c1, c2; uint32_t r1, r2; a1 = extract32(two_a, 0, 16); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_muladd2h)(uint32_t two_a, uint32_t two_b, #define ADVSIMD_CMPRES(test) (test) ? 0xffff : 0 -uint32_t HELPER(advsimd_ceq_f16)(uint32_t a, uint32_t b, void *fpstp) +uint32_t HELPER(advsimd_ceq_f16)(uint32_t a, uint32_t b, float_status *fpst) { - float_status *fpst = fpstp; int compare = float16_compare_quiet(a, b, fpst); return ADVSIMD_CMPRES(compare == float_relation_equal); } -uint32_t HELPER(advsimd_cge_f16)(uint32_t a, uint32_t b, void *fpstp) +uint32_t HELPER(advsimd_cge_f16)(uint32_t a, uint32_t b, float_status *fpst) { - float_status *fpst = fpstp; int compare = float16_compare(a, b, fpst); return ADVSIMD_CMPRES(compare == float_relation_greater || compare == float_relation_equal); } -uint32_t HELPER(advsimd_cgt_f16)(uint32_t a, uint32_t b, void *fpstp) +uint32_t HELPER(advsimd_cgt_f16)(uint32_t a, uint32_t b, float_status *fpst) { - float_status *fpst = fpstp; int compare = float16_compare(a, b, fpst); return ADVSIMD_CMPRES(compare == float_relation_greater); } -uint32_t HELPER(advsimd_acge_f16)(uint32_t a, uint32_t b, void *fpstp) +uint32_t HELPER(advsimd_acge_f16)(uint32_t a, uint32_t b, float_status *fpst) { - float_status *fpst = fpstp; float16 f0 = float16_abs(a); float16 f1 = float16_abs(b); int compare = float16_compare(f0, f1, fpst); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_acge_f16)(uint32_t a, uint32_t b, void *fpstp) compare == float_relation_equal); } -uint32_t HELPER(advsimd_acgt_f16)(uint32_t a, uint32_t b, void *fpstp) +uint32_t HELPER(advsimd_acgt_f16)(uint32_t a, uint32_t b, float_status *fpst) { - float_status *fpst = fpstp; float16 f0 = float16_abs(a); float16 f1 = float16_abs(b); int compare = float16_compare(f0, f1, fpst); @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(advsimd_acgt_f16)(uint32_t a, uint32_t b, void *fpstp) } /* round to integral */ -uint32_t HELPER(advsimd_rinth_exact)(uint32_t x, void *fp_status) +uint32_t HELPER(advsimd_rinth_exact)(uint32_t x, float_status *fp_status) { return float16_round_to_int(x, fp_status); } -uint32_t HELPER(advsimd_rinth)(uint32_t x, void *fp_status) +uint32_t HELPER(advsimd_rinth)(uint32_t x, float_status *fp_status) { int old_flags = get_float_exception_flags(fp_status), new_flags; float16 ret; -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241206031224.78525-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 284 ++++++++++++++++++------------------ target/arm/tcg/helper-a64.h | 18 +-- target/arm/tcg/helper-sve.h | 12 +- target/arm/tcg/vec_helper.c | 60 ++++---- 4 files changed, 183 insertions(+), 191 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_usdot_idx_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcaddh, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fcadds, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fcaddd, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_fcmlah, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_fcmlah_idx, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_fcmlas, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_fcmlas_idx, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_fcmlad, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_4(gvec_sstoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_sitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_ustoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_uitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_tosszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_tosizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_touszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_touizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sstoh, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_sitos, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_ustoh, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_uitos, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_tosszh, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_tosizs, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_touszh, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_touizs, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_sf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_uf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_rz_fs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_rz_fu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_sf, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_uf, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rz_fs, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rz_fu, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_rz_hs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_rz_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_uh, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rz_hs, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rz_hu, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_sd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_ud, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_rz_ds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_rz_du, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_sd, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_ud, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rz_ds, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rz_du, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ud, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ss, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_rm_us, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_rm_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sd, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ud, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ss, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_us, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sh, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_uh, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_4(gvec_vrint_rm_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vrint_rm_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vrint_rm_h, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vrint_rm_s, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_4(gvec_vrintx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vrintx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vrintx_h, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_vrintx_s, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_4(gvec_frsqrte_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_frsqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_frsqrte_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_frsqrte_h, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_frsqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_frsqrte_d, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_4(gvec_fcgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_fcgt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_fcgt0_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fcgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_fcgt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_fcgt0_d, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_4(gvec_fcge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_fcge0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_fcge0_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fcge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_fcge0_s, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_fcge0_d, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_4(gvec_fceq0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_fceq0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_fceq0_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fceq0_h, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_fceq0_s, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_fceq0_d, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_4(gvec_fcle0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_fcle0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_fcle0_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fcle0_h, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_fcle0_s, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_fcle0_d, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_4(gvec_fclt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_fclt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_fclt0_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fclt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_fclt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_4(gvec_fclt0_d, TCG_CALL_NO_RWG, void, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fsub_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fsub_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fsub_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fsub_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fsub_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fsub_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmul_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmul_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmul_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmul_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fabd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fabd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fceq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fceq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fceq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fceq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fceq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fceq_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fcge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcge_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fcge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fcge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fcge_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fcgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fcgt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fcgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fcgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fcgt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_facge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_facge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_facge_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_facge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_facge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_facge_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_facgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_facgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_facgt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_facgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_facgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_facgt_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmax_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmax_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmax_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmax_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmax_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmax_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmin_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmin_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmin_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmin_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmin_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmin_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmaxnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmaxnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmaxnum_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnum_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fminnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fminnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fminnum_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fminnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fminnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fminnum_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_recps_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_recps_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_recps_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_recps_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmls_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmls_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmls_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmls_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_vfma_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_vfma_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_vfms_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_vfms_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fmul_idx_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fmul_idx_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fmul_idx_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fmla_nf_idx_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fmla_nf_idx_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fmls_nf_idx_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_fmls_nf_idx_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_fmla_idx_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_fmla_idx_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_uqadd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_bfmmla, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_6(gvec_bfmlal, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(gvec_bfmlal_idx, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_sclamp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_uclamp_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_uclamp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_faddp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_faddp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_faddp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_faddp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_faddp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_faddp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmaxp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmaxp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmaxp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fminp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fminp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fminp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fminp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fminp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fminp_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmaxnump_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmaxnump_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmaxnump_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnump_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnump_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnump_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fminnump_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fminnump_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fminnump_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fminnump_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fminnump_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fminnump_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(gvec_addp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_addp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_4(cpyfe, void, env, i32, i32, i32) DEF_HELPER_FLAGS_1(guarded_page_check, TCG_CALL_NO_WG, void, env) DEF_HELPER_FLAGS_2(guarded_page_br, TCG_CALL_NO_RWG, void, env, tl) -DEF_HELPER_FLAGS_5(gvec_fdiv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fdiv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fdiv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fdiv_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fdiv_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fdiv_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmulx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmulx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmulx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmulx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmulx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmulx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(gvec_fmulx_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmulx_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(gvec_fmulx_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmulx_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmulx_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(gvec_fmulx_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_umini_s, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_4(sve_umini_d, TCG_CALL_NO_RWG, void, ptr, ptr, i64, i32) DEF_HELPER_FLAGS_5(gvec_recps_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_recps_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_recps_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_rsqrts_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_rsqrts_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(gvec_rsqrts_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_faddv_h, TCG_CALL_NO_RWG, i64, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -XXX,XX +XXX,XX @@ DO_DOT_IDX(gvec_sdot_idx_h, int64_t, int16_t, int16_t, H8) DO_DOT_IDX(gvec_udot_idx_h, uint64_t, uint16_t, uint16_t, H8) void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm, - void *vfpst, uint32_t desc) + float_status *fpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); float16 *d = vd; float16 *n = vn; float16 *m = vm; - float_status *fpst = vfpst; uint32_t neg_real = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = neg_real ^ 1; uintptr_t i; @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcaddh)(void *vd, void *vn, void *vm, } void HELPER(gvec_fcadds)(void *vd, void *vn, void *vm, - void *vfpst, uint32_t desc) + float_status *fpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); float32 *d = vd; float32 *n = vn; float32 *m = vm; - float_status *fpst = vfpst; uint32_t neg_real = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = neg_real ^ 1; uintptr_t i; @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcadds)(void *vd, void *vn, void *vm, } void HELPER(gvec_fcaddd)(void *vd, void *vn, void *vm, - void *vfpst, uint32_t desc) + float_status *fpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); float64 *d = vd; float64 *n = vn; float64 *m = vm; - float_status *fpst = vfpst; uint64_t neg_real = extract64(desc, SIMD_DATA_SHIFT, 1); uint64_t neg_imag = neg_real ^ 1; uintptr_t i; @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcaddd)(void *vd, void *vn, void *vm, } void HELPER(gvec_fcmlah)(void *vd, void *vn, void *vm, void *va, - void *vfpst, uint32_t desc) + float_status *fpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); float16 *d = vd, *n = vn, *m = vm, *a = va; - float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); uint32_t neg_real = flip ^ neg_imag; @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlah)(void *vd, void *vn, void *vm, void *va, } void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, void *va, - void *vfpst, uint32_t desc) + float_status *fpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); float16 *d = vd, *n = vn, *m = vm, *a = va; - float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 2, 2); @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, void *va, } void HELPER(gvec_fcmlas)(void *vd, void *vn, void *vm, void *va, - void *vfpst, uint32_t desc) + float_status *fpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); float32 *d = vd, *n = vn, *m = vm, *a = va; - float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); uint32_t neg_real = flip ^ neg_imag; @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlas)(void *vd, void *vn, void *vm, void *va, } void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, void *va, - void *vfpst, uint32_t desc) + float_status *fpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); float32 *d = vd, *n = vn, *m = vm, *a = va; - float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint32_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 2, 2); @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, void *va, } void HELPER(gvec_fcmlad)(void *vd, void *vn, void *vm, void *va, - void *vfpst, uint32_t desc) + float_status *fpst, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); float64 *d = vd, *n = vn, *m = vm, *a = va; - float_status *fpst = vfpst; intptr_t flip = extract32(desc, SIMD_DATA_SHIFT, 1); uint64_t neg_imag = extract32(desc, SIMD_DATA_SHIFT + 1, 1); uint64_t neg_real = flip ^ neg_imag; @@ -XXX,XX +XXX,XX @@ static uint64_t float64_acgt(float64 op1, float64 op2, float_status *stat) return -float64_lt(float64_abs(op2), float64_abs(op1), stat); } -static int16_t vfp_tosszh(float16 x, void *fpstp) +static int16_t vfp_tosszh(float16 x, float_status *fpst) { - float_status *fpst = fpstp; if (float16_is_any_nan(x)) { float_raise(float_flag_invalid, fpst); return 0; @@ -XXX,XX +XXX,XX @@ static int16_t vfp_tosszh(float16 x, void *fpstp) return float16_to_int16_round_to_zero(x, fpst); } -static uint16_t vfp_touszh(float16 x, void *fpstp) +static uint16_t vfp_touszh(float16 x, float_status *fpst) { - float_status *fpst = fpstp; if (float16_is_any_nan(x)) { float_raise(float_flag_invalid, fpst); return 0; @@ -XXX,XX +XXX,XX @@ static uint16_t vfp_touszh(float16 x, void *fpstp) } #define DO_2OP(NAME, FUNC, TYPE) \ -void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ +void HELPER(NAME)(void *vd, void *vn, float_status *stat, uint32_t desc) \ { \ intptr_t i, oprsz = simd_oprsz(desc); \ TYPE *d = vd, *n = vn; \ @@ -XXX,XX +XXX,XX @@ static float32 float32_rsqrts_nf(float32 op1, float32 op2, float_status *stat) } #define DO_3OP(NAME, FUNC, TYPE) \ -void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, \ + float_status *stat, uint32_t desc) \ { \ intptr_t i, oprsz = simd_oprsz(desc); \ TYPE *d = vd, *n = vn, *m = vm; \ @@ -XXX,XX +XXX,XX @@ static float64 float64_mulsub_f(float64 dest, float64 op1, float64 op2, return float64_muladd(float64_chs(op1), op2, dest, 0, stat); } -#define DO_MULADD(NAME, FUNC, TYPE) \ -void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ +#define DO_MULADD(NAME, FUNC, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, \ + float_status *stat, uint32_t desc) \ { \ intptr_t i, oprsz = simd_oprsz(desc); \ TYPE *d = vd, *n = vn, *m = vm; \ @@ -XXX,XX +XXX,XX @@ DO_MLA_IDX(gvec_mls_idx_d, uint64_t, -, H8) #undef DO_MLA_IDX #define DO_FMUL_IDX(NAME, ADD, MUL, TYPE, H) \ -void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, \ + float_status *stat, uint32_t desc) \ { \ intptr_t i, j, oprsz = simd_oprsz(desc); \ intptr_t segment = MIN(16, oprsz) / sizeof(TYPE); \ @@ -XXX,XX +XXX,XX @@ DO_FMUL_IDX(gvec_fmls_nf_idx_s, float32_sub, float32_mul, float32, H4) #define DO_FMLA_IDX(NAME, TYPE, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, \ - void *stat, uint32_t desc) \ + float_status *stat, uint32_t desc) \ { \ intptr_t i, j, oprsz = simd_oprsz(desc); \ intptr_t segment = MIN(16, oprsz) / sizeof(TYPE); \ @@ -XXX,XX +XXX,XX @@ DO_ABA(gvec_uaba_d, uint64_t) #undef DO_ABA #define DO_3OP_PAIR(NAME, FUNC, TYPE, H) \ -void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, \ + float_status *stat, uint32_t desc) \ { \ ARMVectorReg scratch; \ intptr_t oprsz = simd_oprsz(desc); \ @@ -XXX,XX +XXX,XX @@ DO_3OP_PAIR(gvec_uminp_s, MIN, uint32_t, H4) #undef DO_3OP_PAIR #define DO_VCVT_FIXED(NAME, FUNC, TYPE) \ - void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ + void HELPER(NAME)(void *vd, void *vn, float_status *stat, uint32_t desc) \ { \ intptr_t i, oprsz = simd_oprsz(desc); \ int shift = simd_data(desc); \ @@ -XXX,XX +XXX,XX @@ DO_VCVT_FIXED(gvec_vcvt_rz_hu, helper_vfp_touhh_round_to_zero, uint16_t) #undef DO_VCVT_FIXED #define DO_VCVT_RMODE(NAME, FUNC, TYPE) \ - void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ + void HELPER(NAME)(void *vd, void *vn, float_status *fpst, uint32_t desc) \ { \ - float_status *fpst = stat; \ intptr_t i, oprsz = simd_oprsz(desc); \ uint32_t rmode = simd_data(desc); \ uint32_t prev_rmode = get_float_rounding_mode(fpst); \ @@ -XXX,XX +XXX,XX @@ DO_VCVT_RMODE(gvec_vcvt_rm_uh, helper_vfp_touhh, uint16_t) #undef DO_VCVT_RMODE #define DO_VRINT_RMODE(NAME, FUNC, TYPE) \ - void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ + void HELPER(NAME)(void *vd, void *vn, float_status *fpst, uint32_t desc) \ { \ - float_status *fpst = stat; \ intptr_t i, oprsz = simd_oprsz(desc); \ uint32_t rmode = simd_data(desc); \ uint32_t prev_rmode = get_float_rounding_mode(fpst); \ @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_bfmmla)(void *vd, void *vn, void *vm, void *va, } void HELPER(gvec_bfmlal)(void *vd, void *vn, void *vm, void *va, - void *stat, uint32_t desc) + float_status *stat, uint32_t desc) { intptr_t i, opr_sz = simd_oprsz(desc); intptr_t sel = simd_data(desc); @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_bfmlal)(void *vd, void *vn, void *vm, void *va, } void HELPER(gvec_bfmlal_idx)(void *vd, void *vn, void *vm, - void *va, void *stat, uint32_t desc) + void *va, float_status *stat, uint32_t desc) { intptr_t i, j, opr_sz = simd_oprsz(desc); intptr_t sel = extract32(desc, SIMD_DATA_SHIFT, 1); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241206031224.78525-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 14 +++++++------- target/arm/tcg/neon_helper.c | 21 +++++++-------------- 2 files changed, 14 insertions(+), 21 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(neon_qneg_s16, TCG_CALL_NO_RWG, i32, env, i32) DEF_HELPER_FLAGS_2(neon_qneg_s32, TCG_CALL_NO_RWG, i32, env, i32) DEF_HELPER_FLAGS_2(neon_qneg_s64, TCG_CALL_NO_RWG, i64, env, i64) -DEF_HELPER_3(neon_ceq_f32, i32, i32, i32, ptr) -DEF_HELPER_3(neon_cge_f32, i32, i32, i32, ptr) -DEF_HELPER_3(neon_cgt_f32, i32, i32, i32, ptr) -DEF_HELPER_3(neon_acge_f32, i32, i32, i32, ptr) -DEF_HELPER_3(neon_acgt_f32, i32, i32, i32, ptr) -DEF_HELPER_3(neon_acge_f64, i64, i64, i64, ptr) -DEF_HELPER_3(neon_acgt_f64, i64, i64, i64, ptr) +DEF_HELPER_3(neon_ceq_f32, i32, i32, i32, fpst) +DEF_HELPER_3(neon_cge_f32, i32, i32, i32, fpst) +DEF_HELPER_3(neon_cgt_f32, i32, i32, i32, fpst) +DEF_HELPER_3(neon_acge_f32, i32, i32, i32, fpst) +DEF_HELPER_3(neon_acgt_f32, i32, i32, i32, fpst) +DEF_HELPER_3(neon_acge_f64, i64, i64, i64, fpst) +DEF_HELPER_3(neon_acgt_f64, i64, i64, i64, fpst) /* iwmmxt_helper.c */ DEF_HELPER_2(iwmmxt_maddsq, i64, i64, i64) diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_qneg_s64)(CPUARMState *env, uint64_t x) * Note that EQ doesn't signal InvalidOp for QNaNs but GE and GT do. * Softfloat routines return 0/1, which we convert to the 0/-1 Neon requires. */ -uint32_t HELPER(neon_ceq_f32)(uint32_t a, uint32_t b, void *fpstp) +uint32_t HELPER(neon_ceq_f32)(uint32_t a, uint32_t b, float_status *fpst) { - float_status *fpst = fpstp; return -float32_eq_quiet(make_float32(a), make_float32(b), fpst); } -uint32_t HELPER(neon_cge_f32)(uint32_t a, uint32_t b, void *fpstp) +uint32_t HELPER(neon_cge_f32)(uint32_t a, uint32_t b, float_status *fpst) { - float_status *fpst = fpstp; return -float32_le(make_float32(b), make_float32(a), fpst); } -uint32_t HELPER(neon_cgt_f32)(uint32_t a, uint32_t b, void *fpstp) +uint32_t HELPER(neon_cgt_f32)(uint32_t a, uint32_t b, float_status *fpst) { - float_status *fpst = fpstp; return -float32_lt(make_float32(b), make_float32(a), fpst); } -uint32_t HELPER(neon_acge_f32)(uint32_t a, uint32_t b, void *fpstp) +uint32_t HELPER(neon_acge_f32)(uint32_t a, uint32_t b, float_status *fpst) { - float_status *fpst = fpstp; float32 f0 = float32_abs(make_float32(a)); float32 f1 = float32_abs(make_float32(b)); return -float32_le(f1, f0, fpst); } -uint32_t HELPER(neon_acgt_f32)(uint32_t a, uint32_t b, void *fpstp) +uint32_t HELPER(neon_acgt_f32)(uint32_t a, uint32_t b, float_status *fpst) { - float_status *fpst = fpstp; float32 f0 = float32_abs(make_float32(a)); float32 f1 = float32_abs(make_float32(b)); return -float32_lt(f1, f0, fpst); } -uint64_t HELPER(neon_acge_f64)(uint64_t a, uint64_t b, void *fpstp) +uint64_t HELPER(neon_acge_f64)(uint64_t a, uint64_t b, float_status *fpst) { - float_status *fpst = fpstp; float64 f0 = float64_abs(make_float64(a)); float64 f1 = float64_abs(make_float64(b)); return -float64_le(f1, f0, fpst); } -uint64_t HELPER(neon_acgt_f64)(uint64_t a, uint64_t b, void *fpstp) +uint64_t HELPER(neon_acgt_f64)(uint64_t a, uint64_t b, float_status *fpst) { - float_status *fpst = fpstp; float64 f0 = float64_abs(make_float64(a)); float64 f1 = float64_abs(make_float64(b)); return -float64_lt(f1, f0, fpst); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241206031224.78525-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sve.h | 414 ++++++++++++++++++------------------ target/arm/tcg/sve_helper.c | 96 +++++---- 2 files changed, 258 insertions(+), 252 deletions(-) diff --git a/target/arm/tcg/helper-sve.h b/target/arm/tcg/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sve.h +++ b/target/arm/tcg/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_rsqrts_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_faddv_h, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_faddv_s, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_faddv_d, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_fmaxnmv_h, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_fmaxnmv_s, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_fmaxnmv_d, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_fminnmv_h, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_fminnmv_s, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_fminnmv_d, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_fmaxv_h, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_fmaxv_s, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_fmaxv_d, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_fminv_h, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_fminv_s, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve_fminv_d, TCG_CALL_NO_RWG, - i64, ptr, ptr, ptr, i32) + i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fadda_h, TCG_CALL_NO_RWG, - i64, i64, ptr, ptr, ptr, i32) + i64, i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fadda_s, TCG_CALL_NO_RWG, - i64, i64, ptr, ptr, ptr, i32) + i64, i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fadda_d, TCG_CALL_NO_RWG, - i64, i64, ptr, ptr, ptr, i32) + i64, i64, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmge0_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmge0_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmge0_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmgt0_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmgt0_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmgt0_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmlt0_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmlt0_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmlt0_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmle0_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmle0_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmle0_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmeq0_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmeq0_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmeq0_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmne0_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmne0_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcmne0_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fadd_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fadd_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fadd_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fsub_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fsub_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fsub_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmul_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmul_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmul_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fdiv_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fdiv_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fdiv_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmin_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmin_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmin_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmax_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmax_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmax_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fminnum_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fminnum_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fminnum_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmaxnum_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmaxnum_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmaxnum_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fabd_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fabd_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fabd_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fscalbn_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fscalbn_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fscalbn_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmulx_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmulx_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmulx_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fadds_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fadds_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fadds_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fsubs_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fsubs_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fsubs_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmuls_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmuls_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmuls_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fsubrs_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fsubrs_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fsubrs_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmaxnms_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmaxnms_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmaxnms_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fminnms_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fminnms_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fminnms_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmaxs_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmaxs_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmaxs_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmins_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmins_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_6(sve_fmins_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, i64, ptr, i32) + void, ptr, ptr, ptr, i64, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvt_sh, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvt_dh, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvt_hs, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvt_ds, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvt_hd, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvt_sd, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_bfcvt, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvtzs_hh, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvtzs_hs, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvtzs_ss, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvtzs_ds, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvtzs_hd, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvtzs_sd, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvtzs_dd, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvtzu_hh, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvtzu_hs, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvtzu_ss, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvtzu_ds, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvtzu_hd, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvtzu_sd, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fcvtzu_dd, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_frint_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_frint_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_frint_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_frintx_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_frintx_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_frintx_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_frecpx_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_frecpx_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_frecpx_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fsqrt_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fsqrt_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_fsqrt_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_scvt_hh, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_scvt_sh, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_scvt_dh, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_scvt_ss, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_scvt_sd, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_scvt_ds, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_scvt_dd, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_ucvt_hh, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_ucvt_sh, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_ucvt_dh, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_ucvt_ss, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_ucvt_sd, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_ucvt_ds, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_ucvt_dd, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmge_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmge_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmge_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmgt_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmgt_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmgt_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmeq_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmeq_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmeq_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmne_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmne_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmne_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmuo_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmuo_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcmuo_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_facge_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_facge_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_facge_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_facgt_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_facgt_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_facgt_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcadd_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcadd_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve_fcadd_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fmla_zpzzz_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fmla_zpzzz_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fmla_zpzzz_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fmls_zpzzz_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fmls_zpzzz_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fmls_zpzzz_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fnmla_zpzzz_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fnmla_zpzzz_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fnmla_zpzzz_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fnmls_zpzzz_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fnmls_zpzzz_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fnmls_zpzzz_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fcmla_zpzzz_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fcmla_zpzzz_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sve_fcmla_zpzzz_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(sve_ftmad_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(sve_ftmad_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(sve_ftmad_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_ftmad_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve_ftmad_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(sve_ftmad_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve2_saddl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_saddl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_xar_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_xar_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve2_fmaxnmp_zpzz_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve2_fmaxnmp_zpzz_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve2_fmaxnmp_zpzz_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve2_fminnmp_zpzz_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve2_fminnmp_zpzz_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve2_fminnmp_zpzz_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve2_fmaxp_zpzz_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve2_fmaxp_zpzz_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve2_fmaxp_zpzz_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve2_fminp_zpzz_h, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve2_fminp_zpzz_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_6(sve2_fminp_zpzz_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve2_eor3, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_bcax, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_zzzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_6(fmmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_6(fmmla_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(fmmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_6(fmmla_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve2_sqrdmlah_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve2_cdot_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_fcvtnt_sh, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve2_fcvtnt_ds, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve_bfcvtnt, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve2_fcvtlt_hs, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_5(sve2_fcvtlt_sd, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, fpst, i32) -DEF_HELPER_FLAGS_5(flogb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(flogb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(flogb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(flogb_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(flogb_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) +DEF_HELPER_FLAGS_5(flogb_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_4(sve2_sqshl_zpzi_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve_helper.c +++ b/target/arm/tcg/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZPZZ_PAIR_D(sve2_sminp_zpzz_d, int64_t, DO_MIN) #define DO_ZPZZ_PAIR_FP(NAME, TYPE, H, OP) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, \ - void *status, uint32_t desc) \ + float_status *status, uint32_t desc) \ { \ intptr_t i, opr_sz = simd_oprsz(desc); \ for (i = 0; i < opr_sz; ) { \ @@ -XXX,XX +XXX,XX @@ static TYPE NAME##_reduce(TYPE *data, float_status *status, uintptr_t n) \ return TYPE##_##FUNC(lo, hi, status); \ } \ } \ -uint64_t HELPER(NAME)(void *vn, void *vg, void *vs, uint32_t desc) \ +uint64_t HELPER(NAME)(void *vn, void *vg, float_status *s, uint32_t desc) \ { \ uintptr_t i, oprsz = simd_oprsz(desc), maxsz = simd_data(desc); \ TYPE data[sizeof(ARMVectorReg) / sizeof(TYPE)]; \ @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(NAME)(void *vn, void *vg, void *vs, uint32_t desc) \ for (; i < maxsz; i += sizeof(TYPE)) { \ *(TYPE *)((void *)data + i) = IDENT; \ } \ - return NAME##_reduce(data, vs, maxsz / sizeof(TYPE)); \ + return NAME##_reduce(data, s, maxsz / sizeof(TYPE)); \ } DO_REDUCE(sve_faddv_h, float16, H1_2, add, float16_zero) @@ -XXX,XX +XXX,XX @@ DO_REDUCE(sve_fmaxv_d, float64, H1_8, max, float64_chs(float64_infinity)) #undef DO_REDUCE uint64_t HELPER(sve_fadda_h)(uint64_t nn, void *vm, void *vg, - void *status, uint32_t desc) + float_status *status, uint32_t desc) { intptr_t i = 0, opr_sz = simd_oprsz(desc); float16 result = nn; @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(sve_fadda_h)(uint64_t nn, void *vm, void *vg, } uint64_t HELPER(sve_fadda_s)(uint64_t nn, void *vm, void *vg, - void *status, uint32_t desc) + float_status *status, uint32_t desc) { intptr_t i = 0, opr_sz = simd_oprsz(desc); float32 result = nn; @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(sve_fadda_s)(uint64_t nn, void *vm, void *vg, } uint64_t HELPER(sve_fadda_d)(uint64_t nn, void *vm, void *vg, - void *status, uint32_t desc) + float_status *status, uint32_t desc) { intptr_t i = 0, opr_sz = simd_oprsz(desc) / 8; uint64_t *m = vm; @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(sve_fadda_d)(uint64_t nn, void *vm, void *vg, */ #define DO_ZPZZ_FP(NAME, TYPE, H, OP) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, \ - void *status, uint32_t desc) \ + float_status *status, uint32_t desc) \ { \ intptr_t i = simd_oprsz(desc); \ uint64_t *g = vg; \ @@ -XXX,XX +XXX,XX @@ DO_ZPZZ_FP(sve_fmulx_d, uint64_t, H1_8, helper_vfp_mulxd) */ #define DO_ZPZS_FP(NAME, TYPE, H, OP) \ void HELPER(NAME)(void *vd, void *vn, void *vg, uint64_t scalar, \ - void *status, uint32_t desc) \ + float_status *status, uint32_t desc) \ { \ intptr_t i = simd_oprsz(desc); \ uint64_t *g = vg; \ @@ -XXX,XX +XXX,XX @@ DO_ZPZS_FP(sve_fmins_d, float64, H1_8, float64_min) * With the extra float_status parameter. */ #define DO_ZPZ_FP(NAME, TYPE, H, OP) \ -void HELPER(NAME)(void *vd, void *vn, void *vg, void *status, uint32_t desc) \ +void HELPER(NAME)(void *vd, void *vn, void *vg, \ + float_status *status, uint32_t desc) \ { \ intptr_t i = simd_oprsz(desc); \ uint64_t *g = vg; \ @@ -XXX,XX +XXX,XX @@ static void do_fmla_zpzzz_h(void *vd, void *vn, void *vm, void *va, void *vg, } void HELPER(sve_fmla_zpzzz_h)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { do_fmla_zpzzz_h(vd, vn, vm, va, vg, status, desc, 0, 0); } void HELPER(sve_fmls_zpzzz_h)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { do_fmla_zpzzz_h(vd, vn, vm, va, vg, status, desc, 0x8000, 0); } void HELPER(sve_fnmla_zpzzz_h)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { do_fmla_zpzzz_h(vd, vn, vm, va, vg, status, desc, 0x8000, 0x8000); } void HELPER(sve_fnmls_zpzzz_h)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { do_fmla_zpzzz_h(vd, vn, vm, va, vg, status, desc, 0, 0x8000); } @@ -XXX,XX +XXX,XX @@ static void do_fmla_zpzzz_s(void *vd, void *vn, void *vm, void *va, void *vg, } void HELPER(sve_fmla_zpzzz_s)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { do_fmla_zpzzz_s(vd, vn, vm, va, vg, status, desc, 0, 0); } void HELPER(sve_fmls_zpzzz_s)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { do_fmla_zpzzz_s(vd, vn, vm, va, vg, status, desc, 0x80000000, 0); } void HELPER(sve_fnmla_zpzzz_s)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { do_fmla_zpzzz_s(vd, vn, vm, va, vg, status, desc, 0x80000000, 0x80000000); } void HELPER(sve_fnmls_zpzzz_s)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { do_fmla_zpzzz_s(vd, vn, vm, va, vg, status, desc, 0, 0x80000000); } @@ -XXX,XX +XXX,XX @@ static void do_fmla_zpzzz_d(void *vd, void *vn, void *vm, void *va, void *vg, } void HELPER(sve_fmla_zpzzz_d)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { do_fmla_zpzzz_d(vd, vn, vm, va, vg, status, desc, 0, 0); } void HELPER(sve_fmls_zpzzz_d)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { do_fmla_zpzzz_d(vd, vn, vm, va, vg, status, desc, INT64_MIN, 0); } void HELPER(sve_fnmla_zpzzz_d)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { do_fmla_zpzzz_d(vd, vn, vm, va, vg, status, desc, INT64_MIN, INT64_MIN); } void HELPER(sve_fnmls_zpzzz_d)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { do_fmla_zpzzz_d(vd, vn, vm, va, vg, status, desc, 0, INT64_MIN); } @@ -XXX,XX +XXX,XX @@ void HELPER(sve_fnmls_zpzzz_d)(void *vd, void *vn, void *vm, void *va, */ #define DO_FPCMP_PPZZ(NAME, TYPE, H, OP) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, \ - void *status, uint32_t desc) \ + float_status *status, uint32_t desc) \ { \ intptr_t i = simd_oprsz(desc), j = (i - 1) >> 6; \ uint64_t *d = vd, *g = vg; \ @@ -XXX,XX +XXX,XX @@ DO_FPCMP_PPZZ_ALL(sve_facgt, DO_FACGT) */ #define DO_FPCMP_PPZ0(NAME, TYPE, H, OP) \ void HELPER(NAME)(void *vd, void *vn, void *vg, \ - void *status, uint32_t desc) \ + float_status *status, uint32_t desc) \ { \ intptr_t i = simd_oprsz(desc), j = (i - 1) >> 6; \ uint64_t *d = vd, *g = vg; \ @@ -XXX,XX +XXX,XX @@ DO_FPCMP_PPZ0_ALL(sve_fcmne0, DO_FCMNE) /* FP Trig Multiply-Add. */ -void HELPER(sve_ftmad_h)(void *vd, void *vn, void *vm, void *vs, uint32_t desc) +void HELPER(sve_ftmad_h)(void *vd, void *vn, void *vm, + float_status *s, uint32_t desc) { static const float16 coeff[16] = { 0x3c00, 0xb155, 0x2030, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, @@ -XXX,XX +XXX,XX @@ void HELPER(sve_ftmad_h)(void *vd, void *vn, void *vm, void *vs, uint32_t desc) mm = float16_abs(mm); xx += 8; } - d[i] = float16_muladd(n[i], mm, coeff[xx], 0, vs); + d[i] = float16_muladd(n[i], mm, coeff[xx], 0, s); } } -void HELPER(sve_ftmad_s)(void *vd, void *vn, void *vm, void *vs, uint32_t desc) +void HELPER(sve_ftmad_s)(void *vd, void *vn, void *vm, + float_status *s, uint32_t desc) { static const float32 coeff[16] = { 0x3f800000, 0xbe2aaaab, 0x3c088886, 0xb95008b9, @@ -XXX,XX +XXX,XX @@ void HELPER(sve_ftmad_s)(void *vd, void *vn, void *vm, void *vs, uint32_t desc) mm = float32_abs(mm); xx += 8; } - d[i] = float32_muladd(n[i], mm, coeff[xx], 0, vs); + d[i] = float32_muladd(n[i], mm, coeff[xx], 0, s); } } -void HELPER(sve_ftmad_d)(void *vd, void *vn, void *vm, void *vs, uint32_t desc) +void HELPER(sve_ftmad_d)(void *vd, void *vn, void *vm, + float_status *s, uint32_t desc) { static const float64 coeff[16] = { 0x3ff0000000000000ull, 0xbfc5555555555543ull, @@ -XXX,XX +XXX,XX @@ void HELPER(sve_ftmad_d)(void *vd, void *vn, void *vm, void *vs, uint32_t desc) mm = float64_abs(mm); xx += 8; } - d[i] = float64_muladd(n[i], mm, coeff[xx], 0, vs); + d[i] = float64_muladd(n[i], mm, coeff[xx], 0, s); } } @@ -XXX,XX +XXX,XX @@ void HELPER(sve_ftmad_d)(void *vd, void *vn, void *vm, void *vs, uint32_t desc) */ void HELPER(sve_fcadd_h)(void *vd, void *vn, void *vm, void *vg, - void *vs, uint32_t desc) + float_status *s, uint32_t desc) { intptr_t j, i = simd_oprsz(desc); uint64_t *g = vg; @@ -XXX,XX +XXX,XX @@ void HELPER(sve_fcadd_h)(void *vd, void *vn, void *vm, void *vg, e3 = *(float16 *)(vm + H1_2(i)) ^ neg_imag; if (likely((pg >> (i & 63)) & 1)) { - *(float16 *)(vd + H1_2(i)) = float16_add(e0, e1, vs); + *(float16 *)(vd + H1_2(i)) = float16_add(e0, e1, s); } if (likely((pg >> (j & 63)) & 1)) { - *(float16 *)(vd + H1_2(j)) = float16_add(e2, e3, vs); + *(float16 *)(vd + H1_2(j)) = float16_add(e2, e3, s); } } while (i & 63); } while (i != 0); } void HELPER(sve_fcadd_s)(void *vd, void *vn, void *vm, void *vg, - void *vs, uint32_t desc) + float_status *s, uint32_t desc) { intptr_t j, i = simd_oprsz(desc); uint64_t *g = vg; @@ -XXX,XX +XXX,XX @@ void HELPER(sve_fcadd_s)(void *vd, void *vn, void *vm, void *vg, e3 = *(float32 *)(vm + H1_2(i)) ^ neg_imag; if (likely((pg >> (i & 63)) & 1)) { - *(float32 *)(vd + H1_2(i)) = float32_add(e0, e1, vs); + *(float32 *)(vd + H1_2(i)) = float32_add(e0, e1, s); } if (likely((pg >> (j & 63)) & 1)) { - *(float32 *)(vd + H1_2(j)) = float32_add(e2, e3, vs); + *(float32 *)(vd + H1_2(j)) = float32_add(e2, e3, s); } } while (i & 63); } while (i != 0); } void HELPER(sve_fcadd_d)(void *vd, void *vn, void *vm, void *vg, - void *vs, uint32_t desc) + float_status *s, uint32_t desc) { intptr_t j, i = simd_oprsz(desc); uint64_t *g = vg; @@ -XXX,XX +XXX,XX @@ void HELPER(sve_fcadd_d)(void *vd, void *vn, void *vm, void *vg, e3 = *(float64 *)(vm + H1_2(i)) ^ neg_imag; if (likely((pg >> (i & 63)) & 1)) { - *(float64 *)(vd + H1_2(i)) = float64_add(e0, e1, vs); + *(float64 *)(vd + H1_2(i)) = float64_add(e0, e1, s); } if (likely((pg >> (j & 63)) & 1)) { - *(float64 *)(vd + H1_2(j)) = float64_add(e2, e3, vs); + *(float64 *)(vd + H1_2(j)) = float64_add(e2, e3, s); } } while (i & 63); } while (i != 0); @@ -XXX,XX +XXX,XX @@ void HELPER(sve_fcadd_d)(void *vd, void *vn, void *vm, void *vg, */ void HELPER(sve_fcmla_zpzzz_h)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { intptr_t j, i = simd_oprsz(desc); unsigned rot = simd_data(desc); @@ -XXX,XX +XXX,XX @@ void HELPER(sve_fcmla_zpzzz_h)(void *vd, void *vn, void *vm, void *va, } void HELPER(sve_fcmla_zpzzz_s)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { intptr_t j, i = simd_oprsz(desc); unsigned rot = simd_data(desc); @@ -XXX,XX +XXX,XX @@ void HELPER(sve_fcmla_zpzzz_s)(void *vd, void *vn, void *vm, void *va, } void HELPER(sve_fcmla_zpzzz_d)(void *vd, void *vn, void *vm, void *va, - void *vg, void *status, uint32_t desc) + void *vg, float_status *status, uint32_t desc) { intptr_t j, i = simd_oprsz(desc); unsigned rot = simd_data(desc); @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_xar_s)(void *vd, void *vn, void *vm, uint32_t desc) } void HELPER(fmmla_s)(void *vd, void *vn, void *vm, void *va, - void *status, uint32_t desc) + float_status *status, uint32_t desc) { intptr_t s, opr_sz = simd_oprsz(desc) / (sizeof(float32) * 4); @@ -XXX,XX +XXX,XX @@ void HELPER(fmmla_s)(void *vd, void *vn, void *vm, void *va, } void HELPER(fmmla_d)(void *vd, void *vn, void *vm, void *va, - void *status, uint32_t desc) + float_status *status, uint32_t desc) { intptr_t s, opr_sz = simd_oprsz(desc) / (sizeof(float64) * 4); @@ -XXX,XX +XXX,XX @@ void HELPER(fmmla_d)(void *vd, void *vn, void *vm, void *va, } #define DO_FCVTNT(NAME, TYPEW, TYPEN, HW, HN, OP) \ -void HELPER(NAME)(void *vd, void *vn, void *vg, void *status, uint32_t desc) \ +void HELPER(NAME)(void *vd, void *vn, void *vg, \ + float_status *status, uint32_t desc) \ { \ intptr_t i = simd_oprsz(desc); \ uint64_t *g = vg; \ @@ -XXX,XX +XXX,XX @@ DO_FCVTNT(sve2_fcvtnt_sh, uint32_t, uint16_t, H1_4, H1_2, sve_f32_to_f16) DO_FCVTNT(sve2_fcvtnt_ds, uint64_t, uint32_t, H1_8, H1_4, float64_to_float32) #define DO_FCVTLT(NAME, TYPEW, TYPEN, HW, HN, OP) \ -void HELPER(NAME)(void *vd, void *vn, void *vg, void *status, uint32_t desc) \ +void HELPER(NAME)(void *vd, void *vn, void *vg, \ + float_status *status, uint32_t desc) \ { \ intptr_t i = simd_oprsz(desc); \ uint64_t *g = vg; \ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241206031224.78525-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-sme.h | 4 ++-- target/arm/tcg/sme_helper.c | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/target/arm/tcg/helper-sme.h b/target/arm/tcg/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-sme.h +++ b/target/arm/tcg/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_7(sme_fmopa_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, ptr, fpst, i32) DEF_HELPER_FLAGS_7(sme_bfmopa, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_6(sme_smopa_s, TCG_CALL_NO_RWG, diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme_helper.c +++ b/target/arm/tcg/sme_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sme_addva_d)(void *vzda, void *vzn, void *vpn, } void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, - void *vpm, void *vst, uint32_t desc) + void *vpm, float_status *fpst_in, uint32_t desc) { intptr_t row, col, oprsz = simd_maxsz(desc); uint32_t neg = simd_data(desc) << 31; @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, * update the cumulative fp exception status. It also produces * default nans. */ - fpst = *(float_status *)vst; + fpst = *fpst_in; set_default_nan_mode(true, &fpst); for (row = 0; row < oprsz; ) { @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, } void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn, - void *vpm, void *vst, uint32_t desc) + void *vpm, float_status *fpst_in, uint32_t desc) { intptr_t row, col, oprsz = simd_oprsz(desc) / 8; uint64_t neg = (uint64_t)simd_data(desc) << 63; uint64_t *za = vza, *zn = vzn, *zm = vzm; uint8_t *pn = vpn, *pm = vpm; - float_status fpst = *(float_status *)vst; + float_status fpst = *fpst_in; set_default_nan_mode(true, &fpst); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Allow the helpers to receive CPUARMState* directly instead of via void*. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241206031224.78525-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 12 ++++++------ target/arm/tcg/helper-a64.h | 2 +- target/arm/tcg/vec_helper.c | 21 +++++++-------------- 3 files changed, 14 insertions(+), 21 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_suqadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmlal_a32, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_5(gvec_fmlal_a64, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_5(gvec_fmlal_idx_a32, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_5(gvec_fmlal_idx_a64, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_2(frint32_s, TCG_CALL_NO_RWG, f32, f32, fpst) DEF_HELPER_FLAGS_2(frint64_s, TCG_CALL_NO_RWG, f32, f32, fpst) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve2_sqrdmulh_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sve2_fmlal_zzzw_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_6(sve2_fmlal_zzxw_s, TCG_CALL_NO_RWG, - void, ptr, ptr, ptr, ptr, ptr, i32) + void, ptr, ptr, ptr, ptr, env, i32) DEF_HELPER_FLAGS_4(gvec_xar_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_cmps_a64, i64, f32, f32, fpst) DEF_HELPER_3(vfp_cmpes_a64, i64, f32, f32, fpst) DEF_HELPER_3(vfp_cmpd_a64, i64, f64, f64, fpst) DEF_HELPER_3(vfp_cmped_a64, i64, f64, f64, fpst) -DEF_HELPER_FLAGS_4(simd_tblx, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(simd_tblx, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) DEF_HELPER_FLAGS_3(vfp_mulxs, TCG_CALL_NO_RWG, f32, f32, f32, fpst) DEF_HELPER_FLAGS_3(vfp_mulxd, TCG_CALL_NO_RWG, f64, f64, f64, fpst) DEF_HELPER_FLAGS_3(neon_ceq_f64, TCG_CALL_NO_RWG, i64, i64, i64, fpst) diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -XXX,XX +XXX,XX @@ static void do_fmlal(float32 *d, void *vn, void *vm, float_status *fpst, } void HELPER(gvec_fmlal_a32)(void *vd, void *vn, void *vm, - void *venv, uint32_t desc) + CPUARMState *env, uint32_t desc) { - CPUARMState *env = venv; do_fmlal(vd, vn, vm, &env->vfp.standard_fp_status, desc, get_flush_inputs_to_zero(&env->vfp.fp_status_f16)); } void HELPER(gvec_fmlal_a64)(void *vd, void *vn, void *vm, - void *venv, uint32_t desc) + CPUARMState *env, uint32_t desc) { - CPUARMState *env = venv; do_fmlal(vd, vn, vm, &env->vfp.fp_status, desc, get_flush_inputs_to_zero(&env->vfp.fp_status_f16)); } void HELPER(sve2_fmlal_zzzw_s)(void *vd, void *vn, void *vm, void *va, - void *venv, uint32_t desc) + CPUARMState *env, uint32_t desc) { intptr_t i, oprsz = simd_oprsz(desc); uint16_t negn = extract32(desc, SIMD_DATA_SHIFT, 1) << 15; intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16); - CPUARMState *env = venv; float_status *status = &env->vfp.fp_status; bool fz16 = get_flush_inputs_to_zero(&env->vfp.fp_status_f16); @@ -XXX,XX +XXX,XX @@ static void do_fmlal_idx(float32 *d, void *vn, void *vm, float_status *fpst, } void HELPER(gvec_fmlal_idx_a32)(void *vd, void *vn, void *vm, - void *venv, uint32_t desc) + CPUARMState *env, uint32_t desc) { - CPUARMState *env = venv; do_fmlal_idx(vd, vn, vm, &env->vfp.standard_fp_status, desc, get_flush_inputs_to_zero(&env->vfp.fp_status_f16)); } void HELPER(gvec_fmlal_idx_a64)(void *vd, void *vn, void *vm, - void *venv, uint32_t desc) + CPUARMState *env, uint32_t desc) { - CPUARMState *env = venv; do_fmlal_idx(vd, vn, vm, &env->vfp.fp_status, desc, get_flush_inputs_to_zero(&env->vfp.fp_status_f16)); } void HELPER(sve2_fmlal_zzxw_s)(void *vd, void *vn, void *vm, void *va, - void *venv, uint32_t desc) + CPUARMState *env, uint32_t desc) { intptr_t i, j, oprsz = simd_oprsz(desc); uint16_t negn = extract32(desc, SIMD_DATA_SHIFT, 1) << 15; intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16); intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 3) * sizeof(float16); - CPUARMState *env = venv; float_status *status = &env->vfp.fp_status; bool fz16 = get_flush_inputs_to_zero(&env->vfp.fp_status_f16); @@ -XXX,XX +XXX,XX @@ DO_VRINT_RMODE(gvec_vrint_rm_s, helper_rints, uint32_t) #undef DO_VRINT_RMODE #ifdef TARGET_AARCH64 -void HELPER(simd_tblx)(void *vd, void *vm, void *venv, uint32_t desc) +void HELPER(simd_tblx)(void *vd, void *vm, CPUARMState *env, uint32_t desc) { const uint8_t *indices = vm; - CPUARMState *env = venv; size_t oprsz = simd_oprsz(desc); uint32_t rn = extract32(desc, SIMD_DATA_SHIFT, 5); bool is_tbx = extract32(desc, SIMD_DATA_SHIFT + 5, 1); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241206031224.78525-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 56 ++++++++++++++++++------------------ target/arm/tcg/neon_helper.c | 6 ++-- 2 files changed, 30 insertions(+), 32 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(neon_qrshl_u32, i32, env, i32, i32) DEF_HELPER_3(neon_qrshl_s32, i32, env, i32, i32) DEF_HELPER_3(neon_qrshl_u64, i64, env, i64, i64) DEF_HELPER_3(neon_qrshl_s64, i64, env, i64, i64) -DEF_HELPER_FLAGS_5(neon_sqshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_sqshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_sqshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_sqshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_uqshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_uqshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_uqshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_uqshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_sqrshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_sqrshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_sqrshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_sqrshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_uqrshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_uqrshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_uqrshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_5(neon_uqrshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(neon_sqshli_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(neon_sqshli_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(neon_sqshli_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(neon_sqshli_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(neon_uqshli_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(neon_uqshli_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(neon_uqshli_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(neon_uqshli_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(neon_sqshlui_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(neon_sqshlui_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(neon_sqshlui_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(neon_sqshlui_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_sqshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_sqshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_sqshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_uqshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_uqshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_uqshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_uqshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_sqrshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_sqrshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_sqrshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_sqrshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_uqrshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_uqrshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_uqrshl_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_5(neon_uqrshl_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(neon_sqshli_b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(neon_sqshli_h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(neon_sqshli_s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(neon_sqshli_d, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(neon_uqshli_b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(neon_uqshli_h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(neon_uqshli_s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(neon_uqshli_d, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(neon_sqshlui_b, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(neon_sqshlui_h, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(neon_sqshlui_s, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) +DEF_HELPER_FLAGS_4(neon_sqshlui_d, TCG_CALL_NO_RWG, void, ptr, ptr, env, i32) DEF_HELPER_FLAGS_4(gvec_srshl_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_srshl_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(name)(void *vd, void *vn, void *vm, uint32_t desc) \ } #define NEON_GVEC_VOP2_ENV(name, vtype) \ -void HELPER(name)(void *vd, void *vn, void *vm, void *venv, uint32_t desc) \ +void HELPER(name)(void *vd, void *vn, void *vm, CPUARMState *env, uint32_t desc) \ { \ intptr_t i, opr_sz = simd_oprsz(desc); \ vtype *d = vd, *n = vn, *m = vm; \ - CPUARMState *env = venv; \ for (i = 0; i < opr_sz / sizeof(vtype); i++) { \ NEON_FN(d[i], n[i], m[i]); \ } \ @@ -XXX,XX +XXX,XX @@ void HELPER(name)(void *vd, void *vn, void *vm, void *venv, uint32_t desc) \ } #define NEON_GVEC_VOP2i_ENV(name, vtype) \ -void HELPER(name)(void *vd, void *vn, void *venv, uint32_t desc) \ +void HELPER(name)(void *vd, void *vn, CPUARMState *env, uint32_t desc) \ { \ intptr_t i, opr_sz = simd_oprsz(desc); \ int imm = simd_data(desc); \ vtype *d = vd, *n = vn; \ - CPUARMState *env = venv; \ for (i = 0; i < opr_sz / sizeof(vtype); i++) { \ NEON_FN(d[i], n[i], imm); \ } \ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Pass float_status not env to match other functions. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241206031952.78776-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-a64.h | 2 +- target/arm/tcg/helper-a64.c | 3 +-- target/arm/tcg/translate-a64.c | 2 +- 3 files changed, 3 insertions(+), 4 deletions(-) diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(rsqrtsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, fpst) DEF_HELPER_FLAGS_2(frecpx_f64, TCG_CALL_NO_RWG, f64, f64, fpst) DEF_HELPER_FLAGS_2(frecpx_f32, TCG_CALL_NO_RWG, f32, f32, fpst) DEF_HELPER_FLAGS_2(frecpx_f16, TCG_CALL_NO_RWG, f16, f16, fpst) -DEF_HELPER_FLAGS_2(fcvtx_f64_to_f32, TCG_CALL_NO_RWG, f32, f64, env) +DEF_HELPER_FLAGS_2(fcvtx_f64_to_f32, TCG_CALL_NO_RWG, f32, f64, fpst) DEF_HELPER_FLAGS_3(crc32_64, TCG_CALL_NO_RWG_SE, i64, i64, i64, i32) DEF_HELPER_FLAGS_3(crc32c_64, TCG_CALL_NO_RWG_SE, i64, i64, i64, i32) DEF_HELPER_FLAGS_3(advsimd_maxh, TCG_CALL_NO_RWG, f16, f16, f16, fpst) diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -XXX,XX +XXX,XX @@ float64 HELPER(frecpx_f64)(float64 a, float_status *fpst) } } -float32 HELPER(fcvtx_f64_to_f32)(float64 a, CPUARMState *env) +float32 HELPER(fcvtx_f64_to_f32)(float64 a, float_status *fpst) { float32 r; - float_status *fpst = &env->vfp.fp_status; int old = get_float_rounding_mode(fpst); set_float_rounding_mode(float_round_to_odd, fpst); diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_fcvtxn_sd(TCGv_i64 d, TCGv_i64 n) * with von Neumann rounding (round to odd) */ TCGv_i32 tmp = tcg_temp_new_i32(); - gen_helper_fcvtx_f64_to_f32(tmp, n, tcg_env); + gen_helper_fcvtx_f64_to_f32(tmp, n, fpstatus_ptr(FPST_FPCR)); tcg_gen_extu_i32_i64(d, tmp); } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Pass float_status not env to match other functions. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241206031952.78776-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 4 ++-- target/arm/tcg/translate-a64.c | 15 ++++++++++----- target/arm/tcg/translate-vfp.c | 4 ++-- target/arm/vfp_helper.c | 8 ++++---- 4 files changed, 18 insertions(+), 13 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_cmpeh, void, f16, f16, env) DEF_HELPER_3(vfp_cmpes, void, f32, f32, env) DEF_HELPER_3(vfp_cmped, void, f64, f64, env) -DEF_HELPER_2(vfp_fcvtds, f64, f32, env) -DEF_HELPER_2(vfp_fcvtsd, f32, f64, env) +DEF_HELPER_2(vfp_fcvtds, f64, f32, fpst) +DEF_HELPER_2(vfp_fcvtsd, f32, f64, fpst) DEF_HELPER_FLAGS_2(bfcvt, TCG_CALL_NO_RWG, i32, f32, fpst) DEF_HELPER_FLAGS_2(bfcvt_pair, TCG_CALL_NO_RWG, i32, i64, fpst) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_FCVT_s_ds(DisasContext *s, arg_rr *a) if (fp_access_check(s)) { TCGv_i32 tcg_rn = read_fp_sreg(s, a->rn); TCGv_i64 tcg_rd = tcg_temp_new_i64(); + TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); - gen_helper_vfp_fcvtds(tcg_rd, tcg_rn, tcg_env); + gen_helper_vfp_fcvtds(tcg_rd, tcg_rn, fpst); write_fp_dreg(s, a->rd, tcg_rd); } return true; @@ -XXX,XX +XXX,XX @@ static bool trans_FCVT_s_sd(DisasContext *s, arg_rr *a) if (fp_access_check(s)) { TCGv_i64 tcg_rn = read_fp_dreg(s, a->rn); TCGv_i32 tcg_rd = tcg_temp_new_i32(); + TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); - gen_helper_vfp_fcvtsd(tcg_rd, tcg_rn, tcg_env); + gen_helper_vfp_fcvtsd(tcg_rd, tcg_rn, fpst); write_fp_sreg(s, a->rd, tcg_rd); } return true; @@ -XXX,XX +XXX,XX @@ static void gen_fcvtn_hs(TCGv_i64 d, TCGv_i64 n) static void gen_fcvtn_sd(TCGv_i64 d, TCGv_i64 n) { TCGv_i32 tmp = tcg_temp_new_i32(); - gen_helper_vfp_fcvtsd(tmp, n, tcg_env); + TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); + + gen_helper_vfp_fcvtsd(tmp, n, fpst); tcg_gen_extu_i32_i64(d, tmp); } @@ -XXX,XX +XXX,XX @@ static bool trans_FCVTL_v(DisasContext *s, arg_qrr_e *a) * The only instruction like this is FCVTL. */ int pass; + TCGv_ptr fpst; if (!fp_access_check(s)) { return true; } + fpst = fpstatus_ptr(FPST_FPCR); if (a->esz == MO_64) { /* 32 -> 64 bit fp conversion */ TCGv_i64 tcg_res[2]; @@ -XXX,XX +XXX,XX @@ static bool trans_FCVTL_v(DisasContext *s, arg_qrr_e *a) for (pass = 0; pass < 2; pass++) { tcg_res[pass] = tcg_temp_new_i64(); read_vec_element_i32(s, tcg_op, a->rn, srcelt + pass, MO_32); - gen_helper_vfp_fcvtds(tcg_res[pass], tcg_op, tcg_env); + gen_helper_vfp_fcvtds(tcg_res[pass], tcg_op, fpst); } for (pass = 0; pass < 2; pass++) { write_vec_element(s, tcg_res[pass], a->rd, pass, MO_64); @@ -XXX,XX +XXX,XX @@ static bool trans_FCVTL_v(DisasContext *s, arg_qrr_e *a) /* 16 -> 32 bit fp conversion */ int srcelt = a->q ? 4 : 0; TCGv_i32 tcg_res[4]; - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); TCGv_i32 ahp = get_ahp_flag(); for (pass = 0; pass < 4; pass++) { diff --git a/target/arm/tcg/translate-vfp.c b/target/arm/tcg/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-vfp.c +++ b/target/arm/tcg/translate-vfp.c @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp(DisasContext *s, arg_VCVT_sp *a) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i64(); vfp_load_reg32(vm, a->vm); - gen_helper_vfp_fcvtds(vd, vm, tcg_env); + gen_helper_vfp_fcvtds(vd, vm, fpstatus_ptr(FPST_FPCR)); vfp_store_reg64(vd, a->vd); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a) vd = tcg_temp_new_i32(); vm = tcg_temp_new_i64(); vfp_load_reg64(vm, a->vm); - gen_helper_vfp_fcvtsd(vd, vm, tcg_env); + gen_helper_vfp_fcvtsd(vd, vm, fpstatus_ptr(FPST_FPCR)); vfp_store_reg32(vd, a->vd); return true; } diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ FLOAT_CONVS(ui, d, float64, 64, u) #undef FLOAT_CONVS /* floating point conversion */ -float64 VFP_HELPER(fcvtd, s)(float32 x, CPUARMState *env) +float64 VFP_HELPER(fcvtd, s)(float32 x, float_status *status) { - return float32_to_float64(x, &env->vfp.fp_status); + return float32_to_float64(x, status); } -float32 VFP_HELPER(fcvts, d)(float64 x, CPUARMState *env) +float32 VFP_HELPER(fcvts, d)(float64 x, float_status *status) { - return float64_to_float32(x, &env->vfp.fp_status); + return float64_to_float32(x, status); } uint32_t HELPER(bfcvt)(float32 x, float_status *status) -- 2.34.1 FEAT_XS introduces a set of new TLBI maintenance instructions with an "nXS" qualifier. These behave like the stardard ones except that they do not wait for memory accesses with the XS attribute to complete. They have an interaction with the fine-grained-trap handling: the FGT bits that a hypervisor can use to trap TLBI maintenance instructions normally trap also the nXS variants, but the hypervisor can elect to not trap the nXS variants by setting HCRX_EL2.FGTnXS to 1. Add support to our FGT mechanism for these TLBI bits. For each TLBI-trapping FGT bit we define, for example: * FGT_TLBIVAE1 -- the same value we do at present for the normal variant of the insn * FGT_TLBIVAE1NXS -- for the nXS qualified insn; the value of this enum has an NXS bit ORed into it In access_check_cp_reg() we can then ignore the trap bit for an access where ri->fgt has the NXS bit set and HCRX_EL2.FGTnXS is 1. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241211144440.2700268-2-peter.maydell@linaro.org --- target/arm/cpregs.h | 72 ++++++++++++++++++++++---------------- target/arm/cpu-features.h | 5 +++ target/arm/helper.c | 5 ++- target/arm/tcg/op_helper.c | 11 +++++- 4 files changed, 61 insertions(+), 32 deletions(-) diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -XXX,XX +XXX,XX @@ FIELD(HDFGWTR_EL2, NBRBCTL, 60, 1) FIELD(HDFGWTR_EL2, NBRBDATA, 61, 1) FIELD(HDFGWTR_EL2, NPMSNEVFR_EL1, 62, 1) +FIELD(FGT, NXS, 13, 1) /* Honour HCR_EL2.FGTnXS to suppress FGT */ /* Which fine-grained trap bit register to check, if any */ FIELD(FGT, TYPE, 10, 3) FIELD(FGT, REV, 9, 1) /* Is bit sense reversed? */ @@ -XXX,XX +XXX,XX @@ FIELD(FGT, BITPOS, 0, 6) /* Bit position within the uint64_t */ #define DO_REV_BIT(REG, BITNAME) \ FGT_##BITNAME = FGT_##REG | FGT_REV | R_##REG##_EL2_##BITNAME##_SHIFT +/* + * The FGT bits for TLBI maintenance instructions accessible at EL1 always + * affect the "normal" TLBI insns; they affect the corresponding TLBI insns + * with the nXS qualifier only if HCRX_EL2.FGTnXS is 0. We define e.g. + * FGT_TLBIVAE1 to use for the normal insn, and FGT_TLBIVAE1NXS to use + * for the nXS qualified insn. + */ +#define DO_TLBINXS_BIT(REG, BITNAME) \ + FGT_##BITNAME = FGT_##REG | R_##REG##_EL2_##BITNAME##_SHIFT, \ + FGT_##BITNAME##NXS = FGT_##BITNAME | R_FGT_NXS_MASK + typedef enum FGTBit { /* * These bits tell us which register arrays to use: @@ -XXX,XX +XXX,XX @@ typedef enum FGTBit { DO_BIT(HFGITR, ATS1E0W), DO_BIT(HFGITR, ATS1E1RP), DO_BIT(HFGITR, ATS1E1WP), - DO_BIT(HFGITR, TLBIVMALLE1OS), - DO_BIT(HFGITR, TLBIVAE1OS), - DO_BIT(HFGITR, TLBIASIDE1OS), - DO_BIT(HFGITR, TLBIVAAE1OS), - DO_BIT(HFGITR, TLBIVALE1OS), - DO_BIT(HFGITR, TLBIVAALE1OS), - DO_BIT(HFGITR, TLBIRVAE1OS), - DO_BIT(HFGITR, TLBIRVAAE1OS), - DO_BIT(HFGITR, TLBIRVALE1OS), - DO_BIT(HFGITR, TLBIRVAALE1OS), - DO_BIT(HFGITR, TLBIVMALLE1IS), - DO_BIT(HFGITR, TLBIVAE1IS), - DO_BIT(HFGITR, TLBIASIDE1IS), - DO_BIT(HFGITR, TLBIVAAE1IS), - DO_BIT(HFGITR, TLBIVALE1IS), - DO_BIT(HFGITR, TLBIVAALE1IS), - DO_BIT(HFGITR, TLBIRVAE1IS), - DO_BIT(HFGITR, TLBIRVAAE1IS), - DO_BIT(HFGITR, TLBIRVALE1IS), - DO_BIT(HFGITR, TLBIRVAALE1IS), - DO_BIT(HFGITR, TLBIRVAE1), - DO_BIT(HFGITR, TLBIRVAAE1), - DO_BIT(HFGITR, TLBIRVALE1), - DO_BIT(HFGITR, TLBIRVAALE1), - DO_BIT(HFGITR, TLBIVMALLE1), - DO_BIT(HFGITR, TLBIVAE1), - DO_BIT(HFGITR, TLBIASIDE1), - DO_BIT(HFGITR, TLBIVAAE1), - DO_BIT(HFGITR, TLBIVALE1), - DO_BIT(HFGITR, TLBIVAALE1), + DO_TLBINXS_BIT(HFGITR, TLBIVMALLE1OS), + DO_TLBINXS_BIT(HFGITR, TLBIVAE1OS), + DO_TLBINXS_BIT(HFGITR, TLBIASIDE1OS), + DO_TLBINXS_BIT(HFGITR, TLBIVAAE1OS), + DO_TLBINXS_BIT(HFGITR, TLBIVALE1OS), + DO_TLBINXS_BIT(HFGITR, TLBIVAALE1OS), + DO_TLBINXS_BIT(HFGITR, TLBIRVAE1OS), + DO_TLBINXS_BIT(HFGITR, TLBIRVAAE1OS), + DO_TLBINXS_BIT(HFGITR, TLBIRVALE1OS), + DO_TLBINXS_BIT(HFGITR, TLBIRVAALE1OS), + DO_TLBINXS_BIT(HFGITR, TLBIVMALLE1IS), + DO_TLBINXS_BIT(HFGITR, TLBIVAE1IS), + DO_TLBINXS_BIT(HFGITR, TLBIASIDE1IS), + DO_TLBINXS_BIT(HFGITR, TLBIVAAE1IS), + DO_TLBINXS_BIT(HFGITR, TLBIVALE1IS), + DO_TLBINXS_BIT(HFGITR, TLBIVAALE1IS), + DO_TLBINXS_BIT(HFGITR, TLBIRVAE1IS), + DO_TLBINXS_BIT(HFGITR, TLBIRVAAE1IS), + DO_TLBINXS_BIT(HFGITR, TLBIRVALE1IS), + DO_TLBINXS_BIT(HFGITR, TLBIRVAALE1IS), + DO_TLBINXS_BIT(HFGITR, TLBIRVAE1), + DO_TLBINXS_BIT(HFGITR, TLBIRVAAE1), + DO_TLBINXS_BIT(HFGITR, TLBIRVALE1), + DO_TLBINXS_BIT(HFGITR, TLBIRVAALE1), + DO_TLBINXS_BIT(HFGITR, TLBIVMALLE1), + DO_TLBINXS_BIT(HFGITR, TLBIVAE1), + DO_TLBINXS_BIT(HFGITR, TLBIASIDE1), + DO_TLBINXS_BIT(HFGITR, TLBIVAAE1), + DO_TLBINXS_BIT(HFGITR, TLBIVALE1), + DO_TLBINXS_BIT(HFGITR, TLBIVAALE1), DO_BIT(HFGITR, CFPRCTX), DO_BIT(HFGITR, DVPRCTX), DO_BIT(HFGITR, CPPRCTX), diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-features.h +++ b/target/arm/cpu-features.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; } +static inline bool isar_feature_aa64_xs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, XS) != 0; +} + /* * These are the values from APA/API/APA3. * In general these must be compared '>=', per the normal Arm ARM diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void hcrx_write(CPUARMState *env, const ARMCPRegInfo *ri, valid_mask |= HCRX_TALLINT | HCRX_VINMI | HCRX_VFNMI; } /* FEAT_CMOW adds CMOW */ - if (cpu_isar_feature(aa64_cmow, cpu)) { valid_mask |= HCRX_CMOW; } + /* FEAT_XS adds FGTnXS, FnXS */ + if (cpu_isar_feature(aa64_xs, cpu)) { + valid_mask |= HCRX_FGTNXS | HCRX_FNXS; + } /* Clear RES0 bits. */ env->cp15.hcrx_el2 = value & valid_mask; diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/op_helper.c +++ b/target/arm/tcg/op_helper.c @@ -XXX,XX +XXX,XX @@ const void *HELPER(access_check_cp_reg)(CPUARMState *env, uint32_t key, unsigned int idx = FIELD_EX32(ri->fgt, FGT, IDX); unsigned int bitpos = FIELD_EX32(ri->fgt, FGT, BITPOS); bool rev = FIELD_EX32(ri->fgt, FGT, REV); + bool nxs = FIELD_EX32(ri->fgt, FGT, NXS); bool trapbit; if (ri->fgt & FGT_EXEC) { @@ -XXX,XX +XXX,XX @@ const void *HELPER(access_check_cp_reg)(CPUARMState *env, uint32_t key, trapword = env->cp15.fgt_write[idx]; } - trapbit = extract64(trapword, bitpos, 1); + if (nxs && (arm_hcrx_el2_eff(env) & HCRX_FGTNXS)) { + /* + * If HCRX_EL2.FGTnXS is 1 then the fine-grained trap for + * TLBI maintenance insns does *not* apply to the nXS variant. + */ + trapbit = 0; + } else { + trapbit = extract64(trapword, bitpos, 1); + } if (trapbit != rev) { res = CP_ACCESS_TRAP_EL2; goto fail; -- 2.34.1 All of the TLBI insns with an NXS variant put that variant at the same encoding but with a CRn field that is one greater than for the original TLBI insn. To avoid having to define every TLBI insn effectively twice, once in the normal way and once in a set of cpreg arrays that are only registered when FEAT_XS is present, we define a new ARM_CP_ADD_TLB_NXS type flag for cpregs. When this flag is set in a cpreg struct and FEAT_XS is present, define_one_arm_cp_reg_with_opaque() will automatically add a second cpreg to the hash table for the TLBI NXS insn with: * the crn+1 encoding * an FGT field that indicates that it should honour HCR_EL2.FGTnXS * a name with the "NXS" suffix (If there are future TLBI NXS insns that don't use this same encoding convention, it is also possible to define them manually.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241211144440.2700268-3-peter.maydell@linaro.org --- target/arm/cpregs.h | 8 ++++++++ target/arm/helper.c | 25 +++++++++++++++++++++++++ 2 files changed, 33 insertions(+) diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -XXX,XX +XXX,XX @@ enum { * equivalent EL1 register when FEAT_NV2 is enabled. */ ARM_CP_NV2_REDIRECT = 1 << 20, + /* + * Flag: this is a TLBI insn which (when FEAT_XS is present) also has + * an NXS variant at the same encoding except that crn is 1 greater, + * so when registering this cpreg automatically also register one + * for the TLBI NXS variant. (For QEMU the NXS variant behaves + * identically to the normal one, other than FGT trapping handling.) + */ + ARM_CP_ADD_TLBI_NXS = 1 << 21, }; /* diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void define_one_arm_cp_reg_with_opaque(ARMCPU *cpu, if (r->state != state && r->state != ARM_CP_STATE_BOTH) { continue; } + if ((r->type & ARM_CP_ADD_TLBI_NXS) && + cpu_isar_feature(aa64_xs, cpu)) { + /* + * This is a TLBI insn which has an NXS variant. The + * NXS variant is at the same encoding except that + * crn is +1, and has the same behaviour except for + * fine-grained trapping. Add the NXS insn here and + * then fall through to add the normal register. + * add_cpreg_to_hashtable() copies the cpreg struct + * and name that it is passed, so it's OK to use + * a local struct here. + */ + ARMCPRegInfo nxs_ri = *r; + g_autofree char *name = g_strdup_printf("%sNXS", r->name); + + assert(state == ARM_CP_STATE_AA64); + assert(nxs_ri.crn < 0xf); + nxs_ri.crn++; + if (nxs_ri.fgt) { + nxs_ri.fgt |= R_FGT_NXS_MASK; + } + add_cpreg_to_hashtable(cpu, &nxs_ri, opaque, state, + ARM_CP_SECSTATE_NS, + crm, opc1, opc2, name); + } if (state == ARM_CP_STATE_AA32) { /* * Under AArch32 CP registers can be common -- 2.34.1 Add the ARM_CP_ADD_TLBI_NXS to the TLBI insns with an NXS variant. This is every AArch64 TLBI encoding except for the four FEAT_RME TLBI insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241211144440.2700268-4-peter.maydell@linaro.org --- target/arm/tcg/tlb-insns.c | 202 +++++++++++++++++++++++-------------- 1 file changed, 124 insertions(+), 78 deletions(-) diff --git a/target/arm/tcg/tlb-insns.c b/target/arm/tcg/tlb-insns.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/tlb-insns.c +++ b/target/arm/tcg/tlb-insns.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo tlbi_v8_cp_reginfo[] = { /* AArch64 TLBI operations */ { .name = "TLBI_VMALLE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 0, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbis, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIVMALLE1IS, .writefn = tlbi_aa64_vmalle1is_write }, { .name = "TLBI_VAE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 1, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbis, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIVAE1IS, .writefn = tlbi_aa64_vae1is_write }, { .name = "TLBI_ASIDE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 2, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbis, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIASIDE1IS, .writefn = tlbi_aa64_vmalle1is_write }, { .name = "TLBI_VAAE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 3, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbis, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIVAAE1IS, .writefn = tlbi_aa64_vae1is_write }, { .name = "TLBI_VALE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 5, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbis, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIVALE1IS, .writefn = tlbi_aa64_vae1is_write }, { .name = "TLBI_VAALE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 7, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbis, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIVAALE1IS, .writefn = tlbi_aa64_vae1is_write }, { .name = "TLBI_VMALLE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 0, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlb, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIVMALLE1, .writefn = tlbi_aa64_vmalle1_write }, { .name = "TLBI_VAE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 1, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlb, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIVAE1, .writefn = tlbi_aa64_vae1_write }, { .name = "TLBI_ASIDE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 2, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlb, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIASIDE1, .writefn = tlbi_aa64_vmalle1_write }, { .name = "TLBI_VAAE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 3, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlb, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIVAAE1, .writefn = tlbi_aa64_vae1_write }, { .name = "TLBI_VALE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 5, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlb, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIVALE1, .writefn = tlbi_aa64_vae1_write }, { .name = "TLBI_VAALE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 7, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlb, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIVAALE1, .writefn = tlbi_aa64_vae1_write }, { .name = "TLBI_IPAS2E1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_ipas2e1is_write }, { .name = "TLBI_IPAS2LE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_ipas2e1is_write }, { .name = "TLBI_ALLE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 4, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_alle1is_write }, { .name = "TLBI_VMALLS12E1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 6, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_alle1is_write }, { .name = "TLBI_IPAS2E1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_ipas2e1_write }, { .name = "TLBI_IPAS2LE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_ipas2e1_write }, { .name = "TLBI_ALLE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 4, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_alle1_write }, { .name = "TLBI_VMALLS12E1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 6, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_alle1is_write }, }; @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo tlbi_el2_cp_reginfo[] = { .writefn = tlbimva_hyp_is_write }, { .name = "TLBI_ALLE2", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 0, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_alle2_write }, { .name = "TLBI_VAE2", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_vae2_write }, { .name = "TLBI_VALE2", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_vae2_write }, { .name = "TLBI_ALLE2IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 0, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_alle2is_write }, { .name = "TLBI_VAE2IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_vae2is_write }, { .name = "TLBI_VALE2IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_vae2is_write }, }; static const ARMCPRegInfo tlbi_el3_cp_reginfo[] = { { .name = "TLBI_ALLE3IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 3, .opc2 = 0, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_alle3is_write }, { .name = "TLBI_VAE3IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 3, .opc2 = 1, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_vae3is_write }, { .name = "TLBI_VALE3IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 3, .opc2 = 5, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_vae3is_write }, { .name = "TLBI_ALLE3", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 7, .opc2 = 0, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_alle3_write }, { .name = "TLBI_VAE3", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 7, .opc2 = 1, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_vae3_write }, { .name = "TLBI_VALE3", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 7, .opc2 = 5, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_vae3_write }, }; @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_ripas2e1is_write(CPUARMState *env, static const ARMCPRegInfo tlbirange_reginfo[] = { { .name = "TLBI_RVAE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 1, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbis, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIRVAE1IS, .writefn = tlbi_aa64_rvae1is_write }, { .name = "TLBI_RVAAE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 3, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbis, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIRVAAE1IS, .writefn = tlbi_aa64_rvae1is_write }, { .name = "TLBI_RVALE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 5, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbis, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIRVALE1IS, .writefn = tlbi_aa64_rvae1is_write }, { .name = "TLBI_RVAALE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 7, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbis, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIRVAALE1IS, .writefn = tlbi_aa64_rvae1is_write }, { .name = "TLBI_RVAE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 1, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbos, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIRVAE1OS, .writefn = tlbi_aa64_rvae1is_write }, { .name = "TLBI_RVAAE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 3, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbos, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIRVAAE1OS, .writefn = tlbi_aa64_rvae1is_write }, { .name = "TLBI_RVALE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 5, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbos, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIRVALE1OS, .writefn = tlbi_aa64_rvae1is_write }, { .name = "TLBI_RVAALE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 7, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbos, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIRVAALE1OS, .writefn = tlbi_aa64_rvae1is_write }, { .name = "TLBI_RVAE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 1, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlb, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIRVAE1, .writefn = tlbi_aa64_rvae1_write }, { .name = "TLBI_RVAAE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 3, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlb, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIRVAAE1, .writefn = tlbi_aa64_rvae1_write }, { .name = "TLBI_RVALE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 5, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlb, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIRVALE1, .writefn = tlbi_aa64_rvae1_write }, { .name = "TLBI_RVAALE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 7, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlb, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIRVAALE1, .writefn = tlbi_aa64_rvae1_write }, { .name = "TLBI_RIPAS2E1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 2, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_ripas2e1is_write }, { .name = "TLBI_RIPAS2LE1IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 6, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_ripas2e1is_write }, { .name = "TLBI_RVAE2IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 2, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_rvae2is_write }, { .name = "TLBI_RVALE2IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 2, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_rvae2is_write }, { .name = "TLBI_RIPAS2E1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 2, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_ripas2e1_write }, { .name = "TLBI_RIPAS2LE1", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 6, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_ripas2e1_write }, { .name = "TLBI_RVAE2OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 5, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_rvae2is_write }, { .name = "TLBI_RVALE2OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 5, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_rvae2is_write }, { .name = "TLBI_RVAE2", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 6, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_rvae2_write }, { .name = "TLBI_RVALE2", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 6, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_rvae2_write }, { .name = "TLBI_RVAE3IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 2, .opc2 = 1, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_rvae3is_write }, { .name = "TLBI_RVALE3IS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 2, .opc2 = 5, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_rvae3is_write }, { .name = "TLBI_RVAE3OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 5, .opc2 = 1, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_rvae3is_write }, { .name = "TLBI_RVALE3OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 5, .opc2 = 5, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_rvae3is_write }, { .name = "TLBI_RVAE3", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 6, .opc2 = 1, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_rvae3_write }, { .name = "TLBI_RVALE3", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 6, .opc2 = 5, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_rvae3_write }, }; static const ARMCPRegInfo tlbios_reginfo[] = { { .name = "TLBI_VMALLE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 0, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbos, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIVMALLE1OS, .writefn = tlbi_aa64_vmalle1is_write }, { .name = "TLBI_VAE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 1, .fgt = FGT_TLBIVAE1OS, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbos, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_vae1is_write }, { .name = "TLBI_ASIDE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 2, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbos, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIASIDE1OS, .writefn = tlbi_aa64_vmalle1is_write }, { .name = "TLBI_VAAE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 3, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbos, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIVAAE1OS, .writefn = tlbi_aa64_vae1is_write }, { .name = "TLBI_VALE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 5, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbos, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIVALE1OS, .writefn = tlbi_aa64_vae1is_write }, { .name = "TLBI_VAALE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 7, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .access = PL1_W, .accessfn = access_ttlbos, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .fgt = FGT_TLBIVAALE1OS, .writefn = tlbi_aa64_vae1is_write }, { .name = "TLBI_ALLE2OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 0, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_alle2is_write }, { .name = "TLBI_VAE2OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_vae2is_write }, { .name = "TLBI_ALLE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 4, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_alle1is_write }, { .name = "TLBI_VALE2OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .access = PL2_W, + .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS | ARM_CP_EL3_NO_EL2_UNDEF, .writefn = tlbi_aa64_vae2is_write }, { .name = "TLBI_VMALLS12E1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 6, - .access = PL2_W, .type = ARM_CP_NO_RAW, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_alle1is_write }, { .name = "TLBI_IPAS2E1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 0, - .access = PL2_W, .type = ARM_CP_NOP }, + .access = PL2_W, .type = ARM_CP_NOP | ARM_CP_ADD_TLBI_NXS }, { .name = "TLBI_RIPAS2E1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 3, - .access = PL2_W, .type = ARM_CP_NOP }, + .access = PL2_W, .type = ARM_CP_NOP | ARM_CP_ADD_TLBI_NXS }, { .name = "TLBI_IPAS2LE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 4, - .access = PL2_W, .type = ARM_CP_NOP }, + .access = PL2_W, .type = ARM_CP_NOP | ARM_CP_ADD_TLBI_NXS }, { .name = "TLBI_RIPAS2LE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 7, - .access = PL2_W, .type = ARM_CP_NOP }, + .access = PL2_W, .type = ARM_CP_NOP | ARM_CP_ADD_TLBI_NXS }, { .name = "TLBI_ALLE3OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 1, .opc2 = 0, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_alle3is_write }, { .name = "TLBI_VAE3OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 1, .opc2 = 1, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_vae3is_write }, { .name = "TLBI_VALE3OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 1, .opc2 = 5, - .access = PL3_W, .type = ARM_CP_NO_RAW, + .access = PL3_W, .type = ARM_CP_NO_RAW | ARM_CP_ADD_TLBI_NXS, .writefn = tlbi_aa64_vae3is_write }, }; -- 2.34.1 From: Manos Pitsidianakis <manos.pitsidianakis@linaro.org> The DSB nXS variant is always both a reads and writes request type. Ignore the domain field like we do in plain DSB and perform a full system barrier operation. The DSB nXS variant is part of FEAT_XS made mandatory from Armv8.7. Signed-off-by: Manos Pitsidianakis <manos.pitsidianakis@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241211144440.2700268-5-peter.maydell@linaro.org [PMM: added missing "UNDEF unless feature present" check] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 3 +++ target/arm/tcg/translate-a64.c | 9 +++++++++ 2 files changed, 12 insertions(+) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ WFIT 1101 0101 0000 0011 0001 0000 001 rd:5 CLREX 1101 0101 0000 0011 0011 ---- 010 11111 DSB_DMB 1101 0101 0000 0011 0011 domain:2 types:2 10- 11111 +# For the DSB nXS variant, types always equals MBReqTypes_All and we ignore the +# domain bits. +DSB_nXS 1101 0101 0000 0011 0011 -- 10 001 11111 ISB 1101 0101 0000 0011 0011 ---- 110 11111 SB 1101 0101 0000 0011 0011 0000 111 11111 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_DSB_DMB(DisasContext *s, arg_DSB_DMB *a) return true; } +static bool trans_DSB_nXS(DisasContext *s, arg_DSB_nXS *a) +{ + if (!dc_isar_feature(aa64_xs, s)) { + return false; + } + tcg_gen_mb(TCG_BAR_SC | TCG_MO_ALL); + return true; +} + static bool trans_ISB(DisasContext *s, arg_ISB *a) { /* -- 2.34.1 From: Manos Pitsidianakis <manos.pitsidianakis@linaro.org> Add FEAT_XS feature report value in max cpu's ID_AA64ISAR1 sys register. Signed-off-by: Manos Pitsidianakis <manos.pitsidianakis@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241211144440.2700268-6-peter.maydell@linaro.org [PMM: Add entry for FEAT_XS to documentation] Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/tcg/cpu64.c | 1 + 2 files changed, 2 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_VMID16 (16-bit VMID) - FEAT_WFxT (WFE and WFI instructions with timeout) - FEAT_XNX (Translation table stage 2 Unprivileged Execute-never) +- FEAT_XS (XS attribute) For information on the specifics of these extensions, please refer to the `Arm Architecture Reference Manual for A-profile architecture diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64ISAR1, BF16, 2); /* FEAT_BF16, FEAT_EBF16 */ t = FIELD_DP64(t, ID_AA64ISAR1, DGH, 1); /* FEAT_DGH */ t = FIELD_DP64(t, ID_AA64ISAR1, I8MM, 1); /* FEAT_I8MM */ + t = FIELD_DP64(t, ID_AA64ISAR1, XS, 1); /* FEAT_XS */ cpu->isar.id_aa64isar1 = t; t = cpu->isar.id_aa64isar2; -- 2.34.1 From: Manos Pitsidianakis <manos.pitsidianakis@linaro.org> Add system test to make sure FEAT_XS is enabled for max cpu emulation and that QEMU doesn't crash when encountering an NXS instruction variant. Signed-off-by: Manos Pitsidianakis <manos.pitsidianakis@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241211144440.2700268-7-peter.maydell@linaro.org [PMM: In ISAR field test, mask with 0xf, not 0xff; use < rather than an equality test to follow the standard ID register field check guidelines] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/tcg/aarch64/system/feat-xs.c | 27 +++++++++++++++++++++++++++ 1 file changed, 27 insertions(+) create mode 100644 tests/tcg/aarch64/system/feat-xs.c diff --git a/tests/tcg/aarch64/system/feat-xs.c b/tests/tcg/aarch64/system/feat-xs.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/tcg/aarch64/system/feat-xs.c @@ -XXX,XX +XXX,XX @@ +/* + * FEAT_XS Test + * + * Copyright (c) 2024 Linaro Ltd + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include <minilib.h> +#include <stdint.h> + +int main(void) +{ + uint64_t isar1; + + asm volatile ("mrs %0, id_aa64isar1_el1" : "=r"(isar1)); + if (((isar1 >> 56) & 0xf) < 1) { + ml_printf("FEAT_XS not supported by CPU"); + return 1; + } + /* VMALLE1NXS */ + asm volatile (".inst 0xd508971f"); + /* VMALLE1OSNXS */ + asm volatile (".inst 0xd508911f"); + + return 0; +} -- 2.34.1 In the GICv3 ITS model, we have a common coding pattern which has a local C struct like "DTEntry dte", which is a C representation of an in-guest-memory data structure, and we call a function such as get_dte() to read guest memory and fill in the C struct. These functions to read in the struct sometimes have cases where they will leave early and not fill in the whole struct (for instance get_dte() will set "dte->valid = false" and nothing else for the case where it is passed an entry_addr implying that there is no L2 table entry for the DTE). This then causes potential use of uninitialized memory later, for instance when we call a trace event which prints all the fields of the struct. Sufficiently advanced compilers may produce -Wmaybe-uninitialized warnings about this, especially if LTO is enabled. Rather than trying to carefully separate out these trace events into "only the 'valid' field is initialized" and "all fields can be printed", zero-init all the structs when we define them. None of these structs are large (the biggest is 24 bytes) and having consistent behaviour is less likely to be buggy. Cc: qemu-stable@nongnu.org Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2718 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241213182337.3343068-1-peter.maydell@linaro.org --- hw/intc/arm_gicv3_its.c | 44 ++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 22 deletions(-) diff --git a/hw/intc/arm_gicv3_its.c b/hw/intc/arm_gicv3_its.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_its.c +++ b/hw/intc/arm_gicv3_its.c @@ -XXX,XX +XXX,XX @@ static ItsCmdResult lookup_vte(GICv3ITSState *s, const char *who, static ItsCmdResult process_its_cmd_phys(GICv3ITSState *s, const ITEntry *ite, int irqlevel) { - CTEntry cte; + CTEntry cte = {}; ItsCmdResult cmdres; cmdres = lookup_cte(s, __func__, ite->icid, &cte); @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_its_cmd_phys(GICv3ITSState *s, const ITEntry *ite, static ItsCmdResult process_its_cmd_virt(GICv3ITSState *s, const ITEntry *ite, int irqlevel) { - VTEntry vte; + VTEntry vte = {}; ItsCmdResult cmdres; cmdres = lookup_vte(s, __func__, ite->vpeid, &vte); @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_its_cmd_virt(GICv3ITSState *s, const ITEntry *ite, static ItsCmdResult do_process_its_cmd(GICv3ITSState *s, uint32_t devid, uint32_t eventid, ItsCmdType cmd) { - DTEntry dte; - ITEntry ite; + DTEntry dte = {}; + ITEntry ite = {}; ItsCmdResult cmdres; int irqlevel; @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_mapti(GICv3ITSState *s, const uint64_t *cmdpkt, uint32_t pIntid = 0; uint64_t num_eventids; uint16_t icid = 0; - DTEntry dte; - ITEntry ite; + DTEntry dte = {}; + ITEntry ite = {}; devid = (cmdpkt[0] & DEVID_MASK) >> DEVID_SHIFT; eventid = cmdpkt[1] & EVENTID_MASK; @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_vmapti(GICv3ITSState *s, const uint64_t *cmdpkt, { uint32_t devid, eventid, vintid, doorbell, vpeid; uint32_t num_eventids; - DTEntry dte; - ITEntry ite; + DTEntry dte = {}; + ITEntry ite = {}; if (!its_feature_virtual(s)) { return CMD_CONTINUE; @@ -XXX,XX +XXX,XX @@ static bool update_cte(GICv3ITSState *s, uint16_t icid, const CTEntry *cte) static ItsCmdResult process_mapc(GICv3ITSState *s, const uint64_t *cmdpkt) { uint16_t icid; - CTEntry cte; + CTEntry cte = {}; icid = cmdpkt[2] & ICID_MASK; cte.valid = cmdpkt[2] & CMD_FIELD_VALID_MASK; @@ -XXX,XX +XXX,XX @@ static bool update_dte(GICv3ITSState *s, uint32_t devid, const DTEntry *dte) static ItsCmdResult process_mapd(GICv3ITSState *s, const uint64_t *cmdpkt) { uint32_t devid; - DTEntry dte; + DTEntry dte = {}; devid = (cmdpkt[0] & DEVID_MASK) >> DEVID_SHIFT; dte.size = cmdpkt[1] & SIZE_MASK; @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_movi(GICv3ITSState *s, const uint64_t *cmdpkt) { uint32_t devid, eventid; uint16_t new_icid; - DTEntry dte; - CTEntry old_cte, new_cte; - ITEntry old_ite; + DTEntry dte = {}; + CTEntry old_cte = {}, new_cte = {}; + ITEntry old_ite = {}; ItsCmdResult cmdres; devid = FIELD_EX64(cmdpkt[0], MOVI_0, DEVICEID); @@ -XXX,XX +XXX,XX @@ static bool update_vte(GICv3ITSState *s, uint32_t vpeid, const VTEntry *vte) static ItsCmdResult process_vmapp(GICv3ITSState *s, const uint64_t *cmdpkt) { - VTEntry vte; + VTEntry vte = {}; uint32_t vpeid; if (!its_feature_virtual(s)) { @@ -XXX,XX +XXX,XX @@ static void vmovp_callback(gpointer data, gpointer opaque) */ GICv3ITSState *s = data; VmovpCallbackData *cbdata = opaque; - VTEntry vte; + VTEntry vte = {}; ItsCmdResult cmdres; cmdres = lookup_vte(s, __func__, cbdata->vpeid, &vte); @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_vmovi(GICv3ITSState *s, const uint64_t *cmdpkt) { uint32_t devid, eventid, vpeid, doorbell; bool doorbell_valid; - DTEntry dte; - ITEntry ite; - VTEntry old_vte, new_vte; + DTEntry dte = {}; + ITEntry ite = {}; + VTEntry old_vte = {}, new_vte = {}; ItsCmdResult cmdres; if (!its_feature_virtual(s)) { @@ -XXX,XX +XXX,XX @@ static ItsCmdResult process_vinvall(GICv3ITSState *s, const uint64_t *cmdpkt) static ItsCmdResult process_inv(GICv3ITSState *s, const uint64_t *cmdpkt) { uint32_t devid, eventid; - ITEntry ite; - DTEntry dte; - CTEntry cte; - VTEntry vte; + ITEntry ite = {}; + DTEntry dte = {}; + CTEntry cte = {}; + VTEntry vte = {}; ItsCmdResult cmdres; devid = FIELD_EX64(cmdpkt[0], INV_0, DEVICEID); -- 2.34.1 From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Update the URLs for the binaries we use for the firmware in the sbsa-ref functional tests. The firmware is built using Debian 'bookworm' cross toolchain (gcc 12.2.0). Used versions: - Trusted Firmware v2.12.0 - Tianocore EDK2 stable202411 - Tianocore EDK2 Platforms code commit 4b3530d This allows us to move away from "some git commit on trunk" to a stable release for both TF-A and EDK2. Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Message-id: 20241125125448.185504-1-marcin.juszkiewicz@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/functional/test_aarch64_sbsaref.py | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/tests/functional/test_aarch64_sbsaref.py b/tests/functional/test_aarch64_sbsaref.py index XXXXXXX..XXXXXXX 100755 --- a/tests/functional/test_aarch64_sbsaref.py +++ b/tests/functional/test_aarch64_sbsaref.py @@ -XXX,XX +XXX,XX @@ def fetch_firmware(test): Used components: - - Trusted Firmware v2.11.0 - - Tianocore EDK2 4d4f569924 - - Tianocore EDK2-platforms 3f08401 + - Trusted Firmware v2.12.0 + - Tianocore EDK2 edk2-stable202411 + - Tianocore EDK2-platforms 4b3530d """ @@ -XXX,XX +XXX,XX @@ class Aarch64SbsarefMachine(QemuSystemTest): ASSET_FLASH0 = Asset( ('https://artifacts.codelinaro.org/artifactory/linaro-419-sbsa-ref/' - '20240619-148232/edk2/SBSA_FLASH0.fd.xz'), - '0c954842a590988f526984de22e21ae0ab9cb351a0c99a8a58e928f0c7359cf7') + '20241122-189881/edk2/SBSA_FLASH0.fd.xz'), + '76eb89d42eebe324e4395329f47447cda9ac920aabcf99aca85424609c3384a5') ASSET_FLASH1 = Asset( ('https://artifacts.codelinaro.org/artifactory/linaro-419-sbsa-ref/' - '20240619-148232/edk2/SBSA_FLASH1.fd.xz'), - 'c6ec39374c4d79bb9e9cdeeb6db44732d90bb4a334cec92002b3f4b9cac4b5ee') + '20241122-189881/edk2/SBSA_FLASH1.fd.xz'), + 'f850f243bd8dbd49c51e061e0f79f1697546938f454aeb59ab7d93e5f0d412fc') def test_sbsaref_edk2_firmware(self): @@ -XXX,XX +XXX,XX @@ def test_sbsaref_edk2_firmware(self): # AP Trusted ROM wait_for_console_pattern(self, "Booting Trusted Firmware") - wait_for_console_pattern(self, "BL1: v2.11.0(release):") + wait_for_console_pattern(self, "BL1: v2.12.0(release):") wait_for_console_pattern(self, "BL1: Booting BL2") # Trusted Boot Firmware - wait_for_console_pattern(self, "BL2: v2.11.0(release)") + wait_for_console_pattern(self, "BL2: v2.12.0(release)") wait_for_console_pattern(self, "Booting BL31") # EL3 Runtime Software - wait_for_console_pattern(self, "BL31: v2.11.0(release)") + wait_for_console_pattern(self, "BL31: v2.12.0(release)") # Non-trusted Firmware wait_for_console_pattern(self, "UEFI firmware (version 1.0") -- 2.34.1