I don't have anything else queued up at the moment, so this is just Richard's SME patches. -- PMM The following changes since commit 63b38f6c85acd312c2cab68554abf33adf4ee2b3: Merge tag 'pull-target-arm-20220707' of https://git.linaro.org/people/pmaydell/qemu-arm into staging (2022-07-08 06:17:11 +0530) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20220711 for you to fetch changes up to f9982ceaf26df27d15547a3a7990a95019e9e3a8: linux-user/aarch64: Add SME related hwcap entries (2022-07-11 13:43:52 +0100) ---------------------------------------------------------------- target-arm: * Implement SME emulation, for both system and linux-user ---------------------------------------------------------------- Richard Henderson (45): target/arm: Handle SME in aarch64_cpu_dump_state target/arm: Add infrastructure for disas_sme target/arm: Trap non-streaming usage when Streaming SVE is active target/arm: Mark ADR as non-streaming target/arm: Mark RDFFR, WRFFR, SETFFR as non-streaming target/arm: Mark BDEP, BEXT, BGRP, COMPACT, FEXPA, FTSSEL as non-streaming target/arm: Mark PMULL, FMMLA as non-streaming target/arm: Mark FTSMUL, FTMAD, FADDA as non-streaming target/arm: Mark SMMLA, UMMLA, USMMLA as non-streaming target/arm: Mark string/histo/crypto as non-streaming target/arm: Mark gather/scatter load/store as non-streaming target/arm: Mark gather prefetch as non-streaming target/arm: Mark LDFF1 and LDNF1 as non-streaming target/arm: Mark LD1RO as non-streaming target/arm: Add SME enablement checks target/arm: Handle SME in sve_access_check target/arm: Implement SME RDSVL, ADDSVL, ADDSPL target/arm: Implement SME ZERO target/arm: Implement SME MOVA target/arm: Implement SME LD1, ST1 target/arm: Export unpredicated ld/st from translate-sve.c target/arm: Implement SME LDR, STR target/arm: Implement SME ADDHA, ADDVA target/arm: Implement FMOPA, FMOPS (non-widening) target/arm: Implement BFMOPA, BFMOPS target/arm: Implement FMOPA, FMOPS (widening) target/arm: Implement SME integer outer product target/arm: Implement PSEL target/arm: Implement REVD target/arm: Implement SCLAMP, UCLAMP target/arm: Reset streaming sve state on exception boundaries target/arm: Enable SME for -cpu max linux-user/aarch64: Clear tpidr2_el0 if CLONE_SETTLS linux-user/aarch64: Reset PSTATE.SM on syscalls linux-user/aarch64: Add SM bit to SVE signal context linux-user/aarch64: Tidy target_restore_sigframe error return linux-user/aarch64: Do not allow duplicate or short sve records linux-user/aarch64: Verify extra record lock succeeded linux-user/aarch64: Move sve record checks into restore linux-user/aarch64: Implement SME signal handling linux-user: Rename sve prctls linux-user/aarch64: Implement PR_SME_GET_VL, PR_SME_SET_VL target/arm: Only set ZEN in reset if SVE present target/arm: Enable SME for user-only linux-user/aarch64: Add SME related hwcap entries docs/system/arm/emulation.rst | 4 + linux-user/aarch64/target_cpu.h | 5 +- linux-user/aarch64/target_prctl.h | 62 +- target/arm/cpu.h | 7 + target/arm/helper-sme.h | 126 ++++ target/arm/helper-sve.h | 4 + target/arm/helper.h | 18 + target/arm/translate-a64.h | 45 ++ target/arm/translate.h | 16 + target/arm/sme-fa64.decode | 60 ++ target/arm/sme.decode | 88 +++ target/arm/sve.decode | 41 +- linux-user/aarch64/cpu_loop.c | 9 + linux-user/aarch64/signal.c | 243 ++++++-- linux-user/elfload.c | 20 + linux-user/syscall.c | 28 +- target/arm/cpu.c | 35 +- target/arm/cpu64.c | 11 + target/arm/helper.c | 56 +- target/arm/sme_helper.c | 1140 +++++++++++++++++++++++++++++++++++++ target/arm/sve_helper.c | 28 + target/arm/translate-a64.c | 103 +++- target/arm/translate-sme.c | 373 ++++++++++++ target/arm/translate-sve.c | 393 ++++++++++--- target/arm/translate-vfp.c | 12 + target/arm/translate.c | 2 + target/arm/vec_helper.c | 24 + target/arm/meson.build | 3 + 28 files changed, 2821 insertions(+), 135 deletions(-) create mode 100644 target/arm/sme-fa64.decode create mode 100644 target/arm/sme.decode create mode 100644 target/arm/translate-sme.c From: Richard Henderson <richard.henderson@linaro.org> Dump SVCR, plus use the correct access check for Streaming Mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) int i; int el = arm_current_el(env); const char *ns_status; + bool sve; qemu_fprintf(f, " PC=%016" PRIx64 " ", env->pc); for (i = 0; i < 32; i++) { @@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) el, psr & PSTATE_SP ? 'h' : 't'); + if (cpu_isar_feature(aa64_sme, cpu)) { + qemu_fprintf(f, " SVCR=%08" PRIx64 " %c%c", + env->svcr, + (FIELD_EX64(env->svcr, SVCR, ZA) ? 'Z' : '-'), + (FIELD_EX64(env->svcr, SVCR, SM) ? 'S' : '-')); + } if (cpu_isar_feature(aa64_bti, cpu)) { qemu_fprintf(f, " BTYPE=%d", (psr & PSTATE_BTYPE) >> 10); } @@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) qemu_fprintf(f, " FPCR=%08x FPSR=%08x\n", vfp_get_fpcr(env), vfp_get_fpsr(env)); - if (cpu_isar_feature(aa64_sve, cpu) && sve_exception_el(env, el) == 0) { + if (cpu_isar_feature(aa64_sme, cpu) && FIELD_EX64(env->svcr, SVCR, SM)) { + sve = sme_exception_el(env, el) == 0; + } else if (cpu_isar_feature(aa64_sve, cpu)) { + sve = sve_exception_el(env, el) == 0; + } else { + sve = false; + } + + if (sve) { int j, zcr_len = sve_vqm1_for_el(env, el); for (i = 0; i <= FFR_PRED_NUM; i++) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This includes the build rules for the decoder, and the new file for translation, but excludes any instructions. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 1 + target/arm/sme.decode | 20 ++++++++++++++++++++ target/arm/translate-a64.c | 7 ++++++- target/arm/translate-sme.c | 35 +++++++++++++++++++++++++++++++++++ target/arm/meson.build | 2 ++ 5 files changed, 64 insertions(+), 1 deletion(-) create mode 100644 target/arm/sme.decode create mode 100644 target/arm/translate-sme.c diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ static inline int pred_gvec_reg_size(DisasContext *s) } bool disas_sve(DisasContext *, uint32_t); +bool disas_sme(DisasContext *, uint32_t); void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); diff --git a/target/arm/sme.decode b/target/arm/sme.decode new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ +# AArch64 SME instruction descriptions +# +# Copyright (c) 2022 Linaro, Ltd +# +# This library is free software; you can redistribute it and/or +# modify it under the terms of the GNU Lesser General Public +# License as published by the Free Software Foundation; either +# version 2.1 of the License, or (at your option) any later version. +# +# This library is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# Lesser General Public License for more details. +# +# You should have received a copy of the GNU Lesser General Public +# License along with this library; if not, see <http://www.gnu.org/licenses/>. + +# +# This file is processed by scripts/decodetree.py +# 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 aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) } switch (extract32(insn, 25, 4)) { - case 0x0: case 0x1: case 0x3: /* UNALLOCATED */ + case 0x0: + if (!extract32(insn, 31, 1) || !disas_sme(s, insn)) { + unallocated_encoding(s); + } + break; + case 0x1: case 0x3: /* UNALLOCATED */ unallocated_encoding(s); break; case 0x2: diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ +/* + * AArch64 SME translation + * + * Copyright (c) 2022 Linaro, Ltd + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "cpu.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-op-gvec.h" +#include "tcg/tcg-gvec-desc.h" +#include "translate.h" +#include "exec/helper-gen.h" +#include "translate-a64.h" +#include "fpu/softfloat.h" + + +/* + * Include the generated decoder. + */ + +#include "decode-sme.c.inc" diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ gen = [ decodetree.process('sve.decode', extra_args: '--decode=disas_sve'), + decodetree.process('sme.decode', extra_args: '--decode=disas_sme'), decodetree.process('neon-shared.decode', extra_args: '--decode=disas_neon_shared'), decodetree.process('neon-dp.decode', extra_args: '--decode=disas_neon_dp'), decodetree.process('neon-ls.decode', extra_args: '--decode=disas_neon_ls'), @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'TARGET_AARCH64', if_true: files( 'sme_helper.c', 'translate-a64.c', 'translate-sve.c', + 'translate-sme.c', )) arm_softmmu_ss = ss.source_set() -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This new behaviour is in the ARM pseudocode function AArch64.CheckFPAdvSIMDEnabled, which applies to AArch32 via AArch32.CheckAdvSIMDOrFPEnabled when the EL to which the trap would be delivered is in AArch64 mode. Given that ARMv9 drops support for AArch32 outside EL0, the trap EL detection ought to be trivially true, but the pseudocode still contains a number of conditions, and QEMU has not yet committed to dropping A32 support for EL[12] when v9 features are present. Since the computation of SME_TRAP_NONSTREAMING is necessarily different for the two modes, we might as well preserve bits within TBFLAG_ANY and allocate separate bits within TBFLAG_A32 and TBFLAG_A64 instead. Note that DDI0616A.a has typos for bits [22:21] of LD1RO in the table of instructions illegal in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 7 +++ target/arm/translate.h | 4 ++ target/arm/sme-fa64.decode | 90 ++++++++++++++++++++++++++++++++++++++ target/arm/helper.c | 41 +++++++++++++++++ target/arm/translate-a64.c | 40 ++++++++++++++++- target/arm/translate-vfp.c | 12 +++++ target/arm/translate.c | 2 + target/arm/meson.build | 1 + 8 files changed, 195 insertions(+), 2 deletions(-) create mode 100644 target/arm/sme-fa64.decode 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 @@ FIELD(TBFLAG_A32, HSTR_ACTIVE, 9, 1) * the same thing as the current security state of the processor! */ FIELD(TBFLAG_A32, NS, 10, 1) +/* + * Indicates that SME Streaming mode is active, and SMCR_ELx.FA64 is not. + * This requires an SME trap from AArch32 mode when using NEON. + */ +FIELD(TBFLAG_A32, SME_TRAP_NONSTREAMING, 11, 1) /* * Bit usage when in AArch32 state, for M-profile only. @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A64, SMEEXC_EL, 20, 2) FIELD(TBFLAG_A64, PSTATE_SM, 22, 1) FIELD(TBFLAG_A64, PSTATE_ZA, 23, 1) FIELD(TBFLAG_A64, SVL, 24, 4) +/* Indicates that SME Streaming mode is active, and SMCR_ELx.FA64 is not. */ +FIELD(TBFLAG_A64, SME_TRAP_NONSTREAMING, 28, 1) /* * Helpers for using the above. 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 @@ typedef struct DisasContext { bool pstate_sm; /* True if PSTATE.ZA is set. */ bool pstate_za; + /* True if non-streaming insns should raise an SME Streaming exception. */ + bool sme_trap_nonstreaming; + /* True if the current instruction is non-streaming. */ + bool is_nonstreaming; /* True if MVE insns are definitely not predicated by VPR or LTPSIZE */ bool mve_no_pred; /* diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ +# AArch64 SME allowed instruction decoding +# +# Copyright (c) 2022 Linaro, Ltd +# +# This library is free software; you can redistribute it and/or +# modify it under the terms of the GNU Lesser General Public +# License as published by the Free Software Foundation; either +# version 2.1 of the License, or (at your option) any later version. +# +# This library is distributed in the hope that it will be useful, +# but WITHOUT ANY WARRANTY; without even the implied warranty of +# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU +# Lesser General Public License for more details. +# +# You should have received a copy of the GNU Lesser General Public +# License along with this library; if not, see <http://www.gnu.org/licenses/>. + +# +# This file is processed by scripts/decodetree.py +# + +# These patterns are taken from Appendix E1.1 of DDI0616 A.a, +# Arm Architecture Reference Manual Supplement, +# The Scalable Matrix Extension (SME), for Armv9-A + +{ + [ + OK 0-00 1110 0000 0001 0010 11-- ---- ---- # SMOV W|Xd,Vn.B[0] + OK 0-00 1110 0000 0010 0010 11-- ---- ---- # SMOV W|Xd,Vn.H[0] + OK 0100 1110 0000 0100 0010 11-- ---- ---- # SMOV Xd,Vn.S[0] + OK 0000 1110 0000 0001 0011 11-- ---- ---- # UMOV Wd,Vn.B[0] + OK 0000 1110 0000 0010 0011 11-- ---- ---- # UMOV Wd,Vn.H[0] + OK 0000 1110 0000 0100 0011 11-- ---- ---- # UMOV Wd,Vn.S[0] + OK 0100 1110 0000 1000 0011 11-- ---- ---- # UMOV Xd,Vn.D[0] + ] + FAIL 0--0 111- ---- ---- ---- ---- ---- ---- # Advanced SIMD vector operations +} + +{ + [ + OK 0101 1110 --1- ---- 11-1 11-- ---- ---- # FMULX/FRECPS/FRSQRTS (scalar) + OK 0101 1110 -10- ---- 00-1 11-- ---- ---- # FMULX/FRECPS/FRSQRTS (scalar, FP16) + OK 01-1 1110 1-10 0001 11-1 10-- ---- ---- # FRECPE/FRSQRTE/FRECPX (scalar) + OK 01-1 1110 1111 1001 11-1 10-- ---- ---- # FRECPE/FRSQRTE/FRECPX (scalar, FP16) + ] + FAIL 01-1 111- ---- ---- ---- ---- ---- ---- # Advanced SIMD single-element operations +} + +FAIL 0-00 110- ---- ---- ---- ---- ---- ---- # Advanced SIMD structure load/store +FAIL 1100 1110 ---- ---- ---- ---- ---- ---- # Advanced SIMD cryptography extensions +FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS + +# These are the "avoidance of doubt" final table of Illegal Advanced SIMD instructions +# We don't actually need to include these, as the default is OK. +# -001 111- ---- ---- ---- ---- ---- ---- # Scalar floating-point operations +# --10 110- ---- ---- ---- ---- ---- ---- # Load/store pair of FP registers +# --01 1100 ---- ---- ---- ---- ---- ---- # Load FP register (PC-relative literal) +# --11 1100 --0- ---- ---- ---- ---- ---- # Load/store FP register (unscaled imm) +# --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) +# --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) + +FAIL 0000 0100 --1- ---- 1010 ---- ---- ---- # ADR +FAIL 0000 0100 --1- ---- 1011 -0-- ---- ---- # FTSSEL, FEXPA +FAIL 0000 0101 --10 0001 100- ---- ---- ---- # COMPACT +FAIL 0010 0101 --01 100- 1111 000- ---0 ---- # RDFFR, RDFFRS +FAIL 0010 0101 --10 1--- 1001 ---- ---- ---- # WRFFR, SETFFR +FAIL 0100 0101 --0- ---- 1011 ---- ---- ---- # BDEP, BEXT, BGRP +FAIL 0100 0101 000- ---- 0110 1--- ---- ---- # PMULLB, PMULLT (128b result) +FAIL 0110 0100 --1- ---- 1110 01-- ---- ---- # FMMLA, BFMMLA +FAIL 0110 0101 --0- ---- 0000 11-- ---- ---- # FTSMUL +FAIL 0110 0101 --01 0--- 100- ---- ---- ---- # FTMAD +FAIL 0110 0101 --01 1--- 001- ---- ---- ---- # FADDA +FAIL 0100 0101 --0- ---- 1001 10-- ---- ---- # SMMLA, UMMLA, USMMLA +FAIL 0100 0101 --1- ---- 1--- ---- ---- ---- # SVE2 string/histo/crypto instructions +FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) +FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) +FAIL 1000 0100 0-1- ---- 0--- ---- ---- ---- # SVE 32-bit gather prefetch (scalar+vector) +FAIL 1000 010- -01- ---- 1--- ---- ---- ---- # SVE 32-bit gather load (vector+imm) +FAIL 1000 0100 0-0- ---- 0--- ---- ---- ---- # SVE 32-bit gather load byte (scalar+vector) +FAIL 1000 0100 1--- ---- 0--- ---- ---- ---- # SVE 32-bit gather load half (scalar+vector) +FAIL 1000 0101 0--- ---- 0--- ---- ---- ---- # SVE 32-bit gather load word (scalar+vector) +FAIL 1010 010- ---- ---- 011- ---- ---- ---- # SVE contiguous FF load (scalar+scalar) +FAIL 1010 010- ---1 ---- 101- ---- ---- ---- # SVE contiguous NF load (scalar+imm) +FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) +FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) +FAIL 1100 010- ---- ---- ---- ---- ---- ---- # SVE 64-bit gather load/prefetch +FAIL 1110 010- -00- ---- 001- ---- ---- ---- # SVE2 64-bit scatter NT store (vector+scalar) +FAIL 1110 010- -10- ---- 001- ---- ---- ---- # SVE2 32-bit scatter NT store (vector+scalar) +FAIL 1110 010- ---- ---- 1-0- ---- ---- ---- # SVE scatter store (scalar+32-bit vector) +FAIL 1110 010- ---- ---- 101- ---- ---- ---- # SVE scatter store (misc) 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 @@ int sme_exception_el(CPUARMState *env, int el) return 0; } +/* This corresponds to the ARM pseudocode function IsFullA64Enabled(). */ +static bool sme_fa64(CPUARMState *env, int el) +{ + if (!cpu_isar_feature(aa64_sme_fa64, env_archcpu(env))) { + return false; + } + + if (el <= 1 && !el_is_in_host(env, el)) { + if (!FIELD_EX64(env->vfp.smcr_el[1], SMCR, FA64)) { + return false; + } + } + if (el <= 2 && arm_is_el2_enabled(env)) { + if (!FIELD_EX64(env->vfp.smcr_el[2], SMCR, FA64)) { + return false; + } + } + if (arm_feature(env, ARM_FEATURE_EL3)) { + if (!FIELD_EX64(env->vfp.smcr_el[3], SMCR, FA64)) { + return false; + } + } + + return true; +} + /* * Given that SVE is enabled, return the vector length for EL. */ @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el, DP_TBFLAG_ANY(flags, PSTATE__IL, 1); } + /* + * The SME exception we are testing for is raised via + * AArch64.CheckFPAdvSIMDEnabled(), as called from + * AArch32.CheckAdvSIMDOrFPEnabled(). + */ + if (el == 0 + && FIELD_EX64(env->svcr, SVCR, SM) + && (!arm_is_el2_enabled(env) + || (arm_el_is_aa64(env, 2) && !(env->cp15.hcr_el2 & HCR_TGE))) + && arm_el_is_aa64(env, 1) + && !sme_fa64(env, el)) { + DP_TBFLAG_A32(flags, SME_TRAP_NONSTREAMING, 1); + } + return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); } @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, } if (FIELD_EX64(env->svcr, SVCR, SM)) { DP_TBFLAG_A64(flags, PSTATE_SM, 1); + DP_TBFLAG_A64(flags, SME_TRAP_NONSTREAMING, !sme_fa64(env, el)); } DP_TBFLAG_A64(flags, PSTATE_ZA, FIELD_EX64(env->svcr, SVCR, ZA)); } 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 do_vec_ld(DisasContext *s, int destidx, int element, * unallocated-encoding checks (otherwise the syndrome information * for the resulting exception will be incorrect). */ -static bool fp_access_check(DisasContext *s) +static bool fp_access_check_only(DisasContext *s) { if (s->fp_excp_el) { assert(!s->fp_access_checked); @@ -XXX,XX +XXX,XX @@ static bool fp_access_check(DisasContext *s) return true; } +static bool fp_access_check(DisasContext *s) +{ + if (!fp_access_check_only(s)) { + return false; + } + if (s->sme_trap_nonstreaming && s->is_nonstreaming) { + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_smetrap(SME_ET_Streaming, false)); + return false; + } + return true; +} + /* Check that SVE access is enabled. If it is, return true. * If not, emit code to generate an appropriate exception and return false. */ @@ -XXX,XX +XXX,XX @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, default: g_assert_not_reached(); } - if ((ri->type & ARM_CP_FPU) && !fp_access_check(s)) { + if ((ri->type & ARM_CP_FPU) && !fp_access_check_only(s)) { return; } else if ((ri->type & ARM_CP_SVE) && !sve_access_check(s)) { return; @@ -XXX,XX +XXX,XX @@ static void disas_data_proc_simd_fp(DisasContext *s, uint32_t insn) } } +/* + * Include the generated SME FA64 decoder. + */ + +#include "decode-sme-fa64.c.inc" + +static bool trans_OK(DisasContext *s, arg_OK *a) +{ + return true; +} + +static bool trans_FAIL(DisasContext *s, arg_OK *a) +{ + s->is_nonstreaming = true; + return true; +} + /** * is_guarded_page: * @env: The cpu environment @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->mte_active[1] = EX_TBFLAG_A64(tb_flags, MTE0_ACTIVE); dc->pstate_sm = EX_TBFLAG_A64(tb_flags, PSTATE_SM); dc->pstate_za = EX_TBFLAG_A64(tb_flags, PSTATE_ZA); + dc->sme_trap_nonstreaming = EX_TBFLAG_A64(tb_flags, SME_TRAP_NONSTREAMING); dc->vec_len = 0; dc->vec_stride = 0; dc->cp_regs = arm_cpu->cp_regs; @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) } } + s->is_nonstreaming = false; + if (s->sme_trap_nonstreaming) { + disas_sme_fa64(s, insn); + } + switch (extract32(insn, 25, 4)) { case 0x0: if (!extract32(insn, 31, 1) || !disas_sme(s, insn)) { diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c +++ b/target/arm/translate-vfp.c @@ -XXX,XX +XXX,XX @@ static bool vfp_access_check_a(DisasContext *s, bool ignore_vfp_enabled) return false; } + /* + * Note that rebuild_hflags_a32 has already accounted for being in EL0 + * and the higher EL in A64 mode, etc. Unlike A64 mode, there do not + * appear to be any insns which touch VFP which are allowed. + */ + if (s->sme_trap_nonstreaming) { + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_smetrap(SME_ET_Streaming, + s->base.pc_next - s->pc_curr == 2)); + return false; + } + if (!s->vfp_enabled && !ignore_vfp_enabled) { assert(!arm_dc_feature(s, ARM_FEATURE_M)); unallocated_encoding(s); 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 void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) dc->vec_len = EX_TBFLAG_A32(tb_flags, VECLEN); dc->vec_stride = EX_TBFLAG_A32(tb_flags, VECSTRIDE); } + dc->sme_trap_nonstreaming = + EX_TBFLAG_A32(tb_flags, SME_TRAP_NONSTREAMING); } dc->cp_regs = cpu->cp_regs; dc->features = env->features; diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ gen = [ decodetree.process('sve.decode', extra_args: '--decode=disas_sve'), decodetree.process('sme.decode', extra_args: '--decode=disas_sme'), + decodetree.process('sme-fa64.decode', extra_args: '--static-decode=disas_sme_fa64'), decodetree.process('neon-shared.decode', extra_args: '--decode=disas_neon_shared'), decodetree.process('neon-dp.decode', extra_args: '--decode=disas_neon_dp'), decodetree.process('neon-ls.decode', extra_args: '--decode=disas_neon_ls'), -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark ADR as a non-streaming instruction, which should trap if full a64 support is not enabled in streaming mode. Removing entries from sme-fa64.decode is an easy way to see what remains to be done. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 7 +++++++ target/arm/sme-fa64.decode | 1 - target/arm/translate-sve.c | 8 ++++---- 3 files changed, 11 insertions(+), 5 deletions(-) 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 @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op); static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \ { return dc_isar_feature(FEAT, s) && FUNC(s, __VA_ARGS__); } +#define TRANS_FEAT_NONSTREAMING(NAME, FEAT, FUNC, ...) \ + static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \ + { \ + s->is_nonstreaming = true; \ + return dc_isar_feature(FEAT, s) && FUNC(s, __VA_ARGS__); \ + } + #endif /* TARGET_ARM_TRANSLATE_H */ diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0000 0100 --1- ---- 1010 ---- ---- ---- # ADR FAIL 0000 0100 --1- ---- 1011 -0-- ---- ---- # FTSSEL, FEXPA FAIL 0000 0101 --10 0001 100- ---- ---- ---- # COMPACT FAIL 0010 0101 --01 100- 1111 000- ---0 ---- # RDFFR, RDFFRS 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 do_adr(DisasContext *s, arg_rrri *a, gen_helper_gvec_3 *fn) return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, a->imm); } -TRANS_FEAT(ADR_p32, aa64_sve, do_adr, a, gen_helper_sve_adr_p32) -TRANS_FEAT(ADR_p64, aa64_sve, do_adr, a, gen_helper_sve_adr_p64) -TRANS_FEAT(ADR_s32, aa64_sve, do_adr, a, gen_helper_sve_adr_s32) -TRANS_FEAT(ADR_u32, aa64_sve, do_adr, a, gen_helper_sve_adr_u32) +TRANS_FEAT_NONSTREAMING(ADR_p32, aa64_sve, do_adr, a, gen_helper_sve_adr_p32) +TRANS_FEAT_NONSTREAMING(ADR_p64, aa64_sve, do_adr, a, gen_helper_sve_adr_p64) +TRANS_FEAT_NONSTREAMING(ADR_s32, aa64_sve, do_adr, a, gen_helper_sve_adr_s32) +TRANS_FEAT_NONSTREAMING(ADR_u32, aa64_sve, do_adr, a, gen_helper_sve_adr_u32) /* *** SVE Integer Misc - Unpredicated Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 2 -- target/arm/translate-sve.c | 9 ++++++--- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS FAIL 0000 0100 --1- ---- 1011 -0-- ---- ---- # FTSSEL, FEXPA FAIL 0000 0101 --10 0001 100- ---- ---- ---- # COMPACT -FAIL 0010 0101 --01 100- 1111 000- ---0 ---- # RDFFR, RDFFRS -FAIL 0010 0101 --10 1--- 1001 ---- ---- ---- # WRFFR, SETFFR FAIL 0100 0101 --0- ---- 1011 ---- ---- ---- # BDEP, BEXT, BGRP FAIL 0100 0101 000- ---- 0110 1--- ---- ---- # PMULLB, PMULLT (128b result) FAIL 0110 0100 --1- ---- 1110 01-- ---- ---- # FMMLA, BFMMLA 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 do_predset(DisasContext *s, int esz, int rd, int pat, bool setflag) TRANS_FEAT(PTRUE, aa64_sve, do_predset, a->esz, a->rd, a->pat, a->s) /* Note pat == 31 is #all, to set all elements. */ -TRANS_FEAT(SETFFR, aa64_sve, do_predset, 0, FFR_PRED_NUM, 31, false) +TRANS_FEAT_NONSTREAMING(SETFFR, aa64_sve, + do_predset, 0, FFR_PRED_NUM, 31, false) /* Note pat == 32 is #unimp, to set no elements. */ TRANS_FEAT(PFALSE, aa64_sve, do_predset, 0, a->rd, 32, false) @@ -XXX,XX +XXX,XX @@ static bool trans_RDFFR_p(DisasContext *s, arg_RDFFR_p *a) .rd = a->rd, .pg = a->pg, .s = a->s, .rn = FFR_PRED_NUM, .rm = FFR_PRED_NUM, }; + + s->is_nonstreaming = true; return trans_AND_pppp(s, &alt_a); } -TRANS_FEAT(RDFFR, aa64_sve, do_mov_p, a->rd, FFR_PRED_NUM) -TRANS_FEAT(WRFFR, aa64_sve, do_mov_p, FFR_PRED_NUM, a->rn) +TRANS_FEAT_NONSTREAMING(RDFFR, aa64_sve, do_mov_p, a->rd, FFR_PRED_NUM) +TRANS_FEAT_NONSTREAMING(WRFFR, aa64_sve, do_mov_p, FFR_PRED_NUM, a->rn) static bool do_pfirst_pnext(DisasContext *s, arg_rr_esz *a, void (*gen_fn)(TCGv_i32, TCGv_ptr, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 3 --- target/arm/translate-sve.c | 22 ++++++++++++---------- 2 files changed, 12 insertions(+), 13 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0000 0100 --1- ---- 1011 -0-- ---- ---- # FTSSEL, FEXPA -FAIL 0000 0101 --10 0001 100- ---- ---- ---- # COMPACT -FAIL 0100 0101 --0- ---- 1011 ---- ---- ---- # BDEP, BEXT, BGRP FAIL 0100 0101 000- ---- 0110 1--- ---- ---- # PMULLB, PMULLT (128b result) FAIL 0110 0100 --1- ---- 1110 01-- ---- ---- # FMMLA, BFMMLA FAIL 0110 0101 --0- ---- 0000 11-- ---- ---- # FTSMUL 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 gen_helper_gvec_2 * const fexpa_fns[4] = { NULL, gen_helper_sve_fexpa_h, gen_helper_sve_fexpa_s, gen_helper_sve_fexpa_d, }; -TRANS_FEAT(FEXPA, aa64_sve, gen_gvec_ool_zz, - fexpa_fns[a->esz], a->rd, a->rn, 0) +TRANS_FEAT_NONSTREAMING(FEXPA, aa64_sve, gen_gvec_ool_zz, + fexpa_fns[a->esz], a->rd, a->rn, 0) static gen_helper_gvec_3 * const ftssel_fns[4] = { NULL, gen_helper_sve_ftssel_h, gen_helper_sve_ftssel_s, gen_helper_sve_ftssel_d, }; -TRANS_FEAT(FTSSEL, aa64_sve, gen_gvec_ool_arg_zzz, ftssel_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(FTSSEL, aa64_sve, gen_gvec_ool_arg_zzz, + ftssel_fns[a->esz], a, 0) /* *** SVE Predicate Logical Operations Group @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(TRN2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, static gen_helper_gvec_3 * const compact_fns[4] = { NULL, NULL, gen_helper_sve_compact_s, gen_helper_sve_compact_d }; -TRANS_FEAT(COMPACT, aa64_sve, gen_gvec_ool_arg_zpz, compact_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(COMPACT, aa64_sve, gen_gvec_ool_arg_zpz, + compact_fns[a->esz], a, 0) /* Call the helper that computes the ARM LastActiveElement pseudocode * function, scaled by the element size. This includes the not found @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3 * const bext_fns[4] = { gen_helper_sve2_bext_b, gen_helper_sve2_bext_h, gen_helper_sve2_bext_s, gen_helper_sve2_bext_d, }; -TRANS_FEAT(BEXT, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, - bext_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(BEXT, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, + bext_fns[a->esz], a, 0) static gen_helper_gvec_3 * const bdep_fns[4] = { gen_helper_sve2_bdep_b, gen_helper_sve2_bdep_h, gen_helper_sve2_bdep_s, gen_helper_sve2_bdep_d, }; -TRANS_FEAT(BDEP, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, - bdep_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(BDEP, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, + bdep_fns[a->esz], a, 0) static gen_helper_gvec_3 * const bgrp_fns[4] = { gen_helper_sve2_bgrp_b, gen_helper_sve2_bgrp_h, gen_helper_sve2_bgrp_s, gen_helper_sve2_bgrp_d, }; -TRANS_FEAT(BGRP, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, - bgrp_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(BGRP, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, + bgrp_fns[a->esz], a, 0) static gen_helper_gvec_3 * const cadd_fns[4] = { gen_helper_sve2_cadd_b, gen_helper_sve2_cadd_h, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 2 -- target/arm/translate-sve.c | 24 +++++++++++++++--------- 2 files changed, 15 insertions(+), 11 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0100 0101 000- ---- 0110 1--- ---- ---- # PMULLB, PMULLT (128b result) -FAIL 0110 0100 --1- ---- 1110 01-- ---- ---- # FMMLA, BFMMLA FAIL 0110 0101 --0- ---- 0000 11-- ---- ---- # FTSMUL FAIL 0110 0101 --01 0--- 100- ---- ---- ---- # FTMAD FAIL 0110 0101 --01 1--- 001- ---- ---- ---- # FADDA 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 do_trans_pmull(DisasContext *s, arg_rrr_esz *a, bool sel) gen_helper_gvec_pmull_q, gen_helper_sve2_pmull_h, NULL, gen_helper_sve2_pmull_d, }; - if (a->esz == 0 - ? !dc_isar_feature(aa64_sve2_pmull128, s) - : !dc_isar_feature(aa64_sve, s)) { + + if (a->esz == 0) { + if (!dc_isar_feature(aa64_sve2_pmull128, s)) { + return false; + } + s->is_nonstreaming = true; + } else if (!dc_isar_feature(aa64_sve, s)) { return false; } return gen_gvec_ool_arg_zzz(s, fns[a->esz], a, sel); @@ -XXX,XX +XXX,XX @@ DO_ZPZZ_FP(FMINP, aa64_sve2, sve2_fminp_zpzz) * SVE Integer Multiply-Add (unpredicated) */ -TRANS_FEAT(FMMLA_s, aa64_sve_f32mm, gen_gvec_fpst_zzzz, gen_helper_fmmla_s, - a->rd, a->rn, a->rm, a->ra, 0, FPST_FPCR) -TRANS_FEAT(FMMLA_d, aa64_sve_f64mm, gen_gvec_fpst_zzzz, gen_helper_fmmla_d, - a->rd, a->rn, a->rm, a->ra, 0, FPST_FPCR) +TRANS_FEAT_NONSTREAMING(FMMLA_s, aa64_sve_f32mm, gen_gvec_fpst_zzzz, + gen_helper_fmmla_s, a->rd, a->rn, a->rm, a->ra, + 0, FPST_FPCR) +TRANS_FEAT_NONSTREAMING(FMMLA_d, aa64_sve_f64mm, gen_gvec_fpst_zzzz, + gen_helper_fmmla_d, a->rd, a->rn, a->rm, a->ra, + 0, FPST_FPCR) static gen_helper_gvec_4 * const sqdmlal_zzzw_fns[] = { NULL, gen_helper_sve2_sqdmlal_zzzw_h, @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(BFDOT_zzzz, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, TRANS_FEAT(BFDOT_zzxz, aa64_sve_bf16, gen_gvec_ool_arg_zzxz, gen_helper_gvec_bfdot_idx, a) -TRANS_FEAT(BFMMLA, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, - gen_helper_gvec_bfmmla, a, 0) +TRANS_FEAT_NONSTREAMING(BFMMLA, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_bfmmla, a, 0) static bool do_BFMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 3 --- target/arm/translate-sve.c | 15 +++++++++++---- 2 files changed, 11 insertions(+), 7 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0110 0101 --0- ---- 0000 11-- ---- ---- # FTSMUL -FAIL 0110 0101 --01 0--- 100- ---- ---- ---- # FTMAD -FAIL 0110 0101 --01 1--- 001- ---- ---- ---- # FADDA FAIL 0100 0101 --0- ---- 1001 10-- ---- ---- # SMMLA, UMMLA, USMMLA FAIL 0100 0101 --1- ---- 1--- ---- ---- ---- # SVE2 string/histo/crypto instructions FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) 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 gen_helper_gvec_3_ptr * const ftmad_fns[4] = { NULL, gen_helper_sve_ftmad_h, gen_helper_sve_ftmad_s, gen_helper_sve_ftmad_d, }; -TRANS_FEAT(FTMAD, aa64_sve, gen_gvec_fpst_zzz, - ftmad_fns[a->esz], a->rd, a->rn, a->rm, a->imm, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) +TRANS_FEAT_NONSTREAMING(FTMAD, aa64_sve, gen_gvec_fpst_zzz, + ftmad_fns[a->esz], a->rd, a->rn, a->rm, a->imm, + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) /* *** SVE Floating Point Accumulating Reduction Group @@ -XXX,XX +XXX,XX @@ static bool trans_FADDA(DisasContext *s, arg_rprr_esz *a) if (a->esz == 0 || !dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_FADDA(DisasContext *s, arg_rprr_esz *a) DO_FP3(FADD_zzz, fadd) DO_FP3(FSUB_zzz, fsub) DO_FP3(FMUL_zzz, fmul) -DO_FP3(FTSMUL, ftsmul) DO_FP3(FRECPS, recps) DO_FP3(FRSQRTS, rsqrts) #undef DO_FP3 +static gen_helper_gvec_3_ptr * const ftsmul_fns[4] = { + NULL, gen_helper_gvec_ftsmul_h, + gen_helper_gvec_ftsmul_s, gen_helper_gvec_ftsmul_d +}; +TRANS_FEAT_NONSTREAMING(FTSMUL, aa64_sve, gen_gvec_fpst_arg_zzz, + ftsmul_fns[a->esz], a, 0) + /* *** SVE Floating Point Arithmetic - Predicated Group */ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 1 - target/arm/translate-sve.c | 12 ++++++------ 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0100 0101 --0- ---- 1001 10-- ---- ---- # SMMLA, UMMLA, USMMLA FAIL 0100 0101 --1- ---- 1--- ---- ---- ---- # SVE2 string/histo/crypto instructions FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) 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 @@ TRANS_FEAT(FMLALT_zzxw, aa64_sve2, do_FMLAL_zzxw, a, false, true) TRANS_FEAT(FMLSLB_zzxw, aa64_sve2, do_FMLAL_zzxw, a, true, false) TRANS_FEAT(FMLSLT_zzxw, aa64_sve2, do_FMLAL_zzxw, a, true, true) -TRANS_FEAT(SMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, - gen_helper_gvec_smmla_b, a, 0) -TRANS_FEAT(USMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, - gen_helper_gvec_usmmla_b, a, 0) -TRANS_FEAT(UMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, - gen_helper_gvec_ummla_b, a, 0) +TRANS_FEAT_NONSTREAMING(SMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_smmla_b, a, 0) +TRANS_FEAT_NONSTREAMING(USMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_usmmla_b, a, 0) +TRANS_FEAT_NONSTREAMING(UMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_ummla_b, a, 0) TRANS_FEAT(BFDOT_zzzz, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, gen_helper_gvec_bfdot, a, 0) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 1 - target/arm/translate-sve.c | 35 ++++++++++++++++++----------------- 2 files changed, 18 insertions(+), 18 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0100 0101 --1- ---- 1--- ---- ---- ---- # SVE2 string/histo/crypto instructions FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) FAIL 1000 0100 0-1- ---- 0--- ---- ---- ---- # SVE 32-bit gather prefetch (scalar+vector) 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 @@ DO_SVE2_ZZZ_NARROW(RSUBHNT, rsubhnt) static gen_helper_gvec_flags_4 * const match_fns[4] = { gen_helper_sve2_match_ppzz_b, gen_helper_sve2_match_ppzz_h, NULL, NULL }; -TRANS_FEAT(MATCH, aa64_sve2, do_ppzz_flags, a, match_fns[a->esz]) +TRANS_FEAT_NONSTREAMING(MATCH, aa64_sve2, do_ppzz_flags, a, match_fns[a->esz]) static gen_helper_gvec_flags_4 * const nmatch_fns[4] = { gen_helper_sve2_nmatch_ppzz_b, gen_helper_sve2_nmatch_ppzz_h, NULL, NULL }; -TRANS_FEAT(NMATCH, aa64_sve2, do_ppzz_flags, a, nmatch_fns[a->esz]) +TRANS_FEAT_NONSTREAMING(NMATCH, aa64_sve2, do_ppzz_flags, a, nmatch_fns[a->esz]) static gen_helper_gvec_4 * const histcnt_fns[4] = { NULL, NULL, gen_helper_sve2_histcnt_s, gen_helper_sve2_histcnt_d }; -TRANS_FEAT(HISTCNT, aa64_sve2, gen_gvec_ool_arg_zpzz, - histcnt_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(HISTCNT, aa64_sve2, gen_gvec_ool_arg_zpzz, + histcnt_fns[a->esz], a, 0) -TRANS_FEAT(HISTSEG, aa64_sve2, gen_gvec_ool_arg_zzz, - a->esz == 0 ? gen_helper_sve2_histseg : NULL, a, 0) +TRANS_FEAT_NONSTREAMING(HISTSEG, aa64_sve2, gen_gvec_ool_arg_zzz, + a->esz == 0 ? gen_helper_sve2_histseg : NULL, a, 0) DO_ZPZZ_FP(FADDP, aa64_sve2, sve2_faddp_zpzz) DO_ZPZZ_FP(FMAXNMP, aa64_sve2, sve2_fmaxnmp_zpzz) @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz, TRANS_FEAT(USDOT_zzzz, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, a->esz == 2 ? gen_helper_gvec_usdot_b : NULL, a, 0) -TRANS_FEAT(AESMC, aa64_sve2_aes, gen_gvec_ool_zz, - gen_helper_crypto_aesmc, a->rd, a->rd, a->decrypt) +TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz, + gen_helper_crypto_aesmc, a->rd, a->rd, a->decrypt) -TRANS_FEAT(AESE, aa64_sve2_aes, gen_gvec_ool_arg_zzz, - gen_helper_crypto_aese, a, false) -TRANS_FEAT(AESD, aa64_sve2_aes, gen_gvec_ool_arg_zzz, - gen_helper_crypto_aese, a, true) +TRANS_FEAT_NONSTREAMING(AESE, aa64_sve2_aes, gen_gvec_ool_arg_zzz, + gen_helper_crypto_aese, a, false) +TRANS_FEAT_NONSTREAMING(AESD, aa64_sve2_aes, gen_gvec_ool_arg_zzz, + gen_helper_crypto_aese, a, true) -TRANS_FEAT(SM4E, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, - gen_helper_crypto_sm4e, a, 0) -TRANS_FEAT(SM4EKEY, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, - gen_helper_crypto_sm4ekey, a, 0) +TRANS_FEAT_NONSTREAMING(SM4E, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, + gen_helper_crypto_sm4e, a, 0) +TRANS_FEAT_NONSTREAMING(SM4EKEY, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, + gen_helper_crypto_sm4ekey, a, 0) -TRANS_FEAT(RAX1, aa64_sve2_sha3, gen_gvec_fn_arg_zzz, gen_gvec_rax1, a) +TRANS_FEAT_NONSTREAMING(RAX1, aa64_sve2_sha3, gen_gvec_fn_arg_zzz, + gen_gvec_rax1, a) TRANS_FEAT(FCVTNT_sh, aa64_sve2, gen_gvec_fpst_arg_zpz, gen_helper_sve2_fcvtnt_sh, a, 0, FPST_FPCR) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 9 --------- target/arm/translate-sve.c | 6 ++++++ 2 files changed, 6 insertions(+), 9 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) FAIL 1000 0100 0-1- ---- 0--- ---- ---- ---- # SVE 32-bit gather prefetch (scalar+vector) -FAIL 1000 010- -01- ---- 1--- ---- ---- ---- # SVE 32-bit gather load (vector+imm) -FAIL 1000 0100 0-0- ---- 0--- ---- ---- ---- # SVE 32-bit gather load byte (scalar+vector) -FAIL 1000 0100 1--- ---- 0--- ---- ---- ---- # SVE 32-bit gather load half (scalar+vector) -FAIL 1000 0101 0--- ---- 0--- ---- ---- ---- # SVE 32-bit gather load word (scalar+vector) FAIL 1010 010- ---- ---- 011- ---- ---- ---- # SVE contiguous FF load (scalar+scalar) FAIL 1010 010- ---1 ---- 101- ---- ---- ---- # SVE contiguous NF load (scalar+imm) FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) FAIL 1100 010- ---- ---- ---- ---- ---- ---- # SVE 64-bit gather load/prefetch -FAIL 1110 010- -00- ---- 001- ---- ---- ---- # SVE2 64-bit scatter NT store (vector+scalar) -FAIL 1110 010- -10- ---- 001- ---- ---- ---- # SVE2 32-bit scatter NT store (vector+scalar) -FAIL 1110 010- ---- ---- 1-0- ---- ---- ---- # SVE scatter store (scalar+32-bit vector) -FAIL 1110 010- ---- ---- 101- ---- ---- ---- # SVE scatter store (misc) 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_LD1_zprz(DisasContext *s, arg_LD1_zprz *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_LDNT1_zprz(DisasContext *s, arg_LD1_zprz *a) if (!dc_isar_feature(aa64_sve2, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_STNT1_zprz(DisasContext *s, arg_ST1_zprz *a) if (!dc_isar_feature(aa64_sve2, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. In this case, introduce PRF_ns (prefetch non-streaming) to handle the checks. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 3 --- target/arm/sve.decode | 10 +++++----- target/arm/translate-sve.c | 11 +++++++++++ 3 files changed, 16 insertions(+), 8 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) -FAIL 1000 0100 0-1- ---- 0--- ---- ---- ---- # SVE 32-bit gather prefetch (scalar+vector) FAIL 1010 010- ---- ---- 011- ---- ---- ---- # SVE contiguous FF load (scalar+scalar) FAIL 1010 010- ---1 ---- 101- ---- ---- ---- # SVE contiguous NF load (scalar+imm) FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) -FAIL 1100 010- ---- ---- ---- ---- ---- ---- # SVE 64-bit gather load/prefetch diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ LD1RO_zpri 1010010 .. 01 0.... 001 ... ..... ..... \ @rpri_load_msz nreg=0 # SVE 32-bit gather prefetch (scalar plus 32-bit scaled offsets) -PRF 1000010 00 -1 ----- 0-- --- ----- 0 ---- +PRF_ns 1000010 00 -1 ----- 0-- --- ----- 0 ---- # SVE 32-bit gather prefetch (vector plus immediate) -PRF 1000010 -- 00 ----- 111 --- ----- 0 ---- +PRF_ns 1000010 -- 00 ----- 111 --- ----- 0 ---- # SVE contiguous prefetch (scalar plus immediate) PRF 1000010 11 1- ----- 0-- --- ----- 0 ---- @@ -XXX,XX +XXX,XX @@ LD1_zpiz 1100010 .. 01 ..... 1.. ... ..... ..... \ @rpri_g_load esz=3 # SVE 64-bit gather prefetch (scalar plus 64-bit scaled offsets) -PRF 1100010 00 11 ----- 1-- --- ----- 0 ---- +PRF_ns 1100010 00 11 ----- 1-- --- ----- 0 ---- # SVE 64-bit gather prefetch (scalar plus unpacked 32-bit scaled offsets) -PRF 1100010 00 -1 ----- 0-- --- ----- 0 ---- +PRF_ns 1100010 00 -1 ----- 0-- --- ----- 0 ---- # SVE 64-bit gather prefetch (vector plus immediate) -PRF 1100010 -- 00 ----- 111 --- ----- 0 ---- +PRF_ns 1100010 -- 00 ----- 111 --- ----- 0 ---- ### SVE Memory Store Group 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_PRF_rr(DisasContext *s, arg_PRF_rr *a) return true; } +static bool trans_PRF_ns(DisasContext *s, arg_PRF_ns *a) +{ + if (!dc_isar_feature(aa64_sve, s)) { + return false; + } + /* Prefetch is a nop within QEMU. */ + s->is_nonstreaming = true; + (void)sve_access_check(s); + return true; +} + /* * Move Prefix * -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 2 -- target/arm/translate-sve.c | 2 ++ 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 1010 010- ---- ---- 011- ---- ---- ---- # SVE contiguous FF load (scalar+scalar) -FAIL 1010 010- ---1 ---- 101- ---- ---- ---- # SVE contiguous NF load (scalar+imm) FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) 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_LDFF1_zprr(DisasContext *s, arg_rprr_load *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (sve_access_check(s)) { TCGv_i64 addr = new_tmp_a64(s); tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype)); @@ -XXX,XX +XXX,XX @@ static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (sve_access_check(s)) { int vsz = vec_full_reg_size(s); int elements = vsz >> dtype_esz[a->dtype]; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 3 --- target/arm/translate-sve.c | 2 ++ 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --0- ---- ---- ---- ---- ---- # Load/store FP register (unscaled imm) # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) - -FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) -FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) 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_LD1RO_zprr(DisasContext *s, arg_rprr_load *a) if (a->rm == 31) { return false; } + s->is_nonstreaming = true; if (sve_access_check(s)) { TCGv_i64 addr = new_tmp_a64(s); tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype)); @@ -XXX,XX +XXX,XX @@ static bool trans_LD1RO_zpri(DisasContext *s, arg_rpri_load *a) if (!dc_isar_feature(aa64_sve_f64mm, s)) { return false; } + s->is_nonstreaming = true; if (sve_access_check(s)) { TCGv_i64 addr = new_tmp_a64(s); tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), a->imm * 32); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> These functions will be used to verify that the cpu is in the correct state for a given instruction. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 21 +++++++++++++++++++++ target/arm/translate-a64.c | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 55 insertions(+) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ void write_fp_dreg(DisasContext *s, int reg, TCGv_i64 v); bool logic_imm_decode_wmask(uint64_t *result, unsigned int immn, unsigned int imms, unsigned int immr); bool sve_access_check(DisasContext *s); +bool sme_enabled_check(DisasContext *s); +bool sme_enabled_check_with_svcr(DisasContext *s, unsigned); + +/* This function corresponds to CheckStreamingSVEEnabled. */ +static inline bool sme_sm_enabled_check(DisasContext *s) +{ + return sme_enabled_check_with_svcr(s, R_SVCR_SM_MASK); +} + +/* This function corresponds to CheckSMEAndZAEnabled. */ +static inline bool sme_za_enabled_check(DisasContext *s) +{ + return sme_enabled_check_with_svcr(s, R_SVCR_ZA_MASK); +} + +/* Note that this function corresponds to CheckStreamingSVEAndZAEnabled. */ +static inline bool sme_smza_enabled_check(DisasContext *s) +{ + return sme_enabled_check_with_svcr(s, R_SVCR_SM_MASK | R_SVCR_ZA_MASK); +} + TCGv_i64 clean_data_tbi(DisasContext *s, TCGv_i64 addr); TCGv_i64 gen_mte_check1(DisasContext *s, TCGv_i64 addr, bool is_write, bool tag_checked, int log2_size); 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 bool sme_access_check(DisasContext *s) return true; } +/* This function corresponds to CheckSMEEnabled. */ +bool sme_enabled_check(DisasContext *s) +{ + /* + * Note that unlike sve_excp_el, we have not constrained sme_excp_el + * to be zero when fp_excp_el has priority. This is because we need + * sme_excp_el by itself for cpregs access checks. + */ + if (!s->fp_excp_el || s->sme_excp_el < s->fp_excp_el) { + s->fp_access_checked = true; + return sme_access_check(s); + } + return fp_access_check_only(s); +} + +/* Common subroutine for CheckSMEAnd*Enabled. */ +bool sme_enabled_check_with_svcr(DisasContext *s, unsigned req) +{ + if (!sme_enabled_check(s)) { + return false; + } + if (FIELD_EX64(req, SVCR, SM) && !s->pstate_sm) { + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_smetrap(SME_ET_NotStreaming, false)); + return false; + } + if (FIELD_EX64(req, SVCR, ZA) && !s->pstate_za) { + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_smetrap(SME_ET_InactiveZA, false)); + return false; + } + return true; +} + /* * This utility function is for doing register extension with an * optional shift. You will likely want to pass a temporary for the -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> The pseudocode for CheckSVEEnabled gains a check for Streaming SVE mode, and for SME present but SVE absent. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 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 bool fp_access_check(DisasContext *s) return true; } -/* Check that SVE access is enabled. If it is, return true. +/* + * Check that SVE access is enabled. If it is, return true. * If not, emit code to generate an appropriate exception and return false. + * This function corresponds to CheckSVEEnabled(). */ bool sve_access_check(DisasContext *s) { - if (s->sve_excp_el) { - assert(!s->sve_access_checked); - s->sve_access_checked = true; - + if (s->pstate_sm || !dc_isar_feature(aa64_sve, s)) { + assert(dc_isar_feature(aa64_sme, s)); + if (!sme_sm_enabled_check(s)) { + goto fail_exit; + } + } else if (s->sve_excp_el) { gen_exception_insn_el(s, s->pc_curr, EXCP_UDEF, syn_sve_access_trap(), s->sve_excp_el); - return false; + goto fail_exit; } s->sve_access_checked = true; return fp_access_check(s); + + fail_exit: + /* Assert that we only raise one exception per instruction. */ + assert(!s->sve_access_checked); + s->sve_access_checked = true; + return false; } /* -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> These SME instructions are nominally within the SVE decode space, so we add them to sve.decode and translate-sve.c. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 12 ++++++++++++ target/arm/sve.decode | 5 ++++- target/arm/translate-sve.c | 38 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 54 insertions(+), 1 deletion(-) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ static inline int vec_full_reg_size(DisasContext *s) return s->vl; } +/* Return the byte size of the vector register, SVL / 8. */ +static inline int streaming_vec_reg_size(DisasContext *s) +{ + return s->svl; +} + /* * Return the offset info CPUARMState of the predicate vector register Pn. * Note for this purpose, FFR is P16. @@ -XXX,XX +XXX,XX @@ static inline int pred_full_reg_size(DisasContext *s) return s->vl >> 3; } +/* Return the byte size of the predicate register, SVL / 64. */ +static inline int streaming_pred_reg_size(DisasContext *s) +{ + return s->svl >> 3; +} + /* * Round up the size of a register to a size allowed by * the tcg vector infrastructure. Any operation which uses this diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ INDEX_ri 00000100 esz:2 1 imm:s5 010001 rn:5 rd:5 # SVE index generation (register start, register increment) INDEX_rr 00000100 .. 1 ..... 010011 ..... ..... @rd_rn_rm -### SVE Stack Allocation Group +### SVE / Streaming SVE Stack Allocation Group # SVE stack frame adjustment ADDVL 00000100 001 ..... 01010 ...... ..... @rd_rn_i6 +ADDSVL 00000100 001 ..... 01011 ...... ..... @rd_rn_i6 ADDPL 00000100 011 ..... 01010 ...... ..... @rd_rn_i6 +ADDSPL 00000100 011 ..... 01011 ...... ..... @rd_rn_i6 # SVE stack frame size RDVL 00000100 101 11111 01010 imm:s6 rd:5 +RDSVL 00000100 101 11111 01011 imm:s6 rd:5 ### SVE Bitwise Shift - Unpredicated Group 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_ADDVL(DisasContext *s, arg_ADDVL *a) return true; } +static bool trans_ADDSVL(DisasContext *s, arg_ADDSVL *a) +{ + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (sme_enabled_check(s)) { + TCGv_i64 rd = cpu_reg_sp(s, a->rd); + TCGv_i64 rn = cpu_reg_sp(s, a->rn); + tcg_gen_addi_i64(rd, rn, a->imm * streaming_vec_reg_size(s)); + } + return true; +} + static bool trans_ADDPL(DisasContext *s, arg_ADDPL *a) { if (!dc_isar_feature(aa64_sve, s)) { @@ -XXX,XX +XXX,XX @@ static bool trans_ADDPL(DisasContext *s, arg_ADDPL *a) return true; } +static bool trans_ADDSPL(DisasContext *s, arg_ADDSPL *a) +{ + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (sme_enabled_check(s)) { + TCGv_i64 rd = cpu_reg_sp(s, a->rd); + TCGv_i64 rn = cpu_reg_sp(s, a->rn); + tcg_gen_addi_i64(rd, rn, a->imm * streaming_pred_reg_size(s)); + } + return true; +} + static bool trans_RDVL(DisasContext *s, arg_RDVL *a) { if (!dc_isar_feature(aa64_sve, s)) { @@ -XXX,XX +XXX,XX @@ static bool trans_RDVL(DisasContext *s, arg_RDVL *a) return true; } +static bool trans_RDSVL(DisasContext *s, arg_RDSVL *a) +{ + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (sme_enabled_check(s)) { + TCGv_i64 reg = cpu_reg(s, a->rd); + tcg_gen_movi_i64(reg, a->imm * streaming_vec_reg_size(s)); + } + return true; +} + /* *** SVE Compute Vector Address Group */ -- 2.25.1 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: 20220708151540.18136-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 2 ++ target/arm/sme.decode | 4 ++++ target/arm/sme_helper.c | 25 +++++++++++++++++++++++++ target/arm/translate-sme.c | 13 +++++++++++++ 4 files changed, 44 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(set_pstate_sm, TCG_CALL_NO_RWG, void, env, i32) DEF_HELPER_FLAGS_2(set_pstate_za, TCG_CALL_NO_RWG, void, env, i32) + +DEF_HELPER_FLAGS_3(sme_zero, TCG_CALL_NO_RWG, void, env, i32, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ # # This file is processed by scripts/decodetree.py # + +### SME Misc + +ZERO 11000000 00 001 00000000000 imm:8 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ void helper_set_pstate_za(CPUARMState *env, uint32_t i) memset(env->zarray, 0, sizeof(env->zarray)); } } + +void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl) +{ + uint32_t i; + + /* + * Special case clearing the entire ZA space. + * This falls into the CONSTRAINED UNPREDICTABLE zeroing of any + * parts of the ZA storage outside of SVL. + */ + if (imm == 0xff) { + memset(env->zarray, 0, sizeof(env->zarray)); + return; + } + + /* + * Recall that ZAnH.D[m] is spread across ZA[n+8*m], + * so each row is discontiguous within ZA[]. + */ + for (i = 0; i < svl; i++) { + if (imm & (1 << (i % 8))) { + memset(&env->zarray[i], 0, svl); + } + } +} diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ */ #include "decode-sme.c.inc" + + +static bool trans_ZERO(DisasContext *s, arg_ZERO *a) +{ + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (sme_za_enabled_check(s)) { + gen_helper_sme_zero(cpu_env, tcg_constant_i32(a->imm), + tcg_constant_i32(streaming_vec_reg_size(s))); + } + return true; +} -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We can reuse the SVE functions for implementing moves to/from horizontal tile slices, but we need new ones for moves to/from vertical tile slices. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-20-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 12 +++ target/arm/helper-sve.h | 2 + target/arm/translate-a64.h | 8 ++ target/arm/translate.h | 5 ++ target/arm/sme.decode | 15 ++++ target/arm/sme_helper.c | 151 ++++++++++++++++++++++++++++++++++++- target/arm/sve_helper.c | 12 +++ target/arm/translate-sme.c | 127 +++++++++++++++++++++++++++++++ 8 files changed, 331 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(set_pstate_sm, TCG_CALL_NO_RWG, void, env, i32) DEF_HELPER_FLAGS_2(set_pstate_za, TCG_CALL_NO_RWG, void, env, i32) DEF_HELPER_FLAGS_3(sme_zero, TCG_CALL_NO_RWG, void, env, i32, i32) + +/* Move to/from vertical array slices, i.e. columns, so 'c'. */ +DEF_HELPER_FLAGS_4(sme_mova_cz_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_cz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_cz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_cz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_cz_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_sel_zpzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_sel_zpzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_sel_zpzz_q, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_addp_zpzz_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ static inline int pred_gvec_reg_size(DisasContext *s) return size_for_gvec(pred_full_reg_size(s)); } +/* Return a newly allocated pointer to the predicate register. */ +static inline TCGv_ptr pred_full_reg_ptr(DisasContext *s, int regno) +{ + TCGv_ptr ret = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(ret, cpu_env, pred_full_reg_offset(s, regno)); + return ret; +} + bool disas_sve(DisasContext *, uint32_t); bool disas_sme(DisasContext *, uint32_t); 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 @@ static inline int plus_2(DisasContext *s, int x) return x + 2; } +static inline int plus_12(DisasContext *s, int x) +{ + return x + 12; +} + static inline int times_2(DisasContext *s, int x) { return x * 2; diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ ### SME Misc ZERO 11000000 00 001 00000000000 imm:8 + +### SME Move into/from Array + +%mova_rs 13:2 !function=plus_12 +&mova esz rs pg zr za_imm v:bool to_vec:bool + +MOVA 11000000 esz:2 00000 0 v:1 .. pg:3 zr:5 0 za_imm:4 \ + &mova to_vec=0 rs=%mova_rs +MOVA 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za_imm:4 \ + &mova to_vec=0 rs=%mova_rs esz=4 + +MOVA 11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5 \ + &mova to_vec=1 rs=%mova_rs +MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za_imm:4 zr:5 \ + &mova to_vec=1 rs=%mova_rs esz=4 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" -#include "internals.h" +#include "tcg/tcg-gvec-desc.h" #include "exec/helper-proto.h" +#include "qemu/int128.h" +#include "vec_internal.h" /* ResetSVEState */ void arm_reset_sve_state(CPUARMState *env) @@ -XXX,XX +XXX,XX @@ void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl) } } } + + +/* + * When considering the ZA storage as an array of elements of + * type T, the index within that array of the Nth element of + * a vertical slice of a tile can be calculated like this, + * regardless of the size of type T. This is because the tiles + * are interleaved, so if type T is size N bytes then row 1 of + * the tile is N rows away from row 0. The division by N to + * convert a byte offset into an array index and the multiplication + * by N to convert from vslice-index-within-the-tile to + * the index within the ZA storage cancel out. + */ +#define tile_vslice_index(i) ((i) * sizeof(ARMVectorReg)) + +/* + * When doing byte arithmetic on the ZA storage, the element + * byteoff bytes away in a tile vertical slice is always this + * many bytes away in the ZA storage, regardless of the + * size of the tile element, assuming that byteoff is a multiple + * of the element size. Again this is because of the interleaving + * of the tiles. For instance if we have 1 byte per element then + * each row of the ZA storage has one byte of the vslice data, + * and (counting from 0) byte 8 goes in row 8 of the storage + * at offset (8 * row-size-in-bytes). + * If we have 8 bytes per element then each row of the ZA storage + * has 8 bytes of the data, but there are 8 interleaved tiles and + * so byte 8 of the data goes into row 1 of the tile, + * which is again row 8 of the storage, so the offset is still + * (8 * row-size-in-bytes). Similarly for other element sizes. + */ +#define tile_vslice_offset(byteoff) ((byteoff) * sizeof(ARMVectorReg)) + + +/* + * Move Zreg vector to ZArray column. + */ +#define DO_MOVA_C(NAME, TYPE, H) \ +void HELPER(NAME)(void *za, void *vn, void *vg, uint32_t desc) \ +{ \ + int i, oprsz = simd_oprsz(desc); \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + if (pg & 1) { \ + *(TYPE *)(za + tile_vslice_offset(i)) = *(TYPE *)(vn + H(i)); \ + } \ + i += sizeof(TYPE); \ + pg >>= sizeof(TYPE); \ + } while (i & 15); \ + } \ +} + +DO_MOVA_C(sme_mova_cz_b, uint8_t, H1) +DO_MOVA_C(sme_mova_cz_h, uint16_t, H1_2) +DO_MOVA_C(sme_mova_cz_s, uint32_t, H1_4) + +void HELPER(sme_mova_cz_d)(void *za, void *vn, void *vg, uint32_t desc) +{ + int i, oprsz = simd_oprsz(desc) / 8; + uint8_t *pg = vg; + uint64_t *n = vn; + uint64_t *a = za; + + for (i = 0; i < oprsz; i++) { + if (pg[H1(i)] & 1) { + a[tile_vslice_index(i)] = n[i]; + } + } +} + +void HELPER(sme_mova_cz_q)(void *za, void *vn, void *vg, uint32_t desc) +{ + int i, oprsz = simd_oprsz(desc) / 16; + uint16_t *pg = vg; + Int128 *n = vn; + Int128 *a = za; + + /* + * Int128 is used here simply to copy 16 bytes, and to simplify + * the address arithmetic. + */ + for (i = 0; i < oprsz; i++) { + if (pg[H2(i)] & 1) { + a[tile_vslice_index(i)] = n[i]; + } + } +} + +#undef DO_MOVA_C + +/* + * Move ZArray column to Zreg vector. + */ +#define DO_MOVA_Z(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *za, void *vg, uint32_t desc) \ +{ \ + int i, oprsz = simd_oprsz(desc); \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + if (pg & 1) { \ + *(TYPE *)(vd + H(i)) = *(TYPE *)(za + tile_vslice_offset(i)); \ + } \ + i += sizeof(TYPE); \ + pg >>= sizeof(TYPE); \ + } while (i & 15); \ + } \ +} + +DO_MOVA_Z(sme_mova_zc_b, uint8_t, H1) +DO_MOVA_Z(sme_mova_zc_h, uint16_t, H1_2) +DO_MOVA_Z(sme_mova_zc_s, uint32_t, H1_4) + +void HELPER(sme_mova_zc_d)(void *vd, void *za, void *vg, uint32_t desc) +{ + int i, oprsz = simd_oprsz(desc) / 8; + uint8_t *pg = vg; + uint64_t *d = vd; + uint64_t *a = za; + + for (i = 0; i < oprsz; i++) { + if (pg[H1(i)] & 1) { + d[i] = a[tile_vslice_index(i)]; + } + } +} + +void HELPER(sme_mova_zc_q)(void *vd, void *za, void *vg, uint32_t desc) +{ + int i, oprsz = simd_oprsz(desc) / 16; + uint16_t *pg = vg; + Int128 *d = vd; + Int128 *a = za; + + /* + * Int128 is used here simply to copy 16 bytes, and to simplify + * the address arithmetic. + */ + for (i = 0; i < oprsz; i++, za += sizeof(ARMVectorReg)) { + if (pg[H2(i)] & 1) { + d[i] = a[tile_vslice_index(i)]; + } + } +} + +#undef DO_MOVA_Z diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_sel_zpzz_d)(void *vd, void *vn, void *vm, } } +void HELPER(sve_sel_zpzz_q)(void *vd, void *vn, void *vm, + void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 16; + Int128 *d = vd, *n = vn, *m = vm; + uint16_t *pg = vg; + + for (i = 0; i < opr_sz; i += 1) { + d[i] = (pg[H2(i)] & 1 ? n : m)[i]; + } +} + /* Two operand comparison controlled by a predicate. * ??? It is very tempting to want to be able to expand this inline * with x86 instructions, e.g. diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ #include "decode-sme.c.inc" +/* + * Resolve tile.size[index] to a host pointer, where tile and index + * are always decoded together, dependent on the element size. + */ +static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs, + int tile_index, bool vertical) +{ + int tile = tile_index >> (4 - esz); + int index = esz == MO_128 ? 0 : extract32(tile_index, 0, 4 - esz); + int pos, len, offset; + TCGv_i32 tmp; + TCGv_ptr addr; + + /* Compute the final index, which is Rs+imm. */ + tmp = tcg_temp_new_i32(); + tcg_gen_trunc_tl_i32(tmp, cpu_reg(s, rs)); + tcg_gen_addi_i32(tmp, tmp, index); + + /* Prepare a power-of-two modulo via extraction of @len bits. */ + len = ctz32(streaming_vec_reg_size(s)) - esz; + + if (vertical) { + /* + * Compute the byte offset of the index within the tile: + * (index % (svl / size)) * size + * = (index % (svl >> esz)) << esz + * Perform the power-of-two modulo via extraction of the low @len bits. + * Perform the multiply by shifting left by @pos bits. + * Perform these operations simultaneously via deposit into zero. + */ + pos = esz; + tcg_gen_deposit_z_i32(tmp, tmp, pos, len); + + /* + * For big-endian, adjust the indexed column byte offset within + * the uint64_t host words that make up env->zarray[]. + */ + if (HOST_BIG_ENDIAN && esz < MO_64) { + tcg_gen_xori_i32(tmp, tmp, 8 - (1 << esz)); + } + } else { + /* + * Compute the byte offset of the index within the tile: + * (index % (svl / size)) * (size * sizeof(row)) + * = (index % (svl >> esz)) << (esz + log2(sizeof(row))) + */ + pos = esz + ctz32(sizeof(ARMVectorReg)); + tcg_gen_deposit_z_i32(tmp, tmp, pos, len); + + /* Row slices are always aligned and need no endian adjustment. */ + } + + /* The tile byte offset within env->zarray is the row. */ + offset = tile * sizeof(ARMVectorReg); + + /* Include the byte offset of zarray to make this relative to env. */ + offset += offsetof(CPUARMState, zarray); + tcg_gen_addi_i32(tmp, tmp, offset); + + /* Add the byte offset to env to produce the final pointer. */ + addr = tcg_temp_new_ptr(); + tcg_gen_ext_i32_ptr(addr, tmp); + tcg_temp_free_i32(tmp); + tcg_gen_add_ptr(addr, addr, cpu_env); + + return addr; +} + static bool trans_ZERO(DisasContext *s, arg_ZERO *a) { if (!dc_isar_feature(aa64_sme, s)) { @@ -XXX,XX +XXX,XX @@ static bool trans_ZERO(DisasContext *s, arg_ZERO *a) } return true; } + +static bool trans_MOVA(DisasContext *s, arg_MOVA *a) +{ + static gen_helper_gvec_4 * const h_fns[5] = { + gen_helper_sve_sel_zpzz_b, gen_helper_sve_sel_zpzz_h, + gen_helper_sve_sel_zpzz_s, gen_helper_sve_sel_zpzz_d, + gen_helper_sve_sel_zpzz_q + }; + static gen_helper_gvec_3 * const cz_fns[5] = { + gen_helper_sme_mova_cz_b, gen_helper_sme_mova_cz_h, + gen_helper_sme_mova_cz_s, gen_helper_sme_mova_cz_d, + gen_helper_sme_mova_cz_q, + }; + static gen_helper_gvec_3 * const zc_fns[5] = { + gen_helper_sme_mova_zc_b, gen_helper_sme_mova_zc_h, + gen_helper_sme_mova_zc_s, gen_helper_sme_mova_zc_d, + gen_helper_sme_mova_zc_q, + }; + + TCGv_ptr t_za, t_zr, t_pg; + TCGv_i32 t_desc; + int svl; + + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (!sme_smza_enabled_check(s)) { + return true; + } + + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v); + t_zr = vec_full_reg_ptr(s, a->zr); + t_pg = pred_full_reg_ptr(s, a->pg); + + svl = streaming_vec_reg_size(s); + t_desc = tcg_constant_i32(simd_desc(svl, svl, 0)); + + if (a->v) { + /* Vertical slice -- use sme mova helpers. */ + if (a->to_vec) { + zc_fns[a->esz](t_zr, t_za, t_pg, t_desc); + } else { + cz_fns[a->esz](t_za, t_zr, t_pg, t_desc); + } + } else { + /* Horizontal slice -- reuse sve sel helpers. */ + if (a->to_vec) { + h_fns[a->esz](t_zr, t_za, t_zr, t_pg, t_desc); + } else { + h_fns[a->esz](t_za, t_zr, t_za, t_pg, t_desc); + } + } + + tcg_temp_free_ptr(t_za); + tcg_temp_free_ptr(t_zr); + tcg_temp_free_ptr(t_pg); + + return true; +} -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We cannot reuse the SVE functions for LD[1-4] and ST[1-4], because those functions accept only a Zreg register number. For SME, we want to pass a pointer into ZA storage. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-21-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 82 +++++ target/arm/sme.decode | 9 + target/arm/sme_helper.c | 595 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 70 +++++ 4 files changed, 756 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sme_mova_cz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme_mova_cz_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme_mova_zc_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sme_ld1b_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1b_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1b_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1b_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_ld1h_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_ld1s_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_ld1d_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_ld1q_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1b_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1b_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1b_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1b_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1h_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1s_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1d_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1q_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ MOVA 11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5 \ &mova to_vec=1 rs=%mova_rs MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za_imm:4 zr:5 \ &mova to_vec=1 rs=%mova_rs esz=4 + +### SME Memory + +&ldst esz rs pg rn rm za_imm v:bool st:bool + +LDST1 1110000 0 esz:2 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ + &ldst rs=%mova_rs +LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ + &ldst esz=4 rs=%mova_rs diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" +#include "internals.h" #include "tcg/tcg-gvec-desc.h" #include "exec/helper-proto.h" +#include "exec/cpu_ldst.h" +#include "exec/exec-all.h" #include "qemu/int128.h" #include "vec_internal.h" +#include "sve_ldst_internal.h" /* ResetSVEState */ void arm_reset_sve_state(CPUARMState *env) @@ -XXX,XX +XXX,XX @@ void HELPER(sme_mova_zc_q)(void *vd, void *za, void *vg, uint32_t desc) } #undef DO_MOVA_Z + +/* + * Clear elements in a tile slice comprising len bytes. + */ + +typedef void ClearFn(void *ptr, size_t off, size_t len); + +static void clear_horizontal(void *ptr, size_t off, size_t len) +{ + memset(ptr + off, 0, len); +} + +static void clear_vertical_b(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; ++i) { + *(uint8_t *)(vptr + tile_vslice_offset(i + off)) = 0; + } +} + +static void clear_vertical_h(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; i += 2) { + *(uint16_t *)(vptr + tile_vslice_offset(i + off)) = 0; + } +} + +static void clear_vertical_s(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; i += 4) { + *(uint32_t *)(vptr + tile_vslice_offset(i + off)) = 0; + } +} + +static void clear_vertical_d(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; i += 8) { + *(uint64_t *)(vptr + tile_vslice_offset(i + off)) = 0; + } +} + +static void clear_vertical_q(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; i += 16) { + memset(vptr + tile_vslice_offset(i + off), 0, 16); + } +} + +/* + * Copy elements from an array into a tile slice comprising len bytes. + */ + +typedef void CopyFn(void *dst, const void *src, size_t len); + +static void copy_horizontal(void *dst, const void *src, size_t len) +{ + memcpy(dst, src, len); +} + +static void copy_vertical_b(void *vdst, const void *vsrc, size_t len) +{ + const uint8_t *src = vsrc; + uint8_t *dst = vdst; + size_t i; + + for (i = 0; i < len; ++i) { + dst[tile_vslice_index(i)] = src[i]; + } +} + +static void copy_vertical_h(void *vdst, const void *vsrc, size_t len) +{ + const uint16_t *src = vsrc; + uint16_t *dst = vdst; + size_t i; + + for (i = 0; i < len / 2; ++i) { + dst[tile_vslice_index(i)] = src[i]; + } +} + +static void copy_vertical_s(void *vdst, const void *vsrc, size_t len) +{ + const uint32_t *src = vsrc; + uint32_t *dst = vdst; + size_t i; + + for (i = 0; i < len / 4; ++i) { + dst[tile_vslice_index(i)] = src[i]; + } +} + +static void copy_vertical_d(void *vdst, const void *vsrc, size_t len) +{ + const uint64_t *src = vsrc; + uint64_t *dst = vdst; + size_t i; + + for (i = 0; i < len / 8; ++i) { + dst[tile_vslice_index(i)] = src[i]; + } +} + +static void copy_vertical_q(void *vdst, const void *vsrc, size_t len) +{ + for (size_t i = 0; i < len; i += 16) { + memcpy(vdst + tile_vslice_offset(i), vsrc + i, 16); + } +} + +/* + * Host and TLB primitives for vertical tile slice addressing. + */ + +#define DO_LD(NAME, TYPE, HOST, TLB) \ +static inline void sme_##NAME##_v_host(void *za, intptr_t off, void *host) \ +{ \ + TYPE val = HOST(host); \ + *(TYPE *)(za + tile_vslice_offset(off)) = val; \ +} \ +static inline void sme_##NAME##_v_tlb(CPUARMState *env, void *za, \ + intptr_t off, target_ulong addr, uintptr_t ra) \ +{ \ + TYPE val = TLB(env, useronly_clean_ptr(addr), ra); \ + *(TYPE *)(za + tile_vslice_offset(off)) = val; \ +} + +#define DO_ST(NAME, TYPE, HOST, TLB) \ +static inline void sme_##NAME##_v_host(void *za, intptr_t off, void *host) \ +{ \ + TYPE val = *(TYPE *)(za + tile_vslice_offset(off)); \ + HOST(host, val); \ +} \ +static inline void sme_##NAME##_v_tlb(CPUARMState *env, void *za, \ + intptr_t off, target_ulong addr, uintptr_t ra) \ +{ \ + TYPE val = *(TYPE *)(za + tile_vslice_offset(off)); \ + TLB(env, useronly_clean_ptr(addr), val, ra); \ +} + +/* + * The ARMVectorReg elements are stored in host-endian 64-bit units. + * For 128-bit quantities, the sequence defined by the Elem[] pseudocode + * corresponds to storing the two 64-bit pieces in little-endian order. + */ +#define DO_LDQ(HNAME, VNAME, BE, HOST, TLB) \ +static inline void HNAME##_host(void *za, intptr_t off, void *host) \ +{ \ + uint64_t val0 = HOST(host), val1 = HOST(host + 8); \ + uint64_t *ptr = za + off; \ + ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1; \ +} \ +static inline void VNAME##_v_host(void *za, intptr_t off, void *host) \ +{ \ + HNAME##_host(za, tile_vslice_offset(off), host); \ +} \ +static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off, \ + target_ulong addr, uintptr_t ra) \ +{ \ + uint64_t val0 = TLB(env, useronly_clean_ptr(addr), ra); \ + uint64_t val1 = TLB(env, useronly_clean_ptr(addr + 8), ra); \ + uint64_t *ptr = za + off; \ + ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1; \ +} \ +static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off, \ + target_ulong addr, uintptr_t ra) \ +{ \ + HNAME##_tlb(env, za, tile_vslice_offset(off), addr, ra); \ +} + +#define DO_STQ(HNAME, VNAME, BE, HOST, TLB) \ +static inline void HNAME##_host(void *za, intptr_t off, void *host) \ +{ \ + uint64_t *ptr = za + off; \ + HOST(host, ptr[BE]); \ + HOST(host + 1, ptr[!BE]); \ +} \ +static inline void VNAME##_v_host(void *za, intptr_t off, void *host) \ +{ \ + HNAME##_host(za, tile_vslice_offset(off), host); \ +} \ +static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off, \ + target_ulong addr, uintptr_t ra) \ +{ \ + uint64_t *ptr = za + off; \ + TLB(env, useronly_clean_ptr(addr), ptr[BE], ra); \ + TLB(env, useronly_clean_ptr(addr + 8), ptr[!BE], ra); \ +} \ +static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off, \ + target_ulong addr, uintptr_t ra) \ +{ \ + HNAME##_tlb(env, za, tile_vslice_offset(off), addr, ra); \ +} + +DO_LD(ld1b, uint8_t, ldub_p, cpu_ldub_data_ra) +DO_LD(ld1h_be, uint16_t, lduw_be_p, cpu_lduw_be_data_ra) +DO_LD(ld1h_le, uint16_t, lduw_le_p, cpu_lduw_le_data_ra) +DO_LD(ld1s_be, uint32_t, ldl_be_p, cpu_ldl_be_data_ra) +DO_LD(ld1s_le, uint32_t, ldl_le_p, cpu_ldl_le_data_ra) +DO_LD(ld1d_be, uint64_t, ldq_be_p, cpu_ldq_be_data_ra) +DO_LD(ld1d_le, uint64_t, ldq_le_p, cpu_ldq_le_data_ra) + +DO_LDQ(sve_ld1qq_be, sme_ld1q_be, 1, ldq_be_p, cpu_ldq_be_data_ra) +DO_LDQ(sve_ld1qq_le, sme_ld1q_le, 0, ldq_le_p, cpu_ldq_le_data_ra) + +DO_ST(st1b, uint8_t, stb_p, cpu_stb_data_ra) +DO_ST(st1h_be, uint16_t, stw_be_p, cpu_stw_be_data_ra) +DO_ST(st1h_le, uint16_t, stw_le_p, cpu_stw_le_data_ra) +DO_ST(st1s_be, uint32_t, stl_be_p, cpu_stl_be_data_ra) +DO_ST(st1s_le, uint32_t, stl_le_p, cpu_stl_le_data_ra) +DO_ST(st1d_be, uint64_t, stq_be_p, cpu_stq_be_data_ra) +DO_ST(st1d_le, uint64_t, stq_le_p, cpu_stq_le_data_ra) + +DO_STQ(sve_st1qq_be, sme_st1q_be, 1, stq_be_p, cpu_stq_be_data_ra) +DO_STQ(sve_st1qq_le, sme_st1q_le, 0, stq_le_p, cpu_stq_le_data_ra) + +#undef DO_LD +#undef DO_ST +#undef DO_LDQ +#undef DO_STQ + +/* + * Common helper for all contiguous predicated loads. + */ + +static inline QEMU_ALWAYS_INLINE +void sme_ld1(CPUARMState *env, void *za, uint64_t *vg, + const target_ulong addr, uint32_t desc, const uintptr_t ra, + const int esz, uint32_t mtedesc, bool vertical, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn, + ClearFn *clr_fn, + CopyFn *cpy_fn) +{ + const intptr_t reg_max = simd_oprsz(desc); + const intptr_t esize = 1 << esz; + intptr_t reg_off, reg_last; + SVEContLdSt info; + void *host; + int flags; + + /* Find the active elements. */ + if (!sve_cont_ldst_elements(&info, addr, vg, reg_max, esz, esize)) { + /* The entire predicate was false; no load occurs. */ + clr_fn(za, 0, reg_max); + return; + } + + /* Probe the page(s). Exit with exception for any invalid page. */ + sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_LOAD, ra); + + /* Handle watchpoints for all active elements. */ + sve_cont_ldst_watchpoints(&info, env, vg, addr, esize, esize, + BP_MEM_READ, ra); + + /* + * Handle mte checks for all active elements. + * Since TBI must be set for MTE, !mtedesc => !mte_active. + */ + if (mtedesc) { + sve_cont_ldst_mte_check(&info, env, vg, addr, esize, esize, + mtedesc, ra); + } + + flags = info.page[0].flags | info.page[1].flags; + if (unlikely(flags != 0)) { +#ifdef CONFIG_USER_ONLY + g_assert_not_reached(); +#else + /* + * At least one page includes MMIO. + * Any bus operation can fail with cpu_transaction_failed, + * which for ARM will raise SyncExternal. Perform the load + * into scratch memory to preserve register state until the end. + */ + ARMVectorReg scratch = { }; + + reg_off = info.reg_off_first[0]; + reg_last = info.reg_off_last[1]; + if (reg_last < 0) { + reg_last = info.reg_off_split; + if (reg_last < 0) { + reg_last = info.reg_off_last[0]; + } + } + + do { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + tlb_fn(env, &scratch, reg_off, addr + reg_off, ra); + } + reg_off += esize; + } while (reg_off & 63); + } while (reg_off <= reg_last); + + cpy_fn(za, &scratch, reg_max); + return; +#endif + } + + /* The entire operation is in RAM, on valid pages. */ + + reg_off = info.reg_off_first[0]; + reg_last = info.reg_off_last[0]; + host = info.page[0].host; + + if (!vertical) { + memset(za, 0, reg_max); + } else if (reg_off) { + clr_fn(za, 0, reg_off); + } + + while (reg_off <= reg_last) { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + host_fn(za, reg_off, host + reg_off); + } else if (vertical) { + clr_fn(za, reg_off, esize); + } + reg_off += esize; + } while (reg_off <= reg_last && (reg_off & 63)); + } + + /* + * Use the slow path to manage the cross-page misalignment. + * But we know this is RAM and cannot trap. + */ + reg_off = info.reg_off_split; + if (unlikely(reg_off >= 0)) { + tlb_fn(env, za, reg_off, addr + reg_off, ra); + } + + reg_off = info.reg_off_first[1]; + if (unlikely(reg_off >= 0)) { + reg_last = info.reg_off_last[1]; + host = info.page[1].host; + + do { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + host_fn(za, reg_off, host + reg_off); + } else if (vertical) { + clr_fn(za, reg_off, esize); + } + reg_off += esize; + } while (reg_off & 63); + } while (reg_off <= reg_last); + } +} + +static inline QEMU_ALWAYS_INLINE +void sme_ld1_mte(CPUARMState *env, void *za, uint64_t *vg, + target_ulong addr, uint32_t desc, uintptr_t ra, + const int esz, bool vertical, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn, + ClearFn *clr_fn, + CopyFn *cpy_fn) +{ + uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + int bit55 = extract64(addr, 55, 1); + + /* Remove mtedesc from the normal sve descriptor. */ + desc = extract32(desc, 0, SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + + /* Perform gross MTE suppression early. */ + if (!tbi_check(desc, bit55) || + tcma_check(desc, bit55, allocation_tag_from_addr(addr))) { + mtedesc = 0; + } + + sme_ld1(env, za, vg, addr, desc, ra, esz, mtedesc, vertical, + host_fn, tlb_fn, clr_fn, cpy_fn); +} + +#define DO_LD(L, END, ESZ) \ +void HELPER(sme_ld1##L##END##_h)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_ld1(env, za, vg, addr, desc, GETPC(), ESZ, 0, false, \ + sve_ld1##L##L##END##_host, sve_ld1##L##L##END##_tlb, \ + clear_horizontal, copy_horizontal); \ +} \ +void HELPER(sme_ld1##L##END##_v)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_ld1(env, za, vg, addr, desc, GETPC(), ESZ, 0, true, \ + sme_ld1##L##END##_v_host, sme_ld1##L##END##_v_tlb, \ + clear_vertical_##L, copy_vertical_##L); \ +} \ +void HELPER(sme_ld1##L##END##_h_mte)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_ld1_mte(env, za, vg, addr, desc, GETPC(), ESZ, false, \ + sve_ld1##L##L##END##_host, sve_ld1##L##L##END##_tlb, \ + clear_horizontal, copy_horizontal); \ +} \ +void HELPER(sme_ld1##L##END##_v_mte)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_ld1_mte(env, za, vg, addr, desc, GETPC(), ESZ, true, \ + sme_ld1##L##END##_v_host, sme_ld1##L##END##_v_tlb, \ + clear_vertical_##L, copy_vertical_##L); \ +} + +DO_LD(b, , MO_8) +DO_LD(h, _be, MO_16) +DO_LD(h, _le, MO_16) +DO_LD(s, _be, MO_32) +DO_LD(s, _le, MO_32) +DO_LD(d, _be, MO_64) +DO_LD(d, _le, MO_64) +DO_LD(q, _be, MO_128) +DO_LD(q, _le, MO_128) + +#undef DO_LD + +/* + * Common helper for all contiguous predicated stores. + */ + +static inline QEMU_ALWAYS_INLINE +void sme_st1(CPUARMState *env, void *za, uint64_t *vg, + const target_ulong addr, uint32_t desc, const uintptr_t ra, + const int esz, uint32_t mtedesc, bool vertical, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn) +{ + const intptr_t reg_max = simd_oprsz(desc); + const intptr_t esize = 1 << esz; + intptr_t reg_off, reg_last; + SVEContLdSt info; + void *host; + int flags; + + /* Find the active elements. */ + if (!sve_cont_ldst_elements(&info, addr, vg, reg_max, esz, esize)) { + /* The entire predicate was false; no store occurs. */ + return; + } + + /* Probe the page(s). Exit with exception for any invalid page. */ + sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_STORE, ra); + + /* Handle watchpoints for all active elements. */ + sve_cont_ldst_watchpoints(&info, env, vg, addr, esize, esize, + BP_MEM_WRITE, ra); + + /* + * Handle mte checks for all active elements. + * Since TBI must be set for MTE, !mtedesc => !mte_active. + */ + if (mtedesc) { + sve_cont_ldst_mte_check(&info, env, vg, addr, esize, esize, + mtedesc, ra); + } + + flags = info.page[0].flags | info.page[1].flags; + if (unlikely(flags != 0)) { +#ifdef CONFIG_USER_ONLY + g_assert_not_reached(); +#else + /* + * At least one page includes MMIO. + * Any bus operation can fail with cpu_transaction_failed, + * which for ARM will raise SyncExternal. We cannot avoid + * this fault and will leave with the store incomplete. + */ + reg_off = info.reg_off_first[0]; + reg_last = info.reg_off_last[1]; + if (reg_last < 0) { + reg_last = info.reg_off_split; + if (reg_last < 0) { + reg_last = info.reg_off_last[0]; + } + } + + do { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + tlb_fn(env, za, reg_off, addr + reg_off, ra); + } + reg_off += esize; + } while (reg_off & 63); + } while (reg_off <= reg_last); + return; +#endif + } + + reg_off = info.reg_off_first[0]; + reg_last = info.reg_off_last[0]; + host = info.page[0].host; + + while (reg_off <= reg_last) { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + host_fn(za, reg_off, host + reg_off); + } + reg_off += 1 << esz; + } while (reg_off <= reg_last && (reg_off & 63)); + } + + /* + * Use the slow path to manage the cross-page misalignment. + * But we know this is RAM and cannot trap. + */ + reg_off = info.reg_off_split; + if (unlikely(reg_off >= 0)) { + tlb_fn(env, za, reg_off, addr + reg_off, ra); + } + + reg_off = info.reg_off_first[1]; + if (unlikely(reg_off >= 0)) { + reg_last = info.reg_off_last[1]; + host = info.page[1].host; + + do { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + host_fn(za, reg_off, host + reg_off); + } + reg_off += 1 << esz; + } while (reg_off & 63); + } while (reg_off <= reg_last); + } +} + +static inline QEMU_ALWAYS_INLINE +void sme_st1_mte(CPUARMState *env, void *za, uint64_t *vg, target_ulong addr, + uint32_t desc, uintptr_t ra, int esz, bool vertical, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn) +{ + uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + int bit55 = extract64(addr, 55, 1); + + /* Remove mtedesc from the normal sve descriptor. */ + desc = extract32(desc, 0, SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + + /* Perform gross MTE suppression early. */ + if (!tbi_check(desc, bit55) || + tcma_check(desc, bit55, allocation_tag_from_addr(addr))) { + mtedesc = 0; + } + + sme_st1(env, za, vg, addr, desc, ra, esz, mtedesc, + vertical, host_fn, tlb_fn); +} + +#define DO_ST(L, END, ESZ) \ +void HELPER(sme_st1##L##END##_h)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_st1(env, za, vg, addr, desc, GETPC(), ESZ, 0, false, \ + sve_st1##L##L##END##_host, sve_st1##L##L##END##_tlb); \ +} \ +void HELPER(sme_st1##L##END##_v)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_st1(env, za, vg, addr, desc, GETPC(), ESZ, 0, true, \ + sme_st1##L##END##_v_host, sme_st1##L##END##_v_tlb); \ +} \ +void HELPER(sme_st1##L##END##_h_mte)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_st1_mte(env, za, vg, addr, desc, GETPC(), ESZ, false, \ + sve_st1##L##L##END##_host, sve_st1##L##L##END##_tlb); \ +} \ +void HELPER(sme_st1##L##END##_v_mte)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_st1_mte(env, za, vg, addr, desc, GETPC(), ESZ, true, \ + sme_st1##L##END##_v_host, sme_st1##L##END##_v_tlb); \ +} + +DO_ST(b, , MO_8) +DO_ST(h, _be, MO_16) +DO_ST(h, _le, MO_16) +DO_ST(s, _be, MO_32) +DO_ST(s, _le, MO_32) +DO_ST(d, _be, MO_64) +DO_ST(d, _le, MO_64) +DO_ST(q, _be, MO_128) +DO_ST(q, _le, MO_128) + +#undef DO_ST diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a) return true; } + +static bool trans_LDST1(DisasContext *s, arg_LDST1 *a) +{ + typedef void GenLdSt1(TCGv_env, TCGv_ptr, TCGv_ptr, TCGv, TCGv_i32); + + /* + * Indexed by [esz][be][v][mte][st], which is (except for load/store) + * also the order in which the elements appear in the function names, + * and so how we must concatenate the pieces. + */ + +#define FN_LS(F) { gen_helper_sme_ld1##F, gen_helper_sme_st1##F } +#define FN_MTE(F) { FN_LS(F), FN_LS(F##_mte) } +#define FN_HV(F) { FN_MTE(F##_h), FN_MTE(F##_v) } +#define FN_END(L, B) { FN_HV(L), FN_HV(B) } + + static GenLdSt1 * const fns[5][2][2][2][2] = { + FN_END(b, b), + FN_END(h_le, h_be), + FN_END(s_le, s_be), + FN_END(d_le, d_be), + FN_END(q_le, q_be), + }; + +#undef FN_LS +#undef FN_MTE +#undef FN_HV +#undef FN_END + + TCGv_ptr t_za, t_pg; + TCGv_i64 addr; + int svl, desc = 0; + bool be = s->be_data == MO_BE; + bool mte = s->mte_active[0]; + + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (!sme_smza_enabled_check(s)) { + return true; + } + + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v); + t_pg = pred_full_reg_ptr(s, a->pg); + addr = tcg_temp_new_i64(); + + tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), a->esz); + tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn)); + + if (mte) { + desc = FIELD_DP32(desc, MTEDESC, MIDX, get_mem_index(s)); + desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid); + desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma); + desc = FIELD_DP32(desc, MTEDESC, WRITE, a->st); + desc = FIELD_DP32(desc, MTEDESC, SIZEM1, (1 << a->esz) - 1); + desc <<= SVE_MTEDESC_SHIFT; + } else { + addr = clean_data_tbi(s, addr); + } + svl = streaming_vec_reg_size(s); + desc = simd_desc(svl, svl, desc); + + fns[a->esz][be][a->v][mte][a->st](cpu_env, t_za, t_pg, addr, + tcg_constant_i32(desc)); + + tcg_temp_free_ptr(t_za); + tcg_temp_free_ptr(t_pg); + tcg_temp_free_i64(addr); + return true; +} -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Add a TCGv_ptr base argument, which will be cpu_env for SVE. We will reuse this for SME save and restore array insns. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-22-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 3 +++ target/arm/translate-sve.c | 48 ++++++++++++++++++++++++++++---------- 2 files changed, 39 insertions(+), 12 deletions(-) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_xar(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, int64_t shift, uint32_t opr_sz, uint32_t max_sz); +void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm); +void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm); + #endif /* TARGET_ARM_TRANSLATE_A64_H */ 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 @@ TRANS_FEAT(UCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz, * The load should begin at the address Rn + IMM. */ -static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) +void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, + int len, int rn, int imm) { int len_align = QEMU_ALIGN_DOWN(len, 8); int len_remain = len % 8; @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) t0 = tcg_temp_new_i64(); for (i = 0; i < len_align; i += 8) { tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ); - tcg_gen_st_i64(t0, cpu_env, vofs + i); + tcg_gen_st_i64(t0, base, vofs + i); tcg_gen_addi_i64(clean_addr, clean_addr, 8); } tcg_temp_free_i64(t0); @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) clean_addr = new_tmp_a64_local(s); tcg_gen_mov_i64(clean_addr, t0); + if (base != cpu_env) { + TCGv_ptr b = tcg_temp_local_new_ptr(); + tcg_gen_mov_ptr(b, base); + base = b; + } + gen_set_label(loop); t0 = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) tcg_gen_addi_i64(clean_addr, clean_addr, 8); tp = tcg_temp_new_ptr(); - tcg_gen_add_ptr(tp, cpu_env, i); + tcg_gen_add_ptr(tp, base, i); tcg_gen_addi_ptr(i, i, 8); tcg_gen_st_i64(t0, tp, vofs); tcg_temp_free_ptr(tp); @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop); tcg_temp_free_ptr(i); + + if (base != cpu_env) { + tcg_temp_free_ptr(base); + assert(len_remain == 0); + } } /* @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) default: g_assert_not_reached(); } - tcg_gen_st_i64(t0, cpu_env, vofs + len_align); + tcg_gen_st_i64(t0, base, vofs + len_align); tcg_temp_free_i64(t0); } } /* Similarly for stores. */ -static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm) +void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, + int len, int rn, int imm) { int len_align = QEMU_ALIGN_DOWN(len, 8); int len_remain = len % 8; @@ -XXX,XX +XXX,XX @@ static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm) t0 = tcg_temp_new_i64(); for (i = 0; i < len_align; i += 8) { - tcg_gen_ld_i64(t0, cpu_env, vofs + i); + tcg_gen_ld_i64(t0, base, vofs + i); tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ); tcg_gen_addi_i64(clean_addr, clean_addr, 8); } @@ -XXX,XX +XXX,XX @@ static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm) clean_addr = new_tmp_a64_local(s); tcg_gen_mov_i64(clean_addr, t0); + if (base != cpu_env) { + TCGv_ptr b = tcg_temp_local_new_ptr(); + tcg_gen_mov_ptr(b, base); + base = b; + } + gen_set_label(loop); t0 = tcg_temp_new_i64(); tp = tcg_temp_new_ptr(); - tcg_gen_add_ptr(tp, cpu_env, i); + tcg_gen_add_ptr(tp, base, i); tcg_gen_ld_i64(t0, tp, vofs); tcg_gen_addi_ptr(i, i, 8); tcg_temp_free_ptr(tp); @@ -XXX,XX +XXX,XX @@ static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm) tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop); tcg_temp_free_ptr(i); + + if (base != cpu_env) { + tcg_temp_free_ptr(base); + assert(len_remain == 0); + } } /* Predicate register stores can be any multiple of 2. */ if (len_remain) { t0 = tcg_temp_new_i64(); - tcg_gen_ld_i64(t0, cpu_env, vofs + len_align); + tcg_gen_ld_i64(t0, base, vofs + len_align); switch (len_remain) { case 2: @@ -XXX,XX +XXX,XX @@ static bool trans_LDR_zri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = vec_full_reg_size(s); int off = vec_full_reg_offset(s, a->rd); - do_ldr(s, off, size, a->rn, a->imm * size); + gen_sve_ldr(s, cpu_env, off, size, a->rn, a->imm * size); } return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_LDR_pri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = pred_full_reg_size(s); int off = pred_full_reg_offset(s, a->rd); - do_ldr(s, off, size, a->rn, a->imm * size); + gen_sve_ldr(s, cpu_env, off, size, a->rn, a->imm * size); } return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_STR_zri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = vec_full_reg_size(s); int off = vec_full_reg_offset(s, a->rd); - do_str(s, off, size, a->rn, a->imm * size); + gen_sve_str(s, cpu_env, off, size, a->rn, a->imm * size); } return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_STR_pri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = pred_full_reg_size(s); int off = pred_full_reg_offset(s, a->rd); - do_str(s, off, size, a->rn, a->imm * size); + gen_sve_str(s, cpu_env, off, size, a->rn, a->imm * size); } return true; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We can reuse the SVE functions for LDR and STR, passing in the base of the ZA vector and a zero offset. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-23-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme.decode | 7 +++++++ target/arm/translate-sme.c | 24 ++++++++++++++++++++++++ 2 files changed, 31 insertions(+) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ LDST1 1110000 0 esz:2 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ &ldst rs=%mova_rs LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ &ldst esz=4 rs=%mova_rs + +&ldstr rv rn imm +@ldstr ....... ... . ...... .. ... rn:5 . imm:4 \ + &ldstr rv=%mova_rs + +LDR 1110000 100 0 000000 .. 000 ..... 0 .... @ldstr +STR 1110000 100 1 000000 .. 000 ..... 0 .... @ldstr diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a) tcg_temp_free_i64(addr); return true; } + +typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int); + +static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn) +{ + int svl = streaming_vec_reg_size(s); + int imm = a->imm; + TCGv_ptr base; + + if (!sme_za_enabled_check(s)) { + return true; + } + + /* ZA[n] equates to ZA0H.B[n]. */ + base = get_tile_rowcol(s, MO_8, a->rv, imm, false); + + fn(s, base, 0, svl, a->rn, imm * svl); + + tcg_temp_free_ptr(base); + return true; +} + +TRANS_FEAT(LDR, aa64_sme, do_ldst_r, a, gen_sve_ldr) +TRANS_FEAT(STR, aa64_sme, do_ldst_r, a, gen_sve_str) -- 2.25.1 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: 20220708151540.18136-24-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 5 +++ target/arm/sme.decode | 11 +++++ target/arm/sme_helper.c | 90 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 31 +++++++++++++ 4 files changed, 137 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme_st1q_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i DEF_HELPER_FLAGS_5(sme_st1q_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_5(sme_st1q_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_5(sme_st1q_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_addha_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme_addva_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ LDR 1110000 100 0 000000 .. 000 ..... 0 .... @ldstr STR 1110000 100 1 000000 .. 000 ..... 0 .... @ldstr + +### SME Add Vector to Array + +&adda zad zn pm pn +@adda_32 ........ .. ..... . pm:3 pn:3 zn:5 ... zad:2 &adda +@adda_64 ........ .. ..... . pm:3 pn:3 zn:5 .. zad:3 &adda + +ADDHA_s 11000000 10 01000 0 ... ... ..... 000 .. @adda_32 +ADDVA_s 11000000 10 01000 1 ... ... ..... 000 .. @adda_32 +ADDHA_d 11000000 11 01000 0 ... ... ..... 00 ... @adda_64 +ADDVA_d 11000000 11 01000 1 ... ... ..... 00 ... @adda_64 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ DO_ST(q, _be, MO_128) DO_ST(q, _le, MO_128) #undef DO_ST + +void HELPER(sme_addha_s)(void *vzda, void *vzn, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 4; + uint64_t *pn = vpn, *pm = vpm; + uint32_t *zda = vzda, *zn = vzn; + + for (row = 0; row < oprsz; ) { + uint64_t pa = pn[row >> 4]; + do { + if (pa & 1) { + for (col = 0; col < oprsz; ) { + uint64_t pb = pm[col >> 4]; + do { + if (pb & 1) { + zda[tile_vslice_index(row) + H4(col)] += zn[H4(col)]; + } + pb >>= 4; + } while (++col & 15); + } + } + pa >>= 4; + } while (++row & 15); + } +} + +void HELPER(sme_addha_d)(void *vzda, void *vzn, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 8; + uint8_t *pn = vpn, *pm = vpm; + uint64_t *zda = vzda, *zn = vzn; + + for (row = 0; row < oprsz; ++row) { + if (pn[H1(row)] & 1) { + for (col = 0; col < oprsz; ++col) { + if (pm[H1(col)] & 1) { + zda[tile_vslice_index(row) + col] += zn[col]; + } + } + } + } +} + +void HELPER(sme_addva_s)(void *vzda, void *vzn, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 4; + uint64_t *pn = vpn, *pm = vpm; + uint32_t *zda = vzda, *zn = vzn; + + for (row = 0; row < oprsz; ) { + uint64_t pa = pn[row >> 4]; + do { + if (pa & 1) { + uint32_t zn_row = zn[H4(row)]; + for (col = 0; col < oprsz; ) { + uint64_t pb = pm[col >> 4]; + do { + if (pb & 1) { + zda[tile_vslice_index(row) + H4(col)] += zn_row; + } + pb >>= 4; + } while (++col & 15); + } + } + pa >>= 4; + } while (++row & 15); + } +} + +void HELPER(sme_addva_d)(void *vzda, void *vzn, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 8; + uint8_t *pn = vpn, *pm = vpm; + uint64_t *zda = vzda, *zn = vzn; + + for (row = 0; row < oprsz; ++row) { + if (pn[H1(row)] & 1) { + uint64_t zn_row = zn[row]; + for (col = 0; col < oprsz; ++col) { + if (pm[H1(col)] & 1) { + zda[tile_vslice_index(row) + col] += zn_row; + } + } + } + } +} diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn) TRANS_FEAT(LDR, aa64_sme, do_ldst_r, a, gen_sve_ldr) TRANS_FEAT(STR, aa64_sme, do_ldst_r, a, gen_sve_str) + +static bool do_adda(DisasContext *s, arg_adda *a, MemOp esz, + gen_helper_gvec_4 *fn) +{ + int svl = streaming_vec_reg_size(s); + uint32_t desc = simd_desc(svl, svl, 0); + TCGv_ptr za, zn, pn, pm; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + /* Sum XZR+zad to find ZAd. */ + za = get_tile_rowcol(s, esz, 31, a->zad, false); + zn = vec_full_reg_ptr(s, a->zn); + pn = pred_full_reg_ptr(s, a->pn); + pm = pred_full_reg_ptr(s, a->pm); + + fn(za, zn, pn, pm, tcg_constant_i32(desc)); + + tcg_temp_free_ptr(za); + tcg_temp_free_ptr(zn); + tcg_temp_free_ptr(pn); + tcg_temp_free_ptr(pm); + return true; +} + +TRANS_FEAT(ADDHA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addha_s) +TRANS_FEAT(ADDVA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addva_s) +TRANS_FEAT(ADDHA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addha_d) +TRANS_FEAT(ADDVA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addva_d) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-25-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 5 +++ target/arm/sme.decode | 9 +++++ target/arm/sme_helper.c | 69 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 32 ++++++++++++++++++ 4 files changed, 115 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme_addha_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addva_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ ADDHA_s 11000000 10 01000 0 ... ... ..... 000 .. @adda_32 ADDVA_s 11000000 10 01000 1 ... ... ..... 000 .. @adda_32 ADDHA_d 11000000 11 01000 0 ... ... ..... 00 ... @adda_64 ADDVA_d 11000000 11 01000 1 ... ... ..... 00 ... @adda_64 + +### SME Outer Product + +&op zad zn zm pm pn sub:bool +@op_32 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 .. zad:2 &op +@op_64 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 . zad:3 &op + +FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32 +FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/cpu_ldst.h" #include "exec/exec-all.h" #include "qemu/int128.h" +#include "fpu/softfloat.h" #include "vec_internal.h" #include "sve_ldst_internal.h" @@ -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) +{ + intptr_t row, col, oprsz = simd_maxsz(desc); + uint32_t neg = simd_data(desc) << 31; + uint16_t *pn = vpn, *pm = vpm; + float_status fpst; + + /* + * Make a copy of float_status because this operation does not + * update the cumulative fp exception status. It also produces + * default nans. + */ + fpst = *(float_status *)vst; + set_default_nan_mode(true, &fpst); + + for (row = 0; row < oprsz; ) { + uint16_t pa = pn[H2(row >> 4)]; + do { + if (pa & 1) { + void *vza_row = vza + tile_vslice_offset(row); + uint32_t n = *(uint32_t *)(vzn + H1_4(row)) ^ neg; + + for (col = 0; col < oprsz; ) { + uint16_t pb = pm[H2(col >> 4)]; + do { + if (pb & 1) { + uint32_t *a = vza_row + H1_4(col); + uint32_t *m = vzm + H1_4(col); + *a = float32_muladd(n, *m, *a, 0, vst); + } + col += 4; + pb >>= 4; + } while (col & 15); + } + } + row += 4; + pa >>= 4; + } while (row & 15); + } +} + +void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, void *vst, 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; + + set_default_nan_mode(true, &fpst); + + for (row = 0; row < oprsz; ++row) { + if (pn[H1(row)] & 1) { + uint64_t *za_row = &za[tile_vslice_index(row)]; + uint64_t n = zn[row] ^ neg; + + for (col = 0; col < oprsz; ++col) { + if (pm[H1(col)] & 1) { + uint64_t *a = &za_row[col]; + *a = float64_muladd(n, zm[col], *a, 0, &fpst); + } + } + } + } +} diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(ADDHA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addha_s) TRANS_FEAT(ADDVA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addva_s) TRANS_FEAT(ADDHA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addha_d) TRANS_FEAT(ADDVA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addva_d) + +static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz, + gen_helper_gvec_5_ptr *fn) +{ + int svl = streaming_vec_reg_size(s); + uint32_t desc = simd_desc(svl, svl, a->sub); + TCGv_ptr za, zn, zm, pn, pm, fpst; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + /* Sum XZR+zad to find ZAd. */ + za = get_tile_rowcol(s, esz, 31, a->zad, false); + zn = vec_full_reg_ptr(s, a->zn); + zm = vec_full_reg_ptr(s, a->zm); + pn = pred_full_reg_ptr(s, a->pn); + pm = pred_full_reg_ptr(s, a->pm); + fpst = fpstatus_ptr(FPST_FPCR); + + fn(za, zn, zm, pn, pm, fpst, tcg_constant_i32(desc)); + + tcg_temp_free_ptr(za); + tcg_temp_free_ptr(zn); + tcg_temp_free_ptr(pn); + tcg_temp_free_ptr(pm); + tcg_temp_free_ptr(fpst); + return true; +} + +TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, gen_helper_sme_fmopa_s) +TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, gen_helper_sme_fmopa_d) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-26-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 2 ++ target/arm/sme.decode | 2 ++ target/arm/sme_helper.c | 56 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 30 ++++++++++++++++++++ 4 files changed, 90 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_bfmopa, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ ADDVA_d 11000000 11 01000 1 ... ... ..... 00 ... @adda_64 FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 + +BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn, } } } + +/* + * Alter PAIR as needed for controlling predicates being false, + * and for NEG on an enabled row element. + */ +static inline uint32_t f16mop_adj_pair(uint32_t pair, uint32_t pg, uint32_t neg) +{ + /* + * The pseudocode uses a conditional negate after the conditional zero. + * It is simpler here to unconditionally negate before conditional zero. + */ + pair ^= neg; + if (!(pg & 1)) { + pair &= 0xffff0000u; + } + if (!(pg & 4)) { + pair &= 0x0000ffffu; + } + return pair; +} + +void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_maxsz(desc); + uint32_t neg = simd_data(desc) * 0x80008000u; + uint16_t *pn = vpn, *pm = vpm; + + for (row = 0; row < oprsz; ) { + uint16_t prow = pn[H2(row >> 4)]; + do { + void *vza_row = vza + tile_vslice_offset(row); + uint32_t n = *(uint32_t *)(vzn + H1_4(row)); + + n = f16mop_adj_pair(n, prow, neg); + + for (col = 0; col < oprsz; ) { + uint16_t pcol = pm[H2(col >> 4)]; + do { + if (prow & pcol & 0b0101) { + uint32_t *a = vza_row + H1_4(col); + uint32_t m = *(uint32_t *)(vzm + H1_4(col)); + + m = f16mop_adj_pair(m, pcol, 0); + *a = bfdotadd(*a, n, m); + + col += 4; + pcol >>= 4; + } + } while (col & 15); + } + row += 4; + prow >>= 4; + } while (row & 15); + } +} diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(ADDVA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addva_s) TRANS_FEAT(ADDHA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addha_d) TRANS_FEAT(ADDVA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addva_d) +static bool do_outprod(DisasContext *s, arg_op *a, MemOp esz, + gen_helper_gvec_5 *fn) +{ + int svl = streaming_vec_reg_size(s); + uint32_t desc = simd_desc(svl, svl, a->sub); + TCGv_ptr za, zn, zm, pn, pm; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + /* Sum XZR+zad to find ZAd. */ + za = get_tile_rowcol(s, esz, 31, a->zad, false); + zn = vec_full_reg_ptr(s, a->zn); + zm = vec_full_reg_ptr(s, a->zm); + pn = pred_full_reg_ptr(s, a->pn); + pm = pred_full_reg_ptr(s, a->pm); + + fn(za, zn, zm, pn, pm, tcg_constant_i32(desc)); + + tcg_temp_free_ptr(za); + tcg_temp_free_ptr(zn); + tcg_temp_free_ptr(pn); + tcg_temp_free_ptr(pm); + return true; +} + static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz, gen_helper_gvec_5_ptr *fn) { @@ -XXX,XX +XXX,XX @@ static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz, TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, gen_helper_sme_fmopa_s) TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, gen_helper_sme_fmopa_d) + +/* TODO: FEAT_EBF16 */ +TRANS_FEAT(BFMOPA, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_bfmopa) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-27-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 2 ++ target/arm/sme.decode | 1 + target/arm/sme_helper.c | 74 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 1 + 4 files changed, 78 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme_addva_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) 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, ptr, i32) DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32 +FMOPA_h 10000001 101 ..... ... ... ..... . 00 .. @op_32 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t f16mop_adj_pair(uint32_t pair, uint32_t pg, uint32_t neg) return pair; } +static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2, + float_status *s_std, float_status *s_odd) +{ + float64 e1r = float16_to_float64(e1 & 0xffff, true, s_std); + float64 e1c = float16_to_float64(e1 >> 16, true, s_std); + float64 e2r = float16_to_float64(e2 & 0xffff, true, s_std); + float64 e2c = float16_to_float64(e2 >> 16, true, s_std); + float64 t64; + float32 t32; + + /* + * The ARM pseudocode function FPDot performs both multiplies + * and the add with a single rounding operation. Emulate this + * by performing the first multiply in round-to-odd, then doing + * the second multiply as fused multiply-add, and rounding to + * float32 all in one step. + */ + t64 = float64_mul(e1r, e2r, s_odd); + t64 = float64r32_muladd(e1c, e2c, t64, 0, s_std); + + /* This conversion is exact, because we've already rounded. */ + t32 = float64_to_float32(t64, s_std); + + /* The final accumulation step is not fused. */ + return float32_add(sum, t32, s_std); +} + +void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, void *vst, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_maxsz(desc); + uint32_t neg = simd_data(desc) * 0x80008000u; + uint16_t *pn = vpn, *pm = vpm; + float_status fpst_odd, fpst_std; + + /* + * Make a copy of float_status because this operation does not + * update the cumulative fp exception status. It also produces + * default nans. Make a second copy with round-to-odd -- see above. + */ + fpst_std = *(float_status *)vst; + set_default_nan_mode(true, &fpst_std); + fpst_odd = fpst_std; + set_float_rounding_mode(float_round_to_odd, &fpst_odd); + + for (row = 0; row < oprsz; ) { + uint16_t prow = pn[H2(row >> 4)]; + do { + void *vza_row = vza + tile_vslice_offset(row); + uint32_t n = *(uint32_t *)(vzn + H1_4(row)); + + n = f16mop_adj_pair(n, prow, neg); + + for (col = 0; col < oprsz; ) { + uint16_t pcol = pm[H2(col >> 4)]; + do { + if (prow & pcol & 0b0101) { + uint32_t *a = vza_row + H1_4(col); + uint32_t m = *(uint32_t *)(vzm + H1_4(col)); + + m = f16mop_adj_pair(m, pcol, 0); + *a = f16_dotadd(*a, n, m, &fpst_std, &fpst_odd); + + col += 4; + pcol >>= 4; + } + } while (col & 15); + } + row += 4; + prow >>= 4; + } while (row & 15); + } +} + void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn, void *vpm, uint32_t desc) { diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz, return true; } +TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_fpst, a, MO_32, gen_helper_sme_fmopa_h) TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, gen_helper_sme_fmopa_s) TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, gen_helper_sme_fmopa_d) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This is SMOPA, SUMOPA, USMOPA_s, UMOPA, for both Int8 and Int16. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-28-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 16 ++++++++ target/arm/sme.decode | 10 +++++ target/arm/sme_helper.c | 82 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 10 +++++ 4 files changed, 118 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sme_bfmopa, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_smopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_umopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_sumopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_usmopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_smopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_umopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_sumopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_usmopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_h 10000001 101 ..... ... ... ..... . 00 .. @op_32 + +SMOPA_s 1010000 0 10 0 ..... ... ... ..... . 00 .. @op_32 +SUMOPA_s 1010000 0 10 1 ..... ... ... ..... . 00 .. @op_32 +USMOPA_s 1010000 1 10 0 ..... ... ... ..... . 00 .. @op_32 +UMOPA_s 1010000 1 10 1 ..... ... ... ..... . 00 .. @op_32 + +SMOPA_d 1010000 0 11 0 ..... ... ... ..... . 0 ... @op_64 +SUMOPA_d 1010000 0 11 1 ..... ... ... ..... . 0 ... @op_64 +USMOPA_d 1010000 1 11 0 ..... ... ... ..... . 0 ... @op_64 +UMOPA_d 1010000 1 11 1 ..... ... ... ..... . 0 ... @op_64 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn, } while (row & 15); } } + +typedef uint64_t IMOPFn(uint64_t, uint64_t, uint64_t, uint8_t, bool); + +static inline void do_imopa(uint64_t *za, uint64_t *zn, uint64_t *zm, + uint8_t *pn, uint8_t *pm, + uint32_t desc, IMOPFn *fn) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 8; + bool neg = simd_data(desc); + + for (row = 0; row < oprsz; ++row) { + uint8_t pa = pn[H1(row)]; + uint64_t *za_row = &za[tile_vslice_index(row)]; + uint64_t n = zn[row]; + + for (col = 0; col < oprsz; ++col) { + uint8_t pb = pm[H1(col)]; + uint64_t *a = &za_row[col]; + + *a = fn(n, zm[col], *a, pa & pb, neg); + } + } +} + +#define DEF_IMOP_32(NAME, NTYPE, MTYPE) \ +static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \ +{ \ + uint32_t sum0 = 0, sum1 = 0; \ + /* Apply P to N as a mask, making the inactive elements 0. */ \ + n &= expand_pred_b(p); \ + sum0 += (NTYPE)(n >> 0) * (MTYPE)(m >> 0); \ + sum0 += (NTYPE)(n >> 8) * (MTYPE)(m >> 8); \ + sum0 += (NTYPE)(n >> 16) * (MTYPE)(m >> 16); \ + sum0 += (NTYPE)(n >> 24) * (MTYPE)(m >> 24); \ + sum1 += (NTYPE)(n >> 32) * (MTYPE)(m >> 32); \ + sum1 += (NTYPE)(n >> 40) * (MTYPE)(m >> 40); \ + sum1 += (NTYPE)(n >> 48) * (MTYPE)(m >> 48); \ + sum1 += (NTYPE)(n >> 56) * (MTYPE)(m >> 56); \ + if (neg) { \ + sum0 = (uint32_t)a - sum0, sum1 = (uint32_t)(a >> 32) - sum1; \ + } else { \ + sum0 = (uint32_t)a + sum0, sum1 = (uint32_t)(a >> 32) + sum1; \ + } \ + return ((uint64_t)sum1 << 32) | sum0; \ +} + +#define DEF_IMOP_64(NAME, NTYPE, MTYPE) \ +static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \ +{ \ + uint64_t sum = 0; \ + /* Apply P to N as a mask, making the inactive elements 0. */ \ + n &= expand_pred_h(p); \ + sum += (NTYPE)(n >> 0) * (MTYPE)(m >> 0); \ + sum += (NTYPE)(n >> 16) * (MTYPE)(m >> 16); \ + sum += (NTYPE)(n >> 32) * (MTYPE)(m >> 32); \ + sum += (NTYPE)(n >> 48) * (MTYPE)(m >> 48); \ + return neg ? a - sum : a + sum; \ +} + +DEF_IMOP_32(smopa_s, int8_t, int8_t) +DEF_IMOP_32(umopa_s, uint8_t, uint8_t) +DEF_IMOP_32(sumopa_s, int8_t, uint8_t) +DEF_IMOP_32(usmopa_s, uint8_t, int8_t) + +DEF_IMOP_64(smopa_d, int16_t, int16_t) +DEF_IMOP_64(umopa_d, uint16_t, uint16_t) +DEF_IMOP_64(sumopa_d, int16_t, uint16_t) +DEF_IMOP_64(usmopa_d, uint16_t, int16_t) + +#define DEF_IMOPH(NAME) \ + void HELPER(sme_##NAME)(void *vza, void *vzn, void *vzm, void *vpn, \ + void *vpm, uint32_t desc) \ + { do_imopa(vza, vzn, vzm, vpn, vpm, desc, NAME); } + +DEF_IMOPH(smopa_s) +DEF_IMOPH(umopa_s) +DEF_IMOPH(sumopa_s) +DEF_IMOPH(usmopa_s) +DEF_IMOPH(smopa_d) +DEF_IMOPH(umopa_d) +DEF_IMOPH(sumopa_d) +DEF_IMOPH(usmopa_d) diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, gen_helper_sme_f /* TODO: FEAT_EBF16 */ TRANS_FEAT(BFMOPA, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_bfmopa) + +TRANS_FEAT(SMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_smopa_s) +TRANS_FEAT(UMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_umopa_s) +TRANS_FEAT(SUMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_sumopa_s) +TRANS_FEAT(USMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_usmopa_s) + +TRANS_FEAT(SMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_smopa_d) +TRANS_FEAT(UMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_umopa_d) +TRANS_FEAT(SUMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_sumopa_d) +TRANS_FEAT(USMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_usmopa_d) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This is an SVE instruction that operates using the SVE vector length but that it is present only if SME is implemented. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-29-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 20 +++++++++++++ target/arm/translate-sve.c | 57 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 77 insertions(+) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ BFMLALT_zzxw 01100100 11 1 ..... 0100.1 ..... ..... @rrxr_3a esz=2 ### SVE2 floating-point bfloat16 dot-product (indexed) BFDOT_zzxz 01100100 01 1 ..... 010000 ..... ..... @rrxr_2 esz=2 + +### SVE broadcast predicate element + +&psel esz pd pn pm rv imm +%psel_rv 16:2 !function=plus_12 +%psel_imm_b 22:2 19:2 +%psel_imm_h 22:2 20:1 +%psel_imm_s 22:2 +%psel_imm_d 23:1 +@psel ........ .. . ... .. .. pn:4 . pm:4 . pd:4 \ + &psel rv=%psel_rv + +PSEL 00100101 .. 1 ..1 .. 01 .... 0 .... 0 .... \ + @psel esz=0 imm=%psel_imm_b +PSEL 00100101 .. 1 .10 .. 01 .... 0 .... 0 .... \ + @psel esz=1 imm=%psel_imm_h +PSEL 00100101 .. 1 100 .. 01 .... 0 .... 0 .... \ + @psel esz=2 imm=%psel_imm_s +PSEL 00100101 .1 1 000 .. 01 .... 0 .... 0 .... \ + @psel esz=3 imm=%psel_imm_d 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 do_BFMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel) TRANS_FEAT(BFMLALB_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, false) TRANS_FEAT(BFMLALT_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, true) + +static bool trans_PSEL(DisasContext *s, arg_psel *a) +{ + int vl = vec_full_reg_size(s); + int pl = pred_gvec_reg_size(s); + int elements = vl >> a->esz; + TCGv_i64 tmp, didx, dbit; + TCGv_ptr ptr; + + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + tmp = tcg_temp_new_i64(); + dbit = tcg_temp_new_i64(); + didx = tcg_temp_new_i64(); + ptr = tcg_temp_new_ptr(); + + /* Compute the predicate element. */ + tcg_gen_addi_i64(tmp, cpu_reg(s, a->rv), a->imm); + if (is_power_of_2(elements)) { + tcg_gen_andi_i64(tmp, tmp, elements - 1); + } else { + tcg_gen_remu_i64(tmp, tmp, tcg_constant_i64(elements)); + } + + /* Extract the predicate byte and bit indices. */ + tcg_gen_shli_i64(tmp, tmp, a->esz); + tcg_gen_andi_i64(dbit, tmp, 7); + tcg_gen_shri_i64(didx, tmp, 3); + if (HOST_BIG_ENDIAN) { + tcg_gen_xori_i64(didx, didx, 7); + } + + /* Load the predicate word. */ + tcg_gen_trunc_i64_ptr(ptr, didx); + tcg_gen_add_ptr(ptr, ptr, cpu_env); + tcg_gen_ld8u_i64(tmp, ptr, pred_full_reg_offset(s, a->pm)); + + /* Extract the predicate bit and replicate to MO_64. */ + tcg_gen_shr_i64(tmp, tmp, dbit); + tcg_gen_andi_i64(tmp, tmp, 1); + tcg_gen_neg_i64(tmp, tmp); + + /* Apply to either copy the source, or write zeros. */ + tcg_gen_gvec_ands(MO_64, pred_full_reg_offset(s, a->pd), + pred_full_reg_offset(s, a->pn), tmp, pl, pl); + + tcg_temp_free_i64(tmp); + tcg_temp_free_i64(dbit); + tcg_temp_free_i64(didx); + tcg_temp_free_ptr(ptr); + return true; +} -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This is an SVE instruction that operates using the SVE vector length but that it is present only if SME is implemented. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-30-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 2 ++ target/arm/sve.decode | 1 + target/arm/sve_helper.c | 16 ++++++++++++++++ target/arm/translate-sve.c | 2 ++ 4 files changed, 21 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_revh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_revw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_revd_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve_rbit_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_rbit_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_rbit_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ REVB 00000101 .. 1001 00 100 ... ..... ..... @rd_pg_rn REVH 00000101 .. 1001 01 100 ... ..... ..... @rd_pg_rn REVW 00000101 .. 1001 10 100 ... ..... ..... @rd_pg_rn RBIT 00000101 .. 1001 11 100 ... ..... ..... @rd_pg_rn +REVD 00000101 00 1011 10 100 ... ..... ..... @rd_pg_rn_e0 # SVE vector splice (predicated, destructive) SPLICE 00000101 .. 101 100 100 ... ..... ..... @rdn_pg_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZPZ_D(sve_revh_d, uint64_t, hswap64) DO_ZPZ_D(sve_revw_d, uint64_t, wswap64) +void HELPER(sme_revd_q)(void *vd, void *vn, void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn; + uint8_t *pg = vg; + + for (i = 0; i < opr_sz; i += 2) { + if (pg[H1(i)] & 1) { + uint64_t n0 = n[i + 0]; + uint64_t n1 = n[i + 1]; + d[i + 0] = n1; + d[i + 1] = n0; + } + } +} + DO_ZPZ(sve_rbit_b, uint8_t, H1, revbit8) DO_ZPZ(sve_rbit_h, uint16_t, H1_2, revbit16) DO_ZPZ(sve_rbit_s, uint32_t, H1_4, revbit32) 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 @@ TRANS_FEAT(REVH, aa64_sve, gen_gvec_ool_arg_zpz, revh_fns[a->esz], a, 0) TRANS_FEAT(REVW, aa64_sve, gen_gvec_ool_arg_zpz, a->esz == 3 ? gen_helper_sve_revw_d : NULL, a, 0) +TRANS_FEAT(REVD, aa64_sme, gen_gvec_ool_arg_zpz, gen_helper_sme_revd_q, a, 0) + TRANS_FEAT(SPLICE, aa64_sve, gen_gvec_ool_arg_zpzz, gen_helper_sve_splice, a, a->esz) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This is an SVE instruction that operates using the SVE vector length but that it is present only if SME is implemented. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-31-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 18 +++++++ target/arm/sve.decode | 5 ++ target/arm/translate-sve.c | 102 +++++++++++++++++++++++++++++++++++++ target/arm/vec_helper.c | 24 +++++++++ 4 files changed, 149 insertions(+) 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_bfmlal, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_6(gvec_bfmlal_idx, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sclamp_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sclamp_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sclamp_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sclamp_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_uclamp_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uclamp_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uclamp_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uclamp_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/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ PSEL 00100101 .. 1 100 .. 01 .... 0 .... 0 .... \ @psel esz=2 imm=%psel_imm_s PSEL 00100101 .1 1 000 .. 01 .... 0 .... 0 .... \ @psel esz=3 imm=%psel_imm_d + +### SVE clamp + +SCLAMP 01000100 .. 0 ..... 110000 ..... ..... @rda_rn_rm +UCLAMP 01000100 .. 0 ..... 110001 ..... ..... @rda_rn_rm 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_PSEL(DisasContext *s, arg_psel *a) tcg_temp_free_ptr(ptr); return true; } + +static void gen_sclamp_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_i32 a) +{ + tcg_gen_smax_i32(d, a, n); + tcg_gen_smin_i32(d, d, m); +} + +static void gen_sclamp_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 a) +{ + tcg_gen_smax_i64(d, a, n); + tcg_gen_smin_i64(d, d, m); +} + +static void gen_sclamp_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec a) +{ + tcg_gen_smax_vec(vece, d, a, n); + tcg_gen_smin_vec(vece, d, d, m); +} + +static void gen_sclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const TCGOpcode vecop[] = { + INDEX_op_smin_vec, INDEX_op_smax_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_sclamp_vec, + .fno = gen_helper_gvec_sclamp_b, + .opt_opc = vecop, + .vece = MO_8 }, + { .fniv = gen_sclamp_vec, + .fno = gen_helper_gvec_sclamp_h, + .opt_opc = vecop, + .vece = MO_16 }, + { .fni4 = gen_sclamp_i32, + .fniv = gen_sclamp_vec, + .fno = gen_helper_gvec_sclamp_s, + .opt_opc = vecop, + .vece = MO_32 }, + { .fni8 = gen_sclamp_i64, + .fniv = gen_sclamp_vec, + .fno = gen_helper_gvec_sclamp_d, + .opt_opc = vecop, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64 } + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]); +} + +TRANS_FEAT(SCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_sclamp, a) + +static void gen_uclamp_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_i32 a) +{ + tcg_gen_umax_i32(d, a, n); + tcg_gen_umin_i32(d, d, m); +} + +static void gen_uclamp_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 a) +{ + tcg_gen_umax_i64(d, a, n); + tcg_gen_umin_i64(d, d, m); +} + +static void gen_uclamp_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec a) +{ + tcg_gen_umax_vec(vece, d, a, n); + tcg_gen_umin_vec(vece, d, d, m); +} + +static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const TCGOpcode vecop[] = { + INDEX_op_umin_vec, INDEX_op_umax_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_uclamp_vec, + .fno = gen_helper_gvec_uclamp_b, + .opt_opc = vecop, + .vece = MO_8 }, + { .fniv = gen_uclamp_vec, + .fno = gen_helper_gvec_uclamp_h, + .opt_opc = vecop, + .vece = MO_16 }, + { .fni4 = gen_uclamp_i32, + .fniv = gen_uclamp_vec, + .fno = gen_helper_gvec_uclamp_s, + .opt_opc = vecop, + .vece = MO_32 }, + { .fni8 = gen_uclamp_i64, + .fniv = gen_uclamp_vec, + .fno = gen_helper_gvec_uclamp_d, + .opt_opc = vecop, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64 } + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]); +} + +TRANS_FEAT(UCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_uclamp, a) 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(gvec_bfmlal_idx)(void *vd, void *vn, void *vm, } clear_tail(d, opr_sz, simd_maxsz(desc)); } + +#define DO_CLAMP(NAME, TYPE) \ +void HELPER(NAME)(void *d, void *n, void *m, void *a, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \ + TYPE aa = *(TYPE *)(a + i); \ + TYPE nn = *(TYPE *)(n + i); \ + TYPE mm = *(TYPE *)(m + i); \ + TYPE dd = MIN(MAX(aa, nn), mm); \ + *(TYPE *)(d + i) = dd; \ + } \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ +} + +DO_CLAMP(gvec_sclamp_b, int8_t) +DO_CLAMP(gvec_sclamp_h, int16_t) +DO_CLAMP(gvec_sclamp_s, int32_t) +DO_CLAMP(gvec_sclamp_d, int64_t) + +DO_CLAMP(gvec_uclamp_b, uint8_t) +DO_CLAMP(gvec_uclamp_h, uint16_t) +DO_CLAMP(gvec_uclamp_s, uint32_t) +DO_CLAMP(gvec_uclamp_d, uint64_t) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We can handle both exception entry and exception return by hooking into aarch64_sve_change_el. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-32-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 15 +++++++++++++-- 1 file changed, 13 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 @@ void aarch64_sve_change_el(CPUARMState *env, int old_el, return; } + old_a64 = old_el ? arm_el_is_aa64(env, old_el) : el0_a64; + new_a64 = new_el ? arm_el_is_aa64(env, new_el) : el0_a64; + + /* + * Both AArch64.TakeException and AArch64.ExceptionReturn + * invoke ResetSVEState when taking an exception from, or + * returning to, AArch32 state when PSTATE.SM is enabled. + */ + if (old_a64 != new_a64 && FIELD_EX64(env->svcr, SVCR, SM)) { + arm_reset_sve_state(env); + return; + } + /* * DDI0584A.d sec 3.2: "If SVE instructions are disabled or trapped * at ELx, or not available because the EL is in AArch32 state, then @@ -XXX,XX +XXX,XX @@ void aarch64_sve_change_el(CPUARMState *env, int old_el, * we already have the correct register contents when encountering the * vq0->vq0 transition between EL0->EL1. */ - old_a64 = old_el ? arm_el_is_aa64(env, old_el) : el0_a64; old_len = (old_a64 && !sve_exception_el(env, old_el) ? sve_vqm1_for_el(env, old_el) : 0); - new_a64 = new_el ? arm_el_is_aa64(env, new_el) : el0_a64; new_len = (new_a64 && !sve_exception_el(env, new_el) ? sve_vqm1_for_el(env, new_el) : 0); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Note that SME remains effectively disabled for user-only, because we do not yet set CPACR_EL1.SMEN. This needs to wait until the kernel ABI is implemented. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-33-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 4 ++++ target/arm/cpu64.c | 11 +++++++++++ 2 files changed, 15 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_SHA512 (Advanced SIMD SHA512 instructions) - FEAT_SM3 (Advanced SIMD SM3 instructions) - FEAT_SM4 (Advanced SIMD SM4 instructions) +- FEAT_SME (Scalable Matrix Extension) +- FEAT_SME_FA64 (Full A64 instruction set in Streaming SVE mode) +- FEAT_SME_F64F64 (Double-precision floating-point outer product instructions) +- FEAT_SME_I16I64 (16-bit to 64-bit integer widening outer product instructions) - FEAT_SPECRES (Speculation restriction instructions) - FEAT_SSBS (Speculative Store Bypass Safe) - FEAT_TLBIOS (TLB invalidate instructions in Outer Shareable domain) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) */ t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3); /* FEAT_MTE3 */ t = FIELD_DP64(t, ID_AA64PFR1, RAS_FRAC, 0); /* FEAT_RASv1p1 + FEAT_DoubleFault */ + t = FIELD_DP64(t, ID_AA64PFR1, SME, 1); /* FEAT_SME */ t = FIELD_DP64(t, ID_AA64PFR1, CSV2_FRAC, 0); /* FEAT_CSV2_2 */ cpu->isar.id_aa64pfr1 = t; @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64DFR0, PMUVER, 5); /* FEAT_PMUv3p4 */ cpu->isar.id_aa64dfr0 = t; + t = cpu->isar.id_aa64smfr0; + t = FIELD_DP64(t, ID_AA64SMFR0, F32F32, 1); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, B16F32, 1); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, F16F32, 1); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, I8I32, 0xf); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, F64F64, 1); /* FEAT_SME_F64F64 */ + t = FIELD_DP64(t, ID_AA64SMFR0, I16I64, 0xf); /* FEAT_SME_I16I64 */ + t = FIELD_DP64(t, ID_AA64SMFR0, FA64, 1); /* FEAT_SME_FA64 */ + cpu->isar.id_aa64smfr0 = t; + /* Replicate the same data to the 32-bit id registers. */ aa32_max_features(cpu); -- 2.25.1 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: 20220708151540.18136-34-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/target_cpu.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/linux-user/aarch64/target_cpu.h b/linux-user/aarch64/target_cpu.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/target_cpu.h +++ b/linux-user/aarch64/target_cpu.h @@ -XXX,XX +XXX,XX @@ static inline void cpu_clone_regs_parent(CPUARMState *env, unsigned flags) static inline void cpu_set_tls(CPUARMState *env, target_ulong newtls) { - /* Note that AArch64 Linux keeps the TLS pointer in TPIDR; this is + /* + * Note that AArch64 Linux keeps the TLS pointer in TPIDR; this is * different from AArch32 Linux, which uses TPIDRRO. */ env->cp15.tpidr_el[0] = newtls; + /* TPIDR2_EL0 is cleared with CLONE_SETTLS. */ + env->cp15.tpidr2_el0 = 0; } static inline abi_ulong get_sp_from_cpustate(CPUARMState *state) -- 2.25.1 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: 20220708151540.18136-35-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/cpu_loop.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/linux-user/aarch64/cpu_loop.c b/linux-user/aarch64/cpu_loop.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/cpu_loop.c +++ b/linux-user/aarch64/cpu_loop.c @@ -XXX,XX +XXX,XX @@ void cpu_loop(CPUARMState *env) switch (trapnr) { case EXCP_SWI: + /* + * On syscall, PSTATE.ZA is preserved, along with the ZA matrix. + * PSTATE.SM is cleared, per SMSTOP, which does ResetSVEState. + */ + if (FIELD_EX64(env->svcr, SVCR, SM)) { + env->svcr = FIELD_DP64(env->svcr, SVCR, SM, 0); + arm_rebuild_hflags(env); + arm_reset_sve_state(env); + } ret = do_syscall(env, env->xregs[8], env->xregs[0], -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Make sure to zero the currently reserved fields. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-36-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ struct target_extra_context { struct target_sve_context { struct target_aarch64_ctx head; uint16_t vl; - uint16_t reserved[3]; + uint16_t flags; + uint16_t reserved[2]; /* The actual SVE data immediately follows. It is laid out * according to TARGET_SVE_SIG_{Z,P}REG_OFFSET, based off of * the original struct pointer. @@ -XXX,XX +XXX,XX @@ struct target_sve_context { #define TARGET_SVE_SIG_CONTEXT_SIZE(VQ) \ (TARGET_SVE_SIG_PREG_OFFSET(VQ, 17)) +#define TARGET_SVE_SIG_FLAG_SM 1 + struct target_rt_sigframe { struct target_siginfo info; struct target_ucontext uc; @@ -XXX,XX +XXX,XX @@ static void target_setup_sve_record(struct target_sve_context *sve, { int i, j; + memset(sve, 0, sizeof(*sve)); __put_user(TARGET_SVE_MAGIC, &sve->head.magic); __put_user(size, &sve->head.size); __put_user(vq * TARGET_SVE_VQ_BYTES, &sve->vl); + if (FIELD_EX64(env->svcr, SVCR, SM)) { + __put_user(TARGET_SVE_SIG_FLAG_SM, &sve->flags); + } /* Note that SVE regs are stored as a byte stream, with each byte element * at a subsequent address. This corresponds to a little-endian store -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Fold the return value setting into the goto, so each point of failure need not do both. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-37-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, struct target_sve_context *sve = NULL; uint64_t extra_datap = 0; bool used_extra = false; - bool err = false; int vq = 0, sve_size = 0; target_restore_general_frame(env, sf); @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, switch (magic) { case 0: if (size != 0) { - err = true; - goto exit; + goto err; } if (used_extra) { ctx = NULL; @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, case TARGET_FPSIMD_MAGIC: if (fpsimd || size != sizeof(struct target_fpsimd_context)) { - err = true; - goto exit; + goto err; } fpsimd = (struct target_fpsimd_context *)ctx; break; @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, break; } } - err = true; - goto exit; + goto err; case TARGET_EXTRA_MAGIC: if (extra || size != sizeof(struct target_extra_context)) { - err = true; - goto exit; + goto err; } __get_user(extra_datap, &((struct target_extra_context *)ctx)->datap); @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, /* Unknown record -- we certainly didn't generate it. * Did we in fact get out of sync? */ - err = true; - goto exit; + goto err; } ctx = (void *)ctx + size; } @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, if (fpsimd) { target_restore_fpsimd_record(env, fpsimd); } else { - err = true; + goto err; } /* SVE data, if present, overwrites FPSIMD data. */ if (sve) { target_restore_sve_record(env, sve, vq); } - - exit: unlock_user(extra, extra_datap, 0); - return err; + return 0; + + err: + unlock_user(extra, extra_datap, 0); + return 1; } static abi_ulong get_sigframe(struct target_sigaction *ka, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> In parse_user_sigframe, the kernel rejects duplicate sve records, or records that are smaller than the header. We were silently allowing these cases to pass, dropping the record. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-38-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, break; case TARGET_SVE_MAGIC: + if (sve || size < sizeof(struct target_sve_context)) { + goto err; + } if (cpu_isar_feature(aa64_sve, env_archcpu(env))) { vq = sve_vq(env); sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(vq), 16); - if (!sve && size == sve_size) { + if (size == sve_size) { sve = (struct target_sve_context *)ctx; break; } -- 2.25.1 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: 20220708151540.18136-39-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, __get_user(extra_size, &((struct target_extra_context *)ctx)->size); extra = lock_user(VERIFY_READ, extra_datap, extra_size, 0); + if (!extra) { + return 1; + } break; default: -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Move the checks out of the parsing loop and into the restore function. This more closely mirrors the code structure in the kernel, and is slightly clearer. Reject rather than silently skip incorrect VL and SVE record sizes, bringing our checks in to line with those the kernel does. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-40-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 51 +++++++++++++++++++++++++------------ 1 file changed, 35 insertions(+), 16 deletions(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static void target_restore_fpsimd_record(CPUARMState *env, } } -static void target_restore_sve_record(CPUARMState *env, - struct target_sve_context *sve, int vq) +static bool target_restore_sve_record(CPUARMState *env, + struct target_sve_context *sve, + int size) { - int i, j; + int i, j, vl, vq; - /* Note that SVE regs are stored as a byte stream, with each byte element + if (!cpu_isar_feature(aa64_sve, env_archcpu(env))) { + return false; + } + + __get_user(vl, &sve->vl); + vq = sve_vq(env); + + /* Reject mismatched VL. */ + if (vl != vq * TARGET_SVE_VQ_BYTES) { + return false; + } + + /* Accept empty record -- used to clear PSTATE.SM. */ + if (size <= sizeof(*sve)) { + return true; + } + + /* Reject non-empty but incomplete record. */ + if (size < TARGET_SVE_SIG_CONTEXT_SIZE(vq)) { + return false; + } + + /* + * Note that SVE regs are stored as a byte stream, with each byte element * at a subsequent address. This corresponds to a little-endian load * of our 64-bit hunks. */ @@ -XXX,XX +XXX,XX @@ static void target_restore_sve_record(CPUARMState *env, } } } + return true; } static int target_restore_sigframe(CPUARMState *env, @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, struct target_sve_context *sve = NULL; uint64_t extra_datap = 0; bool used_extra = false; - int vq = 0, sve_size = 0; + int sve_size = 0; target_restore_general_frame(env, sf); @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, if (sve || size < sizeof(struct target_sve_context)) { goto err; } - if (cpu_isar_feature(aa64_sve, env_archcpu(env))) { - vq = sve_vq(env); - sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(vq), 16); - if (size == sve_size) { - sve = (struct target_sve_context *)ctx; - break; - } - } - goto err; + sve = (struct target_sve_context *)ctx; + sve_size = size; + break; case TARGET_EXTRA_MAGIC: if (extra || size != sizeof(struct target_extra_context)) { @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, } /* SVE data, if present, overwrites FPSIMD data. */ - if (sve) { - target_restore_sve_record(env, sve, vq); + if (sve && !target_restore_sve_record(env, sve, sve_size)) { + goto err; } unlock_user(extra, extra_datap, 0); return 0; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Set the SM bit in the SVE record on signal delivery, create the ZA record. Restore SM and ZA state according to the records present on return. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-41-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 167 +++++++++++++++++++++++++++++++++--- 1 file changed, 154 insertions(+), 13 deletions(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ struct target_sve_context { #define TARGET_SVE_SIG_FLAG_SM 1 +#define TARGET_ZA_MAGIC 0x54366345 + +struct target_za_context { + struct target_aarch64_ctx head; + uint16_t vl; + uint16_t reserved[3]; + /* The actual ZA data immediately follows. */ +}; + +#define TARGET_ZA_SIG_REGS_OFFSET \ + QEMU_ALIGN_UP(sizeof(struct target_za_context), TARGET_SVE_VQ_BYTES) +#define TARGET_ZA_SIG_ZAV_OFFSET(VQ, N) \ + (TARGET_ZA_SIG_REGS_OFFSET + (VQ) * TARGET_SVE_VQ_BYTES * (N)) +#define TARGET_ZA_SIG_CONTEXT_SIZE(VQ) \ + TARGET_ZA_SIG_ZAV_OFFSET(VQ, VQ * TARGET_SVE_VQ_BYTES) + struct target_rt_sigframe { struct target_siginfo info; struct target_ucontext uc; @@ -XXX,XX +XXX,XX @@ static void target_setup_end_record(struct target_aarch64_ctx *end) } static void target_setup_sve_record(struct target_sve_context *sve, - CPUARMState *env, int vq, int size) + CPUARMState *env, int size) { - int i, j; + int i, j, vq = sve_vq(env); memset(sve, 0, sizeof(*sve)); __put_user(TARGET_SVE_MAGIC, &sve->head.magic); @@ -XXX,XX +XXX,XX @@ static void target_setup_sve_record(struct target_sve_context *sve, } } +static void target_setup_za_record(struct target_za_context *za, + CPUARMState *env, int size) +{ + int vq = sme_vq(env); + int vl = vq * TARGET_SVE_VQ_BYTES; + int i, j; + + memset(za, 0, sizeof(*za)); + __put_user(TARGET_ZA_MAGIC, &za->head.magic); + __put_user(size, &za->head.size); + __put_user(vl, &za->vl); + + if (size == TARGET_ZA_SIG_CONTEXT_SIZE(0)) { + return; + } + assert(size == TARGET_ZA_SIG_CONTEXT_SIZE(vq)); + + /* + * Note that ZA vectors are stored as a byte stream, + * with each byte element at a subsequent address. + */ + for (i = 0; i < vl; ++i) { + uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i); + for (j = 0; j < vq * 2; ++j) { + __put_user_e(env->zarray[i].d[j], z + j, le); + } + } +} + static void target_restore_general_frame(CPUARMState *env, struct target_rt_sigframe *sf) { @@ -XXX,XX +XXX,XX @@ static void target_restore_fpsimd_record(CPUARMState *env, static bool target_restore_sve_record(CPUARMState *env, struct target_sve_context *sve, - int size) + int size, int *svcr) { - int i, j, vl, vq; + int i, j, vl, vq, flags; + bool sm; - if (!cpu_isar_feature(aa64_sve, env_archcpu(env))) { + __get_user(vl, &sve->vl); + __get_user(flags, &sve->flags); + + sm = flags & TARGET_SVE_SIG_FLAG_SM; + + /* The cpu must support Streaming or Non-streaming SVE. */ + if (sm + ? !cpu_isar_feature(aa64_sme, env_archcpu(env)) + : !cpu_isar_feature(aa64_sve, env_archcpu(env))) { return false; } - __get_user(vl, &sve->vl); - vq = sve_vq(env); + /* + * Note that we cannot use sve_vq() because that depends on the + * current setting of PSTATE.SM, not the state to be restored. + */ + vq = sve_vqm1_for_el_sm(env, 0, sm) + 1; /* Reject mismatched VL. */ if (vl != vq * TARGET_SVE_VQ_BYTES) { @@ -XXX,XX +XXX,XX @@ static bool target_restore_sve_record(CPUARMState *env, return false; } + *svcr = FIELD_DP64(*svcr, SVCR, SM, sm); + /* * Note that SVE regs are stored as a byte stream, with each byte element * at a subsequent address. This corresponds to a little-endian load @@ -XXX,XX +XXX,XX @@ static bool target_restore_sve_record(CPUARMState *env, return true; } +static bool target_restore_za_record(CPUARMState *env, + struct target_za_context *za, + int size, int *svcr) +{ + int i, j, vl, vq; + + if (!cpu_isar_feature(aa64_sme, env_archcpu(env))) { + return false; + } + + __get_user(vl, &za->vl); + vq = sme_vq(env); + + /* Reject mismatched VL. */ + if (vl != vq * TARGET_SVE_VQ_BYTES) { + return false; + } + + /* Accept empty record -- used to clear PSTATE.ZA. */ + if (size <= TARGET_ZA_SIG_CONTEXT_SIZE(0)) { + return true; + } + + /* Reject non-empty but incomplete record. */ + if (size < TARGET_ZA_SIG_CONTEXT_SIZE(vq)) { + return false; + } + + *svcr = FIELD_DP64(*svcr, SVCR, ZA, 1); + + for (i = 0; i < vl; ++i) { + uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i); + for (j = 0; j < vq * 2; ++j) { + __get_user_e(env->zarray[i].d[j], z + j, le); + } + } + return true; +} + static int target_restore_sigframe(CPUARMState *env, struct target_rt_sigframe *sf) { struct target_aarch64_ctx *ctx, *extra = NULL; struct target_fpsimd_context *fpsimd = NULL; struct target_sve_context *sve = NULL; + struct target_za_context *za = NULL; uint64_t extra_datap = 0; bool used_extra = false; int sve_size = 0; + int za_size = 0; + int svcr = 0; target_restore_general_frame(env, sf); @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, sve_size = size; break; + case TARGET_ZA_MAGIC: + if (za || size < sizeof(struct target_za_context)) { + goto err; + } + za = (struct target_za_context *)ctx; + za_size = size; + break; + case TARGET_EXTRA_MAGIC: if (extra || size != sizeof(struct target_extra_context)) { goto err; @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, } /* SVE data, if present, overwrites FPSIMD data. */ - if (sve && !target_restore_sve_record(env, sve, sve_size)) { + if (sve && !target_restore_sve_record(env, sve, sve_size, &svcr)) { goto err; } + if (za && !target_restore_za_record(env, za, za_size, &svcr)) { + goto err; + } + if (env->svcr != svcr) { + env->svcr = svcr; + arm_rebuild_hflags(env); + } unlock_user(extra, extra_datap, 0); return 0; @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, .total_size = offsetof(struct target_rt_sigframe, uc.tuc_mcontext.__reserved), }; - int fpsimd_ofs, fr_ofs, sve_ofs = 0, vq = 0, sve_size = 0; + int fpsimd_ofs, fr_ofs, sve_ofs = 0, za_ofs = 0; + int sve_size = 0, za_size = 0; struct target_rt_sigframe *frame; struct target_rt_frame_record *fr; abi_ulong frame_addr, return_addr; @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, &layout); /* SVE state needs saving only if it exists. */ - if (cpu_isar_feature(aa64_sve, env_archcpu(env))) { - vq = sve_vq(env); - sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(vq), 16); + if (cpu_isar_feature(aa64_sve, env_archcpu(env)) || + cpu_isar_feature(aa64_sme, env_archcpu(env))) { + sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(sve_vq(env)), 16); sve_ofs = alloc_sigframe_space(sve_size, &layout); } + if (cpu_isar_feature(aa64_sme, env_archcpu(env))) { + /* ZA state needs saving only if it is enabled. */ + if (FIELD_EX64(env->svcr, SVCR, ZA)) { + za_size = TARGET_ZA_SIG_CONTEXT_SIZE(sme_vq(env)); + } else { + za_size = TARGET_ZA_SIG_CONTEXT_SIZE(0); + } + za_ofs = alloc_sigframe_space(za_size, &layout); + } if (layout.extra_ofs) { /* Reserve space for the extra end marker. The standard end marker @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, target_setup_end_record((void *)frame + layout.extra_end_ofs); } if (sve_ofs) { - target_setup_sve_record((void *)frame + sve_ofs, env, vq, sve_size); + target_setup_sve_record((void *)frame + sve_ofs, env, sve_size); + } + if (za_ofs) { + target_setup_za_record((void *)frame + za_ofs, env, za_size); } /* Set up the stack frame for unwinding. */ @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, env->btype = 2; } + /* + * Invoke the signal handler with both SM and ZA disabled. + * When clearing SM, ResetSVEState, per SMSTOP. + */ + if (FIELD_EX64(env->svcr, SVCR, SM)) { + arm_reset_sve_state(env); + } + if (env->svcr) { + env->svcr = 0; + arm_rebuild_hflags(env); + } + if (info) { tswap_siginfo(&frame->info, info); env->xregs[1] = frame_addr + offsetof(struct target_rt_sigframe, info); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Add "sve" to the sve prctl functions, to distinguish them from the coming "sme" prctls with similar names. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-42-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/target_prctl.h | 8 ++++---- linux-user/syscall.c | 12 ++++++------ 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/linux-user/aarch64/target_prctl.h b/linux-user/aarch64/target_prctl.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/target_prctl.h +++ b/linux-user/aarch64/target_prctl.h @@ -XXX,XX +XXX,XX @@ #ifndef AARCH64_TARGET_PRCTL_H #define AARCH64_TARGET_PRCTL_H -static abi_long do_prctl_get_vl(CPUArchState *env) +static abi_long do_prctl_sve_get_vl(CPUArchState *env) { ARMCPU *cpu = env_archcpu(env); if (cpu_isar_feature(aa64_sve, cpu)) { @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_get_vl(CPUArchState *env) } return -TARGET_EINVAL; } -#define do_prctl_get_vl do_prctl_get_vl +#define do_prctl_sve_get_vl do_prctl_sve_get_vl -static abi_long do_prctl_set_vl(CPUArchState *env, abi_long arg2) +static abi_long do_prctl_sve_set_vl(CPUArchState *env, abi_long arg2) { /* * We cannot support either PR_SVE_SET_VL_ONEXEC or PR_SVE_VL_INHERIT. @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_set_vl(CPUArchState *env, abi_long arg2) } return -TARGET_EINVAL; } -#define do_prctl_set_vl do_prctl_set_vl +#define do_prctl_sve_set_vl do_prctl_sve_set_vl static abi_long do_prctl_reset_keys(CPUArchState *env, abi_long arg2) { diff --git a/linux-user/syscall.c b/linux-user/syscall.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_inval1(CPUArchState *env, abi_long arg2) #ifndef do_prctl_set_fp_mode #define do_prctl_set_fp_mode do_prctl_inval1 #endif -#ifndef do_prctl_get_vl -#define do_prctl_get_vl do_prctl_inval0 +#ifndef do_prctl_sve_get_vl +#define do_prctl_sve_get_vl do_prctl_inval0 #endif -#ifndef do_prctl_set_vl -#define do_prctl_set_vl do_prctl_inval1 +#ifndef do_prctl_sve_set_vl +#define do_prctl_sve_set_vl do_prctl_inval1 #endif #ifndef do_prctl_reset_keys #define do_prctl_reset_keys do_prctl_inval1 @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl(CPUArchState *env, abi_long option, abi_long arg2, case PR_SET_FP_MODE: return do_prctl_set_fp_mode(env, arg2); case PR_SVE_GET_VL: - return do_prctl_get_vl(env); + return do_prctl_sve_get_vl(env); case PR_SVE_SET_VL: - return do_prctl_set_vl(env, arg2); + return do_prctl_sve_set_vl(env, arg2); case PR_PAC_RESET_KEYS: if (arg3 || arg4 || arg5) { return -TARGET_EINVAL; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> These prctl set the Streaming SVE vector length, which may be completely different from the Normal SVE vector length. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-43-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/target_prctl.h | 54 +++++++++++++++++++++++++++++++ linux-user/syscall.c | 16 +++++++++ 2 files changed, 70 insertions(+) diff --git a/linux-user/aarch64/target_prctl.h b/linux-user/aarch64/target_prctl.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/target_prctl.h +++ b/linux-user/aarch64/target_prctl.h @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_sve_get_vl(CPUArchState *env) { ARMCPU *cpu = env_archcpu(env); if (cpu_isar_feature(aa64_sve, cpu)) { + /* PSTATE.SM is always unset on syscall entry. */ return sve_vq(env) * 16; } return -TARGET_EINVAL; @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_sve_set_vl(CPUArchState *env, abi_long arg2) && arg2 >= 0 && arg2 <= 512 * 16 && !(arg2 & 15)) { uint32_t vq, old_vq; + /* PSTATE.SM is always unset on syscall entry. */ old_vq = sve_vq(env); /* @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_sve_set_vl(CPUArchState *env, abi_long arg2) } #define do_prctl_sve_set_vl do_prctl_sve_set_vl +static abi_long do_prctl_sme_get_vl(CPUArchState *env) +{ + ARMCPU *cpu = env_archcpu(env); + if (cpu_isar_feature(aa64_sme, cpu)) { + return sme_vq(env) * 16; + } + return -TARGET_EINVAL; +} +#define do_prctl_sme_get_vl do_prctl_sme_get_vl + +static abi_long do_prctl_sme_set_vl(CPUArchState *env, abi_long arg2) +{ + /* + * We cannot support either PR_SME_SET_VL_ONEXEC or PR_SME_VL_INHERIT. + * Note the kernel definition of sve_vl_valid allows for VQ=512, + * i.e. VL=8192, even though the architectural maximum is VQ=16. + */ + if (cpu_isar_feature(aa64_sme, env_archcpu(env)) + && arg2 >= 0 && arg2 <= 512 * 16 && !(arg2 & 15)) { + int vq, old_vq; + + old_vq = sme_vq(env); + + /* + * Bound the value of vq, so that we know that it fits into + * the 4-bit field in SMCR_EL1. Because PSTATE.SM is cleared + * on syscall entry, we are not modifying the current SVE + * vector length. + */ + vq = MAX(arg2 / 16, 1); + vq = MIN(vq, 16); + env->vfp.smcr_el[1] = + FIELD_DP64(env->vfp.smcr_el[1], SMCR, LEN, vq - 1); + + /* Delay rebuilding hflags until we know if ZA must change. */ + vq = sve_vqm1_for_el_sm(env, 0, true) + 1; + + if (vq != old_vq) { + /* + * PSTATE.ZA state is cleared on any change to SVL. + * We need not call arm_rebuild_hflags because PSTATE.SM was + * cleared on syscall entry, so this hasn't changed VL. + */ + env->svcr = FIELD_DP64(env->svcr, SVCR, ZA, 0); + arm_rebuild_hflags(env); + } + return vq * 16; + } + return -TARGET_EINVAL; +} +#define do_prctl_sme_set_vl do_prctl_sme_set_vl + static abi_long do_prctl_reset_keys(CPUArchState *env, abi_long arg2) { ARMCPU *cpu = env_archcpu(env); diff --git a/linux-user/syscall.c b/linux-user/syscall.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -XXX,XX +XXX,XX @@ abi_long do_arch_prctl(CPUX86State *env, int code, abi_ulong addr) #ifndef PR_SET_SYSCALL_USER_DISPATCH # define PR_SET_SYSCALL_USER_DISPATCH 59 #endif +#ifndef PR_SME_SET_VL +# define PR_SME_SET_VL 63 +# define PR_SME_GET_VL 64 +# define PR_SME_VL_LEN_MASK 0xffff +# define PR_SME_VL_INHERIT (1 << 17) +#endif #include "target_prctl.h" @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_inval1(CPUArchState *env, abi_long arg2) #ifndef do_prctl_set_unalign #define do_prctl_set_unalign do_prctl_inval1 #endif +#ifndef do_prctl_sme_get_vl +#define do_prctl_sme_get_vl do_prctl_inval0 +#endif +#ifndef do_prctl_sme_set_vl +#define do_prctl_sme_set_vl do_prctl_inval1 +#endif static abi_long do_prctl(CPUArchState *env, abi_long option, abi_long arg2, abi_long arg3, abi_long arg4, abi_long arg5) @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl(CPUArchState *env, abi_long option, abi_long arg2, return do_prctl_sve_get_vl(env); case PR_SVE_SET_VL: return do_prctl_sve_set_vl(env, arg2); + case PR_SME_GET_VL: + return do_prctl_sme_get_vl(env); + case PR_SME_SET_VL: + return do_prctl_sme_set_vl(env, arg2); case PR_PAC_RESET_KEYS: if (arg3 || arg4 || arg5) { return -TARGET_EINVAL; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> There's no reason to set CPACR_EL1.ZEN if SVE disabled. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-44-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(DeviceState *dev) /* and to the FP/Neon instructions */ env->cp15.cpacr_el1 = FIELD_DP64(env->cp15.cpacr_el1, CPACR_EL1, FPEN, 3); - /* and to the SVE instructions */ - env->cp15.cpacr_el1 = FIELD_DP64(env->cp15.cpacr_el1, - CPACR_EL1, ZEN, 3); - /* with reasonable vector length */ + /* and to the SVE instructions, with default vector length */ if (cpu_isar_feature(aa64_sve, cpu)) { + env->cp15.cpacr_el1 = FIELD_DP64(env->cp15.cpacr_el1, + CPACR_EL1, ZEN, 3); env->vfp.zcr_el[1] = cpu->sve_default_vq - 1; } /* -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Enable SME, TPIDR2_EL0, and FA64 if supported by the cpu. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-45-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(DeviceState *dev) CPACR_EL1, ZEN, 3); env->vfp.zcr_el[1] = cpu->sve_default_vq - 1; } + /* and for SME instructions, with default vector length, and TPIDR2 */ + if (cpu_isar_feature(aa64_sme, cpu)) { + env->cp15.sctlr_el[1] |= SCTLR_EnTP2; + env->cp15.cpacr_el1 = FIELD_DP64(env->cp15.cpacr_el1, + CPACR_EL1, SMEN, 3); + env->vfp.smcr_el[1] = cpu->sme_default_vq - 1; + if (cpu_isar_feature(aa64_sme_fa64, cpu)) { + env->vfp.smcr_el[1] = FIELD_DP64(env->vfp.smcr_el[1], + SMCR, FA64, 1); + } + } /* * Enable 48-bit address space (TODO: take reserved_va into account). * Enable TBI0 but not TBI1. -- 2.25.1 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: 20220708151540.18136-46-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/elfload.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) 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 @@ enum { ARM_HWCAP2_A64_RNG = 1 << 16, ARM_HWCAP2_A64_BTI = 1 << 17, ARM_HWCAP2_A64_MTE = 1 << 18, + ARM_HWCAP2_A64_ECV = 1 << 19, + ARM_HWCAP2_A64_AFP = 1 << 20, + ARM_HWCAP2_A64_RPRES = 1 << 21, + ARM_HWCAP2_A64_MTE3 = 1 << 22, + ARM_HWCAP2_A64_SME = 1 << 23, + ARM_HWCAP2_A64_SME_I16I64 = 1 << 24, + ARM_HWCAP2_A64_SME_F64F64 = 1 << 25, + ARM_HWCAP2_A64_SME_I8I32 = 1 << 26, + ARM_HWCAP2_A64_SME_F16F32 = 1 << 27, + ARM_HWCAP2_A64_SME_B16F32 = 1 << 28, + ARM_HWCAP2_A64_SME_F32F32 = 1 << 29, + ARM_HWCAP2_A64_SME_FA64 = 1 << 30, }; #define ELF_HWCAP get_elf_hwcap() @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap2(void) GET_FEATURE_ID(aa64_rndr, ARM_HWCAP2_A64_RNG); GET_FEATURE_ID(aa64_bti, ARM_HWCAP2_A64_BTI); GET_FEATURE_ID(aa64_mte, ARM_HWCAP2_A64_MTE); + GET_FEATURE_ID(aa64_sme, (ARM_HWCAP2_A64_SME | + ARM_HWCAP2_A64_SME_F32F32 | + ARM_HWCAP2_A64_SME_B16F32 | + ARM_HWCAP2_A64_SME_F16F32 | + ARM_HWCAP2_A64_SME_I8I32)); + GET_FEATURE_ID(aa64_sme_f64f64, ARM_HWCAP2_A64_SME_F64F64); + GET_FEATURE_ID(aa64_sme_i16i64, ARM_HWCAP2_A64_SME_I16I64); + GET_FEATURE_ID(aa64_sme_fa64, ARM_HWCAP2_A64_SME_FA64); return hwcaps; } -- 2.25.1 The following changes since commit 3db29dcac23da85486704ef9e7a8e7217f7829cd: Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging (2023-01-12 13:51:36 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20230113 for you to fetch changes up to 08899b5c68a55a3780d707e2464073c8f2670d31: target/arm: allow writes to SCR_EL3.HXEn bit when FEAT_HCX is enabled (2023-01-13 13:19:36 +0000) ---------------------------------------------------------------- target-arm queue: hw/arm/stm32f405: correctly describe the memory layout hw/arm: Add Olimex H405 board cubieboard: Support booting from an SD card image with u-boot on it target/arm: Fix sve_probe_page target/arm: allow writes to SCR_EL3.HXEn bit when FEAT_HCX is enabled various code cleanups ---------------------------------------------------------------- Evgeny Iakovlev (1): target/arm: allow writes to SCR_EL3.HXEn bit when FEAT_HCX is enabled Felipe Balbi (2): hw/arm/stm32f405: correctly describe the memory layout hw/arm: Add Olimex H405 Philippe Mathieu-Daudé (27): hw/arm/pxa2xx: Simplify pxa255_init() hw/arm/pxa2xx: Simplify pxa270_init() hw/arm/collie: Use the IEC binary prefix definitions hw/arm/collie: Simplify flash creation using for() loop hw/arm/gumstix: Improve documentation hw/arm/gumstix: Use the IEC binary prefix definitions hw/arm/mainstone: Use the IEC binary prefix definitions hw/arm/musicpal: Use the IEC binary prefix definitions hw/arm/omap_sx1: Remove unused 'total_ram' definitions hw/arm/omap_sx1: Use the IEC binary prefix definitions hw/arm/z2: Use the IEC binary prefix definitions hw/arm/vexpress: Remove dead code in vexpress_common_init() hw/arm: Remove unreachable code calling pflash_cfi01_register() hw/arm/pxa: Avoid forward-declaring PXA2xxI2CState hw/gpio/omap_gpio: Add local variable to avoid embedded cast hw/arm/omap: Drop useless casts from void * to pointer hw/gpio/omap_gpio: Use CamelCase for TYPE_OMAP1_GPIO type name hw/gpio/omap_gpio: Use CamelCase for TYPE_OMAP2_GPIO type name hw/intc/omap_intc: Use CamelCase for TYPE_OMAP_INTC type name hw/arm/stellaris: Drop useless casts from void * to pointer hw/arm/stellaris: Use CamelCase for STELLARIS_ADC type name hw/arm/bcm2836: Remove definitions generated by OBJECT_DECLARE_TYPE() hw/arm/npcm7xx: Declare QOM macros using OBJECT_DECLARE_SIMPLE_TYPE() hw/misc/sbsa_ec: Rename TYPE_SBSA_EC -> TYPE_SBSA_SECURE_EC hw/misc/sbsa_ec: Declare QOM macros using OBJECT_DECLARE_SIMPLE_TYPE() hw/intc/xilinx_intc: Use 'XpsIntc' typedef instead of 'struct xlx_pic' hw/timer/xilinx_timer: Use XpsTimerState instead of 'struct timerblock' Richard Henderson (1): target/arm: Fix sve_probe_page Strahinja Jankovic (7): hw/misc: Allwinner-A10 Clock Controller Module Emulation hw/misc: Allwinner A10 DRAM Controller Emulation {hw/i2c,docs/system/arm}: Allwinner TWI/I2C Emulation hw/misc: AXP209 PMU Emulation hw/arm: Add AXP209 to Cubieboard hw/arm: Allwinner A10 enable SPL load from MMC tests/avocado: Add SD boot test to Cubieboard docs/system/arm/cubieboard.rst | 1 + docs/system/arm/orangepi.rst | 1 + docs/system/arm/stm32.rst | 1 + configs/devices/arm-softmmu/default.mak | 1 + include/hw/adc/npcm7xx_adc.h | 7 +- include/hw/arm/allwinner-a10.h | 27 ++ include/hw/arm/allwinner-h3.h | 3 + include/hw/arm/npcm7xx.h | 18 +- include/hw/arm/omap.h | 24 +- include/hw/arm/pxa.h | 11 +- include/hw/arm/stm32f405_soc.h | 5 +- include/hw/i2c/allwinner-i2c.h | 55 ++++ include/hw/i2c/npcm7xx_smbus.h | 7 +- include/hw/misc/allwinner-a10-ccm.h | 67 +++++ include/hw/misc/allwinner-a10-dramc.h | 68 +++++ include/hw/misc/npcm7xx_clk.h | 2 +- include/hw/misc/npcm7xx_gcr.h | 6 +- include/hw/misc/npcm7xx_mft.h | 7 +- include/hw/misc/npcm7xx_pwm.h | 3 +- include/hw/misc/npcm7xx_rng.h | 6 +- include/hw/net/npcm7xx_emc.h | 5 +- include/hw/sd/npcm7xx_sdhci.h | 4 +- hw/arm/allwinner-a10.c | 40 +++ hw/arm/allwinner-h3.c | 11 +- hw/arm/bcm2836.c | 9 +- hw/arm/collie.c | 25 +- hw/arm/cubieboard.c | 11 + hw/arm/gumstix.c | 45 ++-- hw/arm/mainstone.c | 37 ++- hw/arm/musicpal.c | 9 +- hw/arm/olimex-stm32-h405.c | 69 +++++ hw/arm/omap1.c | 115 ++++---- hw/arm/omap2.c | 40 ++- hw/arm/omap_sx1.c | 53 ++-- hw/arm/palm.c | 2 +- hw/arm/pxa2xx.c | 8 +- hw/arm/spitz.c | 6 +- hw/arm/stellaris.c | 73 +++-- hw/arm/stm32f405_soc.c | 8 + hw/arm/tosa.c | 2 +- hw/arm/versatilepb.c | 6 +- hw/arm/vexpress.c | 10 +- hw/arm/z2.c | 16 +- hw/char/omap_uart.c | 7 +- hw/display/omap_dss.c | 15 +- hw/display/omap_lcdc.c | 9 +- hw/dma/omap_dma.c | 15 +- hw/gpio/omap_gpio.c | 48 ++-- hw/i2c/allwinner-i2c.c | 459 ++++++++++++++++++++++++++++++++ hw/intc/omap_intc.c | 38 +-- hw/intc/xilinx_intc.c | 28 +- hw/misc/allwinner-a10-ccm.c | 224 ++++++++++++++++ hw/misc/allwinner-a10-dramc.c | 179 +++++++++++++ hw/misc/axp209.c | 238 +++++++++++++++++ hw/misc/omap_gpmc.c | 12 +- hw/misc/omap_l4.c | 7 +- hw/misc/omap_sdrc.c | 7 +- hw/misc/omap_tap.c | 5 +- hw/misc/sbsa_ec.c | 12 +- hw/sd/omap_mmc.c | 9 +- hw/ssi/omap_spi.c | 7 +- hw/timer/omap_gptimer.c | 22 +- hw/timer/omap_synctimer.c | 4 +- hw/timer/xilinx_timer.c | 27 +- target/arm/helper.c | 3 + target/arm/sve_helper.c | 14 +- MAINTAINERS | 8 + hw/arm/Kconfig | 9 + hw/arm/meson.build | 1 + hw/i2c/Kconfig | 4 + hw/i2c/meson.build | 1 + hw/i2c/trace-events | 5 + hw/misc/Kconfig | 10 + hw/misc/meson.build | 3 + hw/misc/trace-events | 5 + tests/avocado/boot_linux_console.py | 47 ++++ 76 files changed, 1951 insertions(+), 455 deletions(-) create mode 100644 include/hw/i2c/allwinner-i2c.h create mode 100644 include/hw/misc/allwinner-a10-ccm.h create mode 100644 include/hw/misc/allwinner-a10-dramc.h create mode 100644 hw/arm/olimex-stm32-h405.c create mode 100644 hw/i2c/allwinner-i2c.c create mode 100644 hw/misc/allwinner-a10-ccm.c create mode 100644 hw/misc/allwinner-a10-dramc.c create mode 100644 hw/misc/axp209.c From: Felipe Balbi <balbi@kernel.org> STM32F405 has 128K of SRAM and another 64K of CCM (Core-coupled Memory) at a different base address. Correctly describe the memory layout to give existing FW images a chance to run unmodified. Reviewed-by: Alistair Francis <alistair@alistair23.me> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Felipe Balbi <balbi@kernel.org> Message-id: 20221230145733.200496-2-balbi@kernel.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/stm32f405_soc.h | 5 ++++- hw/arm/stm32f405_soc.c | 8 ++++++++ 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/include/hw/arm/stm32f405_soc.h b/include/hw/arm/stm32f405_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/stm32f405_soc.h +++ b/include/hw/arm/stm32f405_soc.h @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(STM32F405State, STM32F405_SOC) #define FLASH_BASE_ADDRESS 0x08000000 #define FLASH_SIZE (1024 * 1024) #define SRAM_BASE_ADDRESS 0x20000000 -#define SRAM_SIZE (192 * 1024) +#define SRAM_SIZE (128 * 1024) +#define CCM_BASE_ADDRESS 0x10000000 +#define CCM_SIZE (64 * 1024) struct STM32F405State { /*< private >*/ @@ -XXX,XX +XXX,XX @@ struct STM32F405State { STM32F2XXADCState adc[STM_NUM_ADCS]; STM32F2XXSPIState spi[STM_NUM_SPIS]; + MemoryRegion ccm; MemoryRegion sram; MemoryRegion flash; MemoryRegion flash_alias; diff --git a/hw/arm/stm32f405_soc.c b/hw/arm/stm32f405_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32f405_soc.c +++ b/hw/arm/stm32f405_soc.c @@ -XXX,XX +XXX,XX @@ static void stm32f405_soc_realize(DeviceState *dev_soc, Error **errp) } memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, &s->sram); + memory_region_init_ram(&s->ccm, NULL, "STM32F405.ccm", CCM_SIZE, + &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + memory_region_add_subregion(system_memory, CCM_BASE_ADDRESS, &s->ccm); + armv7m = DEVICE(&s->armv7m); qdev_prop_set_uint32(armv7m, "num-irq", 96); qdev_prop_set_string(armv7m, "cpu-type", s->cpu_type); -- 2.34.1 From: Felipe Balbi <balbi@kernel.org> Olimex makes a series of low-cost STM32 boards. This commit introduces the minimum setup to support SMT32-H405. See [1] for details [1] https://www.olimex.com/Products/ARM/ST/STM32-H405/ Signed-off-by: Felipe Balbi <balbi@kernel.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20221230145733.200496-3-balbi@kernel.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/stm32.rst | 1 + configs/devices/arm-softmmu/default.mak | 1 + hw/arm/olimex-stm32-h405.c | 69 +++++++++++++++++++++++++ MAINTAINERS | 6 +++ hw/arm/Kconfig | 4 ++ hw/arm/meson.build | 1 + 6 files changed, 82 insertions(+) create mode 100644 hw/arm/olimex-stm32-h405.c diff --git a/docs/system/arm/stm32.rst b/docs/system/arm/stm32.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/stm32.rst +++ b/docs/system/arm/stm32.rst @@ -XXX,XX +XXX,XX @@ The STM32F4 series is based on ARM Cortex-M4F core. This series is pin-to-pin compatible with STM32F2 series. The following machines are based on this chip : - ``netduinoplus2`` Netduino Plus 2 board with STM32F405RGT6 microcontroller +- ``olimex-stm32-h405`` Olimex STM32 H405 board with STM32F405RGT6 microcontroller There are many other STM32 series that are currently not supported by QEMU. diff --git a/configs/devices/arm-softmmu/default.mak b/configs/devices/arm-softmmu/default.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/devices/arm-softmmu/default.mak +++ b/configs/devices/arm-softmmu/default.mak @@ -XXX,XX +XXX,XX @@ CONFIG_COLLIE=y CONFIG_ASPEED_SOC=y CONFIG_NETDUINO2=y CONFIG_NETDUINOPLUS2=y +CONFIG_OLIMEX_STM32_H405=y CONFIG_MPS2=y CONFIG_RASPI=y CONFIG_DIGIC=y diff --git a/hw/arm/olimex-stm32-h405.c b/hw/arm/olimex-stm32-h405.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/olimex-stm32-h405.c @@ -XXX,XX +XXX,XX @@ +/* + * ST STM32VLDISCOVERY machine + * Olimex STM32-H405 machine + * + * Copyright (c) 2022 Felipe Balbi <balbi@kernel.org> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "hw/boards.h" +#include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" +#include "qemu/error-report.h" +#include "hw/arm/stm32f405_soc.h" +#include "hw/arm/boot.h" + +/* olimex-stm32-h405 implementation is derived from netduinoplus2 */ + +/* Main SYSCLK frequency in Hz (168MHz) */ +#define SYSCLK_FRQ 168000000ULL + +static void olimex_stm32_h405_init(MachineState *machine) +{ + DeviceState *dev; + Clock *sysclk; + + /* This clock doesn't need migration because it is fixed-frequency */ + sysclk = clock_new(OBJECT(machine), "SYSCLK"); + clock_set_hz(sysclk, SYSCLK_FRQ); + + dev = qdev_new(TYPE_STM32F405_SOC); + qdev_prop_set_string(dev, "cpu-type", ARM_CPU_TYPE_NAME("cortex-m4")); + qdev_connect_clock_in(dev, "sysclk", sysclk); + sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); + + armv7m_load_kernel(ARM_CPU(first_cpu), + machine->kernel_filename, + 0, FLASH_SIZE); +} + +static void olimex_stm32_h405_machine_init(MachineClass *mc) +{ + mc->desc = "Olimex STM32-H405 (Cortex-M4)"; + mc->init = olimex_stm32_h405_init; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m4"); + + /* SRAM pre-allocated as part of the SoC instantiation */ + mc->default_ram_size = 0; +} + +DEFINE_MACHINE("olimex-stm32-h405", olimex_stm32_h405_machine_init) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ L: qemu-arm@nongnu.org S: Maintained F: hw/arm/netduinoplus2.c +Olimex STM32 H405 +M: Felipe Balbi <balbi@kernel.org> +L: qemu-arm@nongnu.org +S: Maintained +F: hw/arm/olimex-stm32-h405.c + SmartFusion2 M: Subbaraya Sundeep <sundeep.lkml@gmail.com> M: Peter Maydell <peter.maydell@linaro.org> diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config NETDUINOPLUS2 bool select STM32F405_SOC +config OLIMEX_STM32_H405 + bool + select STM32F405_SOC + config NSERIES bool select OMAP diff --git a/hw/arm/meson.build b/hw/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/meson.build +++ b/hw/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'CONFIG_MICROBIT', if_true: files('microbit.c')) arm_ss.add(when: 'CONFIG_MUSICPAL', if_true: files('musicpal.c')) arm_ss.add(when: 'CONFIG_NETDUINO2', if_true: files('netduino2.c')) arm_ss.add(when: 'CONFIG_NETDUINOPLUS2', if_true: files('netduinoplus2.c')) +arm_ss.add(when: 'CONFIG_OLIMEX_STM32_H405', if_true: files('olimex-stm32-h405.c')) arm_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx.c', 'npcm7xx_boards.c')) arm_ss.add(when: 'CONFIG_NSERIES', if_true: files('nseries.c')) arm_ss.add(when: 'CONFIG_SX1', if_true: files('omap_sx1.c')) -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> During SPL boot several Clock Controller Module (CCM) registers are read, most important are PLL and Tuning, as well as divisor registers. This patch adds these registers and initializes reset values from user's guide. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-2-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-a10.h | 2 + include/hw/misc/allwinner-a10-ccm.h | 67 +++++++++ hw/arm/allwinner-a10.c | 7 + hw/misc/allwinner-a10-ccm.c | 224 ++++++++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/misc/Kconfig | 3 + hw/misc/meson.build | 1 + 7 files changed, 305 insertions(+) create mode 100644 include/hw/misc/allwinner-a10-ccm.h create mode 100644 hw/misc/allwinner-a10-ccm.c diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -XXX,XX +XXX,XX @@ #include "hw/usb/hcd-ohci.h" #include "hw/usb/hcd-ehci.h" #include "hw/rtc/allwinner-rtc.h" +#include "hw/misc/allwinner-a10-ccm.h" #include "target/arm/cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct AwA10State { /*< public >*/ ARMCPU cpu; + AwA10ClockCtlState ccm; AwA10PITState timer; AwA10PICState intc; AwEmacState emac; diff --git a/include/hw/misc/allwinner-a10-ccm.h b/include/hw/misc/allwinner-a10-ccm.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-a10-ccm.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner A10 Clock Control Module emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from Allwinner H3 CCU, + * by Niek Linnenbank. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_A10_CCM_H +#define HW_MISC_ALLWINNER_A10_CCM_H + +#include "qom/object.h" +#include "hw/sysbus.h" + +/** + * @name Constants + * @{ + */ + +/** Size of register I/O address space used by CCM device */ +#define AW_A10_CCM_IOSIZE (0x400) + +/** Total number of known registers */ +#define AW_A10_CCM_REGS_NUM (AW_A10_CCM_IOSIZE / sizeof(uint32_t)) + +/** @} */ + +/** + * @name Object model + * @{ + */ + +#define TYPE_AW_A10_CCM "allwinner-a10-ccm" +OBJECT_DECLARE_SIMPLE_TYPE(AwA10ClockCtlState, AW_A10_CCM) + +/** @} */ + +/** + * Allwinner A10 CCM object instance state. + */ +struct AwA10ClockCtlState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Array of hardware registers */ + uint32_t regs[AW_A10_CCM_REGS_NUM]; +}; + +#endif /* HW_MISC_ALLWINNER_H3_CCU_H */ diff --git a/hw/arm/allwinner-a10.c b/hw/arm/allwinner-a10.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-a10.c +++ b/hw/arm/allwinner-a10.c @@ -XXX,XX +XXX,XX @@ #include "hw/usb/hcd-ohci.h" #define AW_A10_MMC0_BASE 0x01c0f000 +#define AW_A10_CCM_BASE 0x01c20000 #define AW_A10_PIC_REG_BASE 0x01c20400 #define AW_A10_PIT_REG_BASE 0x01c20c00 #define AW_A10_UART0_REG_BASE 0x01c28000 @@ -XXX,XX +XXX,XX @@ static void aw_a10_init(Object *obj) object_initialize_child(obj, "timer", &s->timer, TYPE_AW_A10_PIT); + object_initialize_child(obj, "ccm", &s->ccm, TYPE_AW_A10_CCM); + object_initialize_child(obj, "emac", &s->emac, TYPE_AW_EMAC); object_initialize_child(obj, "sata", &s->sata, TYPE_ALLWINNER_AHCI); @@ -XXX,XX +XXX,XX @@ static void aw_a10_realize(DeviceState *dev, Error **errp) memory_region_add_subregion(get_system_memory(), 0x00000000, &s->sram_a); create_unimplemented_device("a10-sram-ctrl", 0x01c00000, 4 * KiB); + /* Clock Control Module */ + sysbus_realize(SYS_BUS_DEVICE(&s->ccm), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccm), 0, AW_A10_CCM_BASE); + /* FIXME use qdev NIC properties instead of nd_table[] */ if (nd_table[0].used) { qemu_check_nic_model(&nd_table[0], TYPE_AW_EMAC); diff --git a/hw/misc/allwinner-a10-ccm.c b/hw/misc/allwinner-a10-ccm.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-a10-ccm.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner A10 Clock Control Module emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from Allwinner H3 CCU, + * by Niek Linnenbank. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "hw/misc/allwinner-a10-ccm.h" + +/* CCM register offsets */ +enum { + REG_PLL1_CFG = 0x0000, /* PLL1 Control */ + REG_PLL1_TUN = 0x0004, /* PLL1 Tuning */ + REG_PLL2_CFG = 0x0008, /* PLL2 Control */ + REG_PLL2_TUN = 0x000C, /* PLL2 Tuning */ + REG_PLL3_CFG = 0x0010, /* PLL3 Control */ + REG_PLL4_CFG = 0x0018, /* PLL4 Control */ + REG_PLL5_CFG = 0x0020, /* PLL5 Control */ + REG_PLL5_TUN = 0x0024, /* PLL5 Tuning */ + REG_PLL6_CFG = 0x0028, /* PLL6 Control */ + REG_PLL6_TUN = 0x002C, /* PLL6 Tuning */ + REG_PLL7_CFG = 0x0030, /* PLL7 Control */ + REG_PLL1_TUN2 = 0x0038, /* PLL1 Tuning2 */ + REG_PLL5_TUN2 = 0x003C, /* PLL5 Tuning2 */ + REG_PLL8_CFG = 0x0040, /* PLL8 Control */ + REG_OSC24M_CFG = 0x0050, /* OSC24M Control */ + REG_CPU_AHB_APB0_CFG = 0x0054, /* CPU, AHB and APB0 Divide Ratio */ +}; + +#define REG_INDEX(offset) (offset / sizeof(uint32_t)) + +/* CCM register reset values */ +enum { + REG_PLL1_CFG_RST = 0x21005000, + REG_PLL1_TUN_RST = 0x0A101000, + REG_PLL2_CFG_RST = 0x08100010, + REG_PLL2_TUN_RST = 0x00000000, + REG_PLL3_CFG_RST = 0x0010D063, + REG_PLL4_CFG_RST = 0x21009911, + REG_PLL5_CFG_RST = 0x11049280, + REG_PLL5_TUN_RST = 0x14888000, + REG_PLL6_CFG_RST = 0x21009911, + REG_PLL6_TUN_RST = 0x00000000, + REG_PLL7_CFG_RST = 0x0010D063, + REG_PLL1_TUN2_RST = 0x00000000, + REG_PLL5_TUN2_RST = 0x00000000, + REG_PLL8_CFG_RST = 0x21009911, + REG_OSC24M_CFG_RST = 0x00138013, + REG_CPU_AHB_APB0_CFG_RST = 0x00010010, +}; + +static uint64_t allwinner_a10_ccm_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwA10ClockCtlState *s = AW_A10_CCM(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case REG_PLL1_CFG: + case REG_PLL1_TUN: + case REG_PLL2_CFG: + case REG_PLL2_TUN: + case REG_PLL3_CFG: + case REG_PLL4_CFG: + case REG_PLL5_CFG: + case REG_PLL5_TUN: + case REG_PLL6_CFG: + case REG_PLL6_TUN: + case REG_PLL7_CFG: + case REG_PLL1_TUN2: + case REG_PLL5_TUN2: + case REG_PLL8_CFG: + case REG_OSC24M_CFG: + case REG_CPU_AHB_APB0_CFG: + break; + case 0x158 ... AW_A10_CCM_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + default: + qemu_log_mask(LOG_UNIMP, "%s: unimplemented read offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + return s->regs[idx]; +} + +static void allwinner_a10_ccm_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwA10ClockCtlState *s = AW_A10_CCM(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case REG_PLL1_CFG: + case REG_PLL1_TUN: + case REG_PLL2_CFG: + case REG_PLL2_TUN: + case REG_PLL3_CFG: + case REG_PLL4_CFG: + case REG_PLL5_CFG: + case REG_PLL5_TUN: + case REG_PLL6_CFG: + case REG_PLL6_TUN: + case REG_PLL7_CFG: + case REG_PLL1_TUN2: + case REG_PLL5_TUN2: + case REG_PLL8_CFG: + case REG_OSC24M_CFG: + case REG_CPU_AHB_APB0_CFG: + break; + case 0x158 ... AW_A10_CCM_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + default: + qemu_log_mask(LOG_UNIMP, "%s: unimplemented write offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + } + + s->regs[idx] = (uint32_t) val; +} + +static const MemoryRegionOps allwinner_a10_ccm_ops = { + .read = allwinner_a10_ccm_read, + .write = allwinner_a10_ccm_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_a10_ccm_reset_enter(Object *obj, ResetType type) +{ + AwA10ClockCtlState *s = AW_A10_CCM(obj); + + /* Set default values for registers */ + s->regs[REG_INDEX(REG_PLL1_CFG)] = REG_PLL1_CFG_RST; + s->regs[REG_INDEX(REG_PLL1_TUN)] = REG_PLL1_TUN_RST; + s->regs[REG_INDEX(REG_PLL2_CFG)] = REG_PLL2_CFG_RST; + s->regs[REG_INDEX(REG_PLL2_TUN)] = REG_PLL2_TUN_RST; + s->regs[REG_INDEX(REG_PLL3_CFG)] = REG_PLL3_CFG_RST; + s->regs[REG_INDEX(REG_PLL4_CFG)] = REG_PLL4_CFG_RST; + s->regs[REG_INDEX(REG_PLL5_CFG)] = REG_PLL5_CFG_RST; + s->regs[REG_INDEX(REG_PLL5_TUN)] = REG_PLL5_TUN_RST; + s->regs[REG_INDEX(REG_PLL6_CFG)] = REG_PLL6_CFG_RST; + s->regs[REG_INDEX(REG_PLL6_TUN)] = REG_PLL6_TUN_RST; + s->regs[REG_INDEX(REG_PLL7_CFG)] = REG_PLL7_CFG_RST; + s->regs[REG_INDEX(REG_PLL1_TUN2)] = REG_PLL1_TUN2_RST; + s->regs[REG_INDEX(REG_PLL5_TUN2)] = REG_PLL5_TUN2_RST; + s->regs[REG_INDEX(REG_PLL8_CFG)] = REG_PLL8_CFG_RST; + s->regs[REG_INDEX(REG_OSC24M_CFG)] = REG_OSC24M_CFG_RST; + s->regs[REG_INDEX(REG_CPU_AHB_APB0_CFG)] = REG_CPU_AHB_APB0_CFG_RST; +} + +static void allwinner_a10_ccm_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwA10ClockCtlState *s = AW_A10_CCM(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_a10_ccm_ops, s, + TYPE_AW_A10_CCM, AW_A10_CCM_IOSIZE); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_a10_ccm_vmstate = { + .name = "allwinner-a10-ccm", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AwA10ClockCtlState, AW_A10_CCM_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_a10_ccm_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.enter = allwinner_a10_ccm_reset_enter; + dc->vmsd = &allwinner_a10_ccm_vmstate; +} + +static const TypeInfo allwinner_a10_ccm_info = { + .name = TYPE_AW_A10_CCM, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_a10_ccm_init, + .instance_size = sizeof(AwA10ClockCtlState), + .class_init = allwinner_a10_ccm_class_init, +}; + +static void allwinner_a10_ccm_register(void) +{ + type_register_static(&allwinner_a10_ccm_info); +} + +type_init(allwinner_a10_ccm_register) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10 select AHCI select ALLWINNER_A10_PIT select ALLWINNER_A10_PIC + select ALLWINNER_A10_CCM select ALLWINNER_EMAC select SERIAL select UNIMP diff --git a/hw/misc/Kconfig b/hw/misc/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Kconfig +++ b/hw/misc/Kconfig @@ -XXX,XX +XXX,XX @@ config VIRT_CTRL config LASI bool +config ALLWINNER_A10_CCM + bool + source macio/Kconfig diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ subdir('macio') softmmu_ss.add(when: 'CONFIG_IVSHMEM_DEVICE', if_true: files('ivshmem.c')) +softmmu_ss.add(when: 'CONFIG_ALLWINNER_A10_CCM', if_true: files('allwinner-a10-ccm.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-ccu.c')) specific_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-cpucfg.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-dramc.c')) -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> During SPL boot several DRAM Controller registers are used. Most important registers are those related to DRAM initialization and calibration, where SPL initiates process and waits until certain bit is set/cleared. This patch adds these registers, initializes reset values from user's guide and updates state of registers as SPL expects it. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-3-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-a10.h | 2 + include/hw/misc/allwinner-a10-dramc.h | 68 ++++++++++ hw/arm/allwinner-a10.c | 7 + hw/misc/allwinner-a10-dramc.c | 179 ++++++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/misc/Kconfig | 3 + hw/misc/meson.build | 1 + 7 files changed, 261 insertions(+) create mode 100644 include/hw/misc/allwinner-a10-dramc.h create mode 100644 hw/misc/allwinner-a10-dramc.c diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -XXX,XX +XXX,XX @@ #include "hw/usb/hcd-ehci.h" #include "hw/rtc/allwinner-rtc.h" #include "hw/misc/allwinner-a10-ccm.h" +#include "hw/misc/allwinner-a10-dramc.h" #include "target/arm/cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct AwA10State { ARMCPU cpu; AwA10ClockCtlState ccm; + AwA10DramControllerState dramc; AwA10PITState timer; AwA10PICState intc; AwEmacState emac; diff --git a/include/hw/misc/allwinner-a10-dramc.h b/include/hw/misc/allwinner-a10-dramc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/allwinner-a10-dramc.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner A10 DRAM Controller emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from Allwinner H3 DRAMC, + * by Niek Linnenbank. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#ifndef HW_MISC_ALLWINNER_A10_DRAMC_H +#define HW_MISC_ALLWINNER_A10_DRAMC_H + +#include "qom/object.h" +#include "hw/sysbus.h" +#include "hw/register.h" + +/** + * @name Constants + * @{ + */ + +/** Size of register I/O address space used by DRAMC device */ +#define AW_A10_DRAMC_IOSIZE (0x1000) + +/** Total number of known registers */ +#define AW_A10_DRAMC_REGS_NUM (AW_A10_DRAMC_IOSIZE / sizeof(uint32_t)) + +/** @} */ + +/** + * @name Object model + * @{ + */ + +#define TYPE_AW_A10_DRAMC "allwinner-a10-dramc" +OBJECT_DECLARE_SIMPLE_TYPE(AwA10DramControllerState, AW_A10_DRAMC) + +/** @} */ + +/** + * Allwinner A10 DRAMC object instance state. + */ +struct AwA10DramControllerState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + /** Maps I/O registers in physical memory */ + MemoryRegion iomem; + + /** Array of hardware registers */ + uint32_t regs[AW_A10_DRAMC_REGS_NUM]; +}; + +#endif /* HW_MISC_ALLWINNER_A10_DRAMC_H */ diff --git a/hw/arm/allwinner-a10.c b/hw/arm/allwinner-a10.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-a10.c +++ b/hw/arm/allwinner-a10.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/usb/hcd-ohci.h" +#define AW_A10_DRAMC_BASE 0x01c01000 #define AW_A10_MMC0_BASE 0x01c0f000 #define AW_A10_CCM_BASE 0x01c20000 #define AW_A10_PIC_REG_BASE 0x01c20400 @@ -XXX,XX +XXX,XX @@ static void aw_a10_init(Object *obj) object_initialize_child(obj, "ccm", &s->ccm, TYPE_AW_A10_CCM); + object_initialize_child(obj, "dramc", &s->dramc, TYPE_AW_A10_DRAMC); + object_initialize_child(obj, "emac", &s->emac, TYPE_AW_EMAC); object_initialize_child(obj, "sata", &s->sata, TYPE_ALLWINNER_AHCI); @@ -XXX,XX +XXX,XX @@ static void aw_a10_realize(DeviceState *dev, Error **errp) sysbus_realize(SYS_BUS_DEVICE(&s->ccm), &error_fatal); sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccm), 0, AW_A10_CCM_BASE); + /* DRAM Control Module */ + sysbus_realize(SYS_BUS_DEVICE(&s->dramc), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->dramc), 0, AW_A10_DRAMC_BASE); + /* FIXME use qdev NIC properties instead of nd_table[] */ if (nd_table[0].used) { qemu_check_nic_model(&nd_table[0], TYPE_AW_EMAC); diff --git a/hw/misc/allwinner-a10-dramc.c b/hw/misc/allwinner-a10-dramc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/allwinner-a10-dramc.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner A10 DRAM Controller emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from Allwinner H3 DRAMC, + * by Niek Linnenbank. + * + * This program is free software: you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation, either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program. If not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/units.h" +#include "hw/sysbus.h" +#include "migration/vmstate.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "hw/misc/allwinner-a10-dramc.h" + +/* DRAMC register offsets */ +enum { + REG_SDR_CCR = 0x0000, + REG_SDR_ZQCR0 = 0x00a8, + REG_SDR_ZQSR = 0x00b0 +}; + +#define REG_INDEX(offset) (offset / sizeof(uint32_t)) + +/* DRAMC register flags */ +enum { + REG_SDR_CCR_DATA_TRAINING = (1 << 30), + REG_SDR_CCR_DRAM_INIT = (1 << 31), +}; +enum { + REG_SDR_ZQSR_ZCAL = (1 << 31), +}; + +/* DRAMC register reset values */ +enum { + REG_SDR_CCR_RESET = 0x80020000, + REG_SDR_ZQCR0_RESET = 0x07b00000, + REG_SDR_ZQSR_RESET = 0x80000000 +}; + +static uint64_t allwinner_a10_dramc_read(void *opaque, hwaddr offset, + unsigned size) +{ + const AwA10DramControllerState *s = AW_A10_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case REG_SDR_CCR: + case REG_SDR_ZQCR0: + case REG_SDR_ZQSR: + break; + case 0x2e4 ... AW_A10_DRAMC_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + default: + qemu_log_mask(LOG_UNIMP, "%s: unimplemented read offset 0x%04x\n", + __func__, (uint32_t)offset); + return 0; + } + + return s->regs[idx]; +} + +static void allwinner_a10_dramc_write(void *opaque, hwaddr offset, + uint64_t val, unsigned size) +{ + AwA10DramControllerState *s = AW_A10_DRAMC(opaque); + const uint32_t idx = REG_INDEX(offset); + + switch (offset) { + case REG_SDR_CCR: + if (val & REG_SDR_CCR_DRAM_INIT) { + /* Clear DRAM_INIT to indicate process is done. */ + val &= ~REG_SDR_CCR_DRAM_INIT; + } + if (val & REG_SDR_CCR_DATA_TRAINING) { + /* Clear DATA_TRAINING to indicate process is done. */ + val &= ~REG_SDR_CCR_DATA_TRAINING; + } + break; + case REG_SDR_ZQCR0: + /* Set ZCAL in ZQSR to indicate calibration is done. */ + s->regs[REG_INDEX(REG_SDR_ZQSR)] |= REG_SDR_ZQSR_ZCAL; + break; + case 0x2e4 ... AW_A10_DRAMC_IOSIZE: + qemu_log_mask(LOG_GUEST_ERROR, "%s: out-of-bounds offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + default: + qemu_log_mask(LOG_UNIMP, "%s: unimplemented write offset 0x%04x\n", + __func__, (uint32_t)offset); + break; + } + + s->regs[idx] = (uint32_t) val; +} + +static const MemoryRegionOps allwinner_a10_dramc_ops = { + .read = allwinner_a10_dramc_read, + .write = allwinner_a10_dramc_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, + .impl.min_access_size = 4, +}; + +static void allwinner_a10_dramc_reset_enter(Object *obj, ResetType type) +{ + AwA10DramControllerState *s = AW_A10_DRAMC(obj); + + /* Set default values for registers */ + s->regs[REG_INDEX(REG_SDR_CCR)] = REG_SDR_CCR_RESET; + s->regs[REG_INDEX(REG_SDR_ZQCR0)] = REG_SDR_ZQCR0_RESET; + s->regs[REG_INDEX(REG_SDR_ZQSR)] = REG_SDR_ZQSR_RESET; +} + +static void allwinner_a10_dramc_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + AwA10DramControllerState *s = AW_A10_DRAMC(obj); + + /* Memory mapping */ + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_a10_dramc_ops, s, + TYPE_AW_A10_DRAMC, AW_A10_DRAMC_IOSIZE); + sysbus_init_mmio(sbd, &s->iomem); +} + +static const VMStateDescription allwinner_a10_dramc_vmstate = { + .name = "allwinner-a10-dramc", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, AwA10DramControllerState, + AW_A10_DRAMC_REGS_NUM), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_a10_dramc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.enter = allwinner_a10_dramc_reset_enter; + dc->vmsd = &allwinner_a10_dramc_vmstate; +} + +static const TypeInfo allwinner_a10_dramc_info = { + .name = TYPE_AW_A10_DRAMC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = allwinner_a10_dramc_init, + .instance_size = sizeof(AwA10DramControllerState), + .class_init = allwinner_a10_dramc_class_init, +}; + +static void allwinner_a10_dramc_register(void) +{ + type_register_static(&allwinner_a10_dramc_info); +} + +type_init(allwinner_a10_dramc_register) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10 select ALLWINNER_A10_PIT select ALLWINNER_A10_PIC select ALLWINNER_A10_CCM + select ALLWINNER_A10_DRAMC select ALLWINNER_EMAC select SERIAL select UNIMP diff --git a/hw/misc/Kconfig b/hw/misc/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Kconfig +++ b/hw/misc/Kconfig @@ -XXX,XX +XXX,XX @@ config LASI config ALLWINNER_A10_CCM bool +config ALLWINNER_A10_DRAMC + bool + source macio/Kconfig diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ subdir('macio') softmmu_ss.add(when: 'CONFIG_IVSHMEM_DEVICE', if_true: files('ivshmem.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_A10_CCM', if_true: files('allwinner-a10-ccm.c')) +softmmu_ss.add(when: 'CONFIG_ALLWINNER_A10_DRAMC', if_true: files('allwinner-a10-dramc.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-ccu.c')) specific_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-cpucfg.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-dramc.c')) -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> This patch implements Allwinner TWI/I2C controller emulation. Only master-mode functionality is implemented. The SPL boot for Cubieboard expects AXP209 PMIC on TWI0/I2C0 bus, so this is first part enabling the TWI/I2C bus operation. Since both Allwinner A10 and H3 use the same module, it is added for both boards. Docs are also updated for Cubieboard and Orangepi-PC board to indicate I2C availability. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-4-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/cubieboard.rst | 1 + docs/system/arm/orangepi.rst | 1 + include/hw/arm/allwinner-a10.h | 2 + include/hw/arm/allwinner-h3.h | 3 + include/hw/i2c/allwinner-i2c.h | 55 ++++ hw/arm/allwinner-a10.c | 8 + hw/arm/allwinner-h3.c | 11 +- hw/i2c/allwinner-i2c.c | 459 +++++++++++++++++++++++++++++++++ hw/arm/Kconfig | 2 + hw/i2c/Kconfig | 4 + hw/i2c/meson.build | 1 + hw/i2c/trace-events | 5 + 12 files changed, 551 insertions(+), 1 deletion(-) create mode 100644 include/hw/i2c/allwinner-i2c.h create mode 100644 hw/i2c/allwinner-i2c.c diff --git a/docs/system/arm/cubieboard.rst b/docs/system/arm/cubieboard.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/cubieboard.rst +++ b/docs/system/arm/cubieboard.rst @@ -XXX,XX +XXX,XX @@ Emulated devices: - SDHCI - USB controller - SATA controller +- TWI (I2C) controller diff --git a/docs/system/arm/orangepi.rst b/docs/system/arm/orangepi.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/orangepi.rst +++ b/docs/system/arm/orangepi.rst @@ -XXX,XX +XXX,XX @@ The Orange Pi PC machine supports the following devices: * Clock Control Unit * System Control module * Security Identifier device + * TWI (I2C) Limitations """"""""""" diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -XXX,XX +XXX,XX @@ #include "hw/rtc/allwinner-rtc.h" #include "hw/misc/allwinner-a10-ccm.h" #include "hw/misc/allwinner-a10-dramc.h" +#include "hw/i2c/allwinner-i2c.h" #include "target/arm/cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct AwA10State { AwEmacState emac; AllwinnerAHCIState sata; AwSdHostState mmc0; + AWI2CState i2c0; AwRtcState rtc; MemoryRegion sram_a; EHCISysBusState ehci[AW_A10_NUM_USB]; diff --git a/include/hw/arm/allwinner-h3.h b/include/hw/arm/allwinner-h3.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-h3.h +++ b/include/hw/arm/allwinner-h3.h @@ -XXX,XX +XXX,XX @@ #include "hw/sd/allwinner-sdhost.h" #include "hw/net/allwinner-sun8i-emac.h" #include "hw/rtc/allwinner-rtc.h" +#include "hw/i2c/allwinner-i2c.h" #include "target/arm/cpu.h" #include "sysemu/block-backend.h" @@ -XXX,XX +XXX,XX @@ enum { AW_H3_DEV_UART2, AW_H3_DEV_UART3, AW_H3_DEV_EMAC, + AW_H3_DEV_TWI0, AW_H3_DEV_DRAMCOM, AW_H3_DEV_DRAMCTL, AW_H3_DEV_DRAMPHY, @@ -XXX,XX +XXX,XX @@ struct AwH3State { AwH3SysCtrlState sysctrl; AwSidState sid; AwSdHostState mmc0; + AWI2CState i2c0; AwSun8iEmacState emac; AwRtcState rtc; GICState gic; diff --git a/include/hw/i2c/allwinner-i2c.h b/include/hw/i2c/allwinner-i2c.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/i2c/allwinner-i2c.h @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner I2C Bus Serial Interface registers definition + * + * Copyright (C) 2022 Strahinja Jankovic. <strahinja.p.jankovic@gmail.com> + * + * This file is derived from IMX I2C controller, + * by Jean-Christophe DUBOIS . + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + * + */ + +#ifndef ALLWINNER_I2C_H +#define ALLWINNER_I2C_H + +#include "hw/sysbus.h" +#include "qom/object.h" + +#define TYPE_AW_I2C "allwinner.i2c" +OBJECT_DECLARE_SIMPLE_TYPE(AWI2CState, AW_I2C) + +#define AW_I2C_MEM_SIZE 0x24 + +struct AWI2CState { + /*< private >*/ + SysBusDevice parent_obj; + + /*< public >*/ + MemoryRegion iomem; + I2CBus *bus; + qemu_irq irq; + + uint8_t addr; + uint8_t xaddr; + uint8_t data; + uint8_t cntr; + uint8_t stat; + uint8_t ccr; + uint8_t srst; + uint8_t efr; + uint8_t lcr; +}; + +#endif /* ALLWINNER_I2C_H */ diff --git a/hw/arm/allwinner-a10.c b/hw/arm/allwinner-a10.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-a10.c +++ b/hw/arm/allwinner-a10.c @@ -XXX,XX +XXX,XX @@ #define AW_A10_OHCI_BASE 0x01c14400 #define AW_A10_SATA_BASE 0x01c18000 #define AW_A10_RTC_BASE 0x01c20d00 +#define AW_A10_I2C0_BASE 0x01c2ac00 static void aw_a10_init(Object *obj) { @@ -XXX,XX +XXX,XX @@ static void aw_a10_init(Object *obj) object_initialize_child(obj, "sata", &s->sata, TYPE_ALLWINNER_AHCI); + object_initialize_child(obj, "i2c0", &s->i2c0, TYPE_AW_I2C); + if (machine_usb(current_machine)) { int i; @@ -XXX,XX +XXX,XX @@ static void aw_a10_realize(DeviceState *dev, Error **errp) /* RTC */ sysbus_realize(SYS_BUS_DEVICE(&s->rtc), &error_fatal); sysbus_mmio_map_overlap(SYS_BUS_DEVICE(&s->rtc), 0, AW_A10_RTC_BASE, 10); + + /* I2C */ + sysbus_realize(SYS_BUS_DEVICE(&s->i2c0), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c0), 0, AW_A10_I2C0_BASE); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c0), 0, qdev_get_gpio_in(dev, 7)); } static void aw_a10_class_init(ObjectClass *oc, void *data) diff --git a/hw/arm/allwinner-h3.c b/hw/arm/allwinner-h3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-h3.c +++ b/hw/arm/allwinner-h3.c @@ -XXX,XX +XXX,XX @@ const hwaddr allwinner_h3_memmap[] = { [AW_H3_DEV_UART1] = 0x01c28400, [AW_H3_DEV_UART2] = 0x01c28800, [AW_H3_DEV_UART3] = 0x01c28c00, + [AW_H3_DEV_TWI0] = 0x01c2ac00, [AW_H3_DEV_EMAC] = 0x01c30000, [AW_H3_DEV_DRAMCOM] = 0x01c62000, [AW_H3_DEV_DRAMCTL] = 0x01c63000, @@ -XXX,XX +XXX,XX @@ struct AwH3Unimplemented { { "uart1", 0x01c28400, 1 * KiB }, { "uart2", 0x01c28800, 1 * KiB }, { "uart3", 0x01c28c00, 1 * KiB }, - { "twi0", 0x01c2ac00, 1 * KiB }, { "twi1", 0x01c2b000, 1 * KiB }, { "twi2", 0x01c2b400, 1 * KiB }, { "scr", 0x01c2c400, 1 * KiB }, @@ -XXX,XX +XXX,XX @@ enum { AW_H3_GIC_SPI_UART1 = 1, AW_H3_GIC_SPI_UART2 = 2, AW_H3_GIC_SPI_UART3 = 3, + AW_H3_GIC_SPI_TWI0 = 6, AW_H3_GIC_SPI_TIMER0 = 18, AW_H3_GIC_SPI_TIMER1 = 19, AW_H3_GIC_SPI_MMC0 = 60, @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_init(Object *obj) "ram-size"); object_initialize_child(obj, "rtc", &s->rtc, TYPE_AW_RTC_SUN6I); + + object_initialize_child(obj, "twi0", &s->i2c0, TYPE_AW_I2C); } static void allwinner_h3_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void allwinner_h3_realize(DeviceState *dev, Error **errp) sysbus_realize(SYS_BUS_DEVICE(&s->rtc), &error_fatal); sysbus_mmio_map(SYS_BUS_DEVICE(&s->rtc), 0, s->memmap[AW_H3_DEV_RTC]); + /* I2C */ + sysbus_realize(SYS_BUS_DEVICE(&s->i2c0), &error_fatal); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c0), 0, s->memmap[AW_H3_DEV_TWI0]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c0), 0, + qdev_get_gpio_in(DEVICE(&s->gic), AW_H3_GIC_SPI_TWI0)); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(unimplemented); i++) { create_unimplemented_device(unimplemented[i].device_name, diff --git a/hw/i2c/allwinner-i2c.c b/hw/i2c/allwinner-i2c.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/i2c/allwinner-i2c.c @@ -XXX,XX +XXX,XX @@ +/* + * Allwinner I2C Bus Serial Interface Emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * This file is derived from IMX I2C controller, + * by Jean-Christophe DUBOIS . + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + * + * SPDX-License-Identifier: MIT + */ + +#include "qemu/osdep.h" +#include "hw/i2c/allwinner-i2c.h" +#include "hw/irq.h" +#include "migration/vmstate.h" +#include "hw/i2c/i2c.h" +#include "qemu/log.h" +#include "trace.h" +#include "qemu/module.h" + +/* Allwinner I2C memory map */ +#define TWI_ADDR_REG 0x00 /* slave address register */ +#define TWI_XADDR_REG 0x04 /* extended slave address register */ +#define TWI_DATA_REG 0x08 /* data register */ +#define TWI_CNTR_REG 0x0c /* control register */ +#define TWI_STAT_REG 0x10 /* status register */ +#define TWI_CCR_REG 0x14 /* clock control register */ +#define TWI_SRST_REG 0x18 /* software reset register */ +#define TWI_EFR_REG 0x1c /* enhance feature register */ +#define TWI_LCR_REG 0x20 /* line control register */ + +/* Used only in slave mode, do not set */ +#define TWI_ADDR_RESET 0 +#define TWI_XADDR_RESET 0 + +/* Data register */ +#define TWI_DATA_MASK 0xFF +#define TWI_DATA_RESET 0 + +/* Control register */ +#define TWI_CNTR_INT_EN (1 << 7) +#define TWI_CNTR_BUS_EN (1 << 6) +#define TWI_CNTR_M_STA (1 << 5) +#define TWI_CNTR_M_STP (1 << 4) +#define TWI_CNTR_INT_FLAG (1 << 3) +#define TWI_CNTR_A_ACK (1 << 2) +#define TWI_CNTR_MASK 0xFC +#define TWI_CNTR_RESET 0 + +/* Status register */ +#define TWI_STAT_MASK 0xF8 +#define TWI_STAT_RESET 0xF8 + +/* Clock register */ +#define TWI_CCR_CLK_M_MASK 0x78 +#define TWI_CCR_CLK_N_MASK 0x07 +#define TWI_CCR_MASK 0x7F +#define TWI_CCR_RESET 0 + +/* Soft reset */ +#define TWI_SRST_MASK 0x01 +#define TWI_SRST_RESET 0 + +/* Enhance feature */ +#define TWI_EFR_MASK 0x03 +#define TWI_EFR_RESET 0 + +/* Line control */ +#define TWI_LCR_SCL_STATE (1 << 5) +#define TWI_LCR_SDA_STATE (1 << 4) +#define TWI_LCR_SCL_CTL (1 << 3) +#define TWI_LCR_SCL_CTL_EN (1 << 2) +#define TWI_LCR_SDA_CTL (1 << 1) +#define TWI_LCR_SDA_CTL_EN (1 << 0) +#define TWI_LCR_MASK 0x3F +#define TWI_LCR_RESET 0x3A + +/* Status value in STAT register is shifted by 3 bits */ +#define TWI_STAT_SHIFT 3 +#define STAT_FROM_STA(x) ((x) << TWI_STAT_SHIFT) +#define STAT_TO_STA(x) ((x) >> TWI_STAT_SHIFT) + +enum { + STAT_BUS_ERROR = 0, + /* Master mode */ + STAT_M_STA_TX, + STAT_M_RSTA_TX, + STAT_M_ADDR_WR_ACK, + STAT_M_ADDR_WR_NACK, + STAT_M_DATA_TX_ACK, + STAT_M_DATA_TX_NACK, + STAT_M_ARB_LOST, + STAT_M_ADDR_RD_ACK, + STAT_M_ADDR_RD_NACK, + STAT_M_DATA_RX_ACK, + STAT_M_DATA_RX_NACK, + /* Slave mode */ + STAT_S_ADDR_WR_ACK, + STAT_S_ARB_LOST_AW_ACK, + STAT_S_GCA_ACK, + STAT_S_ARB_LOST_GCA_ACK, + STAT_S_DATA_RX_SA_ACK, + STAT_S_DATA_RX_SA_NACK, + STAT_S_DATA_RX_GCA_ACK, + STAT_S_DATA_RX_GCA_NACK, + STAT_S_STP_RSTA, + STAT_S_ADDR_RD_ACK, + STAT_S_ARB_LOST_AR_ACK, + STAT_S_DATA_TX_ACK, + STAT_S_DATA_TX_NACK, + STAT_S_LB_TX_ACK, + /* Master mode, 10-bit */ + STAT_M_2ND_ADDR_WR_ACK, + STAT_M_2ND_ADDR_WR_NACK, + /* Idle */ + STAT_IDLE = 0x1f +} TWI_STAT_STA; + +static const char *allwinner_i2c_get_regname(unsigned offset) +{ + switch (offset) { + case TWI_ADDR_REG: + return "ADDR"; + case TWI_XADDR_REG: + return "XADDR"; + case TWI_DATA_REG: + return "DATA"; + case TWI_CNTR_REG: + return "CNTR"; + case TWI_STAT_REG: + return "STAT"; + case TWI_CCR_REG: + return "CCR"; + case TWI_SRST_REG: + return "SRST"; + case TWI_EFR_REG: + return "EFR"; + case TWI_LCR_REG: + return "LCR"; + default: + return "[?]"; + } +} + +static inline bool allwinner_i2c_is_reset(AWI2CState *s) +{ + return s->srst & TWI_SRST_MASK; +} + +static inline bool allwinner_i2c_bus_is_enabled(AWI2CState *s) +{ + return s->cntr & TWI_CNTR_BUS_EN; +} + +static inline bool allwinner_i2c_interrupt_is_enabled(AWI2CState *s) +{ + return s->cntr & TWI_CNTR_INT_EN; +} + +static void allwinner_i2c_reset_hold(Object *obj) +{ + AWI2CState *s = AW_I2C(obj); + + if (STAT_TO_STA(s->stat) != STAT_IDLE) { + i2c_end_transfer(s->bus); + } + + s->addr = TWI_ADDR_RESET; + s->xaddr = TWI_XADDR_RESET; + s->data = TWI_DATA_RESET; + s->cntr = TWI_CNTR_RESET; + s->stat = TWI_STAT_RESET; + s->ccr = TWI_CCR_RESET; + s->srst = TWI_SRST_RESET; + s->efr = TWI_EFR_RESET; + s->lcr = TWI_LCR_RESET; +} + +static inline void allwinner_i2c_raise_interrupt(AWI2CState *s) +{ + /* + * Raise an interrupt if the device is not reset and it is configured + * to generate some interrupts. + */ + if (!allwinner_i2c_is_reset(s) && allwinner_i2c_bus_is_enabled(s)) { + if (STAT_TO_STA(s->stat) != STAT_IDLE) { + s->cntr |= TWI_CNTR_INT_FLAG; + if (allwinner_i2c_interrupt_is_enabled(s)) { + qemu_irq_raise(s->irq); + } + } + } +} + +static uint64_t allwinner_i2c_read(void *opaque, hwaddr offset, + unsigned size) +{ + uint16_t value; + AWI2CState *s = AW_I2C(opaque); + + switch (offset) { + case TWI_ADDR_REG: + value = s->addr; + break; + case TWI_XADDR_REG: + value = s->xaddr; + break; + case TWI_DATA_REG: + if ((STAT_TO_STA(s->stat) == STAT_M_ADDR_RD_ACK) || + (STAT_TO_STA(s->stat) == STAT_M_DATA_RX_ACK) || + (STAT_TO_STA(s->stat) == STAT_M_DATA_RX_NACK)) { + /* Get the next byte */ + s->data = i2c_recv(s->bus); + + if (s->cntr & TWI_CNTR_A_ACK) { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_ACK); + } else { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_NACK); + } + allwinner_i2c_raise_interrupt(s); + } + value = s->data; + break; + case TWI_CNTR_REG: + value = s->cntr; + break; + case TWI_STAT_REG: + value = s->stat; + /* + * If polling when reading then change state to indicate data + * is available + */ + if (STAT_TO_STA(s->stat) == STAT_M_ADDR_RD_ACK) { + if (s->cntr & TWI_CNTR_A_ACK) { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_ACK); + } else { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_NACK); + } + allwinner_i2c_raise_interrupt(s); + } + break; + case TWI_CCR_REG: + value = s->ccr; + break; + case TWI_SRST_REG: + value = s->srst; + break; + case TWI_EFR_REG: + value = s->efr; + break; + case TWI_LCR_REG: + value = s->lcr; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Bad address at offset 0x%" + HWADDR_PRIx "\n", TYPE_AW_I2C, __func__, offset); + value = 0; + break; + } + + trace_allwinner_i2c_read(allwinner_i2c_get_regname(offset), offset, value); + + return (uint64_t)value; +} + +static void allwinner_i2c_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + AWI2CState *s = AW_I2C(opaque); + + value &= 0xff; + + trace_allwinner_i2c_write(allwinner_i2c_get_regname(offset), offset, value); + + switch (offset) { + case TWI_ADDR_REG: + s->addr = (uint8_t)value; + break; + case TWI_XADDR_REG: + s->xaddr = (uint8_t)value; + break; + case TWI_DATA_REG: + /* If the device is in reset or not enabled, nothing to do */ + if (allwinner_i2c_is_reset(s) || (!allwinner_i2c_bus_is_enabled(s))) { + break; + } + + s->data = value & TWI_DATA_MASK; + + switch (STAT_TO_STA(s->stat)) { + case STAT_M_STA_TX: + case STAT_M_RSTA_TX: + /* Send address */ + if (i2c_start_transfer(s->bus, extract32(s->data, 1, 7), + extract32(s->data, 0, 1))) { + /* If non zero is returned, the address is not valid */ + s->stat = STAT_FROM_STA(STAT_M_ADDR_WR_NACK); + } else { + /* Determine if read of write */ + if (extract32(s->data, 0, 1)) { + s->stat = STAT_FROM_STA(STAT_M_ADDR_RD_ACK); + } else { + s->stat = STAT_FROM_STA(STAT_M_ADDR_WR_ACK); + } + allwinner_i2c_raise_interrupt(s); + } + break; + case STAT_M_ADDR_WR_ACK: + case STAT_M_DATA_TX_ACK: + if (i2c_send(s->bus, s->data)) { + /* If the target return non zero then end the transfer */ + s->stat = STAT_FROM_STA(STAT_M_DATA_TX_NACK); + i2c_end_transfer(s->bus); + } else { + s->stat = STAT_FROM_STA(STAT_M_DATA_TX_ACK); + allwinner_i2c_raise_interrupt(s); + } + break; + default: + break; + } + break; + case TWI_CNTR_REG: + if (!allwinner_i2c_is_reset(s)) { + /* Do something only if not in software reset */ + s->cntr = value & TWI_CNTR_MASK; + + /* Check if start condition should be sent */ + if (s->cntr & TWI_CNTR_M_STA) { + /* Update status */ + if (STAT_TO_STA(s->stat) == STAT_IDLE) { + /* Send start condition */ + s->stat = STAT_FROM_STA(STAT_M_STA_TX); + } else { + /* Send repeated start condition */ + s->stat = STAT_FROM_STA(STAT_M_RSTA_TX); + } + /* Clear start condition */ + s->cntr &= ~TWI_CNTR_M_STA; + } + if (s->cntr & TWI_CNTR_M_STP) { + /* Update status */ + i2c_end_transfer(s->bus); + s->stat = STAT_FROM_STA(STAT_IDLE); + s->cntr &= ~TWI_CNTR_M_STP; + } + if ((s->cntr & TWI_CNTR_INT_FLAG) == 0) { + /* Interrupt flag cleared */ + qemu_irq_lower(s->irq); + } + if ((s->cntr & TWI_CNTR_A_ACK) == 0) { + if (STAT_TO_STA(s->stat) == STAT_M_DATA_RX_ACK) { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_NACK); + } + } else { + if (STAT_TO_STA(s->stat) == STAT_M_DATA_RX_NACK) { + s->stat = STAT_FROM_STA(STAT_M_DATA_RX_ACK); + } + } + allwinner_i2c_raise_interrupt(s); + + } + break; + case TWI_CCR_REG: + s->ccr = value & TWI_CCR_MASK; + break; + case TWI_SRST_REG: + if (((value & TWI_SRST_MASK) == 0) && (s->srst & TWI_SRST_MASK)) { + /* Perform reset */ + allwinner_i2c_reset_hold(OBJECT(s)); + } + s->srst = value & TWI_SRST_MASK; + break; + case TWI_EFR_REG: + s->efr = value & TWI_EFR_MASK; + break; + case TWI_LCR_REG: + s->lcr = value & TWI_LCR_MASK; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Bad address at offset 0x%" + HWADDR_PRIx "\n", TYPE_AW_I2C, __func__, offset); + break; + } +} + +static const MemoryRegionOps allwinner_i2c_ops = { + .read = allwinner_i2c_read, + .write = allwinner_i2c_write, + .valid.min_access_size = 1, + .valid.max_access_size = 4, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static const VMStateDescription allwinner_i2c_vmstate = { + .name = TYPE_AW_I2C, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT8(addr, AWI2CState), + VMSTATE_UINT8(xaddr, AWI2CState), + VMSTATE_UINT8(data, AWI2CState), + VMSTATE_UINT8(cntr, AWI2CState), + VMSTATE_UINT8(ccr, AWI2CState), + VMSTATE_UINT8(srst, AWI2CState), + VMSTATE_UINT8(efr, AWI2CState), + VMSTATE_UINT8(lcr, AWI2CState), + VMSTATE_END_OF_LIST() + } +}; + +static void allwinner_i2c_realize(DeviceState *dev, Error **errp) +{ + AWI2CState *s = AW_I2C(dev); + + memory_region_init_io(&s->iomem, OBJECT(s), &allwinner_i2c_ops, s, + TYPE_AW_I2C, AW_I2C_MEM_SIZE); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); + sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->irq); + s->bus = i2c_init_bus(dev, "i2c"); +} + +static void allwinner_i2c_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.hold = allwinner_i2c_reset_hold; + dc->vmsd = &allwinner_i2c_vmstate; + dc->realize = allwinner_i2c_realize; + dc->desc = "Allwinner I2C Controller"; +} + +static const TypeInfo allwinner_i2c_type_info = { + .name = TYPE_AW_I2C, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(AWI2CState), + .class_init = allwinner_i2c_class_init, +}; + +static void allwinner_i2c_register_types(void) +{ + type_register_static(&allwinner_i2c_type_info); +} + +type_init(allwinner_i2c_register_types) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10 select ALLWINNER_A10_CCM select ALLWINNER_A10_DRAMC select ALLWINNER_EMAC + select ALLWINNER_I2C select SERIAL select UNIMP @@ -XXX,XX +XXX,XX @@ config ALLWINNER_H3 bool select ALLWINNER_A10_PIT select ALLWINNER_SUN8I_EMAC + select ALLWINNER_I2C select SERIAL select ARM_TIMER select ARM_GIC diff --git a/hw/i2c/Kconfig b/hw/i2c/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/Kconfig +++ b/hw/i2c/Kconfig @@ -XXX,XX +XXX,XX @@ config MPC_I2C bool select I2C +config ALLWINNER_I2C + bool + select I2C + config PCA954X bool select I2C diff --git a/hw/i2c/meson.build b/hw/i2c/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/meson.build +++ b/hw/i2c/meson.build @@ -XXX,XX +XXX,XX @@ i2c_ss.add(when: 'CONFIG_BITBANG_I2C', if_true: files('bitbang_i2c.c')) i2c_ss.add(when: 'CONFIG_EXYNOS4', if_true: files('exynos4210_i2c.c')) i2c_ss.add(when: 'CONFIG_IMX_I2C', if_true: files('imx_i2c.c')) i2c_ss.add(when: 'CONFIG_MPC_I2C', if_true: files('mpc_i2c.c')) +i2c_ss.add(when: 'CONFIG_ALLWINNER_I2C', if_true: files('allwinner-i2c.c')) i2c_ss.add(when: 'CONFIG_NRF51_SOC', if_true: files('microbit_i2c.c')) i2c_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_smbus.c')) i2c_ss.add(when: 'CONFIG_SMBUS_EEPROM', if_true: files('smbus_eeprom.c')) diff --git a/hw/i2c/trace-events b/hw/i2c/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/trace-events +++ b/hw/i2c/trace-events @@ -XXX,XX +XXX,XX @@ i2c_send_async(uint8_t address, uint8_t data) "send_async(addr:0x%02x) data:0x%0 i2c_recv(uint8_t address, uint8_t data) "recv(addr:0x%02x) data:0x%02x" i2c_ack(void) "" +# allwinner_i2c.c + +allwinner_i2c_read(const char* reg_name, uint64_t offset, uint64_t value) "read %s [0x%" PRIx64 "]: -> 0x%" PRIx64 +allwinner_i2c_write(const char* reg_name, uint64_t offset, uint64_t value) "write %s [0x%" PRIx64 "]: <- 0x%" PRIx64 + # aspeed_i2c.c aspeed_i2c_bus_cmd(uint32_t cmd, const char *cmd_flags, uint32_t count, uint32_t intr_status) "handling cmd=0x%x %s count=%d intr=0x%x" -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> This patch adds minimal support for AXP-209 PMU. Most important is chip ID since U-Boot SPL expects version 0x1. Besides the chip ID register, reset values for two more registers used by A10 U-Boot SPL are covered. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Message-id: 20221226220303.14420-5-strahinja.p.jankovic@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/axp209.c | 238 +++++++++++++++++++++++++++++++++++++++++++ MAINTAINERS | 2 + hw/misc/Kconfig | 4 + hw/misc/meson.build | 1 + hw/misc/trace-events | 5 + 5 files changed, 250 insertions(+) create mode 100644 hw/misc/axp209.c diff --git a/hw/misc/axp209.c b/hw/misc/axp209.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/axp209.c @@ -XXX,XX +XXX,XX @@ +/* + * AXP-209 PMU Emulation + * + * Copyright (C) 2022 Strahinja Jankovic <strahinja.p.jankovic@gmail.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE + * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER + * DEALINGS IN THE SOFTWARE. + * + * SPDX-License-Identifier: MIT + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "trace.h" +#include "hw/i2c/i2c.h" +#include "migration/vmstate.h" + +#define TYPE_AXP209_PMU "axp209_pmu" + +#define AXP209(obj) \ + OBJECT_CHECK(AXP209I2CState, (obj), TYPE_AXP209_PMU) + +/* registers */ +enum { + REG_POWER_STATUS = 0x0u, + REG_OPERATING_MODE, + REG_OTG_VBUS_STATUS, + REG_CHIP_VERSION, + REG_DATA_CACHE_0, + REG_DATA_CACHE_1, + REG_DATA_CACHE_2, + REG_DATA_CACHE_3, + REG_DATA_CACHE_4, + REG_DATA_CACHE_5, + REG_DATA_CACHE_6, + REG_DATA_CACHE_7, + REG_DATA_CACHE_8, + REG_DATA_CACHE_9, + REG_DATA_CACHE_A, + REG_DATA_CACHE_B, + REG_POWER_OUTPUT_CTRL = 0x12u, + REG_DC_DC2_OUT_V_CTRL = 0x23u, + REG_DC_DC2_DVS_CTRL = 0x25u, + REG_DC_DC3_OUT_V_CTRL = 0x27u, + REG_LDO2_4_OUT_V_CTRL, + REG_LDO3_OUT_V_CTRL, + REG_VBUS_CH_MGMT = 0x30u, + REG_SHUTDOWN_V_CTRL, + REG_SHUTDOWN_CTRL, + REG_CHARGE_CTRL_1, + REG_CHARGE_CTRL_2, + REG_SPARE_CHARGE_CTRL, + REG_PEK_KEY_CTRL, + REG_DC_DC_FREQ_SET, + REG_CHR_TEMP_TH_SET, + REG_CHR_HIGH_TEMP_TH_CTRL, + REG_IPSOUT_WARN_L1, + REG_IPSOUT_WARN_L2, + REG_DISCHR_TEMP_TH_SET, + REG_DISCHR_HIGH_TEMP_TH_CTRL, + REG_IRQ_BANK_1_CTRL = 0x40u, + REG_IRQ_BANK_2_CTRL, + REG_IRQ_BANK_3_CTRL, + REG_IRQ_BANK_4_CTRL, + REG_IRQ_BANK_5_CTRL, + REG_IRQ_BANK_1_STAT = 0x48u, + REG_IRQ_BANK_2_STAT, + REG_IRQ_BANK_3_STAT, + REG_IRQ_BANK_4_STAT, + REG_IRQ_BANK_5_STAT, + REG_ADC_ACIN_V_H = 0x56u, + REG_ADC_ACIN_V_L, + REG_ADC_ACIN_CURR_H, + REG_ADC_ACIN_CURR_L, + REG_ADC_VBUS_V_H, + REG_ADC_VBUS_V_L, + REG_ADC_VBUS_CURR_H, + REG_ADC_VBUS_CURR_L, + REG_ADC_INT_TEMP_H, + REG_ADC_INT_TEMP_L, + REG_ADC_TEMP_SENS_V_H = 0x62u, + REG_ADC_TEMP_SENS_V_L, + REG_ADC_BAT_V_H = 0x78u, + REG_ADC_BAT_V_L, + REG_ADC_BAT_DISCHR_CURR_H, + REG_ADC_BAT_DISCHR_CURR_L, + REG_ADC_BAT_CHR_CURR_H, + REG_ADC_BAT_CHR_CURR_L, + REG_ADC_IPSOUT_V_H, + REG_ADC_IPSOUT_V_L, + REG_DC_DC_MOD_SEL = 0x80u, + REG_ADC_EN_1, + REG_ADC_EN_2, + REG_ADC_SR_CTRL, + REG_ADC_IN_RANGE, + REG_GPIO1_ADC_IRQ_RISING_TH, + REG_GPIO1_ADC_IRQ_FALLING_TH, + REG_TIMER_CTRL = 0x8au, + REG_VBUS_CTRL_MON_SRP, + REG_OVER_TEMP_SHUTDOWN = 0x8fu, + REG_GPIO0_FEAT_SET, + REG_GPIO_OUT_HIGH_SET, + REG_GPIO1_FEAT_SET, + REG_GPIO2_FEAT_SET, + REG_GPIO_SIG_STATE_SET_MON, + REG_GPIO3_SET, + REG_COULOMB_CNTR_CTRL = 0xb8u, + REG_POWER_MEAS_RES, + NR_REGS +}; + +#define AXP209_CHIP_VERSION_ID (0x01) +#define AXP209_DC_DC2_OUT_V_CTRL_RESET (0x16) +#define AXP209_IRQ_BANK_1_CTRL_RESET (0xd8) + +/* A simple I2C slave which returns values of ID or CNT register. */ +typedef struct AXP209I2CState { + /*< private >*/ + I2CSlave i2c; + /*< public >*/ + uint8_t regs[NR_REGS]; /* peripheral registers */ + uint8_t ptr; /* current register index */ + uint8_t count; /* counter used for tx/rx */ +} AXP209I2CState; + +/* Reset all counters and load ID register */ +static void axp209_reset_enter(Object *obj, ResetType type) +{ + AXP209I2CState *s = AXP209(obj); + + memset(s->regs, 0, NR_REGS); + s->ptr = 0; + s->count = 0; + s->regs[REG_CHIP_VERSION] = AXP209_CHIP_VERSION_ID; + s->regs[REG_DC_DC2_OUT_V_CTRL] = AXP209_DC_DC2_OUT_V_CTRL_RESET; + s->regs[REG_IRQ_BANK_1_CTRL] = AXP209_IRQ_BANK_1_CTRL_RESET; +} + +/* Handle events from master. */ +static int axp209_event(I2CSlave *i2c, enum i2c_event event) +{ + AXP209I2CState *s = AXP209(i2c); + + s->count = 0; + + return 0; +} + +/* Called when master requests read */ +static uint8_t axp209_rx(I2CSlave *i2c) +{ + AXP209I2CState *s = AXP209(i2c); + uint8_t ret = 0xff; + + if (s->ptr < NR_REGS) { + ret = s->regs[s->ptr++]; + } + + trace_axp209_rx(s->ptr - 1, ret); + + return ret; +} + +/* + * Called when master sends write. + * Update ptr with byte 0, then perform write with second byte. + */ +static int axp209_tx(I2CSlave *i2c, uint8_t data) +{ + AXP209I2CState *s = AXP209(i2c); + + if (s->count == 0) { + /* Store register address */ + s->ptr = data; + s->count++; + trace_axp209_select(data); + } else { + trace_axp209_tx(s->ptr, data); + if (s->ptr == REG_DC_DC2_OUT_V_CTRL) { + s->regs[s->ptr++] = data; + } + } + + return 0; +} + +static const VMStateDescription vmstate_axp209 = { + .name = TYPE_AXP209_PMU, + .version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT8_ARRAY(regs, AXP209I2CState, NR_REGS), + VMSTATE_UINT8(count, AXP209I2CState), + VMSTATE_UINT8(ptr, AXP209I2CState), + VMSTATE_END_OF_LIST() + } +}; + +static void axp209_class_init(ObjectClass *oc, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + I2CSlaveClass *isc = I2C_SLAVE_CLASS(oc); + ResettableClass *rc = RESETTABLE_CLASS(oc); + + rc->phases.enter = axp209_reset_enter; + dc->vmsd = &vmstate_axp209; + isc->event = axp209_event; + isc->recv = axp209_rx; + isc->send = axp209_tx; +} + +static const TypeInfo axp209_info = { + .name = TYPE_AXP209_PMU, + .parent = TYPE_I2C_SLAVE, + .instance_size = sizeof(AXP209I2CState), + .class_init = axp209_class_init +}; + +static void axp209_register_devices(void) +{ + type_register_static(&axp209_info); +} + +type_init(axp209_register_devices); diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ ARM Machines Allwinner-a10 M: Beniamino Galvani <b.galvani@gmail.com> M: Peter Maydell <peter.maydell@linaro.org> +R: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> L: qemu-arm@nongnu.org S: Odd Fixes F: hw/*/allwinner* F: include/hw/*/allwinner* F: hw/arm/cubieboard.c F: docs/system/arm/cubieboard.rst +F: hw/misc/axp209.c Allwinner-h3 M: Niek Linnenbank <nieklinnenbank@gmail.com> diff --git a/hw/misc/Kconfig b/hw/misc/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Kconfig +++ b/hw/misc/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10_CCM config ALLWINNER_A10_DRAMC bool +config AXP209_PMU + bool + depends on I2C + source macio/Kconfig diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ specific_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-cpucfg.c' softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-dramc.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-h3-sysctrl.c')) softmmu_ss.add(when: 'CONFIG_ALLWINNER_H3', if_true: files('allwinner-sid.c')) +softmmu_ss.add(when: 'CONFIG_AXP209_PMU', if_true: files('axp209.c')) softmmu_ss.add(when: 'CONFIG_REALVIEW', if_true: files('arm_sysctl.c')) softmmu_ss.add(when: 'CONFIG_NSERIES', if_true: files('cbus.c')) softmmu_ss.add(when: 'CONFIG_ECCMEMCTL', if_true: files('eccmemctl.c')) diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ allwinner_sid_write(uint64_t offset, uint64_t data, unsigned size) "offset 0x%" avr_power_read(uint8_t value) "power_reduc read value:%u" avr_power_write(uint8_t value) "power_reduc write value:%u" +# axp209.c +axp209_rx(uint8_t reg, uint8_t data) "Read reg 0x%" PRIx8 " : 0x%" PRIx8 +axp209_select(uint8_t reg) "Accessing reg 0x%" PRIx8 +axp209_tx(uint8_t reg, uint8_t data) "Write reg 0x%" PRIx8 " : 0x%" PRIx8 + # eccmemctl.c ecc_mem_writel_mer(uint32_t val) "Write memory enable 0x%08x" ecc_mem_writel_mdr(uint32_t val) "Write memory delay 0x%08x" -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> SPL Boot for Cubieboard expects AXP209 connected to I2C0 bus. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20221226220303.14420-6-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/cubieboard.c | 6 ++++++ hw/arm/Kconfig | 1 + 2 files changed, 7 insertions(+) diff --git a/hw/arm/cubieboard.c b/hw/arm/cubieboard.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/cubieboard.c +++ b/hw/arm/cubieboard.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/qdev-properties.h" #include "hw/arm/allwinner-a10.h" +#include "hw/i2c/i2c.h" static struct arm_boot_info cubieboard_binfo = { .loader_start = AW_A10_SDRAM_BASE, @@ -XXX,XX +XXX,XX @@ static void cubieboard_init(MachineState *machine) BlockBackend *blk; BusState *bus; DeviceState *carddev; + I2CBus *i2c; /* BIOS is not supported by this board */ if (machine->firmware) { @@ -XXX,XX +XXX,XX @@ static void cubieboard_init(MachineState *machine) exit(1); } + /* Connect AXP 209 */ + i2c = I2C_BUS(qdev_get_child_bus(DEVICE(&a10->i2c0), "i2c")); + i2c_slave_create_simple(i2c, "axp209_pmu", 0x34); + /* Retrieve SD bus */ di = drive_get(IF_SD, 0, 0); blk = di ? blk_by_legacy_dinfo(di) : NULL; diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10 select ALLWINNER_A10_DRAMC select ALLWINNER_EMAC select ALLWINNER_I2C + select AXP209_PMU select SERIAL select UNIMP -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> This patch enables copying of SPL from MMC if `-kernel` parameter is not passed when starting QEMU. SPL is copied to SRAM_A. The approach is reused from Allwinner H3 implementation. Tested with Armbian and custom Yocto image. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-7-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/allwinner-a10.h | 21 +++++++++++++++++++++ hw/arm/allwinner-a10.c | 18 ++++++++++++++++++ hw/arm/cubieboard.c | 5 +++++ 3 files changed, 44 insertions(+) diff --git a/include/hw/arm/allwinner-a10.h b/include/hw/arm/allwinner-a10.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/allwinner-a10.h +++ b/include/hw/arm/allwinner-a10.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/allwinner-a10-ccm.h" #include "hw/misc/allwinner-a10-dramc.h" #include "hw/i2c/allwinner-i2c.h" +#include "sysemu/block-backend.h" #include "target/arm/cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct AwA10State { OHCISysBusState ohci[AW_A10_NUM_USB]; }; +/** + * Emulate Boot ROM firmware setup functionality. + * + * A real Allwinner A10 SoC contains a Boot ROM + * which is the first code that runs right after + * the SoC is powered on. The Boot ROM is responsible + * for loading user code (e.g. a bootloader) from any + * of the supported external devices and writing the + * downloaded code to internal SRAM. After loading the SoC + * begins executing the code written to SRAM. + * + * This function emulates the Boot ROM by copying 32 KiB + * of data at offset 8 KiB from the given block device and writes it to + * the start of the first internal SRAM memory. + * + * @s: Allwinner A10 state object pointer + * @blk: Block backend device object pointer + */ +void allwinner_a10_bootrom_setup(AwA10State *s, BlockBackend *blk); + #endif diff --git a/hw/arm/allwinner-a10.c b/hw/arm/allwinner-a10.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/allwinner-a10.c +++ b/hw/arm/allwinner-a10.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "hw/boards.h" #include "hw/usb/hcd-ohci.h" +#include "hw/loader.h" +#define AW_A10_SRAM_A_BASE 0x00000000 #define AW_A10_DRAMC_BASE 0x01c01000 #define AW_A10_MMC0_BASE 0x01c0f000 #define AW_A10_CCM_BASE 0x01c20000 @@ -XXX,XX +XXX,XX @@ #define AW_A10_RTC_BASE 0x01c20d00 #define AW_A10_I2C0_BASE 0x01c2ac00 +void allwinner_a10_bootrom_setup(AwA10State *s, BlockBackend *blk) +{ + const int64_t rom_size = 32 * KiB; + g_autofree uint8_t *buffer = g_new0(uint8_t, rom_size); + + if (blk_pread(blk, 8 * KiB, rom_size, buffer, 0) < 0) { + error_setg(&error_fatal, "%s: failed to read BlockBackend data", + __func__); + return; + } + + rom_add_blob("allwinner-a10.bootrom", buffer, rom_size, + rom_size, AW_A10_SRAM_A_BASE, + NULL, NULL, NULL, NULL, false); +} + static void aw_a10_init(Object *obj) { AwA10State *s = AW_A10(obj); diff --git a/hw/arm/cubieboard.c b/hw/arm/cubieboard.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/cubieboard.c +++ b/hw/arm/cubieboard.c @@ -XXX,XX +XXX,XX @@ static void cubieboard_init(MachineState *machine) memory_region_add_subregion(get_system_memory(), AW_A10_SDRAM_BASE, machine->ram); + /* Load target kernel or start using BootROM */ + if (!machine->kernel_filename && blk && blk_is_available(blk)) { + /* Use Boot ROM to copy data from SD card to SRAM */ + allwinner_a10_bootrom_setup(a10, blk); + } /* TODO create and connect IDE devices for ide_drive_get() */ cubieboard_binfo.ram_size = machine->ram_size; -- 2.34.1 From: Strahinja Jankovic <strahinjapjankovic@gmail.com> Cubieboard now can boot directly from SD card, without the need to pass `-kernel` parameter. Update Avocado tests to cover this functionality. Signed-off-by: Strahinja Jankovic <strahinja.p.jankovic@gmail.com> Reviewed-by: Niek Linnenbank <nieklinnenbank@gmail.com> Tested-by: Niek Linnenbank <nieklinnenbank@gmail.com> Message-id: 20221226220303.14420-8-strahinja.p.jankovic@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/avocado/boot_linux_console.py | 47 +++++++++++++++++++++++++++++ 1 file changed, 47 insertions(+) diff --git a/tests/avocado/boot_linux_console.py b/tests/avocado/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/avocado/boot_linux_console.py +++ b/tests/avocado/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ def test_arm_cubieboard_sata(self): 'sda') # cubieboard's reboot is not functioning; omit reboot test. + @skipUnless(os.getenv('AVOCADO_ALLOW_LARGE_STORAGE'), 'storage limited') + def test_arm_cubieboard_openwrt_22_03_2(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:cubieboard + :avocado: tags=device:sd + """ + + # This test download a 7.5 MiB compressed image and expand it + # to 126 MiB. + image_url = ('https://downloads.openwrt.org/releases/22.03.2/targets/' + 'sunxi/cortexa8/openwrt-22.03.2-sunxi-cortexa8-' + 'cubietech_a10-cubieboard-ext4-sdcard.img.gz') + image_hash = ('94b5ecbfbc0b3b56276e5146b899eafa' + '2ac5dc2d08733d6705af9f144f39f554') + image_path_gz = self.fetch_asset(image_url, asset_hash=image_hash, + algorithm='sha256') + image_path = archive.extract(image_path_gz, self.workdir) + image_pow2ceil_expand(image_path) + + self.vm.set_console() + self.vm.add_args('-drive', 'file=' + image_path + ',if=sd,format=raw', + '-nic', 'user', + '-no-reboot') + self.vm.launch() + + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'usbcore.nousb ' + 'noreboot') + + self.wait_for_console_pattern('U-Boot SPL') + + interrupt_interactive_console_until_pattern( + self, 'Hit any key to stop autoboot:', '=>') + exec_command_and_wait_for_pattern(self, "setenv extraargs '" + + kernel_command_line + "'", '=>') + exec_command_and_wait_for_pattern(self, 'boot', 'Starting kernel ...'); + + self.wait_for_console_pattern( + 'Please press Enter to activate this console.') + + exec_command_and_wait_for_pattern(self, ' ', 'root@') + + exec_command_and_wait_for_pattern(self, 'cat /proc/cpuinfo', + 'Allwinner sun4i/sun5i') + # cubieboard's reboot is not functioning; omit reboot test. + @skipUnless(os.getenv('AVOCADO_TIMEOUT_EXPECTED'), 'Test might timeout') def test_arm_quanta_gsj(self): """ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Don't dereference CPUTLBEntryFull until we verify that the page is valid. Move the other user-only info field updates after the valid check to match. Cc: qemu-stable@nongnu.org Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1412 Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230104190056.305143-1-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve_helper.c | 14 +++++++++----- 1 file changed, 9 insertions(+), 5 deletions(-) diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ bool sve_probe_page(SVEHostPage *info, bool nofault, CPUARMState *env, #ifdef CONFIG_USER_ONLY flags = probe_access_flags(env, addr, access_type, mmu_idx, nofault, &info->host, retaddr); - memset(&info->attrs, 0, sizeof(info->attrs)); - /* Require both ANON and MTE; see allocation_tag_mem(). */ - info->tagged = (flags & PAGE_ANON) && (flags & PAGE_MTE); #else CPUTLBEntryFull *full; flags = probe_access_full(env, addr, access_type, mmu_idx, nofault, &info->host, &full, retaddr); - info->attrs = full->attrs; - info->tagged = full->pte_attrs == 0xf0; #endif info->flags = flags; @@ -XXX,XX +XXX,XX @@ bool sve_probe_page(SVEHostPage *info, bool nofault, CPUARMState *env, return false; } +#ifdef CONFIG_USER_ONLY + memset(&info->attrs, 0, sizeof(info->attrs)); + /* Require both ANON and MTE; see allocation_tag_mem(). */ + info->tagged = (flags & PAGE_ANON) && (flags & PAGE_MTE); +#else + info->attrs = full->attrs; + info->tagged = full->pte_attrs == 0xf0; +#endif + /* Ensure that info->host[] is relative to addr, not addr + mem_off. */ info->host -= mem_off; return true; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Since pxa255_init() must map the device in the system memory, there is no point in passing get_system_memory() by argument. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-2-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/pxa.h | 2 +- hw/arm/gumstix.c | 3 +-- hw/arm/pxa2xx.c | 4 +++- hw/arm/tosa.c | 2 +- 4 files changed, 6 insertions(+), 5 deletions(-) diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ struct PXA2xxI2SState { PXA2xxState *pxa270_init(MemoryRegion *address_space, unsigned int sdram_size, const char *revision); -PXA2xxState *pxa255_init(MemoryRegion *address_space, unsigned int sdram_size); +PXA2xxState *pxa255_init(unsigned int sdram_size); #endif /* PXA_H */ diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ static void connex_init(MachineState *machine) { PXA2xxState *cpu; DriveInfo *dinfo; - MemoryRegion *address_space_mem = get_system_memory(); uint32_t connex_rom = 0x01000000; uint32_t connex_ram = 0x04000000; - cpu = pxa255_init(address_space_mem, connex_ram); + cpu = pxa255_init(connex_ram); dinfo = drive_get(IF_PFLASH, 0, 0); if (!dinfo && !qtest_enabled()) { diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -XXX,XX +XXX,XX @@ #include "qemu/error-report.h" #include "qemu/module.h" #include "qapi/error.h" +#include "exec/address-spaces.h" #include "cpu.h" #include "hw/sysbus.h" #include "migration/vmstate.h" @@ -XXX,XX +XXX,XX @@ PXA2xxState *pxa270_init(MemoryRegion *address_space, } /* Initialise a PXA255 integrated chip (ARM based core). */ -PXA2xxState *pxa255_init(MemoryRegion *address_space, unsigned int sdram_size) +PXA2xxState *pxa255_init(unsigned int sdram_size) { + MemoryRegion *address_space = get_system_memory(); PXA2xxState *s; int i; DriveInfo *dinfo; diff --git a/hw/arm/tosa.c b/hw/arm/tosa.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/tosa.c +++ b/hw/arm/tosa.c @@ -XXX,XX +XXX,XX @@ static void tosa_init(MachineState *machine) TC6393xbState *tmio; DeviceState *scp0, *scp1; - mpu = pxa255_init(address_space_mem, tosa_binfo.ram_size); + mpu = pxa255_init(tosa_binfo.ram_size); memory_region_init_rom(rom, NULL, "tosa.rom", TOSA_ROM, &error_fatal); memory_region_add_subregion(address_space_mem, 0, rom); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Since pxa270_init() must map the device in the system memory, there is no point in passing get_system_memory() by argument. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/pxa.h | 3 +-- hw/arm/gumstix.c | 3 +-- hw/arm/mainstone.c | 10 ++++------ hw/arm/pxa2xx.c | 4 ++-- hw/arm/spitz.c | 6 ++---- hw/arm/z2.c | 3 +-- 6 files changed, 11 insertions(+), 18 deletions(-) diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ struct PXA2xxI2SState { # define PA_FMT "0x%08lx" -PXA2xxState *pxa270_init(MemoryRegion *address_space, unsigned int sdram_size, - const char *revision); +PXA2xxState *pxa270_init(unsigned int sdram_size, const char *revision); PXA2xxState *pxa255_init(unsigned int sdram_size); #endif /* PXA_H */ diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) { PXA2xxState *cpu; DriveInfo *dinfo; - MemoryRegion *address_space_mem = get_system_memory(); uint32_t verdex_rom = 0x02000000; uint32_t verdex_ram = 0x10000000; - cpu = pxa270_init(address_space_mem, verdex_ram, machine->cpu_type); + cpu = pxa270_init(verdex_ram, machine->cpu_type); dinfo = drive_get(IF_PFLASH, 0, 0); if (!dinfo && !qtest_enabled()) { diff --git a/hw/arm/mainstone.c b/hw/arm/mainstone.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mainstone.c +++ b/hw/arm/mainstone.c @@ -XXX,XX +XXX,XX @@ static struct arm_boot_info mainstone_binfo = { .ram_size = 0x04000000, }; -static void mainstone_common_init(MemoryRegion *address_space_mem, - MachineState *machine, +static void mainstone_common_init(MachineState *machine, enum mainstone_model_e model, int arm_id) { uint32_t sector_len = 256 * 1024; @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MemoryRegion *address_space_mem, MemoryRegion *rom = g_new(MemoryRegion, 1); /* Setup CPU & memory */ - mpu = pxa270_init(address_space_mem, mainstone_binfo.ram_size, - machine->cpu_type); + mpu = pxa270_init(mainstone_binfo.ram_size, machine->cpu_type); memory_region_init_rom(rom, NULL, "mainstone.rom", MAINSTONE_ROM, &error_fatal); - memory_region_add_subregion(address_space_mem, 0, rom); + memory_region_add_subregion(get_system_memory(), 0x00000000, rom); /* There are two 32MiB flash devices on the board */ for (i = 0; i < 2; i ++) { @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MemoryRegion *address_space_mem, static void mainstone_init(MachineState *machine) { - mainstone_common_init(get_system_memory(), machine, mainstone, 0x196); + mainstone_common_init(machine, mainstone, 0x196); } static void mainstone2_machine_init(MachineClass *mc) diff --git a/hw/arm/pxa2xx.c b/hw/arm/pxa2xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/pxa2xx.c +++ b/hw/arm/pxa2xx.c @@ -XXX,XX +XXX,XX @@ static void pxa2xx_reset(void *opaque, int line, int level) } /* Initialise a PXA270 integrated chip (ARM based core). */ -PXA2xxState *pxa270_init(MemoryRegion *address_space, - unsigned int sdram_size, const char *cpu_type) +PXA2xxState *pxa270_init(unsigned int sdram_size, const char *cpu_type) { + MemoryRegion *address_space = get_system_memory(); PXA2xxState *s; int i; DriveInfo *dinfo; diff --git a/hw/arm/spitz.c b/hw/arm/spitz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/spitz.c +++ b/hw/arm/spitz.c @@ -XXX,XX +XXX,XX @@ static void spitz_common_init(MachineState *machine) SpitzMachineState *sms = SPITZ_MACHINE(machine); enum spitz_model_e model = smc->model; PXA2xxState *mpu; - MemoryRegion *address_space_mem = get_system_memory(); MemoryRegion *rom = g_new(MemoryRegion, 1); /* Setup CPU & memory */ - mpu = pxa270_init(address_space_mem, spitz_binfo.ram_size, - machine->cpu_type); + mpu = pxa270_init(spitz_binfo.ram_size, machine->cpu_type); sms->mpu = mpu; sl_flash_register(mpu, (model == spitz) ? FLASH_128M : FLASH_1024M); memory_region_init_rom(rom, NULL, "spitz.rom", SPITZ_ROM, &error_fatal); - memory_region_add_subregion(address_space_mem, 0, rom); + memory_region_add_subregion(get_system_memory(), 0, rom); /* Setup peripherals */ spitz_keyboard_register(mpu); diff --git a/hw/arm/z2.c b/hw/arm/z2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/z2.c +++ b/hw/arm/z2.c @@ -XXX,XX +XXX,XX @@ static const TypeInfo aer915_info = { static void z2_init(MachineState *machine) { - MemoryRegion *address_space_mem = get_system_memory(); uint32_t sector_len = 0x10000; PXA2xxState *mpu; DriveInfo *dinfo; @@ -XXX,XX +XXX,XX @@ static void z2_init(MachineState *machine) DeviceState *wm; /* Setup CPU & memory */ - mpu = pxa270_init(address_space_mem, z2_binfo.ram_size, machine->cpu_type); + mpu = pxa270_init(z2_binfo.ram_size, machine->cpu_type); dinfo = drive_get(IF_PFLASH, 0, 0); if (!pflash_cfi01_register(Z2_FLASH_BASE, "z2.flash0", Z2_FLASH_SIZE, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Add definitions for RAM / Flash / Flash blocksize. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/collie.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/hw/arm/collie.c b/hw/arm/collie.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/collie.c +++ b/hw/arm/collie.c @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "qom/object.h" +#define RAM_SIZE (512 * MiB) +#define FLASH_SIZE (32 * MiB) +#define FLASH_SECTOR_SIZE (64 * KiB) + struct CollieMachineState { MachineState parent; @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(CollieMachineState, COLLIE_MACHINE) static struct arm_boot_info collie_binfo = { .loader_start = SA_SDCS0, - .ram_size = 0x20000000, + .ram_size = RAM_SIZE, }; static void collie_init(MachineState *machine) @@ -XXX,XX +XXX,XX @@ static void collie_init(MachineState *machine) memory_region_add_subregion(get_system_memory(), SA_SDCS0, machine->ram); dinfo = drive_get(IF_PFLASH, 0, 0); - pflash_cfi01_register(SA_CS0, "collie.fl1", 0x02000000, + pflash_cfi01_register(SA_CS0, "collie.fl1", FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - 64 * KiB, 4, 0x00, 0x00, 0x00, 0x00, 0); + FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); dinfo = drive_get(IF_PFLASH, 0, 1); - pflash_cfi01_register(SA_CS1, "collie.fl2", 0x02000000, + pflash_cfi01_register(SA_CS1, "collie.fl2", FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - 64 * KiB, 4, 0x00, 0x00, 0x00, 0x00, 0); + FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); sysbus_create_simple("scoop", 0x40800000, NULL); @@ -XXX,XX +XXX,XX @@ static void collie_machine_class_init(ObjectClass *oc, void *data) mc->init = collie_init; mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("sa1110"); - mc->default_ram_size = 0x20000000; + mc->default_ram_size = RAM_SIZE; mc->default_ram_id = "strongarm.sdram"; } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-5-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/collie.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) diff --git a/hw/arm/collie.c b/hw/arm/collie.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/collie.c +++ b/hw/arm/collie.c @@ -XXX,XX +XXX,XX @@ static struct arm_boot_info collie_binfo = { static void collie_init(MachineState *machine) { - DriveInfo *dinfo; MachineClass *mc = MACHINE_GET_CLASS(machine); CollieMachineState *cms = COLLIE_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void collie_init(MachineState *machine) memory_region_add_subregion(get_system_memory(), SA_SDCS0, machine->ram); - dinfo = drive_get(IF_PFLASH, 0, 0); - pflash_cfi01_register(SA_CS0, "collie.fl1", FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); - - dinfo = drive_get(IF_PFLASH, 0, 1); - pflash_cfi01_register(SA_CS1, "collie.fl2", FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); + for (unsigned i = 0; i < 2; i++) { + DriveInfo *dinfo = drive_get(IF_PFLASH, 0, i); + pflash_cfi01_register(i ? SA_CS1 : SA_CS0, + i ? "collie.fl2" : "collie.fl1", FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 4, 0x00, 0x00, 0x00, 0x00, 0); + } sysbus_create_simple("scoop", 0x40800000, NULL); -- 2.34.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Add a comment describing the Connex uses a Numonyx RC28F128J3F75 flash, and the Verdex uses a Micron RC28F256P30TFA. Correct the Verdex machine description (we model the 'Pro' board). Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-6-philmd@linaro.org Message-Id: <20200223231044.8003-3-philmd@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/gumstix.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ * Contributions after 2012-01-13 are licensed under the terms of the * GNU GPL, version 2 or (at your option) any later version. */ - + /* * Example usage: * @@ -XXX,XX +XXX,XX @@ static void connex_init(MachineState *machine) exit(1); } + /* Numonyx RC28F128J3F75 */ if (!pflash_cfi01_register(0x00000000, "connext.rom", connex_rom, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, sector_len, 2, 0, 0, 0, 0, 0)) { @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) exit(1); } + /* Micron RC28F256P30TFA */ if (!pflash_cfi01_register(0x00000000, "verdex.rom", verdex_rom, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, sector_len, 2, 0, 0, 0, 0, 0)) { @@ -XXX,XX +XXX,XX @@ static void verdex_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); - mc->desc = "Gumstix Verdex (PXA270)"; + mc->desc = "Gumstix Verdex Pro XL6P COMs (PXA270)"; mc->init = verdex_init; mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("pxa270-c0"); -- 2.34.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> IEC binary prefixes ease code review: the unit is explicit. Add definitions for RAM / Flash / Flash blocksize. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-7-philmd@linaro.org Message-Id: <20200223231044.8003-3-philmd@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/gumstix.c | 27 ++++++++++++++------------- 1 file changed, 14 insertions(+), 13 deletions(-) diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qemu/error-report.h" #include "hw/arm/pxa.h" #include "net/net.h" @@ -XXX,XX +XXX,XX @@ #include "sysemu/qtest.h" #include "cpu.h" -static const int sector_len = 128 * 1024; +#define CONNEX_FLASH_SIZE (16 * MiB) +#define CONNEX_RAM_SIZE (64 * MiB) + +#define VERDEX_FLASH_SIZE (32 * MiB) +#define VERDEX_RAM_SIZE (256 * MiB) + +#define FLASH_SECTOR_SIZE (128 * KiB) static void connex_init(MachineState *machine) { PXA2xxState *cpu; DriveInfo *dinfo; - uint32_t connex_rom = 0x01000000; - uint32_t connex_ram = 0x04000000; - - cpu = pxa255_init(connex_ram); + cpu = pxa255_init(CONNEX_RAM_SIZE); dinfo = drive_get(IF_PFLASH, 0, 0); if (!dinfo && !qtest_enabled()) { @@ -XXX,XX +XXX,XX @@ static void connex_init(MachineState *machine) } /* Numonyx RC28F128J3F75 */ - if (!pflash_cfi01_register(0x00000000, "connext.rom", connex_rom, + if (!pflash_cfi01_register(0x00000000, "connext.rom", CONNEX_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - sector_len, 2, 0, 0, 0, 0, 0)) { + FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0)) { error_report("Error registering flash memory"); exit(1); } @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) PXA2xxState *cpu; DriveInfo *dinfo; - uint32_t verdex_rom = 0x02000000; - uint32_t verdex_ram = 0x10000000; - - cpu = pxa270_init(verdex_ram, machine->cpu_type); + cpu = pxa270_init(VERDEX_RAM_SIZE, machine->cpu_type); dinfo = drive_get(IF_PFLASH, 0, 0); if (!dinfo && !qtest_enabled()) { @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) } /* Micron RC28F256P30TFA */ - if (!pflash_cfi01_register(0x00000000, "verdex.rom", verdex_rom, + if (!pflash_cfi01_register(0x00000000, "verdex.rom", VERDEX_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - sector_len, 2, 0, 0, 0, 0, 0)) { + FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0)) { error_report("Error registering flash memory"); exit(1); } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Add the FLASH_SECTOR_SIZE definition. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-8-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/mainstone.c | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/hw/arm/mainstone.c b/hw/arm/mainstone.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mainstone.c +++ b/hw/arm/mainstone.c @@ -XXX,XX +XXX,XX @@ * GNU GPL, version 2 or (at your option) any later version. */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qemu/error-report.h" #include "qapi/error.h" #include "hw/arm/pxa.h" @@ -XXX,XX +XXX,XX @@ static const struct keymap map[0xE0] = { enum mainstone_model_e { mainstone }; -#define MAINSTONE_RAM 0x04000000 -#define MAINSTONE_ROM 0x00800000 -#define MAINSTONE_FLASH 0x02000000 +#define MAINSTONE_RAM_SIZE (64 * MiB) +#define MAINSTONE_ROM_SIZE (8 * MiB) +#define MAINSTONE_FLASH_SIZE (32 * MiB) static struct arm_boot_info mainstone_binfo = { .loader_start = PXA2XX_SDRAM_BASE, - .ram_size = 0x04000000, + .ram_size = MAINSTONE_RAM_SIZE, }; +#define FLASH_SECTOR_SIZE (256 * KiB) + static void mainstone_common_init(MachineState *machine, enum mainstone_model_e model, int arm_id) { - uint32_t sector_len = 256 * 1024; hwaddr mainstone_flash_base[] = { MST_FLASH_0, MST_FLASH_1 }; PXA2xxState *mpu; DeviceState *mst_irq; @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MachineState *machine, /* Setup CPU & memory */ mpu = pxa270_init(mainstone_binfo.ram_size, machine->cpu_type); - memory_region_init_rom(rom, NULL, "mainstone.rom", MAINSTONE_ROM, + memory_region_init_rom(rom, NULL, "mainstone.rom", MAINSTONE_ROM_SIZE, &error_fatal); memory_region_add_subregion(get_system_memory(), 0x00000000, rom); @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MachineState *machine, dinfo = drive_get(IF_PFLASH, 0, i); if (!pflash_cfi01_register(mainstone_flash_base[i], i ? "mainstone.flash1" : "mainstone.flash0", - MAINSTONE_FLASH, + MAINSTONE_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - sector_len, 4, 0, 0, 0, 0, 0)) { + FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { error_report("Error registering flash memory"); exit(1); } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Add the FLASH_SECTOR_SIZE definition. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-9-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/musicpal.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/musicpal.c +++ b/hw/arm/musicpal.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qapi/error.h" #include "cpu.h" #include "hw/sysbus.h" @@ -XXX,XX +XXX,XX @@ static const TypeInfo musicpal_key_info = { .class_init = musicpal_key_class_init, }; +#define FLASH_SECTOR_SIZE (64 * KiB) + static struct arm_boot_info musicpal_binfo = { .loader_start = 0x0, .board_id = 0x20e, @@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine) BlockBackend *blk = blk_by_legacy_dinfo(dinfo); flash_size = blk_getlength(blk); - if (flash_size != 8*1024*1024 && flash_size != 16*1024*1024 && - flash_size != 32*1024*1024) { + if (flash_size != 8 * MiB && flash_size != 16 * MiB && + flash_size != 32 * MiB) { error_report("Invalid flash image size"); exit(1); } @@ -XXX,XX +XXX,XX @@ static void musicpal_init(MachineState *machine) */ pflash_cfi02_register(0x100000000ULL - MP_FLASH_SIZE_MAX, "musicpal.flash", flash_size, - blk, 0x10000, + blk, FLASH_SECTOR_SIZE, MP_FLASH_SIZE_MAX / flash_size, 2, 0x00BF, 0x236D, 0x0000, 0x0000, 0x5555, 0x2AAA, 0); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> The total_ram_v1/total_ram_v2 definitions were never used. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-10-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/omap_sx1.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/hw/arm/omap_sx1.c b/hw/arm/omap_sx1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap_sx1.c +++ b/hw/arm/omap_sx1.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps static_ops = { #define flash0_size (16 * 1024 * 1024) #define flash1_size ( 8 * 1024 * 1024) #define flash2_size (32 * 1024 * 1024) -#define total_ram_v1 (sdram_size + flash0_size + flash1_size + OMAP15XX_SRAM_SIZE) -#define total_ram_v2 (sdram_size + flash2_size + OMAP15XX_SRAM_SIZE) static struct arm_boot_info sx1_binfo = { .loader_start = OMAP_EMIFF_BASE, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-11-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/omap_sx1.c | 33 +++++++++++++++++---------------- 1 file changed, 17 insertions(+), 16 deletions(-) diff --git a/hw/arm/omap_sx1.c b/hw/arm/omap_sx1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap_sx1.c +++ b/hw/arm/omap_sx1.c @@ -XXX,XX +XXX,XX @@ * with this program; if not, see <http://www.gnu.org/licenses/>. */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "qapi/error.h" #include "ui/console.h" #include "hw/arm/omap.h" @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps static_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -#define sdram_size 0x02000000 -#define sector_size (128 * 1024) -#define flash0_size (16 * 1024 * 1024) -#define flash1_size ( 8 * 1024 * 1024) -#define flash2_size (32 * 1024 * 1024) +#define SDRAM_SIZE (32 * MiB) +#define SECTOR_SIZE (128 * KiB) +#define FLASH0_SIZE (16 * MiB) +#define FLASH1_SIZE (8 * MiB) +#define FLASH2_SIZE (32 * MiB) static struct arm_boot_info sx1_binfo = { .loader_start = OMAP_EMIFF_BASE, - .ram_size = sdram_size, + .ram_size = SDRAM_SIZE, .board_id = 0x265, }; @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) static uint32_t cs3val = 0x00001139; DriveInfo *dinfo; int fl_idx; - uint32_t flash_size = flash0_size; + uint32_t flash_size = FLASH0_SIZE; if (machine->ram_size != mc->default_ram_size) { char *sz = size_to_str(mc->default_ram_size); @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) } if (version == 2) { - flash_size = flash2_size; + flash_size = FLASH2_SIZE; } memory_region_add_subregion(address_space, OMAP_EMIFF_BASE, machine->ram); @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) if (!pflash_cfi01_register(OMAP_CS0_BASE, "omap_sx1.flash0-1", flash_size, blk_by_legacy_dinfo(dinfo), - sector_size, 4, 0, 0, 0, 0, 0)) { + SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { fprintf(stderr, "qemu: Error registering flash memory %d.\n", fl_idx); } @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) (dinfo = drive_get(IF_PFLASH, 0, fl_idx)) != NULL) { MemoryRegion *flash_1 = g_new(MemoryRegion, 1); memory_region_init_rom(flash_1, NULL, "omap_sx1.flash1-0", - flash1_size, &error_fatal); + FLASH1_SIZE, &error_fatal); memory_region_add_subregion(address_space, OMAP_CS1_BASE, flash_1); memory_region_init_io(&cs[1], NULL, &static_ops, &cs1val, - "sx1.cs1", OMAP_CS1_SIZE - flash1_size); + "sx1.cs1", OMAP_CS1_SIZE - FLASH1_SIZE); memory_region_add_subregion(address_space, - OMAP_CS1_BASE + flash1_size, &cs[1]); + OMAP_CS1_BASE + FLASH1_SIZE, &cs[1]); if (!pflash_cfi01_register(OMAP_CS1_BASE, - "omap_sx1.flash1-1", flash1_size, + "omap_sx1.flash1-1", FLASH1_SIZE, blk_by_legacy_dinfo(dinfo), - sector_size, 4, 0, 0, 0, 0, 0)) { + SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { fprintf(stderr, "qemu: Error registering flash memory %d.\n", fl_idx); } @@ -XXX,XX +XXX,XX @@ static void sx1_machine_v2_class_init(ObjectClass *oc, void *data) mc->init = sx1_init_v2; mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("ti925t"); - mc->default_ram_size = sdram_size; + mc->default_ram_size = SDRAM_SIZE; mc->default_ram_id = "omap1.dram"; } @@ -XXX,XX +XXX,XX @@ static void sx1_machine_v1_class_init(ObjectClass *oc, void *data) mc->init = sx1_init_v1; mc->ignore_memory_transaction_failures = true; mc->default_cpu_type = ARM_CPU_TYPE_NAME("ti925t"); - mc->default_ram_size = sdram_size; + mc->default_ram_size = SDRAM_SIZE; mc->default_ram_id = "omap1.dram"; } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> IEC binary prefixes ease code review: the unit is explicit. Add the FLASH_SECTOR_SIZE definition. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-12-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/z2.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/hw/arm/z2.c b/hw/arm/z2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/z2.c +++ b/hw/arm/z2.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/units.h" #include "hw/arm/pxa.h" #include "hw/arm/boot.h" #include "hw/i2c/i2c.h" @@ -XXX,XX +XXX,XX @@ static const TypeInfo aer915_info = { .class_init = aer915_class_init, }; +#define FLASH_SECTOR_SIZE (64 * KiB) + static void z2_init(MachineState *machine) { - uint32_t sector_len = 0x10000; PXA2xxState *mpu; DriveInfo *dinfo; void *z2_lcd; @@ -XXX,XX +XXX,XX @@ static void z2_init(MachineState *machine) dinfo = drive_get(IF_PFLASH, 0, 0); if (!pflash_cfi01_register(Z2_FLASH_BASE, "z2.flash0", Z2_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - sector_len, 4, 0, 0, 0, 0, 0)) { + FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { error_report("Error registering flash memory"); exit(1); } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Upon introduction in commit b8433303fb ("Set proper device-width for vexpress flash"), ve_pflash_cfi01_register() was calling qdev_init_nofail() which can not fail. This call was later converted with a script to use &error_fatal, still unable to fail. Remove the unreachable code. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-13-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/vexpress.c | 10 +--------- 1 file changed, 1 insertion(+), 9 deletions(-) diff --git a/hw/arm/vexpress.c b/hw/arm/vexpress.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/vexpress.c +++ b/hw/arm/vexpress.c @@ -XXX,XX +XXX,XX @@ static void vexpress_common_init(MachineState *machine) dinfo = drive_get(IF_PFLASH, 0, 0); pflash0 = ve_pflash_cfi01_register(map[VE_NORFLASH0], "vexpress.flash0", dinfo); - if (!pflash0) { - error_report("vexpress: error registering flash 0"); - exit(1); - } if (map[VE_NORFLASHALIAS] != -1) { /* Map flash 0 as an alias into low memory */ @@ -XXX,XX +XXX,XX @@ static void vexpress_common_init(MachineState *machine) } dinfo = drive_get(IF_PFLASH, 0, 1); - if (!ve_pflash_cfi01_register(map[VE_NORFLASH1], "vexpress.flash1", - dinfo)) { - error_report("vexpress: error registering flash 1"); - exit(1); - } + ve_pflash_cfi01_register(map[VE_NORFLASH1], "vexpress.flash1", dinfo); sram_size = 0x2000000; memory_region_init_ram(sram, NULL, "vexpress.sram", sram_size, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Since its QOM'ification in commit 368a354f02 ("pflash_cfi0x: QOMified") the pflash_cfi01_register() function does not fail. This call was later converted with a script to use &error_fatal, still unable to fail. Remove the unreachable code. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109115316.2235-14-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/gumstix.c | 18 ++++++------------ hw/arm/mainstone.c | 13 +++++-------- hw/arm/omap_sx1.c | 22 ++++++++-------------- hw/arm/versatilepb.c | 6 ++---- hw/arm/z2.c | 9 +++------ 5 files changed, 24 insertions(+), 44 deletions(-) diff --git a/hw/arm/gumstix.c b/hw/arm/gumstix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/gumstix.c +++ b/hw/arm/gumstix.c @@ -XXX,XX +XXX,XX @@ static void connex_init(MachineState *machine) } /* Numonyx RC28F128J3F75 */ - if (!pflash_cfi01_register(0x00000000, "connext.rom", CONNEX_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0)) { - error_report("Error registering flash memory"); - exit(1); - } + pflash_cfi01_register(0x00000000, "connext.rom", CONNEX_FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0); /* Interrupt line of NIC is connected to GPIO line 36 */ smc91c111_init(&nd_table[0], 0x04000300, @@ -XXX,XX +XXX,XX @@ static void verdex_init(MachineState *machine) } /* Micron RC28F256P30TFA */ - if (!pflash_cfi01_register(0x00000000, "verdex.rom", VERDEX_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0)) { - error_report("Error registering flash memory"); - exit(1); - } + pflash_cfi01_register(0x00000000, "verdex.rom", VERDEX_FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 2, 0, 0, 0, 0, 0); /* Interrupt line of NIC is connected to GPIO line 99 */ smc91c111_init(&nd_table[0], 0x04000300, diff --git a/hw/arm/mainstone.c b/hw/arm/mainstone.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mainstone.c +++ b/hw/arm/mainstone.c @@ -XXX,XX +XXX,XX @@ static void mainstone_common_init(MachineState *machine, /* There are two 32MiB flash devices on the board */ for (i = 0; i < 2; i ++) { dinfo = drive_get(IF_PFLASH, 0, i); - if (!pflash_cfi01_register(mainstone_flash_base[i], - i ? "mainstone.flash1" : "mainstone.flash0", - MAINSTONE_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { - error_report("Error registering flash memory"); - exit(1); - } + pflash_cfi01_register(mainstone_flash_base[i], + i ? "mainstone.flash1" : "mainstone.flash0", + MAINSTONE_FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0); } mst_irq = sysbus_create_simple("mainstone-fpga", MST_FPGA_PHYS, diff --git a/hw/arm/omap_sx1.c b/hw/arm/omap_sx1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap_sx1.c +++ b/hw/arm/omap_sx1.c @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) fl_idx = 0; if ((dinfo = drive_get(IF_PFLASH, 0, fl_idx)) != NULL) { - if (!pflash_cfi01_register(OMAP_CS0_BASE, - "omap_sx1.flash0-1", flash_size, - blk_by_legacy_dinfo(dinfo), - SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { - fprintf(stderr, "qemu: Error registering flash memory %d.\n", - fl_idx); - } + pflash_cfi01_register(OMAP_CS0_BASE, + "omap_sx1.flash0-1", flash_size, + blk_by_legacy_dinfo(dinfo), + SECTOR_SIZE, 4, 0, 0, 0, 0, 0); fl_idx++; } @@ -XXX,XX +XXX,XX @@ static void sx1_init(MachineState *machine, const int version) memory_region_add_subregion(address_space, OMAP_CS1_BASE + FLASH1_SIZE, &cs[1]); - if (!pflash_cfi01_register(OMAP_CS1_BASE, - "omap_sx1.flash1-1", FLASH1_SIZE, - blk_by_legacy_dinfo(dinfo), - SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { - fprintf(stderr, "qemu: Error registering flash memory %d.\n", - fl_idx); - } + pflash_cfi01_register(OMAP_CS1_BASE, + "omap_sx1.flash1-1", FLASH1_SIZE, + blk_by_legacy_dinfo(dinfo), + SECTOR_SIZE, 4, 0, 0, 0, 0, 0); fl_idx++; } else { memory_region_init_io(&cs[1], NULL, &static_ops, &cs1val, diff --git a/hw/arm/versatilepb.c b/hw/arm/versatilepb.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/versatilepb.c +++ b/hw/arm/versatilepb.c @@ -XXX,XX +XXX,XX @@ static void versatile_init(MachineState *machine, int board_id) /* 0x34000000 NOR Flash */ dinfo = drive_get(IF_PFLASH, 0, 0); - if (!pflash_cfi01_register(VERSATILE_FLASH_ADDR, "versatile.flash", + pflash_cfi01_register(VERSATILE_FLASH_ADDR, "versatile.flash", VERSATILE_FLASH_SIZE, dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, VERSATILE_FLASH_SECT_SIZE, - 4, 0x0089, 0x0018, 0x0000, 0x0, 0)) { - fprintf(stderr, "qemu: Error registering flash memory.\n"); - } + 4, 0x0089, 0x0018, 0x0000, 0x0, 0); versatile_binfo.ram_size = machine->ram_size; versatile_binfo.board_id = board_id; diff --git a/hw/arm/z2.c b/hw/arm/z2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/z2.c +++ b/hw/arm/z2.c @@ -XXX,XX +XXX,XX @@ static void z2_init(MachineState *machine) mpu = pxa270_init(z2_binfo.ram_size, machine->cpu_type); dinfo = drive_get(IF_PFLASH, 0, 0); - if (!pflash_cfi01_register(Z2_FLASH_BASE, "z2.flash0", Z2_FLASH_SIZE, - dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, - FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0)) { - error_report("Error registering flash memory"); - exit(1); - } + pflash_cfi01_register(Z2_FLASH_BASE, "z2.flash0", Z2_FLASH_SIZE, + dinfo ? blk_by_legacy_dinfo(dinfo) : NULL, + FLASH_SECTOR_SIZE, 4, 0, 0, 0, 0, 0); /* setup keypad */ pxa27x_register_keypad(mpu->kp, map, 0x100); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> To avoid forward-declaring PXA2xxI2CState, declare PXA2XX_I2C before its use in pxa2xx_i2c_init() prototype. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-2-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/pxa.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/include/hw/arm/pxa.h b/include/hw/arm/pxa.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/pxa.h +++ b/include/hw/arm/pxa.h @@ -XXX,XX +XXX,XX @@ void pxa27x_register_keypad(PXA2xxKeyPadState *kp, const struct keymap *map, int size); /* pxa2xx.c */ -typedef struct PXA2xxI2CState PXA2xxI2CState; +#define TYPE_PXA2XX_I2C "pxa2xx_i2c" +OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxI2CState, PXA2XX_I2C) + PXA2xxI2CState *pxa2xx_i2c_init(hwaddr base, qemu_irq irq, uint32_t page_size); I2CBus *pxa2xx_i2c_bus(PXA2xxI2CState *s); -#define TYPE_PXA2XX_I2C "pxa2xx_i2c" typedef struct PXA2xxI2SState PXA2xxI2SState; -OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxI2CState, PXA2XX_I2C) #define TYPE_PXA2XX_FIR "pxa2xx-fir" OBJECT_DECLARE_SIMPLE_TYPE(PXA2xxFIrState, PXA2XX_FIR) -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Add a local 'struct omap_gpif_s *' variable to improve readability. (This also eases next commit conversion). Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/gpio/omap_gpio.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/omap_gpio.c +++ b/hw/gpio/omap_gpio.c @@ -XXX,XX +XXX,XX @@ struct omap_gpif_s { /* General-Purpose I/O of OMAP1 */ static void omap_gpio_set(void *opaque, int line, int level) { - struct omap_gpio_s *s = &((struct omap_gpif_s *) opaque)->omap1; + struct omap_gpif_s *p = opaque; + struct omap_gpio_s *s = &p->omap1; uint16_t prev = s->inputs; if (level) -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/omap1.c | 115 ++++++++++++++++++-------------------- hw/arm/omap2.c | 40 ++++++------- hw/arm/omap_sx1.c | 2 +- hw/arm/palm.c | 2 +- hw/char/omap_uart.c | 7 +-- hw/display/omap_dss.c | 15 +++-- hw/display/omap_lcdc.c | 9 ++- hw/dma/omap_dma.c | 15 +++-- hw/gpio/omap_gpio.c | 15 +++-- hw/intc/omap_intc.c | 12 ++-- hw/misc/omap_gpmc.c | 12 ++-- hw/misc/omap_l4.c | 7 +-- hw/misc/omap_sdrc.c | 7 +-- hw/misc/omap_tap.c | 5 +- hw/sd/omap_mmc.c | 9 ++- hw/ssi/omap_spi.c | 7 +-- hw/timer/omap_gptimer.c | 22 ++++---- hw/timer/omap_synctimer.c | 4 +- 18 files changed, 142 insertions(+), 163 deletions(-) diff --git a/hw/arm/omap1.c b/hw/arm/omap1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap1.c +++ b/hw/arm/omap1.c @@ -XXX,XX +XXX,XX @@ static void omap_timer_fire(void *opaque) static void omap_timer_tick(void *opaque) { - struct omap_mpu_timer_s *timer = (struct omap_mpu_timer_s *) opaque; + struct omap_mpu_timer_s *timer = opaque; omap_timer_sync(timer); omap_timer_fire(timer); @@ -XXX,XX +XXX,XX @@ static void omap_timer_tick(void *opaque) static void omap_timer_clk_update(void *opaque, int line, int on) { - struct omap_mpu_timer_s *timer = (struct omap_mpu_timer_s *) opaque; + struct omap_mpu_timer_s *timer = opaque; omap_timer_sync(timer); timer->rate = on ? omap_clk_getrate(timer->clk) : 0; @@ -XXX,XX +XXX,XX @@ static void omap_timer_clk_setup(struct omap_mpu_timer_s *timer) static uint64_t omap_mpu_timer_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_timer_s *s = (struct omap_mpu_timer_s *) opaque; + struct omap_mpu_timer_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mpu_timer_read(void *opaque, hwaddr addr, static void omap_mpu_timer_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_timer_s *s = (struct omap_mpu_timer_s *) opaque; + struct omap_mpu_timer_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct omap_watchdog_timer_s { static uint64_t omap_wd_timer_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_watchdog_timer_s *s = (struct omap_watchdog_timer_s *) opaque; + struct omap_watchdog_timer_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_wd_timer_read(void *opaque, hwaddr addr, static void omap_wd_timer_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_watchdog_timer_s *s = (struct omap_watchdog_timer_s *) opaque; + struct omap_watchdog_timer_s *s = opaque; if (size != 2) { omap_badwidth_write16(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct omap_32khz_timer_s { static uint64_t omap_os_timer_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_32khz_timer_s *s = (struct omap_32khz_timer_s *) opaque; + struct omap_32khz_timer_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_os_timer_read(void *opaque, hwaddr addr, static void omap_os_timer_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_32khz_timer_s *s = (struct omap_32khz_timer_s *) opaque; + struct omap_32khz_timer_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static struct omap_32khz_timer_s *omap_os_timer_init(MemoryRegion *memory, static uint64_t omap_ulpd_pm_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint16_t ret; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static inline void omap_ulpd_req_update(struct omap_mpu_state_s *s, static void omap_ulpd_pm_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; int64_t now, ticks; int div, mult; static const int bypass_div[4] = { 1, 2, 4, 4 }; @@ -XXX,XX +XXX,XX @@ static void omap_ulpd_pm_init(MemoryRegion *system_memory, static uint64_t omap_pin_cfg_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static inline void omap_pin_modconf1_update(struct omap_mpu_state_s *s, static void omap_pin_cfg_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint32_t diff; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static void omap_pin_cfg_init(MemoryRegion *system_memory, static uint64_t omap_id_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static void omap_id_init(MemoryRegion *memory, struct omap_mpu_state_s *mpu) static uint64_t omap_mpui_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mpui_read(void *opaque, hwaddr addr, static void omap_mpui_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct omap_tipb_bridge_s { static uint64_t omap_tipb_bridge_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_tipb_bridge_s *s = (struct omap_tipb_bridge_s *) opaque; + struct omap_tipb_bridge_s *s = opaque; if (size < 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_tipb_bridge_read(void *opaque, hwaddr addr, static void omap_tipb_bridge_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_tipb_bridge_s *s = (struct omap_tipb_bridge_s *) opaque; + struct omap_tipb_bridge_s *s = opaque; if (size < 2) { omap_badwidth_write16(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static struct omap_tipb_bridge_s *omap_tipb_bridge_init( static uint64_t omap_tcmi_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint32_t ret; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_tcmi_read(void *opaque, hwaddr addr, static void omap_tcmi_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct dpll_ctl_s { static uint64_t omap_dpll_read(void *opaque, hwaddr addr, unsigned size) { - struct dpll_ctl_s *s = (struct dpll_ctl_s *) opaque; + struct dpll_ctl_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_dpll_read(void *opaque, hwaddr addr, static void omap_dpll_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct dpll_ctl_s *s = (struct dpll_ctl_s *) opaque; + struct dpll_ctl_s *s = opaque; uint16_t diff; static const int bypass_div[4] = { 1, 2, 4, 4 }; int div, mult; @@ -XXX,XX +XXX,XX @@ static struct dpll_ctl_s *omap_dpll_init(MemoryRegion *memory, static uint64_t omap_clkm_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static inline void omap_clkm_ckout1_update(struct omap_mpu_state_s *s, static void omap_clkm_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint16_t diff; omap_clk clk; static const char *clkschemename[8] = { @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_clkm_ops = { static uint64_t omap_clkdsp_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; CPUState *cpu = CPU(s->cpu); if (size != 2) { @@ -XXX,XX +XXX,XX @@ static inline void omap_clkdsp_idlect2_update(struct omap_mpu_state_s *s, static void omap_clkdsp_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; uint16_t diff; if (size != 2) { @@ -XXX,XX +XXX,XX @@ struct omap_mpuio_s { static void omap_mpuio_set(void *opaque, int line, int level) { - struct omap_mpuio_s *s = (struct omap_mpuio_s *) opaque; + struct omap_mpuio_s *s = opaque; uint16_t prev = s->inputs; if (level) @@ -XXX,XX +XXX,XX @@ static void omap_mpuio_kbd_update(struct omap_mpuio_s *s) static uint64_t omap_mpuio_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpuio_s *s = (struct omap_mpuio_s *) opaque; + struct omap_mpuio_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint16_t ret; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mpuio_read(void *opaque, hwaddr addr, static void omap_mpuio_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mpuio_s *s = (struct omap_mpuio_s *) opaque; + struct omap_mpuio_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint16_t diff; int ln; @@ -XXX,XX +XXX,XX @@ static void omap_mpuio_reset(struct omap_mpuio_s *s) static void omap_mpuio_onoff(void *opaque, int line, int on) { - struct omap_mpuio_s *s = (struct omap_mpuio_s *) opaque; + struct omap_mpuio_s *s = opaque; s->clk = on; if (on) @@ -XXX,XX +XXX,XX @@ static void omap_uwire_transfer_start(struct omap_uwire_s *s) } } -static uint64_t omap_uwire_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_uwire_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_uwire_s *s = (struct omap_uwire_s *) opaque; + struct omap_uwire_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_uwire_read(void *opaque, hwaddr addr, static void omap_uwire_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_uwire_s *s = (struct omap_uwire_s *) opaque; + struct omap_uwire_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static void omap_pwl_update(struct omap_pwl_s *s) } } -static uint64_t omap_pwl_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_pwl_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_pwl_s *s = (struct omap_pwl_s *) opaque; + struct omap_pwl_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_pwl_read(void *opaque, hwaddr addr, static void omap_pwl_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_pwl_s *s = (struct omap_pwl_s *) opaque; + struct omap_pwl_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static void omap_pwl_reset(struct omap_pwl_s *s) static void omap_pwl_clk_update(void *opaque, int line, int on) { - struct omap_pwl_s *s = (struct omap_pwl_s *) opaque; + struct omap_pwl_s *s = opaque; s->clk = on; omap_pwl_update(s); @@ -XXX,XX +XXX,XX @@ struct omap_pwt_s { omap_clk clk; }; -static uint64_t omap_pwt_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_pwt_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_pwt_s *s = (struct omap_pwt_s *) opaque; + struct omap_pwt_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_pwt_read(void *opaque, hwaddr addr, static void omap_pwt_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_pwt_s *s = (struct omap_pwt_s *) opaque; + struct omap_pwt_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static void omap_rtc_alarm_update(struct omap_rtc_s *s) printf("%s: conversion failed\n", __func__); } -static uint64_t omap_rtc_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_rtc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_rtc_s *s = (struct omap_rtc_s *) opaque; + struct omap_rtc_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint8_t i; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_rtc_read(void *opaque, hwaddr addr, static void omap_rtc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_rtc_s *s = (struct omap_rtc_s *) opaque; + struct omap_rtc_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; struct tm new_tm; time_t ti[2]; @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_rx_newdata(struct omap_mcbsp_s *s) static void omap_mcbsp_source_tick(void *opaque) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; static const int bps[8] = { 0, 1, 1, 2, 2, 2, -255, -255 }; if (!s->rx_rate) @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_tx_newdata(struct omap_mcbsp_s *s) static void omap_mcbsp_sink_tick(void *opaque) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; static const int bps[8] = { 0, 1, 1, 2, 2, 2, -255, -255 }; if (!s->tx_rate) @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_req_update(struct omap_mcbsp_s *s) static uint64_t omap_mcbsp_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint16_t ret; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mcbsp_read(void *opaque, hwaddr addr, static void omap_mcbsp_writeh(void *opaque, hwaddr addr, uint32_t value) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; switch (offset) { @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_writeh(void *opaque, hwaddr addr, static void omap_mcbsp_writew(void *opaque, hwaddr addr, uint32_t value) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (offset == 0x04) { /* DXR */ @@ -XXX,XX +XXX,XX @@ static struct omap_mcbsp_s *omap_mcbsp_init(MemoryRegion *system_memory, static void omap_mcbsp_i2s_swallow(void *opaque, int line, int level) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; if (s->rx_rate) { s->rx_req = s->codec->in.len; @@ -XXX,XX +XXX,XX @@ static void omap_mcbsp_i2s_swallow(void *opaque, int line, int level) static void omap_mcbsp_i2s_start(void *opaque, int line, int level) { - struct omap_mcbsp_s *s = (struct omap_mcbsp_s *) opaque; + struct omap_mcbsp_s *s = opaque; if (s->tx_rate) { s->tx_req = s->codec->out.size; @@ -XXX,XX +XXX,XX @@ static void omap_lpg_reset(struct omap_lpg_s *s) omap_lpg_update(s); } -static uint64_t omap_lpg_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_lpg_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_lpg_s *s = (struct omap_lpg_s *) opaque; + struct omap_lpg_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_lpg_read(void *opaque, hwaddr addr, static void omap_lpg_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_lpg_s *s = (struct omap_lpg_s *) opaque; + struct omap_lpg_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 1) { @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_lpg_ops = { static void omap_lpg_clk_update(void *opaque, int line, int on) { - struct omap_lpg_s *s = (struct omap_lpg_s *) opaque; + struct omap_lpg_s *s = opaque; s->clk = on; omap_lpg_update(s); @@ -XXX,XX +XXX,XX @@ static void omap_setup_mpui_io(MemoryRegion *system_memory, /* General chip reset */ static void omap1_mpu_reset(void *opaque) { - struct omap_mpu_state_s *mpu = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *mpu = opaque; omap_dma_reset(mpu->dma); omap_mpu_timer_reset(mpu->timer[0]); @@ -XXX,XX +XXX,XX @@ static void omap_setup_dsp_mapping(MemoryRegion *system_memory, void omap_mpu_wakeup(void *opaque, int irq, int req) { - struct omap_mpu_state_s *mpu = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *mpu = opaque; CPUState *cpu = CPU(mpu->cpu); if (cpu->halted) { diff --git a/hw/arm/omap2.c b/hw/arm/omap2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap2.c +++ b/hw/arm/omap2.c @@ -XXX,XX +XXX,XX @@ static inline void omap_eac_out_empty(struct omap_eac_s *s) static void omap_eac_in_cb(void *opaque, int avail_b) { - struct omap_eac_s *s = (struct omap_eac_s *) opaque; + struct omap_eac_s *s = opaque; s->codec.rxavail = avail_b >> 2; omap_eac_in_refill(s); @@ -XXX,XX +XXX,XX @@ static void omap_eac_in_cb(void *opaque, int avail_b) static void omap_eac_out_cb(void *opaque, int free_b) { - struct omap_eac_s *s = (struct omap_eac_s *) opaque; + struct omap_eac_s *s = opaque; s->codec.txavail = free_b >> 2; if (s->codec.txlen) @@ -XXX,XX +XXX,XX @@ static void omap_eac_reset(struct omap_eac_s *s) omap_eac_interrupt_update(s); } -static uint64_t omap_eac_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_eac_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_eac_s *s = (struct omap_eac_s *) opaque; + struct omap_eac_s *s = opaque; uint32_t ret; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_eac_read(void *opaque, hwaddr addr, static void omap_eac_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_eac_s *s = (struct omap_eac_s *) opaque; + struct omap_eac_s *s = opaque; if (size != 2) { omap_badwidth_write16(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static void omap_sti_reset(struct omap_sti_s *s) static uint64_t omap_sti_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_sti_s *s = (struct omap_sti_s *) opaque; + struct omap_sti_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_sti_read(void *opaque, hwaddr addr, static void omap_sti_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_sti_s *s = (struct omap_sti_s *) opaque; + struct omap_sti_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_sti_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -static uint64_t omap_sti_fifo_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_sti_fifo_read(void *opaque, hwaddr addr, unsigned size) { OMAP_BAD_REG(addr); return 0; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_sti_fifo_read(void *opaque, hwaddr addr, static void omap_sti_fifo_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_sti_s *s = (struct omap_sti_s *) opaque; + struct omap_sti_s *s = opaque; int ch = addr >> 6; uint8_t byte = value; @@ -XXX,XX +XXX,XX @@ static void omap_prcm_int_update(struct omap_prcm_s *s, int dom) static uint64_t omap_prcm_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_prcm_s *s = (struct omap_prcm_s *) opaque; + struct omap_prcm_s *s = opaque; uint32_t ret; if (size != 4) { @@ -XXX,XX +XXX,XX @@ static void omap_prcm_dpll_update(struct omap_prcm_s *s) static void omap_prcm_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_prcm_s *s = (struct omap_prcm_s *) opaque; + struct omap_prcm_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ struct omap_sysctl_s { static uint32_t omap_sysctl_read8(void *opaque, hwaddr addr) { - struct omap_sysctl_s *s = (struct omap_sysctl_s *) opaque; + struct omap_sysctl_s *s = opaque; int pad_offset, byte_offset; int value; @@ -XXX,XX +XXX,XX @@ static uint32_t omap_sysctl_read8(void *opaque, hwaddr addr) static uint32_t omap_sysctl_read(void *opaque, hwaddr addr) { - struct omap_sysctl_s *s = (struct omap_sysctl_s *) opaque; + struct omap_sysctl_s *s = opaque; switch (addr) { case 0x000: /* CONTROL_REVISION */ @@ -XXX,XX +XXX,XX @@ static uint32_t omap_sysctl_read(void *opaque, hwaddr addr) return 0; } -static void omap_sysctl_write8(void *opaque, hwaddr addr, - uint32_t value) +static void omap_sysctl_write8(void *opaque, hwaddr addr, uint32_t value) { - struct omap_sysctl_s *s = (struct omap_sysctl_s *) opaque; + struct omap_sysctl_s *s = opaque; int pad_offset, byte_offset; int prev_value; @@ -XXX,XX +XXX,XX @@ static void omap_sysctl_write8(void *opaque, hwaddr addr, } } -static void omap_sysctl_write(void *opaque, hwaddr addr, - uint32_t value) +static void omap_sysctl_write(void *opaque, hwaddr addr, uint32_t value) { - struct omap_sysctl_s *s = (struct omap_sysctl_s *) opaque; + struct omap_sysctl_s *s = opaque; switch (addr) { case 0x000: /* CONTROL_REVISION */ @@ -XXX,XX +XXX,XX @@ static struct omap_sysctl_s *omap_sysctl_init(struct omap_target_agent_s *ta, /* General chip reset */ static void omap2_mpu_reset(void *opaque) { - struct omap_mpu_state_s *mpu = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *mpu = opaque; omap_dma_reset(mpu->dma); omap_prcm_reset(mpu->prcm); diff --git a/hw/arm/omap_sx1.c b/hw/arm/omap_sx1.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/omap_sx1.c +++ b/hw/arm/omap_sx1.c @@ -XXX,XX +XXX,XX @@ static uint64_t static_read(void *opaque, hwaddr offset, unsigned size) { - uint32_t *val = (uint32_t *) opaque; + uint32_t *val = opaque; uint32_t mask = (4 / size) - 1; return *val >> ((offset & mask) << 3); diff --git a/hw/arm/palm.c b/hw/arm/palm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/palm.c +++ b/hw/arm/palm.c @@ -XXX,XX +XXX,XX @@ static struct { static void palmte_button_event(void *opaque, int keycode) { - struct omap_mpu_state_s *cpu = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *cpu = opaque; if (palmte_keymap[keycode & 0x7f].row != -1) omap_mpuio_key(cpu->mpuio, diff --git a/hw/char/omap_uart.c b/hw/char/omap_uart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/omap_uart.c +++ b/hw/char/omap_uart.c @@ -XXX,XX +XXX,XX @@ struct omap_uart_s *omap_uart_init(hwaddr base, return s; } -static uint64_t omap_uart_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_uart_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_uart_s *s = (struct omap_uart_s *) opaque; + struct omap_uart_s *s = opaque; if (size == 4) { return omap_badwidth_read8(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_uart_read(void *opaque, hwaddr addr, static void omap_uart_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_uart_s *s = (struct omap_uart_s *) opaque; + struct omap_uart_s *s = opaque; if (size == 4) { omap_badwidth_write8(opaque, addr, value); diff --git a/hw/display/omap_dss.c b/hw/display/omap_dss.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_dss.c +++ b/hw/display/omap_dss.c @@ -XXX,XX +XXX,XX @@ void omap_dss_reset(struct omap_dss_s *s) static uint64_t omap_diss_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_diss_read(void *opaque, hwaddr addr, static void omap_diss_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_diss_ops = { static uint64_t omap_disc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_disc_read(void *opaque, hwaddr addr, static void omap_disc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); @@ -XXX,XX +XXX,XX @@ static void omap_rfbi_transfer_start(struct omap_dss_s *s) omap_dispc_interrupt_update(s); } -static uint64_t omap_rfbi_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_rfbi_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_rfbi_read(void *opaque, hwaddr addr, static void omap_rfbi_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dss_s *s = (struct omap_dss_s *) opaque; + struct omap_dss_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); diff --git a/hw/display/omap_lcdc.c b/hw/display/omap_lcdc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcdc.c +++ b/hw/display/omap_lcdc.c @@ -XXX,XX +XXX,XX @@ static void draw_line16_32(void *opaque, uint8_t *d, const uint8_t *s, static void omap_update_display(void *opaque) { - struct omap_lcd_panel_s *omap_lcd = (struct omap_lcd_panel_s *) opaque; + struct omap_lcd_panel_s *omap_lcd = opaque; DisplaySurface *surface; drawfn draw_line; int size, height, first, last; @@ -XXX,XX +XXX,XX @@ static void omap_lcd_update(struct omap_lcd_panel_s *s) { } } -static uint64_t omap_lcdc_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_lcdc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_lcd_panel_s *s = (struct omap_lcd_panel_s *) opaque; + struct omap_lcd_panel_s *s = opaque; switch (addr) { case 0x00: /* LCD_CONTROL */ @@ -XXX,XX +XXX,XX @@ static uint64_t omap_lcdc_read(void *opaque, hwaddr addr, static void omap_lcdc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_lcd_panel_s *s = (struct omap_lcd_panel_s *) opaque; + struct omap_lcd_panel_s *s = opaque; switch (addr) { case 0x00: /* LCD_CONTROL */ diff --git a/hw/dma/omap_dma.c b/hw/dma/omap_dma.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/omap_dma.c +++ b/hw/dma/omap_dma.c @@ -XXX,XX +XXX,XX @@ static int omap_dma_sys_read(struct omap_dma_s *s, int offset, return 0; } -static uint64_t omap_dma_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_dma_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int reg, ch; uint16_t ret; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_dma_read(void *opaque, hwaddr addr, static void omap_dma_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int reg, ch; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_dma_ops = { static void omap_dma_request(void *opaque, int drq, int req) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; /* The request pins are level triggered in QEMU. */ if (req) { if (~s->dma->drqbmp & (1ULL << drq)) { @@ -XXX,XX +XXX,XX @@ static void omap_dma_request(void *opaque, int drq, int req) /* XXX: this won't be needed once soc_dma knows about clocks. */ static void omap_dma_clk_update(void *opaque, int line, int on) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int i; s->dma->freq = omap_clk_getrate(s->clk); @@ -XXX,XX +XXX,XX @@ static void omap_dma_interrupts_4_update(struct omap_dma_s *s) static uint64_t omap_dma4_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int irqn = 0, chnum; struct omap_dma_channel_s *ch; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_dma4_read(void *opaque, hwaddr addr, static void omap_dma4_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_dma_s *s = (struct omap_dma_s *) opaque; + struct omap_dma_s *s = opaque; int chnum, irqn = 0; struct omap_dma_channel_s *ch; diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/omap_gpio.c +++ b/hw/gpio/omap_gpio.c @@ -XXX,XX +XXX,XX @@ static void omap_gpio_set(void *opaque, int line, int level) static uint64_t omap_gpio_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_gpio_s *s = (struct omap_gpio_s *) opaque; + struct omap_gpio_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; if (size != 2) { @@ -XXX,XX +XXX,XX @@ static uint64_t omap_gpio_read(void *opaque, hwaddr addr, static void omap_gpio_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_gpio_s *s = (struct omap_gpio_s *) opaque; + struct omap_gpio_s *s = opaque; int offset = addr & OMAP_MPUI_REG_MASK; uint16_t diff; int ln; @@ -XXX,XX +XXX,XX @@ static void omap2_gpio_module_reset(struct omap2_gpio_s *s) static uint32_t omap2_gpio_module_read(void *opaque, hwaddr addr) { - struct omap2_gpio_s *s = (struct omap2_gpio_s *) opaque; + struct omap2_gpio_s *s = opaque; switch (addr) { case 0x00: /* GPIO_REVISION */ @@ -XXX,XX +XXX,XX @@ static uint32_t omap2_gpio_module_read(void *opaque, hwaddr addr) static void omap2_gpio_module_write(void *opaque, hwaddr addr, uint32_t value) { - struct omap2_gpio_s *s = (struct omap2_gpio_s *) opaque; + struct omap2_gpio_s *s = opaque; uint32_t diff; int ln; @@ -XXX,XX +XXX,XX @@ static void omap2_gpif_reset(DeviceState *dev) s->gpo = 0; } -static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, unsigned size) { - struct omap2_gpif_s *s = (struct omap2_gpif_s *) opaque; + struct omap2_gpif_s *s = opaque; switch (addr) { case 0x00: /* IPGENERICOCPSPL_REVISION */ @@ -XXX,XX +XXX,XX @@ static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, static void omap2_gpif_top_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap2_gpif_s *s = (struct omap2_gpif_s *) opaque; + struct omap2_gpif_s *s = opaque; switch (addr) { case 0x00: /* IPGENERICOCPSPL_REVISION */ diff --git a/hw/intc/omap_intc.c b/hw/intc/omap_intc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/omap_intc.c +++ b/hw/intc/omap_intc.c @@ -XXX,XX +XXX,XX @@ static inline void omap_inth_update(struct omap_intr_handler_s *s, int is_fiq) static void omap_set_intr(void *opaque, int irq, int req) { - struct omap_intr_handler_s *ih = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *ih = opaque; uint32_t rise; struct omap_intr_handler_bank_s *bank = &ih->bank[irq >> 5]; @@ -XXX,XX +XXX,XX @@ static void omap_set_intr(void *opaque, int irq, int req) /* Simplified version with no edge detection */ static void omap_set_intr_noedge(void *opaque, int irq, int req) { - struct omap_intr_handler_s *ih = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *ih = opaque; uint32_t rise; struct omap_intr_handler_bank_s *bank = &ih->bank[irq >> 5]; @@ -XXX,XX +XXX,XX @@ static void omap_set_intr_noedge(void *opaque, int irq, int req) static uint64_t omap_inth_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_intr_handler_s *s = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *s = opaque; int i, offset = addr; int bank_no = offset >> 8; int line_no; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_inth_read(void *opaque, hwaddr addr, static void omap_inth_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_intr_handler_s *s = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *s = opaque; int i, offset = addr; int bank_no = offset >> 8; struct omap_intr_handler_bank_s *bank = &s->bank[bank_no]; @@ -XXX,XX +XXX,XX @@ static const TypeInfo omap_intc_info = { static uint64_t omap2_inth_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_intr_handler_s *s = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *s = opaque; int offset = addr; int bank_no, line_no; struct omap_intr_handler_bank_s *bank = NULL; @@ -XXX,XX +XXX,XX @@ static uint64_t omap2_inth_read(void *opaque, hwaddr addr, static void omap2_inth_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_intr_handler_s *s = (struct omap_intr_handler_s *) opaque; + struct omap_intr_handler_s *s = opaque; int offset = addr; int bank_no, line_no; struct omap_intr_handler_bank_s *bank = NULL; diff --git a/hw/misc/omap_gpmc.c b/hw/misc/omap_gpmc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/omap_gpmc.c +++ b/hw/misc/omap_gpmc.c @@ -XXX,XX +XXX,XX @@ static void omap_gpmc_dma_update(struct omap_gpmc_s *s, int value) static uint64_t omap_nand_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_gpmc_cs_file_s *f = (struct omap_gpmc_cs_file_s *)opaque; + struct omap_gpmc_cs_file_s *f = opaque; uint64_t v; nand_setpins(f->dev, 0, 0, 0, 1, 0); switch (omap_gpmc_devsize(f)) { @@ -XXX,XX +XXX,XX @@ static void omap_nand_setio(DeviceState *dev, uint64_t value, static void omap_nand_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_gpmc_cs_file_s *f = (struct omap_gpmc_cs_file_s *)opaque; + struct omap_gpmc_cs_file_s *f = opaque; nand_setpins(f->dev, 0, 0, 0, 1, 0); omap_nand_setio(f->dev, value, omap_gpmc_devsize(f), size); } @@ -XXX,XX +XXX,XX @@ static void fill_prefetch_fifo(struct omap_gpmc_s *s) static uint64_t omap_gpmc_prefetch_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_gpmc_s *s = (struct omap_gpmc_s *) opaque; + struct omap_gpmc_s *s = opaque; uint32_t data; if (s->prefetch.config1 & 1) { /* The TRM doesn't define the behaviour if you read from the @@ -XXX,XX +XXX,XX @@ static uint64_t omap_gpmc_prefetch_read(void *opaque, hwaddr addr, static void omap_gpmc_prefetch_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_gpmc_s *s = (struct omap_gpmc_s *) opaque; + struct omap_gpmc_s *s = opaque; int cs = prefetch_cs(s->prefetch.config1); if ((s->prefetch.config1 & 1) == 0) { /* The TRM doesn't define the behaviour of writing to the @@ -XXX,XX +XXX,XX @@ static int gpmc_wordaccess_only(hwaddr addr) static uint64_t omap_gpmc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_gpmc_s *s = (struct omap_gpmc_s *) opaque; + struct omap_gpmc_s *s = opaque; int cs; struct omap_gpmc_cs_file_s *f; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_gpmc_read(void *opaque, hwaddr addr, static void omap_gpmc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_gpmc_s *s = (struct omap_gpmc_s *) opaque; + struct omap_gpmc_s *s = opaque; int cs; struct omap_gpmc_cs_file_s *f; diff --git a/hw/misc/omap_l4.c b/hw/misc/omap_l4.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/omap_l4.c +++ b/hw/misc/omap_l4.c @@ -XXX,XX +XXX,XX @@ hwaddr omap_l4_region_size(struct omap_target_agent_s *ta, return ta->start[region].size; } -static uint64_t omap_l4ta_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_l4ta_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_target_agent_s *s = (struct omap_target_agent_s *) opaque; + struct omap_target_agent_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_l4ta_read(void *opaque, hwaddr addr, static void omap_l4ta_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_target_agent_s *s = (struct omap_target_agent_s *) opaque; + struct omap_target_agent_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); diff --git a/hw/misc/omap_sdrc.c b/hw/misc/omap_sdrc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/omap_sdrc.c +++ b/hw/misc/omap_sdrc.c @@ -XXX,XX +XXX,XX @@ void omap_sdrc_reset(struct omap_sdrc_s *s) s->config = 0x10; } -static uint64_t omap_sdrc_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_sdrc_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_sdrc_s *s = (struct omap_sdrc_s *) opaque; + struct omap_sdrc_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); @@ -XXX,XX +XXX,XX @@ static uint64_t omap_sdrc_read(void *opaque, hwaddr addr, static void omap_sdrc_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_sdrc_s *s = (struct omap_sdrc_s *) opaque; + struct omap_sdrc_s *s = opaque; if (size != 4) { omap_badwidth_write32(opaque, addr, value); diff --git a/hw/misc/omap_tap.c b/hw/misc/omap_tap.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/omap_tap.c +++ b/hw/misc/omap_tap.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/omap.h" /* TEST-Chip-level TAP */ -static uint64_t omap_tap_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_tap_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mpu_state_s *s = (struct omap_mpu_state_s *) opaque; + struct omap_mpu_state_s *s = opaque; if (size != 4) { return omap_badwidth_read32(opaque, addr); diff --git a/hw/sd/omap_mmc.c b/hw/sd/omap_mmc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/omap_mmc.c +++ b/hw/sd/omap_mmc.c @@ -XXX,XX +XXX,XX @@ void omap_mmc_reset(struct omap_mmc_s *host) device_cold_reset(DEVICE(host->card)); } -static uint64_t omap_mmc_read(void *opaque, hwaddr offset, - unsigned size) +static uint64_t omap_mmc_read(void *opaque, hwaddr offset, unsigned size) { uint16_t i; - struct omap_mmc_s *s = (struct omap_mmc_s *) opaque; + struct omap_mmc_s *s = opaque; if (size != 2) { return omap_badwidth_read16(opaque, offset); @@ -XXX,XX +XXX,XX @@ static void omap_mmc_write(void *opaque, hwaddr offset, uint64_t value, unsigned size) { int i; - struct omap_mmc_s *s = (struct omap_mmc_s *) opaque; + struct omap_mmc_s *s = opaque; if (size != 2) { omap_badwidth_write16(opaque, offset, value); @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_mmc_ops = { static void omap_mmc_cover_cb(void *opaque, int line, int level) { - struct omap_mmc_s *host = (struct omap_mmc_s *) opaque; + struct omap_mmc_s *host = opaque; if (!host->cdet_state && level) { host->status |= 0x0002; diff --git a/hw/ssi/omap_spi.c b/hw/ssi/omap_spi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ssi/omap_spi.c +++ b/hw/ssi/omap_spi.c @@ -XXX,XX +XXX,XX @@ void omap_mcspi_reset(struct omap_mcspi_s *s) omap_mcspi_interrupt_update(s); } -static uint64_t omap_mcspi_read(void *opaque, hwaddr addr, - unsigned size) +static uint64_t omap_mcspi_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_mcspi_s *s = (struct omap_mcspi_s *) opaque; + struct omap_mcspi_s *s = opaque; int ch = 0; uint32_t ret; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_mcspi_read(void *opaque, hwaddr addr, static void omap_mcspi_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_mcspi_s *s = (struct omap_mcspi_s *) opaque; + struct omap_mcspi_s *s = opaque; int ch = 0; if (size != 4) { diff --git a/hw/timer/omap_gptimer.c b/hw/timer/omap_gptimer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/omap_gptimer.c +++ b/hw/timer/omap_gptimer.c @@ -XXX,XX +XXX,XX @@ static inline void omap_gp_timer_trigger(struct omap_gp_timer_s *timer) static void omap_gp_timer_tick(void *opaque) { - struct omap_gp_timer_s *timer = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *timer = opaque; if (!timer->ar) { timer->st = 0; @@ -XXX,XX +XXX,XX @@ static void omap_gp_timer_tick(void *opaque) static void omap_gp_timer_match(void *opaque) { - struct omap_gp_timer_s *timer = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *timer = opaque; if (timer->trigger == gpt_trigger_both) omap_gp_timer_trigger(timer); @@ -XXX,XX +XXX,XX @@ static void omap_gp_timer_match(void *opaque) static void omap_gp_timer_input(void *opaque, int line, int on) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; int trigger; switch (s->capture) { @@ -XXX,XX +XXX,XX @@ static void omap_gp_timer_input(void *opaque, int line, int on) static void omap_gp_timer_clk_update(void *opaque, int line, int on) { - struct omap_gp_timer_s *timer = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *timer = opaque; omap_gp_timer_sync(timer); timer->rate = on ? omap_clk_getrate(timer->clk) : 0; @@ -XXX,XX +XXX,XX @@ void omap_gp_timer_reset(struct omap_gp_timer_s *s) static uint32_t omap_gp_timer_readw(void *opaque, hwaddr addr) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; switch (addr) { case 0x00: /* TIDR */ @@ -XXX,XX +XXX,XX @@ static uint32_t omap_gp_timer_readw(void *opaque, hwaddr addr) static uint32_t omap_gp_timer_readh(void *opaque, hwaddr addr) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; uint32_t ret; if (addr & 2) @@ -XXX,XX +XXX,XX @@ static uint32_t omap_gp_timer_readh(void *opaque, hwaddr addr) } } -static void omap_gp_timer_write(void *opaque, hwaddr addr, - uint32_t value) +static void omap_gp_timer_write(void *opaque, hwaddr addr, uint32_t value) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; switch (addr) { case 0x00: /* TIDR */ @@ -XXX,XX +XXX,XX @@ static void omap_gp_timer_write(void *opaque, hwaddr addr, } } -static void omap_gp_timer_writeh(void *opaque, hwaddr addr, - uint32_t value) +static void omap_gp_timer_writeh(void *opaque, hwaddr addr, uint32_t value) { - struct omap_gp_timer_s *s = (struct omap_gp_timer_s *) opaque; + struct omap_gp_timer_s *s = opaque; if (addr & 2) omap_gp_timer_write(opaque, addr, (value << 16) | s->writeh); diff --git a/hw/timer/omap_synctimer.c b/hw/timer/omap_synctimer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/omap_synctimer.c +++ b/hw/timer/omap_synctimer.c @@ -XXX,XX +XXX,XX @@ void omap_synctimer_reset(struct omap_synctimer_s *s) static uint32_t omap_synctimer_readw(void *opaque, hwaddr addr) { - struct omap_synctimer_s *s = (struct omap_synctimer_s *) opaque; + struct omap_synctimer_s *s = opaque; switch (addr) { case 0x00: /* 32KSYNCNT_REV */ @@ -XXX,XX +XXX,XX @@ static uint32_t omap_synctimer_readw(void *opaque, hwaddr addr) static uint32_t omap_synctimer_readh(void *opaque, hwaddr addr) { - struct omap_synctimer_s *s = (struct omap_synctimer_s *) opaque; + struct omap_synctimer_s *s = opaque; uint32_t ret; if (addr & 2) -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Following docs/devel/style.rst guidelines, rename omap_gpif_s -> Omap1GpioState. This also remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-5-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/omap.h | 6 +++--- hw/gpio/omap_gpio.c | 16 ++++++++-------- 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ void omap_i2c_set_fclk(OMAPI2CState *i2c, omap_clk clk); /* omap_gpio.c */ #define TYPE_OMAP1_GPIO "omap-gpio" -DECLARE_INSTANCE_CHECKER(struct omap_gpif_s, OMAP1_GPIO, +typedef struct Omap1GpioState Omap1GpioState; +DECLARE_INSTANCE_CHECKER(Omap1GpioState, OMAP1_GPIO, TYPE_OMAP1_GPIO) #define TYPE_OMAP2_GPIO "omap2-gpio" DECLARE_INSTANCE_CHECKER(struct omap2_gpif_s, OMAP2_GPIO, TYPE_OMAP2_GPIO) -typedef struct omap_gpif_s omap_gpif; typedef struct omap2_gpif_s omap2_gpif; /* TODO: clock framework (see above) */ -void omap_gpio_set_clk(omap_gpif *gpio, omap_clk clk); +void omap_gpio_set_clk(Omap1GpioState *gpio, omap_clk clk); void omap2_gpio_set_iclk(omap2_gpif *gpio, omap_clk clk); void omap2_gpio_set_fclk(omap2_gpif *gpio, uint8_t i, omap_clk clk); diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/omap_gpio.c +++ b/hw/gpio/omap_gpio.c @@ -XXX,XX +XXX,XX @@ struct omap_gpio_s { uint16_t pins; }; -struct omap_gpif_s { +struct Omap1GpioState { SysBusDevice parent_obj; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ struct omap_gpif_s { /* General-Purpose I/O of OMAP1 */ static void omap_gpio_set(void *opaque, int line, int level) { - struct omap_gpif_s *p = opaque; + Omap1GpioState *p = opaque; struct omap_gpio_s *s = &p->omap1; uint16_t prev = s->inputs; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap2_gpio_module_ops = { static void omap_gpif_reset(DeviceState *dev) { - struct omap_gpif_s *s = OMAP1_GPIO(dev); + Omap1GpioState *s = OMAP1_GPIO(dev); omap_gpio_reset(&s->omap1); } @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap2_gpif_top_ops = { static void omap_gpio_init(Object *obj) { DeviceState *dev = DEVICE(obj); - struct omap_gpif_s *s = OMAP1_GPIO(obj); + Omap1GpioState *s = OMAP1_GPIO(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); qdev_init_gpio_in(dev, omap_gpio_set, 16); @@ -XXX,XX +XXX,XX @@ static void omap_gpio_init(Object *obj) static void omap_gpio_realize(DeviceState *dev, Error **errp) { - struct omap_gpif_s *s = OMAP1_GPIO(dev); + Omap1GpioState *s = OMAP1_GPIO(dev); if (!s->clk) { error_setg(errp, "omap-gpio: clk not connected"); @@ -XXX,XX +XXX,XX @@ static void omap2_gpio_realize(DeviceState *dev, Error **errp) } } -void omap_gpio_set_clk(omap_gpif *gpio, omap_clk clk) +void omap_gpio_set_clk(Omap1GpioState *gpio, omap_clk clk) { gpio->clk = clk; } static Property omap_gpio_properties[] = { - DEFINE_PROP_INT32("mpu_model", struct omap_gpif_s, mpu_model, 0), + DEFINE_PROP_INT32("mpu_model", Omap1GpioState, mpu_model, 0), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static void omap_gpio_class_init(ObjectClass *klass, void *data) static const TypeInfo omap_gpio_info = { .name = TYPE_OMAP1_GPIO, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(struct omap_gpif_s), + .instance_size = sizeof(Omap1GpioState), .instance_init = omap_gpio_init, .class_init = omap_gpio_class_init, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Following docs/devel/style.rst guidelines, rename omap2_gpif_s -> Omap2GpioState. This also remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-6-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/omap.h | 9 ++++----- hw/gpio/omap_gpio.c | 20 ++++++++++---------- 2 files changed, 14 insertions(+), 15 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ DECLARE_INSTANCE_CHECKER(Omap1GpioState, OMAP1_GPIO, TYPE_OMAP1_GPIO) #define TYPE_OMAP2_GPIO "omap2-gpio" -DECLARE_INSTANCE_CHECKER(struct omap2_gpif_s, OMAP2_GPIO, +typedef struct Omap2GpioState Omap2GpioState; +DECLARE_INSTANCE_CHECKER(Omap2GpioState, OMAP2_GPIO, TYPE_OMAP2_GPIO) -typedef struct omap2_gpif_s omap2_gpif; - /* TODO: clock framework (see above) */ void omap_gpio_set_clk(Omap1GpioState *gpio, omap_clk clk); -void omap2_gpio_set_iclk(omap2_gpif *gpio, omap_clk clk); -void omap2_gpio_set_fclk(omap2_gpif *gpio, uint8_t i, omap_clk clk); +void omap2_gpio_set_iclk(Omap2GpioState *gpio, omap_clk clk); +void omap2_gpio_set_fclk(Omap2GpioState *gpio, uint8_t i, omap_clk clk); /* OMAP2 l4 Interconnect */ struct omap_l4_s; diff --git a/hw/gpio/omap_gpio.c b/hw/gpio/omap_gpio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/omap_gpio.c +++ b/hw/gpio/omap_gpio.c @@ -XXX,XX +XXX,XX @@ struct omap2_gpio_s { uint8_t delay; }; -struct omap2_gpif_s { +struct Omap2GpioState { SysBusDevice parent_obj; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ static inline void omap2_gpio_module_int(struct omap2_gpio_s *s, int line) static void omap2_gpio_set(void *opaque, int line, int level) { - struct omap2_gpif_s *p = opaque; + Omap2GpioState *p = opaque; struct omap2_gpio_s *s = &p->modules[line >> 5]; line &= 31; @@ -XXX,XX +XXX,XX @@ static void omap_gpif_reset(DeviceState *dev) static void omap2_gpif_reset(DeviceState *dev) { - struct omap2_gpif_s *s = OMAP2_GPIO(dev); + Omap2GpioState *s = OMAP2_GPIO(dev); int i; for (i = 0; i < s->modulecount; i++) { @@ -XXX,XX +XXX,XX @@ static void omap2_gpif_reset(DeviceState *dev) static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, unsigned size) { - struct omap2_gpif_s *s = opaque; + Omap2GpioState *s = opaque; switch (addr) { case 0x00: /* IPGENERICOCPSPL_REVISION */ @@ -XXX,XX +XXX,XX @@ static uint64_t omap2_gpif_top_read(void *opaque, hwaddr addr, unsigned size) static void omap2_gpif_top_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap2_gpif_s *s = opaque; + Omap2GpioState *s = opaque; switch (addr) { case 0x00: /* IPGENERICOCPSPL_REVISION */ @@ -XXX,XX +XXX,XX @@ static void omap_gpio_realize(DeviceState *dev, Error **errp) static void omap2_gpio_realize(DeviceState *dev, Error **errp) { - struct omap2_gpif_s *s = OMAP2_GPIO(dev); + Omap2GpioState *s = OMAP2_GPIO(dev); SysBusDevice *sbd = SYS_BUS_DEVICE(dev); int i; @@ -XXX,XX +XXX,XX @@ static const TypeInfo omap_gpio_info = { .class_init = omap_gpio_class_init, }; -void omap2_gpio_set_iclk(omap2_gpif *gpio, omap_clk clk) +void omap2_gpio_set_iclk(Omap2GpioState *gpio, omap_clk clk) { gpio->iclk = clk; } -void omap2_gpio_set_fclk(omap2_gpif *gpio, uint8_t i, omap_clk clk) +void omap2_gpio_set_fclk(Omap2GpioState *gpio, uint8_t i, omap_clk clk) { assert(i <= 5); gpio->fclk[i] = clk; } static Property omap2_gpio_properties[] = { - DEFINE_PROP_INT32("mpu_model", struct omap2_gpif_s, mpu_model, 0), + DEFINE_PROP_INT32("mpu_model", Omap2GpioState, mpu_model, 0), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static void omap2_gpio_class_init(ObjectClass *klass, void *data) static const TypeInfo omap2_gpio_info = { .name = TYPE_OMAP2_GPIO, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(struct omap2_gpif_s), + .instance_size = sizeof(Omap2GpioState), .class_init = omap2_gpio_class_init, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Following docs/devel/style.rst guidelines, rename omap_intr_handler_s -> OMAPIntcState. This also remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-7-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/omap.h | 9 ++++----- hw/intc/omap_intc.c | 38 +++++++++++++++++++------------------- 2 files changed, 23 insertions(+), 24 deletions(-) diff --git a/include/hw/arm/omap.h b/include/hw/arm/omap.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/omap.h +++ b/include/hw/arm/omap.h @@ -XXX,XX +XXX,XX @@ void omap_clk_reparent(omap_clk clk, omap_clk parent); /* omap_intc.c */ #define TYPE_OMAP_INTC "common-omap-intc" -typedef struct omap_intr_handler_s omap_intr_handler; -DECLARE_INSTANCE_CHECKER(omap_intr_handler, OMAP_INTC, - TYPE_OMAP_INTC) +typedef struct OMAPIntcState OMAPIntcState; +DECLARE_INSTANCE_CHECKER(OMAPIntcState, OMAP_INTC, TYPE_OMAP_INTC) /* @@ -XXX,XX +XXX,XX @@ DECLARE_INSTANCE_CHECKER(omap_intr_handler, OMAP_INTC, * (ie the struct omap_mpu_state_s*) to do the clockname to pointer * translation.) */ -void omap_intc_set_iclk(omap_intr_handler *intc, omap_clk clk); -void omap_intc_set_fclk(omap_intr_handler *intc, omap_clk clk); +void omap_intc_set_iclk(OMAPIntcState *intc, omap_clk clk); +void omap_intc_set_fclk(OMAPIntcState *intc, omap_clk clk); /* omap_i2c.c */ #define TYPE_OMAP_I2C "omap_i2c" diff --git a/hw/intc/omap_intc.c b/hw/intc/omap_intc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/omap_intc.c +++ b/hw/intc/omap_intc.c @@ -XXX,XX +XXX,XX @@ struct omap_intr_handler_bank_s { unsigned char priority[32]; }; -struct omap_intr_handler_s { +struct OMAPIntcState { SysBusDevice parent_obj; qemu_irq *pins; @@ -XXX,XX +XXX,XX @@ struct omap_intr_handler_s { struct omap_intr_handler_bank_s bank[3]; }; -static void omap_inth_sir_update(struct omap_intr_handler_s *s, int is_fiq) +static void omap_inth_sir_update(OMAPIntcState *s, int is_fiq) { int i, j, sir_intr, p_intr, p; uint32_t level; @@ -XXX,XX +XXX,XX @@ static void omap_inth_sir_update(struct omap_intr_handler_s *s, int is_fiq) s->sir_intr[is_fiq] = sir_intr; } -static inline void omap_inth_update(struct omap_intr_handler_s *s, int is_fiq) +static inline void omap_inth_update(OMAPIntcState *s, int is_fiq) { int i; uint32_t has_intr = 0; @@ -XXX,XX +XXX,XX @@ static inline void omap_inth_update(struct omap_intr_handler_s *s, int is_fiq) static void omap_set_intr(void *opaque, int irq, int req) { - struct omap_intr_handler_s *ih = opaque; + OMAPIntcState *ih = opaque; uint32_t rise; struct omap_intr_handler_bank_s *bank = &ih->bank[irq >> 5]; @@ -XXX,XX +XXX,XX @@ static void omap_set_intr(void *opaque, int irq, int req) /* Simplified version with no edge detection */ static void omap_set_intr_noedge(void *opaque, int irq, int req) { - struct omap_intr_handler_s *ih = opaque; + OMAPIntcState *ih = opaque; uint32_t rise; struct omap_intr_handler_bank_s *bank = &ih->bank[irq >> 5]; @@ -XXX,XX +XXX,XX @@ static void omap_set_intr_noedge(void *opaque, int irq, int req) static uint64_t omap_inth_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_intr_handler_s *s = opaque; + OMAPIntcState *s = opaque; int i, offset = addr; int bank_no = offset >> 8; int line_no; @@ -XXX,XX +XXX,XX @@ static uint64_t omap_inth_read(void *opaque, hwaddr addr, static void omap_inth_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_intr_handler_s *s = opaque; + OMAPIntcState *s = opaque; int i, offset = addr; int bank_no = offset >> 8; struct omap_intr_handler_bank_s *bank = &s->bank[bank_no]; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap_inth_mem_ops = { static void omap_inth_reset(DeviceState *dev) { - struct omap_intr_handler_s *s = OMAP_INTC(dev); + OMAPIntcState *s = OMAP_INTC(dev); int i; for (i = 0; i < s->nbanks; ++i){ @@ -XXX,XX +XXX,XX @@ static void omap_inth_reset(DeviceState *dev) static void omap_intc_init(Object *obj) { DeviceState *dev = DEVICE(obj); - struct omap_intr_handler_s *s = OMAP_INTC(obj); + OMAPIntcState *s = OMAP_INTC(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); s->nbanks = 1; @@ -XXX,XX +XXX,XX @@ static void omap_intc_init(Object *obj) static void omap_intc_realize(DeviceState *dev, Error **errp) { - struct omap_intr_handler_s *s = OMAP_INTC(dev); + OMAPIntcState *s = OMAP_INTC(dev); if (!s->iclk) { error_setg(errp, "omap-intc: clk not connected"); } } -void omap_intc_set_iclk(omap_intr_handler *intc, omap_clk clk) +void omap_intc_set_iclk(OMAPIntcState *intc, omap_clk clk) { intc->iclk = clk; } -void omap_intc_set_fclk(omap_intr_handler *intc, omap_clk clk) +void omap_intc_set_fclk(OMAPIntcState *intc, omap_clk clk) { intc->fclk = clk; } static Property omap_intc_properties[] = { - DEFINE_PROP_UINT32("size", struct omap_intr_handler_s, size, 0x100), + DEFINE_PROP_UINT32("size", OMAPIntcState, size, 0x100), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static const TypeInfo omap_intc_info = { static uint64_t omap2_inth_read(void *opaque, hwaddr addr, unsigned size) { - struct omap_intr_handler_s *s = opaque; + OMAPIntcState *s = opaque; int offset = addr; int bank_no, line_no; struct omap_intr_handler_bank_s *bank = NULL; @@ -XXX,XX +XXX,XX @@ static uint64_t omap2_inth_read(void *opaque, hwaddr addr, static void omap2_inth_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { - struct omap_intr_handler_s *s = opaque; + OMAPIntcState *s = opaque; int offset = addr; int bank_no, line_no; struct omap_intr_handler_bank_s *bank = NULL; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps omap2_inth_mem_ops = { static void omap2_intc_init(Object *obj) { DeviceState *dev = DEVICE(obj); - struct omap_intr_handler_s *s = OMAP_INTC(obj); + OMAPIntcState *s = OMAP_INTC(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); s->level_only = 1; @@ -XXX,XX +XXX,XX @@ static void omap2_intc_init(Object *obj) static void omap2_intc_realize(DeviceState *dev, Error **errp) { - struct omap_intr_handler_s *s = OMAP_INTC(dev); + OMAPIntcState *s = OMAP_INTC(dev); if (!s->iclk) { error_setg(errp, "omap2-intc: iclk not connected"); @@ -XXX,XX +XXX,XX @@ static void omap2_intc_realize(DeviceState *dev, Error **errp) } static Property omap2_intc_properties[] = { - DEFINE_PROP_UINT8("revision", struct omap_intr_handler_s, + DEFINE_PROP_UINT8("revision", OMAPIntcState, revision, 0x21), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static const TypeInfo omap2_intc_info = { static const TypeInfo omap_intc_type_info = { .name = TYPE_OMAP_INTC, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(omap_intr_handler), + .instance_size = sizeof(OMAPIntcState), .abstract = true, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-8-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_update(stellaris_adc_state *s) static void stellaris_adc_trigger(void *opaque, int irq, int level) { - stellaris_adc_state *s = (stellaris_adc_state *)opaque; + stellaris_adc_state *s = opaque; int n; for (n = 0; n < 4; n++) { @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_reset(stellaris_adc_state *s) static uint64_t stellaris_adc_read(void *opaque, hwaddr offset, unsigned size) { - stellaris_adc_state *s = (stellaris_adc_state *)opaque; + stellaris_adc_state *s = opaque; /* TODO: Implement this. */ if (offset >= 0x40 && offset < 0xc0) { @@ -XXX,XX +XXX,XX @@ static uint64_t stellaris_adc_read(void *opaque, hwaddr offset, static void stellaris_adc_write(void *opaque, hwaddr offset, uint64_t value, unsigned size) { - stellaris_adc_state *s = (stellaris_adc_state *)opaque; + stellaris_adc_state *s = opaque; /* TODO: Implement this. */ if (offset >= 0x40 && offset < 0xc0) { -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Following docs/devel/style.rst guidelines, rename stellaris_adc_state -> StellarisADCState. This also remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-9-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 73 +++++++++++++++++++++++----------------------- 1 file changed, 36 insertions(+), 37 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_i2c_init(Object *obj) #define STELLARIS_ADC_FIFO_FULL 0x1000 #define TYPE_STELLARIS_ADC "stellaris-adc" -typedef struct StellarisADCState stellaris_adc_state; -DECLARE_INSTANCE_CHECKER(stellaris_adc_state, STELLARIS_ADC, - TYPE_STELLARIS_ADC) +typedef struct StellarisADCState StellarisADCState; +DECLARE_INSTANCE_CHECKER(StellarisADCState, STELLARIS_ADC, TYPE_STELLARIS_ADC) struct StellarisADCState { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct StellarisADCState { qemu_irq irq[4]; }; -static uint32_t stellaris_adc_fifo_read(stellaris_adc_state *s, int n) +static uint32_t stellaris_adc_fifo_read(StellarisADCState *s, int n) { int tail; @@ -XXX,XX +XXX,XX @@ static uint32_t stellaris_adc_fifo_read(stellaris_adc_state *s, int n) return s->fifo[n].data[tail]; } -static void stellaris_adc_fifo_write(stellaris_adc_state *s, int n, +static void stellaris_adc_fifo_write(StellarisADCState *s, int n, uint32_t value) { int head; @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_fifo_write(stellaris_adc_state *s, int n, s->fifo[n].state |= STELLARIS_ADC_FIFO_FULL; } -static void stellaris_adc_update(stellaris_adc_state *s) +static void stellaris_adc_update(StellarisADCState *s) { int level; int n; @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_update(stellaris_adc_state *s) static void stellaris_adc_trigger(void *opaque, int irq, int level) { - stellaris_adc_state *s = opaque; + StellarisADCState *s = opaque; int n; for (n = 0; n < 4; n++) { @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_trigger(void *opaque, int irq, int level) } } -static void stellaris_adc_reset(stellaris_adc_state *s) +static void stellaris_adc_reset(StellarisADCState *s) { int n; @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_reset(stellaris_adc_state *s) static uint64_t stellaris_adc_read(void *opaque, hwaddr offset, unsigned size) { - stellaris_adc_state *s = opaque; + StellarisADCState *s = opaque; /* TODO: Implement this. */ if (offset >= 0x40 && offset < 0xc0) { @@ -XXX,XX +XXX,XX @@ static uint64_t stellaris_adc_read(void *opaque, hwaddr offset, static void stellaris_adc_write(void *opaque, hwaddr offset, uint64_t value, unsigned size) { - stellaris_adc_state *s = opaque; + StellarisADCState *s = opaque; /* TODO: Implement this. */ if (offset >= 0x40 && offset < 0xc0) { @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_stellaris_adc = { .version_id = 1, .minimum_version_id = 1, .fields = (VMStateField[]) { - VMSTATE_UINT32(actss, stellaris_adc_state), - VMSTATE_UINT32(ris, stellaris_adc_state), - VMSTATE_UINT32(im, stellaris_adc_state), - VMSTATE_UINT32(emux, stellaris_adc_state), - VMSTATE_UINT32(ostat, stellaris_adc_state), - VMSTATE_UINT32(ustat, stellaris_adc_state), - VMSTATE_UINT32(sspri, stellaris_adc_state), - VMSTATE_UINT32(sac, stellaris_adc_state), - VMSTATE_UINT32(fifo[0].state, stellaris_adc_state), - VMSTATE_UINT32_ARRAY(fifo[0].data, stellaris_adc_state, 16), - VMSTATE_UINT32(ssmux[0], stellaris_adc_state), - VMSTATE_UINT32(ssctl[0], stellaris_adc_state), - VMSTATE_UINT32(fifo[1].state, stellaris_adc_state), - VMSTATE_UINT32_ARRAY(fifo[1].data, stellaris_adc_state, 16), - VMSTATE_UINT32(ssmux[1], stellaris_adc_state), - VMSTATE_UINT32(ssctl[1], stellaris_adc_state), - VMSTATE_UINT32(fifo[2].state, stellaris_adc_state), - VMSTATE_UINT32_ARRAY(fifo[2].data, stellaris_adc_state, 16), - VMSTATE_UINT32(ssmux[2], stellaris_adc_state), - VMSTATE_UINT32(ssctl[2], stellaris_adc_state), - VMSTATE_UINT32(fifo[3].state, stellaris_adc_state), - VMSTATE_UINT32_ARRAY(fifo[3].data, stellaris_adc_state, 16), - VMSTATE_UINT32(ssmux[3], stellaris_adc_state), - VMSTATE_UINT32(ssctl[3], stellaris_adc_state), - VMSTATE_UINT32(noise, stellaris_adc_state), + VMSTATE_UINT32(actss, StellarisADCState), + VMSTATE_UINT32(ris, StellarisADCState), + VMSTATE_UINT32(im, StellarisADCState), + VMSTATE_UINT32(emux, StellarisADCState), + VMSTATE_UINT32(ostat, StellarisADCState), + VMSTATE_UINT32(ustat, StellarisADCState), + VMSTATE_UINT32(sspri, StellarisADCState), + VMSTATE_UINT32(sac, StellarisADCState), + VMSTATE_UINT32(fifo[0].state, StellarisADCState), + VMSTATE_UINT32_ARRAY(fifo[0].data, StellarisADCState, 16), + VMSTATE_UINT32(ssmux[0], StellarisADCState), + VMSTATE_UINT32(ssctl[0], StellarisADCState), + VMSTATE_UINT32(fifo[1].state, StellarisADCState), + VMSTATE_UINT32_ARRAY(fifo[1].data, StellarisADCState, 16), + VMSTATE_UINT32(ssmux[1], StellarisADCState), + VMSTATE_UINT32(ssctl[1], StellarisADCState), + VMSTATE_UINT32(fifo[2].state, StellarisADCState), + VMSTATE_UINT32_ARRAY(fifo[2].data, StellarisADCState, 16), + VMSTATE_UINT32(ssmux[2], StellarisADCState), + VMSTATE_UINT32(ssctl[2], StellarisADCState), + VMSTATE_UINT32(fifo[3].state, StellarisADCState), + VMSTATE_UINT32_ARRAY(fifo[3].data, StellarisADCState, 16), + VMSTATE_UINT32(ssmux[3], StellarisADCState), + VMSTATE_UINT32(ssctl[3], StellarisADCState), + VMSTATE_UINT32(noise, StellarisADCState), VMSTATE_END_OF_LIST() } }; @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_stellaris_adc = { static void stellaris_adc_init(Object *obj) { DeviceState *dev = DEVICE(obj); - stellaris_adc_state *s = STELLARIS_ADC(obj); + StellarisADCState *s = STELLARIS_ADC(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); int n; @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_class_init(ObjectClass *klass, void *data) static const TypeInfo stellaris_adc_info = { .name = TYPE_STELLARIS_ADC, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(stellaris_adc_state), + .instance_size = sizeof(StellarisADCState), .instance_init = stellaris_adc_init, .class_init = stellaris_adc_class_init, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> The typedef and definitions are generated by the OBJECT_DECLARE_TYPE macro in "hw/arm/bcm2836.h": 20 #define TYPE_BCM283X "bcm283x" 21 OBJECT_DECLARE_TYPE(BCM283XState, BCM283XClass, BCM283X) The script ran in commit a489d1951c ("Use OBJECT_DECLARE_TYPE when possible") missed them because they are declared in a different file unit. Remove them. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-10-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/bcm2836.c | 9 ++------- 1 file changed, 2 insertions(+), 7 deletions(-) diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2836.c +++ b/hw/arm/bcm2836.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/raspi_platform.h" #include "hw/sysbus.h" -typedef struct BCM283XClass { +struct BCM283XClass { /*< private >*/ DeviceClass parent_class; /*< public >*/ @@ -XXX,XX +XXX,XX @@ typedef struct BCM283XClass { hwaddr peri_base; /* Peripheral base address seen by the CPU */ hwaddr ctrl_base; /* Interrupt controller and mailboxes etc. */ int clusterid; -} BCM283XClass; - -#define BCM283X_CLASS(klass) \ - OBJECT_CLASS_CHECK(BCM283XClass, (klass), TYPE_BCM283X) -#define BCM283X_GET_CLASS(obj) \ - OBJECT_GET_CLASS(BCM283XClass, (obj), TYPE_BCM283X) +}; static Property bcm2836_enabled_cores_property = DEFINE_PROP_UINT32("enabled-cpus", BCM283XState, enabled_cpus, 0); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> NPCM7XX models have been commited after the conversion from commit 8063396bf3 ("Use OBJECT_DECLARE_SIMPLE_TYPE when possible"). Manually convert them. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-11-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/adc/npcm7xx_adc.h | 7 +++---- include/hw/arm/npcm7xx.h | 18 ++++++------------ include/hw/i2c/npcm7xx_smbus.h | 7 +++---- include/hw/misc/npcm7xx_clk.h | 2 +- include/hw/misc/npcm7xx_gcr.h | 6 +++--- include/hw/misc/npcm7xx_mft.h | 7 +++---- include/hw/misc/npcm7xx_pwm.h | 3 +-- include/hw/misc/npcm7xx_rng.h | 6 +++--- include/hw/net/npcm7xx_emc.h | 5 +---- include/hw/sd/npcm7xx_sdhci.h | 4 ++-- 10 files changed, 26 insertions(+), 39 deletions(-) diff --git a/include/hw/adc/npcm7xx_adc.h b/include/hw/adc/npcm7xx_adc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/adc/npcm7xx_adc.h +++ b/include/hw/adc/npcm7xx_adc.h @@ -XXX,XX +XXX,XX @@ * @iref: The internal reference voltage, initialized at launch time. * @rv: The calibrated output values of 0.5V and 1.5V for the ADC. */ -typedef struct { +struct NPCM7xxADCState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct { uint32_t iref; uint16_t calibration_r_values[NPCM7XX_ADC_NUM_CALIB]; -} NPCM7xxADCState; +}; #define TYPE_NPCM7XX_ADC "npcm7xx-adc" -#define NPCM7XX_ADC(obj) \ - OBJECT_CHECK(NPCM7xxADCState, (obj), TYPE_NPCM7XX_ADC) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxADCState, NPCM7XX_ADC) #endif /* NPCM7XX_ADC_H */ diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #define NPCM7XX_NR_PWM_MODULES 2 -typedef struct NPCM7xxMachine { +struct NPCM7xxMachine { MachineState parent; /* * PWM fan splitter. each splitter connects to one PWM output and @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxMachine { */ SplitIRQ fan_splitter[NPCM7XX_NR_PWM_MODULES * NPCM7XX_PWM_PER_MODULE]; -} NPCM7xxMachine; +}; #define TYPE_NPCM7XX_MACHINE MACHINE_TYPE_NAME("npcm7xx") -#define NPCM7XX_MACHINE(obj) \ - OBJECT_CHECK(NPCM7xxMachine, (obj), TYPE_NPCM7XX_MACHINE) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxMachine, NPCM7XX_MACHINE) typedef struct NPCM7xxMachineClass { MachineClass parent; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxMachineClass { #define NPCM7XX_MACHINE_GET_CLASS(obj) \ OBJECT_GET_CLASS(NPCM7xxMachineClass, (obj), TYPE_NPCM7XX_MACHINE) -typedef struct NPCM7xxState { +struct NPCM7xxState { DeviceState parent; ARMCPU cpu[NPCM7XX_MAX_NUM_CPUS]; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { NPCM7xxFIUState fiu[2]; NPCM7xxEMCState emc[2]; NPCM7xxSDHCIState mmc; -} NPCM7xxState; +}; #define TYPE_NPCM7XX "npcm7xx" -#define NPCM7XX(obj) OBJECT_CHECK(NPCM7xxState, (obj), TYPE_NPCM7XX) +OBJECT_DECLARE_TYPE(NPCM7xxState, NPCM7xxClass, NPCM7XX) #define TYPE_NPCM730 "npcm730" #define TYPE_NPCM750 "npcm750" @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxClass { uint32_t num_cpus; } NPCM7xxClass; -#define NPCM7XX_CLASS(klass) \ - OBJECT_CLASS_CHECK(NPCM7xxClass, (klass), TYPE_NPCM7XX) -#define NPCM7XX_GET_CLASS(obj) \ - OBJECT_GET_CLASS(NPCM7xxClass, (obj), TYPE_NPCM7XX) - /** * npcm7xx_load_kernel - Loads memory with everything needed to boot * @machine - The machine containing the SoC to be booted. diff --git a/include/hw/i2c/npcm7xx_smbus.h b/include/hw/i2c/npcm7xx_smbus.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/i2c/npcm7xx_smbus.h +++ b/include/hw/i2c/npcm7xx_smbus.h @@ -XXX,XX +XXX,XX @@ typedef enum NPCM7xxSMBusStatus { * @rx_cur: The current position of rx_fifo. * @status: The current status of the SMBus. */ -typedef struct NPCM7xxSMBusState { +struct NPCM7xxSMBusState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxSMBusState { uint8_t rx_cur; NPCM7xxSMBusStatus status; -} NPCM7xxSMBusState; +}; #define TYPE_NPCM7XX_SMBUS "npcm7xx-smbus" -#define NPCM7XX_SMBUS(obj) OBJECT_CHECK(NPCM7xxSMBusState, (obj), \ - TYPE_NPCM7XX_SMBUS) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxSMBusState, NPCM7XX_SMBUS) #endif /* NPCM7XX_SMBUS_H */ diff --git a/include/hw/misc/npcm7xx_clk.h b/include/hw/misc/npcm7xx_clk.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_clk.h +++ b/include/hw/misc/npcm7xx_clk.h @@ -XXX,XX +XXX,XX @@ struct NPCM7xxCLKState { }; #define TYPE_NPCM7XX_CLK "npcm7xx-clk" -#define NPCM7XX_CLK(obj) OBJECT_CHECK(NPCM7xxCLKState, (obj), TYPE_NPCM7XX_CLK) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxCLKState, NPCM7XX_CLK) #endif /* NPCM7XX_CLK_H */ diff --git a/include/hw/misc/npcm7xx_gcr.h b/include/hw/misc/npcm7xx_gcr.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_gcr.h +++ b/include/hw/misc/npcm7xx_gcr.h @@ -XXX,XX +XXX,XX @@ */ #define NPCM7XX_GCR_NR_REGS (0x148 / sizeof(uint32_t)) -typedef struct NPCM7xxGCRState { +struct NPCM7xxGCRState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxGCRState { uint32_t reset_pwron; uint32_t reset_mdlr; uint32_t reset_intcr3; -} NPCM7xxGCRState; +}; #define TYPE_NPCM7XX_GCR "npcm7xx-gcr" -#define NPCM7XX_GCR(obj) OBJECT_CHECK(NPCM7xxGCRState, (obj), TYPE_NPCM7XX_GCR) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxGCRState, NPCM7XX_GCR) #endif /* NPCM7XX_GCR_H */ diff --git a/include/hw/misc/npcm7xx_mft.h b/include/hw/misc/npcm7xx_mft.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_mft.h +++ b/include/hw/misc/npcm7xx_mft.h @@ -XXX,XX +XXX,XX @@ * @max_rpm: The maximum rpm for fans. Order: A0, B0, A1, B1. * @duty: The duty cycles for fans, relative to NPCM7XX_PWM_MAX_DUTY. */ -typedef struct NPCM7xxMFTState { +struct NPCM7xxMFTState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxMFTState { uint32_t max_rpm[NPCM7XX_MFT_FANIN_COUNT]; uint32_t duty[NPCM7XX_MFT_FANIN_COUNT]; -} NPCM7xxMFTState; +}; #define TYPE_NPCM7XX_MFT "npcm7xx-mft" -#define NPCM7XX_MFT(obj) \ - OBJECT_CHECK(NPCM7xxMFTState, (obj), TYPE_NPCM7XX_MFT) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxMFTState, NPCM7XX_MFT) #endif /* NPCM7XX_MFT_H */ diff --git a/include/hw/misc/npcm7xx_pwm.h b/include/hw/misc/npcm7xx_pwm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_pwm.h +++ b/include/hw/misc/npcm7xx_pwm.h @@ -XXX,XX +XXX,XX @@ struct NPCM7xxPWMState { }; #define TYPE_NPCM7XX_PWM "npcm7xx-pwm" -#define NPCM7XX_PWM(obj) \ - OBJECT_CHECK(NPCM7xxPWMState, (obj), TYPE_NPCM7XX_PWM) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxPWMState, NPCM7XX_PWM) #endif /* NPCM7XX_PWM_H */ diff --git a/include/hw/misc/npcm7xx_rng.h b/include/hw/misc/npcm7xx_rng.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_rng.h +++ b/include/hw/misc/npcm7xx_rng.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" -typedef struct NPCM7xxRNGState { +struct NPCM7xxRNGState { SysBusDevice parent; MemoryRegion iomem; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxRNGState { uint8_t rngcs; uint8_t rngd; uint8_t rngmode; -} NPCM7xxRNGState; +}; #define TYPE_NPCM7XX_RNG "npcm7xx-rng" -#define NPCM7XX_RNG(obj) OBJECT_CHECK(NPCM7xxRNGState, (obj), TYPE_NPCM7XX_RNG) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxRNGState, NPCM7XX_RNG) #endif /* NPCM7XX_RNG_H */ diff --git a/include/hw/net/npcm7xx_emc.h b/include/hw/net/npcm7xx_emc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/net/npcm7xx_emc.h +++ b/include/hw/net/npcm7xx_emc.h @@ -XXX,XX +XXX,XX @@ struct NPCM7xxEMCState { bool rx_active; }; -typedef struct NPCM7xxEMCState NPCM7xxEMCState; - #define TYPE_NPCM7XX_EMC "npcm7xx-emc" -#define NPCM7XX_EMC(obj) \ - OBJECT_CHECK(NPCM7xxEMCState, (obj), TYPE_NPCM7XX_EMC) +OBJECT_DECLARE_SIMPLE_TYPE(NPCM7xxEMCState, NPCM7XX_EMC) #endif /* NPCM7XX_EMC_H */ diff --git a/include/hw/sd/npcm7xx_sdhci.h b/include/hw/sd/npcm7xx_sdhci.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/sd/npcm7xx_sdhci.h +++ b/include/hw/sd/npcm7xx_sdhci.h @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxRegs { uint32_t boottoctrl; } NPCM7xxRegisters; -typedef struct NPCM7xxSDHCIState { +struct NPCM7xxSDHCIState { SysBusDevice parent; MemoryRegion container; @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxSDHCIState { NPCM7xxRegisters regs; SDHCIState sdhci; -} NPCM7xxSDHCIState; +}; #endif /* NPCM7XX_SDHCI_H */ -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> The structure is named SECUREECState. Rename the type accordingly. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-12-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/sbsa_ec.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/hw/misc/sbsa_ec.c b/hw/misc/sbsa_ec.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/sbsa_ec.c +++ b/hw/misc/sbsa_ec.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "sysemu/runstate.h" -typedef struct { +typedef struct SECUREECState { SysBusDevice parent_obj; MemoryRegion iomem; } SECUREECState; -#define TYPE_SBSA_EC "sbsa-ec" -#define SECURE_EC(obj) OBJECT_CHECK(SECUREECState, (obj), TYPE_SBSA_EC) +#define TYPE_SBSA_SECURE_EC "sbsa-ec" +#define SBSA_SECURE_EC(obj) \ + OBJECT_CHECK(SECUREECState, (obj), TYPE_SBSA_SECURE_EC) enum sbsa_ec_powerstates { SBSA_EC_CMD_POWEROFF = 0x01, @@ -XXX,XX +XXX,XX @@ static uint64_t sbsa_ec_read(void *opaque, hwaddr offset, unsigned size) } static void sbsa_ec_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) + uint64_t value, unsigned size) { if (offset == 0) { /* PSCI machine power command register */ switch (value) { @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps sbsa_ec_ops = { static void sbsa_ec_init(Object *obj) { - SECUREECState *s = SECURE_EC(obj); + SECUREECState *s = SBSA_SECURE_EC(obj); SysBusDevice *dev = SYS_BUS_DEVICE(obj); memory_region_init_io(&s->iomem, obj, &sbsa_ec_ops, s, "sbsa-ec", @@ -XXX,XX +XXX,XX @@ static void sbsa_ec_class_init(ObjectClass *klass, void *data) } static const TypeInfo sbsa_ec_info = { - .name = TYPE_SBSA_EC, + .name = TYPE_SBSA_SECURE_EC, .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(SECUREECState), .instance_init = sbsa_ec_init, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> This model was merged few days before the QOM cleanup from commit 8063396bf3 ("Use OBJECT_DECLARE_SIMPLE_TYPE when possible") was pulled and merged. Manually adapt. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230109140306.23161-13-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/sbsa_ec.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/hw/misc/sbsa_ec.c b/hw/misc/sbsa_ec.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/sbsa_ec.c +++ b/hw/misc/sbsa_ec.c @@ -XXX,XX +XXX,XX @@ typedef struct SECUREECState { } SECUREECState; #define TYPE_SBSA_SECURE_EC "sbsa-ec" -#define SBSA_SECURE_EC(obj) \ - OBJECT_CHECK(SECUREECState, (obj), TYPE_SBSA_SECURE_EC) +OBJECT_DECLARE_SIMPLE_TYPE(SECUREECState, SBSA_SECURE_EC) enum sbsa_ec_powerstates { SBSA_EC_CMD_POWEROFF = 0x01, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> This remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call, to avoid after a QOM refactor: hw/intc/xilinx_intc.c:45:1: error: declaration of anonymous struct must be a definition DECLARE_INSTANCE_CHECKER(struct xlx_pic, XILINX_INTC, ^ Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar@zeroasic.com> Message-id: 20230109140306.23161-14-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/xilinx_intc.c | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/hw/intc/xilinx_intc.c b/hw/intc/xilinx_intc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/xilinx_intc.c +++ b/hw/intc/xilinx_intc.c @@ -XXX,XX +XXX,XX @@ #define R_MAX 8 #define TYPE_XILINX_INTC "xlnx.xps-intc" -DECLARE_INSTANCE_CHECKER(struct xlx_pic, XILINX_INTC, - TYPE_XILINX_INTC) +typedef struct XpsIntc XpsIntc; +DECLARE_INSTANCE_CHECKER(XpsIntc, XILINX_INTC, TYPE_XILINX_INTC) -struct xlx_pic +struct XpsIntc { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct xlx_pic uint32_t irq_pin_state; }; -static void update_irq(struct xlx_pic *p) +static void update_irq(XpsIntc *p) { uint32_t i; @@ -XXX,XX +XXX,XX @@ static void update_irq(struct xlx_pic *p) qemu_set_irq(p->parent_irq, (p->regs[R_MER] & 1) && p->regs[R_IPR]); } -static uint64_t -pic_read(void *opaque, hwaddr addr, unsigned int size) +static uint64_t pic_read(void *opaque, hwaddr addr, unsigned int size) { - struct xlx_pic *p = opaque; + XpsIntc *p = opaque; uint32_t r = 0; addr >>= 2; @@ -XXX,XX +XXX,XX @@ pic_read(void *opaque, hwaddr addr, unsigned int size) return r; } -static void -pic_write(void *opaque, hwaddr addr, - uint64_t val64, unsigned int size) +static void pic_write(void *opaque, hwaddr addr, + uint64_t val64, unsigned int size) { - struct xlx_pic *p = opaque; + XpsIntc *p = opaque; uint32_t value = val64; addr >>= 2; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps pic_ops = { static void irq_handler(void *opaque, int irq, int level) { - struct xlx_pic *p = opaque; + XpsIntc *p = opaque; /* edge triggered interrupt */ if (p->c_kind_of_intr & (1 << irq) && p->regs[R_MER] & 2) { @@ -XXX,XX +XXX,XX @@ static void irq_handler(void *opaque, int irq, int level) static void xilinx_intc_init(Object *obj) { - struct xlx_pic *p = XILINX_INTC(obj); + XpsIntc *p = XILINX_INTC(obj); qdev_init_gpio_in(DEVICE(obj), irq_handler, 32); sysbus_init_irq(SYS_BUS_DEVICE(obj), &p->parent_irq); @@ -XXX,XX +XXX,XX @@ static void xilinx_intc_init(Object *obj) } static Property xilinx_intc_properties[] = { - DEFINE_PROP_UINT32("kind-of-intr", struct xlx_pic, c_kind_of_intr, 0), + DEFINE_PROP_UINT32("kind-of-intr", XpsIntc, c_kind_of_intr, 0), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static void xilinx_intc_class_init(ObjectClass *klass, void *data) static const TypeInfo xilinx_intc_info = { .name = TYPE_XILINX_INTC, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(struct xlx_pic), + .instance_size = sizeof(XpsIntc), .instance_init = xilinx_intc_init, .class_init = xilinx_intc_class_init, }; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> This remove a use of 'struct' in the DECLARE_INSTANCE_CHECKER() macro call, to avoid after a QOM refactor: hw/timer/xilinx_timer.c:65:1: error: declaration of anonymous struct must be a definition DECLARE_INSTANCE_CHECKER(struct timerblock, XILINX_TIMER, ^ Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar@zeroasic.com> Message-id: 20230109140306.23161-15-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/timer/xilinx_timer.c | 27 +++++++++++++-------------- 1 file changed, 13 insertions(+), 14 deletions(-) diff --git a/hw/timer/xilinx_timer.c b/hw/timer/xilinx_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/xilinx_timer.c +++ b/hw/timer/xilinx_timer.c @@ -XXX,XX +XXX,XX @@ struct xlx_timer }; #define TYPE_XILINX_TIMER "xlnx.xps-timer" -DECLARE_INSTANCE_CHECKER(struct timerblock, XILINX_TIMER, - TYPE_XILINX_TIMER) +typedef struct XpsTimerState XpsTimerState; +DECLARE_INSTANCE_CHECKER(XpsTimerState, XILINX_TIMER, TYPE_XILINX_TIMER) -struct timerblock +struct XpsTimerState { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct timerblock struct xlx_timer *timers; }; -static inline unsigned int num_timers(struct timerblock *t) +static inline unsigned int num_timers(XpsTimerState *t) { return 2 - t->one_timer_only; } @@ -XXX,XX +XXX,XX @@ static inline unsigned int timer_from_addr(hwaddr addr) return addr >> 2; } -static void timer_update_irq(struct timerblock *t) +static void timer_update_irq(XpsTimerState *t) { unsigned int i, irq = 0; uint32_t csr; @@ -XXX,XX +XXX,XX @@ static void timer_update_irq(struct timerblock *t) static uint64_t timer_read(void *opaque, hwaddr addr, unsigned int size) { - struct timerblock *t = opaque; + XpsTimerState *t = opaque; struct xlx_timer *xt; uint32_t r = 0; unsigned int timer; @@ -XXX,XX +XXX,XX @@ static void timer_write(void *opaque, hwaddr addr, uint64_t val64, unsigned int size) { - struct timerblock *t = opaque; + XpsTimerState *t = opaque; struct xlx_timer *xt; unsigned int timer; uint32_t value = val64; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps timer_ops = { static void timer_hit(void *opaque) { struct xlx_timer *xt = opaque; - struct timerblock *t = xt->parent; + XpsTimerState *t = xt->parent; D(fprintf(stderr, "%s %d\n", __func__, xt->nr)); xt->regs[R_TCSR] |= TCSR_TINT; @@ -XXX,XX +XXX,XX @@ static void timer_hit(void *opaque) static void xilinx_timer_realize(DeviceState *dev, Error **errp) { - struct timerblock *t = XILINX_TIMER(dev); + XpsTimerState *t = XILINX_TIMER(dev); unsigned int i; /* Init all the ptimers. */ @@ -XXX,XX +XXX,XX @@ static void xilinx_timer_realize(DeviceState *dev, Error **errp) static void xilinx_timer_init(Object *obj) { - struct timerblock *t = XILINX_TIMER(obj); + XpsTimerState *t = XILINX_TIMER(obj); /* All timers share a single irq line. */ sysbus_init_irq(SYS_BUS_DEVICE(obj), &t->irq); } static Property xilinx_timer_properties[] = { - DEFINE_PROP_UINT32("clock-frequency", struct timerblock, freq_hz, - 62 * 1000000), - DEFINE_PROP_UINT8("one-timer-only", struct timerblock, one_timer_only, 0), + DEFINE_PROP_UINT32("clock-frequency", XpsTimerState, freq_hz, 62 * 1000000), + DEFINE_PROP_UINT8("one-timer-only", XpsTimerState, one_timer_only, 0), DEFINE_PROP_END_OF_LIST(), }; @@ -XXX,XX +XXX,XX @@ static void xilinx_timer_class_init(ObjectClass *klass, void *data) static const TypeInfo xilinx_timer_info = { .name = TYPE_XILINX_TIMER, .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(struct timerblock), + .instance_size = sizeof(XpsTimerState), .instance_init = xilinx_timer_init, .class_init = xilinx_timer_class_init, }; -- 2.34.1 From: Evgeny Iakovlev <eiakovlev@linux.microsoft.com> ARM trusted firmware, when built with FEAT_HCX support, sets SCR_EL3.HXEn bit to allow EL2 to modify HCRX_EL2 register without trapping it in EL3. Qemu uses a valid mask to clear unsupported SCR_EL3 bits when emulating SCR_EL3 write, and that mask doesn't include SCR_EL3.HXEn bit even if FEAT_HCX is enabled and exposed to the guest. As a result EL3 writes of that bit are ignored. Cc: qemu-stable@nongnu.org Signed-off-by: Evgeny Iakovlev <eiakovlev@linux.microsoft.com> Message-id: 20230105221251.17896-4-eiakovlev@linux.microsoft.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 3 +++ 1 file changed, 3 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 void scr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) if (cpu_isar_feature(aa64_sme, cpu)) { valid_mask |= SCR_ENTP2; } + if (cpu_isar_feature(aa64_hcx, cpu)) { + valid_mask |= SCR_HXEN; + } } else { valid_mask &= ~(SCR_RW | SCR_ST); if (cpu_isar_feature(aa32_ras, cpu)) { -- 2.34.1