Mostly this is patches from me and RTH cleaning up and doing more decodetree conversion for AArch32 Neon. The major new feature is Dongjiu Geng's patchset to report host memory errors to KVM guests; also a new aspeed board from Patrick Williams. thanks -- PMM The following changes since commit 035b448b84f3557206abc44d786c5d3db2638f7d: Merge remote-tracking branch 'remotes/gkurz/tags/9p-next-2020-05-14' into staging (2020-05-14 10:58:30 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200514 for you to fetch changes up to e95485f85657be21135c17a9226e297c21e73360: target/arm: Convert NEON VFMA, VFMS 3-reg-same insns to decodetree (2020-05-14 15:03:09 +0100) ---------------------------------------------------------------- target-arm queue: * target/arm: Use correct GDB XML for M-profile cores * target/arm: Code cleanup to use gvec APIs better * aspeed: Add support for the sonorapass-bmc board * target/arm: Support reporting KVM host memory errors to the guest via ACPI notifications * target/arm: Finish conversion of Neon 3-reg-same insns to decodetree ---------------------------------------------------------------- Dongjiu Geng (10): acpi: nvdimm: change NVDIMM_UUID_LE to a common macro hw/arm/virt: Introduce a RAS machine option docs: APEI GHES generation and CPER record description ACPI: Build related register address fields via hardware error fw_cfg blob ACPI: Build Hardware Error Source Table ACPI: Record the Generic Error Status Block address KVM: Move hwpoison page related functions into kvm-all.c ACPI: Record Generic Error Status Block(GESB) table target-arm: kvm64: handle SIGBUS signal from kernel or KVM MAINTAINERS: Add ACPI/HEST/GHES entries Patrick Williams (1): aspeed: Add support for the sonorapass-bmc board Peter Maydell (18): target/arm: Use correct GDB XML for M-profile cores target/arm: Convert Neon 3-reg-same VQRDMLAH/VQRDMLSH to decodetree target/arm: Convert Neon 3-reg-same SHA to decodetree target/arm: Convert Neon 64-bit element 3-reg-same insns target/arm: Convert Neon VHADD 3-reg-same insns target/arm: Convert Neon VABA/VABD 3-reg-same to decodetree target/arm: Convert Neon VRHADD, VHSUB 3-reg-same insns to decodetree target/arm: Convert Neon VQSHL, VRSHL, VQRSHL 3-reg-same insns to decodetree target/arm: Convert Neon VPMAX/VPMIN 3-reg-same insns to decodetree target/arm: Convert Neon VPADD 3-reg-same insns to decodetree target/arm: Convert Neon VQDMULH/VQRDMULH 3-reg-same to decodetree target/arm: Convert Neon VADD, VSUB, VABD 3-reg-same insns to decodetree target/arm: Convert Neon VPMIN/VPMAX/VPADD float 3-reg-same insns to decodetree target/arm: Convert Neon fp VMUL, VMLA, VMLS 3-reg-same insns to decodetree target/arm: Convert Neon 3-reg-same compare insns to decodetree target/arm: Move 'env' argument of recps_f32 and rsqrts_f32 helpers to usual place target/arm: Convert Neon fp VMAX/VMIN/VMAXNM/VMINNM/VRECPS/VRSQRTS to decodetree target/arm: Convert NEON VFMA, VFMS 3-reg-same insns to decodetree Richard Henderson (16): target/arm: Create gen_gvec_[us]sra target/arm: Create gen_gvec_{u,s}{rshr,rsra} target/arm: Create gen_gvec_{sri,sli} target/arm: Remove unnecessary range check for VSHL target/arm: Tidy handle_vec_simd_shri target/arm: Create gen_gvec_{ceq,clt,cle,cgt,cge}0 target/arm: Create gen_gvec_{mla,mls} target/arm: Swap argument order for VSHL during decode target/arm: Create gen_gvec_{cmtst,ushl,sshl} target/arm: Create gen_gvec_{uqadd, sqadd, uqsub, sqsub} target/arm: Remove fp_status from helper_{recpe, rsqrte}_u32 target/arm: Create gen_gvec_{qrdmla,qrdmls} target/arm: Pass pointer to qc to qrdmla/qrdmls target/arm: Clear tail in gvec_fmul_idx_*, gvec_fmla_idx_* target/arm: Vectorize SABD/UABD target/arm: Vectorize SABA/UABA docs/specs/acpi_hest_ghes.rst | 110 ++ docs/specs/index.rst | 1 + configure | 4 +- default-configs/arm-softmmu.mak | 1 + include/hw/acpi/aml-build.h | 1 + include/hw/acpi/generic_event_device.h | 2 + include/hw/acpi/ghes.h | 74 + include/hw/arm/virt.h | 1 + include/qemu/uuid.h | 27 + include/sysemu/kvm.h | 3 +- include/sysemu/kvm_int.h | 12 + target/arm/cpu.h | 4 + target/arm/helper.h | 78 +- target/arm/internals.h | 5 +- target/arm/translate.h | 84 +- target/i386/cpu.h | 2 + target/arm/neon-dp.decode | 119 +- accel/kvm/kvm-all.c | 36 + hw/acpi/aml-build.c | 2 + hw/acpi/generic_event_device.c | 19 + hw/acpi/ghes.c | 448 ++++++ hw/acpi/nvdimm.c | 10 +- hw/arm/aspeed.c | 78 ++ hw/arm/virt-acpi-build.c | 15 + hw/arm/virt.c | 23 + target/arm/cpu_tcg.c | 1 + target/arm/gdbstub.c | 22 +- target/arm/helper.c | 2 +- target/arm/kvm64.c | 77 ++ target/arm/neon_helper.c | 17 - target/arm/tlb_helper.c | 2 +- target/arm/translate-a64.c | 210 +-- target/arm/translate-neon.inc.c | 682 +++++++++- target/arm/translate.c | 2349 +++++++++++++++++--------------- target/arm/vec_helper.c | 240 +++- target/arm/vfp_helper.c | 9 +- target/i386/kvm.c | 36 - MAINTAINERS | 9 + gdb-xml/arm-m-profile.xml | 27 + hw/acpi/Kconfig | 4 + hw/acpi/Makefile.objs | 1 + 41 files changed, 3402 insertions(+), 1445 deletions(-) create mode 100644 docs/specs/acpi_hest_ghes.rst create mode 100644 include/hw/acpi/ghes.h create mode 100644 hw/acpi/ghes.c create mode 100644 gdb-xml/arm-m-profile.xml GDB's remote protocol requires M-profile cores to use the feature name 'org.gnu.gdb.arm.m-profile' instead of the 'org.gnu.gdb.arm.core' feature used for A- and R-profile cores. We weren't doing this, which meant GDB treated our M-profile cores like A-profile ones. This mostly doesn't matter, but for instance means that it doesn't correctly handle backtraces where an M-profile exception frame is involved. Ship a copy of GDB's arm-m-profile.xml and use it on the M-profile cores. The integer registers have the same offsets as the arm-core.xml, but register 25 is the M-profile XPSR rather than the A-profile CPSR, so we need to update arm_cpu_gdb_read_register() and arm_cpu_gdb_write_register() to handle XSPR reads and writes. Fixes: https://bugs.launchpad.net/qemu/+bug/1877136 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200507134755.13997-1-peter.maydell@linaro.org --- configure | 4 ++-- target/arm/cpu_tcg.c | 1 + target/arm/gdbstub.c | 22 ++++++++++++++++++---- gdb-xml/arm-m-profile.xml | 27 +++++++++++++++++++++++++++ 4 files changed, 48 insertions(+), 6 deletions(-) create mode 100644 gdb-xml/arm-m-profile.xml diff --git a/configure b/configure index XXXXXXX..XXXXXXX 100755 --- a/configure +++ b/configure @@ -XXX,XX +XXX,XX @@ case "$target_name" in TARGET_SYSTBL_ABI=common,oabi bflt="yes" mttcg="yes" - gdb_xml_files="arm-core.xml arm-vfp.xml arm-vfp3.xml arm-neon.xml" + gdb_xml_files="arm-core.xml arm-vfp.xml arm-vfp3.xml arm-neon.xml arm-m-profile.xml" ;; aarch64|aarch64_be) TARGET_ARCH=aarch64 TARGET_BASE_ARCH=arm bflt="yes" mttcg="yes" - gdb_xml_files="aarch64-core.xml aarch64-fpu.xml arm-core.xml arm-vfp.xml arm-vfp3.xml arm-neon.xml" + gdb_xml_files="aarch64-core.xml aarch64-fpu.xml arm-core.xml arm-vfp.xml arm-vfp3.xml arm-neon.xml arm-m-profile.xml" ;; cris) ;; diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ static void arm_v7m_class_init(ObjectClass *oc, void *data) #endif cc->cpu_exec_interrupt = arm_v7m_cpu_exec_interrupt; + cc->gdb_core_xml_file = "arm-m-profile.xml"; } static const ARMCPUInfo arm_tcg_cpus[] = { diff --git a/target/arm/gdbstub.c b/target/arm/gdbstub.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/gdbstub.c +++ b/target/arm/gdbstub.c @@ -XXX,XX +XXX,XX @@ int arm_cpu_gdb_read_register(CPUState *cs, GByteArray *mem_buf, int n) } return gdb_get_reg32(mem_buf, 0); case 25: - /* CPSR */ - return gdb_get_reg32(mem_buf, cpsr_read(env)); + /* CPSR, or XPSR for M-profile */ + if (arm_feature(env, ARM_FEATURE_M)) { + return gdb_get_reg32(mem_buf, xpsr_read(env)); + } else { + return gdb_get_reg32(mem_buf, cpsr_read(env)); + } } /* Unknown register. */ return 0; @@ -XXX,XX +XXX,XX @@ int arm_cpu_gdb_write_register(CPUState *cs, uint8_t *mem_buf, int n) } return 4; case 25: - /* CPSR */ - cpsr_write(env, tmp, 0xffffffff, CPSRWriteByGDBStub); + /* CPSR, or XPSR for M-profile */ + if (arm_feature(env, ARM_FEATURE_M)) { + /* + * Don't allow writing to XPSR.Exception as it can cause + * a transition into or out of handler mode (it's not + * writeable via the MSR insn so this is a reasonable + * restriction). Other fields are safe to update. + */ + xpsr_write(env, tmp, ~XPSR_EXCP); + } else { + cpsr_write(env, tmp, 0xffffffff, CPSRWriteByGDBStub); + } return 4; } /* Unknown register. */ diff --git a/gdb-xml/arm-m-profile.xml b/gdb-xml/arm-m-profile.xml new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/gdb-xml/arm-m-profile.xml @@ -XXX,XX +XXX,XX @@ +<?xml version="1.0"?> +<!-- Copyright (C) 2010-2020 Free Software Foundation, Inc. + + Copying and distribution of this file, with or without modification, + are permitted in any medium without royalty provided the copyright + notice and this notice are preserved. --> + +<!DOCTYPE feature SYSTEM "gdb-target.dtd"> +<feature name="org.gnu.gdb.arm.m-profile"> + <reg name="r0" bitsize="32"/> + <reg name="r1" bitsize="32"/> + <reg name="r2" bitsize="32"/> + <reg name="r3" bitsize="32"/> + <reg name="r4" bitsize="32"/> + <reg name="r5" bitsize="32"/> + <reg name="r6" bitsize="32"/> + <reg name="r7" bitsize="32"/> + <reg name="r8" bitsize="32"/> + <reg name="r9" bitsize="32"/> + <reg name="r10" bitsize="32"/> + <reg name="r11" bitsize="32"/> + <reg name="r12" bitsize="32"/> + <reg name="sp" bitsize="32" type="data_ptr"/> + <reg name="lr" bitsize="32"/> + <reg name="pc" bitsize="32" type="code_ptr"/> + <reg name="xpsr" bitsize="32" regnum="25"/> +</feature> -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The functions eliminate duplication of the special cases for this operation. They match up with the GVecGen2iFn typedef. Add out-of-line helpers. We got away with only having inline expanders because the neon vector size is only 16 bytes, and we know that the inline expansion will always succeed. When we reuse this for SVE, tcg-gvec-op may decide to use an out-of-line helper due to longer vector lengths. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 10 +++ target/arm/translate.h | 7 +- target/arm/translate-a64.c | 15 +--- target/arm/translate.c | 161 ++++++++++++++++++++++--------------- target/arm/vec_helper.c | 25 ++++++ 5 files changed, 139 insertions(+), 79 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(gvec_pmull_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(neon_pmull_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_ssra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_ssra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_ssra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_ssra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(gvec_usra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_usra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_usra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_usra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ extern const GVecGen3 mls_op[4]; extern const GVecGen3 cmtst_op[4]; extern const GVecGen3 sshl_op[4]; extern const GVecGen3 ushl_op[4]; -extern const GVecGen2i ssra_op[4]; -extern const GVecGen2i usra_op[4]; extern const GVecGen2i sri_op[4]; extern const GVecGen2i sli_op[4]; extern const GVecGen4 uqadd_op[4]; @@ -XXX,XX +XXX,XX @@ void gen_sshl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); void gen_ushl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); void gen_sshl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); +void gen_gvec_ssra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_usra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz); + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ 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 handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, switch (opcode) { case 0x02: /* SSRA / USRA (accumulate) */ - if (is_u) { - /* Shift count same as element size produces zero to add. */ - if (shift == 8 << size) { - goto done; - } - gen_gvec_op2i(s, is_q, rd, rn, shift, &usra_op[size]); - } else { - /* Shift count same as element size produces all sign to add. */ - if (shift == 8 << size) { - shift -= 1; - } - gen_gvec_op2i(s, is_q, rd, rn, shift, &ssra_op[size]); - } + gen_gvec_fn2i(s, is_q, rd, rn, shift, + is_u ? gen_gvec_usra : gen_gvec_ssra, size); return; case 0x08: /* SRI */ /* Shift count same as element size is valid but does nothing. */ 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 gen_ssra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) tcg_gen_add_vec(vece, d, d, a); } -static const TCGOpcode vecop_list_ssra[] = { - INDEX_op_sari_vec, INDEX_op_add_vec, 0 -}; +void gen_gvec_ssra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sari_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2i ops[4] = { + { .fni8 = gen_ssra8_i64, + .fniv = gen_ssra_vec, + .fno = gen_helper_gvec_ssra_b, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_ssra16_i64, + .fniv = gen_ssra_vec, + .fno = gen_helper_gvec_ssra_h, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_ssra32_i32, + .fniv = gen_ssra_vec, + .fno = gen_helper_gvec_ssra_s, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_ssra64_i64, + .fniv = gen_ssra_vec, + .fno = gen_helper_gvec_ssra_b, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 }, + }; -const GVecGen2i ssra_op[4] = { - { .fni8 = gen_ssra8_i64, - .fniv = gen_ssra_vec, - .load_dest = true, - .opt_opc = vecop_list_ssra, - .vece = MO_8 }, - { .fni8 = gen_ssra16_i64, - .fniv = gen_ssra_vec, - .load_dest = true, - .opt_opc = vecop_list_ssra, - .vece = MO_16 }, - { .fni4 = gen_ssra32_i32, - .fniv = gen_ssra_vec, - .load_dest = true, - .opt_opc = vecop_list_ssra, - .vece = MO_32 }, - { .fni8 = gen_ssra64_i64, - .fniv = gen_ssra_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .opt_opc = vecop_list_ssra, - .load_dest = true, - .vece = MO_64 }, -}; + /* tszimm encoding produces immediates in the range [1..esize]. */ + tcg_debug_assert(shift > 0); + tcg_debug_assert(shift <= (8 << vece)); + + /* + * Shifts larger than the element size are architecturally valid. + * Signed results in all sign bits. + */ + shift = MIN(shift, (8 << vece) - 1); + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); +} static void gen_usra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) { @@ -XXX,XX +XXX,XX @@ static void gen_usra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) tcg_gen_add_vec(vece, d, d, a); } -static const TCGOpcode vecop_list_usra[] = { - INDEX_op_shri_vec, INDEX_op_add_vec, 0 -}; +void gen_gvec_usra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2i ops[4] = { + { .fni8 = gen_usra8_i64, + .fniv = gen_usra_vec, + .fno = gen_helper_gvec_usra_b, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_8, }, + { .fni8 = gen_usra16_i64, + .fniv = gen_usra_vec, + .fno = gen_helper_gvec_usra_h, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_16, }, + { .fni4 = gen_usra32_i32, + .fniv = gen_usra_vec, + .fno = gen_helper_gvec_usra_s, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_32, }, + { .fni8 = gen_usra64_i64, + .fniv = gen_usra_vec, + .fno = gen_helper_gvec_usra_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_64, }, + }; -const GVecGen2i usra_op[4] = { - { .fni8 = gen_usra8_i64, - .fniv = gen_usra_vec, - .load_dest = true, - .opt_opc = vecop_list_usra, - .vece = MO_8, }, - { .fni8 = gen_usra16_i64, - .fniv = gen_usra_vec, - .load_dest = true, - .opt_opc = vecop_list_usra, - .vece = MO_16, }, - { .fni4 = gen_usra32_i32, - .fniv = gen_usra_vec, - .load_dest = true, - .opt_opc = vecop_list_usra, - .vece = MO_32, }, - { .fni8 = gen_usra64_i64, - .fniv = gen_usra_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opt_opc = vecop_list_usra, - .vece = MO_64, }, -}; + /* tszimm encoding produces immediates in the range [1..esize]. */ + tcg_debug_assert(shift > 0); + tcg_debug_assert(shift <= (8 << vece)); + + /* + * Shifts larger than the element size are architecturally valid. + * Unsigned results in all zeros as input to accumulate: nop. + */ + if (shift < (8 << vece)) { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); + } else { + /* Nop, but we do need to clear the tail. */ + tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz); + } +} static void gen_shr8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 1: /* VSRA */ /* Right shift comes here negative. */ shift = -shift; - /* Shifts larger than the element size are architecturally - * valid. Unsigned results in all zeros; signed results - * in all sign bits. - */ - if (!u) { - tcg_gen_gvec_2i(rd_ofs, rm_ofs, vec_size, vec_size, - MIN(shift, (8 << size) - 1), - &ssra_op[size]); - } else if (shift >= 8 << size) { - /* rd += 0 */ + if (u) { + gen_gvec_usra(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); } else { - tcg_gen_gvec_2i(rd_ofs, rm_ofs, vec_size, vec_size, - shift, &usra_op[size]); + gen_gvec_ssra(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); } return 0; 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_sqsub_d)(void *vd, void *vq, void *vn, clear_tail(d, oprsz, simd_maxsz(desc)); } + +#define DO_SRA(NAME, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + int shift = simd_data(desc); \ + TYPE *d = vd, *n = vn; \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + d[i] += n[i] >> shift; \ + } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ +} + +DO_SRA(gvec_ssra_b, int8_t) +DO_SRA(gvec_ssra_h, int16_t) +DO_SRA(gvec_ssra_s, int32_t) +DO_SRA(gvec_ssra_d, int64_t) + +DO_SRA(gvec_usra_b, uint8_t) +DO_SRA(gvec_usra_h, uint16_t) +DO_SRA(gvec_usra_s, uint32_t) +DO_SRA(gvec_usra_d, uint64_t) + +#undef DO_SRA + /* * Convert float16 to float32, raising no exceptions and * preserving exceptional values, including SNaN. -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Create vectorized versions of handle_shri_with_rndacc for shift+round and shift+round+accumulate. Add out-of-line helpers in preparation for longer vector lengths from SVE. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 20 ++ target/arm/translate.h | 9 + target/arm/translate-a64.c | 11 +- target/arm/translate.c | 463 +++++++++++++++++++++++++++++++++++-- target/arm/vec_helper.c | 50 ++++ 5 files changed, 527 insertions(+), 26 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(gvec_usra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_usra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_usra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_srshr_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_srshr_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_srshr_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_srshr_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(gvec_urshr_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_urshr_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_urshr_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_urshr_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(gvec_srsra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_srsra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_srsra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_srsra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(gvec_ursra_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_ursra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_ursra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_ursra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_ssra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, void gen_gvec_usra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, int64_t shift, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_srshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_urshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_srsra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_ursra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz); + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ 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 handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, return; case 0x04: /* SRSHR / URSHR (rounding) */ - break; + gen_gvec_fn2i(s, is_q, rd, rn, shift, + is_u ? gen_gvec_urshr : gen_gvec_srshr, size); + return; + case 0x06: /* SRSRA / URSRA (accum + rounding) */ - accumulate = true; - break; + gen_gvec_fn2i(s, is_q, rd, rn, shift, + is_u ? gen_gvec_ursra : gen_gvec_srsra, size); + return; + default: g_assert_not_reached(); } diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ void gen_gvec_usra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, } } +/* + * Shift one less than the requested amount, and the low bit is + * the rounding bit. For the 8 and 16-bit operations, because we + * mask the low bit, we can perform a normal integer shift instead + * of a vector shift. + */ +static void gen_srshr8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shri_i64(t, a, sh - 1); + tcg_gen_andi_i64(t, t, dup_const(MO_8, 1)); + tcg_gen_vec_sar8i_i64(d, a, sh); + tcg_gen_vec_add8_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_srshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shri_i64(t, a, sh - 1); + tcg_gen_andi_i64(t, t, dup_const(MO_16, 1)); + tcg_gen_vec_sar16i_i64(d, a, sh); + tcg_gen_vec_add16_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_srshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_extract_i32(t, a, sh - 1, 1); + tcg_gen_sari_i32(d, a, sh); + tcg_gen_add_i32(d, d, t); + tcg_temp_free_i32(t); +} + +static void gen_srshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_extract_i64(t, a, sh - 1, 1); + tcg_gen_sari_i64(d, a, sh); + tcg_gen_add_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_srshr_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + TCGv_vec ones = tcg_temp_new_vec_matching(d); + + tcg_gen_shri_vec(vece, t, a, sh - 1); + tcg_gen_dupi_vec(vece, ones, 1); + tcg_gen_and_vec(vece, t, t, ones); + tcg_gen_sari_vec(vece, d, a, sh); + tcg_gen_add_vec(vece, d, d, t); + + tcg_temp_free_vec(t); + tcg_temp_free_vec(ones); +} + +void gen_gvec_srshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_sari_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2i ops[4] = { + { .fni8 = gen_srshr8_i64, + .fniv = gen_srshr_vec, + .fno = gen_helper_gvec_srshr_b, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_srshr16_i64, + .fniv = gen_srshr_vec, + .fno = gen_helper_gvec_srshr_h, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_srshr32_i32, + .fniv = gen_srshr_vec, + .fno = gen_helper_gvec_srshr_s, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_srshr64_i64, + .fniv = gen_srshr_vec, + .fno = gen_helper_gvec_srshr_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + + /* tszimm encoding produces immediates in the range [1..esize] */ + tcg_debug_assert(shift > 0); + tcg_debug_assert(shift <= (8 << vece)); + + if (shift == (8 << vece)) { + /* + * Shifts larger than the element size are architecturally valid. + * Signed results in all sign bits. With rounding, this produces + * (-1 + 1) >> 1 == 0, or (0 + 1) >> 1 == 0. + * I.e. always zero. + */ + tcg_gen_gvec_dup_imm(vece, rd_ofs, opr_sz, max_sz, 0); + } else { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); + } +} + +static void gen_srsra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + gen_srshr8_i64(t, a, sh); + tcg_gen_vec_add8_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_srsra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + gen_srshr16_i64(t, a, sh); + tcg_gen_vec_add16_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_srsra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + gen_srshr32_i32(t, a, sh); + tcg_gen_add_i32(d, d, t); + tcg_temp_free_i32(t); +} + +static void gen_srsra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + gen_srshr64_i64(t, a, sh); + tcg_gen_add_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_srsra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + gen_srshr_vec(vece, t, a, sh); + tcg_gen_add_vec(vece, d, d, t); + tcg_temp_free_vec(t); +} + +void gen_gvec_srsra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_sari_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2i ops[4] = { + { .fni8 = gen_srsra8_i64, + .fniv = gen_srsra_vec, + .fno = gen_helper_gvec_srsra_b, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_8 }, + { .fni8 = gen_srsra16_i64, + .fniv = gen_srsra_vec, + .fno = gen_helper_gvec_srsra_h, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_16 }, + { .fni4 = gen_srsra32_i32, + .fniv = gen_srsra_vec, + .fno = gen_helper_gvec_srsra_s, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_32 }, + { .fni8 = gen_srsra64_i64, + .fniv = gen_srsra_vec, + .fno = gen_helper_gvec_srsra_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 }, + }; + + /* tszimm encoding produces immediates in the range [1..esize] */ + tcg_debug_assert(shift > 0); + tcg_debug_assert(shift <= (8 << vece)); + + /* + * Shifts larger than the element size are architecturally valid. + * Signed results in all sign bits. With rounding, this produces + * (-1 + 1) >> 1 == 0, or (0 + 1) >> 1 == 0. + * I.e. always zero. With accumulation, this leaves D unchanged. + */ + if (shift == (8 << vece)) { + /* Nop, but we do need to clear the tail. */ + tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz); + } else { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); + } +} + +static void gen_urshr8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shri_i64(t, a, sh - 1); + tcg_gen_andi_i64(t, t, dup_const(MO_8, 1)); + tcg_gen_vec_shr8i_i64(d, a, sh); + tcg_gen_vec_add8_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_urshr16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shri_i64(t, a, sh - 1); + tcg_gen_andi_i64(t, t, dup_const(MO_16, 1)); + tcg_gen_vec_shr16i_i64(d, a, sh); + tcg_gen_vec_add16_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_urshr32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_extract_i32(t, a, sh - 1, 1); + tcg_gen_shri_i32(d, a, sh); + tcg_gen_add_i32(d, d, t); + tcg_temp_free_i32(t); +} + +static void gen_urshr64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_extract_i64(t, a, sh - 1, 1); + tcg_gen_shri_i64(d, a, sh); + tcg_gen_add_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_urshr_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t shift) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + TCGv_vec ones = tcg_temp_new_vec_matching(d); + + tcg_gen_shri_vec(vece, t, a, shift - 1); + tcg_gen_dupi_vec(vece, ones, 1); + tcg_gen_and_vec(vece, t, t, ones); + tcg_gen_shri_vec(vece, d, a, shift); + tcg_gen_add_vec(vece, d, d, t); + + tcg_temp_free_vec(t); + tcg_temp_free_vec(ones); +} + +void gen_gvec_urshr(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2i ops[4] = { + { .fni8 = gen_urshr8_i64, + .fniv = gen_urshr_vec, + .fno = gen_helper_gvec_urshr_b, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_urshr16_i64, + .fniv = gen_urshr_vec, + .fno = gen_helper_gvec_urshr_h, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_urshr32_i32, + .fniv = gen_urshr_vec, + .fno = gen_helper_gvec_urshr_s, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_urshr64_i64, + .fniv = gen_urshr_vec, + .fno = gen_helper_gvec_urshr_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + + /* tszimm encoding produces immediates in the range [1..esize] */ + tcg_debug_assert(shift > 0); + tcg_debug_assert(shift <= (8 << vece)); + + if (shift == (8 << vece)) { + /* + * Shifts larger than the element size are architecturally valid. + * Unsigned results in zero. With rounding, this produces a + * copy of the most significant bit. + */ + tcg_gen_gvec_shri(vece, rd_ofs, rm_ofs, shift - 1, opr_sz, max_sz); + } else { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); + } +} + +static void gen_ursra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + if (sh == 8) { + tcg_gen_vec_shr8i_i64(t, a, 7); + } else { + gen_urshr8_i64(t, a, sh); + } + tcg_gen_vec_add8_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_ursra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + if (sh == 16) { + tcg_gen_vec_shr16i_i64(t, a, 15); + } else { + gen_urshr16_i64(t, a, sh); + } + tcg_gen_vec_add16_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_ursra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t sh) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + if (sh == 32) { + tcg_gen_shri_i32(t, a, 31); + } else { + gen_urshr32_i32(t, a, sh); + } + tcg_gen_add_i32(d, d, t); + tcg_temp_free_i32(t); +} + +static void gen_ursra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t sh) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + if (sh == 64) { + tcg_gen_shri_i64(t, a, 63); + } else { + gen_urshr64_i64(t, a, sh); + } + tcg_gen_add_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_ursra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + if (sh == (8 << vece)) { + tcg_gen_shri_vec(vece, t, a, sh - 1); + } else { + gen_urshr_vec(vece, t, a, sh); + } + tcg_gen_add_vec(vece, d, d, t); + tcg_temp_free_vec(t); +} + +void gen_gvec_ursra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2i ops[4] = { + { .fni8 = gen_ursra8_i64, + .fniv = gen_ursra_vec, + .fno = gen_helper_gvec_ursra_b, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_8 }, + { .fni8 = gen_ursra16_i64, + .fniv = gen_ursra_vec, + .fno = gen_helper_gvec_ursra_h, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_16 }, + { .fni4 = gen_ursra32_i32, + .fniv = gen_ursra_vec, + .fno = gen_helper_gvec_ursra_s, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_32 }, + { .fni8 = gen_ursra64_i64, + .fniv = gen_ursra_vec, + .fno = gen_helper_gvec_ursra_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 }, + }; + + /* tszimm encoding produces immediates in the range [1..esize] */ + tcg_debug_assert(shift > 0); + tcg_debug_assert(shift <= (8 << vece)); + + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); +} + static void gen_shr8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) { uint64_t mask = dup_const(MO_8, 0xff >> shift); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } return 0; + case 2: /* VRSHR */ + /* Right shift comes here negative. */ + shift = -shift; + if (u) { + gen_gvec_urshr(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); + } else { + gen_gvec_srshr(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); + } + return 0; + + case 3: /* VRSRA */ + /* Right shift comes here negative. */ + shift = -shift; + if (u) { + gen_gvec_ursra(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); + } else { + gen_gvec_srsra(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); + } + return 0; + case 4: /* VSRI */ if (!u) { return 1; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) neon_load_reg64(cpu_V0, rm + pass); tcg_gen_movi_i64(cpu_V1, imm); switch (op) { - case 2: /* VRSHR */ - case 3: /* VRSRA */ - if (u) - gen_helper_neon_rshl_u64(cpu_V0, cpu_V0, cpu_V1); - else - gen_helper_neon_rshl_s64(cpu_V0, cpu_V0, cpu_V1); - break; case 6: /* VQSHLU */ gen_helper_neon_qshlu_s64(cpu_V0, cpu_env, cpu_V0, cpu_V1); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) default: g_assert_not_reached(); } - if (op == 3) { - /* Accumulate. */ - neon_load_reg64(cpu_V1, rd + pass); - tcg_gen_add_i64(cpu_V0, cpu_V0, cpu_V1); - } neon_store_reg64(cpu_V0, rd + pass); } else { /* size < 3 */ /* Operands in T0 and T1. */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp2, imm); switch (op) { - case 2: /* VRSHR */ - case 3: /* VRSRA */ - GEN_NEON_INTEGER_OP(rshl); - break; case 6: /* VQSHLU */ switch (size) { case 0: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) g_assert_not_reached(); } tcg_temp_free_i32(tmp2); - - if (op == 3) { - /* Accumulate. */ - tmp2 = neon_load_reg(rd, pass); - gen_neon_add(size, tmp, tmp2); - tcg_temp_free_i32(tmp2); - } neon_store_reg(rd, pass, tmp); } } /* for pass */ diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ DO_SRA(gvec_usra_d, uint64_t) #undef DO_SRA +#define DO_RSHR(NAME, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + int shift = simd_data(desc); \ + TYPE *d = vd, *n = vn; \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + TYPE tmp = n[i] >> (shift - 1); \ + d[i] = (tmp >> 1) + (tmp & 1); \ + } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ +} + +DO_RSHR(gvec_srshr_b, int8_t) +DO_RSHR(gvec_srshr_h, int16_t) +DO_RSHR(gvec_srshr_s, int32_t) +DO_RSHR(gvec_srshr_d, int64_t) + +DO_RSHR(gvec_urshr_b, uint8_t) +DO_RSHR(gvec_urshr_h, uint16_t) +DO_RSHR(gvec_urshr_s, uint32_t) +DO_RSHR(gvec_urshr_d, uint64_t) + +#undef DO_RSHR + +#define DO_RSRA(NAME, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + int shift = simd_data(desc); \ + TYPE *d = vd, *n = vn; \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + TYPE tmp = n[i] >> (shift - 1); \ + d[i] += (tmp >> 1) + (tmp & 1); \ + } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ +} + +DO_RSRA(gvec_srsra_b, int8_t) +DO_RSRA(gvec_srsra_h, int16_t) +DO_RSRA(gvec_srsra_s, int32_t) +DO_RSRA(gvec_srsra_d, int64_t) + +DO_RSRA(gvec_ursra_b, uint8_t) +DO_RSRA(gvec_ursra_h, uint16_t) +DO_RSRA(gvec_ursra_s, uint32_t) +DO_RSRA(gvec_ursra_d, uint64_t) + +#undef DO_RSRA + /* * Convert float16 to float32, raising no exceptions and * preserving exceptional values, including SNaN. -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The functions eliminate duplication of the special cases for this operation. They match up with the GVecGen2iFn typedef. Add out-of-line helpers. We got away with only having inline expanders because the neon vector size is only 16 bytes, and we know that the inline expansion will always succeed. When we reuse this for SVE, tcg-gvec-op may decide to use an out-of-line helper due to longer vector lengths. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 10 ++ target/arm/translate.h | 7 +- target/arm/translate-a64.c | 20 +--- target/arm/translate.c | 186 +++++++++++++++++++++---------------- target/arm/vec_helper.c | 38 ++++++++ 5 files changed, 160 insertions(+), 101 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(gvec_ursra_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_ursra_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_ursra_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_sri_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_sri_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_sri_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_sri_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(gvec_sli_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_sli_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_sli_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_sli_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ extern const GVecGen3 mls_op[4]; extern const GVecGen3 cmtst_op[4]; extern const GVecGen3 sshl_op[4]; extern const GVecGen3 ushl_op[4]; -extern const GVecGen2i sri_op[4]; -extern const GVecGen2i sli_op[4]; extern const GVecGen4 uqadd_op[4]; extern const GVecGen4 sqadd_op[4]; extern const GVecGen4 uqsub_op[4]; @@ -XXX,XX +XXX,XX @@ void gen_gvec_srsra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, void gen_gvec_ursra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, int64_t shift, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_sri(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_sli(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz); + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ 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 gen_gvec_op2(DisasContext *s, bool is_q, int rd, is_q ? 16 : 8, vec_full_reg_size(s), gvec_op); } -/* Expand a 2-operand + immediate AdvSIMD vector operation using - * an op descriptor. - */ -static void gen_gvec_op2i(DisasContext *s, bool is_q, int rd, - int rn, int64_t imm, const GVecGen2i *gvec_op) -{ - tcg_gen_gvec_2i(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn), - is_q ? 16 : 8, vec_full_reg_size(s), imm, gvec_op); -} - /* Expand a 3-operand AdvSIMD vector operation using an op descriptor. */ static void gen_gvec_op3(DisasContext *s, bool is_q, int rd, int rn, int rm, const GVecGen3 *gvec_op) @@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, gen_gvec_fn2i(s, is_q, rd, rn, shift, is_u ? gen_gvec_usra : gen_gvec_ssra, size); return; + case 0x08: /* SRI */ - /* Shift count same as element size is valid but does nothing. */ - if (shift == 8 << size) { - goto done; - } - gen_gvec_op2i(s, is_q, rd, rn, shift, &sri_op[size]); + gen_gvec_fn2i(s, is_q, rd, rn, shift, gen_gvec_sri, size); return; case 0x00: /* SSHR / USHR */ @@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, } tcg_temp_free_i64(tcg_round); - done: clear_vec_high(s, is_q, rd); } @@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shli(DisasContext *s, bool is_q, bool insert, } if (insert) { - gen_gvec_op2i(s, is_q, rd, rn, shift, &sli_op[size]); + gen_gvec_fn2i(s, is_q, rd, rn, shift, gen_gvec_sli, size); } else { gen_gvec_fn2i(s, is_q, rd, rn, shift, tcg_gen_gvec_shli, size); } 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 gen_shr64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) static void gen_shr_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) { - if (sh == 0) { - tcg_gen_mov_vec(d, a); - } else { - TCGv_vec t = tcg_temp_new_vec_matching(d); - TCGv_vec m = tcg_temp_new_vec_matching(d); + TCGv_vec t = tcg_temp_new_vec_matching(d); + TCGv_vec m = tcg_temp_new_vec_matching(d); - tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK((8 << vece) - sh, sh)); - tcg_gen_shri_vec(vece, t, a, sh); - tcg_gen_and_vec(vece, d, d, m); - tcg_gen_or_vec(vece, d, d, t); + tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK((8 << vece) - sh, sh)); + tcg_gen_shri_vec(vece, t, a, sh); + tcg_gen_and_vec(vece, d, d, m); + tcg_gen_or_vec(vece, d, d, t); - tcg_temp_free_vec(t); - tcg_temp_free_vec(m); - } + tcg_temp_free_vec(t); + tcg_temp_free_vec(m); } -static const TCGOpcode vecop_list_sri[] = { INDEX_op_shri_vec, 0 }; +void gen_gvec_sri(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { INDEX_op_shri_vec, 0 }; + const GVecGen2i ops[4] = { + { .fni8 = gen_shr8_ins_i64, + .fniv = gen_shr_ins_vec, + .fno = gen_helper_gvec_sri_b, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_shr16_ins_i64, + .fniv = gen_shr_ins_vec, + .fno = gen_helper_gvec_sri_h, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_shr32_ins_i32, + .fniv = gen_shr_ins_vec, + .fno = gen_helper_gvec_sri_s, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_shr64_ins_i64, + .fniv = gen_shr_ins_vec, + .fno = gen_helper_gvec_sri_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; -const GVecGen2i sri_op[4] = { - { .fni8 = gen_shr8_ins_i64, - .fniv = gen_shr_ins_vec, - .load_dest = true, - .opt_opc = vecop_list_sri, - .vece = MO_8 }, - { .fni8 = gen_shr16_ins_i64, - .fniv = gen_shr_ins_vec, - .load_dest = true, - .opt_opc = vecop_list_sri, - .vece = MO_16 }, - { .fni4 = gen_shr32_ins_i32, - .fniv = gen_shr_ins_vec, - .load_dest = true, - .opt_opc = vecop_list_sri, - .vece = MO_32 }, - { .fni8 = gen_shr64_ins_i64, - .fniv = gen_shr_ins_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opt_opc = vecop_list_sri, - .vece = MO_64 }, -}; + /* tszimm encoding produces immediates in the range [1..esize]. */ + tcg_debug_assert(shift > 0); + tcg_debug_assert(shift <= (8 << vece)); + + /* Shift of esize leaves destination unchanged. */ + if (shift < (8 << vece)) { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); + } else { + /* Nop, but we do need to clear the tail. */ + tcg_gen_gvec_mov(vece, rd_ofs, rd_ofs, opr_sz, max_sz); + } +} static void gen_shl8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) { @@ -XXX,XX +XXX,XX @@ static void gen_shl64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) static void gen_shl_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) { - if (sh == 0) { - tcg_gen_mov_vec(d, a); - } else { - TCGv_vec t = tcg_temp_new_vec_matching(d); - TCGv_vec m = tcg_temp_new_vec_matching(d); + TCGv_vec t = tcg_temp_new_vec_matching(d); + TCGv_vec m = tcg_temp_new_vec_matching(d); - tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK(0, sh)); - tcg_gen_shli_vec(vece, t, a, sh); - tcg_gen_and_vec(vece, d, d, m); - tcg_gen_or_vec(vece, d, d, t); + tcg_gen_shli_vec(vece, t, a, sh); + tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK(0, sh)); + tcg_gen_and_vec(vece, d, d, m); + tcg_gen_or_vec(vece, d, d, t); - tcg_temp_free_vec(t); - tcg_temp_free_vec(m); - } + tcg_temp_free_vec(t); + tcg_temp_free_vec(m); } -static const TCGOpcode vecop_list_sli[] = { INDEX_op_shli_vec, 0 }; +void gen_gvec_sli(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + int64_t shift, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { INDEX_op_shli_vec, 0 }; + const GVecGen2i ops[4] = { + { .fni8 = gen_shl8_ins_i64, + .fniv = gen_shl_ins_vec, + .fno = gen_helper_gvec_sli_b, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni8 = gen_shl16_ins_i64, + .fniv = gen_shl_ins_vec, + .fno = gen_helper_gvec_sli_h, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_shl32_ins_i32, + .fniv = gen_shl_ins_vec, + .fno = gen_helper_gvec_sli_s, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_shl64_ins_i64, + .fniv = gen_shl_ins_vec, + .fno = gen_helper_gvec_sli_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; -const GVecGen2i sli_op[4] = { - { .fni8 = gen_shl8_ins_i64, - .fniv = gen_shl_ins_vec, - .load_dest = true, - .opt_opc = vecop_list_sli, - .vece = MO_8 }, - { .fni8 = gen_shl16_ins_i64, - .fniv = gen_shl_ins_vec, - .load_dest = true, - .opt_opc = vecop_list_sli, - .vece = MO_16 }, - { .fni4 = gen_shl32_ins_i32, - .fniv = gen_shl_ins_vec, - .load_dest = true, - .opt_opc = vecop_list_sli, - .vece = MO_32 }, - { .fni8 = gen_shl64_ins_i64, - .fniv = gen_shl_ins_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opt_opc = vecop_list_sli, - .vece = MO_64 }, -}; + /* tszimm encoding produces immediates in the range [0..esize-1]. */ + tcg_debug_assert(shift >= 0); + tcg_debug_assert(shift < (8 << vece)); + + if (shift == 0) { + tcg_gen_gvec_mov(vece, rd_ofs, rm_ofs, opr_sz, max_sz); + } else { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, opr_sz, max_sz, shift, &ops[vece]); + } +} static void gen_mla8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } /* Right shift comes here negative. */ shift = -shift; - /* Shift out of range leaves destination unchanged. */ - if (shift < 8 << size) { - tcg_gen_gvec_2i(rd_ofs, rm_ofs, vec_size, vec_size, - shift, &sri_op[size]); - } + gen_gvec_sri(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); return 0; case 5: /* VSHL, VSLI */ if (u) { /* VSLI */ - /* Shift out of range leaves destination unchanged. */ - if (shift < 8 << size) { - tcg_gen_gvec_2i(rd_ofs, rm_ofs, vec_size, - vec_size, shift, &sli_op[size]); - } + gen_gvec_sli(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); } else { /* VSHL */ /* Shifts larger than the element size are * architecturally valid and results in zero. diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ DO_RSRA(gvec_ursra_d, uint64_t) #undef DO_RSRA +#define DO_SRI(NAME, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + int shift = simd_data(desc); \ + TYPE *d = vd, *n = vn; \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + d[i] = deposit64(d[i], 0, sizeof(TYPE) * 8 - shift, n[i] >> shift); \ + } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ +} + +DO_SRI(gvec_sri_b, uint8_t) +DO_SRI(gvec_sri_h, uint16_t) +DO_SRI(gvec_sri_s, uint32_t) +DO_SRI(gvec_sri_d, uint64_t) + +#undef DO_SRI + +#define DO_SLI(NAME, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + int shift = simd_data(desc); \ + TYPE *d = vd, *n = vn; \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + d[i] = deposit64(d[i], shift, sizeof(TYPE) * 8 - shift, n[i]); \ + } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ +} + +DO_SLI(gvec_sli_b, uint8_t) +DO_SLI(gvec_sli_h, uint16_t) +DO_SLI(gvec_sli_s, uint32_t) +DO_SLI(gvec_sli_d, uint64_t) + +#undef DO_SLI + /* * Convert float16 to float32, raising no exceptions and * preserving exceptional values, including SNaN. -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> In 1dc8425e551, while converting to gvec, I added an extra range check against the shift count. This was unnecessary because the encoding of the shift count produces 0 to the element size - 1. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 12 ++---------- 1 file changed, 2 insertions(+), 10 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) gen_gvec_sli(size, rd_ofs, rm_ofs, shift, vec_size, vec_size); } else { /* VSHL */ - /* Shifts larger than the element size are - * architecturally valid and results in zero. - */ - if (shift >= 8 << size) { - tcg_gen_gvec_dup_imm(size, rd_ofs, - vec_size, vec_size, 0); - } else { - tcg_gen_gvec_shli(size, rd_ofs, rm_ofs, shift, - vec_size, vec_size); - } + tcg_gen_gvec_shli(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); } return 0; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Now that we've converted all cases to gvec, there is quite a bit of dead code at the end of the function. Remove it. Sink the call to gen_gvec_fn2i to the end, loading a function pointer within the switch statement. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 56 ++++++++++---------------------------- 1 file changed, 14 insertions(+), 42 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, int size = 32 - clz32(immh) - 1; int immhb = immh << 3 | immb; int shift = 2 * (8 << size) - immhb; - bool accumulate = false; - int dsize = is_q ? 128 : 64; - int esize = 8 << size; - int elements = dsize/esize; - MemOp memop = size | (is_u ? 0 : MO_SIGN); - TCGv_i64 tcg_rn = new_tmp_a64(s); - TCGv_i64 tcg_rd = new_tmp_a64(s); - TCGv_i64 tcg_round; - uint64_t round_const; - int i; + GVecGen2iFn *gvec_fn; if (extract32(immh, 3, 1) && !is_q) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, switch (opcode) { case 0x02: /* SSRA / USRA (accumulate) */ - gen_gvec_fn2i(s, is_q, rd, rn, shift, - is_u ? gen_gvec_usra : gen_gvec_ssra, size); - return; + gvec_fn = is_u ? gen_gvec_usra : gen_gvec_ssra; + break; case 0x08: /* SRI */ - gen_gvec_fn2i(s, is_q, rd, rn, shift, gen_gvec_sri, size); - return; + gvec_fn = gen_gvec_sri; + break; case 0x00: /* SSHR / USHR */ if (is_u) { @@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, /* Shift count the same size as element size produces zero. */ tcg_gen_gvec_dup_imm(size, vec_full_reg_offset(s, rd), is_q ? 16 : 8, vec_full_reg_size(s), 0); - } else { - gen_gvec_fn2i(s, is_q, rd, rn, shift, tcg_gen_gvec_shri, size); + return; } + gvec_fn = tcg_gen_gvec_shri; } else { /* Shift count the same size as element size produces all sign. */ if (shift == 8 << size) { shift -= 1; } - gen_gvec_fn2i(s, is_q, rd, rn, shift, tcg_gen_gvec_sari, size); + gvec_fn = tcg_gen_gvec_sari; } - return; + break; case 0x04: /* SRSHR / URSHR (rounding) */ - gen_gvec_fn2i(s, is_q, rd, rn, shift, - is_u ? gen_gvec_urshr : gen_gvec_srshr, size); - return; + gvec_fn = is_u ? gen_gvec_urshr : gen_gvec_srshr; + break; case 0x06: /* SRSRA / URSRA (accum + rounding) */ - gen_gvec_fn2i(s, is_q, rd, rn, shift, - is_u ? gen_gvec_ursra : gen_gvec_srsra, size); - return; + gvec_fn = is_u ? gen_gvec_ursra : gen_gvec_srsra; + break; default: g_assert_not_reached(); } - round_const = 1ULL << (shift - 1); - tcg_round = tcg_const_i64(round_const); - - for (i = 0; i < elements; i++) { - read_vec_element(s, tcg_rn, rn, i, memop); - if (accumulate) { - read_vec_element(s, tcg_rd, rd, i, memop); - } - - handle_shri_with_rndacc(tcg_rd, tcg_rn, tcg_round, - accumulate, is_u, size, shift); - - write_vec_element(s, tcg_rd, rd, i, size); - } - tcg_temp_free_i64(tcg_round); - - clear_vec_high(s, is_q, rd); + gen_gvec_fn2i(s, is_q, rd, rn, shift, gvec_fn, size); } /* SHL/SLI - Vector shift left */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Provide a functional interface for the vector expansion. This fits better with the existing set of helpers that we provide for other operations. Macro-ize the 5 nearly identical comparisons. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 16 ++- target/arm/translate-a64.c | 22 ++-- target/arm/translate.c | 254 ++++++++----------------------------- 3 files changed, 74 insertions(+), 218 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 @@ static inline void gen_swstep_exception(DisasContext *s, int isv, int ex) uint64_t vfp_expand_imm(int size, uint8_t imm8); /* Vector operations shared between ARM and AArch64. */ -extern const GVecGen2 ceq0_op[4]; -extern const GVecGen2 clt0_op[4]; -extern const GVecGen2 cgt0_op[4]; -extern const GVecGen2 cle0_op[4]; -extern const GVecGen2 cge0_op[4]; +void gen_gvec_ceq0(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_clt0(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_cgt0(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_cle0(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_cge0(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz); + extern const GVecGen3 mla_op[4]; extern const GVecGen3 mls_op[4]; extern const GVecGen3 cmtst_op[4]; 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 gen_gvec_fn4(DisasContext *s, bool is_q, int rd, int rn, int rm, is_q ? 16 : 8, vec_full_reg_size(s)); } -/* Expand a 2-operand AdvSIMD vector operation using an op descriptor. */ -static void gen_gvec_op2(DisasContext *s, bool is_q, int rd, - int rn, const GVecGen2 *gvec_op) -{ - tcg_gen_gvec_2(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn), - is_q ? 16 : 8, vec_full_reg_size(s), gvec_op); -} - /* Expand a 3-operand AdvSIMD vector operation using an op descriptor. */ static void gen_gvec_op3(DisasContext *s, bool is_q, int rd, int rn, int rm, const GVecGen3 *gvec_op) @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } break; case 0x8: /* CMGT, CMGE */ - gen_gvec_op2(s, is_q, rd, rn, u ? &cge0_op[size] : &cgt0_op[size]); + if (u) { + gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cge0, size); + } else { + gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cgt0, size); + } return; case 0x9: /* CMEQ, CMLE */ - gen_gvec_op2(s, is_q, rd, rn, u ? &cle0_op[size] : &ceq0_op[size]); + if (u) { + gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cle0, size); + } else { + gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_ceq0, size); + } return; case 0xa: /* CMLT */ - gen_gvec_op2(s, is_q, rd, rn, &clt0_op[size]); + gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_clt0, size); return; case 0xb: if (u) { /* ABS, NEG */ diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int do_v81_helper(DisasContext *s, gen_helper_gvec_3_ptr *fn, return 1; } -static void gen_ceq0_i32(TCGv_i32 d, TCGv_i32 a) -{ - tcg_gen_setcondi_i32(TCG_COND_EQ, d, a, 0); - tcg_gen_neg_i32(d, d); -} - -static void gen_ceq0_i64(TCGv_i64 d, TCGv_i64 a) -{ - tcg_gen_setcondi_i64(TCG_COND_EQ, d, a, 0); - tcg_gen_neg_i64(d, d); -} - -static void gen_ceq0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) -{ - TCGv_vec zero = tcg_const_zeros_vec_matching(d); - tcg_gen_cmp_vec(TCG_COND_EQ, vece, d, a, zero); - tcg_temp_free_vec(zero); -} +#define GEN_CMP0(NAME, COND) \ + static void gen_##NAME##0_i32(TCGv_i32 d, TCGv_i32 a) \ + { \ + tcg_gen_setcondi_i32(COND, d, a, 0); \ + tcg_gen_neg_i32(d, d); \ + } \ + static void gen_##NAME##0_i64(TCGv_i64 d, TCGv_i64 a) \ + { \ + tcg_gen_setcondi_i64(COND, d, a, 0); \ + tcg_gen_neg_i64(d, d); \ + } \ + static void gen_##NAME##0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) \ + { \ + TCGv_vec zero = tcg_const_zeros_vec_matching(d); \ + tcg_gen_cmp_vec(COND, vece, d, a, zero); \ + tcg_temp_free_vec(zero); \ + } \ + void gen_gvec_##NAME##0(unsigned vece, uint32_t d, uint32_t m, \ + uint32_t opr_sz, uint32_t max_sz) \ + { \ + const GVecGen2 op[4] = { \ + { .fno = gen_helper_gvec_##NAME##0_b, \ + .fniv = gen_##NAME##0_vec, \ + .opt_opc = vecop_list_cmp, \ + .vece = MO_8 }, \ + { .fno = gen_helper_gvec_##NAME##0_h, \ + .fniv = gen_##NAME##0_vec, \ + .opt_opc = vecop_list_cmp, \ + .vece = MO_16 }, \ + { .fni4 = gen_##NAME##0_i32, \ + .fniv = gen_##NAME##0_vec, \ + .opt_opc = vecop_list_cmp, \ + .vece = MO_32 }, \ + { .fni8 = gen_##NAME##0_i64, \ + .fniv = gen_##NAME##0_vec, \ + .opt_opc = vecop_list_cmp, \ + .prefer_i64 = TCG_TARGET_REG_BITS == 64, \ + .vece = MO_64 }, \ + }; \ + tcg_gen_gvec_2(d, m, opr_sz, max_sz, &op[vece]); \ + } static const TCGOpcode vecop_list_cmp[] = { INDEX_op_cmp_vec, 0 }; -const GVecGen2 ceq0_op[4] = { - { .fno = gen_helper_gvec_ceq0_b, - .fniv = gen_ceq0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_8 }, - { .fno = gen_helper_gvec_ceq0_h, - .fniv = gen_ceq0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_16 }, - { .fni4 = gen_ceq0_i32, - .fniv = gen_ceq0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_32 }, - { .fni8 = gen_ceq0_i64, - .fniv = gen_ceq0_vec, - .opt_opc = vecop_list_cmp, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .vece = MO_64 }, -}; +GEN_CMP0(ceq, TCG_COND_EQ) +GEN_CMP0(cle, TCG_COND_LE) +GEN_CMP0(cge, TCG_COND_GE) +GEN_CMP0(clt, TCG_COND_LT) +GEN_CMP0(cgt, TCG_COND_GT) -static void gen_cle0_i32(TCGv_i32 d, TCGv_i32 a) -{ - tcg_gen_setcondi_i32(TCG_COND_LE, d, a, 0); - tcg_gen_neg_i32(d, d); -} - -static void gen_cle0_i64(TCGv_i64 d, TCGv_i64 a) -{ - tcg_gen_setcondi_i64(TCG_COND_LE, d, a, 0); - tcg_gen_neg_i64(d, d); -} - -static void gen_cle0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) -{ - TCGv_vec zero = tcg_const_zeros_vec_matching(d); - tcg_gen_cmp_vec(TCG_COND_LE, vece, d, a, zero); - tcg_temp_free_vec(zero); -} - -const GVecGen2 cle0_op[4] = { - { .fno = gen_helper_gvec_cle0_b, - .fniv = gen_cle0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_8 }, - { .fno = gen_helper_gvec_cle0_h, - .fniv = gen_cle0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_16 }, - { .fni4 = gen_cle0_i32, - .fniv = gen_cle0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_32 }, - { .fni8 = gen_cle0_i64, - .fniv = gen_cle0_vec, - .opt_opc = vecop_list_cmp, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .vece = MO_64 }, -}; - -static void gen_cge0_i32(TCGv_i32 d, TCGv_i32 a) -{ - tcg_gen_setcondi_i32(TCG_COND_GE, d, a, 0); - tcg_gen_neg_i32(d, d); -} - -static void gen_cge0_i64(TCGv_i64 d, TCGv_i64 a) -{ - tcg_gen_setcondi_i64(TCG_COND_GE, d, a, 0); - tcg_gen_neg_i64(d, d); -} - -static void gen_cge0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) -{ - TCGv_vec zero = tcg_const_zeros_vec_matching(d); - tcg_gen_cmp_vec(TCG_COND_GE, vece, d, a, zero); - tcg_temp_free_vec(zero); -} - -const GVecGen2 cge0_op[4] = { - { .fno = gen_helper_gvec_cge0_b, - .fniv = gen_cge0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_8 }, - { .fno = gen_helper_gvec_cge0_h, - .fniv = gen_cge0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_16 }, - { .fni4 = gen_cge0_i32, - .fniv = gen_cge0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_32 }, - { .fni8 = gen_cge0_i64, - .fniv = gen_cge0_vec, - .opt_opc = vecop_list_cmp, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .vece = MO_64 }, -}; - -static void gen_clt0_i32(TCGv_i32 d, TCGv_i32 a) -{ - tcg_gen_setcondi_i32(TCG_COND_LT, d, a, 0); - tcg_gen_neg_i32(d, d); -} - -static void gen_clt0_i64(TCGv_i64 d, TCGv_i64 a) -{ - tcg_gen_setcondi_i64(TCG_COND_LT, d, a, 0); - tcg_gen_neg_i64(d, d); -} - -static void gen_clt0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) -{ - TCGv_vec zero = tcg_const_zeros_vec_matching(d); - tcg_gen_cmp_vec(TCG_COND_LT, vece, d, a, zero); - tcg_temp_free_vec(zero); -} - -const GVecGen2 clt0_op[4] = { - { .fno = gen_helper_gvec_clt0_b, - .fniv = gen_clt0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_8 }, - { .fno = gen_helper_gvec_clt0_h, - .fniv = gen_clt0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_16 }, - { .fni4 = gen_clt0_i32, - .fniv = gen_clt0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_32 }, - { .fni8 = gen_clt0_i64, - .fniv = gen_clt0_vec, - .opt_opc = vecop_list_cmp, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .vece = MO_64 }, -}; - -static void gen_cgt0_i32(TCGv_i32 d, TCGv_i32 a) -{ - tcg_gen_setcondi_i32(TCG_COND_GT, d, a, 0); - tcg_gen_neg_i32(d, d); -} - -static void gen_cgt0_i64(TCGv_i64 d, TCGv_i64 a) -{ - tcg_gen_setcondi_i64(TCG_COND_GT, d, a, 0); - tcg_gen_neg_i64(d, d); -} - -static void gen_cgt0_vec(unsigned vece, TCGv_vec d, TCGv_vec a) -{ - TCGv_vec zero = tcg_const_zeros_vec_matching(d); - tcg_gen_cmp_vec(TCG_COND_GT, vece, d, a, zero); - tcg_temp_free_vec(zero); -} - -const GVecGen2 cgt0_op[4] = { - { .fno = gen_helper_gvec_cgt0_b, - .fniv = gen_cgt0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_8 }, - { .fno = gen_helper_gvec_cgt0_h, - .fniv = gen_cgt0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_16 }, - { .fni4 = gen_cgt0_i32, - .fniv = gen_cgt0_vec, - .opt_opc = vecop_list_cmp, - .vece = MO_32 }, - { .fni8 = gen_cgt0_i64, - .fniv = gen_cgt0_vec, - .opt_opc = vecop_list_cmp, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .vece = MO_64 }, -}; +#undef GEN_CMP0 static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) break; case NEON_2RM_VCEQ0: - tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, - vec_size, &ceq0_op[size]); + gen_gvec_ceq0(size, rd_ofs, rm_ofs, vec_size, vec_size); break; case NEON_2RM_VCGT0: - tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, - vec_size, &cgt0_op[size]); + gen_gvec_cgt0(size, rd_ofs, rm_ofs, vec_size, vec_size); break; case NEON_2RM_VCLE0: - tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, - vec_size, &cle0_op[size]); + gen_gvec_cle0(size, rd_ofs, rm_ofs, vec_size, vec_size); break; case NEON_2RM_VCGE0: - tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, - vec_size, &cge0_op[size]); + gen_gvec_cge0(size, rd_ofs, rm_ofs, vec_size, vec_size); break; case NEON_2RM_VCLT0: - tcg_gen_gvec_2(rd_ofs, rm_ofs, vec_size, - vec_size, &clt0_op[size]); + gen_gvec_clt0(size, rd_ofs, rm_ofs, vec_size, vec_size); break; default: -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Provide a functional interface for the vector expansion. This fits better with the existing set of helpers that we provide for other operations. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 7 +- target/arm/translate-a64.c | 4 +- target/arm/translate-neon.inc.c | 16 +---- target/arm/translate.c | 117 +++++++++++++++++--------------- 4 files changed, 71 insertions(+), 73 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 @@ void gen_gvec_cle0(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, void gen_gvec_cge0(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); -extern const GVecGen3 mla_op[4]; -extern const GVecGen3 mls_op[4]; +void gen_gvec_mla(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_mls(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + extern const GVecGen3 cmtst_op[4]; extern const GVecGen3 sshl_op[4]; extern const GVecGen3 ushl_op[4]; diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) return; case 0x12: /* MLA, MLS */ if (u) { - gen_gvec_op3(s, is_q, rd, rn, rm, &mls_op[size]); + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_mls, size); } else { - gen_gvec_op3(s, is_q, rd, rn, rm, &mla_op[size]); + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_mla, size); } return; case 0x11: diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_NO_SZ_3(VMAX_U, tcg_gen_gvec_umax) DO_3SAME_NO_SZ_3(VMIN_S, tcg_gen_gvec_smin) DO_3SAME_NO_SZ_3(VMIN_U, tcg_gen_gvec_umin) DO_3SAME_NO_SZ_3(VMUL, tcg_gen_gvec_mul) +DO_3SAME_NO_SZ_3(VMLA, gen_gvec_mla) +DO_3SAME_NO_SZ_3(VMLS, gen_gvec_mls) #define DO_3SAME_CMP(INSN, COND) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ @@ -XXX,XX +XXX,XX @@ static bool trans_VMUL_p_3s(DisasContext *s, arg_3same *a) return do_3same(s, a, gen_VMUL_p_3s); } -#define DO_3SAME_GVEC3_NO_SZ_3(INSN, OPARRAY) \ - static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ - uint32_t rn_ofs, uint32_t rm_ofs, \ - uint32_t oprsz, uint32_t maxsz) \ - { \ - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, \ - oprsz, maxsz, &OPARRAY[vece]); \ - } \ - DO_3SAME_NO_SZ_3(INSN, gen_##INSN##_3s) - - -DO_3SAME_GVEC3_NO_SZ_3(VMLA, mla_op) -DO_3SAME_GVEC3_NO_SZ_3(VMLS, mls_op) - #define DO_3SAME_GVEC3_SHIFT(INSN, OPARRAY) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ uint32_t rn_ofs, uint32_t rm_ofs, \ 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 gen_mls_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) /* Note that while NEON does not support VMLA and VMLS as 64-bit ops, * these tables are shared with AArch64 which does support them. */ +void gen_gvec_mla(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_mul_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fni4 = gen_mla8_i32, + .fniv = gen_mla_vec, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni4 = gen_mla16_i32, + .fniv = gen_mla_vec, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_mla32_i32, + .fniv = gen_mla_vec, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_mla64_i64, + .fniv = gen_mla_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} -static const TCGOpcode vecop_list_mla[] = { - INDEX_op_mul_vec, INDEX_op_add_vec, 0 -}; - -static const TCGOpcode vecop_list_mls[] = { - INDEX_op_mul_vec, INDEX_op_sub_vec, 0 -}; - -const GVecGen3 mla_op[4] = { - { .fni4 = gen_mla8_i32, - .fniv = gen_mla_vec, - .load_dest = true, - .opt_opc = vecop_list_mla, - .vece = MO_8 }, - { .fni4 = gen_mla16_i32, - .fniv = gen_mla_vec, - .load_dest = true, - .opt_opc = vecop_list_mla, - .vece = MO_16 }, - { .fni4 = gen_mla32_i32, - .fniv = gen_mla_vec, - .load_dest = true, - .opt_opc = vecop_list_mla, - .vece = MO_32 }, - { .fni8 = gen_mla64_i64, - .fniv = gen_mla_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opt_opc = vecop_list_mla, - .vece = MO_64 }, -}; - -const GVecGen3 mls_op[4] = { - { .fni4 = gen_mls8_i32, - .fniv = gen_mls_vec, - .load_dest = true, - .opt_opc = vecop_list_mls, - .vece = MO_8 }, - { .fni4 = gen_mls16_i32, - .fniv = gen_mls_vec, - .load_dest = true, - .opt_opc = vecop_list_mls, - .vece = MO_16 }, - { .fni4 = gen_mls32_i32, - .fniv = gen_mls_vec, - .load_dest = true, - .opt_opc = vecop_list_mls, - .vece = MO_32 }, - { .fni8 = gen_mls64_i64, - .fniv = gen_mls_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opt_opc = vecop_list_mls, - .vece = MO_64 }, -}; +void gen_gvec_mls(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_mul_vec, INDEX_op_sub_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fni4 = gen_mls8_i32, + .fniv = gen_mls_vec, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni4 = gen_mls16_i32, + .fniv = gen_mls_vec, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_mls32_i32, + .fniv = gen_mls_vec, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_mls64_i64, + .fniv = gen_mls_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} /* CMTST : test is "if (X & Y != 0)". */ static void gen_cmtst_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Rather than perform the argument swap during code generation, perform it during decode. This means it doesn't have to be special cased later, and we can share code with aarch64 code generation. Hopefully the decode comment addresses any confusion that might arise in between. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/neon-dp.decode | 17 +++++++++++++++-- target/arm/translate-neon.inc.c | 3 +-- 2 files changed, 16 insertions(+), 4 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VCGT_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 0 .... @3same VCGE_S_3s 1111 001 0 0 . .. .... .... 0011 . . . 1 .... @3same VCGE_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same -VSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 0 .... @3same -VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same +# The _rev suffix indicates that Vn and Vm are reversed. This is +# the case for shifts. In the Arm ARM these insns are documented +# with the Vm and Vn fields in their usual places, but in the +# assembly the operands are listed "backwards", ie in the order +# Dd, Dm, Dn where other insns use Dd, Dn, Dm. For QEMU we choose +# to consider Vm and Vn as being in different fields in the insn, +# which allows us to avoid special-casing shifts in the trans_ +# function code. We would otherwise need to manually swap the operands +# over to call Neon helper functions that are shared with AArch64, +# which does not have this odd reversed-operand situation. +@3same_rev .... ... . . . size:2 .... .... .... . q:1 . . .... \ + &3same vn=%vm_dp vm=%vn_dp vd=%vd_dp + +VSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 0 .... @3same_rev +VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VMUL_p_3s(DisasContext *s, arg_3same *a) uint32_t rn_ofs, uint32_t rm_ofs, \ uint32_t oprsz, uint32_t maxsz) \ { \ - /* Note the operation is vshl vd,vm,vn */ \ - tcg_gen_gvec_3(rd_ofs, rm_ofs, rn_ofs, \ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, \ oprsz, maxsz, &OPARRAY[vece]); \ } \ DO_3SAME(INSN, gen_##INSN##_3s) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Provide a functional interface for the vector expansion. This fits better with the existing set of helpers that we provide for other operations. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 10 ++- target/arm/translate-a64.c | 18 ++-- target/arm/translate-neon.inc.c | 23 +---- target/arm/translate.c | 146 +++++++++++++++++--------------- 4 files changed, 95 insertions(+), 102 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 @@ void gen_gvec_mla(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, void gen_gvec_mls(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); -extern const GVecGen3 cmtst_op[4]; -extern const GVecGen3 sshl_op[4]; -extern const GVecGen3 ushl_op[4]; +void gen_gvec_cmtst(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_ushl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + extern const GVecGen4 uqadd_op[4]; extern const GVecGen4 sqadd_op[4]; extern const GVecGen4 uqsub_op[4]; 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 gen_gvec_fn4(DisasContext *s, bool is_q, int rd, int rn, int rm, is_q ? 16 : 8, vec_full_reg_size(s)); } -/* Expand a 3-operand AdvSIMD vector operation using an op descriptor. */ -static void gen_gvec_op3(DisasContext *s, bool is_q, int rd, - int rn, int rm, const GVecGen3 *gvec_op) -{ - tcg_gen_gvec_3(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), is_q ? 16 : 8, - vec_full_reg_size(s), gvec_op); -} - /* Expand a 3-operand operation using an out-of-line helper. */ static void gen_gvec_op3_ool(DisasContext *s, bool is_q, int rd, int rn, int rm, int data, gen_helper_gvec_3 *fn) @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) (u ? uqsub_op : sqsub_op) + size); return; case 0x08: /* SSHL, USHL */ - gen_gvec_op3(s, is_q, rd, rn, rm, - u ? &ushl_op[size] : &sshl_op[size]); + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_ushl, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sshl, size); + } return; case 0x0c: /* SMAX, UMAX */ if (u) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) return; case 0x11: if (!u) { /* CMTST */ - gen_gvec_op3(s, is_q, rd, rn, rm, &cmtst_op[size]); + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_cmtst, size); return; } /* else CMEQ */ diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME(VBIC, tcg_gen_gvec_andc) DO_3SAME(VORR, tcg_gen_gvec_or) DO_3SAME(VORN, tcg_gen_gvec_orc) DO_3SAME(VEOR, tcg_gen_gvec_xor) +DO_3SAME(VSHL_S, gen_gvec_sshl) +DO_3SAME(VSHL_U, gen_gvec_ushl) /* These insns are all gvec_bitsel but with the inputs in various orders. */ #define DO_3SAME_BITSEL(INSN, O1, O2, O3) \ @@ -XXX,XX +XXX,XX @@ DO_3SAME_NO_SZ_3(VMIN_U, tcg_gen_gvec_umin) DO_3SAME_NO_SZ_3(VMUL, tcg_gen_gvec_mul) DO_3SAME_NO_SZ_3(VMLA, gen_gvec_mla) DO_3SAME_NO_SZ_3(VMLS, gen_gvec_mls) +DO_3SAME_NO_SZ_3(VTST, gen_gvec_cmtst) #define DO_3SAME_CMP(INSN, COND) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ @@ -XXX,XX +XXX,XX @@ DO_3SAME_CMP(VCGE_S, TCG_COND_GE) DO_3SAME_CMP(VCGE_U, TCG_COND_GEU) DO_3SAME_CMP(VCEQ, TCG_COND_EQ) -static void gen_VTST_3s(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, - uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz) -{ - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &cmtst_op[vece]); -} -DO_3SAME_NO_SZ_3(VTST, gen_VTST_3s) - #define DO_3SAME_GVEC4(INSN, OPARRAY) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ uint32_t rn_ofs, uint32_t rm_ofs, \ @@ -XXX,XX +XXX,XX @@ static bool trans_VMUL_p_3s(DisasContext *s, arg_3same *a) } return do_3same(s, a, gen_VMUL_p_3s); } - -#define DO_3SAME_GVEC3_SHIFT(INSN, OPARRAY) \ - static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ - uint32_t rn_ofs, uint32_t rm_ofs, \ - uint32_t oprsz, uint32_t maxsz) \ - { \ - tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, \ - oprsz, maxsz, &OPARRAY[vece]); \ - } \ - DO_3SAME(INSN, gen_##INSN##_3s) - -DO_3SAME_GVEC3_SHIFT(VSHL_S, sshl_op) -DO_3SAME_GVEC3_SHIFT(VSHL_U, ushl_op) 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 gen_cmtst_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) tcg_gen_cmp_vec(TCG_COND_NE, vece, d, d, a); } -static const TCGOpcode vecop_list_cmtst[] = { INDEX_op_cmp_vec, 0 }; - -const GVecGen3 cmtst_op[4] = { - { .fni4 = gen_helper_neon_tst_u8, - .fniv = gen_cmtst_vec, - .opt_opc = vecop_list_cmtst, - .vece = MO_8 }, - { .fni4 = gen_helper_neon_tst_u16, - .fniv = gen_cmtst_vec, - .opt_opc = vecop_list_cmtst, - .vece = MO_16 }, - { .fni4 = gen_cmtst_i32, - .fniv = gen_cmtst_vec, - .opt_opc = vecop_list_cmtst, - .vece = MO_32 }, - { .fni8 = gen_cmtst_i64, - .fniv = gen_cmtst_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .opt_opc = vecop_list_cmtst, - .vece = MO_64 }, -}; +void gen_gvec_cmtst(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { INDEX_op_cmp_vec, 0 }; + static const GVecGen3 ops[4] = { + { .fni4 = gen_helper_neon_tst_u8, + .fniv = gen_cmtst_vec, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fni4 = gen_helper_neon_tst_u16, + .fniv = gen_cmtst_vec, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_cmtst_i32, + .fniv = gen_cmtst_vec, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_cmtst_i64, + .fniv = gen_cmtst_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} void gen_ushl_i32(TCGv_i32 dst, TCGv_i32 src, TCGv_i32 shift) { @@ -XXX,XX +XXX,XX @@ static void gen_ushl_vec(unsigned vece, TCGv_vec dst, tcg_temp_free_vec(rsh); } -static const TCGOpcode ushl_list[] = { - INDEX_op_neg_vec, INDEX_op_shlv_vec, - INDEX_op_shrv_vec, INDEX_op_cmp_vec, 0 -}; - -const GVecGen3 ushl_op[4] = { - { .fniv = gen_ushl_vec, - .fno = gen_helper_gvec_ushl_b, - .opt_opc = ushl_list, - .vece = MO_8 }, - { .fniv = gen_ushl_vec, - .fno = gen_helper_gvec_ushl_h, - .opt_opc = ushl_list, - .vece = MO_16 }, - { .fni4 = gen_ushl_i32, - .fniv = gen_ushl_vec, - .opt_opc = ushl_list, - .vece = MO_32 }, - { .fni8 = gen_ushl_i64, - .fniv = gen_ushl_vec, - .opt_opc = ushl_list, - .vece = MO_64 }, -}; +void gen_gvec_ushl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_neg_vec, INDEX_op_shlv_vec, + INDEX_op_shrv_vec, INDEX_op_cmp_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fniv = gen_ushl_vec, + .fno = gen_helper_gvec_ushl_b, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fniv = gen_ushl_vec, + .fno = gen_helper_gvec_ushl_h, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_ushl_i32, + .fniv = gen_ushl_vec, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_ushl_i64, + .fniv = gen_ushl_vec, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} void gen_sshl_i32(TCGv_i32 dst, TCGv_i32 src, TCGv_i32 shift) { @@ -XXX,XX +XXX,XX @@ static void gen_sshl_vec(unsigned vece, TCGv_vec dst, tcg_temp_free_vec(tmp); } -static const TCGOpcode sshl_list[] = { - INDEX_op_neg_vec, INDEX_op_umin_vec, INDEX_op_shlv_vec, - INDEX_op_sarv_vec, INDEX_op_cmp_vec, INDEX_op_cmpsel_vec, 0 -}; - -const GVecGen3 sshl_op[4] = { - { .fniv = gen_sshl_vec, - .fno = gen_helper_gvec_sshl_b, - .opt_opc = sshl_list, - .vece = MO_8 }, - { .fniv = gen_sshl_vec, - .fno = gen_helper_gvec_sshl_h, - .opt_opc = sshl_list, - .vece = MO_16 }, - { .fni4 = gen_sshl_i32, - .fniv = gen_sshl_vec, - .opt_opc = sshl_list, - .vece = MO_32 }, - { .fni8 = gen_sshl_i64, - .fniv = gen_sshl_vec, - .opt_opc = sshl_list, - .vece = MO_64 }, -}; +void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_neg_vec, INDEX_op_umin_vec, INDEX_op_shlv_vec, + INDEX_op_sarv_vec, INDEX_op_cmp_vec, INDEX_op_cmpsel_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fniv = gen_sshl_vec, + .fno = gen_helper_gvec_sshl_b, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fniv = gen_sshl_vec, + .fno = gen_helper_gvec_sshl_h, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_sshl_i32, + .fniv = gen_sshl_vec, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_sshl_i64, + .fniv = gen_sshl_vec, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} static void gen_uqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, TCGv_vec a, TCGv_vec b) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Provide a functional interface for the vector expansion. This fits better with the existing set of helpers that we provide for other operations. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 13 +- target/arm/translate-a64.c | 22 ++- target/arm/translate-neon.inc.c | 19 +-- target/arm/translate.c | 228 +++++++++++++++++--------------- 4 files changed, 147 insertions(+), 135 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 @@ void gen_gvec_sshl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, void gen_gvec_ushl(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); -extern const GVecGen4 uqadd_op[4]; -extern const GVecGen4 sqadd_op[4]; -extern const GVecGen4 uqsub_op[4]; -extern const GVecGen4 sqsub_op[4]; void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); void gen_ushl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); void gen_sshl_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b); void gen_ushl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); void gen_sshl_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); +void gen_gvec_uqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_sqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_uqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_sqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + void gen_gvec_ssra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, int64_t shift, uint32_t opr_sz, uint32_t max_sz); void gen_gvec_usra(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) switch (opcode) { case 0x01: /* SQADD, UQADD */ - tcg_gen_gvec_4(vec_full_reg_offset(s, rd), - offsetof(CPUARMState, vfp.qc), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), - is_q ? 16 : 8, vec_full_reg_size(s), - (u ? uqadd_op : sqadd_op) + size); + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uqadd_qc, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqadd_qc, size); + } return; case 0x05: /* SQSUB, UQSUB */ - tcg_gen_gvec_4(vec_full_reg_offset(s, rd), - offsetof(CPUARMState, vfp.qc), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), - is_q ? 16 : 8, vec_full_reg_size(s), - (u ? uqsub_op : sqsub_op) + size); + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uqsub_qc, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqsub_qc, size); + } return; case 0x08: /* SSHL, USHL */ if (u) { diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME(VORN, tcg_gen_gvec_orc) DO_3SAME(VEOR, tcg_gen_gvec_xor) DO_3SAME(VSHL_S, gen_gvec_sshl) DO_3SAME(VSHL_U, gen_gvec_ushl) +DO_3SAME(VQADD_S, gen_gvec_sqadd_qc) +DO_3SAME(VQADD_U, gen_gvec_uqadd_qc) +DO_3SAME(VQSUB_S, gen_gvec_sqsub_qc) +DO_3SAME(VQSUB_U, gen_gvec_uqsub_qc) /* These insns are all gvec_bitsel but with the inputs in various orders. */ #define DO_3SAME_BITSEL(INSN, O1, O2, O3) \ @@ -XXX,XX +XXX,XX @@ DO_3SAME_CMP(VCGE_S, TCG_COND_GE) DO_3SAME_CMP(VCGE_U, TCG_COND_GEU) DO_3SAME_CMP(VCEQ, TCG_COND_EQ) -#define DO_3SAME_GVEC4(INSN, OPARRAY) \ - static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ - uint32_t rn_ofs, uint32_t rm_ofs, \ - uint32_t oprsz, uint32_t maxsz) \ - { \ - tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), \ - rn_ofs, rm_ofs, oprsz, maxsz, &OPARRAY[vece]); \ - } \ - DO_3SAME(INSN, gen_##INSN##_3s) - -DO_3SAME_GVEC4(VQADD_S, sqadd_op) -DO_3SAME_GVEC4(VQADD_U, uqadd_op) -DO_3SAME_GVEC4(VQSUB_S, sqsub_op) -DO_3SAME_GVEC4(VQSUB_U, uqsub_op) - static void gen_VMUL_p_3s(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz) { 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 gen_uqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, tcg_temp_free_vec(x); } -static const TCGOpcode vecop_list_uqadd[] = { - INDEX_op_usadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0 -}; - -const GVecGen4 uqadd_op[4] = { - { .fniv = gen_uqadd_vec, - .fno = gen_helper_gvec_uqadd_b, - .write_aofs = true, - .opt_opc = vecop_list_uqadd, - .vece = MO_8 }, - { .fniv = gen_uqadd_vec, - .fno = gen_helper_gvec_uqadd_h, - .write_aofs = true, - .opt_opc = vecop_list_uqadd, - .vece = MO_16 }, - { .fniv = gen_uqadd_vec, - .fno = gen_helper_gvec_uqadd_s, - .write_aofs = true, - .opt_opc = vecop_list_uqadd, - .vece = MO_32 }, - { .fniv = gen_uqadd_vec, - .fno = gen_helper_gvec_uqadd_d, - .write_aofs = true, - .opt_opc = vecop_list_uqadd, - .vece = MO_64 }, -}; +void gen_gvec_uqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_usadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_uqadd_vec, + .fno = gen_helper_gvec_uqadd_b, + .write_aofs = true, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fniv = gen_uqadd_vec, + .fno = gen_helper_gvec_uqadd_h, + .write_aofs = true, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fniv = gen_uqadd_vec, + .fno = gen_helper_gvec_uqadd_s, + .write_aofs = true, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fniv = gen_uqadd_vec, + .fno = gen_helper_gvec_uqadd_d, + .write_aofs = true, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), + rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} static void gen_sqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, TCGv_vec a, TCGv_vec b) @@ -XXX,XX +XXX,XX @@ static void gen_sqadd_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, tcg_temp_free_vec(x); } -static const TCGOpcode vecop_list_sqadd[] = { - INDEX_op_ssadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0 -}; - -const GVecGen4 sqadd_op[4] = { - { .fniv = gen_sqadd_vec, - .fno = gen_helper_gvec_sqadd_b, - .opt_opc = vecop_list_sqadd, - .write_aofs = true, - .vece = MO_8 }, - { .fniv = gen_sqadd_vec, - .fno = gen_helper_gvec_sqadd_h, - .opt_opc = vecop_list_sqadd, - .write_aofs = true, - .vece = MO_16 }, - { .fniv = gen_sqadd_vec, - .fno = gen_helper_gvec_sqadd_s, - .opt_opc = vecop_list_sqadd, - .write_aofs = true, - .vece = MO_32 }, - { .fniv = gen_sqadd_vec, - .fno = gen_helper_gvec_sqadd_d, - .opt_opc = vecop_list_sqadd, - .write_aofs = true, - .vece = MO_64 }, -}; +void gen_gvec_sqadd_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_ssadd_vec, INDEX_op_cmp_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_sqadd_vec, + .fno = gen_helper_gvec_sqadd_b, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_8 }, + { .fniv = gen_sqadd_vec, + .fno = gen_helper_gvec_sqadd_h, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_16 }, + { .fniv = gen_sqadd_vec, + .fno = gen_helper_gvec_sqadd_s, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_32 }, + { .fniv = gen_sqadd_vec, + .fno = gen_helper_gvec_sqadd_d, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_64 }, + }; + tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), + rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} static void gen_uqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, TCGv_vec a, TCGv_vec b) @@ -XXX,XX +XXX,XX @@ static void gen_uqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, tcg_temp_free_vec(x); } -static const TCGOpcode vecop_list_uqsub[] = { - INDEX_op_ussub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0 -}; - -const GVecGen4 uqsub_op[4] = { - { .fniv = gen_uqsub_vec, - .fno = gen_helper_gvec_uqsub_b, - .opt_opc = vecop_list_uqsub, - .write_aofs = true, - .vece = MO_8 }, - { .fniv = gen_uqsub_vec, - .fno = gen_helper_gvec_uqsub_h, - .opt_opc = vecop_list_uqsub, - .write_aofs = true, - .vece = MO_16 }, - { .fniv = gen_uqsub_vec, - .fno = gen_helper_gvec_uqsub_s, - .opt_opc = vecop_list_uqsub, - .write_aofs = true, - .vece = MO_32 }, - { .fniv = gen_uqsub_vec, - .fno = gen_helper_gvec_uqsub_d, - .opt_opc = vecop_list_uqsub, - .write_aofs = true, - .vece = MO_64 }, -}; +void gen_gvec_uqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_ussub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_uqsub_vec, + .fno = gen_helper_gvec_uqsub_b, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_8 }, + { .fniv = gen_uqsub_vec, + .fno = gen_helper_gvec_uqsub_h, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_16 }, + { .fniv = gen_uqsub_vec, + .fno = gen_helper_gvec_uqsub_s, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_32 }, + { .fniv = gen_uqsub_vec, + .fno = gen_helper_gvec_uqsub_d, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_64 }, + }; + tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), + rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} static void gen_sqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, TCGv_vec a, TCGv_vec b) @@ -XXX,XX +XXX,XX @@ static void gen_sqsub_vec(unsigned vece, TCGv_vec t, TCGv_vec sat, tcg_temp_free_vec(x); } -static const TCGOpcode vecop_list_sqsub[] = { - INDEX_op_sssub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0 -}; - -const GVecGen4 sqsub_op[4] = { - { .fniv = gen_sqsub_vec, - .fno = gen_helper_gvec_sqsub_b, - .opt_opc = vecop_list_sqsub, - .write_aofs = true, - .vece = MO_8 }, - { .fniv = gen_sqsub_vec, - .fno = gen_helper_gvec_sqsub_h, - .opt_opc = vecop_list_sqsub, - .write_aofs = true, - .vece = MO_16 }, - { .fniv = gen_sqsub_vec, - .fno = gen_helper_gvec_sqsub_s, - .opt_opc = vecop_list_sqsub, - .write_aofs = true, - .vece = MO_32 }, - { .fniv = gen_sqsub_vec, - .fno = gen_helper_gvec_sqsub_d, - .opt_opc = vecop_list_sqsub, - .write_aofs = true, - .vece = MO_64 }, -}; +void gen_gvec_sqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sssub_vec, INDEX_op_cmp_vec, INDEX_op_sub_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_sqsub_vec, + .fno = gen_helper_gvec_sqsub_b, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_8 }, + { .fniv = gen_sqsub_vec, + .fno = gen_helper_gvec_sqsub_h, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_16 }, + { .fniv = gen_sqsub_vec, + .fno = gen_helper_gvec_sqsub_s, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_32 }, + { .fniv = gen_sqsub_vec, + .fno = gen_helper_gvec_sqsub_d, + .opt_opc = vecop_list, + .write_aofs = true, + .vece = MO_64 }, + }; + tcg_gen_gvec_4(rd_ofs, offsetof(CPUARMState, vfp.qc), + rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> These operations do not touch fp_status. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 4 ++-- target/arm/translate-a64.c | 5 ++--- target/arm/translate.c | 12 ++---------- target/arm/vfp_helper.c | 5 ++--- 4 files changed, 8 insertions(+), 18 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(recpe_f64, TCG_CALL_NO_RWG, f64, f64, ptr) DEF_HELPER_FLAGS_2(rsqrte_f16, TCG_CALL_NO_RWG, f16, f16, ptr) DEF_HELPER_FLAGS_2(rsqrte_f32, TCG_CALL_NO_RWG, f32, f32, ptr) DEF_HELPER_FLAGS_2(rsqrte_f64, TCG_CALL_NO_RWG, f64, f64, ptr) -DEF_HELPER_2(recpe_u32, i32, i32, ptr) -DEF_HELPER_FLAGS_2(rsqrte_u32, TCG_CALL_NO_RWG, i32, i32, ptr) +DEF_HELPER_FLAGS_1(recpe_u32, TCG_CALL_NO_RWG, i32, i32) +DEF_HELPER_FLAGS_1(rsqrte_u32, TCG_CALL_NO_RWG, i32, i32) DEF_HELPER_FLAGS_4(neon_tbl, TCG_CALL_NO_RWG, i32, i32, i32, ptr, i32) DEF_HELPER_3(shl_cc, i32, env, i32, i32) 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 handle_2misc_reciprocal(DisasContext *s, int opcode, switch (opcode) { case 0x3c: /* URECPE */ - gen_helper_recpe_u32(tcg_res, tcg_op, fpst); + gen_helper_recpe_u32(tcg_res, tcg_op); break; case 0x3d: /* FRECPE */ gen_helper_recpe_f32(tcg_res, tcg_op, fpst); @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - need_fpstatus = true; break; case 0x1e: /* FRINT32Z */ case 0x1f: /* FRINT64Z */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) gen_helper_rints_exact(tcg_res, tcg_op, tcg_fpstatus); break; case 0x7c: /* URSQRTE */ - gen_helper_rsqrte_u32(tcg_res, tcg_op, tcg_fpstatus); + gen_helper_rsqrte_u32(tcg_res, tcg_op); break; case 0x1e: /* FRINT32Z */ case 0x5e: /* FRINT32X */ diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) break; } case NEON_2RM_VRECPE: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_recpe_u32(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); + gen_helper_recpe_u32(tmp, tmp); break; - } case NEON_2RM_VRSQRTE: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_rsqrte_u32(tmp, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); + gen_helper_rsqrte_u32(tmp, tmp); break; - } case NEON_2RM_VRECPE_F: { TCGv_ptr fpstatus = get_fpstatus_ptr(1); diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ float64 HELPER(rsqrte_f64)(float64 input, void *fpstp) return make_float64(val); } -uint32_t HELPER(recpe_u32)(uint32_t a, void *fpstp) +uint32_t HELPER(recpe_u32)(uint32_t a) { - /* float_status *s = fpstp; */ int input, estimate; if ((a & 0x80000000) == 0) { @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(recpe_u32)(uint32_t a, void *fpstp) return deposit32(0, (32 - 9), 9, estimate); } -uint32_t HELPER(rsqrte_u32)(uint32_t a, void *fpstp) +uint32_t HELPER(rsqrte_u32)(uint32_t a) { int estimate; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Provide a functional interface for the vector expansion. This fits better with the existing set of helpers that we provide for other operations. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 5 ++++ target/arm/translate-a64.c | 34 ++---------------------- target/arm/translate.c | 54 +++++++++++++++++++------------------- 3 files changed, 34 insertions(+), 59 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 @@ void gen_gvec_sri(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, void gen_gvec_sli(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, int64_t shift, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_sqrdmlah_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_sqrdmlsh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ 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 gen_gvec_op3_ool(DisasContext *s, bool is_q, int rd, is_q ? 16 : 8, vec_full_reg_size(s), data, fn); } -/* Expand a 3-operand + env pointer operation using - * an out-of-line helper. - */ -static void gen_gvec_op3_env(DisasContext *s, bool is_q, int rd, - int rn, int rm, gen_helper_gvec_3_ptr *fn) -{ - tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), cpu_env, - is_q ? 16 : 8, vec_full_reg_size(s), 0, fn); -} - /* Expand a 3-operand + fpstatus pointer + simd data value operation using * an out-of-line helper. */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) switch (opcode) { case 0x0: /* SQRDMLAH (vector) */ - switch (size) { - case 1: - gen_gvec_op3_env(s, is_q, rd, rn, rm, gen_helper_gvec_qrdmlah_s16); - break; - case 2: - gen_gvec_op3_env(s, is_q, rd, rn, rm, gen_helper_gvec_qrdmlah_s32); - break; - default: - g_assert_not_reached(); - } + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqrdmlah_qc, size); return; case 0x1: /* SQRDMLSH (vector) */ - switch (size) { - case 1: - gen_gvec_op3_env(s, is_q, rd, rn, rm, gen_helper_gvec_qrdmlsh_s16); - break; - case 2: - gen_gvec_op3_env(s, is_q, rd, rn, rm, gen_helper_gvec_qrdmlsh_s32); - break; - default: - g_assert_not_reached(); - } + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqrdmlsh_qc, size); return; case 0x2: /* SDOT / UDOT */ 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 const uint8_t neon_2rm_sizes[] = { [NEON_2RM_VCVT_UF] = 0x4, }; - -/* Expand v8.1 simd helper. */ -static int do_v81_helper(DisasContext *s, gen_helper_gvec_3_ptr *fn, - int q, int rd, int rn, int rm) +void gen_gvec_sqrdmlah_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) { - if (dc_isar_feature(aa32_rdm, s)) { - int opr_sz = (1 + q) * 8; - tcg_gen_gvec_3_ptr(vfp_reg_offset(1, rd), - vfp_reg_offset(1, rn), - vfp_reg_offset(1, rm), cpu_env, - opr_sz, opr_sz, 0, fn); - return 0; - } - return 1; + static gen_helper_gvec_3_ptr * const fns[2] = { + gen_helper_gvec_qrdmlah_s16, gen_helper_gvec_qrdmlah_s32 + }; + tcg_debug_assert(vece >= 1 && vece <= 2); + tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, cpu_env, + opr_sz, max_sz, 0, fns[vece - 1]); +} + +void gen_gvec_sqrdmlsh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static gen_helper_gvec_3_ptr * const fns[2] = { + gen_helper_gvec_qrdmlsh_s16, gen_helper_gvec_qrdmlsh_s32 + }; + tcg_debug_assert(vece >= 1 && vece <= 2); + tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, cpu_env, + opr_sz, max_sz, 0, fns[vece - 1]); } #define GEN_CMP0(NAME, COND) \ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) break; /* VPADD */ } /* VQRDMLAH */ - switch (size) { - case 1: - return do_v81_helper(s, gen_helper_gvec_qrdmlah_s16, - q, rd, rn, rm); - case 2: - return do_v81_helper(s, gen_helper_gvec_qrdmlah_s32, - q, rd, rn, rm); + if (dc_isar_feature(aa32_rdm, s) && (size == 1 || size == 2)) { + gen_gvec_sqrdmlah_qc(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + return 0; } return 1; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) break; } /* VQRDMLSH */ - switch (size) { - case 1: - return do_v81_helper(s, gen_helper_gvec_qrdmlsh_s16, - q, rd, rn, rm); - case 2: - return do_v81_helper(s, gen_helper_gvec_qrdmlsh_s32, - q, rd, rn, rm); + if (dc_isar_feature(aa32_rdm, s) && (size == 1 || size == 2)) { + gen_gvec_sqrdmlsh_qc(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + return 0; } return 1; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Pass a pointer directly to env->vfp.qc[0], rather than env. This will allow SVE2, which does not modify QC, to pass a pointer to dummy storage. Change the return type of inl_qrdml.h_s16 to match the sense of the operation: signed. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 18 ++++++++--- target/arm/vec_helper.c | 70 +++++++++++++++++++++++------------------ 2 files changed, 54 insertions(+), 34 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static const uint8_t neon_2rm_sizes[] = { [NEON_2RM_VCVT_UF] = 0x4, }; +static void gen_gvec_fn3_qc(uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, + uint32_t opr_sz, uint32_t max_sz, + gen_helper_gvec_3_ptr *fn) +{ + TCGv_ptr qc_ptr = tcg_temp_new_ptr(); + + tcg_gen_addi_ptr(qc_ptr, cpu_env, offsetof(CPUARMState, vfp.qc)); + tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, qc_ptr, + opr_sz, max_sz, 0, fn); + tcg_temp_free_ptr(qc_ptr); +} + void gen_gvec_sqrdmlah_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) { @@ -XXX,XX +XXX,XX @@ void gen_gvec_sqrdmlah_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, gen_helper_gvec_qrdmlah_s16, gen_helper_gvec_qrdmlah_s32 }; tcg_debug_assert(vece >= 1 && vece <= 2); - tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, cpu_env, - opr_sz, max_sz, 0, fns[vece - 1]); + gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]); } void gen_gvec_sqrdmlsh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, @@ -XXX,XX +XXX,XX @@ void gen_gvec_sqrdmlsh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, gen_helper_gvec_qrdmlsh_s16, gen_helper_gvec_qrdmlsh_s32 }; tcg_debug_assert(vece >= 1 && vece <= 2); - tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, cpu_env, - opr_sz, max_sz, 0, fns[vece - 1]); + gen_gvec_fn3_qc(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, fns[vece - 1]); } #define GEN_CMP0(NAME, COND) \ diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ #define H4(x) (x) #endif -#define SET_QC() env->vfp.qc[0] = 1 - static void clear_tail(void *vd, uintptr_t opr_sz, uintptr_t max_sz) { uint64_t *d = vd + opr_sz; @@ -XXX,XX +XXX,XX @@ static void clear_tail(void *vd, uintptr_t opr_sz, uintptr_t max_sz) } /* Signed saturating rounding doubling multiply-accumulate high half, 16-bit */ -static uint16_t inl_qrdmlah_s16(CPUARMState *env, int16_t src1, - int16_t src2, int16_t src3) +static int16_t inl_qrdmlah_s16(int16_t src1, int16_t src2, + int16_t src3, uint32_t *sat) { /* Simplify: * = ((a3 << 16) + ((e1 * e2) << 1) + (1 << 15)) >> 16 @@ -XXX,XX +XXX,XX @@ static uint16_t inl_qrdmlah_s16(CPUARMState *env, int16_t src1, ret = ((int32_t)src3 << 15) + ret + (1 << 14); ret >>= 15; if (ret != (int16_t)ret) { - SET_QC(); + *sat = 1; ret = (ret < 0 ? -0x8000 : 0x7fff); } return ret; @@ -XXX,XX +XXX,XX @@ static uint16_t inl_qrdmlah_s16(CPUARMState *env, int16_t src1, uint32_t HELPER(neon_qrdmlah_s16)(CPUARMState *env, uint32_t src1, uint32_t src2, uint32_t src3) { - uint16_t e1 = inl_qrdmlah_s16(env, src1, src2, src3); - uint16_t e2 = inl_qrdmlah_s16(env, src1 >> 16, src2 >> 16, src3 >> 16); + uint32_t *sat = &env->vfp.qc[0]; + uint16_t e1 = inl_qrdmlah_s16(src1, src2, src3, sat); + uint16_t e2 = inl_qrdmlah_s16(src1 >> 16, src2 >> 16, src3 >> 16, sat); return deposit32(e1, 16, 16, e2); } void HELPER(gvec_qrdmlah_s16)(void *vd, void *vn, void *vm, - void *ve, uint32_t desc) + void *vq, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); int16_t *d = vd; int16_t *n = vn; int16_t *m = vm; - CPUARMState *env = ve; uintptr_t i; for (i = 0; i < opr_sz / 2; ++i) { - d[i] = inl_qrdmlah_s16(env, n[i], m[i], d[i]); + d[i] = inl_qrdmlah_s16(n[i], m[i], d[i], vq); } clear_tail(d, opr_sz, simd_maxsz(desc)); } /* Signed saturating rounding doubling multiply-subtract high half, 16-bit */ -static uint16_t inl_qrdmlsh_s16(CPUARMState *env, int16_t src1, - int16_t src2, int16_t src3) +static int16_t inl_qrdmlsh_s16(int16_t src1, int16_t src2, + int16_t src3, uint32_t *sat) { /* Similarly, using subtraction: * = ((a3 << 16) - ((e1 * e2) << 1) + (1 << 15)) >> 16 @@ -XXX,XX +XXX,XX @@ static uint16_t inl_qrdmlsh_s16(CPUARMState *env, int16_t src1, ret = ((int32_t)src3 << 15) - ret + (1 << 14); ret >>= 15; if (ret != (int16_t)ret) { - SET_QC(); + *sat = 1; ret = (ret < 0 ? -0x8000 : 0x7fff); } return ret; @@ -XXX,XX +XXX,XX @@ static uint16_t inl_qrdmlsh_s16(CPUARMState *env, int16_t src1, uint32_t HELPER(neon_qrdmlsh_s16)(CPUARMState *env, uint32_t src1, uint32_t src2, uint32_t src3) { - uint16_t e1 = inl_qrdmlsh_s16(env, src1, src2, src3); - uint16_t e2 = inl_qrdmlsh_s16(env, src1 >> 16, src2 >> 16, src3 >> 16); + uint32_t *sat = &env->vfp.qc[0]; + uint16_t e1 = inl_qrdmlsh_s16(src1, src2, src3, sat); + uint16_t e2 = inl_qrdmlsh_s16(src1 >> 16, src2 >> 16, src3 >> 16, sat); return deposit32(e1, 16, 16, e2); } void HELPER(gvec_qrdmlsh_s16)(void *vd, void *vn, void *vm, - void *ve, uint32_t desc) + void *vq, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); int16_t *d = vd; int16_t *n = vn; int16_t *m = vm; - CPUARMState *env = ve; uintptr_t i; for (i = 0; i < opr_sz / 2; ++i) { - d[i] = inl_qrdmlsh_s16(env, n[i], m[i], d[i]); + d[i] = inl_qrdmlsh_s16(n[i], m[i], d[i], vq); } clear_tail(d, opr_sz, simd_maxsz(desc)); } /* Signed saturating rounding doubling multiply-accumulate high half, 32-bit */ -uint32_t HELPER(neon_qrdmlah_s32)(CPUARMState *env, int32_t src1, - int32_t src2, int32_t src3) +static int32_t inl_qrdmlah_s32(int32_t src1, int32_t src2, + int32_t src3, uint32_t *sat) { /* Simplify similarly to int_qrdmlah_s16 above. */ int64_t ret = (int64_t)src1 * src2; ret = ((int64_t)src3 << 31) + ret + (1 << 30); ret >>= 31; if (ret != (int32_t)ret) { - SET_QC(); + *sat = 1; ret = (ret < 0 ? INT32_MIN : INT32_MAX); } return ret; } +uint32_t HELPER(neon_qrdmlah_s32)(CPUARMState *env, int32_t src1, + int32_t src2, int32_t src3) +{ + uint32_t *sat = &env->vfp.qc[0]; + return inl_qrdmlah_s32(src1, src2, src3, sat); +} + void HELPER(gvec_qrdmlah_s32)(void *vd, void *vn, void *vm, - void *ve, uint32_t desc) + void *vq, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); int32_t *d = vd; int32_t *n = vn; int32_t *m = vm; - CPUARMState *env = ve; uintptr_t i; for (i = 0; i < opr_sz / 4; ++i) { - d[i] = helper_neon_qrdmlah_s32(env, n[i], m[i], d[i]); + d[i] = inl_qrdmlah_s32(n[i], m[i], d[i], vq); } clear_tail(d, opr_sz, simd_maxsz(desc)); } /* Signed saturating rounding doubling multiply-subtract high half, 32-bit */ -uint32_t HELPER(neon_qrdmlsh_s32)(CPUARMState *env, int32_t src1, - int32_t src2, int32_t src3) +static int32_t inl_qrdmlsh_s32(int32_t src1, int32_t src2, + int32_t src3, uint32_t *sat) { /* Simplify similarly to int_qrdmlsh_s16 above. */ int64_t ret = (int64_t)src1 * src2; ret = ((int64_t)src3 << 31) - ret + (1 << 30); ret >>= 31; if (ret != (int32_t)ret) { - SET_QC(); + *sat = 1; ret = (ret < 0 ? INT32_MIN : INT32_MAX); } return ret; } +uint32_t HELPER(neon_qrdmlsh_s32)(CPUARMState *env, int32_t src1, + int32_t src2, int32_t src3) +{ + uint32_t *sat = &env->vfp.qc[0]; + return inl_qrdmlsh_s32(src1, src2, src3, sat); +} + void HELPER(gvec_qrdmlsh_s32)(void *vd, void *vn, void *vm, - void *ve, uint32_t desc) + void *vq, uint32_t desc) { uintptr_t opr_sz = simd_oprsz(desc); int32_t *d = vd; int32_t *n = vn; int32_t *m = vm; - CPUARMState *env = ve; uintptr_t i; for (i = 0; i < opr_sz / 4; ++i) { - d[i] = helper_neon_qrdmlsh_s32(env, n[i], m[i], d[i]); + d[i] = inl_qrdmlsh_s32(n[i], m[i], d[i], vq); } clear_tail(d, opr_sz, simd_maxsz(desc)); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Must clear the tail for AdvSIMD when SVE is enabled. Fixes: ca40a6e6e39 Cc: qemu-stable@nongnu.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/vec_helper.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ d[i + j] = TYPE##_mul(n[i + j], mm, stat); \ } \ } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ } DO_MUL_IDX(gvec_fmul_idx_h, float16, H2) @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, \ mm, a[i + j], 0, stat); \ } \ } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ } DO_FMLA_IDX(gvec_fmla_idx_h, float16, H2) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Include 64-bit element size in preparation for SVE2. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 10 +++ target/arm/translate.h | 5 ++ target/arm/translate-a64.c | 8 ++- target/arm/translate.c | 133 ++++++++++++++++++++++++++++++++++++- target/arm/vec_helper.c | 24 +++++++ 5 files changed, 176 insertions(+), 4 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(gvec_sli_h, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_sli_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_FLAGS_3(gvec_sli_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sabd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sabd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_uabd_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_uabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_uabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_uabd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_sqrdmlah_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, void gen_gvec_sqrdmlsh_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_sabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_uabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_smin, size); } return; + case 0xe: /* SABD, UABD */ + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uabd, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sabd, size); + } + return; case 0x10: /* ADD, SUB */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_sub, size); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genenvfn = fns[size][u]; break; } - case 0xe: /* SABD, UABD */ case 0xf: /* SABA, UABA */ { static NeonGenTwoOpFn * const fns[3][2] = { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ void gen_gvec_sqsub_qc(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } +static void gen_sabd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_sub_i32(t, a, b); + tcg_gen_sub_i32(d, b, a); + tcg_gen_movcond_i32(TCG_COND_LT, d, a, b, d, t); + tcg_temp_free_i32(t); +} + +static void gen_sabd_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_sub_i64(t, a, b); + tcg_gen_sub_i64(d, b, a); + tcg_gen_movcond_i64(TCG_COND_LT, d, a, b, d, t); + tcg_temp_free_i64(t); +} + +static void gen_sabd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + tcg_gen_smin_vec(vece, t, a, b); + tcg_gen_smax_vec(vece, d, a, b); + tcg_gen_sub_vec(vece, d, d, t); + tcg_temp_free_vec(t); +} + +void gen_gvec_sabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sub_vec, INDEX_op_smin_vec, INDEX_op_smax_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fniv = gen_sabd_vec, + .fno = gen_helper_gvec_sabd_b, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fniv = gen_sabd_vec, + .fno = gen_helper_gvec_sabd_h, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_sabd_i32, + .fniv = gen_sabd_vec, + .fno = gen_helper_gvec_sabd_s, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_sabd_i64, + .fniv = gen_sabd_vec, + .fno = gen_helper_gvec_sabd_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +static void gen_uabd_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + + tcg_gen_sub_i32(t, a, b); + tcg_gen_sub_i32(d, b, a); + tcg_gen_movcond_i32(TCG_COND_LTU, d, a, b, d, t); + tcg_temp_free_i32(t); +} + +static void gen_uabd_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_sub_i64(t, a, b); + tcg_gen_sub_i64(d, b, a); + tcg_gen_movcond_i64(TCG_COND_LTU, d, a, b, d, t); + tcg_temp_free_i64(t); +} + +static void gen_uabd_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + tcg_gen_umin_vec(vece, t, a, b); + tcg_gen_umax_vec(vece, d, a, b); + tcg_gen_sub_vec(vece, d, d, t); + tcg_temp_free_vec(t); +} + +void gen_gvec_uabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sub_vec, INDEX_op_umin_vec, INDEX_op_umax_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fniv = gen_uabd_vec, + .fno = gen_helper_gvec_uabd_b, + .opt_opc = vecop_list, + .vece = MO_8 }, + { .fniv = gen_uabd_vec, + .fno = gen_helper_gvec_uabd_h, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fni4 = gen_uabd_i32, + .fniv = gen_uabd_vec, + .fno = gen_helper_gvec_uabd_s, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fni8 = gen_uabd_i64, + .fniv = gen_uabd_vec, + .fno = gen_helper_gvec_uabd_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. We process data in a mixture of 32-bit and 64-bit chunks. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } return 1; + case NEON_3R_VABD: + if (u) { + gen_gvec_uabd(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } else { + gen_gvec_sabd(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } + return 0; + case NEON_3R_VADD_VSUB: case NEON_3R_LOGIC: case NEON_3R_VMAX: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VQRSHL: GEN_NEON_INTEGER_OP_ENV(qrshl); break; - case NEON_3R_VABD: - GEN_NEON_INTEGER_OP(abd); - break; case NEON_3R_VABA: GEN_NEON_INTEGER_OP(abd); tcg_temp_free_i32(tmp2); diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ DO_CMP0(gvec_cgt0_h, int16_t, >) DO_CMP0(gvec_cge0_h, int16_t, >=) #undef DO_CMP0 + +#define DO_ABD(NAME, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + TYPE *d = vd, *n = vn, *m = vm; \ + \ + for (i = 0; i < opr_sz / sizeof(TYPE); ++i) { \ + d[i] = n[i] < m[i] ? m[i] - n[i] : n[i] - m[i]; \ + } \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ +} + +DO_ABD(gvec_sabd_b, int8_t) +DO_ABD(gvec_sabd_h, int16_t) +DO_ABD(gvec_sabd_s, int32_t) +DO_ABD(gvec_sabd_d, int64_t) + +DO_ABD(gvec_uabd_b, uint8_t) +DO_ABD(gvec_uabd_h, uint16_t) +DO_ABD(gvec_uabd_s, uint32_t) +DO_ABD(gvec_uabd_d, uint64_t) + +#undef DO_ABD -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Include 64-bit element size in preparation for SVE2. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200513163245.17915-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 17 +++-- target/arm/translate.h | 5 ++ target/arm/neon_helper.c | 10 --- target/arm/translate-a64.c | 17 ++--- target/arm/translate.c | 134 +++++++++++++++++++++++++++++++++++-- target/arm/vec_helper.c | 24 +++++++ 6 files changed, 174 insertions(+), 33 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(neon_pmax_s8, i32, i32, i32) DEF_HELPER_2(neon_pmax_u16, i32, i32, i32) DEF_HELPER_2(neon_pmax_s16, i32, i32, i32) -DEF_HELPER_2(neon_abd_u8, i32, i32, i32) -DEF_HELPER_2(neon_abd_s8, i32, i32, i32) -DEF_HELPER_2(neon_abd_u16, i32, i32, i32) -DEF_HELPER_2(neon_abd_s16, i32, i32, i32) -DEF_HELPER_2(neon_abd_u32, i32, i32, i32) -DEF_HELPER_2(neon_abd_s32, i32, i32, i32) - DEF_HELPER_2(neon_shl_u16, i32, i32, i32) DEF_HELPER_2(neon_shl_s16, i32, i32, i32) DEF_HELPER_2(neon_rshl_u8, i32, i32, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(gvec_uabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_uabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_uabd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_saba_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_saba_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_saba_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_saba_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_uaba_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_uaba_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_uaba_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_uaba_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_sabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, void gen_gvec_uabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_saba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon_helper.c +++ b/target/arm/neon_helper.c @@ -XXX,XX +XXX,XX @@ NEON_POP(pmax_s16, neon_s16, 2) NEON_POP(pmax_u16, neon_u16, 2) #undef NEON_FN -#define NEON_FN(dest, src1, src2) \ - dest = (src1 > src2) ? (src1 - src2) : (src2 - src1) -NEON_VOP(abd_s8, neon_s8, 4) -NEON_VOP(abd_u8, neon_u8, 4) -NEON_VOP(abd_s16, neon_s16, 2) -NEON_VOP(abd_u16, neon_u16, 2) -NEON_VOP(abd_s32, neon_s32, 1) -NEON_VOP(abd_u32, neon_u32, 1) -#undef NEON_FN - #define NEON_FN(dest, src1, src2) do { \ int8_t tmp; \ tmp = (int8_t)src2; \ diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sabd, size); } return; + case 0xf: /* SABA, UABA */ + if (u) { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_uaba, size); + } else { + gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_saba, size); + } + return; case 0x10: /* ADD, SUB */ if (u) { gen_gvec_fn3(s, is_q, rd, rn, rm, tcg_gen_gvec_sub, size); @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) genenvfn = fns[size][u]; break; } - case 0xf: /* SABA, UABA */ - { - static NeonGenTwoOpFn * const fns[3][2] = { - { gen_helper_neon_abd_s8, gen_helper_neon_abd_u8 }, - { gen_helper_neon_abd_s16, gen_helper_neon_abd_u16 }, - { gen_helper_neon_abd_s32, gen_helper_neon_abd_u32 }, - }; - genfn = fns[size][u]; - break; - } case 0x16: /* SQDMULH, SQRDMULH */ { static NeonGenTwoOpEnvFn * const fns[2][2] = { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ void gen_gvec_uabd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); } +static void gen_saba_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + gen_sabd_i32(t, a, b); + tcg_gen_add_i32(d, d, t); + tcg_temp_free_i32(t); +} + +static void gen_saba_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + gen_sabd_i64(t, a, b); + tcg_gen_add_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_saba_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + gen_sabd_vec(vece, t, a, b); + tcg_gen_add_vec(vece, d, d, t); + tcg_temp_free_vec(t); +} + +void gen_gvec_saba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sub_vec, INDEX_op_add_vec, + INDEX_op_smin_vec, INDEX_op_smax_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fniv = gen_saba_vec, + .fno = gen_helper_gvec_saba_b, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_8 }, + { .fniv = gen_saba_vec, + .fno = gen_helper_gvec_saba_h, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_16 }, + { .fni4 = gen_saba_i32, + .fniv = gen_saba_vec, + .fno = gen_helper_gvec_saba_s, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_32 }, + { .fni8 = gen_saba_i64, + .fniv = gen_saba_vec, + .fno = gen_helper_gvec_saba_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + +static void gen_uaba_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + TCGv_i32 t = tcg_temp_new_i32(); + gen_uabd_i32(t, a, b); + tcg_gen_add_i32(d, d, t); + tcg_temp_free_i32(t); +} + +static void gen_uaba_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + TCGv_i64 t = tcg_temp_new_i64(); + gen_uabd_i64(t, a, b); + tcg_gen_add_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_uaba_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + gen_uabd_vec(vece, t, a, b); + tcg_gen_add_vec(vece, d, d, t); + tcg_temp_free_vec(t); +} + +void gen_gvec_uaba(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sub_vec, INDEX_op_add_vec, + INDEX_op_umin_vec, INDEX_op_umax_vec, 0 + }; + static const GVecGen3 ops[4] = { + { .fniv = gen_uaba_vec, + .fno = gen_helper_gvec_uaba_b, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_8 }, + { .fniv = gen_uaba_vec, + .fno = gen_helper_gvec_uaba_h, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_16 }, + { .fni4 = gen_uaba_i32, + .fniv = gen_uaba_vec, + .fno = gen_helper_gvec_uaba_s, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_32 }, + { .fni8 = gen_uaba_i64, + .fniv = gen_uaba_vec, + .fno = gen_helper_gvec_uaba_d, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 }, + }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &ops[vece]); +} + /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. We process data in a mixture of 32-bit and 64-bit chunks. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } return 0; + case NEON_3R_VABA: + if (u) { + gen_gvec_uaba(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } else { + gen_gvec_saba(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } + return 0; + case NEON_3R_VADD_VSUB: case NEON_3R_LOGIC: case NEON_3R_VMAX: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VQRSHL: GEN_NEON_INTEGER_OP_ENV(qrshl); break; - case NEON_3R_VABA: - GEN_NEON_INTEGER_OP(abd); - tcg_temp_free_i32(tmp2); - tmp2 = neon_load_reg(rd, pass); - gen_neon_add(size, tmp, tmp2); - break; case NEON_3R_VPMAX: GEN_NEON_INTEGER_OP(pmax); break; diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ DO_ABD(gvec_uabd_s, uint32_t) DO_ABD(gvec_uabd_d, uint64_t) #undef DO_ABD + +#define DO_ABA(NAME, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + TYPE *d = vd, *n = vn, *m = vm; \ + \ + for (i = 0; i < opr_sz / sizeof(TYPE); ++i) { \ + d[i] += n[i] < m[i] ? m[i] - n[i] : n[i] - m[i]; \ + } \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ +} + +DO_ABA(gvec_saba_b, int8_t) +DO_ABA(gvec_saba_h, int16_t) +DO_ABA(gvec_saba_s, int32_t) +DO_ABA(gvec_saba_d, int64_t) + +DO_ABA(gvec_uaba_b, uint8_t) +DO_ABA(gvec_uaba_h, uint16_t) +DO_ABA(gvec_uaba_s, uint32_t) +DO_ABA(gvec_uaba_d, uint64_t) + +#undef DO_ABA -- 2.20.1 From: Patrick Williams <patrick@stwcx.xyz> Sonora Pass is a 2 socket x86 motherboard designed by Facebook and supported by OpenBMC. Strapping configuration was obtained from hardware and i2c configuration is based on dts found at: https://github.com/facebook/openbmc-linux/blob/1633c87b8ba7c162095787c988979b748ba65dc8/arch/arm/boot/dts/aspeed-bmc-facebook-sonorapass.dts Booted a test image of http://github.com/facebook/openbmc to login prompt. Signed-off-by: Patrick Williams <patrick@stwcx.xyz> Reviewed-by: Amithash Prasad <amithash@fb.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> [PMM: fixed block comment style nit] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed.c | 78 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 78 insertions(+) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ struct AspeedBoardState { SCU_AST2500_HW_STRAP_ACPI_ENABLE | \ SCU_HW_STRAP_SPI_MODE(SCU_HW_STRAP_SPI_MASTER)) +/* Sonorapass hardware value: 0xF100D216 */ +#define SONORAPASS_BMC_HW_STRAP1 ( \ + SCU_AST2500_HW_STRAP_SPI_AUTOFETCH_ENABLE | \ + SCU_AST2500_HW_STRAP_GPIO_STRAP_ENABLE | \ + SCU_AST2500_HW_STRAP_UART_DEBUG | \ + SCU_AST2500_HW_STRAP_RESERVED28 | \ + SCU_AST2500_HW_STRAP_DDR4_ENABLE | \ + SCU_HW_STRAP_VGA_CLASS_CODE | \ + SCU_HW_STRAP_LPC_RESET_PIN | \ + SCU_HW_STRAP_SPI_MODE(SCU_HW_STRAP_SPI_MASTER) | \ + SCU_AST2500_HW_STRAP_SET_AXI_AHB_RATIO(AXI_AHB_RATIO_2_1) | \ + SCU_HW_STRAP_VGA_BIOS_ROM | \ + SCU_HW_STRAP_VGA_SIZE_SET(VGA_16M_DRAM) | \ + SCU_AST2500_HW_STRAP_RESERVED1) + /* Swift hardware value: 0xF11AD206 */ #define SWIFT_BMC_HW_STRAP1 ( \ AST2500_HW_STRAP1_DEFAULTS | \ @@ -XXX,XX +XXX,XX @@ static void swift_bmc_i2c_init(AspeedBoardState *bmc) i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 12), "tmp105", 0x4a); } +static void sonorapass_bmc_i2c_init(AspeedBoardState *bmc) +{ + AspeedSoCState *soc = &bmc->soc; + + /* bus 2 : */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 2), "tmp105", 0x48); + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 2), "tmp105", 0x49); + /* bus 2 : pca9546 @ 0x73 */ + + /* bus 3 : pca9548 @ 0x70 */ + + /* bus 4 : */ + uint8_t *eeprom4_54 = g_malloc0(8 * 1024); + smbus_eeprom_init_one(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 4), 0x54, + eeprom4_54); + /* PCA9539 @ 0x76, but PCA9552 is compatible */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 4), "pca9552", 0x76); + /* PCA9539 @ 0x77, but PCA9552 is compatible */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 4), "pca9552", 0x77); + + /* bus 6 : */ + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 6), "tmp105", 0x48); + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 6), "tmp105", 0x49); + /* bus 6 : pca9546 @ 0x73 */ + + /* bus 8 : */ + uint8_t *eeprom8_56 = g_malloc0(8 * 1024); + smbus_eeprom_init_one(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 8), 0x56, + eeprom8_56); + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 8), "pca9552", 0x60); + i2c_create_slave(aspeed_i2c_get_bus(DEVICE(&soc->i2c), 8), "pca9552", 0x61); + /* bus 8 : adc128d818 @ 0x1d */ + /* bus 8 : adc128d818 @ 0x1f */ + + /* + * bus 13 : pca9548 @ 0x71 + * - channel 3: + * - tmm421 @ 0x4c + * - tmp421 @ 0x4e + * - tmp421 @ 0x4f + */ + +} + static void witherspoon_bmc_i2c_init(AspeedBoardState *bmc) { AspeedSoCState *soc = &bmc->soc; @@ -XXX,XX +XXX,XX @@ static void aspeed_machine_romulus_class_init(ObjectClass *oc, void *data) mc->default_ram_size = 512 * MiB; }; +static void aspeed_machine_sonorapass_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + AspeedMachineClass *amc = ASPEED_MACHINE_CLASS(oc); + + mc->desc = "OCP SonoraPass BMC (ARM1176)"; + amc->soc_name = "ast2500-a1"; + amc->hw_strap1 = SONORAPASS_BMC_HW_STRAP1; + amc->fmc_model = "mx66l1g45g"; + amc->spi_model = "mx66l1g45g"; + amc->num_cs = 2; + amc->i2c_init = sonorapass_bmc_i2c_init; + mc->default_ram_size = 512 * MiB; +}; + static void aspeed_machine_swift_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); @@ -XXX,XX +XXX,XX @@ static const TypeInfo aspeed_machine_types[] = { .name = MACHINE_TYPE_NAME("swift-bmc"), .parent = TYPE_ASPEED_MACHINE, .class_init = aspeed_machine_swift_class_init, + }, { + .name = MACHINE_TYPE_NAME("sonorapass-bmc"), + .parent = TYPE_ASPEED_MACHINE, + .class_init = aspeed_machine_sonorapass_class_init, }, { .name = MACHINE_TYPE_NAME("witherspoon-bmc"), .parent = TYPE_ASPEED_MACHINE, -- 2.20.1 From: Dongjiu Geng <gengdongjiu@huawei.com> The little end UUID is used in many places, so make NVDIMM_UUID_LE to a common macro to convert the UUID to a little end array. Reviewed-by: Xiang Zheng <zhengxiang9@huawei.com> Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Message-id: 20200512030609.19593-2-gengdongjiu@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/qemu/uuid.h | 27 +++++++++++++++++++++++++++ hw/acpi/nvdimm.c | 10 +++------- 2 files changed, 30 insertions(+), 7 deletions(-) diff --git a/include/qemu/uuid.h b/include/qemu/uuid.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/uuid.h +++ b/include/qemu/uuid.h @@ -XXX,XX +XXX,XX @@ typedef struct { }; } QemuUUID; +/** + * UUID_LE - converts the fields of UUID to little-endian array, + * each of parameters is the filed of UUID. + * + * @time_low: The low field of the timestamp + * @time_mid: The middle field of the timestamp + * @time_hi_and_version: The high field of the timestamp + * multiplexed with the version number + * @clock_seq_hi_and_reserved: The high field of the clock + * sequence multiplexed with the variant + * @clock_seq_low: The low field of the clock sequence + * @node0: The spatially unique node0 identifier + * @node1: The spatially unique node1 identifier + * @node2: The spatially unique node2 identifier + * @node3: The spatially unique node3 identifier + * @node4: The spatially unique node4 identifier + * @node5: The spatially unique node5 identifier + */ +#define UUID_LE(time_low, time_mid, time_hi_and_version, \ + clock_seq_hi_and_reserved, clock_seq_low, node0, node1, node2, \ + node3, node4, node5) \ + { (time_low) & 0xff, ((time_low) >> 8) & 0xff, ((time_low) >> 16) & 0xff, \ + ((time_low) >> 24) & 0xff, (time_mid) & 0xff, ((time_mid) >> 8) & 0xff, \ + (time_hi_and_version) & 0xff, ((time_hi_and_version) >> 8) & 0xff, \ + (clock_seq_hi_and_reserved), (clock_seq_low), (node0), (node1), (node2),\ + (node3), (node4), (node5) } + #define UUID_FMT "%02hhx%02hhx%02hhx%02hhx-" \ "%02hhx%02hhx-%02hhx%02hhx-" \ "%02hhx%02hhx-" \ diff --git a/hw/acpi/nvdimm.c b/hw/acpi/nvdimm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/nvdimm.c +++ b/hw/acpi/nvdimm.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/uuid.h" #include "hw/acpi/acpi.h" #include "hw/acpi/aml-build.h" #include "hw/acpi/bios-linker-loader.h" @@ -XXX,XX +XXX,XX @@ #include "hw/mem/nvdimm.h" #include "qemu/nvdimm-utils.h" -#define NVDIMM_UUID_LE(a, b, c, d0, d1, d2, d3, d4, d5, d6, d7) \ - { (a) & 0xff, ((a) >> 8) & 0xff, ((a) >> 16) & 0xff, ((a) >> 24) & 0xff, \ - (b) & 0xff, ((b) >> 8) & 0xff, (c) & 0xff, ((c) >> 8) & 0xff, \ - (d0), (d1), (d2), (d3), (d4), (d5), (d6), (d7) } - /* * define Byte Addressable Persistent Memory (PM) Region according to * ACPI 6.0: 5.2.25.1 System Physical Address Range Structure. */ static const uint8_t nvdimm_nfit_spa_uuid[] = - NVDIMM_UUID_LE(0x66f0d379, 0xb4f3, 0x4074, 0xac, 0x43, 0x0d, 0x33, - 0x18, 0xb7, 0x8c, 0xdb); + UUID_LE(0x66f0d379, 0xb4f3, 0x4074, 0xac, 0x43, 0x0d, 0x33, + 0x18, 0xb7, 0x8c, 0xdb); /* * NVDIMM Firmware Interface Table -- 2.20.1 From: Dongjiu Geng <gengdongjiu@huawei.com> RAS Virtualization feature is not supported now, so add a RAS machine option and disable it by default. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20200512030609.19593-3-gengdongjiu@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/virt.h | 1 + hw/arm/virt.c | 23 +++++++++++++++++++++++ 2 files changed, 24 insertions(+) diff --git a/include/hw/arm/virt.h b/include/hw/arm/virt.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/virt.h +++ b/include/hw/arm/virt.h @@ -XXX,XX +XXX,XX @@ typedef struct { bool highmem_ecam; bool its; bool virt; + bool ras; OnOffAuto acpi; VirtGICType gic_version; VirtIOMMUType iommu; diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void virt_set_acpi(Object *obj, Visitor *v, const char *name, visit_type_OnOffAuto(v, name, &vms->acpi, errp); } +static bool virt_get_ras(Object *obj, Error **errp) +{ + VirtMachineState *vms = VIRT_MACHINE(obj); + + return vms->ras; +} + +static void virt_set_ras(Object *obj, bool value, Error **errp) +{ + VirtMachineState *vms = VIRT_MACHINE(obj); + + vms->ras = value; +} + static char *virt_get_gic_version(Object *obj, Error **errp) { VirtMachineState *vms = VIRT_MACHINE(obj); @@ -XXX,XX +XXX,XX @@ static void virt_instance_init(Object *obj) "Valid values are none and smmuv3", NULL); + /* Default disallows RAS instantiation */ + vms->ras = false; + object_property_add_bool(obj, "ras", virt_get_ras, + virt_set_ras, NULL); + object_property_set_description(obj, "ras", + "Set on/off to enable/disable reporting host memory errors " + "to a KVM guest using ACPI and guest external abort exceptions", + NULL); + vms->irqmap = a15irqmap; virt_flash_create(vms); -- 2.20.1 From: Dongjiu Geng <gengdongjiu@huawei.com> Add APEI/GHES detailed design document Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20200512030609.19593-4-gengdongjiu@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/specs/acpi_hest_ghes.rst | 110 ++++++++++++++++++++++++++++++++++ docs/specs/index.rst | 1 + 2 files changed, 111 insertions(+) create mode 100644 docs/specs/acpi_hest_ghes.rst diff --git a/docs/specs/acpi_hest_ghes.rst b/docs/specs/acpi_hest_ghes.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/specs/acpi_hest_ghes.rst @@ -XXX,XX +XXX,XX @@ +APEI tables generating and CPER record +====================================== + +.. + Copyright (c) 2020 HUAWEI TECHNOLOGIES CO., LTD. + + This work is licensed under the terms of the GNU GPL, version 2 or later. + See the COPYING file in the top-level directory. + +Design Details +-------------- + +:: + + etc/acpi/tables etc/hardware_errors + ==================== =============================== + + +--------------------------+ +----------------------------+ + | | HEST | +--------->| error_block_address1 |------+ + | +--------------------------+ | +----------------------------+ | + | | GHES1 | | +------->| error_block_address2 |------+-+ + | +--------------------------+ | | +----------------------------+ | | + | | ................. | | | | .............. | | | + | | error_status_address-----+-+ | -----------------------------+ | | + | | ................. | | +--->| error_block_addressN |------+-+---+ + | | read_ack_register--------+-+ | | +----------------------------+ | | | + | | read_ack_preserve | +-+---+--->| read_ack_register1 | | | | + | | read_ack_write | | | +----------------------------+ | | | + + +--------------------------+ | +-+--->| read_ack_register2 | | | | + | | GHES2 | | | | +----------------------------+ | | | + + +--------------------------+ | | | | ............. | | | | + | | ................. | | | | +----------------------------+ | | | + | | error_status_address-----+---+ | | +->| read_ack_registerN | | | | + | | ................. | | | | +----------------------------+ | | | + | | read_ack_register--------+-----+ | | |Generic Error Status Block 1|<-----+ | | + | | read_ack_preserve | | | |-+------------------------+-+ | | + | | read_ack_write | | | | | CPER | | | | + + +--------------------------| | | | | CPER | | | | + | | ............... | | | | | .... | | | | + + +--------------------------+ | | | | CPER | | | | + | | GHESN | | | |-+------------------------+-| | | + + +--------------------------+ | | |Generic Error Status Block 2|<-------+ | + | | ................. | | | |-+------------------------+-+ | + | | error_status_address-----+-------+ | | | CPER | | | + | | ................. | | | | CPER | | | + | | read_ack_register--------+---------+ | | .... | | | + | | read_ack_preserve | | | CPER | | | + | | read_ack_write | +-+------------------------+-+ | + + +--------------------------+ | .......... | | + |----------------------------+ | + |Generic Error Status Block N |<----------+ + |-+-------------------------+-+ + | | CPER | | + | | CPER | | + | | .... | | + | | CPER | | + +-+-------------------------+-+ + + +(1) QEMU generates the ACPI HEST table. This table goes in the current + "etc/acpi/tables" fw_cfg blob. Each error source has different + notification types. + +(2) A new fw_cfg blob called "etc/hardware_errors" is introduced. QEMU + also needs to populate this blob. The "etc/hardware_errors" fw_cfg blob + contains an address registers table and an Error Status Data Block table. + +(3) The address registers table contains N Error Block Address entries + and N Read Ack Register entries. The size for each entry is 8-byte. + The Error Status Data Block table contains N Error Status Data Block + entries. The size for each entry is 4096(0x1000) bytes. The total size + for the "etc/hardware_errors" fw_cfg blob is (N * 8 * 2 + N * 4096) bytes. + N is the number of the kinds of hardware error sources. + +(4) QEMU generates the ACPI linker/loader script for the firmware. The + firmware pre-allocates memory for "etc/acpi/tables", "etc/hardware_errors" + and copies blob contents there. + +(5) QEMU generates N ADD_POINTER commands, which patch addresses in the + "error_status_address" fields of the HEST table with a pointer to the + corresponding "address registers" in the "etc/hardware_errors" blob. + +(6) QEMU generates N ADD_POINTER commands, which patch addresses in the + "read_ack_register" fields of the HEST table with a pointer to the + corresponding "read_ack_register" within the "etc/hardware_errors" blob. + +(7) QEMU generates N ADD_POINTER commands for the firmware, which patch + addresses in the "error_block_address" fields with a pointer to the + respective "Error Status Data Block" in the "etc/hardware_errors" blob. + +(8) QEMU defines a third and write-only fw_cfg blob which is called + "etc/hardware_errors_addr". Through that blob, the firmware can send back + the guest-side allocation addresses to QEMU. The "etc/hardware_errors_addr" + blob contains a 8-byte entry. QEMU generates a single WRITE_POINTER command + for the firmware. The firmware will write back the start address of + "etc/hardware_errors" blob to the fw_cfg file "etc/hardware_errors_addr". + +(9) When QEMU gets a SIGBUS from the kernel, QEMU writes CPER into corresponding + "Error Status Data Block", guest memory, and then injects platform specific + interrupt (in case of arm/virt machine it's Synchronous External Abort) as a + notification which is necessary for notifying the guest. + +(10) This notification (in virtual hardware) will be handled by the guest + kernel, on receiving notification, guest APEI driver could read the CPER error + and take appropriate action. + +(11) kvm_arch_on_sigbus_vcpu() uses source_id as index in "etc/hardware_errors" to + find out "Error Status Data Block" entry corresponding to error source. So supported + source_id values should be assigned here and not be changed afterwards to make sure + that guest will write error into expected "Error Status Data Block" even if guest was + migrated to a newer QEMU. diff --git a/docs/specs/index.rst b/docs/specs/index.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/specs/index.rst +++ b/docs/specs/index.rst @@ -XXX,XX +XXX,XX @@ Contents: ppc-spapr-xive acpi_hw_reduced_hotplug tpm + acpi_hest_ghes -- 2.20.1 From: Dongjiu Geng <gengdongjiu@huawei.com> This patch builds error_block_address and read_ack_register fields in hardware errors table , the error_block_address points to Generic Error Status Block(GESB) via bios_linker. The max size for one GESB is 1kb, For more detailed information, please refer to document: docs/specs/acpi_hest_ghes.rst Now we only support one Error source, if necessary, we can extend to support more. Suggested-by: Laszlo Ersek <lersek@redhat.com> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Message-id: 20200512030609.19593-5-gengdongjiu@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- default-configs/arm-softmmu.mak | 1 + include/hw/acpi/aml-build.h | 1 + include/hw/acpi/ghes.h | 28 +++++++++++ hw/acpi/aml-build.c | 2 + hw/acpi/ghes.c | 89 +++++++++++++++++++++++++++++++++ hw/arm/virt-acpi-build.c | 5 ++ hw/acpi/Kconfig | 4 ++ hw/acpi/Makefile.objs | 1 + 8 files changed, 131 insertions(+) create mode 100644 include/hw/acpi/ghes.h create mode 100644 hw/acpi/ghes.c diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/default-configs/arm-softmmu.mak +++ b/default-configs/arm-softmmu.mak @@ -XXX,XX +XXX,XX @@ CONFIG_FSL_IMX7=y CONFIG_FSL_IMX6UL=y CONFIG_SEMIHOSTING=y CONFIG_ALLWINNER_H3=y +CONFIG_ACPI_APEI=y diff --git a/include/hw/acpi/aml-build.h b/include/hw/acpi/aml-build.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/aml-build.h +++ b/include/hw/acpi/aml-build.h @@ -XXX,XX +XXX,XX @@ struct AcpiBuildTables { GArray *rsdp; GArray *tcpalog; GArray *vmgenid; + GArray *hardware_errors; BIOSLinker *linker; } AcpiBuildTables; diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/acpi/ghes.h @@ -XXX,XX +XXX,XX @@ +/* + * Support for generating APEI tables and recording CPER for Guests + * + * Copyright (c) 2020 HUAWEI TECHNOLOGIES CO., LTD. + * + * Author: Dongjiu Geng <gengdongjiu@huawei.com> + * + * 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 ACPI_GHES_H +#define ACPI_GHES_H + +#include "hw/acpi/bios-linker-loader.h" + +void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker); +#endif diff --git a/hw/acpi/aml-build.c b/hw/acpi/aml-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/aml-build.c +++ b/hw/acpi/aml-build.c @@ -XXX,XX +XXX,XX @@ void acpi_build_tables_init(AcpiBuildTables *tables) tables->table_data = g_array_new(false, true /* clear */, 1); tables->tcpalog = g_array_new(false, true /* clear */, 1); tables->vmgenid = g_array_new(false, true /* clear */, 1); + tables->hardware_errors = g_array_new(false, true /* clear */, 1); tables->linker = bios_linker_loader_init(); } @@ -XXX,XX +XXX,XX @@ void acpi_build_tables_cleanup(AcpiBuildTables *tables, bool mfre) g_array_free(tables->table_data, true); g_array_free(tables->tcpalog, mfre); g_array_free(tables->vmgenid, mfre); + g_array_free(tables->hardware_errors, mfre); } /* diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/acpi/ghes.c @@ -XXX,XX +XXX,XX @@ +/* + * Support for generating APEI tables and recording CPER for Guests + * + * Copyright (c) 2020 HUAWEI TECHNOLOGIES CO., LTD. + * + * Author: Dongjiu Geng <gengdongjiu@huawei.com> + * + * 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/acpi/ghes.h" +#include "hw/acpi/aml-build.h" + +#define ACPI_GHES_ERRORS_FW_CFG_FILE "etc/hardware_errors" +#define ACPI_GHES_DATA_ADDR_FW_CFG_FILE "etc/hardware_errors_addr" + +/* The max size in bytes for one error block */ +#define ACPI_GHES_MAX_RAW_DATA_LENGTH (1 * KiB) + +/* Now only support ARMv8 SEA notification type error source */ +#define ACPI_GHES_ERROR_SOURCE_COUNT 1 + +/* + * Build table for the hardware error fw_cfg blob. + * Initialize "etc/hardware_errors" and "etc/hardware_errors_addr" fw_cfg blobs. + * See docs/specs/acpi_hest_ghes.rst for blobs format. + */ +void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker) +{ + int i, error_status_block_offset; + + /* Build error_block_address */ + for (i = 0; i < ACPI_GHES_ERROR_SOURCE_COUNT; i++) { + build_append_int_noprefix(hardware_errors, 0, sizeof(uint64_t)); + } + + /* Build read_ack_register */ + for (i = 0; i < ACPI_GHES_ERROR_SOURCE_COUNT; i++) { + /* + * Initialize the value of read_ack_register to 1, so GHES can be + * writeable after (re)boot. + * ACPI 6.2: 18.3.2.8 Generic Hardware Error Source version 2 + * (GHESv2 - Type 10) + */ + build_append_int_noprefix(hardware_errors, 1, sizeof(uint64_t)); + } + + /* Generic Error Status Block offset in the hardware error fw_cfg blob */ + error_status_block_offset = hardware_errors->len; + + /* Reserve space for Error Status Data Block */ + acpi_data_push(hardware_errors, + ACPI_GHES_MAX_RAW_DATA_LENGTH * ACPI_GHES_ERROR_SOURCE_COUNT); + + /* Tell guest firmware to place hardware_errors blob into RAM */ + bios_linker_loader_alloc(linker, ACPI_GHES_ERRORS_FW_CFG_FILE, + hardware_errors, sizeof(uint64_t), false); + + for (i = 0; i < ACPI_GHES_ERROR_SOURCE_COUNT; i++) { + /* + * Tell firmware to patch error_block_address entries to point to + * corresponding "Generic Error Status Block" + */ + bios_linker_loader_add_pointer(linker, + ACPI_GHES_ERRORS_FW_CFG_FILE, sizeof(uint64_t) * i, + sizeof(uint64_t), ACPI_GHES_ERRORS_FW_CFG_FILE, + error_status_block_offset + i * ACPI_GHES_MAX_RAW_DATA_LENGTH); + } + + /* + * tell firmware to write hardware_errors GPA into + * hardware_errors_addr fw_cfg, once the former has been initialized. + */ + bios_linker_loader_write_pointer(linker, ACPI_GHES_DATA_ADDR_FW_CFG_FILE, + 0, sizeof(uint64_t), ACPI_GHES_ERRORS_FW_CFG_FILE, 0); +} diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/reset.h" #include "kvm_arm.h" #include "migration/vmstate.h" +#include "hw/acpi/ghes.h" #define ARM_SPI_BASE 32 @@ -XXX,XX +XXX,XX @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables) acpi_add_table(table_offsets, tables_blob); build_spcr(tables_blob, tables->linker, vms); + if (vms->ras) { + build_ghes_error_table(tables->hardware_errors, tables->linker); + } + if (ms->numa_state->num_nodes > 0) { acpi_add_table(table_offsets, tables_blob); build_srat(tables_blob, tables->linker, vms); diff --git a/hw/acpi/Kconfig b/hw/acpi/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/Kconfig +++ b/hw/acpi/Kconfig @@ -XXX,XX +XXX,XX @@ config ACPI_HMAT bool depends on ACPI +config ACPI_APEI + bool + depends on ACPI + config ACPI_PCI bool depends on ACPI && PCI diff --git a/hw/acpi/Makefile.objs b/hw/acpi/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/Makefile.objs +++ b/hw/acpi/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_ACPI_NVDIMM) += nvdimm.o common-obj-$(CONFIG_ACPI_VMGENID) += vmgenid.o common-obj-$(CONFIG_ACPI_HW_REDUCED) += generic_event_device.o common-obj-$(CONFIG_ACPI_HMAT) += hmat.o +common-obj-$(CONFIG_ACPI_APEI) += ghes.o common-obj-$(call lnot,$(CONFIG_ACPI_X86)) += acpi-stub.o common-obj-$(call lnot,$(CONFIG_PC)) += acpi-x86-stub.o -- 2.20.1 From: Dongjiu Geng <gengdongjiu@huawei.com> This patch builds Hardware Error Source Table(HEST) via fw_cfg blobs. Now it only supports ARMv8 SEA, a type of Generic Hardware Error Source version 2(GHESv2) error source. Afterwards, we can extend the supported types if needed. For the CPER section, currently it is memory section because kernel mainly wants userspace to handle the memory errors. This patch follows the spec ACPI 6.2 to build the Hardware Error Source table. For more detailed information, please refer to document: docs/specs/acpi_hest_ghes.rst build_ghes_hw_error_notification() helper will help to add Hardware Error Notification to ACPI tables without using packed C structures and avoid endianness issues as API doesn't need explicit conversion. Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Message-id: 20200512030609.19593-6-gengdongjiu@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/acpi/ghes.h | 39 ++++++++++++ hw/acpi/ghes.c | 126 +++++++++++++++++++++++++++++++++++++++ hw/arm/virt-acpi-build.c | 2 + 3 files changed, 167 insertions(+) diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/ghes.h +++ b/include/hw/acpi/ghes.h @@ -XXX,XX +XXX,XX @@ #include "hw/acpi/bios-linker-loader.h" +/* + * Values for Hardware Error Notification Type field + */ +enum AcpiGhesNotifyType { + /* Polled */ + ACPI_GHES_NOTIFY_POLLED = 0, + /* External Interrupt */ + ACPI_GHES_NOTIFY_EXTERNAL = 1, + /* Local Interrupt */ + ACPI_GHES_NOTIFY_LOCAL = 2, + /* SCI */ + ACPI_GHES_NOTIFY_SCI = 3, + /* NMI */ + ACPI_GHES_NOTIFY_NMI = 4, + /* CMCI, ACPI 5.0: 18.3.2.7, Table 18-290 */ + ACPI_GHES_NOTIFY_CMCI = 5, + /* MCE, ACPI 5.0: 18.3.2.7, Table 18-290 */ + ACPI_GHES_NOTIFY_MCE = 6, + /* GPIO-Signal, ACPI 6.0: 18.3.2.7, Table 18-332 */ + ACPI_GHES_NOTIFY_GPIO = 7, + /* ARMv8 SEA, ACPI 6.1: 18.3.2.9, Table 18-345 */ + ACPI_GHES_NOTIFY_SEA = 8, + /* ARMv8 SEI, ACPI 6.1: 18.3.2.9, Table 18-345 */ + ACPI_GHES_NOTIFY_SEI = 9, + /* External Interrupt - GSIV, ACPI 6.1: 18.3.2.9, Table 18-345 */ + ACPI_GHES_NOTIFY_GSIV = 10, + /* Software Delegated Exception, ACPI 6.2: 18.3.2.9, Table 18-383 */ + ACPI_GHES_NOTIFY_SDEI = 11, + /* 12 and greater are reserved */ + ACPI_GHES_NOTIFY_RESERVED = 12 +}; + +enum { + ACPI_HEST_SRC_ID_SEA = 0, + /* future ids go here */ + ACPI_HEST_SRC_ID_RESERVED, +}; + void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker); +void acpi_build_hest(GArray *table_data, BIOSLinker *linker); #endif diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/ghes.c +++ b/hw/acpi/ghes.c @@ -XXX,XX +XXX,XX @@ #include "qemu/units.h" #include "hw/acpi/ghes.h" #include "hw/acpi/aml-build.h" +#include "qemu/error-report.h" #define ACPI_GHES_ERRORS_FW_CFG_FILE "etc/hardware_errors" #define ACPI_GHES_DATA_ADDR_FW_CFG_FILE "etc/hardware_errors_addr" @@ -XXX,XX +XXX,XX @@ /* Now only support ARMv8 SEA notification type error source */ #define ACPI_GHES_ERROR_SOURCE_COUNT 1 +/* Generic Hardware Error Source version 2 */ +#define ACPI_GHES_SOURCE_GENERIC_ERROR_V2 10 + +/* Address offset in Generic Address Structure(GAS) */ +#define GAS_ADDR_OFFSET 4 + +/* + * Hardware Error Notification + * ACPI 4.0: 17.3.2.7 Hardware Error Notification + * Composes dummy Hardware Error Notification descriptor of specified type + */ +static void build_ghes_hw_error_notification(GArray *table, const uint8_t type) +{ + /* Type */ + build_append_int_noprefix(table, type, 1); + /* + * Length: + * Total length of the structure in bytes + */ + build_append_int_noprefix(table, 28, 1); + /* Configuration Write Enable */ + build_append_int_noprefix(table, 0, 2); + /* Poll Interval */ + build_append_int_noprefix(table, 0, 4); + /* Vector */ + build_append_int_noprefix(table, 0, 4); + /* Switch To Polling Threshold Value */ + build_append_int_noprefix(table, 0, 4); + /* Switch To Polling Threshold Window */ + build_append_int_noprefix(table, 0, 4); + /* Error Threshold Value */ + build_append_int_noprefix(table, 0, 4); + /* Error Threshold Window */ + build_append_int_noprefix(table, 0, 4); +} + /* * Build table for the hardware error fw_cfg blob. * Initialize "etc/hardware_errors" and "etc/hardware_errors_addr" fw_cfg blobs. @@ -XXX,XX +XXX,XX @@ void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker) bios_linker_loader_write_pointer(linker, ACPI_GHES_DATA_ADDR_FW_CFG_FILE, 0, sizeof(uint64_t), ACPI_GHES_ERRORS_FW_CFG_FILE, 0); } + +/* Build Generic Hardware Error Source version 2 (GHESv2) */ +static void build_ghes_v2(GArray *table_data, int source_id, BIOSLinker *linker) +{ + uint64_t address_offset; + /* + * Type: + * Generic Hardware Error Source version 2(GHESv2 - Type 10) + */ + build_append_int_noprefix(table_data, ACPI_GHES_SOURCE_GENERIC_ERROR_V2, 2); + /* Source Id */ + build_append_int_noprefix(table_data, source_id, 2); + /* Related Source Id */ + build_append_int_noprefix(table_data, 0xffff, 2); + /* Flags */ + build_append_int_noprefix(table_data, 0, 1); + /* Enabled */ + build_append_int_noprefix(table_data, 1, 1); + + /* Number of Records To Pre-allocate */ + build_append_int_noprefix(table_data, 1, 4); + /* Max Sections Per Record */ + build_append_int_noprefix(table_data, 1, 4); + /* Max Raw Data Length */ + build_append_int_noprefix(table_data, ACPI_GHES_MAX_RAW_DATA_LENGTH, 4); + + address_offset = table_data->len; + /* Error Status Address */ + build_append_gas(table_data, AML_AS_SYSTEM_MEMORY, 0x40, 0, + 4 /* QWord access */, 0); + bios_linker_loader_add_pointer(linker, ACPI_BUILD_TABLE_FILE, + address_offset + GAS_ADDR_OFFSET, sizeof(uint64_t), + ACPI_GHES_ERRORS_FW_CFG_FILE, source_id * sizeof(uint64_t)); + + switch (source_id) { + case ACPI_HEST_SRC_ID_SEA: + /* + * Notification Structure + * Now only enable ARMv8 SEA notification type + */ + build_ghes_hw_error_notification(table_data, ACPI_GHES_NOTIFY_SEA); + break; + default: + error_report("Not support this error source"); + abort(); + } + + /* Error Status Block Length */ + build_append_int_noprefix(table_data, ACPI_GHES_MAX_RAW_DATA_LENGTH, 4); + + /* + * Read Ack Register + * ACPI 6.1: 18.3.2.8 Generic Hardware Error Source + * version 2 (GHESv2 - Type 10) + */ + address_offset = table_data->len; + build_append_gas(table_data, AML_AS_SYSTEM_MEMORY, 0x40, 0, + 4 /* QWord access */, 0); + bios_linker_loader_add_pointer(linker, ACPI_BUILD_TABLE_FILE, + address_offset + GAS_ADDR_OFFSET, + sizeof(uint64_t), ACPI_GHES_ERRORS_FW_CFG_FILE, + (ACPI_GHES_ERROR_SOURCE_COUNT + source_id) * sizeof(uint64_t)); + + /* + * Read Ack Preserve field + * We only provide the first bit in Read Ack Register to OSPM to write + * while the other bits are preserved. + */ + build_append_int_noprefix(table_data, ~0x1ULL, 8); + /* Read Ack Write */ + build_append_int_noprefix(table_data, 0x1, 8); +} + +/* Build Hardware Error Source Table */ +void acpi_build_hest(GArray *table_data, BIOSLinker *linker) +{ + uint64_t hest_start = table_data->len; + + /* Hardware Error Source Table header*/ + acpi_data_push(table_data, sizeof(AcpiTableHeader)); + + /* Error Source Count */ + build_append_int_noprefix(table_data, ACPI_GHES_ERROR_SOURCE_COUNT, 4); + + build_ghes_v2(table_data, ACPI_HEST_SRC_ID_SEA, linker); + + build_header(linker, table_data, (void *)(table_data->data + hest_start), + "HEST", table_data->len - hest_start, 1, NULL, NULL); +} diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -XXX,XX +XXX,XX @@ void virt_acpi_build(VirtMachineState *vms, AcpiBuildTables *tables) if (vms->ras) { build_ghes_error_table(tables->hardware_errors, tables->linker); + acpi_add_table(table_offsets, tables_blob); + acpi_build_hest(tables_blob, tables->linker); } if (ms->numa_state->num_nodes > 0) { -- 2.20.1 From: Dongjiu Geng <gengdongjiu@huawei.com> Record the GHEB address via fw_cfg file, when recording a error to CPER, it will use this address to find out Generic Error Data Entries and write the error. In order to avoid migration failure, make hardware error table address to a part of GED device instead of global variable, then this address will be migrated to target QEMU. Acked-by: Xiang Zheng <zhengxiang9@huawei.com> Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Message-id: 20200512030609.19593-7-gengdongjiu@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/acpi/generic_event_device.h | 2 ++ include/hw/acpi/ghes.h | 6 ++++++ hw/acpi/generic_event_device.c | 19 +++++++++++++++++++ hw/acpi/ghes.c | 14 ++++++++++++++ hw/arm/virt-acpi-build.c | 8 ++++++++ 5 files changed, 49 insertions(+) diff --git a/include/hw/acpi/generic_event_device.h b/include/hw/acpi/generic_event_device.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/generic_event_device.h +++ b/include/hw/acpi/generic_event_device.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/acpi/memory_hotplug.h" +#include "hw/acpi/ghes.h" #define ACPI_POWER_BUTTON_DEVICE "PWRB" @@ -XXX,XX +XXX,XX @@ typedef struct AcpiGedState { GEDState ged_state; uint32_t ged_event_bitmap; qemu_irq irq; + AcpiGhesState ghes_state; } AcpiGedState; void build_ged_aml(Aml *table, const char* name, HotplugHandler *hotplug_dev, diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/ghes.h +++ b/include/hw/acpi/ghes.h @@ -XXX,XX +XXX,XX @@ enum { ACPI_HEST_SRC_ID_RESERVED, }; +typedef struct AcpiGhesState { + uint64_t ghes_addr_le; +} AcpiGhesState; + void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker); void acpi_build_hest(GArray *table_data, BIOSLinker *linker); +void acpi_ghes_add_fw_cfg(AcpiGhesState *vms, FWCfgState *s, + GArray *hardware_errors); #endif diff --git a/hw/acpi/generic_event_device.c b/hw/acpi/generic_event_device.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/generic_event_device.c +++ b/hw/acpi/generic_event_device.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_ged_state = { } }; +static bool ghes_needed(void *opaque) +{ + AcpiGedState *s = opaque; + return s->ghes_state.ghes_addr_le; +} + +static const VMStateDescription vmstate_ghes_state = { + .name = "acpi-ged/ghes", + .version_id = 1, + .minimum_version_id = 1, + .needed = ghes_needed, + .fields = (VMStateField[]) { + VMSTATE_STRUCT(ghes_state, AcpiGedState, 1, + vmstate_ghes_state, AcpiGhesState), + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_acpi_ged = { .name = "acpi-ged", .version_id = 1, @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_acpi_ged = { }, .subsections = (const VMStateDescription * []) { &vmstate_memhp_state, + &vmstate_ghes_state, NULL } }; diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/ghes.c +++ b/hw/acpi/ghes.c @@ -XXX,XX +XXX,XX @@ #include "hw/acpi/ghes.h" #include "hw/acpi/aml-build.h" #include "qemu/error-report.h" +#include "hw/acpi/generic_event_device.h" +#include "hw/nvram/fw_cfg.h" #define ACPI_GHES_ERRORS_FW_CFG_FILE "etc/hardware_errors" #define ACPI_GHES_DATA_ADDR_FW_CFG_FILE "etc/hardware_errors_addr" @@ -XXX,XX +XXX,XX @@ void acpi_build_hest(GArray *table_data, BIOSLinker *linker) build_header(linker, table_data, (void *)(table_data->data + hest_start), "HEST", table_data->len - hest_start, 1, NULL, NULL); } + +void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s, + GArray *hardware_error) +{ + /* Create a read-only fw_cfg file for GHES */ + fw_cfg_add_file(s, ACPI_GHES_ERRORS_FW_CFG_FILE, hardware_error->data, + hardware_error->len); + + /* Create a read-write fw_cfg file for Address */ + fw_cfg_add_file_callback(s, ACPI_GHES_DATA_ADDR_FW_CFG_FILE, NULL, NULL, + NULL, &(ags->ghes_addr_le), sizeof(ags->ghes_addr_le), false); +} diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -XXX,XX +XXX,XX @@ void virt_acpi_setup(VirtMachineState *vms) { AcpiBuildTables tables; AcpiBuildState *build_state; + AcpiGedState *acpi_ged_state; if (!vms->fw_cfg) { trace_virt_acpi_setup(); @@ -XXX,XX +XXX,XX @@ void virt_acpi_setup(VirtMachineState *vms) fw_cfg_add_file(vms->fw_cfg, ACPI_BUILD_TPMLOG_FILE, tables.tcpalog->data, acpi_data_len(tables.tcpalog)); + if (vms->ras) { + assert(vms->acpi_dev); + acpi_ged_state = ACPI_GED(vms->acpi_dev); + acpi_ghes_add_fw_cfg(&acpi_ged_state->ghes_state, + vms->fw_cfg, tables.hardware_errors); + } + build_state->rsdp_mr = acpi_add_rom_blob(virt_acpi_build_update, build_state, tables.rsdp, ACPI_BUILD_RSDP_FILE, 0); -- 2.20.1 From: Dongjiu Geng <gengdongjiu@huawei.com> kvm_hwpoison_page_add() and kvm_unpoison_all() will both be used by X86 and ARM platforms, so moving them into "accel/kvm/kvm-all.c" to avoid duplicate code. For architectures that don't use the poison-list functionality the reset handler will harmlessly do nothing, so let's register the kvm_unpoison_all() function in the generic kvm_init() function. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Acked-by: Xiang Zheng <zhengxiang9@huawei.com> Message-id: 20200512030609.19593-8-gengdongjiu@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/sysemu/kvm_int.h | 12 ++++++++++++ accel/kvm/kvm-all.c | 36 ++++++++++++++++++++++++++++++++++++ target/i386/kvm.c | 36 ------------------------------------ 3 files changed, 48 insertions(+), 36 deletions(-) diff --git a/include/sysemu/kvm_int.h b/include/sysemu/kvm_int.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/kvm_int.h +++ b/include/sysemu/kvm_int.h @@ -XXX,XX +XXX,XX @@ void kvm_memory_listener_register(KVMState *s, KVMMemoryListener *kml, AddressSpace *as, int as_id); void kvm_set_max_memslot_size(hwaddr max_slot_size); + +/** + * kvm_hwpoison_page_add: + * + * Parameters: + * @ram_addr: the address in the RAM for the poisoned page + * + * Add a poisoned page to the list + * + * Return: None. + */ +void kvm_hwpoison_page_add(ram_addr_t ram_addr); #endif diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -XXX,XX +XXX,XX @@ #include "qapi/visitor.h" #include "qapi/qapi-types-common.h" #include "qapi/qapi-visit-common.h" +#include "sysemu/reset.h" #include "hw/boards.h" @@ -XXX,XX +XXX,XX @@ int kvm_vm_check_extension(KVMState *s, unsigned int extension) return ret; } +typedef struct HWPoisonPage { + ram_addr_t ram_addr; + QLIST_ENTRY(HWPoisonPage) list; +} HWPoisonPage; + +static QLIST_HEAD(, HWPoisonPage) hwpoison_page_list = + QLIST_HEAD_INITIALIZER(hwpoison_page_list); + +static void kvm_unpoison_all(void *param) +{ + HWPoisonPage *page, *next_page; + + QLIST_FOREACH_SAFE(page, &hwpoison_page_list, list, next_page) { + QLIST_REMOVE(page, list); + qemu_ram_remap(page->ram_addr, TARGET_PAGE_SIZE); + g_free(page); + } +} + +void kvm_hwpoison_page_add(ram_addr_t ram_addr) +{ + HWPoisonPage *page; + + QLIST_FOREACH(page, &hwpoison_page_list, list) { + if (page->ram_addr == ram_addr) { + return; + } + } + page = g_new(HWPoisonPage, 1); + page->ram_addr = ram_addr; + QLIST_INSERT_HEAD(&hwpoison_page_list, page, list); +} + static uint32_t adjust_ioeventfd_endianness(uint32_t val, uint32_t size) { #if defined(HOST_WORDS_BIGENDIAN) != defined(TARGET_WORDS_BIGENDIAN) @@ -XXX,XX +XXX,XX @@ static int kvm_init(MachineState *ms) s->kernel_irqchip_split = mc->default_kernel_irqchip_split ? ON_OFF_AUTO_ON : ON_OFF_AUTO_OFF; } + qemu_register_reset(kvm_unpoison_all, NULL); + if (s->kernel_irqchip_allowed) { kvm_irqchip_create(s); } diff --git a/target/i386/kvm.c b/target/i386/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/kvm.c +++ b/target/i386/kvm.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "sysemu/hw_accel.h" #include "sysemu/kvm_int.h" -#include "sysemu/reset.h" #include "sysemu/runstate.h" #include "kvm_i386.h" #include "hyperv.h" @@ -XXX,XX +XXX,XX @@ uint64_t kvm_arch_get_supported_msr_feature(KVMState *s, uint32_t index) } } - -typedef struct HWPoisonPage { - ram_addr_t ram_addr; - QLIST_ENTRY(HWPoisonPage) list; -} HWPoisonPage; - -static QLIST_HEAD(, HWPoisonPage) hwpoison_page_list = - QLIST_HEAD_INITIALIZER(hwpoison_page_list); - -static void kvm_unpoison_all(void *param) -{ - HWPoisonPage *page, *next_page; - - QLIST_FOREACH_SAFE(page, &hwpoison_page_list, list, next_page) { - QLIST_REMOVE(page, list); - qemu_ram_remap(page->ram_addr, TARGET_PAGE_SIZE); - g_free(page); - } -} - -static void kvm_hwpoison_page_add(ram_addr_t ram_addr) -{ - HWPoisonPage *page; - - QLIST_FOREACH(page, &hwpoison_page_list, list) { - if (page->ram_addr == ram_addr) { - return; - } - } - page = g_new(HWPoisonPage, 1); - page->ram_addr = ram_addr; - QLIST_INSERT_HEAD(&hwpoison_page_list, page, list); -} - static int kvm_get_mce_cap_supported(KVMState *s, uint64_t *mce_cap, int *max_banks) { @@ -XXX,XX +XXX,XX @@ int kvm_arch_init(MachineState *ms, KVMState *s) fprintf(stderr, "e820_add_entry() table is full\n"); return ret; } - qemu_register_reset(kvm_unpoison_all, NULL); shadow_mem = object_property_get_int(OBJECT(s), "kvm-shadow-mem", &error_abort); if (shadow_mem != -1) { -- 2.20.1 From: Dongjiu Geng <gengdongjiu@huawei.com> kvm_arch_on_sigbus_vcpu() error injection uses source_id as index in etc/hardware_errors to find out Error Status Data Block entry corresponding to error source. So supported source_id values should be assigned here and not be changed afterwards to make sure that guest will write error into expected Error Status Data Block. Before QEMU writes a new error to ACPI table, it will check whether previous error has been acknowledged. If not acknowledged, the new errors will be ignored and not be recorded. For the errors section type, QEMU simulate it to memory section error. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Message-id: 20200512030609.19593-9-gengdongjiu@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/acpi/ghes.h | 1 + hw/acpi/ghes.c | 219 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 220 insertions(+) diff --git a/include/hw/acpi/ghes.h b/include/hw/acpi/ghes.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/ghes.h +++ b/include/hw/acpi/ghes.h @@ -XXX,XX +XXX,XX @@ void build_ghes_error_table(GArray *hardware_errors, BIOSLinker *linker); void acpi_build_hest(GArray *table_data, BIOSLinker *linker); void acpi_ghes_add_fw_cfg(AcpiGhesState *vms, FWCfgState *s, GArray *hardware_errors); +int acpi_ghes_record_errors(uint8_t notify, uint64_t error_physical_addr); #endif diff --git a/hw/acpi/ghes.c b/hw/acpi/ghes.c index XXXXXXX..XXXXXXX 100644 --- a/hw/acpi/ghes.c +++ b/hw/acpi/ghes.c @@ -XXX,XX +XXX,XX @@ #include "qemu/error-report.h" #include "hw/acpi/generic_event_device.h" #include "hw/nvram/fw_cfg.h" +#include "qemu/uuid.h" #define ACPI_GHES_ERRORS_FW_CFG_FILE "etc/hardware_errors" #define ACPI_GHES_DATA_ADDR_FW_CFG_FILE "etc/hardware_errors_addr" @@ -XXX,XX +XXX,XX @@ /* Address offset in Generic Address Structure(GAS) */ #define GAS_ADDR_OFFSET 4 +/* + * The total size of Generic Error Data Entry + * ACPI 6.1/6.2: 18.3.2.7.1 Generic Error Data, + * Table 18-343 Generic Error Data Entry + */ +#define ACPI_GHES_DATA_LENGTH 72 + +/* The memory section CPER size, UEFI 2.6: N.2.5 Memory Error Section */ +#define ACPI_GHES_MEM_CPER_LENGTH 80 + +/* Masks for block_status flags */ +#define ACPI_GEBS_UNCORRECTABLE 1 + +/* + * Total size for Generic Error Status Block except Generic Error Data Entries + * ACPI 6.2: 18.3.2.7.1 Generic Error Data, + * Table 18-380 Generic Error Status Block + */ +#define ACPI_GHES_GESB_SIZE 20 + +/* + * Values for error_severity field + */ +enum AcpiGenericErrorSeverity { + ACPI_CPER_SEV_RECOVERABLE = 0, + ACPI_CPER_SEV_FATAL = 1, + ACPI_CPER_SEV_CORRECTED = 2, + ACPI_CPER_SEV_NONE = 3, +}; + /* * Hardware Error Notification * ACPI 4.0: 17.3.2.7 Hardware Error Notification @@ -XXX,XX +XXX,XX @@ static void build_ghes_hw_error_notification(GArray *table, const uint8_t type) build_append_int_noprefix(table, 0, 4); } +/* + * Generic Error Data Entry + * ACPI 6.1: 18.3.2.7.1 Generic Error Data + */ +static void acpi_ghes_generic_error_data(GArray *table, + const uint8_t *section_type, uint32_t error_severity, + uint8_t validation_bits, uint8_t flags, + uint32_t error_data_length, QemuUUID fru_id, + uint64_t time_stamp) +{ + const uint8_t fru_text[20] = {0}; + + /* Section Type */ + g_array_append_vals(table, section_type, 16); + + /* Error Severity */ + build_append_int_noprefix(table, error_severity, 4); + /* Revision */ + build_append_int_noprefix(table, 0x300, 2); + /* Validation Bits */ + build_append_int_noprefix(table, validation_bits, 1); + /* Flags */ + build_append_int_noprefix(table, flags, 1); + /* Error Data Length */ + build_append_int_noprefix(table, error_data_length, 4); + + /* FRU Id */ + g_array_append_vals(table, fru_id.data, ARRAY_SIZE(fru_id.data)); + + /* FRU Text */ + g_array_append_vals(table, fru_text, sizeof(fru_text)); + + /* Timestamp */ + build_append_int_noprefix(table, time_stamp, 8); +} + +/* + * Generic Error Status Block + * ACPI 6.1: 18.3.2.7.1 Generic Error Data + */ +static void acpi_ghes_generic_error_status(GArray *table, uint32_t block_status, + uint32_t raw_data_offset, uint32_t raw_data_length, + uint32_t data_length, uint32_t error_severity) +{ + /* Block Status */ + build_append_int_noprefix(table, block_status, 4); + /* Raw Data Offset */ + build_append_int_noprefix(table, raw_data_offset, 4); + /* Raw Data Length */ + build_append_int_noprefix(table, raw_data_length, 4); + /* Data Length */ + build_append_int_noprefix(table, data_length, 4); + /* Error Severity */ + build_append_int_noprefix(table, error_severity, 4); +} + +/* UEFI 2.6: N.2.5 Memory Error Section */ +static void acpi_ghes_build_append_mem_cper(GArray *table, + uint64_t error_physical_addr) +{ + /* + * Memory Error Record + */ + + /* Validation Bits */ + build_append_int_noprefix(table, + (1ULL << 14) | /* Type Valid */ + (1ULL << 1) /* Physical Address Valid */, + 8); + /* Error Status */ + build_append_int_noprefix(table, 0, 8); + /* Physical Address */ + build_append_int_noprefix(table, error_physical_addr, 8); + /* Skip all the detailed information normally found in such a record */ + build_append_int_noprefix(table, 0, 48); + /* Memory Error Type */ + build_append_int_noprefix(table, 0 /* Unknown error */, 1); + /* Skip all the detailed information normally found in such a record */ + build_append_int_noprefix(table, 0, 7); +} + +static int acpi_ghes_record_mem_error(uint64_t error_block_address, + uint64_t error_physical_addr) +{ + GArray *block; + + /* Memory Error Section Type */ + const uint8_t uefi_cper_mem_sec[] = + UUID_LE(0xA5BC1114, 0x6F64, 0x4EDE, 0xB8, 0x63, 0x3E, 0x83, \ + 0xED, 0x7C, 0x83, 0xB1); + + /* invalid fru id: ACPI 4.0: 17.3.2.6.1 Generic Error Data, + * Table 17-13 Generic Error Data Entry + */ + QemuUUID fru_id = {}; + uint32_t data_length; + + block = g_array_new(false, true /* clear */, 1); + + /* This is the length if adding a new generic error data entry*/ + data_length = ACPI_GHES_DATA_LENGTH + ACPI_GHES_MEM_CPER_LENGTH; + + /* + * Check whether it will run out of the preallocated memory if adding a new + * generic error data entry + */ + if ((data_length + ACPI_GHES_GESB_SIZE) > ACPI_GHES_MAX_RAW_DATA_LENGTH) { + error_report("Not enough memory to record new CPER!!!"); + g_array_free(block, true); + return -1; + } + + /* Build the new generic error status block header */ + acpi_ghes_generic_error_status(block, ACPI_GEBS_UNCORRECTABLE, + 0, 0, data_length, ACPI_CPER_SEV_RECOVERABLE); + + /* Build this new generic error data entry header */ + acpi_ghes_generic_error_data(block, uefi_cper_mem_sec, + ACPI_CPER_SEV_RECOVERABLE, 0, 0, + ACPI_GHES_MEM_CPER_LENGTH, fru_id, 0); + + /* Build the memory section CPER for above new generic error data entry */ + acpi_ghes_build_append_mem_cper(block, error_physical_addr); + + /* Write the generic error data entry into guest memory */ + cpu_physical_memory_write(error_block_address, block->data, block->len); + + g_array_free(block, true); + + return 0; +} + /* * Build table for the hardware error fw_cfg blob. * Initialize "etc/hardware_errors" and "etc/hardware_errors_addr" fw_cfg blobs. @@ -XXX,XX +XXX,XX @@ void acpi_ghes_add_fw_cfg(AcpiGhesState *ags, FWCfgState *s, fw_cfg_add_file_callback(s, ACPI_GHES_DATA_ADDR_FW_CFG_FILE, NULL, NULL, NULL, &(ags->ghes_addr_le), sizeof(ags->ghes_addr_le), false); } + +int acpi_ghes_record_errors(uint8_t source_id, uint64_t physical_address) +{ + uint64_t error_block_addr, read_ack_register_addr, read_ack_register = 0; + uint64_t start_addr; + bool ret = -1; + AcpiGedState *acpi_ged_state; + AcpiGhesState *ags; + + assert(source_id < ACPI_HEST_SRC_ID_RESERVED); + + acpi_ged_state = ACPI_GED(object_resolve_path_type("", TYPE_ACPI_GED, + NULL)); + g_assert(acpi_ged_state); + ags = &acpi_ged_state->ghes_state; + + start_addr = le64_to_cpu(ags->ghes_addr_le); + + if (physical_address) { + + if (source_id < ACPI_HEST_SRC_ID_RESERVED) { + start_addr += source_id * sizeof(uint64_t); + } + + cpu_physical_memory_read(start_addr, &error_block_addr, + sizeof(error_block_addr)); + + error_block_addr = le64_to_cpu(error_block_addr); + + read_ack_register_addr = start_addr + + ACPI_GHES_ERROR_SOURCE_COUNT * sizeof(uint64_t); + + cpu_physical_memory_read(read_ack_register_addr, + &read_ack_register, sizeof(read_ack_register)); + + /* zero means OSPM does not acknowledge the error */ + if (!read_ack_register) { + error_report("OSPM does not acknowledge previous error," + " so can not record CPER for current error anymore"); + } else if (error_block_addr) { + read_ack_register = cpu_to_le64(0); + /* + * Clear the Read Ack Register, OSPM will write it to 1 when + * it acknowledges this error. + */ + cpu_physical_memory_write(read_ack_register_addr, + &read_ack_register, sizeof(uint64_t)); + + ret = acpi_ghes_record_mem_error(error_block_addr, + physical_address); + } else + error_report("can not find Generic Error Status Block"); + } + + return ret; +} -- 2.20.1 From: Dongjiu Geng <gengdongjiu@huawei.com> Add a SIGBUS signal handler. In this handler, it checks the SIGBUS type, translates the host VA delivered by host to guest PA, then fills this PA to guest APEI GHES memory, then notifies guest according to the SIGBUS type. When guest accesses the poisoned memory, it will generate a Synchronous External Abort(SEA). Then host kernel gets an APEI notification and calls memory_failure() to unmapped the affected page in stage 2, finally returns to guest. Guest continues to access the PG_hwpoison page, it will trap to KVM as stage2 fault, then a SIGBUS_MCEERR_AR synchronous signal is delivered to Qemu, Qemu records this error address into guest APEI GHES memory and notifes guest using Synchronous-External-Abort(SEA). In order to inject a vSEA, we introduce the kvm_inject_arm_sea() function in which we can setup the type of exception and the syndrome information. When switching to guest, the target vcpu will jump to the synchronous external abort vector table entry. The ESR_ELx.DFSC is set to synchronous external abort(0x10), and the ESR_ELx.FnV is set to not valid(0x1), which will tell guest that FAR is not valid and hold an UNKNOWN value. These values will be set to KVM register structures through KVM_SET_ONE_REG IOCTL. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Acked-by: Xiang Zheng <zhengxiang9@huawei.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Message-id: 20200512030609.19593-10-gengdongjiu@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/sysemu/kvm.h | 3 +- target/arm/cpu.h | 4 +++ target/arm/internals.h | 5 +-- target/i386/cpu.h | 2 ++ target/arm/helper.c | 2 +- target/arm/kvm64.c | 77 +++++++++++++++++++++++++++++++++++++++++ target/arm/tlb_helper.c | 2 +- 7 files changed, 89 insertions(+), 6 deletions(-) diff --git a/include/sysemu/kvm.h b/include/sysemu/kvm.h index XXXXXXX..XXXXXXX 100644 --- a/include/sysemu/kvm.h +++ b/include/sysemu/kvm.h @@ -XXX,XX +XXX,XX @@ bool kvm_vcpu_id_is_valid(int vcpu_id); /* Returns VCPU ID to be used on KVM_CREATE_VCPU ioctl() */ unsigned long kvm_arch_vcpu_id(CPUState *cpu); -#ifdef TARGET_I386 -#define KVM_HAVE_MCE_INJECTION 1 +#ifdef KVM_HAVE_MCE_INJECTION void kvm_arch_on_sigbus_vcpu(CPUState *cpu, int code, void *addr); #endif 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 @@ /* ARM processors have a weak memory model */ #define TCG_GUEST_DEFAULT_MO (0) +#ifdef TARGET_AARCH64 +#define KVM_HAVE_MCE_INJECTION 1 +#endif + #define EXCP_UDEF 1 /* undefined instruction */ #define EXCP_SWI 2 /* software interrupt */ #define EXCP_PREFETCH_ABORT 3 diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_insn_abort(int same_el, int ea, int s1ptw, int fsc) | ARM_EL_IL | (ea << 9) | (s1ptw << 7) | fsc; } -static inline uint32_t syn_data_abort_no_iss(int same_el, +static inline uint32_t syn_data_abort_no_iss(int same_el, int fnv, int ea, int cm, int s1ptw, int wnr, int fsc) { return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) | ARM_EL_IL - | (ea << 9) | (cm << 8) | (s1ptw << 7) | (wnr << 6) | fsc; + | (fnv << 10) | (ea << 9) | (cm << 8) | (s1ptw << 7) + | (wnr << 6) | fsc; } static inline uint32_t syn_data_abort_with_iss(int same_el, diff --git a/target/i386/cpu.h b/target/i386/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -XXX,XX +XXX,XX @@ /* The x86 has a strong memory model with some store-after-load re-ordering */ #define TCG_GUEST_DEFAULT_MO (TCG_MO_ALL & ~TCG_MO_ST_LD) +#define KVM_HAVE_MCE_INJECTION 1 + /* Maximum instruction code size */ #define TARGET_MAX_INSN_SIZE 16 diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value, * Report exception with ESR indicating a fault due to a * translation table walk for a cache maintenance instruction. */ - syn = syn_data_abort_no_iss(current_el == target_el, + syn = syn_data_abort_no_iss(current_el == target_el, 0, fi.ea, 1, fi.s1ptw, 1, fsc); env->exception.vaddress = value; env->exception.fsr = fsr; diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/kvm_int.h" #include "kvm_arm.h" #include "internals.h" +#include "hw/acpi/acpi.h" +#include "hw/acpi/ghes.h" +#include "hw/arm/virt.h" static bool have_guest_debug; @@ -XXX,XX +XXX,XX @@ int kvm_arm_cpreg_level(uint64_t regidx) return KVM_PUT_RUNTIME_STATE; } +/* Callers must hold the iothread mutex lock */ +static void kvm_inject_arm_sea(CPUState *c) +{ + ARMCPU *cpu = ARM_CPU(c); + CPUARMState *env = &cpu->env; + CPUClass *cc = CPU_GET_CLASS(c); + uint32_t esr; + bool same_el; + + c->exception_index = EXCP_DATA_ABORT; + env->exception.target_el = 1; + + /* + * Set the DFSC to synchronous external abort and set FnV to not valid, + * this will tell guest the FAR_ELx is UNKNOWN for this abort. + */ + same_el = arm_current_el(env) == env->exception.target_el; + esr = syn_data_abort_no_iss(same_el, 1, 0, 0, 0, 0, 0x10); + + env->exception.syndrome = esr; + + cc->do_interrupt(c); +} + #define AARCH64_CORE_REG(x) (KVM_REG_ARM64 | KVM_REG_SIZE_U64 | \ KVM_REG_ARM_CORE | KVM_REG_ARM_CORE_REG(x)) @@ -XXX,XX +XXX,XX @@ int kvm_arch_get_registers(CPUState *cs) return ret; } +void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr) +{ + ram_addr_t ram_addr; + hwaddr paddr; + Object *obj = qdev_get_machine(); + VirtMachineState *vms = VIRT_MACHINE(obj); + bool acpi_enabled = virt_is_acpi_enabled(vms); + + assert(code == BUS_MCEERR_AR || code == BUS_MCEERR_AO); + + if (acpi_enabled && addr && + object_property_get_bool(obj, "ras", NULL)) { + ram_addr = qemu_ram_addr_from_host(addr); + if (ram_addr != RAM_ADDR_INVALID && + kvm_physical_memory_addr_from_host(c->kvm_state, addr, &paddr)) { + kvm_hwpoison_page_add(ram_addr); + /* + * If this is a BUS_MCEERR_AR, we know we have been called + * synchronously from the vCPU thread, so we can easily + * synchronize the state and inject an error. + * + * TODO: we currently don't tell the guest at all about + * BUS_MCEERR_AO. In that case we might either be being + * called synchronously from the vCPU thread, or a bit + * later from the main thread, so doing the injection of + * the error would be more complicated. + */ + if (code == BUS_MCEERR_AR) { + kvm_cpu_synchronize_state(c); + if (!acpi_ghes_record_errors(ACPI_HEST_SRC_ID_SEA, paddr)) { + kvm_inject_arm_sea(c); + } else { + error_report("failed to record the error"); + abort(); + } + } + return; + } + if (code == BUS_MCEERR_AO) { + error_report("Hardware memory error at addr %p for memory used by " + "QEMU itself instead of guest system!", addr); + } + } + + if (code == BUS_MCEERR_AR) { + error_report("Hardware memory error!"); + exit(1); + } +} + /* C6.6.29 BRK instruction */ static const uint32_t brk_insn = 0xd4200000; diff --git a/target/arm/tlb_helper.c b/target/arm/tlb_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tlb_helper.c +++ b/target/arm/tlb_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t merge_syn_data_abort(uint32_t template_syn, * ISV field. */ if (!(template_syn & ARM_EL_ISV) || target_el != 2 || s1ptw) { - syn = syn_data_abort_no_iss(same_el, + syn = syn_data_abort_no_iss(same_el, 0, ea, 0, s1ptw, is_write, fsc); } else { /* -- 2.20.1 From: Dongjiu Geng <gengdongjiu@huawei.com> I and Xiang are willing to review the APEI-related patches and volunteer as the reviewers for the HEST/GHES part. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Signed-off-by: Xiang Zheng <zhengxiang9@huawei.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Acked-by: Michael S. Tsirkin <mst@redhat.com> Message-id: 20200512030609.19593-11-gengdongjiu@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: tests/qtest/bios-tables-test.c F: tests/qtest/acpi-utils.[hc] F: tests/data/acpi/ +ACPI/HEST/GHES +R: Dongjiu Geng <gengdongjiu@huawei.com> +R: Xiang Zheng <zhengxiang9@huawei.com> +L: qemu-arm@nongnu.org +S: Maintained +F: hw/acpi/ghes.c +F: include/hw/acpi/ghes.h +F: docs/specs/acpi_hest_ghes.rst + ppc4xx M: David Gibson <david@gibson.dropbear.id.au> L: qemu-ppc@nongnu.org -- 2.20.1 Convert the Neon VQRDMLAH and VQRDMLSH insns in the 3-reg-same group to decodetree. These don't use do_3same() because they want to operate on VFP double registers, whose offsets are different from the neon_reg_offset() calculations do_3same does. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-2-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 3 +++ target/arm/translate-neon.inc.c | 15 +++++++++++++++ target/arm/translate.c | 14 ++------------ 3 files changed, 20 insertions(+), 12 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VMLS_3s 1111 001 1 0 . .. .... .... 1001 . . . 0 .... @3same VMUL_3s 1111 001 0 0 . .. .... .... 1001 . . . 1 .... @3same VMUL_p_3s 1111 001 1 0 . .. .... .... 1001 . . . 1 .... @3same + +VQRDMLAH_3s 1111 001 1 0 . .. .... .... 1011 ... 1 .... @3same +VQRDMLSH_3s 1111 001 1 0 . .. .... .... 1100 ... 1 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VMUL_p_3s(DisasContext *s, arg_3same *a) } return do_3same(s, a, gen_VMUL_p_3s); } + +#define DO_VQRDMLAH(INSN, FUNC) \ + static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ + { \ + if (!dc_isar_feature(aa32_rdm, s)) { \ + return false; \ + } \ + if (a->size != 1 && a->size != 2) { \ + return false; \ + } \ + return do_3same(s, a, FUNC); \ + } + +DO_VQRDMLAH(VQRDMLAH, gen_gvec_sqrdmlah_qc) +DO_VQRDMLAH(VQRDMLSH, gen_gvec_sqrdmlsh_qc) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) if (!u) { break; /* VPADD */ } - /* VQRDMLAH */ - if (dc_isar_feature(aa32_rdm, s) && (size == 1 || size == 2)) { - gen_gvec_sqrdmlah_qc(size, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - return 0; - } + /* VQRDMLAH : handled by decodetree */ return 1; case NEON_3R_VFM_VQRDMLSH: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } break; } - /* VQRDMLSH */ - if (dc_isar_feature(aa32_rdm, s) && (size == 1 || size == 2)) { - gen_gvec_sqrdmlsh_qc(size, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - return 0; - } + /* VQRDMLSH : handled by decodetree */ return 1; case NEON_3R_VABD: -- 2.20.1 Convert the Neon SHA instructions in the 3-reg-same group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-3-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 10 +++ target/arm/translate-neon.inc.c | 139 ++++++++++++++++++++++++++++++++ target/arm/translate.c | 46 +---------- 3 files changed, 151 insertions(+), 44 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VMUL_3s 1111 001 0 0 . .. .... .... 1001 . . . 1 .... @3same VMUL_p_3s 1111 001 1 0 . .. .... .... 1001 . . . 1 .... @3same VQRDMLAH_3s 1111 001 1 0 . .. .... .... 1011 ... 1 .... @3same + +SHA1_3s 1111 001 0 0 . optype:2 .... .... 1100 . 1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp +SHA256H_3s 1111 001 1 0 . 00 .... .... 1100 . 1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp +SHA256H2_3s 1111 001 1 0 . 01 .... .... 1100 . 1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp +SHA256SU1_3s 1111 001 1 0 . 10 .... .... 1100 . 1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp + VQRDMLSH_3s 1111 001 1 0 . .. .... .... 1100 ... 1 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VMUL_p_3s(DisasContext *s, arg_3same *a) DO_VQRDMLAH(VQRDMLAH, gen_gvec_sqrdmlah_qc) DO_VQRDMLAH(VQRDMLSH, gen_gvec_sqrdmlsh_qc) + +static bool trans_SHA1_3s(DisasContext *s, arg_SHA1_3s *a) +{ + TCGv_ptr ptr1, ptr2, ptr3; + TCGv_i32 tmp; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON) || + !dc_isar_feature(aa32_sha1, s)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if ((a->vn | a->vm | a->vd) & 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + ptr1 = vfp_reg_ptr(true, a->vd); + ptr2 = vfp_reg_ptr(true, a->vn); + ptr3 = vfp_reg_ptr(true, a->vm); + tmp = tcg_const_i32(a->optype); + gen_helper_crypto_sha1_3reg(ptr1, ptr2, ptr3, tmp); + tcg_temp_free_i32(tmp); + tcg_temp_free_ptr(ptr1); + tcg_temp_free_ptr(ptr2); + tcg_temp_free_ptr(ptr3); + + return true; +} + +static bool trans_SHA256H_3s(DisasContext *s, arg_SHA256H_3s *a) +{ + TCGv_ptr ptr1, ptr2, ptr3; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON) || + !dc_isar_feature(aa32_sha2, s)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if ((a->vn | a->vm | a->vd) & 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + ptr1 = vfp_reg_ptr(true, a->vd); + ptr2 = vfp_reg_ptr(true, a->vn); + ptr3 = vfp_reg_ptr(true, a->vm); + gen_helper_crypto_sha256h(ptr1, ptr2, ptr3); + tcg_temp_free_ptr(ptr1); + tcg_temp_free_ptr(ptr2); + tcg_temp_free_ptr(ptr3); + + return true; +} + +static bool trans_SHA256H2_3s(DisasContext *s, arg_SHA256H2_3s *a) +{ + TCGv_ptr ptr1, ptr2, ptr3; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON) || + !dc_isar_feature(aa32_sha2, s)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if ((a->vn | a->vm | a->vd) & 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + ptr1 = vfp_reg_ptr(true, a->vd); + ptr2 = vfp_reg_ptr(true, a->vn); + ptr3 = vfp_reg_ptr(true, a->vm); + gen_helper_crypto_sha256h2(ptr1, ptr2, ptr3); + tcg_temp_free_ptr(ptr1); + tcg_temp_free_ptr(ptr2); + tcg_temp_free_ptr(ptr3); + + return true; +} + +static bool trans_SHA256SU1_3s(DisasContext *s, arg_SHA256SU1_3s *a) +{ + TCGv_ptr ptr1, ptr2, ptr3; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON) || + !dc_isar_feature(aa32_sha2, s)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if ((a->vn | a->vm | a->vd) & 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + ptr1 = vfp_reg_ptr(true, a->vd); + ptr2 = vfp_reg_ptr(true, a->vn); + ptr3 = vfp_reg_ptr(true, a->vm); + gen_helper_crypto_sha256su1(ptr1, ptr2, ptr3); + tcg_temp_free_ptr(ptr1); + tcg_temp_free_ptr(ptr2); + tcg_temp_free_ptr(ptr3); + + return true; +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) int vec_size; uint32_t imm; TCGv_i32 tmp, tmp2, tmp3, tmp4, tmp5; - TCGv_ptr ptr1, ptr2, ptr3; + TCGv_ptr ptr1, ptr2; TCGv_i64 tmp64; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } switch (op) { - case NEON_3R_SHA: - /* The SHA-1/SHA-256 3-register instructions require special - * treatment here, as their size field is overloaded as an - * op type selector, and they all consume their input in a - * single pass. - */ - if (!q) { - return 1; - } - if (!u) { /* SHA-1 */ - if (!dc_isar_feature(aa32_sha1, s)) { - return 1; - } - ptr1 = vfp_reg_ptr(true, rd); - ptr2 = vfp_reg_ptr(true, rn); - ptr3 = vfp_reg_ptr(true, rm); - tmp4 = tcg_const_i32(size); - gen_helper_crypto_sha1_3reg(ptr1, ptr2, ptr3, tmp4); - tcg_temp_free_i32(tmp4); - } else { /* SHA-256 */ - if (!dc_isar_feature(aa32_sha2, s) || size == 3) { - return 1; - } - ptr1 = vfp_reg_ptr(true, rd); - ptr2 = vfp_reg_ptr(true, rn); - ptr3 = vfp_reg_ptr(true, rm); - switch (size) { - case 0: - gen_helper_crypto_sha256h(ptr1, ptr2, ptr3); - break; - case 1: - gen_helper_crypto_sha256h2(ptr1, ptr2, ptr3); - break; - case 2: - gen_helper_crypto_sha256su1(ptr1, ptr2, ptr3); - break; - } - } - tcg_temp_free_ptr(ptr1); - tcg_temp_free_ptr(ptr2); - tcg_temp_free_ptr(ptr3); - return 0; - case NEON_3R_VPADD_VQRDMLAH: if (!u) { break; /* VPADD */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VMUL: case NEON_3R_VML: case NEON_3R_VSHL: + case NEON_3R_SHA: /* Already handled by decodetree */ return 1; } -- 2.20.1 Convert the 64-bit element insns in the 3-reg-same group to decodetree. This covers VQSHL, VRSHL and VQRSHL where size==0b11. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-4-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 13 +++++++++++ target/arm/translate-neon.inc.c | 24 +++++++++++++++++++++ target/arm/translate.c | 38 ++------------------------------- 3 files changed, 39 insertions(+), 36 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VCGE_U_3s 1111 001 1 0 . .. .... .... 0011 . . . 1 .... @3same VSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 0 .... @3same_rev VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev +# Insns operating on 64-bit elements (size!=0b11 handled elsewhere) +# The _rev suffix indicates that Vn and Vm are reversed (as explained +# by the comment for the @3same_rev format). +@3same_64_rev .... ... . . . 11 .... .... .... . q:1 . . .... \ + &3same vm=%vn_dp vn=%vm_dp vd=%vd_dp size=3 + +VQSHL_S64_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev +VQSHL_U64_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev +VRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev +VRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev +VQRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev +VQRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev + VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same VMIN_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 1 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_SHA256SU1_3s(DisasContext *s, arg_SHA256SU1_3s *a) return true; } + +#define DO_3SAME_64(INSN, FUNC) \ + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ + uint32_t rn_ofs, uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ + { \ + static const GVecGen3 op = { .fni8 = FUNC }; \ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &op); \ + } \ + DO_3SAME(INSN, gen_##INSN##_3s) + +#define DO_3SAME_64_ENV(INSN, FUNC) \ + static void gen_##INSN##_elt(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m) \ + { \ + FUNC(d, cpu_env, n, m); \ + } \ + DO_3SAME_64(INSN, gen_##INSN##_elt) + +DO_3SAME_64(VRSHL_S64, gen_helper_neon_rshl_s64) +DO_3SAME_64(VRSHL_U64, gen_helper_neon_rshl_u64) +DO_3SAME_64_ENV(VQSHL_S64, gen_helper_neon_qshl_s64) +DO_3SAME_64_ENV(VQSHL_U64, gen_helper_neon_qshl_u64) +DO_3SAME_64_ENV(VQRSHL_S64, gen_helper_neon_qrshl_s64) +DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } if (size == 3) { - /* 64-bit element instructions. */ - for (pass = 0; pass < (q ? 2 : 1); pass++) { - neon_load_reg64(cpu_V0, rn + pass); - neon_load_reg64(cpu_V1, rm + pass); - switch (op) { - case NEON_3R_VQSHL: - if (u) { - gen_helper_neon_qshl_u64(cpu_V0, cpu_env, - cpu_V1, cpu_V0); - } else { - gen_helper_neon_qshl_s64(cpu_V0, cpu_env, - cpu_V1, cpu_V0); - } - break; - case NEON_3R_VRSHL: - if (u) { - gen_helper_neon_rshl_u64(cpu_V0, cpu_V1, cpu_V0); - } else { - gen_helper_neon_rshl_s64(cpu_V0, cpu_V1, cpu_V0); - } - break; - case NEON_3R_VQRSHL: - if (u) { - gen_helper_neon_qrshl_u64(cpu_V0, cpu_env, - cpu_V1, cpu_V0); - } else { - gen_helper_neon_qrshl_s64(cpu_V0, cpu_env, - cpu_V1, cpu_V0); - } - break; - default: - abort(); - } - neon_store_reg64(cpu_V0, rd + pass); - } - return 0; + /* 64-bit element instructions: handled by decodetree */ + return 1; } pairwise = 0; switch (op) { -- 2.20.1 Convert the Neon VHADD insns in the 3-reg-same group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-5-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 2 ++ target/arm/translate-neon.inc.c | 24 ++++++++++++++++++++++++ target/arm/translate.c | 4 +--- 3 files changed, 27 insertions(+), 3 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ @3same .... ... . . . size:2 .... .... .... . q:1 . . .... \ &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp +VHADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 0 .... @3same +VHADD_U_3s 1111 001 1 0 . .. .... .... 0000 . . . 0 .... @3same VQADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 1 .... @3same VQADD_U_3s 1111 001 1 0 . .. .... .... 0000 . . . 1 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_64_ENV(VQSHL_S64, gen_helper_neon_qshl_s64) DO_3SAME_64_ENV(VQSHL_U64, gen_helper_neon_qshl_u64) DO_3SAME_64_ENV(VQRSHL_S64, gen_helper_neon_qrshl_s64) DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64) + +#define DO_3SAME_32(INSN, FUNC) \ + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ + uint32_t rn_ofs, uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ + { \ + static const GVecGen3 ops[4] = { \ + { .fni4 = gen_helper_neon_##FUNC##8 }, \ + { .fni4 = gen_helper_neon_##FUNC##16 }, \ + { .fni4 = gen_helper_neon_##FUNC##32 }, \ + { 0 }, \ + }; \ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops[vece]); \ + } \ + static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ + { \ + if (a->size > 2) { \ + return false; \ + } \ + return do_3same(s, a, gen_##INSN##_3s); \ + } + +DO_3SAME_32(VHADD_S, hadd_s) +DO_3SAME_32(VHADD_U, hadd_u) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VML: case NEON_3R_VSHL: case NEON_3R_SHA: + case NEON_3R_VHADD: /* Already handled by decodetree */ return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = neon_load_reg(rm, pass); } switch (op) { - case NEON_3R_VHADD: - GEN_NEON_INTEGER_OP(hadd); - break; case NEON_3R_VRHADD: GEN_NEON_INTEGER_OP(rhadd); break; -- 2.20.1 Convert the Neon VABA and VABD insns in the 3-reg-same group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-6-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 6 ++++++ target/arm/translate-neon.inc.c | 4 ++++ target/arm/translate.c | 22 ++-------------------- 3 files changed, 12 insertions(+), 20 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same VMIN_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 1 .... @3same VMIN_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 1 .... @3same +VABD_S_3s 1111 001 0 0 . .. .... .... 0111 . . . 0 .... @3same +VABD_U_3s 1111 001 1 0 . .. .... .... 0111 . . . 0 .... @3same + +VABA_S_3s 1111 001 0 0 . .. .... .... 0111 . . . 1 .... @3same +VABA_U_3s 1111 001 1 0 . .. .... .... 0111 . . . 1 .... @3same + VADD_3s 1111 001 0 0 . .. .... .... 1000 . . . 0 .... @3same VSUB_3s 1111 001 1 0 . .. .... .... 1000 . . . 0 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_NO_SZ_3(VMUL, tcg_gen_gvec_mul) DO_3SAME_NO_SZ_3(VMLA, gen_gvec_mla) DO_3SAME_NO_SZ_3(VMLS, gen_gvec_mls) DO_3SAME_NO_SZ_3(VTST, gen_gvec_cmtst) +DO_3SAME_NO_SZ_3(VABD_S, gen_gvec_sabd) +DO_3SAME_NO_SZ_3(VABA_S, gen_gvec_saba) +DO_3SAME_NO_SZ_3(VABD_U, gen_gvec_uabd) +DO_3SAME_NO_SZ_3(VABA_U, gen_gvec_uaba) #define DO_3SAME_CMP(INSN, COND) \ static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) /* VQRDMLSH : handled by decodetree */ return 1; - case NEON_3R_VABD: - if (u) { - gen_gvec_uabd(size, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - } else { - gen_gvec_sabd(size, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - } - return 0; - - case NEON_3R_VABA: - if (u) { - gen_gvec_uaba(size, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - } else { - gen_gvec_saba(size, rd_ofs, rn_ofs, rm_ofs, - vec_size, vec_size); - } - return 0; - case NEON_3R_VADD_VSUB: case NEON_3R_LOGIC: case NEON_3R_VMAX: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VSHL: case NEON_3R_SHA: case NEON_3R_VHADD: + case NEON_3R_VABD: + case NEON_3R_VABA: /* Already handled by decodetree */ return 1; } -- 2.20.1 Convert the Neon VRHADD and VHSUB 3-reg-same insns to decodetree. (These are all the other insns in 3-reg-same which were using GEN_NEON_INTEGER_OP() and which are not pairwise or reversed-operands.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-7-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 6 ++++++ target/arm/translate-neon.inc.c | 4 ++++ target/arm/translate.c | 8 ++------ 3 files changed, 12 insertions(+), 6 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VHADD_U_3s 1111 001 1 0 . .. .... .... 0000 . . . 0 .... @3same VQADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 1 .... @3same VQADD_U_3s 1111 001 1 0 . .. .... .... 0000 . . . 1 .... @3same +VRHADD_S_3s 1111 001 0 0 . .. .... .... 0001 . . . 0 .... @3same +VRHADD_U_3s 1111 001 1 0 . .. .... .... 0001 . . . 0 .... @3same + @3same_logic .... ... . . . .. .... .... .... . q:1 .. .... \ &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp size=0 @@ -XXX,XX +XXX,XX @@ VBSL_3s 1111 001 1 0 . 01 .... .... 0001 ... 1 .... @3same_logic VBIT_3s 1111 001 1 0 . 10 .... .... 0001 ... 1 .... @3same_logic VBIF_3s 1111 001 1 0 . 11 .... .... 0001 ... 1 .... @3same_logic +VHSUB_S_3s 1111 001 0 0 . .. .... .... 0010 . . . 0 .... @3same +VHSUB_U_3s 1111 001 1 0 . .. .... .... 0010 . . . 0 .... @3same + VQSUB_S_3s 1111 001 0 0 . .. .... .... 0010 . . . 1 .... @3same VQSUB_U_3s 1111 001 1 0 . .. .... .... 0010 . . . 1 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64) DO_3SAME_32(VHADD_S, hadd_s) DO_3SAME_32(VHADD_U, hadd_u) +DO_3SAME_32(VHSUB_S, hsub_s) +DO_3SAME_32(VHSUB_U, hsub_u) +DO_3SAME_32(VRHADD_S, rhadd_s) +DO_3SAME_32(VRHADD_U, rhadd_u) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VSHL: case NEON_3R_SHA: case NEON_3R_VHADD: + case NEON_3R_VRHADD: + case NEON_3R_VHSUB: case NEON_3R_VABD: case NEON_3R_VABA: /* Already handled by decodetree */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = neon_load_reg(rm, pass); } switch (op) { - case NEON_3R_VRHADD: - GEN_NEON_INTEGER_OP(rhadd); - break; - case NEON_3R_VHSUB: - GEN_NEON_INTEGER_OP(hsub); - break; case NEON_3R_VQSHL: GEN_NEON_INTEGER_OP_ENV(qshl); break; -- 2.20.1 Convert the VQSHL, VRSHL and VQRSHL insns in the 3-reg-same group to decodetree. We have already implemented the size==0b11 case of these insns; this commit handles the remaining sizes. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-8-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 30 ++++++++++++++++++----- target/arm/translate-neon.inc.c | 43 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 22 +++-------------- 3 files changed, 70 insertions(+), 25 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 0 .... @3same_rev @3same_64_rev .... ... . . . 11 .... .... .... . q:1 . . .... \ &3same vm=%vn_dp vn=%vm_dp vd=%vd_dp size=3 -VQSHL_S64_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev -VQSHL_U64_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev -VRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev -VRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev -VQRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev -VQRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev +{ + VQSHL_S64_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev + VQSHL_S_3s 1111 001 0 0 . .. .... .... 0100 . . . 1 .... @3same_rev +} +{ + VQSHL_U64_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_64_rev + VQSHL_U_3s 1111 001 1 0 . .. .... .... 0100 . . . 1 .... @3same_rev +} +{ + VRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev + VRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 0 .... @3same_rev +} +{ + VRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_64_rev + VRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 0 .... @3same_rev +} +{ + VQRSHL_S64_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev + VQRSHL_S_3s 1111 001 0 0 . .. .... .... 0101 . . . 1 .... @3same_rev +} +{ + VQRSHL_U64_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_64_rev + VQRSHL_U_3s 1111 001 1 0 . .. .... .... 0101 . . . 1 .... @3same_rev +} VMAX_S_3s 1111 001 0 0 . .. .... .... 0110 . . . 0 .... @3same VMAX_U_3s 1111 001 1 0 . .. .... .... 0110 . . . 0 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_64_ENV(VQRSHL_U64, gen_helper_neon_qrshl_u64) return do_3same(s, a, gen_##INSN##_3s); \ } +/* + * Some helper functions need to be passed the cpu_env. In order + * to use those with the gvec APIs like tcg_gen_gvec_3() we need + * to create wrapper functions whose prototype is a NeonGenTwoOpFn() + * and which call a NeonGenTwoOpEnvFn(). + */ +#define WRAP_ENV_FN(WRAPNAME, FUNC) \ + static void WRAPNAME(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m) \ + { \ + FUNC(d, cpu_env, n, m); \ + } + +#define DO_3SAME_32_ENV(INSN, FUNC) \ + WRAP_ENV_FN(gen_##INSN##_tramp8, gen_helper_neon_##FUNC##8); \ + WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##16); \ + WRAP_ENV_FN(gen_##INSN##_tramp32, gen_helper_neon_##FUNC##32); \ + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ + uint32_t rn_ofs, uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ + { \ + static const GVecGen3 ops[4] = { \ + { .fni4 = gen_##INSN##_tramp8 }, \ + { .fni4 = gen_##INSN##_tramp16 }, \ + { .fni4 = gen_##INSN##_tramp32 }, \ + { 0 }, \ + }; \ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops[vece]); \ + } \ + static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ + { \ + if (a->size > 2) { \ + return false; \ + } \ + return do_3same(s, a, gen_##INSN##_3s); \ + } + DO_3SAME_32(VHADD_S, hadd_s) DO_3SAME_32(VHADD_U, hadd_u) DO_3SAME_32(VHSUB_S, hsub_s) DO_3SAME_32(VHSUB_U, hsub_u) DO_3SAME_32(VRHADD_S, rhadd_s) DO_3SAME_32(VRHADD_U, rhadd_u) +DO_3SAME_32(VRSHL_S, rshl_s) +DO_3SAME_32(VRSHL_U, rshl_u) + +DO_3SAME_32_ENV(VQSHL_S, qshl_s) +DO_3SAME_32_ENV(VQSHL_U, qshl_u) +DO_3SAME_32_ENV(VQRSHL_S, qrshl_s) +DO_3SAME_32_ENV(VQRSHL_U, qrshl_u) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VHSUB: case NEON_3R_VABD: case NEON_3R_VABA: + case NEON_3R_VQSHL: + case NEON_3R_VRSHL: + case NEON_3R_VQRSHL: /* Already handled by decodetree */ return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } pairwise = 0; switch (op) { - case NEON_3R_VQSHL: - case NEON_3R_VRSHL: - case NEON_3R_VQRSHL: - { - int rtmp; - /* Shift instruction operands are reversed. */ - rtmp = rn; - rn = rm; - rm = rtmp; - } - break; case NEON_3R_VPADD_VQRDMLAH: case NEON_3R_VPMAX: case NEON_3R_VPMIN: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = neon_load_reg(rm, pass); } switch (op) { - case NEON_3R_VQSHL: - GEN_NEON_INTEGER_OP_ENV(qshl); - break; - case NEON_3R_VRSHL: - GEN_NEON_INTEGER_OP(rshl); - break; - case NEON_3R_VQRSHL: - GEN_NEON_INTEGER_OP_ENV(qrshl); break; case NEON_3R_VPMAX: GEN_NEON_INTEGER_OP(pmax); -- 2.20.1 Convert the Neon integer VPMAX and VPMIN 3-reg-same insns to decodetree. These are 'pairwise' operations. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-9-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 9 +++++ target/arm/translate-neon.inc.c | 71 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 17 +------- 3 files changed, 82 insertions(+), 15 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ @3same .... ... . . . size:2 .... .... .... . q:1 . . .... \ &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp +@3same_q0 .... ... . . . size:2 .... .... .... . 0 . . .... \ + &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp q=0 + VHADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 0 .... @3same VHADD_U_3s 1111 001 1 0 . .. .... .... 0000 . . . 0 .... @3same VQADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 1 .... @3same @@ -XXX,XX +XXX,XX @@ VMLS_3s 1111 001 1 0 . .. .... .... 1001 . . . 0 .... @3same VMUL_3s 1111 001 0 0 . .. .... .... 1001 . . . 1 .... @3same VMUL_p_3s 1111 001 1 0 . .. .... .... 1001 . . . 1 .... @3same +VPMAX_S_3s 1111 001 0 0 . .. .... .... 1010 . . . 0 .... @3same_q0 +VPMAX_U_3s 1111 001 1 0 . .. .... .... 1010 . . . 0 .... @3same_q0 + +VPMIN_S_3s 1111 001 0 0 . .. .... .... 1010 . . . 1 .... @3same_q0 +VPMIN_U_3s 1111 001 1 0 . .. .... .... 1010 . . . 1 .... @3same_q0 + VQRDMLAH_3s 1111 001 1 0 . .. .... .... 1011 ... 1 .... @3same SHA1_3s 1111 001 0 0 . optype:2 .... .... 1100 . 1 . 0 .... \ diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_32_ENV(VQSHL_S, qshl_s) DO_3SAME_32_ENV(VQSHL_U, qshl_u) DO_3SAME_32_ENV(VQRSHL_S, qrshl_s) DO_3SAME_32_ENV(VQRSHL_U, qrshl_u) + +static bool do_3same_pair(DisasContext *s, arg_3same *a, NeonGenTwoOpFn *fn) +{ + /* Operations handled pairwise 32 bits at a time */ + TCGv_i32 tmp, tmp2, tmp3; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if (a->size == 3) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + assert(a->q == 0); /* enforced by decode patterns */ + + /* + * Note that we have to be careful not to clobber the source operands + * in the "vm == vd" case by storing the result of the first pass too + * early. Since Q is 0 there are always just two passes, so instead + * of a complicated loop over each pass we just unroll. + */ + tmp = neon_load_reg(a->vn, 0); + tmp2 = neon_load_reg(a->vn, 1); + fn(tmp, tmp, tmp2); + tcg_temp_free_i32(tmp2); + + tmp3 = neon_load_reg(a->vm, 0); + tmp2 = neon_load_reg(a->vm, 1); + fn(tmp3, tmp3, tmp2); + tcg_temp_free_i32(tmp2); + + neon_store_reg(a->vd, 0, tmp); + neon_store_reg(a->vd, 1, tmp3); + return true; +} + +#define DO_3SAME_PAIR(INSN, func) \ + static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ + { \ + static NeonGenTwoOpFn * const fns[] = { \ + gen_helper_neon_##func##8, \ + gen_helper_neon_##func##16, \ + gen_helper_neon_##func##32, \ + }; \ + if (a->size > 2) { \ + return false; \ + } \ + return do_3same_pair(s, a, fns[a->size]); \ + } + +/* 32-bit pairwise ops end up the same as the elementwise versions. */ +#define gen_helper_neon_pmax_s32 tcg_gen_smax_i32 +#define gen_helper_neon_pmax_u32 tcg_gen_umax_i32 +#define gen_helper_neon_pmin_s32 tcg_gen_smin_i32 +#define gen_helper_neon_pmin_u32 tcg_gen_umin_i32 + +DO_3SAME_PAIR(VPMAX_S, pmax_s) +DO_3SAME_PAIR(VPMIN_S, pmin_s) +DO_3SAME_PAIR(VPMAX_U, pmax_u) +DO_3SAME_PAIR(VPMIN_U, pmin_u) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void gen_neon_rsb(int size, TCGv_i32 t0, TCGv_i32 t1) } } -/* 32-bit pairwise ops end up the same as the elementwise versions. */ -#define gen_helper_neon_pmax_s32 tcg_gen_smax_i32 -#define gen_helper_neon_pmax_u32 tcg_gen_umax_i32 -#define gen_helper_neon_pmin_s32 tcg_gen_smin_i32 -#define gen_helper_neon_pmin_u32 tcg_gen_umin_i32 - #define GEN_NEON_INTEGER_OP_ENV(name) do { \ switch ((size << 1) | u) { \ case 0: \ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VQSHL: case NEON_3R_VRSHL: case NEON_3R_VQRSHL: + case NEON_3R_VPMAX: + case NEON_3R_VPMIN: /* Already handled by decodetree */ return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) pairwise = 0; switch (op) { case NEON_3R_VPADD_VQRDMLAH: - case NEON_3R_VPMAX: - case NEON_3R_VPMIN: pairwise = 1; break; case NEON_3R_FLOAT_ARITH: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = neon_load_reg(rm, pass); } switch (op) { - break; - case NEON_3R_VPMAX: - GEN_NEON_INTEGER_OP(pmax); - break; - case NEON_3R_VPMIN: - GEN_NEON_INTEGER_OP(pmin); - break; case NEON_3R_VQDMULH_VQRDMULH: /* Multiply high. */ if (!u) { /* VQDMULH */ switch (size) { -- 2.20.1 Convert the Neon integer VPADD 3-reg-same insns to decodetree. These are 'pairwise' operations. (Note that VQRDMLAH, which shares the same primary opcode but has U=1, has already been converted.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-10-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 2 ++ target/arm/translate-neon.inc.c | 2 ++ target/arm/translate.c | 19 +------------------ 3 files changed, 5 insertions(+), 18 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VPMAX_U_3s 1111 001 1 0 . .. .... .... 1010 . . . 0 .... @3same_q0 VPMIN_S_3s 1111 001 0 0 . .. .... .... 1010 . . . 1 .... @3same_q0 VPMIN_U_3s 1111 001 1 0 . .. .... .... 1010 . . . 1 .... @3same_q0 +VPADD_3s 1111 001 0 0 . .. .... .... 1011 . . . 1 .... @3same_q0 + VQRDMLAH_3s 1111 001 1 0 . .. .... .... 1011 ... 1 .... @3same SHA1_3s 1111 001 0 0 . optype:2 .... .... 1100 . 1 . 0 .... \ diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool do_3same_pair(DisasContext *s, arg_3same *a, NeonGenTwoOpFn *fn) #define gen_helper_neon_pmax_u32 tcg_gen_umax_i32 #define gen_helper_neon_pmin_s32 tcg_gen_smin_i32 #define gen_helper_neon_pmin_u32 tcg_gen_umin_i32 +#define gen_helper_neon_padd_u32 tcg_gen_add_i32 DO_3SAME_PAIR(VPMAX_S, pmax_s) DO_3SAME_PAIR(VPMIN_S, pmin_s) DO_3SAME_PAIR(VPMAX_U, pmax_u) DO_3SAME_PAIR(VPMIN_U, pmin_u) +DO_3SAME_PAIR(VPADD, padd_u) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } switch (op) { - case NEON_3R_VPADD_VQRDMLAH: - if (!u) { - break; /* VPADD */ - } - /* VQRDMLAH : handled by decodetree */ - return 1; - case NEON_3R_VFM_VQRDMLSH: if (!u) { /* VFM, VFMS */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VQRSHL: case NEON_3R_VPMAX: case NEON_3R_VPMIN: + case NEON_3R_VPADD_VQRDMLAH: /* Already handled by decodetree */ return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } pairwise = 0; switch (op) { - case NEON_3R_VPADD_VQRDMLAH: - pairwise = 1; - break; case NEON_3R_FLOAT_ARITH: pairwise = (u && size < 2); /* if VPADD (float) */ break; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } } break; - case NEON_3R_VPADD_VQRDMLAH: - switch (size) { - case 0: gen_helper_neon_padd_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_padd_u16(tmp, tmp, tmp2); break; - case 2: tcg_gen_add_i32(tmp, tmp, tmp2); break; - default: abort(); - } - break; case NEON_3R_FLOAT_ARITH: /* Floating point arithmetic. */ { TCGv_ptr fpstatus = get_fpstatus_ptr(1); -- 2.20.1 Convert the Neon VQDMULH and VQRDMULH 3-reg-same insns to decodetree. These are the last integer operations in the 3-reg-same group. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-11-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 3 +++ target/arm/translate-neon.inc.c | 24 ++++++++++++++++++++++++ target/arm/translate.c | 24 +----------------------- 3 files changed, 28 insertions(+), 23 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VPMAX_U_3s 1111 001 1 0 . .. .... .... 1010 . . . 0 .... @3same_q0 VPMIN_S_3s 1111 001 0 0 . .. .... .... 1010 . . . 1 .... @3same_q0 VPMIN_U_3s 1111 001 1 0 . .. .... .... 1010 . . . 1 .... @3same_q0 +VQDMULH_3s 1111 001 0 0 . .. .... .... 1011 . . . 0 .... @3same +VQRDMULH_3s 1111 001 1 0 . .. .... .... 1011 . . . 0 .... @3same + VPADD_3s 1111 001 0 0 . .. .... .... 1011 . . . 1 .... @3same_q0 VQRDMLAH_3s 1111 001 1 0 . .. .... .... 1011 ... 1 .... @3same diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_PAIR(VPMIN_S, pmin_s) DO_3SAME_PAIR(VPMAX_U, pmax_u) DO_3SAME_PAIR(VPMIN_U, pmin_u) DO_3SAME_PAIR(VPADD, padd_u) + +#define DO_3SAME_VQDMULH(INSN, FUNC) \ + WRAP_ENV_FN(gen_##INSN##_tramp16, gen_helper_neon_##FUNC##_s16); \ + WRAP_ENV_FN(gen_##INSN##_tramp32, gen_helper_neon_##FUNC##_s32); \ + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ + uint32_t rn_ofs, uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ + { \ + static const GVecGen3 ops[2] = { \ + { .fni4 = gen_##INSN##_tramp16 }, \ + { .fni4 = gen_##INSN##_tramp32 }, \ + }; \ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops[vece - 1]); \ + } \ + static bool trans_##INSN##_3s(DisasContext *s, arg_3same *a) \ + { \ + if (a->size != 1 && a->size != 2) { \ + return false; \ + } \ + return do_3same(s, a, gen_##INSN##_3s); \ + } + +DO_3SAME_VQDMULH(VQDMULH, qdmulh) +DO_3SAME_VQDMULH(VQRDMULH, qrdmulh) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VPMAX: case NEON_3R_VPMIN: case NEON_3R_VPADD_VQRDMLAH: + case NEON_3R_VQDMULH_VQRDMULH: /* Already handled by decodetree */ return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = neon_load_reg(rm, pass); } switch (op) { - case NEON_3R_VQDMULH_VQRDMULH: /* Multiply high. */ - if (!u) { /* VQDMULH */ - switch (size) { - case 1: - gen_helper_neon_qdmulh_s16(tmp, cpu_env, tmp, tmp2); - break; - case 2: - gen_helper_neon_qdmulh_s32(tmp, cpu_env, tmp, tmp2); - break; - default: abort(); - } - } else { /* VQRDMULH */ - switch (size) { - case 1: - gen_helper_neon_qrdmulh_s16(tmp, cpu_env, tmp, tmp2); - break; - case 2: - gen_helper_neon_qrdmulh_s32(tmp, cpu_env, tmp, tmp2); - break; - default: abort(); - } - } - break; case NEON_3R_FLOAT_ARITH: /* Floating point arithmetic. */ { TCGv_ptr fpstatus = get_fpstatus_ptr(1); -- 2.20.1 Convert the Neon VADD, VSUB, VABD 3-reg-same insns to decodetree. We already have gvec helpers for addition and subtraction, but must add one for fabd. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-12-peter.maydell@linaro.org --- target/arm/helper.h | 3 ++- target/arm/neon-dp.decode | 8 ++++++++ target/arm/neon_helper.c | 7 ------- target/arm/translate-neon.inc.c | 28 ++++++++++++++++++++++++++++ target/arm/translate.c | 10 +++------- target/arm/vec_helper.c | 7 +++++++ 6 files changed, 48 insertions(+), 15 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(neon_qneg_s16, TCG_CALL_NO_RWG, i32, env, i32) DEF_HELPER_FLAGS_2(neon_qneg_s32, TCG_CALL_NO_RWG, i32, env, i32) DEF_HELPER_FLAGS_2(neon_qneg_s64, TCG_CALL_NO_RWG, i64, env, i64) -DEF_HELPER_3(neon_abd_f32, i32, i32, i32, ptr) DEF_HELPER_3(neon_ceq_f32, i32, i32, i32, ptr) DEF_HELPER_3(neon_cge_f32, i32, i32, i32, ptr) DEF_HELPER_3(neon_cgt_f32, i32, i32, i32, ptr) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmul_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmul_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_s, TCG_CALL_NO_RWG, diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ @3same_q0 .... ... . . . size:2 .... .... .... . 0 . . .... \ &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp q=0 +# For FP insns the high bit of 'size' is used as part of opcode decode +@3same_fp .... ... . . . . size:1 .... .... .... . q:1 . . .... \ + &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp + VHADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 0 .... @3same VHADD_U_3s 1111 001 1 0 . .. .... .... 0000 . . . 0 .... @3same VQADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 1 .... @3same @@ -XXX,XX +XXX,XX @@ SHA256SU1_3s 1111 001 1 0 . 10 .... .... 1100 . 1 . 0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp VQRDMLSH_3s 1111 001 1 0 . .. .... .... 1100 ... 1 .... @3same + +VADD_fp_3s 1111 001 0 0 . 0 . .... .... 1101 ... 0 .... @3same_fp +VSUB_fp_3s 1111 001 0 0 . 1 . .... .... 1101 ... 0 .... @3same_fp +VABD_fp_3s 1111 001 1 0 . 1 . .... .... 1101 ... 0 .... @3same_fp diff --git a/target/arm/neon_helper.c b/target/arm/neon_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon_helper.c +++ b/target/arm/neon_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_qneg_s64)(CPUARMState *env, uint64_t x) } /* NEON Float helpers. */ -uint32_t HELPER(neon_abd_f32)(uint32_t a, uint32_t b, void *fpstp) -{ - float_status *fpst = fpstp; - float32 f0 = make_float32(a); - float32 f1 = make_float32(b); - return float32_val(float32_abs(float32_sub(f0, f1, fpst))); -} /* Floating point comparisons produce an integer result. * Note that EQ doesn't signal InvalidOp for QNaNs but GE and GT do. diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_PAIR(VPADD, padd_u) DO_3SAME_VQDMULH(VQDMULH, qdmulh) DO_3SAME_VQDMULH(VQRDMULH, qrdmulh) + +/* + * For all the functions using this macro, size == 1 means fp16, + * which is an architecture extension we don't implement yet. + */ +#define DO_3S_FP_GVEC(INSN,FUNC) \ + static void gen_##INSN##_3s(unsigned vece, uint32_t rd_ofs, \ + uint32_t rn_ofs, uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ + { \ + TCGv_ptr fpst = get_fpstatus_ptr(1); \ + tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpst, \ + oprsz, maxsz, 0, FUNC); \ + tcg_temp_free_ptr(fpst); \ + } \ + static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \ + { \ + if (a->size != 0) { \ + /* TODO fp16 support */ \ + return false; \ + } \ + return do_3same(s, a, gen_##INSN##_3s); \ + } + + +DO_3S_FP_GVEC(VADD, gen_helper_gvec_fadd_s) +DO_3S_FP_GVEC(VSUB, gen_helper_gvec_fsub_s) +DO_3S_FP_GVEC(VABD, gen_helper_gvec_fabd_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 int disas_neon_data_insn(DisasContext *s, uint32_t insn) switch (op) { case NEON_3R_FLOAT_ARITH: pairwise = (u && size < 2); /* if VPADD (float) */ + if (!pairwise) { + return 1; /* handled by decodetree */ + } break; case NEON_3R_FLOAT_MINMAX: pairwise = u; /* if VPMIN/VPMAX (float) */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) { TCGv_ptr fpstatus = get_fpstatus_ptr(1); switch ((u << 2) | size) { - case 0: /* VADD */ case 4: /* VPADD */ gen_helper_vfp_adds(tmp, tmp, tmp2, fpstatus); break; - case 2: /* VSUB */ - gen_helper_vfp_subs(tmp, tmp, tmp2, fpstatus); - break; - case 6: /* VABD */ - gen_helper_neon_abd_f32(tmp, tmp, tmp2, fpstatus); - break; default: abort(); } 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 @@ static float64 float64_ftsmul(float64 op1, uint64_t op2, float_status *stat) return result; } +static float32 float32_abd(float32 op1, float32 op2, float_status *stat) +{ + return float32_abs(float32_sub(op1, op2, stat)); +} + #define DO_3OP(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ { \ @@ -XXX,XX +XXX,XX @@ DO_3OP(gvec_ftsmul_h, float16_ftsmul, float16) DO_3OP(gvec_ftsmul_s, float32_ftsmul, float32) DO_3OP(gvec_ftsmul_d, float64_ftsmul, float64) +DO_3OP(gvec_fabd_s, float32_abd, float32) + #ifdef TARGET_AARCH64 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) -- 2.20.1 Convert the Neon float VPMIN, VPMAX and VPADD 3-reg-same insns to decodetree. These are the only remaining 'pairwise' operations, so we can delete the pairwise-specific bits of the old decoder's for-each-element loop now. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-13-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 5 +++ target/arm/translate-neon.inc.c | 63 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 63 +++++---------------------------- 3 files changed, 76 insertions(+), 55 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ # For FP insns the high bit of 'size' is used as part of opcode decode @3same_fp .... ... . . . . size:1 .... .... .... . q:1 . . .... \ &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp +@3same_fp_q0 .... ... . . . . size:1 .... .... .... . 0 . . .... \ + &3same vm=%vm_dp vn=%vn_dp vd=%vd_dp q=0 VHADD_S_3s 1111 001 0 0 . .. .... .... 0000 . . . 0 .... @3same VHADD_U_3s 1111 001 1 0 . .. .... .... 0000 . . . 0 .... @3same @@ -XXX,XX +XXX,XX @@ VQRDMLSH_3s 1111 001 1 0 . .. .... .... 1100 ... 1 .... @3same VADD_fp_3s 1111 001 0 0 . 0 . .... .... 1101 ... 0 .... @3same_fp VSUB_fp_3s 1111 001 0 0 . 1 . .... .... 1101 ... 0 .... @3same_fp +VPADD_fp_3s 1111 001 1 0 . 0 . .... .... 1101 ... 0 .... @3same_fp_q0 VABD_fp_3s 1111 001 1 0 . 1 . .... .... 1101 ... 0 .... @3same_fp +VPMAX_fp_3s 1111 001 1 0 . 0 . .... .... 1111 ... 0 .... @3same_fp_q0 +VPMIN_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 0 .... @3same_fp_q0 diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_VQDMULH(VQRDMULH, qrdmulh) DO_3S_FP_GVEC(VADD, gen_helper_gvec_fadd_s) DO_3S_FP_GVEC(VSUB, gen_helper_gvec_fsub_s) DO_3S_FP_GVEC(VABD, gen_helper_gvec_fabd_s) + +static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn) +{ + /* FP operations handled pairwise 32 bits at a time */ + TCGv_i32 tmp, tmp2, tmp3; + TCGv_ptr fpstatus; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + assert(a->q == 0); /* enforced by decode patterns */ + + /* + * Note that we have to be careful not to clobber the source operands + * in the "vm == vd" case by storing the result of the first pass too + * early. Since Q is 0 there are always just two passes, so instead + * of a complicated loop over each pass we just unroll. + */ + fpstatus = get_fpstatus_ptr(1); + tmp = neon_load_reg(a->vn, 0); + tmp2 = neon_load_reg(a->vn, 1); + fn(tmp, tmp, tmp2, fpstatus); + tcg_temp_free_i32(tmp2); + + tmp3 = neon_load_reg(a->vm, 0); + tmp2 = neon_load_reg(a->vm, 1); + fn(tmp3, tmp3, tmp2, fpstatus); + tcg_temp_free_i32(tmp2); + tcg_temp_free_ptr(fpstatus); + + neon_store_reg(a->vd, 0, tmp); + neon_store_reg(a->vd, 1, tmp3); + return true; +} + +/* + * For all the functions using this macro, size == 1 means fp16, + * which is an architecture extension we don't implement yet. + */ +#define DO_3S_FP_PAIR(INSN,FUNC) \ + static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \ + { \ + if (a->size != 0) { \ + /* TODO fp16 support */ \ + return false; \ + } \ + return do_3same_fp_pair(s, a, FUNC); \ + } + +DO_3S_FP_PAIR(VPADD, gen_helper_vfp_adds) +DO_3S_FP_PAIR(VPMAX, gen_helper_vfp_maxs) +DO_3S_FP_PAIR(VPMIN, gen_helper_vfp_mins) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) int shift; int pass; int count; - int pairwise; int u; int vec_size; uint32_t imm; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VPMIN: case NEON_3R_VPADD_VQRDMLAH: case NEON_3R_VQDMULH_VQRDMULH: + case NEON_3R_FLOAT_ARITH: /* Already handled by decodetree */ return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) /* 64-bit element instructions: handled by decodetree */ return 1; } - pairwise = 0; switch (op) { - case NEON_3R_FLOAT_ARITH: - pairwise = (u && size < 2); /* if VPADD (float) */ - if (!pairwise) { - return 1; /* handled by decodetree */ - } - break; case NEON_3R_FLOAT_MINMAX: - pairwise = u; /* if VPMIN/VPMAX (float) */ + if (u) { + return 1; /* VPMIN/VPMAX handled by decodetree */ + } break; case NEON_3R_FLOAT_CMP: if (!u && size) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) break; } - if (pairwise && q) { - /* All the pairwise insns UNDEF if Q is set */ - return 1; - } - for (pass = 0; pass < (q ? 4 : 2); pass++) { - if (pairwise) { - /* Pairwise. */ - if (pass < 1) { - tmp = neon_load_reg(rn, 0); - tmp2 = neon_load_reg(rn, 1); - } else { - tmp = neon_load_reg(rm, 0); - tmp2 = neon_load_reg(rm, 1); - } - } else { - /* Elementwise. */ - tmp = neon_load_reg(rn, pass); - tmp2 = neon_load_reg(rm, pass); - } + /* Elementwise. */ + tmp = neon_load_reg(rn, pass); + tmp2 = neon_load_reg(rm, pass); switch (op) { - case NEON_3R_FLOAT_ARITH: /* Floating point arithmetic. */ - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - switch ((u << 2) | size) { - case 4: /* VPADD */ - gen_helper_vfp_adds(tmp, tmp, tmp2, fpstatus); - break; - default: - abort(); - } - tcg_temp_free_ptr(fpstatus); - break; - } case NEON_3R_FLOAT_MULTIPLY: { TCGv_ptr fpstatus = get_fpstatus_ptr(1); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } tcg_temp_free_i32(tmp2); - /* Save the result. For elementwise operations we can put it - straight into the destination register. For pairwise operations - we have to be careful to avoid clobbering the source operands. */ - if (pairwise && rd == rm) { - neon_store_scratch(pass, tmp); - } else { - neon_store_reg(rd, pass, tmp); - } + neon_store_reg(rd, pass, tmp); } /* for pass */ - if (pairwise && rd == rm) { - for (pass = 0; pass < (q ? 4 : 2); pass++) { - tmp = neon_load_scratch(pass); - neon_store_reg(rd, pass, tmp); - } - } /* End of 3 register same size operations. */ } else if (insn & (1 << 4)) { if ((insn & 0x00380080) != 0) { -- 2.20.1 Convert the Neon integer VMUL, VMLA, and VMLS 3-reg-same inssn to decodetree. We don't have a gvec helper for multiply-accumulate, so VMLA and VMLS need a loop function do_3same_fp(). This takes a reads_vd parameter to do_3same_fp() which tells it to load the old value into vd before calling the callback function, in the same way that the do_vfp_3op_sp() and do_vfp_3op_dp() functions in translate-vfp.inc.c work. (The only uses in this patch pass reads_vd == true, but later commits will use reads_vd == false.) This conversion fixes in passing an underdecoding for VMUL (originally reported by Fredrik Strupe <fredrik@strupe.net>): bit 1 of the 'size' field must be 0. The old decoder didn't enforce this, but the decodetree pattern does. The gen_VMLA_fp_reg() function performs the addition operation with the operands in the opposite order to the old decoder: since Neon sets 'default NaN mode' float32_add operations are commutative so there is no behaviour difference, but putting them this way around matches the Arm ARM pseudocode and the required operation order for the subtraction in gen_VMLS_fp_reg(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-14-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 3 ++ target/arm/translate-neon.inc.c | 81 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 17 +------ 3 files changed, 85 insertions(+), 16 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VADD_fp_3s 1111 001 0 0 . 0 . .... .... 1101 ... 0 .... @3same_fp VSUB_fp_3s 1111 001 0 0 . 1 . .... .... 1101 ... 0 .... @3same_fp VPADD_fp_3s 1111 001 1 0 . 0 . .... .... 1101 ... 0 .... @3same_fp_q0 VABD_fp_3s 1111 001 1 0 . 1 . .... .... 1101 ... 0 .... @3same_fp +VMLA_fp_3s 1111 001 0 0 . 0 . .... .... 1101 ... 1 .... @3same_fp +VMLS_fp_3s 1111 001 0 0 . 1 . .... .... 1101 ... 1 .... @3same_fp +VMUL_fp_3s 1111 001 1 0 . 0 . .... .... 1101 ... 1 .... @3same_fp VPMAX_fp_3s 1111 001 1 0 . 0 . .... .... 1111 ... 0 .... @3same_fp_q0 VPMIN_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 0 .... @3same_fp_q0 diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3SAME_PAIR(VPADD, padd_u) DO_3SAME_VQDMULH(VQDMULH, qdmulh) DO_3SAME_VQDMULH(VQRDMULH, qrdmulh) +static bool do_3same_fp(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn, + bool reads_vd) +{ + /* + * FP operations handled elementwise 32 bits at a time. + * If reads_vd is true then the old value of Vd will be + * loaded before calling the callback function. This is + * used for multiply-accumulate type operations. + */ + TCGv_i32 tmp, tmp2; + int pass; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if ((a->vn | a->vm | a->vd) & a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + TCGv_ptr fpstatus = get_fpstatus_ptr(1); + for (pass = 0; pass < (a->q ? 4 : 2); pass++) { + tmp = neon_load_reg(a->vn, pass); + tmp2 = neon_load_reg(a->vm, pass); + if (reads_vd) { + TCGv_i32 tmp_rd = neon_load_reg(a->vd, pass); + fn(tmp_rd, tmp, tmp2, fpstatus); + neon_store_reg(a->vd, pass, tmp_rd); + tcg_temp_free_i32(tmp); + } else { + fn(tmp, tmp, tmp2, fpstatus); + neon_store_reg(a->vd, pass, tmp); + } + tcg_temp_free_i32(tmp2); + } + tcg_temp_free_ptr(fpstatus); + return true; +} + /* * For all the functions using this macro, size == 1 means fp16, * which is an architecture extension we don't implement yet. @@ -XXX,XX +XXX,XX @@ DO_3SAME_VQDMULH(VQRDMULH, qrdmulh) DO_3S_FP_GVEC(VADD, gen_helper_gvec_fadd_s) DO_3S_FP_GVEC(VSUB, gen_helper_gvec_fsub_s) DO_3S_FP_GVEC(VABD, gen_helper_gvec_fabd_s) +DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s) + +/* + * For all the functions using this macro, size == 1 means fp16, + * which is an architecture extension we don't implement yet. + */ +#define DO_3S_FP(INSN,FUNC,READS_VD) \ + static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \ + { \ + if (a->size != 0) { \ + /* TODO fp16 support */ \ + return false; \ + } \ + return do_3same_fp(s, a, FUNC, READS_VD); \ + } + +static void gen_VMLA_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, + TCGv_ptr fpstatus) +{ + gen_helper_vfp_muls(vn, vn, vm, fpstatus); + gen_helper_vfp_adds(vd, vd, vn, fpstatus); +} + +static void gen_VMLS_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, + TCGv_ptr fpstatus) +{ + gen_helper_vfp_muls(vn, vn, vm, fpstatus); + gen_helper_vfp_subs(vd, vd, vn, fpstatus); +} + +DO_3S_FP(VMLA, gen_VMLA_fp_3s, true) +DO_3S_FP(VMLS, gen_VMLS_fp_3s, true) static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn) { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VPADD_VQRDMLAH: case NEON_3R_VQDMULH_VQRDMULH: case NEON_3R_FLOAT_ARITH: + case NEON_3R_FLOAT_MULTIPLY: /* Already handled by decodetree */ return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp = neon_load_reg(rn, pass); tmp2 = neon_load_reg(rm, pass); switch (op) { - case NEON_3R_FLOAT_MULTIPLY: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_vfp_muls(tmp, tmp, tmp2, fpstatus); - if (!u) { - tcg_temp_free_i32(tmp2); - tmp2 = neon_load_reg(rd, pass); - if (size == 0) { - gen_helper_vfp_adds(tmp, tmp, tmp2, fpstatus); - } else { - gen_helper_vfp_subs(tmp, tmp2, tmp, fpstatus); - } - } - tcg_temp_free_ptr(fpstatus); - break; - } case NEON_3R_FLOAT_CMP: { TCGv_ptr fpstatus = get_fpstatus_ptr(1); -- 2.20.1 Convert the Neon integer 3-reg-same compare insns VCGE, VCGT, VCEQ, VACGE and VACGT to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-15-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 5 +++++ target/arm/translate-neon.inc.c | 6 +++++ target/arm/translate.c | 39 ++------------------------------- 3 files changed, 13 insertions(+), 37 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VABD_fp_3s 1111 001 1 0 . 1 . .... .... 1101 ... 0 .... @3same_fp VMLA_fp_3s 1111 001 0 0 . 0 . .... .... 1101 ... 1 .... @3same_fp VMLS_fp_3s 1111 001 0 0 . 1 . .... .... 1101 ... 1 .... @3same_fp VMUL_fp_3s 1111 001 1 0 . 0 . .... .... 1101 ... 1 .... @3same_fp +VCEQ_fp_3s 1111 001 0 0 . 0 . .... .... 1110 ... 0 .... @3same_fp +VCGE_fp_3s 1111 001 1 0 . 0 . .... .... 1110 ... 0 .... @3same_fp +VACGE_fp_3s 1111 001 1 0 . 0 . .... .... 1110 ... 1 .... @3same_fp +VCGT_fp_3s 1111 001 1 0 . 1 . .... .... 1110 ... 0 .... @3same_fp +VACGT_fp_3s 1111 001 1 0 . 1 . .... .... 1110 ... 1 .... @3same_fp VPMAX_fp_3s 1111 001 1 0 . 0 . .... .... 1111 ... 0 .... @3same_fp_q0 VPMIN_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 0 .... @3same_fp_q0 diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s) return do_3same_fp(s, a, FUNC, READS_VD); \ } +DO_3S_FP(VCEQ, gen_helper_neon_ceq_f32, false) +DO_3S_FP(VCGE, gen_helper_neon_cge_f32, false) +DO_3S_FP(VCGT, gen_helper_neon_cgt_f32, false) +DO_3S_FP(VACGE, gen_helper_neon_acge_f32, false) +DO_3S_FP(VACGT, gen_helper_neon_acgt_f32, false) + static void gen_VMLA_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpstatus) { diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VQDMULH_VQRDMULH: case NEON_3R_FLOAT_ARITH: case NEON_3R_FLOAT_MULTIPLY: + case NEON_3R_FLOAT_CMP: + case NEON_3R_FLOAT_ACMP: /* Already handled by decodetree */ return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; /* VPMIN/VPMAX handled by decodetree */ } break; - case NEON_3R_FLOAT_CMP: - if (!u && size) { - /* no encoding for U=0 C=1x */ - return 1; - } - break; - case NEON_3R_FLOAT_ACMP: - if (!u) { - return 1; - } - break; case NEON_3R_FLOAT_MISC: /* VMAXNM/VMINNM in ARMv8 */ if (u && !arm_dc_feature(s, ARM_FEATURE_V8)) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp = neon_load_reg(rn, pass); tmp2 = neon_load_reg(rm, pass); switch (op) { - case NEON_3R_FLOAT_CMP: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - if (!u) { - gen_helper_neon_ceq_f32(tmp, tmp, tmp2, fpstatus); - } else { - if (size == 0) { - gen_helper_neon_cge_f32(tmp, tmp, tmp2, fpstatus); - } else { - gen_helper_neon_cgt_f32(tmp, tmp, tmp2, fpstatus); - } - } - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_3R_FLOAT_ACMP: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - if (size == 0) { - gen_helper_neon_acge_f32(tmp, tmp, tmp2, fpstatus); - } else { - gen_helper_neon_acgt_f32(tmp, tmp, tmp2, fpstatus); - } - tcg_temp_free_ptr(fpstatus); - break; - } case NEON_3R_FLOAT_MINMAX: { TCGv_ptr fpstatus = get_fpstatus_ptr(1); -- 2.20.1 The usual location for the env argument in the argument list of a TCG helper is immediately after the return-value argument. recps_f32 and rsqrts_f32 differ in that they put it at the end. Move the env argument to its usual place; this will allow us to more easily use these helper functions with the gvec APIs. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-16-peter.maydell@linaro.org --- target/arm/helper.h | 4 ++-- target/arm/translate.c | 4 ++-- target/arm/vfp_helper.c | 4 ++-- 3 files changed, 6 insertions(+), 6 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(vfp_fcvt_f64_to_f16, TCG_CALL_NO_RWG, f16, f64, ptr, i32) DEF_HELPER_4(vfp_muladdd, f64, f64, f64, f64, ptr) DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, ptr) -DEF_HELPER_3(recps_f32, f32, f32, f32, env) -DEF_HELPER_3(rsqrts_f32, f32, f32, f32, env) +DEF_HELPER_3(recps_f32, f32, env, f32, f32) +DEF_HELPER_3(rsqrts_f32, f32, env, f32, f32) DEF_HELPER_FLAGS_2(recpe_f16, TCG_CALL_NO_RWG, f16, f16, ptr) DEF_HELPER_FLAGS_2(recpe_f32, TCG_CALL_NO_RWG, f32, f32, ptr) DEF_HELPER_FLAGS_2(recpe_f64, TCG_CALL_NO_RWG, f64, f64, ptr) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_temp_free_ptr(fpstatus); } else { if (size == 0) { - gen_helper_recps_f32(tmp, tmp, tmp2, cpu_env); + gen_helper_recps_f32(tmp, cpu_env, tmp, tmp2); } else { - gen_helper_rsqrts_f32(tmp, tmp, tmp2, cpu_env); + gen_helper_rsqrts_f32(tmp, cpu_env, tmp, tmp2); } } break; diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode) #define float32_three make_float32(0x40400000) #define float32_one_point_five make_float32(0x3fc00000) -float32 HELPER(recps_f32)(float32 a, float32 b, CPUARMState *env) +float32 HELPER(recps_f32)(CPUARMState *env, float32 a, float32 b) { float_status *s = &env->vfp.standard_fp_status; if ((float32_is_infinity(a) && float32_is_zero_or_denormal(b)) || @@ -XXX,XX +XXX,XX @@ float32 HELPER(recps_f32)(float32 a, float32 b, CPUARMState *env) return float32_sub(float32_two, float32_mul(a, b, s), s); } -float32 HELPER(rsqrts_f32)(float32 a, float32 b, CPUARMState *env) +float32 HELPER(rsqrts_f32)(CPUARMState *env, float32 a, float32 b) { float_status *s = &env->vfp.standard_fp_status; float32 product; -- 2.20.1 Convert the Neon fp VMAX/VMIN/VMAXNM/VMINNM/VRECPS/VRSQRTS 3-reg-same insns to decodetree. (These are all the remaining non-accumulation instructions in this group.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-17-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 6 +++ target/arm/translate-neon.inc.c | 70 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 42 +------------------- 3 files changed, 78 insertions(+), 40 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VCGE_fp_3s 1111 001 1 0 . 0 . .... .... 1110 ... 0 .... @3same_fp VACGE_fp_3s 1111 001 1 0 . 0 . .... .... 1110 ... 1 .... @3same_fp VCGT_fp_3s 1111 001 1 0 . 1 . .... .... 1110 ... 0 .... @3same_fp VACGT_fp_3s 1111 001 1 0 . 1 . .... .... 1110 ... 1 .... @3same_fp +VMAX_fp_3s 1111 001 0 0 . 0 . .... .... 1111 ... 0 .... @3same_fp +VMIN_fp_3s 1111 001 0 0 . 1 . .... .... 1111 ... 0 .... @3same_fp VPMAX_fp_3s 1111 001 1 0 . 0 . .... .... 1111 ... 0 .... @3same_fp_q0 VPMIN_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 0 .... @3same_fp_q0 +VRECPS_fp_3s 1111 001 0 0 . 0 . .... .... 1111 ... 1 .... @3same_fp +VRSQRTS_fp_3s 1111 001 0 0 . 1 . .... .... 1111 ... 1 .... @3same_fp +VMAXNM_fp_3s 1111 001 1 0 . 0 . .... .... 1111 ... 1 .... @3same_fp +VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_3S_FP(VCGE, gen_helper_neon_cge_f32, false) DO_3S_FP(VCGT, gen_helper_neon_cgt_f32, false) DO_3S_FP(VACGE, gen_helper_neon_acge_f32, false) DO_3S_FP(VACGT, gen_helper_neon_acgt_f32, false) +DO_3S_FP(VMAX, gen_helper_vfp_maxs, false) +DO_3S_FP(VMIN, gen_helper_vfp_mins, false) static void gen_VMLA_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpstatus) @@ -XXX,XX +XXX,XX @@ static void gen_VMLS_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, DO_3S_FP(VMLA, gen_VMLA_fp_3s, true) DO_3S_FP(VMLS, gen_VMLS_fp_3s, true) +static bool trans_VMAXNM_fp_3s(DisasContext *s, arg_3same *a) +{ + if (!arm_dc_feature(s, ARM_FEATURE_V8)) { + return false; + } + + if (a->size != 0) { + /* TODO fp16 support */ + return false; + } + + return do_3same_fp(s, a, gen_helper_vfp_maxnums, false); +} + +static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) +{ + if (!arm_dc_feature(s, ARM_FEATURE_V8)) { + return false; + } + + if (a->size != 0) { + /* TODO fp16 support */ + return false; + } + + return do_3same_fp(s, a, gen_helper_vfp_minnums, false); +} + +WRAP_ENV_FN(gen_VRECPS_tramp, gen_helper_recps_f32) + +static void gen_VRECPS_fp_3s(unsigned vece, uint32_t rd_ofs, + uint32_t rn_ofs, uint32_t rm_ofs, + uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen3 ops = { .fni4 = gen_VRECPS_tramp }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops); +} + +static bool trans_VRECPS_fp_3s(DisasContext *s, arg_3same *a) +{ + if (a->size != 0) { + /* TODO fp16 support */ + return false; + } + + return do_3same(s, a, gen_VRECPS_fp_3s); +} + +WRAP_ENV_FN(gen_VRSQRTS_tramp, gen_helper_rsqrts_f32) + +static void gen_VRSQRTS_fp_3s(unsigned vece, uint32_t rd_ofs, + uint32_t rn_ofs, uint32_t rm_ofs, + uint32_t oprsz, uint32_t maxsz) +{ + static const GVecGen3 ops = { .fni4 = gen_VRSQRTS_tramp }; + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, oprsz, maxsz, &ops); +} + +static bool trans_VRSQRTS_fp_3s(DisasContext *s, arg_3same *a) +{ + if (a->size != 0) { + /* TODO fp16 support */ + return false; + } + + return do_3same(s, a, gen_VRSQRTS_fp_3s); +} + static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn) { /* FP operations handled pairwise 32 bits at a time */ diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_FLOAT_MULTIPLY: case NEON_3R_FLOAT_CMP: case NEON_3R_FLOAT_ACMP: + case NEON_3R_FLOAT_MINMAX: + case NEON_3R_FLOAT_MISC: /* Already handled by decodetree */ return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } switch (op) { - case NEON_3R_FLOAT_MINMAX: - if (u) { - return 1; /* VPMIN/VPMAX handled by decodetree */ - } - break; - case NEON_3R_FLOAT_MISC: - /* VMAXNM/VMINNM in ARMv8 */ - if (u && !arm_dc_feature(s, ARM_FEATURE_V8)) { - return 1; - } - break; case NEON_3R_VFM_VQRDMLSH: if (!dc_isar_feature(aa32_simdfmac, s)) { return 1; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp = neon_load_reg(rn, pass); tmp2 = neon_load_reg(rm, pass); switch (op) { - case NEON_3R_FLOAT_MINMAX: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - if (size == 0) { - gen_helper_vfp_maxs(tmp, tmp, tmp2, fpstatus); - } else { - gen_helper_vfp_mins(tmp, tmp, tmp2, fpstatus); - } - tcg_temp_free_ptr(fpstatus); - break; - } - case NEON_3R_FLOAT_MISC: - if (u) { - /* VMAXNM/VMINNM */ - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - if (size == 0) { - gen_helper_vfp_maxnums(tmp, tmp, tmp2, fpstatus); - } else { - gen_helper_vfp_minnums(tmp, tmp, tmp2, fpstatus); - } - tcg_temp_free_ptr(fpstatus); - } else { - if (size == 0) { - gen_helper_recps_f32(tmp, cpu_env, tmp, tmp2); - } else { - gen_helper_rsqrts_f32(tmp, cpu_env, tmp, tmp2); - } - } - break; case NEON_3R_VFM_VQRDMLSH: { /* VFMA, VFMS: fused multiply-add */ -- 2.20.1 Convert the Neon floating point VFMA and VFMS insn to decodetree. These are the last insns in the 3-reg-same group so we can remove all the support/loop code from the old decoder. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200512163904.10918-18-peter.maydell@linaro.org --- target/arm/neon-dp.decode | 3 + target/arm/translate-neon.inc.c | 41 ++++++++ target/arm/translate.c | 176 +------------------------------- 3 files changed, 46 insertions(+), 174 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ SHA256H2_3s 1111 001 1 0 . 01 .... .... 1100 . 1 . 0 .... \ SHA256SU1_3s 1111 001 1 0 . 10 .... .... 1100 . 1 . 0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp +VFMA_fp_3s 1111 001 0 0 . 0 . .... .... 1100 ... 1 .... @3same_fp +VFMS_fp_3s 1111 001 0 0 . 1 . .... .... 1100 ... 1 .... @3same_fp + VQRDMLSH_3s 1111 001 1 0 . .. .... .... 1100 ... 1 .... @3same VADD_fp_3s 1111 001 0 0 . 0 . .... .... 1101 ... 0 .... @3same_fp diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VRSQRTS_fp_3s(DisasContext *s, arg_3same *a) return do_3same(s, a, gen_VRSQRTS_fp_3s); } +static void gen_VFMA_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, + TCGv_ptr fpstatus) +{ + gen_helper_vfp_muladds(vd, vn, vm, vd, fpstatus); +} + +static bool trans_VFMA_fp_3s(DisasContext *s, arg_3same *a) +{ + if (!dc_isar_feature(aa32_simdfmac, s)) { + return false; + } + + if (a->size != 0) { + /* TODO fp16 support */ + return false; + } + + return do_3same_fp(s, a, gen_VFMA_fp_3s, true); +} + +static void gen_VFMS_fp_3s(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, + TCGv_ptr fpstatus) +{ + gen_helper_vfp_negs(vn, vn); + gen_helper_vfp_muladds(vd, vn, vm, vd, fpstatus); +} + +static bool trans_VFMS_fp_3s(DisasContext *s, arg_3same *a) +{ + if (!dc_isar_feature(aa32_simdfmac, s)) { + return false; + } + + if (a->size != 0) { + /* TODO fp16 support */ + return false; + } + + return do_3same_fp(s, a, gen_VFMS_fp_3s, true); +} + static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn) { /* FP operations handled pairwise 32 bits at a time */ 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 gen_neon_narrow_op(int op, int u, int size, } } -/* Symbolic constants for op fields for Neon 3-register same-length. - * The values correspond to bits [11:8,4]; see the ARM ARM DDI0406B - * table A7-9. - */ -#define NEON_3R_VHADD 0 -#define NEON_3R_VQADD 1 -#define NEON_3R_VRHADD 2 -#define NEON_3R_LOGIC 3 /* VAND,VBIC,VORR,VMOV,VORN,VEOR,VBIF,VBIT,VBSL */ -#define NEON_3R_VHSUB 4 -#define NEON_3R_VQSUB 5 -#define NEON_3R_VCGT 6 -#define NEON_3R_VCGE 7 -#define NEON_3R_VSHL 8 -#define NEON_3R_VQSHL 9 -#define NEON_3R_VRSHL 10 -#define NEON_3R_VQRSHL 11 -#define NEON_3R_VMAX 12 -#define NEON_3R_VMIN 13 -#define NEON_3R_VABD 14 -#define NEON_3R_VABA 15 -#define NEON_3R_VADD_VSUB 16 -#define NEON_3R_VTST_VCEQ 17 -#define NEON_3R_VML 18 /* VMLA, VMLS */ -#define NEON_3R_VMUL 19 -#define NEON_3R_VPMAX 20 -#define NEON_3R_VPMIN 21 -#define NEON_3R_VQDMULH_VQRDMULH 22 -#define NEON_3R_VPADD_VQRDMLAH 23 -#define NEON_3R_SHA 24 /* SHA1C,SHA1P,SHA1M,SHA1SU0,SHA256H{2},SHA256SU1 */ -#define NEON_3R_VFM_VQRDMLSH 25 /* VFMA, VFMS, VQRDMLSH */ -#define NEON_3R_FLOAT_ARITH 26 /* float VADD, VSUB, VPADD, VABD */ -#define NEON_3R_FLOAT_MULTIPLY 27 /* float VMLA, VMLS, VMUL */ -#define NEON_3R_FLOAT_CMP 28 /* float VCEQ, VCGE, VCGT */ -#define NEON_3R_FLOAT_ACMP 29 /* float VACGE, VACGT, VACLE, VACLT */ -#define NEON_3R_FLOAT_MINMAX 30 /* float VMIN, VMAX */ -#define NEON_3R_FLOAT_MISC 31 /* float VRECPS, VRSQRTS, VMAXNM/MINNM */ - -static const uint8_t neon_3r_sizes[] = { - [NEON_3R_VHADD] = 0x7, - [NEON_3R_VQADD] = 0xf, - [NEON_3R_VRHADD] = 0x7, - [NEON_3R_LOGIC] = 0xf, /* size field encodes op type */ - [NEON_3R_VHSUB] = 0x7, - [NEON_3R_VQSUB] = 0xf, - [NEON_3R_VCGT] = 0x7, - [NEON_3R_VCGE] = 0x7, - [NEON_3R_VSHL] = 0xf, - [NEON_3R_VQSHL] = 0xf, - [NEON_3R_VRSHL] = 0xf, - [NEON_3R_VQRSHL] = 0xf, - [NEON_3R_VMAX] = 0x7, - [NEON_3R_VMIN] = 0x7, - [NEON_3R_VABD] = 0x7, - [NEON_3R_VABA] = 0x7, - [NEON_3R_VADD_VSUB] = 0xf, - [NEON_3R_VTST_VCEQ] = 0x7, - [NEON_3R_VML] = 0x7, - [NEON_3R_VMUL] = 0x7, - [NEON_3R_VPMAX] = 0x7, - [NEON_3R_VPMIN] = 0x7, - [NEON_3R_VQDMULH_VQRDMULH] = 0x6, - [NEON_3R_VPADD_VQRDMLAH] = 0x7, - [NEON_3R_SHA] = 0xf, /* size field encodes op type */ - [NEON_3R_VFM_VQRDMLSH] = 0x7, /* For VFM, size bit 1 encodes op */ - [NEON_3R_FLOAT_ARITH] = 0x5, /* size bit 1 encodes op */ - [NEON_3R_FLOAT_MULTIPLY] = 0x5, /* size bit 1 encodes op */ - [NEON_3R_FLOAT_CMP] = 0x5, /* size bit 1 encodes op */ - [NEON_3R_FLOAT_ACMP] = 0x5, /* size bit 1 encodes op */ - [NEON_3R_FLOAT_MINMAX] = 0x5, /* size bit 1 encodes op */ - [NEON_3R_FLOAT_MISC] = 0x5, /* size bit 1 encodes op */ -}; - /* Symbolic constants for op fields for Neon 2-register miscellaneous. * The values correspond to bits [17:16,10:7]; see the ARM ARM DDI0406B * table A7-13. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) rm_ofs = neon_reg_offset(rm, 0); if ((insn & (1 << 23)) == 0) { - /* Three register same length. */ - op = ((insn >> 7) & 0x1e) | ((insn >> 4) & 1); - /* Catch invalid op and bad size combinations: UNDEF */ - if ((neon_3r_sizes[op] & (1 << size)) == 0) { - return 1; - } - /* All insns of this form UNDEF for either this condition or the - * superset of cases "Q==1"; we catch the latter later. - */ - if (q && ((rd | rn | rm) & 1)) { - return 1; - } - switch (op) { - case NEON_3R_VFM_VQRDMLSH: - if (!u) { - /* VFM, VFMS */ - if (size == 1) { - return 1; - } - break; - } - /* VQRDMLSH : handled by decodetree */ - return 1; - - case NEON_3R_VADD_VSUB: - case NEON_3R_LOGIC: - case NEON_3R_VMAX: - case NEON_3R_VMIN: - case NEON_3R_VTST_VCEQ: - case NEON_3R_VCGT: - case NEON_3R_VCGE: - case NEON_3R_VQADD: - case NEON_3R_VQSUB: - case NEON_3R_VMUL: - case NEON_3R_VML: - case NEON_3R_VSHL: - case NEON_3R_SHA: - case NEON_3R_VHADD: - case NEON_3R_VRHADD: - case NEON_3R_VHSUB: - case NEON_3R_VABD: - case NEON_3R_VABA: - case NEON_3R_VQSHL: - case NEON_3R_VRSHL: - case NEON_3R_VQRSHL: - case NEON_3R_VPMAX: - case NEON_3R_VPMIN: - case NEON_3R_VPADD_VQRDMLAH: - case NEON_3R_VQDMULH_VQRDMULH: - case NEON_3R_FLOAT_ARITH: - case NEON_3R_FLOAT_MULTIPLY: - case NEON_3R_FLOAT_CMP: - case NEON_3R_FLOAT_ACMP: - case NEON_3R_FLOAT_MINMAX: - case NEON_3R_FLOAT_MISC: - /* Already handled by decodetree */ - return 1; - } - - if (size == 3) { - /* 64-bit element instructions: handled by decodetree */ - return 1; - } - switch (op) { - case NEON_3R_VFM_VQRDMLSH: - if (!dc_isar_feature(aa32_simdfmac, s)) { - return 1; - } - break; - default: - break; - } - - for (pass = 0; pass < (q ? 4 : 2); pass++) { - - /* Elementwise. */ - tmp = neon_load_reg(rn, pass); - tmp2 = neon_load_reg(rm, pass); - switch (op) { - case NEON_3R_VFM_VQRDMLSH: - { - /* VFMA, VFMS: fused multiply-add */ - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - TCGv_i32 tmp3 = neon_load_reg(rd, pass); - if (size) { - /* VFMS */ - gen_helper_vfp_negs(tmp, tmp); - } - gen_helper_vfp_muladds(tmp, tmp, tmp2, tmp3, fpstatus); - tcg_temp_free_i32(tmp3); - tcg_temp_free_ptr(fpstatus); - break; - } - default: - abort(); - } - tcg_temp_free_i32(tmp2); - - neon_store_reg(rd, pass, tmp); - - } /* for pass */ - /* End of 3 register same size operations. */ + /* Three register same length: handled by decodetree */ + return 1; } else if (insn & (1 << 4)) { if ((insn & 0x00380080) != 0) { /* Two registers and shift. */ -- 2.20.1 Hi; here's another arm pullreq; main parts here are the new i.MX 8MM EVK board, and a lot of refactoring. thanks -- PMM The following changes since commit aa15257174da180c6a8a9d58f87319cfe61c5520: Merge tag 'pbouvier/pr/plugins-20260424' of https://gitlab.com/p-b-o/qemu into staging (2026-04-25 10:22:04 -0400) are available in the Git repository at: https://gitlab.com/pm215/qemu.git tags/pull-target-arm-20260427 for you to fetch changes up to 4575da5ecb7a27544aa6da1f78e700e8100ceaea: target/arm: report register in WFIT syndromes (2026-04-27 11:46:34 +0100) ---------------------------------------------------------------- target-arm queue: docs/system: add FEAT_AA32 and FEAT_AA64 to emulation list hw/arm: Add the i.MX 8MM EVK(Evaluation Kit) board target/arm: Build M-profile helper code once only hw/arm: Remove hw_error() for the unimplemented CM_LMBUSCNT register hw: Move ARM_SYSCTL_GPIO definitions to arm sysctl specific header target/arm: Allow 'aarch64=off' to be set for TCG CPUs target/arm: Allow some sysregs to not have to be an exact match for migration hw/arm/raspi4b: NOP all DTB nodes when removing unimplemented devices hw/arm/fsl-imx6ul: Implement LCDIF display device target/arm: Refactor syndrome value code to use registerfields target/arm: Report the register in WFxT syndromes ---------------------------------------------------------------- Alex Bennée (24): docs/system: add FEAT_AA32 and FEAT_AA64 to emulation list target/arm: migrate basic syndrome helpers to registerfields target/arm: migrate system/cp trap syndromes to registerfields target/arm: migrate FP/SIMD trap syndromes to registerfields target/arm: migrate eret trap syndromes to registerfields target/arm: migrate SME trap syndromes to registerfields target/arm: migrate PAC trap syndromes to registerfields target/arm: migrate BTI trap syndromes to registerfields target/arm: migrate BXJ trap syndromes to registerfields target/arm: migrate Granule Protection traps to registerfields target/arm: migrate fault syndromes to registerfields target/arm: migrate debug syndromes to registerfields target/arm: migrate wfx syndromes to registerfields target/arm: migrate gcs syndromes to registerfields target/arm: migrate memory op syndromes to registerfields target/arm: migrate check_hcr_el2_trap to use syndrome helper target/arm: use syndrome helpers in arm_cpu_do_interrupt_aarch32_hyp target/arm: use syndrome helpers to set SAME_EL EC bit target/arm: make whpx use syndrome helpers for decode target/arm: make hvf use syndrome helpers for decode target/arm: use syndrome helpers in merge_syn_data_abort target/arm: use syndrome helpers to query VNCR bit target/arm: remove old syndrome defines target/arm: report register in WFIT syndromes Eric Auger (7): target/arm/cpu: Introduce the infrastructure for cpreg migration tolerances target/arm/machine: Handle ToleranceNotOnBothEnds migration tolerances target/arm/machine: Handle ToleranceOnlySrcTestValue migration tolerance target/arm/cpu64: Mitigate migration failures due to spurious TCR_EL1, PIRE0_EL1 and PIR_EL1 target/arm/cpu64: Define cpreg migration tolerance for KVM_REG_ARM_VENDOR_HYP_BMAP_2 target/arm/helper: Define cpreg migration tolerance for DGBDTR_EL0 Revert "target/arm: Reinstate bogus AArch32 DBGDTRTX register for migration compat" Gaurav Sharma (15): hw/arm: Add the i.MX 8MM EVK(Evaluation Kit) board hw/misc/imx8mp_analog: Add property to analog device hw/arm/fsl-imx8mm: Add Analog device IP to iMX8MM SOC hw/arm/fsl-imx8mm: Add Clock Control Module IP to iMX8MM hw/arm/fsl-imx8mm: Implemented support for SNVS hw/arm/fsl-imx8mm: Adding support for USDHC storage controllers hw/arm/fsl-imx8mm: Add PCIe support hw/arm/fsl-imx8mm: Add GPIO controllers hw/arm/fsl-imx8mm: Adding support for I2C emulation hw/arm/fsl-imx8mm: Adding support for SPI controller hw/arm/fsl-imx8mm: Adding support for Watchdog Timers hw/arm/fsl-imx8mm: Adding support for General Purpose Timers hw/arm/fsl-imx8mm: Adding support for ENET ethernet controller hw/arm/fsl-imx8mm: Adding support for USB controller hw/arm/fsl-imx8mm: Adding functional testing of iMX8MM emulation Osama Abdelkader (1): hw/arm/raspi4b: NOP all DTB nodes when removing unimplemented devices Peter Maydell (4): hw: Move ARM_SYSCTL_GPIO definitions to arm sysctl specific header target/arm: Clear AArch64 ID regs from ARMISARegisters if AArch64 disabled target/arm: Allow 'aarch64=off' to be set for TCG CPUs tests/functional/aarch64: Add basic test of TCG aarch64=off Philippe Mathieu-Daudé (9): target/arm: Ignore endianness when setting MTE tags target/arm: Explode MO_TExx -> MO_TE | MO_xx target/arm: Hoist MO_TE into mve_advance_vpt() target/arm: Hoist MO_TE into MVE DO_VSTR() macro target/arm: Introduce mo_endian() helper target/arm: Replace MO_TE -> mo_endian() for MVE helpers target/arm: Compile mve_helper.c once target/arm: Replace MO_TE -> mo_endian() for Cortex-M helpers target/arm: Compile m_helper.c once Thomas Huth (1): hw/arm: Remove hw_error() for the unimplemented CM_LMBUSCNT register Yucai Liu (2): hw/display: Add i.MX6UL LCDIF device model hw/arm/fsl-imx6ul: Wire in the LCDIF device model MAINTAINERS | 16 +- docs/system/arm/cpu-features.rst | 10 +- docs/system/arm/emulation.rst | 2 + docs/system/arm/{imx8mp-evk.rst => imx8m.rst} | 49 +- docs/system/target-arm.rst | 2 +- hw/arm/Kconfig | 25 + hw/arm/fsl-imx6ul.c | 12 +- hw/arm/fsl-imx8mm.c | 704 ++++++++++++++++++++++ hw/arm/imx8mm-evk.c | 130 ++++ hw/arm/integratorcp.c | 3 - hw/arm/meson.build | 2 + hw/arm/raspi4b.c | 10 +- hw/arm/realview.c | 2 +- hw/arm/vexpress.c | 2 +- hw/arm/virt.c | 1 - hw/display/Kconfig | 4 + hw/display/imx6ul_lcdif.c | 453 ++++++++++++++ hw/display/meson.build | 1 + hw/misc/arm_sysctl.c | 2 +- hw/misc/imx8mp_analog.c | 12 +- hw/timer/imx_gpt.c | 26 + hw/vmapple/vmapple.c | 1 - include/hw/arm/fsl-imx6ul.h | 4 +- include/hw/arm/fsl-imx8mm.h | 242 ++++++++ include/hw/arm/primecell.h | 12 - include/hw/display/imx6ul_lcdif.h | 37 ++ include/hw/misc/arm_sysctl.h | 16 + include/hw/misc/imx8mp_analog.h | 3 + include/hw/timer/imx_gpt.h | 2 + target/arm/cpu-features.h | 5 + target/arm/cpu.c | 153 ++++- target/arm/cpu.h | 4 +- target/arm/cpu64.c | 39 ++ target/arm/debug_helper.c | 29 - target/arm/helper.c | 27 +- target/arm/hvf/hvf.c | 14 +- target/arm/internals.h | 60 ++ target/arm/machine.c | 33 +- target/arm/syndrome.h | 595 ++++++++++++++---- target/arm/tcg/debug.c | 2 +- target/arm/tcg/helper-a64.c | 2 +- target/arm/tcg/helper-defs.h | 2 +- target/arm/tcg/m_helper.c | 8 +- target/arm/tcg/meson.build | 6 +- target/arm/tcg/mve_helper.c | 102 ++-- target/arm/tcg/op_helper.c | 7 +- target/arm/tcg/tlb_helper.c | 6 +- target/arm/tcg/translate-a64.c | 2 +- target/arm/tcg/vfp_helper.c | 5 +- target/arm/trace-events | 2 + target/arm/whpx/whpx-all.c | 13 +- tests/functional/aarch64/meson.build | 3 + tests/functional/aarch64/test_imx8mm_evk.py | 69 +++ tests/functional/aarch64/test_virt_aarch64_off.py | 37 ++ tests/qtest/arm-cpu-features.c | 8 +- 55 files changed, 2743 insertions(+), 275 deletions(-) rename docs/system/arm/{imx8mp-evk.rst => imx8m.rst} (58%) create mode 100644 hw/arm/fsl-imx8mm.c create mode 100644 hw/arm/imx8mm-evk.c create mode 100644 hw/display/imx6ul_lcdif.c create mode 100644 include/hw/arm/fsl-imx8mm.h delete mode 100644 include/hw/arm/primecell.h create mode 100644 include/hw/display/imx6ul_lcdif.h create mode 100644 include/hw/misc/arm_sysctl.h create mode 100755 tests/functional/aarch64/test_imx8mm_evk.py create mode 100755 tests/functional/aarch64/test_virt_aarch64_off.py From: Alex Bennée <alex.bennee@linaro.org> This is just a documentation tweak as we already support both. FEAT_AA32 implies FEAT_AA32EL0. FEAT_AA64 implies FEAT_AA64EL[0123]. This is however useful if you are using emulation.rst as a source of truth of what QEMU emulates and when cross checking with Features.json from Arm. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20260421093506.616307-1-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 2 ++ 1 file changed, 2 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ QEMU's TCG emulation includes support for the Armv5, Armv6, Armv7, Armv8 and Armv9 versions of the A-profile architecture. It also has support for the following architecture extensions: +- FEAT_AA32 (PE Support for AArch32) - FEAT_AA32BF16 (AArch32 BFloat16 instructions) - FEAT_AA32EL0 (Support for AArch32 at EL0) - FEAT_AA32EL1 (Support for AArch32 at EL1) @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_AA32EL3 (Support for AArch32 at EL3) - FEAT_AA32HPD (AArch32 hierarchical permission disables) - FEAT_AA32I8MM (AArch32 Int8 matrix multiplication instructions) +- FEAT_AA64 (PE uses AArch64 after last reboot) - FEAT_AA64EL0 (Support for AArch64 at EL0) - FEAT_AA64EL1 (Support for AArch64 at EL1) - FEAT_AA64EL2 (Support for AArch64 at EL2) -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> Implemented CPUs, RAM, UARTs and Interrupt Controller Other peripherals are represented as TYPE_UNIMPLEMENTED_DEVICE Complete memory map of the SoC is provided. Set default RAM size to 2GB and default CPU count to 4 to match the real i.MX8MM EVK hardware configuration. Documentation is shared with imx8mp-evk to avoid duplication. Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> [PMM: fixed over-long lines in doc] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 11 +- docs/system/arm/{imx8mp-evk.rst => imx8m.rst} | 49 ++- docs/system/target-arm.rst | 2 +- hw/arm/Kconfig | 12 + hw/arm/fsl-imx8mm.c | 377 ++++++++++++++++++ hw/arm/imx8mm-evk.c | 112 ++++++ hw/arm/meson.build | 2 + include/hw/arm/fsl-imx8mm.h | 158 ++++++++ 8 files changed, 709 insertions(+), 14 deletions(-) rename docs/system/arm/{imx8mp-evk.rst => imx8m.rst} (58%) create mode 100644 hw/arm/fsl-imx8mm.c create mode 100644 hw/arm/imx8mm-evk.c create mode 100644 include/hw/arm/fsl-imx8mm.h diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/pci-host/designware.c F: include/hw/pci-host/designware.h F: docs/system/arm/mcimx7d-sabre.rst +MCIMX8MM-EVK / iMX8MM +M: Gaurav Sharma <gaurav.sharma_7@nxp.com> +L: qemu-arm@nongnu.org +S: Maintained +F: hw/arm/fsl-imx8mm.c +F: hw/arm/imx8mm-evk.c +F: include/hw/arm/fsl-imx8mm.h +F: docs/system/arm/imx8m.rst + MCIMX8MP-EVK / i.MX8MP M: Bernhard Beschow <shentey@gmail.com> L: qemu-arm@nongnu.org @@ -XXX,XX +XXX,XX @@ F: hw/rtc/rs5c372.c F: include/hw/arm/fsl-imx8mp.h F: include/hw/misc/imx8mp_*.h F: include/hw/pci-host/fsl_imx8m_phy.h -F: docs/system/arm/imx8mp-evk.rst +F: docs/system/arm/imx8m.rst F: tests/functional/aarch64/test_imx8mp_evk.py F: tests/qtest/rs5c372-test.c diff --git a/docs/system/arm/imx8mp-evk.rst b/docs/system/arm/imx8m.rst similarity index 58% rename from docs/system/arm/imx8mp-evk.rst rename to docs/system/arm/imx8m.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/imx8mp-evk.rst +++ b/docs/system/arm/imx8m.rst @@ -XXX,XX +XXX,XX @@ -NXP i.MX 8M Plus Evaluation Kit (``imx8mp-evk``) -================================================ +NXP i.MX 8M Plus and i.MX 8M Mini Evaluation Kits (``imx8mp-evk``, ``imx8mm-evk``) +================================================================================== -The ``imx8mp-evk`` machine models the i.MX 8M Plus Evaluation Kit, based on an -i.MX 8M Plus SoC. +The ``imx8mp-evk`` and ``imx8mm-evk`` machine models the i.MX 8M Plus +and i.MX 8M Mini Evaluation Kits, based on i.MX 8M Plus and i.MX8M +Mini SoCs. Supported devices ----------------- -The ``imx8mp-evk`` machine implements the following devices: +The ``imx8mp-evk`` and ``imx8mm-evk`` machines implement the +following devices: * Up to 4 Cortex-A53 cores * Generic Interrupt Controller (GICv3) @@ -XXX,XX +XXX,XX @@ The ``imx8mp-evk`` machine implements the following devices: Boot options ------------ -The ``imx8mp-evk`` machine can start a Linux kernel directly using the standard -``-kernel`` functionality. +The ``imx8mp-evk`` and ``imx8mm-evk`` machines can start a Linux +kernel directly using the standard ``-kernel`` functionality. Direct Linux Kernel Boot '''''''''''''''''''''''' @@ -XXX,XX +XXX,XX @@ is to generate an image with Buildroot. Version 2024.11.1 is tested at the time of writing and involves two steps. First run the following commands in the toplevel directory of the Buildroot source tree: +For i.MX 8M Plus EVK: + .. code-block:: bash $ make freescale_imx8mpevk_defconfig $ make +For i.MX 8M Mini EVK: + +.. code-block:: bash + + $ make freescale_imx8mmevk_defconfig + $ make + Once finished successfully there is an ``output/image`` subfolder. Navigate into it and resize the SD card image to a power of two: @@ -XXX,XX +XXX,XX @@ it and resize the SD card image to a power of two: Now that everything is prepared the machine can be started as follows: +For i.MX 8M Plus EVK: + .. code-block:: bash $ qemu-system-aarch64 -M imx8mp-evk \ @@ -XXX,XX +XXX,XX @@ Now that everything is prepared the machine can be started as follows: -append "root=/dev/mmcblk2p2" \ -drive file=sdcard.img,if=sd,bus=2,format=raw,id=mmcblk2 +For i.MX 8M Mini EVK: + +.. code-block:: bash + + $ qemu-system-aarch64 -M imx8mm-evk -smp 4 -m 2G \ + -display none -serial null -serial stdio \ + -kernel Image \ + -dtb imx8mm-evk.dtb \ + -append "root=/dev/mmcblk2p2" \ + -drive file=sdcard.img,if=sd,bus=2,format=raw,id=mmcblk2 KVM Acceleration ---------------- @@ -XXX,XX +XXX,XX @@ To enable hardware-assisted acceleration via KVM, append ``-accel kvm`` to the command line. While this speeds up performance significantly, be aware of the following limitations: -* The ``imx8mp-evk`` machine is not included under the "virtualization use case" - of :doc:`QEMU's security policy </system/security>`. This means that you - should not trust that it can contain malicious guests, whether it is run - using TCG or KVM. If you don't trust your guests and you're relying on QEMU to - be the security boundary, you want to choose another machine such as ``virt``. +* The ``imx8mp-evk`` and ``imx8mm-evk`` machines are not included + under the "virtualization use case" of :doc:`QEMU's security + policy </system/security>`. This means that you should not trust that + it can contain malicious guests, whether it is run using TCG or KVM. + If you don't trust your guests and you're relying on QEMU to be the + security boundary, you want to choose another machine such as + ``virt``. * Rather than Cortex-A53 CPUs, the same CPU type as the host's will be used. This is a limitation of KVM and may not work with guests with a tight dependency on Cortex-A53. diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -XXX,XX +XXX,XX @@ Board-specific documentation arm/imx25-pdk arm/mcimx6ul-evk arm/mcimx7d-sabre - arm/imx8mp-evk + arm/imx8m arm/orangepi arm/raspi arm/collie 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 FSL_IMX8MP_EVK depends on TCG select FSL_IMX8MP +config FSL_IMX8MM + bool + select ARM_GIC + select IMX + +config FSL_IMX8MM_EVK + bool + default y + depends on AARCH64 + depends on TCG + select FSL_IMX8MM + config ARM_SMMUV3_ACCEL bool depends on ARM_SMMUV3 diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ +/* + * i.MX 8MM SoC Implementation + * + * Based on hw/arm/fsl-imx6.c + * + * Copyright (c) 2025, NXP Semiconductors + * Author: Gaurav Sharma <gaurav.sharma_7@nxp.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + * iMX8MM Reference Manual - https://www.nxp.com/products/i.MX8MMINI -> Documentation + */ + +#include "qemu/osdep.h" +#include "system/address-spaces.h" +#include "hw/arm/bsa.h" +#include "hw/arm/fsl-imx8mm.h" +#include "hw/misc/unimp.h" +#include "hw/core/boards.h" +#include "system/kvm.h" +#include "system/system.h" +#include "target/arm/cpu.h" +#include "target/arm/cpu-qom.h" +#include "target/arm/kvm_arm.h" +#include "qapi/error.h" +#include "qobject/qlist.h" + +static const struct { + hwaddr addr; + size_t size; + const char *name; +} fsl_imx8mm_memmap[] = { + [FSL_IMX8MM_RAM] = { FSL_IMX8MM_RAM_START, FSL_IMX8MM_RAM_SIZE_MAX, "ram" }, + [FSL_IMX8MM_DDR_PHY_BROADCAST] = { 0x3dc00000, 4 * MiB, "ddr_phy_broadcast" }, + [FSL_IMX8MM_DDR_PERF_MON] = { 0x3d800000, 4 * MiB, "ddr_perf_mon" }, + [FSL_IMX8MM_DDR_CTL] = { 0x3d400000, 4 * MiB, "ddr_ctl" }, + [FSL_IMX8MM_DDR_PHY] = { 0x3c000000, 16 * MiB, "ddr_phy" }, + [FSL_IMX8MM_GIC_DIST] = { 0x38800000, 512 * KiB, "gic_dist" }, + [FSL_IMX8MM_GIC_REDIST] = { 0x38880000, 512 * KiB, "gic_redist" }, + [FSL_IMX8MM_VPU] = { 0x38340000, 2 * MiB, "vpu" }, + [FSL_IMX8MM_VPU_BLK_CTRL] = { 0x38330000, 2 * MiB, "vpu_blk_ctrl" }, + [FSL_IMX8MM_VPU_G2_DECODER] = { 0x38310000, 1 * MiB, "vpu_g2_decoder" }, + [FSL_IMX8MM_VPU_G1_DECODER] = { 0x38300000, 1 * MiB, "vpu_g1_decoder" }, + [FSL_IMX8MM_USB2_OTG] = { 0x32e50200, 0x200, "usb2_otg" }, + [FSL_IMX8MM_USB2] = { 0x32e50000, 0x200, "usb2" }, + [FSL_IMX8MM_USB1_OTG] = { 0x32e40200, 0x200, "usb1_otg" }, + [FSL_IMX8MM_USB1] = { 0x32e40000, 0x200, "usb1" }, + [FSL_IMX8MM_GPU2D] = { 0x38000000, 64 * KiB, "gpu2d" }, + [FSL_IMX8MM_QSPI1_RX_BUFFER] = { 0x34000000, 32 * MiB, "qspi1_rx_buffer" }, + [FSL_IMX8MM_PCIE1] = { 0x33800000, 4 * MiB, "pcie1" }, + [FSL_IMX8MM_QSPI1_TX_BUFFER] = { 0x33008000, 32 * KiB, "qspi1_tx_buffer" }, + [FSL_IMX8MM_APBH_DMA] = { 0x33000000, 32 * KiB, "apbh_dma" }, + + /* AIPS-4 Begin */ + [FSL_IMX8MM_TZASC] = { 0x32f80000, 64 * KiB, "tzasc" }, + [FSL_IMX8MM_PCIE_PHY1] = { 0x32f00000, 64 * KiB, "pcie_phy1" }, + [FSL_IMX8MM_MEDIA_BLK_CTL] = { 0x32e28000, 256, "media_blk_ctl" }, + [FSL_IMX8MM_LCDIF] = { 0x32e00000, 64 * KiB, "lcdif" }, + [FSL_IMX8MM_MIPI_DSI] = { 0x32e10000, 64 * KiB, "mipi_dsi" }, + [FSL_IMX8MM_MIPI_CSI] = { 0x32e30000, 64 * KiB, "mipi_csi" }, + [FSL_IMX8MM_AIPS4_CONFIGURATION] = { 0x32df0000, 64 * KiB, "aips4_configuration" }, + /* AIPS-4 End */ + + [FSL_IMX8MM_INTERCONNECT] = { 0x32700000, 1 * MiB, "interconnect" }, + + /* AIPS-3 Begin */ + [FSL_IMX8MM_ENET1] = { 0x30be0000, 64 * KiB, "enet1" }, + [FSL_IMX8MM_SDMA1] = { 0x30bd0000, 64 * KiB, "sdma1" }, + [FSL_IMX8MM_QSPI] = { 0x30bb0000, 64 * KiB, "qspi" }, + [FSL_IMX8MM_USDHC3] = { 0x30b60000, 64 * KiB, "usdhc3" }, + [FSL_IMX8MM_USDHC2] = { 0x30b50000, 64 * KiB, "usdhc2" }, + [FSL_IMX8MM_USDHC1] = { 0x30b40000, 64 * KiB, "usdhc1" }, + [FSL_IMX8MM_SEMAPHORE_HS] = { 0x30ac0000, 64 * KiB, "semaphore_hs" }, + [FSL_IMX8MM_MU_B] = { 0x30ab0000, 64 * KiB, "mu_b" }, + [FSL_IMX8MM_MU_A] = { 0x30aa0000, 64 * KiB, "mu_a" }, + [FSL_IMX8MM_UART4] = { 0x30a60000, 64 * KiB, "uart4" }, + [FSL_IMX8MM_I2C4] = { 0x30a50000, 64 * KiB, "i2c4" }, + [FSL_IMX8MM_I2C3] = { 0x30a40000, 64 * KiB, "i2c3" }, + [FSL_IMX8MM_I2C2] = { 0x30a30000, 64 * KiB, "i2c2" }, + [FSL_IMX8MM_I2C1] = { 0x30a20000, 64 * KiB, "i2c1" }, + [FSL_IMX8MM_AIPS3_CONFIGURATION] = { 0x309f0000, 64 * KiB, "aips3_configuration" }, + [FSL_IMX8MM_CAAM] = { 0x30900000, 256 * KiB, "caam" }, + [FSL_IMX8MM_SPBA1] = { 0x308f0000, 64 * KiB, "spba1" }, + [FSL_IMX8MM_UART2] = { 0x30890000, 64 * KiB, "uart2" }, + [FSL_IMX8MM_UART3] = { 0x30880000, 64 * KiB, "uart3" }, + [FSL_IMX8MM_UART1] = { 0x30860000, 64 * KiB, "uart1" }, + [FSL_IMX8MM_ECSPI3] = { 0x30840000, 64 * KiB, "ecspi3" }, + [FSL_IMX8MM_ECSPI2] = { 0x30830000, 64 * KiB, "ecspi2" }, + [FSL_IMX8MM_ECSPI1] = { 0x30820000, 64 * KiB, "ecspi1" }, + /* AIPS-3 End */ + + /* AIPS-2 Begin */ + [FSL_IMX8MM_QOSC] = { 0x307f0000, 64 * KiB, "qosc" }, + [FSL_IMX8MM_PERFMON2] = { 0x307d0000, 64 * KiB, "perfmon2" }, + [FSL_IMX8MM_PERFMON1] = { 0x307c0000, 64 * KiB, "perfmon1" }, + [FSL_IMX8MM_GPT4] = { 0x30700000, 64 * KiB, "gpt4" }, + [FSL_IMX8MM_GPT5] = { 0x306f0000, 64 * KiB, "gpt5" }, + [FSL_IMX8MM_GPT6] = { 0x306e0000, 64 * KiB, "gpt6" }, + [FSL_IMX8MM_SYSCNT_CTRL] = { 0x306c0000, 64 * KiB, "syscnt_ctrl" }, + [FSL_IMX8MM_SYSCNT_CMP] = { 0x306b0000, 64 * KiB, "syscnt_cmp" }, + [FSL_IMX8MM_SYSCNT_RD] = { 0x306a0000, 64 * KiB, "syscnt_rd" }, + [FSL_IMX8MM_PWM4] = { 0x30690000, 64 * KiB, "pwm4" }, + [FSL_IMX8MM_PWM3] = { 0x30680000, 64 * KiB, "pwm3" }, + [FSL_IMX8MM_PWM2] = { 0x30670000, 64 * KiB, "pwm2" }, + [FSL_IMX8MM_PWM1] = { 0x30660000, 64 * KiB, "pwm1" }, + [FSL_IMX8MM_AIPS2_CONFIGURATION] = { 0x305f0000, 64 * KiB, "aips2_configuration" }, + /* AIPS-2 End */ + + /* AIPS-1 Begin */ + [FSL_IMX8MM_CSU] = { 0x303e0000, 64 * KiB, "csu" }, + [FSL_IMX8MM_RDC] = { 0x303d0000, 64 * KiB, "rdc" }, + [FSL_IMX8MM_SEMAPHORE2] = { 0x303c0000, 64 * KiB, "semaphore2" }, + [FSL_IMX8MM_SEMAPHORE1] = { 0x303b0000, 64 * KiB, "semaphore1" }, + [FSL_IMX8MM_GPC] = { 0x303a0000, 64 * KiB, "gpc" }, + [FSL_IMX8MM_SRC] = { 0x30390000, 64 * KiB, "src" }, + [FSL_IMX8MM_CCM] = { 0x30380000, 64 * KiB, "ccm" }, + [FSL_IMX8MM_SNVS_HP] = { 0x30370000, 64 * KiB, "snvs_hp" }, + [FSL_IMX8MM_ANA_PLL] = { 0x30360000, 64 * KiB, "ana_pll" }, + [FSL_IMX8MM_OCOTP_CTRL] = { 0x30350000, 64 * KiB, "ocotp_ctrl" }, + [FSL_IMX8MM_IOMUXC_GPR] = { 0x30340000, 64 * KiB, "iomuxc_gpr" }, + [FSL_IMX8MM_IOMUXC] = { 0x30330000, 64 * KiB, "iomuxc" }, + [FSL_IMX8MM_GPT3] = { 0x302f0000, 64 * KiB, "gpt3" }, + [FSL_IMX8MM_GPT2] = { 0x302e0000, 64 * KiB, "gpt2" }, + [FSL_IMX8MM_GPT1] = { 0x302d0000, 64 * KiB, "gpt1" }, + [FSL_IMX8MM_SDMA2] = { 0x302c0000, 64 * KiB, "sdma2" }, + [FSL_IMX8MM_SDMA3] = { 0x302b0000, 64 * KiB, "sdma3" }, + [FSL_IMX8MM_WDOG3] = { 0x302a0000, 64 * KiB, "wdog3" }, + [FSL_IMX8MM_WDOG2] = { 0x30290000, 64 * KiB, "wdog2" }, + [FSL_IMX8MM_WDOG1] = { 0x30280000, 64 * KiB, "wdog1" }, + [FSL_IMX8MM_ANA_OSC] = { 0x30270000, 64 * KiB, "ana_osc" }, + [FSL_IMX8MM_ANA_TSENSOR] = { 0x30260000, 64 * KiB, "ana_tsensor" }, + [FSL_IMX8MM_GPIO5] = { 0x30240000, 64 * KiB, "gpio5" }, + [FSL_IMX8MM_GPIO4] = { 0x30230000, 64 * KiB, "gpio4" }, + [FSL_IMX8MM_GPIO3] = { 0x30220000, 64 * KiB, "gpio3" }, + [FSL_IMX8MM_GPIO2] = { 0x30210000, 64 * KiB, "gpio2" }, + [FSL_IMX8MM_GPIO1] = { 0x30200000, 64 * KiB, "gpio1" }, + [FSL_IMX8MM_AIPS1_CONFIGURATION] = { 0x301f0000, 64 * KiB, "aips1_configuration" }, + [FSL_IMX8MM_SAI6] = { 0x30060000, 64 * KiB, "sai6" }, + [FSL_IMX8MM_SAI5] = { 0x30050000, 64 * KiB, "sai5" }, + [FSL_IMX8MM_SAI3] = { 0x30030000, 64 * KiB, "sai3" }, + [FSL_IMX8MM_SAI2] = { 0x30020000, 64 * KiB, "sai2" }, + [FSL_IMX8MM_SAI1] = { 0x30010000, 64 * KiB, "sai1" }, + + /* AIPS-1 End */ + + [FSL_IMX8MM_A53_DAP] = { 0x28000000, 16 * MiB, "a53_dap" }, + [FSL_IMX8MM_PCIE1_MEM] = { 0x18000000, 128 * MiB, "pcie1_mem" }, + [FSL_IMX8MM_QSPI_MEM] = { 0x08000000, 256 * MiB, "qspi_mem" }, + [FSL_IMX8MM_OCRAM] = { 0x00900000, 256 * KiB, "ocram" }, + [FSL_IMX8MM_TCM_DTCM] = { 0x00800000, 128 * KiB, "tcm_dtcm" }, + [FSL_IMX8MM_TCM_ITCM] = { 0x007e0000, 128 * KiB, "tcm_itcm" }, + [FSL_IMX8MM_OCRAM_S] = { 0x00180000, 32 * KiB, "ocram_s" }, + [FSL_IMX8MM_CAAM_MEM] = { 0x00100000, 32 * KiB, "caam_mem" }, + [FSL_IMX8MM_BOOT_ROM_PROTECTED] = { 0x0003f000, 4 * KiB, "boot_rom_protected" }, + [FSL_IMX8MM_BOOT_ROM] = { 0x00000000, 252 * KiB, "boot_rom" }, +}; + +static void fsl_imx8mm_init(Object *obj) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + FslImx8mmState *s = FSL_IMX8MM(obj); + const char *cpu_type = ms->cpu_type ?: ARM_CPU_TYPE_NAME("cortex-a53"); + int i; + + for (i = 0; i < MIN(ms->smp.cpus, FSL_IMX8MM_NUM_CPUS); i++) { + g_autofree char *name = g_strdup_printf("cpu%d", i); + object_initialize_child(obj, name, &s->cpu[i], cpu_type); + } + + object_initialize_child(obj, "gic", &s->gic, gicv3_class_name()); + + for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) { + g_autofree char *name = g_strdup_printf("uart%d", i + 1); + object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL); + } + +} + +static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + FslImx8mmState *s = FSL_IMX8MM(dev); + DeviceState *gicdev = DEVICE(&s->gic); + int i; + + if (ms->smp.cpus > FSL_IMX8MM_NUM_CPUS) { + error_setg(errp, "%s: Only %d CPUs are supported (%d requested)", + TYPE_FSL_IMX8MM, FSL_IMX8MM_NUM_CPUS, ms->smp.cpus); + return; + } + + /* CPUs */ + for (i = 0; i < ms->smp.cpus; i++) { + /* On uniprocessor, the CBAR is set to 0 */ + if (ms->smp.cpus > 1 && + object_property_find(OBJECT(&s->cpu[i]), "reset-cbar")) { + object_property_set_int(OBJECT(&s->cpu[i]), "reset-cbar", + fsl_imx8mm_memmap[FSL_IMX8MM_GIC_DIST].addr, + &error_abort); + } + + /* + * CNTFID0 base frequency in Hz of system counter + */ + object_property_set_int(OBJECT(&s->cpu[i]), "cntfrq", 8000000, + &error_abort); + + if (object_property_find(OBJECT(&s->cpu[i]), "has_el2")) { + object_property_set_bool(OBJECT(&s->cpu[i]), "has_el2", + !kvm_enabled(), &error_abort); + } + + if (object_property_find(OBJECT(&s->cpu[i]), "has_el3")) { + object_property_set_bool(OBJECT(&s->cpu[i]), "has_el3", + !kvm_enabled(), &error_abort); + } + + if (i) { + /* + * Secondary CPUs start in powered-down state (and can be + * powered up via the SRC system reset controller) + */ + object_property_set_bool(OBJECT(&s->cpu[i]), "start-powered-off", + true, &error_abort); + } + + if (!qdev_realize(DEVICE(&s->cpu[i]), NULL, errp)) { + return; + } + } + + /* GIC */ + { + SysBusDevice *gicsbd = SYS_BUS_DEVICE(&s->gic); + QList *redist_region_count; + bool pmu = object_property_get_bool(OBJECT(first_cpu), "pmu", NULL); + + qdev_prop_set_uint32(gicdev, "num-cpu", ms->smp.cpus); + qdev_prop_set_uint32(gicdev, "num-irq", + FSL_IMX8MM_NUM_IRQS + GIC_INTERNAL); + redist_region_count = qlist_new(); + qlist_append_int(redist_region_count, ms->smp.cpus); + qdev_prop_set_array(gicdev, "redist-region-count", redist_region_count); + object_property_set_link(OBJECT(&s->gic), "sysmem", + OBJECT(get_system_memory()), &error_fatal); + if (!sysbus_realize(gicsbd, errp)) { + return; + } + sysbus_mmio_map(gicsbd, 0, fsl_imx8mm_memmap[FSL_IMX8MM_GIC_DIST].addr); + sysbus_mmio_map(gicsbd, 1, fsl_imx8mm_memmap[FSL_IMX8MM_GIC_REDIST].addr); + + /* + * Wire the outputs from each CPU's generic timer and the GICv3 + * maintenance interrupt signal to the appropriate GIC PPI inputs, and + * the GIC's IRQ/FIQ interrupt outputs to the CPU's inputs. + */ + for (i = 0; i < ms->smp.cpus; i++) { + DeviceState *cpudev = DEVICE(&s->cpu[i]); + int intidbase = FSL_IMX8MM_NUM_IRQS + i * GIC_INTERNAL; + qemu_irq irq; + + /* + * Mapping from the output timer irq lines from the CPU to the + * GIC PPI inputs. + */ + static const int timer_irqs[] = { + [GTIMER_PHYS] = ARCH_TIMER_NS_EL1_IRQ, + [GTIMER_VIRT] = ARCH_TIMER_VIRT_IRQ, + [GTIMER_HYP] = ARCH_TIMER_NS_EL2_IRQ, + [GTIMER_SEC] = ARCH_TIMER_S_EL1_IRQ, + }; + + for (int j = 0; j < ARRAY_SIZE(timer_irqs); j++) { + irq = qdev_get_gpio_in(gicdev, intidbase + timer_irqs[j]); + qdev_connect_gpio_out(cpudev, j, irq); + } + + irq = qdev_get_gpio_in(gicdev, intidbase + ARCH_GIC_MAINT_IRQ); + qdev_connect_gpio_out_named(cpudev, "gicv3-maintenance-interrupt", + 0, irq); + + irq = qdev_get_gpio_in(gicdev, intidbase + VIRTUAL_PMU_IRQ); + qdev_connect_gpio_out_named(cpudev, "pmu-interrupt", 0, irq); + + sysbus_connect_irq(gicsbd, i, + qdev_get_gpio_in(cpudev, ARM_CPU_IRQ)); + sysbus_connect_irq(gicsbd, i + ms->smp.cpus, + qdev_get_gpio_in(cpudev, ARM_CPU_FIQ)); + sysbus_connect_irq(gicsbd, i + 2 * ms->smp.cpus, + qdev_get_gpio_in(cpudev, ARM_CPU_VIRQ)); + sysbus_connect_irq(gicsbd, i + 3 * ms->smp.cpus, + qdev_get_gpio_in(cpudev, ARM_CPU_VFIQ)); + + if (kvm_enabled()) { + if (pmu) { + assert(arm_feature(&s->cpu[i].env, ARM_FEATURE_PMU)); + if (kvm_irqchip_in_kernel()) { + kvm_arm_pmu_set_irq(&s->cpu[i], VIRTUAL_PMU_IRQ); + } + kvm_arm_pmu_init(&s->cpu[i]); + } + } + } + } + + /* UARTs */ + for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } serial_table[FSL_IMX8MM_NUM_UARTS] = { + { fsl_imx8mm_memmap[FSL_IMX8MM_UART1].addr, FSL_IMX8MM_UART1_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_UART2].addr, FSL_IMX8MM_UART2_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_UART3].addr, FSL_IMX8MM_UART3_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_UART4].addr, FSL_IMX8MM_UART4_IRQ }, + }; + + qdev_prop_set_chr(DEVICE(&s->uart[i]), "chardev", serial_hd(i)); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->uart[i]), errp)) { + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->uart[i]), 0, serial_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->uart[i]), 0, + qdev_get_gpio_in(gicdev, serial_table[i].irq)); + } + + /* On-Chip RAM */ + if (!memory_region_init_ram(&s->ocram, OBJECT(dev), "imx8mm.ocram", + fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].size, + errp)) { + return; + } + memory_region_add_subregion(get_system_memory(), + fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr, + &s->ocram); + + /* Unimplemented devices */ + for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) { + switch (i) { + case FSL_IMX8MM_GIC_DIST: + case FSL_IMX8MM_GIC_REDIST: + case FSL_IMX8MM_RAM: + case FSL_IMX8MM_OCRAM: + case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4: + /* device implemented and treated above */ + break; + + default: + create_unimplemented_device(fsl_imx8mm_memmap[i].name, + fsl_imx8mm_memmap[i].addr, + fsl_imx8mm_memmap[i].size); + break; + } + } +} + +static void fsl_imx8mm_class_init(ObjectClass *oc, const void *data) +{ + DeviceClass *dc = DEVICE_CLASS(oc); + + dc->realize = fsl_imx8mm_realize; + + dc->desc = "i.MX 8MM SoC"; +} + +static const TypeInfo fsl_imx8mm_types[] = { + { + .name = TYPE_FSL_IMX8MM, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(FslImx8mmState), + .instance_init = fsl_imx8mm_init, + .class_init = fsl_imx8mm_class_init, + }, +}; + +DEFINE_TYPES(fsl_imx8mm_types) diff --git a/hw/arm/imx8mm-evk.c b/hw/arm/imx8mm-evk.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/imx8mm-evk.c @@ -XXX,XX +XXX,XX @@ +/* + * NXP i.MX 8MM Evaluation Kit System Emulation + * + * Copyright (c) 2025, NXP Semiconductors + * Author: Gaurav Sharma <gaurav.sharma_7@nxp.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "system/address-spaces.h" +#include "hw/arm/boot.h" +#include "hw/arm/fsl-imx8mm.h" +#include "hw/arm/machines-qom.h" +#include "hw/core/boards.h" +#include "hw/core/qdev-properties.h" +#include "system/kvm.h" +#include "system/qtest.h" +#include "qemu/error-report.h" +#include "qapi/error.h" +#include <libfdt.h> + +static void imx8mm_evk_modify_dtb(const struct arm_boot_info *info, void *fdt) +{ + int i, offset; + + /* Temporarily disable following nodes until they are implemented */ + const char *nodes_to_remove[] = { + "nxp,imx8mm-fspi", + "fsl,imx8mm-mipi-csi", + "fsl,imx8mm-mipi-dsim" + }; + + for (i = 0; i < ARRAY_SIZE(nodes_to_remove); i++) { + const char *dev_str = nodes_to_remove[i]; + + offset = fdt_node_offset_by_compatible(fdt, -1, dev_str); + while (offset >= 0) { + fdt_nop_node(fdt, offset); + offset = fdt_node_offset_by_compatible(fdt, offset, dev_str); + } + } + + /* Remove cpu-idle-states property from CPU nodes */ + offset = fdt_node_offset_by_compatible(fdt, -1, "arm,cortex-a53"); + while (offset >= 0) { + fdt_nop_property(fdt, offset, "cpu-idle-states"); + offset = fdt_node_offset_by_compatible(fdt, offset, "arm,cortex-a53"); + } + + if (kvm_enabled()) { + /* Use system counter frequency from host CPU to fix time in guest */ + offset = fdt_node_offset_by_compatible(fdt, -1, "arm,armv8-timer"); + while (offset >= 0) { + fdt_nop_property(fdt, offset, "clock-frequency"); + offset = fdt_node_offset_by_compatible(fdt, offset, "arm,armv8-timer"); + } + } +} + +static void imx8mm_evk_init(MachineState *machine) +{ + static struct arm_boot_info boot_info; + FslImx8mmState *s; + + if (machine->ram_size > FSL_IMX8MM_RAM_SIZE_MAX) { + error_report("RAM size " RAM_ADDR_FMT " above max supported (%08" PRIx64 ")", + machine->ram_size, FSL_IMX8MM_RAM_SIZE_MAX); + exit(1); + } + + boot_info = (struct arm_boot_info) { + .loader_start = FSL_IMX8MM_RAM_START, + .board_id = -1, + .ram_size = machine->ram_size, + .psci_conduit = QEMU_PSCI_CONDUIT_SMC, + .modify_dtb = imx8mm_evk_modify_dtb, + }; + + s = FSL_IMX8MM(object_new_with_props(TYPE_FSL_IMX8MM, OBJECT(machine), + "soc", &error_fatal, NULL)); + sysbus_realize_and_unref(SYS_BUS_DEVICE(s), &error_fatal); + + memory_region_add_subregion(get_system_memory(), FSL_IMX8MM_RAM_START, + machine->ram); + + if (!qtest_enabled()) { + arm_load_kernel(&s->cpu[0], machine, &boot_info); + } +} + +static const char *imx8mm_evk_get_default_cpu_type(const MachineState *ms) +{ + if (kvm_enabled()) { + return ARM_CPU_TYPE_NAME("host"); + } + + return ARM_CPU_TYPE_NAME("cortex-a53"); +} + +static void imx8mm_evk_machine_init(MachineClass *mc) +{ + mc->desc = "NXP i.MX 8MM EVK Board"; + mc->init = imx8mm_evk_init; + mc->max_cpus = FSL_IMX8MM_NUM_CPUS; + mc->default_cpus = FSL_IMX8MM_NUM_CPUS; + mc->default_ram_size = 2 * GiB; + mc->default_ram_id = "imx8mm-evk.ram"; + mc->get_default_cpu_type = imx8mm_evk_get_default_cpu_type; +} + +DEFINE_MACHINE_AARCH64("imx8mm-evk", imx8mm_evk_machine_init) 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_common_ss.add(when: 'CONFIG_ARMSSE', if_true: files('armsse.c')) arm_common_ss.add(when: 'CONFIG_FSL_IMX7', if_true: files('fsl-imx7.c', 'mcimx7d-sabre.c')) arm_common_ss.add(when: 'CONFIG_FSL_IMX8MP', if_true: files('fsl-imx8mp.c')) arm_common_ss.add(when: 'CONFIG_FSL_IMX8MP_EVK', if_true: files('imx8mp-evk.c')) +arm_common_ss.add(when: 'CONFIG_FSL_IMX8MM', if_true: files('fsl-imx8mm.c')) +arm_common_ss.add(when: 'CONFIG_FSL_IMX8MM_EVK', if_true: files('imx8mm-evk.c')) arm_common_ss.add(when: 'CONFIG_ARM_SMMUV3', if_true: files('smmuv3.c')) arm_common_ss.add(when: 'CONFIG_ARM_SMMUV3_ACCEL', if_true: files('smmuv3-accel.c')) stub_ss.add(files('smmuv3-accel-stubs.c')) diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ +/* + * i.MX 8MM SoC Definitions + * + * Copyright (c) 2025, NXP Semiconductors + * Author: Gaurav Sharma <gaurav.sharma_7@nxp.com> + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef FSL_IMX8MM_H +#define FSL_IMX8MM_H + +#include "cpu.h" +#include "hw/char/imx_serial.h" +#include "hw/intc/arm_gicv3_common.h" +#include "qom/object.h" +#include "qemu/units.h" + +#define TYPE_FSL_IMX8MM "fsl-imx8mm" +OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM) + +#define FSL_IMX8MM_RAM_START 0x40000000 +#define FSL_IMX8MM_RAM_SIZE_MAX (4 * GiB) + +enum FslImx8mmConfiguration { + FSL_IMX8MM_NUM_CPUS = 4, + FSL_IMX8MM_NUM_IRQS = 128, + FSL_IMX8MM_NUM_UARTS = 4, +}; + +struct FslImx8mmState { + SysBusDevice parent_obj; + + ARMCPU cpu[FSL_IMX8MM_NUM_CPUS]; + GICv3State gic; + IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; + MemoryRegion ocram; +}; + +enum FslImx8mmMemoryRegions { + FSL_IMX8MM_A53_DAP, + FSL_IMX8MM_AIPS1_CONFIGURATION, + FSL_IMX8MM_AIPS2_CONFIGURATION, + FSL_IMX8MM_AIPS3_CONFIGURATION, + FSL_IMX8MM_AIPS4_CONFIGURATION, + FSL_IMX8MM_ANA_OSC, + FSL_IMX8MM_ANA_PLL, + FSL_IMX8MM_ANA_TSENSOR, + FSL_IMX8MM_APBH_DMA, + FSL_IMX8MM_BOOT_ROM, + FSL_IMX8MM_BOOT_ROM_PROTECTED, + FSL_IMX8MM_CAAM, + FSL_IMX8MM_CAAM_MEM, + FSL_IMX8MM_CCM, + FSL_IMX8MM_CSU, + FSL_IMX8MM_DDR_CTL, + FSL_IMX8MM_DDR_PERF_MON, + FSL_IMX8MM_DDR_PHY, + FSL_IMX8MM_DDR_PHY_BROADCAST, + FSL_IMX8MM_ECSPI1, + FSL_IMX8MM_ECSPI2, + FSL_IMX8MM_ECSPI3, + FSL_IMX8MM_ENET1, + FSL_IMX8MM_GIC_DIST, + FSL_IMX8MM_GIC_REDIST, + FSL_IMX8MM_GPC, + FSL_IMX8MM_GPIO1, + FSL_IMX8MM_GPIO2, + FSL_IMX8MM_GPIO3, + FSL_IMX8MM_GPIO4, + FSL_IMX8MM_GPIO5, + FSL_IMX8MM_GPT1, + FSL_IMX8MM_GPT2, + FSL_IMX8MM_GPT3, + FSL_IMX8MM_GPT4, + FSL_IMX8MM_GPT5, + FSL_IMX8MM_GPT6, + FSL_IMX8MM_GPU2D, + FSL_IMX8MM_I2C1, + FSL_IMX8MM_I2C2, + FSL_IMX8MM_I2C3, + FSL_IMX8MM_I2C4, + FSL_IMX8MM_INTERCONNECT, + FSL_IMX8MM_IOMUXC, + FSL_IMX8MM_IOMUXC_GPR, + FSL_IMX8MM_MEDIA_BLK_CTL, + FSL_IMX8MM_LCDIF, + FSL_IMX8MM_MIPI_CSI, + FSL_IMX8MM_MIPI_DSI, + FSL_IMX8MM_MU_A, + FSL_IMX8MM_MU_B, + FSL_IMX8MM_OCOTP_CTRL, + FSL_IMX8MM_OCRAM, + FSL_IMX8MM_OCRAM_S, + FSL_IMX8MM_PCIE1, + FSL_IMX8MM_PCIE1_MEM, + FSL_IMX8MM_PCIE_PHY1, + FSL_IMX8MM_PERFMON1, + FSL_IMX8MM_PERFMON2, + FSL_IMX8MM_PWM1, + FSL_IMX8MM_PWM2, + FSL_IMX8MM_PWM3, + FSL_IMX8MM_PWM4, + FSL_IMX8MM_QOSC, + FSL_IMX8MM_QSPI, + FSL_IMX8MM_QSPI1_RX_BUFFER, + FSL_IMX8MM_QSPI1_TX_BUFFER, + FSL_IMX8MM_QSPI_MEM, + FSL_IMX8MM_RAM, + FSL_IMX8MM_RDC, + FSL_IMX8MM_SAI1, + FSL_IMX8MM_SAI2, + FSL_IMX8MM_SAI3, + FSL_IMX8MM_SAI5, + FSL_IMX8MM_SAI6, + FSL_IMX8MM_SDMA1, + FSL_IMX8MM_SDMA2, + FSL_IMX8MM_SDMA3, + FSL_IMX8MM_SEMAPHORE1, + FSL_IMX8MM_SEMAPHORE2, + FSL_IMX8MM_SEMAPHORE_HS, + FSL_IMX8MM_SNVS_HP, + FSL_IMX8MM_SPBA1, + FSL_IMX8MM_SRC, + FSL_IMX8MM_SYSCNT_CMP, + FSL_IMX8MM_SYSCNT_CTRL, + FSL_IMX8MM_SYSCNT_RD, + FSL_IMX8MM_TCM_DTCM, + FSL_IMX8MM_TCM_ITCM, + FSL_IMX8MM_TZASC, + FSL_IMX8MM_UART1, + FSL_IMX8MM_UART2, + FSL_IMX8MM_UART3, + FSL_IMX8MM_UART4, + FSL_IMX8MM_USB1, + FSL_IMX8MM_USB2, + FSL_IMX8MM_USB1_OTG, + FSL_IMX8MM_USB2_OTG, + FSL_IMX8MM_USDHC1, + FSL_IMX8MM_USDHC2, + FSL_IMX8MM_USDHC3, + FSL_IMX8MM_VPU, + FSL_IMX8MM_VPU_BLK_CTRL, + FSL_IMX8MM_VPU_G1_DECODER, + FSL_IMX8MM_VPU_G2_DECODER, + FSL_IMX8MM_WDOG1, + FSL_IMX8MM_WDOG2, + FSL_IMX8MM_WDOG3, +}; + +enum FslImx8mmIrqs { + FSL_IMX8MM_UART1_IRQ = 26, + FSL_IMX8MM_UART2_IRQ = 27, + FSL_IMX8MM_UART3_IRQ = 28, + FSL_IMX8MM_UART4_IRQ = 29, +}; + +#endif /* FSL_IMX8MM_H */ -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> Add configurable properties for register reset values that differ between i.MX 8M variants (Plus, Mini, etc.). This allows the same device implementation to be shared across multiple SoCs. Properties added: - arm-pll-fdiv-ctl0-reset: ARM PLL divider control reset value Default value is set to match i.MX 8MP reset value (0x000FA031). This can be overridden in the variant like iMX8MM with its own reset value. Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/imx8mp_analog.c | 12 +++++++++++- include/hw/misc/imx8mp_analog.h | 3 +++ 2 files changed, 14 insertions(+), 1 deletion(-) diff --git a/hw/misc/imx8mp_analog.c b/hw/misc/imx8mp_analog.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/imx8mp_analog.c +++ b/hw/misc/imx8mp_analog.c @@ -XXX,XX +XXX,XX @@ #include "qemu/log.h" #include "hw/misc/imx8mp_analog.h" +#include "hw/core/qdev-properties.h" #include "migration/vmstate.h" #define ANALOG_PLL_LOCK BIT(31) @@ -XXX,XX +XXX,XX @@ static void imx8mp_analog_reset(DeviceState *dev) s->analog[ANALOG_VPU_PLL_LOCKD_CTRL] = 0x0010003f; s->analog[ANALOG_VPU_PLL_MNIT_CTRL] = 0x00280081; s->analog[ANALOG_ARM_PLL_GEN_CTRL] = 0x00000810; - s->analog[ANALOG_ARM_PLL_FDIV_CTL0] = 0x000fa031; + + /* Use property value instead of hardcoded */ + s->analog[ANALOG_ARM_PLL_FDIV_CTL0] = s->arm_pll_fdiv_ctl0_reset; + s->analog[ANALOG_ARM_PLL_LOCKD_CTRL] = 0x0010003f; s->analog[ANALOG_ARM_PLL_MNIT_CTRL] = 0x00280081; s->analog[ANALOG_SYS_PLL1_GEN_CTRL] = 0x0aaaa810; @@ -XXX,XX +XXX,XX @@ static const VMStateDescription imx8mp_analog_vmstate = { }, }; +static const Property imx8mp_analog_properties[] = { + DEFINE_PROP_UINT32("arm-pll-fdiv-ctl0-reset", IMX8MPAnalogState, + arm_pll_fdiv_ctl0_reset, 0x000fa031), /* imx8mp default */ +}; + static void imx8mp_analog_class_init(ObjectClass *klass, const void *data) { DeviceClass *dc = DEVICE_CLASS(klass); device_class_set_legacy_reset(dc, imx8mp_analog_reset); + device_class_set_props(dc, imx8mp_analog_properties); dc->vmsd = &imx8mp_analog_vmstate; dc->desc = "i.MX 8M Plus Analog Module"; } diff --git a/include/hw/misc/imx8mp_analog.h b/include/hw/misc/imx8mp_analog.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/imx8mp_analog.h +++ b/include/hw/misc/imx8mp_analog.h @@ -XXX,XX +XXX,XX @@ struct IMX8MPAnalogState { } mmio; uint32_t analog[ANALOG_MAX]; + + /* Property for variant-specific reset values */ + uint32_t arm_pll_fdiv_ctl0_reset; }; #endif /* IMX8MP_ANALOG_H */ -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> Add the Analog IP to i.MX8MM SoC. iMX8MM and i.MX8MP uses the same Analog IP so the analog ip source will be shared. The ARM PLL divider control register (arm-pll-fdiv-ctl0) has a different reset value on i.MX8MM (0x000fa030) compared to i.MX8MP (0x000fa031). So iMX8MM will be overriding this property with its own reset-value. Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx8mm.c | 12 ++++++++++++ include/hw/arm/fsl-imx8mm.h | 2 ++ 3 files changed, 15 insertions(+) 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 FSL_IMX8MP_EVK config FSL_IMX8MM bool select ARM_GIC + select FSL_IMX8MP_ANALOG select IMX config FSL_IMX8MM_EVK diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, "gic", &s->gic, gicv3_class_name()); + object_initialize_child(obj, "analog", &s->analog, TYPE_IMX8MP_ANALOG); + for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) { g_autofree char *name = g_strdup_printf("uart%d", i + 1); object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) } } + /* Analog */ + object_property_set_uint(OBJECT(&s->analog), "arm-pll-fdiv-ctl0-reset", + 0x000fa030, &error_abort); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->analog), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->analog), 0, + fsl_imx8mm_memmap[FSL_IMX8MM_ANA_PLL].addr); + /* UARTs */ for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) { static const struct { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) { switch (i) { + case FSL_IMX8MM_ANA_PLL: case FSL_IMX8MM_GIC_DIST: case FSL_IMX8MM_GIC_REDIST: case FSL_IMX8MM_RAM: diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "hw/char/imx_serial.h" #include "hw/intc/arm_gicv3_common.h" +#include "hw/misc/imx8mp_analog.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { ARMCPU cpu[FSL_IMX8MM_NUM_CPUS]; GICv3State gic; + IMX8MPAnalogState analog; IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; }; -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> Add the Clock Control Module (CCM) device to i.MX8MM SoC. The CCM implementation is shared with i.MX8MP as the register layout is identical between the two variants.Hence iMX8MM will be using the source of iMX8MP CCM. Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx8mm.c | 10 ++++++++++ include/hw/arm/fsl-imx8mm.h | 2 ++ 3 files changed, 13 insertions(+) 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 FSL_IMX8MM bool select ARM_GIC select FSL_IMX8MP_ANALOG + select FSL_IMX8MP_CCM select IMX config FSL_IMX8MM_EVK diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, "gic", &s->gic, gicv3_class_name()); + object_initialize_child(obj, "ccm", &s->ccm, TYPE_IMX8MP_CCM); + object_initialize_child(obj, "analog", &s->analog, TYPE_IMX8MP_ANALOG); for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) } } + /* CCM */ + if (!sysbus_realize(SYS_BUS_DEVICE(&s->ccm), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->ccm), 0, + fsl_imx8mm_memmap[FSL_IMX8MM_CCM].addr); + /* Analog */ object_property_set_uint(OBJECT(&s->analog), "arm-pll-fdiv-ctl0-reset", 0x000fa030, &error_abort); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) { switch (i) { case FSL_IMX8MM_ANA_PLL: + case FSL_IMX8MM_CCM: case FSL_IMX8MM_GIC_DIST: case FSL_IMX8MM_GIC_REDIST: case FSL_IMX8MM_RAM: diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/char/imx_serial.h" #include "hw/intc/arm_gicv3_common.h" #include "hw/misc/imx8mp_analog.h" +#include "hw/misc/imx8mp_ccm.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { ARMCPU cpu[FSL_IMX8MM_NUM_CPUS]; GICv3State gic; + IMX8MPCCMState ccm; IMX8MPAnalogState analog; IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> SNVS contains an RTC which allows Linux to deal correctly with time Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx8mm.c | 10 ++++++++++ include/hw/arm/fsl-imx8mm.h | 2 ++ 2 files changed, 12 insertions(+) diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, "analog", &s->analog, TYPE_IMX8MP_ANALOG); + object_initialize_child(obj, "snvs", &s->snvs, TYPE_IMX7_SNVS); + for (i = 0; i < FSL_IMX8MM_NUM_UARTS; i++) { g_autofree char *name = g_strdup_printf("uart%d", i + 1); object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr, &s->ocram); + /* SNVS */ + if (!sysbus_realize(SYS_BUS_DEVICE(&s->snvs), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->snvs), 0, + fsl_imx8mm_memmap[FSL_IMX8MM_SNVS_HP].addr); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) { switch (i) { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_GIC_REDIST: case FSL_IMX8MM_RAM: case FSL_IMX8MM_OCRAM: + case FSL_IMX8MM_SNVS_HP: case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4: /* device implemented and treated above */ break; diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "hw/char/imx_serial.h" #include "hw/intc/arm_gicv3_common.h" +#include "hw/misc/imx7_snvs.h" #include "hw/misc/imx8mp_analog.h" #include "hw/misc/imx8mp_ccm.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { GICv3State gic; IMX8MPCCMState ccm; IMX8MPAnalogState analog; + IMX7SNVSState snvs; IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; }; -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> It enables emulation of SD/MMC cards through a virtual SDHCI interface The emulated SDHCI controller allows guest OS to use emulated storage as a standard block device. This will allow running the images such as those generated by Buildroot. Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx8mm.c | 25 +++++++++++++++++++++++++ hw/arm/imx8mm-evk.c | 17 +++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 7 +++++++ 4 files changed, 50 insertions(+) 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 FSL_IMX8MM select FSL_IMX8MP_ANALOG select FSL_IMX8MP_CCM select IMX + select SDHCI config FSL_IMX8MM_EVK bool diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL); } + for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) { + g_autofree char *name = g_strdup_printf("usdhc%d", i + 1); + object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC); + } } static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr, &s->ocram); + /* USDHCs */ + for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } usdhc_table[FSL_IMX8MM_NUM_USDHCS] = { + { fsl_imx8mm_memmap[FSL_IMX8MM_USDHC1].addr, FSL_IMX8MM_USDHC1_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_USDHC2].addr, FSL_IMX8MM_USDHC2_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_USDHC3].addr, FSL_IMX8MM_USDHC3_IRQ }, + }; + + if (!sysbus_realize(SYS_BUS_DEVICE(&s->usdhc[i]), errp)) { + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->usdhc[i]), 0, usdhc_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->usdhc[i]), 0, + qdev_get_gpio_in(gicdev, usdhc_table[i].irq)); + } + /* SNVS */ if (!sysbus_realize(SYS_BUS_DEVICE(&s->snvs), errp)) { return; @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_OCRAM: case FSL_IMX8MM_SNVS_HP: case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4: + case FSL_IMX8MM_USDHC1 ... FSL_IMX8MM_USDHC3: /* device implemented and treated above */ break; diff --git a/hw/arm/imx8mm-evk.c b/hw/arm/imx8mm-evk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/imx8mm-evk.c +++ b/hw/arm/imx8mm-evk.c @@ -XXX,XX +XXX,XX @@ static void imx8mm_evk_init(MachineState *machine) memory_region_add_subregion(get_system_memory(), FSL_IMX8MM_RAM_START, machine->ram); + for (int i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) { + BusState *bus; + DeviceState *carddev; + BlockBackend *blk; + DriveInfo *di = drive_get(IF_SD, i, 0); + + if (!di) { + continue; + } + + blk = blk_by_legacy_dinfo(di); + bus = qdev_get_child_bus(DEVICE(&s->usdhc[i]), "sd-bus"); + carddev = qdev_new(TYPE_SD_CARD); + qdev_prop_set_drive_err(carddev, "drive", blk, &error_fatal); + qdev_realize_and_unref(carddev, bus, &error_fatal); + } + if (!qtest_enabled()) { arm_load_kernel(&s->cpu[0], machine, &boot_info); } diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/imx7_snvs.h" #include "hw/misc/imx8mp_analog.h" #include "hw/misc/imx8mp_ccm.h" +#include "hw/sd/sdhci.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration { FSL_IMX8MM_NUM_CPUS = 4, FSL_IMX8MM_NUM_IRQS = 128, FSL_IMX8MM_NUM_UARTS = 4, + FSL_IMX8MM_NUM_USDHCS = 3, }; struct FslImx8mmState { @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMX7SNVSState snvs; IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; + SDHCIState usdhc[FSL_IMX8MM_NUM_USDHCS]; }; enum FslImx8mmMemoryRegions { @@ -XXX,XX +XXX,XX @@ enum FslImx8mmMemoryRegions { }; enum FslImx8mmIrqs { + FSL_IMX8MM_USDHC1_IRQ = 22, + FSL_IMX8MM_USDHC2_IRQ = 23, + FSL_IMX8MM_USDHC3_IRQ = 24, + FSL_IMX8MM_UART1_IRQ = 26, FSL_IMX8MM_UART2_IRQ = 27, FSL_IMX8MM_UART3_IRQ = 28, -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> This enables support for Designware PCI Express Controller emulation It provides a controlled environment to debug the linux pci subsystem Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 3 +++ hw/arm/fsl-imx8mm.c | 30 ++++++++++++++++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 10 ++++++++++ 3 files changed, 43 insertions(+) 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 FSL_IMX8MP_EVK config FSL_IMX8MM bool + imply PCI_DEVICES select ARM_GIC select FSL_IMX8MP_ANALOG select FSL_IMX8MP_CCM select IMX select SDHCI + select PCI_EXPRESS_DESIGNWARE + select PCI_EXPRESS_FSL_IMX8M_PHY config FSL_IMX8MM_EVK bool diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) g_autofree char *name = g_strdup_printf("usdhc%d", i + 1); object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC); } + + object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST); + object_initialize_child(obj, "pcie_phy", &s->pcie_phy, + TYPE_FSL_IMX8M_PCIE_PHY); } static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->snvs), 0, fsl_imx8mm_memmap[FSL_IMX8MM_SNVS_HP].addr); + /* PCIe */ + if (!sysbus_realize(SYS_BUS_DEVICE(&s->pcie), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->pcie), 0, + fsl_imx8mm_memmap[FSL_IMX8MM_PCIE1].addr); + + sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 0, + qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTA_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 1, + qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTB_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 2, + qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTC_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 3, + qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_INTD_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 4, + qdev_get_gpio_in(gicdev, FSL_IMX8MM_PCI_MSI_IRQ)); + + if (!sysbus_realize(SYS_BUS_DEVICE(&s->pcie_phy), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->pcie_phy), 0, + fsl_imx8mm_memmap[FSL_IMX8MM_PCIE_PHY1].addr); + /* Unimplemented devices */ for (i = 0; i < ARRAY_SIZE(fsl_imx8mm_memmap); i++) { switch (i) { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_CCM: case FSL_IMX8MM_GIC_DIST: case FSL_IMX8MM_GIC_REDIST: + case FSL_IMX8MM_PCIE1: + case FSL_IMX8MM_PCIE_PHY1: case FSL_IMX8MM_RAM: case FSL_IMX8MM_OCRAM: case FSL_IMX8MM_SNVS_HP: diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/imx7_snvs.h" #include "hw/misc/imx8mp_analog.h" #include "hw/misc/imx8mp_ccm.h" +#include "hw/pci-host/designware.h" +#include "hw/pci-host/fsl_imx8m_phy.h" #include "hw/sd/sdhci.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; SDHCIState usdhc[FSL_IMX8MM_NUM_USDHCS]; + DesignwarePCIEHost pcie; + FslImx8mPciePhyState pcie_phy; }; enum FslImx8mmMemoryRegions { @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_UART2_IRQ = 27, FSL_IMX8MM_UART3_IRQ = 28, FSL_IMX8MM_UART4_IRQ = 29, + + FSL_IMX8MM_PCI_INTA_IRQ = 122, + FSL_IMX8MM_PCI_INTB_IRQ = 123, + FSL_IMX8MM_PCI_INTC_IRQ = 124, + FSL_IMX8MM_PCI_INTD_IRQ = 125, + FSL_IMX8MM_PCI_MSI_IRQ = 127, }; #endif /* FSL_IMX8MM_H */ -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> Enabled GPIO controller emulation Also updated the GPIO IRQ lines of iMX8MM Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx8mm.c | 54 +++++++++++++++++++++++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 14 ++++++++++ 2 files changed, 68 insertions(+) diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL); } + for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) { + g_autofree char *name = g_strdup_printf("gpio%d", i + 1); + object_initialize_child(obj, name, &s->gpio[i], TYPE_IMX_GPIO); + } + for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) { g_autofree char *name = g_strdup_printf("usdhc%d", i + 1); object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr, &s->ocram); + /* GPIOs */ + for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) { + static const struct { + hwaddr addr; + unsigned int irq_low; + unsigned int irq_high; + } gpio_table[FSL_IMX8MM_NUM_GPIOS] = { + { + fsl_imx8mm_memmap[FSL_IMX8MM_GPIO1].addr, + FSL_IMX8MM_GPIO1_LOW_IRQ, + FSL_IMX8MM_GPIO1_HIGH_IRQ + }, + { + fsl_imx8mm_memmap[FSL_IMX8MM_GPIO2].addr, + FSL_IMX8MM_GPIO2_LOW_IRQ, + FSL_IMX8MM_GPIO2_HIGH_IRQ + }, + { + fsl_imx8mm_memmap[FSL_IMX8MM_GPIO3].addr, + FSL_IMX8MM_GPIO3_LOW_IRQ, + FSL_IMX8MM_GPIO3_HIGH_IRQ + }, + { + fsl_imx8mm_memmap[FSL_IMX8MM_GPIO4].addr, + FSL_IMX8MM_GPIO4_LOW_IRQ, + FSL_IMX8MM_GPIO4_HIGH_IRQ + }, + { + fsl_imx8mm_memmap[FSL_IMX8MM_GPIO5].addr, + FSL_IMX8MM_GPIO5_LOW_IRQ, + FSL_IMX8MM_GPIO5_HIGH_IRQ + }, + }; + object_property_set_bool(OBJECT(&s->gpio[i]), "has-edge-sel", true, + &error_abort); + object_property_set_bool(OBJECT(&s->gpio[i]), "has-upper-pin-irq", + true, &error_abort); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->gpio[i]), errp)) { + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpio[i]), 0, gpio_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio[i]), 0, + qdev_get_gpio_in(gicdev, gpio_table[i].irq_low)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio[i]), 1, + qdev_get_gpio_in(gicdev, gpio_table[i].irq_high)); + } + /* USDHCs */ for (i = 0; i < FSL_IMX8MM_NUM_USDHCS; i++) { static const struct { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_CCM: case FSL_IMX8MM_GIC_DIST: case FSL_IMX8MM_GIC_REDIST: + case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5: case FSL_IMX8MM_PCIE1: case FSL_IMX8MM_PCIE_PHY1: case FSL_IMX8MM_RAM: diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "hw/char/imx_serial.h" +#include "hw/gpio/imx_gpio.h" #include "hw/intc/arm_gicv3_common.h" #include "hw/misc/imx7_snvs.h" #include "hw/misc/imx8mp_analog.h" @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM) enum FslImx8mmConfiguration { FSL_IMX8MM_NUM_CPUS = 4, + FSL_IMX8MM_NUM_GPIOS = 5, FSL_IMX8MM_NUM_IRQS = 128, FSL_IMX8MM_NUM_UARTS = 4, FSL_IMX8MM_NUM_USDHCS = 3, @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { ARMCPU cpu[FSL_IMX8MM_NUM_CPUS]; GICv3State gic; + IMXGPIOState gpio[FSL_IMX8MM_NUM_GPIOS]; IMX8MPCCMState ccm; IMX8MPAnalogState analog; IMX7SNVSState snvs; @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_UART3_IRQ = 28, FSL_IMX8MM_UART4_IRQ = 29, + FSL_IMX8MM_GPIO1_LOW_IRQ = 64, + FSL_IMX8MM_GPIO1_HIGH_IRQ = 65, + FSL_IMX8MM_GPIO2_LOW_IRQ = 66, + FSL_IMX8MM_GPIO2_HIGH_IRQ = 67, + FSL_IMX8MM_GPIO3_LOW_IRQ = 68, + FSL_IMX8MM_GPIO3_HIGH_IRQ = 69, + FSL_IMX8MM_GPIO4_LOW_IRQ = 70, + FSL_IMX8MM_GPIO4_HIGH_IRQ = 71, + FSL_IMX8MM_GPIO5_LOW_IRQ = 72, + FSL_IMX8MM_GPIO5_HIGH_IRQ = 73, + FSL_IMX8MM_PCI_INTA_IRQ = 122, FSL_IMX8MM_PCI_INTB_IRQ = 123, FSL_IMX8MM_PCI_INTC_IRQ = 124, -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> This can be used to test and debug I2C device drivers. Added I2C interrupts Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 2 ++ hw/arm/fsl-imx8mm.c | 27 +++++++++++++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 8 ++++++++ 3 files changed, 37 insertions(+) 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 FSL_IMX8MP_EVK config FSL_IMX8MM bool imply PCI_DEVICES + imply I2C_DEVICES select ARM_GIC select FSL_IMX8MP_ANALOG select FSL_IMX8MP_CCM select IMX + select IMX_I2C select SDHCI select PCI_EXPRESS_DESIGNWARE select PCI_EXPRESS_FSL_IMX8M_PHY diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL); } + for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) { + g_autofree char *name = g_strdup_printf("i2c%d", i + 1); + object_initialize_child(obj, name, &s->i2c[i], TYPE_IMX_I2C); + } + for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) { g_autofree char *name = g_strdup_printf("gpio%d", i + 1); object_initialize_child(obj, name, &s->gpio[i], TYPE_IMX_GPIO); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr, &s->ocram); + /* I2Cs */ + for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } i2c_table[FSL_IMX8MM_NUM_I2CS] = { + { fsl_imx8mm_memmap[FSL_IMX8MM_I2C1].addr, FSL_IMX8MM_I2C1_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_I2C2].addr, FSL_IMX8MM_I2C2_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_I2C3].addr, FSL_IMX8MM_I2C3_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_I2C4].addr, FSL_IMX8MM_I2C4_IRQ }, + }; + + if (!sysbus_realize(SYS_BUS_DEVICE(&s->i2c[i]), errp)) { + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c[i]), 0, i2c_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c[i]), 0, + qdev_get_gpio_in(gicdev, i2c_table[i].irq)); + } + /* GPIOs */ for (i = 0; i < FSL_IMX8MM_NUM_GPIOS; i++) { static const struct { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_GIC_DIST: case FSL_IMX8MM_GIC_REDIST: case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5: + case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4: case FSL_IMX8MM_PCIE1: case FSL_IMX8MM_PCIE_PHY1: case FSL_IMX8MM_RAM: diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "cpu.h" #include "hw/char/imx_serial.h" #include "hw/gpio/imx_gpio.h" +#include "hw/i2c/imx_i2c.h" #include "hw/intc/arm_gicv3_common.h" #include "hw/misc/imx7_snvs.h" #include "hw/misc/imx8mp_analog.h" @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM) enum FslImx8mmConfiguration { FSL_IMX8MM_NUM_CPUS = 4, FSL_IMX8MM_NUM_GPIOS = 5, + FSL_IMX8MM_NUM_I2CS = 4, FSL_IMX8MM_NUM_IRQS = 128, FSL_IMX8MM_NUM_UARTS = 4, FSL_IMX8MM_NUM_USDHCS = 3, @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMX8MPCCMState ccm; IMX8MPAnalogState analog; IMX7SNVSState snvs; + IMXI2CState i2c[FSL_IMX8MM_NUM_I2CS]; IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; SDHCIState usdhc[FSL_IMX8MM_NUM_USDHCS]; @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_UART3_IRQ = 28, FSL_IMX8MM_UART4_IRQ = 29, + FSL_IMX8MM_I2C1_IRQ = 35, + FSL_IMX8MM_I2C2_IRQ = 36, + FSL_IMX8MM_I2C3_IRQ = 37, + FSL_IMX8MM_I2C4_IRQ = 38, + FSL_IMX8MM_GPIO1_LOW_IRQ = 64, FSL_IMX8MM_GPIO1_HIGH_IRQ = 65, FSL_IMX8MM_GPIO2_LOW_IRQ = 66, -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> It enables emulation of ECSPI in iMX8MM Added SPI IRQ lines Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx8mm.c | 26 ++++++++++++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 7 +++++++ 2 files changed, 33 insertions(+) diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC); } + for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) { + g_autofree char *name = g_strdup_printf("spi%d", i + 1); + object_initialize_child(obj, name, &s->spi[i], TYPE_IMX_SPI); + } + object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST); object_initialize_child(obj, "pcie_phy", &s->pcie_phy, TYPE_FSL_IMX8M_PCIE_PHY); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in(gicdev, usdhc_table[i].irq)); } + /* ECSPIs */ + for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } spi_table[FSL_IMX8MM_NUM_ECSPIS] = { + { fsl_imx8mm_memmap[FSL_IMX8MM_ECSPI1].addr, FSL_IMX8MM_ECSPI1_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_ECSPI2].addr, FSL_IMX8MM_ECSPI2_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_ECSPI3].addr, FSL_IMX8MM_ECSPI3_IRQ }, + }; + + if (!sysbus_realize(SYS_BUS_DEVICE(&s->spi[i]), errp)) { + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->spi[i]), 0, spi_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->spi[i]), 0, + qdev_get_gpio_in(gicdev, spi_table[i].irq)); + } + /* SNVS */ if (!sysbus_realize(SYS_BUS_DEVICE(&s->snvs), errp)) { return; @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_GIC_DIST: case FSL_IMX8MM_GIC_REDIST: case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5: + case FSL_IMX8MM_ECSPI1 ... FSL_IMX8MM_ECSPI3: case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4: case FSL_IMX8MM_PCIE1: case FSL_IMX8MM_PCIE_PHY1: diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/pci-host/designware.h" #include "hw/pci-host/fsl_imx8m_phy.h" #include "hw/sd/sdhci.h" +#include "hw/ssi/imx_spi.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(FslImx8mmState, FSL_IMX8MM) enum FslImx8mmConfiguration { FSL_IMX8MM_NUM_CPUS = 4, + FSL_IMX8MM_NUM_ECSPIS = 3, FSL_IMX8MM_NUM_GPIOS = 5, FSL_IMX8MM_NUM_I2CS = 4, FSL_IMX8MM_NUM_IRQS = 128, @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMX8MPCCMState ccm; IMX8MPAnalogState analog; IMX7SNVSState snvs; + IMXSPIState spi[FSL_IMX8MM_NUM_ECSPIS]; IMXI2CState i2c[FSL_IMX8MM_NUM_I2CS]; IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_UART3_IRQ = 28, FSL_IMX8MM_UART4_IRQ = 29, + FSL_IMX8MM_ECSPI1_IRQ = 31, + FSL_IMX8MM_ECSPI2_IRQ = 32, + FSL_IMX8MM_ECSPI3_IRQ = 33, + FSL_IMX8MM_I2C1_IRQ = 35, FSL_IMX8MM_I2C2_IRQ = 36, FSL_IMX8MM_I2C3_IRQ = 37, -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> It enables emulation of WDT in iMX8MM Added WDT IRQ lines Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx8mm.c | 28 ++++++++++++++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 7 +++++++ 3 files changed, 36 insertions(+) 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 FSL_IMX8MM select SDHCI select PCI_EXPRESS_DESIGNWARE select PCI_EXPRESS_FSL_IMX8M_PHY + select WDT_IMX2 config FSL_IMX8MM_EVK bool diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->spi[i], TYPE_IMX_SPI); } + for (i = 0; i < FSL_IMX8MM_NUM_WDTS; i++) { + g_autofree char *name = g_strdup_printf("wdt%d", i); + object_initialize_child(obj, name, &s->wdt[i], TYPE_IMX2_WDT); + } + object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST); object_initialize_child(obj, "pcie_phy", &s->pcie_phy, TYPE_FSL_IMX8M_PCIE_PHY); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->snvs), 0, fsl_imx8mm_memmap[FSL_IMX8MM_SNVS_HP].addr); + /* Watchdogs */ + for (i = 0; i < FSL_IMX8MM_NUM_WDTS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } wdog_table[FSL_IMX8MM_NUM_WDTS] = { + { fsl_imx8mm_memmap[FSL_IMX8MM_WDOG1].addr, FSL_IMX8MM_WDOG1_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_WDOG2].addr, FSL_IMX8MM_WDOG2_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_WDOG3].addr, FSL_IMX8MM_WDOG3_IRQ }, + }; + + object_property_set_bool(OBJECT(&s->wdt[i]), "pretimeout-support", + true, &error_abort); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->wdt[i]), errp)) { + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->wdt[i]), 0, wdog_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->wdt[i]), 0, + qdev_get_gpio_in(gicdev, wdog_table[i].irq)); + } + /* PCIe */ if (!sysbus_realize(SYS_BUS_DEVICE(&s->pcie), errp)) { return; @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_SNVS_HP: case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4: case FSL_IMX8MM_USDHC1 ... FSL_IMX8MM_USDHC3: + case FSL_IMX8MM_WDOG1 ... FSL_IMX8MM_WDOG3: /* device implemented and treated above */ break; diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/pci-host/fsl_imx8m_phy.h" #include "hw/sd/sdhci.h" #include "hw/ssi/imx_spi.h" +#include "hw/watchdog/wdt_imx2.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration { FSL_IMX8MM_NUM_IRQS = 128, FSL_IMX8MM_NUM_UARTS = 4, FSL_IMX8MM_NUM_USDHCS = 3, + FSL_IMX8MM_NUM_WDTS = 3, }; struct FslImx8mmState { @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; SDHCIState usdhc[FSL_IMX8MM_NUM_USDHCS]; + IMX2WdtState wdt[FSL_IMX8MM_NUM_WDTS]; DesignwarePCIEHost pcie; FslImx8mPciePhyState pcie_phy; }; @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_GPIO5_LOW_IRQ = 72, FSL_IMX8MM_GPIO5_HIGH_IRQ = 73, + FSL_IMX8MM_WDOG1_IRQ = 78, + FSL_IMX8MM_WDOG2_IRQ = 79, + FSL_IMX8MM_WDOG3_IRQ = 10, + FSL_IMX8MM_PCI_INTA_IRQ = 122, FSL_IMX8MM_PCI_INTB_IRQ = 123, FSL_IMX8MM_PCI_INTC_IRQ = 124, -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> It enables emulation of GPT in iMX8MM Added GPT IRQ lines Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx8mm.c | 54 +++++++++++++++++++++++++++++++++++++ hw/timer/imx_gpt.c | 26 ++++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 11 ++++++++ include/hw/timer/imx_gpt.h | 2 ++ 5 files changed, 94 insertions(+) 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 FSL_IMX8MM select FSL_IMX8MP_CCM select IMX select IMX_I2C + select OR_IRQ select SDHCI select PCI_EXPRESS_DESIGNWARE select PCI_EXPRESS_FSL_IMX8M_PHY diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->uart[i], TYPE_IMX_SERIAL); } + for (i = 0; i < FSL_IMX8MM_NUM_GPTS; i++) { + g_autofree char *name = g_strdup_printf("gpt%d", i + 1); + object_initialize_child(obj, name, &s->gpt[i], TYPE_IMX8MM_GPT); + } + object_initialize_child(obj, "gpt5-gpt6-irq", &s->gpt5_gpt6_irq, + TYPE_OR_IRQ); + for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) { g_autofree char *name = g_strdup_printf("i2c%d", i + 1); object_initialize_child(obj, name, &s->i2c[i], TYPE_IMX_I2C); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) fsl_imx8mm_memmap[FSL_IMX8MM_OCRAM].addr, &s->ocram); + /* GPTs */ + object_property_set_int(OBJECT(&s->gpt5_gpt6_irq), "num-lines", 2, + &error_abort); + if (!qdev_realize(DEVICE(&s->gpt5_gpt6_irq), NULL, errp)) { + return; + } + + qdev_connect_gpio_out(DEVICE(&s->gpt5_gpt6_irq), 0, + qdev_get_gpio_in(gicdev, FSL_IMX8MM_GPT5_GPT6_IRQ)); + + for (i = 0; i < FSL_IMX8MM_NUM_GPTS; i++) { + hwaddr gpt_addrs[FSL_IMX8MM_NUM_GPTS] = { + fsl_imx8mm_memmap[FSL_IMX8MM_GPT1].addr, + fsl_imx8mm_memmap[FSL_IMX8MM_GPT2].addr, + fsl_imx8mm_memmap[FSL_IMX8MM_GPT3].addr, + fsl_imx8mm_memmap[FSL_IMX8MM_GPT4].addr, + fsl_imx8mm_memmap[FSL_IMX8MM_GPT5].addr, + fsl_imx8mm_memmap[FSL_IMX8MM_GPT6].addr, + }; + + s->gpt[i].ccm = IMX_CCM(&s->ccm); + + if (!sysbus_realize(SYS_BUS_DEVICE(&s->gpt[i]), errp)) { + return; + } + + sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpt[i]), 0, gpt_addrs[i]); + + if (i < FSL_IMX8MM_NUM_GPTS - 2) { + static const unsigned int gpt_irqs[FSL_IMX8MM_NUM_GPTS - 2] = { + FSL_IMX8MM_GPT1_IRQ, + FSL_IMX8MM_GPT2_IRQ, + FSL_IMX8MM_GPT3_IRQ, + FSL_IMX8MM_GPT4_IRQ, + }; + + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpt[i]), 0, + qdev_get_gpio_in(gicdev, gpt_irqs[i])); + } else { + int irq = i - FSL_IMX8MM_NUM_GPTS + 2; + + sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpt[i]), 0, + qdev_get_gpio_in(DEVICE(&s->gpt5_gpt6_irq), irq)); + } + } + /* I2Cs */ for (i = 0; i < FSL_IMX8MM_NUM_I2CS; i++) { static const struct { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_GIC_DIST: case FSL_IMX8MM_GIC_REDIST: case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5: + case FSL_IMX8MM_GPT1 ... FSL_IMX8MM_GPT6: case FSL_IMX8MM_ECSPI1 ... FSL_IMX8MM_ECSPI3: case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4: case FSL_IMX8MM_PCIE1: diff --git a/hw/timer/imx_gpt.c b/hw/timer/imx_gpt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/imx_gpt.c +++ b/hw/timer/imx_gpt.c @@ -XXX,XX +XXX,XX @@ * Originally written by Hans Jiang * Updated by Peter Chubb * Updated by Jean-Christophe Dubois <jcd@tribudubois.net> + * Updated by Gaurav Sharma <gaurav.sharma_7@nxp.com> * * This code is licensed under GPL version 2 or later. See * the COPYING file in the top-level directory. @@ -XXX,XX +XXX,XX @@ static const IMXClk imx8mp_gpt_clocks[] = { CLK_NONE, /* 111 not defined */ }; +static const IMXClk imx8mm_gpt_clocks[] = { + CLK_NONE, /* 000 No clock source */ + CLK_IPG, /* 001 ipg_clk, 532MHz */ + CLK_IPG_HIGH, /* 010 ipg_clk_highfreq */ + CLK_EXT, /* 011 External clock */ + CLK_32k, /* 100 ipg_clk_32k */ + CLK_HIGH, /* 101 ipg_clk_16M */ + CLK_NONE, /* 110 not defined */ + CLK_NONE, /* 111 not defined */ +}; + /* Must be called from within ptimer_transaction_begin/commit block */ static void imx_gpt_set_freq(IMXGPTState *s) { @@ -XXX,XX +XXX,XX @@ static void imx8mp_gpt_init(Object *obj) s->clocks = imx8mp_gpt_clocks; } +static void imx8mm_gpt_init(Object *obj) +{ + IMXGPTState *s = IMX_GPT(obj); + + s->clocks = imx8mm_gpt_clocks; +} + static const TypeInfo imx25_gpt_info = { .name = TYPE_IMX25_GPT, .parent = TYPE_SYS_BUS_DEVICE, @@ -XXX,XX +XXX,XX @@ static const TypeInfo imx8mp_gpt_info = { .instance_init = imx8mp_gpt_init, }; +static const TypeInfo imx8mm_gpt_info = { + .name = TYPE_IMX8MM_GPT, + .parent = TYPE_IMX25_GPT, + .instance_init = imx8mm_gpt_init, +}; + static void imx_gpt_register_types(void) { type_register_static(&imx25_gpt_info); @@ -XXX,XX +XXX,XX @@ static void imx_gpt_register_types(void) type_register_static(&imx6ul_gpt_info); type_register_static(&imx7_gpt_info); type_register_static(&imx8mp_gpt_info); + type_register_static(&imx8mm_gpt_info); } type_init(imx_gpt_register_types) diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/imx7_snvs.h" #include "hw/misc/imx8mp_analog.h" #include "hw/misc/imx8mp_ccm.h" +#include "hw/or-irq.h" #include "hw/pci-host/designware.h" #include "hw/pci-host/fsl_imx8m_phy.h" #include "hw/sd/sdhci.h" #include "hw/ssi/imx_spi.h" +#include "hw/timer/imx_gpt.h" #include "hw/watchdog/wdt_imx2.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration { FSL_IMX8MM_NUM_CPUS = 4, FSL_IMX8MM_NUM_ECSPIS = 3, FSL_IMX8MM_NUM_GPIOS = 5, + FSL_IMX8MM_NUM_GPTS = 6, FSL_IMX8MM_NUM_I2CS = 4, FSL_IMX8MM_NUM_IRQS = 128, FSL_IMX8MM_NUM_UARTS = 4, @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { ARMCPU cpu[FSL_IMX8MM_NUM_CPUS]; GICv3State gic; + IMXGPTState gpt[FSL_IMX8MM_NUM_GPTS]; IMXGPIOState gpio[FSL_IMX8MM_NUM_GPIOS]; IMX8MPCCMState ccm; IMX8MPAnalogState analog; @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMX2WdtState wdt[FSL_IMX8MM_NUM_WDTS]; DesignwarePCIEHost pcie; FslImx8mPciePhyState pcie_phy; + OrIRQState gpt5_gpt6_irq; }; enum FslImx8mmMemoryRegions { @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_I2C3_IRQ = 37, FSL_IMX8MM_I2C4_IRQ = 38, + FSL_IMX8MM_GPT1_IRQ = 55, + FSL_IMX8MM_GPT2_IRQ = 54, + FSL_IMX8MM_GPT3_IRQ = 53, + FSL_IMX8MM_GPT4_IRQ = 52, + FSL_IMX8MM_GPT5_GPT6_IRQ = 51, + FSL_IMX8MM_GPIO1_LOW_IRQ = 64, FSL_IMX8MM_GPIO1_HIGH_IRQ = 65, FSL_IMX8MM_GPIO2_LOW_IRQ = 66, diff --git a/include/hw/timer/imx_gpt.h b/include/hw/timer/imx_gpt.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/timer/imx_gpt.h +++ b/include/hw/timer/imx_gpt.h @@ -XXX,XX +XXX,XX @@ * Originally written by Hans Jiang * Updated by Peter Chubb * Updated by Jean-Christophe Dubois <jcd@tribudubois.net> + * Updated by Gaurav Sharma <gaurav.sharma_7@nxp.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 @@ -XXX,XX +XXX,XX @@ #define TYPE_IMX6UL_GPT "imx6ul.gpt" #define TYPE_IMX7_GPT "imx7.gpt" #define TYPE_IMX8MP_GPT "imx8mp.gpt" +#define TYPE_IMX8MM_GPT "imx8mm.gpt" #define TYPE_IMX_GPT TYPE_IMX25_GPT -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> It enables emulation of ENET ethernet controller in iMX8MM Enables testing and debugging of network dependent drivers Added ENET MAC IRQ lines Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx8mm.c | 24 ++++++++++++++++++++++++ hw/arm/imx8mm-evk.c | 1 + include/hw/arm/fsl-imx8mm.h | 10 +++++++++- 4 files changed, 35 insertions(+), 1 deletion(-) 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 FSL_IMX8MM select FSL_IMX8MP_ANALOG select FSL_IMX8MP_CCM select IMX + select IMX_FEC select IMX_I2C select OR_IRQ select SDHCI diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->wdt[i], TYPE_IMX2_WDT); } + object_initialize_child(obj, "eth0", &s->enet, TYPE_IMX_ENET); + object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST); object_initialize_child(obj, "pcie_phy", &s->pcie_phy, TYPE_FSL_IMX8M_PCIE_PHY); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in(gicdev, spi_table[i].irq)); } + /* ENET1 */ + object_property_set_uint(OBJECT(&s->enet), "phy-num", s->phy_num, + &error_abort); + object_property_set_uint(OBJECT(&s->enet), "tx-ring-num", 3, &error_abort); + qemu_configure_nic_device(DEVICE(&s->enet), true, NULL); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->enet), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->enet), 0, + fsl_imx8mm_memmap[FSL_IMX8MM_ENET1].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->enet), 0, + qdev_get_gpio_in(gicdev, FSL_IMX8MM_ENET1_MAC_IRQ)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->enet), 1, + qdev_get_gpio_in(gicdev, FSL_IMX6_ENET1_MAC_1588_IRQ)); + /* SNVS */ if (!sysbus_realize(SYS_BUS_DEVICE(&s->snvs), errp)) { return; @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_GPIO1 ... FSL_IMX8MM_GPIO5: case FSL_IMX8MM_GPT1 ... FSL_IMX8MM_GPT6: case FSL_IMX8MM_ECSPI1 ... FSL_IMX8MM_ECSPI3: + case FSL_IMX8MM_ENET1: case FSL_IMX8MM_I2C1 ... FSL_IMX8MM_I2C4: case FSL_IMX8MM_PCIE1: case FSL_IMX8MM_PCIE_PHY1: @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) } } +static const Property fsl_imx8mm_properties[] = { + DEFINE_PROP_UINT32("fec1-phy-num", FslImx8mmState, phy_num, 0), + DEFINE_PROP_BOOL("fec1-phy-connected", FslImx8mmState, phy_connected, true), +}; + static void fsl_imx8mm_class_init(ObjectClass *oc, const void *data) { DeviceClass *dc = DEVICE_CLASS(oc); + device_class_set_props(dc, fsl_imx8mm_properties); dc->realize = fsl_imx8mm_realize; dc->desc = "i.MX 8MM SoC"; diff --git a/hw/arm/imx8mm-evk.c b/hw/arm/imx8mm-evk.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/imx8mm-evk.c +++ b/hw/arm/imx8mm-evk.c @@ -XXX,XX +XXX,XX @@ static void imx8mm_evk_init(MachineState *machine) s = FSL_IMX8MM(object_new_with_props(TYPE_FSL_IMX8MM, OBJECT(machine), "soc", &error_fatal, NULL)); + object_property_set_uint(OBJECT(s), "fec1-phy-num", 1, &error_fatal); sysbus_realize_and_unref(SYS_BUS_DEVICE(s), &error_fatal); memory_region_add_subregion(get_system_memory(), FSL_IMX8MM_RAM_START, diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/imx7_snvs.h" #include "hw/misc/imx8mp_analog.h" #include "hw/misc/imx8mp_ccm.h" -#include "hw/or-irq.h" +#include "hw/net/imx_fec.h" +#include "hw/core/or-irq.h" #include "hw/pci-host/designware.h" #include "hw/pci-host/fsl_imx8m_phy.h" #include "hw/sd/sdhci.h" @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMXI2CState i2c[FSL_IMX8MM_NUM_I2CS]; IMXSerialState uart[FSL_IMX8MM_NUM_UARTS]; MemoryRegion ocram; + IMXFECState enet; SDHCIState usdhc[FSL_IMX8MM_NUM_USDHCS]; IMX2WdtState wdt[FSL_IMX8MM_NUM_WDTS]; DesignwarePCIEHost pcie; FslImx8mPciePhyState pcie_phy; OrIRQState gpt5_gpt6_irq; + + uint32_t phy_num; + bool phy_connected; }; enum FslImx8mmMemoryRegions { @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_WDOG2_IRQ = 79, FSL_IMX8MM_WDOG3_IRQ = 10, + FSL_IMX8MM_ENET1_MAC_IRQ = 118, + FSL_IMX6_ENET1_MAC_1588_IRQ = 121, + FSL_IMX8MM_PCI_INTA_IRQ = 122, FSL_IMX8MM_PCI_INTB_IRQ = 123, FSL_IMX8MM_PCI_INTC_IRQ = 124, -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> It enables emulation of USB on iMX8MM Enables testing and debugging of USB drivers Reviewed-by: Philippe Mathieu-Daude <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Bernhard Beschow <shentey@gmail.com> Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx8mm.c | 27 +++++++++++++++++++++++++++ include/hw/arm/fsl-imx8mm.h | 6 ++++++ 3 files changed, 34 insertions(+) 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 FSL_IMX8MM select SDHCI select PCI_EXPRESS_DESIGNWARE select PCI_EXPRESS_FSL_IMX8M_PHY + select USB_DWC3 select WDT_IMX2 config FSL_IMX8MM_EVK diff --git a/hw/arm/fsl-imx8mm.c b/hw/arm/fsl-imx8mm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx8mm.c +++ b/hw/arm/fsl-imx8mm.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_init(Object *obj) object_initialize_child(obj, name, &s->usdhc[i], TYPE_IMX_USDHC); } + for (i = 0; i < FSL_IMX8MM_NUM_USBS; i++) { + g_autofree char *name = g_strdup_printf("usb%d", i); + object_initialize_child(obj, name, &s->usb[i], TYPE_USB_DWC3); + } + for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) { g_autofree char *name = g_strdup_printf("spi%d", i + 1); object_initialize_child(obj, name, &s->spi[i], TYPE_IMX_SPI); @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) qdev_get_gpio_in(gicdev, usdhc_table[i].irq)); } + /* USBs */ + for (i = 0; i < FSL_IMX8MM_NUM_USBS; i++) { + static const struct { + hwaddr addr; + unsigned int irq; + } usb_table[FSL_IMX8MM_NUM_USBS] = { + { fsl_imx8mm_memmap[FSL_IMX8MM_USB1].addr, FSL_IMX8MM_USB1_IRQ }, + { fsl_imx8mm_memmap[FSL_IMX8MM_USB2].addr, FSL_IMX8MM_USB2_IRQ }, + }; + + qdev_prop_set_uint32(DEVICE(&s->usb[i].sysbus_xhci), "p2", 1); + qdev_prop_set_uint32(DEVICE(&s->usb[i].sysbus_xhci), "p3", 1); + qdev_prop_set_uint32(DEVICE(&s->usb[i].sysbus_xhci), "slots", 2); + if (!sysbus_realize(SYS_BUS_DEVICE(&s->usb[i]), errp)) { + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->usb[i]), 0, usb_table[i].addr); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->usb[i].sysbus_xhci), 0, + qdev_get_gpio_in(gicdev, usb_table[i].irq)); + } + /* ECSPIs */ for (i = 0; i < FSL_IMX8MM_NUM_ECSPIS; i++) { static const struct { @@ -XXX,XX +XXX,XX @@ static void fsl_imx8mm_realize(DeviceState *dev, Error **errp) case FSL_IMX8MM_OCRAM: case FSL_IMX8MM_SNVS_HP: case FSL_IMX8MM_UART1 ... FSL_IMX8MM_UART4: + case FSL_IMX8MM_USB1 ... FSL_IMX8MM_USB2: case FSL_IMX8MM_USDHC1 ... FSL_IMX8MM_USDHC3: case FSL_IMX8MM_WDOG1 ... FSL_IMX8MM_WDOG3: /* device implemented and treated above */ diff --git a/include/hw/arm/fsl-imx8mm.h b/include/hw/arm/fsl-imx8mm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx8mm.h +++ b/include/hw/arm/fsl-imx8mm.h @@ -XXX,XX +XXX,XX @@ #include "hw/sd/sdhci.h" #include "hw/ssi/imx_spi.h" #include "hw/timer/imx_gpt.h" +#include "hw/usb/hcd-dwc3.h" #include "hw/watchdog/wdt_imx2.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ enum FslImx8mmConfiguration { FSL_IMX8MM_NUM_I2CS = 4, FSL_IMX8MM_NUM_IRQS = 128, FSL_IMX8MM_NUM_UARTS = 4, + FSL_IMX8MM_NUM_USBS = 2, FSL_IMX8MM_NUM_USDHCS = 3, FSL_IMX8MM_NUM_WDTS = 3, }; @@ -XXX,XX +XXX,XX @@ struct FslImx8mmState { IMXFECState enet; SDHCIState usdhc[FSL_IMX8MM_NUM_USDHCS]; IMX2WdtState wdt[FSL_IMX8MM_NUM_WDTS]; + USBDWC3 usb[FSL_IMX8MM_NUM_USBS]; DesignwarePCIEHost pcie; FslImx8mPciePhyState pcie_phy; OrIRQState gpt5_gpt6_irq; @@ -XXX,XX +XXX,XX @@ enum FslImx8mmIrqs { FSL_IMX8MM_I2C3_IRQ = 37, FSL_IMX8MM_I2C4_IRQ = 38, + FSL_IMX8MM_USB1_IRQ = 40, + FSL_IMX8MM_USB2_IRQ = 41, + FSL_IMX8MM_GPT1_IRQ = 55, FSL_IMX8MM_GPT2_IRQ = 54, FSL_IMX8MM_GPT3_IRQ = 53, -- 2.43.0 From: Gaurav Sharma <gaurav.sharma_7@nxp.com> Added script that would validate the iMX8MM emulation by checking the linux console log. If it succeeds, it will return:- ok 1 test_imx8mm_evk.Imx8mmEvkMachine.test_aarch64_imx8mm_evk_usdhc Signed-off-by: Gaurav Sharma <gaurav.sharma_7@nxp.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Bernhard Beschow <shentey@gmail.com> [PMM: Add missing blank lines that flake8 wants] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 1 + tests/functional/aarch64/meson.build | 2 + tests/functional/aarch64/test_imx8mm_evk.py | 69 +++++++++++++++++++++ 3 files changed, 72 insertions(+) create mode 100755 tests/functional/aarch64/test_imx8mm_evk.py diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/arm/fsl-imx8mm.c F: hw/arm/imx8mm-evk.c F: include/hw/arm/fsl-imx8mm.h F: docs/system/arm/imx8m.rst +F: tests/functional/aarch64/test_imx8mm_evk.py MCIMX8MP-EVK / i.MX8MP M: Bernhard Beschow <shentey@gmail.com> diff --git a/tests/functional/aarch64/meson.build b/tests/functional/aarch64/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/functional/aarch64/meson.build +++ b/tests/functional/aarch64/meson.build @@ -XXX,XX +XXX,XX @@ test_aarch64_timeouts = { 'aspeed_ast2700a2' : 600, 'aspeed_ast2700fc' : 600, 'device_passthrough' : 720, + 'imx8mm_evk' : 240, 'imx8mp_evk' : 240, 'raspi4' : 480, 'reverse_debug' : 180, @@ -XXX,XX +XXX,XX @@ tests_aarch64_system_thorough = [ 'aspeed_ast2700fc', 'device_passthrough', 'hotplug_pci', + 'imx8mm_evk', 'imx8mp_evk', 'kvm', 'multiprocess', diff --git a/tests/functional/aarch64/test_imx8mm_evk.py b/tests/functional/aarch64/test_imx8mm_evk.py new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/functional/aarch64/test_imx8mm_evk.py @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env python3 +# +# Functional test that boots a Linux kernel and checks the console +# +# SPDX-License-Identifier: GPL-2.0-or-later + +from qemu_test import LinuxKernelTest, Asset + + +class Imx8mmEvkMachine(LinuxKernelTest): + + ASSET_IMAGE = Asset( + ('https://cloud.debian.org/images/cloud/bookworm/20231210-1590/' + 'debian-12-generic-arm64-20231210-1590.tar.xz'), + '7ebf1577b32d5af6204df74b54ca2e4675de9b5a9fa14f3ff70b88eeb7b3b359') + + KERNEL_OFFSET = 0x51000000 + KERNEL_SIZE = 32622528 + INITRD_OFFSET = 0x76000000 + INITRD_SIZE = 30987766 + DTB_OFFSET = 0x64DB5000 + DTB_SIZE = 36812 + + def extract(self, in_path, out_path, offset, size): + try: + with open(in_path, "rb") as source: + source.seek(offset) + data = source.read(size) + with open(out_path, "wb") as target: + target.write(data) + except (IOError, ValueError) as e: + self.log.error(f"Failed to extract {out_path}: {e}") + raise + + def setUp(self): + super().setUp() + + self.image_path = self.scratch_file("disk.raw") + self.kernel_path = self.scratch_file("linux") + self.initrd_path = self.scratch_file("initrd.zstd") + self.dtb_path = self.scratch_file("imx8mm-evk.dtb") + + self.archive_extract(self.ASSET_IMAGE) + self.extract(self.image_path, self.kernel_path, + self.KERNEL_OFFSET, self.KERNEL_SIZE) + self.extract(self.image_path, self.initrd_path, + self.INITRD_OFFSET, self.INITRD_SIZE) + self.extract(self.image_path, self.dtb_path, + self.DTB_OFFSET, self.DTB_SIZE) + + def test_aarch64_imx8mm_evk_usdhc(self): + self.require_accelerator("tcg") + self.set_machine('imx8mm-evk') + self.vm.set_console(console_index=1) + self.vm.add_args('-m', '2G', + '-smp', '4', + '-kernel', self.kernel_path, + '-initrd', self.initrd_path, + '-dtb', self.dtb_path, + '-append', 'root=/dev/mmcblk2p1', + '-drive', f'file={self.image_path},if=sd,bus=2,' + 'format=raw,id=mmcblk2,snapshot=on') + + self.vm.launch() + self.wait_for_console_pattern('Welcome to ') + + +if __name__ == '__main__': + LinuxKernelTest.main() -- 2.43.0 From: Philippe Mathieu-Daudé <philmd@linaro.org> As mentioned by Richard in [*]: We don't actually need any specific endianness here, because every byte has the same value. So we could simply drop MO_TE. That would produce a store in host-endianness, which will be fractionally more efficient on some hosts. [*] https://lore.kernel.org/qemu-devel/d64d3576-9188-4e74-afdc-3492c9feb8e0@linaro.org/ Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20260414005348.4767-2-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/helper-a64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -XXX,XX +XXX,XX @@ static uint64_t set_step_tags(CPUARMState *env, uint64_t toaddr, * the page dirty and will use the fast path. */ uint64_t repldata = data * 0x0101010101010101ULL; - MemOpIdx oi16 = make_memop_idx(MO_TE | MO_128, memidx); + MemOpIdx oi16 = make_memop_idx(MO_128, memidx); cpu_st16_mmu(env, toaddr, int128_make128(repldata, repldata), oi16, ra); mte_mops_set_tags(env, toaddr, 16, *mtedesc); return 16; -- 2.43.0 From: Philippe Mathieu-Daudé <philmd@linaro.org> Extract the implicit MO_TE definition in order to replace it in the next commit. Mechanical change using: $ for n in UW UL UQ UO SW SL SQ; do \ sed -i -e "s/MO_TE$n/MO_TE | MO_$n/" \ $(git grep -l MO_TE$n target/arm); \ done Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20260414005348.4767-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/m_helper.c | 6 +-- target/arm/tcg/mve_helper.c | 79 ++++++++++++++++++++----------------- 2 files changed, 45 insertions(+), 40 deletions(-) diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) /* Note that these stores can throw exceptions on MPU faults */ ARMMMUIdx mmu_idx = arm_mmu_idx(env); - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx)); cpu_stl_mmu(env, sp, nextinst, oi, GETPC()); cpu_stl_mmu(env, sp + 4, saved_psr, oi, GETPC()); @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr) bool lspact = env->v7m.fpccr[s] & R_V7M_FPCCR_LSPACT_MASK; uintptr_t ra = GETPC(); ARMMMUIdx mmu_idx = arm_mmu_idx(env); - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx)); assert(env->v7m.secure); @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr) ARMCPU *cpu = env_archcpu(env); uintptr_t ra = GETPC(); ARMMMUIdx mmu_idx = arm_mmu_idx(env); - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx)); /* fptr is the value of Rn, the frame pointer we load the FP regs from */ diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) } DO_VLDR(vldrb, MO_UB, 1, uint8_t, ldb, 1, uint8_t) -DO_VLDR(vldrh, MO_TEUW, 2, uint16_t, ldw, 2, uint16_t) -DO_VLDR(vldrw, MO_TEUL, 4, uint32_t, ldl, 4, uint32_t) +DO_VLDR(vldrh, MO_TE | MO_UW, 2, uint16_t, ldw, 2, uint16_t) +DO_VLDR(vldrw, MO_TE | MO_UL, 4, uint32_t, ldl, 4, uint32_t) DO_VSTR(vstrb, MO_UB, 1, stb, 1, uint8_t) -DO_VSTR(vstrh, MO_TEUW, 2, stw, 2, uint16_t) -DO_VSTR(vstrw, MO_TEUL, 4, stl, 4, uint32_t) +DO_VSTR(vstrh, MO_TE | MO_UW, 2, stw, 2, uint16_t) +DO_VSTR(vstrw, MO_TE | MO_UL, 4, stl, 4, uint32_t) DO_VLDR(vldrb_sh, MO_SB, 1, int8_t, ldb, 2, int16_t) DO_VLDR(vldrb_sw, MO_SB, 1, int8_t, ldb, 4, int32_t) DO_VLDR(vldrb_uh, MO_UB, 1, uint8_t, ldb, 2, uint16_t) DO_VLDR(vldrb_uw, MO_UB, 1, uint8_t, ldb, 4, uint32_t) -DO_VLDR(vldrh_sw, MO_TESW, 2, int16_t, ldw, 4, int32_t) -DO_VLDR(vldrh_uw, MO_TEUW, 2, uint16_t, ldw, 4, uint32_t) +DO_VLDR(vldrh_sw, MO_TE | MO_SW, 2, int16_t, ldw, 4, int32_t) +DO_VLDR(vldrh_uw, MO_TE | MO_UW, 2, uint16_t, ldw, 4, uint32_t) DO_VSTR(vstrb_h, MO_UB, 1, stb, 2, int16_t) DO_VSTR(vstrb_w, MO_UB, 1, stb, 4, int32_t) -DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) +DO_VSTR(vstrh_w, MO_TE | MO_UW, 2, stw, 4, int32_t) #undef DO_VLDR #undef DO_VSTR @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ if (!(eci_mask & 1)) { \ continue; \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ if (!(eci_mask & 1)) { \ continue; \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_TEUW, 2, stw, 4, int32_t) DO_VLDR_SG(vldrb_sg_sh, MO_SB, int8_t, ldb, 2, int16_t, uint16_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_sw, MO_SB, int8_t, ldb, 4, int32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_sw, MO_TESW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_sw, MO_TE | MO_SW, int16_t, ldw, 4, + int32_t, uint32_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_ub, MO_UB, uint8_t, ldb, 1, uint8_t, uint8_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_uh, MO_UB, uint8_t, ldb, 2, uint16_t, uint16_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_uw, MO_UB, uint8_t, ldb, 4, uint32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_uh, MO_TEUW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_uw, MO_TEUW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrw_sg_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uh, MO_TE | MO_UW, uint16_t, ldw, 2, + uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uw, MO_TE | MO_UW, uint16_t, ldw, 4, + uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrw_sg_uw, MO_TE | MO_UL, uint32_t, ldl, 4, + uint32_t, uint32_t, ADDR_ADD, false) DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_os_sw, MO_TESW, int16_t, ldw, 4, +DO_VLDR_SG(vldrh_sg_os_sw, MO_TE | MO_SW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrh_sg_os_uh, MO_TEUW, uint16_t, ldw, 2, +DO_VLDR_SG(vldrh_sg_os_uh, MO_TE | MO_UW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrh_sg_os_uw, MO_TEUW, uint16_t, ldw, 4, +DO_VLDR_SG(vldrh_sg_os_uw, MO_TE | MO_UW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrw_sg_os_uw, MO_TEUL, uint32_t, ldl, 4, +DO_VLDR_SG(vldrw_sg_os_uw, MO_TE | MO_UL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false) DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false) DO_VSTR_SG(vstrb_sg_ub, MO_UB, stb, 1, uint8_t, ADDR_ADD, false) DO_VSTR_SG(vstrb_sg_uh, MO_UB, stb, 2, uint16_t, ADDR_ADD, false) DO_VSTR_SG(vstrb_sg_uw, MO_UB, stb, 4, uint32_t, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_uh, MO_TEUW, stw, 2, uint16_t, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_uw, MO_TEUW, stw, 4, uint32_t, ADDR_ADD, false) -DO_VSTR_SG(vstrw_sg_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrw_sg_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, false) DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_os_uh, MO_TEUW, stw, 2, uint16_t, ADDR_ADD_OSH, false) -DO_VSTR_SG(vstrh_sg_os_uw, MO_TEUW, stw, 4, uint32_t, ADDR_ADD_OSH, false) -DO_VSTR_SG(vstrw_sg_os_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD_OSW, false) +DO_VSTR_SG(vstrh_sg_os_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrh_sg_os_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrw_sg_os_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD_OSW, false) DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false) -DO_VLDR_SG(vldrw_sg_wb_uw, MO_TEUL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true) +DO_VLDR_SG(vldrw_sg_wb_uw, MO_TE | MO_UL, uint32_t, ldl, 4, + uint32_t, uint32_t, ADDR_ADD, true) DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) -DO_VSTR_SG(vstrw_sg_wb_uw, MO_TEUL, stl, 4, uint32_t, ADDR_ADD, true) +DO_VSTR_SG(vstrw_sg_wb_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, true) DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) /* @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) int y; /* y counts 0 2 0 2 */ \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) uint32_t *qd; \ int y; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) uint32_t addr, data; \ uint8_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) int e; \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) uint32_t addr, data; \ uint32_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) int y; /* y counts 0 2 0 2 */ \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) uint32_t *qd; \ int y; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) uint32_t addr, data; \ uint8_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) int e; \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) uint32_t addr, data; \ uint32_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TEUL | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ -- 2.43.0 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: 20260414005348.4767-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/mve_helper.c | 20 +++++++++++--------- 1 file changed, 11 insertions(+), 9 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) uint16_t eci_mask = mve_eci_mask(env); \ unsigned b, e; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + mmu_idx); \ /* \ * R_SXTM allows the dest reg to become UNKNOWN for abandoned \ * beats so we don't care if we update part of the dest and \ @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) uint16_t mask = mve_element_mask(env); \ unsigned b, e; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + mmu_idx); \ for (b = 0, e = 0; b < 16; b += ESIZE, e++) { \ if (mask & (1 << b)) { \ cpu_##STTYPE##_mmu(env, addr, d[H##ESIZE(e)], oi, GETPC()); \ @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) } DO_VLDR(vldrb, MO_UB, 1, uint8_t, ldb, 1, uint8_t) -DO_VLDR(vldrh, MO_TE | MO_UW, 2, uint16_t, ldw, 2, uint16_t) -DO_VLDR(vldrw, MO_TE | MO_UL, 4, uint32_t, ldl, 4, uint32_t) +DO_VLDR(vldrh, MO_UW, 2, uint16_t, ldw, 2, uint16_t) +DO_VLDR(vldrw, MO_UL, 4, uint32_t, ldl, 4, uint32_t) DO_VSTR(vstrb, MO_UB, 1, stb, 1, uint8_t) -DO_VSTR(vstrh, MO_TE | MO_UW, 2, stw, 2, uint16_t) -DO_VSTR(vstrw, MO_TE | MO_UL, 4, stl, 4, uint32_t) +DO_VSTR(vstrh, MO_UW, 2, stw, 2, uint16_t) +DO_VSTR(vstrw, MO_UL, 4, stl, 4, uint32_t) DO_VLDR(vldrb_sh, MO_SB, 1, int8_t, ldb, 2, int16_t) DO_VLDR(vldrb_sw, MO_SB, 1, int8_t, ldb, 4, int32_t) DO_VLDR(vldrb_uh, MO_UB, 1, uint8_t, ldb, 2, uint16_t) DO_VLDR(vldrb_uw, MO_UB, 1, uint8_t, ldb, 4, uint32_t) -DO_VLDR(vldrh_sw, MO_TE | MO_SW, 2, int16_t, ldw, 4, int32_t) -DO_VLDR(vldrh_uw, MO_TE | MO_UW, 2, uint16_t, ldw, 4, uint32_t) +DO_VLDR(vldrh_sw, MO_SW, 2, int16_t, ldw, 4, int32_t) +DO_VLDR(vldrh_uw, MO_UW, 2, uint16_t, ldw, 4, uint32_t) DO_VSTR(vstrb_h, MO_UB, 1, stb, 2, int16_t) DO_VSTR(vstrb_w, MO_UB, 1, stb, 4, int32_t) -DO_VSTR(vstrh_w, MO_TE | MO_UW, 2, stw, 4, int32_t) +DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) #undef DO_VLDR #undef DO_VSTR -- 2.43.0 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: 20260414005348.4767-5-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/mve_helper.c | 43 +++++++++++++++++-------------------- 1 file changed, 20 insertions(+), 23 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + mmu_idx); \ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ if (!(eci_mask & 1)) { \ continue; \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MFLAG | MO_ALIGN, mmu_idx); \ + MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + mmu_idx); \ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ if (!(eci_mask & 1)) { \ continue; \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) DO_VLDR_SG(vldrb_sg_sh, MO_SB, int8_t, ldb, 2, int16_t, uint16_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_sw, MO_SB, int8_t, ldb, 4, int32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_sw, MO_TE | MO_SW, int16_t, ldw, 4, - int32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_sw, MO_SW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_ub, MO_UB, uint8_t, ldb, 1, uint8_t, uint8_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_uh, MO_UB, uint8_t, ldb, 2, uint16_t, uint16_t, ADDR_ADD, false) DO_VLDR_SG(vldrb_sg_uw, MO_UB, uint8_t, ldb, 4, uint32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_uh, MO_TE | MO_UW, uint16_t, ldw, 2, - uint16_t, uint16_t, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_uw, MO_TE | MO_UW, uint16_t, ldw, 4, - uint32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrw_sg_uw, MO_TE | MO_UL, uint32_t, ldl, 4, - uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uh, MO_UW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uw, MO_UW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrw_sg_uw, MO_UL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false) DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_os_sw, MO_TE | MO_SW, int16_t, ldw, 4, +DO_VLDR_SG(vldrh_sg_os_sw, MO_SW, int16_t, ldw, 4, int32_t, uint32_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrh_sg_os_uh, MO_TE | MO_UW, uint16_t, ldw, 2, +DO_VLDR_SG(vldrh_sg_os_uh, MO_UW, uint16_t, ldw, 2, uint16_t, uint16_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrh_sg_os_uw, MO_TE | MO_UW, uint16_t, ldw, 4, +DO_VLDR_SG(vldrh_sg_os_uw, MO_UW, uint16_t, ldw, 4, uint32_t, uint32_t, ADDR_ADD_OSH, false) -DO_VLDR_SG(vldrw_sg_os_uw, MO_TE | MO_UL, uint32_t, ldl, 4, +DO_VLDR_SG(vldrw_sg_os_uw, MO_UL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false) DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false) DO_VSTR_SG(vstrb_sg_ub, MO_UB, stb, 1, uint8_t, ADDR_ADD, false) DO_VSTR_SG(vstrb_sg_uh, MO_UB, stb, 2, uint16_t, ADDR_ADD, false) DO_VSTR_SG(vstrb_sg_uw, MO_UB, stb, 4, uint32_t, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD, false) -DO_VSTR_SG(vstrw_sg_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uh, MO_UW, stw, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uw, MO_UW, stw, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrw_sg_uw, MO_UL, stl, 4, uint32_t, ADDR_ADD, false) DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_os_uh, MO_TE | MO_UW, stw, 2, uint16_t, ADDR_ADD_OSH, false) -DO_VSTR_SG(vstrh_sg_os_uw, MO_TE | MO_UW, stw, 4, uint32_t, ADDR_ADD_OSH, false) -DO_VSTR_SG(vstrw_sg_os_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD_OSW, false) +DO_VSTR_SG(vstrh_sg_os_uh, MO_UW, stw, 2, uint16_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrh_sg_os_uw, MO_UW, stw, 4, uint32_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrw_sg_os_uw, MO_UL, stl, 4, uint32_t, ADDR_ADD_OSW, false) DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false) -DO_VLDR_SG(vldrw_sg_wb_uw, MO_TE | MO_UL, uint32_t, ldl, 4, - uint32_t, uint32_t, ADDR_ADD, true) +DO_VLDR_SG(vldrw_sg_wb_uw, MO_UL, uint32_t, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true) DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) -DO_VSTR_SG(vstrw_sg_wb_uw, MO_TE | MO_UL, stl, 4, uint32_t, ADDR_ADD, true) +DO_VSTR_SG(vstrw_sg_wb_uw, MO_UL, stl, 4, uint32_t, ADDR_ADD, true) DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) /* -- 2.43.0 From: Philippe Mathieu-Daudé <philmd@linaro.org> Suggested-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20260414005348.4767-6-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 6 ++++++ target/arm/tcg/mve_helper.c | 3 ++- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ #include "exec/hwaddr.h" #include "exec/vaddr.h" #include "exec/breakpoint.h" +#include "exec/memop.h" #include "accel/tcg/tb-cpu-state.h" #include "hw/core/registerfields.h" #include "tcg/tcg-gvec-desc.h" @@ -XXX,XX +XXX,XX @@ #define BANK_HYP 6 #define BANK_MON 7 +static inline MemOp mo_endian(CPUARMState *env) +{ + return EX_TBFLAG_ANY(env->hflags, BE_DATA) ? MO_BE : MO_LE; +} + static inline int arm_env_mmu_index(CPUARMState *env) { return EX_TBFLAG_ANY(env->hflags, MMUIDX); diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ if (!(eci_mask & 1)) { \ continue; \ -- 2.43.0 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: 20260414005348.4767-7-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/mve_helper.c | 47 +++++++++++++++++++++++-------------- 1 file changed, 30 insertions(+), 17 deletions(-) diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) uint16_t eci_mask = mve_eci_mask(env); \ unsigned b, e; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \ mmu_idx); \ /* \ * R_SXTM allows the dest reg to become UNKNOWN for abandoned \ @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) uint16_t mask = mve_element_mask(env); \ unsigned b, e; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \ mmu_idx); \ for (b = 0, e = 0; b < 16; b += ESIZE, e++) { \ if (mask & (1 << b)) { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \ mmu_idx); \ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ if (!(eci_mask & 1)) { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MFLAG | MO_ALIGN, \ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MFLAG | MO_ALIGN, \ mmu_idx); \ for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ if (!(eci_mask & 1)) { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, MO_UW, 2, stw, 4, int32_t) unsigned e; \ uint32_t addr; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ if (!(eci_mask & 1)) { \ continue; \ @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) int y; /* y counts 0 2 0 2 */ \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) uint32_t *qd; \ int y; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) uint32_t addr, data; \ uint8_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) int e; \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD4W(vld43w, 6, 7, 8, 9) uint32_t addr, data; \ uint32_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) static const uint8_t off[4] = { O1, O2, O3, O4 }; \ uint32_t addr, data; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) int y; /* y counts 0 2 0 2 */ \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VLD2W(vld21w, 8, 12, 16, 20) uint32_t *qd; \ int y; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) uint32_t addr, data; \ uint8_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) int e; \ uint16_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ @@ -XXX,XX +XXX,XX @@ DO_VST4W(vst43w, 6, 7, 8, 9) uint32_t addr, data; \ uint32_t *qd; \ int mmu_idx = arm_to_core_mmu_idx(arm_mmu_idx(env)); \ - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, mmu_idx);\ + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, \ + mmu_idx); \ for (beat = 0; beat < 4; beat++, mask >>= 4) { \ if ((mask & 1) == 0) { \ /* ECI says skip this beat */ \ -- 2.43.0 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: 20260414005348.4767-8-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/meson.build | 3 ++- target/arm/tcg/mve_helper.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/meson.build +++ b/target/arm/tcg/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'TARGET_AARCH64', if_false: files('stubs32.c')) arm_ss.add(files( 'cpu32.c', 'm_helper.c', - 'mve_helper.c', )) arm_ss.add(when: 'TARGET_AARCH64', if_true: files( @@ -XXX,XX +XXX,XX @@ arm_common_system_ss.add( 'debug.c', 'hflags.c', 'gengvec.c', + 'mve_helper.c', 'neon_helper.c', 'op_helper.c', 'psci.c', @@ -XXX,XX +XXX,XX @@ arm_user_ss.add( 'debug.c', 'gengvec.c', 'hflags.c', + 'mve_helper.c', 'neon_helper.c', 'op_helper.c', 'tlb_helper.c', diff --git a/target/arm/tcg/mve_helper.c b/target/arm/tcg/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/mve_helper.c +++ b/target/arm/tcg/mve_helper.c @@ -XXX,XX +XXX,XX @@ #include "helper-mve.h" #include "internals.h" #include "vec_internal.h" -#include "accel/tcg/cpu-ldst.h" +#include "accel/tcg/cpu-ldst-common.h" #include "tcg/tcg.h" #include "fpu/softfloat.h" #include "crypto/clmul.h" -- 2.43.0 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: 20260414005348.4767-9-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/m_helper.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_blxns)(CPUARMState *env, uint32_t dest) /* Note that these stores can throw exceptions on MPU faults */ ARMMMUIdx mmu_idx = arm_mmu_idx(env); - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx)); cpu_stl_mmu(env, sp, nextinst, oi, GETPC()); cpu_stl_mmu(env, sp + 4, saved_psr, oi, GETPC()); @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlstm)(CPUARMState *env, uint32_t fptr) bool lspact = env->v7m.fpccr[s] & R_V7M_FPCCR_LSPACT_MASK; uintptr_t ra = GETPC(); ARMMMUIdx mmu_idx = arm_mmu_idx(env); - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx)); assert(env->v7m.secure); @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_vlldm)(CPUARMState *env, uint32_t fptr) ARMCPU *cpu = env_archcpu(env); uintptr_t ra = GETPC(); ARMMMUIdx mmu_idx = arm_mmu_idx(env); - MemOpIdx oi = make_memop_idx(MO_TE | MO_UL | MO_ALIGN, + MemOpIdx oi = make_memop_idx(mo_endian(env) | MO_UL | MO_ALIGN, arm_to_core_mmu_idx(mmu_idx)); /* fptr is the value of Rn, the frame pointer we load the FP regs from */ -- 2.43.0 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: 20260414005348.4767-10-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/m_helper.c | 2 +- target/arm/tcg/meson.build | 3 ++- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/m_helper.c b/target/arm/tcg/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/m_helper.c +++ b/target/arm/tcg/m_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/log.h" #include "exec/page-protection.h" #ifdef CONFIG_TCG -#include "accel/tcg/cpu-ldst.h" +#include "accel/tcg/cpu-ldst-common.h" #include "semihosting/common-semi.h" #endif #if !defined(CONFIG_USER_ONLY) diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/meson.build +++ b/target/arm/tcg/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'TARGET_AARCH64', if_false: files('stubs32.c')) arm_ss.add(files( 'cpu32.c', - 'm_helper.c', )) arm_ss.add(when: 'TARGET_AARCH64', if_true: files( @@ -XXX,XX +XXX,XX @@ arm_common_system_ss.add( 'debug.c', 'hflags.c', 'gengvec.c', + 'm_helper.c', 'mve_helper.c', 'neon_helper.c', 'op_helper.c', @@ -XXX,XX +XXX,XX @@ arm_user_ss.add( 'debug.c', 'gengvec.c', 'hflags.c', + 'm_helper.c', 'mve_helper.c', 'neon_helper.c', 'op_helper.c', -- 2.43.0 From: Thomas Huth <thuth@redhat.com> When writing to this register, QEMU currently aborts: $ echo "readl 0x10000018" | ./qemu-system-arm -audiodev none,id=snd0 \ -M integratorcp,accel=qtest,audiodev=snd0 -display none -qtest stdio [I 0.000000] OPENED [R +0.001907] readl 0x10000018 qemu: hardware error: integratorcm_read: CM_LMBUSCNT [...] Aborted (core dumped) This is bad, a guest should ideally never be able to kill QEMU like this. Now, according to the "Intergrator/CP User Guide" from: https://developer.arm.com/documentation/dui0159/b/porting-integrator-ap-and-im-pd1/registers "The Integrator/AP CM_LMBUSCNT has been removed." That means this register does not seem to be implemented on real CP boards at all, only for older AP boards. Thus it should be fine if we simply ignore this register in QEMU and handle it like all other unimplemented registers in the "default" handler of the case statement. Resolves: https://gitlab.com/qemu-project/qemu/-/work_items/3407 Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20260420064933.64765-1-thuth@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/integratorcp.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/hw/arm/integratorcp.c b/hw/arm/integratorcp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/integratorcp.c +++ b/hw/arm/integratorcp.c @@ -XXX,XX +XXX,XX @@ static uint64_t integratorcm_read(void *opaque, hwaddr offset, } else { return s->cm_lock; } - case 6: /* CM_LMBUSCNT */ - /* ??? High frequency timer. */ - hw_error("integratorcm_read: CM_LMBUSCNT"); case 7: /* CM_AUXOSC */ return s->cm_auxosc; case 8: /* CM_SDRAM */ -- 2.43.0 include/hw/arm/primecell.h used to be more expansive, but now the only thing it defines is the ARM_SYSCTL_GPIO_* constants for the GPIO lines for the arm-sysctl system-control device used on the Realview, Versatile and Versatile Express boards. Replace it with a header file specific to that device. virt.c and vmapple.c included primecell.h despite not using the constants it defined; there we can simply drop the include entirely. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20260416172627.690396-1-peter.maydell@linaro.org --- MAINTAINERS | 2 +- hw/arm/realview.c | 2 +- hw/arm/vexpress.c | 2 +- hw/arm/virt.c | 1 - hw/misc/arm_sysctl.c | 2 +- hw/vmapple/vmapple.c | 1 - include/hw/arm/primecell.h | 12 ------------ include/hw/misc/arm_sysctl.h | 16 ++++++++++++++++ 8 files changed, 20 insertions(+), 18 deletions(-) delete mode 100644 include/hw/arm/primecell.h create mode 100644 include/hw/misc/arm_sysctl.h diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/ssi/pl022.c F: include/hw/ssi/pl022.h F: hw/rtc/pl031.c F: include/hw/rtc/pl031.h -F: include/hw/arm/primecell.h F: hw/timer/cmsdk-apb-timer.c F: include/hw/timer/cmsdk-apb-timer.h F: tests/qtest/cmsdk-apb-timer-test.c @@ -XXX,XX +XXX,XX @@ F: hw/*/versatile* F: hw/i2c/arm_sbcon_i2c.c F: include/hw/i2c/arm_sbcon_i2c.h F: hw/misc/arm_sysctl.c +F: include/hw/misc/arm_sysctl.h F: docs/system/arm/versatile.rst Virt diff --git a/hw/arm/realview.c b/hw/arm/realview.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/realview.c +++ b/hw/arm/realview.c @@ -XXX,XX +XXX,XX @@ #include "target/arm/cpu.h" #include "hw/core/sysbus.h" #include "hw/arm/boot.h" -#include "hw/arm/primecell.h" #include "hw/arm/machines-qom.h" #include "hw/core/split-irq.h" +#include "hw/misc/arm_sysctl.h" #include "hw/net/lan9118.h" #include "hw/net/smc91c111.h" #include "hw/pci/pci.h" 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 @@ #include "qemu/datadir.h" #include "hw/core/sysbus.h" #include "hw/arm/boot.h" -#include "hw/arm/primecell.h" #include "hw/arm/machines-qom.h" +#include "hw/misc/arm_sysctl.h" #include "hw/net/lan9118.h" #include "hw/i2c/i2c.h" #include "net/net.h" diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ #include "monitor/qdev.h" #include "hw/core/sysbus.h" #include "hw/arm/boot.h" -#include "hw/arm/primecell.h" #include "hw/arm/virt.h" #include "hw/arm/machines-qom.h" #include "hw/block/flash.h" diff --git a/hw/misc/arm_sysctl.c b/hw/misc/arm_sysctl.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/arm_sysctl.c +++ b/hw/misc/arm_sysctl.c @@ -XXX,XX +XXX,XX @@ #include "system/runstate.h" #include "qemu/bitops.h" #include "hw/core/sysbus.h" +#include "hw/misc/arm_sysctl.h" #include "migration/vmstate.h" -#include "hw/arm/primecell.h" #include "qemu/log.h" #include "qemu/module.h" #include "qom/object.h" diff --git a/hw/vmapple/vmapple.c b/hw/vmapple/vmapple.c index XXXXXXX..XXXXXXX 100644 --- a/hw/vmapple/vmapple.c +++ b/hw/vmapple/vmapple.c @@ -XXX,XX +XXX,XX @@ #include "hw/core/sysbus.h" #include "hw/usb/usb.h" #include "hw/arm/boot.h" -#include "hw/arm/primecell.h" #include "hw/char/pl011.h" #include "hw/intc/arm_gic.h" #include "hw/intc/arm_gicv3_common.h" diff --git a/include/hw/arm/primecell.h b/include/hw/arm/primecell.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/include/hw/arm/primecell.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -#ifndef PRIMECELL_H -#define PRIMECELL_H - -/* Declarations for ARM PrimeCell based periperals. */ -/* Also includes some devices that are currently only used by the - ARM boards. */ - -/* arm_sysctl GPIO lines */ -#define ARM_SYSCTL_GPIO_MMC_WPROT 0 -#define ARM_SYSCTL_GPIO_MMC_CARDIN 1 - -#endif diff --git a/include/hw/misc/arm_sysctl.h b/include/hw/misc/arm_sysctl.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/arm_sysctl.h @@ -XXX,XX +XXX,XX @@ +/* + * Status and system control registers for ARM RealView/Versatile boards. + * + * Copyright (c) Linaro Ltd + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef HW_MISC_ARM_SYSCTL_H +#define HW_MISC_ARM_SYSCTL_H + +/* arm_sysctl inbound GPIO lines */ +#define ARM_SYSCTL_GPIO_MMC_WPROT 0 +#define ARM_SYSCTL_GPIO_MMC_CARDIN 1 + +#endif -- 2.43.0 If we create a normally-AArch64 CPU and configure it with aarch64=off, this will by default leave all the AArch64 ID register values in its ARMISARegisters struct untouched. That in turn means that tests of cpu_isar_feature(aa64_something, cpu) will return true. Until now we have had a design policy that you shouldn't check an aa64_ feature unless you know that the CPU has AArch64; but this is quite fragile as it's easy to forget and only causes a problem in the corner case where AArch64 was turned off. In particular, when we extend the ability to disable AArch64 from only KVM to also TCG there are many more aa64 feature check points which we would otherwise have to audit for whether they needed to be guarded with a check on ARM_FEATURE_AARCH64. Instead, make the CPU realize function zero out all the 64-bit ID registers if a TCG CPU doesn't have AArch64; this will make aa64_ feature tests generally return false. We only do this for TCG because only TCG really needs it, and for KVM it might be confusing to have QEMU's idea of the ID registers be different from KVM's. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20260416165353.589569-2-peter.maydell@linaro.org --- target/arm/cpu.c | 35 +++++++++++++++++++++++++++++++++++ target/arm/cpu.h | 3 ++- 2 files changed, 37 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 @@ void arm_cpu_finalize_features(ARMCPU *cpu, Error **errp) } } +static void arm_clear_aarch64_idregs(ARMCPU *cpu) +{ + /* Zero out all the AArch64 ID registers in ARMISARegisters */ + SET_IDREG(&cpu->isar, ID_AA64ISAR0, 0); + SET_IDREG(&cpu->isar, ID_AA64ISAR1, 0); + SET_IDREG(&cpu->isar, ID_AA64ISAR2, 0); + SET_IDREG(&cpu->isar, ID_AA64PFR0, 0); + SET_IDREG(&cpu->isar, ID_AA64PFR1, 0); + SET_IDREG(&cpu->isar, ID_AA64PFR2, 0); + SET_IDREG(&cpu->isar, ID_AA64MMFR0, 0); + SET_IDREG(&cpu->isar, ID_AA64MMFR1, 0); + SET_IDREG(&cpu->isar, ID_AA64MMFR2, 0); + SET_IDREG(&cpu->isar, ID_AA64MMFR3, 0); + SET_IDREG(&cpu->isar, ID_AA64DFR0, 0); + SET_IDREG(&cpu->isar, ID_AA64DFR1, 0); + SET_IDREG(&cpu->isar, ID_AA64AFR0, 0); + SET_IDREG(&cpu->isar, ID_AA64AFR1, 0); + SET_IDREG(&cpu->isar, ID_AA64ZFR0, 0); + SET_IDREG(&cpu->isar, ID_AA64SMFR0, 0); +} + static void arm_cpu_realizefn(DeviceState *dev, Error **errp) { CPUState *cs = CPU(dev); @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) } #endif + /* + * A TCG aarch64=off CPU has no AArch64 at all, so we clear out the + * ID registers to avoid cpu_isar_feature(aa64_something, cpu) tests + * incorrectly returning true. We don't do this for other accelerators + * (which in practice means "for KVM", since no others have AArch32 + * guest support) because from KVM's point of view the AArch64 ID + * registers still exist and must have their correct values. So we + * avoid clearing them out so that we don't have QEMU and KVM with + * different ideas of the ID registers. + */ + if (tcg_enabled() && !arm_feature(env, ARM_FEATURE_AARCH64)) { + arm_clear_aarch64_idregs(cpu); + } + #ifdef CONFIG_USER_ONLY /* * User mode relies on IC IVAU instructions to catch modification of 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 @@ struct ArchCPU { * Note that if you add an ID register to the ARMISARegisters struct * you need to also update the 32-bit and 64-bit versions of the * kvm_arm_get_host_cpu_features() function to correctly populate the - * field by reading the value from the KVM vCPU. + * field by reading the value from the KVM vCPU. If it is an AArch64 + * ID register then you also must update arm_clear_aarch64_idregs(). */ struct ARMISARegisters { uint32_t mvfr0; -- 2.43.0 Allow the 'aarch64=off' property, which is currently KVM-only, to be set for TCG CPUs also. Note that we don't permit it on the qemu-aarch64 user-mode binary: this makes no sense as that executable can only handle AArch64 syscalls (and it would also assert at startup since it doesn't compile in the A32-specific GDB xml files like arm-neon.xml). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Clément Chigot <chigot@adacore.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20260416165353.589569-3-peter.maydell@linaro.org --- docs/system/arm/cpu-features.rst | 10 +++++---- target/arm/cpu-features.h | 5 +++++ target/arm/cpu.c | 36 ++++++++++++++++++++++++++++---- tests/qtest/arm-cpu-features.c | 8 ++----- 4 files changed, 45 insertions(+), 14 deletions(-) diff --git a/docs/system/arm/cpu-features.rst b/docs/system/arm/cpu-features.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/cpu-features.rst +++ b/docs/system/arm/cpu-features.rst @@ -XXX,XX +XXX,XX @@ not implement ARMv8-A, will not have the ``aarch64`` CPU property. QEMU's support may be limited for some CPU features, only partially supporting the feature or only supporting the feature under certain configurations. For example, the ``aarch64`` CPU feature, which, when -disabled, enables the optional AArch32 CPU feature, is only supported -when using the KVM accelerator and when running on a host CPU type that -supports the feature. While ``aarch64`` currently only works with KVM, -it could work with TCG. CPU features that are specific to KVM are +disabled, enables the optional AArch32 CPU feature, can only be set to +``off`` on the TCG and KVM accelerators, and it cannot be set to +``off`` under KVM unless running on a host CPU type that supports +running guests in AArch32. + +CPU features that are inherently specific to KVM are prefixed with "kvm-" and are described in "KVM VCPU Features". CPU Feature Probing diff --git a/target/arm/cpu-features.h b/target/arm/cpu-features.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu-features.h +++ b/target/arm/cpu-features.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_aa32_el2(const ARMISARegisters *id) return FIELD_EX64_IDREG(id, ID_AA64PFR0, EL2) >= 2; } +static inline bool isar_feature_aa64_aa32_el3(const ARMISARegisters *id) +{ + return FIELD_EX64_IDREG(id, ID_AA64PFR0, EL3) >= 2; +} + static inline bool isar_feature_aa64_ras(const ARMISARegisters *id) { return FIELD_EX64_IDREG(id, ID_AA64PFR0, RAS) != 0; 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_set_aarch64(Object *obj, bool value, Error **errp) * uniform execution state like do_interrupt. */ if (value == false) { - if (!kvm_enabled() || !kvm_arm_aarch32_supported()) { - error_setg(errp, "'aarch64' feature cannot be disabled " - "unless KVM is enabled and 32-bit EL1 " - "is supported"); + if (kvm_enabled()) { + if (!kvm_arm_aarch32_supported()) { + error_setg(errp, "'aarch64' feature cannot be disabled for KVM " + "because this host does not support 32-bit EL1"); + return; + } + } else if (tcg_enabled()) { +#ifdef CONFIG_USER_ONLY + error_setg(errp, "'aarch64' feature cannot be disabled for " + "usermode emulator qemu-aarch64; use qemu-arm instead"); + return; +#else + bool aa32_at_highest_el; + if (arm_feature(&cpu->env, ARM_FEATURE_EL3)) { + aa32_at_highest_el = cpu_isar_feature(aa64_aa32_el3, cpu); + } else if (arm_feature(&cpu->env, ARM_FEATURE_EL2)) { + aa32_at_highest_el = cpu_isar_feature(aa64_aa32_el2, cpu); + } else { + aa32_at_highest_el = cpu_isar_feature(aa64_aa32_el1, cpu); + } + + if (!aa32_at_highest_el) { + error_setg(errp, "'aarch64' feature cannot be disabled for " + "this TCG CPU because it does not support 32-bit " + "execution at its highest implemented exception " + "level"); + return; + } +#endif + } else { + error_setg(errp, "'aarch64' feature cannot be disabled for " + "this accelerator"); return; } unset_feature(&cpu->env, ARM_FEATURE_AARCH64); diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/arm-cpu-features.c +++ b/tests/qtest/arm-cpu-features.c @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion(const void *data) sve_tests_default(qts, "max"); pauth_tests_default(qts, "max"); - /* Test that features that depend on KVM generate errors without. */ - assert_error(qts, "max", - "'aarch64' feature cannot be disabled " - "unless KVM is enabled and 32-bit EL1 " - "is supported", - "{ 'aarch64': false }"); + /* TCG allows us to turn off AArch64 on the 'max' CPU type */ + assert_set_feature(qts, "max", "aarch64", false); } qtest_quit(qts); -- 2.43.0 Add a basic test of the TCG 'aarch64=off' functionality; this is the same as our existing arm/test_virt test, but it runs the AArch32 guest kernel on qemu-system-aarch64 with -cpu max,aarch64=off. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20260416165353.589569-4-peter.maydell@linaro.org --- tests/functional/aarch64/meson.build | 1 + .../aarch64/test_virt_aarch64_off.py | 37 +++++++++++++++++++ 2 files changed, 38 insertions(+) create mode 100755 tests/functional/aarch64/test_virt_aarch64_off.py diff --git a/tests/functional/aarch64/meson.build b/tests/functional/aarch64/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/functional/aarch64/meson.build +++ b/tests/functional/aarch64/meson.build @@ -XXX,XX +XXX,XX @@ tests_aarch64_system_thorough = [ 'tcg_plugins', 'tuxrun', 'virt', + 'virt_aarch64_off', 'virt_gpu', 'virt_vbsa', 'xen', diff --git a/tests/functional/aarch64/test_virt_aarch64_off.py b/tests/functional/aarch64/test_virt_aarch64_off.py new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/functional/aarch64/test_virt_aarch64_off.py @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env python3 +# +# Functional test that boots an AArch32 Linux kernel and checks the console +# on a TCG aarch64 CPU with aarch64=off. This is the same image etc +# as we use in tests/functional/arm/test_virt.py. +# +# SPDX-License-Identifier: GPL-2.0-or-later + +from qemu_test import LinuxKernelTest, Asset + +class ArmVirtMachine(LinuxKernelTest): + + ASSET_KERNEL = Asset( + ('https://archives.fedoraproject.org/pub/archive/fedora/linux/' + 'releases/29/Everything/armhfp/os/images/pxeboot/vmlinuz'), + '18dd5f1a9a28bd539f9d047f7c0677211bae528e8712b40ca5a229a4ad8e2591') + + def test_arm_virt(self): + self.set_machine('virt') + # KVM aarch64=off requires a host CPU that supports it, so + # restrict the test to TCG only + self.require_accelerator('tcg') + self.vm.add_args('-cpu', 'max,aarch64=off') + + kernel_path = self.ASSET_KERNEL.fetch() + + self.vm.set_console() + kernel_command_line = (self.KERNEL_COMMON_COMMAND_LINE + + 'console=ttyAMA0') + self.vm.add_args('-kernel', kernel_path, + '-append', kernel_command_line) + self.vm.launch() + console_pattern = 'Kernel command line: %s' % kernel_command_line + self.wait_for_console_pattern(console_pattern) + +if __name__ == '__main__': + LinuxKernelTest.main() -- 2.43.0 From: Eric Auger <eric.auger@redhat.com> We introduce a datatype for a tolerance with respect to a given cpreg migration issue. The tolerance applies to a given cpreg kvm index, and can be of different types: a) mismatch in cpreg indexes - ToleranceNotOnBothEnds (cpreg index is allowed to be only present on one end) - ToleranceOnlySrcTestValue (cpreg index is allowed to be only present in source if its value @mask field matches @value) b) mismatch in cpreg values - ToleranceDiffInMask (value differences are allowed only within a mask) - ToleranceFieldLT (incoming field value must be less than a given value) - ToleranceFieldGT (incoming field value must be greater than a given value) A QLIST of such tolerances can be populated using a new helper: arm_register_cpreg_mig_tolerance() and arm_cpu_match_cpreg_mig_tolerance() allows to check whether a tolerance exists for a given kvm index and its criterion is matched. callers for those helpers will be introduced in subsequent patches. Only registration of migration tolerances related to cpreg index mismatch is currently allowed. Signed-off-by: Eric Auger <eric.auger@redhat.com> Message-id: 20260420140552.104369-2-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 82 ++++++++++++++++++++++++++++++++++++++++++ target/arm/cpu.h | 1 + target/arm/internals.h | 54 ++++++++++++++++++++++++++++ 3 files changed, 137 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 @@ void arm_register_el_change_hook(ARMCPU *cpu, ARMELChangeHookFn *hook, QLIST_INSERT_HEAD(&cpu->el_change_hooks, entry, node); } +static ARMCPRegMigTolerance *find_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx) +{ + ARMCPRegMigTolerance *t; + QLIST_FOREACH(t, &cpu->cpreg_mig_tolerances, node) { + if (t->kvmidx == kvmidx) { + return t; + } + } + return NULL; +} + +void arm_register_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx, + uint64_t mask, uint64_t value, + ARMCPRegMigToleranceType type) +{ + ARMCPRegMigTolerance *entry; + + /* make sure the kvmidx has not tolerance already registered */ + assert(!find_mig_tolerance(cpu, kvmidx)); + + assert(type == ToleranceNotOnBothEnds || + type == ToleranceOnlySrcTestValue); + + entry = g_new0(ARMCPRegMigTolerance, 1); + + entry->kvmidx = kvmidx; + entry->mask = mask; + entry->value = value; + entry->type = type; + + QLIST_INSERT_HEAD(&cpu->cpreg_mig_tolerances, entry, node); +} + +bool arm_cpu_match_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx, + uint64_t vmstate_value, uint64_t local_value, + ARMCPRegMigToleranceType type) +{ + ARMCPRegMigTolerance *t = find_mig_tolerance(cpu, kvmidx); + uint64_t diff, diff_outside_mask, field; + + if (!t || t->type != type) { + return false; + } + + if (type == ToleranceNotOnBothEnds) { + return true; + } + + if (type == ToleranceOnlySrcTestValue && + ((vmstate_value & t->mask) == t->value)) { + return true; + } + + /* Need to check the mask */ + diff = vmstate_value ^ local_value; + diff_outside_mask = diff & ~t->mask; + + if (diff_outside_mask) { + /* there are differences outside of the mask */ + return false; + } + if (type == ToleranceDiffInMask) { + /* differences only in the field, tolerance matched */ + return true; + } + /* need to compare field value against authorized ones */ + field = vmstate_value & t->mask; + if (type == ToleranceFieldLT && (field < t->value)) { + return true; + } + if (type == ToleranceFieldGT && (field > t->value)) { + return true; + } + return false; +} + static void cp_reg_reset(gpointer key, gpointer value, gpointer opaque) { /* Reset a single ARMCPRegInfo register */ @@ -XXX,XX +XXX,XX @@ static void arm_cpu_initfn(Object *obj) QLIST_INIT(&cpu->pre_el_change_hooks); QLIST_INIT(&cpu->el_change_hooks); + QLIST_INIT(&cpu->cpreg_mig_tolerances); #ifdef CONFIG_USER_ONLY # ifdef TARGET_AARCH64 @@ -XXX,XX +XXX,XX @@ static void arm_cpu_finalizefn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); ARMELChangeHook *hook, *next; + ARMCPRegMigTolerance *t, *n; g_hash_table_destroy(cpu->cp_regs); @@ -XXX,XX +XXX,XX @@ static void arm_cpu_finalizefn(Object *obj) QLIST_REMOVE(hook, node); g_free(hook); } + QLIST_FOREACH_SAFE(t, &cpu->cpreg_mig_tolerances, node, n) { + QLIST_REMOVE(t, node); + g_free(t); + } #ifndef CONFIG_USER_ONLY if (cpu->pmu_timer) { timer_free(cpu->pmu_timer); 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 @@ struct ArchCPU { QLIST_HEAD(, ARMELChangeHook) pre_el_change_hooks; QLIST_HEAD(, ARMELChangeHook) el_change_hooks; + QLIST_HEAD(, ARMCPRegMigTolerance) cpreg_mig_tolerances; int32_t node_id; /* NUMA node this CPU belongs to */ diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ int compare_u64(const void *a, const void *b); /* Used in FEAT_MEC to set the MECIDWidthm1 field in the MECIDR_EL2 register. */ #define MECID_WIDTH 16 +typedef enum { + ToleranceNotOnBothEnds, + ToleranceOnlySrcTestValue, + ToleranceDiffInMask, + ToleranceFieldLT, + ToleranceFieldGT, +} ARMCPRegMigToleranceType; + +typedef struct ARMCPRegMigTolerance { + uint64_t kvmidx; + uint64_t mask; + uint64_t value; + ARMCPRegMigToleranceType type; + QLIST_ENTRY(ARMCPRegMigTolerance) node; +} ARMCPRegMigTolerance; + +/** + * arm_register_cpreg_mig_tolerance: + * Register a migration tolerance wrt one given cpreg identified by its + * @kvmidx. Calling this function twice for the same @kvmidx is a + * programming error and will cause an assertion failure. + * + * @cpu: vcpu to apply the migration tolerance on + * @kvmidx: kvm index of the cpreg the tolerance applies to + * @mask: bitmask where a difference is tolerated + * (relevant with ToleranceDiffInMask) + * @value: value the bitmask field is compared with + * (relevant with ToleranceFieldLT and ToleranceFieldGT) + * @type: type of the migration tolerance: + * - ToleranceNotOnBothEnds (cpreg index is allowed to be only present + * on one end) + * - ToleranceOnlySrcTestValue (cpreg index is allowed to be only + * present in source if its value @mask field matches @value) + * - ToleranceDiffInMask (mismatch in cpreg values are only tolerated + * if differences are within @mask) + * - ToleranceFieldLT (mismatch in cpreg values are only tolerated + * if incoming @bitmask field value is less than @value) + * - ToleranceFieldGT (mismatch in cpreg values are only tolerated + * if incoming @bitmask field value is greater than @value) + */ +void arm_register_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx, + uint64_t mask, uint64_t value, + ARMCPRegMigToleranceType type); + +/** + * arm_cpu_match_cpreg_mig_tolerance: + * Check whether a tolerance of type @type exists for a given @kvmidx + * and the tolerance criterion is satisfied + */ +bool arm_cpu_match_cpreg_mig_tolerance(ARMCPU *cpu, uint64_t kvmidx, + uint64_t vmstate_value, uint64_t local_value, + ARMCPRegMigToleranceType type); + + #endif -- 2.43.0 From: Eric Auger <eric.auger@redhat.com> If there is a mismatch between the cpreg indexes found on both ends, check whether a tolerance was registered for the given kvmidx. If any, silence warning/errors. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20260420140552.104369-3-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/machine.c | 21 +++++++++++++++------ target/arm/trace-events | 2 ++ 2 files changed, 17 insertions(+), 6 deletions(-) diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static void handle_cpreg_missing_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx { g_autofree gchar *name = print_register_name(kvmidx); + if (arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx, + 0, 0, ToleranceNotOnBothEnds)) { + trace_tolerate_cpreg_missing_in_incoming_stream(name); + return; + } warn_report("%s: %s " "expected by the destination but not in the incoming stream: " "skip it", __func__, name); } /* - * Handle the situation where @kvmidx is in the incoming stream - * but not on destination. This currently fails the migration but - * we plan to accomodate some exceptions, hence the boolean returned value. + * Handle the situation where @kvmidx is in the incoming + * stream but not on destination. This fails the migration if + * no cpreg mig tolerance is matched for this @kvmidx + * Return true if the migration should eventually fail */ static bool handle_cpreg_only_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx) { g_autofree gchar *name = print_register_name(kvmidx); - bool fail = true; + if (arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx, + 0, 0, ToleranceNotOnBothEnds)) { + trace_tolerate_cpreg_only_in_incoming_stream(name); + return false; + } error_report("%s: %s in the incoming stream but unknown on the " "destination: fail migration", __func__, name); - - return fail; + return true; } static int cpu_post_load(void *opaque, int version_id) diff --git a/target/arm/trace-events b/target/arm/trace-events index XXXXXXX..XXXXXXX 100644 --- a/target/arm/trace-events +++ b/target/arm/trace-events @@ -XXX,XX +XXX,XX @@ arm_psci_call(uint64_t x0, uint64_t x1, uint64_t x2, uint64_t x3, uint32_t cpuid # machine.c cpu_post_load(uint32_t cpreg_vmstate_array_len, uint32_t cpreg_array_len) "cpreg_vmstate_array_len=%d cpreg_array_len=%d" +tolerate_cpreg_missing_in_incoming_stream(char *name) "%s is missing in incoming stream but this is explicitly tolerated" +tolerate_cpreg_only_in_incoming_stream(char *name) "%s is in incoming stream but not on destination but this is explicitly tolerated" -- 2.43.0 From: Eric Auger <eric.auger@redhat.com> Pass the value of the incoming register to handle_cpreg_only_in_incoming_stream and check whether there is a matching ToleranceOnlySrcTestValue tolerance. Signed-off-by: Eric Auger <eric.auger@redhat.com> Message-id: 20260420140552.104369-4-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/machine.c | 14 ++++++++++---- 1 file changed, 10 insertions(+), 4 deletions(-) diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static void handle_cpreg_missing_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx * no cpreg mig tolerance is matched for this @kvmidx * Return true if the migration should eventually fail */ -static bool handle_cpreg_only_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx) +static bool +handle_cpreg_only_in_incoming_stream(ARMCPU *cpu, uint64_t kvmidx, uint64_t value) { g_autofree gchar *name = print_register_name(kvmidx); if (arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx, - 0, 0, ToleranceNotOnBothEnds)) { + 0, 0, ToleranceNotOnBothEnds) || + arm_cpu_match_cpreg_mig_tolerance(cpu, kvmidx, + value, 0, ToleranceOnlySrcTestValue)) { trace_tolerate_cpreg_only_in_incoming_stream(name); return false; } @@ -XXX,XX +XXX,XX @@ static int cpu_post_load(void *opaque, int version_id) } if (cpu->cpreg_vmstate_indexes[v] < cpu->cpreg_indexes[i]) { fail = handle_cpreg_only_in_incoming_stream(cpu, - cpu->cpreg_vmstate_indexes[v++]); + cpu->cpreg_vmstate_indexes[v], + cpu->cpreg_vmstate_values[v]); + v++; continue; } /* matching register, copy the value over */ @@ -XXX,XX +XXX,XX @@ static int cpu_post_load(void *opaque, int version_id) */ for ( ; v < cpu->cpreg_vmstate_array_len; v++) { fail = handle_cpreg_only_in_incoming_stream(cpu, - cpu->cpreg_vmstate_indexes[v]); + cpu->cpreg_vmstate_indexes[v], + cpu->cpreg_vmstate_values[v]); } if (fail) { return -1; -- 2.43.0 From: Eric Auger <eric.auger@redhat.com> Before linux v6.13 those registers were erroneously unconditionally exposed and this was fixed by commits: - 0fcb4eea5345 ("KVM: arm64: Hide TCR2_EL1 from userspace when disabled for guests") - a68cddbe47ef ("KVM: arm64: Hide S1PIE registers from userspace when disabled for guests") in v6.13. This means if we migrate from an old kernel host to a >= 6.13 kernel host, migration currently fails. Declare cpreg migration tolerance for those registers. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Sebastian Ott <sebott@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20260420140552.104369-5-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) 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_a53_initfn(Object *obj) define_cortex_a72_a57_a53_cp_reginfo(cpu); } +#if defined(CONFIG_KVM) +static void kvm_arm_set_cpreg_mig_tolerances(ARMCPU *cpu) +{ + /* + * Registers that may be in the incoming stream and not exposed + * on the destination + */ + + /* + * TCR_EL1 was erroneously unconditionnally exposed before linux v6.13. + * See commit 0fcb4eea5345 ("KVM: arm64: Hide TCR2_EL1 from userspace + * when disabled for guests") + */ + arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 2, 0, 3), + 0, 0, ToleranceNotOnBothEnds); + /* + * PIRE0_EL1 and PIR_EL1 were erroneously unconditionnally exposed + * before linux v6.13. See commit a68cddbe47ef ("KVM: arm64: Hide + * S1PIE registers from userspace when disabled for guests") + */ + arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 10, 2, 2), + 0, 0, ToleranceNotOnBothEnds); + arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 10, 2, 3), + 0, 0, ToleranceNotOnBothEnds); +} +#endif + static void aarch64_host_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); @@ -XXX,XX +XXX,XX @@ static void aarch64_host_initfn(Object *obj) #endif #if defined(CONFIG_KVM) + kvm_arm_set_cpreg_mig_tolerances(cpu); kvm_arm_set_cpu_features_from_host(cpu); aarch64_add_sve_properties(obj); #elif defined(CONFIG_HVF) -- 2.43.0 From: Eric Auger <eric.auger@redhat.com> KVM_REG_ARM_VENDOR_HYP_BMAP_2 pseudo FW register is exposed from v6.15 onwards. Backward migration from a >= v6.15 to an older kernel would fail without cpreg migration tolerance definition for this register. If the register is present on source but not on destination, its value must be checked to make sure it matches the reset value, ie. 0, meaning no service is exposed to the guest, hence the choice of a ToleranceOnlySrcTestValue migration tolerance. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20260420140552.104369-6-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 11 +++++++++++ 1 file changed, 11 insertions(+) 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 kvm_arm_set_cpreg_mig_tolerances(ARMCPU *cpu) 0, 0, ToleranceNotOnBothEnds); arm_register_cpreg_mig_tolerance(cpu, ARM64_SYS_REG(3, 0, 10, 2, 3), 0, 0, ToleranceNotOnBothEnds); + + /* + * KVM_REG_ARM_VENDOR_HYP_BMAP_2 pseudo FW register is exposed + * from v6.15 onwards. Backward migration from a >= v6.15 to an older + * kernel would fail without cpreg migration tolerance definition. + * If the register is present on source but not on destination, make + * sure it has its reset value, ie. 0, meaning no service is exposed + * to the guest. + */ + arm_register_cpreg_mig_tolerance(cpu, KVM_REG_ARM_FW_FEAT_BMAP_REG(3), + UINT64_MAX, 0, ToleranceOnlySrcTestValue); } #endif -- 2.43.0 From: Eric Auger <eric.auger@redhat.com> We want to remove AArch32 DBGDTRTX which was erroneously exposed. This was attempted by 655659a74a36b ("target/arm: Correct encoding of Debug Communications Channel registers") but it was discovered that the removal of this debug register broke forward migration on TCG. Now we have the cpreg migration tolerance infrastructure, we can declare one for the DBGDTRTX. This allow to revert the reinstate patch. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Sebastian Ott <sebott@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20260420140552.104369-7-eric.auger@redhat.com [PMM: revised comment, included note about when we can drop the workaround] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 23 +++++++++++++++++++++++ 1 file changed, 23 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 @@ void register_cp_regs_for_features(ARMCPU *cpu) .fgt = FGT_CLIDR_EL1, .resetvalue = GET_IDREG(isar, CLIDR) }; + uint64_t dbgtr_el0_kvmidx = + cpreg_to_kvm_id(ENCODE_CP_REG(14, 0, 1, 0, 5, 3, 0)); + define_one_arm_cp_reg(cpu, &clidr); define_arm_cp_regs(cpu, v7_cp_reginfo); define_debug_regs(cpu); + /* + * We used to incorrectly expose a non-existent AArch32 "DBGDTRTX" + * register with this encoding. This has been fixed by commit + * 655659a74a36 ("target/arm: Correct encoding of Debug + * Communications Channel registers") by the introduction of correct + * separate cpreg definitions for AA64 and AA32 versions. However, + * the old cpreg definition couldn't be removed without breaking + * migration, so commit 4f2b82f604 reinstated the bogus encoding + * for migration data only. + * + * Now that we have migration tolerance infrastructure, we can use + * this to allow forward migration from the buggy QEMU versions, + * accepting and ignoring the bogus register if it is in the + * source data. QEMU 11.0 was the last version that sent the + * bogus encoding, so this workaround can be removed at the point + * where we no longer care about migration from that version + * (i.e. when we remove the "virt-11.0" machine type). + */ + arm_register_cpreg_mig_tolerance(cpu, dbgtr_el0_kvmidx, + 0, 0, ToleranceNotOnBothEnds); } else { define_arm_cp_regs(cpu, not_v7_cp_reginfo); } -- 2.43.0 From: Eric Auger <eric.auger@redhat.com> This reverts commit 4f2b82f60431 ("target/arm: Reinstate bogus AArch32 DBGDTRTX register for migration compat). We don't need that commit anymore as the AArch32 DBGDTRTX register is declared to be safe to ignore in the incoming migration stream. Signed-off-by: Eric Auger <eric.auger@redhat.com> Reviewed-by: Sebastian Ott <sebott@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20260420140552.104369-8-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/debug_helper.c | 29 ----------------------------- 1 file changed, 29 deletions(-) diff --git a/target/arm/debug_helper.c b/target/arm/debug_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/debug_helper.c +++ b/target/arm/debug_helper.c @@ -XXX,XX +XXX,XX @@ static void dbgclaimclr_write(CPUARMState *env, const ARMCPRegInfo *ri, env->cp15.dbgclaim &= ~(value & 0xFF); } -static CPAccessResult access_bogus(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread) -{ - /* Always UNDEF, as if this cpreg didn't exist */ - return CP_ACCESS_UNDEFINED; -} - static const ARMCPRegInfo debug_cp_reginfo[] = { /* * DBGDRAR, DBGDSAR: always RAZ since we don't implement memory mapped @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo debug_cp_reginfo[] = { .opc0 = 2, .opc1 = 3, .crn = 0, .crm = 4, .opc2 = 0, .access = PL0_RW, .accessfn = access_tdcc, .type = ARM_CP_CONST, .resetvalue = 0 }, - /* - * This is not a real AArch32 register. We used to incorrectly expose - * this due to a QEMU bug; to avoid breaking migration compatibility we - * need to continue to provide it so that we don't fail the inbound - * migration when it tells us about a sysreg that we don't have. - * We set an always-fails .accessfn, which means that the guest doesn't - * actually see this register (it will always UNDEF, identically to if - * there were no cpreg definition for it other than that we won't print - * a LOG_UNIMP message about it), and we set the ARM_CP_NO_GDB flag so the - * gdbstub won't see it either. - * (We can't just set .access = 0, because add_cpreg_to_hashtable() - * helpfully ignores cpregs which aren't accessible to the highest - * implemented EL.) - * - * TODO: implement a system for being able to describe "this register - * can be ignored if it appears in the inbound stream"; then we can - * remove this temporary hack. - */ - { .name = "BOGUS_DBGDTR_EL0", .state = ARM_CP_STATE_AA32, - .cp = 14, .opc1 = 3, .crn = 0, .crm = 5, .opc2 = 0, - .access = PL0_RW, .accessfn = access_bogus, - .type = ARM_CP_CONST | ARM_CP_NO_GDB, .resetvalue = 0 }, /* * OSECCR_EL1 provides a mechanism for an operating system * to access the contents of EDECCR. EDECCR is not implemented though, -- 2.43.0 From: Osama Abdelkader <osama.abdelkader@gmail.com> fdt_node_offset_by_compatible(fdt, -1, compat) only finds the first match. If the blob has more than one node with the same compatible string, extra nodes will remain active. Remove all the matching nodes, using the same loop as imx8mp-evk.c does for this purpose. Signed-off-by: Osama Abdelkader <osama.abdelkader@gmail.com> Message-id: 20260420162114.308519-1-osama.abdelkader@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/raspi4b.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/hw/arm/raspi4b.c b/hw/arm/raspi4b.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/raspi4b.c +++ b/hw/arm/raspi4b.c @@ -XXX,XX +XXX,XX @@ static void raspi4_modify_dtb(const struct arm_boot_info *info, void *fdt) for (int i = 0; i < ARRAY_SIZE(nodes_to_remove); i++) { const char *dev_str = nodes_to_remove[i]; + int offset; - int offset = fdt_node_offset_by_compatible(fdt, -1, dev_str); - if (offset >= 0) { - if (!fdt_nop_node(fdt, offset)) { - warn_report("bcm2711 dtc: %s has been disabled!", dev_str); + offset = fdt_node_offset_by_compatible(fdt, -1, dev_str); + while (offset >= 0) { + if (fdt_nop_node(fdt, offset) == 0) { + warn_report("bcm2711 dtb: %s has been disabled!", dev_str); } + offset = fdt_node_offset_by_compatible(fdt, offset, dev_str); } } -- 2.43.0 From: Yucai Liu <1486344514@qq.com> Implement a basic i.MX6UL LCDIF controller model with MMIO registers, frame-done interrupt behavior, and framebuffer-backed display updates for RGB565 and XRGB8888 input formats. Place the LCDIF device under hw/display and build it via a dedicated CONFIG_IMX6UL_LCDIF symbol. Model register fields with registerfields.h helpers and provide migration support via vmstate. Signed-off-by: Yucai Liu <1486344514@qq.com> Message-id: 20260412110240.93116-2-yangyanglan718@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 2 + hw/display/Kconfig | 4 + hw/display/imx6ul_lcdif.c | 453 ++++++++++++++++++++++++++++++ hw/display/meson.build | 1 + include/hw/display/imx6ul_lcdif.h | 37 +++ 5 files changed, 497 insertions(+) create mode 100644 hw/display/imx6ul_lcdif.c create mode 100644 include/hw/display/imx6ul_lcdif.h diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ L: qemu-arm@nongnu.org S: Odd Fixes F: hw/arm/mcimx6ul-evk.c F: hw/arm/fsl-imx6ul.c +F: hw/display/imx6ul_lcdif.c F: hw/misc/imx6ul_ccm.c F: include/hw/arm/fsl-imx6ul.h +F: include/hw/display/imx6ul_lcdif.h F: include/hw/misc/imx6ul_ccm.h F: docs/system/arm/mcimx6ul-evk.rst diff --git a/hw/display/Kconfig b/hw/display/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/display/Kconfig +++ b/hw/display/Kconfig @@ -XXX,XX +XXX,XX @@ config PL110 bool select FRAMEBUFFER +config IMX6UL_LCDIF + bool + select FRAMEBUFFER + config SII9022 bool depends on I2C diff --git a/hw/display/imx6ul_lcdif.c b/hw/display/imx6ul_lcdif.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/display/imx6ul_lcdif.c @@ -XXX,XX +XXX,XX @@ +/* + * SPDX-License-Identifier: GPL-2.0-or-later + * + * i.MX6UL LCDIF controller + * + * Copyright (c) 2026 Yucai Liu <1486344514@qq.com> + */ + +#include "qemu/osdep.h" +#include "hw/display/imx6ul_lcdif.h" +#include "hw/core/irq.h" +#include "hw/core/registerfields.h" +#include "hw/display/framebuffer.h" +#include "migration/vmstate.h" +#include "system/address-spaces.h" +#include "qemu/module.h" +#include "qemu/units.h" +#include "ui/pixel_ops.h" + +#define LCDIF_MMIO_SIZE (16 * KiB) +#define LCDIF_RESET_CTRL1 0x000f0000 + +REG32(CTRL, 0x00) + FIELD(CTRL, RUN, 0, 1) + FIELD(CTRL, WORD_LENGTH, 8, 2) +REG32(CTRL1, 0x10) + FIELD(CTRL1, CUR_FRAME_DONE_IRQ, 9, 1) + FIELD(CTRL1, CUR_FRAME_DONE_IRQ_EN, 13, 1) + FIELD(CTRL1, BYTE_PACKING_FORMAT, 16, 4) +REG32(V4_TRANSFER_COUNT, 0x30) + FIELD(V4_TRANSFER_COUNT, H_COUNT, 0, 16) + FIELD(V4_TRANSFER_COUNT, V_COUNT, 16, 16) +REG32(V4_CUR_BUF, 0x40) +REG32(V4_NEXT_BUF, 0x50) +REG32(AS_NEXT_BUF, 0x230) + +#define REG_SET 0x4 +#define REG_CLR 0x8 +#define REG_TOG 0xc + +#define CTRL_WORD_LENGTH_16 0 +#define CTRL_WORD_LENGTH_24 3 + +#define FRAME_PERIOD_NS (16 * 1000 * 1000ULL) + +enum IMX6ULLCDIFReg { + IMX6UL_LCDIF_REG_CTRL = A_CTRL >> 4, + IMX6UL_LCDIF_REG_CTRL1 = A_CTRL1 >> 4, + IMX6UL_LCDIF_REG_V4_TRANSFER_COUNT = A_V4_TRANSFER_COUNT >> 4, + IMX6UL_LCDIF_REG_V4_CUR_BUF = A_V4_CUR_BUF >> 4, + IMX6UL_LCDIF_REG_V4_NEXT_BUF = A_V4_NEXT_BUF >> 4, + IMX6UL_LCDIF_REG_AS_NEXT_BUF = A_AS_NEXT_BUF >> 4, +}; + +static inline bool imx6ul_lcdif_reg_exists(hwaddr reg) +{ + return (reg >> 4) < IMX6UL_LCDIF_REGS_NUM; +} + +static inline bool imx6ul_lcdif_reg_has_setclr(hwaddr reg) +{ + switch (reg) { + case A_CTRL: + case A_CTRL1: + return true; + default: + return false; + } +} + +static inline bool imx6ul_lcdif_is_running(IMX6ULLCDIFState *s) +{ + uint32_t ctrl = s->regs[IMX6UL_LCDIF_REG_CTRL]; + + return FIELD_EX32(ctrl, CTRL, RUN); +} + +static inline bool imx6ul_lcdif_frame_done_pending(IMX6ULLCDIFState *s) +{ + uint32_t ctrl1 = s->regs[IMX6UL_LCDIF_REG_CTRL1]; + + return FIELD_EX32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ); +} + +static void imx6ul_lcdif_schedule_frame(IMX6ULLCDIFState *s) +{ + int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + + timer_mod(s->frame_timer, now + FRAME_PERIOD_NS); +} + +static void imx6ul_lcdif_maybe_schedule_frame(IMX6ULLCDIFState *s) +{ + if (imx6ul_lcdif_is_running(s) && !imx6ul_lcdif_frame_done_pending(s)) { + imx6ul_lcdif_schedule_frame(s); + } else { + timer_del(s->frame_timer); + } +} + +static void imx6ul_lcdif_update_irq(IMX6ULLCDIFState *s) +{ + uint32_t ctrl1 = s->regs[IMX6UL_LCDIF_REG_CTRL1]; + bool level = FIELD_EX32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ_EN) && + FIELD_EX32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ); + + qemu_set_irq(s->irq, level); +} + +static void imx6ul_lcdif_frame_done(IMX6ULLCDIFState *s) +{ + uint32_t ctrl1 = s->regs[IMX6UL_LCDIF_REG_CTRL1]; + + ctrl1 = FIELD_DP32(ctrl1, CTRL1, CUR_FRAME_DONE_IRQ, 1); + s->regs[IMX6UL_LCDIF_REG_CTRL1] = ctrl1; + imx6ul_lcdif_update_irq(s); +} + +static void imx6ul_lcdif_draw_line_rgb565(void *opaque, uint8_t *dst, + const uint8_t *src, int width, + int dststep) +{ + uint32_t *dst32 = (uint32_t *)dst; + int i; + + for (i = 0; i < width; i++) { + uint16_t pixel = lduw_le_p(src); + uint8_t r = ((pixel >> 11) & 0x1f) << 3; + uint8_t g = ((pixel >> 5) & 0x3f) << 2; + uint8_t b = (pixel & 0x1f) << 3; + + *dst32++ = rgb_to_pixel32(r, g, b); + src += 2; + } +} + +static void imx6ul_lcdif_draw_line_xrgb8888(void *opaque, uint8_t *dst, + const uint8_t *src, int width, + int dststep) +{ + uint32_t *dst32 = (uint32_t *)dst; + int i; + + for (i = 0; i < width; i++) { + uint32_t pixel = ldl_le_p(src); + uint8_t r = (pixel >> 16) & 0xff; + uint8_t g = (pixel >> 8) & 0xff; + uint8_t b = pixel & 0xff; + + *dst32++ = rgb_to_pixel32(r, g, b); + src += 4; + } +} + +static void imx6ul_lcdif_update_display(void *opaque) +{ + IMX6ULLCDIFState *s = opaque; + DisplaySurface *surface = qemu_console_surface(s->con); + uint32_t transfer_count = s->regs[IMX6UL_LCDIF_REG_V4_TRANSFER_COUNT]; + uint32_t width = FIELD_EX32(transfer_count, V4_TRANSFER_COUNT, H_COUNT); + uint32_t height = FIELD_EX32(transfer_count, V4_TRANSFER_COUNT, V_COUNT); + uint32_t ctrl = s->regs[IMX6UL_LCDIF_REG_CTRL]; + uint32_t frame_base = s->regs[IMX6UL_LCDIF_REG_V4_CUR_BUF]; + drawfn fn; + int first = 0; + int last = 0; + int src_width; + + if (!imx6ul_lcdif_is_running(s) || width == 0 || height == 0) { + return; + } + + switch (FIELD_EX32(ctrl, CTRL, WORD_LENGTH)) { + case CTRL_WORD_LENGTH_16: + s->src_bpp = 2; + fn = imx6ul_lcdif_draw_line_rgb565; + break; + case CTRL_WORD_LENGTH_24: + s->src_bpp = 4; + fn = imx6ul_lcdif_draw_line_xrgb8888; + break; + default: + return; + } + + if (surface_width(surface) != width || surface_height(surface) != height) { + qemu_console_resize(s->con, width, height); + surface = qemu_console_surface(s->con); + s->invalidate = true; + } + + src_width = width * s->src_bpp; + if (s->invalidate || s->fb_base != frame_base || + s->src_width != src_width || s->rows != height) { + framebuffer_update_memory_section(&s->fbsection, get_system_memory(), + frame_base, height, src_width); + s->fb_base = frame_base; + s->src_width = src_width; + s->rows = height; + } + + framebuffer_update_display(surface, &s->fbsection, width, height, + src_width, surface_stride(surface), 0, + s->invalidate, fn, s, &first, &last); + if (first >= 0) { + dpy_gfx_update(s->con, 0, first, width, last - first + 1); + } + + s->invalidate = false; +} + +static void imx6ul_lcdif_invalidate_display(void *opaque) +{ + IMX6ULLCDIFState *s = opaque; + + s->invalidate = true; +} + +static const GraphicHwOps imx6ul_lcdif_graphic_ops = { + .invalidate = imx6ul_lcdif_invalidate_display, + .gfx_update = imx6ul_lcdif_update_display, +}; + +static void imx6ul_lcdif_frame_timer_cb(void *opaque) +{ + IMX6ULLCDIFState *s = opaque; + + if (!imx6ul_lcdif_is_running(s) || imx6ul_lcdif_frame_done_pending(s)) { + return; + } + + imx6ul_lcdif_frame_done(s); +} + +static uint64_t imx6ul_lcdif_read(void *opaque, hwaddr offset, unsigned size) +{ + IMX6ULLCDIFState *s = opaque; + hwaddr reg = offset & ~0xf; + uint32_t idx; + + assert(size == 4); + assert(!(offset & 0x3)); + assert(offset < LCDIF_MMIO_SIZE); + + idx = reg >> 4; + if (idx >= ARRAY_SIZE(s->regs)) { + return 0; + } + + return s->regs[idx]; +} + +static void imx6ul_lcdif_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + IMX6ULLCDIFState *s = opaque; + hwaddr reg = offset & ~0xf; + uint32_t idx; + uint32_t oldv; + + assert(size == 4); + assert(!(offset & 0x3)); + assert(offset < LCDIF_MMIO_SIZE); + + if (!imx6ul_lcdif_reg_exists(reg)) { + return; + } + + idx = reg >> 4; + oldv = s->regs[idx]; + + switch (offset & 0xf) { + case 0: + s->regs[idx] = (uint32_t)value; + break; + case REG_SET: + if (!imx6ul_lcdif_reg_has_setclr(reg)) { + return; + } + s->regs[idx] = oldv | (uint32_t)value; + break; + case REG_CLR: + if (!imx6ul_lcdif_reg_has_setclr(reg)) { + return; + } + s->regs[idx] = oldv & ~(uint32_t)value; + break; + case REG_TOG: + if (!imx6ul_lcdif_reg_has_setclr(reg)) { + return; + } + s->regs[idx] = oldv ^ (uint32_t)value; + break; + default: + g_assert_not_reached(); + } + + switch (reg) { + case A_CTRL: + if (!FIELD_EX32(oldv, CTRL, RUN) && + FIELD_EX32(s->regs[idx], CTRL, RUN)) { + s->invalidate = true; + graphic_hw_invalidate(s->con); + imx6ul_lcdif_maybe_schedule_frame(s); + break; + } + if (FIELD_EX32(oldv, CTRL, RUN) && + !FIELD_EX32(s->regs[idx], CTRL, RUN)) { + timer_del(s->frame_timer); + } + break; + case A_CTRL1: + if (FIELD_EX32(oldv, CTRL1, CUR_FRAME_DONE_IRQ) && + !FIELD_EX32(s->regs[idx], CTRL1, CUR_FRAME_DONE_IRQ)) { + imx6ul_lcdif_maybe_schedule_frame(s); + } + break; + case A_V4_TRANSFER_COUNT: + s->invalidate = true; + graphic_hw_invalidate(s->con); + break; + case A_V4_CUR_BUF: + s->invalidate = true; + graphic_hw_invalidate(s->con); + break; + case A_V4_NEXT_BUF: + s->regs[IMX6UL_LCDIF_REG_V4_CUR_BUF] = s->regs[idx]; + imx6ul_lcdif_frame_done(s); + s->invalidate = true; + graphic_hw_invalidate(s->con); + imx6ul_lcdif_maybe_schedule_frame(s); + return; + case A_AS_NEXT_BUF: + imx6ul_lcdif_frame_done(s); + imx6ul_lcdif_maybe_schedule_frame(s); + return; + default: + break; + } + + imx6ul_lcdif_update_irq(s); +} + +static const MemoryRegionOps imx6ul_lcdif_ops = { + .read = imx6ul_lcdif_read, + .write = imx6ul_lcdif_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void imx6ul_lcdif_reset(DeviceState *dev) +{ + IMX6ULLCDIFState *s = IMX6UL_LCDIF(dev); + + memset(s->regs, 0, sizeof(s->regs)); + s->regs[IMX6UL_LCDIF_REG_CTRL1] = LCDIF_RESET_CTRL1; + s->fb_base = 0; + s->src_width = 0; + s->rows = 0; + s->src_bpp = 0; + s->invalidate = true; + timer_del(s->frame_timer); + imx6ul_lcdif_update_irq(s); +} + +static int imx6ul_lcdif_post_load(void *opaque, int version_id) +{ + IMX6ULLCDIFState *s = opaque; + + s->fb_base = 0; + s->src_width = 0; + s->rows = 0; + s->src_bpp = 0; + s->invalidate = true; + + imx6ul_lcdif_update_irq(s); + if (imx6ul_lcdif_is_running(s) && + !imx6ul_lcdif_frame_done_pending(s) && + !timer_pending(s->frame_timer)) { + imx6ul_lcdif_schedule_frame(s); + } + + return 0; +} + +static const VMStateDescription vmstate_imx6ul_lcdif = { + .name = TYPE_IMX6UL_LCDIF, + .version_id = 1, + .minimum_version_id = 1, + .post_load = imx6ul_lcdif_post_load, + .fields = (const VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, IMX6ULLCDIFState, IMX6UL_LCDIF_REGS_NUM), + VMSTATE_TIMER_PTR(frame_timer, IMX6ULLCDIFState), + VMSTATE_END_OF_LIST() + }, +}; + +static void imx6ul_lcdif_realize(DeviceState *dev, Error **errp) +{ + IMX6ULLCDIFState *s = IMX6UL_LCDIF(dev); + + s->frame_timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, + imx6ul_lcdif_frame_timer_cb, s); + s->invalidate = true; + memory_region_init_io(&s->iomem, OBJECT(dev), &imx6ul_lcdif_ops, s, + TYPE_IMX6UL_LCDIF, LCDIF_MMIO_SIZE); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); + sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->irq); + s->con = graphic_console_init(dev, 0, &imx6ul_lcdif_graphic_ops, s); +} + +static void imx6ul_lcdif_unrealize(DeviceState *dev) +{ + IMX6ULLCDIFState *s = IMX6UL_LCDIF(dev); + + timer_del(s->frame_timer); + timer_free(s->frame_timer); + s->frame_timer = NULL; + + if (s->con) { + graphic_console_close(s->con); + s->con = NULL; + } +} + +static void imx6ul_lcdif_class_init(ObjectClass *klass, const void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = imx6ul_lcdif_realize; + dc->unrealize = imx6ul_lcdif_unrealize; + dc->vmsd = &vmstate_imx6ul_lcdif; + device_class_set_legacy_reset(dc, imx6ul_lcdif_reset); + dc->desc = "i.MX6UL LCDIF"; +} + +static const TypeInfo imx6ul_lcdif_info = { + .name = TYPE_IMX6UL_LCDIF, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(IMX6ULLCDIFState), + .class_init = imx6ul_lcdif_class_init, +}; + +static void imx6ul_lcdif_register_types(void) +{ + type_register_static(&imx6ul_lcdif_info); +} + +type_init(imx6ul_lcdif_register_types) diff --git a/hw/display/meson.build b/hw/display/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/display/meson.build +++ b/hw/display/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: ['CONFIG_VGA_CIRRUS', 'CONFIG_VGA_ISA'], if_true: files('cir system_ss.add(when: 'CONFIG_G364FB', if_true: files('g364fb.c')) system_ss.add(when: 'CONFIG_JAZZ_LED', if_true: files('jazz_led.c')) system_ss.add(when: 'CONFIG_PL110', if_true: files('pl110.c')) +system_ss.add(when: 'CONFIG_IMX6UL_LCDIF', if_true: files('imx6ul_lcdif.c')) system_ss.add(when: 'CONFIG_SII9022', if_true: files('sii9022.c')) system_ss.add(when: 'CONFIG_SSD0303', if_true: files('ssd0303.c')) system_ss.add(when: 'CONFIG_SSD0323', if_true: files('ssd0323.c')) diff --git a/include/hw/display/imx6ul_lcdif.h b/include/hw/display/imx6ul_lcdif.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/display/imx6ul_lcdif.h @@ -XXX,XX +XXX,XX @@ +/* + * SPDX-License-Identifier: GPL-2.0-or-later + * + * i.MX6UL LCDIF controller + * + * Copyright (c) 2026 Yucai Liu <1486344514@qq.com> + */ + +#ifndef IMX6UL_LCDIF_H +#define IMX6UL_LCDIF_H + +#include "hw/core/sysbus.h" +#include "qom/object.h" +#include "qemu/timer.h" +#include "ui/console.h" + +#define TYPE_IMX6UL_LCDIF "imx6ul-lcdif" +#define IMX6UL_LCDIF_REGS_NUM ((0x230 >> 4) + 1) +OBJECT_DECLARE_SIMPLE_TYPE(IMX6ULLCDIFState, IMX6UL_LCDIF) + +struct IMX6ULLCDIFState { + SysBusDevice parent_obj; + + MemoryRegion iomem; + MemoryRegionSection fbsection; + qemu_irq irq; + QemuConsole *con; + QEMUTimer *frame_timer; + uint32_t fb_base; + uint32_t src_width; + uint32_t rows; + uint8_t src_bpp; + bool invalidate; + uint32_t regs[IMX6UL_LCDIF_REGS_NUM]; +}; + +#endif /* IMX6UL_LCDIF_H */ -- 2.43.0 From: Yucai Liu <1486344514@qq.com> Instantiate LCDIF as a child object of the i.MX6UL SoC in init and realize it in the SoC realize path before MMIO/IRQ hookup. Also make FSL_IMX6UL select CONFIG_IMX6UL_LCDIF and map the LCDIF region with a 16 KiB size to match the SoC memory map. Signed-off-by: Yucai Liu <1486344514@qq.com> Message-id: 20260412110240.93116-3-yangyanglan718@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + hw/arm/fsl-imx6ul.c | 12 ++++++++++-- include/hw/arm/fsl-imx6ul.h | 4 +++- 3 files changed, 14 insertions(+), 3 deletions(-) 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 FSL_IMX6UL imply I2C_DEVICES select A15MPCORE select IMX + select IMX6UL_LCDIF select IMX_FEC select IMX_I2C select IMX_USBPHY diff --git a/hw/arm/fsl-imx6ul.c b/hw/arm/fsl-imx6ul.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx6ul.c +++ b/hw/arm/fsl-imx6ul.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "hw/arm/fsl-imx6ul.h" +#include "hw/display/imx6ul_lcdif.h" #include "hw/misc/unimp.h" #include "hw/usb/imx-usb-phy.h" #include "hw/core/boards.h" @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_init(Object *obj) object_initialize_child(obj, name, &s->usb[i], TYPE_CHIPIDEA); } + /* + * LCDIF + */ + object_initialize_child(obj, "lcdif", &s->lcdif, TYPE_IMX6UL_LCDIF); + /* * SDHCIs */ @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) /* * LCD */ - create_unimplemented_device("lcdif", FSL_IMX6UL_LCDIF_ADDR, - FSL_IMX6UL_LCDIF_SIZE); + sysbus_realize(SYS_BUS_DEVICE(&s->lcdif), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(&s->lcdif), 0, FSL_IMX6UL_LCDIF_ADDR); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->lcdif), 0, + qdev_get_gpio_in(gic, FSL_IMX6UL_LCDIF_IRQ)); /* * CSU diff --git a/include/hw/arm/fsl-imx6ul.h b/include/hw/arm/fsl-imx6ul.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx6ul.h +++ b/include/hw/arm/fsl-imx6ul.h @@ -XXX,XX +XXX,XX @@ #include "hw/net/imx_fec.h" #include "hw/usb/chipidea.h" #include "hw/usb/imx-usb-phy.h" +#include "hw/display/imx6ul_lcdif.h" #include "system/memory.h" #include "target/arm/cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct FslIMX6ULState { IMX2WdtState wdt[FSL_IMX6UL_NUM_WDTS]; IMXUSBPHYState usbphy[FSL_IMX6UL_NUM_USB_PHYS]; ChipideaState usb[FSL_IMX6UL_NUM_USBS]; + IMX6ULLCDIFState lcdif; MemoryRegion rom; MemoryRegion caam; MemoryRegion ocram; @@ -XXX,XX +XXX,XX @@ enum FslIMX6ULMemoryMap { FSL_IMX6UL_PXP_SIZE = (16 * KiB), FSL_IMX6UL_LCDIF_ADDR = 0x021C8000, - FSL_IMX6UL_LCDIF_SIZE = 0x100, + FSL_IMX6UL_LCDIF_SIZE = (16 * KiB), FSL_IMX6UL_CSI_ADDR = 0x021C4000, FSL_IMX6UL_CSI_SIZE = 0x100, -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> We have a registerfields interface which we can use for defining fields alongside helpers to access them. Define the basic syndrome layout and convert the helpers that take the imm16 data directly. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-2-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 75 ++++++++++++++++++++++++++++++++----------- 1 file changed, 57 insertions(+), 18 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ #ifndef TARGET_ARM_SYNDROME_H #define TARGET_ARM_SYNDROME_H -#include "qemu/bitops.h" +#include "hw/core/registerfields.h" /* Valid Syndrome Register EC field values */ enum arm_exception_class { @@ -XXX,XX +XXX,XX @@ enum arm_exception_class { EC_AA64_BKPT = 0x3c, }; +/* Generic syndrome encoding layout for HSR and lower 32 bits of ESR_EL2 */ +FIELD(SYNDROME, EC, 26, 6) +FIELD(SYNDROME, IL, 25, 1) +FIELD(SYNDROME, ISS, 0, 25) + typedef enum { SME_ET_AccessTrap, SME_ET_Streaming, @@ -XXX,XX +XXX,XX @@ typedef enum { static inline uint32_t syn_get_ec(uint32_t syn) { - return syn >> ARM_EL_EC_SHIFT; + return FIELD_EX32(syn, SYNDROME, EC); } static inline uint32_t syn_set_ec(uint32_t syn, uint32_t ec) { - return deposit32(syn, ARM_EL_EC_SHIFT, ARM_EL_EC_LENGTH, ec); + return FIELD_DP32(syn, SYNDROME, EC, ec); } /* @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_set_ec(uint32_t syn, uint32_t ec) */ static inline uint32_t syn_uncategorized(void) { - return (EC_UNCATEGORIZED << ARM_EL_EC_SHIFT) | ARM_EL_IL; + uint32_t res = syn_set_ec(0, EC_UNCATEGORIZED); + res = FIELD_DP32(res, SYNDROME, IL, 1); + return res; } +FIELD(ISS_IMM16, IMM16, 0, 16) + static inline uint32_t syn_aa64_svc(uint32_t imm16) { - return (EC_AA64_SVC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff); + uint32_t res = syn_set_ec(0, EC_AA64_SVC); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); + return res; } static inline uint32_t syn_aa64_hvc(uint32_t imm16) { - return (EC_AA64_HVC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff); + uint32_t res = syn_set_ec(0, EC_AA64_HVC); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); + return res; } static inline uint32_t syn_aa64_smc(uint32_t imm16) { - return (EC_AA64_SMC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff); + uint32_t res = syn_set_ec(0, EC_AA64_SMC); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); + return res; } static inline uint32_t syn_aa32_svc(uint32_t imm16, bool is_16bit) { - return (EC_AA32_SVC << ARM_EL_EC_SHIFT) | (imm16 & 0xffff) - | (is_16bit ? 0 : ARM_EL_IL); + uint32_t res = syn_set_ec(0, EC_AA32_SVC); + res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1); + res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); + return res; } static inline uint32_t syn_aa32_hvc(uint32_t imm16) { - return (EC_AA32_HVC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff); + uint32_t res = syn_set_ec(0, EC_AA32_HVC); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); + return res; } static inline uint32_t syn_aa32_smc(void) { - return (EC_AA32_SMC << ARM_EL_EC_SHIFT) | ARM_EL_IL; + uint32_t res = syn_set_ec(0, EC_AA32_SMC); + res = FIELD_DP32(res, SYNDROME, IL, 1); + return res; } static inline uint32_t syn_aa64_bkpt(uint32_t imm16) { - return (EC_AA64_BKPT << ARM_EL_EC_SHIFT) | ARM_EL_IL | (imm16 & 0xffff); + uint32_t res = syn_set_ec(0, EC_AA64_BKPT); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); + return res; } static inline uint32_t syn_aa32_bkpt(uint32_t imm16, bool is_16bit) { - return (EC_AA32_BKPT << ARM_EL_EC_SHIFT) | (imm16 & 0xffff) - | (is_16bit ? 0 : ARM_EL_IL); + uint32_t res = syn_set_ec(0, EC_AA32_BKPT); + res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1); + res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); + return res; } static inline uint32_t syn_aa64_sysregtrap(int op0, int op1, int op2, @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_simd_access_trap(int cv, int cond, bool is_16bit) static inline uint32_t syn_sve_access_trap(void) { - return (EC_SVEACCESSTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL; + uint32_t res = syn_set_ec(0, EC_SVEACCESSTRAP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + return res; } /* @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit) static inline uint32_t syn_illegalstate(void) { - return (EC_ILLEGALSTATE << ARM_EL_EC_SHIFT) | ARM_EL_IL; + uint32_t res = syn_set_ec(0, EC_ILLEGALSTATE); + res = FIELD_DP32(res, SYNDROME, IL, 1); + return res; } static inline uint32_t syn_pcalignment(void) { - return (EC_PCALIGNMENT << ARM_EL_EC_SHIFT) | ARM_EL_IL; + uint32_t res = syn_set_ec(0, EC_PCALIGNMENT); + res = FIELD_DP32(res, SYNDROME, IL, 1); + return res; } static inline uint32_t syn_gcs_data_check(GCSInstructionType it, int rn) @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_gcs_gcsstr(int ra, int rn) static inline uint32_t syn_serror(uint32_t extra) { - return (EC_SERROR << ARM_EL_EC_SHIFT) | ARM_EL_IL | extra; + uint32_t res = syn_set_ec(0, EC_SERROR); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, SYNDROME, ISS, extra); + return res; } static inline uint32_t syn_mop(bool is_set, bool is_setg, int options, -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Migrate syn_aa64_sysregtrap and co-processor register trap syndromes to the registerfields API. The co-processor syndromes are split between single and duel register moves. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-3-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 124 ++++++++++++++++++++++++++++++++++-------- 1 file changed, 102 insertions(+), 22 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ enum arm_exception_class { /* Generic syndrome encoding layout for HSR and lower 32 bits of ESR_EL2 */ FIELD(SYNDROME, EC, 26, 6) -FIELD(SYNDROME, IL, 25, 1) +FIELD(SYNDROME, IL, 25, 1) /* IL=1 for 32 bit instructions */ FIELD(SYNDROME, ISS, 0, 25) typedef enum { @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_aa64_smc(uint32_t imm16) static inline uint32_t syn_aa32_svc(uint32_t imm16, bool is_16bit) { uint32_t res = syn_set_ec(0, EC_AA32_SVC); - res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); return res; } @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_aa64_bkpt(uint32_t imm16) static inline uint32_t syn_aa32_bkpt(uint32_t imm16, bool is_16bit) { uint32_t res = syn_set_ec(0, EC_AA32_BKPT); - res = FIELD_DP32(res, SYNDROME, IL, is_16bit ? 0 : 1); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); res = FIELD_DP32(res, ISS_IMM16, IMM16, imm16); return res; } +/* + * ISS encoding for an exception from MSR, MRS, or System instruction + * in AArch64 state. + */ +FIELD(SYSREG_ISS, ISREAD, 0, 1) /* Direction, 1 is read */ +FIELD(SYSREG_ISS, CRM, 1, 4) +FIELD(SYSREG_ISS, RT, 5, 5) +FIELD(SYSREG_ISS, CRN, 10, 4) +FIELD(SYSREG_ISS, OP1, 14, 3) +FIELD(SYSREG_ISS, OP2, 17, 3) +FIELD(SYSREG_ISS, OP0, 20, 2) + static inline uint32_t syn_aa64_sysregtrap(int op0, int op1, int op2, int crn, int crm, int rt, int isread) { - return (EC_SYSTEMREGISTERTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL - | (op0 << 20) | (op2 << 17) | (op1 << 14) | (crn << 10) | (rt << 5) - | (crm << 1) | isread; + uint32_t res = syn_set_ec(0, EC_SYSTEMREGISTERTRAP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, SYSREG_ISS, OP0, op0); + res = FIELD_DP32(res, SYSREG_ISS, OP2, op2); + res = FIELD_DP32(res, SYSREG_ISS, OP1, op1); + res = FIELD_DP32(res, SYSREG_ISS, CRN, crn); + res = FIELD_DP32(res, SYSREG_ISS, RT, rt); + res = FIELD_DP32(res, SYSREG_ISS, CRM, crm); + res = FIELD_DP32(res, SYSREG_ISS, ISREAD, isread); + + return res; } +/* + * ISS encoding for an exception from an MCR or MRC access + * (move to/from co-processor) + */ +FIELD(COPROC_ISS, ISREAD, 0, 1) +FIELD(COPROC_ISS, CRM, 1, 4) +FIELD(COPROC_ISS, RT, 5, 5) +FIELD(COPROC_ISS, CRN, 10, 4) +FIELD(COPROC_ISS, OP1, 14, 3) +FIELD(COPROC_ISS, OP2, 17, 3) +FIELD(COPROC_ISS, COND, 20, 4) +FIELD(COPROC_ISS, CV, 24, 1) + static inline uint32_t syn_cp14_rt_trap(int cv, int cond, int opc1, int opc2, int crn, int crm, int rt, int isread, bool is_16bit) { - return (EC_CP14RTTRAP << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) - | (cv << 24) | (cond << 20) | (opc2 << 17) | (opc1 << 14) - | (crn << 10) | (rt << 5) | (crm << 1) | isread; + uint32_t res = syn_set_ec(0, EC_CP14RTTRAP); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); + + res = FIELD_DP32(res, COPROC_ISS, CV, cv); + res = FIELD_DP32(res, COPROC_ISS, COND, cond); + res = FIELD_DP32(res, COPROC_ISS, OP2, opc2); + res = FIELD_DP32(res, COPROC_ISS, OP1, opc1); + res = FIELD_DP32(res, COPROC_ISS, CRN, crn); + res = FIELD_DP32(res, COPROC_ISS, RT, rt); + res = FIELD_DP32(res, COPROC_ISS, CRM, crm); + res = FIELD_DP32(res, COPROC_ISS, ISREAD, isread); + + return res; } static inline uint32_t syn_cp15_rt_trap(int cv, int cond, int opc1, int opc2, int crn, int crm, int rt, int isread, bool is_16bit) { - return (EC_CP15RTTRAP << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) - | (cv << 24) | (cond << 20) | (opc2 << 17) | (opc1 << 14) - | (crn << 10) | (rt << 5) | (crm << 1) | isread; + uint32_t res = syn_set_ec(0, EC_CP15RTTRAP); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); + + res = FIELD_DP32(res, COPROC_ISS, CV, cv); + res = FIELD_DP32(res, COPROC_ISS, COND, cond); + res = FIELD_DP32(res, COPROC_ISS, OP2, opc2); + res = FIELD_DP32(res, COPROC_ISS, OP1, opc1); + res = FIELD_DP32(res, COPROC_ISS, CRN, crn); + res = FIELD_DP32(res, COPROC_ISS, RT, rt); + res = FIELD_DP32(res, COPROC_ISS, CRM, crm); + res = FIELD_DP32(res, COPROC_ISS, ISREAD, isread); + + return res; } +/* + * ISS encoding for an exception from an MCRR or MRRC access + * (move to/from co-processor with 2 regs) + */ +FIELD(COPROC_R2_ISS, ISREAD, 0, 1) +FIELD(COPROC_R2_ISS, CRM, 1, 4) +FIELD(COPROC_R2_ISS, RT, 5, 5) +FIELD(COPROC_R2_ISS, RT2, 10, 5) +FIELD(COPROC_R2_ISS, OP1, 16, 4) +FIELD(COPROC_R2_ISS, COND, 20, 4) +FIELD(COPROC_R2_ISS, CV, 24, 1) + static inline uint32_t syn_cp14_rrt_trap(int cv, int cond, int opc1, int crm, int rt, int rt2, int isread, bool is_16bit) { - return (EC_CP14RRTTRAP << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) - | (cv << 24) | (cond << 20) | (opc1 << 16) - | (rt2 << 10) | (rt << 5) | (crm << 1) | isread; + uint32_t res = syn_set_ec(0, EC_CP14RRTTRAP); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); + + res = FIELD_DP32(res, COPROC_R2_ISS, CV, cv); + res = FIELD_DP32(res, COPROC_R2_ISS, COND, cond); + res = FIELD_DP32(res, COPROC_R2_ISS, OP1, opc1); + res = FIELD_DP32(res, COPROC_R2_ISS, RT2, rt2); + res = FIELD_DP32(res, COPROC_R2_ISS, RT, rt); + res = FIELD_DP32(res, COPROC_R2_ISS, CRM, crm); + res = FIELD_DP32(res, COPROC_R2_ISS, ISREAD, isread); + + return res; } static inline uint32_t syn_cp15_rrt_trap(int cv, int cond, int opc1, int crm, int rt, int rt2, int isread, bool is_16bit) { - return (EC_CP15RRTTRAP << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) - | (cv << 24) | (cond << 20) | (opc1 << 16) - | (rt2 << 10) | (rt << 5) | (crm << 1) | isread; + uint32_t res = syn_set_ec(0, EC_CP15RRTTRAP); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); + + res = FIELD_DP32(res, COPROC_R2_ISS, CV, cv); + res = FIELD_DP32(res, COPROC_R2_ISS, COND, cond); + res = FIELD_DP32(res, COPROC_R2_ISS, OP1, opc1); + res = FIELD_DP32(res, COPROC_R2_ISS, RT2, rt2); + res = FIELD_DP32(res, COPROC_R2_ISS, RT, rt); + res = FIELD_DP32(res, COPROC_R2_ISS, CRM, crm); + res = FIELD_DP32(res, COPROC_R2_ISS, ISREAD, isread); + + return res; } static inline uint32_t syn_fp_access_trap(int cv, int cond, bool is_16bit, -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> The syn_simd_access trap was never used so remove it. We should only see the COPROC encoding on v7 architectures. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-4-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_cp15_rrt_trap(int cv, int cond, int opc1, int crm, return res; } +/* + * ISS encoding for an exception from an access to a register of + * instruction resulting from the FPEN or TFP traps. + */ +FIELD(FP_ISS, COPROC, 0, 4) /* ARMv7 only */ +FIELD(FP_ISS, COND, 20, 4) +FIELD(FP_ISS, CV, 24, 1) + static inline uint32_t syn_fp_access_trap(int cv, int cond, bool is_16bit, int coproc) { /* AArch32 FP trap or any AArch64 FP/SIMD trap: TA == 0 */ - return (EC_ADVSIMDFPACCESSTRAP << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) - | (cv << 24) | (cond << 20) | coproc; -} + uint32_t res = syn_set_ec(0, EC_ADVSIMDFPACCESSTRAP); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); -static inline uint32_t syn_simd_access_trap(int cv, int cond, bool is_16bit) -{ - /* AArch32 SIMD trap: TA == 1 coproc == 0 */ - return (EC_ADVSIMDFPACCESSTRAP << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) - | (cv << 24) | (cond << 20) | (1 << 5); + res = FIELD_DP32(res, FP_ISS, CV, cv); + res = FIELD_DP32(res, FP_ISS, COND, cond); + res = FIELD_DP32(res, FP_ISS, COPROC, coproc); + + return res; } static inline uint32_t syn_sve_access_trap(void) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> For simplicity keep the OP as a two bit field rather than the two interlinked fields in the docs (ERET/ERETA). Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-5-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_sve_access_trap(void) } /* + * ISS encoding for an exception from an ERET, ERETAA or ERETAB + * instructions. + * * eret_op is bits [1:0] of the ERET instruction, so: * 0 for ERET, 2 for ERETAA, 3 for ERETAB. */ +FIELD(ERET_ISS, OP, 0, 2) + static inline uint32_t syn_erettrap(int eret_op) { - return (EC_ERETTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL | eret_op; + uint32_t res = syn_set_ec(0, EC_ERETTRAP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, ERET_ISS, OP, eret_op); + + return res; } static inline uint32_t syn_smetrap(SMEExceptionType etype, bool is_16bit) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-6-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_erettrap(int eret_op) return res; } +/* + * ISS encoding for an exception due to SME functionality + */ +FIELD(SME_ISS, SMTC, 0, 2) + static inline uint32_t syn_smetrap(SMEExceptionType etype, bool is_16bit) { - return (EC_SMETRAP << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) | etype; + uint32_t res = syn_set_ec(0, EC_SMETRAP); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); + res = FIELD_DP32(res, SME_ISS, SMTC, etype); + + return res; } static inline uint32_t syn_pacfail(bool data, int keynumber) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> syn_pactrap is fairly simple as the ISS is all RES0. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-7-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_smetrap(SMEExceptionType etype, bool is_16bit) return res; } +/* + * ISS encoding for a PAC Fail exceptions + */ +FIELD(PACFAIL_ISS, BnA, 0, 1) /* B key or A key */ +FIELD(PACFAIL_ISS, DnI, 1, 1) /* Data or Instruction */ + static inline uint32_t syn_pacfail(bool data, int keynumber) { - int error_code = (data << 1) | keynumber; - return (EC_PACFAIL << ARM_EL_EC_SHIFT) | ARM_EL_IL | error_code; + uint32_t res = syn_set_ec(0, EC_PACFAIL); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, PACFAIL_ISS, DnI, data); + res = FIELD_DP32(res, PACFAIL_ISS, BnA, keynumber); + + return res; } +/* + * ISS encoding for an exception from a trapped Pointer + * Authentication instruction is RES0 + */ static inline uint32_t syn_pactrap(void) { - return (EC_PACTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL; + uint32_t res = syn_set_ec(0, EC_PACTRAP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + return res; } static inline uint32_t syn_btitrap(int btype) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-8-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_pactrap(void) return res; } +/* + * ISS encoding for an exception from a Branch Target Identification + * instruction. + */ +FIELD(BTI_ISS, BTYPE, 0, 2) + static inline uint32_t syn_btitrap(int btype) { - return (EC_BTITRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL | btype; + uint32_t res = syn_set_ec(0, EC_BTITRAP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, BTI_ISS, BTYPE, btype); + return res; } static inline uint32_t syn_bxjtrap(int cv, int cond, int rm) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> This is an Armv7 specific syndrome for chips with Jazelle functionality. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-9-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 20 ++++++++++++++++++-- 1 file changed, 18 insertions(+), 2 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_btitrap(int btype) return res; } +/* + * ISS encoding for trapped BXJ execution + * + * This is an Armv7 encoding. + */ +FIELD(BXJ_ISS, RM, 0, 4) +/* bits 4:19 are Reserved, UNK/SBZP */ +FIELD(BXJ_ISS, COND, 20, 4) +FIELD(BXJ_ISS, CV, 24, 1) + static inline uint32_t syn_bxjtrap(int cv, int cond, int rm) { - return (EC_BXJTRAP << ARM_EL_EC_SHIFT) | ARM_EL_IL | - (cv << 24) | (cond << 20) | rm; + uint32_t res = syn_set_ec(0, EC_BXJTRAP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, BXJ_ISS, CV, cv); + res = FIELD_DP32(res, BXJ_ISS, COND, cond); + res = FIELD_DP32(res, BXJ_ISS, RM, rm); + + return res; } static inline uint32_t syn_gpc(int s2ptw, int ind, int gpcsc, int vncr, -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-10-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_bxjtrap(int cv, int cond, int rm) return res; } +/* + * ISS encoding for a Granule Protection Check exception + * + * These are only reported to EL3 + */ +FIELD(GPC_ISS, xFSC, 0, 6) +FIELD(GPC_ISS, WnR, 6, 1) /* Write not Read */ +FIELD(GPC_ISS, S1PTW, 7, 1) +FIELD(GPC_ISS, CM, 8, 1) +FIELD(GPC_ISS, VNCR, 13, 1) +FIELD(GPC_ISS, GPCSC, 14, 6) +FIELD(GPC_ISS, InD, 20, 1) /* Instruction not Data access */ +FIELD(GPC_ISS, S2PTW, 21, 1) + static inline uint32_t syn_gpc(int s2ptw, int ind, int gpcsc, int vncr, int cm, int s1ptw, int wnr, int fsc) { - return (EC_GPC << ARM_EL_EC_SHIFT) | ARM_EL_IL | (s2ptw << 21) - | (ind << 20) | (gpcsc << 14) | (vncr << 13) | (cm << 8) - | (s1ptw << 7) | (wnr << 6) | fsc; + uint32_t res = syn_set_ec(0, EC_GPC); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, GPC_ISS, S2PTW, s2ptw); + res = FIELD_DP32(res, GPC_ISS, InD, ind); + res = FIELD_DP32(res, GPC_ISS, GPCSC, gpcsc); + res = FIELD_DP32(res, GPC_ISS, VNCR, vncr); + res = FIELD_DP32(res, GPC_ISS, CM, cm); + res = FIELD_DP32(res, GPC_ISS, S1PTW, s1ptw); + res = FIELD_DP32(res, GPC_ISS, WnR, wnr); + res = FIELD_DP32(res, GPC_ISS, xFSC, fsc); + + return res; } static inline uint32_t syn_insn_abort(int same_el, int ea, int s1ptw, int fsc) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Migrate syn_insn_abort and syn_data_abort_* to the registerfields API. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20260422125250.1303100-11-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 87 ++++++++++++++++++++++++++++++++++++------- 1 file changed, 74 insertions(+), 13 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_gpc(int s2ptw, int ind, int gpcsc, int vncr, return res; } +/* + * ISS encoding for an exception from an Instruction Abort + * + * (aka instruction abort) + */ +FIELD(IABORT_ISS, IFSC, 0, 6) +FIELD(IABORT_ISS, S1PTW, 7, 1) +FIELD(IABORT_ISS, EA, 9, 1) +FIELD(IABORT_ISS, FnV, 10, 1) /* FAR not Valid */ +FIELD(IABORT_ISS, SET, 11, 2) +FIELD(IABORT_ISS, PFV, 14, 1) +FIELD(IABORT_ISS, TopLevel, 21, 1) /* FEAT_THE */ + static inline uint32_t syn_insn_abort(int same_el, int ea, int s1ptw, int fsc) { - return (EC_INSNABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) - | ARM_EL_IL | (ea << 9) | (s1ptw << 7) | fsc; + uint32_t res = syn_set_ec(0, EC_INSNABORT + same_el); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, IABORT_ISS, EA, ea); + res = FIELD_DP32(res, IABORT_ISS, S1PTW, s1ptw); + res = FIELD_DP32(res, IABORT_ISS, IFSC, fsc); + + return res; } +/* + * ISS encoding for an exception from a Data Abort + */ +FIELD(DABORT_ISS, DFSC, 0, 6) +FIELD(DABORT_ISS, WNR, 6, 1) +FIELD(DABORT_ISS, S1PTW, 7, 1) +FIELD(DABORT_ISS, CM, 8, 1) +FIELD(DABORT_ISS, EA, 9, 1) +FIELD(DABORT_ISS, FnV, 10, 1) +FIELD(DABORT_ISS, LST, 11, 2) +FIELD(DABORT_ISS, VNCR, 13, 1) +FIELD(DABORT_ISS, AR, 14, 1) +FIELD(DABORT_ISS, SF, 15, 1) +FIELD(DABORT_ISS, SRT, 16, 5) +FIELD(DABORT_ISS, SSE, 21, 1) +FIELD(DABORT_ISS, SAS, 22, 2) +FIELD(DABORT_ISS, ISV, 24, 1) + static inline uint32_t syn_data_abort_no_iss(int same_el, int fnv, int ea, int cm, int s1ptw, int wnr, int fsc) { - return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) - | ARM_EL_IL - | (fnv << 10) | (ea << 9) | (cm << 8) | (s1ptw << 7) - | (wnr << 6) | fsc; + uint32_t res = syn_set_ec(0, EC_DATAABORT + same_el); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, DABORT_ISS, FnV, fnv); + res = FIELD_DP32(res, DABORT_ISS, EA, ea); + res = FIELD_DP32(res, DABORT_ISS, CM, cm); + res = FIELD_DP32(res, DABORT_ISS, S1PTW, s1ptw); + res = FIELD_DP32(res, DABORT_ISS, WNR, wnr); + res = FIELD_DP32(res, DABORT_ISS, DFSC, fsc); + + return res; } static inline uint32_t syn_data_abort_with_iss(int same_el, @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_data_abort_with_iss(int same_el, int wnr, int fsc, bool is_16bit) { - return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) - | (is_16bit ? 0 : ARM_EL_IL) - | ARM_EL_ISV | (sas << 22) | (sse << 21) | (srt << 16) - | (sf << 15) | (ar << 14) - | (ea << 9) | (cm << 8) | (s1ptw << 7) | (wnr << 6) | fsc; + uint32_t res = syn_set_ec(0, EC_DATAABORT + same_el); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); + + res = FIELD_DP32(res, DABORT_ISS, ISV, 1); + res = FIELD_DP32(res, DABORT_ISS, SAS, sas); + res = FIELD_DP32(res, DABORT_ISS, SSE, sse); + res = FIELD_DP32(res, DABORT_ISS, SRT, srt); + res = FIELD_DP32(res, DABORT_ISS, SF, sf); + res = FIELD_DP32(res, DABORT_ISS, AR, ar); + res = FIELD_DP32(res, DABORT_ISS, EA, ea); + res = FIELD_DP32(res, DABORT_ISS, CM, cm); + res = FIELD_DP32(res, DABORT_ISS, S1PTW, s1ptw); + res = FIELD_DP32(res, DABORT_ISS, WNR, wnr); + res = FIELD_DP32(res, DABORT_ISS, DFSC, fsc); + + return res; } /* @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_data_abort_with_iss(int same_el, */ static inline uint32_t syn_data_abort_vncr(int ea, int wnr, int fsc) { - return (EC_DATAABORT << ARM_EL_EC_SHIFT) | (1 << ARM_EL_EC_SHIFT) - | ARM_EL_IL | ARM_EL_VNCR | (wnr << 6) | fsc; + uint32_t res = syn_set_ec(0, EC_DATAABORT_SAME_EL); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, DABORT_ISS, VNCR, 1); + res = FIELD_DP32(res, DABORT_ISS, WNR, wnr); + res = FIELD_DP32(res, DABORT_ISS, DFSC, fsc); + + return res; } static inline uint32_t syn_swstep(int same_el, int isv, int ex) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Migrate syn_swstep, syn_watchpoint and syn_breakpoint to the registerfields API. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-12-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 54 ++++++++++++++++++++++++++++++++++++++----- 1 file changed, 48 insertions(+), 6 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_data_abort_vncr(int ea, int wnr, int fsc) return res; } +/* + * ISS encoding for an exception from a Software Step exception. + */ +FIELD(SOFTSTEP_ISS, IFSC, 0, 6) +FIELD(SOFTSTEP_ISS, EX, 6, 1) +FIELD(SOFTSTEP_ISS, ISV, 24, 1) + static inline uint32_t syn_swstep(int same_el, int isv, int ex) { - return (EC_SOFTWARESTEP << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) - | ARM_EL_IL | (isv << 24) | (ex << 6) | 0x22; + uint32_t res = syn_set_ec(0, EC_SOFTWARESTEP + same_el); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, SOFTSTEP_ISS, ISV, isv); + res = FIELD_DP32(res, SOFTSTEP_ISS, EX, ex); + res = FIELD_DP32(res, SOFTSTEP_ISS, IFSC, 0x22); + + return res; } +/* + * ISS encoding for an exception from a Watchpoint exception + */ +FIELD(WATCHPOINT_ISS, DFSC, 0, 6) +FIELD(WATCHPOINT_ISS, WNR, 6, 1) +FIELD(WATCHPOINT_ISS, CM, 8, 1) +FIELD(WATCHPOINT_ISS, FnV, 10, 1) +FIELD(WATCHPOINT_ISS, VNCR, 13, 1) /* FEAT_NV2 */ +FIELD(WATCHPOINT_ISS, FnP, 15, 1) +FIELD(WATCHPOINT_ISS, WPF, 16, 1) +/* bellow mandatory from FEAT_Debugv8p9 */ +FIELD(WATCHPOINT_ISS, WPTV, 17, 1) /* FEAT_Debugv8p2 - WPT valid */ +FIELD(WATCHPOINT_ISS, WPT, 18, 6) /* FEAT_Debugv8p2 - missing WP number */ + static inline uint32_t syn_watchpoint(int same_el, int cm, int wnr) { - return (EC_WATCHPOINT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) - | ARM_EL_IL | (cm << 8) | (wnr << 6) | 0x22; + uint32_t res = syn_set_ec(0, EC_WATCHPOINT + same_el); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, WATCHPOINT_ISS, CM, cm); + res = FIELD_DP32(res, WATCHPOINT_ISS, WNR, wnr); + res = FIELD_DP32(res, WATCHPOINT_ISS, DFSC, 0x22); + + return res; } +/* + * ISS encoding for an exception from a Breakpoint or a Vector Catch + * debug exception. + */ +FIELD(BREAKPOINT_ISS, IFSC, 0, 6) + static inline uint32_t syn_breakpoint(int same_el) { - return (EC_BREAKPOINT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) - | ARM_EL_IL | 0x22; + uint32_t res = syn_set_ec(0, EC_BREAKPOINT + same_el); + res = FIELD_DP32(res, SYNDROME, IL, 1); + res = FIELD_DP32(res, BREAKPOINT_ISS, IFSC, 0x22); + + return res; } static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> This will help later when we expand the fields we report. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-13-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_breakpoint(int same_el) return res; } +/* + * ISS encoding for an exception from a WF* instruction + */ +FIELD(WFX_ISS, TI, 0, 2) +FIELD(WFX_ISS, RV, 2, 1) +FIELD(WFX_ISS, RN, 5, 5) +FIELD(WFX_ISS, COND, 20, 4) +FIELD(WFX_ISS, CV, 24, 1) + static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit) { - return (EC_WFX_TRAP << ARM_EL_EC_SHIFT) | - (is_16bit ? 0 : (1 << ARM_EL_IL_SHIFT)) | - (cv << 24) | (cond << 20) | ti; + uint32_t res = syn_set_ec(0, EC_WFX_TRAP); + res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); + + res = FIELD_DP32(res, WFX_ISS, CV, cv); + res = FIELD_DP32(res, WFX_ISS, COND, cond); + res = FIELD_DP32(res, WFX_ISS, TI, ti); + + return res; } static inline uint32_t syn_illegalstate(void) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Tweak arg names to make it clear raddr is the data address register number. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-14-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 39 +++++++++++++++++++++++++++++++++------ 1 file changed, 33 insertions(+), 6 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_pcalignment(void) return res; } +/* + * ISS encoding for a GCS exception + * + * Field validity depends on EXTYPE + */ +FIELD(GCS_ISS, IT, 0, 5) +FIELD(GCS_ISS, RN, 5, 5) /* only for non EXLOCK exceptions */ +FIELD(GCS_ISS, RADDR, 10, 5) /* only for GCSSTR/GCSSTTR traps */ +FIELD(GCS_ISS, EXTYPE, 20, 4) + static inline uint32_t syn_gcs_data_check(GCSInstructionType it, int rn) { - return ((EC_GCS << ARM_EL_EC_SHIFT) | ARM_EL_IL | - (GCS_ET_DataCheck << 20) | (rn << 5) | it); + uint32_t res = syn_set_ec(0, EC_GCS); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, GCS_ISS, EXTYPE, GCS_ET_DataCheck); + res = FIELD_DP32(res, GCS_ISS, RN, rn); + res = FIELD_DP32(res, GCS_ISS, IT, it); + + return res; } static inline uint32_t syn_gcs_exlock(void) { - return (EC_GCS << ARM_EL_EC_SHIFT) | ARM_EL_IL | (GCS_ET_EXLOCK << 20); + uint32_t res = syn_set_ec(0, EC_GCS); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, GCS_ISS, EXTYPE, GCS_ET_EXLOCK); + + return res; } -static inline uint32_t syn_gcs_gcsstr(int ra, int rn) +static inline uint32_t syn_gcs_gcsstr(int raddr, int rn) { - return ((EC_GCS << ARM_EL_EC_SHIFT) | ARM_EL_IL | - (GCS_ET_GCSSTR_GCSSTTR << 20) | (ra << 10) | (rn << 5)); + uint32_t res = syn_set_ec(0, EC_GCS); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, GCS_ISS, EXTYPE, GCS_ET_GCSSTR_GCSSTTR); + res = FIELD_DP32(res, GCS_ISS, RADDR, raddr); + res = FIELD_DP32(res, GCS_ISS, RN, rn); + + return res; } static inline uint32_t syn_serror(uint32_t extra) -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-15-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_serror(uint32_t extra) return res; } +/* + * ISS encoding for an exception from the Memory Copy and Memory Set + * instructions. + */ +FIELD(MOP_ISS, SIZEREG, 0, 5) +FIELD(MOP_ISS, SRCREG, 5, 5) +FIELD(MOP_ISS, DESTREG, 10, 5) +FIELD(MOP_ISS, FORMATOPT, 16, 2) +FIELD(MOP_ISS, OPT_A, 16, 1) +FIELD(MOP_ISS, WRONG_OPT, 17, 1) +FIELD(MOP_ISS, EPILOGUE, 18, 1) +FIELD(MOP_ISS, OPTIONS, 19, 4) +FIELD(MOP_ISS, IS_SETG, 23, 1) +FIELD(MOP_ISS, MEMINST, 24, 1) + static inline uint32_t syn_mop(bool is_set, bool is_setg, int options, bool epilogue, bool wrong_option, bool option_a, int destreg, int srcreg, int sizereg) { - return (EC_MOP << ARM_EL_EC_SHIFT) | ARM_EL_IL | - (is_set << 24) | (is_setg << 23) | (options << 19) | - (epilogue << 18) | (wrong_option << 17) | (option_a << 16) | - (destreg << 10) | (srcreg << 5) | sizereg; + uint32_t res = syn_set_ec(0, EC_MOP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, MOP_ISS, MEMINST, is_set); + res = FIELD_DP32(res, MOP_ISS, IS_SETG, is_setg); + res = FIELD_DP32(res, MOP_ISS, OPTIONS, options); + res = FIELD_DP32(res, MOP_ISS, EPILOGUE, epilogue); + res = FIELD_DP32(res, MOP_ISS, WRONG_OPT, wrong_option); + res = FIELD_DP32(res, MOP_ISS, OPT_A, option_a); + res = FIELD_DP32(res, MOP_ISS, DESTREG, destreg); + res = FIELD_DP32(res, MOP_ISS, SRCREG, srcreg); + res = FIELD_DP32(res, MOP_ISS, SIZEREG, sizereg); + + return res; } -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> It shares the same COPROC_ISS encoding as the other CP traps although not all the fields are used. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-16-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 16 ++++++++++++++++ target/arm/tcg/vfp_helper.c | 5 +---- 2 files changed, 17 insertions(+), 4 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ FIELD(COPROC_ISS, OP2, 17, 3) FIELD(COPROC_ISS, COND, 20, 4) FIELD(COPROC_ISS, CV, 24, 1) +static inline uint32_t syn_cp10_rt_trap(int cv, int cond, int opc1, + int crn, int rt, int isread) +{ + uint32_t res = syn_set_ec(0, EC_FPIDTRAP); + res = FIELD_DP32(res, SYNDROME, IL, 1); + + res = FIELD_DP32(res, COPROC_ISS, CV, cv); + res = FIELD_DP32(res, COPROC_ISS, COND, cond); + res = FIELD_DP32(res, COPROC_ISS, OP1, opc1); + res = FIELD_DP32(res, COPROC_ISS, CRN, crn); + res = FIELD_DP32(res, COPROC_ISS, RT, rt); + res = FIELD_DP32(res, COPROC_ISS, ISREAD, isread); + + return res; +} + static inline uint32_t syn_cp14_rt_trap(int cv, int cond, int opc1, int opc2, int crn, int crm, int rt, int isread, bool is_16bit) diff --git a/target/arm/tcg/vfp_helper.c b/target/arm/tcg/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vfp_helper.c +++ b/target/arm/tcg/vfp_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(check_hcr_el2_trap)(CPUARMState *env, uint32_t rt, uint32_t reg) g_assert_not_reached(); } - syndrome = ((EC_FPIDTRAP << ARM_EL_EC_SHIFT) - | ARM_EL_IL - | (1 << 24) | (0xe << 20) | (7 << 14) - | (reg << 10) | (rt << 5) | 1); + syndrome = syn_cp10_rt_trap(1, 0xe, 7, reg, rt, 1); raise_exception(env, EXCP_HYP_TRAP, syndrome, 2); } -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> One more step towards dropping the old #defines. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-17-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch32_hyp(CPUState *cs) */ if (cs->exception_index == EXCP_PREFETCH_ABORT || (cs->exception_index == EXCP_DATA_ABORT && - !(env->exception.syndrome & ARM_EL_ISV)) || + !FIELD_EX32(env->exception.syndrome, SYNDROME, IL)) || syn_get_ec(env->exception.syndrome) == EC_UNCATEGORIZED) { - env->exception.syndrome &= ~ARM_EL_IL; + env->exception.syndrome = FIELD_DP32(env->exception.syndrome, SYNDROME, IL, 0); } } env->cp15.esr_el[2] = env->exception.syndrome; -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> This removes the last use of ARM_EL_EC_SHIFT. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-18-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 1 - target/arm/tcg/debug.c | 2 +- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ typedef enum { } GCSInstructionType; #define ARM_EL_EC_LENGTH 6 -#define ARM_EL_EC_SHIFT 26 #define ARM_EL_IL_SHIFT 25 #define ARM_EL_ISV_SHIFT 24 #define ARM_EL_IL (1 << ARM_EL_IL_SHIFT) diff --git a/target/arm/tcg/debug.c b/target/arm/tcg/debug.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/debug.c +++ b/target/arm/tcg/debug.c @@ -XXX,XX +XXX,XX @@ raise_exception_debug(CPUARMState *env, uint32_t excp, uint32_t syndrome) * Similarly for watchpoint and breakpoint matches. */ assert(debug_el >= cur_el); - syndrome |= (debug_el == cur_el) << ARM_EL_EC_SHIFT; + syndrome |= (debug_el == cur_el) << R_SYNDROME_EC_SHIFT; raise_exception(env, excp, syndrome, debug_el); } -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Rather than open coding a bunch of shifts and masks we can use the syndrome definitions. While we are at it assert it really is a EC_DATAABORT. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-19-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/whpx/whpx-all.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/target/arm/whpx/whpx-all.c b/target/arm/whpx/whpx-all.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/whpx/whpx-all.c +++ b/target/arm/whpx/whpx-all.c @@ -XXX,XX +XXX,XX @@ static int whpx_handle_mmio(CPUState *cpu, WHV_MEMORY_ACCESS_CONTEXT *ctx) { uint64_t syndrome = ctx->Syndrome; - bool isv = syndrome & ARM_EL_ISV; - bool iswrite = (syndrome >> 6) & 1; - bool sse = (syndrome >> 21) & 1; - uint32_t sas = (syndrome >> 22) & 3; + bool isv = FIELD_EX32(syndrome, DABORT_ISS, ISV); + bool iswrite = FIELD_EX32(syndrome, DABORT_ISS, WNR); + bool sse = FIELD_EX32(syndrome, DABORT_ISS, SSE); + uint32_t sas = FIELD_EX32(syndrome, DABORT_ISS, SAS); uint32_t len = 1 << sas; - uint32_t srt = (syndrome >> 16) & 0x1f; - uint32_t cm = (syndrome >> 8) & 0x1; + uint32_t srt = FIELD_EX32(syndrome, DABORT_ISS, SRT); + uint32_t cm = FIELD_EX32(syndrome, DABORT_ISS, CM); uint64_t val = 0; + assert(syn_get_ec(syndrome) == EC_DATAABORT); assert(!cm); assert(isv); -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Rather than open coding a bunch of shifts and masks we can use the syndrome definitions. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20260422125250.1303100-20-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/hvf/hvf.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/target/arm/hvf/hvf.c b/target/arm/hvf/hvf.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/hvf/hvf.c +++ b/target/arm/hvf/hvf.c @@ -XXX,XX +XXX,XX @@ static int hvf_handle_exception(CPUState *cpu, hv_vcpu_exit_exception_t *excp) break; } case EC_DATAABORT: { - bool isv = syndrome & ARM_EL_ISV; - bool iswrite = (syndrome >> 6) & 1; - bool s1ptw = (syndrome >> 7) & 1; - bool sse = (syndrome >> 21) & 1; - uint32_t sas = (syndrome >> 22) & 3; + bool isv = FIELD_EX32(syndrome, DABORT_ISS, ISV); + bool iswrite = FIELD_EX32(syndrome, DABORT_ISS, WNR); + bool s1ptw = FIELD_EX32(syndrome, DABORT_ISS, S1PTW); + bool sse = FIELD_EX32(syndrome, DABORT_ISS, SSE); + uint32_t sas = FIELD_EX32(syndrome, DABORT_ISS, SAS); uint32_t len = 1 << sas; - uint32_t srt = (syndrome >> 16) & 0x1f; - uint32_t cm = (syndrome >> 8) & 0x1; + uint32_t srt = FIELD_EX32(syndrome, DABORT_ISS, SRT); + uint32_t cm = FIELD_EX32(syndrome, DABORT_ISS, CM); uint64_t val = 0; uint64_t ipa = excp->physical_address; AddressSpace *as = cpu_get_address_space(cpu, ARMASIdx_NS); -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> One more step to removing the old defines. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-21-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/tlb_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/tcg/tlb_helper.c b/target/arm/tcg/tlb_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/tlb_helper.c +++ b/target/arm/tcg/tlb_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint64_t merge_syn_data_abort(uint32_t template_syn, */ assert(!fi->stage2); syn = syn_data_abort_vncr(fi->ea, is_write, fsc); - } else if (!(template_syn & ARM_EL_ISV) || target_el != 2 + } else if (!FIELD_EX32(template_syn, DABORT_ISS, ISV) || target_el != 2 || fi->s1ptw || !fi->stage2) { syn = syn_data_abort_no_iss(same_el, 0, fi->ea, 0, fi->s1ptw, is_write, fsc); -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> These are only valid for data abort syndromes. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-22-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/tlb_helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/tlb_helper.c b/target/arm/tcg/tlb_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/tlb_helper.c +++ b/target/arm/tcg/tlb_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint64_t merge_syn_data_abort(uint32_t template_syn, * ST64BV, or ST64BV0 insns report syndrome info even for stage-1 * faults and regardless of the target EL. */ - if (template_syn & ARM_EL_VNCR) { + if (FIELD_EX32(template_syn, DABORT_ISS, VNCR)) { /* * FEAT_NV2 faults on accesses via VNCR_EL2 are a special case: * they are always reported as "same EL", even though we are going @@ -XXX,XX +XXX,XX @@ void arm_deliver_fault(ARMCPU *cpu, vaddr addr, * because we masked that out in disas_set_insn_syndrome()) */ bool is_vncr = (access_type != MMU_INST_FETCH) && - (env->exception.syndrome & ARM_EL_VNCR); + FIELD_EX32(env->exception.syndrome, DABORT_ISS, VNCR); if (is_vncr) { /* FEAT_NV2 faults on accesses via VNCR_EL2 go to EL2 */ -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Now everything is defined with registerfields we can drop the old defines. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-23-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 9 --------- 1 file changed, 9 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ typedef enum { GCS_IT_GCSPOPX = 9, } GCSInstructionType; -#define ARM_EL_EC_LENGTH 6 -#define ARM_EL_IL_SHIFT 25 -#define ARM_EL_ISV_SHIFT 24 -#define ARM_EL_IL (1 << ARM_EL_IL_SHIFT) -#define ARM_EL_ISV (1 << ARM_EL_ISV_SHIFT) - -/* In the Data Abort syndrome */ -#define ARM_EL_VNCR (1 << 13) - static inline uint32_t syn_get_ec(uint32_t syn) { return FIELD_EX32(syn, SYNDROME, EC); -- 2.43.0 From: Alex Bennée <alex.bennee@linaro.org> Pass the register number (rd) to the wfit helper and report it in the syndrome ISS. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20260422125250.1303100-24-alex.bennee@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/syndrome.h | 11 ++++++++++- target/arm/tcg/helper-defs.h | 2 +- target/arm/tcg/op_helper.c | 7 ++++--- target/arm/tcg/translate-a64.c | 2 +- 4 files changed, 16 insertions(+), 6 deletions(-) diff --git a/target/arm/syndrome.h b/target/arm/syndrome.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/syndrome.h +++ b/target/arm/syndrome.h @@ -XXX,XX +XXX,XX @@ FIELD(WFX_ISS, RN, 5, 5) FIELD(WFX_ISS, COND, 20, 4) FIELD(WFX_ISS, CV, 24, 1) -static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit) +typedef enum { + WFI = 0b00, + WFE = 0b01, + WFIT = 0b10, + WFET = 0xb11 +} wfx_ti; + +static inline uint32_t syn_wfx(int cv, int cond, int rn, bool rv, wfx_ti ti, bool is_16bit) { uint32_t res = syn_set_ec(0, EC_WFX_TRAP); res = FIELD_DP32(res, SYNDROME, IL, !is_16bit); @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_wfx(int cv, int cond, int ti, bool is_16bit) res = FIELD_DP32(res, WFX_ISS, CV, cv); res = FIELD_DP32(res, WFX_ISS, COND, cond); res = FIELD_DP32(res, WFX_ISS, TI, ti); + res = FIELD_DP32(res, WFX_ISS, RN, rn); + res = FIELD_DP32(res, WFX_ISS, RV, rv); return res; } diff --git a/target/arm/tcg/helper-defs.h b/target/arm/tcg/helper-defs.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-defs.h +++ b/target/arm/tcg/helper-defs.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(exception_pc_alignment, noreturn, env, vaddr) DEF_HELPER_1(setend, void, env) DEF_HELPER_2(wfi, void, env, i32) DEF_HELPER_1(wfe, void, env) -DEF_HELPER_2(wfit, void, env, i64) +DEF_HELPER_2(wfit, void, env, i32) DEF_HELPER_1(yield, void, env) DEF_HELPER_1(pre_hvc, void, env) DEF_HELPER_2(pre_smc, void, env, i32) diff --git a/target/arm/tcg/op_helper.c b/target/arm/tcg/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/op_helper.c +++ b/target/arm/tcg/op_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(wfi)(CPUARMState *env, uint32_t insn_len) env->regs[15] -= insn_len; } - raise_exception(env, excp, syn_wfx(1, 0xe, 0, insn_len == 2), + raise_exception(env, excp, syn_wfx(1, 0xe, 0, false, WFI, insn_len == 2), target_el); } @@ -XXX,XX +XXX,XX @@ void HELPER(wfi)(CPUARMState *env, uint32_t insn_len) #endif } -void HELPER(wfit)(CPUARMState *env, uint64_t timeout) +void HELPER(wfit)(CPUARMState *env, uint32_t rd) { #ifdef CONFIG_USER_ONLY /* @@ -XXX,XX +XXX,XX @@ void HELPER(wfit)(CPUARMState *env, uint64_t timeout) int target_el = check_wfx_trap(env, false, &excp); /* The WFIT should time out when CNTVCT_EL0 >= the specified value. */ uint64_t cntval = gt_get_countervalue(env); + uint64_t timeout = env->xregs[rd]; /* * We want the value that we would get if we read CNTVCT_EL0 from * the current exception level, so the direct_access offset, not @@ -XXX,XX +XXX,XX @@ void HELPER(wfit)(CPUARMState *env, uint64_t timeout) if (target_el) { env->pc -= 4; - raise_exception(env, excp, syn_wfx(1, 0xe, 2, false), target_el); + raise_exception(env, excp, syn_wfx(1, 0xe, rd, true, WFIT, false), target_el); } if (uadd64_overflow(timeout, offset, &nexttick)) { diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_WFIT(DisasContext *s, arg_WFIT *a) } gen_a64_update_pc(s, 4); - gen_helper_wfit(tcg_env, cpu_reg(s, a->rd)); + gen_helper_wfit(tcg_env, tcg_constant_i32(a->rd)); /* Go back to the main loop to check for interrupts */ s->base.is_jmp = DISAS_EXIT; return true; -- 2.43.0