Just my fp16 work, plus some small stuff for the sbsa-ref board; but my rule of thumb is to send a pullreq once I get over about 30 patches... -- PMM The following changes since commit 2f4c51c0f384d7888a04b4815861e6d5fd244d75: Merge remote-tracking branch 'remotes/kraxel/tags/usb-20200831-pull-request' into staging (2020-08-31 19:39:13 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200901 for you to fetch changes up to 3f462bf0f6ea6382dd1502d4eb1fcd33c8e774f5: hw/arm/sbsa-ref : Add embedded controller in secure memory (2020-09-01 14:01:34 +0100) ---------------------------------------------------------------- target-arm queue: * Implement fp16 support for AArch32 VFP and Neon * hw/arm/sbsa-ref: add "reg" property to DT cpu nodes * hw/arm/sbsa-ref : Add embedded controller in secure memory ---------------------------------------------------------------- Graeme Gregory (2): hw/misc/sbsa_ec : Add an embedded controller for sbsa-ref hw/arm/sbsa-ref : Add embedded controller in secure memory Leif Lindholm (1): hw/arm/sbsa-ref: add "reg" property to DT cpu nodes Peter Maydell (44): target/arm: Remove local definitions of float constants target/arm: Use correct ID register check for aa32_fp16_arith target/arm: Implement VFP fp16 for VFP_BINOP operations target/arm: Implement VFP fp16 VMLA, VMLS, VNMLS, VNMLA, VNMUL target/arm: Macroify trans functions for VFMA, VFMS, VFNMA, VFNMS target/arm: Implement VFP fp16 for fused-multiply-add target/arm: Macroify uses of do_vfp_2op_sp() and do_vfp_2op_dp() target/arm: Implement VFP fp16 for VABS, VNEG, VSQRT target/arm: Implement VFP fp16 for VMOV immediate target/arm: Implement VFP fp16 VCMP target/arm: Implement VFP fp16 VLDR and VSTR target/arm: Implement VFP fp16 VCVT between float and integer target/arm: Make VFP_CONV_FIX macros take separate float type and float size target/arm: Use macros instead of open-coding fp16 conversion helpers target/arm: Implement VFP fp16 VCVT between float and fixed-point target/arm: Implement VFP vp16 VCVT-with-specified-rounding-mode target/arm: Implement VFP fp16 VSEL target/arm: Implement VFP fp16 VRINT* target/arm: Implement new VFP fp16 insn VINS target/arm: Implement new VFP fp16 insn VMOVX target/arm: Implement VFP fp16 VMOV between gp and halfprec registers target/arm: Implement FP16 for Neon VADD, VSUB, VABD, VMUL target/arm: Implement fp16 for Neon VRECPE, VRSQRTE using gvec target/arm: Implement fp16 for Neon VABS, VNEG of floats target/arm: Implement fp16 for VCEQ, VCGE, VCGT comparisons target/arm: Implement fp16 for VACGE, VACGT target/arm: Implement fp16 for Neon VMAX, VMIN target/arm: Implement fp16 for Neon VMAXNM, VMINNM target/arm: Implement fp16 for Neon VMLA, VMLS operations target/arm: Implement fp16 for Neon VFMA, VMFS target/arm: Implement fp16 for Neon fp compare-vs-0 target/arm: Implement fp16 for Neon VRECPS target/arm: Implement fp16 for Neon VRSQRTS target/arm: Implement fp16 for Neon pairwise fp ops target/arm: Implement fp16 for Neon float-integer VCVT target/arm: Convert Neon VCVT fixed-point to gvec target/arm: Implement fp16 for Neon VCVT fixed-point target/arm: Implement fp16 for Neon VCVT with rounding modes target/arm: Implement fp16 for Neon VRINT-with-specified-rounding-mode target/arm: Implement fp16 for Neon VRINTX target/arm/vec_helper: Handle oprsz less than 16 bytes in indexed operations target/arm/vec_helper: Add gvec fp indexed multiply-and-add operations target/arm: Implement fp16 for Neon VMUL, VMLA, VMLS target/arm: Enable FP16 in '-cpu max' target/arm/cpu.h | 7 +- target/arm/helper.h | 133 ++++++- target/arm/neon-dp.decode | 8 +- target/arm/vfp-uncond.decode | 27 +- target/arm/vfp.decode | 34 +- hw/arm/sbsa-ref.c | 43 ++- hw/misc/sbsa_ec.c | 98 +++++ target/arm/cpu.c | 3 +- target/arm/cpu64.c | 10 +- target/arm/helper-a64.c | 11 - target/arm/translate-sve.c | 4 - target/arm/vec_helper.c | 431 ++++++++++++++++++++- target/arm/vfp_helper.c | 244 +++++------- hw/misc/meson.build | 2 + target/arm/translate-neon.c.inc | 755 +++++++++++++------------------------ target/arm/translate-vfp.c.inc | 810 ++++++++++++++++++++++++++++++++++++---- 16 files changed, 1819 insertions(+), 801 deletions(-) create mode 100644 hw/misc/sbsa_ec.c In several places the target/arm code defines local float constants for 2, 3 and 1.5, which are also provided by include/fpu/softfloat.h. Remove the unnecessary local duplicate versions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-2-peter.maydell@linaro.org --- target/arm/helper-a64.c | 11 ----------- target/arm/translate-sve.c | 4 ---- target/arm/vfp_helper.c | 4 ---- 3 files changed, 19 deletions(-) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(neon_cgt_f64)(float64 a, float64 b, void *fpstp) * versions, these do a fully fused multiply-add or * multiply-add-and-halve. */ -#define float16_two make_float16(0x4000) -#define float16_three make_float16(0x4200) -#define float16_one_point_five make_float16(0x3e00) - -#define float32_two make_float32(0x40000000) -#define float32_three make_float32(0x40400000) -#define float32_one_point_five make_float32(0x3fc00000) - -#define float64_two make_float64(0x4000000000000000ULL) -#define float64_three make_float64(0x4008000000000000ULL) -#define float64_one_point_five make_float64(0x3FF8000000000000ULL) uint32_t HELPER(recpsf_f16)(uint32_t a, uint32_t b, void *fpstp) { diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_##NAME##_zpzi(DisasContext *s, arg_rpri_esz *a) \ return true; \ } -#define float16_two make_float16(0x4000) -#define float32_two make_float32(0x40000000) -#define float64_two make_float64(0x4000000000000000ULL) - DO_FP_IMM(FADD, fadds, half, one) DO_FP_IMM(FSUB, fsubs, half, one) DO_FP_IMM(FMUL, fmuls, half, two) 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) return r; } -#define float32_two make_float32(0x40000000) -#define float32_three make_float32(0x40400000) -#define float32_one_point_five make_float32(0x3fc00000) - float32 HELPER(recps_f32)(CPUARMState *env, float32 a, float32 b) { float_status *s = &env->vfp.standard_fp_status; -- 2.20.1 The aa32_fp16_arith feature check function currently looks at the AArch64 ID_AA64PFR0 register. This is (as the comment notes) not correct. The bogus check was put in mostly to allow testing of the fp16 variants of the VCMLA instructions and it was something of a mistake that we allowed them to exist in master. Switch the feature check function to testing VMFR1.FPHP, which is what it ought to be. This will remove emulation of the VCMLA and VCADD insns from AArch32 code running on an AArch64 '-cpu max' using system emulation. (They were never enabled for aarch32 linux-user and system-emulation.) Since we weren't advertising their existence via the AArch32 ID register, well-behaved guests wouldn't have been using them anyway. Once we have implemented all the AArch32 support for the FP16 extension we will advertise it in the MVFR1 ID register field, which will reenable these insns along with all the others. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-3-peter.maydell@linaro.org --- target/arm/cpu.h | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_predinv(const ARMISARegisters *id) static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id) { - /* - * This is a placeholder for use by VCMA until the rest of - * the ARMv8.2-FP16 extension is implemented for aa32 mode. - * At which point we can properly set and check MVFR1.FPHP. - */ - return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) == 1; + return FIELD_EX32(id->mvfr1, MVFR1, FPHP) >= 3; } static inline bool isar_feature_aa32_vfp_simd(const ARMISARegisters *id) -- 2.20.1 Implmeent VFP fp16 support for simple binary-operator VFP insns VADD, VSUB, VMUL, VDIV, VMINNM and VMAXNM: * make the VFP_BINOP() macro generate float16 helpers as well as float32 and float64 * implement a do_vfp_3op_hp() function similar to the existing do_vfp_3op_sp() * add decode for the half-precision insn patterns Note that the VFP_BINOP macro use creates a couple of unused helper functions vfp_maxh and vfp_minh, but they're small so it's not worth splitting the BINOP operations into "needs halfprec" and "no halfprec" groups. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-4-peter.maydell@linaro.org --- target/arm/helper.h | 8 ++++ target/arm/vfp-uncond.decode | 3 ++ target/arm/vfp.decode | 4 ++ target/arm/vfp_helper.c | 5 ++ target/arm/translate-vfp.c.inc | 86 ++++++++++++++++++++++++++++++++++ 5 files changed, 106 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(probe_access, TCG_CALL_NO_WG, void, env, tl, i32, i32, i32) DEF_HELPER_1(vfp_get_fpscr, i32, env) DEF_HELPER_2(vfp_set_fpscr, void, env, i32) +DEF_HELPER_3(vfp_addh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_adds, f32, f32, f32, ptr) DEF_HELPER_3(vfp_addd, f64, f64, f64, ptr) +DEF_HELPER_3(vfp_subh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_subs, f32, f32, f32, ptr) DEF_HELPER_3(vfp_subd, f64, f64, f64, ptr) +DEF_HELPER_3(vfp_mulh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_muls, f32, f32, f32, ptr) DEF_HELPER_3(vfp_muld, f64, f64, f64, ptr) +DEF_HELPER_3(vfp_divh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_divs, f32, f32, f32, ptr) DEF_HELPER_3(vfp_divd, f64, f64, f64, ptr) +DEF_HELPER_3(vfp_maxh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_maxs, f32, f32, f32, ptr) DEF_HELPER_3(vfp_maxd, f64, f64, f64, ptr) +DEF_HELPER_3(vfp_minh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_mins, f32, f32, f32, ptr) DEF_HELPER_3(vfp_mind, f64, f64, f64, ptr) +DEF_HELPER_3(vfp_maxnumh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_maxnums, f32, f32, f32, ptr) DEF_HELPER_3(vfp_maxnumd, f64, f64, f64, ptr) +DEF_HELPER_3(vfp_minnumh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_minnums, f32, f32, f32, ptr) DEF_HELPER_3(vfp_minnumd, f64, f64, f64, ptr) DEF_HELPER_1(vfp_negs, f32, f32) diff --git a/target/arm/vfp-uncond.decode b/target/arm/vfp-uncond.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp-uncond.decode +++ b/target/arm/vfp-uncond.decode @@ -XXX,XX +XXX,XX @@ VSEL 1111 1110 0. cc:2 .... .... 1010 .0.0 .... \ VSEL 1111 1110 0. cc:2 .... .... 1011 .0.0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp dp=1 +VMAXNM_hp 1111 1110 1.00 .... .... 1001 .0.0 .... @vfp_dnm_s +VMINNM_hp 1111 1110 1.00 .... .... 1001 .1.0 .... @vfp_dnm_s + VMAXNM_sp 1111 1110 1.00 .... .... 1010 .0.0 .... @vfp_dnm_s VMINNM_sp 1111 1110 1.00 .... .... 1010 .1.0 .... @vfp_dnm_s diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VNMLS_dp ---- 1110 0.01 .... .... 1011 .0.0 .... @vfp_dnm_d VNMLA_sp ---- 1110 0.01 .... .... 1010 .1.0 .... @vfp_dnm_s VNMLA_dp ---- 1110 0.01 .... .... 1011 .1.0 .... @vfp_dnm_d +VMUL_hp ---- 1110 0.10 .... .... 1001 .0.0 .... @vfp_dnm_s VMUL_sp ---- 1110 0.10 .... .... 1010 .0.0 .... @vfp_dnm_s VMUL_dp ---- 1110 0.10 .... .... 1011 .0.0 .... @vfp_dnm_d VNMUL_sp ---- 1110 0.10 .... .... 1010 .1.0 .... @vfp_dnm_s VNMUL_dp ---- 1110 0.10 .... .... 1011 .1.0 .... @vfp_dnm_d +VADD_hp ---- 1110 0.11 .... .... 1001 .0.0 .... @vfp_dnm_s VADD_sp ---- 1110 0.11 .... .... 1010 .0.0 .... @vfp_dnm_s VADD_dp ---- 1110 0.11 .... .... 1011 .0.0 .... @vfp_dnm_d +VSUB_hp ---- 1110 0.11 .... .... 1001 .1.0 .... @vfp_dnm_s VSUB_sp ---- 1110 0.11 .... .... 1010 .1.0 .... @vfp_dnm_s VSUB_dp ---- 1110 0.11 .... .... 1011 .1.0 .... @vfp_dnm_d +VDIV_hp ---- 1110 1.00 .... .... 1001 .0.0 .... @vfp_dnm_s VDIV_sp ---- 1110 1.00 .... .... 1010 .0.0 .... @vfp_dnm_s VDIV_dp ---- 1110 1.00 .... .... 1011 .0.0 .... @vfp_dnm_d diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val) #define VFP_HELPER(name, p) HELPER(glue(glue(vfp_,name),p)) #define VFP_BINOP(name) \ +dh_ctype_f16 VFP_HELPER(name, h)(dh_ctype_f16 a, dh_ctype_f16 b, void *fpstp) \ +{ \ + float_status *fpst = fpstp; \ + return float16_ ## name(a, b, fpst); \ +} \ float32 VFP_HELPER(name, s)(float32 a, float32 b, void *fpstp) \ { \ float_status *fpst = fpstp; \ diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_sp(DisasContext *s, VFPGen3OpSPFn *fn, return true; } +static bool do_vfp_3op_hp(DisasContext *s, VFPGen3OpSPFn *fn, + int vd, int vn, int vm, bool reads_vd) +{ + /* + * Do a half-precision operation. Functionally this is + * the same as do_vfp_3op_sp(), except: + * - it uses the FPST_FPCR_F16 + * - it doesn't need the VFP vector handling (fp16 is a + * v8 feature, and in v8 VFP vectors don't exist) + * - it does the aa32_fp16_arith feature test + */ + TCGv_i32 f0, f1, fd; + TCGv_ptr fpst; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (s->vec_len != 0 || s->vec_stride != 0) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + f0 = tcg_temp_new_i32(); + f1 = tcg_temp_new_i32(); + fd = tcg_temp_new_i32(); + fpst = fpstatus_ptr(FPST_FPCR_F16); + + neon_load_reg32(f0, vn); + neon_load_reg32(f1, vm); + + if (reads_vd) { + neon_load_reg32(fd, vd); + } + fn(fd, f0, f1, fpst); + neon_store_reg32(fd, vd); + + tcg_temp_free_i32(f0); + tcg_temp_free_i32(f1); + tcg_temp_free_i32(fd); + tcg_temp_free_ptr(fpst); + + return true; +} + static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn, int vd, int vn, int vm, bool reads_vd) { @@ -XXX,XX +XXX,XX @@ static bool trans_VNMLA_dp(DisasContext *s, arg_VNMLA_dp *a) return do_vfp_3op_dp(s, gen_VNMLA_dp, a->vd, a->vn, a->vm, true); } +static bool trans_VMUL_hp(DisasContext *s, arg_VMUL_sp *a) +{ + return do_vfp_3op_hp(s, gen_helper_vfp_mulh, a->vd, a->vn, a->vm, false); +} + static bool trans_VMUL_sp(DisasContext *s, arg_VMUL_sp *a) { return do_vfp_3op_sp(s, gen_helper_vfp_muls, a->vd, a->vn, a->vm, false); @@ -XXX,XX +XXX,XX @@ static bool trans_VNMUL_dp(DisasContext *s, arg_VNMUL_dp *a) return do_vfp_3op_dp(s, gen_VNMUL_dp, a->vd, a->vn, a->vm, false); } +static bool trans_VADD_hp(DisasContext *s, arg_VADD_sp *a) +{ + return do_vfp_3op_hp(s, gen_helper_vfp_addh, a->vd, a->vn, a->vm, false); +} + static bool trans_VADD_sp(DisasContext *s, arg_VADD_sp *a) { return do_vfp_3op_sp(s, gen_helper_vfp_adds, a->vd, a->vn, a->vm, false); @@ -XXX,XX +XXX,XX @@ static bool trans_VADD_dp(DisasContext *s, arg_VADD_dp *a) return do_vfp_3op_dp(s, gen_helper_vfp_addd, a->vd, a->vn, a->vm, false); } +static bool trans_VSUB_hp(DisasContext *s, arg_VSUB_sp *a) +{ + return do_vfp_3op_hp(s, gen_helper_vfp_subh, a->vd, a->vn, a->vm, false); +} + static bool trans_VSUB_sp(DisasContext *s, arg_VSUB_sp *a) { return do_vfp_3op_sp(s, gen_helper_vfp_subs, a->vd, a->vn, a->vm, false); @@ -XXX,XX +XXX,XX @@ static bool trans_VSUB_dp(DisasContext *s, arg_VSUB_dp *a) return do_vfp_3op_dp(s, gen_helper_vfp_subd, a->vd, a->vn, a->vm, false); } +static bool trans_VDIV_hp(DisasContext *s, arg_VDIV_sp *a) +{ + return do_vfp_3op_hp(s, gen_helper_vfp_divh, a->vd, a->vn, a->vm, false); +} + static bool trans_VDIV_sp(DisasContext *s, arg_VDIV_sp *a) { return do_vfp_3op_sp(s, gen_helper_vfp_divs, a->vd, a->vn, a->vm, false); @@ -XXX,XX +XXX,XX @@ static bool trans_VDIV_dp(DisasContext *s, arg_VDIV_dp *a) return do_vfp_3op_dp(s, gen_helper_vfp_divd, a->vd, a->vn, a->vm, false); } +static bool trans_VMINNM_hp(DisasContext *s, arg_VMINNM_sp *a) +{ + if (!dc_isar_feature(aa32_vminmaxnm, s)) { + return false; + } + return do_vfp_3op_hp(s, gen_helper_vfp_minnumh, + a->vd, a->vn, a->vm, false); +} + +static bool trans_VMAXNM_hp(DisasContext *s, arg_VMAXNM_sp *a) +{ + if (!dc_isar_feature(aa32_vminmaxnm, s)) { + return false; + } + return do_vfp_3op_hp(s, gen_helper_vfp_maxnumh, + a->vd, a->vn, a->vm, false); +} + static bool trans_VMINNM_sp(DisasContext *s, arg_VMINNM_sp *a) { if (!dc_isar_feature(aa32_vminmaxnm, s)) { -- 2.20.1 Implement fp16 versions of the VFP VMLA, VMLS, VNMLS, VNMLA, VNMUL instructions. (These are all the remaining ones which we implement via do_vfp_3op_[hsd]p().) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-5-peter.maydell@linaro.org --- target/arm/helper.h | 1 + target/arm/vfp.decode | 5 ++ target/arm/vfp_helper.c | 5 ++ target/arm/translate-vfp.c.inc | 84 ++++++++++++++++++++++++++++++++++ 4 files changed, 95 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_maxnumd, f64, f64, f64, ptr) DEF_HELPER_3(vfp_minnumh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_minnums, f32, f32, f32, ptr) DEF_HELPER_3(vfp_minnumd, f64, f64, f64, ptr) +DEF_HELPER_1(vfp_negh, f16, f16) DEF_HELPER_1(vfp_negs, f32, f32) DEF_HELPER_1(vfp_negd, f64, f64) DEF_HELPER_1(vfp_abss, f32, f32) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VLDM_VSTM_dp ---- 1101 0.1 l:1 rn:4 .... 1011 imm:8 \ vd=%vd_dp p=1 u=0 w=1 # 3-register VFP data-processing; bits [23,21:20,6] identify the operation. +VMLA_hp ---- 1110 0.00 .... .... 1001 .0.0 .... @vfp_dnm_s VMLA_sp ---- 1110 0.00 .... .... 1010 .0.0 .... @vfp_dnm_s VMLA_dp ---- 1110 0.00 .... .... 1011 .0.0 .... @vfp_dnm_d +VMLS_hp ---- 1110 0.00 .... .... 1001 .1.0 .... @vfp_dnm_s VMLS_sp ---- 1110 0.00 .... .... 1010 .1.0 .... @vfp_dnm_s VMLS_dp ---- 1110 0.00 .... .... 1011 .1.0 .... @vfp_dnm_d +VNMLS_hp ---- 1110 0.01 .... .... 1001 .0.0 .... @vfp_dnm_s VNMLS_sp ---- 1110 0.01 .... .... 1010 .0.0 .... @vfp_dnm_s VNMLS_dp ---- 1110 0.01 .... .... 1011 .0.0 .... @vfp_dnm_d +VNMLA_hp ---- 1110 0.01 .... .... 1001 .1.0 .... @vfp_dnm_s VNMLA_sp ---- 1110 0.01 .... .... 1010 .1.0 .... @vfp_dnm_s VNMLA_dp ---- 1110 0.01 .... .... 1011 .1.0 .... @vfp_dnm_d @@ -XXX,XX +XXX,XX @@ VMUL_hp ---- 1110 0.10 .... .... 1001 .0.0 .... @vfp_dnm_s VMUL_sp ---- 1110 0.10 .... .... 1010 .0.0 .... @vfp_dnm_s VMUL_dp ---- 1110 0.10 .... .... 1011 .0.0 .... @vfp_dnm_d +VNMUL_hp ---- 1110 0.10 .... .... 1001 .1.0 .... @vfp_dnm_s VNMUL_sp ---- 1110 0.10 .... .... 1010 .1.0 .... @vfp_dnm_s VNMUL_dp ---- 1110 0.10 .... .... 1011 .1.0 .... @vfp_dnm_d 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 @@ VFP_BINOP(minnum) VFP_BINOP(maxnum) #undef VFP_BINOP +dh_ctype_f16 VFP_HELPER(neg, h)(dh_ctype_f16 a) +{ + return float16_chs(a); +} + float32 VFP_HELPER(neg, s)(float32 a) { return float32_chs(a); diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) return true; } +static void gen_VMLA_hp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) +{ + /* Note that order of inputs to the add matters for NaNs */ + TCGv_i32 tmp = tcg_temp_new_i32(); + + gen_helper_vfp_mulh(tmp, vn, vm, fpst); + gen_helper_vfp_addh(vd, vd, tmp, fpst); + tcg_temp_free_i32(tmp); +} + +static bool trans_VMLA_hp(DisasContext *s, arg_VMLA_sp *a) +{ + return do_vfp_3op_hp(s, gen_VMLA_hp, a->vd, a->vn, a->vm, true); +} + static void gen_VMLA_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) { /* Note that order of inputs to the add matters for NaNs */ @@ -XXX,XX +XXX,XX @@ static bool trans_VMLA_dp(DisasContext *s, arg_VMLA_dp *a) return do_vfp_3op_dp(s, gen_VMLA_dp, a->vd, a->vn, a->vm, true); } +static void gen_VMLS_hp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) +{ + /* + * VMLS: vd = vd + -(vn * vm) + * Note that order of inputs to the add matters for NaNs. + */ + TCGv_i32 tmp = tcg_temp_new_i32(); + + gen_helper_vfp_mulh(tmp, vn, vm, fpst); + gen_helper_vfp_negh(tmp, tmp); + gen_helper_vfp_addh(vd, vd, tmp, fpst); + tcg_temp_free_i32(tmp); +} + +static bool trans_VMLS_hp(DisasContext *s, arg_VMLS_sp *a) +{ + return do_vfp_3op_hp(s, gen_VMLS_hp, a->vd, a->vn, a->vm, true); +} + static void gen_VMLS_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) { /* @@ -XXX,XX +XXX,XX @@ static bool trans_VMLS_dp(DisasContext *s, arg_VMLS_dp *a) return do_vfp_3op_dp(s, gen_VMLS_dp, a->vd, a->vn, a->vm, true); } +static void gen_VNMLS_hp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) +{ + /* + * VNMLS: -fd + (fn * fm) + * Note that it isn't valid to replace (-A + B) with (B - A) or similar + * plausible looking simplifications because this will give wrong results + * for NaNs. + */ + TCGv_i32 tmp = tcg_temp_new_i32(); + + gen_helper_vfp_mulh(tmp, vn, vm, fpst); + gen_helper_vfp_negh(vd, vd); + gen_helper_vfp_addh(vd, vd, tmp, fpst); + tcg_temp_free_i32(tmp); +} + +static bool trans_VNMLS_hp(DisasContext *s, arg_VNMLS_sp *a) +{ + return do_vfp_3op_hp(s, gen_VNMLS_hp, a->vd, a->vn, a->vm, true); +} + static void gen_VNMLS_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) { /* @@ -XXX,XX +XXX,XX @@ static bool trans_VNMLS_dp(DisasContext *s, arg_VNMLS_dp *a) return do_vfp_3op_dp(s, gen_VNMLS_dp, a->vd, a->vn, a->vm, true); } +static void gen_VNMLA_hp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) +{ + /* VNMLA: -fd + -(fn * fm) */ + TCGv_i32 tmp = tcg_temp_new_i32(); + + gen_helper_vfp_mulh(tmp, vn, vm, fpst); + gen_helper_vfp_negh(tmp, tmp); + gen_helper_vfp_negh(vd, vd); + gen_helper_vfp_addh(vd, vd, tmp, fpst); + tcg_temp_free_i32(tmp); +} + +static bool trans_VNMLA_hp(DisasContext *s, arg_VNMLA_sp *a) +{ + return do_vfp_3op_hp(s, gen_VNMLA_hp, a->vd, a->vn, a->vm, true); +} + static void gen_VNMLA_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) { /* VNMLA: -fd + -(fn * fm) */ @@ -XXX,XX +XXX,XX @@ static bool trans_VMUL_dp(DisasContext *s, arg_VMUL_dp *a) return do_vfp_3op_dp(s, gen_helper_vfp_muld, a->vd, a->vn, a->vm, false); } +static void gen_VNMUL_hp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) +{ + /* VNMUL: -(fn * fm) */ + gen_helper_vfp_mulh(vd, vn, vm, fpst); + gen_helper_vfp_negh(vd, vd); +} + +static bool trans_VNMUL_hp(DisasContext *s, arg_VNMUL_sp *a) +{ + return do_vfp_3op_hp(s, gen_VNMUL_hp, a->vd, a->vn, a->vm, false); +} + static void gen_VNMUL_sp(TCGv_i32 vd, TCGv_i32 vn, TCGv_i32 vm, TCGv_ptr fpst) { /* VNMUL: -(fn * fm) */ -- 2.20.1 Macroify creation of the trans functions for single and double precision VFMA, VFMS, VFNMA, VFNMS. The repetition was OK for two sizes, but we're about to add halfprec and it will get a bit more than seems reasonable. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-6-peter.maydell@linaro.org --- target/arm/translate-vfp.c.inc | 50 +++++++++------------------------- 1 file changed, 13 insertions(+), 37 deletions(-) diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_vfm_sp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) return true; } -static bool trans_VFMA_sp(DisasContext *s, arg_VFMA_sp *a) -{ - return do_vfm_sp(s, a, false, false); -} - -static bool trans_VFMS_sp(DisasContext *s, arg_VFMS_sp *a) -{ - return do_vfm_sp(s, a, true, false); -} - -static bool trans_VFNMA_sp(DisasContext *s, arg_VFNMA_sp *a) -{ - return do_vfm_sp(s, a, false, true); -} - -static bool trans_VFNMS_sp(DisasContext *s, arg_VFNMS_sp *a) -{ - return do_vfm_sp(s, a, true, true); -} - static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d) { /* @@ -XXX,XX +XXX,XX @@ static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d) return true; } -static bool trans_VFMA_dp(DisasContext *s, arg_VFMA_dp *a) -{ - return do_vfm_dp(s, a, false, false); -} +#define MAKE_ONE_VFM_TRANS_FN(INSN, PREC, NEGN, NEGD) \ + static bool trans_##INSN##_##PREC(DisasContext *s, \ + arg_##INSN##_##PREC *a) \ + { \ + return do_vfm_##PREC(s, a, NEGN, NEGD); \ + } -static bool trans_VFMS_dp(DisasContext *s, arg_VFMS_dp *a) -{ - return do_vfm_dp(s, a, true, false); -} +#define MAKE_VFM_TRANS_FNS(PREC) \ + MAKE_ONE_VFM_TRANS_FN(VFMA, PREC, false, false) \ + MAKE_ONE_VFM_TRANS_FN(VFMS, PREC, true, false) \ + MAKE_ONE_VFM_TRANS_FN(VFNMA, PREC, false, true) \ + MAKE_ONE_VFM_TRANS_FN(VFNMS, PREC, true, true) -static bool trans_VFNMA_dp(DisasContext *s, arg_VFNMA_dp *a) -{ - return do_vfm_dp(s, a, false, true); -} - -static bool trans_VFNMS_dp(DisasContext *s, arg_VFNMS_dp *a) -{ - return do_vfm_dp(s, a, true, true); -} +MAKE_VFM_TRANS_FNS(sp) +MAKE_VFM_TRANS_FNS(dp) static bool trans_VMOV_imm_sp(DisasContext *s, arg_VMOV_imm_sp *a) { -- 2.20.1 Implement VFP fp16 support for fused multiply-add insns VFNMA, VFNMS, VFMA, VFMS. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-7-peter.maydell@linaro.org --- target/arm/helper.h | 1 + target/arm/vfp.decode | 5 +++ target/arm/vfp_helper.c | 7 ++++ target/arm/translate-vfp.c.inc | 64 ++++++++++++++++++++++++++++++++++ 4 files changed, 77 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_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_4(vfp_muladdh, f16, f16, f16, f16, ptr) DEF_HELPER_3(recps_f32, f32, env, f32, f32) DEF_HELPER_3(rsqrts_f32, f32, env, f32, f32) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VDIV_hp ---- 1110 1.00 .... .... 1001 .0.0 .... @vfp_dnm_s VDIV_sp ---- 1110 1.00 .... .... 1010 .0.0 .... @vfp_dnm_s VDIV_dp ---- 1110 1.00 .... .... 1011 .0.0 .... @vfp_dnm_d +VFMA_hp ---- 1110 1.10 .... .... 1001 .0. 0 .... @vfp_dnm_s +VFMS_hp ---- 1110 1.10 .... .... 1001 .1. 0 .... @vfp_dnm_s +VFNMA_hp ---- 1110 1.01 .... .... 1001 .0. 0 .... @vfp_dnm_s +VFNMS_hp ---- 1110 1.01 .... .... 1001 .1. 0 .... @vfp_dnm_s + VFMA_sp ---- 1110 1.10 .... .... 1010 .0. 0 .... @vfp_dnm_s VFMS_sp ---- 1110 1.10 .... .... 1010 .1. 0 .... @vfp_dnm_s VFNMA_sp ---- 1110 1.01 .... .... 1010 .0. 0 .... @vfp_dnm_s 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(rsqrte_u32)(uint32_t a) } /* VFPv4 fused multiply-accumulate */ +dh_ctype_f16 VFP_HELPER(muladd, h)(dh_ctype_f16 a, dh_ctype_f16 b, + dh_ctype_f16 c, void *fpstp) +{ + float_status *fpst = fpstp; + return float16_muladd(a, b, c, 0, fpst); +} + float32 VFP_HELPER(muladd, s)(float32 a, float32 b, float32 c, void *fpstp) { float_status *fpst = fpstp; diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMAXNM_dp(DisasContext *s, arg_VMAXNM_dp *a) a->vd, a->vn, a->vm, false); } +static bool do_vfm_hp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) +{ + /* + * VFNMA : fd = muladd(-fd, fn, fm) + * VFNMS : fd = muladd(-fd, -fn, fm) + * VFMA : fd = muladd( fd, fn, fm) + * VFMS : fd = muladd( fd, -fn, fm) + * + * These are fused multiply-add, and must be done as one floating + * point operation with no rounding between the multiplication and + * addition steps. NB that doing the negations here as separate + * steps is correct : an input NaN should come out with its sign + * bit flipped if it is a negated-input. + */ + TCGv_ptr fpst; + TCGv_i32 vn, vm, vd; + + /* + * Present in VFPv4 only, and only with the FP16 extension. + * Note that we can't rely on the SIMDFMAC check alone, because + * in a Neon-no-VFP core that ID register field will be non-zero. + */ + if (!dc_isar_feature(aa32_fp16_arith, s) || + !dc_isar_feature(aa32_simdfmac, s) || + !dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + + if (s->vec_len != 0 || s->vec_stride != 0) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + vn = tcg_temp_new_i32(); + vm = tcg_temp_new_i32(); + vd = tcg_temp_new_i32(); + + neon_load_reg32(vn, a->vn); + neon_load_reg32(vm, a->vm); + if (neg_n) { + /* VFNMS, VFMS */ + gen_helper_vfp_negh(vn, vn); + } + neon_load_reg32(vd, a->vd); + if (neg_d) { + /* VFNMA, VFNMS */ + gen_helper_vfp_negh(vd, vd); + } + fpst = fpstatus_ptr(FPST_FPCR_F16); + gen_helper_vfp_muladdh(vd, vn, vm, vd, fpst); + neon_store_reg32(vd, a->vd); + + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(vn); + tcg_temp_free_i32(vm); + tcg_temp_free_i32(vd); + + return true; +} + static bool do_vfm_sp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) { /* @@ -XXX,XX +XXX,XX @@ static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d) MAKE_ONE_VFM_TRANS_FN(VFNMA, PREC, false, true) \ MAKE_ONE_VFM_TRANS_FN(VFNMS, PREC, true, true) +MAKE_VFM_TRANS_FNS(hp) MAKE_VFM_TRANS_FNS(sp) MAKE_VFM_TRANS_FNS(dp) -- 2.20.1 Macroify the uses of do_vfp_2op_sp() and do_vfp_2op_dp(); this will make it easier to add the halfprec support. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-8-peter.maydell@linaro.org --- target/arm/translate-vfp.c.inc | 49 ++++++++++------------------------ 1 file changed, 14 insertions(+), 35 deletions(-) diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) return true; } -static bool trans_VMOV_reg_sp(DisasContext *s, arg_VMOV_reg_sp *a) -{ - return do_vfp_2op_sp(s, tcg_gen_mov_i32, a->vd, a->vm); -} +#define DO_VFP_2OP(INSN, PREC, FN) \ + static bool trans_##INSN##_##PREC(DisasContext *s, \ + arg_##INSN##_##PREC *a) \ + { \ + return do_vfp_2op_##PREC(s, FN, a->vd, a->vm); \ + } -static bool trans_VMOV_reg_dp(DisasContext *s, arg_VMOV_reg_dp *a) -{ - return do_vfp_2op_dp(s, tcg_gen_mov_i64, a->vd, a->vm); -} +DO_VFP_2OP(VMOV_reg, sp, tcg_gen_mov_i32) +DO_VFP_2OP(VMOV_reg, dp, tcg_gen_mov_i64) -static bool trans_VABS_sp(DisasContext *s, arg_VABS_sp *a) -{ - return do_vfp_2op_sp(s, gen_helper_vfp_abss, a->vd, a->vm); -} +DO_VFP_2OP(VABS, sp, gen_helper_vfp_abss) +DO_VFP_2OP(VABS, dp, gen_helper_vfp_absd) -static bool trans_VABS_dp(DisasContext *s, arg_VABS_dp *a) -{ - return do_vfp_2op_dp(s, gen_helper_vfp_absd, a->vd, a->vm); -} - -static bool trans_VNEG_sp(DisasContext *s, arg_VNEG_sp *a) -{ - return do_vfp_2op_sp(s, gen_helper_vfp_negs, a->vd, a->vm); -} - -static bool trans_VNEG_dp(DisasContext *s, arg_VNEG_dp *a) -{ - return do_vfp_2op_dp(s, gen_helper_vfp_negd, a->vd, a->vm); -} +DO_VFP_2OP(VNEG, sp, gen_helper_vfp_negs) +DO_VFP_2OP(VNEG, dp, gen_helper_vfp_negd) static void gen_VSQRT_sp(TCGv_i32 vd, TCGv_i32 vm) { gen_helper_vfp_sqrts(vd, vm, cpu_env); } -static bool trans_VSQRT_sp(DisasContext *s, arg_VSQRT_sp *a) -{ - return do_vfp_2op_sp(s, gen_VSQRT_sp, a->vd, a->vm); -} - static void gen_VSQRT_dp(TCGv_i64 vd, TCGv_i64 vm) { gen_helper_vfp_sqrtd(vd, vm, cpu_env); } -static bool trans_VSQRT_dp(DisasContext *s, arg_VSQRT_dp *a) -{ - return do_vfp_2op_dp(s, gen_VSQRT_dp, a->vd, a->vm); -} +DO_VFP_2OP(VSQRT, sp, gen_VSQRT_sp) +DO_VFP_2OP(VSQRT, dp, gen_VSQRT_dp) static bool trans_VCMP_sp(DisasContext *s, arg_VCMP_sp *a) { -- 2.20.1 Implement VFP fp16 for VABS, VNEG and VSQRT. This is all the fp16 insns that use the DO_VFP_2OP macro, because there is no fp16 version of VMOV_reg. Notes: * the gen_helper_vfp_negh already exists as we needed to create it for the fp16 multiply-add insns * as usual we need to use the f16 version of the fp_status; this is only relevant for VSQRT Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-9-peter.maydell@linaro.org --- target/arm/helper.h | 2 ++ target/arm/vfp.decode | 3 +++ target/arm/vfp_helper.c | 10 +++++++++ target/arm/translate-vfp.c.inc | 40 ++++++++++++++++++++++++++++++++++ 4 files changed, 55 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_minnumd, f64, f64, f64, ptr) DEF_HELPER_1(vfp_negh, f16, f16) DEF_HELPER_1(vfp_negs, f32, f32) DEF_HELPER_1(vfp_negd, f64, f64) +DEF_HELPER_1(vfp_absh, f16, f16) DEF_HELPER_1(vfp_abss, f32, f32) DEF_HELPER_1(vfp_absd, f64, f64) +DEF_HELPER_2(vfp_sqrth, f16, f16, env) DEF_HELPER_2(vfp_sqrts, f32, f32, env) DEF_HELPER_2(vfp_sqrtd, f64, f64, env) DEF_HELPER_3(vfp_cmps, void, f32, f32, env) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VMOV_imm_dp ---- 1110 1.11 .... .... 1011 0000 .... \ VMOV_reg_sp ---- 1110 1.11 0000 .... 1010 01.0 .... @vfp_dm_ss VMOV_reg_dp ---- 1110 1.11 0000 .... 1011 01.0 .... @vfp_dm_dd +VABS_hp ---- 1110 1.11 0000 .... 1001 11.0 .... @vfp_dm_ss VABS_sp ---- 1110 1.11 0000 .... 1010 11.0 .... @vfp_dm_ss VABS_dp ---- 1110 1.11 0000 .... 1011 11.0 .... @vfp_dm_dd +VNEG_hp ---- 1110 1.11 0001 .... 1001 01.0 .... @vfp_dm_ss VNEG_sp ---- 1110 1.11 0001 .... 1010 01.0 .... @vfp_dm_ss VNEG_dp ---- 1110 1.11 0001 .... 1011 01.0 .... @vfp_dm_dd +VSQRT_hp ---- 1110 1.11 0001 .... 1001 11.0 .... @vfp_dm_ss VSQRT_sp ---- 1110 1.11 0001 .... 1010 11.0 .... @vfp_dm_ss VSQRT_dp ---- 1110 1.11 0001 .... 1011 11.0 .... @vfp_dm_dd 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 VFP_HELPER(neg, d)(float64 a) return float64_chs(a); } +dh_ctype_f16 VFP_HELPER(abs, h)(dh_ctype_f16 a) +{ + return float16_abs(a); +} + float32 VFP_HELPER(abs, s)(float32 a) { return float32_abs(a); @@ -XXX,XX +XXX,XX @@ float64 VFP_HELPER(abs, d)(float64 a) return float64_abs(a); } +dh_ctype_f16 VFP_HELPER(sqrt, h)(dh_ctype_f16 a, CPUARMState *env) +{ + return float16_sqrt(a, &env->vfp.fp_status_f16); +} + float32 VFP_HELPER(sqrt, s)(float32 a, CPUARMState *env) { return float32_sqrt(a, &env->vfp.fp_status); diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) return true; } +static bool do_vfp_2op_hp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) +{ + /* + * Do a half-precision operation. Functionally this is + * the same as do_vfp_2op_sp(), except: + * - it doesn't need the VFP vector handling (fp16 is a + * v8 feature, and in v8 VFP vectors don't exist) + * - it does the aa32_fp16_arith feature test + */ + TCGv_i32 f0; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (s->vec_len != 0 || s->vec_stride != 0) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + f0 = tcg_temp_new_i32(); + neon_load_reg32(f0, vm); + fn(f0, f0); + neon_store_reg32(f0, vd); + tcg_temp_free_i32(f0); + + return true; +} + static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) { uint32_t delta_m = 0; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) DO_VFP_2OP(VMOV_reg, sp, tcg_gen_mov_i32) DO_VFP_2OP(VMOV_reg, dp, tcg_gen_mov_i64) +DO_VFP_2OP(VABS, hp, gen_helper_vfp_absh) DO_VFP_2OP(VABS, sp, gen_helper_vfp_abss) DO_VFP_2OP(VABS, dp, gen_helper_vfp_absd) +DO_VFP_2OP(VNEG, hp, gen_helper_vfp_negh) DO_VFP_2OP(VNEG, sp, gen_helper_vfp_negs) DO_VFP_2OP(VNEG, dp, gen_helper_vfp_negd) +static void gen_VSQRT_hp(TCGv_i32 vd, TCGv_i32 vm) +{ + gen_helper_vfp_sqrth(vd, vm, cpu_env); +} + static void gen_VSQRT_sp(TCGv_i32 vd, TCGv_i32 vm) { gen_helper_vfp_sqrts(vd, vm, cpu_env); @@ -XXX,XX +XXX,XX @@ static void gen_VSQRT_dp(TCGv_i64 vd, TCGv_i64 vm) gen_helper_vfp_sqrtd(vd, vm, cpu_env); } +DO_VFP_2OP(VSQRT, hp, gen_VSQRT_hp) DO_VFP_2OP(VSQRT, sp, gen_VSQRT_sp) DO_VFP_2OP(VSQRT, dp, gen_VSQRT_dp) -- 2.20.1 Implement VFP fp16 support for the VMOV immediate insn. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-10-peter.maydell@linaro.org --- target/arm/vfp.decode | 2 ++ target/arm/translate-vfp.c.inc | 22 ++++++++++++++++++++++ 2 files changed, 24 insertions(+) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VFMS_dp ---- 1110 1.10 .... .... 1011 .1.0 .... @vfp_dnm_d VFNMA_dp ---- 1110 1.01 .... .... 1011 .0.0 .... @vfp_dnm_d VFNMS_dp ---- 1110 1.01 .... .... 1011 .1.0 .... @vfp_dnm_d +VMOV_imm_hp ---- 1110 1.11 .... .... 1001 0000 .... \ + vd=%vd_sp imm=%vmov_imm VMOV_imm_sp ---- 1110 1.11 .... .... 1010 0000 .... \ vd=%vd_sp imm=%vmov_imm VMOV_imm_dp ---- 1110 1.11 .... .... 1011 0000 .... \ diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ MAKE_VFM_TRANS_FNS(hp) MAKE_VFM_TRANS_FNS(sp) MAKE_VFM_TRANS_FNS(dp) +static bool trans_VMOV_imm_hp(DisasContext *s, arg_VMOV_imm_sp *a) +{ + TCGv_i32 fd; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (s->vec_len != 0 || s->vec_stride != 0) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fd = tcg_const_i32(vfp_expand_imm(MO_16, a->imm)); + neon_store_reg32(fd, a->vd); + tcg_temp_free_i32(fd); + return true; +} + static bool trans_VMOV_imm_sp(DisasContext *s, arg_VMOV_imm_sp *a) { uint32_t delta_d = 0; -- 2.20.1 Implement fp16 version of VCMP. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-11-peter.maydell@linaro.org --- target/arm/helper.h | 2 ++ target/arm/vfp.decode | 2 ++ target/arm/vfp_helper.c | 15 +++++++------ target/arm/translate-vfp.c.inc | 39 ++++++++++++++++++++++++++++++++++ 4 files changed, 51 insertions(+), 7 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_1(vfp_absd, f64, f64) DEF_HELPER_2(vfp_sqrth, f16, f16, env) DEF_HELPER_2(vfp_sqrts, f32, f32, env) DEF_HELPER_2(vfp_sqrtd, f64, f64, env) +DEF_HELPER_3(vfp_cmph, void, f16, f16, env) DEF_HELPER_3(vfp_cmps, void, f32, f32, env) DEF_HELPER_3(vfp_cmpd, void, f64, f64, env) +DEF_HELPER_3(vfp_cmpeh, void, f16, f16, env) DEF_HELPER_3(vfp_cmpes, void, f32, f32, env) DEF_HELPER_3(vfp_cmped, void, f64, f64, env) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VSQRT_hp ---- 1110 1.11 0001 .... 1001 11.0 .... @vfp_dm_ss VSQRT_sp ---- 1110 1.11 0001 .... 1010 11.0 .... @vfp_dm_ss VSQRT_dp ---- 1110 1.11 0001 .... 1011 11.0 .... @vfp_dm_dd +VCMP_hp ---- 1110 1.11 010 z:1 .... 1001 e:1 1.0 .... \ + vd=%vd_sp vm=%vm_sp VCMP_sp ---- 1110 1.11 010 z:1 .... 1010 e:1 1.0 .... \ vd=%vd_sp vm=%vm_sp VCMP_dp ---- 1110 1.11 010 z:1 .... 1011 e:1 1.0 .... \ 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 @@ static void softfloat_to_vfp_compare(CPUARMState *env, FloatRelation cmp) } /* XXX: check quiet/signaling case */ -#define DO_VFP_cmp(p, type) \ -void VFP_HELPER(cmp, p)(type a, type b, CPUARMState *env) \ +#define DO_VFP_cmp(P, FLOATTYPE, ARGTYPE, FPST) \ +void VFP_HELPER(cmp, P)(ARGTYPE a, ARGTYPE b, CPUARMState *env) \ { \ softfloat_to_vfp_compare(env, \ - type ## _compare_quiet(a, b, &env->vfp.fp_status)); \ + FLOATTYPE ## _compare_quiet(a, b, &env->vfp.FPST)); \ } \ -void VFP_HELPER(cmpe, p)(type a, type b, CPUARMState *env) \ +void VFP_HELPER(cmpe, P)(ARGTYPE a, ARGTYPE b, CPUARMState *env) \ { \ softfloat_to_vfp_compare(env, \ - type ## _compare(a, b, &env->vfp.fp_status)); \ + FLOATTYPE ## _compare(a, b, &env->vfp.FPST)); \ } -DO_VFP_cmp(s, float32) -DO_VFP_cmp(d, float64) +DO_VFP_cmp(h, float16, dh_ctype_f16, fp_status_f16) +DO_VFP_cmp(s, float32, float32, fp_status) +DO_VFP_cmp(d, float64, float64, fp_status) #undef DO_VFP_cmp /* Integer to float and float to integer conversions */ diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ DO_VFP_2OP(VSQRT, hp, gen_VSQRT_hp) DO_VFP_2OP(VSQRT, sp, gen_VSQRT_sp) DO_VFP_2OP(VSQRT, dp, gen_VSQRT_dp) +static bool trans_VCMP_hp(DisasContext *s, arg_VCMP_sp *a) +{ + TCGv_i32 vd, vm; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + /* Vm/M bits must be zero for the Z variant */ + if (a->z && a->vm != 0) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + vd = tcg_temp_new_i32(); + vm = tcg_temp_new_i32(); + + neon_load_reg32(vd, a->vd); + if (a->z) { + tcg_gen_movi_i32(vm, 0); + } else { + neon_load_reg32(vm, a->vm); + } + + if (a->e) { + gen_helper_vfp_cmpeh(vd, vm, cpu_env); + } else { + gen_helper_vfp_cmph(vd, vm, cpu_env); + } + + tcg_temp_free_i32(vd); + tcg_temp_free_i32(vm); + + return true; +} + static bool trans_VCMP_sp(DisasContext *s, arg_VCMP_sp *a) { TCGv_i32 vd, vm; -- 2.20.1 Implement the fp16 versions of the VFP VLDR/VSTR (immediate). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-12-peter.maydell@linaro.org --- target/arm/vfp.decode | 3 +-- target/arm/translate-vfp.c.inc | 35 ++++++++++++++++++++++++++++++++++ 2 files changed, 36 insertions(+), 2 deletions(-) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VMOV_single ---- 1110 000 l:1 .... rt:4 1010 . 001 0000 vn=%vn_sp VMOV_64_sp ---- 1100 010 op:1 rt2:4 rt:4 1010 00.1 .... vm=%vm_sp VMOV_64_dp ---- 1100 010 op:1 rt2:4 rt:4 1011 00.1 .... vm=%vm_dp -# Note that the half-precision variants of VLDR and VSTR are -# not part of this decodetree at all because they have bits [9:8] == 0b01 +VLDR_VSTR_hp ---- 1101 u:1 .0 l:1 rn:4 .... 1001 imm:8 vd=%vd_sp VLDR_VSTR_sp ---- 1101 u:1 .0 l:1 rn:4 .... 1010 imm:8 vd=%vd_sp VLDR_VSTR_dp ---- 1101 u:1 .0 l:1 rn:4 .... 1011 imm:8 vd=%vd_dp diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_dp *a) return true; } +static bool trans_VLDR_VSTR_hp(DisasContext *s, arg_VLDR_VSTR_sp *a) +{ + uint32_t offset; + TCGv_i32 addr, tmp; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* imm8 field is offset/2 for fp16, unlike fp32 and fp64 */ + offset = a->imm << 1; + if (!a->u) { + offset = -offset; + } + + /* For thumb, use of PC is UNPREDICTABLE. */ + addr = add_reg_for_lit(s, a->rn, offset); + tmp = tcg_temp_new_i32(); + if (a->l) { + gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); + neon_store_reg32(tmp, a->vd); + } else { + neon_load_reg32(tmp, a->vd); + gen_aa32_st16(s, tmp, addr, get_mem_index(s)); + } + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(addr); + + return true; +} + static bool trans_VLDR_VSTR_sp(DisasContext *s, arg_VLDR_VSTR_sp *a) { uint32_t offset; -- 2.20.1 Implement the fp16 versions of the VFP VCVT instruction forms which convert between floating point and integer. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-13-peter.maydell@linaro.org --- target/arm/vfp.decode | 4 +++ target/arm/translate-vfp.c.inc | 65 ++++++++++++++++++++++++++++++++++ 2 files changed, 69 insertions(+) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VCVT_sp ---- 1110 1.11 0111 .... 1010 11.0 .... @vfp_dm_ds VCVT_dp ---- 1110 1.11 0111 .... 1011 11.0 .... @vfp_dm_sd # VCVT from integer to floating point: Vm always single; Vd depends on size +VCVT_int_hp ---- 1110 1.11 1000 .... 1001 s:1 1.0 .... \ + vd=%vd_sp vm=%vm_sp VCVT_int_sp ---- 1110 1.11 1000 .... 1010 s:1 1.0 .... \ vd=%vd_sp vm=%vm_sp VCVT_int_dp ---- 1110 1.11 1000 .... 1011 s:1 1.0 .... \ @@ -XXX,XX +XXX,XX @@ VCVT_fix_dp ---- 1110 1.11 1.1. .... 1011 .1.0 .... \ vd=%vd_dp imm=%vm_sp opc=%vcvt_fix_op # VCVT float to integer (VCVT and VCVTR): Vd always single; Vd depends on size +VCVT_hp_int ---- 1110 1.11 110 s:1 .... 1001 rz:1 1.0 .... \ + vd=%vd_sp vm=%vm_sp VCVT_sp_int ---- 1110 1.11 110 s:1 .... 1010 rz:1 1.0 .... \ vd=%vd_sp vm=%vm_sp VCVT_dp_int ---- 1110 1.11 110 s:1 .... 1011 rz:1 1.0 .... \ diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a) return true; } +static bool trans_VCVT_int_hp(DisasContext *s, arg_VCVT_int_sp *a) +{ + TCGv_i32 vm; + TCGv_ptr fpst; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + vm = tcg_temp_new_i32(); + neon_load_reg32(vm, a->vm); + fpst = fpstatus_ptr(FPST_FPCR_F16); + if (a->s) { + /* i32 -> f16 */ + gen_helper_vfp_sitoh(vm, vm, fpst); + } else { + /* u32 -> f16 */ + gen_helper_vfp_uitoh(vm, vm, fpst); + } + neon_store_reg32(vm, a->vd); + tcg_temp_free_i32(vm); + tcg_temp_free_ptr(fpst); + return true; +} + static bool trans_VCVT_int_sp(DisasContext *s, arg_VCVT_int_sp *a) { TCGv_i32 vm; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) return true; } +static bool trans_VCVT_hp_int(DisasContext *s, arg_VCVT_sp_int *a) +{ + TCGv_i32 vm; + TCGv_ptr fpst; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + fpst = fpstatus_ptr(FPST_FPCR_F16); + vm = tcg_temp_new_i32(); + neon_load_reg32(vm, a->vm); + + if (a->s) { + if (a->rz) { + gen_helper_vfp_tosizh(vm, vm, fpst); + } else { + gen_helper_vfp_tosih(vm, vm, fpst); + } + } else { + if (a->rz) { + gen_helper_vfp_touizh(vm, vm, fpst); + } else { + gen_helper_vfp_touih(vm, vm, fpst); + } + } + neon_store_reg32(vm, a->vd); + tcg_temp_free_i32(vm); + tcg_temp_free_ptr(fpst); + return true; +} + static bool trans_VCVT_sp_int(DisasContext *s, arg_VCVT_sp_int *a) { TCGv_i32 vm; -- 2.20.1 Currently the VFP_CONV_FIX macros take a single fsz argument for the size of the float type, which is used both to select the name of the functions to call (eg float32_is_any_nan()) and also for the type to use for the float inputs and outputs (eg float32). Separate these into fsz and ftype arguments, so that we can use them for fp16, which uses 'float16' in the function names but is still passing inputs and outputs in a 32-bit sized type. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-14-peter.maydell@linaro.org --- target/arm/vfp_helper.c | 46 ++++++++++++++++++++--------------------- 1 file changed, 23 insertions(+), 23 deletions(-) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ float32 VFP_HELPER(fcvts, d)(float64 x, CPUARMState *env) } /* VFP3 fixed point conversion. */ -#define VFP_CONV_FIX_FLOAT(name, p, fsz, isz, itype) \ -float##fsz HELPER(vfp_##name##to##p)(uint##isz##_t x, uint32_t shift, \ +#define VFP_CONV_FIX_FLOAT(name, p, fsz, ftype, isz, itype) \ +ftype HELPER(vfp_##name##to##p)(uint##isz##_t x, uint32_t shift, \ void *fpstp) \ { return itype##_to_##float##fsz##_scalbn(x, -shift, fpstp); } -#define VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, isz, itype, ROUND, suff) \ -uint##isz##_t HELPER(vfp_to##name##p##suff)(float##fsz x, uint32_t shift, \ +#define VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, ROUND, suff) \ +uint##isz##_t HELPER(vfp_to##name##p##suff)(ftype x, uint32_t shift, \ void *fpst) \ { \ if (unlikely(float##fsz##_is_any_nan(x))) { \ @@ -XXX,XX +XXX,XX @@ uint##isz##_t HELPER(vfp_to##name##p##suff)(float##fsz x, uint32_t shift, \ return float##fsz##_to_##itype##_scalbn(x, ROUND, shift, fpst); \ } -#define VFP_CONV_FIX(name, p, fsz, isz, itype) \ -VFP_CONV_FIX_FLOAT(name, p, fsz, isz, itype) \ -VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, isz, itype, \ +#define VFP_CONV_FIX(name, p, fsz, ftype, isz, itype) \ +VFP_CONV_FIX_FLOAT(name, p, fsz, ftype, isz, itype) \ +VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, \ float_round_to_zero, _round_to_zero) \ -VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, isz, itype, \ +VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, \ get_float_rounding_mode(fpst), ) -#define VFP_CONV_FIX_A64(name, p, fsz, isz, itype) \ -VFP_CONV_FIX_FLOAT(name, p, fsz, isz, itype) \ -VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, isz, itype, \ +#define VFP_CONV_FIX_A64(name, p, fsz, ftype, isz, itype) \ +VFP_CONV_FIX_FLOAT(name, p, fsz, ftype, isz, itype) \ +VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, ftype, isz, itype, \ get_float_rounding_mode(fpst), ) -VFP_CONV_FIX(sh, d, 64, 64, int16) -VFP_CONV_FIX(sl, d, 64, 64, int32) -VFP_CONV_FIX_A64(sq, d, 64, 64, int64) -VFP_CONV_FIX(uh, d, 64, 64, uint16) -VFP_CONV_FIX(ul, d, 64, 64, uint32) -VFP_CONV_FIX_A64(uq, d, 64, 64, uint64) -VFP_CONV_FIX(sh, s, 32, 32, int16) -VFP_CONV_FIX(sl, s, 32, 32, int32) -VFP_CONV_FIX_A64(sq, s, 32, 64, int64) -VFP_CONV_FIX(uh, s, 32, 32, uint16) -VFP_CONV_FIX(ul, s, 32, 32, uint32) -VFP_CONV_FIX_A64(uq, s, 32, 64, uint64) +VFP_CONV_FIX(sh, d, 64, float64, 64, int16) +VFP_CONV_FIX(sl, d, 64, float64, 64, int32) +VFP_CONV_FIX_A64(sq, d, 64, float64, 64, int64) +VFP_CONV_FIX(uh, d, 64, float64, 64, uint16) +VFP_CONV_FIX(ul, d, 64, float64, 64, uint32) +VFP_CONV_FIX_A64(uq, d, 64, float64, 64, uint64) +VFP_CONV_FIX(sh, s, 32, float32, 32, int16) +VFP_CONV_FIX(sl, s, 32, float32, 32, int32) +VFP_CONV_FIX_A64(sq, s, 32, float32, 64, int64) +VFP_CONV_FIX(uh, s, 32, float32, 32, uint16) +VFP_CONV_FIX(ul, s, 32, float32, 32, uint32) +VFP_CONV_FIX_A64(uq, s, 32, float32, 64, uint64) #undef VFP_CONV_FIX #undef VFP_CONV_FIX_FLOAT -- 2.20.1 Now the VFP_CONV_FIX macros can handle fp16's distinction between the width of the operation and the width of the type used to pass operands, use the macros rather than the open-coded functions. This creates an extra six helper functions, all of which we are going to need for the AArch32 VFP fp16 instructions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-15-peter.maydell@linaro.org --- target/arm/helper.h | 6 +++ target/arm/vfp_helper.c | 86 +++-------------------------------------- 2 files changed, 12 insertions(+), 80 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(vfp_tosizh, s32, f16, ptr) DEF_HELPER_2(vfp_tosizs, s32, f32, ptr) DEF_HELPER_2(vfp_tosizd, s32, f64, ptr) +DEF_HELPER_3(vfp_toshh_round_to_zero, i32, f16, i32, ptr) +DEF_HELPER_3(vfp_toslh_round_to_zero, i32, f16, i32, ptr) +DEF_HELPER_3(vfp_touhh_round_to_zero, i32, f16, i32, ptr) +DEF_HELPER_3(vfp_toulh_round_to_zero, i32, f16, i32, ptr) DEF_HELPER_3(vfp_toshs_round_to_zero, i32, f32, i32, ptr) DEF_HELPER_3(vfp_tosls_round_to_zero, i32, f32, i32, ptr) DEF_HELPER_3(vfp_touhs_round_to_zero, i32, f32, i32, ptr) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_sqtod, f64, i64, i32, ptr) DEF_HELPER_3(vfp_uhtod, f64, i64, i32, ptr) DEF_HELPER_3(vfp_ultod, f64, i64, i32, ptr) DEF_HELPER_3(vfp_uqtod, f64, i64, i32, ptr) +DEF_HELPER_3(vfp_shtoh, f16, i32, i32, ptr) +DEF_HELPER_3(vfp_uhtoh, f16, i32, i32, ptr) DEF_HELPER_3(vfp_sltoh, f16, i32, i32, ptr) DEF_HELPER_3(vfp_ultoh, f16, i32, i32, ptr) DEF_HELPER_3(vfp_sqtoh, f16, i64, i32, ptr) 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 @@ VFP_CONV_FIX_A64(sq, s, 32, float32, 64, int64) VFP_CONV_FIX(uh, s, 32, float32, 32, uint16) VFP_CONV_FIX(ul, s, 32, float32, 32, uint32) VFP_CONV_FIX_A64(uq, s, 32, float32, 64, uint64) +VFP_CONV_FIX(sh, h, 16, dh_ctype_f16, 32, int16) +VFP_CONV_FIX(sl, h, 16, dh_ctype_f16, 32, int32) +VFP_CONV_FIX_A64(sq, h, 16, dh_ctype_f16, 64, int64) +VFP_CONV_FIX(uh, h, 16, dh_ctype_f16, 32, uint16) +VFP_CONV_FIX(ul, h, 16, dh_ctype_f16, 32, uint32) +VFP_CONV_FIX_A64(uq, h, 16, dh_ctype_f16, 64, uint64) #undef VFP_CONV_FIX #undef VFP_CONV_FIX_FLOAT #undef VFP_CONV_FLOAT_FIX_ROUND #undef VFP_CONV_FIX_A64 -uint32_t HELPER(vfp_sltoh)(uint32_t x, uint32_t shift, void *fpst) -{ - return int32_to_float16_scalbn(x, -shift, fpst); -} - -uint32_t HELPER(vfp_ultoh)(uint32_t x, uint32_t shift, void *fpst) -{ - return uint32_to_float16_scalbn(x, -shift, fpst); -} - -uint32_t HELPER(vfp_sqtoh)(uint64_t x, uint32_t shift, void *fpst) -{ - return int64_to_float16_scalbn(x, -shift, fpst); -} - -uint32_t HELPER(vfp_uqtoh)(uint64_t x, uint32_t shift, void *fpst) -{ - return uint64_to_float16_scalbn(x, -shift, fpst); -} - -uint32_t HELPER(vfp_toshh)(uint32_t x, uint32_t shift, void *fpst) -{ - if (unlikely(float16_is_any_nan(x))) { - float_raise(float_flag_invalid, fpst); - return 0; - } - return float16_to_int16_scalbn(x, get_float_rounding_mode(fpst), - shift, fpst); -} - -uint32_t HELPER(vfp_touhh)(uint32_t x, uint32_t shift, void *fpst) -{ - if (unlikely(float16_is_any_nan(x))) { - float_raise(float_flag_invalid, fpst); - return 0; - } - return float16_to_uint16_scalbn(x, get_float_rounding_mode(fpst), - shift, fpst); -} - -uint32_t HELPER(vfp_toslh)(uint32_t x, uint32_t shift, void *fpst) -{ - if (unlikely(float16_is_any_nan(x))) { - float_raise(float_flag_invalid, fpst); - return 0; - } - return float16_to_int32_scalbn(x, get_float_rounding_mode(fpst), - shift, fpst); -} - -uint32_t HELPER(vfp_toulh)(uint32_t x, uint32_t shift, void *fpst) -{ - if (unlikely(float16_is_any_nan(x))) { - float_raise(float_flag_invalid, fpst); - return 0; - } - return float16_to_uint32_scalbn(x, get_float_rounding_mode(fpst), - shift, fpst); -} - -uint64_t HELPER(vfp_tosqh)(uint32_t x, uint32_t shift, void *fpst) -{ - if (unlikely(float16_is_any_nan(x))) { - float_raise(float_flag_invalid, fpst); - return 0; - } - return float16_to_int64_scalbn(x, get_float_rounding_mode(fpst), - shift, fpst); -} - -uint64_t HELPER(vfp_touqh)(uint32_t x, uint32_t shift, void *fpst) -{ - if (unlikely(float16_is_any_nan(x))) { - float_raise(float_flag_invalid, fpst); - return 0; - } - return float16_to_uint64_scalbn(x, get_float_rounding_mode(fpst), - shift, fpst); -} - /* Set the current fp rounding mode and return the old one. * The argument is a softfloat float_round_ value. */ -- 2.20.1 Implement the fp16 versions of the VFP VCVT instruction forms which convert between floating point and fixed-point. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-16-peter.maydell@linaro.org --- target/arm/vfp.decode | 2 ++ target/arm/translate-vfp.c.inc | 59 ++++++++++++++++++++++++++++++++++ 2 files changed, 61 insertions(+) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VJCVT ---- 1110 1.11 1001 .... 1011 11.0 .... @vfp_dm_sd # We assemble bits 18 (op), 16 (u) and 7 (sx) into a single opc field # for the convenience of the trans_VCVT_fix functions. %vcvt_fix_op 18:1 16:1 7:1 +VCVT_fix_hp ---- 1110 1.11 1.1. .... 1001 .1.0 .... \ + vd=%vd_sp imm=%vm_sp opc=%vcvt_fix_op VCVT_fix_sp ---- 1110 1.11 1.1. .... 1010 .1.0 .... \ vd=%vd_sp imm=%vm_sp opc=%vcvt_fix_op VCVT_fix_dp ---- 1110 1.11 1.1. .... 1011 .1.0 .... \ diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VJCVT(DisasContext *s, arg_VJCVT *a) return true; } +static bool trans_VCVT_fix_hp(DisasContext *s, arg_VCVT_fix_sp *a) +{ + TCGv_i32 vd, shift; + TCGv_ptr fpst; + int frac_bits; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + frac_bits = (a->opc & 1) ? (32 - a->imm) : (16 - a->imm); + + vd = tcg_temp_new_i32(); + neon_load_reg32(vd, a->vd); + + fpst = fpstatus_ptr(FPST_FPCR_F16); + shift = tcg_const_i32(frac_bits); + + /* Switch on op:U:sx bits */ + switch (a->opc) { + case 0: + gen_helper_vfp_shtoh(vd, vd, shift, fpst); + break; + case 1: + gen_helper_vfp_sltoh(vd, vd, shift, fpst); + break; + case 2: + gen_helper_vfp_uhtoh(vd, vd, shift, fpst); + break; + case 3: + gen_helper_vfp_ultoh(vd, vd, shift, fpst); + break; + case 4: + gen_helper_vfp_toshh_round_to_zero(vd, vd, shift, fpst); + break; + case 5: + gen_helper_vfp_toslh_round_to_zero(vd, vd, shift, fpst); + break; + case 6: + gen_helper_vfp_touhh_round_to_zero(vd, vd, shift, fpst); + break; + case 7: + gen_helper_vfp_toulh_round_to_zero(vd, vd, shift, fpst); + break; + default: + g_assert_not_reached(); + } + + neon_store_reg32(vd, a->vd); + tcg_temp_free_i32(vd); + tcg_temp_free_i32(shift); + tcg_temp_free_ptr(fpst); + return true; +} + static bool trans_VCVT_fix_sp(DisasContext *s, arg_VCVT_fix_sp *a) { TCGv_i32 vd, shift; -- 2.20.1 Implement the fp16 versions of the VFP VCVT instruction forms which convert between floating point and integer with a specified rounding mode. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-17-peter.maydell@linaro.org --- target/arm/vfp-uncond.decode | 6 ++++-- target/arm/translate-vfp.c.inc | 32 ++++++++++++++++++++++++-------- 2 files changed, 28 insertions(+), 10 deletions(-) diff --git a/target/arm/vfp-uncond.decode b/target/arm/vfp-uncond.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp-uncond.decode +++ b/target/arm/vfp-uncond.decode @@ -XXX,XX +XXX,XX @@ VRINT 1111 1110 1.11 10 rm:2 .... 1011 01.0 .... \ vm=%vm_dp vd=%vd_dp dp=1 # VCVT float to int with specified rounding mode; Vd is always single-precision +VCVT 1111 1110 1.11 11 rm:2 .... 1001 op:1 1.0 .... \ + vm=%vm_sp vd=%vd_sp sz=1 VCVT 1111 1110 1.11 11 rm:2 .... 1010 op:1 1.0 .... \ - vm=%vm_sp vd=%vd_sp dp=0 + vm=%vm_sp vd=%vd_sp sz=2 VCVT 1111 1110 1.11 11 rm:2 .... 1011 op:1 1.0 .... \ - vm=%vm_dp vd=%vd_sp dp=1 + vm=%vm_dp vd=%vd_sp sz=3 diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) static bool trans_VCVT(DisasContext *s, arg_VCVT *a) { uint32_t rd, rm; - bool dp = a->dp; + int sz = a->sz; TCGv_ptr fpst; TCGv_i32 tcg_rmode, tcg_shift; int rounding = fp_decode_rm[a->rm]; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) return false; } - if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { + if (sz == 3 && !dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + + if (sz == 1 && !dc_isar_feature(aa32_fp16_arith, s)) { return false; } /* UNDEF accesses to D16-D31 if they don't exist */ - if (dp && !dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { + if (sz == 3 && !dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) return true; } - fpst = fpstatus_ptr(FPST_FPCR); + if (sz == 1) { + fpst = fpstatus_ptr(FPST_FPCR_F16); + } else { + fpst = fpstatus_ptr(FPST_FPCR); + } tcg_shift = tcg_const_i32(0); tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rounding)); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); - if (dp) { + if (sz == 3) { TCGv_i64 tcg_double, tcg_res; TCGv_i32 tcg_tmp; tcg_double = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) tcg_single = tcg_temp_new_i32(); tcg_res = tcg_temp_new_i32(); neon_load_reg32(tcg_single, rm); - if (is_signed) { - gen_helper_vfp_tosls(tcg_res, tcg_single, tcg_shift, fpst); + if (sz == 1) { + if (is_signed) { + gen_helper_vfp_toslh(tcg_res, tcg_single, tcg_shift, fpst); + } else { + gen_helper_vfp_toulh(tcg_res, tcg_single, tcg_shift, fpst); + } } else { - gen_helper_vfp_touls(tcg_res, tcg_single, tcg_shift, fpst); + if (is_signed) { + gen_helper_vfp_tosls(tcg_res, tcg_single, tcg_shift, fpst); + } else { + gen_helper_vfp_touls(tcg_res, tcg_single, tcg_shift, fpst); + } } neon_store_reg32(tcg_res, rd); tcg_temp_free_i32(tcg_res); -- 2.20.1 Implement the fp16 versions of the VFP VSEL instruction. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-18-peter.maydell@linaro.org --- target/arm/vfp-uncond.decode | 6 ++++-- target/arm/translate-vfp.c.inc | 16 ++++++++++++---- 2 files changed, 16 insertions(+), 6 deletions(-) diff --git a/target/arm/vfp-uncond.decode b/target/arm/vfp-uncond.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp-uncond.decode +++ b/target/arm/vfp-uncond.decode @@ -XXX,XX +XXX,XX @@ @vfp_dnm_s ................................ vm=%vm_sp vn=%vn_sp vd=%vd_sp @vfp_dnm_d ................................ vm=%vm_dp vn=%vn_dp vd=%vd_dp +VSEL 1111 1110 0. cc:2 .... .... 1001 .0.0 .... \ + vm=%vm_sp vn=%vn_sp vd=%vd_sp sz=1 VSEL 1111 1110 0. cc:2 .... .... 1010 .0.0 .... \ - vm=%vm_sp vn=%vn_sp vd=%vd_sp dp=0 + vm=%vm_sp vn=%vn_sp vd=%vd_sp sz=2 VSEL 1111 1110 0. cc:2 .... .... 1011 .0.0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp dp=1 + vm=%vm_dp vn=%vn_dp vd=%vd_dp sz=3 VMAXNM_hp 1111 1110 1.00 .... .... 1001 .0.0 .... @vfp_dnm_s VMINNM_hp 1111 1110 1.00 .... .... 1001 .1.0 .... @vfp_dnm_s diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool vfp_access_check(DisasContext *s) static bool trans_VSEL(DisasContext *s, arg_VSEL *a) { uint32_t rd, rn, rm; - bool dp = a->dp; + int sz = a->sz; if (!dc_isar_feature(aa32_vsel, s)) { return false; } - if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { + if (sz == 3 && !dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + + if (sz == 1 && !dc_isar_feature(aa32_fp16_arith, s)) { return false; } /* UNDEF accesses to D16-D31 if they don't exist */ - if (dp && !dc_isar_feature(aa32_simd_r32, s) && + if (sz == 3 && !dc_isar_feature(aa32_simd_r32, s) && ((a->vm | a->vn | a->vd) & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) return true; } - if (dp) { + if (sz == 3) { TCGv_i64 frn, frm, dest; TCGv_i64 tmp, zero, zf, nf, vf; @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) tcg_temp_free_i32(tmp); break; } + /* For fp16 the top half is always zeroes */ + if (sz == 1) { + tcg_gen_andi_i32(dest, dest, 0xffff); + } neon_store_reg32(dest, rd); tcg_temp_free_i32(frn); tcg_temp_free_i32(frm); -- 2.20.1 Implement the fp16 version of the VFP VRINT* insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-19-peter.maydell@linaro.org --- target/arm/helper.h | 2 + target/arm/vfp-uncond.decode | 6 ++- target/arm/vfp.decode | 3 ++ target/arm/vfp_helper.c | 21 ++++++++ target/arm/translate-vfp.c.inc | 98 +++++++++++++++++++++++++++++++--- 5 files changed, 122 insertions(+), 8 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(shr_cc, i32, env, i32, i32) DEF_HELPER_3(sar_cc, i32, env, i32, i32) DEF_HELPER_3(ror_cc, i32, env, i32, i32) +DEF_HELPER_FLAGS_2(rinth_exact, TCG_CALL_NO_RWG, f16, f16, ptr) DEF_HELPER_FLAGS_2(rints_exact, TCG_CALL_NO_RWG, f32, f32, ptr) DEF_HELPER_FLAGS_2(rintd_exact, TCG_CALL_NO_RWG, f64, f64, ptr) +DEF_HELPER_FLAGS_2(rinth, TCG_CALL_NO_RWG, f16, f16, ptr) DEF_HELPER_FLAGS_2(rints, TCG_CALL_NO_RWG, f32, f32, ptr) DEF_HELPER_FLAGS_2(rintd, TCG_CALL_NO_RWG, f64, f64, ptr) diff --git a/target/arm/vfp-uncond.decode b/target/arm/vfp-uncond.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp-uncond.decode +++ b/target/arm/vfp-uncond.decode @@ -XXX,XX +XXX,XX @@ VMINNM_sp 1111 1110 1.00 .... .... 1010 .1.0 .... @vfp_dnm_s VMAXNM_dp 1111 1110 1.00 .... .... 1011 .0.0 .... @vfp_dnm_d VMINNM_dp 1111 1110 1.00 .... .... 1011 .1.0 .... @vfp_dnm_d +VRINT 1111 1110 1.11 10 rm:2 .... 1001 01.0 .... \ + vm=%vm_sp vd=%vd_sp sz=1 VRINT 1111 1110 1.11 10 rm:2 .... 1010 01.0 .... \ - vm=%vm_sp vd=%vd_sp dp=0 + vm=%vm_sp vd=%vd_sp sz=2 VRINT 1111 1110 1.11 10 rm:2 .... 1011 01.0 .... \ - vm=%vm_dp vd=%vd_dp dp=1 + vm=%vm_dp vd=%vd_dp sz=3 # VCVT float to int with specified rounding mode; Vd is always single-precision VCVT 1111 1110 1.11 11 rm:2 .... 1001 op:1 1.0 .... \ diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VCVT_f16_f32 ---- 1110 1.11 0011 .... 1010 t:1 1.0 .... \ VCVT_f16_f64 ---- 1110 1.11 0011 .... 1011 t:1 1.0 .... \ vd=%vd_sp vm=%vm_dp +VRINTR_hp ---- 1110 1.11 0110 .... 1001 01.0 .... @vfp_dm_ss VRINTR_sp ---- 1110 1.11 0110 .... 1010 01.0 .... @vfp_dm_ss VRINTR_dp ---- 1110 1.11 0110 .... 1011 01.0 .... @vfp_dm_dd +VRINTZ_hp ---- 1110 1.11 0110 .... 1001 11.0 .... @vfp_dm_ss VRINTZ_sp ---- 1110 1.11 0110 .... 1010 11.0 .... @vfp_dm_ss VRINTZ_dp ---- 1110 1.11 0110 .... 1011 11.0 .... @vfp_dm_dd +VRINTX_hp ---- 1110 1.11 0111 .... 1001 01.0 .... @vfp_dm_ss VRINTX_sp ---- 1110 1.11 0111 .... 1010 01.0 .... @vfp_dm_ss VRINTX_dp ---- 1110 1.11 0111 .... 1011 01.0 .... @vfp_dm_dd 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 VFP_HELPER(muladd, d)(float64 a, float64 b, float64 c, void *fpstp) } /* ARMv8 round to integral */ +dh_ctype_f16 HELPER(rinth_exact)(dh_ctype_f16 x, void *fp_status) +{ + return float16_round_to_int(x, fp_status); +} + float32 HELPER(rints_exact)(float32 x, void *fp_status) { return float32_round_to_int(x, fp_status); @@ -XXX,XX +XXX,XX @@ float64 HELPER(rintd_exact)(float64 x, void *fp_status) return float64_round_to_int(x, fp_status); } +dh_ctype_f16 HELPER(rinth)(dh_ctype_f16 x, void *fp_status) +{ + int old_flags = get_float_exception_flags(fp_status), new_flags; + float16 ret; + + ret = float16_round_to_int(x, fp_status); + + /* Suppress any inexact exceptions the conversion produced */ + if (!(old_flags & float_flag_inexact)) { + new_flags = get_float_exception_flags(fp_status); + set_float_exception_flags(new_flags & ~float_flag_inexact, fp_status); + } + + return ret; +} + float32 HELPER(rints)(float32 x, void *fp_status) { int old_flags = get_float_exception_flags(fp_status), new_flags; diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static const uint8_t fp_decode_rm[] = { static bool trans_VRINT(DisasContext *s, arg_VRINT *a) { uint32_t rd, rm; - bool dp = a->dp; + int sz = a->sz; TCGv_ptr fpst; TCGv_i32 tcg_rmode; int rounding = fp_decode_rm[a->rm]; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) return false; } - if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { + if (sz == 3 && !dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + + if (sz == 1 && !dc_isar_feature(aa32_fp16_arith, s)) { return false; } /* UNDEF accesses to D16-D31 if they don't exist */ - if (dp && !dc_isar_feature(aa32_simd_r32, s) && + if (sz == 3 && !dc_isar_feature(aa32_simd_r32, s) && ((a->vm | a->vd) & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) return true; } - fpst = fpstatus_ptr(FPST_FPCR); + if (sz == 1) { + fpst = fpstatus_ptr(FPST_FPCR_F16); + } else { + fpst = fpstatus_ptr(FPST_FPCR); + } tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rounding)); gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); - if (dp) { + if (sz == 3) { TCGv_i64 tcg_op; TCGv_i64 tcg_res; tcg_op = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) tcg_op = tcg_temp_new_i32(); tcg_res = tcg_temp_new_i32(); neon_load_reg32(tcg_op, rm); - gen_helper_rints(tcg_res, tcg_op, fpst); + if (sz == 1) { + gen_helper_rinth(tcg_res, tcg_op, fpst); + } else { + gen_helper_rints(tcg_res, tcg_op, fpst); + } neon_store_reg32(tcg_res, rd); tcg_temp_free_i32(tcg_op); tcg_temp_free_i32(tcg_res); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f16_f64(DisasContext *s, arg_VCVT_f16_f64 *a) return true; } +static bool trans_VRINTR_hp(DisasContext *s, arg_VRINTR_sp *a) +{ + TCGv_ptr fpst; + TCGv_i32 tmp; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + tmp = tcg_temp_new_i32(); + neon_load_reg32(tmp, a->vm); + fpst = fpstatus_ptr(FPST_FPCR_F16); + gen_helper_rinth(tmp, tmp, fpst); + neon_store_reg32(tmp, a->vd); + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(tmp); + return true; +} + static bool trans_VRINTR_sp(DisasContext *s, arg_VRINTR_sp *a) { TCGv_ptr fpst; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_dp(DisasContext *s, arg_VRINTR_dp *a) return true; } +static bool trans_VRINTZ_hp(DisasContext *s, arg_VRINTZ_sp *a) +{ + TCGv_ptr fpst; + TCGv_i32 tmp; + TCGv_i32 tcg_rmode; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + tmp = tcg_temp_new_i32(); + neon_load_reg32(tmp, a->vm); + fpst = fpstatus_ptr(FPST_FPCR_F16); + tcg_rmode = tcg_const_i32(float_round_to_zero); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); + gen_helper_rinth(tmp, tmp, fpst); + gen_helper_set_rmode(tcg_rmode, tcg_rmode, fpst); + neon_store_reg32(tmp, a->vd); + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(tcg_rmode); + tcg_temp_free_i32(tmp); + return true; +} + static bool trans_VRINTZ_sp(DisasContext *s, arg_VRINTZ_sp *a) { TCGv_ptr fpst; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_dp(DisasContext *s, arg_VRINTZ_dp *a) return true; } +static bool trans_VRINTX_hp(DisasContext *s, arg_VRINTX_sp *a) +{ + TCGv_ptr fpst; + TCGv_i32 tmp; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + tmp = tcg_temp_new_i32(); + neon_load_reg32(tmp, a->vm); + fpst = fpstatus_ptr(FPST_FPCR_F16); + gen_helper_rinth_exact(tmp, tmp, fpst); + neon_store_reg32(tmp, a->vd); + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(tmp); + return true; +} + static bool trans_VRINTX_sp(DisasContext *s, arg_VRINTX_sp *a) { TCGv_ptr fpst; -- 2.20.1 The fp16 extension includes a new instruction VINS, which copies the lower 16 bits of a 32-bit source VFP register into the upper 16 bits of the destination. Implement it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-20-peter.maydell@linaro.org --- target/arm/vfp-uncond.decode | 3 +++ target/arm/translate-vfp.c.inc | 28 ++++++++++++++++++++++++++++ 2 files changed, 31 insertions(+) diff --git a/target/arm/vfp-uncond.decode b/target/arm/vfp-uncond.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp-uncond.decode +++ b/target/arm/vfp-uncond.decode @@ -XXX,XX +XXX,XX @@ VCVT 1111 1110 1.11 11 rm:2 .... 1010 op:1 1.0 .... \ vm=%vm_sp vd=%vd_sp sz=2 VCVT 1111 1110 1.11 11 rm:2 .... 1011 op:1 1.0 .... \ vm=%vm_dp vd=%vd_sp sz=3 + +VINS 1111 1110 1.11 0000 .... 1010 11 . 0 .... \ + vd=%vd_sp vm=%vm_sp diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_NOCP(DisasContext *s, arg_NOCP *a) return false; } + +static bool trans_VINS(DisasContext *s, arg_VINS *a) +{ + TCGv_i32 rd, rm; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (s->vec_len != 0 || s->vec_stride != 0) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* Insert low half of Vm into high half of Vd */ + rm = tcg_temp_new_i32(); + rd = tcg_temp_new_i32(); + neon_load_reg32(rm, a->vm); + neon_load_reg32(rd, a->vd); + tcg_gen_deposit_i32(rd, rd, rm, 16, 16); + neon_store_reg32(rd, a->vd); + tcg_temp_free_i32(rm); + tcg_temp_free_i32(rd); + return true; +} -- 2.20.1 The fp16 extension includes a new instruction VMOVX, which copies the upper 16 bits of a 32-bit source VFP register into the lower 16 bits of the destination and zeroes the high half of the destination. Implement it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-21-peter.maydell@linaro.org --- target/arm/vfp-uncond.decode | 3 +++ target/arm/translate-vfp.c.inc | 25 +++++++++++++++++++++++++ 2 files changed, 28 insertions(+) diff --git a/target/arm/vfp-uncond.decode b/target/arm/vfp-uncond.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp-uncond.decode +++ b/target/arm/vfp-uncond.decode @@ -XXX,XX +XXX,XX @@ VCVT 1111 1110 1.11 11 rm:2 .... 1010 op:1 1.0 .... \ VCVT 1111 1110 1.11 11 rm:2 .... 1011 op:1 1.0 .... \ vm=%vm_dp vd=%vd_sp sz=3 +VMOVX 1111 1110 1.11 0000 .... 1010 01 . 0 .... \ + vd=%vd_sp vm=%vm_sp + VINS 1111 1110 1.11 0000 .... 1010 11 . 0 .... \ vd=%vd_sp vm=%vm_sp diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VINS(DisasContext *s, arg_VINS *a) tcg_temp_free_i32(rd); return true; } + +static bool trans_VMOVX(DisasContext *s, arg_VINS *a) +{ + TCGv_i32 rm; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (s->vec_len != 0 || s->vec_stride != 0) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* Set Vd to high half of Vm */ + rm = tcg_temp_new_i32(); + neon_load_reg32(rm, a->vm); + tcg_gen_shri_i32(rm, rm, 16); + neon_store_reg32(rm, a->vd); + tcg_temp_free_i32(rm); + return true; +} -- 2.20.1 Implement the VFP fp16 variant of VMOV that transfers a 16-bit value between a general purpose register and a VFP register. Note that Rt == 15 is UNPREDICTABLE; since this insn is v8 and later only we have no need to replicate the old "updates CPSR.NZCV" behaviour that the singleprec version of this insn does. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-22-peter.maydell@linaro.org --- target/arm/vfp.decode | 1 + target/arm/translate-vfp.c.inc | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 35 insertions(+) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VDUP ---- 1110 1 b:1 q:1 0 .... rt:4 1011 . 0 e:1 1 0000 \ vn=%vn_dp VMSR_VMRS ---- 1110 111 l:1 reg:4 rt:4 1010 0001 0000 +VMOV_half ---- 1110 000 l:1 .... rt:4 1001 . 001 0000 vn=%vn_sp VMOV_single ---- 1110 000 l:1 .... rt:4 1010 . 001 0000 vn=%vn_sp VMOV_64_sp ---- 1100 010 op:1 rt2:4 rt:4 1010 00.1 .... vm=%vm_sp diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) return true; } +static bool trans_VMOV_half(DisasContext *s, arg_VMOV_single *a) +{ + TCGv_i32 tmp; + + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + + if (a->rt == 15) { + /* UNPREDICTABLE; we choose to UNDEF */ + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + if (a->l) { + /* VFP to general purpose register */ + tmp = tcg_temp_new_i32(); + neon_load_reg32(tmp, a->vn); + tcg_gen_andi_i32(tmp, tmp, 0xffff); + store_reg(s, a->rt, tmp); + } else { + /* general purpose register to VFP */ + tmp = load_reg(s, a->rt); + tcg_gen_andi_i32(tmp, tmp, 0xffff); + neon_store_reg32(tmp, a->vn); + tcg_temp_free_i32(tmp); + } + + return true; +} + static bool trans_VMOV_single(DisasContext *s, arg_VMOV_single *a) { TCGv_i32 tmp; -- 2.20.1 Implement FP16 support for the Neon insns which use the DO_3S_FP_GVEC macro: VADD, VSUB, VABD, VMUL. For VABD this requires us to implement a new gvec_fabd_h helper using the machinery we have already for the other helpers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-24-peter.maydell@linaro.org --- target/arm/helper.h | 1 + target/arm/vec_helper.c | 6 ++++++ target/arm/translate-neon.c.inc | 36 +++++++++++++++++---------------- 3 files changed, 26 insertions(+), 17 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_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_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_ftsmul_h, TCG_CALL_NO_RWG, 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 float16 float16_abd(float16 op1, float16 op2, float_status *stat) +{ + return float16_abs(float16_sub(op1, op2, stat)); +} + static float32 float32_abd(float32 op1, float32 op2, float_status *stat) { return float32_abs(float32_sub(op1, op2, stat)); @@ -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_h, float16_abd, float16) DO_3OP(gvec_fabd_s, float32_abd, float32) #ifdef TARGET_AARCH64 diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_3same_fp(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn, 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_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) \ +#define WRAP_FP_GVEC(WRAPNAME, FPST, FUNC) \ + static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \ + uint32_t rn_ofs, uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ { \ - TCGv_ptr fpst = fpstatus_ptr(FPST_STD); \ + TCGv_ptr fpst = fpstatus_ptr(FPST); \ tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpst, \ oprsz, maxsz, 0, FUNC); \ tcg_temp_free_ptr(fpst); \ - } \ + } + +#define DO_3S_FP_GVEC(INSN,SFUNC,HFUNC) \ + WRAP_FP_GVEC(gen_##INSN##_fp32_3s, FPST_STD, SFUNC) \ + WRAP_FP_GVEC(gen_##INSN##_fp16_3s, FPST_STD_F16, HFUNC) \ static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \ { \ if (a->size != 0) { \ - /* TODO fp16 support */ \ - return false; \ + if (!dc_isar_feature(aa32_fp16_arith, s)) { \ + return false; \ + } \ + return do_3same(s, a, gen_##INSN##_fp16_3s); \ } \ - return do_3same(s, a, gen_##INSN##_3s); \ + return do_3same(s, a, gen_##INSN##_fp32_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) -DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s) +DO_3S_FP_GVEC(VADD, gen_helper_gvec_fadd_s, gen_helper_gvec_fadd_h) +DO_3S_FP_GVEC(VSUB, gen_helper_gvec_fsub_s, gen_helper_gvec_fsub_h) +DO_3S_FP_GVEC(VABD, gen_helper_gvec_fabd_s, gen_helper_gvec_fabd_h) +DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s, gen_helper_gvec_fmul_h) /* * For all the functions using this macro, size == 1 means fp16, -- 2.20.1 We already have gvec helpers for floating point VRECPE and VRQSRTE, so convert the Neon decoder to use them and add the fp16 support. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-25-peter.maydell@linaro.org --- target/arm/translate-neon.c.inc | 31 +++++++++++++++++++++++++++++-- 1 file changed, 29 insertions(+), 2 deletions(-) diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_2misc_fp(DisasContext *s, arg_2misc *a, return do_2misc_fp(s, a, FUNC); \ } -DO_2MISC_FP(VRECPE_F, gen_helper_recpe_f32) -DO_2MISC_FP(VRSQRTE_F, gen_helper_rsqrte_f32) DO_2MISC_FP(VCVT_FS, gen_helper_vfp_sitos) DO_2MISC_FP(VCVT_FU, gen_helper_vfp_uitos) DO_2MISC_FP(VCVT_SF, gen_helper_vfp_tosizs) DO_2MISC_FP(VCVT_UF, gen_helper_vfp_touizs) +#define DO_2MISC_FP_VEC(INSN, HFUNC, SFUNC) \ + static void gen_##INSN(unsigned vece, uint32_t rd_ofs, \ + uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ + { \ + static gen_helper_gvec_2_ptr * const fns[4] = { \ + NULL, HFUNC, SFUNC, NULL, \ + }; \ + TCGv_ptr fpst; \ + fpst = fpstatus_ptr(vece == MO_16 ? FPST_STD_F16 : FPST_STD); \ + tcg_gen_gvec_2_ptr(rd_ofs, rm_ofs, fpst, oprsz, maxsz, 0, \ + fns[vece]); \ + tcg_temp_free_ptr(fpst); \ + } \ + static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ + { \ + if (a->size == MO_16) { \ + if (!dc_isar_feature(aa32_fp16_arith, s)) { \ + return false; \ + } \ + } else if (a->size != MO_32) { \ + return false; \ + } \ + return do_2misc_vec(s, a, gen_##INSN); \ + } + +DO_2MISC_FP_VEC(VRECPE_F, gen_helper_gvec_frecpe_h, gen_helper_gvec_frecpe_s) +DO_2MISC_FP_VEC(VRSQRTE_F, gen_helper_gvec_frsqrte_h, gen_helper_gvec_frsqrte_s) + static bool trans_VRINTX(DisasContext *s, arg_2misc *a) { if (!arm_dc_feature(s, ARM_FEATURE_V8)) { -- 2.20.1 Rewrite Neon VABS/VNEG of floats to use gvec logical AND and XOR, so that we can implement the fp16 version of the insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-26-peter.maydell@linaro.org --- target/arm/translate-neon.c.inc | 34 +++++++++++++++++++++++++++------ 1 file changed, 28 insertions(+), 6 deletions(-) diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VCNT(DisasContext *s, arg_2misc *a) return do_2misc(s, a, gen_helper_neon_cnt_u8); } +static void gen_VABS_F(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + uint32_t oprsz, uint32_t maxsz) +{ + tcg_gen_gvec_andi(vece, rd_ofs, rm_ofs, + vece == MO_16 ? 0x7fff : 0x7fffffff, + oprsz, maxsz); +} + static bool trans_VABS_F(DisasContext *s, arg_2misc *a) { - if (a->size != 2) { + if (a->size == MO_16) { + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + } else if (a->size != MO_32) { return false; } - /* TODO: FP16 : size == 1 */ - return do_2misc(s, a, gen_helper_vfp_abss); + return do_2misc_vec(s, a, gen_VABS_F); +} + +static void gen_VNEG_F(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, + uint32_t oprsz, uint32_t maxsz) +{ + tcg_gen_gvec_xori(vece, rd_ofs, rm_ofs, + vece == MO_16 ? 0x8000 : 0x80000000, + oprsz, maxsz); } static bool trans_VNEG_F(DisasContext *s, arg_2misc *a) { - if (a->size != 2) { + if (a->size == MO_16) { + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + } else if (a->size != MO_32) { return false; } - /* TODO: FP16 : size == 1 */ - return do_2misc(s, a, gen_helper_vfp_negs); + return do_2misc_vec(s, a, gen_VNEG_F); } static bool trans_VRECPE(DisasContext *s, arg_2misc *a) -- 2.20.1 Convert the Neon floating-point vector comparison ops VCEQ, VCGE and VCGT over to using a gvec helper and use this to implement the fp16 case. (We put the float16_ceq() etc functions above the DO_2OP() macro definition because later when we convert the compare-against-zero instructions we'll want their definitions to be visible at that point in the source file.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-27-peter.maydell@linaro.org --- target/arm/helper.h | 9 +++++++ target/arm/vec_helper.c | 44 +++++++++++++++++++++++++++++++++ target/arm/translate-neon.c.inc | 6 ++--- 3 files changed, 56 insertions(+), 3 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fmul_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fabd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fabd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fceq_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fceq_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fcge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fcge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fcgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fcgt_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/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_fcmlad)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } +/* + * Floating point comparisons producing an integer result (all 1s or all 0s). + * Note that EQ doesn't signal InvalidOp for QNaNs but GE and GT do. + * Softfloat routines return 0/1, which we convert to the 0/-1 Neon requires. + */ +static uint16_t float16_ceq(float16 op1, float16 op2, float_status *stat) +{ + return -float16_eq_quiet(op1, op2, stat); +} + +static uint32_t float32_ceq(float32 op1, float32 op2, float_status *stat) +{ + return -float32_eq_quiet(op1, op2, stat); +} + +static uint16_t float16_cge(float16 op1, float16 op2, float_status *stat) +{ + return -float16_le(op2, op1, stat); +} + +static uint32_t float32_cge(float32 op1, float32 op2, float_status *stat) +{ + return -float32_le(op2, op1, stat); +} + +static uint16_t float16_cgt(float16 op1, float16 op2, float_status *stat) +{ + return -float16_lt(op2, op1, stat); +} + +static uint32_t float32_cgt(float32 op1, float32 op2, float_status *stat) +{ + return -float32_lt(op2, op1, stat); +} + #define DO_2OP(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ { \ @@ -XXX,XX +XXX,XX @@ DO_3OP(gvec_ftsmul_d, float64_ftsmul, float64) DO_3OP(gvec_fabd_h, float16_abd, float16) DO_3OP(gvec_fabd_s, float32_abd, float32) +DO_3OP(gvec_fceq_h, float16_ceq, float16) +DO_3OP(gvec_fceq_s, float32_ceq, float32) + +DO_3OP(gvec_fcge_h, float16_cge, float16) +DO_3OP(gvec_fcge_s, float32_cge, float32) + +DO_3OP(gvec_fcgt_h, float16_cgt, float16) +DO_3OP(gvec_fcgt_s, float32_cgt, float32) + #ifdef TARGET_AARCH64 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VADD, gen_helper_gvec_fadd_s, gen_helper_gvec_fadd_h) DO_3S_FP_GVEC(VSUB, gen_helper_gvec_fsub_s, gen_helper_gvec_fsub_h) DO_3S_FP_GVEC(VABD, gen_helper_gvec_fabd_s, gen_helper_gvec_fabd_h) DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s, gen_helper_gvec_fmul_h) +DO_3S_FP_GVEC(VCEQ, gen_helper_gvec_fceq_s, gen_helper_gvec_fceq_h) +DO_3S_FP_GVEC(VCGE, gen_helper_gvec_fcge_s, gen_helper_gvec_fcge_h) +DO_3S_FP_GVEC(VCGT, gen_helper_gvec_fcgt_s, gen_helper_gvec_fcgt_h) /* * For all the functions using this macro, size == 1 means fp16, @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s, gen_helper_gvec_fmul_h) 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) DO_3S_FP(VMAX, gen_helper_vfp_maxs, false) -- 2.20.1 Convert the neon floating-point vector absolute comparison ops VACGE and VACGT over to using a gvec hepler and use this to implement the fp16 case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-28-peter.maydell@linaro.org --- target/arm/helper.h | 6 ++++++ target/arm/vec_helper.c | 26 ++++++++++++++++++++++++++ target/arm/translate-neon.c.inc | 4 ++-- 3 files changed, 34 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fcge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fcgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_facge_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_facge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_facgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_facgt_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/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 uint32_t float32_cgt(float32 op1, float32 op2, float_status *stat) return -float32_lt(op2, op1, stat); } +static uint16_t float16_acge(float16 op1, float16 op2, float_status *stat) +{ + return -float16_le(float16_abs(op2), float16_abs(op1), stat); +} + +static uint32_t float32_acge(float32 op1, float32 op2, float_status *stat) +{ + return -float32_le(float32_abs(op2), float32_abs(op1), stat); +} + +static uint16_t float16_acgt(float16 op1, float16 op2, float_status *stat) +{ + return -float16_lt(float16_abs(op2), float16_abs(op1), stat); +} + +static uint32_t float32_acgt(float32 op1, float32 op2, float_status *stat) +{ + return -float32_lt(float32_abs(op2), float32_abs(op1), stat); +} + #define DO_2OP(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ { \ @@ -XXX,XX +XXX,XX @@ DO_3OP(gvec_fcge_s, float32_cge, float32) DO_3OP(gvec_fcgt_h, float16_cgt, float16) DO_3OP(gvec_fcgt_s, float32_cgt, float32) +DO_3OP(gvec_facge_h, float16_acge, float16) +DO_3OP(gvec_facge_s, float32_acge, float32) + +DO_3OP(gvec_facgt_h, float16_acgt, float16) +DO_3OP(gvec_facgt_s, float32_acgt, float32) + #ifdef TARGET_AARCH64 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VMUL, gen_helper_gvec_fmul_s, gen_helper_gvec_fmul_h) DO_3S_FP_GVEC(VCEQ, gen_helper_gvec_fceq_s, gen_helper_gvec_fceq_h) DO_3S_FP_GVEC(VCGE, gen_helper_gvec_fcge_s, gen_helper_gvec_fcge_h) DO_3S_FP_GVEC(VCGT, gen_helper_gvec_fcgt_s, gen_helper_gvec_fcgt_h) +DO_3S_FP_GVEC(VACGE, gen_helper_gvec_facge_s, gen_helper_gvec_facge_h) +DO_3S_FP_GVEC(VACGT, gen_helper_gvec_facgt_s, gen_helper_gvec_facgt_h) /* * For all the functions using this macro, size == 1 means fp16, @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VCGT, gen_helper_gvec_fcgt_s, gen_helper_gvec_fcgt_h) return do_3same_fp(s, a, FUNC, READS_VD); \ } -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) -- 2.20.1 Convert the Neon float-point VMAX and VMIN insns over to using a gvec helper, and use this to implement the fp16 case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-29-peter.maydell@linaro.org --- target/arm/helper.h | 6 ++++++ target/arm/vec_helper.c | 6 ++++++ target/arm/translate-neon.c.inc | 5 ++--- 3 files changed, 14 insertions(+), 3 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_facge_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_facgt_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_facgt_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmax_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmax_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fmin_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmin_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/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_3OP(gvec_facge_s, float32_acge, float32) DO_3OP(gvec_facgt_h, float16_acgt, float16) DO_3OP(gvec_facgt_s, float32_acgt, float32) +DO_3OP(gvec_fmax_h, float16_max, float16) +DO_3OP(gvec_fmax_s, float32_max, float32) + +DO_3OP(gvec_fmin_h, float16_min, float16) +DO_3OP(gvec_fmin_s, float32_min, float32) + #ifdef TARGET_AARCH64 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VCGE, gen_helper_gvec_fcge_s, gen_helper_gvec_fcge_h) DO_3S_FP_GVEC(VCGT, gen_helper_gvec_fcgt_s, gen_helper_gvec_fcgt_h) DO_3S_FP_GVEC(VACGE, gen_helper_gvec_facge_s, gen_helper_gvec_facge_h) DO_3S_FP_GVEC(VACGT, gen_helper_gvec_facgt_s, gen_helper_gvec_facgt_h) +DO_3S_FP_GVEC(VMAX, gen_helper_gvec_fmax_s, gen_helper_gvec_fmax_h) +DO_3S_FP_GVEC(VMIN, gen_helper_gvec_fmin_s, gen_helper_gvec_fmin_h) /* * For all the functions using this macro, size == 1 means fp16, @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VACGT, gen_helper_gvec_facgt_s, gen_helper_gvec_facgt_h) return do_3same_fp(s, a, FUNC, READS_VD); \ } -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) { -- 2.20.1 Convert the Neon floating point VMAXNM and VMINNM insns to using a gvec helper and use this to implement the fp16 case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-30-peter.maydell@linaro.org --- target/arm/helper.h | 6 ++++++ target/arm/vec_helper.c | 6 ++++++ target/arm/translate-neon.c.inc | 23 +++++++++++++++-------- 3 files changed, 27 insertions(+), 8 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fmax_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmin_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmin_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmaxnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fminnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fminnum_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/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_3OP(gvec_fmax_s, float32_max, float32) DO_3OP(gvec_fmin_h, float16_min, float16) DO_3OP(gvec_fmin_s, float32_min, float32) +DO_3OP(gvec_fmaxnum_h, float16_maxnum, float16) +DO_3OP(gvec_fmaxnum_s, float32_maxnum, float32) + +DO_3OP(gvec_fminnum_h, float16_minnum, float16) +DO_3OP(gvec_fminnum_s, float32_minnum, float32) + #ifdef TARGET_AARCH64 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -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) +WRAP_FP_GVEC(gen_VMAXNM_fp32_3s, FPST_STD, gen_helper_gvec_fmaxnum_s) +WRAP_FP_GVEC(gen_VMAXNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fmaxnum_h) +WRAP_FP_GVEC(gen_VMINNM_fp32_3s, FPST_STD, gen_helper_gvec_fminnum_s) +WRAP_FP_GVEC(gen_VMINNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fminnum_h) + static bool trans_VMAXNM_fp_3s(DisasContext *s, arg_3same *a) { if (!arm_dc_feature(s, ARM_FEATURE_V8)) { @@ -XXX,XX +XXX,XX @@ static bool trans_VMAXNM_fp_3s(DisasContext *s, arg_3same *a) } if (a->size != 0) { - /* TODO fp16 support */ - return false; + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + return do_3same(s, a, gen_VMAXNM_fp16_3s); } - - return do_3same_fp(s, a, gen_helper_vfp_maxnums, false); + return do_3same(s, a, gen_VMAXNM_fp32_3s); } static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) @@ -XXX,XX +XXX,XX @@ static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) } if (a->size != 0) { - /* TODO fp16 support */ - return false; + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + return do_3same(s, a, gen_VMINNM_fp16_3s); } - - return do_3same_fp(s, a, gen_helper_vfp_minnums, false); + return do_3same(s, a, gen_VMINNM_fp32_3s); } WRAP_ENV_FN(gen_VRECPS_tramp, gen_helper_recps_f32) -- 2.20.1 Convert the Neon floating-point VMLA and VMLS insns over to using a gvec helper, and use this to implement the fp16 case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-31-peter.maydell@linaro.org --- target/arm/helper.h | 6 +++++ target/arm/vec_helper.c | 42 +++++++++++++++++++++++++++++++++ target/arm/translate-neon.c.inc | 33 ++------------------------ 3 files changed, 50 insertions(+), 31 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fmaxnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i3 DEF_HELPER_FLAGS_5(gvec_fminnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fminnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fmls_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmls_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_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/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_3OP(gvec_rsqrts_d, helper_rsqrtsf_f64, float64) #endif #undef DO_3OP +/* Non-fused multiply-add (unlike float16_muladd etc, which are fused) */ +static float16 float16_muladd_nf(float16 dest, float16 op1, float16 op2, + float_status *stat) +{ + return float16_add(dest, float16_mul(op1, op2, stat), stat); +} + +static float32 float32_muladd_nf(float32 dest, float32 op1, float32 op2, + float_status *stat) +{ + return float32_add(dest, float32_mul(op1, op2, stat), stat); +} + +static float16 float16_mulsub_nf(float16 dest, float16 op1, float16 op2, + float_status *stat) +{ + return float16_sub(dest, float16_mul(op1, op2, stat), stat); +} + +static float32 float32_mulsub_nf(float32 dest, float32 op1, float32 op2, + float_status *stat) +{ + return float32_sub(dest, float32_mul(op1, op2, stat), stat); +} + +#define DO_MULADD(NAME, FUNC, TYPE) \ +void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ +{ \ + intptr_t i, oprsz = simd_oprsz(desc); \ + TYPE *d = vd, *n = vn, *m = vm; \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + d[i] = FUNC(d[i], n[i], m[i], stat); \ + } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ +} + +DO_MULADD(gvec_fmla_h, float16_muladd_nf, float16) +DO_MULADD(gvec_fmla_s, float32_muladd_nf, float32) + +DO_MULADD(gvec_fmls_h, float16_mulsub_nf, float16) +DO_MULADD(gvec_fmls_s, float32_mulsub_nf, float32) + /* For the indexed ops, SVE applies the index per 128-bit vector segment. * For AdvSIMD, there is of course only one such vector segment. */ diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VACGE, gen_helper_gvec_facge_s, gen_helper_gvec_facge_h) DO_3S_FP_GVEC(VACGT, gen_helper_gvec_facgt_s, gen_helper_gvec_facgt_h) DO_3S_FP_GVEC(VMAX, gen_helper_gvec_fmax_s, gen_helper_gvec_fmax_h) DO_3S_FP_GVEC(VMIN, gen_helper_gvec_fmin_s, gen_helper_gvec_fmin_h) - -/* - * 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) +DO_3S_FP_GVEC(VMLA, gen_helper_gvec_fmla_s, gen_helper_gvec_fmla_h) +DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_s, gen_helper_gvec_fmls_h) WRAP_FP_GVEC(gen_VMAXNM_fp32_3s, FPST_STD, gen_helper_gvec_fmaxnum_s) WRAP_FP_GVEC(gen_VMAXNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fmaxnum_h) -- 2.20.1 Convert the neon floating-point vector operations VFMA and VFMS to use a gvec helper, and use this to implement the fp16 case. This is the last use of do_3same_fp() so we can now delete that function. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-32-peter.maydell@linaro.org --- target/arm/helper.h | 6 +++ target/arm/vec_helper.c | 33 +++++++++++- target/arm/translate-neon.c.inc | 92 +-------------------------------- 3 files changed, 40 insertions(+), 91 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmls_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmls_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_vfma_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_vfma_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_vfms_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_vfms_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/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 float32 float32_mulsub_nf(float32 dest, float32 op1, float32 op2, return float32_sub(dest, float32_mul(op1, op2, stat), stat); } -#define DO_MULADD(NAME, FUNC, TYPE) \ +/* Fused versions; these have the semantics Neon VFMA/VFMS want */ +static float16 float16_muladd_f(float16 dest, float16 op1, float16 op2, + float_status *stat) +{ + return float16_muladd(op1, op2, dest, 0, stat); +} + +static float32 float32_muladd_f(float32 dest, float32 op1, float32 op2, + float_status *stat) +{ + return float32_muladd(op1, op2, dest, 0, stat); +} + +static float16 float16_mulsub_f(float16 dest, float16 op1, float16 op2, + float_status *stat) +{ + return float16_muladd(float16_chs(op1), op2, dest, 0, stat); +} + +static float32 float32_mulsub_f(float32 dest, float32 op1, float32 op2, + float_status *stat) +{ + return float32_muladd(float32_chs(op1), op2, dest, 0, stat); +} + +#define DO_MULADD(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ { \ intptr_t i, oprsz = simd_oprsz(desc); \ @@ -XXX,XX +XXX,XX @@ DO_MULADD(gvec_fmla_s, float32_muladd_nf, float32) DO_MULADD(gvec_fmls_h, float16_mulsub_nf, float16) DO_MULADD(gvec_fmls_s, float32_mulsub_nf, float32) +DO_MULADD(gvec_vfma_h, float16_muladd_f, float16) +DO_MULADD(gvec_vfma_s, float32_muladd_f, float32) + +DO_MULADD(gvec_vfms_h, float16_mulsub_f, float16) +DO_MULADD(gvec_vfms_s, float32_mulsub_f, float32) + /* For the indexed ops, SVE applies the index per 128-bit vector segment. * For AdvSIMD, there is of course only one such vector segment. */ diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -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 = fpstatus_ptr(FPST_STD); - 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; -} - #define WRAP_FP_GVEC(WRAPNAME, FPST, FUNC) \ static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \ uint32_t rn_ofs, uint32_t rm_ofs, \ @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VMAX, gen_helper_gvec_fmax_s, gen_helper_gvec_fmax_h) DO_3S_FP_GVEC(VMIN, gen_helper_gvec_fmin_s, gen_helper_gvec_fmin_h) DO_3S_FP_GVEC(VMLA, gen_helper_gvec_fmla_s, gen_helper_gvec_fmla_h) DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_s, gen_helper_gvec_fmls_h) +DO_3S_FP_GVEC(VFMA, gen_helper_gvec_vfma_s, gen_helper_gvec_vfma_h) +DO_3S_FP_GVEC(VFMS, gen_helper_gvec_vfms_s, gen_helper_gvec_vfms_h) WRAP_FP_GVEC(gen_VMAXNM_fp32_3s, FPST_STD, gen_helper_gvec_fmaxnum_s) WRAP_FP_GVEC(gen_VMAXNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fmaxnum_h) @@ -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 */ -- 2.20.1 Convert the neon floating-point vector compare-vs-0 insns VCEQ0, VCGT0, VCLE0, VCGE0 and VCLT0 to use a gvec helper, and use this to implement the fp16 case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-33-peter.maydell@linaro.org --- target/arm/helper.h | 15 +++++++++++++++ target/arm/vec_helper.c | 25 +++++++++++++++++++++++++ target/arm/translate-neon.c.inc | 33 +++++---------------------------- 3 files changed, 45 insertions(+), 28 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_frsqrte_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frsqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frsqrte_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fcgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fcgt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_fcge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fcge0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_fceq0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fceq0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_fcle0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fcle0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(gvec_fclt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fclt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fadd_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) 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_2OP(gvec_frsqrte_h, helper_rsqrte_f16, float16) DO_2OP(gvec_frsqrte_s, helper_rsqrte_f32, float32) DO_2OP(gvec_frsqrte_d, helper_rsqrte_f64, float64) +#define WRAP_CMP0_FWD(FN, CMPOP, TYPE) \ + static TYPE TYPE##_##FN##0(TYPE op, float_status *stat) \ + { \ + return TYPE##_##CMPOP(op, TYPE##_zero, stat); \ + } + +#define WRAP_CMP0_REV(FN, CMPOP, TYPE) \ + static TYPE TYPE##_##FN##0(TYPE op, float_status *stat) \ + { \ + return TYPE##_##CMPOP(TYPE##_zero, op, stat); \ + } + +#define DO_2OP_CMP0(FN, CMPOP, DIRN) \ + WRAP_CMP0_##DIRN(FN, CMPOP, float16) \ + WRAP_CMP0_##DIRN(FN, CMPOP, float32) \ + DO_2OP(gvec_f##FN##0_h, float16_##FN##0, float16) \ + DO_2OP(gvec_f##FN##0_s, float32_##FN##0, float32) + +DO_2OP_CMP0(cgt, cgt, FWD) +DO_2OP_CMP0(cge, cge, FWD) +DO_2OP_CMP0(ceq, ceq, FWD) +DO_2OP_CMP0(clt, cgt, REV) +DO_2OP_CMP0(cle, cge, REV) + #undef DO_2OP +#undef DO_2OP_CMP0 /* Floating-point trigonometric starting value. * See the ARM ARM pseudocode function FPTrigSMul. diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ DO_2MISC_FP(VCVT_UF, gen_helper_vfp_touizs) DO_2MISC_FP_VEC(VRECPE_F, gen_helper_gvec_frecpe_h, gen_helper_gvec_frecpe_s) DO_2MISC_FP_VEC(VRSQRTE_F, gen_helper_gvec_frsqrte_h, gen_helper_gvec_frsqrte_s) +DO_2MISC_FP_VEC(VCGT0_F, gen_helper_gvec_fcgt0_h, gen_helper_gvec_fcgt0_s) +DO_2MISC_FP_VEC(VCGE0_F, gen_helper_gvec_fcge0_h, gen_helper_gvec_fcge0_s) +DO_2MISC_FP_VEC(VCEQ0_F, gen_helper_gvec_fceq0_h, gen_helper_gvec_fceq0_s) +DO_2MISC_FP_VEC(VCLT0_F, gen_helper_gvec_fclt0_h, gen_helper_gvec_fclt0_s) +DO_2MISC_FP_VEC(VCLE0_F, gen_helper_gvec_fcle0_h, gen_helper_gvec_fcle0_s) static bool trans_VRINTX(DisasContext *s, arg_2misc *a) { @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX(DisasContext *s, arg_2misc *a) return do_2misc_fp(s, a, gen_helper_rints_exact); } -#define WRAP_FP_CMP0_FWD(WRAPNAME, FUNC) \ - static void WRAPNAME(TCGv_i32 d, TCGv_i32 m, TCGv_ptr fpst) \ - { \ - TCGv_i32 zero = tcg_const_i32(0); \ - FUNC(d, m, zero, fpst); \ - tcg_temp_free_i32(zero); \ - } -#define WRAP_FP_CMP0_REV(WRAPNAME, FUNC) \ - static void WRAPNAME(TCGv_i32 d, TCGv_i32 m, TCGv_ptr fpst) \ - { \ - TCGv_i32 zero = tcg_const_i32(0); \ - FUNC(d, zero, m, fpst); \ - tcg_temp_free_i32(zero); \ - } - -#define DO_FP_CMP0(INSN, FUNC, REV) \ - WRAP_FP_CMP0_##REV(gen_##INSN, FUNC) \ - static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ - { \ - return do_2misc_fp(s, a, gen_##INSN); \ - } - -DO_FP_CMP0(VCGT0_F, gen_helper_neon_cgt_f32, FWD) -DO_FP_CMP0(VCGE0_F, gen_helper_neon_cge_f32, FWD) -DO_FP_CMP0(VCEQ0_F, gen_helper_neon_ceq_f32, FWD) -DO_FP_CMP0(VCLE0_F, gen_helper_neon_cge_f32, REV) -DO_FP_CMP0(VCLT0_F, gen_helper_neon_cgt_f32, REV) - static bool do_vrint(DisasContext *s, arg_2misc *a, int rmode) { /* -- 2.20.1 Convert the Neon VRECPS insn to using a gvec helper, and use this to implement the fp16 case. The phrasing of the new float32_recps_nf() is slightly different from the old recps_f32() so that it parallels the f16 version; for f16 we can't assume that flush-to-zero is always enabled. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-34-peter.maydell@linaro.org --- target/arm/helper.h | 4 +++- target/arm/vec_helper.c | 31 +++++++++++++++++++++++++++++++ target/arm/vfp_helper.c | 13 ------------- target/arm/translate-neon.c.inc | 21 +-------------------- 4 files changed, 35 insertions(+), 34 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_4(vfp_muladdd, f64, f64, f64, f64, ptr) DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, ptr) DEF_HELPER_4(vfp_muladdh, f16, f16, f16, f16, ptr) -DEF_HELPER_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) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fmaxnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i3 DEF_HELPER_FLAGS_5(gvec_fminnum_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fminnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_recps_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_recps_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) 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 float32 float32_abd(float32 op1, float32 op2, float_status *stat) return float32_abs(float32_sub(op1, op2, stat)); } +/* + * Reciprocal step. These are the AArch32 version which uses a + * non-fused multiply-and-subtract. + */ +static float16 float16_recps_nf(float16 op1, float16 op2, float_status *stat) +{ + op1 = float16_squash_input_denormal(op1, stat); + op2 = float16_squash_input_denormal(op2, stat); + + if ((float16_is_infinity(op1) && float16_is_zero(op2)) || + (float16_is_infinity(op2) && float16_is_zero(op1))) { + return float16_two; + } + return float16_sub(float16_two, float16_mul(op1, op2, stat), stat); +} + +static float32 float32_recps_nf(float32 op1, float32 op2, float_status *stat) +{ + op1 = float32_squash_input_denormal(op1, stat); + op2 = float32_squash_input_denormal(op2, stat); + + if ((float32_is_infinity(op1) && float32_is_zero(op2)) || + (float32_is_infinity(op2) && float32_is_zero(op1))) { + return float32_two; + } + return float32_sub(float32_two, float32_mul(op1, op2, stat), 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_fmaxnum_s, float32_maxnum, float32) DO_3OP(gvec_fminnum_h, float16_minnum, float16) DO_3OP(gvec_fminnum_s, float32_minnum, float32) +DO_3OP(gvec_recps_nf_h, float16_recps_nf, float16) +DO_3OP(gvec_recps_nf_s, float32_recps_nf, float32) + #ifdef TARGET_AARCH64 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) 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) return r; } -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)) || - (float32_is_infinity(b) && float32_is_zero_or_denormal(a))) { - if (!(float32_is_zero(a) || float32_is_zero(b))) { - float_raise(float_flag_input_denormal, s); - } - return float32_two; - } - return float32_sub(float32_two, float32_mul(a, b, s), s); -} - float32 HELPER(rsqrts_f32)(CPUARMState *env, float32 a, float32 b) { float_status *s = &env->vfp.standard_fp_status; diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VMLA, gen_helper_gvec_fmla_s, gen_helper_gvec_fmla_h) DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_s, gen_helper_gvec_fmls_h) DO_3S_FP_GVEC(VFMA, gen_helper_gvec_vfma_s, gen_helper_gvec_vfma_h) DO_3S_FP_GVEC(VFMS, gen_helper_gvec_vfms_s, gen_helper_gvec_vfms_h) +DO_3S_FP_GVEC(VRECPS, gen_helper_gvec_recps_nf_s, gen_helper_gvec_recps_nf_h) WRAP_FP_GVEC(gen_VMAXNM_fp32_3s, FPST_STD, gen_helper_gvec_fmaxnum_s) WRAP_FP_GVEC(gen_VMAXNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fmaxnum_h) @@ -XXX,XX +XXX,XX @@ static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) return do_3same(s, a, gen_VMINNM_fp32_3s); } -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, -- 2.20.1 Convert the Neon VRSQRTS insn to using a gvec helper, and use this to implement the fp16 case. As with VRECPS, we adjust the phrasing of the new implementation slightly so that the fp32 version parallels the fp16 one. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-35-peter.maydell@linaro.org --- target/arm/helper.h | 4 +++- target/arm/vec_helper.c | 30 ++++++++++++++++++++++++++++++ target/arm/vfp_helper.c | 15 --------------- target/arm/translate-neon.c.inc | 21 +-------------------- 4 files changed, 34 insertions(+), 36 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_4(vfp_muladdd, f64, f64, f64, f64, ptr) DEF_HELPER_4(vfp_muladds, f32, f32, f32, f32, ptr) DEF_HELPER_4(vfp_muladdh, f16, f16, f16, f16, ptr) -DEF_HELPER_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) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fminnum_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i3 DEF_HELPER_FLAGS_5(gvec_recps_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_recps_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_rsqrts_nf_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_5(gvec_fmla_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fmla_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) 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 float32 float32_recps_nf(float32 op1, float32 op2, float_status *stat) return float32_sub(float32_two, float32_mul(op1, op2, stat), stat); } +/* Reciprocal square-root step. AArch32 non-fused semantics. */ +static float16 float16_rsqrts_nf(float16 op1, float16 op2, float_status *stat) +{ + op1 = float16_squash_input_denormal(op1, stat); + op2 = float16_squash_input_denormal(op2, stat); + + if ((float16_is_infinity(op1) && float16_is_zero(op2)) || + (float16_is_infinity(op2) && float16_is_zero(op1))) { + return float16_one_point_five; + } + op1 = float16_sub(float16_three, float16_mul(op1, op2, stat), stat); + return float16_div(op1, float16_two, stat); +} + +static float32 float32_rsqrts_nf(float32 op1, float32 op2, float_status *stat) +{ + op1 = float32_squash_input_denormal(op1, stat); + op2 = float32_squash_input_denormal(op2, stat); + + if ((float32_is_infinity(op1) && float32_is_zero(op2)) || + (float32_is_infinity(op2) && float32_is_zero(op1))) { + return float32_one_point_five; + } + op1 = float32_sub(float32_three, float32_mul(op1, op2, stat), stat); + return float32_div(op1, float32_two, 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_fminnum_s, float32_minnum, float32) DO_3OP(gvec_recps_nf_h, float16_recps_nf, float16) DO_3OP(gvec_recps_nf_s, float32_recps_nf, float32) +DO_3OP(gvec_rsqrts_nf_h, float16_rsqrts_nf, float16) +DO_3OP(gvec_rsqrts_nf_s, float32_rsqrts_nf, float32) + #ifdef TARGET_AARCH64 DO_3OP(gvec_recps_h, helper_recpsf_f16, float16) 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) return r; } -float32 HELPER(rsqrts_f32)(CPUARMState *env, float32 a, float32 b) -{ - float_status *s = &env->vfp.standard_fp_status; - float32 product; - if ((float32_is_infinity(a) && float32_is_zero_or_denormal(b)) || - (float32_is_infinity(b) && float32_is_zero_or_denormal(a))) { - if (!(float32_is_zero(a) || float32_is_zero(b))) { - float_raise(float_flag_input_denormal, s); - } - return float32_one_point_five; - } - product = float32_mul(a, b, s); - return float32_div(float32_sub(float32_three, product, s), float32_two, s); -} - /* NEON helpers. */ /* Constants 256 and 512 are used in some helpers; we avoid relying on diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ DO_3S_FP_GVEC(VMLS, gen_helper_gvec_fmls_s, gen_helper_gvec_fmls_h) DO_3S_FP_GVEC(VFMA, gen_helper_gvec_vfma_s, gen_helper_gvec_vfma_h) DO_3S_FP_GVEC(VFMS, gen_helper_gvec_vfms_s, gen_helper_gvec_vfms_h) DO_3S_FP_GVEC(VRECPS, gen_helper_gvec_recps_nf_s, gen_helper_gvec_recps_nf_h) +DO_3S_FP_GVEC(VRSQRTS, gen_helper_gvec_rsqrts_nf_s, gen_helper_gvec_rsqrts_nf_h) WRAP_FP_GVEC(gen_VMAXNM_fp32_3s, FPST_STD, gen_helper_gvec_fmaxnum_s) WRAP_FP_GVEC(gen_VMAXNM_fp16_3s, FPST_STD_F16, gen_helper_gvec_fmaxnum_h) @@ -XXX,XX +XXX,XX @@ static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) return do_3same(s, a, gen_VMINNM_fp32_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 */ -- 2.20.1 Convert the Neon pairwise fp ops to use a single gvic-style helper to do the full operation instead of one helper call for each 32-bit part. This allows us to use the same framework to implement the fp16. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-36-peter.maydell@linaro.org --- target/arm/helper.h | 7 +++++ target/arm/vec_helper.c | 45 +++++++++++++++++++++++++++++++++ target/arm/translate-neon.c.inc | 42 ++++++++++++------------------ 3 files changed, 68 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_5(gvec_fcmlas_idx, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_fcmlad, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_paddh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_pmaxh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_pminh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_padds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_pmaxs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_pmins, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) 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_ABA(gvec_uaba_s, uint32_t) DO_ABA(gvec_uaba_d, uint64_t) #undef DO_ABA + +#define DO_NEON_PAIRWISE(NAME, OP) \ + void HELPER(NAME##s)(void *vd, void *vn, void *vm, \ + void *stat, uint32_t oprsz) \ + { \ + float_status *fpst = stat; \ + float32 *d = vd; \ + float32 *n = vn; \ + float32 *m = vm; \ + float32 r0, r1; \ + \ + /* Read all inputs before writing outputs in case vm == vd */ \ + r0 = float32_##OP(n[H4(0)], n[H4(1)], fpst); \ + r1 = float32_##OP(m[H4(0)], m[H4(1)], fpst); \ + \ + d[H4(0)] = r0; \ + d[H4(1)] = r1; \ + } \ + \ + void HELPER(NAME##h)(void *vd, void *vn, void *vm, \ + void *stat, uint32_t oprsz) \ + { \ + float_status *fpst = stat; \ + float16 *d = vd; \ + float16 *n = vn; \ + float16 *m = vm; \ + float16 r0, r1, r2, r3; \ + \ + /* Read all inputs before writing outputs in case vm == vd */ \ + r0 = float16_##OP(n[H2(0)], n[H2(1)], fpst); \ + r1 = float16_##OP(n[H2(2)], n[H2(3)], fpst); \ + r2 = float16_##OP(m[H2(0)], m[H2(1)], fpst); \ + r3 = float16_##OP(m[H2(2)], m[H2(3)], fpst); \ + \ + d[H4(0)] = r0; \ + d[H4(1)] = r1; \ + d[H4(2)] = r2; \ + d[H4(3)] = r3; \ + } + +DO_NEON_PAIRWISE(neon_padd, add) +DO_NEON_PAIRWISE(neon_pmax, max) +DO_NEON_PAIRWISE(neon_pmin, min) + +#undef DO_NEON_PAIRWISE diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMINNM_fp_3s(DisasContext *s, arg_3same *a) return do_3same(s, a, gen_VMINNM_fp32_3s); } -static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn) +static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, + gen_helper_gvec_3_ptr *fn) { - /* FP operations handled pairwise 32 bits at a time */ - TCGv_i32 tmp, tmp2, tmp3; + /* FP pairwise operations */ TCGv_ptr fpstatus; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { @@ -XXX,XX +XXX,XX @@ static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn) 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 = fpstatus_ptr(FPST_STD); - 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); + fpstatus = fpstatus_ptr(a->size != 0 ? FPST_STD_F16 : FPST_STD); + tcg_gen_gvec_3_ptr(vfp_reg_offset(1, a->vd), + vfp_reg_offset(1, a->vn), + vfp_reg_offset(1, a->vm), + fpstatus, 8, 8, 0, fn); tcg_temp_free_ptr(fpstatus); - neon_store_reg(a->vd, 0, tmp); - neon_store_reg(a->vd, 1, tmp3); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_3same_fp_pair(DisasContext *s, arg_3same *a, VFPGen3OpSPFn *fn) static bool trans_##INSN##_fp_3s(DisasContext *s, arg_3same *a) \ { \ if (a->size != 0) { \ - /* TODO fp16 support */ \ - return false; \ + if (!dc_isar_feature(aa32_fp16_arith, s)) { \ + return false; \ + } \ + return do_3same_fp_pair(s, a, FUNC##h); \ } \ - return do_3same_fp_pair(s, a, FUNC); \ + return do_3same_fp_pair(s, a, FUNC##s); \ } -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) +DO_3S_FP_PAIR(VPADD, gen_helper_neon_padd) +DO_3S_FP_PAIR(VPMAX, gen_helper_neon_pmax) +DO_3S_FP_PAIR(VPMIN, gen_helper_neon_pmin) static bool do_vector_2sh(DisasContext *s, arg_2reg_shift *a, GVecGen2iFn *fn) { -- 2.20.1 Convert the Neon float-integer VCVT insns to gvec, and use this to implement fp16 support for them. Note that unlike the VFP int<->fp16 VCVT insns we converted earlier and which convert to/from a 32-bit integer, these Neon insns convert to/from 16-bit integers. So we can use the existing vfp conversion helpers for the f32<->u32/i32 case but need to provide our own for f16<->u16/i16. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-37-peter.maydell@linaro.org --- target/arm/helper.h | 9 +++++++++ target/arm/vec_helper.c | 29 +++++++++++++++++++++++++++++ target/arm/translate-neon.c.inc | 15 ++++----------- 3 files changed, 42 insertions(+), 11 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(neon_padds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(neon_pmaxs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(neon_pmins, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sstoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_sitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_ustoh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_uitos, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_tosszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_tosizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_touszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_touizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) 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 uint32_t float32_acgt(float32 op1, float32 op2, float_status *stat) return -float32_lt(float32_abs(op2), float32_abs(op1), stat); } +static int16_t vfp_tosszh(float16 x, void *fpstp) +{ + float_status *fpst = fpstp; + if (float16_is_any_nan(x)) { + float_raise(float_flag_invalid, fpst); + return 0; + } + return float16_to_int16_round_to_zero(x, fpst); +} + +static uint16_t vfp_touszh(float16 x, void *fpstp) +{ + float_status *fpst = fpstp; + if (float16_is_any_nan(x)) { + float_raise(float_flag_invalid, fpst); + return 0; + } + return float16_to_uint16_round_to_zero(x, fpst); +} + #define DO_2OP(NAME, FUNC, TYPE) \ void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ { \ @@ -XXX,XX +XXX,XX @@ DO_2OP(gvec_frsqrte_h, helper_rsqrte_f16, float16) DO_2OP(gvec_frsqrte_s, helper_rsqrte_f32, float32) DO_2OP(gvec_frsqrte_d, helper_rsqrte_f64, float64) +DO_2OP(gvec_sitos, helper_vfp_sitos, int32_t) +DO_2OP(gvec_uitos, helper_vfp_uitos, uint32_t) +DO_2OP(gvec_tosizs, helper_vfp_tosizs, float32) +DO_2OP(gvec_touizs, helper_vfp_touizs, float32) +DO_2OP(gvec_sstoh, int16_to_float16, int16_t) +DO_2OP(gvec_ustoh, uint16_to_float16, uint16_t) +DO_2OP(gvec_tosszh, vfp_tosszh, float16) +DO_2OP(gvec_touszh, vfp_touszh, float16) + #define WRAP_CMP0_FWD(FN, CMPOP, TYPE) \ static TYPE TYPE##_##FN##0(TYPE op, float_status *stat) \ { \ diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool do_2misc_fp(DisasContext *s, arg_2misc *a, return true; } -#define DO_2MISC_FP(INSN, FUNC) \ - static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ - { \ - return do_2misc_fp(s, a, FUNC); \ - } - -DO_2MISC_FP(VCVT_FS, gen_helper_vfp_sitos) -DO_2MISC_FP(VCVT_FU, gen_helper_vfp_uitos) -DO_2MISC_FP(VCVT_SF, gen_helper_vfp_tosizs) -DO_2MISC_FP(VCVT_UF, gen_helper_vfp_touizs) - #define DO_2MISC_FP_VEC(INSN, HFUNC, SFUNC) \ static void gen_##INSN(unsigned vece, uint32_t rd_ofs, \ uint32_t rm_ofs, \ @@ -XXX,XX +XXX,XX @@ DO_2MISC_FP_VEC(VCGE0_F, gen_helper_gvec_fcge0_h, gen_helper_gvec_fcge0_s) DO_2MISC_FP_VEC(VCEQ0_F, gen_helper_gvec_fceq0_h, gen_helper_gvec_fceq0_s) DO_2MISC_FP_VEC(VCLT0_F, gen_helper_gvec_fclt0_h, gen_helper_gvec_fclt0_s) DO_2MISC_FP_VEC(VCLE0_F, gen_helper_gvec_fcle0_h, gen_helper_gvec_fcle0_s) +DO_2MISC_FP_VEC(VCVT_FS, gen_helper_gvec_sstoh, gen_helper_gvec_sitos) +DO_2MISC_FP_VEC(VCVT_FU, gen_helper_gvec_ustoh, gen_helper_gvec_uitos) +DO_2MISC_FP_VEC(VCVT_SF, gen_helper_gvec_tosszh, gen_helper_gvec_tosizs) +DO_2MISC_FP_VEC(VCVT_UF, gen_helper_gvec_touszh, gen_helper_gvec_touizs) static bool trans_VRINTX(DisasContext *s, arg_2misc *a) { -- 2.20.1 Convert the Neon VCVT float<->fixed-point insns to a gvec style, in preparation for adding fp16 support. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-38-peter.maydell@linaro.org --- target/arm/helper.h | 5 +++++ target/arm/vec_helper.c | 20 +++++++++++++++++++ target/arm/translate-neon.c.inc | 35 +++++++++++++++++---------------- 3 files changed, 43 insertions(+), 17 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_tosizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_touszh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_touizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_sf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_uf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_fs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_fu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) 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_NEON_PAIRWISE(neon_pmax, max) DO_NEON_PAIRWISE(neon_pmin, min) #undef DO_NEON_PAIRWISE + +#define DO_VCVT_FIXED(NAME, FUNC, TYPE) \ + void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ + { \ + intptr_t i, oprsz = simd_oprsz(desc); \ + int shift = simd_data(desc); \ + TYPE *d = vd, *n = vn; \ + float_status *fpst = stat; \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + d[i] = FUNC(n[i], shift, fpst); \ + } \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ + } + +DO_VCVT_FIXED(gvec_vcvt_sf, helper_vfp_sltos, uint32_t) +DO_VCVT_FIXED(gvec_vcvt_uf, helper_vfp_ultos, uint32_t) +DO_VCVT_FIXED(gvec_vcvt_fs, helper_vfp_tosls_round_to_zero, uint32_t) +DO_VCVT_FIXED(gvec_vcvt_fu, helper_vfp_touls_round_to_zero, uint32_t) + +#undef DO_VCVT_FIXED diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VSHLL_U_2sh(DisasContext *s, arg_2reg_shift *a) } static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, - NeonGenTwoSingleOpFn *fn) + gen_helper_gvec_2_ptr *fn) { /* FP operations in 2-reg-and-shift group */ - TCGv_i32 tmp, shiftv; - TCGv_ptr fpstatus; - int pass; + int vec_size = a->q ? 16 : 8; + int rd_ofs = neon_reg_offset(a->vd, 0); + int rm_ofs = neon_reg_offset(a->vm, 0); + TCGv_ptr fpst; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return false; } + if (a->size != 0) { + if (!dc_isar_feature(aa32_fp16_arith, s)) { + return false; + } + } + /* UNDEF accesses to D16-D31 if they don't exist. */ if (!dc_isar_feature(aa32_simd_r32, s) && ((a->vd | a->vm) & 0x10)) { @@ -XXX,XX +XXX,XX @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, return true; } - fpstatus = fpstatus_ptr(FPST_STD); - shiftv = tcg_const_i32(a->shift); - for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - tmp = neon_load_reg(a->vm, pass); - fn(tmp, tmp, shiftv, fpstatus); - neon_store_reg(a->vd, pass, tmp); - } - tcg_temp_free_ptr(fpstatus); - tcg_temp_free_i32(shiftv); + fpst = fpstatus_ptr(a->size ? FPST_STD_F16 : FPST_STD); + tcg_gen_gvec_2_ptr(rd_ofs, rm_ofs, fpst, vec_size, vec_size, a->shift, fn); + tcg_temp_free_ptr(fpst); return true; } @@ -XXX,XX +XXX,XX @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, return do_fp_2sh(s, a, FUNC); \ } -DO_FP_2SH(VCVT_SF, gen_helper_vfp_sltos) -DO_FP_2SH(VCVT_UF, gen_helper_vfp_ultos) -DO_FP_2SH(VCVT_FS, gen_helper_vfp_tosls_round_to_zero) -DO_FP_2SH(VCVT_FU, gen_helper_vfp_touls_round_to_zero) +DO_FP_2SH(VCVT_SF, gen_helper_gvec_vcvt_sf) +DO_FP_2SH(VCVT_UF, gen_helper_gvec_vcvt_uf) +DO_FP_2SH(VCVT_FS, gen_helper_gvec_vcvt_fs) +DO_FP_2SH(VCVT_FU, gen_helper_gvec_vcvt_fu) static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) { -- 2.20.1 Implement fp16 for the Neon VCVT insns which convert between float and fixed-point. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-39-peter.maydell@linaro.org --- target/arm/helper.h | 5 +++++ target/arm/neon-dp.decode | 8 +++++++- target/arm/vec_helper.c | 4 ++++ target/arm/translate-neon.c.inc | 5 +++++ 4 files changed, 21 insertions(+), 1 deletion(-) 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_vcvt_uf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_fs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_fu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_hs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) 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 @@ VMINNM_fp_3s 1111 001 1 0 . 1 . .... .... 1111 ... 1 .... @3same_fp # We use size=0 for fp32 and size=1 for fp16 to match the 3-same encodings. @2reg_vcvt .... ... . . . 1 ..... .... .... . q:1 . . .... \ &2reg_shift vm=%vm_dp vd=%vd_dp size=0 shift=%neon_rshift_i5 +@2reg_vcvt_f16 .... ... . . . 11 .... .... .... . q:1 . . .... \ + &2reg_shift vm=%vm_dp vd=%vd_dp size=1 shift=%neon_rshift_i4 VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_d VSHR_S_2sh 1111 001 0 1 . ...... .... 0000 . . . 1 .... @2reg_shr_s @@ -XXX,XX +XXX,XX @@ VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_h VSHLL_U_2sh 1111 001 1 1 . ...... .... 1010 . 0 . 1 .... @2reg_shll_b # VCVT fixed<->float conversions -# TODO: FP16 fixed<->float conversions are opc==0b1100 and 0b1101 +VCVT_SH_2sh 1111 001 0 1 . ...... .... 1100 0 . . 1 .... @2reg_vcvt_f16 +VCVT_UH_2sh 1111 001 1 1 . ...... .... 1100 0 . . 1 .... @2reg_vcvt_f16 +VCVT_HS_2sh 1111 001 0 1 . ...... .... 1101 0 . . 1 .... @2reg_vcvt_f16 +VCVT_HU_2sh 1111 001 1 1 . ...... .... 1101 0 . . 1 .... @2reg_vcvt_f16 + VCVT_SF_2sh 1111 001 0 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt VCVT_UF_2sh 1111 001 1 1 . ...... .... 1110 0 . . 1 .... @2reg_vcvt VCVT_FS_2sh 1111 001 0 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt 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_VCVT_FIXED(gvec_vcvt_sf, helper_vfp_sltos, uint32_t) DO_VCVT_FIXED(gvec_vcvt_uf, helper_vfp_ultos, uint32_t) DO_VCVT_FIXED(gvec_vcvt_fs, helper_vfp_tosls_round_to_zero, uint32_t) DO_VCVT_FIXED(gvec_vcvt_fu, helper_vfp_touls_round_to_zero, uint32_t) +DO_VCVT_FIXED(gvec_vcvt_sh, helper_vfp_shtoh, uint16_t) +DO_VCVT_FIXED(gvec_vcvt_uh, helper_vfp_uhtoh, uint16_t) +DO_VCVT_FIXED(gvec_vcvt_hs, helper_vfp_toshh_round_to_zero, uint16_t) +DO_VCVT_FIXED(gvec_vcvt_hu, helper_vfp_touhh_round_to_zero, uint16_t) #undef DO_VCVT_FIXED diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ DO_FP_2SH(VCVT_UF, gen_helper_gvec_vcvt_uf) DO_FP_2SH(VCVT_FS, gen_helper_gvec_vcvt_fs) DO_FP_2SH(VCVT_FU, gen_helper_gvec_vcvt_fu) +DO_FP_2SH(VCVT_SH, gen_helper_gvec_vcvt_sh) +DO_FP_2SH(VCVT_UH, gen_helper_gvec_vcvt_uh) +DO_FP_2SH(VCVT_HS, gen_helper_gvec_vcvt_hs) +DO_FP_2SH(VCVT_HU, gen_helper_gvec_vcvt_hu) + static uint64_t asimd_imm_const(uint32_t imm, int cmode, int op) { /* -- 2.20.1 Convert the Neon VCVT with-specified-rounding-mode instructions to gvec, and use this to implement fp16 support for them. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-40-peter.maydell@linaro.org --- target/arm/helper.h | 5 ++ target/arm/vec_helper.c | 23 +++++++ target/arm/translate-neon.c.inc | 105 ++++++++++++-------------------- 3 files changed, 66 insertions(+), 67 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_vcvt_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_hs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ss, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_us, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) 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_VCVT_FIXED(gvec_vcvt_hs, helper_vfp_toshh_round_to_zero, uint16_t) DO_VCVT_FIXED(gvec_vcvt_hu, helper_vfp_touhh_round_to_zero, uint16_t) #undef DO_VCVT_FIXED + +#define DO_VCVT_RMODE(NAME, FUNC, TYPE) \ + void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ + { \ + float_status *fpst = stat; \ + intptr_t i, oprsz = simd_oprsz(desc); \ + uint32_t rmode = simd_data(desc); \ + uint32_t prev_rmode = get_float_rounding_mode(fpst); \ + TYPE *d = vd, *n = vn; \ + set_float_rounding_mode(rmode, fpst); \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + d[i] = FUNC(n[i], 0, fpst); \ + } \ + set_float_rounding_mode(prev_rmode, fpst); \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ + } + +DO_VCVT_RMODE(gvec_vcvt_rm_ss, helper_vfp_tosls, uint32_t) +DO_VCVT_RMODE(gvec_vcvt_rm_us, helper_vfp_touls, uint32_t) +DO_VCVT_RMODE(gvec_vcvt_rm_sh, helper_vfp_toshh, uint16_t) +DO_VCVT_RMODE(gvec_vcvt_rm_uh, helper_vfp_touhh, uint16_t) + +#undef DO_VCVT_RMODE diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ DO_VRINT(VRINTZ, FPROUNDING_ZERO) DO_VRINT(VRINTM, FPROUNDING_NEGINF) DO_VRINT(VRINTP, FPROUNDING_POSINF) -static bool do_vcvt(DisasContext *s, arg_2misc *a, int rmode, bool is_signed) -{ - /* - * Handle a VCVT* operation by iterating 32 bits at a time, - * with a specified rounding mode in operation. - */ - int pass; - TCGv_ptr fpst; - TCGv_i32 tcg_rmode, tcg_shift; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON) || - !arm_dc_feature(s, ARM_FEATURE_V8)) { - return false; +#define DO_VEC_RMODE(INSN, RMODE, OP) \ + static void gen_##INSN(unsigned vece, uint32_t rd_ofs, \ + uint32_t rm_ofs, \ + uint32_t oprsz, uint32_t maxsz) \ + { \ + static gen_helper_gvec_2_ptr * const fns[4] = { \ + NULL, \ + gen_helper_gvec_##OP##h, \ + gen_helper_gvec_##OP##s, \ + NULL, \ + }; \ + TCGv_ptr fpst; \ + fpst = fpstatus_ptr(vece == 1 ? FPST_STD_F16 : FPST_STD); \ + tcg_gen_gvec_2_ptr(rd_ofs, rm_ofs, fpst, oprsz, maxsz, \ + arm_rmode_to_sf(RMODE), fns[vece]); \ + tcg_temp_free_ptr(fpst); \ + } \ + static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ + { \ + if (!arm_dc_feature(s, ARM_FEATURE_V8)) { \ + return false; \ + } \ + if (a->size == MO_16) { \ + if (!dc_isar_feature(aa32_fp16_arith, s)) { \ + return false; \ + } \ + } else if (a->size != MO_32) { \ + return false; \ + } \ + return do_2misc_vec(s, a, gen_##INSN); \ } - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vm) & 0x10)) { - return false; - } - - if (a->size != 2) { - /* TODO: FP16 will be the size == 1 case */ - return false; - } - - if ((a->vd | a->vm) & a->q) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - fpst = fpstatus_ptr(FPST_STD); - tcg_shift = tcg_const_i32(0); - tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode)); - gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env); - for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vm, pass); - if (is_signed) { - gen_helper_vfp_tosls(tmp, tmp, tcg_shift, fpst); - } else { - gen_helper_vfp_touls(tmp, tmp, tcg_shift, fpst); - } - neon_store_reg(a->vd, pass, tmp); - } - gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env); - tcg_temp_free_i32(tcg_rmode); - tcg_temp_free_i32(tcg_shift); - tcg_temp_free_ptr(fpst); - - return true; -} - -#define DO_VCVT(INSN, RMODE, SIGNED) \ - static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ - { \ - return do_vcvt(s, a, RMODE, SIGNED); \ - } - -DO_VCVT(VCVTAU, FPROUNDING_TIEAWAY, false) -DO_VCVT(VCVTAS, FPROUNDING_TIEAWAY, true) -DO_VCVT(VCVTNU, FPROUNDING_TIEEVEN, false) -DO_VCVT(VCVTNS, FPROUNDING_TIEEVEN, true) -DO_VCVT(VCVTPU, FPROUNDING_POSINF, false) -DO_VCVT(VCVTPS, FPROUNDING_POSINF, true) -DO_VCVT(VCVTMU, FPROUNDING_NEGINF, false) -DO_VCVT(VCVTMS, FPROUNDING_NEGINF, true) +DO_VEC_RMODE(VCVTAU, FPROUNDING_TIEAWAY, vcvt_rm_u) +DO_VEC_RMODE(VCVTAS, FPROUNDING_TIEAWAY, vcvt_rm_s) +DO_VEC_RMODE(VCVTNU, FPROUNDING_TIEEVEN, vcvt_rm_u) +DO_VEC_RMODE(VCVTNS, FPROUNDING_TIEEVEN, vcvt_rm_s) +DO_VEC_RMODE(VCVTPU, FPROUNDING_POSINF, vcvt_rm_u) +DO_VEC_RMODE(VCVTPS, FPROUNDING_POSINF, vcvt_rm_s) +DO_VEC_RMODE(VCVTMU, FPROUNDING_NEGINF, vcvt_rm_u) +DO_VEC_RMODE(VCVTMS, FPROUNDING_NEGINF, vcvt_rm_s) static bool trans_VSWP(DisasContext *s, arg_2misc *a) { -- 2.20.1 Convert the Neon VRINT-with-specified-rounding-mode insns to gvec, and use this to implement the fp16 versions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-41-peter.maydell@linaro.org --- target/arm/helper.h | 4 +- target/arm/vec_helper.c | 21 +++++++++++ target/arm/vfp_helper.c | 17 --------- target/arm/translate-neon.c.inc | 67 +++------------------------------ 4 files changed, 30 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_3(vfp_sqtoh, f16, i64, i32, ptr) DEF_HELPER_3(vfp_uqtoh, f16, i64, i32, ptr) DEF_HELPER_FLAGS_2(set_rmode, TCG_CALL_NO_RWG, i32, i32, ptr) -DEF_HELPER_FLAGS_2(set_neon_rmode, TCG_CALL_NO_RWG, i32, i32, env) DEF_HELPER_FLAGS_3(vfp_fcvt_f16_to_f32, TCG_CALL_NO_RWG, f32, f16, ptr, i32) DEF_HELPER_FLAGS_3(vfp_fcvt_f32_to_f16, TCG_CALL_NO_RWG, f16, f32, ptr, i32) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(gvec_vcvt_rm_us, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rm_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vrint_rm_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vrint_rm_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) 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_VCVT_RMODE(gvec_vcvt_rm_sh, helper_vfp_toshh, uint16_t) DO_VCVT_RMODE(gvec_vcvt_rm_uh, helper_vfp_touhh, uint16_t) #undef DO_VCVT_RMODE + +#define DO_VRINT_RMODE(NAME, FUNC, TYPE) \ + void HELPER(NAME)(void *vd, void *vn, void *stat, uint32_t desc) \ + { \ + float_status *fpst = stat; \ + intptr_t i, oprsz = simd_oprsz(desc); \ + uint32_t rmode = simd_data(desc); \ + uint32_t prev_rmode = get_float_rounding_mode(fpst); \ + TYPE *d = vd, *n = vn; \ + set_float_rounding_mode(rmode, fpst); \ + for (i = 0; i < oprsz / sizeof(TYPE); i++) { \ + d[i] = FUNC(n[i], fpst); \ + } \ + set_float_rounding_mode(prev_rmode, fpst); \ + clear_tail(d, oprsz, simd_maxsz(desc)); \ + } + +DO_VRINT_RMODE(gvec_vrint_rm_h, helper_rinth, uint16_t) +DO_VRINT_RMODE(gvec_vrint_rm_s, helper_rints, uint32_t) + +#undef DO_VRINT_RMODE 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(set_rmode)(uint32_t rmode, void *fpstp) return prev_rmode; } -/* Set the current fp rounding mode in the standard fp status and return - * the old one. This is for NEON instructions that need to change the - * rounding mode but wish to use the standard FPSCR values for everything - * else. Always set the rounding mode back to the correct value after - * modifying it. - * The argument is a softfloat float_round_ value. - */ -uint32_t HELPER(set_neon_rmode)(uint32_t rmode, CPUARMState *env) -{ - float_status *fp_status = &env->vfp.standard_fp_status; - - uint32_t prev_rmode = get_float_rounding_mode(fp_status); - set_float_rounding_mode(rmode, fp_status); - - return prev_rmode; -} - /* Half precision conversions. */ float32 HELPER(vfp_fcvt_f16_to_f32)(uint32_t a, void *fpstp, uint32_t ahp_mode) { diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX(DisasContext *s, arg_2misc *a) return do_2misc_fp(s, a, gen_helper_rints_exact); } -static bool do_vrint(DisasContext *s, arg_2misc *a, int rmode) -{ - /* - * Handle a VRINT* operation by iterating 32 bits at a time, - * with a specified rounding mode in operation. - */ - int pass; - TCGv_ptr fpst; - TCGv_i32 tcg_rmode; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON) || - !arm_dc_feature(s, ARM_FEATURE_V8)) { - return false; - } - - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vm) & 0x10)) { - return false; - } - - if (a->size != 2) { - /* TODO: FP16 will be the size == 1 case */ - return false; - } - - if ((a->vd | a->vm) & a->q) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - fpst = fpstatus_ptr(FPST_STD); - tcg_rmode = tcg_const_i32(arm_rmode_to_sf(rmode)); - gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env); - for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vm, pass); - gen_helper_rints(tmp, tmp, fpst); - neon_store_reg(a->vd, pass, tmp); - } - gen_helper_set_neon_rmode(tcg_rmode, tcg_rmode, cpu_env); - tcg_temp_free_i32(tcg_rmode); - tcg_temp_free_ptr(fpst); - - return true; -} - -#define DO_VRINT(INSN, RMODE) \ - static bool trans_##INSN(DisasContext *s, arg_2misc *a) \ - { \ - return do_vrint(s, a, RMODE); \ - } - -DO_VRINT(VRINTN, FPROUNDING_TIEEVEN) -DO_VRINT(VRINTA, FPROUNDING_TIEAWAY) -DO_VRINT(VRINTZ, FPROUNDING_ZERO) -DO_VRINT(VRINTM, FPROUNDING_NEGINF) -DO_VRINT(VRINTP, FPROUNDING_POSINF) - #define DO_VEC_RMODE(INSN, RMODE, OP) \ static void gen_##INSN(unsigned vece, uint32_t rd_ofs, \ uint32_t rm_ofs, \ @@ -XXX,XX +XXX,XX @@ DO_VEC_RMODE(VCVTPS, FPROUNDING_POSINF, vcvt_rm_s) DO_VEC_RMODE(VCVTMU, FPROUNDING_NEGINF, vcvt_rm_u) DO_VEC_RMODE(VCVTMS, FPROUNDING_NEGINF, vcvt_rm_s) +DO_VEC_RMODE(VRINTN, FPROUNDING_TIEEVEN, vrint_rm_) +DO_VEC_RMODE(VRINTA, FPROUNDING_TIEAWAY, vrint_rm_) +DO_VEC_RMODE(VRINTZ, FPROUNDING_ZERO, vrint_rm_) +DO_VEC_RMODE(VRINTM, FPROUNDING_NEGINF, vrint_rm_) +DO_VEC_RMODE(VRINTP, FPROUNDING_POSINF, vrint_rm_) + static bool trans_VSWP(DisasContext *s, arg_2misc *a) { TCGv_i64 rm, rd; -- 2.20.1 Convert the Neon VRINTX insn to use gvec, and use this to implement fp16 support for it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-42-peter.maydell@linaro.org --- target/arm/helper.h | 3 +++ target/arm/vec_helper.c | 3 +++ target/arm/translate-neon.c.inc | 45 +++------------------------------ 3 files changed, 9 insertions(+), 42 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_vcvt_rm_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vrint_rm_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vrint_rm_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vrintx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vrintx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_frecpe_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_frecpe_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) 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_2OP(gvec_frsqrte_h, helper_rsqrte_f16, float16) DO_2OP(gvec_frsqrte_s, helper_rsqrte_f32, float32) DO_2OP(gvec_frsqrte_d, helper_rsqrte_f64, float64) +DO_2OP(gvec_vrintx_h, float16_round_to_int, float16) +DO_2OP(gvec_vrintx_s, float32_round_to_int, float32) + DO_2OP(gvec_sitos, helper_vfp_sitos, int32_t) DO_2OP(gvec_uitos, helper_vfp_uitos, uint32_t) DO_2OP(gvec_tosizs, helper_vfp_tosizs, float32) diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VQNEG(DisasContext *s, arg_2misc *a) return do_2misc(s, a, fn[a->size]); } -static bool do_2misc_fp(DisasContext *s, arg_2misc *a, - NeonGenOneSingleOpFn *fn) -{ - int pass; - TCGv_ptr fpst; - - /* Handle a 2-reg-misc operation by iterating 32 bits at a time */ - 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->vm) & 0x10)) { - return false; - } - - if (a->size != 2) { - /* TODO: FP16 will be the size == 1 case */ - return false; - } - - if ((a->vd | a->vm) & a->q) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - fpst = fpstatus_ptr(FPST_STD); - for (pass = 0; pass < (a->q ? 4 : 2); pass++) { - TCGv_i32 tmp = neon_load_reg(a->vm, pass); - fn(tmp, tmp, fpst); - neon_store_reg(a->vd, pass, tmp); - } - tcg_temp_free_ptr(fpst); - - return true; -} - #define DO_2MISC_FP_VEC(INSN, HFUNC, SFUNC) \ static void gen_##INSN(unsigned vece, uint32_t rd_ofs, \ uint32_t rm_ofs, \ @@ -XXX,XX +XXX,XX @@ DO_2MISC_FP_VEC(VCVT_FU, gen_helper_gvec_ustoh, gen_helper_gvec_uitos) DO_2MISC_FP_VEC(VCVT_SF, gen_helper_gvec_tosszh, gen_helper_gvec_tosizs) DO_2MISC_FP_VEC(VCVT_UF, gen_helper_gvec_touszh, gen_helper_gvec_touizs) +DO_2MISC_FP_VEC(VRINTX_impl, gen_helper_gvec_vrintx_h, gen_helper_gvec_vrintx_s) + static bool trans_VRINTX(DisasContext *s, arg_2misc *a) { if (!arm_dc_feature(s, ARM_FEATURE_V8)) { return false; } - return do_2misc_fp(s, a, gen_helper_rints_exact); + return trans_VRINTX_impl(s, a); } #define DO_VEC_RMODE(INSN, RMODE, OP) \ -- 2.20.1 In the gvec helper functions for indexed operations, for AArch32 Neon the oprsz (total size of the vector) can be less than 16 bytes if the operation is on a D reg. Since the inner loop in these helpers always goes from 0 to segment, we must clamp it based on oprsz to avoid processing a full 16 byte segment when asked to handle an 8 byte wide vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-43-peter.maydell@linaro.org --- target/arm/vec_helper.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) 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_MULADD(gvec_vfms_s, float32_mulsub_f, float32) #define DO_MUL_IDX(NAME, TYPE, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, uint32_t desc) \ { \ - intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ + intptr_t i, j, oprsz = simd_oprsz(desc); \ + intptr_t segment = MIN(16, oprsz) / sizeof(TYPE); \ intptr_t idx = simd_data(desc); \ TYPE *d = vd, *n = vn, *m = vm; \ for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ @@ -XXX,XX +XXX,XX @@ DO_MUL_IDX(gvec_mul_idx_d, uint64_t, ) #define DO_MLA_IDX(NAME, TYPE, OP, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, uint32_t desc) \ { \ - intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ + intptr_t i, j, oprsz = simd_oprsz(desc); \ + intptr_t segment = MIN(16, oprsz) / sizeof(TYPE); \ intptr_t idx = simd_data(desc); \ TYPE *d = vd, *n = vn, *m = vm, *a = va; \ for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ @@ -XXX,XX +XXX,XX @@ DO_MLA_IDX(gvec_mls_idx_d, uint64_t, -, ) #define DO_FMUL_IDX(NAME, TYPE, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ { \ - intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ + intptr_t i, j, oprsz = simd_oprsz(desc); \ + intptr_t segment = MIN(16, oprsz) / sizeof(TYPE); \ intptr_t idx = simd_data(desc); \ TYPE *d = vd, *n = vn, *m = vm; \ for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ @@ -XXX,XX +XXX,XX @@ DO_FMUL_IDX(gvec_fmul_idx_d, float64, ) void HELPER(NAME)(void *vd, void *vn, void *vm, void *va, \ void *stat, uint32_t desc) \ { \ - intptr_t i, j, oprsz = simd_oprsz(desc), segment = 16 / sizeof(TYPE); \ + intptr_t i, j, oprsz = simd_oprsz(desc); \ + intptr_t segment = MIN(16, oprsz) / sizeof(TYPE); \ TYPE op1_neg = extract32(desc, SIMD_DATA_SHIFT, 1); \ intptr_t idx = desc >> (SIMD_DATA_SHIFT + 1); \ TYPE *d = vd, *n = vn, *m = vm, *a = va; \ -- 2.20.1 Add gvec helpers for doing Neon-style indexed non-fused fp multiply-and-accumulate operations. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20200828183354.27913-44-peter.maydell@linaro.org --- target/arm/helper.h | 10 ++++++++++ target/arm/vec_helper.c | 27 ++++++++++++++++++++++----- 2 files changed, 32 insertions(+), 5 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(gvec_fmul_idx_s, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(gvec_fmul_idx_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmla_nf_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmla_nf_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_fmls_nf_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_fmls_nf_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_6(gvec_fmla_idx_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(gvec_fmla_idx_s, TCG_CALL_NO_RWG, 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_MLA_IDX(gvec_mls_idx_d, uint64_t, -, ) #undef DO_MLA_IDX -#define DO_FMUL_IDX(NAME, TYPE, H) \ +#define DO_FMUL_IDX(NAME, ADD, TYPE, H) \ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ { \ intptr_t i, j, oprsz = simd_oprsz(desc); \ @@ -XXX,XX +XXX,XX @@ void HELPER(NAME)(void *vd, void *vn, void *vm, void *stat, uint32_t desc) \ for (i = 0; i < oprsz / sizeof(TYPE); i += segment) { \ TYPE mm = m[H(i + idx)]; \ for (j = 0; j < segment; j++) { \ - d[i + j] = TYPE##_mul(n[i + j], mm, stat); \ + d[i + j] = TYPE##_##ADD(d[i + j], \ + TYPE##_mul(n[i + j], mm, stat), stat); \ } \ } \ clear_tail(d, oprsz, simd_maxsz(desc)); \ } -DO_FMUL_IDX(gvec_fmul_idx_h, float16, H2) -DO_FMUL_IDX(gvec_fmul_idx_s, float32, H4) -DO_FMUL_IDX(gvec_fmul_idx_d, float64, ) +#define float16_nop(N, M, S) (M) +#define float32_nop(N, M, S) (M) +#define float64_nop(N, M, S) (M) +DO_FMUL_IDX(gvec_fmul_idx_h, nop, float16, H2) +DO_FMUL_IDX(gvec_fmul_idx_s, nop, float32, H4) +DO_FMUL_IDX(gvec_fmul_idx_d, nop, float64, ) + +/* + * Non-fused multiply-accumulate operations, for Neon. NB that unlike + * the fused ops below they assume accumulate both from and into Vd. + */ +DO_FMUL_IDX(gvec_fmla_nf_idx_h, add, float16, H2) +DO_FMUL_IDX(gvec_fmla_nf_idx_s, add, float32, H4) +DO_FMUL_IDX(gvec_fmls_nf_idx_h, sub, float16, H2) +DO_FMUL_IDX(gvec_fmls_nf_idx_s, sub, float32, H4) + +#undef float16_nop +#undef float32_nop +#undef float64_nop #undef DO_FMUL_IDX #define DO_FMLA_IDX(NAME, TYPE, H) \ -- 2.20.1 Convert the Neon floating-point VMUL, VMLA and VMLS to use gvec, and use this to implement fp16 support. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-45-peter.maydell@linaro.org --- target/arm/translate-neon.c.inc | 114 ++++++++++++++++---------------- 1 file changed, 57 insertions(+), 57 deletions(-) diff --git a/target/arm/translate-neon.c.inc b/target/arm/translate-neon.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c.inc +++ b/target/arm/translate-neon.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMLS_2sc(DisasContext *s, arg_2scalar *a) return do_2scalar(s, a, opfn[a->size], accfn[a->size]); } -/* - * Rather than have a float-specific version of do_2scalar just for - * three insns, we wrap a NeonGenTwoSingleOpFn to turn it into - * a NeonGenTwoOpFn. - */ -#define WRAP_FP_FN(WRAPNAME, FUNC) \ - static void WRAPNAME(TCGv_i32 rd, TCGv_i32 rn, TCGv_i32 rm) \ - { \ - TCGv_ptr fpstatus = fpstatus_ptr(FPST_STD); \ - FUNC(rd, rn, rm, fpstatus); \ - tcg_temp_free_ptr(fpstatus); \ +static bool do_2scalar_fp_vec(DisasContext *s, arg_2scalar *a, + gen_helper_gvec_3_ptr *fn) +{ + /* Two registers and a scalar, using gvec */ + int vec_size = a->q ? 16 : 8; + int rd_ofs = neon_reg_offset(a->vd, 0); + int rn_ofs = neon_reg_offset(a->vn, 0); + int rm_ofs; + int idx; + TCGv_ptr fpstatus; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; } -WRAP_FP_FN(gen_VMUL_F_mul, gen_helper_vfp_muls) -WRAP_FP_FN(gen_VMUL_F_add, gen_helper_vfp_adds) -WRAP_FP_FN(gen_VMUL_F_sub, gen_helper_vfp_subs) + /* 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; + } -static bool trans_VMUL_F_2sc(DisasContext *s, arg_2scalar *a) -{ - static NeonGenTwoOpFn * const opfn[] = { - NULL, - NULL, /* TODO: fp16 support */ - gen_VMUL_F_mul, - NULL, - }; + if (!fn) { + /* Bad size (including size == 3, which is a different insn group) */ + return false; + } - return do_2scalar(s, a, opfn[a->size], NULL); + if (a->q && ((a->vd | a->vn) & 1)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* a->vm is M:Vm, which encodes both register and index */ + idx = extract32(a->vm, a->size + 2, 2); + a->vm = extract32(a->vm, 0, a->size + 2); + rm_ofs = neon_reg_offset(a->vm, 0); + + fpstatus = fpstatus_ptr(a->size == 1 ? FPST_STD_F16 : FPST_STD); + tcg_gen_gvec_3_ptr(rd_ofs, rn_ofs, rm_ofs, fpstatus, + vec_size, vec_size, idx, fn); + tcg_temp_free_ptr(fpstatus); + return true; } -static bool trans_VMLA_F_2sc(DisasContext *s, arg_2scalar *a) -{ - static NeonGenTwoOpFn * const opfn[] = { - NULL, - NULL, /* TODO: fp16 support */ - gen_VMUL_F_mul, - NULL, - }; - static NeonGenTwoOpFn * const accfn[] = { - NULL, - NULL, /* TODO: fp16 support */ - gen_VMUL_F_add, - NULL, - }; +#define DO_VMUL_F_2sc(NAME, FUNC) \ + static bool trans_##NAME##_F_2sc(DisasContext *s, arg_2scalar *a) \ + { \ + static gen_helper_gvec_3_ptr * const opfn[] = { \ + NULL, \ + gen_helper_##FUNC##_h, \ + gen_helper_##FUNC##_s, \ + NULL, \ + }; \ + if (a->size == MO_16 && !dc_isar_feature(aa32_fp16_arith, s)) { \ + return false; \ + } \ + return do_2scalar_fp_vec(s, a, opfn[a->size]); \ + } - return do_2scalar(s, a, opfn[a->size], accfn[a->size]); -} - -static bool trans_VMLS_F_2sc(DisasContext *s, arg_2scalar *a) -{ - static NeonGenTwoOpFn * const opfn[] = { - NULL, - NULL, /* TODO: fp16 support */ - gen_VMUL_F_mul, - NULL, - }; - static NeonGenTwoOpFn * const accfn[] = { - NULL, - NULL, /* TODO: fp16 support */ - gen_VMUL_F_sub, - NULL, - }; - - return do_2scalar(s, a, opfn[a->size], accfn[a->size]); -} +DO_VMUL_F_2sc(VMUL, gvec_fmul_idx) +DO_VMUL_F_2sc(VMLA, gvec_fmla_nf_idx) +DO_VMUL_F_2sc(VMLS, gvec_fmls_nf_idx) WRAP_ENV_FN(gen_VQDMULH_16, gen_helper_neon_qdmulh_s16) WRAP_ENV_FN(gen_VQDMULH_32, gen_helper_neon_qdmulh_s32) -- 2.20.1 Set the MVFR1 ID register FPHP and SIMDHP fields to indicate that our "-cpu max" has v8.2-FP16. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200828183354.27913-46-peter.maydell@linaro.org --- target/arm/cpu.c | 3 ++- target/arm/cpu64.c | 10 ++++------ 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) cpu->isar.id_isar6 = t; t = cpu->isar.mvfr1; - t = FIELD_DP32(t, MVFR1, FPHP, 2); /* v8.0 FP support */ + t = FIELD_DP32(t, MVFR1, FPHP, 3); /* v8.2-FP16 */ + t = FIELD_DP32(t, MVFR1, SIMDHP, 2); /* v8.2-FP16 */ cpu->isar.mvfr1 = t; t = cpu->isar.mvfr2; diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) u = FIELD_DP32(u, ID_DFR0, PERFMON, 5); /* v8.4-PMU */ cpu->isar.id_dfr0 = u; - /* - * FIXME: We do not yet support ARMv8.2-fp16 for AArch32 yet, - * so do not set MVFR1.FPHP. Strictly speaking this is not legal, - * but it is also not legal to enable SVE without support for FP16, - * and enabling SVE in system mode is more useful in the short term. - */ + u = cpu->isar.mvfr1; + u = FIELD_DP32(u, MVFR1, FPHP, 3); /* v8.2-FP16 */ + u = FIELD_DP32(u, MVFR1, SIMDHP, 2); /* v8.2-FP16 */ + cpu->isar.mvfr1 = u; #ifdef CONFIG_USER_ONLY /* For usermode -cpu max we can use a larger and more efficient DCZ -- 2.20.1 From: Leif Lindholm <leif@nuviainc.com> The sbsa-ref platform uses a minimal device tree to pass amount of memory as well as number of cpus to the firmware. However, when dumping that minimal dtb (with -M sbsa-virt,dumpdtb=<file>), the resulting blob generates a warning when decompiled by dtc due to lack of reg property. Add a simple reg property per cpu, representing a 64-bit MPIDR_EL1. This also ends up being cleaner than having the firmware calculating its own IDs for generating APCI. Signed-off-by: Leif Lindholm <leif@nuviainc.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200827124335.30586-1-leif@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 29 +++++++++++++++++++++++------ 1 file changed, 23 insertions(+), 6 deletions(-) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ static const int sbsa_ref_irqmap[] = { [SBSA_EHCI] = 11, }; +static uint64_t sbsa_ref_cpu_mp_affinity(SBSAMachineState *sms, int idx) +{ + uint8_t clustersz = ARM_DEFAULT_CPUS_PER_CLUSTER; + return arm_cpu_mp_affinity(idx, clustersz); +} + /* * Firmware on this machine only uses ACPI table to load OS, these limited * device tree nodes are just to let firmware know the info which varies from @@ -XXX,XX +XXX,XX @@ static void create_fdt(SBSAMachineState *sms) g_free(matrix); } + /* + * From Documentation/devicetree/bindings/arm/cpus.yaml + * On ARM v8 64-bit systems this property is required + * and matches the MPIDR_EL1 register affinity bits. + * + * * If cpus node's #address-cells property is set to 2 + * + * The first reg cell bits [7:0] must be set to + * bits [39:32] of MPIDR_EL1. + * + * The second reg cell bits [23:0] must be set to + * bits [23:0] of MPIDR_EL1. + */ qemu_fdt_add_subnode(sms->fdt, "/cpus"); + qemu_fdt_setprop_cell(sms->fdt, "/cpus", "#address-cells", 2); + qemu_fdt_setprop_cell(sms->fdt, "/cpus", "#size-cells", 0x0); for (cpu = sms->smp_cpus - 1; cpu >= 0; cpu--) { char *nodename = g_strdup_printf("/cpus/cpu@%d", cpu); ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(cpu)); CPUState *cs = CPU(armcpu); + uint64_t mpidr = sbsa_ref_cpu_mp_affinity(sms, cpu); qemu_fdt_add_subnode(sms->fdt, nodename); + qemu_fdt_setprop_u64(sms->fdt, nodename, "reg", mpidr); if (ms->possible_cpus->cpus[cs->cpu_index].props.has_node_id) { qemu_fdt_setprop_cell(sms->fdt, nodename, "numa-node-id", @@ -XXX,XX +XXX,XX @@ static void sbsa_ref_init(MachineState *machine) arm_load_kernel(ARM_CPU(first_cpu), machine, &sms->bootinfo); } -static uint64_t sbsa_ref_cpu_mp_affinity(SBSAMachineState *sms, int idx) -{ - uint8_t clustersz = ARM_DEFAULT_CPUS_PER_CLUSTER; - return arm_cpu_mp_affinity(idx, clustersz); -} - static const CPUArchIdList *sbsa_ref_possible_cpu_arch_ids(MachineState *ms) { unsigned int max_cpus = ms->smp.max_cpus; -- 2.20.1 From: Graeme Gregory <graeme@nuviainc.com> A difference between sbsa platform and the virt platform is PSCI is handled by ARM-TF in the sbsa platform. This means that the PSCI code there needs to communicate some of the platform power changes down to the qemu code for things like shutdown/reset control. Space has been left to extend the EC if we find other use cases in future where ARM-TF and qemu need to communicate. Signed-off-by: Graeme Gregory <graeme@nuviainc.com> Reviewed-by: Leif Lindholm <leif@nuviainc.com> Tested-by: Leif Lindholm <leif@nuviainc.com> Message-id: 20200826141952.136164-2-graeme@nuviainc.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/sbsa_ec.c | 98 +++++++++++++++++++++++++++++++++++++++++++++ hw/misc/meson.build | 2 + 2 files changed, 100 insertions(+) create mode 100644 hw/misc/sbsa_ec.c diff --git a/hw/misc/sbsa_ec.c b/hw/misc/sbsa_ec.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/sbsa_ec.c @@ -XXX,XX +XXX,XX @@ +/* + * ARM SBSA Reference Platform Embedded Controller + * + * A device to allow PSCI running in the secure side of sbsa-ref machine + * to communicate platform power states to qemu. + * + * Copyright (c) 2020 Nuvia Inc + * Written by Graeme Gregory <graeme@nuviainc.com> + * + * SPDX-License-Identifer: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/log.h" +#include "hw/sysbus.h" +#include "sysemu/runstate.h" + +typedef struct { + SysBusDevice parent_obj; + MemoryRegion iomem; +} SECUREECState; + +#define TYPE_SBSA_EC "sbsa-ec" +#define SECURE_EC(obj) OBJECT_CHECK(SECUREECState, (obj), TYPE_SBSA_EC) + +enum sbsa_ec_powerstates { + SBSA_EC_CMD_POWEROFF = 0x01, + SBSA_EC_CMD_REBOOT = 0x02, +}; + +static uint64_t sbsa_ec_read(void *opaque, hwaddr offset, unsigned size) +{ + /* No use for this currently */ + qemu_log_mask(LOG_GUEST_ERROR, "sbsa-ec: no readable registers"); + return 0; +} + +static void sbsa_ec_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + if (offset == 0) { /* PSCI machine power command register */ + switch (value) { + case SBSA_EC_CMD_POWEROFF: + qemu_system_shutdown_request(SHUTDOWN_CAUSE_GUEST_SHUTDOWN); + break; + case SBSA_EC_CMD_REBOOT: + qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "sbsa-ec: unknown power command"); + } + } else { + qemu_log_mask(LOG_GUEST_ERROR, "sbsa-ec: unknown EC register"); + } +} + +static const MemoryRegionOps sbsa_ec_ops = { + .read = sbsa_ec_read, + .write = sbsa_ec_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid.min_access_size = 4, + .valid.max_access_size = 4, +}; + +static void sbsa_ec_init(Object *obj) +{ + SECUREECState *s = SECURE_EC(obj); + SysBusDevice *dev = SYS_BUS_DEVICE(obj); + + memory_region_init_io(&s->iomem, obj, &sbsa_ec_ops, s, "sbsa-ec", + 0x1000); + sysbus_init_mmio(dev, &s->iomem); +} + +static void sbsa_ec_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + /* No vmstate or reset required: device has no internal state */ + dc->user_creatable = false; +} + +static const TypeInfo sbsa_ec_info = { + .name = TYPE_SBSA_EC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(SECUREECState), + .instance_init = sbsa_ec_init, + .class_init = sbsa_ec_class_init, +}; + +static void sbsa_ec_register_type(void) +{ + type_register_static(&sbsa_ec_info); +} + +type_init(sbsa_ec_register_type); diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ specific_ss.add(when: 'CONFIG_MAC_VIA', if_true: files('mac_via.c')) specific_ss.add(when: 'CONFIG_MIPS_CPS', if_true: files('mips_cmgcr.c', 'mips_cpc.c')) specific_ss.add(when: 'CONFIG_MIPS_ITU', if_true: files('mips_itu.c')) + +specific_ss.add(when: 'CONFIG_SBSA_REF', if_true: files('sbsa_ec.c')) -- 2.20.1 From: Graeme Gregory <graeme@nuviainc.com> Add the previously created sbsa-ec device to the sbsa-ref machine in secure memory so the PSCI implementation in ARM-TF can access it, but not expose it to non secure firmware or OS except by via ARM-TF. Signed-off-by: Graeme Gregory <graeme@nuviainc.com> Reviewed-by: Leif Lindholm <leif@nuviainc.com> Tested-by: Leif Lindholm <leif@nuviainc.com> Message-id: 20200826141952.136164-3-graeme@nuviainc.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ enum { SBSA_CPUPERIPHS, SBSA_GIC_DIST, SBSA_GIC_REDIST, + SBSA_SECURE_EC, SBSA_SMMU, SBSA_UART, SBSA_RTC, @@ -XXX,XX +XXX,XX @@ static const MemMapEntry sbsa_ref_memmap[] = { [SBSA_CPUPERIPHS] = { 0x40000000, 0x00040000 }, [SBSA_GIC_DIST] = { 0x40060000, 0x00010000 }, [SBSA_GIC_REDIST] = { 0x40080000, 0x04000000 }, + [SBSA_SECURE_EC] = { 0x50000000, 0x00001000 }, [SBSA_UART] = { 0x60000000, 0x00001000 }, [SBSA_RTC] = { 0x60010000, 0x00001000 }, [SBSA_GPIO] = { 0x60020000, 0x00001000 }, @@ -XXX,XX +XXX,XX @@ static void *sbsa_ref_dtb(const struct arm_boot_info *binfo, int *fdt_size) return board->fdt; } +static void create_secure_ec(MemoryRegion *mem) +{ + hwaddr base = sbsa_ref_memmap[SBSA_SECURE_EC].base; + DeviceState *dev = qdev_new("sbsa-ec"); + SysBusDevice *s = SYS_BUS_DEVICE(dev); + + memory_region_add_subregion(mem, base, + sysbus_mmio_get_region(s, 0)); +} + static void sbsa_ref_init(MachineState *machine) { unsigned int smp_cpus = machine->smp.cpus; @@ -XXX,XX +XXX,XX @@ static void sbsa_ref_init(MachineState *machine) create_pcie(sms); + create_secure_ec(secure_sysmem); + sms->bootinfo.ram_size = machine->ram_size; sms->bootinfo.nb_cpus = smp_cpus; sms->bootinfo.board_id = -1; -- 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