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 target-arm queue: I have a lot more still in my to-review queue, but my rule of thumb is when I get to 50 patches or so to send out what I have. thanks -- PMM The following changes since commit 9a7beaad3dbba982f7a461d676b55a5c3851d312: Merge remote-tracking branch 'remotes/alistair/tags/pull-riscv-to-apply-20210304' into staging (2021-03-05 10:47:46 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210305 for you to fetch changes up to 2c669ff88ec6733420a000103a2b8b9e93df4945: hw/arm/mps2: Update old infocenter.arm.com URLs (2021-03-05 15:17:38 +0000) ---------------------------------------------------------------- * sbsa-ref: remove cortex-a53 from list of supported cpus * sbsa-ref: add 'max' to list of allowed cpus * target/arm: Add support for FEAT_SSBS, Speculative Store Bypass Safe * npcm7xx: add EMC model * xlnx-zynqmp: Remove obsolete 'has_rpu' property * target/arm: Speed up aarch64 TBL/TBX * virtio-mmio: improve virtio-mmio get_dev_path alog * target/arm: Use TCF0 and TFSRE0 for unprivileged tag checks * target/arm: Restrict v8M IDAU to TCG * target/arm/cpu: Update coding style to make checkpatch.pl happy * musicpal, tc6393xb, omap_lcdc, tcx: drop dead code for non-32-bit-RGB surfaces * Add new board: mps3-an524 ---------------------------------------------------------------- Doug Evans (3): hw/net: Add npcm7xx emc model hw/arm: Add npcm7xx emc model tests/qtests: Add npcm7xx emc model test Marcin Juszkiewicz (2): sbsa-ref: remove cortex-a53 from list of supported cpus sbsa-ref: add 'max' to list of allowed cpus Peter Collingbourne (1): target/arm: Use TCF0 and TFSRE0 for unprivileged tag checks Peter Maydell (34): hw/arm/musicpal: Remove dead code for non-32-bit-RGB surfaces hw/display/tc6393xb: Remove dead code for handling non-32bpp surfaces hw/display/tc6393xb: Expand out macros in template header hw/display/tc6393xb: Inline tc6393xb_draw_graphic32() at its callsite hw/display/omap_lcdc: Expand out macros in template header hw/display/omap_lcdc: Drop broken bigendian ifdef hw/display/omap_lcdc: Fix coding style issues in template header hw/display/omap_lcdc: Inline template header into C file hw/display/omap_lcdc: Delete unnecessary macro hw/display/tcx: Drop unnecessary code for handling BGR format outputs hw/arm/mps2-tz: Make SYSCLK frequency board-specific hw/misc/mps2-scc: Support configurable number of OSCCLK values hw/arm/mps2-tz: Correct the OSCCLK settings for mps2-an505 and mps2-an511 hw/arm/mps2-tz: Make the OSCCLK settings be configurable per-board hw/misc/mps2-fpgaio: Make number of LEDs configurable by board hw/misc/mps2-fpgaio: Support SWITCH register hw/arm/mps2-tz: Make FPGAIO switch and LED config per-board hw/arm/mps2-tz: Condition IRQ splitting on number of CPUs, not board type hw/arm/mps2-tz: Make number of IRQs board-specific hw/misc/mps2-scc: Implement CFG_REG5 and CFG_REG6 for MPS3 AN524 hw/arm/mps2-tz: Correct wrong interrupt numbers for DMA and SPI hw/arm/mps2-tz: Allow PPCPortInfo structures to specify device interrupts hw/arm/mps2-tz: Move device IRQ info to data structures hw/arm/mps2-tz: Size the uart-irq-orgate based on the number of UARTs hw/arm/mps2-tz: Allow boards to have different PPCInfo data hw/arm/mps2-tz: Make RAM arrangement board-specific hw/arm/mps2-tz: Set MachineClass default_ram info from RAMInfo data hw/arm/mps2-tz: Support ROMs as well as RAMs hw/arm/mps2-tz: Get armv7m_load_kernel() size argument from RAMInfo hw/arm/mps2-tz: Add new mps3-an524 board hw/arm/mps2-tz: Stub out USB controller for mps3-an524 hw/arm/mps2-tz: Provide PL031 RTC on mps3-an524 docs/system/arm/mps2.rst: Document the new mps3-an524 board hw/arm/mps2: Update old infocenter.arm.com URLs Philippe Mathieu-Daudé (4): hw/arm/xlnx-zynqmp: Remove obsolete 'has_rpu' property hw/i2c/npcm7xx_smbus: Simplify npcm7xx_smbus_init() target/arm: Restrict v8M IDAU to TCG target/arm/cpu: Update coding style to make checkpatch.pl happy Rebecca Cran (3): target/arm: Add support for FEAT_SSBS, Speculative Store Bypass Safe target/arm: Enable FEAT_SSBS for "max" AARCH64 CPU target/arm: Set ID_PFR2.SSBS to 1 for "max" 32-bit CPU Richard Henderson (1): target/arm: Speed up aarch64 TBL/TBX schspa (1): virtio-mmio: improve virtio-mmio get_dev_path alog docs/system/arm/mps2.rst | 24 +- docs/system/arm/nuvoton.rst | 3 +- hw/display/omap_lcd_template.h | 169 -------- hw/display/tc6393xb_template.h | 72 ---- include/hw/arm/armsse.h | 4 +- include/hw/arm/npcm7xx.h | 2 + include/hw/arm/xlnx-zynqmp.h | 2 - include/hw/misc/armsse-cpuid.h | 2 +- include/hw/misc/armsse-mhu.h | 2 +- include/hw/misc/iotkit-secctl.h | 2 +- include/hw/misc/iotkit-sysctl.h | 2 +- include/hw/misc/iotkit-sysinfo.h | 2 +- include/hw/misc/mps2-fpgaio.h | 8 +- include/hw/misc/mps2-scc.h | 10 +- include/hw/net/npcm7xx_emc.h | 286 +++++++++++++ include/ui/console.h | 10 - target/arm/cpu.h | 15 +- target/arm/helper-a64.h | 2 +- target/arm/internals.h | 6 + hw/arm/mps2-tz.c | 632 +++++++++++++++++++++++----- hw/arm/mps2.c | 5 + hw/arm/musicpal.c | 64 ++- hw/arm/npcm7xx.c | 50 ++- hw/arm/sbsa-ref.c | 2 +- hw/arm/xlnx-zynqmp.c | 6 - hw/display/omap_lcdc.c | 129 +++++- hw/display/tc6393xb.c | 48 +-- hw/display/tcx.c | 31 +- hw/i2c/npcm7xx_smbus.c | 1 - hw/misc/armsse-cpuid.c | 2 +- hw/misc/armsse-mhu.c | 2 +- hw/misc/iotkit-sysctl.c | 2 +- hw/misc/iotkit-sysinfo.c | 2 +- hw/misc/mps2-fpgaio.c | 43 +- hw/misc/mps2-scc.c | 93 ++++- hw/net/npcm7xx_emc.c | 857 ++++++++++++++++++++++++++++++++++++++ hw/virtio/virtio-mmio.c | 13 +- target/arm/cpu.c | 23 +- target/arm/cpu64.c | 5 + target/arm/cpu_tcg.c | 8 + target/arm/helper-a64.c | 32 -- target/arm/helper.c | 39 +- target/arm/mte_helper.c | 13 +- target/arm/translate-a64.c | 70 +--- target/arm/vec_helper.c | 48 +++ tests/qtest/npcm7xx_emc-test.c | 862 +++++++++++++++++++++++++++++++++++++++ hw/net/meson.build | 1 + hw/net/trace-events | 17 + tests/qtest/meson.build | 3 +- 49 files changed, 3098 insertions(+), 628 deletions(-) delete mode 100644 hw/display/omap_lcd_template.h delete mode 100644 hw/display/tc6393xb_template.h create mode 100644 include/hw/net/npcm7xx_emc.h create mode 100644 hw/net/npcm7xx_emc.c create mode 100644 tests/qtest/npcm7xx_emc-test.c From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Cortex-A53 supports 40bits of address space. sbsa-ref's memory starts above this limit. Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Acked-by: Leif Lindholm <leif@nuviainc.com> Message-id: 20210216150122.3830863-2-marcin.juszkiewicz@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 1 - 1 file changed, 1 deletion(-) 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[] = { }; static const char * const valid_cpus[] = { - ARM_CPU_TYPE_NAME("cortex-a53"), ARM_CPU_TYPE_NAME("cortex-a57"), ARM_CPU_TYPE_NAME("cortex-a72"), }; -- 2.20.1 From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Let add 'max' cpu while work goes on adding newer CPU types than Cortex-A72. This allows us to check SVE etc support. Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Acked-by: Leif Lindholm <leif@nuviainc.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210216150122.3830863-3-marcin.juszkiewicz@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 1 + 1 file changed, 1 insertion(+) 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[] = { static const char * const valid_cpus[] = { ARM_CPU_TYPE_NAME("cortex-a57"), ARM_CPU_TYPE_NAME("cortex-a72"), + ARM_CPU_TYPE_NAME("max"), }; static bool cpu_type_valid(const char *cpu) -- 2.20.1 From: Rebecca Cran <rebecca@nuviainc.com> Add support for FEAT_SSBS. SSBS (Speculative Store Bypass Safe) is an optional feature in ARMv8.0, and mandatory in ARMv8.5. Signed-off-by: Rebecca Cran <rebecca@nuviainc.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210216224543.16142-2-rebecca@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 15 ++++++++++++++- target/arm/internals.h | 6 ++++++ target/arm/helper.c | 37 +++++++++++++++++++++++++++++++++++++ target/arm/translate-a64.c | 12 ++++++++++++ 4 files changed, 69 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define SCTLR_TE (1U << 30) /* AArch32 only */ #define SCTLR_EnIB (1U << 30) /* v8.3, AArch64 only */ #define SCTLR_EnIA (1U << 31) /* v8.3, AArch64 only */ +#define SCTLR_DSSBS_32 (1U << 31) /* v8.5, AArch32 only */ #define SCTLR_BT0 (1ULL << 35) /* v8.5-BTI */ #define SCTLR_BT1 (1ULL << 36) /* v8.5-BTI */ #define SCTLR_ITFSB (1ULL << 37) /* v8.5-MemTag */ @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define SCTLR_TCF (3ULL << 40) /* v8.5-MemTag */ #define SCTLR_ATA0 (1ULL << 42) /* v8.5-MemTag */ #define SCTLR_ATA (1ULL << 43) /* v8.5-MemTag */ -#define SCTLR_DSSBS (1ULL << 44) /* v8.5 */ +#define SCTLR_DSSBS_64 (1ULL << 44) /* v8.5, AArch64 only */ #define CPTR_TCPAC (1U << 31) #define CPTR_TTA (1U << 20) @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define CPSR_IL (1U << 20) #define CPSR_DIT (1U << 21) #define CPSR_PAN (1U << 22) +#define CPSR_SSBS (1U << 23) #define CPSR_J (1U << 24) #define CPSR_IT_0_1 (3U << 25) #define CPSR_Q (1U << 27) @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define PSTATE_A (1U << 8) #define PSTATE_D (1U << 9) #define PSTATE_BTYPE (3U << 10) +#define PSTATE_SSBS (1U << 12) #define PSTATE_IL (1U << 20) #define PSTATE_SS (1U << 21) #define PSTATE_PAN (1U << 22) @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_dit(const ARMISARegisters *id) return FIELD_EX32(id->id_pfr0, ID_PFR0, DIT) != 0; } +static inline bool isar_feature_aa32_ssbs(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_pfr2, ID_PFR2, SSBS) != 0; +} + /* * 64-bit feature tests via id registers. */ @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; } +static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0; +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t aarch32_cpsr_valid_mask(uint64_t features, if (isar_feature_aa32_dit(id)) { valid |= CPSR_DIT; } + if (isar_feature_aa32_ssbs(id)) { + valid |= CPSR_SSBS; + } return valid; } @@ -XXX,XX +XXX,XX @@ static inline uint32_t aarch64_pstate_valid_mask(const ARMISARegisters *id) if (isar_feature_aa64_dit(id)) { valid |= PSTATE_DIT; } + if (isar_feature_aa64_ssbs(id)) { + valid |= PSTATE_SSBS; + } if (isar_feature_aa64_mte(id)) { valid |= PSTATE_TCO; } diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo dit_reginfo = { .readfn = aa64_dit_read, .writefn = aa64_dit_write }; +static uint64_t aa64_ssbs_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + return env->pstate & PSTATE_SSBS; +} + +static void aa64_ssbs_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + env->pstate = (env->pstate & ~PSTATE_SSBS) | (value & PSTATE_SSBS); +} + +static const ARMCPRegInfo ssbs_reginfo = { + .name = "SSBS", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 4, .crm = 2, .opc2 = 6, + .type = ARM_CP_NO_RAW, .access = PL0_RW, + .readfn = aa64_ssbs_read, .writefn = aa64_ssbs_write +}; + static CPAccessResult aa64_cacheop_poc_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) if (cpu_isar_feature(aa64_dit, cpu)) { define_one_arm_cp_reg(cpu, &dit_reginfo); } + if (cpu_isar_feature(aa64_ssbs, cpu)) { + define_one_arm_cp_reg(cpu, &ssbs_reginfo); + } if (arm_feature(env, ARM_FEATURE_EL2) && cpu_isar_feature(aa64_vh, cpu)) { define_arm_cp_regs(cpu, vhe_reginfo); @@ -XXX,XX +XXX,XX @@ static void take_aarch32_exception(CPUARMState *env, int new_mode, env->uncached_cpsr &= ~(CPSR_IL | CPSR_J); env->daif |= mask; + if (cpu_isar_feature(aa32_ssbs, env_archcpu(env))) { + if (env->cp15.sctlr_el[new_el] & SCTLR_DSSBS_32) { + env->uncached_cpsr |= CPSR_SSBS; + } else { + env->uncached_cpsr &= ~CPSR_SSBS; + } + } + if (new_mode == ARM_CPU_MODE_HYP) { env->thumb = (env->cp15.sctlr_el[2] & SCTLR_TE) != 0; env->elr_el[2] = env->regs[15]; @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs) new_mode |= PSTATE_TCO; } + if (cpu_isar_feature(aa64_ssbs, cpu)) { + if (env->cp15.sctlr_el[new_el] & SCTLR_DSSBS_64) { + new_mode |= PSTATE_SSBS; + } else { + new_mode &= ~PSTATE_SSBS; + } + } + pstate_write(env, PSTATE_DAIF | new_mode); env->aarch64 = 1; aarch64_restore_sp(env, new_el); diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void handle_msr_i(DisasContext *s, uint32_t insn, tcg_temp_free_i32(t1); break; + case 0x19: /* SSBS */ + if (!dc_isar_feature(aa64_ssbs, s)) { + goto do_unallocated; + } + if (crm & 1) { + set_pstate_bits(PSTATE_SSBS); + } else { + clear_pstate_bits(PSTATE_SSBS); + } + /* Don't need to rebuild hflags since SSBS is a nop */ + break; + case 0x1a: /* DIT */ if (!dc_isar_feature(aa64_dit, s)) { goto do_unallocated; -- 2.20.1 From: Rebecca Cran <rebecca@nuviainc.com> Set ID_AA64PFR1_EL1.SSBS to 2 and ID_PFR2.SSBS to 1. Signed-off-by: Rebecca Cran <rebecca@nuviainc.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210216224543.16142-3-rebecca@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 5 +++++ 1 file changed, 5 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_max_initfn(Object *obj) t = cpu->isar.id_aa64pfr1; t = FIELD_DP64(t, ID_AA64PFR1, BT, 1); + t = FIELD_DP64(t, ID_AA64PFR1, SSBS, 2); /* * Begin with full support for MTE. This will be downgraded to MTE=0 * during realize if the board provides no tag memory, much like @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) u = FIELD_DP32(u, ID_PFR0, DIT, 1); cpu->isar.id_pfr0 = u; + u = cpu->isar.id_pfr2; + u = FIELD_DP32(u, ID_PFR2, SSBS, 1); + cpu->isar.id_pfr2 = u; + u = cpu->isar.id_mmfr3; u = FIELD_DP32(u, ID_MMFR3, PAN, 2); /* ATS1E1 */ cpu->isar.id_mmfr3 = u; -- 2.20.1 From: Rebecca Cran <rebecca@nuviainc.com> Enable FEAT_SSBS for the "max" 32-bit CPU. Signed-off-by: Rebecca Cran <rebecca@nuviainc.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210216224543.16142-4-rebecca@nuviainc.com [PMM: fix typo causing compilation failure] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) t = cpu->isar.id_pfr0; t = FIELD_DP32(t, ID_PFR0, DIT, 1); cpu->isar.id_pfr0 = t; + + t = cpu->isar.id_pfr2; + t = FIELD_DP32(t, ID_PFR2, SSBS, 1); + cpu->isar.id_pfr2 = t; } #endif } -- 2.20.1 From: Doug Evans <dje@google.com> This is a 10/100 ethernet device that has several features. Only the ones needed by the Linux driver have been implemented. See npcm7xx_emc.c for a list of unimplemented features. Reviewed-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Avi Fishman <avi.fishman@nuvoton.com> Signed-off-by: Doug Evans <dje@google.com> Message-id: 20210218212453.831406-2-dje@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/net/npcm7xx_emc.h | 286 ++++++++++++ hw/net/npcm7xx_emc.c | 857 +++++++++++++++++++++++++++++++++++ hw/net/meson.build | 1 + hw/net/trace-events | 17 + 4 files changed, 1161 insertions(+) create mode 100644 include/hw/net/npcm7xx_emc.h create mode 100644 hw/net/npcm7xx_emc.c diff --git a/include/hw/net/npcm7xx_emc.h b/include/hw/net/npcm7xx_emc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/net/npcm7xx_emc.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx EMC Module + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#ifndef NPCM7XX_EMC_H +#define NPCM7XX_EMC_H + +#include "hw/irq.h" +#include "hw/sysbus.h" +#include "net/net.h" + +/* 32-bit register indices. */ +enum NPCM7xxPWMRegister { + /* Control registers. */ + REG_CAMCMR, + REG_CAMEN, + + /* There are 16 CAMn[ML] registers. */ + REG_CAMM_BASE, + REG_CAML_BASE, + REG_CAMML_LAST = 0x21, + + REG_TXDLSA = 0x22, + REG_RXDLSA, + REG_MCMDR, + REG_MIID, + REG_MIIDA, + REG_FFTCR, + REG_TSDR, + REG_RSDR, + REG_DMARFC, + REG_MIEN, + + /* Status registers. */ + REG_MISTA, + REG_MGSTA, + REG_MPCNT, + REG_MRPC, + REG_MRPCC, + REG_MREPC, + REG_DMARFS, + REG_CTXDSA, + REG_CTXBSA, + REG_CRXDSA, + REG_CRXBSA, + + NPCM7XX_NUM_EMC_REGS, +}; + +/* REG_CAMCMR fields */ +/* Enable CAM Compare */ +#define REG_CAMCMR_ECMP (1 << 4) +/* Complement CAM Compare */ +#define REG_CAMCMR_CCAM (1 << 3) +/* Accept Broadcast Packet */ +#define REG_CAMCMR_ABP (1 << 2) +/* Accept Multicast Packet */ +#define REG_CAMCMR_AMP (1 << 1) +/* Accept Unicast Packet */ +#define REG_CAMCMR_AUP (1 << 0) + +/* REG_MCMDR fields */ +/* Software Reset */ +#define REG_MCMDR_SWR (1 << 24) +/* Internal Loopback Select */ +#define REG_MCMDR_LBK (1 << 21) +/* Operation Mode Select */ +#define REG_MCMDR_OPMOD (1 << 20) +/* Enable MDC Clock Generation */ +#define REG_MCMDR_ENMDC (1 << 19) +/* Full-Duplex Mode Select */ +#define REG_MCMDR_FDUP (1 << 18) +/* Enable SQE Checking */ +#define REG_MCMDR_ENSEQ (1 << 17) +/* Send PAUSE Frame */ +#define REG_MCMDR_SDPZ (1 << 16) +/* No Defer */ +#define REG_MCMDR_NDEF (1 << 9) +/* Frame Transmission On */ +#define REG_MCMDR_TXON (1 << 8) +/* Strip CRC Checksum */ +#define REG_MCMDR_SPCRC (1 << 5) +/* Accept CRC Error Packet */ +#define REG_MCMDR_AEP (1 << 4) +/* Accept Control Packet */ +#define REG_MCMDR_ACP (1 << 3) +/* Accept Runt Packet */ +#define REG_MCMDR_ARP (1 << 2) +/* Accept Long Packet */ +#define REG_MCMDR_ALP (1 << 1) +/* Frame Reception On */ +#define REG_MCMDR_RXON (1 << 0) + +/* REG_MIEN fields */ +/* Enable Transmit Descriptor Unavailable Interrupt */ +#define REG_MIEN_ENTDU (1 << 23) +/* Enable Transmit Completion Interrupt */ +#define REG_MIEN_ENTXCP (1 << 18) +/* Enable Transmit Interrupt */ +#define REG_MIEN_ENTXINTR (1 << 16) +/* Enable Receive Descriptor Unavailable Interrupt */ +#define REG_MIEN_ENRDU (1 << 10) +/* Enable Receive Good Interrupt */ +#define REG_MIEN_ENRXGD (1 << 4) +/* Enable Receive Interrupt */ +#define REG_MIEN_ENRXINTR (1 << 0) + +/* REG_MISTA fields */ +/* TODO: Add error fields and support simulated errors? */ +/* Transmit Bus Error Interrupt */ +#define REG_MISTA_TXBERR (1 << 24) +/* Transmit Descriptor Unavailable Interrupt */ +#define REG_MISTA_TDU (1 << 23) +/* Transmit Completion Interrupt */ +#define REG_MISTA_TXCP (1 << 18) +/* Transmit Interrupt */ +#define REG_MISTA_TXINTR (1 << 16) +/* Receive Bus Error Interrupt */ +#define REG_MISTA_RXBERR (1 << 11) +/* Receive Descriptor Unavailable Interrupt */ +#define REG_MISTA_RDU (1 << 10) +/* DMA Early Notification Interrupt */ +#define REG_MISTA_DENI (1 << 9) +/* Maximum Frame Length Interrupt */ +#define REG_MISTA_DFOI (1 << 8) +/* Receive Good Interrupt */ +#define REG_MISTA_RXGD (1 << 4) +/* Packet Too Long Interrupt */ +#define REG_MISTA_PTLE (1 << 3) +/* Receive Interrupt */ +#define REG_MISTA_RXINTR (1 << 0) + +/* REG_MGSTA fields */ +/* Transmission Halted */ +#define REG_MGSTA_TXHA (1 << 11) +/* Receive Halted */ +#define REG_MGSTA_RXHA (1 << 11) + +/* REG_DMARFC fields */ +/* Maximum Receive Frame Length */ +#define REG_DMARFC_RXMS(word) extract32((word), 0, 16) + +/* REG MIIDA fields */ +/* Busy Bit */ +#define REG_MIIDA_BUSY (1 << 17) + +/* Transmit and receive descriptors */ +typedef struct NPCM7xxEMCTxDesc NPCM7xxEMCTxDesc; +typedef struct NPCM7xxEMCRxDesc NPCM7xxEMCRxDesc; + +struct NPCM7xxEMCTxDesc { + uint32_t flags; + uint32_t txbsa; + uint32_t status_and_length; + uint32_t ntxdsa; +}; + +struct NPCM7xxEMCRxDesc { + uint32_t status_and_length; + uint32_t rxbsa; + uint32_t reserved; + uint32_t nrxdsa; +}; + +/* NPCM7xxEMCTxDesc.flags values */ +/* Owner: 0 = cpu, 1 = emc */ +#define TX_DESC_FLAG_OWNER_MASK (1 << 31) +/* Transmit interrupt enable */ +#define TX_DESC_FLAG_INTEN (1 << 2) +/* CRC append */ +#define TX_DESC_FLAG_CRCAPP (1 << 1) +/* Padding enable */ +#define TX_DESC_FLAG_PADEN (1 << 0) + +/* NPCM7xxEMCTxDesc.status_and_length values */ +/* Collision count */ +#define TX_DESC_STATUS_CCNT_SHIFT 28 +#define TX_DESC_STATUS_CCNT_BITSIZE 4 +/* SQE error */ +#define TX_DESC_STATUS_SQE (1 << 26) +/* Transmission paused */ +#define TX_DESC_STATUS_PAU (1 << 25) +/* P transmission halted */ +#define TX_DESC_STATUS_TXHA (1 << 24) +/* Late collision */ +#define TX_DESC_STATUS_LC (1 << 23) +/* Transmission abort */ +#define TX_DESC_STATUS_TXABT (1 << 22) +/* No carrier sense */ +#define TX_DESC_STATUS_NCS (1 << 21) +/* Defer exceed */ +#define TX_DESC_STATUS_EXDEF (1 << 20) +/* Transmission complete */ +#define TX_DESC_STATUS_TXCP (1 << 19) +/* Transmission deferred */ +#define TX_DESC_STATUS_DEF (1 << 17) +/* Transmit interrupt */ +#define TX_DESC_STATUS_TXINTR (1 << 16) + +#define TX_DESC_PKT_LEN(word) extract32((word), 0, 16) + +/* Transmit buffer start address */ +#define TX_DESC_TXBSA(word) ((uint32_t) (word) & ~3u) + +/* Next transmit descriptor start address */ +#define TX_DESC_NTXDSA(word) ((uint32_t) (word) & ~3u) + +/* NPCM7xxEMCRxDesc.status_and_length values */ +/* Owner: 0b00 = cpu, 0b01 = undefined, 0b10 = emc, 0b11 = undefined */ +#define RX_DESC_STATUS_OWNER_SHIFT 30 +#define RX_DESC_STATUS_OWNER_BITSIZE 2 +#define RX_DESC_STATUS_OWNER_MASK (3 << RX_DESC_STATUS_OWNER_SHIFT) +/* Runt packet */ +#define RX_DESC_STATUS_RP (1 << 22) +/* Alignment error */ +#define RX_DESC_STATUS_ALIE (1 << 21) +/* Frame reception complete */ +#define RX_DESC_STATUS_RXGD (1 << 20) +/* Packet too long */ +#define RX_DESC_STATUS_PTLE (1 << 19) +/* CRC error */ +#define RX_DESC_STATUS_CRCE (1 << 17) +/* Receive interrupt */ +#define RX_DESC_STATUS_RXINTR (1 << 16) + +#define RX_DESC_PKT_LEN(word) extract32((word), 0, 16) + +/* Receive buffer start address */ +#define RX_DESC_RXBSA(word) ((uint32_t) (word) & ~3u) + +/* Next receive descriptor start address */ +#define RX_DESC_NRXDSA(word) ((uint32_t) (word) & ~3u) + +/* Minimum packet length, when TX_DESC_FLAG_PADEN is set. */ +#define MIN_PACKET_LENGTH 64 + +struct NPCM7xxEMCState { + /*< private >*/ + SysBusDevice parent; + /*< public >*/ + + MemoryRegion iomem; + + qemu_irq tx_irq; + qemu_irq rx_irq; + + NICState *nic; + NICConf conf; + + /* 0 or 1, for log messages */ + uint8_t emc_num; + + uint32_t regs[NPCM7XX_NUM_EMC_REGS]; + + /* + * tx is active. Set to true by TSDR and then switches off when out of + * descriptors. If the TXON bit in REG_MCMDR is off then this is off. + */ + bool tx_active; + + /* + * rx is active. Set to true by RSDR and then switches off when out of + * descriptors. If the RXON bit in REG_MCMDR is off then this is off. + */ + bool rx_active; +}; + +typedef struct NPCM7xxEMCState NPCM7xxEMCState; + +#define TYPE_NPCM7XX_EMC "npcm7xx-emc" +#define NPCM7XX_EMC(obj) \ + OBJECT_CHECK(NPCM7xxEMCState, (obj), TYPE_NPCM7XX_EMC) + +#endif /* NPCM7XX_EMC_H */ diff --git a/hw/net/npcm7xx_emc.c b/hw/net/npcm7xx_emc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/npcm7xx_emc.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx EMC Module + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + * Unsupported/unimplemented features: + * - MCMDR.FDUP (full duplex) is ignored, half duplex is not supported + * - Only CAM0 is supported, CAM[1-15] are not + * - writes to CAMEN.[1-15] are ignored, these bits always read as zeroes + * - MII is not implemented, MIIDA.BUSY and MIID always return zero + * - MCMDR.LBK is not implemented + * - MCMDR.{OPMOD,ENSQE,AEP,ARP} are not supported + * - H/W FIFOs are not supported, MCMDR.FFTCR is ignored + * - MGSTA.SQE is not supported + * - pause and control frames are not implemented + * - MGSTA.CCNT is not supported + * - MPCNT, DMARFS are not implemented + */ + +#include "qemu/osdep.h" + +/* For crc32 */ +#include <zlib.h> + +#include "qemu-common.h" +#include "hw/irq.h" +#include "hw/qdev-clock.h" +#include "hw/qdev-properties.h" +#include "hw/net/npcm7xx_emc.h" +#include "net/eth.h" +#include "migration/vmstate.h" +#include "qemu/bitops.h" +#include "qemu/error-report.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/units.h" +#include "sysemu/dma.h" +#include "trace.h" + +#define CRC_LENGTH 4 + +/* + * The maximum size of a (layer 2) ethernet frame as defined by 802.3. + * 1518 = 6(dest macaddr) + 6(src macaddr) + 2(proto) + 4(crc) + 1500(payload) + * This does not include an additional 4 for the vlan field (802.1q). + */ +#define MAX_ETH_FRAME_SIZE 1518 + +static const char *emc_reg_name(int regno) +{ +#define REG(name) case REG_ ## name: return #name; + switch (regno) { + REG(CAMCMR) + REG(CAMEN) + REG(TXDLSA) + REG(RXDLSA) + REG(MCMDR) + REG(MIID) + REG(MIIDA) + REG(FFTCR) + REG(TSDR) + REG(RSDR) + REG(DMARFC) + REG(MIEN) + REG(MISTA) + REG(MGSTA) + REG(MPCNT) + REG(MRPC) + REG(MRPCC) + REG(MREPC) + REG(DMARFS) + REG(CTXDSA) + REG(CTXBSA) + REG(CRXDSA) + REG(CRXBSA) + case REG_CAMM_BASE + 0: return "CAM0M"; + case REG_CAML_BASE + 0: return "CAM0L"; + case REG_CAMM_BASE + 2 ... REG_CAMML_LAST: + /* Only CAM0 is supported, fold the others into something simple. */ + if (regno & 1) { + return "CAM<n>L"; + } else { + return "CAM<n>M"; + } + default: return "UNKNOWN"; + } +#undef REG +} + +static void emc_reset(NPCM7xxEMCState *emc) +{ + trace_npcm7xx_emc_reset(emc->emc_num); + + memset(&emc->regs[0], 0, sizeof(emc->regs)); + + /* These regs have non-zero reset values. */ + emc->regs[REG_TXDLSA] = 0xfffffffc; + emc->regs[REG_RXDLSA] = 0xfffffffc; + emc->regs[REG_MIIDA] = 0x00900000; + emc->regs[REG_FFTCR] = 0x0101; + emc->regs[REG_DMARFC] = 0x0800; + emc->regs[REG_MPCNT] = 0x7fff; + + emc->tx_active = false; + emc->rx_active = false; +} + +static void npcm7xx_emc_reset(DeviceState *dev) +{ + NPCM7xxEMCState *emc = NPCM7XX_EMC(dev); + emc_reset(emc); +} + +static void emc_soft_reset(NPCM7xxEMCState *emc) +{ + /* + * The docs say at least MCMDR.{LBK,OPMOD} bits are not changed during a + * soft reset, but does not go into further detail. For now, KISS. + */ + uint32_t mcmdr = emc->regs[REG_MCMDR]; + emc_reset(emc); + emc->regs[REG_MCMDR] = mcmdr & (REG_MCMDR_LBK | REG_MCMDR_OPMOD); + + qemu_set_irq(emc->tx_irq, 0); + qemu_set_irq(emc->rx_irq, 0); +} + +static void emc_set_link(NetClientState *nc) +{ + /* Nothing to do yet. */ +} + +/* MISTA.TXINTR is the union of the individual bits with their enables. */ +static void emc_update_mista_txintr(NPCM7xxEMCState *emc) +{ + /* Only look at the bits we support. */ + uint32_t mask = (REG_MISTA_TXBERR | + REG_MISTA_TDU | + REG_MISTA_TXCP); + if (emc->regs[REG_MISTA] & emc->regs[REG_MIEN] & mask) { + emc->regs[REG_MISTA] |= REG_MISTA_TXINTR; + } else { + emc->regs[REG_MISTA] &= ~REG_MISTA_TXINTR; + } +} + +/* MISTA.RXINTR is the union of the individual bits with their enables. */ +static void emc_update_mista_rxintr(NPCM7xxEMCState *emc) +{ + /* Only look at the bits we support. */ + uint32_t mask = (REG_MISTA_RXBERR | + REG_MISTA_RDU | + REG_MISTA_RXGD); + if (emc->regs[REG_MISTA] & emc->regs[REG_MIEN] & mask) { + emc->regs[REG_MISTA] |= REG_MISTA_RXINTR; + } else { + emc->regs[REG_MISTA] &= ~REG_MISTA_RXINTR; + } +} + +/* N.B. emc_update_mista_txintr must have already been called. */ +static void emc_update_tx_irq(NPCM7xxEMCState *emc) +{ + int level = !!(emc->regs[REG_MISTA] & + emc->regs[REG_MIEN] & + REG_MISTA_TXINTR); + trace_npcm7xx_emc_update_tx_irq(level); + qemu_set_irq(emc->tx_irq, level); +} + +/* N.B. emc_update_mista_rxintr must have already been called. */ +static void emc_update_rx_irq(NPCM7xxEMCState *emc) +{ + int level = !!(emc->regs[REG_MISTA] & + emc->regs[REG_MIEN] & + REG_MISTA_RXINTR); + trace_npcm7xx_emc_update_rx_irq(level); + qemu_set_irq(emc->rx_irq, level); +} + +/* Update IRQ states due to changes in MIEN,MISTA. */ +static void emc_update_irq_from_reg_change(NPCM7xxEMCState *emc) +{ + emc_update_mista_txintr(emc); + emc_update_tx_irq(emc); + + emc_update_mista_rxintr(emc); + emc_update_rx_irq(emc); +} + +static int emc_read_tx_desc(dma_addr_t addr, NPCM7xxEMCTxDesc *desc) +{ + if (dma_memory_read(&address_space_memory, addr, desc, sizeof(*desc))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Failed to read descriptor @ 0x%" + HWADDR_PRIx "\n", __func__, addr); + return -1; + } + desc->flags = le32_to_cpu(desc->flags); + desc->txbsa = le32_to_cpu(desc->txbsa); + desc->status_and_length = le32_to_cpu(desc->status_and_length); + desc->ntxdsa = le32_to_cpu(desc->ntxdsa); + return 0; +} + +static int emc_write_tx_desc(const NPCM7xxEMCTxDesc *desc, dma_addr_t addr) +{ + NPCM7xxEMCTxDesc le_desc; + + le_desc.flags = cpu_to_le32(desc->flags); + le_desc.txbsa = cpu_to_le32(desc->txbsa); + le_desc.status_and_length = cpu_to_le32(desc->status_and_length); + le_desc.ntxdsa = cpu_to_le32(desc->ntxdsa); + if (dma_memory_write(&address_space_memory, addr, &le_desc, + sizeof(le_desc))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Failed to write descriptor @ 0x%" + HWADDR_PRIx "\n", __func__, addr); + return -1; + } + return 0; +} + +static int emc_read_rx_desc(dma_addr_t addr, NPCM7xxEMCRxDesc *desc) +{ + if (dma_memory_read(&address_space_memory, addr, desc, sizeof(*desc))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Failed to read descriptor @ 0x%" + HWADDR_PRIx "\n", __func__, addr); + return -1; + } + desc->status_and_length = le32_to_cpu(desc->status_and_length); + desc->rxbsa = le32_to_cpu(desc->rxbsa); + desc->reserved = le32_to_cpu(desc->reserved); + desc->nrxdsa = le32_to_cpu(desc->nrxdsa); + return 0; +} + +static int emc_write_rx_desc(const NPCM7xxEMCRxDesc *desc, dma_addr_t addr) +{ + NPCM7xxEMCRxDesc le_desc; + + le_desc.status_and_length = cpu_to_le32(desc->status_and_length); + le_desc.rxbsa = cpu_to_le32(desc->rxbsa); + le_desc.reserved = cpu_to_le32(desc->reserved); + le_desc.nrxdsa = cpu_to_le32(desc->nrxdsa); + if (dma_memory_write(&address_space_memory, addr, &le_desc, + sizeof(le_desc))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Failed to write descriptor @ 0x%" + HWADDR_PRIx "\n", __func__, addr); + return -1; + } + return 0; +} + +static void emc_set_mista(NPCM7xxEMCState *emc, uint32_t flags) +{ + trace_npcm7xx_emc_set_mista(flags); + emc->regs[REG_MISTA] |= flags; + if (extract32(flags, 16, 16)) { + emc_update_mista_txintr(emc); + } + if (extract32(flags, 0, 16)) { + emc_update_mista_rxintr(emc); + } +} + +static void emc_halt_tx(NPCM7xxEMCState *emc, uint32_t mista_flag) +{ + emc->tx_active = false; + emc_set_mista(emc, mista_flag); +} + +static void emc_halt_rx(NPCM7xxEMCState *emc, uint32_t mista_flag) +{ + emc->rx_active = false; + emc_set_mista(emc, mista_flag); +} + +static void emc_set_next_tx_descriptor(NPCM7xxEMCState *emc, + const NPCM7xxEMCTxDesc *tx_desc, + uint32_t desc_addr) +{ + /* Update the current descriptor, if only to reset the owner flag. */ + if (emc_write_tx_desc(tx_desc, desc_addr)) { + /* + * We just read it so this shouldn't generally happen. + * Error already reported. + */ + emc_set_mista(emc, REG_MISTA_TXBERR); + } + emc->regs[REG_CTXDSA] = TX_DESC_NTXDSA(tx_desc->ntxdsa); +} + +static void emc_set_next_rx_descriptor(NPCM7xxEMCState *emc, + const NPCM7xxEMCRxDesc *rx_desc, + uint32_t desc_addr) +{ + /* Update the current descriptor, if only to reset the owner flag. */ + if (emc_write_rx_desc(rx_desc, desc_addr)) { + /* + * We just read it so this shouldn't generally happen. + * Error already reported. + */ + emc_set_mista(emc, REG_MISTA_RXBERR); + } + emc->regs[REG_CRXDSA] = RX_DESC_NRXDSA(rx_desc->nrxdsa); +} + +static void emc_try_send_next_packet(NPCM7xxEMCState *emc) +{ + /* Working buffer for sending out packets. Most packets fit in this. */ +#define TX_BUFFER_SIZE 2048 + uint8_t tx_send_buffer[TX_BUFFER_SIZE]; + uint32_t desc_addr = TX_DESC_NTXDSA(emc->regs[REG_CTXDSA]); + NPCM7xxEMCTxDesc tx_desc; + uint32_t next_buf_addr, length; + uint8_t *buf; + g_autofree uint8_t *malloced_buf = NULL; + + if (emc_read_tx_desc(desc_addr, &tx_desc)) { + /* Error reading descriptor, already reported. */ + emc_halt_tx(emc, REG_MISTA_TXBERR); + emc_update_tx_irq(emc); + return; + } + + /* Nothing we can do if we don't own the descriptor. */ + if (!(tx_desc.flags & TX_DESC_FLAG_OWNER_MASK)) { + trace_npcm7xx_emc_cpu_owned_desc(desc_addr); + emc_halt_tx(emc, REG_MISTA_TDU); + emc_update_tx_irq(emc); + return; + } + + /* Give the descriptor back regardless of what happens. */ + tx_desc.flags &= ~TX_DESC_FLAG_OWNER_MASK; + tx_desc.status_and_length &= 0xffff; + + /* + * Despite the h/w documentation saying the tx buffer is word aligned, + * the linux driver does not word align the buffer. There is value in not + * aligning the buffer: See the description of NET_IP_ALIGN in linux + * kernel sources. + */ + next_buf_addr = tx_desc.txbsa; + emc->regs[REG_CTXBSA] = next_buf_addr; + length = TX_DESC_PKT_LEN(tx_desc.status_and_length); + buf = &tx_send_buffer[0]; + + if (length > sizeof(tx_send_buffer)) { + malloced_buf = g_malloc(length); + buf = malloced_buf; + } + + if (dma_memory_read(&address_space_memory, next_buf_addr, buf, length)) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Failed to read packet @ 0x%x\n", + __func__, next_buf_addr); + emc_set_mista(emc, REG_MISTA_TXBERR); + emc_set_next_tx_descriptor(emc, &tx_desc, desc_addr); + emc_update_tx_irq(emc); + trace_npcm7xx_emc_tx_done(emc->regs[REG_CTXDSA]); + return; + } + + if ((tx_desc.flags & TX_DESC_FLAG_PADEN) && (length < MIN_PACKET_LENGTH)) { + memset(buf + length, 0, MIN_PACKET_LENGTH - length); + length = MIN_PACKET_LENGTH; + } + + /* N.B. emc_receive can get called here. */ + qemu_send_packet(qemu_get_queue(emc->nic), buf, length); + trace_npcm7xx_emc_sent_packet(length); + + tx_desc.status_and_length |= TX_DESC_STATUS_TXCP; + if (tx_desc.flags & TX_DESC_FLAG_INTEN) { + emc_set_mista(emc, REG_MISTA_TXCP); + } + if (emc->regs[REG_MISTA] & emc->regs[REG_MIEN] & REG_MISTA_TXINTR) { + tx_desc.status_and_length |= TX_DESC_STATUS_TXINTR; + } + + emc_set_next_tx_descriptor(emc, &tx_desc, desc_addr); + emc_update_tx_irq(emc); + trace_npcm7xx_emc_tx_done(emc->regs[REG_CTXDSA]); +} + +static bool emc_can_receive(NetClientState *nc) +{ + NPCM7xxEMCState *emc = NPCM7XX_EMC(qemu_get_nic_opaque(nc)); + + bool can_receive = emc->rx_active; + trace_npcm7xx_emc_can_receive(can_receive); + return can_receive; +} + +/* If result is false then *fail_reason contains the reason. */ +static bool emc_receive_filter1(NPCM7xxEMCState *emc, const uint8_t *buf, + size_t len, const char **fail_reason) +{ + eth_pkt_types_e pkt_type = get_eth_packet_type(PKT_GET_ETH_HDR(buf)); + + switch (pkt_type) { + case ETH_PKT_BCAST: + if (emc->regs[REG_CAMCMR] & REG_CAMCMR_CCAM) { + return true; + } else { + *fail_reason = "Broadcast packet disabled"; + return !!(emc->regs[REG_CAMCMR] & REG_CAMCMR_ABP); + } + case ETH_PKT_MCAST: + if (emc->regs[REG_CAMCMR] & REG_CAMCMR_CCAM) { + return true; + } else { + *fail_reason = "Multicast packet disabled"; + return !!(emc->regs[REG_CAMCMR] & REG_CAMCMR_AMP); + } + case ETH_PKT_UCAST: { + bool matches; + if (emc->regs[REG_CAMCMR] & REG_CAMCMR_AUP) { + return true; + } + matches = ((emc->regs[REG_CAMCMR] & REG_CAMCMR_ECMP) && + /* We only support one CAM register, CAM0. */ + (emc->regs[REG_CAMEN] & (1 << 0)) && + memcmp(buf, emc->conf.macaddr.a, ETH_ALEN) == 0); + if (emc->regs[REG_CAMCMR] & REG_CAMCMR_CCAM) { + *fail_reason = "MACADDR matched, comparison complemented"; + return !matches; + } else { + *fail_reason = "MACADDR didn't match"; + return matches; + } + } + default: + g_assert_not_reached(); + } +} + +static bool emc_receive_filter(NPCM7xxEMCState *emc, const uint8_t *buf, + size_t len) +{ + const char *fail_reason = NULL; + bool ok = emc_receive_filter1(emc, buf, len, &fail_reason); + if (!ok) { + trace_npcm7xx_emc_packet_filtered_out(fail_reason); + } + return ok; +} + +static ssize_t emc_receive(NetClientState *nc, const uint8_t *buf, size_t len1) +{ + NPCM7xxEMCState *emc = NPCM7XX_EMC(qemu_get_nic_opaque(nc)); + const uint32_t len = len1; + size_t max_frame_len; + bool long_frame; + uint32_t desc_addr; + NPCM7xxEMCRxDesc rx_desc; + uint32_t crc; + uint8_t *crc_ptr; + uint32_t buf_addr; + + trace_npcm7xx_emc_receiving_packet(len); + + if (!emc_can_receive(nc)) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Unexpected packet\n", __func__); + return -1; + } + + if (len < ETH_HLEN || + /* Defensive programming: drop unsupportable large packets. */ + len > 0xffff - CRC_LENGTH) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Dropped frame of %u bytes\n", + __func__, len); + return len; + } + + /* + * DENI is set if EMC received the Length/Type field of the incoming + * packet, so it will be set regardless of what happens next. + */ + emc_set_mista(emc, REG_MISTA_DENI); + + if (!emc_receive_filter(emc, buf, len)) { + emc_update_rx_irq(emc); + return len; + } + + /* Huge frames (> DMARFC) are dropped. */ + max_frame_len = REG_DMARFC_RXMS(emc->regs[REG_DMARFC]); + if (len + CRC_LENGTH > max_frame_len) { + trace_npcm7xx_emc_packet_dropped(len); + emc_set_mista(emc, REG_MISTA_DFOI); + emc_update_rx_irq(emc); + return len; + } + + /* + * Long Frames (> MAX_ETH_FRAME_SIZE) are also dropped, unless MCMDR.ALP + * is set. + */ + long_frame = false; + if (len + CRC_LENGTH > MAX_ETH_FRAME_SIZE) { + if (emc->regs[REG_MCMDR] & REG_MCMDR_ALP) { + long_frame = true; + } else { + trace_npcm7xx_emc_packet_dropped(len); + emc_set_mista(emc, REG_MISTA_PTLE); + emc_update_rx_irq(emc); + return len; + } + } + + desc_addr = RX_DESC_NRXDSA(emc->regs[REG_CRXDSA]); + if (emc_read_rx_desc(desc_addr, &rx_desc)) { + /* Error reading descriptor, already reported. */ + emc_halt_rx(emc, REG_MISTA_RXBERR); + emc_update_rx_irq(emc); + return len; + } + + /* Nothing we can do if we don't own the descriptor. */ + if (!(rx_desc.status_and_length & RX_DESC_STATUS_OWNER_MASK)) { + trace_npcm7xx_emc_cpu_owned_desc(desc_addr); + emc_halt_rx(emc, REG_MISTA_RDU); + emc_update_rx_irq(emc); + return len; + } + + crc = 0; + crc_ptr = (uint8_t *) &crc; + if (!(emc->regs[REG_MCMDR] & REG_MCMDR_SPCRC)) { + crc = cpu_to_be32(crc32(~0, buf, len)); + } + + /* Give the descriptor back regardless of what happens. */ + rx_desc.status_and_length &= ~RX_DESC_STATUS_OWNER_MASK; + + buf_addr = rx_desc.rxbsa; + emc->regs[REG_CRXBSA] = buf_addr; + if (dma_memory_write(&address_space_memory, buf_addr, buf, len) || + (!(emc->regs[REG_MCMDR] & REG_MCMDR_SPCRC) && + dma_memory_write(&address_space_memory, buf_addr + len, crc_ptr, + 4))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Bus error writing packet\n", + __func__); + emc_set_mista(emc, REG_MISTA_RXBERR); + emc_set_next_rx_descriptor(emc, &rx_desc, desc_addr); + emc_update_rx_irq(emc); + trace_npcm7xx_emc_rx_done(emc->regs[REG_CRXDSA]); + return len; + } + + trace_npcm7xx_emc_received_packet(len); + + /* Note: We've already verified len+4 <= 0xffff. */ + rx_desc.status_and_length = len; + if (!(emc->regs[REG_MCMDR] & REG_MCMDR_SPCRC)) { + rx_desc.status_and_length += 4; + } + rx_desc.status_and_length |= RX_DESC_STATUS_RXGD; + emc_set_mista(emc, REG_MISTA_RXGD); + + if (emc->regs[REG_MISTA] & emc->regs[REG_MIEN] & REG_MISTA_RXINTR) { + rx_desc.status_and_length |= RX_DESC_STATUS_RXINTR; + } + if (long_frame) { + rx_desc.status_and_length |= RX_DESC_STATUS_PTLE; + } + + emc_set_next_rx_descriptor(emc, &rx_desc, desc_addr); + emc_update_rx_irq(emc); + trace_npcm7xx_emc_rx_done(emc->regs[REG_CRXDSA]); + return len; +} + +static void emc_try_receive_next_packet(NPCM7xxEMCState *emc) +{ + if (emc_can_receive(qemu_get_queue(emc->nic))) { + qemu_flush_queued_packets(qemu_get_queue(emc->nic)); + } +} + +static uint64_t npcm7xx_emc_read(void *opaque, hwaddr offset, unsigned size) +{ + NPCM7xxEMCState *emc = opaque; + uint32_t reg = offset / sizeof(uint32_t); + uint32_t result; + + if (reg >= NPCM7XX_NUM_EMC_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Invalid offset 0x%04" HWADDR_PRIx "\n", + __func__, offset); + return 0; + } + + switch (reg) { + case REG_MIID: + /* + * We don't implement MII. For determinism, always return zero as + * writes record the last value written for debugging purposes. + */ + qemu_log_mask(LOG_UNIMP, "%s: Read of MIID, returning 0\n", __func__); + result = 0; + break; + case REG_TSDR: + case REG_RSDR: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Read of write-only reg, %s/%d\n", + __func__, emc_reg_name(reg), reg); + return 0; + default: + result = emc->regs[reg]; + break; + } + + trace_npcm7xx_emc_reg_read(emc->emc_num, result, emc_reg_name(reg), reg); + return result; +} + +static void npcm7xx_emc_write(void *opaque, hwaddr offset, + uint64_t v, unsigned size) +{ + NPCM7xxEMCState *emc = opaque; + uint32_t reg = offset / sizeof(uint32_t); + uint32_t value = v; + + g_assert(size == sizeof(uint32_t)); + + if (reg >= NPCM7XX_NUM_EMC_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Invalid offset 0x%04" HWADDR_PRIx "\n", + __func__, offset); + return; + } + + trace_npcm7xx_emc_reg_write(emc->emc_num, emc_reg_name(reg), reg, value); + + switch (reg) { + case REG_CAMCMR: + emc->regs[reg] = value; + break; + case REG_CAMEN: + /* Only CAM0 is supported, don't pretend otherwise. */ + if (value & ~1) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Only CAM0 is supported, cannot enable others" + ": 0x%x\n", + __func__, value); + } + emc->regs[reg] = value & 1; + break; + case REG_CAMM_BASE + 0: + emc->regs[reg] = value; + emc->conf.macaddr.a[0] = value >> 24; + emc->conf.macaddr.a[1] = value >> 16; + emc->conf.macaddr.a[2] = value >> 8; + emc->conf.macaddr.a[3] = value >> 0; + break; + case REG_CAML_BASE + 0: + emc->regs[reg] = value; + emc->conf.macaddr.a[4] = value >> 24; + emc->conf.macaddr.a[5] = value >> 16; + break; + case REG_MCMDR: { + uint32_t prev; + if (value & REG_MCMDR_SWR) { + emc_soft_reset(emc); + /* On h/w the reset happens over multiple cycles. For now KISS. */ + break; + } + prev = emc->regs[reg]; + emc->regs[reg] = value; + /* Update tx state. */ + if (!(prev & REG_MCMDR_TXON) && + (value & REG_MCMDR_TXON)) { + emc->regs[REG_CTXDSA] = emc->regs[REG_TXDLSA]; + /* + * Linux kernel turns TX on with CPU still holding descriptor, + * which suggests we should wait for a write to TSDR before trying + * to send a packet: so we don't send one here. + */ + } else if ((prev & REG_MCMDR_TXON) && + !(value & REG_MCMDR_TXON)) { + emc->regs[REG_MGSTA] |= REG_MGSTA_TXHA; + } + if (!(value & REG_MCMDR_TXON)) { + emc_halt_tx(emc, 0); + } + /* Update rx state. */ + if (!(prev & REG_MCMDR_RXON) && + (value & REG_MCMDR_RXON)) { + emc->regs[REG_CRXDSA] = emc->regs[REG_RXDLSA]; + } else if ((prev & REG_MCMDR_RXON) && + !(value & REG_MCMDR_RXON)) { + emc->regs[REG_MGSTA] |= REG_MGSTA_RXHA; + } + if (!(value & REG_MCMDR_RXON)) { + emc_halt_rx(emc, 0); + } + break; + } + case REG_TXDLSA: + case REG_RXDLSA: + case REG_DMARFC: + case REG_MIID: + emc->regs[reg] = value; + break; + case REG_MIEN: + emc->regs[reg] = value; + emc_update_irq_from_reg_change(emc); + break; + case REG_MISTA: + /* Clear the bits that have 1 in "value". */ + emc->regs[reg] &= ~value; + emc_update_irq_from_reg_change(emc); + break; + case REG_MGSTA: + /* Clear the bits that have 1 in "value". */ + emc->regs[reg] &= ~value; + break; + case REG_TSDR: + if (emc->regs[REG_MCMDR] & REG_MCMDR_TXON) { + emc->tx_active = true; + /* Keep trying to send packets until we run out. */ + while (emc->tx_active) { + emc_try_send_next_packet(emc); + } + } + break; + case REG_RSDR: + if (emc->regs[REG_MCMDR] & REG_MCMDR_RXON) { + emc->rx_active = true; + emc_try_receive_next_packet(emc); + } + break; + case REG_MIIDA: + emc->regs[reg] = value & ~REG_MIIDA_BUSY; + break; + case REG_MRPC: + case REG_MRPCC: + case REG_MREPC: + case REG_CTXDSA: + case REG_CTXBSA: + case REG_CRXDSA: + case REG_CRXBSA: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Write to read-only reg %s/%d\n", + __func__, emc_reg_name(reg), reg); + break; + default: + qemu_log_mask(LOG_UNIMP, "%s: Write to unimplemented reg %s/%d\n", + __func__, emc_reg_name(reg), reg); + break; + } +} + +static const struct MemoryRegionOps npcm7xx_emc_ops = { + .read = npcm7xx_emc_read, + .write = npcm7xx_emc_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void emc_cleanup(NetClientState *nc) +{ + /* Nothing to do yet. */ +} + +static NetClientInfo net_npcm7xx_emc_info = { + .type = NET_CLIENT_DRIVER_NIC, + .size = sizeof(NICState), + .can_receive = emc_can_receive, + .receive = emc_receive, + .cleanup = emc_cleanup, + .link_status_changed = emc_set_link, +}; + +static void npcm7xx_emc_realize(DeviceState *dev, Error **errp) +{ + NPCM7xxEMCState *emc = NPCM7XX_EMC(dev); + SysBusDevice *sbd = SYS_BUS_DEVICE(emc); + + memory_region_init_io(&emc->iomem, OBJECT(emc), &npcm7xx_emc_ops, emc, + TYPE_NPCM7XX_EMC, 4 * KiB); + sysbus_init_mmio(sbd, &emc->iomem); + sysbus_init_irq(sbd, &emc->tx_irq); + sysbus_init_irq(sbd, &emc->rx_irq); + + qemu_macaddr_default_if_unset(&emc->conf.macaddr); + emc->nic = qemu_new_nic(&net_npcm7xx_emc_info, &emc->conf, + object_get_typename(OBJECT(dev)), dev->id, emc); + qemu_format_nic_info_str(qemu_get_queue(emc->nic), emc->conf.macaddr.a); +} + +static void npcm7xx_emc_unrealize(DeviceState *dev) +{ + NPCM7xxEMCState *emc = NPCM7XX_EMC(dev); + + qemu_del_nic(emc->nic); +} + +static const VMStateDescription vmstate_npcm7xx_emc = { + .name = TYPE_NPCM7XX_EMC, + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT8(emc_num, NPCM7xxEMCState), + VMSTATE_UINT32_ARRAY(regs, NPCM7xxEMCState, NPCM7XX_NUM_EMC_REGS), + VMSTATE_BOOL(tx_active, NPCM7xxEMCState), + VMSTATE_BOOL(rx_active, NPCM7xxEMCState), + VMSTATE_END_OF_LIST(), + }, +}; + +static Property npcm7xx_emc_properties[] = { + DEFINE_NIC_PROPERTIES(NPCM7xxEMCState, conf), + DEFINE_PROP_END_OF_LIST(), +}; + +static void npcm7xx_emc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + set_bit(DEVICE_CATEGORY_NETWORK, dc->categories); + dc->desc = "NPCM7xx EMC Controller"; + dc->realize = npcm7xx_emc_realize; + dc->unrealize = npcm7xx_emc_unrealize; + dc->reset = npcm7xx_emc_reset; + dc->vmsd = &vmstate_npcm7xx_emc; + device_class_set_props(dc, npcm7xx_emc_properties); +} + +static const TypeInfo npcm7xx_emc_info = { + .name = TYPE_NPCM7XX_EMC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxEMCState), + .class_init = npcm7xx_emc_class_init, +}; + +static void npcm7xx_emc_register_type(void) +{ + type_register_static(&npcm7xx_emc_info); +} + +type_init(npcm7xx_emc_register_type) diff --git a/hw/net/meson.build b/hw/net/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/net/meson.build +++ b/hw/net/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_I82596_COMMON', if_true: files('i82596.c')) softmmu_ss.add(when: 'CONFIG_SUNHME', if_true: files('sunhme.c')) softmmu_ss.add(when: 'CONFIG_FTGMAC100', if_true: files('ftgmac100.c')) softmmu_ss.add(when: 'CONFIG_SUNGEM', if_true: files('sungem.c')) +softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_emc.c')) softmmu_ss.add(when: 'CONFIG_ETRAXFS', if_true: files('etraxfs_eth.c')) softmmu_ss.add(when: 'CONFIG_COLDFIRE', if_true: files('mcf_fec.c')) diff --git a/hw/net/trace-events b/hw/net/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/net/trace-events +++ b/hw/net/trace-events @@ -XXX,XX +XXX,XX @@ imx_fec_receive_last(int last) "rx frame flags 0x%04x" imx_enet_receive(size_t size) "len %zu" imx_enet_receive_len(uint64_t addr, int len) "rx_bd 0x%"PRIx64" length %d" imx_enet_receive_last(int last) "rx frame flags 0x%04x" + +# npcm7xx_emc.c +npcm7xx_emc_reset(int emc_num) "Resetting emc%d" +npcm7xx_emc_update_tx_irq(int level) "Setting tx irq to %d" +npcm7xx_emc_update_rx_irq(int level) "Setting rx irq to %d" +npcm7xx_emc_set_mista(uint32_t flags) "ORing 0x%x into MISTA" +npcm7xx_emc_cpu_owned_desc(uint32_t addr) "Can't process cpu-owned descriptor @0x%x" +npcm7xx_emc_sent_packet(uint32_t len) "Sent %u byte packet" +npcm7xx_emc_tx_done(uint32_t ctxdsa) "TX done, CTXDSA=0x%x" +npcm7xx_emc_can_receive(int can_receive) "Can receive: %d" +npcm7xx_emc_packet_filtered_out(const char* fail_reason) "Packet filtered out: %s" +npcm7xx_emc_packet_dropped(uint32_t len) "%u byte packet dropped" +npcm7xx_emc_receiving_packet(uint32_t len) "Receiving %u byte packet" +npcm7xx_emc_received_packet(uint32_t len) "Received %u byte packet" +npcm7xx_emc_rx_done(uint32_t crxdsa) "RX done, CRXDSA=0x%x" +npcm7xx_emc_reg_read(int emc_num, uint32_t result, const char *name, int regno) "emc%d: 0x%x = reg[%s/%d]" +npcm7xx_emc_reg_write(int emc_num, const char *name, int regno, uint32_t value) "emc%d: reg[%s/%d] = 0x%x" -- 2.20.1 From: Doug Evans <dje@google.com> This is a 10/100 ethernet device that has several features. Only the ones needed by the Linux driver have been implemented. See npcm7xx_emc.c for a list of unimplemented features. Reviewed-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Avi Fishman <avi.fishman@nuvoton.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Doug Evans <dje@google.com> Message-id: 20210218212453.831406-3-dje@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/nuvoton.rst | 3 ++- include/hw/arm/npcm7xx.h | 2 ++ hw/arm/npcm7xx.c | 50 +++++++++++++++++++++++++++++++++++-- 3 files changed, 52 insertions(+), 3 deletions(-) diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/nuvoton.rst +++ b/docs/system/arm/nuvoton.rst @@ -XXX,XX +XXX,XX @@ Supported devices * Analog to Digital Converter (ADC) * Pulse Width Modulation (PWM) * SMBus controller (SMBF) + * Ethernet controller (EMC) Missing devices --------------- @@ -XXX,XX +XXX,XX @@ Missing devices * Shared memory (SHM) * eSPI slave interface - * Ethernet controllers (GMAC and EMC) + * Ethernet controller (GMAC) * USB device (USBD) * Peripheral SPI controller (PSPI) * SD/MMC host diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/npcm7xx_gcr.h" #include "hw/misc/npcm7xx_pwm.h" #include "hw/misc/npcm7xx_rng.h" +#include "hw/net/npcm7xx_emc.h" #include "hw/nvram/npcm7xx_otp.h" #include "hw/timer/npcm7xx_timer.h" #include "hw/ssi/npcm7xx_fiu.h" @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { EHCISysBusState ehci; OHCISysBusState ohci; NPCM7xxFIUState fiu[2]; + NPCM7xxEMCState emc[2]; } NPCM7xxState; #define TYPE_NPCM7XX "npcm7xx" diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ enum NPCM7xxInterrupt { NPCM7XX_UART1_IRQ, NPCM7XX_UART2_IRQ, NPCM7XX_UART3_IRQ, + NPCM7XX_EMC1RX_IRQ = 15, + NPCM7XX_EMC1TX_IRQ, NPCM7XX_TIMER0_IRQ = 32, /* Timer Module 0 */ NPCM7XX_TIMER1_IRQ, NPCM7XX_TIMER2_IRQ, @@ -XXX,XX +XXX,XX @@ enum NPCM7xxInterrupt { NPCM7XX_SMBUS15_IRQ, NPCM7XX_PWM0_IRQ = 93, /* PWM module 0 */ NPCM7XX_PWM1_IRQ, /* PWM module 1 */ + NPCM7XX_EMC2RX_IRQ = 114, + NPCM7XX_EMC2TX_IRQ, NPCM7XX_GPIO0_IRQ = 116, NPCM7XX_GPIO1_IRQ, NPCM7XX_GPIO2_IRQ, @@ -XXX,XX +XXX,XX @@ static const hwaddr npcm7xx_smbus_addr[] = { 0xf008f000, }; +/* Register base address for each EMC Module */ +static const hwaddr npcm7xx_emc_addr[] = { + 0xf0825000, + 0xf0826000, +}; + static const struct { hwaddr regs_addr; uint32_t unconnected_pins; @@ -XXX,XX +XXX,XX @@ static void npcm7xx_init(Object *obj) for (i = 0; i < ARRAY_SIZE(s->pwm); i++) { object_initialize_child(obj, "pwm[*]", &s->pwm[i], TYPE_NPCM7XX_PWM); } + + for (i = 0; i < ARRAY_SIZE(s->emc); i++) { + object_initialize_child(obj, "emc[*]", &s->emc[i], TYPE_NPCM7XX_EMC); + } } static void npcm7xx_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(sbd, i, npcm7xx_irq(s, NPCM7XX_PWM0_IRQ + i)); } + /* + * EMC Modules. Cannot fail. + * The mapping of the device to its netdev backend works as follows: + * emc[i] = nd_table[i] + * This works around the inability to specify the netdev property for the + * emc device: it's not pluggable and thus the -device option can't be + * used. + */ + QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_emc_addr) != ARRAY_SIZE(s->emc)); + QEMU_BUILD_BUG_ON(ARRAY_SIZE(s->emc) != 2); + for (i = 0; i < ARRAY_SIZE(s->emc); i++) { + s->emc[i].emc_num = i; + SysBusDevice *sbd = SYS_BUS_DEVICE(&s->emc[i]); + if (nd_table[i].used) { + qemu_check_nic_model(&nd_table[i], TYPE_NPCM7XX_EMC); + qdev_set_nic_properties(DEVICE(sbd), &nd_table[i]); + } + /* + * The device exists regardless of whether it's connected to a QEMU + * netdev backend. So always instantiate it even if there is no + * backend. + */ + sysbus_realize(sbd, &error_abort); + sysbus_mmio_map(sbd, 0, npcm7xx_emc_addr[i]); + int tx_irq = i == 0 ? NPCM7XX_EMC1TX_IRQ : NPCM7XX_EMC2TX_IRQ; + int rx_irq = i == 0 ? NPCM7XX_EMC1RX_IRQ : NPCM7XX_EMC2RX_IRQ; + /* + * N.B. The values for the second argument sysbus_connect_irq are + * chosen to match the registration order in npcm7xx_emc_realize. + */ + sysbus_connect_irq(sbd, 0, npcm7xx_irq(s, tx_irq)); + sysbus_connect_irq(sbd, 1, npcm7xx_irq(s, rx_irq)); + } + /* * Flash Interface Unit (FIU). Can fail if incorrect number of chip selects * specified, but this is a programming error. @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) create_unimplemented_device("npcm7xx.vcd", 0xf0810000, 64 * KiB); create_unimplemented_device("npcm7xx.ece", 0xf0820000, 8 * KiB); create_unimplemented_device("npcm7xx.vdma", 0xf0822000, 8 * KiB); - create_unimplemented_device("npcm7xx.emc1", 0xf0825000, 4 * KiB); - create_unimplemented_device("npcm7xx.emc2", 0xf0826000, 4 * KiB); create_unimplemented_device("npcm7xx.usbd[0]", 0xf0830000, 4 * KiB); create_unimplemented_device("npcm7xx.usbd[1]", 0xf0831000, 4 * KiB); create_unimplemented_device("npcm7xx.usbd[2]", 0xf0832000, 4 * KiB); -- 2.20.1 From: Doug Evans <dje@google.com> Reviewed-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Avi Fishman <avi.fishman@nuvoton.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Doug Evans <dje@google.com> Message-id: 20210218212453.831406-4-dje@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/npcm7xx_emc-test.c | 862 +++++++++++++++++++++++++++++++++ tests/qtest/meson.build | 3 +- 2 files changed, 864 insertions(+), 1 deletion(-) create mode 100644 tests/qtest/npcm7xx_emc-test.c diff --git a/tests/qtest/npcm7xx_emc-test.c b/tests/qtest/npcm7xx_emc-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/npcm7xx_emc-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTests for Nuvoton NPCM7xx EMC Modules. + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "libqos/libqos.h" +#include "qapi/qmp/qdict.h" +#include "qapi/qmp/qnum.h" +#include "qemu/bitops.h" +#include "qemu/iov.h" + +/* Name of the emc device. */ +#define TYPE_NPCM7XX_EMC "npcm7xx-emc" + +/* Timeout for various operations, in seconds. */ +#define TIMEOUT_SECONDS 10 + +/* Address in memory of the descriptor. */ +#define DESC_ADDR (1 << 20) /* 1 MiB */ + +/* Address in memory of the data packet. */ +#define DATA_ADDR (DESC_ADDR + 4096) + +#define CRC_LENGTH 4 + +#define NUM_TX_DESCRIPTORS 3 +#define NUM_RX_DESCRIPTORS 2 + +/* Size of tx,rx test buffers. */ +#define TX_DATA_LEN 64 +#define RX_DATA_LEN 64 + +#define TX_STEP_COUNT 10000 +#define RX_STEP_COUNT 10000 + +/* 32-bit register indices. */ +typedef enum NPCM7xxPWMRegister { + /* Control registers. */ + REG_CAMCMR, + REG_CAMEN, + + /* There are 16 CAMn[ML] registers. */ + REG_CAMM_BASE, + REG_CAML_BASE, + + REG_TXDLSA = 0x22, + REG_RXDLSA, + REG_MCMDR, + REG_MIID, + REG_MIIDA, + REG_FFTCR, + REG_TSDR, + REG_RSDR, + REG_DMARFC, + REG_MIEN, + + /* Status registers. */ + REG_MISTA, + REG_MGSTA, + REG_MPCNT, + REG_MRPC, + REG_MRPCC, + REG_MREPC, + REG_DMARFS, + REG_CTXDSA, + REG_CTXBSA, + REG_CRXDSA, + REG_CRXBSA, + + NPCM7XX_NUM_EMC_REGS, +} NPCM7xxPWMRegister; + +enum { NUM_CAMML_REGS = 16 }; + +/* REG_CAMCMR fields */ +/* Enable CAM Compare */ +#define REG_CAMCMR_ECMP (1 << 4) +/* Accept Unicast Packet */ +#define REG_CAMCMR_AUP (1 << 0) + +/* REG_MCMDR fields */ +/* Software Reset */ +#define REG_MCMDR_SWR (1 << 24) +/* Frame Transmission On */ +#define REG_MCMDR_TXON (1 << 8) +/* Accept Long Packet */ +#define REG_MCMDR_ALP (1 << 1) +/* Frame Reception On */ +#define REG_MCMDR_RXON (1 << 0) + +/* REG_MIEN fields */ +/* Enable Transmit Completion Interrupt */ +#define REG_MIEN_ENTXCP (1 << 18) +/* Enable Transmit Interrupt */ +#define REG_MIEN_ENTXINTR (1 << 16) +/* Enable Receive Good Interrupt */ +#define REG_MIEN_ENRXGD (1 << 4) +/* ENable Receive Interrupt */ +#define REG_MIEN_ENRXINTR (1 << 0) + +/* REG_MISTA fields */ +/* Transmit Bus Error Interrupt */ +#define REG_MISTA_TXBERR (1 << 24) +/* Transmit Descriptor Unavailable Interrupt */ +#define REG_MISTA_TDU (1 << 23) +/* Transmit Completion Interrupt */ +#define REG_MISTA_TXCP (1 << 18) +/* Transmit Interrupt */ +#define REG_MISTA_TXINTR (1 << 16) +/* Receive Bus Error Interrupt */ +#define REG_MISTA_RXBERR (1 << 11) +/* Receive Descriptor Unavailable Interrupt */ +#define REG_MISTA_RDU (1 << 10) +/* DMA Early Notification Interrupt */ +#define REG_MISTA_DENI (1 << 9) +/* Maximum Frame Length Interrupt */ +#define REG_MISTA_DFOI (1 << 8) +/* Receive Good Interrupt */ +#define REG_MISTA_RXGD (1 << 4) +/* Packet Too Long Interrupt */ +#define REG_MISTA_PTLE (1 << 3) +/* Receive Interrupt */ +#define REG_MISTA_RXINTR (1 << 0) + +typedef struct NPCM7xxEMCTxDesc NPCM7xxEMCTxDesc; +typedef struct NPCM7xxEMCRxDesc NPCM7xxEMCRxDesc; + +struct NPCM7xxEMCTxDesc { + uint32_t flags; + uint32_t txbsa; + uint32_t status_and_length; + uint32_t ntxdsa; +}; + +struct NPCM7xxEMCRxDesc { + uint32_t status_and_length; + uint32_t rxbsa; + uint32_t reserved; + uint32_t nrxdsa; +}; + +/* NPCM7xxEMCTxDesc.flags values */ +/* Owner: 0 = cpu, 1 = emc */ +#define TX_DESC_FLAG_OWNER_MASK (1 << 31) +/* Transmit interrupt enable */ +#define TX_DESC_FLAG_INTEN (1 << 2) + +/* NPCM7xxEMCTxDesc.status_and_length values */ +/* Transmission complete */ +#define TX_DESC_STATUS_TXCP (1 << 19) +/* Transmit interrupt */ +#define TX_DESC_STATUS_TXINTR (1 << 16) + +/* NPCM7xxEMCRxDesc.status_and_length values */ +/* Owner: 0b00 = cpu, 0b10 = emc */ +#define RX_DESC_STATUS_OWNER_SHIFT 30 +#define RX_DESC_STATUS_OWNER_MASK 0xc0000000 +/* Frame Reception Complete */ +#define RX_DESC_STATUS_RXGD (1 << 20) +/* Packet too long */ +#define RX_DESC_STATUS_PTLE (1 << 19) +/* Receive Interrupt */ +#define RX_DESC_STATUS_RXINTR (1 << 16) + +#define RX_DESC_PKT_LEN(word) ((uint32_t) (word) & 0xffff) + +typedef struct EMCModule { + int rx_irq; + int tx_irq; + uint64_t base_addr; +} EMCModule; + +typedef struct TestData { + const EMCModule *module; +} TestData; + +static const EMCModule emc_module_list[] = { + { + .rx_irq = 15, + .tx_irq = 16, + .base_addr = 0xf0825000 + }, + { + .rx_irq = 114, + .tx_irq = 115, + .base_addr = 0xf0826000 + } +}; + +/* Returns the index of the EMC module. */ +static int emc_module_index(const EMCModule *mod) +{ + ptrdiff_t diff = mod - emc_module_list; + + g_assert_true(diff >= 0 && diff < ARRAY_SIZE(emc_module_list)); + + return diff; +} + +static void packet_test_clear(void *sockets) +{ + int *test_sockets = sockets; + + close(test_sockets[0]); + g_free(test_sockets); +} + +static int *packet_test_init(int module_num, GString *cmd_line) +{ + int *test_sockets = g_new(int, 2); + int ret = socketpair(PF_UNIX, SOCK_STREAM, 0, test_sockets); + g_assert_cmpint(ret, != , -1); + + /* + * KISS and use -nic. We specify two nics (both emc{0,1}) because there's + * currently no way to specify only emc1: The driver implicitly relies on + * emc[i] == nd_table[i]. + */ + if (module_num == 0) { + g_string_append_printf(cmd_line, + " -nic socket,fd=%d,model=" TYPE_NPCM7XX_EMC " " + " -nic user,model=" TYPE_NPCM7XX_EMC " ", + test_sockets[1]); + } else { + g_string_append_printf(cmd_line, + " -nic user,model=" TYPE_NPCM7XX_EMC " " + " -nic socket,fd=%d,model=" TYPE_NPCM7XX_EMC " ", + test_sockets[1]); + } + + g_test_queue_destroy(packet_test_clear, test_sockets); + return test_sockets; +} + +static uint32_t emc_read(QTestState *qts, const EMCModule *mod, + NPCM7xxPWMRegister regno) +{ + return qtest_readl(qts, mod->base_addr + regno * sizeof(uint32_t)); +} + +static void emc_write(QTestState *qts, const EMCModule *mod, + NPCM7xxPWMRegister regno, uint32_t value) +{ + qtest_writel(qts, mod->base_addr + regno * sizeof(uint32_t), value); +} + +static void emc_read_tx_desc(QTestState *qts, uint32_t addr, + NPCM7xxEMCTxDesc *desc) +{ + qtest_memread(qts, addr, desc, sizeof(*desc)); + desc->flags = le32_to_cpu(desc->flags); + desc->txbsa = le32_to_cpu(desc->txbsa); + desc->status_and_length = le32_to_cpu(desc->status_and_length); + desc->ntxdsa = le32_to_cpu(desc->ntxdsa); +} + +static void emc_write_tx_desc(QTestState *qts, const NPCM7xxEMCTxDesc *desc, + uint32_t addr) +{ + NPCM7xxEMCTxDesc le_desc; + + le_desc.flags = cpu_to_le32(desc->flags); + le_desc.txbsa = cpu_to_le32(desc->txbsa); + le_desc.status_and_length = cpu_to_le32(desc->status_and_length); + le_desc.ntxdsa = cpu_to_le32(desc->ntxdsa); + qtest_memwrite(qts, addr, &le_desc, sizeof(le_desc)); +} + +static void emc_read_rx_desc(QTestState *qts, uint32_t addr, + NPCM7xxEMCRxDesc *desc) +{ + qtest_memread(qts, addr, desc, sizeof(*desc)); + desc->status_and_length = le32_to_cpu(desc->status_and_length); + desc->rxbsa = le32_to_cpu(desc->rxbsa); + desc->reserved = le32_to_cpu(desc->reserved); + desc->nrxdsa = le32_to_cpu(desc->nrxdsa); +} + +static void emc_write_rx_desc(QTestState *qts, const NPCM7xxEMCRxDesc *desc, + uint32_t addr) +{ + NPCM7xxEMCRxDesc le_desc; + + le_desc.status_and_length = cpu_to_le32(desc->status_and_length); + le_desc.rxbsa = cpu_to_le32(desc->rxbsa); + le_desc.reserved = cpu_to_le32(desc->reserved); + le_desc.nrxdsa = cpu_to_le32(desc->nrxdsa); + qtest_memwrite(qts, addr, &le_desc, sizeof(le_desc)); +} + +/* + * Reset the EMC module. + * The module must be reset before, e.g., TXDLSA,RXDLSA are changed. + */ +static bool emc_soft_reset(QTestState *qts, const EMCModule *mod) +{ + uint32_t val; + uint64_t end_time; + + emc_write(qts, mod, REG_MCMDR, REG_MCMDR_SWR); + + /* + * Wait for device to reset as the linux driver does. + * During reset the AHB reads 0 for all registers. So first wait for + * something that resets to non-zero, and then wait for SWR becoming 0. + */ + end_time = g_get_monotonic_time() + TIMEOUT_SECONDS * G_TIME_SPAN_SECOND; + + do { + qtest_clock_step(qts, 100); + val = emc_read(qts, mod, REG_FFTCR); + } while (val == 0 && g_get_monotonic_time() < end_time); + if (val != 0) { + do { + qtest_clock_step(qts, 100); + val = emc_read(qts, mod, REG_MCMDR); + if ((val & REG_MCMDR_SWR) == 0) { + /* + * N.B. The CAMs have been reset here, so macaddr matching of + * incoming packets will not work. + */ + return true; + } + } while (g_get_monotonic_time() < end_time); + } + + g_message("%s: Timeout expired", __func__); + return false; +} + +/* Check emc registers are reset to default value. */ +static void test_init(gconstpointer test_data) +{ + const TestData *td = test_data; + const EMCModule *mod = td->module; + QTestState *qts = qtest_init("-machine quanta-gsj"); + int i; + +#define CHECK_REG(regno, value) \ + do { \ + g_assert_cmphex(emc_read(qts, mod, (regno)), ==, (value)); \ + } while (0) + + CHECK_REG(REG_CAMCMR, 0); + CHECK_REG(REG_CAMEN, 0); + CHECK_REG(REG_TXDLSA, 0xfffffffc); + CHECK_REG(REG_RXDLSA, 0xfffffffc); + CHECK_REG(REG_MCMDR, 0); + CHECK_REG(REG_MIID, 0); + CHECK_REG(REG_MIIDA, 0x00900000); + CHECK_REG(REG_FFTCR, 0x0101); + CHECK_REG(REG_DMARFC, 0x0800); + CHECK_REG(REG_MIEN, 0); + CHECK_REG(REG_MISTA, 0); + CHECK_REG(REG_MGSTA, 0); + CHECK_REG(REG_MPCNT, 0x7fff); + CHECK_REG(REG_MRPC, 0); + CHECK_REG(REG_MRPCC, 0); + CHECK_REG(REG_MREPC, 0); + CHECK_REG(REG_DMARFS, 0); + CHECK_REG(REG_CTXDSA, 0); + CHECK_REG(REG_CTXBSA, 0); + CHECK_REG(REG_CRXDSA, 0); + CHECK_REG(REG_CRXBSA, 0); + +#undef CHECK_REG + + for (i = 0; i < NUM_CAMML_REGS; ++i) { + g_assert_cmpuint(emc_read(qts, mod, REG_CAMM_BASE + i * 2), ==, + 0); + g_assert_cmpuint(emc_read(qts, mod, REG_CAML_BASE + i * 2), ==, + 0); + } + + qtest_quit(qts); +} + +static bool emc_wait_irq(QTestState *qts, const EMCModule *mod, int step, + bool is_tx) +{ + uint64_t end_time = + g_get_monotonic_time() + TIMEOUT_SECONDS * G_TIME_SPAN_SECOND; + + do { + if (qtest_get_irq(qts, is_tx ? mod->tx_irq : mod->rx_irq)) { + return true; + } + qtest_clock_step(qts, step); + } while (g_get_monotonic_time() < end_time); + + g_message("%s: Timeout expired", __func__); + return false; +} + +static bool emc_wait_mista(QTestState *qts, const EMCModule *mod, int step, + uint32_t flag) +{ + uint64_t end_time = + g_get_monotonic_time() + TIMEOUT_SECONDS * G_TIME_SPAN_SECOND; + + do { + uint32_t mista = emc_read(qts, mod, REG_MISTA); + if (mista & flag) { + return true; + } + qtest_clock_step(qts, step); + } while (g_get_monotonic_time() < end_time); + + g_message("%s: Timeout expired", __func__); + return false; +} + +static bool wait_socket_readable(int fd) +{ + fd_set read_fds; + struct timeval tv; + int rv; + + FD_ZERO(&read_fds); + FD_SET(fd, &read_fds); + tv.tv_sec = TIMEOUT_SECONDS; + tv.tv_usec = 0; + rv = select(fd + 1, &read_fds, NULL, NULL, &tv); + if (rv == -1) { + perror("select"); + } else if (rv == 0) { + g_message("%s: Timeout expired", __func__); + } + return rv == 1; +} + +/* Initialize *desc (in host endian format). */ +static void init_tx_desc(NPCM7xxEMCTxDesc *desc, size_t count, + uint32_t desc_addr) +{ + g_assert(count >= 2); + memset(&desc[0], 0, sizeof(*desc) * count); + /* Leave the last one alone, owned by the cpu -> stops transmission. */ + for (size_t i = 0; i < count - 1; ++i) { + desc[i].flags = + (TX_DESC_FLAG_OWNER_MASK | /* owner = 1: emc */ + TX_DESC_FLAG_INTEN | + 0 | /* crc append = 0 */ + 0 /* padding enable = 0 */); + desc[i].status_and_length = + (0 | /* collision count = 0 */ + 0 | /* SQE = 0 */ + 0 | /* PAU = 0 */ + 0 | /* TXHA = 0 */ + 0 | /* LC = 0 */ + 0 | /* TXABT = 0 */ + 0 | /* NCS = 0 */ + 0 | /* EXDEF = 0 */ + 0 | /* TXCP = 0 */ + 0 | /* DEF = 0 */ + 0 | /* TXINTR = 0 */ + 0 /* length filled in later */); + desc[i].ntxdsa = desc_addr + (i + 1) * sizeof(*desc); + } +} + +static void enable_tx(QTestState *qts, const EMCModule *mod, + const NPCM7xxEMCTxDesc *desc, size_t count, + uint32_t desc_addr, uint32_t mien_flags) +{ + /* Write the descriptors to guest memory. */ + for (size_t i = 0; i < count; ++i) { + emc_write_tx_desc(qts, desc + i, desc_addr + i * sizeof(*desc)); + } + + /* Trigger sending the packet. */ + /* The module must be reset before changing TXDLSA. */ + g_assert(emc_soft_reset(qts, mod)); + emc_write(qts, mod, REG_TXDLSA, desc_addr); + emc_write(qts, mod, REG_CTXDSA, ~0); + emc_write(qts, mod, REG_MIEN, REG_MIEN_ENTXCP | mien_flags); + { + uint32_t mcmdr = emc_read(qts, mod, REG_MCMDR); + mcmdr |= REG_MCMDR_TXON; + emc_write(qts, mod, REG_MCMDR, mcmdr); + } + + /* Prod the device to send the packet. */ + emc_write(qts, mod, REG_TSDR, 1); +} + +static void emc_send_verify1(QTestState *qts, const EMCModule *mod, int fd, + bool with_irq, uint32_t desc_addr, + uint32_t next_desc_addr, + const char *test_data, int test_size) +{ + NPCM7xxEMCTxDesc result_desc; + uint32_t expected_mask, expected_value, recv_len; + int ret; + char buffer[TX_DATA_LEN]; + + g_assert(wait_socket_readable(fd)); + + /* Read the descriptor back. */ + emc_read_tx_desc(qts, desc_addr, &result_desc); + /* Descriptor should be owned by cpu now. */ + g_assert((result_desc.flags & TX_DESC_FLAG_OWNER_MASK) == 0); + /* Test the status bits, ignoring the length field. */ + expected_mask = 0xffff << 16; + expected_value = TX_DESC_STATUS_TXCP; + if (with_irq) { + expected_value |= TX_DESC_STATUS_TXINTR; + } + g_assert_cmphex((result_desc.status_and_length & expected_mask), ==, + expected_value); + + /* Check data sent to the backend. */ + recv_len = ~0; + ret = qemu_recv(fd, &recv_len, sizeof(recv_len), MSG_DONTWAIT); + g_assert_cmpint(ret, == , sizeof(recv_len)); + + g_assert(wait_socket_readable(fd)); + memset(buffer, 0xff, sizeof(buffer)); + ret = qemu_recv(fd, buffer, test_size, MSG_DONTWAIT); + g_assert_cmpmem(buffer, ret, test_data, test_size); +} + +static void emc_send_verify(QTestState *qts, const EMCModule *mod, int fd, + bool with_irq) +{ + NPCM7xxEMCTxDesc desc[NUM_TX_DESCRIPTORS]; + uint32_t desc_addr = DESC_ADDR; + static const char test1_data[] = "TEST1"; + static const char test2_data[] = "Testing 1 2 3 ..."; + uint32_t data1_addr = DATA_ADDR; + uint32_t data2_addr = data1_addr + sizeof(test1_data); + bool got_tdu; + uint32_t end_desc_addr; + + /* Prepare test data buffer. */ + qtest_memwrite(qts, data1_addr, test1_data, sizeof(test1_data)); + qtest_memwrite(qts, data2_addr, test2_data, sizeof(test2_data)); + + init_tx_desc(&desc[0], NUM_TX_DESCRIPTORS, desc_addr); + desc[0].txbsa = data1_addr; + desc[0].status_and_length |= sizeof(test1_data); + desc[1].txbsa = data2_addr; + desc[1].status_and_length |= sizeof(test2_data); + + enable_tx(qts, mod, &desc[0], NUM_TX_DESCRIPTORS, desc_addr, + with_irq ? REG_MIEN_ENTXINTR : 0); + + /* + * It's problematic to observe the interrupt for each packet. + * Instead just wait until all the packets go out. + */ + got_tdu = false; + while (!got_tdu) { + if (with_irq) { + g_assert_true(emc_wait_irq(qts, mod, TX_STEP_COUNT, + /*is_tx=*/true)); + } else { + g_assert_true(emc_wait_mista(qts, mod, TX_STEP_COUNT, + REG_MISTA_TXINTR)); + } + got_tdu = !!(emc_read(qts, mod, REG_MISTA) & REG_MISTA_TDU); + /* If we don't have TDU yet, reset the interrupt. */ + if (!got_tdu) { + emc_write(qts, mod, REG_MISTA, + emc_read(qts, mod, REG_MISTA) & 0xffff0000); + } + } + + end_desc_addr = desc_addr + 2 * sizeof(desc[0]); + g_assert_cmphex(emc_read(qts, mod, REG_CTXDSA), ==, end_desc_addr); + g_assert_cmphex(emc_read(qts, mod, REG_MISTA), ==, + REG_MISTA_TXCP | REG_MISTA_TXINTR | REG_MISTA_TDU); + + emc_send_verify1(qts, mod, fd, with_irq, + desc_addr, end_desc_addr, + test1_data, sizeof(test1_data)); + emc_send_verify1(qts, mod, fd, with_irq, + desc_addr + sizeof(desc[0]), end_desc_addr, + test2_data, sizeof(test2_data)); +} + +/* Initialize *desc (in host endian format). */ +static void init_rx_desc(NPCM7xxEMCRxDesc *desc, size_t count, + uint32_t desc_addr, uint32_t data_addr) +{ + g_assert_true(count >= 2); + memset(desc, 0, sizeof(*desc) * count); + desc[0].rxbsa = data_addr; + desc[0].status_and_length = + (0b10 << RX_DESC_STATUS_OWNER_SHIFT | /* owner = 10: emc */ + 0 | /* RP = 0 */ + 0 | /* ALIE = 0 */ + 0 | /* RXGD = 0 */ + 0 | /* PTLE = 0 */ + 0 | /* CRCE = 0 */ + 0 | /* RXINTR = 0 */ + 0 /* length (filled in later) */); + /* Leave the last one alone, owned by the cpu -> stops transmission. */ + desc[0].nrxdsa = desc_addr + sizeof(*desc); +} + +static void enable_rx(QTestState *qts, const EMCModule *mod, + const NPCM7xxEMCRxDesc *desc, size_t count, + uint32_t desc_addr, uint32_t mien_flags, + uint32_t mcmdr_flags) +{ + /* + * Write the descriptor to guest memory. + * FWIW, IWBN if the docs said the buffer needs to be at least DMARFC + * bytes. + */ + for (size_t i = 0; i < count; ++i) { + emc_write_rx_desc(qts, desc + i, desc_addr + i * sizeof(*desc)); + } + + /* Trigger receiving the packet. */ + /* The module must be reset before changing RXDLSA. */ + g_assert(emc_soft_reset(qts, mod)); + emc_write(qts, mod, REG_RXDLSA, desc_addr); + emc_write(qts, mod, REG_MIEN, REG_MIEN_ENRXGD | mien_flags); + + /* + * We don't know what the device's macaddr is, so just accept all + * unicast packets (AUP). + */ + emc_write(qts, mod, REG_CAMCMR, REG_CAMCMR_AUP); + emc_write(qts, mod, REG_CAMEN, 1 << 0); + { + uint32_t mcmdr = emc_read(qts, mod, REG_MCMDR); + mcmdr |= REG_MCMDR_RXON | mcmdr_flags; + emc_write(qts, mod, REG_MCMDR, mcmdr); + } + + /* Prod the device to accept a packet. */ + emc_write(qts, mod, REG_RSDR, 1); +} + +static void emc_recv_verify(QTestState *qts, const EMCModule *mod, int fd, + bool with_irq) +{ + NPCM7xxEMCRxDesc desc[NUM_RX_DESCRIPTORS]; + uint32_t desc_addr = DESC_ADDR; + uint32_t data_addr = DATA_ADDR; + int ret; + uint32_t expected_mask, expected_value; + NPCM7xxEMCRxDesc result_desc; + + /* Prepare test data buffer. */ + const char test[RX_DATA_LEN] = "TEST"; + int len = htonl(sizeof(test)); + const struct iovec iov[] = { + { + .iov_base = &len, + .iov_len = sizeof(len), + },{ + .iov_base = (char *) test, + .iov_len = sizeof(test), + }, + }; + + /* + * Reset the device BEFORE sending a test packet, otherwise the packet + * may get swallowed by an active device of an earlier test. + */ + init_rx_desc(&desc[0], NUM_RX_DESCRIPTORS, desc_addr, data_addr); + enable_rx(qts, mod, &desc[0], NUM_RX_DESCRIPTORS, desc_addr, + with_irq ? REG_MIEN_ENRXINTR : 0, 0); + + /* Send test packet to device's socket. */ + ret = iov_send(fd, iov, 2, 0, sizeof(len) + sizeof(test)); + g_assert_cmpint(ret, == , sizeof(test) + sizeof(len)); + + /* Wait for RX interrupt. */ + if (with_irq) { + g_assert_true(emc_wait_irq(qts, mod, RX_STEP_COUNT, /*is_tx=*/false)); + } else { + g_assert_true(emc_wait_mista(qts, mod, RX_STEP_COUNT, REG_MISTA_RXGD)); + } + + g_assert_cmphex(emc_read(qts, mod, REG_CRXDSA), ==, + desc_addr + sizeof(desc[0])); + + expected_mask = 0xffff; + expected_value = (REG_MISTA_DENI | + REG_MISTA_RXGD | + REG_MISTA_RXINTR); + g_assert_cmphex((emc_read(qts, mod, REG_MISTA) & expected_mask), + ==, expected_value); + + /* Read the descriptor back. */ + emc_read_rx_desc(qts, desc_addr, &result_desc); + /* Descriptor should be owned by cpu now. */ + g_assert((result_desc.status_and_length & RX_DESC_STATUS_OWNER_MASK) == 0); + /* Test the status bits, ignoring the length field. */ + expected_mask = 0xffff << 16; + expected_value = RX_DESC_STATUS_RXGD; + if (with_irq) { + expected_value |= RX_DESC_STATUS_RXINTR; + } + g_assert_cmphex((result_desc.status_and_length & expected_mask), ==, + expected_value); + g_assert_cmpint(RX_DESC_PKT_LEN(result_desc.status_and_length), ==, + RX_DATA_LEN + CRC_LENGTH); + + { + char buffer[RX_DATA_LEN]; + qtest_memread(qts, data_addr, buffer, sizeof(buffer)); + g_assert_cmpstr(buffer, == , "TEST"); + } +} + +static void emc_test_ptle(QTestState *qts, const EMCModule *mod, int fd) +{ + NPCM7xxEMCRxDesc desc[NUM_RX_DESCRIPTORS]; + uint32_t desc_addr = DESC_ADDR; + uint32_t data_addr = DATA_ADDR; + int ret; + NPCM7xxEMCRxDesc result_desc; + uint32_t expected_mask, expected_value; + + /* Prepare test data buffer. */ +#define PTLE_DATA_LEN 1600 + char test_data[PTLE_DATA_LEN]; + int len = htonl(sizeof(test_data)); + const struct iovec iov[] = { + { + .iov_base = &len, + .iov_len = sizeof(len), + },{ + .iov_base = (char *) test_data, + .iov_len = sizeof(test_data), + }, + }; + memset(test_data, 42, sizeof(test_data)); + + /* + * Reset the device BEFORE sending a test packet, otherwise the packet + * may get swallowed by an active device of an earlier test. + */ + init_rx_desc(&desc[0], NUM_RX_DESCRIPTORS, desc_addr, data_addr); + enable_rx(qts, mod, &desc[0], NUM_RX_DESCRIPTORS, desc_addr, + REG_MIEN_ENRXINTR, REG_MCMDR_ALP); + + /* Send test packet to device's socket. */ + ret = iov_send(fd, iov, 2, 0, sizeof(len) + sizeof(test_data)); + g_assert_cmpint(ret, == , sizeof(test_data) + sizeof(len)); + + /* Wait for RX interrupt. */ + g_assert_true(emc_wait_irq(qts, mod, RX_STEP_COUNT, /*is_tx=*/false)); + + /* Read the descriptor back. */ + emc_read_rx_desc(qts, desc_addr, &result_desc); + /* Descriptor should be owned by cpu now. */ + g_assert((result_desc.status_and_length & RX_DESC_STATUS_OWNER_MASK) == 0); + /* Test the status bits, ignoring the length field. */ + expected_mask = 0xffff << 16; + expected_value = (RX_DESC_STATUS_RXGD | + RX_DESC_STATUS_PTLE | + RX_DESC_STATUS_RXINTR); + g_assert_cmphex((result_desc.status_and_length & expected_mask), ==, + expected_value); + g_assert_cmpint(RX_DESC_PKT_LEN(result_desc.status_and_length), ==, + PTLE_DATA_LEN + CRC_LENGTH); + + { + char buffer[PTLE_DATA_LEN]; + qtest_memread(qts, data_addr, buffer, sizeof(buffer)); + g_assert(memcmp(buffer, test_data, PTLE_DATA_LEN) == 0); + } +} + +static void test_tx(gconstpointer test_data) +{ + const TestData *td = test_data; + GString *cmd_line = g_string_new("-machine quanta-gsj"); + int *test_sockets = packet_test_init(emc_module_index(td->module), + cmd_line); + QTestState *qts = qtest_init(cmd_line->str); + + /* + * TODO: For pedantic correctness test_sockets[0] should be closed after + * the fork and before the exec, but that will require some harness + * improvements. + */ + close(test_sockets[1]); + /* Defensive programming */ + test_sockets[1] = -1; + + qtest_irq_intercept_in(qts, "/machine/soc/a9mpcore/gic"); + + emc_send_verify(qts, td->module, test_sockets[0], /*with_irq=*/false); + emc_send_verify(qts, td->module, test_sockets[0], /*with_irq=*/true); + + qtest_quit(qts); +} + +static void test_rx(gconstpointer test_data) +{ + const TestData *td = test_data; + GString *cmd_line = g_string_new("-machine quanta-gsj"); + int *test_sockets = packet_test_init(emc_module_index(td->module), + cmd_line); + QTestState *qts = qtest_init(cmd_line->str); + + /* + * TODO: For pedantic correctness test_sockets[0] should be closed after + * the fork and before the exec, but that will require some harness + * improvements. + */ + close(test_sockets[1]); + /* Defensive programming */ + test_sockets[1] = -1; + + qtest_irq_intercept_in(qts, "/machine/soc/a9mpcore/gic"); + + emc_recv_verify(qts, td->module, test_sockets[0], /*with_irq=*/false); + emc_recv_verify(qts, td->module, test_sockets[0], /*with_irq=*/true); + emc_test_ptle(qts, td->module, test_sockets[0]); + + qtest_quit(qts); +} + +static void emc_add_test(const char *name, const TestData* td, + GTestDataFunc fn) +{ + g_autofree char *full_name = g_strdup_printf( + "npcm7xx_emc/emc[%d]/%s", emc_module_index(td->module), name); + qtest_add_data_func(full_name, td, fn); +} +#define add_test(name, td) emc_add_test(#name, td, test_##name) + +int main(int argc, char **argv) +{ + TestData test_data_list[ARRAY_SIZE(emc_module_list)]; + + g_test_init(&argc, &argv, NULL); + + for (int i = 0; i < ARRAY_SIZE(emc_module_list); ++i) { + TestData *td = &test_data_list[i]; + + td->module = &emc_module_list[i]; + + add_test(init, td); + add_test(tx, td); + add_test(rx, td); + } + + return g_test_run(); +} diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qtests_npcm7xx = \ 'npcm7xx_rng-test', 'npcm7xx_smbus-test', 'npcm7xx_timer-test', - 'npcm7xx_watchdog_timer-test'] + 'npcm7xx_watchdog_timer-test'] + \ + (slirp.found() ? ['npcm7xx_emc-test'] : []) qtests_arm = \ (config_all_devices.has_key('CONFIG_CMSDK_APB_DUALTIMER') ? ['cmsdk-apb-dualtimer-test'] : []) + \ (config_all_devices.has_key('CONFIG_CMSDK_APB_TIMER') ? ['cmsdk-apb-timer-test'] : []) + \ -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> We hint the 'has_rpu' property is no longer required since commit 6908ec448b4 ("xlnx-zynqmp: Properly support the smp command line option") which was released in QEMU v2.11.0. Beside, this device is marked 'user_creatable = false', so the only thing that could be setting the property is the board code that creates the device. Since the property is not user-facing, we can remove it without going through the deprecation process. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210219144350.1979905-1-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-zynqmp.h | 2 -- hw/arm/xlnx-zynqmp.c | 6 ------ 2 files changed, 8 deletions(-) diff --git a/include/hw/arm/xlnx-zynqmp.h b/include/hw/arm/xlnx-zynqmp.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-zynqmp.h +++ b/include/hw/arm/xlnx-zynqmp.h @@ -XXX,XX +XXX,XX @@ struct XlnxZynqMPState { bool secure; /* Has the ARM Virtualization extensions? */ bool virt; - /* Has the RPU subsystem? */ - bool has_rpu; /* CAN bus. */ CanBusState *canbus[XLNX_ZYNQMP_NUM_CAN]; diff --git a/hw/arm/xlnx-zynqmp.c b/hw/arm/xlnx-zynqmp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zynqmp.c +++ b/hw/arm/xlnx-zynqmp.c @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp) } } - if (s->has_rpu) { - info_report("The 'has_rpu' property is no longer required, to use the " - "RPUs just use -smp 6."); - } - xlnx_zynqmp_create_rpu(ms, s, boot_cpu, &err); if (err) { error_propagate(errp, err); @@ -XXX,XX +XXX,XX @@ static Property xlnx_zynqmp_props[] = { DEFINE_PROP_STRING("boot-cpu", XlnxZynqMPState, boot_cpu), DEFINE_PROP_BOOL("secure", XlnxZynqMPState, secure, false), DEFINE_PROP_BOOL("virtualization", XlnxZynqMPState, virt, false), - DEFINE_PROP_BOOL("has_rpu", XlnxZynqMPState, has_rpu, false), DEFINE_PROP_LINK("ddr-ram", XlnxZynqMPState, ddr_ram, TYPE_MEMORY_REGION, MemoryRegion *), DEFINE_PROP_LINK("canbus0", XlnxZynqMPState, canbus[0], TYPE_CAN_BUS, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Always perform one call instead of two for 16-byte operands. Use byte loads/stores directly into the vector register file instead of extractions and deposits to a 64-bit local variable. In order to easily receive pointers into the vector register file, convert the helper to the gvec out-of-line signature. Move the helper into vec_helper.c, where it can make use of H1 and clear_tail. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20210224230532.276878-1-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.h | 2 +- target/arm/helper-a64.c | 32 --------------------- target/arm/translate-a64.c | 58 +++++--------------------------------- target/arm/vec_helper.c | 48 +++++++++++++++++++++++++++++++ 4 files changed, 56 insertions(+), 84 deletions(-) diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_cmps_a64, i64, f32, f32, ptr) DEF_HELPER_3(vfp_cmpes_a64, i64, f32, f32, ptr) DEF_HELPER_3(vfp_cmpd_a64, i64, f64, f64, ptr) DEF_HELPER_3(vfp_cmped_a64, i64, f64, f64, ptr) -DEF_HELPER_FLAGS_5(simd_tbl, TCG_CALL_NO_RWG_SE, i64, env, i64, i64, i32, i32) +DEF_HELPER_FLAGS_4(simd_tblx, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(vfp_mulxs, TCG_CALL_NO_RWG, f32, f32, f32, ptr) DEF_HELPER_FLAGS_3(vfp_mulxd, TCG_CALL_NO_RWG, f64, f64, f64, ptr) DEF_HELPER_FLAGS_3(neon_ceq_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr) 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 @@ float64 HELPER(vfp_mulxd)(float64 a, float64 b, void *fpstp) return float64_mul(a, b, fpst); } -uint64_t HELPER(simd_tbl)(CPUARMState *env, uint64_t result, uint64_t indices, - uint32_t rn, uint32_t numregs) -{ - /* Helper function for SIMD TBL and TBX. We have to do the table - * lookup part for the 64 bits worth of indices we're passed in. - * result is the initial results vector (either zeroes for TBL - * or some guest values for TBX), rn the register number where - * the table starts, and numregs the number of registers in the table. - * We return the results of the lookups. - */ - int shift; - - for (shift = 0; shift < 64; shift += 8) { - int index = extract64(indices, shift, 8); - if (index < 16 * numregs) { - /* Convert index (a byte offset into the virtual table - * which is a series of 128-bit vectors concatenated) - * into the correct register element plus a bit offset - * into that element, bearing in mind that the table - * can wrap around from V31 to V0. - */ - int elt = (rn * 2 + (index >> 3)) % 64; - int bitidx = (index & 7) * 8; - uint64_t *q = aa64_vfp_qreg(env, elt >> 1); - uint64_t val = extract64(q[elt & 1], bitidx, 8); - - result = deposit64(result, shift, 8, val); - } - } - return result; -} - /* 64bit/double versions of the neon float compare functions */ uint64_t HELPER(neon_ceq_f64)(float64 a, float64 b, void *fpstp) { diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_tb(DisasContext *s, uint32_t insn) int rm = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - int is_tblx = extract32(insn, 12, 1); - int len = extract32(insn, 13, 2); - TCGv_i64 tcg_resl, tcg_resh, tcg_idx; - TCGv_i32 tcg_regno, tcg_numregs; + int is_tbx = extract32(insn, 12, 1); + int len = (extract32(insn, 13, 2) + 1) * 16; if (op2 != 0) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_tb(DisasContext *s, uint32_t insn) return; } - /* This does a table lookup: for every byte element in the input - * we index into a table formed from up to four vector registers, - * and then the output is the result of the lookups. Our helper - * function does the lookup operation for a single 64 bit part of - * the input. - */ - tcg_resl = tcg_temp_new_i64(); - tcg_resh = NULL; - - if (is_tblx) { - read_vec_element(s, tcg_resl, rd, 0, MO_64); - } else { - tcg_gen_movi_i64(tcg_resl, 0); - } - - if (is_q) { - tcg_resh = tcg_temp_new_i64(); - if (is_tblx) { - read_vec_element(s, tcg_resh, rd, 1, MO_64); - } else { - tcg_gen_movi_i64(tcg_resh, 0); - } - } - - tcg_idx = tcg_temp_new_i64(); - tcg_regno = tcg_const_i32(rn); - tcg_numregs = tcg_const_i32(len + 1); - read_vec_element(s, tcg_idx, rm, 0, MO_64); - gen_helper_simd_tbl(tcg_resl, cpu_env, tcg_resl, tcg_idx, - tcg_regno, tcg_numregs); - if (is_q) { - read_vec_element(s, tcg_idx, rm, 1, MO_64); - gen_helper_simd_tbl(tcg_resh, cpu_env, tcg_resh, tcg_idx, - tcg_regno, tcg_numregs); - } - tcg_temp_free_i64(tcg_idx); - tcg_temp_free_i32(tcg_regno); - tcg_temp_free_i32(tcg_numregs); - - write_vec_element(s, tcg_resl, rd, 0, MO_64); - tcg_temp_free_i64(tcg_resl); - - if (is_q) { - write_vec_element(s, tcg_resh, rd, 1, MO_64); - tcg_temp_free_i64(tcg_resh); - } - clear_vec_high(s, is_q, rd); + tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rm), cpu_env, + is_q ? 16 : 8, vec_full_reg_size(s), + (len << 6) | (is_tbx << 5) | rn, + gen_helper_simd_tblx); } /* ZIP/UZP/TRN 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_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 + +#ifdef TARGET_AARCH64 +void HELPER(simd_tblx)(void *vd, void *vm, void *venv, uint32_t desc) +{ + const uint8_t *indices = vm; + CPUARMState *env = venv; + size_t oprsz = simd_oprsz(desc); + uint32_t rn = extract32(desc, SIMD_DATA_SHIFT, 5); + bool is_tbx = extract32(desc, SIMD_DATA_SHIFT + 5, 1); + uint32_t table_len = desc >> (SIMD_DATA_SHIFT + 6); + union { + uint8_t b[16]; + uint64_t d[2]; + } result; + + /* + * We must construct the final result in a temp, lest the output + * overlaps the input table. For TBL, begin with zero; for TBX, + * begin with the original register contents. Note that we always + * copy 16 bytes here to avoid an extra branch; clearing the high + * bits of the register for oprsz == 8 is handled below. + */ + if (is_tbx) { + memcpy(&result, vd, 16); + } else { + memset(&result, 0, 16); + } + + for (size_t i = 0; i < oprsz; ++i) { + uint32_t index = indices[H1(i)]; + + if (index < table_len) { + /* + * Convert index (a byte offset into the virtual table + * which is a series of 128-bit vectors concatenated) + * into the correct register element, bearing in mind + * that the table can wrap around from V31 to V0. + */ + const uint8_t *table = (const uint8_t *) + aa64_vfp_qreg(env, (rn + (index >> 4)) % 32); + result.b[H1(i)] = table[H1(index % 16)]; + } + } + + memcpy(vd, &result, 16); + clear_tail(vd, oprsz, simd_maxsz(desc)); +} +#endif -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> The STATUS register will be reset to IDLE in cnpcm7xx_smbus_enter_reset(), no need to preset it in instance_init(). Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Hao Wu <wuhaotsh@google.com> Message-id: 20210228224813.312532-1-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/i2c/npcm7xx_smbus.c | 1 - 1 file changed, 1 deletion(-) diff --git a/hw/i2c/npcm7xx_smbus.c b/hw/i2c/npcm7xx_smbus.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/npcm7xx_smbus.c +++ b/hw/i2c/npcm7xx_smbus.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_smbus_init(Object *obj) sysbus_init_mmio(sbd, &s->iomem); s->bus = i2c_init_bus(DEVICE(s), "i2c-bus"); - s->status = NPCM7XX_SMBUS_STATUS_IDLE; } static const VMStateDescription vmstate_npcm7xx_smbus = { -- 2.20.1 From: schspa <schspa@gmail.com> At the moment the following QEMU command line triggers an assertion failure On xlnx-versal SOC: qemu-system-aarch64 \ -machine xlnx-versal-virt -nographic -smp 2 -m 128 \ -fsdev local,id=shareid,path=${HOME}/work,security_model=none \ -device virtio-9p-device,fsdev=shareid,mount_tag=share \ -fsdev local,id=shareid1,path=${HOME}/Music,security_model=none \ -device virtio-9p-device,fsdev=shareid1,mount_tag=share1 qemu-system-aarch64: ../migration/savevm.c:860: vmstate_register_with_alias_id: Assertion `!se->compat || se->instance_id == 0' failed. This problem was fixed on arm virt platform in commit f58b39d2d5b ("virtio-mmio: format transport base address in BusClass.get_dev_path") It works perfectly on arm virt platform. but there is still there on xlnx-versal SOC. The main difference between arm virt and xlnx-versal is they use different way to create virtio-mmio qdev. on arm virt, it calls sysbus_create_simple("virtio-mmio", base, pic[irq]); which will call sysbus_mmio_map internally and assign base address to subsys device mmio correctly. but xlnx-versal's implements won't do this. However, xlnx-versal can't switch to sysbus_create_simple() to create virtio-mmio device. It's because xlnx-versal's cpu use VersalVirt.soc.fpd.apu.mr as it's memory. which is subregion of system_memory. sysbus_create_simple will add virtio to system_memory, which can't be accessed by cpu. Besides, xlnx-versal can't add sysbus_mmio_map api call too, because this will add memory region to system_memory, and it can't be added to VersalVirt.soc.fpd.apu.mr again. We can solve this by assign correct base address offset on dev_path. This path was test on aarch64 virt & xlnx-versal platform. Signed-off-by: schspa <schspa@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/virtio/virtio-mmio.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/hw/virtio/virtio-mmio.c b/hw/virtio/virtio-mmio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/virtio/virtio-mmio.c +++ b/hw/virtio/virtio-mmio.c @@ -XXX,XX +XXX,XX @@ static char *virtio_mmio_bus_get_dev_path(DeviceState *dev) BusState *virtio_mmio_bus; VirtIOMMIOProxy *virtio_mmio_proxy; char *proxy_path; - SysBusDevice *proxy_sbd; char *path; + MemoryRegionSection section; virtio_mmio_bus = qdev_get_parent_bus(dev); virtio_mmio_proxy = VIRTIO_MMIO(virtio_mmio_bus->parent); @@ -XXX,XX +XXX,XX @@ static char *virtio_mmio_bus_get_dev_path(DeviceState *dev) } /* Otherwise, we append the base address of the transport. */ - proxy_sbd = SYS_BUS_DEVICE(virtio_mmio_proxy); - assert(proxy_sbd->num_mmio == 1); - assert(proxy_sbd->mmio[0].memory == &virtio_mmio_proxy->iomem); + section = memory_region_find(&virtio_mmio_proxy->iomem, 0, 0x200); + assert(section.mr); if (proxy_path) { path = g_strdup_printf("%s/virtio-mmio@" TARGET_FMT_plx, proxy_path, - proxy_sbd->mmio[0].addr); + section.offset_within_address_space); } else { path = g_strdup_printf("virtio-mmio@" TARGET_FMT_plx, - proxy_sbd->mmio[0].addr); + section.offset_within_address_space); } + memory_region_unref(section.mr); + g_free(proxy_path); return path; } -- 2.20.1 From: Peter Collingbourne <pcc@google.com> Section D6.7 of the ARM ARM states: For the purpose of determining Tag Check Fault handling, unprivileged load and store instructions are treated as if executed at EL0 when executed at either: - EL1, when the Effective value of PSTATE.UAO is 0. - EL2, when both the Effective value of HCR_EL2.{E2H, TGE} is {1, 1} and the Effective value of PSTATE.UAO is 0. ARM has confirmed a defect in the pseudocode function AArch64.TagCheckFault that makes it inconsistent with the above wording. The remedy is to adjust references to PSTATE.EL in that function to instead refer to AArch64.AccessUsesEL(acctype), so that unprivileged instructions use SCTLR_EL1.TCF0 and TFSRE0_EL1. The exception type for synchronous tag check faults remains unchanged. This patch implements the described change by partially reverting commits 50244cc76abc and cc97b0019bb5. Signed-off-by: Peter Collingbourne <pcc@google.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210219201820.2672077-1-pcc@google.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 2 +- target/arm/mte_helper.c | 13 +++++++++---- 2 files changed, 10 insertions(+), 5 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 uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, if (FIELD_EX32(flags, TBFLAG_A64, UNPRIV) && tbid && !(env->pstate & PSTATE_TCO) - && (sctlr & SCTLR_TCF) + && (sctlr & SCTLR_TCF0) && allocation_tag_access_enabled(env, 0, sctlr)) { flags = FIELD_DP32(flags, TBFLAG_A64, MTE0_ACTIVE, 1); } diff --git a/target/arm/mte_helper.c b/target/arm/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mte_helper.c +++ b/target/arm/mte_helper.c @@ -XXX,XX +XXX,XX @@ static void mte_check_fail(CPUARMState *env, uint32_t desc, reg_el = regime_el(env, arm_mmu_idx); sctlr = env->cp15.sctlr_el[reg_el]; - el = arm_current_el(env); - if (el == 0) { + switch (arm_mmu_idx) { + case ARMMMUIdx_E10_0: + case ARMMMUIdx_E20_0: + el = 0; tcf = extract64(sctlr, 38, 2); - } else { + break; + default: + el = reg_el; tcf = extract64(sctlr, 40, 2); } @@ -XXX,XX +XXX,XX @@ static void mte_check_fail(CPUARMState *env, uint32_t desc, env->exception.vaddress = dirty_ptr; is_write = FIELD_EX32(desc, MTEDESC, WRITE); - syn = syn_data_abort_no_iss(el != 0, 0, 0, 0, 0, is_write, 0x11); + syn = syn_data_abort_no_iss(arm_current_el(env) != 0, 0, 0, 0, 0, + is_write, 0x11); raise_exception(env, EXCP_DATA_ABORT, syn, exception_target_el(env)); /* noreturn, but fall through to the assert anyway */ -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> IDAU is specific to M-profile. KVM only supports A-profile. Restrict this interface to TCG, as it is pointless (and confusing) on a KVM-only build. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210221222617.2579610-2-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 7 ------- target/arm/cpu_tcg.c | 8 ++++++++ 2 files changed, 8 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 const TypeInfo arm_cpu_type_info = { .class_init = arm_cpu_class_init, }; -static const TypeInfo idau_interface_type_info = { - .name = TYPE_IDAU_INTERFACE, - .parent = TYPE_INTERFACE, - .class_size = sizeof(IDAUInterfaceClass), -}; - static void arm_cpu_register_types(void) { const size_t cpu_count = ARRAY_SIZE(arm_cpus); @@ -XXX,XX +XXX,XX @@ static void arm_cpu_register_types(void) if (cpu_count) { size_t i; - type_register_static(&idau_interface_type_info); for (i = 0; i < cpu_count; ++i) { arm_cpu_register(&arm_cpus[i]); } diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ #include "hw/core/tcg-cpu-ops.h" #endif /* CONFIG_TCG */ #include "internals.h" +#include "target/arm/idau.h" /* CPU models. These are not needed for the AArch64 linux-user build. */ #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64) @@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo arm_tcg_cpus[] = { { .name = "pxa270-c5", .initfn = pxa270c5_initfn }, }; +static const TypeInfo idau_interface_type_info = { + .name = TYPE_IDAU_INTERFACE, + .parent = TYPE_INTERFACE, + .class_size = sizeof(IDAUInterfaceClass), +}; + static void arm_tcg_cpu_register_types(void) { size_t i; + type_register_static(&idau_interface_type_info); for (i = 0; i < ARRAY_SIZE(arm_tcg_cpus); ++i) { arm_cpu_register(&arm_tcg_cpus[i]); } -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> We will move this code in the next commit. Clean it up first to avoid checkpatch.pl errors. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210221222617.2579610-3-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void cortex_a8_initfn(Object *obj) } static const ARMCPRegInfo cortexa9_cp_reginfo[] = { - /* power_control should be set to maximum latency. Again, + /* + * power_control should be set to maximum latency. Again, * default to 0 and set by private hook */ { .name = "A9_PWRCTL", .cp = 15, .crn = 15, .crm = 0, .opc1 = 0, .opc2 = 0, @@ -XXX,XX +XXX,XX @@ static void cortex_a9_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_EL3); - /* Note that A9 supports the MP extensions even for + /* + * Note that A9 supports the MP extensions even for * A9UP and single-core A9MP (which are both different * and valid configurations; we don't model A9UP). */ @@ -XXX,XX +XXX,XX @@ static uint64_t a15_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri) { MachineState *ms = MACHINE(qdev_get_machine()); - /* Linux wants the number of processors from here. + /* + * Linux wants the number of processors from here. * Might as well set the interrupt-controller bit too. */ return ((ms->smp.cpus - 1) << 24) | (1 << 23); @@ -XXX,XX +XXX,XX @@ static void cortex_a7_initfn(Object *obj) cpu->isar.id_mmfr1 = 0x40000000; cpu->isar.id_mmfr2 = 0x01240000; cpu->isar.id_mmfr3 = 0x02102211; - /* a7_mpcore_r0p5_trm, page 4-4 gives 0x01101110; but + /* + * a7_mpcore_r0p5_trm, page 4-4 gives 0x01101110; but * table 4-41 gives 0x02101110, which includes the arm div insns. */ cpu->isar.id_isar0 = 0x02101110; -- 2.20.1 For a long time now the UI layer has guaranteed that the console surface is always 32 bits per pixel RGB. Remove the legacy dead code from the milkymist display device which was handling the possibility that the console surface was some other format. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215103215.4944-2-peter.maydell@linaro.org --- hw/arm/musicpal.c | 64 ++++++++++++++++++----------------------------- 1 file changed, 24 insertions(+), 40 deletions(-) diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/musicpal.c +++ b/hw/arm/musicpal.c @@ -XXX,XX +XXX,XX @@ static uint8_t scale_lcd_color(musicpal_lcd_state *s, uint8_t col) } } -#define SET_LCD_PIXEL(depth, type) \ -static inline void glue(set_lcd_pixel, depth) \ - (musicpal_lcd_state *s, int x, int y, type col) \ -{ \ - int dx, dy; \ - DisplaySurface *surface = qemu_console_surface(s->con); \ - type *pixel = &((type *) surface_data(surface))[(y * 128 * 3 + x) * 3]; \ -\ - for (dy = 0; dy < 3; dy++, pixel += 127 * 3) \ - for (dx = 0; dx < 3; dx++, pixel++) \ - *pixel = col; \ +static inline void set_lcd_pixel32(musicpal_lcd_state *s, + int x, int y, uint32_t col) +{ + int dx, dy; + DisplaySurface *surface = qemu_console_surface(s->con); + uint32_t *pixel = + &((uint32_t *) surface_data(surface))[(y * 128 * 3 + x) * 3]; + + for (dy = 0; dy < 3; dy++, pixel += 127 * 3) { + for (dx = 0; dx < 3; dx++, pixel++) { + *pixel = col; + } + } } -SET_LCD_PIXEL(8, uint8_t) -SET_LCD_PIXEL(16, uint16_t) -SET_LCD_PIXEL(32, uint32_t) static void lcd_refresh(void *opaque) { musicpal_lcd_state *s = opaque; - DisplaySurface *surface = qemu_console_surface(s->con); int x, y, col; - switch (surface_bits_per_pixel(surface)) { - case 0: - return; -#define LCD_REFRESH(depth, func) \ - case depth: \ - col = func(scale_lcd_color(s, (MP_LCD_TEXTCOLOR >> 16) & 0xff), \ - scale_lcd_color(s, (MP_LCD_TEXTCOLOR >> 8) & 0xff), \ - scale_lcd_color(s, MP_LCD_TEXTCOLOR & 0xff)); \ - for (x = 0; x < 128; x++) { \ - for (y = 0; y < 64; y++) { \ - if (s->video_ram[x + (y/8)*128] & (1 << (y % 8))) { \ - glue(set_lcd_pixel, depth)(s, x, y, col); \ - } else { \ - glue(set_lcd_pixel, depth)(s, x, y, 0); \ - } \ - } \ - } \ - break; - LCD_REFRESH(8, rgb_to_pixel8) - LCD_REFRESH(16, rgb_to_pixel16) - LCD_REFRESH(32, (is_surface_bgr(surface) ? - rgb_to_pixel32bgr : rgb_to_pixel32)) - default: - hw_error("unsupported colour depth %i\n", - surface_bits_per_pixel(surface)); + col = rgb_to_pixel32(scale_lcd_color(s, (MP_LCD_TEXTCOLOR >> 16) & 0xff), + scale_lcd_color(s, (MP_LCD_TEXTCOLOR >> 8) & 0xff), + scale_lcd_color(s, MP_LCD_TEXTCOLOR & 0xff)); + for (x = 0; x < 128; x++) { + for (y = 0; y < 64; y++) { + if (s->video_ram[x + (y / 8) * 128] & (1 << (y % 8))) { + set_lcd_pixel32(s, x, y, col); + } else { + set_lcd_pixel32(s, x, y, 0); + } + } } dpy_gfx_update(s->con, 0, 0, 128*3, 64*3); -- 2.20.1 For a long time now the UI layer has guaranteed that the console surface is always 32 bits per pixel RGB. Remove the legacy dead code from the tc6393xb display device which was handling the possibility that the console surface was some other format. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215103215.4944-3-peter.maydell@linaro.org --- include/ui/console.h | 10 ---------- hw/display/tc6393xb.c | 33 +-------------------------------- 2 files changed, 1 insertion(+), 42 deletions(-) diff --git a/include/ui/console.h b/include/ui/console.h index XXXXXXX..XXXXXXX 100644 --- a/include/ui/console.h +++ b/include/ui/console.h @@ -XXX,XX +XXX,XX @@ PixelFormat qemu_default_pixelformat(int bpp); DisplaySurface *qemu_create_displaysurface(int width, int height); void qemu_free_displaysurface(DisplaySurface *surface); -static inline int is_surface_bgr(DisplaySurface *surface) -{ - if (PIXMAN_FORMAT_BPP(surface->format) == 32 && - PIXMAN_FORMAT_TYPE(surface->format) == PIXMAN_TYPE_ABGR) { - return 1; - } else { - return 0; - } -} - static inline int is_buffer_shared(DisplaySurface *surface) { return !(surface->flags & QEMU_ALLOCATED_FLAG); diff --git a/hw/display/tc6393xb.c b/hw/display/tc6393xb.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/tc6393xb.c +++ b/hw/display/tc6393xb.c @@ -XXX,XX +XXX,XX @@ static void tc6393xb_nand_writeb(TC6393xbState *s, hwaddr addr, uint32_t value) (uint32_t) addr, value & 0xff); } -#define BITS 8 -#include "tc6393xb_template.h" -#define BITS 15 -#include "tc6393xb_template.h" -#define BITS 16 -#include "tc6393xb_template.h" -#define BITS 24 -#include "tc6393xb_template.h" #define BITS 32 #include "tc6393xb_template.h" static void tc6393xb_draw_graphic(TC6393xbState *s, int full_update) { - DisplaySurface *surface = qemu_console_surface(s->con); - - switch (surface_bits_per_pixel(surface)) { - case 8: - tc6393xb_draw_graphic8(s); - break; - case 15: - tc6393xb_draw_graphic15(s); - break; - case 16: - tc6393xb_draw_graphic16(s); - break; - case 24: - tc6393xb_draw_graphic24(s); - break; - case 32: - tc6393xb_draw_graphic32(s); - break; - default: - printf("tc6393xb: unknown depth %d\n", - surface_bits_per_pixel(surface)); - return; - } - + tc6393xb_draw_graphic32(s); dpy_gfx_update_full(s->con); } -- 2.20.1 Now the template header is included only for BITS==32, expand out all the macros that depended on the BITS setting. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215103215.4944-4-peter.maydell@linaro.org --- hw/display/tc6393xb_template.h | 35 ++++------------------------------ 1 file changed, 4 insertions(+), 31 deletions(-) diff --git a/hw/display/tc6393xb_template.h b/hw/display/tc6393xb_template.h index XXXXXXX..XXXXXXX 100644 --- a/hw/display/tc6393xb_template.h +++ b/hw/display/tc6393xb_template.h @@ -XXX,XX +XXX,XX @@ * with this program; if not, see <http://www.gnu.org/licenses/>. */ -#if BITS == 8 -# define SET_PIXEL(addr, color) (*(uint8_t *)addr = color) -#elif BITS == 15 || BITS == 16 -# define SET_PIXEL(addr, color) (*(uint16_t *)addr = color) -#elif BITS == 24 -# define SET_PIXEL(addr, color) \ - do { \ - addr[0] = color; \ - addr[1] = (color) >> 8; \ - addr[2] = (color) >> 16; \ - } while (0) -#elif BITS == 32 -# define SET_PIXEL(addr, color) (*(uint32_t *)addr = color) -#else -# error unknown bit depth -#endif - - -static void glue(tc6393xb_draw_graphic, BITS)(TC6393xbState *s) +static void tc6393xb_draw_graphic32(TC6393xbState *s) { DisplaySurface *surface = qemu_console_surface(s->con); int i; @@ -XXX,XX +XXX,XX @@ static void glue(tc6393xb_draw_graphic, BITS)(TC6393xbState *s) data_buffer = s->vram_ptr; data_display = surface_data(surface); for(i = 0; i < s->scr_height; i++) { -#if (BITS == 16) - memcpy(data_display, data_buffer, s->scr_width * 2); - data_buffer += s->scr_width; - data_display += surface_stride(surface); -#else int j; - for (j = 0; j < s->scr_width; j++, data_display += BITS / 8, data_buffer++) { + for (j = 0; j < s->scr_width; j++, data_display += 4, data_buffer++) { uint16_t color = *data_buffer; - uint32_t dest_color = glue(rgb_to_pixel, BITS)( + uint32_t dest_color = rgb_to_pixel32( ((color & 0xf800) * 0x108) >> 11, ((color & 0x7e0) * 0x41) >> 9, ((color & 0x1f) * 0x21) >> 2 ); - SET_PIXEL(data_display, dest_color); + *(uint32_t *)data_display = dest_color; } -#endif } } - -#undef BITS -#undef SET_PIXEL -- 2.20.1 The function tc6393xb_draw_graphic32() is called in exactly one place, so just inline the function body at its callsite. This allows us to drop the template header entirely. The code move includes a single added space after 'for' to fix the coding style. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210215103215.4944-5-peter.maydell@linaro.org --- hw/display/tc6393xb_template.h | 45 ---------------------------------- hw/display/tc6393xb.c | 23 ++++++++++++++--- 2 files changed, 19 insertions(+), 49 deletions(-) delete mode 100644 hw/display/tc6393xb_template.h diff --git a/hw/display/tc6393xb_template.h b/hw/display/tc6393xb_template.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/display/tc6393xb_template.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Toshiba TC6393XB I/O Controller. - * Found in Sharp Zaurus SL-6000 (tosa) or some - * Toshiba e-Series PDAs. - * - * FB support code. Based on G364 fb emulator - * - * Copyright (c) 2007 Hervé Poussineau - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of - * the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -static void tc6393xb_draw_graphic32(TC6393xbState *s) -{ - DisplaySurface *surface = qemu_console_surface(s->con); - int i; - uint16_t *data_buffer; - uint8_t *data_display; - - data_buffer = s->vram_ptr; - data_display = surface_data(surface); - for(i = 0; i < s->scr_height; i++) { - int j; - for (j = 0; j < s->scr_width; j++, data_display += 4, data_buffer++) { - uint16_t color = *data_buffer; - uint32_t dest_color = rgb_to_pixel32( - ((color & 0xf800) * 0x108) >> 11, - ((color & 0x7e0) * 0x41) >> 9, - ((color & 0x1f) * 0x21) >> 2 - ); - *(uint32_t *)data_display = dest_color; - } - } -} diff --git a/hw/display/tc6393xb.c b/hw/display/tc6393xb.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/tc6393xb.c +++ b/hw/display/tc6393xb.c @@ -XXX,XX +XXX,XX @@ static void tc6393xb_nand_writeb(TC6393xbState *s, hwaddr addr, uint32_t value) (uint32_t) addr, value & 0xff); } -#define BITS 32 -#include "tc6393xb_template.h" - static void tc6393xb_draw_graphic(TC6393xbState *s, int full_update) { - tc6393xb_draw_graphic32(s); + DisplaySurface *surface = qemu_console_surface(s->con); + int i; + uint16_t *data_buffer; + uint8_t *data_display; + + data_buffer = s->vram_ptr; + data_display = surface_data(surface); + for (i = 0; i < s->scr_height; i++) { + int j; + for (j = 0; j < s->scr_width; j++, data_display += 4, data_buffer++) { + uint16_t color = *data_buffer; + uint32_t dest_color = rgb_to_pixel32( + ((color & 0xf800) * 0x108) >> 11, + ((color & 0x7e0) * 0x41) >> 9, + ((color & 0x1f) * 0x21) >> 2 + ); + *(uint32_t *)data_display = dest_color; + } + } dpy_gfx_update_full(s->con); } -- 2.20.1 The omap_lcdc template header is already only included once, for DEPTH==32, but it still has all the macro-driven parameterization for other depths. Expand out all the macros in the header. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210215103215.4944-6-peter.maydell@linaro.org --- hw/display/omap_lcd_template.h | 67 ++++++++++++++-------------------- 1 file changed, 28 insertions(+), 39 deletions(-) diff --git a/hw/display/omap_lcd_template.h b/hw/display/omap_lcd_template.h index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcd_template.h +++ b/hw/display/omap_lcd_template.h @@ -XXX,XX +XXX,XX @@ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ -#if DEPTH == 32 -# define BPP 4 -# define PIXEL_TYPE uint32_t -#else -# error unsupport depth -#endif - /* * 2-bit colour */ -static void glue(draw_line2_, DEPTH)(void *opaque, - uint8_t *d, const uint8_t *s, int width, int deststep) +static void draw_line2_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) { uint16_t *pal = opaque; uint8_t v, r, g, b; @@ -XXX,XX +XXX,XX @@ static void glue(draw_line2_, DEPTH)(void *opaque, r = (pal[v & 3] >> 4) & 0xf0; g = pal[v & 3] & 0xf0; b = (pal[v & 3] << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); - d += BPP; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; v >>= 2; r = (pal[v & 3] >> 4) & 0xf0; g = pal[v & 3] & 0xf0; b = (pal[v & 3] << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); - d += BPP; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; v >>= 2; r = (pal[v & 3] >> 4) & 0xf0; g = pal[v & 3] & 0xf0; b = (pal[v & 3] << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); - d += BPP; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; v >>= 2; r = (pal[v & 3] >> 4) & 0xf0; g = pal[v & 3] & 0xf0; b = (pal[v & 3] << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); - d += BPP; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; s ++; width -= 4; } while (width > 0); @@ -XXX,XX +XXX,XX @@ static void glue(draw_line2_, DEPTH)(void *opaque, /* * 4-bit colour */ -static void glue(draw_line4_, DEPTH)(void *opaque, - uint8_t *d, const uint8_t *s, int width, int deststep) +static void draw_line4_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) { uint16_t *pal = opaque; uint8_t v, r, g, b; @@ -XXX,XX +XXX,XX @@ static void glue(draw_line4_, DEPTH)(void *opaque, r = (pal[v & 0xf] >> 4) & 0xf0; g = pal[v & 0xf] & 0xf0; b = (pal[v & 0xf] << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); - d += BPP; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; v >>= 4; r = (pal[v & 0xf] >> 4) & 0xf0; g = pal[v & 0xf] & 0xf0; b = (pal[v & 0xf] << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); - d += BPP; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; s ++; width -= 2; } while (width > 0); @@ -XXX,XX +XXX,XX @@ static void glue(draw_line4_, DEPTH)(void *opaque, /* * 8-bit colour */ -static void glue(draw_line8_, DEPTH)(void *opaque, - uint8_t *d, const uint8_t *s, int width, int deststep) +static void draw_line8_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) { uint16_t *pal = opaque; uint8_t v, r, g, b; @@ -XXX,XX +XXX,XX @@ static void glue(draw_line8_, DEPTH)(void *opaque, r = (pal[v] >> 4) & 0xf0; g = pal[v] & 0xf0; b = (pal[v] << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); s ++; - d += BPP; + d += 4; } while (-- width != 0); } /* * 12-bit colour */ -static void glue(draw_line12_, DEPTH)(void *opaque, - uint8_t *d, const uint8_t *s, int width, int deststep) +static void draw_line12_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) { uint16_t v; uint8_t r, g, b; @@ -XXX,XX +XXX,XX @@ static void glue(draw_line12_, DEPTH)(void *opaque, r = (v >> 4) & 0xf0; g = v & 0xf0; b = (v << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); s += 2; - d += BPP; + d += 4; } while (-- width != 0); } /* * 16-bit colour */ -static void glue(draw_line16_, DEPTH)(void *opaque, - uint8_t *d, const uint8_t *s, int width, int deststep) +static void draw_line16_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) { #if defined(HOST_WORDS_BIGENDIAN) == defined(TARGET_WORDS_BIGENDIAN) memcpy(d, s, width * 2); @@ -XXX,XX +XXX,XX @@ static void glue(draw_line16_, DEPTH)(void *opaque, r = (v >> 8) & 0xf8; g = (v >> 3) & 0xfc; b = (v << 3) & 0xf8; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); s += 2; - d += BPP; + d += 4; } while (-- width != 0); #endif } - -#undef DEPTH -#undef BPP -#undef PIXEL_TYPE -- 2.20.1 The draw_line16_32() function in the omap_lcdc template header includes an ifdef for the case where HOST_WORDS_BIGENDIAN matches TARGET_WORDS_BIGENDIAN. This is trying to optimise for "source bitmap and destination bitmap format match", but it is broken, because in this function the formats don't match: the source is 16-bit colour and the destination is 32-bit colour, so a memcpy() will produce corrupted graphics output. Drop the bogus ifdef. This bug was introduced in commit ea644cf343129, when we dropped support for DEPTH values other than 32 from the template header. The old #if line was #if DEPTH == 16 && defined(HOST_WORDS_BIGENDIAN) == defined(TARGET_WORDS_BIGENDIAN) and this was mistakenly changed to #if defined(HOST_WORDS_BIGENDIAN) == defined(TARGET_WORDS_BIGENDIAN) rather than deleting the #if as now having an always-false condition. Fixes: ea644cf343129 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210215103215.4944-7-peter.maydell@linaro.org --- hw/display/omap_lcd_template.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/hw/display/omap_lcd_template.h b/hw/display/omap_lcd_template.h index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcd_template.h +++ b/hw/display/omap_lcd_template.h @@ -XXX,XX +XXX,XX @@ static void draw_line12_32(void *opaque, uint8_t *d, const uint8_t *s, static void draw_line16_32(void *opaque, uint8_t *d, const uint8_t *s, int width, int deststep) { -#if defined(HOST_WORDS_BIGENDIAN) == defined(TARGET_WORDS_BIGENDIAN) - memcpy(d, s, width * 2); -#else uint16_t v; uint8_t r, g, b; @@ -XXX,XX +XXX,XX @@ static void draw_line16_32(void *opaque, uint8_t *d, const uint8_t *s, s += 2; d += 4; } while (-- width != 0); -#endif } -- 2.20.1 Fix some minor coding style issues in the template header, so checkpatch doesn't complain when we move the code. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210215103215.4944-8-peter.maydell@linaro.org --- hw/display/omap_lcd_template.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/hw/display/omap_lcd_template.h b/hw/display/omap_lcd_template.h index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcd_template.h +++ b/hw/display/omap_lcd_template.h @@ -XXX,XX +XXX,XX @@ static void draw_line2_32(void *opaque, uint8_t *d, const uint8_t *s, b = (pal[v & 3] << 4) & 0xf0; ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); d += 4; - s ++; + s++; width -= 4; } while (width > 0); } @@ -XXX,XX +XXX,XX @@ static void draw_line4_32(void *opaque, uint8_t *d, const uint8_t *s, b = (pal[v & 0xf] << 4) & 0xf0; ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); d += 4; - s ++; + s++; width -= 2; } while (width > 0); } @@ -XXX,XX +XXX,XX @@ static void draw_line8_32(void *opaque, uint8_t *d, const uint8_t *s, g = pal[v] & 0xf0; b = (pal[v] << 4) & 0xf0; ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - s ++; + s++; d += 4; } while (-- width != 0); } -- 2.20.1 We only include the template header once, so just inline it into the source file for the device. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210215103215.4944-9-peter.maydell@linaro.org --- hw/display/omap_lcd_template.h | 154 --------------------------------- hw/display/omap_lcdc.c | 127 ++++++++++++++++++++++++++- 2 files changed, 125 insertions(+), 156 deletions(-) delete mode 100644 hw/display/omap_lcd_template.h diff --git a/hw/display/omap_lcd_template.h b/hw/display/omap_lcd_template.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/display/omap_lcd_template.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * QEMU OMAP LCD Emulator templates - * - * Copyright (c) 2006 Andrzej Zaborowski <balrog@zabor.org> - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, - * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A - * PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR - * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, - * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, - * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR - * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY - * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -/* - * 2-bit colour - */ -static void draw_line2_32(void *opaque, uint8_t *d, const uint8_t *s, - int width, int deststep) -{ - uint16_t *pal = opaque; - uint8_t v, r, g, b; - - do { - v = ldub_p((void *) s); - r = (pal[v & 3] >> 4) & 0xf0; - g = pal[v & 3] & 0xf0; - b = (pal[v & 3] << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - d += 4; - v >>= 2; - r = (pal[v & 3] >> 4) & 0xf0; - g = pal[v & 3] & 0xf0; - b = (pal[v & 3] << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - d += 4; - v >>= 2; - r = (pal[v & 3] >> 4) & 0xf0; - g = pal[v & 3] & 0xf0; - b = (pal[v & 3] << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - d += 4; - v >>= 2; - r = (pal[v & 3] >> 4) & 0xf0; - g = pal[v & 3] & 0xf0; - b = (pal[v & 3] << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - d += 4; - s++; - width -= 4; - } while (width > 0); -} - -/* - * 4-bit colour - */ -static void draw_line4_32(void *opaque, uint8_t *d, const uint8_t *s, - int width, int deststep) -{ - uint16_t *pal = opaque; - uint8_t v, r, g, b; - - do { - v = ldub_p((void *) s); - r = (pal[v & 0xf] >> 4) & 0xf0; - g = pal[v & 0xf] & 0xf0; - b = (pal[v & 0xf] << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - d += 4; - v >>= 4; - r = (pal[v & 0xf] >> 4) & 0xf0; - g = pal[v & 0xf] & 0xf0; - b = (pal[v & 0xf] << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - d += 4; - s++; - width -= 2; - } while (width > 0); -} - -/* - * 8-bit colour - */ -static void draw_line8_32(void *opaque, uint8_t *d, const uint8_t *s, - int width, int deststep) -{ - uint16_t *pal = opaque; - uint8_t v, r, g, b; - - do { - v = ldub_p((void *) s); - r = (pal[v] >> 4) & 0xf0; - g = pal[v] & 0xf0; - b = (pal[v] << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - s++; - d += 4; - } while (-- width != 0); -} - -/* - * 12-bit colour - */ -static void draw_line12_32(void *opaque, uint8_t *d, const uint8_t *s, - int width, int deststep) -{ - uint16_t v; - uint8_t r, g, b; - - do { - v = lduw_le_p((void *) s); - r = (v >> 4) & 0xf0; - g = v & 0xf0; - b = (v << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - s += 2; - d += 4; - } while (-- width != 0); -} - -/* - * 16-bit colour - */ -static void draw_line16_32(void *opaque, uint8_t *d, const uint8_t *s, - int width, int deststep) -{ - uint16_t v; - uint8_t r, g, b; - - do { - v = lduw_le_p((void *) s); - r = (v >> 8) & 0xf8; - g = (v >> 3) & 0xfc; - b = (v << 3) & 0xf8; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - s += 2; - d += 4; - } while (-- width != 0); -} diff --git a/hw/display/omap_lcdc.c b/hw/display/omap_lcdc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcdc.c +++ b/hw/display/omap_lcdc.c @@ -XXX,XX +XXX,XX @@ static void omap_lcd_interrupts(struct omap_lcd_panel_s *s) #define draw_line_func drawfn -#define DEPTH 32 -#include "omap_lcd_template.h" +/* + * 2-bit colour + */ +static void draw_line2_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) +{ + uint16_t *pal = opaque; + uint8_t v, r, g, b; + + do { + v = ldub_p((void *) s); + r = (pal[v & 3] >> 4) & 0xf0; + g = pal[v & 3] & 0xf0; + b = (pal[v & 3] << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; + v >>= 2; + r = (pal[v & 3] >> 4) & 0xf0; + g = pal[v & 3] & 0xf0; + b = (pal[v & 3] << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; + v >>= 2; + r = (pal[v & 3] >> 4) & 0xf0; + g = pal[v & 3] & 0xf0; + b = (pal[v & 3] << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; + v >>= 2; + r = (pal[v & 3] >> 4) & 0xf0; + g = pal[v & 3] & 0xf0; + b = (pal[v & 3] << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; + s++; + width -= 4; + } while (width > 0); +} + +/* + * 4-bit colour + */ +static void draw_line4_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) +{ + uint16_t *pal = opaque; + uint8_t v, r, g, b; + + do { + v = ldub_p((void *) s); + r = (pal[v & 0xf] >> 4) & 0xf0; + g = pal[v & 0xf] & 0xf0; + b = (pal[v & 0xf] << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; + v >>= 4; + r = (pal[v & 0xf] >> 4) & 0xf0; + g = pal[v & 0xf] & 0xf0; + b = (pal[v & 0xf] << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; + s++; + width -= 2; + } while (width > 0); +} + +/* + * 8-bit colour + */ +static void draw_line8_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) +{ + uint16_t *pal = opaque; + uint8_t v, r, g, b; + + do { + v = ldub_p((void *) s); + r = (pal[v] >> 4) & 0xf0; + g = pal[v] & 0xf0; + b = (pal[v] << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + s++; + d += 4; + } while (-- width != 0); +} + +/* + * 12-bit colour + */ +static void draw_line12_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) +{ + uint16_t v; + uint8_t r, g, b; + + do { + v = lduw_le_p((void *) s); + r = (v >> 4) & 0xf0; + g = v & 0xf0; + b = (v << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + s += 2; + d += 4; + } while (-- width != 0); +} + +/* + * 16-bit colour + */ +static void draw_line16_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) +{ + uint16_t v; + uint8_t r, g, b; + + do { + v = lduw_le_p((void *) s); + r = (v >> 8) & 0xf8; + g = (v >> 3) & 0xfc; + b = (v << 3) & 0xf8; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + s += 2; + d += 4; + } while (-- width != 0); +} static void omap_update_display(void *opaque) { -- 2.20.1 The macro draw_line_func is used only once; just expand it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210215103215.4944-10-peter.maydell@linaro.org --- hw/display/omap_lcdc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/hw/display/omap_lcdc.c b/hw/display/omap_lcdc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcdc.c +++ b/hw/display/omap_lcdc.c @@ -XXX,XX +XXX,XX @@ static void omap_lcd_interrupts(struct omap_lcd_panel_s *s) qemu_irq_lower(s->irq); } -#define draw_line_func drawfn - /* * 2-bit colour */ @@ -XXX,XX +XXX,XX @@ static void omap_update_display(void *opaque) { struct omap_lcd_panel_s *omap_lcd = (struct omap_lcd_panel_s *) opaque; DisplaySurface *surface; - draw_line_func draw_line; + drawfn draw_line; int size, height, first, last; int width, linesize, step, bpp, frame_offset; hwaddr frame_base; -- 2.20.1 For a long time now the UI layer has guaranteed that the console surface is always 32 bits per pixel, RGB. The TCX code already assumes 32bpp, but it still has some checks of is_surface_bgr() in an attempt to support 32bpp BGR. is_surface_bgr() will always return false for the qemu_console_surface(), unless the display device itself has deliberately created an alternate-format surface via a function like qemu_create_displaysurface_from(). Drop the never-used BGR-handling code, and assert that we have a 32-bit surface rather than just doing nothing if it isn't. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215102149.20513-1-peter.maydell@linaro.org --- hw/display/tcx.c | 31 ++++++++----------------------- 1 file changed, 8 insertions(+), 23 deletions(-) diff --git a/hw/display/tcx.c b/hw/display/tcx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/tcx.c +++ b/hw/display/tcx.c @@ -XXX,XX +XXX,XX @@ static int tcx_check_dirty(TCXState *s, DirtyBitmapSnapshot *snap, static void update_palette_entries(TCXState *s, int start, int end) { - DisplaySurface *surface = qemu_console_surface(s->con); int i; for (i = start; i < end; i++) { - if (is_surface_bgr(surface)) { - s->palette[i] = rgb_to_pixel32bgr(s->r[i], s->g[i], s->b[i]); - } else { - s->palette[i] = rgb_to_pixel32(s->r[i], s->g[i], s->b[i]); - } + s->palette[i] = rgb_to_pixel32(s->r[i], s->g[i], s->b[i]); } tcx_set_dirty(s, 0, memory_region_size(&s->vram_mem)); } @@ -XXX,XX +XXX,XX @@ static void tcx_draw_cursor32(TCXState *s1, uint8_t *d, } /* - XXX Could be much more optimal: - * detect if line/page/whole screen is in 24 bit mode - * if destination is also BGR, use memcpy - */ + * XXX Could be much more optimal: + * detect if line/page/whole screen is in 24 bit mode + */ static inline void tcx24_draw_line32(TCXState *s1, uint8_t *d, const uint8_t *s, int width, const uint32_t *cplane, const uint32_t *s24) { - DisplaySurface *surface = qemu_console_surface(s1->con); - int x, bgr, r, g, b; + int x, r, g, b; uint8_t val, *p8; uint32_t *p = (uint32_t *)d; uint32_t dval; - bgr = is_surface_bgr(surface); for(x = 0; x < width; x++, s++, s24++) { if (be32_to_cpu(*cplane) & 0x03000000) { /* 24-bit direct, BGR order */ @@ -XXX,XX +XXX,XX @@ static inline void tcx24_draw_line32(TCXState *s1, uint8_t *d, b = *p8++; g = *p8++; r = *p8; - if (bgr) - dval = rgb_to_pixel32bgr(r, g, b); - else - dval = rgb_to_pixel32(r, g, b); + dval = rgb_to_pixel32(r, g, b); } else { /* 8-bit pseudocolor */ val = *s; @@ -XXX,XX +XXX,XX @@ static void tcx_update_display(void *opaque) int y, y_start, dd, ds; uint8_t *d, *s; - if (surface_bits_per_pixel(surface) != 32) { - return; - } + assert(surface_bits_per_pixel(surface) == 32); page = 0; y_start = -1; @@ -XXX,XX +XXX,XX @@ static void tcx24_update_display(void *opaque) uint8_t *d, *s; uint32_t *cptr, *s24; - if (surface_bits_per_pixel(surface) != 32) { - return; - } + assert(surface_bits_per_pixel(surface) == 32); page = 0; y_start = -1; -- 2.20.1 The AN524 has a different SYSCLK frequency from the AN505 and AN521; make the SYSCLK frequency a field in the MPS2TZMachineClass rather than a compile-time constant so we can support the AN524. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-2-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass { MachineClass parent; MPS2TZFPGAType fpga_type; uint32_t scc_id; + uint32_t sysclk_frq; /* Main SYSCLK frequency in Hz */ const char *armsse_type; }; @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { OBJECT_DECLARE_TYPE(MPS2TZMachineState, MPS2TZMachineClass, MPS2TZ_MACHINE) -/* Main SYSCLK frequency in Hz */ -#define SYSCLK_FRQ 20000000 /* Slow 32Khz S32KCLK frequency in Hz */ #define S32KCLK_FRQ (32 * 1000) @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_unimp_dev(MPS2TZMachineState *mms, static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size) { + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); CMSDKAPBUART *uart = opaque; int i = uart - &mms->uart[0]; int rxirqno = i * 2; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, object_initialize_child(OBJECT(mms), name, uart, TYPE_CMSDK_APB_UART); qdev_prop_set_chr(DEVICE(uart), "chardev", serial_hd(i)); - qdev_prop_set_uint32(DEVICE(uart), "pclk-frq", SYSCLK_FRQ); + qdev_prop_set_uint32(DEVICE(uart), "pclk-frq", mmc->sysclk_frq); sysbus_realize(SYS_BUS_DEVICE(uart), &error_fatal); s = SYS_BUS_DEVICE(uart); sysbus_connect_irq(s, 0, get_sse_irq_in(mms, txirqno)); @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) /* These clocks don't need migration because they are fixed-frequency */ mms->sysclk = clock_new(OBJECT(machine), "SYSCLK"); - clock_set_hz(mms->sysclk, SYSCLK_FRQ); + clock_set_hz(mms->sysclk, mmc->sysclk_frq); mms->s32kclk = clock_new(OBJECT(machine), "S32KCLK"); clock_set_hz(mms->s32kclk, S32KCLK_FRQ); @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mmc->fpga_type = FPGA_AN505; mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"); mmc->scc_id = 0x41045050; + mmc->sysclk_frq = 20 * 1000 * 1000; /* 20MHz */ mmc->armsse_type = TYPE_IOTKIT; } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mmc->fpga_type = FPGA_AN521; mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"); mmc->scc_id = 0x41045210; + mmc->sysclk_frq = 20 * 1000 * 1000; /* 20MHz */ mmc->armsse_type = TYPE_SSE200; } -- 2.20.1 Currently the MPS2 SCC device implements a fixed number of OSCCLK values (3). The variant of this device in the MPS3 AN524 board has 6 OSCCLK values. Switch to using a PROP_ARRAY, which allows board code to specify how large the OSCCLK array should be as well as its values. With a variable-length property array, the SCC no longer specifies default values for the OSCCLKs, so we must set them explicitly in the board code. This defaults are actually incorrect for the an521 and an505; we will correct this bug in a following patch. This is a migration compatibility break for all the mps boards. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-3-peter.maydell@linaro.org --- include/hw/misc/mps2-scc.h | 7 +++---- hw/arm/mps2-tz.c | 5 +++++ hw/arm/mps2.c | 5 +++++ hw/misc/mps2-scc.c | 24 +++++++++++++----------- 4 files changed, 26 insertions(+), 15 deletions(-) diff --git a/include/hw/misc/mps2-scc.h b/include/hw/misc/mps2-scc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/mps2-scc.h +++ b/include/hw/misc/mps2-scc.h @@ -XXX,XX +XXX,XX @@ #define TYPE_MPS2_SCC "mps2-scc" OBJECT_DECLARE_SIMPLE_TYPE(MPS2SCC, MPS2_SCC) -#define NUM_OSCCLK 3 - struct MPS2SCC { /*< private >*/ SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct MPS2SCC { uint32_t dll; uint32_t aid; uint32_t id; - uint32_t oscclk[NUM_OSCCLK]; - uint32_t oscclk_reset[NUM_OSCCLK]; + uint32_t num_oscclk; + uint32_t *oscclk; + uint32_t *oscclk_reset; }; #endif diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, qdev_prop_set_uint32(sccdev, "scc-cfg4", 0x2); qdev_prop_set_uint32(sccdev, "scc-aid", 0x00200008); qdev_prop_set_uint32(sccdev, "scc-id", mmc->scc_id); + /* This will need to be per-FPGA image eventually */ + qdev_prop_set_uint32(sccdev, "len-oscclk", 3); + qdev_prop_set_uint32(sccdev, "oscclk[0]", 50000000); + qdev_prop_set_uint32(sccdev, "oscclk[1]", 24576000); + qdev_prop_set_uint32(sccdev, "oscclk[2]", 25000000); sysbus_realize(SYS_BUS_DEVICE(scc), &error_fatal); return sysbus_mmio_get_region(SYS_BUS_DEVICE(sccdev), 0); } diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2.c +++ b/hw/arm/mps2.c @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) qdev_prop_set_uint32(sccdev, "scc-cfg4", 0x2); qdev_prop_set_uint32(sccdev, "scc-aid", 0x00200008); qdev_prop_set_uint32(sccdev, "scc-id", mmc->scc_id); + /* All these FPGA images have the same OSCCLK configuration */ + qdev_prop_set_uint32(sccdev, "len-oscclk", 3); + qdev_prop_set_uint32(sccdev, "oscclk[0]", 50000000); + qdev_prop_set_uint32(sccdev, "oscclk[1]", 24576000); + qdev_prop_set_uint32(sccdev, "oscclk[2]", 25000000); sysbus_realize(SYS_BUS_DEVICE(&mms->scc), &error_fatal); sysbus_mmio_map(SYS_BUS_DEVICE(sccdev), 0, 0x4002f000); object_initialize_child(OBJECT(mms), "fpgaio", diff --git a/hw/misc/mps2-scc.c b/hw/misc/mps2-scc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mps2-scc.c +++ b/hw/misc/mps2-scc.c @@ -XXX,XX +XXX,XX @@ static bool scc_cfg_write(MPS2SCC *s, unsigned function, { trace_mps2_scc_cfg_write(function, device, value); - if (function != 1 || device >= NUM_OSCCLK) { + if (function != 1 || device >= s->num_oscclk) { qemu_log_mask(LOG_GUEST_ERROR, "MPS2 SCC config write: bad function %d device %d\n", function, device); @@ -XXX,XX +XXX,XX @@ static bool scc_cfg_write(MPS2SCC *s, unsigned function, static bool scc_cfg_read(MPS2SCC *s, unsigned function, unsigned device, uint32_t *value) { - if (function != 1 || device >= NUM_OSCCLK) { + if (function != 1 || device >= s->num_oscclk) { qemu_log_mask(LOG_GUEST_ERROR, "MPS2 SCC config read: bad function %d device %d\n", function, device); @@ -XXX,XX +XXX,XX @@ static void mps2_scc_reset(DeviceState *dev) s->cfgctrl = 0x100000; s->cfgstat = 0; s->dll = 0xffff0001; - for (i = 0; i < NUM_OSCCLK; i++) { + for (i = 0; i < s->num_oscclk; i++) { s->oscclk[i] = s->oscclk_reset[i]; } for (i = 0; i < ARRAY_SIZE(s->led); i++) { @@ -XXX,XX +XXX,XX @@ static void mps2_scc_realize(DeviceState *dev, Error **errp) LED_COLOR_GREEN, name); g_free(name); } + + s->oscclk = g_new0(uint32_t, s->num_oscclk); } static const VMStateDescription mps2_scc_vmstate = { .name = "mps2-scc", - .version_id = 1, - .minimum_version_id = 1, + .version_id = 2, + .minimum_version_id = 2, .fields = (VMStateField[]) { VMSTATE_UINT32(cfg0, MPS2SCC), VMSTATE_UINT32(cfg1, MPS2SCC), @@ -XXX,XX +XXX,XX @@ static const VMStateDescription mps2_scc_vmstate = { VMSTATE_UINT32(cfgctrl, MPS2SCC), VMSTATE_UINT32(cfgstat, MPS2SCC), VMSTATE_UINT32(dll, MPS2SCC), - VMSTATE_UINT32_ARRAY(oscclk, MPS2SCC, NUM_OSCCLK), + VMSTATE_VARRAY_UINT32(oscclk, MPS2SCC, num_oscclk, + 0, vmstate_info_uint32, uint32_t), VMSTATE_END_OF_LIST() } }; @@ -XXX,XX +XXX,XX @@ static Property mps2_scc_properties[] = { DEFINE_PROP_UINT32("scc-cfg4", MPS2SCC, cfg4, 0), DEFINE_PROP_UINT32("scc-aid", MPS2SCC, aid, 0), DEFINE_PROP_UINT32("scc-id", MPS2SCC, id, 0), - /* These are the initial settings for the source clocks on the board. + /* + * These are the initial settings for the source clocks on the board. * In hardware they can be configured via a config file read by the * motherboard configuration controller to suit the FPGA image. - * These default values are used by most of the standard FPGA images. */ - DEFINE_PROP_UINT32("oscclk0", MPS2SCC, oscclk_reset[0], 50000000), - DEFINE_PROP_UINT32("oscclk1", MPS2SCC, oscclk_reset[1], 24576000), - DEFINE_PROP_UINT32("oscclk2", MPS2SCC, oscclk_reset[2], 25000000), + DEFINE_PROP_ARRAY("oscclk", MPS2SCC, num_oscclk, oscclk_reset, + qdev_prop_uint32, uint32_t), DEFINE_PROP_END_OF_LIST(), }; -- 2.20.1 We were previously using the default OSCCLK settings, which are correct for the older MPS2 boards (mps2-an385, mps2-an386, mps2-an500, mps2-an511), but wrong for the mps2-an505 and mps2-511 implemented in mps2-tz.c. Now we're setting the values explicitly we can fix them to be correct. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-4-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, qdev_prop_set_uint32(sccdev, "scc-id", mmc->scc_id); /* This will need to be per-FPGA image eventually */ qdev_prop_set_uint32(sccdev, "len-oscclk", 3); - qdev_prop_set_uint32(sccdev, "oscclk[0]", 50000000); - qdev_prop_set_uint32(sccdev, "oscclk[1]", 24576000); + qdev_prop_set_uint32(sccdev, "oscclk[0]", 40000000); + qdev_prop_set_uint32(sccdev, "oscclk[1]", 24580000); qdev_prop_set_uint32(sccdev, "oscclk[2]", 25000000); sysbus_realize(SYS_BUS_DEVICE(scc), &error_fatal); return sysbus_mmio_get_region(SYS_BUS_DEVICE(sccdev), 0); -- 2.20.1 The AN505 and AN511 happen to share the same OSCCLK values, but the AN524 will have a different set (and more of them), so split the settings out to be per-board. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-5-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass { MPS2TZFPGAType fpga_type; uint32_t scc_id; uint32_t sysclk_frq; /* Main SYSCLK frequency in Hz */ + uint32_t len_oscclk; + const uint32_t *oscclk; const char *armsse_type; }; @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_TYPE(MPS2TZMachineState, MPS2TZMachineClass, MPS2TZ_MACHINE) /* Slow 32Khz S32KCLK frequency in Hz */ #define S32KCLK_FRQ (32 * 1000) +static const uint32_t an505_oscclk[] = { + 40000000, + 24580000, + 25000000, +}; + /* Create an alias of an entire original MemoryRegion @orig * located at @base in the memory map. */ @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, MPS2SCC *scc = opaque; DeviceState *sccdev; MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + uint32_t i; object_initialize_child(OBJECT(mms), "scc", scc, TYPE_MPS2_SCC); sccdev = DEVICE(scc); qdev_prop_set_uint32(sccdev, "scc-cfg4", 0x2); qdev_prop_set_uint32(sccdev, "scc-aid", 0x00200008); qdev_prop_set_uint32(sccdev, "scc-id", mmc->scc_id); - /* This will need to be per-FPGA image eventually */ - qdev_prop_set_uint32(sccdev, "len-oscclk", 3); - qdev_prop_set_uint32(sccdev, "oscclk[0]", 40000000); - qdev_prop_set_uint32(sccdev, "oscclk[1]", 24580000); - qdev_prop_set_uint32(sccdev, "oscclk[2]", 25000000); + qdev_prop_set_uint32(sccdev, "len-oscclk", mmc->len_oscclk); + for (i = 0; i < mmc->len_oscclk; i++) { + g_autofree char *propname = g_strdup_printf("oscclk[%u]", i); + qdev_prop_set_uint32(sccdev, propname, mmc->oscclk[i]); + } sysbus_realize(SYS_BUS_DEVICE(scc), &error_fatal); return sysbus_mmio_get_region(SYS_BUS_DEVICE(sccdev), 0); } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"); mmc->scc_id = 0x41045050; mmc->sysclk_frq = 20 * 1000 * 1000; /* 20MHz */ + mmc->oscclk = an505_oscclk; + mmc->len_oscclk = ARRAY_SIZE(an505_oscclk); mmc->armsse_type = TYPE_IOTKIT; } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"); mmc->scc_id = 0x41045210; mmc->sysclk_frq = 20 * 1000 * 1000; /* 20MHz */ + mmc->oscclk = an505_oscclk; /* AN521 is the same as AN505 here */ + mmc->len_oscclk = ARRAY_SIZE(an505_oscclk); mmc->armsse_type = TYPE_SSE200; } -- 2.20.1 The MPS2 board has 2 LEDs, but the MPS3 board has 10 LEDs. The FPGAIO device is similar on both sets of boards, but the LED0 register has correspondingly more bits that have an effect. Add a device property for number of LEDs. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-6-peter.maydell@linaro.org --- include/hw/misc/mps2-fpgaio.h | 5 ++++- hw/misc/mps2-fpgaio.c | 31 +++++++++++++++++++++++-------- 2 files changed, 27 insertions(+), 9 deletions(-) diff --git a/include/hw/misc/mps2-fpgaio.h b/include/hw/misc/mps2-fpgaio.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/mps2-fpgaio.h +++ b/include/hw/misc/mps2-fpgaio.h @@ -XXX,XX +XXX,XX @@ #define TYPE_MPS2_FPGAIO "mps2-fpgaio" OBJECT_DECLARE_SIMPLE_TYPE(MPS2FPGAIO, MPS2_FPGAIO) +#define MPS2FPGAIO_MAX_LEDS 32 + struct MPS2FPGAIO { /*< private >*/ SysBusDevice parent_obj; /*< public >*/ MemoryRegion iomem; - LEDState *led[2]; + LEDState *led[MPS2FPGAIO_MAX_LEDS]; + uint32_t num_leds; uint32_t led0; uint32_t prescale; diff --git a/hw/misc/mps2-fpgaio.c b/hw/misc/mps2-fpgaio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mps2-fpgaio.c +++ b/hw/misc/mps2-fpgaio.c @@ -XXX,XX +XXX,XX @@ static void mps2_fpgaio_write(void *opaque, hwaddr offset, uint64_t value, switch (offset) { case A_LED0: - s->led0 = value & 0x3; - led_set_state(s->led[0], value & 0x01); - led_set_state(s->led[1], value & 0x02); + if (s->num_leds != 0) { + uint32_t i; + + s->led0 = value & MAKE_64BIT_MASK(0, s->num_leds); + for (i = 0; i < s->num_leds; i++) { + led_set_state(s->led[i], value & (1 << i)); + } + } break; case A_PRESCALE: resync_counter(s); @@ -XXX,XX +XXX,XX @@ static void mps2_fpgaio_reset(DeviceState *dev) s->pscntr = 0; s->pscntr_sync_ticks = now; - for (size_t i = 0; i < ARRAY_SIZE(s->led); i++) { + for (size_t i = 0; i < s->num_leds; i++) { device_cold_reset(DEVICE(s->led[i])); } } @@ -XXX,XX +XXX,XX @@ static void mps2_fpgaio_init(Object *obj) static void mps2_fpgaio_realize(DeviceState *dev, Error **errp) { MPS2FPGAIO *s = MPS2_FPGAIO(dev); + uint32_t i; - s->led[0] = led_create_simple(OBJECT(dev), GPIO_POLARITY_ACTIVE_HIGH, - LED_COLOR_GREEN, "USERLED0"); - s->led[1] = led_create_simple(OBJECT(dev), GPIO_POLARITY_ACTIVE_HIGH, - LED_COLOR_GREEN, "USERLED1"); + if (s->num_leds > MPS2FPGAIO_MAX_LEDS) { + error_setg(errp, "num-leds cannot be greater than %d", + MPS2FPGAIO_MAX_LEDS); + return; + } + + for (i = 0; i < s->num_leds; i++) { + g_autofree char *ledname = g_strdup_printf("USERLED%d", i); + s->led[i] = led_create_simple(OBJECT(dev), GPIO_POLARITY_ACTIVE_HIGH, + LED_COLOR_GREEN, ledname); + } } static bool mps2_fpgaio_counters_needed(void *opaque) @@ -XXX,XX +XXX,XX @@ static const VMStateDescription mps2_fpgaio_vmstate = { static Property mps2_fpgaio_properties[] = { /* Frequency of the prescale counter */ DEFINE_PROP_UINT32("prescale-clk", MPS2FPGAIO, prescale_clk, 20000000), + /* Number of LEDs controlled by LED0 register */ + DEFINE_PROP_UINT32("num-leds", MPS2FPGAIO, num_leds, 2), DEFINE_PROP_END_OF_LIST(), }; -- 2.20.1 MPS3 boards have an extra SWITCH register in the FPGAIO block which reports the value of some switches. Implement this, governed by a property the board code can use to specify whether whether it exists. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-7-peter.maydell@linaro.org --- include/hw/misc/mps2-fpgaio.h | 1 + hw/misc/mps2-fpgaio.c | 10 ++++++++++ 2 files changed, 11 insertions(+) diff --git a/include/hw/misc/mps2-fpgaio.h b/include/hw/misc/mps2-fpgaio.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/mps2-fpgaio.h +++ b/include/hw/misc/mps2-fpgaio.h @@ -XXX,XX +XXX,XX @@ struct MPS2FPGAIO { MemoryRegion iomem; LEDState *led[MPS2FPGAIO_MAX_LEDS]; uint32_t num_leds; + bool has_switches; uint32_t led0; uint32_t prescale; diff --git a/hw/misc/mps2-fpgaio.c b/hw/misc/mps2-fpgaio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mps2-fpgaio.c +++ b/hw/misc/mps2-fpgaio.c @@ -XXX,XX +XXX,XX @@ REG32(CLK100HZ, 0x14) REG32(COUNTER, 0x18) REG32(PRESCALE, 0x1c) REG32(PSCNTR, 0x20) +REG32(SWITCH, 0x28) REG32(MISC, 0x4c) static uint32_t counter_from_tickoff(int64_t now, int64_t tick_offset, int frq) @@ -XXX,XX +XXX,XX @@ static uint64_t mps2_fpgaio_read(void *opaque, hwaddr offset, unsigned size) resync_counter(s); r = s->pscntr; break; + case A_SWITCH: + if (!s->has_switches) { + goto bad_offset; + } + /* User-togglable board switches. We don't model that, so report 0. */ + r = 0; + break; default: + bad_offset: qemu_log_mask(LOG_GUEST_ERROR, "MPS2 FPGAIO read: bad offset %x\n", (int) offset); r = 0; @@ -XXX,XX +XXX,XX @@ static Property mps2_fpgaio_properties[] = { DEFINE_PROP_UINT32("prescale-clk", MPS2FPGAIO, prescale_clk, 20000000), /* Number of LEDs controlled by LED0 register */ DEFINE_PROP_UINT32("num-leds", MPS2FPGAIO, num_leds, 2), + DEFINE_PROP_BOOL("has-switches", MPS2FPGAIO, has_switches, false), DEFINE_PROP_END_OF_LIST(), }; -- 2.20.1 Set the FPGAIO num-leds and have-switches properties explicitly per-board, rather than relying on the defaults. The AN505 and AN521 both have the same settings as the default values, but the AN524 will be different. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-8-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass { uint32_t sysclk_frq; /* Main SYSCLK frequency in Hz */ uint32_t len_oscclk; const uint32_t *oscclk; + uint32_t fpgaio_num_leds; /* Number of LEDs in FPGAIO LED0 register */ + bool fpgaio_has_switches; /* Does FPGAIO have SWITCH register? */ const char *armsse_type; }; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_fpgaio(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size) { MPS2FPGAIO *fpgaio = opaque; + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); object_initialize_child(OBJECT(mms), "fpgaio", fpgaio, TYPE_MPS2_FPGAIO); + qdev_prop_set_uint32(DEVICE(fpgaio), "num-leds", mmc->fpgaio_num_leds); + qdev_prop_set_bit(DEVICE(fpgaio), "has-switches", mmc->fpgaio_has_switches); sysbus_realize(SYS_BUS_DEVICE(fpgaio), &error_fatal); return sysbus_mmio_get_region(SYS_BUS_DEVICE(fpgaio), 0); } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mmc->sysclk_frq = 20 * 1000 * 1000; /* 20MHz */ mmc->oscclk = an505_oscclk; mmc->len_oscclk = ARRAY_SIZE(an505_oscclk); + mmc->fpgaio_num_leds = 2; + mmc->fpgaio_has_switches = false; mmc->armsse_type = TYPE_IOTKIT; } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mmc->sysclk_frq = 20 * 1000 * 1000; /* 20MHz */ mmc->oscclk = an505_oscclk; /* AN521 is the same as AN505 here */ mmc->len_oscclk = ARRAY_SIZE(an505_oscclk); + mmc->fpgaio_num_leds = 2; + mmc->fpgaio_has_switches = false; mmc->armsse_type = TYPE_SSE200; } -- 2.20.1 In the mps2-tz board code, we handle devices whose interrupt lines must be wired to all CPUs by creating IRQ splitter devices for the AN521, because it has 2 CPUs, but wiring the device IRQ directly to the SSE/IoTKit input for the AN505, which has only 1 CPU. We can avoid making an explicit check on the board type constant by instead creating and using the IRQ splitters for any board with more than 1 CPU. This avoids having to add extra cases to the conditionals every time we add new boards. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-9-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void make_ram_alias(MemoryRegion *mr, const char *name, static qemu_irq get_sse_irq_in(MPS2TZMachineState *mms, int irqno) { /* Return a qemu_irq which will signal IRQ n to all CPUs in the SSE. */ - MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + MachineClass *mc = MACHINE_GET_CLASS(mms); assert(irqno < MPS2TZ_NUMIRQ); - switch (mmc->fpga_type) { - case FPGA_AN505: - return qdev_get_gpio_in_named(DEVICE(&mms->iotkit), "EXP_IRQ", irqno); - case FPGA_AN521: + if (mc->max_cpus > 1) { return qdev_get_gpio_in(DEVICE(&mms->cpu_irq_splitter[irqno]), 0); - default: - g_assert_not_reached(); + } else { + return qdev_get_gpio_in_named(DEVICE(&mms->iotkit), "EXP_IRQ", irqno); } } @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) sysbus_realize(SYS_BUS_DEVICE(&mms->iotkit), &error_fatal); /* - * The AN521 needs us to create splitters to feed the IRQ inputs - * for each CPU in the SSE-200 from each device in the board. + * If this board has more than one CPU, then we need to create splitters + * to feed the IRQ inputs for each CPU in the SSE from each device in the + * board. If there is only one CPU, we can just wire the device IRQ + * directly to the SSE's IRQ input. */ - if (mmc->fpga_type == FPGA_AN521) { + if (mc->max_cpus > 1) { for (i = 0; i < MPS2TZ_NUMIRQ; i++) { char *name = g_strdup_printf("mps2-irq-splitter%d", i); SplitIRQ *splitter = &mms->cpu_irq_splitter[i]; -- 2.20.1 The AN524 has more interrupt lines than the AN505 and AN521; make numirq board-specific rather than a compile-time constant. Since the difference is small (92 on the current boards and 95 on the new one) we don't dynamically allocate the cpu_irq_splitter[] array but leave it as a fixed length array whose size is the maximum needed for any of the boards. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-10-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-clock.h" #include "qom/object.h" -#define MPS2TZ_NUMIRQ 92 +#define MPS2TZ_NUMIRQ_MAX 92 typedef enum MPS2TZFPGAType { FPGA_AN505, @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass { const uint32_t *oscclk; uint32_t fpgaio_num_leds; /* Number of LEDs in FPGAIO LED0 register */ bool fpgaio_has_switches; /* Does FPGAIO have SWITCH register? */ + int numirq; /* Number of external interrupts */ const char *armsse_type; }; @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { SplitIRQ sec_resp_splitter; qemu_or_irq uart_irq_orgate; DeviceState *lan9118; - SplitIRQ cpu_irq_splitter[MPS2TZ_NUMIRQ]; + SplitIRQ cpu_irq_splitter[MPS2TZ_NUMIRQ_MAX]; Clock *sysclk; Clock *s32kclk; }; @@ -XXX,XX +XXX,XX @@ static qemu_irq get_sse_irq_in(MPS2TZMachineState *mms, int irqno) { /* Return a qemu_irq which will signal IRQ n to all CPUs in the SSE. */ MachineClass *mc = MACHINE_GET_CLASS(mms); + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); - assert(irqno < MPS2TZ_NUMIRQ); + assert(irqno < mmc->numirq); if (mc->max_cpus > 1) { return qdev_get_gpio_in(DEVICE(&mms->cpu_irq_splitter[irqno]), 0); @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) iotkitdev = DEVICE(&mms->iotkit); object_property_set_link(OBJECT(&mms->iotkit), "memory", OBJECT(system_memory), &error_abort); - qdev_prop_set_uint32(iotkitdev, "EXP_NUMIRQ", MPS2TZ_NUMIRQ); + qdev_prop_set_uint32(iotkitdev, "EXP_NUMIRQ", mmc->numirq); qdev_connect_clock_in(iotkitdev, "MAINCLK", mms->sysclk); qdev_connect_clock_in(iotkitdev, "S32KCLK", mms->s32kclk); sysbus_realize(SYS_BUS_DEVICE(&mms->iotkit), &error_fatal); @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) * board. If there is only one CPU, we can just wire the device IRQ * directly to the SSE's IRQ input. */ + assert(mmc->numirq <= MPS2TZ_NUMIRQ_MAX); if (mc->max_cpus > 1) { - for (i = 0; i < MPS2TZ_NUMIRQ; i++) { + for (i = 0; i < mmc->numirq; i++) { char *name = g_strdup_printf("mps2-irq-splitter%d", i); SplitIRQ *splitter = &mms->cpu_irq_splitter[i]; @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mmc->len_oscclk = ARRAY_SIZE(an505_oscclk); mmc->fpgaio_num_leds = 2; mmc->fpgaio_has_switches = false; + mmc->numirq = 92; mmc->armsse_type = TYPE_IOTKIT; } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mmc->len_oscclk = ARRAY_SIZE(an505_oscclk); mmc->fpgaio_num_leds = 2; mmc->fpgaio_has_switches = false; + mmc->numirq = 92; mmc->armsse_type = TYPE_SSE200; } -- 2.20.1 The AN524 version of the SCC interface has different behaviour for some of the CFG registers; implement it. Each board in this family can have minor differences in the meaning of the CFG registers, so rather than trying to specify all the possible semantics via individual device properties, we make the behaviour conditional on the part-number field of the SCC_ID register which the board code already passes us. For the AN524, the differences are: * CFG3 is reserved rather than being board switches * CFG5 is a new register ("ACLK Frequency in Hz") * CFG6 is a new register ("Clock divider for BRAM") We implement both of the new registers as reads-as-written. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-11-peter.maydell@linaro.org --- include/hw/misc/mps2-scc.h | 3 ++ hw/misc/mps2-scc.c | 71 ++++++++++++++++++++++++++++++++++++-- 2 files changed, 72 insertions(+), 2 deletions(-) diff --git a/include/hw/misc/mps2-scc.h b/include/hw/misc/mps2-scc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/mps2-scc.h +++ b/include/hw/misc/mps2-scc.h @@ -XXX,XX +XXX,XX @@ struct MPS2SCC { uint32_t cfg0; uint32_t cfg1; + uint32_t cfg2; uint32_t cfg4; + uint32_t cfg5; + uint32_t cfg6; uint32_t cfgdata_rtn; uint32_t cfgdata_out; uint32_t cfgctrl; diff --git a/hw/misc/mps2-scc.c b/hw/misc/mps2-scc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mps2-scc.c +++ b/hw/misc/mps2-scc.c @@ -XXX,XX +XXX,XX @@ REG32(CFG0, 0) REG32(CFG1, 4) +REG32(CFG2, 8) REG32(CFG3, 0xc) REG32(CFG4, 0x10) +REG32(CFG5, 0x14) +REG32(CFG6, 0x18) REG32(CFGDATA_RTN, 0xa0) REG32(CFGDATA_OUT, 0xa4) REG32(CFGCTRL, 0xa8) @@ -XXX,XX +XXX,XX @@ REG32(DLL, 0x100) REG32(AID, 0xFF8) REG32(ID, 0xFFC) +static int scc_partno(MPS2SCC *s) +{ + /* Return the partno field of the SCC_ID (0x524, 0x511, etc) */ + return extract32(s->id, 4, 8); +} + /* Handle a write via the SYS_CFG channel to the specified function/device. * Return false on error (reported to guest via SYS_CFGCTRL ERROR bit). */ @@ -XXX,XX +XXX,XX @@ static uint64_t mps2_scc_read(void *opaque, hwaddr offset, unsigned size) case A_CFG1: r = s->cfg1; break; + case A_CFG2: + if (scc_partno(s) != 0x524) { + /* CFG2 reserved on other boards */ + goto bad_offset; + } + r = s->cfg2; + break; case A_CFG3: + if (scc_partno(s) == 0x524) { + /* CFG3 reserved on AN524 */ + goto bad_offset; + } /* These are user-settable DIP switches on the board. We don't * model that, so just return zeroes. */ @@ -XXX,XX +XXX,XX @@ static uint64_t mps2_scc_read(void *opaque, hwaddr offset, unsigned size) case A_CFG4: r = s->cfg4; break; + case A_CFG5: + if (scc_partno(s) != 0x524) { + /* CFG5 reserved on other boards */ + goto bad_offset; + } + r = s->cfg5; + break; + case A_CFG6: + if (scc_partno(s) != 0x524) { + /* CFG6 reserved on other boards */ + goto bad_offset; + } + r = s->cfg6; + break; case A_CFGDATA_RTN: r = s->cfgdata_rtn; break; @@ -XXX,XX +XXX,XX @@ static uint64_t mps2_scc_read(void *opaque, hwaddr offset, unsigned size) r = s->id; break; default: + bad_offset: qemu_log_mask(LOG_GUEST_ERROR, "MPS2 SCC read: bad offset %x\n", (int) offset); r = 0; @@ -XXX,XX +XXX,XX @@ static void mps2_scc_write(void *opaque, hwaddr offset, uint64_t value, led_set_state(s->led[i], extract32(value, i, 1)); } break; + case A_CFG2: + if (scc_partno(s) != 0x524) { + /* CFG2 reserved on other boards */ + goto bad_offset; + } + /* AN524: QSPI Select signal */ + s->cfg2 = value; + break; + case A_CFG5: + if (scc_partno(s) != 0x524) { + /* CFG5 reserved on other boards */ + goto bad_offset; + } + /* AN524: ACLK frequency in Hz */ + s->cfg5 = value; + break; + case A_CFG6: + if (scc_partno(s) != 0x524) { + /* CFG6 reserved on other boards */ + goto bad_offset; + } + /* AN524: Clock divider for BRAM */ + s->cfg6 = value; + break; case A_CFGDATA_OUT: s->cfgdata_out = value; break; @@ -XXX,XX +XXX,XX @@ static void mps2_scc_write(void *opaque, hwaddr offset, uint64_t value, s->dll = deposit32(s->dll, 24, 8, extract32(value, 24, 8)); break; default: + bad_offset: qemu_log_mask(LOG_GUEST_ERROR, "MPS2 SCC write: bad offset 0x%x\n", (int) offset); break; @@ -XXX,XX +XXX,XX @@ static void mps2_scc_reset(DeviceState *dev) trace_mps2_scc_reset(); s->cfg0 = 0; s->cfg1 = 0; + s->cfg2 = 0; + s->cfg5 = 0; + s->cfg6 = 0; s->cfgdata_rtn = 0; s->cfgdata_out = 0; s->cfgctrl = 0x100000; @@ -XXX,XX +XXX,XX @@ static void mps2_scc_realize(DeviceState *dev, Error **errp) static const VMStateDescription mps2_scc_vmstate = { .name = "mps2-scc", - .version_id = 2, - .minimum_version_id = 2, + .version_id = 3, + .minimum_version_id = 3, .fields = (VMStateField[]) { VMSTATE_UINT32(cfg0, MPS2SCC), VMSTATE_UINT32(cfg1, MPS2SCC), + VMSTATE_UINT32(cfg2, MPS2SCC), + /* cfg3, cfg4 are read-only so need not be migrated */ + VMSTATE_UINT32(cfg5, MPS2SCC), + VMSTATE_UINT32(cfg6, MPS2SCC), VMSTATE_UINT32(cfgdata_rtn, MPS2SCC), VMSTATE_UINT32(cfgdata_out, MPS2SCC), VMSTATE_UINT32(cfgctrl, MPS2SCC), -- 2.20.1 On the MPS2 boards, the first 32 interrupt lines are entirely internal to the SSE; interrupt lines for devices outside the SSE start at 32. In the application notes that document each FPGA image, the interrupt wiring is documented from the point of view of the CPU, so '0' is the first of the SSE's interrupts and the devices in the FPGA image itself are '32' and up: so the UART 0 Receive interrupt is 32, the SPI #0 interrupt is 51, and so on. Within our implementation, because the external interrupts must be connected to the EXP_IRQ[0...n] lines of the SSE object, we made the get_sse_irq_in() function take an irqno whose values start at 0 for the first FPGA device interrupt. In this numbering scheme the UART 0 Receive interrupt is 0, the SPI #0 interrupt is 19, and so on. The result of these two different numbering schemes has been that half of the devices were wired up to the wrong IRQs: the UART IRQs are wired up correctly, but the DMA and SPI devices were passing start-at-32 values to get_sse_irq_in() and so being mis-connected. Fix the bug by making get_sse_irq_in() take values specified with the same scheme that the hardware manuals use, to avoid confusion. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-12-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void make_ram_alias(MemoryRegion *mr, const char *name, static qemu_irq get_sse_irq_in(MPS2TZMachineState *mms, int irqno) { - /* Return a qemu_irq which will signal IRQ n to all CPUs in the SSE. */ + /* + * Return a qemu_irq which will signal IRQ n to all CPUs in the + * SSE. The irqno should be as the CPU sees it, so the first + * external-to-the-SSE interrupt is 32. + */ MachineClass *mc = MACHINE_GET_CLASS(mms); MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); - assert(irqno < mmc->numirq); + assert(irqno >= 32 && irqno < (mmc->numirq + 32)); + + /* + * Convert from "CPU irq number" (as listed in the FPGA image + * documentation) to the SSE external-interrupt number. + */ + irqno -= 32; if (mc->max_cpus > 1) { return qdev_get_gpio_in(DEVICE(&mms->cpu_irq_splitter[irqno]), 0); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); CMSDKAPBUART *uart = opaque; int i = uart - &mms->uart[0]; - int rxirqno = i * 2; - int txirqno = i * 2 + 1; - int combirqno = i + 10; + int rxirqno = i * 2 + 32; + int txirqno = i * 2 + 33; + int combirqno = i + 42; SysBusDevice *s; DeviceState *orgate_dev = DEVICE(&mms->uart_irq_orgate); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, s = SYS_BUS_DEVICE(mms->lan9118); sysbus_realize_and_unref(s, &error_fatal); - sysbus_connect_irq(s, 0, get_sse_irq_in(mms, 16)); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, 48)); return sysbus_mmio_get_region(s, 0); } @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) &error_fatal); qdev_realize(DEVICE(&mms->uart_irq_orgate), NULL, &error_fatal); qdev_connect_gpio_out(DEVICE(&mms->uart_irq_orgate), 0, - get_sse_irq_in(mms, 15)); + get_sse_irq_in(mms, 47)); /* Most of the devices in the FPGA are behind Peripheral Protection * Controllers. The required order for initializing things is: -- 2.20.1 The mps2-tz code uses PPCPortInfo data structures to define what devices are present and how they are wired up. Currently we use these to specify device types and addresses, but hard-code the interrupt line wiring in each make_* helper function. This works for the two boards we have at the moment, but the AN524 has some devices with different interrupt assignments. This commit adds the framework to allow PPCPortInfo structures to specify interrupt numbers. We add an array of interrupt numbers to the PPCPortInfo struct, and pass it through to the make_* helpers. The following commit will change the make_* helpers over to using the framework. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-13-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 36 ++++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 12 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static qemu_irq get_sse_irq_in(MPS2TZMachineState *mms, int irqno) * needs to be plugged into the downstream end of the PPC port. */ typedef MemoryRegion *MakeDevFn(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size); + const char *name, hwaddr size, + const int *irqs); typedef struct PPCPortInfo { const char *name; @@ -XXX,XX +XXX,XX @@ typedef struct PPCPortInfo { void *opaque; hwaddr addr; hwaddr size; + int irqs[3]; /* currently no device needs more IRQ lines than this */ } PPCPortInfo; typedef struct PPCInfo { @@ -XXX,XX +XXX,XX @@ typedef struct PPCInfo { } PPCInfo; static MemoryRegion *make_unimp_dev(MPS2TZMachineState *mms, - void *opaque, - const char *name, hwaddr size) + void *opaque, + const char *name, hwaddr size, + const int *irqs) { /* Initialize, configure and realize a TYPE_UNIMPLEMENTED_DEVICE, * and return a pointer to its MemoryRegion. @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_unimp_dev(MPS2TZMachineState *mms, } static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); CMSDKAPBUART *uart = opaque; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, } static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { MPS2SCC *scc = opaque; DeviceState *sccdev; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, } static MemoryRegion *make_fpgaio(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { MPS2FPGAIO *fpgaio = opaque; MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_fpgaio(MPS2TZMachineState *mms, void *opaque, } static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { SysBusDevice *s; NICInfo *nd = &nd_table[0]; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, } static MemoryRegion *make_mpc(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { TZMPC *mpc = opaque; int i = mpc - &mms->ssram_mpc[0]; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_mpc(MPS2TZMachineState *mms, void *opaque, } static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { PL080State *dma = opaque; int i = dma - &mms->dma[0]; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, } static MemoryRegion *make_spi(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { /* * The AN505 has five PL022 SPI controllers. @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_spi(MPS2TZMachineState *mms, void *opaque, } static MemoryRegion *make_i2c(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { ArmSbconI2CState *i2c = opaque; SysBusDevice *s; @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) continue; } - mr = pinfo->devfn(mms, pinfo->opaque, pinfo->name, pinfo->size); + mr = pinfo->devfn(mms, pinfo->opaque, pinfo->name, pinfo->size, + pinfo->irqs); portname = g_strdup_printf("port[%d]", port); object_property_set_link(OBJECT(ppc), portname, OBJECT(mr), &error_fatal); -- 2.20.1 Move the specification of the IRQ information for the uart, ethernet, dma and spi devices to the data structures. (The other devices handled by the PPCPortInfo structures don't have any interrupt lines we need to wire up.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-14-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 52 +++++++++++++++++++++++------------------------- 1 file changed, 25 insertions(+), 27 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, const int *irqs) { + /* The irq[] array is tx, rx, combined, in that order */ MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); CMSDKAPBUART *uart = opaque; int i = uart - &mms->uart[0]; - int rxirqno = i * 2 + 32; - int txirqno = i * 2 + 33; - int combirqno = i + 42; SysBusDevice *s; DeviceState *orgate_dev = DEVICE(&mms->uart_irq_orgate); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, qdev_prop_set_uint32(DEVICE(uart), "pclk-frq", mmc->sysclk_frq); sysbus_realize(SYS_BUS_DEVICE(uart), &error_fatal); s = SYS_BUS_DEVICE(uart); - sysbus_connect_irq(s, 0, get_sse_irq_in(mms, txirqno)); - sysbus_connect_irq(s, 1, get_sse_irq_in(mms, rxirqno)); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqs[0])); + sysbus_connect_irq(s, 1, get_sse_irq_in(mms, irqs[1])); sysbus_connect_irq(s, 2, qdev_get_gpio_in(orgate_dev, i * 2)); sysbus_connect_irq(s, 3, qdev_get_gpio_in(orgate_dev, i * 2 + 1)); - sysbus_connect_irq(s, 4, get_sse_irq_in(mms, combirqno)); + sysbus_connect_irq(s, 4, get_sse_irq_in(mms, irqs[2])); return sysbus_mmio_get_region(SYS_BUS_DEVICE(uart), 0); } @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, s = SYS_BUS_DEVICE(mms->lan9118); sysbus_realize_and_unref(s, &error_fatal); - sysbus_connect_irq(s, 0, get_sse_irq_in(mms, 48)); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqs[0])); return sysbus_mmio_get_region(s, 0); } @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, const int *irqs) { + /* The irq[] array is DMACINTR, DMACINTERR, DMACINTTC, in that order */ PL080State *dma = opaque; int i = dma - &mms->dma[0]; SysBusDevice *s; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, s = SYS_BUS_DEVICE(dma); /* Wire up DMACINTR, DMACINTERR, DMACINTTC */ - sysbus_connect_irq(s, 0, get_sse_irq_in(mms, 58 + i * 3)); - sysbus_connect_irq(s, 1, get_sse_irq_in(mms, 56 + i * 3)); - sysbus_connect_irq(s, 2, get_sse_irq_in(mms, 57 + i * 3)); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqs[0])); + sysbus_connect_irq(s, 1, get_sse_irq_in(mms, irqs[1])); + sysbus_connect_irq(s, 2, get_sse_irq_in(mms, irqs[2])); g_free(mscname); return sysbus_mmio_get_region(s, 0); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_spi(MPS2TZMachineState *mms, void *opaque, * lines are set via the "MISC" register in the MPS2 FPGAIO device. */ PL022State *spi = opaque; - int i = spi - &mms->spi[0]; SysBusDevice *s; object_initialize_child(OBJECT(mms), name, spi, TYPE_PL022); sysbus_realize(SYS_BUS_DEVICE(spi), &error_fatal); s = SYS_BUS_DEVICE(spi); - sysbus_connect_irq(s, 0, get_sse_irq_in(mms, 51 + i)); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqs[0])); return sysbus_mmio_get_region(s, 0); } @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) }, { .name = "apb_ppcexp1", .ports = { - { "spi0", make_spi, &mms->spi[0], 0x40205000, 0x1000 }, - { "spi1", make_spi, &mms->spi[1], 0x40206000, 0x1000 }, - { "spi2", make_spi, &mms->spi[2], 0x40209000, 0x1000 }, - { "spi3", make_spi, &mms->spi[3], 0x4020a000, 0x1000 }, - { "spi4", make_spi, &mms->spi[4], 0x4020b000, 0x1000 }, - { "uart0", make_uart, &mms->uart[0], 0x40200000, 0x1000 }, - { "uart1", make_uart, &mms->uart[1], 0x40201000, 0x1000 }, - { "uart2", make_uart, &mms->uart[2], 0x40202000, 0x1000 }, - { "uart3", make_uart, &mms->uart[3], 0x40203000, 0x1000 }, - { "uart4", make_uart, &mms->uart[4], 0x40204000, 0x1000 }, + { "spi0", make_spi, &mms->spi[0], 0x40205000, 0x1000, { 51 } }, + { "spi1", make_spi, &mms->spi[1], 0x40206000, 0x1000, { 52 } }, + { "spi2", make_spi, &mms->spi[2], 0x40209000, 0x1000, { 53 } }, + { "spi3", make_spi, &mms->spi[3], 0x4020a000, 0x1000, { 54 } }, + { "spi4", make_spi, &mms->spi[4], 0x4020b000, 0x1000, { 55 } }, + { "uart0", make_uart, &mms->uart[0], 0x40200000, 0x1000, { 32, 33, 42 } }, + { "uart1", make_uart, &mms->uart[1], 0x40201000, 0x1000, { 34, 35, 43 } }, + { "uart2", make_uart, &mms->uart[2], 0x40202000, 0x1000, { 36, 37, 44 } }, + { "uart3", make_uart, &mms->uart[3], 0x40203000, 0x1000, { 38, 39, 45 } }, + { "uart4", make_uart, &mms->uart[4], 0x40204000, 0x1000, { 40, 41, 46 } }, { "i2c0", make_i2c, &mms->i2c[0], 0x40207000, 0x1000 }, { "i2c1", make_i2c, &mms->i2c[1], 0x40208000, 0x1000 }, { "i2c2", make_i2c, &mms->i2c[2], 0x4020c000, 0x1000 }, @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) { "gpio1", make_unimp_dev, &mms->gpio[1], 0x40101000, 0x1000 }, { "gpio2", make_unimp_dev, &mms->gpio[2], 0x40102000, 0x1000 }, { "gpio3", make_unimp_dev, &mms->gpio[3], 0x40103000, 0x1000 }, - { "eth", make_eth_dev, NULL, 0x42000000, 0x100000 }, + { "eth", make_eth_dev, NULL, 0x42000000, 0x100000, { 48 } }, }, }, { .name = "ahb_ppcexp1", .ports = { - { "dma0", make_dma, &mms->dma[0], 0x40110000, 0x1000 }, - { "dma1", make_dma, &mms->dma[1], 0x40111000, 0x1000 }, - { "dma2", make_dma, &mms->dma[2], 0x40112000, 0x1000 }, - { "dma3", make_dma, &mms->dma[3], 0x40113000, 0x1000 }, + { "dma0", make_dma, &mms->dma[0], 0x40110000, 0x1000, { 58, 56, 57 } }, + { "dma1", make_dma, &mms->dma[1], 0x40111000, 0x1000, { 61, 59, 60 } }, + { "dma2", make_dma, &mms->dma[2], 0x40112000, 0x1000, { 64, 62, 63 } }, + { "dma3", make_dma, &mms->dma[3], 0x40113000, 0x1000, { 67, 65, 66 } }, }, }, }; -- 2.20.1 We create an OR gate to wire together the overflow IRQs for all the UARTs on the board; this has to have twice the number of inputs as there are UARTs, since each UART feeds it a TX overflow and an RX overflow interrupt line. Replace the hardcoded '10' with a calculation based on the size of the uart[] array in the MPS2TZMachineState. (We rely on OR gate inputs that are never wired up or asserted being treated as always-zero.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-15-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) */ memory_region_add_subregion(system_memory, 0x80000000, machine->ram); - /* The overflow IRQs for all UARTs are ORed together. + /* + * The overflow IRQs for all UARTs are ORed together. * Tx, Rx and "combined" IRQs are sent to the NVIC separately. - * Create the OR gate for this. + * Create the OR gate for this: it has one input for the TX overflow + * and one for the RX overflow for each UART we might have. + * (If the board has fewer than the maximum possible number of UARTs + * those inputs are never wired up and are treated as always-zero.) */ object_initialize_child(OBJECT(mms), "uart-irq-orgate", &mms->uart_irq_orgate, TYPE_OR_IRQ); - object_property_set_int(OBJECT(&mms->uart_irq_orgate), "num-lines", 10, + object_property_set_int(OBJECT(&mms->uart_irq_orgate), "num-lines", + 2 * ARRAY_SIZE(mms->uart), &error_fatal); qdev_realize(DEVICE(&mms->uart_irq_orgate), NULL, &error_fatal); qdev_connect_gpio_out(DEVICE(&mms->uart_irq_orgate), 0, -- 2.20.1 The AN505 and AN521 have the same device layout, but the AN524 is somewhat different. Allow for more than one PPCInfo array, which can be selected based on the board type. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-16-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) MemoryRegion *system_memory = get_system_memory(); DeviceState *iotkitdev; DeviceState *dev_splitter; + const PPCInfo *ppcs; + int num_ppcs; int i; if (strcmp(machine->cpu_type, mc->default_cpu_type) != 0) { @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) * + wire up the PPC's control lines to the IoTKit object */ - const PPCInfo ppcs[] = { { + const PPCInfo an505_ppcs[] = { { .name = "apb_ppcexp0", .ports = { { "ssram-0", make_mpc, &mms->ssram_mpc[0], 0x58007000, 0x1000 }, @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) }, }; - for (i = 0; i < ARRAY_SIZE(ppcs); i++) { + switch (mmc->fpga_type) { + case FPGA_AN505: + case FPGA_AN521: + ppcs = an505_ppcs; + num_ppcs = ARRAY_SIZE(an505_ppcs); + break; + default: + g_assert_not_reached(); + } + + for (i = 0; i < num_ppcs; i++) { const PPCInfo *ppcinfo = &ppcs[i]; TZPPC *ppc = &mms->ppc[i]; DeviceState *ppcdev; -- 2.20.1 The AN505 and AN521 have the same layout of RAM; the AN524 does not. Replace the current hard-coding of where the RAM is and which parts of it are behind which MPCs with a data-driven approach. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-17-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 175 +++++++++++++++++++++++++++++++++++++---------- 1 file changed, 138 insertions(+), 37 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ #include "qom/object.h" #define MPS2TZ_NUMIRQ_MAX 92 +#define MPS2TZ_RAM_MAX 4 typedef enum MPS2TZFPGAType { FPGA_AN505, FPGA_AN521, } MPS2TZFPGAType; +/* + * Define the layout of RAM in a board, including which parts are + * behind which MPCs. + * mrindex specifies the index into mms->ram[] to use for the backing RAM; + * -1 means "use the system RAM". + */ +typedef struct RAMInfo { + const char *name; + uint32_t base; + uint32_t size; + int mpc; /* MPC number, -1 for "not behind an MPC" */ + int mrindex; + int flags; +} RAMInfo; + +/* + * Flag values: + * IS_ALIAS: this RAM area is an alias to the upstream end of the + * MPC specified by its .mpc value + */ +#define IS_ALIAS 1 + struct MPS2TZMachineClass { MachineClass parent; MPS2TZFPGAType fpga_type; @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass { uint32_t fpgaio_num_leds; /* Number of LEDs in FPGAIO LED0 register */ bool fpgaio_has_switches; /* Does FPGAIO have SWITCH register? */ int numirq; /* Number of external interrupts */ + const RAMInfo *raminfo; const char *armsse_type; }; @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { MachineState parent; ARMSSE iotkit; - MemoryRegion ssram[3]; - MemoryRegion ssram1_m; + MemoryRegion ram[MPS2TZ_RAM_MAX]; MPS2SCC scc; MPS2FPGAIO fpgaio; TZPPC ppc[5]; - TZMPC ssram_mpc[3]; + TZMPC mpc[3]; PL022State spi[5]; ArmSbconI2CState i2c[4]; UnimplementedDeviceState i2s_audio; @@ -XXX,XX +XXX,XX @@ static const uint32_t an505_oscclk[] = { 25000000, }; +static const RAMInfo an505_raminfo[] = { { + .name = "ssram-0", + .base = 0x00000000, + .size = 0x00400000, + .mpc = 0, + .mrindex = 0, + }, { + .name = "ssram-1", + .base = 0x28000000, + .size = 0x00200000, + .mpc = 1, + .mrindex = 1, + }, { + .name = "ssram-2", + .base = 0x28200000, + .size = 0x00200000, + .mpc = 2, + .mrindex = 2, + }, { + .name = "ssram-0-alias", + .base = 0x00400000, + .size = 0x00400000, + .mpc = 0, + .mrindex = 3, + .flags = IS_ALIAS, + }, { + /* Use the largest bit of contiguous RAM as our "system memory" */ + .name = "mps.ram", + .base = 0x80000000, + .size = 16 * MiB, + .mpc = -1, + .mrindex = -1, + }, { + .name = NULL, + }, +}; + +static const RAMInfo *find_raminfo_for_mpc(MPS2TZMachineState *mms, int mpc) +{ + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + const RAMInfo *p; + + for (p = mmc->raminfo; p->name; p++) { + if (p->mpc == mpc && !(p->flags & IS_ALIAS)) { + return p; + } + } + /* if raminfo array doesn't have an entry for each MPC this is a bug */ + g_assert_not_reached(); +} + +static MemoryRegion *mr_for_raminfo(MPS2TZMachineState *mms, + const RAMInfo *raminfo) +{ + /* Return an initialized MemoryRegion for the RAMInfo. */ + MemoryRegion *ram; + + if (raminfo->mrindex < 0) { + /* Means this RAMInfo is for QEMU's "system memory" */ + MachineState *machine = MACHINE(mms); + return machine->ram; + } + + assert(raminfo->mrindex < MPS2TZ_RAM_MAX); + ram = &mms->ram[raminfo->mrindex]; + + memory_region_init_ram(ram, NULL, raminfo->name, + raminfo->size, &error_fatal); + return ram; +} + /* Create an alias of an entire original MemoryRegion @orig * located at @base in the memory map. */ @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_mpc(MPS2TZMachineState *mms, void *opaque, const int *irqs) { TZMPC *mpc = opaque; - int i = mpc - &mms->ssram_mpc[0]; - MemoryRegion *ssram = &mms->ssram[i]; + int i = mpc - &mms->mpc[0]; MemoryRegion *upstream; - char *mpcname = g_strdup_printf("%s-mpc", name); - static uint32_t ramsize[] = { 0x00400000, 0x00200000, 0x00200000 }; - static uint32_t rambase[] = { 0x00000000, 0x28000000, 0x28200000 }; + const RAMInfo *raminfo = find_raminfo_for_mpc(mms, i); + MemoryRegion *ram = mr_for_raminfo(mms, raminfo); - memory_region_init_ram(ssram, NULL, name, ramsize[i], &error_fatal); - - object_initialize_child(OBJECT(mms), mpcname, mpc, TYPE_TZ_MPC); - object_property_set_link(OBJECT(mpc), "downstream", OBJECT(ssram), + object_initialize_child(OBJECT(mms), name, mpc, TYPE_TZ_MPC); + object_property_set_link(OBJECT(mpc), "downstream", OBJECT(ram), &error_fatal); sysbus_realize(SYS_BUS_DEVICE(mpc), &error_fatal); /* Map the upstream end of the MPC into system memory */ upstream = sysbus_mmio_get_region(SYS_BUS_DEVICE(mpc), 1); - memory_region_add_subregion(get_system_memory(), rambase[i], upstream); + memory_region_add_subregion(get_system_memory(), raminfo->base, upstream); /* and connect its interrupt to the IoTKit */ qdev_connect_gpio_out_named(DEVICE(mpc), "irq", 0, qdev_get_gpio_in_named(DEVICE(&mms->iotkit), "mpcexp_status", i)); - /* The first SSRAM is a special case as it has an alias; accesses to - * the alias region at 0x00400000 must also go to the MPC upstream. - */ - if (i == 0) { - make_ram_alias(&mms->ssram1_m, "mps.ssram1_m", upstream, 0x00400000); - } - - g_free(mpcname); /* Return the register interface MR for our caller to map behind the PPC */ return sysbus_mmio_get_region(SYS_BUS_DEVICE(mpc), 0); } @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_i2c(MPS2TZMachineState *mms, void *opaque, return sysbus_mmio_get_region(s, 0); } +static void create_non_mpc_ram(MPS2TZMachineState *mms) +{ + /* + * Handle the RAMs which are either not behind MPCs or which are + * aliases to another MPC. + */ + const RAMInfo *p; + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + + for (p = mmc->raminfo; p->name; p++) { + if (p->flags & IS_ALIAS) { + SysBusDevice *mpc_sbd = SYS_BUS_DEVICE(&mms->mpc[p->mpc]); + MemoryRegion *upstream = sysbus_mmio_get_region(mpc_sbd, 1); + make_ram_alias(&mms->ram[p->mrindex], p->name, upstream, p->base); + } else if (p->mpc == -1) { + /* RAM not behind an MPC */ + MemoryRegion *mr = mr_for_raminfo(mms, p); + memory_region_add_subregion(get_system_memory(), p->base, mr); + } + } +} + static void mps2tz_common_init(MachineState *machine) { MPS2TZMachineState *mms = MPS2TZ_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) qdev_connect_gpio_out_named(iotkitdev, "sec_resp_cfg", 0, qdev_get_gpio_in(dev_splitter, 0)); - /* The IoTKit sets up much of the memory layout, including + /* + * The IoTKit sets up much of the memory layout, including * the aliases between secure and non-secure regions in the - * address space. The FPGA itself contains: - * - * 0x00000000..0x003fffff SSRAM1 - * 0x00400000..0x007fffff alias of SSRAM1 - * 0x28000000..0x283fffff 4MB SSRAM2 + SSRAM3 - * 0x40100000..0x4fffffff AHB Master Expansion 1 interface devices - * 0x80000000..0x80ffffff 16MB PSRAM - */ - - /* The FPGA images have an odd combination of different RAMs, + * address space, and also most of the devices in the system. + * The FPGA itself contains various RAMs and some additional devices. + * The FPGA images have an odd combination of different RAMs, * because in hardware they are different implementations and * connected to different buses, giving varying performance/size * tradeoffs. For QEMU they're all just RAM, though. We arbitrarily - * call the 16MB our "system memory", as it's the largest lump. + * call the largest lump our "system memory". */ - memory_region_add_subregion(system_memory, 0x80000000, machine->ram); /* * The overflow IRQs for all UARTs are ORed together. @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) const PPCInfo an505_ppcs[] = { { .name = "apb_ppcexp0", .ports = { - { "ssram-0", make_mpc, &mms->ssram_mpc[0], 0x58007000, 0x1000 }, - { "ssram-1", make_mpc, &mms->ssram_mpc[1], 0x58008000, 0x1000 }, - { "ssram-2", make_mpc, &mms->ssram_mpc[2], 0x58009000, 0x1000 }, + { "ssram-0-mpc", make_mpc, &mms->mpc[0], 0x58007000, 0x1000 }, + { "ssram-1-mpc", make_mpc, &mms->mpc[1], 0x58008000, 0x1000 }, + { "ssram-2-mpc", make_mpc, &mms->mpc[2], 0x58009000, 0x1000 }, }, }, { .name = "apb_ppcexp1", @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) create_unimplemented_device("FPGA NS PC", 0x48007000, 0x1000); + create_non_mpc_ram(mms); + armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, 0x400000); } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mmc->fpgaio_num_leds = 2; mmc->fpgaio_has_switches = false; mmc->numirq = 92; + mmc->raminfo = an505_raminfo; mmc->armsse_type = TYPE_IOTKIT; } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mmc->fpgaio_num_leds = 2; mmc->fpgaio_has_switches = false; mmc->numirq = 92; + mmc->raminfo = an505_raminfo; /* AN521 is the same as AN505 here */ mmc->armsse_type = TYPE_SSE200; } -- 2.20.1 Instead of hardcoding the MachineClass default_ram_size and default_ram_id fields, set them on class creation by finding the entry in the RAMInfo array which is marked as being the QEMU system RAM. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-18-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void mps2tz_class_init(ObjectClass *oc, void *data) mc->init = mps2tz_common_init; iic->check = mps2_tz_idau_check; - mc->default_ram_size = 16 * MiB; - mc->default_ram_id = "mps.ram"; +} + +static void mps2tz_set_default_ram_info(MPS2TZMachineClass *mmc) +{ + /* + * Set mc->default_ram_size and default_ram_id from the + * information in mmc->raminfo. + */ + MachineClass *mc = MACHINE_CLASS(mmc); + const RAMInfo *p; + + for (p = mmc->raminfo; p->name; p++) { + if (p->mrindex < 0) { + /* Found the entry for "system memory" */ + mc->default_ram_size = p->size; + mc->default_ram_id = p->name; + return; + } + } + g_assert_not_reached(); } static void mps2tz_an505_class_init(ObjectClass *oc, void *data) @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mmc->numirq = 92; mmc->raminfo = an505_raminfo; mmc->armsse_type = TYPE_IOTKIT; + mps2tz_set_default_ram_info(mmc); } static void mps2tz_an521_class_init(ObjectClass *oc, void *data) @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mmc->numirq = 92; mmc->raminfo = an505_raminfo; /* AN521 is the same as AN505 here */ mmc->armsse_type = TYPE_SSE200; + mps2tz_set_default_ram_info(mmc); } static const TypeInfo mps2tz_info = { -- 2.20.1 The AN505 and AN521 don't have any read-only memory, but the AN524 does; add a flag to ROMInfo to mark a region as ROM. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-19-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ typedef struct RAMInfo { * Flag values: * IS_ALIAS: this RAM area is an alias to the upstream end of the * MPC specified by its .mpc value + * IS_ROM: this RAM area is read-only */ #define IS_ALIAS 1 +#define IS_ROM 2 struct MPS2TZMachineClass { MachineClass parent; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *mr_for_raminfo(MPS2TZMachineState *mms, if (raminfo->mrindex < 0) { /* Means this RAMInfo is for QEMU's "system memory" */ MachineState *machine = MACHINE(mms); + assert(!(raminfo->flags & IS_ROM)); return machine->ram; } @@ -XXX,XX +XXX,XX @@ static MemoryRegion *mr_for_raminfo(MPS2TZMachineState *mms, memory_region_init_ram(ram, NULL, raminfo->name, raminfo->size, &error_fatal); + if (raminfo->flags & IS_ROM) { + memory_region_set_readonly(ram, true); + } return ram; } -- 2.20.1 The armv7m_load_kernel() function takes a mem_size argument which it expects to be the size of the memory region at guest address 0. (It uses this argument only as a limit on how large a raw image file it can load at address zero). Instead of hardcoding this value, find the RAMInfo corresponding to the 0 address and extract its size. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-20-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void create_non_mpc_ram(MPS2TZMachineState *mms) } } +static uint32_t boot_ram_size(MPS2TZMachineState *mms) +{ + /* Return the size of the RAM block at guest address zero */ + const RAMInfo *p; + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + + for (p = mmc->raminfo; p->name; p++) { + if (p->base == 0) { + return p->size; + } + } + g_assert_not_reached(); +} + static void mps2tz_common_init(MachineState *machine) { MPS2TZMachineState *mms = MPS2TZ_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) create_non_mpc_ram(mms); - armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, 0x400000); + armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, + boot_ram_size(mms)); } static void mps2_tz_idau_check(IDAUInterface *ii, uint32_t address, -- 2.20.1 Add support for the mps3-an524 board; this is an SSE-200 based FPGA image, like the existing mps2-an521. It has a usefully larger amount of RAM, and a PL031 RTC, as well as some more minor differences. In real hardware this image runs on a newer generation of the FPGA board, the MPS3 rather than the older MPS2. Architecturally the two boards are similar, so we implement the MPS3 boards in the mps2-tz.c file as variations of the existing MPS2 boards. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-21-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 139 +++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 135 insertions(+), 4 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ * This source file covers the following FPGA images, for TrustZone cores: * "mps2-an505" -- Cortex-M33 as documented in ARM Application Note AN505 * "mps2-an521" -- Dual Cortex-M33 as documented in Application Note AN521 + * "mps2-an524" -- Dual Cortex-M33 as documented in Application Note AN524 * * Links to the TRM for the board itself and to the various Application * Notes which document the FPGA images can be found here: @@ -XXX,XX +XXX,XX @@ * http://infocenter.arm.com/help/topic/com.arm.doc.dai0505b/index.html * Application Note AN521: * http://infocenter.arm.com/help/topic/com.arm.doc.dai0521c/index.html + * Application Note AN524: + * https://developer.arm.com/documentation/dai0524/latest/ * * The AN505 defers to the Cortex-M33 processor ARMv8M IoT Kit FVP User Guide * (ARM ECM0601256) for the details of some of the device layout: * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html - * Similarly, the AN521 uses the SSE-200, and the SSE-200 TRM defines + * Similarly, the AN521 and AN524 use the SSE-200, and the SSE-200 TRM defines * most of the device layout: * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf * @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-clock.h" #include "qom/object.h" -#define MPS2TZ_NUMIRQ_MAX 92 +#define MPS2TZ_NUMIRQ_MAX 95 #define MPS2TZ_RAM_MAX 4 typedef enum MPS2TZFPGAType { FPGA_AN505, FPGA_AN521, + FPGA_AN524, } MPS2TZFPGAType; /* @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { TZPPC ppc[5]; TZMPC mpc[3]; PL022State spi[5]; - ArmSbconI2CState i2c[4]; + ArmSbconI2CState i2c[5]; UnimplementedDeviceState i2s_audio; UnimplementedDeviceState gpio[4]; UnimplementedDeviceState gfx; + UnimplementedDeviceState cldc; + UnimplementedDeviceState rtc; PL080State dma[4]; TZMSC msc[4]; - CMSDKAPBUART uart[5]; + CMSDKAPBUART uart[6]; SplitIRQ sec_resp_splitter; qemu_or_irq uart_irq_orgate; DeviceState *lan9118; @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { #define TYPE_MPS2TZ_MACHINE "mps2tz" #define TYPE_MPS2TZ_AN505_MACHINE MACHINE_TYPE_NAME("mps2-an505") #define TYPE_MPS2TZ_AN521_MACHINE MACHINE_TYPE_NAME("mps2-an521") +#define TYPE_MPS3TZ_AN524_MACHINE MACHINE_TYPE_NAME("mps3-an524") OBJECT_DECLARE_TYPE(MPS2TZMachineState, MPS2TZMachineClass, MPS2TZ_MACHINE) @@ -XXX,XX +XXX,XX @@ static const uint32_t an505_oscclk[] = { 25000000, }; +static const uint32_t an524_oscclk[] = { + 24000000, + 32000000, + 50000000, + 50000000, + 24576000, + 23750000, +}; + static const RAMInfo an505_raminfo[] = { { .name = "ssram-0", .base = 0x00000000, @@ -XXX,XX +XXX,XX @@ static const RAMInfo an505_raminfo[] = { { }, }; +static const RAMInfo an524_raminfo[] = { { + .name = "bram", + .base = 0x00000000, + .size = 512 * KiB, + .mpc = 0, + .mrindex = 0, + }, { + .name = "sram", + .base = 0x20000000, + .size = 32 * 4 * KiB, + .mpc = 1, + .mrindex = 1, + }, { + /* We don't model QSPI flash yet; for now expose it as simple ROM */ + .name = "QSPI", + .base = 0x28000000, + .size = 8 * MiB, + .mpc = 1, + .mrindex = 2, + .flags = IS_ROM, + }, { + .name = "DDR", + .base = 0x60000000, + .size = 2 * GiB, + .mpc = 2, + .mrindex = -1, + }, { + .name = NULL, + }, +}; + static const RAMInfo *find_raminfo_for_mpc(MPS2TZMachineState *mms, int mpc) { MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) }, }; + const PPCInfo an524_ppcs[] = { { + .name = "apb_ppcexp0", + .ports = { + { "bram-mpc", make_mpc, &mms->mpc[0], 0x58007000, 0x1000 }, + { "qspi-mpc", make_mpc, &mms->mpc[1], 0x58008000, 0x1000 }, + { "ddr-mpc", make_mpc, &mms->mpc[2], 0x58009000, 0x1000 }, + }, + }, { + .name = "apb_ppcexp1", + .ports = { + { "i2c0", make_i2c, &mms->i2c[0], 0x41200000, 0x1000 }, + { "i2c1", make_i2c, &mms->i2c[1], 0x41201000, 0x1000 }, + { "spi0", make_spi, &mms->spi[0], 0x41202000, 0x1000, { 52 } }, + { "spi1", make_spi, &mms->spi[1], 0x41203000, 0x1000, { 53 } }, + { "spi2", make_spi, &mms->spi[2], 0x41204000, 0x1000, { 54 } }, + { "i2c2", make_i2c, &mms->i2c[2], 0x41205000, 0x1000 }, + { "i2c3", make_i2c, &mms->i2c[3], 0x41206000, 0x1000 }, + { /* port 7 reserved */ }, + { "i2c4", make_i2c, &mms->i2c[4], 0x41208000, 0x1000 }, + }, + }, { + .name = "apb_ppcexp2", + .ports = { + { "scc", make_scc, &mms->scc, 0x41300000, 0x1000 }, + { "i2s-audio", make_unimp_dev, &mms->i2s_audio, + 0x41301000, 0x1000 }, + { "fpgaio", make_fpgaio, &mms->fpgaio, 0x41302000, 0x1000 }, + { "uart0", make_uart, &mms->uart[0], 0x41303000, 0x1000, { 32, 33, 42 } }, + { "uart1", make_uart, &mms->uart[1], 0x41304000, 0x1000, { 34, 35, 43 } }, + { "uart2", make_uart, &mms->uart[2], 0x41305000, 0x1000, { 36, 37, 44 } }, + { "uart3", make_uart, &mms->uart[3], 0x41306000, 0x1000, { 38, 39, 45 } }, + { "uart4", make_uart, &mms->uart[4], 0x41307000, 0x1000, { 40, 41, 46 } }, + { "uart5", make_uart, &mms->uart[5], 0x41308000, 0x1000, { 124, 125, 126 } }, + + { /* port 9 reserved */ }, + { "clcd", make_unimp_dev, &mms->cldc, 0x4130a000, 0x1000 }, + { "rtc", make_unimp_dev, &mms->rtc, 0x4130b000, 0x1000 }, + }, + }, { + .name = "ahb_ppcexp0", + .ports = { + { "gpio0", make_unimp_dev, &mms->gpio[0], 0x41100000, 0x1000 }, + { "gpio1", make_unimp_dev, &mms->gpio[1], 0x41101000, 0x1000 }, + { "gpio2", make_unimp_dev, &mms->gpio[2], 0x41102000, 0x1000 }, + { "gpio3", make_unimp_dev, &mms->gpio[3], 0x41103000, 0x1000 }, + { "eth", make_eth_dev, NULL, 0x41400000, 0x100000, { 48 } }, + }, + }, + }; + switch (mmc->fpga_type) { case FPGA_AN505: case FPGA_AN521: ppcs = an505_ppcs; num_ppcs = ARRAY_SIZE(an505_ppcs); break; + case FPGA_AN524: + ppcs = an524_ppcs; + num_ppcs = ARRAY_SIZE(an524_ppcs); + break; default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mps2tz_set_default_ram_info(mmc); } +static void mps3tz_an524_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_CLASS(oc); + + mc->desc = "ARM MPS3 with AN524 FPGA image for dual Cortex-M33"; + mc->default_cpus = 2; + mc->min_cpus = mc->default_cpus; + mc->max_cpus = mc->default_cpus; + mmc->fpga_type = FPGA_AN524; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"); + mmc->scc_id = 0x41045240; + mmc->sysclk_frq = 32 * 1000 * 1000; /* 32MHz */ + mmc->oscclk = an524_oscclk; + mmc->len_oscclk = ARRAY_SIZE(an524_oscclk); + mmc->fpgaio_num_leds = 10; + mmc->fpgaio_has_switches = true; + mmc->numirq = 95; + mmc->raminfo = an524_raminfo; + mmc->armsse_type = TYPE_SSE200; + mps2tz_set_default_ram_info(mmc); +} + static const TypeInfo mps2tz_info = { .name = TYPE_MPS2TZ_MACHINE, .parent = TYPE_MACHINE, @@ -XXX,XX +XXX,XX @@ static const TypeInfo mps2tz_an521_info = { .class_init = mps2tz_an521_class_init, }; +static const TypeInfo mps3tz_an524_info = { + .name = TYPE_MPS3TZ_AN524_MACHINE, + .parent = TYPE_MPS2TZ_MACHINE, + .class_init = mps3tz_an524_class_init, +}; + static void mps2tz_machine_init(void) { type_register_static(&mps2tz_info); type_register_static(&mps2tz_an505_info); type_register_static(&mps2tz_an521_info); + type_register_static(&mps3tz_an524_info); } type_init(mps2tz_machine_init); -- 2.20.1 The AN524 has a USB controller (an ISP1763); we don't have a model of it but we should provide a stub "unimplemented-device" for it. This is slightly complicated because the USB controller shares a PPC port with the ethernet controller. Implement a make_* function which provides creates a container MemoryRegion with both the ethernet controller and an unimplemented-device stub for the USB controller. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-22-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 48 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 47 insertions(+), 1 deletion(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { ARMSSE iotkit; MemoryRegion ram[MPS2TZ_RAM_MAX]; + MemoryRegion eth_usb_container; + MPS2SCC scc; MPS2FPGAIO fpgaio; TZPPC ppc[5]; @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { UnimplementedDeviceState gfx; UnimplementedDeviceState cldc; UnimplementedDeviceState rtc; + UnimplementedDeviceState usb; PL080State dma[4]; TZMSC msc[4]; CMSDKAPBUART uart[6]; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, return sysbus_mmio_get_region(s, 0); } +static MemoryRegion *make_eth_usb(MPS2TZMachineState *mms, void *opaque, + const char *name, hwaddr size, + const int *irqs) +{ + /* + * The AN524 makes the ethernet and USB share a PPC port. + * irqs[] is the ethernet IRQ. + */ + SysBusDevice *s; + NICInfo *nd = &nd_table[0]; + + memory_region_init(&mms->eth_usb_container, OBJECT(mms), + "mps2-tz-eth-usb-container", 0x200000); + + /* + * In hardware this is a LAN9220; the LAN9118 is software compatible + * except that it doesn't support the checksum-offload feature. + */ + qemu_check_nic_model(nd, "lan9118"); + mms->lan9118 = qdev_new(TYPE_LAN9118); + qdev_set_nic_properties(mms->lan9118, nd); + + s = SYS_BUS_DEVICE(mms->lan9118); + sysbus_realize_and_unref(s, &error_fatal); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqs[0])); + + memory_region_add_subregion(&mms->eth_usb_container, + 0, sysbus_mmio_get_region(s, 0)); + + /* The USB OTG controller is an ISP1763; we don't have a model of it. */ + object_initialize_child(OBJECT(mms), "usb-otg", + &mms->usb, TYPE_UNIMPLEMENTED_DEVICE); + qdev_prop_set_string(DEVICE(&mms->usb), "name", "usb-otg"); + qdev_prop_set_uint64(DEVICE(&mms->usb), "size", 0x100000); + s = SYS_BUS_DEVICE(&mms->usb); + sysbus_realize(s, &error_fatal); + + memory_region_add_subregion(&mms->eth_usb_container, + 0x100000, sysbus_mmio_get_region(s, 0)); + + return &mms->eth_usb_container; +} + static MemoryRegion *make_mpc(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, const int *irqs) @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) { "gpio1", make_unimp_dev, &mms->gpio[1], 0x41101000, 0x1000 }, { "gpio2", make_unimp_dev, &mms->gpio[2], 0x41102000, 0x1000 }, { "gpio3", make_unimp_dev, &mms->gpio[3], 0x41103000, 0x1000 }, - { "eth", make_eth_dev, NULL, 0x41400000, 0x100000, { 48 } }, + { "eth-usb", make_eth_usb, NULL, 0x41400000, 0x200000, { 48 } }, }, }, }; -- 2.20.1 The AN524 has a PL031 RTC, which we have a model of; provide it rather than an unimplemented-device stub. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-23-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ #include "hw/misc/tz-msc.h" #include "hw/arm/armsse.h" #include "hw/dma/pl080.h" +#include "hw/rtc/pl031.h" #include "hw/ssi/pl022.h" #include "hw/i2c/arm_sbcon_i2c.h" #include "hw/net/lan9118.h" @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { UnimplementedDeviceState gpio[4]; UnimplementedDeviceState gfx; UnimplementedDeviceState cldc; - UnimplementedDeviceState rtc; UnimplementedDeviceState usb; + PL031State rtc; PL080State dma[4]; TZMSC msc[4]; CMSDKAPBUART uart[6]; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_i2c(MPS2TZMachineState *mms, void *opaque, return sysbus_mmio_get_region(s, 0); } +static MemoryRegion *make_rtc(MPS2TZMachineState *mms, void *opaque, + const char *name, hwaddr size, + const int *irqs) +{ + PL031State *pl031 = opaque; + SysBusDevice *s; + + object_initialize_child(OBJECT(mms), name, pl031, TYPE_PL031); + s = SYS_BUS_DEVICE(pl031); + sysbus_realize(s, &error_fatal); + /* + * The board docs don't give an IRQ number for the PL031, so + * presumably it is not connected. + */ + return sysbus_mmio_get_region(s, 0); +} + static void create_non_mpc_ram(MPS2TZMachineState *mms) { /* @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) { /* port 9 reserved */ }, { "clcd", make_unimp_dev, &mms->cldc, 0x4130a000, 0x1000 }, - { "rtc", make_unimp_dev, &mms->rtc, 0x4130b000, 0x1000 }, + { "rtc", make_rtc, &mms->rtc, 0x4130b000, 0x1000 }, }, }, { .name = "ahb_ppcexp0", -- 2.20.1 Add brief documentation of the new mps3-an524 board. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-24-peter.maydell@linaro.org --- docs/system/arm/mps2.rst | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/docs/system/arm/mps2.rst b/docs/system/arm/mps2.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/mps2.rst +++ b/docs/system/arm/mps2.rst @@ -XXX,XX +XXX,XX @@ -Arm MPS2 boards (``mps2-an385``, ``mps2-an386``, ``mps2-an500``, ``mps2-an505``, ``mps2-an511``, ``mps2-an521``) -================================================================================================================ +Arm MPS2 and MPS3 boards (``mps2-an385``, ``mps2-an386``, ``mps2-an500``, ``mps2-an505``, ``mps2-an511``, ``mps2-an521``, ``mps3-an524``) +========================================================================================================================================= These board models all use Arm M-profile CPUs. -The Arm MPS2 and MPS2+ dev boards are FPGA based (the 2+ has a bigger -FPGA but is otherwise the same as the 2). Since the CPU itself -and most of the devices are in the FPGA, the details of the board -as seen by the guest depend significantly on the FPGA image. +The Arm MPS2, MPS2+ and MPS3 dev boards are FPGA based (the 2+ has a +bigger FPGA but is otherwise the same as the 2; the 3 has a bigger +FPGA again, can handle 4GB of RAM and has a USB controller and QSPI flash). + +Since the CPU itself and most of the devices are in the FPGA, the +details of the board as seen by the guest depend significantly on the +FPGA image. QEMU models the following FPGA images: @@ -XXX,XX +XXX,XX @@ QEMU models the following FPGA images: Cortex-M3 'DesignStart' as documented in Arm Application Note AN511 ``mps2-an521`` Dual Cortex-M33 as documented in Arm Application Note AN521 +``mps3-an524`` + Dual Cortex-M33 on an MPS3, as documented in Arm Application Note AN524 Differences between QEMU and real hardware: - AN385/AN386 remapping of low 16K of memory to either ZBT SSRAM1 or to block RAM is unimplemented (QEMU always maps this to ZBT SSRAM1, as if zbt_boot_ctrl is always zero) +- AN524 remapping of low memory to either BRAM or to QSPI flash is + unimplemented (QEMU always maps this to BRAM, ignoring the + SCC CFG_REG0 memory-remap bit) - QEMU provides a LAN9118 ethernet rather than LAN9220; the only guest visible difference is that the LAN9118 doesn't support checksum offloading +- QEMU does not model the QSPI flash in MPS3 boards as real QSPI + flash, but only as simple ROM, so attempting to rewrite the flash + from the guest will fail +- QEMU does not model the USB controller in MPS3 boards -- 2.20.1 Update old infocenter.arm.com URLs to the equivalent developer.arm.com ones (the old URLs should redirect, but we might as well avoid the redirection notice, and the new URLs are pleasantly shorter). This commit covers the links to the MPS2 board TRM, the various Application Notes, the IoTKit and SSE-200 documents. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-25-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 4 ++-- include/hw/misc/armsse-cpuid.h | 2 +- include/hw/misc/armsse-mhu.h | 2 +- include/hw/misc/iotkit-secctl.h | 2 +- include/hw/misc/iotkit-sysctl.h | 2 +- include/hw/misc/iotkit-sysinfo.h | 2 +- include/hw/misc/mps2-fpgaio.h | 2 +- hw/arm/mps2-tz.c | 11 +++++------ hw/misc/armsse-cpuid.c | 2 +- hw/misc/armsse-mhu.c | 2 +- hw/misc/iotkit-sysctl.c | 2 +- hw/misc/iotkit-sysinfo.c | 2 +- hw/misc/mps2-fpgaio.c | 2 +- hw/misc/mps2-scc.c | 2 +- 14 files changed, 19 insertions(+), 20 deletions(-) diff --git a/include/hw/arm/armsse.h b/include/hw/arm/armsse.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/armsse.h +++ b/include/hw/arm/armsse.h @@ -XXX,XX +XXX,XX @@ * hardware, which include the IoT Kit and the SSE-050, SSE-100 and * SSE-200. Currently we model: * - the Arm IoT Kit which is documented in - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * https://developer.arm.com/documentation/ecm0601256/latest * - the SSE-200 which is documented in - * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf + * https://developer.arm.com/documentation/101104/latest/ * * The IoTKit contains: * a Cortex-M33 diff --git a/include/hw/misc/armsse-cpuid.h b/include/hw/misc/armsse-cpuid.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/armsse-cpuid.h +++ b/include/hw/misc/armsse-cpuid.h @@ -XXX,XX +XXX,XX @@ /* * This is a model of the "CPU_IDENTITY" register block which is part of the * Arm SSE-200 and documented in - * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf + * https://developer.arm.com/documentation/101104/latest/ * * QEMU interface: * + QOM property "CPUID": the value to use for the CPUID register diff --git a/include/hw/misc/armsse-mhu.h b/include/hw/misc/armsse-mhu.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/armsse-mhu.h +++ b/include/hw/misc/armsse-mhu.h @@ -XXX,XX +XXX,XX @@ /* * This is a model of the Message Handling Unit (MHU) which is part of the * Arm SSE-200 and documented in - * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf + * https://developer.arm.com/documentation/101104/latest/ * * QEMU interface: * + sysbus MMIO region 0: the system information register bank diff --git a/include/hw/misc/iotkit-secctl.h b/include/hw/misc/iotkit-secctl.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/iotkit-secctl.h +++ b/include/hw/misc/iotkit-secctl.h @@ -XXX,XX +XXX,XX @@ /* This is a model of the security controller which is part of the * Arm IoT Kit and documented in - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * https://developer.arm.com/documentation/ecm0601256/latest * * QEMU interface: * + sysbus MMIO region 0 is the "secure privilege control block" registers diff --git a/include/hw/misc/iotkit-sysctl.h b/include/hw/misc/iotkit-sysctl.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/iotkit-sysctl.h +++ b/include/hw/misc/iotkit-sysctl.h @@ -XXX,XX +XXX,XX @@ /* * This is a model of the "system control element" which is part of the * Arm IoTKit and documented in - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * https://developer.arm.com/documentation/ecm0601256/latest * Specifically, it implements the "system information block" and * "system control register" blocks. * diff --git a/include/hw/misc/iotkit-sysinfo.h b/include/hw/misc/iotkit-sysinfo.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/iotkit-sysinfo.h +++ b/include/hw/misc/iotkit-sysinfo.h @@ -XXX,XX +XXX,XX @@ /* * This is a model of the "system information block" which is part of the * Arm IoTKit and documented in - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * https://developer.arm.com/documentation/ecm0601256/latest * QEMU interface: * + QOM property "SYS_VERSION": value to use for SYS_VERSION register * + QOM property "SYS_CONFIG": value to use for SYS_CONFIG register diff --git a/include/hw/misc/mps2-fpgaio.h b/include/hw/misc/mps2-fpgaio.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/mps2-fpgaio.h +++ b/include/hw/misc/mps2-fpgaio.h @@ -XXX,XX +XXX,XX @@ /* This is a model of the FPGAIO register block in the AN505 * FPGA image for the MPS2 dev board; it is documented in the * application note: - * http://infocenter.arm.com/help/topic/com.arm.doc.dai0505b/index.html + * https://developer.arm.com/documentation/dai0505/latest/ * * QEMU interface: * + sysbus MMIO region 0: the register bank diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ * https://developer.arm.com/products/system-design/development-boards/fpga-prototyping-boards/mps2 * * Board TRM: - * http://infocenter.arm.com/help/topic/com.arm.doc.100112_0200_06_en/versatile_express_cortex_m_prototyping_systems_v2m_mps2_and_v2m_mps2plus_technical_reference_100112_0200_06_en.pdf + * https://developer.arm.com/documentation/100112/latest/ * Application Note AN505: - * http://infocenter.arm.com/help/topic/com.arm.doc.dai0505b/index.html + * https://developer.arm.com/documentation/dai0505/latest/ * Application Note AN521: - * http://infocenter.arm.com/help/topic/com.arm.doc.dai0521c/index.html + * https://developer.arm.com/documentation/dai0521/latest/ * Application Note AN524: * https://developer.arm.com/documentation/dai0524/latest/ * * The AN505 defers to the Cortex-M33 processor ARMv8M IoT Kit FVP User Guide * (ARM ECM0601256) for the details of some of the device layout: - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * https://developer.arm.com/documentation/ecm0601256/latest * Similarly, the AN521 and AN524 use the SSE-200, and the SSE-200 TRM defines * most of the device layout: - * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf - * + * https://developer.arm.com/documentation/101104/latest/ */ #include "qemu/osdep.h" diff --git a/hw/misc/armsse-cpuid.c b/hw/misc/armsse-cpuid.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/armsse-cpuid.c +++ b/hw/misc/armsse-cpuid.c @@ -XXX,XX +XXX,XX @@ /* * This is a model of the "CPU_IDENTITY" register block which is part of the * Arm SSE-200 and documented in - * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf + * https://developer.arm.com/documentation/101104/latest/ * * It consists of one read-only CPUID register (set by QOM property), plus the * usual ID registers. diff --git a/hw/misc/armsse-mhu.c b/hw/misc/armsse-mhu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/armsse-mhu.c +++ b/hw/misc/armsse-mhu.c @@ -XXX,XX +XXX,XX @@ /* * This is a model of the Message Handling Unit (MHU) which is part of the * Arm SSE-200 and documented in - * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf + * https://developer.arm.com/documentation/101104/latest/ */ #include "qemu/osdep.h" diff --git a/hw/misc/iotkit-sysctl.c b/hw/misc/iotkit-sysctl.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/iotkit-sysctl.c +++ b/hw/misc/iotkit-sysctl.c @@ -XXX,XX +XXX,XX @@ /* * This is a model of the "system control element" which is part of the * Arm IoTKit and documented in - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * https://developer.arm.com/documentation/ecm0601256/latest * Specifically, it implements the "system control register" blocks. */ diff --git a/hw/misc/iotkit-sysinfo.c b/hw/misc/iotkit-sysinfo.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/iotkit-sysinfo.c +++ b/hw/misc/iotkit-sysinfo.c @@ -XXX,XX +XXX,XX @@ /* * This is a model of the "system information block" which is part of the * Arm IoTKit and documented in - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * https://developer.arm.com/documentation/ecm0601256/latest * It consists of 2 read-only version/config registers, plus the * usual ID registers. */ diff --git a/hw/misc/mps2-fpgaio.c b/hw/misc/mps2-fpgaio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mps2-fpgaio.c +++ b/hw/misc/mps2-fpgaio.c @@ -XXX,XX +XXX,XX @@ /* This is a model of the "FPGA system control and I/O" block found * in the AN505 FPGA image for the MPS2 devboard. * It is documented in AN505: - * http://infocenter.arm.com/help/topic/com.arm.doc.dai0505b/index.html + * https://developer.arm.com/documentation/dai0505/latest/ */ #include "qemu/osdep.h" diff --git a/hw/misc/mps2-scc.c b/hw/misc/mps2-scc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mps2-scc.c +++ b/hw/misc/mps2-scc.c @@ -XXX,XX +XXX,XX @@ * found in the FPGA images of MPS2 development boards. * * Documentation of it can be found in the MPS2 TRM: - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.100112_0100_03_en/index.html + * https://developer.arm.com/documentation/100112/latest/ * and also in the Application Notes documenting individual FPGA images. */ -- 2.20.1