Arm queue -- mostly the first slice of my Musca patches. thanks -- PMM The following changes since commit fc3dbb90f2eb069801bfb4cfe9cbc83cf9c5f4a9: Merge remote-tracking branch 'remotes/jnsnow/tags/bitmaps-pull-request' into staging (2019-02-21 13:09:33 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20190221 for you to fetch changes up to 3733f80308d2a7f23f5e39b039e0547aba6c07f1: hw/arm/armsse: Make 0x5... alias region work for per-CPU devices (2019-02-21 18:17:48 +0000) ---------------------------------------------------------------- target-arm queue: * Model the Arm "Musca" development boards: "musca-a" and "musca-b1" * Implement the ARMv8.3-JSConv extension * v8M MPU should use background region as default, not always * Stop unintentional sign extension in pmu_init ---------------------------------------------------------------- Aaron Lindsay OS (1): target/arm: Stop unintentional sign extension in pmu_init Peter Maydell (16): hw/arm/armsse: Fix memory leak in error-exit path target/arm: v8M MPU should use background region as default, not always hw/misc/tz-ppc: Support having unused ports in the middle of the range hw/timer/pl031: Allow use as an embedded-struct device hw/timer/pl031: Convert to using trace events hw/char/pl011: Allow use as an embedded-struct device hw/char/pl011: Support all interrupt lines hw/char/pl011: Use '0x' prefix when logging hex numbers hw/arm/armsse: Document SRAM_ADDR_WIDTH property in header comment hw/arm/armsse: Allow boards to specify init-svtor hw/arm/musca.c: Implement models of the Musca-A and -B1 boards hw/arm/musca: Add PPCs hw/arm/musca: Add MPCs hw/arm/musca: Wire up PL031 RTC hw/arm/musca: Wire up PL011 UARTs hw/arm/armsse: Make 0x5... alias region work for per-CPU devices Richard Henderson (4): target/arm: Restructure disas_fp_int_conv target/arm: Split out vfp_helper.c target/arm: Rearrange Floating-point data-processing (2 regs) target/arm: Implement ARMv8.3-JSConv hw/arm/Makefile.objs | 1 + target/arm/Makefile.objs | 2 +- include/hw/arm/armsse.h | 7 +- include/hw/char/pl011.h | 34 ++ include/hw/misc/tz-ppc.h | 8 +- include/hw/timer/pl031.h | 44 ++ target/arm/cpu.h | 10 + target/arm/helper.h | 3 + hw/arm/armsse.c | 44 +- hw/arm/musca.c | 669 ++++++++++++++++++++++ hw/char/pl011.c | 81 +-- hw/misc/tz-ppc.c | 32 ++ hw/timer/pl031.c | 80 ++- target/arm/cpu.c | 1 + target/arm/cpu64.c | 2 + target/arm/helper.c | 1072 +---------------------------------- target/arm/translate-a64.c | 120 ++-- target/arm/translate.c | 237 ++++---- target/arm/vfp_helper.c | 1176 +++++++++++++++++++++++++++++++++++++++ MAINTAINERS | 7 + default-configs/arm-softmmu.mak | 1 + hw/timer/trace-events | 6 + 22 files changed, 2307 insertions(+), 1330 deletions(-) create mode 100644 include/hw/timer/pl031.h create mode 100644 hw/arm/musca.c create mode 100644 target/arm/vfp_helper.c Coverity points out (CID 1398632, CID 1398650) that we leak a couple of allocated strings in the error-exit code path for setting up the MHUs in the ARMSSE. Fix this bug by moving the allocate-and-free of each string to be closer to the use, so we do the free before doing the error-exit check. Fixes: f8574705f62b38a ("hw/arm/armsse: Add unimplemented-device stubs for MHUs") Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20190215113707.24553-1-peter.maydell@linaro.org --- hw/arm/armsse.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armsse.c +++ b/hw/arm/armsse.c @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) if (info->has_mhus) { for (i = 0; i < ARRAY_SIZE(s->mhu); i++) { - char *name = g_strdup_printf("MHU%d", i); - char *port = g_strdup_printf("port[%d]", i + 3); + char *name; + char *port; + name = g_strdup_printf("MHU%d", i); qdev_prop_set_string(DEVICE(&s->mhu[i]), "name", name); qdev_prop_set_uint64(DEVICE(&s->mhu[i]), "size", 0x1000); object_property_set_bool(OBJECT(&s->mhu[i]), true, "realized", &err); + g_free(name); if (err) { error_propagate(errp, err); return; } + port = g_strdup_printf("port[%d]", i + 3); mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->mhu[i]), 0); object_property_set_link(OBJECT(&s->apb_ppc0), OBJECT(mr), port, &err); + g_free(port); if (err) { error_propagate(errp, err); return; } - g_free(name); - g_free(port); } } -- 2.20.1 The "background region" for a v8M MPU is a default which will be used (if enabled, and if the access is privileged) if the access does not match any specific MPU region. We were incorrectly using it always (by putting the condition at the wrong nesting level). This meant that we would always return the default background permissions rather than the correct permissions for a specific region, and also that we would not return the right information in response to a TT instruction. Move the check for the background region to the same place in the logic as the equivalent v8M MPUCheck() pseudocode puts it. This in turn means we must adjust the condition we use to detect matches in multiple regions to avoid false-positives. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190214113408.10214-1-peter.maydell@linaro.org --- target/arm/helper.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 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 bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, hit = true; } else if (m_is_ppb_region(env, address)) { hit = true; - } else if (pmsav7_use_background_region(cpu, mmu_idx, is_user)) { - hit = true; } else { + if (pmsav7_use_background_region(cpu, mmu_idx, is_user)) { + hit = true; + } + for (n = (int)cpu->pmsav7_dregion - 1; n >= 0; n--) { /* region search */ /* Note that the base address is bits [31:5] from the register @@ -XXX,XX +XXX,XX @@ static bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, *is_subpage = true; } - if (hit) { + if (matchregion != -1) { /* Multiple regions match -- always a failure (unlike * PMSAv7 where highest-numbered-region wins) */ -- 2.20.1 From: Aaron Lindsay OS <aaron@os.amperecomputing.com> This was introduced by commit bf8d09694ccc07487cd73d7562081fdaec3370c8 target/arm: Don't clear supported PMU events when initializing PMCEID1 and identified by Coverity (CID 1398645). Signed-off-by: Aaron Lindsay <aaron@os.amperecomputing.com> Reported-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190219144621.450-1-aaron@os.amperecomputing.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu) if (cnt->supported(&cpu->env)) { supported_event_map[cnt->number] = i; - uint64_t event_mask = 1 << (cnt->number & 0x1f); + uint64_t event_mask = 1ULL << (cnt->number & 0x1f); if (cnt->number & 0x20) { cpu->pmceid1 |= event_mask; } else { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> For opcodes 0-5, move some if conditions into the structure of a switch statement. For opcodes 6 & 7, decode everything at once with a second switch. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190215192302.27855-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 94 ++++++++++++++++++++------------------ 1 file changed, 49 insertions(+), 45 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) int type = extract32(insn, 22, 2); bool sbit = extract32(insn, 29, 1); bool sf = extract32(insn, 31, 1); + bool itof = false; if (sbit) { - unallocated_encoding(s); - return; + goto do_unallocated; } - if (opcode > 5) { - /* FMOV */ - bool itof = opcode & 1; - - if (rmode >= 2) { - unallocated_encoding(s); - return; - } - - switch (sf << 3 | type << 1 | rmode) { - case 0x0: /* 32 bit */ - case 0xa: /* 64 bit */ - case 0xd: /* 64 bit to top half of quad */ - break; - case 0x6: /* 16-bit float, 32-bit int */ - case 0xe: /* 16-bit float, 64-bit int */ - if (dc_isar_feature(aa64_fp16, s)) { - break; - } - /* fallthru */ - default: - /* all other sf/type/rmode combinations are invalid */ - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - handle_fmov(s, rd, rn, type, itof); - } else { - /* actual FP conversions */ - bool itof = extract32(opcode, 1, 1); - - if (rmode != 0 && opcode > 1) { - unallocated_encoding(s); - return; + switch (opcode) { + case 2: /* SCVTF */ + case 3: /* UCVTF */ + itof = true; + /* fallthru */ + case 4: /* FCVTAS */ + case 5: /* FCVTAU */ + if (rmode != 0) { + goto do_unallocated; } + /* fallthru */ + case 0: /* FCVT[NPMZ]S */ + case 1: /* FCVT[NPMZ]U */ switch (type) { case 0: /* float32 */ case 1: /* float64 */ break; case 3: /* float16 */ - if (dc_isar_feature(aa64_fp16, s)) { - break; + if (!dc_isar_feature(aa64_fp16, s)) { + goto do_unallocated; } - /* fallthru */ + break; default: - unallocated_encoding(s); - return; + goto do_unallocated; } - if (!fp_access_check(s)) { return; } handle_fpfpcvt(s, rd, rn, opcode, itof, rmode, 64, sf, type); + break; + + default: + switch (sf << 7 | type << 5 | rmode << 3 | opcode) { + case 0b01100110: /* FMOV half <-> 32-bit int */ + case 0b01100111: + case 0b11100110: /* FMOV half <-> 64-bit int */ + case 0b11100111: + if (!dc_isar_feature(aa64_fp16, s)) { + goto do_unallocated; + } + /* fallthru */ + case 0b00000110: /* FMOV 32-bit */ + case 0b00000111: + case 0b10100110: /* FMOV 64-bit */ + case 0b10100111: + case 0b11001110: /* FMOV top half of 128-bit */ + case 0b11001111: + if (!fp_access_check(s)) { + return; + } + itof = opcode & 1; + handle_fmov(s, rd, rn, type, itof); + break; + + default: + do_unallocated: + unallocated_encoding(s); + return; + } + break; } } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Move all of the fp helpers out of helper.c into a new file. This is code movement only. Since helper.c has no copyright header, take the one from cpu.h for the new file. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190215192302.27855-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/Makefile.objs | 2 +- target/arm/helper.c | 1062 ------------------------------------- target/arm/vfp_helper.c | 1088 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 1089 insertions(+), 1063 deletions(-) create mode 100644 target/arm/vfp_helper.c diff --git a/target/arm/Makefile.objs b/target/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/target/arm/Makefile.objs +++ b/target/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(call land,$(CONFIG_KVM),$(call lnot,$(TARGET_AARCH64))) += kvm32.o obj-$(call land,$(CONFIG_KVM),$(TARGET_AARCH64)) += kvm64.o obj-$(call lnot,$(CONFIG_KVM)) += kvm-stub.o obj-y += translate.o op_helper.o helper.o cpu.o -obj-y += neon_helper.o iwmmxt_helper.o vec_helper.o +obj-y += neon_helper.o iwmmxt_helper.o vec_helper.o vfp_helper.o obj-y += gdbstub.o obj-$(TARGET_AARCH64) += cpu64.o translate-a64.o helper-a64.o gdbstub64.o obj-$(TARGET_AARCH64) += pauth_helper.o diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(sel_flags)(uint32_t flags, uint32_t a, uint32_t b) return (a & mask) | (b & ~mask); } -/* VFP support. We follow the convention used for VFP instructions: - Single precision routines have a "s" suffix, double precision a - "d" suffix. */ - -/* Convert host exception flags to vfp form. */ -static inline int vfp_exceptbits_from_host(int host_bits) -{ - int target_bits = 0; - - if (host_bits & float_flag_invalid) - target_bits |= 1; - if (host_bits & float_flag_divbyzero) - target_bits |= 2; - if (host_bits & float_flag_overflow) - target_bits |= 4; - if (host_bits & (float_flag_underflow | float_flag_output_denormal)) - target_bits |= 8; - if (host_bits & float_flag_inexact) - target_bits |= 0x10; - if (host_bits & float_flag_input_denormal) - target_bits |= 0x80; - return target_bits; -} - -uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env) -{ - uint32_t i, fpscr; - - fpscr = env->vfp.xregs[ARM_VFP_FPSCR] - | (env->vfp.vec_len << 16) - | (env->vfp.vec_stride << 20); - - i = get_float_exception_flags(&env->vfp.fp_status); - i |= get_float_exception_flags(&env->vfp.standard_fp_status); - /* FZ16 does not generate an input denormal exception. */ - i |= (get_float_exception_flags(&env->vfp.fp_status_f16) - & ~float_flag_input_denormal); - fpscr |= vfp_exceptbits_from_host(i); - - i = env->vfp.qc[0] | env->vfp.qc[1] | env->vfp.qc[2] | env->vfp.qc[3]; - fpscr |= i ? FPCR_QC : 0; - - return fpscr; -} - -uint32_t vfp_get_fpscr(CPUARMState *env) -{ - return HELPER(vfp_get_fpscr)(env); -} - -/* Convert vfp exception flags to target form. */ -static inline int vfp_exceptbits_to_host(int target_bits) -{ - int host_bits = 0; - - if (target_bits & 1) - host_bits |= float_flag_invalid; - if (target_bits & 2) - host_bits |= float_flag_divbyzero; - if (target_bits & 4) - host_bits |= float_flag_overflow; - if (target_bits & 8) - host_bits |= float_flag_underflow; - if (target_bits & 0x10) - host_bits |= float_flag_inexact; - if (target_bits & 0x80) - host_bits |= float_flag_input_denormal; - return host_bits; -} - -void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) -{ - int i; - uint32_t changed = env->vfp.xregs[ARM_VFP_FPSCR]; - - /* When ARMv8.2-FP16 is not supported, FZ16 is RES0. */ - if (!cpu_isar_feature(aa64_fp16, arm_env_get_cpu(env))) { - val &= ~FPCR_FZ16; - } - - /* - * We don't implement trapped exception handling, so the - * trap enable bits, IDE|IXE|UFE|OFE|DZE|IOE are all RAZ/WI (not RES0!) - * - * If we exclude the exception flags, IOC|DZC|OFC|UFC|IXC|IDC - * (which are stored in fp_status), and the other RES0 bits - * in between, then we clear all of the low 16 bits. - */ - env->vfp.xregs[ARM_VFP_FPSCR] = val & 0xf7c80000; - env->vfp.vec_len = (val >> 16) & 7; - env->vfp.vec_stride = (val >> 20) & 3; - - /* - * The bit we set within fpscr_q is arbitrary; the register as a - * whole being zero/non-zero is what counts. - */ - env->vfp.qc[0] = val & FPCR_QC; - env->vfp.qc[1] = 0; - env->vfp.qc[2] = 0; - env->vfp.qc[3] = 0; - - changed ^= val; - if (changed & (3 << 22)) { - i = (val >> 22) & 3; - switch (i) { - case FPROUNDING_TIEEVEN: - i = float_round_nearest_even; - break; - case FPROUNDING_POSINF: - i = float_round_up; - break; - case FPROUNDING_NEGINF: - i = float_round_down; - break; - case FPROUNDING_ZERO: - i = float_round_to_zero; - break; - } - set_float_rounding_mode(i, &env->vfp.fp_status); - set_float_rounding_mode(i, &env->vfp.fp_status_f16); - } - if (changed & FPCR_FZ16) { - bool ftz_enabled = val & FPCR_FZ16; - set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_f16); - set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status_f16); - } - if (changed & FPCR_FZ) { - bool ftz_enabled = val & FPCR_FZ; - set_flush_to_zero(ftz_enabled, &env->vfp.fp_status); - set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status); - } - if (changed & FPCR_DN) { - bool dnan_enabled = val & FPCR_DN; - set_default_nan_mode(dnan_enabled, &env->vfp.fp_status); - set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_f16); - } - - /* The exception flags are ORed together when we read fpscr so we - * only need to preserve the current state in one of our - * float_status values. - */ - i = vfp_exceptbits_to_host(val); - set_float_exception_flags(i, &env->vfp.fp_status); - set_float_exception_flags(0, &env->vfp.fp_status_f16); - set_float_exception_flags(0, &env->vfp.standard_fp_status); -} - -void vfp_set_fpscr(CPUARMState *env, uint32_t val) -{ - HELPER(vfp_set_fpscr)(env, val); -} - -#define VFP_HELPER(name, p) HELPER(glue(glue(vfp_,name),p)) - -#define VFP_BINOP(name) \ -float32 VFP_HELPER(name, s)(float32 a, float32 b, void *fpstp) \ -{ \ - float_status *fpst = fpstp; \ - return float32_ ## name(a, b, fpst); \ -} \ -float64 VFP_HELPER(name, d)(float64 a, float64 b, void *fpstp) \ -{ \ - float_status *fpst = fpstp; \ - return float64_ ## name(a, b, fpst); \ -} -VFP_BINOP(add) -VFP_BINOP(sub) -VFP_BINOP(mul) -VFP_BINOP(div) -VFP_BINOP(min) -VFP_BINOP(max) -VFP_BINOP(minnum) -VFP_BINOP(maxnum) -#undef VFP_BINOP - -float32 VFP_HELPER(neg, s)(float32 a) -{ - return float32_chs(a); -} - -float64 VFP_HELPER(neg, d)(float64 a) -{ - return float64_chs(a); -} - -float32 VFP_HELPER(abs, s)(float32 a) -{ - return float32_abs(a); -} - -float64 VFP_HELPER(abs, d)(float64 a) -{ - return float64_abs(a); -} - -float32 VFP_HELPER(sqrt, s)(float32 a, CPUARMState *env) -{ - return float32_sqrt(a, &env->vfp.fp_status); -} - -float64 VFP_HELPER(sqrt, d)(float64 a, CPUARMState *env) -{ - return float64_sqrt(a, &env->vfp.fp_status); -} - -static void softfloat_to_vfp_compare(CPUARMState *env, int cmp) -{ - uint32_t flags; - switch (cmp) { - case float_relation_equal: - flags = 0x6; - break; - case float_relation_less: - flags = 0x8; - break; - case float_relation_greater: - flags = 0x2; - break; - case float_relation_unordered: - flags = 0x3; - break; - default: - g_assert_not_reached(); - } - env->vfp.xregs[ARM_VFP_FPSCR] = - deposit32(env->vfp.xregs[ARM_VFP_FPSCR], 28, 4, flags); -} - -/* XXX: check quiet/signaling case */ -#define DO_VFP_cmp(p, type) \ -void VFP_HELPER(cmp, p)(type a, type b, CPUARMState *env) \ -{ \ - softfloat_to_vfp_compare(env, \ - type ## _compare_quiet(a, b, &env->vfp.fp_status)); \ -} \ -void VFP_HELPER(cmpe, p)(type a, type b, CPUARMState *env) \ -{ \ - softfloat_to_vfp_compare(env, \ - type ## _compare(a, b, &env->vfp.fp_status)); \ -} -DO_VFP_cmp(s, float32) -DO_VFP_cmp(d, float64) -#undef DO_VFP_cmp - -/* Integer to float and float to integer conversions */ - -#define CONV_ITOF(name, ftype, fsz, sign) \ -ftype HELPER(name)(uint32_t x, void *fpstp) \ -{ \ - float_status *fpst = fpstp; \ - return sign##int32_to_##float##fsz((sign##int32_t)x, fpst); \ -} - -#define CONV_FTOI(name, ftype, fsz, sign, round) \ -sign##int32_t HELPER(name)(ftype x, void *fpstp) \ -{ \ - float_status *fpst = fpstp; \ - if (float##fsz##_is_any_nan(x)) { \ - float_raise(float_flag_invalid, fpst); \ - return 0; \ - } \ - return float##fsz##_to_##sign##int32##round(x, fpst); \ -} - -#define FLOAT_CONVS(name, p, ftype, fsz, sign) \ - CONV_ITOF(vfp_##name##to##p, ftype, fsz, sign) \ - CONV_FTOI(vfp_to##name##p, ftype, fsz, sign, ) \ - CONV_FTOI(vfp_to##name##z##p, ftype, fsz, sign, _round_to_zero) - -FLOAT_CONVS(si, h, uint32_t, 16, ) -FLOAT_CONVS(si, s, float32, 32, ) -FLOAT_CONVS(si, d, float64, 64, ) -FLOAT_CONVS(ui, h, uint32_t, 16, u) -FLOAT_CONVS(ui, s, float32, 32, u) -FLOAT_CONVS(ui, d, float64, 64, u) - -#undef CONV_ITOF -#undef CONV_FTOI -#undef FLOAT_CONVS - -/* floating point conversion */ -float64 VFP_HELPER(fcvtd, s)(float32 x, CPUARMState *env) -{ - return float32_to_float64(x, &env->vfp.fp_status); -} - -float32 VFP_HELPER(fcvts, d)(float64 x, CPUARMState *env) -{ - return float64_to_float32(x, &env->vfp.fp_status); -} - -/* 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, \ - 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, \ - void *fpst) \ -{ \ - if (unlikely(float##fsz##_is_any_nan(x))) { \ - float_raise(float_flag_invalid, fpst); \ - return 0; \ - } \ - 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, \ - float_round_to_zero, _round_to_zero) \ -VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, 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, \ - 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) - -#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. - */ -uint32_t HELPER(set_rmode)(uint32_t rmode, void *fpstp) -{ - float_status *fp_status = fpstp; - - uint32_t prev_rmode = get_float_rounding_mode(fp_status); - set_float_rounding_mode(rmode, fp_status); - - 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) -{ - /* Squash FZ16 to 0 for the duration of conversion. In this case, - * it would affect flushing input denormals. - */ - float_status *fpst = fpstp; - flag save = get_flush_inputs_to_zero(fpst); - set_flush_inputs_to_zero(false, fpst); - float32 r = float16_to_float32(a, !ahp_mode, fpst); - set_flush_inputs_to_zero(save, fpst); - return r; -} - -uint32_t HELPER(vfp_fcvt_f32_to_f16)(float32 a, void *fpstp, uint32_t ahp_mode) -{ - /* Squash FZ16 to 0 for the duration of conversion. In this case, - * it would affect flushing output denormals. - */ - float_status *fpst = fpstp; - flag save = get_flush_to_zero(fpst); - set_flush_to_zero(false, fpst); - float16 r = float32_to_float16(a, !ahp_mode, fpst); - set_flush_to_zero(save, fpst); - return r; -} - -float64 HELPER(vfp_fcvt_f16_to_f64)(uint32_t a, void *fpstp, uint32_t ahp_mode) -{ - /* Squash FZ16 to 0 for the duration of conversion. In this case, - * it would affect flushing input denormals. - */ - float_status *fpst = fpstp; - flag save = get_flush_inputs_to_zero(fpst); - set_flush_inputs_to_zero(false, fpst); - float64 r = float16_to_float64(a, !ahp_mode, fpst); - set_flush_inputs_to_zero(save, fpst); - return r; -} - -uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode) -{ - /* Squash FZ16 to 0 for the duration of conversion. In this case, - * it would affect flushing output denormals. - */ - float_status *fpst = fpstp; - flag save = get_flush_to_zero(fpst); - set_flush_to_zero(false, fpst); - float16 r = float64_to_float16(a, !ahp_mode, fpst); - set_flush_to_zero(save, fpst); - 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)(float32 a, float32 b, CPUARMState *env) -{ - 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)(float32 a, float32 b, CPUARMState *env) -{ - 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 - * int->float conversions at run-time. */ -#define float64_256 make_float64(0x4070000000000000LL) -#define float64_512 make_float64(0x4080000000000000LL) -#define float16_maxnorm make_float16(0x7bff) -#define float32_maxnorm make_float32(0x7f7fffff) -#define float64_maxnorm make_float64(0x7fefffffffffffffLL) - -/* Reciprocal functions - * - * The algorithm that must be used to calculate the estimate - * is specified by the ARM ARM, see FPRecipEstimate()/RecipEstimate - */ - -/* See RecipEstimate() - * - * input is a 9 bit fixed point number - * input range 256 .. 511 for a number from 0.5 <= x < 1.0. - * result range 256 .. 511 for a number from 1.0 to 511/256. - */ - -static int recip_estimate(int input) -{ - int a, b, r; - assert(256 <= input && input < 512); - a = (input * 2) + 1; - b = (1 << 19) / a; - r = (b + 1) >> 1; - assert(256 <= r && r < 512); - return r; -} - -/* - * Common wrapper to call recip_estimate - * - * The parameters are exponent and 64 bit fraction (without implicit - * bit) where the binary point is nominally at bit 52. Returns a - * float64 which can then be rounded to the appropriate size by the - * callee. - */ - -static uint64_t call_recip_estimate(int *exp, int exp_off, uint64_t frac) -{ - uint32_t scaled, estimate; - uint64_t result_frac; - int result_exp; - - /* Handle sub-normals */ - if (*exp == 0) { - if (extract64(frac, 51, 1) == 0) { - *exp = -1; - frac <<= 2; - } else { - frac <<= 1; - } - } - - /* scaled = UInt('1':fraction<51:44>) */ - scaled = deposit32(1 << 8, 0, 8, extract64(frac, 44, 8)); - estimate = recip_estimate(scaled); - - result_exp = exp_off - *exp; - result_frac = deposit64(0, 44, 8, estimate); - if (result_exp == 0) { - result_frac = deposit64(result_frac >> 1, 51, 1, 1); - } else if (result_exp == -1) { - result_frac = deposit64(result_frac >> 2, 50, 2, 1); - result_exp = 0; - } - - *exp = result_exp; - - return result_frac; -} - -static bool round_to_inf(float_status *fpst, bool sign_bit) -{ - switch (fpst->float_rounding_mode) { - case float_round_nearest_even: /* Round to Nearest */ - return true; - case float_round_up: /* Round to +Inf */ - return !sign_bit; - case float_round_down: /* Round to -Inf */ - return sign_bit; - case float_round_to_zero: /* Round to Zero */ - return false; - } - - g_assert_not_reached(); -} - -uint32_t HELPER(recpe_f16)(uint32_t input, void *fpstp) -{ - float_status *fpst = fpstp; - float16 f16 = float16_squash_input_denormal(input, fpst); - uint32_t f16_val = float16_val(f16); - uint32_t f16_sign = float16_is_neg(f16); - int f16_exp = extract32(f16_val, 10, 5); - uint32_t f16_frac = extract32(f16_val, 0, 10); - uint64_t f64_frac; - - if (float16_is_any_nan(f16)) { - float16 nan = f16; - if (float16_is_signaling_nan(f16, fpst)) { - float_raise(float_flag_invalid, fpst); - nan = float16_silence_nan(f16, fpst); - } - if (fpst->default_nan_mode) { - nan = float16_default_nan(fpst); - } - return nan; - } else if (float16_is_infinity(f16)) { - return float16_set_sign(float16_zero, float16_is_neg(f16)); - } else if (float16_is_zero(f16)) { - float_raise(float_flag_divbyzero, fpst); - return float16_set_sign(float16_infinity, float16_is_neg(f16)); - } else if (float16_abs(f16) < (1 << 8)) { - /* Abs(value) < 2.0^-16 */ - float_raise(float_flag_overflow | float_flag_inexact, fpst); - if (round_to_inf(fpst, f16_sign)) { - return float16_set_sign(float16_infinity, f16_sign); - } else { - return float16_set_sign(float16_maxnorm, f16_sign); - } - } else if (f16_exp >= 29 && fpst->flush_to_zero) { - float_raise(float_flag_underflow, fpst); - return float16_set_sign(float16_zero, float16_is_neg(f16)); - } - - f64_frac = call_recip_estimate(&f16_exp, 29, - ((uint64_t) f16_frac) << (52 - 10)); - - /* result = sign : result_exp<4:0> : fraction<51:42> */ - f16_val = deposit32(0, 15, 1, f16_sign); - f16_val = deposit32(f16_val, 10, 5, f16_exp); - f16_val = deposit32(f16_val, 0, 10, extract64(f64_frac, 52 - 10, 10)); - return make_float16(f16_val); -} - -float32 HELPER(recpe_f32)(float32 input, void *fpstp) -{ - float_status *fpst = fpstp; - float32 f32 = float32_squash_input_denormal(input, fpst); - uint32_t f32_val = float32_val(f32); - bool f32_sign = float32_is_neg(f32); - int f32_exp = extract32(f32_val, 23, 8); - uint32_t f32_frac = extract32(f32_val, 0, 23); - uint64_t f64_frac; - - if (float32_is_any_nan(f32)) { - float32 nan = f32; - if (float32_is_signaling_nan(f32, fpst)) { - float_raise(float_flag_invalid, fpst); - nan = float32_silence_nan(f32, fpst); - } - if (fpst->default_nan_mode) { - nan = float32_default_nan(fpst); - } - return nan; - } else if (float32_is_infinity(f32)) { - return float32_set_sign(float32_zero, float32_is_neg(f32)); - } else if (float32_is_zero(f32)) { - float_raise(float_flag_divbyzero, fpst); - return float32_set_sign(float32_infinity, float32_is_neg(f32)); - } else if (float32_abs(f32) < (1ULL << 21)) { - /* Abs(value) < 2.0^-128 */ - float_raise(float_flag_overflow | float_flag_inexact, fpst); - if (round_to_inf(fpst, f32_sign)) { - return float32_set_sign(float32_infinity, f32_sign); - } else { - return float32_set_sign(float32_maxnorm, f32_sign); - } - } else if (f32_exp >= 253 && fpst->flush_to_zero) { - float_raise(float_flag_underflow, fpst); - return float32_set_sign(float32_zero, float32_is_neg(f32)); - } - - f64_frac = call_recip_estimate(&f32_exp, 253, - ((uint64_t) f32_frac) << (52 - 23)); - - /* result = sign : result_exp<7:0> : fraction<51:29> */ - f32_val = deposit32(0, 31, 1, f32_sign); - f32_val = deposit32(f32_val, 23, 8, f32_exp); - f32_val = deposit32(f32_val, 0, 23, extract64(f64_frac, 52 - 23, 23)); - return make_float32(f32_val); -} - -float64 HELPER(recpe_f64)(float64 input, void *fpstp) -{ - float_status *fpst = fpstp; - float64 f64 = float64_squash_input_denormal(input, fpst); - uint64_t f64_val = float64_val(f64); - bool f64_sign = float64_is_neg(f64); - int f64_exp = extract64(f64_val, 52, 11); - uint64_t f64_frac = extract64(f64_val, 0, 52); - - /* Deal with any special cases */ - if (float64_is_any_nan(f64)) { - float64 nan = f64; - if (float64_is_signaling_nan(f64, fpst)) { - float_raise(float_flag_invalid, fpst); - nan = float64_silence_nan(f64, fpst); - } - if (fpst->default_nan_mode) { - nan = float64_default_nan(fpst); - } - return nan; - } else if (float64_is_infinity(f64)) { - return float64_set_sign(float64_zero, float64_is_neg(f64)); - } else if (float64_is_zero(f64)) { - float_raise(float_flag_divbyzero, fpst); - return float64_set_sign(float64_infinity, float64_is_neg(f64)); - } else if ((f64_val & ~(1ULL << 63)) < (1ULL << 50)) { - /* Abs(value) < 2.0^-1024 */ - float_raise(float_flag_overflow | float_flag_inexact, fpst); - if (round_to_inf(fpst, f64_sign)) { - return float64_set_sign(float64_infinity, f64_sign); - } else { - return float64_set_sign(float64_maxnorm, f64_sign); - } - } else if (f64_exp >= 2045 && fpst->flush_to_zero) { - float_raise(float_flag_underflow, fpst); - return float64_set_sign(float64_zero, float64_is_neg(f64)); - } - - f64_frac = call_recip_estimate(&f64_exp, 2045, f64_frac); - - /* result = sign : result_exp<10:0> : fraction<51:0>; */ - f64_val = deposit64(0, 63, 1, f64_sign); - f64_val = deposit64(f64_val, 52, 11, f64_exp); - f64_val = deposit64(f64_val, 0, 52, f64_frac); - return make_float64(f64_val); -} - -/* The algorithm that must be used to calculate the estimate - * is specified by the ARM ARM. - */ - -static int do_recip_sqrt_estimate(int a) -{ - int b, estimate; - - assert(128 <= a && a < 512); - if (a < 256) { - a = a * 2 + 1; - } else { - a = (a >> 1) << 1; - a = (a + 1) * 2; - } - b = 512; - while (a * (b + 1) * (b + 1) < (1 << 28)) { - b += 1; - } - estimate = (b + 1) / 2; - assert(256 <= estimate && estimate < 512); - - return estimate; -} - - -static uint64_t recip_sqrt_estimate(int *exp , int exp_off, uint64_t frac) -{ - int estimate; - uint32_t scaled; - - if (*exp == 0) { - while (extract64(frac, 51, 1) == 0) { - frac = frac << 1; - *exp -= 1; - } - frac = extract64(frac, 0, 51) << 1; - } - - if (*exp & 1) { - /* scaled = UInt('01':fraction<51:45>) */ - scaled = deposit32(1 << 7, 0, 7, extract64(frac, 45, 7)); - } else { - /* scaled = UInt('1':fraction<51:44>) */ - scaled = deposit32(1 << 8, 0, 8, extract64(frac, 44, 8)); - } - estimate = do_recip_sqrt_estimate(scaled); - - *exp = (exp_off - *exp) / 2; - return extract64(estimate, 0, 8) << 44; -} - -uint32_t HELPER(rsqrte_f16)(uint32_t input, void *fpstp) -{ - float_status *s = fpstp; - float16 f16 = float16_squash_input_denormal(input, s); - uint16_t val = float16_val(f16); - bool f16_sign = float16_is_neg(f16); - int f16_exp = extract32(val, 10, 5); - uint16_t f16_frac = extract32(val, 0, 10); - uint64_t f64_frac; - - if (float16_is_any_nan(f16)) { - float16 nan = f16; - if (float16_is_signaling_nan(f16, s)) { - float_raise(float_flag_invalid, s); - nan = float16_silence_nan(f16, s); - } - if (s->default_nan_mode) { - nan = float16_default_nan(s); - } - return nan; - } else if (float16_is_zero(f16)) { - float_raise(float_flag_divbyzero, s); - return float16_set_sign(float16_infinity, f16_sign); - } else if (f16_sign) { - float_raise(float_flag_invalid, s); - return float16_default_nan(s); - } else if (float16_is_infinity(f16)) { - return float16_zero; - } - - /* Scale and normalize to a double-precision value between 0.25 and 1.0, - * preserving the parity of the exponent. */ - - f64_frac = ((uint64_t) f16_frac) << (52 - 10); - - f64_frac = recip_sqrt_estimate(&f16_exp, 44, f64_frac); - - /* result = sign : result_exp<4:0> : estimate<7:0> : Zeros(2) */ - val = deposit32(0, 15, 1, f16_sign); - val = deposit32(val, 10, 5, f16_exp); - val = deposit32(val, 2, 8, extract64(f64_frac, 52 - 8, 8)); - return make_float16(val); -} - -float32 HELPER(rsqrte_f32)(float32 input, void *fpstp) -{ - float_status *s = fpstp; - float32 f32 = float32_squash_input_denormal(input, s); - uint32_t val = float32_val(f32); - uint32_t f32_sign = float32_is_neg(f32); - int f32_exp = extract32(val, 23, 8); - uint32_t f32_frac = extract32(val, 0, 23); - uint64_t f64_frac; - - if (float32_is_any_nan(f32)) { - float32 nan = f32; - if (float32_is_signaling_nan(f32, s)) { - float_raise(float_flag_invalid, s); - nan = float32_silence_nan(f32, s); - } - if (s->default_nan_mode) { - nan = float32_default_nan(s); - } - return nan; - } else if (float32_is_zero(f32)) { - float_raise(float_flag_divbyzero, s); - return float32_set_sign(float32_infinity, float32_is_neg(f32)); - } else if (float32_is_neg(f32)) { - float_raise(float_flag_invalid, s); - return float32_default_nan(s); - } else if (float32_is_infinity(f32)) { - return float32_zero; - } - - /* Scale and normalize to a double-precision value between 0.25 and 1.0, - * preserving the parity of the exponent. */ - - f64_frac = ((uint64_t) f32_frac) << 29; - - f64_frac = recip_sqrt_estimate(&f32_exp, 380, f64_frac); - - /* result = sign : result_exp<4:0> : estimate<7:0> : Zeros(15) */ - val = deposit32(0, 31, 1, f32_sign); - val = deposit32(val, 23, 8, f32_exp); - val = deposit32(val, 15, 8, extract64(f64_frac, 52 - 8, 8)); - return make_float32(val); -} - -float64 HELPER(rsqrte_f64)(float64 input, void *fpstp) -{ - float_status *s = fpstp; - float64 f64 = float64_squash_input_denormal(input, s); - uint64_t val = float64_val(f64); - bool f64_sign = float64_is_neg(f64); - int f64_exp = extract64(val, 52, 11); - uint64_t f64_frac = extract64(val, 0, 52); - - if (float64_is_any_nan(f64)) { - float64 nan = f64; - if (float64_is_signaling_nan(f64, s)) { - float_raise(float_flag_invalid, s); - nan = float64_silence_nan(f64, s); - } - if (s->default_nan_mode) { - nan = float64_default_nan(s); - } - return nan; - } else if (float64_is_zero(f64)) { - float_raise(float_flag_divbyzero, s); - return float64_set_sign(float64_infinity, float64_is_neg(f64)); - } else if (float64_is_neg(f64)) { - float_raise(float_flag_invalid, s); - return float64_default_nan(s); - } else if (float64_is_infinity(f64)) { - return float64_zero; - } - - f64_frac = recip_sqrt_estimate(&f64_exp, 3068, f64_frac); - - /* result = sign : result_exp<4:0> : estimate<7:0> : Zeros(44) */ - val = deposit64(0, 61, 1, f64_sign); - val = deposit64(val, 52, 11, f64_exp); - val = deposit64(val, 44, 8, extract64(f64_frac, 52 - 8, 8)); - return make_float64(val); -} - -uint32_t HELPER(recpe_u32)(uint32_t a, void *fpstp) -{ - /* float_status *s = fpstp; */ - int input, estimate; - - if ((a & 0x80000000) == 0) { - return 0xffffffff; - } - - input = extract32(a, 23, 9); - estimate = recip_estimate(input); - - return deposit32(0, (32 - 9), 9, estimate); -} - -uint32_t HELPER(rsqrte_u32)(uint32_t a, void *fpstp) -{ - int estimate; - - if ((a & 0xc0000000) == 0) { - return 0xffffffff; - } - - estimate = do_recip_sqrt_estimate(extract32(a, 23, 9)); - - return deposit32(0, 23, 9, estimate); -} - -/* VFPv4 fused multiply-accumulate */ -float32 VFP_HELPER(muladd, s)(float32 a, float32 b, float32 c, void *fpstp) -{ - float_status *fpst = fpstp; - return float32_muladd(a, b, c, 0, fpst); -} - -float64 VFP_HELPER(muladd, d)(float64 a, float64 b, float64 c, void *fpstp) -{ - float_status *fpst = fpstp; - return float64_muladd(a, b, c, 0, fpst); -} - -/* ARMv8 round to integral */ -float32 HELPER(rints_exact)(float32 x, void *fp_status) -{ - return float32_round_to_int(x, fp_status); -} - -float64 HELPER(rintd_exact)(float64 x, void *fp_status) -{ - return float64_round_to_int(x, fp_status); -} - -float32 HELPER(rints)(float32 x, void *fp_status) -{ - int old_flags = get_float_exception_flags(fp_status), new_flags; - float32 ret; - - ret = float32_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; -} - -float64 HELPER(rintd)(float64 x, void *fp_status) -{ - int old_flags = get_float_exception_flags(fp_status), new_flags; - float64 ret; - - ret = float64_round_to_int(x, fp_status); - - new_flags = get_float_exception_flags(fp_status); - - /* Suppress any inexact exceptions the conversion produced */ - if (!(old_flags & float_flag_inexact)) { - new_flags = get_float_exception_flags(fp_status); - set_float_exception_flags(new_flags & ~float_flag_inexact, fp_status); - } - - return ret; -} - -/* Convert ARM rounding mode to softfloat */ -int arm_rmode_to_sf(int rmode) -{ - switch (rmode) { - case FPROUNDING_TIEAWAY: - rmode = float_round_ties_away; - break; - case FPROUNDING_ODD: - /* FIXME: add support for TIEAWAY and ODD */ - qemu_log_mask(LOG_UNIMP, "arm: unimplemented rounding mode: %d\n", - rmode); - /* fall through for now */ - case FPROUNDING_TIEEVEN: - default: - rmode = float_round_nearest_even; - break; - case FPROUNDING_POSINF: - rmode = float_round_up; - break; - case FPROUNDING_NEGINF: - rmode = float_round_down; - break; - case FPROUNDING_ZERO: - rmode = float_round_to_zero; - break; - } - return rmode; -} - /* CRC helpers. * The upper bytes of val (above the number specified by 'bytes') must have * been zeroed out by the caller. diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ +/* + * ARM VFP floating-point operations + * + * Copyright (c) 2003 Fabrice Bellard + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "cpu.h" +#include "exec/helper-proto.h" +#include "fpu/softfloat.h" +#include "internals.h" + + +/* VFP support. We follow the convention used for VFP instructions: + Single precision routines have a "s" suffix, double precision a + "d" suffix. */ + +/* Convert host exception flags to vfp form. */ +static inline int vfp_exceptbits_from_host(int host_bits) +{ + int target_bits = 0; + + if (host_bits & float_flag_invalid) + target_bits |= 1; + if (host_bits & float_flag_divbyzero) + target_bits |= 2; + if (host_bits & float_flag_overflow) + target_bits |= 4; + if (host_bits & (float_flag_underflow | float_flag_output_denormal)) + target_bits |= 8; + if (host_bits & float_flag_inexact) + target_bits |= 0x10; + if (host_bits & float_flag_input_denormal) + target_bits |= 0x80; + return target_bits; +} + +uint32_t HELPER(vfp_get_fpscr)(CPUARMState *env) +{ + uint32_t i, fpscr; + + fpscr = env->vfp.xregs[ARM_VFP_FPSCR] + | (env->vfp.vec_len << 16) + | (env->vfp.vec_stride << 20); + + i = get_float_exception_flags(&env->vfp.fp_status); + i |= get_float_exception_flags(&env->vfp.standard_fp_status); + /* FZ16 does not generate an input denormal exception. */ + i |= (get_float_exception_flags(&env->vfp.fp_status_f16) + & ~float_flag_input_denormal); + fpscr |= vfp_exceptbits_from_host(i); + + i = env->vfp.qc[0] | env->vfp.qc[1] | env->vfp.qc[2] | env->vfp.qc[3]; + fpscr |= i ? FPCR_QC : 0; + + return fpscr; +} + +uint32_t vfp_get_fpscr(CPUARMState *env) +{ + return HELPER(vfp_get_fpscr)(env); +} + +/* Convert vfp exception flags to target form. */ +static inline int vfp_exceptbits_to_host(int target_bits) +{ + int host_bits = 0; + + if (target_bits & 1) + host_bits |= float_flag_invalid; + if (target_bits & 2) + host_bits |= float_flag_divbyzero; + if (target_bits & 4) + host_bits |= float_flag_overflow; + if (target_bits & 8) + host_bits |= float_flag_underflow; + if (target_bits & 0x10) + host_bits |= float_flag_inexact; + if (target_bits & 0x80) + host_bits |= float_flag_input_denormal; + return host_bits; +} + +void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) +{ + int i; + uint32_t changed = env->vfp.xregs[ARM_VFP_FPSCR]; + + /* When ARMv8.2-FP16 is not supported, FZ16 is RES0. */ + if (!cpu_isar_feature(aa64_fp16, arm_env_get_cpu(env))) { + val &= ~FPCR_FZ16; + } + + /* + * We don't implement trapped exception handling, so the + * trap enable bits, IDE|IXE|UFE|OFE|DZE|IOE are all RAZ/WI (not RES0!) + * + * If we exclude the exception flags, IOC|DZC|OFC|UFC|IXC|IDC + * (which are stored in fp_status), and the other RES0 bits + * in between, then we clear all of the low 16 bits. + */ + env->vfp.xregs[ARM_VFP_FPSCR] = val & 0xf7c80000; + env->vfp.vec_len = (val >> 16) & 7; + env->vfp.vec_stride = (val >> 20) & 3; + + /* + * The bit we set within fpscr_q is arbitrary; the register as a + * whole being zero/non-zero is what counts. + */ + env->vfp.qc[0] = val & FPCR_QC; + env->vfp.qc[1] = 0; + env->vfp.qc[2] = 0; + env->vfp.qc[3] = 0; + + changed ^= val; + if (changed & (3 << 22)) { + i = (val >> 22) & 3; + switch (i) { + case FPROUNDING_TIEEVEN: + i = float_round_nearest_even; + break; + case FPROUNDING_POSINF: + i = float_round_up; + break; + case FPROUNDING_NEGINF: + i = float_round_down; + break; + case FPROUNDING_ZERO: + i = float_round_to_zero; + break; + } + set_float_rounding_mode(i, &env->vfp.fp_status); + set_float_rounding_mode(i, &env->vfp.fp_status_f16); + } + if (changed & FPCR_FZ16) { + bool ftz_enabled = val & FPCR_FZ16; + set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_f16); + set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status_f16); + } + if (changed & FPCR_FZ) { + bool ftz_enabled = val & FPCR_FZ; + set_flush_to_zero(ftz_enabled, &env->vfp.fp_status); + set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status); + } + if (changed & FPCR_DN) { + bool dnan_enabled = val & FPCR_DN; + set_default_nan_mode(dnan_enabled, &env->vfp.fp_status); + set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_f16); + } + + /* The exception flags are ORed together when we read fpscr so we + * only need to preserve the current state in one of our + * float_status values. + */ + i = vfp_exceptbits_to_host(val); + set_float_exception_flags(i, &env->vfp.fp_status); + set_float_exception_flags(0, &env->vfp.fp_status_f16); + set_float_exception_flags(0, &env->vfp.standard_fp_status); +} + +void vfp_set_fpscr(CPUARMState *env, uint32_t val) +{ + HELPER(vfp_set_fpscr)(env, val); +} + +#define VFP_HELPER(name, p) HELPER(glue(glue(vfp_,name),p)) + +#define VFP_BINOP(name) \ +float32 VFP_HELPER(name, s)(float32 a, float32 b, void *fpstp) \ +{ \ + float_status *fpst = fpstp; \ + return float32_ ## name(a, b, fpst); \ +} \ +float64 VFP_HELPER(name, d)(float64 a, float64 b, void *fpstp) \ +{ \ + float_status *fpst = fpstp; \ + return float64_ ## name(a, b, fpst); \ +} +VFP_BINOP(add) +VFP_BINOP(sub) +VFP_BINOP(mul) +VFP_BINOP(div) +VFP_BINOP(min) +VFP_BINOP(max) +VFP_BINOP(minnum) +VFP_BINOP(maxnum) +#undef VFP_BINOP + +float32 VFP_HELPER(neg, s)(float32 a) +{ + return float32_chs(a); +} + +float64 VFP_HELPER(neg, d)(float64 a) +{ + return float64_chs(a); +} + +float32 VFP_HELPER(abs, s)(float32 a) +{ + return float32_abs(a); +} + +float64 VFP_HELPER(abs, d)(float64 a) +{ + return float64_abs(a); +} + +float32 VFP_HELPER(sqrt, s)(float32 a, CPUARMState *env) +{ + return float32_sqrt(a, &env->vfp.fp_status); +} + +float64 VFP_HELPER(sqrt, d)(float64 a, CPUARMState *env) +{ + return float64_sqrt(a, &env->vfp.fp_status); +} + +static void softfloat_to_vfp_compare(CPUARMState *env, int cmp) +{ + uint32_t flags; + switch (cmp) { + case float_relation_equal: + flags = 0x6; + break; + case float_relation_less: + flags = 0x8; + break; + case float_relation_greater: + flags = 0x2; + break; + case float_relation_unordered: + flags = 0x3; + break; + default: + g_assert_not_reached(); + } + env->vfp.xregs[ARM_VFP_FPSCR] = + deposit32(env->vfp.xregs[ARM_VFP_FPSCR], 28, 4, flags); +} + +/* XXX: check quiet/signaling case */ +#define DO_VFP_cmp(p, type) \ +void VFP_HELPER(cmp, p)(type a, type b, CPUARMState *env) \ +{ \ + softfloat_to_vfp_compare(env, \ + type ## _compare_quiet(a, b, &env->vfp.fp_status)); \ +} \ +void VFP_HELPER(cmpe, p)(type a, type b, CPUARMState *env) \ +{ \ + softfloat_to_vfp_compare(env, \ + type ## _compare(a, b, &env->vfp.fp_status)); \ +} +DO_VFP_cmp(s, float32) +DO_VFP_cmp(d, float64) +#undef DO_VFP_cmp + +/* Integer to float and float to integer conversions */ + +#define CONV_ITOF(name, ftype, fsz, sign) \ +ftype HELPER(name)(uint32_t x, void *fpstp) \ +{ \ + float_status *fpst = fpstp; \ + return sign##int32_to_##float##fsz((sign##int32_t)x, fpst); \ +} + +#define CONV_FTOI(name, ftype, fsz, sign, round) \ +sign##int32_t HELPER(name)(ftype x, void *fpstp) \ +{ \ + float_status *fpst = fpstp; \ + if (float##fsz##_is_any_nan(x)) { \ + float_raise(float_flag_invalid, fpst); \ + return 0; \ + } \ + return float##fsz##_to_##sign##int32##round(x, fpst); \ +} + +#define FLOAT_CONVS(name, p, ftype, fsz, sign) \ + CONV_ITOF(vfp_##name##to##p, ftype, fsz, sign) \ + CONV_FTOI(vfp_to##name##p, ftype, fsz, sign, ) \ + CONV_FTOI(vfp_to##name##z##p, ftype, fsz, sign, _round_to_zero) + +FLOAT_CONVS(si, h, uint32_t, 16, ) +FLOAT_CONVS(si, s, float32, 32, ) +FLOAT_CONVS(si, d, float64, 64, ) +FLOAT_CONVS(ui, h, uint32_t, 16, u) +FLOAT_CONVS(ui, s, float32, 32, u) +FLOAT_CONVS(ui, d, float64, 64, u) + +#undef CONV_ITOF +#undef CONV_FTOI +#undef FLOAT_CONVS + +/* floating point conversion */ +float64 VFP_HELPER(fcvtd, s)(float32 x, CPUARMState *env) +{ + return float32_to_float64(x, &env->vfp.fp_status); +} + +float32 VFP_HELPER(fcvts, d)(float64 x, CPUARMState *env) +{ + return float64_to_float32(x, &env->vfp.fp_status); +} + +/* 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, \ + 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, \ + void *fpst) \ +{ \ + if (unlikely(float##fsz##_is_any_nan(x))) { \ + float_raise(float_flag_invalid, fpst); \ + return 0; \ + } \ + 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, \ + float_round_to_zero, _round_to_zero) \ +VFP_CONV_FLOAT_FIX_ROUND(name, p, fsz, 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, \ + 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) + +#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. + */ +uint32_t HELPER(set_rmode)(uint32_t rmode, void *fpstp) +{ + float_status *fp_status = fpstp; + + uint32_t prev_rmode = get_float_rounding_mode(fp_status); + set_float_rounding_mode(rmode, fp_status); + + 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) +{ + /* Squash FZ16 to 0 for the duration of conversion. In this case, + * it would affect flushing input denormals. + */ + float_status *fpst = fpstp; + flag save = get_flush_inputs_to_zero(fpst); + set_flush_inputs_to_zero(false, fpst); + float32 r = float16_to_float32(a, !ahp_mode, fpst); + set_flush_inputs_to_zero(save, fpst); + return r; +} + +uint32_t HELPER(vfp_fcvt_f32_to_f16)(float32 a, void *fpstp, uint32_t ahp_mode) +{ + /* Squash FZ16 to 0 for the duration of conversion. In this case, + * it would affect flushing output denormals. + */ + float_status *fpst = fpstp; + flag save = get_flush_to_zero(fpst); + set_flush_to_zero(false, fpst); + float16 r = float32_to_float16(a, !ahp_mode, fpst); + set_flush_to_zero(save, fpst); + return r; +} + +float64 HELPER(vfp_fcvt_f16_to_f64)(uint32_t a, void *fpstp, uint32_t ahp_mode) +{ + /* Squash FZ16 to 0 for the duration of conversion. In this case, + * it would affect flushing input denormals. + */ + float_status *fpst = fpstp; + flag save = get_flush_inputs_to_zero(fpst); + set_flush_inputs_to_zero(false, fpst); + float64 r = float16_to_float64(a, !ahp_mode, fpst); + set_flush_inputs_to_zero(save, fpst); + return r; +} + +uint32_t HELPER(vfp_fcvt_f64_to_f16)(float64 a, void *fpstp, uint32_t ahp_mode) +{ + /* Squash FZ16 to 0 for the duration of conversion. In this case, + * it would affect flushing output denormals. + */ + float_status *fpst = fpstp; + flag save = get_flush_to_zero(fpst); + set_flush_to_zero(false, fpst); + float16 r = float64_to_float16(a, !ahp_mode, fpst); + set_flush_to_zero(save, fpst); + 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)(float32 a, float32 b, CPUARMState *env) +{ + 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)(float32 a, float32 b, CPUARMState *env) +{ + 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 + * int->float conversions at run-time. */ +#define float64_256 make_float64(0x4070000000000000LL) +#define float64_512 make_float64(0x4080000000000000LL) +#define float16_maxnorm make_float16(0x7bff) +#define float32_maxnorm make_float32(0x7f7fffff) +#define float64_maxnorm make_float64(0x7fefffffffffffffLL) + +/* Reciprocal functions + * + * The algorithm that must be used to calculate the estimate + * is specified by the ARM ARM, see FPRecipEstimate()/RecipEstimate + */ + +/* See RecipEstimate() + * + * input is a 9 bit fixed point number + * input range 256 .. 511 for a number from 0.5 <= x < 1.0. + * result range 256 .. 511 for a number from 1.0 to 511/256. + */ + +static int recip_estimate(int input) +{ + int a, b, r; + assert(256 <= input && input < 512); + a = (input * 2) + 1; + b = (1 << 19) / a; + r = (b + 1) >> 1; + assert(256 <= r && r < 512); + return r; +} + +/* + * Common wrapper to call recip_estimate + * + * The parameters are exponent and 64 bit fraction (without implicit + * bit) where the binary point is nominally at bit 52. Returns a + * float64 which can then be rounded to the appropriate size by the + * callee. + */ + +static uint64_t call_recip_estimate(int *exp, int exp_off, uint64_t frac) +{ + uint32_t scaled, estimate; + uint64_t result_frac; + int result_exp; + + /* Handle sub-normals */ + if (*exp == 0) { + if (extract64(frac, 51, 1) == 0) { + *exp = -1; + frac <<= 2; + } else { + frac <<= 1; + } + } + + /* scaled = UInt('1':fraction<51:44>) */ + scaled = deposit32(1 << 8, 0, 8, extract64(frac, 44, 8)); + estimate = recip_estimate(scaled); + + result_exp = exp_off - *exp; + result_frac = deposit64(0, 44, 8, estimate); + if (result_exp == 0) { + result_frac = deposit64(result_frac >> 1, 51, 1, 1); + } else if (result_exp == -1) { + result_frac = deposit64(result_frac >> 2, 50, 2, 1); + result_exp = 0; + } + + *exp = result_exp; + + return result_frac; +} + +static bool round_to_inf(float_status *fpst, bool sign_bit) +{ + switch (fpst->float_rounding_mode) { + case float_round_nearest_even: /* Round to Nearest */ + return true; + case float_round_up: /* Round to +Inf */ + return !sign_bit; + case float_round_down: /* Round to -Inf */ + return sign_bit; + case float_round_to_zero: /* Round to Zero */ + return false; + } + + g_assert_not_reached(); +} + +uint32_t HELPER(recpe_f16)(uint32_t input, void *fpstp) +{ + float_status *fpst = fpstp; + float16 f16 = float16_squash_input_denormal(input, fpst); + uint32_t f16_val = float16_val(f16); + uint32_t f16_sign = float16_is_neg(f16); + int f16_exp = extract32(f16_val, 10, 5); + uint32_t f16_frac = extract32(f16_val, 0, 10); + uint64_t f64_frac; + + if (float16_is_any_nan(f16)) { + float16 nan = f16; + if (float16_is_signaling_nan(f16, fpst)) { + float_raise(float_flag_invalid, fpst); + nan = float16_silence_nan(f16, fpst); + } + if (fpst->default_nan_mode) { + nan = float16_default_nan(fpst); + } + return nan; + } else if (float16_is_infinity(f16)) { + return float16_set_sign(float16_zero, float16_is_neg(f16)); + } else if (float16_is_zero(f16)) { + float_raise(float_flag_divbyzero, fpst); + return float16_set_sign(float16_infinity, float16_is_neg(f16)); + } else if (float16_abs(f16) < (1 << 8)) { + /* Abs(value) < 2.0^-16 */ + float_raise(float_flag_overflow | float_flag_inexact, fpst); + if (round_to_inf(fpst, f16_sign)) { + return float16_set_sign(float16_infinity, f16_sign); + } else { + return float16_set_sign(float16_maxnorm, f16_sign); + } + } else if (f16_exp >= 29 && fpst->flush_to_zero) { + float_raise(float_flag_underflow, fpst); + return float16_set_sign(float16_zero, float16_is_neg(f16)); + } + + f64_frac = call_recip_estimate(&f16_exp, 29, + ((uint64_t) f16_frac) << (52 - 10)); + + /* result = sign : result_exp<4:0> : fraction<51:42> */ + f16_val = deposit32(0, 15, 1, f16_sign); + f16_val = deposit32(f16_val, 10, 5, f16_exp); + f16_val = deposit32(f16_val, 0, 10, extract64(f64_frac, 52 - 10, 10)); + return make_float16(f16_val); +} + +float32 HELPER(recpe_f32)(float32 input, void *fpstp) +{ + float_status *fpst = fpstp; + float32 f32 = float32_squash_input_denormal(input, fpst); + uint32_t f32_val = float32_val(f32); + bool f32_sign = float32_is_neg(f32); + int f32_exp = extract32(f32_val, 23, 8); + uint32_t f32_frac = extract32(f32_val, 0, 23); + uint64_t f64_frac; + + if (float32_is_any_nan(f32)) { + float32 nan = f32; + if (float32_is_signaling_nan(f32, fpst)) { + float_raise(float_flag_invalid, fpst); + nan = float32_silence_nan(f32, fpst); + } + if (fpst->default_nan_mode) { + nan = float32_default_nan(fpst); + } + return nan; + } else if (float32_is_infinity(f32)) { + return float32_set_sign(float32_zero, float32_is_neg(f32)); + } else if (float32_is_zero(f32)) { + float_raise(float_flag_divbyzero, fpst); + return float32_set_sign(float32_infinity, float32_is_neg(f32)); + } else if (float32_abs(f32) < (1ULL << 21)) { + /* Abs(value) < 2.0^-128 */ + float_raise(float_flag_overflow | float_flag_inexact, fpst); + if (round_to_inf(fpst, f32_sign)) { + return float32_set_sign(float32_infinity, f32_sign); + } else { + return float32_set_sign(float32_maxnorm, f32_sign); + } + } else if (f32_exp >= 253 && fpst->flush_to_zero) { + float_raise(float_flag_underflow, fpst); + return float32_set_sign(float32_zero, float32_is_neg(f32)); + } + + f64_frac = call_recip_estimate(&f32_exp, 253, + ((uint64_t) f32_frac) << (52 - 23)); + + /* result = sign : result_exp<7:0> : fraction<51:29> */ + f32_val = deposit32(0, 31, 1, f32_sign); + f32_val = deposit32(f32_val, 23, 8, f32_exp); + f32_val = deposit32(f32_val, 0, 23, extract64(f64_frac, 52 - 23, 23)); + return make_float32(f32_val); +} + +float64 HELPER(recpe_f64)(float64 input, void *fpstp) +{ + float_status *fpst = fpstp; + float64 f64 = float64_squash_input_denormal(input, fpst); + uint64_t f64_val = float64_val(f64); + bool f64_sign = float64_is_neg(f64); + int f64_exp = extract64(f64_val, 52, 11); + uint64_t f64_frac = extract64(f64_val, 0, 52); + + /* Deal with any special cases */ + if (float64_is_any_nan(f64)) { + float64 nan = f64; + if (float64_is_signaling_nan(f64, fpst)) { + float_raise(float_flag_invalid, fpst); + nan = float64_silence_nan(f64, fpst); + } + if (fpst->default_nan_mode) { + nan = float64_default_nan(fpst); + } + return nan; + } else if (float64_is_infinity(f64)) { + return float64_set_sign(float64_zero, float64_is_neg(f64)); + } else if (float64_is_zero(f64)) { + float_raise(float_flag_divbyzero, fpst); + return float64_set_sign(float64_infinity, float64_is_neg(f64)); + } else if ((f64_val & ~(1ULL << 63)) < (1ULL << 50)) { + /* Abs(value) < 2.0^-1024 */ + float_raise(float_flag_overflow | float_flag_inexact, fpst); + if (round_to_inf(fpst, f64_sign)) { + return float64_set_sign(float64_infinity, f64_sign); + } else { + return float64_set_sign(float64_maxnorm, f64_sign); + } + } else if (f64_exp >= 2045 && fpst->flush_to_zero) { + float_raise(float_flag_underflow, fpst); + return float64_set_sign(float64_zero, float64_is_neg(f64)); + } + + f64_frac = call_recip_estimate(&f64_exp, 2045, f64_frac); + + /* result = sign : result_exp<10:0> : fraction<51:0>; */ + f64_val = deposit64(0, 63, 1, f64_sign); + f64_val = deposit64(f64_val, 52, 11, f64_exp); + f64_val = deposit64(f64_val, 0, 52, f64_frac); + return make_float64(f64_val); +} + +/* The algorithm that must be used to calculate the estimate + * is specified by the ARM ARM. + */ + +static int do_recip_sqrt_estimate(int a) +{ + int b, estimate; + + assert(128 <= a && a < 512); + if (a < 256) { + a = a * 2 + 1; + } else { + a = (a >> 1) << 1; + a = (a + 1) * 2; + } + b = 512; + while (a * (b + 1) * (b + 1) < (1 << 28)) { + b += 1; + } + estimate = (b + 1) / 2; + assert(256 <= estimate && estimate < 512); + + return estimate; +} + + +static uint64_t recip_sqrt_estimate(int *exp , int exp_off, uint64_t frac) +{ + int estimate; + uint32_t scaled; + + if (*exp == 0) { + while (extract64(frac, 51, 1) == 0) { + frac = frac << 1; + *exp -= 1; + } + frac = extract64(frac, 0, 51) << 1; + } + + if (*exp & 1) { + /* scaled = UInt('01':fraction<51:45>) */ + scaled = deposit32(1 << 7, 0, 7, extract64(frac, 45, 7)); + } else { + /* scaled = UInt('1':fraction<51:44>) */ + scaled = deposit32(1 << 8, 0, 8, extract64(frac, 44, 8)); + } + estimate = do_recip_sqrt_estimate(scaled); + + *exp = (exp_off - *exp) / 2; + return extract64(estimate, 0, 8) << 44; +} + +uint32_t HELPER(rsqrte_f16)(uint32_t input, void *fpstp) +{ + float_status *s = fpstp; + float16 f16 = float16_squash_input_denormal(input, s); + uint16_t val = float16_val(f16); + bool f16_sign = float16_is_neg(f16); + int f16_exp = extract32(val, 10, 5); + uint16_t f16_frac = extract32(val, 0, 10); + uint64_t f64_frac; + + if (float16_is_any_nan(f16)) { + float16 nan = f16; + if (float16_is_signaling_nan(f16, s)) { + float_raise(float_flag_invalid, s); + nan = float16_silence_nan(f16, s); + } + if (s->default_nan_mode) { + nan = float16_default_nan(s); + } + return nan; + } else if (float16_is_zero(f16)) { + float_raise(float_flag_divbyzero, s); + return float16_set_sign(float16_infinity, f16_sign); + } else if (f16_sign) { + float_raise(float_flag_invalid, s); + return float16_default_nan(s); + } else if (float16_is_infinity(f16)) { + return float16_zero; + } + + /* Scale and normalize to a double-precision value between 0.25 and 1.0, + * preserving the parity of the exponent. */ + + f64_frac = ((uint64_t) f16_frac) << (52 - 10); + + f64_frac = recip_sqrt_estimate(&f16_exp, 44, f64_frac); + + /* result = sign : result_exp<4:0> : estimate<7:0> : Zeros(2) */ + val = deposit32(0, 15, 1, f16_sign); + val = deposit32(val, 10, 5, f16_exp); + val = deposit32(val, 2, 8, extract64(f64_frac, 52 - 8, 8)); + return make_float16(val); +} + +float32 HELPER(rsqrte_f32)(float32 input, void *fpstp) +{ + float_status *s = fpstp; + float32 f32 = float32_squash_input_denormal(input, s); + uint32_t val = float32_val(f32); + uint32_t f32_sign = float32_is_neg(f32); + int f32_exp = extract32(val, 23, 8); + uint32_t f32_frac = extract32(val, 0, 23); + uint64_t f64_frac; + + if (float32_is_any_nan(f32)) { + float32 nan = f32; + if (float32_is_signaling_nan(f32, s)) { + float_raise(float_flag_invalid, s); + nan = float32_silence_nan(f32, s); + } + if (s->default_nan_mode) { + nan = float32_default_nan(s); + } + return nan; + } else if (float32_is_zero(f32)) { + float_raise(float_flag_divbyzero, s); + return float32_set_sign(float32_infinity, float32_is_neg(f32)); + } else if (float32_is_neg(f32)) { + float_raise(float_flag_invalid, s); + return float32_default_nan(s); + } else if (float32_is_infinity(f32)) { + return float32_zero; + } + + /* Scale and normalize to a double-precision value between 0.25 and 1.0, + * preserving the parity of the exponent. */ + + f64_frac = ((uint64_t) f32_frac) << 29; + + f64_frac = recip_sqrt_estimate(&f32_exp, 380, f64_frac); + + /* result = sign : result_exp<4:0> : estimate<7:0> : Zeros(15) */ + val = deposit32(0, 31, 1, f32_sign); + val = deposit32(val, 23, 8, f32_exp); + val = deposit32(val, 15, 8, extract64(f64_frac, 52 - 8, 8)); + return make_float32(val); +} + +float64 HELPER(rsqrte_f64)(float64 input, void *fpstp) +{ + float_status *s = fpstp; + float64 f64 = float64_squash_input_denormal(input, s); + uint64_t val = float64_val(f64); + bool f64_sign = float64_is_neg(f64); + int f64_exp = extract64(val, 52, 11); + uint64_t f64_frac = extract64(val, 0, 52); + + if (float64_is_any_nan(f64)) { + float64 nan = f64; + if (float64_is_signaling_nan(f64, s)) { + float_raise(float_flag_invalid, s); + nan = float64_silence_nan(f64, s); + } + if (s->default_nan_mode) { + nan = float64_default_nan(s); + } + return nan; + } else if (float64_is_zero(f64)) { + float_raise(float_flag_divbyzero, s); + return float64_set_sign(float64_infinity, float64_is_neg(f64)); + } else if (float64_is_neg(f64)) { + float_raise(float_flag_invalid, s); + return float64_default_nan(s); + } else if (float64_is_infinity(f64)) { + return float64_zero; + } + + f64_frac = recip_sqrt_estimate(&f64_exp, 3068, f64_frac); + + /* result = sign : result_exp<4:0> : estimate<7:0> : Zeros(44) */ + val = deposit64(0, 61, 1, f64_sign); + val = deposit64(val, 52, 11, f64_exp); + val = deposit64(val, 44, 8, extract64(f64_frac, 52 - 8, 8)); + return make_float64(val); +} + +uint32_t HELPER(recpe_u32)(uint32_t a, void *fpstp) +{ + /* float_status *s = fpstp; */ + int input, estimate; + + if ((a & 0x80000000) == 0) { + return 0xffffffff; + } + + input = extract32(a, 23, 9); + estimate = recip_estimate(input); + + return deposit32(0, (32 - 9), 9, estimate); +} + +uint32_t HELPER(rsqrte_u32)(uint32_t a, void *fpstp) +{ + int estimate; + + if ((a & 0xc0000000) == 0) { + return 0xffffffff; + } + + estimate = do_recip_sqrt_estimate(extract32(a, 23, 9)); + + return deposit32(0, 23, 9, estimate); +} + +/* VFPv4 fused multiply-accumulate */ +float32 VFP_HELPER(muladd, s)(float32 a, float32 b, float32 c, void *fpstp) +{ + float_status *fpst = fpstp; + return float32_muladd(a, b, c, 0, fpst); +} + +float64 VFP_HELPER(muladd, d)(float64 a, float64 b, float64 c, void *fpstp) +{ + float_status *fpst = fpstp; + return float64_muladd(a, b, c, 0, fpst); +} + +/* ARMv8 round to integral */ +float32 HELPER(rints_exact)(float32 x, void *fp_status) +{ + return float32_round_to_int(x, fp_status); +} + +float64 HELPER(rintd_exact)(float64 x, void *fp_status) +{ + return float64_round_to_int(x, fp_status); +} + +float32 HELPER(rints)(float32 x, void *fp_status) +{ + int old_flags = get_float_exception_flags(fp_status), new_flags; + float32 ret; + + ret = float32_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; +} + +float64 HELPER(rintd)(float64 x, void *fp_status) +{ + int old_flags = get_float_exception_flags(fp_status), new_flags; + float64 ret; + + ret = float64_round_to_int(x, fp_status); + + new_flags = get_float_exception_flags(fp_status); + + /* Suppress any inexact exceptions the conversion produced */ + if (!(old_flags & float_flag_inexact)) { + new_flags = get_float_exception_flags(fp_status); + set_float_exception_flags(new_flags & ~float_flag_inexact, fp_status); + } + + return ret; +} + +/* Convert ARM rounding mode to softfloat */ +int arm_rmode_to_sf(int rmode) +{ + switch (rmode) { + case FPROUNDING_TIEAWAY: + rmode = float_round_ties_away; + break; + case FPROUNDING_ODD: + /* FIXME: add support for TIEAWAY and ODD */ + qemu_log_mask(LOG_UNIMP, "arm: unimplemented rounding mode: %d\n", + rmode); + /* fall through for now */ + case FPROUNDING_TIEEVEN: + default: + rmode = float_round_nearest_even; + break; + case FPROUNDING_POSINF: + rmode = float_round_up; + break; + case FPROUNDING_NEGINF: + rmode = float_round_down; + break; + case FPROUNDING_ZERO: + rmode = float_round_to_zero; + break; + } + return rmode; +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> There are lots of special cases within these insns. Split the major argument decode/loading/saving into no_output (compares), rd_is_dp, and rm_is_dp. We still need to special case argument load for compare (rd as input, rm as zero) and vcvt fixed (rd as input+output), but lots of special cases do disappear. Now that we have a full switch at the beginning, hoist the ISA checks from the code generation. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190215192302.27855-4-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 227 ++++++++++++++++++++--------------------- 1 file changed, 111 insertions(+), 116 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) } } else { /* data processing */ + bool rd_is_dp = dp; + bool rm_is_dp = dp; + bool no_output = false; + /* The opcode is in bits 23, 21, 20 and 6. */ op = ((insn >> 20) & 8) | ((insn >> 19) & 6) | ((insn >> 6) & 1); - if (dp) { - if (op == 15) { - /* rn is opcode */ - rn = ((insn >> 15) & 0x1e) | ((insn >> 7) & 1); - } else { - /* rn is register number */ - VFP_DREG_N(rn, insn); - } + rn = VFP_SREG_N(insn); - if (op == 15 && (rn == 15 || ((rn & 0x1c) == 0x18) || - ((rn & 0x1e) == 0x6))) { - /* Integer or single/half precision destination. */ - rd = VFP_SREG_D(insn); - } else { - VFP_DREG_D(rd, insn); - } - if (op == 15 && - (((rn & 0x1c) == 0x10) || ((rn & 0x14) == 0x14) || - ((rn & 0x1e) == 0x4))) { - /* VCVT from int or half precision is always from S reg - * regardless of dp bit. VCVT with immediate frac_bits - * has same format as SREG_M. + if (op == 15) { + /* rn is opcode, encoded as per VFP_SREG_N. */ + switch (rn) { + case 0x00: /* vmov */ + case 0x01: /* vabs */ + case 0x02: /* vneg */ + case 0x03: /* vsqrt */ + break; + + case 0x04: /* vcvtb.f64.f16, vcvtb.f32.f16 */ + case 0x05: /* vcvtt.f64.f16, vcvtt.f32.f16 */ + /* + * VCVTB, VCVTT: only present with the halfprec extension + * UNPREDICTABLE if bit 8 is set prior to ARMv8 + * (we choose to UNDEF) */ - rm = VFP_SREG_M(insn); - } else { - VFP_DREG_M(rm, insn); + if ((dp && !arm_dc_feature(s, ARM_FEATURE_V8)) || + !arm_dc_feature(s, ARM_FEATURE_VFP_FP16)) { + return 1; + } + rm_is_dp = false; + break; + case 0x06: /* vcvtb.f16.f32, vcvtb.f16.f64 */ + case 0x07: /* vcvtt.f16.f32, vcvtt.f16.f64 */ + if ((dp && !arm_dc_feature(s, ARM_FEATURE_V8)) || + !arm_dc_feature(s, ARM_FEATURE_VFP_FP16)) { + return 1; + } + rd_is_dp = false; + break; + + case 0x08: case 0x0a: /* vcmp, vcmpz */ + case 0x09: case 0x0b: /* vcmpe, vcmpez */ + no_output = true; + break; + + case 0x0c: /* vrintr */ + case 0x0d: /* vrintz */ + case 0x0e: /* vrintx */ + break; + + case 0x0f: /* vcvt double<->single */ + rd_is_dp = !dp; + break; + + case 0x10: /* vcvt.fxx.u32 */ + case 0x11: /* vcvt.fxx.s32 */ + rm_is_dp = false; + break; + case 0x18: /* vcvtr.u32.fxx */ + case 0x19: /* vcvtz.u32.fxx */ + case 0x1a: /* vcvtr.s32.fxx */ + case 0x1b: /* vcvtz.s32.fxx */ + rd_is_dp = false; + break; + + case 0x14: /* vcvt fp <-> fixed */ + case 0x15: + case 0x16: + case 0x17: + case 0x1c: + case 0x1d: + case 0x1e: + case 0x1f: + if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { + return 1; + } + /* Immediate frac_bits has same format as SREG_M. */ + rm_is_dp = false; + break; + + default: + return 1; } + } else if (dp) { + /* rn is register number */ + VFP_DREG_N(rn, insn); + } + + if (rd_is_dp) { + VFP_DREG_D(rd, insn); + } else { + rd = VFP_SREG_D(insn); + } + if (rm_is_dp) { + VFP_DREG_M(rm, insn); } else { - rn = VFP_SREG_N(insn); - if (op == 15 && rn == 15) { - /* Double precision destination. */ - VFP_DREG_D(rd, insn); - } else { - rd = VFP_SREG_D(insn); - } - /* NB that we implicitly rely on the encoding for the frac_bits - * in VCVT of fixed to float being the same as that of an SREG_M - */ rm = VFP_SREG_M(insn); } veclen = s->vec_len; - if (op == 15 && rn > 3) + if (op == 15 && rn > 3) { veclen = 0; + } /* Shut up compiler warnings. */ delta_m = 0; @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) /* Load the initial operands. */ if (op == 15) { switch (rn) { - case 16: - case 17: - /* Integer source */ - gen_mov_F0_vreg(0, rm); - break; - case 8: - case 9: - /* Compare */ + case 0x08: case 0x09: /* Compare */ gen_mov_F0_vreg(dp, rd); gen_mov_F1_vreg(dp, rm); break; - case 10: - case 11: - /* Compare with zero */ + case 0x0a: case 0x0b: /* Compare with zero */ gen_mov_F0_vreg(dp, rd); gen_vfp_F1_ld0(dp); break; - case 20: - case 21: - case 22: - case 23: - case 28: - case 29: - case 30: - case 31: + case 0x14: /* vcvt fp <-> fixed */ + case 0x15: + case 0x16: + case 0x17: + case 0x1c: + case 0x1d: + case 0x1e: + case 0x1f: /* Source and destination the same. */ gen_mov_F0_vreg(dp, rd); break; - case 4: - case 5: - case 6: - case 7: - /* VCVTB, VCVTT: only present with the halfprec extension - * UNPREDICTABLE if bit 8 is set prior to ARMv8 - * (we choose to UNDEF) - */ - if ((dp && !arm_dc_feature(s, ARM_FEATURE_V8)) || - !arm_dc_feature(s, ARM_FEATURE_VFP_FP16)) { - return 1; - } - if (!extract32(rn, 1, 1)) { - /* Half precision source. */ - gen_mov_F0_vreg(0, rm); - break; - } - /* Otherwise fall through */ default: /* One source operand. */ - gen_mov_F0_vreg(dp, rm); + gen_mov_F0_vreg(rm_is_dp, rm); break; } } else { @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) break; } case 15: /* single<->double conversion */ - if (dp) + if (dp) { gen_helper_vfp_fcvtsd(cpu_F0s, cpu_F0d, cpu_env); - else + } else { gen_helper_vfp_fcvtds(cpu_F0d, cpu_F0s, cpu_env); + } break; case 16: /* fuito */ gen_vfp_uito(dp, 0); @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) gen_vfp_sito(dp, 0); break; case 20: /* fshto */ - if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { - return 1; - } gen_vfp_shto(dp, 16 - rm, 0); break; case 21: /* fslto */ - if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { - return 1; - } gen_vfp_slto(dp, 32 - rm, 0); break; case 22: /* fuhto */ - if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { - return 1; - } gen_vfp_uhto(dp, 16 - rm, 0); break; case 23: /* fulto */ - if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { - return 1; - } gen_vfp_ulto(dp, 32 - rm, 0); break; case 24: /* ftoui */ @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) gen_vfp_tosiz(dp, 0); break; case 28: /* ftosh */ - if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { - return 1; - } gen_vfp_tosh(dp, 16 - rm, 0); break; case 29: /* ftosl */ - if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { - return 1; - } gen_vfp_tosl(dp, 32 - rm, 0); break; case 30: /* ftouh */ - if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { - return 1; - } gen_vfp_touh(dp, 16 - rm, 0); break; case 31: /* ftoul */ - if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { - return 1; - } gen_vfp_toul(dp, 32 - rm, 0); break; default: /* undefined */ - return 1; + g_assert_not_reached(); } break; default: /* undefined */ return 1; } - /* Write back the result. */ - if (op == 15 && (rn >= 8 && rn <= 11)) { - /* Comparison, do nothing. */ - } else if (op == 15 && dp && ((rn & 0x1c) == 0x18 || - (rn & 0x1e) == 0x6)) { - /* VCVT double to int: always integer result. - * VCVT double to half precision is always a single - * precision result. - */ - gen_mov_vreg_F0(0, rd); - } else if (op == 15 && rn == 15) { - /* conversion */ - gen_mov_vreg_F0(!dp, rd); - } else { - gen_mov_vreg_F0(dp, rd); + /* Write back the result, if any. */ + if (!no_output) { + gen_mov_vreg_F0(rd_is_dp, rd); } /* break out of the loop if we have finished */ - if (veclen == 0) + if (veclen == 0) { break; + } if (op == 15 && delta_m == 0) { /* single source one-many */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190215192302.27855-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: fixed a couple of comment typos] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 10 +++++ target/arm/helper.h | 3 ++ target/arm/cpu.c | 1 + target/arm/cpu64.c | 2 + target/arm/translate-a64.c | 26 +++++++++++ target/arm/translate.c | 10 +++++ target/arm/vfp_helper.c | 88 ++++++++++++++++++++++++++++++++++++++ 7 files changed, 140 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_vcma(const ARMISARegisters *id) return FIELD_EX32(id->id_isar5, ID_ISAR5, VCMA) != 0; } +static inline bool isar_feature_aa32_jscvt(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, JSCVT) != 0; +} + static inline bool isar_feature_aa32_dp(const ARMISARegisters *id) { return FIELD_EX32(id->id_isar6, ID_ISAR6, DP) != 0; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_dp(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, DP) != 0; } +static inline bool isar_feature_aa64_jscvt(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, JSCVT) != 0; +} + static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(rintd_exact, TCG_CALL_NO_RWG, f64, f64, ptr) DEF_HELPER_FLAGS_2(rints, TCG_CALL_NO_RWG, f32, f32, ptr) DEF_HELPER_FLAGS_2(rintd, TCG_CALL_NO_RWG, f64, f64, ptr) +DEF_HELPER_FLAGS_2(vjcvt, TCG_CALL_NO_RWG, i32, f64, env) +DEF_HELPER_FLAGS_2(fjcvtzs, TCG_CALL_NO_RWG, i64, f64, ptr) + /* neon_helper.c */ DEF_HELPER_FLAGS_3(neon_qadd_u8, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(neon_qadd_s8, TCG_CALL_NO_RWG, i32, env, i32, i32) 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_isar5 = t; t = cpu->isar.id_isar6; + t = FIELD_DP32(t, ID_ISAR6, JSCVT, 1); t = FIELD_DP32(t, ID_ISAR6, DP, 1); cpu->isar.id_isar6 = t; 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) cpu->isar.id_aa64isar0 = t; t = cpu->isar.id_aa64isar1; + t = FIELD_DP64(t, ID_AA64ISAR1, JSCVT, 1); t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); t = FIELD_DP64(t, ID_AA64ISAR1, APA, 1); /* PAuth, architected only */ t = FIELD_DP64(t, ID_AA64ISAR1, API, 0); @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) cpu->isar.id_isar5 = u; u = cpu->isar.id_isar6; + u = FIELD_DP32(u, ID_ISAR6, JSCVT, 1); u = FIELD_DP32(u, ID_ISAR6, DP, 1); cpu->isar.id_isar6 = u; 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_fmov(DisasContext *s, int rd, int rn, int type, bool itof) } } +static void handle_fjcvtzs(DisasContext *s, int rd, int rn) +{ + TCGv_i64 t = read_fp_dreg(s, rn); + TCGv_ptr fpstatus = get_fpstatus_ptr(false); + + gen_helper_fjcvtzs(t, t, fpstatus); + + tcg_temp_free_ptr(fpstatus); + + tcg_gen_ext32u_i64(cpu_reg(s, rd), t); + tcg_gen_extrh_i64_i32(cpu_ZF, t); + tcg_gen_movi_i32(cpu_CF, 0); + tcg_gen_movi_i32(cpu_NF, 0); + tcg_gen_movi_i32(cpu_VF, 0); + + tcg_temp_free_i64(t); +} + /* Floating point <-> integer conversions * 31 30 29 28 24 23 22 21 20 19 18 16 15 10 9 5 4 0 * +----+---+---+-----------+------+---+-------+-----+-------------+----+----+ @@ -XXX,XX +XXX,XX @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) handle_fmov(s, rd, rn, type, itof); break; + case 0b00111110: /* FJCVTZS */ + if (!dc_isar_feature(aa64_jscvt, s)) { + goto do_unallocated; + } else if (fp_access_check(s)) { + handle_fjcvtzs(s, rd, rn); + } + break; + default: do_unallocated: unallocated_encoding(s); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) rm_is_dp = false; break; + case 0x13: /* vjcvt */ + if (!dp || !dc_isar_feature(aa32_jscvt, s)) { + return 1; + } + rd_is_dp = false; + break; + default: return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) case 17: /* fsito */ gen_vfp_sito(dp, 0); break; + case 19: /* vjcvt */ + gen_helper_vjcvt(cpu_F0s, cpu_F0d, cpu_env); + break; case 20: /* fshto */ gen_vfp_shto(dp, 16 - rm, 0); break; diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ int arm_rmode_to_sf(int rmode) } return rmode; } + +/* + * Implement float64 to int32_t conversion without saturation; + * the result is supplied modulo 2^32. + */ +uint64_t HELPER(fjcvtzs)(float64 value, void *vstatus) +{ + float_status *status = vstatus; + uint32_t exp, sign; + uint64_t frac; + uint32_t inexact = 1; /* !Z */ + + sign = extract64(value, 63, 1); + exp = extract64(value, 52, 11); + frac = extract64(value, 0, 52); + + if (exp == 0) { + /* While not inexact for IEEE FP, -0.0 is inexact for JavaScript. */ + inexact = sign; + if (frac != 0) { + if (status->flush_inputs_to_zero) { + float_raise(float_flag_input_denormal, status); + } else { + float_raise(float_flag_inexact, status); + inexact = 1; + } + } + frac = 0; + } else if (exp == 0x7ff) { + /* This operation raises Invalid for both NaN and overflow (Inf). */ + float_raise(float_flag_invalid, status); + frac = 0; + } else { + int true_exp = exp - 1023; + int shift = true_exp - 52; + + /* Restore implicit bit. */ + frac |= 1ull << 52; + + /* Shift the fraction into place. */ + if (shift >= 0) { + /* The number is so large we must shift the fraction left. */ + if (shift >= 64) { + /* The fraction is shifted out entirely. */ + frac = 0; + } else { + frac <<= shift; + } + } else if (shift > -64) { + /* Normal case -- shift right and notice if bits shift out. */ + inexact = (frac << (64 + shift)) != 0; + frac >>= -shift; + } else { + /* The fraction is shifted out entirely. */ + frac = 0; + } + + /* Notice overflow or inexact exceptions. */ + if (true_exp > 31 || frac > (sign ? 0x80000000ull : 0x7fffffff)) { + /* Overflow, for which this operation raises invalid. */ + float_raise(float_flag_invalid, status); + inexact = 1; + } else if (inexact) { + float_raise(float_flag_inexact, status); + } + + /* Honor the sign. */ + if (sign) { + frac = -frac; + } + } + + /* Pack the result and the env->ZF representation of Z together. */ + return deposit64(frac, 32, 32, inexact); +} + +uint32_t HELPER(vjcvt)(float64 value, CPUARMState *env) +{ + uint64_t pair = HELPER(fjcvtzs)(value, &env->vfp.fp_status); + uint32_t result = pair; + uint32_t z = (pair >> 32) == 0; + + /* Store Z, clear NCV, in FPSCR.NZCV. */ + env->vfp.xregs[ARM_VFP_FPSCR] + = (env->vfp.xregs[ARM_VFP_FPSCR] & ~CPSR_NZCV) | (z * CPSR_Z); + + return result; +} -- 2.20.1 The Peripheral Protection Controller's handling of unused ports is that if there is nothing connected to the port's downstream then it does not create the sysbus MMIO region for the upstream end of the port. This results in odd behaviour when there is an unused port in the middle of the range: since sysbus MMIO regions are implicitly consecutively allocated, any used ports above the unused ones end up with sysbus MMIO region numbers that don't match the port number. Avoid this numbering mismatch by creating dummy MMIO regions for the unused ports. This doesn't change anything for our existing boards, which don't have any gaps in the middle of the port ranges they use; but it will be needed for the Musca board. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- include/hw/misc/tz-ppc.h | 8 +++++++- hw/misc/tz-ppc.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+), 1 deletion(-) diff --git a/include/hw/misc/tz-ppc.h b/include/hw/misc/tz-ppc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/tz-ppc.h +++ b/include/hw/misc/tz-ppc.h @@ -XXX,XX +XXX,XX @@ * * QEMU interface: * + sysbus MMIO regions 0..15: MemoryRegions defining the upstream end - * of each of the 16 ports of the PPC + * of each of the 16 ports of the PPC. When a port is unused (i.e. no + * downstream MemoryRegion is connected to it) at the end of the 0..15 + * range then no sysbus MMIO region is created for its upstream. When an + * unused port lies in the middle of the range with other used ports at + * higher port numbers, a dummy MMIO region is created to ensure that + * port N's upstream is always sysbus MMIO region N. Dummy regions should + * not be mapped, and will assert if any access is made to them. * + Property "port[0..15]": MemoryRegion defining the downstream device(s) * for each of the 16 ports of the PPC * + Named GPIO inputs "cfg_nonsec[0..15]": set to 1 if the port should be diff --git a/hw/misc/tz-ppc.c b/hw/misc/tz-ppc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/tz-ppc.c +++ b/hw/misc/tz-ppc.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps tz_ppc_ops = { .endianness = DEVICE_LITTLE_ENDIAN, }; +static bool tz_ppc_dummy_accepts(void *opaque, hwaddr addr, + unsigned size, bool is_write, + MemTxAttrs attrs) +{ + /* + * Board code should never map the upstream end of an unused port, + * so we should never try to make a memory access to it. + */ + g_assert_not_reached(); +} + +static const MemoryRegionOps tz_ppc_dummy_ops = { + .valid.accepts = tz_ppc_dummy_accepts, +}; + static void tz_ppc_reset(DeviceState *dev) { TZPPC *s = TZ_PPC(dev); @@ -XXX,XX +XXX,XX @@ static void tz_ppc_realize(DeviceState *dev, Error **errp) SysBusDevice *sbd = SYS_BUS_DEVICE(dev); TZPPC *s = TZ_PPC(dev); int i; + int max_port = 0; /* We can't create the upstream end of the port until realize, * as we don't know the size of the MR used as the downstream until then. */ for (i = 0; i < TZ_NUM_PORTS; i++) { + if (s->port[i].downstream) { + max_port = i; + } + } + + for (i = 0; i <= max_port; i++) { TZPPCPort *port = &s->port[i]; char *name; uint64_t size; if (!port->downstream) { + /* + * Create dummy sysbus MMIO region so the sysbus region + * numbering doesn't get out of sync with the port numbers. + * The size is entirely arbitrary. + */ + name = g_strdup_printf("tz-ppc-dummy-port[%d]", i); + memory_region_init_io(&port->upstream, obj, &tz_ppc_dummy_ops, + port, name, 0x10000); + sysbus_init_mmio(sbd, &port->upstream); + g_free(name); continue; } -- 2.20.1 Create a new include file for the pl031's device struct, type macros, etc, so that it can be instantiated using the "embedded struct" coding style. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- include/hw/timer/pl031.h | 44 ++++++++++++++++++++++++++++++++++++++++ hw/timer/pl031.c | 25 +---------------------- MAINTAINERS | 1 + 3 files changed, 46 insertions(+), 24 deletions(-) create mode 100644 include/hw/timer/pl031.h diff --git a/include/hw/timer/pl031.h b/include/hw/timer/pl031.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/timer/pl031.h @@ -XXX,XX +XXX,XX @@ +/* + * ARM AMBA PrimeCell PL031 RTC + * + * Copyright (c) 2007 CodeSourcery + * + * This file is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#ifndef HW_TIMER_PL031 +#define HW_TIMER_PL031 + +#include "hw/sysbus.h" + +#define TYPE_PL031 "pl031" +#define PL031(obj) OBJECT_CHECK(PL031State, (obj), TYPE_PL031) + +typedef struct PL031State { + SysBusDevice parent_obj; + + MemoryRegion iomem; + QEMUTimer *timer; + qemu_irq irq; + + /* + * Needed to preserve the tick_count across migration, even if the + * absolute value of the rtc_clock is different on the source and + * destination. + */ + uint32_t tick_offset_vmstate; + uint32_t tick_offset; + + uint32_t mr; + uint32_t lr; + uint32_t cr; + uint32_t im; + uint32_t is; +} PL031State; + +#endif diff --git a/hw/timer/pl031.c b/hw/timer/pl031.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/pl031.c +++ b/hw/timer/pl031.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "hw/timer/pl031.h" #include "hw/sysbus.h" #include "qemu/timer.h" #include "sysemu/sysemu.h" @@ -XXX,XX +XXX,XX @@ do { printf("pl031: " fmt , ## __VA_ARGS__); } while (0) #define RTC_MIS 0x18 /* Masked interrupt status register */ #define RTC_ICR 0x1c /* Interrupt clear register */ -#define TYPE_PL031 "pl031" -#define PL031(obj) OBJECT_CHECK(PL031State, (obj), TYPE_PL031) - -typedef struct PL031State { - SysBusDevice parent_obj; - - MemoryRegion iomem; - QEMUTimer *timer; - qemu_irq irq; - - /* Needed to preserve the tick_count across migration, even if the - * absolute value of the rtc_clock is different on the source and - * destination. - */ - uint32_t tick_offset_vmstate; - uint32_t tick_offset; - - uint32_t mr; - uint32_t lr; - uint32_t cr; - uint32_t im; - uint32_t is; -} PL031State; - static const unsigned char pl031_id[] = { 0x31, 0x10, 0x14, 0x00, /* Device ID */ 0x0d, 0xf0, 0x05, 0xb1 /* Cell ID */ diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/sd/pl181.c F: hw/ssi/pl022.c F: include/hw/ssi/pl022.h F: hw/timer/pl031.c +F: include/hw/timer/pl031.h F: include/hw/arm/primecell.h F: hw/timer/cmsdk-apb-timer.c F: include/hw/timer/cmsdk-apb-timer.h -- 2.20.1 Convert the debug printing in the PL031 device to use trace events, and augment it to cover the interesting parts of device operation. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- hw/timer/pl031.c | 55 +++++++++++++++++++++++-------------------- hw/timer/trace-events | 6 +++++ 2 files changed, 36 insertions(+), 25 deletions(-) diff --git a/hw/timer/pl031.c b/hw/timer/pl031.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/pl031.c +++ b/hw/timer/pl031.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "qemu/cutils.h" #include "qemu/log.h" - -//#define DEBUG_PL031 - -#ifdef DEBUG_PL031 -#define DPRINTF(fmt, ...) \ -do { printf("pl031: " fmt , ## __VA_ARGS__); } while (0) -#else -#define DPRINTF(fmt, ...) do {} while(0) -#endif +#include "trace.h" #define RTC_DR 0x00 /* Data read register */ #define RTC_MR 0x04 /* Match register */ @@ -XXX,XX +XXX,XX @@ static const unsigned char pl031_id[] = { static void pl031_update(PL031State *s) { - qemu_set_irq(s->irq, s->is & s->im); + uint32_t flags = s->is & s->im; + + trace_pl031_irq_state(flags); + qemu_set_irq(s->irq, flags); } static void pl031_interrupt(void * opaque) @@ -XXX,XX +XXX,XX @@ static void pl031_interrupt(void * opaque) PL031State *s = (PL031State *)opaque; s->is = 1; - DPRINTF("Alarm raised\n"); + trace_pl031_alarm_raised(); pl031_update(s); } @@ -XXX,XX +XXX,XX @@ static void pl031_set_alarm(PL031State *s) /* The timer wraps around. This subtraction also wraps in the same way, and gives correct results when alarm < now_ticks. */ ticks = s->mr - pl031_get_count(s); - DPRINTF("Alarm set in %ud ticks\n", ticks); + trace_pl031_set_alarm(ticks); if (ticks == 0) { timer_del(s->timer); pl031_interrupt(s); @@ -XXX,XX +XXX,XX @@ static uint64_t pl031_read(void *opaque, hwaddr offset, unsigned size) { PL031State *s = (PL031State *)opaque; - - if (offset >= 0xfe0 && offset < 0x1000) - return pl031_id[(offset - 0xfe0) >> 2]; + uint64_t r; switch (offset) { case RTC_DR: - return pl031_get_count(s); + r = pl031_get_count(s); + break; case RTC_MR: - return s->mr; + r = s->mr; + break; case RTC_IMSC: - return s->im; + r = s->im; + break; case RTC_RIS: - return s->is; + r = s->is; + break; case RTC_LR: - return s->lr; + r = s->lr; + break; case RTC_CR: /* RTC is permanently enabled. */ - return 1; + r = 1; + break; case RTC_MIS: - return s->is & s->im; + r = s->is & s->im; + break; + case 0xfe0 ... 0xfff: + r = pl031_id[(offset - 0xfe0) >> 2]; + break; case RTC_ICR: qemu_log_mask(LOG_GUEST_ERROR, "pl031: read of write-only register at offset 0x%x\n", (int)offset); + r = 0; break; default: qemu_log_mask(LOG_GUEST_ERROR, "pl031_read: Bad offset 0x%x\n", (int)offset); + r = 0; break; } - return 0; + trace_pl031_read(offset, r); + return r; } static void pl031_write(void * opaque, hwaddr offset, @@ -XXX,XX +XXX,XX @@ static void pl031_write(void * opaque, hwaddr offset, { PL031State *s = (PL031State *)opaque; + trace_pl031_write(offset, value); switch (offset) { case RTC_LR: @@ -XXX,XX +XXX,XX @@ static void pl031_write(void * opaque, hwaddr offset, break; case RTC_IMSC: s->im = value & 1; - DPRINTF("Interrupt mask %d\n", s->im); pl031_update(s); break; case RTC_ICR: @@ -XXX,XX +XXX,XX @@ static void pl031_write(void * opaque, hwaddr offset, cleared when bit 0 of the written value is set. However the arm926e documentation (DDI0287B) states that the interrupt is cleared when any value is written. */ - DPRINTF("Interrupt cleared"); s->is = 0; pl031_update(s); break; diff --git a/hw/timer/trace-events b/hw/timer/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/trace-events +++ b/hw/timer/trace-events @@ -XXX,XX +XXX,XX @@ xlnx_zynqmp_rtc_gettime(int year, int month, int day, int hour, int min, int sec nrf51_timer_read(uint64_t addr, uint32_t value, unsigned size) "read addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u" nrf51_timer_write(uint64_t addr, uint32_t value, unsigned size) "write addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u" +# hw/timer/pl031.c +pl031_irq_state(int level) "irq state %d" +pl031_read(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" +pl031_write(uint32_t addr, uint32_t value) "addr 0x%08x value 0x%08x" +pl031_alarm_raised(void) "alarm raised" +pl031_set_alarm(uint32_t ticks) "alarm set for %u ticks" -- 2.20.1 Create a new include file for the pl011's device struct, type macros, etc, so that it can be instantiated using the "embedded struct" coding style. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- include/hw/char/pl011.h | 34 ++++++++++++++++++++++++++++++++++ hw/char/pl011.c | 31 ++----------------------------- 2 files changed, 36 insertions(+), 29 deletions(-) diff --git a/include/hw/char/pl011.h b/include/hw/char/pl011.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/char/pl011.h +++ b/include/hw/char/pl011.h @@ -XXX,XX +XXX,XX @@ #ifndef HW_PL011_H #define HW_PL011_H +#include "hw/sysbus.h" +#include "chardev/char-fe.h" + +#define TYPE_PL011 "pl011" +#define PL011(obj) OBJECT_CHECK(PL011State, (obj), TYPE_PL011) + +/* This shares the same struct (and cast macro) as the base pl011 device */ +#define TYPE_PL011_LUMINARY "pl011_luminary" + +typedef struct PL011State { + SysBusDevice parent_obj; + + MemoryRegion iomem; + uint32_t readbuff; + uint32_t flags; + uint32_t lcr; + uint32_t rsr; + uint32_t cr; + uint32_t dmacr; + uint32_t int_enabled; + uint32_t int_level; + uint32_t read_fifo[16]; + uint32_t ilpr; + uint32_t ibrd; + uint32_t fbrd; + uint32_t ifl; + int read_pos; + int read_count; + int read_trigger; + CharBackend chr; + qemu_irq irq; + const unsigned char *id; +} PL011State; + static inline DeviceState *pl011_create(hwaddr addr, qemu_irq irq, Chardev *chr) diff --git a/hw/char/pl011.c b/hw/char/pl011.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/pl011.c +++ b/hw/char/pl011.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "hw/char/pl011.h" #include "hw/sysbus.h" #include "chardev/char-fe.h" #include "qemu/log.h" #include "trace.h" -#define TYPE_PL011 "pl011" -#define PL011(obj) OBJECT_CHECK(PL011State, (obj), TYPE_PL011) - -typedef struct PL011State { - SysBusDevice parent_obj; - - MemoryRegion iomem; - uint32_t readbuff; - uint32_t flags; - uint32_t lcr; - uint32_t rsr; - uint32_t cr; - uint32_t dmacr; - uint32_t int_enabled; - uint32_t int_level; - uint32_t read_fifo[16]; - uint32_t ilpr; - uint32_t ibrd; - uint32_t fbrd; - uint32_t ifl; - int read_pos; - int read_count; - int read_trigger; - CharBackend chr; - qemu_irq irq; - const unsigned char *id; -} PL011State; - #define PL011_INT_TX 0x20 #define PL011_INT_RX 0x10 @@ -XXX,XX +XXX,XX @@ static void pl011_luminary_init(Object *obj) } static const TypeInfo pl011_luminary_info = { - .name = "pl011_luminary", + .name = TYPE_PL011_LUMINARY, .parent = TYPE_PL011, .instance_init = pl011_luminary_init, }; -- 2.20.1 The PL011 UART has six interrupt lines: * RX (receive data) * TX (transmit data) * RT (receive timeout) * MS (modem status) * E (errors) * combined (logical OR of all the above) So far we have only emulated the combined interrupt line; add support for the others, so that boards that wire them up to different interrupt controller inputs can do so. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- include/hw/char/pl011.h | 2 +- hw/char/pl011.c | 46 +++++++++++++++++++++++++++++++++++++++-- 2 files changed, 45 insertions(+), 3 deletions(-) diff --git a/include/hw/char/pl011.h b/include/hw/char/pl011.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/char/pl011.h +++ b/include/hw/char/pl011.h @@ -XXX,XX +XXX,XX @@ typedef struct PL011State { int read_count; int read_trigger; CharBackend chr; - qemu_irq irq; + qemu_irq irq[6]; const unsigned char *id; } PL011State; diff --git a/hw/char/pl011.c b/hw/char/pl011.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/pl011.c +++ b/hw/char/pl011.c @@ -XXX,XX +XXX,XX @@ * This code is licensed under the GPL. */ +/* + * QEMU interface: + * + sysbus MMIO region 0: device registers + * + sysbus IRQ 0: UARTINTR (combined interrupt line) + * + sysbus IRQ 1: UARTRXINTR (receive FIFO interrupt line) + * + sysbus IRQ 2: UARTTXINTR (transmit FIFO interrupt line) + * + sysbus IRQ 3: UARTRTINTR (receive timeout interrupt line) + * + sysbus IRQ 4: UARTMSINTR (momem status interrupt line) + * + sysbus IRQ 5: UARTEINTR (error interrupt line) + */ + #include "qemu/osdep.h" #include "hw/char/pl011.h" #include "hw/sysbus.h" @@ -XXX,XX +XXX,XX @@ #define PL011_FLAG_TXFF 0x20 #define PL011_FLAG_RXFE 0x10 +/* Interrupt status bits in UARTRIS, UARTMIS, UARTIMSC */ +#define INT_OE (1 << 10) +#define INT_BE (1 << 9) +#define INT_PE (1 << 8) +#define INT_FE (1 << 7) +#define INT_RT (1 << 6) +#define INT_TX (1 << 5) +#define INT_RX (1 << 4) +#define INT_DSR (1 << 3) +#define INT_DCD (1 << 2) +#define INT_CTS (1 << 1) +#define INT_RI (1 << 0) +#define INT_E (INT_OE | INT_BE | INT_PE | INT_FE) +#define INT_MS (INT_RI | INT_DSR | INT_DCD | INT_CTS) + static const unsigned char pl011_id_arm[8] = { 0x11, 0x10, 0x14, 0x00, 0x0d, 0xf0, 0x05, 0xb1 }; static const unsigned char pl011_id_luminary[8] = { 0x11, 0x00, 0x18, 0x01, 0x0d, 0xf0, 0x05, 0xb1 }; +/* Which bits in the interrupt status matter for each outbound IRQ line ? */ +static const uint32_t irqmask[] = { + INT_E | INT_MS | INT_RT | INT_TX | INT_RX, /* combined IRQ */ + INT_RX, + INT_TX, + INT_RT, + INT_MS, + INT_E, +}; + static void pl011_update(PL011State *s) { uint32_t flags; + int i; flags = s->int_level & s->int_enabled; trace_pl011_irq_state(flags != 0); - qemu_set_irq(s->irq, flags != 0); + for (i = 0; i < ARRAY_SIZE(s->irq); i++) { + qemu_set_irq(s->irq[i], (flags & irqmask[i]) != 0); + } } static uint64_t pl011_read(void *opaque, hwaddr offset, @@ -XXX,XX +XXX,XX @@ static void pl011_init(Object *obj) { SysBusDevice *sbd = SYS_BUS_DEVICE(obj); PL011State *s = PL011(obj); + int i; memory_region_init_io(&s->iomem, OBJECT(s), &pl011_ops, s, "pl011", 0x1000); sysbus_init_mmio(sbd, &s->iomem); - sysbus_init_irq(sbd, &s->irq); + for (i = 0; i < ARRAY_SIZE(s->irq); i++) { + sysbus_init_irq(sbd, &s->irq[i]); + } s->read_trigger = 1; s->ifl = 0x12; -- 2.20.1 The pl011 logs when the guest makes a bad access. It prints the address offset in hex but confusingly omits the '0x' prefix; add it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- hw/char/pl011.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/char/pl011.c b/hw/char/pl011.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/pl011.c +++ b/hw/char/pl011.c @@ -XXX,XX +XXX,XX @@ static uint64_t pl011_read(void *opaque, hwaddr offset, break; default: qemu_log_mask(LOG_GUEST_ERROR, - "pl011_read: Bad offset %x\n", (int)offset); + "pl011_read: Bad offset 0x%x\n", (int)offset); r = 0; break; } @@ -XXX,XX +XXX,XX @@ static void pl011_write(void *opaque, hwaddr offset, break; default: qemu_log_mask(LOG_GUEST_ERROR, - "pl011_write: Bad offset %x\n", (int)offset); + "pl011_write: Bad offset 0x%x\n", (int)offset); } } -- 2.20.1 In commit 4b635cf7a95e501211 we added a QOM property to the ARMSSE object, but forgot to add it to the documentation comment in the header. Correct the omission. Fixes: 4b635cf7a95e501211 ("hw/arm/armsse: Make SRAM bank size configurable") Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- include/hw/arm/armsse.h | 2 ++ 1 file changed, 2 insertions(+) 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 @@ * being the same for both, to avoid having to have separate Property * lists for different variants. This restriction can be relaxed later * if necessary.) + * + QOM property "SRAM_ADDR_WIDTH" sets the number of bits used for the + * address of each SRAM bank (and thus the total amount of internal SRAM) * + Named GPIO inputs "EXP_IRQ" 0..n are the expansion interrupts for CPU 0, * which are wired to its NVIC lines 32 .. n+32 * + Named GPIO inputs "EXP_CPU1_IRQ" 0..n are the expansion interrupts for -- 2.20.1 The Musca boards have DAPLink firmware that sets the initial secure VTOR value (the location of the vector table) differently depending on the boot mode (from flash, from RAM, etc). Export the init-svtor as a QOM property of the ARMSSE object so that the board can change it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- include/hw/arm/armsse.h | 3 +++ hw/arm/armsse.c | 8 ++++---- 2 files changed, 7 insertions(+), 4 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 @@ * if necessary.) * + QOM property "SRAM_ADDR_WIDTH" sets the number of bits used for the * address of each SRAM bank (and thus the total amount of internal SRAM) + * + QOM property "init-svtor" sets the initial value of the CPU SVTOR register + * (where it expects to load the PC and SP from the vector table on reset) * + Named GPIO inputs "EXP_IRQ" 0..n are the expansion interrupts for CPU 0, * which are wired to its NVIC lines 32 .. n+32 * + Named GPIO inputs "EXP_CPU1_IRQ" 0..n are the expansion interrupts for @@ -XXX,XX +XXX,XX @@ typedef struct ARMSSE { uint32_t exp_numirq; uint32_t mainclk_frq; uint32_t sram_addr_width; + uint32_t init_svtor; } ARMSSE; typedef struct ARMSSEInfo ARMSSEInfo; diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armsse.c +++ b/hw/arm/armsse.c @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) * the INITSVTOR* registers before powering up the CPUs in any case, * so the hardware's default value doesn't matter. QEMU doesn't emulate * the control processor, so instead we behave in the way that the - * firmware does. All boards currently known about have firmware that - * sets the INITSVTOR0 and INITSVTOR1 registers to 0x10000000, like the - * IoTKit default. We can make this more configurable if necessary. + * firmware does. The initial value is configurable by the board code + * to match whatever its firmware does. */ - qdev_prop_set_uint32(cpudev, "init-svtor", 0x10000000); + qdev_prop_set_uint32(cpudev, "init-svtor", s->init_svtor); /* * Start all CPUs except CPU0 powered down. In real hardware it is * a configurable property of the SSE-200 which CPUs start powered up @@ -XXX,XX +XXX,XX @@ static Property armsse_properties[] = { DEFINE_PROP_UINT32("EXP_NUMIRQ", ARMSSE, exp_numirq, 64), DEFINE_PROP_UINT32("MAINCLK", ARMSSE, mainclk_frq, 0), DEFINE_PROP_UINT32("SRAM_ADDR_WIDTH", ARMSSE, sram_addr_width, 15), + DEFINE_PROP_UINT32("init-svtor", ARMSSE, init_svtor, 0x10000000), DEFINE_PROP_END_OF_LIST() }; -- 2.20.1 The Musca-A and Musca-B1 development boards are based on the SSE-200 subsystem for embedded. Implement an initial skeleton model of these boards, which are similar but not identical. This commit creates the board model with the SSE and the IRQ splitters to wire IRQs up to its two CPUs. As yet there are no devices and no memory: these will be added later. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- hw/arm/Makefile.objs | 1 + hw/arm/musca.c | 197 ++++++++++++++++++++++++++++++++ MAINTAINERS | 6 + default-configs/arm-softmmu.mak | 1 + 4 files changed, 205 insertions(+) create mode 100644 hw/arm/musca.c diff --git a/hw/arm/Makefile.objs b/hw/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Makefile.objs +++ b/hw/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_ASPEED_SOC) += aspeed_soc.o aspeed.o obj-$(CONFIG_MPS2) += mps2.o obj-$(CONFIG_MPS2) += mps2-tz.o obj-$(CONFIG_MSF2) += msf2-soc.o msf2-som.o +obj-$(CONFIG_MUSCA) += musca.o obj-$(CONFIG_ARMSSE) += armsse.o obj-$(CONFIG_FSL_IMX7) += fsl-imx7.o mcimx7d-sabre.o obj-$(CONFIG_ARM_SMMUV3) += smmu-common.o smmuv3.o diff --git a/hw/arm/musca.c b/hw/arm/musca.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/arm/musca.c @@ -XXX,XX +XXX,XX @@ +/* + * Arm Musca-B1 test chip board emulation + * + * Copyright (c) 2019 Linaro Limited + * Written by Peter Maydell + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 or + * (at your option) any later version. + */ + +/* + * The Musca boards are a reference implementation of a system using + * the SSE-200 subsystem for embedded: + * https://developer.arm.com/products/system-design/development-boards/iot-test-chips-and-boards/musca-a-test-chip-board + * https://developer.arm.com/products/system-design/development-boards/iot-test-chips-and-boards/musca-b-test-chip-board + * We model the A and B1 variants of this board, as described in the TRMs: + * http://infocenter.arm.com/help/topic/com.arm.doc.101107_0000_00_en/index.html + * http://infocenter.arm.com/help/topic/com.arm.doc.101312_0000_00_en/index.html + */ + +#include "qemu/osdep.h" +#include "qemu/error-report.h" +#include "qapi/error.h" +#include "exec/address-spaces.h" +#include "hw/arm/arm.h" +#include "hw/arm/armsse.h" +#include "hw/boards.h" +#include "hw/core/split-irq.h" + +#define MUSCA_NUMIRQ_MAX 96 + +typedef enum MuscaType { + MUSCA_A, + MUSCA_B1, +} MuscaType; + +typedef struct { + MachineClass parent; + MuscaType type; + uint32_t init_svtor; + int sram_addr_width; + int num_irqs; +} MuscaMachineClass; + +typedef struct { + MachineState parent; + + ARMSSE sse; + SplitIRQ cpu_irq_splitter[MUSCA_NUMIRQ_MAX]; +} MuscaMachineState; + +#define TYPE_MUSCA_MACHINE "musca" +#define TYPE_MUSCA_A_MACHINE MACHINE_TYPE_NAME("musca-a") +#define TYPE_MUSCA_B1_MACHINE MACHINE_TYPE_NAME("musca-b1") + +#define MUSCA_MACHINE(obj) \ + OBJECT_CHECK(MuscaMachineState, obj, TYPE_MUSCA_MACHINE) +#define MUSCA_MACHINE_GET_CLASS(obj) \ + OBJECT_GET_CLASS(MuscaMachineClass, obj, TYPE_MUSCA_MACHINE) +#define MUSCA_MACHINE_CLASS(klass) \ + OBJECT_CLASS_CHECK(MuscaMachineClass, klass, TYPE_MUSCA_MACHINE) + +/* + * Main SYSCLK frequency in Hz + * TODO this should really be different for the two cores, but we + * don't model that in our SSE-200 model yet. + */ +#define SYSCLK_FRQ 40000000 + +static void musca_init(MachineState *machine) +{ + MuscaMachineState *mms = MUSCA_MACHINE(machine); + MuscaMachineClass *mmc = MUSCA_MACHINE_GET_CLASS(mms); + MachineClass *mc = MACHINE_GET_CLASS(machine); + MemoryRegion *system_memory = get_system_memory(); + DeviceState *ssedev; + int i; + + assert(mmc->num_irqs <= MUSCA_NUMIRQ_MAX); + + if (strcmp(machine->cpu_type, mc->default_cpu_type) != 0) { + error_report("This board can only be used with CPU %s", + mc->default_cpu_type); + exit(1); + } + + sysbus_init_child_obj(OBJECT(machine), "sse-200", &mms->sse, + sizeof(mms->sse), TYPE_SSE200); + ssedev = DEVICE(&mms->sse); + object_property_set_link(OBJECT(&mms->sse), OBJECT(system_memory), + "memory", &error_fatal); + qdev_prop_set_uint32(ssedev, "EXP_NUMIRQ", mmc->num_irqs); + qdev_prop_set_uint32(ssedev, "init-svtor", mmc->init_svtor); + qdev_prop_set_uint32(ssedev, "SRAM_ADDR_WIDTH", mmc->sram_addr_width); + qdev_prop_set_uint32(ssedev, "MAINCLK", SYSCLK_FRQ); + object_property_set_bool(OBJECT(&mms->sse), true, "realized", + &error_fatal); + + /* + * We need to create splitters to feed the IRQ inputs + * for each CPU in the SSE-200 from each device in the board. + */ + for (i = 0; i < mmc->num_irqs; i++) { + char *name = g_strdup_printf("musca-irq-splitter%d", i); + SplitIRQ *splitter = &mms->cpu_irq_splitter[i]; + + object_initialize_child(OBJECT(machine), name, + splitter, sizeof(*splitter), + TYPE_SPLIT_IRQ, &error_fatal, NULL); + g_free(name); + + object_property_set_int(OBJECT(splitter), 2, "num-lines", + &error_fatal); + object_property_set_bool(OBJECT(splitter), true, "realized", + &error_fatal); + qdev_connect_gpio_out(DEVICE(splitter), 0, + qdev_get_gpio_in_named(ssedev, "EXP_IRQ", i)); + qdev_connect_gpio_out(DEVICE(splitter), 1, + qdev_get_gpio_in_named(ssedev, + "EXP_CPU1_IRQ", i)); + } + + armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, 0x2000000); +} + +static void musca_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + + mc->default_cpus = 2; + mc->min_cpus = mc->default_cpus; + mc->max_cpus = mc->default_cpus; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"); + mc->init = musca_init; +} + +static void musca_a_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + MuscaMachineClass *mmc = MUSCA_MACHINE_CLASS(oc); + + mc->desc = "ARM Musca-A board (dual Cortex-M33)"; + mmc->type = MUSCA_A; + mmc->init_svtor = 0x10200000; + mmc->sram_addr_width = 15; + mmc->num_irqs = 64; +} + +static void musca_b1_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + MuscaMachineClass *mmc = MUSCA_MACHINE_CLASS(oc); + + mc->desc = "ARM Musca-B1 board (dual Cortex-M33)"; + mmc->type = MUSCA_B1; + /* + * This matches the DAPlink firmware which boots from QSPI. There + * is also a firmware blob which boots from the eFlash, which + * uses init_svtor = 0x1A000000. QEMU doesn't currently support that, + * though we could in theory expose a machine property on the command + * line to allow the user to request eFlash boot. + */ + mmc->init_svtor = 0x10000000; + mmc->sram_addr_width = 17; + mmc->num_irqs = 96; +} + +static const TypeInfo musca_info = { + .name = TYPE_MUSCA_MACHINE, + .parent = TYPE_MACHINE, + .abstract = true, + .instance_size = sizeof(MuscaMachineState), + .class_size = sizeof(MuscaMachineClass), + .class_init = musca_class_init, +}; + +static const TypeInfo musca_a_info = { + .name = TYPE_MUSCA_A_MACHINE, + .parent = TYPE_MUSCA_MACHINE, + .class_init = musca_a_class_init, +}; + +static const TypeInfo musca_b1_info = { + .name = TYPE_MUSCA_B1_MACHINE, + .parent = TYPE_MUSCA_MACHINE, + .class_init = musca_b1_class_init, +}; + +static void musca_machine_init(void) +{ + type_register_static(&musca_info); + type_register_static(&musca_a_info); + type_register_static(&musca_b1_info); +} + +type_init(musca_machine_init); diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/hw/misc/iotkit-sysinfo.h F: hw/misc/armsse-cpuid.c F: include/hw/misc/armsse-cpuid.h +Musca +M: Peter Maydell <peter.maydell@linaro.org> +L: qemu-arm@nongnu.org +S: Maintained +F: hw/arm/musca.c + Musicpal M: Jan Kiszka <jan.kiszka@web.de> M: Peter Maydell <peter.maydell@linaro.org> diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/default-configs/arm-softmmu.mak +++ b/default-configs/arm-softmmu.mak @@ -XXX,XX +XXX,XX @@ CONFIG_TUSB6010=y CONFIG_IMX=y CONFIG_MAINSTONE=y CONFIG_MPS2=y +CONFIG_MUSCA=y CONFIG_NSERIES=y CONFIG_RASPI=y CONFIG_REALVIEW=y -- 2.20.1 Many of the devices on the Musca board live behind TrustZone Peripheral Protection Controllers (PPCs); add models of the PPCs, using a similar scheme to the MPS2 board models. This commit wires up the PPCs with "unimplemented device" stubs behind them in the correct places in the address map. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- hw/arm/musca.c | 289 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 289 insertions(+) diff --git a/hw/arm/musca.c b/hw/arm/musca.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/musca.c +++ b/hw/arm/musca.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/armsse.h" #include "hw/boards.h" #include "hw/core/split-irq.h" +#include "hw/misc/tz-ppc.h" +#include "hw/misc/unimp.h" #define MUSCA_NUMIRQ_MAX 96 +#define MUSCA_PPC_MAX 3 typedef enum MuscaType { MUSCA_A, @@ -XXX,XX +XXX,XX @@ typedef struct { ARMSSE sse; SplitIRQ cpu_irq_splitter[MUSCA_NUMIRQ_MAX]; + SplitIRQ sec_resp_splitter; + TZPPC ppc[MUSCA_PPC_MAX]; + MemoryRegion container; + UnimplementedDeviceState eflash[2]; + UnimplementedDeviceState qspi; + UnimplementedDeviceState mpc[5]; + UnimplementedDeviceState mhu[2]; + UnimplementedDeviceState pwm[3]; + UnimplementedDeviceState i2s; + UnimplementedDeviceState uart[2]; + UnimplementedDeviceState i2c[2]; + UnimplementedDeviceState spi; + UnimplementedDeviceState scc; + UnimplementedDeviceState timer; + UnimplementedDeviceState rtc; + UnimplementedDeviceState pvt; + UnimplementedDeviceState sdio; + UnimplementedDeviceState gpio; } MuscaMachineState; #define TYPE_MUSCA_MACHINE "musca" @@ -XXX,XX +XXX,XX @@ typedef struct { */ #define SYSCLK_FRQ 40000000 +/* + * Most of the devices in the Musca board sit behind Peripheral Protection + * Controllers. These data structures define the layout of which devices + * sit behind which PPCs. + * The devfn for each port is a function which creates, configures + * and initializes the device, returning the MemoryRegion which + * needs to be plugged into the downstream end of the PPC port. + */ +typedef MemoryRegion *MakeDevFn(MuscaMachineState *mms, void *opaque, + const char *name, hwaddr size); + +typedef struct PPCPortInfo { + const char *name; + MakeDevFn *devfn; + void *opaque; + hwaddr addr; + hwaddr size; +} PPCPortInfo; + +typedef struct PPCInfo { + const char *name; + PPCPortInfo ports[TZ_NUM_PORTS]; +} PPCInfo; + +static MemoryRegion *make_unimp_dev(MuscaMachineState *mms, + void *opaque, const char *name, hwaddr size) +{ + /* + * Initialize, configure and realize a TYPE_UNIMPLEMENTED_DEVICE, + * and return a pointer to its MemoryRegion. + */ + UnimplementedDeviceState *uds = opaque; + + sysbus_init_child_obj(OBJECT(mms), name, uds, + sizeof(UnimplementedDeviceState), + TYPE_UNIMPLEMENTED_DEVICE); + qdev_prop_set_string(DEVICE(uds), "name", name); + qdev_prop_set_uint64(DEVICE(uds), "size", size); + object_property_set_bool(OBJECT(uds), true, "realized", &error_fatal); + return sysbus_mmio_get_region(SYS_BUS_DEVICE(uds), 0); +} + +static MemoryRegion *make_musca_a_devs(MuscaMachineState *mms, void *opaque, + const char *name, hwaddr size) +{ + /* + * Create the container MemoryRegion for all the devices that live + * behind the Musca-A PPC's single port. These devices don't have a PPC + * port each, but we use the PPCPortInfo struct as a convenient way + * to describe them. Note that addresses here are relative to the base + * address of the PPC port region: 0x40100000, and devices appear both + * at the 0x4... NS region and the 0x5... S region. + */ + int i; + MemoryRegion *container = &mms->container; + + const PPCPortInfo devices[] = { + { "uart0", make_unimp_dev, &mms->uart[0], 0x1000, 0x1000 }, + { "uart1", make_unimp_dev, &mms->uart[1], 0x2000, 0x1000 }, + { "spi", make_unimp_dev, &mms->spi, 0x3000, 0x1000 }, + { "i2c0", make_unimp_dev, &mms->i2c[0], 0x4000, 0x1000 }, + { "i2c1", make_unimp_dev, &mms->i2c[1], 0x5000, 0x1000 }, + { "i2s", make_unimp_dev, &mms->i2s, 0x6000, 0x1000 }, + { "pwm0", make_unimp_dev, &mms->pwm[0], 0x7000, 0x1000 }, + { "rtc", make_unimp_dev, &mms->rtc, 0x8000, 0x1000 }, + { "qspi", make_unimp_dev, &mms->qspi, 0xa000, 0x1000 }, + { "timer", make_unimp_dev, &mms->timer, 0xb000, 0x1000 }, + { "scc", make_unimp_dev, &mms->scc, 0xc000, 0x1000 }, + { "pwm1", make_unimp_dev, &mms->pwm[1], 0xe000, 0x1000 }, + { "pwm2", make_unimp_dev, &mms->pwm[2], 0xf000, 0x1000 }, + { "gpio", make_unimp_dev, &mms->gpio, 0x10000, 0x1000 }, + { "mpc0", make_unimp_dev, &mms->mpc[0], 0x12000, 0x1000 }, + { "mpc1", make_unimp_dev, &mms->mpc[1], 0x13000, 0x1000 }, + }; + + memory_region_init(container, OBJECT(mms), "musca-device-container", size); + + for (i = 0; i < ARRAY_SIZE(devices); i++) { + const PPCPortInfo *pinfo = &devices[i]; + MemoryRegion *mr; + + mr = pinfo->devfn(mms, pinfo->opaque, pinfo->name, pinfo->size); + memory_region_add_subregion(container, pinfo->addr, mr); + } + + return &mms->container; +} + static void musca_init(MachineState *machine) { MuscaMachineState *mms = MUSCA_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void musca_init(MachineState *machine) MachineClass *mc = MACHINE_GET_CLASS(machine); MemoryRegion *system_memory = get_system_memory(); DeviceState *ssedev; + DeviceState *dev_splitter; + const PPCInfo *ppcs; + int num_ppcs; int i; assert(mmc->num_irqs <= MUSCA_NUMIRQ_MAX); @@ -XXX,XX +XXX,XX @@ static void musca_init(MachineState *machine) "EXP_CPU1_IRQ", i)); } + /* + * The sec_resp_cfg output from the SSE-200 must be split into multiple + * lines, one for each of the PPCs we create here. + */ + object_initialize(&mms->sec_resp_splitter, sizeof(mms->sec_resp_splitter), + TYPE_SPLIT_IRQ); + object_property_add_child(OBJECT(machine), "sec-resp-splitter", + OBJECT(&mms->sec_resp_splitter), &error_fatal); + object_property_set_int(OBJECT(&mms->sec_resp_splitter), + ARRAY_SIZE(mms->ppc), "num-lines", &error_fatal); + object_property_set_bool(OBJECT(&mms->sec_resp_splitter), true, + "realized", &error_fatal); + dev_splitter = DEVICE(&mms->sec_resp_splitter); + qdev_connect_gpio_out_named(ssedev, "sec_resp_cfg", 0, + qdev_get_gpio_in(dev_splitter, 0)); + + /* + * Most of the devices in the board are behind Peripheral Protection + * Controllers. The required order for initializing things is: + * + initialize the PPC + * + initialize, configure and realize downstream devices + * + connect downstream device MemoryRegions to the PPC + * + realize the PPC + * + map the PPC's MemoryRegions to the places in the address map + * where the downstream devices should appear + * + wire up the PPC's control lines to the SSE object + * + * The PPC mapping differs for the -A and -B1 variants; the -A version + * is much simpler, using only a single port of a single PPC and putting + * all the devices behind that. + */ + const PPCInfo a_ppcs[] = { { + .name = "ahb_ppcexp0", + .ports = { + { "musca-devices", make_musca_a_devs, 0, 0x40100000, 0x100000 }, + }, + }, + }; + + /* + * Devices listed with an 0x4.. address appear in both the NS 0x4.. region + * and the 0x5.. S region. Devices listed with an 0x5.. address appear + * only in the S region. + */ + const PPCInfo b1_ppcs[] = { { + .name = "apb_ppcexp0", + .ports = { + { "eflash0", make_unimp_dev, &mms->eflash[0], + 0x52400000, 0x1000 }, + { "eflash1", make_unimp_dev, &mms->eflash[1], + 0x52500000, 0x1000 }, + { "qspi", make_unimp_dev, &mms->qspi, 0x42800000, 0x100000 }, + { "mpc0", make_unimp_dev, &mms->mpc[0], 0x52000000, 0x1000 }, + { "mpc1", make_unimp_dev, &mms->mpc[1], 0x52100000, 0x1000 }, + { "mpc2", make_unimp_dev, &mms->mpc[2], 0x52200000, 0x1000 }, + { "mpc3", make_unimp_dev, &mms->mpc[3], 0x52300000, 0x1000 }, + { "mhu0", make_unimp_dev, &mms->mhu[0], 0x42600000, 0x100000 }, + { "mhu1", make_unimp_dev, &mms->mhu[1], 0x42700000, 0x100000 }, + { }, /* port 9: unused */ + { }, /* port 10: unused */ + { }, /* port 11: unused */ + { }, /* port 12: unused */ + { }, /* port 13: unused */ + { "mpc4", make_unimp_dev, &mms->mpc[4], 0x52e00000, 0x1000 }, + }, + }, { + .name = "apb_ppcexp1", + .ports = { + { "pwm0", make_unimp_dev, &mms->pwm[0], 0x40101000, 0x1000 }, + { "pwm1", make_unimp_dev, &mms->pwm[1], 0x40102000, 0x1000 }, + { "pwm2", make_unimp_dev, &mms->pwm[2], 0x40103000, 0x1000 }, + { "i2s", make_unimp_dev, &mms->i2s, 0x40104000, 0x1000 }, + { "uart0", make_unimp_dev, &mms->uart[0], 0x40105000, 0x1000 }, + { "uart1", make_unimp_dev, &mms->uart[1], 0x40106000, 0x1000 }, + { "i2c0", make_unimp_dev, &mms->i2c[0], 0x40108000, 0x1000 }, + { "i2c1", make_unimp_dev, &mms->i2c[1], 0x40109000, 0x1000 }, + { "spi", make_unimp_dev, &mms->spi, 0x4010a000, 0x1000 }, + { "scc", make_unimp_dev, &mms->scc, 0x5010b000, 0x1000 }, + { "timer", make_unimp_dev, &mms->timer, 0x4010c000, 0x1000 }, + { "rtc", make_unimp_dev, &mms->rtc, 0x4010d000, 0x1000 }, + { "pvt", make_unimp_dev, &mms->pvt, 0x4010e000, 0x1000 }, + { "sdio", make_unimp_dev, &mms->sdio, 0x4010f000, 0x1000 }, + }, + }, { + .name = "ahb_ppcexp0", + .ports = { + { }, /* port 0: unused */ + { "gpio", make_unimp_dev, &mms->gpio, 0x41000000, 0x1000 }, + }, + }, + }; + + switch (mmc->type) { + case MUSCA_A: + ppcs = a_ppcs; + num_ppcs = ARRAY_SIZE(a_ppcs); + break; + case MUSCA_B1: + ppcs = b1_ppcs; + num_ppcs = ARRAY_SIZE(b1_ppcs); + break; + default: + g_assert_not_reached(); + } + assert(num_ppcs <= MUSCA_PPC_MAX); + + for (i = 0; i < num_ppcs; i++) { + const PPCInfo *ppcinfo = &ppcs[i]; + TZPPC *ppc = &mms->ppc[i]; + DeviceState *ppcdev; + int port; + char *gpioname; + + sysbus_init_child_obj(OBJECT(machine), ppcinfo->name, ppc, + sizeof(TZPPC), TYPE_TZ_PPC); + ppcdev = DEVICE(ppc); + + for (port = 0; port < TZ_NUM_PORTS; port++) { + const PPCPortInfo *pinfo = &ppcinfo->ports[port]; + MemoryRegion *mr; + char *portname; + + if (!pinfo->devfn) { + continue; + } + + mr = pinfo->devfn(mms, pinfo->opaque, pinfo->name, pinfo->size); + portname = g_strdup_printf("port[%d]", port); + object_property_set_link(OBJECT(ppc), OBJECT(mr), + portname, &error_fatal); + g_free(portname); + } + + object_property_set_bool(OBJECT(ppc), true, "realized", &error_fatal); + + for (port = 0; port < TZ_NUM_PORTS; port++) { + const PPCPortInfo *pinfo = &ppcinfo->ports[port]; + + if (!pinfo->devfn) { + continue; + } + sysbus_mmio_map(SYS_BUS_DEVICE(ppc), port, pinfo->addr); + + gpioname = g_strdup_printf("%s_nonsec", ppcinfo->name); + qdev_connect_gpio_out_named(ssedev, gpioname, port, + qdev_get_gpio_in_named(ppcdev, + "cfg_nonsec", + port)); + g_free(gpioname); + gpioname = g_strdup_printf("%s_ap", ppcinfo->name); + qdev_connect_gpio_out_named(ssedev, gpioname, port, + qdev_get_gpio_in_named(ppcdev, + "cfg_ap", port)); + g_free(gpioname); + } + + gpioname = g_strdup_printf("%s_irq_enable", ppcinfo->name); + qdev_connect_gpio_out_named(ssedev, gpioname, 0, + qdev_get_gpio_in_named(ppcdev, + "irq_enable", 0)); + g_free(gpioname); + gpioname = g_strdup_printf("%s_irq_clear", ppcinfo->name); + qdev_connect_gpio_out_named(ssedev, gpioname, 0, + qdev_get_gpio_in_named(ppcdev, + "irq_clear", 0)); + g_free(gpioname); + gpioname = g_strdup_printf("%s_irq_status", ppcinfo->name); + qdev_connect_gpio_out_named(ppcdev, "irq", 0, + qdev_get_gpio_in_named(ssedev, + gpioname, 0)); + g_free(gpioname); + + qdev_connect_gpio_out(dev_splitter, i, + qdev_get_gpio_in_named(ppcdev, + "cfg_sec_resp", 0)); + } + armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, 0x2000000); } -- 2.20.1 The Musca board puts its SRAM and flash behind TrustZone Memory Protection Controllers (MPCs). Each MPC sits between the CPU and the RAM/flash, and also has a set of memory mapped control registers. Wire up the MPCs, and the memory behind them. For the moment we implement the flash as simple ROM, which cannot be reprogrammed by the guest. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- hw/arm/musca.c | 155 ++++++++++++++++++++++++++++++++++++++++++++++--- 1 file changed, 147 insertions(+), 8 deletions(-) diff --git a/hw/arm/musca.c b/hw/arm/musca.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/musca.c +++ b/hw/arm/musca.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/armsse.h" #include "hw/boards.h" #include "hw/core/split-irq.h" +#include "hw/misc/tz-mpc.h" #include "hw/misc/tz-ppc.h" #include "hw/misc/unimp.h" #define MUSCA_NUMIRQ_MAX 96 #define MUSCA_PPC_MAX 3 +#define MUSCA_MPC_MAX 5 + +typedef struct MPCInfo MPCInfo; typedef enum MuscaType { MUSCA_A, @@ -XXX,XX +XXX,XX @@ typedef struct { uint32_t init_svtor; int sram_addr_width; int num_irqs; + const MPCInfo *mpc_info; + int num_mpcs; } MuscaMachineClass; typedef struct { MachineState parent; ARMSSE sse; + /* RAM and flash */ + MemoryRegion ram[MUSCA_MPC_MAX]; SplitIRQ cpu_irq_splitter[MUSCA_NUMIRQ_MAX]; SplitIRQ sec_resp_splitter; TZPPC ppc[MUSCA_PPC_MAX]; MemoryRegion container; UnimplementedDeviceState eflash[2]; UnimplementedDeviceState qspi; - UnimplementedDeviceState mpc[5]; + TZMPC mpc[MUSCA_MPC_MAX]; UnimplementedDeviceState mhu[2]; UnimplementedDeviceState pwm[3]; UnimplementedDeviceState i2s; @@ -XXX,XX +XXX,XX @@ typedef struct { UnimplementedDeviceState pvt; UnimplementedDeviceState sdio; UnimplementedDeviceState gpio; + UnimplementedDeviceState cryptoisland; } MuscaMachineState; #define TYPE_MUSCA_MACHINE "musca" @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_unimp_dev(MuscaMachineState *mms, return sysbus_mmio_get_region(SYS_BUS_DEVICE(uds), 0); } +typedef enum MPCInfoType { + MPC_RAM, + MPC_ROM, + MPC_CRYPTOISLAND, +} MPCInfoType; + +struct MPCInfo { + const char *name; + hwaddr addr; + hwaddr size; + MPCInfoType type; +}; + +/* Order of the MPCs here must match the order of the bits in SECMPCINTSTATUS */ +static const MPCInfo a_mpc_info[] = { { + .name = "qspi", + .type = MPC_ROM, + .addr = 0x00200000, + .size = 0x00800000, + }, { + .name = "sram", + .type = MPC_RAM, + .addr = 0x00000000, + .size = 0x00200000, + } +}; + +static const MPCInfo b1_mpc_info[] = { { + .name = "qspi", + .type = MPC_ROM, + .addr = 0x00000000, + .size = 0x02000000, + }, { + .name = "sram", + .type = MPC_RAM, + .addr = 0x0a400000, + .size = 0x00080000, + }, { + .name = "eflash0", + .type = MPC_ROM, + .addr = 0x0a000000, + .size = 0x00200000, + }, { + .name = "eflash1", + .type = MPC_ROM, + .addr = 0x0a200000, + .size = 0x00200000, + }, { + .name = "cryptoisland", + .type = MPC_CRYPTOISLAND, + .addr = 0x0a000000, + .size = 0x00200000, + } +}; + +static MemoryRegion *make_mpc(MuscaMachineState *mms, void *opaque, + const char *name, hwaddr size) +{ + /* + * Create an MPC and the RAM or flash behind it. + * MPC 0: eFlash 0 + * MPC 1: eFlash 1 + * MPC 2: SRAM + * MPC 3: QSPI flash + * MPC 4: CryptoIsland + * For now we implement the flash regions as ROM (ie not programmable) + * (with their control interface memory regions being unimplemented + * stubs behind the PPCs). + * The whole CryptoIsland region behind its MPC is an unimplemented stub. + */ + MuscaMachineClass *mmc = MUSCA_MACHINE_GET_CLASS(mms); + TZMPC *mpc = opaque; + int i = mpc - &mms->mpc[0]; + MemoryRegion *downstream; + MemoryRegion *upstream; + UnimplementedDeviceState *uds; + char *mpcname; + const MPCInfo *mpcinfo = mmc->mpc_info; + + mpcname = g_strdup_printf("%s-mpc", mpcinfo[i].name); + + switch (mpcinfo[i].type) { + case MPC_ROM: + downstream = &mms->ram[i]; + memory_region_init_rom(downstream, NULL, mpcinfo[i].name, + mpcinfo[i].size, &error_fatal); + break; + case MPC_RAM: + downstream = &mms->ram[i]; + memory_region_init_ram(downstream, NULL, mpcinfo[i].name, + mpcinfo[i].size, &error_fatal); + break; + case MPC_CRYPTOISLAND: + /* We don't implement the CryptoIsland yet */ + uds = &mms->cryptoisland; + sysbus_init_child_obj(OBJECT(mms), name, uds, + sizeof(UnimplementedDeviceState), + TYPE_UNIMPLEMENTED_DEVICE); + qdev_prop_set_string(DEVICE(uds), "name", mpcinfo[i].name); + qdev_prop_set_uint64(DEVICE(uds), "size", mpcinfo[i].size); + object_property_set_bool(OBJECT(uds), true, "realized", &error_fatal); + downstream = sysbus_mmio_get_region(SYS_BUS_DEVICE(uds), 0); + break; + default: + g_assert_not_reached(); + } + + sysbus_init_child_obj(OBJECT(mms), mpcname, mpc, sizeof(mms->mpc[0]), + TYPE_TZ_MPC); + object_property_set_link(OBJECT(mpc), OBJECT(downstream), + "downstream", &error_fatal); + object_property_set_bool(OBJECT(mpc), true, "realized", &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(), mpcinfo[i].addr, upstream); + /* and connect its interrupt to the SSE-200 */ + qdev_connect_gpio_out_named(DEVICE(mpc), "irq", 0, + qdev_get_gpio_in_named(DEVICE(&mms->sse), + "mpcexp_status", i)); + + 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); +} + static MemoryRegion *make_musca_a_devs(MuscaMachineState *mms, void *opaque, const char *name, hwaddr size) { @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_musca_a_devs(MuscaMachineState *mms, void *opaque, { "pwm1", make_unimp_dev, &mms->pwm[1], 0xe000, 0x1000 }, { "pwm2", make_unimp_dev, &mms->pwm[2], 0xf000, 0x1000 }, { "gpio", make_unimp_dev, &mms->gpio, 0x10000, 0x1000 }, - { "mpc0", make_unimp_dev, &mms->mpc[0], 0x12000, 0x1000 }, - { "mpc1", make_unimp_dev, &mms->mpc[1], 0x13000, 0x1000 }, + { "mpc0", make_mpc, &mms->mpc[0], 0x12000, 0x1000 }, + { "mpc1", make_mpc, &mms->mpc[1], 0x13000, 0x1000 }, }; memory_region_init(container, OBJECT(mms), "musca-device-container", size); @@ -XXX,XX +XXX,XX @@ static void musca_init(MachineState *machine) int i; assert(mmc->num_irqs <= MUSCA_NUMIRQ_MAX); + assert(mmc->num_mpcs <= MUSCA_MPC_MAX); if (strcmp(machine->cpu_type, mc->default_cpu_type) != 0) { error_report("This board can only be used with CPU %s", @@ -XXX,XX +XXX,XX @@ static void musca_init(MachineState *machine) { "eflash1", make_unimp_dev, &mms->eflash[1], 0x52500000, 0x1000 }, { "qspi", make_unimp_dev, &mms->qspi, 0x42800000, 0x100000 }, - { "mpc0", make_unimp_dev, &mms->mpc[0], 0x52000000, 0x1000 }, - { "mpc1", make_unimp_dev, &mms->mpc[1], 0x52100000, 0x1000 }, - { "mpc2", make_unimp_dev, &mms->mpc[2], 0x52200000, 0x1000 }, - { "mpc3", make_unimp_dev, &mms->mpc[3], 0x52300000, 0x1000 }, + { "mpc0", make_mpc, &mms->mpc[0], 0x52000000, 0x1000 }, + { "mpc1", make_mpc, &mms->mpc[1], 0x52100000, 0x1000 }, + { "mpc2", make_mpc, &mms->mpc[2], 0x52200000, 0x1000 }, + { "mpc3", make_mpc, &mms->mpc[3], 0x52300000, 0x1000 }, { "mhu0", make_unimp_dev, &mms->mhu[0], 0x42600000, 0x100000 }, { "mhu1", make_unimp_dev, &mms->mhu[1], 0x42700000, 0x100000 }, { }, /* port 9: unused */ @@ -XXX,XX +XXX,XX @@ static void musca_init(MachineState *machine) { }, /* port 11: unused */ { }, /* port 12: unused */ { }, /* port 13: unused */ - { "mpc4", make_unimp_dev, &mms->mpc[4], 0x52e00000, 0x1000 }, + { "mpc4", make_mpc, &mms->mpc[4], 0x52e00000, 0x1000 }, }, }, { .name = "apb_ppcexp1", @@ -XXX,XX +XXX,XX @@ static void musca_a_class_init(ObjectClass *oc, void *data) mmc->init_svtor = 0x10200000; mmc->sram_addr_width = 15; mmc->num_irqs = 64; + mmc->mpc_info = a_mpc_info; + mmc->num_mpcs = ARRAY_SIZE(a_mpc_info); } static void musca_b1_class_init(ObjectClass *oc, void *data) @@ -XXX,XX +XXX,XX @@ static void musca_b1_class_init(ObjectClass *oc, void *data) mmc->init_svtor = 0x10000000; mmc->sram_addr_width = 17; mmc->num_irqs = 96; + mmc->mpc_info = b1_mpc_info; + mmc->num_mpcs = ARRAY_SIZE(b1_mpc_info); } static const TypeInfo musca_info = { -- 2.20.1 Wire up the PL031 RTC for the Musca board. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- hw/arm/musca.c | 26 +++++++++++++++++++++++--- 1 file changed, 23 insertions(+), 3 deletions(-) diff --git a/hw/arm/musca.c b/hw/arm/musca.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/musca.c +++ b/hw/arm/musca.c @@ -XXX,XX +XXX,XX @@ #include "hw/misc/tz-mpc.h" #include "hw/misc/tz-ppc.h" #include "hw/misc/unimp.h" +#include "hw/timer/pl031.h" #define MUSCA_NUMIRQ_MAX 96 #define MUSCA_PPC_MAX 3 @@ -XXX,XX +XXX,XX @@ typedef struct { UnimplementedDeviceState spi; UnimplementedDeviceState scc; UnimplementedDeviceState timer; - UnimplementedDeviceState rtc; + PL031State rtc; UnimplementedDeviceState pvt; UnimplementedDeviceState sdio; UnimplementedDeviceState gpio; @@ -XXX,XX +XXX,XX @@ typedef struct { */ #define SYSCLK_FRQ 40000000 +static qemu_irq get_sse_irq_in(MuscaMachineState *mms, int irqno) +{ + /* Return a qemu_irq which will signal IRQ n to all CPUs in the SSE. */ + assert(irqno < MUSCA_NUMIRQ_MAX); + + return qdev_get_gpio_in(DEVICE(&mms->cpu_irq_splitter[irqno]), 0); +} + /* * Most of the devices in the Musca board sit behind Peripheral Protection * Controllers. These data structures define the layout of which devices @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_mpc(MuscaMachineState *mms, void *opaque, return sysbus_mmio_get_region(SYS_BUS_DEVICE(mpc), 0); } +static MemoryRegion *make_rtc(MuscaMachineState *mms, void *opaque, + const char *name, hwaddr size) +{ + PL031State *rtc = opaque; + + sysbus_init_child_obj(OBJECT(mms), name, rtc, sizeof(mms->rtc), TYPE_PL031); + object_property_set_bool(OBJECT(rtc), true, "realized", &error_fatal); + sysbus_connect_irq(SYS_BUS_DEVICE(rtc), 0, get_sse_irq_in(mms, 39)); + return sysbus_mmio_get_region(SYS_BUS_DEVICE(rtc), 0); +} + static MemoryRegion *make_musca_a_devs(MuscaMachineState *mms, void *opaque, const char *name, hwaddr size) { @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_musca_a_devs(MuscaMachineState *mms, void *opaque, { "i2c1", make_unimp_dev, &mms->i2c[1], 0x5000, 0x1000 }, { "i2s", make_unimp_dev, &mms->i2s, 0x6000, 0x1000 }, { "pwm0", make_unimp_dev, &mms->pwm[0], 0x7000, 0x1000 }, - { "rtc", make_unimp_dev, &mms->rtc, 0x8000, 0x1000 }, + { "rtc", make_rtc, &mms->rtc, 0x8000, 0x1000 }, { "qspi", make_unimp_dev, &mms->qspi, 0xa000, 0x1000 }, { "timer", make_unimp_dev, &mms->timer, 0xb000, 0x1000 }, { "scc", make_unimp_dev, &mms->scc, 0xc000, 0x1000 }, @@ -XXX,XX +XXX,XX @@ static void musca_init(MachineState *machine) { "spi", make_unimp_dev, &mms->spi, 0x4010a000, 0x1000 }, { "scc", make_unimp_dev, &mms->scc, 0x5010b000, 0x1000 }, { "timer", make_unimp_dev, &mms->timer, 0x4010c000, 0x1000 }, - { "rtc", make_unimp_dev, &mms->rtc, 0x4010d000, 0x1000 }, + { "rtc", make_rtc, &mms->rtc, 0x4010d000, 0x1000 }, { "pvt", make_unimp_dev, &mms->pvt, 0x4010e000, 0x1000 }, { "sdio", make_unimp_dev, &mms->sdio, 0x4010f000, 0x1000 }, }, -- 2.20.1 Wire up the two PL011 UARTs in the Musca board. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- hw/arm/musca.c | 34 +++++++++++++++++++++++++++++----- 1 file changed, 29 insertions(+), 5 deletions(-) diff --git a/hw/arm/musca.c b/hw/arm/musca.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/musca.c +++ b/hw/arm/musca.c @@ -XXX,XX +XXX,XX @@ #include "qemu/error-report.h" #include "qapi/error.h" #include "exec/address-spaces.h" +#include "sysemu/sysemu.h" #include "hw/arm/arm.h" #include "hw/arm/armsse.h" #include "hw/boards.h" +#include "hw/char/pl011.h" #include "hw/core/split-irq.h" #include "hw/misc/tz-mpc.h" #include "hw/misc/tz-ppc.h" @@ -XXX,XX +XXX,XX @@ typedef struct { UnimplementedDeviceState mhu[2]; UnimplementedDeviceState pwm[3]; UnimplementedDeviceState i2s; - UnimplementedDeviceState uart[2]; + PL011State uart[2]; UnimplementedDeviceState i2c[2]; UnimplementedDeviceState spi; UnimplementedDeviceState scc; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_rtc(MuscaMachineState *mms, void *opaque, return sysbus_mmio_get_region(SYS_BUS_DEVICE(rtc), 0); } +static MemoryRegion *make_uart(MuscaMachineState *mms, void *opaque, + const char *name, hwaddr size) +{ + PL011State *uart = opaque; + int i = uart - &mms->uart[0]; + int irqbase = 7 + i * 6; + SysBusDevice *s; + + sysbus_init_child_obj(OBJECT(mms), name, uart, sizeof(mms->uart[0]), + TYPE_PL011); + qdev_prop_set_chr(DEVICE(uart), "chardev", serial_hd(i)); + object_property_set_bool(OBJECT(uart), true, "realized", &error_fatal); + s = SYS_BUS_DEVICE(uart); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqbase + 5)); /* combined */ + sysbus_connect_irq(s, 1, get_sse_irq_in(mms, irqbase + 0)); /* RX */ + sysbus_connect_irq(s, 2, get_sse_irq_in(mms, irqbase + 1)); /* TX */ + sysbus_connect_irq(s, 3, get_sse_irq_in(mms, irqbase + 2)); /* RT */ + sysbus_connect_irq(s, 4, get_sse_irq_in(mms, irqbase + 3)); /* MS */ + sysbus_connect_irq(s, 5, get_sse_irq_in(mms, irqbase + 4)); /* E */ + return sysbus_mmio_get_region(SYS_BUS_DEVICE(uart), 0); +} + static MemoryRegion *make_musca_a_devs(MuscaMachineState *mms, void *opaque, const char *name, hwaddr size) { @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_musca_a_devs(MuscaMachineState *mms, void *opaque, MemoryRegion *container = &mms->container; const PPCPortInfo devices[] = { - { "uart0", make_unimp_dev, &mms->uart[0], 0x1000, 0x1000 }, - { "uart1", make_unimp_dev, &mms->uart[1], 0x2000, 0x1000 }, + { "uart0", make_uart, &mms->uart[0], 0x1000, 0x1000 }, + { "uart1", make_uart, &mms->uart[1], 0x2000, 0x1000 }, { "spi", make_unimp_dev, &mms->spi, 0x3000, 0x1000 }, { "i2c0", make_unimp_dev, &mms->i2c[0], 0x4000, 0x1000 }, { "i2c1", make_unimp_dev, &mms->i2c[1], 0x5000, 0x1000 }, @@ -XXX,XX +XXX,XX @@ static void musca_init(MachineState *machine) { "pwm1", make_unimp_dev, &mms->pwm[1], 0x40102000, 0x1000 }, { "pwm2", make_unimp_dev, &mms->pwm[2], 0x40103000, 0x1000 }, { "i2s", make_unimp_dev, &mms->i2s, 0x40104000, 0x1000 }, - { "uart0", make_unimp_dev, &mms->uart[0], 0x40105000, 0x1000 }, - { "uart1", make_unimp_dev, &mms->uart[1], 0x40106000, 0x1000 }, + { "uart0", make_uart, &mms->uart[0], 0x40105000, 0x1000 }, + { "uart1", make_uart, &mms->uart[1], 0x40106000, 0x1000 }, { "i2c0", make_unimp_dev, &mms->i2c[0], 0x40108000, 0x1000 }, { "i2c1", make_unimp_dev, &mms->i2c[1], 0x40109000, 0x1000 }, { "spi", make_unimp_dev, &mms->spi, 0x4010a000, 0x1000 }, -- 2.20.1 The region 0x40010000 .. 0x4001ffff and its secure-only alias at 0x50010000... are for per-CPU devices. We implement this by giving each CPU its own container memory region, where the per-CPU devices live. Unfortunately, the alias region which makes devices mapped at 0x4... addresses also appear at 0x5... is only implemented in the overall "all CPUs" container. The effect of this bug is that the CPU_IDENTITY register block appears only at 0x4001f000, but not at the 0x5001f000 alias where it should also appear. Guests (like very recent Arm Trusted Firmware-M) which try to access it at 0x5001f000 will crash. Fix this by moving the handling for this alias from the "all CPUs" container to the per-CPU container. (We leave the aliases for 0x1... and 0x3... in the overall container, because there are no per-CPU devices there.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190215180500.6906-1-peter.maydell@linaro.org Reviewed-by: Alex Bennée <alex.bennee@linaro.org> --- include/hw/arm/armsse.h | 2 +- hw/arm/armsse.c | 26 ++++++++++++++++---------- 2 files changed, 17 insertions(+), 11 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 @@ typedef struct ARMSSE { MemoryRegion cpu_container[SSE_MAX_CPUS]; MemoryRegion alias1; MemoryRegion alias2; - MemoryRegion alias3; + MemoryRegion alias3[SSE_MAX_CPUS]; MemoryRegion sram[MAX_SRAM_BANKS]; qemu_irq *exp_irqs[SSE_MAX_CPUS]; diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armsse.c +++ b/hw/arm/armsse.c @@ -XXX,XX +XXX,XX @@ static bool irq_is_common[32] = { /* 30, 31: reserved */ }; -/* Create an alias region of @size bytes starting at @base +/* + * Create an alias region in @container of @size bytes starting at @base * which mirrors the memory starting at @orig. */ -static void make_alias(ARMSSE *s, MemoryRegion *mr, const char *name, - hwaddr base, hwaddr size, hwaddr orig) +static void make_alias(ARMSSE *s, MemoryRegion *mr, MemoryRegion *container, + const char *name, hwaddr base, hwaddr size, hwaddr orig) { - memory_region_init_alias(mr, NULL, name, &s->container, orig, size); + memory_region_init_alias(mr, NULL, name, container, orig, size); /* The alias is even lower priority than unimplemented_device regions */ - memory_region_add_subregion_overlap(&s->container, base, mr, -1500); + memory_region_add_subregion_overlap(container, base, mr, -1500); } static void irq_status_forwarder(void *opaque, int n, int level) @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) } /* Set up the big aliases first */ - make_alias(s, &s->alias1, "alias 1", 0x10000000, 0x10000000, 0x00000000); - make_alias(s, &s->alias2, "alias 2", 0x30000000, 0x10000000, 0x20000000); + make_alias(s, &s->alias1, &s->container, "alias 1", + 0x10000000, 0x10000000, 0x00000000); + make_alias(s, &s->alias2, &s->container, + "alias 2", 0x30000000, 0x10000000, 0x20000000); /* The 0x50000000..0x5fffffff region is not a pure alias: it has * a few extra devices that only appear there (generally the * control interfaces for the protection controllers). * We implement this by mapping those devices over the top of this - * alias MR at a higher priority. + * alias MR at a higher priority. Some of the devices in this range + * are per-CPU, so we must put this alias in the per-cpu containers. */ - make_alias(s, &s->alias3, "alias 3", 0x50000000, 0x10000000, 0x40000000); - + for (i = 0; i < info->num_cpus; i++) { + make_alias(s, &s->alias3[i], &s->cpu_container[i], + "alias 3", 0x50000000, 0x10000000, 0x40000000); + } /* Security controller */ object_property_set_bool(OBJECT(&s->secctl), true, "realized", &err); -- 2.20.1 Another arm pullreq; nothing particularly exciting here. -- PMM The following changes since commit e27d5b488ef08408691bfed61f34ee2858136287: Merge remote-tracking branch 'remotes/juanquintela/tags/pull-migration-pull-request' into staging (2020-02-28 14:02:31 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200228 for you to fetch changes up to 1904f9b5f1d94fe12fe021db6b504c87d684f6db: hw/intc/arm_gic_kvm: Don't assume kernel can provide a GICv2 (2020-02-28 16:14:57 +0000) ---------------------------------------------------------------- target-arm queue: * hw/arm: Use TYPE_PL011 to create serial port * target/arm: Set ID_MMFR4.HPDS for aarch64_max_initfn * hw/arm/integratorcp: Map the audio codec controller * GICv2: Correctly implement the limited number of priority bits * target/arm: refactoring of VFP related feature checks and decode * xilinx_zynq: Fix USB port instantiation * acceptance tests for n800, n810, integratorcp * Implement v8.3-RCPC, v8.4-RCPC, v8.3-CCIDX * arm_gic_kvm: Don't assume kernel can provide a GICv2 (provide better error message for user error) ---------------------------------------------------------------- Gavin Shan (1): hw/arm: Use TYPE_PL011 to create serial port Guenter Roeck (2): hw/arm/xilinx_zynq: Fix USB port instantiation hw/usb/hcd-ehci-sysbus: Remove obsolete xlnx, ps7-usb class Peter Maydell (5): target/arm: Fix wrong use of FIELD_EX32 on ID_AA64DFR0 target/arm: Implement v8.3-RCPC target/arm: Implement v8.4-RCPC target/arm: Implement ARMv8.3-CCIDX hw/intc/arm_gic_kvm: Don't assume kernel can provide a GICv2 Philippe Mathieu-Daudé (3): hw/arm/integratorcp: Map the audio codec controller tests/acceptance: Extract boot_integratorcp() from test_integratorcp() tests/acceptance/integratorcp: Verify Tux is displayed on framebuffer Richard Henderson (17): target/arm: Set ID_MMFR4.HPDS for aarch64_max_initfn target/arm: Add isar_feature_aa32_vfp_simd target/arm: Rename isar_feature_aa32_fpdp_v2 target/arm: Add isar_feature_aa32_{fpsp_v2, fpsp_v3, fpdp_v3} target/arm: Add isar_feature_aa64_fp_simd, isar_feature_aa32_vfp target/arm: Perform fpdp_v2 check first target/arm: Replace ARM_FEATURE_VFP3 checks with fp{sp, dp}_v3 target/arm: Add missing checks for fpsp_v2 target/arm: Replace ARM_FEATURE_VFP4 with isar_feature_aa32_simdfmac target/arm: Remove ARM_FEATURE_VFP check from disas_vfp_insn target/arm: Move VLLDM and VLSTM to vfp.decode target/arm: Move the vfp decodetree calls next to the base isa linux-user/arm: Replace ARM_FEATURE_VFP* tests for HWCAP target/arm: Remove ARM_FEATURE_VFP* target/arm: Add formats for some vfp 2 and 3-register insns target/arm: Split VFM decode target/arm: Split VMINMAXNM decode Sai Pavan Boddu (3): arm_gic: Mask the un-supported priority bits cpu/a9mpcore: Set number of GIC priority bits to 5 cpu/arm11mpcore: Set number of GIC priority bits to 4 Thomas Huth (2): tests/acceptance: Add a test for the N800 and N810 arm machines tests/acceptance: Add a test for the integratorcp arm machine include/hw/intc/arm_gic.h | 2 + include/hw/intc/arm_gic_common.h | 1 + target/arm/cpu.h | 88 +++++- hw/arm/integratorcp.c | 1 + hw/arm/sbsa-ref.c | 3 +- hw/arm/virt.c | 3 +- hw/arm/xilinx_zynq.c | 5 +- hw/arm/xlnx-versal.c | 3 +- hw/cpu/a9mpcore.c | 4 + hw/cpu/arm11mpcore.c | 5 + hw/intc/arm_gic.c | 33 +- hw/intc/arm_gic_common.c | 1 + hw/intc/arm_gic_kvm.c | 9 + hw/intc/armv7m_nvic.c | 20 +- hw/usb/hcd-ehci-sysbus.c | 17 - linux-user/arm/signal.c | 4 +- linux-user/elfload.c | 25 +- target/arm/arch_dump.c | 11 +- target/arm/cpu.c | 44 +-- target/arm/cpu64.c | 5 +- target/arm/helper.c | 23 +- target/arm/kvm32.c | 5 - target/arm/kvm64.c | 1 - target/arm/m_helper.c | 11 +- target/arm/machine.c | 5 +- target/arm/translate-a64.c | 114 +++++++ target/arm/translate-vfp.inc.c | 448 +++++++++++++++++---------- target/arm/translate.c | 122 ++------ MAINTAINERS | 2 + hw/arm/Kconfig | 1 + target/arm/vfp-uncond.decode | 12 +- target/arm/vfp.decode | 153 ++++----- tests/acceptance/machine_arm_integratorcp.py | 99 ++++++ tests/acceptance/machine_arm_n8x0.py | 49 +++ 34 files changed, 865 insertions(+), 464 deletions(-) create mode 100644 tests/acceptance/machine_arm_integratorcp.py create mode 100644 tests/acceptance/machine_arm_n8x0.py From: Gavin Shan <gshan@redhat.com> This uses TYPE_PL011 when creating the serial port so that the code looks cleaner. Signed-off-by: Gavin Shan <gshan@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20200224222223.4128-1-gshan@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 3 ++- hw/arm/virt.c | 3 ++- hw/arm/xlnx-versal.c | 3 ++- 3 files changed, 6 insertions(+), 3 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 @@ #include "hw/pci-host/gpex.h" #include "hw/qdev-properties.h" #include "hw/usb.h" +#include "hw/char/pl011.h" #include "net/net.h" #define RAMLIMIT_GB 8192 @@ -XXX,XX +XXX,XX @@ static void create_uart(const SBSAMachineState *sms, int uart, { hwaddr base = sbsa_ref_memmap[uart].base; int irq = sbsa_ref_irqmap[uart]; - DeviceState *dev = qdev_create(NULL, "pl011"); + DeviceState *dev = qdev_create(NULL, TYPE_PL011); SysBusDevice *s = SYS_BUS_DEVICE(dev); qdev_prop_set_chr(dev, "chardev", chr); diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ #include "hw/mem/nvdimm.h" #include "hw/acpi/generic_event_device.h" #include "hw/virtio/virtio-iommu.h" +#include "hw/char/pl011.h" #define DEFINE_VIRT_MACHINE_LATEST(major, minor, latest) \ static void virt_##major##_##minor##_class_init(ObjectClass *oc, \ @@ -XXX,XX +XXX,XX @@ static void create_uart(const VirtMachineState *vms, int uart, int irq = vms->irqmap[uart]; const char compat[] = "arm,pl011\0arm,primecell"; const char clocknames[] = "uartclk\0apb_pclk"; - DeviceState *dev = qdev_create(NULL, "pl011"); + DeviceState *dev = qdev_create(NULL, TYPE_PL011); SysBusDevice *s = SYS_BUS_DEVICE(dev); qdev_prop_set_chr(dev, "chardev", chr); diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ #include "hw/misc/unimp.h" #include "hw/intc/arm_gicv3_common.h" #include "hw/arm/xlnx-versal.h" +#include "hw/char/pl011.h" #define XLNX_VERSAL_ACPU_TYPE ARM_CPU_TYPE_NAME("cortex-a72") #define GEM_REVISION 0x40070106 @@ -XXX,XX +XXX,XX @@ static void versal_create_uarts(Versal *s, qemu_irq *pic) DeviceState *dev; MemoryRegion *mr; - dev = qdev_create(NULL, "pl011"); + dev = qdev_create(NULL, TYPE_PL011); s->lpd.iou.uart[i] = SYS_BUS_DEVICE(dev); qdev_prop_set_chr(dev, "chardev", serial_hd(i)); object_property_add_child(OBJECT(s), name, OBJECT(dev), &error_fatal); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We had set this for aarch32-only in arm_max_initfn, but failed to set the same bit for aarch64. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200218190958.745-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 1 + 1 file changed, 1 insertion(+) 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) cpu->isar.id_mmfr3 = u; u = cpu->isar.id_mmfr4; + u = FIELD_DP32(u, ID_MMFR4, HPDS, 1); /* AA32HPD */ u = FIELD_DP32(u, ID_MMFR4, AC2, 1); /* ACTLR2, HACTLR2 */ cpu->isar.id_mmfr4 = u; -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> The Linux kernel displays errors why trying to detect the PL041 audio interface: Linux version 4.16.0 (linus@genomnajs) (gcc version 7.2.1 20171011 (Linaro GCC 7.2-2017.11)) #142 PREEMPT Wed May 9 13:24:55 CEST 2018 CPU: ARM926EJ-S [41069265] revision 5 (ARMv5TEJ), cr=00093177 CPU: VIVT data cache, VIVT instruction cache OF: fdt: Machine model: ARM Integrator/CP ... OF: amba_device_add() failed (-19) for /fpga/aaci@1d000000 Since we have it already modelled, simply plug it. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200223233033.15371-2-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/integratorcp.c | 1 + hw/arm/Kconfig | 1 + 2 files changed, 2 insertions(+) diff --git a/hw/arm/integratorcp.c b/hw/arm/integratorcp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/integratorcp.c +++ b/hw/arm/integratorcp.c @@ -XXX,XX +XXX,XX @@ static void integratorcp_init(MachineState *machine) qdev_get_gpio_in_named(icp, ICP_GPIO_MMC_WPROT, 0)); qdev_connect_gpio_out(dev, 1, qdev_get_gpio_in_named(icp, ICP_GPIO_MMC_CARDIN, 0)); + sysbus_create_varargs("pl041", 0x1d000000, pic[25], NULL); if (nd_table[0].used) smc91c111_init(&nd_table[0], 0xc8000000, pic[27]); diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config INTEGRATOR select INTEGRATOR_DEBUG select PL011 # UART select PL031 # RTC + select PL041 # audio select PL050 # keyboard/mouse select PL110 # pl111 LCD controller select PL181 # display -- 2.20.1 From: Sai Pavan Boddu <sai.pavan.boddu@xilinx.com> The GICv2 allows the implementation to implement a variable number of priority bits; unimplemented bits in the priority registers are read as zeros, writes ignored. We were previously always implementing a full 8 bits of priority, which is allowed but not what the real hardware typically does (which is usually to have 4 or 5 bits of priority). Add a new device property to allow the number of implemented property bits to be specified. Signed-off-by: Sai Pavan Boddu <sai.pavan.boddu@xilinx.com> Message-id: 1582537164-764-2-git-send-email-sai.pavan.boddu@xilinx.com Suggested-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: improved commit message] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/intc/arm_gic.h | 2 ++ include/hw/intc/arm_gic_common.h | 1 + hw/intc/arm_gic.c | 33 ++++++++++++++++++++++++++++++-- hw/intc/arm_gic_common.c | 1 + 4 files changed, 35 insertions(+), 2 deletions(-) diff --git a/include/hw/intc/arm_gic.h b/include/hw/intc/arm_gic.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gic.h +++ b/include/hw/intc/arm_gic.h @@ -XXX,XX +XXX,XX @@ /* Number of SGI target-list bits */ #define GIC_TARGETLIST_BITS 8 +#define GIC_MAX_PRIORITY_BITS 8 +#define GIC_MIN_PRIORITY_BITS 4 #define TYPE_ARM_GIC "arm_gic" #define ARM_GIC(obj) \ diff --git a/include/hw/intc/arm_gic_common.h b/include/hw/intc/arm_gic_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gic_common.h +++ b/include/hw/intc/arm_gic_common.h @@ -XXX,XX +XXX,XX @@ typedef struct GICState { uint16_t priority_mask[GIC_NCPU_VCPU]; uint16_t running_priority[GIC_NCPU_VCPU]; uint16_t current_pending[GIC_NCPU_VCPU]; + uint32_t n_prio_bits; /* If we present the GICv2 without security extensions to a guest, * the guest can configure the GICC_CTLR to configure group 1 binary point diff --git a/hw/intc/arm_gic.c b/hw/intc/arm_gic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gic.c +++ b/hw/intc/arm_gic.c @@ -XXX,XX +XXX,XX @@ uint32_t gic_acknowledge_irq(GICState *s, int cpu, MemTxAttrs attrs) return ret; } +static uint32_t gic_fullprio_mask(GICState *s, int cpu) +{ + /* + * Return a mask word which clears the unimplemented priority + * bits from a priority value for an interrupt. (Not to be + * confused with the group priority, whose mask depends on BPR.) + */ + int priBits; + + if (gic_is_vcpu(cpu)) { + priBits = GIC_VIRT_MAX_GROUP_PRIO_BITS; + } else { + priBits = s->n_prio_bits; + } + return ~0U << (8 - priBits); +} + void gic_dist_set_priority(GICState *s, int cpu, int irq, uint8_t val, MemTxAttrs attrs) { @@ -XXX,XX +XXX,XX @@ void gic_dist_set_priority(GICState *s, int cpu, int irq, uint8_t val, val = 0x80 | (val >> 1); /* Non-secure view */ } + val &= gic_fullprio_mask(s, cpu); + if (irq < GIC_INTERNAL) { s->priority1[irq][cpu] = val; } else { @@ -XXX,XX +XXX,XX @@ static uint32_t gic_dist_get_priority(GICState *s, int cpu, int irq, } prio = (prio << 1) & 0xff; /* Non-secure view */ } - return prio; + return prio & gic_fullprio_mask(s, cpu); } static void gic_set_priority_mask(GICState *s, int cpu, uint8_t pmask, @@ -XXX,XX +XXX,XX @@ static void gic_set_priority_mask(GICState *s, int cpu, uint8_t pmask, return; } } - s->priority_mask[cpu] = pmask; + s->priority_mask[cpu] = pmask & gic_fullprio_mask(s, cpu); } static uint32_t gic_get_priority_mask(GICState *s, int cpu, MemTxAttrs attrs) @@ -XXX,XX +XXX,XX @@ static void arm_gic_realize(DeviceState *dev, Error **errp) return; } + if (s->n_prio_bits > GIC_MAX_PRIORITY_BITS || + (s->virt_extn ? s->n_prio_bits < GIC_VIRT_MAX_GROUP_PRIO_BITS : + s->n_prio_bits < GIC_MIN_PRIORITY_BITS)) { + error_setg(errp, "num-priority-bits cannot be greater than %d" + " or less than %d", GIC_MAX_PRIORITY_BITS, + s->virt_extn ? GIC_VIRT_MAX_GROUP_PRIO_BITS : + GIC_MIN_PRIORITY_BITS); + return; + } + /* This creates distributor, main CPU interface (s->cpuiomem[0]) and if * enabled, virtualization extensions related interfaces (main virtual * interface (s->vifaceiomem[0]) and virtual CPU interface). diff --git a/hw/intc/arm_gic_common.c b/hw/intc/arm_gic_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gic_common.c +++ b/hw/intc/arm_gic_common.c @@ -XXX,XX +XXX,XX @@ static Property arm_gic_common_properties[] = { DEFINE_PROP_BOOL("has-security-extensions", GICState, security_extn, 0), /* True if the GIC should implement the virtualization extensions */ DEFINE_PROP_BOOL("has-virtualization-extensions", GICState, virt_extn, 0), + DEFINE_PROP_UINT32("num-priority-bits", GICState, n_prio_bits, 8), DEFINE_PROP_END_OF_LIST(), }; -- 2.20.1 From: Sai Pavan Boddu <sai.pavan.boddu@xilinx.com> All A9 CPUs have a GIC with 5 bits of priority. Signed-off-by: Sai Pavan Boddu <sai.pavan.boddu@xilinx.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1582537164-764-3-git-send-email-sai.pavan.boddu@xilinx.com Suggested-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/cpu/a9mpcore.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/hw/cpu/a9mpcore.c b/hw/cpu/a9mpcore.c index XXXXXXX..XXXXXXX 100644 --- a/hw/cpu/a9mpcore.c +++ b/hw/cpu/a9mpcore.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-properties.h" #include "hw/core/cpu.h" +#define A9_GIC_NUM_PRIORITY_BITS 5 + static void a9mp_priv_set_irq(void *opaque, int irq, int level) { A9MPPrivState *s = (A9MPPrivState *)opaque; @@ -XXX,XX +XXX,XX @@ static void a9mp_priv_realize(DeviceState *dev, Error **errp) gicdev = DEVICE(&s->gic); qdev_prop_set_uint32(gicdev, "num-cpu", s->num_cpu); qdev_prop_set_uint32(gicdev, "num-irq", s->num_irq); + qdev_prop_set_uint32(gicdev, "num-priority-bits", + A9_GIC_NUM_PRIORITY_BITS); /* Make the GIC's TZ support match the CPUs. We assume that * either all the CPUs have TZ, or none do. -- 2.20.1 From: Sai Pavan Boddu <sai.pavan.boddu@xilinx.com> The GIC built into the ARM11MPCore is always implemented with 4 priority bits; set the GIC property accordingly. Signed-off-by: Sai Pavan Boddu <sai.pavan.boddu@xilinx.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1582537164-764-4-git-send-email-sai.pavan.boddu@xilinx.com Suggested-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: tweaked commit message] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/cpu/arm11mpcore.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/hw/cpu/arm11mpcore.c b/hw/cpu/arm11mpcore.c index XXXXXXX..XXXXXXX 100644 --- a/hw/cpu/arm11mpcore.c +++ b/hw/cpu/arm11mpcore.c @@ -XXX,XX +XXX,XX @@ #include "hw/irq.h" #include "hw/qdev-properties.h" +#define ARM11MPCORE_NUM_GIC_PRIORITY_BITS 4 static void mpcore_priv_set_irq(void *opaque, int irq, int level) { @@ -XXX,XX +XXX,XX @@ static void mpcore_priv_realize(DeviceState *dev, Error **errp) qdev_prop_set_uint32(gicdev, "num-cpu", s->num_cpu); qdev_prop_set_uint32(gicdev, "num-irq", s->num_irq); + qdev_prop_set_uint32(gicdev, "num-priority-bits", + ARM11MPCORE_NUM_GIC_PRIORITY_BITS); + + object_property_set_bool(OBJECT(&s->gic), true, "realized", &err); if (err != NULL) { error_propagate(errp, err); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Use this in the places that were checking ARM_FEATURE_VFP, and are obviously testing for the existance of the register set as opposed to testing for some particular instruction extension. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20200224222232.13807-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 9 +++++++++ hw/intc/armv7m_nvic.c | 20 ++++++++++---------- linux-user/arm/signal.c | 4 ++-- target/arm/arch_dump.c | 11 ++++++----- target/arm/cpu.c | 4 ++-- target/arm/helper.c | 4 ++-- target/arm/m_helper.c | 11 ++++++----- 7 files changed, 37 insertions(+), 26 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_fp16_arith(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) == 1; } +static inline bool isar_feature_aa32_vfp_simd(const ARMISARegisters *id) +{ + /* + * Return true if either VFP or SIMD is implemented. + * In this case, a minimum of VFP w/ D0-D15. + */ + return FIELD_EX32(id->mvfr0, MVFR0, SIMDREG) > 0; +} + static inline bool isar_feature_aa32_simd_r32(const ARMISARegisters *id) { /* Return true if D16-D31 are implemented */ diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) case 0xd84: /* CSSELR */ return cpu->env.v7m.csselr[attrs.secure]; case 0xd88: /* CPACR */ - if (!arm_feature(&cpu->env, ARM_FEATURE_VFP)) { + if (!cpu_isar_feature(aa32_vfp_simd, cpu)) { return 0; } return cpu->env.v7m.cpacr[attrs.secure]; case 0xd8c: /* NSACR */ - if (!attrs.secure || !arm_feature(&cpu->env, ARM_FEATURE_VFP)) { + if (!attrs.secure || !cpu_isar_feature(aa32_vfp_simd, cpu)) { return 0; } return cpu->env.v7m.nsacr; @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) } return cpu->env.v7m.sfar; case 0xf34: /* FPCCR */ - if (!arm_feature(&cpu->env, ARM_FEATURE_VFP)) { + if (!cpu_isar_feature(aa32_vfp_simd, cpu)) { return 0; } if (attrs.secure) { @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) return value; } case 0xf38: /* FPCAR */ - if (!arm_feature(&cpu->env, ARM_FEATURE_VFP)) { + if (!cpu_isar_feature(aa32_vfp_simd, cpu)) { return 0; } return cpu->env.v7m.fpcar[attrs.secure]; case 0xf3c: /* FPDSCR */ - if (!arm_feature(&cpu->env, ARM_FEATURE_VFP)) { + if (!cpu_isar_feature(aa32_vfp_simd, cpu)) { return 0; } return cpu->env.v7m.fpdscr[attrs.secure]; @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, } break; case 0xd88: /* CPACR */ - if (arm_feature(&cpu->env, ARM_FEATURE_VFP)) { + if (cpu_isar_feature(aa32_vfp_simd, cpu)) { /* We implement only the Floating Point extension's CP10/CP11 */ cpu->env.v7m.cpacr[attrs.secure] = value & (0xf << 20); } break; case 0xd8c: /* NSACR */ - if (attrs.secure && arm_feature(&cpu->env, ARM_FEATURE_VFP)) { + if (attrs.secure && cpu_isar_feature(aa32_vfp_simd, cpu)) { /* We implement only the Floating Point extension's CP10/CP11 */ cpu->env.v7m.nsacr = value & (3 << 10); } @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, break; } case 0xf34: /* FPCCR */ - if (arm_feature(&cpu->env, ARM_FEATURE_VFP)) { + if (cpu_isar_feature(aa32_vfp_simd, cpu)) { /* Not all bits here are banked. */ uint32_t fpccr_s; @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, } break; case 0xf38: /* FPCAR */ - if (arm_feature(&cpu->env, ARM_FEATURE_VFP)) { + if (cpu_isar_feature(aa32_vfp_simd, cpu)) { value &= ~7; cpu->env.v7m.fpcar[attrs.secure] = value; } break; case 0xf3c: /* FPDSCR */ - if (arm_feature(&cpu->env, ARM_FEATURE_VFP)) { + if (cpu_isar_feature(aa32_vfp_simd, cpu)) { value &= 0x07c00000; cpu->env.v7m.fpdscr[attrs.secure] = value; } diff --git a/linux-user/arm/signal.c b/linux-user/arm/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/arm/signal.c +++ b/linux-user/arm/signal.c @@ -XXX,XX +XXX,XX @@ static void setup_sigframe_v2(struct target_ucontext_v2 *uc, setup_sigcontext(&uc->tuc_mcontext, env, set->sig[0]); /* Save coprocessor signal frame. */ regspace = uc->tuc_regspace; - if (arm_feature(env, ARM_FEATURE_VFP)) { + if (cpu_isar_feature(aa32_vfp_simd, env_archcpu(env))) { regspace = setup_sigframe_v2_vfp(regspace, env); } if (arm_feature(env, ARM_FEATURE_IWMMXT)) { @@ -XXX,XX +XXX,XX @@ static int do_sigframe_return_v2(CPUARMState *env, /* Restore coprocessor signal frame */ regspace = uc->tuc_regspace; - if (arm_feature(env, ARM_FEATURE_VFP)) { + if (cpu_isar_feature(aa32_vfp_simd, env_archcpu(env))) { regspace = restore_sigframe_v2_vfp(env, regspace); if (!regspace) { return 1; diff --git a/target/arm/arch_dump.c b/target/arm/arch_dump.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/arch_dump.c +++ b/target/arm/arch_dump.c @@ -XXX,XX +XXX,XX @@ int arm_cpu_write_elf32_note(WriteCoreDumpFunction f, CPUState *cs, int cpuid, void *opaque) { struct arm_note note; - CPUARMState *env = &ARM_CPU(cs)->env; + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; DumpState *s = opaque; - int ret, i, fpvalid = !!arm_feature(env, ARM_FEATURE_VFP); + int ret, i; + bool fpvalid = cpu_isar_feature(aa32_vfp_simd, cpu); arm_note_init(&note, s, "CORE", 5, NT_PRSTATUS, sizeof(note.prstatus)); @@ -XXX,XX +XXX,XX @@ int cpu_get_dump_info(ArchDumpInfo *info, ssize_t cpu_get_note_size(int class, int machine, int nr_cpus) { ARMCPU *cpu = ARM_CPU(first_cpu); - CPUARMState *env = &cpu->env; size_t note_size; if (class == ELFCLASS64) { @@ -XXX,XX +XXX,XX @@ ssize_t cpu_get_note_size(int class, int machine, int nr_cpus) note_size += AARCH64_PRFPREG_NOTE_SIZE; #ifdef TARGET_AARCH64 if (cpu_isar_feature(aa64_sve, cpu)) { - note_size += AARCH64_SVE_NOTE_SIZE(env); + note_size += AARCH64_SVE_NOTE_SIZE(&cpu->env); } #endif } else { note_size = ARM_PRSTATUS_NOTE_SIZE; - if (arm_feature(env, ARM_FEATURE_VFP)) { + if (cpu_isar_feature(aa32_vfp_simd, cpu)) { note_size += ARM_VFP_NOTE_SIZE; } } diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(CPUState *s) env->v7m.ccr[M_REG_S] |= R_V7M_CCR_UNALIGN_TRP_MASK; } - if (arm_feature(env, ARM_FEATURE_VFP)) { + if (cpu_isar_feature(aa32_vfp_simd, cpu)) { env->v7m.fpccr[M_REG_NS] = R_V7M_FPCCR_ASPEN_MASK; env->v7m.fpccr[M_REG_S] = R_V7M_FPCCR_ASPEN_MASK | R_V7M_FPCCR_LSPEN_MASK | R_V7M_FPCCR_S_MASK; @@ -XXX,XX +XXX,XX @@ static void arm_cpu_dump_state(CPUState *cs, FILE *f, int flags) int numvfpregs = 0; if (cpu_isar_feature(aa32_simd_r32, cpu)) { numvfpregs = 32; - } else if (arm_feature(env, ARM_FEATURE_VFP)) { + } else if (cpu_isar_feature(aa32_vfp_simd, cpu)) { numvfpregs = 16; } for (i = 0; i < numvfpregs; i++) { diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void cpacr_write(CPUARMState *env, const ARMCPRegInfo *ri, * ASEDIS [31] and D32DIS [30] are both UNK/SBZP without VFP. * TRCDIS [28] is RAZ/WI since we do not implement a trace macrocell. */ - if (arm_feature(env, ARM_FEATURE_VFP)) { + if (cpu_isar_feature(aa32_vfp_simd, env_archcpu(env))) { /* VFP coprocessor: cp10 & cp11 [23:20] */ mask |= (1 << 31) | (1 << 30) | (0xf << 20); @@ -XXX,XX +XXX,XX @@ void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu) } else if (cpu_isar_feature(aa32_simd_r32, cpu)) { gdb_register_coprocessor(cs, vfp_gdb_get_reg, vfp_gdb_set_reg, 35, "arm-vfp3.xml", 0); - } else if (arm_feature(env, ARM_FEATURE_VFP)) { + } else if (cpu_isar_feature(aa32_vfp_simd, cpu)) { gdb_register_coprocessor(cs, vfp_gdb_get_reg, vfp_gdb_set_reg, 19, "arm-vfp.xml", 0); } diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -XXX,XX +XXX,XX @@ static uint32_t v7m_integrity_sig(CPUARMState *env, uint32_t lr) */ uint32_t sig = 0xfefa125a; - if (!arm_feature(env, ARM_FEATURE_VFP) || (lr & R_V7M_EXCRET_FTYPE_MASK)) { + if (!cpu_isar_feature(aa32_vfp_simd, env_archcpu(env)) + || (lr & R_V7M_EXCRET_FTYPE_MASK)) { sig |= 1; } return sig; @@ -XXX,XX +XXX,XX @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, if (dotailchain) { /* Sanitize LR FType and PREFIX bits */ - if (!arm_feature(env, ARM_FEATURE_VFP)) { + if (!cpu_isar_feature(aa32_vfp_simd, cpu)) { lr |= R_V7M_EXCRET_FTYPE_MASK; } lr = deposit32(lr, 24, 8, 0xff); @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) ftype = excret & R_V7M_EXCRET_FTYPE_MASK; - if (!arm_feature(env, ARM_FEATURE_VFP) && !ftype) { + if (!ftype && !cpu_isar_feature(aa32_vfp_simd, cpu)) { qemu_log_mask(LOG_GUEST_ERROR, "M profile: zero FTYPE in exception " "exit PC value 0x%" PRIx32 " is UNPREDICTABLE " "if FPU not present\n", @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_msr)(CPUARMState *env, uint32_t maskreg, uint32_t val) * SFPA is RAZ/WI from NS. FPCA is RO if NSACR.CP10 == 0, * RES0 if the FPU is not present, and is stored in the S bank */ - if (arm_feature(env, ARM_FEATURE_VFP) && + if (cpu_isar_feature(aa32_vfp_simd, env_archcpu(env)) && extract32(env->v7m.nsacr, 10, 1)) { env->v7m.control[M_REG_S] &= ~R_V7M_CONTROL_FPCA_MASK; env->v7m.control[M_REG_S] |= val & R_V7M_CONTROL_FPCA_MASK; @@ -XXX,XX +XXX,XX @@ void HELPER(v7m_msr)(CPUARMState *env, uint32_t maskreg, uint32_t val) env->v7m.control[env->v7m.secure] &= ~R_V7M_CONTROL_NPRIV_MASK; env->v7m.control[env->v7m.secure] |= val & R_V7M_CONTROL_NPRIV_MASK; } - if (arm_feature(env, ARM_FEATURE_VFP)) { + if (cpu_isar_feature(aa32_vfp_simd, env_archcpu(env))) { /* * SFPA is RAZ/WI from NS or if no FPU. * FPCA is RO if NSACR.CP10 == 0, RES0 if the FPU is not present. -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The old name, isar_feature_aa32_fpdp, does not reflect that the test includes VFPv2. We will introduce another feature tests for VFPv3. Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200224222232.13807-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 4 ++-- target/arm/translate-vfp.inc.c | 40 +++++++++++++++++----------------- 2 files changed, 22 insertions(+), 22 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_fpshvec(const ARMISARegisters *id) return FIELD_EX32(id->mvfr0, MVFR0, FPSHVEC) > 0; } -static inline bool isar_feature_aa32_fpdp(const ARMISARegisters *id) +static inline bool isar_feature_aa32_fpdp_v2(const ARMISARegisters *id) { - /* Return true if CPU supports double precision floating point */ + /* Return true if CPU supports double precision floating point, VFPv2 */ return FIELD_EX32(id->mvfr0, MVFR0, FPDP) > 0; } diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) return false; } - if (dp && !dc_isar_feature(aa32_fpdp, s)) { + if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMINMAXNM(DisasContext *s, arg_VMINMAXNM *a) return false; } - if (dp && !dc_isar_feature(aa32_fpdp, s)) { + if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) return false; } - if (dp && !dc_isar_feature(aa32_fpdp, s)) { + if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) return false; } - if (dp && !dc_isar_feature(aa32_fpdp, s)) { + if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn, return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VFM_dp(DisasContext *s, arg_VFM_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCMP_dp(DisasContext *s, arg_VCMP_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f64_f16(DisasContext *s, arg_VCVT_f64_f16 *a) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f16_f64(DisasContext *s, arg_VCVT_f16_f64 *a) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_dp(DisasContext *s, arg_VRINTR_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_dp(DisasContext *s, arg_VRINTZ_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_dp(DisasContext *s, arg_VRINTX_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp(DisasContext *s, arg_VCVT_sp *a) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_dp(DisasContext *s, arg_VCVT_int_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VJCVT(DisasContext *s, arg_VJCVT *a) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) return false; } - if (!dc_isar_feature(aa32_fpdp, s)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We will shortly use these to test for VFPv2 and VFPv3 in different situations. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200224222232.13807-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_fpshvec(const ARMISARegisters *id) return FIELD_EX32(id->mvfr0, MVFR0, FPSHVEC) > 0; } +static inline bool isar_feature_aa32_fpsp_v2(const ARMISARegisters *id) +{ + /* Return true if CPU supports single precision floating point, VFPv2 */ + return FIELD_EX32(id->mvfr0, MVFR0, FPSP) > 0; +} + +static inline bool isar_feature_aa32_fpsp_v3(const ARMISARegisters *id) +{ + /* Return true if CPU supports single precision floating point, VFPv3 */ + return FIELD_EX32(id->mvfr0, MVFR0, FPSP) >= 2; +} + static inline bool isar_feature_aa32_fpdp_v2(const ARMISARegisters *id) { /* Return true if CPU supports double precision floating point, VFPv2 */ return FIELD_EX32(id->mvfr0, MVFR0, FPDP) > 0; } +static inline bool isar_feature_aa32_fpdp_v3(const ARMISARegisters *id) +{ + /* Return true if CPU supports double precision floating point, VFPv3 */ + return FIELD_EX32(id->mvfr0, MVFR0, FPDP) >= 2; +} + /* * We always set the FP and SIMD FP16 fields to indicate identical * levels of support (assuming SIMD is implemented at all), so -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We cannot easily create "any" functions for these, because the ID_AA64PFR0 fields for FP and SIMD signal "enabled" with zero. Which means that an aarch32-only cpu will return incorrect results when testing the aarch64 registers. To use these, we must either have context or additionally test vs ARM_FEATURE_AARCH64. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20200224222232.13807-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 11 +++++++++++ target/arm/cpu.c | 9 ++++++--- target/arm/machine.c | 5 +++-- 3 files changed, 20 insertions(+), 5 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_fpdp_v3(const ARMISARegisters *id) return FIELD_EX32(id->mvfr0, MVFR0, FPDP) >= 2; } +static inline bool isar_feature_aa32_vfp(const ARMISARegisters *id) +{ + return isar_feature_aa32_fpsp_v2(id) || isar_feature_aa32_fpdp_v2(id); +} + /* * We always set the FP and SIMD FP16 fields to indicate identical * levels of support (assuming SIMD is implemented at all), so @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_dcpodp(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, DPB) >= 2; } +static inline bool isar_feature_aa64_fp_simd(const ARMISARegisters *id) +{ + /* We always set the AdvSIMD and FP fields identically. */ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) != 0xf; +} + static inline bool isar_feature_aa64_fp16(const ARMISARegisters *id) { /* We always set the AdvSIMD and FP fields identically wrt FP16. */ diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_post_init(Object *obj) * KVM does not currently allow us to lie to the guest about its * ID/feature registers, so the guest always sees what the host has. */ - if (arm_feature(&cpu->env, ARM_FEATURE_VFP)) { + if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64) + ? cpu_isar_feature(aa64_fp_simd, cpu) + : cpu_isar_feature(aa32_vfp, cpu)) { cpu->has_vfp = true; if (!kvm_enabled()) { qdev_property_add_static(DEVICE(obj), &arm_cpu_has_vfp_property); @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) * We rely on no XScale CPU having VFP so we can use the same bits in the * TB flags field for VECSTRIDE and XSCALE_CPAR. */ - assert(!(arm_feature(env, ARM_FEATURE_VFP) && - arm_feature(env, ARM_FEATURE_XSCALE))); + assert(arm_feature(&cpu->env, ARM_FEATURE_AARCH64) || + !cpu_isar_feature(aa32_vfp_simd, cpu) || + !arm_feature(env, ARM_FEATURE_XSCALE)); if (arm_feature(env, ARM_FEATURE_V7) && !arm_feature(env, ARM_FEATURE_M) && diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static bool vfp_needed(void *opaque) { ARMCPU *cpu = opaque; - CPUARMState *env = &cpu->env; - return arm_feature(env, ARM_FEATURE_VFP); + return (arm_feature(&cpu->env, ARM_FEATURE_AARCH64) + ? cpu_isar_feature(aa64_fp_simd, cpu) + : cpu_isar_feature(aa32_vfp_simd, cpu)); } static int get_fpscr(QEMUFile *f, void *opaque, size_t size, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Shuffle the order of the checks so that we test the ISA before we test anything else, such as the register arguments. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200224222232.13807-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-vfp.inc.c | 140 +++++++++++++++++---------------- 1 file changed, 71 insertions(+), 69 deletions(-) diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) return false; } - /* UNDEF accesses to D16-D31 if they don't exist */ - if (dp && !dc_isar_feature(aa32_simd_r32, s) && - ((a->vm | a->vn | a->vd) & 0x10)) { + if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { return false; } - if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { + /* UNDEF accesses to D16-D31 if they don't exist */ + if (dp && !dc_isar_feature(aa32_simd_r32, s) && + ((a->vm | a->vn | a->vd) & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMINMAXNM(DisasContext *s, arg_VMINMAXNM *a) return false; } - /* UNDEF accesses to D16-D31 if they don't exist */ - if (dp && !dc_isar_feature(aa32_simd_r32, s) && - ((a->vm | a->vn | a->vd) & 0x10)) { + if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { return false; } - if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { + /* UNDEF accesses to D16-D31 if they don't exist */ + if (dp && !dc_isar_feature(aa32_simd_r32, s) && + ((a->vm | a->vn | a->vd) & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) return false; } - /* UNDEF accesses to D16-D31 if they don't exist */ - if (dp && !dc_isar_feature(aa32_simd_r32, s) && - ((a->vm | a->vd) & 0x10)) { + if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { return false; } - if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { + /* UNDEF accesses to D16-D31 if they don't exist */ + if (dp && !dc_isar_feature(aa32_simd_r32, s) && + ((a->vm | a->vd) & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) 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 (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { return false; } - if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { + /* UNDEF accesses to D16-D31 if they don't exist */ + if (dp && !dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn, TCGv_i64 f0, f1, fd; TCGv_ptr fpst; - /* UNDEF accesses to D16-D31 if they don't exist */ - if (!dc_isar_feature(aa32_simd_r32, s) && ((vd | vn | vm) & 0x10)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { + /* UNDEF accesses to D16-D31 if they don't exist */ + if (!dc_isar_feature(aa32_simd_r32, s) && ((vd | vn | vm) & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_dp(DisasContext *s, VFPGen2OpDPFn *fn, int vd, int vm) int veclen = s->vec_len; TCGv_i64 f0, fd; - /* UNDEF accesses to D16-D31 if they don't exist */ - if (!dc_isar_feature(aa32_simd_r32, s) && ((vd | vm) & 0x10)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { + /* UNDEF accesses to D16-D31 if they don't exist */ + if (!dc_isar_feature(aa32_simd_r32, s) && ((vd | vm) & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VFM_dp(DisasContext *s, arg_VFM_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { + /* 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; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) vd = a->vd; - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && (vd & 0x10)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && (vd & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCMP_dp(DisasContext *s, arg_VCMP_dp *a) { TCGv_i64 vd, vm; + if (!dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + /* Vm/M bits must be zero for the Z variant */ if (a->z && a->vm != 0) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VCMP_dp(DisasContext *s, arg_VCMP_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { - return false; - } - if (!vfp_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f64_f16(DisasContext *s, arg_VCVT_f64_f16 *a) TCGv_i32 tmp; TCGv_i64 vd; + if (!dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + if (!dc_isar_feature(aa32_fp16_dpconv, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f64_f16(DisasContext *s, arg_VCVT_f64_f16 *a) return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { - return false; - } - if (!vfp_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f16_f64(DisasContext *s, arg_VCVT_f16_f64 *a) TCGv_i32 tmp; TCGv_i64 vm; + if (!dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + if (!dc_isar_feature(aa32_fp16_dpconv, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f16_f64(DisasContext *s, arg_VCVT_f16_f64 *a) return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { - return false; - } - if (!vfp_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_dp(DisasContext *s, arg_VRINTR_dp *a) TCGv_ptr fpst; TCGv_i64 tmp; + if (!dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + if (!dc_isar_feature(aa32_vrint, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_dp(DisasContext *s, arg_VRINTR_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { - return false; - } - if (!vfp_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_dp(DisasContext *s, arg_VRINTZ_dp *a) TCGv_i64 tmp; TCGv_i32 tcg_rmode; + if (!dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + if (!dc_isar_feature(aa32_vrint, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_dp(DisasContext *s, arg_VRINTZ_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { - return false; - } - if (!vfp_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_dp(DisasContext *s, arg_VRINTX_dp *a) TCGv_ptr fpst; TCGv_i64 tmp; + if (!dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + if (!dc_isar_feature(aa32_vrint, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_dp(DisasContext *s, arg_VRINTX_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { - return false; - } - if (!vfp_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp(DisasContext *s, arg_VCVT_sp *a) TCGv_i64 vd; TCGv_i32 vm; - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a) TCGv_i64 vm; TCGv_i32 vd; - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_dp(DisasContext *s, arg_VCVT_int_dp *a) TCGv_i64 vd; TCGv_ptr fpst; - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VJCVT(DisasContext *s, arg_VJCVT *a) TCGv_i32 vd; TCGv_i64 vm; + if (!dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + if (!dc_isar_feature(aa32_jscvt, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VJCVT(DisasContext *s, arg_VJCVT *a) return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { - return false; - } - if (!vfp_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) TCGv_ptr fpst; int frac_bits; + if (!dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { - return false; - } - if (!vfp_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) TCGv_i64 vm; TCGv_ptr fpst; - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { + if (!dc_isar_feature(aa32_fpdp_v2, s)) { return false; } - if (!dc_isar_feature(aa32_fpdp_v2, s)) { + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { return false; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Sort this check to the start of a trans_* function. Merge this with any existing test for fpdp_v2. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200224222232.13807-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-vfp.inc.c | 24 ++++++++---------------- 1 file changed, 8 insertions(+), 16 deletions(-) diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) * VFPv2 allows access to FPSID from userspace; VFPv3 restricts * all ID registers to privileged access only. */ - if (IS_USER(s) && arm_dc_feature(s, ARM_FEATURE_VFP3)) { + if (IS_USER(s) && dc_isar_feature(aa32_fpsp_v3, s)) { return false; } ignore_vfp_enabled = true; @@ -XXX,XX +XXX,XX @@ static bool trans_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) case ARM_VFP_FPINST: case ARM_VFP_FPINST2: /* Not present in VFPv3 */ - if (IS_USER(s) || arm_dc_feature(s, ARM_FEATURE_VFP3)) { + if (IS_USER(s) || dc_isar_feature(aa32_fpsp_v3, s)) { return false; } break; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_sp(DisasContext *s, arg_VMOV_imm_sp *a) vd = a->vd; - if (!dc_isar_feature(aa32_fpshvec, s) && - (veclen != 0 || s->vec_stride != 0)) { + if (!dc_isar_feature(aa32_fpsp_v3, s)) { return false; } - if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { + if (!dc_isar_feature(aa32_fpshvec, s) && + (veclen != 0 || s->vec_stride != 0)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) vd = a->vd; - if (!dc_isar_feature(aa32_fpdp_v2, s)) { + if (!dc_isar_feature(aa32_fpdp_v3, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_imm_dp(DisasContext *s, arg_VMOV_imm_dp *a) return false; } - if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { - return false; - } - if (!vfp_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_sp(DisasContext *s, arg_VCVT_fix_sp *a) TCGv_ptr fpst; int frac_bits; - if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { + if (!dc_isar_feature(aa32_fpsp_v3, s)) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) TCGv_ptr fpst; int frac_bits; - if (!dc_isar_feature(aa32_fpdp_v2, s)) { - return false; - } - - if (!arm_dc_feature(s, ARM_FEATURE_VFP3)) { + if (!dc_isar_feature(aa32_fpdp_v3, s)) { return false; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We will eventually remove the early ARM_FEATURE_VFP test, so add a proper test for each trans_* that does not already have another ISA test. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200224222232.13807-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-vfp.inc.c | 78 ++++++++++++++++++++++++++++++---- 1 file changed, 69 insertions(+), 9 deletions(-) diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a) int pass; uint32_t offset; + /* SIZE == 2 is a VFP instruction; otherwise NEON. */ + if (a->size == 2 + ? !dc_isar_feature(aa32_fpsp_v2, s) + : !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->vn & 0x10)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_to_gp(DisasContext *s, arg_VMOV_to_gp *a) pass = extract32(offset, 2, 1); offset = extract32(offset, 0, 2) * 8; - if (a->size != 2 && !arm_dc_feature(s, ARM_FEATURE_NEON)) { - return false; - } - if (!vfp_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_from_gp(DisasContext *s, arg_VMOV_from_gp *a) int pass; uint32_t offset; + /* SIZE == 2 is a VFP instruction; otherwise NEON. */ + if (a->size == 2 + ? !dc_isar_feature(aa32_fpsp_v2, s) + : !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->vn & 0x10)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_from_gp(DisasContext *s, arg_VMOV_from_gp *a) pass = extract32(offset, 2, 1); offset = extract32(offset, 0, 2) * 8; - if (a->size != 2 && !arm_dc_feature(s, ARM_FEATURE_NEON)) { - return false; - } - if (!vfp_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) TCGv_i32 tmp; bool ignore_vfp_enabled = false; + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + if (arm_dc_feature(s, ARM_FEATURE_M)) { /* * The only M-profile VFP vmrs/vmsr sysreg is FPSCR. @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_single(DisasContext *s, arg_VMOV_single *a) { TCGv_i32 tmp; + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + if (!vfp_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_64_sp(DisasContext *s, arg_VMOV_64_sp *a) { TCGv_i32 tmp; + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + /* * VMOV between two general-purpose registers and two single precision * floating point registers @@ -XXX,XX +XXX,XX @@ static bool trans_VMOV_64_dp(DisasContext *s, arg_VMOV_64_dp *a) /* * VMOV between two general-purpose registers and one double precision - * floating point register + * floating point register. Note that this does not require support + * for double precision arithmetic. */ + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } /* UNDEF accesses to D16-D31 if they don't exist */ if (!dc_isar_feature(aa32_simd_r32, s) && (a->vm & 0x10)) { @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_sp(DisasContext *s, arg_VLDR_VSTR_sp *a) uint32_t offset; TCGv_i32 addr, tmp; + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + if (!vfp_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VLDR_VSTR_dp(DisasContext *s, arg_VLDR_VSTR_dp *a) TCGv_i32 addr; TCGv_i64 tmp; + /* Note that this does not require support for double arithmetic. */ + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + /* UNDEF accesses to D16-D31 if they don't exist */ if (!dc_isar_feature(aa32_simd_r32, s) && (a->vd & 0x10)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VLDM_VSTM_sp(DisasContext *s, arg_VLDM_VSTM_sp *a) TCGv_i32 addr, tmp; int i, n; + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + n = a->imm; if (n == 0 || (a->vd + n) > 32) { @@ -XXX,XX +XXX,XX @@ static bool trans_VLDM_VSTM_dp(DisasContext *s, arg_VLDM_VSTM_dp *a) TCGv_i64 tmp; int i, n; + /* Note that this does not require support for double arithmetic. */ + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + n = a->imm >> 1; if (n == 0 || (a->vd + n) > 32 || n > 16) { @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_sp(DisasContext *s, VFPGen3OpSPFn *fn, TCGv_i32 f0, f1, fd; TCGv_ptr fpst; + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + if (!dc_isar_feature(aa32_fpshvec, s) && (veclen != 0 || s->vec_stride != 0)) { return false; @@ -XXX,XX +XXX,XX @@ static bool do_vfp_2op_sp(DisasContext *s, VFPGen2OpSPFn *fn, int vd, int vm) int veclen = s->vec_len; TCGv_i32 f0, fd; + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + if (!dc_isar_feature(aa32_fpshvec, s) && (veclen != 0 || s->vec_stride != 0)) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VCMP_sp(DisasContext *s, arg_VCMP_sp *a) { TCGv_i32 vd, vm; + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + /* Vm/M bits must be zero for the Z variant */ if (a->z && a->vm != 0) { return false; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_sp(DisasContext *s, arg_VCVT_int_sp *a) TCGv_i32 vm; TCGv_ptr fpst; + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + if (!vfp_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp_int(DisasContext *s, arg_VCVT_sp_int *a) TCGv_i32 vm; TCGv_ptr fpst; + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + if (!vfp_access_check(s)) { return true; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> All remaining tests for VFP4 are for fused multiply-add insns. Since the MVFR1 field is used for both VFP and NEON, move its adjustment from the !has_neon block to the (!has_vfp && !has_neon) block. Test for vfp of the appropraite width alongside the test for simdfmac within translate-vfp.inc.c. Within disas_neon_data_insn, we have already tested for ARM_FEATURE_NEON. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20200224222232.13807-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 12 ++++++++++++ target/arm/cpu.c | 6 +++++- target/arm/translate-vfp.inc.c | 22 ++++++++++++++++++---- target/arm/translate.c | 2 +- 4 files changed, 36 insertions(+), 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_fp16_dpconv(const ARMISARegisters *id) return FIELD_EX32(id->mvfr1, MVFR1, FPHP) > 1; } +/* + * Note that this ID register field covers both VFP and Neon FMAC, + * so should usually be tested in combination with some other + * check that confirms the presence of whichever of VFP or Neon is + * relevant, to avoid accidentally enabling a Neon feature on + * a VFP-no-Neon core or vice-versa. + */ +static inline bool isar_feature_aa32_simdfmac(const ARMISARegisters *id) +{ + return FIELD_EX32(id->mvfr1, MVFR1, SIMDFMAC) != 0; +} + static inline bool isar_feature_aa32_vsel(const ARMISARegisters *id) { return FIELD_EX32(id->mvfr2, MVFR2, FPMISC) >= 1; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) u = FIELD_DP32(u, MVFR1, SIMDINT, 0); u = FIELD_DP32(u, MVFR1, SIMDSP, 0); u = FIELD_DP32(u, MVFR1, SIMDHP, 0); - u = FIELD_DP32(u, MVFR1, SIMDFMAC, 0); cpu->isar.mvfr1 = u; u = cpu->isar.mvfr2; @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) u = cpu->isar.mvfr0; u = FIELD_DP32(u, MVFR0, SIMDREG, 0); cpu->isar.mvfr0 = u; + + /* Despite the name, this field covers both VFP and Neon */ + u = cpu->isar.mvfr1; + u = FIELD_DP32(u, MVFR1, SIMDFMAC, 0); + cpu->isar.mvfr1 = u; } if (arm_feature(env, ARM_FEATURE_M) && !cpu->has_dsp) { diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VFM_sp(DisasContext *s, arg_VFM_sp *a) /* * Present in VFPv4 only. + * 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_simdfmac, s) || + !dc_isar_feature(aa32_fpsp_v2, s)) { + return false; + } + /* * In v7A, UNPREDICTABLE with non-zero vector length/stride; from * v8A, must UNDEF. We choose to UNDEF for both v7A and v8A. */ - if (!arm_dc_feature(s, ARM_FEATURE_VFP4) || - (s->vec_len != 0 || s->vec_stride != 0)) { + if (s->vec_len != 0 || s->vec_stride != 0) { return false; } @@ -XXX,XX +XXX,XX @@ static bool trans_VFM_dp(DisasContext *s, arg_VFM_dp *a) /* * Present in VFPv4 only. + * 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_simdfmac, s) || + !dc_isar_feature(aa32_fpdp_v2, s)) { + return false; + } + /* * In v7A, UNPREDICTABLE with non-zero vector length/stride; from * v8A, must UNDEF. We choose to UNDEF for both v7A and v8A. */ - if (!arm_dc_feature(s, ARM_FEATURE_VFP4) || - (s->vec_len != 0 || s->vec_stride != 0)) { + if (s->vec_len != 0 || s->vec_stride != 0) { return false; } diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } break; case NEON_3R_VFM_VQRDMLSH: - if (!arm_dc_feature(s, ARM_FEATURE_VFP4)) { + if (!dc_isar_feature(aa32_simdfmac, s)) { return 1; } break; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We now have proper ISA checks within each trans_* function. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200224222232.13807-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 4 ---- 1 file changed, 4 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_neon_dup_high16(TCGv_i32 var) */ static int disas_vfp_insn(DisasContext *s, uint32_t insn) { - if (!arm_dc_feature(s, ARM_FEATURE_VFP)) { - return 1; - } - /* * If the decodetree decoder handles this insn it will always * emit code to either execute the insn or generate an appropriate -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Now that we no longer have an early check for ARM_FEATURE_VFP, we can use the proper ISA check in trans_VLLDM_VLSTM. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20200224222232.13807-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-vfp.inc.c | 39 +++++++++++++++++++++++++ target/arm/translate.c | 53 ++++++---------------------------- target/arm/vfp.decode | 2 ++ 3 files changed, 50 insertions(+), 44 deletions(-) diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) tcg_temp_free_ptr(fpst); return true; } + +/* + * Decode VLLDM and VLSTM are nonstandard because: + * * if there is no FPU then these insns must NOP in + * Secure state and UNDEF in Nonsecure state + * * if there is an FPU then these insns do not have + * the usual behaviour that vfp_access_check() provides of + * being controlled by CPACR/NSACR enable bits or the + * lazy-stacking logic. + */ +static bool trans_VLLDM_VLSTM(DisasContext *s, arg_VLLDM_VLSTM *a) +{ + TCGv_i32 fptr; + + if (!arm_dc_feature(s, ARM_FEATURE_M) || + !arm_dc_feature(s, ARM_FEATURE_V8)) { + return false; + } + /* If not secure, UNDEF. */ + if (!s->v8m_secure) { + return false; + } + /* If no fpu, NOP. */ + if (!dc_isar_feature(aa32_vfp, s)) { + return true; + } + + fptr = load_reg(s, a->rn); + if (a->l) { + gen_helper_v7m_vlldm(cpu_env, fptr); + } else { + gen_helper_v7m_vlstm(cpu_env, fptr); + } + tcg_temp_free_i32(fptr); + + /* End the TB, because we have updated FP control bits */ + s->base.is_jmp = DISAS_UPDATE; + return true; +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) goto illegal_op; /* op0 = 0b11 : unallocated */ } - /* - * Decode VLLDM and VLSTM first: these are nonstandard because: - * * if there is no FPU then these insns must NOP in - * Secure state and UNDEF in Nonsecure state - * * if there is an FPU then these insns do not have - * the usual behaviour that disas_vfp_insn() provides of - * being controlled by CPACR/NSACR enable bits or the - * lazy-stacking logic. - */ - if (arm_dc_feature(s, ARM_FEATURE_V8) && - (insn & 0xffa00f00) == 0xec200a00) { - /* 0b1110_1100_0x1x_xxxx_xxxx_1010_xxxx_xxxx - * - VLLDM, VLSTM - * We choose to UNDEF if the RAZ bits are non-zero. - */ - if (!s->v8m_secure || (insn & 0x0040f0ff)) { + if (disas_vfp_insn(s, insn)) { + if (((insn >> 8) & 0xe) == 10 && + dc_isar_feature(aa32_fpsp_v2, s)) { + /* FP, and the CPU supports it */ goto illegal_op; + } else { + /* All other insns: NOCP */ + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, + syn_uncategorized(), + default_exception_el(s)); } - - if (arm_dc_feature(s, ARM_FEATURE_VFP)) { - uint32_t rn = (insn >> 16) & 0xf; - TCGv_i32 fptr = load_reg(s, rn); - - if (extract32(insn, 20, 1)) { - gen_helper_v7m_vlldm(cpu_env, fptr); - } else { - gen_helper_v7m_vlstm(cpu_env, fptr); - } - tcg_temp_free_i32(fptr); - - /* End the TB, because we have updated FP control bits */ - s->base.is_jmp = DISAS_UPDATE; - } - break; } - if (arm_dc_feature(s, ARM_FEATURE_VFP) && - ((insn >> 8) & 0xe) == 10) { - /* FP, and the CPU supports it */ - if (disas_vfp_insn(s, insn)) { - goto illegal_op; - } - break; - } - - /* All other insns: NOCP */ - gen_exception_insn(s, s->pc_curr, EXCP_NOCP, syn_uncategorized(), - default_exception_el(s)); break; } if ((insn & 0xfe000a00) == 0xfc000800 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_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 .... \ vd=%vd_sp vm=%vm_dp + +VLLDM_VLSTM 1110 1100 001 l:1 rn:4 0000 1010 0000 0000 -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Have the calls adjacent as an intermediate step toward actually merging the decodes. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20200224222232.13807-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 83 +++++++++++++++--------------------------- 1 file changed, 29 insertions(+), 54 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_neon_dup_high16(TCGv_i32 var) tcg_temp_free_i32(tmp); } -/* - * Disassemble a VFP instruction. Returns nonzero if an error occurred - * (ie. an undefined instruction). - */ -static int disas_vfp_insn(DisasContext *s, uint32_t insn) -{ - /* - * If the decodetree decoder handles this insn it will always - * emit code to either execute the insn or generate an appropriate - * exception; so we don't need to ever return non-zero to tell - * the calling code to emit an UNDEF exception. - */ - if (extract32(insn, 28, 4) == 0xf) { - if (disas_vfp_uncond(s, insn)) { - return 0; - } - } else { - if (disas_vfp(s, insn)) { - return 0; - } - } - /* If the decodetree decoder didn't handle this insn, it must be UNDEF */ - return 1; -} - static inline bool use_goto_tb(DisasContext *s, target_ulong dest) { #ifndef CONFIG_USER_ONLY @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) ARCH(5); /* Unconditional instructions. */ - if (disas_a32_uncond(s, insn)) { + /* TODO: Perhaps merge these into one decodetree output file. */ + if (disas_a32_uncond(s, insn) || + disas_vfp_uncond(s, insn)) { return; } /* fall back to legacy decoder */ @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) } return; } - if ((insn & 0x0f000e10) == 0x0e000a00) { - /* VFP. */ - if (disas_vfp_insn(s, insn)) { - goto illegal_op; - } - return; - } if ((insn & 0x0e000f00) == 0x0c000100) { if (arm_dc_feature(s, ARM_FEATURE_IWMMXT)) { /* iWMMXt register transfer. */ @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) arm_skip_unless(s, cond); } - if (disas_a32(s, insn)) { + /* TODO: Perhaps merge these into one decodetree output file. */ + if (disas_a32(s, insn) || + disas_vfp(s, insn)) { return; } /* fall back to legacy decoder */ @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) case 0xd: case 0xe: if (((insn >> 8) & 0xe) == 10) { - /* VFP. */ - if (disas_vfp_insn(s, insn)) { - goto illegal_op; - } - } else if (disas_coproc_insn(s, insn)) { + /* VFP, but failed disas_vfp. */ + goto illegal_op; + } + if (disas_coproc_insn(s, insn)) { /* Coprocessor. */ goto illegal_op; } @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) ARCH(6T2); } - if (disas_t32(s, insn)) { + /* + * TODO: Perhaps merge these into one decodetree output file. + * Note disas_vfp is written for a32 with cond field in the + * top nibble. The t32 encoding requires 0xe in the top nibble. + */ + if (disas_t32(s, insn) || + disas_vfp_uncond(s, insn) || + ((insn >> 28) == 0xe && disas_vfp(s, insn))) { return; } /* fall back to legacy decoder */ @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) goto illegal_op; /* op0 = 0b11 : unallocated */ } - if (disas_vfp_insn(s, insn)) { - if (((insn >> 8) & 0xe) == 10 && - dc_isar_feature(aa32_fpsp_v2, s)) { - /* FP, and the CPU supports it */ - goto illegal_op; - } else { - /* All other insns: NOCP */ - gen_exception_insn(s, s->pc_curr, EXCP_NOCP, - syn_uncategorized(), - default_exception_el(s)); - } + if (((insn >> 8) & 0xe) == 10 && + dc_isar_feature(aa32_fpsp_v2, s)) { + /* FP, and the CPU supports it */ + goto illegal_op; + } else { + /* All other insns: NOCP */ + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, + syn_uncategorized(), + default_exception_el(s)); } break; } @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) goto illegal_op; } } else if (((insn >> 8) & 0xe) == 10) { - if (disas_vfp_insn(s, insn)) { - goto illegal_op; - } + /* VFP, but failed disas_vfp. */ + goto illegal_op; } else { if (insn & (1 << 28)) goto illegal_op; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Use isar feature tests instead of feature bit tests. Although none of QEMUs current cpus have VFPv3 without D32, replace the large comment explaining why with one line that sets ARM_HWCAP_ARM_VFPv3D16 under the correct conditions. Mirror the test sequence used in the linux kernel. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20200224222232.13807-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/elfload.c | 23 +++++++++++++---------- 1 file changed, 13 insertions(+), 10 deletions(-) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) /* EDSP is in v5TE and above, but all our v5 CPUs are v5TE */ GET_FEATURE(ARM_FEATURE_V5, ARM_HWCAP_ARM_EDSP); - GET_FEATURE(ARM_FEATURE_VFP, ARM_HWCAP_ARM_VFP); GET_FEATURE(ARM_FEATURE_IWMMXT, ARM_HWCAP_ARM_IWMMXT); GET_FEATURE(ARM_FEATURE_THUMB2EE, ARM_HWCAP_ARM_THUMBEE); GET_FEATURE(ARM_FEATURE_NEON, ARM_HWCAP_ARM_NEON); - GET_FEATURE(ARM_FEATURE_VFP3, ARM_HWCAP_ARM_VFPv3); GET_FEATURE(ARM_FEATURE_V6K, ARM_HWCAP_ARM_TLS); - GET_FEATURE(ARM_FEATURE_VFP4, ARM_HWCAP_ARM_VFPv4); + GET_FEATURE(ARM_FEATURE_LPAE, ARM_HWCAP_ARM_LPAE); GET_FEATURE_ID(aa32_arm_div, ARM_HWCAP_ARM_IDIVA); GET_FEATURE_ID(aa32_thumb_div, ARM_HWCAP_ARM_IDIVT); - /* All QEMU's VFPv3 CPUs have 32 registers, see VFP_DREG in translate.c. - * Note that the ARM_HWCAP_ARM_VFPv3D16 bit is always the inverse of - * ARM_HWCAP_ARM_VFPD32 (and so always clear for QEMU); it is unrelated - * to our VFP_FP16 feature bit. - */ - GET_FEATURE(ARM_FEATURE_VFP3, ARM_HWCAP_ARM_VFPD32); - GET_FEATURE(ARM_FEATURE_LPAE, ARM_HWCAP_ARM_LPAE); + GET_FEATURE_ID(aa32_vfp, ARM_HWCAP_ARM_VFP); + + if (cpu_isar_feature(aa32_fpsp_v3, cpu) || + cpu_isar_feature(aa32_fpdp_v3, cpu)) { + hwcaps |= ARM_HWCAP_ARM_VFPv3; + if (cpu_isar_feature(aa32_simd_r32, cpu)) { + hwcaps |= ARM_HWCAP_ARM_VFPD32; + } else { + hwcaps |= ARM_HWCAP_ARM_VFPv3D16; + } + } + GET_FEATURE_ID(aa32_simdfmac, ARM_HWCAP_ARM_VFPv4); return hwcaps; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We have converted all tests against these features to ISAR tests. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200224222232.13807-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 3 --- target/arm/cpu.c | 25 ------------------------- target/arm/cpu64.c | 3 --- target/arm/kvm32.c | 5 ----- target/arm/kvm64.c | 1 - 5 files changed, 37 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 @@ QEMU_BUILD_BUG_ON(ARRAY_SIZE(((ARMCPU *)0)->ccsidr) <= R_V7M_CSSELR_INDEX_MASK); * mapping in linux-user/elfload.c:get_elf_hwcap(). */ enum arm_features { - ARM_FEATURE_VFP, ARM_FEATURE_AUXCR, /* ARM1026 Auxiliary control register. */ ARM_FEATURE_XSCALE, /* Intel XScale extensions. */ ARM_FEATURE_IWMMXT, /* Intel iwMMXt extension. */ @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_V7, ARM_FEATURE_THUMB2, ARM_FEATURE_PMSA, /* no MMU; may have Memory Protection Unit */ - ARM_FEATURE_VFP3, ARM_FEATURE_NEON, ARM_FEATURE_M, /* Microcontroller profile. */ ARM_FEATURE_OMAPCP, /* OMAP specific CP15 ops handling. */ @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_V5, ARM_FEATURE_STRONGARM, ARM_FEATURE_VAPA, /* cp15 VA to PA lookups */ - ARM_FEATURE_VFP4, /* VFPv4 (implies that NEON is v2) */ ARM_FEATURE_GENERIC_TIMER, ARM_FEATURE_MVFR, /* Media and VFP Feature Registers 0 and 1 */ ARM_FEATURE_DUMMY_C15_REGS, /* RAZ/WI all of cp15 crn=15 */ diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_post_init(Object *obj) if (arm_feature(&cpu->env, ARM_FEATURE_M)) { set_feature(&cpu->env, ARM_FEATURE_PMSA); } - /* Similarly for the VFP feature bits */ - if (arm_feature(&cpu->env, ARM_FEATURE_VFP4)) { - set_feature(&cpu->env, ARM_FEATURE_VFP3); - } - if (arm_feature(&cpu->env, ARM_FEATURE_VFP3)) { - set_feature(&cpu->env, ARM_FEATURE_VFP); - } if (arm_feature(&cpu->env, ARM_FEATURE_CBAR) || arm_feature(&cpu->env, ARM_FEATURE_CBAR_RO)) { @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) uint64_t t; uint32_t u; - unset_feature(env, ARM_FEATURE_VFP); - unset_feature(env, ARM_FEATURE_VFP3); - unset_feature(env, ARM_FEATURE_VFP4); - t = cpu->isar.id_aa64isar1; t = FIELD_DP64(t, ID_AA64ISAR1, JSCVT, 0); cpu->isar.id_aa64isar1 = t; @@ -XXX,XX +XXX,XX @@ static void arm926_initfn(Object *obj) cpu->dtb_compatible = "arm,arm926"; set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_VFP); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CACHE_TEST_CLEAN); cpu->midr = 0x41069265; @@ -XXX,XX +XXX,XX @@ static void arm1026_initfn(Object *obj) cpu->dtb_compatible = "arm,arm1026"; set_feature(&cpu->env, ARM_FEATURE_V5); - set_feature(&cpu->env, ARM_FEATURE_VFP); set_feature(&cpu->env, ARM_FEATURE_AUXCR); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CACHE_TEST_CLEAN); @@ -XXX,XX +XXX,XX @@ static void arm1136_r2_initfn(Object *obj) cpu->dtb_compatible = "arm,arm1136"; set_feature(&cpu->env, ARM_FEATURE_V6); - set_feature(&cpu->env, ARM_FEATURE_VFP); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CACHE_DIRTY_REG); set_feature(&cpu->env, ARM_FEATURE_CACHE_BLOCK_OPS); @@ -XXX,XX +XXX,XX @@ static void arm1136_initfn(Object *obj) cpu->dtb_compatible = "arm,arm1136"; set_feature(&cpu->env, ARM_FEATURE_V6K); set_feature(&cpu->env, ARM_FEATURE_V6); - set_feature(&cpu->env, ARM_FEATURE_VFP); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CACHE_DIRTY_REG); set_feature(&cpu->env, ARM_FEATURE_CACHE_BLOCK_OPS); @@ -XXX,XX +XXX,XX @@ static void arm1176_initfn(Object *obj) cpu->dtb_compatible = "arm,arm1176"; set_feature(&cpu->env, ARM_FEATURE_V6K); - set_feature(&cpu->env, ARM_FEATURE_VFP); set_feature(&cpu->env, ARM_FEATURE_VAPA); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CACHE_DIRTY_REG); @@ -XXX,XX +XXX,XX @@ static void arm11mpcore_initfn(Object *obj) cpu->dtb_compatible = "arm,arm11mpcore"; set_feature(&cpu->env, ARM_FEATURE_V6K); - set_feature(&cpu->env, ARM_FEATURE_VFP); set_feature(&cpu->env, ARM_FEATURE_VAPA); set_feature(&cpu->env, ARM_FEATURE_MPIDR); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); @@ -XXX,XX +XXX,XX @@ static void cortex_m4_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_M); set_feature(&cpu->env, ARM_FEATURE_M_MAIN); set_feature(&cpu->env, ARM_FEATURE_THUMB_DSP); - set_feature(&cpu->env, ARM_FEATURE_VFP4); cpu->midr = 0x410fc240; /* r0p0 */ cpu->pmsav7_dregion = 8; cpu->isar.mvfr0 = 0x10110021; @@ -XXX,XX +XXX,XX @@ static void cortex_m7_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_M); set_feature(&cpu->env, ARM_FEATURE_M_MAIN); set_feature(&cpu->env, ARM_FEATURE_THUMB_DSP); - set_feature(&cpu->env, ARM_FEATURE_VFP4); cpu->midr = 0x411fc272; /* r1p2 */ cpu->pmsav7_dregion = 8; cpu->isar.mvfr0 = 0x10110221; @@ -XXX,XX +XXX,XX @@ static void cortex_m33_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_M_MAIN); set_feature(&cpu->env, ARM_FEATURE_M_SECURITY); set_feature(&cpu->env, ARM_FEATURE_THUMB_DSP); - set_feature(&cpu->env, ARM_FEATURE_VFP4); cpu->midr = 0x410fd213; /* r0p3 */ cpu->pmsav7_dregion = 16; cpu->sau_sregion = 8; @@ -XXX,XX +XXX,XX @@ static void cortex_r5f_initfn(Object *obj) ARMCPU *cpu = ARM_CPU(obj); cortex_r5_initfn(obj); - set_feature(&cpu->env, ARM_FEATURE_VFP3); cpu->isar.mvfr0 = 0x10110221; cpu->isar.mvfr1 = 0x00000011; } @@ -XXX,XX +XXX,XX @@ static void cortex_a8_initfn(Object *obj) cpu->dtb_compatible = "arm,cortex-a8"; set_feature(&cpu->env, ARM_FEATURE_V7); - set_feature(&cpu->env, ARM_FEATURE_VFP3); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); @@ -XXX,XX +XXX,XX @@ static void cortex_a9_initfn(Object *obj) cpu->dtb_compatible = "arm,cortex-a9"; set_feature(&cpu->env, ARM_FEATURE_V7); - set_feature(&cpu->env, ARM_FEATURE_VFP3); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_EL3); @@ -XXX,XX +XXX,XX @@ static void cortex_a7_initfn(Object *obj) cpu->dtb_compatible = "arm,cortex-a7"; set_feature(&cpu->env, ARM_FEATURE_V7VE); - set_feature(&cpu->env, ARM_FEATURE_VFP4); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); @@ -XXX,XX +XXX,XX @@ static void cortex_a15_initfn(Object *obj) cpu->dtb_compatible = "arm,cortex-a15"; set_feature(&cpu->env, ARM_FEATURE_V7VE); - set_feature(&cpu->env, ARM_FEATURE_VFP4); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); 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_a57_initfn(Object *obj) cpu->dtb_compatible = "arm,cortex-a57"; set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_VFP4); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_AARCH64); @@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj) cpu->dtb_compatible = "arm,cortex-a53"; set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_VFP4); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_AARCH64); @@ -XXX,XX +XXX,XX @@ static void aarch64_a72_initfn(Object *obj) cpu->dtb_compatible = "arm,cortex-a72"; set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_VFP4); set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_AARCH64); diff --git a/target/arm/kvm32.c b/target/arm/kvm32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm32.c +++ b/target/arm/kvm32.c @@ -XXX,XX +XXX,XX @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) * bits, but a few must be tested. */ set_feature(&features, ARM_FEATURE_V7VE); - set_feature(&features, ARM_FEATURE_VFP3); set_feature(&features, ARM_FEATURE_GENERIC_TIMER); if (extract32(id_pfr0, 12, 4) == 1) { @@ -XXX,XX +XXX,XX @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) if (extract32(ahcf->isar.mvfr1, 12, 4) == 1) { set_feature(&features, ARM_FEATURE_NEON); } - if (extract32(ahcf->isar.mvfr1, 28, 4) == 1) { - /* FMAC support implies VFPv4 */ - set_feature(&features, ARM_FEATURE_VFP4); - } ahcf->features = features; diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ bool kvm_arm_get_host_cpu_features(ARMHostCPUFeatures *ahcf) * feature bits. */ set_feature(&features, ARM_FEATURE_V8); - set_feature(&features, ARM_FEATURE_VFP4); set_feature(&features, ARM_FEATURE_NEON); set_feature(&features, ARM_FEATURE_AARCH64); set_feature(&features, ARM_FEATURE_PMU); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Those vfp instructions without extra opcode fields can share a common @format for brevity. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200224222232.13807-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/vfp.decode | 134 ++++++++++++++++-------------------------- 1 file changed, 52 insertions(+), 82 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_imm 16:4 0:4 +@vfp_dnm_s ................................ vm=%vm_sp vn=%vn_sp vd=%vd_sp +@vfp_dnm_d ................................ vm=%vm_dp vn=%vn_dp vd=%vd_dp + +@vfp_dm_ss ................................ vm=%vm_sp vd=%vd_sp +@vfp_dm_dd ................................ vm=%vm_dp vd=%vd_dp +@vfp_dm_ds ................................ vm=%vm_sp vd=%vd_dp +@vfp_dm_sd ................................ vm=%vm_dp vd=%vd_sp + # VMOV scalar to general-purpose register; note that this does # include some Neon cases. VMOV_to_gp ---- 1110 u:1 1. 1 .... rt:4 1011 ... 1 0000 \ @@ -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_single ---- 1110 000 l:1 .... rt:4 1010 . 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 -VMOV_64_dp ---- 1100 010 op:1 rt2:4 rt:4 1011 00.1 .... \ - vm=%vm_dp +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_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 +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 # We split the load/store multiple up into two patterns to avoid # overlap with other insns in the "Advanced SIMD load/store and 64-bit move" @@ -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_sp ---- 1110 0.00 .... .... 1010 .0.0 .... \ - vm=%vm_sp vn=%vn_sp vd=%vd_sp -VMLA_dp ---- 1110 0.00 .... .... 1011 .0.0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +VMLA_sp ---- 1110 0.00 .... .... 1010 .0.0 .... @vfp_dnm_s +VMLA_dp ---- 1110 0.00 .... .... 1011 .0.0 .... @vfp_dnm_d -VMLS_sp ---- 1110 0.00 .... .... 1010 .1.0 .... \ - vm=%vm_sp vn=%vn_sp vd=%vd_sp -VMLS_dp ---- 1110 0.00 .... .... 1011 .1.0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +VMLS_sp ---- 1110 0.00 .... .... 1010 .1.0 .... @vfp_dnm_s +VMLS_dp ---- 1110 0.00 .... .... 1011 .1.0 .... @vfp_dnm_d -VNMLS_sp ---- 1110 0.01 .... .... 1010 .0.0 .... \ - vm=%vm_sp vn=%vn_sp vd=%vd_sp -VNMLS_dp ---- 1110 0.01 .... .... 1011 .0.0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +VNMLS_sp ---- 1110 0.01 .... .... 1010 .0.0 .... @vfp_dnm_s +VNMLS_dp ---- 1110 0.01 .... .... 1011 .0.0 .... @vfp_dnm_d -VNMLA_sp ---- 1110 0.01 .... .... 1010 .1.0 .... \ - vm=%vm_sp vn=%vn_sp vd=%vd_sp -VNMLA_dp ---- 1110 0.01 .... .... 1011 .1.0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +VNMLA_sp ---- 1110 0.01 .... .... 1010 .1.0 .... @vfp_dnm_s +VNMLA_dp ---- 1110 0.01 .... .... 1011 .1.0 .... @vfp_dnm_d -VMUL_sp ---- 1110 0.10 .... .... 1010 .0.0 .... \ - vm=%vm_sp vn=%vn_sp vd=%vd_sp -VMUL_dp ---- 1110 0.10 .... .... 1011 .0.0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +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 .... \ - vm=%vm_sp vn=%vn_sp vd=%vd_sp -VNMUL_dp ---- 1110 0.10 .... .... 1011 .1.0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +VNMUL_sp ---- 1110 0.10 .... .... 1010 .1.0 .... @vfp_dnm_s +VNMUL_dp ---- 1110 0.10 .... .... 1011 .1.0 .... @vfp_dnm_d -VADD_sp ---- 1110 0.11 .... .... 1010 .0.0 .... \ - vm=%vm_sp vn=%vn_sp vd=%vd_sp -VADD_dp ---- 1110 0.11 .... .... 1011 .0.0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +VADD_sp ---- 1110 0.11 .... .... 1010 .0.0 .... @vfp_dnm_s +VADD_dp ---- 1110 0.11 .... .... 1011 .0.0 .... @vfp_dnm_d -VSUB_sp ---- 1110 0.11 .... .... 1010 .1.0 .... \ - vm=%vm_sp vn=%vn_sp vd=%vd_sp -VSUB_dp ---- 1110 0.11 .... .... 1011 .1.0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +VSUB_sp ---- 1110 0.11 .... .... 1010 .1.0 .... @vfp_dnm_s +VSUB_dp ---- 1110 0.11 .... .... 1011 .1.0 .... @vfp_dnm_d -VDIV_sp ---- 1110 1.00 .... .... 1010 .0.0 .... \ - vm=%vm_sp vn=%vn_sp vd=%vd_sp -VDIV_dp ---- 1110 1.00 .... .... 1011 .0.0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp +VDIV_sp ---- 1110 1.00 .... .... 1010 .0.0 .... @vfp_dnm_s +VDIV_dp ---- 1110 1.00 .... .... 1011 .0.0 .... @vfp_dnm_d VFM_sp ---- 1110 1.01 .... .... 1010 . o2:1 . 0 .... \ vm=%vm_sp vn=%vn_sp vd=%vd_sp o1=1 @@ -XXX,XX +XXX,XX @@ VMOV_imm_sp ---- 1110 1.11 .... .... 1010 0000 .... \ VMOV_imm_dp ---- 1110 1.11 .... .... 1011 0000 .... \ vd=%vd_dp imm=%vmov_imm -VMOV_reg_sp ---- 1110 1.11 0000 .... 1010 01.0 .... \ - vd=%vd_sp vm=%vm_sp -VMOV_reg_dp ---- 1110 1.11 0000 .... 1011 01.0 .... \ - vd=%vd_dp vm=%vm_dp +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_sp ---- 1110 1.11 0000 .... 1010 11.0 .... \ - vd=%vd_sp vm=%vm_sp -VABS_dp ---- 1110 1.11 0000 .... 1011 11.0 .... \ - vd=%vd_dp vm=%vm_dp +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_sp ---- 1110 1.11 0001 .... 1010 01.0 .... \ - vd=%vd_sp vm=%vm_sp -VNEG_dp ---- 1110 1.11 0001 .... 1011 01.0 .... \ - vd=%vd_dp vm=%vm_dp +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_sp ---- 1110 1.11 0001 .... 1010 11.0 .... \ - vd=%vd_sp vm=%vm_sp -VSQRT_dp ---- 1110 1.11 0001 .... 1011 11.0 .... \ - vd=%vd_dp vm=%vm_dp +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_sp ---- 1110 1.11 010 z:1 .... 1010 e:1 1.0 .... \ vd=%vd_sp vm=%vm_sp @@ -XXX,XX +XXX,XX @@ VCVT_f32_f16 ---- 1110 1.11 0010 .... 1010 t:1 1.0 .... \ VCVT_f64_f16 ---- 1110 1.11 0010 .... 1011 t:1 1.0 .... \ vd=%vd_dp vm=%vm_sp -# VCVTB and VCVTT to f16: Vd format is always vd_sp; Vm format depends on size bit +# VCVTB and VCVTT to f16: Vd format is always vd_sp; +# Vm format depends on size bit VCVT_f16_f32 ---- 1110 1.11 0011 .... 1010 t:1 1.0 .... \ vd=%vd_sp vm=%vm_sp VCVT_f16_f64 ---- 1110 1.11 0011 .... 1011 t:1 1.0 .... \ vd=%vd_sp vm=%vm_dp -VRINTR_sp ---- 1110 1.11 0110 .... 1010 01.0 .... \ - vd=%vd_sp vm=%vm_sp -VRINTR_dp ---- 1110 1.11 0110 .... 1011 01.0 .... \ - vd=%vd_dp vm=%vm_dp +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_sp ---- 1110 1.11 0110 .... 1010 11.0 .... \ - vd=%vd_sp vm=%vm_sp -VRINTZ_dp ---- 1110 1.11 0110 .... 1011 11.0 .... \ - vd=%vd_dp vm=%vm_dp +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_sp ---- 1110 1.11 0111 .... 1010 01.0 .... \ - vd=%vd_sp vm=%vm_sp -VRINTX_dp ---- 1110 1.11 0111 .... 1011 01.0 .... \ - vd=%vd_dp vm=%vm_dp +VRINTX_sp ---- 1110 1.11 0111 .... 1010 01.0 .... @vfp_dm_ss +VRINTX_dp ---- 1110 1.11 0111 .... 1011 01.0 .... @vfp_dm_dd -# VCVT between single and double: Vm precision depends on size; Vd is its reverse -VCVT_sp ---- 1110 1.11 0111 .... 1010 11.0 .... \ - vd=%vd_dp vm=%vm_sp -VCVT_dp ---- 1110 1.11 0111 .... 1011 11.0 .... \ - vd=%vd_sp vm=%vm_dp +# VCVT between single and double: +# Vm precision depends on size; Vd is its reverse +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_sp ---- 1110 1.11 1000 .... 1010 s:1 1.0 .... \ @@ -XXX,XX +XXX,XX @@ VCVT_int_dp ---- 1110 1.11 1000 .... 1011 s:1 1.0 .... \ vd=%vd_dp vm=%vm_sp # VJCVT is always dp to sp -VJCVT ---- 1110 1.11 1001 .... 1011 11.0 .... \ - vd=%vd_sp vm=%vm_dp +VJCVT ---- 1110 1.11 1001 .... 1011 11.0 .... @vfp_dm_sd # VCVT between floating-point and fixed-point. The immediate value # is in the same format as a Vm single-precision register number. -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Passing the raw o1 and o2 fields from the manual is less instructive than it might be. Do the full decode and let the trans_* functions pass in booleans to a helper. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200224222232.13807-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-vfp.inc.c | 52 ++++++++++++++++++++++++++++++---- target/arm/vfp.decode | 17 +++++------ 2 files changed, 55 insertions(+), 14 deletions(-) diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -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_VFM_sp(DisasContext *s, arg_VFM_sp *a) +static bool do_vfm_sp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) { /* * VFNMA : fd = muladd(-fd, fn, fm) @@ -XXX,XX +XXX,XX @@ static bool trans_VFM_sp(DisasContext *s, arg_VFM_sp *a) neon_load_reg32(vn, a->vn); neon_load_reg32(vm, a->vm); - if (a->o2) { + if (neg_n) { /* VFNMS, VFMS */ gen_helper_vfp_negs(vn, vn); } neon_load_reg32(vd, a->vd); - if (a->o1 & 1) { + if (neg_d) { /* VFNMA, VFNMS */ gen_helper_vfp_negs(vd, vd); } @@ -XXX,XX +XXX,XX @@ static bool trans_VFM_sp(DisasContext *s, arg_VFM_sp *a) return true; } -static bool trans_VFM_dp(DisasContext *s, arg_VFM_dp *a) +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) { /* * VFNMA : fd = muladd(-fd, fn, fm) @@ -XXX,XX +XXX,XX @@ static bool trans_VFM_dp(DisasContext *s, arg_VFM_dp *a) neon_load_reg64(vn, a->vn); neon_load_reg64(vm, a->vm); - if (a->o2) { + if (neg_n) { /* VFNMS, VFMS */ gen_helper_vfp_negd(vn, vn); } neon_load_reg64(vd, a->vd); - if (a->o1 & 1) { + if (neg_d) { /* VFNMA, VFNMS */ gen_helper_vfp_negd(vd, vd); } @@ -XXX,XX +XXX,XX @@ static bool trans_VFM_dp(DisasContext *s, arg_VFM_dp *a) return true; } +static bool trans_VFMA_dp(DisasContext *s, arg_VFMA_dp *a) +{ + return do_vfm_dp(s, a, false, false); +} + +static bool trans_VFMS_dp(DisasContext *s, arg_VFMS_dp *a) +{ + return do_vfm_dp(s, a, true, false); +} + +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); +} + static bool trans_VMOV_imm_sp(DisasContext *s, arg_VMOV_imm_sp *a) { uint32_t delta_d = 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 @@ VSUB_dp ---- 1110 0.11 .... .... 1011 .1.0 .... @vfp_dnm_d VDIV_sp ---- 1110 1.00 .... .... 1010 .0.0 .... @vfp_dnm_s VDIV_dp ---- 1110 1.00 .... .... 1011 .0.0 .... @vfp_dnm_d -VFM_sp ---- 1110 1.01 .... .... 1010 . o2:1 . 0 .... \ - vm=%vm_sp vn=%vn_sp vd=%vd_sp o1=1 -VFM_dp ---- 1110 1.01 .... .... 1011 . o2:1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp o1=1 -VFM_sp ---- 1110 1.10 .... .... 1010 . o2:1 . 0 .... \ - vm=%vm_sp vn=%vn_sp vd=%vd_sp o1=2 -VFM_dp ---- 1110 1.10 .... .... 1011 . o2:1 . 0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp o1=2 +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 +VFNMS_sp ---- 1110 1.01 .... .... 1010 .1. 0 .... @vfp_dnm_s + +VFMA_dp ---- 1110 1.10 .... .... 1011 .0.0 .... @vfp_dnm_d +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_sp ---- 1110 1.11 .... .... 1010 0000 .... \ vd=%vd_sp imm=%vmov_imm -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Passing the raw op field from the manual is less instructive than it might be. Do the full decode and use the existing helpers to perform the expansion. Since these are v8 insns, VECLEN+VECSTRIDE are already RES0. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200224222232.13807-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-vfp.inc.c | 109 +++++++++++---------------------- target/arm/vfp-uncond.decode | 12 ++-- 2 files changed, 44 insertions(+), 77 deletions(-) diff --git a/target/arm/translate-vfp.inc.c b/target/arm/translate-vfp.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.inc.c +++ b/target/arm/translate-vfp.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSEL(DisasContext *s, arg_VSEL *a) return true; } -static bool trans_VMINMAXNM(DisasContext *s, arg_VMINMAXNM *a) -{ - uint32_t rd, rn, rm; - bool dp = a->dp; - bool vmin = a->op; - TCGv_ptr fpst; - - if (!dc_isar_feature(aa32_vminmaxnm, s)) { - return false; - } - - if (dp && !dc_isar_feature(aa32_fpdp_v2, s)) { - return false; - } - - /* UNDEF accesses to D16-D31 if they don't exist */ - if (dp && !dc_isar_feature(aa32_simd_r32, s) && - ((a->vm | a->vn | a->vd) & 0x10)) { - return false; - } - - rd = a->vd; - rn = a->vn; - rm = a->vm; - - if (!vfp_access_check(s)) { - return true; - } - - fpst = get_fpstatus_ptr(0); - - if (dp) { - TCGv_i64 frn, frm, dest; - - frn = tcg_temp_new_i64(); - frm = tcg_temp_new_i64(); - dest = tcg_temp_new_i64(); - - neon_load_reg64(frn, rn); - neon_load_reg64(frm, rm); - if (vmin) { - gen_helper_vfp_minnumd(dest, frn, frm, fpst); - } else { - gen_helper_vfp_maxnumd(dest, frn, frm, fpst); - } - neon_store_reg64(dest, rd); - tcg_temp_free_i64(frn); - tcg_temp_free_i64(frm); - tcg_temp_free_i64(dest); - } else { - TCGv_i32 frn, frm, dest; - - frn = tcg_temp_new_i32(); - frm = tcg_temp_new_i32(); - dest = tcg_temp_new_i32(); - - neon_load_reg32(frn, rn); - neon_load_reg32(frm, rm); - if (vmin) { - gen_helper_vfp_minnums(dest, frn, frm, fpst); - } else { - gen_helper_vfp_maxnums(dest, frn, frm, fpst); - } - neon_store_reg32(dest, rd); - tcg_temp_free_i32(frn); - tcg_temp_free_i32(frm); - tcg_temp_free_i32(dest); - } - - tcg_temp_free_ptr(fpst); - return true; -} - /* * Table for converting the most common AArch32 encoding of * rounding mode to arm_fprounding order (which matches the @@ -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_sp(DisasContext *s, arg_VMINNM_sp *a) +{ + if (!dc_isar_feature(aa32_vminmaxnm, s)) { + return false; + } + return do_vfp_3op_sp(s, gen_helper_vfp_minnums, + a->vd, a->vn, a->vm, false); +} + +static bool trans_VMAXNM_sp(DisasContext *s, arg_VMAXNM_sp *a) +{ + if (!dc_isar_feature(aa32_vminmaxnm, s)) { + return false; + } + return do_vfp_3op_sp(s, gen_helper_vfp_maxnums, + a->vd, a->vn, a->vm, false); +} + +static bool trans_VMINNM_dp(DisasContext *s, arg_VMINNM_dp *a) +{ + if (!dc_isar_feature(aa32_vminmaxnm, s)) { + return false; + } + return do_vfp_3op_dp(s, gen_helper_vfp_minnumd, + a->vd, a->vn, a->vm, false); +} + +static bool trans_VMAXNM_dp(DisasContext *s, arg_VMAXNM_dp *a) +{ + if (!dc_isar_feature(aa32_vminmaxnm, s)) { + return false; + } + return do_vfp_3op_dp(s, gen_helper_vfp_maxnumd, + a->vd, a->vn, a->vm, false); +} + static bool do_vfm_sp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) { /* 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 @@ %vd_dp 22:1 12:4 %vd_sp 12:4 22:1 +@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 .... .... 1010 .0.0 .... \ vm=%vm_sp vn=%vn_sp vd=%vd_sp dp=0 VSEL 1111 1110 0. cc:2 .... .... 1011 .0.0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp dp=1 -VMINMAXNM 1111 1110 1.00 .... .... 1010 . op:1 .0 .... \ - vm=%vm_sp vn=%vn_sp vd=%vd_sp dp=0 -VMINMAXNM 1111 1110 1.00 .... .... 1011 . op:1 .0 .... \ - vm=%vm_dp vn=%vn_dp vd=%vd_dp dp=1 +VMAXNM_sp 1111 1110 1.00 .... .... 1010 .0.0 .... @vfp_dnm_s +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 .... 1010 01.0 .... \ vm=%vm_sp vd=%vd_sp dp=0 -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> USB ports on Xilinx Zync must be instantiated as TYPE_CHIPIDEA to work. Linux expects and checks various chipidea registers, which do not exist with the basic ehci emulation. This patch series fixes the problem. Without this patch, USB ports fail to instantiate under Linux. ci_hdrc ci_hdrc.0: doesn't support host ci_hdrc ci_hdrc.0: no supported roles With this patch, USB ports are instantiated, and it is possible to boot from USB drive. ci_hdrc ci_hdrc.0: EHCI Host Controller ci_hdrc ci_hdrc.0: new USB bus registered, assigned bus number 1 ci_hdrc ci_hdrc.0: USB 2.0 started, EHCI 1.00 usb 1-1: new full-speed USB device number 2 using ci_hdrc usb 1-1: not running at top speed; connect to a high speed hub usb 1-1: config 1 interface 0 altsetting 0 endpoint 0x81 has invalid maxpacket 512, setting to 64 usb 1-1: config 1 interface 0 altsetting 0 endpoint 0x2 has invalid maxpacket 512, setting to 64 usb-storage 1-1:1.0: USB Mass Storage device detected scsi host0: usb-storage 1-1:1.0 Signed-off-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Gerd Hoffmann <kraxel@redhat.com> Message-id: 20200215122354.13706-2-linux@roeck-us.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xilinx_zynq.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ #include "hw/loader.h" #include "hw/misc/zynq-xadc.h" #include "hw/ssi/ssi.h" +#include "hw/usb/chipidea.h" #include "qemu/error-report.h" #include "hw/sd/sdhci.h" #include "hw/char/cadence_uart.h" @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) zynq_init_spi_flashes(0xE0007000, pic[81-IRQ_OFFSET], false); zynq_init_spi_flashes(0xE000D000, pic[51-IRQ_OFFSET], true); - sysbus_create_simple("xlnx,ps7-usb", 0xE0002000, pic[53-IRQ_OFFSET]); - sysbus_create_simple("xlnx,ps7-usb", 0xE0003000, pic[76-IRQ_OFFSET]); + sysbus_create_simple(TYPE_CHIPIDEA, 0xE0002000, pic[53 - IRQ_OFFSET]); + sysbus_create_simple(TYPE_CHIPIDEA, 0xE0003000, pic[76 - IRQ_OFFSET]); cadence_uart_create(0xE0000000, pic[59 - IRQ_OFFSET], serial_hd(0)); cadence_uart_create(0xE0001000, pic[82 - IRQ_OFFSET], serial_hd(1)); -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> Xilinx USB devices are now instantiated through TYPE_CHIPIDEA, and xlnx support in the EHCI code is no longer needed. Signed-off-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Gerd Hoffmann <kraxel@redhat.com> Message-id: 20200215122354.13706-3-linux@roeck-us.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/usb/hcd-ehci-sysbus.c | 17 ----------------- 1 file changed, 17 deletions(-) diff --git a/hw/usb/hcd-ehci-sysbus.c b/hw/usb/hcd-ehci-sysbus.c index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/hcd-ehci-sysbus.c +++ b/hw/usb/hcd-ehci-sysbus.c @@ -XXX,XX +XXX,XX @@ static const TypeInfo ehci_platform_type_info = { .class_init = ehci_platform_class_init, }; -static void ehci_xlnx_class_init(ObjectClass *oc, void *data) -{ - SysBusEHCIClass *sec = SYS_BUS_EHCI_CLASS(oc); - DeviceClass *dc = DEVICE_CLASS(oc); - - set_bit(DEVICE_CATEGORY_USB, dc->categories); - sec->capsbase = 0x100; - sec->opregbase = 0x140; -} - -static const TypeInfo ehci_xlnx_type_info = { - .name = "xlnx,ps7-usb", - .parent = TYPE_SYS_BUS_EHCI, - .class_init = ehci_xlnx_class_init, -}; - static void ehci_exynos4210_class_init(ObjectClass *oc, void *data) { SysBusEHCIClass *sec = SYS_BUS_EHCI_CLASS(oc); @@ -XXX,XX +XXX,XX @@ static void ehci_sysbus_register_types(void) { type_register_static(&ehci_type_info); type_register_static(&ehci_platform_type_info); - type_register_static(&ehci_xlnx_type_info); type_register_static(&ehci_exynos4210_type_info); type_register_static(&ehci_tegra2_type_info); type_register_static(&ehci_ppc4xx_type_info); -- 2.20.1 From: Thomas Huth <thuth@redhat.com> Old kernels from the Meego project can be used to check that Linux is at least starting on these machines. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200225172501.29609-2-philmd@redhat.com Message-Id: <20200129131920.22302-1-thuth@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 1 + tests/acceptance/machine_arm_n8x0.py | 49 ++++++++++++++++++++++++++++ 2 files changed, 50 insertions(+) create mode 100644 tests/acceptance/machine_arm_n8x0.py diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/rtc/twl92230.c F: include/hw/display/blizzard.h F: include/hw/input/tsc2xxx.h F: include/hw/misc/cbus.h +F: tests/acceptance/machine_arm_n8x0.py Palm M: Andrzej Zaborowski <balrogg@gmail.com> diff --git a/tests/acceptance/machine_arm_n8x0.py b/tests/acceptance/machine_arm_n8x0.py new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/acceptance/machine_arm_n8x0.py @@ -XXX,XX +XXX,XX @@ +# Functional test that boots a Linux kernel and checks the console +# +# Copyright (c) 2020 Red Hat, Inc. +# +# Author: +# Thomas Huth <thuth@redhat.com> +# +# This work is licensed under the terms of the GNU GPL, version 2 or +# later. See the COPYING file in the top-level directory. + +import os + +from avocado import skipUnless +from avocado_qemu import Test +from avocado_qemu import wait_for_console_pattern + +class N8x0Machine(Test): + """Boots the Linux kernel and checks that the console is operational""" + + timeout = 90 + + def __do_test_n8x0(self): + kernel_url = ('http://stskeeps.subnetmask.net/meego-n8x0/' + 'meego-arm-n8x0-1.0.80.20100712.1431-' + 'vmlinuz-2.6.35~rc4-129.1-n8x0') + kernel_hash = 'e9d5ab8d7548923a0061b6fbf601465e479ed269' + kernel_path = self.fetch_asset(kernel_url, asset_hash=kernel_hash) + + self.vm.set_console(console_index=1) + self.vm.add_args('-kernel', kernel_path, + '-append', 'printk.time=0 console=ttyS1') + self.vm.launch() + wait_for_console_pattern(self, 'TSC2005 driver initializing') + + @skipUnless(os.getenv('AVOCADO_ALLOW_UNTRUSTED_CODE'), 'untrusted code') + def test_n800(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:n800 + """ + self.__do_test_n8x0() + + @skipUnless(os.getenv('AVOCADO_ALLOW_UNTRUSTED_CODE'), 'untrusted code') + def test_n810(self): + """ + :avocado: tags=arch:arm + :avocado: tags=machine:n810 + """ + self.__do_test_n8x0() -- 2.20.1 From: Thomas Huth <thuth@redhat.com> There is a kernel and initrd available on github which we can use for testing this machine. Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Tested-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200225172501.29609-3-philmd@redhat.com Message-Id: <20200131170233.14584-1-thuth@redhat.com> [PMD: Renamed test method, moved description from class to method] Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 1 + tests/acceptance/machine_arm_integratorcp.py | 43 ++++++++++++++++++++ 2 files changed, 44 insertions(+) create mode 100644 tests/acceptance/machine_arm_integratorcp.py diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ S: Maintained F: hw/arm/integratorcp.c F: hw/misc/arm_integrator_debug.c F: include/hw/misc/arm_integrator_debug.h +F: tests/acceptance/machine_arm_integratorcp.py MCIMX6UL EVK / i.MX6ul M: Peter Maydell <peter.maydell@linaro.org> diff --git a/tests/acceptance/machine_arm_integratorcp.py b/tests/acceptance/machine_arm_integratorcp.py new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/acceptance/machine_arm_integratorcp.py @@ -XXX,XX +XXX,XX @@ +# Functional test that boots a Linux kernel and checks the console +# +# Copyright (c) 2020 Red Hat, Inc. +# +# Author: +# Thomas Huth <thuth@redhat.com> +# +# This work is licensed under the terms of the GNU GPL, version 2 or +# later. See the COPYING file in the top-level directory. + +import os + +from avocado import skipUnless +from avocado_qemu import Test +from avocado_qemu import wait_for_console_pattern + +class IntegratorMachine(Test): + + timeout = 90 + + @skipUnless(os.getenv('AVOCADO_ALLOW_UNTRUSTED_CODE'), 'untrusted code') + def test_integratorcp_console(self): + """ + Boots the Linux kernel and checks that the console is operational + :avocado: tags=arch:arm + :avocado: tags=machine:integratorcp + """ + kernel_url = ('https://github.com/zayac/qemu-arm/raw/master/' + 'arm-test/kernel/zImage.integrator') + kernel_hash = '0d7adba893c503267c946a3cbdc63b4b54f25468' + kernel_path = self.fetch_asset(kernel_url, asset_hash=kernel_hash) + + initrd_url = ('https://github.com/zayac/qemu-arm/raw/master/' + 'arm-test/kernel/arm_root.img') + initrd_hash = 'b51e4154285bf784e017a37586428332d8c7bd8b' + initrd_path = self.fetch_asset(initrd_url, asset_hash=initrd_hash) + + self.vm.set_console() + self.vm.add_args('-kernel', kernel_path, + '-initrd', initrd_path, + '-append', 'printk.time=0 console=ttyAMA0') + self.vm.launch() + wait_for_console_pattern(self, 'Log in as root') -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> As we want to re-use this code, extract it as a new function. Since we are using the PL011 serial console, add a Avocado tag to ease filtering of tests. Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200225172501.29609-4-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/machine_arm_integratorcp.py | 18 +++++++++++------- 1 file changed, 11 insertions(+), 7 deletions(-) diff --git a/tests/acceptance/machine_arm_integratorcp.py b/tests/acceptance/machine_arm_integratorcp.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/machine_arm_integratorcp.py +++ b/tests/acceptance/machine_arm_integratorcp.py @@ -XXX,XX +XXX,XX @@ class IntegratorMachine(Test): timeout = 90 - @skipUnless(os.getenv('AVOCADO_ALLOW_UNTRUSTED_CODE'), 'untrusted code') - def test_integratorcp_console(self): - """ - Boots the Linux kernel and checks that the console is operational - :avocado: tags=arch:arm - :avocado: tags=machine:integratorcp - """ + def boot_integratorcp(self): kernel_url = ('https://github.com/zayac/qemu-arm/raw/master/' 'arm-test/kernel/zImage.integrator') kernel_hash = '0d7adba893c503267c946a3cbdc63b4b54f25468' @@ -XXX,XX +XXX,XX @@ class IntegratorMachine(Test): '-initrd', initrd_path, '-append', 'printk.time=0 console=ttyAMA0') self.vm.launch() + + @skipUnless(os.getenv('AVOCADO_ALLOW_UNTRUSTED_CODE'), 'untrusted code') + def test_integratorcp_console(self): + """ + Boots the Linux kernel and checks that the console is operational + :avocado: tags=arch:arm + :avocado: tags=machine:integratorcp + :avocado: tags=device:pl011 + """ + self.boot_integratorcp() wait_for_console_pattern(self, 'Log in as root') -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Add a test that verifies the Tux logo is displayed on the framebuffer. We simply follow the OpenCV "Template Matching with Multiple Objects" tutorial, replacing Lionel Messi by Tux: https://docs.opencv.org/4.2.0/d4/dc6/tutorial_py_template_matching.html When OpenCV and NumPy are installed, this test can be run using: $ AVOCADO_ALLOW_UNTRUSTED_CODE=hmmm \ avocado --show=app,framebuffer run -t device:framebuffer \ tests/acceptance/machine_arm_integratorcp.py JOB ID : 8c46b0f8269242e87d738247883ea2a470df949e JOB LOG : avocado/job-results/job-2020-01-31T21.38-8c46b0f/job.log (1/1) tests/acceptance/machine_arm_integratorcp.py:IntegratorMachine.test_framebuffer_tux_logo: framebuffer: found Tux at position [x, y] = (0, 0) PASS (3.96 s) RESULTS : PASS 1 | ERROR 0 | FAIL 0 | SKIP 0 | WARN 0 | INTERRUPT 0 | CANCEL 0 JOB TIME : 4.23 s Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Wainer dos Santos Moschetta <wainersm@redhat.com> Message-id: 20200225172501.29609-5-philmd@redhat.com Message-Id: <20200131211102.29612-3-f4bug@amsat.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/acceptance/machine_arm_integratorcp.py | 52 ++++++++++++++++++++ 1 file changed, 52 insertions(+) diff --git a/tests/acceptance/machine_arm_integratorcp.py b/tests/acceptance/machine_arm_integratorcp.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/machine_arm_integratorcp.py +++ b/tests/acceptance/machine_arm_integratorcp.py @@ -XXX,XX +XXX,XX @@ # later. See the COPYING file in the top-level directory. import os +import logging from avocado import skipUnless from avocado_qemu import Test from avocado_qemu import wait_for_console_pattern + +NUMPY_AVAILABLE = True +try: + import numpy as np +except ImportError: + NUMPY_AVAILABLE = False + +CV2_AVAILABLE = True +try: + import cv2 +except ImportError: + CV2_AVAILABLE = False + + class IntegratorMachine(Test): timeout = 90 @@ -XXX,XX +XXX,XX @@ class IntegratorMachine(Test): """ self.boot_integratorcp() wait_for_console_pattern(self, 'Log in as root') + + @skipUnless(NUMPY_AVAILABLE, 'Python NumPy not installed') + @skipUnless(CV2_AVAILABLE, 'Python OpenCV not installed') + @skipUnless(os.getenv('AVOCADO_ALLOW_UNTRUSTED_CODE'), 'untrusted code') + def test_framebuffer_tux_logo(self): + """ + Boot Linux and verify the Tux logo is displayed on the framebuffer. + :avocado: tags=arch:arm + :avocado: tags=machine:integratorcp + :avocado: tags=device:pl110 + :avocado: tags=device:framebuffer + """ + screendump_path = os.path.join(self.workdir, "screendump.pbm") + tuxlogo_url = ('https://github.com/torvalds/linux/raw/v2.6.12/' + 'drivers/video/logo/logo_linux_vga16.ppm') + tuxlogo_hash = '3991c2ddbd1ddaecda7601f8aafbcf5b02dc86af' + tuxlogo_path = self.fetch_asset(tuxlogo_url, asset_hash=tuxlogo_hash) + + self.boot_integratorcp() + framebuffer_ready = 'Console: switching to colour frame buffer device' + wait_for_console_pattern(self, framebuffer_ready) + self.vm.command('human-monitor-command', command_line='stop') + self.vm.command('human-monitor-command', + command_line='screendump %s' % screendump_path) + logger = logging.getLogger('framebuffer') + + cpu_count = 1 + match_threshold = 0.92 + screendump_bgr = cv2.imread(screendump_path) + screendump_gray = cv2.cvtColor(screendump_bgr, cv2.COLOR_BGR2GRAY) + result = cv2.matchTemplate(screendump_gray, cv2.imread(tuxlogo_path, 0), + cv2.TM_CCOEFF_NORMED) + loc = np.where(result >= match_threshold) + tux_count = 0 + for tux_count, pt in enumerate(zip(*loc[::-1]), start=1): + logger.debug('found Tux at position [x, y] = %s', pt) + self.assertGreaterEqual(tux_count, cpu_count) -- 2.20.1 We missed an instance of using FIELD_EX32 on a 64-bit ID register, in isar_feature_aa64_pmu_8_4(). Fix it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200224172846.13053-2-peter.maydell@linaro.org --- target/arm/cpu.h | 4 ++-- 1 file changed, 2 insertions(+), 2 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_aa64_pmu_8_1(const ARMISARegisters *id) static inline bool isar_feature_aa64_pmu_8_4(const ARMISARegisters *id) { - return FIELD_EX32(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 5 && - FIELD_EX32(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; + return FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) >= 5 && + FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; } /* -- 2.20.1 The v8.3-RCPC extension implements three new load instructions which provide slightly weaker consistency guarantees than the existing load-acquire operations. For QEMU we choose to simply implement them with a full LDAQ barrier. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200224172846.13053-3-peter.maydell@linaro.org --- target/arm/cpu.h | 5 +++++ linux-user/elfload.c | 1 + target/arm/cpu64.c | 1 + target/arm/translate-a64.c | 24 ++++++++++++++++++++++++ 4 files changed, 31 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_pmu_8_4(const ARMISARegisters *id) FIELD_EX64(id->id_aa64dfr0, ID_AA64DFR0, PMUVER) != 0xf; } +static inline bool isar_feature_aa64_rcpc_8_3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) != 0; +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) GET_FEATURE_ID(aa64_sb, ARM_HWCAP_A64_SB); GET_FEATURE_ID(aa64_condm_4, ARM_HWCAP_A64_FLAGM); GET_FEATURE_ID(aa64_dcpop, ARM_HWCAP_A64_DCPOP); + GET_FEATURE_ID(aa64_rcpc_8_3, ARM_HWCAP_A64_LRCPC); return hwcaps; } diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64ISAR1, SB, 1); t = FIELD_DP64(t, ID_AA64ISAR1, SPECRES, 1); t = FIELD_DP64(t, ID_AA64ISAR1, FRINTTS, 1); + t = FIELD_DP64(t, ID_AA64ISAR1, LRCPC, 1); /* ARMv8.3-RCPC */ cpu->isar.id_aa64isar1 = t; t = cpu->isar.id_aa64pfr0; 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_ldst_atomic(DisasContext *s, uint32_t insn, int rs = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int o3_opc = extract32(insn, 12, 4); + bool r = extract32(insn, 22, 1); + bool a = extract32(insn, 23, 1); TCGv_i64 tcg_rs, clean_addr; AtomicThreeOpFn *fn; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, case 010: /* SWP */ fn = tcg_gen_atomic_xchg_i64; break; + case 014: /* LDAPR, LDAPRH, LDAPRB */ + if (!dc_isar_feature(aa64_rcpc_8_3, s) || + rs != 31 || a != 1 || r != 0) { + unallocated_encoding(s); + return; + } + break; default: unallocated_encoding(s); return; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, gen_check_sp_alignment(s); } clean_addr = clean_data_tbi(s, cpu_reg_sp(s, rn)); + + if (o3_opc == 014) { + /* + * LDAPR* are a special case because they are a simple load, not a + * fetch-and-do-something op. + * The architectural consistency requirements here are weaker than + * full load-acquire (we only need "load-acquire processor consistent"), + * but we choose to implement them as full LDAQ. + */ + do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size, false, false, + true, rt, disas_ldst_compute_iss_sf(size, false, 0), true); + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); + return; + } + tcg_rs = read_cpu_reg(s, rs, true); if (o3_opc == 1) { /* LDCLR */ -- 2.20.1 The v8.4-RCPC extension implements some new instructions: * LDAPUR, LDAPURB, LDAPURH, LDAPRSB, LDAPRSH, LDAPRSW * STLUR, STLURB, STLURH These are all in a new subgroup of encodings that sits below the top-level "Loads and Stores" group in the Arm ARM. The STLUR* instructions have standard store-release semantics; the LDAPUR* have Load-AcquirePC semantics, but (as with LDAPR*) we choose to implement them as the slightly stronger Load-Acquire. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200224172846.13053-4-peter.maydell@linaro.org --- target/arm/cpu.h | 5 +++ linux-user/elfload.c | 1 + target/arm/cpu64.c | 2 +- target/arm/translate-a64.c | 90 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 97 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_rcpc_8_3(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) != 0; } +static inline bool isar_feature_aa64_rcpc_8_4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) >= 2; +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) GET_FEATURE_ID(aa64_condm_4, ARM_HWCAP_A64_FLAGM); GET_FEATURE_ID(aa64_dcpop, ARM_HWCAP_A64_DCPOP); GET_FEATURE_ID(aa64_rcpc_8_3, ARM_HWCAP_A64_LRCPC); + GET_FEATURE_ID(aa64_rcpc_8_4, ARM_HWCAP_A64_ILRCPC); return hwcaps; } diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64ISAR1, SB, 1); t = FIELD_DP64(t, ID_AA64ISAR1, SPECRES, 1); t = FIELD_DP64(t, ID_AA64ISAR1, FRINTTS, 1); - t = FIELD_DP64(t, ID_AA64ISAR1, LRCPC, 1); /* ARMv8.3-RCPC */ + t = FIELD_DP64(t, ID_AA64ISAR1, LRCPC, 2); /* ARMv8.4-RCPC */ cpu->isar.id_aa64isar1 = t; t = cpu->isar.id_aa64pfr0; 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_ldst_pac(DisasContext *s, uint32_t insn, } } +/* + * LDAPR/STLR (unscaled immediate) + * + * 31 30 24 22 21 12 10 5 0 + * +------+-------------+-----+---+--------+-----+----+-----+ + * | size | 0 1 1 0 0 1 | opc | 0 | imm9 | 0 0 | Rn | Rt | + * +------+-------------+-----+---+--------+-----+----+-----+ + * + * Rt: source or destination register + * Rn: base register + * imm9: unscaled immediate offset + * opc: 00: STLUR*, 01/10/11: various LDAPUR* + * size: size of load/store + */ +static void disas_ldst_ldapr_stlr(DisasContext *s, uint32_t insn) +{ + int rt = extract32(insn, 0, 5); + int rn = extract32(insn, 5, 5); + int offset = sextract32(insn, 12, 9); + int opc = extract32(insn, 22, 2); + int size = extract32(insn, 30, 2); + TCGv_i64 clean_addr, dirty_addr; + bool is_store = false; + bool is_signed = false; + bool extend = false; + bool iss_sf; + + if (!dc_isar_feature(aa64_rcpc_8_4, s)) { + unallocated_encoding(s); + return; + } + + switch (opc) { + case 0: /* STLURB */ + is_store = true; + break; + case 1: /* LDAPUR* */ + break; + case 2: /* LDAPURS* 64-bit variant */ + if (size == 3) { + unallocated_encoding(s); + return; + } + is_signed = true; + break; + case 3: /* LDAPURS* 32-bit variant */ + if (size > 1) { + unallocated_encoding(s); + return; + } + is_signed = true; + extend = true; /* zero-extend 32->64 after signed load */ + break; + default: + g_assert_not_reached(); + } + + iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc); + + if (rn == 31) { + gen_check_sp_alignment(s); + } + + dirty_addr = read_cpu_reg_sp(s, rn, 1); + tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); + clean_addr = clean_data_tbi(s, dirty_addr); + + if (is_store) { + /* Store-Release semantics */ + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); + do_gpr_st(s, cpu_reg(s, rt), clean_addr, size, true, rt, iss_sf, true); + } else { + /* + * Load-AcquirePC semantics; we implement as the slightly more + * restrictive Load-Acquire. + */ + do_gpr_ld(s, cpu_reg(s, rt), clean_addr, size, is_signed, extend, + true, rt, iss_sf, true); + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); + } +} + /* Load/store register (all forms) */ static void disas_ldst_reg(DisasContext *s, uint32_t insn) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst(DisasContext *s, uint32_t insn) case 0x0d: /* AdvSIMD load/store single structure */ disas_ldst_single_struct(s, insn); break; + case 0x19: /* LDAPR/STLR (unscaled immediate) */ + if (extract32(insn, 10, 2) != 0 || + extract32(insn, 21, 1) != 0) { + unallocated_encoding(s); + break; + } + disas_ldst_ldapr_stlr(s, insn); + break; default: unallocated_encoding(s); break; -- 2.20.1 The ARMv8.3-CCIDX extension makes the CCSIDR_EL1 system ID registers have a format that uses the full 64 bit width of the register, and adds a new CCSIDR2 register so AArch32 can get at the high 32 bits. QEMU doesn't implement caches, so we just treat these ID registers as opaque values that are set to the correct constant values for each CPU. The only thing we need to do is allow 64-bit values in our cssidr[] array and provide the CCSIDR2 accessors. We don't set the CCIDX field in our 'max' CPU because the CCSIDR constant values we use are the same as the ones used by the Cortex-A57 and they are in the old 32-bit format. This means that the extra regdef added here is unused currently, but it means that whenever in the future we add a CPU that does need the new 64-bit format it will just work when we set the cssidr values and the ID registers for it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20200224182626.29252-1-peter.maydell@linaro.org --- target/arm/cpu.h | 17 ++++++++++++++++- target/arm/helper.c | 19 +++++++++++++++++++ 2 files changed, 35 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 @@ struct ARMCPU { /* The elements of this array are the CCSIDR values for each cache, * in the order L1DCache, L1ICache, L2DCache, L2ICache, etc. */ - uint32_t ccsidr[16]; + uint64_t ccsidr[16]; uint64_t reset_cbar; uint32_t reset_auxcr; bool reset_hivecs; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_ac2(const ARMISARegisters *id) return FIELD_EX32(id->id_mmfr4, ID_MMFR4, AC2) != 0; } +static inline bool isar_feature_aa32_ccidx(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_mmfr4, ID_MMFR4, CCIDX) != 0; +} + /* * 64-bit feature tests via id registers. */ @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_rcpc_8_4(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, LRCPC) >= 2; } +static inline bool isar_feature_aa64_ccidx(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64mmfr2, ID_AA64MMFR2, CCIDX) != 0; +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_any_pmu_8_4(const ARMISARegisters *id) return isar_feature_aa64_pmu_8_4(id) || isar_feature_aa32_pmu_8_4(id); } +static inline bool isar_feature_any_ccidx(const ARMISARegisters *id) +{ + return isar_feature_aa64_ccidx(id) || isar_feature_aa32_ccidx(id); +} + /* * Forward to the above feature tests given an ARMCPU pointer. */ 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 predinv_reginfo[] = { REGINFO_SENTINEL }; +static uint64_t ccsidr2_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + /* Read the high 32 bits of the current CCSIDR */ + return extract64(ccsidr_read(env, ri), 32, 32); +} + +static const ARMCPRegInfo ccsidr2_reginfo[] = { + { .name = "CCSIDR2", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 1, .crn = 0, .crm = 0, .opc2 = 2, + .access = PL1_R, + .accessfn = access_aa64_tid2, + .readfn = ccsidr2_read, .type = ARM_CP_NO_RAW }, + REGINFO_SENTINEL +}; + static CPAccessResult access_aa64_tid3(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) define_arm_cp_regs(cpu, predinv_reginfo); } + if (cpu_isar_feature(any_ccidx, cpu)) { + define_arm_cp_regs(cpu, ccsidr2_reginfo); + } + #ifndef CONFIG_USER_ONLY /* * Register redirections and aliases must be done last, -- 2.20.1 In our KVM GICv2 realize function, we try to cope with old kernels that don't provide the device control API (KVM_CAP_DEVICE_CTRL): we try to use the device control, and if that fails we fall back to assuming that the kernel has the old style KVM_CREATE_IRQCHIP and that it will provide a GICv2. This doesn't cater for the possibility of a kernel and hardware which only provide a GICv3, which is very common now. On that setup we will abort() later on in kvm_arm_pmu_set_irq() when we try to wire up an interrupt to the GIC we failed to create: qemu-system-aarch64: PMU: KVM_SET_DEVICE_ATTR: Invalid argument qemu-system-aarch64: failed to set irq for PMU Aborted If the kernel advertises KVM_CAP_DEVICE_CTRL we should trust it if it says it can't create a GICv2, rather than assuming it has one. We can then produce a more helpful error message including a hint about the most probable reason for the failure. If the kernel doesn't advertise KVM_CAP_DEVICE_CTRL then it is truly ancient by this point but we might as well still fall back to a KVM_CREATE_IRQCHIP GICv2. With this patch then the user misconfiguration which previously caused an abort now prints: qemu-system-aarch64: Initialization of device kvm-arm-gic failed: error creating in-kernel VGIC: No such device Perhaps the host CPU does not support GICv2? Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Tested-by: Andrew Jones <drjones@redhat.com> Message-id: 20200225182435.1131-1-peter.maydell@linaro.org --- hw/intc/arm_gic_kvm.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/hw/intc/arm_gic_kvm.c b/hw/intc/arm_gic_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gic_kvm.c +++ b/hw/intc/arm_gic_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gic_realize(DeviceState *dev, Error **errp) KVM_DEV_ARM_VGIC_CTRL_INIT, NULL, true, &error_abort); } + } else if (kvm_check_extension(kvm_state, KVM_CAP_DEVICE_CTRL)) { + error_setg_errno(errp, -ret, "error creating in-kernel VGIC"); + error_append_hint(errp, + "Perhaps the host CPU does not support GICv2?\n"); } else if (ret != -ENODEV && ret != -ENOTSUP) { + /* + * Very ancient kernel without KVM_CAP_DEVICE_CTRL: assume that + * ENODEV or ENOTSUP mean "can't create GICv2 with KVM_CREATE_DEVICE", + * and that we will get a GICv2 via KVM_CREATE_IRQCHIP. + */ error_setg_errno(errp, -ret, "error creating in-kernel VGIC"); return; } -- 2.20.1