The following changes since commit ad1b4ec39caa5b3f17cbd8160283a03a3dcfe2ae: Merge remote-tracking branch 'remotes/kraxel/tags/input-20180515-pull-request' into staging (2018-05-15 12:50:06 +0100) are available in the Git repository at: git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20180515 for you to fetch changes up to ae7651804748c6b479d5ae09aeac4edb9c44f76e: tcg: Optionally log FPU state in TCG -d cpu logging (2018-05-15 14:58:44 +0100) ---------------------------------------------------------------- target-arm queue: * Fix coverity nit in int_to_float code * Don't set Invalid for float-to-int(MAXINT) * Fix fp_status_f16 tininess before rounding * Add various missing insns from the v8.2-FP16 extension * Fix sqrt_f16 exception raising * sdcard: Correct CRC16 offset in sd_function_switch() * tcg: Optionally log FPU state in TCG -d cpu logging ---------------------------------------------------------------- Alex Bennée (5): fpu/softfloat: int_to_float ensure r fully initialised target/arm: Implement FCMP for fp16 target/arm: Implement FCSEL for fp16 target/arm: Implement FMOV (immediate) for fp16 target/arm: Fix sqrt_f16 exception raising Peter Maydell (3): fpu/softfloat: Don't set Invalid for float-to-int(MAXINT) target/arm: Fix fp_status_f16 tininess before rounding tcg: Optionally log FPU state in TCG -d cpu logging Philippe Mathieu-Daudé (1): sdcard: Correct CRC16 offset in sd_function_switch() Richard Henderson (7): target/arm: Implement FMOV (general) for fp16 target/arm: Early exit after unallocated_encoding in disas_fp_int_conv target/arm: Implement FCVT (scalar, integer) for fp16 target/arm: Implement FCVT (scalar, fixed-point) for fp16 target/arm: Introduce and use read_fp_hreg target/arm: Implement FP data-processing (2 source) for fp16 target/arm: Implement FP data-processing (3 source) for fp16 include/qemu/log.h | 1 + target/arm/helper-a64.h | 2 + target/arm/helper.h | 6 + accel/tcg/cpu-exec.c | 9 +- fpu/softfloat.c | 6 +- hw/sd/sd.c | 2 +- target/arm/cpu.c | 2 + target/arm/helper-a64.c | 10 ++ target/arm/helper.c | 38 +++- target/arm/translate-a64.c | 421 ++++++++++++++++++++++++++++++++++++++------- util/log.c | 2 + 11 files changed, 428 insertions(+), 71 deletions(-) From: Alex Bennée <alex.bennee@linaro.org> Reported by Coverity (CID1390635). We ensure this for uint_to_float later on so we might as well mirror that. Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fpu/softfloat.c b/fpu/softfloat.c index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -XXX,XX +XXX,XX @@ FLOAT_TO_UINT(64, 64) static FloatParts int_to_float(int64_t a, float_status *status) { - FloatParts r; + FloatParts r = {}; if (a == 0) { r.cls = float_class_zero; r.sign = false; -- 2.17.0 In float-to-integer conversion, if the floating point input converts exactly to the largest or smallest integer that fits in to the result type, this is not an overflow. In this situation we were producing the correct result value, but were incorrectly setting the Invalid flag. For example for Arm A64, "FCVTAS w0, d0" on an input of 0x41dfffffffc00000 should produce 0x7fffffff and set no flags. Fix the boundary case to take the right half of the if() statements. This fixes a regression from 2.11 introduced by the softfloat refactoring. Cc: qemu-stable@nongnu.org Fixes: ab52f973a50 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180510140141.12120-1-peter.maydell@linaro.org --- fpu/softfloat.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fpu/softfloat.c b/fpu/softfloat.c index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -XXX,XX +XXX,XX @@ static int64_t round_to_int_and_pack(FloatParts in, int rmode, r = UINT64_MAX; } if (p.sign) { - if (r < -(uint64_t) min) { + if (r <= -(uint64_t) min) { return -r; } else { s->float_exception_flags = orig_flags | float_flag_invalid; return min; } } else { - if (r < max) { + if (r <= max) { return r; } else { s->float_exception_flags = orig_flags | float_flag_invalid; -- 2.17.0 In commit d81ce0ef2c4f105 we added an extra float_status field fp_status_fp16 for Arm, but forgot to initialize it correctly by setting it to float_tininess_before_rounding. This currently will only cause problems for the new V8_FP16 feature, since the float-to-float conversion code doesn't use it yet. The effect would be that we failed to set the Underflow IEEE exception flag in all the cases where we should. Add the missing initialization. Fixes: d81ce0ef2c4f105 Cc: qemu-stable@nongnu.org Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20180512004311.9299-16-richard.henderson@linaro.org --- target/arm/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(CPUState *s) &env->vfp.fp_status); set_float_detect_tininess(float_tininess_before_rounding, &env->vfp.standard_fp_status); + set_float_detect_tininess(float_tininess_before_rounding, + &env->vfp.fp_status_f16); #ifndef CONFIG_USER_ONLY if (kvm_enabled()) { kvm_arm_reset_vcpu(cpu); -- 2.17.0 From: Richard Henderson <richard.henderson@linaro.org> Adding the fp16 moves to/from general registers. Cc: qemu-stable@nongnu.org Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180512003217.9105-2-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 | 21 +++++++++++++++++++++ 1 file changed, 21 insertions(+) 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) tcg_gen_st_i64(tcg_rn, cpu_env, fp_reg_hi_offset(s, rd)); clear_vec_high(s, true, rd); break; + case 3: + /* 16 bit */ + tmp = tcg_temp_new_i64(); + tcg_gen_ext16u_i64(tmp, tcg_rn); + write_fp_dreg(s, rd, tmp); + tcg_temp_free_i64(tmp); + break; + default: + g_assert_not_reached(); } } else { TCGv_i64 tcg_rd = cpu_reg(s, rd); @@ -XXX,XX +XXX,XX @@ static void handle_fmov(DisasContext *s, int rd, int rn, int type, bool itof) /* 64 bits from top half */ tcg_gen_ld_i64(tcg_rd, cpu_env, fp_reg_hi_offset(s, rn)); break; + case 3: + /* 16 bit */ + tcg_gen_ld16u_i64(tcg_rd, cpu_env, fp_reg_offset(s, rn, MO_16)); + break; + default: + g_assert_not_reached(); } } } @@ -XXX,XX +XXX,XX @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) 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 (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + break; + } + /* fallthru */ default: /* all other sf/type/rmode combinations are invalid */ unallocated_encoding(s); -- 2.17.0 From: Richard Henderson <richard.henderson@linaro.org> No sense in emitting code after the exception. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180512003217.9105-3-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 | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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) default: /* all other sf/type/rmode combinations are invalid */ unallocated_encoding(s); - break; + return; } if (!fp_access_check(s)) { -- 2.17.0 From: Richard Henderson <richard.henderson@linaro.org> Cc: qemu-stable@nongnu.org Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180512003217.9105-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 6 +++ target/arm/helper.c | 38 ++++++++++++++- target/arm/translate-a64.c | 96 +++++++++++++++++++++++++++++++------- 3 files changed, 122 insertions(+), 18 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_touhd_round_to_zero, i64, f64, i32, ptr) DEF_HELPER_3(vfp_tould_round_to_zero, i64, f64, i32, ptr) DEF_HELPER_3(vfp_touhh, i32, f16, i32, ptr) DEF_HELPER_3(vfp_toshh, i32, f16, i32, ptr) +DEF_HELPER_3(vfp_toulh, i32, f16, i32, ptr) +DEF_HELPER_3(vfp_toslh, i32, f16, i32, ptr) +DEF_HELPER_3(vfp_touqh, i64, f16, i32, ptr) +DEF_HELPER_3(vfp_tosqh, i64, f16, i32, ptr) DEF_HELPER_3(vfp_toshs, i32, f32, i32, ptr) DEF_HELPER_3(vfp_tosls, i32, f32, i32, ptr) DEF_HELPER_3(vfp_tosqs, i64, f32, i32, ptr) @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_ultod, f64, i64, i32, ptr) DEF_HELPER_3(vfp_uqtod, f64, i64, i32, ptr) DEF_HELPER_3(vfp_sltoh, f16, i32, i32, ptr) DEF_HELPER_3(vfp_ultoh, f16, i32, i32, ptr) +DEF_HELPER_3(vfp_sqtoh, f16, i64, i32, ptr) +DEF_HELPER_3(vfp_uqtoh, f16, i64, i32, ptr) DEF_HELPER_FLAGS_2(set_rmode, TCG_CALL_NO_RWG, i32, i32, ptr) DEF_HELPER_FLAGS_2(set_neon_rmode, TCG_CALL_NO_RWG, i32, i32, env) 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 @@ VFP_CONV_FIX_A64(uq, s, 32, 64, uint64) #undef VFP_CONV_FIX_A64 /* Conversion to/from f16 can overflow to infinity before/after scaling. - * Therefore we convert to f64 (which does not round), scale, - * and then convert f64 to f16 (which may round). + * Therefore we convert to f64, scale, and then convert f64 to f16; or + * vice versa for conversion to integer. + * + * For 16- and 32-bit integers, the conversion to f64 never rounds. + * For 64-bit integers, any integer that would cause rounding will also + * overflow to f16 infinity, so there is no double rounding problem. */ static float16 do_postscale_fp16(float64 f, int shift, float_status *fpst) @@ -XXX,XX +XXX,XX @@ float16 HELPER(vfp_ultoh)(uint32_t x, uint32_t shift, void *fpst) return do_postscale_fp16(uint32_to_float64(x, fpst), shift, fpst); } +float16 HELPER(vfp_sqtoh)(uint64_t x, uint32_t shift, void *fpst) +{ + return do_postscale_fp16(int64_to_float64(x, fpst), shift, fpst); +} + +float16 HELPER(vfp_uqtoh)(uint64_t x, uint32_t shift, void *fpst) +{ + return do_postscale_fp16(uint64_to_float64(x, fpst), shift, fpst); +} + static float64 do_prescale_fp16(float16 f, int shift, float_status *fpst) { if (unlikely(float16_is_any_nan(f))) { @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(vfp_touhh)(float16 x, uint32_t shift, void *fpst) return float64_to_uint16(do_prescale_fp16(x, shift, fpst), fpst); } +uint32_t HELPER(vfp_toslh)(float16 x, uint32_t shift, void *fpst) +{ + return float64_to_int32(do_prescale_fp16(x, shift, fpst), fpst); +} + +uint32_t HELPER(vfp_toulh)(float16 x, uint32_t shift, void *fpst) +{ + return float64_to_uint32(do_prescale_fp16(x, shift, fpst), fpst); +} + +uint64_t HELPER(vfp_tosqh)(float16 x, uint32_t shift, void *fpst) +{ + return float64_to_int64(do_prescale_fp16(x, shift, fpst), fpst); +} + +uint64_t HELPER(vfp_touqh)(float16 x, uint32_t shift, void *fpst) +{ + return float64_to_uint64(do_prescale_fp16(x, shift, fpst), fpst); +} + /* Set the current fp rounding mode and return the old one. * The argument is a softfloat float_round_ value. */ 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_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, bool itof, int rmode, int scale, int sf, int type) { bool is_signed = !(opcode & 1); - bool is_double = type; TCGv_ptr tcg_fpstatus; - TCGv_i32 tcg_shift; + TCGv_i32 tcg_shift, tcg_single; + TCGv_i64 tcg_double; - tcg_fpstatus = get_fpstatus_ptr(false); + tcg_fpstatus = get_fpstatus_ptr(type == 3); tcg_shift = tcg_const_i32(64 - scale); @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, tcg_int = tcg_extend; } - if (is_double) { - TCGv_i64 tcg_double = tcg_temp_new_i64(); + switch (type) { + case 1: /* float64 */ + tcg_double = tcg_temp_new_i64(); if (is_signed) { gen_helper_vfp_sqtod(tcg_double, tcg_int, tcg_shift, tcg_fpstatus); @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, } write_fp_dreg(s, rd, tcg_double); tcg_temp_free_i64(tcg_double); - } else { - TCGv_i32 tcg_single = tcg_temp_new_i32(); + break; + + case 0: /* float32 */ + tcg_single = tcg_temp_new_i32(); if (is_signed) { gen_helper_vfp_sqtos(tcg_single, tcg_int, tcg_shift, tcg_fpstatus); @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, } write_fp_sreg(s, rd, tcg_single); tcg_temp_free_i32(tcg_single); + break; + + case 3: /* float16 */ + tcg_single = tcg_temp_new_i32(); + if (is_signed) { + gen_helper_vfp_sqtoh(tcg_single, tcg_int, + tcg_shift, tcg_fpstatus); + } else { + gen_helper_vfp_uqtoh(tcg_single, tcg_int, + tcg_shift, tcg_fpstatus); + } + write_fp_sreg(s, rd, tcg_single); + tcg_temp_free_i32(tcg_single); + break; + + default: + g_assert_not_reached(); } } else { TCGv_i64 tcg_int = cpu_reg(s, rd); @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); - if (is_double) { - TCGv_i64 tcg_double = read_fp_dreg(s, rn); + switch (type) { + case 1: /* float64 */ + tcg_double = read_fp_dreg(s, rn); if (is_signed) { if (!sf) { gen_helper_vfp_tosld(tcg_int, tcg_double, @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, tcg_shift, tcg_fpstatus); } } + if (!sf) { + tcg_gen_ext32u_i64(tcg_int, tcg_int); + } tcg_temp_free_i64(tcg_double); - } else { - TCGv_i32 tcg_single = read_fp_sreg(s, rn); + break; + + case 0: /* float32 */ + tcg_single = read_fp_sreg(s, rn); if (sf) { if (is_signed) { gen_helper_vfp_tosqs(tcg_int, tcg_single, @@ -XXX,XX +XXX,XX @@ static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, tcg_temp_free_i32(tcg_dest); } tcg_temp_free_i32(tcg_single); + break; + + case 3: /* float16 */ + tcg_single = read_fp_sreg(s, rn); + if (sf) { + if (is_signed) { + gen_helper_vfp_tosqh(tcg_int, tcg_single, + tcg_shift, tcg_fpstatus); + } else { + gen_helper_vfp_touqh(tcg_int, tcg_single, + tcg_shift, tcg_fpstatus); + } + } else { + TCGv_i32 tcg_dest = tcg_temp_new_i32(); + if (is_signed) { + gen_helper_vfp_toslh(tcg_dest, tcg_single, + tcg_shift, tcg_fpstatus); + } else { + gen_helper_vfp_toulh(tcg_dest, tcg_single, + tcg_shift, tcg_fpstatus); + } + tcg_gen_extu_i32_i64(tcg_int, tcg_dest); + tcg_temp_free_i32(tcg_dest); + } + tcg_temp_free_i32(tcg_single); + break; + + default: + g_assert_not_reached(); } gen_helper_set_rmode(tcg_rmode, tcg_rmode, tcg_fpstatus); tcg_temp_free_i32(tcg_rmode); - - if (!sf) { - tcg_gen_ext32u_i64(tcg_int, tcg_int); - } } tcg_temp_free_ptr(tcg_fpstatus); @@ -XXX,XX +XXX,XX @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) /* actual FP conversions */ bool itof = extract32(opcode, 1, 1); - if (type > 1 || (rmode != 0 && opcode > 1)) { + if (rmode != 0 && opcode > 1) { + unallocated_encoding(s); + return; + } + switch (type) { + case 0: /* float32 */ + case 1: /* float64 */ + break; + case 3: /* float16 */ + if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + break; + } + /* fallthru */ + default: unallocated_encoding(s); return; } -- 2.17.0 From: Richard Henderson <richard.henderson@linaro.org> Cc: qemu-stable@nongnu.org Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180512003217.9105-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 17 +++++++++++++++-- 1 file changed, 15 insertions(+), 2 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_fixed_conv(DisasContext *s, uint32_t insn) bool sf = extract32(insn, 31, 1); bool itof; - if (sbit || (type > 1) - || (!sf && scale < 32)) { + if (sbit || (!sf && scale < 32)) { + unallocated_encoding(s); + return; + } + + switch (type) { + case 0: /* float32 */ + case 1: /* float64 */ + break; + case 3: /* float16 */ + if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + break; + } + /* fallthru */ + default: unallocated_encoding(s); return; } -- 2.17.0 From: Richard Henderson <richard.henderson@linaro.org> Cc: qemu-stable@nongnu.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180512003217.9105-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 30 ++++++++++++++---------------- 1 file changed, 14 insertions(+), 16 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 TCGv_i32 read_fp_sreg(DisasContext *s, int reg) return v; } +static TCGv_i32 read_fp_hreg(DisasContext *s, int reg) +{ + TCGv_i32 v = tcg_temp_new_i32(); + + tcg_gen_ld16u_i32(v, cpu_env, fp_reg_offset(s, reg, MO_16)); + return v; +} + /* Clear the bits above an N-bit vector, for N = (is_q ? 128 : 64). * If SVE is not enabled, then there are only 128 bits in the vector. */ @@ -XXX,XX +XXX,XX @@ static void disas_fp_csel(DisasContext *s, uint32_t insn) static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) { TCGv_ptr fpst = NULL; - TCGv_i32 tcg_op = tcg_temp_new_i32(); + TCGv_i32 tcg_op = read_fp_hreg(s, rn); TCGv_i32 tcg_res = tcg_temp_new_i32(); - read_vec_element_i32(s, tcg_op, rn, 0, MO_16); - switch (opcode) { case 0x0: /* FMOV */ tcg_gen_mov_i32(tcg_res, tcg_op); @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_diff(DisasContext *s, uint32_t insn) tcg_temp_free_i64(tcg_op2); tcg_temp_free_i64(tcg_res); } else { - TCGv_i32 tcg_op1 = tcg_temp_new_i32(); - TCGv_i32 tcg_op2 = tcg_temp_new_i32(); + TCGv_i32 tcg_op1 = read_fp_hreg(s, rn); + TCGv_i32 tcg_op2 = read_fp_hreg(s, rm); TCGv_i64 tcg_res = tcg_temp_new_i64(); - read_vec_element_i32(s, tcg_op1, rn, 0, MO_16); - read_vec_element_i32(s, tcg_op2, rm, 0, MO_16); - gen_helper_neon_mull_s16(tcg_res, tcg_op1, tcg_op2); gen_helper_neon_addl_saturate_s32(tcg_res, cpu_env, tcg_res, tcg_res); @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same_fp16(DisasContext *s, fpst = get_fpstatus_ptr(true); - tcg_op1 = tcg_temp_new_i32(); - tcg_op2 = tcg_temp_new_i32(); + tcg_op1 = read_fp_hreg(s, rn); + tcg_op2 = read_fp_hreg(s, rm); tcg_res = tcg_temp_new_i32(); - read_vec_element_i32(s, tcg_op1, rn, 0, MO_16); - read_vec_element_i32(s, tcg_op2, rm, 0, MO_16); - switch (fpopcode) { case 0x03: /* FMULX */ gen_helper_advsimd_mulxh(tcg_res, tcg_op1, tcg_op2, fpst); @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) } if (is_scalar) { - TCGv_i32 tcg_op = tcg_temp_new_i32(); + TCGv_i32 tcg_op = read_fp_hreg(s, rn); TCGv_i32 tcg_res = tcg_temp_new_i32(); - read_vec_element_i32(s, tcg_op, rn, 0, MO_16); - switch (fpop) { case 0x1a: /* FCVTNS */ case 0x1b: /* FCVTMS */ -- 2.17.0 From: Richard Henderson <richard.henderson@linaro.org> We missed all of the scalar fp16 binary operations. Cc: qemu-stable@nongnu.org Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180512003217.9105-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 65 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 65 insertions(+) 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_fp_2src_double(DisasContext *s, int opcode, tcg_temp_free_i64(tcg_res); } +/* Floating-point data-processing (2 source) - half precision */ +static void handle_fp_2src_half(DisasContext *s, int opcode, + int rd, int rn, int rm) +{ + TCGv_i32 tcg_op1; + TCGv_i32 tcg_op2; + TCGv_i32 tcg_res; + TCGv_ptr fpst; + + tcg_res = tcg_temp_new_i32(); + fpst = get_fpstatus_ptr(true); + tcg_op1 = read_fp_hreg(s, rn); + tcg_op2 = read_fp_hreg(s, rm); + + switch (opcode) { + case 0x0: /* FMUL */ + gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x1: /* FDIV */ + gen_helper_advsimd_divh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x2: /* FADD */ + gen_helper_advsimd_addh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x3: /* FSUB */ + gen_helper_advsimd_subh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x4: /* FMAX */ + gen_helper_advsimd_maxh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x5: /* FMIN */ + gen_helper_advsimd_minh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x6: /* FMAXNM */ + gen_helper_advsimd_maxnumh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x7: /* FMINNM */ + gen_helper_advsimd_minnumh(tcg_res, tcg_op1, tcg_op2, fpst); + break; + case 0x8: /* FNMUL */ + gen_helper_advsimd_mulh(tcg_res, tcg_op1, tcg_op2, fpst); + tcg_gen_xori_i32(tcg_res, tcg_res, 0x8000); + break; + default: + g_assert_not_reached(); + } + + write_fp_sreg(s, rd, tcg_res); + + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(tcg_op1); + tcg_temp_free_i32(tcg_op2); + tcg_temp_free_i32(tcg_res); +} + /* Floating point data-processing (2 source) * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 0 * +---+---+---+-----------+------+---+------+--------+-----+------+------+ @@ -XXX,XX +XXX,XX @@ static void disas_fp_2src(DisasContext *s, uint32_t insn) } handle_fp_2src_double(s, opcode, rd, rn, rm); break; + case 3: + if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + unallocated_encoding(s); + return; + } + if (!fp_access_check(s)) { + return; + } + handle_fp_2src_half(s, opcode, rd, rn, rm); + break; default: unallocated_encoding(s); } -- 2.17.0 From: Richard Henderson <richard.henderson@linaro.org> We missed all of the scalar fp16 fma operations. Cc: qemu-stable@nongnu.org Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180512003217.9105-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 48 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) 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_fp_3src_double(DisasContext *s, bool o0, bool o1, tcg_temp_free_i64(tcg_res); } +/* Floating-point data-processing (3 source) - half precision */ +static void handle_fp_3src_half(DisasContext *s, bool o0, bool o1, + int rd, int rn, int rm, int ra) +{ + TCGv_i32 tcg_op1, tcg_op2, tcg_op3; + TCGv_i32 tcg_res = tcg_temp_new_i32(); + TCGv_ptr fpst = get_fpstatus_ptr(true); + + tcg_op1 = read_fp_hreg(s, rn); + tcg_op2 = read_fp_hreg(s, rm); + tcg_op3 = read_fp_hreg(s, ra); + + /* These are fused multiply-add, and must be done as one + * floating point operation with no rounding between the + * multiplication and addition steps. + * NB that doing the negations here as separate steps is + * correct : an input NaN should come out with its sign bit + * flipped if it is a negated-input. + */ + if (o1 == true) { + tcg_gen_xori_i32(tcg_op3, tcg_op3, 0x8000); + } + + if (o0 != o1) { + tcg_gen_xori_i32(tcg_op1, tcg_op1, 0x8000); + } + + gen_helper_advsimd_muladdh(tcg_res, tcg_op1, tcg_op2, tcg_op3, fpst); + + write_fp_sreg(s, rd, tcg_res); + + tcg_temp_free_ptr(fpst); + tcg_temp_free_i32(tcg_op1); + tcg_temp_free_i32(tcg_op2); + tcg_temp_free_i32(tcg_op3); + tcg_temp_free_i32(tcg_res); +} + /* Floating point data-processing (3 source) * 31 30 29 28 24 23 22 21 20 16 15 14 10 9 5 4 0 * +---+---+---+-----------+------+----+------+----+------+------+------+ @@ -XXX,XX +XXX,XX @@ static void disas_fp_3src(DisasContext *s, uint32_t insn) } handle_fp_3src_double(s, o0, o1, rd, rn, rm, ra); break; + case 3: + if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + unallocated_encoding(s); + return; + } + if (!fp_access_check(s)) { + return; + } + handle_fp_3src_half(s, o0, o1, rd, rn, rm, ra); + break; default: unallocated_encoding(s); } -- 2.17.0 From: Alex Bennée <alex.bennee@linaro.org> These where missed out from the rest of the half-precision work. Cc: qemu-stable@nongnu.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180512003217.9105-9-richard.henderson@linaro.org [rth: Diagnose lack of FP16 before fp_access_check] Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.h | 2 + target/arm/helper-a64.c | 10 +++++ target/arm/translate-a64.c | 88 ++++++++++++++++++++++++++++++-------- 3 files changed, 83 insertions(+), 17 deletions(-) diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(udiv64, TCG_CALL_NO_RWG_SE, i64, i64, i64) DEF_HELPER_FLAGS_2(sdiv64, TCG_CALL_NO_RWG_SE, s64, s64, s64) DEF_HELPER_FLAGS_1(rbit64, TCG_CALL_NO_RWG_SE, i64, i64) +DEF_HELPER_3(vfp_cmph_a64, i64, f16, f16, ptr) +DEF_HELPER_3(vfp_cmpeh_a64, i64, f16, f16, ptr) DEF_HELPER_3(vfp_cmps_a64, i64, f32, f32, ptr) DEF_HELPER_3(vfp_cmpes_a64, i64, f32, f32, ptr) DEF_HELPER_3(vfp_cmpd_a64, i64, f64, f64, ptr) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t float_rel_to_flags(int res) return flags; } +uint64_t HELPER(vfp_cmph_a64)(float16 x, float16 y, void *fp_status) +{ + return float_rel_to_flags(float16_compare_quiet(x, y, fp_status)); +} + +uint64_t HELPER(vfp_cmpeh_a64)(float16 x, float16 y, void *fp_status) +{ + return float_rel_to_flags(float16_compare(x, y, fp_status)); +} + uint64_t HELPER(vfp_cmps_a64)(float32 x, float32 y, void *fp_status) { return float_rel_to_flags(float32_compare_quiet(x, y, fp_status)); 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_data_proc_reg(DisasContext *s, uint32_t insn) } } -static void handle_fp_compare(DisasContext *s, bool is_double, +static void handle_fp_compare(DisasContext *s, int size, unsigned int rn, unsigned int rm, bool cmp_with_zero, bool signal_all_nans) { TCGv_i64 tcg_flags = tcg_temp_new_i64(); - TCGv_ptr fpst = get_fpstatus_ptr(false); + TCGv_ptr fpst = get_fpstatus_ptr(size == MO_16); - if (is_double) { + if (size == MO_64) { TCGv_i64 tcg_vn, tcg_vm; tcg_vn = read_fp_dreg(s, rn); @@ -XXX,XX +XXX,XX @@ static void handle_fp_compare(DisasContext *s, bool is_double, tcg_temp_free_i64(tcg_vn); tcg_temp_free_i64(tcg_vm); } else { - TCGv_i32 tcg_vn, tcg_vm; + TCGv_i32 tcg_vn = tcg_temp_new_i32(); + TCGv_i32 tcg_vm = tcg_temp_new_i32(); - tcg_vn = read_fp_sreg(s, rn); + read_vec_element_i32(s, tcg_vn, rn, 0, size); if (cmp_with_zero) { - tcg_vm = tcg_const_i32(0); + tcg_gen_movi_i32(tcg_vm, 0); } else { - tcg_vm = read_fp_sreg(s, rm); + read_vec_element_i32(s, tcg_vm, rm, 0, size); } - if (signal_all_nans) { - gen_helper_vfp_cmpes_a64(tcg_flags, tcg_vn, tcg_vm, fpst); - } else { - gen_helper_vfp_cmps_a64(tcg_flags, tcg_vn, tcg_vm, fpst); + + switch (size) { + case MO_32: + if (signal_all_nans) { + gen_helper_vfp_cmpes_a64(tcg_flags, tcg_vn, tcg_vm, fpst); + } else { + gen_helper_vfp_cmps_a64(tcg_flags, tcg_vn, tcg_vm, fpst); + } + break; + case MO_16: + if (signal_all_nans) { + gen_helper_vfp_cmpeh_a64(tcg_flags, tcg_vn, tcg_vm, fpst); + } else { + gen_helper_vfp_cmph_a64(tcg_flags, tcg_vn, tcg_vm, fpst); + } + break; + default: + g_assert_not_reached(); } + tcg_temp_free_i32(tcg_vn); tcg_temp_free_i32(tcg_vm); } @@ -XXX,XX +XXX,XX @@ static void handle_fp_compare(DisasContext *s, bool is_double, static void disas_fp_compare(DisasContext *s, uint32_t insn) { unsigned int mos, type, rm, op, rn, opc, op2r; + int size; mos = extract32(insn, 29, 3); - type = extract32(insn, 22, 2); /* 0 = single, 1 = double */ + type = extract32(insn, 22, 2); rm = extract32(insn, 16, 5); op = extract32(insn, 14, 2); rn = extract32(insn, 5, 5); opc = extract32(insn, 3, 2); op2r = extract32(insn, 0, 3); - if (mos || op || op2r || type > 1) { + if (mos || op || op2r) { + unallocated_encoding(s); + return; + } + + switch (type) { + case 0: + size = MO_32; + break; + case 1: + size = MO_64; + break; + case 3: + size = MO_16; + if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + break; + } + /* fallthru */ + default: unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_fp_compare(DisasContext *s, uint32_t insn) return; } - handle_fp_compare(s, type, rn, rm, opc & 1, opc & 2); + handle_fp_compare(s, size, rn, rm, opc & 1, opc & 2); } /* Floating point conditional compare @@ -XXX,XX +XXX,XX @@ static void disas_fp_ccomp(DisasContext *s, uint32_t insn) unsigned int mos, type, rm, cond, rn, op, nzcv; TCGv_i64 tcg_flags; TCGLabel *label_continue = NULL; + int size; mos = extract32(insn, 29, 3); - type = extract32(insn, 22, 2); /* 0 = single, 1 = double */ + type = extract32(insn, 22, 2); rm = extract32(insn, 16, 5); cond = extract32(insn, 12, 4); rn = extract32(insn, 5, 5); op = extract32(insn, 4, 1); nzcv = extract32(insn, 0, 4); - if (mos || type > 1) { + if (mos) { + unallocated_encoding(s); + return; + } + + switch (type) { + case 0: + size = MO_32; + break; + case 1: + size = MO_64; + break; + case 3: + size = MO_16; + if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + break; + } + /* fallthru */ + default: unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_fp_ccomp(DisasContext *s, uint32_t insn) gen_set_label(label_match); } - handle_fp_compare(s, type, rn, rm, false, op); + handle_fp_compare(s, size, rn, rm, false, op); if (cond < 0x0e) { gen_set_label(label_continue); -- 2.17.0 From: Alex Bennée <alex.bennee@linaro.org> These were missed out from the rest of the half-precision work. Cc: qemu-stable@nongnu.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180512003217.9105-10-richard.henderson@linaro.org [rth: Fix erroneous check vs type] Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 31 +++++++++++++++++++++++++------ 1 file changed, 25 insertions(+), 6 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_fp_csel(DisasContext *s, uint32_t insn) unsigned int mos, type, rm, cond, rn, rd; TCGv_i64 t_true, t_false, t_zero; DisasCompare64 c; + TCGMemOp sz; mos = extract32(insn, 29, 3); - type = extract32(insn, 22, 2); /* 0 = single, 1 = double */ + type = extract32(insn, 22, 2); rm = extract32(insn, 16, 5); cond = extract32(insn, 12, 4); rn = extract32(insn, 5, 5); rd = extract32(insn, 0, 5); - if (mos || type > 1) { + if (mos) { + unallocated_encoding(s); + return; + } + + switch (type) { + case 0: + sz = MO_32; + break; + case 1: + sz = MO_64; + break; + case 3: + sz = MO_16; + if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + break; + } + /* fallthru */ + default: unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_fp_csel(DisasContext *s, uint32_t insn) return; } - /* Zero extend sreg inputs to 64 bits now. */ + /* Zero extend sreg & hreg inputs to 64 bits now. */ t_true = tcg_temp_new_i64(); t_false = tcg_temp_new_i64(); - read_vec_element(s, t_true, rn, 0, type ? MO_64 : MO_32); - read_vec_element(s, t_false, rm, 0, type ? MO_64 : MO_32); + read_vec_element(s, t_true, rn, 0, sz); + read_vec_element(s, t_false, rm, 0, sz); a64_test_cc(&c, cond); t_zero = tcg_const_i64(0); @@ -XXX,XX +XXX,XX @@ static void disas_fp_csel(DisasContext *s, uint32_t insn) tcg_temp_free_i64(t_false); a64_free_cc(&c); - /* Note that sregs write back zeros to the high bits, + /* Note that sregs & hregs write back zeros to the high bits, and we've already done the zero-extension. */ write_fp_dreg(s, rd, t_true); tcg_temp_free_i64(t_true); -- 2.17.0 From: Alex Bennée <alex.bennee@linaro.org> All the hard work is already done by vfp_expand_imm, we just need to make sure we pick up the correct size. Cc: qemu-stable@nongnu.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180512003217.9105-11-richard.henderson@linaro.org [rth: Merge unallocated_encoding check with TCGMemOp conversion.] Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 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_imm(DisasContext *s, uint32_t insn) { int rd = extract32(insn, 0, 5); int imm8 = extract32(insn, 13, 8); - int is_double = extract32(insn, 22, 2); + int type = extract32(insn, 22, 2); uint64_t imm; TCGv_i64 tcg_res; + TCGMemOp sz; - if (is_double > 1) { + switch (type) { + case 0: + sz = MO_32; + break; + case 1: + sz = MO_64; + break; + case 3: + sz = MO_16; + if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + break; + } + /* fallthru */ + default: unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_fp_imm(DisasContext *s, uint32_t insn) return; } - imm = vfp_expand_imm(MO_32 + is_double, imm8); + imm = vfp_expand_imm(sz, imm8); tcg_res = tcg_const_i64(imm); write_fp_dreg(s, rd, tcg_res); -- 2.17.0 From: Alex Bennée <alex.bennee@linaro.org> We are meant to explicitly pass fpst, not cpu_env. Cc: qemu-stable@nongnu.org Signed-off-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20180512003217.9105-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) 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_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) tcg_gen_xori_i32(tcg_res, tcg_op, 0x8000); break; case 0x3: /* FSQRT */ - gen_helper_sqrt_f16(tcg_res, tcg_op, cpu_env); + fpst = get_fpstatus_ptr(true); + gen_helper_sqrt_f16(tcg_res, tcg_op, fpst); break; case 0x8: /* FRINTN */ case 0x9: /* FRINTP */ -- 2.17.0 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Per the Physical Layer Simplified Spec. "4.3.10.4 Switch Function Status": The block length is predefined to 512 bits and "4.10.2 SD Status": The SD Status contains status bits that are related to the SD Memory Card proprietary features and may be used for future application-specific usage. The size of the SD Status is one data block of 512 bit. The content of this register is transmitted to the Host over the DAT bus along with a 16-bit CRC. Thus the 16-bit CRC goes at offset 64. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20180509060104.4458-3-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/sd.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/sd/sd.c b/hw/sd/sd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/sd.c +++ b/hw/sd/sd.c @@ -XXX,XX +XXX,XX @@ static void sd_function_switch(SDState *sd, uint32_t arg) sd->data[14 + (i >> 1)] = new_func << ((i * 4) & 4); } memset(&sd->data[17], 0, 47); - stw_be_p(sd->data + 65, sd_crc16(sd->data, 64)); + stw_be_p(sd->data + 64, sd_crc16(sd->data, 64)); } static inline bool sd_wp_addr(SDState *sd, uint64_t addr) -- 2.17.0 Usually the logging of the CPU state produced by -d cpu is sufficient to diagnose problems, but sometimes you want to see the state of the floating point registers as well. We don't want to enable that by default as it adds a lot of extra data to the log; instead, allow it to be optionally enabled via -d fpu. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20180510130024.31678-1-peter.maydell@linaro.org --- include/qemu/log.h | 1 + accel/tcg/cpu-exec.c | 9 ++++++--- util/log.c | 2 ++ 3 files changed, 9 insertions(+), 3 deletions(-) diff --git a/include/qemu/log.h b/include/qemu/log.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/log.h +++ b/include/qemu/log.h @@ -XXX,XX +XXX,XX @@ static inline bool qemu_log_separate(void) #define CPU_LOG_PAGE (1 << 14) /* LOG_TRACE (1 << 15) is defined in log-for-trace.h */ #define CPU_LOG_TB_OP_IND (1 << 16) +#define CPU_LOG_TB_FPU (1 << 17) /* Lock output for a series of related logs. Since this is not needed * for a single qemu_log / qemu_log_mask / qemu_log_mask_and_addr, we diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -XXX,XX +XXX,XX @@ static inline tcg_target_ulong cpu_tb_exec(CPUState *cpu, TranslationBlock *itb) if (qemu_loglevel_mask(CPU_LOG_TB_CPU) && qemu_log_in_addr_range(itb->pc)) { qemu_log_lock(); + int flags = 0; + if (qemu_loglevel_mask(CPU_LOG_TB_FPU)) { + flags |= CPU_DUMP_FPU; + } #if defined(TARGET_I386) - log_cpu_state(cpu, CPU_DUMP_CCOP); -#else - log_cpu_state(cpu, 0); + flags |= CPU_DUMP_CCOP; #endif + log_cpu_state(cpu, flags); qemu_log_unlock(); } #endif /* DEBUG_DISAS */ diff --git a/util/log.c b/util/log.c index XXXXXXX..XXXXXXX 100644 --- a/util/log.c +++ b/util/log.c @@ -XXX,XX +XXX,XX @@ const QEMULogItem qemu_log_items[] = { "show trace before each executed TB (lots of logs)" }, { CPU_LOG_TB_CPU, "cpu", "show CPU registers before entering a TB (lots of logs)" }, + { CPU_LOG_TB_FPU, "fpu", + "include FPU registers in the 'cpu' logging" }, { CPU_LOG_MMU, "mmu", "log MMU-related activities" }, { CPU_LOG_PCALL, "pcall", -- 2.17.0 Hi; here's an arm pullreq. The big bits here are Fabiano's CONFIG_TCG=n patches and my set that deprecate -singlestep; other than that there's a collection of smaller bugfixes. thanks -- PMM The following changes since commit 7c18f2d663521f1b31b821a13358ce38075eaf7d: Merge tag 'for-upstream' of https://gitlab.com/bonzini/qemu into staging (2023-04-29 23:07:17 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20230502-1 for you to fetch changes up to 0ab99e4252f21550f2c16f859cbcdd3cced9f8bf: hw/net/allwinner-sun8i-emac: Correctly byteswap descriptor fields (2023-05-02 13:10:42 +0100) ---------------------------------------------------------------- * Support building Arm targets with CONFIG_TCG=no (ie KVM only) * hw/net: npcm7xx_emc: set MAC in register space * hw/arm/bcm2835_property: Implement "get command line" message * Deprecate the '-singlestep' command line option in favour of '-one-insn-per-tb' and '-accel one-insn-per-tb=on' * Deprecate 'singlestep' member of QMP StatusInfo struct * docs/about/deprecated.rst: Add "since 7.1" tag to dtb-kaslr-seed deprecation * hw/net/msf2-emac: Don't modify descriptor in-place in emac_store_desc() * raspi, aspeed: Write bootloader code correctly on big-endian hosts * hw/intc/allwinner-a10-pic: Fix bug on big-endian hosts * Fix bug in A32 ERET on big-endian hosts that caused guest crash * hw/sd/allwinner-sdhost: Correctly byteswap descriptor fields * hw/net/allwinner-sun8i-emac: Correctly byteswap descriptor fields ---------------------------------------------------------------- Claudio Fontana (1): target/arm: move cpu_tcg to tcg/cpu32.c Cédric Le Goater (2): hw/arm/boot: Make write_bootloader() public as arm_write_bootloader() hw/arm/aspeed: Use arm_write_bootloader() to write the bootloader Daniel Bertalan (1): hw/arm/bcm2835_property: Implement "get command line" message Fabiano Rosas (11): target/arm: Move cortex sysregs into a separate file target/arm: Remove dead code from cpu_max_set_sve_max_vq target/arm: Extract TCG -cpu max code into a function target/arm: Do not expose all -cpu max features to qtests target/arm: Move 64-bit TCG CPUs into tcg/ tests/qtest: Adjust and document query-cpu-model-expansion test for arm tests/qtest: Fix tests when no KVM or TCG are present tests/avocado: Pass parameters to migration test arm/Kconfig: Always select SEMIHOSTING when TCG is present arm/Kconfig: Do not build TCG-only boards on a KVM-only build tests/qtest: Restrict tpm-tis-i2c-test to CONFIG_TCG Patrick Venture (1): hw/net: npcm7xx_emc: set MAC in register space Peter Maydell (18): make one-insn-per-tb an accel option softmmu: Don't use 'singlestep' global in QMP and HMP commands accel/tcg: Use one_insn_per_tb global instead of old singlestep global linux-user: Add '-one-insn-per-tb' option equivalent to '-singlestep' bsd-user: Add '-one-insn-per-tb' option equivalent to '-singlestep' Document that -singlestep command line option is deprecated accel/tcg: Report one-insn-per-tb in 'info jit', not 'info status' hmp: Add 'one-insn-per-tb' command equivalent to 'singlestep' qapi/run-state.json: Fix missing newline at end of file qmp: Deprecate 'singlestep' member of StatusInfo docs/about/deprecated.rst: Add "since 7.1" tag to dtb-kaslr-seed deprecation hw/net/msf2-emac: Don't modify descriptor in-place in emac_store_desc() hw/arm/raspi: Use arm_write_bootloader() to write boot code hw/intc/allwinner-a10-pic: Don't use set_bit()/clear_bit() target/arm: Define and use new load_cpu_field_low32() target/arm: Add compile time asserts to load/store_cpu_field macros hw/sd/allwinner-sdhost: Correctly byteswap descriptor fields hw/net/allwinner-sun8i-emac: Correctly byteswap descriptor fields Philippe Mathieu-Daudé (1): gitlab-ci: Check building KVM-only aarch64 target docs/about/deprecated.rst | 43 +- docs/user/main.rst | 14 +- configs/devices/aarch64-softmmu/default.mak | 4 - configs/devices/arm-softmmu/default.mak | 39 -- qapi/run-state.json | 16 +- accel/tcg/internal.h | 2 + include/exec/cpu-common.h | 2 - include/hw/arm/boot.h | 49 ++ include/hw/misc/bcm2835_property.h | 1 + include/monitor/hmp.h | 2 +- target/arm/cpregs.h | 6 + target/arm/internals.h | 10 +- target/arm/translate-a32.h | 24 +- accel/tcg/cpu-exec.c | 2 +- accel/tcg/monitor.c | 14 + accel/tcg/tcg-all.c | 23 + bsd-user/main.c | 14 +- hw/arm/aspeed.c | 38 +- hw/arm/bcm2835_peripherals.c | 2 + hw/arm/bcm2836.c | 2 + hw/arm/boot.c | 35 +- hw/arm/raspi.c | 66 +- hw/arm/virt.c | 6 +- hw/intc/allwinner-a10-pic.c | 7 +- hw/misc/bcm2835_property.c | 13 +- hw/net/allwinner-sun8i-emac.c | 22 +- hw/net/msf2-emac.c | 16 +- hw/net/npcm7xx_emc.c | 32 +- hw/sd/allwinner-sdhost.c | 31 +- linux-user/main.c | 18 +- softmmu/globals.c | 1 - softmmu/runstate-hmp-cmds.c | 25 +- softmmu/runstate.c | 10 +- softmmu/vl.c | 17 +- target/arm/cortex-regs.c | 69 ++ target/arm/cpu64.c | 702 +------------------- target/arm/{cpu_tcg.c => tcg/cpu32.c} | 72 +- target/arm/tcg/cpu64.c | 723 +++++++++++++++++++++ target/arm/tcg/translate.c | 4 +- tests/qtest/arm-cpu-features.c | 20 +- tests/qtest/bios-tables-test.c | 11 +- tests/qtest/boot-serial-test.c | 5 + tests/qtest/migration-test.c | 9 +- tests/qtest/pxe-test.c | 8 +- tests/qtest/test-hmp.c | 1 + tests/qtest/vmgenid-test.c | 9 +- .gitlab-ci.d/crossbuilds.yml | 11 + .../custom-runners/ubuntu-22.04-aarch64.yml | 4 - hmp-commands.hx | 25 +- hw/arm/Kconfig | 43 +- qemu-options.hx | 12 +- target/arm/Kconfig | 7 + target/arm/meson.build | 2 +- target/arm/tcg/meson.build | 2 + tcg/tci/README | 2 +- tests/avocado/migration.py | 83 ++- tests/qtest/meson.build | 3 +- 57 files changed, 1449 insertions(+), 984 deletions(-) create mode 100644 target/arm/cortex-regs.c rename target/arm/{cpu_tcg.c => tcg/cpu32.c} (93%) create mode 100644 target/arm/tcg/cpu64.c From: Fabiano Rosas <farosas@suse.de> The file cpu_tcg.c is about to be moved into the tcg/ directory, so move the register definitions into a new file. Also move the function declaration to the more appropriate cpregs.h. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230426180013.14814-2-farosas@suse.de Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpregs.h | 6 ++++ target/arm/internals.h | 6 ---- target/arm/cortex-regs.c | 69 ++++++++++++++++++++++++++++++++++++++++ target/arm/cpu64.c | 1 + target/arm/cpu_tcg.c | 59 ---------------------------------- target/arm/meson.build | 1 + 6 files changed, 77 insertions(+), 65 deletions(-) create mode 100644 target/arm/cortex-regs.c diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -XXX,XX +XXX,XX @@ static inline bool arm_cpreg_in_idspace(const ARMCPRegInfo *ri) ri->crn, ri->crm); } +#ifdef CONFIG_USER_ONLY +static inline void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu) { } +#else +void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu); +#endif + #endif /* TARGET_ARM_CPREGS_H */ diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ uint32_t arm_v7m_mrs_control(CPUARMState *env, uint32_t secure); uint32_t *arm_v7m_get_sp_ptr(CPUARMState *env, bool secure, bool threadmode, bool spsel); -#ifdef CONFIG_USER_ONLY -static inline void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu) { } -#else -void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu); -#endif - bool el_is_in_host(CPUARMState *env, int el); void aa32_max_features(ARMCPU *cpu); diff --git a/target/arm/cortex-regs.c b/target/arm/cortex-regs.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/cortex-regs.c @@ -XXX,XX +XXX,XX @@ +/* + * ARM Cortex-A registers + * + * This code is licensed under the GNU GPL v2 or later. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#include "qemu/osdep.h" +#include "cpu.h" +#include "cpregs.h" + + +static uint64_t l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + ARMCPU *cpu = env_archcpu(env); + + /* Number of cores is in [25:24]; otherwise we RAZ */ + return (cpu->core_count - 1) << 24; +} + +static const ARMCPRegInfo cortex_a72_a57_a53_cp_reginfo[] = { + { .name = "L2CTLR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 1, .crn = 11, .crm = 0, .opc2 = 2, + .access = PL1_RW, .readfn = l2ctlr_read, + .writefn = arm_cp_write_ignore }, + { .name = "L2CTLR", + .cp = 15, .opc1 = 1, .crn = 9, .crm = 0, .opc2 = 2, + .access = PL1_RW, .readfn = l2ctlr_read, + .writefn = arm_cp_write_ignore }, + { .name = "L2ECTLR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 1, .crn = 11, .crm = 0, .opc2 = 3, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "L2ECTLR", + .cp = 15, .opc1 = 1, .crn = 9, .crm = 0, .opc2 = 3, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "L2ACTLR", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 0, .opc2 = 0, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUACTLR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 0, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUACTLR", + .cp = 15, .opc1 = 0, .crm = 15, + .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, + { .name = "CPUECTLR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 1, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUECTLR", + .cp = 15, .opc1 = 1, .crm = 15, + .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, + { .name = "CPUMERRSR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 2, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "CPUMERRSR", + .cp = 15, .opc1 = 2, .crm = 15, + .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, + { .name = "L2MERRSR_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 3, + .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, + { .name = "L2MERRSR", + .cp = 15, .opc1 = 3, .crm = 15, + .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, +}; + +void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu) +{ + define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo); +} 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 @@ #include "qapi/visitor.h" #include "hw/qdev-properties.h" #include "internals.h" +#include "cpregs.h" static void aarch64_a35_initfn(Object *obj) { diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ void aa32_max_features(ARMCPU *cpu) cpu->isar.id_dfr0 = t; } -#ifndef CONFIG_USER_ONLY -static uint64_t l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri) -{ - ARMCPU *cpu = env_archcpu(env); - - /* Number of cores is in [25:24]; otherwise we RAZ */ - return (cpu->core_count - 1) << 24; -} - -static const ARMCPRegInfo cortex_a72_a57_a53_cp_reginfo[] = { - { .name = "L2CTLR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 1, .crn = 11, .crm = 0, .opc2 = 2, - .access = PL1_RW, .readfn = l2ctlr_read, - .writefn = arm_cp_write_ignore }, - { .name = "L2CTLR", - .cp = 15, .opc1 = 1, .crn = 9, .crm = 0, .opc2 = 2, - .access = PL1_RW, .readfn = l2ctlr_read, - .writefn = arm_cp_write_ignore }, - { .name = "L2ECTLR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 1, .crn = 11, .crm = 0, .opc2 = 3, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "L2ECTLR", - .cp = 15, .opc1 = 1, .crn = 9, .crm = 0, .opc2 = 3, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "L2ACTLR", .state = ARM_CP_STATE_BOTH, - .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 0, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUACTLR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUACTLR", - .cp = 15, .opc1 = 0, .crm = 15, - .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, - { .name = "CPUECTLR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 1, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUECTLR", - .cp = 15, .opc1 = 1, .crm = 15, - .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, - { .name = "CPUMERRSR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 2, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUMERRSR", - .cp = 15, .opc1 = 2, .crm = 15, - .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, - { .name = "L2MERRSR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 1, .crn = 15, .crm = 2, .opc2 = 3, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "L2MERRSR", - .cp = 15, .opc1 = 3, .crm = 15, - .access = PL1_RW, .type = ARM_CP_CONST | ARM_CP_64BIT, .resetvalue = 0 }, -}; - -void define_cortex_a72_a57_a53_cp_reginfo(ARMCPU *cpu) -{ - define_arm_cp_regs(cpu, cortex_a72_a57_a53_cp_reginfo); -} -#endif /* !CONFIG_USER_ONLY */ - /* CPU models. These are not needed for the AArch64 linux-user build. */ #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64) diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_softmmu_ss.add(files( 'arch_dump.c', 'arm-powerctl.c', 'arm-qmp-cmds.c', + 'cortex-regs.c', 'machine.c', 'ptw.c', )) -- 2.34.1 From: Fabiano Rosas <farosas@suse.de> The sve-max-vq property has been removed from the -cpu max used with KVM, so code under kvm_enabled in cpu_max_set_sve_max_vq is not reachable. Fixes: 0baa21be49 ("target/arm: Make KVM -cpu max exactly like -cpu host") Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Fabiano Rosas <farosas@suse.de> Message-id: 20230426180013.14814-3-farosas@suse.de Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 6 ------ 1 file changed, 6 deletions(-) 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 cpu_max_set_sve_max_vq(Object *obj, Visitor *v, const char *name, return; } - if (kvm_enabled() && !kvm_arm_sve_supported()) { - error_setg(errp, "cannot set sve-max-vq"); - error_append_hint(errp, "SVE not supported by KVM on this host\n"); - return; - } - if (max_vq == 0 || max_vq > ARM_MAX_VQ) { error_setg(errp, "unsupported SVE vector length"); error_append_hint(errp, "Valid sve-max-vq in range [1-%d]\n", -- 2.34.1 From: Fabiano Rosas <farosas@suse.de> Introduce aarch64_max_tcg_initfn that contains the TCG-only part of -cpu max configuration. We'll need that to be able to restrict this code to a TCG-only config in the next patches. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Fabiano Rosas <farosas@suse.de> Message-id: 20230426180013.14814-4-farosas@suse.de Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 32 ++++++++++++++++++-------------- 1 file changed, 18 insertions(+), 14 deletions(-) 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_host_initfn(Object *obj) #endif } -/* -cpu max: if KVM is enabled, like -cpu host (best possible with this host); - * otherwise, a CPU with as many features enabled as our emulation supports. - * The version of '-cpu max' for qemu-system-arm is defined in cpu.c; +/* + * -cpu max: a CPU with as many features enabled as our emulation supports. + * The version of '-cpu max' for qemu-system-arm is defined in cpu_tcg.c; * this only needs to handle 64 bits. */ -static void aarch64_max_initfn(Object *obj) +static void aarch64_max_tcg_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); uint64_t t; uint32_t u; - if (kvm_enabled() || hvf_enabled()) { - /* With KVM or HVF, '-cpu max' is identical to '-cpu host' */ - aarch64_host_initfn(obj); - return; - } - - /* '-cpu max' for TCG: we currently do this as "A57 with extra things" */ - - aarch64_a57_initfn(obj); - /* * Reset MIDR so the guest doesn't mistake our 'max' CPU type for a real * one and try to apply errata workarounds or use impdef features we @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) qdev_property_add_static(DEVICE(obj), &arm_cpu_lpa2_property); } +static void aarch64_max_initfn(Object *obj) +{ + if (kvm_enabled() || hvf_enabled()) { + /* With KVM or HVF, '-cpu max' is identical to '-cpu host' */ + aarch64_host_initfn(obj); + return; + } + + /* '-cpu max' for TCG: we currently do this as "A57 with extra things" */ + + aarch64_a57_initfn(obj); + aarch64_max_tcg_initfn(obj); +} + static const ARMCPUInfo aarch64_cpus[] = { { .name = "cortex-a35", .initfn = aarch64_a35_initfn }, { .name = "cortex-a57", .initfn = aarch64_a57_initfn }, -- 2.34.1 From: Fabiano Rosas <farosas@suse.de> We're about to move the TCG-only -cpu max configuration code under CONFIG_TCG. To be able to do that we need to make sure the qtests still have some cpu configured even when no other accelerator is available. Delineate now what is used with TCG-only and what is also used with qtests to make the subsequent patches cleaner. Signed-off-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230426180013.14814-5-farosas@suse.de Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 12 +++++++++--- 1 file changed, 9 insertions(+), 3 deletions(-) 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 @@ #include "qemu/module.h" #include "sysemu/kvm.h" #include "sysemu/hvf.h" +#include "sysemu/qtest.h" +#include "sysemu/tcg.h" #include "kvm_arm.h" #include "hvf_arm.h" #include "qapi/visitor.h" @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) return; } - /* '-cpu max' for TCG: we currently do this as "A57 with extra things" */ + if (tcg_enabled() || qtest_enabled()) { + aarch64_a57_initfn(obj); + } - aarch64_a57_initfn(obj); - aarch64_max_tcg_initfn(obj); + /* '-cpu max' for TCG: we currently do this as "A57 with extra things" */ + if (tcg_enabled()) { + aarch64_max_tcg_initfn(obj); + } } static const ARMCPUInfo aarch64_cpus[] = { -- 2.34.1 From: Fabiano Rosas <farosas@suse.de> Move the 64-bit CPUs that are TCG-only: - cortex-a35 - cortex-a55 - cortex-a72 - cortex-a76 - a64fx - neoverse-n1 Keep the CPUs that can be used with KVM: - cortex-a57 - cortex-a53 - max - host Signed-off-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230426180013.14814-6-farosas@suse.de Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 4 + hw/arm/virt.c | 6 +- target/arm/cpu64.c | 687 +----------------------------- target/arm/{ => tcg}/cpu64.c | 782 +---------------------------------- target/arm/tcg/meson.build | 1 + 5 files changed, 14 insertions(+), 1466 deletions(-) copy target/arm/{ => tcg}/cpu64.c (51%) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp); void arm_cpu_sme_finalize(ARMCPU *cpu, Error **errp); void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp); void arm_cpu_lpa2_finalize(ARMCPU *cpu, Error **errp); +void aarch64_max_tcg_initfn(Object *obj); +void aarch64_add_pauth_properties(Object *obj); +void aarch64_add_sve_properties(Object *obj); +void aarch64_add_sme_properties(Object *obj); #endif /* Read the CONTROL register as the MRS instruction would. */ diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static const char *valid_cpus[] = { ARM_CPU_TYPE_NAME("cortex-a7"), #endif ARM_CPU_TYPE_NAME("cortex-a15"), +#ifdef CONFIG_TCG ARM_CPU_TYPE_NAME("cortex-a35"), - ARM_CPU_TYPE_NAME("cortex-a53"), ARM_CPU_TYPE_NAME("cortex-a55"), - ARM_CPU_TYPE_NAME("cortex-a57"), ARM_CPU_TYPE_NAME("cortex-a72"), ARM_CPU_TYPE_NAME("cortex-a76"), ARM_CPU_TYPE_NAME("a64fx"), ARM_CPU_TYPE_NAME("neoverse-n1"), +#endif + ARM_CPU_TYPE_NAME("cortex-a53"), + ARM_CPU_TYPE_NAME("cortex-a57"), ARM_CPU_TYPE_NAME("host"), ARM_CPU_TYPE_NAME("max"), }; 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 @@ #include "internals.h" #include "cpregs.h" -static void aarch64_a35_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "arm,cortex-a35"; - set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); - set_feature(&cpu->env, ARM_FEATURE_AARCH64); - set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_EL2); - set_feature(&cpu->env, ARM_FEATURE_EL3); - set_feature(&cpu->env, ARM_FEATURE_PMU); - - /* From B2.2 AArch64 identification registers. */ - cpu->midr = 0x411fd040; - cpu->revidr = 0; - cpu->ctr = 0x84448004; - cpu->isar.id_pfr0 = 0x00000131; - cpu->isar.id_pfr1 = 0x00011011; - cpu->isar.id_dfr0 = 0x03010066; - cpu->id_afr0 = 0; - cpu->isar.id_mmfr0 = 0x10201105; - cpu->isar.id_mmfr1 = 0x40000000; - cpu->isar.id_mmfr2 = 0x01260000; - cpu->isar.id_mmfr3 = 0x02102211; - cpu->isar.id_isar0 = 0x02101110; - cpu->isar.id_isar1 = 0x13112111; - cpu->isar.id_isar2 = 0x21232042; - cpu->isar.id_isar3 = 0x01112131; - cpu->isar.id_isar4 = 0x00011142; - cpu->isar.id_isar5 = 0x00011121; - cpu->isar.id_aa64pfr0 = 0x00002222; - cpu->isar.id_aa64pfr1 = 0; - cpu->isar.id_aa64dfr0 = 0x10305106; - cpu->isar.id_aa64dfr1 = 0; - cpu->isar.id_aa64isar0 = 0x00011120; - cpu->isar.id_aa64isar1 = 0; - cpu->isar.id_aa64mmfr0 = 0x00101122; - cpu->isar.id_aa64mmfr1 = 0; - cpu->clidr = 0x0a200023; - cpu->dcz_blocksize = 4; - - /* From B2.4 AArch64 Virtual Memory control registers */ - cpu->reset_sctlr = 0x00c50838; - - /* From B2.10 AArch64 performance monitor registers */ - cpu->isar.reset_pmcr_el0 = 0x410a3000; - - /* From B2.29 Cache ID registers */ - cpu->ccsidr[0] = 0x700fe01a; /* 32KB L1 dcache */ - cpu->ccsidr[1] = 0x201fe00a; /* 32KB L1 icache */ - cpu->ccsidr[2] = 0x703fe03a; /* 512KB L2 cache */ - - /* From B3.5 VGIC Type register */ - cpu->gic_num_lrs = 4; - cpu->gic_vpribits = 5; - cpu->gic_vprebits = 5; - cpu->gic_pribits = 5; - - /* From C6.4 Debug ID Register */ - cpu->isar.dbgdidr = 0x3516d000; - /* From C6.5 Debug Device ID Register */ - cpu->isar.dbgdevid = 0x00110f13; - /* From C6.6 Debug Device ID Register 1 */ - cpu->isar.dbgdevid1 = 0x2; - - /* From Cortex-A35 SIMD and Floating-point Support r1p0 */ - /* From 3.2 AArch32 register summary */ - cpu->reset_fpsid = 0x41034043; - - /* From 2.2 AArch64 register summary */ - cpu->isar.mvfr0 = 0x10110222; - cpu->isar.mvfr1 = 0x12111111; - cpu->isar.mvfr2 = 0x00000043; - - /* These values are the same with A53/A57/A72. */ - define_cortex_a72_a57_a53_cp_reginfo(cpu); -} - void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) { /* @@ -XXX,XX +XXX,XX @@ void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) cpu->sve_vq.map = vq_map; } -static void cpu_max_get_sve_max_vq(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - ARMCPU *cpu = ARM_CPU(obj); - uint32_t value; - - /* All vector lengths are disabled when SVE is off. */ - if (!cpu_isar_feature(aa64_sve, cpu)) { - value = 0; - } else { - value = cpu->sve_max_vq; - } - visit_type_uint32(v, name, &value, errp); -} - -static void cpu_max_set_sve_max_vq(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - ARMCPU *cpu = ARM_CPU(obj); - uint32_t max_vq; - - if (!visit_type_uint32(v, name, &max_vq, errp)) { - return; - } - - if (max_vq == 0 || max_vq > ARM_MAX_VQ) { - error_setg(errp, "unsupported SVE vector length"); - error_append_hint(errp, "Valid sve-max-vq in range [1-%d]\n", - ARM_MAX_VQ); - return; - } - - cpu->sve_max_vq = max_vq; -} - /* * Note that cpu_arm_{get,set}_vq cannot use the simpler * object_property_add_bool interface because they make use of the @@ -XXX,XX +XXX,XX @@ static void cpu_arm_get_default_vec_len(Object *obj, Visitor *v, } #endif -static void aarch64_add_sve_properties(Object *obj) +void aarch64_add_sve_properties(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); uint32_t vq; @@ -XXX,XX +XXX,XX @@ static void aarch64_add_sve_properties(Object *obj) #endif } -static void aarch64_add_sme_properties(Object *obj) +void aarch64_add_sme_properties(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); uint32_t vq; @@ -XXX,XX +XXX,XX @@ static Property arm_cpu_pauth_property = static Property arm_cpu_pauth_impdef_property = DEFINE_PROP_BOOL("pauth-impdef", ARMCPU, prop_pauth_impdef, false); -static void aarch64_add_pauth_properties(Object *obj) +void aarch64_add_pauth_properties(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); @@ -XXX,XX +XXX,XX @@ static void aarch64_add_pauth_properties(Object *obj) } } -static Property arm_cpu_lpa2_property = - DEFINE_PROP_BOOL("lpa2", ARMCPU, prop_lpa2, true); - void arm_cpu_lpa2_finalize(ARMCPU *cpu, Error **errp) { uint64_t t; @@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj) define_cortex_a72_a57_a53_cp_reginfo(cpu); } -static void aarch64_a55_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "arm,cortex-a55"; - set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); - set_feature(&cpu->env, ARM_FEATURE_AARCH64); - set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_EL2); - set_feature(&cpu->env, ARM_FEATURE_EL3); - set_feature(&cpu->env, ARM_FEATURE_PMU); - - /* Ordered by B2.4 AArch64 registers by functional group */ - cpu->clidr = 0x82000023; - cpu->ctr = 0x84448004; /* L1Ip = VIPT */ - cpu->dcz_blocksize = 4; /* 64 bytes */ - cpu->isar.id_aa64dfr0 = 0x0000000010305408ull; - cpu->isar.id_aa64isar0 = 0x0000100010211120ull; - cpu->isar.id_aa64isar1 = 0x0000000000100001ull; - cpu->isar.id_aa64mmfr0 = 0x0000000000101122ull; - cpu->isar.id_aa64mmfr1 = 0x0000000010212122ull; - cpu->isar.id_aa64mmfr2 = 0x0000000000001011ull; - cpu->isar.id_aa64pfr0 = 0x0000000010112222ull; - cpu->isar.id_aa64pfr1 = 0x0000000000000010ull; - cpu->id_afr0 = 0x00000000; - cpu->isar.id_dfr0 = 0x04010088; - cpu->isar.id_isar0 = 0x02101110; - cpu->isar.id_isar1 = 0x13112111; - cpu->isar.id_isar2 = 0x21232042; - cpu->isar.id_isar3 = 0x01112131; - cpu->isar.id_isar4 = 0x00011142; - cpu->isar.id_isar5 = 0x01011121; - cpu->isar.id_isar6 = 0x00000010; - cpu->isar.id_mmfr0 = 0x10201105; - cpu->isar.id_mmfr1 = 0x40000000; - cpu->isar.id_mmfr2 = 0x01260000; - cpu->isar.id_mmfr3 = 0x02122211; - cpu->isar.id_mmfr4 = 0x00021110; - cpu->isar.id_pfr0 = 0x10010131; - cpu->isar.id_pfr1 = 0x00011011; - cpu->isar.id_pfr2 = 0x00000011; - cpu->midr = 0x412FD050; /* r2p0 */ - cpu->revidr = 0; - - /* From B2.23 CCSIDR_EL1 */ - cpu->ccsidr[0] = 0x700fe01a; /* 32KB L1 dcache */ - cpu->ccsidr[1] = 0x200fe01a; /* 32KB L1 icache */ - cpu->ccsidr[2] = 0x703fe07a; /* 512KB L2 cache */ - - /* From B2.96 SCTLR_EL3 */ - cpu->reset_sctlr = 0x30c50838; - - /* From B4.45 ICH_VTR_EL2 */ - cpu->gic_num_lrs = 4; - cpu->gic_vpribits = 5; - cpu->gic_vprebits = 5; - cpu->gic_pribits = 5; - - cpu->isar.mvfr0 = 0x10110222; - cpu->isar.mvfr1 = 0x13211111; - cpu->isar.mvfr2 = 0x00000043; - - /* From D5.4 AArch64 PMU register summary */ - cpu->isar.reset_pmcr_el0 = 0x410b3000; -} - -static void aarch64_a72_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "arm,cortex-a72"; - set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); - set_feature(&cpu->env, ARM_FEATURE_AARCH64); - set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_EL2); - set_feature(&cpu->env, ARM_FEATURE_EL3); - set_feature(&cpu->env, ARM_FEATURE_PMU); - cpu->midr = 0x410fd083; - cpu->revidr = 0x00000000; - cpu->reset_fpsid = 0x41034080; - cpu->isar.mvfr0 = 0x10110222; - cpu->isar.mvfr1 = 0x12111111; - cpu->isar.mvfr2 = 0x00000043; - cpu->ctr = 0x8444c004; - cpu->reset_sctlr = 0x00c50838; - cpu->isar.id_pfr0 = 0x00000131; - cpu->isar.id_pfr1 = 0x00011011; - cpu->isar.id_dfr0 = 0x03010066; - cpu->id_afr0 = 0x00000000; - cpu->isar.id_mmfr0 = 0x10201105; - cpu->isar.id_mmfr1 = 0x40000000; - cpu->isar.id_mmfr2 = 0x01260000; - cpu->isar.id_mmfr3 = 0x02102211; - cpu->isar.id_isar0 = 0x02101110; - cpu->isar.id_isar1 = 0x13112111; - cpu->isar.id_isar2 = 0x21232042; - cpu->isar.id_isar3 = 0x01112131; - cpu->isar.id_isar4 = 0x00011142; - cpu->isar.id_isar5 = 0x00011121; - cpu->isar.id_aa64pfr0 = 0x00002222; - cpu->isar.id_aa64dfr0 = 0x10305106; - cpu->isar.id_aa64isar0 = 0x00011120; - cpu->isar.id_aa64mmfr0 = 0x00001124; - cpu->isar.dbgdidr = 0x3516d000; - cpu->isar.dbgdevid = 0x01110f13; - cpu->isar.dbgdevid1 = 0x2; - cpu->isar.reset_pmcr_el0 = 0x41023000; - cpu->clidr = 0x0a200023; - cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */ - cpu->ccsidr[1] = 0x201fe012; /* 48KB L1 icache */ - cpu->ccsidr[2] = 0x707fe07a; /* 1MB L2 cache */ - cpu->dcz_blocksize = 4; /* 64 bytes */ - cpu->gic_num_lrs = 4; - cpu->gic_vpribits = 5; - cpu->gic_vprebits = 5; - cpu->gic_pribits = 5; - define_cortex_a72_a57_a53_cp_reginfo(cpu); -} - -static void aarch64_a76_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "arm,cortex-a76"; - set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); - set_feature(&cpu->env, ARM_FEATURE_AARCH64); - set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_EL2); - set_feature(&cpu->env, ARM_FEATURE_EL3); - set_feature(&cpu->env, ARM_FEATURE_PMU); - - /* Ordered by B2.4 AArch64 registers by functional group */ - cpu->clidr = 0x82000023; - cpu->ctr = 0x8444C004; - cpu->dcz_blocksize = 4; - cpu->isar.id_aa64dfr0 = 0x0000000010305408ull; - cpu->isar.id_aa64isar0 = 0x0000100010211120ull; - cpu->isar.id_aa64isar1 = 0x0000000000100001ull; - cpu->isar.id_aa64mmfr0 = 0x0000000000101122ull; - cpu->isar.id_aa64mmfr1 = 0x0000000010212122ull; - cpu->isar.id_aa64mmfr2 = 0x0000000000001011ull; - cpu->isar.id_aa64pfr0 = 0x1100000010111112ull; /* GIC filled in later */ - cpu->isar.id_aa64pfr1 = 0x0000000000000010ull; - cpu->id_afr0 = 0x00000000; - cpu->isar.id_dfr0 = 0x04010088; - cpu->isar.id_isar0 = 0x02101110; - cpu->isar.id_isar1 = 0x13112111; - cpu->isar.id_isar2 = 0x21232042; - cpu->isar.id_isar3 = 0x01112131; - cpu->isar.id_isar4 = 0x00010142; - cpu->isar.id_isar5 = 0x01011121; - cpu->isar.id_isar6 = 0x00000010; - cpu->isar.id_mmfr0 = 0x10201105; - cpu->isar.id_mmfr1 = 0x40000000; - cpu->isar.id_mmfr2 = 0x01260000; - cpu->isar.id_mmfr3 = 0x02122211; - cpu->isar.id_mmfr4 = 0x00021110; - cpu->isar.id_pfr0 = 0x10010131; - cpu->isar.id_pfr1 = 0x00010000; /* GIC filled in later */ - cpu->isar.id_pfr2 = 0x00000011; - cpu->midr = 0x414fd0b1; /* r4p1 */ - cpu->revidr = 0; - - /* From B2.18 CCSIDR_EL1 */ - cpu->ccsidr[0] = 0x701fe01a; /* 64KB L1 dcache */ - cpu->ccsidr[1] = 0x201fe01a; /* 64KB L1 icache */ - cpu->ccsidr[2] = 0x707fe03a; /* 512KB L2 cache */ - - /* From B2.93 SCTLR_EL3 */ - cpu->reset_sctlr = 0x30c50838; - - /* From B4.23 ICH_VTR_EL2 */ - cpu->gic_num_lrs = 4; - cpu->gic_vpribits = 5; - cpu->gic_vprebits = 5; - cpu->gic_pribits = 5; - - /* From B5.1 AdvSIMD AArch64 register summary */ - cpu->isar.mvfr0 = 0x10110222; - cpu->isar.mvfr1 = 0x13211111; - cpu->isar.mvfr2 = 0x00000043; - - /* From D5.1 AArch64 PMU register summary */ - cpu->isar.reset_pmcr_el0 = 0x410b3000; -} - -static void aarch64_a64fx_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "arm,a64fx"; - set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); - set_feature(&cpu->env, ARM_FEATURE_AARCH64); - set_feature(&cpu->env, ARM_FEATURE_EL2); - set_feature(&cpu->env, ARM_FEATURE_EL3); - set_feature(&cpu->env, ARM_FEATURE_PMU); - cpu->midr = 0x461f0010; - cpu->revidr = 0x00000000; - cpu->ctr = 0x86668006; - cpu->reset_sctlr = 0x30000180; - cpu->isar.id_aa64pfr0 = 0x0000000101111111; /* No RAS Extensions */ - cpu->isar.id_aa64pfr1 = 0x0000000000000000; - cpu->isar.id_aa64dfr0 = 0x0000000010305408; - cpu->isar.id_aa64dfr1 = 0x0000000000000000; - cpu->id_aa64afr0 = 0x0000000000000000; - cpu->id_aa64afr1 = 0x0000000000000000; - cpu->isar.id_aa64mmfr0 = 0x0000000000001122; - cpu->isar.id_aa64mmfr1 = 0x0000000011212100; - cpu->isar.id_aa64mmfr2 = 0x0000000000001011; - cpu->isar.id_aa64isar0 = 0x0000000010211120; - cpu->isar.id_aa64isar1 = 0x0000000000010001; - cpu->isar.id_aa64zfr0 = 0x0000000000000000; - cpu->clidr = 0x0000000080000023; - cpu->ccsidr[0] = 0x7007e01c; /* 64KB L1 dcache */ - cpu->ccsidr[1] = 0x2007e01c; /* 64KB L1 icache */ - cpu->ccsidr[2] = 0x70ffe07c; /* 8MB L2 cache */ - cpu->dcz_blocksize = 6; /* 256 bytes */ - cpu->gic_num_lrs = 4; - cpu->gic_vpribits = 5; - cpu->gic_vprebits = 5; - cpu->gic_pribits = 5; - - /* The A64FX supports only 128, 256 and 512 bit vector lengths */ - aarch64_add_sve_properties(obj); - cpu->sve_vq.supported = (1 << 0) /* 128bit */ - | (1 << 1) /* 256bit */ - | (1 << 3); /* 512bit */ - - cpu->isar.reset_pmcr_el0 = 0x46014040; - - /* TODO: Add A64FX specific HPC extension registers */ -} - -static const ARMCPRegInfo neoverse_n1_cp_reginfo[] = { - { .name = "ATCR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 7, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "ATCR_EL2", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 4, .crn = 15, .crm = 7, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "ATCR_EL3", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 7, .opc2 = 0, - .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "ATCR_EL12", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 5, .crn = 15, .crm = 7, .opc2 = 0, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "AVTCR_EL2", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 4, .crn = 15, .crm = 7, .opc2 = 1, - .access = PL2_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUACTLR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUACTLR2_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 1, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUACTLR3_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 2, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - /* - * Report CPUCFR_EL1.SCU as 1, as we do not implement the DSU - * (and in particular its system registers). - */ - { .name = "CPUCFR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 0, .opc2 = 0, - .access = PL1_R, .type = ARM_CP_CONST, .resetvalue = 4 }, - { .name = "CPUECTLR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 1, .opc2 = 4, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0x961563010 }, - { .name = "CPUPCR_EL3", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 8, .opc2 = 1, - .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUPMR_EL3", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 8, .opc2 = 3, - .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUPOR_EL3", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 8, .opc2 = 2, - .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUPSELR_EL3", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 6, .crn = 15, .crm = 8, .opc2 = 0, - .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "CPUPWRCTLR_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 2, .opc2 = 7, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "ERXPFGCDN_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 2, .opc2 = 2, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "ERXPFGCTL_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 2, .opc2 = 1, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "ERXPFGF_EL1", .state = ARM_CP_STATE_AA64, - .opc0 = 3, .opc1 = 0, .crn = 15, .crm = 2, .opc2 = 0, - .access = PL1_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, -}; - -static void define_neoverse_n1_cp_reginfo(ARMCPU *cpu) -{ - define_arm_cp_regs(cpu, neoverse_n1_cp_reginfo); -} - -static void aarch64_neoverse_n1_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "arm,neoverse-n1"; - set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); - set_feature(&cpu->env, ARM_FEATURE_AARCH64); - set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_EL2); - set_feature(&cpu->env, ARM_FEATURE_EL3); - set_feature(&cpu->env, ARM_FEATURE_PMU); - - /* Ordered by B2.4 AArch64 registers by functional group */ - cpu->clidr = 0x82000023; - cpu->ctr = 0x8444c004; - cpu->dcz_blocksize = 4; - cpu->isar.id_aa64dfr0 = 0x0000000110305408ull; - cpu->isar.id_aa64isar0 = 0x0000100010211120ull; - cpu->isar.id_aa64isar1 = 0x0000000000100001ull; - cpu->isar.id_aa64mmfr0 = 0x0000000000101125ull; - cpu->isar.id_aa64mmfr1 = 0x0000000010212122ull; - cpu->isar.id_aa64mmfr2 = 0x0000000000001011ull; - cpu->isar.id_aa64pfr0 = 0x1100000010111112ull; /* GIC filled in later */ - cpu->isar.id_aa64pfr1 = 0x0000000000000020ull; - cpu->id_afr0 = 0x00000000; - cpu->isar.id_dfr0 = 0x04010088; - cpu->isar.id_isar0 = 0x02101110; - cpu->isar.id_isar1 = 0x13112111; - cpu->isar.id_isar2 = 0x21232042; - cpu->isar.id_isar3 = 0x01112131; - cpu->isar.id_isar4 = 0x00010142; - cpu->isar.id_isar5 = 0x01011121; - cpu->isar.id_isar6 = 0x00000010; - cpu->isar.id_mmfr0 = 0x10201105; - cpu->isar.id_mmfr1 = 0x40000000; - cpu->isar.id_mmfr2 = 0x01260000; - cpu->isar.id_mmfr3 = 0x02122211; - cpu->isar.id_mmfr4 = 0x00021110; - cpu->isar.id_pfr0 = 0x10010131; - cpu->isar.id_pfr1 = 0x00010000; /* GIC filled in later */ - cpu->isar.id_pfr2 = 0x00000011; - cpu->midr = 0x414fd0c1; /* r4p1 */ - cpu->revidr = 0; - - /* From B2.23 CCSIDR_EL1 */ - cpu->ccsidr[0] = 0x701fe01a; /* 64KB L1 dcache */ - cpu->ccsidr[1] = 0x201fe01a; /* 64KB L1 icache */ - cpu->ccsidr[2] = 0x70ffe03a; /* 1MB L2 cache */ - - /* From B2.98 SCTLR_EL3 */ - cpu->reset_sctlr = 0x30c50838; - - /* From B4.23 ICH_VTR_EL2 */ - cpu->gic_num_lrs = 4; - cpu->gic_vpribits = 5; - cpu->gic_vprebits = 5; - cpu->gic_pribits = 5; - - /* From B5.1 AdvSIMD AArch64 register summary */ - cpu->isar.mvfr0 = 0x10110222; - cpu->isar.mvfr1 = 0x13211111; - cpu->isar.mvfr2 = 0x00000043; - - /* From D5.1 AArch64 PMU register summary */ - cpu->isar.reset_pmcr_el0 = 0x410c3000; - - define_neoverse_n1_cp_reginfo(cpu); -} - static void aarch64_host_initfn(Object *obj) { #if defined(CONFIG_KVM) @@ -XXX,XX +XXX,XX @@ static void aarch64_host_initfn(Object *obj) #endif } -/* - * -cpu max: a CPU with as many features enabled as our emulation supports. - * The version of '-cpu max' for qemu-system-arm is defined in cpu_tcg.c; - * this only needs to handle 64 bits. - */ -static void aarch64_max_tcg_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - uint64_t t; - uint32_t u; - - /* - * Reset MIDR so the guest doesn't mistake our 'max' CPU type for a real - * one and try to apply errata workarounds or use impdef features we - * don't provide. - * An IMPLEMENTER field of 0 means "reserved for software use"; - * ARCHITECTURE must be 0xf indicating "v7 or later, check ID registers - * to see which features are present"; - * the VARIANT, PARTNUM and REVISION fields are all implementation - * defined and we choose to define PARTNUM just in case guest - * code needs to distinguish this QEMU CPU from other software - * implementations, though this shouldn't be needed. - */ - t = FIELD_DP64(0, MIDR_EL1, IMPLEMENTER, 0); - t = FIELD_DP64(t, MIDR_EL1, ARCHITECTURE, 0xf); - t = FIELD_DP64(t, MIDR_EL1, PARTNUM, 'Q'); - t = FIELD_DP64(t, MIDR_EL1, VARIANT, 0); - t = FIELD_DP64(t, MIDR_EL1, REVISION, 0); - cpu->midr = t; - - /* - * We're going to set FEAT_S2FWB, which mandates that CLIDR_EL1.{LoUU,LoUIS} - * are zero. - */ - u = cpu->clidr; - u = FIELD_DP32(u, CLIDR_EL1, LOUIS, 0); - u = FIELD_DP32(u, CLIDR_EL1, LOUU, 0); - cpu->clidr = u; - - t = cpu->isar.id_aa64isar0; - t = FIELD_DP64(t, ID_AA64ISAR0, AES, 2); /* FEAT_PMULL */ - t = FIELD_DP64(t, ID_AA64ISAR0, SHA1, 1); /* FEAT_SHA1 */ - t = FIELD_DP64(t, ID_AA64ISAR0, SHA2, 2); /* FEAT_SHA512 */ - t = FIELD_DP64(t, ID_AA64ISAR0, CRC32, 1); - t = FIELD_DP64(t, ID_AA64ISAR0, ATOMIC, 2); /* FEAT_LSE */ - t = FIELD_DP64(t, ID_AA64ISAR0, RDM, 1); /* FEAT_RDM */ - t = FIELD_DP64(t, ID_AA64ISAR0, SHA3, 1); /* FEAT_SHA3 */ - t = FIELD_DP64(t, ID_AA64ISAR0, SM3, 1); /* FEAT_SM3 */ - t = FIELD_DP64(t, ID_AA64ISAR0, SM4, 1); /* FEAT_SM4 */ - t = FIELD_DP64(t, ID_AA64ISAR0, DP, 1); /* FEAT_DotProd */ - t = FIELD_DP64(t, ID_AA64ISAR0, FHM, 1); /* FEAT_FHM */ - t = FIELD_DP64(t, ID_AA64ISAR0, TS, 2); /* FEAT_FlagM2 */ - t = FIELD_DP64(t, ID_AA64ISAR0, TLB, 2); /* FEAT_TLBIRANGE */ - t = FIELD_DP64(t, ID_AA64ISAR0, RNDR, 1); /* FEAT_RNG */ - cpu->isar.id_aa64isar0 = t; - - t = cpu->isar.id_aa64isar1; - t = FIELD_DP64(t, ID_AA64ISAR1, DPB, 2); /* FEAT_DPB2 */ - t = FIELD_DP64(t, ID_AA64ISAR1, JSCVT, 1); /* FEAT_JSCVT */ - t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); /* FEAT_FCMA */ - t = FIELD_DP64(t, ID_AA64ISAR1, LRCPC, 2); /* FEAT_LRCPC2 */ - t = FIELD_DP64(t, ID_AA64ISAR1, FRINTTS, 1); /* FEAT_FRINTTS */ - t = FIELD_DP64(t, ID_AA64ISAR1, SB, 1); /* FEAT_SB */ - t = FIELD_DP64(t, ID_AA64ISAR1, SPECRES, 1); /* FEAT_SPECRES */ - t = FIELD_DP64(t, ID_AA64ISAR1, BF16, 1); /* FEAT_BF16 */ - t = FIELD_DP64(t, ID_AA64ISAR1, DGH, 1); /* FEAT_DGH */ - t = FIELD_DP64(t, ID_AA64ISAR1, I8MM, 1); /* FEAT_I8MM */ - cpu->isar.id_aa64isar1 = t; - - t = cpu->isar.id_aa64pfr0; - t = FIELD_DP64(t, ID_AA64PFR0, FP, 1); /* FEAT_FP16 */ - t = FIELD_DP64(t, ID_AA64PFR0, ADVSIMD, 1); /* FEAT_FP16 */ - t = FIELD_DP64(t, ID_AA64PFR0, RAS, 2); /* FEAT_RASv1p1 + FEAT_DoubleFault */ - t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1); - t = FIELD_DP64(t, ID_AA64PFR0, SEL2, 1); /* FEAT_SEL2 */ - t = FIELD_DP64(t, ID_AA64PFR0, DIT, 1); /* FEAT_DIT */ - t = FIELD_DP64(t, ID_AA64PFR0, CSV2, 2); /* FEAT_CSV2_2 */ - t = FIELD_DP64(t, ID_AA64PFR0, CSV3, 1); /* FEAT_CSV3 */ - cpu->isar.id_aa64pfr0 = t; - - t = cpu->isar.id_aa64pfr1; - t = FIELD_DP64(t, ID_AA64PFR1, BT, 1); /* FEAT_BTI */ - t = FIELD_DP64(t, ID_AA64PFR1, SSBS, 2); /* FEAT_SSBS2 */ - /* - * Begin with full support for MTE. This will be downgraded to MTE=0 - * during realize if the board provides no tag memory, much like - * we do for EL2 with the virtualization=on property. - */ - t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3); /* FEAT_MTE3 */ - t = FIELD_DP64(t, ID_AA64PFR1, RAS_FRAC, 0); /* FEAT_RASv1p1 + FEAT_DoubleFault */ - t = FIELD_DP64(t, ID_AA64PFR1, SME, 1); /* FEAT_SME */ - t = FIELD_DP64(t, ID_AA64PFR1, CSV2_FRAC, 0); /* FEAT_CSV2_2 */ - cpu->isar.id_aa64pfr1 = t; - - t = cpu->isar.id_aa64mmfr0; - t = FIELD_DP64(t, ID_AA64MMFR0, PARANGE, 6); /* FEAT_LPA: 52 bits */ - t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN16, 1); /* 16k pages supported */ - t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN16_2, 2); /* 16k stage2 supported */ - t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN64_2, 2); /* 64k stage2 supported */ - t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN4_2, 2); /* 4k stage2 supported */ - t = FIELD_DP64(t, ID_AA64MMFR0, FGT, 1); /* FEAT_FGT */ - cpu->isar.id_aa64mmfr0 = t; - - t = cpu->isar.id_aa64mmfr1; - t = FIELD_DP64(t, ID_AA64MMFR1, HAFDBS, 2); /* FEAT_HAFDBS */ - t = FIELD_DP64(t, ID_AA64MMFR1, VMIDBITS, 2); /* FEAT_VMID16 */ - t = FIELD_DP64(t, ID_AA64MMFR1, VH, 1); /* FEAT_VHE */ - t = FIELD_DP64(t, ID_AA64MMFR1, HPDS, 1); /* FEAT_HPDS */ - t = FIELD_DP64(t, ID_AA64MMFR1, LO, 1); /* FEAT_LOR */ - t = FIELD_DP64(t, ID_AA64MMFR1, PAN, 3); /* FEAT_PAN3 */ - t = FIELD_DP64(t, ID_AA64MMFR1, XNX, 1); /* FEAT_XNX */ - t = FIELD_DP64(t, ID_AA64MMFR1, ETS, 1); /* FEAT_ETS */ - t = FIELD_DP64(t, ID_AA64MMFR1, HCX, 1); /* FEAT_HCX */ - cpu->isar.id_aa64mmfr1 = t; - - t = cpu->isar.id_aa64mmfr2; - t = FIELD_DP64(t, ID_AA64MMFR2, CNP, 1); /* FEAT_TTCNP */ - t = FIELD_DP64(t, ID_AA64MMFR2, UAO, 1); /* FEAT_UAO */ - t = FIELD_DP64(t, ID_AA64MMFR2, IESB, 1); /* FEAT_IESB */ - t = FIELD_DP64(t, ID_AA64MMFR2, VARANGE, 1); /* FEAT_LVA */ - t = FIELD_DP64(t, ID_AA64MMFR2, ST, 1); /* FEAT_TTST */ - t = FIELD_DP64(t, ID_AA64MMFR2, IDS, 1); /* FEAT_IDST */ - t = FIELD_DP64(t, ID_AA64MMFR2, FWB, 1); /* FEAT_S2FWB */ - t = FIELD_DP64(t, ID_AA64MMFR2, TTL, 1); /* FEAT_TTL */ - t = FIELD_DP64(t, ID_AA64MMFR2, BBM, 2); /* FEAT_BBM at level 2 */ - t = FIELD_DP64(t, ID_AA64MMFR2, EVT, 2); /* FEAT_EVT */ - t = FIELD_DP64(t, ID_AA64MMFR2, E0PD, 1); /* FEAT_E0PD */ - cpu->isar.id_aa64mmfr2 = t; - - t = cpu->isar.id_aa64zfr0; - t = FIELD_DP64(t, ID_AA64ZFR0, SVEVER, 1); - t = FIELD_DP64(t, ID_AA64ZFR0, AES, 2); /* FEAT_SVE_PMULL128 */ - t = FIELD_DP64(t, ID_AA64ZFR0, BITPERM, 1); /* FEAT_SVE_BitPerm */ - t = FIELD_DP64(t, ID_AA64ZFR0, BFLOAT16, 1); /* FEAT_BF16 */ - t = FIELD_DP64(t, ID_AA64ZFR0, SHA3, 1); /* FEAT_SVE_SHA3 */ - t = FIELD_DP64(t, ID_AA64ZFR0, SM4, 1); /* FEAT_SVE_SM4 */ - t = FIELD_DP64(t, ID_AA64ZFR0, I8MM, 1); /* FEAT_I8MM */ - t = FIELD_DP64(t, ID_AA64ZFR0, F32MM, 1); /* FEAT_F32MM */ - t = FIELD_DP64(t, ID_AA64ZFR0, F64MM, 1); /* FEAT_F64MM */ - cpu->isar.id_aa64zfr0 = t; - - t = cpu->isar.id_aa64dfr0; - t = FIELD_DP64(t, ID_AA64DFR0, DEBUGVER, 9); /* FEAT_Debugv8p4 */ - t = FIELD_DP64(t, ID_AA64DFR0, PMUVER, 6); /* FEAT_PMUv3p5 */ - cpu->isar.id_aa64dfr0 = t; - - t = cpu->isar.id_aa64smfr0; - t = FIELD_DP64(t, ID_AA64SMFR0, F32F32, 1); /* FEAT_SME */ - t = FIELD_DP64(t, ID_AA64SMFR0, B16F32, 1); /* FEAT_SME */ - t = FIELD_DP64(t, ID_AA64SMFR0, F16F32, 1); /* FEAT_SME */ - t = FIELD_DP64(t, ID_AA64SMFR0, I8I32, 0xf); /* FEAT_SME */ - t = FIELD_DP64(t, ID_AA64SMFR0, F64F64, 1); /* FEAT_SME_F64F64 */ - t = FIELD_DP64(t, ID_AA64SMFR0, I16I64, 0xf); /* FEAT_SME_I16I64 */ - t = FIELD_DP64(t, ID_AA64SMFR0, FA64, 1); /* FEAT_SME_FA64 */ - cpu->isar.id_aa64smfr0 = t; - - /* Replicate the same data to the 32-bit id registers. */ - aa32_max_features(cpu); - -#ifdef CONFIG_USER_ONLY - /* - * For usermode -cpu max we can use a larger and more efficient DCZ - * blocksize since we don't have to follow what the hardware does. - */ - cpu->ctr = 0x80038003; /* 32 byte I and D cacheline size, VIPT icache */ - cpu->dcz_blocksize = 7; /* 512 bytes */ -#endif - - cpu->sve_vq.supported = MAKE_64BIT_MASK(0, ARM_MAX_VQ); - cpu->sme_vq.supported = SVE_VQ_POW2_MAP; - - aarch64_add_pauth_properties(obj); - aarch64_add_sve_properties(obj); - aarch64_add_sme_properties(obj); - object_property_add(obj, "sve-max-vq", "uint32", cpu_max_get_sve_max_vq, - cpu_max_set_sve_max_vq, NULL, NULL); - qdev_property_add_static(DEVICE(obj), &arm_cpu_lpa2_property); -} - static void aarch64_max_initfn(Object *obj) { if (kvm_enabled() || hvf_enabled()) { @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) } static const ARMCPUInfo aarch64_cpus[] = { - { .name = "cortex-a35", .initfn = aarch64_a35_initfn }, { .name = "cortex-a57", .initfn = aarch64_a57_initfn }, { .name = "cortex-a53", .initfn = aarch64_a53_initfn }, - { .name = "cortex-a55", .initfn = aarch64_a55_initfn }, - { .name = "cortex-a72", .initfn = aarch64_a72_initfn }, - { .name = "cortex-a76", .initfn = aarch64_a76_initfn }, - { .name = "a64fx", .initfn = aarch64_a64fx_initfn }, - { .name = "neoverse-n1", .initfn = aarch64_neoverse_n1_initfn }, { .name = "max", .initfn = aarch64_max_initfn }, #if defined(CONFIG_KVM) || defined(CONFIG_HVF) { .name = "host", .initfn = aarch64_host_initfn }, diff --git a/target/arm/cpu64.c b/target/arm/tcg/cpu64.c similarity index 51% copy from target/arm/cpu64.c copy to target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ /* - * QEMU AArch64 CPU + * QEMU AArch64 TCG CPUs * * Copyright (c) 2013 Linaro Ltd * @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" #include "cpu.h" -#include "cpregs.h" #include "qemu/module.h" -#include "sysemu/kvm.h" -#include "sysemu/hvf.h" -#include "sysemu/qtest.h" -#include "sysemu/tcg.h" -#include "kvm_arm.h" -#include "hvf_arm.h" #include "qapi/visitor.h" #include "hw/qdev-properties.h" #include "internals.h" @@ -XXX,XX +XXX,XX @@ static void aarch64_a35_initfn(Object *obj) define_cortex_a72_a57_a53_cp_reginfo(cpu); } -void arm_cpu_sve_finalize(ARMCPU *cpu, Error **errp) -{ - /* - * If any vector lengths are explicitly enabled with sve<N> properties, - * then all other lengths are implicitly disabled. If sve-max-vq is - * specified then it is the same as explicitly enabling all lengths - * up to and including the specified maximum, which means all larger - * lengths will be implicitly disabled. If no sve<N> properties - * are enabled and sve-max-vq is not specified, then all lengths not - * explicitly disabled will be enabled. Additionally, all power-of-two - * vector lengths less than the maximum enabled length will be - * automatically enabled and all vector lengths larger than the largest - * disabled power-of-two vector length will be automatically disabled. - * Errors are generated if the user provided input that interferes with - * any of the above. Finally, if SVE is not disabled, then at least one - * vector length must be enabled. - */ - uint32_t vq_map = cpu->sve_vq.map; - uint32_t vq_init = cpu->sve_vq.init; - uint32_t vq_supported; - uint32_t vq_mask = 0; - uint32_t tmp, vq, max_vq = 0; - - /* - * CPU models specify a set of supported vector lengths which are - * enabled by default. Attempting to enable any vector length not set - * in the supported bitmap results in an error. When KVM is enabled we - * fetch the supported bitmap from the host. - */ - if (kvm_enabled()) { - if (kvm_arm_sve_supported()) { - cpu->sve_vq.supported = kvm_arm_sve_get_vls(CPU(cpu)); - vq_supported = cpu->sve_vq.supported; - } else { - assert(!cpu_isar_feature(aa64_sve, cpu)); - vq_supported = 0; - } - } else { - vq_supported = cpu->sve_vq.supported; - } - - /* - * Process explicit sve<N> properties. - * From the properties, sve_vq_map<N> implies sve_vq_init<N>. - * Check first for any sve<N> enabled. - */ - if (vq_map != 0) { - max_vq = 32 - clz32(vq_map); - vq_mask = MAKE_64BIT_MASK(0, max_vq); - - if (cpu->sve_max_vq && max_vq > cpu->sve_max_vq) { - error_setg(errp, "cannot enable sve%d", max_vq * 128); - error_append_hint(errp, "sve%d is larger than the maximum vector " - "length, sve-max-vq=%d (%d bits)\n", - max_vq * 128, cpu->sve_max_vq, - cpu->sve_max_vq * 128); - return; - } - - if (kvm_enabled()) { - /* - * For KVM we have to automatically enable all supported unitialized - * lengths, even when the smaller lengths are not all powers-of-two. - */ - vq_map |= vq_supported & ~vq_init & vq_mask; - } else { - /* Propagate enabled bits down through required powers-of-two. */ - vq_map |= SVE_VQ_POW2_MAP & ~vq_init & vq_mask; - } - } else if (cpu->sve_max_vq == 0) { - /* - * No explicit bits enabled, and no implicit bits from sve-max-vq. - */ - if (!cpu_isar_feature(aa64_sve, cpu)) { - /* SVE is disabled and so are all vector lengths. Good. */ - return; - } - - if (kvm_enabled()) { - /* Disabling a supported length disables all larger lengths. */ - tmp = vq_init & vq_supported; - } else { - /* Disabling a power-of-two disables all larger lengths. */ - tmp = vq_init & SVE_VQ_POW2_MAP; - } - vq = ctz32(tmp) + 1; - - max_vq = vq <= ARM_MAX_VQ ? vq - 1 : ARM_MAX_VQ; - vq_mask = MAKE_64BIT_MASK(0, max_vq); - vq_map = vq_supported & ~vq_init & vq_mask; - - if (max_vq == 0 || vq_map == 0) { - error_setg(errp, "cannot disable sve%d", vq * 128); - error_append_hint(errp, "Disabling sve%d results in all " - "vector lengths being disabled.\n", - vq * 128); - error_append_hint(errp, "With SVE enabled, at least one " - "vector length must be enabled.\n"); - return; - } - - max_vq = 32 - clz32(vq_map); - vq_mask = MAKE_64BIT_MASK(0, max_vq); - } - - /* - * Process the sve-max-vq property. - * Note that we know from the above that no bit above - * sve-max-vq is currently set. - */ - if (cpu->sve_max_vq != 0) { - max_vq = cpu->sve_max_vq; - vq_mask = MAKE_64BIT_MASK(0, max_vq); - - if (vq_init & ~vq_map & (1 << (max_vq - 1))) { - error_setg(errp, "cannot disable sve%d", max_vq * 128); - error_append_hint(errp, "The maximum vector length must be " - "enabled, sve-max-vq=%d (%d bits)\n", - max_vq, max_vq * 128); - return; - } - - /* Set all bits not explicitly set within sve-max-vq. */ - vq_map |= ~vq_init & vq_mask; - } - - /* - * We should know what max-vq is now. Also, as we're done - * manipulating sve-vq-map, we ensure any bits above max-vq - * are clear, just in case anybody looks. - */ - assert(max_vq != 0); - assert(vq_mask != 0); - vq_map &= vq_mask; - - /* Ensure the set of lengths matches what is supported. */ - tmp = vq_map ^ (vq_supported & vq_mask); - if (tmp) { - vq = 32 - clz32(tmp); - if (vq_map & (1 << (vq - 1))) { - if (cpu->sve_max_vq) { - error_setg(errp, "cannot set sve-max-vq=%d", cpu->sve_max_vq); - error_append_hint(errp, "This CPU does not support " - "the vector length %d-bits.\n", vq * 128); - error_append_hint(errp, "It may not be possible to use " - "sve-max-vq with this CPU. Try " - "using only sve<N> properties.\n"); - } else { - error_setg(errp, "cannot enable sve%d", vq * 128); - if (vq_supported) { - error_append_hint(errp, "This CPU does not support " - "the vector length %d-bits.\n", vq * 128); - } else { - error_append_hint(errp, "SVE not supported by KVM " - "on this host\n"); - } - } - return; - } else { - if (kvm_enabled()) { - error_setg(errp, "cannot disable sve%d", vq * 128); - error_append_hint(errp, "The KVM host requires all " - "supported vector lengths smaller " - "than %d bits to also be enabled.\n", - max_vq * 128); - return; - } else { - /* Ensure all required powers-of-two are enabled. */ - tmp = SVE_VQ_POW2_MAP & vq_mask & ~vq_map; - if (tmp) { - vq = 32 - clz32(tmp); - error_setg(errp, "cannot disable sve%d", vq * 128); - error_append_hint(errp, "sve%d is required as it " - "is a power-of-two length smaller " - "than the maximum, sve%d\n", - vq * 128, max_vq * 128); - return; - } - } - } - } - - /* - * Now that we validated all our vector lengths, the only question - * left to answer is if we even want SVE at all. - */ - if (!cpu_isar_feature(aa64_sve, cpu)) { - error_setg(errp, "cannot enable sve%d", max_vq * 128); - error_append_hint(errp, "SVE must be enabled to enable vector " - "lengths.\n"); - error_append_hint(errp, "Add sve=on to the CPU property list.\n"); - return; - } - - /* From now on sve_max_vq is the actual maximum supported length. */ - cpu->sve_max_vq = max_vq; - cpu->sve_vq.map = vq_map; -} - static void cpu_max_get_sve_max_vq(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) { @@ -XXX,XX +XXX,XX @@ static void cpu_max_set_sve_max_vq(Object *obj, Visitor *v, const char *name, cpu->sve_max_vq = max_vq; } -/* - * Note that cpu_arm_{get,set}_vq cannot use the simpler - * object_property_add_bool interface because they make use of the - * contents of "name" to determine which bit on which to operate. - */ -static void cpu_arm_get_vq(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - ARMCPU *cpu = ARM_CPU(obj); - ARMVQMap *vq_map = opaque; - uint32_t vq = atoi(&name[3]) / 128; - bool sve = vq_map == &cpu->sve_vq; - bool value; - - /* All vector lengths are disabled when feature is off. */ - if (sve - ? !cpu_isar_feature(aa64_sve, cpu) - : !cpu_isar_feature(aa64_sme, cpu)) { - value = false; - } else { - value = extract32(vq_map->map, vq - 1, 1); - } - visit_type_bool(v, name, &value, errp); -} - -static void cpu_arm_set_vq(Object *obj, Visitor *v, const char *name, - void *opaque, Error **errp) -{ - ARMVQMap *vq_map = opaque; - uint32_t vq = atoi(&name[3]) / 128; - bool value; - - if (!visit_type_bool(v, name, &value, errp)) { - return; - } - - vq_map->map = deposit32(vq_map->map, vq - 1, 1, value); - vq_map->init |= 1 << (vq - 1); -} - -static bool cpu_arm_get_sve(Object *obj, Error **errp) -{ - ARMCPU *cpu = ARM_CPU(obj); - return cpu_isar_feature(aa64_sve, cpu); -} - -static void cpu_arm_set_sve(Object *obj, bool value, Error **errp) -{ - ARMCPU *cpu = ARM_CPU(obj); - uint64_t t; - - if (value && kvm_enabled() && !kvm_arm_sve_supported()) { - error_setg(errp, "'sve' feature not supported by KVM on this host"); - return; - } - - t = cpu->isar.id_aa64pfr0; - t = FIELD_DP64(t, ID_AA64PFR0, SVE, value); - cpu->isar.id_aa64pfr0 = t; -} - -void arm_cpu_sme_finalize(ARMCPU *cpu, Error **errp) -{ - uint32_t vq_map = cpu->sme_vq.map; - uint32_t vq_init = cpu->sme_vq.init; - uint32_t vq_supported = cpu->sme_vq.supported; - uint32_t vq; - - if (vq_map == 0) { - if (!cpu_isar_feature(aa64_sme, cpu)) { - cpu->isar.id_aa64smfr0 = 0; - return; - } - - /* TODO: KVM will require limitations via SMCR_EL2. */ - vq_map = vq_supported & ~vq_init; - - if (vq_map == 0) { - vq = ctz32(vq_supported) + 1; - error_setg(errp, "cannot disable sme%d", vq * 128); - error_append_hint(errp, "All SME vector lengths are disabled.\n"); - error_append_hint(errp, "With SME enabled, at least one " - "vector length must be enabled.\n"); - return; - } - } else { - if (!cpu_isar_feature(aa64_sme, cpu)) { - vq = 32 - clz32(vq_map); - error_setg(errp, "cannot enable sme%d", vq * 128); - error_append_hint(errp, "SME must be enabled to enable " - "vector lengths.\n"); - error_append_hint(errp, "Add sme=on to the CPU property list.\n"); - return; - } - /* TODO: KVM will require limitations via SMCR_EL2. */ - } - - cpu->sme_vq.map = vq_map; -} - -static bool cpu_arm_get_sme(Object *obj, Error **errp) -{ - ARMCPU *cpu = ARM_CPU(obj); - return cpu_isar_feature(aa64_sme, cpu); -} - -static void cpu_arm_set_sme(Object *obj, bool value, Error **errp) -{ - ARMCPU *cpu = ARM_CPU(obj); - uint64_t t; - - t = cpu->isar.id_aa64pfr1; - t = FIELD_DP64(t, ID_AA64PFR1, SME, value); - cpu->isar.id_aa64pfr1 = t; -} - -static bool cpu_arm_get_sme_fa64(Object *obj, Error **errp) -{ - ARMCPU *cpu = ARM_CPU(obj); - return cpu_isar_feature(aa64_sme, cpu) && - cpu_isar_feature(aa64_sme_fa64, cpu); -} - -static void cpu_arm_set_sme_fa64(Object *obj, bool value, Error **errp) -{ - ARMCPU *cpu = ARM_CPU(obj); - uint64_t t; - - t = cpu->isar.id_aa64smfr0; - t = FIELD_DP64(t, ID_AA64SMFR0, FA64, value); - cpu->isar.id_aa64smfr0 = t; -} - -#ifdef CONFIG_USER_ONLY -/* Mirror linux /proc/sys/abi/{sve,sme}_default_vector_length. */ -static void cpu_arm_set_default_vec_len(Object *obj, Visitor *v, - const char *name, void *opaque, - Error **errp) -{ - uint32_t *ptr_default_vq = opaque; - int32_t default_len, default_vq, remainder; - - if (!visit_type_int32(v, name, &default_len, errp)) { - return; - } - - /* Undocumented, but the kernel allows -1 to indicate "maximum". */ - if (default_len == -1) { - *ptr_default_vq = ARM_MAX_VQ; - return; - } - - default_vq = default_len / 16; - remainder = default_len % 16; - - /* - * Note that the 512 max comes from include/uapi/asm/sve_context.h - * and is the maximum architectural width of ZCR_ELx.LEN. - */ - if (remainder || default_vq < 1 || default_vq > 512) { - ARMCPU *cpu = ARM_CPU(obj); - const char *which = - (ptr_default_vq == &cpu->sve_default_vq ? "sve" : "sme"); - - error_setg(errp, "cannot set %s-default-vector-length", which); - if (remainder) { - error_append_hint(errp, "Vector length not a multiple of 16\n"); - } else if (default_vq < 1) { - error_append_hint(errp, "Vector length smaller than 16\n"); - } else { - error_append_hint(errp, "Vector length larger than %d\n", - 512 * 16); - } - return; - } - - *ptr_default_vq = default_vq; -} - -static void cpu_arm_get_default_vec_len(Object *obj, Visitor *v, - const char *name, void *opaque, - Error **errp) -{ - uint32_t *ptr_default_vq = opaque; - int32_t value = *ptr_default_vq * 16; - - visit_type_int32(v, name, &value, errp); -} -#endif - -static void aarch64_add_sve_properties(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - uint32_t vq; - - object_property_add_bool(obj, "sve", cpu_arm_get_sve, cpu_arm_set_sve); - - for (vq = 1; vq <= ARM_MAX_VQ; ++vq) { - char name[8]; - sprintf(name, "sve%d", vq * 128); - object_property_add(obj, name, "bool", cpu_arm_get_vq, - cpu_arm_set_vq, NULL, &cpu->sve_vq); - } - -#ifdef CONFIG_USER_ONLY - /* Mirror linux /proc/sys/abi/sve_default_vector_length. */ - object_property_add(obj, "sve-default-vector-length", "int32", - cpu_arm_get_default_vec_len, - cpu_arm_set_default_vec_len, NULL, - &cpu->sve_default_vq); -#endif -} - -static void aarch64_add_sme_properties(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - uint32_t vq; - - object_property_add_bool(obj, "sme", cpu_arm_get_sme, cpu_arm_set_sme); - object_property_add_bool(obj, "sme_fa64", cpu_arm_get_sme_fa64, - cpu_arm_set_sme_fa64); - - for (vq = 1; vq <= ARM_MAX_VQ; vq <<= 1) { - char name[8]; - sprintf(name, "sme%d", vq * 128); - object_property_add(obj, name, "bool", cpu_arm_get_vq, - cpu_arm_set_vq, NULL, &cpu->sme_vq); - } - -#ifdef CONFIG_USER_ONLY - /* Mirror linux /proc/sys/abi/sme_default_vector_length. */ - object_property_add(obj, "sme-default-vector-length", "int32", - cpu_arm_get_default_vec_len, - cpu_arm_set_default_vec_len, NULL, - &cpu->sme_default_vq); -#endif -} - -void arm_cpu_pauth_finalize(ARMCPU *cpu, Error **errp) -{ - int arch_val = 0, impdef_val = 0; - uint64_t t; - - /* Exit early if PAuth is enabled, and fall through to disable it */ - if ((kvm_enabled() || hvf_enabled()) && cpu->prop_pauth) { - if (!cpu_isar_feature(aa64_pauth, cpu)) { - error_setg(errp, "'pauth' feature not supported by %s on this host", - kvm_enabled() ? "KVM" : "hvf"); - } - - return; - } - - /* TODO: Handle HaveEnhancedPAC, HaveEnhancedPAC2, HaveFPAC. */ - if (cpu->prop_pauth) { - if (cpu->prop_pauth_impdef) { - impdef_val = 1; - } else { - arch_val = 1; - } - } else if (cpu->prop_pauth_impdef) { - error_setg(errp, "cannot enable pauth-impdef without pauth"); - error_append_hint(errp, "Add pauth=on to the CPU property list.\n"); - } - - t = cpu->isar.id_aa64isar1; - t = FIELD_DP64(t, ID_AA64ISAR1, APA, arch_val); - t = FIELD_DP64(t, ID_AA64ISAR1, GPA, arch_val); - t = FIELD_DP64(t, ID_AA64ISAR1, API, impdef_val); - t = FIELD_DP64(t, ID_AA64ISAR1, GPI, impdef_val); - cpu->isar.id_aa64isar1 = t; -} - -static Property arm_cpu_pauth_property = - DEFINE_PROP_BOOL("pauth", ARMCPU, prop_pauth, true); -static Property arm_cpu_pauth_impdef_property = - DEFINE_PROP_BOOL("pauth-impdef", ARMCPU, prop_pauth_impdef, false); - -static void aarch64_add_pauth_properties(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - /* Default to PAUTH on, with the architected algorithm on TCG. */ - qdev_property_add_static(DEVICE(obj), &arm_cpu_pauth_property); - if (kvm_enabled() || hvf_enabled()) { - /* - * Mirror PAuth support from the probed sysregs back into the - * property for KVM or hvf. Is it just a bit backward? Yes it is! - * Note that prop_pauth is true whether the host CPU supports the - * architected QARMA5 algorithm or the IMPDEF one. We don't - * provide the separate pauth-impdef property for KVM or hvf, - * only for TCG. - */ - cpu->prop_pauth = cpu_isar_feature(aa64_pauth, cpu); - } else { - qdev_property_add_static(DEVICE(obj), &arm_cpu_pauth_impdef_property); - } -} - static Property arm_cpu_lpa2_property = DEFINE_PROP_BOOL("lpa2", ARMCPU, prop_lpa2, true); -void arm_cpu_lpa2_finalize(ARMCPU *cpu, Error **errp) -{ - uint64_t t; - - /* - * We only install the property for tcg -cpu max; this is the - * only situation in which the cpu field can be true. - */ - if (!cpu->prop_lpa2) { - return; - } - - t = cpu->isar.id_aa64mmfr0; - t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN16, 2); /* 16k pages w/ LPA2 */ - t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN4, 1); /* 4k pages w/ LPA2 */ - t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN16_2, 3); /* 16k stage2 w/ LPA2 */ - t = FIELD_DP64(t, ID_AA64MMFR0, TGRAN4_2, 3); /* 4k stage2 w/ LPA2 */ - cpu->isar.id_aa64mmfr0 = t; -} - -static void aarch64_a57_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "arm,cortex-a57"; - set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); - set_feature(&cpu->env, ARM_FEATURE_AARCH64); - set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_EL2); - set_feature(&cpu->env, ARM_FEATURE_EL3); - set_feature(&cpu->env, ARM_FEATURE_PMU); - cpu->kvm_target = QEMU_KVM_ARM_TARGET_CORTEX_A57; - cpu->midr = 0x411fd070; - cpu->revidr = 0x00000000; - cpu->reset_fpsid = 0x41034070; - cpu->isar.mvfr0 = 0x10110222; - cpu->isar.mvfr1 = 0x12111111; - cpu->isar.mvfr2 = 0x00000043; - cpu->ctr = 0x8444c004; - cpu->reset_sctlr = 0x00c50838; - cpu->isar.id_pfr0 = 0x00000131; - cpu->isar.id_pfr1 = 0x00011011; - cpu->isar.id_dfr0 = 0x03010066; - cpu->id_afr0 = 0x00000000; - cpu->isar.id_mmfr0 = 0x10101105; - cpu->isar.id_mmfr1 = 0x40000000; - cpu->isar.id_mmfr2 = 0x01260000; - cpu->isar.id_mmfr3 = 0x02102211; - cpu->isar.id_isar0 = 0x02101110; - cpu->isar.id_isar1 = 0x13112111; - cpu->isar.id_isar2 = 0x21232042; - cpu->isar.id_isar3 = 0x01112131; - cpu->isar.id_isar4 = 0x00011142; - cpu->isar.id_isar5 = 0x00011121; - cpu->isar.id_isar6 = 0; - cpu->isar.id_aa64pfr0 = 0x00002222; - cpu->isar.id_aa64dfr0 = 0x10305106; - cpu->isar.id_aa64isar0 = 0x00011120; - cpu->isar.id_aa64mmfr0 = 0x00001124; - cpu->isar.dbgdidr = 0x3516d000; - cpu->isar.dbgdevid = 0x01110f13; - cpu->isar.dbgdevid1 = 0x2; - cpu->isar.reset_pmcr_el0 = 0x41013000; - cpu->clidr = 0x0a200023; - cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */ - cpu->ccsidr[1] = 0x201fe012; /* 48KB L1 icache */ - cpu->ccsidr[2] = 0x70ffe07a; /* 2048KB L2 cache */ - cpu->dcz_blocksize = 4; /* 64 bytes */ - cpu->gic_num_lrs = 4; - cpu->gic_vpribits = 5; - cpu->gic_vprebits = 5; - cpu->gic_pribits = 5; - define_cortex_a72_a57_a53_cp_reginfo(cpu); -} - -static void aarch64_a53_initfn(Object *obj) -{ - ARMCPU *cpu = ARM_CPU(obj); - - cpu->dtb_compatible = "arm,cortex-a53"; - set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); - set_feature(&cpu->env, ARM_FEATURE_AARCH64); - set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_EL2); - set_feature(&cpu->env, ARM_FEATURE_EL3); - set_feature(&cpu->env, ARM_FEATURE_PMU); - cpu->kvm_target = QEMU_KVM_ARM_TARGET_CORTEX_A53; - cpu->midr = 0x410fd034; - cpu->revidr = 0x00000000; - cpu->reset_fpsid = 0x41034070; - cpu->isar.mvfr0 = 0x10110222; - cpu->isar.mvfr1 = 0x12111111; - cpu->isar.mvfr2 = 0x00000043; - cpu->ctr = 0x84448004; /* L1Ip = VIPT */ - cpu->reset_sctlr = 0x00c50838; - cpu->isar.id_pfr0 = 0x00000131; - cpu->isar.id_pfr1 = 0x00011011; - cpu->isar.id_dfr0 = 0x03010066; - cpu->id_afr0 = 0x00000000; - cpu->isar.id_mmfr0 = 0x10101105; - cpu->isar.id_mmfr1 = 0x40000000; - cpu->isar.id_mmfr2 = 0x01260000; - cpu->isar.id_mmfr3 = 0x02102211; - cpu->isar.id_isar0 = 0x02101110; - cpu->isar.id_isar1 = 0x13112111; - cpu->isar.id_isar2 = 0x21232042; - cpu->isar.id_isar3 = 0x01112131; - cpu->isar.id_isar4 = 0x00011142; - cpu->isar.id_isar5 = 0x00011121; - cpu->isar.id_isar6 = 0; - cpu->isar.id_aa64pfr0 = 0x00002222; - cpu->isar.id_aa64dfr0 = 0x10305106; - cpu->isar.id_aa64isar0 = 0x00011120; - cpu->isar.id_aa64mmfr0 = 0x00001122; /* 40 bit physical addr */ - cpu->isar.dbgdidr = 0x3516d000; - cpu->isar.dbgdevid = 0x00110f13; - cpu->isar.dbgdevid1 = 0x1; - cpu->isar.reset_pmcr_el0 = 0x41033000; - cpu->clidr = 0x0a200023; - cpu->ccsidr[0] = 0x700fe01a; /* 32KB L1 dcache */ - cpu->ccsidr[1] = 0x201fe00a; /* 32KB L1 icache */ - cpu->ccsidr[2] = 0x707fe07a; /* 1024KB L2 cache */ - cpu->dcz_blocksize = 4; /* 64 bytes */ - cpu->gic_num_lrs = 4; - cpu->gic_vpribits = 5; - cpu->gic_vprebits = 5; - cpu->gic_pribits = 5; - define_cortex_a72_a57_a53_cp_reginfo(cpu); -} - static void aarch64_a55_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); @@ -XXX,XX +XXX,XX @@ static void aarch64_neoverse_n1_initfn(Object *obj) define_neoverse_n1_cp_reginfo(cpu); } -static void aarch64_host_initfn(Object *obj) -{ -#if defined(CONFIG_KVM) - ARMCPU *cpu = ARM_CPU(obj); - kvm_arm_set_cpu_features_from_host(cpu); - if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { - aarch64_add_sve_properties(obj); - aarch64_add_pauth_properties(obj); - } -#elif defined(CONFIG_HVF) - ARMCPU *cpu = ARM_CPU(obj); - hvf_arm_set_cpu_features_from_host(cpu); - aarch64_add_pauth_properties(obj); -#else - g_assert_not_reached(); -#endif -} - /* * -cpu max: a CPU with as many features enabled as our emulation supports. * The version of '-cpu max' for qemu-system-arm is defined in cpu_tcg.c; * this only needs to handle 64 bits. */ -static void aarch64_max_tcg_initfn(Object *obj) +void aarch64_max_tcg_initfn(Object *obj) { ARMCPU *cpu = ARM_CPU(obj); uint64_t t; @@ -XXX,XX +XXX,XX @@ static void aarch64_max_tcg_initfn(Object *obj) qdev_property_add_static(DEVICE(obj), &arm_cpu_lpa2_property); } -static void aarch64_max_initfn(Object *obj) -{ - if (kvm_enabled() || hvf_enabled()) { - /* With KVM or HVF, '-cpu max' is identical to '-cpu host' */ - aarch64_host_initfn(obj); - return; - } - - if (tcg_enabled() || qtest_enabled()) { - aarch64_a57_initfn(obj); - } - - /* '-cpu max' for TCG: we currently do this as "A57 with extra things" */ - if (tcg_enabled()) { - aarch64_max_tcg_initfn(obj); - } -} - static const ARMCPUInfo aarch64_cpus[] = { { .name = "cortex-a35", .initfn = aarch64_a35_initfn }, - { .name = "cortex-a57", .initfn = aarch64_a57_initfn }, - { .name = "cortex-a53", .initfn = aarch64_a53_initfn }, { .name = "cortex-a55", .initfn = aarch64_a55_initfn }, { .name = "cortex-a72", .initfn = aarch64_a72_initfn }, { .name = "cortex-a76", .initfn = aarch64_a76_initfn }, { .name = "a64fx", .initfn = aarch64_a64fx_initfn }, { .name = "neoverse-n1", .initfn = aarch64_neoverse_n1_initfn }, - { .name = "max", .initfn = aarch64_max_initfn }, -#if defined(CONFIG_KVM) || defined(CONFIG_HVF) - { .name = "host", .initfn = aarch64_host_initfn }, -#endif -}; - -static bool aarch64_cpu_get_aarch64(Object *obj, Error **errp) -{ - ARMCPU *cpu = ARM_CPU(obj); - - return arm_feature(&cpu->env, ARM_FEATURE_AARCH64); -} - -static void aarch64_cpu_set_aarch64(Object *obj, bool value, Error **errp) -{ - ARMCPU *cpu = ARM_CPU(obj); - - /* At this time, this property is only allowed if KVM is enabled. This - * restriction allows us to avoid fixing up functionality that assumes a - * uniform execution state like do_interrupt. - */ - if (value == false) { - if (!kvm_enabled() || !kvm_arm_aarch32_supported()) { - error_setg(errp, "'aarch64' feature cannot be disabled " - "unless KVM is enabled and 32-bit EL1 " - "is supported"); - return; - } - unset_feature(&cpu->env, ARM_FEATURE_AARCH64); - } else { - set_feature(&cpu->env, ARM_FEATURE_AARCH64); - } -} - -static void aarch64_cpu_finalizefn(Object *obj) -{ -} - -static gchar *aarch64_gdb_arch_name(CPUState *cs) -{ - return g_strdup("aarch64"); -} - -static void aarch64_cpu_class_init(ObjectClass *oc, void *data) -{ - CPUClass *cc = CPU_CLASS(oc); - - cc->gdb_read_register = aarch64_cpu_gdb_read_register; - cc->gdb_write_register = aarch64_cpu_gdb_write_register; - cc->gdb_num_core_regs = 34; - cc->gdb_core_xml_file = "aarch64-core.xml"; - cc->gdb_arch_name = aarch64_gdb_arch_name; - - object_class_property_add_bool(oc, "aarch64", aarch64_cpu_get_aarch64, - aarch64_cpu_set_aarch64); - object_class_property_set_description(oc, "aarch64", - "Set on/off to enable/disable aarch64 " - "execution state "); -} - -static void aarch64_cpu_instance_init(Object *obj) -{ - ARMCPUClass *acc = ARM_CPU_GET_CLASS(obj); - - acc->info->initfn(obj); - arm_cpu_post_init(obj); -} - -static void cpu_register_class_init(ObjectClass *oc, void *data) -{ - ARMCPUClass *acc = ARM_CPU_CLASS(oc); - - acc->info = data; -} - -void aarch64_cpu_register(const ARMCPUInfo *info) -{ - TypeInfo type_info = { - .parent = TYPE_AARCH64_CPU, - .instance_size = sizeof(ARMCPU), - .instance_init = aarch64_cpu_instance_init, - .class_size = sizeof(ARMCPUClass), - .class_init = info->class_init ?: cpu_register_class_init, - .class_data = (void *)info, - }; - - type_info.name = g_strdup_printf("%s-" TYPE_ARM_CPU, info->name); - type_register(&type_info); - g_free((void *)type_info.name); -} - -static const TypeInfo aarch64_cpu_type_info = { - .name = TYPE_AARCH64_CPU, - .parent = TYPE_ARM_CPU, - .instance_size = sizeof(ARMCPU), - .instance_finalize = aarch64_cpu_finalizefn, - .abstract = true, - .class_size = sizeof(AArch64CPUClass), - .class_init = aarch64_cpu_class_init, }; static void aarch64_cpu_register_types(void) { size_t i; - type_register_static(&aarch64_cpu_type_info); - for (i = 0; i < ARRAY_SIZE(aarch64_cpus); ++i) { aarch64_cpu_register(&aarch64_cpus[i]); } diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/meson.build +++ b/target/arm/tcg/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(files( )) arm_ss.add(when: 'TARGET_AARCH64', if_true: files( + 'cpu64.c', 'translate-a64.c', 'translate-sve.c', 'translate-sme.c', -- 2.34.1 From: Fabiano Rosas <farosas@suse.de> We're about to move the 32-bit CPUs under CONFIG_TCG, so adjust the query-cpu-model-expansion test to check against the cortex-a7, which is already under CONFIG_TCG. That allows the next patch to contain only code movement. (All the test cares about is that the CPU type it's checking is one which definitely doesn't work under KVM.) While here add comments clarifying what we're testing. Signed-off-by: Fabiano Rosas <farosas@suse.de> Acked-by: Thomas Huth <thuth@redhat.com> Message-id: 20230426180013.14814-7-farosas@suse.de Suggested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/arm-cpu-features.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/arm-cpu-features.c +++ b/tests/qtest/arm-cpu-features.c @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion_kvm(const void *data) QDict *resp; char *error; - assert_error(qts, "cortex-a15", - "We cannot guarantee the CPU type 'cortex-a15' works " - "with KVM on this host", NULL); + /* + * When using KVM, only the 'host' and 'max' CPU models are + * supported. Test that we're emitting a suitable error for + * unsupported CPU models. + */ + if (qtest_has_accel("tcg")) { + assert_error(qts, "cortex-a7", + "We cannot guarantee the CPU type 'cortex-a7' works " + "with KVM on this host", NULL); + } else { + /* + * With a KVM-only build the 32-bit CPUs are not present. + */ + assert_error(qts, "cortex-a7", + "The CPU type 'cortex-a7' is not a " + "recognized ARM CPU type", NULL); + } assert_has_feature_enabled(qts, "host", "aarch64"); -- 2.34.1 From: Claudio Fontana <cfontana@suse.de> move the module containing cpu models definitions for 32bit TCG-only CPUs to tcg/ and rename it for clarity. Signed-off-by: Claudio Fontana <cfontana@suse.de> Signed-off-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Acked-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230426180013.14814-8-farosas@suse.de Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/virt.c | 2 -- target/arm/{cpu_tcg.c => tcg/cpu32.c} | 13 +++---------- target/arm/tcg/cpu64.c | 2 +- target/arm/meson.build | 1 - target/arm/tcg/meson.build | 1 + 5 files changed, 5 insertions(+), 14 deletions(-) rename target/arm/{cpu_tcg.c => tcg/cpu32.c} (99%) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static const int a15irqmap[] = { static const char *valid_cpus[] = { #ifdef CONFIG_TCG ARM_CPU_TYPE_NAME("cortex-a7"), -#endif ARM_CPU_TYPE_NAME("cortex-a15"), -#ifdef CONFIG_TCG ARM_CPU_TYPE_NAME("cortex-a35"), ARM_CPU_TYPE_NAME("cortex-a55"), ARM_CPU_TYPE_NAME("cortex-a72"), diff --git a/target/arm/cpu_tcg.c b/target/arm/tcg/cpu32.c similarity index 99% rename from target/arm/cpu_tcg.c rename to target/arm/tcg/cpu32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/tcg/cpu32.c @@ -XXX,XX +XXX,XX @@ /* - * QEMU ARM TCG CPUs. + * QEMU ARM TCG-only CPUs. * * Copyright (c) 2012 SUSE LINUX Products GmbH * @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" -#ifdef CONFIG_TCG #include "hw/core/tcg-cpu-ops.h" -#endif /* CONFIG_TCG */ #include "internals.h" #include "target/arm/idau.h" #if !defined(CONFIG_USER_ONLY) @@ -XXX,XX +XXX,XX @@ void aa32_max_features(ARMCPU *cpu) /* CPU models. These are not needed for the AArch64 linux-user build. */ #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64) -#if !defined(CONFIG_USER_ONLY) && defined(CONFIG_TCG) +#if !defined(CONFIG_USER_ONLY) static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request) { CPUClass *cc = CPU_GET_CLASS(cs); @@ -XXX,XX +XXX,XX @@ static bool arm_v7m_cpu_exec_interrupt(CPUState *cs, int interrupt_request) } return ret; } -#endif /* !CONFIG_USER_ONLY && CONFIG_TCG */ +#endif /* !CONFIG_USER_ONLY */ static void arm926_initfn(Object *obj) { @@ -XXX,XX +XXX,XX @@ static void pxa270c5_initfn(Object *obj) cpu->reset_sctlr = 0x00000078; } -#ifdef CONFIG_TCG static const struct TCGCPUOps arm_v7m_tcg_ops = { .initialize = arm_translate_init, .synchronize_from_tb = arm_cpu_synchronize_from_tb, @@ -XXX,XX +XXX,XX @@ static const struct TCGCPUOps arm_v7m_tcg_ops = { .debug_check_breakpoint = arm_debug_check_breakpoint, #endif /* !CONFIG_USER_ONLY */ }; -#endif /* CONFIG_TCG */ static void arm_v7m_class_init(ObjectClass *oc, void *data) { @@ -XXX,XX +XXX,XX @@ static void arm_v7m_class_init(ObjectClass *oc, void *data) CPUClass *cc = CPU_CLASS(oc); acc->info = data; -#ifdef CONFIG_TCG cc->tcg_ops = &arm_v7m_tcg_ops; -#endif /* CONFIG_TCG */ - cc->gdb_core_xml_file = "arm-m-profile.xml"; } diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_neoverse_n1_initfn(Object *obj) /* * -cpu max: a CPU with as many features enabled as our emulation supports. - * The version of '-cpu max' for qemu-system-arm is defined in cpu_tcg.c; + * The version of '-cpu max' for qemu-system-arm is defined in cpu32.c; * this only needs to handle 64 bits. */ void aarch64_max_tcg_initfn(Object *obj) diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ arm_ss.add(files( 'gdbstub.c', 'helper.c', 'vfp_helper.c', - 'cpu_tcg.c', )) arm_ss.add(zlib) diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/meson.build +++ b/target/arm/tcg/meson.build @@ -XXX,XX +XXX,XX @@ gen = [ arm_ss.add(gen) arm_ss.add(files( + 'cpu32.c', 'translate.c', 'translate-m-nocp.c', 'translate-mve.c', -- 2.34.1 From: Fabiano Rosas <farosas@suse.de> It is possible to have a build with both TCG and KVM disabled due to Xen requiring the i386 and x86_64 binaries to be present in an aarch64 host. If we build with --disable-tcg on the aarch64 host, we will end-up with a QEMU binary (x86) that does not support TCG nor KVM. Skip tests that crash or hang in the above scenario. Do not include any test cases if TCG and KVM are missing. Make sure that calls to qtest_has_accel are placed after g_test_init in similar fashion to commit ae4b01b349 ("tests: Ensure TAP version is printed before other messages") to avoid TAP parsing errors. Reviewed-by: Juan Quintela <quintela@redhat.com> Reviewed-by: Thomas Huth <thuth@redhat.com> Signed-off-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Michael S. Tsirkin <mst@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230426180013.14814-9-farosas@suse.de Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/bios-tables-test.c | 11 +++++++++-- tests/qtest/boot-serial-test.c | 5 +++++ tests/qtest/migration-test.c | 9 ++++++++- tests/qtest/pxe-test.c | 8 +++++++- tests/qtest/vmgenid-test.c | 9 +++++++-- 5 files changed, 36 insertions(+), 6 deletions(-) diff --git a/tests/qtest/bios-tables-test.c b/tests/qtest/bios-tables-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/bios-tables-test.c +++ b/tests/qtest/bios-tables-test.c @@ -XXX,XX +XXX,XX @@ static void test_acpi_virt_oem_fields(void) int main(int argc, char *argv[]) { const char *arch = qtest_get_arch(); - const bool has_kvm = qtest_has_accel("kvm"); - const bool has_tcg = qtest_has_accel("tcg"); + bool has_kvm, has_tcg; char *v_env = getenv("V"); int ret; @@ -XXX,XX +XXX,XX @@ int main(int argc, char *argv[]) g_test_init(&argc, &argv, NULL); + has_kvm = qtest_has_accel("kvm"); + has_tcg = qtest_has_accel("tcg"); + + if (!has_tcg && !has_kvm) { + g_test_skip("No KVM or TCG accelerator available"); + return 0; + } + if (strcmp(arch, "i386") == 0 || strcmp(arch, "x86_64") == 0) { ret = boot_sector_init(disk); if (ret) { diff --git a/tests/qtest/boot-serial-test.c b/tests/qtest/boot-serial-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/boot-serial-test.c +++ b/tests/qtest/boot-serial-test.c @@ -XXX,XX +XXX,XX @@ int main(int argc, char *argv[]) g_test_init(&argc, &argv, NULL); + if (!qtest_has_accel("tcg") && !qtest_has_accel("kvm")) { + g_test_skip("No KVM or TCG accelerator available"); + return 0; + } + for (i = 0; tests[i].arch != NULL; i++) { if (g_str_equal(arch, tests[i].arch) && qtest_has_machine(tests[i].machine)) { diff --git a/tests/qtest/migration-test.c b/tests/qtest/migration-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/migration-test.c +++ b/tests/qtest/migration-test.c @@ -XXX,XX +XXX,XX @@ static bool kvm_dirty_ring_supported(void) int main(int argc, char **argv) { - bool has_kvm; + bool has_kvm, has_tcg; bool has_uffd; const char *arch; g_autoptr(GError) err = NULL; @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) g_test_init(&argc, &argv, NULL); has_kvm = qtest_has_accel("kvm"); + has_tcg = qtest_has_accel("tcg"); + + if (!has_tcg && !has_kvm) { + g_test_skip("No KVM or TCG accelerator available"); + return 0; + } + has_uffd = ufd_version_check(); arch = qtest_get_arch(); diff --git a/tests/qtest/pxe-test.c b/tests/qtest/pxe-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/pxe-test.c +++ b/tests/qtest/pxe-test.c @@ -XXX,XX +XXX,XX @@ int main(int argc, char *argv[]) int ret; const char *arch = qtest_get_arch(); + g_test_init(&argc, &argv, NULL); + + if (!qtest_has_accel("tcg") && !qtest_has_accel("kvm")) { + g_test_skip("No KVM or TCG accelerator available"); + return 0; + } + ret = boot_sector_init(disk); if(ret) return ret; - g_test_init(&argc, &argv, NULL); if (strcmp(arch, "i386") == 0 || strcmp(arch, "x86_64") == 0) { test_batch(x86_tests, false); diff --git a/tests/qtest/vmgenid-test.c b/tests/qtest/vmgenid-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/vmgenid-test.c +++ b/tests/qtest/vmgenid-test.c @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) { int ret; + g_test_init(&argc, &argv, NULL); + + if (!qtest_has_accel("tcg") && !qtest_has_accel("kvm")) { + g_test_skip("No KVM or TCG accelerator available"); + return 0; + } + ret = boot_sector_init(disk); if (ret) { return ret; } - g_test_init(&argc, &argv, NULL); - qtest_add_func("/vmgenid/vmgenid/set-guid", vmgenid_set_guid_test); qtest_add_func("/vmgenid/vmgenid/set-guid-auto", -- 2.34.1 From: Fabiano Rosas <farosas@suse.de> The migration tests are currently broken for an aarch64 host because the tests pass no 'machine' and 'cpu' options on the QEMU command line. Add a separate class to each architecture so that we can specify 'machine' and 'cpu' options instead of relying on defaults. Add a skip decorator to keep the current behavior of only running migration tests when the qemu target matches the host architecture. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Fabiano Rosas <farosas@suse.de> Message-id: 20230426180013.14814-10-farosas@suse.de Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/avocado/migration.py | 83 +++++++++++++++++++++++++++++++++++--- 1 file changed, 78 insertions(+), 5 deletions(-) diff --git a/tests/avocado/migration.py b/tests/avocado/migration.py index XXXXXXX..XXXXXXX 100644 --- a/tests/avocado/migration.py +++ b/tests/avocado/migration.py @@ -XXX,XX +XXX,XX @@ import tempfile +import os + from avocado_qemu import QemuSystemTest from avocado import skipUnless @@ -XXX,XX +XXX,XX @@ from avocado.utils.path import find_command -class Migration(QemuSystemTest): +class MigrationTest(QemuSystemTest): """ :avocado: tags=migration """ @@ -XXX,XX +XXX,XX @@ def _get_free_port(self): self.cancel('Failed to find a free port') return port - - def test_migration_with_tcp_localhost(self): + def migration_with_tcp_localhost(self): dest_uri = 'tcp:localhost:%u' % self._get_free_port() self.do_migrate(dest_uri) - def test_migration_with_unix(self): + def migration_with_unix(self): with tempfile.TemporaryDirectory(prefix='socket_') as socket_path: dest_uri = 'unix:%s/qemu-test.sock' % socket_path self.do_migrate(dest_uri) @skipUnless(find_command('nc', default=False), "'nc' command not found") - def test_migration_with_exec(self): + def migration_with_exec(self): """The test works for both netcat-traditional and netcat-openbsd packages.""" free_port = self._get_free_port() dest_uri = 'exec:nc -l localhost %u' % free_port src_uri = 'exec:nc localhost %u' % free_port self.do_migrate(dest_uri, src_uri) + + +@skipUnless('aarch64' in os.uname()[4], "host != target") +class Aarch64(MigrationTest): + """ + :avocado: tags=arch:aarch64 + :avocado: tags=machine:virt + :avocado: tags=cpu:max + """ + + def test_migration_with_tcp_localhost(self): + self.migration_with_tcp_localhost() + + def test_migration_with_unix(self): + self.migration_with_unix() + + def test_migration_with_exec(self): + self.migration_with_exec() + + +@skipUnless('x86_64' in os.uname()[4], "host != target") +class X86_64(MigrationTest): + """ + :avocado: tags=arch:x86_64 + :avocado: tags=machine:pc + :avocado: tags=cpu:qemu64 + """ + + def test_migration_with_tcp_localhost(self): + self.migration_with_tcp_localhost() + + def test_migration_with_unix(self): + self.migration_with_unix() + + def test_migration_with_exec(self): + self.migration_with_exec() + + +@skipUnless('ppc64le' in os.uname()[4], "host != target") +class PPC64(MigrationTest): + """ + :avocado: tags=arch:ppc64 + :avocado: tags=machine:pseries + :avocado: tags=cpu:power9_v2.0 + """ + + def test_migration_with_tcp_localhost(self): + self.migration_with_tcp_localhost() + + def test_migration_with_unix(self): + self.migration_with_unix() + + def test_migration_with_exec(self): + self.migration_with_exec() + + +@skipUnless('s390x' in os.uname()[4], "host != target") +class S390X(MigrationTest): + """ + :avocado: tags=arch:s390x + :avocado: tags=machine:s390-ccw-virtio + :avocado: tags=cpu:qemu + """ + + def test_migration_with_tcp_localhost(self): + self.migration_with_tcp_localhost() + + def test_migration_with_unix(self): + self.migration_with_unix() + + def test_migration_with_exec(self): + self.migration_with_exec() -- 2.34.1 From: Fabiano Rosas <farosas@suse.de> We are about to enable the build without TCG, so CONFIG_SEMIHOSTING and CONFIG_ARM_COMPATIBLE_SEMIHOSTING cannot be unconditionally set in default.mak anymore. So reflect the change in a Kconfig. Instead of using semihosting/Kconfig, use a target-specific file, so that the change doesn't affect other architectures which might implement semihosting in a way compatible with KVM. The selection from ARM_v7M needs to be removed to avoid a cycle during parsing. Signed-off-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230426180013.14814-11-farosas@suse.de Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- configs/devices/arm-softmmu/default.mak | 2 -- hw/arm/Kconfig | 1 - target/arm/Kconfig | 7 +++++++ 3 files changed, 7 insertions(+), 3 deletions(-) diff --git a/configs/devices/arm-softmmu/default.mak b/configs/devices/arm-softmmu/default.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/devices/arm-softmmu/default.mak +++ b/configs/devices/arm-softmmu/default.mak @@ -XXX,XX +XXX,XX @@ CONFIG_MICROBIT=y CONFIG_FSL_IMX25=y CONFIG_FSL_IMX7=y CONFIG_FSL_IMX6UL=y -CONFIG_SEMIHOSTING=y -CONFIG_ARM_COMPATIBLE_SEMIHOSTING=y CONFIG_ALLWINNER_H3=y 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 ARM_V7M # currently v7M must be included in a TCG build due to translate.c default y if TCG && (ARM || AARCH64) select PTIMER - select ARM_COMPATIBLE_SEMIHOSTING config ALLWINNER_A10 bool diff --git a/target/arm/Kconfig b/target/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/target/arm/Kconfig +++ b/target/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config ARM config AARCH64 bool select ARM + +# This config exists just so we can make SEMIHOSTING default when TCG +# is selected without also changing it for other architectures. +config ARM_SEMIHOSTING + bool + default y if TCG && ARM + select ARM_COMPATIBLE_SEMIHOSTING -- 2.34.1 From: Fabiano Rosas <farosas@suse.de> Move all the CONFIG_FOO=y from default.mak into "default y if TCG" statements in Kconfig. That way they won't be selected when CONFIG_TCG=n. I'm leaving CONFIG_ARM_VIRT in default.mak because it allows us to keep the two default.mak files not empty and keep aarch64-default.mak including arm-default.mak. That way we don't surprise anyone that's used to altering these files. With this change we can start building with --disable-tcg. Signed-off-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230426180013.14814-12-farosas@suse.de Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- configs/devices/aarch64-softmmu/default.mak | 4 -- configs/devices/arm-softmmu/default.mak | 37 ------------------ hw/arm/Kconfig | 42 ++++++++++++++++++++- 3 files changed, 41 insertions(+), 42 deletions(-) diff --git a/configs/devices/aarch64-softmmu/default.mak b/configs/devices/aarch64-softmmu/default.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/devices/aarch64-softmmu/default.mak +++ b/configs/devices/aarch64-softmmu/default.mak @@ -XXX,XX +XXX,XX @@ # We support all the 32 bit boards so need all their config include ../arm-softmmu/default.mak - -CONFIG_XLNX_ZYNQMP_ARM=y -CONFIG_XLNX_VERSAL=y -CONFIG_SBSA_REF=y diff --git a/configs/devices/arm-softmmu/default.mak b/configs/devices/arm-softmmu/default.mak index XXXXXXX..XXXXXXX 100644 --- a/configs/devices/arm-softmmu/default.mak +++ b/configs/devices/arm-softmmu/default.mak @@ -XXX,XX +XXX,XX @@ # CONFIG_TEST_DEVICES=n CONFIG_ARM_VIRT=y -CONFIG_CUBIEBOARD=y -CONFIG_EXYNOS4=y -CONFIG_HIGHBANK=y -CONFIG_INTEGRATOR=y -CONFIG_FSL_IMX31=y -CONFIG_MUSICPAL=y -CONFIG_MUSCA=y -CONFIG_CHEETAH=y -CONFIG_SX1=y -CONFIG_NSERIES=y -CONFIG_STELLARIS=y -CONFIG_STM32VLDISCOVERY=y -CONFIG_REALVIEW=y -CONFIG_VERSATILE=y -CONFIG_VEXPRESS=y -CONFIG_ZYNQ=y -CONFIG_MAINSTONE=y -CONFIG_GUMSTIX=y -CONFIG_SPITZ=y -CONFIG_TOSA=y -CONFIG_Z2=y -CONFIG_NPCM7XX=y -CONFIG_COLLIE=y -CONFIG_ASPEED_SOC=y -CONFIG_NETDUINO2=y -CONFIG_NETDUINOPLUS2=y -CONFIG_OLIMEX_STM32_H405=y -CONFIG_MPS2=y -CONFIG_RASPI=y -CONFIG_DIGIC=y -CONFIG_SABRELITE=y -CONFIG_EMCRAFT_SF2=y -CONFIG_MICROBIT=y -CONFIG_FSL_IMX25=y -CONFIG_FSL_IMX7=y -CONFIG_FSL_IMX6UL=y -CONFIG_ALLWINNER_H3=y 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 ARM_VIRT config CHEETAH bool + default y if TCG && ARM select OMAP select TSC210X config CUBIEBOARD bool + default y if TCG && ARM select ALLWINNER_A10 config DIGIC bool + default y if TCG && ARM select PTIMER select PFLASH_CFI02 config EXYNOS4 bool + default y if TCG && ARM imply I2C_DEVICES select A9MPCORE select I2C @@ -XXX,XX +XXX,XX @@ config EXYNOS4 config HIGHBANK bool + default y if TCG && ARM select A9MPCORE select A15MPCORE select AHCI @@ -XXX,XX +XXX,XX @@ config HIGHBANK config INTEGRATOR bool + default y if TCG && ARM select ARM_TIMER select INTEGRATOR_DEBUG select PL011 # UART @@ -XXX,XX +XXX,XX @@ config INTEGRATOR config MAINSTONE bool + default y if TCG && ARM select PXA2XX select PFLASH_CFI01 select SMC91C111 config MUSCA bool + default y if TCG && ARM select ARMSSE select PL011 select PL031 @@ -XXX,XX +XXX,XX @@ config MARVELL_88W8618 config MUSICPAL bool + default y if TCG && ARM select OR_IRQ select BITBANG_I2C select MARVELL_88W8618 @@ -XXX,XX +XXX,XX @@ config MUSICPAL config NETDUINO2 bool + default y if TCG && ARM select STM32F205_SOC config NETDUINOPLUS2 bool + default y if TCG && ARM select STM32F405_SOC config OLIMEX_STM32_H405 bool + default y if TCG && ARM select STM32F405_SOC config NSERIES bool + default y if TCG && ARM select OMAP select TMP105 # temperature sensor select BLIZZARD # LCD/TV controller @@ -XXX,XX +XXX,XX @@ config PXA2XX config GUMSTIX bool + default y if TCG && ARM select PFLASH_CFI01 select SMC91C111 select PXA2XX config TOSA bool + default y if TCG && ARM select ZAURUS # scoop select MICRODRIVE select PXA2XX @@ -XXX,XX +XXX,XX @@ config TOSA config SPITZ bool + default y if TCG && ARM select ADS7846 # touch-screen controller select MAX111X # A/D converter select WM8750 # audio codec @@ -XXX,XX +XXX,XX @@ config SPITZ config Z2 bool + default y if TCG && ARM select PFLASH_CFI01 select WM8750 select PL011 # UART @@ -XXX,XX +XXX,XX @@ config Z2 config REALVIEW bool + default y if TCG && ARM imply PCI_DEVICES imply PCI_TESTDEV imply I2C_DEVICES @@ -XXX,XX +XXX,XX @@ config REALVIEW config SBSA_REF bool + default y if TCG && AARCH64 imply PCI_DEVICES select AHCI select ARM_SMMUV3 @@ -XXX,XX +XXX,XX @@ config SBSA_REF config SABRELITE bool + default y if TCG && ARM select FSL_IMX6 select SSI_M25P80 config STELLARIS bool + default y if TCG && ARM imply I2C_DEVICES select ARM_V7M select CMSDK_APB_WATCHDOG @@ -XXX,XX +XXX,XX @@ config STELLARIS config STM32VLDISCOVERY bool + default y if TCG && ARM select STM32F100_SOC config STRONGARM @@ -XXX,XX +XXX,XX @@ config STRONGARM config COLLIE bool + default y if TCG && ARM select PFLASH_CFI01 select ZAURUS # scoop select STRONGARM config SX1 bool + default y if TCG && ARM select OMAP config VERSATILE bool + default y if TCG && ARM select ARM_TIMER # sp804 select PFLASH_CFI01 select LSI_SCSI_PCI @@ -XXX,XX +XXX,XX @@ config VERSATILE config VEXPRESS bool + default y if TCG && ARM select A9MPCORE select A15MPCORE select ARM_MPTIMER @@ -XXX,XX +XXX,XX @@ config VEXPRESS config ZYNQ bool + default y if TCG && ARM select A9MPCORE select CADENCE # UART select PFLASH_CFI02 @@ -XXX,XX +XXX,XX @@ config ZYNQ config ARM_V7M bool # currently v7M must be included in a TCG build due to translate.c - default y if TCG && (ARM || AARCH64) + default y if TCG && ARM select PTIMER config ALLWINNER_A10 @@ -XXX,XX +XXX,XX @@ config ALLWINNER_A10 config ALLWINNER_H3 bool + default y if TCG && ARM select ALLWINNER_A10_PIT select ALLWINNER_SUN8I_EMAC select ALLWINNER_I2C @@ -XXX,XX +XXX,XX @@ config ALLWINNER_H3 config RASPI bool + default y if TCG && ARM select FRAMEBUFFER select PL011 # UART select SDHCI @@ -XXX,XX +XXX,XX @@ config STM32F405_SOC config XLNX_ZYNQMP_ARM bool + default y if TCG && AARCH64 select AHCI select ARM_GIC select CADENCE @@ -XXX,XX +XXX,XX @@ config XLNX_ZYNQMP_ARM config XLNX_VERSAL bool + default y if TCG && AARCH64 select ARM_GIC select PL011 select CADENCE @@ -XXX,XX +XXX,XX @@ config XLNX_VERSAL config NPCM7XX bool + default y if TCG && ARM select A9MPCORE select ADM1272 select ARM_GIC @@ -XXX,XX +XXX,XX @@ config NPCM7XX config FSL_IMX25 bool + default y if TCG && ARM imply I2C_DEVICES select IMX select IMX_FEC @@ -XXX,XX +XXX,XX @@ config FSL_IMX25 config FSL_IMX31 bool + default y if TCG && ARM imply I2C_DEVICES select SERIAL select IMX @@ -XXX,XX +XXX,XX @@ config FSL_IMX6 config ASPEED_SOC bool + default y if TCG && ARM select DS1338 select FTGMAC100 select I2C @@ -XXX,XX +XXX,XX @@ config ASPEED_SOC config MPS2 bool + default y if TCG && ARM imply I2C_DEVICES select ARMSSE select LAN9118 @@ -XXX,XX +XXX,XX @@ config MPS2 config FSL_IMX7 bool + default y if TCG && ARM imply PCI_DEVICES imply TEST_DEVICES imply I2C_DEVICES @@ -XXX,XX +XXX,XX @@ config ARM_SMMUV3 config FSL_IMX6UL bool + default y if TCG && ARM imply I2C_DEVICES select A15MPCORE select IMX @@ -XXX,XX +XXX,XX @@ config FSL_IMX6UL config MICROBIT bool + default y if TCG && ARM select NRF51_SOC config NRF51_SOC @@ -XXX,XX +XXX,XX @@ config NRF51_SOC config EMCRAFT_SF2 bool + default y if TCG && ARM select MSF2 select SSI_M25P80 -- 2.34.1 From: Fabiano Rosas <farosas@suse.de> The test set -accel tcg, so restrict it to when TCG is present. Signed-off-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230426180013.14814-13-farosas@suse.de Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/meson.build | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qtests_aarch64 = \ ['tpm-tis-device-test', 'tpm-tis-device-swtpm-test'] : []) + \ (config_all_devices.has_key('CONFIG_XLNX_ZYNQMP_ARM') ? ['xlnx-can-test', 'fuzz-xlnx-dp-test'] : []) + \ (config_all_devices.has_key('CONFIG_RASPI') ? ['bcm2835-dma-test'] : []) + \ - (config_all_devices.has_key('CONFIG_TPM_TIS_I2C') ? ['tpm-tis-i2c-test'] : []) + \ + (config_all.has_key('CONFIG_TCG') and \ + config_all_devices.has_key('CONFIG_TPM_TIS_I2C') ? ['tpm-tis-i2c-test'] : []) + \ ['arm-cpu-features', 'numa-test', 'boot-serial-test', -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Add a manual new job to cross-build the aarch64 target with only the KVM accelerator enabled (in particular, no TCG). Re-enable running the similar job on the project Aarch64 custom runner. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Fabiano Rosas <farosas@suse.de> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230426180013.14814-14-farosas@suse.de Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- .gitlab-ci.d/crossbuilds.yml | 11 +++++++++++ .gitlab-ci.d/custom-runners/ubuntu-22.04-aarch64.yml | 4 ---- 2 files changed, 11 insertions(+), 4 deletions(-) diff --git a/.gitlab-ci.d/crossbuilds.yml b/.gitlab-ci.d/crossbuilds.yml index XXXXXXX..XXXXXXX 100644 --- a/.gitlab-ci.d/crossbuilds.yml +++ b/.gitlab-ci.d/crossbuilds.yml @@ -XXX,XX +XXX,XX @@ cross-arm64-xen-only: IMAGE: debian-arm64-cross ACCEL: xen EXTRA_CONFIGURE_OPTS: --disable-tcg --disable-kvm + +# Similar job is run by qemu-project's custom runner by default +cross-arm64-kvm-only: + extends: .cross_accel_build_job + needs: + job: arm64-debian-cross-container + variables: + QEMU_JOB_OPTIONAL: 1 + IMAGE: debian-arm64-cross + ACCEL: kvm + EXTRA_CONFIGURE_OPTS: --disable-tcg --disable-xen --without-default-devices diff --git a/.gitlab-ci.d/custom-runners/ubuntu-22.04-aarch64.yml b/.gitlab-ci.d/custom-runners/ubuntu-22.04-aarch64.yml index XXXXXXX..XXXXXXX 100644 --- a/.gitlab-ci.d/custom-runners/ubuntu-22.04-aarch64.yml +++ b/.gitlab-ci.d/custom-runners/ubuntu-22.04-aarch64.yml @@ -XXX,XX +XXX,XX @@ ubuntu-22.04-aarch64-notcg: - aarch64 rules: - if: '$CI_PROJECT_NAMESPACE == "qemu-project" && $CI_COMMIT_BRANCH =~ /^staging/' - when: manual - allow_failure: true - if: "$AARCH64_RUNNER_AVAILABLE" - when: manual - allow_failure: true script: - mkdir build - cd build -- 2.34.1 From: Patrick Venture <venture@google.com> The MAC address set from Qemu wasn't being saved into the register space. Reviewed-by: Hao Wu <wuhaotsh@google.com> Signed-off-by: Patrick Venture <venture@google.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: moved variable declaration to top of function] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/npcm7xx_emc.c | 32 +++++++++++++++++++++++++------- 1 file changed, 25 insertions(+), 7 deletions(-) diff --git a/hw/net/npcm7xx_emc.c b/hw/net/npcm7xx_emc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/npcm7xx_emc.c +++ b/hw/net/npcm7xx_emc.c @@ -XXX,XX +XXX,XX @@ static const char *emc_reg_name(int regno) static void emc_reset(NPCM7xxEMCState *emc) { + uint32_t value; + trace_npcm7xx_emc_reset(emc->emc_num); memset(&emc->regs[0], 0, sizeof(emc->regs)); @@ -XXX,XX +XXX,XX @@ static void emc_reset(NPCM7xxEMCState *emc) emc->tx_active = false; emc->rx_active = false; + + /* Set the MAC address in the register space. */ + value = (emc->conf.macaddr.a[0] << 24) | + (emc->conf.macaddr.a[1] << 16) | + (emc->conf.macaddr.a[2] << 8) | + emc->conf.macaddr.a[3]; + emc->regs[REG_CAMM_BASE] = value; + + value = (emc->conf.macaddr.a[4] << 24) | (emc->conf.macaddr.a[5] << 16); + emc->regs[REG_CAML_BASE] = value; } static void npcm7xx_emc_reset(DeviceState *dev) @@ -XXX,XX +XXX,XX @@ static bool emc_receive_filter1(NPCM7xxEMCState *emc, const uint8_t *buf, } case ETH_PKT_UCAST: { bool matches; + uint32_t value; + struct MACAddr mac; if (emc->regs[REG_CAMCMR] & REG_CAMCMR_AUP) { return true; } + + value = emc->regs[REG_CAMM_BASE]; + mac.a[0] = value >> 24; + mac.a[1] = value >> 16; + mac.a[2] = value >> 8; + mac.a[3] = value >> 0; + value = emc->regs[REG_CAML_BASE]; + mac.a[4] = value >> 24; + mac.a[5] = value >> 16; + matches = ((emc->regs[REG_CAMCMR] & REG_CAMCMR_ECMP) && /* We only support one CAM register, CAM0. */ (emc->regs[REG_CAMEN] & (1 << 0)) && - memcmp(buf, emc->conf.macaddr.a, ETH_ALEN) == 0); + memcmp(buf, mac.a, ETH_ALEN) == 0); if (emc->regs[REG_CAMCMR] & REG_CAMCMR_CCAM) { *fail_reason = "MACADDR matched, comparison complemented"; return !matches; @@ -XXX,XX +XXX,XX @@ static void npcm7xx_emc_write(void *opaque, hwaddr offset, break; case REG_CAMM_BASE + 0: emc->regs[reg] = value; - emc->conf.macaddr.a[0] = value >> 24; - emc->conf.macaddr.a[1] = value >> 16; - emc->conf.macaddr.a[2] = value >> 8; - emc->conf.macaddr.a[3] = value >> 0; break; case REG_CAML_BASE + 0: emc->regs[reg] = value; - emc->conf.macaddr.a[4] = value >> 24; - emc->conf.macaddr.a[5] = value >> 16; break; case REG_MCMDR: { uint32_t prev; -- 2.34.1 From: Daniel Bertalan <dani@danielbertalan.dev> This query copies the kernel command line into the message buffer. It was previously stubbed out to return empty, this commit makes it reflect the arguments specified with `-append`. I observed the following peculiarities on my Pi 3B+: - If the buffer is shorter than the string, the response header gives the full length, but no data is actually copied. - No NUL terminator is added: even if the buffer is long enough to fit one, the buffer's original contents are preserved past the string's end. - The VC firmware adds the following extra parameters beside the user-supplied ones (via /boot/cmdline.txt): `video`, `vc_mem.mem_base` and `vc_mem.mem_size`. This is currently not implemented in qemu. Signed-off-by: Daniel Bertalan <dani@danielbertalan.dev> Message-id: 20230425103250.56653-1-dani@danielbertalan.dev Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: added comment about NUL and short-buffer behaviour] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/bcm2835_property.h | 1 + hw/arm/bcm2835_peripherals.c | 2 ++ hw/arm/bcm2836.c | 2 ++ hw/arm/raspi.c | 2 ++ hw/misc/bcm2835_property.c | 13 ++++++++++++- 5 files changed, 19 insertions(+), 1 deletion(-) diff --git a/include/hw/misc/bcm2835_property.h b/include/hw/misc/bcm2835_property.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/bcm2835_property.h +++ b/include/hw/misc/bcm2835_property.h @@ -XXX,XX +XXX,XX @@ struct BCM2835PropertyState { MACAddr macaddr; uint32_t board_rev; uint32_t addr; + char *command_line; bool pending; }; diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj) TYPE_BCM2835_PROPERTY); object_property_add_alias(obj, "board-rev", OBJECT(&s->property), "board-rev"); + object_property_add_alias(obj, "command-line", OBJECT(&s->property), + "command-line"); object_property_add_const_link(OBJECT(&s->property), "fb", OBJECT(&s->fb)); diff --git a/hw/arm/bcm2836.c b/hw/arm/bcm2836.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2836.c +++ b/hw/arm/bcm2836.c @@ -XXX,XX +XXX,XX @@ static void bcm2836_init(Object *obj) TYPE_BCM2835_PERIPHERALS); object_property_add_alias(obj, "board-rev", OBJECT(&s->peripherals), "board-rev"); + object_property_add_alias(obj, "command-line", OBJECT(&s->peripherals), + "command-line"); object_property_add_alias(obj, "vcram-size", OBJECT(&s->peripherals), "vcram-size"); } diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/raspi.c +++ b/hw/arm/raspi.c @@ -XXX,XX +XXX,XX @@ static void raspi_machine_init(MachineState *machine) object_property_add_const_link(OBJECT(&s->soc), "ram", OBJECT(machine->ram)); object_property_set_int(OBJECT(&s->soc), "board-rev", board_rev, &error_abort); + object_property_set_str(OBJECT(&s->soc), "command-line", + machine->kernel_cmdline, &error_abort); qdev_realize(DEVICE(&s->soc), NULL, &error_fatal); /* Create and plug in the SD cards */ diff --git a/hw/misc/bcm2835_property.c b/hw/misc/bcm2835_property.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/bcm2835_property.c +++ b/hw/misc/bcm2835_property.c @@ -XXX,XX +XXX,XX @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value) break; case 0x00050001: /* Get command line */ - resplen = 0; + /* + * We follow the firmware behaviour: no NUL terminator is + * written to the buffer, and if the buffer is too short + * we report the required length in the response header + * and copy nothing to the buffer. + */ + resplen = strlen(s->command_line); + if (bufsize >= resplen) + address_space_write(&s->dma_as, value + 12, + MEMTXATTRS_UNSPECIFIED, s->command_line, + resplen); break; default: @@ -XXX,XX +XXX,XX @@ static void bcm2835_property_realize(DeviceState *dev, Error **errp) static Property bcm2835_property_props[] = { DEFINE_PROP_UINT32("board-rev", BCM2835PropertyState, board_rev, 0), + DEFINE_PROP_STRING("command-line", BCM2835PropertyState, command_line), DEFINE_PROP_END_OF_LIST() }; -- 2.34.1 This commit adds 'one-insn-per-tb' as a property on the TCG accelerator object, so you can enable it with -accel tcg,one-insn-per-tb=on It has the same behaviour as the existing '-singlestep' command line option. We use a different name because 'singlestep' has always been a confusing choice, because it doesn't have anything to do with single-stepping the CPU. What it does do is force TCG emulation to put one guest instruction in each TB, which can be useful in some situations (such as analysing debug logs). The existing '-singlestep' commandline options are decoupled from the global 'singlestep' variable and instead now are syntactic sugar for setting the accel property. (These can then go away after a deprecation period.) The global variable remains for the moment as: * what the TCG code looks at to change its behaviour * what HMP and QMP use to query and set the behaviour In the following commits we'll clean those up to not directly look at the global variable. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230417164041.684562-2-peter.maydell@linaro.org --- accel/tcg/tcg-all.c | 21 +++++++++++++++++++++ bsd-user/main.c | 8 ++++++-- linux-user/main.c | 8 ++++++-- softmmu/vl.c | 17 +++++++++++++++-- qemu-options.hx | 7 +++++++ 5 files changed, 55 insertions(+), 6 deletions(-) diff --git a/accel/tcg/tcg-all.c b/accel/tcg/tcg-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tcg-all.c +++ b/accel/tcg/tcg-all.c @@ -XXX,XX +XXX,XX @@ struct TCGState { AccelState parent_obj; bool mttcg_enabled; + bool one_insn_per_tb; int splitwx_enabled; unsigned long tb_size; }; @@ -XXX,XX +XXX,XX @@ static void tcg_set_splitwx(Object *obj, bool value, Error **errp) s->splitwx_enabled = value; } +static bool tcg_get_one_insn_per_tb(Object *obj, Error **errp) +{ + TCGState *s = TCG_STATE(obj); + return s->one_insn_per_tb; +} + +static void tcg_set_one_insn_per_tb(Object *obj, bool value, Error **errp) +{ + TCGState *s = TCG_STATE(obj); + s->one_insn_per_tb = value; + /* For the moment, set the global also: this changes the behaviour */ + singlestep = value; +} + static int tcg_gdbstub_supported_sstep_flags(void) { /* @@ -XXX,XX +XXX,XX @@ static void tcg_accel_class_init(ObjectClass *oc, void *data) tcg_get_splitwx, tcg_set_splitwx); object_class_property_set_description(oc, "split-wx", "Map jit pages into separate RW and RX regions"); + + object_class_property_add_bool(oc, "one-insn-per-tb", + tcg_get_one_insn_per_tb, + tcg_set_one_insn_per_tb); + object_class_property_set_description(oc, "one-insn-per-tb", + "Only put one guest insn in each translation block"); } static const TypeInfo tcg_accel_type = { diff --git a/bsd-user/main.c b/bsd-user/main.c index XXXXXXX..XXXXXXX 100644 --- a/bsd-user/main.c +++ b/bsd-user/main.c @@ -XXX,XX +XXX,XX @@ #include "target_arch_cpu.h" int singlestep; +static bool opt_one_insn_per_tb; uintptr_t guest_base; bool have_guest_base; /* @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) } else if (!strcmp(r, "seed")) { seed_optarg = optarg; } else if (!strcmp(r, "singlestep")) { - singlestep = 1; + opt_one_insn_per_tb = true; } else if (!strcmp(r, "strace")) { do_strace = 1; } else if (!strcmp(r, "trace")) { @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) /* init tcg before creating CPUs and to get qemu_host_page_size */ { - AccelClass *ac = ACCEL_GET_CLASS(current_accel()); + AccelState *accel = current_accel(); + AccelClass *ac = ACCEL_GET_CLASS(accel); accel_init_interfaces(ac); + object_property_set_bool(OBJECT(accel), "one-insn-per-tb", + opt_one_insn_per_tb, &error_abort); ac->init_machine(NULL); } cpu = cpu_create(cpu_type); diff --git a/linux-user/main.c b/linux-user/main.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/main.c +++ b/linux-user/main.c @@ -XXX,XX +XXX,XX @@ char *exec_path; char real_exec_path[PATH_MAX]; int singlestep; +static bool opt_one_insn_per_tb; static const char *argv0; static const char *gdbstub; static envlist_t *envlist; @@ -XXX,XX +XXX,XX @@ static void handle_arg_reserved_va(const char *arg) static void handle_arg_singlestep(const char *arg) { - singlestep = 1; + opt_one_insn_per_tb = true; } static void handle_arg_strace(const char *arg) @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv, char **envp) /* init tcg before creating CPUs and to get qemu_host_page_size */ { - AccelClass *ac = ACCEL_GET_CLASS(current_accel()); + AccelState *accel = current_accel(); + AccelClass *ac = ACCEL_GET_CLASS(accel); accel_init_interfaces(ac); + object_property_set_bool(OBJECT(accel), "one-insn-per-tb", + opt_one_insn_per_tb, &error_abort); ac->init_machine(NULL); } cpu = cpu_create(cpu_type); diff --git a/softmmu/vl.c b/softmmu/vl.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/vl.c +++ b/softmmu/vl.c @@ -XXX,XX +XXX,XX @@ static const char *log_file; static bool list_data_dirs; static const char *qtest_chrdev; static const char *qtest_log; +static bool opt_one_insn_per_tb; static int has_defaults = 1; static int default_serial = 1; @@ -XXX,XX +XXX,XX @@ static int do_configure_accelerator(void *opaque, QemuOpts *opts, Error **errp) qemu_opt_foreach(opts, accelerator_set_property, accel, &error_fatal); - + /* + * If legacy -singlestep option is set, honour it for TCG and + * silently ignore for any other accelerator (which is how this + * option has always behaved). + */ + if (opt_one_insn_per_tb) { + /* + * This will always succeed for TCG, and we want to ignore + * the error from trying to set a nonexistent property + * on any other accelerator. + */ + object_property_set_bool(OBJECT(accel), "one-insn-per-tb", true, NULL); + } ret = accel_init_machine(accel, current_machine); if (ret < 0) { if (!qtest_with_kvm || ret != -ENOENT) { @@ -XXX,XX +XXX,XX @@ void qemu_init(int argc, char **argv) qdict_put_str(machine_opts_dict, "firmware", optarg); break; case QEMU_OPTION_singlestep: - singlestep = 1; + opt_one_insn_per_tb = true; break; case QEMU_OPTION_S: autostart = 0; diff --git a/qemu-options.hx b/qemu-options.hx index XXXXXXX..XXXXXXX 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -XXX,XX +XXX,XX @@ DEF("accel", HAS_ARG, QEMU_OPTION_accel, " igd-passthru=on|off (enable Xen integrated Intel graphics passthrough, default=off)\n" " kernel-irqchip=on|off|split controls accelerated irqchip support (default=on)\n" " kvm-shadow-mem=size of KVM shadow MMU in bytes\n" + " one-insn-per-tb=on|off (one guest instruction per TCG translation block)\n" " split-wx=on|off (enable TCG split w^x mapping)\n" " tb-size=n (TCG translation block cache size)\n" " dirty-ring-size=n (KVM dirty ring GFN count, default 0)\n" @@ -XXX,XX +XXX,XX @@ SRST ``kvm-shadow-mem=size`` Defines the size of the KVM shadow MMU. + ``one-insn-per-tb=on|off`` + Makes the TCG accelerator put only one guest instruction into + each translation block. This slows down emulation a lot, but + can be useful in some situations, such as when trying to analyse + the logs produced by the ``-d`` option. + ``split-wx=on|off`` Controls the use of split w^x mapping for the TCG code generation buffer. Some operating systems require this to be enabled, and in -- 2.34.1 The HMP 'singlestep' command, the QMP 'query-status' command and the HMP 'info status' command (which is just wrapping the QMP command implementation) look at the 'singlestep' global variable. Make them access the new TCG accelerator 'one-insn-per-tb' property instead. This leaves the HMP and QMP command/field names and output strings unchanged; we will clean that up later. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230417164041.684562-3-peter.maydell@linaro.org --- softmmu/runstate-hmp-cmds.c | 18 ++++++++++++++++-- softmmu/runstate.c | 10 +++++++++- 2 files changed, 25 insertions(+), 3 deletions(-) diff --git a/softmmu/runstate-hmp-cmds.c b/softmmu/runstate-hmp-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/runstate-hmp-cmds.c +++ b/softmmu/runstate-hmp-cmds.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "qapi/qapi-commands-run-state.h" #include "qapi/qmp/qdict.h" +#include "qemu/accel.h" void hmp_info_status(Monitor *mon, const QDict *qdict) { @@ -XXX,XX +XXX,XX @@ void hmp_info_status(Monitor *mon, const QDict *qdict) void hmp_singlestep(Monitor *mon, const QDict *qdict) { const char *option = qdict_get_try_str(qdict, "option"); + AccelState *accel = current_accel(); + bool newval; + + if (!object_property_find(OBJECT(accel), "one-insn-per-tb")) { + monitor_printf(mon, + "This accelerator does not support setting one-insn-per-tb\n"); + return; + } + if (!option || !strcmp(option, "on")) { - singlestep = 1; + newval = true; } else if (!strcmp(option, "off")) { - singlestep = 0; + newval = false; } else { monitor_printf(mon, "unexpected option %s\n", option); + return; } + /* If the property exists then setting it can never fail */ + object_property_set_bool(OBJECT(accel), "one-insn-per-tb", + newval, &error_abort); } void hmp_watchdog_action(Monitor *mon, const QDict *qdict) diff --git a/softmmu/runstate.c b/softmmu/runstate.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/runstate.c +++ b/softmmu/runstate.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "qapi/qapi-commands-run-state.h" #include "qapi/qapi-events-run-state.h" +#include "qemu/accel.h" #include "qemu/error-report.h" #include "qemu/job.h" #include "qemu/log.h" @@ -XXX,XX +XXX,XX @@ bool runstate_needs_reset(void) StatusInfo *qmp_query_status(Error **errp) { StatusInfo *info = g_malloc0(sizeof(*info)); + AccelState *accel = current_accel(); + /* + * We ignore errors, which will happen if the accelerator + * is not TCG. "singlestep" is meaningless for other accelerators, + * so we will set the StatusInfo field to false for those. + */ + info->singlestep = object_property_get_bool(OBJECT(accel), + "one-insn-per-tb", NULL); info->running = runstate_is_running(); - info->singlestep = singlestep; info->status = current_run_state; return info; -- 2.34.1 The only place left that looks at the old 'singlestep' global variable is the TCG curr_cflags() function. Replace the old global with a new 'one_insn_per_tb' which is defined in tcg-all.c and declared in accel/tcg/internal.h. This keeps it restricted to the TCG code, unlike 'singlestep' which was available to every file in the system and defined in multiple different places for softmmu vs linux-user vs bsd-user. While we're making this change, use qatomic_read() and qatomic_set() on the accesses to the new global, because TCG will read it without holding a lock. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230417164041.684562-4-peter.maydell@linaro.org --- accel/tcg/internal.h | 2 ++ include/exec/cpu-common.h | 2 -- accel/tcg/cpu-exec.c | 2 +- accel/tcg/tcg-all.c | 6 ++++-- bsd-user/main.c | 1 - linux-user/main.c | 1 - softmmu/globals.c | 1 - 7 files changed, 7 insertions(+), 8 deletions(-) diff --git a/accel/tcg/internal.h b/accel/tcg/internal.h index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/internal.h +++ b/accel/tcg/internal.h @@ -XXX,XX +XXX,XX @@ static inline target_ulong log_pc(CPUState *cpu, const TranslationBlock *tb) extern int64_t max_delay; extern int64_t max_advance; +extern bool one_insn_per_tb; + #endif /* ACCEL_TCG_INTERNAL_H */ diff --git a/include/exec/cpu-common.h b/include/exec/cpu-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-common.h +++ b/include/exec/cpu-common.h @@ -XXX,XX +XXX,XX @@ int cpu_memory_rw_debug(CPUState *cpu, vaddr addr, void *ptr, size_t len, bool is_write); /* vl.c */ -extern int singlestep; - void list_cpus(void); #endif /* CPU_COMMON_H */ diff --git a/accel/tcg/cpu-exec.c b/accel/tcg/cpu-exec.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cpu-exec.c +++ b/accel/tcg/cpu-exec.c @@ -XXX,XX +XXX,XX @@ uint32_t curr_cflags(CPUState *cpu) */ if (unlikely(cpu->singlestep_enabled)) { cflags |= CF_NO_GOTO_TB | CF_NO_GOTO_PTR | CF_SINGLE_STEP | 1; - } else if (singlestep) { + } else if (qatomic_read(&one_insn_per_tb)) { cflags |= CF_NO_GOTO_TB | 1; } else if (qemu_loglevel_mask(CPU_LOG_TB_NOCHAIN)) { cflags |= CF_NO_GOTO_TB; diff --git a/accel/tcg/tcg-all.c b/accel/tcg/tcg-all.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/tcg-all.c +++ b/accel/tcg/tcg-all.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "qemu/error-report.h" #include "qemu/accel.h" +#include "qemu/atomic.h" #include "qapi/qapi-builtin-visit.h" #include "qemu/units.h" #if !defined(CONFIG_USER_ONLY) @@ -XXX,XX +XXX,XX @@ static void tcg_accel_instance_init(Object *obj) } bool mttcg_enabled; +bool one_insn_per_tb; static int tcg_init_machine(MachineState *ms) { @@ -XXX,XX +XXX,XX @@ static void tcg_set_one_insn_per_tb(Object *obj, bool value, Error **errp) { TCGState *s = TCG_STATE(obj); s->one_insn_per_tb = value; - /* For the moment, set the global also: this changes the behaviour */ - singlestep = value; + /* Set the global also: this changes the behaviour */ + qatomic_set(&one_insn_per_tb, value); } static int tcg_gdbstub_supported_sstep_flags(void) diff --git a/bsd-user/main.c b/bsd-user/main.c index XXXXXXX..XXXXXXX 100644 --- a/bsd-user/main.c +++ b/bsd-user/main.c @@ -XXX,XX +XXX,XX @@ #include "host-os.h" #include "target_arch_cpu.h" -int singlestep; static bool opt_one_insn_per_tb; uintptr_t guest_base; bool have_guest_base; diff --git a/linux-user/main.c b/linux-user/main.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/main.c +++ b/linux-user/main.c @@ -XXX,XX +XXX,XX @@ char *exec_path; char real_exec_path[PATH_MAX]; -int singlestep; static bool opt_one_insn_per_tb; static const char *argv0; static const char *gdbstub; diff --git a/softmmu/globals.c b/softmmu/globals.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/globals.c +++ b/softmmu/globals.c @@ -XXX,XX +XXX,XX @@ int vga_interface_type = VGA_NONE; bool vga_interface_created; Chardev *parallel_hds[MAX_PARALLEL_PORTS]; int win2k_install_hack; -int singlestep; int fd_bootchk = 1; int graphic_rotate; QEMUOptionRom option_rom[MAX_OPTION_ROMS]; -- 2.34.1 The '-singlestep' option is confusing, because it doesn't actually have anything to do with single-stepping the CPU. What it does do is force TCG emulation to put one guest instruction in each TB, which can be useful in some situations. Create a new command line argument -one-insn-per-tb, so we can document that -singlestep is just a deprecated synonym for it, and eventually perhaps drop it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Warner Losh <imp@bsdimp.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230417164041.684562-5-peter.maydell@linaro.org --- docs/user/main.rst | 7 ++++++- linux-user/main.c | 9 ++++++--- 2 files changed, 12 insertions(+), 4 deletions(-) diff --git a/docs/user/main.rst b/docs/user/main.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/user/main.rst +++ b/docs/user/main.rst @@ -XXX,XX +XXX,XX @@ Debug options: ``-g port`` Wait gdb connection to port +``-one-insn-per-tb`` + Run the emulation with one guest instruction per translation block. + This slows down emulation a lot, but can be useful in some situations, + such as when trying to analyse the logs produced by the ``-d`` option. + ``-singlestep`` - Run the emulation in single step mode. + This is a deprecated synonym for the ``-one-insn-per-tb`` option. Environment variables: diff --git a/linux-user/main.c b/linux-user/main.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/main.c +++ b/linux-user/main.c @@ -XXX,XX +XXX,XX @@ static void handle_arg_reserved_va(const char *arg) reserved_va = val ? val - 1 : 0; } -static void handle_arg_singlestep(const char *arg) +static void handle_arg_one_insn_per_tb(const char *arg) { opt_one_insn_per_tb = true; } @@ -XXX,XX +XXX,XX @@ static const struct qemu_argument arg_table[] = { "logfile", "write logs to 'logfile' (default stderr)"}, {"p", "QEMU_PAGESIZE", true, handle_arg_pagesize, "pagesize", "set the host page size to 'pagesize'"}, - {"singlestep", "QEMU_SINGLESTEP", false, handle_arg_singlestep, - "", "run in singlestep mode"}, + {"one-insn-per-tb", + "QEMU_ONE_INSN_PER_TB", false, handle_arg_one_insn_per_tb, + "", "run with one guest instruction per emulated TB"}, + {"singlestep", "QEMU_SINGLESTEP", false, handle_arg_one_insn_per_tb, + "", "deprecated synonym for -one-insn-per-tb"}, {"strace", "QEMU_STRACE", false, handle_arg_strace, "", "log system calls"}, {"seed", "QEMU_RAND_SEED", true, handle_arg_seed, -- 2.34.1 The '-singlestep' option is confusing, because it doesn't actually have anything to do with single-stepping the CPU. What it does do is force TCG emulation to put one guest instruction in each TB, which can be useful in some situations. Create a new command line argument -one-insn-per-tb, so we can document that -singlestep is just a deprecated synonym for it, and eventually perhaps drop it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Warner Losh <imp@bsdimp.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230417164041.684562-6-peter.maydell@linaro.org --- docs/user/main.rst | 7 ++++++- bsd-user/main.c | 5 +++-- 2 files changed, 9 insertions(+), 3 deletions(-) diff --git a/docs/user/main.rst b/docs/user/main.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/user/main.rst +++ b/docs/user/main.rst @@ -XXX,XX +XXX,XX @@ Debug options: ``-p pagesize`` Act as if the host page size was 'pagesize' bytes +``-one-insn-per-tb`` + Run the emulation with one guest instruction per translation block. + This slows down emulation a lot, but can be useful in some situations, + such as when trying to analyse the logs produced by the ``-d`` option. + ``-singlestep`` - Run the emulation in single step mode. + This is a deprecated synonym for the ``-one-insn-per-tb`` option. diff --git a/bsd-user/main.c b/bsd-user/main.c index XXXXXXX..XXXXXXX 100644 --- a/bsd-user/main.c +++ b/bsd-user/main.c @@ -XXX,XX +XXX,XX @@ static void usage(void) "-d item1[,...] enable logging of specified items\n" " (use '-d help' for a list of log items)\n" "-D logfile write logs to 'logfile' (default stderr)\n" - "-singlestep always run in singlestep mode\n" + "-one-insn-per-tb run with one guest instruction per emulated TB\n" + "-singlestep deprecated synonym for -one-insn-per-tb\n" "-strace log system calls\n" "-trace [[enable=]<pattern>][,events=<file>][,file=<file>]\n" " specify tracing options\n" @@ -XXX,XX +XXX,XX @@ int main(int argc, char **argv) (void) envlist_unsetenv(envlist, "LD_PRELOAD"); } else if (!strcmp(r, "seed")) { seed_optarg = optarg; - } else if (!strcmp(r, "singlestep")) { + } else if (!strcmp(r, "singlestep") || !strcmp(r, "one-insn-per-tb")) { opt_one_insn_per_tb = true; } else if (!strcmp(r, "strace")) { do_strace = 1; -- 2.34.1 Document that the -singlestep command line option is now deprecated, as it is replaced by either the TCG accelerator property 'one-insn-per-tb' for system emulation or the new '-one-insn-per-tb' option for usermode emulation, and remove the only use of the deprecated syntax from a README. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230417164041.684562-7-peter.maydell@linaro.org --- docs/about/deprecated.rst | 16 ++++++++++++++++ qemu-options.hx | 5 +++-- tcg/tci/README | 2 +- 3 files changed, 20 insertions(+), 3 deletions(-) diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -XXX,XX +XXX,XX @@ Use ``-machine acpi=off`` instead. The HAXM project has been retired (see https://github.com/intel/haxm#status). Use "whpx" (on Windows) or "hvf" (on macOS) instead. +``-singlestep`` (since 8.1) +''''''''''''''''''''''''''' + +The ``-singlestep`` option has been turned into an accelerator property, +and given a name that better reflects what it actually does. +Use ``-accel tcg,one-insn-per-tb=on`` instead. + +User-mode emulator command line arguments +----------------------------------------- + +``-singlestep`` (since 8.1) +''''''''''''''''''''''''''' + +The ``-singlestep`` option has been given a name that better reflects +what it actually does. For both linux-user and bsd-user, use the +new ``-one-insn-per-tb`` option instead. QEMU Machine Protocol (QMP) commands ------------------------------------ diff --git a/qemu-options.hx b/qemu-options.hx index XXXXXXX..XXXXXXX 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -XXX,XX +XXX,XX @@ SRST ERST DEF("singlestep", 0, QEMU_OPTION_singlestep, \ - "-singlestep always run in singlestep mode\n", QEMU_ARCH_ALL) + "-singlestep deprecated synonym for -accel tcg,one-insn-per-tb=on\n", QEMU_ARCH_ALL) SRST ``-singlestep`` - Run the emulation in single step mode. + This is a deprecated synonym for the TCG accelerator property + ``one-insn-per-tb``. ERST DEF("preconfig", 0, QEMU_OPTION_preconfig, \ diff --git a/tcg/tci/README b/tcg/tci/README index XXXXXXX..XXXXXXX 100644 --- a/tcg/tci/README +++ b/tcg/tci/README @@ -XXX,XX +XXX,XX @@ The only difference from running QEMU with TCI to running without TCI should be speed. Especially during development of TCI, it was very useful to compare runs with and without TCI. Create /tmp/qemu.log by - qemu-system-i386 -d in_asm,op_opt,cpu -D /tmp/qemu.log -singlestep + qemu-system-i386 -d in_asm,op_opt,cpu -D /tmp/qemu.log -accel tcg,one-insn-per-tb=on once with interpreter and once without interpreter and compare the resulting qemu.log files. This is also useful to see the effects of additional -- 2.34.1 Currently we report whether the TCG accelerator is in 'one-insn-per-tb' mode in the 'info status' output. This is a pretty minor piece of TCG specific information, and we want to deprecate the 'singlestep' field of the associated QMP command. Move the 'one-insn-per-tb' reporting to 'info jit'. We don't need a deprecate-and-drop period for this because the HMP interface has no stability guarantees. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230417164041.684562-8-peter.maydell@linaro.org --- accel/tcg/monitor.c | 14 ++++++++++++++ softmmu/runstate-hmp-cmds.c | 5 ++--- 2 files changed, 16 insertions(+), 3 deletions(-) diff --git a/accel/tcg/monitor.c b/accel/tcg/monitor.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/monitor.c +++ b/accel/tcg/monitor.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/accel.h" #include "qapi/error.h" #include "qapi/type-helpers.h" #include "qapi/qapi-commands-machine.h" @@ -XXX,XX +XXX,XX @@ static void dump_drift_info(GString *buf) } } +static void dump_accel_info(GString *buf) +{ + AccelState *accel = current_accel(); + bool one_insn_per_tb = object_property_get_bool(OBJECT(accel), + "one-insn-per-tb", + &error_fatal); + + g_string_append_printf(buf, "Accelerator settings:\n"); + g_string_append_printf(buf, "one-insn-per-tb: %s\n\n", + one_insn_per_tb ? "on" : "off"); +} + HumanReadableText *qmp_x_query_jit(Error **errp) { g_autoptr(GString) buf = g_string_new(""); @@ -XXX,XX +XXX,XX @@ HumanReadableText *qmp_x_query_jit(Error **errp) return NULL; } + dump_accel_info(buf); dump_exec_info(buf); dump_drift_info(buf); diff --git a/softmmu/runstate-hmp-cmds.c b/softmmu/runstate-hmp-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/runstate-hmp-cmds.c +++ b/softmmu/runstate-hmp-cmds.c @@ -XXX,XX +XXX,XX @@ void hmp_info_status(Monitor *mon, const QDict *qdict) info = qmp_query_status(NULL); - monitor_printf(mon, "VM status: %s%s", - info->running ? "running" : "paused", - info->singlestep ? " (single step mode)" : ""); + monitor_printf(mon, "VM status: %s", + info->running ? "running" : "paused"); if (!info->running && info->status != RUN_STATE_PAUSED) { monitor_printf(mon, " (%s)", RunState_str(info->status)); -- 2.34.1 The 'singlestep' HMP command is confusing, because it doesn't actually have anything to do with single-stepping the CPU. What it does do is force TCG emulation to put one guest instruction in each TB, which can be useful in some situations. Create a new HMP command 'one-insn-per-tb', so we can document that 'singlestep' is just a deprecated synonym for it, and eventually perhaps drop it. We aren't obliged to do deprecate-and-drop for HMP commands, but it's easy enough to do so, so we do. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230417164041.684562-9-peter.maydell@linaro.org --- docs/about/deprecated.rst | 9 +++++++++ include/monitor/hmp.h | 2 +- softmmu/runstate-hmp-cmds.c | 2 +- tests/qtest/test-hmp.c | 1 + hmp-commands.hx | 25 +++++++++++++++++++++---- 5 files changed, 33 insertions(+), 6 deletions(-) diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -XXX,XX +XXX,XX @@ accepted incorrect commands will return an error. Users should make sure that all arguments passed to ``device_add`` are consistent with the documented property types. +Human Monitor Protocol (HMP) commands +------------------------------------- + +``singlestep`` (since 8.1) +'''''''''''''''''''''''''' + +The ``singlestep`` command has been replaced by the ``one-insn-per-tb`` +command, which has the same behaviour but a less misleading name. + Host Architectures ------------------ diff --git a/include/monitor/hmp.h b/include/monitor/hmp.h index XXXXXXX..XXXXXXX 100644 --- a/include/monitor/hmp.h +++ b/include/monitor/hmp.h @@ -XXX,XX +XXX,XX @@ void hmp_info_vcpu_dirty_limit(Monitor *mon, const QDict *qdict); void hmp_human_readable_text_helper(Monitor *mon, HumanReadableText *(*qmp_handler)(Error **)); void hmp_info_stats(Monitor *mon, const QDict *qdict); -void hmp_singlestep(Monitor *mon, const QDict *qdict); +void hmp_one_insn_per_tb(Monitor *mon, const QDict *qdict); void hmp_watchdog_action(Monitor *mon, const QDict *qdict); void hmp_pcie_aer_inject_error(Monitor *mon, const QDict *qdict); void hmp_info_capture(Monitor *mon, const QDict *qdict); diff --git a/softmmu/runstate-hmp-cmds.c b/softmmu/runstate-hmp-cmds.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/runstate-hmp-cmds.c +++ b/softmmu/runstate-hmp-cmds.c @@ -XXX,XX +XXX,XX @@ void hmp_info_status(Monitor *mon, const QDict *qdict) qapi_free_StatusInfo(info); } -void hmp_singlestep(Monitor *mon, const QDict *qdict) +void hmp_one_insn_per_tb(Monitor *mon, const QDict *qdict) { const char *option = qdict_get_try_str(qdict, "option"); AccelState *accel = current_accel(); diff --git a/tests/qtest/test-hmp.c b/tests/qtest/test-hmp.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/test-hmp.c +++ b/tests/qtest/test-hmp.c @@ -XXX,XX +XXX,XX @@ static const char *hmp_cmds[] = { "o /w 0 0x1234", "object_add memory-backend-ram,id=mem1,size=256M", "object_del mem1", + "one-insn-per-tb on", "pmemsave 0 4096 \"/dev/null\"", "p $pc + 8", "qom-list /", diff --git a/hmp-commands.hx b/hmp-commands.hx index XXXXXXX..XXXXXXX 100644 --- a/hmp-commands.hx +++ b/hmp-commands.hx @@ -XXX,XX +XXX,XX @@ SRST only *tag* as parameter. ERST + { + .name = "one-insn-per-tb", + .args_type = "option:s?", + .params = "[on|off]", + .help = "run emulation with one guest instruction per translation block", + .cmd = hmp_one_insn_per_tb, + }, + +SRST +``one-insn-per-tb [off]`` + Run the emulation with one guest instruction per translation block. + This slows down emulation a lot, but can be useful in some situations, + such as when trying to analyse the logs produced by the ``-d`` option. + This only has an effect when using TCG, not with KVM or other accelerators. + + If called with option off, the emulation returns to normal mode. +ERST + { .name = "singlestep", .args_type = "option:s?", .params = "[on|off]", - .help = "run emulation in singlestep mode or switch to normal mode", - .cmd = hmp_singlestep, + .help = "deprecated synonym for one-insn-per-tb", + .cmd = hmp_one_insn_per_tb, }, SRST ``singlestep [off]`` - Run the emulation in single step mode. - If called with option off, the emulation returns to normal mode. + This is a deprecated synonym for the one-insn-per-tb command. ERST { -- 2.34.1 The run-state.json file is missing a trailing newline; add it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230417164041.684562-10-peter.maydell@linaro.org --- qapi/run-state.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/qapi/run-state.json b/qapi/run-state.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/run-state.json +++ b/qapi/run-state.json @@ -XXX,XX +XXX,XX @@ # Since: 7.2 ## { 'enum': 'NotifyVmexitOption', - 'data': [ 'run', 'internal-error', 'disable' ] } \ No newline at end of file + 'data': [ 'run', 'internal-error', 'disable' ] } -- 2.34.1 The 'singlestep' member of StatusInfo has never done what the QMP documentation claims it does. What it actually reports is whether TCG is working in "one guest instruction per translation block" mode. We no longer need this field for the HMP 'info status' command, as we've moved that information to 'info jit'. It seems unlikely that anybody is monitoring the state of this obscure TCG setting via QMP, especially since QMP provides no means for changing the setting. So simply deprecate the field, without providing any replacement. Until we do eventually delete the member, correct the misstatements in the QAPI documentation about it. If we do find that there are users for this, then the most likely way we would provide replacement access to the information would be to put the accelerator QOM object at a well-known path such as /machine/accel, which could then be used with the existing qom-set and qom-get commands. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Markus Armbruster <armbru@redhat.com> Message-id: 20230417164041.684562-11-peter.maydell@linaro.org --- docs/about/deprecated.rst | 14 ++++++++++++++ qapi/run-state.json | 14 +++++++++++--- 2 files changed, 25 insertions(+), 3 deletions(-) diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -XXX,XX +XXX,XX @@ accepted incorrect commands will return an error. Users should make sure that all arguments passed to ``device_add`` are consistent with the documented property types. +``StatusInfo`` member ``singlestep`` (since 8.1) +'''''''''''''''''''''''''''''''''''''''''''''''' + +The ``singlestep`` member of the ``StatusInfo`` returned from the +``query-status`` command is deprecated. This member has a confusing +name and it never did what the documentation claimed or what its name +suggests. We do not believe that anybody is actually using the +information provided in this member. + +The information it reports is whether the TCG JIT is in "one +instruction per translated block" mode (which can be set on the +command line or via the HMP, but not via QMP). The information remains +available via the HMP 'info jit' command. + Human Monitor Protocol (HMP) commands ------------------------------------- diff --git a/qapi/run-state.json b/qapi/run-state.json index XXXXXXX..XXXXXXX 100644 --- a/qapi/run-state.json +++ b/qapi/run-state.json @@ -XXX,XX +XXX,XX @@ # # @running: true if all VCPUs are runnable, false if not runnable # -# @singlestep: true if VCPUs are in single-step mode +# @singlestep: true if using TCG with one guest instruction +# per translation block # # @status: the virtual machine @RunState # +# Features: +# @deprecated: Member 'singlestep' is deprecated (with no replacement). +# # Since: 0.14 # -# Notes: @singlestep is enabled through the GDB stub +# Notes: @singlestep is enabled on the command line with +# '-accel tcg,one-insn-per-tb=on', or with the HMP +# 'one-insn-per-tb' command. ## { 'struct': 'StatusInfo', - 'data': {'running': 'bool', 'singlestep': 'bool', 'status': 'RunState'} } + 'data': {'running': 'bool', + 'singlestep': { 'type': 'bool', 'features': [ 'deprecated' ]}, + 'status': 'RunState'} } ## # @query-status: -- 2.34.1 In commit 5242876f37ca we deprecated the dtb-kaslr-seed property of the virt board, but forgot the "since n.n" tag in the documentation of this in deprecated.rst. This deprecation note first appeared in the 7.1 release, so retrospectively add the correct "since 7.1" annotation to it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20230420122256.1023709-1-peter.maydell@linaro.org --- docs/about/deprecated.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -XXX,XX +XXX,XX @@ Use the more generic event ``DEVICE_UNPLUG_GUEST_ERROR`` instead. System emulator machines ------------------------ -Arm ``virt`` machine ``dtb-kaslr-seed`` property -'''''''''''''''''''''''''''''''''''''''''''''''' +Arm ``virt`` machine ``dtb-kaslr-seed`` property (since 7.1) +'''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' The ``dtb-kaslr-seed`` property on the ``virt`` board has been deprecated; use the new name ``dtb-randomness`` instead. The new name -- 2.34.1 The msf2-emac ethernet controller has functions emac_load_desc() and emac_store_desc() which read and write the in-memory descriptor blocks and handle conversion between guest and host endianness. As currently written, emac_store_desc() does the endianness conversion in-place; this means that it effectively consumes the input EmacDesc struct, because on a big-endian host the fields will be overwritten with the little-endian versions of their values. Unfortunately, in all the callsites the code continues to access fields in the EmacDesc struct after it has called emac_store_desc() -- specifically, it looks at the d.next field. The effect of this is that on a big-endian host networking doesn't work because the address of the next descriptor is corrupted. We could fix this by making the callsite avoid using the struct; but it's more robust to have emac_store_desc() leave its input alone. (emac_load_desc() also does an in-place conversion, but here this is fine, because the function is supposed to be initializing the struct.) Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20230424151919.1333299-1-peter.maydell@linaro.org --- hw/net/msf2-emac.c | 16 ++++++++++------ 1 file changed, 10 insertions(+), 6 deletions(-) diff --git a/hw/net/msf2-emac.c b/hw/net/msf2-emac.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/msf2-emac.c +++ b/hw/net/msf2-emac.c @@ -XXX,XX +XXX,XX @@ static void emac_load_desc(MSF2EmacState *s, EmacDesc *d, hwaddr desc) d->next = le32_to_cpu(d->next); } -static void emac_store_desc(MSF2EmacState *s, EmacDesc *d, hwaddr desc) +static void emac_store_desc(MSF2EmacState *s, const EmacDesc *d, hwaddr desc) { - /* Convert from host endianness into LE. */ - d->pktaddr = cpu_to_le32(d->pktaddr); - d->pktsize = cpu_to_le32(d->pktsize); - d->next = cpu_to_le32(d->next); + EmacDesc outd; + /* + * Convert from host endianness into LE. We use a local struct because + * calling code may still want to look at the fields afterwards. + */ + outd.pktaddr = cpu_to_le32(d->pktaddr); + outd.pktsize = cpu_to_le32(d->pktsize); + outd.next = cpu_to_le32(d->next); - address_space_write(&s->dma_as, desc, MEMTXATTRS_UNSPECIFIED, d, sizeof *d); + address_space_write(&s->dma_as, desc, MEMTXATTRS_UNSPECIFIED, &outd, sizeof outd); } static void msf2_dma_tx(MSF2EmacState *s) -- 2.34.1 From: Cédric Le Goater <clg@kaod.org> The arm boot.c code includes a utility function write_bootloader() which assists in writing a boot-code fragment into guest memory, including handling endianness and fixing it up with entry point addresses and similar things. This is useful not just for the boot.c code but also in board model code, so rename it to arm_write_bootloader() and make it globally visible. Since we are making it public, make its API a little neater: move the AddressSpace* argument to be next to the hwaddr argument, and allow the fixupcontext array to be const, since we never modify it in this function. Cc: qemu-stable@nongnu.org Signed-off-by: Cédric Le Goater <clg@kaod.org> Tested-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20230424152717.1333930-2-peter.maydell@linaro.org [PMM: Split out from another patch by Cédric, added doc comment] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/boot.h | 49 +++++++++++++++++++++++++++++++++++++++++++ hw/arm/boot.c | 35 +++++++------------------------ 2 files changed, 57 insertions(+), 27 deletions(-) diff --git a/include/hw/arm/boot.h b/include/hw/arm/boot.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/boot.h +++ b/include/hw/arm/boot.h @@ -XXX,XX +XXX,XX @@ void arm_write_secure_board_setup_dummy_smc(ARMCPU *cpu, const struct arm_boot_info *info, hwaddr mvbar_addr); +typedef enum { + FIXUP_NONE = 0, /* do nothing */ + FIXUP_TERMINATOR, /* end of insns */ + FIXUP_BOARDID, /* overwrite with board ID number */ + FIXUP_BOARD_SETUP, /* overwrite with board specific setup code address */ + FIXUP_ARGPTR_LO, /* overwrite with pointer to kernel args */ + FIXUP_ARGPTR_HI, /* overwrite with pointer to kernel args (high half) */ + FIXUP_ENTRYPOINT_LO, /* overwrite with kernel entry point */ + FIXUP_ENTRYPOINT_HI, /* overwrite with kernel entry point (high half) */ + FIXUP_GIC_CPU_IF, /* overwrite with GIC CPU interface address */ + FIXUP_BOOTREG, /* overwrite with boot register address */ + FIXUP_DSB, /* overwrite with correct DSB insn for cpu */ + FIXUP_MAX, +} FixupType; + +typedef struct ARMInsnFixup { + uint32_t insn; + FixupType fixup; +} ARMInsnFixup; + +/** + * arm_write_bootloader - write a bootloader to guest memory + * @name: name of the bootloader blob + * @as: AddressSpace to write the bootloader + * @addr: guest address to write it + * @insns: the blob to be loaded + * @fixupcontext: context to be used for any fixups in @insns + * + * Write a bootloader to guest memory at address @addr in the address + * space @as. @name is the name to use for the resulting ROM blob, so + * it should be unique in the system and reasonably identifiable for debugging. + * + * @insns must be an array of ARMInsnFixup structs, each of which has + * one 32-bit value to be written to the guest memory, and a fixup to be + * applied to the value. FIXUP_NONE (do nothing) is value 0, so effectively + * the fixup is optional when writing a struct initializer. + * The final entry in the array must be { 0, FIXUP_TERMINATOR }. + * + * All other supported fixup types have the semantics "ignore insn + * and instead use the value from the array element @fixupcontext[fixup]". + * The caller should therefore provide @fixupcontext as an array of + * size FIXUP_MAX whose elements have been initialized for at least + * the entries that @insns refers to. + */ +void arm_write_bootloader(const char *name, + AddressSpace *as, hwaddr addr, + const ARMInsnFixup *insns, + const uint32_t *fixupcontext); + #endif /* HW_ARM_BOOT_H */ diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ AddressSpace *arm_boot_address_space(ARMCPU *cpu, return cpu_get_address_space(cs, asidx); } -typedef enum { - FIXUP_NONE = 0, /* do nothing */ - FIXUP_TERMINATOR, /* end of insns */ - FIXUP_BOARDID, /* overwrite with board ID number */ - FIXUP_BOARD_SETUP, /* overwrite with board specific setup code address */ - FIXUP_ARGPTR_LO, /* overwrite with pointer to kernel args */ - FIXUP_ARGPTR_HI, /* overwrite with pointer to kernel args (high half) */ - FIXUP_ENTRYPOINT_LO, /* overwrite with kernel entry point */ - FIXUP_ENTRYPOINT_HI, /* overwrite with kernel entry point (high half) */ - FIXUP_GIC_CPU_IF, /* overwrite with GIC CPU interface address */ - FIXUP_BOOTREG, /* overwrite with boot register address */ - FIXUP_DSB, /* overwrite with correct DSB insn for cpu */ - FIXUP_MAX, -} FixupType; - -typedef struct ARMInsnFixup { - uint32_t insn; - FixupType fixup; -} ARMInsnFixup; - static const ARMInsnFixup bootloader_aarch64[] = { { 0x580000c0 }, /* ldr x0, arg ; Load the lower 32-bits of DTB */ { 0xaa1f03e1 }, /* mov x1, xzr */ @@ -XXX,XX +XXX,XX @@ static const ARMInsnFixup smpboot[] = { { 0, FIXUP_TERMINATOR } }; -static void write_bootloader(const char *name, hwaddr addr, - const ARMInsnFixup *insns, uint32_t *fixupcontext, - AddressSpace *as) +void arm_write_bootloader(const char *name, + AddressSpace *as, hwaddr addr, + const ARMInsnFixup *insns, + const uint32_t *fixupcontext) { /* Fix up the specified bootloader fragment and write it into * guest memory using rom_add_blob_fixed(). fixupcontext is @@ -XXX,XX +XXX,XX @@ static void default_write_secondary(ARMCPU *cpu, fixupcontext[FIXUP_DSB] = CP15_DSB_INSN; } - write_bootloader("smpboot", info->smp_loader_start, - smpboot, fixupcontext, as); + arm_write_bootloader("smpboot", as, info->smp_loader_start, + smpboot, fixupcontext); } void arm_write_secure_board_setup_dummy_smc(ARMCPU *cpu, @@ -XXX,XX +XXX,XX @@ static void arm_setup_direct_kernel_boot(ARMCPU *cpu, fixupcontext[FIXUP_ENTRYPOINT_LO] = entry; fixupcontext[FIXUP_ENTRYPOINT_HI] = entry >> 32; - write_bootloader("bootloader", info->loader_start, - primary_loader, fixupcontext, as); + arm_write_bootloader("bootloader", as, info->loader_start, + primary_loader, fixupcontext); if (info->write_board_setup) { info->write_board_setup(cpu, info); -- 2.34.1 From: Cédric Le Goater <clg@kaod.org> When writing the secondary-CPU stub boot loader code to the guest, use arm_write_bootloader() instead of directly calling rom_add_blob_fixed(). This fixes a bug on big-endian hosts, because arm_write_bootloader() will correctly byte-swap the host-byte-order array values into the guest-byte-order to write into the guest memory. Cc: qemu-stable@nongnu.org Signed-off-by: Cédric Le Goater <clg@kaod.org> Tested-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20230424152717.1333930-3-peter.maydell@linaro.org [PMM: Moved the "make arm_write_bootloader() function public" part to its own patch; updated commit message to note that this fixes an actual bug; adjust to the API changes noted in previous commit] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/aspeed.c | 38 ++++++++++++++++++++------------------ 1 file changed, 20 insertions(+), 18 deletions(-) diff --git a/hw/arm/aspeed.c b/hw/arm/aspeed.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed.c +++ b/hw/arm/aspeed.c @@ -XXX,XX +XXX,XX @@ struct AspeedMachineState { static void aspeed_write_smpboot(ARMCPU *cpu, const struct arm_boot_info *info) { - static const uint32_t poll_mailbox_ready[] = { + AddressSpace *as = arm_boot_address_space(cpu, info); + static const ARMInsnFixup poll_mailbox_ready[] = { /* * r2 = per-cpu go sign value * r1 = AST_SMP_MBOX_FIELD_ENTRY * r0 = AST_SMP_MBOX_FIELD_GOSIGN */ - 0xee100fb0, /* mrc p15, 0, r0, c0, c0, 5 */ - 0xe21000ff, /* ands r0, r0, #255 */ - 0xe59f201c, /* ldr r2, [pc, #28] */ - 0xe1822000, /* orr r2, r2, r0 */ + { 0xee100fb0 }, /* mrc p15, 0, r0, c0, c0, 5 */ + { 0xe21000ff }, /* ands r0, r0, #255 */ + { 0xe59f201c }, /* ldr r2, [pc, #28] */ + { 0xe1822000 }, /* orr r2, r2, r0 */ - 0xe59f1018, /* ldr r1, [pc, #24] */ - 0xe59f0018, /* ldr r0, [pc, #24] */ + { 0xe59f1018 }, /* ldr r1, [pc, #24] */ + { 0xe59f0018 }, /* ldr r0, [pc, #24] */ - 0xe320f002, /* wfe */ - 0xe5904000, /* ldr r4, [r0] */ - 0xe1520004, /* cmp r2, r4 */ - 0x1afffffb, /* bne <wfe> */ - 0xe591f000, /* ldr pc, [r1] */ - AST_SMP_MBOX_GOSIGN, - AST_SMP_MBOX_FIELD_ENTRY, - AST_SMP_MBOX_FIELD_GOSIGN, + { 0xe320f002 }, /* wfe */ + { 0xe5904000 }, /* ldr r4, [r0] */ + { 0xe1520004 }, /* cmp r2, r4 */ + { 0x1afffffb }, /* bne <wfe> */ + { 0xe591f000 }, /* ldr pc, [r1] */ + { AST_SMP_MBOX_GOSIGN }, + { AST_SMP_MBOX_FIELD_ENTRY }, + { AST_SMP_MBOX_FIELD_GOSIGN }, + { 0, FIXUP_TERMINATOR } }; + static const uint32_t fixupcontext[FIXUP_MAX] = { 0 }; - rom_add_blob_fixed("aspeed.smpboot", poll_mailbox_ready, - sizeof(poll_mailbox_ready), - info->smp_loader_start); + arm_write_bootloader("aspeed.smpboot", as, info->smp_loader_start, + poll_mailbox_ready, fixupcontext); } static void aspeed_reset_secondary(ARMCPU *cpu, -- 2.34.1 When writing the secondary-CPU stub boot loader code to the guest, use arm_write_bootloader() instead of directly calling rom_add_blob_fixed(). This fixes a bug on big-endian hosts, because arm_write_bootloader() will correctly byte-swap the host-byte-order array values into the guest-byte-order to write into the guest memory. Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Tested-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230424152717.1333930-4-peter.maydell@linaro.org --- hw/arm/raspi.c | 64 +++++++++++++++++++++++++++----------------------- 1 file changed, 34 insertions(+), 30 deletions(-) diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/raspi.c +++ b/hw/arm/raspi.c @@ -XXX,XX +XXX,XX @@ #include "qemu/units.h" #include "qemu/cutils.h" #include "qapi/error.h" +#include "hw/arm/boot.h" #include "hw/arm/bcm2836.h" #include "hw/registerfields.h" #include "qemu/error-report.h" @@ -XXX,XX +XXX,XX @@ static const char *board_type(uint32_t board_rev) static void write_smpboot(ARMCPU *cpu, const struct arm_boot_info *info) { - static const uint32_t smpboot[] = { - 0xe1a0e00f, /* mov lr, pc */ - 0xe3a0fe00 + (BOARDSETUP_ADDR >> 4), /* mov pc, BOARDSETUP_ADDR */ - 0xee100fb0, /* mrc p15, 0, r0, c0, c0, 5;get core ID */ - 0xe7e10050, /* ubfx r0, r0, #0, #2 ;extract LSB */ - 0xe59f5014, /* ldr r5, =0x400000CC ;load mbox base */ - 0xe320f001, /* 1: yield */ - 0xe7953200, /* ldr r3, [r5, r0, lsl #4] ;read mbox for our core*/ - 0xe3530000, /* cmp r3, #0 ;spin while zero */ - 0x0afffffb, /* beq 1b */ - 0xe7853200, /* str r3, [r5, r0, lsl #4] ;clear mbox */ - 0xe12fff13, /* bx r3 ;jump to target */ - 0x400000cc, /* (constant: mailbox 3 read/clear base) */ + static const ARMInsnFixup smpboot[] = { + { 0xe1a0e00f }, /* mov lr, pc */ + { 0xe3a0fe00 + (BOARDSETUP_ADDR >> 4) }, /* mov pc, BOARDSETUP_ADDR */ + { 0xee100fb0 }, /* mrc p15, 0, r0, c0, c0, 5;get core ID */ + { 0xe7e10050 }, /* ubfx r0, r0, #0, #2 ;extract LSB */ + { 0xe59f5014 }, /* ldr r5, =0x400000CC ;load mbox base */ + { 0xe320f001 }, /* 1: yield */ + { 0xe7953200 }, /* ldr r3, [r5, r0, lsl #4] ;read mbox for our core */ + { 0xe3530000 }, /* cmp r3, #0 ;spin while zero */ + { 0x0afffffb }, /* beq 1b */ + { 0xe7853200 }, /* str r3, [r5, r0, lsl #4] ;clear mbox */ + { 0xe12fff13 }, /* bx r3 ;jump to target */ + { 0x400000cc }, /* (constant: mailbox 3 read/clear base) */ + { 0, FIXUP_TERMINATOR } }; + static const uint32_t fixupcontext[FIXUP_MAX] = { 0 }; /* check that we don't overrun board setup vectors */ QEMU_BUILD_BUG_ON(SMPBOOT_ADDR + sizeof(smpboot) > MVBAR_ADDR); @@ -XXX,XX +XXX,XX @@ static void write_smpboot(ARMCPU *cpu, const struct arm_boot_info *info) QEMU_BUILD_BUG_ON((BOARDSETUP_ADDR & 0xf) != 0 || (BOARDSETUP_ADDR >> 4) >= 0x100); - rom_add_blob_fixed_as("raspi_smpboot", smpboot, sizeof(smpboot), - info->smp_loader_start, - arm_boot_address_space(cpu, info)); + arm_write_bootloader("raspi_smpboot", arm_boot_address_space(cpu, info), + info->smp_loader_start, smpboot, fixupcontext); } static void write_smpboot64(ARMCPU *cpu, const struct arm_boot_info *info) @@ -XXX,XX +XXX,XX @@ static void write_smpboot64(ARMCPU *cpu, const struct arm_boot_info *info) * the primary CPU goes into the kernel. We put these variables inside * a rom blob, so that the reset for ROM contents zeroes them for us. */ - static const uint32_t smpboot[] = { - 0xd2801b05, /* mov x5, 0xd8 */ - 0xd53800a6, /* mrs x6, mpidr_el1 */ - 0x924004c6, /* and x6, x6, #0x3 */ - 0xd503205f, /* spin: wfe */ - 0xf86678a4, /* ldr x4, [x5,x6,lsl #3] */ - 0xb4ffffc4, /* cbz x4, spin */ - 0xd2800000, /* mov x0, #0x0 */ - 0xd2800001, /* mov x1, #0x0 */ - 0xd2800002, /* mov x2, #0x0 */ - 0xd2800003, /* mov x3, #0x0 */ - 0xd61f0080, /* br x4 */ + static const ARMInsnFixup smpboot[] = { + { 0xd2801b05 }, /* mov x5, 0xd8 */ + { 0xd53800a6 }, /* mrs x6, mpidr_el1 */ + { 0x924004c6 }, /* and x6, x6, #0x3 */ + { 0xd503205f }, /* spin: wfe */ + { 0xf86678a4 }, /* ldr x4, [x5,x6,lsl #3] */ + { 0xb4ffffc4 }, /* cbz x4, spin */ + { 0xd2800000 }, /* mov x0, #0x0 */ + { 0xd2800001 }, /* mov x1, #0x0 */ + { 0xd2800002 }, /* mov x2, #0x0 */ + { 0xd2800003 }, /* mov x3, #0x0 */ + { 0xd61f0080 }, /* br x4 */ + { 0, FIXUP_TERMINATOR } }; + static const uint32_t fixupcontext[FIXUP_MAX] = { 0 }; static const uint64_t spintables[] = { 0, 0, 0, 0 }; - rom_add_blob_fixed_as("raspi_smpboot", smpboot, sizeof(smpboot), - info->smp_loader_start, as); + arm_write_bootloader("raspi_smpboot", as, info->smp_loader_start, + smpboot, fixupcontext); rom_add_blob_fixed_as("raspi_spintables", spintables, sizeof(spintables), SPINTABLE_ADDR, as); } -- 2.34.1 The Allwinner PIC model uses set_bit() and clear_bit() to update the values in its irq_pending[] array when an interrupt arrives. However it is using these functions wrongly: they work on an array of type 'long', and it is passing an array of type 'uint32_t'. Because the code manually figures out the right array element, this works on little-endian hosts and on 32-bit big-endian hosts, where bits 0..31 in a 'long' are in the same place as they are in a 'uint32_t'. However it breaks on 64-bit big-endian hosts. Remove the use of set_bit() and clear_bit() in favour of using deposit32() on the array element. This fixes a bug where on big-endian 64-bit hosts the guest kernel would hang early on in bootup. Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230424152833.1334136-1-peter.maydell@linaro.org --- hw/intc/allwinner-a10-pic.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/hw/intc/allwinner-a10-pic.c b/hw/intc/allwinner-a10-pic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/allwinner-a10-pic.c +++ b/hw/intc/allwinner-a10-pic.c @@ -XXX,XX +XXX,XX @@ static void aw_a10_pic_update(AwA10PICState *s) static void aw_a10_pic_set_irq(void *opaque, int irq, int level) { AwA10PICState *s = opaque; + uint32_t *pending_reg = &s->irq_pending[irq / 32]; - if (level) { - set_bit(irq % 32, (void *)&s->irq_pending[irq / 32]); - } else { - clear_bit(irq % 32, (void *)&s->irq_pending[irq / 32]); - } + *pending_reg = deposit32(*pending_reg, irq % 32, 1, level); aw_a10_pic_update(s); } -- 2.34.1 In several places in the 32-bit Arm translate.c, we try to use load_cpu_field() to load from a CPUARMState field into a TCGv_i32 where the field is actually 64-bit. This works on little-endian hosts, but gives the wrong half of the register on big-endian. Add a new load_cpu_field_low32() which loads the low 32 bits of a 64-bit field into a TCGv_i32. The new macro includes a compile-time check against accidentally using it on a field of the wrong size. Use it to fix the two places in the code where we were using load_cpu_field() on a 64-bit field. This fixes a bug where on big-endian hosts the guest would crash after executing an ERET instruction, and a more corner case one where some UNDEFs for attempted accesses to MSR banked registers from Secure EL1 might go to the wrong EL. Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230424153909.1419369-2-peter.maydell@linaro.org --- target/arm/translate-a32.h | 7 +++++++ target/arm/tcg/translate.c | 4 ++-- 2 files changed, 9 insertions(+), 2 deletions(-) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 load_cpu_offset(int offset) #define load_cpu_field(name) load_cpu_offset(offsetof(CPUARMState, name)) +/* Load from the low half of a 64-bit field to a TCGv_i32 */ +#define load_cpu_field_low32(name) \ + ({ \ + QEMU_BUILD_BUG_ON(sizeof_field(CPUARMState, name) != 8); \ + load_cpu_offset(offsetoflow32(CPUARMState, name)); \ + }) + void store_cpu_offset(TCGv_i32 var, int offset, int size); #define store_cpu_field(var, name) \ diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -XXX,XX +XXX,XX @@ static bool msr_banked_access_decode(DisasContext *s, int r, int sysm, int rn, if (arm_dc_feature(s, ARM_FEATURE_AARCH64) && dc_isar_feature(aa64_sel2, s)) { /* Target EL is EL<3 minus SCR_EL3.EEL2> */ - tcg_el = load_cpu_field(cp15.scr_el3); + tcg_el = load_cpu_field_low32(cp15.scr_el3); tcg_gen_sextract_i32(tcg_el, tcg_el, ctz32(SCR_EEL2), 1); tcg_gen_addi_i32(tcg_el, tcg_el, 3); } else { @@ -XXX,XX +XXX,XX @@ static bool trans_ERET(DisasContext *s, arg_ERET *a) } if (s->current_el == 2) { /* ERET from Hyp uses ELR_Hyp, not LR */ - tmp = load_cpu_field(elr_el[2]); + tmp = load_cpu_field_low32(elr_el[2]); } else { tmp = load_reg(s, 14); } -- 2.34.1 Add some compile-time asserts to the load_cpu_field() and store_cpu_field() macros that the struct field being accessed is the expected size. This lets us catch cases where we incorrectly tried to do a 32-bit load from a 64-bit struct field. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230424153909.1419369-3-peter.maydell@linaro.org --- target/arm/translate-a32.h | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 load_cpu_offset(int offset) return tmp; } -#define load_cpu_field(name) load_cpu_offset(offsetof(CPUARMState, name)) +/* Load from a 32-bit field to a TCGv_i32 */ +#define load_cpu_field(name) \ + ({ \ + QEMU_BUILD_BUG_ON(sizeof_field(CPUARMState, name) != 4); \ + load_cpu_offset(offsetof(CPUARMState, name)); \ + }) /* Load from the low half of a 64-bit field to a TCGv_i32 */ #define load_cpu_field_low32(name) \ @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 load_cpu_offset(int offset) void store_cpu_offset(TCGv_i32 var, int offset, int size); -#define store_cpu_field(var, name) \ - store_cpu_offset(var, offsetof(CPUARMState, name), \ - sizeof_field(CPUARMState, name)) +#define store_cpu_field(val, name) \ + ({ \ + QEMU_BUILD_BUG_ON(sizeof_field(CPUARMState, name) != 4 \ + && sizeof_field(CPUARMState, name) != 1); \ + store_cpu_offset(val, offsetof(CPUARMState, name), \ + sizeof_field(CPUARMState, name)); \ + }) #define store_cpu_field_constant(val, name) \ store_cpu_field(tcg_constant_i32(val), name) -- 2.34.1 In allwinner_sdhost_process_desc() we just read directly from guest memory into a host TransferDescriptor struct and back. This only works on little-endian hosts. Abstract the reading and writing of descriptors into functions that handle the byte-swapping so that TransferDescriptor structs as seen by the rest of the code are always in host-order. This fixes a failure of one of the avocado tests on s390. Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230424165053.1428857-2-peter.maydell@linaro.org --- hw/sd/allwinner-sdhost.c | 31 ++++++++++++++++++++++++++----- 1 file changed, 26 insertions(+), 5 deletions(-) diff --git a/hw/sd/allwinner-sdhost.c b/hw/sd/allwinner-sdhost.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/allwinner-sdhost.c +++ b/hw/sd/allwinner-sdhost.c @@ -XXX,XX +XXX,XX @@ static void allwinner_sdhost_auto_stop(AwSdHostState *s) } } +static void read_descriptor(AwSdHostState *s, hwaddr desc_addr, + TransferDescriptor *desc) +{ + uint32_t desc_words[4]; + dma_memory_read(&s->dma_as, desc_addr, &desc_words, sizeof(desc_words), + MEMTXATTRS_UNSPECIFIED); + desc->status = le32_to_cpu(desc_words[0]); + desc->size = le32_to_cpu(desc_words[1]); + desc->addr = le32_to_cpu(desc_words[2]); + desc->next = le32_to_cpu(desc_words[3]); +} + +static void write_descriptor(AwSdHostState *s, hwaddr desc_addr, + const TransferDescriptor *desc) +{ + uint32_t desc_words[4]; + desc_words[0] = cpu_to_le32(desc->status); + desc_words[1] = cpu_to_le32(desc->size); + desc_words[2] = cpu_to_le32(desc->addr); + desc_words[3] = cpu_to_le32(desc->next); + dma_memory_write(&s->dma_as, desc_addr, &desc_words, sizeof(desc_words), + MEMTXATTRS_UNSPECIFIED); +} + static uint32_t allwinner_sdhost_process_desc(AwSdHostState *s, hwaddr desc_addr, TransferDescriptor *desc, @@ -XXX,XX +XXX,XX @@ static uint32_t allwinner_sdhost_process_desc(AwSdHostState *s, uint32_t num_bytes = max_bytes; uint8_t buf[1024]; - /* Read descriptor */ - dma_memory_read(&s->dma_as, desc_addr, desc, sizeof(*desc), - MEMTXATTRS_UNSPECIFIED); + read_descriptor(s, desc_addr, desc); if (desc->size == 0) { desc->size = klass->max_desc_size; } else if (desc->size > klass->max_desc_size) { @@ -XXX,XX +XXX,XX @@ static uint32_t allwinner_sdhost_process_desc(AwSdHostState *s, /* Clear hold flag and flush descriptor */ desc->status &= ~DESC_STATUS_HOLD; - dma_memory_write(&s->dma_as, desc_addr, desc, sizeof(*desc), - MEMTXATTRS_UNSPECIFIED); + write_descriptor(s, desc_addr, desc); return num_done; } -- 2.34.1 In allwinner-sun8i-emac we just read directly from guest memory into a host FrameDescriptor struct and back. This only works on little-endian hosts. Reading and writing of descriptors is already abstracted into functions; make those functions also handle the byte-swapping so that TransferDescriptor structs as seen by the rest of the code are always in host-order, and fix two places that were doing ad-hoc descriptor reading without using the functions. Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230424165053.1428857-3-peter.maydell@linaro.org --- hw/net/allwinner-sun8i-emac.c | 22 +++++++++++++++------- 1 file changed, 15 insertions(+), 7 deletions(-) diff --git a/hw/net/allwinner-sun8i-emac.c b/hw/net/allwinner-sun8i-emac.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/allwinner-sun8i-emac.c +++ b/hw/net/allwinner-sun8i-emac.c @@ -XXX,XX +XXX,XX @@ static void allwinner_sun8i_emac_get_desc(AwSun8iEmacState *s, FrameDescriptor *desc, uint32_t phys_addr) { - dma_memory_read(&s->dma_as, phys_addr, desc, sizeof(*desc), + uint32_t desc_words[4]; + dma_memory_read(&s->dma_as, phys_addr, &desc_words, sizeof(desc_words), MEMTXATTRS_UNSPECIFIED); + desc->status = le32_to_cpu(desc_words[0]); + desc->status2 = le32_to_cpu(desc_words[1]); + desc->addr = le32_to_cpu(desc_words[2]); + desc->next = le32_to_cpu(desc_words[3]); } static uint32_t allwinner_sun8i_emac_next_desc(AwSun8iEmacState *s, @@ -XXX,XX +XXX,XX @@ static uint32_t allwinner_sun8i_emac_tx_desc(AwSun8iEmacState *s, } static void allwinner_sun8i_emac_flush_desc(AwSun8iEmacState *s, - FrameDescriptor *desc, + const FrameDescriptor *desc, uint32_t phys_addr) { - dma_memory_write(&s->dma_as, phys_addr, desc, sizeof(*desc), + uint32_t desc_words[4]; + desc_words[0] = cpu_to_le32(desc->status); + desc_words[1] = cpu_to_le32(desc->status2); + desc_words[2] = cpu_to_le32(desc->addr); + desc_words[3] = cpu_to_le32(desc->next); + dma_memory_write(&s->dma_as, phys_addr, &desc_words, sizeof(desc_words), MEMTXATTRS_UNSPECIFIED); } @@ -XXX,XX +XXX,XX @@ static uint64_t allwinner_sun8i_emac_read(void *opaque, hwaddr offset, break; case REG_TX_CUR_BUF: /* Transmit Current Buffer */ if (s->tx_desc_curr != 0) { - dma_memory_read(&s->dma_as, s->tx_desc_curr, &desc, sizeof(desc), - MEMTXATTRS_UNSPECIFIED); + allwinner_sun8i_emac_get_desc(s, &desc, s->tx_desc_curr); value = desc.addr; } else { value = 0; @@ -XXX,XX +XXX,XX @@ static uint64_t allwinner_sun8i_emac_read(void *opaque, hwaddr offset, break; case REG_RX_CUR_BUF: /* Receive Current Buffer */ if (s->rx_desc_curr != 0) { - dma_memory_read(&s->dma_as, s->rx_desc_curr, &desc, sizeof(desc), - MEMTXATTRS_UNSPECIFIED); + allwinner_sun8i_emac_get_desc(s, &desc, s->rx_desc_curr); value = desc.addr; } else { value = 0; -- 2.34.1