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 A largish pull request: the big things are Richard's PAuth work and Aaron's PMU emulation improvements. thanks -- PMM The following changes since commit 681d61362d3f766a00806b89d6581869041f73cb: Merge remote-tracking branch 'remotes/jnsnow/tags/bitmaps-pull-request' into staging (2019-01-17 12:48:42 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20190118 for you to fetch changes up to 2a0ed2804e2c77a1c4e255f05ab739618e05c85d: tests/libqtest: Introduce qtest_init_with_serial() (2019-01-18 14:17:38 +0000) ---------------------------------------------------------------- target-arm queue: * hw/char/stm32f2xx_usart: Do not update data register when device is disabled * hw/arm/virt-acpi-build: Set COHACC override flag in IORT SMMUv3 node * target/arm: Allow Aarch32 exception return to switch from Mon->Hyp * ftgmac100: implement the new MDIO interface on Aspeed SoC * implement the ARMv8.3-PAuth extension * improve emulation of the ARM PMU ---------------------------------------------------------------- Aaron Lindsay (13): migration: Add post_save function to VMStateDescription target/arm: Reorganize PMCCNTR accesses target/arm: Swap PMU values before/after migrations target/arm: Filter cycle counter based on PMCCFILTR_EL0 target/arm: Allow AArch32 access for PMCCFILTR target/arm: Implement PMOVSSET target/arm: Define FIELDs for ID_DFR0 target/arm: Make PMCEID[01]_EL0 64 bit registers, add PMCEID[23] target/arm: Add array for supported PMU events, generate PMCEID[01]_EL0 target/arm: Finish implementation of PM[X]EVCNTR and PM[X]EVTYPER target/arm: PMU: Add instruction and cycle events target/arm: PMU: Set PMCR.N to 4 target/arm: Implement PMSWINC Alexander Graf (1): target/arm: Allow Aarch32 exception return to switch from Mon->Hyp Cédric Le Goater (1): ftgmac100: implement the new MDIO interface on Aspeed SoC Eric Auger (1): hw/arm/virt-acpi-build: Set COHACC override flag in IORT SMMUv3 node Julia Suvorova (1): tests/libqtest: Introduce qtest_init_with_serial() Philippe Mathieu-Daudé (1): hw/char/stm32f2xx_usart: Do not update data register when device is disabled Richard Henderson (31): target/arm: Add state for the ARMv8.3-PAuth extension target/arm: Add SCTLR bits through ARMv8.5 target/arm: Add PAuth active bit to tbflags target/arm: Introduce raise_exception_ra target/arm: Add PAuth helpers target/arm: Decode PAuth within system hint space target/arm: Rearrange decode in disas_data_proc_1src target/arm: Decode PAuth within disas_data_proc_1src target/arm: Decode PAuth within disas_data_proc_2src target/arm: Move helper_exception_return to helper-a64.c target/arm: Add new_pc argument to helper_exception_return target/arm: Rearrange decode in disas_uncond_b_reg target/arm: Decode PAuth within disas_uncond_b_reg target/arm: Decode Load/store register (pac) target/arm: Move cpu_mmu_index out of line target/arm: Introduce arm_mmu_idx target/arm: Introduce arm_stage1_mmu_idx target/arm: Create ARMVAParameters and helpers target/arm: Merge TBFLAG_AA_TB{0, 1} to TBII target/arm: Export aa64_va_parameters to internals.h target/arm: Add aa64_va_parameters_both target/arm: Decode TBID from TCR target/arm: Reuse aa64_va_parameters for setting tbflags target/arm: Implement pauth_strip target/arm: Implement pauth_auth target/arm: Implement pauth_addpac target/arm: Implement pauth_computepac target/arm: Add PAuth system registers target/arm: Enable PAuth for -cpu max target/arm: Enable PAuth for user-only target/arm: Tidy TBI handling in gen_a64_set_pc target/arm/Makefile.objs | 1 + include/hw/acpi/acpi-defs.h | 2 + include/migration/vmstate.h | 1 + target/arm/cpu.h | 244 +++++---- target/arm/helper-a64.h | 14 + target/arm/helper.h | 1 - target/arm/internals.h | 77 +++ target/arm/translate.h | 5 +- tests/libqtest.h | 11 + hw/arm/virt-acpi-build.c | 1 + hw/char/stm32f2xx_usart.c | 3 +- hw/net/ftgmac100.c | 80 ++- migration/vmstate.c | 13 +- target/arm/cpu.c | 19 +- target/arm/cpu64.c | 68 ++- target/arm/helper-a64.c | 155 ++++++ target/arm/helper.c | 1222 +++++++++++++++++++++++++++++++++---------- target/arm/machine.c | 24 + target/arm/op_helper.c | 174 +----- target/arm/pauth_helper.c | 497 ++++++++++++++++++ target/arm/translate-a64.c | 537 ++++++++++++++++--- tests/libqtest.c | 26 + docs/devel/migration.rst | 9 +- 23 files changed, 2552 insertions(+), 632 deletions(-) create mode 100644 target/arm/pauth_helper.c From: Philippe Mathieu-Daudé <philmd@redhat.com> When the device is disabled, the internal circuitry keeps the data register loaded and doesn't update it. Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20190104182057.8778-1-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/stm32f2xx_usart.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/hw/char/stm32f2xx_usart.c b/hw/char/stm32f2xx_usart.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/stm32f2xx_usart.c +++ b/hw/char/stm32f2xx_usart.c @@ -XXX,XX +XXX,XX @@ static void stm32f2xx_usart_receive(void *opaque, const uint8_t *buf, int size) { STM32F2XXUsartState *s = opaque; - s->usart_dr = *buf; - if (!(s->usart_cr1 & USART_CR1_UE && s->usart_cr1 & USART_CR1_RE)) { /* USART not enabled - drop the chars */ DB_PRINT("Dropping the chars\n"); return; } + s->usart_dr = *buf; s->usart_sr |= USART_SR_RXNE; if (s->usart_cr1 & USART_CR1_RXNEIE) { -- 2.20.1 From: Eric Auger <eric.auger@redhat.com> Let's report IO-coherent access is supported for translation table walks, descriptor fetches and queues by setting the COHACC override flag. Without that, we observe wrong command opcodes. The DT description also advertises the dma coherency. Fixes a703b4f6c1ee ("hw/arm/virt-acpi-build: Add smmuv3 node in IORT table") Signed-off-by: Eric Auger <eric.auger@redhat.com> Reported-by: Shameerali Kolothum Thodi <shameerali.kolothum.thodi@huawei.com> Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20190107101041.765-1-eric.auger@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/acpi/acpi-defs.h | 2 ++ hw/arm/virt-acpi-build.c | 1 + 2 files changed, 3 insertions(+) diff --git a/include/hw/acpi/acpi-defs.h b/include/hw/acpi/acpi-defs.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/acpi/acpi-defs.h +++ b/include/hw/acpi/acpi-defs.h @@ -XXX,XX +XXX,XX @@ struct AcpiIortItsGroup { } QEMU_PACKED; typedef struct AcpiIortItsGroup AcpiIortItsGroup; +#define ACPI_IORT_SMMU_V3_COHACC_OVERRIDE 1 + struct AcpiIortSmmu3 { ACPI_IORT_NODE_HEADER_DEF uint64_t base_address; diff --git a/hw/arm/virt-acpi-build.c b/hw/arm/virt-acpi-build.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt-acpi-build.c +++ b/hw/arm/virt-acpi-build.c @@ -XXX,XX +XXX,XX @@ build_iort(GArray *table_data, BIOSLinker *linker, VirtMachineState *vms) smmu->mapping_count = cpu_to_le32(1); smmu->mapping_offset = cpu_to_le32(sizeof(*smmu)); smmu->base_address = cpu_to_le64(vms->memmap[VIRT_SMMU].base); + smmu->flags = cpu_to_le32(ACPI_IORT_SMMU_V3_COHACC_OVERRIDE); smmu->event_gsiv = cpu_to_le32(irq); smmu->pri_gsiv = cpu_to_le32(irq + 1); smmu->gerr_gsiv = cpu_to_le32(irq + 2); -- 2.20.1 From: Alexander Graf <agraf@suse.de> In U-boot, we switch from S-SVC -> Mon -> Hyp mode when we want to enter Hyp mode. The change into Hyp mode is done by doing an exception return from Mon. This doesn't work with current QEMU. The problem is that in bad_mode_switch() we refuse to allow the change of mode. Note that bad_mode_switch() is used to do validation for two situations: (1) changes to mode by instructions writing to CPSR.M (ie not exception take/return) -- this corresponds to the Armv8 Arm ARM pseudocode Arch32.WriteModeByInstr (2) changes to mode by exception return Attempting to enter or leave Hyp mode via case (1) is forbidden in v8 and UNPREDICTABLE in v7, and QEMU is correct to disallow it there. However, we're already doing that check at the top of the bad_mode_switch() function, so if that passes then we should allow the case (2) exception return mode changes to switch into Hyp mode. We want to test whether we're trying to return to the nonexistent "secure Hyp" mode, so we need to look at arm_is_secure_below_el3() rather than arm_is_secure(), since the latter is always true if we're in Mon (EL3). Signed-off-by: Alexander Graf <agraf@suse.de> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190109152430.32359-1-agraf@suse.de [PMM: rewrote commit message] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static int bad_mode_switch(CPUARMState *env, int mode, CPSRWriteType write_type) return 0; case ARM_CPU_MODE_HYP: return !arm_feature(env, ARM_FEATURE_EL2) - || arm_current_el(env) < 2 || arm_is_secure(env); + || arm_current_el(env) < 2 || arm_is_secure_below_el3(env); case ARM_CPU_MODE_MON: return arm_current_el(env) < 3; default: -- 2.20.1 From: Cédric Le Goater <clg@kaod.org> The PHY behind the MAC of an Aspeed SoC can be controlled using two different MDC/MDIO interfaces. The same registers PHYCR (MAC60) and PHYDATA (MAC64) are involved but they have a different layout. BIT31 of the Feature Register (MAC40) controls which MDC/MDIO interface is active. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Andrew Jeffery <andrew@aj.id.au> Reviewed-by: Joel Stanley <joel@jms.id.au> Message-id: 20190111125759.31577-1-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/ftgmac100.c | 80 +++++++++++++++++++++++++++++++++++++++------- 1 file changed, 68 insertions(+), 12 deletions(-) diff --git a/hw/net/ftgmac100.c b/hw/net/ftgmac100.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/ftgmac100.c +++ b/hw/net/ftgmac100.c @@ -XXX,XX +XXX,XX @@ #define FTGMAC100_PHYDATA_MIIWDATA(x) ((x) & 0xffff) #define FTGMAC100_PHYDATA_MIIRDATA(x) (((x) >> 16) & 0xffff) +/* + * PHY control register - New MDC/MDIO interface + */ +#define FTGMAC100_PHYCR_NEW_DATA(x) (((x) >> 16) & 0xffff) +#define FTGMAC100_PHYCR_NEW_FIRE (1 << 15) +#define FTGMAC100_PHYCR_NEW_ST_22 (1 << 12) +#define FTGMAC100_PHYCR_NEW_OP(x) (((x) >> 10) & 3) +#define FTGMAC100_PHYCR_NEW_OP_WRITE 0x1 +#define FTGMAC100_PHYCR_NEW_OP_READ 0x2 +#define FTGMAC100_PHYCR_NEW_DEV(x) (((x) >> 5) & 0x1f) +#define FTGMAC100_PHYCR_NEW_REG(x) ((x) & 0x1f) + /* * Feature Register */ @@ -XXX,XX +XXX,XX @@ static void phy_reset(FTGMAC100State *s) s->phy_int = 0; } -static uint32_t do_phy_read(FTGMAC100State *s, int reg) +static uint16_t do_phy_read(FTGMAC100State *s, uint8_t reg) { - uint32_t val; + uint16_t val; switch (reg) { case MII_BMCR: /* Basic Control */ @@ -XXX,XX +XXX,XX @@ static uint32_t do_phy_read(FTGMAC100State *s, int reg) MII_BMCR_FD | MII_BMCR_CTST) #define MII_ANAR_MASK 0x2d7f -static void do_phy_write(FTGMAC100State *s, int reg, uint32_t val) +static void do_phy_write(FTGMAC100State *s, uint8_t reg, uint16_t val) { switch (reg) { case MII_BMCR: /* Basic Control */ @@ -XXX,XX +XXX,XX @@ static void do_phy_write(FTGMAC100State *s, int reg, uint32_t val) } } +static void do_phy_new_ctl(FTGMAC100State *s) +{ + uint8_t reg; + uint16_t data; + + if (!(s->phycr & FTGMAC100_PHYCR_NEW_ST_22)) { + qemu_log_mask(LOG_UNIMP, "%s: unsupported ST code\n", __func__); + return; + } + + /* Nothing to do */ + if (!(s->phycr & FTGMAC100_PHYCR_NEW_FIRE)) { + return; + } + + reg = FTGMAC100_PHYCR_NEW_REG(s->phycr); + data = FTGMAC100_PHYCR_NEW_DATA(s->phycr); + + switch (FTGMAC100_PHYCR_NEW_OP(s->phycr)) { + case FTGMAC100_PHYCR_NEW_OP_WRITE: + do_phy_write(s, reg, data); + break; + case FTGMAC100_PHYCR_NEW_OP_READ: + s->phydata = do_phy_read(s, reg) & 0xffff; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid OP code %08x\n", + __func__, s->phycr); + } + + s->phycr &= ~FTGMAC100_PHYCR_NEW_FIRE; +} + +static void do_phy_ctl(FTGMAC100State *s) +{ + uint8_t reg = FTGMAC100_PHYCR_REG(s->phycr); + + if (s->phycr & FTGMAC100_PHYCR_MIIWR) { + do_phy_write(s, reg, s->phydata & 0xffff); + s->phycr &= ~FTGMAC100_PHYCR_MIIWR; + } else if (s->phycr & FTGMAC100_PHYCR_MIIRD) { + s->phydata = do_phy_read(s, reg) << 16; + s->phycr &= ~FTGMAC100_PHYCR_MIIRD; + } else { + qemu_log_mask(LOG_GUEST_ERROR, "%s: no OP code %08x\n", + __func__, s->phycr); + } +} + static int ftgmac100_read_bd(FTGMAC100Desc *bd, dma_addr_t addr) { if (dma_memory_read(&address_space_memory, addr, bd, sizeof(*bd))) { @@ -XXX,XX +XXX,XX @@ static void ftgmac100_write(void *opaque, hwaddr addr, uint64_t value, unsigned size) { FTGMAC100State *s = FTGMAC100(opaque); - int reg; switch (addr & 0xff) { case FTGMAC100_ISR: /* Interrupt status */ @@ -XXX,XX +XXX,XX @@ static void ftgmac100_write(void *opaque, hwaddr addr, break; case FTGMAC100_PHYCR: /* PHY Device control */ - reg = FTGMAC100_PHYCR_REG(value); s->phycr = value; - if (value & FTGMAC100_PHYCR_MIIWR) { - do_phy_write(s, reg, s->phydata & 0xffff); - s->phycr &= ~FTGMAC100_PHYCR_MIIWR; + if (s->revr & FTGMAC100_REVR_NEW_MDIO_INTERFACE) { + do_phy_new_ctl(s); } else { - s->phydata = do_phy_read(s, reg) << 16; - s->phycr &= ~FTGMAC100_PHYCR_MIIRD; + do_phy_ctl(s); } break; case FTGMAC100_PHYDATA: @@ -XXX,XX +XXX,XX @@ static void ftgmac100_write(void *opaque, hwaddr addr, s->dblac = value; break; case FTGMAC100_REVR: /* Feature Register */ - /* TODO: Only Old MDIO interface is supported */ - s->revr = value & ~FTGMAC100_REVR_NEW_MDIO_INTERFACE; + s->revr = value; break; case FTGMAC100_FEAR1: /* Feature Register 1 */ s->fear1 = value; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Add storage space for the 5 encryption keys. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 30 +++++++++++++++++++++++++++++- 1 file changed, 29 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct ARMVectorReg { uint64_t d[2 * ARM_MAX_VQ] QEMU_ALIGNED(16); } ARMVectorReg; -/* In AArch32 mode, predicate registers do not exist at all. */ #ifdef TARGET_AARCH64 +/* In AArch32 mode, predicate registers do not exist at all. */ typedef struct ARMPredicateReg { uint64_t p[2 * ARM_MAX_VQ / 8] QEMU_ALIGNED(16); } ARMPredicateReg; + +/* In AArch32 mode, PAC keys do not exist at all. */ +typedef struct ARMPACKey { + uint64_t lo, hi; +} ARMPACKey; #endif @@ -XXX,XX +XXX,XX @@ typedef struct CPUARMState { uint32_t cregs[16]; } iwmmxt; +#ifdef TARGET_AARCH64 + ARMPACKey apia_key; + ARMPACKey apib_key; + ARMPACKey apda_key; + ARMPACKey apdb_key; + ARMPACKey apga_key; +#endif + #if defined(CONFIG_USER_ONLY) /* For usermode syscall translation. */ int eabi; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; } +static inline bool isar_feature_aa64_pauth(const ARMISARegisters *id) +{ + /* + * Note that while QEMU will only implement the architected algorithm + * QARMA, and thus APA+GPA, the host cpu for kvm may use implementation + * defined algorithms, and thus API+GPI, and this predicate controls + * migration of the 128-bit keys. + */ + return (id->id_aa64isar1 & + (FIELD_DP64(0, ID_AA64ISAR1, APA, -1) | + FIELD_DP64(0, ID_AA64ISAR1, API, -1) | + FIELD_DP64(0, ID_AA64ISAR1, GPA, -1) | + FIELD_DP64(0, ID_AA64ISAR1, GPI, -1))) != 0; +} + static inline bool isar_feature_aa64_fp16(const ARMISARegisters *id) { /* We always set the AdvSIMD and FP fields identically wrt FP16. */ -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Post v8.4 bits taken from SysReg_v85_xml-00bet8. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 45 +++++++++++++++++++++++++++++++++------------ 1 file changed, 33 insertions(+), 12 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ void pmccntr_sync(CPUARMState *env); #define SCTLR_A (1U << 1) #define SCTLR_C (1U << 2) #define SCTLR_W (1U << 3) /* up to v6; RAO in v7 */ -#define SCTLR_SA (1U << 3) +#define SCTLR_nTLSMD_32 (1U << 3) /* v8.2-LSMAOC, AArch32 only */ +#define SCTLR_SA (1U << 3) /* AArch64 only */ #define SCTLR_P (1U << 4) /* up to v5; RAO in v6 and v7 */ +#define SCTLR_LSMAOE_32 (1U << 4) /* v8.2-LSMAOC, AArch32 only */ #define SCTLR_SA0 (1U << 4) /* v8 onward, AArch64 only */ #define SCTLR_D (1U << 5) /* up to v5; RAO in v6 */ #define SCTLR_CP15BEN (1U << 5) /* v7 onward */ #define SCTLR_L (1U << 6) /* up to v5; RAO in v6 and v7; RAZ in v8 */ +#define SCTLR_nAA (1U << 6) /* when v8.4-LSE is implemented */ #define SCTLR_B (1U << 7) /* up to v6; RAZ in v7 */ #define SCTLR_ITD (1U << 7) /* v8 onward */ #define SCTLR_S (1U << 8) /* up to v6; RAZ in v7 */ @@ -XXX,XX +XXX,XX @@ void pmccntr_sync(CPUARMState *env); #define SCTLR_R (1U << 9) /* up to v6; RAZ in v7 */ #define SCTLR_UMA (1U << 9) /* v8 onward, AArch64 only */ #define SCTLR_F (1U << 10) /* up to v6 */ -#define SCTLR_SW (1U << 10) /* v7 onward */ -#define SCTLR_Z (1U << 11) +#define SCTLR_SW (1U << 10) /* v7, RES0 in v8 */ +#define SCTLR_Z (1U << 11) /* in v7, RES1 in v8 */ +#define SCTLR_EOS (1U << 11) /* v8.5-ExS */ #define SCTLR_I (1U << 12) -#define SCTLR_V (1U << 13) +#define SCTLR_V (1U << 13) /* AArch32 only */ +#define SCTLR_EnDB (1U << 13) /* v8.3, AArch64 only */ #define SCTLR_RR (1U << 14) /* up to v7 */ #define SCTLR_DZE (1U << 14) /* v8 onward, AArch64 only */ #define SCTLR_L4 (1U << 15) /* up to v6; RAZ in v7 */ #define SCTLR_UCT (1U << 15) /* v8 onward, AArch64 only */ #define SCTLR_DT (1U << 16) /* up to ??, RAO in v6 and v7 */ #define SCTLR_nTWI (1U << 16) /* v8 onward */ -#define SCTLR_HA (1U << 17) +#define SCTLR_HA (1U << 17) /* up to v7, RES0 in v8 */ #define SCTLR_BR (1U << 17) /* PMSA only */ #define SCTLR_IT (1U << 18) /* up to ??, RAO in v6 and v7 */ #define SCTLR_nTWE (1U << 18) /* v8 onward */ #define SCTLR_WXN (1U << 19) #define SCTLR_ST (1U << 20) /* up to ??, RAZ in v6 */ -#define SCTLR_UWXN (1U << 20) /* v7 onward */ -#define SCTLR_FI (1U << 21) -#define SCTLR_U (1U << 22) +#define SCTLR_UWXN (1U << 20) /* v7 onward, AArch32 only */ +#define SCTLR_FI (1U << 21) /* up to v7, v8 RES0 */ +#define SCTLR_IESB (1U << 21) /* v8.2-IESB, AArch64 only */ +#define SCTLR_U (1U << 22) /* up to v6, RAO in v7 */ +#define SCTLR_EIS (1U << 22) /* v8.5-ExS */ #define SCTLR_XP (1U << 23) /* up to v6; v7 onward RAO */ +#define SCTLR_SPAN (1U << 23) /* v8.1-PAN */ #define SCTLR_VE (1U << 24) /* up to v7 */ #define SCTLR_E0E (1U << 24) /* v8 onward, AArch64 only */ #define SCTLR_EE (1U << 25) #define SCTLR_L2 (1U << 26) /* up to v6, RAZ in v7 */ #define SCTLR_UCI (1U << 26) /* v8 onward, AArch64 only */ -#define SCTLR_NMFI (1U << 27) -#define SCTLR_TRE (1U << 28) -#define SCTLR_AFE (1U << 29) -#define SCTLR_TE (1U << 30) +#define SCTLR_NMFI (1U << 27) /* up to v7, RAZ in v7VE and v8 */ +#define SCTLR_EnDA (1U << 27) /* v8.3, AArch64 only */ +#define SCTLR_TRE (1U << 28) /* AArch32 only */ +#define SCTLR_nTLSMD_64 (1U << 28) /* v8.2-LSMAOC, AArch64 only */ +#define SCTLR_AFE (1U << 29) /* AArch32 only */ +#define SCTLR_LSMAOE_64 (1U << 29) /* v8.2-LSMAOC, AArch64 only */ +#define SCTLR_TE (1U << 30) /* AArch32 only */ +#define SCTLR_EnIB (1U << 30) /* v8.3, AArch64 only */ +#define SCTLR_EnIA (1U << 31) /* v8.3, AArch64 only */ +#define SCTLR_BT0 (1ULL << 35) /* v8.5-BTI */ +#define SCTLR_BT1 (1ULL << 36) /* v8.5-BTI */ +#define SCTLR_ITFSB (1ULL << 37) /* v8.5-MemTag */ +#define SCTLR_TCF0 (3ULL << 38) /* v8.5-MemTag */ +#define SCTLR_TCF (3ULL << 40) /* v8.5-MemTag */ +#define SCTLR_ATA0 (1ULL << 42) /* v8.5-MemTag */ +#define SCTLR_ATA (1ULL << 43) /* v8.5-MemTag */ +#define SCTLR_DSSBS (1ULL << 44) /* v8.5 */ #define CPTR_TCPAC (1U << 31) #define CPTR_TTA (1U << 20) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> There are 5 bits of state that could be added, but to save space within tbflags, add only a single enable bit. Helpers will determine the rest of the state at runtime. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 1 + target/arm/translate.h | 2 ++ target/arm/helper.c | 19 +++++++++++++++++++ target/arm/translate-a64.c | 1 + 4 files changed, 23 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A64, TBI0, 0, 1) FIELD(TBFLAG_A64, TBI1, 1, 1) FIELD(TBFLAG_A64, SVEEXC_EL, 2, 2) FIELD(TBFLAG_A64, ZCR_LEN, 4, 4) +FIELD(TBFLAG_A64, PAUTH_ACTIVE, 8, 1) static inline bool bswap_code(bool sctlr_b) { diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { bool is_ldex; /* True if a single-step exception will be taken to the current EL */ bool ss_same_el; + /* True if v8.3-PAuth is active. */ + bool pauth_active; /* Bottom two bits of XScale c15_cpar coprocessor access control reg */ int c15_cpar; /* TCG op of the current insn_start. */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, flags = FIELD_DP32(flags, TBFLAG_A64, SVEEXC_EL, sve_el); flags = FIELD_DP32(flags, TBFLAG_A64, ZCR_LEN, zcr_len); } + + if (cpu_isar_feature(aa64_pauth, cpu)) { + /* + * In order to save space in flags, we record only whether + * pauth is "inactive", meaning all insns are implemented as + * a nop, or "active" when some action must be performed. + * The decision of which action to take is left to a helper. + */ + uint64_t sctlr; + if (current_el == 0) { + /* FIXME: ARMv8.1-VHE S2 translation regime. */ + sctlr = env->cp15.sctlr_el[1]; + } else { + sctlr = env->cp15.sctlr_el[current_el]; + } + if (sctlr & (SCTLR_EnIA | SCTLR_EnIB | SCTLR_EnDA | SCTLR_EnDB)) { + flags = FIELD_DP32(flags, TBFLAG_A64, PAUTH_ACTIVE, 1); + } + } } else { *pc = env->regs[15]; flags = FIELD_DP32(flags, TBFLAG_A32, THUMB, env->thumb); 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 aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->fp_excp_el = FIELD_EX32(tb_flags, TBFLAG_ANY, FPEXC_EL); dc->sve_excp_el = FIELD_EX32(tb_flags, TBFLAG_A64, SVEEXC_EL); dc->sve_len = (FIELD_EX32(tb_flags, TBFLAG_A64, ZCR_LEN) + 1) * 16; + dc->pauth_active = FIELD_EX32(tb_flags, TBFLAG_A64, PAUTH_ACTIVE); dc->vec_len = 0; dc->vec_stride = 0; dc->cp_regs = arm_cpu->cp_regs; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This path uses cpu_loop_exit_restore to unwind current processor state. Suggested-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190108223129.5570-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 7 +++++++ target/arm/op_helper.c | 19 +++++++++++++++++-- 2 files changed, 24 insertions(+), 2 deletions(-) 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 @@ FIELD(V7M_EXCRET, RES1, 7, 25) /* including the must-be-1 prefix */ void QEMU_NORETURN raise_exception(CPUARMState *env, uint32_t excp, uint32_t syndrome, uint32_t target_el); +/* + * Similarly, but also use unwinding to restore cpu state. + */ +void QEMU_NORETURN raise_exception_ra(CPUARMState *env, uint32_t excp, + uint32_t syndrome, uint32_t target_el, + uintptr_t ra); + /* * For AArch64, map a given EL to an index in the banked_spsr array. * Note that this mapping and the AArch32 mapping defined in bank_number() diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ #define SIGNBIT (uint32_t)0x80000000 #define SIGNBIT64 ((uint64_t)1 << 63) -void raise_exception(CPUARMState *env, uint32_t excp, - uint32_t syndrome, uint32_t target_el) +static CPUState *do_raise_exception(CPUARMState *env, uint32_t excp, + uint32_t syndrome, uint32_t target_el) { CPUState *cs = CPU(arm_env_get_cpu(env)); @@ -XXX,XX +XXX,XX @@ void raise_exception(CPUARMState *env, uint32_t excp, cs->exception_index = excp; env->exception.syndrome = syndrome; env->exception.target_el = target_el; + + return cs; +} + +void raise_exception(CPUARMState *env, uint32_t excp, + uint32_t syndrome, uint32_t target_el) +{ + CPUState *cs = do_raise_exception(env, excp, syndrome, target_el); cpu_loop_exit(cs); } +void raise_exception_ra(CPUARMState *env, uint32_t excp, uint32_t syndrome, + uint32_t target_el, uintptr_t ra) +{ + CPUState *cs = do_raise_exception(env, excp, syndrome, target_el); + cpu_loop_exit_restore(cs, ra); +} + static int exception_target_el(CPUARMState *env) { int target_el = MAX(1, arm_current_el(env)); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The cryptographic internals are stubbed out for now, but the enable and trap bits are checked. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190108223129.5570-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/Makefile.objs | 1 + target/arm/helper-a64.h | 12 +++ target/arm/internals.h | 6 ++ target/arm/pauth_helper.c | 186 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 205 insertions(+) create mode 100644 target/arm/pauth_helper.c diff --git a/target/arm/Makefile.objs b/target/arm/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/target/arm/Makefile.objs +++ b/target/arm/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-y += translate.o op_helper.o helper.o cpu.o obj-y += neon_helper.o iwmmxt_helper.o vec_helper.o obj-y += gdbstub.o obj-$(TARGET_AARCH64) += cpu64.o translate-a64.o helper-a64.o gdbstub64.o +obj-$(TARGET_AARCH64) += pauth_helper.o obj-y += crypto_helper.o obj-$(CONFIG_SOFTMMU) += arm-powerctl.o 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_2(advsimd_rinth, f16, f16, ptr) DEF_HELPER_2(advsimd_f16tosinth, i32, f16, ptr) DEF_HELPER_2(advsimd_f16touinth, i32, f16, ptr) DEF_HELPER_2(sqrt_f16, f16, f16, ptr) + +DEF_HELPER_FLAGS_3(pacia, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(pacib, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(pacda, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(pacdb, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(pacga, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(autia, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(autib, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(autda, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_3(autdb, TCG_CALL_NO_WG, i64, env, i64, i64) +DEF_HELPER_FLAGS_2(xpaci, TCG_CALL_NO_RWG_SE, i64, env, i64) +DEF_HELPER_FLAGS_2(xpacd, TCG_CALL_NO_RWG_SE, i64, env, i64) 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 @@ enum arm_exception_class { EC_CP14DTTRAP = 0x06, EC_ADVSIMDFPACCESSTRAP = 0x07, EC_FPIDTRAP = 0x08, + EC_PACTRAP = 0x09, EC_CP14RRTTRAP = 0x0c, EC_ILLEGALSTATE = 0x0e, EC_AA32_SVC = 0x11, @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_sve_access_trap(void) return EC_SVEACCESSTRAP << ARM_EL_EC_SHIFT; } +static inline uint32_t syn_pactrap(void) +{ + return EC_PACTRAP << ARM_EL_EC_SHIFT; +} + static inline uint32_t syn_insn_abort(int same_el, int ea, int s1ptw, int fsc) { return (EC_INSNABORT << ARM_EL_EC_SHIFT) | (same_el << ARM_EL_EC_SHIFT) diff --git a/target/arm/pauth_helper.c b/target/arm/pauth_helper.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/pauth_helper.c @@ -XXX,XX +XXX,XX @@ +/* + * ARM v8.3-PAuth Operations + * + * Copyright (c) 2019 Linaro, Ltd. + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2 of the License, or (at your option) any later version. + * + * This library is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "cpu.h" +#include "internals.h" +#include "exec/exec-all.h" +#include "exec/cpu_ldst.h" +#include "exec/helper-proto.h" +#include "tcg/tcg-gvec-desc.h" + + +static uint64_t pauth_computepac(uint64_t data, uint64_t modifier, + ARMPACKey key) +{ + g_assert_not_reached(); /* FIXME */ +} + +static uint64_t pauth_addpac(CPUARMState *env, uint64_t ptr, uint64_t modifier, + ARMPACKey *key, bool data) +{ + g_assert_not_reached(); /* FIXME */ +} + +static uint64_t pauth_auth(CPUARMState *env, uint64_t ptr, uint64_t modifier, + ARMPACKey *key, bool data, int keynumber) +{ + g_assert_not_reached(); /* FIXME */ +} + +static uint64_t pauth_strip(CPUARMState *env, uint64_t ptr, bool data) +{ + g_assert_not_reached(); /* FIXME */ +} + +static void QEMU_NORETURN pauth_trap(CPUARMState *env, int target_el, + uintptr_t ra) +{ + raise_exception_ra(env, EXCP_UDEF, syn_pactrap(), target_el, ra); +} + +static void pauth_check_trap(CPUARMState *env, int el, uintptr_t ra) +{ + if (el < 2 && arm_feature(env, ARM_FEATURE_EL2)) { + uint64_t hcr = arm_hcr_el2_eff(env); + bool trap = !(hcr & HCR_API); + /* FIXME: ARMv8.1-VHE: trap only applies to EL1&0 regime. */ + /* FIXME: ARMv8.3-NV: HCR_NV trap takes precedence for ERETA[AB]. */ + if (trap) { + pauth_trap(env, 2, ra); + } + } + if (el < 3 && arm_feature(env, ARM_FEATURE_EL3)) { + if (!(env->cp15.scr_el3 & SCR_API)) { + pauth_trap(env, 3, ra); + } + } +} + +static bool pauth_key_enabled(CPUARMState *env, int el, uint32_t bit) +{ + uint32_t sctlr; + if (el == 0) { + /* FIXME: ARMv8.1-VHE S2 translation regime. */ + sctlr = env->cp15.sctlr_el[1]; + } else { + sctlr = env->cp15.sctlr_el[el]; + } + return (sctlr & bit) != 0; +} + +uint64_t HELPER(pacia)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnIA)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_addpac(env, x, y, &env->apia_key, false); +} + +uint64_t HELPER(pacib)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnIB)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_addpac(env, x, y, &env->apib_key, false); +} + +uint64_t HELPER(pacda)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnDA)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_addpac(env, x, y, &env->apda_key, true); +} + +uint64_t HELPER(pacdb)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnDB)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_addpac(env, x, y, &env->apdb_key, true); +} + +uint64_t HELPER(pacga)(CPUARMState *env, uint64_t x, uint64_t y) +{ + uint64_t pac; + + pauth_check_trap(env, arm_current_el(env), GETPC()); + pac = pauth_computepac(x, y, env->apga_key); + + return pac & 0xffffffff00000000ull; +} + +uint64_t HELPER(autia)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnIA)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_auth(env, x, y, &env->apia_key, false, 0); +} + +uint64_t HELPER(autib)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnIB)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_auth(env, x, y, &env->apib_key, false, 1); +} + +uint64_t HELPER(autda)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnDA)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_auth(env, x, y, &env->apda_key, true, 0); +} + +uint64_t HELPER(autdb)(CPUARMState *env, uint64_t x, uint64_t y) +{ + int el = arm_current_el(env); + if (!pauth_key_enabled(env, el, SCTLR_EnDB)) { + return x; + } + pauth_check_trap(env, el, GETPC()); + return pauth_auth(env, x, y, &env->apdb_key, true, 1); +} + +uint64_t HELPER(xpaci)(CPUARMState *env, uint64_t a) +{ + return pauth_strip(env, a, false); +} + +uint64_t HELPER(xpacd)(CPUARMState *env, uint64_t a) +{ + return pauth_strip(env, a, true); +} -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 93 +++++++++++++++++++++++++++++++++----- 1 file changed, 81 insertions(+), 12 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void handle_hint(DisasContext *s, uint32_t insn, } switch (selector) { - case 0: /* NOP */ - return; - case 3: /* WFI */ + case 0b00000: /* NOP */ + break; + case 0b00011: /* WFI */ s->base.is_jmp = DISAS_WFI; - return; + break; + case 0b00001: /* YIELD */ /* When running in MTTCG we don't generate jumps to the yield and * WFE helpers as it won't affect the scheduling of other vCPUs. * If we wanted to more completely model WFE/SEV so we don't busy * spin unnecessarily we would need to do something more involved. */ - case 1: /* YIELD */ if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) { s->base.is_jmp = DISAS_YIELD; } - return; - case 2: /* WFE */ + break; + case 0b00010: /* WFE */ if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) { s->base.is_jmp = DISAS_WFE; } - return; - case 4: /* SEV */ - case 5: /* SEVL */ + break; + case 0b00100: /* SEV */ + case 0b00101: /* SEVL */ /* we treat all as NOP at least for now */ - return; + break; + case 0b00111: /* XPACLRI */ + if (s->pauth_active) { + gen_helper_xpaci(cpu_X[30], cpu_env, cpu_X[30]); + } + break; + case 0b01000: /* PACIA1716 */ + if (s->pauth_active) { + gen_helper_pacia(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); + } + break; + case 0b01010: /* PACIB1716 */ + if (s->pauth_active) { + gen_helper_pacib(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); + } + break; + case 0b01100: /* AUTIA1716 */ + if (s->pauth_active) { + gen_helper_autia(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); + } + break; + case 0b01110: /* AUTIB1716 */ + if (s->pauth_active) { + gen_helper_autib(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); + } + break; + case 0b11000: /* PACIAZ */ + if (s->pauth_active) { + gen_helper_pacia(cpu_X[30], cpu_env, cpu_X[30], + new_tmp_a64_zero(s)); + } + break; + case 0b11001: /* PACIASP */ + if (s->pauth_active) { + gen_helper_pacia(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); + } + break; + case 0b11010: /* PACIBZ */ + if (s->pauth_active) { + gen_helper_pacib(cpu_X[30], cpu_env, cpu_X[30], + new_tmp_a64_zero(s)); + } + break; + case 0b11011: /* PACIBSP */ + if (s->pauth_active) { + gen_helper_pacib(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); + } + break; + case 0b11100: /* AUTIAZ */ + if (s->pauth_active) { + gen_helper_autia(cpu_X[30], cpu_env, cpu_X[30], + new_tmp_a64_zero(s)); + } + break; + case 0b11101: /* AUTIASP */ + if (s->pauth_active) { + gen_helper_autia(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); + } + break; + case 0b11110: /* AUTIBZ */ + if (s->pauth_active) { + gen_helper_autib(cpu_X[30], cpu_env, cpu_X[30], + new_tmp_a64_zero(s)); + } + break; + case 0b11111: /* AUTIBSP */ + if (s->pauth_active) { + gen_helper_autib(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); + } + break; default: /* default specified as NOP equivalent */ - return; + break; } } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Now properly signals unallocated for REV64 with SF=0. Allows for the opcode2 field to be decoded shortly. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 31 ++++++++++++++++++++++--------- 1 file changed, 22 insertions(+), 9 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void handle_rev16(DisasContext *s, unsigned int sf, */ static void disas_data_proc_1src(DisasContext *s, uint32_t insn) { - unsigned int sf, opcode, rn, rd; + unsigned int sf, opcode, opcode2, rn, rd; - if (extract32(insn, 29, 1) || extract32(insn, 16, 5)) { + if (extract32(insn, 29, 1)) { unallocated_encoding(s); return; } sf = extract32(insn, 31, 1); opcode = extract32(insn, 10, 6); + opcode2 = extract32(insn, 16, 5); rn = extract32(insn, 5, 5); rd = extract32(insn, 0, 5); - switch (opcode) { - case 0: /* RBIT */ +#define MAP(SF, O2, O1) ((SF) | (O1 << 1) | (O2 << 7)) + + switch (MAP(sf, opcode2, opcode)) { + case MAP(0, 0x00, 0x00): /* RBIT */ + case MAP(1, 0x00, 0x00): handle_rbit(s, sf, rn, rd); break; - case 1: /* REV16 */ + case MAP(0, 0x00, 0x01): /* REV16 */ + case MAP(1, 0x00, 0x01): handle_rev16(s, sf, rn, rd); break; - case 2: /* REV32 */ + case MAP(0, 0x00, 0x02): /* REV/REV32 */ + case MAP(1, 0x00, 0x02): handle_rev32(s, sf, rn, rd); break; - case 3: /* REV64 */ + case MAP(1, 0x00, 0x03): /* REV64 */ handle_rev64(s, sf, rn, rd); break; - case 4: /* CLZ */ + case MAP(0, 0x00, 0x04): /* CLZ */ + case MAP(1, 0x00, 0x04): handle_clz(s, sf, rn, rd); break; - case 5: /* CLS */ + case MAP(0, 0x00, 0x05): /* CLS */ + case MAP(1, 0x00, 0x05): handle_cls(s, sf, rn, rd); break; + default: + unallocated_encoding(s); + break; } + +#undef MAP } static void handle_div(DisasContext *s, bool is_signed, unsigned int sf, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 146 +++++++++++++++++++++++++++++++++++++ 1 file changed, 146 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_rev16(DisasContext *s, unsigned int sf, static void disas_data_proc_1src(DisasContext *s, uint32_t insn) { unsigned int sf, opcode, opcode2, rn, rd; + TCGv_i64 tcg_rd; if (extract32(insn, 29, 1)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_data_proc_1src(DisasContext *s, uint32_t insn) case MAP(1, 0x00, 0x05): handle_cls(s, sf, rn, rd); break; + case MAP(1, 0x01, 0x00): /* PACIA */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacia(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x01): /* PACIB */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacib(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x02): /* PACDA */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacda(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x03): /* PACDB */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacdb(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x04): /* AUTIA */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autia(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x05): /* AUTIB */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autib(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x06): /* AUTDA */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autda(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x07): /* AUTDB */ + if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autdb(tcg_rd, cpu_env, tcg_rd, cpu_reg_sp(s, rn)); + } else if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + break; + case MAP(1, 0x01, 0x08): /* PACIZA */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacia(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x09): /* PACIZB */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacib(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x0a): /* PACDZA */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacda(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x0b): /* PACDZB */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_pacdb(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x0c): /* AUTIZA */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autia(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x0d): /* AUTIZB */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autib(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x0e): /* AUTDZA */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autda(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x0f): /* AUTDZB */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_autdb(tcg_rd, cpu_env, tcg_rd, new_tmp_a64_zero(s)); + } + break; + case MAP(1, 0x01, 0x10): /* XPACI */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_xpaci(tcg_rd, cpu_env, tcg_rd); + } + break; + case MAP(1, 0x01, 0x11): /* XPACD */ + if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { + goto do_unallocated; + } else if (s->pauth_active) { + tcg_rd = cpu_reg(s, rd); + gen_helper_xpacd(tcg_rd, cpu_env, tcg_rd); + } + break; default: + do_unallocated: unallocated_encoding(s); break; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 8 ++++++++ 1 file changed, 8 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 disas_data_proc_2src(DisasContext *s, uint32_t insn) case 11: /* RORV */ handle_shift_reg(s, A64_SHIFT_TYPE_ROR, sf, rm, rn, rd); break; + case 12: /* PACGA */ + if (sf == 0 || !dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + gen_helper_pacga(cpu_reg(s, rd), cpu_env, + cpu_reg(s, rn), cpu_reg_sp(s, rm)); + break; case 16: case 17: case 18: @@ -XXX,XX +XXX,XX @@ static void disas_data_proc_2src(DisasContext *s, uint32_t insn) break; } default: + do_unallocated: unallocated_encoding(s); break; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This function is only used by AArch64. Code movement only. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.h | 2 + target/arm/helper.h | 1 - target/arm/helper-a64.c | 155 ++++++++++++++++++++++++++++++++++++++++ target/arm/op_helper.c | 155 ---------------------------------------- 4 files changed, 157 insertions(+), 156 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_2(advsimd_f16tosinth, i32, f16, ptr) DEF_HELPER_2(advsimd_f16touinth, i32, f16, ptr) DEF_HELPER_2(sqrt_f16, f16, f16, ptr) +DEF_HELPER_1(exception_return, void, env) + DEF_HELPER_FLAGS_3(pacia, TCG_CALL_NO_WG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(pacib, TCG_CALL_NO_WG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(pacda, TCG_CALL_NO_WG, i64, env, i64, i64) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_2(get_cp_reg64, i64, env, ptr) DEF_HELPER_3(msr_i_pstate, void, env, i32, i32) DEF_HELPER_1(clear_pstate_ss, void, env) -DEF_HELPER_1(exception_return, void, env) DEF_HELPER_2(get_r13_banked, i32, env, i32) DEF_HELPER_3(set_r13_banked, void, env, i32, i32) 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 @@ uint32_t HELPER(advsimd_f16touinth)(uint32_t a, void *fpstp) return float16_to_uint16(a, fpst); } +static int el_from_spsr(uint32_t spsr) +{ + /* Return the exception level that this SPSR is requesting a return to, + * or -1 if it is invalid (an illegal return) + */ + if (spsr & PSTATE_nRW) { + switch (spsr & CPSR_M) { + case ARM_CPU_MODE_USR: + return 0; + case ARM_CPU_MODE_HYP: + return 2; + case ARM_CPU_MODE_FIQ: + case ARM_CPU_MODE_IRQ: + case ARM_CPU_MODE_SVC: + case ARM_CPU_MODE_ABT: + case ARM_CPU_MODE_UND: + case ARM_CPU_MODE_SYS: + return 1; + case ARM_CPU_MODE_MON: + /* Returning to Mon from AArch64 is never possible, + * so this is an illegal return. + */ + default: + return -1; + } + } else { + if (extract32(spsr, 1, 1)) { + /* Return with reserved M[1] bit set */ + return -1; + } + if (extract32(spsr, 0, 4) == 1) { + /* return to EL0 with M[0] bit set */ + return -1; + } + return extract32(spsr, 2, 2); + } +} + +void HELPER(exception_return)(CPUARMState *env) +{ + int cur_el = arm_current_el(env); + unsigned int spsr_idx = aarch64_banked_spsr_index(cur_el); + uint32_t spsr = env->banked_spsr[spsr_idx]; + int new_el; + bool return_to_aa64 = (spsr & PSTATE_nRW) == 0; + + aarch64_save_sp(env, cur_el); + + arm_clear_exclusive(env); + + /* We must squash the PSTATE.SS bit to zero unless both of the + * following hold: + * 1. debug exceptions are currently disabled + * 2. singlestep will be active in the EL we return to + * We check 1 here and 2 after we've done the pstate/cpsr write() to + * transition to the EL we're going to. + */ + if (arm_generate_debug_exceptions(env)) { + spsr &= ~PSTATE_SS; + } + + new_el = el_from_spsr(spsr); + if (new_el == -1) { + goto illegal_return; + } + if (new_el > cur_el + || (new_el == 2 && !arm_feature(env, ARM_FEATURE_EL2))) { + /* Disallow return to an EL which is unimplemented or higher + * than the current one. + */ + goto illegal_return; + } + + if (new_el != 0 && arm_el_is_aa64(env, new_el) != return_to_aa64) { + /* Return to an EL which is configured for a different register width */ + goto illegal_return; + } + + if (new_el == 2 && arm_is_secure_below_el3(env)) { + /* Return to the non-existent secure-EL2 */ + goto illegal_return; + } + + if (new_el == 1 && (arm_hcr_el2_eff(env) & HCR_TGE)) { + goto illegal_return; + } + + qemu_mutex_lock_iothread(); + arm_call_pre_el_change_hook(arm_env_get_cpu(env)); + qemu_mutex_unlock_iothread(); + + if (!return_to_aa64) { + env->aarch64 = 0; + /* We do a raw CPSR write because aarch64_sync_64_to_32() + * will sort the register banks out for us, and we've already + * caught all the bad-mode cases in el_from_spsr(). + */ + cpsr_write(env, spsr, ~0, CPSRWriteRaw); + if (!arm_singlestep_active(env)) { + env->uncached_cpsr &= ~PSTATE_SS; + } + aarch64_sync_64_to_32(env); + + if (spsr & CPSR_T) { + env->regs[15] = env->elr_el[cur_el] & ~0x1; + } else { + env->regs[15] = env->elr_el[cur_el] & ~0x3; + } + qemu_log_mask(CPU_LOG_INT, "Exception return from AArch64 EL%d to " + "AArch32 EL%d PC 0x%" PRIx32 "\n", + cur_el, new_el, env->regs[15]); + } else { + env->aarch64 = 1; + pstate_write(env, spsr); + if (!arm_singlestep_active(env)) { + env->pstate &= ~PSTATE_SS; + } + aarch64_restore_sp(env, new_el); + env->pc = env->elr_el[cur_el]; + qemu_log_mask(CPU_LOG_INT, "Exception return from AArch64 EL%d to " + "AArch64 EL%d PC 0x%" PRIx64 "\n", + cur_el, new_el, env->pc); + } + /* + * Note that cur_el can never be 0. If new_el is 0, then + * el0_a64 is return_to_aa64, else el0_a64 is ignored. + */ + aarch64_sve_change_el(env, cur_el, new_el, return_to_aa64); + + qemu_mutex_lock_iothread(); + arm_call_el_change_hook(arm_env_get_cpu(env)); + qemu_mutex_unlock_iothread(); + + return; + +illegal_return: + /* Illegal return events of various kinds have architecturally + * mandated behaviour: + * restore NZCV and DAIF from SPSR_ELx + * set PSTATE.IL + * restore PC from ELR_ELx + * no change to exception level, execution state or stack pointer + */ + env->pstate |= PSTATE_IL; + env->pc = env->elr_el[cur_el]; + spsr &= PSTATE_NZCV | PSTATE_DAIF; + spsr |= pstate_read(env) & ~(PSTATE_NZCV | PSTATE_DAIF); + pstate_write(env, spsr); + if (!arm_singlestep_active(env)) { + env->pstate &= ~PSTATE_SS; + } + qemu_log_mask(LOG_GUEST_ERROR, "Illegal exception return at EL%d: " + "resuming execution at 0x%" PRIx64 "\n", cur_el, env->pc); +} + /* * Square Root and Reciprocal square root */ diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(pre_smc)(CPUARMState *env, uint32_t syndrome) } } -static int el_from_spsr(uint32_t spsr) -{ - /* Return the exception level that this SPSR is requesting a return to, - * or -1 if it is invalid (an illegal return) - */ - if (spsr & PSTATE_nRW) { - switch (spsr & CPSR_M) { - case ARM_CPU_MODE_USR: - return 0; - case ARM_CPU_MODE_HYP: - return 2; - case ARM_CPU_MODE_FIQ: - case ARM_CPU_MODE_IRQ: - case ARM_CPU_MODE_SVC: - case ARM_CPU_MODE_ABT: - case ARM_CPU_MODE_UND: - case ARM_CPU_MODE_SYS: - return 1; - case ARM_CPU_MODE_MON: - /* Returning to Mon from AArch64 is never possible, - * so this is an illegal return. - */ - default: - return -1; - } - } else { - if (extract32(spsr, 1, 1)) { - /* Return with reserved M[1] bit set */ - return -1; - } - if (extract32(spsr, 0, 4) == 1) { - /* return to EL0 with M[0] bit set */ - return -1; - } - return extract32(spsr, 2, 2); - } -} - -void HELPER(exception_return)(CPUARMState *env) -{ - int cur_el = arm_current_el(env); - unsigned int spsr_idx = aarch64_banked_spsr_index(cur_el); - uint32_t spsr = env->banked_spsr[spsr_idx]; - int new_el; - bool return_to_aa64 = (spsr & PSTATE_nRW) == 0; - - aarch64_save_sp(env, cur_el); - - arm_clear_exclusive(env); - - /* We must squash the PSTATE.SS bit to zero unless both of the - * following hold: - * 1. debug exceptions are currently disabled - * 2. singlestep will be active in the EL we return to - * We check 1 here and 2 after we've done the pstate/cpsr write() to - * transition to the EL we're going to. - */ - if (arm_generate_debug_exceptions(env)) { - spsr &= ~PSTATE_SS; - } - - new_el = el_from_spsr(spsr); - if (new_el == -1) { - goto illegal_return; - } - if (new_el > cur_el - || (new_el == 2 && !arm_feature(env, ARM_FEATURE_EL2))) { - /* Disallow return to an EL which is unimplemented or higher - * than the current one. - */ - goto illegal_return; - } - - if (new_el != 0 && arm_el_is_aa64(env, new_el) != return_to_aa64) { - /* Return to an EL which is configured for a different register width */ - goto illegal_return; - } - - if (new_el == 2 && arm_is_secure_below_el3(env)) { - /* Return to the non-existent secure-EL2 */ - goto illegal_return; - } - - if (new_el == 1 && (arm_hcr_el2_eff(env) & HCR_TGE)) { - goto illegal_return; - } - - qemu_mutex_lock_iothread(); - arm_call_pre_el_change_hook(arm_env_get_cpu(env)); - qemu_mutex_unlock_iothread(); - - if (!return_to_aa64) { - env->aarch64 = 0; - /* We do a raw CPSR write because aarch64_sync_64_to_32() - * will sort the register banks out for us, and we've already - * caught all the bad-mode cases in el_from_spsr(). - */ - cpsr_write(env, spsr, ~0, CPSRWriteRaw); - if (!arm_singlestep_active(env)) { - env->uncached_cpsr &= ~PSTATE_SS; - } - aarch64_sync_64_to_32(env); - - if (spsr & CPSR_T) { - env->regs[15] = env->elr_el[cur_el] & ~0x1; - } else { - env->regs[15] = env->elr_el[cur_el] & ~0x3; - } - qemu_log_mask(CPU_LOG_INT, "Exception return from AArch64 EL%d to " - "AArch32 EL%d PC 0x%" PRIx32 "\n", - cur_el, new_el, env->regs[15]); - } else { - env->aarch64 = 1; - pstate_write(env, spsr); - if (!arm_singlestep_active(env)) { - env->pstate &= ~PSTATE_SS; - } - aarch64_restore_sp(env, new_el); - env->pc = env->elr_el[cur_el]; - qemu_log_mask(CPU_LOG_INT, "Exception return from AArch64 EL%d to " - "AArch64 EL%d PC 0x%" PRIx64 "\n", - cur_el, new_el, env->pc); - } - /* - * Note that cur_el can never be 0. If new_el is 0, then - * el0_a64 is return_to_aa64, else el0_a64 is ignored. - */ - aarch64_sve_change_el(env, cur_el, new_el, return_to_aa64); - - qemu_mutex_lock_iothread(); - arm_call_el_change_hook(arm_env_get_cpu(env)); - qemu_mutex_unlock_iothread(); - - return; - -illegal_return: - /* Illegal return events of various kinds have architecturally - * mandated behaviour: - * restore NZCV and DAIF from SPSR_ELx - * set PSTATE.IL - * restore PC from ELR_ELx - * no change to exception level, execution state or stack pointer - */ - env->pstate |= PSTATE_IL; - env->pc = env->elr_el[cur_el]; - spsr &= PSTATE_NZCV | PSTATE_DAIF; - spsr |= pstate_read(env) & ~(PSTATE_NZCV | PSTATE_DAIF); - pstate_write(env, spsr); - if (!arm_singlestep_active(env)) { - env->pstate &= ~PSTATE_SS; - } - qemu_log_mask(LOG_GUEST_ERROR, "Illegal exception return at EL%d: " - "resuming execution at 0x%" PRIx64 "\n", cur_el, env->pc); -} - /* Return true if the linked breakpoint entry lbn passes its checks */ static bool linked_bp_matches(ARMCPU *cpu, int lbn) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-12-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 | 7 ++++++- 3 files changed, 12 insertions(+), 7 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_2(advsimd_f16tosinth, i32, f16, ptr) DEF_HELPER_2(advsimd_f16touinth, i32, f16, ptr) DEF_HELPER_2(sqrt_f16, f16, f16, ptr) -DEF_HELPER_1(exception_return, void, env) +DEF_HELPER_2(exception_return, void, env, i64) DEF_HELPER_FLAGS_3(pacia, TCG_CALL_NO_WG, i64, env, i64, i64) DEF_HELPER_FLAGS_3(pacib, TCG_CALL_NO_WG, i64, env, i64, i64) 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 int el_from_spsr(uint32_t spsr) } } -void HELPER(exception_return)(CPUARMState *env) +void HELPER(exception_return)(CPUARMState *env, uint64_t new_pc) { int cur_el = arm_current_el(env); unsigned int spsr_idx = aarch64_banked_spsr_index(cur_el); @@ -XXX,XX +XXX,XX @@ void HELPER(exception_return)(CPUARMState *env) aarch64_sync_64_to_32(env); if (spsr & CPSR_T) { - env->regs[15] = env->elr_el[cur_el] & ~0x1; + env->regs[15] = new_pc & ~0x1; } else { - env->regs[15] = env->elr_el[cur_el] & ~0x3; + env->regs[15] = new_pc & ~0x3; } qemu_log_mask(CPU_LOG_INT, "Exception return from AArch64 EL%d to " "AArch32 EL%d PC 0x%" PRIx32 "\n", @@ -XXX,XX +XXX,XX @@ void HELPER(exception_return)(CPUARMState *env) env->pstate &= ~PSTATE_SS; } aarch64_restore_sp(env, new_el); - env->pc = env->elr_el[cur_el]; + env->pc = new_pc; qemu_log_mask(CPU_LOG_INT, "Exception return from AArch64 EL%d to " "AArch64 EL%d PC 0x%" PRIx64 "\n", cur_el, new_el, env->pc); @@ -XXX,XX +XXX,XX @@ illegal_return: * no change to exception level, execution state or stack pointer */ env->pstate |= PSTATE_IL; - env->pc = env->elr_el[cur_el]; + env->pc = new_pc; spsr &= PSTATE_NZCV | PSTATE_DAIF; spsr |= pstate_read(env) & ~(PSTATE_NZCV | PSTATE_DAIF); pstate_write(env, spsr); 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_exc(DisasContext *s, uint32_t insn) static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) { unsigned int opc, op2, op3, rn, op4; + TCGv_i64 dst; opc = extract32(insn, 21, 4); op2 = extract32(insn, 16, 5); @@ -XXX,XX +XXX,XX @@ static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { gen_io_start(); } - gen_helper_exception_return(cpu_env); + dst = tcg_temp_new_i64(); + tcg_gen_ld_i64(dst, cpu_env, + offsetof(CPUARMState, elr_el[s->current_el])); + gen_helper_exception_return(cpu_env, dst); + tcg_temp_free_i64(dst); if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { gen_io_end(); } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This will enable PAuth decode in a subsequent patch. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190108223129.5570-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 47 +++++++++++++++++++++++++++++--------- 1 file changed, 36 insertions(+), 11 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_uncond_b_reg(DisasContext *s, uint32_t insn) rn = extract32(insn, 5, 5); op4 = extract32(insn, 0, 5); - if (op4 != 0x0 || op3 != 0x0 || op2 != 0x1f) { - unallocated_encoding(s); - return; + if (op2 != 0x1f) { + goto do_unallocated; } switch (opc) { case 0: /* BR */ case 1: /* BLR */ case 2: /* RET */ - gen_a64_set_pc(s, cpu_reg(s, rn)); + switch (op3) { + case 0: + if (op4 != 0) { + goto do_unallocated; + } + dst = cpu_reg(s, rn); + break; + + default: + goto do_unallocated; + } + + gen_a64_set_pc(s, dst); /* BLR also needs to load return address */ if (opc == 1) { tcg_gen_movi_i64(cpu_reg(s, 30), s->pc); } break; + case 4: /* ERET */ if (s->current_el == 0) { - unallocated_encoding(s); - return; + goto do_unallocated; + } + switch (op3) { + case 0: + if (op4 != 0) { + goto do_unallocated; + } + dst = tcg_temp_new_i64(); + tcg_gen_ld_i64(dst, cpu_env, + offsetof(CPUARMState, elr_el[s->current_el])); + break; + + default: + goto do_unallocated; } if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { gen_io_start(); } - dst = tcg_temp_new_i64(); - tcg_gen_ld_i64(dst, cpu_env, - offsetof(CPUARMState, elr_el[s->current_el])); + gen_helper_exception_return(cpu_env, dst); tcg_temp_free_i64(dst); if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { @@ -XXX,XX +XXX,XX @@ static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) /* Must exit loop to check un-masked IRQs */ s->base.is_jmp = DISAS_EXIT; return; + case 5: /* DRPS */ - if (rn != 0x1f) { - unallocated_encoding(s); + if (op3 != 0 || op4 != 0 || rn != 0x1f) { + goto do_unallocated; } else { unsupported_encoding(s, insn); } return; + default: + do_unallocated: unallocated_encoding(s); return; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 82 +++++++++++++++++++++++++++++++++++++- 1 file changed, 81 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 disas_uncond_b_reg(DisasContext *s, uint32_t insn) { unsigned int opc, op2, op3, rn, op4; TCGv_i64 dst; + TCGv_i64 modifier; opc = extract32(insn, 21, 4); op2 = extract32(insn, 16, 5); @@ -XXX,XX +XXX,XX @@ static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) case 2: /* RET */ switch (op3) { case 0: + /* BR, BLR, RET */ if (op4 != 0) { goto do_unallocated; } dst = cpu_reg(s, rn); break; + case 2: + case 3: + if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + if (opc == 2) { + /* RETAA, RETAB */ + if (rn != 0x1f || op4 != 0x1f) { + goto do_unallocated; + } + rn = 30; + modifier = cpu_X[31]; + } else { + /* BRAAZ, BRABZ, BLRAAZ, BLRABZ */ + if (op4 != 0x1f) { + goto do_unallocated; + } + modifier = new_tmp_a64_zero(s); + } + if (s->pauth_active) { + dst = new_tmp_a64(s); + if (op3 == 2) { + gen_helper_autia(dst, cpu_env, cpu_reg(s, rn), modifier); + } else { + gen_helper_autib(dst, cpu_env, cpu_reg(s, rn), modifier); + } + } else { + dst = cpu_reg(s, rn); + } + break; + default: goto do_unallocated; } @@ -XXX,XX +XXX,XX @@ static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) } break; + case 8: /* BRAA */ + case 9: /* BLRAA */ + if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + if (op3 != 2 || op3 != 3) { + goto do_unallocated; + } + if (s->pauth_active) { + dst = new_tmp_a64(s); + modifier = cpu_reg_sp(s, op4); + if (op3 == 2) { + gen_helper_autia(dst, cpu_env, cpu_reg(s, rn), modifier); + } else { + gen_helper_autib(dst, cpu_env, cpu_reg(s, rn), modifier); + } + } else { + dst = cpu_reg(s, rn); + } + gen_a64_set_pc(s, dst); + /* BLRAA also needs to load return address */ + if (opc == 9) { + tcg_gen_movi_i64(cpu_reg(s, 30), s->pc); + } + break; + case 4: /* ERET */ if (s->current_el == 0) { goto do_unallocated; } switch (op3) { - case 0: + case 0: /* ERET */ if (op4 != 0) { goto do_unallocated; } @@ -XXX,XX +XXX,XX @@ static void disas_uncond_b_reg(DisasContext *s, uint32_t insn) offsetof(CPUARMState, elr_el[s->current_el])); break; + case 2: /* ERETAA */ + case 3: /* ERETAB */ + if (!dc_isar_feature(aa64_pauth, s)) { + goto do_unallocated; + } + if (rn != 0x1f || op4 != 0x1f) { + goto do_unallocated; + } + dst = tcg_temp_new_i64(); + tcg_gen_ld_i64(dst, cpu_env, + offsetof(CPUARMState, elr_el[s->current_el])); + if (s->pauth_active) { + modifier = cpu_X[31]; + if (op3 == 2) { + gen_helper_autia(dst, cpu_env, dst, modifier); + } else { + gen_helper_autib(dst, cpu_env, dst, modifier); + } + } + break; + default: goto do_unallocated; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Not that there are any stores involved, but why argue with ARM's naming convention. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190108223129.5570-15-richard.henderson@linaro.org [fixed trivial comment nit] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 61 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 61 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 disas_ldst_atomic(DisasContext *s, uint32_t insn, s->be_data | size | MO_ALIGN); } +/* + * PAC memory operations + * + * 31 30 27 26 24 22 21 12 11 10 5 0 + * +------+-------+---+-----+-----+---+--------+---+---+----+-----+ + * | size | 1 1 1 | V | 0 0 | M S | 1 | imm9 | W | 1 | Rn | Rt | + * +------+-------+---+-----+-----+---+--------+---+---+----+-----+ + * + * Rt: the result register + * Rn: base address or SP + * V: vector flag (always 0 as of v8.3) + * M: clear for key DA, set for key DB + * W: pre-indexing flag + * S: sign for imm9. + */ +static void disas_ldst_pac(DisasContext *s, uint32_t insn, + int size, int rt, bool is_vector) +{ + int rn = extract32(insn, 5, 5); + bool is_wback = extract32(insn, 11, 1); + bool use_key_a = !extract32(insn, 23, 1); + int offset; + TCGv_i64 tcg_addr, tcg_rt; + + if (size != 3 || is_vector || !dc_isar_feature(aa64_pauth, s)) { + unallocated_encoding(s); + return; + } + + if (rn == 31) { + gen_check_sp_alignment(s); + } + tcg_addr = read_cpu_reg_sp(s, rn, 1); + + if (s->pauth_active) { + if (use_key_a) { + gen_helper_autda(tcg_addr, cpu_env, tcg_addr, cpu_X[31]); + } else { + gen_helper_autdb(tcg_addr, cpu_env, tcg_addr, cpu_X[31]); + } + } + + /* Form the 10-bit signed, scaled offset. */ + offset = (extract32(insn, 22, 1) << 9) | extract32(insn, 12, 9); + offset = sextract32(offset << size, 0, 10 + size); + tcg_gen_addi_i64(tcg_addr, tcg_addr, offset); + + tcg_rt = cpu_reg(s, rt); + + do_gpr_ld(s, tcg_rt, tcg_addr, size, /* is_signed */ false, + /* extend */ false, /* iss_valid */ !is_wback, + /* iss_srt */ rt, /* iss_sf */ true, /* iss_ar */ false); + + if (is_wback) { + tcg_gen_mov_i64(cpu_reg_sp(s, rn), tcg_addr); + } +} + /* Load/store register (all forms) */ static void disas_ldst_reg(DisasContext *s, uint32_t insn) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg(DisasContext *s, uint32_t insn) case 2: disas_ldst_reg_roffset(s, insn, opc, size, rt, is_vector); return; + default: + disas_ldst_pac(s, insn, size, rt, is_vector); + return; } break; case 1: -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This function is, or will shortly become, too big to inline. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 48 +++++---------------------------------------- target/arm/helper.c | 44 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 49 insertions(+), 43 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline int arm_mmu_idx_to_el(ARMMMUIdx mmu_idx) } /* Return the MMU index for a v7M CPU in the specified security and - * privilege state + * privilege state. */ -static inline ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env, - bool secstate, - bool priv) -{ - ARMMMUIdx mmu_idx = ARM_MMU_IDX_M; - - if (priv) { - mmu_idx |= ARM_MMU_IDX_M_PRIV; - } - - if (armv7m_nvic_neg_prio_requested(env->nvic, secstate)) { - mmu_idx |= ARM_MMU_IDX_M_NEGPRI; - } - - if (secstate) { - mmu_idx |= ARM_MMU_IDX_M_S; - } - - return mmu_idx; -} +ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env, + bool secstate, bool priv); /* Return the MMU index for a v7M CPU in the specified security state */ -static inline ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, - bool secstate) -{ - bool priv = arm_current_el(env) != 0; - - return arm_v7m_mmu_idx_for_secstate_and_priv(env, secstate, priv); -} +ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate); /* Determine the current mmu_idx to use for normal loads/stores */ -static inline int cpu_mmu_index(CPUARMState *env, bool ifetch) -{ - int el = arm_current_el(env); - - if (arm_feature(env, ARM_FEATURE_M)) { - ARMMMUIdx mmu_idx = arm_v7m_mmu_idx_for_secstate(env, env->v7m.secure); - - return arm_to_core_mmu_idx(mmu_idx); - } - - if (el < 2 && arm_is_secure_below_el3(env)) { - return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0 + el); - } - return el; -} +int cpu_mmu_index(CPUARMState *env, bool ifetch); /* Indexes used when registering address spaces with cpu_address_space_init */ typedef enum ARMASIdx { 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 @@ int fp_exception_el(CPUARMState *env, int cur_el) return 0; } +ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env, + bool secstate, bool priv) +{ + ARMMMUIdx mmu_idx = ARM_MMU_IDX_M; + + if (priv) { + mmu_idx |= ARM_MMU_IDX_M_PRIV; + } + + if (armv7m_nvic_neg_prio_requested(env->nvic, secstate)) { + mmu_idx |= ARM_MMU_IDX_M_NEGPRI; + } + + if (secstate) { + mmu_idx |= ARM_MMU_IDX_M_S; + } + + return mmu_idx; +} + +/* Return the MMU index for a v7M CPU in the specified security state */ +ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate) +{ + bool priv = arm_current_el(env) != 0; + + return arm_v7m_mmu_idx_for_secstate_and_priv(env, secstate, priv); +} + +int cpu_mmu_index(CPUARMState *env, bool ifetch) +{ + int el = arm_current_el(env); + + if (arm_feature(env, ARM_FEATURE_M)) { + ARMMMUIdx mmu_idx = arm_v7m_mmu_idx_for_secstate(env, env->v7m.secure); + + return arm_to_core_mmu_idx(mmu_idx); + } + + if (el < 2 && arm_is_secure_below_el3(env)) { + return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0 + el); + } + return el; +} + void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *pflags) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The pattern ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); is computing the full ARMMMUIdx, stripping off the ARM bits, and then putting them back. Avoid the extra two steps with the appropriate helper function. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 9 ++++++++- target/arm/internals.h | 8 ++++++++ target/arm/helper.c | 27 ++++++++++++++++----------- 3 files changed, 32 insertions(+), 12 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ ARMMMUIdx arm_v7m_mmu_idx_for_secstate_and_priv(CPUARMState *env, /* Return the MMU index for a v7M CPU in the specified security state */ ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate); -/* Determine the current mmu_idx to use for normal loads/stores */ +/** + * cpu_mmu_index: + * @env: The cpu environment + * @ifetch: True for code access, false for data access. + * + * Return the core mmu index for the current translation regime. + * This function is used by generic TCG code paths. + */ int cpu_mmu_index(CPUARMState *env, bool ifetch); /* Indexes used when registering address spaces with cpu_address_space_init */ 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_update_virq(ARMCPU *cpu); */ void arm_cpu_update_vfiq(ARMCPU *cpu); +/** + * arm_mmu_idx: + * @env: The cpu environment + * + * Return the full ARMMMUIdx for the current translation regime. + */ +ARMMMUIdx arm_mmu_idx(CPUARMState *env); + #endif diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static bool v7m_push_callee_stack(ARMCPU *cpu, uint32_t lr, bool dotailchain, limit = env->v7m.msplim[M_REG_S]; } } else { - mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); + mmu_idx = arm_mmu_idx(env); frame_sp_p = &env->regs[13]; limit = v7m_sp_limit(env); } @@ -XXX,XX +XXX,XX @@ static bool v7m_push_stack(ARMCPU *cpu) CPUARMState *env = &cpu->env; uint32_t xpsr = xpsr_read(env); uint32_t frameptr = env->regs[13]; - ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); + ARMMMUIdx mmu_idx = arm_mmu_idx(env); /* Align stack pointer if the guest wants that */ if ((frameptr & 4) && @@ -XXX,XX +XXX,XX @@ hwaddr arm_cpu_get_phys_page_attrs_debug(CPUState *cs, vaddr addr, int prot; bool ret; ARMMMUFaultInfo fi = {}; - ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); + ARMMMUIdx mmu_idx = arm_mmu_idx(env); *attrs = (MemTxAttrs) {}; @@ -XXX,XX +XXX,XX @@ ARMMMUIdx arm_v7m_mmu_idx_for_secstate(CPUARMState *env, bool secstate) return arm_v7m_mmu_idx_for_secstate_and_priv(env, secstate, priv); } -int cpu_mmu_index(CPUARMState *env, bool ifetch) +ARMMMUIdx arm_mmu_idx(CPUARMState *env) { - int el = arm_current_el(env); + int el; if (arm_feature(env, ARM_FEATURE_M)) { - ARMMMUIdx mmu_idx = arm_v7m_mmu_idx_for_secstate(env, env->v7m.secure); - - return arm_to_core_mmu_idx(mmu_idx); + return arm_v7m_mmu_idx_for_secstate(env, env->v7m.secure); } + el = arm_current_el(env); if (el < 2 && arm_is_secure_below_el3(env)) { - return arm_to_core_mmu_idx(ARMMMUIdx_S1SE0 + el); + return ARMMMUIdx_S1SE0 + el; + } else { + return ARMMMUIdx_S12NSE0 + el; } - return el; +} + +int cpu_mmu_index(CPUARMState *env, bool ifetch) +{ + return arm_to_core_mmu_idx(arm_mmu_idx(env)); } void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *pflags) { - ARMMMUIdx mmu_idx = core_to_arm_mmu_idx(env, cpu_mmu_index(env, false)); + ARMMMUIdx mmu_idx = arm_mmu_idx(env); int current_el = arm_current_el(env); int fp_el = fp_exception_el(env, current_el); uint32_t flags = 0; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> While we could expose stage_1_mmu_idx, the combination is probably going to be more useful. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 15 +++++++++++++++ target/arm/helper.c | 7 +++++++ 2 files changed, 22 insertions(+) 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_update_vfiq(ARMCPU *cpu); */ ARMMMUIdx arm_mmu_idx(CPUARMState *env); +/** + * arm_stage1_mmu_idx: + * @env: The cpu environment + * + * Return the ARMMMUIdx for the stage1 traversal for the current regime. + */ +#ifdef CONFIG_USER_ONLY +static inline ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env) +{ + return ARMMMUIdx_S1NSE0; +} +#else +ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env); +#endif + #endif 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 @@ int cpu_mmu_index(CPUARMState *env, bool ifetch) return arm_to_core_mmu_idx(arm_mmu_idx(env)); } +#ifndef CONFIG_USER_ONLY +ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env) +{ + return stage_1_mmu_idx(arm_mmu_idx(env)); +} +#endif + void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *pflags) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Split out functions to extract the virtual address parameters. Let the functions choose T0 or T1 address space half, if present. Extract (most of) the control bits that vary between EL or Tx. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190108223129.5570-19-richard.henderson@linaro.org [PMM: fixed minor checkpatch comment nits] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 14 +++ target/arm/helper.c | 278 ++++++++++++++++++++++------------------- 2 files changed, 164 insertions(+), 128 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env) ARMMMUIdx arm_stage1_mmu_idx(CPUARMState *env); #endif +/* + * Parameters of a given virtual address, as extracted from the + * translation control register (TCR) for a given regime. + */ +typedef struct ARMVAParameters { + unsigned tsz : 8; + unsigned select : 1; + bool tbi : 1; + bool epd : 1; + bool hpd : 1; + bool using16k : 1; + bool using64k : 1; +} ARMVAParameters; + #endif diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint8_t convert_stage2_attrs(CPUARMState *env, uint8_t s2attrs) return (hiattr << 6) | (hihint << 4) | (loattr << 2) | lohint; } +static ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, + ARMMMUIdx mmu_idx, bool data) +{ + uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; + uint32_t el = regime_el(env, mmu_idx); + bool tbi, epd, hpd, using16k, using64k; + int select, tsz; + + /* + * Bit 55 is always between the two regions, and is canonical for + * determining if address tagging is enabled. + */ + select = extract64(va, 55, 1); + + if (el > 1) { + tsz = extract32(tcr, 0, 6); + using64k = extract32(tcr, 14, 1); + using16k = extract32(tcr, 15, 1); + if (mmu_idx == ARMMMUIdx_S2NS) { + /* VTCR_EL2 */ + tbi = hpd = false; + } else { + tbi = extract32(tcr, 20, 1); + hpd = extract32(tcr, 24, 1); + } + epd = false; + } else if (!select) { + tsz = extract32(tcr, 0, 6); + epd = extract32(tcr, 7, 1); + using64k = extract32(tcr, 14, 1); + using16k = extract32(tcr, 15, 1); + tbi = extract64(tcr, 37, 1); + hpd = extract64(tcr, 41, 1); + } else { + int tg = extract32(tcr, 30, 2); + using16k = tg == 1; + using64k = tg == 3; + tsz = extract32(tcr, 16, 6); + epd = extract32(tcr, 23, 1); + tbi = extract64(tcr, 38, 1); + hpd = extract64(tcr, 42, 1); + } + tsz = MIN(tsz, 39); /* TODO: ARMv8.4-TTST */ + tsz = MAX(tsz, 16); /* TODO: ARMv8.2-LVA */ + + return (ARMVAParameters) { + .tsz = tsz, + .select = select, + .tbi = tbi, + .epd = epd, + .hpd = hpd, + .using16k = using16k, + .using64k = using64k, + }; +} + +static ARMVAParameters aa32_va_parameters(CPUARMState *env, uint32_t va, + ARMMMUIdx mmu_idx) +{ + uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; + uint32_t el = regime_el(env, mmu_idx); + int select, tsz; + bool epd, hpd; + + if (mmu_idx == ARMMMUIdx_S2NS) { + /* VTCR */ + bool sext = extract32(tcr, 4, 1); + bool sign = extract32(tcr, 3, 1); + + /* + * If the sign-extend bit is not the same as t0sz[3], the result + * is unpredictable. Flag this as a guest error. + */ + if (sign != sext) { + qemu_log_mask(LOG_GUEST_ERROR, + "AArch32: VTCR.S / VTCR.T0SZ[3] mismatch\n"); + } + tsz = sextract32(tcr, 0, 4) + 8; + select = 0; + hpd = false; + epd = false; + } else if (el == 2) { + /* HTCR */ + tsz = extract32(tcr, 0, 3); + select = 0; + hpd = extract64(tcr, 24, 1); + epd = false; + } else { + int t0sz = extract32(tcr, 0, 3); + int t1sz = extract32(tcr, 16, 3); + + if (t1sz == 0) { + select = va > (0xffffffffu >> t0sz); + } else { + /* Note that we will detect errors later. */ + select = va >= ~(0xffffffffu >> t1sz); + } + if (!select) { + tsz = t0sz; + epd = extract32(tcr, 7, 1); + hpd = extract64(tcr, 41, 1); + } else { + tsz = t1sz; + epd = extract32(tcr, 23, 1); + hpd = extract64(tcr, 42, 1); + } + /* For aarch32, hpd0 is not enabled without t2e as well. */ + hpd &= extract32(tcr, 6, 1); + } + + return (ARMVAParameters) { + .tsz = tsz, + .select = select, + .epd = epd, + .hpd = hpd, + }; +} + static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, MMUAccessType access_type, ARMMMUIdx mmu_idx, hwaddr *phys_ptr, MemTxAttrs *txattrs, int *prot, @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, /* Read an LPAE long-descriptor translation table. */ ARMFaultType fault_type = ARMFault_Translation; uint32_t level; - uint32_t epd = 0; - int32_t t0sz, t1sz; - uint32_t tg; + ARMVAParameters param; uint64_t ttbr; - int ttbr_select; hwaddr descaddr, indexmask, indexmask_grainsize; uint32_t tableattrs; - target_ulong page_size; + target_ulong page_size, top_bits; uint32_t attrs; - int32_t stride = 9; - int32_t addrsize; - int inputsize; - int32_t tbi = 0; + int32_t stride; + int addrsize, inputsize; TCR *tcr = regime_tcr(env, mmu_idx); int ap, ns, xn, pxn; uint32_t el = regime_el(env, mmu_idx); - bool ttbr1_valid = true; + bool ttbr1_valid; uint64_t descaddrmask; bool aarch64 = arm_el_is_aa64(env, el); - bool hpd = false; /* TODO: * This code does not handle the different format TCR for VTCR_EL2. @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, * support for those page table walks. */ if (aarch64) { + param = aa64_va_parameters(env, address, mmu_idx, + access_type != MMU_INST_FETCH); level = 0; - addrsize = 64; - if (el > 1) { - if (mmu_idx != ARMMMUIdx_S2NS) { - tbi = extract64(tcr->raw_tcr, 20, 1); - } - } else { - if (extract64(address, 55, 1)) { - tbi = extract64(tcr->raw_tcr, 38, 1); - } else { - tbi = extract64(tcr->raw_tcr, 37, 1); - } - } - tbi *= 8; - /* If we are in 64-bit EL2 or EL3 then there is no TTBR1, so mark it * invalid. */ - if (el > 1) { - ttbr1_valid = false; - } + ttbr1_valid = (el < 2); + addrsize = 64 - 8 * param.tbi; + inputsize = 64 - param.tsz; } else { + param = aa32_va_parameters(env, address, mmu_idx); level = 1; - addrsize = 32; /* There is no TTBR1 for EL2 */ - if (el == 2) { - ttbr1_valid = false; - } + ttbr1_valid = (el != 2); + addrsize = (mmu_idx == ARMMMUIdx_S2NS ? 40 : 32); + inputsize = addrsize - param.tsz; } - /* Determine whether this address is in the region controlled by - * TTBR0 or TTBR1 (or if it is in neither region and should fault). - * This is a Non-secure PL0/1 stage 1 translation, so controlled by - * TTBCR/TTBR0/TTBR1 in accordance with ARM ARM DDI0406C table B-32: + /* + * We determined the region when collecting the parameters, but we + * have not yet validated that the address is valid for the region. + * Extract the top bits and verify that they all match select. */ - if (aarch64) { - /* AArch64 translation. */ - t0sz = extract32(tcr->raw_tcr, 0, 6); - t0sz = MIN(t0sz, 39); - t0sz = MAX(t0sz, 16); - } else if (mmu_idx != ARMMMUIdx_S2NS) { - /* AArch32 stage 1 translation. */ - t0sz = extract32(tcr->raw_tcr, 0, 3); - } else { - /* AArch32 stage 2 translation. */ - bool sext = extract32(tcr->raw_tcr, 4, 1); - bool sign = extract32(tcr->raw_tcr, 3, 1); - /* Address size is 40-bit for a stage 2 translation, - * and t0sz can be negative (from -8 to 7), - * so we need to adjust it to use the TTBR selecting logic below. - */ - addrsize = 40; - t0sz = sextract32(tcr->raw_tcr, 0, 4) + 8; - - /* If the sign-extend bit is not the same as t0sz[3], the result - * is unpredictable. Flag this as a guest error. */ - if (sign != sext) { - qemu_log_mask(LOG_GUEST_ERROR, - "AArch32: VTCR.S / VTCR.T0SZ[3] mismatch\n"); - } - } - t1sz = extract32(tcr->raw_tcr, 16, 6); - if (aarch64) { - t1sz = MIN(t1sz, 39); - t1sz = MAX(t1sz, 16); - } - if (t0sz && !extract64(address, addrsize - t0sz, t0sz - tbi)) { - /* there is a ttbr0 region and we are in it (high bits all zero) */ - ttbr_select = 0; - } else if (ttbr1_valid && t1sz && - !extract64(~address, addrsize - t1sz, t1sz - tbi)) { - /* there is a ttbr1 region and we are in it (high bits all one) */ - ttbr_select = 1; - } else if (!t0sz) { - /* ttbr0 region is "everything not in the ttbr1 region" */ - ttbr_select = 0; - } else if (!t1sz && ttbr1_valid) { - /* ttbr1 region is "everything not in the ttbr0 region" */ - ttbr_select = 1; - } else { - /* in the gap between the two regions, this is a Translation fault */ + top_bits = sextract64(address, inputsize, addrsize - inputsize); + if (-top_bits != param.select || (param.select && !ttbr1_valid)) { + /* In the gap between the two regions, this is a Translation fault */ fault_type = ARMFault_Translation; goto do_fault; } + if (param.using64k) { + stride = 13; + } else if (param.using16k) { + stride = 11; + } else { + stride = 9; + } + /* Note that QEMU ignores shareability and cacheability attributes, * so we don't need to do anything with the SH, ORGN, IRGN fields * in the TTBCR. Similarly, TTBCR:A1 selects whether we get the @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, * implement any ASID-like capability so we can ignore it (instead * we will always flush the TLB any time the ASID is changed). */ - if (ttbr_select == 0) { - ttbr = regime_ttbr(env, mmu_idx, 0); - if (el < 2) { - epd = extract32(tcr->raw_tcr, 7, 1); - } - inputsize = addrsize - t0sz; - - tg = extract32(tcr->raw_tcr, 14, 2); - if (tg == 1) { /* 64KB pages */ - stride = 13; - } - if (tg == 2) { /* 16KB pages */ - stride = 11; - } - if (aarch64 && el > 1) { - hpd = extract64(tcr->raw_tcr, 24, 1); - } else { - hpd = extract64(tcr->raw_tcr, 41, 1); - } - if (!aarch64) { - /* For aarch32, hpd0 is not enabled without t2e as well. */ - hpd &= extract64(tcr->raw_tcr, 6, 1); - } - } else { - /* We should only be here if TTBR1 is valid */ - assert(ttbr1_valid); - - ttbr = regime_ttbr(env, mmu_idx, 1); - epd = extract32(tcr->raw_tcr, 23, 1); - inputsize = addrsize - t1sz; - - tg = extract32(tcr->raw_tcr, 30, 2); - if (tg == 3) { /* 64KB pages */ - stride = 13; - } - if (tg == 1) { /* 16KB pages */ - stride = 11; - } - hpd = extract64(tcr->raw_tcr, 42, 1); - if (!aarch64) { - /* For aarch32, hpd1 is not enabled without t2e as well. */ - hpd &= extract64(tcr->raw_tcr, 6, 1); - } - } + ttbr = regime_ttbr(env, mmu_idx, param.select); /* Here we should have set up all the parameters for the translation: * inputsize, ttbr, epd, stride, tbi */ - if (epd) { + if (param.epd) { /* Translation table walk disabled => Translation fault on TLB miss * Note: This is always 0 on 64-bit EL2 and EL3. */ @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, target_ulong address, } /* Merge in attributes from table descriptors */ attrs |= nstable << 3; /* NS */ - if (hpd) { + if (param.hpd) { /* HPD disables all the table attributes except NSTable. */ break; } -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We will shortly want to talk about TBI as it relates to data. Passing around a pair of variables is less convenient than a single variable. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190108223129.5570-20-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 3 +-- target/arm/translate.h | 3 +-- target/arm/helper.c | 5 ++--- target/arm/translate-a64.c | 13 +++++++------ 4 files changed, 11 insertions(+), 13 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A32, HANDLER, 21, 1) FIELD(TBFLAG_A32, STACKCHECK, 22, 1) /* Bit usage when in AArch64 state */ -FIELD(TBFLAG_A64, TBI0, 0, 1) -FIELD(TBFLAG_A64, TBI1, 1, 1) +FIELD(TBFLAG_A64, TBII, 0, 2) FIELD(TBFLAG_A64, SVEEXC_EL, 2, 2) FIELD(TBFLAG_A64, ZCR_LEN, 4, 4) FIELD(TBFLAG_A64, PAUTH_ACTIVE, 8, 1) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { int user; #endif ARMMMUIdx mmu_idx; /* MMU index to use for normal loads/stores */ - bool tbi0; /* TBI0 for EL0/1 or TBI for EL2/3 */ - bool tbi1; /* TBI1 for EL0/1, not used for EL2/3 */ + uint8_t tbii; /* TBI1|TBI0 for EL0/1 or TBI for EL2/3 */ bool ns; /* Use non-secure CPREG bank on access */ int fp_excp_el; /* FP exception EL or 0 if enabled */ int sve_excp_el; /* SVE exception EL or 0 if enabled */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, *pc = env->pc; flags = FIELD_DP32(flags, TBFLAG_ANY, AARCH64_STATE, 1); /* Get control bits for tagged addresses */ - flags = FIELD_DP32(flags, TBFLAG_A64, TBI0, + flags = FIELD_DP32(flags, TBFLAG_A64, TBII, + (arm_regime_tbi1(env, mmu_idx) << 1) | arm_regime_tbi0(env, mmu_idx)); - flags = FIELD_DP32(flags, TBFLAG_A64, TBI1, - arm_regime_tbi1(env, mmu_idx)); if (cpu_isar_feature(aa64_sve, cpu)) { int sve_el = sve_exception_el(env, current_el); diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ void gen_a64_set_pc_im(uint64_t val) */ static void gen_a64_set_pc(DisasContext *s, TCGv_i64 src) { + /* Note that TBII is TBI1:TBI0. */ + int tbi = s->tbii; if (s->current_el <= 1) { /* Test if NEITHER or BOTH TBI values are set. If so, no need to * examine bit 55 of address, can just generate code. * If mixed, then test via generated code */ - if (s->tbi0 && s->tbi1) { + if (tbi == 3) { TCGv_i64 tmp_reg = tcg_temp_new_i64(); /* Both bits set, sign extension from bit 55 into [63:56] will * cover both cases @@ -XXX,XX +XXX,XX @@ static void gen_a64_set_pc(DisasContext *s, TCGv_i64 src) tcg_gen_shli_i64(tmp_reg, src, 8); tcg_gen_sari_i64(cpu_pc, tmp_reg, 8); tcg_temp_free_i64(tmp_reg); - } else if (!s->tbi0 && !s->tbi1) { + } else if (tbi == 0) { /* Neither bit set, just load it as-is */ tcg_gen_mov_i64(cpu_pc, src); } else { @@ -XXX,XX +XXX,XX @@ static void gen_a64_set_pc(DisasContext *s, TCGv_i64 src) tcg_gen_andi_i64(tcg_bit55, src, (1ull << 55)); - if (s->tbi0) { + if (tbi == 1) { /* tbi0==1, tbi1==0, so 0-fill upper byte if bit 55 = 0 */ tcg_gen_andi_i64(tcg_tmpval, src, 0x00FFFFFFFFFFFFFFull); @@ -XXX,XX +XXX,XX @@ static void gen_a64_set_pc(DisasContext *s, TCGv_i64 src) tcg_temp_free_i64(tcg_tmpval); } } else { /* EL > 1 */ - if (s->tbi0) { + if (tbi != 0) { /* Force tag byte to all zero */ tcg_gen_andi_i64(cpu_pc, src, 0x00FFFFFFFFFFFFFFull); } else { @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->condexec_cond = 0; core_mmu_idx = FIELD_EX32(tb_flags, TBFLAG_ANY, MMUIDX); dc->mmu_idx = core_to_arm_mmu_idx(env, core_mmu_idx); - dc->tbi0 = FIELD_EX32(tb_flags, TBFLAG_A64, TBI0); - dc->tbi1 = FIELD_EX32(tb_flags, TBFLAG_A64, TBI1); + dc->tbii = FIELD_EX32(tb_flags, TBFLAG_A64, TBII); dc->current_el = arm_mmu_idx_to_el(dc->mmu_idx); #if !defined(CONFIG_USER_ONLY) dc->user = (dc->current_el == 0); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We need to reuse this from helper-a64.c. Provide a stub definition for CONFIG_USER_ONLY. This matches the stub definitions that we removed for arm_regime_tbi{0,1} before. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-21-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 17 +++++++++++++++++ target/arm/helper.c | 4 ++-- 2 files changed, 19 insertions(+), 2 deletions(-) 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 @@ typedef struct ARMVAParameters { bool using64k : 1; } ARMVAParameters; +#ifdef CONFIG_USER_ONLY +static inline ARMVAParameters aa64_va_parameters(CPUARMState *env, + uint64_t va, + ARMMMUIdx mmu_idx, bool data) +{ + return (ARMVAParameters) { + /* 48-bit address space */ + .tsz = 16, + /* We can't handle tagged addresses properly in user-only mode */ + .tbi = false, + }; +} +#else +ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, + ARMMMUIdx mmu_idx, bool data); +#endif + #endif diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint8_t convert_stage2_attrs(CPUARMState *env, uint8_t s2attrs) return (hiattr << 6) | (hihint << 4) | (loattr << 2) | lohint; } -static ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, - ARMMMUIdx mmu_idx, bool data) +ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, + ARMMMUIdx mmu_idx, bool data) { uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; uint32_t el = regime_el(env, mmu_idx); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We will want to check TBI for I and D simultaneously. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190108223129.5570-22-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 15 ++++++++++++--- target/arm/helper.c | 10 ++++++++-- 2 files changed, 20 insertions(+), 5 deletions(-) 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 @@ typedef struct ARMVAParameters { } ARMVAParameters; #ifdef CONFIG_USER_ONLY -static inline ARMVAParameters aa64_va_parameters(CPUARMState *env, - uint64_t va, - ARMMMUIdx mmu_idx, bool data) +static inline ARMVAParameters aa64_va_parameters_both(CPUARMState *env, + uint64_t va, + ARMMMUIdx mmu_idx) { return (ARMVAParameters) { /* 48-bit address space */ @@ -XXX,XX +XXX,XX @@ static inline ARMVAParameters aa64_va_parameters(CPUARMState *env, .tbi = false, }; } + +static inline ARMVAParameters aa64_va_parameters(CPUARMState *env, + uint64_t va, + ARMMMUIdx mmu_idx, bool data) +{ + return aa64_va_parameters_both(env, va, mmu_idx); +} #else +ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, + ARMMMUIdx mmu_idx); ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, ARMMMUIdx mmu_idx, bool data); #endif diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint8_t convert_stage2_attrs(CPUARMState *env, uint8_t s2attrs) return (hiattr << 6) | (hihint << 4) | (loattr << 2) | lohint; } -ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, - ARMMMUIdx mmu_idx, bool data) +ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, + ARMMMUIdx mmu_idx) { uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; uint32_t el = regime_el(env, mmu_idx); @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, }; } +ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, + ARMMMUIdx mmu_idx, bool data) +{ + return aa64_va_parameters_both(env, va, mmu_idx); +} + static ARMVAParameters aa32_va_parameters(CPUARMState *env, uint32_t va, ARMMMUIdx mmu_idx) { -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Use TBID in aa64_va_parameters depending on the data parameter. This automatically updates all existing users of the function. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190108223129.5570-23-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/internals.h | 1 + target/arm/helper.c | 14 +++++++++++--- 2 files changed, 12 insertions(+), 3 deletions(-) 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 @@ typedef struct ARMVAParameters { unsigned tsz : 8; unsigned select : 1; bool tbi : 1; + bool tbid : 1; bool epd : 1; bool hpd : 1; bool using16k : 1; 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 @@ ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, { uint64_t tcr = regime_tcr(env, mmu_idx)->raw_tcr; uint32_t el = regime_el(env, mmu_idx); - bool tbi, epd, hpd, using16k, using64k; + bool tbi, tbid, epd, hpd, using16k, using64k; int select, tsz; /* @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, using16k = extract32(tcr, 15, 1); if (mmu_idx == ARMMMUIdx_S2NS) { /* VTCR_EL2 */ - tbi = hpd = false; + tbi = tbid = hpd = false; } else { tbi = extract32(tcr, 20, 1); hpd = extract32(tcr, 24, 1); + tbid = extract32(tcr, 29, 1); } epd = false; } else if (!select) { @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, using16k = extract32(tcr, 15, 1); tbi = extract64(tcr, 37, 1); hpd = extract64(tcr, 41, 1); + tbid = extract64(tcr, 51, 1); } else { int tg = extract32(tcr, 30, 2); using16k = tg == 1; @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, epd = extract32(tcr, 23, 1); tbi = extract64(tcr, 38, 1); hpd = extract64(tcr, 42, 1); + tbid = extract64(tcr, 52, 1); } tsz = MIN(tsz, 39); /* TODO: ARMv8.4-TTST */ tsz = MAX(tsz, 16); /* TODO: ARMv8.2-LVA */ @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, .tsz = tsz, .select = select, .tbi = tbi, + .tbid = tbid, .epd = epd, .hpd = hpd, .using16k = using16k, @@ -XXX,XX +XXX,XX @@ ARMVAParameters aa64_va_parameters_both(CPUARMState *env, uint64_t va, ARMVAParameters aa64_va_parameters(CPUARMState *env, uint64_t va, ARMMMUIdx mmu_idx, bool data) { - return aa64_va_parameters_both(env, va, mmu_idx); + ARMVAParameters ret = aa64_va_parameters_both(env, va, mmu_idx); + + /* Present TBI as a composite with TBID. */ + ret.tbi &= (data || !ret.tbid); + return ret; } static ARMVAParameters aa32_va_parameters(CPUARMState *env, uint32_t va, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> The arm_regime_tbi{0,1} functions are replacable with the new function by giving the lowest and highest address. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-24-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 35 ----------------------- target/arm/helper.c | 70 ++++++++++++++++----------------------------- 2 files changed, 24 insertions(+), 81 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool arm_cpu_bswap_data(CPUARMState *env) } #endif -#ifndef CONFIG_USER_ONLY -/** - * arm_regime_tbi0: - * @env: CPUARMState - * @mmu_idx: MMU index indicating required translation regime - * - * Extracts the TBI0 value from the appropriate TCR for the current EL - * - * Returns: the TBI0 value. - */ -uint32_t arm_regime_tbi0(CPUARMState *env, ARMMMUIdx mmu_idx); - -/** - * arm_regime_tbi1: - * @env: CPUARMState - * @mmu_idx: MMU index indicating required translation regime - * - * Extracts the TBI1 value from the appropriate TCR for the current EL - * - * Returns: the TBI1 value. - */ -uint32_t arm_regime_tbi1(CPUARMState *env, ARMMMUIdx mmu_idx); -#else -/* We can't handle tagged addresses properly in user-only mode */ -static inline uint32_t arm_regime_tbi0(CPUARMState *env, ARMMMUIdx mmu_idx) -{ - return 0; -} - -static inline uint32_t arm_regime_tbi1(CPUARMState *env, ARMMMUIdx mmu_idx) -{ - return 0; -} -#endif - void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, target_ulong *cs_base, uint32_t *flags); diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static inline ARMMMUIdx stage_1_mmu_idx(ARMMMUIdx mmu_idx) return mmu_idx; } -/* Returns TBI0 value for current regime el */ -uint32_t arm_regime_tbi0(CPUARMState *env, ARMMMUIdx mmu_idx) -{ - TCR *tcr; - uint32_t el; - - /* For EL0 and EL1, TBI is controlled by stage 1's TCR, so convert - * a stage 1+2 mmu index into the appropriate stage 1 mmu index. - */ - mmu_idx = stage_1_mmu_idx(mmu_idx); - - tcr = regime_tcr(env, mmu_idx); - el = regime_el(env, mmu_idx); - - if (el > 1) { - return extract64(tcr->raw_tcr, 20, 1); - } else { - return extract64(tcr->raw_tcr, 37, 1); - } -} - -/* Returns TBI1 value for current regime el */ -uint32_t arm_regime_tbi1(CPUARMState *env, ARMMMUIdx mmu_idx) -{ - TCR *tcr; - uint32_t el; - - /* For EL0 and EL1, TBI is controlled by stage 1's TCR, so convert - * a stage 1+2 mmu index into the appropriate stage 1 mmu index. - */ - mmu_idx = stage_1_mmu_idx(mmu_idx); - - tcr = regime_tcr(env, mmu_idx); - el = regime_el(env, mmu_idx); - - if (el > 1) { - return 0; - } else { - return extract64(tcr->raw_tcr, 38, 1); - } -} - /* Return the TTBR associated with this translation regime */ static inline uint64_t regime_ttbr(CPUARMState *env, ARMMMUIdx mmu_idx, int ttbrn) @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, *pc = env->pc; flags = FIELD_DP32(flags, TBFLAG_ANY, AARCH64_STATE, 1); - /* Get control bits for tagged addresses */ - flags = FIELD_DP32(flags, TBFLAG_A64, TBII, - (arm_regime_tbi1(env, mmu_idx) << 1) | - arm_regime_tbi0(env, mmu_idx)); + +#ifndef CONFIG_USER_ONLY + /* + * Get control bits for tagged addresses. Note that the + * translator only uses this for instruction addresses. + */ + { + ARMMMUIdx stage1 = stage_1_mmu_idx(mmu_idx); + ARMVAParameters p0 = aa64_va_parameters_both(env, 0, stage1); + int tbii, tbid; + + /* FIXME: ARMv8.1-VHE S2 translation regime. */ + if (regime_el(env, stage1) < 2) { + ARMVAParameters p1 = aa64_va_parameters_both(env, -1, stage1); + tbid = (p1.tbi << 1) | p0.tbi; + tbii = tbid & ~((p1.tbid << 1) | p0.tbid); + } else { + tbid = p0.tbi; + tbii = tbid & !p0.tbid; + } + + flags = FIELD_DP32(flags, TBFLAG_A64, TBII, tbii); + } +#endif if (cpu_isar_feature(aa64_sve, cpu)) { int sve_el = sve_exception_el(env, current_el); -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Stripping out the authentication data does not require any crypto, it merely requires the virtual address parameters. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-25-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/pauth_helper.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/target/arm/pauth_helper.c b/target/arm/pauth_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/pauth_helper.c +++ b/target/arm/pauth_helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t pauth_addpac(CPUARMState *env, uint64_t ptr, uint64_t modifier, g_assert_not_reached(); /* FIXME */ } +static uint64_t pauth_original_ptr(uint64_t ptr, ARMVAParameters param) +{ + uint64_t extfield = -param.select; + int bot_pac_bit = 64 - param.tsz; + int top_pac_bit = 64 - 8 * param.tbi; + + return deposit64(ptr, bot_pac_bit, top_pac_bit - bot_pac_bit, extfield); +} + static uint64_t pauth_auth(CPUARMState *env, uint64_t ptr, uint64_t modifier, ARMPACKey *key, bool data, int keynumber) { @@ -XXX,XX +XXX,XX @@ static uint64_t pauth_auth(CPUARMState *env, uint64_t ptr, uint64_t modifier, static uint64_t pauth_strip(CPUARMState *env, uint64_t ptr, bool data) { - g_assert_not_reached(); /* FIXME */ + ARMMMUIdx mmu_idx = arm_stage1_mmu_idx(env); + ARMVAParameters param = aa64_va_parameters(env, ptr, mmu_idx, data); + + return pauth_original_ptr(ptr, param); } static void QEMU_NORETURN pauth_trap(CPUARMState *env, int target_el, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This is not really functional yet, because the crypto is not yet implemented. This, however follows the Auth pseudo function. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-26-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/pauth_helper.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/target/arm/pauth_helper.c b/target/arm/pauth_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/pauth_helper.c +++ b/target/arm/pauth_helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t pauth_original_ptr(uint64_t ptr, ARMVAParameters param) static uint64_t pauth_auth(CPUARMState *env, uint64_t ptr, uint64_t modifier, ARMPACKey *key, bool data, int keynumber) { - g_assert_not_reached(); /* FIXME */ + ARMMMUIdx mmu_idx = arm_stage1_mmu_idx(env); + ARMVAParameters param = aa64_va_parameters(env, ptr, mmu_idx, data); + int bot_bit, top_bit; + uint64_t pac, orig_ptr, test; + + orig_ptr = pauth_original_ptr(ptr, param); + pac = pauth_computepac(orig_ptr, modifier, *key); + bot_bit = 64 - param.tsz; + top_bit = 64 - 8 * param.tbi; + + test = (pac ^ ptr) & ~MAKE_64BIT_MASK(55, 1); + if (unlikely(extract64(test, bot_bit, top_bit - bot_bit))) { + int error_code = (keynumber << 1) | (keynumber ^ 1); + if (param.tbi) { + return deposit64(ptr, 53, 2, error_code); + } else { + return deposit64(ptr, 61, 2, error_code); + } + } + return orig_ptr; } static uint64_t pauth_strip(CPUARMState *env, uint64_t ptr, bool data) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This is not really functional yet, because the crypto is not yet implemented. This, however follows the AddPAC pseudo function. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-27-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/pauth_helper.c | 42 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 41 insertions(+), 1 deletion(-) diff --git a/target/arm/pauth_helper.c b/target/arm/pauth_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/pauth_helper.c +++ b/target/arm/pauth_helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t pauth_computepac(uint64_t data, uint64_t modifier, static uint64_t pauth_addpac(CPUARMState *env, uint64_t ptr, uint64_t modifier, ARMPACKey *key, bool data) { - g_assert_not_reached(); /* FIXME */ + ARMMMUIdx mmu_idx = arm_stage1_mmu_idx(env); + ARMVAParameters param = aa64_va_parameters(env, ptr, mmu_idx, data); + uint64_t pac, ext_ptr, ext, test; + int bot_bit, top_bit; + + /* If tagged pointers are in use, use ptr<55>, otherwise ptr<63>. */ + if (param.tbi) { + ext = sextract64(ptr, 55, 1); + } else { + ext = sextract64(ptr, 63, 1); + } + + /* Build a pointer with known good extension bits. */ + top_bit = 64 - 8 * param.tbi; + bot_bit = 64 - param.tsz; + ext_ptr = deposit64(ptr, bot_bit, top_bit - bot_bit, ext); + + pac = pauth_computepac(ext_ptr, modifier, *key); + + /* + * Check if the ptr has good extension bits and corrupt the + * pointer authentication code if not. + */ + test = sextract64(ptr, bot_bit, top_bit - bot_bit); + if (test != 0 && test != -1) { + pac ^= MAKE_64BIT_MASK(top_bit - 1, 1); + } + + /* + * Preserve the determination between upper and lower at bit 55, + * and insert pointer authentication code. + */ + if (param.tbi) { + ptr &= ~MAKE_64BIT_MASK(bot_bit, 55 - bot_bit + 1); + pac &= MAKE_64BIT_MASK(bot_bit, 54 - bot_bit + 1); + } else { + ptr &= MAKE_64BIT_MASK(0, bot_bit); + pac &= ~(MAKE_64BIT_MASK(55, 1) | MAKE_64BIT_MASK(0, bot_bit)); + } + ext &= MAKE_64BIT_MASK(55, 1); + return pac | ext | ptr; } static uint64_t pauth_original_ptr(uint64_t ptr, ARMVAParameters param) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> This is the main crypto routine, an implementation of QARMA. This matches, as much as possible, ARM pseudocode. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190108223129.5570-28-richard.henderson@linaro.org [PMM: fixed minor checkpatch nits] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/pauth_helper.c | 242 +++++++++++++++++++++++++++++++++++++- 1 file changed, 241 insertions(+), 1 deletion(-) diff --git a/target/arm/pauth_helper.c b/target/arm/pauth_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/pauth_helper.c +++ b/target/arm/pauth_helper.c @@ -XXX,XX +XXX,XX @@ #include "tcg/tcg-gvec-desc.h" +static uint64_t pac_cell_shuffle(uint64_t i) +{ + uint64_t o = 0; + + o |= extract64(i, 52, 4); + o |= extract64(i, 24, 4) << 4; + o |= extract64(i, 44, 4) << 8; + o |= extract64(i, 0, 4) << 12; + + o |= extract64(i, 28, 4) << 16; + o |= extract64(i, 48, 4) << 20; + o |= extract64(i, 4, 4) << 24; + o |= extract64(i, 40, 4) << 28; + + o |= extract64(i, 32, 4) << 32; + o |= extract64(i, 12, 4) << 36; + o |= extract64(i, 56, 4) << 40; + o |= extract64(i, 20, 4) << 44; + + o |= extract64(i, 8, 4) << 48; + o |= extract64(i, 36, 4) << 52; + o |= extract64(i, 16, 4) << 56; + o |= extract64(i, 60, 4) << 60; + + return o; +} + +static uint64_t pac_cell_inv_shuffle(uint64_t i) +{ + uint64_t o = 0; + + o |= extract64(i, 12, 4); + o |= extract64(i, 24, 4) << 4; + o |= extract64(i, 48, 4) << 8; + o |= extract64(i, 36, 4) << 12; + + o |= extract64(i, 56, 4) << 16; + o |= extract64(i, 44, 4) << 20; + o |= extract64(i, 4, 4) << 24; + o |= extract64(i, 16, 4) << 28; + + o |= i & MAKE_64BIT_MASK(32, 4); + o |= extract64(i, 52, 4) << 36; + o |= extract64(i, 28, 4) << 40; + o |= extract64(i, 8, 4) << 44; + + o |= extract64(i, 20, 4) << 48; + o |= extract64(i, 0, 4) << 52; + o |= extract64(i, 40, 4) << 56; + o |= i & MAKE_64BIT_MASK(60, 4); + + return o; +} + +static uint64_t pac_sub(uint64_t i) +{ + static const uint8_t sub[16] = { + 0xb, 0x6, 0x8, 0xf, 0xc, 0x0, 0x9, 0xe, + 0x3, 0x7, 0x4, 0x5, 0xd, 0x2, 0x1, 0xa, + }; + uint64_t o = 0; + int b; + + for (b = 0; b < 64; b += 16) { + o |= (uint64_t)sub[(i >> b) & 0xf] << b; + } + return o; +} + +static uint64_t pac_inv_sub(uint64_t i) +{ + static const uint8_t inv_sub[16] = { + 0x5, 0xe, 0xd, 0x8, 0xa, 0xb, 0x1, 0x9, + 0x2, 0x6, 0xf, 0x0, 0x4, 0xc, 0x7, 0x3, + }; + uint64_t o = 0; + int b; + + for (b = 0; b < 64; b += 16) { + o |= (uint64_t)inv_sub[(i >> b) & 0xf] << b; + } + return o; +} + +static int rot_cell(int cell, int n) +{ + /* 4-bit rotate left by n. */ + cell |= cell << 4; + return extract32(cell, 4 - n, 4); +} + +static uint64_t pac_mult(uint64_t i) +{ + uint64_t o = 0; + int b; + + for (b = 0; b < 4 * 4; b += 4) { + int i0, i4, i8, ic, t0, t1, t2, t3; + + i0 = extract64(i, b, 4); + i4 = extract64(i, b + 4 * 4, 4); + i8 = extract64(i, b + 8 * 4, 4); + ic = extract64(i, b + 12 * 4, 4); + + t0 = rot_cell(i8, 1) ^ rot_cell(i4, 2) ^ rot_cell(i0, 1); + t1 = rot_cell(ic, 1) ^ rot_cell(i4, 1) ^ rot_cell(i0, 2); + t2 = rot_cell(ic, 2) ^ rot_cell(i8, 1) ^ rot_cell(i0, 1); + t3 = rot_cell(ic, 1) ^ rot_cell(i8, 2) ^ rot_cell(i4, 1); + + o |= (uint64_t)t3 << b; + o |= (uint64_t)t2 << (b + 4 * 4); + o |= (uint64_t)t1 << (b + 8 * 4); + o |= (uint64_t)t0 << (b + 12 * 4); + } + return o; +} + +static uint64_t tweak_cell_rot(uint64_t cell) +{ + return (cell >> 1) | (((cell ^ (cell >> 1)) & 1) << 3); +} + +static uint64_t tweak_shuffle(uint64_t i) +{ + uint64_t o = 0; + + o |= extract64(i, 16, 4) << 0; + o |= extract64(i, 20, 4) << 4; + o |= tweak_cell_rot(extract64(i, 24, 4)) << 8; + o |= extract64(i, 28, 4) << 12; + + o |= tweak_cell_rot(extract64(i, 44, 4)) << 16; + o |= extract64(i, 8, 4) << 20; + o |= extract64(i, 12, 4) << 24; + o |= tweak_cell_rot(extract64(i, 32, 4)) << 28; + + o |= extract64(i, 48, 4) << 32; + o |= extract64(i, 52, 4) << 36; + o |= extract64(i, 56, 4) << 40; + o |= tweak_cell_rot(extract64(i, 60, 4)) << 44; + + o |= tweak_cell_rot(extract64(i, 0, 4)) << 48; + o |= extract64(i, 4, 4) << 52; + o |= tweak_cell_rot(extract64(i, 40, 4)) << 56; + o |= tweak_cell_rot(extract64(i, 36, 4)) << 60; + + return o; +} + +static uint64_t tweak_cell_inv_rot(uint64_t cell) +{ + return ((cell << 1) & 0xf) | ((cell & 1) ^ (cell >> 3)); +} + +static uint64_t tweak_inv_shuffle(uint64_t i) +{ + uint64_t o = 0; + + o |= tweak_cell_inv_rot(extract64(i, 48, 4)); + o |= extract64(i, 52, 4) << 4; + o |= extract64(i, 20, 4) << 8; + o |= extract64(i, 24, 4) << 12; + + o |= extract64(i, 0, 4) << 16; + o |= extract64(i, 4, 4) << 20; + o |= tweak_cell_inv_rot(extract64(i, 8, 4)) << 24; + o |= extract64(i, 12, 4) << 28; + + o |= tweak_cell_inv_rot(extract64(i, 28, 4)) << 32; + o |= tweak_cell_inv_rot(extract64(i, 60, 4)) << 36; + o |= tweak_cell_inv_rot(extract64(i, 56, 4)) << 40; + o |= tweak_cell_inv_rot(extract64(i, 16, 4)) << 44; + + o |= extract64(i, 32, 4) << 48; + o |= extract64(i, 36, 4) << 52; + o |= extract64(i, 40, 4) << 56; + o |= tweak_cell_inv_rot(extract64(i, 44, 4)) << 60; + + return o; +} + static uint64_t pauth_computepac(uint64_t data, uint64_t modifier, ARMPACKey key) { - g_assert_not_reached(); /* FIXME */ + static const uint64_t RC[5] = { + 0x0000000000000000ull, + 0x13198A2E03707344ull, + 0xA4093822299F31D0ull, + 0x082EFA98EC4E6C89ull, + 0x452821E638D01377ull, + }; + const uint64_t alpha = 0xC0AC29B7C97C50DDull; + /* + * Note that in the ARM pseudocode, key0 contains bits <127:64> + * and key1 contains bits <63:0> of the 128-bit key. + */ + uint64_t key0 = key.hi, key1 = key.lo; + uint64_t workingval, runningmod, roundkey, modk0; + int i; + + modk0 = (key0 << 63) | ((key0 >> 1) ^ (key0 >> 63)); + runningmod = modifier; + workingval = data ^ key0; + + for (i = 0; i <= 4; ++i) { + roundkey = key1 ^ runningmod; + workingval ^= roundkey; + workingval ^= RC[i]; + if (i > 0) { + workingval = pac_cell_shuffle(workingval); + workingval = pac_mult(workingval); + } + workingval = pac_sub(workingval); + runningmod = tweak_shuffle(runningmod); + } + roundkey = modk0 ^ runningmod; + workingval ^= roundkey; + workingval = pac_cell_shuffle(workingval); + workingval = pac_mult(workingval); + workingval = pac_sub(workingval); + workingval = pac_cell_shuffle(workingval); + workingval = pac_mult(workingval); + workingval ^= key1; + workingval = pac_cell_inv_shuffle(workingval); + workingval = pac_inv_sub(workingval); + workingval = pac_mult(workingval); + workingval = pac_cell_inv_shuffle(workingval); + workingval ^= key0; + workingval ^= runningmod; + for (i = 0; i <= 4; ++i) { + workingval = pac_inv_sub(workingval); + if (i < 4) { + workingval = pac_mult(workingval); + workingval = pac_cell_inv_shuffle(workingval); + } + runningmod = tweak_inv_shuffle(runningmod); + roundkey = key1 ^ runningmod; + workingval ^= RC[4 - i]; + workingval ^= roundkey; + workingval ^= alpha; + } + workingval ^= modk0; + + return workingval; } static uint64_t pauth_addpac(CPUARMState *env, uint64_t ptr, uint64_t modifier, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-29-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 70 +++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 70 insertions(+) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static CPAccessResult access_lor_other(CPUARMState *env, return access_lor_ns(env); } +#ifdef TARGET_AARCH64 +static CPAccessResult access_pauth(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread) +{ + int el = arm_current_el(env); + + if (el < 2 && + arm_feature(env, ARM_FEATURE_EL2) && + !(arm_hcr_el2_eff(env) & HCR_APK)) { + return CP_ACCESS_TRAP_EL2; + } + if (el < 3 && + arm_feature(env, ARM_FEATURE_EL3) && + !(env->cp15.scr_el3 & SCR_APK)) { + return CP_ACCESS_TRAP_EL3; + } + return CP_ACCESS_OK; +} + +static const ARMCPRegInfo pauth_reginfo[] = { + { .name = "APDAKEYLO_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 2, .opc2 = 0, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apda_key.lo) }, + { .name = "APDAKEYHI_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 2, .opc2 = 1, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apda_key.hi) }, + { .name = "APDBKEYLO_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 2, .opc2 = 2, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apdb_key.lo) }, + { .name = "APDBKEYHI_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 2, .opc2 = 3, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apdb_key.hi) }, + { .name = "APGAKEYLO_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 3, .opc2 = 0, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apga_key.lo) }, + { .name = "APGAKEYHI_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 3, .opc2 = 1, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apga_key.hi) }, + { .name = "APIAKEYLO_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 1, .opc2 = 0, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apia_key.lo) }, + { .name = "APIAKEYHI_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 1, .opc2 = 1, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apia_key.hi) }, + { .name = "APIBKEYLO_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 1, .opc2 = 2, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apib_key.lo) }, + { .name = "APIBKEYHI_EL1", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 0, .crn = 2, .crm = 1, .opc2 = 3, + .access = PL1_RW, .accessfn = access_pauth, + .fieldoffset = offsetof(CPUARMState, apib_key.hi) }, + REGINFO_SENTINEL +}; +#endif + void register_cp_regs_for_features(ARMCPU *cpu) { /* Register all the coprocessor registers based on feature bits */ @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) define_one_arm_cp_reg(cpu, &zcr_el3_reginfo); } } + +#ifdef TARGET_AARCH64 + if (cpu_isar_feature(aa64_pauth, cpu)) { + define_arm_cp_regs(cpu, pauth_reginfo); + } +#endif } void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu) -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-30-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = cpu->isar.id_aa64isar1; t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); + t = FIELD_DP64(t, ID_AA64ISAR1, APA, 1); /* PAuth, architected only */ + t = FIELD_DP64(t, ID_AA64ISAR1, API, 0); + t = FIELD_DP64(t, ID_AA64ISAR1, GPA, 1); + t = FIELD_DP64(t, ID_AA64ISAR1, GPI, 0); cpu->isar.id_aa64isar1 = t; t = cpu->isar.id_aa64pfr0; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Add 4 attributes that controls the EL1 enable bits, as we may not always want to turn on pointer authentication with -cpu max. However, by default they are enabled. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20190108223129.5570-31-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 3 +++ target/arm/cpu64.c | 60 ++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 63 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->pstate = PSTATE_MODE_EL0t; /* Userspace expects access to DC ZVA, CTL_EL0 and the cache ops */ env->cp15.sctlr_el[1] |= SCTLR_UCT | SCTLR_UCI | SCTLR_DZE; + /* Enable all PAC instructions */ + env->cp15.hcr_el2 |= HCR_API; + env->cp15.scr_el3 |= SCR_API; /* and to the FP/Neon instructions */ env->cp15.cpacr_el1 = deposit64(env->cp15.cpacr_el1, 20, 2, 3); /* and to the SVE instructions */ 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_vq(Object *obj, Visitor *v, const char *name, error_propagate(errp, err); } +#ifdef CONFIG_USER_ONLY +static void cpu_max_get_packey(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + ARMCPU *cpu = ARM_CPU(obj); + const uint64_t *bit = opaque; + bool enabled = (cpu->env.cp15.sctlr_el[1] & *bit) != 0; + + visit_type_bool(v, name, &enabled, errp); +} + +static void cpu_max_set_packey(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + ARMCPU *cpu = ARM_CPU(obj); + Error *err = NULL; + const uint64_t *bit = opaque; + bool enabled; + + visit_type_bool(v, name, &enabled, errp); + + if (!err) { + if (enabled) { + cpu->env.cp15.sctlr_el[1] |= *bit; + } else { + cpu->env.cp15.sctlr_el[1] &= ~*bit; + } + } + error_propagate(errp, err); +} +#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; @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) */ cpu->ctr = 0x80038003; /* 32 byte I and D cacheline size, VIPT icache */ cpu->dcz_blocksize = 7; /* 512 bytes */ + + /* + * Note that Linux will enable enable all of the keys at once. + * But doing it this way will allow experimentation beyond that. + */ + { + static const uint64_t apia_bit = SCTLR_EnIA; + static const uint64_t apib_bit = SCTLR_EnIB; + static const uint64_t apda_bit = SCTLR_EnDA; + static const uint64_t apdb_bit = SCTLR_EnDB; + + object_property_add(obj, "apia", "bool", cpu_max_get_packey, + cpu_max_set_packey, NULL, + (void *)&apia_bit, &error_fatal); + object_property_add(obj, "apib", "bool", cpu_max_get_packey, + cpu_max_set_packey, NULL, + (void *)&apib_bit, &error_fatal); + object_property_add(obj, "apda", "bool", cpu_max_get_packey, + cpu_max_set_packey, NULL, + (void *)&apda_bit, &error_fatal); + object_property_add(obj, "apdb", "bool", cpu_max_get_packey, + cpu_max_set_packey, NULL, + (void *)&apdb_bit, &error_fatal); + + /* Enable all PAC keys by default. */ + cpu->env.cp15.sctlr_el[1] |= SCTLR_EnIA | SCTLR_EnIB; + cpu->env.cp15.sctlr_el[1] |= SCTLR_EnDA | SCTLR_EnDB; + } #endif cpu->sve_max_vq = ARM_MAX_VQ; -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> We can perform this with fewer operations. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20190108223129.5570-32-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 62 +++++++++++++------------------------- 1 file changed, 21 insertions(+), 41 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 @@ void gen_a64_set_pc_im(uint64_t val) /* Load the PC from a generic TCG variable. * * If address tagging is enabled via the TCR TBI bits, then loading - * an address into the PC will clear out any tag in the it: + * an address into the PC will clear out any tag in it: * + for EL2 and EL3 there is only one TBI bit, and if it is set * then the address is zero-extended, clearing bits [63:56] * + for EL0 and EL1, TBI0 controls addresses with bit 55 == 0 @@ -XXX,XX +XXX,XX @@ static void gen_a64_set_pc(DisasContext *s, TCGv_i64 src) int tbi = s->tbii; if (s->current_el <= 1) { - /* Test if NEITHER or BOTH TBI values are set. If so, no need to - * examine bit 55 of address, can just generate code. - * If mixed, then test via generated code - */ - if (tbi == 3) { - TCGv_i64 tmp_reg = tcg_temp_new_i64(); - /* Both bits set, sign extension from bit 55 into [63:56] will - * cover both cases - */ - tcg_gen_shli_i64(tmp_reg, src, 8); - tcg_gen_sari_i64(cpu_pc, tmp_reg, 8); - tcg_temp_free_i64(tmp_reg); - } else if (tbi == 0) { - /* Neither bit set, just load it as-is */ - tcg_gen_mov_i64(cpu_pc, src); - } else { - TCGv_i64 tcg_tmpval = tcg_temp_new_i64(); - TCGv_i64 tcg_bit55 = tcg_temp_new_i64(); - TCGv_i64 tcg_zero = tcg_const_i64(0); + if (tbi != 0) { + /* Sign-extend from bit 55. */ + tcg_gen_sextract_i64(cpu_pc, src, 0, 56); - tcg_gen_andi_i64(tcg_bit55, src, (1ull << 55)); + if (tbi != 3) { + TCGv_i64 tcg_zero = tcg_const_i64(0); - if (tbi == 1) { - /* tbi0==1, tbi1==0, so 0-fill upper byte if bit 55 = 0 */ - tcg_gen_andi_i64(tcg_tmpval, src, - 0x00FFFFFFFFFFFFFFull); - tcg_gen_movcond_i64(TCG_COND_EQ, cpu_pc, tcg_bit55, tcg_zero, - tcg_tmpval, src); - } else { - /* tbi0==0, tbi1==1, so 1-fill upper byte if bit 55 = 1 */ - tcg_gen_ori_i64(tcg_tmpval, src, - 0xFF00000000000000ull); - tcg_gen_movcond_i64(TCG_COND_NE, cpu_pc, tcg_bit55, tcg_zero, - tcg_tmpval, src); + /* + * The two TBI bits differ. + * If tbi0, then !tbi1: only use the extension if positive. + * if !tbi0, then tbi1: only use the extension if negative. + */ + tcg_gen_movcond_i64(tbi == 1 ? TCG_COND_GE : TCG_COND_LT, + cpu_pc, cpu_pc, tcg_zero, cpu_pc, src); + tcg_temp_free_i64(tcg_zero); } - tcg_temp_free_i64(tcg_zero); - tcg_temp_free_i64(tcg_bit55); - tcg_temp_free_i64(tcg_tmpval); + return; } - } else { /* EL > 1 */ + } else { if (tbi != 0) { /* Force tag byte to all zero */ - tcg_gen_andi_i64(cpu_pc, src, 0x00FFFFFFFFFFFFFFull); - } else { - /* Load unmodified address */ - tcg_gen_mov_i64(cpu_pc, src); + tcg_gen_extract_i64(cpu_pc, src, 0, 56); + return; } } + + /* Load unmodified address */ + tcg_gen_mov_i64(cpu_pc, src); } typedef struct DisasCompare64 { -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> In some cases it may be helpful to modify state before saving it for migration, and then modify the state back after it has been saved. The existing pre_save function provides half of this functionality. This patch adds a post_save function to provide the second half. Signed-off-by: Aaron Lindsay <aclindsa@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Dr. David Alan Gilbert <dgilbert@redhat.com> Message-id: 20181211151945.29137-2-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/migration/vmstate.h | 1 + migration/vmstate.c | 13 ++++++++++++- docs/devel/migration.rst | 9 +++++++-- 3 files changed, 20 insertions(+), 3 deletions(-) diff --git a/include/migration/vmstate.h b/include/migration/vmstate.h index XXXXXXX..XXXXXXX 100644 --- a/include/migration/vmstate.h +++ b/include/migration/vmstate.h @@ -XXX,XX +XXX,XX @@ struct VMStateDescription { int (*pre_load)(void *opaque); int (*post_load)(void *opaque, int version_id); int (*pre_save)(void *opaque); + int (*post_save)(void *opaque); bool (*needed)(void *opaque); const VMStateField *fields; const VMStateDescription **subsections; diff --git a/migration/vmstate.c b/migration/vmstate.c index XXXXXXX..XXXXXXX 100644 --- a/migration/vmstate.c +++ b/migration/vmstate.c @@ -XXX,XX +XXX,XX @@ int vmstate_save_state_v(QEMUFile *f, const VMStateDescription *vmsd, if (ret) { error_report("Save of field %s/%s failed", vmsd->name, field->name); + if (vmsd->post_save) { + vmsd->post_save(opaque); + } return ret; } @@ -XXX,XX +XXX,XX @@ int vmstate_save_state_v(QEMUFile *f, const VMStateDescription *vmsd, json_end_array(vmdesc); } - return vmstate_subsection_save(f, vmsd, opaque, vmdesc); + ret = vmstate_subsection_save(f, vmsd, opaque, vmdesc); + + if (vmsd->post_save) { + int ps_ret = vmsd->post_save(opaque); + if (!ret) { + ret = ps_ret; + } + } + return ret; } static const VMStateDescription * diff --git a/docs/devel/migration.rst b/docs/devel/migration.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/migration.rst +++ b/docs/devel/migration.rst @@ -XXX,XX +XXX,XX @@ The functions to do that are inside a vmstate definition, and are called: This function is called before we save the state of one device. -Example: You can look at hpet.c, that uses the three function to -massage the state that is transferred. +- ``int (*post_save)(void *opaque);`` + + This function is called after we save the state of one device + (even upon failure, unless the call to pre_save returned an error). + +Example: You can look at hpet.c, that uses the first three functions +to massage the state that is transferred. The ``VMSTATE_WITH_TMP`` macro may be useful when the migration data doesn't match the stored device data well; it allows an -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> pmccntr_read and pmccntr_write contained duplicate code that was already being handled by pmccntr_sync. Consolidate the duplicated code into two functions: pmccntr_op_start and pmccntr_op_finish. Add a companion to c15_ccnt in CPUARMState so that we can simultaneously save both the architectural register value and the last underlying cycle count - this ensures time isn't lost and will also allow us to access the 'old' architectural register value in order to detect overflows in later patches. Signed-off-by: Aaron Lindsay <alindsay@codeaurora.org> Signed-off-by: Aaron Lindsay <aclindsa@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20181211151945.29137-3-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 37 +++++++++++--- target/arm/helper.c | 118 ++++++++++++++++++++++++++------------------ 2 files changed, 100 insertions(+), 55 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUARMState { uint64_t oslsr_el1; /* OS Lock Status */ uint64_t mdcr_el2; uint64_t mdcr_el3; - /* If the counter is enabled, this stores the last time the counter - * was reset. Otherwise it stores the counter value + /* Stores the architectural value of the counter *the last time it was + * updated* by pmccntr_op_start. Accesses should always be surrounded + * by pmccntr_op_start/pmccntr_op_finish to guarantee the latest + * architecturally-correct value is being read/set. */ uint64_t c15_ccnt; + /* Stores the delta between the architectural value and the underlying + * cycle count during normal operation. It is used to update c15_ccnt + * to be the correct architectural value before accesses. During + * accesses, c15_ccnt_delta contains the underlying count being used + * for the access, after which it reverts to the delta value in + * pmccntr_op_finish. + */ + uint64_t c15_ccnt_delta; uint64_t pmccfiltr_el0; /* Performance Monitor Filter Register */ uint64_t vpidr_el2; /* Virtualization Processor ID Register */ uint64_t vmpidr_el2; /* Virtualization Multiprocessor ID Register */ @@ -XXX,XX +XXX,XX @@ int cpu_arm_signal_handler(int host_signum, void *pinfo, void *puc); /** - * pmccntr_sync + * pmccntr_op_start/finish * @env: CPUARMState * - * Synchronises the counter in the PMCCNTR. This must always be called twice, - * once before any action that might affect the timer and again afterwards. - * The function is used to swap the state of the register if required. - * This only happens when not in user mode (!CONFIG_USER_ONLY) + * Convert the counter in the PMCCNTR between its delta form (the typical mode + * when it's enabled) and the guest-visible value. These two calls must always + * surround any action which might affect the counter. */ -void pmccntr_sync(CPUARMState *env); +void pmccntr_op_start(CPUARMState *env); +void pmccntr_op_finish(CPUARMState *env); + +/** + * pmu_op_start/finish + * @env: CPUARMState + * + * Convert all PMU counters between their delta form (the typical mode when + * they are enabled) and the guest-visible values. These two calls must + * surround any action which might affect the counters. + */ +void pmu_op_start(CPUARMState *env); +void pmu_op_finish(CPUARMState *env); /* SCTLR bit meanings. Several bits have been reused in newer * versions of the architecture; in that case we define constants diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static inline bool arm_ccnt_enabled(CPUARMState *env) return true; } - -void pmccntr_sync(CPUARMState *env) +/* + * Ensure c15_ccnt is the guest-visible count so that operations such as + * enabling/disabling the counter or filtering, modifying the count itself, + * etc. can be done logically. This is essentially a no-op if the counter is + * not enabled at the time of the call. + */ +void pmccntr_op_start(CPUARMState *env) { - uint64_t temp_ticks; - - temp_ticks = muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), + uint64_t cycles = 0; + cycles = muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), ARM_CPU_FREQ, NANOSECONDS_PER_SECOND); - if (env->cp15.c9_pmcr & PMCRD) { - /* Increment once every 64 processor clock cycles */ - temp_ticks /= 64; - } - if (arm_ccnt_enabled(env)) { - env->cp15.c15_ccnt = temp_ticks - env->cp15.c15_ccnt; + uint64_t eff_cycles = cycles; + if (env->cp15.c9_pmcr & PMCRD) { + /* Increment once every 64 processor clock cycles */ + eff_cycles /= 64; + } + + env->cp15.c15_ccnt = eff_cycles - env->cp15.c15_ccnt_delta; } + env->cp15.c15_ccnt_delta = cycles; +} + +/* + * If PMCCNTR is enabled, recalculate the delta between the clock and the + * guest-visible count. A call to pmccntr_op_finish should follow every call to + * pmccntr_op_start. + */ +void pmccntr_op_finish(CPUARMState *env) +{ + if (arm_ccnt_enabled(env)) { + uint64_t prev_cycles = env->cp15.c15_ccnt_delta; + + if (env->cp15.c9_pmcr & PMCRD) { + /* Increment once every 64 processor clock cycles */ + prev_cycles /= 64; + } + + env->cp15.c15_ccnt_delta = prev_cycles - env->cp15.c15_ccnt; + } +} + +void pmu_op_start(CPUARMState *env) +{ + pmccntr_op_start(env); +} + +void pmu_op_finish(CPUARMState *env) +{ + pmccntr_op_finish(env); } static void pmcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { - pmccntr_sync(env); + pmu_op_start(env); if (value & PMCRC) { /* The counter has been reset */ @@ -XXX,XX +XXX,XX @@ static void pmcr_write(CPUARMState *env, const ARMCPRegInfo *ri, env->cp15.c9_pmcr &= ~0x39; env->cp15.c9_pmcr |= (value & 0x39); - pmccntr_sync(env); + pmu_op_finish(env); } static uint64_t pmccntr_read(CPUARMState *env, const ARMCPRegInfo *ri) { - uint64_t total_ticks; - - if (!arm_ccnt_enabled(env)) { - /* Counter is disabled, do not change value */ - return env->cp15.c15_ccnt; - } - - total_ticks = muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), - ARM_CPU_FREQ, NANOSECONDS_PER_SECOND); - - if (env->cp15.c9_pmcr & PMCRD) { - /* Increment once every 64 processor clock cycles */ - total_ticks /= 64; - } - return total_ticks - env->cp15.c15_ccnt; + uint64_t ret; + pmccntr_op_start(env); + ret = env->cp15.c15_ccnt; + pmccntr_op_finish(env); + return ret; } static void pmselr_write(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void pmselr_write(CPUARMState *env, const ARMCPRegInfo *ri, static void pmccntr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { - uint64_t total_ticks; - - if (!arm_ccnt_enabled(env)) { - /* Counter is disabled, set the absolute value */ - env->cp15.c15_ccnt = value; - return; - } - - total_ticks = muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), - ARM_CPU_FREQ, NANOSECONDS_PER_SECOND); - - if (env->cp15.c9_pmcr & PMCRD) { - /* Increment once every 64 processor clock cycles */ - total_ticks /= 64; - } - env->cp15.c15_ccnt = total_ticks - value; + pmccntr_op_start(env); + env->cp15.c15_ccnt = value; + pmccntr_op_finish(env); } static void pmccntr_write32(CPUARMState *env, const ARMCPRegInfo *ri, @@ -XXX,XX +XXX,XX @@ static void pmccntr_write32(CPUARMState *env, const ARMCPRegInfo *ri, #else /* CONFIG_USER_ONLY */ -void pmccntr_sync(CPUARMState *env) +void pmccntr_op_start(CPUARMState *env) +{ +} + +void pmccntr_op_finish(CPUARMState *env) +{ +} + +void pmu_op_start(CPUARMState *env) +{ +} + +void pmu_op_finish(CPUARMState *env) { } @@ -XXX,XX +XXX,XX @@ void pmccntr_sync(CPUARMState *env) static void pmccfiltr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { - pmccntr_sync(env); + pmccntr_op_start(env); env->cp15.pmccfiltr_el0 = value & 0xfc000000; - pmccntr_sync(env); + pmccntr_op_finish(env); } static void pmcntenset_write(CPUARMState *env, const ARMCPRegInfo *ri, -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> Because of the PMU's design, many register accesses have side effects which are inter-related, meaning that the normal method of saving CP registers can result in inconsistent state. These side-effects are largely handled in pmu_op_start/finish functions which can be called before and after the state is saved/restored. By doing this and adding raw read/write functions for the affected registers, we avoid migration-related inconsistencies. Signed-off-by: Aaron Lindsay <aclindsa@gmail.com> Signed-off-by: Aaron Lindsay <aaron@os.amperecomputing.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20181211151945.29137-4-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 6 ++++-- target/arm/machine.c | 24 ++++++++++++++++++++++++ 2 files changed, 28 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v7_cp_reginfo[] = { .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 13, .opc2 = 0, .access = PL0_RW, .accessfn = pmreg_access_ccntr, .type = ARM_CP_IO, - .readfn = pmccntr_read, .writefn = pmccntr_write, }, + .fieldoffset = offsetof(CPUARMState, cp15.c15_ccnt), + .readfn = pmccntr_read, .writefn = pmccntr_write, + .raw_readfn = raw_read, .raw_writefn = raw_write, }, #endif { .name = "PMCCFILTR_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 15, .opc2 = 7, - .writefn = pmccfiltr_write, + .writefn = pmccfiltr_write, .raw_writefn = raw_write, .access = PL0_RW, .accessfn = pmreg_access, .type = ARM_CP_IO, .fieldoffset = offsetof(CPUARMState, cp15.pmccfiltr_el0), diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static int cpu_pre_save(void *opaque) { ARMCPU *cpu = opaque; + if (!kvm_enabled()) { + pmu_op_start(&cpu->env); + } + if (kvm_enabled()) { if (!write_kvmstate_to_list(cpu)) { /* This should never fail */ @@ -XXX,XX +XXX,XX @@ static int cpu_pre_save(void *opaque) return 0; } +static int cpu_post_save(void *opaque) +{ + ARMCPU *cpu = opaque; + + if (!kvm_enabled()) { + pmu_op_finish(&cpu->env); + } + + return 0; +} + static int cpu_pre_load(void *opaque) { ARMCPU *cpu = opaque; @@ -XXX,XX +XXX,XX @@ static int cpu_pre_load(void *opaque) */ env->irq_line_state = UINT32_MAX; + if (!kvm_enabled()) { + pmu_op_start(&cpu->env); + } + return 0; } @@ -XXX,XX +XXX,XX @@ static int cpu_post_load(void *opaque, int version_id) hw_breakpoint_update_all(cpu); hw_watchpoint_update_all(cpu); + if (!kvm_enabled()) { + pmu_op_finish(&cpu->env); + } + return 0; } @@ -XXX,XX +XXX,XX @@ const VMStateDescription vmstate_arm_cpu = { .version_id = 22, .minimum_version_id = 22, .pre_save = cpu_pre_save, + .post_save = cpu_post_save, .pre_load = cpu_pre_load, .post_load = cpu_post_load, .fields = (VMStateField[]) { -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> Rename arm_ccnt_enabled to pmu_counter_enabled, and add logic to only return 'true' if the specified counter is enabled and neither prohibited or filtered. Signed-off-by: Aaron Lindsay <alindsay@codeaurora.org> Signed-off-by: Aaron Lindsay <aclindsa@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181211151945.29137-5-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 10 ++++- target/arm/cpu.c | 3 ++ target/arm/helper.c | 96 +++++++++++++++++++++++++++++++++++++++++---- 3 files changed, 101 insertions(+), 8 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ void pmccntr_op_finish(CPUARMState *env); void pmu_op_start(CPUARMState *env); void pmu_op_finish(CPUARMState *env); +/** + * Functions to register as EL change hooks for PMU mode filtering + */ +void pmu_pre_el_change(ARMCPU *cpu, void *ignored); +void pmu_post_el_change(ARMCPU *cpu, void *ignored); + /* SCTLR bit meanings. Several bits have been reused in newer * versions of the architecture; in that case we define constants * for both old and new bit meanings. Code which tests against those @@ -XXX,XX +XXX,XX @@ void pmu_op_finish(CPUARMState *env); #define MDCR_EPMAD (1U << 21) #define MDCR_EDAD (1U << 20) -#define MDCR_SPME (1U << 17) +#define MDCR_SPME (1U << 17) /* MDCR_EL3 */ +#define MDCR_HPMD (1U << 17) /* MDCR_EL2 */ #define MDCR_SDD (1U << 16) #define MDCR_SPD (3U << 14) #define MDCR_TDRA (1U << 11) @@ -XXX,XX +XXX,XX @@ void pmu_op_finish(CPUARMState *env); #define MDCR_HPME (1U << 7) #define MDCR_TPM (1U << 6) #define MDCR_TPMCR (1U << 5) +#define MDCR_HPMN (0x1fU) /* Not all of the MDCR_EL3 bits are present in the 32-bit SDCR */ #define SDCR_VALID_MASK (MDCR_EPMAD | MDCR_EDAD | MDCR_SPME | MDCR_SPD) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) if (!cpu->has_pmu) { unset_feature(env, ARM_FEATURE_PMU); cpu->id_aa64dfr0 &= ~0xf00; + } else if (!kvm_enabled()) { + arm_register_pre_el_change_hook(cpu, &pmu_pre_el_change, 0); + arm_register_el_change_hook(cpu, &pmu_post_el_change, 0); } if (!arm_feature(env, ARM_FEATURE_EL2)) { diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v6_cp_reginfo[] = { /* Definitions for the PMU registers */ #define PMCRN_MASK 0xf800 #define PMCRN_SHIFT 11 +#define PMCRDP 0x10 #define PMCRD 0x8 #define PMCRC 0x4 #define PMCRE 0x1 +#define PMXEVTYPER_P 0x80000000 +#define PMXEVTYPER_U 0x40000000 +#define PMXEVTYPER_NSK 0x20000000 +#define PMXEVTYPER_NSU 0x10000000 +#define PMXEVTYPER_NSH 0x08000000 +#define PMXEVTYPER_M 0x04000000 +#define PMXEVTYPER_MT 0x02000000 +#define PMXEVTYPER_EVTCOUNT 0x0000ffff +#define PMXEVTYPER_MASK (PMXEVTYPER_P | PMXEVTYPER_U | PMXEVTYPER_NSK | \ + PMXEVTYPER_NSU | PMXEVTYPER_NSH | \ + PMXEVTYPER_M | PMXEVTYPER_MT | \ + PMXEVTYPER_EVTCOUNT) + static inline uint32_t pmu_num_counters(CPUARMState *env) { return (env->cp15.c9_pmcr & PMCRN_MASK) >> PMCRN_SHIFT; @@ -XXX,XX +XXX,XX @@ static CPAccessResult pmreg_access_ccntr(CPUARMState *env, return pmreg_access(env, ri, isread); } -static inline bool arm_ccnt_enabled(CPUARMState *env) +/* Returns true if the counter (pass 31 for PMCCNTR) should count events using + * the current EL, security state, and register configuration. + */ +static bool pmu_counter_enabled(CPUARMState *env, uint8_t counter) { - /* This does not support checking PMCCFILTR_EL0 register */ + uint64_t filter; + bool e, p, u, nsk, nsu, nsh, m; + bool enabled, prohibited, filtered; + bool secure = arm_is_secure(env); + int el = arm_current_el(env); + uint8_t hpmn = env->cp15.mdcr_el2 & MDCR_HPMN; - if (!(env->cp15.c9_pmcr & PMCRE) || !(env->cp15.c9_pmcnten & (1 << 31))) { - return false; + if (!arm_feature(env, ARM_FEATURE_EL2) || + (counter < hpmn || counter == 31)) { + e = env->cp15.c9_pmcr & PMCRE; + } else { + e = env->cp15.mdcr_el2 & MDCR_HPME; + } + enabled = e && (env->cp15.c9_pmcnten & (1 << counter)); + + if (!secure) { + if (el == 2 && (counter < hpmn || counter == 31)) { + prohibited = env->cp15.mdcr_el2 & MDCR_HPMD; + } else { + prohibited = false; + } + } else { + prohibited = arm_feature(env, ARM_FEATURE_EL3) && + (env->cp15.mdcr_el3 & MDCR_SPME); } - return true; + if (prohibited && counter == 31) { + prohibited = env->cp15.c9_pmcr & PMCRDP; + } + + /* TODO Remove assert, set filter to correct PMEVTYPER */ + assert(counter == 31); + filter = env->cp15.pmccfiltr_el0; + + p = filter & PMXEVTYPER_P; + u = filter & PMXEVTYPER_U; + nsk = arm_feature(env, ARM_FEATURE_EL3) && (filter & PMXEVTYPER_NSK); + nsu = arm_feature(env, ARM_FEATURE_EL3) && (filter & PMXEVTYPER_NSU); + nsh = arm_feature(env, ARM_FEATURE_EL2) && (filter & PMXEVTYPER_NSH); + m = arm_el_is_aa64(env, 1) && + arm_feature(env, ARM_FEATURE_EL3) && (filter & PMXEVTYPER_M); + + if (el == 0) { + filtered = secure ? u : u != nsu; + } else if (el == 1) { + filtered = secure ? p : p != nsk; + } else if (el == 2) { + filtered = !nsh; + } else { /* EL3 */ + filtered = m != p; + } + + return enabled && !prohibited && !filtered; } + /* * Ensure c15_ccnt is the guest-visible count so that operations such as * enabling/disabling the counter or filtering, modifying the count itself, @@ -XXX,XX +XXX,XX @@ void pmccntr_op_start(CPUARMState *env) cycles = muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), ARM_CPU_FREQ, NANOSECONDS_PER_SECOND); - if (arm_ccnt_enabled(env)) { + if (pmu_counter_enabled(env, 31)) { uint64_t eff_cycles = cycles; if (env->cp15.c9_pmcr & PMCRD) { /* Increment once every 64 processor clock cycles */ @@ -XXX,XX +XXX,XX @@ void pmccntr_op_start(CPUARMState *env) */ void pmccntr_op_finish(CPUARMState *env) { - if (arm_ccnt_enabled(env)) { + if (pmu_counter_enabled(env, 31)) { uint64_t prev_cycles = env->cp15.c15_ccnt_delta; if (env->cp15.c9_pmcr & PMCRD) { @@ -XXX,XX +XXX,XX @@ void pmu_op_finish(CPUARMState *env) pmccntr_op_finish(env); } +void pmu_pre_el_change(ARMCPU *cpu, void *ignored) +{ + pmu_op_start(&cpu->env); +} + +void pmu_post_el_change(ARMCPU *cpu, void *ignored) +{ + pmu_op_finish(&cpu->env); +} + static void pmcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ void pmu_op_finish(CPUARMState *env) { } +void pmu_pre_el_change(ARMCPU *cpu, void *ignored) +{ +} + +void pmu_post_el_change(ARMCPU *cpu, void *ignored) +{ +} + #endif static void pmccfiltr_write(CPUARMState *env, const ARMCPRegInfo *ri, -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> Signed-off-by: Aaron Lindsay <alindsay@codeaurora.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181211151945.29137-6-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 27 ++++++++++++++++++++++++++- 1 file changed, 26 insertions(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v6_cp_reginfo[] = { PMXEVTYPER_M | PMXEVTYPER_MT | \ PMXEVTYPER_EVTCOUNT) +#define PMCCFILTR 0xf8000000 +#define PMCCFILTR_M PMXEVTYPER_M +#define PMCCFILTR_EL0 (PMCCFILTR | PMCCFILTR_M) + static inline uint32_t pmu_num_counters(CPUARMState *env) { return (env->cp15.c9_pmcr & PMCRN_MASK) >> PMCRN_SHIFT; @@ -XXX,XX +XXX,XX @@ static void pmccfiltr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { pmccntr_op_start(env); - env->cp15.pmccfiltr_el0 = value & 0xfc000000; + env->cp15.pmccfiltr_el0 = value & PMCCFILTR_EL0; pmccntr_op_finish(env); } +static void pmccfiltr_write_a32(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + pmccntr_op_start(env); + /* M is not accessible from AArch32 */ + env->cp15.pmccfiltr_el0 = (env->cp15.pmccfiltr_el0 & PMCCFILTR_M) | + (value & PMCCFILTR); + pmccntr_op_finish(env); +} + +static uint64_t pmccfiltr_read_a32(CPUARMState *env, const ARMCPRegInfo *ri) +{ + /* M is not visible in AArch32 */ + return env->cp15.pmccfiltr_el0 & PMCCFILTR; +} + static void pmcntenset_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v7_cp_reginfo[] = { .readfn = pmccntr_read, .writefn = pmccntr_write, .raw_readfn = raw_read, .raw_writefn = raw_write, }, #endif + { .name = "PMCCFILTR", .cp = 15, .opc1 = 0, .crn = 14, .crm = 15, .opc2 = 7, + .writefn = pmccfiltr_write_a32, .readfn = pmccfiltr_read_a32, + .access = PL0_RW, .accessfn = pmreg_access, + .type = ARM_CP_ALIAS | ARM_CP_IO, + .resetvalue = 0, }, { .name = "PMCCFILTR_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 14, .crm = 15, .opc2 = 7, .writefn = pmccfiltr_write, .raw_writefn = raw_write, -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> Add an array for PMOVSSET so we only define it for v7ve+ platforms Signed-off-by: Aaron Lindsay <alindsay@codeaurora.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181211151945.29137-7-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 28 ++++++++++++++++++++++++++++ 1 file changed, 28 insertions(+) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void pmovsr_write(CPUARMState *env, const ARMCPRegInfo *ri, env->cp15.c9_pmovsr &= ~value; } +static void pmovsset_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + value &= pmu_counter_mask(env); + env->cp15.c9_pmovsr |= value; +} + static void pmxevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v7mp_cp_reginfo[] = { REGINFO_SENTINEL }; +static const ARMCPRegInfo pmovsset_cp_reginfo[] = { + /* PMOVSSET is not implemented in v7 before v7ve */ + { .name = "PMOVSSET", .cp = 15, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 3, + .access = PL0_RW, .accessfn = pmreg_access, + .type = ARM_CP_ALIAS, + .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmovsr), + .writefn = pmovsset_write, + .raw_writefn = raw_write }, + { .name = "PMOVSSET_EL0", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 14, .opc2 = 3, + .access = PL0_RW, .accessfn = pmreg_access, + .type = ARM_CP_ALIAS, + .fieldoffset = offsetof(CPUARMState, cp15.c9_pmovsr), + .writefn = pmovsset_write, + .raw_writefn = raw_write }, + REGINFO_SENTINEL +}; + static void teecr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) !arm_feature(env, ARM_FEATURE_PMSA)) { define_arm_cp_regs(cpu, v7mp_cp_reginfo); } + if (arm_feature(env, ARM_FEATURE_V7VE)) { + define_arm_cp_regs(cpu, pmovsset_cp_reginfo); + } if (arm_feature(env, ARM_FEATURE_V7)) { /* v7 performance monitor control register: same implementor * field as main ID register, and we implement only the cycle -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> This is immediately necessary for the PMUv3 implementation to check ID_DFR0.PerfMon to enable/disable specific features, but defines the full complement of fields for possible future use elsewhere. Signed-off-by: Aaron Lindsay <aaron@os.amperecomputing.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20181211151945.29137-8-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64MMFR1, PAN, 20, 4) FIELD(ID_AA64MMFR1, SPECSEI, 24, 4) FIELD(ID_AA64MMFR1, XNX, 28, 4) +FIELD(ID_DFR0, COPDBG, 0, 4) +FIELD(ID_DFR0, COPSDBG, 4, 4) +FIELD(ID_DFR0, MMAPDBG, 8, 4) +FIELD(ID_DFR0, COPTRC, 12, 4) +FIELD(ID_DFR0, MMAPTRC, 16, 4) +FIELD(ID_DFR0, MPROFDBG, 20, 4) +FIELD(ID_DFR0, PERFMON, 24, 4) +FIELD(ID_DFR0, TRACEFILT, 28, 4) + QEMU_BUILD_BUG_ON(ARRAY_SIZE(((ARMCPU *)0)->ccsidr) <= R_V7M_CSSELR_INDEX_MASK); /* If adding a feature bit which corresponds to a Linux ELF -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> Signed-off-by: Aaron Lindsay <aaron@os.amperecomputing.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20181211151945.29137-9-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 4 ++-- target/arm/helper.c | 19 +++++++++++++++++-- 2 files changed, 19 insertions(+), 4 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ struct ARMCPU { uint32_t id_pfr0; uint32_t id_pfr1; uint32_t id_dfr0; - uint32_t pmceid0; - uint32_t pmceid1; + uint64_t pmceid0; + uint64_t pmceid1; uint32_t id_afr0; uint32_t id_mmfr0; uint32_t id_mmfr1; diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) } else { define_arm_cp_regs(cpu, not_v7_cp_reginfo); } + if (FIELD_EX32(cpu->id_dfr0, ID_DFR0, PERFMON) >= 4 && + FIELD_EX32(cpu->id_dfr0, ID_DFR0, PERFMON) != 0xf) { + ARMCPRegInfo v81_pmu_regs[] = { + { .name = "PMCEID2", .state = ARM_CP_STATE_AA32, + .cp = 15, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 4, + .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, + .resetvalue = extract64(cpu->pmceid0, 32, 32) }, + { .name = "PMCEID3", .state = ARM_CP_STATE_AA32, + .cp = 15, .opc1 = 0, .crn = 9, .crm = 14, .opc2 = 5, + .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, + .resetvalue = extract64(cpu->pmceid1, 32, 32) }, + REGINFO_SENTINEL + }; + define_arm_cp_regs(cpu, v81_pmu_regs); + } if (arm_feature(env, ARM_FEATURE_V8)) { /* AArch64 ID registers, which all have impdef reset values. * Note that within the ID register ranges the unused slots @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "PMCEID0", .state = ARM_CP_STATE_AA32, .cp = 15, .opc1 = 0, .crn = 9, .crm = 12, .opc2 = 6, .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, - .resetvalue = cpu->pmceid0 }, + .resetvalue = extract64(cpu->pmceid0, 0, 32) }, { .name = "PMCEID0_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 6, .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "PMCEID1", .state = ARM_CP_STATE_AA32, .cp = 15, .opc1 = 0, .crn = 9, .crm = 12, .opc2 = 7, .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, - .resetvalue = cpu->pmceid1 }, + .resetvalue = extract64(cpu->pmceid1, 0, 32) }, { .name = "PMCEID1_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 7, .access = PL0_R, .accessfn = pmreg_access, .type = ARM_CP_CONST, -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> This commit doesn't add any supported events, but provides the framework for adding them. We store the pm_event structs in a simple array, and provide the mapping from the event numbers to array indexes in the supported_event_map array. Because the value of PMCEID[01] depends upon which events are supported at runtime, generate it dynamically. Signed-off-by: Aaron Lindsay <alindsay@codeaurora.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20181211151945.29137-10-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 10 ++++++++ target/arm/cpu.c | 19 +++++++++------ target/arm/cpu64.c | 4 ---- target/arm/helper.c | 57 +++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 79 insertions(+), 11 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ void pmu_op_finish(CPUARMState *env); void pmu_pre_el_change(ARMCPU *cpu, void *ignored); void pmu_post_el_change(ARMCPU *cpu, void *ignored); +/* + * get_pmceid + * @env: CPUARMState + * @which: which PMCEID register to return (0 or 1) + * + * Return the PMCEID[01]_EL0 register values corresponding to the counters + * which are supported given the current configuration + */ +uint64_t get_pmceid(CPUARMState *env, unsigned which); + /* SCTLR bit meanings. Several bits have been reused in newer * versions of the architecture; in that case we define constants * for both old and new bit meanings. Code which tests against those diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) if (!cpu->has_pmu) { unset_feature(env, ARM_FEATURE_PMU); + } + if (arm_feature(env, ARM_FEATURE_PMU)) { + cpu->pmceid0 = get_pmceid(&cpu->env, 0); + cpu->pmceid1 = get_pmceid(&cpu->env, 1); + + if (!kvm_enabled()) { + arm_register_pre_el_change_hook(cpu, &pmu_pre_el_change, 0); + arm_register_el_change_hook(cpu, &pmu_post_el_change, 0); + } + } else { cpu->id_aa64dfr0 &= ~0xf00; - } else if (!kvm_enabled()) { - arm_register_pre_el_change_hook(cpu, &pmu_pre_el_change, 0); - arm_register_el_change_hook(cpu, &pmu_post_el_change, 0); + cpu->pmceid0 = 0; + cpu->pmceid1 = 0; } if (!arm_feature(env, ARM_FEATURE_EL2)) { @@ -XXX,XX +XXX,XX @@ static void cortex_a7_initfn(Object *obj) cpu->id_pfr0 = 0x00001131; cpu->id_pfr1 = 0x00011011; cpu->id_dfr0 = 0x02010555; - cpu->pmceid0 = 0x00000000; - cpu->pmceid1 = 0x00000000; cpu->id_afr0 = 0x00000000; cpu->id_mmfr0 = 0x10101105; cpu->id_mmfr1 = 0x40000000; @@ -XXX,XX +XXX,XX @@ static void cortex_a15_initfn(Object *obj) cpu->id_pfr0 = 0x00001131; cpu->id_pfr1 = 0x00011011; cpu->id_dfr0 = 0x02010555; - cpu->pmceid0 = 0x0000000; - cpu->pmceid1 = 0x00000000; cpu->id_afr0 = 0x00000000; cpu->id_mmfr0 = 0x10201105; cpu->id_mmfr1 = 0x20000000; diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_a57_initfn(Object *obj) cpu->isar.id_isar6 = 0; cpu->isar.id_aa64pfr0 = 0x00002222; cpu->id_aa64dfr0 = 0x10305106; - cpu->pmceid0 = 0x00000000; - cpu->pmceid1 = 0x00000000; cpu->isar.id_aa64isar0 = 0x00011120; cpu->isar.id_aa64mmfr0 = 0x00001124; cpu->dbgdidr = 0x3516d000; @@ -XXX,XX +XXX,XX @@ static void aarch64_a72_initfn(Object *obj) cpu->isar.id_isar5 = 0x00011121; cpu->isar.id_aa64pfr0 = 0x00002222; cpu->id_aa64dfr0 = 0x10305106; - cpu->pmceid0 = 0x00000000; - cpu->pmceid1 = 0x00000000; cpu->isar.id_aa64isar0 = 0x00011120; cpu->isar.id_aa64mmfr0 = 0x00001124; cpu->dbgdidr = 0x3516d000; diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static inline uint64_t pmu_counter_mask(CPUARMState *env) return (1 << 31) | ((1 << pmu_num_counters(env)) - 1); } +typedef struct pm_event { + uint16_t number; /* PMEVTYPER.evtCount is 16 bits wide */ + /* If the event is supported on this CPU (used to generate PMCEID[01]) */ + bool (*supported)(CPUARMState *); + /* + * Retrieve the current count of the underlying event. The programmed + * counters hold a difference from the return value from this function + */ + uint64_t (*get_count)(CPUARMState *); +} pm_event; + +static const pm_event pm_events[] = { +}; + +/* + * Note: Before increasing MAX_EVENT_ID beyond 0x3f into the 0x40xx range of + * events (i.e. the statistical profiling extension), this implementation + * should first be updated to something sparse instead of the current + * supported_event_map[] array. + */ +#define MAX_EVENT_ID 0x0 +#define UNSUPPORTED_EVENT UINT16_MAX +static uint16_t supported_event_map[MAX_EVENT_ID + 1]; + +/* + * Called upon initialization to build PMCEID0_EL0 or PMCEID1_EL0 (indicated by + * 'which'). We also use it to build a map of ARM event numbers to indices in + * our pm_events array. + * + * Note: Events in the 0x40XX range are not currently supported. + */ +uint64_t get_pmceid(CPUARMState *env, unsigned which) +{ + uint64_t pmceid = 0; + unsigned int i; + + assert(which <= 1); + + for (i = 0; i < ARRAY_SIZE(supported_event_map); i++) { + supported_event_map[i] = UNSUPPORTED_EVENT; + } + + for (i = 0; i < ARRAY_SIZE(pm_events); i++) { + const pm_event *cnt = &pm_events[i]; + assert(cnt->number <= MAX_EVENT_ID); + /* We do not currently support events in the 0x40xx range */ + assert(cnt->number <= 0x3f); + + if ((cnt->number & 0x20) == (which << 6) && + cnt->supported(env)) { + pmceid |= (1 << (cnt->number & 0x1f)); + supported_event_map[cnt->number] = i; + } + } + return pmceid; +} + static CPAccessResult pmreg_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> Add arrays to hold the registers, the definitions themselves, access functions, and logic to reset counters when PMCR.P is set. Update filtering code to support counters other than PMCCNTR. Support migration with raw read/write functions. Signed-off-by: Aaron Lindsay <alindsay@codeaurora.org> Signed-off-by: Aaron Lindsay <aaron@os.amperecomputing.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181211151945.29137-11-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 3 + target/arm/helper.c | 296 +++++++++++++++++++++++++++++++++++++++++--- 2 files changed, 282 insertions(+), 17 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUARMState { * pmccntr_op_finish. */ uint64_t c15_ccnt_delta; + uint64_t c14_pmevcntr[31]; + uint64_t c14_pmevcntr_delta[31]; + uint64_t c14_pmevtyper[31]; uint64_t pmccfiltr_el0; /* Performance Monitor Filter Register */ uint64_t vpidr_el2; /* Virtualization Processor ID Register */ uint64_t vmpidr_el2; /* Virtualization Multiprocessor ID Register */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v6_cp_reginfo[] = { #define PMCRDP 0x10 #define PMCRD 0x8 #define PMCRC 0x4 +#define PMCRP 0x2 #define PMCRE 0x1 #define PMXEVTYPER_P 0x80000000 @@ -XXX,XX +XXX,XX @@ uint64_t get_pmceid(CPUARMState *env, unsigned which) return pmceid; } +/* + * Check at runtime whether a PMU event is supported for the current machine + */ +static bool event_supported(uint16_t number) +{ + if (number > MAX_EVENT_ID) { + return false; + } + return supported_event_map[number] != UNSUPPORTED_EVENT; +} + static CPAccessResult pmreg_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { @@ -XXX,XX +XXX,XX @@ static bool pmu_counter_enabled(CPUARMState *env, uint8_t counter) prohibited = env->cp15.c9_pmcr & PMCRDP; } - /* TODO Remove assert, set filter to correct PMEVTYPER */ - assert(counter == 31); - filter = env->cp15.pmccfiltr_el0; + if (counter == 31) { + filter = env->cp15.pmccfiltr_el0; + } else { + filter = env->cp15.c14_pmevtyper[counter]; + } p = filter & PMXEVTYPER_P; u = filter & PMXEVTYPER_U; @@ -XXX,XX +XXX,XX @@ static bool pmu_counter_enabled(CPUARMState *env, uint8_t counter) filtered = m != p; } + if (counter != 31) { + /* + * If not checking PMCCNTR, ensure the counter is setup to an event we + * support + */ + uint16_t event = filter & PMXEVTYPER_EVTCOUNT; + if (!event_supported(event)) { + return false; + } + } + return enabled && !prohibited && !filtered; } @@ -XXX,XX +XXX,XX @@ void pmccntr_op_finish(CPUARMState *env) } } +static void pmevcntr_op_start(CPUARMState *env, uint8_t counter) +{ + + uint16_t event = env->cp15.c14_pmevtyper[counter] & PMXEVTYPER_EVTCOUNT; + uint64_t count = 0; + if (event_supported(event)) { + uint16_t event_idx = supported_event_map[event]; + count = pm_events[event_idx].get_count(env); + } + + if (pmu_counter_enabled(env, counter)) { + env->cp15.c14_pmevcntr[counter] = + count - env->cp15.c14_pmevcntr_delta[counter]; + } + env->cp15.c14_pmevcntr_delta[counter] = count; +} + +static void pmevcntr_op_finish(CPUARMState *env, uint8_t counter) +{ + if (pmu_counter_enabled(env, counter)) { + env->cp15.c14_pmevcntr_delta[counter] -= + env->cp15.c14_pmevcntr[counter]; + } +} + void pmu_op_start(CPUARMState *env) { + unsigned int i; pmccntr_op_start(env); + for (i = 0; i < pmu_num_counters(env); i++) { + pmevcntr_op_start(env, i); + } } void pmu_op_finish(CPUARMState *env) { + unsigned int i; pmccntr_op_finish(env); + for (i = 0; i < pmu_num_counters(env); i++) { + pmevcntr_op_finish(env, i); + } } void pmu_pre_el_change(ARMCPU *cpu, void *ignored) @@ -XXX,XX +XXX,XX @@ static void pmcr_write(CPUARMState *env, const ARMCPRegInfo *ri, env->cp15.c15_ccnt = 0; } + if (value & PMCRP) { + unsigned int i; + for (i = 0; i < pmu_num_counters(env); i++) { + env->cp15.c14_pmevcntr[i] = 0; + } + } + /* only the DP, X, D and E bits are writable */ env->cp15.c9_pmcr &= ~0x39; env->cp15.c9_pmcr |= (value & 0x39); @@ -XXX,XX +XXX,XX @@ void pmccntr_op_finish(CPUARMState *env) { } +void pmevcntr_op_start(CPUARMState *env, uint8_t i) +{ +} + +void pmevcntr_op_finish(CPUARMState *env, uint8_t i) +{ +} + void pmu_op_start(CPUARMState *env) { } @@ -XXX,XX +XXX,XX @@ static void pmovsset_write(CPUARMState *env, const ARMCPRegInfo *ri, env->cp15.c9_pmovsr |= value; } -static void pmxevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +static void pmevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value, const uint8_t counter) { + if (counter == 31) { + pmccfiltr_write(env, ri, value); + } else if (counter < pmu_num_counters(env)) { + pmevcntr_op_start(env, counter); + + /* + * If this counter's event type is changing, store the current + * underlying count for the new type in c14_pmevcntr_delta[counter] so + * pmevcntr_op_finish has the correct baseline when it converts back to + * a delta. + */ + uint16_t old_event = env->cp15.c14_pmevtyper[counter] & + PMXEVTYPER_EVTCOUNT; + uint16_t new_event = value & PMXEVTYPER_EVTCOUNT; + if (old_event != new_event) { + uint64_t count = 0; + if (event_supported(new_event)) { + uint16_t event_idx = supported_event_map[new_event]; + count = pm_events[event_idx].get_count(env); + } + env->cp15.c14_pmevcntr_delta[counter] = count; + } + + env->cp15.c14_pmevtyper[counter] = value & PMXEVTYPER_MASK; + pmevcntr_op_finish(env, counter); + } /* Attempts to access PMXEVTYPER are CONSTRAINED UNPREDICTABLE when * PMSELR value is equal to or greater than the number of implemented * counters, but not equal to 0x1f. We opt to behave as a RAZ/WI. */ - if (env->cp15.c9_pmselr == 0x1f) { - pmccfiltr_write(env, ri, value); +} + +static uint64_t pmevtyper_read(CPUARMState *env, const ARMCPRegInfo *ri, + const uint8_t counter) +{ + if (counter == 31) { + return env->cp15.pmccfiltr_el0; + } else if (counter < pmu_num_counters(env)) { + return env->cp15.c14_pmevtyper[counter]; + } else { + /* + * We opt to behave as a RAZ/WI when attempts to access PMXEVTYPER + * are CONSTRAINED UNPREDICTABLE. See comments in pmevtyper_write(). + */ + return 0; } } +static void pmevtyper_writefn(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7); + pmevtyper_write(env, ri, value, counter); +} + +static void pmevtyper_rawwrite(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7); + env->cp15.c14_pmevtyper[counter] = value; + + /* + * pmevtyper_rawwrite is called between a pair of pmu_op_start and + * pmu_op_finish calls when loading saved state for a migration. Because + * we're potentially updating the type of event here, the value written to + * c14_pmevcntr_delta by the preceeding pmu_op_start call may be for a + * different counter type. Therefore, we need to set this value to the + * current count for the counter type we're writing so that pmu_op_finish + * has the correct count for its calculation. + */ + uint16_t event = value & PMXEVTYPER_EVTCOUNT; + if (event_supported(event)) { + uint16_t event_idx = supported_event_map[event]; + env->cp15.c14_pmevcntr_delta[counter] = + pm_events[event_idx].get_count(env); + } +} + +static uint64_t pmevtyper_readfn(CPUARMState *env, const ARMCPRegInfo *ri) +{ + uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7); + return pmevtyper_read(env, ri, counter); +} + +static void pmxevtyper_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + pmevtyper_write(env, ri, value, env->cp15.c9_pmselr & 31); +} + static uint64_t pmxevtyper_read(CPUARMState *env, const ARMCPRegInfo *ri) { - /* We opt to behave as a RAZ/WI when attempts to access PMXEVTYPER - * are CONSTRAINED UNPREDICTABLE. See comments in pmxevtyper_write(). + return pmevtyper_read(env, ri, env->cp15.c9_pmselr & 31); +} + +static void pmevcntr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value, uint8_t counter) +{ + if (counter < pmu_num_counters(env)) { + pmevcntr_op_start(env, counter); + env->cp15.c14_pmevcntr[counter] = value; + pmevcntr_op_finish(env, counter); + } + /* + * We opt to behave as a RAZ/WI when attempts to access PM[X]EVCNTR + * are CONSTRAINED UNPREDICTABLE. */ - if (env->cp15.c9_pmselr == 0x1f) { - return env->cp15.pmccfiltr_el0; +} + +static uint64_t pmevcntr_read(CPUARMState *env, const ARMCPRegInfo *ri, + uint8_t counter) +{ + if (counter < pmu_num_counters(env)) { + uint64_t ret; + pmevcntr_op_start(env, counter); + ret = env->cp15.c14_pmevcntr[counter]; + pmevcntr_op_finish(env, counter); + return ret; } else { + /* We opt to behave as a RAZ/WI when attempts to access PM[X]EVCNTR + * are CONSTRAINED UNPREDICTABLE. */ return 0; } } +static void pmevcntr_writefn(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7); + pmevcntr_write(env, ri, value, counter); +} + +static uint64_t pmevcntr_readfn(CPUARMState *env, const ARMCPRegInfo *ri) +{ + uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7); + return pmevcntr_read(env, ri, counter); +} + +static void pmevcntr_rawwrite(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7); + assert(counter < pmu_num_counters(env)); + env->cp15.c14_pmevcntr[counter] = value; + pmevcntr_write(env, ri, value, counter); +} + +static uint64_t pmevcntr_rawread(CPUARMState *env, const ARMCPRegInfo *ri) +{ + uint8_t counter = ((ri->crm & 3) << 3) | (ri->opc2 & 7); + assert(counter < pmu_num_counters(env)); + return env->cp15.c14_pmevcntr[counter]; +} + +static void pmxevcntr_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + pmevcntr_write(env, ri, value, env->cp15.c9_pmselr & 31); +} + +static uint64_t pmxevcntr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + return pmevcntr_read(env, ri, env->cp15.c9_pmselr & 31); +} + static void pmuserenr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v7_cp_reginfo[] = { .fieldoffset = offsetof(CPUARMState, cp15.pmccfiltr_el0), .resetvalue = 0, }, { .name = "PMXEVTYPER", .cp = 15, .crn = 9, .crm = 13, .opc1 = 0, .opc2 = 1, - .access = PL0_RW, .type = ARM_CP_NO_RAW, .accessfn = pmreg_access, + .access = PL0_RW, .type = ARM_CP_NO_RAW | ARM_CP_IO, + .accessfn = pmreg_access, .writefn = pmxevtyper_write, .readfn = pmxevtyper_read }, { .name = "PMXEVTYPER_EL0", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 13, .opc2 = 1, - .access = PL0_RW, .type = ARM_CP_NO_RAW, .accessfn = pmreg_access, + .access = PL0_RW, .type = ARM_CP_NO_RAW | ARM_CP_IO, + .accessfn = pmreg_access, .writefn = pmxevtyper_write, .readfn = pmxevtyper_read }, - /* Unimplemented, RAZ/WI. */ { .name = "PMXEVCNTR", .cp = 15, .crn = 9, .crm = 13, .opc1 = 0, .opc2 = 2, - .access = PL0_RW, .type = ARM_CP_CONST, .resetvalue = 0, - .accessfn = pmreg_access_xevcntr }, + .access = PL0_RW, .type = ARM_CP_NO_RAW | ARM_CP_IO, + .accessfn = pmreg_access_xevcntr, + .writefn = pmxevcntr_write, .readfn = pmxevcntr_read }, + { .name = "PMXEVCNTR_EL0", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 13, .opc2 = 2, + .access = PL0_RW, .type = ARM_CP_NO_RAW | ARM_CP_IO, + .accessfn = pmreg_access_xevcntr, + .writefn = pmxevcntr_write, .readfn = pmxevcntr_read }, { .name = "PMUSERENR", .cp = 15, .crn = 9, .crm = 14, .opc1 = 0, .opc2 = 0, .access = PL0_R | PL1_RW, .accessfn = access_tpm, .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmuserenr), @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo el2_cp_reginfo[] = { #endif /* The only field of MDCR_EL2 that has a defined architectural reset value * is MDCR_EL2.HPMN which should reset to the value of PMCR_EL0.N; but we - * don't impelment any PMU event counters, so using zero as a reset + * don't implement any PMU event counters, so using zero as a reset * value for MDCR_EL2 is okay */ { .name = "MDCR_EL2", .state = ARM_CP_STATE_BOTH, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) * field as main ID register, and we implement only the cycle * count register. */ + unsigned int i, pmcrn = 0; #ifndef CONFIG_USER_ONLY ARMCPRegInfo pmcr = { .name = "PMCR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 0, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) }; define_one_arm_cp_reg(cpu, &pmcr); define_one_arm_cp_reg(cpu, &pmcr64); + for (i = 0; i < pmcrn; i++) { + char *pmevcntr_name = g_strdup_printf("PMEVCNTR%d", i); + char *pmevcntr_el0_name = g_strdup_printf("PMEVCNTR%d_EL0", i); + char *pmevtyper_name = g_strdup_printf("PMEVTYPER%d", i); + char *pmevtyper_el0_name = g_strdup_printf("PMEVTYPER%d_EL0", i); + ARMCPRegInfo pmev_regs[] = { + { .name = pmevcntr_name, .cp = 15, .crn = 15, + .crm = 8 | (3 & (i >> 3)), .opc1 = 0, .opc2 = i & 7, + .access = PL0_RW, .type = ARM_CP_IO | ARM_CP_ALIAS, + .readfn = pmevcntr_readfn, .writefn = pmevcntr_writefn, + .accessfn = pmreg_access }, + { .name = pmevcntr_el0_name, .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 15, .crm = 8 | (3 & (i >> 3)), + .opc2 = i & 7, .access = PL0_RW, .accessfn = pmreg_access, + .type = ARM_CP_IO, + .readfn = pmevcntr_readfn, .writefn = pmevcntr_writefn, + .raw_readfn = pmevcntr_rawread, + .raw_writefn = pmevcntr_rawwrite }, + { .name = pmevtyper_name, .cp = 15, .crn = 15, + .crm = 12 | (3 & (i >> 3)), .opc1 = 0, .opc2 = i & 7, + .access = PL0_RW, .type = ARM_CP_IO | ARM_CP_ALIAS, + .readfn = pmevtyper_readfn, .writefn = pmevtyper_writefn, + .accessfn = pmreg_access }, + { .name = pmevtyper_el0_name, .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 15, .crm = 12 | (3 & (i >> 3)), + .opc2 = i & 7, .access = PL0_RW, .accessfn = pmreg_access, + .type = ARM_CP_IO, + .readfn = pmevtyper_readfn, .writefn = pmevtyper_writefn, + .raw_writefn = pmevtyper_rawwrite }, + REGINFO_SENTINEL + }; + define_arm_cp_regs(cpu, pmev_regs); + g_free(pmevcntr_name); + g_free(pmevcntr_el0_name); + g_free(pmevtyper_name); + g_free(pmevtyper_el0_name); + } #endif ARMCPRegInfo clidr = { .name = "CLIDR", .state = ARM_CP_STATE_BOTH, -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> The instruction event is only enabled when icount is used, cycles are always supported. Always defining get_cycle_count (but altering its behavior depending on CONFIG_USER_ONLY) allows us to remove some CONFIG_USER_ONLY #defines throughout the rest of the code. Signed-off-by: Aaron Lindsay <alindsay@codeaurora.org> Signed-off-by: Aaron Lindsay <aaron@os.amperecomputing.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20181211151945.29137-12-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 90 ++++++++++++++++++++++----------------------- 1 file changed, 44 insertions(+), 46 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ #include "arm_ldst.h" #include <zlib.h> /* For crc32 */ #include "exec/semihost.h" +#include "sysemu/cpus.h" #include "sysemu/kvm.h" #include "fpu/softfloat.h" #include "qemu/range.h" @@ -XXX,XX +XXX,XX @@ typedef struct pm_event { uint64_t (*get_count)(CPUARMState *); } pm_event; +static bool event_always_supported(CPUARMState *env) +{ + return true; +} + +/* + * Return the underlying cycle count for the PMU cycle counters. If we're in + * usermode, simply return 0. + */ +static uint64_t cycles_get_count(CPUARMState *env) +{ +#ifndef CONFIG_USER_ONLY + return muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), + ARM_CPU_FREQ, NANOSECONDS_PER_SECOND); +#else + return cpu_get_host_ticks(); +#endif +} + +#ifndef CONFIG_USER_ONLY +static bool instructions_supported(CPUARMState *env) +{ + return use_icount == 1 /* Precise instruction counting */; +} + +static uint64_t instructions_get_count(CPUARMState *env) +{ + return (uint64_t)cpu_get_icount_raw(); +} +#endif + static const pm_event pm_events[] = { +#ifndef CONFIG_USER_ONLY + { .number = 0x008, /* INST_RETIRED, Instruction architecturally executed */ + .supported = instructions_supported, + .get_count = instructions_get_count, + }, + { .number = 0x011, /* CPU_CYCLES, Cycle */ + .supported = event_always_supported, + .get_count = cycles_get_count, + } +#endif }; /* @@ -XXX,XX +XXX,XX @@ static const pm_event pm_events[] = { * should first be updated to something sparse instead of the current * supported_event_map[] array. */ -#define MAX_EVENT_ID 0x0 +#define MAX_EVENT_ID 0x11 #define UNSUPPORTED_EVENT UINT16_MAX static uint16_t supported_event_map[MAX_EVENT_ID + 1]; @@ -XXX,XX +XXX,XX @@ static CPAccessResult pmreg_access_swinc(CPUARMState *env, return pmreg_access(env, ri, isread); } -#ifndef CONFIG_USER_ONLY - static CPAccessResult pmreg_access_selr(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) @@ -XXX,XX +XXX,XX @@ static bool pmu_counter_enabled(CPUARMState *env, uint8_t counter) */ void pmccntr_op_start(CPUARMState *env) { - uint64_t cycles = 0; - cycles = muldiv64(qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL), - ARM_CPU_FREQ, NANOSECONDS_PER_SECOND); + uint64_t cycles = cycles_get_count(env); if (pmu_counter_enabled(env, 31)) { uint64_t eff_cycles = cycles; @@ -XXX,XX +XXX,XX @@ static void pmccntr_write32(CPUARMState *env, const ARMCPRegInfo *ri, pmccntr_write(env, ri, deposit64(cur_val, 0, 32, value)); } -#else /* CONFIG_USER_ONLY */ - -void pmccntr_op_start(CPUARMState *env) -{ -} - -void pmccntr_op_finish(CPUARMState *env) -{ -} - -void pmevcntr_op_start(CPUARMState *env, uint8_t i) -{ -} - -void pmevcntr_op_finish(CPUARMState *env, uint8_t i) -{ -} - -void pmu_op_start(CPUARMState *env) -{ -} - -void pmu_op_finish(CPUARMState *env) -{ -} - -void pmu_pre_el_change(ARMCPU *cpu, void *ignored) -{ -} - -void pmu_post_el_change(ARMCPU *cpu, void *ignored) -{ -} - -#endif - static void pmccfiltr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v7_cp_reginfo[] = { /* Unimplemented so WI. */ { .name = "PMSWINC", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 4, .access = PL0_W, .accessfn = pmreg_access_swinc, .type = ARM_CP_NOP }, -#ifndef CONFIG_USER_ONLY { .name = "PMSELR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 5, .access = PL0_RW, .type = ARM_CP_ALIAS, .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmselr), @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v7_cp_reginfo[] = { .fieldoffset = offsetof(CPUARMState, cp15.c15_ccnt), .readfn = pmccntr_read, .writefn = pmccntr_write, .raw_readfn = raw_read, .raw_writefn = raw_write, }, -#endif { .name = "PMCCFILTR", .cp = 15, .opc1 = 0, .crn = 14, .crm = 15, .opc2 = 7, .writefn = pmccfiltr_write_a32, .readfn = pmccfiltr_read_a32, .access = PL0_RW, .accessfn = pmreg_access, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) * count register. */ unsigned int i, pmcrn = 0; -#ifndef CONFIG_USER_ONLY ARMCPRegInfo pmcr = { .name = "PMCR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 0, .access = PL0_RW, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) g_free(pmevtyper_name); g_free(pmevtyper_el0_name); } -#endif ARMCPRegInfo clidr = { .name = "CLIDR", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .crn = 0, .crm = 0, .opc1 = 1, .opc2 = 1, -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> This both advertises that we support four counters and enables them because the pmu_num_counters() reads this value from PMCR. Signed-off-by: Aaron Lindsay <alindsay@codeaurora.org> Signed-off-by: Aaron Lindsay <aaron@os.amperecomputing.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20181211151945.29137-13-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v7_cp_reginfo[] = { .access = PL1_W, .type = ARM_CP_NOP }, /* Performance monitors are implementation defined in v7, * but with an ARM recommended set of registers, which we - * follow (although we don't actually implement any counters) + * follow. * * Performance registers fall into three categories: * (a) always UNDEF in PL0, RW in PL1 (PMINTENSET, PMINTENCLR) @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) } if (arm_feature(env, ARM_FEATURE_V7)) { /* v7 performance monitor control register: same implementor - * field as main ID register, and we implement only the cycle - * count register. + * field as main ID register, and we implement four counters in + * addition to the cycle count register. */ - unsigned int i, pmcrn = 0; + unsigned int i, pmcrn = 4; ARMCPRegInfo pmcr = { .name = "PMCR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 0, .access = PL0_RW, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) .access = PL0_RW, .accessfn = pmreg_access, .type = ARM_CP_IO, .fieldoffset = offsetof(CPUARMState, cp15.c9_pmcr), - .resetvalue = cpu->midr & 0xff000000, + .resetvalue = (cpu->midr & 0xff000000) | (pmcrn << PMCRN_SHIFT), .writefn = pmcr_write, .raw_writefn = raw_write, }; define_one_arm_cp_reg(cpu, &pmcr); -- 2.20.1 From: Aaron Lindsay <aaron@os.amperecomputing.com> Signed-off-by: Aaron Lindsay <alindsay@codeaurora.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181211151945.29137-14-aaron@os.amperecomputing.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 39 +++++++++++++++++++++++++++++++++++++-- 1 file changed, 37 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static bool event_always_supported(CPUARMState *env) return true; } +static uint64_t swinc_get_count(CPUARMState *env) +{ + /* + * SW_INCR events are written directly to the pmevcntr's by writes to + * PMSWINC, so there is no underlying count maintained by the PMU itself + */ + return 0; +} + /* * Return the underlying cycle count for the PMU cycle counters. If we're in * usermode, simply return 0. @@ -XXX,XX +XXX,XX @@ static uint64_t instructions_get_count(CPUARMState *env) #endif static const pm_event pm_events[] = { + { .number = 0x000, /* SW_INCR */ + .supported = event_always_supported, + .get_count = swinc_get_count, + }, #ifndef CONFIG_USER_ONLY { .number = 0x008, /* INST_RETIRED, Instruction architecturally executed */ .supported = instructions_supported, @@ -XXX,XX +XXX,XX @@ static void pmcr_write(CPUARMState *env, const ARMCPRegInfo *ri, pmu_op_finish(env); } +static void pmswinc_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + unsigned int i; + for (i = 0; i < pmu_num_counters(env); i++) { + /* Increment a counter's count iff: */ + if ((value & (1 << i)) && /* counter's bit is set */ + /* counter is enabled and not filtered */ + pmu_counter_enabled(env, i) && + /* counter is SW_INCR */ + (env->cp15.c14_pmevtyper[i] & PMXEVTYPER_EVTCOUNT) == 0x0) { + pmevcntr_op_start(env, i); + env->cp15.c14_pmevcntr[i]++; + pmevcntr_op_finish(env, i); + } + } +} + static uint64_t pmccntr_read(CPUARMState *env, const ARMCPRegInfo *ri) { uint64_t ret; @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo v7_cp_reginfo[] = { .fieldoffset = offsetof(CPUARMState, cp15.c9_pmovsr), .writefn = pmovsr_write, .raw_writefn = raw_write }, - /* Unimplemented so WI. */ { .name = "PMSWINC", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 4, - .access = PL0_W, .accessfn = pmreg_access_swinc, .type = ARM_CP_NOP }, + .access = PL0_W, .accessfn = pmreg_access_swinc, .type = ARM_CP_NO_RAW, + .writefn = pmswinc_write }, + { .name = "PMSWINC_EL0", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 9, .crm = 12, .opc2 = 4, + .access = PL0_W, .accessfn = pmreg_access_swinc, .type = ARM_CP_NO_RAW, + .writefn = pmswinc_write }, { .name = "PMSELR", .cp = 15, .crn = 9, .crm = 12, .opc1 = 0, .opc2 = 5, .access = PL0_RW, .type = ARM_CP_ALIAS, .fieldoffset = offsetoflow32(CPUARMState, cp15.c9_pmselr), -- 2.20.1 From: Julia Suvorova <jusual@mail.ru> Run qtest with a socket that connects QEMU chardev and test code. Signed-off-by: Julia Suvorova <jusual@mail.ru> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com> Message-id: 20190117161640.5496-2-jusual@mail.ru Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/libqtest.h | 11 +++++++++++ tests/libqtest.c | 26 ++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) diff --git a/tests/libqtest.h b/tests/libqtest.h index XXXXXXX..XXXXXXX 100644 --- a/tests/libqtest.h +++ b/tests/libqtest.h @@ -XXX,XX +XXX,XX @@ QTestState *qtest_init(const char *extra_args); */ QTestState *qtest_init_without_qmp_handshake(const char *extra_args); +/** + * qtest_init_with_serial: + * @extra_args: other arguments to pass to QEMU. CAUTION: these + * arguments are subject to word splitting and shell evaluation. + * @sock_fd: pointer to store the socket file descriptor for + * connection with serial. + * + * Returns: #QTestState instance. + */ +QTestState *qtest_init_with_serial(const char *extra_args, int *sock_fd); + /** * qtest_quit: * @s: #QTestState instance to operate on. diff --git a/tests/libqtest.c b/tests/libqtest.c index XXXXXXX..XXXXXXX 100644 --- a/tests/libqtest.c +++ b/tests/libqtest.c @@ -XXX,XX +XXX,XX @@ QTestState *qtest_initf(const char *fmt, ...) return s; } +QTestState *qtest_init_with_serial(const char *extra_args, int *sock_fd) +{ + int sock_fd_init; + char *sock_path, sock_dir[] = "/tmp/qtest-serial-XXXXXX"; + QTestState *qts; + + g_assert(mkdtemp(sock_dir)); + sock_path = g_strdup_printf("%s/sock", sock_dir); + + sock_fd_init = init_socket(sock_path); + + qts = qtest_initf("-chardev socket,id=s0,path=%s,nowait " + "-serial chardev:s0 %s", + sock_path, extra_args); + + *sock_fd = socket_accept(sock_fd_init); + + unlink(sock_path); + g_free(sock_path); + rmdir(sock_dir); + + g_assert(*sock_fd >= 0); + + return qts; +} + void qtest_quit(QTestState *s) { g_hook_destroy_link(&abrt_hooks, g_hook_find_data(&abrt_hooks, TRUE, s)); -- 2.20.1