From 1d7ab0288cbc6eb6163455fc25dde7a640ef959b Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:28 -0600 Subject: [PATCH 01/85] target/arm: Add section labels for "Data Processing (register)" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit At the same time, use ### to separate 3rd-level sections. We already use ### for 4.1.92 Data Processing (immediate), but not the two following two third-level sections: 4.1.93 Branches, and 4.1.94 Loads and stores. Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 331a8e180c..d28efb884d 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -161,7 +161,7 @@ UBFM . 10 100110 . ...... ...... ..... ..... @bitfield_32 EXTR 1 00 100111 1 0 rm:5 imm:6 rn:5 rd:5 &extract sf=1 EXTR 0 00 100111 0 0 rm:5 0 imm:5 rn:5 rd:5 &extract sf=0 -# Branches +### Branches %imm26 0:s26 !function=times_4 @branch . ..... .......................... &i imm=%imm26 @@ -291,7 +291,7 @@ HLT 1101 0100 010 ................ 000 00 @i16 # DCPS2 1101 0100 101 ................ 000 10 @i16 # DCPS3 1101 0100 101 ................ 000 11 @i16 -# Loads and stores +### Loads and stores &stxr rn rt rt2 rs sz lasr &stlr rn rt sz lasr @@ -649,6 +649,21 @@ CPYP 00 011 1 01000 ..... .... 01 ..... ..... @cpy CPYM 00 011 1 01010 ..... .... 01 ..... ..... @cpy CPYE 00 011 1 01100 ..... .... 01 ..... ..... @cpy +### Data Processing (register) + +# Data Processing (2-source) +# Data Processing (1-source) +# Logical (shifted reg) +# Add/subtract (shifted reg) +# Add/subtract (extended reg) +# Add/subtract (carry) +# Rotate right into flags +# Evaluate into flags +# Conditional compare (regster) +# Conditional compare (immediate) +# Conditional select +# Data Processing (3-source) + ### Cryptographic AES AESE 01001110 00 10100 00100 10 ..... ..... @r2r_q1e0 From 68298370475c57e3057e3b4d5203e95d0f08647a Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:29 -0600 Subject: [PATCH 02/85] target/arm: Convert UDIV, SDIV to decodetree MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 7 ++++ target/arm/tcg/translate-a64.c | 64 +++++++++++++++++----------------- 2 files changed, 39 insertions(+), 32 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index d28efb884d..c218f6afbc 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -28,6 +28,7 @@ &r rn &ri rd imm &rri_sf rd rn imm sf +&rrr_sf rd rn rm sf &i imm &rr_e rd rn esz &rri_e rd rn imm esz @@ -652,6 +653,12 @@ CPYE 00 011 1 01100 ..... .... 01 ..... ..... @cpy ### Data Processing (register) # Data Processing (2-source) + +@rrr_sf sf:1 .......... rm:5 ...... rn:5 rd:5 &rrr_sf + +UDIV . 00 11010110 ..... 00001 0 ..... ..... @rrr_sf +SDIV . 00 11010110 ..... 00001 1 ..... ..... @rrr_sf + # Data Processing (1-source) # Logical (shifted reg) # Add/subtract (shifted reg) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index b2851ea503..9f687ba840 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -7485,6 +7485,36 @@ TRANS(UQRSHRN_si, do_scalar_shift_imm_narrow, a, uqrshrn_fns, 0, false) TRANS(SQSHRUN_si, do_scalar_shift_imm_narrow, a, sqshrun_fns, MO_SIGN, false) TRANS(SQRSHRUN_si, do_scalar_shift_imm_narrow, a, sqrshrun_fns, MO_SIGN, false) +static bool do_div(DisasContext *s, arg_rrr_sf *a, bool is_signed) +{ + TCGv_i64 tcg_n, tcg_m, tcg_rd; + tcg_rd = cpu_reg(s, a->rd); + + if (!a->sf && is_signed) { + tcg_n = tcg_temp_new_i64(); + tcg_m = tcg_temp_new_i64(); + tcg_gen_ext32s_i64(tcg_n, cpu_reg(s, a->rn)); + tcg_gen_ext32s_i64(tcg_m, cpu_reg(s, a->rm)); + } else { + tcg_n = read_cpu_reg(s, a->rn, a->sf); + tcg_m = read_cpu_reg(s, a->rm, a->sf); + } + + if (is_signed) { + gen_helper_sdiv64(tcg_rd, tcg_n, tcg_m); + } else { + gen_helper_udiv64(tcg_rd, tcg_n, tcg_m); + } + + if (!a->sf) { /* zero extend final result */ + tcg_gen_ext32u_i64(tcg_rd, tcg_rd); + } + return true; +} + +TRANS(SDIV, do_div, a, true) +TRANS(UDIV, do_div, a, false) + /* Shift a TCGv src by TCGv shift_amount, put result in dst. * Note that it is the caller's responsibility to ensure that the * shift amount is in range (ie 0..31 or 0..63) and provide the ARM @@ -8425,32 +8455,6 @@ static void disas_data_proc_1src(DisasContext *s, uint32_t insn) #undef MAP } -static void handle_div(DisasContext *s, bool is_signed, unsigned int sf, - unsigned int rm, unsigned int rn, unsigned int rd) -{ - TCGv_i64 tcg_n, tcg_m, tcg_rd; - tcg_rd = cpu_reg(s, rd); - - if (!sf && is_signed) { - tcg_n = tcg_temp_new_i64(); - tcg_m = tcg_temp_new_i64(); - tcg_gen_ext32s_i64(tcg_n, cpu_reg(s, rn)); - tcg_gen_ext32s_i64(tcg_m, cpu_reg(s, rm)); - } else { - tcg_n = read_cpu_reg(s, rn, sf); - tcg_m = read_cpu_reg(s, rm, sf); - } - - if (is_signed) { - gen_helper_sdiv64(tcg_rd, tcg_n, tcg_m); - } else { - gen_helper_udiv64(tcg_rd, tcg_n, tcg_m); - } - - if (!sf) { /* zero extend final result */ - tcg_gen_ext32u_i64(tcg_rd, tcg_rd); - } -} /* LSLV, LSRV, ASRV, RORV */ static void handle_shift_reg(DisasContext *s, @@ -8552,12 +8556,6 @@ static void disas_data_proc_2src(DisasContext *s, uint32_t insn) } } break; - case 2: /* UDIV */ - handle_div(s, false, sf, rm, rn, rd); - break; - case 3: /* SDIV */ - handle_div(s, true, sf, rm, rn, rd); - break; case 4: /* IRG */ if (sf == 0 || !dc_isar_feature(aa64_mte_insn_reg, s)) { goto do_unallocated; @@ -8616,6 +8614,8 @@ static void disas_data_proc_2src(DisasContext *s, uint32_t insn) } default: do_unallocated: + case 2: /* UDIV */ + case 3: /* SDIV */ unallocated_encoding(s); break; } From f2b6e3531dfccc6b22bd638c8ecfc58cc26135ab Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:30 -0600 Subject: [PATCH 03/85] target/arm: Convert LSLV, LSRV, ASRV, RORV to decodetree MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 4 +++ target/arm/tcg/translate-a64.c | 46 ++++++++++++++++------------------ 2 files changed, 25 insertions(+), 25 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index c218f6afbc..3db55b78a6 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -658,6 +658,10 @@ CPYE 00 011 1 01100 ..... .... 01 ..... ..... @cpy UDIV . 00 11010110 ..... 00001 0 ..... ..... @rrr_sf SDIV . 00 11010110 ..... 00001 1 ..... ..... @rrr_sf +LSLV . 00 11010110 ..... 00100 0 ..... ..... @rrr_sf +LSRV . 00 11010110 ..... 00100 1 ..... ..... @rrr_sf +ASRV . 00 11010110 ..... 00101 0 ..... ..... @rrr_sf +RORV . 00 11010110 ..... 00101 1 ..... ..... @rrr_sf # Data Processing (1-source) # Logical (shifted reg) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 9f687ba840..8b7ca2c68a 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -7575,6 +7575,23 @@ static void shift_reg_imm(TCGv_i64 dst, TCGv_i64 src, int sf, } } +static bool do_shift_reg(DisasContext *s, arg_rrr_sf *a, + enum a64_shift_type shift_type) +{ + TCGv_i64 tcg_shift = tcg_temp_new_i64(); + TCGv_i64 tcg_rd = cpu_reg(s, a->rd); + TCGv_i64 tcg_rn = read_cpu_reg(s, a->rn, a->sf); + + tcg_gen_andi_i64(tcg_shift, cpu_reg(s, a->rm), a->sf ? 63 : 31); + shift_reg(tcg_rd, tcg_rn, a->sf, shift_type, tcg_shift); + return true; +} + +TRANS(LSLV, do_shift_reg, a, A64_SHIFT_TYPE_LSL) +TRANS(LSRV, do_shift_reg, a, A64_SHIFT_TYPE_LSR) +TRANS(ASRV, do_shift_reg, a, A64_SHIFT_TYPE_ASR) +TRANS(RORV, do_shift_reg, a, A64_SHIFT_TYPE_ROR) + /* Logical (shifted register) * 31 30 29 28 24 23 22 21 20 16 15 10 9 5 4 0 * +----+-----+-----------+-------+---+------+--------+------+------+ @@ -8456,19 +8473,6 @@ static void disas_data_proc_1src(DisasContext *s, uint32_t insn) } -/* LSLV, LSRV, ASRV, RORV */ -static void handle_shift_reg(DisasContext *s, - enum a64_shift_type shift_type, unsigned int sf, - unsigned int rm, unsigned int rn, unsigned int rd) -{ - TCGv_i64 tcg_shift = tcg_temp_new_i64(); - TCGv_i64 tcg_rd = cpu_reg(s, rd); - TCGv_i64 tcg_rn = read_cpu_reg(s, rn, sf); - - tcg_gen_andi_i64(tcg_shift, cpu_reg(s, rm), sf ? 63 : 31); - shift_reg(tcg_rd, tcg_rn, sf, shift_type, tcg_shift); -} - /* CRC32[BHWX], CRC32C[BHWX] */ static void handle_crc32(DisasContext *s, unsigned int sf, unsigned int sz, bool crc32c, @@ -8579,18 +8583,6 @@ static void disas_data_proc_2src(DisasContext *s, uint32_t insn) tcg_gen_or_i64(cpu_reg(s, rd), cpu_reg(s, rm), t); } break; - case 8: /* LSLV */ - handle_shift_reg(s, A64_SHIFT_TYPE_LSL, sf, rm, rn, rd); - break; - case 9: /* LSRV */ - handle_shift_reg(s, A64_SHIFT_TYPE_LSR, sf, rm, rn, rd); - break; - case 10: /* ASRV */ - handle_shift_reg(s, A64_SHIFT_TYPE_ASR, sf, rm, rn, rd); - break; - 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; @@ -8616,6 +8608,10 @@ static void disas_data_proc_2src(DisasContext *s, uint32_t insn) do_unallocated: case 2: /* UDIV */ case 3: /* SDIV */ + case 8: /* LSLV */ + case 9: /* LSRV */ + case 10: /* ASRV */ + case 11: /* RORV */ unallocated_encoding(s); break; } From 2a1560f5d35f33f1650964fdf6337f2f4a2cd7ef Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:31 -0600 Subject: [PATCH 04/85] target/arm: Convert CRC32, CRC32C to decodetree MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 12 ++++ target/arm/tcg/translate-a64.c | 101 +++++++++++++-------------------- 2 files changed, 53 insertions(+), 60 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 3db55b78a6..1664f4793c 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -45,7 +45,9 @@ @rr_d ........ ... ..... ...... rn:5 rd:5 &rr_e esz=3 @rr_sd ........ ... ..... ...... rn:5 rd:5 &rr_e esz=%esz_sd +@rrr_b ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=0 @rrr_h ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=1 +@rrr_s ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=2 @rrr_d ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=3 @rrr_sd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_sd @rrr_hsd ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=%esz_hsd @@ -663,6 +665,16 @@ LSRV . 00 11010110 ..... 00100 1 ..... ..... @rrr_sf ASRV . 00 11010110 ..... 00101 0 ..... ..... @rrr_sf RORV . 00 11010110 ..... 00101 1 ..... ..... @rrr_sf +CRC32 0 00 11010110 ..... 0100 00 ..... ..... @rrr_b +CRC32 0 00 11010110 ..... 0100 01 ..... ..... @rrr_h +CRC32 0 00 11010110 ..... 0100 10 ..... ..... @rrr_s +CRC32 1 00 11010110 ..... 0100 11 ..... ..... @rrr_d + +CRC32C 0 00 11010110 ..... 0101 00 ..... ..... @rrr_b +CRC32C 0 00 11010110 ..... 0101 01 ..... ..... @rrr_h +CRC32C 0 00 11010110 ..... 0101 10 ..... ..... @rrr_s +CRC32C 1 00 11010110 ..... 0101 11 ..... ..... @rrr_d + # Data Processing (1-source) # Logical (shifted reg) # Add/subtract (shifted reg) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 8b7ca2c68a..22594a1149 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -7592,6 +7592,39 @@ TRANS(LSRV, do_shift_reg, a, A64_SHIFT_TYPE_LSR) TRANS(ASRV, do_shift_reg, a, A64_SHIFT_TYPE_ASR) TRANS(RORV, do_shift_reg, a, A64_SHIFT_TYPE_ROR) +static bool do_crc32(DisasContext *s, arg_rrr_e *a, bool crc32c) +{ + TCGv_i64 tcg_acc, tcg_val, tcg_rd; + TCGv_i32 tcg_bytes; + + switch (a->esz) { + case MO_8: + case MO_16: + case MO_32: + tcg_val = tcg_temp_new_i64(); + tcg_gen_extract_i64(tcg_val, cpu_reg(s, a->rm), 0, 8 << a->esz); + break; + case MO_64: + tcg_val = cpu_reg(s, a->rm); + break; + default: + g_assert_not_reached(); + } + tcg_acc = cpu_reg(s, a->rn); + tcg_bytes = tcg_constant_i32(1 << a->esz); + tcg_rd = cpu_reg(s, a->rd); + + if (crc32c) { + gen_helper_crc32c_64(tcg_rd, tcg_acc, tcg_val, tcg_bytes); + } else { + gen_helper_crc32_64(tcg_rd, tcg_acc, tcg_val, tcg_bytes); + } + return true; +} + +TRANS_FEAT(CRC32, aa64_crc32, do_crc32, a, false) +TRANS_FEAT(CRC32C, aa64_crc32, do_crc32, a, true) + /* Logical (shifted register) * 31 30 29 28 24 23 22 21 20 16 15 10 9 5 4 0 * +----+-----+-----------+-------+---+------+--------+------+------+ @@ -8473,52 +8506,6 @@ static void disas_data_proc_1src(DisasContext *s, uint32_t insn) } -/* CRC32[BHWX], CRC32C[BHWX] */ -static void handle_crc32(DisasContext *s, - unsigned int sf, unsigned int sz, bool crc32c, - unsigned int rm, unsigned int rn, unsigned int rd) -{ - TCGv_i64 tcg_acc, tcg_val; - TCGv_i32 tcg_bytes; - - if (!dc_isar_feature(aa64_crc32, s) - || (sf == 1 && sz != 3) - || (sf == 0 && sz == 3)) { - unallocated_encoding(s); - return; - } - - if (sz == 3) { - tcg_val = cpu_reg(s, rm); - } else { - uint64_t mask; - switch (sz) { - case 0: - mask = 0xFF; - break; - case 1: - mask = 0xFFFF; - break; - case 2: - mask = 0xFFFFFFFF; - break; - default: - g_assert_not_reached(); - } - tcg_val = tcg_temp_new_i64(); - tcg_gen_andi_i64(tcg_val, cpu_reg(s, rm), mask); - } - - tcg_acc = cpu_reg(s, rn); - tcg_bytes = tcg_constant_i32(1 << sz); - - if (crc32c) { - gen_helper_crc32c_64(cpu_reg(s, rd), tcg_acc, tcg_val, tcg_bytes); - } else { - gen_helper_crc32_64(cpu_reg(s, rd), tcg_acc, tcg_val, tcg_bytes); - } -} - /* Data-processing (2 source) * 31 30 29 28 21 20 16 15 10 9 5 4 0 * +----+---+---+-----------------+------+--------+------+------+ @@ -8590,20 +8577,6 @@ static void disas_data_proc_2src(DisasContext *s, uint32_t insn) gen_helper_pacga(cpu_reg(s, rd), tcg_env, cpu_reg(s, rn), cpu_reg_sp(s, rm)); break; - case 16: - case 17: - case 18: - case 19: - case 20: - case 21: - case 22: - case 23: /* CRC32 */ - { - int sz = extract32(opcode, 0, 2); - bool crc32c = extract32(opcode, 2, 1); - handle_crc32(s, sf, sz, crc32c, rm, rn, rd); - break; - } default: do_unallocated: case 2: /* UDIV */ @@ -8612,6 +8585,14 @@ static void disas_data_proc_2src(DisasContext *s, uint32_t insn) case 9: /* LSRV */ case 10: /* ASRV */ case 11: /* RORV */ + case 16: + case 17: + case 18: + case 19: + case 20: + case 21: + case 22: + case 23: /* CRC32 */ unallocated_encoding(s); break; } From 9be60681c24f1834e93d1ac9d79f77556cd648a3 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:32 -0600 Subject: [PATCH 05/85] target/arm: Convert SUBP, IRG, GMI to decodetree MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 7 +++ target/arm/tcg/translate-a64.c | 94 +++++++++++++++++++--------------- 2 files changed, 59 insertions(+), 42 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 1664f4793c..f0a5ffb1cd 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -26,6 +26,7 @@ %hlm 11:1 20:2 &r rn +&rrr rd rn rm &ri rd imm &rri_sf rd rn imm sf &rrr_sf rd rn rm sf @@ -656,6 +657,7 @@ CPYE 00 011 1 01100 ..... .... 01 ..... ..... @cpy # Data Processing (2-source) +@rrr . .......... rm:5 ...... rn:5 rd:5 &rrr @rrr_sf sf:1 .......... rm:5 ...... rn:5 rd:5 &rrr_sf UDIV . 00 11010110 ..... 00001 0 ..... ..... @rrr_sf @@ -675,6 +677,11 @@ CRC32C 0 00 11010110 ..... 0101 01 ..... ..... @rrr_h CRC32C 0 00 11010110 ..... 0101 10 ..... ..... @rrr_s CRC32C 1 00 11010110 ..... 0101 11 ..... ..... @rrr_d +SUBP 1 00 11010110 ..... 000000 ..... ..... @rrr +SUBPS 1 01 11010110 ..... 000000 ..... ..... @rrr +IRG 1 00 11010110 ..... 000100 ..... ..... @rrr +GMI 1 00 11010110 ..... 000101 ..... ..... @rrr + # Data Processing (1-source) # Logical (shifted reg) # Add/subtract (shifted reg) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 22594a1149..00e55d42ff 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -7625,6 +7625,55 @@ static bool do_crc32(DisasContext *s, arg_rrr_e *a, bool crc32c) TRANS_FEAT(CRC32, aa64_crc32, do_crc32, a, false) TRANS_FEAT(CRC32C, aa64_crc32, do_crc32, a, true) +static bool do_subp(DisasContext *s, arg_rrr *a, bool setflag) +{ + TCGv_i64 tcg_n = read_cpu_reg_sp(s, a->rn, true); + TCGv_i64 tcg_m = read_cpu_reg_sp(s, a->rm, true); + TCGv_i64 tcg_d = cpu_reg(s, a->rd); + + tcg_gen_sextract_i64(tcg_n, tcg_n, 0, 56); + tcg_gen_sextract_i64(tcg_m, tcg_m, 0, 56); + + if (setflag) { + gen_sub_CC(true, tcg_d, tcg_n, tcg_m); + } else { + tcg_gen_sub_i64(tcg_d, tcg_n, tcg_m); + } + return true; +} + +TRANS_FEAT(SUBP, aa64_mte_insn_reg, do_subp, a, false) +TRANS_FEAT(SUBPS, aa64_mte_insn_reg, do_subp, a, true) + +static bool trans_IRG(DisasContext *s, arg_rrr *a) +{ + if (dc_isar_feature(aa64_mte_insn_reg, s)) { + TCGv_i64 tcg_rd = cpu_reg_sp(s, a->rd); + TCGv_i64 tcg_rn = cpu_reg_sp(s, a->rn); + + if (s->ata[0]) { + gen_helper_irg(tcg_rd, tcg_env, tcg_rn, cpu_reg(s, a->rm)); + } else { + gen_address_with_allocation_tag0(tcg_rd, tcg_rn); + } + return true; + } + return false; +} + +static bool trans_GMI(DisasContext *s, arg_rrr *a) +{ + if (dc_isar_feature(aa64_mte_insn_reg, s)) { + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_extract_i64(t, cpu_reg_sp(s, a->rn), 56, 4); + tcg_gen_shl_i64(t, tcg_constant_i64(1), t); + tcg_gen_or_i64(cpu_reg(s, a->rd), cpu_reg(s, a->rm), t); + return true; + } + return false; +} + /* Logical (shifted register) * 31 30 29 28 24 23 22 21 20 16 15 10 9 5 4 0 * +----+-----+-----------+-------+---+------+--------+------+------+ @@ -8528,48 +8577,6 @@ static void disas_data_proc_2src(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0: /* SUBP(S) */ - if (sf == 0 || !dc_isar_feature(aa64_mte_insn_reg, s)) { - goto do_unallocated; - } else { - TCGv_i64 tcg_n, tcg_m, tcg_d; - - tcg_n = read_cpu_reg_sp(s, rn, true); - tcg_m = read_cpu_reg_sp(s, rm, true); - tcg_gen_sextract_i64(tcg_n, tcg_n, 0, 56); - tcg_gen_sextract_i64(tcg_m, tcg_m, 0, 56); - tcg_d = cpu_reg(s, rd); - - if (setflag) { - gen_sub_CC(true, tcg_d, tcg_n, tcg_m); - } else { - tcg_gen_sub_i64(tcg_d, tcg_n, tcg_m); - } - } - break; - case 4: /* IRG */ - if (sf == 0 || !dc_isar_feature(aa64_mte_insn_reg, s)) { - goto do_unallocated; - } - if (s->ata[0]) { - gen_helper_irg(cpu_reg_sp(s, rd), tcg_env, - cpu_reg_sp(s, rn), cpu_reg(s, rm)); - } else { - gen_address_with_allocation_tag0(cpu_reg_sp(s, rd), - cpu_reg_sp(s, rn)); - } - break; - case 5: /* GMI */ - if (sf == 0 || !dc_isar_feature(aa64_mte_insn_reg, s)) { - goto do_unallocated; - } else { - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_extract_i64(t, cpu_reg_sp(s, rn), 56, 4); - tcg_gen_shl_i64(t, tcg_constant_i64(1), t); - tcg_gen_or_i64(cpu_reg(s, rd), cpu_reg(s, rm), t); - } - break; case 12: /* PACGA */ if (sf == 0 || !dc_isar_feature(aa64_pauth, s)) { goto do_unallocated; @@ -8579,8 +8586,11 @@ static void disas_data_proc_2src(DisasContext *s, uint32_t insn) break; default: do_unallocated: + case 0: /* SUBP(S) */ case 2: /* UDIV */ case 3: /* SDIV */ + case 4: /* IRG */ + case 5: /* GMI */ case 8: /* LSLV */ case 9: /* LSRV */ case 10: /* ASRV */ From b466ea8f216508788d33202b5db5a5666a08cb28 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:33 -0600 Subject: [PATCH 06/85] target/arm: Convert PACGA to decodetree MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove disas_data_proc_2src, as this was the last insn decoded by that function. Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 2 ++ target/arm/tcg/translate-a64.c | 65 ++++++---------------------------- 2 files changed, 13 insertions(+), 54 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index f0a5ffb1cd..a23d6a6645 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -682,6 +682,8 @@ SUBPS 1 01 11010110 ..... 000000 ..... ..... @rrr IRG 1 00 11010110 ..... 000100 ..... ..... @rrr GMI 1 00 11010110 ..... 000101 ..... ..... @rrr +PACGA 1 00 11010110 ..... 001100 ..... ..... @rrr + # Data Processing (1-source) # Logical (shifted reg) # Add/subtract (shifted reg) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 00e55d42ff..ca8b644dc7 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -7674,6 +7674,16 @@ static bool trans_GMI(DisasContext *s, arg_rrr *a) return false; } +static bool trans_PACGA(DisasContext *s, arg_rrr *a) +{ + if (dc_isar_feature(aa64_pauth, s)) { + gen_helper_pacga(cpu_reg(s, a->rd), tcg_env, + cpu_reg(s, a->rn), cpu_reg_sp(s, a->rm)); + return true; + } + return false; +} + /* Logical (shifted register) * 31 30 29 28 24 23 22 21 20 16 15 10 9 5 4 0 * +----+-----+-----------+-------+---+------+--------+------+------+ @@ -8555,59 +8565,6 @@ static void disas_data_proc_1src(DisasContext *s, uint32_t insn) } -/* Data-processing (2 source) - * 31 30 29 28 21 20 16 15 10 9 5 4 0 - * +----+---+---+-----------------+------+--------+------+------+ - * | sf | 0 | S | 1 1 0 1 0 1 1 0 | Rm | opcode | Rn | Rd | - * +----+---+---+-----------------+------+--------+------+------+ - */ -static void disas_data_proc_2src(DisasContext *s, uint32_t insn) -{ - unsigned int sf, rm, opcode, rn, rd, setflag; - sf = extract32(insn, 31, 1); - setflag = extract32(insn, 29, 1); - rm = extract32(insn, 16, 5); - opcode = extract32(insn, 10, 6); - rn = extract32(insn, 5, 5); - rd = extract32(insn, 0, 5); - - if (setflag && opcode != 0) { - unallocated_encoding(s); - return; - } - - switch (opcode) { - case 12: /* PACGA */ - if (sf == 0 || !dc_isar_feature(aa64_pauth, s)) { - goto do_unallocated; - } - gen_helper_pacga(cpu_reg(s, rd), tcg_env, - cpu_reg(s, rn), cpu_reg_sp(s, rm)); - break; - default: - do_unallocated: - case 0: /* SUBP(S) */ - case 2: /* UDIV */ - case 3: /* SDIV */ - case 4: /* IRG */ - case 5: /* GMI */ - case 8: /* LSLV */ - case 9: /* LSRV */ - case 10: /* ASRV */ - case 11: /* RORV */ - case 16: - case 17: - case 18: - case 19: - case 20: - case 21: - case 22: - case 23: /* CRC32 */ - unallocated_encoding(s); - break; - } -} - /* * Data processing - register * 31 30 29 28 25 21 20 16 10 0 @@ -8674,7 +8631,7 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) if (op0) { /* (1 source) */ disas_data_proc_1src(s, insn); } else { /* (2 source) */ - disas_data_proc_2src(s, insn); + goto do_unallocated; } break; case 0x8 ... 0xf: /* (3 source) */ From 506a8c11e7fa1447644f728e4ebd2c00eb8e67ff Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:34 -0600 Subject: [PATCH 07/85] target/arm: Convert RBIT, REV16, REV32, REV64 to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 11 +++ target/arm/tcg/translate-a64.c | 137 +++++++++++++++------------------ 2 files changed, 72 insertions(+), 76 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index a23d6a6645..dd44651f34 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -28,6 +28,8 @@ &r rn &rrr rd rn rm &ri rd imm +&rr rd rn +&rr_sf rd rn sf &rri_sf rd rn imm sf &rrr_sf rd rn rm sf &i imm @@ -685,6 +687,15 @@ GMI 1 00 11010110 ..... 000101 ..... ..... @rrr PACGA 1 00 11010110 ..... 001100 ..... ..... @rrr # Data Processing (1-source) + +@rr . .......... ..... ...... rn:5 rd:5 &rr +@rr_sf sf:1 .......... ..... ...... rn:5 rd:5 &rr_sf + +RBIT . 10 11010110 00000 000000 ..... ..... @rr_sf +REV16 . 10 11010110 00000 000001 ..... ..... @rr_sf +REV32 . 10 11010110 00000 000010 ..... ..... @rr_sf +REV64 1 10 11010110 00000 000011 ..... ..... @rr + # Logical (shifted reg) # Add/subtract (shifted reg) # Add/subtract (extended reg) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index ca8b644dc7..1805d77f43 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -7684,6 +7684,60 @@ static bool trans_PACGA(DisasContext *s, arg_rrr *a) return false; } +typedef void ArithOneOp(TCGv_i64, TCGv_i64); + +static bool gen_rr(DisasContext *s, int rd, int rn, ArithOneOp fn) +{ + fn(cpu_reg(s, rd), cpu_reg(s, rn)); + return true; +} + +static void gen_rbit32(TCGv_i64 tcg_rd, TCGv_i64 tcg_rn) +{ + TCGv_i32 t32 = tcg_temp_new_i32(); + + tcg_gen_extrl_i64_i32(t32, tcg_rn); + gen_helper_rbit(t32, t32); + tcg_gen_extu_i32_i64(tcg_rd, t32); +} + +static void gen_rev16_xx(TCGv_i64 tcg_rd, TCGv_i64 tcg_rn, TCGv_i64 mask) +{ + TCGv_i64 tcg_tmp = tcg_temp_new_i64(); + + tcg_gen_shri_i64(tcg_tmp, tcg_rn, 8); + tcg_gen_and_i64(tcg_rd, tcg_rn, mask); + tcg_gen_and_i64(tcg_tmp, tcg_tmp, mask); + tcg_gen_shli_i64(tcg_rd, tcg_rd, 8); + tcg_gen_or_i64(tcg_rd, tcg_rd, tcg_tmp); +} + +static void gen_rev16_32(TCGv_i64 tcg_rd, TCGv_i64 tcg_rn) +{ + gen_rev16_xx(tcg_rd, tcg_rn, tcg_constant_i64(0x00ff00ff)); +} + +static void gen_rev16_64(TCGv_i64 tcg_rd, TCGv_i64 tcg_rn) +{ + gen_rev16_xx(tcg_rd, tcg_rn, tcg_constant_i64(0x00ff00ff00ff00ffull)); +} + +static void gen_rev_32(TCGv_i64 tcg_rd, TCGv_i64 tcg_rn) +{ + tcg_gen_bswap32_i64(tcg_rd, tcg_rn, TCG_BSWAP_OZ); +} + +static void gen_rev32(TCGv_i64 tcg_rd, TCGv_i64 tcg_rn) +{ + tcg_gen_bswap64_i64(tcg_rd, tcg_rn); + tcg_gen_rotri_i64(tcg_rd, tcg_rd, 32); +} + +TRANS(RBIT, gen_rr, a->rd, a->rn, a->sf ? gen_helper_rbit64 : gen_rbit32) +TRANS(REV16, gen_rr, a->rd, a->rn, a->sf ? gen_rev16_64 : gen_rev16_32) +TRANS(REV32, gen_rr, a->rd, a->rn, a->sf ? gen_rev32 : gen_rev_32) +TRANS(REV64, gen_rr, a->rd, a->rn, tcg_gen_bswap64_i64) + /* Logical (shifted register) * 31 30 29 28 24 23 22 21 20 16 15 10 9 5 4 0 * +----+-----+-----------+-------+---+------+--------+------+------+ @@ -8302,67 +8356,6 @@ static void handle_cls(DisasContext *s, unsigned int sf, } } -static void handle_rbit(DisasContext *s, unsigned int sf, - unsigned int rn, unsigned int rd) -{ - TCGv_i64 tcg_rd, tcg_rn; - tcg_rd = cpu_reg(s, rd); - tcg_rn = cpu_reg(s, rn); - - if (sf) { - gen_helper_rbit64(tcg_rd, tcg_rn); - } else { - TCGv_i32 tcg_tmp32 = tcg_temp_new_i32(); - tcg_gen_extrl_i64_i32(tcg_tmp32, tcg_rn); - gen_helper_rbit(tcg_tmp32, tcg_tmp32); - tcg_gen_extu_i32_i64(tcg_rd, tcg_tmp32); - } -} - -/* REV with sf==1, opcode==3 ("REV64") */ -static void handle_rev64(DisasContext *s, unsigned int sf, - unsigned int rn, unsigned int rd) -{ - if (!sf) { - unallocated_encoding(s); - return; - } - tcg_gen_bswap64_i64(cpu_reg(s, rd), cpu_reg(s, rn)); -} - -/* REV with sf==0, opcode==2 - * REV32 (sf==1, opcode==2) - */ -static void handle_rev32(DisasContext *s, unsigned int sf, - unsigned int rn, unsigned int rd) -{ - TCGv_i64 tcg_rd = cpu_reg(s, rd); - TCGv_i64 tcg_rn = cpu_reg(s, rn); - - if (sf) { - tcg_gen_bswap64_i64(tcg_rd, tcg_rn); - tcg_gen_rotri_i64(tcg_rd, tcg_rd, 32); - } else { - tcg_gen_bswap32_i64(tcg_rd, tcg_rn, TCG_BSWAP_OZ); - } -} - -/* REV16 (opcode==1) */ -static void handle_rev16(DisasContext *s, unsigned int sf, - unsigned int rn, unsigned int rd) -{ - TCGv_i64 tcg_rd = cpu_reg(s, rd); - TCGv_i64 tcg_tmp = tcg_temp_new_i64(); - TCGv_i64 tcg_rn = read_cpu_reg(s, rn, sf); - TCGv_i64 mask = tcg_constant_i64(sf ? 0x00ff00ff00ff00ffull : 0x00ff00ff); - - tcg_gen_shri_i64(tcg_tmp, tcg_rn, 8); - tcg_gen_and_i64(tcg_rd, tcg_rn, mask); - tcg_gen_and_i64(tcg_tmp, tcg_tmp, mask); - tcg_gen_shli_i64(tcg_rd, tcg_rd, 8); - tcg_gen_or_i64(tcg_rd, tcg_rd, tcg_tmp); -} - /* Data-processing (1 source) * 31 30 29 28 21 20 16 15 10 9 5 4 0 * +----+---+---+-----------------+---------+--------+------+------+ @@ -8388,21 +8381,6 @@ static void disas_data_proc_1src(DisasContext *s, uint32_t insn) #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 MAP(0, 0x00, 0x01): /* REV16 */ - case MAP(1, 0x00, 0x01): - handle_rev16(s, sf, rn, rd); - break; - case MAP(0, 0x00, 0x02): /* REV/REV32 */ - case MAP(1, 0x00, 0x02): - handle_rev32(s, sf, rn, rd); - break; - case MAP(1, 0x00, 0x03): /* REV64 */ - handle_rev64(s, sf, rn, rd); - break; case MAP(0, 0x00, 0x04): /* CLZ */ case MAP(1, 0x00, 0x04): handle_clz(s, sf, rn, rd); @@ -8557,6 +8535,13 @@ static void disas_data_proc_1src(DisasContext *s, uint32_t insn) break; default: do_unallocated: + case MAP(0, 0x00, 0x00): /* RBIT */ + case MAP(1, 0x00, 0x00): + case MAP(0, 0x00, 0x01): /* REV16 */ + case MAP(1, 0x00, 0x01): + case MAP(0, 0x00, 0x02): /* REV/REV32 */ + case MAP(1, 0x00, 0x02): + case MAP(1, 0x00, 0x03): /* REV64 */ unallocated_encoding(s); break; } From faa966dffe296654b23ecc7879f34e10b5700d6f Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:35 -0600 Subject: [PATCH 08/85] target/arm: Convert CLZ, CLS to decodetree MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 3 ++ target/arm/tcg/translate-a64.c | 72 ++++++++++++++-------------------- 2 files changed, 33 insertions(+), 42 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index dd44651f34..410eaa9333 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -696,6 +696,9 @@ REV16 . 10 11010110 00000 000001 ..... ..... @rr_sf REV32 . 10 11010110 00000 000010 ..... ..... @rr_sf REV64 1 10 11010110 00000 000011 ..... ..... @rr +CLZ . 10 11010110 00000 000100 ..... ..... @rr_sf +CLS . 10 11010110 00000 000101 ..... ..... @rr_sf + # Logical (shifted reg) # Add/subtract (shifted reg) # Add/subtract (extended reg) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 1805d77f43..552b45b4e2 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -7738,6 +7738,32 @@ TRANS(REV16, gen_rr, a->rd, a->rn, a->sf ? gen_rev16_64 : gen_rev16_32) TRANS(REV32, gen_rr, a->rd, a->rn, a->sf ? gen_rev32 : gen_rev_32) TRANS(REV64, gen_rr, a->rd, a->rn, tcg_gen_bswap64_i64) +static void gen_clz32(TCGv_i64 tcg_rd, TCGv_i64 tcg_rn) +{ + TCGv_i32 t32 = tcg_temp_new_i32(); + + tcg_gen_extrl_i64_i32(t32, tcg_rn); + tcg_gen_clzi_i32(t32, t32, 32); + tcg_gen_extu_i32_i64(tcg_rd, t32); +} + +static void gen_clz64(TCGv_i64 tcg_rd, TCGv_i64 tcg_rn) +{ + tcg_gen_clzi_i64(tcg_rd, tcg_rn, 64); +} + +static void gen_cls32(TCGv_i64 tcg_rd, TCGv_i64 tcg_rn) +{ + TCGv_i32 t32 = tcg_temp_new_i32(); + + tcg_gen_extrl_i64_i32(t32, tcg_rn); + tcg_gen_clrsb_i32(t32, t32); + tcg_gen_extu_i32_i64(tcg_rd, t32); +} + +TRANS(CLZ, gen_rr, a->rd, a->rn, a->sf ? gen_clz64 : gen_clz32) +TRANS(CLS, gen_rr, a->rd, a->rn, a->sf ? tcg_gen_clrsb_i64 : gen_cls32) + /* Logical (shifted register) * 31 30 29 28 24 23 22 21 20 16 15 10 9 5 4 0 * +----+-----+-----------+-------+---+------+--------+------+------+ @@ -8322,40 +8348,6 @@ static void disas_cond_select(DisasContext *s, uint32_t insn) } } -static void handle_clz(DisasContext *s, unsigned int sf, - unsigned int rn, unsigned int rd) -{ - TCGv_i64 tcg_rd, tcg_rn; - tcg_rd = cpu_reg(s, rd); - tcg_rn = cpu_reg(s, rn); - - if (sf) { - tcg_gen_clzi_i64(tcg_rd, tcg_rn, 64); - } else { - TCGv_i32 tcg_tmp32 = tcg_temp_new_i32(); - tcg_gen_extrl_i64_i32(tcg_tmp32, tcg_rn); - tcg_gen_clzi_i32(tcg_tmp32, tcg_tmp32, 32); - tcg_gen_extu_i32_i64(tcg_rd, tcg_tmp32); - } -} - -static void handle_cls(DisasContext *s, unsigned int sf, - unsigned int rn, unsigned int rd) -{ - TCGv_i64 tcg_rd, tcg_rn; - tcg_rd = cpu_reg(s, rd); - tcg_rn = cpu_reg(s, rn); - - if (sf) { - tcg_gen_clrsb_i64(tcg_rd, tcg_rn); - } else { - TCGv_i32 tcg_tmp32 = tcg_temp_new_i32(); - tcg_gen_extrl_i64_i32(tcg_tmp32, tcg_rn); - tcg_gen_clrsb_i32(tcg_tmp32, tcg_tmp32); - tcg_gen_extu_i32_i64(tcg_rd, tcg_tmp32); - } -} - /* Data-processing (1 source) * 31 30 29 28 21 20 16 15 10 9 5 4 0 * +----+---+---+-----------------+---------+--------+------+------+ @@ -8381,14 +8373,6 @@ static void disas_data_proc_1src(DisasContext *s, uint32_t insn) #define MAP(SF, O2, O1) ((SF) | (O1 << 1) | (O2 << 7)) switch (MAP(sf, opcode2, opcode)) { - case MAP(0, 0x00, 0x04): /* CLZ */ - case MAP(1, 0x00, 0x04): - handle_clz(s, sf, rn, rd); - break; - case MAP(0, 0x00, 0x05): /* CLS */ - 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); @@ -8542,6 +8526,10 @@ static void disas_data_proc_1src(DisasContext *s, uint32_t insn) case MAP(0, 0x00, 0x02): /* REV/REV32 */ case MAP(1, 0x00, 0x02): case MAP(1, 0x00, 0x03): /* REV64 */ + case MAP(0, 0x00, 0x04): /* CLZ */ + case MAP(1, 0x00, 0x04): + case MAP(0, 0x00, 0x05): /* CLS */ + case MAP(1, 0x00, 0x05): unallocated_encoding(s); break; } From 6934d6c35c5253ece2577d3475bdee78f489aeef Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:36 -0600 Subject: [PATCH 09/85] target/arm: Convert PAC[ID]*, AUT[ID]* to decodetree This includes PACIA, PACIZA, PACIB, PACIZB, PACDA, PACDZA, PACDB, PACDZB, AUTIA, AUTIZA, AUTIB, AUTIZB, AUTDA, AUTDZA, AUTDB, AUTDZB. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 13 +++ target/arm/tcg/translate-a64.c | 173 +++++++++------------------------ 2 files changed, 58 insertions(+), 128 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 410eaa9333..9083ac4ac3 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -699,6 +699,19 @@ REV64 1 10 11010110 00000 000011 ..... ..... @rr CLZ . 10 11010110 00000 000100 ..... ..... @rr_sf CLS . 10 11010110 00000 000101 ..... ..... @rr_sf +&pacaut rd rn z +@pacaut . .. ........ ..... .. z:1 ... rn:5 rd:5 &pacaut + +PACIA 1 10 11010110 00001 00.000 ..... ..... @pacaut +PACIB 1 10 11010110 00001 00.001 ..... ..... @pacaut +PACDA 1 10 11010110 00001 00.010 ..... ..... @pacaut +PACDB 1 10 11010110 00001 00.011 ..... ..... @pacaut + +AUTIA 1 10 11010110 00001 00.100 ..... ..... @pacaut +AUTIB 1 10 11010110 00001 00.101 ..... ..... @pacaut +AUTDA 1 10 11010110 00001 00.110 ..... ..... @pacaut +AUTDB 1 10 11010110 00001 00.111 ..... ..... @pacaut + # Logical (shifted reg) # Add/subtract (shifted reg) # Add/subtract (extended reg) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 552b45b4e2..852545dfcc 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -7764,6 +7764,35 @@ static void gen_cls32(TCGv_i64 tcg_rd, TCGv_i64 tcg_rn) TRANS(CLZ, gen_rr, a->rd, a->rn, a->sf ? gen_clz64 : gen_clz32) TRANS(CLS, gen_rr, a->rd, a->rn, a->sf ? tcg_gen_clrsb_i64 : gen_cls32) +static bool gen_pacaut(DisasContext *s, arg_pacaut *a, NeonGenTwo64OpEnvFn fn) +{ + TCGv_i64 tcg_rd, tcg_rn; + + if (a->z) { + if (a->rn != 31) { + return false; + } + tcg_rn = tcg_constant_i64(0); + } else { + tcg_rn = cpu_reg_sp(s, a->rn); + } + if (s->pauth_active) { + tcg_rd = cpu_reg(s, a->rd); + fn(tcg_rd, tcg_env, tcg_rd, tcg_rn); + } + return true; +} + +TRANS_FEAT(PACIA, aa64_pauth, gen_pacaut, a, gen_helper_pacia) +TRANS_FEAT(PACIB, aa64_pauth, gen_pacaut, a, gen_helper_pacib) +TRANS_FEAT(PACDA, aa64_pauth, gen_pacaut, a, gen_helper_pacda) +TRANS_FEAT(PACDB, aa64_pauth, gen_pacaut, a, gen_helper_pacdb) + +TRANS_FEAT(AUTIA, aa64_pauth, gen_pacaut, a, gen_helper_autia) +TRANS_FEAT(AUTIB, aa64_pauth, gen_pacaut, a, gen_helper_autib) +TRANS_FEAT(AUTDA, aa64_pauth, gen_pacaut, a, gen_helper_autda) +TRANS_FEAT(AUTDB, aa64_pauth, gen_pacaut, a, gen_helper_autdb) + /* Logical (shifted register) * 31 30 29 28 24 23 22 21 20 16 15 10 9 5 4 0 * +----+-----+-----------+-------+---+------+--------+------+------+ @@ -8373,134 +8402,6 @@ static void disas_data_proc_1src(DisasContext *s, uint32_t insn) #define MAP(SF, O2, O1) ((SF) | (O1 << 1) | (O2 << 7)) switch (MAP(sf, opcode2, opcode)) { - case MAP(1, 0x01, 0x00): /* PACIA */ - if (s->pauth_active) { - tcg_rd = cpu_reg(s, rd); - gen_helper_pacia(tcg_rd, tcg_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, tcg_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, tcg_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, tcg_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, tcg_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, tcg_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, tcg_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, tcg_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, tcg_env, tcg_rd, tcg_constant_i64(0)); - } - 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, tcg_env, tcg_rd, tcg_constant_i64(0)); - } - 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, tcg_env, tcg_rd, tcg_constant_i64(0)); - } - 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, tcg_env, tcg_rd, tcg_constant_i64(0)); - } - 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, tcg_env, tcg_rd, tcg_constant_i64(0)); - } - 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, tcg_env, tcg_rd, tcg_constant_i64(0)); - } - 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, tcg_env, tcg_rd, tcg_constant_i64(0)); - } - 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, tcg_env, tcg_rd, tcg_constant_i64(0)); - } - break; case MAP(1, 0x01, 0x10): /* XPACI */ if (!dc_isar_feature(aa64_pauth, s) || rn != 31) { goto do_unallocated; @@ -8530,6 +8431,22 @@ static void disas_data_proc_1src(DisasContext *s, uint32_t insn) case MAP(1, 0x00, 0x04): case MAP(0, 0x00, 0x05): /* CLS */ case MAP(1, 0x00, 0x05): + case MAP(1, 0x01, 0x00): /* PACIA */ + case MAP(1, 0x01, 0x01): /* PACIB */ + case MAP(1, 0x01, 0x02): /* PACDA */ + case MAP(1, 0x01, 0x03): /* PACDB */ + case MAP(1, 0x01, 0x04): /* AUTIA */ + case MAP(1, 0x01, 0x05): /* AUTIB */ + case MAP(1, 0x01, 0x06): /* AUTDA */ + case MAP(1, 0x01, 0x07): /* AUTDB */ + case MAP(1, 0x01, 0x08): /* PACIZA */ + case MAP(1, 0x01, 0x09): /* PACIZB */ + case MAP(1, 0x01, 0x0a): /* PACDZA */ + case MAP(1, 0x01, 0x0b): /* PACDZB */ + case MAP(1, 0x01, 0x0c): /* AUTIZA */ + case MAP(1, 0x01, 0x0d): /* AUTIZB */ + case MAP(1, 0x01, 0x0e): /* AUTDZA */ + case MAP(1, 0x01, 0x0f): /* AUTDZB */ unallocated_encoding(s); break; } From 44e12416e8b0689252acbb7324adda1b9297e816 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:37 -0600 Subject: [PATCH 10/85] target/arm: Convert XPAC[ID] to decodetree MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Remove disas_data_proc_1src, as these were the last insns decoded by that function. Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 3 ++ target/arm/tcg/translate-a64.c | 99 +++++----------------------------- 2 files changed, 16 insertions(+), 86 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 9083ac4ac3..0e04ab6ce4 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -712,6 +712,9 @@ AUTIB 1 10 11010110 00001 00.101 ..... ..... @pacaut AUTDA 1 10 11010110 00001 00.110 ..... ..... @pacaut AUTDB 1 10 11010110 00001 00.111 ..... ..... @pacaut +XPACI 1 10 11010110 00001 010000 11111 rd:5 +XPACD 1 10 11010110 00001 010001 11111 rd:5 + # Logical (shifted reg) # Add/subtract (shifted reg) # Add/subtract (extended reg) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 852545dfcc..d92fe68299 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -7793,6 +7793,18 @@ TRANS_FEAT(AUTIB, aa64_pauth, gen_pacaut, a, gen_helper_autib) TRANS_FEAT(AUTDA, aa64_pauth, gen_pacaut, a, gen_helper_autda) TRANS_FEAT(AUTDB, aa64_pauth, gen_pacaut, a, gen_helper_autdb) +static bool do_xpac(DisasContext *s, int rd, NeonGenOne64OpEnvFn *fn) +{ + if (s->pauth_active) { + TCGv_i64 tcg_rd = cpu_reg(s, rd); + fn(tcg_rd, tcg_env, tcg_rd); + } + return true; +} + +TRANS_FEAT(XPACI, aa64_pauth, do_xpac, a->rd, gen_helper_xpaci) +TRANS_FEAT(XPACD, aa64_pauth, do_xpac, a->rd, gen_helper_xpacd) + /* Logical (shifted register) * 31 30 29 28 24 23 22 21 20 16 15 10 9 5 4 0 * +----+-----+-----------+-------+---+------+--------+------+------+ @@ -8377,84 +8389,6 @@ static void disas_cond_select(DisasContext *s, uint32_t insn) } } -/* Data-processing (1 source) - * 31 30 29 28 21 20 16 15 10 9 5 4 0 - * +----+---+---+-----------------+---------+--------+------+------+ - * | sf | 1 | S | 1 1 0 1 0 1 1 0 | opcode2 | opcode | Rn | Rd | - * +----+---+---+-----------------+---------+--------+------+------+ - */ -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); - 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); - -#define MAP(SF, O2, O1) ((SF) | (O1 << 1) | (O2 << 7)) - - switch (MAP(sf, opcode2, opcode)) { - 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, tcg_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, tcg_env, tcg_rd); - } - break; - default: - do_unallocated: - case MAP(0, 0x00, 0x00): /* RBIT */ - case MAP(1, 0x00, 0x00): - case MAP(0, 0x00, 0x01): /* REV16 */ - case MAP(1, 0x00, 0x01): - case MAP(0, 0x00, 0x02): /* REV/REV32 */ - case MAP(1, 0x00, 0x02): - case MAP(1, 0x00, 0x03): /* REV64 */ - case MAP(0, 0x00, 0x04): /* CLZ */ - case MAP(1, 0x00, 0x04): - case MAP(0, 0x00, 0x05): /* CLS */ - case MAP(1, 0x00, 0x05): - case MAP(1, 0x01, 0x00): /* PACIA */ - case MAP(1, 0x01, 0x01): /* PACIB */ - case MAP(1, 0x01, 0x02): /* PACDA */ - case MAP(1, 0x01, 0x03): /* PACDB */ - case MAP(1, 0x01, 0x04): /* AUTIA */ - case MAP(1, 0x01, 0x05): /* AUTIB */ - case MAP(1, 0x01, 0x06): /* AUTDA */ - case MAP(1, 0x01, 0x07): /* AUTDB */ - case MAP(1, 0x01, 0x08): /* PACIZA */ - case MAP(1, 0x01, 0x09): /* PACIZB */ - case MAP(1, 0x01, 0x0a): /* PACDZA */ - case MAP(1, 0x01, 0x0b): /* PACDZB */ - case MAP(1, 0x01, 0x0c): /* AUTIZA */ - case MAP(1, 0x01, 0x0d): /* AUTIZB */ - case MAP(1, 0x01, 0x0e): /* AUTDZA */ - case MAP(1, 0x01, 0x0f): /* AUTDZB */ - unallocated_encoding(s); - break; - } - -#undef MAP -} - - /* * Data processing - register * 31 30 29 28 25 21 20 16 10 0 @@ -8464,7 +8398,6 @@ static void disas_data_proc_1src(DisasContext *s, uint32_t insn) */ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) { - int op0 = extract32(insn, 30, 1); int op1 = extract32(insn, 28, 1); int op2 = extract32(insn, 21, 4); int op3 = extract32(insn, 10, 6); @@ -8517,19 +8450,13 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) disas_cond_select(s, insn); break; - case 0x6: /* Data-processing */ - if (op0) { /* (1 source) */ - disas_data_proc_1src(s, insn); - } else { /* (2 source) */ - goto do_unallocated; - } - break; case 0x8 ... 0xf: /* (3 source) */ disas_data_proc_3src(s, insn); break; default: do_unallocated: + case 0x6: /* Data-processing */ unallocated_encoding(s); break; } From 03a1723bd187e30cf45daae120e6236164af2dc4 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:38 -0600 Subject: [PATCH 11/85] target/arm: Convert disas_logic_reg to decodetree This includes AND, BIC, ORR, ORN, EOR, EON, ANDS, BICS (shifted reg). Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 9 +++ target/arm/tcg/translate-a64.c | 117 ++++++++++++--------------------- 2 files changed, 51 insertions(+), 75 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 0e04ab6ce4..8e2949d236 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -716,6 +716,15 @@ XPACI 1 10 11010110 00001 010000 11111 rd:5 XPACD 1 10 11010110 00001 010001 11111 rd:5 # Logical (shifted reg) + +&logic_shift rd rn rm sf sa st n +@logic_shift sf:1 .. ..... st:2 n:1 rm:5 sa:6 rn:5 rd:5 &logic_shift + +AND_r . 00 01010 .. . ..... ...... ..... ..... @logic_shift +ORR_r . 01 01010 .. . ..... ...... ..... ..... @logic_shift +EOR_r . 10 01010 .. . ..... ...... ..... ..... @logic_shift +ANDS_r . 11 01010 .. . ..... ...... ..... ..... @logic_shift + # Add/subtract (shifted reg) # Add/subtract (extended reg) # Add/subtract (carry) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index d92fe68299..ecc8899dd8 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -7805,96 +7805,65 @@ static bool do_xpac(DisasContext *s, int rd, NeonGenOne64OpEnvFn *fn) TRANS_FEAT(XPACI, aa64_pauth, do_xpac, a->rd, gen_helper_xpaci) TRANS_FEAT(XPACD, aa64_pauth, do_xpac, a->rd, gen_helper_xpacd) -/* Logical (shifted register) - * 31 30 29 28 24 23 22 21 20 16 15 10 9 5 4 0 - * +----+-----+-----------+-------+---+------+--------+------+------+ - * | sf | opc | 0 1 0 1 0 | shift | N | Rm | imm6 | Rn | Rd | - * +----+-----+-----------+-------+---+------+--------+------+------+ - */ -static void disas_logic_reg(DisasContext *s, uint32_t insn) +static bool do_logic_reg(DisasContext *s, arg_logic_shift *a, + ArithTwoOp *fn, ArithTwoOp *inv_fn, bool setflags) { TCGv_i64 tcg_rd, tcg_rn, tcg_rm; - unsigned int sf, opc, shift_type, invert, rm, shift_amount, rn, rd; - sf = extract32(insn, 31, 1); - opc = extract32(insn, 29, 2); - shift_type = extract32(insn, 22, 2); - invert = extract32(insn, 21, 1); - rm = extract32(insn, 16, 5); - shift_amount = extract32(insn, 10, 6); - rn = extract32(insn, 5, 5); - rd = extract32(insn, 0, 5); - - if (!sf && (shift_amount & (1 << 5))) { - unallocated_encoding(s); - return; + if (!a->sf && (a->sa & (1 << 5))) { + return false; } - tcg_rd = cpu_reg(s, rd); + tcg_rd = cpu_reg(s, a->rd); + tcg_rn = cpu_reg(s, a->rn); - if (opc == 1 && shift_amount == 0 && shift_type == 0 && rn == 31) { - /* Unshifted ORR and ORN with WZR/XZR is the standard encoding for - * register-register MOV and MVN, so it is worth special casing. - */ - tcg_rm = cpu_reg(s, rm); - if (invert) { + tcg_rm = read_cpu_reg(s, a->rm, a->sf); + if (a->sa) { + shift_reg_imm(tcg_rm, tcg_rm, a->sf, a->st, a->sa); + } + + (a->n ? inv_fn : fn)(tcg_rd, tcg_rn, tcg_rm); + if (!a->sf) { + tcg_gen_ext32u_i64(tcg_rd, tcg_rd); + } + if (setflags) { + gen_logic_CC(a->sf, tcg_rd); + } + return true; +} + +static bool trans_ORR_r(DisasContext *s, arg_logic_shift *a) +{ + /* + * Unshifted ORR and ORN with WZR/XZR is the standard encoding for + * register-register MOV and MVN, so it is worth special casing. + */ + if (a->sa == 0 && a->st == 0 && a->rn == 31) { + TCGv_i64 tcg_rd = cpu_reg(s, a->rd); + TCGv_i64 tcg_rm = cpu_reg(s, a->rm); + + if (a->n) { tcg_gen_not_i64(tcg_rd, tcg_rm); - if (!sf) { + if (!a->sf) { tcg_gen_ext32u_i64(tcg_rd, tcg_rd); } } else { - if (sf) { + if (a->sf) { tcg_gen_mov_i64(tcg_rd, tcg_rm); } else { tcg_gen_ext32u_i64(tcg_rd, tcg_rm); } } - return; + return true; } - tcg_rm = read_cpu_reg(s, rm, sf); - - if (shift_amount) { - shift_reg_imm(tcg_rm, tcg_rm, sf, shift_type, shift_amount); - } - - tcg_rn = cpu_reg(s, rn); - - switch (opc | (invert << 2)) { - case 0: /* AND */ - case 3: /* ANDS */ - tcg_gen_and_i64(tcg_rd, tcg_rn, tcg_rm); - break; - case 1: /* ORR */ - tcg_gen_or_i64(tcg_rd, tcg_rn, tcg_rm); - break; - case 2: /* EOR */ - tcg_gen_xor_i64(tcg_rd, tcg_rn, tcg_rm); - break; - case 4: /* BIC */ - case 7: /* BICS */ - tcg_gen_andc_i64(tcg_rd, tcg_rn, tcg_rm); - break; - case 5: /* ORN */ - tcg_gen_orc_i64(tcg_rd, tcg_rn, tcg_rm); - break; - case 6: /* EON */ - tcg_gen_eqv_i64(tcg_rd, tcg_rn, tcg_rm); - break; - default: - assert(FALSE); - break; - } - - if (!sf) { - tcg_gen_ext32u_i64(tcg_rd, tcg_rd); - } - - if (opc == 3) { - gen_logic_CC(sf, tcg_rd); - } + return do_logic_reg(s, a, tcg_gen_or_i64, tcg_gen_orc_i64, false); } +TRANS(AND_r, do_logic_reg, a, tcg_gen_and_i64, tcg_gen_andc_i64, false) +TRANS(ANDS_r, do_logic_reg, a, tcg_gen_and_i64, tcg_gen_andc_i64, true) +TRANS(EOR_r, do_logic_reg, a, tcg_gen_xor_i64, tcg_gen_eqv_i64, false) + /* * Add/subtract (extended register) * @@ -8411,11 +8380,9 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) /* Add/sub (shifted register) */ disas_add_sub_reg(s, insn); } - } else { - /* Logical (shifted register) */ - disas_logic_reg(s, insn); + return; } - return; + goto do_unallocated; } switch (op2) { From 7e16f3c3d4e044279b645b56f0b500048acd7cc9 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:39 -0600 Subject: [PATCH 12/85] target/arm: Convert disas_add_sub_ext_reg to decodetree This includes ADD, SUB, ADDS, SUBS (extended register). Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 9 +++++ target/arm/tcg/translate-a64.c | 65 +++++++++++----------------------- 2 files changed, 29 insertions(+), 45 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 8e2949d236..0539694506 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -727,6 +727,15 @@ ANDS_r . 11 01010 .. . ..... ...... ..... ..... @logic_shift # Add/subtract (shifted reg) # Add/subtract (extended reg) + +&addsub_ext rd rn rm sf sa st +@addsub_ext sf:1 .. ........ rm:5 st:3 sa:3 rn:5 rd:5 &addsub_ext + +ADD_ext . 00 01011001 ..... ... ... ..... ..... @addsub_ext +SUB_ext . 10 01011001 ..... ... ... ..... ..... @addsub_ext +ADDS_ext . 01 01011001 ..... ... ... ..... ..... @addsub_ext +SUBS_ext . 11 01011001 ..... ... ... ..... ..... @addsub_ext + # Add/subtract (carry) # Rotate right into flags # Evaluate into flags diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index ecc8899dd8..8f777875fe 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -7864,57 +7864,27 @@ TRANS(AND_r, do_logic_reg, a, tcg_gen_and_i64, tcg_gen_andc_i64, false) TRANS(ANDS_r, do_logic_reg, a, tcg_gen_and_i64, tcg_gen_andc_i64, true) TRANS(EOR_r, do_logic_reg, a, tcg_gen_xor_i64, tcg_gen_eqv_i64, false) -/* - * Add/subtract (extended register) - * - * 31|30|29|28 24|23 22|21|20 16|15 13|12 10|9 5|4 0| - * +--+--+--+-----------+-----+--+-------+------+------+----+----+ - * |sf|op| S| 0 1 0 1 1 | opt | 1| Rm |option| imm3 | Rn | Rd | - * +--+--+--+-----------+-----+--+-------+------+------+----+----+ - * - * sf: 0 -> 32bit, 1 -> 64bit - * op: 0 -> add , 1 -> sub - * S: 1 -> set flags - * opt: 00 - * option: extension type (see DecodeRegExtend) - * imm3: optional shift to Rm - * - * Rd = Rn + LSL(extend(Rm), amount) - */ -static void disas_add_sub_ext_reg(DisasContext *s, uint32_t insn) +static bool do_addsub_ext(DisasContext *s, arg_addsub_ext *a, + bool sub_op, bool setflags) { - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int imm3 = extract32(insn, 10, 3); - int option = extract32(insn, 13, 3); - int rm = extract32(insn, 16, 5); - int opt = extract32(insn, 22, 2); - bool setflags = extract32(insn, 29, 1); - bool sub_op = extract32(insn, 30, 1); - bool sf = extract32(insn, 31, 1); + TCGv_i64 tcg_rm, tcg_rn, tcg_rd, tcg_result; - TCGv_i64 tcg_rm, tcg_rn; /* temps */ - TCGv_i64 tcg_rd; - TCGv_i64 tcg_result; - - if (imm3 > 4 || opt != 0) { - unallocated_encoding(s); - return; + if (a->sa > 4) { + return false; } /* non-flag setting ops may use SP */ if (!setflags) { - tcg_rd = cpu_reg_sp(s, rd); + tcg_rd = cpu_reg_sp(s, a->rd); } else { - tcg_rd = cpu_reg(s, rd); + tcg_rd = cpu_reg(s, a->rd); } - tcg_rn = read_cpu_reg_sp(s, rn, sf); + tcg_rn = read_cpu_reg_sp(s, a->rn, a->sf); - tcg_rm = read_cpu_reg(s, rm, sf); - ext_and_shift_reg(tcg_rm, tcg_rm, option, imm3); + tcg_rm = read_cpu_reg(s, a->rm, a->sf); + ext_and_shift_reg(tcg_rm, tcg_rm, a->st, a->sa); tcg_result = tcg_temp_new_i64(); - if (!setflags) { if (sub_op) { tcg_gen_sub_i64(tcg_result, tcg_rn, tcg_rm); @@ -7923,19 +7893,25 @@ static void disas_add_sub_ext_reg(DisasContext *s, uint32_t insn) } } else { if (sub_op) { - gen_sub_CC(sf, tcg_result, tcg_rn, tcg_rm); + gen_sub_CC(a->sf, tcg_result, tcg_rn, tcg_rm); } else { - gen_add_CC(sf, tcg_result, tcg_rn, tcg_rm); + gen_add_CC(a->sf, tcg_result, tcg_rn, tcg_rm); } } - if (sf) { + if (a->sf) { tcg_gen_mov_i64(tcg_rd, tcg_result); } else { tcg_gen_ext32u_i64(tcg_rd, tcg_result); } + return true; } +TRANS(ADD_ext, do_addsub_ext, a, false, false) +TRANS(SUB_ext, do_addsub_ext, a, true, false) +TRANS(ADDS_ext, do_addsub_ext, a, false, true) +TRANS(SUBS_ext, do_addsub_ext, a, true, true) + /* * Add/subtract (shifted register) * @@ -8374,8 +8350,7 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) if (!op1) { if (op2 & 8) { if (op2 & 1) { - /* Add/sub (extended register) */ - disas_add_sub_ext_reg(s, insn); + goto do_unallocated; } else { /* Add/sub (shifted register) */ disas_add_sub_reg(s, insn); From bde86f2868f8d271b5c5f42e13e879ef2df990e9 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:40 -0600 Subject: [PATCH 13/85] target/arm: Convert disas_add_sub_reg to decodetree This includes ADD, SUB, ADDS, SUBS (shifted register). Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 9 +++++ target/arm/tcg/translate-a64.c | 64 ++++++++++------------------------ 2 files changed, 27 insertions(+), 46 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 0539694506..27a3101bc6 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -726,6 +726,15 @@ EOR_r . 10 01010 .. . ..... ...... ..... ..... @logic_shift ANDS_r . 11 01010 .. . ..... ...... ..... ..... @logic_shift # Add/subtract (shifted reg) + +&addsub_shift rd rn rm sf sa st +@addsub_shift sf:1 .. ..... st:2 . rm:5 sa:6 rn:5 rd:5 &addsub_shift + +ADD_r . 00 01011 .. 0 ..... ...... ..... ..... @addsub_shift +SUB_r . 10 01011 .. 0 ..... ...... ..... ..... @addsub_shift +ADDS_r . 01 01011 .. 0 ..... ...... ..... ..... @addsub_shift +SUBS_r . 11 01011 .. 0 ..... ...... ..... ..... @addsub_shift + # Add/subtract (extended reg) &addsub_ext rd rn rm sf sa st diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 8f777875fe..d570bbb696 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -7912,47 +7912,22 @@ TRANS(SUB_ext, do_addsub_ext, a, true, false) TRANS(ADDS_ext, do_addsub_ext, a, false, true) TRANS(SUBS_ext, do_addsub_ext, a, true, true) -/* - * Add/subtract (shifted register) - * - * 31 30 29 28 24 23 22 21 20 16 15 10 9 5 4 0 - * +--+--+--+-----------+-----+--+-------+---------+------+------+ - * |sf|op| S| 0 1 0 1 1 |shift| 0| Rm | imm6 | Rn | Rd | - * +--+--+--+-----------+-----+--+-------+---------+------+------+ - * - * sf: 0 -> 32bit, 1 -> 64bit - * op: 0 -> add , 1 -> sub - * S: 1 -> set flags - * shift: 00 -> LSL, 01 -> LSR, 10 -> ASR, 11 -> RESERVED - * imm6: Shift amount to apply to Rm before the add/sub - */ -static void disas_add_sub_reg(DisasContext *s, uint32_t insn) +static bool do_addsub_reg(DisasContext *s, arg_addsub_shift *a, + bool sub_op, bool setflags) { - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int imm6 = extract32(insn, 10, 6); - int rm = extract32(insn, 16, 5); - int shift_type = extract32(insn, 22, 2); - bool setflags = extract32(insn, 29, 1); - bool sub_op = extract32(insn, 30, 1); - bool sf = extract32(insn, 31, 1); + TCGv_i64 tcg_rd, tcg_rn, tcg_rm, tcg_result; - TCGv_i64 tcg_rd = cpu_reg(s, rd); - TCGv_i64 tcg_rn, tcg_rm; - TCGv_i64 tcg_result; - - if ((shift_type == 3) || (!sf && (imm6 > 31))) { - unallocated_encoding(s); - return; + if (a->st == 3 || (!a->sf && (a->sa & 32))) { + return false; } - tcg_rn = read_cpu_reg(s, rn, sf); - tcg_rm = read_cpu_reg(s, rm, sf); + tcg_rd = cpu_reg(s, a->rd); + tcg_rn = read_cpu_reg(s, a->rn, a->sf); + tcg_rm = read_cpu_reg(s, a->rm, a->sf); - shift_reg_imm(tcg_rm, tcg_rm, sf, shift_type, imm6); + shift_reg_imm(tcg_rm, tcg_rm, a->sf, a->st, a->sa); tcg_result = tcg_temp_new_i64(); - if (!setflags) { if (sub_op) { tcg_gen_sub_i64(tcg_result, tcg_rn, tcg_rm); @@ -7961,19 +7936,25 @@ static void disas_add_sub_reg(DisasContext *s, uint32_t insn) } } else { if (sub_op) { - gen_sub_CC(sf, tcg_result, tcg_rn, tcg_rm); + gen_sub_CC(a->sf, tcg_result, tcg_rn, tcg_rm); } else { - gen_add_CC(sf, tcg_result, tcg_rn, tcg_rm); + gen_add_CC(a->sf, tcg_result, tcg_rn, tcg_rm); } } - if (sf) { + if (a->sf) { tcg_gen_mov_i64(tcg_rd, tcg_result); } else { tcg_gen_ext32u_i64(tcg_rd, tcg_result); } + return true; } +TRANS(ADD_r, do_addsub_reg, a, false, false) +TRANS(SUB_r, do_addsub_reg, a, true, false) +TRANS(ADDS_r, do_addsub_reg, a, false, true) +TRANS(SUBS_r, do_addsub_reg, a, true, true) + /* Data-processing (3 source) * * 31 30 29 28 24 23 21 20 16 15 14 10 9 5 4 0 @@ -8348,15 +8329,6 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) int op3 = extract32(insn, 10, 6); if (!op1) { - if (op2 & 8) { - if (op2 & 1) { - goto do_unallocated; - } else { - /* Add/sub (shifted register) */ - disas_add_sub_reg(s, insn); - } - return; - } goto do_unallocated; } From 4d1c86efb3eb369643966439ec5f3717673e8616 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:41 -0600 Subject: [PATCH 14/85] target/arm: Convert disas_data_proc_3src to decodetree This includes MADD, MSUB, SMADDL, SMSUBL, UMADDL, UMSUBL, SMULH, UMULH. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 16 +++++ target/arm/tcg/translate-a64.c | 119 ++++++++++++--------------------- 2 files changed, 59 insertions(+), 76 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 27a3101bc6..b0cc8bd476 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -753,6 +753,22 @@ SUBS_ext . 11 01011001 ..... ... ... ..... ..... @addsub_ext # Conditional select # Data Processing (3-source) +&rrrr rd rn rm ra +@rrrr . .. ........ rm:5 . ra:5 rn:5 rd:5 &rrrr + +MADD_w 0 00 11011000 ..... 0 ..... ..... ..... @rrrr +MSUB_w 0 00 11011000 ..... 1 ..... ..... ..... @rrrr +MADD_x 1 00 11011000 ..... 0 ..... ..... ..... @rrrr +MSUB_x 1 00 11011000 ..... 1 ..... ..... ..... @rrrr + +SMADDL 1 00 11011001 ..... 0 ..... ..... ..... @rrrr +SMSUBL 1 00 11011001 ..... 1 ..... ..... ..... @rrrr +UMADDL 1 00 11011101 ..... 0 ..... ..... ..... @rrrr +UMSUBL 1 00 11011101 ..... 1 ..... ..... ..... @rrrr + +SMULH 1 00 11011010 ..... 0 11111 ..... ..... @rrr +UMULH 1 00 11011110 ..... 0 11111 ..... ..... @rrr + ### Cryptographic AES AESE 01001110 00 10100 00100 10 ..... ..... @r2r_q1e0 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index d570bbb696..99ff787c61 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -7955,98 +7955,68 @@ TRANS(SUB_r, do_addsub_reg, a, true, false) TRANS(ADDS_r, do_addsub_reg, a, false, true) TRANS(SUBS_r, do_addsub_reg, a, true, true) -/* Data-processing (3 source) - * - * 31 30 29 28 24 23 21 20 16 15 14 10 9 5 4 0 - * +--+------+-----------+------+------+----+------+------+------+ - * |sf| op54 | 1 1 0 1 1 | op31 | Rm | o0 | Ra | Rn | Rd | - * +--+------+-----------+------+------+----+------+------+------+ - */ -static void disas_data_proc_3src(DisasContext *s, uint32_t insn) +static bool do_mulh(DisasContext *s, arg_rrr *a, + void (*fn)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64)) { - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int ra = extract32(insn, 10, 5); - int rm = extract32(insn, 16, 5); - int op_id = (extract32(insn, 29, 3) << 4) | - (extract32(insn, 21, 3) << 1) | - extract32(insn, 15, 1); - bool sf = extract32(insn, 31, 1); - bool is_sub = extract32(op_id, 0, 1); - bool is_high = extract32(op_id, 2, 1); - bool is_signed = false; - TCGv_i64 tcg_op1; - TCGv_i64 tcg_op2; - TCGv_i64 tcg_tmp; + TCGv_i64 discard = tcg_temp_new_i64(); + TCGv_i64 tcg_rd = cpu_reg(s, a->rd); + TCGv_i64 tcg_rn = cpu_reg(s, a->rn); + TCGv_i64 tcg_rm = cpu_reg(s, a->rm); - /* Note that op_id is sf:op54:op31:o0 so it includes the 32/64 size flag */ - switch (op_id) { - case 0x42: /* SMADDL */ - case 0x43: /* SMSUBL */ - case 0x44: /* SMULH */ - is_signed = true; - break; - case 0x0: /* MADD (32bit) */ - case 0x1: /* MSUB (32bit) */ - case 0x40: /* MADD (64bit) */ - case 0x41: /* MSUB (64bit) */ - case 0x4a: /* UMADDL */ - case 0x4b: /* UMSUBL */ - case 0x4c: /* UMULH */ - break; - default: - unallocated_encoding(s); - return; - } + fn(discard, tcg_rd, tcg_rn, tcg_rm); + return true; +} - if (is_high) { - TCGv_i64 low_bits = tcg_temp_new_i64(); /* low bits discarded */ - TCGv_i64 tcg_rd = cpu_reg(s, rd); - TCGv_i64 tcg_rn = cpu_reg(s, rn); - TCGv_i64 tcg_rm = cpu_reg(s, rm); +TRANS(SMULH, do_mulh, a, tcg_gen_muls2_i64) +TRANS(UMULH, do_mulh, a, tcg_gen_mulu2_i64) - if (is_signed) { - tcg_gen_muls2_i64(low_bits, tcg_rd, tcg_rn, tcg_rm); - } else { - tcg_gen_mulu2_i64(low_bits, tcg_rd, tcg_rn, tcg_rm); - } - return; - } +static bool do_muladd(DisasContext *s, arg_rrrr *a, + bool sf, bool is_sub, MemOp mop) +{ + TCGv_i64 tcg_rd = cpu_reg(s, a->rd); + TCGv_i64 tcg_op1, tcg_op2; - tcg_op1 = tcg_temp_new_i64(); - tcg_op2 = tcg_temp_new_i64(); - tcg_tmp = tcg_temp_new_i64(); - - if (op_id < 0x42) { - tcg_gen_mov_i64(tcg_op1, cpu_reg(s, rn)); - tcg_gen_mov_i64(tcg_op2, cpu_reg(s, rm)); + if (mop == MO_64) { + tcg_op1 = cpu_reg(s, a->rn); + tcg_op2 = cpu_reg(s, a->rm); } else { - if (is_signed) { - tcg_gen_ext32s_i64(tcg_op1, cpu_reg(s, rn)); - tcg_gen_ext32s_i64(tcg_op2, cpu_reg(s, rm)); - } else { - tcg_gen_ext32u_i64(tcg_op1, cpu_reg(s, rn)); - tcg_gen_ext32u_i64(tcg_op2, cpu_reg(s, rm)); - } + tcg_op1 = tcg_temp_new_i64(); + tcg_op2 = tcg_temp_new_i64(); + tcg_gen_ext_i64(tcg_op1, cpu_reg(s, a->rn), mop); + tcg_gen_ext_i64(tcg_op2, cpu_reg(s, a->rm), mop); } - if (ra == 31 && !is_sub) { + if (a->ra == 31 && !is_sub) { /* Special-case MADD with rA == XZR; it is the standard MUL alias */ - tcg_gen_mul_i64(cpu_reg(s, rd), tcg_op1, tcg_op2); + tcg_gen_mul_i64(tcg_rd, tcg_op1, tcg_op2); } else { + TCGv_i64 tcg_tmp = tcg_temp_new_i64(); + TCGv_i64 tcg_ra = cpu_reg(s, a->ra); + tcg_gen_mul_i64(tcg_tmp, tcg_op1, tcg_op2); if (is_sub) { - tcg_gen_sub_i64(cpu_reg(s, rd), cpu_reg(s, ra), tcg_tmp); + tcg_gen_sub_i64(tcg_rd, tcg_ra, tcg_tmp); } else { - tcg_gen_add_i64(cpu_reg(s, rd), cpu_reg(s, ra), tcg_tmp); + tcg_gen_add_i64(tcg_rd, tcg_ra, tcg_tmp); } } if (!sf) { - tcg_gen_ext32u_i64(cpu_reg(s, rd), cpu_reg(s, rd)); + tcg_gen_ext32u_i64(tcg_rd, tcg_rd); } + return true; } +TRANS(MADD_w, do_muladd, a, false, false, MO_64) +TRANS(MSUB_w, do_muladd, a, false, true, MO_64) +TRANS(MADD_x, do_muladd, a, true, false, MO_64) +TRANS(MSUB_x, do_muladd, a, true, true, MO_64) + +TRANS(SMADDL, do_muladd, a, true, false, MO_SL) +TRANS(SMSUBL, do_muladd, a, true, true, MO_SL) +TRANS(UMADDL, do_muladd, a, true, false, MO_UL) +TRANS(UMSUBL, do_muladd, a, true, true, MO_UL) + /* Add/subtract (with carry) * 31 30 29 28 27 26 25 24 23 22 21 20 16 15 10 9 5 4 0 * +--+--+--+------------------------+------+-------------+------+-----+ @@ -8364,13 +8334,10 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) disas_cond_select(s, insn); break; - case 0x8 ... 0xf: /* (3 source) */ - disas_data_proc_3src(s, insn); - break; - default: do_unallocated: case 0x6: /* Data-processing */ + case 0x8 ... 0xf: /* (3 source) */ unallocated_encoding(s); break; } From eeb4a519628cb48258d87ab704e8ed78048f81b0 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:42 -0600 Subject: [PATCH 15/85] target/arm: Convert disas_adc_sbc to decodetree This includes ADC, SBC, ADCS, SBCS. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 6 +++++ target/arm/tcg/translate-a64.c | 43 +++++++++++++--------------------- 2 files changed, 22 insertions(+), 27 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index b0cc8bd476..7a40ca455e 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -746,6 +746,12 @@ ADDS_ext . 01 01011001 ..... ... ... ..... ..... @addsub_ext SUBS_ext . 11 01011001 ..... ... ... ..... ..... @addsub_ext # Add/subtract (carry) + +ADC . 00 11010000 ..... 000000 ..... ..... @rrr_sf +ADCS . 01 11010000 ..... 000000 ..... ..... @rrr_sf +SBC . 10 11010000 ..... 000000 ..... ..... @rrr_sf +SBCS . 11 11010000 ..... 000000 ..... ..... @rrr_sf + # Rotate right into flags # Evaluate into flags # Conditional compare (regster) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 99ff787c61..d7747fcf57 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8017,42 +8017,34 @@ TRANS(SMSUBL, do_muladd, a, true, true, MO_SL) TRANS(UMADDL, do_muladd, a, true, false, MO_UL) TRANS(UMSUBL, do_muladd, a, true, true, MO_UL) -/* Add/subtract (with carry) - * 31 30 29 28 27 26 25 24 23 22 21 20 16 15 10 9 5 4 0 - * +--+--+--+------------------------+------+-------------+------+-----+ - * |sf|op| S| 1 1 0 1 0 0 0 0 | rm | 0 0 0 0 0 0 | Rn | Rd | - * +--+--+--+------------------------+------+-------------+------+-----+ - */ - -static void disas_adc_sbc(DisasContext *s, uint32_t insn) +static bool do_adc_sbc(DisasContext *s, arg_rrr_sf *a, + bool is_sub, bool setflags) { - unsigned int sf, op, setflags, rm, rn, rd; TCGv_i64 tcg_y, tcg_rn, tcg_rd; - sf = extract32(insn, 31, 1); - op = extract32(insn, 30, 1); - setflags = extract32(insn, 29, 1); - rm = extract32(insn, 16, 5); - rn = extract32(insn, 5, 5); - rd = extract32(insn, 0, 5); + tcg_rd = cpu_reg(s, a->rd); + tcg_rn = cpu_reg(s, a->rn); - tcg_rd = cpu_reg(s, rd); - tcg_rn = cpu_reg(s, rn); - - if (op) { + if (is_sub) { tcg_y = tcg_temp_new_i64(); - tcg_gen_not_i64(tcg_y, cpu_reg(s, rm)); + tcg_gen_not_i64(tcg_y, cpu_reg(s, a->rm)); } else { - tcg_y = cpu_reg(s, rm); + tcg_y = cpu_reg(s, a->rm); } if (setflags) { - gen_adc_CC(sf, tcg_rd, tcg_rn, tcg_y); + gen_adc_CC(a->sf, tcg_rd, tcg_rn, tcg_y); } else { - gen_adc(sf, tcg_rd, tcg_rn, tcg_y); + gen_adc(a->sf, tcg_rd, tcg_rn, tcg_y); } + return true; } +TRANS(ADC, do_adc_sbc, a, false, false) +TRANS(SBC, do_adc_sbc, a, true, false) +TRANS(ADCS, do_adc_sbc, a, false, true) +TRANS(SBCS, do_adc_sbc, a, true, true) + /* * Rotate right into flags * 31 30 29 21 15 10 5 4 0 @@ -8305,10 +8297,6 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) switch (op2) { case 0x0: switch (op3) { - case 0x00: /* Add/subtract (with carry) */ - disas_adc_sbc(s, insn); - break; - case 0x01: /* Rotate right into flags */ case 0x21: disas_rotate_right_into_flags(s, insn); @@ -8322,6 +8310,7 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) break; default: + case 0x00: /* Add/subtract (with carry) */ goto do_unallocated; } break; From 9fa4829be6f93468a73e7bd7399ad1ea332da0eb Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:43 -0600 Subject: [PATCH 16/85] target/arm: Convert RMIF to decodetree MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 3 +++ target/arm/tcg/translate-a64.c | 32 +++++++++----------------------- 2 files changed, 12 insertions(+), 23 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 7a40ca455e..454494742e 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -753,6 +753,9 @@ SBC . 10 11010000 ..... 000000 ..... ..... @rrr_sf SBCS . 11 11010000 ..... 000000 ..... ..... @rrr_sf # Rotate right into flags + +RMIF 1 01 11010000 imm:6 00001 rn:5 0 mask:4 + # Evaluate into flags # Conditional compare (regster) # Conditional compare (immediate) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index d7747fcf57..1af41e22eb 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8045,30 +8045,18 @@ TRANS(SBC, do_adc_sbc, a, true, false) TRANS(ADCS, do_adc_sbc, a, false, true) TRANS(SBCS, do_adc_sbc, a, true, true) -/* - * Rotate right into flags - * 31 30 29 21 15 10 5 4 0 - * +--+--+--+-----------------+--------+-----------+------+--+------+ - * |sf|op| S| 1 1 0 1 0 0 0 0 | imm6 | 0 0 0 0 1 | Rn |o2| mask | - * +--+--+--+-----------------+--------+-----------+------+--+------+ - */ -static void disas_rotate_right_into_flags(DisasContext *s, uint32_t insn) +static bool trans_RMIF(DisasContext *s, arg_RMIF *a) { - int mask = extract32(insn, 0, 4); - int o2 = extract32(insn, 4, 1); - int rn = extract32(insn, 5, 5); - int imm6 = extract32(insn, 15, 6); - int sf_op_s = extract32(insn, 29, 3); + int mask = a->mask; TCGv_i64 tcg_rn; TCGv_i32 nzcv; - if (sf_op_s != 5 || o2 != 0 || !dc_isar_feature(aa64_condm_4, s)) { - unallocated_encoding(s); - return; + if (!dc_isar_feature(aa64_condm_4, s)) { + return false; } - tcg_rn = read_cpu_reg(s, rn, 1); - tcg_gen_rotri_i64(tcg_rn, tcg_rn, imm6); + tcg_rn = read_cpu_reg(s, a->rn, 1); + tcg_gen_rotri_i64(tcg_rn, tcg_rn, a->imm); nzcv = tcg_temp_new_i32(); tcg_gen_extrl_i64_i32(nzcv, tcg_rn); @@ -8086,6 +8074,7 @@ static void disas_rotate_right_into_flags(DisasContext *s, uint32_t insn) if (mask & 1) { /* V */ tcg_gen_shli_i32(cpu_VF, nzcv, 31 - 0); } + return true; } /* @@ -8297,11 +8286,6 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) switch (op2) { case 0x0: switch (op3) { - case 0x01: /* Rotate right into flags */ - case 0x21: - disas_rotate_right_into_flags(s, insn); - break; - case 0x02: /* Evaluate into flags */ case 0x12: case 0x22: @@ -8311,6 +8295,8 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) default: case 0x00: /* Add/subtract (with carry) */ + case 0x01: /* Rotate right into flags */ + case 0x21: goto do_unallocated; } break; From 729bca958d906350f994e87b9f9b68cc0d945d59 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:44 -0600 Subject: [PATCH 17/85] target/arm: Convert SETF8, SETF16 to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 4 +++ target/arm/tcg/translate-a64.c | 48 +++++----------------------------- 2 files changed, 11 insertions(+), 41 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 454494742e..ae2c6831d7 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -757,6 +757,10 @@ SBCS . 11 11010000 ..... 000000 ..... ..... @rrr_sf RMIF 1 01 11010000 imm:6 00001 rn:5 0 mask:4 # Evaluate into flags + +SETF8 0 01 11010000 00000 000010 rn:5 01101 +SETF16 0 01 11010000 00000 010010 rn:5 01101 + # Conditional compare (regster) # Conditional compare (immediate) # Conditional select diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 1af41e22eb..774689641d 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8077,38 +8077,21 @@ static bool trans_RMIF(DisasContext *s, arg_RMIF *a) return true; } -/* - * Evaluate into flags - * 31 30 29 21 15 14 10 5 4 0 - * +--+--+--+-----------------+---------+----+---------+------+--+------+ - * |sf|op| S| 1 1 0 1 0 0 0 0 | opcode2 | sz | 0 0 1 0 | Rn |o3| mask | - * +--+--+--+-----------------+---------+----+---------+------+--+------+ - */ -static void disas_evaluate_into_flags(DisasContext *s, uint32_t insn) +static bool do_setf(DisasContext *s, int rn, int shift) { - int o3_mask = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int o2 = extract32(insn, 15, 6); - int sz = extract32(insn, 14, 1); - int sf_op_s = extract32(insn, 29, 3); - TCGv_i32 tmp; - int shift; + TCGv_i32 tmp = tcg_temp_new_i32(); - if (sf_op_s != 1 || o2 != 0 || o3_mask != 0xd || - !dc_isar_feature(aa64_condm_4, s)) { - unallocated_encoding(s); - return; - } - shift = sz ? 16 : 24; /* SETF16 or SETF8 */ - - tmp = tcg_temp_new_i32(); tcg_gen_extrl_i64_i32(tmp, cpu_reg(s, rn)); tcg_gen_shli_i32(cpu_NF, tmp, shift); tcg_gen_shli_i32(cpu_VF, tmp, shift - 1); tcg_gen_mov_i32(cpu_ZF, cpu_NF); tcg_gen_xor_i32(cpu_VF, cpu_VF, cpu_NF); + return true; } +TRANS_FEAT(SETF8, aa64_condm_4, do_setf, a->rn, 24) +TRANS_FEAT(SETF16, aa64_condm_4, do_setf, a->rn, 16) + /* Conditional compare (immediate / register) * 31 30 29 28 27 26 25 24 23 22 21 20 16 15 12 11 10 9 5 4 3 0 * +--+--+--+------------------------+--------+------+----+--+------+--+-----+ @@ -8277,30 +8260,12 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) { int op1 = extract32(insn, 28, 1); int op2 = extract32(insn, 21, 4); - int op3 = extract32(insn, 10, 6); if (!op1) { goto do_unallocated; } switch (op2) { - case 0x0: - switch (op3) { - case 0x02: /* Evaluate into flags */ - case 0x12: - case 0x22: - case 0x32: - disas_evaluate_into_flags(s, insn); - break; - - default: - case 0x00: /* Add/subtract (with carry) */ - case 0x01: /* Rotate right into flags */ - case 0x21: - goto do_unallocated; - } - break; - case 0x2: /* Conditional compare */ disas_cc(s, insn); /* both imm and reg forms */ break; @@ -8311,6 +8276,7 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) default: do_unallocated: + case 0x0: case 0x6: /* Data-processing */ case 0x8 ... 0xf: /* (3 source) */ unallocated_encoding(s); From 916ad3f733a54e2dc424c4b210beea552bbeedd1 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:45 -0600 Subject: [PATCH 18/85] target/arm: Convert CCMP, CCMN to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 6 ++-- target/arm/tcg/translate-a64.c | 66 +++++++++++----------------------- 2 files changed, 25 insertions(+), 47 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index ae2c6831d7..a9d7d57199 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -761,8 +761,10 @@ RMIF 1 01 11010000 imm:6 00001 rn:5 0 mask:4 SETF8 0 01 11010000 00000 000010 rn:5 01101 SETF16 0 01 11010000 00000 010010 rn:5 01101 -# Conditional compare (regster) -# Conditional compare (immediate) +# Conditional compare + +CCMP sf:1 op:1 1 11010010 y:5 cond:4 imm:1 0 rn:5 0 nzcv:4 + # Conditional select # Data Processing (3-source) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 774689641d..56a445a3c2 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8092,68 +8092,46 @@ static bool do_setf(DisasContext *s, int rn, int shift) TRANS_FEAT(SETF8, aa64_condm_4, do_setf, a->rn, 24) TRANS_FEAT(SETF16, aa64_condm_4, do_setf, a->rn, 16) -/* Conditional compare (immediate / register) - * 31 30 29 28 27 26 25 24 23 22 21 20 16 15 12 11 10 9 5 4 3 0 - * +--+--+--+------------------------+--------+------+----+--+------+--+-----+ - * |sf|op| S| 1 1 0 1 0 0 1 0 |imm5/rm | cond |i/r |o2| Rn |o3|nzcv | - * +--+--+--+------------------------+--------+------+----+--+------+--+-----+ - * [1] y [0] [0] - */ -static void disas_cc(DisasContext *s, uint32_t insn) +/* CCMP, CCMN */ +static bool trans_CCMP(DisasContext *s, arg_CCMP *a) { - unsigned int sf, op, y, cond, rn, nzcv, is_imm; - TCGv_i32 tcg_t0, tcg_t1, tcg_t2; - TCGv_i64 tcg_tmp, tcg_y, tcg_rn; + TCGv_i32 tcg_t0 = tcg_temp_new_i32(); + TCGv_i32 tcg_t1 = tcg_temp_new_i32(); + TCGv_i32 tcg_t2 = tcg_temp_new_i32(); + TCGv_i64 tcg_tmp = tcg_temp_new_i64(); + TCGv_i64 tcg_rn, tcg_y; DisasCompare c; - - if (!extract32(insn, 29, 1)) { - unallocated_encoding(s); - return; - } - if (insn & (1 << 10 | 1 << 4)) { - unallocated_encoding(s); - return; - } - sf = extract32(insn, 31, 1); - op = extract32(insn, 30, 1); - is_imm = extract32(insn, 11, 1); - y = extract32(insn, 16, 5); /* y = rm (reg) or imm5 (imm) */ - cond = extract32(insn, 12, 4); - rn = extract32(insn, 5, 5); - nzcv = extract32(insn, 0, 4); + unsigned nzcv; /* Set T0 = !COND. */ - tcg_t0 = tcg_temp_new_i32(); - arm_test_cc(&c, cond); + arm_test_cc(&c, a->cond); tcg_gen_setcondi_i32(tcg_invert_cond(c.cond), tcg_t0, c.value, 0); /* Load the arguments for the new comparison. */ - if (is_imm) { - tcg_y = tcg_temp_new_i64(); - tcg_gen_movi_i64(tcg_y, y); + if (a->imm) { + tcg_y = tcg_constant_i64(a->y); } else { - tcg_y = cpu_reg(s, y); + tcg_y = cpu_reg(s, a->y); } - tcg_rn = cpu_reg(s, rn); + tcg_rn = cpu_reg(s, a->rn); /* Set the flags for the new comparison. */ - tcg_tmp = tcg_temp_new_i64(); - if (op) { - gen_sub_CC(sf, tcg_tmp, tcg_rn, tcg_y); + if (a->op) { + gen_sub_CC(a->sf, tcg_tmp, tcg_rn, tcg_y); } else { - gen_add_CC(sf, tcg_tmp, tcg_rn, tcg_y); + gen_add_CC(a->sf, tcg_tmp, tcg_rn, tcg_y); } - /* If COND was false, force the flags to #nzcv. Compute two masks + /* + * If COND was false, force the flags to #nzcv. Compute two masks * to help with this: T1 = (COND ? 0 : -1), T2 = (COND ? -1 : 0). * For tcg hosts that support ANDC, we can make do with just T1. * In either case, allow the tcg optimizer to delete any unused mask. */ - tcg_t1 = tcg_temp_new_i32(); - tcg_t2 = tcg_temp_new_i32(); tcg_gen_neg_i32(tcg_t1, tcg_t0); tcg_gen_subi_i32(tcg_t2, tcg_t0, 1); + nzcv = a->nzcv; if (nzcv & 8) { /* N */ tcg_gen_or_i32(cpu_NF, cpu_NF, tcg_t1); } else { @@ -8190,6 +8168,7 @@ static void disas_cc(DisasContext *s, uint32_t insn) tcg_gen_and_i32(cpu_VF, cpu_VF, tcg_t2); } } + return true; } /* Conditional select @@ -8266,10 +8245,6 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) } switch (op2) { - case 0x2: /* Conditional compare */ - disas_cc(s, insn); /* both imm and reg forms */ - break; - case 0x4: /* Conditional select */ disas_cond_select(s, insn); break; @@ -8277,6 +8252,7 @@ static void disas_data_proc_reg(DisasContext *s, uint32_t insn) default: do_unallocated: case 0x0: + case 0x2: /* Conditional compare */ case 0x6: /* Data-processing */ case 0x8 ... 0xf: /* (3 source) */ unallocated_encoding(s); From 32f06615732bba12ef32d52b6dd292e57b83dfc6 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:46 -0600 Subject: [PATCH 19/85] target/arm: Convert disas_cond_select to decodetree This includes CSEL, CSINC, CSINV, CSNEG. Remove disas_data_proc_reg, as these were the last insns decoded by that function. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-20-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 3 ++ target/arm/tcg/translate-a64.c | 84 ++++++---------------------------- 2 files changed, 17 insertions(+), 70 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index a9d7d57199..5670846768 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -766,6 +766,9 @@ SETF16 0 01 11010000 00000 010010 rn:5 01101 CCMP sf:1 op:1 1 11010010 y:5 cond:4 imm:1 0 rn:5 0 nzcv:4 # Conditional select + +CSEL sf:1 else_inv:1 011010100 rm:5 cond:4 0 else_inc:1 rn:5 rd:5 + # Data Processing (3-source) &rrrr rd rn rm ra diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 56a445a3c2..9c6365f5ef 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8171,39 +8171,17 @@ static bool trans_CCMP(DisasContext *s, arg_CCMP *a) return true; } -/* Conditional select - * 31 30 29 28 21 20 16 15 12 11 10 9 5 4 0 - * +----+----+---+-----------------+------+------+-----+------+------+ - * | sf | op | S | 1 1 0 1 0 1 0 0 | Rm | cond | op2 | Rn | Rd | - * +----+----+---+-----------------+------+------+-----+------+------+ - */ -static void disas_cond_select(DisasContext *s, uint32_t insn) +static bool trans_CSEL(DisasContext *s, arg_CSEL *a) { - unsigned int sf, else_inv, rm, cond, else_inc, rn, rd; - TCGv_i64 tcg_rd, zero; + TCGv_i64 tcg_rd = cpu_reg(s, a->rd); + TCGv_i64 zero = tcg_constant_i64(0); DisasCompare64 c; - if (extract32(insn, 29, 1) || extract32(insn, 11, 1)) { - /* S == 1 or op2<1> == 1 */ - unallocated_encoding(s); - return; - } - sf = extract32(insn, 31, 1); - else_inv = extract32(insn, 30, 1); - rm = extract32(insn, 16, 5); - cond = extract32(insn, 12, 4); - else_inc = extract32(insn, 10, 1); - rn = extract32(insn, 5, 5); - rd = extract32(insn, 0, 5); + a64_test_cc(&c, a->cond); - tcg_rd = cpu_reg(s, rd); - - a64_test_cc(&c, cond); - zero = tcg_constant_i64(0); - - if (rn == 31 && rm == 31 && (else_inc ^ else_inv)) { + if (a->rn == 31 && a->rm == 31 && (a->else_inc ^ a->else_inv)) { /* CSET & CSETM. */ - if (else_inv) { + if (a->else_inv) { tcg_gen_negsetcond_i64(tcg_invert_cond(c.cond), tcg_rd, c.value, zero); } else { @@ -8211,53 +8189,23 @@ static void disas_cond_select(DisasContext *s, uint32_t insn) tcg_rd, c.value, zero); } } else { - TCGv_i64 t_true = cpu_reg(s, rn); - TCGv_i64 t_false = read_cpu_reg(s, rm, 1); - if (else_inv && else_inc) { + TCGv_i64 t_true = cpu_reg(s, a->rn); + TCGv_i64 t_false = read_cpu_reg(s, a->rm, 1); + + if (a->else_inv && a->else_inc) { tcg_gen_neg_i64(t_false, t_false); - } else if (else_inv) { + } else if (a->else_inv) { tcg_gen_not_i64(t_false, t_false); - } else if (else_inc) { + } else if (a->else_inc) { tcg_gen_addi_i64(t_false, t_false, 1); } tcg_gen_movcond_i64(c.cond, tcg_rd, c.value, zero, t_true, t_false); } - if (!sf) { + if (!a->sf) { tcg_gen_ext32u_i64(tcg_rd, tcg_rd); } -} - -/* - * Data processing - register - * 31 30 29 28 25 21 20 16 10 0 - * +--+---+--+---+-------+-----+-------+-------+---------+ - * | |op0| |op1| 1 0 1 | op2 | | op3 | | - * +--+---+--+---+-------+-----+-------+-------+---------+ - */ -static void disas_data_proc_reg(DisasContext *s, uint32_t insn) -{ - int op1 = extract32(insn, 28, 1); - int op2 = extract32(insn, 21, 4); - - if (!op1) { - goto do_unallocated; - } - - switch (op2) { - case 0x4: /* Conditional select */ - disas_cond_select(s, insn); - break; - - default: - do_unallocated: - case 0x0: - case 0x2: /* Conditional compare */ - case 0x6: /* Data-processing */ - case 0x8 ... 0xf: /* (3 source) */ - unallocated_encoding(s); - break; - } + return true; } static void handle_fp_compare(DisasContext *s, int size, @@ -11212,10 +11160,6 @@ static bool btype_destination_ok(uint32_t insn, bool bt, int btype) static void disas_a64_legacy(DisasContext *s, uint32_t insn) { switch (extract32(insn, 25, 4)) { - case 0x5: - case 0xd: /* Data processing - register */ - disas_data_proc_reg(s, insn); - break; case 0x7: case 0xf: /* Data processing - SIMD and floating point */ disas_data_proc_simd_fp(s, insn); From 648e654efa05e21779daf0b1f623948c92c83fe0 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:47 -0600 Subject: [PATCH 20/85] target/arm: Introduce fp_access_check_scalar_hsd Provide a simple way to check for float64, float32, and float16 support, as well as the fpu enabled. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-21-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/translate-a64.c | 62 ++++++++++++++++++---------------- 1 file changed, 32 insertions(+), 30 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 9c6365f5ef..4e47b8a804 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -1239,6 +1239,27 @@ static bool fp_access_check(DisasContext *s) return true; } +/* + * Return <0 for non-supported element sizes, with MO_16 controlled by + * FEAT_FP16; return 0 for fp disabled; otherwise return >0 for success. + */ +static int fp_access_check_scalar_hsd(DisasContext *s, MemOp esz) +{ + switch (esz) { + case MO_64: + case MO_32: + break; + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return -1; + } + break; + default: + return -1; + } + return fp_access_check(s); +} + /* * Check that SVE access is enabled. If it is, return true. * If not, emit code to generate an appropriate exception and return false. @@ -6628,22 +6649,10 @@ static bool trans_FCSEL(DisasContext *s, arg_FCSEL *a) { TCGv_i64 t_true, t_false; DisasCompare64 c; + int check = fp_access_check_scalar_hsd(s, a->esz); - switch (a->esz) { - case MO_32: - case MO_64: - break; - case MO_16: - if (!dc_isar_feature(aa64_fp16, s)) { - return false; - } - break; - default: - return false; - } - - if (!fp_access_check(s)) { - return true; + if (check <= 0) { + return check == 0; } /* Zero extend sreg & hreg inputs to 64 bits now. */ @@ -6894,22 +6903,15 @@ TRANS(FMINV_s, do_fp_reduction, a, gen_helper_vfp_mins) static bool trans_FMOVI_s(DisasContext *s, arg_FMOVI_s *a) { - switch (a->esz) { - case MO_32: - case MO_64: - break; - case MO_16: - if (!dc_isar_feature(aa64_fp16, s)) { - return false; - } - break; - default: - return false; - } - if (fp_access_check(s)) { - uint64_t imm = vfp_expand_imm(a->esz, a->imm); - write_fp_dreg(s, a->rd, tcg_constant_i64(imm)); + int check = fp_access_check_scalar_hsd(s, a->esz); + uint64_t imm; + + if (check <= 0) { + return check == 0; } + + imm = vfp_expand_imm(a->esz, a->imm); + write_fp_dreg(s, a->rd, tcg_constant_i64(imm)); return true; } From 43218f234692bc4893b082a016885ae650aea8fd Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:48 -0600 Subject: [PATCH 21/85] target/arm: Introduce fp_access_check_vector_hsd Provide a simple way to check for float64, float32, and float16 support vs vector width, as well as the fpu enabled. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-22-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/translate-a64.c | 135 +++++++++++++-------------------- 1 file changed, 54 insertions(+), 81 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 4e47b8a804..4611ae4ade 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -1260,6 +1260,28 @@ static int fp_access_check_scalar_hsd(DisasContext *s, MemOp esz) return fp_access_check(s); } +/* Likewise, but vector MO_64 must have two elements. */ +static int fp_access_check_vector_hsd(DisasContext *s, bool is_q, MemOp esz) +{ + switch (esz) { + case MO_64: + if (!is_q) { + return -1; + } + break; + case MO_32: + break; + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return -1; + } + break; + default: + return -1; + } + return fp_access_check(s); +} + /* * Check that SVE access is enabled. If it is, return true. * If not, emit code to generate an appropriate exception and return false. @@ -5420,27 +5442,14 @@ static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, int data, gen_helper_gvec_3_ptr * const fns[3]) { MemOp esz = a->esz; + int check = fp_access_check_vector_hsd(s, a->q, esz); - switch (esz) { - case MO_64: - if (!a->q) { - return false; - } - break; - case MO_32: - break; - case MO_16: - if (!dc_isar_feature(aa64_fp16, s)) { - return false; - } - break; - default: - return false; - } - if (fp_access_check(s)) { - gen_gvec_op3_fpst(s, a->q, a->rd, a->rn, a->rm, - esz == MO_16, data, fns[esz - 1]); + if (check <= 0) { + return check == 0; } + + gen_gvec_op3_fpst(s, a->q, a->rd, a->rn, a->rm, + esz == MO_16, data, fns[esz - 1]); return true; } @@ -5768,34 +5777,24 @@ TRANS_FEAT(FCADD_270, aa64_fcma, do_fp3_vector, a, 1, f_vector_fcadd) static bool trans_FCMLA_v(DisasContext *s, arg_FCMLA_v *a) { - gen_helper_gvec_4_ptr *fn; + static gen_helper_gvec_4_ptr * const fn[] = { + [MO_16] = gen_helper_gvec_fcmlah, + [MO_32] = gen_helper_gvec_fcmlas, + [MO_64] = gen_helper_gvec_fcmlad, + }; + int check; if (!dc_isar_feature(aa64_fcma, s)) { return false; } - switch (a->esz) { - case MO_64: - if (!a->q) { - return false; - } - fn = gen_helper_gvec_fcmlad; - break; - case MO_32: - fn = gen_helper_gvec_fcmlas; - break; - case MO_16: - if (!dc_isar_feature(aa64_fp16, s)) { - return false; - } - fn = gen_helper_gvec_fcmlah; - break; - default: - return false; - } - if (fp_access_check(s)) { - gen_gvec_op4_fpst(s, a->q, a->rd, a->rn, a->rm, a->rd, - a->esz == MO_16, a->rot, fn); + + check = fp_access_check_vector_hsd(s, a->q, a->esz); + if (check <= 0) { + return check == 0; } + + gen_gvec_op4_fpst(s, a->q, a->rd, a->rn, a->rm, a->rd, + a->esz == MO_16, a->rot, fn[a->esz]); return true; } @@ -6337,27 +6336,14 @@ static bool do_fp3_vector_idx(DisasContext *s, arg_qrrx_e *a, gen_helper_gvec_3_ptr * const fns[3]) { MemOp esz = a->esz; + int check = fp_access_check_vector_hsd(s, a->q, esz); - switch (esz) { - case MO_64: - if (!a->q) { - return false; - } - break; - case MO_32: - break; - case MO_16: - if (!dc_isar_feature(aa64_fp16, s)) { - return false; - } - break; - default: - g_assert_not_reached(); - } - if (fp_access_check(s)) { - gen_gvec_op3_fpst(s, a->q, a->rd, a->rn, a->rm, - esz == MO_16, a->idx, fns[esz - 1]); + if (check <= 0) { + return check == 0; } + + gen_gvec_op3_fpst(s, a->q, a->rd, a->rn, a->rm, + esz == MO_16, a->idx, fns[esz - 1]); return true; } @@ -6383,28 +6369,15 @@ static bool do_fmla_vector_idx(DisasContext *s, arg_qrrx_e *a, bool neg) gen_helper_gvec_fmla_idx_d, }; MemOp esz = a->esz; + int check = fp_access_check_vector_hsd(s, a->q, esz); - switch (esz) { - case MO_64: - if (!a->q) { - return false; - } - break; - case MO_32: - break; - case MO_16: - if (!dc_isar_feature(aa64_fp16, s)) { - return false; - } - break; - default: - g_assert_not_reached(); - } - if (fp_access_check(s)) { - gen_gvec_op4_fpst(s, a->q, a->rd, a->rn, a->rm, a->rd, - esz == MO_16, (a->idx << 1) | neg, - fns[esz - 1]); + if (check <= 0) { + return check == 0; } + + gen_gvec_op4_fpst(s, a->q, a->rd, a->rn, a->rm, a->rd, + esz == MO_16, (a->idx << 1) | neg, + fns[esz - 1]); return true; } From cc0db9dea0e02373a7440ec6d19a00b0f70bbc9e Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:49 -0600 Subject: [PATCH 22/85] target/arm: Convert FCMP, FCMPE, FCCMP, FCCMPE to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-23-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 8 + target/arm/tcg/translate-a64.c | 283 ++++++++++++--------------------- 2 files changed, 112 insertions(+), 179 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 5670846768..7868b1cb24 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1325,6 +1325,14 @@ FMINV_s 0110 1110 10 11000 01111 10 ..... ..... @rr_q1e2 FMOVI_s 0001 1110 .. 1 imm:8 100 00000 rd:5 esz=%esz_hsd +# Floating-point Compare + +FCMP 00011110 .. 1 rm:5 001000 rn:5 e:1 z:1 000 esz=%esz_hsd + +# Floating-point Conditional Compare + +FCCMP 00011110 .. 1 rm:5 cond:4 01 rn:5 e:1 nzcv:4 esz=%esz_hsd + # Advanced SIMD Modified Immediate / Shift by Immediate %abcdefgh 16:3 5:5 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 4611ae4ade..a99f3d0d13 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -6888,6 +6888,106 @@ static bool trans_FMOVI_s(DisasContext *s, arg_FMOVI_s *a) return true; } +/* + * Floating point compare, conditional compare + */ + +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 = fpstatus_ptr(size == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + + if (size == MO_64) { + TCGv_i64 tcg_vn, tcg_vm; + + tcg_vn = read_fp_dreg(s, rn); + if (cmp_with_zero) { + tcg_vm = tcg_constant_i64(0); + } else { + tcg_vm = read_fp_dreg(s, rm); + } + if (signal_all_nans) { + gen_helper_vfp_cmped_a64(tcg_flags, tcg_vn, tcg_vm, fpst); + } else { + gen_helper_vfp_cmpd_a64(tcg_flags, tcg_vn, tcg_vm, fpst); + } + } else { + TCGv_i32 tcg_vn = tcg_temp_new_i32(); + TCGv_i32 tcg_vm = tcg_temp_new_i32(); + + read_vec_element_i32(s, tcg_vn, rn, 0, size); + if (cmp_with_zero) { + tcg_gen_movi_i32(tcg_vm, 0); + } else { + read_vec_element_i32(s, tcg_vm, rm, 0, size); + } + + 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(); + } + } + + gen_set_nzcv(tcg_flags); +} + +/* FCMP, FCMPE */ +static bool trans_FCMP(DisasContext *s, arg_FCMP *a) +{ + int check = fp_access_check_scalar_hsd(s, a->esz); + + if (check <= 0) { + return check == 0; + } + + handle_fp_compare(s, a->esz, a->rn, a->rm, a->z, a->e); + return true; +} + +/* FCCMP, FCCMPE */ +static bool trans_FCCMP(DisasContext *s, arg_FCCMP *a) +{ + TCGLabel *label_continue = NULL; + int check = fp_access_check_scalar_hsd(s, a->esz); + + if (check <= 0) { + return check == 0; + } + + if (a->cond < 0x0e) { /* not always */ + TCGLabel *label_match = gen_new_label(); + label_continue = gen_new_label(); + arm_gen_test_cc(a->cond, label_match); + /* nomatch: */ + gen_set_nzcv(tcg_constant_i64(a->nzcv << 28)); + tcg_gen_br(label_continue); + gen_set_label(label_match); + } + + handle_fp_compare(s, a->esz, a->rn, a->rm, false, a->e); + + if (label_continue) { + gen_set_label(label_continue); + } + return true; +} + /* * Advanced SIMD Modified Immediate */ @@ -8183,174 +8283,6 @@ static bool trans_CSEL(DisasContext *s, arg_CSEL *a) return true; } -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 = fpstatus_ptr(size == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); - - if (size == MO_64) { - TCGv_i64 tcg_vn, tcg_vm; - - tcg_vn = read_fp_dreg(s, rn); - if (cmp_with_zero) { - tcg_vm = tcg_constant_i64(0); - } else { - tcg_vm = read_fp_dreg(s, rm); - } - if (signal_all_nans) { - gen_helper_vfp_cmped_a64(tcg_flags, tcg_vn, tcg_vm, fpst); - } else { - gen_helper_vfp_cmpd_a64(tcg_flags, tcg_vn, tcg_vm, fpst); - } - } else { - TCGv_i32 tcg_vn = tcg_temp_new_i32(); - TCGv_i32 tcg_vm = tcg_temp_new_i32(); - - read_vec_element_i32(s, tcg_vn, rn, 0, size); - if (cmp_with_zero) { - tcg_gen_movi_i32(tcg_vm, 0); - } else { - read_vec_element_i32(s, tcg_vm, rm, 0, size); - } - - 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(); - } - } - - gen_set_nzcv(tcg_flags); -} - -/* Floating point compare - * 31 30 29 28 24 23 22 21 20 16 15 14 13 10 9 5 4 0 - * +---+---+---+-----------+------+---+------+-----+---------+------+-------+ - * | M | 0 | S | 1 1 1 1 0 | type | 1 | Rm | op | 1 0 0 0 | Rn | op2 | - * +---+---+---+-----------+------+---+------+-----+---------+------+-------+ - */ -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); - 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) { - unallocated_encoding(s); - return; - } - - switch (type) { - case 0: - size = MO_32; - break; - case 1: - size = MO_64; - break; - case 3: - size = MO_16; - if (dc_isar_feature(aa64_fp16, s)) { - break; - } - /* fallthru */ - default: - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - handle_fp_compare(s, size, rn, rm, opc & 1, opc & 2); -} - -/* Floating point conditional compare - * 31 30 29 28 24 23 22 21 20 16 15 12 11 10 9 5 4 3 0 - * +---+---+---+-----------+------+---+------+------+-----+------+----+------+ - * | M | 0 | S | 1 1 1 1 0 | type | 1 | Rm | cond | 0 1 | Rn | op | nzcv | - * +---+---+---+-----------+------+---+------+------+-----+------+----+------+ - */ -static void disas_fp_ccomp(DisasContext *s, uint32_t insn) -{ - unsigned int mos, type, rm, cond, rn, op, nzcv; - TCGLabel *label_continue = NULL; - int size; - - mos = extract32(insn, 29, 3); - 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) { - unallocated_encoding(s); - return; - } - - switch (type) { - case 0: - size = MO_32; - break; - case 1: - size = MO_64; - break; - case 3: - size = MO_16; - if (dc_isar_feature(aa64_fp16, s)) { - break; - } - /* fallthru */ - default: - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - if (cond < 0x0e) { /* not always */ - TCGLabel *label_match = gen_new_label(); - label_continue = gen_new_label(); - arm_gen_test_cc(cond, label_match); - /* nomatch: */ - gen_set_nzcv(tcg_constant_i64(nzcv << 28)); - tcg_gen_br(label_continue); - gen_set_label(label_match); - } - - handle_fp_compare(s, size, rn, rm, false, op); - - if (cond < 0x0e) { - gen_set_label(label_continue); - } -} - /* Floating-point data-processing (1 source) - half precision */ static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) { @@ -9107,16 +9039,9 @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn) disas_fp_fixed_conv(s, insn); } else { switch (extract32(insn, 10, 2)) { - case 1: - /* Floating point conditional compare */ - disas_fp_ccomp(s, insn); - break; - case 2: - /* Floating point data-processing (2 source) */ - unallocated_encoding(s); /* in decodetree */ - break; - case 3: - /* Floating point conditional select */ + case 1: /* Floating point conditional compare */ + case 2: /* Floating point data-processing (2 source) */ + case 3: /* Floating point conditional select */ unallocated_encoding(s); /* in decodetree */ break; case 0: @@ -9127,7 +9052,7 @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn) break; case 1: /* [15:12] == xx10 */ /* Floating point compare */ - disas_fp_compare(s, insn); + unallocated_encoding(s); /* in decodetree */ break; case 2: /* [15:12] == x100 */ /* Floating point data-processing (1 source) */ From 7261f2a7a75ab9be4aa3f8a7896f21a39df74006 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:50 -0600 Subject: [PATCH 23/85] target/arm: Fix decode of fp16 vector fabs, fneg, fsqrt These opcodes are only supported as vector operations, not as advsimd scalar. Set only_in_vector, and remove the unreachable implementation of scalar fneg. Reported-by: Peter Maydell Signed-off-by: Richard Henderson Reviewed-by: Peter Maydell Message-id: 20241211163036.2297116-24-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/translate-a64.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index a99f3d0d13..3c1784593a 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -10816,10 +10816,13 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) break; case 0x2f: /* FABS */ case 0x6f: /* FNEG */ + only_in_vector = true; need_fpst = false; break; case 0x7d: /* FRSQRTE */ + break; case 0x7f: /* FSQRT (vector) */ + only_in_vector = true; break; default: unallocated_encoding(s); @@ -10877,9 +10880,6 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x7b: /* FCVTZU */ gen_helper_advsimd_f16touinth(tcg_res, tcg_op, tcg_fpstatus); break; - case 0x6f: /* FNEG */ - tcg_gen_xori_i32(tcg_res, tcg_op, 0x8000); - break; case 0x7d: /* FRSQRTE */ gen_helper_rsqrte_f16(tcg_res, tcg_op, tcg_fpstatus); break; From 5ee3c6c8fd8a8af1c45944d9c9794e9ec233b72e Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:51 -0600 Subject: [PATCH 24/85] target/arm: Convert FMOV, FABS, FNEG (scalar) to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-25-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 7 +++ target/arm/tcg/translate-a64.c | 105 +++++++++++++++++++++++---------- 2 files changed, 81 insertions(+), 31 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 7868b1cb24..b9cc8963da 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -47,6 +47,7 @@ @rr_h ........ ... ..... ...... rn:5 rd:5 &rr_e esz=1 @rr_d ........ ... ..... ...... rn:5 rd:5 &rr_e esz=3 @rr_sd ........ ... ..... ...... rn:5 rd:5 &rr_e esz=%esz_sd +@rr_hsd ........ ... ..... ...... rn:5 rd:5 &rr_e esz=%esz_hsd @rrr_b ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=0 @rrr_h ........ ... rm:5 ...... rn:5 rd:5 &rrr_e esz=1 @@ -1321,6 +1322,12 @@ FMAXV_s 0110 1110 00 11000 01111 10 ..... ..... @rr_q1e2 FMINV_h 0.00 1110 10 11000 01111 10 ..... ..... @qrr_h FMINV_s 0110 1110 10 11000 01111 10 ..... ..... @rr_q1e2 +# Floating-point data processing (1 source) + +FMOV_s 00011110 .. 1 000000 10000 ..... ..... @rr_hsd +FABS_s 00011110 .. 1 000001 10000 ..... ..... @rr_hsd +FNEG_s 00011110 .. 1 000010 10000 ..... ..... @rr_hsd + # Floating-point Immediate FMOVI_s 0001 1110 .. 1 imm:8 100 00000 rd:5 esz=%esz_hsd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 3c1784593a..ca2b95510e 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8283,6 +8283,67 @@ static bool trans_CSEL(DisasContext *s, arg_CSEL *a) return true; } +typedef struct FPScalar1Int { + void (*gen_h)(TCGv_i32, TCGv_i32); + void (*gen_s)(TCGv_i32, TCGv_i32); + void (*gen_d)(TCGv_i64, TCGv_i64); +} FPScalar1Int; + +static bool do_fp1_scalar_int(DisasContext *s, arg_rr_e *a, + const FPScalar1Int *f) +{ + switch (a->esz) { + case MO_64: + if (fp_access_check(s)) { + TCGv_i64 t = read_fp_dreg(s, a->rn); + f->gen_d(t, t); + write_fp_dreg(s, a->rd, t); + } + break; + case MO_32: + if (fp_access_check(s)) { + TCGv_i32 t = read_fp_sreg(s, a->rn); + f->gen_s(t, t); + write_fp_sreg(s, a->rd, t); + } + break; + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return false; + } + if (fp_access_check(s)) { + TCGv_i32 t = read_fp_hreg(s, a->rn); + f->gen_h(t, t); + write_fp_sreg(s, a->rd, t); + } + break; + default: + return false; + } + return true; +} + +static const FPScalar1Int f_scalar_fmov = { + tcg_gen_mov_i32, + tcg_gen_mov_i32, + tcg_gen_mov_i64, +}; +TRANS(FMOV_s, do_fp1_scalar_int, a, &f_scalar_fmov) + +static const FPScalar1Int f_scalar_fabs = { + gen_vfp_absh, + gen_vfp_abss, + gen_vfp_absd, +}; +TRANS(FABS_s, do_fp1_scalar_int, a, &f_scalar_fabs) + +static const FPScalar1Int f_scalar_fneg = { + gen_vfp_negh, + gen_vfp_negs, + gen_vfp_negd, +}; +TRANS(FNEG_s, do_fp1_scalar_int, a, &f_scalar_fneg) + /* Floating-point data-processing (1 source) - half precision */ static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) { @@ -8291,15 +8352,6 @@ static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) TCGv_i32 tcg_res = tcg_temp_new_i32(); switch (opcode) { - case 0x0: /* FMOV */ - tcg_gen_mov_i32(tcg_res, tcg_op); - break; - case 0x1: /* FABS */ - gen_vfp_absh(tcg_res, tcg_op); - break; - case 0x2: /* FNEG */ - gen_vfp_negh(tcg_res, tcg_op); - break; case 0x3: /* FSQRT */ fpst = fpstatus_ptr(FPST_FPCR_F16); gen_helper_sqrt_f16(tcg_res, tcg_op, fpst); @@ -8327,6 +8379,9 @@ static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) gen_helper_advsimd_rinth(tcg_res, tcg_op, fpst); break; default: + case 0x0: /* FMOV */ + case 0x1: /* FABS */ + case 0x2: /* FNEG */ g_assert_not_reached(); } @@ -8345,15 +8400,6 @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) tcg_res = tcg_temp_new_i32(); switch (opcode) { - case 0x0: /* FMOV */ - tcg_gen_mov_i32(tcg_res, tcg_op); - goto done; - case 0x1: /* FABS */ - gen_vfp_abss(tcg_res, tcg_op); - goto done; - case 0x2: /* FNEG */ - gen_vfp_negs(tcg_res, tcg_op); - goto done; case 0x3: /* FSQRT */ gen_helper_vfp_sqrts(tcg_res, tcg_op, tcg_env); goto done; @@ -8389,6 +8435,9 @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) gen_fpst = gen_helper_frint64_s; break; default: + case 0x0: /* FMOV */ + case 0x1: /* FABS */ + case 0x2: /* FNEG */ g_assert_not_reached(); } @@ -8413,22 +8462,10 @@ static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn) TCGv_ptr fpst; int rmode = -1; - switch (opcode) { - case 0x0: /* FMOV */ - gen_gvec_fn2(s, false, rd, rn, tcg_gen_gvec_mov, 0); - return; - } - tcg_op = read_fp_dreg(s, rn); tcg_res = tcg_temp_new_i64(); switch (opcode) { - case 0x1: /* FABS */ - gen_vfp_absd(tcg_res, tcg_op); - goto done; - case 0x2: /* FNEG */ - gen_vfp_negd(tcg_res, tcg_op); - goto done; case 0x3: /* FSQRT */ gen_helper_vfp_sqrtd(tcg_res, tcg_op, tcg_env); goto done; @@ -8461,6 +8498,9 @@ static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn) gen_fpst = gen_helper_frint64_d; break; default: + case 0x0: /* FMOV */ + case 0x1: /* FABS */ + case 0x2: /* FNEG */ g_assert_not_reached(); } @@ -8581,7 +8621,7 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) goto do_unallocated; } /* fall through */ - case 0x0 ... 0x3: + case 0x3: case 0x8 ... 0xc: case 0xe ... 0xf: /* 32-to-32 and 64-to-64 ops */ @@ -8631,6 +8671,9 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) default: do_unallocated: + case 0x0: /* FMOV */ + case 0x1: /* FABS */ + case 0x2: /* FNEG */ unallocated_encoding(s); break; } From cf866d81b86633bda2d60da9eca33dbeb07a78af Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:52 -0600 Subject: [PATCH 25/85] target/arm: Pass fpstatus to vfp_sqrt* Pass fpstatus not env, like most other fp helpers. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-26-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 6 +++--- target/arm/tcg/translate-a64.c | 15 +++++++-------- target/arm/tcg/translate-vfp.c | 6 +++--- target/arm/vfp_helper.c | 12 ++++++------ 4 files changed, 19 insertions(+), 20 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 58919b670e..0a697e752b 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -133,9 +133,9 @@ DEF_HELPER_3(vfp_maxnumd, f64, f64, f64, ptr) DEF_HELPER_3(vfp_minnumh, f16, f16, f16, ptr) DEF_HELPER_3(vfp_minnums, f32, f32, f32, ptr) DEF_HELPER_3(vfp_minnumd, f64, f64, f64, ptr) -DEF_HELPER_2(vfp_sqrth, f16, f16, env) -DEF_HELPER_2(vfp_sqrts, f32, f32, env) -DEF_HELPER_2(vfp_sqrtd, f64, f64, env) +DEF_HELPER_2(vfp_sqrth, f16, f16, ptr) +DEF_HELPER_2(vfp_sqrts, f32, f32, ptr) +DEF_HELPER_2(vfp_sqrtd, f64, f64, ptr) DEF_HELPER_3(vfp_cmph, void, f16, f16, env) DEF_HELPER_3(vfp_cmps, void, f32, f32, env) DEF_HELPER_3(vfp_cmpd, void, f64, f64, env) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index ca2b95510e..cfc73b8506 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8401,8 +8401,8 @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) switch (opcode) { case 0x3: /* FSQRT */ - gen_helper_vfp_sqrts(tcg_res, tcg_op, tcg_env); - goto done; + gen_fpst = gen_helper_vfp_sqrts; + break; case 0x6: /* BFCVT */ gen_fpst = gen_helper_bfcvt; break; @@ -8450,7 +8450,6 @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) gen_fpst(tcg_res, tcg_op, fpst); } - done: write_fp_sreg(s, rd, tcg_res); } @@ -8467,8 +8466,8 @@ static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn) switch (opcode) { case 0x3: /* FSQRT */ - gen_helper_vfp_sqrtd(tcg_res, tcg_op, tcg_env); - goto done; + gen_fpst = gen_helper_vfp_sqrtd; + break; case 0x8: /* FRINTN */ case 0x9: /* FRINTP */ case 0xa: /* FRINTM */ @@ -8513,7 +8512,6 @@ static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn) gen_fpst(tcg_res, tcg_op, fpst); } - done: write_fp_dreg(s, rd, tcg_res); } @@ -9459,7 +9457,7 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, gen_vfp_negd(tcg_rd, tcg_rn); break; case 0x7f: /* FSQRT */ - gen_helper_vfp_sqrtd(tcg_rd, tcg_rn, tcg_env); + gen_helper_vfp_sqrtd(tcg_rd, tcg_rn, tcg_fpstatus); break; case 0x1a: /* FCVTNS */ case 0x1b: /* FCVTMS */ @@ -10402,6 +10400,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) handle_2misc_fcmp_zero(s, opcode, false, u, is_q, size, rn, rd); return; case 0x7f: /* FSQRT */ + need_fpstatus = true; if (size == 3 && !is_q) { unallocated_encoding(s); return; @@ -10631,7 +10630,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) gen_vfp_negs(tcg_res, tcg_op); break; case 0x7f: /* FSQRT */ - gen_helper_vfp_sqrts(tcg_res, tcg_op, tcg_env); + gen_helper_vfp_sqrts(tcg_res, tcg_op, tcg_fpstatus); break; case 0x1a: /* FCVTNS */ case 0x1b: /* FCVTMS */ diff --git a/target/arm/tcg/translate-vfp.c b/target/arm/tcg/translate-vfp.c index b6fa28a7bf..c160a86e70 100644 --- a/target/arm/tcg/translate-vfp.c +++ b/target/arm/tcg/translate-vfp.c @@ -2424,17 +2424,17 @@ DO_VFP_2OP(VNEG, dp, gen_vfp_negd, aa32_fpdp_v2) static void gen_VSQRT_hp(TCGv_i32 vd, TCGv_i32 vm) { - gen_helper_vfp_sqrth(vd, vm, tcg_env); + gen_helper_vfp_sqrth(vd, vm, fpstatus_ptr(FPST_FPCR_F16)); } static void gen_VSQRT_sp(TCGv_i32 vd, TCGv_i32 vm) { - gen_helper_vfp_sqrts(vd, vm, tcg_env); + gen_helper_vfp_sqrts(vd, vm, fpstatus_ptr(FPST_FPCR)); } static void gen_VSQRT_dp(TCGv_i64 vd, TCGv_i64 vm) { - gen_helper_vfp_sqrtd(vd, vm, tcg_env); + gen_helper_vfp_sqrtd(vd, vm, fpstatus_ptr(FPST_FPCR)); } DO_VFP_2OP(VSQRT, hp, gen_VSQRT_hp, aa32_fp16_arith) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index 62638d2b1f..f24992c798 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -314,19 +314,19 @@ VFP_BINOP(minnum) VFP_BINOP(maxnum) #undef VFP_BINOP -dh_ctype_f16 VFP_HELPER(sqrt, h)(dh_ctype_f16 a, CPUARMState *env) +dh_ctype_f16 VFP_HELPER(sqrt, h)(dh_ctype_f16 a, void *fpstp) { - return float16_sqrt(a, &env->vfp.fp_status_f16); + return float16_sqrt(a, fpstp); } -float32 VFP_HELPER(sqrt, s)(float32 a, CPUARMState *env) +float32 VFP_HELPER(sqrt, s)(float32 a, void *fpstp) { - return float32_sqrt(a, &env->vfp.fp_status); + return float32_sqrt(a, fpstp); } -float64 VFP_HELPER(sqrt, d)(float64 a, CPUARMState *env) +float64 VFP_HELPER(sqrt, d)(float64 a, void *fpstp) { - return float64_sqrt(a, &env->vfp.fp_status); + return float64_sqrt(a, fpstp); } static void softfloat_to_vfp_compare(CPUARMState *env, FloatRelation cmp) From 62b85fd044a71f45a5620e1de11b2b17579ce69f Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:53 -0600 Subject: [PATCH 26/85] target/arm: Remove helper_sqrt_f16 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This function is identical with helper_vfp_sqrth. Replace all uses. Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-27-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/helper-a64.c | 11 ----------- target/arm/tcg/helper-a64.h | 1 - target/arm/tcg/translate-a64.c | 4 ++-- 3 files changed, 2 insertions(+), 14 deletions(-) diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index 8f42a28d07..3f4d7b9aba 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -915,17 +915,6 @@ illegal_return: "resuming execution at 0x%" PRIx64 "\n", cur_el, env->pc); } -/* - * Square Root and Reciprocal square root - */ - -uint32_t HELPER(sqrt_f16)(uint32_t a, void *fpstp) -{ - float_status *s = fpstp; - - return float16_sqrt(a, s); -} - void HELPER(dc_zva)(CPUARMState *env, uint64_t vaddr_in) { uintptr_t ra = GETPC(); diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index 481007bf39..203b7b7ac8 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -80,7 +80,6 @@ DEF_HELPER_2(advsimd_rinth_exact, f16, f16, ptr) 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_2(exception_return, void, env, i64) DEF_HELPER_FLAGS_2(dc_zva, TCG_CALL_NO_WG, void, env, i64) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index cfc73b8506..2a5cb70475 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8354,7 +8354,7 @@ static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) switch (opcode) { case 0x3: /* FSQRT */ fpst = fpstatus_ptr(FPST_FPCR_F16); - gen_helper_sqrt_f16(tcg_res, tcg_op, fpst); + gen_helper_vfp_sqrth(tcg_res, tcg_op, fpst); break; case 0x8: /* FRINTN */ case 0x9: /* FRINTP */ @@ -10978,7 +10978,7 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) gen_helper_rsqrte_f16(tcg_res, tcg_op, tcg_fpstatus); break; case 0x7f: /* FSQRT */ - gen_helper_sqrt_f16(tcg_res, tcg_op, tcg_fpstatus); + gen_helper_vfp_sqrth(tcg_res, tcg_op, tcg_fpstatus); break; default: g_assert_not_reached(); From dbc739724aceb300c62fbe3716efceb16f392ce5 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:54 -0600 Subject: [PATCH 27/85] target/arm: Convert FSQRT (scalar) to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-28-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 1 + target/arm/tcg/translate-a64.c | 72 ++++++++++++++++++++++++++++------ 2 files changed, 62 insertions(+), 11 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index b9cc8963da..3b1e8e0776 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1327,6 +1327,7 @@ FMINV_s 0110 1110 10 11000 01111 10 ..... ..... @rr_q1e2 FMOV_s 00011110 .. 1 000000 10000 ..... ..... @rr_hsd FABS_s 00011110 .. 1 000001 10000 ..... ..... @rr_hsd FNEG_s 00011110 .. 1 000010 10000 ..... ..... @rr_hsd +FSQRT_s 00011110 .. 1 000011 10000 ..... ..... @rr_hsd # Floating-point Immediate diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 2a5cb70475..f3989246f9 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8344,6 +8344,63 @@ static const FPScalar1Int f_scalar_fneg = { }; TRANS(FNEG_s, do_fp1_scalar_int, a, &f_scalar_fneg) +typedef struct FPScalar1 { + void (*gen_h)(TCGv_i32, TCGv_i32, TCGv_ptr); + void (*gen_s)(TCGv_i32, TCGv_i32, TCGv_ptr); + void (*gen_d)(TCGv_i64, TCGv_i64, TCGv_ptr); +} FPScalar1; + +static bool do_fp1_scalar(DisasContext *s, arg_rr_e *a, + const FPScalar1 *f, int rmode) +{ + TCGv_i32 tcg_rmode = NULL; + TCGv_ptr fpst; + TCGv_i64 t64; + TCGv_i32 t32; + int check = fp_access_check_scalar_hsd(s, a->esz); + + if (check <= 0) { + return check == 0; + } + + fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + if (rmode >= 0) { + tcg_rmode = gen_set_rmode(rmode, fpst); + } + + switch (a->esz) { + case MO_64: + t64 = read_fp_dreg(s, a->rn); + f->gen_d(t64, t64, fpst); + write_fp_dreg(s, a->rd, t64); + break; + case MO_32: + t32 = read_fp_sreg(s, a->rn); + f->gen_s(t32, t32, fpst); + write_fp_sreg(s, a->rd, t32); + break; + case MO_16: + t32 = read_fp_hreg(s, a->rn); + f->gen_h(t32, t32, fpst); + write_fp_sreg(s, a->rd, t32); + break; + default: + g_assert_not_reached(); + } + + if (rmode >= 0) { + gen_restore_rmode(tcg_rmode, fpst); + } + return true; +} + +static const FPScalar1 f_scalar_fsqrt = { + gen_helper_vfp_sqrth, + gen_helper_vfp_sqrts, + gen_helper_vfp_sqrtd, +}; +TRANS(FSQRT_s, do_fp1_scalar, a, &f_scalar_fsqrt, -1) + /* Floating-point data-processing (1 source) - half precision */ static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) { @@ -8352,10 +8409,6 @@ static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) TCGv_i32 tcg_res = tcg_temp_new_i32(); switch (opcode) { - case 0x3: /* FSQRT */ - fpst = fpstatus_ptr(FPST_FPCR_F16); - gen_helper_vfp_sqrth(tcg_res, tcg_op, fpst); - break; case 0x8: /* FRINTN */ case 0x9: /* FRINTP */ case 0xa: /* FRINTM */ @@ -8382,6 +8435,7 @@ static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) case 0x0: /* FMOV */ case 0x1: /* FABS */ case 0x2: /* FNEG */ + case 0x3: /* FSQRT */ g_assert_not_reached(); } @@ -8400,9 +8454,6 @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) tcg_res = tcg_temp_new_i32(); switch (opcode) { - case 0x3: /* FSQRT */ - gen_fpst = gen_helper_vfp_sqrts; - break; case 0x6: /* BFCVT */ gen_fpst = gen_helper_bfcvt; break; @@ -8438,6 +8489,7 @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) case 0x0: /* FMOV */ case 0x1: /* FABS */ case 0x2: /* FNEG */ + case 0x3: /* FSQRT */ g_assert_not_reached(); } @@ -8465,9 +8517,6 @@ static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn) tcg_res = tcg_temp_new_i64(); switch (opcode) { - case 0x3: /* FSQRT */ - gen_fpst = gen_helper_vfp_sqrtd; - break; case 0x8: /* FRINTN */ case 0x9: /* FRINTP */ case 0xa: /* FRINTM */ @@ -8500,6 +8549,7 @@ static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn) case 0x0: /* FMOV */ case 0x1: /* FABS */ case 0x2: /* FNEG */ + case 0x3: /* FSQRT */ g_assert_not_reached(); } @@ -8619,7 +8669,6 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) goto do_unallocated; } /* fall through */ - case 0x3: case 0x8 ... 0xc: case 0xe ... 0xf: /* 32-to-32 and 64-to-64 ops */ @@ -8672,6 +8721,7 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) case 0x0: /* FMOV */ case 0x1: /* FABS */ case 0x2: /* FNEG */ + case 0x3: /* FSQRT */ unallocated_encoding(s); break; } From cf85790bb82665887203b9e34f865158c130b27b Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:55 -0600 Subject: [PATCH 28/85] target/arm: Convert FRINT[NPMSAXI] (scalar) to decodetree Remove handle_fp_1src_half as these were the last insns decoded by that function. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-29-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 8 +++ target/arm/tcg/translate-a64.c | 117 +++++++++++---------------------- 2 files changed, 46 insertions(+), 79 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 3b1e8e0776..9d2f099c9c 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1329,6 +1329,14 @@ FABS_s 00011110 .. 1 000001 10000 ..... ..... @rr_hsd FNEG_s 00011110 .. 1 000010 10000 ..... ..... @rr_hsd FSQRT_s 00011110 .. 1 000011 10000 ..... ..... @rr_hsd +FRINTN_s 00011110 .. 1 001000 10000 ..... ..... @rr_hsd +FRINTP_s 00011110 .. 1 001001 10000 ..... ..... @rr_hsd +FRINTM_s 00011110 .. 1 001010 10000 ..... ..... @rr_hsd +FRINTZ_s 00011110 .. 1 001011 10000 ..... ..... @rr_hsd +FRINTA_s 00011110 .. 1 001100 10000 ..... ..... @rr_hsd +FRINTX_s 00011110 .. 1 001110 10000 ..... ..... @rr_hsd +FRINTI_s 00011110 .. 1 001111 10000 ..... ..... @rr_hsd + # Floating-point Immediate FMOVI_s 0001 1110 .. 1 imm:8 100 00000 rd:5 esz=%esz_hsd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index f3989246f9..5a347bece3 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8401,46 +8401,24 @@ static const FPScalar1 f_scalar_fsqrt = { }; TRANS(FSQRT_s, do_fp1_scalar, a, &f_scalar_fsqrt, -1) -/* Floating-point data-processing (1 source) - half precision */ -static void handle_fp_1src_half(DisasContext *s, int opcode, int rd, int rn) -{ - TCGv_ptr fpst = NULL; - TCGv_i32 tcg_op = read_fp_hreg(s, rn); - TCGv_i32 tcg_res = tcg_temp_new_i32(); +static const FPScalar1 f_scalar_frint = { + gen_helper_advsimd_rinth, + gen_helper_rints, + gen_helper_rintd, +}; +TRANS(FRINTN_s, do_fp1_scalar, a, &f_scalar_frint, FPROUNDING_TIEEVEN) +TRANS(FRINTP_s, do_fp1_scalar, a, &f_scalar_frint, FPROUNDING_POSINF) +TRANS(FRINTM_s, do_fp1_scalar, a, &f_scalar_frint, FPROUNDING_NEGINF) +TRANS(FRINTZ_s, do_fp1_scalar, a, &f_scalar_frint, FPROUNDING_ZERO) +TRANS(FRINTA_s, do_fp1_scalar, a, &f_scalar_frint, FPROUNDING_TIEAWAY) +TRANS(FRINTI_s, do_fp1_scalar, a, &f_scalar_frint, -1) - switch (opcode) { - case 0x8: /* FRINTN */ - case 0x9: /* FRINTP */ - case 0xa: /* FRINTM */ - case 0xb: /* FRINTZ */ - case 0xc: /* FRINTA */ - { - TCGv_i32 tcg_rmode; - - fpst = fpstatus_ptr(FPST_FPCR_F16); - tcg_rmode = gen_set_rmode(opcode & 7, fpst); - gen_helper_advsimd_rinth(tcg_res, tcg_op, fpst); - gen_restore_rmode(tcg_rmode, fpst); - break; - } - case 0xe: /* FRINTX */ - fpst = fpstatus_ptr(FPST_FPCR_F16); - gen_helper_advsimd_rinth_exact(tcg_res, tcg_op, fpst); - break; - case 0xf: /* FRINTI */ - fpst = fpstatus_ptr(FPST_FPCR_F16); - gen_helper_advsimd_rinth(tcg_res, tcg_op, fpst); - break; - default: - case 0x0: /* FMOV */ - case 0x1: /* FABS */ - case 0x2: /* FNEG */ - case 0x3: /* FSQRT */ - g_assert_not_reached(); - } - - write_fp_sreg(s, rd, tcg_res); -} +static const FPScalar1 f_scalar_frintx = { + gen_helper_advsimd_rinth_exact, + gen_helper_rints_exact, + gen_helper_rintd_exact, +}; +TRANS(FRINTX_s, do_fp1_scalar, a, &f_scalar_frintx, -1) /* Floating-point data-processing (1 source) - single precision */ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) @@ -8457,20 +8435,6 @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) case 0x6: /* BFCVT */ gen_fpst = gen_helper_bfcvt; break; - case 0x8: /* FRINTN */ - case 0x9: /* FRINTP */ - case 0xa: /* FRINTM */ - case 0xb: /* FRINTZ */ - case 0xc: /* FRINTA */ - rmode = opcode & 7; - gen_fpst = gen_helper_rints; - break; - case 0xe: /* FRINTX */ - gen_fpst = gen_helper_rints_exact; - break; - case 0xf: /* FRINTI */ - gen_fpst = gen_helper_rints; - break; case 0x10: /* FRINT32Z */ rmode = FPROUNDING_ZERO; gen_fpst = gen_helper_frint32_s; @@ -8490,6 +8454,13 @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) case 0x1: /* FABS */ case 0x2: /* FNEG */ case 0x3: /* FSQRT */ + case 0x8: /* FRINTN */ + case 0x9: /* FRINTP */ + case 0xa: /* FRINTM */ + case 0xb: /* FRINTZ */ + case 0xc: /* FRINTA */ + case 0xe: /* FRINTX */ + case 0xf: /* FRINTI */ g_assert_not_reached(); } @@ -8517,20 +8488,6 @@ static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn) tcg_res = tcg_temp_new_i64(); switch (opcode) { - case 0x8: /* FRINTN */ - case 0x9: /* FRINTP */ - case 0xa: /* FRINTM */ - case 0xb: /* FRINTZ */ - case 0xc: /* FRINTA */ - rmode = opcode & 7; - gen_fpst = gen_helper_rintd; - break; - case 0xe: /* FRINTX */ - gen_fpst = gen_helper_rintd_exact; - break; - case 0xf: /* FRINTI */ - gen_fpst = gen_helper_rintd; - break; case 0x10: /* FRINT32Z */ rmode = FPROUNDING_ZERO; gen_fpst = gen_helper_frint32_d; @@ -8550,6 +8507,13 @@ static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn) case 0x1: /* FABS */ case 0x2: /* FNEG */ case 0x3: /* FSQRT */ + case 0x8: /* FRINTN */ + case 0x9: /* FRINTP */ + case 0xa: /* FRINTM */ + case 0xb: /* FRINTZ */ + case 0xc: /* FRINTA */ + case 0xe: /* FRINTX */ + case 0xf: /* FRINTI */ g_assert_not_reached(); } @@ -8668,9 +8632,6 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) if (type > 1 || !dc_isar_feature(aa64_frint, s)) { goto do_unallocated; } - /* fall through */ - case 0x8 ... 0xc: - case 0xe ... 0xf: /* 32-to-32 and 64-to-64 ops */ switch (type) { case 0: @@ -8686,15 +8647,6 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) handle_fp_1src_double(s, opcode, rd, rn); break; case 3: - if (!dc_isar_feature(aa64_fp16, s)) { - goto do_unallocated; - } - - if (!fp_access_check(s)) { - return; - } - handle_fp_1src_half(s, opcode, rd, rn); - break; default: goto do_unallocated; } @@ -8722,6 +8674,13 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) case 0x1: /* FABS */ case 0x2: /* FNEG */ case 0x3: /* FSQRT */ + case 0x8: /* FRINTN */ + case 0x9: /* FRINTP */ + case 0xa: /* FRINTM */ + case 0xb: /* FRINTZ */ + case 0xc: /* FRINTA */ + case 0xe: /* FRINTX */ + case 0xf: /* FRINTI */ unallocated_encoding(s); break; } From a55df233989a8493fcc946384a4a5109067e6c25 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:56 -0600 Subject: [PATCH 29/85] target/arm: Convert BFCVT to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-30-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 3 +++ target/arm/tcg/translate-a64.c | 26 +++++++------------------- 2 files changed, 10 insertions(+), 19 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 9d2f099c9c..4a48fcff1d 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -45,6 +45,7 @@ &qrrrr_e q rd rn rm ra esz @rr_h ........ ... ..... ...... rn:5 rd:5 &rr_e esz=1 +@rr_s ........ ... ..... ...... rn:5 rd:5 &rr_e esz=2 @rr_d ........ ... ..... ...... rn:5 rd:5 &rr_e esz=3 @rr_sd ........ ... ..... ...... rn:5 rd:5 &rr_e esz=%esz_sd @rr_hsd ........ ... ..... ...... rn:5 rd:5 &rr_e esz=%esz_hsd @@ -1337,6 +1338,8 @@ FRINTA_s 00011110 .. 1 001100 10000 ..... ..... @rr_hsd FRINTX_s 00011110 .. 1 001110 10000 ..... ..... @rr_hsd FRINTI_s 00011110 .. 1 001111 10000 ..... ..... @rr_hsd +BFCVT_s 00011110 01 1 000110 10000 ..... ..... @rr_s + # Floating-point Immediate FMOVI_s 0001 1110 .. 1 imm:8 100 00000 rd:5 esz=%esz_hsd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 5a347bece3..5b30b4caca 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8420,6 +8420,11 @@ static const FPScalar1 f_scalar_frintx = { }; TRANS(FRINTX_s, do_fp1_scalar, a, &f_scalar_frintx, -1) +static const FPScalar1 f_scalar_bfcvt = { + .gen_s = gen_helper_bfcvt, +}; +TRANS_FEAT(BFCVT_s, aa64_bf16, do_fp1_scalar, a, &f_scalar_bfcvt, -1) + /* Floating-point data-processing (1 source) - single precision */ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) { @@ -8432,9 +8437,6 @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) tcg_res = tcg_temp_new_i32(); switch (opcode) { - case 0x6: /* BFCVT */ - gen_fpst = gen_helper_bfcvt; - break; case 0x10: /* FRINT32Z */ rmode = FPROUNDING_ZERO; gen_fpst = gen_helper_frint32_s; @@ -8454,6 +8456,7 @@ static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) case 0x1: /* FABS */ case 0x2: /* FNEG */ case 0x3: /* FSQRT */ + case 0x6: /* BFCVT */ case 0x8: /* FRINTN */ case 0x9: /* FRINTP */ case 0xa: /* FRINTM */ @@ -8652,28 +8655,13 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) } break; - case 0x6: - switch (type) { - case 1: /* BFCVT */ - if (!dc_isar_feature(aa64_bf16, s)) { - goto do_unallocated; - } - if (!fp_access_check(s)) { - return; - } - handle_fp_1src_single(s, opcode, rd, rn); - break; - default: - goto do_unallocated; - } - break; - default: do_unallocated: case 0x0: /* FMOV */ case 0x1: /* FABS */ case 0x2: /* FNEG */ case 0x3: /* FSQRT */ + case 0x6: /* BFCVT */ case 0x8: /* FRINTN */ case 0x9: /* FRINTP */ case 0xa: /* FRINTM */ From 9982ccec41cda638adb75367523c359c621928ff Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:57 -0600 Subject: [PATCH 30/85] target/arm: Convert FRINT{32, 64}[ZX] (scalar) to decodetree Remove handle_fp_1src_single and handle_fp_1src_double as these were the last insns decoded by those functions. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-31-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 5 ++ target/arm/tcg/translate-a64.c | 146 ++++----------------------------- 2 files changed, 22 insertions(+), 129 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 4a48fcff1d..4f7b3ee3d9 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1340,6 +1340,11 @@ FRINTI_s 00011110 .. 1 001111 10000 ..... ..... @rr_hsd BFCVT_s 00011110 01 1 000110 10000 ..... ..... @rr_s +FRINT32Z_s 00011110 0. 1 010000 10000 ..... ..... @rr_sd +FRINT32X_s 00011110 0. 1 010001 10000 ..... ..... @rr_sd +FRINT64Z_s 00011110 0. 1 010010 10000 ..... ..... @rr_sd +FRINT64X_s 00011110 0. 1 010011 10000 ..... ..... @rr_sd + # Floating-point Immediate FMOVI_s 0001 1110 .. 1 imm:8 100 00000 rd:5 esz=%esz_hsd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 5b30b4caca..e48dd308fc 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8425,112 +8425,23 @@ static const FPScalar1 f_scalar_bfcvt = { }; TRANS_FEAT(BFCVT_s, aa64_bf16, do_fp1_scalar, a, &f_scalar_bfcvt, -1) -/* Floating-point data-processing (1 source) - single precision */ -static void handle_fp_1src_single(DisasContext *s, int opcode, int rd, int rn) -{ - void (*gen_fpst)(TCGv_i32, TCGv_i32, TCGv_ptr); - TCGv_i32 tcg_op, tcg_res; - TCGv_ptr fpst; - int rmode = -1; +static const FPScalar1 f_scalar_frint32 = { + NULL, + gen_helper_frint32_s, + gen_helper_frint32_d, +}; +TRANS_FEAT(FRINT32Z_s, aa64_frint, do_fp1_scalar, a, + &f_scalar_frint32, FPROUNDING_ZERO) +TRANS_FEAT(FRINT32X_s, aa64_frint, do_fp1_scalar, a, &f_scalar_frint32, -1) - tcg_op = read_fp_sreg(s, rn); - tcg_res = tcg_temp_new_i32(); - - switch (opcode) { - case 0x10: /* FRINT32Z */ - rmode = FPROUNDING_ZERO; - gen_fpst = gen_helper_frint32_s; - break; - case 0x11: /* FRINT32X */ - gen_fpst = gen_helper_frint32_s; - break; - case 0x12: /* FRINT64Z */ - rmode = FPROUNDING_ZERO; - gen_fpst = gen_helper_frint64_s; - break; - case 0x13: /* FRINT64X */ - gen_fpst = gen_helper_frint64_s; - break; - default: - case 0x0: /* FMOV */ - case 0x1: /* FABS */ - case 0x2: /* FNEG */ - case 0x3: /* FSQRT */ - case 0x6: /* BFCVT */ - case 0x8: /* FRINTN */ - case 0x9: /* FRINTP */ - case 0xa: /* FRINTM */ - case 0xb: /* FRINTZ */ - case 0xc: /* FRINTA */ - case 0xe: /* FRINTX */ - case 0xf: /* FRINTI */ - g_assert_not_reached(); - } - - fpst = fpstatus_ptr(FPST_FPCR); - if (rmode >= 0) { - TCGv_i32 tcg_rmode = gen_set_rmode(rmode, fpst); - gen_fpst(tcg_res, tcg_op, fpst); - gen_restore_rmode(tcg_rmode, fpst); - } else { - gen_fpst(tcg_res, tcg_op, fpst); - } - - write_fp_sreg(s, rd, tcg_res); -} - -/* Floating-point data-processing (1 source) - double precision */ -static void handle_fp_1src_double(DisasContext *s, int opcode, int rd, int rn) -{ - void (*gen_fpst)(TCGv_i64, TCGv_i64, TCGv_ptr); - TCGv_i64 tcg_op, tcg_res; - TCGv_ptr fpst; - int rmode = -1; - - tcg_op = read_fp_dreg(s, rn); - tcg_res = tcg_temp_new_i64(); - - switch (opcode) { - case 0x10: /* FRINT32Z */ - rmode = FPROUNDING_ZERO; - gen_fpst = gen_helper_frint32_d; - break; - case 0x11: /* FRINT32X */ - gen_fpst = gen_helper_frint32_d; - break; - case 0x12: /* FRINT64Z */ - rmode = FPROUNDING_ZERO; - gen_fpst = gen_helper_frint64_d; - break; - case 0x13: /* FRINT64X */ - gen_fpst = gen_helper_frint64_d; - break; - default: - case 0x0: /* FMOV */ - case 0x1: /* FABS */ - case 0x2: /* FNEG */ - case 0x3: /* FSQRT */ - case 0x8: /* FRINTN */ - case 0x9: /* FRINTP */ - case 0xa: /* FRINTM */ - case 0xb: /* FRINTZ */ - case 0xc: /* FRINTA */ - case 0xe: /* FRINTX */ - case 0xf: /* FRINTI */ - g_assert_not_reached(); - } - - fpst = fpstatus_ptr(FPST_FPCR); - if (rmode >= 0) { - TCGv_i32 tcg_rmode = gen_set_rmode(rmode, fpst); - gen_fpst(tcg_res, tcg_op, fpst); - gen_restore_rmode(tcg_rmode, fpst); - } else { - gen_fpst(tcg_res, tcg_op, fpst); - } - - write_fp_dreg(s, rd, tcg_res); -} +static const FPScalar1 f_scalar_frint64 = { + NULL, + gen_helper_frint64_s, + gen_helper_frint64_d, +}; +TRANS_FEAT(FRINT64Z_s, aa64_frint, do_fp1_scalar, a, + &f_scalar_frint64, FPROUNDING_ZERO) +TRANS_FEAT(FRINT64X_s, aa64_frint, do_fp1_scalar, a, &f_scalar_frint64, -1) static void handle_fp_fcvt(DisasContext *s, int opcode, int rd, int rn, int dtype, int ntype) @@ -8631,30 +8542,6 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) break; } - case 0x10 ... 0x13: /* FRINT{32,64}{X,Z} */ - if (type > 1 || !dc_isar_feature(aa64_frint, s)) { - goto do_unallocated; - } - /* 32-to-32 and 64-to-64 ops */ - switch (type) { - case 0: - if (!fp_access_check(s)) { - return; - } - handle_fp_1src_single(s, opcode, rd, rn); - break; - case 1: - if (!fp_access_check(s)) { - return; - } - handle_fp_1src_double(s, opcode, rd, rn); - break; - case 3: - default: - goto do_unallocated; - } - break; - default: do_unallocated: case 0x0: /* FMOV */ @@ -8669,6 +8556,7 @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) case 0xc: /* FRINTA */ case 0xe: /* FRINTX */ case 0xf: /* FRINTI */ + case 0x10 ... 0x13: /* FRINT{32,64}{X,Z} */ unallocated_encoding(s); break; } From 7b0f8dc1ec6b554300c85a835100e615d7ce070b Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:58 -0600 Subject: [PATCH 31/85] target/arm: Convert FCVT (scalar) to decodetree Remove handle_fp_fcvt and disas_fp_1src as these were the last insns decoded by those functions. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-32-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 7 ++ target/arm/tcg/translate-a64.c | 172 +++++++++++++-------------------- 2 files changed, 74 insertions(+), 105 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 4f7b3ee3d9..211346c4d9 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1345,6 +1345,13 @@ FRINT32X_s 00011110 0. 1 010001 10000 ..... ..... @rr_sd FRINT64Z_s 00011110 0. 1 010010 10000 ..... ..... @rr_sd FRINT64X_s 00011110 0. 1 010011 10000 ..... ..... @rr_sd +FCVT_s_ds 00011110 00 1 000101 10000 ..... ..... @rr +FCVT_s_hs 00011110 00 1 000111 10000 ..... ..... @rr +FCVT_s_sd 00011110 01 1 000100 10000 ..... ..... @rr +FCVT_s_hd 00011110 01 1 000111 10000 ..... ..... @rr +FCVT_s_sh 00011110 11 1 000100 10000 ..... ..... @rr +FCVT_s_dh 00011110 11 1 000101 10000 ..... ..... @rr + # Floating-point Immediate FMOVI_s 0001 1110 .. 1 imm:8 100 00000 rd:5 esz=%esz_hsd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index e48dd308fc..b31a6d4dff 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8443,123 +8443,85 @@ TRANS_FEAT(FRINT64Z_s, aa64_frint, do_fp1_scalar, a, &f_scalar_frint64, FPROUNDING_ZERO) TRANS_FEAT(FRINT64X_s, aa64_frint, do_fp1_scalar, a, &f_scalar_frint64, -1) -static void handle_fp_fcvt(DisasContext *s, int opcode, - int rd, int rn, int dtype, int ntype) +static bool trans_FCVT_s_ds(DisasContext *s, arg_rr *a) { - switch (ntype) { - case 0x0: - { - TCGv_i32 tcg_rn = read_fp_sreg(s, rn); - if (dtype == 1) { - /* Single to double */ - TCGv_i64 tcg_rd = tcg_temp_new_i64(); - gen_helper_vfp_fcvtds(tcg_rd, tcg_rn, tcg_env); - write_fp_dreg(s, rd, tcg_rd); - } else { - /* Single to half */ - TCGv_i32 tcg_rd = tcg_temp_new_i32(); - TCGv_i32 ahp = get_ahp_flag(); - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); + if (fp_access_check(s)) { + TCGv_i32 tcg_rn = read_fp_sreg(s, a->rn); + TCGv_i64 tcg_rd = tcg_temp_new_i64(); - gen_helper_vfp_fcvt_f32_to_f16(tcg_rd, tcg_rn, fpst, ahp); - /* write_fp_sreg is OK here because top half of tcg_rd is zero */ - write_fp_sreg(s, rd, tcg_rd); - } - break; - } - case 0x1: - { - TCGv_i64 tcg_rn = read_fp_dreg(s, rn); - TCGv_i32 tcg_rd = tcg_temp_new_i32(); - if (dtype == 0) { - /* Double to single */ - gen_helper_vfp_fcvtsd(tcg_rd, tcg_rn, tcg_env); - } else { - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); - TCGv_i32 ahp = get_ahp_flag(); - /* Double to half */ - gen_helper_vfp_fcvt_f64_to_f16(tcg_rd, tcg_rn, fpst, ahp); - /* write_fp_sreg is OK here because top half of tcg_rd is zero */ - } - write_fp_sreg(s, rd, tcg_rd); - break; - } - case 0x3: - { - TCGv_i32 tcg_rn = read_fp_sreg(s, rn); - TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_FPCR); - TCGv_i32 tcg_ahp = get_ahp_flag(); - tcg_gen_ext16u_i32(tcg_rn, tcg_rn); - if (dtype == 0) { - /* Half to single */ - TCGv_i32 tcg_rd = tcg_temp_new_i32(); - gen_helper_vfp_fcvt_f16_to_f32(tcg_rd, tcg_rn, tcg_fpst, tcg_ahp); - write_fp_sreg(s, rd, tcg_rd); - } else { - /* Half to double */ - TCGv_i64 tcg_rd = tcg_temp_new_i64(); - gen_helper_vfp_fcvt_f16_to_f64(tcg_rd, tcg_rn, tcg_fpst, tcg_ahp); - write_fp_dreg(s, rd, tcg_rd); - } - break; - } - default: - g_assert_not_reached(); + gen_helper_vfp_fcvtds(tcg_rd, tcg_rn, tcg_env); + write_fp_dreg(s, a->rd, tcg_rd); } + return true; } -/* Floating point data-processing (1 source) - * 31 30 29 28 24 23 22 21 20 15 14 10 9 5 4 0 - * +---+---+---+-----------+------+---+--------+-----------+------+------+ - * | M | 0 | S | 1 1 1 1 0 | type | 1 | opcode | 1 0 0 0 0 | Rn | Rd | - * +---+---+---+-----------+------+---+--------+-----------+------+------+ - */ -static void disas_fp_1src(DisasContext *s, uint32_t insn) +static bool trans_FCVT_s_hs(DisasContext *s, arg_rr *a) { - int mos = extract32(insn, 29, 3); - int type = extract32(insn, 22, 2); - int opcode = extract32(insn, 15, 6); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); + if (fp_access_check(s)) { + TCGv_i32 tmp = read_fp_sreg(s, a->rn); + TCGv_i32 ahp = get_ahp_flag(); + TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); - if (mos) { - goto do_unallocated; + gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp); + /* write_fp_sreg is OK here because top half of result is zero */ + write_fp_sreg(s, a->rd, tmp); } + return true; +} - switch (opcode) { - case 0x4: case 0x5: case 0x7: - { - /* FCVT between half, single and double precision */ - int dtype = extract32(opcode, 0, 2); - if (type == 2 || dtype == type) { - goto do_unallocated; - } - if (!fp_access_check(s)) { - return; - } +static bool trans_FCVT_s_sd(DisasContext *s, arg_rr *a) +{ + if (fp_access_check(s)) { + TCGv_i64 tcg_rn = read_fp_dreg(s, a->rn); + TCGv_i32 tcg_rd = tcg_temp_new_i32(); - handle_fp_fcvt(s, opcode, rd, rn, dtype, type); - break; + gen_helper_vfp_fcvtsd(tcg_rd, tcg_rn, tcg_env); + write_fp_sreg(s, a->rd, tcg_rd); } + return true; +} - default: - do_unallocated: - case 0x0: /* FMOV */ - case 0x1: /* FABS */ - case 0x2: /* FNEG */ - case 0x3: /* FSQRT */ - case 0x6: /* BFCVT */ - case 0x8: /* FRINTN */ - case 0x9: /* FRINTP */ - case 0xa: /* FRINTM */ - case 0xb: /* FRINTZ */ - case 0xc: /* FRINTA */ - case 0xe: /* FRINTX */ - case 0xf: /* FRINTI */ - case 0x10 ... 0x13: /* FRINT{32,64}{X,Z} */ - unallocated_encoding(s); - break; +static bool trans_FCVT_s_hd(DisasContext *s, arg_rr *a) +{ + if (fp_access_check(s)) { + TCGv_i64 tcg_rn = read_fp_dreg(s, a->rn); + TCGv_i32 tcg_rd = tcg_temp_new_i32(); + TCGv_i32 ahp = get_ahp_flag(); + TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); + + gen_helper_vfp_fcvt_f64_to_f16(tcg_rd, tcg_rn, fpst, ahp); + /* write_fp_sreg is OK here because top half of tcg_rd is zero */ + write_fp_sreg(s, a->rd, tcg_rd); } + return true; +} + +static bool trans_FCVT_s_sh(DisasContext *s, arg_rr *a) +{ + if (fp_access_check(s)) { + TCGv_i32 tcg_rn = read_fp_hreg(s, a->rn); + TCGv_i32 tcg_rd = tcg_temp_new_i32(); + TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_FPCR); + TCGv_i32 tcg_ahp = get_ahp_flag(); + + gen_helper_vfp_fcvt_f16_to_f32(tcg_rd, tcg_rn, tcg_fpst, tcg_ahp); + write_fp_sreg(s, a->rd, tcg_rd); + } + return true; +} + +static bool trans_FCVT_s_dh(DisasContext *s, arg_rr *a) +{ + if (fp_access_check(s)) { + TCGv_i32 tcg_rn = read_fp_hreg(s, a->rn); + TCGv_i64 tcg_rd = tcg_temp_new_i64(); + TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_FPCR); + TCGv_i32 tcg_ahp = get_ahp_flag(); + + gen_helper_vfp_fcvt_f16_to_f64(tcg_rd, tcg_rn, tcg_fpst, tcg_ahp); + write_fp_dreg(s, a->rd, tcg_rd); + } + return true; } /* Handle floating point <=> fixed point conversions. Note that we can @@ -8982,7 +8944,7 @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn) break; case 2: /* [15:12] == x100 */ /* Floating point data-processing (1 source) */ - disas_fp_1src(s, insn); + unallocated_encoding(s); /* in decodetree */ break; case 3: /* [15:12] == 1000 */ unallocated_encoding(s); From f568134a57719d22a96163d899614460a89f451b Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:29:59 -0600 Subject: [PATCH 32/85] target/arm: Convert handle_fpfpcvt to decodetree This includes SCVTF, UCVTF, FCVT{N,P,M,Z,A}{S,U}. Remove disas_fp_fixed_conv as those were the last insns decoded by that function. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-33-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 40 ++++ target/arm/tcg/translate-a64.c | 391 ++++++++++++++------------------- 2 files changed, 209 insertions(+), 222 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 211346c4d9..5e170cec7a 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1323,6 +1323,46 @@ FMAXV_s 0110 1110 00 11000 01111 10 ..... ..... @rr_q1e2 FMINV_h 0.00 1110 10 11000 01111 10 ..... ..... @qrr_h FMINV_s 0110 1110 10 11000 01111 10 ..... ..... @rr_q1e2 +# Conversion between floating-point and fixed-point (general register) + +&fcvt rd rn esz sf shift +%fcvt_shift32 10:5 !function=rsub_32 +%fcvt_shift64 10:6 !function=rsub_64 + +@fcvt32 0 ....... .. ...... 1..... rn:5 rd:5 \ + &fcvt sf=0 esz=%esz_hsd shift=%fcvt_shift32 +@fcvt64 1 ....... .. ...... ...... rn:5 rd:5 \ + &fcvt sf=1 esz=%esz_hsd shift=%fcvt_shift64 + +SCVTF_g . 0011110 .. 000010 ...... ..... ..... @fcvt32 +SCVTF_g . 0011110 .. 000010 ...... ..... ..... @fcvt64 +UCVTF_g . 0011110 .. 000011 ...... ..... ..... @fcvt32 +UCVTF_g . 0011110 .. 000011 ...... ..... ..... @fcvt64 + +FCVTZS_g . 0011110 .. 011000 ...... ..... ..... @fcvt32 +FCVTZS_g . 0011110 .. 011000 ...... ..... ..... @fcvt64 +FCVTZU_g . 0011110 .. 011001 ...... ..... ..... @fcvt32 +FCVTZU_g . 0011110 .. 011001 ...... ..... ..... @fcvt64 + +# Conversion between floating-point and integer (general register) + +@icvt sf:1 ....... .. ...... ...... rn:5 rd:5 \ + &fcvt esz=%esz_hsd shift=0 + +SCVTF_g . 0011110 .. 100010 000000 ..... ..... @icvt +UCVTF_g . 0011110 .. 100011 000000 ..... ..... @icvt + +FCVTNS_g . 0011110 .. 100000 000000 ..... ..... @icvt +FCVTNU_g . 0011110 .. 100001 000000 ..... ..... @icvt +FCVTPS_g . 0011110 .. 101000 000000 ..... ..... @icvt +FCVTPU_g . 0011110 .. 101001 000000 ..... ..... @icvt +FCVTMS_g . 0011110 .. 110000 000000 ..... ..... @icvt +FCVTMU_g . 0011110 .. 110001 000000 ..... ..... @icvt +FCVTZS_g . 0011110 .. 111000 000000 ..... ..... @icvt +FCVTZU_g . 0011110 .. 111001 000000 ..... ..... @icvt +FCVTAS_g . 0011110 .. 100100 000000 ..... ..... @icvt +FCVTAU_g . 0011110 .. 100101 000000 ..... ..... @icvt + # Floating-point data processing (1 source) FMOV_s 00011110 .. 1 000000 10000 ..... ..... @rr_hsd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index b31a6d4dff..67227e2676 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8524,227 +8524,196 @@ static bool trans_FCVT_s_dh(DisasContext *s, arg_rr *a) return true; } -/* Handle floating point <=> fixed point conversions. Note that we can - * also deal with fp <=> integer conversions as a special case (scale == 64) - * OPTME: consider handling that special case specially or at least skipping - * the call to scalbn in the helpers for zero shifts. - */ -static void handle_fpfpcvt(DisasContext *s, int rd, int rn, int opcode, - bool itof, int rmode, int scale, int sf, int type) +static bool do_cvtf_scalar(DisasContext *s, MemOp esz, int rd, int shift, + TCGv_i64 tcg_int, bool is_signed) { - bool is_signed = !(opcode & 1); TCGv_ptr tcg_fpstatus; TCGv_i32 tcg_shift, tcg_single; TCGv_i64 tcg_double; - tcg_fpstatus = fpstatus_ptr(type == 3 ? FPST_FPCR_F16 : FPST_FPCR); + tcg_fpstatus = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + tcg_shift = tcg_constant_i32(shift); - tcg_shift = tcg_constant_i32(64 - scale); - - if (itof) { - TCGv_i64 tcg_int = cpu_reg(s, rn); - if (!sf) { - TCGv_i64 tcg_extend = tcg_temp_new_i64(); - - if (is_signed) { - tcg_gen_ext32s_i64(tcg_extend, tcg_int); - } else { - tcg_gen_ext32u_i64(tcg_extend, tcg_int); - } - - tcg_int = tcg_extend; + switch (esz) { + case MO_64: + tcg_double = tcg_temp_new_i64(); + if (is_signed) { + gen_helper_vfp_sqtod(tcg_double, tcg_int, tcg_shift, tcg_fpstatus); + } else { + gen_helper_vfp_uqtod(tcg_double, tcg_int, tcg_shift, tcg_fpstatus); } + write_fp_dreg(s, rd, tcg_double); + break; - 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); - } else { - gen_helper_vfp_uqtod(tcg_double, tcg_int, - tcg_shift, tcg_fpstatus); - } - write_fp_dreg(s, rd, tcg_double); - 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); - } else { - gen_helper_vfp_uqtos(tcg_single, tcg_int, - tcg_shift, tcg_fpstatus); - } - write_fp_sreg(s, rd, 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); - break; - - default: - g_assert_not_reached(); + case MO_32: + tcg_single = tcg_temp_new_i32(); + if (is_signed) { + gen_helper_vfp_sqtos(tcg_single, tcg_int, tcg_shift, tcg_fpstatus); + } else { + gen_helper_vfp_uqtos(tcg_single, tcg_int, tcg_shift, tcg_fpstatus); } - } else { - TCGv_i64 tcg_int = cpu_reg(s, rd); - TCGv_i32 tcg_rmode; + write_fp_sreg(s, rd, tcg_single); + break; - if (extract32(opcode, 2, 1)) { - /* There are too many rounding modes to all fit into rmode, - * so FCVTA[US] is a special case. - */ - rmode = FPROUNDING_TIEAWAY; + case MO_16: + 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); + break; - tcg_rmode = gen_set_rmode(rmode, tcg_fpstatus); - - 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, - tcg_shift, tcg_fpstatus); - } else { - gen_helper_vfp_tosqd(tcg_int, tcg_double, - tcg_shift, tcg_fpstatus); - } - } else { - if (!sf) { - gen_helper_vfp_tould(tcg_int, tcg_double, - tcg_shift, tcg_fpstatus); - } else { - gen_helper_vfp_touqd(tcg_int, tcg_double, - tcg_shift, tcg_fpstatus); - } - } - if (!sf) { - tcg_gen_ext32u_i64(tcg_int, tcg_int); - } - break; - - case 0: /* float32 */ - tcg_single = read_fp_sreg(s, rn); - if (sf) { - if (is_signed) { - gen_helper_vfp_tosqs(tcg_int, tcg_single, - tcg_shift, tcg_fpstatus); - } else { - gen_helper_vfp_touqs(tcg_int, tcg_single, - tcg_shift, tcg_fpstatus); - } - } else { - TCGv_i32 tcg_dest = tcg_temp_new_i32(); - if (is_signed) { - gen_helper_vfp_tosls(tcg_dest, tcg_single, - tcg_shift, tcg_fpstatus); - } else { - gen_helper_vfp_touls(tcg_dest, tcg_single, - tcg_shift, tcg_fpstatus); - } - tcg_gen_extu_i32_i64(tcg_int, tcg_dest); - } - 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); - } - break; - - default: - g_assert_not_reached(); - } - - gen_restore_rmode(tcg_rmode, tcg_fpstatus); + default: + g_assert_not_reached(); } + return true; } -/* Floating point <-> fixed point conversions - * 31 30 29 28 24 23 22 21 20 19 18 16 15 10 9 5 4 0 - * +----+---+---+-----------+------+---+-------+--------+-------+------+------+ - * | sf | 0 | S | 1 1 1 1 0 | type | 0 | rmode | opcode | scale | Rn | Rd | - * +----+---+---+-----------+------+---+-------+--------+-------+------+------+ - */ -static void disas_fp_fixed_conv(DisasContext *s, uint32_t insn) +static bool do_cvtf_g(DisasContext *s, arg_fcvt *a, bool is_signed) { - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int scale = extract32(insn, 10, 6); - int opcode = extract32(insn, 16, 3); - int rmode = extract32(insn, 19, 2); - int type = extract32(insn, 22, 2); - bool sbit = extract32(insn, 29, 1); - bool sf = extract32(insn, 31, 1); - bool itof; + TCGv_i64 tcg_int; + int check = fp_access_check_scalar_hsd(s, a->esz); - if (sbit || (!sf && scale < 32)) { - unallocated_encoding(s); - return; + if (check <= 0) { + return check == 0; } - switch (type) { - case 0: /* float32 */ - case 1: /* float64 */ - break; - case 3: /* float16 */ - if (dc_isar_feature(aa64_fp16, s)) { - break; + if (a->sf) { + tcg_int = cpu_reg(s, a->rn); + } else { + tcg_int = read_cpu_reg(s, a->rn, true); + if (is_signed) { + tcg_gen_ext32s_i64(tcg_int, tcg_int); + } else { + tcg_gen_ext32u_i64(tcg_int, tcg_int); } - /* fallthru */ - default: - unallocated_encoding(s); - return; } - - switch ((rmode << 3) | opcode) { - case 0x2: /* SCVTF */ - case 0x3: /* UCVTF */ - itof = true; - break; - case 0x18: /* FCVTZS */ - case 0x19: /* FCVTZU */ - itof = false; - break; - default: - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - handle_fpfpcvt(s, rd, rn, opcode, itof, FPROUNDING_ZERO, scale, sf, type); + return do_cvtf_scalar(s, a->esz, a->rd, a->shift, tcg_int, is_signed); } +TRANS(SCVTF_g, do_cvtf_g, a, true) +TRANS(UCVTF_g, do_cvtf_g, a, false) + +static void do_fcvt_scalar(DisasContext *s, MemOp out, MemOp esz, + TCGv_i64 tcg_out, int shift, int rn, + ARMFPRounding rmode) +{ + TCGv_ptr tcg_fpstatus; + TCGv_i32 tcg_shift, tcg_rmode, tcg_single; + + tcg_fpstatus = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + tcg_shift = tcg_constant_i32(shift); + tcg_rmode = gen_set_rmode(rmode, tcg_fpstatus); + + switch (esz) { + case MO_64: + read_vec_element(s, tcg_out, rn, 0, MO_64); + switch (out) { + case MO_64 | MO_SIGN: + gen_helper_vfp_tosqd(tcg_out, tcg_out, tcg_shift, tcg_fpstatus); + break; + case MO_64: + gen_helper_vfp_touqd(tcg_out, tcg_out, tcg_shift, tcg_fpstatus); + break; + case MO_32 | MO_SIGN: + gen_helper_vfp_tosld(tcg_out, tcg_out, tcg_shift, tcg_fpstatus); + break; + case MO_32: + gen_helper_vfp_tould(tcg_out, tcg_out, tcg_shift, tcg_fpstatus); + break; + default: + g_assert_not_reached(); + } + break; + + case MO_32: + tcg_single = read_fp_sreg(s, rn); + switch (out) { + case MO_64 | MO_SIGN: + gen_helper_vfp_tosqs(tcg_out, tcg_single, tcg_shift, tcg_fpstatus); + break; + case MO_64: + gen_helper_vfp_touqs(tcg_out, tcg_single, tcg_shift, tcg_fpstatus); + break; + case MO_32 | MO_SIGN: + gen_helper_vfp_tosls(tcg_single, tcg_single, + tcg_shift, tcg_fpstatus); + tcg_gen_extu_i32_i64(tcg_out, tcg_single); + break; + case MO_32: + gen_helper_vfp_touls(tcg_single, tcg_single, + tcg_shift, tcg_fpstatus); + tcg_gen_extu_i32_i64(tcg_out, tcg_single); + break; + default: + g_assert_not_reached(); + } + break; + + case MO_16: + tcg_single = read_fp_hreg(s, rn); + switch (out) { + case MO_64 | MO_SIGN: + gen_helper_vfp_tosqh(tcg_out, tcg_single, tcg_shift, tcg_fpstatus); + break; + case MO_64: + gen_helper_vfp_touqh(tcg_out, tcg_single, tcg_shift, tcg_fpstatus); + break; + case MO_32 | MO_SIGN: + gen_helper_vfp_toslh(tcg_single, tcg_single, + tcg_shift, tcg_fpstatus); + tcg_gen_extu_i32_i64(tcg_out, tcg_single); + break; + case MO_32: + gen_helper_vfp_toulh(tcg_single, tcg_single, + tcg_shift, tcg_fpstatus); + tcg_gen_extu_i32_i64(tcg_out, tcg_single); + break; + default: + g_assert_not_reached(); + } + break; + + default: + g_assert_not_reached(); + } + + gen_restore_rmode(tcg_rmode, tcg_fpstatus); +} + +static bool do_fcvt_g(DisasContext *s, arg_fcvt *a, + ARMFPRounding rmode, bool is_signed) +{ + TCGv_i64 tcg_int; + int check = fp_access_check_scalar_hsd(s, a->esz); + + if (check <= 0) { + return check == 0; + } + + tcg_int = cpu_reg(s, a->rd); + do_fcvt_scalar(s, (a->sf ? MO_64 : MO_32) | (is_signed ? MO_SIGN : 0), + a->esz, tcg_int, a->shift, a->rn, rmode); + + if (!a->sf) { + tcg_gen_ext32u_i64(tcg_int, tcg_int); + } + return true; +} + +TRANS(FCVTNS_g, do_fcvt_g, a, FPROUNDING_TIEEVEN, true) +TRANS(FCVTNU_g, do_fcvt_g, a, FPROUNDING_TIEEVEN, false) +TRANS(FCVTPS_g, do_fcvt_g, a, FPROUNDING_POSINF, true) +TRANS(FCVTPU_g, do_fcvt_g, a, FPROUNDING_POSINF, false) +TRANS(FCVTMS_g, do_fcvt_g, a, FPROUNDING_NEGINF, true) +TRANS(FCVTMU_g, do_fcvt_g, a, FPROUNDING_NEGINF, false) +TRANS(FCVTZS_g, do_fcvt_g, a, FPROUNDING_ZERO, true) +TRANS(FCVTZU_g, do_fcvt_g, a, FPROUNDING_ZERO, false) +TRANS(FCVTAS_g, do_fcvt_g, a, FPROUNDING_TIEAWAY, true) +TRANS(FCVTAU_g, do_fcvt_g, a, FPROUNDING_TIEAWAY, false) + static void handle_fmov(DisasContext *s, int rd, int rn, int type, bool itof) { /* FMOV: gpr to or from float, double, or top half of quad fp reg, @@ -8844,33 +8813,11 @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) switch (opcode) { case 2: /* SCVTF */ case 3: /* UCVTF */ - itof = true; - /* fallthru */ case 4: /* FCVTAS */ case 5: /* FCVTAU */ - if (rmode != 0) { - goto do_unallocated; - } - /* fallthru */ case 0: /* FCVT[NPMZ]S */ case 1: /* FCVT[NPMZ]U */ - switch (type) { - case 0: /* float32 */ - case 1: /* float64 */ - break; - case 3: /* float16 */ - if (!dc_isar_feature(aa64_fp16, s)) { - goto do_unallocated; - } - break; - default: - goto do_unallocated; - } - if (!fp_access_check(s)) { - return; - } - handle_fpfpcvt(s, rd, rn, opcode, itof, rmode, 64, sf, type); - break; + goto do_unallocated; default: switch (sf << 7 | type << 5 | rmode << 3 | opcode) { @@ -8924,7 +8871,7 @@ static void disas_data_proc_fp(DisasContext *s, uint32_t insn) unallocated_encoding(s); /* in decodetree */ } else if (extract32(insn, 21, 1) == 0) { /* Floating point to fixed point conversions */ - disas_fp_fixed_conv(s, insn); + unallocated_encoding(s); /* in decodetree */ } else { switch (extract32(insn, 10, 2)) { case 1: /* Floating point conditional compare */ From a769f854e6d37818d434958696e62503a5606ed5 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:00 -0600 Subject: [PATCH 33/85] target/arm: Convert FJCVTZS to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-34-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 2 ++ target/arm/tcg/translate-a64.c | 41 +++++++++++++++++----------------- 2 files changed, 22 insertions(+), 21 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 5e170cec7a..cd10961618 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1363,6 +1363,8 @@ FCVTZU_g . 0011110 .. 111001 000000 ..... ..... @icvt FCVTAS_g . 0011110 .. 100100 000000 ..... ..... @icvt FCVTAU_g . 0011110 .. 100101 000000 ..... ..... @icvt +FJCVTZS 0 0011110 01 111110 000000 ..... ..... @rr + # Floating-point data processing (1 source) FMOV_s 00011110 .. 1 000000 10000 ..... ..... @rr_hsd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 67227e2676..d260b45ddb 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8714,6 +8714,26 @@ TRANS(FCVTZU_g, do_fcvt_g, a, FPROUNDING_ZERO, false) TRANS(FCVTAS_g, do_fcvt_g, a, FPROUNDING_TIEAWAY, true) TRANS(FCVTAU_g, do_fcvt_g, a, FPROUNDING_TIEAWAY, false) +static bool trans_FJCVTZS(DisasContext *s, arg_FJCVTZS *a) +{ + if (!dc_isar_feature(aa64_jscvt, s)) { + return false; + } + if (fp_access_check(s)) { + TCGv_i64 t = read_fp_dreg(s, a->rn); + TCGv_ptr fpstatus = fpstatus_ptr(FPST_FPCR); + + gen_helper_fjcvtzs(t, t, fpstatus); + + tcg_gen_ext32u_i64(cpu_reg(s, a->rd), t); + tcg_gen_extrh_i64_i32(cpu_ZF, t); + tcg_gen_movi_i32(cpu_CF, 0); + tcg_gen_movi_i32(cpu_NF, 0); + tcg_gen_movi_i32(cpu_VF, 0); + } + return true; +} + static void handle_fmov(DisasContext *s, int rd, int rn, int type, bool itof) { /* FMOV: gpr to or from float, double, or top half of quad fp reg, @@ -8775,20 +8795,6 @@ static void handle_fmov(DisasContext *s, int rd, int rn, int type, bool itof) } } -static void handle_fjcvtzs(DisasContext *s, int rd, int rn) -{ - TCGv_i64 t = read_fp_dreg(s, rn); - TCGv_ptr fpstatus = fpstatus_ptr(FPST_FPCR); - - gen_helper_fjcvtzs(t, t, fpstatus); - - tcg_gen_ext32u_i64(cpu_reg(s, rd), t); - tcg_gen_extrh_i64_i32(cpu_ZF, t); - tcg_gen_movi_i32(cpu_CF, 0); - tcg_gen_movi_i32(cpu_NF, 0); - tcg_gen_movi_i32(cpu_VF, 0); -} - /* Floating point <-> integer conversions * 31 30 29 28 24 23 22 21 20 19 18 16 15 10 9 5 4 0 * +----+---+---+-----------+------+---+-------+-----+-------------+----+----+ @@ -8843,13 +8849,6 @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) break; case 0b00111110: /* FJCVTZS */ - if (!dc_isar_feature(aa64_jscvt, s)) { - goto do_unallocated; - } else if (fp_access_check(s)) { - handle_fjcvtzs(s, rd, rn); - } - break; - default: do_unallocated: unallocated_encoding(s); From 5f4fe0e6580d861013de73e36692ce811860fc82 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:01 -0600 Subject: [PATCH 34/85] target/arm: Convert handle_fmov to decodetree Remove disas_fp_int_conv and disas_data_proc_fp as these were the last insns decoded by those functions. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-35-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 14 ++ target/arm/tcg/translate-a64.c | 232 ++++++++++----------------------- 2 files changed, 86 insertions(+), 160 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index cd10961618..5b9f7caa7f 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1365,6 +1365,20 @@ FCVTAU_g . 0011110 .. 100101 000000 ..... ..... @icvt FJCVTZS 0 0011110 01 111110 000000 ..... ..... @rr +FMOV_ws 0 0011110 00 100110 000000 ..... ..... @rr +FMOV_sw 0 0011110 00 100111 000000 ..... ..... @rr + +FMOV_xd 1 0011110 01 100110 000000 ..... ..... @rr +FMOV_dx 1 0011110 01 100111 000000 ..... ..... @rr + +# Move to/from upper half of 128-bit +FMOV_xu 1 0011110 10 101110 000000 ..... ..... @rr +FMOV_ux 1 0011110 10 101111 000000 ..... ..... @rr + +# Half-precision allows both sf=0 and sf=1 with identical results +FMOV_xh - 0011110 11 100110 000000 ..... ..... @rr +FMOV_hx - 0011110 11 100111 000000 ..... ..... @rr + # Floating-point data processing (1 source) FMOV_s 00011110 .. 1 000000 10000 ..... ..... @rr_hsd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index d260b45ddb..95bb2b1ca9 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8734,175 +8734,87 @@ static bool trans_FJCVTZS(DisasContext *s, arg_FJCVTZS *a) return true; } -static void handle_fmov(DisasContext *s, int rd, int rn, int type, bool itof) +static bool trans_FMOV_hx(DisasContext *s, arg_rr *a) { - /* FMOV: gpr to or from float, double, or top half of quad fp reg, - * without conversion. - */ - - if (itof) { - TCGv_i64 tcg_rn = cpu_reg(s, rn); - TCGv_i64 tmp; - - switch (type) { - case 0: - /* 32 bit */ - tmp = tcg_temp_new_i64(); - tcg_gen_ext32u_i64(tmp, tcg_rn); - write_fp_dreg(s, rd, tmp); - break; - case 1: - /* 64 bit */ - write_fp_dreg(s, rd, tcg_rn); - break; - case 2: - /* 64 bit to top half. */ - tcg_gen_st_i64(tcg_rn, tcg_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); - break; - default: - g_assert_not_reached(); - } - } else { - TCGv_i64 tcg_rd = cpu_reg(s, rd); - - switch (type) { - case 0: - /* 32 bit */ - tcg_gen_ld32u_i64(tcg_rd, tcg_env, fp_reg_offset(s, rn, MO_32)); - break; - case 1: - /* 64 bit */ - tcg_gen_ld_i64(tcg_rd, tcg_env, fp_reg_offset(s, rn, MO_64)); - break; - case 2: - /* 64 bits from top half */ - tcg_gen_ld_i64(tcg_rd, tcg_env, fp_reg_hi_offset(s, rn)); - break; - case 3: - /* 16 bit */ - tcg_gen_ld16u_i64(tcg_rd, tcg_env, fp_reg_offset(s, rn, MO_16)); - break; - default: - g_assert_not_reached(); - } + if (!dc_isar_feature(aa64_fp16, s)) { + return false; } + if (fp_access_check(s)) { + TCGv_i64 tcg_rn = cpu_reg(s, a->rn); + TCGv_i64 tmp = tcg_temp_new_i64(); + tcg_gen_ext16u_i64(tmp, tcg_rn); + write_fp_dreg(s, a->rd, tmp); + } + return true; } -/* Floating point <-> integer conversions - * 31 30 29 28 24 23 22 21 20 19 18 16 15 10 9 5 4 0 - * +----+---+---+-----------+------+---+-------+-----+-------------+----+----+ - * | sf | 0 | S | 1 1 1 1 0 | type | 1 | rmode | opc | 0 0 0 0 0 0 | Rn | Rd | - * +----+---+---+-----------+------+---+-------+-----+-------------+----+----+ - */ -static void disas_fp_int_conv(DisasContext *s, uint32_t insn) +static bool trans_FMOV_sw(DisasContext *s, arg_rr *a) { - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int opcode = extract32(insn, 16, 3); - int rmode = extract32(insn, 19, 2); - int type = extract32(insn, 22, 2); - bool sbit = extract32(insn, 29, 1); - bool sf = extract32(insn, 31, 1); - bool itof = false; - - if (sbit) { - goto do_unallocated; - } - - switch (opcode) { - case 2: /* SCVTF */ - case 3: /* UCVTF */ - case 4: /* FCVTAS */ - case 5: /* FCVTAU */ - case 0: /* FCVT[NPMZ]S */ - case 1: /* FCVT[NPMZ]U */ - goto do_unallocated; - - default: - switch (sf << 7 | type << 5 | rmode << 3 | opcode) { - case 0b01100110: /* FMOV half <-> 32-bit int */ - case 0b01100111: - case 0b11100110: /* FMOV half <-> 64-bit int */ - case 0b11100111: - if (!dc_isar_feature(aa64_fp16, s)) { - goto do_unallocated; - } - /* fallthru */ - case 0b00000110: /* FMOV 32-bit */ - case 0b00000111: - case 0b10100110: /* FMOV 64-bit */ - case 0b10100111: - case 0b11001110: /* FMOV top half of 128-bit */ - case 0b11001111: - if (!fp_access_check(s)) { - return; - } - itof = opcode & 1; - handle_fmov(s, rd, rn, type, itof); - break; - - case 0b00111110: /* FJCVTZS */ - default: - do_unallocated: - unallocated_encoding(s); - return; - } - break; + if (fp_access_check(s)) { + TCGv_i64 tcg_rn = cpu_reg(s, a->rn); + TCGv_i64 tmp = tcg_temp_new_i64(); + tcg_gen_ext32u_i64(tmp, tcg_rn); + write_fp_dreg(s, a->rd, tmp); } + return true; } -/* FP-specific subcases of table C3-6 (SIMD and FP data processing) - * 31 30 29 28 25 24 0 - * +---+---+---+---------+-----------------------------+ - * | | 0 | | 1 1 1 1 | | - * +---+---+---+---------+-----------------------------+ - */ -static void disas_data_proc_fp(DisasContext *s, uint32_t insn) +static bool trans_FMOV_dx(DisasContext *s, arg_rr *a) { - if (extract32(insn, 24, 1)) { - unallocated_encoding(s); /* in decodetree */ - } else if (extract32(insn, 21, 1) == 0) { - /* Floating point to fixed point conversions */ - unallocated_encoding(s); /* in decodetree */ - } else { - switch (extract32(insn, 10, 2)) { - case 1: /* Floating point conditional compare */ - case 2: /* Floating point data-processing (2 source) */ - case 3: /* Floating point conditional select */ - unallocated_encoding(s); /* in decodetree */ - break; - case 0: - switch (ctz32(extract32(insn, 12, 4))) { - case 0: /* [15:12] == xxx1 */ - /* Floating point immediate */ - unallocated_encoding(s); /* in decodetree */ - break; - case 1: /* [15:12] == xx10 */ - /* Floating point compare */ - unallocated_encoding(s); /* in decodetree */ - break; - case 2: /* [15:12] == x100 */ - /* Floating point data-processing (1 source) */ - unallocated_encoding(s); /* in decodetree */ - break; - case 3: /* [15:12] == 1000 */ - unallocated_encoding(s); - break; - default: /* [15:12] == 0000 */ - /* Floating point <-> integer conversions */ - disas_fp_int_conv(s, insn); - break; - } - break; - } + if (fp_access_check(s)) { + TCGv_i64 tcg_rn = cpu_reg(s, a->rn); + write_fp_dreg(s, a->rd, tcg_rn); } + return true; +} + +static bool trans_FMOV_ux(DisasContext *s, arg_rr *a) +{ + if (fp_access_check(s)) { + TCGv_i64 tcg_rn = cpu_reg(s, a->rn); + tcg_gen_st_i64(tcg_rn, tcg_env, fp_reg_hi_offset(s, a->rd)); + clear_vec_high(s, true, a->rd); + } + return true; +} + +static bool trans_FMOV_xh(DisasContext *s, arg_rr *a) +{ + if (!dc_isar_feature(aa64_fp16, s)) { + return false; + } + if (fp_access_check(s)) { + TCGv_i64 tcg_rd = cpu_reg(s, a->rd); + tcg_gen_ld16u_i64(tcg_rd, tcg_env, fp_reg_offset(s, a->rn, MO_16)); + } + return true; +} + +static bool trans_FMOV_ws(DisasContext *s, arg_rr *a) +{ + if (fp_access_check(s)) { + TCGv_i64 tcg_rd = cpu_reg(s, a->rd); + tcg_gen_ld32u_i64(tcg_rd, tcg_env, fp_reg_offset(s, a->rn, MO_32)); + } + return true; +} + +static bool trans_FMOV_xd(DisasContext *s, arg_rr *a) +{ + if (fp_access_check(s)) { + TCGv_i64 tcg_rd = cpu_reg(s, a->rd); + tcg_gen_ld_i64(tcg_rd, tcg_env, fp_reg_offset(s, a->rn, MO_64)); + } + return true; +} + +static bool trans_FMOV_xu(DisasContext *s, arg_rr *a) +{ + if (fp_access_check(s)) { + TCGv_i64 tcg_rd = cpu_reg(s, a->rd); + tcg_gen_ld_i64(tcg_rd, tcg_env, fp_reg_hi_offset(s, a->rn)); + } + return true; } /* Common vector code for handling integer to FP conversion */ @@ -10821,7 +10733,7 @@ static void disas_data_proc_simd(DisasContext *s, uint32_t insn) static void disas_data_proc_simd_fp(DisasContext *s, uint32_t insn) { if (extract32(insn, 28, 1) == 1 && extract32(insn, 30, 1) == 0) { - disas_data_proc_fp(s, insn); + unallocated_encoding(s); /* in decodetree */ } else { /* SIMD, including crypto */ disas_data_proc_simd(s, insn); From df79bfcf75d64dbd96b71e01618fc363925251cb Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:02 -0600 Subject: [PATCH 35/85] target/arm: Convert SQABS, SQNEG to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-36-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 11 +++ target/arm/tcg/translate-a64.c | 123 +++++++++++++++++++++------------ 2 files changed, 89 insertions(+), 45 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 5b9f7caa7f..17ecdac9db 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -47,6 +47,7 @@ @rr_h ........ ... ..... ...... rn:5 rd:5 &rr_e esz=1 @rr_s ........ ... ..... ...... rn:5 rd:5 &rr_e esz=2 @rr_d ........ ... ..... ...... rn:5 rd:5 &rr_e esz=3 +@rr_e ........ esz:2 . ..... ...... rn:5 rd:5 &rr_e @rr_sd ........ ... ..... ...... rn:5 rd:5 &rr_e esz=%esz_sd @rr_hsd ........ ... ..... ...... rn:5 rd:5 &rr_e esz=%esz_hsd @@ -1626,3 +1627,13 @@ UQRSHRN_si 0111 11110 .... ... 10011 1 ..... ..... @shri_s SQRSHRUN_si 0111 11110 .... ... 10001 1 ..... ..... @shri_b SQRSHRUN_si 0111 11110 .... ... 10001 1 ..... ..... @shri_h SQRSHRUN_si 0111 11110 .... ... 10001 1 ..... ..... @shri_s + +# Advanced SIMD scalar two-register miscellaneous + +SQABS_s 0101 1110 ..1 00000 01111 0 ..... ..... @rr_e +SQNEG_s 0111 1110 ..1 00000 01111 0 ..... ..... @rr_e + +# Advanced SIMD two-register miscellaneous + +SQABS_v 0.00 1110 ..1 00000 01111 0 ..... ..... @qrr_e +SQNEG_v 0.10 1110 ..1 00000 01111 0 ..... ..... @qrr_e diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 95bb2b1ca9..9bb9668d11 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8817,6 +8817,78 @@ static bool trans_FMOV_xu(DisasContext *s, arg_rr *a) return true; } +typedef struct ENVScalar1 { + NeonGenOneOpEnvFn *gen_bhs[3]; + NeonGenOne64OpEnvFn *gen_d; +} ENVScalar1; + +static bool do_env_scalar1(DisasContext *s, arg_rr_e *a, const ENVScalar1 *f) +{ + if (!fp_access_check(s)) { + return true; + } + if (a->esz == MO_64) { + TCGv_i64 t = read_fp_dreg(s, a->rn); + f->gen_d(t, tcg_env, t); + write_fp_dreg(s, a->rd, t); + } else { + TCGv_i32 t = tcg_temp_new_i32(); + + read_vec_element_i32(s, t, a->rn, 0, a->esz); + f->gen_bhs[a->esz](t, tcg_env, t); + write_fp_sreg(s, a->rd, t); + } + return true; +} + +static bool do_env_vector1(DisasContext *s, arg_qrr_e *a, const ENVScalar1 *f) +{ + if (a->esz == MO_64 && !a->q) { + return false; + } + if (!fp_access_check(s)) { + return true; + } + if (a->esz == MO_64) { + TCGv_i64 t = tcg_temp_new_i64(); + + for (int i = 0; i < 2; ++i) { + read_vec_element(s, t, a->rn, i, MO_64); + f->gen_d(t, tcg_env, t); + write_vec_element(s, t, a->rd, i, MO_64); + } + } else { + TCGv_i32 t = tcg_temp_new_i32(); + int n = (a->q ? 16 : 8) >> a->esz; + + for (int i = 0; i < n; ++i) { + read_vec_element_i32(s, t, a->rn, i, a->esz); + f->gen_bhs[a->esz](t, tcg_env, t); + write_vec_element_i32(s, t, a->rd, i, a->esz); + } + } + clear_vec_high(s, a->q, a->rd); + return true; +} + +static const ENVScalar1 f_scalar_sqabs = { + { gen_helper_neon_qabs_s8, + gen_helper_neon_qabs_s16, + gen_helper_neon_qabs_s32 }, + gen_helper_neon_qabs_s64, +}; +TRANS(SQABS_s, do_env_scalar1, a, &f_scalar_sqabs) +TRANS(SQABS_v, do_env_vector1, a, &f_scalar_sqabs) + +static const ENVScalar1 f_scalar_sqneg = { + { gen_helper_neon_qneg_s8, + gen_helper_neon_qneg_s16, + gen_helper_neon_qneg_s32 }, + gen_helper_neon_qneg_s64, +}; +TRANS(SQNEG_s, do_env_scalar1, a, &f_scalar_sqneg) +TRANS(SQNEG_v, do_env_vector1, a, &f_scalar_sqneg) + /* Common vector code for handling integer to FP conversion */ static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn, int elements, int is_signed, @@ -9129,13 +9201,6 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, */ tcg_gen_not_i64(tcg_rd, tcg_rn); break; - case 0x7: /* SQABS, SQNEG */ - if (u) { - gen_helper_neon_qneg_s64(tcg_rd, tcg_env, tcg_rn); - } else { - gen_helper_neon_qabs_s64(tcg_rd, tcg_env, tcg_rn); - } - break; case 0xa: /* CMLT */ cond = TCG_COND_LT; do_cmop: @@ -9198,6 +9263,7 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, gen_helper_frint64_d(tcg_rd, tcg_rn, tcg_fpstatus); break; default: + case 0x7: /* SQABS, SQNEG */ g_assert_not_reached(); } } @@ -9540,8 +9606,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) TCGv_ptr tcg_fpstatus; switch (opcode) { - case 0x7: /* SQABS / SQNEG */ - break; case 0xa: /* CMLT */ if (u) { unallocated_encoding(s); @@ -9640,6 +9704,7 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) break; default: case 0x3: /* USQADD / SUQADD */ + case 0x7: /* SQABS / SQNEG */ unallocated_encoding(s); return; } @@ -9669,18 +9734,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) read_vec_element_i32(s, tcg_rn, rn, 0, size); switch (opcode) { - case 0x7: /* SQABS, SQNEG */ - { - NeonGenOneOpEnvFn *genfn; - static NeonGenOneOpEnvFn * const fns[3][2] = { - { gen_helper_neon_qabs_s8, gen_helper_neon_qneg_s8 }, - { gen_helper_neon_qabs_s16, gen_helper_neon_qneg_s16 }, - { gen_helper_neon_qabs_s32, gen_helper_neon_qneg_s32 }, - }; - genfn = fns[size][u]; - genfn(tcg_rd, tcg_env, tcg_rn); - break; - } case 0x1a: /* FCVTNS */ case 0x1b: /* FCVTMS */ case 0x1c: /* FCVTAS */ @@ -9698,6 +9751,7 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) tcg_fpstatus); break; default: + case 0x7: /* SQABS, SQNEG */ g_assert_not_reached(); } @@ -10055,12 +10109,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) return; } break; - case 0x7: /* SQABS, SQNEG */ - if (size == 3 && !is_q) { - unallocated_encoding(s); - return; - } - break; case 0xc ... 0xf: case 0x16 ... 0x1f: { @@ -10231,6 +10279,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } default: case 0x3: /* SUQADD, USQADD */ + case 0x7: /* SQABS, SQNEG */ unallocated_encoding(s); return; } @@ -10321,13 +10370,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) tcg_gen_clrsb_i32(tcg_res, tcg_op); } break; - case 0x7: /* SQABS, SQNEG */ - if (u) { - gen_helper_neon_qneg_s32(tcg_res, tcg_env, tcg_op); - } else { - gen_helper_neon_qabs_s32(tcg_res, tcg_env, tcg_op); - } - break; case 0x2f: /* FABS */ gen_vfp_abss(tcg_res, tcg_op); break; @@ -10376,6 +10418,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) gen_helper_frint64_s(tcg_res, tcg_op, tcg_fpstatus); break; default: + case 0x7: /* SQABS, SQNEG */ g_assert_not_reached(); } } else { @@ -10391,17 +10434,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) gen_helper_neon_cnt_u8(tcg_res, tcg_op); } break; - case 0x7: /* SQABS, SQNEG */ - { - NeonGenOneOpEnvFn *genfn; - static NeonGenOneOpEnvFn * const fns[2][2] = { - { gen_helper_neon_qabs_s8, gen_helper_neon_qneg_s8 }, - { gen_helper_neon_qabs_s16, gen_helper_neon_qneg_s16 }, - }; - genfn = fns[size][u]; - genfn(tcg_res, tcg_env, tcg_op); - break; - } case 0x4: /* CLS, CLZ */ if (u) { if (size == 0) { @@ -10418,6 +10450,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } break; default: + case 0x7: /* SQABS, SQNEG */ g_assert_not_reached(); } } From 9187b72cff0372270d5b02cfd2e2ade10daafb4c Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:03 -0600 Subject: [PATCH 36/85] target/arm: Convert ABS, NEG to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-37-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 4 +++ target/arm/tcg/translate-a64.c | 46 +++++++++++++++++++++++----------- 2 files changed, 35 insertions(+), 15 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 17ecdac9db..f112951df7 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1632,8 +1632,12 @@ SQRSHRUN_si 0111 11110 .... ... 10001 1 ..... ..... @shri_s SQABS_s 0101 1110 ..1 00000 01111 0 ..... ..... @rr_e SQNEG_s 0111 1110 ..1 00000 01111 0 ..... ..... @rr_e +ABS_s 0101 1110 111 00000 10111 0 ..... ..... @rr +NEG_s 0111 1110 111 00000 10111 0 ..... ..... @rr # Advanced SIMD two-register miscellaneous SQABS_v 0.00 1110 ..1 00000 01111 0 ..... ..... @qrr_e SQNEG_v 0.10 1110 ..1 00000 01111 0 ..... ..... @qrr_e +ABS_v 0.00 1110 ..1 00000 10111 0 ..... ..... @qrr_e +NEG_v 0.10 1110 ..1 00000 10111 0 ..... ..... @qrr_e diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 9bb9668d11..c697f0e944 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8889,6 +8889,33 @@ static const ENVScalar1 f_scalar_sqneg = { TRANS(SQNEG_s, do_env_scalar1, a, &f_scalar_sqneg) TRANS(SQNEG_v, do_env_vector1, a, &f_scalar_sqneg) +static bool do_scalar1_d(DisasContext *s, arg_rr *a, ArithOneOp *f) +{ + if (fp_access_check(s)) { + TCGv_i64 t = read_fp_dreg(s, a->rn); + f(t, t); + write_fp_dreg(s, a->rd, t); + } + return true; +} + +TRANS(ABS_s, do_scalar1_d, a, tcg_gen_abs_i64) +TRANS(NEG_s, do_scalar1_d, a, tcg_gen_neg_i64) + +static bool do_gvec_fn2(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) +{ + if (!a->q && a->esz == MO_64) { + return false; + } + if (fp_access_check(s)) { + gen_gvec_fn2(s, a->q, a->rd, a->rn, fn, a->esz); + } + return true; +} + +TRANS(ABS_v, do_gvec_fn2, a, tcg_gen_gvec_abs) +TRANS(NEG_v, do_gvec_fn2, a, tcg_gen_gvec_neg) + /* Common vector code for handling integer to FP conversion */ static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn, int elements, int is_signed, @@ -9213,13 +9240,6 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, case 0x9: /* CMEQ, CMLE */ cond = u ? TCG_COND_LE : TCG_COND_EQ; goto do_cmop; - case 0xb: /* ABS, NEG */ - if (u) { - tcg_gen_neg_i64(tcg_rd, tcg_rn); - } else { - tcg_gen_abs_i64(tcg_rd, tcg_rn); - } - break; case 0x2f: /* FABS */ gen_vfp_absd(tcg_rd, tcg_rn); break; @@ -9264,6 +9284,7 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, break; default: case 0x7: /* SQABS, SQNEG */ + case 0xb: /* ABS, NEG */ g_assert_not_reached(); } } @@ -9614,7 +9635,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) /* fall through */ case 0x8: /* CMGT, CMGE */ case 0x9: /* CMEQ, CMLE */ - case 0xb: /* ABS, NEG */ if (size != 3) { unallocated_encoding(s); return; @@ -9705,6 +9725,7 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) default: case 0x3: /* USQADD / SUQADD */ case 0x7: /* SQABS / SQNEG */ + case 0xb: /* ABS, NEG */ unallocated_encoding(s); return; } @@ -10103,7 +10124,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) /* fall through */ case 0x8: /* CMGT, CMGE */ case 0x9: /* CMEQ, CMLE */ - case 0xb: /* ABS, NEG */ if (size == 3 && !is_q) { unallocated_encoding(s); return; @@ -10280,6 +10300,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) default: case 0x3: /* SUQADD, USQADD */ case 0x7: /* SQABS, SQNEG */ + case 0xb: /* ABS, NEG */ unallocated_encoding(s); return; } @@ -10324,12 +10345,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_clt0, size); return; case 0xb: - if (u) { /* ABS, NEG */ - gen_gvec_fn2(s, is_q, rd, rn, tcg_gen_gvec_neg, size); - } else { - gen_gvec_fn2(s, is_q, rd, rn, tcg_gen_gvec_abs, size); - } - return; + g_assert_not_reached(); } if (size == 3) { From 4fedfb483b35cbe98863f0dafb908727676292b5 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:04 -0600 Subject: [PATCH 37/85] target/arm: Introduce gen_gvec_cls, gen_gvec_clz MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Add gvec interfaces for CLS and CLZ operations. Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-38-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/gengvec.c | 35 +++++++++++++++++++++++++++++++++ target/arm/tcg/translate-a64.c | 29 +++++++-------------------- target/arm/tcg/translate-neon.c | 29 ++------------------------- target/arm/tcg/translate.h | 5 +++++ 4 files changed, 49 insertions(+), 49 deletions(-) diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index f652520b65..834b2961c0 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -2358,3 +2358,38 @@ void gen_gvec_urhadd(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, assert(vece <= MO_32); tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, opr_sz, max_sz, &g[vece]); } + +void gen_gvec_cls(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + static const GVecGen2 g[] = { + { .fni4 = gen_helper_neon_cls_s8, + .vece = MO_8 }, + { .fni4 = gen_helper_neon_cls_s16, + .vece = MO_16 }, + { .fni4 = tcg_gen_clrsb_i32, + .vece = MO_32 }, + }; + assert(vece <= MO_32); + tcg_gen_gvec_2(rd_ofs, rn_ofs, opr_sz, max_sz, &g[vece]); +} + +static void gen_clz32_i32(TCGv_i32 d, TCGv_i32 n) +{ + tcg_gen_clzi_i32(d, n, 32); +} + +void gen_gvec_clz(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + static const GVecGen2 g[] = { + { .fni4 = gen_helper_neon_clz_u8, + .vece = MO_8 }, + { .fni4 = gen_helper_neon_clz_u16, + .vece = MO_16 }, + { .fni4 = gen_clz32_i32, + .vece = MO_32 }, + }; + assert(vece <= MO_32); + tcg_gen_gvec_2(rd_ofs, rn_ofs, opr_sz, max_sz, &g[vece]); +} diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index c697f0e944..387bbbf906 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -10321,6 +10321,13 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } switch (opcode) { + case 0x4: /* CLZ, CLS */ + if (u) { + gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_clz, size); + } else { + gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cls, size); + } + return; case 0x5: if (u && size == 0) { /* NOT */ gen_gvec_fn2(s, is_q, rd, rn, tcg_gen_gvec_not, 0); @@ -10379,13 +10386,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) if (size == 2) { /* Special cases for 32 bit elements */ switch (opcode) { - case 0x4: /* CLS */ - if (u) { - tcg_gen_clzi_i32(tcg_res, tcg_op, 32); - } else { - tcg_gen_clrsb_i32(tcg_res, tcg_op); - } - break; case 0x2f: /* FABS */ gen_vfp_abss(tcg_res, tcg_op); break; @@ -10450,21 +10450,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) gen_helper_neon_cnt_u8(tcg_res, tcg_op); } break; - case 0x4: /* CLS, CLZ */ - if (u) { - if (size == 0) { - gen_helper_neon_clz_u8(tcg_res, tcg_op); - } else { - gen_helper_neon_clz_u16(tcg_res, tcg_op); - } - } else { - if (size == 0) { - gen_helper_neon_cls_s8(tcg_res, tcg_op); - } else { - gen_helper_neon_cls_s16(tcg_res, tcg_op); - } - } - break; default: case 0x7: /* SQABS, SQNEG */ g_assert_not_reached(); diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index 9c8829ad7d..1c89a53272 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -3120,6 +3120,8 @@ DO_2MISC_VEC(VCGT0, gen_gvec_cgt0) DO_2MISC_VEC(VCLE0, gen_gvec_cle0) DO_2MISC_VEC(VCGE0, gen_gvec_cge0) DO_2MISC_VEC(VCLT0, gen_gvec_clt0) +DO_2MISC_VEC(VCLS, gen_gvec_cls) +DO_2MISC_VEC(VCLZ, gen_gvec_clz) static bool trans_VMVN(DisasContext *s, arg_2misc *a) { @@ -3227,33 +3229,6 @@ static bool trans_VREV16(DisasContext *s, arg_2misc *a) return do_2misc(s, a, gen_rev16); } -static bool trans_VCLS(DisasContext *s, arg_2misc *a) -{ - static NeonGenOneOpFn * const fn[] = { - gen_helper_neon_cls_s8, - gen_helper_neon_cls_s16, - gen_helper_neon_cls_s32, - NULL, - }; - return do_2misc(s, a, fn[a->size]); -} - -static void do_VCLZ_32(TCGv_i32 rd, TCGv_i32 rm) -{ - tcg_gen_clzi_i32(rd, rm, 32); -} - -static bool trans_VCLZ(DisasContext *s, arg_2misc *a) -{ - static NeonGenOneOpFn * const fn[] = { - gen_helper_neon_clz_u8, - gen_helper_neon_clz_u16, - do_VCLZ_32, - NULL, - }; - return do_2misc(s, a, fn[a->size]); -} - static bool trans_VCNT(DisasContext *s, arg_2misc *a) { if (a->size != 0) { diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index 20cd0e851c..5c6c24f057 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -578,6 +578,11 @@ void gen_gvec_umaxp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, void gen_gvec_uminp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_cls(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_clz(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz); + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ From 4e728364c919af537fbd1dc425641ae04f562915 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:05 -0600 Subject: [PATCH 38/85] target/arm: Convert CLS, CLZ (vector) to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-39-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 2 ++ target/arm/tcg/translate-a64.c | 37 ++++++++++++++++------------------ 2 files changed, 19 insertions(+), 20 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index f112951df7..32355ee633 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1641,3 +1641,5 @@ SQABS_v 0.00 1110 ..1 00000 01111 0 ..... ..... @qrr_e SQNEG_v 0.10 1110 ..1 00000 01111 0 ..... ..... @qrr_e ABS_v 0.00 1110 ..1 00000 10111 0 ..... ..... @qrr_e NEG_v 0.10 1110 ..1 00000 10111 0 ..... ..... @qrr_e +CLS_v 0.00 1110 ..1 00000 01001 0 ..... ..... @qrr_e +CLZ_v 0.10 1110 ..1 00000 01001 0 ..... ..... @qrr_e diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 387bbbf906..ecb4578998 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8916,6 +8916,20 @@ static bool do_gvec_fn2(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) TRANS(ABS_v, do_gvec_fn2, a, tcg_gen_gvec_abs) TRANS(NEG_v, do_gvec_fn2, a, tcg_gen_gvec_neg) +static bool do_gvec_fn2_bhs(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) +{ + if (a->esz == MO_64) { + return false; + } + if (fp_access_check(s)) { + gen_gvec_fn2(s, a->q, a->rd, a->rn, fn, a->esz); + } + return true; +} + +TRANS(CLS_v, do_gvec_fn2_bhs, a, gen_gvec_cls) +TRANS(CLZ_v, do_gvec_fn2_bhs, a, gen_gvec_clz) + /* Common vector code for handling integer to FP conversion */ static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn, int elements, int is_signed, @@ -9215,13 +9229,6 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, TCGCond cond; switch (opcode) { - case 0x4: /* CLS, CLZ */ - if (u) { - tcg_gen_clzi_i64(tcg_rd, tcg_rn, 64); - } else { - tcg_gen_clrsb_i64(tcg_rd, tcg_rn); - } - break; case 0x5: /* NOT */ /* This opcode is shared with CNT and RBIT but we have earlier * enforced that size == 3 if and only if this is the NOT insn. @@ -9283,6 +9290,7 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, gen_helper_frint64_d(tcg_rd, tcg_rn, tcg_fpstatus); break; default: + case 0x4: /* CLS, CLZ */ case 0x7: /* SQABS, SQNEG */ case 0xb: /* ABS, NEG */ g_assert_not_reached(); @@ -10089,12 +10097,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) handle_2misc_narrow(s, false, opcode, u, is_q, size, rn, rd); return; - case 0x4: /* CLS, CLZ */ - if (size == 3) { - unallocated_encoding(s); - return; - } - break; case 0x2: /* SADDLP, UADDLP */ case 0x6: /* SADALP, UADALP */ if (size == 3) { @@ -10299,6 +10301,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } default: case 0x3: /* SUQADD, USQADD */ + case 0x4: /* CLS, CLZ */ case 0x7: /* SQABS, SQNEG */ case 0xb: /* ABS, NEG */ unallocated_encoding(s); @@ -10321,13 +10324,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x4: /* CLZ, CLS */ - if (u) { - gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_clz, size); - } else { - gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cls, size); - } - return; case 0x5: if (u && size == 0) { /* NOT */ gen_gvec_fn2(s, is_q, rd, rn, tcg_gen_gvec_not, 0); @@ -10351,6 +10347,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0xa: /* CMLT */ gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_clt0, size); return; + case 0x4: /* CLZ, CLS */ case 0xb: g_assert_not_reached(); } From 4694d57458fb8850d95865dae619e284aa1cedbc Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:06 -0600 Subject: [PATCH 39/85] target/arm: Introduce gen_gvec_cnt, gen_gvec_rbit Add gvec interfaces for CNT and RBIT operations. Use ctpop8 for CNT and revbit+bswap for RBIT. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-40-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 4 ++-- target/arm/tcg/gengvec.c | 16 ++++++++++++++++ target/arm/tcg/neon_helper.c | 21 --------------------- target/arm/tcg/translate-a64.c | 32 +++++++++----------------------- target/arm/tcg/translate-neon.c | 16 ++++++++-------- target/arm/tcg/translate.h | 4 ++++ target/arm/tcg/vec_helper.c | 24 ++++++++++++++++++++++++ 7 files changed, 63 insertions(+), 54 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 0a697e752b..167e331a83 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -363,8 +363,8 @@ DEF_HELPER_1(neon_clz_u16, i32, i32) DEF_HELPER_1(neon_cls_s8, i32, i32) DEF_HELPER_1(neon_cls_s16, i32, i32) DEF_HELPER_1(neon_cls_s32, i32, i32) -DEF_HELPER_1(neon_cnt_u8, i32, i32) -DEF_HELPER_FLAGS_1(neon_rbit_u8, TCG_CALL_NO_RWG_SE, i32, i32) +DEF_HELPER_FLAGS_3(gvec_cnt_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_rbit_b, TCG_CALL_NO_RWG, void, ptr, ptr, i32) DEF_HELPER_3(neon_qdmulh_s16, i32, env, i32, i32) DEF_HELPER_3(neon_qrdmulh_s16, i32, env, i32, i32) diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index 834b2961c0..85a0b50496 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -2393,3 +2393,19 @@ void gen_gvec_clz(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, assert(vece <= MO_32); tcg_gen_gvec_2(rd_ofs, rn_ofs, opr_sz, max_sz, &g[vece]); } + +void gen_gvec_cnt(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + assert(vece == MO_8); + tcg_gen_gvec_2_ool(rd_ofs, rn_ofs, opr_sz, max_sz, 0, + gen_helper_gvec_cnt_b); +} + +void gen_gvec_rbit(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + assert(vece == MO_8); + tcg_gen_gvec_2_ool(rd_ofs, rn_ofs, opr_sz, max_sz, 0, + gen_helper_gvec_rbit_b); +} diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index 93b2076c64..4e501925de 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -525,27 +525,6 @@ uint32_t HELPER(neon_cls_s32)(uint32_t x) return count - 1; } -/* Bit count. */ -uint32_t HELPER(neon_cnt_u8)(uint32_t x) -{ - x = (x & 0x55555555) + ((x >> 1) & 0x55555555); - x = (x & 0x33333333) + ((x >> 2) & 0x33333333); - x = (x & 0x0f0f0f0f) + ((x >> 4) & 0x0f0f0f0f); - return x; -} - -/* Reverse bits in each 8 bit word */ -uint32_t HELPER(neon_rbit_u8)(uint32_t x) -{ - x = ((x & 0xf0f0f0f0) >> 4) - | ((x & 0x0f0f0f0f) << 4); - x = ((x & 0x88888888) >> 3) - | ((x & 0x44444444) >> 1) - | ((x & 0x22222222) << 1) - | ((x & 0x11111111) << 3); - return x; -} - #define NEON_QDMULH16(dest, src1, src2, round) do { \ uint32_t tmp = (int32_t)(int16_t) src1 * (int16_t) src2; \ if ((tmp ^ (tmp << 1)) & SIGNBIT) { \ diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index ecb4578998..3e0c061b3c 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -10324,12 +10324,15 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x5: - if (u && size == 0) { /* NOT */ + case 0x5: /* CNT, NOT, RBIT */ + if (!u) { + gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cnt, 0); + } else if (size) { + gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_rbit, 0); + } else { gen_gvec_fn2(s, is_q, rd, rn, tcg_gen_gvec_not, 0); - return; } - break; + return; case 0x8: /* CMGT, CMGE */ if (u) { gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cge0, size); @@ -10374,13 +10377,14 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } else { int pass; + assert(size == 2); for (pass = 0; pass < (is_q ? 4 : 2); pass++) { TCGv_i32 tcg_op = tcg_temp_new_i32(); TCGv_i32 tcg_res = tcg_temp_new_i32(); read_vec_element_i32(s, tcg_op, rn, pass, MO_32); - if (size == 2) { + { /* Special cases for 32 bit elements */ switch (opcode) { case 0x2f: /* FABS */ @@ -10434,25 +10438,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x7: /* SQABS, SQNEG */ g_assert_not_reached(); } - } else { - /* Use helpers for 8 and 16 bit elements */ - switch (opcode) { - case 0x5: /* CNT, RBIT */ - /* For these two insns size is part of the opcode specifier - * (handled earlier); they always operate on byte elements. - */ - if (u) { - gen_helper_neon_rbit_u8(tcg_res, tcg_op); - } else { - gen_helper_neon_cnt_u8(tcg_res, tcg_op); - } - break; - default: - case 0x7: /* SQABS, SQNEG */ - g_assert_not_reached(); - } } - write_vec_element_i32(s, tcg_res, rd, pass, MO_32); } } diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index 1c89a53272..50d0bf7753 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -3131,6 +3131,14 @@ static bool trans_VMVN(DisasContext *s, arg_2misc *a) return do_2misc_vec(s, a, tcg_gen_gvec_not); } +static bool trans_VCNT(DisasContext *s, arg_2misc *a) +{ + if (a->size != 0) { + return false; + } + return do_2misc_vec(s, a, gen_gvec_cnt); +} + #define WRAP_2M_3_OOL_FN(WRAPNAME, FUNC, DATA) \ static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \ uint32_t rm_ofs, uint32_t oprsz, \ @@ -3229,14 +3237,6 @@ static bool trans_VREV16(DisasContext *s, arg_2misc *a) return do_2misc(s, a, gen_rev16); } -static bool trans_VCNT(DisasContext *s, arg_2misc *a) -{ - if (a->size != 0) { - return false; - } - return do_2misc(s, a, gen_helper_neon_cnt_u8); -} - static void gen_VABS_F(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz) { diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index 5c6c24f057..cb8e1b2586 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -582,6 +582,10 @@ void gen_gvec_cls(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_gvec_clz(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_cnt(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_rbit(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz); /* * Forward to the isar_feature_* tests given a DisasContext pointer. diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index ad6f26545a..91a9130641 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -3066,3 +3066,27 @@ DO_CLAMP(gvec_uclamp_b, uint8_t) DO_CLAMP(gvec_uclamp_h, uint16_t) DO_CLAMP(gvec_uclamp_s, uint32_t) DO_CLAMP(gvec_uclamp_d, uint64_t) + +/* Bit count in each 8-bit word. */ +void HELPER(gvec_cnt_b)(void *vd, void *vn, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint8_t *d = vd, *n = vn; + + for (i = 0; i < opr_sz; ++i) { + d[i] = ctpop8(n[i]); + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +/* Reverse bits in each 8 bit word */ +void HELPER(gvec_rbit_b)(void *vd, void *vn, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint64_t *d = vd, *n = vn; + + for (i = 0; i < opr_sz / 8; ++i) { + d[i] = revbit64(bswap64(n[i])); + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} From 95288cc1654c80e0ab301faa3ed55ef43e0c8f1e Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:07 -0600 Subject: [PATCH 40/85] target/arm: Convert CNT, NOT, RBIT (vector) to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-41-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 4 ++++ target/arm/tcg/translate-a64.c | 34 ++++++---------------------------- 2 files changed, 10 insertions(+), 28 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 32355ee633..bac81eec7e 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -71,6 +71,7 @@ @rrr_q1e3 ........ ... rm:5 ...... rn:5 rd:5 &qrrr_e q=1 esz=3 @rrrr_q1e3 ........ ... rm:5 . ra:5 rn:5 rd:5 &qrrrr_e q=1 esz=3 +@qrr_b . q:1 ...... .. ...... ...... rn:5 rd:5 &qrr_e esz=0 @qrr_h . q:1 ...... .. ...... ...... rn:5 rd:5 &qrr_e esz=1 @qrr_e . q:1 ...... esz:2 ...... ...... rn:5 rd:5 &qrr_e @@ -1643,3 +1644,6 @@ ABS_v 0.00 1110 ..1 00000 10111 0 ..... ..... @qrr_e NEG_v 0.10 1110 ..1 00000 10111 0 ..... ..... @qrr_e CLS_v 0.00 1110 ..1 00000 01001 0 ..... ..... @qrr_e CLZ_v 0.10 1110 ..1 00000 01001 0 ..... ..... @qrr_e +CNT_v 0.00 1110 001 00000 01011 0 ..... ..... @qrr_b +NOT_v 0.10 1110 001 00000 01011 0 ..... ..... @qrr_b +RBIT_v 0.10 1110 011 00000 01011 0 ..... ..... @qrr_b diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 3e0c061b3c..aff1984a22 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8915,6 +8915,9 @@ static bool do_gvec_fn2(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) TRANS(ABS_v, do_gvec_fn2, a, tcg_gen_gvec_abs) TRANS(NEG_v, do_gvec_fn2, a, tcg_gen_gvec_neg) +TRANS(NOT_v, do_gvec_fn2, a, tcg_gen_gvec_not) +TRANS(CNT_v, do_gvec_fn2, a, gen_gvec_cnt) +TRANS(RBIT_v, do_gvec_fn2, a, gen_gvec_rbit) static bool do_gvec_fn2_bhs(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) { @@ -9229,12 +9232,6 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, TCGCond cond; switch (opcode) { - case 0x5: /* NOT */ - /* This opcode is shared with CNT and RBIT but we have earlier - * enforced that size == 3 if and only if this is the NOT insn. - */ - tcg_gen_not_i64(tcg_rd, tcg_rn); - break; case 0xa: /* CMLT */ cond = TCG_COND_LT; do_cmop: @@ -9291,6 +9288,7 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, break; default: case 0x4: /* CLS, CLZ */ + case 0x5: /* NOT */ case 0x7: /* SQABS, SQNEG */ case 0xb: /* ABS, NEG */ g_assert_not_reached(); @@ -10072,19 +10070,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x1: /* REV16 */ handle_rev(s, opcode, u, is_q, size, rn, rd); return; - case 0x5: /* CNT, NOT, RBIT */ - if (u && size == 0) { - /* NOT */ - break; - } else if (u && size == 1) { - /* RBIT */ - break; - } else if (!u && size == 0) { - /* CNT */ - break; - } - unallocated_encoding(s); - return; case 0x12: /* XTN, XTN2, SQXTUN, SQXTUN2 */ case 0x14: /* SQXTN, SQXTN2, UQXTN, UQXTN2 */ if (size == 3) { @@ -10302,6 +10287,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) default: case 0x3: /* SUQADD, USQADD */ case 0x4: /* CLS, CLZ */ + case 0x5: /* CNT, NOT, RBIT */ case 0x7: /* SQABS, SQNEG */ case 0xb: /* ABS, NEG */ unallocated_encoding(s); @@ -10324,15 +10310,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x5: /* CNT, NOT, RBIT */ - if (!u) { - gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cnt, 0); - } else if (size) { - gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_rbit, 0); - } else { - gen_gvec_fn2(s, is_q, rd, rn, tcg_gen_gvec_not, 0); - } - return; case 0x8: /* CMGT, CMGE */ if (u) { gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cge0, size); @@ -10351,6 +10328,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_clt0, size); return; case 0x4: /* CLZ, CLS */ + case 0x5: /* CNT, NOT, RBIT */ case 0xb: g_assert_not_reached(); } From 72040d9200f64960aefd9c88a539ecd8d9b3adcf Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:08 -0600 Subject: [PATCH 41/85] target/arm: Convert CMGT, CMGE, GMLT, GMLE, CMEQ (zero) to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-42-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 10 ++++ target/arm/tcg/translate-a64.c | 94 +++++++++++----------------------- 2 files changed, 40 insertions(+), 64 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index bac81eec7e..247d3a7bda 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1635,6 +1635,11 @@ SQABS_s 0101 1110 ..1 00000 01111 0 ..... ..... @rr_e SQNEG_s 0111 1110 ..1 00000 01111 0 ..... ..... @rr_e ABS_s 0101 1110 111 00000 10111 0 ..... ..... @rr NEG_s 0111 1110 111 00000 10111 0 ..... ..... @rr +CMGT0_s 0101 1110 111 00000 10001 0 ..... ..... @rr +CMGE0_s 0111 1110 111 00000 10001 0 ..... ..... @rr +CMEQ0_s 0101 1110 111 00000 10011 0 ..... ..... @rr +CMLE0_s 0111 1110 111 00000 10011 0 ..... ..... @rr +CMLT0_s 0101 1110 111 00000 10101 0 ..... ..... @rr # Advanced SIMD two-register miscellaneous @@ -1647,3 +1652,8 @@ CLZ_v 0.10 1110 ..1 00000 01001 0 ..... ..... @qrr_e CNT_v 0.00 1110 001 00000 01011 0 ..... ..... @qrr_b NOT_v 0.10 1110 001 00000 01011 0 ..... ..... @qrr_b RBIT_v 0.10 1110 011 00000 01011 0 ..... ..... @qrr_b +CMGT0_v 0.00 1110 ..1 00000 10001 0 ..... ..... @qrr_e +CMGE0_v 0.10 1110 ..1 00000 10001 0 ..... ..... @qrr_e +CMEQ0_v 0.00 1110 ..1 00000 10011 0 ..... ..... @qrr_e +CMLE0_v 0.10 1110 ..1 00000 10011 0 ..... ..... @qrr_e +CMLT0_v 0.00 1110 ..1 00000 10101 0 ..... ..... @qrr_e diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index aff1984a22..547c6dc5cc 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8902,6 +8902,22 @@ static bool do_scalar1_d(DisasContext *s, arg_rr *a, ArithOneOp *f) TRANS(ABS_s, do_scalar1_d, a, tcg_gen_abs_i64) TRANS(NEG_s, do_scalar1_d, a, tcg_gen_neg_i64) +static bool do_cmop0_d(DisasContext *s, arg_rr *a, TCGCond cond) +{ + if (fp_access_check(s)) { + TCGv_i64 t = read_fp_dreg(s, a->rn); + tcg_gen_negsetcond_i64(cond, t, t, tcg_constant_i64(0)); + write_fp_dreg(s, a->rd, t); + } + return true; +} + +TRANS(CMGT0_s, do_cmop0_d, a, TCG_COND_GT) +TRANS(CMGE0_s, do_cmop0_d, a, TCG_COND_GE) +TRANS(CMLE0_s, do_cmop0_d, a, TCG_COND_LE) +TRANS(CMLT0_s, do_cmop0_d, a, TCG_COND_LT) +TRANS(CMEQ0_s, do_cmop0_d, a, TCG_COND_EQ) + static bool do_gvec_fn2(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) { if (!a->q && a->esz == MO_64) { @@ -8918,6 +8934,11 @@ TRANS(NEG_v, do_gvec_fn2, a, tcg_gen_gvec_neg) TRANS(NOT_v, do_gvec_fn2, a, tcg_gen_gvec_not) TRANS(CNT_v, do_gvec_fn2, a, gen_gvec_cnt) TRANS(RBIT_v, do_gvec_fn2, a, gen_gvec_rbit) +TRANS(CMGT0_v, do_gvec_fn2, a, gen_gvec_cgt0) +TRANS(CMGE0_v, do_gvec_fn2, a, gen_gvec_cge0) +TRANS(CMLT0_v, do_gvec_fn2, a, gen_gvec_clt0) +TRANS(CMLE0_v, do_gvec_fn2, a, gen_gvec_cle0) +TRANS(CMEQ0_v, do_gvec_fn2, a, gen_gvec_ceq0) static bool do_gvec_fn2_bhs(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) { @@ -9229,21 +9250,7 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, * The caller only need provide tcg_rmode and tcg_fpstatus if the op * requires them. */ - TCGCond cond; - switch (opcode) { - case 0xa: /* CMLT */ - cond = TCG_COND_LT; - do_cmop: - /* 64 bit integer comparison against zero, result is test ? -1 : 0. */ - tcg_gen_negsetcond_i64(cond, tcg_rd, tcg_rn, tcg_constant_i64(0)); - break; - case 0x8: /* CMGT, CMGE */ - cond = u ? TCG_COND_GE : TCG_COND_GT; - goto do_cmop; - case 0x9: /* CMEQ, CMLE */ - cond = u ? TCG_COND_LE : TCG_COND_EQ; - goto do_cmop; case 0x2f: /* FABS */ gen_vfp_absd(tcg_rd, tcg_rn); break; @@ -9290,6 +9297,9 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, case 0x4: /* CLS, CLZ */ case 0x5: /* NOT */ case 0x7: /* SQABS, SQNEG */ + case 0x8: /* CMGT, CMGE */ + case 0x9: /* CMEQ, CMLE */ + case 0xa: /* CMLT */ case 0xb: /* ABS, NEG */ g_assert_not_reached(); } @@ -9633,19 +9643,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) TCGv_ptr tcg_fpstatus; switch (opcode) { - case 0xa: /* CMLT */ - if (u) { - unallocated_encoding(s); - return; - } - /* fall through */ - case 0x8: /* CMGT, CMGE */ - case 0x9: /* CMEQ, CMLE */ - if (size != 3) { - unallocated_encoding(s); - return; - } - break; case 0x12: /* SQXTUN */ if (!u) { unallocated_encoding(s); @@ -9731,6 +9728,9 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) default: case 0x3: /* USQADD / SUQADD */ case 0x7: /* SQABS / SQNEG */ + case 0x8: /* CMGT, CMGE */ + case 0x9: /* CMEQ, CMLE */ + case 0xa: /* CMLT */ case 0xb: /* ABS, NEG */ unallocated_encoding(s); return; @@ -10103,19 +10103,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } handle_shll(s, is_q, size, rn, rd); return; - case 0xa: /* CMLT */ - if (u == 1) { - unallocated_encoding(s); - return; - } - /* fall through */ - case 0x8: /* CMGT, CMGE */ - case 0x9: /* CMEQ, CMLE */ - if (size == 3 && !is_q) { - unallocated_encoding(s); - return; - } - break; case 0xc ... 0xf: case 0x16 ... 0x1f: { @@ -10289,6 +10276,9 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x4: /* CLS, CLZ */ case 0x5: /* CNT, NOT, RBIT */ case 0x7: /* SQABS, SQNEG */ + case 0x8: /* CMGT, CMGE */ + case 0x9: /* CMEQ, CMLE */ + case 0xa: /* CMLT */ case 0xb: /* ABS, NEG */ unallocated_encoding(s); return; @@ -10309,30 +10299,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) tcg_rmode = NULL; } - switch (opcode) { - case 0x8: /* CMGT, CMGE */ - if (u) { - gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cge0, size); - } else { - gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cgt0, size); - } - return; - case 0x9: /* CMEQ, CMLE */ - if (u) { - gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_cle0, size); - } else { - gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_ceq0, size); - } - return; - case 0xa: /* CMLT */ - gen_gvec_fn2(s, is_q, rd, rn, gen_gvec_clt0, size); - return; - case 0x4: /* CLZ, CLS */ - case 0x5: /* CNT, NOT, RBIT */ - case 0xb: - g_assert_not_reached(); - } - if (size == 3) { /* All 64-bit element operations can be shared with scalar 2misc */ int pass; From 38f9950c8e0315d7b26803018a3f73d5f42e6703 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:09 -0600 Subject: [PATCH 42/85] target/arm: Introduce gen_gvec_rev{16,32,64} Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-43-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/gengvec.c | 58 ++++++++++++++++++++++ target/arm/tcg/translate-neon.c | 88 +++++++-------------------------- target/arm/tcg/translate.h | 6 +++ 3 files changed, 81 insertions(+), 71 deletions(-) diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index 85a0b50496..33c0a94958 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -2409,3 +2409,61 @@ void gen_gvec_rbit(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, tcg_gen_gvec_2_ool(rd_ofs, rn_ofs, opr_sz, max_sz, 0, gen_helper_gvec_rbit_b); } + +void gen_gvec_rev16(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + assert(vece == MO_8); + tcg_gen_gvec_rotli(MO_16, rd_ofs, rn_ofs, 8, opr_sz, max_sz); +} + +static void gen_bswap32_i64(TCGv_i64 d, TCGv_i64 n) +{ + tcg_gen_bswap64_i64(d, n); + tcg_gen_rotli_i64(d, d, 32); +} + +void gen_gvec_rev32(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + static const GVecGen2 g = { + .fni8 = gen_bswap32_i64, + .fni4 = tcg_gen_bswap32_i32, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_32 + }; + + switch (vece) { + case MO_16: + tcg_gen_gvec_rotli(MO_32, rd_ofs, rn_ofs, 16, opr_sz, max_sz); + break; + case MO_8: + tcg_gen_gvec_2(rd_ofs, rn_ofs, opr_sz, max_sz, &g); + break; + default: + g_assert_not_reached(); + } +} + +void gen_gvec_rev64(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + static const GVecGen2 g[] = { + { .fni8 = tcg_gen_bswap64_i64, + .vece = MO_64 }, + { .fni8 = tcg_gen_hswap_i64, + .vece = MO_64 }, + }; + + switch (vece) { + case MO_32: + tcg_gen_gvec_rotli(MO_64, rd_ofs, rn_ofs, 32, opr_sz, max_sz); + break; + case MO_8: + case MO_16: + tcg_gen_gvec_2(rd_ofs, rn_ofs, opr_sz, max_sz, &g[vece]); + break; + default: + g_assert_not_reached(); + } +} diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index 50d0bf7753..ca6f5578b4 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -2565,58 +2565,6 @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a) return true; } -static bool trans_VREV64(DisasContext *s, arg_VREV64 *a) -{ - int pass, half; - TCGv_i32 tmp[2]; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { - return false; - } - - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vm) & 0x10)) { - return false; - } - - if ((a->vd | a->vm) & a->q) { - return false; - } - - if (a->size == 3) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - tmp[0] = tcg_temp_new_i32(); - tmp[1] = tcg_temp_new_i32(); - - for (pass = 0; pass < (a->q ? 2 : 1); pass++) { - for (half = 0; half < 2; half++) { - read_neon_element32(tmp[half], a->vm, pass * 2 + half, MO_32); - switch (a->size) { - case 0: - tcg_gen_bswap32_i32(tmp[half], tmp[half]); - break; - case 1: - gen_swap_half(tmp[half], tmp[half]); - break; - case 2: - break; - default: - g_assert_not_reached(); - } - } - write_neon_element32(tmp[1], a->vd, pass * 2, MO_32); - write_neon_element32(tmp[0], a->vd, pass * 2 + 1, MO_32); - } - return true; -} - static bool do_2misc_pairwise(DisasContext *s, arg_2misc *a, NeonGenWidenFn *widenfn, NeonGenTwo64OpFn *opfn, @@ -3122,6 +3070,7 @@ DO_2MISC_VEC(VCGE0, gen_gvec_cge0) DO_2MISC_VEC(VCLT0, gen_gvec_clt0) DO_2MISC_VEC(VCLS, gen_gvec_cls) DO_2MISC_VEC(VCLZ, gen_gvec_clz) +DO_2MISC_VEC(VREV64, gen_gvec_rev64) static bool trans_VMVN(DisasContext *s, arg_2misc *a) { @@ -3139,6 +3088,22 @@ static bool trans_VCNT(DisasContext *s, arg_2misc *a) return do_2misc_vec(s, a, gen_gvec_cnt); } +static bool trans_VREV16(DisasContext *s, arg_2misc *a) +{ + if (a->size != 0) { + return false; + } + return do_2misc_vec(s, a, gen_gvec_rev16); +} + +static bool trans_VREV32(DisasContext *s, arg_2misc *a) +{ + if (a->size != 0 && a->size != 1) { + return false; + } + return do_2misc_vec(s, a, gen_gvec_rev32); +} + #define WRAP_2M_3_OOL_FN(WRAPNAME, FUNC, DATA) \ static void WRAPNAME(unsigned vece, uint32_t rd_ofs, \ uint32_t rm_ofs, uint32_t oprsz, \ @@ -3218,25 +3183,6 @@ static bool do_2misc(DisasContext *s, arg_2misc *a, NeonGenOneOpFn *fn) return true; } -static bool trans_VREV32(DisasContext *s, arg_2misc *a) -{ - static NeonGenOneOpFn * const fn[] = { - tcg_gen_bswap32_i32, - gen_swap_half, - NULL, - NULL, - }; - return do_2misc(s, a, fn[a->size]); -} - -static bool trans_VREV16(DisasContext *s, arg_2misc *a) -{ - if (a->size != 0) { - return false; - } - return do_2misc(s, a, gen_rev16); -} - static void gen_VABS_F(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, uint32_t oprsz, uint32_t maxsz) { diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index cb8e1b2586..342ebedafc 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -586,6 +586,12 @@ void gen_gvec_cnt(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t opr_sz, uint32_t max_sz); void gen_gvec_rbit(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_rev16(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_rev32(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_rev64(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz); /* * Forward to the isar_feature_* tests given a DisasContext pointer. From 7c6bdcdaed9372601b1b366315c45029e0b2f28a Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:10 -0600 Subject: [PATCH 43/85] target/arm: Convert handle_rev to decodetree This includes REV16, REV32, REV64. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-44-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 5 +++ target/arm/tcg/translate-a64.c | 79 +++------------------------------- 2 files changed, 10 insertions(+), 74 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 247d3a7bda..05f1bc99b5 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -73,6 +73,7 @@ @qrr_b . q:1 ...... .. ...... ...... rn:5 rd:5 &qrr_e esz=0 @qrr_h . q:1 ...... .. ...... ...... rn:5 rd:5 &qrr_e esz=1 +@qrr_bh . q:1 ...... . esz:1 ...... ...... rn:5 rd:5 &qrr_e @qrr_e . q:1 ...... esz:2 ...... ...... rn:5 rd:5 &qrr_e @qrrr_b . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=0 @@ -1657,3 +1658,7 @@ CMGE0_v 0.10 1110 ..1 00000 10001 0 ..... ..... @qrr_e CMEQ0_v 0.00 1110 ..1 00000 10011 0 ..... ..... @qrr_e CMLE0_v 0.10 1110 ..1 00000 10011 0 ..... ..... @qrr_e CMLT0_v 0.00 1110 ..1 00000 10101 0 ..... ..... @qrr_e + +REV16_v 0.00 1110 001 00000 00011 0 ..... ..... @qrr_b +REV32_v 0.10 1110 0.1 00000 00001 0 ..... ..... @qrr_bh +REV64_v 0.00 1110 ..1 00000 00001 0 ..... ..... @qrr_e diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 547c6dc5cc..f57b5e2855 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8939,6 +8939,8 @@ TRANS(CMGE0_v, do_gvec_fn2, a, gen_gvec_cge0) TRANS(CMLT0_v, do_gvec_fn2, a, gen_gvec_clt0) TRANS(CMLE0_v, do_gvec_fn2, a, gen_gvec_cle0) TRANS(CMEQ0_v, do_gvec_fn2, a, gen_gvec_ceq0) +TRANS(REV16_v, do_gvec_fn2, a, gen_gvec_rev16) +TRANS(REV32_v, do_gvec_fn2, a, gen_gvec_rev32) static bool do_gvec_fn2_bhs(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) { @@ -8953,6 +8955,7 @@ static bool do_gvec_fn2_bhs(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) TRANS(CLS_v, do_gvec_fn2_bhs, a, gen_gvec_cls) TRANS(CLZ_v, do_gvec_fn2_bhs, a, gen_gvec_clz) +TRANS(REV64_v, do_gvec_fn2_bhs, a, gen_gvec_rev64) /* Common vector code for handling integer to FP conversion */ static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn, @@ -9882,76 +9885,6 @@ static void handle_2misc_widening(DisasContext *s, int opcode, bool is_q, } } -static void handle_rev(DisasContext *s, int opcode, bool u, - bool is_q, int size, int rn, int rd) -{ - int op = (opcode << 1) | u; - int opsz = op + size; - int grp_size = 3 - opsz; - int dsize = is_q ? 128 : 64; - int i; - - if (opsz >= 3) { - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - if (size == 0) { - /* Special case bytes, use bswap op on each group of elements */ - int groups = dsize / (8 << grp_size); - - for (i = 0; i < groups; i++) { - TCGv_i64 tcg_tmp = tcg_temp_new_i64(); - - read_vec_element(s, tcg_tmp, rn, i, grp_size); - switch (grp_size) { - case MO_16: - tcg_gen_bswap16_i64(tcg_tmp, tcg_tmp, TCG_BSWAP_IZ); - break; - case MO_32: - tcg_gen_bswap32_i64(tcg_tmp, tcg_tmp, TCG_BSWAP_IZ); - break; - case MO_64: - tcg_gen_bswap64_i64(tcg_tmp, tcg_tmp); - break; - default: - g_assert_not_reached(); - } - write_vec_element(s, tcg_tmp, rd, i, grp_size); - } - clear_vec_high(s, is_q, rd); - } else { - int revmask = (1 << grp_size) - 1; - int esize = 8 << size; - int elements = dsize / esize; - TCGv_i64 tcg_rn = tcg_temp_new_i64(); - TCGv_i64 tcg_rd[2]; - - for (i = 0; i < 2; i++) { - tcg_rd[i] = tcg_temp_new_i64(); - tcg_gen_movi_i64(tcg_rd[i], 0); - } - - for (i = 0; i < elements; i++) { - int e_rev = (i & 0xf) ^ revmask; - int w = (e_rev * esize) / 64; - int o = (e_rev * esize) % 64; - - read_vec_element(s, tcg_rn, rn, i, size); - tcg_gen_deposit_i64(tcg_rd[w], tcg_rd[w], tcg_rn, o, esize); - } - - for (i = 0; i < 2; i++) { - write_vec_element(s, tcg_rd[i], rd, i, MO_64); - } - clear_vec_high(s, true, rd); - } -} - static void handle_2misc_pairwise(DisasContext *s, int opcode, bool u, bool is_q, int size, int rn, int rd) { @@ -10066,10 +9999,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) TCGv_ptr tcg_fpstatus; switch (opcode) { - case 0x0: /* REV64, REV32 */ - case 0x1: /* REV16 */ - handle_rev(s, opcode, u, is_q, size, rn, rd); - return; case 0x12: /* XTN, XTN2, SQXTUN, SQXTUN2 */ case 0x14: /* SQXTN, SQXTN2, UQXTN, UQXTN2 */ if (size == 3) { @@ -10272,6 +10201,8 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) break; } default: + case 0x0: /* REV64, REV32 */ + case 0x1: /* REV16 */ case 0x3: /* SUQADD, USQADD */ case 0x4: /* CLS, CLZ */ case 0x5: /* CNT, NOT, RBIT */ From e90cf92209d07e8fb4564f82adc09b9fb764cf41 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:11 -0600 Subject: [PATCH 44/85] target/arm: Move helper_neon_addlp_{s8, s16} to neon_helper.c Move from helper-a64.c to neon_helper.c so that these functions are available for arm32 code as well. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-45-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 2 ++ target/arm/tcg/helper-a64.c | 43 ------------------------------------ target/arm/tcg/helper-a64.h | 2 -- target/arm/tcg/neon_helper.c | 43 ++++++++++++++++++++++++++++++++++++ 4 files changed, 45 insertions(+), 45 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 167e331a83..57e0ce387b 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -399,6 +399,8 @@ DEF_HELPER_2(neon_addl_u16, i64, i64, i64) DEF_HELPER_2(neon_addl_u32, i64, i64, i64) DEF_HELPER_2(neon_paddl_u16, i64, i64, i64) DEF_HELPER_2(neon_paddl_u32, i64, i64, i64) +DEF_HELPER_FLAGS_1(neon_addlp_s8, TCG_CALL_NO_RWG_SE, i64, i64) +DEF_HELPER_FLAGS_1(neon_addlp_s16, TCG_CALL_NO_RWG_SE, i64, i64) DEF_HELPER_2(neon_subl_u16, i64, i64, i64) DEF_HELPER_2(neon_subl_u32, i64, i64, i64) DEF_HELPER_3(neon_addl_saturate_s32, i64, env, i64, i64) diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index 3f4d7b9aba..9b3c407be3 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -306,39 +306,6 @@ float64 HELPER(rsqrtsf_f64)(float64 a, float64 b, void *fpstp) return float64_muladd(a, b, float64_three, float_muladd_halve_result, fpst); } -/* Pairwise long add: add pairs of adjacent elements into - * double-width elements in the result (eg _s8 is an 8x8->16 op) - */ -uint64_t HELPER(neon_addlp_s8)(uint64_t a) -{ - uint64_t nsignmask = 0x0080008000800080ULL; - uint64_t wsignmask = 0x8000800080008000ULL; - uint64_t elementmask = 0x00ff00ff00ff00ffULL; - uint64_t tmp1, tmp2; - uint64_t res, signres; - - /* Extract odd elements, sign extend each to a 16 bit field */ - tmp1 = a & elementmask; - tmp1 ^= nsignmask; - tmp1 |= wsignmask; - tmp1 = (tmp1 - nsignmask) ^ wsignmask; - /* Ditto for the even elements */ - tmp2 = (a >> 8) & elementmask; - tmp2 ^= nsignmask; - tmp2 |= wsignmask; - tmp2 = (tmp2 - nsignmask) ^ wsignmask; - - /* calculate the result by summing bits 0..14, 16..22, etc, - * and then adjusting the sign bits 15, 23, etc manually. - * This ensures the addition can't overflow the 16 bit field. - */ - signres = (tmp1 ^ tmp2) & wsignmask; - res = (tmp1 & ~wsignmask) + (tmp2 & ~wsignmask); - res ^= signres; - - return res; -} - uint64_t HELPER(neon_addlp_u8)(uint64_t a) { uint64_t tmp; @@ -348,16 +315,6 @@ uint64_t HELPER(neon_addlp_u8)(uint64_t a) return tmp; } -uint64_t HELPER(neon_addlp_s16)(uint64_t a) -{ - int32_t reslo, reshi; - - reslo = (int32_t)(int16_t)a + (int32_t)(int16_t)(a >> 16); - reshi = (int32_t)(int16_t)(a >> 32) + (int32_t)(int16_t)(a >> 48); - - return (uint32_t)reslo | (((uint64_t)reshi) << 32); -} - uint64_t HELPER(neon_addlp_u16)(uint64_t a) { uint64_t tmp; diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index 203b7b7ac8..f811bb85dc 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -41,9 +41,7 @@ DEF_HELPER_FLAGS_3(recpsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr) DEF_HELPER_FLAGS_3(rsqrtsf_f16, TCG_CALL_NO_RWG, f16, f16, f16, ptr) DEF_HELPER_FLAGS_3(rsqrtsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, ptr) DEF_HELPER_FLAGS_3(rsqrtsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr) -DEF_HELPER_FLAGS_1(neon_addlp_s8, TCG_CALL_NO_RWG_SE, i64, i64) DEF_HELPER_FLAGS_1(neon_addlp_u8, TCG_CALL_NO_RWG_SE, i64, i64) -DEF_HELPER_FLAGS_1(neon_addlp_s16, TCG_CALL_NO_RWG_SE, i64, i64) DEF_HELPER_FLAGS_1(neon_addlp_u16, TCG_CALL_NO_RWG_SE, i64, i64) DEF_HELPER_FLAGS_2(frecpx_f64, TCG_CALL_NO_RWG, f64, f64, ptr) DEF_HELPER_FLAGS_2(frecpx_f32, TCG_CALL_NO_RWG, f32, f32, ptr) diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index 4e501925de..b92ddd4914 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -866,6 +866,49 @@ uint64_t HELPER(neon_paddl_u32)(uint64_t a, uint64_t b) return low + ((uint64_t)high << 32); } +/* Pairwise long add: add pairs of adjacent elements into + * double-width elements in the result (eg _s8 is an 8x8->16 op) + */ +uint64_t HELPER(neon_addlp_s8)(uint64_t a) +{ + uint64_t nsignmask = 0x0080008000800080ULL; + uint64_t wsignmask = 0x8000800080008000ULL; + uint64_t elementmask = 0x00ff00ff00ff00ffULL; + uint64_t tmp1, tmp2; + uint64_t res, signres; + + /* Extract odd elements, sign extend each to a 16 bit field */ + tmp1 = a & elementmask; + tmp1 ^= nsignmask; + tmp1 |= wsignmask; + tmp1 = (tmp1 - nsignmask) ^ wsignmask; + /* Ditto for the even elements */ + tmp2 = (a >> 8) & elementmask; + tmp2 ^= nsignmask; + tmp2 |= wsignmask; + tmp2 = (tmp2 - nsignmask) ^ wsignmask; + + /* calculate the result by summing bits 0..14, 16..22, etc, + * and then adjusting the sign bits 15, 23, etc manually. + * This ensures the addition can't overflow the 16 bit field. + */ + signres = (tmp1 ^ tmp2) & wsignmask; + res = (tmp1 & ~wsignmask) + (tmp2 & ~wsignmask); + res ^= signres; + + return res; +} + +uint64_t HELPER(neon_addlp_s16)(uint64_t a) +{ + int32_t reslo, reshi; + + reslo = (int32_t)(int16_t)a + (int32_t)(int16_t)(a >> 16); + reshi = (int32_t)(int16_t)(a >> 32) + (int32_t)(int16_t)(a >> 48); + + return (uint32_t)reslo | (((uint64_t)reshi) << 32); +} + uint64_t HELPER(neon_subl_u16)(uint64_t a, uint64_t b) { uint64_t mask; From c14bde6998398d19187e9eff8a9f69ddb00fdf5b Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:12 -0600 Subject: [PATCH 45/85] target/arm: Introduce gen_gvec_{s,u}{add,ada}lp Pairwise addition with and without accumulation. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-46-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 2 - target/arm/tcg/gengvec.c | 230 ++++++++++++++++++++++++++++++++ target/arm/tcg/neon_helper.c | 22 --- target/arm/tcg/translate-neon.c | 150 +-------------------- target/arm/tcg/translate.h | 9 ++ 5 files changed, 243 insertions(+), 170 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 57e0ce387b..6369d07d05 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -397,8 +397,6 @@ DEF_HELPER_1(neon_widen_s16, i64, i32) DEF_HELPER_2(neon_addl_u16, i64, i64, i64) DEF_HELPER_2(neon_addl_u32, i64, i64, i64) -DEF_HELPER_2(neon_paddl_u16, i64, i64, i64) -DEF_HELPER_2(neon_paddl_u32, i64, i64, i64) DEF_HELPER_FLAGS_1(neon_addlp_s8, TCG_CALL_NO_RWG_SE, i64, i64) DEF_HELPER_FLAGS_1(neon_addlp_s16, TCG_CALL_NO_RWG_SE, i64, i64) DEF_HELPER_2(neon_subl_u16, i64, i64, i64) diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index 33c0a94958..2755da8ac7 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -2467,3 +2467,233 @@ void gen_gvec_rev64(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, g_assert_not_reached(); } } + +static void gen_saddlp_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + int half = 4 << vece; + TCGv_vec t = tcg_temp_new_vec_matching(d); + + tcg_gen_shli_vec(vece, t, n, half); + tcg_gen_sari_vec(vece, d, n, half); + tcg_gen_sari_vec(vece, t, t, half); + tcg_gen_add_vec(vece, d, d, t); +} + +static void gen_saddlp_s_i64(TCGv_i64 d, TCGv_i64 n) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_ext32s_i64(t, n); + tcg_gen_sari_i64(d, n, 32); + tcg_gen_add_i64(d, d, t); +} + +void gen_gvec_saddlp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sari_vec, INDEX_op_shli_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2 g[] = { + { .fniv = gen_saddlp_vec, + .fni8 = gen_helper_neon_addlp_s8, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fniv = gen_saddlp_vec, + .fni8 = gen_helper_neon_addlp_s16, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fniv = gen_saddlp_vec, + .fni8 = gen_saddlp_s_i64, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + assert(vece <= MO_32); + tcg_gen_gvec_2(rd_ofs, rn_ofs, opr_sz, max_sz, &g[vece]); +} + +static void gen_sadalp_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + gen_saddlp_vec(vece, t, n); + tcg_gen_add_vec(vece, d, d, t); +} + +static void gen_sadalp_b_i64(TCGv_i64 d, TCGv_i64 n) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + gen_helper_neon_addlp_s8(t, n); + tcg_gen_vec_add16_i64(d, d, t); +} + +static void gen_sadalp_h_i64(TCGv_i64 d, TCGv_i64 n) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + gen_helper_neon_addlp_s16(t, n); + tcg_gen_vec_add32_i64(d, d, t); +} + +static void gen_sadalp_s_i64(TCGv_i64 d, TCGv_i64 n) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + gen_saddlp_s_i64(t, n); + tcg_gen_add_i64(d, d, t); +} + +void gen_gvec_sadalp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_sari_vec, INDEX_op_shli_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2 g[] = { + { .fniv = gen_sadalp_vec, + .fni8 = gen_sadalp_b_i64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_16 }, + { .fniv = gen_sadalp_vec, + .fni8 = gen_sadalp_h_i64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_32 }, + { .fniv = gen_sadalp_vec, + .fni8 = gen_sadalp_s_i64, + .opt_opc = vecop_list, + .load_dest = true, + .vece = MO_64 }, + }; + assert(vece <= MO_32); + tcg_gen_gvec_2(rd_ofs, rn_ofs, opr_sz, max_sz, &g[vece]); +} + +static void gen_uaddlp_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + int half = 4 << vece; + TCGv_vec t = tcg_temp_new_vec_matching(d); + TCGv_vec m = tcg_constant_vec_matching(d, vece, MAKE_64BIT_MASK(0, half)); + + tcg_gen_shri_vec(vece, t, n, half); + tcg_gen_and_vec(vece, d, n, m); + tcg_gen_add_vec(vece, d, d, t); +} + +static void gen_uaddlp_b_i64(TCGv_i64 d, TCGv_i64 n) +{ + TCGv_i64 t = tcg_temp_new_i64(); + TCGv_i64 m = tcg_constant_i64(dup_const(MO_16, 0xff)); + + tcg_gen_shri_i64(t, n, 8); + tcg_gen_and_i64(d, n, m); + tcg_gen_and_i64(t, t, m); + /* No carry between widened unsigned elements. */ + tcg_gen_add_i64(d, d, t); +} + +static void gen_uaddlp_h_i64(TCGv_i64 d, TCGv_i64 n) +{ + TCGv_i64 t = tcg_temp_new_i64(); + TCGv_i64 m = tcg_constant_i64(dup_const(MO_32, 0xffff)); + + tcg_gen_shri_i64(t, n, 16); + tcg_gen_and_i64(d, n, m); + tcg_gen_and_i64(t, t, m); + /* No carry between widened unsigned elements. */ + tcg_gen_add_i64(d, d, t); +} + +static void gen_uaddlp_s_i64(TCGv_i64 d, TCGv_i64 n) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_ext32u_i64(t, n); + tcg_gen_shri_i64(d, n, 32); + tcg_gen_add_i64(d, d, t); +} + +void gen_gvec_uaddlp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2 g[] = { + { .fniv = gen_uaddlp_vec, + .fni8 = gen_uaddlp_b_i64, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fniv = gen_uaddlp_vec, + .fni8 = gen_uaddlp_h_i64, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fniv = gen_uaddlp_vec, + .fni8 = gen_uaddlp_s_i64, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + assert(vece <= MO_32); + tcg_gen_gvec_2(rd_ofs, rn_ofs, opr_sz, max_sz, &g[vece]); +} + +static void gen_uadalp_vec(unsigned vece, TCGv_vec d, TCGv_vec n) +{ + TCGv_vec t = tcg_temp_new_vec_matching(d); + + gen_uaddlp_vec(vece, t, n); + tcg_gen_add_vec(vece, d, d, t); +} + +static void gen_uadalp_b_i64(TCGv_i64 d, TCGv_i64 n) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + gen_uaddlp_b_i64(t, n); + tcg_gen_vec_add16_i64(d, d, t); +} + +static void gen_uadalp_h_i64(TCGv_i64 d, TCGv_i64 n) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + gen_uaddlp_h_i64(t, n); + tcg_gen_vec_add32_i64(d, d, t); +} + +static void gen_uadalp_s_i64(TCGv_i64 d, TCGv_i64 n) +{ + TCGv_i64 t = tcg_temp_new_i64(); + + gen_uaddlp_s_i64(t, n); + tcg_gen_add_i64(d, d, t); +} + +void gen_gvec_uadalp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + static const TCGOpcode vecop_list[] = { + INDEX_op_shri_vec, INDEX_op_add_vec, 0 + }; + static const GVecGen2 g[] = { + { .fniv = gen_uadalp_vec, + .fni8 = gen_uadalp_b_i64, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_16 }, + { .fniv = gen_uadalp_vec, + .fni8 = gen_uadalp_h_i64, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_32 }, + { .fniv = gen_uadalp_vec, + .fni8 = gen_uadalp_s_i64, + .load_dest = true, + .opt_opc = vecop_list, + .vece = MO_64 }, + }; + assert(vece <= MO_32); + tcg_gen_gvec_2(rd_ofs, rn_ofs, opr_sz, max_sz, &g[vece]); +} diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index b92ddd4914..1a22857b5e 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -844,28 +844,6 @@ uint64_t HELPER(neon_addl_u32)(uint64_t a, uint64_t b) return (a + b) ^ mask; } -uint64_t HELPER(neon_paddl_u16)(uint64_t a, uint64_t b) -{ - uint64_t tmp; - uint64_t tmp2; - - tmp = a & 0x0000ffff0000ffffull; - tmp += (a >> 16) & 0x0000ffff0000ffffull; - tmp2 = b & 0xffff0000ffff0000ull; - tmp2 += (b << 16) & 0xffff0000ffff0000ull; - return ( tmp & 0xffff) - | ((tmp >> 16) & 0xffff0000ull) - | ((tmp2 << 16) & 0xffff00000000ull) - | ( tmp2 & 0xffff000000000000ull); -} - -uint64_t HELPER(neon_paddl_u32)(uint64_t a, uint64_t b) -{ - uint32_t low = a + (a >> 32); - uint32_t high = b + (b >> 32); - return low + ((uint64_t)high << 32); -} - /* Pairwise long add: add pairs of adjacent elements into * double-width elements in the result (eg _s8 is an 8x8->16 op) */ diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index ca6f5578b4..19a18018f1 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -2565,152 +2565,6 @@ static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a) return true; } -static bool do_2misc_pairwise(DisasContext *s, arg_2misc *a, - NeonGenWidenFn *widenfn, - NeonGenTwo64OpFn *opfn, - NeonGenTwo64OpFn *accfn) -{ - /* - * Pairwise long operations: widen both halves of the pair, - * combine the pairs with the opfn, and then possibly accumulate - * into the destination with the accfn. - */ - int pass; - - if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { - return false; - } - - /* UNDEF accesses to D16-D31 if they don't exist. */ - if (!dc_isar_feature(aa32_simd_r32, s) && - ((a->vd | a->vm) & 0x10)) { - return false; - } - - if ((a->vd | a->vm) & a->q) { - return false; - } - - if (!widenfn) { - return false; - } - - if (!vfp_access_check(s)) { - return true; - } - - for (pass = 0; pass < a->q + 1; pass++) { - TCGv_i32 tmp; - TCGv_i64 rm0_64, rm1_64, rd_64; - - rm0_64 = tcg_temp_new_i64(); - rm1_64 = tcg_temp_new_i64(); - rd_64 = tcg_temp_new_i64(); - - tmp = tcg_temp_new_i32(); - read_neon_element32(tmp, a->vm, pass * 2, MO_32); - widenfn(rm0_64, tmp); - read_neon_element32(tmp, a->vm, pass * 2 + 1, MO_32); - widenfn(rm1_64, tmp); - - opfn(rd_64, rm0_64, rm1_64); - - if (accfn) { - TCGv_i64 tmp64 = tcg_temp_new_i64(); - read_neon_element64(tmp64, a->vd, pass, MO_64); - accfn(rd_64, tmp64, rd_64); - } - write_neon_element64(rd_64, a->vd, pass, MO_64); - } - return true; -} - -static bool trans_VPADDL_S(DisasContext *s, arg_2misc *a) -{ - static NeonGenWidenFn * const widenfn[] = { - gen_helper_neon_widen_s8, - gen_helper_neon_widen_s16, - tcg_gen_ext_i32_i64, - NULL, - }; - static NeonGenTwo64OpFn * const opfn[] = { - gen_helper_neon_paddl_u16, - gen_helper_neon_paddl_u32, - tcg_gen_add_i64, - NULL, - }; - - return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size], NULL); -} - -static bool trans_VPADDL_U(DisasContext *s, arg_2misc *a) -{ - static NeonGenWidenFn * const widenfn[] = { - gen_helper_neon_widen_u8, - gen_helper_neon_widen_u16, - tcg_gen_extu_i32_i64, - NULL, - }; - static NeonGenTwo64OpFn * const opfn[] = { - gen_helper_neon_paddl_u16, - gen_helper_neon_paddl_u32, - tcg_gen_add_i64, - NULL, - }; - - return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size], NULL); -} - -static bool trans_VPADAL_S(DisasContext *s, arg_2misc *a) -{ - static NeonGenWidenFn * const widenfn[] = { - gen_helper_neon_widen_s8, - gen_helper_neon_widen_s16, - tcg_gen_ext_i32_i64, - NULL, - }; - static NeonGenTwo64OpFn * const opfn[] = { - gen_helper_neon_paddl_u16, - gen_helper_neon_paddl_u32, - tcg_gen_add_i64, - NULL, - }; - static NeonGenTwo64OpFn * const accfn[] = { - gen_helper_neon_addl_u16, - gen_helper_neon_addl_u32, - tcg_gen_add_i64, - NULL, - }; - - return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size], - accfn[a->size]); -} - -static bool trans_VPADAL_U(DisasContext *s, arg_2misc *a) -{ - static NeonGenWidenFn * const widenfn[] = { - gen_helper_neon_widen_u8, - gen_helper_neon_widen_u16, - tcg_gen_extu_i32_i64, - NULL, - }; - static NeonGenTwo64OpFn * const opfn[] = { - gen_helper_neon_paddl_u16, - gen_helper_neon_paddl_u32, - tcg_gen_add_i64, - NULL, - }; - static NeonGenTwo64OpFn * const accfn[] = { - gen_helper_neon_addl_u16, - gen_helper_neon_addl_u32, - tcg_gen_add_i64, - NULL, - }; - - return do_2misc_pairwise(s, a, widenfn[a->size], opfn[a->size], - accfn[a->size]); -} - typedef void ZipFn(TCGv_ptr, TCGv_ptr); static bool do_zip_uzp(DisasContext *s, arg_2misc *a, @@ -3071,6 +2925,10 @@ DO_2MISC_VEC(VCLT0, gen_gvec_clt0) DO_2MISC_VEC(VCLS, gen_gvec_cls) DO_2MISC_VEC(VCLZ, gen_gvec_clz) DO_2MISC_VEC(VREV64, gen_gvec_rev64) +DO_2MISC_VEC(VPADDL_S, gen_gvec_saddlp) +DO_2MISC_VEC(VPADDL_U, gen_gvec_uaddlp) +DO_2MISC_VEC(VPADAL_S, gen_gvec_sadalp) +DO_2MISC_VEC(VPADAL_U, gen_gvec_uadalp) static bool trans_VMVN(DisasContext *s, arg_2misc *a) { diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index 342ebedafc..edd775d564 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -593,6 +593,15 @@ void gen_gvec_rev32(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, void gen_gvec_rev64(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_saddlp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_sadalp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_uaddlp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_uadalp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz); + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ From 09e7f80e586af445ad70ba1d12c7ae282367b964 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:13 -0600 Subject: [PATCH 46/85] target/arm: Convert handle_2misc_pairwise to decodetree This includes SADDLP, UADDLP, SADALP, UADALP. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-47-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 5 ++ target/arm/tcg/helper-a64.c | 18 -------- target/arm/tcg/helper-a64.h | 2 - target/arm/tcg/translate-a64.c | 84 +++------------------------------- 4 files changed, 11 insertions(+), 98 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 05f1bc99b5..f3488766b2 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1662,3 +1662,8 @@ CMLT0_v 0.00 1110 ..1 00000 10101 0 ..... ..... @qrr_e REV16_v 0.00 1110 001 00000 00011 0 ..... ..... @qrr_b REV32_v 0.10 1110 0.1 00000 00001 0 ..... ..... @qrr_bh REV64_v 0.00 1110 ..1 00000 00001 0 ..... ..... @qrr_e + +SADDLP_v 0.00 1110 ..1 00000 00101 0 ..... ..... @qrr_e +UADDLP_v 0.10 1110 ..1 00000 00101 0 ..... ..... @qrr_e +SADALP_v 0.00 1110 ..1 00000 01101 0 ..... ..... @qrr_e +UADALP_v 0.10 1110 ..1 00000 01101 0 ..... ..... @qrr_e diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index 9b3c407be3..3de564e0fe 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -306,24 +306,6 @@ float64 HELPER(rsqrtsf_f64)(float64 a, float64 b, void *fpstp) return float64_muladd(a, b, float64_three, float_muladd_halve_result, fpst); } -uint64_t HELPER(neon_addlp_u8)(uint64_t a) -{ - uint64_t tmp; - - tmp = a & 0x00ff00ff00ff00ffULL; - tmp += (a >> 8) & 0x00ff00ff00ff00ffULL; - return tmp; -} - -uint64_t HELPER(neon_addlp_u16)(uint64_t a) -{ - uint64_t tmp; - - tmp = a & 0x0000ffff0000ffffULL; - tmp += (a >> 16) & 0x0000ffff0000ffffULL; - return tmp; -} - /* Floating-point reciprocal exponent - see FPRecpX in ARM ARM */ uint32_t HELPER(frecpx_f16)(uint32_t a, void *fpstp) { diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index f811bb85dc..ac7ca190fa 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -41,8 +41,6 @@ DEF_HELPER_FLAGS_3(recpsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr) DEF_HELPER_FLAGS_3(rsqrtsf_f16, TCG_CALL_NO_RWG, f16, f16, f16, ptr) DEF_HELPER_FLAGS_3(rsqrtsf_f32, TCG_CALL_NO_RWG, f32, f32, f32, ptr) DEF_HELPER_FLAGS_3(rsqrtsf_f64, TCG_CALL_NO_RWG, f64, f64, f64, ptr) -DEF_HELPER_FLAGS_1(neon_addlp_u8, TCG_CALL_NO_RWG_SE, i64, i64) -DEF_HELPER_FLAGS_1(neon_addlp_u16, TCG_CALL_NO_RWG_SE, i64, i64) DEF_HELPER_FLAGS_2(frecpx_f64, TCG_CALL_NO_RWG, f64, f64, ptr) DEF_HELPER_FLAGS_2(frecpx_f32, TCG_CALL_NO_RWG, f32, f32, ptr) DEF_HELPER_FLAGS_2(frecpx_f16, TCG_CALL_NO_RWG, f16, f16, ptr) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index f57b5e2855..717d30dd5b 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8956,6 +8956,10 @@ static bool do_gvec_fn2_bhs(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) TRANS(CLS_v, do_gvec_fn2_bhs, a, gen_gvec_cls) TRANS(CLZ_v, do_gvec_fn2_bhs, a, gen_gvec_clz) TRANS(REV64_v, do_gvec_fn2_bhs, a, gen_gvec_rev64) +TRANS(SADDLP_v, do_gvec_fn2_bhs, a, gen_gvec_saddlp) +TRANS(UADDLP_v, do_gvec_fn2_bhs, a, gen_gvec_uaddlp) +TRANS(SADALP_v, do_gvec_fn2_bhs, a, gen_gvec_sadalp) +TRANS(UADALP_v, do_gvec_fn2_bhs, a, gen_gvec_uadalp) /* Common vector code for handling integer to FP conversion */ static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn, @@ -9885,73 +9889,6 @@ static void handle_2misc_widening(DisasContext *s, int opcode, bool is_q, } } -static void handle_2misc_pairwise(DisasContext *s, int opcode, bool u, - bool is_q, int size, int rn, int rd) -{ - /* Implement the pairwise operations from 2-misc: - * SADDLP, UADDLP, SADALP, UADALP. - * These all add pairs of elements in the input to produce a - * double-width result element in the output (possibly accumulating). - */ - bool accum = (opcode == 0x6); - int maxpass = is_q ? 2 : 1; - int pass; - TCGv_i64 tcg_res[2]; - - if (size == 2) { - /* 32 + 32 -> 64 op */ - MemOp memop = size + (u ? 0 : MO_SIGN); - - for (pass = 0; pass < maxpass; pass++) { - TCGv_i64 tcg_op1 = tcg_temp_new_i64(); - TCGv_i64 tcg_op2 = tcg_temp_new_i64(); - - tcg_res[pass] = tcg_temp_new_i64(); - - read_vec_element(s, tcg_op1, rn, pass * 2, memop); - read_vec_element(s, tcg_op2, rn, pass * 2 + 1, memop); - tcg_gen_add_i64(tcg_res[pass], tcg_op1, tcg_op2); - if (accum) { - read_vec_element(s, tcg_op1, rd, pass, MO_64); - tcg_gen_add_i64(tcg_res[pass], tcg_res[pass], tcg_op1); - } - } - } else { - for (pass = 0; pass < maxpass; pass++) { - TCGv_i64 tcg_op = tcg_temp_new_i64(); - NeonGenOne64OpFn *genfn; - static NeonGenOne64OpFn * const fns[2][2] = { - { gen_helper_neon_addlp_s8, gen_helper_neon_addlp_u8 }, - { gen_helper_neon_addlp_s16, gen_helper_neon_addlp_u16 }, - }; - - genfn = fns[size][u]; - - tcg_res[pass] = tcg_temp_new_i64(); - - read_vec_element(s, tcg_op, rn, pass, MO_64); - genfn(tcg_res[pass], tcg_op); - - if (accum) { - read_vec_element(s, tcg_op, rd, pass, MO_64); - if (size == 0) { - gen_helper_neon_addl_u16(tcg_res[pass], - tcg_res[pass], tcg_op); - } else { - gen_helper_neon_addl_u32(tcg_res[pass], - tcg_res[pass], tcg_op); - } - } - } - } - if (!is_q) { - tcg_res[1] = tcg_constant_i64(0); - } - for (pass = 0; pass < 2; pass++) { - write_vec_element(s, tcg_res[pass], rd, pass, MO_64); - } -} - static void handle_shll(DisasContext *s, bool is_q, int size, int rn, int rd) { /* Implement SHLL and SHLL2 */ @@ -10011,17 +9948,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) handle_2misc_narrow(s, false, opcode, u, is_q, size, rn, rd); return; - case 0x2: /* SADDLP, UADDLP */ - case 0x6: /* SADALP, UADALP */ - if (size == 3) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - handle_2misc_pairwise(s, opcode, u, is_q, size, rn, rd); - return; case 0x13: /* SHLL, SHLL2 */ if (u == 0 || size == 3) { unallocated_encoding(s); @@ -10203,9 +10129,11 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) default: case 0x0: /* REV64, REV32 */ case 0x1: /* REV16 */ + case 0x2: /* SADDLP, UADDLP */ case 0x3: /* SUQADD, USQADD */ case 0x4: /* CLS, CLZ */ case 0x5: /* CNT, NOT, RBIT */ + case 0x6: /* SADALP, UADALP */ case 0x7: /* SQABS, SQNEG */ case 0x8: /* CMGT, CMGE */ case 0x9: /* CMEQ, CMLE */ From 07e0d7a0c79fe1f694f668398bea7aa686659afb Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:14 -0600 Subject: [PATCH 47/85] target/arm: Remove helper_neon_{add,sub}l_u{16,32} These have generic equivalents: tcg_gen_vec_{add,sub}{16,32}_i64. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-48-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 4 ---- target/arm/tcg/neon_helper.c | 36 --------------------------------- target/arm/tcg/translate-neon.c | 22 ++++++++++---------- 3 files changed, 11 insertions(+), 51 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 6369d07d05..04e422ab08 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -395,12 +395,8 @@ DEF_HELPER_1(neon_widen_s8, i64, i32) DEF_HELPER_1(neon_widen_u16, i64, i32) DEF_HELPER_1(neon_widen_s16, i64, i32) -DEF_HELPER_2(neon_addl_u16, i64, i64, i64) -DEF_HELPER_2(neon_addl_u32, i64, i64, i64) DEF_HELPER_FLAGS_1(neon_addlp_s8, TCG_CALL_NO_RWG_SE, i64, i64) DEF_HELPER_FLAGS_1(neon_addlp_s16, TCG_CALL_NO_RWG_SE, i64, i64) -DEF_HELPER_2(neon_subl_u16, i64, i64, i64) -DEF_HELPER_2(neon_subl_u32, i64, i64, i64) DEF_HELPER_3(neon_addl_saturate_s32, i64, env, i64, i64) DEF_HELPER_3(neon_addl_saturate_s64, i64, env, i64, i64) DEF_HELPER_2(neon_abdl_u16, i64, i32, i32) diff --git a/target/arm/tcg/neon_helper.c b/target/arm/tcg/neon_helper.c index 1a22857b5e..c687e882ad 100644 --- a/target/arm/tcg/neon_helper.c +++ b/target/arm/tcg/neon_helper.c @@ -826,24 +826,6 @@ uint64_t HELPER(neon_widen_s16)(uint32_t x) return ((uint32_t)(int16_t)x) | (high << 32); } -uint64_t HELPER(neon_addl_u16)(uint64_t a, uint64_t b) -{ - uint64_t mask; - mask = (a ^ b) & 0x8000800080008000ull; - a &= ~0x8000800080008000ull; - b &= ~0x8000800080008000ull; - return (a + b) ^ mask; -} - -uint64_t HELPER(neon_addl_u32)(uint64_t a, uint64_t b) -{ - uint64_t mask; - mask = (a ^ b) & 0x8000000080000000ull; - a &= ~0x8000000080000000ull; - b &= ~0x8000000080000000ull; - return (a + b) ^ mask; -} - /* Pairwise long add: add pairs of adjacent elements into * double-width elements in the result (eg _s8 is an 8x8->16 op) */ @@ -887,24 +869,6 @@ uint64_t HELPER(neon_addlp_s16)(uint64_t a) return (uint32_t)reslo | (((uint64_t)reshi) << 32); } -uint64_t HELPER(neon_subl_u16)(uint64_t a, uint64_t b) -{ - uint64_t mask; - mask = (a ^ ~b) & 0x8000800080008000ull; - a |= 0x8000800080008000ull; - b &= ~0x8000800080008000ull; - return (a - b) ^ mask; -} - -uint64_t HELPER(neon_subl_u32)(uint64_t a, uint64_t b) -{ - uint64_t mask; - mask = (a ^ ~b) & 0x8000000080000000ull; - a |= 0x8000000080000000ull; - b &= ~0x8000000080000000ull; - return (a - b) ^ mask; -} - uint64_t HELPER(neon_addl_saturate_s32)(CPUARMState *env, uint64_t a, uint64_t b) { uint32_t x, y; diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index 19a18018f1..0821f10fad 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -1560,8 +1560,8 @@ static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, NULL, NULL, \ }; \ static NeonGenTwo64OpFn * const addfn[] = { \ - gen_helper_neon_##OP##l_u16, \ - gen_helper_neon_##OP##l_u32, \ + tcg_gen_vec_##OP##16_i64, \ + tcg_gen_vec_##OP##32_i64, \ tcg_gen_##OP##_i64, \ NULL, \ }; \ @@ -1639,8 +1639,8 @@ static bool do_narrow_3d(DisasContext *s, arg_3diff *a, static bool trans_##INSN##_3d(DisasContext *s, arg_3diff *a) \ { \ static NeonGenTwo64OpFn * const addfn[] = { \ - gen_helper_neon_##OP##l_u16, \ - gen_helper_neon_##OP##l_u32, \ + tcg_gen_vec_##OP##16_i64, \ + tcg_gen_vec_##OP##32_i64, \ tcg_gen_##OP##_i64, \ NULL, \ }; \ @@ -1761,8 +1761,8 @@ static bool trans_VABAL_S_3d(DisasContext *s, arg_3diff *a) NULL, }; static NeonGenTwo64OpFn * const addfn[] = { - gen_helper_neon_addl_u16, - gen_helper_neon_addl_u32, + tcg_gen_vec_add16_i64, + tcg_gen_vec_add32_i64, tcg_gen_add_i64, NULL, }; @@ -1779,8 +1779,8 @@ static bool trans_VABAL_U_3d(DisasContext *s, arg_3diff *a) NULL, }; static NeonGenTwo64OpFn * const addfn[] = { - gen_helper_neon_addl_u16, - gen_helper_neon_addl_u32, + tcg_gen_vec_add16_i64, + tcg_gen_vec_add32_i64, tcg_gen_add_i64, NULL, }; @@ -1840,8 +1840,8 @@ static bool trans_VMULL_U_3d(DisasContext *s, arg_3diff *a) NULL, \ }; \ static NeonGenTwo64OpFn * const accfn[] = { \ - gen_helper_neon_##ACC##l_u16, \ - gen_helper_neon_##ACC##l_u32, \ + tcg_gen_vec_##ACC##16_i64, \ + tcg_gen_vec_##ACC##32_i64, \ tcg_gen_##ACC##_i64, \ NULL, \ }; \ @@ -2371,7 +2371,7 @@ static bool trans_VMULL_U_2sc(DisasContext *s, arg_2scalar *a) }; \ static NeonGenTwo64OpFn * const accfn[] = { \ NULL, \ - gen_helper_neon_##ACC##l_u32, \ + tcg_gen_vec_##ACC##32_i64, \ tcg_gen_##ACC##_i64, \ NULL, \ }; \ From ace363a1e970a1f61b407f6e205caaacd7918e09 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:15 -0600 Subject: [PATCH 48/85] target/arm: Introduce clear_vec MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In a couple of places, clearing the entire vector before storing one element is the easiest solution. Wrap that into a helper function. Reviewed-by: Philippe Mathieu-Daudé Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-49-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/translate-a64.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 717d30dd5b..0e8e867058 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -628,7 +628,16 @@ static TCGv_i32 read_fp_hreg(DisasContext *s, int reg) return v; } -/* Clear the bits above an N-bit vector, for N = (is_q ? 128 : 64). +static void clear_vec(DisasContext *s, int rd) +{ + unsigned ofs = fp_reg_offset(s, rd, MO_64); + unsigned vsz = vec_full_reg_size(s); + + tcg_gen_gvec_dup_imm(MO_64, ofs, vsz, vsz, 0); +} + +/* + * 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. */ static void clear_vec_high(DisasContext *s, bool is_q, int rd) @@ -4851,7 +4860,6 @@ static bool trans_SM3SS1(DisasContext *s, arg_SM3SS1 *a) TCGv_i32 tcg_op2 = tcg_temp_new_i32(); TCGv_i32 tcg_op3 = tcg_temp_new_i32(); TCGv_i32 tcg_res = tcg_temp_new_i32(); - unsigned vsz, dofs; read_vec_element_i32(s, tcg_op1, a->rn, 3, MO_32); read_vec_element_i32(s, tcg_op2, a->rm, 3, MO_32); @@ -4863,9 +4871,7 @@ static bool trans_SM3SS1(DisasContext *s, arg_SM3SS1 *a) tcg_gen_rotri_i32(tcg_res, tcg_res, 25); /* Clear the whole register first, then store bits [127:96]. */ - vsz = vec_full_reg_size(s); - dofs = vec_full_reg_offset(s, a->rd); - tcg_gen_gvec_dup_imm(MO_64, dofs, vsz, vsz, 0); + clear_vec(s, a->rd); write_vec_element_i32(s, tcg_res, a->rd, 3, MO_32); } return true; @@ -6307,7 +6313,6 @@ static bool do_scalar_muladd_widening_idx(DisasContext *s, arg_rrx_e *a, TCGv_i64 t0 = tcg_temp_new_i64(); TCGv_i64 t1 = tcg_temp_new_i64(); TCGv_i64 t2 = tcg_temp_new_i64(); - unsigned vsz, dofs; if (acc) { read_vec_element(s, t0, a->rd, 0, a->esz + 1); @@ -6317,9 +6322,7 @@ static bool do_scalar_muladd_widening_idx(DisasContext *s, arg_rrx_e *a, fn(t0, t1, t2); /* Clear the whole register first, then store scalar. */ - vsz = vec_full_reg_size(s); - dofs = vec_full_reg_offset(s, a->rd); - tcg_gen_gvec_dup_imm(MO_64, dofs, vsz, vsz, 0); + clear_vec(s, a->rd); write_vec_element(s, t0, a->rd, 0, a->esz + 1); } return true; From fbbc0b2c8a17d4dc23311b613f82e725246a8022 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:16 -0600 Subject: [PATCH 49/85] target/arm: Convert XTN, SQXTUN, SQXTN, UQXTN to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-50-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 9 ++ target/arm/tcg/translate-a64.c | 153 ++++++++++++++++++++------------- 2 files changed, 102 insertions(+), 60 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index f3488766b2..295329448f 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1642,6 +1642,10 @@ CMEQ0_s 0101 1110 111 00000 10011 0 ..... ..... @rr CMLE0_s 0111 1110 111 00000 10011 0 ..... ..... @rr CMLT0_s 0101 1110 111 00000 10101 0 ..... ..... @rr +SQXTUN_s 0111 1110 ..1 00001 00101 0 ..... ..... @rr_e +SQXTN_s 0101 1110 ..1 00001 01001 0 ..... ..... @rr_e +UQXTN_s 0111 1110 ..1 00001 01001 0 ..... ..... @rr_e + # Advanced SIMD two-register miscellaneous SQABS_v 0.00 1110 ..1 00000 01111 0 ..... ..... @qrr_e @@ -1667,3 +1671,8 @@ SADDLP_v 0.00 1110 ..1 00000 00101 0 ..... ..... @qrr_e UADDLP_v 0.10 1110 ..1 00000 00101 0 ..... ..... @qrr_e SADALP_v 0.00 1110 ..1 00000 01101 0 ..... ..... @qrr_e UADALP_v 0.10 1110 ..1 00000 01101 0 ..... ..... @qrr_e + +XTN 0.00 1110 ..1 00001 00101 0 ..... ..... @qrr_e +SQXTUN_v 0.10 1110 ..1 00001 00101 0 ..... ..... @qrr_e +SQXTN_v 0.00 1110 ..1 00001 01001 0 ..... ..... @qrr_e +UQXTN_v 0.10 1110 ..1 00001 01001 0 ..... ..... @qrr_e diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 0e8e867058..7b76945b0a 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8921,6 +8921,62 @@ TRANS(CMLE0_s, do_cmop0_d, a, TCG_COND_LE) TRANS(CMLT0_s, do_cmop0_d, a, TCG_COND_LT) TRANS(CMEQ0_s, do_cmop0_d, a, TCG_COND_EQ) +static bool do_2misc_narrow_scalar(DisasContext *s, arg_rr_e *a, + ArithOneOp * const fn[3]) +{ + if (a->esz == MO_64) { + return false; + } + if (fp_access_check(s)) { + TCGv_i64 t = tcg_temp_new_i64(); + + read_vec_element(s, t, a->rn, 0, a->esz + 1); + fn[a->esz](t, t); + clear_vec(s, a->rd); + write_vec_element(s, t, a->rd, 0, a->esz); + } + return true; +} + +#define WRAP_ENV(NAME) \ + static void gen_##NAME(TCGv_i64 d, TCGv_i64 n) \ + { gen_helper_##NAME(d, tcg_env, n); } + +WRAP_ENV(neon_unarrow_sat8) +WRAP_ENV(neon_unarrow_sat16) +WRAP_ENV(neon_unarrow_sat32) + +static ArithOneOp * const f_scalar_sqxtun[] = { + gen_neon_unarrow_sat8, + gen_neon_unarrow_sat16, + gen_neon_unarrow_sat32, +}; +TRANS(SQXTUN_s, do_2misc_narrow_scalar, a, f_scalar_sqxtun) + +WRAP_ENV(neon_narrow_sat_s8) +WRAP_ENV(neon_narrow_sat_s16) +WRAP_ENV(neon_narrow_sat_s32) + +static ArithOneOp * const f_scalar_sqxtn[] = { + gen_neon_narrow_sat_s8, + gen_neon_narrow_sat_s16, + gen_neon_narrow_sat_s32, +}; +TRANS(SQXTN_s, do_2misc_narrow_scalar, a, f_scalar_sqxtn) + +WRAP_ENV(neon_narrow_sat_u8) +WRAP_ENV(neon_narrow_sat_u16) +WRAP_ENV(neon_narrow_sat_u32) + +static ArithOneOp * const f_scalar_uqxtn[] = { + gen_neon_narrow_sat_u8, + gen_neon_narrow_sat_u16, + gen_neon_narrow_sat_u32, +}; +TRANS(UQXTN_s, do_2misc_narrow_scalar, a, f_scalar_uqxtn) + +#undef WRAP_ENV + static bool do_gvec_fn2(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) { if (!a->q && a->esz == MO_64) { @@ -8964,6 +9020,37 @@ TRANS(UADDLP_v, do_gvec_fn2_bhs, a, gen_gvec_uaddlp) TRANS(SADALP_v, do_gvec_fn2_bhs, a, gen_gvec_sadalp) TRANS(UADALP_v, do_gvec_fn2_bhs, a, gen_gvec_uadalp) +static bool do_2misc_narrow_vector(DisasContext *s, arg_qrr_e *a, + ArithOneOp * const fn[3]) +{ + if (a->esz == MO_64) { + return false; + } + if (fp_access_check(s)) { + TCGv_i64 t0 = tcg_temp_new_i64(); + TCGv_i64 t1 = tcg_temp_new_i64(); + + read_vec_element(s, t0, a->rn, 0, MO_64); + read_vec_element(s, t1, a->rn, 1, MO_64); + fn[a->esz](t0, t0); + fn[a->esz](t1, t1); + write_vec_element(s, t0, a->rd, a->q ? 2 : 0, MO_32); + write_vec_element(s, t1, a->rd, a->q ? 3 : 1, MO_32); + clear_vec_high(s, a->q, a->rd); + } + return true; +} + +static ArithOneOp * const f_scalar_xtn[] = { + gen_helper_neon_narrow_u8, + gen_helper_neon_narrow_u16, + tcg_gen_ext32u_i64, +}; +TRANS(XTN, do_2misc_narrow_vector, a, f_scalar_xtn) +TRANS(SQXTUN_v, do_2misc_narrow_vector, a, f_scalar_sqxtun) +TRANS(SQXTN_v, do_2misc_narrow_vector, a, f_scalar_sqxtn) +TRANS(UQXTN_v, do_2misc_narrow_vector, a, f_scalar_uqxtn) + /* Common vector code for handling integer to FP conversion */ static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn, int elements, int is_signed, @@ -9546,38 +9633,6 @@ static void handle_2misc_narrow(DisasContext *s, bool scalar, tcg_res[pass] = tcg_temp_new_i64(); switch (opcode) { - case 0x12: /* XTN, SQXTUN */ - { - static NeonGenOne64OpFn * const xtnfns[3] = { - gen_helper_neon_narrow_u8, - gen_helper_neon_narrow_u16, - tcg_gen_ext32u_i64, - }; - static NeonGenOne64OpEnvFn * const sqxtunfns[3] = { - gen_helper_neon_unarrow_sat8, - gen_helper_neon_unarrow_sat16, - gen_helper_neon_unarrow_sat32, - }; - if (u) { - genenvfn = sqxtunfns[size]; - } else { - genfn = xtnfns[size]; - } - break; - } - case 0x14: /* SQXTN, UQXTN */ - { - static NeonGenOne64OpEnvFn * const fns[3][2] = { - { gen_helper_neon_narrow_sat_s8, - gen_helper_neon_narrow_sat_u8 }, - { gen_helper_neon_narrow_sat_s16, - gen_helper_neon_narrow_sat_u16 }, - { gen_helper_neon_narrow_sat_s32, - gen_helper_neon_narrow_sat_u32 }, - }; - genenvfn = fns[size][u]; - break; - } case 0x16: /* FCVTN, FCVTN2 */ /* 32 bit to 16 bit or 64 bit to 32 bit float conversion */ if (size == 2) { @@ -9618,6 +9673,8 @@ static void handle_2misc_narrow(DisasContext *s, bool scalar, } break; default: + case 0x12: /* XTN, SQXTUN */ + case 0x14: /* SQXTN, UQXTN */ g_assert_not_reached(); } @@ -9653,22 +9710,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) TCGv_ptr tcg_fpstatus; switch (opcode) { - case 0x12: /* SQXTUN */ - if (!u) { - unallocated_encoding(s); - return; - } - /* fall through */ - case 0x14: /* SQXTN, UQXTN */ - if (size == 3) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - handle_2misc_narrow(s, true, opcode, u, false, size, rn, rd); - return; case 0xc ... 0xf: case 0x16 ... 0x1d: case 0x1f: @@ -9742,6 +9783,8 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) case 0x9: /* CMEQ, CMLE */ case 0xa: /* CMLT */ case 0xb: /* ABS, NEG */ + case 0x12: /* SQXTUN */ + case 0x14: /* SQXTN, UQXTN */ unallocated_encoding(s); return; } @@ -9939,18 +9982,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) TCGv_ptr tcg_fpstatus; switch (opcode) { - case 0x12: /* XTN, XTN2, SQXTUN, SQXTUN2 */ - case 0x14: /* SQXTN, SQXTN2, UQXTN, UQXTN2 */ - if (size == 3) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - - handle_2misc_narrow(s, false, opcode, u, is_q, size, rn, rd); - return; case 0x13: /* SHLL, SHLL2 */ if (u == 0 || size == 3) { unallocated_encoding(s); @@ -10142,6 +10173,8 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x9: /* CMEQ, CMLE */ case 0xa: /* CMLT */ case 0xb: /* ABS, NEG */ + case 0x12: /* XTN, XTN2, SQXTUN, SQXTUN2 */ + case 0x14: /* SQXTN, SQXTN2, UQXTN, UQXTN2 */ unallocated_encoding(s); return; } From febacdb237bdd93922c3c452083a2e840179ab6a Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:17 -0600 Subject: [PATCH 50/85] target/arm: Convert FCVTN, BFCVTN to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-51-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 5 ++ target/arm/tcg/translate-a64.c | 89 ++++++++++++++++++---------------- 2 files changed, 52 insertions(+), 42 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 295329448f..456912cd7c 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -21,6 +21,7 @@ %rd 0:5 %esz_sd 22:1 !function=plus_2 +%esz_hs 22:1 !function=plus_1 %esz_hsd 22:2 !function=xor_2 %hl 11:1 21:1 %hlm 11:1 20:2 @@ -74,6 +75,7 @@ @qrr_b . q:1 ...... .. ...... ...... rn:5 rd:5 &qrr_e esz=0 @qrr_h . q:1 ...... .. ...... ...... rn:5 rd:5 &qrr_e esz=1 @qrr_bh . q:1 ...... . esz:1 ...... ...... rn:5 rd:5 &qrr_e +@qrr_hs . q:1 ...... .. ...... ...... rn:5 rd:5 &qrr_e esz=%esz_hs @qrr_e . q:1 ...... esz:2 ...... ...... rn:5 rd:5 &qrr_e @qrrr_b . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=0 @@ -1676,3 +1678,6 @@ XTN 0.00 1110 ..1 00001 00101 0 ..... ..... @qrr_e SQXTUN_v 0.10 1110 ..1 00001 00101 0 ..... ..... @qrr_e SQXTN_v 0.00 1110 ..1 00001 01001 0 ..... ..... @qrr_e UQXTN_v 0.10 1110 ..1 00001 01001 0 ..... ..... @qrr_e + +FCVTN_v 0.00 1110 0.1 00001 01101 0 ..... ..... @qrr_hs +BFCVTN_v 0.00 1110 101 00001 01101 0 ..... ..... @qrr_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 7b76945b0a..d4d19c9caa 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -9051,6 +9051,49 @@ TRANS(SQXTUN_v, do_2misc_narrow_vector, a, f_scalar_sqxtun) TRANS(SQXTN_v, do_2misc_narrow_vector, a, f_scalar_sqxtn) TRANS(UQXTN_v, do_2misc_narrow_vector, a, f_scalar_uqxtn) +static void gen_fcvtn_hs(TCGv_i64 d, TCGv_i64 n) +{ + TCGv_i32 tcg_lo = tcg_temp_new_i32(); + TCGv_i32 tcg_hi = tcg_temp_new_i32(); + TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); + TCGv_i32 ahp = get_ahp_flag(); + + tcg_gen_extr_i64_i32(tcg_lo, tcg_hi, n); + gen_helper_vfp_fcvt_f32_to_f16(tcg_lo, tcg_lo, fpst, ahp); + gen_helper_vfp_fcvt_f32_to_f16(tcg_hi, tcg_hi, fpst, ahp); + tcg_gen_deposit_i32(tcg_lo, tcg_lo, tcg_hi, 16, 16); + tcg_gen_extu_i32_i64(d, tcg_lo); +} + +static void gen_fcvtn_sd(TCGv_i64 d, TCGv_i64 n) +{ + TCGv_i32 tmp = tcg_temp_new_i32(); + gen_helper_vfp_fcvtsd(tmp, n, tcg_env); + tcg_gen_extu_i32_i64(d, tmp); +} + +static ArithOneOp * const f_vector_fcvtn[] = { + NULL, + gen_fcvtn_hs, + gen_fcvtn_sd, +}; +TRANS(FCVTN_v, do_2misc_narrow_vector, a, f_vector_fcvtn) + +static void gen_bfcvtn_hs(TCGv_i64 d, TCGv_i64 n) +{ + TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); + TCGv_i32 tmp = tcg_temp_new_i32(); + gen_helper_bfcvt_pair(tmp, n, fpst); + tcg_gen_extu_i32_i64(d, tmp); +} + +static ArithOneOp * const f_vector_bfcvtn[] = { + NULL, + gen_bfcvtn_hs, + NULL, +}; +TRANS_FEAT(BFCVTN_v, aa64_bf16, do_2misc_narrow_vector, a, f_vector_bfcvtn) + /* Common vector code for handling integer to FP conversion */ static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn, int elements, int is_signed, @@ -9633,33 +9676,6 @@ static void handle_2misc_narrow(DisasContext *s, bool scalar, tcg_res[pass] = tcg_temp_new_i64(); switch (opcode) { - case 0x16: /* FCVTN, FCVTN2 */ - /* 32 bit to 16 bit or 64 bit to 32 bit float conversion */ - if (size == 2) { - TCGv_i32 tmp = tcg_temp_new_i32(); - gen_helper_vfp_fcvtsd(tmp, tcg_op, tcg_env); - tcg_gen_extu_i32_i64(tcg_res[pass], tmp); - } else { - TCGv_i32 tcg_lo = tcg_temp_new_i32(); - TCGv_i32 tcg_hi = tcg_temp_new_i32(); - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); - TCGv_i32 ahp = get_ahp_flag(); - - tcg_gen_extr_i64_i32(tcg_lo, tcg_hi, tcg_op); - gen_helper_vfp_fcvt_f32_to_f16(tcg_lo, tcg_lo, fpst, ahp); - gen_helper_vfp_fcvt_f32_to_f16(tcg_hi, tcg_hi, fpst, ahp); - tcg_gen_deposit_i32(tcg_lo, tcg_lo, tcg_hi, 16, 16); - tcg_gen_extu_i32_i64(tcg_res[pass], tcg_lo); - } - break; - case 0x36: /* BFCVTN, BFCVTN2 */ - { - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); - TCGv_i32 tmp = tcg_temp_new_i32(); - gen_helper_bfcvt_pair(tmp, tcg_op, fpst); - tcg_gen_extu_i32_i64(tcg_res[pass], tmp); - } - break; case 0x56: /* FCVTXN, FCVTXN2 */ { /* @@ -9675,6 +9691,8 @@ static void handle_2misc_narrow(DisasContext *s, bool scalar, default: case 0x12: /* XTN, SQXTUN */ case 0x14: /* SQXTN, UQXTN */ + case 0x16: /* FCVTN, FCVTN2 */ + case 0x36: /* BFCVTN, BFCVTN2 */ g_assert_not_reached(); } @@ -10088,21 +10106,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - /* fall through */ - case 0x16: /* FCVTN, FCVTN2 */ - /* handle_2misc_narrow does a 2*size -> size operation, but these - * instructions encode the source size rather than dest size. - */ - if (!fp_access_check(s)) { - return; - } - handle_2misc_narrow(s, false, opcode, 0, is_q, size - 1, rn, rd); - return; - case 0x36: /* BFCVTN, BFCVTN2 */ - if (!dc_isar_feature(aa64_bf16, s) || size != 2) { - unallocated_encoding(s); - return; - } if (!fp_access_check(s)) { return; } @@ -10155,6 +10158,8 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } break; default: + case 0x16: /* FCVTN, FCVTN2 */ + case 0x36: /* BFCVTN, BFCVTN2 */ unallocated_encoding(s); return; } From 1fd9aa0b89f16343e9aa50cf1f2e84e7339646f4 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:18 -0600 Subject: [PATCH 51/85] target/arm: Convert FCVTXN to decodetree Remove handle_2misc_narrow as this was the last insn decoded by that function. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-52-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 4 ++ target/arm/tcg/translate-a64.c | 101 +++++++-------------------------- 2 files changed, 24 insertions(+), 81 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 456912cd7c..d8902dfb22 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -74,6 +74,7 @@ @qrr_b . q:1 ...... .. ...... ...... rn:5 rd:5 &qrr_e esz=0 @qrr_h . q:1 ...... .. ...... ...... rn:5 rd:5 &qrr_e esz=1 +@qrr_s . q:1 ...... .. ...... ...... rn:5 rd:5 &qrr_e esz=2 @qrr_bh . q:1 ...... . esz:1 ...... ...... rn:5 rd:5 &qrr_e @qrr_hs . q:1 ...... .. ...... ...... rn:5 rd:5 &qrr_e esz=%esz_hs @qrr_e . q:1 ...... esz:2 ...... ...... rn:5 rd:5 &qrr_e @@ -1648,6 +1649,8 @@ SQXTUN_s 0111 1110 ..1 00001 00101 0 ..... ..... @rr_e SQXTN_s 0101 1110 ..1 00001 01001 0 ..... ..... @rr_e UQXTN_s 0111 1110 ..1 00001 01001 0 ..... ..... @rr_e +FCVTXN_s 0111 1110 011 00001 01101 0 ..... ..... @rr_s + # Advanced SIMD two-register miscellaneous SQABS_v 0.00 1110 ..1 00000 01111 0 ..... ..... @qrr_e @@ -1680,4 +1683,5 @@ SQXTN_v 0.00 1110 ..1 00001 01001 0 ..... ..... @qrr_e UQXTN_v 0.10 1110 ..1 00001 01001 0 ..... ..... @qrr_e FCVTN_v 0.00 1110 0.1 00001 01101 0 ..... ..... @qrr_hs +FCVTXN_v 0.10 1110 011 00001 01101 0 ..... ..... @qrr_s BFCVTN_v 0.00 1110 101 00001 01101 0 ..... ..... @qrr_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index d4d19c9caa..1c454a37f4 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8975,6 +8975,24 @@ static ArithOneOp * const f_scalar_uqxtn[] = { }; TRANS(UQXTN_s, do_2misc_narrow_scalar, a, f_scalar_uqxtn) +static void gen_fcvtxn_sd(TCGv_i64 d, TCGv_i64 n) +{ + /* + * 64 bit to 32 bit float conversion + * with von Neumann rounding (round to odd) + */ + TCGv_i32 tmp = tcg_temp_new_i32(); + gen_helper_fcvtx_f64_to_f32(tmp, n, tcg_env); + tcg_gen_extu_i32_i64(d, tmp); +} + +static ArithOneOp * const f_scalar_fcvtxn[] = { + NULL, + NULL, + gen_fcvtxn_sd, +}; +TRANS(FCVTXN_s, do_2misc_narrow_scalar, a, f_scalar_fcvtxn) + #undef WRAP_ENV static bool do_gvec_fn2(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) @@ -9078,6 +9096,7 @@ static ArithOneOp * const f_vector_fcvtn[] = { gen_fcvtn_sd, }; TRANS(FCVTN_v, do_2misc_narrow_vector, a, f_vector_fcvtn) +TRANS(FCVTXN_v, do_2misc_narrow_vector, a, f_scalar_fcvtxn) static void gen_bfcvtn_hs(TCGv_i64 d, TCGv_i64 n) { @@ -9647,68 +9666,6 @@ static void handle_2misc_reciprocal(DisasContext *s, int opcode, } } -static void handle_2misc_narrow(DisasContext *s, bool scalar, - int opcode, bool u, bool is_q, - int size, int rn, int rd) -{ - /* Handle 2-reg-misc ops which are narrowing (so each 2*size element - * in the source becomes a size element in the destination). - */ - int pass; - TCGv_i64 tcg_res[2]; - int destelt = is_q ? 2 : 0; - int passes = scalar ? 1 : 2; - - if (scalar) { - tcg_res[1] = tcg_constant_i64(0); - } - - for (pass = 0; pass < passes; pass++) { - TCGv_i64 tcg_op = tcg_temp_new_i64(); - NeonGenOne64OpFn *genfn = NULL; - NeonGenOne64OpEnvFn *genenvfn = NULL; - - if (scalar) { - read_vec_element(s, tcg_op, rn, pass, size + 1); - } else { - read_vec_element(s, tcg_op, rn, pass, MO_64); - } - tcg_res[pass] = tcg_temp_new_i64(); - - switch (opcode) { - case 0x56: /* FCVTXN, FCVTXN2 */ - { - /* - * 64 bit to 32 bit float conversion - * with von Neumann rounding (round to odd) - */ - TCGv_i32 tmp = tcg_temp_new_i32(); - assert(size == 2); - gen_helper_fcvtx_f64_to_f32(tmp, tcg_op, tcg_env); - tcg_gen_extu_i32_i64(tcg_res[pass], tmp); - } - break; - default: - case 0x12: /* XTN, SQXTUN */ - case 0x14: /* SQXTN, UQXTN */ - case 0x16: /* FCVTN, FCVTN2 */ - case 0x36: /* BFCVTN, BFCVTN2 */ - g_assert_not_reached(); - } - - if (genfn) { - genfn(tcg_res[pass], tcg_op); - } else if (genenvfn) { - genenvfn(tcg_res[pass], tcg_env, tcg_op); - } - } - - for (pass = 0; pass < 2; pass++) { - write_vec_element(s, tcg_res[pass], rd, destelt + pass, MO_32); - } - clear_vec_high(s, is_q, rd); -} - /* AdvSIMD scalar two reg misc * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0 * +-----+---+-----------+------+-----------+--------+-----+------+------+ @@ -9780,15 +9737,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) rmode = FPROUNDING_TIEAWAY; break; case 0x56: /* FCVTXN, FCVTXN2 */ - if (size == 2) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - handle_2misc_narrow(s, true, opcode, u, false, size - 1, rn, rd); - return; default: unallocated_encoding(s); return; @@ -10101,16 +10049,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } handle_2misc_reciprocal(s, opcode, false, u, is_q, size, rn, rd); return; - case 0x56: /* FCVTXN, FCVTXN2 */ - if (size == 2) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - handle_2misc_narrow(s, false, opcode, 0, is_q, size - 1, rn, rd); - return; case 0x17: /* FCVTL, FCVTL2 */ if (!fp_access_check(s)) { return; @@ -10160,6 +10098,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) default: case 0x16: /* FCVTN, FCVTN2 */ case 0x36: /* BFCVTN, BFCVTN2 */ + case 0x56: /* FCVTXN, FCVTXN2 */ unallocated_encoding(s); return; } From a05c56178af71852bf8035c24861bf1fb0e28c77 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:19 -0600 Subject: [PATCH 52/85] target/arm: Convert SHLL to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-53-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 2 + target/arm/tcg/translate-a64.c | 75 +++++++++++++++++----------------- 2 files changed, 40 insertions(+), 37 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index d8902dfb22..ec0d46a563 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1685,3 +1685,5 @@ UQXTN_v 0.10 1110 ..1 00001 01001 0 ..... ..... @qrr_e FCVTN_v 0.00 1110 0.1 00001 01101 0 ..... ..... @qrr_hs FCVTXN_v 0.10 1110 011 00001 01101 0 ..... ..... @qrr_s BFCVTN_v 0.00 1110 101 00001 01101 0 ..... ..... @qrr_h + +SHLL_v 0.10 1110 ..1 00001 00111 0 ..... ..... @qrr_e diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 1c454a37f4..c5d456de3b 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -9113,6 +9113,43 @@ static ArithOneOp * const f_vector_bfcvtn[] = { }; TRANS_FEAT(BFCVTN_v, aa64_bf16, do_2misc_narrow_vector, a, f_vector_bfcvtn) +static bool trans_SHLL_v(DisasContext *s, arg_qrr_e *a) +{ + static NeonGenWidenFn * const widenfns[3] = { + gen_helper_neon_widen_u8, + gen_helper_neon_widen_u16, + tcg_gen_extu_i32_i64, + }; + NeonGenWidenFn *widenfn; + TCGv_i64 tcg_res[2]; + TCGv_i32 tcg_op; + int part, pass; + + if (a->esz == MO_64) { + return false; + } + if (!fp_access_check(s)) { + return true; + } + + tcg_op = tcg_temp_new_i32(); + widenfn = widenfns[a->esz]; + part = a->q ? 2 : 0; + + for (pass = 0; pass < 2; pass++) { + read_vec_element_i32(s, tcg_op, a->rn, part + pass, MO_32); + tcg_res[pass] = tcg_temp_new_i64(); + widenfn(tcg_res[pass], tcg_op); + tcg_gen_shli_i64(tcg_res[pass], tcg_res[pass], 8 << a->esz); + } + + for (pass = 0; pass < 2; pass++) { + write_vec_element(s, tcg_res[pass], a->rd, pass, MO_64); + } + return true; +} + + /* Common vector code for handling integer to FP conversion */ static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn, int elements, int is_signed, @@ -9901,33 +9938,6 @@ static void handle_2misc_widening(DisasContext *s, int opcode, bool is_q, } } -static void handle_shll(DisasContext *s, bool is_q, int size, int rn, int rd) -{ - /* Implement SHLL and SHLL2 */ - int pass; - int part = is_q ? 2 : 0; - TCGv_i64 tcg_res[2]; - - for (pass = 0; pass < 2; pass++) { - static NeonGenWidenFn * const widenfns[3] = { - gen_helper_neon_widen_u8, - gen_helper_neon_widen_u16, - tcg_gen_extu_i32_i64, - }; - NeonGenWidenFn *widenfn = widenfns[size]; - TCGv_i32 tcg_op = tcg_temp_new_i32(); - - read_vec_element_i32(s, tcg_op, rn, part + pass, MO_32); - tcg_res[pass] = tcg_temp_new_i64(); - widenfn(tcg_res[pass], tcg_op); - tcg_gen_shli_i64(tcg_res[pass], tcg_res[pass], 8 << size); - } - - for (pass = 0; pass < 2; pass++) { - write_vec_element(s, tcg_res[pass], rd, pass, MO_64); - } -} - /* AdvSIMD two reg misc * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0 * +---+---+---+-----------+------+-----------+--------+-----+------+------+ @@ -9948,16 +9958,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) TCGv_ptr tcg_fpstatus; switch (opcode) { - case 0x13: /* SHLL, SHLL2 */ - if (u == 0 || size == 3) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - handle_shll(s, is_q, size, rn, rd); - return; case 0xc ... 0xf: case 0x16 ... 0x1f: { @@ -10118,6 +10118,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0xa: /* CMLT */ case 0xb: /* ABS, NEG */ case 0x12: /* XTN, XTN2, SQXTUN, SQXTUN2 */ + case 0x13: /* SHLL, SHLL2 */ case 0x14: /* SQXTN, SQXTN2, UQXTN, UQXTN2 */ unallocated_encoding(s); return; From f0632d48a7391fabe3539d54ee1aec56a2fe1cb6 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:20 -0600 Subject: [PATCH 53/85] target/arm: Implement gen_gvec_fabs, gen_gvec_fneg Move the current implementation out of translate-neon.c, and extend to handle all element sizes. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-54-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/gengvec.c | 14 ++++++++++++++ target/arm/tcg/translate-neon.c | 20 ++------------------ target/arm/tcg/translate.h | 6 ++++++ 3 files changed, 22 insertions(+), 18 deletions(-) diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index 2755da8ac7..01c9d5436d 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -2697,3 +2697,17 @@ void gen_gvec_uadalp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, assert(vece <= MO_32); tcg_gen_gvec_2(rd_ofs, rn_ofs, opr_sz, max_sz, &g[vece]); } + +void gen_gvec_fabs(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t oprsz, uint32_t maxsz) +{ + uint64_t s_bit = 1ull << ((8 << vece) - 1); + tcg_gen_gvec_andi(vece, dofs, aofs, s_bit - 1, oprsz, maxsz); +} + +void gen_gvec_fneg(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t oprsz, uint32_t maxsz) +{ + uint64_t s_bit = 1ull << ((8 << vece) - 1); + tcg_gen_gvec_xori(vece, dofs, aofs, s_bit, oprsz, maxsz); +} diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index 0821f10fad..b9b3d1c1fb 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -3041,14 +3041,6 @@ static bool do_2misc(DisasContext *s, arg_2misc *a, NeonGenOneOpFn *fn) return true; } -static void gen_VABS_F(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, - uint32_t oprsz, uint32_t maxsz) -{ - tcg_gen_gvec_andi(vece, rd_ofs, rm_ofs, - vece == MO_16 ? 0x7fff : 0x7fffffff, - oprsz, maxsz); -} - static bool trans_VABS_F(DisasContext *s, arg_2misc *a) { if (a->size == MO_16) { @@ -3058,15 +3050,7 @@ static bool trans_VABS_F(DisasContext *s, arg_2misc *a) } else if (a->size != MO_32) { return false; } - return do_2misc_vec(s, a, gen_VABS_F); -} - -static void gen_VNEG_F(unsigned vece, uint32_t rd_ofs, uint32_t rm_ofs, - uint32_t oprsz, uint32_t maxsz) -{ - tcg_gen_gvec_xori(vece, rd_ofs, rm_ofs, - vece == MO_16 ? 0x8000 : 0x80000000, - oprsz, maxsz); + return do_2misc_vec(s, a, gen_gvec_fabs); } static bool trans_VNEG_F(DisasContext *s, arg_2misc *a) @@ -3078,7 +3062,7 @@ static bool trans_VNEG_F(DisasContext *s, arg_2misc *a) } else if (a->size != MO_32) { return false; } - return do_2misc_vec(s, a, gen_VNEG_F); + return do_2misc_vec(s, a, gen_gvec_fneg); } static bool trans_VRECPE(DisasContext *s, arg_2misc *a) diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index edd775d564..b996de2c15 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -602,6 +602,12 @@ void gen_gvec_uaddlp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, void gen_gvec_uadalp(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t opr_sz, uint32_t max_sz); +/* These exclusively manipulate the sign bit. */ +void gen_gvec_fabs(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t oprsz, uint32_t maxsz); +void gen_gvec_fneg(unsigned vece, uint32_t dofs, uint32_t aofs, + uint32_t oprsz, uint32_t maxsz); + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ From ea30b3522afe996b684bb1d9a5cd3c9cf1cadc7a Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:21 -0600 Subject: [PATCH 54/85] target/arm: Convert FABS, FNEG (vector) to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-55-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 7 +++++ target/arm/tcg/translate-a64.c | 54 +++++++++++++++------------------- 2 files changed, 31 insertions(+), 30 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index ec0d46a563..f46bd1a715 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -77,6 +77,7 @@ @qrr_s . q:1 ...... .. ...... ...... rn:5 rd:5 &qrr_e esz=2 @qrr_bh . q:1 ...... . esz:1 ...... ...... rn:5 rd:5 &qrr_e @qrr_hs . q:1 ...... .. ...... ...... rn:5 rd:5 &qrr_e esz=%esz_hs +@qrr_sd . q:1 ...... .. ...... ...... rn:5 rd:5 &qrr_e esz=%esz_sd @qrr_e . q:1 ...... esz:2 ...... ...... rn:5 rd:5 &qrr_e @qrrr_b . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=0 @@ -1687,3 +1688,9 @@ FCVTXN_v 0.10 1110 011 00001 01101 0 ..... ..... @qrr_s BFCVTN_v 0.00 1110 101 00001 01101 0 ..... ..... @qrr_h SHLL_v 0.10 1110 ..1 00001 00111 0 ..... ..... @qrr_e + +FABS_v 0.00 1110 111 11000 11111 0 ..... ..... @qrr_h +FABS_v 0.00 1110 1.1 00000 11111 0 ..... ..... @qrr_sd + +FNEG_v 0.10 1110 111 11000 11111 0 ..... ..... @qrr_h +FNEG_v 0.10 1110 1.1 00000 11111 0 ..... ..... @qrr_sd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index c5d456de3b..fd7f7ae714 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -9149,6 +9149,20 @@ static bool trans_SHLL_v(DisasContext *s, arg_qrr_e *a) return true; } +static bool do_fabs_fneg_v(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) +{ + int check = fp_access_check_vector_hsd(s, a->q, a->esz); + + if (check <= 0) { + return check == 0; + } + + gen_gvec_fn2(s, a->q, a->rd, a->rn, fn, a->esz); + return true; +} + +TRANS(FABS_v, do_fabs_fneg_v, a, gen_gvec_fabs) +TRANS(FNEG_v, do_fabs_fneg_v, a, gen_gvec_fneg) /* Common vector code for handling integer to FP conversion */ static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn, @@ -9447,12 +9461,6 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, * requires them. */ switch (opcode) { - case 0x2f: /* FABS */ - gen_vfp_absd(tcg_rd, tcg_rn); - break; - case 0x6f: /* FNEG */ - gen_vfp_negd(tcg_rd, tcg_rn); - break; case 0x7f: /* FSQRT */ gen_helper_vfp_sqrtd(tcg_rd, tcg_rn, tcg_fpstatus); break; @@ -9497,6 +9505,8 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, case 0x9: /* CMEQ, CMLE */ case 0xa: /* CMLT */ case 0xb: /* ABS, NEG */ + case 0x2f: /* FABS */ + case 0x6f: /* FNEG */ g_assert_not_reached(); } } @@ -9968,13 +9978,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) opcode |= (extract32(size, 1, 1) << 5) | (u << 6); size = is_double ? 3 : 2; switch (opcode) { - case 0x2f: /* FABS */ - case 0x6f: /* FNEG */ - if (size == 3 && !is_q) { - unallocated_encoding(s); - return; - } - break; case 0x1d: /* SCVTF */ case 0x5d: /* UCVTF */ { @@ -10099,6 +10102,8 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x16: /* FCVTN, FCVTN2 */ case 0x36: /* BFCVTN, BFCVTN2 */ case 0x56: /* FCVTXN, FCVTXN2 */ + case 0x2f: /* FABS */ + case 0x6f: /* FNEG */ unallocated_encoding(s); return; } @@ -10171,12 +10176,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) { /* Special cases for 32 bit elements */ switch (opcode) { - case 0x2f: /* FABS */ - gen_vfp_abss(tcg_res, tcg_op); - break; - case 0x6f: /* FNEG */ - gen_vfp_negs(tcg_res, tcg_op); - break; case 0x7f: /* FSQRT */ gen_helper_vfp_sqrts(tcg_res, tcg_op, tcg_fpstatus); break; @@ -10220,6 +10219,8 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) break; default: case 0x7: /* SQABS, SQNEG */ + case 0x2f: /* FABS */ + case 0x6f: /* FNEG */ g_assert_not_reached(); } } @@ -10362,17 +10363,14 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x7b: /* FCVTZU */ rmode = FPROUNDING_ZERO; break; - case 0x2f: /* FABS */ - case 0x6f: /* FNEG */ - only_in_vector = true; - need_fpst = false; - break; case 0x7d: /* FRSQRTE */ break; case 0x7f: /* FSQRT (vector) */ only_in_vector = true; break; default: + case 0x2f: /* FABS */ + case 0x6f: /* FNEG */ unallocated_encoding(s); return; } @@ -10474,12 +10472,6 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x59: /* FRINTX */ gen_helper_advsimd_rinth_exact(tcg_res, tcg_op, tcg_fpstatus); break; - case 0x2f: /* FABS */ - tcg_gen_andi_i32(tcg_res, tcg_op, 0x7fff); - break; - case 0x6f: /* FNEG */ - tcg_gen_xori_i32(tcg_res, tcg_op, 0x8000); - break; case 0x7d: /* FRSQRTE */ gen_helper_rsqrte_f16(tcg_res, tcg_op, tcg_fpstatus); break; @@ -10487,6 +10479,8 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) gen_helper_vfp_sqrth(tcg_res, tcg_op, tcg_fpstatus); break; default: + case 0x2f: /* FABS */ + case 0x6f: /* FNEG */ g_assert_not_reached(); } From 73a6f0c245d613109b40a7d858775bedd49dff34 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:22 -0600 Subject: [PATCH 55/85] target/arm: Convert FSQRT (vector) to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-56-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 3 ++ target/arm/tcg/translate-a64.c | 69 ++++++++++++++++++++++++---------- 2 files changed, 53 insertions(+), 19 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index f46bd1a715..1e0eb4a748 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1694,3 +1694,6 @@ FABS_v 0.00 1110 1.1 00000 11111 0 ..... ..... @qrr_sd FNEG_v 0.10 1110 111 11000 11111 0 ..... ..... @qrr_h FNEG_v 0.10 1110 1.1 00000 11111 0 ..... ..... @qrr_sd + +FSQRT_v 0.10 1110 111 11001 11111 0 ..... ..... @qrr_h +FSQRT_v 0.10 1110 1.1 00001 11111 0 ..... ..... @qrr_sd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index fd7f7ae714..287e9338a4 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -9164,6 +9164,51 @@ static bool do_fabs_fneg_v(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) TRANS(FABS_v, do_fabs_fneg_v, a, gen_gvec_fabs) TRANS(FNEG_v, do_fabs_fneg_v, a, gen_gvec_fneg) +static bool do_fp1_vector(DisasContext *s, arg_qrr_e *a, + const FPScalar1 *f, int rmode) +{ + TCGv_i32 tcg_rmode = NULL; + TCGv_ptr fpst; + int check = fp_access_check_vector_hsd(s, a->q, a->esz); + + if (check <= 0) { + return check == 0; + } + + fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + if (rmode >= 0) { + tcg_rmode = gen_set_rmode(rmode, fpst); + } + + if (a->esz == MO_64) { + TCGv_i64 t64 = tcg_temp_new_i64(); + + for (int pass = 0; pass < 2; ++pass) { + read_vec_element(s, t64, a->rn, pass, MO_64); + f->gen_d(t64, t64, fpst); + write_vec_element(s, t64, a->rd, pass, MO_64); + } + } else { + TCGv_i32 t32 = tcg_temp_new_i32(); + void (*gen)(TCGv_i32, TCGv_i32, TCGv_ptr) + = (a->esz == MO_16 ? f->gen_h : f->gen_s); + + for (int pass = 0, n = (a->q ? 16 : 8) >> a->esz; pass < n; ++pass) { + read_vec_element_i32(s, t32, a->rn, pass, a->esz); + gen(t32, t32, fpst); + write_vec_element_i32(s, t32, a->rd, pass, a->esz); + } + } + clear_vec_high(s, a->q, a->rd); + + if (rmode >= 0) { + gen_restore_rmode(tcg_rmode, fpst); + } + return true; +} + +TRANS(FSQRT_v, do_fp1_vector, a, &f_scalar_fsqrt, -1) + /* Common vector code for handling integer to FP conversion */ static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn, int elements, int is_signed, @@ -9461,9 +9506,6 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, * requires them. */ switch (opcode) { - case 0x7f: /* FSQRT */ - gen_helper_vfp_sqrtd(tcg_rd, tcg_rn, tcg_fpstatus); - break; case 0x1a: /* FCVTNS */ case 0x1b: /* FCVTMS */ case 0x1c: /* FCVTAS */ @@ -9507,6 +9549,7 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, case 0xb: /* ABS, NEG */ case 0x2f: /* FABS */ case 0x6f: /* FNEG */ + case 0x7f: /* FSQRT */ g_assert_not_reached(); } } @@ -10004,13 +10047,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } handle_2misc_fcmp_zero(s, opcode, false, u, is_q, size, rn, rd); return; - case 0x7f: /* FSQRT */ - need_fpstatus = true; - if (size == 3 && !is_q) { - unallocated_encoding(s); - return; - } - break; case 0x1a: /* FCVTNS */ case 0x1b: /* FCVTMS */ case 0x3a: /* FCVTPS */ @@ -10104,6 +10140,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x56: /* FCVTXN, FCVTXN2 */ case 0x2f: /* FABS */ case 0x6f: /* FNEG */ + case 0x7f: /* FSQRT */ unallocated_encoding(s); return; } @@ -10176,9 +10213,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) { /* Special cases for 32 bit elements */ switch (opcode) { - case 0x7f: /* FSQRT */ - gen_helper_vfp_sqrts(tcg_res, tcg_op, tcg_fpstatus); - break; case 0x1a: /* FCVTNS */ case 0x1b: /* FCVTMS */ case 0x1c: /* FCVTAS */ @@ -10221,6 +10255,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x7: /* SQABS, SQNEG */ case 0x2f: /* FABS */ case 0x6f: /* FNEG */ + case 0x7f: /* FSQRT */ g_assert_not_reached(); } } @@ -10365,12 +10400,10 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) break; case 0x7d: /* FRSQRTE */ break; - case 0x7f: /* FSQRT (vector) */ - only_in_vector = true; - break; default: case 0x2f: /* FABS */ case 0x6f: /* FNEG */ + case 0x7f: /* FSQRT (vector) */ unallocated_encoding(s); return; } @@ -10475,12 +10508,10 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x7d: /* FRSQRTE */ gen_helper_rsqrte_f16(tcg_res, tcg_op, tcg_fpstatus); break; - case 0x7f: /* FSQRT */ - gen_helper_vfp_sqrth(tcg_res, tcg_op, tcg_fpstatus); - break; default: case 0x2f: /* FABS */ case 0x6f: /* FNEG */ + case 0x7f: /* FSQRT */ g_assert_not_reached(); } From 09facda3428d0a41b44949bd410702f2c52ac2d3 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:23 -0600 Subject: [PATCH 56/85] target/arm: Convert FRINT* (vector) to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-57-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 26 +++++ target/arm/tcg/translate-a64.c | 176 ++++++++++++--------------------- 2 files changed, 88 insertions(+), 114 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 1e0eb4a748..5e02144f65 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1697,3 +1697,29 @@ FNEG_v 0.10 1110 1.1 00000 11111 0 ..... ..... @qrr_sd FSQRT_v 0.10 1110 111 11001 11111 0 ..... ..... @qrr_h FSQRT_v 0.10 1110 1.1 00001 11111 0 ..... ..... @qrr_sd + +FRINTN_v 0.00 1110 011 11001 10001 0 ..... ..... @qrr_h +FRINTN_v 0.00 1110 0.1 00001 10001 0 ..... ..... @qrr_sd + +FRINTM_v 0.00 1110 011 11001 10011 0 ..... ..... @qrr_h +FRINTM_v 0.00 1110 0.1 00001 10011 0 ..... ..... @qrr_sd + +FRINTP_v 0.00 1110 111 11001 10001 0 ..... ..... @qrr_h +FRINTP_v 0.00 1110 1.1 00001 10001 0 ..... ..... @qrr_sd + +FRINTZ_v 0.00 1110 111 11001 10011 0 ..... ..... @qrr_h +FRINTZ_v 0.00 1110 1.1 00001 10011 0 ..... ..... @qrr_sd + +FRINTA_v 0.10 1110 011 11001 10001 0 ..... ..... @qrr_h +FRINTA_v 0.10 1110 0.1 00001 10001 0 ..... ..... @qrr_sd + +FRINTX_v 0.10 1110 011 11001 10011 0 ..... ..... @qrr_h +FRINTX_v 0.10 1110 0.1 00001 10011 0 ..... ..... @qrr_sd + +FRINTI_v 0.10 1110 111 11001 10011 0 ..... ..... @qrr_h +FRINTI_v 0.10 1110 1.1 00001 10011 0 ..... ..... @qrr_sd + +FRINT32Z_v 0.00 1110 0.1 00001 11101 0 ..... ..... @qrr_sd +FRINT32X_v 0.10 1110 0.1 00001 11101 0 ..... ..... @qrr_sd +FRINT64Z_v 0.00 1110 0.1 00001 11111 0 ..... ..... @qrr_sd +FRINT64X_v 0.10 1110 0.1 00001 11111 0 ..... ..... @qrr_sd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 287e9338a4..0f924b07dc 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -9209,6 +9209,21 @@ static bool do_fp1_vector(DisasContext *s, arg_qrr_e *a, TRANS(FSQRT_v, do_fp1_vector, a, &f_scalar_fsqrt, -1) +TRANS(FRINTN_v, do_fp1_vector, a, &f_scalar_frint, FPROUNDING_TIEEVEN) +TRANS(FRINTP_v, do_fp1_vector, a, &f_scalar_frint, FPROUNDING_POSINF) +TRANS(FRINTM_v, do_fp1_vector, a, &f_scalar_frint, FPROUNDING_NEGINF) +TRANS(FRINTZ_v, do_fp1_vector, a, &f_scalar_frint, FPROUNDING_ZERO) +TRANS(FRINTA_v, do_fp1_vector, a, &f_scalar_frint, FPROUNDING_TIEAWAY) +TRANS(FRINTI_v, do_fp1_vector, a, &f_scalar_frint, -1) +TRANS(FRINTX_v, do_fp1_vector, a, &f_scalar_frintx, -1) + +TRANS_FEAT(FRINT32Z_v, aa64_frint, do_fp1_vector, a, + &f_scalar_frint32, FPROUNDING_ZERO) +TRANS_FEAT(FRINT32X_v, aa64_frint, do_fp1_vector, a, &f_scalar_frint32, -1) +TRANS_FEAT(FRINT64Z_v, aa64_frint, do_fp1_vector, a, + &f_scalar_frint64, FPROUNDING_ZERO) +TRANS_FEAT(FRINT64X_v, aa64_frint, do_fp1_vector, a, &f_scalar_frint64, -1) + /* Common vector code for handling integer to FP conversion */ static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn, int elements, int is_signed, @@ -9520,25 +9535,6 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, case 0x7b: /* FCVTZU */ gen_helper_vfp_touqd(tcg_rd, tcg_rn, tcg_constant_i32(0), tcg_fpstatus); break; - case 0x18: /* FRINTN */ - case 0x19: /* FRINTM */ - case 0x38: /* FRINTP */ - case 0x39: /* FRINTZ */ - case 0x58: /* FRINTA */ - case 0x79: /* FRINTI */ - gen_helper_rintd(tcg_rd, tcg_rn, tcg_fpstatus); - break; - case 0x59: /* FRINTX */ - gen_helper_rintd_exact(tcg_rd, tcg_rn, tcg_fpstatus); - break; - case 0x1e: /* FRINT32Z */ - case 0x5e: /* FRINT32X */ - gen_helper_frint32_d(tcg_rd, tcg_rn, tcg_fpstatus); - break; - case 0x1f: /* FRINT64Z */ - case 0x5f: /* FRINT64X */ - gen_helper_frint64_d(tcg_rd, tcg_rn, tcg_fpstatus); - break; default: case 0x4: /* CLS, CLZ */ case 0x5: /* NOT */ @@ -9550,6 +9546,17 @@ static void handle_2misc_64(DisasContext *s, int opcode, bool u, case 0x2f: /* FABS */ case 0x6f: /* FNEG */ case 0x7f: /* FSQRT */ + case 0x18: /* FRINTN */ + case 0x19: /* FRINTM */ + case 0x38: /* FRINTP */ + case 0x39: /* FRINTZ */ + case 0x58: /* FRINTA */ + case 0x79: /* FRINTI */ + case 0x59: /* FRINTX */ + case 0x1e: /* FRINT32Z */ + case 0x5e: /* FRINT32X */ + case 0x1f: /* FRINT64Z */ + case 0x5f: /* FRINT64X */ g_assert_not_reached(); } } @@ -10094,46 +10101,12 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } handle_2misc_widening(s, opcode, is_q, size, rn, rd); return; - case 0x18: /* FRINTN */ - case 0x19: /* FRINTM */ - case 0x38: /* FRINTP */ - case 0x39: /* FRINTZ */ - rmode = extract32(opcode, 5, 1) | (extract32(opcode, 0, 1) << 1); - /* fall through */ - case 0x59: /* FRINTX */ - case 0x79: /* FRINTI */ - need_fpstatus = true; - if (size == 3 && !is_q) { - unallocated_encoding(s); - return; - } - break; - case 0x58: /* FRINTA */ - rmode = FPROUNDING_TIEAWAY; - need_fpstatus = true; - if (size == 3 && !is_q) { - unallocated_encoding(s); - return; - } - break; case 0x7c: /* URSQRTE */ if (size == 3) { unallocated_encoding(s); return; } break; - case 0x1e: /* FRINT32Z */ - case 0x1f: /* FRINT64Z */ - rmode = FPROUNDING_ZERO; - /* fall through */ - case 0x5e: /* FRINT32X */ - case 0x5f: /* FRINT64X */ - need_fpstatus = true; - if ((size == 3 && !is_q) || !dc_isar_feature(aa64_frint, s)) { - unallocated_encoding(s); - return; - } - break; default: case 0x16: /* FCVTN, FCVTN2 */ case 0x36: /* BFCVTN, BFCVTN2 */ @@ -10141,6 +10114,17 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x2f: /* FABS */ case 0x6f: /* FNEG */ case 0x7f: /* FSQRT */ + case 0x18: /* FRINTN */ + case 0x19: /* FRINTM */ + case 0x38: /* FRINTP */ + case 0x39: /* FRINTZ */ + case 0x59: /* FRINTX */ + case 0x79: /* FRINTI */ + case 0x58: /* FRINTA */ + case 0x1e: /* FRINT32Z */ + case 0x1f: /* FRINT64Z */ + case 0x5e: /* FRINT32X */ + case 0x5f: /* FRINT64X */ unallocated_encoding(s); return; } @@ -10229,33 +10213,25 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) gen_helper_vfp_touls(tcg_res, tcg_op, tcg_constant_i32(0), tcg_fpstatus); break; - case 0x18: /* FRINTN */ - case 0x19: /* FRINTM */ - case 0x38: /* FRINTP */ - case 0x39: /* FRINTZ */ - case 0x58: /* FRINTA */ - case 0x79: /* FRINTI */ - gen_helper_rints(tcg_res, tcg_op, tcg_fpstatus); - break; - case 0x59: /* FRINTX */ - gen_helper_rints_exact(tcg_res, tcg_op, tcg_fpstatus); - break; case 0x7c: /* URSQRTE */ gen_helper_rsqrte_u32(tcg_res, tcg_op); break; - case 0x1e: /* FRINT32Z */ - case 0x5e: /* FRINT32X */ - gen_helper_frint32_s(tcg_res, tcg_op, tcg_fpstatus); - break; - case 0x1f: /* FRINT64Z */ - case 0x5f: /* FRINT64X */ - gen_helper_frint64_s(tcg_res, tcg_op, tcg_fpstatus); - break; default: case 0x7: /* SQABS, SQNEG */ case 0x2f: /* FABS */ case 0x6f: /* FNEG */ case 0x7f: /* FSQRT */ + case 0x18: /* FRINTN */ + case 0x19: /* FRINTM */ + case 0x38: /* FRINTP */ + case 0x39: /* FRINTZ */ + case 0x58: /* FRINTA */ + case 0x79: /* FRINTI */ + case 0x59: /* FRINTX */ + case 0x1e: /* FRINT32Z */ + case 0x5e: /* FRINT32X */ + case 0x1f: /* FRINT64Z */ + case 0x5f: /* FRINT64X */ g_assert_not_reached(); } } @@ -10289,7 +10265,6 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) int rn, rd; bool is_q; bool is_scalar; - bool only_in_vector = false; int pass; TCGv_i32 tcg_rmode = NULL; @@ -10343,31 +10318,6 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x3d: /* FRECPE */ case 0x3f: /* FRECPX */ break; - case 0x18: /* FRINTN */ - only_in_vector = true; - rmode = FPROUNDING_TIEEVEN; - break; - case 0x19: /* FRINTM */ - only_in_vector = true; - rmode = FPROUNDING_NEGINF; - break; - case 0x38: /* FRINTP */ - only_in_vector = true; - rmode = FPROUNDING_POSINF; - break; - case 0x39: /* FRINTZ */ - only_in_vector = true; - rmode = FPROUNDING_ZERO; - break; - case 0x58: /* FRINTA */ - only_in_vector = true; - rmode = FPROUNDING_TIEAWAY; - break; - case 0x59: /* FRINTX */ - case 0x79: /* FRINTI */ - only_in_vector = true; - /* current rounding mode */ - break; case 0x1a: /* FCVTNS */ rmode = FPROUNDING_TIEEVEN; break; @@ -10404,6 +10354,13 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x2f: /* FABS */ case 0x6f: /* FNEG */ case 0x7f: /* FSQRT (vector) */ + case 0x18: /* FRINTN */ + case 0x19: /* FRINTM */ + case 0x38: /* FRINTP */ + case 0x39: /* FRINTZ */ + case 0x58: /* FRINTA */ + case 0x59: /* FRINTX */ + case 0x79: /* FRINTI */ unallocated_encoding(s); return; } @@ -10415,11 +10372,6 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - /* FRINTxx is only in the vector form */ - if (only_in_vector) { - unallocated_encoding(s); - return; - } } if (!fp_access_check(s)) { @@ -10494,17 +10446,6 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x7b: /* FCVTZU */ gen_helper_advsimd_f16touinth(tcg_res, tcg_op, tcg_fpstatus); break; - case 0x18: /* FRINTN */ - case 0x19: /* FRINTM */ - case 0x38: /* FRINTP */ - case 0x39: /* FRINTZ */ - case 0x58: /* FRINTA */ - case 0x79: /* FRINTI */ - gen_helper_advsimd_rinth(tcg_res, tcg_op, tcg_fpstatus); - break; - case 0x59: /* FRINTX */ - gen_helper_advsimd_rinth_exact(tcg_res, tcg_op, tcg_fpstatus); - break; case 0x7d: /* FRSQRTE */ gen_helper_rsqrte_f16(tcg_res, tcg_op, tcg_fpstatus); break; @@ -10512,6 +10453,13 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x2f: /* FABS */ case 0x6f: /* FNEG */ case 0x7f: /* FSQRT */ + case 0x18: /* FRINTN */ + case 0x19: /* FRINTM */ + case 0x38: /* FRINTP */ + case 0x39: /* FRINTZ */ + case 0x58: /* FRINTA */ + case 0x79: /* FRINTI */ + case 0x59: /* FRINTX */ g_assert_not_reached(); } From fe78ebaae92668e8924e65e01fa562610b03acd4 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:24 -0600 Subject: [PATCH 57/85] target/arm: Convert FCVT* (vector, integer) scalar to decodetree Arm silliness with naming, the scalar insns described as part of the vector instructions, as separate from the "regular" scalar insns which output to general registers. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-58-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 30 ++++++++ target/arm/tcg/translate-a64.c | 133 ++++++++++++++------------------- 2 files changed, 86 insertions(+), 77 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 5e02144f65..f7fcc32adc 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1652,6 +1652,36 @@ UQXTN_s 0111 1110 ..1 00001 01001 0 ..... ..... @rr_e FCVTXN_s 0111 1110 011 00001 01101 0 ..... ..... @rr_s +@icvt_h . ....... .. ...... ...... rn:5 rd:5 \ + &fcvt sf=0 esz=1 shift=0 +@icvt_sd . ....... .. ...... ...... rn:5 rd:5 \ + &fcvt sf=0 esz=%esz_sd shift=0 + +FCVTNS_f 0101 1110 011 11001 10101 0 ..... ..... @icvt_h +FCVTNS_f 0101 1110 0.1 00001 10101 0 ..... ..... @icvt_sd +FCVTNU_f 0111 1110 011 11001 10101 0 ..... ..... @icvt_h +FCVTNU_f 0111 1110 0.1 00001 10101 0 ..... ..... @icvt_sd + +FCVTPS_f 0101 1110 111 11001 10101 0 ..... ..... @icvt_h +FCVTPS_f 0101 1110 1.1 00001 10101 0 ..... ..... @icvt_sd +FCVTPU_f 0111 1110 111 11001 10101 0 ..... ..... @icvt_h +FCVTPU_f 0111 1110 1.1 00001 10101 0 ..... ..... @icvt_sd + +FCVTMS_f 0101 1110 011 11001 10111 0 ..... ..... @icvt_h +FCVTMS_f 0101 1110 0.1 00001 10111 0 ..... ..... @icvt_sd +FCVTMU_f 0111 1110 011 11001 10111 0 ..... ..... @icvt_h +FCVTMU_f 0111 1110 0.1 00001 10111 0 ..... ..... @icvt_sd + +FCVTZS_f 0101 1110 111 11001 10111 0 ..... ..... @icvt_h +FCVTZS_f 0101 1110 1.1 00001 10111 0 ..... ..... @icvt_sd +FCVTZU_f 0111 1110 111 11001 10111 0 ..... ..... @icvt_h +FCVTZU_f 0111 1110 1.1 00001 10111 0 ..... ..... @icvt_sd + +FCVTAS_f 0101 1110 011 11001 11001 0 ..... ..... @icvt_h +FCVTAS_f 0101 1110 0.1 00001 11001 0 ..... ..... @icvt_sd +FCVTAU_f 0111 1110 011 11001 11001 0 ..... ..... @icvt_h +FCVTAU_f 0111 1110 0.1 00001 11001 0 ..... ..... @icvt_sd + # Advanced SIMD two-register miscellaneous SQABS_v 0.00 1110 ..1 00000 01111 0 ..... ..... @qrr_e diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 0f924b07dc..71f1d6f778 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8674,6 +8674,16 @@ static void do_fcvt_scalar(DisasContext *s, MemOp out, MemOp esz, tcg_shift, tcg_fpstatus); tcg_gen_extu_i32_i64(tcg_out, tcg_single); break; + case MO_16 | MO_SIGN: + gen_helper_vfp_toshh(tcg_single, tcg_single, + tcg_shift, tcg_fpstatus); + tcg_gen_extu_i32_i64(tcg_out, tcg_single); + break; + case MO_16: + gen_helper_vfp_touhh(tcg_single, tcg_single, + tcg_shift, tcg_fpstatus); + tcg_gen_extu_i32_i64(tcg_out, tcg_single); + break; default: g_assert_not_reached(); } @@ -8717,6 +8727,42 @@ TRANS(FCVTZU_g, do_fcvt_g, a, FPROUNDING_ZERO, false) TRANS(FCVTAS_g, do_fcvt_g, a, FPROUNDING_TIEAWAY, true) TRANS(FCVTAU_g, do_fcvt_g, a, FPROUNDING_TIEAWAY, false) +/* + * FCVT* (vector), scalar version. + * Which sounds weird, but really just means output to fp register + * instead of output to general register. Input and output element + * size are always equal. + */ +static bool do_fcvt_f(DisasContext *s, arg_fcvt *a, + ARMFPRounding rmode, bool is_signed) +{ + TCGv_i64 tcg_int; + int check = fp_access_check_scalar_hsd(s, a->esz); + + if (check <= 0) { + return check == 0; + } + + tcg_int = tcg_temp_new_i64(); + do_fcvt_scalar(s, a->esz | (is_signed ? MO_SIGN : 0), + a->esz, tcg_int, a->shift, a->rn, rmode); + + clear_vec(s, a->rd); + write_vec_element(s, tcg_int, a->rd, 0, a->esz); + return true; +} + +TRANS(FCVTNS_f, do_fcvt_f, a, FPROUNDING_TIEEVEN, true) +TRANS(FCVTNU_f, do_fcvt_f, a, FPROUNDING_TIEEVEN, false) +TRANS(FCVTPS_f, do_fcvt_f, a, FPROUNDING_POSINF, true) +TRANS(FCVTPU_f, do_fcvt_f, a, FPROUNDING_POSINF, false) +TRANS(FCVTMS_f, do_fcvt_f, a, FPROUNDING_NEGINF, true) +TRANS(FCVTMU_f, do_fcvt_f, a, FPROUNDING_NEGINF, false) +TRANS(FCVTZS_f, do_fcvt_f, a, FPROUNDING_ZERO, true) +TRANS(FCVTZU_f, do_fcvt_f, a, FPROUNDING_ZERO, false) +TRANS(FCVTAS_f, do_fcvt_f, a, FPROUNDING_TIEAWAY, true) +TRANS(FCVTAU_f, do_fcvt_f, a, FPROUNDING_TIEAWAY, false) + static bool trans_FJCVTZS(DisasContext *s, arg_FJCVTZS *a) { if (!dc_isar_feature(aa64_jscvt, s)) { @@ -9776,10 +9822,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) int opcode = extract32(insn, 12, 5); int size = extract32(insn, 22, 2); bool u = extract32(insn, 29, 1); - bool is_fcvt = false; - int rmode; - TCGv_i32 tcg_rmode; - TCGv_ptr tcg_fpstatus; switch (opcode) { case 0xc ... 0xf: @@ -9824,15 +9866,8 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) case 0x5b: /* FCVTMU */ case 0x7a: /* FCVTPU */ case 0x7b: /* FCVTZU */ - is_fcvt = true; - rmode = extract32(opcode, 5, 1) | (extract32(opcode, 0, 1) << 1); - break; case 0x1c: /* FCVTAS */ case 0x5c: /* FCVTAU */ - /* TIEAWAY doesn't fit in the usual rounding mode encoding */ - is_fcvt = true; - rmode = FPROUNDING_TIEAWAY; - break; case 0x56: /* FCVTXN, FCVTXN2 */ default: unallocated_encoding(s); @@ -9851,59 +9886,7 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - - if (!fp_access_check(s)) { - return; - } - - if (is_fcvt) { - tcg_fpstatus = fpstatus_ptr(FPST_FPCR); - tcg_rmode = gen_set_rmode(rmode, tcg_fpstatus); - } else { - tcg_fpstatus = NULL; - tcg_rmode = NULL; - } - - if (size == 3) { - TCGv_i64 tcg_rn = read_fp_dreg(s, rn); - TCGv_i64 tcg_rd = tcg_temp_new_i64(); - - handle_2misc_64(s, opcode, u, tcg_rd, tcg_rn, tcg_rmode, tcg_fpstatus); - write_fp_dreg(s, rd, tcg_rd); - } else { - TCGv_i32 tcg_rn = tcg_temp_new_i32(); - TCGv_i32 tcg_rd = tcg_temp_new_i32(); - - read_vec_element_i32(s, tcg_rn, rn, 0, size); - - switch (opcode) { - case 0x1a: /* FCVTNS */ - case 0x1b: /* FCVTMS */ - case 0x1c: /* FCVTAS */ - case 0x3a: /* FCVTPS */ - case 0x3b: /* FCVTZS */ - gen_helper_vfp_tosls(tcg_rd, tcg_rn, tcg_constant_i32(0), - tcg_fpstatus); - break; - case 0x5a: /* FCVTNU */ - case 0x5b: /* FCVTMU */ - case 0x5c: /* FCVTAU */ - case 0x7a: /* FCVTPU */ - case 0x7b: /* FCVTZU */ - gen_helper_vfp_touls(tcg_rd, tcg_rn, tcg_constant_i32(0), - tcg_fpstatus); - break; - default: - case 0x7: /* SQABS, SQNEG */ - g_assert_not_reached(); - } - - write_fp_sreg(s, rd, tcg_rd); - } - - if (is_fcvt) { - gen_restore_rmode(tcg_rmode, tcg_fpstatus); - } + g_assert_not_reached(); } /* AdvSIMD shift by immediate @@ -10391,30 +10374,26 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) TCGv_i32 tcg_res = tcg_temp_new_i32(); switch (fpop) { - case 0x1a: /* FCVTNS */ - case 0x1b: /* FCVTMS */ - case 0x1c: /* FCVTAS */ - case 0x3a: /* FCVTPS */ - case 0x3b: /* FCVTZS */ - gen_helper_advsimd_f16tosinth(tcg_res, tcg_op, tcg_fpstatus); - break; case 0x3d: /* FRECPE */ gen_helper_recpe_f16(tcg_res, tcg_op, tcg_fpstatus); break; case 0x3f: /* FRECPX */ gen_helper_frecpx_f16(tcg_res, tcg_op, tcg_fpstatus); break; + case 0x7d: /* FRSQRTE */ + gen_helper_rsqrte_f16(tcg_res, tcg_op, tcg_fpstatus); + break; + default: + case 0x1a: /* FCVTNS */ + case 0x1b: /* FCVTMS */ + case 0x1c: /* FCVTAS */ + case 0x3a: /* FCVTPS */ + case 0x3b: /* FCVTZS */ case 0x5a: /* FCVTNU */ case 0x5b: /* FCVTMU */ case 0x5c: /* FCVTAU */ case 0x7a: /* FCVTPU */ case 0x7b: /* FCVTZU */ - gen_helper_advsimd_f16touinth(tcg_res, tcg_op, tcg_fpstatus); - break; - case 0x7d: /* FRSQRTE */ - gen_helper_rsqrte_f16(tcg_res, tcg_op, tcg_fpstatus); - break; - default: g_assert_not_reached(); } From 6697b35e98997dc51201bab3a077446ac5c31a96 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:25 -0600 Subject: [PATCH 58/85] target/arm: Convert FCVT* (vector, fixed-point) scalar to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-59-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 19 +++++++++++++++++++ target/arm/tcg/translate-a64.c | 4 +--- 2 files changed, 20 insertions(+), 3 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index f7fcc32adc..f66f62da4f 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1682,6 +1682,25 @@ FCVTAS_f 0101 1110 0.1 00001 11001 0 ..... ..... @icvt_sd FCVTAU_f 0111 1110 011 11001 11001 0 ..... ..... @icvt_h FCVTAU_f 0111 1110 0.1 00001 11001 0 ..... ..... @icvt_sd +%fcvt_f_sh_h 16:4 !function=rsub_16 +%fcvt_f_sh_s 16:5 !function=rsub_32 +%fcvt_f_sh_d 16:6 !function=rsub_64 + +@fcvt_fixed_h .... .... . 001 .... ...... rn:5 rd:5 \ + &fcvt sf=0 esz=1 shift=%fcvt_f_sh_h +@fcvt_fixed_s .... .... . 01 ..... ...... rn:5 rd:5 \ + &fcvt sf=0 esz=2 shift=%fcvt_f_sh_s +@fcvt_fixed_d .... .... . 1 ...... ...... rn:5 rd:5 \ + &fcvt sf=0 esz=3 shift=%fcvt_f_sh_d + +FCVTZS_f 0101 1111 0 ....... 111111 ..... ..... @fcvt_fixed_h +FCVTZS_f 0101 1111 0 ....... 111111 ..... ..... @fcvt_fixed_s +FCVTZS_f 0101 1111 0 ....... 111111 ..... ..... @fcvt_fixed_d + +FCVTZU_f 0111 1111 0 ....... 111111 ..... ..... @fcvt_fixed_h +FCVTZU_f 0111 1111 0 ....... 111111 ..... ..... @fcvt_fixed_s +FCVTZU_f 0111 1111 0 ....... 111111 ..... ..... @fcvt_fixed_d + # Advanced SIMD two-register miscellaneous SQABS_v 0.00 1110 ..1 00000 01111 0 ..... ..... @qrr_e diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 71f1d6f778..894befef4d 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -9535,9 +9535,6 @@ static void disas_simd_scalar_shift_imm(DisasContext *s, uint32_t insn) handle_simd_shift_intfp_conv(s, true, false, is_u, immh, immb, opcode, rn, rd); break; - case 0x1f: /* FCVTZS, FCVTZU */ - handle_simd_shift_fpint_conv(s, true, false, is_u, immh, immb, rn, rd); - break; default: case 0x00: /* SSHR / USHR */ case 0x02: /* SSRA / USRA */ @@ -9551,6 +9548,7 @@ static void disas_simd_scalar_shift_imm(DisasContext *s, uint32_t insn) case 0x11: /* SQRSHRUN */ case 0x12: /* SQSHRN, UQSHRN */ case 0x13: /* SQRSHRN, UQRSHRN */ + case 0x1f: /* FCVTZS, FCVTZU */ unallocated_encoding(s); break; } From f469ca170d843b657a6e6e9d5b72059c3d171dc6 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:26 -0600 Subject: [PATCH 59/85] target/arm: Convert [US]CVTF (vector, integer) scalar to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-60-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 6 ++++++ target/arm/tcg/translate-a64.c | 35 ++++++++++++++++++++++++---------- 2 files changed, 31 insertions(+), 10 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index f66f62da4f..146500d9c4 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1657,6 +1657,12 @@ FCVTXN_s 0111 1110 011 00001 01101 0 ..... ..... @rr_s @icvt_sd . ....... .. ...... ...... rn:5 rd:5 \ &fcvt sf=0 esz=%esz_sd shift=0 +SCVTF_f 0101 1110 011 11001 11011 0 ..... ..... @icvt_h +SCVTF_f 0101 1110 0.1 00001 11011 0 ..... ..... @icvt_sd + +UCVTF_f 0111 1110 011 11001 11011 0 ..... ..... @icvt_h +UCVTF_f 0111 1110 0.1 00001 11011 0 ..... ..... @icvt_sd + FCVTNS_f 0101 1110 011 11001 10101 0 ..... ..... @icvt_h FCVTNS_f 0101 1110 0.1 00001 10101 0 ..... ..... @icvt_sd FCVTNU_f 0111 1110 011 11001 10101 0 ..... ..... @icvt_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 894befef4d..6e9d040ebf 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8599,6 +8599,29 @@ static bool do_cvtf_g(DisasContext *s, arg_fcvt *a, bool is_signed) TRANS(SCVTF_g, do_cvtf_g, a, true) TRANS(UCVTF_g, do_cvtf_g, a, false) +/* + * [US]CVTF (vector), scalar version. + * Which sounds weird, but really just means input from fp register + * instead of input from general register. Input and output element + * size are always equal. + */ +static bool do_cvtf_f(DisasContext *s, arg_fcvt *a, bool is_signed) +{ + TCGv_i64 tcg_int; + int check = fp_access_check_scalar_hsd(s, a->esz); + + if (check <= 0) { + return check == 0; + } + + tcg_int = tcg_temp_new_i64(); + read_vec_element(s, tcg_int, a->rn, 0, a->esz | (is_signed ? MO_SIGN : 0)); + return do_cvtf_scalar(s, a->esz, a->rd, a->shift, tcg_int, is_signed); +} + +TRANS(SCVTF_f, do_cvtf_f, a, true) +TRANS(UCVTF_f, do_cvtf_f, a, false) + static void do_fcvt_scalar(DisasContext *s, MemOp out, MemOp esz, TCGv_i64 tcg_out, int shift, int rn, ARMFPRounding rmode) @@ -9838,16 +9861,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) case 0x6d: /* FCMLE (zero) */ handle_2misc_fcmp_zero(s, opcode, true, u, true, size, rn, rd); return; - case 0x1d: /* SCVTF */ - case 0x5d: /* UCVTF */ - { - bool is_signed = (opcode == 0x1d); - if (!fp_access_check(s)) { - return; - } - handle_simd_intfp_conv(s, rd, rn, 1, is_signed, 0, size); - return; - } case 0x3d: /* FRECPE */ case 0x3f: /* FRECPX */ case 0x7d: /* FRSQRTE */ @@ -9867,6 +9880,8 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) case 0x1c: /* FCVTAS */ case 0x5c: /* FCVTAU */ case 0x56: /* FCVTXN, FCVTXN2 */ + case 0x1d: /* SCVTF */ + case 0x5d: /* UCVTF */ default: unallocated_encoding(s); return; From 69d5391a6695aff76f62b64e73c3ac399dddfffa Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:27 -0600 Subject: [PATCH 60/85] target/arm: Convert [US]CVTF (vector, fixed-point) scalar to decodetree Remove disas_simd_scalar_shift_imm as these were the last insns decoded by that function. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-61-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 8 ++++++ target/arm/tcg/translate-a64.c | 47 ---------------------------------- 2 files changed, 8 insertions(+), 47 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 146500d9c4..30e1834d99 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1699,6 +1699,14 @@ FCVTAU_f 0111 1110 0.1 00001 11001 0 ..... ..... @icvt_sd @fcvt_fixed_d .... .... . 1 ...... ...... rn:5 rd:5 \ &fcvt sf=0 esz=3 shift=%fcvt_f_sh_d +SCVTF_f 0101 1111 0 ....... 111001 ..... ..... @fcvt_fixed_h +SCVTF_f 0101 1111 0 ....... 111001 ..... ..... @fcvt_fixed_s +SCVTF_f 0101 1111 0 ....... 111001 ..... ..... @fcvt_fixed_d + +UCVTF_f 0111 1111 0 ....... 111001 ..... ..... @fcvt_fixed_h +UCVTF_f 0111 1111 0 ....... 111001 ..... ..... @fcvt_fixed_s +UCVTF_f 0111 1111 0 ....... 111001 ..... ..... @fcvt_fixed_d + FCVTZS_f 0101 1111 0 ....... 111111 ..... ..... @fcvt_fixed_h FCVTZS_f 0101 1111 0 ....... 111111 ..... ..... @fcvt_fixed_s FCVTZS_f 0101 1111 0 ....... 111111 ..... ..... @fcvt_fixed_d diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 6e9d040ebf..08f24908a4 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -9531,52 +9531,6 @@ static void handle_simd_shift_fpint_conv(DisasContext *s, bool is_scalar, gen_restore_rmode(tcg_rmode, tcg_fpstatus); } -/* AdvSIMD scalar shift by immediate - * 31 30 29 28 23 22 19 18 16 15 11 10 9 5 4 0 - * +-----+---+-------------+------+------+--------+---+------+------+ - * | 0 1 | U | 1 1 1 1 1 0 | immh | immb | opcode | 1 | Rn | Rd | - * +-----+---+-------------+------+------+--------+---+------+------+ - * - * This is the scalar version so it works on a fixed sized registers - */ -static void disas_simd_scalar_shift_imm(DisasContext *s, uint32_t insn) -{ - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int opcode = extract32(insn, 11, 5); - int immb = extract32(insn, 16, 3); - int immh = extract32(insn, 19, 4); - bool is_u = extract32(insn, 29, 1); - - if (immh == 0) { - unallocated_encoding(s); - return; - } - - switch (opcode) { - case 0x1c: /* SCVTF, UCVTF */ - handle_simd_shift_intfp_conv(s, true, false, is_u, immh, immb, - opcode, rn, rd); - break; - default: - case 0x00: /* SSHR / USHR */ - case 0x02: /* SSRA / USRA */ - case 0x04: /* SRSHR / URSHR */ - case 0x06: /* SRSRA / URSRA */ - case 0x08: /* SRI */ - case 0x0a: /* SHL / SLI */ - case 0x0c: /* SQSHLU */ - case 0x0e: /* SQSHL, UQSHL */ - case 0x10: /* SQSHRUN */ - case 0x11: /* SQRSHRUN */ - case 0x12: /* SQSHRN, UQSHRN */ - case 0x13: /* SQRSHRN, UQRSHRN */ - case 0x1f: /* FCVTZS, FCVTZU */ - unallocated_encoding(s); - break; - } -} - static void handle_2misc_64(DisasContext *s, int opcode, bool u, TCGv_i64 tcg_rd, TCGv_i64 tcg_rn, TCGv_i32 tcg_rmode, TCGv_ptr tcg_fpstatus) @@ -10476,7 +10430,6 @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x0e200800, 0x9f3e0c00, disas_simd_two_reg_misc }, { 0x0f000400, 0x9f800400, disas_simd_shift_imm }, { 0x5e200800, 0xdf3e0c00, disas_simd_scalar_two_reg_misc }, - { 0x5f000400, 0xdf800400, disas_simd_scalar_shift_imm }, { 0x0e780800, 0x8f7e0c00, disas_simd_two_reg_misc_fp16 }, { 0x00000000, 0x00000000, NULL } }; From c2e13388165fb32e716c4c04a966a9b538493c37 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:28 -0600 Subject: [PATCH 61/85] target/arm: Rename helper_gvec_vcvt_[hf][su] with _rz Emphasize that these functions use round-to-zero mode. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-62-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 8 ++++---- target/arm/tcg/translate-neon.c | 8 ++++---- target/arm/tcg/vec_helper.c | 8 ++++---- 3 files changed, 12 insertions(+), 12 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 04e422ab08..f2cfee40de 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -650,13 +650,13 @@ DEF_HELPER_FLAGS_4(gvec_touizs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_sf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_uf, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_fs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_fu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rz_fs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rz_fu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_hs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) -DEF_HELPER_FLAGS_4(gvec_vcvt_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rz_hs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rz_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ss, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rm_us, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index b9b3d1c1fb..f9ca889bec 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -1409,13 +1409,13 @@ static bool do_fp_2sh(DisasContext *s, arg_2reg_shift *a, DO_FP_2SH(VCVT_SF, gen_helper_gvec_vcvt_sf) DO_FP_2SH(VCVT_UF, gen_helper_gvec_vcvt_uf) -DO_FP_2SH(VCVT_FS, gen_helper_gvec_vcvt_fs) -DO_FP_2SH(VCVT_FU, gen_helper_gvec_vcvt_fu) +DO_FP_2SH(VCVT_FS, gen_helper_gvec_vcvt_rz_fs) +DO_FP_2SH(VCVT_FU, gen_helper_gvec_vcvt_rz_fu) DO_FP_2SH(VCVT_SH, gen_helper_gvec_vcvt_sh) DO_FP_2SH(VCVT_UH, gen_helper_gvec_vcvt_uh) -DO_FP_2SH(VCVT_HS, gen_helper_gvec_vcvt_hs) -DO_FP_2SH(VCVT_HU, gen_helper_gvec_vcvt_hu) +DO_FP_2SH(VCVT_HS, gen_helper_gvec_vcvt_rz_hs) +DO_FP_2SH(VCVT_HU, gen_helper_gvec_vcvt_rz_hu) static bool do_1reg_imm(DisasContext *s, arg_1reg_imm *a, GVecGen2iFn *fn) diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index 91a9130641..ec6b640fda 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -2507,12 +2507,12 @@ DO_3OP_PAIR(gvec_uminp_s, MIN, uint32_t, H4) DO_VCVT_FIXED(gvec_vcvt_sf, helper_vfp_sltos, uint32_t) DO_VCVT_FIXED(gvec_vcvt_uf, helper_vfp_ultos, uint32_t) -DO_VCVT_FIXED(gvec_vcvt_fs, helper_vfp_tosls_round_to_zero, uint32_t) -DO_VCVT_FIXED(gvec_vcvt_fu, helper_vfp_touls_round_to_zero, uint32_t) +DO_VCVT_FIXED(gvec_vcvt_rz_fs, helper_vfp_tosls_round_to_zero, uint32_t) +DO_VCVT_FIXED(gvec_vcvt_rz_fu, helper_vfp_touls_round_to_zero, uint32_t) DO_VCVT_FIXED(gvec_vcvt_sh, helper_vfp_shtoh, uint16_t) DO_VCVT_FIXED(gvec_vcvt_uh, helper_vfp_uhtoh, uint16_t) -DO_VCVT_FIXED(gvec_vcvt_hs, helper_vfp_toshh_round_to_zero, uint16_t) -DO_VCVT_FIXED(gvec_vcvt_hu, helper_vfp_touhh_round_to_zero, uint16_t) +DO_VCVT_FIXED(gvec_vcvt_rz_hs, helper_vfp_toshh_round_to_zero, uint16_t) +DO_VCVT_FIXED(gvec_vcvt_rz_hu, helper_vfp_touhh_round_to_zero, uint16_t) #undef DO_VCVT_FIXED From 53b9486be7e182cca15190e01d2d08647949515e Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:29 -0600 Subject: [PATCH 62/85] target/arm: Convert [US]CVTF (vector) to decodetree Remove handle_simd_intfp_conv and handle_simd_shift_intfp_conv as these were the last insns decoded by those functions. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-63-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 3 + target/arm/tcg/a64.decode | 22 ++++ target/arm/tcg/translate-a64.c | 201 ++++++--------------------------- target/arm/tcg/vec_helper.c | 7 +- 4 files changed, 66 insertions(+), 167 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index f2cfee40de..b227ac54d9 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -658,6 +658,9 @@ DEF_HELPER_FLAGS_4(gvec_vcvt_uh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rz_hs, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rz_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_sd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_ud, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ss, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rm_us, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 30e1834d99..4f832e7a4c 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1786,3 +1786,25 @@ FRINT32Z_v 0.00 1110 0.1 00001 11101 0 ..... ..... @qrr_sd FRINT32X_v 0.10 1110 0.1 00001 11101 0 ..... ..... @qrr_sd FRINT64Z_v 0.00 1110 0.1 00001 11111 0 ..... ..... @qrr_sd FRINT64X_v 0.10 1110 0.1 00001 11111 0 ..... ..... @qrr_sd + +SCVTF_vi 0.00 1110 011 11001 11011 0 ..... ..... @qrr_h +SCVTF_vi 0.00 1110 0.1 00001 11011 0 ..... ..... @qrr_sd + +UCVTF_vi 0.10 1110 011 11001 11011 0 ..... ..... @qrr_h +UCVTF_vi 0.10 1110 0.1 00001 11011 0 ..... ..... @qrr_sd + +&fcvt_q rd rn esz q shift +@fcvtq_h . q:1 . ...... 001 .... ...... rn:5 rd:5 \ + &fcvt_q esz=1 shift=%fcvt_f_sh_h +@fcvtq_s . q:1 . ...... 01 ..... ...... rn:5 rd:5 \ + &fcvt_q esz=2 shift=%fcvt_f_sh_s +@fcvtq_d . q:1 . ...... 1 ...... ...... rn:5 rd:5 \ + &fcvt_q esz=3 shift=%fcvt_f_sh_d + +SCVTF_vf 0.00 11110 ....... 111001 ..... ..... @fcvtq_h +SCVTF_vf 0.00 11110 ....... 111001 ..... ..... @fcvtq_s +SCVTF_vf 0.00 11110 ....... 111001 ..... ..... @fcvtq_d + +UCVTF_vf 0.10 11110 ....... 111001 ..... ..... @fcvtq_h +UCVTF_vf 0.10 11110 ....... 111001 ..... ..... @fcvtq_s +UCVTF_vf 0.10 11110 ....... 111001 ..... ..... @fcvtq_d diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 08f24908a4..0f94fa4fdc 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -9293,141 +9293,44 @@ TRANS_FEAT(FRINT64Z_v, aa64_frint, do_fp1_vector, a, &f_scalar_frint64, FPROUNDING_ZERO) TRANS_FEAT(FRINT64X_v, aa64_frint, do_fp1_vector, a, &f_scalar_frint64, -1) -/* Common vector code for handling integer to FP conversion */ -static void handle_simd_intfp_conv(DisasContext *s, int rd, int rn, - int elements, int is_signed, - int fracbits, int size) +static bool do_gvec_op2_fpst(DisasContext *s, MemOp esz, bool is_q, + int rd, int rn, int data, + gen_helper_gvec_2_ptr * const fns[3]) { - TCGv_ptr tcg_fpst = fpstatus_ptr(size == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); - TCGv_i32 tcg_shift = NULL; + int check = fp_access_check_vector_hsd(s, is_q, esz); + TCGv_ptr fpst; - MemOp mop = size | (is_signed ? MO_SIGN : 0); - int pass; - - if (fracbits || size == MO_64) { - tcg_shift = tcg_constant_i32(fracbits); + if (check <= 0) { + return check == 0; } - if (size == MO_64) { - TCGv_i64 tcg_int64 = tcg_temp_new_i64(); - TCGv_i64 tcg_double = tcg_temp_new_i64(); - - for (pass = 0; pass < elements; pass++) { - read_vec_element(s, tcg_int64, rn, pass, mop); - - if (is_signed) { - gen_helper_vfp_sqtod(tcg_double, tcg_int64, - tcg_shift, tcg_fpst); - } else { - gen_helper_vfp_uqtod(tcg_double, tcg_int64, - tcg_shift, tcg_fpst); - } - if (elements == 1) { - write_fp_dreg(s, rd, tcg_double); - } else { - write_vec_element(s, tcg_double, rd, pass, MO_64); - } - } - } else { - TCGv_i32 tcg_int32 = tcg_temp_new_i32(); - TCGv_i32 tcg_float = tcg_temp_new_i32(); - - for (pass = 0; pass < elements; pass++) { - read_vec_element_i32(s, tcg_int32, rn, pass, mop); - - switch (size) { - case MO_32: - if (fracbits) { - if (is_signed) { - gen_helper_vfp_sltos(tcg_float, tcg_int32, - tcg_shift, tcg_fpst); - } else { - gen_helper_vfp_ultos(tcg_float, tcg_int32, - tcg_shift, tcg_fpst); - } - } else { - if (is_signed) { - gen_helper_vfp_sitos(tcg_float, tcg_int32, tcg_fpst); - } else { - gen_helper_vfp_uitos(tcg_float, tcg_int32, tcg_fpst); - } - } - break; - case MO_16: - if (fracbits) { - if (is_signed) { - gen_helper_vfp_sltoh(tcg_float, tcg_int32, - tcg_shift, tcg_fpst); - } else { - gen_helper_vfp_ultoh(tcg_float, tcg_int32, - tcg_shift, tcg_fpst); - } - } else { - if (is_signed) { - gen_helper_vfp_sitoh(tcg_float, tcg_int32, tcg_fpst); - } else { - gen_helper_vfp_uitoh(tcg_float, tcg_int32, tcg_fpst); - } - } - break; - default: - g_assert_not_reached(); - } - - if (elements == 1) { - write_fp_sreg(s, rd, tcg_float); - } else { - write_vec_element_i32(s, tcg_float, rd, pass, size); - } - } - } - - clear_vec_high(s, elements << size == 16, rd); + fpst = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rn), fpst, + is_q ? 16 : 8, vec_full_reg_size(s), + data, fns[esz - 1]); + return true; } -/* UCVTF/SCVTF - Integer to FP conversion */ -static void handle_simd_shift_intfp_conv(DisasContext *s, bool is_scalar, - bool is_q, bool is_u, - int immh, int immb, int opcode, - int rn, int rd) -{ - int size, elements, fracbits; - int immhb = immh << 3 | immb; +static gen_helper_gvec_2_ptr * const f_scvtf_v[] = { + gen_helper_gvec_vcvt_sh, + gen_helper_gvec_vcvt_sf, + gen_helper_gvec_vcvt_sd, +}; +TRANS(SCVTF_vi, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, 0, f_scvtf_v) +TRANS(SCVTF_vf, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, a->shift, f_scvtf_v) - if (immh & 8) { - size = MO_64; - if (!is_scalar && !is_q) { - unallocated_encoding(s); - return; - } - } else if (immh & 4) { - size = MO_32; - } else if (immh & 2) { - size = MO_16; - if (!dc_isar_feature(aa64_fp16, s)) { - unallocated_encoding(s); - return; - } - } else { - /* immh == 0 would be a failure of the decode logic */ - g_assert(immh == 1); - unallocated_encoding(s); - return; - } - - if (is_scalar) { - elements = 1; - } else { - elements = (8 << is_q) >> size; - } - fracbits = (16 << size) - immhb; - - if (!fp_access_check(s)) { - return; - } - - handle_simd_intfp_conv(s, rd, rn, elements, !is_u, fracbits, size); -} +static gen_helper_gvec_2_ptr * const f_ucvtf_v[] = { + gen_helper_gvec_vcvt_uh, + gen_helper_gvec_vcvt_uf, + gen_helper_gvec_vcvt_ud, +}; +TRANS(UCVTF_vi, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, 0, f_ucvtf_v) +TRANS(UCVTF_vf, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, a->shift, f_ucvtf_v) /* FCVTZS, FVCVTZU - FP to fixedpoint conversion */ static void handle_simd_shift_fpint_conv(DisasContext *s, bool is_scalar, @@ -9878,10 +9781,6 @@ static void disas_simd_shift_imm(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x1c: /* SCVTF / UCVTF */ - handle_simd_shift_intfp_conv(s, false, is_q, is_u, immh, immb, - opcode, rn, rd); - break; case 0x1f: /* FCVTZS/ FCVTZU */ handle_simd_shift_fpint_conv(s, false, is_q, is_u, immh, immb, rn, rd); return; @@ -9899,6 +9798,7 @@ static void disas_simd_shift_imm(DisasContext *s, uint32_t insn) case 0x12: /* SQSHRN / UQSHRN */ case 0x13: /* SQRSHRN / UQRSHRN */ case 0x14: /* SSHLL / USHLL */ + case 0x1c: /* SCVTF / UCVTF */ unallocated_encoding(s); return; } @@ -9978,21 +9878,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) opcode |= (extract32(size, 1, 1) << 5) | (u << 6); size = is_double ? 3 : 2; switch (opcode) { - case 0x1d: /* SCVTF */ - case 0x5d: /* UCVTF */ - { - bool is_signed = (opcode == 0x1d) ? true : false; - int elements = is_double ? 2 : is_q ? 4 : 2; - if (is_double && !is_q) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - handle_simd_intfp_conv(s, rd, rn, elements, is_signed, 0, size); - return; - } case 0x2c: /* FCMGT (zero) */ case 0x2d: /* FCMEQ (zero) */ case 0x2e: /* FCMLT (zero) */ @@ -10075,6 +9960,8 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x1f: /* FRINT64Z */ case 0x5e: /* FRINT32X */ case 0x5f: /* FRINT64X */ + case 0x1d: /* SCVTF */ + case 0x5d: /* UCVTF */ unallocated_encoding(s); return; } @@ -10240,24 +10127,6 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) fpop = deposit32(fpop, 6, 1, u); switch (fpop) { - case 0x1d: /* SCVTF */ - case 0x5d: /* UCVTF */ - { - int elements; - - if (is_scalar) { - elements = 1; - } else { - elements = (is_q ? 8 : 4); - } - - if (!fp_access_check(s)) { - return; - } - handle_simd_intfp_conv(s, rd, rn, elements, !u, 0, MO_16); - return; - } - break; case 0x2c: /* FCMGT (zero) */ case 0x2d: /* FCMEQ (zero) */ case 0x2e: /* FCMLT (zero) */ @@ -10311,6 +10180,8 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x58: /* FRINTA */ case 0x59: /* FRINTX */ case 0x79: /* FRINTI */ + case 0x1d: /* SCVTF */ + case 0x5d: /* UCVTF */ unallocated_encoding(s); return; } diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index ec6b640fda..07f8d5f467 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -2505,12 +2505,15 @@ DO_3OP_PAIR(gvec_uminp_s, MIN, uint32_t, H4) clear_tail(d, oprsz, simd_maxsz(desc)); \ } +DO_VCVT_FIXED(gvec_vcvt_sd, helper_vfp_sqtod, uint64_t) +DO_VCVT_FIXED(gvec_vcvt_ud, helper_vfp_uqtod, uint64_t) DO_VCVT_FIXED(gvec_vcvt_sf, helper_vfp_sltos, uint32_t) DO_VCVT_FIXED(gvec_vcvt_uf, helper_vfp_ultos, uint32_t) -DO_VCVT_FIXED(gvec_vcvt_rz_fs, helper_vfp_tosls_round_to_zero, uint32_t) -DO_VCVT_FIXED(gvec_vcvt_rz_fu, helper_vfp_touls_round_to_zero, uint32_t) DO_VCVT_FIXED(gvec_vcvt_sh, helper_vfp_shtoh, uint16_t) DO_VCVT_FIXED(gvec_vcvt_uh, helper_vfp_uhtoh, uint16_t) + +DO_VCVT_FIXED(gvec_vcvt_rz_fs, helper_vfp_tosls_round_to_zero, uint32_t) +DO_VCVT_FIXED(gvec_vcvt_rz_fu, helper_vfp_touls_round_to_zero, uint32_t) DO_VCVT_FIXED(gvec_vcvt_rz_hs, helper_vfp_toshh_round_to_zero, uint16_t) DO_VCVT_FIXED(gvec_vcvt_rz_hu, helper_vfp_touhh_round_to_zero, uint16_t) From 9a93223c86c6721a9c868085dae28698852bb8d2 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:30 -0600 Subject: [PATCH 63/85] target/arm: Convert FCVTZ[SU] (vector, fixed-point) to decodetree Remove handle_simd_shift_fpint_conv and disas_simd_shift_imm as these were the last insns decoded by those functions. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-64-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 4 + target/arm/tcg/a64.decode | 8 ++ target/arm/tcg/translate-a64.c | 160 +++------------------------------ target/arm/tcg/vec_helper.c | 2 + target/arm/vfp_helper.c | 4 + 5 files changed, 32 insertions(+), 146 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index b227ac54d9..0c8a56c3ae 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -178,8 +178,10 @@ DEF_HELPER_3(vfp_touhs_round_to_zero, i32, f32, i32, ptr) DEF_HELPER_3(vfp_touls_round_to_zero, i32, f32, i32, ptr) DEF_HELPER_3(vfp_toshd_round_to_zero, i64, f64, i32, ptr) DEF_HELPER_3(vfp_tosld_round_to_zero, i64, f64, i32, ptr) +DEF_HELPER_3(vfp_tosqd_round_to_zero, i64, f64, i32, ptr) 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_touqd_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) @@ -660,6 +662,8 @@ DEF_HELPER_FLAGS_4(gvec_vcvt_rz_hu, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_sd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_ud, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rz_ds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rz_du, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ss, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rm_us, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 4f832e7a4c..61d519b96a 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1808,3 +1808,11 @@ SCVTF_vf 0.00 11110 ....... 111001 ..... ..... @fcvtq_d UCVTF_vf 0.10 11110 ....... 111001 ..... ..... @fcvtq_h UCVTF_vf 0.10 11110 ....... 111001 ..... ..... @fcvtq_s UCVTF_vf 0.10 11110 ....... 111001 ..... ..... @fcvtq_d + +FCVTZS_vf 0.00 11110 ....... 111111 ..... ..... @fcvtq_h +FCVTZS_vf 0.00 11110 ....... 111111 ..... ..... @fcvtq_s +FCVTZS_vf 0.00 11110 ....... 111111 ..... ..... @fcvtq_d + +FCVTZU_vf 0.10 11110 ....... 111111 ..... ..... @fcvtq_h +FCVTZU_vf 0.10 11110 ....... 111111 ..... ..... @fcvtq_s +FCVTZU_vf 0.10 11110 ....... 111111 ..... ..... @fcvtq_d diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 0f94fa4fdc..1c4e53770b 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -9332,107 +9332,21 @@ TRANS(UCVTF_vi, do_gvec_op2_fpst, TRANS(UCVTF_vf, do_gvec_op2_fpst, a->esz, a->q, a->rd, a->rn, a->shift, f_ucvtf_v) -/* FCVTZS, FVCVTZU - FP to fixedpoint conversion */ -static void handle_simd_shift_fpint_conv(DisasContext *s, bool is_scalar, - bool is_q, bool is_u, - int immh, int immb, int rn, int rd) -{ - int immhb = immh << 3 | immb; - int pass, size, fracbits; - TCGv_ptr tcg_fpstatus; - TCGv_i32 tcg_rmode, tcg_shift; +static gen_helper_gvec_2_ptr * const f_fcvtzs_vf[] = { + gen_helper_gvec_vcvt_rz_hs, + gen_helper_gvec_vcvt_rz_fs, + gen_helper_gvec_vcvt_rz_ds, +}; +TRANS(FCVTZS_vf, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, a->shift, f_fcvtzs_vf) - if (immh & 0x8) { - size = MO_64; - if (!is_scalar && !is_q) { - unallocated_encoding(s); - return; - } - } else if (immh & 0x4) { - size = MO_32; - } else if (immh & 0x2) { - size = MO_16; - if (!dc_isar_feature(aa64_fp16, s)) { - unallocated_encoding(s); - return; - } - } else { - /* Should have split out AdvSIMD modified immediate earlier. */ - assert(immh == 1); - unallocated_encoding(s); - return; - } - - if (!fp_access_check(s)) { - return; - } - - assert(!(is_scalar && is_q)); - - tcg_fpstatus = fpstatus_ptr(size == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); - tcg_rmode = gen_set_rmode(FPROUNDING_ZERO, tcg_fpstatus); - fracbits = (16 << size) - immhb; - tcg_shift = tcg_constant_i32(fracbits); - - if (size == MO_64) { - int maxpass = is_scalar ? 1 : 2; - - for (pass = 0; pass < maxpass; pass++) { - TCGv_i64 tcg_op = tcg_temp_new_i64(); - - read_vec_element(s, tcg_op, rn, pass, MO_64); - if (is_u) { - gen_helper_vfp_touqd(tcg_op, tcg_op, tcg_shift, tcg_fpstatus); - } else { - gen_helper_vfp_tosqd(tcg_op, tcg_op, tcg_shift, tcg_fpstatus); - } - write_vec_element(s, tcg_op, rd, pass, MO_64); - } - clear_vec_high(s, is_q, rd); - } else { - void (*fn)(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); - int maxpass = is_scalar ? 1 : ((8 << is_q) >> size); - - switch (size) { - case MO_16: - if (is_u) { - fn = gen_helper_vfp_touhh; - } else { - fn = gen_helper_vfp_toshh; - } - break; - case MO_32: - if (is_u) { - fn = gen_helper_vfp_touls; - } else { - fn = gen_helper_vfp_tosls; - } - break; - default: - g_assert_not_reached(); - } - - for (pass = 0; pass < maxpass; pass++) { - TCGv_i32 tcg_op = tcg_temp_new_i32(); - - read_vec_element_i32(s, tcg_op, rn, pass, size); - fn(tcg_op, tcg_op, tcg_shift, tcg_fpstatus); - if (is_scalar) { - if (size == MO_16 && !is_u) { - tcg_gen_ext16u_i32(tcg_op, tcg_op); - } - write_fp_sreg(s, rd, tcg_op); - } else { - write_vec_element_i32(s, tcg_op, rd, pass, size); - } - } - if (!is_scalar) { - clear_vec_high(s, is_q, rd); - } - } - - gen_restore_rmode(tcg_rmode, tcg_fpstatus); -} +static gen_helper_gvec_2_ptr * const f_fcvtzu_vf[] = { + gen_helper_gvec_vcvt_rz_hu, + gen_helper_gvec_vcvt_rz_fu, + gen_helper_gvec_vcvt_rz_du, +}; +TRANS(FCVTZU_vf, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, a->shift, f_fcvtzu_vf) static void handle_2misc_64(DisasContext *s, int opcode, bool u, TCGv_i64 tcg_rd, TCGv_i64 tcg_rn, @@ -9759,51 +9673,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) g_assert_not_reached(); } -/* AdvSIMD shift by immediate - * 31 30 29 28 23 22 19 18 16 15 11 10 9 5 4 0 - * +---+---+---+-------------+------+------+--------+---+------+------+ - * | 0 | Q | U | 0 1 1 1 1 0 | immh | immb | opcode | 1 | Rn | Rd | - * +---+---+---+-------------+------+------+--------+---+------+------+ - */ -static void disas_simd_shift_imm(DisasContext *s, uint32_t insn) -{ - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int opcode = extract32(insn, 11, 5); - int immb = extract32(insn, 16, 3); - int immh = extract32(insn, 19, 4); - bool is_u = extract32(insn, 29, 1); - bool is_q = extract32(insn, 30, 1); - - if (immh == 0) { - unallocated_encoding(s); - return; - } - - switch (opcode) { - case 0x1f: /* FCVTZS/ FCVTZU */ - handle_simd_shift_fpint_conv(s, false, is_q, is_u, immh, immb, rn, rd); - return; - default: - case 0x00: /* SSHR / USHR */ - case 0x02: /* SSRA / USRA (accumulate) */ - case 0x04: /* SRSHR / URSHR (rounding) */ - case 0x06: /* SRSRA / URSRA (accum + rounding) */ - case 0x08: /* SRI */ - case 0x0a: /* SHL / SLI */ - case 0x0c: /* SQSHLU */ - case 0x0e: /* SQSHL, UQSHL */ - case 0x10: /* SHRN / SQSHRUN */ - case 0x11: /* RSHRN / SQRSHRUN */ - case 0x12: /* SQSHRN / UQSHRN */ - case 0x13: /* SQRSHRN / UQRSHRN */ - case 0x14: /* SSHLL / USHLL */ - case 0x1c: /* SCVTF / UCVTF */ - unallocated_encoding(s); - return; - } -} - static void handle_2misc_widening(DisasContext *s, int opcode, bool is_q, int size, int rn, int rd) { @@ -10299,7 +10168,6 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) static const AArch64DecodeTable data_proc_simd[] = { /* pattern , mask , fn */ { 0x0e200800, 0x9f3e0c00, disas_simd_two_reg_misc }, - { 0x0f000400, 0x9f800400, disas_simd_shift_imm }, { 0x5e200800, 0xdf3e0c00, disas_simd_scalar_two_reg_misc }, { 0x0e780800, 0x8f7e0c00, disas_simd_two_reg_misc_fp16 }, { 0x00000000, 0x00000000, NULL } diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index 07f8d5f467..b5ab8d1e15 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -2512,6 +2512,8 @@ DO_VCVT_FIXED(gvec_vcvt_uf, helper_vfp_ultos, uint32_t) DO_VCVT_FIXED(gvec_vcvt_sh, helper_vfp_shtoh, uint16_t) DO_VCVT_FIXED(gvec_vcvt_uh, helper_vfp_uhtoh, uint16_t) +DO_VCVT_FIXED(gvec_vcvt_rz_ds, helper_vfp_tosqd_round_to_zero, uint64_t) +DO_VCVT_FIXED(gvec_vcvt_rz_du, helper_vfp_touqd_round_to_zero, uint64_t) DO_VCVT_FIXED(gvec_vcvt_rz_fs, helper_vfp_tosls_round_to_zero, uint32_t) DO_VCVT_FIXED(gvec_vcvt_rz_fu, helper_vfp_touls_round_to_zero, uint32_t) DO_VCVT_FIXED(gvec_vcvt_rz_hs, helper_vfp_toshh_round_to_zero, uint16_t) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index f24992c798..5a19af509c 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -495,6 +495,10 @@ VFP_CONV_FIX_A64(sq, h, 16, dh_ctype_f16, 64, int64) VFP_CONV_FIX(uh, h, 16, dh_ctype_f16, 32, uint16) VFP_CONV_FIX(ul, h, 16, dh_ctype_f16, 32, uint32) VFP_CONV_FIX_A64(uq, h, 16, dh_ctype_f16, 64, uint64) +VFP_CONV_FLOAT_FIX_ROUND(sq, d, 64, float64, 64, int64, + float_round_to_zero, _round_to_zero) +VFP_CONV_FLOAT_FIX_ROUND(uq, d, 64, float64, 64, uint64, + float_round_to_zero, _round_to_zero) #undef VFP_CONV_FIX #undef VFP_CONV_FIX_FLOAT From 475dbea47d57102682a16c798b200df7e16c0776 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:31 -0600 Subject: [PATCH 64/85] target/arm: Convert FCVT* (vector, integer) to decodetree Remove handle_2misc_64 as these were the last insns decoded by that function. Remove helper_advsimd_f16to[su]inth as unused; we now always go through helper_vfp_to[su]hh or a specialized vector function instead. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-65-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 2 + target/arm/tcg/a64.decode | 25 ++++ target/arm/tcg/helper-a64.c | 32 ----- target/arm/tcg/helper-a64.h | 2 - target/arm/tcg/translate-a64.c | 227 +++++++++++---------------------- target/arm/tcg/vec_helper.c | 2 + 6 files changed, 102 insertions(+), 188 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 0c8a56c3ae..64aa603465 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -665,6 +665,8 @@ DEF_HELPER_FLAGS_4(gvec_vcvt_ud, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rz_ds, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rz_du, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sd, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ud, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rm_ss, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rm_us, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_vcvt_rm_sh, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 61d519b96a..05a0b84416 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1793,6 +1793,31 @@ SCVTF_vi 0.00 1110 0.1 00001 11011 0 ..... ..... @qrr_sd UCVTF_vi 0.10 1110 011 11001 11011 0 ..... ..... @qrr_h UCVTF_vi 0.10 1110 0.1 00001 11011 0 ..... ..... @qrr_sd +FCVTNS_vi 0.00 1110 011 11001 10101 0 ..... ..... @qrr_h +FCVTNS_vi 0.00 1110 0.1 00001 10101 0 ..... ..... @qrr_sd +FCVTNU_vi 0.10 1110 011 11001 10101 0 ..... ..... @qrr_h +FCVTNU_vi 0.10 1110 0.1 00001 10101 0 ..... ..... @qrr_sd + +FCVTPS_vi 0.00 1110 111 11001 10101 0 ..... ..... @qrr_h +FCVTPS_vi 0.00 1110 1.1 00001 10101 0 ..... ..... @qrr_sd +FCVTPU_vi 0.10 1110 111 11001 10101 0 ..... ..... @qrr_h +FCVTPU_vi 0.10 1110 1.1 00001 10101 0 ..... ..... @qrr_sd + +FCVTMS_vi 0.00 1110 011 11001 10111 0 ..... ..... @qrr_h +FCVTMS_vi 0.00 1110 0.1 00001 10111 0 ..... ..... @qrr_sd +FCVTMU_vi 0.10 1110 011 11001 10111 0 ..... ..... @qrr_h +FCVTMU_vi 0.10 1110 0.1 00001 10111 0 ..... ..... @qrr_sd + +FCVTZS_vi 0.00 1110 111 11001 10111 0 ..... ..... @qrr_h +FCVTZS_vi 0.00 1110 1.1 00001 10111 0 ..... ..... @qrr_sd +FCVTZU_vi 0.10 1110 111 11001 10111 0 ..... ..... @qrr_h +FCVTZU_vi 0.10 1110 1.1 00001 10111 0 ..... ..... @qrr_sd + +FCVTAS_vi 0.00 1110 011 11001 11001 0 ..... ..... @qrr_h +FCVTAS_vi 0.00 1110 0.1 00001 11001 0 ..... ..... @qrr_sd +FCVTAU_vi 0.10 1110 011 11001 11001 0 ..... ..... @qrr_h +FCVTAU_vi 0.10 1110 0.1 00001 11001 0 ..... ..... @qrr_sd + &fcvt_q rd rn esz q shift @fcvtq_h . q:1 . ...... 001 .... ...... rn:5 rd:5 \ &fcvt_q esz=1 shift=%fcvt_f_sh_h diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index 3de564e0fe..28de7468cd 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -618,38 +618,6 @@ uint32_t HELPER(advsimd_rinth)(uint32_t x, void *fp_status) return ret; } -/* - * Half-precision floating point conversion functions - * - * There are a multitude of conversion functions with various - * different rounding modes. This is dealt with by the calling code - * setting the mode appropriately before calling the helper. - */ - -uint32_t HELPER(advsimd_f16tosinth)(uint32_t a, void *fpstp) -{ - float_status *fpst = fpstp; - - /* Invalid if we are passed a NaN */ - if (float16_is_any_nan(a)) { - float_raise(float_flag_invalid, fpst); - return 0; - } - return float16_to_int16(a, fpst); -} - -uint32_t HELPER(advsimd_f16touinth)(uint32_t a, void *fpstp) -{ - float_status *fpst = fpstp; - - /* Invalid if we are passed a NaN */ - if (float16_is_any_nan(a)) { - float_raise(float_flag_invalid, fpst); - return 0; - } - 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, diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index ac7ca190fa..3c0774139b 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -74,8 +74,6 @@ DEF_HELPER_3(advsimd_mulx2h, i32, i32, i32, ptr) DEF_HELPER_4(advsimd_muladd2h, i32, i32, i32, i32, ptr) DEF_HELPER_2(advsimd_rinth_exact, f16, f16, ptr) 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(exception_return, void, env, i64) DEF_HELPER_FLAGS_2(dc_zva, TCG_CALL_NO_WG, void, env, i64) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 1c4e53770b..ec1ce44c4b 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -9348,56 +9348,38 @@ static gen_helper_gvec_2_ptr * const f_fcvtzu_vf[] = { TRANS(FCVTZU_vf, do_gvec_op2_fpst, a->esz, a->q, a->rd, a->rn, a->shift, f_fcvtzu_vf) -static void handle_2misc_64(DisasContext *s, int opcode, bool u, - TCGv_i64 tcg_rd, TCGv_i64 tcg_rn, - TCGv_i32 tcg_rmode, TCGv_ptr tcg_fpstatus) -{ - /* Handle 64->64 opcodes which are shared between the scalar and - * vector 2-reg-misc groups. We cover every integer opcode where size == 3 - * is valid in either group and also the double-precision fp ops. - * The caller only need provide tcg_rmode and tcg_fpstatus if the op - * requires them. - */ - switch (opcode) { - case 0x1a: /* FCVTNS */ - case 0x1b: /* FCVTMS */ - case 0x1c: /* FCVTAS */ - case 0x3a: /* FCVTPS */ - case 0x3b: /* FCVTZS */ - gen_helper_vfp_tosqd(tcg_rd, tcg_rn, tcg_constant_i32(0), tcg_fpstatus); - break; - case 0x5a: /* FCVTNU */ - case 0x5b: /* FCVTMU */ - case 0x5c: /* FCVTAU */ - case 0x7a: /* FCVTPU */ - case 0x7b: /* FCVTZU */ - gen_helper_vfp_touqd(tcg_rd, tcg_rn, tcg_constant_i32(0), tcg_fpstatus); - break; - default: - case 0x4: /* CLS, CLZ */ - case 0x5: /* NOT */ - case 0x7: /* SQABS, SQNEG */ - case 0x8: /* CMGT, CMGE */ - case 0x9: /* CMEQ, CMLE */ - case 0xa: /* CMLT */ - case 0xb: /* ABS, NEG */ - case 0x2f: /* FABS */ - case 0x6f: /* FNEG */ - case 0x7f: /* FSQRT */ - case 0x18: /* FRINTN */ - case 0x19: /* FRINTM */ - case 0x38: /* FRINTP */ - case 0x39: /* FRINTZ */ - case 0x58: /* FRINTA */ - case 0x79: /* FRINTI */ - case 0x59: /* FRINTX */ - case 0x1e: /* FRINT32Z */ - case 0x5e: /* FRINT32X */ - case 0x1f: /* FRINT64Z */ - case 0x5f: /* FRINT64X */ - g_assert_not_reached(); - } -} +static gen_helper_gvec_2_ptr * const f_fcvt_s_vi[] = { + gen_helper_gvec_vcvt_rm_sh, + gen_helper_gvec_vcvt_rm_ss, + gen_helper_gvec_vcvt_rm_sd, +}; + +static gen_helper_gvec_2_ptr * const f_fcvt_u_vi[] = { + gen_helper_gvec_vcvt_rm_uh, + gen_helper_gvec_vcvt_rm_us, + gen_helper_gvec_vcvt_rm_ud, +}; + +TRANS(FCVTNS_vi, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, float_round_nearest_even, f_fcvt_s_vi) +TRANS(FCVTNU_vi, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, float_round_nearest_even, f_fcvt_u_vi) +TRANS(FCVTPS_vi, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, float_round_up, f_fcvt_s_vi) +TRANS(FCVTPU_vi, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, float_round_up, f_fcvt_u_vi) +TRANS(FCVTMS_vi, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, float_round_down, f_fcvt_s_vi) +TRANS(FCVTMU_vi, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, float_round_down, f_fcvt_u_vi) +TRANS(FCVTZS_vi, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, float_round_to_zero, f_fcvt_s_vi) +TRANS(FCVTZU_vi, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, float_round_to_zero, f_fcvt_u_vi) +TRANS(FCVTAS_vi, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, float_round_ties_away, f_fcvt_s_vi) +TRANS(FCVTAU_vi, do_gvec_op2_fpst, + a->esz, a->q, a->rd, a->rn, float_round_ties_away, f_fcvt_u_vi) static void handle_2misc_fcmp_zero(DisasContext *s, int opcode, bool is_scalar, bool is_u, bool is_q, @@ -9758,30 +9740,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } handle_2misc_fcmp_zero(s, opcode, false, u, is_q, size, rn, rd); return; - case 0x1a: /* FCVTNS */ - case 0x1b: /* FCVTMS */ - case 0x3a: /* FCVTPS */ - case 0x3b: /* FCVTZS */ - case 0x5a: /* FCVTNU */ - case 0x5b: /* FCVTMU */ - case 0x7a: /* FCVTPU */ - case 0x7b: /* FCVTZU */ - need_fpstatus = true; - rmode = extract32(opcode, 5, 1) | (extract32(opcode, 0, 1) << 1); - if (size == 3 && !is_q) { - unallocated_encoding(s); - return; - } - break; - case 0x5c: /* FCVTAU */ - case 0x1c: /* FCVTAS */ - need_fpstatus = true; - rmode = FPROUNDING_TIEAWAY; - if (size == 3 && !is_q) { - unallocated_encoding(s); - return; - } - break; case 0x3c: /* URECPE */ if (size == 3) { unallocated_encoding(s); @@ -9831,6 +9789,16 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x5f: /* FRINT64X */ case 0x1d: /* SCVTF */ case 0x5d: /* UCVTF */ + case 0x1a: /* FCVTNS */ + case 0x1b: /* FCVTMS */ + case 0x3a: /* FCVTPS */ + case 0x3b: /* FCVTZS */ + case 0x5a: /* FCVTNU */ + case 0x5b: /* FCVTMU */ + case 0x7a: /* FCVTPU */ + case 0x7b: /* FCVTZU */ + case 0x5c: /* FCVTAU */ + case 0x1c: /* FCVTAS */ unallocated_encoding(s); return; } @@ -9871,26 +9839,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) tcg_rmode = NULL; } - if (size == 3) { - /* All 64-bit element operations can be shared with scalar 2misc */ - int pass; - - /* Coverity claims (size == 3 && !is_q) has been eliminated - * from all paths leading to here. - */ - tcg_debug_assert(is_q); - for (pass = 0; pass < 2; pass++) { - TCGv_i64 tcg_op = tcg_temp_new_i64(); - TCGv_i64 tcg_res = tcg_temp_new_i64(); - - read_vec_element(s, tcg_op, rn, pass, MO_64); - - handle_2misc_64(s, opcode, u, tcg_res, tcg_op, - tcg_rmode, tcg_fpstatus); - - write_vec_element(s, tcg_res, rd, pass, MO_64); - } - } else { + { int pass; assert(size == 2); @@ -9903,22 +9852,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) { /* Special cases for 32 bit elements */ switch (opcode) { - case 0x1a: /* FCVTNS */ - case 0x1b: /* FCVTMS */ - case 0x1c: /* FCVTAS */ - case 0x3a: /* FCVTPS */ - case 0x3b: /* FCVTZS */ - gen_helper_vfp_tosls(tcg_res, tcg_op, - tcg_constant_i32(0), tcg_fpstatus); - break; - case 0x5a: /* FCVTNU */ - case 0x5b: /* FCVTMU */ - case 0x5c: /* FCVTAU */ - case 0x7a: /* FCVTPU */ - case 0x7b: /* FCVTZU */ - gen_helper_vfp_touls(tcg_res, tcg_op, - tcg_constant_i32(0), tcg_fpstatus); - break; case 0x7c: /* URSQRTE */ gen_helper_rsqrte_u32(tcg_res, tcg_op); break; @@ -9938,6 +9871,16 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x5e: /* FRINT32X */ case 0x1f: /* FRINT64Z */ case 0x5f: /* FRINT64X */ + case 0x1a: /* FCVTNS */ + case 0x1b: /* FCVTMS */ + case 0x1c: /* FCVTAS */ + case 0x3a: /* FCVTPS */ + case 0x3b: /* FCVTZS */ + case 0x5a: /* FCVTNU */ + case 0x5b: /* FCVTMU */ + case 0x5c: /* FCVTAU */ + case 0x7a: /* FCVTPU */ + case 0x7b: /* FCVTZU */ g_assert_not_reached(); } } @@ -10006,36 +9949,6 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x3d: /* FRECPE */ case 0x3f: /* FRECPX */ break; - case 0x1a: /* FCVTNS */ - rmode = FPROUNDING_TIEEVEN; - break; - case 0x1b: /* FCVTMS */ - rmode = FPROUNDING_NEGINF; - break; - case 0x1c: /* FCVTAS */ - rmode = FPROUNDING_TIEAWAY; - break; - case 0x3a: /* FCVTPS */ - rmode = FPROUNDING_POSINF; - break; - case 0x3b: /* FCVTZS */ - rmode = FPROUNDING_ZERO; - break; - case 0x5a: /* FCVTNU */ - rmode = FPROUNDING_TIEEVEN; - break; - case 0x5b: /* FCVTMU */ - rmode = FPROUNDING_NEGINF; - break; - case 0x5c: /* FCVTAU */ - rmode = FPROUNDING_TIEAWAY; - break; - case 0x7a: /* FCVTPU */ - rmode = FPROUNDING_POSINF; - break; - case 0x7b: /* FCVTZU */ - rmode = FPROUNDING_ZERO; - break; case 0x7d: /* FRSQRTE */ break; default: @@ -10051,6 +9964,16 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x79: /* FRINTI */ case 0x1d: /* SCVTF */ case 0x5d: /* UCVTF */ + case 0x1a: /* FCVTNS */ + case 0x1b: /* FCVTMS */ + case 0x1c: /* FCVTAS */ + case 0x3a: /* FCVTPS */ + case 0x3b: /* FCVTZS */ + case 0x5a: /* FCVTNU */ + case 0x5b: /* FCVTMU */ + case 0x5c: /* FCVTAU */ + case 0x7a: /* FCVTPU */ + case 0x7b: /* FCVTZU */ unallocated_encoding(s); return; } @@ -10115,23 +10038,9 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) read_vec_element_i32(s, tcg_op, rn, pass, MO_16); switch (fpop) { - case 0x1a: /* FCVTNS */ - case 0x1b: /* FCVTMS */ - case 0x1c: /* FCVTAS */ - case 0x3a: /* FCVTPS */ - case 0x3b: /* FCVTZS */ - gen_helper_advsimd_f16tosinth(tcg_res, tcg_op, tcg_fpstatus); - break; case 0x3d: /* FRECPE */ gen_helper_recpe_f16(tcg_res, tcg_op, tcg_fpstatus); break; - case 0x5a: /* FCVTNU */ - case 0x5b: /* FCVTMU */ - case 0x5c: /* FCVTAU */ - case 0x7a: /* FCVTPU */ - case 0x7b: /* FCVTZU */ - gen_helper_advsimd_f16touinth(tcg_res, tcg_op, tcg_fpstatus); - break; case 0x7d: /* FRSQRTE */ gen_helper_rsqrte_f16(tcg_res, tcg_op, tcg_fpstatus); break; @@ -10146,6 +10055,16 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x58: /* FRINTA */ case 0x79: /* FRINTI */ case 0x59: /* FRINTX */ + case 0x1a: /* FCVTNS */ + case 0x1b: /* FCVTMS */ + case 0x1c: /* FCVTAS */ + case 0x3a: /* FCVTPS */ + case 0x3b: /* FCVTZS */ + case 0x5a: /* FCVTNU */ + case 0x5b: /* FCVTMU */ + case 0x5c: /* FCVTAU */ + case 0x7a: /* FCVTPU */ + case 0x7b: /* FCVTZU */ g_assert_not_reached(); } diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index b5ab8d1e15..bc752ff988 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -2537,6 +2537,8 @@ DO_VCVT_FIXED(gvec_vcvt_rz_hu, helper_vfp_touhh_round_to_zero, uint16_t) clear_tail(d, oprsz, simd_maxsz(desc)); \ } +DO_VCVT_RMODE(gvec_vcvt_rm_sd, helper_vfp_tosqd, uint64_t) +DO_VCVT_RMODE(gvec_vcvt_rm_ud, helper_vfp_touqd, uint64_t) DO_VCVT_RMODE(gvec_vcvt_rm_ss, helper_vfp_tosls, uint32_t) DO_VCVT_RMODE(gvec_vcvt_rm_us, helper_vfp_touls, uint32_t) DO_VCVT_RMODE(gvec_vcvt_rm_sh, helper_vfp_toshh, uint16_t) From df112a2578e94ffb36e0c6d091056bf708a7c24d Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:32 -0600 Subject: [PATCH 65/85] target/arm: Convert handle_2misc_fcmp_zero to decodetree This includes FCMEQ, FCMGT, FCMGE, FCMLT, FCMLE. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-66-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 5 + target/arm/tcg/a64.decode | 30 ++++ target/arm/tcg/translate-a64.c | 249 +++++++++++++-------------------- target/arm/tcg/vec_helper.c | 4 +- 4 files changed, 138 insertions(+), 150 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 64aa603465..1132a5cab6 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -688,18 +688,23 @@ DEF_HELPER_FLAGS_4(gvec_frsqrte_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_fcgt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_fcgt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fcgt0_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_fcge0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_fcge0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fcge0_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_fceq0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_fceq0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fceq0_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_fcle0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_fcle0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fcle0_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_fclt0_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_fclt0_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(gvec_fclt0_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fadd_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(gvec_fadd_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 05a0b84416..d1c4a330f2 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1652,6 +1652,21 @@ UQXTN_s 0111 1110 ..1 00001 01001 0 ..... ..... @rr_e FCVTXN_s 0111 1110 011 00001 01101 0 ..... ..... @rr_s +FCMGT0_s 0101 1110 111 11000 11001 0 ..... ..... @rr_h +FCMGT0_s 0101 1110 1.1 00000 11001 0 ..... ..... @rr_sd + +FCMGE0_s 0111 1110 111 11000 11001 0 ..... ..... @rr_h +FCMGE0_s 0111 1110 1.1 00000 11001 0 ..... ..... @rr_sd + +FCMEQ0_s 0101 1110 111 11000 11011 0 ..... ..... @rr_h +FCMEQ0_s 0101 1110 1.1 00000 11011 0 ..... ..... @rr_sd + +FCMLE0_s 0111 1110 111 11000 11011 0 ..... ..... @rr_h +FCMLE0_s 0111 1110 1.1 00000 11011 0 ..... ..... @rr_sd + +FCMLT0_s 0101 1110 111 11000 11101 0 ..... ..... @rr_h +FCMLT0_s 0101 1110 1.1 00000 11101 0 ..... ..... @rr_sd + @icvt_h . ....... .. ...... ...... rn:5 rd:5 \ &fcvt sf=0 esz=1 shift=0 @icvt_sd . ....... .. ...... ...... rn:5 rd:5 \ @@ -1818,6 +1833,21 @@ FCVTAS_vi 0.00 1110 0.1 00001 11001 0 ..... ..... @qrr_sd FCVTAU_vi 0.10 1110 011 11001 11001 0 ..... ..... @qrr_h FCVTAU_vi 0.10 1110 0.1 00001 11001 0 ..... ..... @qrr_sd +FCMGT0_v 0.00 1110 111 11000 11001 0 ..... ..... @qrr_h +FCMGT0_v 0.00 1110 1.1 00000 11001 0 ..... ..... @qrr_sd + +FCMGE0_v 0.10 1110 111 11000 11001 0 ..... ..... @qrr_h +FCMGE0_v 0.10 1110 1.1 00000 11001 0 ..... ..... @qrr_sd + +FCMEQ0_v 0.00 1110 111 11000 11011 0 ..... ..... @qrr_h +FCMEQ0_v 0.00 1110 1.1 00000 11011 0 ..... ..... @qrr_sd + +FCMLE0_v 0.10 1110 111 11000 11011 0 ..... ..... @qrr_h +FCMLE0_v 0.10 1110 1.1 00000 11011 0 ..... ..... @qrr_sd + +FCMLT0_v 0.00 1110 111 11000 11101 0 ..... ..... @qrr_h +FCMLT0_v 0.00 1110 1.1 00000 11101 0 ..... ..... @qrr_sd + &fcvt_q rd rn esz q shift @fcvtq_h . q:1 . ...... 001 .... ...... rn:5 rd:5 \ &fcvt_q esz=1 shift=%fcvt_f_sh_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index ec1ce44c4b..1776862161 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5250,6 +5250,61 @@ static const FPScalar f_scalar_frsqrts = { }; TRANS(FRSQRTS_s, do_fp3_scalar, a, &f_scalar_frsqrts) +static bool do_fcmp0_s(DisasContext *s, arg_rr_e *a, + const FPScalar *f, bool swap) +{ + switch (a->esz) { + case MO_64: + if (fp_access_check(s)) { + TCGv_i64 t0 = read_fp_dreg(s, a->rn); + TCGv_i64 t1 = tcg_constant_i64(0); + if (swap) { + f->gen_d(t0, t1, t0, fpstatus_ptr(FPST_FPCR)); + } else { + f->gen_d(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + } + write_fp_dreg(s, a->rd, t0); + } + break; + case MO_32: + if (fp_access_check(s)) { + TCGv_i32 t0 = read_fp_sreg(s, a->rn); + TCGv_i32 t1 = tcg_constant_i32(0); + if (swap) { + f->gen_s(t0, t1, t0, fpstatus_ptr(FPST_FPCR)); + } else { + f->gen_s(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + } + write_fp_sreg(s, a->rd, t0); + } + break; + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return false; + } + if (fp_access_check(s)) { + TCGv_i32 t0 = read_fp_hreg(s, a->rn); + TCGv_i32 t1 = tcg_constant_i32(0); + if (swap) { + f->gen_h(t0, t1, t0, fpstatus_ptr(FPST_FPCR_F16)); + } else { + f->gen_h(t0, t0, t1, fpstatus_ptr(FPST_FPCR_F16)); + } + write_fp_sreg(s, a->rd, t0); + } + break; + default: + return false; + } + return true; +} + +TRANS(FCMEQ0_s, do_fcmp0_s, a, &f_scalar_fcmeq, false) +TRANS(FCMGT0_s, do_fcmp0_s, a, &f_scalar_fcmgt, false) +TRANS(FCMGE0_s, do_fcmp0_s, a, &f_scalar_fcmge, false) +TRANS(FCMLT0_s, do_fcmp0_s, a, &f_scalar_fcmgt, true) +TRANS(FCMLE0_s, do_fcmp0_s, a, &f_scalar_fcmge, true) + static bool do_satacc_s(DisasContext *s, arg_rrr_e *a, MemOp sgn_n, MemOp sgn_m, void (*gen_bhs)(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_i64, MemOp), @@ -9381,134 +9436,40 @@ TRANS(FCVTAS_vi, do_gvec_op2_fpst, TRANS(FCVTAU_vi, do_gvec_op2_fpst, a->esz, a->q, a->rd, a->rn, float_round_ties_away, f_fcvt_u_vi) -static void handle_2misc_fcmp_zero(DisasContext *s, int opcode, - bool is_scalar, bool is_u, bool is_q, - int size, int rn, int rd) -{ - bool is_double = (size == MO_64); - TCGv_ptr fpst; +static gen_helper_gvec_2_ptr * const f_fceq0[] = { + gen_helper_gvec_fceq0_h, + gen_helper_gvec_fceq0_s, + gen_helper_gvec_fceq0_d, +}; +TRANS(FCMEQ0_v, do_gvec_op2_fpst, a->esz, a->q, a->rd, a->rn, 0, f_fceq0) - if (!fp_access_check(s)) { - return; - } +static gen_helper_gvec_2_ptr * const f_fcgt0[] = { + gen_helper_gvec_fcgt0_h, + gen_helper_gvec_fcgt0_s, + gen_helper_gvec_fcgt0_d, +}; +TRANS(FCMGT0_v, do_gvec_op2_fpst, a->esz, a->q, a->rd, a->rn, 0, f_fcgt0) - fpst = fpstatus_ptr(size == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); +static gen_helper_gvec_2_ptr * const f_fcge0[] = { + gen_helper_gvec_fcge0_h, + gen_helper_gvec_fcge0_s, + gen_helper_gvec_fcge0_d, +}; +TRANS(FCMGE0_v, do_gvec_op2_fpst, a->esz, a->q, a->rd, a->rn, 0, f_fcge0) - if (is_double) { - TCGv_i64 tcg_op = tcg_temp_new_i64(); - TCGv_i64 tcg_zero = tcg_constant_i64(0); - TCGv_i64 tcg_res = tcg_temp_new_i64(); - NeonGenTwoDoubleOpFn *genfn; - bool swap = false; - int pass; +static gen_helper_gvec_2_ptr * const f_fclt0[] = { + gen_helper_gvec_fclt0_h, + gen_helper_gvec_fclt0_s, + gen_helper_gvec_fclt0_d, +}; +TRANS(FCMLT0_v, do_gvec_op2_fpst, a->esz, a->q, a->rd, a->rn, 0, f_fclt0) - switch (opcode) { - case 0x2e: /* FCMLT (zero) */ - swap = true; - /* fallthrough */ - case 0x2c: /* FCMGT (zero) */ - genfn = gen_helper_neon_cgt_f64; - break; - case 0x2d: /* FCMEQ (zero) */ - genfn = gen_helper_neon_ceq_f64; - break; - case 0x6d: /* FCMLE (zero) */ - swap = true; - /* fall through */ - case 0x6c: /* FCMGE (zero) */ - genfn = gen_helper_neon_cge_f64; - break; - default: - g_assert_not_reached(); - } - - for (pass = 0; pass < (is_scalar ? 1 : 2); pass++) { - read_vec_element(s, tcg_op, rn, pass, MO_64); - if (swap) { - genfn(tcg_res, tcg_zero, tcg_op, fpst); - } else { - genfn(tcg_res, tcg_op, tcg_zero, fpst); - } - write_vec_element(s, tcg_res, rd, pass, MO_64); - } - - clear_vec_high(s, !is_scalar, rd); - } else { - TCGv_i32 tcg_op = tcg_temp_new_i32(); - TCGv_i32 tcg_zero = tcg_constant_i32(0); - TCGv_i32 tcg_res = tcg_temp_new_i32(); - NeonGenTwoSingleOpFn *genfn; - bool swap = false; - int pass, maxpasses; - - if (size == MO_16) { - switch (opcode) { - case 0x2e: /* FCMLT (zero) */ - swap = true; - /* fall through */ - case 0x2c: /* FCMGT (zero) */ - genfn = gen_helper_advsimd_cgt_f16; - break; - case 0x2d: /* FCMEQ (zero) */ - genfn = gen_helper_advsimd_ceq_f16; - break; - case 0x6d: /* FCMLE (zero) */ - swap = true; - /* fall through */ - case 0x6c: /* FCMGE (zero) */ - genfn = gen_helper_advsimd_cge_f16; - break; - default: - g_assert_not_reached(); - } - } else { - switch (opcode) { - case 0x2e: /* FCMLT (zero) */ - swap = true; - /* fall through */ - case 0x2c: /* FCMGT (zero) */ - genfn = gen_helper_neon_cgt_f32; - break; - case 0x2d: /* FCMEQ (zero) */ - genfn = gen_helper_neon_ceq_f32; - break; - case 0x6d: /* FCMLE (zero) */ - swap = true; - /* fall through */ - case 0x6c: /* FCMGE (zero) */ - genfn = gen_helper_neon_cge_f32; - break; - default: - g_assert_not_reached(); - } - } - - if (is_scalar) { - maxpasses = 1; - } else { - int vector_size = 8 << is_q; - maxpasses = vector_size >> size; - } - - for (pass = 0; pass < maxpasses; pass++) { - read_vec_element_i32(s, tcg_op, rn, pass, size); - if (swap) { - genfn(tcg_res, tcg_zero, tcg_op, fpst); - } else { - genfn(tcg_res, tcg_op, tcg_zero, fpst); - } - if (is_scalar) { - write_fp_sreg(s, rd, tcg_res); - } else { - write_vec_element_i32(s, tcg_res, rd, pass, size); - } - } - - if (!is_scalar) { - clear_vec_high(s, is_q, rd); - } - } -} +static gen_helper_gvec_2_ptr * const f_fcle0[] = { + gen_helper_gvec_fcle0_h, + gen_helper_gvec_fcle0_s, + gen_helper_gvec_fcle0_d, +}; +TRANS(FCMLE0_v, do_gvec_op2_fpst, a->esz, a->q, a->rd, a->rn, 0, f_fcle0) static void handle_2misc_reciprocal(DisasContext *s, int opcode, bool is_scalar, bool is_u, bool is_q, @@ -9607,13 +9568,6 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) opcode |= (extract32(size, 1, 1) << 5) | (u << 6); size = extract32(size, 0, 1) ? 3 : 2; switch (opcode) { - case 0x2c: /* FCMGT (zero) */ - case 0x2d: /* FCMEQ (zero) */ - case 0x2e: /* FCMLT (zero) */ - case 0x6c: /* FCMGE (zero) */ - case 0x6d: /* FCMLE (zero) */ - handle_2misc_fcmp_zero(s, opcode, true, u, true, size, rn, rd); - return; case 0x3d: /* FRECPE */ case 0x3f: /* FRECPX */ case 0x7d: /* FRSQRTE */ @@ -9635,6 +9589,11 @@ static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) case 0x56: /* FCVTXN, FCVTXN2 */ case 0x1d: /* SCVTF */ case 0x5d: /* UCVTF */ + case 0x2c: /* FCMGT (zero) */ + case 0x2d: /* FCMEQ (zero) */ + case 0x2e: /* FCMLT (zero) */ + case 0x6c: /* FCMGE (zero) */ + case 0x6d: /* FCMLE (zero) */ default: unallocated_encoding(s); return; @@ -9729,17 +9688,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) opcode |= (extract32(size, 1, 1) << 5) | (u << 6); size = is_double ? 3 : 2; switch (opcode) { - case 0x2c: /* FCMGT (zero) */ - case 0x2d: /* FCMEQ (zero) */ - case 0x2e: /* FCMLT (zero) */ - case 0x6c: /* FCMGE (zero) */ - case 0x6d: /* FCMLE (zero) */ - if (size == 3 && !is_q) { - unallocated_encoding(s); - return; - } - handle_2misc_fcmp_zero(s, opcode, false, u, is_q, size, rn, rd); - return; case 0x3c: /* URECPE */ if (size == 3) { unallocated_encoding(s); @@ -9799,6 +9747,11 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x7b: /* FCVTZU */ case 0x5c: /* FCVTAU */ case 0x1c: /* FCVTAS */ + case 0x2c: /* FCMGT (zero) */ + case 0x2d: /* FCMEQ (zero) */ + case 0x2e: /* FCMLT (zero) */ + case 0x6c: /* FCMGE (zero) */ + case 0x6d: /* FCMLE (zero) */ unallocated_encoding(s); return; } @@ -9939,13 +9892,6 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) fpop = deposit32(fpop, 6, 1, u); switch (fpop) { - case 0x2c: /* FCMGT (zero) */ - case 0x2d: /* FCMEQ (zero) */ - case 0x2e: /* FCMLT (zero) */ - case 0x6c: /* FCMGE (zero) */ - case 0x6d: /* FCMLE (zero) */ - handle_2misc_fcmp_zero(s, fpop, is_scalar, 0, is_q, MO_16, rn, rd); - return; case 0x3d: /* FRECPE */ case 0x3f: /* FRECPX */ break; @@ -9974,6 +9920,11 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) case 0x5c: /* FCVTAU */ case 0x7a: /* FCVTPU */ case 0x7b: /* FCVTZU */ + case 0x2c: /* FCMGT (zero) */ + case 0x2d: /* FCMEQ (zero) */ + case 0x2e: /* FCMLT (zero) */ + case 0x6c: /* FCMGE (zero) */ + case 0x6d: /* FCMLE (zero) */ unallocated_encoding(s); return; } diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index bc752ff988..ee84774517 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -1253,8 +1253,10 @@ DO_2OP(gvec_touszh, vfp_touszh, float16) #define DO_2OP_CMP0(FN, CMPOP, DIRN) \ WRAP_CMP0_##DIRN(FN, CMPOP, float16) \ WRAP_CMP0_##DIRN(FN, CMPOP, float32) \ + WRAP_CMP0_##DIRN(FN, CMPOP, float64) \ DO_2OP(gvec_f##FN##0_h, float16_##FN##0, float16) \ - DO_2OP(gvec_f##FN##0_s, float32_##FN##0, float32) + DO_2OP(gvec_f##FN##0_s, float32_##FN##0, float32) \ + DO_2OP(gvec_f##FN##0_d, float64_##FN##0, float64) DO_2OP_CMP0(cgt, cgt, FWD) DO_2OP_CMP0(cge, cge, FWD) From 31e65acf7bc54d80910f94353b710f8bafa049c2 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:33 -0600 Subject: [PATCH 66/85] target/arm: Convert FRECPE, FRECPX, FRSQRTE to decodetree Remove disas_simd_scalar_two_reg_misc and disas_simd_two_reg_misc_fp16 as these were the last insns decoded by those functions. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-67-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 15 ++ target/arm/tcg/translate-a64.c | 329 ++++----------------------------- 2 files changed, 53 insertions(+), 291 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index d1c4a330f2..9b3b09c3bb 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1667,6 +1667,15 @@ FCMLE0_s 0111 1110 1.1 00000 11011 0 ..... ..... @rr_sd FCMLT0_s 0101 1110 111 11000 11101 0 ..... ..... @rr_h FCMLT0_s 0101 1110 1.1 00000 11101 0 ..... ..... @rr_sd +FRECPE_s 0101 1110 111 11001 11011 0 ..... ..... @rr_h +FRECPE_s 0101 1110 1.1 00001 11011 0 ..... ..... @rr_sd + +FRECPX_s 0101 1110 111 11001 11111 0 ..... ..... @rr_h +FRECPX_s 0101 1110 1.1 00001 11111 0 ..... ..... @rr_sd + +FRSQRTE_s 0111 1110 111 11001 11011 0 ..... ..... @rr_h +FRSQRTE_s 0111 1110 1.1 00001 11011 0 ..... ..... @rr_sd + @icvt_h . ....... .. ...... ...... rn:5 rd:5 \ &fcvt sf=0 esz=1 shift=0 @icvt_sd . ....... .. ...... ...... rn:5 rd:5 \ @@ -1848,6 +1857,12 @@ FCMLE0_v 0.10 1110 1.1 00000 11011 0 ..... ..... @qrr_sd FCMLT0_v 0.00 1110 111 11000 11101 0 ..... ..... @qrr_h FCMLT0_v 0.00 1110 1.1 00000 11101 0 ..... ..... @qrr_sd +FRECPE_v 0.00 1110 111 11001 11011 0 ..... ..... @qrr_h +FRECPE_v 0.00 1110 1.1 00001 11011 0 ..... ..... @qrr_sd + +FRSQRTE_v 0.10 1110 111 11001 11011 0 ..... ..... @qrr_h +FRSQRTE_v 0.10 1110 1.1 00001 11011 0 ..... ..... @qrr_sd + &fcvt_q rd rn esz q shift @fcvtq_h . q:1 . ...... 001 .... ...... rn:5 rd:5 \ &fcvt_q esz=1 shift=%fcvt_f_sh_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 1776862161..63cf25251b 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -8501,6 +8501,27 @@ TRANS_FEAT(FRINT64Z_s, aa64_frint, do_fp1_scalar, a, &f_scalar_frint64, FPROUNDING_ZERO) TRANS_FEAT(FRINT64X_s, aa64_frint, do_fp1_scalar, a, &f_scalar_frint64, -1) +static const FPScalar1 f_scalar_frecpe = { + gen_helper_recpe_f16, + gen_helper_recpe_f32, + gen_helper_recpe_f64, +}; +TRANS(FRECPE_s, do_fp1_scalar, a, &f_scalar_frecpe, -1) + +static const FPScalar1 f_scalar_frecpx = { + gen_helper_frecpx_f16, + gen_helper_frecpx_f32, + gen_helper_frecpx_f64, +}; +TRANS(FRECPX_s, do_fp1_scalar, a, &f_scalar_frecpx, -1) + +static const FPScalar1 f_scalar_frsqrte = { + gen_helper_rsqrte_f16, + gen_helper_rsqrte_f32, + gen_helper_rsqrte_f64, +}; +TRANS(FRSQRTE_s, do_fp1_scalar, a, &f_scalar_frsqrte, -1) + static bool trans_FCVT_s_ds(DisasContext *s, arg_rr *a) { if (fp_access_check(s)) { @@ -9471,36 +9492,28 @@ static gen_helper_gvec_2_ptr * const f_fcle0[] = { }; TRANS(FCMLE0_v, do_gvec_op2_fpst, a->esz, a->q, a->rd, a->rn, 0, f_fcle0) +static gen_helper_gvec_2_ptr * const f_frecpe[] = { + gen_helper_gvec_frecpe_h, + gen_helper_gvec_frecpe_s, + gen_helper_gvec_frecpe_d, +}; +TRANS(FRECPE_v, do_gvec_op2_fpst, a->esz, a->q, a->rd, a->rn, 0, f_frecpe) + +static gen_helper_gvec_2_ptr * const f_frsqrte[] = { + gen_helper_gvec_frsqrte_h, + gen_helper_gvec_frsqrte_s, + gen_helper_gvec_frsqrte_d, +}; +TRANS(FRSQRTE_v, do_gvec_op2_fpst, a->esz, a->q, a->rd, a->rn, 0, f_frsqrte) + static void handle_2misc_reciprocal(DisasContext *s, int opcode, bool is_scalar, bool is_u, bool is_q, int size, int rn, int rd) { bool is_double = (size == 3); - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); if (is_double) { - TCGv_i64 tcg_op = tcg_temp_new_i64(); - TCGv_i64 tcg_res = tcg_temp_new_i64(); - int pass; - - for (pass = 0; pass < (is_scalar ? 1 : 2); pass++) { - read_vec_element(s, tcg_op, rn, pass, MO_64); - switch (opcode) { - case 0x3d: /* FRECPE */ - gen_helper_recpe_f64(tcg_res, tcg_op, fpst); - break; - case 0x3f: /* FRECPX */ - gen_helper_frecpx_f64(tcg_res, tcg_op, fpst); - break; - case 0x7d: /* FRSQRTE */ - gen_helper_rsqrte_f64(tcg_res, tcg_op, fpst); - break; - default: - g_assert_not_reached(); - } - write_vec_element(s, tcg_res, rd, pass, MO_64); - } - clear_vec_high(s, !is_scalar, rd); + g_assert_not_reached(); } else { TCGv_i32 tcg_op = tcg_temp_new_i32(); TCGv_i32 tcg_res = tcg_temp_new_i32(); @@ -9520,14 +9533,8 @@ static void handle_2misc_reciprocal(DisasContext *s, int opcode, gen_helper_recpe_u32(tcg_res, tcg_op); break; case 0x3d: /* FRECPE */ - gen_helper_recpe_f32(tcg_res, tcg_op, fpst); - break; case 0x3f: /* FRECPX */ - gen_helper_frecpx_f32(tcg_res, tcg_op, fpst); - break; case 0x7d: /* FRSQRTE */ - gen_helper_rsqrte_f32(tcg_res, tcg_op, fpst); - break; default: g_assert_not_reached(); } @@ -9544,76 +9551,6 @@ static void handle_2misc_reciprocal(DisasContext *s, int opcode, } } -/* AdvSIMD scalar two reg misc - * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0 - * +-----+---+-----------+------+-----------+--------+-----+------+------+ - * | 0 1 | U | 1 1 1 1 0 | size | 1 0 0 0 0 | opcode | 1 0 | Rn | Rd | - * +-----+---+-----------+------+-----------+--------+-----+------+------+ - */ -static void disas_simd_scalar_two_reg_misc(DisasContext *s, uint32_t insn) -{ - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int opcode = extract32(insn, 12, 5); - int size = extract32(insn, 22, 2); - bool u = extract32(insn, 29, 1); - - switch (opcode) { - case 0xc ... 0xf: - case 0x16 ... 0x1d: - case 0x1f: - /* Floating point: U, size[1] and opcode indicate operation; - * size[0] indicates single or double precision. - */ - opcode |= (extract32(size, 1, 1) << 5) | (u << 6); - size = extract32(size, 0, 1) ? 3 : 2; - switch (opcode) { - case 0x3d: /* FRECPE */ - case 0x3f: /* FRECPX */ - case 0x7d: /* FRSQRTE */ - if (!fp_access_check(s)) { - return; - } - handle_2misc_reciprocal(s, opcode, true, u, true, size, rn, rd); - return; - case 0x1a: /* FCVTNS */ - case 0x1b: /* FCVTMS */ - case 0x3a: /* FCVTPS */ - case 0x3b: /* FCVTZS */ - case 0x5a: /* FCVTNU */ - case 0x5b: /* FCVTMU */ - case 0x7a: /* FCVTPU */ - case 0x7b: /* FCVTZU */ - case 0x1c: /* FCVTAS */ - case 0x5c: /* FCVTAU */ - case 0x56: /* FCVTXN, FCVTXN2 */ - case 0x1d: /* SCVTF */ - case 0x5d: /* UCVTF */ - case 0x2c: /* FCMGT (zero) */ - case 0x2d: /* FCMEQ (zero) */ - case 0x2e: /* FCMLT (zero) */ - case 0x6c: /* FCMGE (zero) */ - case 0x6d: /* FCMLE (zero) */ - default: - unallocated_encoding(s); - return; - } - break; - default: - case 0x3: /* USQADD / SUQADD */ - case 0x7: /* SQABS / SQNEG */ - case 0x8: /* CMGT, CMGE */ - case 0x9: /* CMEQ, CMLE */ - case 0xa: /* CMLT */ - case 0xb: /* ABS, NEG */ - case 0x12: /* SQXTUN */ - case 0x14: /* SQXTN, UQXTN */ - unallocated_encoding(s); - return; - } - g_assert_not_reached(); -} - static void handle_2misc_widening(DisasContext *s, int opcode, bool is_q, int size, int rn, int rd) { @@ -9693,13 +9630,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - /* fall through */ - case 0x3d: /* FRECPE */ - case 0x7d: /* FRSQRTE */ - if (size == 3 && !is_q) { - unallocated_encoding(s); - return; - } if (!fp_access_check(s)) { return; } @@ -9752,6 +9682,8 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x2e: /* FCMLT (zero) */ case 0x6c: /* FCMGE (zero) */ case 0x6d: /* FCMLE (zero) */ + case 0x3d: /* FRECPE */ + case 0x7d: /* FRSQRTE */ unallocated_encoding(s); return; } @@ -9847,189 +9779,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) } } -/* AdvSIMD [scalar] two register miscellaneous (FP16) - * - * 31 30 29 28 27 24 23 22 21 17 16 12 11 10 9 5 4 0 - * +---+---+---+---+---------+---+-------------+--------+-----+------+------+ - * | 0 | Q | U | S | 1 1 1 0 | a | 1 1 1 1 0 0 | opcode | 1 0 | Rn | Rd | - * +---+---+---+---+---------+---+-------------+--------+-----+------+------+ - * mask: 1000 1111 0111 1110 0000 1100 0000 0000 0x8f7e 0c00 - * val: 0000 1110 0111 1000 0000 1000 0000 0000 0x0e78 0800 - * - * This actually covers two groups where scalar access is governed by - * bit 28. A bunch of the instructions (float to integral) only exist - * in the vector form and are un-allocated for the scalar decode. Also - * in the scalar decode Q is always 1. - */ -static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) -{ - int fpop, opcode, a, u; - int rn, rd; - bool is_q; - bool is_scalar; - - int pass; - TCGv_i32 tcg_rmode = NULL; - TCGv_ptr tcg_fpstatus = NULL; - bool need_fpst = true; - int rmode = -1; - - if (!dc_isar_feature(aa64_fp16, s)) { - unallocated_encoding(s); - return; - } - - rd = extract32(insn, 0, 5); - rn = extract32(insn, 5, 5); - - a = extract32(insn, 23, 1); - u = extract32(insn, 29, 1); - is_scalar = extract32(insn, 28, 1); - is_q = extract32(insn, 30, 1); - - opcode = extract32(insn, 12, 5); - fpop = deposit32(opcode, 5, 1, a); - fpop = deposit32(fpop, 6, 1, u); - - switch (fpop) { - case 0x3d: /* FRECPE */ - case 0x3f: /* FRECPX */ - break; - case 0x7d: /* FRSQRTE */ - break; - default: - case 0x2f: /* FABS */ - case 0x6f: /* FNEG */ - case 0x7f: /* FSQRT (vector) */ - case 0x18: /* FRINTN */ - case 0x19: /* FRINTM */ - case 0x38: /* FRINTP */ - case 0x39: /* FRINTZ */ - case 0x58: /* FRINTA */ - case 0x59: /* FRINTX */ - case 0x79: /* FRINTI */ - case 0x1d: /* SCVTF */ - case 0x5d: /* UCVTF */ - case 0x1a: /* FCVTNS */ - case 0x1b: /* FCVTMS */ - case 0x1c: /* FCVTAS */ - case 0x3a: /* FCVTPS */ - case 0x3b: /* FCVTZS */ - case 0x5a: /* FCVTNU */ - case 0x5b: /* FCVTMU */ - case 0x5c: /* FCVTAU */ - case 0x7a: /* FCVTPU */ - case 0x7b: /* FCVTZU */ - case 0x2c: /* FCMGT (zero) */ - case 0x2d: /* FCMEQ (zero) */ - case 0x2e: /* FCMLT (zero) */ - case 0x6c: /* FCMGE (zero) */ - case 0x6d: /* FCMLE (zero) */ - unallocated_encoding(s); - return; - } - - - /* Check additional constraints for the scalar encoding */ - if (is_scalar) { - if (!is_q) { - unallocated_encoding(s); - return; - } - } - - if (!fp_access_check(s)) { - return; - } - - if (rmode >= 0 || need_fpst) { - tcg_fpstatus = fpstatus_ptr(FPST_FPCR_F16); - } - - if (rmode >= 0) { - tcg_rmode = gen_set_rmode(rmode, tcg_fpstatus); - } - - if (is_scalar) { - TCGv_i32 tcg_op = read_fp_hreg(s, rn); - TCGv_i32 tcg_res = tcg_temp_new_i32(); - - switch (fpop) { - case 0x3d: /* FRECPE */ - gen_helper_recpe_f16(tcg_res, tcg_op, tcg_fpstatus); - break; - case 0x3f: /* FRECPX */ - gen_helper_frecpx_f16(tcg_res, tcg_op, tcg_fpstatus); - break; - case 0x7d: /* FRSQRTE */ - gen_helper_rsqrte_f16(tcg_res, tcg_op, tcg_fpstatus); - break; - default: - case 0x1a: /* FCVTNS */ - case 0x1b: /* FCVTMS */ - case 0x1c: /* FCVTAS */ - case 0x3a: /* FCVTPS */ - case 0x3b: /* FCVTZS */ - case 0x5a: /* FCVTNU */ - case 0x5b: /* FCVTMU */ - case 0x5c: /* FCVTAU */ - case 0x7a: /* FCVTPU */ - case 0x7b: /* FCVTZU */ - g_assert_not_reached(); - } - - /* limit any sign extension going on */ - tcg_gen_andi_i32(tcg_res, tcg_res, 0xffff); - write_fp_sreg(s, rd, tcg_res); - } else { - for (pass = 0; pass < (is_q ? 8 : 4); pass++) { - TCGv_i32 tcg_op = tcg_temp_new_i32(); - TCGv_i32 tcg_res = tcg_temp_new_i32(); - - read_vec_element_i32(s, tcg_op, rn, pass, MO_16); - - switch (fpop) { - case 0x3d: /* FRECPE */ - gen_helper_recpe_f16(tcg_res, tcg_op, tcg_fpstatus); - break; - case 0x7d: /* FRSQRTE */ - gen_helper_rsqrte_f16(tcg_res, tcg_op, tcg_fpstatus); - break; - default: - case 0x2f: /* FABS */ - case 0x6f: /* FNEG */ - case 0x7f: /* FSQRT */ - case 0x18: /* FRINTN */ - case 0x19: /* FRINTM */ - case 0x38: /* FRINTP */ - case 0x39: /* FRINTZ */ - case 0x58: /* FRINTA */ - case 0x79: /* FRINTI */ - case 0x59: /* FRINTX */ - case 0x1a: /* FCVTNS */ - case 0x1b: /* FCVTMS */ - case 0x1c: /* FCVTAS */ - case 0x3a: /* FCVTPS */ - case 0x3b: /* FCVTZS */ - case 0x5a: /* FCVTNU */ - case 0x5b: /* FCVTMU */ - case 0x5c: /* FCVTAU */ - case 0x7a: /* FCVTPU */ - case 0x7b: /* FCVTZU */ - g_assert_not_reached(); - } - - write_vec_element_i32(s, tcg_res, rd, pass, MO_16); - } - - clear_vec_high(s, is_q, rd); - } - - if (tcg_rmode) { - gen_restore_rmode(tcg_rmode, tcg_fpstatus); - } -} - /* C3.6 Data processing - SIMD, inc Crypto * * As the decode gets a little complex we are using a table based @@ -10038,8 +9787,6 @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) static const AArch64DecodeTable data_proc_simd[] = { /* pattern , mask , fn */ { 0x0e200800, 0x9f3e0c00, disas_simd_two_reg_misc }, - { 0x5e200800, 0xdf3e0c00, disas_simd_scalar_two_reg_misc }, - { 0x0e780800, 0x8f7e0c00, disas_simd_two_reg_misc_fp16 }, { 0x00000000, 0x00000000, NULL } }; From 8710a43de1268948bfa2e5b3cc77504246dd6d20 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:34 -0600 Subject: [PATCH 67/85] target/arm: Introduce gen_gvec_urecpe, gen_gvec_ursqrte Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-68-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/helper.h | 3 +++ target/arm/tcg/gengvec.c | 16 ++++++++++++++++ target/arm/tcg/translate-neon.c | 4 ++-- target/arm/tcg/translate.h | 5 +++++ target/arm/tcg/vec_helper.c | 22 ++++++++++++++++++++++ 5 files changed, 48 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.h b/target/arm/helper.h index 1132a5cab6..9919b1367b 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -1121,6 +1121,9 @@ DEF_HELPER_FLAGS_4(gvec_uminp_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_uminp_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(gvec_uminp_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_urecpe_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(gvec_ursqrte_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "tcg/helper-a64.h" #include "tcg/helper-sve.h" diff --git a/target/arm/tcg/gengvec.c b/target/arm/tcg/gengvec.c index 01c9d5436d..01867f8ace 100644 --- a/target/arm/tcg/gengvec.c +++ b/target/arm/tcg/gengvec.c @@ -2711,3 +2711,19 @@ void gen_gvec_fneg(unsigned vece, uint32_t dofs, uint32_t aofs, uint64_t s_bit = 1ull << ((8 << vece) - 1); tcg_gen_gvec_xori(vece, dofs, aofs, s_bit, oprsz, maxsz); } + +void gen_gvec_urecpe(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + assert(vece == MO_32); + tcg_gen_gvec_2_ool(rd_ofs, rn_ofs, opr_sz, max_sz, 0, + gen_helper_gvec_urecpe_s); +} + +void gen_gvec_ursqrte(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz) +{ + assert(vece == MO_32); + tcg_gen_gvec_2_ool(rd_ofs, rn_ofs, opr_sz, max_sz, 0, + gen_helper_gvec_ursqrte_s); +} diff --git a/target/arm/tcg/translate-neon.c b/target/arm/tcg/translate-neon.c index f9ca889bec..c4fecb8fd6 100644 --- a/target/arm/tcg/translate-neon.c +++ b/target/arm/tcg/translate-neon.c @@ -3070,7 +3070,7 @@ static bool trans_VRECPE(DisasContext *s, arg_2misc *a) if (a->size != 2) { return false; } - return do_2misc(s, a, gen_helper_recpe_u32); + return do_2misc_vec(s, a, gen_gvec_urecpe); } static bool trans_VRSQRTE(DisasContext *s, arg_2misc *a) @@ -3078,7 +3078,7 @@ static bool trans_VRSQRTE(DisasContext *s, arg_2misc *a) if (a->size != 2) { return false; } - return do_2misc(s, a, gen_helper_rsqrte_u32); + return do_2misc_vec(s, a, gen_gvec_ursqrte); } #define WRAP_1OP_ENV_FN(WRAPNAME, FUNC) \ diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index b996de2c15..9b9abf1992 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -608,6 +608,11 @@ void gen_gvec_fabs(unsigned vece, uint32_t dofs, uint32_t aofs, void gen_gvec_fneg(unsigned vece, uint32_t dofs, uint32_t aofs, uint32_t oprsz, uint32_t maxsz); +void gen_gvec_urecpe(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz); +void gen_gvec_ursqrte(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, + uint32_t opr_sz, uint32_t max_sz); + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index ee84774517..768f745828 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -3099,3 +3099,25 @@ void HELPER(gvec_rbit_b)(void *vd, void *vn, uint32_t desc) } clear_tail(d, opr_sz, simd_maxsz(desc)); } + +void HELPER(gvec_urecpe_s)(void *vd, void *vn, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint32_t *d = vd, *n = vn; + + for (i = 0; i < opr_sz / 4; ++i) { + d[i] = helper_recpe_u32(n[i]); + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(gvec_ursqrte_s)(void *vd, void *vn, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc); + uint32_t *d = vd, *n = vn; + + for (i = 0; i < opr_sz / 4; ++i) { + d[i] = helper_rsqrte_u32(n[i]); + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} From 4280c9b5affeb6b9907f45fb452d6ffda03b68dd Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:35 -0600 Subject: [PATCH 68/85] target/arm: Convert URECPE and URSQRTE to decodetree Remove handle_2misc_reciprocal as these were the last insns decoded by that function. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-69-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 3 + target/arm/tcg/translate-a64.c | 139 ++------------------------------- 2 files changed, 8 insertions(+), 134 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index 9b3b09c3bb..f35d123821 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1863,6 +1863,9 @@ FRECPE_v 0.00 1110 1.1 00001 11011 0 ..... ..... @qrr_sd FRSQRTE_v 0.10 1110 111 11001 11011 0 ..... ..... @qrr_h FRSQRTE_v 0.10 1110 1.1 00001 11011 0 ..... ..... @qrr_sd +URECPE_v 0.00 1110 101 00001 11001 0 ..... ..... @qrr_s +URSQRTE_v 0.10 1110 101 00001 11001 0 ..... ..... @qrr_s + &fcvt_q rd rn esz q shift @fcvtq_h . q:1 . ...... 001 .... ...... rn:5 rd:5 \ &fcvt_q esz=1 shift=%fcvt_f_sh_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index 63cf25251b..fa3170da86 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -9163,6 +9163,8 @@ TRANS(CMLE0_v, do_gvec_fn2, a, gen_gvec_cle0) TRANS(CMEQ0_v, do_gvec_fn2, a, gen_gvec_ceq0) TRANS(REV16_v, do_gvec_fn2, a, gen_gvec_rev16) TRANS(REV32_v, do_gvec_fn2, a, gen_gvec_rev32) +TRANS(URECPE_v, do_gvec_fn2, a, gen_gvec_urecpe) +TRANS(URSQRTE_v, do_gvec_fn2, a, gen_gvec_ursqrte) static bool do_gvec_fn2_bhs(DisasContext *s, arg_qrr_e *a, GVecGen2Fn *fn) { @@ -9506,51 +9508,6 @@ static gen_helper_gvec_2_ptr * const f_frsqrte[] = { }; TRANS(FRSQRTE_v, do_gvec_op2_fpst, a->esz, a->q, a->rd, a->rn, 0, f_frsqrte) -static void handle_2misc_reciprocal(DisasContext *s, int opcode, - bool is_scalar, bool is_u, bool is_q, - int size, int rn, int rd) -{ - bool is_double = (size == 3); - - if (is_double) { - g_assert_not_reached(); - } else { - TCGv_i32 tcg_op = tcg_temp_new_i32(); - TCGv_i32 tcg_res = tcg_temp_new_i32(); - int pass, maxpasses; - - if (is_scalar) { - maxpasses = 1; - } else { - maxpasses = is_q ? 4 : 2; - } - - for (pass = 0; pass < maxpasses; pass++) { - read_vec_element_i32(s, tcg_op, rn, pass, MO_32); - - switch (opcode) { - case 0x3c: /* URECPE */ - gen_helper_recpe_u32(tcg_res, tcg_op); - break; - case 0x3d: /* FRECPE */ - case 0x3f: /* FRECPX */ - case 0x7d: /* FRSQRTE */ - default: - g_assert_not_reached(); - } - - if (is_scalar) { - write_fp_sreg(s, rd, tcg_res); - } else { - write_vec_element_i32(s, tcg_res, rd, pass, MO_32); - } - } - if (!is_scalar) { - clear_vec_high(s, is_q, rd); - } - } -} - static void handle_2misc_widening(DisasContext *s, int opcode, bool is_q, int size, int rn, int rd) { @@ -9609,10 +9566,6 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) bool is_q = extract32(insn, 30, 1); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - bool need_fpstatus = false; - int rmode = -1; - TCGv_i32 tcg_rmode; - TCGv_ptr tcg_fpstatus; switch (opcode) { case 0xc ... 0xf: @@ -9625,28 +9578,12 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) opcode |= (extract32(size, 1, 1) << 5) | (u << 6); size = is_double ? 3 : 2; switch (opcode) { - case 0x3c: /* URECPE */ - if (size == 3) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - handle_2misc_reciprocal(s, opcode, false, u, is_q, size, rn, rd); - return; case 0x17: /* FCVTL, FCVTL2 */ if (!fp_access_check(s)) { return; } handle_2misc_widening(s, opcode, is_q, size, rn, rd); return; - case 0x7c: /* URSQRTE */ - if (size == 3) { - unallocated_encoding(s); - return; - } - break; default: case 0x16: /* FCVTN, FCVTN2 */ case 0x36: /* BFCVTN, BFCVTN2 */ @@ -9684,6 +9621,8 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) case 0x6d: /* FCMLE (zero) */ case 0x3d: /* FRECPE */ case 0x7d: /* FRSQRTE */ + case 0x3c: /* URECPE */ + case 0x7c: /* URSQRTE */ unallocated_encoding(s); return; } @@ -9708,75 +9647,7 @@ static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - - if (!fp_access_check(s)) { - return; - } - - if (need_fpstatus || rmode >= 0) { - tcg_fpstatus = fpstatus_ptr(FPST_FPCR); - } else { - tcg_fpstatus = NULL; - } - if (rmode >= 0) { - tcg_rmode = gen_set_rmode(rmode, tcg_fpstatus); - } else { - tcg_rmode = NULL; - } - - { - int pass; - - assert(size == 2); - for (pass = 0; pass < (is_q ? 4 : 2); pass++) { - TCGv_i32 tcg_op = tcg_temp_new_i32(); - TCGv_i32 tcg_res = tcg_temp_new_i32(); - - read_vec_element_i32(s, tcg_op, rn, pass, MO_32); - - { - /* Special cases for 32 bit elements */ - switch (opcode) { - case 0x7c: /* URSQRTE */ - gen_helper_rsqrte_u32(tcg_res, tcg_op); - break; - default: - case 0x7: /* SQABS, SQNEG */ - case 0x2f: /* FABS */ - case 0x6f: /* FNEG */ - case 0x7f: /* FSQRT */ - case 0x18: /* FRINTN */ - case 0x19: /* FRINTM */ - case 0x38: /* FRINTP */ - case 0x39: /* FRINTZ */ - case 0x58: /* FRINTA */ - case 0x79: /* FRINTI */ - case 0x59: /* FRINTX */ - case 0x1e: /* FRINT32Z */ - case 0x5e: /* FRINT32X */ - case 0x1f: /* FRINT64Z */ - case 0x5f: /* FRINT64X */ - case 0x1a: /* FCVTNS */ - case 0x1b: /* FCVTMS */ - case 0x1c: /* FCVTAS */ - case 0x3a: /* FCVTPS */ - case 0x3b: /* FCVTZS */ - case 0x5a: /* FCVTNU */ - case 0x5b: /* FCVTMU */ - case 0x5c: /* FCVTAU */ - case 0x7a: /* FCVTPU */ - case 0x7b: /* FCVTZU */ - g_assert_not_reached(); - } - } - write_vec_element_i32(s, tcg_res, rd, pass, MO_32); - } - } - clear_vec_high(s, is_q, rd); - - if (tcg_rmode) { - gen_restore_rmode(tcg_rmode, tcg_fpstatus); - } + g_assert_not_reached(); } /* C3.6 Data processing - SIMD, inc Crypto From 53ac794af68bcd69d121e70592bc684b14407c71 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Wed, 11 Dec 2024 10:30:36 -0600 Subject: [PATCH 69/85] target/arm: Convert FCVTL to decodetree Remove lookup_disas_fn, handle_2misc_widening, disas_simd_two_reg_misc, disas_data_proc_simd, disas_data_proc_simd_fp, disas_a64_legacy, as this is the final insn to be converted. Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20241211163036.2297116-70-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- target/arm/tcg/a64.decode | 2 + target/arm/tcg/translate-a64.c | 202 +++------------------------------ 2 files changed, 18 insertions(+), 186 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index f35d123821..7aa10f5147 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -1866,6 +1866,8 @@ FRSQRTE_v 0.10 1110 1.1 00001 11011 0 ..... ..... @qrr_sd URECPE_v 0.00 1110 101 00001 11001 0 ..... ..... @qrr_s URSQRTE_v 0.10 1110 101 00001 11001 0 ..... ..... @qrr_s +FCVTL_v 0.00 1110 0.1 00001 01111 0 ..... ..... @qrr_sd + &fcvt_q rd rn esz q shift @fcvtq_h . q:1 . ...... 001 .... ...... rn:5 rd:5 \ &fcvt_q esz=1 shift=%fcvt_f_sh_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index fa3170da86..3e57b98c27 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -1465,31 +1465,6 @@ static inline void gen_check_sp_alignment(DisasContext *s) */ } -/* - * This provides a simple table based table lookup decoder. It is - * intended to be used when the relevant bits for decode are too - * awkwardly placed and switch/if based logic would be confusing and - * deeply nested. Since it's a linear search through the table, tables - * should be kept small. - * - * It returns the first handler where insn & mask == pattern, or - * NULL if there is no match. - * The table is terminated by an empty mask (i.e. 0) - */ -static inline AArch64DecodeFn *lookup_disas_fn(const AArch64DecodeTable *table, - uint32_t insn) -{ - const AArch64DecodeTable *tptr = table; - - while (tptr->mask) { - if ((insn & tptr->mask) == tptr->pattern) { - return tptr->disas_fn; - } - tptr++; - } - return NULL; -} - /* * The instruction disassembly implemented here matches * the instruction encoding classifications in chapter C4 @@ -9508,8 +9483,7 @@ static gen_helper_gvec_2_ptr * const f_frsqrte[] = { }; TRANS(FRSQRTE_v, do_gvec_op2_fpst, a->esz, a->q, a->rd, a->rn, 0, f_frsqrte) -static void handle_2misc_widening(DisasContext *s, int opcode, bool is_q, - int size, int rn, int rd) +static bool trans_FCVTL_v(DisasContext *s, arg_qrr_e *a) { /* Handle 2-reg-misc ops which are widening (so each size element * in the source becomes a 2*size element in the destination. @@ -9517,173 +9491,43 @@ static void handle_2misc_widening(DisasContext *s, int opcode, bool is_q, */ int pass; - if (size == 3) { + if (!fp_access_check(s)) { + return true; + } + + if (a->esz == MO_64) { /* 32 -> 64 bit fp conversion */ TCGv_i64 tcg_res[2]; - int srcelt = is_q ? 2 : 0; + TCGv_i32 tcg_op = tcg_temp_new_i32(); + int srcelt = a->q ? 2 : 0; for (pass = 0; pass < 2; pass++) { - TCGv_i32 tcg_op = tcg_temp_new_i32(); tcg_res[pass] = tcg_temp_new_i64(); - - read_vec_element_i32(s, tcg_op, rn, srcelt + pass, MO_32); + read_vec_element_i32(s, tcg_op, a->rn, srcelt + pass, MO_32); gen_helper_vfp_fcvtds(tcg_res[pass], tcg_op, tcg_env); } for (pass = 0; pass < 2; pass++) { - write_vec_element(s, tcg_res[pass], rd, pass, MO_64); + write_vec_element(s, tcg_res[pass], a->rd, pass, MO_64); } } else { /* 16 -> 32 bit fp conversion */ - int srcelt = is_q ? 4 : 0; + int srcelt = a->q ? 4 : 0; TCGv_i32 tcg_res[4]; TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); TCGv_i32 ahp = get_ahp_flag(); for (pass = 0; pass < 4; pass++) { tcg_res[pass] = tcg_temp_new_i32(); - - read_vec_element_i32(s, tcg_res[pass], rn, srcelt + pass, MO_16); + read_vec_element_i32(s, tcg_res[pass], a->rn, srcelt + pass, MO_16); gen_helper_vfp_fcvt_f16_to_f32(tcg_res[pass], tcg_res[pass], fpst, ahp); } for (pass = 0; pass < 4; pass++) { - write_vec_element_i32(s, tcg_res[pass], rd, pass, MO_32); + write_vec_element_i32(s, tcg_res[pass], a->rd, pass, MO_32); } } -} - -/* AdvSIMD two reg misc - * 31 30 29 28 24 23 22 21 17 16 12 11 10 9 5 4 0 - * +---+---+---+-----------+------+-----------+--------+-----+------+------+ - * | 0 | Q | U | 0 1 1 1 0 | size | 1 0 0 0 0 | opcode | 1 0 | Rn | Rd | - * +---+---+---+-----------+------+-----------+--------+-----+------+------+ - */ -static void disas_simd_two_reg_misc(DisasContext *s, uint32_t insn) -{ - int size = extract32(insn, 22, 2); - int opcode = extract32(insn, 12, 5); - bool u = extract32(insn, 29, 1); - bool is_q = extract32(insn, 30, 1); - int rn = extract32(insn, 5, 5); - int rd = extract32(insn, 0, 5); - - switch (opcode) { - case 0xc ... 0xf: - case 0x16 ... 0x1f: - { - /* Floating point: U, size[1] and opcode indicate operation; - * size[0] indicates single or double precision. - */ - int is_double = extract32(size, 0, 1); - opcode |= (extract32(size, 1, 1) << 5) | (u << 6); - size = is_double ? 3 : 2; - switch (opcode) { - case 0x17: /* FCVTL, FCVTL2 */ - if (!fp_access_check(s)) { - return; - } - handle_2misc_widening(s, opcode, is_q, size, rn, rd); - return; - default: - case 0x16: /* FCVTN, FCVTN2 */ - case 0x36: /* BFCVTN, BFCVTN2 */ - case 0x56: /* FCVTXN, FCVTXN2 */ - case 0x2f: /* FABS */ - case 0x6f: /* FNEG */ - case 0x7f: /* FSQRT */ - case 0x18: /* FRINTN */ - case 0x19: /* FRINTM */ - case 0x38: /* FRINTP */ - case 0x39: /* FRINTZ */ - case 0x59: /* FRINTX */ - case 0x79: /* FRINTI */ - case 0x58: /* FRINTA */ - case 0x1e: /* FRINT32Z */ - case 0x1f: /* FRINT64Z */ - case 0x5e: /* FRINT32X */ - case 0x5f: /* FRINT64X */ - case 0x1d: /* SCVTF */ - case 0x5d: /* UCVTF */ - case 0x1a: /* FCVTNS */ - case 0x1b: /* FCVTMS */ - case 0x3a: /* FCVTPS */ - case 0x3b: /* FCVTZS */ - case 0x5a: /* FCVTNU */ - case 0x5b: /* FCVTMU */ - case 0x7a: /* FCVTPU */ - case 0x7b: /* FCVTZU */ - case 0x5c: /* FCVTAU */ - case 0x1c: /* FCVTAS */ - case 0x2c: /* FCMGT (zero) */ - case 0x2d: /* FCMEQ (zero) */ - case 0x2e: /* FCMLT (zero) */ - case 0x6c: /* FCMGE (zero) */ - case 0x6d: /* FCMLE (zero) */ - case 0x3d: /* FRECPE */ - case 0x7d: /* FRSQRTE */ - case 0x3c: /* URECPE */ - case 0x7c: /* URSQRTE */ - unallocated_encoding(s); - return; - } - break; - } - default: - case 0x0: /* REV64, REV32 */ - case 0x1: /* REV16 */ - case 0x2: /* SADDLP, UADDLP */ - case 0x3: /* SUQADD, USQADD */ - case 0x4: /* CLS, CLZ */ - case 0x5: /* CNT, NOT, RBIT */ - case 0x6: /* SADALP, UADALP */ - case 0x7: /* SQABS, SQNEG */ - case 0x8: /* CMGT, CMGE */ - case 0x9: /* CMEQ, CMLE */ - case 0xa: /* CMLT */ - case 0xb: /* ABS, NEG */ - case 0x12: /* XTN, XTN2, SQXTUN, SQXTUN2 */ - case 0x13: /* SHLL, SHLL2 */ - case 0x14: /* SQXTN, SQXTN2, UQXTN, UQXTN2 */ - unallocated_encoding(s); - return; - } - g_assert_not_reached(); -} - -/* C3.6 Data processing - SIMD, inc Crypto - * - * As the decode gets a little complex we are using a table based - * approach for this part of the decode. - */ -static const AArch64DecodeTable data_proc_simd[] = { - /* pattern , mask , fn */ - { 0x0e200800, 0x9f3e0c00, disas_simd_two_reg_misc }, - { 0x00000000, 0x00000000, NULL } -}; - -static void disas_data_proc_simd(DisasContext *s, uint32_t insn) -{ - /* Note that this is called with all non-FP cases from - * table C3-6 so it must UNDEF for entries not specifically - * allocated to instructions in that table. - */ - AArch64DecodeFn *fn = lookup_disas_fn(&data_proc_simd[0], insn); - if (fn) { - fn(s, insn); - } else { - unallocated_encoding(s); - } -} - -/* C3.6 Data processing - SIMD and floating point */ -static void disas_data_proc_simd_fp(DisasContext *s, uint32_t insn) -{ - if (extract32(insn, 28, 1) == 1 && extract32(insn, 30, 1) == 0) { - unallocated_encoding(s); /* in decodetree */ - } else { - /* SIMD, including crypto */ - disas_data_proc_simd(s, insn); - } + clear_vec_high(s, true, a->rd); + return true; } static bool trans_OK(DisasContext *s, arg_OK *a) @@ -9749,20 +9593,6 @@ static bool btype_destination_ok(uint32_t insn, bool bt, int btype) return false; } -/* C3.1 A64 instruction index by encoding */ -static void disas_a64_legacy(DisasContext *s, uint32_t insn) -{ - switch (extract32(insn, 25, 4)) { - case 0x7: - case 0xf: /* Data processing - SIMD and floating point */ - disas_data_proc_simd_fp(s, insn); - break; - default: - unallocated_encoding(s); - break; - } -} - static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cpu) { @@ -9965,7 +9795,7 @@ static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) if (!disas_a64(s, insn) && !disas_sme(s, insn) && !disas_sve(s, insn)) { - disas_a64_legacy(s, insn); + unallocated_encoding(s); } /* From c66be53ce7460d061cbd9061a85ecfb219515901 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Thu, 5 Dec 2024 21:14:28 -0600 Subject: [PATCH 70/85] target/arm: Use float_round_to_odd in helper_fcvtx_f64_to_f32 Softfloat has native support for round-to-odd. Use it. Signed-off-by: Richard Henderson Message-id: 20241206031428.78634-1-richard.henderson@linaro.org Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- target/arm/tcg/helper-a64.c | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index 28de7468cd..fb6fe0fcaa 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -408,23 +408,13 @@ float64 HELPER(frecpx_f64)(float64 a, void *fpstp) float32 HELPER(fcvtx_f64_to_f32)(float64 a, CPUARMState *env) { - /* Von Neumann rounding is implemented by using round-to-zero - * and then setting the LSB of the result if Inexact was raised. - */ float32 r; float_status *fpst = &env->vfp.fp_status; - float_status tstat = *fpst; - int exflags; + int old = get_float_rounding_mode(fpst); - set_float_rounding_mode(float_round_to_zero, &tstat); - set_float_exception_flags(0, &tstat); - r = float64_to_float32(a, &tstat); - exflags = get_float_exception_flags(&tstat); - if (exflags & float_flag_inexact) { - r = make_float32(float32_val(r) | 1); - } - exflags |= get_float_exception_flags(fpst); - set_float_exception_flags(exflags, fpst); + set_float_rounding_mode(float_round_to_odd, fpst); + r = float64_to_float32(a, fpst); + set_float_rounding_mode(old, fpst); return r; } From 3297e31392890842db99b572c08c836cbcab9011 Mon Sep 17 00:00:00 2001 From: Pierrick Bouvier Date: Fri, 6 Dec 2024 11:22:51 -0800 Subject: [PATCH 71/85] docs/system/arm/orangepi: update links www.orangepi.org does not support https, it's expected to stick to http. Reviewed-by: Niek Linnenbank Signed-off-by: Pierrick Bouvier Message-id: 20241206192254.3889131-2-pierrick.bouvier@linaro.org Signed-off-by: Peter Maydell --- docs/system/arm/orangepi.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/system/arm/orangepi.rst b/docs/system/arm/orangepi.rst index 9afa54213b..db87e81fec 100644 --- a/docs/system/arm/orangepi.rst +++ b/docs/system/arm/orangepi.rst @@ -119,7 +119,7 @@ Orange Pi PC images Note that the mainline kernel does not have a root filesystem. You may provide it with an official Orange Pi PC image from the official website: - http://www.orangepi.org/downloadresources/ + http://www.orangepi.org/html/serviceAndSupport/index.html Another possibility is to run an Armbian image for Orange Pi PC which can be downloaded from: @@ -213,7 +213,7 @@ including the Orange Pi PC. NetBSD 9.0 is known to work best for the Orange Pi P board and provides a fully working system with serial console, networking and storage. For the Orange Pi PC machine, get the 'evbarm-earmv7hf' based image from: - https://cdn.netbsd.org/pub/NetBSD/NetBSD-9.0/evbarm-earmv7hf/binary/gzimg/armv7.img.gz + https://archive.netbsd.org/pub/NetBSD-archive/NetBSD-9.0/evbarm-earmv7hf/binary/gzimg/armv7.img.gz The image requires manually installing U-Boot in the image. Build U-Boot with the orangepi_pc_defconfig configuration as described in the previous section. From 3314731a7f5e96e7c4649b8a5a8253887a2242a7 Mon Sep 17 00:00:00 2001 From: Pierrick Bouvier Date: Fri, 6 Dec 2024 11:22:52 -0800 Subject: [PATCH 72/85] docs/system/arm/fby35: document execute-in-place property MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Reviewed-by: Cédric Le Goater Signed-off-by: Pierrick Bouvier Message-id: 20241206192254.3889131-3-pierrick.bouvier@linaro.org Signed-off-by: Peter Maydell --- docs/system/arm/fby35.rst | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/docs/system/arm/fby35.rst b/docs/system/arm/fby35.rst index bf6da6baa2..e19274e75c 100644 --- a/docs/system/arm/fby35.rst +++ b/docs/system/arm/fby35.rst @@ -45,3 +45,8 @@ process starts. $ screen /dev/tty0 # In a separate TMUX pane, terminal window, etc. $ screen /dev/tty1 $ (qemu) c # Start the boot process once screen is setup. + +This machine model supports emulation of the boot from the CE0 flash device by +setting option ``execute-in-place``. When using this option, the CPU fetches +instructions to execute by reading CE0 and not from a preloaded ROM +initialized at machine init time. As a result, execution will be slower. From 332a04b63a6c17ea38a091d1593ec78f3a8a063f Mon Sep 17 00:00:00 2001 From: Pierrick Bouvier Date: Fri, 6 Dec 2024 11:22:53 -0800 Subject: [PATCH 73/85] docs/system/arm/xlnx-versal-virt: document ospi-flash property Signed-off-by: Pierrick Bouvier Message-id: 20241206192254.3889131-4-pierrick.bouvier@linaro.org Signed-off-by: Peter Maydell Reviewed-by: Peter Maydell --- docs/system/arm/xlnx-versal-virt.rst | 3 +++ 1 file changed, 3 insertions(+) diff --git a/docs/system/arm/xlnx-versal-virt.rst b/docs/system/arm/xlnx-versal-virt.rst index 0bafc76469..c5f35f28e4 100644 --- a/docs/system/arm/xlnx-versal-virt.rst +++ b/docs/system/arm/xlnx-versal-virt.rst @@ -178,6 +178,9 @@ Run the following at the U-Boot prompt: fdt set /chosen/dom0 reg <0x00000000 0x40000000 0x0 0x03100000> booti 30000000 - 20000000 +It's possible to change the OSPI flash model emulated by using the machine model +option ``ospi-flash``. + BBRAM File Backend """""""""""""""""" BBRAM can have an optional file backend, which must be a seekable From e30e6fdcc59c980e83514ba731394a85428a9405 Mon Sep 17 00:00:00 2001 From: Pierrick Bouvier Date: Fri, 6 Dec 2024 11:22:54 -0800 Subject: [PATCH 74/85] docs/system/arm/virt: document missing properties Signed-off-by: Pierrick Bouvier Message-id: 20241206192254.3889131-5-pierrick.bouvier@linaro.org Signed-off-by: Peter Maydell Reviewed-by: Peter Maydell --- docs/system/arm/virt.rst | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst index e67e7f0f7c..f87adeb444 100644 --- a/docs/system/arm/virt.rst +++ b/docs/system/arm/virt.rst @@ -167,10 +167,18 @@ iommu ``smmuv3`` Create an SMMUv3 +default-bus-bypass-iommu + Set ``on``/``off`` to enable/disable `bypass_iommu + `_ + for default root bus. + ras Set ``on``/``off`` to enable/disable reporting host memory errors to a guest using ACPI and guest external abort exceptions. The default is off. +acpi + Set ``on``/``off``/``auto`` to enable/disable ACPI. + dtb-randomness Set ``on``/``off`` to pass random seeds via the guest DTB rng-seed and kaslr-seed nodes (in both "/chosen" and @@ -184,6 +192,14 @@ dtb-randomness dtb-kaslr-seed A deprecated synonym for dtb-randomness. +x-oem-id + Set string (up to 6 bytes) to override the default value of field OEMID in ACPI + table header. + +x-oem-table-id + Set string (up to 8 bytes) to override the default value of field OEM Table ID + in ACPI table header. + Linux guest kernel configuration """""""""""""""""""""""""""""""" From 08e199bbc6a4a9b9d929a472e14cc47116811afb Mon Sep 17 00:00:00 2001 From: Brian Cain Date: Mon, 9 Dec 2024 10:12:42 -0800 Subject: [PATCH 75/85] MAINTAINERS: correct my email address Mea culpa, I don't know how I got this wrong in 2dfe93699c. Still getting used to the new address, I suppose. Somehow I got it right in the mailmap, though. Signed-off-by: Brian Cain Message-id: 20241209181242.1434231-1-brian.cain@oss.qualcomm.com Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 7c1ab51b2d..822f34344b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -226,7 +226,7 @@ F: target/avr/ F: tests/functional/test_avr_mega2560.py Hexagon TCG CPUs -M: Brian Cain +M: Brian Cain S: Supported F: target/hexagon/ X: target/hexagon/idef-parser/ From 1e32ee23cdc5405a5b575286bbfa705d78da410c Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Tue, 10 Dec 2024 16:04:43 +0000 Subject: [PATCH 76/85] target/arm: Move some TLBI insns to their own source file target/arm/helper.c is very large and unwieldy. One subset of code that we can pull out into its own file is the cpreg arrays and corresponding functions for the TLBI instructions. Because these are instructions they are only relevant for TCG and we can make the new file only be built for CONFIG_TCG. In this commit we move the AArch32 instructions from: not_v7_cp_reginfo[] v7_cp_reginfo[] v7mp_cp_reginfo[] v8_cp_reginfo[] into a new file target/arm/tcg/tlb-insns.c. A few small functions are used both by functions we haven't yet moved across and by functions we have already moved. We temporarily make these global with a prototype in cpregs.h; when the move of all TLBI insns is complete these will return to being file-local. For CONFIG_TCG, this is just moving code around. For a KVM only build, these cpregs will no longer be added to the cpregs hashtable for the CPU. However this should not be a behaviour change, because: * we never try to migration sync or otherwise include ARM_CP_NO_RAW cpregs * for migration we treat the kernel's list of system registers as the authoritative one, so these TLBI insns were never in it anyway The no-tcg stub of define_tlb_insn_regs() therefore does nothing. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson Message-id: 20241210160452.2427965-2-peter.maydell@linaro.org --- target/arm/cpregs.h | 14 +++ target/arm/helper.c | 231 ++-------------------------------- target/arm/internals.h | 3 + target/arm/tcg-stubs.c | 5 + target/arm/tcg/meson.build | 1 + target/arm/tcg/tlb-insns.c | 246 +++++++++++++++++++++++++++++++++++++ 6 files changed, 280 insertions(+), 220 deletions(-) create mode 100644 target/arm/tcg/tlb-insns.c diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index cc7c54378f..26c27dc5cb 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -1134,4 +1134,18 @@ static inline bool arm_cpreg_traps_in_nv(const ARMCPRegInfo *ri) return ri->opc1 == 4 || ri->opc1 == 5; } +/* + * Temporary declarations of functions until the move to tlb_insn_helper.c + * is complete and we can make the functions static again + */ +CPAccessResult access_ttlb(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread); +CPAccessResult access_ttlbis(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread); +bool tlb_force_broadcast(CPUARMState *env); +void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value); +void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value); + #endif /* TARGET_ARM_CPREGS_H */ diff --git a/target/arm/helper.c b/target/arm/helper.c index f38eb054c0..6a9bf70f18 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -366,8 +366,8 @@ static CPAccessResult access_tacr(CPUARMState *env, const ARMCPRegInfo *ri, } /* Check for traps from EL1 due to HCR_EL2.TTLB. */ -static CPAccessResult access_ttlb(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread) +CPAccessResult access_ttlb(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread) { if (arm_current_el(env) == 1 && (arm_hcr_el2_eff(env) & HCR_TTLB)) { return CP_ACCESS_TRAP_EL2; @@ -376,8 +376,8 @@ static CPAccessResult access_ttlb(CPUARMState *env, const ARMCPRegInfo *ri, } /* Check for traps from EL1 due to HCR_EL2.TTLB or TTLBIS. */ -static CPAccessResult access_ttlbis(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread) +CPAccessResult access_ttlbis(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread) { if (arm_current_el(env) == 1 && (arm_hcr_el2_eff(env) & (HCR_TTLB | HCR_TTLBIS))) { @@ -455,104 +455,16 @@ static int alle1_tlbmask(CPUARMState *env) ARMMMUIdxBit_Stage2_S); } - -/* IS variants of TLB operations must affect all cores */ -static void tlbiall_is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - - tlb_flush_all_cpus_synced(cs); -} - -static void tlbiasid_is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - - tlb_flush_all_cpus_synced(cs); -} - -static void tlbimva_is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - - tlb_flush_page_all_cpus_synced(cs, value & TARGET_PAGE_MASK); -} - -static void tlbimvaa_is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - - tlb_flush_page_all_cpus_synced(cs, value & TARGET_PAGE_MASK); -} - /* * Non-IS variants of TLB operations are upgraded to * IS versions if we are at EL1 and HCR_EL2.FB is effectively set to * force broadcast of these operations. */ -static bool tlb_force_broadcast(CPUARMState *env) +bool tlb_force_broadcast(CPUARMState *env) { return arm_current_el(env) == 1 && (arm_hcr_el2_eff(env) & HCR_FB); } -static void tlbiall_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate all (TLBIALL) */ - CPUState *cs = env_cpu(env); - - if (tlb_force_broadcast(env)) { - tlb_flush_all_cpus_synced(cs); - } else { - tlb_flush(cs); - } -} - -static void tlbimva_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate single TLB entry by MVA and ASID (TLBIMVA) */ - CPUState *cs = env_cpu(env); - - value &= TARGET_PAGE_MASK; - if (tlb_force_broadcast(env)) { - tlb_flush_page_all_cpus_synced(cs, value); - } else { - tlb_flush_page(cs, value); - } -} - -static void tlbiasid_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate by ASID (TLBIASID) */ - CPUState *cs = env_cpu(env); - - if (tlb_force_broadcast(env)) { - tlb_flush_all_cpus_synced(cs); - } else { - tlb_flush(cs); - } -} - -static void tlbimvaa_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate single entry by MVA, all ASIDs (TLBIMVAA) */ - CPUState *cs = env_cpu(env); - - value &= TARGET_PAGE_MASK; - if (tlb_force_broadcast(env)) { - tlb_flush_page_all_cpus_synced(cs, value); - } else { - tlb_flush_page(cs, value); - } -} - static void tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -586,8 +498,8 @@ static void tlbiall_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_E2); } -static void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { CPUState *cs = env_cpu(env); uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12); @@ -595,8 +507,8 @@ static void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_E2); } -static void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { CPUState *cs = env_cpu(env); uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12); @@ -605,24 +517,6 @@ static void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, ARMMMUIdxBit_E2); } -static void tlbiipas2_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - uint64_t pageaddr = (value & MAKE_64BIT_MASK(0, 28)) << 12; - - tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_Stage2); -} - -static void tlbiipas2is_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - uint64_t pageaddr = (value & MAKE_64BIT_MASK(0, 28)) << 12; - - tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, ARMMMUIdxBit_Stage2); -} - static const ARMCPRegInfo cp_reginfo[] = { /* * Define the secure and non-secure FCSE identifier CP registers @@ -732,22 +626,6 @@ static const ARMCPRegInfo not_v7_cp_reginfo[] = { */ { .name = "DBGDIDR", .cp = 14, .crn = 0, .crm = 0, .opc1 = 0, .opc2 = 0, .access = PL0_R, .type = ARM_CP_CONST, .resetvalue = 0 }, - /* - * MMU TLB control. Note that the wildcarding means we cover not just - * the unified TLB ops but also the dside/iside/inner-shareable variants. - */ - { .name = "TLBIALL", .cp = 15, .crn = 8, .crm = CP_ANY, - .opc1 = CP_ANY, .opc2 = 0, .access = PL1_W, .writefn = tlbiall_write, - .type = ARM_CP_NO_RAW }, - { .name = "TLBIMVA", .cp = 15, .crn = 8, .crm = CP_ANY, - .opc1 = CP_ANY, .opc2 = 1, .access = PL1_W, .writefn = tlbimva_write, - .type = ARM_CP_NO_RAW }, - { .name = "TLBIASID", .cp = 15, .crn = 8, .crm = CP_ANY, - .opc1 = CP_ANY, .opc2 = 2, .access = PL1_W, .writefn = tlbiasid_write, - .type = ARM_CP_NO_RAW }, - { .name = "TLBIMVAA", .cp = 15, .crn = 8, .crm = CP_ANY, - .opc1 = CP_ANY, .opc2 = 3, .access = PL1_W, .writefn = tlbimvaa_write, - .type = ARM_CP_NO_RAW }, { .name = "PRRR", .cp = 15, .crn = 10, .crm = 2, .opc1 = 0, .opc2 = 0, .access = PL1_RW, .type = ARM_CP_NOP }, { .name = "NMRR", .cp = 15, .crn = 10, .crm = 2, @@ -2331,55 +2209,6 @@ static const ARMCPRegInfo v7_cp_reginfo[] = { .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 1, .opc2 = 0, .fgt = FGT_ISR_EL1, .type = ARM_CP_NO_RAW, .access = PL1_R, .readfn = isr_read }, - /* 32 bit ITLB invalidates */ - { .name = "ITLBIALL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 0, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, - .writefn = tlbiall_write }, - { .name = "ITLBIMVA", .cp = 15, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 1, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, - .writefn = tlbimva_write }, - { .name = "ITLBIASID", .cp = 15, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 2, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, - .writefn = tlbiasid_write }, - /* 32 bit DTLB invalidates */ - { .name = "DTLBIALL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 0, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, - .writefn = tlbiall_write }, - { .name = "DTLBIMVA", .cp = 15, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 1, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, - .writefn = tlbimva_write }, - { .name = "DTLBIASID", .cp = 15, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 2, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, - .writefn = tlbiasid_write }, - /* 32 bit TLB invalidates */ - { .name = "TLBIALL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 0, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, - .writefn = tlbiall_write }, - { .name = "TLBIMVA", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 1, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, - .writefn = tlbimva_write }, - { .name = "TLBIASID", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 2, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, - .writefn = tlbiasid_write }, - { .name = "TLBIMVAA", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 3, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, - .writefn = tlbimvaa_write }, -}; - -static const ARMCPRegInfo v7mp_cp_reginfo[] = { - /* 32 bit TLB invalidates, Inner Shareable */ - { .name = "TLBIALLIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 0, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlbis, - .writefn = tlbiall_is_write }, - { .name = "TLBIMVAIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 1, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlbis, - .writefn = tlbimva_is_write }, - { .name = "TLBIASIDIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 2, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlbis, - .writefn = tlbiasid_is_write }, - { .name = "TLBIMVAAIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 3, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlbis, - .writefn = tlbimvaa_is_write }, }; static const ARMCPRegInfo pmovsset_cp_reginfo[] = { @@ -5833,42 +5662,6 @@ static const ARMCPRegInfo v8_cp_reginfo[] = { .fieldoffset = offsetof(CPUARMState, cp15.par_el[1]), .writefn = par_write }, #endif - /* TLB invalidate last level of translation table walk */ - { .name = "TLBIMVALIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 5, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlbis, - .writefn = tlbimva_is_write }, - { .name = "TLBIMVAALIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 7, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlbis, - .writefn = tlbimvaa_is_write }, - { .name = "TLBIMVAL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 5, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, - .writefn = tlbimva_write }, - { .name = "TLBIMVAAL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 7, - .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, - .writefn = tlbimvaa_write }, - { .name = "TLBIMVALH", .cp = 15, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 5, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbimva_hyp_write }, - { .name = "TLBIMVALHIS", - .cp = 15, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 5, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbimva_hyp_is_write }, - { .name = "TLBIIPAS2", - .cp = 15, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 1, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbiipas2_hyp_write }, - { .name = "TLBIIPAS2IS", - .cp = 15, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 1, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbiipas2is_hyp_write }, - { .name = "TLBIIPAS2L", - .cp = 15, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 5, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbiipas2_hyp_write }, - { .name = "TLBIIPAS2LIS", - .cp = 15, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 5, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbiipas2is_hyp_write }, /* 32 bit cache operations */ { .name = "ICIALLUIS", .cp = 15, .opc1 = 0, .crn = 7, .crm = 1, .opc2 = 0, .type = ARM_CP_NOP, .access = PL1_W, .accessfn = access_ticab }, @@ -8734,6 +8527,8 @@ void register_cp_regs_for_features(ARMCPU *cpu) define_arm_cp_regs(cpu, not_v8_cp_reginfo); } + define_tlb_insn_regs(cpu); + if (arm_feature(env, ARM_FEATURE_V6)) { /* The ID registers all have impdef reset values */ ARMCPRegInfo v6_idregs[] = { @@ -8839,10 +8634,6 @@ void register_cp_regs_for_features(ARMCPU *cpu) if (arm_feature(env, ARM_FEATURE_V6K)) { define_arm_cp_regs(cpu, v6k_cp_reginfo); } - if (arm_feature(env, ARM_FEATURE_V7MP) && - !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); } diff --git a/target/arm/internals.h b/target/arm/internals.h index e37f459af3..2adedb9477 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -1727,6 +1727,9 @@ static inline uint64_t pauth_ptr_mask(ARMVAParameters param) /* Add the cpreg definitions for debug related system registers */ void define_debug_regs(ARMCPU *cpu); +/* Add the cpreg definitions for TLBI instructions */ +void define_tlb_insn_regs(ARMCPU *cpu); + /* Effective value of MDCR_EL2 */ static inline uint64_t arm_mdcr_el2_eff(CPUARMState *env) { diff --git a/target/arm/tcg-stubs.c b/target/arm/tcg-stubs.c index 152b172e24..f3f45d54f2 100644 --- a/target/arm/tcg-stubs.c +++ b/target/arm/tcg-stubs.c @@ -25,3 +25,8 @@ void raise_exception_ra(CPUARMState *env, uint32_t excp, uint32_t syndrome, void assert_hflags_rebuild_correctly(CPUARMState *env) { } + +/* TLBI insns are only used by TCG, so we don't need to do anything for KVM */ +void define_tlb_insn_regs(ARMCPU *cpu) +{ +} diff --git a/target/arm/tcg/meson.build b/target/arm/tcg/meson.build index 508932a249..09238989c5 100644 --- a/target/arm/tcg/meson.build +++ b/target/arm/tcg/meson.build @@ -39,6 +39,7 @@ arm_ss.add(files( 'op_helper.c', 'tlb_helper.c', 'vec_helper.c', + 'tlb-insns.c', )) arm_ss.add(when: 'TARGET_AARCH64', if_true: files( diff --git a/target/arm/tcg/tlb-insns.c b/target/arm/tcg/tlb-insns.c new file mode 100644 index 0000000000..cdf23352d7 --- /dev/null +++ b/target/arm/tcg/tlb-insns.c @@ -0,0 +1,246 @@ +/* + * Helpers for TLBI insns + * + * This code is licensed under the GNU GPL v2 or later. + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ +#include "qemu/osdep.h" +#include "exec/exec-all.h" +#include "cpu.h" +#include "internals.h" +#include "cpu-features.h" +#include "cpregs.h" + +/* IS variants of TLB operations must affect all cores */ +static void tlbiall_is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + + tlb_flush_all_cpus_synced(cs); +} + +static void tlbiasid_is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + + tlb_flush_all_cpus_synced(cs); +} + +static void tlbimva_is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + + tlb_flush_page_all_cpus_synced(cs, value & TARGET_PAGE_MASK); +} + +static void tlbimvaa_is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + + tlb_flush_page_all_cpus_synced(cs, value & TARGET_PAGE_MASK); +} + +static void tlbiall_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Invalidate all (TLBIALL) */ + CPUState *cs = env_cpu(env); + + if (tlb_force_broadcast(env)) { + tlb_flush_all_cpus_synced(cs); + } else { + tlb_flush(cs); + } +} + +static void tlbimva_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Invalidate single TLB entry by MVA and ASID (TLBIMVA) */ + CPUState *cs = env_cpu(env); + + value &= TARGET_PAGE_MASK; + if (tlb_force_broadcast(env)) { + tlb_flush_page_all_cpus_synced(cs, value); + } else { + tlb_flush_page(cs, value); + } +} + +static void tlbiasid_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Invalidate by ASID (TLBIASID) */ + CPUState *cs = env_cpu(env); + + if (tlb_force_broadcast(env)) { + tlb_flush_all_cpus_synced(cs); + } else { + tlb_flush(cs); + } +} + +static void tlbimvaa_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Invalidate single entry by MVA, all ASIDs (TLBIMVAA) */ + CPUState *cs = env_cpu(env); + + value &= TARGET_PAGE_MASK; + if (tlb_force_broadcast(env)) { + tlb_flush_page_all_cpus_synced(cs, value); + } else { + tlb_flush_page(cs, value); + } +} + +static void tlbiipas2_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + uint64_t pageaddr = (value & MAKE_64BIT_MASK(0, 28)) << 12; + + tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_Stage2); +} + +static void tlbiipas2is_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + uint64_t pageaddr = (value & MAKE_64BIT_MASK(0, 28)) << 12; + + tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, ARMMMUIdxBit_Stage2); +} + +static const ARMCPRegInfo tlbi_not_v7_cp_reginfo[] = { + /* + * MMU TLB control. Note that the wildcarding means we cover not just + * the unified TLB ops but also the dside/iside/inner-shareable variants. + */ + { .name = "TLBIALL", .cp = 15, .crn = 8, .crm = CP_ANY, + .opc1 = CP_ANY, .opc2 = 0, .access = PL1_W, .writefn = tlbiall_write, + .type = ARM_CP_NO_RAW }, + { .name = "TLBIMVA", .cp = 15, .crn = 8, .crm = CP_ANY, + .opc1 = CP_ANY, .opc2 = 1, .access = PL1_W, .writefn = tlbimva_write, + .type = ARM_CP_NO_RAW }, + { .name = "TLBIASID", .cp = 15, .crn = 8, .crm = CP_ANY, + .opc1 = CP_ANY, .opc2 = 2, .access = PL1_W, .writefn = tlbiasid_write, + .type = ARM_CP_NO_RAW }, + { .name = "TLBIMVAA", .cp = 15, .crn = 8, .crm = CP_ANY, + .opc1 = CP_ANY, .opc2 = 3, .access = PL1_W, .writefn = tlbimvaa_write, + .type = ARM_CP_NO_RAW }, +}; + +static const ARMCPRegInfo tlbi_v7_cp_reginfo[] = { + /* 32 bit ITLB invalidates */ + { .name = "ITLBIALL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 0, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, + .writefn = tlbiall_write }, + { .name = "ITLBIMVA", .cp = 15, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 1, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, + .writefn = tlbimva_write }, + { .name = "ITLBIASID", .cp = 15, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 2, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, + .writefn = tlbiasid_write }, + /* 32 bit DTLB invalidates */ + { .name = "DTLBIALL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 0, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, + .writefn = tlbiall_write }, + { .name = "DTLBIMVA", .cp = 15, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 1, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, + .writefn = tlbimva_write }, + { .name = "DTLBIASID", .cp = 15, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 2, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, + .writefn = tlbiasid_write }, + /* 32 bit TLB invalidates */ + { .name = "TLBIALL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 0, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, + .writefn = tlbiall_write }, + { .name = "TLBIMVA", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 1, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, + .writefn = tlbimva_write }, + { .name = "TLBIASID", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 2, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, + .writefn = tlbiasid_write }, + { .name = "TLBIMVAA", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 3, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, + .writefn = tlbimvaa_write }, +}; + +static const ARMCPRegInfo tlbi_v7mp_cp_reginfo[] = { + /* 32 bit TLB invalidates, Inner Shareable */ + { .name = "TLBIALLIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 0, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlbis, + .writefn = tlbiall_is_write }, + { .name = "TLBIMVAIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 1, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlbis, + .writefn = tlbimva_is_write }, + { .name = "TLBIASIDIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 2, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlbis, + .writefn = tlbiasid_is_write }, + { .name = "TLBIMVAAIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 3, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlbis, + .writefn = tlbimvaa_is_write }, +}; + +static const ARMCPRegInfo tlbi_v8_cp_reginfo[] = { + /* AArch32 TLB invalidate last level of translation table walk */ + { .name = "TLBIMVALIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 5, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlbis, + .writefn = tlbimva_is_write }, + { .name = "TLBIMVAALIS", .cp = 15, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 7, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlbis, + .writefn = tlbimvaa_is_write }, + { .name = "TLBIMVAL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 5, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, + .writefn = tlbimva_write }, + { .name = "TLBIMVAAL", .cp = 15, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 7, + .type = ARM_CP_NO_RAW, .access = PL1_W, .accessfn = access_ttlb, + .writefn = tlbimvaa_write }, + { .name = "TLBIMVALH", .cp = 15, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 5, + .type = ARM_CP_NO_RAW, .access = PL2_W, + .writefn = tlbimva_hyp_write }, + { .name = "TLBIMVALHIS", + .cp = 15, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 5, + .type = ARM_CP_NO_RAW, .access = PL2_W, + .writefn = tlbimva_hyp_is_write }, + { .name = "TLBIIPAS2", + .cp = 15, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 1, + .type = ARM_CP_NO_RAW, .access = PL2_W, + .writefn = tlbiipas2_hyp_write }, + { .name = "TLBIIPAS2IS", + .cp = 15, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 1, + .type = ARM_CP_NO_RAW, .access = PL2_W, + .writefn = tlbiipas2is_hyp_write }, + { .name = "TLBIIPAS2L", + .cp = 15, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 5, + .type = ARM_CP_NO_RAW, .access = PL2_W, + .writefn = tlbiipas2_hyp_write }, + { .name = "TLBIIPAS2LIS", + .cp = 15, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 5, + .type = ARM_CP_NO_RAW, .access = PL2_W, + .writefn = tlbiipas2is_hyp_write }, +}; + +void define_tlb_insn_regs(ARMCPU *cpu) +{ + CPUARMState *env = &cpu->env; + + if (!arm_feature(env, ARM_FEATURE_V7)) { + define_arm_cp_regs(cpu, tlbi_not_v7_cp_reginfo); + } else { + define_arm_cp_regs(cpu, tlbi_v7_cp_reginfo); + } + if (arm_feature(env, ARM_FEATURE_V7MP) && + !arm_feature(env, ARM_FEATURE_PMSA)) { + define_arm_cp_regs(cpu, tlbi_v7mp_cp_reginfo); + } + if (arm_feature(env, ARM_FEATURE_V8)) { + define_arm_cp_regs(cpu, tlbi_v8_cp_reginfo); + } +} From d6b6da1fc84173d1d8e8777c487c21ffeab5f5ce Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Tue, 10 Dec 2024 16:04:44 +0000 Subject: [PATCH 77/85] target/arm: Move TLBI insns for AArch32 EL2 to tlbi_insn_helper.c Move the AArch32 TLBI insns for AArch32 EL2 to tlbi_insn_helper.c. To keep this as an obviously pure code-movement, we retain the same condition for registering tlbi_el2_cp_reginfo that we use for el2_cp_reginfo. We'll be able to simplify this condition later, since the need to define the reginfo for EL3-without-EL2 doesn't apply for the TLBI ops specifically. This move brings all the uses of tlbimva_hyp_write() and tlbimva_hyp_is_write() back into a single file, so we can move those also, and make them file-local again. The helper alle1_tlbmask() is an exception to the pattern that we only need to make these functions global temporarily, because once this refactoring is complete it will be called by both code in helper.c (vttbr_write()) and by code in tlb-insns.c. We therefore put its prototype in a permanent home in internals.h. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson Message-id: 20241210160452.2427965-3-peter.maydell@linaro.org --- target/arm/cpregs.h | 4 -- target/arm/helper.c | 74 +-------------------------------- target/arm/internals.h | 6 +++ target/arm/tcg/tlb-insns.c | 85 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 92 insertions(+), 77 deletions(-) diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index 26c27dc5cb..851cd045b2 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -1143,9 +1143,5 @@ CPAccessResult access_ttlb(CPUARMState *env, const ARMCPRegInfo *ri, CPAccessResult access_ttlbis(CPUARMState *env, const ARMCPRegInfo *ri, bool isread); bool tlb_force_broadcast(CPUARMState *env); -void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value); -void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value); #endif /* TARGET_ARM_CPREGS_H */ diff --git a/target/arm/helper.c b/target/arm/helper.c index 6a9bf70f18..3c69225e1d 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -438,7 +438,7 @@ static void contextidr_write(CPUARMState *env, const ARMCPRegInfo *ri, raw_write(env, ri, value); } -static int alle1_tlbmask(CPUARMState *env) +int alle1_tlbmask(CPUARMState *env) { /* * Note that the 'ALL' scope must invalidate both stage 1 and @@ -465,58 +465,6 @@ bool tlb_force_broadcast(CPUARMState *env) return arm_current_el(env) == 1 && (arm_hcr_el2_eff(env) & HCR_FB); } -static void tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - - tlb_flush_by_mmuidx(cs, alle1_tlbmask(env)); -} - -static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - - tlb_flush_by_mmuidx_all_cpus_synced(cs, alle1_tlbmask(env)); -} - - -static void tlbiall_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - - tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_E2); -} - -static void tlbiall_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - - tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_E2); -} - -void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12); - - tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_E2); -} - -void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12); - - tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, - ARMMMUIdxBit_E2); -} - static const ARMCPRegInfo cp_reginfo[] = { /* * Define the secure and non-secure FCSE identifier CP registers @@ -6248,26 +6196,6 @@ static const ARMCPRegInfo el2_cp_reginfo[] = { { .name = "HTTBR", .cp = 15, .opc1 = 4, .crm = 2, .access = PL2_RW, .type = ARM_CP_64BIT | ARM_CP_ALIAS, .fieldoffset = offsetof(CPUARMState, cp15.ttbr0_el[2]) }, - { .name = "TLBIALLNSNH", - .cp = 15, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 4, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbiall_nsnh_write }, - { .name = "TLBIALLNSNHIS", - .cp = 15, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 4, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbiall_nsnh_is_write }, - { .name = "TLBIALLH", .cp = 15, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 0, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbiall_hyp_write }, - { .name = "TLBIALLHIS", .cp = 15, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 0, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbiall_hyp_is_write }, - { .name = "TLBIMVAH", .cp = 15, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 1, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbimva_hyp_write }, - { .name = "TLBIMVAHIS", .cp = 15, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 1, - .type = ARM_CP_NO_RAW, .access = PL2_W, - .writefn = tlbimva_hyp_is_write }, { .name = "TLBI_ALLE2", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 0, .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, diff --git a/target/arm/internals.h b/target/arm/internals.h index 2adedb9477..c3a5b1385f 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -1820,4 +1820,10 @@ uint64_t gt_get_countervalue(CPUARMState *env); * and CNTVCT_EL0 (this will be either 0 or the value of CNTVOFF_EL2). */ uint64_t gt_virt_cnt_offset(CPUARMState *env); + +/* + * Return mask of ARMMMUIdxBit values corresponding to an "invalidate + * all EL1" scope; this covers stage 1 and stage 2. + */ +int alle1_tlbmask(CPUARMState *env); #endif diff --git a/target/arm/tcg/tlb-insns.c b/target/arm/tcg/tlb-insns.c index cdf23352d7..66096093dc 100644 --- a/target/arm/tcg/tlb-insns.c +++ b/target/arm/tcg/tlb-insns.c @@ -99,6 +99,25 @@ static void tlbimvaa_write(CPUARMState *env, const ARMCPRegInfo *ri, } } +static void tlbimva_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12); + + tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_E2); +} + +static void tlbimva_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + uint64_t pageaddr = value & ~MAKE_64BIT_MASK(0, 12); + + tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, + ARMMMUIdxBit_E2); +} + static void tlbiipas2_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -117,6 +136,39 @@ static void tlbiipas2is_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, ARMMMUIdxBit_Stage2); } +static void tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + + tlb_flush_by_mmuidx(cs, alle1_tlbmask(env)); +} + +static void tlbiall_nsnh_is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + + tlb_flush_by_mmuidx_all_cpus_synced(cs, alle1_tlbmask(env)); +} + + +static void tlbiall_hyp_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + + tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_E2); +} + +static void tlbiall_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + + tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_E2); +} + static const ARMCPRegInfo tlbi_not_v7_cp_reginfo[] = { /* * MMU TLB control. Note that the wildcarding means we cover not just @@ -227,6 +279,29 @@ static const ARMCPRegInfo tlbi_v8_cp_reginfo[] = { .writefn = tlbiipas2is_hyp_write }, }; +static const ARMCPRegInfo tlbi_el2_cp_reginfo[] = { + { .name = "TLBIALLNSNH", + .cp = 15, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 4, + .type = ARM_CP_NO_RAW, .access = PL2_W, + .writefn = tlbiall_nsnh_write }, + { .name = "TLBIALLNSNHIS", + .cp = 15, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 4, + .type = ARM_CP_NO_RAW, .access = PL2_W, + .writefn = tlbiall_nsnh_is_write }, + { .name = "TLBIALLH", .cp = 15, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 0, + .type = ARM_CP_NO_RAW, .access = PL2_W, + .writefn = tlbiall_hyp_write }, + { .name = "TLBIALLHIS", .cp = 15, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 0, + .type = ARM_CP_NO_RAW, .access = PL2_W, + .writefn = tlbiall_hyp_is_write }, + { .name = "TLBIMVAH", .cp = 15, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 1, + .type = ARM_CP_NO_RAW, .access = PL2_W, + .writefn = tlbimva_hyp_write }, + { .name = "TLBIMVAHIS", .cp = 15, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 1, + .type = ARM_CP_NO_RAW, .access = PL2_W, + .writefn = tlbimva_hyp_is_write }, +}; + void define_tlb_insn_regs(ARMCPU *cpu) { CPUARMState *env = &cpu->env; @@ -243,4 +318,14 @@ void define_tlb_insn_regs(ARMCPU *cpu) if (arm_feature(env, ARM_FEATURE_V8)) { define_arm_cp_regs(cpu, tlbi_v8_cp_reginfo); } + /* + * We retain the existing logic for when to register these TLBI + * ops (i.e. matching the condition for el2_cp_reginfo[] in + * helper.c), but we will be able to simplify this later. + */ + if (arm_feature(env, ARM_FEATURE_EL2) + || (arm_feature(env, ARM_FEATURE_EL3) + && arm_feature(env, ARM_FEATURE_V8))) { + define_arm_cp_regs(cpu, tlbi_el2_cp_reginfo); + } } From abbb82646a1fab2075aae3c9ea8acf63e9fa80f7 Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Tue, 10 Dec 2024 16:04:45 +0000 Subject: [PATCH 78/85] target/arm: Move AArch64 TLBI insns from v8_cp_reginfo[] Move the AArch64 TLBI insns that are declared in v8_cp_reginfo[] into tlb-insns.c. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson Message-id: 20241210160452.2427965-4-peter.maydell@linaro.org --- target/arm/cpregs.h | 11 +++ target/arm/helper.c | 182 +++---------------------------------- target/arm/tcg/tlb-insns.c | 160 ++++++++++++++++++++++++++++++++ 3 files changed, 182 insertions(+), 171 deletions(-) diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index 851cd045b2..a14f5bb6c9 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -1143,5 +1143,16 @@ CPAccessResult access_ttlb(CPUARMState *env, const ARMCPRegInfo *ri, CPAccessResult access_ttlbis(CPUARMState *env, const ARMCPRegInfo *ri, bool isread); bool tlb_force_broadcast(CPUARMState *env); +int tlbbits_for_regime(CPUARMState *env, ARMMMUIdx mmu_idx, + uint64_t addr); +int vae1_tlbbits(CPUARMState *env, uint64_t addr); +int vae1_tlbmask(CPUARMState *env); +int ipas2e1_tlbmask(CPUARMState *env, int64_t value); +void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value); +void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value); +void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value); #endif /* TARGET_ARM_CPREGS_H */ diff --git a/target/arm/helper.c b/target/arm/helper.c index 3c69225e1d..cc7da7f115 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -4685,7 +4685,7 @@ static CPAccessResult access_tocu(CPUARMState *env, const ARMCPRegInfo *ri, * Page D4-1736 (DDI0487A.b) */ -static int vae1_tlbmask(CPUARMState *env) +int vae1_tlbmask(CPUARMState *env) { uint64_t hcr = arm_hcr_el2_eff(env); uint16_t mask; @@ -4721,8 +4721,8 @@ static int vae2_tlbmask(CPUARMState *env) } /* Return 56 if TBI is enabled, 64 otherwise. */ -static int tlbbits_for_regime(CPUARMState *env, ARMMMUIdx mmu_idx, - uint64_t addr) +int tlbbits_for_regime(CPUARMState *env, ARMMMUIdx mmu_idx, + uint64_t addr) { uint64_t tcr = regime_tcr(env, mmu_idx); int tbi = aa64_va_parameter_tbi(tcr, mmu_idx); @@ -4731,7 +4731,7 @@ static int tlbbits_for_regime(CPUARMState *env, ARMMMUIdx mmu_idx, return (tbi >> select) & 1 ? 56 : 64; } -static int vae1_tlbbits(CPUARMState *env, uint64_t addr) +int vae1_tlbbits(CPUARMState *env, uint64_t addr) { uint64_t hcr = arm_hcr_el2_eff(env); ARMMMUIdx mmu_idx; @@ -4767,8 +4767,8 @@ static int vae2_tlbbits(CPUARMState *env, uint64_t addr) return tlbbits_for_regime(env, mmu_idx, addr); } -static void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { CPUState *cs = env_cpu(env); int mask = vae1_tlbmask(env); @@ -4776,19 +4776,6 @@ static void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx_all_cpus_synced(cs, mask); } -static void tlbi_aa64_vmalle1_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - int mask = vae1_tlbmask(env); - - if (tlb_force_broadcast(env)) { - tlb_flush_by_mmuidx_all_cpus_synced(cs, mask); - } else { - tlb_flush_by_mmuidx(cs, mask); - } -} - static int e2_tlbmask(CPUARMState *env) { return (ARMMMUIdxBit_E20_0 | @@ -4797,15 +4784,6 @@ static int e2_tlbmask(CPUARMState *env) ARMMMUIdxBit_E2); } -static void tlbi_aa64_alle1_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - int mask = alle1_tlbmask(env); - - tlb_flush_by_mmuidx(cs, mask); -} - static void tlbi_aa64_alle2_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -4824,8 +4802,8 @@ static void tlbi_aa64_alle3_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_E3); } -static void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { CPUState *cs = env_cpu(env); int mask = alle1_tlbmask(env); @@ -4881,8 +4859,8 @@ static void tlbi_aa64_vae3_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_E3); } -static void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { CPUState *cs = env_cpu(env); int mask = vae1_tlbmask(env); @@ -4892,27 +4870,6 @@ static void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_page_bits_by_mmuidx_all_cpus_synced(cs, pageaddr, mask, bits); } -static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* - * Invalidate by VA, EL1&0 (AArch64 version). - * Currently handles all of VAE1, VAAE1, VAALE1 and VALE1, - * since we don't support flush-for-specific-ASID-only or - * flush-last-level-only. - */ - CPUState *cs = env_cpu(env); - int mask = vae1_tlbmask(env); - uint64_t pageaddr = sextract64(value << 12, 0, 56); - int bits = vae1_tlbbits(env, pageaddr); - - if (tlb_force_broadcast(env)) { - tlb_flush_page_bits_by_mmuidx_all_cpus_synced(cs, pageaddr, mask, bits); - } else { - tlb_flush_page_bits_by_mmuidx(cs, pageaddr, mask, bits); - } -} - static void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -4935,7 +4892,7 @@ static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, ARMMMUIdxBit_E3, bits); } -static int ipas2e1_tlbmask(CPUARMState *env, int64_t value) +int ipas2e1_tlbmask(CPUARMState *env, int64_t value) { /* * The MSB of value is the NS field, which only applies if SEL2 @@ -4948,30 +4905,6 @@ static int ipas2e1_tlbmask(CPUARMState *env, int64_t value) : ARMMMUIdxBit_Stage2); } -static void tlbi_aa64_ipas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - int mask = ipas2e1_tlbmask(env, value); - uint64_t pageaddr = sextract64(value << 12, 0, 56); - - if (tlb_force_broadcast(env)) { - tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, mask); - } else { - tlb_flush_page_by_mmuidx(cs, pageaddr, mask); - } -} - -static void tlbi_aa64_ipas2e1is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - int mask = ipas2e1_tlbmask(env, value); - uint64_t pageaddr = sextract64(value << 12, 0, 56); - - tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, mask); -} - #ifdef TARGET_AARCH64 typedef struct { uint64_t base; @@ -5462,99 +5395,6 @@ static const ARMCPRegInfo v8_cp_reginfo[] = { .opc0 = 1, .opc1 = 0, .crn = 7, .crm = 14, .opc2 = 2, .fgt = FGT_DCCISW, .access = PL1_W, .accessfn = access_tsw, .type = ARM_CP_NOP }, - /* TLBI operations */ - { .name = "TLBI_VMALLE1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 0, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIVMALLE1IS, - .writefn = tlbi_aa64_vmalle1is_write }, - { .name = "TLBI_VAE1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 1, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIVAE1IS, - .writefn = tlbi_aa64_vae1is_write }, - { .name = "TLBI_ASIDE1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 2, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIASIDE1IS, - .writefn = tlbi_aa64_vmalle1is_write }, - { .name = "TLBI_VAAE1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 3, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIVAAE1IS, - .writefn = tlbi_aa64_vae1is_write }, - { .name = "TLBI_VALE1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 5, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIVALE1IS, - .writefn = tlbi_aa64_vae1is_write }, - { .name = "TLBI_VAALE1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 7, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIVAALE1IS, - .writefn = tlbi_aa64_vae1is_write }, - { .name = "TLBI_VMALLE1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 0, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIVMALLE1, - .writefn = tlbi_aa64_vmalle1_write }, - { .name = "TLBI_VAE1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 1, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIVAE1, - .writefn = tlbi_aa64_vae1_write }, - { .name = "TLBI_ASIDE1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 2, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIASIDE1, - .writefn = tlbi_aa64_vmalle1_write }, - { .name = "TLBI_VAAE1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 3, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIVAAE1, - .writefn = tlbi_aa64_vae1_write }, - { .name = "TLBI_VALE1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 5, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIVALE1, - .writefn = tlbi_aa64_vae1_write }, - { .name = "TLBI_VAALE1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 7, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIVAALE1, - .writefn = tlbi_aa64_vae1_write }, - { .name = "TLBI_IPAS2E1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_ipas2e1is_write }, - { .name = "TLBI_IPAS2LE1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_ipas2e1is_write }, - { .name = "TLBI_ALLE1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 4, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_alle1is_write }, - { .name = "TLBI_VMALLS12E1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 6, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_alle1is_write }, - { .name = "TLBI_IPAS2E1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_ipas2e1_write }, - { .name = "TLBI_IPAS2LE1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_ipas2e1_write }, - { .name = "TLBI_ALLE1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 4, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_alle1_write }, - { .name = "TLBI_VMALLS12E1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 6, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_alle1is_write }, #ifndef CONFIG_USER_ONLY /* 64 bit address translation operations */ { .name = "AT_S1E1R", .state = ARM_CP_STATE_AA64, diff --git a/target/arm/tcg/tlb-insns.c b/target/arm/tcg/tlb-insns.c index 66096093dc..ff7698e31b 100644 --- a/target/arm/tcg/tlb-insns.c +++ b/target/arm/tcg/tlb-insns.c @@ -169,6 +169,73 @@ static void tlbiall_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_E2); } +static void tlbi_aa64_vmalle1_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + int mask = vae1_tlbmask(env); + + if (tlb_force_broadcast(env)) { + tlb_flush_by_mmuidx_all_cpus_synced(cs, mask); + } else { + tlb_flush_by_mmuidx(cs, mask); + } +} + +static void tlbi_aa64_alle1_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + int mask = alle1_tlbmask(env); + + tlb_flush_by_mmuidx(cs, mask); +} + +static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA, EL1&0 (AArch64 version). + * Currently handles all of VAE1, VAAE1, VAALE1 and VALE1, + * since we don't support flush-for-specific-ASID-only or + * flush-last-level-only. + */ + CPUState *cs = env_cpu(env); + int mask = vae1_tlbmask(env); + uint64_t pageaddr = sextract64(value << 12, 0, 56); + int bits = vae1_tlbbits(env, pageaddr); + + if (tlb_force_broadcast(env)) { + tlb_flush_page_bits_by_mmuidx_all_cpus_synced(cs, pageaddr, mask, bits); + } else { + tlb_flush_page_bits_by_mmuidx(cs, pageaddr, mask, bits); + } +} + +static void tlbi_aa64_ipas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + int mask = ipas2e1_tlbmask(env, value); + uint64_t pageaddr = sextract64(value << 12, 0, 56); + + if (tlb_force_broadcast(env)) { + tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, mask); + } else { + tlb_flush_page_by_mmuidx(cs, pageaddr, mask); + } +} + +static void tlbi_aa64_ipas2e1is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + int mask = ipas2e1_tlbmask(env, value); + uint64_t pageaddr = sextract64(value << 12, 0, 56); + + tlb_flush_page_by_mmuidx_all_cpus_synced(cs, pageaddr, mask); +} + static const ARMCPRegInfo tlbi_not_v7_cp_reginfo[] = { /* * MMU TLB control. Note that the wildcarding means we cover not just @@ -277,6 +344,99 @@ static const ARMCPRegInfo tlbi_v8_cp_reginfo[] = { .cp = 15, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 5, .type = ARM_CP_NO_RAW, .access = PL2_W, .writefn = tlbiipas2is_hyp_write }, + /* AArch64 TLBI operations */ + { .name = "TLBI_VMALLE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 0, + .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIVMALLE1IS, + .writefn = tlbi_aa64_vmalle1is_write }, + { .name = "TLBI_VAE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 1, + .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIVAE1IS, + .writefn = tlbi_aa64_vae1is_write }, + { .name = "TLBI_ASIDE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 2, + .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIASIDE1IS, + .writefn = tlbi_aa64_vmalle1is_write }, + { .name = "TLBI_VAAE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 3, + .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIVAAE1IS, + .writefn = tlbi_aa64_vae1is_write }, + { .name = "TLBI_VALE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 5, + .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIVALE1IS, + .writefn = tlbi_aa64_vae1is_write }, + { .name = "TLBI_VAALE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 3, .opc2 = 7, + .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIVAALE1IS, + .writefn = tlbi_aa64_vae1is_write }, + { .name = "TLBI_VMALLE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 0, + .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIVMALLE1, + .writefn = tlbi_aa64_vmalle1_write }, + { .name = "TLBI_VAE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 1, + .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIVAE1, + .writefn = tlbi_aa64_vae1_write }, + { .name = "TLBI_ASIDE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 2, + .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIASIDE1, + .writefn = tlbi_aa64_vmalle1_write }, + { .name = "TLBI_VAAE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 3, + .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIVAAE1, + .writefn = tlbi_aa64_vae1_write }, + { .name = "TLBI_VALE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 5, + .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIVALE1, + .writefn = tlbi_aa64_vae1_write }, + { .name = "TLBI_VAALE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 7, .opc2 = 7, + .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIVAALE1, + .writefn = tlbi_aa64_vae1_write }, + { .name = "TLBI_IPAS2E1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 1, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_ipas2e1is_write }, + { .name = "TLBI_IPAS2LE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 5, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_ipas2e1is_write }, + { .name = "TLBI_ALLE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 4, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle1is_write }, + { .name = "TLBI_VMALLS12E1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 6, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle1is_write }, + { .name = "TLBI_IPAS2E1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 1, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_ipas2e1_write }, + { .name = "TLBI_IPAS2LE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 5, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_ipas2e1_write }, + { .name = "TLBI_ALLE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 4, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle1_write }, + { .name = "TLBI_VMALLS12E1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 6, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle1is_write }, }; static const ARMCPRegInfo tlbi_el2_cp_reginfo[] = { From 7cadf1139db301d603ff5f1f0a3cc56391f68d12 Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Tue, 10 Dec 2024 16:04:46 +0000 Subject: [PATCH 79/85] target/arm: Move the AArch64 EL2 TLBI insns Move the AArch64 EL2 TLBI insn definitions that were in el2_cp_reginfo[] across to tlb-insns.c. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson Message-id: 20241210160452.2427965-5-peter.maydell@linaro.org --- target/arm/cpregs.h | 7 +++++ target/arm/helper.c | 61 ++++---------------------------------- target/arm/tcg/tlb-insns.c | 49 ++++++++++++++++++++++++++++++ 3 files changed, 62 insertions(+), 55 deletions(-) diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index a14f5bb6c9..57446ae1b5 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -1146,13 +1146,20 @@ bool tlb_force_broadcast(CPUARMState *env); int tlbbits_for_regime(CPUARMState *env, ARMMMUIdx mmu_idx, uint64_t addr); int vae1_tlbbits(CPUARMState *env, uint64_t addr); +int vae2_tlbbits(CPUARMState *env, uint64_t addr); int vae1_tlbmask(CPUARMState *env); +int vae2_tlbmask(CPUARMState *env); int ipas2e1_tlbmask(CPUARMState *env, int64_t value); +int e2_tlbmask(CPUARMState *env); void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value); void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value); void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value); +void tlbi_aa64_alle2is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value); +void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value); #endif /* TARGET_ARM_CPREGS_H */ diff --git a/target/arm/helper.c b/target/arm/helper.c index cc7da7f115..6942d2f2fb 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -4705,7 +4705,7 @@ int vae1_tlbmask(CPUARMState *env) return mask; } -static int vae2_tlbmask(CPUARMState *env) +int vae2_tlbmask(CPUARMState *env) { uint64_t hcr = arm_hcr_el2_eff(env); uint16_t mask; @@ -4748,7 +4748,7 @@ int vae1_tlbbits(CPUARMState *env, uint64_t addr) return tlbbits_for_regime(env, mmu_idx, addr); } -static int vae2_tlbbits(CPUARMState *env, uint64_t addr) +int vae2_tlbbits(CPUARMState *env, uint64_t addr) { uint64_t hcr = arm_hcr_el2_eff(env); ARMMMUIdx mmu_idx; @@ -4776,7 +4776,7 @@ void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx_all_cpus_synced(cs, mask); } -static int e2_tlbmask(CPUARMState *env) +int e2_tlbmask(CPUARMState *env) { return (ARMMMUIdxBit_E20_0 | ARMMMUIdxBit_E20_2 | @@ -4784,15 +4784,6 @@ static int e2_tlbmask(CPUARMState *env) ARMMMUIdxBit_E2); } -static void tlbi_aa64_alle2_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - int mask = e2_tlbmask(env); - - tlb_flush_by_mmuidx(cs, mask); -} - static void tlbi_aa64_alle3_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -4811,8 +4802,8 @@ void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx_all_cpus_synced(cs, mask); } -static void tlbi_aa64_alle2is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +void tlbi_aa64_alle2is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { CPUState *cs = env_cpu(env); int mask = e2_tlbmask(env); @@ -4828,22 +4819,6 @@ static void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_E3); } -static void tlbi_aa64_vae2_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* - * Invalidate by VA, EL2 - * Currently handles both VAE2 and VALE2, since we don't support - * flush-last-level-only. - */ - CPUState *cs = env_cpu(env); - int mask = vae2_tlbmask(env); - uint64_t pageaddr = sextract64(value << 12, 0, 56); - int bits = vae2_tlbbits(env, pageaddr); - - tlb_flush_page_bits_by_mmuidx(cs, pageaddr, mask, bits); -} - static void tlbi_aa64_vae3_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -4870,7 +4845,7 @@ void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_page_bits_by_mmuidx_all_cpus_synced(cs, pageaddr, mask, bits); } -static void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, +void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { CPUState *cs = env_cpu(env); @@ -6036,30 +6011,6 @@ static const ARMCPRegInfo el2_cp_reginfo[] = { { .name = "HTTBR", .cp = 15, .opc1 = 4, .crm = 2, .access = PL2_RW, .type = ARM_CP_64BIT | ARM_CP_ALIAS, .fieldoffset = offsetof(CPUARMState, cp15.ttbr0_el[2]) }, - { .name = "TLBI_ALLE2", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 0, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_alle2_write }, - { .name = "TLBI_VAE2", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_vae2_write }, - { .name = "TLBI_VALE2", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_vae2_write }, - { .name = "TLBI_ALLE2IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 0, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_alle2is_write }, - { .name = "TLBI_VAE2IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_vae2is_write }, - { .name = "TLBI_VALE2IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_vae2is_write }, #ifndef CONFIG_USER_ONLY /* * Unlike the other EL2-related AT operations, these must diff --git a/target/arm/tcg/tlb-insns.c b/target/arm/tcg/tlb-insns.c index ff7698e31b..1eebb6055c 100644 --- a/target/arm/tcg/tlb-insns.c +++ b/target/arm/tcg/tlb-insns.c @@ -191,6 +191,31 @@ static void tlbi_aa64_alle1_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx(cs, mask); } +static void tlbi_aa64_alle2_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + int mask = e2_tlbmask(env); + + tlb_flush_by_mmuidx(cs, mask); +} + +static void tlbi_aa64_vae2_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA, EL2 + * Currently handles both VAE2 and VALE2, since we don't support + * flush-last-level-only. + */ + CPUState *cs = env_cpu(env); + int mask = vae2_tlbmask(env); + uint64_t pageaddr = sextract64(value << 12, 0, 56); + int bits = vae2_tlbbits(env, pageaddr); + + tlb_flush_page_bits_by_mmuidx(cs, pageaddr, mask, bits); +} + static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -460,6 +485,30 @@ static const ARMCPRegInfo tlbi_el2_cp_reginfo[] = { { .name = "TLBIMVAHIS", .cp = 15, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 1, .type = ARM_CP_NO_RAW, .access = PL2_W, .writefn = tlbimva_hyp_is_write }, + { .name = "TLBI_ALLE2", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 0, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_alle2_write }, + { .name = "TLBI_VAE2", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 1, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_vae2_write }, + { .name = "TLBI_VALE2", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 7, .opc2 = 5, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_vae2_write }, + { .name = "TLBI_ALLE2IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 0, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_alle2is_write }, + { .name = "TLBI_VAE2IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 1, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_vae2is_write }, + { .name = "TLBI_VALE2IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 3, .opc2 = 5, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_vae2is_write }, }; void define_tlb_insn_regs(ARMCPU *cpu) From 5991e5abe36e228143a6488718c71ba05da05cc3 Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Tue, 10 Dec 2024 16:04:47 +0000 Subject: [PATCH 80/85] target/arm: Move AArch64 EL3 TLBI insns Move the AArch64 EL3 TLBI insns from el3_cp_reginfo[] across to tlb-insns.c. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson Message-id: 20241210160452.2427965-6-peter.maydell@linaro.org --- target/arm/cpregs.h | 4 +++ target/arm/helper.c | 56 +++----------------------------------- target/arm/tcg/tlb-insns.c | 54 ++++++++++++++++++++++++++++++++++++ 3 files changed, 62 insertions(+), 52 deletions(-) diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index 57446ae1b5..722ac5bb88 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -1161,5 +1161,9 @@ void tlbi_aa64_alle2is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value); void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value); +void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value); +void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value); #endif /* TARGET_ARM_CPREGS_H */ diff --git a/target/arm/helper.c b/target/arm/helper.c index 6942d2f2fb..baeabb5ec7 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -4784,15 +4784,6 @@ int e2_tlbmask(CPUARMState *env) ARMMMUIdxBit_E2); } -static void tlbi_aa64_alle3_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - ARMCPU *cpu = env_archcpu(env); - CPUState *cs = CPU(cpu); - - tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_E3); -} - void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -4811,29 +4802,14 @@ void tlbi_aa64_alle2is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx_all_cpus_synced(cs, mask); } -static void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { CPUState *cs = env_cpu(env); tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_E3); } -static void tlbi_aa64_vae3_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* - * Invalidate by VA, EL3 - * Currently handles both VAE3 and VALE3, since we don't support - * flush-last-level-only. - */ - ARMCPU *cpu = env_archcpu(env); - CPUState *cs = CPU(cpu); - uint64_t pageaddr = sextract64(value << 12, 0, 56); - - tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_E3); -} - void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -4856,8 +4832,8 @@ void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_page_bits_by_mmuidx_all_cpus_synced(cs, pageaddr, mask, bits); } -static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) +void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) { CPUState *cs = env_cpu(env); uint64_t pageaddr = sextract64(value << 12, 0, 56); @@ -6223,30 +6199,6 @@ static const ARMCPRegInfo el3_cp_reginfo[] = { .opc0 = 3, .opc1 = 6, .crn = 5, .crm = 1, .opc2 = 1, .access = PL3_RW, .type = ARM_CP_CONST, .resetvalue = 0 }, - { .name = "TLBI_ALLE3IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 3, .opc2 = 0, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_alle3is_write }, - { .name = "TLBI_VAE3IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 3, .opc2 = 1, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_vae3is_write }, - { .name = "TLBI_VALE3IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 3, .opc2 = 5, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_vae3is_write }, - { .name = "TLBI_ALLE3", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 7, .opc2 = 0, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_alle3_write }, - { .name = "TLBI_VAE3", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 7, .opc2 = 1, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_vae3_write }, - { .name = "TLBI_VALE3", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 7, .opc2 = 5, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_vae3_write }, }; #ifndef CONFIG_USER_ONLY diff --git a/target/arm/tcg/tlb-insns.c b/target/arm/tcg/tlb-insns.c index 1eebb6055c..528265404d 100644 --- a/target/arm/tcg/tlb-insns.c +++ b/target/arm/tcg/tlb-insns.c @@ -200,6 +200,15 @@ static void tlbi_aa64_alle2_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx(cs, mask); } +static void tlbi_aa64_alle3_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + ARMCPU *cpu = env_archcpu(env); + CPUState *cs = CPU(cpu); + + tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_E3); +} + static void tlbi_aa64_vae2_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -216,6 +225,21 @@ static void tlbi_aa64_vae2_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_page_bits_by_mmuidx(cs, pageaddr, mask, bits); } +static void tlbi_aa64_vae3_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA, EL3 + * Currently handles both VAE3 and VALE3, since we don't support + * flush-last-level-only. + */ + ARMCPU *cpu = env_archcpu(env); + CPUState *cs = CPU(cpu); + uint64_t pageaddr = sextract64(value << 12, 0, 56); + + tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_E3); +} + static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -511,6 +535,33 @@ static const ARMCPRegInfo tlbi_el2_cp_reginfo[] = { .writefn = tlbi_aa64_vae2is_write }, }; +static const ARMCPRegInfo tlbi_el3_cp_reginfo[] = { + { .name = "TLBI_ALLE3IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 3, .opc2 = 0, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle3is_write }, + { .name = "TLBI_VAE3IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 3, .opc2 = 1, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_vae3is_write }, + { .name = "TLBI_VALE3IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 3, .opc2 = 5, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_vae3is_write }, + { .name = "TLBI_ALLE3", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 7, .opc2 = 0, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle3_write }, + { .name = "TLBI_VAE3", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 7, .opc2 = 1, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_vae3_write }, + { .name = "TLBI_VALE3", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 7, .opc2 = 5, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_vae3_write }, +}; + void define_tlb_insn_regs(ARMCPU *cpu) { CPUARMState *env = &cpu->env; @@ -537,4 +588,7 @@ void define_tlb_insn_regs(ARMCPU *cpu) && arm_feature(env, ARM_FEATURE_V8))) { define_arm_cp_regs(cpu, tlbi_el2_cp_reginfo); } + if (arm_feature(env, ARM_FEATURE_EL3)) { + define_arm_cp_regs(cpu, tlbi_el3_cp_reginfo); + } } From 65593799571abeccd9a69f9b03be6e4c48e75532 Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Tue, 10 Dec 2024 16:04:48 +0000 Subject: [PATCH 81/85] target/arm: Move TLBI range insns Move the TLBI invalidate-range insns across to tlb-insns.c. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson Message-id: 20241210160452.2427965-7-peter.maydell@linaro.org --- target/arm/cpregs.h | 2 + target/arm/helper.c | 330 +------------------------------------ target/arm/tcg/tlb-insns.c | 329 ++++++++++++++++++++++++++++++++++++ 3 files changed, 333 insertions(+), 328 deletions(-) diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index 722ac5bb88..fe838bcfd9 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -1142,6 +1142,8 @@ CPAccessResult access_ttlb(CPUARMState *env, const ARMCPRegInfo *ri, bool isread); CPAccessResult access_ttlbis(CPUARMState *env, const ARMCPRegInfo *ri, bool isread); +CPAccessResult access_ttlbos(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread); bool tlb_force_broadcast(CPUARMState *env); int tlbbits_for_regime(CPUARMState *env, ARMMMUIdx mmu_idx, uint64_t addr); diff --git a/target/arm/helper.c b/target/arm/helper.c index baeabb5ec7..376aa9aecd 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -388,8 +388,8 @@ CPAccessResult access_ttlbis(CPUARMState *env, const ARMCPRegInfo *ri, #ifdef TARGET_AARCH64 /* Check for traps from EL1 due to HCR_EL2.TTLB or TTLBOS. */ -static CPAccessResult access_ttlbos(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread) +CPAccessResult access_ttlbos(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread) { if (arm_current_el(env) == 1 && (arm_hcr_el2_eff(env) & (HCR_TTLB | HCR_TTLBOS))) { @@ -4856,202 +4856,6 @@ int ipas2e1_tlbmask(CPUARMState *env, int64_t value) : ARMMMUIdxBit_Stage2); } -#ifdef TARGET_AARCH64 -typedef struct { - uint64_t base; - uint64_t length; -} TLBIRange; - -static ARMGranuleSize tlbi_range_tg_to_gran_size(int tg) -{ - /* - * Note that the TLBI range TG field encoding differs from both - * TG0 and TG1 encodings. - */ - switch (tg) { - case 1: - return Gran4K; - case 2: - return Gran16K; - case 3: - return Gran64K; - default: - return GranInvalid; - } -} - -static TLBIRange tlbi_aa64_get_range(CPUARMState *env, ARMMMUIdx mmuidx, - uint64_t value) -{ - unsigned int page_size_granule, page_shift, num, scale, exponent; - /* Extract one bit to represent the va selector in use. */ - uint64_t select = sextract64(value, 36, 1); - ARMVAParameters param = aa64_va_parameters(env, select, mmuidx, true, false); - TLBIRange ret = { }; - ARMGranuleSize gran; - - page_size_granule = extract64(value, 46, 2); - gran = tlbi_range_tg_to_gran_size(page_size_granule); - - /* The granule encoded in value must match the granule in use. */ - if (gran != param.gran) { - qemu_log_mask(LOG_GUEST_ERROR, "Invalid tlbi page size granule %d\n", - page_size_granule); - return ret; - } - - page_shift = arm_granule_bits(gran); - num = extract64(value, 39, 5); - scale = extract64(value, 44, 2); - exponent = (5 * scale) + 1; - - ret.length = (num + 1) << (exponent + page_shift); - - if (param.select) { - ret.base = sextract64(value, 0, 37); - } else { - ret.base = extract64(value, 0, 37); - } - if (param.ds) { - /* - * With DS=1, BaseADDR is always shifted 16 so that it is able - * to address all 52 va bits. The input address is perforce - * aligned on a 64k boundary regardless of translation granule. - */ - page_shift = 16; - } - ret.base <<= page_shift; - - return ret; -} - -static void do_rvae_write(CPUARMState *env, uint64_t value, - int idxmap, bool synced) -{ - ARMMMUIdx one_idx = ARM_MMU_IDX_A | ctz32(idxmap); - TLBIRange range; - int bits; - - range = tlbi_aa64_get_range(env, one_idx, value); - bits = tlbbits_for_regime(env, one_idx, range.base); - - if (synced) { - tlb_flush_range_by_mmuidx_all_cpus_synced(env_cpu(env), - range.base, - range.length, - idxmap, - bits); - } else { - tlb_flush_range_by_mmuidx(env_cpu(env), range.base, - range.length, idxmap, bits); - } -} - -static void tlbi_aa64_rvae1_write(CPUARMState *env, - const ARMCPRegInfo *ri, - uint64_t value) -{ - /* - * Invalidate by VA range, EL1&0. - * Currently handles all of RVAE1, RVAAE1, RVAALE1 and RVALE1, - * since we don't support flush-for-specific-ASID-only or - * flush-last-level-only. - */ - - do_rvae_write(env, value, vae1_tlbmask(env), - tlb_force_broadcast(env)); -} - -static void tlbi_aa64_rvae1is_write(CPUARMState *env, - const ARMCPRegInfo *ri, - uint64_t value) -{ - /* - * Invalidate by VA range, Inner/Outer Shareable EL1&0. - * Currently handles all of RVAE1IS, RVAE1OS, RVAAE1IS, RVAAE1OS, - * RVAALE1IS, RVAALE1OS, RVALE1IS and RVALE1OS, since we don't support - * flush-for-specific-ASID-only, flush-last-level-only or inner/outer - * shareable specific flushes. - */ - - do_rvae_write(env, value, vae1_tlbmask(env), true); -} - -static void tlbi_aa64_rvae2_write(CPUARMState *env, - const ARMCPRegInfo *ri, - uint64_t value) -{ - /* - * Invalidate by VA range, EL2. - * Currently handles all of RVAE2 and RVALE2, - * since we don't support flush-for-specific-ASID-only or - * flush-last-level-only. - */ - - do_rvae_write(env, value, vae2_tlbmask(env), - tlb_force_broadcast(env)); - - -} - -static void tlbi_aa64_rvae2is_write(CPUARMState *env, - const ARMCPRegInfo *ri, - uint64_t value) -{ - /* - * Invalidate by VA range, Inner/Outer Shareable, EL2. - * Currently handles all of RVAE2IS, RVAE2OS, RVALE2IS and RVALE2OS, - * since we don't support flush-for-specific-ASID-only, - * flush-last-level-only or inner/outer shareable specific flushes. - */ - - do_rvae_write(env, value, vae2_tlbmask(env), true); - -} - -static void tlbi_aa64_rvae3_write(CPUARMState *env, - const ARMCPRegInfo *ri, - uint64_t value) -{ - /* - * Invalidate by VA range, EL3. - * Currently handles all of RVAE3 and RVALE3, - * since we don't support flush-for-specific-ASID-only or - * flush-last-level-only. - */ - - do_rvae_write(env, value, ARMMMUIdxBit_E3, tlb_force_broadcast(env)); -} - -static void tlbi_aa64_rvae3is_write(CPUARMState *env, - const ARMCPRegInfo *ri, - uint64_t value) -{ - /* - * Invalidate by VA range, EL3, Inner/Outer Shareable. - * Currently handles all of RVAE3IS, RVAE3OS, RVALE3IS and RVALE3OS, - * since we don't support flush-for-specific-ASID-only, - * flush-last-level-only or inner/outer specific flushes. - */ - - do_rvae_write(env, value, ARMMMUIdxBit_E3, true); -} - -static void tlbi_aa64_ripas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - do_rvae_write(env, value, ipas2e1_tlbmask(env, value), - tlb_force_broadcast(env)); -} - -static void tlbi_aa64_ripas2e1is_write(CPUARMState *env, - const ARMCPRegInfo *ri, - uint64_t value) -{ - do_rvae_write(env, value, ipas2e1_tlbmask(env, value), true); -} -#endif - static CPAccessResult aa64_zva_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { @@ -7312,133 +7116,6 @@ static const ARMCPRegInfo pauth_reginfo[] = { .fieldoffset = offsetof(CPUARMState, keys.apib.hi) }, }; -static const ARMCPRegInfo tlbirange_reginfo[] = { - { .name = "TLBI_RVAE1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 1, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIRVAE1IS, - .writefn = tlbi_aa64_rvae1is_write }, - { .name = "TLBI_RVAAE1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 3, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIRVAAE1IS, - .writefn = tlbi_aa64_rvae1is_write }, - { .name = "TLBI_RVALE1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 5, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIRVALE1IS, - .writefn = tlbi_aa64_rvae1is_write }, - { .name = "TLBI_RVAALE1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 7, - .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIRVAALE1IS, - .writefn = tlbi_aa64_rvae1is_write }, - { .name = "TLBI_RVAE1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 1, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIRVAE1OS, - .writefn = tlbi_aa64_rvae1is_write }, - { .name = "TLBI_RVAAE1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 3, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIRVAAE1OS, - .writefn = tlbi_aa64_rvae1is_write }, - { .name = "TLBI_RVALE1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 5, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIRVALE1OS, - .writefn = tlbi_aa64_rvae1is_write }, - { .name = "TLBI_RVAALE1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 7, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIRVAALE1OS, - .writefn = tlbi_aa64_rvae1is_write }, - { .name = "TLBI_RVAE1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 1, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIRVAE1, - .writefn = tlbi_aa64_rvae1_write }, - { .name = "TLBI_RVAAE1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 3, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIRVAAE1, - .writefn = tlbi_aa64_rvae1_write }, - { .name = "TLBI_RVALE1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 5, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIRVALE1, - .writefn = tlbi_aa64_rvae1_write }, - { .name = "TLBI_RVAALE1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 7, - .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIRVAALE1, - .writefn = tlbi_aa64_rvae1_write }, - { .name = "TLBI_RIPAS2E1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 2, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_ripas2e1is_write }, - { .name = "TLBI_RIPAS2LE1IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 6, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_ripas2e1is_write }, - { .name = "TLBI_RVAE2IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 2, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_rvae2is_write }, - { .name = "TLBI_RVALE2IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 2, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_rvae2is_write }, - { .name = "TLBI_RIPAS2E1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 2, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_ripas2e1_write }, - { .name = "TLBI_RIPAS2LE1", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 6, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_ripas2e1_write }, - { .name = "TLBI_RVAE2OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 5, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_rvae2is_write }, - { .name = "TLBI_RVALE2OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 5, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_rvae2is_write }, - { .name = "TLBI_RVAE2", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 6, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_rvae2_write }, - { .name = "TLBI_RVALE2", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 6, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_rvae2_write }, - { .name = "TLBI_RVAE3IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 2, .opc2 = 1, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_rvae3is_write }, - { .name = "TLBI_RVALE3IS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 2, .opc2 = 5, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_rvae3is_write }, - { .name = "TLBI_RVAE3OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 5, .opc2 = 1, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_rvae3is_write }, - { .name = "TLBI_RVALE3OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 5, .opc2 = 5, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_rvae3is_write }, - { .name = "TLBI_RVAE3", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 6, .opc2 = 1, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_rvae3_write }, - { .name = "TLBI_RVALE3", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 6, .opc2 = 5, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_rvae3_write }, -}; - static const ARMCPRegInfo tlbios_reginfo[] = { { .name = "TLBI_VMALLE1OS", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 0, @@ -9389,9 +9066,6 @@ void register_cp_regs_for_features(ARMCPU *cpu) if (cpu_isar_feature(aa64_rndr, cpu)) { define_arm_cp_regs(cpu, rndr_reginfo); } - if (cpu_isar_feature(aa64_tlbirange, cpu)) { - define_arm_cp_regs(cpu, tlbirange_reginfo); - } if (cpu_isar_feature(aa64_tlbios, cpu)) { define_arm_cp_regs(cpu, tlbios_reginfo); } diff --git a/target/arm/tcg/tlb-insns.c b/target/arm/tcg/tlb-insns.c index 528265404d..a273c6f4b5 100644 --- a/target/arm/tcg/tlb-insns.c +++ b/target/arm/tcg/tlb-insns.c @@ -6,6 +6,7 @@ * SPDX-License-Identifier: GPL-2.0-or-later */ #include "qemu/osdep.h" +#include "qemu/log.h" #include "exec/exec-all.h" #include "cpu.h" #include "internals.h" @@ -562,6 +563,329 @@ static const ARMCPRegInfo tlbi_el3_cp_reginfo[] = { .writefn = tlbi_aa64_vae3_write }, }; +#ifdef TARGET_AARCH64 +typedef struct { + uint64_t base; + uint64_t length; +} TLBIRange; + +static ARMGranuleSize tlbi_range_tg_to_gran_size(int tg) +{ + /* + * Note that the TLBI range TG field encoding differs from both + * TG0 and TG1 encodings. + */ + switch (tg) { + case 1: + return Gran4K; + case 2: + return Gran16K; + case 3: + return Gran64K; + default: + return GranInvalid; + } +} + +static TLBIRange tlbi_aa64_get_range(CPUARMState *env, ARMMMUIdx mmuidx, + uint64_t value) +{ + unsigned int page_size_granule, page_shift, num, scale, exponent; + /* Extract one bit to represent the va selector in use. */ + uint64_t select = sextract64(value, 36, 1); + ARMVAParameters param = aa64_va_parameters(env, select, mmuidx, true, false); + TLBIRange ret = { }; + ARMGranuleSize gran; + + page_size_granule = extract64(value, 46, 2); + gran = tlbi_range_tg_to_gran_size(page_size_granule); + + /* The granule encoded in value must match the granule in use. */ + if (gran != param.gran) { + qemu_log_mask(LOG_GUEST_ERROR, "Invalid tlbi page size granule %d\n", + page_size_granule); + return ret; + } + + page_shift = arm_granule_bits(gran); + num = extract64(value, 39, 5); + scale = extract64(value, 44, 2); + exponent = (5 * scale) + 1; + + ret.length = (num + 1) << (exponent + page_shift); + + if (param.select) { + ret.base = sextract64(value, 0, 37); + } else { + ret.base = extract64(value, 0, 37); + } + if (param.ds) { + /* + * With DS=1, BaseADDR is always shifted 16 so that it is able + * to address all 52 va bits. The input address is perforce + * aligned on a 64k boundary regardless of translation granule. + */ + page_shift = 16; + } + ret.base <<= page_shift; + + return ret; +} + +static void do_rvae_write(CPUARMState *env, uint64_t value, + int idxmap, bool synced) +{ + ARMMMUIdx one_idx = ARM_MMU_IDX_A | ctz32(idxmap); + TLBIRange range; + int bits; + + range = tlbi_aa64_get_range(env, one_idx, value); + bits = tlbbits_for_regime(env, one_idx, range.base); + + if (synced) { + tlb_flush_range_by_mmuidx_all_cpus_synced(env_cpu(env), + range.base, + range.length, + idxmap, + bits); + } else { + tlb_flush_range_by_mmuidx(env_cpu(env), range.base, + range.length, idxmap, bits); + } +} + +static void tlbi_aa64_rvae1_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, EL1&0. + * Currently handles all of RVAE1, RVAAE1, RVAALE1 and RVALE1, + * since we don't support flush-for-specific-ASID-only or + * flush-last-level-only. + */ + + do_rvae_write(env, value, vae1_tlbmask(env), + tlb_force_broadcast(env)); +} + +static void tlbi_aa64_rvae1is_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, Inner/Outer Shareable EL1&0. + * Currently handles all of RVAE1IS, RVAE1OS, RVAAE1IS, RVAAE1OS, + * RVAALE1IS, RVAALE1OS, RVALE1IS and RVALE1OS, since we don't support + * flush-for-specific-ASID-only, flush-last-level-only or inner/outer + * shareable specific flushes. + */ + + do_rvae_write(env, value, vae1_tlbmask(env), true); +} + +static void tlbi_aa64_rvae2_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, EL2. + * Currently handles all of RVAE2 and RVALE2, + * since we don't support flush-for-specific-ASID-only or + * flush-last-level-only. + */ + + do_rvae_write(env, value, vae2_tlbmask(env), + tlb_force_broadcast(env)); + + +} + +static void tlbi_aa64_rvae2is_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, Inner/Outer Shareable, EL2. + * Currently handles all of RVAE2IS, RVAE2OS, RVALE2IS and RVALE2OS, + * since we don't support flush-for-specific-ASID-only, + * flush-last-level-only or inner/outer shareable specific flushes. + */ + + do_rvae_write(env, value, vae2_tlbmask(env), true); + +} + +static void tlbi_aa64_rvae3_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, EL3. + * Currently handles all of RVAE3 and RVALE3, + * since we don't support flush-for-specific-ASID-only or + * flush-last-level-only. + */ + + do_rvae_write(env, value, ARMMMUIdxBit_E3, tlb_force_broadcast(env)); +} + +static void tlbi_aa64_rvae3is_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + /* + * Invalidate by VA range, EL3, Inner/Outer Shareable. + * Currently handles all of RVAE3IS, RVAE3OS, RVALE3IS and RVALE3OS, + * since we don't support flush-for-specific-ASID-only, + * flush-last-level-only or inner/outer specific flushes. + */ + + do_rvae_write(env, value, ARMMMUIdxBit_E3, true); +} + +static void tlbi_aa64_ripas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + do_rvae_write(env, value, ipas2e1_tlbmask(env, value), + tlb_force_broadcast(env)); +} + +static void tlbi_aa64_ripas2e1is_write(CPUARMState *env, + const ARMCPRegInfo *ri, + uint64_t value) +{ + do_rvae_write(env, value, ipas2e1_tlbmask(env, value), true); +} + +static const ARMCPRegInfo tlbirange_reginfo[] = { + { .name = "TLBI_RVAE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 1, + .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIRVAE1IS, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAAE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 3, + .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIRVAAE1IS, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVALE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 5, + .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIRVALE1IS, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAALE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 2, .opc2 = 7, + .access = PL1_W, .accessfn = access_ttlbis, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIRVAALE1IS, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 1, + .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIRVAE1OS, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAAE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 3, + .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIRVAAE1OS, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVALE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 5, + .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIRVALE1OS, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAALE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 5, .opc2 = 7, + .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIRVAALE1OS, + .writefn = tlbi_aa64_rvae1is_write }, + { .name = "TLBI_RVAE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 1, + .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIRVAE1, + .writefn = tlbi_aa64_rvae1_write }, + { .name = "TLBI_RVAAE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 3, + .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIRVAAE1, + .writefn = tlbi_aa64_rvae1_write }, + { .name = "TLBI_RVALE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 5, + .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIRVALE1, + .writefn = tlbi_aa64_rvae1_write }, + { .name = "TLBI_RVAALE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 6, .opc2 = 7, + .access = PL1_W, .accessfn = access_ttlb, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIRVAALE1, + .writefn = tlbi_aa64_rvae1_write }, + { .name = "TLBI_RIPAS2E1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 2, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_ripas2e1is_write }, + { .name = "TLBI_RIPAS2LE1IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 0, .opc2 = 6, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_ripas2e1is_write }, + { .name = "TLBI_RVAE2IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 2, .opc2 = 1, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_rvae2is_write }, + { .name = "TLBI_RVALE2IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 2, .opc2 = 5, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_rvae2is_write }, + { .name = "TLBI_RIPAS2E1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 2, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_ripas2e1_write }, + { .name = "TLBI_RIPAS2LE1", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 6, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_ripas2e1_write }, + { .name = "TLBI_RVAE2OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 5, .opc2 = 1, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_rvae2is_write }, + { .name = "TLBI_RVALE2OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 5, .opc2 = 5, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_rvae2is_write }, + { .name = "TLBI_RVAE2", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 6, .opc2 = 1, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_rvae2_write }, + { .name = "TLBI_RVALE2", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 6, .opc2 = 5, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_rvae2_write }, + { .name = "TLBI_RVAE3IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 2, .opc2 = 1, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3is_write }, + { .name = "TLBI_RVALE3IS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 2, .opc2 = 5, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3is_write }, + { .name = "TLBI_RVAE3OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 5, .opc2 = 1, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3is_write }, + { .name = "TLBI_RVALE3OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 5, .opc2 = 5, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3is_write }, + { .name = "TLBI_RVAE3", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 6, .opc2 = 1, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3_write }, + { .name = "TLBI_RVALE3", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 6, .opc2 = 5, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_rvae3_write }, +}; +#endif + void define_tlb_insn_regs(ARMCPU *cpu) { CPUARMState *env = &cpu->env; @@ -591,4 +915,9 @@ void define_tlb_insn_regs(ARMCPU *cpu) if (arm_feature(env, ARM_FEATURE_EL3)) { define_arm_cp_regs(cpu, tlbi_el3_cp_reginfo); } +#ifdef TARGET_AARCH64 + if (cpu_isar_feature(aa64_tlbirange, cpu)) { + define_arm_cp_regs(cpu, tlbirange_reginfo); + } +#endif } From b0f7cd357218a0697b03e009e3cbc74d22a8133b Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Tue, 10 Dec 2024 16:04:49 +0000 Subject: [PATCH 82/85] target/arm: Move the TLBI OS insns to tlb-insns.c. Move the TLBI OS insns across to tlb-insns.c. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson Message-id: 20241210160452.2427965-8-peter.maydell@linaro.org --- target/arm/helper.c | 80 -------------------------------------- target/arm/tcg/tlb-insns.c | 80 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 80 insertions(+), 80 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index 376aa9aecd..3f7d56e809 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -7116,83 +7116,6 @@ static const ARMCPRegInfo pauth_reginfo[] = { .fieldoffset = offsetof(CPUARMState, keys.apib.hi) }, }; -static const ARMCPRegInfo tlbios_reginfo[] = { - { .name = "TLBI_VMALLE1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 0, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIVMALLE1OS, - .writefn = tlbi_aa64_vmalle1is_write }, - { .name = "TLBI_VAE1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 1, - .fgt = FGT_TLBIVAE1OS, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_vae1is_write }, - { .name = "TLBI_ASIDE1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 2, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIASIDE1OS, - .writefn = tlbi_aa64_vmalle1is_write }, - { .name = "TLBI_VAAE1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 3, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIVAAE1OS, - .writefn = tlbi_aa64_vae1is_write }, - { .name = "TLBI_VALE1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 5, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIVALE1OS, - .writefn = tlbi_aa64_vae1is_write }, - { .name = "TLBI_VAALE1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 7, - .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, - .fgt = FGT_TLBIVAALE1OS, - .writefn = tlbi_aa64_vae1is_write }, - { .name = "TLBI_ALLE2OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 0, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_alle2is_write }, - { .name = "TLBI_VAE2OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 1, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_vae2is_write }, - { .name = "TLBI_ALLE1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 4, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_alle1is_write }, - { .name = "TLBI_VALE2OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 5, - .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, - .writefn = tlbi_aa64_vae2is_write }, - { .name = "TLBI_VMALLS12E1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 6, - .access = PL2_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_alle1is_write }, - { .name = "TLBI_IPAS2E1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 0, - .access = PL2_W, .type = ARM_CP_NOP }, - { .name = "TLBI_RIPAS2E1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 3, - .access = PL2_W, .type = ARM_CP_NOP }, - { .name = "TLBI_IPAS2LE1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 4, - .access = PL2_W, .type = ARM_CP_NOP }, - { .name = "TLBI_RIPAS2LE1OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 7, - .access = PL2_W, .type = ARM_CP_NOP }, - { .name = "TLBI_ALLE3OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 1, .opc2 = 0, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_alle3is_write }, - { .name = "TLBI_VAE3OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 1, .opc2 = 1, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_vae3is_write }, - { .name = "TLBI_VALE3OS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 1, .opc2 = 5, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_vae3is_write }, -}; - static uint64_t rndr_readfn(CPUARMState *env, const ARMCPRegInfo *ri) { Error *err = NULL; @@ -9066,9 +8989,6 @@ void register_cp_regs_for_features(ARMCPU *cpu) if (cpu_isar_feature(aa64_rndr, cpu)) { define_arm_cp_regs(cpu, rndr_reginfo); } - if (cpu_isar_feature(aa64_tlbios, cpu)) { - define_arm_cp_regs(cpu, tlbios_reginfo); - } /* Data Cache clean instructions up to PoP */ if (cpu_isar_feature(aa64_dcpop, cpu)) { define_one_arm_cp_reg(cpu, dcpop_reg); diff --git a/target/arm/tcg/tlb-insns.c b/target/arm/tcg/tlb-insns.c index a273c6f4b5..45ebfc512f 100644 --- a/target/arm/tcg/tlb-insns.c +++ b/target/arm/tcg/tlb-insns.c @@ -884,6 +884,83 @@ static const ARMCPRegInfo tlbirange_reginfo[] = { .access = PL3_W, .type = ARM_CP_NO_RAW, .writefn = tlbi_aa64_rvae3_write }, }; + +static const ARMCPRegInfo tlbios_reginfo[] = { + { .name = "TLBI_VMALLE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 0, + .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIVMALLE1OS, + .writefn = tlbi_aa64_vmalle1is_write }, + { .name = "TLBI_VAE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 1, + .fgt = FGT_TLBIVAE1OS, + .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_vae1is_write }, + { .name = "TLBI_ASIDE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 2, + .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIASIDE1OS, + .writefn = tlbi_aa64_vmalle1is_write }, + { .name = "TLBI_VAAE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 3, + .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIVAAE1OS, + .writefn = tlbi_aa64_vae1is_write }, + { .name = "TLBI_VALE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 5, + .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIVALE1OS, + .writefn = tlbi_aa64_vae1is_write }, + { .name = "TLBI_VAALE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 0, .crn = 8, .crm = 1, .opc2 = 7, + .access = PL1_W, .accessfn = access_ttlbos, .type = ARM_CP_NO_RAW, + .fgt = FGT_TLBIVAALE1OS, + .writefn = tlbi_aa64_vae1is_write }, + { .name = "TLBI_ALLE2OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 0, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_alle2is_write }, + { .name = "TLBI_VAE2OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 1, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_vae2is_write }, + { .name = "TLBI_ALLE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 4, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle1is_write }, + { .name = "TLBI_VALE2OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 5, + .access = PL2_W, .type = ARM_CP_NO_RAW | ARM_CP_EL3_NO_EL2_UNDEF, + .writefn = tlbi_aa64_vae2is_write }, + { .name = "TLBI_VMALLS12E1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 1, .opc2 = 6, + .access = PL2_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle1is_write }, + { .name = "TLBI_IPAS2E1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 0, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_RIPAS2E1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 3, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_IPAS2LE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 4, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_RIPAS2LE1OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 4, .crn = 8, .crm = 4, .opc2 = 7, + .access = PL2_W, .type = ARM_CP_NOP }, + { .name = "TLBI_ALLE3OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 1, .opc2 = 0, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_alle3is_write }, + { .name = "TLBI_VAE3OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 1, .opc2 = 1, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_vae3is_write }, + { .name = "TLBI_VALE3OS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 1, .opc2 = 5, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_vae3is_write }, +}; #endif void define_tlb_insn_regs(ARMCPU *cpu) @@ -919,5 +996,8 @@ void define_tlb_insn_regs(ARMCPU *cpu) if (cpu_isar_feature(aa64_tlbirange, cpu)) { define_arm_cp_regs(cpu, tlbirange_reginfo); } + if (cpu_isar_feature(aa64_tlbios, cpu)) { + define_arm_cp_regs(cpu, tlbios_reginfo); + } #endif } From 27fb860fd4f1524aac245a3e9849a06dae44bdba Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Tue, 10 Dec 2024 16:04:50 +0000 Subject: [PATCH 83/85] target/arm: Move small helper functions to tlb-insns.c The remaining functions that we temporarily made global are now used only from callsits in tlb-insns.c; move them across and make them file-local again. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson Message-id: 20241210160452.2427965-9-peter.maydell@linaro.org --- target/arm/cpregs.h | 34 ------ target/arm/helper.c | 220 ------------------------------------- target/arm/tcg/tlb-insns.c | 220 +++++++++++++++++++++++++++++++++++++ 3 files changed, 220 insertions(+), 254 deletions(-) diff --git a/target/arm/cpregs.h b/target/arm/cpregs.h index fe838bcfd9..cc7c54378f 100644 --- a/target/arm/cpregs.h +++ b/target/arm/cpregs.h @@ -1134,38 +1134,4 @@ static inline bool arm_cpreg_traps_in_nv(const ARMCPRegInfo *ri) return ri->opc1 == 4 || ri->opc1 == 5; } -/* - * Temporary declarations of functions until the move to tlb_insn_helper.c - * is complete and we can make the functions static again - */ -CPAccessResult access_ttlb(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread); -CPAccessResult access_ttlbis(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread); -CPAccessResult access_ttlbos(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread); -bool tlb_force_broadcast(CPUARMState *env); -int tlbbits_for_regime(CPUARMState *env, ARMMMUIdx mmu_idx, - uint64_t addr); -int vae1_tlbbits(CPUARMState *env, uint64_t addr); -int vae2_tlbbits(CPUARMState *env, uint64_t addr); -int vae1_tlbmask(CPUARMState *env); -int vae2_tlbmask(CPUARMState *env); -int ipas2e1_tlbmask(CPUARMState *env, int64_t value); -int e2_tlbmask(CPUARMState *env); -void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value); -void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value); -void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value); -void tlbi_aa64_alle2is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value); -void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value); -void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value); -void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value); - #endif /* TARGET_ARM_CPREGS_H */ diff --git a/target/arm/helper.c b/target/arm/helper.c index 3f7d56e809..cd9f865031 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -365,40 +365,6 @@ static CPAccessResult access_tacr(CPUARMState *env, const ARMCPRegInfo *ri, return CP_ACCESS_OK; } -/* Check for traps from EL1 due to HCR_EL2.TTLB. */ -CPAccessResult access_ttlb(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread) -{ - if (arm_current_el(env) == 1 && (arm_hcr_el2_eff(env) & HCR_TTLB)) { - return CP_ACCESS_TRAP_EL2; - } - return CP_ACCESS_OK; -} - -/* Check for traps from EL1 due to HCR_EL2.TTLB or TTLBIS. */ -CPAccessResult access_ttlbis(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread) -{ - if (arm_current_el(env) == 1 && - (arm_hcr_el2_eff(env) & (HCR_TTLB | HCR_TTLBIS))) { - return CP_ACCESS_TRAP_EL2; - } - return CP_ACCESS_OK; -} - -#ifdef TARGET_AARCH64 -/* Check for traps from EL1 due to HCR_EL2.TTLB or TTLBOS. */ -CPAccessResult access_ttlbos(CPUARMState *env, const ARMCPRegInfo *ri, - bool isread) -{ - if (arm_current_el(env) == 1 && - (arm_hcr_el2_eff(env) & (HCR_TTLB | HCR_TTLBOS))) { - return CP_ACCESS_TRAP_EL2; - } - return CP_ACCESS_OK; -} -#endif - static void dacr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { ARMCPU *cpu = env_archcpu(env); @@ -455,16 +421,6 @@ int alle1_tlbmask(CPUARMState *env) ARMMMUIdxBit_Stage2_S); } -/* - * Non-IS variants of TLB operations are upgraded to - * IS versions if we are at EL1 and HCR_EL2.FB is effectively set to - * force broadcast of these operations. - */ -bool tlb_force_broadcast(CPUARMState *env) -{ - return arm_current_el(env) == 1 && (arm_hcr_el2_eff(env) & HCR_FB); -} - static const ARMCPRegInfo cp_reginfo[] = { /* * Define the secure and non-secure FCSE identifier CP registers @@ -4680,182 +4636,6 @@ static CPAccessResult access_tocu(CPUARMState *env, const ARMCPRegInfo *ri, return do_cacheop_pou_access(env, HCR_TOCU | HCR_TPU); } -/* - * See: D4.7.2 TLB maintenance requirements and the TLB maintenance instructions - * Page D4-1736 (DDI0487A.b) - */ - -int vae1_tlbmask(CPUARMState *env) -{ - uint64_t hcr = arm_hcr_el2_eff(env); - uint16_t mask; - - assert(arm_feature(env, ARM_FEATURE_AARCH64)); - - if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) { - mask = ARMMMUIdxBit_E20_2 | - ARMMMUIdxBit_E20_2_PAN | - ARMMMUIdxBit_E20_0; - } else { - /* This is AArch64 only, so we don't need to touch the EL30_x TLBs */ - mask = ARMMMUIdxBit_E10_1 | - ARMMMUIdxBit_E10_1_PAN | - ARMMMUIdxBit_E10_0; - } - return mask; -} - -int vae2_tlbmask(CPUARMState *env) -{ - uint64_t hcr = arm_hcr_el2_eff(env); - uint16_t mask; - - if (hcr & HCR_E2H) { - mask = ARMMMUIdxBit_E20_2 | - ARMMMUIdxBit_E20_2_PAN | - ARMMMUIdxBit_E20_0; - } else { - mask = ARMMMUIdxBit_E2; - } - return mask; -} - -/* Return 56 if TBI is enabled, 64 otherwise. */ -int tlbbits_for_regime(CPUARMState *env, ARMMMUIdx mmu_idx, - uint64_t addr) -{ - uint64_t tcr = regime_tcr(env, mmu_idx); - int tbi = aa64_va_parameter_tbi(tcr, mmu_idx); - int select = extract64(addr, 55, 1); - - return (tbi >> select) & 1 ? 56 : 64; -} - -int vae1_tlbbits(CPUARMState *env, uint64_t addr) -{ - uint64_t hcr = arm_hcr_el2_eff(env); - ARMMMUIdx mmu_idx; - - assert(arm_feature(env, ARM_FEATURE_AARCH64)); - - /* Only the regime of the mmu_idx below is significant. */ - if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) { - mmu_idx = ARMMMUIdx_E20_0; - } else { - mmu_idx = ARMMMUIdx_E10_0; - } - - return tlbbits_for_regime(env, mmu_idx, addr); -} - -int vae2_tlbbits(CPUARMState *env, uint64_t addr) -{ - uint64_t hcr = arm_hcr_el2_eff(env); - ARMMMUIdx mmu_idx; - - /* - * Only the regime of the mmu_idx below is significant. - * Regime EL2&0 has two ranges with separate TBI configuration, while EL2 - * only has one. - */ - if (hcr & HCR_E2H) { - mmu_idx = ARMMMUIdx_E20_2; - } else { - mmu_idx = ARMMMUIdx_E2; - } - - return tlbbits_for_regime(env, mmu_idx, addr); -} - -void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - int mask = vae1_tlbmask(env); - - tlb_flush_by_mmuidx_all_cpus_synced(cs, mask); -} - -int e2_tlbmask(CPUARMState *env) -{ - return (ARMMMUIdxBit_E20_0 | - ARMMMUIdxBit_E20_2 | - ARMMMUIdxBit_E20_2_PAN | - ARMMMUIdxBit_E2); -} - -void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - int mask = alle1_tlbmask(env); - - tlb_flush_by_mmuidx_all_cpus_synced(cs, mask); -} - -void tlbi_aa64_alle2is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - int mask = e2_tlbmask(env); - - tlb_flush_by_mmuidx_all_cpus_synced(cs, mask); -} - -void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - - tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_E3); -} - -void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - int mask = vae1_tlbmask(env); - uint64_t pageaddr = sextract64(value << 12, 0, 56); - int bits = vae1_tlbbits(env, pageaddr); - - tlb_flush_page_bits_by_mmuidx_all_cpus_synced(cs, pageaddr, mask, bits); -} - -void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - int mask = vae2_tlbmask(env); - uint64_t pageaddr = sextract64(value << 12, 0, 56); - int bits = vae2_tlbbits(env, pageaddr); - - tlb_flush_page_bits_by_mmuidx_all_cpus_synced(cs, pageaddr, mask, bits); -} - -void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - uint64_t pageaddr = sextract64(value << 12, 0, 56); - int bits = tlbbits_for_regime(env, ARMMMUIdx_E3, pageaddr); - - tlb_flush_page_bits_by_mmuidx_all_cpus_synced(cs, pageaddr, - ARMMMUIdxBit_E3, bits); -} - -int ipas2e1_tlbmask(CPUARMState *env, int64_t value) -{ - /* - * The MSB of value is the NS field, which only applies if SEL2 - * is implemented and SCR_EL3.NS is not set (i.e. in secure mode). - */ - return (value >= 0 - && cpu_isar_feature(aa64_sel2, env_archcpu(env)) - && arm_is_secure_below_el3(env) - ? ARMMMUIdxBit_Stage2_S - : ARMMMUIdxBit_Stage2); -} - static CPAccessResult aa64_zva_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) { diff --git a/target/arm/tcg/tlb-insns.c b/target/arm/tcg/tlb-insns.c index 45ebfc512f..51b4756e31 100644 --- a/target/arm/tcg/tlb-insns.c +++ b/target/arm/tcg/tlb-insns.c @@ -13,6 +13,40 @@ #include "cpu-features.h" #include "cpregs.h" +/* Check for traps from EL1 due to HCR_EL2.TTLB. */ +static CPAccessResult access_ttlb(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread) +{ + if (arm_current_el(env) == 1 && (arm_hcr_el2_eff(env) & HCR_TTLB)) { + return CP_ACCESS_TRAP_EL2; + } + return CP_ACCESS_OK; +} + +/* Check for traps from EL1 due to HCR_EL2.TTLB or TTLBIS. */ +static CPAccessResult access_ttlbis(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread) +{ + if (arm_current_el(env) == 1 && + (arm_hcr_el2_eff(env) & (HCR_TTLB | HCR_TTLBIS))) { + return CP_ACCESS_TRAP_EL2; + } + return CP_ACCESS_OK; +} + +#ifdef TARGET_AARCH64 +/* Check for traps from EL1 due to HCR_EL2.TTLB or TTLBOS. */ +static CPAccessResult access_ttlbos(CPUARMState *env, const ARMCPRegInfo *ri, + bool isread) +{ + if (arm_current_el(env) == 1 && + (arm_hcr_el2_eff(env) & (HCR_TTLB | HCR_TTLBOS))) { + return CP_ACCESS_TRAP_EL2; + } + return CP_ACCESS_OK; +} +#endif + /* IS variants of TLB operations must affect all cores */ static void tlbiall_is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) @@ -46,6 +80,16 @@ static void tlbimvaa_is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_page_all_cpus_synced(cs, value & TARGET_PAGE_MASK); } +/* + * Non-IS variants of TLB operations are upgraded to + * IS versions if we are at EL1 and HCR_EL2.FB is effectively set to + * force broadcast of these operations. + */ +static bool tlb_force_broadcast(CPUARMState *env) +{ + return arm_current_el(env) == 1 && (arm_hcr_el2_eff(env) & HCR_FB); +} + static void tlbiall_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -170,6 +214,102 @@ static void tlbiall_hyp_is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_E2); } +/* + * See: D4.7.2 TLB maintenance requirements and the TLB maintenance instructions + * Page D4-1736 (DDI0487A.b) + */ + +static int vae1_tlbmask(CPUARMState *env) +{ + uint64_t hcr = arm_hcr_el2_eff(env); + uint16_t mask; + + assert(arm_feature(env, ARM_FEATURE_AARCH64)); + + if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) { + mask = ARMMMUIdxBit_E20_2 | + ARMMMUIdxBit_E20_2_PAN | + ARMMMUIdxBit_E20_0; + } else { + /* This is AArch64 only, so we don't need to touch the EL30_x TLBs */ + mask = ARMMMUIdxBit_E10_1 | + ARMMMUIdxBit_E10_1_PAN | + ARMMMUIdxBit_E10_0; + } + return mask; +} + +static int vae2_tlbmask(CPUARMState *env) +{ + uint64_t hcr = arm_hcr_el2_eff(env); + uint16_t mask; + + if (hcr & HCR_E2H) { + mask = ARMMMUIdxBit_E20_2 | + ARMMMUIdxBit_E20_2_PAN | + ARMMMUIdxBit_E20_0; + } else { + mask = ARMMMUIdxBit_E2; + } + return mask; +} + +/* Return 56 if TBI is enabled, 64 otherwise. */ +static int tlbbits_for_regime(CPUARMState *env, ARMMMUIdx mmu_idx, + uint64_t addr) +{ + uint64_t tcr = regime_tcr(env, mmu_idx); + int tbi = aa64_va_parameter_tbi(tcr, mmu_idx); + int select = extract64(addr, 55, 1); + + return (tbi >> select) & 1 ? 56 : 64; +} + +static int vae1_tlbbits(CPUARMState *env, uint64_t addr) +{ + uint64_t hcr = arm_hcr_el2_eff(env); + ARMMMUIdx mmu_idx; + + assert(arm_feature(env, ARM_FEATURE_AARCH64)); + + /* Only the regime of the mmu_idx below is significant. */ + if ((hcr & (HCR_E2H | HCR_TGE)) == (HCR_E2H | HCR_TGE)) { + mmu_idx = ARMMMUIdx_E20_0; + } else { + mmu_idx = ARMMMUIdx_E10_0; + } + + return tlbbits_for_regime(env, mmu_idx, addr); +} + +static int vae2_tlbbits(CPUARMState *env, uint64_t addr) +{ + uint64_t hcr = arm_hcr_el2_eff(env); + ARMMMUIdx mmu_idx; + + /* + * Only the regime of the mmu_idx below is significant. + * Regime EL2&0 has two ranges with separate TBI configuration, while EL2 + * only has one. + */ + if (hcr & HCR_E2H) { + mmu_idx = ARMMMUIdx_E20_2; + } else { + mmu_idx = ARMMMUIdx_E2; + } + + return tlbbits_for_regime(env, mmu_idx, addr); +} + +static void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + int mask = vae1_tlbmask(env); + + tlb_flush_by_mmuidx_all_cpus_synced(cs, mask); +} + static void tlbi_aa64_vmalle1_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -183,6 +323,14 @@ static void tlbi_aa64_vmalle1_write(CPUARMState *env, const ARMCPRegInfo *ri, } } +static int e2_tlbmask(CPUARMState *env) +{ + return (ARMMMUIdxBit_E20_0 | + ARMMMUIdxBit_E20_2 | + ARMMMUIdxBit_E20_2_PAN | + ARMMMUIdxBit_E2); +} + static void tlbi_aa64_alle1_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -210,6 +358,32 @@ static void tlbi_aa64_alle3_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx(cs, ARMMMUIdxBit_E3); } +static void tlbi_aa64_alle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + int mask = alle1_tlbmask(env); + + tlb_flush_by_mmuidx_all_cpus_synced(cs, mask); +} + +static void tlbi_aa64_alle2is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + int mask = e2_tlbmask(env); + + tlb_flush_by_mmuidx_all_cpus_synced(cs, mask); +} + +static void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + + tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_E3); +} + static void tlbi_aa64_vae2_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -241,6 +415,17 @@ static void tlbi_aa64_vae3_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_page_by_mmuidx(cs, pageaddr, ARMMMUIdxBit_E3); } +static void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + int mask = vae1_tlbmask(env); + uint64_t pageaddr = sextract64(value << 12, 0, 56); + int bits = vae1_tlbbits(env, pageaddr); + + tlb_flush_page_bits_by_mmuidx_all_cpus_synced(cs, pageaddr, mask, bits); +} + static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -262,6 +447,41 @@ static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri, } } +static void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + int mask = vae2_tlbmask(env); + uint64_t pageaddr = sextract64(value << 12, 0, 56); + int bits = vae2_tlbbits(env, pageaddr); + + tlb_flush_page_bits_by_mmuidx_all_cpus_synced(cs, pageaddr, mask, bits); +} + +static void tlbi_aa64_vae3is_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + uint64_t pageaddr = sextract64(value << 12, 0, 56); + int bits = tlbbits_for_regime(env, ARMMMUIdx_E3, pageaddr); + + tlb_flush_page_bits_by_mmuidx_all_cpus_synced(cs, pageaddr, + ARMMMUIdxBit_E3, bits); +} + +static int ipas2e1_tlbmask(CPUARMState *env, int64_t value) +{ + /* + * The MSB of value is the NS field, which only applies if SEL2 + * is implemented and SCR_EL3.NS is not set (i.e. in secure mode). + */ + return (value >= 0 + && cpu_isar_feature(aa64_sel2, env_archcpu(env)) + && arm_is_secure_below_el3(env) + ? ARMMMUIdxBit_Stage2_S + : ARMMMUIdxBit_Stage2); +} + static void tlbi_aa64_ipas2e1_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { From 0b7aefb9ebf5c0165aea5c8b4dde18508d015eff Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Tue, 10 Dec 2024 16:04:51 +0000 Subject: [PATCH 84/85] target/arm: Move RME TLB insns to tlb-insns.c Move the FEAT_RME specific TLB insns across to tlb-insns.c. Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson Message-id: 20241210160452.2427965-10-peter.maydell@linaro.org --- target/arm/helper.c | 38 -------------------------------- target/arm/tcg/tlb-insns.c | 45 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 45 insertions(+), 38 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index cd9f865031..910ae62c47 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -6525,14 +6525,6 @@ static const ARMCPRegInfo sme_reginfo[] = { .type = ARM_CP_CONST, .resetvalue = 0 }, }; -static void tlbi_aa64_paall_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - - tlb_flush(cs); -} - static void gpccr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -6550,14 +6542,6 @@ static void gpccr_reset(CPUARMState *env, const ARMCPRegInfo *ri) env_archcpu(env)->reset_l0gptsz); } -static void tlbi_aa64_paallos_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = env_cpu(env); - - tlb_flush_all_cpus_synced(cs); -} - static const ARMCPRegInfo rme_reginfo[] = { { .name = "GPCCR_EL3", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 6, .crn = 2, .crm = 1, .opc2 = 6, @@ -6569,28 +6553,6 @@ static const ARMCPRegInfo rme_reginfo[] = { { .name = "MFAR_EL3", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 6, .crn = 6, .crm = 0, .opc2 = 5, .access = PL3_RW, .fieldoffset = offsetof(CPUARMState, cp15.mfar_el3) }, - { .name = "TLBI_PAALL", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 7, .opc2 = 4, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_paall_write }, - { .name = "TLBI_PAALLOS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 1, .opc2 = 4, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_paallos_write }, - /* - * QEMU does not have a way to invalidate by physical address, thus - * invalidating a range of physical addresses is accomplished by - * flushing all tlb entries in the outer shareable domain, - * just like PAALLOS. - */ - { .name = "TLBI_RPALOS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 4, .opc2 = 7, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_paallos_write }, - { .name = "TLBI_RPAOS", .state = ARM_CP_STATE_AA64, - .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 4, .opc2 = 3, - .access = PL3_W, .type = ARM_CP_NO_RAW, - .writefn = tlbi_aa64_paallos_write }, { .name = "DC_CIPAPA", .state = ARM_CP_STATE_AA64, .opc0 = 1, .opc1 = 6, .crn = 7, .crm = 14, .opc2 = 1, .access = PL3_W, .type = ARM_CP_NOP }, diff --git a/target/arm/tcg/tlb-insns.c b/target/arm/tcg/tlb-insns.c index 51b4756e31..d20d32624d 100644 --- a/target/arm/tcg/tlb-insns.c +++ b/target/arm/tcg/tlb-insns.c @@ -1181,6 +1181,48 @@ static const ARMCPRegInfo tlbios_reginfo[] = { .access = PL3_W, .type = ARM_CP_NO_RAW, .writefn = tlbi_aa64_vae3is_write }, }; + +static void tlbi_aa64_paall_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + + tlb_flush(cs); +} + +static void tlbi_aa64_paallos_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = env_cpu(env); + + tlb_flush_all_cpus_synced(cs); +} + +static const ARMCPRegInfo tlbi_rme_reginfo[] = { + { .name = "TLBI_PAALL", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 7, .opc2 = 4, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_paall_write }, + { .name = "TLBI_PAALLOS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 1, .opc2 = 4, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_paallos_write }, + /* + * QEMU does not have a way to invalidate by physical address, thus + * invalidating a range of physical addresses is accomplished by + * flushing all tlb entries in the outer shareable domain, + * just like PAALLOS. + */ + { .name = "TLBI_RPALOS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 4, .opc2 = 7, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_paallos_write }, + { .name = "TLBI_RPAOS", .state = ARM_CP_STATE_AA64, + .opc0 = 1, .opc1 = 6, .crn = 8, .crm = 4, .opc2 = 3, + .access = PL3_W, .type = ARM_CP_NO_RAW, + .writefn = tlbi_aa64_paallos_write }, +}; + #endif void define_tlb_insn_regs(ARMCPU *cpu) @@ -1219,5 +1261,8 @@ void define_tlb_insn_regs(ARMCPU *cpu) if (cpu_isar_feature(aa64_tlbios, cpu)) { define_arm_cp_regs(cpu, tlbios_reginfo); } + if (cpu_isar_feature(aa64_rme, cpu)) { + define_arm_cp_regs(cpu, tlbi_rme_reginfo); + } #endif } From 48e652c4bd9570f6f24def25355cb3009a7300f8 Mon Sep 17 00:00:00 2001 From: Peter Maydell Date: Tue, 10 Dec 2024 16:04:52 +0000 Subject: [PATCH 85/85] target/arm: Simplify condition for tlbi_el2_cp_reginfo[] We currently register the tlbi_el2_cp_reginfo[] TLBI insns if EL2 is implemented, or if EL3 and v8 is implemented. This is a copy of the logic used for el2_cp_reginfo[], but for the specific case of the TLBI insns we can simplify it. This is because we do not need the "if EL2 does not exist but EL3 does then EL2 registers should exist and be RAZ/WI" handling here: all our cpregs are for instructions, which UNDEF when EL3 exists and EL2 does not. Simplify the condition down to just "if EL2 exists". This is not a behaviour change because: * for AArch64 insns we marked them with ARM_CP_EL3_NO_EL2_UNDEF, which meant that define_arm_cp_regs() would ignore them if EL2 wasn't present * for AArch32 insns, the .access = PL2_W meant that if EL2 was not present the only way to get at them was from AArch32 EL3; but we have no CPUs which have ARM_FEATURE_V8 but start in AArch32 Signed-off-by: Peter Maydell Reviewed-by: Richard Henderson Message-id: 20241210160452.2427965-11-peter.maydell@linaro.org --- target/arm/tcg/tlb-insns.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/target/arm/tcg/tlb-insns.c b/target/arm/tcg/tlb-insns.c index d20d32624d..0f67294edc 100644 --- a/target/arm/tcg/tlb-insns.c +++ b/target/arm/tcg/tlb-insns.c @@ -1246,9 +1246,7 @@ void define_tlb_insn_regs(ARMCPU *cpu) * ops (i.e. matching the condition for el2_cp_reginfo[] in * helper.c), but we will be able to simplify this later. */ - if (arm_feature(env, ARM_FEATURE_EL2) - || (arm_feature(env, ARM_FEATURE_EL3) - && arm_feature(env, ARM_FEATURE_V8))) { + if (arm_feature(env, ARM_FEATURE_EL2)) { define_arm_cp_regs(cpu, tlbi_el2_cp_reginfo); } if (arm_feature(env, ARM_FEATURE_EL3)) {