Mostly my decodetree stuff, but also some patches for various smaller bugs/features from others. thanks -- PMM The following changes since commit 53550e81e2cafe7c03a39526b95cd21b5194d9b1: Merge remote-tracking branch 'remotes/berrange/tags/qcrypto-next-pull-request' into staging (2020-06-15 16:36:34 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20200616 for you to fetch changes up to 64b397417a26509bcdff44ab94356a35c7901c79: hw: arm: Set vendor property for IMX SDHCI emulations (2020-06-16 10:32:29 +0100) ---------------------------------------------------------------- * hw: arm: Set vendor property for IMX SDHCI emulations * sd: sdhci: Implement basic vendor specific register support * hw/net/imx_fec: Convert debug fprintf() to trace events * target/arm/cpu: adjust virtual time for all KVM arm cpus * Implement configurable descriptor size in ftgmac100 * hw/misc/imx6ul_ccm: Implement non writable bits in CCM registers * target/arm: More Neon decodetree conversion work ---------------------------------------------------------------- Erik Smit (1): Implement configurable descriptor size in ftgmac100 Guenter Roeck (2): sd: sdhci: Implement basic vendor specific register support hw: arm: Set vendor property for IMX SDHCI emulations Jean-Christophe Dubois (2): hw/misc/imx6ul_ccm: Implement non writable bits in CCM registers hw/net/imx_fec: Convert debug fprintf() to trace events Peter Maydell (17): target/arm: Fix missing temp frees in do_vshll_2sh target/arm: Convert Neon 3-reg-diff prewidening ops to decodetree target/arm: Convert Neon 3-reg-diff narrowing ops to decodetree target/arm: Convert Neon 3-reg-diff VABAL, VABDL to decodetree target/arm: Convert Neon 3-reg-diff long multiplies target/arm: Convert Neon 3-reg-diff saturating doubling multiplies target/arm: Convert Neon 3-reg-diff polynomial VMULL target/arm: Add 'static' and 'const' annotations to VSHLL function arrays target/arm: Add missing TCG temp free in do_2shift_env_64() target/arm: Convert Neon 2-reg-scalar integer multiplies to decodetree target/arm: Convert Neon 2-reg-scalar float multiplies to decodetree target/arm: Convert Neon 2-reg-scalar VQDMULH, VQRDMULH to decodetree target/arm: Convert Neon 2-reg-scalar VQRDMLAH, VQRDMLSH to decodetree target/arm: Convert Neon 2-reg-scalar long multiplies to decodetree target/arm: Convert Neon VEXT to decodetree target/arm: Convert Neon VTBL, VTBX to decodetree target/arm: Convert Neon VDUP (scalar) to decodetree fangying (1): target/arm/cpu: adjust virtual time for all KVM arm cpus hw/sd/sdhci-internal.h | 5 + include/hw/sd/sdhci.h | 5 + target/arm/translate.h | 1 + target/arm/neon-dp.decode | 130 +++++ hw/arm/fsl-imx25.c | 6 + hw/arm/fsl-imx6.c | 6 + hw/arm/fsl-imx6ul.c | 2 + hw/arm/fsl-imx7.c | 2 + hw/misc/imx6ul_ccm.c | 76 ++- hw/net/ftgmac100.c | 26 +- hw/net/imx_fec.c | 106 ++-- hw/sd/sdhci.c | 18 +- target/arm/cpu.c | 6 +- target/arm/cpu64.c | 1 - target/arm/kvm.c | 21 +- target/arm/translate-neon.inc.c | 1148 ++++++++++++++++++++++++++++++++++++++- target/arm/translate.c | 684 +---------------------- hw/net/trace-events | 18 + 18 files changed, 1495 insertions(+), 766 deletions(-) The widenfn() in do_vshll_2sh() does not free the input 32-bit TCGv, so we need to do this in the calling code. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> --- target/arm/translate-neon.inc.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a, tmp = tcg_temp_new_i64(); widenfn(tmp, rm0); + tcg_temp_free_i32(rm0); if (a->shift != 0) { tcg_gen_shli_i64(tmp, tmp, a->shift); tcg_gen_andi_i64(tmp, tmp, ~widen_mask); @@ -XXX,XX +XXX,XX @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a, neon_store_reg64(tmp, a->vd); widenfn(tmp, rm1); + tcg_temp_free_i32(rm1); if (a->shift != 0) { tcg_gen_shli_i64(tmp, tmp, a->shift); tcg_gen_andi_i64(tmp, tmp, ~widen_mask); -- 2.20.1 Convert the "pre-widening" insns VADDL, VSUBL, VADDW and VSUBW in the Neon 3-registers-different-lengths group to decodetree. These insns work by widening one or both inputs to double their size, performing an add or subtract at the doubled size and then storing the double-size result. As usual, rather than copying the loop of the original decoder (which needs awkward code to avoid problems when source and destination registers overlap) we just unroll the two passes. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/neon-dp.decode | 43 +++++++++++++ target/arm/translate-neon.inc.c | 104 ++++++++++++++++++++++++++++++++ target/arm/translate.c | 16 ++--- 3 files changed, 151 insertions(+), 12 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ VCVT_FU_2sh 1111 001 1 1 . ...... .... 1111 0 . . 1 .... @2reg_vcvt # So we have a single decode line and check the cmode/op in the # trans function. Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm + +###################################################################### +# Within the "two registers, or three registers of different lengths" +# grouping ([23,4]=0b10), bits [21:20] are either part of the opcode +# decode: 0b11 for VEXT, two-reg-misc, VTBL, and duplicate-scalar; +# or they are a size field for the three-reg-different-lengths and +# two-reg-and-scalar insn groups (where size cannot be 0b11). This +# is slightly awkward for decodetree: we handle it with this +# non-exclusive group which contains within it two exclusive groups: +# one for the size=0b11 patterns, and one for the size-not-0b11 +# patterns. This allows us to check that none of the insns within +# each subgroup accidentally overlap each other. Note that all the +# trans functions for the size-not-0b11 patterns must check and +# return false for size==3. +###################################################################### +{ + # 0b11 subgroup will go here + + # Subgroup for size != 0b11 + [ + ################################################################## + # 3-reg-different-length grouping: + # 1111 001 U 1 D sz!=11 Vn:4 Vd:4 opc:4 N 0 M 0 Vm:4 + ################################################################## + + &3diff vm vn vd size + + @3diff .... ... . . . size:2 .... .... .... . . . . .... \ + &3diff vm=%vm_dp vn=%vn_dp vd=%vd_dp + + VADDL_S_3d 1111 001 0 1 . .. .... .... 0000 . 0 . 0 .... @3diff + VADDL_U_3d 1111 001 1 1 . .. .... .... 0000 . 0 . 0 .... @3diff + + VADDW_S_3d 1111 001 0 1 . .. .... .... 0001 . 0 . 0 .... @3diff + VADDW_U_3d 1111 001 1 1 . .. .... .... 0001 . 0 . 0 .... @3diff + + VSUBL_S_3d 1111 001 0 1 . .. .... .... 0010 . 0 . 0 .... @3diff + VSUBL_U_3d 1111 001 1 1 . .. .... .... 0010 . 0 . 0 .... @3diff + + VSUBW_S_3d 1111 001 0 1 . .. .... .... 0011 . 0 . 0 .... @3diff + VSUBW_U_3d 1111 001 1 1 . .. .... .... 0011 . 0 . 0 .... @3diff + ] +} diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_Vimm_1r(DisasContext *s, arg_1reg_imm *a) } return do_1reg_imm(s, a, fn); } + +static bool do_prewiden_3d(DisasContext *s, arg_3diff *a, + NeonGenWidenFn *widenfn, + NeonGenTwo64OpFn *opfn, + bool src1_wide) +{ + /* 3-regs different lengths, prewidening case (VADDL/VSUBL/VAADW/VSUBW) */ + TCGv_i64 rn0_64, rn1_64, rm_64; + TCGv_i32 rm; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if (!widenfn || !opfn) { + /* size == 3 case, which is an entirely different insn group */ + return false; + } + + if ((a->vd & 1) || (src1_wide && (a->vn & 1))) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + rn0_64 = tcg_temp_new_i64(); + rn1_64 = tcg_temp_new_i64(); + rm_64 = tcg_temp_new_i64(); + + if (src1_wide) { + neon_load_reg64(rn0_64, a->vn); + } else { + TCGv_i32 tmp = neon_load_reg(a->vn, 0); + widenfn(rn0_64, tmp); + tcg_temp_free_i32(tmp); + } + rm = neon_load_reg(a->vm, 0); + + widenfn(rm_64, rm); + tcg_temp_free_i32(rm); + opfn(rn0_64, rn0_64, rm_64); + + /* + * Load second pass inputs before storing the first pass result, to + * avoid incorrect results if a narrow input overlaps with the result. + */ + if (src1_wide) { + neon_load_reg64(rn1_64, a->vn + 1); + } else { + TCGv_i32 tmp = neon_load_reg(a->vn, 1); + widenfn(rn1_64, tmp); + tcg_temp_free_i32(tmp); + } + rm = neon_load_reg(a->vm, 1); + + neon_store_reg64(rn0_64, a->vd); + + widenfn(rm_64, rm); + tcg_temp_free_i32(rm); + opfn(rn1_64, rn1_64, rm_64); + neon_store_reg64(rn1_64, a->vd + 1); + + tcg_temp_free_i64(rn0_64); + tcg_temp_free_i64(rn1_64); + tcg_temp_free_i64(rm_64); + + return true; +} + +#define DO_PREWIDEN(INSN, S, EXT, OP, SRC1WIDE) \ + static bool trans_##INSN##_3d(DisasContext *s, arg_3diff *a) \ + { \ + static NeonGenWidenFn * const widenfn[] = { \ + gen_helper_neon_widen_##S##8, \ + gen_helper_neon_widen_##S##16, \ + tcg_gen_##EXT##_i32_i64, \ + NULL, \ + }; \ + static NeonGenTwo64OpFn * const addfn[] = { \ + gen_helper_neon_##OP##l_u16, \ + gen_helper_neon_##OP##l_u32, \ + tcg_gen_##OP##_i64, \ + NULL, \ + }; \ + return do_prewiden_3d(s, a, widenfn[a->size], \ + addfn[a->size], SRC1WIDE); \ + } + +DO_PREWIDEN(VADDL_S, s, ext, add, false) +DO_PREWIDEN(VADDL_U, u, extu, add, false) +DO_PREWIDEN(VSUBL_S, s, ext, sub, false) +DO_PREWIDEN(VSUBL_U, u, extu, sub, false) +DO_PREWIDEN(VADDW_S, s, ext, add, true) +DO_PREWIDEN(VADDW_U, u, extu, add, true) +DO_PREWIDEN(VSUBW_S, s, ext, sub, true) +DO_PREWIDEN(VSUBW_U, u, extu, sub, true) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) /* Three registers of different lengths. */ int src1_wide; int src2_wide; - int prewiden; /* undefreq: bit 0 : UNDEF if size == 0 * bit 1 : UNDEF if size == 1 * bit 2 : UNDEF if size == 2 @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) int undefreq; /* prewiden, src1_wide, src2_wide, undefreq */ static const int neon_3reg_wide[16][4] = { - {1, 0, 0, 0}, /* VADDL */ - {1, 1, 0, 0}, /* VADDW */ - {1, 0, 0, 0}, /* VSUBL */ - {1, 1, 0, 0}, /* VSUBW */ + {0, 0, 0, 7}, /* VADDL: handled by decodetree */ + {0, 0, 0, 7}, /* VADDW: handled by decodetree */ + {0, 0, 0, 7}, /* VSUBL: handled by decodetree */ + {0, 0, 0, 7}, /* VSUBW: handled by decodetree */ {0, 1, 1, 0}, /* VADDHN */ {0, 0, 0, 0}, /* VABAL */ {0, 1, 1, 0}, /* VSUBHN */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) {0, 0, 0, 7}, /* Reserved: always UNDEF */ }; - prewiden = neon_3reg_wide[op][0]; src1_wide = neon_3reg_wide[op][1]; src2_wide = neon_3reg_wide[op][2]; undefreq = neon_3reg_wide[op][3]; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } else { tmp = neon_load_reg(rn, pass); } - if (prewiden) { - gen_neon_widen(cpu_V0, tmp, size, u); - } } if (src2_wide) { neon_load_reg64(cpu_V1, rm + pass); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } else { tmp2 = neon_load_reg(rm, pass); } - if (prewiden) { - gen_neon_widen(cpu_V1, tmp2, size, u); - } } switch (op) { case 0: case 1: case 4: /* VADDL, VADDW, VADDHN, VRADDHN */ -- 2.20.1 Convert the narrow-to-high-half insns VADDHN, VSUBHN, VRADDHN, VRSUBHN in the Neon 3-registers-different-lengths group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/neon-dp.decode | 6 +++ target/arm/translate-neon.inc.c | 87 +++++++++++++++++++++++++++++++ target/arm/translate.c | 91 ++++----------------------------- 3 files changed, 104 insertions(+), 80 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm VSUBW_S_3d 1111 001 0 1 . .. .... .... 0011 . 0 . 0 .... @3diff VSUBW_U_3d 1111 001 1 1 . .. .... .... 0011 . 0 . 0 .... @3diff + + VADDHN_3d 1111 001 0 1 . .. .... .... 0100 . 0 . 0 .... @3diff + VRADDHN_3d 1111 001 1 1 . .. .... .... 0100 . 0 . 0 .... @3diff + + VSUBHN_3d 1111 001 0 1 . .. .... .... 0110 . 0 . 0 .... @3diff + VRSUBHN_3d 1111 001 1 1 . .. .... .... 0110 . 0 . 0 .... @3diff ] } diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_PREWIDEN(VADDW_S, s, ext, add, true) DO_PREWIDEN(VADDW_U, u, extu, add, true) DO_PREWIDEN(VSUBW_S, s, ext, sub, true) DO_PREWIDEN(VSUBW_U, u, extu, sub, true) + +static bool do_narrow_3d(DisasContext *s, arg_3diff *a, + NeonGenTwo64OpFn *opfn, NeonGenNarrowFn *narrowfn) +{ + /* 3-regs different lengths, narrowing (VADDHN/VSUBHN/VRADDHN/VRSUBHN) */ + TCGv_i64 rn_64, rm_64; + TCGv_i32 rd0, rd1; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if (!opfn || !narrowfn) { + /* size == 3 case, which is an entirely different insn group */ + return false; + } + + if ((a->vn | a->vm) & 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + rn_64 = tcg_temp_new_i64(); + rm_64 = tcg_temp_new_i64(); + rd0 = tcg_temp_new_i32(); + rd1 = tcg_temp_new_i32(); + + neon_load_reg64(rn_64, a->vn); + neon_load_reg64(rm_64, a->vm); + + opfn(rn_64, rn_64, rm_64); + + narrowfn(rd0, rn_64); + + neon_load_reg64(rn_64, a->vn + 1); + neon_load_reg64(rm_64, a->vm + 1); + + opfn(rn_64, rn_64, rm_64); + + narrowfn(rd1, rn_64); + + neon_store_reg(a->vd, 0, rd0); + neon_store_reg(a->vd, 1, rd1); + + tcg_temp_free_i64(rn_64); + tcg_temp_free_i64(rm_64); + + return true; +} + +#define DO_NARROW_3D(INSN, OP, NARROWTYPE, EXTOP) \ + 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_##OP##_i64, \ + NULL, \ + }; \ + static NeonGenNarrowFn * const narrowfn[] = { \ + gen_helper_neon_##NARROWTYPE##_high_u8, \ + gen_helper_neon_##NARROWTYPE##_high_u16, \ + EXTOP, \ + NULL, \ + }; \ + return do_narrow_3d(s, a, addfn[a->size], narrowfn[a->size]); \ + } + +static void gen_narrow_round_high_u32(TCGv_i32 rd, TCGv_i64 rn) +{ + tcg_gen_addi_i64(rn, rn, 1u << 31); + tcg_gen_extrh_i64_i32(rd, rn); +} + +DO_NARROW_3D(VADDHN, add, narrow, tcg_gen_extrh_i64_i32) +DO_NARROW_3D(VSUBHN, sub, narrow, tcg_gen_extrh_i64_i32) +DO_NARROW_3D(VRADDHN, add, narrow_round, gen_narrow_round_high_u32) +DO_NARROW_3D(VRSUBHN, sub, narrow_round, gen_narrow_round_high_u32) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static inline void gen_neon_addl(int size) } } -static inline void gen_neon_subl(int size) -{ - switch (size) { - case 0: gen_helper_neon_subl_u16(CPU_V001); break; - case 1: gen_helper_neon_subl_u32(CPU_V001); break; - case 2: tcg_gen_sub_i64(CPU_V001); break; - default: abort(); - } -} - static inline void gen_neon_negl(TCGv_i64 var, int size) { switch (size) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) op = (insn >> 8) & 0xf; if ((insn & (1 << 6)) == 0) { /* Three registers of different lengths. */ - int src1_wide; - int src2_wide; /* undefreq: bit 0 : UNDEF if size == 0 * bit 1 : UNDEF if size == 1 * bit 2 : UNDEF if size == 2 @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) {0, 0, 0, 7}, /* VADDW: handled by decodetree */ {0, 0, 0, 7}, /* VSUBL: handled by decodetree */ {0, 0, 0, 7}, /* VSUBW: handled by decodetree */ - {0, 1, 1, 0}, /* VADDHN */ + {0, 0, 0, 7}, /* VADDHN: handled by decodetree */ {0, 0, 0, 0}, /* VABAL */ - {0, 1, 1, 0}, /* VSUBHN */ + {0, 0, 0, 7}, /* VSUBHN: handled by decodetree */ {0, 0, 0, 0}, /* VABDL */ {0, 0, 0, 0}, /* VMLAL */ {0, 0, 0, 9}, /* VQDMLAL */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) {0, 0, 0, 7}, /* Reserved: always UNDEF */ }; - src1_wide = neon_3reg_wide[op][1]; - src2_wide = neon_3reg_wide[op][2]; undefreq = neon_3reg_wide[op][3]; if ((undefreq & (1 << size)) || ((undefreq & 8) && u)) { return 1; } - if ((src1_wide && (rn & 1)) || - (src2_wide && (rm & 1)) || - (!src2_wide && (rd & 1))) { + if (rd & 1) { return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) /* Avoid overlapping operands. Wide source operands are always aligned so will never overlap with wide destinations in problematic ways. */ - if (rd == rm && !src2_wide) { + if (rd == rm) { tmp = neon_load_reg(rm, 1); neon_store_scratch(2, tmp); - } else if (rd == rn && !src1_wide) { + } else if (rd == rn) { tmp = neon_load_reg(rn, 1); neon_store_scratch(2, tmp); } tmp3 = NULL; for (pass = 0; pass < 2; pass++) { - if (src1_wide) { - neon_load_reg64(cpu_V0, rn + pass); - tmp = NULL; + if (pass == 1 && rd == rn) { + tmp = neon_load_scratch(2); } else { - if (pass == 1 && rd == rn) { - tmp = neon_load_scratch(2); - } else { - tmp = neon_load_reg(rn, pass); - } + tmp = neon_load_reg(rn, pass); } - if (src2_wide) { - neon_load_reg64(cpu_V1, rm + pass); - tmp2 = NULL; + if (pass == 1 && rd == rm) { + tmp2 = neon_load_scratch(2); } else { - if (pass == 1 && rd == rm) { - tmp2 = neon_load_scratch(2); - } else { - tmp2 = neon_load_reg(rm, pass); - } + tmp2 = neon_load_reg(rm, pass); } switch (op) { - case 0: case 1: case 4: /* VADDL, VADDW, VADDHN, VRADDHN */ - gen_neon_addl(size); - break; - case 2: case 3: case 6: /* VSUBL, VSUBW, VSUBHN, VRSUBHN */ - gen_neon_subl(size); - break; case 5: case 7: /* VABAL, VABDL */ switch ((size << 1) | u) { case 0: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) abort(); } neon_store_reg64(cpu_V0, rd + pass); - } else if (op == 4 || op == 6) { - /* Narrowing operation. */ - tmp = tcg_temp_new_i32(); - if (!u) { - switch (size) { - case 0: - gen_helper_neon_narrow_high_u8(tmp, cpu_V0); - break; - case 1: - gen_helper_neon_narrow_high_u16(tmp, cpu_V0); - break; - case 2: - tcg_gen_extrh_i64_i32(tmp, cpu_V0); - break; - default: abort(); - } - } else { - switch (size) { - case 0: - gen_helper_neon_narrow_round_high_u8(tmp, cpu_V0); - break; - case 1: - gen_helper_neon_narrow_round_high_u16(tmp, cpu_V0); - break; - case 2: - tcg_gen_addi_i64(cpu_V0, cpu_V0, 1u << 31); - tcg_gen_extrh_i64_i32(tmp, cpu_V0); - break; - default: abort(); - } - } - if (pass == 0) { - tmp3 = tmp; - } else { - neon_store_reg(rd, 0, tmp3); - neon_store_reg(rd, 1, tmp); - } } else { /* Write back the result. */ neon_store_reg64(cpu_V0, rd + pass); -- 2.20.1 Convert the Neon 3-reg-diff insns VABAL and VABDL to decodetree. Like almost all the remaining insns in this group, these are a combination of a two-input operation which returns a double width result and then a possible accumulation of that double width result into the destination. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate.h | 1 + target/arm/neon-dp.decode | 6 ++ target/arm/translate-neon.inc.c | 132 ++++++++++++++++++++++++++++++++ target/arm/translate.c | 31 +------- 4 files changed, 142 insertions(+), 28 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef void NeonGenTwo64OpEnvFn(TCGv_i64, TCGv_ptr, TCGv_i64, TCGv_i64); typedef void NeonGenNarrowFn(TCGv_i32, TCGv_i64); typedef void NeonGenNarrowEnvFn(TCGv_i32, TCGv_ptr, TCGv_i64); typedef void NeonGenWidenFn(TCGv_i64, TCGv_i32); +typedef void NeonGenTwoOpWidenFn(TCGv_i64, TCGv_i32, TCGv_i32); typedef void NeonGenTwoSingleOPFn(TCGv_i32, TCGv_i32, TCGv_i32, TCGv_ptr); typedef void NeonGenTwoDoubleOPFn(TCGv_i64, TCGv_i64, TCGv_i64, TCGv_ptr); typedef void NeonGenOneOpFn(TCGv_i64, TCGv_i64); diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm VADDHN_3d 1111 001 0 1 . .. .... .... 0100 . 0 . 0 .... @3diff VRADDHN_3d 1111 001 1 1 . .. .... .... 0100 . 0 . 0 .... @3diff + VABAL_S_3d 1111 001 0 1 . .. .... .... 0101 . 0 . 0 .... @3diff + VABAL_U_3d 1111 001 1 1 . .. .... .... 0101 . 0 . 0 .... @3diff + VSUBHN_3d 1111 001 0 1 . .. .... .... 0110 . 0 . 0 .... @3diff VRSUBHN_3d 1111 001 1 1 . .. .... .... 0110 . 0 . 0 .... @3diff + + VABDL_S_3d 1111 001 0 1 . .. .... .... 0111 . 0 . 0 .... @3diff + VABDL_U_3d 1111 001 1 1 . .. .... .... 0111 . 0 . 0 .... @3diff ] } diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_NARROW_3D(VADDHN, add, narrow, tcg_gen_extrh_i64_i32) DO_NARROW_3D(VSUBHN, sub, narrow, tcg_gen_extrh_i64_i32) DO_NARROW_3D(VRADDHN, add, narrow_round, gen_narrow_round_high_u32) DO_NARROW_3D(VRSUBHN, sub, narrow_round, gen_narrow_round_high_u32) + +static bool do_long_3d(DisasContext *s, arg_3diff *a, + NeonGenTwoOpWidenFn *opfn, + NeonGenTwo64OpFn *accfn) +{ + /* + * 3-regs different lengths, long operations. + * These perform an operation on two inputs that returns a double-width + * result, and then possibly perform an accumulation operation of + * that result into the double-width destination. + */ + TCGv_i64 rd0, rd1, tmp; + TCGv_i32 rn, rm; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if (!opfn) { + /* size == 3 case, which is an entirely different insn group */ + return false; + } + + if (a->vd & 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + rd0 = tcg_temp_new_i64(); + rd1 = tcg_temp_new_i64(); + + rn = neon_load_reg(a->vn, 0); + rm = neon_load_reg(a->vm, 0); + opfn(rd0, rn, rm); + tcg_temp_free_i32(rn); + tcg_temp_free_i32(rm); + + rn = neon_load_reg(a->vn, 1); + rm = neon_load_reg(a->vm, 1); + opfn(rd1, rn, rm); + tcg_temp_free_i32(rn); + tcg_temp_free_i32(rm); + + /* Don't store results until after all loads: they might overlap */ + if (accfn) { + tmp = tcg_temp_new_i64(); + neon_load_reg64(tmp, a->vd); + accfn(tmp, tmp, rd0); + neon_store_reg64(tmp, a->vd); + neon_load_reg64(tmp, a->vd + 1); + accfn(tmp, tmp, rd1); + neon_store_reg64(tmp, a->vd + 1); + tcg_temp_free_i64(tmp); + } else { + neon_store_reg64(rd0, a->vd); + neon_store_reg64(rd1, a->vd + 1); + } + + tcg_temp_free_i64(rd0); + tcg_temp_free_i64(rd1); + + return true; +} + +static bool trans_VABDL_S_3d(DisasContext *s, arg_3diff *a) +{ + static NeonGenTwoOpWidenFn * const opfn[] = { + gen_helper_neon_abdl_s16, + gen_helper_neon_abdl_s32, + gen_helper_neon_abdl_s64, + NULL, + }; + + return do_long_3d(s, a, opfn[a->size], NULL); +} + +static bool trans_VABDL_U_3d(DisasContext *s, arg_3diff *a) +{ + static NeonGenTwoOpWidenFn * const opfn[] = { + gen_helper_neon_abdl_u16, + gen_helper_neon_abdl_u32, + gen_helper_neon_abdl_u64, + NULL, + }; + + return do_long_3d(s, a, opfn[a->size], NULL); +} + +static bool trans_VABAL_S_3d(DisasContext *s, arg_3diff *a) +{ + static NeonGenTwoOpWidenFn * const opfn[] = { + gen_helper_neon_abdl_s16, + gen_helper_neon_abdl_s32, + gen_helper_neon_abdl_s64, + NULL, + }; + static NeonGenTwo64OpFn * const addfn[] = { + gen_helper_neon_addl_u16, + gen_helper_neon_addl_u32, + tcg_gen_add_i64, + NULL, + }; + + return do_long_3d(s, a, opfn[a->size], addfn[a->size]); +} + +static bool trans_VABAL_U_3d(DisasContext *s, arg_3diff *a) +{ + static NeonGenTwoOpWidenFn * const opfn[] = { + gen_helper_neon_abdl_u16, + gen_helper_neon_abdl_u32, + gen_helper_neon_abdl_u64, + NULL, + }; + static NeonGenTwo64OpFn * const addfn[] = { + gen_helper_neon_addl_u16, + gen_helper_neon_addl_u32, + tcg_gen_add_i64, + NULL, + }; + + return do_long_3d(s, a, opfn[a->size], addfn[a->size]); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) {0, 0, 0, 7}, /* VSUBL: handled by decodetree */ {0, 0, 0, 7}, /* VSUBW: handled by decodetree */ {0, 0, 0, 7}, /* VADDHN: handled by decodetree */ - {0, 0, 0, 0}, /* VABAL */ + {0, 0, 0, 7}, /* VABAL */ {0, 0, 0, 7}, /* VSUBHN: handled by decodetree */ - {0, 0, 0, 0}, /* VABDL */ + {0, 0, 0, 7}, /* VABDL */ {0, 0, 0, 0}, /* VMLAL */ {0, 0, 0, 9}, /* VQDMLAL */ {0, 0, 0, 0}, /* VMLSL */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = neon_load_reg(rm, pass); } switch (op) { - case 5: case 7: /* VABAL, VABDL */ - switch ((size << 1) | u) { - case 0: - gen_helper_neon_abdl_s16(cpu_V0, tmp, tmp2); - break; - case 1: - gen_helper_neon_abdl_u16(cpu_V0, tmp, tmp2); - break; - case 2: - gen_helper_neon_abdl_s32(cpu_V0, tmp, tmp2); - break; - case 3: - gen_helper_neon_abdl_u32(cpu_V0, tmp, tmp2); - break; - case 4: - gen_helper_neon_abdl_s64(cpu_V0, tmp, tmp2); - break; - case 5: - gen_helper_neon_abdl_u64(cpu_V0, tmp, tmp2); - break; - default: abort(); - } - tcg_temp_free_i32(tmp2); - tcg_temp_free_i32(tmp); - break; case 8: case 9: case 10: case 11: case 12: case 13: /* VMLAL, VQDMLAL, VMLSL, VQDMLSL, VMULL, VQDMULL */ gen_neon_mull(cpu_V0, tmp, tmp2, size, u); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 10: /* VMLSL */ gen_neon_negl(cpu_V0, size); /* Fall through */ - case 5: case 8: /* VABAL, VMLAL */ + case 8: /* VABAL, VMLAL */ gen_neon_addl(size); break; case 9: case 11: /* VQDMLAL, VQDMLSL */ -- 2.20.1 Convert the Neon 3-reg-diff insns VMULL, VMLAL and VMLSL; these perform a 32x32->64 multiply with possible accumulate. Note that for VMLSL we do the accumulate directly with a subtraction rather than doing a negate-then-add as the old code did. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/neon-dp.decode | 9 +++++ target/arm/translate-neon.inc.c | 71 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 21 +++------- 3 files changed, 86 insertions(+), 15 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm VABDL_S_3d 1111 001 0 1 . .. .... .... 0111 . 0 . 0 .... @3diff VABDL_U_3d 1111 001 1 1 . .. .... .... 0111 . 0 . 0 .... @3diff + + VMLAL_S_3d 1111 001 0 1 . .. .... .... 1000 . 0 . 0 .... @3diff + VMLAL_U_3d 1111 001 1 1 . .. .... .... 1000 . 0 . 0 .... @3diff + + VMLSL_S_3d 1111 001 0 1 . .. .... .... 1010 . 0 . 0 .... @3diff + VMLSL_U_3d 1111 001 1 1 . .. .... .... 1010 . 0 . 0 .... @3diff + + VMULL_S_3d 1111 001 0 1 . .. .... .... 1100 . 0 . 0 .... @3diff + VMULL_U_3d 1111 001 1 1 . .. .... .... 1100 . 0 . 0 .... @3diff ] } diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VABAL_U_3d(DisasContext *s, arg_3diff *a) return do_long_3d(s, a, opfn[a->size], addfn[a->size]); } + +static void gen_mull_s32(TCGv_i64 rd, TCGv_i32 rn, TCGv_i32 rm) +{ + TCGv_i32 lo = tcg_temp_new_i32(); + TCGv_i32 hi = tcg_temp_new_i32(); + + tcg_gen_muls2_i32(lo, hi, rn, rm); + tcg_gen_concat_i32_i64(rd, lo, hi); + + tcg_temp_free_i32(lo); + tcg_temp_free_i32(hi); +} + +static void gen_mull_u32(TCGv_i64 rd, TCGv_i32 rn, TCGv_i32 rm) +{ + TCGv_i32 lo = tcg_temp_new_i32(); + TCGv_i32 hi = tcg_temp_new_i32(); + + tcg_gen_mulu2_i32(lo, hi, rn, rm); + tcg_gen_concat_i32_i64(rd, lo, hi); + + tcg_temp_free_i32(lo); + tcg_temp_free_i32(hi); +} + +static bool trans_VMULL_S_3d(DisasContext *s, arg_3diff *a) +{ + static NeonGenTwoOpWidenFn * const opfn[] = { + gen_helper_neon_mull_s8, + gen_helper_neon_mull_s16, + gen_mull_s32, + NULL, + }; + + return do_long_3d(s, a, opfn[a->size], NULL); +} + +static bool trans_VMULL_U_3d(DisasContext *s, arg_3diff *a) +{ + static NeonGenTwoOpWidenFn * const opfn[] = { + gen_helper_neon_mull_u8, + gen_helper_neon_mull_u16, + gen_mull_u32, + NULL, + }; + + return do_long_3d(s, a, opfn[a->size], NULL); +} + +#define DO_VMLAL(INSN,MULL,ACC) \ + static bool trans_##INSN##_3d(DisasContext *s, arg_3diff *a) \ + { \ + static NeonGenTwoOpWidenFn * const opfn[] = { \ + gen_helper_neon_##MULL##8, \ + gen_helper_neon_##MULL##16, \ + gen_##MULL##32, \ + NULL, \ + }; \ + static NeonGenTwo64OpFn * const accfn[] = { \ + gen_helper_neon_##ACC##l_u16, \ + gen_helper_neon_##ACC##l_u32, \ + tcg_gen_##ACC##_i64, \ + NULL, \ + }; \ + return do_long_3d(s, a, opfn[a->size], accfn[a->size]); \ + } + +DO_VMLAL(VMLAL_S,mull_s,add) +DO_VMLAL(VMLAL_U,mull_u,add) +DO_VMLAL(VMLSL_S,mull_s,sub) +DO_VMLAL(VMLSL_U,mull_u,sub) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) {0, 0, 0, 7}, /* VABAL */ {0, 0, 0, 7}, /* VSUBHN: handled by decodetree */ {0, 0, 0, 7}, /* VABDL */ - {0, 0, 0, 0}, /* VMLAL */ + {0, 0, 0, 7}, /* VMLAL */ {0, 0, 0, 9}, /* VQDMLAL */ - {0, 0, 0, 0}, /* VMLSL */ + {0, 0, 0, 7}, /* VMLSL */ {0, 0, 0, 9}, /* VQDMLSL */ - {0, 0, 0, 0}, /* Integer VMULL */ + {0, 0, 0, 7}, /* Integer VMULL */ {0, 0, 0, 9}, /* VQDMULL */ {0, 0, 0, 0xa}, /* Polynomial VMULL */ {0, 0, 0, 7}, /* Reserved: always UNDEF */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = neon_load_reg(rm, pass); } switch (op) { - case 8: case 9: case 10: case 11: case 12: case 13: - /* VMLAL, VQDMLAL, VMLSL, VQDMLSL, VMULL, VQDMULL */ + case 9: case 11: case 13: + /* VQDMLAL, VQDMLSL, VQDMULL */ gen_neon_mull(cpu_V0, tmp, tmp2, size, u); break; default: /* 15 is RESERVED: caught earlier */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) /* VQDMULL */ gen_neon_addl_saturate(cpu_V0, cpu_V0, size); neon_store_reg64(cpu_V0, rd + pass); - } else if (op == 5 || (op >= 8 && op <= 11)) { + } else { /* Accumulate. */ neon_load_reg64(cpu_V1, rd + pass); switch (op) { - case 10: /* VMLSL */ - gen_neon_negl(cpu_V0, size); - /* Fall through */ - case 8: /* VABAL, VMLAL */ - gen_neon_addl(size); - break; case 9: case 11: /* VQDMLAL, VQDMLSL */ gen_neon_addl_saturate(cpu_V0, cpu_V0, size); if (op == 11) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) abort(); } neon_store_reg64(cpu_V0, rd + pass); - } else { - /* Write back the result. */ - neon_store_reg64(cpu_V0, rd + pass); } } } else { -- 2.20.1 Convert the Neon 3-reg-diff insns VQDMULL, VQDMLAL and VQDMLSL: these are all saturating doubling long multiplies with a possible accumulate step. These are the last insns in the group which use the pass-over-each elements loop, so we can delete that code. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/neon-dp.decode | 6 +++ target/arm/translate-neon.inc.c | 82 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 59 ++---------------------- 3 files changed, 92 insertions(+), 55 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm VMLAL_S_3d 1111 001 0 1 . .. .... .... 1000 . 0 . 0 .... @3diff VMLAL_U_3d 1111 001 1 1 . .. .... .... 1000 . 0 . 0 .... @3diff + VQDMLAL_3d 1111 001 0 1 . .. .... .... 1001 . 0 . 0 .... @3diff + VMLSL_S_3d 1111 001 0 1 . .. .... .... 1010 . 0 . 0 .... @3diff VMLSL_U_3d 1111 001 1 1 . .. .... .... 1010 . 0 . 0 .... @3diff + VQDMLSL_3d 1111 001 0 1 . .. .... .... 1011 . 0 . 0 .... @3diff + VMULL_S_3d 1111 001 0 1 . .. .... .... 1100 . 0 . 0 .... @3diff VMULL_U_3d 1111 001 1 1 . .. .... .... 1100 . 0 . 0 .... @3diff + + VQDMULL_3d 1111 001 0 1 . .. .... .... 1101 . 0 . 0 .... @3diff ] } diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ DO_VMLAL(VMLAL_S,mull_s,add) DO_VMLAL(VMLAL_U,mull_u,add) DO_VMLAL(VMLSL_S,mull_s,sub) DO_VMLAL(VMLSL_U,mull_u,sub) + +static void gen_VQDMULL_16(TCGv_i64 rd, TCGv_i32 rn, TCGv_i32 rm) +{ + gen_helper_neon_mull_s16(rd, rn, rm); + gen_helper_neon_addl_saturate_s32(rd, cpu_env, rd, rd); +} + +static void gen_VQDMULL_32(TCGv_i64 rd, TCGv_i32 rn, TCGv_i32 rm) +{ + gen_mull_s32(rd, rn, rm); + gen_helper_neon_addl_saturate_s64(rd, cpu_env, rd, rd); +} + +static bool trans_VQDMULL_3d(DisasContext *s, arg_3diff *a) +{ + static NeonGenTwoOpWidenFn * const opfn[] = { + NULL, + gen_VQDMULL_16, + gen_VQDMULL_32, + NULL, + }; + + return do_long_3d(s, a, opfn[a->size], NULL); +} + +static void gen_VQDMLAL_acc_16(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) +{ + gen_helper_neon_addl_saturate_s32(rd, cpu_env, rn, rm); +} + +static void gen_VQDMLAL_acc_32(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) +{ + gen_helper_neon_addl_saturate_s64(rd, cpu_env, rn, rm); +} + +static bool trans_VQDMLAL_3d(DisasContext *s, arg_3diff *a) +{ + static NeonGenTwoOpWidenFn * const opfn[] = { + NULL, + gen_VQDMULL_16, + gen_VQDMULL_32, + NULL, + }; + static NeonGenTwo64OpFn * const accfn[] = { + NULL, + gen_VQDMLAL_acc_16, + gen_VQDMLAL_acc_32, + NULL, + }; + + return do_long_3d(s, a, opfn[a->size], accfn[a->size]); +} + +static void gen_VQDMLSL_acc_16(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) +{ + gen_helper_neon_negl_u32(rm, rm); + gen_helper_neon_addl_saturate_s32(rd, cpu_env, rn, rm); +} + +static void gen_VQDMLSL_acc_32(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) +{ + tcg_gen_neg_i64(rm, rm); + gen_helper_neon_addl_saturate_s64(rd, cpu_env, rn, rm); +} + +static bool trans_VQDMLSL_3d(DisasContext *s, arg_3diff *a) +{ + static NeonGenTwoOpWidenFn * const opfn[] = { + NULL, + gen_VQDMULL_16, + gen_VQDMULL_32, + NULL, + }; + static NeonGenTwo64OpFn * const accfn[] = { + NULL, + gen_VQDMLSL_acc_16, + gen_VQDMLSL_acc_32, + NULL, + }; + + return do_long_3d(s, a, opfn[a->size], accfn[a->size]); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) {0, 0, 0, 7}, /* VSUBHN: handled by decodetree */ {0, 0, 0, 7}, /* VABDL */ {0, 0, 0, 7}, /* VMLAL */ - {0, 0, 0, 9}, /* VQDMLAL */ + {0, 0, 0, 7}, /* VQDMLAL */ {0, 0, 0, 7}, /* VMLSL */ - {0, 0, 0, 9}, /* VQDMLSL */ + {0, 0, 0, 7}, /* VQDMLSL */ {0, 0, 0, 7}, /* Integer VMULL */ - {0, 0, 0, 9}, /* VQDMULL */ + {0, 0, 0, 7}, /* VQDMULL */ {0, 0, 0, 0xa}, /* Polynomial VMULL */ {0, 0, 0, 7}, /* Reserved: always UNDEF */ }; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } return 0; } - - /* Avoid overlapping operands. Wide source operands are - always aligned so will never overlap with wide - destinations in problematic ways. */ - if (rd == rm) { - tmp = neon_load_reg(rm, 1); - neon_store_scratch(2, tmp); - } else if (rd == rn) { - tmp = neon_load_reg(rn, 1); - neon_store_scratch(2, tmp); - } - tmp3 = NULL; - for (pass = 0; pass < 2; pass++) { - if (pass == 1 && rd == rn) { - tmp = neon_load_scratch(2); - } else { - tmp = neon_load_reg(rn, pass); - } - if (pass == 1 && rd == rm) { - tmp2 = neon_load_scratch(2); - } else { - tmp2 = neon_load_reg(rm, pass); - } - switch (op) { - case 9: case 11: case 13: - /* VQDMLAL, VQDMLSL, VQDMULL */ - gen_neon_mull(cpu_V0, tmp, tmp2, size, u); - break; - default: /* 15 is RESERVED: caught earlier */ - abort(); - } - if (op == 13) { - /* VQDMULL */ - gen_neon_addl_saturate(cpu_V0, cpu_V0, size); - neon_store_reg64(cpu_V0, rd + pass); - } else { - /* Accumulate. */ - neon_load_reg64(cpu_V1, rd + pass); - switch (op) { - case 9: case 11: /* VQDMLAL, VQDMLSL */ - gen_neon_addl_saturate(cpu_V0, cpu_V0, size); - if (op == 11) { - gen_neon_negl(cpu_V0, size); - } - gen_neon_addl_saturate(cpu_V0, cpu_V1, size); - break; - default: - abort(); - } - neon_store_reg64(cpu_V0, rd + pass); - } - } + abort(); /* all others handled by decodetree */ } else { /* Two registers and a scalar. NB that for ops of this form * the ARM ARM labels bit 24 as Q, but it is in our variable -- 2.20.1 Convert the Neon 3-reg-diff insn polynomial VMULL. This is the last insn in this group to be converted. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/neon-dp.decode | 2 ++ target/arm/translate-neon.inc.c | 43 +++++++++++++++++++++++ target/arm/translate.c | 60 ++------------------------------- 3 files changed, 48 insertions(+), 57 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm VMULL_U_3d 1111 001 1 1 . .. .... .... 1100 . 0 . 0 .... @3diff VQDMULL_3d 1111 001 0 1 . .. .... .... 1101 . 0 . 0 .... @3diff + + VMULL_P_3d 1111 001 0 1 . .. .... .... 1110 . 0 . 0 .... @3diff ] } diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VQDMLSL_3d(DisasContext *s, arg_3diff *a) return do_long_3d(s, a, opfn[a->size], accfn[a->size]); } + +static bool trans_VMULL_P_3d(DisasContext *s, arg_3diff *a) +{ + gen_helper_gvec_3 *fn_gvec; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if (a->vd & 1) { + return false; + } + + switch (a->size) { + case 0: + fn_gvec = gen_helper_neon_pmull_h; + break; + case 2: + if (!dc_isar_feature(aa32_pmull, s)) { + return false; + } + fn_gvec = gen_helper_gvec_pmull_q; + break; + default: + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + tcg_gen_gvec_3_ool(neon_reg_offset(a->vd, 0), + neon_reg_offset(a->vn, 0), + neon_reg_offset(a->vm, 0), + 16, 16, 0, fn_gvec); + return true; +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) { int op; int q; - int rd, rn, rm, rd_ofs, rn_ofs, rm_ofs; + int rd, rn, rm, rd_ofs, rm_ofs; int size; int pass; int u; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) size = (insn >> 20) & 3; vec_size = q ? 16 : 8; rd_ofs = neon_reg_offset(rd, 0); - rn_ofs = neon_reg_offset(rn, 0); rm_ofs = neon_reg_offset(rm, 0); if ((insn & (1 << 23)) == 0) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) if (size != 3) { op = (insn >> 8) & 0xf; if ((insn & (1 << 6)) == 0) { - /* Three registers of different lengths. */ - /* undefreq: bit 0 : UNDEF if size == 0 - * bit 1 : UNDEF if size == 1 - * bit 2 : UNDEF if size == 2 - * bit 3 : UNDEF if U == 1 - * Note that [2:0] set implies 'always UNDEF' - */ - int undefreq; - /* prewiden, src1_wide, src2_wide, undefreq */ - static const int neon_3reg_wide[16][4] = { - {0, 0, 0, 7}, /* VADDL: handled by decodetree */ - {0, 0, 0, 7}, /* VADDW: handled by decodetree */ - {0, 0, 0, 7}, /* VSUBL: handled by decodetree */ - {0, 0, 0, 7}, /* VSUBW: handled by decodetree */ - {0, 0, 0, 7}, /* VADDHN: handled by decodetree */ - {0, 0, 0, 7}, /* VABAL */ - {0, 0, 0, 7}, /* VSUBHN: handled by decodetree */ - {0, 0, 0, 7}, /* VABDL */ - {0, 0, 0, 7}, /* VMLAL */ - {0, 0, 0, 7}, /* VQDMLAL */ - {0, 0, 0, 7}, /* VMLSL */ - {0, 0, 0, 7}, /* VQDMLSL */ - {0, 0, 0, 7}, /* Integer VMULL */ - {0, 0, 0, 7}, /* VQDMULL */ - {0, 0, 0, 0xa}, /* Polynomial VMULL */ - {0, 0, 0, 7}, /* Reserved: always UNDEF */ - }; - - undefreq = neon_3reg_wide[op][3]; - - if ((undefreq & (1 << size)) || - ((undefreq & 8) && u)) { - return 1; - } - if (rd & 1) { - return 1; - } - - /* Handle polynomial VMULL in a single pass. */ - if (op == 14) { - if (size == 0) { - /* VMULL.P8 */ - tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, 16, 16, - 0, gen_helper_neon_pmull_h); - } else { - /* VMULL.P64 */ - if (!dc_isar_feature(aa32_pmull, s)) { - return 1; - } - tcg_gen_gvec_3_ool(rd_ofs, rn_ofs, rm_ofs, 16, 16, - 0, gen_helper_gvec_pmull_q); - } - return 0; - } - abort(); /* all others handled by decodetree */ + /* Three registers of different lengths: handled by decodetree */ + return 1; } else { /* Two registers and a scalar. NB that for ops of this form * the ARM ARM labels bit 24 as Q, but it is in our variable -- 2.20.1 Mark the arrays of function pointers in trans_VSHLL_S_2sh() and trans_VSHLL_U_2sh() as both 'static' and 'const'. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-neon.inc.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool do_vshll_2sh(DisasContext *s, arg_2reg_shift *a, static bool trans_VSHLL_S_2sh(DisasContext *s, arg_2reg_shift *a) { - NeonGenWidenFn *widenfn[] = { + static NeonGenWidenFn * const widenfn[] = { gen_helper_neon_widen_s8, gen_helper_neon_widen_s16, tcg_gen_ext_i32_i64, @@ -XXX,XX +XXX,XX @@ static bool trans_VSHLL_S_2sh(DisasContext *s, arg_2reg_shift *a) static bool trans_VSHLL_U_2sh(DisasContext *s, arg_2reg_shift *a) { - NeonGenWidenFn *widenfn[] = { + static NeonGenWidenFn * const widenfn[] = { gen_helper_neon_widen_u8, gen_helper_neon_widen_u16, tcg_gen_extu_i32_i64, -- 2.20.1 In commit 37bfce81b10450071 we accidentally introduced a leak of a TCG temporary in do_2shift_env_64(); free it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-neon.inc.c | 1 + 1 file changed, 1 insertion(+) diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool do_2shift_env_64(DisasContext *s, arg_2reg_shift *a, neon_load_reg64(tmp, a->vm + pass); fn(tmp, cpu_env, tmp, constimm); neon_store_reg64(tmp, a->vd + pass); + tcg_temp_free_i64(tmp); } tcg_temp_free_i64(constimm); return true; -- 2.20.1 Convert the VMLA, VMLS and VMUL insns in the Neon "2 registers and a scalar" group to decodetree. These are 32x32->32 operations where one of the inputs is the scalar, followed by a possible accumulate operation of the 32-bit result. The refactoring removes some of the oddities of the old decoder: * operands to the operation and accumulation were often reversed (taking advantage of the fact that most of these ops are commutative); the new code follows the pseudocode order * the Q bit in the insn was in a local variable 'u'; in the new code it is decoded into a->q Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/neon-dp.decode | 15 ++++ target/arm/translate-neon.inc.c | 133 ++++++++++++++++++++++++++++++++ target/arm/translate.c | 77 ++---------------- 3 files changed, 154 insertions(+), 71 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm VQDMULL_3d 1111 001 0 1 . .. .... .... 1101 . 0 . 0 .... @3diff VMULL_P_3d 1111 001 0 1 . .. .... .... 1110 . 0 . 0 .... @3diff + + ################################################################## + # 2-regs-plus-scalar grouping: + # 1111 001 Q 1 D sz!=11 Vn:4 Vd:4 opc:4 N 1 M 0 Vm:4 + ################################################################## + &2scalar vm vn vd size q + + @2scalar .... ... q:1 . . size:2 .... .... .... . . . . .... \ + &2scalar vm=%vm_dp vn=%vn_dp vd=%vd_dp + + VMLA_2sc 1111 001 . 1 . .. .... .... 0000 . 1 . 0 .... @2scalar + + VMLS_2sc 1111 001 . 1 . .. .... .... 0100 . 1 . 0 .... @2scalar + + VMUL_2sc 1111 001 . 1 . .. .... .... 1000 . 1 . 0 .... @2scalar ] } diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VMULL_P_3d(DisasContext *s, arg_3diff *a) 16, 16, 0, fn_gvec); return true; } + +static void gen_neon_dup_low16(TCGv_i32 var) +{ + TCGv_i32 tmp = tcg_temp_new_i32(); + tcg_gen_ext16u_i32(var, var); + tcg_gen_shli_i32(tmp, var, 16); + tcg_gen_or_i32(var, var, tmp); + tcg_temp_free_i32(tmp); +} + +static void gen_neon_dup_high16(TCGv_i32 var) +{ + TCGv_i32 tmp = tcg_temp_new_i32(); + tcg_gen_andi_i32(var, var, 0xffff0000); + tcg_gen_shri_i32(tmp, var, 16); + tcg_gen_or_i32(var, var, tmp); + tcg_temp_free_i32(tmp); +} + +static inline TCGv_i32 neon_get_scalar(int size, int reg) +{ + TCGv_i32 tmp; + if (size == 1) { + tmp = neon_load_reg(reg & 7, reg >> 4); + if (reg & 8) { + gen_neon_dup_high16(tmp); + } else { + gen_neon_dup_low16(tmp); + } + } else { + tmp = neon_load_reg(reg & 15, reg >> 4); + } + return tmp; +} + +static bool do_2scalar(DisasContext *s, arg_2scalar *a, + NeonGenTwoOpFn *opfn, NeonGenTwoOpFn *accfn) +{ + /* + * Two registers and a scalar: perform an operation between + * the input elements and the scalar, and then possibly + * perform an accumulation operation of that result into the + * destination. + */ + TCGv_i32 scalar; + int pass; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if (!opfn) { + /* Bad size (including size == 3, which is a different insn group) */ + return false; + } + + if (a->q && ((a->vd | a->vn) & 1)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + scalar = neon_get_scalar(a->size, a->vm); + + for (pass = 0; pass < (a->q ? 4 : 2); pass++) { + TCGv_i32 tmp = neon_load_reg(a->vn, pass); + opfn(tmp, tmp, scalar); + if (accfn) { + TCGv_i32 rd = neon_load_reg(a->vd, pass); + accfn(tmp, rd, tmp); + tcg_temp_free_i32(rd); + } + neon_store_reg(a->vd, pass, tmp); + } + tcg_temp_free_i32(scalar); + return true; +} + +static bool trans_VMUL_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenTwoOpFn * const opfn[] = { + NULL, + gen_helper_neon_mul_u16, + tcg_gen_mul_i32, + NULL, + }; + + return do_2scalar(s, a, opfn[a->size], NULL); +} + +static bool trans_VMLA_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenTwoOpFn * const opfn[] = { + NULL, + gen_helper_neon_mul_u16, + tcg_gen_mul_i32, + NULL, + }; + static NeonGenTwoOpFn * const accfn[] = { + NULL, + gen_helper_neon_add_u16, + tcg_gen_add_i32, + NULL, + }; + + return do_2scalar(s, a, opfn[a->size], accfn[a->size]); +} + +static bool trans_VMLS_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenTwoOpFn * const opfn[] = { + NULL, + gen_helper_neon_mul_u16, + tcg_gen_mul_i32, + NULL, + }; + static NeonGenTwoOpFn * const accfn[] = { + NULL, + gen_helper_neon_sub_u16, + tcg_gen_sub_i32, + NULL, + }; + + return do_2scalar(s, a, opfn[a->size], accfn[a->size]); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_dsp_insn(DisasContext *s, uint32_t insn) #define VFP_DREG_N(reg, insn) VFP_DREG(reg, insn, 16, 7) #define VFP_DREG_M(reg, insn) VFP_DREG(reg, insn, 0, 5) -static void gen_neon_dup_low16(TCGv_i32 var) -{ - TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_ext16u_i32(var, var); - tcg_gen_shli_i32(tmp, var, 16); - tcg_gen_or_i32(var, var, tmp); - tcg_temp_free_i32(tmp); -} - -static void gen_neon_dup_high16(TCGv_i32 var) -{ - TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_andi_i32(var, var, 0xffff0000); - tcg_gen_shri_i32(tmp, var, 16); - tcg_gen_or_i32(var, var, tmp); - tcg_temp_free_i32(tmp); -} - static inline bool use_goto_tb(DisasContext *s, target_ulong dest) { #ifndef CONFIG_USER_ONLY @@ -XXX,XX +XXX,XX @@ static void gen_exception_return(DisasContext *s, TCGv_i32 pc) #define CPU_V001 cpu_V0, cpu_V0, cpu_V1 -static inline void gen_neon_add(int size, TCGv_i32 t0, TCGv_i32 t1) -{ - switch (size) { - case 0: gen_helper_neon_add_u8(t0, t0, t1); break; - case 1: gen_helper_neon_add_u16(t0, t0, t1); break; - case 2: tcg_gen_add_i32(t0, t0, t1); break; - default: abort(); - } -} - -static inline void gen_neon_rsb(int size, TCGv_i32 t0, TCGv_i32 t1) -{ - switch (size) { - case 0: gen_helper_neon_sub_u8(t0, t1, t0); break; - case 1: gen_helper_neon_sub_u16(t0, t1, t0); break; - case 2: tcg_gen_sub_i32(t0, t1, t0); break; - default: return; - } -} - static TCGv_i32 neon_load_scratch(int scratch) { TCGv_i32 tmp = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static void neon_store_scratch(int scratch, TCGv_i32 var) tcg_temp_free_i32(var); } -static inline TCGv_i32 neon_get_scalar(int size, int reg) -{ - TCGv_i32 tmp; - if (size == 1) { - tmp = neon_load_reg(reg & 7, reg >> 4); - if (reg & 8) { - gen_neon_dup_high16(tmp); - } else { - gen_neon_dup_low16(tmp); - } - } else { - tmp = neon_load_reg(reg & 15, reg >> 4); - } - return tmp; -} - static int gen_neon_unzip(int rd, int rm, int size, int q) { TCGv_ptr pd, pm; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } switch (op) { + case 0: /* Integer VMLA scalar */ + case 4: /* Integer VMLS scalar */ + case 8: /* Integer VMUL scalar */ + return 1; /* handled by decodetree */ + case 1: /* Float VMLA scalar */ case 5: /* Floating point VMLS scalar */ case 9: /* Floating point VMUL scalar */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } /* fall through */ - case 0: /* Integer VMLA scalar */ - case 4: /* Integer VMLS scalar */ - case 8: /* Integer VMUL scalar */ case 12: /* VQDMULH scalar */ case 13: /* VQRDMULH scalar */ if (u && ((rd | rn) & 1)) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } else { gen_helper_neon_qrdmulh_s32(tmp, cpu_env, tmp, tmp2); } - } else if (op & 1) { + } else { TCGv_ptr fpstatus = get_fpstatus_ptr(1); gen_helper_vfp_muls(tmp, tmp, tmp2, fpstatus); tcg_temp_free_ptr(fpstatus); - } else { - switch (size) { - case 0: gen_helper_neon_mul_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_mul_u16(tmp, tmp, tmp2); break; - case 2: tcg_gen_mul_i32(tmp, tmp, tmp2); break; - default: abort(); - } } tcg_temp_free_i32(tmp2); if (op < 8) { /* Accumulate. */ tmp2 = neon_load_reg(rd, pass); switch (op) { - case 0: - gen_neon_add(size, tmp, tmp2); - break; case 1: { TCGv_ptr fpstatus = get_fpstatus_ptr(1); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_temp_free_ptr(fpstatus); break; } - case 4: - gen_neon_rsb(size, tmp, tmp2); - break; case 5: { TCGv_ptr fpstatus = get_fpstatus_ptr(1); -- 2.20.1 Convert the float versions of VMLA, VMLS and VMUL in the Neon 2-reg-scalar group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- As noted in the comment on the WRAP_FP_FN macro, we could have had a do_2scalar_fp() function, but for 3 insns it seemed simpler to just do the wrapping to get hold of the fpstatus ptr. (These are the only fp insns in the group.) Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/neon-dp.decode | 3 ++ target/arm/translate-neon.inc.c | 65 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 37 ++----------------- 3 files changed, 71 insertions(+), 34 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm &2scalar vm=%vm_dp vn=%vn_dp vd=%vd_dp VMLA_2sc 1111 001 . 1 . .. .... .... 0000 . 1 . 0 .... @2scalar + VMLA_F_2sc 1111 001 . 1 . .. .... .... 0001 . 1 . 0 .... @2scalar VMLS_2sc 1111 001 . 1 . .. .... .... 0100 . 1 . 0 .... @2scalar + VMLS_F_2sc 1111 001 . 1 . .. .... .... 0101 . 1 . 0 .... @2scalar VMUL_2sc 1111 001 . 1 . .. .... .... 1000 . 1 . 0 .... @2scalar + VMUL_F_2sc 1111 001 . 1 . .. .... .... 1001 . 1 . 0 .... @2scalar ] } diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VMLS_2sc(DisasContext *s, arg_2scalar *a) return do_2scalar(s, a, opfn[a->size], accfn[a->size]); } + +/* + * Rather than have a float-specific version of do_2scalar just for + * three insns, we wrap a NeonGenTwoSingleOpFn to turn it into + * a NeonGenTwoOpFn. + */ +#define WRAP_FP_FN(WRAPNAME, FUNC) \ + static void WRAPNAME(TCGv_i32 rd, TCGv_i32 rn, TCGv_i32 rm) \ + { \ + TCGv_ptr fpstatus = get_fpstatus_ptr(1); \ + FUNC(rd, rn, rm, fpstatus); \ + tcg_temp_free_ptr(fpstatus); \ + } + +WRAP_FP_FN(gen_VMUL_F_mul, gen_helper_vfp_muls) +WRAP_FP_FN(gen_VMUL_F_add, gen_helper_vfp_adds) +WRAP_FP_FN(gen_VMUL_F_sub, gen_helper_vfp_subs) + +static bool trans_VMUL_F_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenTwoOpFn * const opfn[] = { + NULL, + NULL, /* TODO: fp16 support */ + gen_VMUL_F_mul, + NULL, + }; + + return do_2scalar(s, a, opfn[a->size], NULL); +} + +static bool trans_VMLA_F_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenTwoOpFn * const opfn[] = { + NULL, + NULL, /* TODO: fp16 support */ + gen_VMUL_F_mul, + NULL, + }; + static NeonGenTwoOpFn * const accfn[] = { + NULL, + NULL, /* TODO: fp16 support */ + gen_VMUL_F_add, + NULL, + }; + + return do_2scalar(s, a, opfn[a->size], accfn[a->size]); +} + +static bool trans_VMLS_F_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenTwoOpFn * const opfn[] = { + NULL, + NULL, /* TODO: fp16 support */ + gen_VMUL_F_mul, + NULL, + }; + static NeonGenTwoOpFn * const accfn[] = { + NULL, + NULL, /* TODO: fp16 support */ + gen_VMUL_F_sub, + NULL, + }; + + return do_2scalar(s, a, opfn[a->size], accfn[a->size]); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 0: /* Integer VMLA scalar */ case 4: /* Integer VMLS scalar */ case 8: /* Integer VMUL scalar */ - return 1; /* handled by decodetree */ - case 1: /* Float VMLA scalar */ case 5: /* Floating point VMLS scalar */ case 9: /* Floating point VMUL scalar */ - if (size == 1) { - return 1; - } - /* fall through */ + return 1; /* handled by decodetree */ + case 12: /* VQDMULH scalar */ case 13: /* VQRDMULH scalar */ if (u && ((rd | rn) & 1)) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } else { gen_helper_neon_qdmulh_s32(tmp, cpu_env, tmp, tmp2); } - } else if (op == 13) { + } else { if (size == 1) { gen_helper_neon_qrdmulh_s16(tmp, cpu_env, tmp, tmp2); } else { gen_helper_neon_qrdmulh_s32(tmp, cpu_env, tmp, tmp2); } - } else { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_vfp_muls(tmp, tmp, tmp2, fpstatus); - tcg_temp_free_ptr(fpstatus); } tcg_temp_free_i32(tmp2); - if (op < 8) { - /* Accumulate. */ - tmp2 = neon_load_reg(rd, pass); - switch (op) { - case 1: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_vfp_adds(tmp, tmp, tmp2, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } - case 5: - { - TCGv_ptr fpstatus = get_fpstatus_ptr(1); - gen_helper_vfp_subs(tmp, tmp2, tmp, fpstatus); - tcg_temp_free_ptr(fpstatus); - break; - } - default: - abort(); - } - tcg_temp_free_i32(tmp2); - } neon_store_reg(rd, pass, tmp); } break; -- 2.20.1 Convert the VQDMULH and VQRDMULH insns in the 2-reg-scalar group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/neon-dp.decode | 3 +++ target/arm/translate-neon.inc.c | 29 +++++++++++++++++++++++ target/arm/translate.c | 42 ++------------------------------- 3 files changed, 34 insertions(+), 40 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm VMUL_2sc 1111 001 . 1 . .. .... .... 1000 . 1 . 0 .... @2scalar VMUL_F_2sc 1111 001 . 1 . .. .... .... 1001 . 1 . 0 .... @2scalar + + VQDMULH_2sc 1111 001 . 1 . .. .... .... 1100 . 1 . 0 .... @2scalar + VQRDMULH_2sc 1111 001 . 1 . .. .... .... 1101 . 1 . 0 .... @2scalar ] } diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VMLS_F_2sc(DisasContext *s, arg_2scalar *a) return do_2scalar(s, a, opfn[a->size], accfn[a->size]); } + +WRAP_ENV_FN(gen_VQDMULH_16, gen_helper_neon_qdmulh_s16) +WRAP_ENV_FN(gen_VQDMULH_32, gen_helper_neon_qdmulh_s32) +WRAP_ENV_FN(gen_VQRDMULH_16, gen_helper_neon_qrdmulh_s16) +WRAP_ENV_FN(gen_VQRDMULH_32, gen_helper_neon_qrdmulh_s32) + +static bool trans_VQDMULH_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenTwoOpFn * const opfn[] = { + NULL, + gen_VQDMULH_16, + gen_VQDMULH_32, + NULL, + }; + + return do_2scalar(s, a, opfn[a->size], NULL); +} + +static bool trans_VQRDMULH_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenTwoOpFn * const opfn[] = { + NULL, + gen_VQRDMULH_16, + gen_VQRDMULH_32, + NULL, + }; + + return do_2scalar(s, a, opfn[a->size], NULL); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_exception_return(DisasContext *s, TCGv_i32 pc) #define CPU_V001 cpu_V0, cpu_V0, cpu_V1 -static TCGv_i32 neon_load_scratch(int scratch) -{ - TCGv_i32 tmp = tcg_temp_new_i32(); - tcg_gen_ld_i32(tmp, cpu_env, offsetof(CPUARMState, vfp.scratch[scratch])); - return tmp; -} - -static void neon_store_scratch(int scratch, TCGv_i32 var) -{ - tcg_gen_st_i32(var, cpu_env, offsetof(CPUARMState, vfp.scratch[scratch])); - tcg_temp_free_i32(var); -} - static int gen_neon_unzip(int rd, int rm, int size, int q) { TCGv_ptr pd, pm; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 1: /* Float VMLA scalar */ case 5: /* Floating point VMLS scalar */ case 9: /* Floating point VMUL scalar */ - return 1; /* handled by decodetree */ - case 12: /* VQDMULH scalar */ case 13: /* VQRDMULH scalar */ - if (u && ((rd | rn) & 1)) { - return 1; - } - tmp = neon_get_scalar(size, rm); - neon_store_scratch(0, tmp); - for (pass = 0; pass < (u ? 4 : 2); pass++) { - tmp = neon_load_scratch(0); - tmp2 = neon_load_reg(rn, pass); - if (op == 12) { - if (size == 1) { - gen_helper_neon_qdmulh_s16(tmp, cpu_env, tmp, tmp2); - } else { - gen_helper_neon_qdmulh_s32(tmp, cpu_env, tmp, tmp2); - } - } else { - if (size == 1) { - gen_helper_neon_qrdmulh_s16(tmp, cpu_env, tmp, tmp2); - } else { - gen_helper_neon_qrdmulh_s32(tmp, cpu_env, tmp, tmp2); - } - } - tcg_temp_free_i32(tmp2); - neon_store_reg(rd, pass, tmp); - } - break; + return 1; /* handled by decodetree */ + case 3: /* VQDMLAL scalar */ case 7: /* VQDMLSL scalar */ case 11: /* VQDMULL scalar */ -- 2.20.1 Convert the VQRDMLAH and VQRDMLSH insns in the 2-reg-scalar group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/neon-dp.decode | 3 ++ target/arm/translate-neon.inc.c | 74 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 38 +---------------- 3 files changed, 79 insertions(+), 36 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm VQDMULH_2sc 1111 001 . 1 . .. .... .... 1100 . 1 . 0 .... @2scalar VQRDMULH_2sc 1111 001 . 1 . .. .... .... 1101 . 1 . 0 .... @2scalar + + VQRDMLAH_2sc 1111 001 . 1 . .. .... .... 1110 . 1 . 0 .... @2scalar + VQRDMLSH_2sc 1111 001 . 1 . .. .... .... 1111 . 1 . 0 .... @2scalar ] } diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VQRDMULH_2sc(DisasContext *s, arg_2scalar *a) return do_2scalar(s, a, opfn[a->size], NULL); } + +static bool do_vqrdmlah_2sc(DisasContext *s, arg_2scalar *a, + NeonGenThreeOpEnvFn *opfn) +{ + /* + * VQRDMLAH/VQRDMLSH: this is like do_2scalar, but the opfn + * performs a kind of fused op-then-accumulate using a helper + * function that takes all of rd, rn and the scalar at once. + */ + TCGv_i32 scalar; + int pass; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + if (!dc_isar_feature(aa32_rdm, s)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if (!opfn) { + /* Bad size (including size == 3, which is a different insn group) */ + return false; + } + + if (a->q && ((a->vd | a->vn) & 1)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + scalar = neon_get_scalar(a->size, a->vm); + + for (pass = 0; pass < (a->q ? 4 : 2); pass++) { + TCGv_i32 rn = neon_load_reg(a->vn, pass); + TCGv_i32 rd = neon_load_reg(a->vd, pass); + opfn(rd, cpu_env, rn, scalar, rd); + tcg_temp_free_i32(rn); + neon_store_reg(a->vd, pass, rd); + } + tcg_temp_free_i32(scalar); + + return true; +} + +static bool trans_VQRDMLAH_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenThreeOpEnvFn *opfn[] = { + NULL, + gen_helper_neon_qrdmlah_s16, + gen_helper_neon_qrdmlah_s32, + NULL, + }; + return do_vqrdmlah_2sc(s, a, opfn[a->size]); +} + +static bool trans_VQRDMLSH_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenThreeOpEnvFn *opfn[] = { + NULL, + gen_helper_neon_qrdmlsh_s16, + gen_helper_neon_qrdmlsh_s32, + NULL, + }; + return do_vqrdmlah_2sc(s, a, opfn[a->size]); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 9: /* Floating point VMUL scalar */ case 12: /* VQDMULH scalar */ case 13: /* VQRDMULH scalar */ + case 14: /* VQRDMLAH scalar */ + case 15: /* VQRDMLSH scalar */ return 1; /* handled by decodetree */ case 3: /* VQDMLAL scalar */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) neon_store_reg64(cpu_V0, rd + pass); } break; - case 14: /* VQRDMLAH scalar */ - case 15: /* VQRDMLSH scalar */ - { - NeonGenThreeOpEnvFn *fn; - - if (!dc_isar_feature(aa32_rdm, s)) { - return 1; - } - if (u && ((rd | rn) & 1)) { - return 1; - } - if (op == 14) { - if (size == 1) { - fn = gen_helper_neon_qrdmlah_s16; - } else { - fn = gen_helper_neon_qrdmlah_s32; - } - } else { - if (size == 1) { - fn = gen_helper_neon_qrdmlsh_s16; - } else { - fn = gen_helper_neon_qrdmlsh_s32; - } - } - - tmp2 = neon_get_scalar(size, rm); - for (pass = 0; pass < (u ? 4 : 2); pass++) { - tmp = neon_load_reg(rn, pass); - tmp3 = neon_load_reg(rd, pass); - fn(tmp, cpu_env, tmp, tmp2, tmp3); - tcg_temp_free_i32(tmp3); - neon_store_reg(rd, pass, tmp); - } - tcg_temp_free_i32(tmp2); - } - break; default: g_assert_not_reached(); } -- 2.20.1 Convert the Neon 2-reg-scalar long multiplies to decodetree. These are the last instructions in the group. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/neon-dp.decode | 18 ++++ target/arm/translate-neon.inc.c | 163 ++++++++++++++++++++++++++++ target/arm/translate.c | 182 ++------------------------------ 3 files changed, 187 insertions(+), 176 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm @2scalar .... ... q:1 . . size:2 .... .... .... . . . . .... \ &2scalar vm=%vm_dp vn=%vn_dp vd=%vd_dp + # For the 'long' ops the Q bit is part of insn decode + @2scalar_q0 .... ... . . . size:2 .... .... .... . . . . .... \ + &2scalar vm=%vm_dp vn=%vn_dp vd=%vd_dp q=0 VMLA_2sc 1111 001 . 1 . .. .... .... 0000 . 1 . 0 .... @2scalar VMLA_F_2sc 1111 001 . 1 . .. .... .... 0001 . 1 . 0 .... @2scalar + VMLAL_S_2sc 1111 001 0 1 . .. .... .... 0010 . 1 . 0 .... @2scalar_q0 + VMLAL_U_2sc 1111 001 1 1 . .. .... .... 0010 . 1 . 0 .... @2scalar_q0 + + VQDMLAL_2sc 1111 001 0 1 . .. .... .... 0011 . 1 . 0 .... @2scalar_q0 + VMLS_2sc 1111 001 . 1 . .. .... .... 0100 . 1 . 0 .... @2scalar VMLS_F_2sc 1111 001 . 1 . .. .... .... 0101 . 1 . 0 .... @2scalar + VMLSL_S_2sc 1111 001 0 1 . .. .... .... 0110 . 1 . 0 .... @2scalar_q0 + VMLSL_U_2sc 1111 001 1 1 . .. .... .... 0110 . 1 . 0 .... @2scalar_q0 + + VQDMLSL_2sc 1111 001 0 1 . .. .... .... 0111 . 1 . 0 .... @2scalar_q0 + VMUL_2sc 1111 001 . 1 . .. .... .... 1000 . 1 . 0 .... @2scalar VMUL_F_2sc 1111 001 . 1 . .. .... .... 1001 . 1 . 0 .... @2scalar + VMULL_S_2sc 1111 001 0 1 . .. .... .... 1010 . 1 . 0 .... @2scalar_q0 + VMULL_U_2sc 1111 001 1 1 . .. .... .... 1010 . 1 . 0 .... @2scalar_q0 + + VQDMULL_2sc 1111 001 0 1 . .. .... .... 1011 . 1 . 0 .... @2scalar_q0 + VQDMULH_2sc 1111 001 . 1 . .. .... .... 1100 . 1 . 0 .... @2scalar VQRDMULH_2sc 1111 001 . 1 . .. .... .... 1101 . 1 . 0 .... @2scalar diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VQRDMLSH_2sc(DisasContext *s, arg_2scalar *a) }; return do_vqrdmlah_2sc(s, a, opfn[a->size]); } + +static bool do_2scalar_long(DisasContext *s, arg_2scalar *a, + NeonGenTwoOpWidenFn *opfn, + NeonGenTwo64OpFn *accfn) +{ + /* + * Two registers and a scalar, long operations: perform an + * operation on the input elements and the scalar which produces + * a double-width result, and then possibly perform an accumulation + * operation of that result into the destination. + */ + TCGv_i32 scalar, rn; + TCGv_i64 rn0_64, rn1_64; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if (!opfn) { + /* Bad size (including size == 3, which is a different insn group) */ + return false; + } + + if (a->vd & 1) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + scalar = neon_get_scalar(a->size, a->vm); + + /* Load all inputs before writing any outputs, in case of overlap */ + rn = neon_load_reg(a->vn, 0); + rn0_64 = tcg_temp_new_i64(); + opfn(rn0_64, rn, scalar); + tcg_temp_free_i32(rn); + + rn = neon_load_reg(a->vn, 1); + rn1_64 = tcg_temp_new_i64(); + opfn(rn1_64, rn, scalar); + tcg_temp_free_i32(rn); + tcg_temp_free_i32(scalar); + + if (accfn) { + TCGv_i64 t64 = tcg_temp_new_i64(); + neon_load_reg64(t64, a->vd); + accfn(t64, t64, rn0_64); + neon_store_reg64(t64, a->vd); + neon_load_reg64(t64, a->vd + 1); + accfn(t64, t64, rn1_64); + neon_store_reg64(t64, a->vd + 1); + tcg_temp_free_i64(t64); + } else { + neon_store_reg64(rn0_64, a->vd); + neon_store_reg64(rn1_64, a->vd + 1); + } + tcg_temp_free_i64(rn0_64); + tcg_temp_free_i64(rn1_64); + return true; +} + +static bool trans_VMULL_S_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenTwoOpWidenFn * const opfn[] = { + NULL, + gen_helper_neon_mull_s16, + gen_mull_s32, + NULL, + }; + + return do_2scalar_long(s, a, opfn[a->size], NULL); +} + +static bool trans_VMULL_U_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenTwoOpWidenFn * const opfn[] = { + NULL, + gen_helper_neon_mull_u16, + gen_mull_u32, + NULL, + }; + + return do_2scalar_long(s, a, opfn[a->size], NULL); +} + +#define DO_VMLAL_2SC(INSN, MULL, ACC) \ + static bool trans_##INSN##_2sc(DisasContext *s, arg_2scalar *a) \ + { \ + static NeonGenTwoOpWidenFn * const opfn[] = { \ + NULL, \ + gen_helper_neon_##MULL##16, \ + gen_##MULL##32, \ + NULL, \ + }; \ + static NeonGenTwo64OpFn * const accfn[] = { \ + NULL, \ + gen_helper_neon_##ACC##l_u32, \ + tcg_gen_##ACC##_i64, \ + NULL, \ + }; \ + return do_2scalar_long(s, a, opfn[a->size], accfn[a->size]); \ + } + +DO_VMLAL_2SC(VMLAL_S, mull_s, add) +DO_VMLAL_2SC(VMLAL_U, mull_u, add) +DO_VMLAL_2SC(VMLSL_S, mull_s, sub) +DO_VMLAL_2SC(VMLSL_U, mull_u, sub) + +static bool trans_VQDMULL_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenTwoOpWidenFn * const opfn[] = { + NULL, + gen_VQDMULL_16, + gen_VQDMULL_32, + NULL, + }; + + return do_2scalar_long(s, a, opfn[a->size], NULL); +} + +static bool trans_VQDMLAL_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenTwoOpWidenFn * const opfn[] = { + NULL, + gen_VQDMULL_16, + gen_VQDMULL_32, + NULL, + }; + static NeonGenTwo64OpFn * const accfn[] = { + NULL, + gen_VQDMLAL_acc_16, + gen_VQDMLAL_acc_32, + NULL, + }; + + return do_2scalar_long(s, a, opfn[a->size], accfn[a->size]); +} + +static bool trans_VQDMLSL_2sc(DisasContext *s, arg_2scalar *a) +{ + static NeonGenTwoOpWidenFn * const opfn[] = { + NULL, + gen_VQDMULL_16, + gen_VQDMULL_32, + NULL, + }; + static NeonGenTwo64OpFn * const accfn[] = { + NULL, + gen_VQDMLSL_acc_16, + gen_VQDMLSL_acc_32, + NULL, + }; + + return do_2scalar_long(s, a, opfn[a->size], accfn[a->size]); +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_revsh(TCGv_i32 dest, TCGv_i32 var) tcg_gen_ext16s_i32(dest, var); } -/* 32x32->64 multiply. Marks inputs as dead. */ -static TCGv_i64 gen_mulu_i64_i32(TCGv_i32 a, TCGv_i32 b) -{ - TCGv_i32 lo = tcg_temp_new_i32(); - TCGv_i32 hi = tcg_temp_new_i32(); - TCGv_i64 ret; - - tcg_gen_mulu2_i32(lo, hi, a, b); - tcg_temp_free_i32(a); - tcg_temp_free_i32(b); - - ret = tcg_temp_new_i64(); - tcg_gen_concat_i32_i64(ret, lo, hi); - tcg_temp_free_i32(lo); - tcg_temp_free_i32(hi); - - return ret; -} - -static TCGv_i64 gen_muls_i64_i32(TCGv_i32 a, TCGv_i32 b) -{ - TCGv_i32 lo = tcg_temp_new_i32(); - TCGv_i32 hi = tcg_temp_new_i32(); - TCGv_i64 ret; - - tcg_gen_muls2_i32(lo, hi, a, b); - tcg_temp_free_i32(a); - tcg_temp_free_i32(b); - - ret = tcg_temp_new_i64(); - tcg_gen_concat_i32_i64(ret, lo, hi); - tcg_temp_free_i32(lo); - tcg_temp_free_i32(hi); - - return ret; -} - /* Swap low and high halfwords. */ static void gen_swap_half(TCGv_i32 var) { @@ -XXX,XX +XXX,XX @@ static inline void gen_neon_addl(int size) } } -static inline void gen_neon_negl(TCGv_i64 var, int size) -{ - switch (size) { - case 0: gen_helper_neon_negl_u16(var, var); break; - case 1: gen_helper_neon_negl_u32(var, var); break; - case 2: - tcg_gen_neg_i64(var, var); - break; - default: abort(); - } -} - -static inline void gen_neon_addl_saturate(TCGv_i64 op0, TCGv_i64 op1, int size) -{ - switch (size) { - case 1: gen_helper_neon_addl_saturate_s32(op0, cpu_env, op0, op1); break; - case 2: gen_helper_neon_addl_saturate_s64(op0, cpu_env, op0, op1); break; - default: abort(); - } -} - -static inline void gen_neon_mull(TCGv_i64 dest, TCGv_i32 a, TCGv_i32 b, - int size, int u) -{ - TCGv_i64 tmp; - - switch ((size << 1) | u) { - case 0: gen_helper_neon_mull_s8(dest, a, b); break; - case 1: gen_helper_neon_mull_u8(dest, a, b); break; - case 2: gen_helper_neon_mull_s16(dest, a, b); break; - case 3: gen_helper_neon_mull_u16(dest, a, b); break; - case 4: - tmp = gen_muls_i64_i32(a, b); - tcg_gen_mov_i64(dest, tmp); - tcg_temp_free_i64(tmp); - break; - case 5: - tmp = gen_mulu_i64_i32(a, b); - tcg_gen_mov_i64(dest, tmp); - tcg_temp_free_i64(tmp); - break; - default: abort(); - } - - /* gen_helper_neon_mull_[su]{8|16} do not free their parameters. - Don't forget to clean them now. */ - if (size < 2) { - tcg_temp_free_i32(a); - tcg_temp_free_i32(b); - } -} - static void gen_neon_narrow_op(int op, int u, int size, TCGv_i32 dest, TCGv_i64 src) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) int u; int vec_size; uint32_t imm; - TCGv_i32 tmp, tmp2, tmp3, tmp4, tmp5; + TCGv_i32 tmp, tmp2, tmp3, tmp5; TCGv_ptr ptr1; TCGv_i64 tmp64; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } else { /* (insn & 0x00800010 == 0x00800000) */ if (size != 3) { - op = (insn >> 8) & 0xf; - if ((insn & (1 << 6)) == 0) { - /* Three registers of different lengths: handled by decodetree */ - return 1; - } else { - /* Two registers and a scalar. NB that for ops of this form - * the ARM ARM labels bit 24 as Q, but it is in our variable - * 'u', not 'q'. - */ - if (size == 0) { - return 1; - } - switch (op) { - case 0: /* Integer VMLA scalar */ - case 4: /* Integer VMLS scalar */ - case 8: /* Integer VMUL scalar */ - case 1: /* Float VMLA scalar */ - case 5: /* Floating point VMLS scalar */ - case 9: /* Floating point VMUL scalar */ - case 12: /* VQDMULH scalar */ - case 13: /* VQRDMULH scalar */ - case 14: /* VQRDMLAH scalar */ - case 15: /* VQRDMLSH scalar */ - return 1; /* handled by decodetree */ - - case 3: /* VQDMLAL scalar */ - case 7: /* VQDMLSL scalar */ - case 11: /* VQDMULL scalar */ - if (u == 1) { - return 1; - } - /* fall through */ - case 2: /* VMLAL sclar */ - case 6: /* VMLSL scalar */ - case 10: /* VMULL scalar */ - if (rd & 1) { - return 1; - } - tmp2 = neon_get_scalar(size, rm); - /* We need a copy of tmp2 because gen_neon_mull - * deletes it during pass 0. */ - tmp4 = tcg_temp_new_i32(); - tcg_gen_mov_i32(tmp4, tmp2); - tmp3 = neon_load_reg(rn, 1); - - for (pass = 0; pass < 2; pass++) { - if (pass == 0) { - tmp = neon_load_reg(rn, 0); - } else { - tmp = tmp3; - tmp2 = tmp4; - } - gen_neon_mull(cpu_V0, tmp, tmp2, size, u); - if (op != 11) { - neon_load_reg64(cpu_V1, rd + pass); - } - switch (op) { - case 6: - gen_neon_negl(cpu_V0, size); - /* Fall through */ - case 2: - gen_neon_addl(size); - break; - case 3: case 7: - gen_neon_addl_saturate(cpu_V0, cpu_V0, size); - if (op == 7) { - gen_neon_negl(cpu_V0, size); - } - gen_neon_addl_saturate(cpu_V0, cpu_V1, size); - break; - case 10: - /* no-op */ - break; - case 11: - gen_neon_addl_saturate(cpu_V0, cpu_V0, size); - break; - default: - abort(); - } - neon_store_reg64(cpu_V0, rd + pass); - } - break; - default: - g_assert_not_reached(); - } - } + /* + * Three registers of different lengths, or two registers and + * a scalar: handled by decodetree + */ + return 1; } else { /* size == 3 */ if (!u) { /* Extract. */ -- 2.20.1 Convert the Neon VEXT insn to decodetree. Rather than keeping the old implementation which used fixed temporaries cpu_V0 and cpu_V1 and did the extraction with by-hand shift and logic ops, we use the TCG extract2 insn. We don't need to special case 0 or 8 immediates any more as the optimizer is smart enough to throw away the dead code. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/neon-dp.decode | 8 +++- target/arm/translate-neon.inc.c | 76 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 58 +------------------------ 3 files changed, 85 insertions(+), 57 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm # return false for size==3. ###################################################################### { - # 0b11 subgroup will go here + [ + ################################################################## + # Miscellaneous size=0b11 insns + ################################################################## + VEXT 1111 001 0 1 . 11 .... .... imm:4 . q:1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp + ] # Subgroup for size != 0b11 [ diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VQDMLSL_2sc(DisasContext *s, arg_2scalar *a) return do_2scalar_long(s, a, opfn[a->size], accfn[a->size]); } + +static bool trans_VEXT(DisasContext *s, arg_VEXT *a) +{ + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if ((a->vn | a->vm | a->vd) & a->q) { + return false; + } + + if (a->imm > 7 && !a->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + if (!a->q) { + /* Extract 64 bits from <Vm:Vn> */ + TCGv_i64 left, right, dest; + + left = tcg_temp_new_i64(); + right = tcg_temp_new_i64(); + dest = tcg_temp_new_i64(); + + neon_load_reg64(right, a->vn); + neon_load_reg64(left, a->vm); + tcg_gen_extract2_i64(dest, right, left, a->imm * 8); + neon_store_reg64(dest, a->vd); + + tcg_temp_free_i64(left); + tcg_temp_free_i64(right); + tcg_temp_free_i64(dest); + } else { + /* Extract 128 bits from <Vm+1:Vm:Vn+1:Vn> */ + TCGv_i64 left, middle, right, destleft, destright; + + left = tcg_temp_new_i64(); + middle = tcg_temp_new_i64(); + right = tcg_temp_new_i64(); + destleft = tcg_temp_new_i64(); + destright = tcg_temp_new_i64(); + + if (a->imm < 8) { + neon_load_reg64(right, a->vn); + neon_load_reg64(middle, a->vn + 1); + tcg_gen_extract2_i64(destright, right, middle, a->imm * 8); + neon_load_reg64(left, a->vm); + tcg_gen_extract2_i64(destleft, middle, left, a->imm * 8); + } else { + neon_load_reg64(right, a->vn + 1); + neon_load_reg64(middle, a->vm); + tcg_gen_extract2_i64(destright, right, middle, (a->imm - 8) * 8); + neon_load_reg64(left, a->vm + 1); + tcg_gen_extract2_i64(destleft, middle, left, (a->imm - 8) * 8); + } + + neon_store_reg64(destright, a->vd); + neon_store_reg64(destleft, a->vd + 1); + + tcg_temp_free_i64(destright); + tcg_temp_free_i64(destleft); + tcg_temp_free_i64(right); + tcg_temp_free_i64(middle); + tcg_temp_free_i64(left); + } + return true; +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) int pass; int u; int vec_size; - uint32_t imm; TCGv_i32 tmp, tmp2, tmp3, tmp5; TCGv_ptr ptr1; - TCGv_i64 tmp64; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return 1; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } else { /* size == 3 */ if (!u) { - /* Extract. */ - imm = (insn >> 8) & 0xf; - - if (imm > 7 && !q) - return 1; - - if (q && ((rd | rn | rm) & 1)) { - return 1; - } - - if (imm == 0) { - neon_load_reg64(cpu_V0, rn); - if (q) { - neon_load_reg64(cpu_V1, rn + 1); - } - } else if (imm == 8) { - neon_load_reg64(cpu_V0, rn + 1); - if (q) { - neon_load_reg64(cpu_V1, rm); - } - } else if (q) { - tmp64 = tcg_temp_new_i64(); - if (imm < 8) { - neon_load_reg64(cpu_V0, rn); - neon_load_reg64(tmp64, rn + 1); - } else { - neon_load_reg64(cpu_V0, rn + 1); - neon_load_reg64(tmp64, rm); - } - tcg_gen_shri_i64(cpu_V0, cpu_V0, (imm & 7) * 8); - tcg_gen_shli_i64(cpu_V1, tmp64, 64 - ((imm & 7) * 8)); - tcg_gen_or_i64(cpu_V0, cpu_V0, cpu_V1); - if (imm < 8) { - neon_load_reg64(cpu_V1, rm); - } else { - neon_load_reg64(cpu_V1, rm + 1); - imm -= 8; - } - tcg_gen_shli_i64(cpu_V1, cpu_V1, 64 - (imm * 8)); - tcg_gen_shri_i64(tmp64, tmp64, imm * 8); - tcg_gen_or_i64(cpu_V1, cpu_V1, tmp64); - tcg_temp_free_i64(tmp64); - } else { - /* BUGFIX */ - neon_load_reg64(cpu_V0, rn); - tcg_gen_shri_i64(cpu_V0, cpu_V0, imm * 8); - neon_load_reg64(cpu_V1, rm); - tcg_gen_shli_i64(cpu_V1, cpu_V1, 64 - (imm * 8)); - tcg_gen_or_i64(cpu_V0, cpu_V0, cpu_V1); - } - neon_store_reg64(cpu_V0, rd); - if (q) { - neon_store_reg64(cpu_V1, rd + 1); - } + /* Extract: handled by decodetree */ + return 1; } else if ((insn & (1 << 11)) == 0) { /* Two register misc. */ op = ((insn >> 12) & 0x30) | ((insn >> 7) & 0xf); -- 2.20.1 Convert the Neon VTBL, VTBX instructions to decodetree. The actual implementation of the insn is copied across to the new trans function unchanged except for renaming 'tmp5' to 'tmp4'. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/neon-dp.decode | 3 ++ target/arm/translate-neon.inc.c | 56 +++++++++++++++++++++++++++++++++ target/arm/translate.c | 41 +++--------------------- 3 files changed, 63 insertions(+), 37 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm ################################################################## VEXT 1111 001 0 1 . 11 .... .... imm:4 . q:1 . 0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp + + VTBL 1111 001 1 1 . 11 .... .... 10 len:2 . op:1 . 0 .... \ + vm=%vm_dp vn=%vn_dp vd=%vd_dp ] # Subgroup for size != 0b11 diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VEXT(DisasContext *s, arg_VEXT *a) } return true; } + +static bool trans_VTBL(DisasContext *s, arg_VTBL *a) +{ + int n; + TCGv_i32 tmp, tmp2, tmp3, tmp4; + TCGv_ptr ptr1; + + if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { + return false; + } + + /* UNDEF accesses to D16-D31 if they don't exist. */ + if (!dc_isar_feature(aa32_simd_r32, s) && + ((a->vd | a->vn | a->vm) & 0x10)) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + n = a->len + 1; + if ((a->vn + n) > 32) { + /* + * This is UNPREDICTABLE; we choose to UNDEF to avoid the + * helper function running off the end of the register file. + */ + return false; + } + n <<= 3; + if (a->op) { + tmp = neon_load_reg(a->vd, 0); + } else { + tmp = tcg_temp_new_i32(); + tcg_gen_movi_i32(tmp, 0); + } + tmp2 = neon_load_reg(a->vm, 0); + ptr1 = vfp_reg_ptr(true, a->vn); + tmp4 = tcg_const_i32(n); + gen_helper_neon_tbl(tmp2, tmp2, tmp, ptr1, tmp4); + tcg_temp_free_i32(tmp); + if (a->op) { + tmp = neon_load_reg(a->vd, 1); + } else { + tmp = tcg_temp_new_i32(); + tcg_gen_movi_i32(tmp, 0); + } + tmp3 = neon_load_reg(a->vm, 1); + gen_helper_neon_tbl(tmp3, tmp3, tmp, ptr1, tmp4); + tcg_temp_free_i32(tmp4); + tcg_temp_free_ptr(ptr1); + neon_store_reg(a->vd, 0, tmp2); + neon_store_reg(a->vd, 1, tmp3); + tcg_temp_free_i32(tmp); + return true; +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) { int op; int q; - int rd, rn, rm, rd_ofs, rm_ofs; + int rd, rm, rd_ofs, rm_ofs; int size; int pass; int u; int vec_size; - TCGv_i32 tmp, tmp2, tmp3, tmp5; - TCGv_ptr ptr1; + TCGv_i32 tmp, tmp2, tmp3; if (!arm_dc_feature(s, ARM_FEATURE_NEON)) { return 1; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) q = (insn & (1 << 6)) != 0; u = (insn >> 24) & 1; VFP_DREG_D(rd, insn); - VFP_DREG_N(rn, insn); VFP_DREG_M(rm, insn); size = (insn >> 20) & 3; vec_size = q ? 16 : 8; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) break; } } else if ((insn & (1 << 10)) == 0) { - /* VTBL, VTBX. */ - int n = ((insn >> 8) & 3) + 1; - if ((rn + n) > 32) { - /* This is UNPREDICTABLE; we choose to UNDEF to avoid the - * helper function running off the end of the register file. - */ - return 1; - } - n <<= 3; - if (insn & (1 << 6)) { - tmp = neon_load_reg(rd, 0); - } else { - tmp = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp, 0); - } - tmp2 = neon_load_reg(rm, 0); - ptr1 = vfp_reg_ptr(true, rn); - tmp5 = tcg_const_i32(n); - gen_helper_neon_tbl(tmp2, tmp2, tmp, ptr1, tmp5); - tcg_temp_free_i32(tmp); - if (insn & (1 << 6)) { - tmp = neon_load_reg(rd, 1); - } else { - tmp = tcg_temp_new_i32(); - tcg_gen_movi_i32(tmp, 0); - } - tmp3 = neon_load_reg(rm, 1); - gen_helper_neon_tbl(tmp3, tmp3, tmp, ptr1, tmp5); - tcg_temp_free_i32(tmp5); - tcg_temp_free_ptr(ptr1); - neon_store_reg(rd, 0, tmp2); - neon_store_reg(rd, 1, tmp3); - tcg_temp_free_i32(tmp); + /* VTBL, VTBX: handled by decodetree */ + return 1; } else if ((insn & 0x380) == 0) { /* VDUP */ int element; -- 2.20.1 Convert the Neon VDUP (scalar) insn to decodetree. (Note that we can't call this just "VDUP" as we used that already in vfp.decode for the "VDUP (general purpose register" insn.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/neon-dp.decode | 7 +++++++ target/arm/translate-neon.inc.c | 26 ++++++++++++++++++++++++++ target/arm/translate.c | 25 +------------------------ 3 files changed, 34 insertions(+), 24 deletions(-) diff --git a/target/arm/neon-dp.decode b/target/arm/neon-dp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/neon-dp.decode +++ b/target/arm/neon-dp.decode @@ -XXX,XX +XXX,XX @@ Vimm_1r 1111 001 . 1 . 000 ... .... cmode:4 0 . op:1 1 .... @1reg_imm VTBL 1111 001 1 1 . 11 .... .... 10 len:2 . op:1 . 0 .... \ vm=%vm_dp vn=%vn_dp vd=%vd_dp + + VDUP_scalar 1111 001 1 1 . 11 index:3 1 .... 11 000 q:1 . 0 .... \ + vm=%vm_dp vd=%vd_dp size=0 + VDUP_scalar 1111 001 1 1 . 11 index:2 10 .... 11 000 q:1 . 0 .... \ + vm=%vm_dp vd=%vd_dp size=1 + VDUP_scalar 1111 001 1 1 . 11 index:1 100 .... 11 000 q:1 . 0 .... \ + vm=%vm_dp vd=%vd_dp size=2 ] # Subgroup for size != 0b11 diff --git a/target/arm/translate-neon.inc.c b/target/arm/translate-neon.inc.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.inc.c +++ b/target/arm/translate-neon.inc.c @@ -XXX,XX +XXX,XX @@ static bool trans_VTBL(DisasContext *s, arg_VTBL *a) tcg_temp_free_i32(tmp); return true; } + +static bool trans_VDUP_scalar(DisasContext *s, arg_VDUP_scalar *a) +{ + 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->q) { + return false; + } + + if (!vfp_access_check(s)) { + return true; + } + + tcg_gen_gvec_dup_mem(a->size, neon_reg_offset(a->vd, 0), + neon_element_offset(a->vm, a->index, a->size), + a->q ? 16 : 8, a->q ? 16 : 8); + return true; +} diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } break; } - } else if ((insn & (1 << 10)) == 0) { - /* VTBL, VTBX: handled by decodetree */ - return 1; - } else if ((insn & 0x380) == 0) { - /* VDUP */ - int element; - MemOp size; - - if ((insn & (7 << 16)) == 0 || (q && (rd & 1))) { - return 1; - } - if (insn & (1 << 16)) { - size = MO_8; - element = (insn >> 17) & 7; - } else if (insn & (1 << 17)) { - size = MO_16; - element = (insn >> 18) & 3; - } else { - size = MO_32; - element = (insn >> 19) & 1; - } - tcg_gen_gvec_dup_mem(size, neon_reg_offset(rd, 0), - neon_element_offset(rm, element, size), - q ? 16 : 8, q ? 16 : 8); } else { + /* VTBL, VTBX, VDUP: handled by decodetree */ return 1; } } -- 2.20.1 From: Jean-Christophe Dubois <jcd@tribudubois.net> Some bits of the CCM registers are non writable. This was left undone in the initial commit (all bits of registers were writable). This patch adds the required code to protect the non writable bits. Signed-off-by: Jean-Christophe Dubois <jcd@tribudubois.net> Message-id: 20200608133508.550046-1-jcd@tribudubois.net Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/imx6ul_ccm.c | 76 ++++++++++++++++++++++++++++++++++++-------- 1 file changed, 63 insertions(+), 13 deletions(-) diff --git a/hw/misc/imx6ul_ccm.c b/hw/misc/imx6ul_ccm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/imx6ul_ccm.c +++ b/hw/misc/imx6ul_ccm.c @@ -XXX,XX +XXX,XX @@ #include "trace.h" +static const uint32_t ccm_mask[CCM_MAX] = { + [CCM_CCR] = 0xf01fef80, + [CCM_CCDR] = 0xfffeffff, + [CCM_CSR] = 0xffffffff, + [CCM_CCSR] = 0xfffffef2, + [CCM_CACRR] = 0xfffffff8, + [CCM_CBCDR] = 0xc1f8e000, + [CCM_CBCMR] = 0xfc03cfff, + [CCM_CSCMR1] = 0x80700000, + [CCM_CSCMR2] = 0xe01ff003, + [CCM_CSCDR1] = 0xfe00c780, + [CCM_CS1CDR] = 0xfe00fe00, + [CCM_CS2CDR] = 0xf8007000, + [CCM_CDCDR] = 0xf00fffff, + [CCM_CHSCCDR] = 0xfffc01ff, + [CCM_CSCDR2] = 0xfe0001ff, + [CCM_CSCDR3] = 0xffffc1ff, + [CCM_CDHIPR] = 0xffffffff, + [CCM_CTOR] = 0x00000000, + [CCM_CLPCR] = 0xf39ff01c, + [CCM_CISR] = 0xfb85ffbe, + [CCM_CIMR] = 0xfb85ffbf, + [CCM_CCOSR] = 0xfe00fe00, + [CCM_CGPR] = 0xfffc3fea, + [CCM_CCGR0] = 0x00000000, + [CCM_CCGR1] = 0x00000000, + [CCM_CCGR2] = 0x00000000, + [CCM_CCGR3] = 0x00000000, + [CCM_CCGR4] = 0x00000000, + [CCM_CCGR5] = 0x00000000, + [CCM_CCGR6] = 0x00000000, + [CCM_CMEOR] = 0xafffff1f, +}; + +static const uint32_t analog_mask[CCM_ANALOG_MAX] = { + [CCM_ANALOG_PLL_ARM] = 0xfff60f80, + [CCM_ANALOG_PLL_USB1] = 0xfffe0fbc, + [CCM_ANALOG_PLL_USB2] = 0xfffe0fbc, + [CCM_ANALOG_PLL_SYS] = 0xfffa0ffe, + [CCM_ANALOG_PLL_SYS_SS] = 0x00000000, + [CCM_ANALOG_PLL_SYS_NUM] = 0xc0000000, + [CCM_ANALOG_PLL_SYS_DENOM] = 0xc0000000, + [CCM_ANALOG_PLL_AUDIO] = 0xffe20f80, + [CCM_ANALOG_PLL_AUDIO_NUM] = 0xc0000000, + [CCM_ANALOG_PLL_AUDIO_DENOM] = 0xc0000000, + [CCM_ANALOG_PLL_VIDEO] = 0xffe20f80, + [CCM_ANALOG_PLL_VIDEO_NUM] = 0xc0000000, + [CCM_ANALOG_PLL_VIDEO_DENOM] = 0xc0000000, + [CCM_ANALOG_PLL_ENET] = 0xffc20ff0, + [CCM_ANALOG_PFD_480] = 0x40404040, + [CCM_ANALOG_PFD_528] = 0x40404040, + [PMU_MISC0] = 0x01fe8306, + [PMU_MISC1] = 0x07fcede0, + [PMU_MISC2] = 0x005f5f5f, +}; + static const char *imx6ul_ccm_reg_name(uint32_t reg) { static char unknown[20]; @@ -XXX,XX +XXX,XX @@ static void imx6ul_ccm_write(void *opaque, hwaddr offset, uint64_t value, trace_ccm_write_reg(imx6ul_ccm_reg_name(index), (uint32_t)value); - /* - * We will do a better implementation later. In particular some bits - * cannot be written to. - */ - s->ccm[index] = (uint32_t)value; + s->ccm[index] = (s->ccm[index] & ccm_mask[index]) | + ((uint32_t)value & ~ccm_mask[index]); } static uint64_t imx6ul_analog_read(void *opaque, hwaddr offset, unsigned size) @@ -XXX,XX +XXX,XX @@ static void imx6ul_analog_write(void *opaque, hwaddr offset, uint64_t value, * the REG_NAME register. So we change the value of the * REG_NAME register, setting bits passed in the value. */ - s->analog[index - 1] |= value; + s->analog[index - 1] |= (value & ~analog_mask[index - 1]); break; case CCM_ANALOG_PLL_ARM_CLR: case CCM_ANALOG_PLL_USB1_CLR: @@ -XXX,XX +XXX,XX @@ static void imx6ul_analog_write(void *opaque, hwaddr offset, uint64_t value, * the REG_NAME register. So we change the value of the * REG_NAME register, unsetting bits passed in the value. */ - s->analog[index - 2] &= ~value; + s->analog[index - 2] &= ~(value & ~analog_mask[index - 2]); break; case CCM_ANALOG_PLL_ARM_TOG: case CCM_ANALOG_PLL_USB1_TOG: @@ -XXX,XX +XXX,XX @@ static void imx6ul_analog_write(void *opaque, hwaddr offset, uint64_t value, * the REG_NAME register. So we change the value of the * REG_NAME register, toggling bits passed in the value. */ - s->analog[index - 3] ^= value; + s->analog[index - 3] ^= (value & ~analog_mask[index - 3]); break; default: - /* - * We will do a better implementation later. In particular some bits - * cannot be written to. - */ - s->analog[index] = value; + s->analog[index] = (s->analog[index] & analog_mask[index]) | + (value & ~analog_mask[index]); break; } } -- 2.20.1 From: Erik Smit <erik.lucas.smit@gmail.com> The hardware supports configurable descriptor sizes, configured in the DBLAC register. Most drivers use the default 4 word descriptor, which is currently hardcoded, but Aspeed SDK configures 8 words to store extra data. Signed-off-by: Erik Smit <erik.lucas.smit@gmail.com> Reviewed-by: Cédric Le Goater <clg@kaod.org> [PMM: removed unnecessary parens] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/ftgmac100.c | 26 ++++++++++++++++++++++++-- 1 file changed, 24 insertions(+), 2 deletions(-) diff --git a/hw/net/ftgmac100.c b/hw/net/ftgmac100.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/ftgmac100.c +++ b/hw/net/ftgmac100.c @@ -XXX,XX +XXX,XX @@ #define FTGMAC100_APTC_TXPOLL_CNT(x) (((x) >> 8) & 0xf) #define FTGMAC100_APTC_TXPOLL_TIME_SEL (1 << 12) +/* + * DMA burst length and arbitration control register + */ +#define FTGMAC100_DBLAC_RXBURST_SIZE(x) (((x) >> 8) & 0x3) +#define FTGMAC100_DBLAC_TXBURST_SIZE(x) (((x) >> 10) & 0x3) +#define FTGMAC100_DBLAC_RXDES_SIZE(x) ((((x) >> 12) & 0xf) * 8) +#define FTGMAC100_DBLAC_TXDES_SIZE(x) ((((x) >> 16) & 0xf) * 8) +#define FTGMAC100_DBLAC_IFG_CNT(x) (((x) >> 20) & 0x7) +#define FTGMAC100_DBLAC_IFG_INC (1 << 23) + /* * PHY control register */ @@ -XXX,XX +XXX,XX @@ static void ftgmac100_do_tx(FTGMAC100State *s, uint32_t tx_ring, if (bd.des0 & s->txdes0_edotr) { addr = tx_ring; } else { - addr += sizeof(FTGMAC100Desc); + addr += FTGMAC100_DBLAC_TXDES_SIZE(s->dblac); } } @@ -XXX,XX +XXX,XX @@ static void ftgmac100_write(void *opaque, hwaddr addr, s->phydata = value & 0xffff; break; case FTGMAC100_DBLAC: /* DMA Burst Length and Arbitration Control */ + if (FTGMAC100_DBLAC_TXDES_SIZE(s->dblac) < sizeof(FTGMAC100Desc)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: transmit descriptor too small : %d bytes\n", + __func__, FTGMAC100_DBLAC_TXDES_SIZE(s->dblac)); + break; + } + if (FTGMAC100_DBLAC_RXDES_SIZE(s->dblac) < sizeof(FTGMAC100Desc)) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: receive descriptor too small : %d bytes\n", + __func__, FTGMAC100_DBLAC_RXDES_SIZE(s->dblac)); + break; + } s->dblac = value; break; case FTGMAC100_REVR: /* Feature Register */ @@ -XXX,XX +XXX,XX @@ static ssize_t ftgmac100_receive(NetClientState *nc, const uint8_t *buf, if (bd.des0 & s->rxdes0_edorr) { addr = s->rx_ring; } else { - addr += sizeof(FTGMAC100Desc); + addr += FTGMAC100_DBLAC_RXDES_SIZE(s->dblac); } } s->rx_descriptor = addr; -- 2.20.1 From: fangying <fangying1@huawei.com> Virtual time adjustment was implemented for virt-5.0 machine type, but the cpu property was enabled only for host-passthrough and max cpu model. Let's add it for any KVM arm cpu which has the generic timer feature enabled. Signed-off-by: Ying Fang <fangying1@huawei.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Message-id: 20200608121243.2076-1-fangying1@huawei.com [PMM: minor commit message tweak, removed inaccurate suggested-by tag] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 6 ++++-- target/arm/cpu64.c | 1 - target/arm/kvm.c | 21 +++++++++++---------- 3 files changed, 15 insertions(+), 13 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ void arm_cpu_post_init(Object *obj) if (arm_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER)) { qdev_property_add_static(DEVICE(cpu), &arm_cpu_gt_cntfrq_property); } + + if (kvm_enabled()) { + kvm_arm_add_vcpu_properties(obj); + } } static void arm_cpu_finalizefn(Object *obj) @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) if (kvm_enabled()) { kvm_arm_set_cpu_features_from_host(cpu); - kvm_arm_add_vcpu_properties(obj); } else { cortex_a15_initfn(obj); @@ -XXX,XX +XXX,XX @@ static void arm_host_initfn(Object *obj) if (arm_feature(&cpu->env, ARM_FEATURE_AARCH64)) { aarch64_add_sve_properties(obj); } - kvm_arm_add_vcpu_properties(obj); arm_cpu_post_init(obj); } diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) if (kvm_enabled()) { kvm_arm_set_cpu_features_from_host(cpu); - kvm_arm_add_vcpu_properties(obj); } else { uint64_t t; uint32_t u; diff --git a/target/arm/kvm.c b/target/arm/kvm.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm.c +++ b/target/arm/kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_no_adjvtime_set(Object *obj, bool value, Error **errp) /* KVM VCPU properties should be prefixed with "kvm-". */ void kvm_arm_add_vcpu_properties(Object *obj) { - if (!kvm_enabled()) { - return; - } + ARMCPU *cpu = ARM_CPU(obj); + CPUARMState *env = &cpu->env; - ARM_CPU(obj)->kvm_adjvtime = true; - object_property_add_bool(obj, "kvm-no-adjvtime", kvm_no_adjvtime_get, - kvm_no_adjvtime_set); - object_property_set_description(obj, "kvm-no-adjvtime", - "Set on to disable the adjustment of " - "the virtual counter. VM stopped time " - "will be counted."); + if (arm_feature(env, ARM_FEATURE_GENERIC_TIMER)) { + cpu->kvm_adjvtime = true; + object_property_add_bool(obj, "kvm-no-adjvtime", kvm_no_adjvtime_get, + kvm_no_adjvtime_set); + object_property_set_description(obj, "kvm-no-adjvtime", + "Set on to disable the adjustment of " + "the virtual counter. VM stopped time " + "will be counted."); + } } bool kvm_arm_pmu_supported(CPUState *cpu) -- 2.20.1 From: Jean-Christophe Dubois <jcd@tribudubois.net> Signed-off-by: Jean-Christophe Dubois <jcd@tribudubois.net> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> [PMD: Fixed 32-bit format string using PRIx32/PRIx64] Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/imx_fec.c | 106 +++++++++++++++++++------------------------- hw/net/trace-events | 18 ++++++++ 2 files changed, 63 insertions(+), 61 deletions(-) diff --git a/hw/net/imx_fec.c b/hw/net/imx_fec.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/imx_fec.c +++ b/hw/net/imx_fec.c @@ -XXX,XX +XXX,XX @@ #include "qemu/module.h" #include "net/checksum.h" #include "net/eth.h" +#include "trace.h" /* For crc32 */ #include <zlib.h> -#ifndef DEBUG_IMX_FEC -#define DEBUG_IMX_FEC 0 -#endif - -#define FEC_PRINTF(fmt, args...) \ - do { \ - if (DEBUG_IMX_FEC) { \ - fprintf(stderr, "[%s]%s: " fmt , TYPE_IMX_FEC, \ - __func__, ##args); \ - } \ - } while (0) - -#ifndef DEBUG_IMX_PHY -#define DEBUG_IMX_PHY 0 -#endif - -#define PHY_PRINTF(fmt, args...) \ - do { \ - if (DEBUG_IMX_PHY) { \ - fprintf(stderr, "[%s.phy]%s: " fmt , TYPE_IMX_FEC, \ - __func__, ##args); \ - } \ - } while (0) - #define IMX_MAX_DESC 1024 static const char *imx_default_reg_name(IMXFECState *s, uint32_t index) @@ -XXX,XX +XXX,XX @@ static void imx_eth_update(IMXFECState *s); * For now we don't handle any GPIO/interrupt line, so the OS will * have to poll for the PHY status. */ -static void phy_update_irq(IMXFECState *s) +static void imx_phy_update_irq(IMXFECState *s) { imx_eth_update(s); } -static void phy_update_link(IMXFECState *s) +static void imx_phy_update_link(IMXFECState *s) { /* Autonegotiation status mirrors link status. */ if (qemu_get_queue(s->nic)->link_down) { - PHY_PRINTF("link is down\n"); + trace_imx_phy_update_link("down"); s->phy_status &= ~0x0024; s->phy_int |= PHY_INT_DOWN; } else { - PHY_PRINTF("link is up\n"); + trace_imx_phy_update_link("up"); s->phy_status |= 0x0024; s->phy_int |= PHY_INT_ENERGYON; s->phy_int |= PHY_INT_AUTONEG_COMPLETE; } - phy_update_irq(s); + imx_phy_update_irq(s); } static void imx_eth_set_link(NetClientState *nc) { - phy_update_link(IMX_FEC(qemu_get_nic_opaque(nc))); + imx_phy_update_link(IMX_FEC(qemu_get_nic_opaque(nc))); } -static void phy_reset(IMXFECState *s) +static void imx_phy_reset(IMXFECState *s) { + trace_imx_phy_reset(); + s->phy_status = 0x7809; s->phy_control = 0x3000; s->phy_advertise = 0x01e1; s->phy_int_mask = 0; s->phy_int = 0; - phy_update_link(s); + imx_phy_update_link(s); } -static uint32_t do_phy_read(IMXFECState *s, int reg) +static uint32_t imx_phy_read(IMXFECState *s, int reg) { uint32_t val; @@ -XXX,XX +XXX,XX @@ static uint32_t do_phy_read(IMXFECState *s, int reg) case 29: /* Interrupt source. */ val = s->phy_int; s->phy_int = 0; - phy_update_irq(s); + imx_phy_update_irq(s); break; case 30: /* Interrupt mask */ val = s->phy_int_mask; @@ -XXX,XX +XXX,XX @@ static uint32_t do_phy_read(IMXFECState *s, int reg) break; } - PHY_PRINTF("read 0x%04x @ %d\n", val, reg); + trace_imx_phy_read(val, reg); return val; } -static void do_phy_write(IMXFECState *s, int reg, uint32_t val) +static void imx_phy_write(IMXFECState *s, int reg, uint32_t val) { - PHY_PRINTF("write 0x%04x @ %d\n", val, reg); + trace_imx_phy_write(val, reg); if (reg > 31) { /* we only advertise one phy */ @@ -XXX,XX +XXX,XX @@ static void do_phy_write(IMXFECState *s, int reg, uint32_t val) switch (reg) { case 0: /* Basic Control */ if (val & 0x8000) { - phy_reset(s); + imx_phy_reset(s); } else { s->phy_control = val & 0x7980; /* Complete autonegotiation immediately. */ @@ -XXX,XX +XXX,XX @@ static void do_phy_write(IMXFECState *s, int reg, uint32_t val) break; case 30: /* Interrupt mask */ s->phy_int_mask = val & 0xff; - phy_update_irq(s); + imx_phy_update_irq(s); break; case 17: case 18: @@ -XXX,XX +XXX,XX @@ static void do_phy_write(IMXFECState *s, int reg, uint32_t val) static void imx_fec_read_bd(IMXFECBufDesc *bd, dma_addr_t addr) { dma_memory_read(&address_space_memory, addr, bd, sizeof(*bd)); + + trace_imx_fec_read_bd(addr, bd->flags, bd->length, bd->data); } static void imx_fec_write_bd(IMXFECBufDesc *bd, dma_addr_t addr) @@ -XXX,XX +XXX,XX @@ static void imx_fec_write_bd(IMXFECBufDesc *bd, dma_addr_t addr) static void imx_enet_read_bd(IMXENETBufDesc *bd, dma_addr_t addr) { dma_memory_read(&address_space_memory, addr, bd, sizeof(*bd)); + + trace_imx_enet_read_bd(addr, bd->flags, bd->length, bd->data, + bd->option, bd->status); } static void imx_enet_write_bd(IMXENETBufDesc *bd, dma_addr_t addr) @@ -XXX,XX +XXX,XX @@ static void imx_fec_do_tx(IMXFECState *s) int len; imx_fec_read_bd(&bd, addr); - FEC_PRINTF("tx_bd %x flags %04x len %d data %08x\n", - addr, bd.flags, bd.length, bd.data); if ((bd.flags & ENET_BD_R) == 0) { + /* Run out of descriptors to transmit. */ - FEC_PRINTF("tx_bd ran out of descriptors to transmit\n"); + trace_imx_eth_tx_bd_busy(); + break; } len = bd.length; @@ -XXX,XX +XXX,XX @@ static void imx_enet_do_tx(IMXFECState *s, uint32_t index) int len; imx_enet_read_bd(&bd, addr); - FEC_PRINTF("tx_bd %x flags %04x len %d data %08x option %04x " - "status %04x\n", addr, bd.flags, bd.length, bd.data, - bd.option, bd.status); if ((bd.flags & ENET_BD_R) == 0) { /* Run out of descriptors to transmit. */ + + trace_imx_eth_tx_bd_busy(); + break; } len = bd.length; @@ -XXX,XX +XXX,XX @@ static void imx_eth_enable_rx(IMXFECState *s, bool flush) s->regs[ENET_RDAR] = (bd.flags & ENET_BD_E) ? ENET_RDAR_RDAR : 0; if (!s->regs[ENET_RDAR]) { - FEC_PRINTF("RX buffer full\n"); + trace_imx_eth_rx_bd_full(); } else if (flush) { qemu_flush_queued_packets(qemu_get_queue(s->nic)); } @@ -XXX,XX +XXX,XX @@ static void imx_eth_reset(DeviceState *d) memset(s->tx_descriptor, 0, sizeof(s->tx_descriptor)); /* We also reset the PHY */ - phy_reset(s); + imx_phy_reset(s); } static uint32_t imx_default_read(IMXFECState *s, uint32_t index) @@ -XXX,XX +XXX,XX @@ static uint64_t imx_eth_read(void *opaque, hwaddr offset, unsigned size) break; } - FEC_PRINTF("reg[%s] => 0x%" PRIx32 "\n", imx_eth_reg_name(s, index), - value); + trace_imx_eth_read(index, imx_eth_reg_name(s, index), value); return value; } @@ -XXX,XX +XXX,XX @@ static void imx_eth_write(void *opaque, hwaddr offset, uint64_t value, const bool single_tx_ring = !imx_eth_is_multi_tx_ring(s); uint32_t index = offset >> 2; - FEC_PRINTF("reg[%s] <= 0x%" PRIx32 "\n", imx_eth_reg_name(s, index), - (uint32_t)value); + trace_imx_eth_write(index, imx_eth_reg_name(s, index), value); switch (index) { case ENET_EIR: @@ -XXX,XX +XXX,XX @@ static void imx_eth_write(void *opaque, hwaddr offset, uint64_t value, if (extract32(value, 29, 1)) { /* This is a read operation */ s->regs[ENET_MMFR] = deposit32(s->regs[ENET_MMFR], 0, 16, - do_phy_read(s, + imx_phy_read(s, extract32(value, 18, 10))); } else { /* This a write operation */ - do_phy_write(s, extract32(value, 18, 10), extract32(value, 0, 16)); + imx_phy_write(s, extract32(value, 18, 10), extract32(value, 0, 16)); } /* raise the interrupt as the PHY operation is done */ s->regs[ENET_EIR] |= ENET_INT_MII; @@ -XXX,XX +XXX,XX @@ static bool imx_eth_can_receive(NetClientState *nc) { IMXFECState *s = IMX_FEC(qemu_get_nic_opaque(nc)); - FEC_PRINTF("\n"); - return !!s->regs[ENET_RDAR]; } @@ -XXX,XX +XXX,XX @@ static ssize_t imx_fec_receive(NetClientState *nc, const uint8_t *buf, unsigned int buf_len; size_t size = len; - FEC_PRINTF("len %d\n", (int)size); + trace_imx_fec_receive(size); if (!s->regs[ENET_RDAR]) { qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Unexpected packet\n", @@ -XXX,XX +XXX,XX @@ static ssize_t imx_fec_receive(NetClientState *nc, const uint8_t *buf, bd.length = buf_len; size -= buf_len; - FEC_PRINTF("rx_bd 0x%x length %d\n", addr, bd.length); + trace_imx_fec_receive_len(addr, bd.length); /* The last 4 bytes are the CRC. */ if (size < 4) { @@ -XXX,XX +XXX,XX @@ static ssize_t imx_fec_receive(NetClientState *nc, const uint8_t *buf, if (size == 0) { /* Last buffer in frame. */ bd.flags |= flags | ENET_BD_L; - FEC_PRINTF("rx frame flags %04x\n", bd.flags); + + trace_imx_fec_receive_last(bd.flags); + s->regs[ENET_EIR] |= ENET_INT_RXF; } else { s->regs[ENET_EIR] |= ENET_INT_RXB; @@ -XXX,XX +XXX,XX @@ static ssize_t imx_enet_receive(NetClientState *nc, const uint8_t *buf, size_t size = len; bool shift16 = s->regs[ENET_RACC] & ENET_RACC_SHIFT16; - FEC_PRINTF("len %d\n", (int)size); + trace_imx_enet_receive(size); if (!s->regs[ENET_RDAR]) { qemu_log_mask(LOG_GUEST_ERROR, "[%s]%s: Unexpected packet\n", @@ -XXX,XX +XXX,XX @@ static ssize_t imx_enet_receive(NetClientState *nc, const uint8_t *buf, bd.length = buf_len; size -= buf_len; - FEC_PRINTF("rx_bd 0x%x length %d\n", addr, bd.length); + trace_imx_enet_receive_len(addr, bd.length); /* The last 4 bytes are the CRC. */ if (size < 4) { @@ -XXX,XX +XXX,XX @@ static ssize_t imx_enet_receive(NetClientState *nc, const uint8_t *buf, if (size == 0) { /* Last buffer in frame. */ bd.flags |= flags | ENET_BD_L; - FEC_PRINTF("rx frame flags %04x\n", bd.flags); + + trace_imx_enet_receive_last(bd.flags); + /* Indicate that we've updated the last buffer descriptor. */ bd.last_buffer = ENET_BD_BDU; if (bd.option & ENET_BD_RX_INT) { diff --git a/hw/net/trace-events b/hw/net/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/net/trace-events +++ b/hw/net/trace-events @@ -XXX,XX +XXX,XX @@ i82596_receive_packet(size_t sz) "len=%zu" i82596_new_mac(const char *id_with_mac) "New MAC for: %s" i82596_set_multicast(uint16_t count) "Added %d multicast entries" i82596_channel_attention(void *s) "%p: Received CHANNEL ATTENTION" + +# imx_fec.c +imx_phy_read(uint32_t val, int reg) "0x%04"PRIx32" <= reg[%d]" +imx_phy_write(uint32_t val, int reg) "0x%04"PRIx32" => reg[%d]" +imx_phy_update_link(const char *s) "%s" +imx_phy_reset(void) "" +imx_fec_read_bd(uint64_t addr, int flags, int len, int data) "tx_bd 0x%"PRIx64" flags 0x%04x len %d data 0x%08x" +imx_enet_read_bd(uint64_t addr, int flags, int len, int data, int options, int status) "tx_bd 0x%"PRIx64" flags 0x%04x len %d data 0x%08x option 0x%04x status 0x%04x" +imx_eth_tx_bd_busy(void) "tx_bd ran out of descriptors to transmit" +imx_eth_rx_bd_full(void) "RX buffer is full" +imx_eth_read(int reg, const char *reg_name, uint32_t value) "reg[%d:%s] => 0x%08"PRIx32 +imx_eth_write(int reg, const char *reg_name, uint64_t value) "reg[%d:%s] <= 0x%08"PRIx64 +imx_fec_receive(size_t size) "len %zu" +imx_fec_receive_len(uint64_t addr, int len) "rx_bd 0x%"PRIx64" length %d" +imx_fec_receive_last(int last) "rx frame flags 0x%04x" +imx_enet_receive(size_t size) "len %zu" +imx_enet_receive_len(uint64_t addr, int len) "rx_bd 0x%"PRIx64" length %d" +imx_enet_receive_last(int last) "rx frame flags 0x%04x" -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> The Linux kernel's IMX code now uses vendor specific commands. This results in endless warnings when booting the Linux kernel. sdhci-esdhc-imx 2194000.usdhc: esdhc_wait_for_card_clock_gate_off: card clock still not gate off in 100us!. Implement support for the vendor specific command implemented in IMX hardware to be able to avoid this warning. Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20200603145258.195920-2-linux@roeck-us.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/sdhci-internal.h | 5 +++++ include/hw/sd/sdhci.h | 5 +++++ hw/sd/sdhci.c | 18 +++++++++++++++++- 3 files changed, 27 insertions(+), 1 deletion(-) diff --git a/hw/sd/sdhci-internal.h b/hw/sd/sdhci-internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/sdhci-internal.h +++ b/hw/sd/sdhci-internal.h @@ -XXX,XX +XXX,XX @@ #define SDHC_CMD_INHIBIT 0x00000001 #define SDHC_DATA_INHIBIT 0x00000002 #define SDHC_DAT_LINE_ACTIVE 0x00000004 +#define SDHC_IMX_CLOCK_GATE_OFF 0x00000080 #define SDHC_DOING_WRITE 0x00000100 #define SDHC_DOING_READ 0x00000200 #define SDHC_SPACE_AVAILABLE 0x00000400 @@ -XXX,XX +XXX,XX @@ extern const VMStateDescription sdhci_vmstate; #define ESDHC_MIX_CTRL 0x48 + #define ESDHC_VENDOR_SPEC 0xc0 +#define ESDHC_IMX_FRC_SDCLK_ON (1 << 8) + #define ESDHC_DLL_CTRL 0x60 #define ESDHC_TUNING_CTRL 0xcc @@ -XXX,XX +XXX,XX @@ extern const VMStateDescription sdhci_vmstate; #define DEFINE_SDHCI_COMMON_PROPERTIES(_state) \ DEFINE_PROP_UINT8("sd-spec-version", _state, sd_spec_version, 2), \ DEFINE_PROP_UINT8("uhs", _state, uhs_mode, UHS_NOT_SUPPORTED), \ + DEFINE_PROP_UINT8("vendor", _state, vendor, SDHCI_VENDOR_NONE), \ \ /* Capabilities registers provide information on supported * features of this specific host controller implementation */ \ diff --git a/include/hw/sd/sdhci.h b/include/hw/sd/sdhci.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/sd/sdhci.h +++ b/include/hw/sd/sdhci.h @@ -XXX,XX +XXX,XX @@ typedef struct SDHCIState { uint16_t acmd12errsts; /* Auto CMD12 error status register */ uint16_t hostctl2; /* Host Control 2 */ uint64_t admasysaddr; /* ADMA System Address Register */ + uint16_t vendor_spec; /* Vendor specific register */ /* Read-only registers */ uint64_t capareg; /* Capabilities Register */ @@ -XXX,XX +XXX,XX @@ typedef struct SDHCIState { uint32_t quirks; uint8_t sd_spec_version; uint8_t uhs_mode; + uint8_t vendor; /* For vendor specific functionality */ } SDHCIState; +#define SDHCI_VENDOR_NONE 0 +#define SDHCI_VENDOR_IMX 1 + /* * Controller does not provide transfer-complete interrupt when not * busy. diff --git a/hw/sd/sdhci.c b/hw/sd/sdhci.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/sdhci.c +++ b/hw/sd/sdhci.c @@ -XXX,XX +XXX,XX @@ static uint64_t usdhc_read(void *opaque, hwaddr offset, unsigned size) } break; + case ESDHC_VENDOR_SPEC: + ret = s->vendor_spec; + break; case ESDHC_DLL_CTRL: case ESDHC_TUNE_CTRL_STATUS: case ESDHC_UNDOCUMENTED_REG27: case ESDHC_TUNING_CTRL: - case ESDHC_VENDOR_SPEC: case ESDHC_MIX_CTRL: case ESDHC_WTMK_LVL: ret = 0; @@ -XXX,XX +XXX,XX @@ usdhc_write(void *opaque, hwaddr offset, uint64_t val, unsigned size) case ESDHC_UNDOCUMENTED_REG27: case ESDHC_TUNING_CTRL: case ESDHC_WTMK_LVL: + break; + case ESDHC_VENDOR_SPEC: + s->vendor_spec = value; + switch (s->vendor) { + case SDHCI_VENDOR_IMX: + if (value & ESDHC_IMX_FRC_SDCLK_ON) { + s->prnsts &= ~SDHC_IMX_CLOCK_GATE_OFF; + } else { + s->prnsts |= SDHC_IMX_CLOCK_GATE_OFF; + } + break; + default: + break; + } break; case SDHC_HOSTCTL: -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> Set vendor property to IMX to enable IMX specific functionality in sdhci code. Tested-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20200603145258.195920-3-linux@roeck-us.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx25.c | 6 ++++++ hw/arm/fsl-imx6.c | 6 ++++++ hw/arm/fsl-imx6ul.c | 2 ++ hw/arm/fsl-imx7.c | 2 ++ 4 files changed, 16 insertions(+) diff --git a/hw/arm/fsl-imx25.c b/hw/arm/fsl-imx25.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx25.c +++ b/hw/arm/fsl-imx25.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx25_realize(DeviceState *dev, Error **errp) &err); object_property_set_uint(OBJECT(&s->esdhc[i]), IMX25_ESDHC_CAPABILITIES, "capareg", &err); + object_property_set_uint(OBJECT(&s->esdhc[i]), SDHCI_VENDOR_IMX, + "vendor", &err); + if (err) { + error_propagate(errp, err); + return; + } object_property_set_bool(OBJECT(&s->esdhc[i]), true, "realized", &err); if (err) { error_propagate(errp, err); diff --git a/hw/arm/fsl-imx6.c b/hw/arm/fsl-imx6.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx6.c +++ b/hw/arm/fsl-imx6.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp) &err); object_property_set_uint(OBJECT(&s->esdhc[i]), IMX6_ESDHC_CAPABILITIES, "capareg", &err); + object_property_set_uint(OBJECT(&s->esdhc[i]), SDHCI_VENDOR_IMX, + "vendor", &err); + if (err) { + error_propagate(errp, err); + return; + } object_property_set_bool(OBJECT(&s->esdhc[i]), true, "realized", &err); if (err) { error_propagate(errp, err); diff --git a/hw/arm/fsl-imx6ul.c b/hw/arm/fsl-imx6ul.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx6ul.c +++ b/hw/arm/fsl-imx6ul.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) FSL_IMX6UL_USDHC2_IRQ, }; + object_property_set_uint(OBJECT(&s->usdhc[i]), SDHCI_VENDOR_IMX, + "vendor", &error_abort); object_property_set_bool(OBJECT(&s->usdhc[i]), true, "realized", &error_abort); diff --git a/hw/arm/fsl-imx7.c b/hw/arm/fsl-imx7.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx7.c +++ b/hw/arm/fsl-imx7.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) FSL_IMX7_USDHC3_IRQ, }; + object_property_set_uint(OBJECT(&s->usdhc[i]), SDHCI_VENDOR_IMX, + "vendor", &error_abort); object_property_set_bool(OBJECT(&s->usdhc[i]), true, "realized", &error_abort); -- 2.20.1 The following changes since commit ec397e90d21269037280633b6058d1f280e27667: Merge remote-tracking branch 'remotes/alistair/tags/pull-riscv-to-apply-20210901-2' into staging (2021-09-01 08:33:02 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210901 for you to fetch changes up to 683754c7b61f9e2ff098720ec80c9ab86c54663d: arm: Remove system_clock_scale global (2021-09-01 11:08:21 +0100) ---------------------------------------------------------------- * Refactor M-profile systick to use Clocks instead of system_clock_scale global * clock: Provide builtin multiplier/divider * Add A64FX processor model * Enable MVE emulation in Cortex-M55 * hw: Add compat machines for 6.2 * hw/intc/arm_gicv3: Replace mis-used MEMTX_* constants by booleans * hw/arm/raspi: Remove deprecated raspi2/raspi3 aliases ---------------------------------------------------------------- Peter Maydell (43): target/arm: Implement MVE VADD (floating-point) target/arm: Implement MVE VSUB, VMUL, VABD, VMAXNM, VMINNM target/arm: Implement MVE VCADD target/arm: Implement MVE VFMA and VFMS target/arm: Implement MVE VCMUL and VCMLA target/arm: Implement MVE VMAXNMA and VMINNMA target/arm: Implement MVE scalar fp insns target/arm: Implement MVE fp-with-scalar VFMA, VFMAS softfloat: Remove assertion preventing silencing of NaN in default-NaN mode target/arm: Implement MVE FP max/min across vector target/arm: Implement MVE fp vector comparisons target/arm: Implement MVE fp scalar comparisons target/arm: Implement MVE VCVT between floating and fixed point target/arm: Implement MVE VCVT between fp and integer target/arm: Implement MVE VCVT with specified rounding mode target/arm: Implement MVE VCVT between single and half precision target/arm: Implement MVE VRINT insns target/arm: Enable MVE in Cortex-M55 arm: Move M-profile RAS register block into its own device arm: Move systick device creation from NVIC to ARMv7M object arm: Move system PPB container handling to armv7m hw/timer/armv7m_systick: Add usual QEMU interface comment hw/timer/armv7m_systick: Add input clocks hw/arm/armv7m: Create input clocks armsse: Wire up systick cpuclk clock hw/arm/mps2.c: Connect up armv7m clocks clock: Provide builtin multiplier/divider hw/arm: Don't allocate separate MemoryRegions in stm32 SoC realize hw/arm/stm32f100: Wire up sysclk and refclk hw/arm/stm32f205: Wire up sysclk and refclk hw/arm/stm32f405: Wire up sysclk and refclk hw/arm/stm32vldiscovery: Delete trailing blank line hw/arm/nrf51: Wire up sysclk hw/arm/stellaris: split stellaris_sys_init() hw/arm/stellaris: Wire sysclk up to armv7m hw/arm/msf2_soc: Don't allocate separate MemoryRegions hw/arm/msf2: Use Clock input to MSF2_SOC instead of m3clk property hw/arm/msf2-soc: Wire up refclk hw/timer/armv7m_systick: Use clock inputs instead of system_clock_scale hw/arm/stellaris: Fix code style issues in GPTM code hw/arm/stellaris: Split stellaris-gptm into its own file hw/timer/stellaris-gptm: Use Clock input instead of system_clock_scale arm: Remove system_clock_scale global Philippe Mathieu-Daudé (4): tests: Remove uses of deprecated raspi2/raspi3 machine names hw/arm/raspi: Remove deprecated raspi2/raspi3 aliases hw/intc/arm_gicv3_dist: Rename 64-bit accessors with 'q' suffix hw/intc/arm_gicv3: Replace mis-used MEMTX_* constants by booleans Shuuichirou Ishii (3): target-arm: Add support for Fujitsu A64FX hw/arm/virt: target-arm: Add A64FX processor support to virt machine tests/arm-cpu-features: Add A64FX processor related tests Yanan Wang (1): hw: Add compat machines for 6.2 docs/about/deprecated.rst | 7 - docs/about/removed-features.rst | 7 + docs/devel/clocks.rst | 23 ++ docs/devel/qgraph.rst | 38 +- docs/system/arm/virt.rst | 1 + include/hw/arm/armv7m.h | 24 ++ include/hw/arm/msf2-soc.h | 8 +- include/hw/arm/nrf51_soc.h | 2 + include/hw/arm/stm32f100_soc.h | 8 + include/hw/arm/stm32f205_soc.h | 8 + include/hw/arm/stm32f405_soc.h | 3 + include/hw/boards.h | 3 + include/hw/clock.h | 29 ++ include/hw/i386/pc.h | 3 + include/hw/intc/armv7m_nvic.h | 8 - include/hw/misc/armv7m_ras.h | 37 ++ include/hw/timer/armv7m_systick.h | 36 +- include/hw/timer/stellaris-gptm.h | 51 +++ target/arm/helper-mve.h | 142 +++++++ target/arm/translate.h | 6 + tests/qtest/libqos/qgraph.h | 6 +- tests/qtest/libqos/qgraph_internal.h | 2 +- target/arm/mve.decode | 297 +++++++++++++-- hw/arm/armsse.c | 20 +- hw/arm/armv7m.c | 260 ++++++++++++- hw/arm/mps2.c | 17 +- hw/arm/msf2-soc.c | 68 ++-- hw/arm/msf2-som.c | 7 +- hw/arm/netduino2.c | 12 +- hw/arm/netduinoplus2.c | 12 +- hw/arm/nrf51_soc.c | 20 +- hw/arm/raspi.c | 2 - hw/arm/stellaris.c | 396 +++---------------- hw/arm/stm32f100_soc.c | 47 ++- hw/arm/stm32f205_soc.c | 47 ++- hw/arm/stm32f405_soc.c | 30 ++ hw/arm/stm32vldiscovery.c | 13 +- hw/arm/virt.c | 12 +- hw/core/clock-vmstate.c | 40 +- hw/core/clock.c | 31 +- hw/core/machine.c | 3 + hw/i386/pc.c | 3 + hw/i386/pc_piix.c | 14 +- hw/i386/pc_q35.c | 13 +- hw/intc/arm_gicv3_dist.c | 205 +++++----- hw/intc/armv7m_nvic.c | 274 +------------- hw/misc/armv7m_ras.c | 93 +++++ hw/ppc/spapr.c | 17 +- hw/s390x/s390-virtio-ccw.c | 14 +- hw/timer/armv7m_systick.c | 118 ++++-- hw/timer/stellaris-gptm.c | 332 ++++++++++++++++ target/arm/cpu64.c | 48 +++ target/arm/cpu_tcg.c | 7 +- target/arm/mve_helper.c | 650 ++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 277 +++++++++++++- target/arm/translate-neon.c | 6 - tests/qtest/arm-cpu-features.c | 13 + tests/qtest/boot-serial-test.c | 2 +- tests/qtest/libqos/arm-raspi2-machine.c | 8 +- tests/unit/test-qgraph.c | 2 +- fpu/softfloat-specialize.c.inc | 1 - MAINTAINERS | 2 + hw/arm/Kconfig | 1 + hw/core/trace-events | 1 + hw/misc/meson.build | 2 + hw/timer/Kconfig | 3 + hw/timer/meson.build | 1 + tests/acceptance/boot_linux_console.py | 6 +- 68 files changed, 2928 insertions(+), 971 deletions(-) create mode 100644 include/hw/misc/armv7m_ras.h create mode 100644 include/hw/timer/stellaris-gptm.h create mode 100644 hw/misc/armv7m_ras.c create mode 100644 hw/timer/stellaris-gptm.c From: Philippe Mathieu-Daudé <f4bug@amsat.org> Commit 155e1c82ed0 deprecated the raspi2/raspi3 machine names. Use the recommended new names: raspi2b and raspi3b. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Willian Rampazzo <willianr@redhat.com> Message-id: 20210827060815.2384760-2-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/devel/qgraph.rst | 38 ++++++++++++------------- tests/qtest/libqos/qgraph.h | 6 ++-- tests/qtest/libqos/qgraph_internal.h | 2 +- tests/qtest/boot-serial-test.c | 2 +- tests/qtest/libqos/arm-raspi2-machine.c | 8 +++--- tests/unit/test-qgraph.c | 2 +- tests/acceptance/boot_linux_console.py | 6 ++-- 7 files changed, 32 insertions(+), 32 deletions(-) diff --git a/docs/devel/qgraph.rst b/docs/devel/qgraph.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/qgraph.rst +++ b/docs/devel/qgraph.rst @@ -XXX,XX +XXX,XX @@ Nodes A node can be of four types: -- **QNODE_MACHINE**: for example ``arm/raspi2`` +- **QNODE_MACHINE**: for example ``arm/raspi2b`` - **QNODE_DRIVER**: for example ``generic-sdhci`` - **QNODE_INTERFACE**: for example ``sdhci`` (interface for all ``-sdhci`` drivers). @@ -XXX,XX +XXX,XX @@ It is possible to troubleshoot unavailable tests by running:: # |-> dest='i440FX-pcihost' type=0 (node=0x5591421117f0) # src='' # |-> dest='x86_64/pc' type=0 (node=0x559142111600) - # |-> dest='arm/raspi2' type=0 (node=0x559142110740) + # |-> dest='arm/raspi2b' type=0 (node=0x559142110740) ... # } # ALL QGRAPH NODES: { # name='virtio-net-tests/announce-self' type=3 cmd_line='(null)' [available] - # name='arm/raspi2' type=0 cmd_line='-M raspi2 ' [UNAVAILABLE] + # name='arm/raspi2b' type=0 cmd_line='-M raspi2b ' [UNAVAILABLE] ... # } @@ -XXX,XX +XXX,XX @@ qgraph path in the "ALL QGRAPH EDGES" output as follows: '' -> 'x86_64/pc' -> 'virtio-net'. The root of the qgraph is '' and the depth first search begins there. -The ``arm/raspi`` machine node is listed as "UNAVAILABLE". Although it is -reachable from the root via '' -> 'arm/raspi2' the node is unavailable because +The ``arm/raspi2b`` machine node is listed as "UNAVAILABLE". Although it is +reachable from the root via '' -> 'arm/raspi2b' the node is unavailable because the QEMU binary did not list it when queried by the framework. This is expected because we used the ``qemu-system-x86_64`` binary which does not support ARM machine types. @@ -XXX,XX +XXX,XX @@ Here we continue the ``sdhci`` use case, with the following scenario: - ``sdhci-test`` aims to test the ``read[q,w], writeq`` functions offered by the ``sdhci`` drivers. - The current ``sdhci`` device is supported by both ``x86_64/pc`` and ``ARM`` - (in this example we focus on the ``arm-raspi2``) machines. + (in this example we focus on the ``arm-raspi2b``) machines. - QEMU offers 2 types of drivers: ``QSDHCI_MemoryMapped`` for ``ARM`` and ``QSDHCI_PCI`` for ``x86_64/pc``. Both implement the ``read[q,w], writeq`` functions. @@ -XXX,XX +XXX,XX @@ In order to implement such scenario in qgraph, the test developer needs to: all the pci drivers available) ``sdhci-pci --consumes--> pci-bus`` -- Create an ``arm/raspi2`` machine node. This machine ``contains`` +- Create an ``arm/raspi2b`` machine node. This machine ``contains`` a ``generic-sdhci`` memory mapped ``sdhci`` driver node, representing ``QSDHCI_MemoryMapped``. - ``arm/raspi2 --contains--> generic-sdhci`` + ``arm/raspi2b --contains--> generic-sdhci`` - Create the ``sdhci`` interface node. This interface offers the functions that are shared by all ``sdhci`` devices. The interface is produced by ``sdhci-pci`` and ``generic-sdhci``, @@ -XXX,XX +XXX,XX @@ In order to implement such scenario in qgraph, the test developer needs to: ``sdhci-test --consumes--> sdhci`` -``arm-raspi2`` machine, simplified from +``arm-raspi2b`` machine, simplified from ``tests/qtest/libqos/arm-raspi2-machine.c``:: #include "qgraph.h" @@ -XXX,XX +XXX,XX @@ In order to implement such scenario in qgraph, the test developer needs to: return &machine->alloc; } - fprintf(stderr, "%s not present in arm/raspi2\n", interface); + fprintf(stderr, "%s not present in arm/raspi2b\n", interface); g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ In order to implement such scenario in qgraph, the test developer needs to: return &machine->sdhci.obj; } - fprintf(stderr, "%s not present in arm/raspi2\n", device); + fprintf(stderr, "%s not present in arm/raspi2b\n", device); g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ In order to implement such scenario in qgraph, the test developer needs to: static void raspi2_register_nodes(void) { - /* arm/raspi2 --contains--> generic-sdhci */ - qos_node_create_machine("arm/raspi2", + /* arm/raspi2b --contains--> generic-sdhci */ + qos_node_create_machine("arm/raspi2b", qos_create_machine_arm_raspi2); - qos_node_contains("arm/raspi2", "generic-sdhci", NULL); + qos_node_contains("arm/raspi2b", "generic-sdhci", NULL); } libqos_init(raspi2_register_nodes); @@ -XXX,XX +XXX,XX @@ In the above example, all possible types of relations are created:: | +--produces-- + | - arm/raspi2 --contains--> generic-sdhci + arm/raspi2b --contains--> generic-sdhci or inverting the consumes edge in consumed_by:: @@ -XXX,XX +XXX,XX @@ or inverting the consumes edge in consumed_by:: | +--produces-- + | - arm/raspi2 --contains--> generic-sdhci + arm/raspi2b --contains--> generic-sdhci Adding a new test """"""""""""""""" @@ -XXX,XX +XXX,XX @@ Final graph will be like this:: | +--produces-- + | - arm/raspi2 --contains--> generic-sdhci + arm/raspi2b --contains--> generic-sdhci or inverting the consumes edge in consumed_by:: @@ -XXX,XX +XXX,XX @@ or inverting the consumes edge in consumed_by:: | +--produces-- + | - arm/raspi2 --contains--> generic-sdhci + arm/raspi2b --contains--> generic-sdhci Assuming there the binary is ``QTEST_QEMU_BINARY=./qemu-system-x86_64`` @@ -XXX,XX +XXX,XX @@ a valid test path will be: and for the binary ``QTEST_QEMU_BINARY=./qemu-system-arm``: -``/arm/raspi2/generic-sdhci/sdhci/sdhci-test`` +``/arm/raspi2b/generic-sdhci/sdhci/sdhci-test`` Additional examples are also in ``test-qgraph.c`` diff --git a/tests/qtest/libqos/qgraph.h b/tests/qtest/libqos/qgraph.h index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/libqos/qgraph.h +++ b/tests/qtest/libqos/qgraph.h @@ -XXX,XX +XXX,XX @@ void qos_node_create_driver_named(const char *name, const char *qemu_name, * This function can be useful when there are multiple devices * with the same node name contained in a machine/other node * - * For example, if ``arm/raspi2`` contains 2 ``generic-sdhci`` + * For example, if ``arm/raspi2b`` contains 2 ``generic-sdhci`` * devices, the right commands will be: * * .. code:: * - * qos_node_create_machine("arm/raspi2"); + * qos_node_create_machine("arm/raspi2b"); * qos_node_create_driver("generic-sdhci", constructor); * // assume rest of the fields are set NULL * QOSGraphEdgeOptions op1 = { .edge_name = "emmc" }; * QOSGraphEdgeOptions op2 = { .edge_name = "sdcard" }; - * qos_node_contains("arm/raspi2", "generic-sdhci", &op1, &op2, NULL); + * qos_node_contains("arm/raspi2b", "generic-sdhci", &op1, &op2, NULL); * * Of course this also requires that the @container's get_device function * should implement a case for "emmc" and "sdcard". diff --git a/tests/qtest/libqos/qgraph_internal.h b/tests/qtest/libqos/qgraph_internal.h index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/libqos/qgraph_internal.h +++ b/tests/qtest/libqos/qgraph_internal.h @@ -XXX,XX +XXX,XX @@ void qos_graph_foreach_test_path(QOSTestCallback fn); /** * qos_get_machine_type(): return QEMU machine type for a machine node. * This function requires every machine @name to be in the form - * <arch>/<machine_name>, like "arm/raspi2" or "x86_64/pc". + * <arch>/<machine_name>, like "arm/raspi2b" or "x86_64/pc". * * The function will validate the format and return a pointer to * @machine to <machine_name>. For example, when passed "x86_64/pc" diff --git a/tests/qtest/boot-serial-test.c b/tests/qtest/boot-serial-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/boot-serial-test.c +++ b/tests/qtest/boot-serial-test.c @@ -XXX,XX +XXX,XX @@ static testdef_t tests[] = { sizeof(kernel_pls3adsp1800), kernel_pls3adsp1800 }, { "microblazeel", "petalogix-ml605", "", "TT", sizeof(kernel_plml605), kernel_plml605 }, - { "arm", "raspi2", "", "TT", sizeof(bios_raspi2), 0, bios_raspi2 }, + { "arm", "raspi2b", "", "TT", sizeof(bios_raspi2), 0, bios_raspi2 }, /* For hppa, force bios to output to serial by disabling graphics. */ { "hppa", "hppa", "-vga none", "SeaBIOS wants SYSTEM HALT" }, { "aarch64", "virt", "-cpu max", "TT", sizeof(kernel_aarch64), diff --git a/tests/qtest/libqos/arm-raspi2-machine.c b/tests/qtest/libqos/arm-raspi2-machine.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/libqos/arm-raspi2-machine.c +++ b/tests/qtest/libqos/arm-raspi2-machine.c @@ -XXX,XX +XXX,XX @@ static void *raspi2_get_driver(void *object, const char *interface) return &machine->alloc; } - fprintf(stderr, "%s not present in arm/raspi2\n", interface); + fprintf(stderr, "%s not present in arm/raspi2b\n", interface); g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static QOSGraphObject *raspi2_get_device(void *obj, const char *device) return &machine->sdhci.obj; } - fprintf(stderr, "%s not present in arm/raspi2\n", device); + fprintf(stderr, "%s not present in arm/raspi2b\n", device); g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static void *qos_create_machine_arm_raspi2(QTestState *qts) static void raspi2_register_nodes(void) { - qos_node_create_machine("arm/raspi2", qos_create_machine_arm_raspi2); - qos_node_contains("arm/raspi2", "generic-sdhci", NULL); + qos_node_create_machine("arm/raspi2b", qos_create_machine_arm_raspi2); + qos_node_contains("arm/raspi2b", "generic-sdhci", NULL); } libqos_init(raspi2_register_nodes); diff --git a/tests/unit/test-qgraph.c b/tests/unit/test-qgraph.c index XXXXXXX..XXXXXXX 100644 --- a/tests/unit/test-qgraph.c +++ b/tests/unit/test-qgraph.c @@ -XXX,XX +XXX,XX @@ #include "../qtest/libqos/qgraph_internal.h" #define MACHINE_PC "x86_64/pc" -#define MACHINE_RASPI2 "arm/raspi2" +#define MACHINE_RASPI2 "arm/raspi2b" #define I440FX "i440FX-pcihost" #define PCIBUS_PC "pcibus-pc" #define SDHCI "sdhci" diff --git a/tests/acceptance/boot_linux_console.py b/tests/acceptance/boot_linux_console.py index XXXXXXX..XXXXXXX 100644 --- a/tests/acceptance/boot_linux_console.py +++ b/tests/acceptance/boot_linux_console.py @@ -XXX,XX +XXX,XX @@ def do_test_arm_raspi2(self, uart_id): def test_arm_raspi2_uart0(self): """ :avocado: tags=arch:arm - :avocado: tags=machine:raspi2 + :avocado: tags=machine:raspi2b :avocado: tags=device:pl011 :avocado: tags=accel:tcg """ @@ -XXX,XX +XXX,XX @@ def test_arm_raspi2_uart0(self): def test_arm_raspi2_initrd(self): """ :avocado: tags=arch:arm - :avocado: tags=machine:raspi2 + :avocado: tags=machine:raspi2b """ deb_url = ('http://archive.raspberrypi.org/debian/' 'pool/main/r/raspberrypi-firmware/' @@ -XXX,XX +XXX,XX @@ def test_arm_orangepi_uboot_netbsd9(self): def test_aarch64_raspi3_atf(self): """ :avocado: tags=arch:aarch64 - :avocado: tags=machine:raspi3 + :avocado: tags=machine:raspi3b :avocado: tags=cpu:cortex-a53 :avocado: tags=device:pl011 :avocado: tags=atf -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Remove the raspi2/raspi3 machine aliases, deprecated since commit 155e1c82ed0. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210827060815.2384760-3-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/about/deprecated.rst | 7 ------- docs/about/removed-features.rst | 7 +++++++ hw/arm/raspi.c | 2 -- 3 files changed, 7 insertions(+), 9 deletions(-) diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -XXX,XX +XXX,XX @@ this CPU is also deprecated. System emulator machines ------------------------ -Raspberry Pi ``raspi2`` and ``raspi3`` machines (since 5.2) -''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' - -The Raspberry Pi machines come in various models (A, A+, B, B+). To be able -to distinguish which model QEMU is implementing, the ``raspi2`` and ``raspi3`` -machines have been renamed ``raspi2b`` and ``raspi3b``. - Aspeed ``swift-bmc`` machine (since 6.1) '''''''''''''''''''''''''''''''''''''''' diff --git a/docs/about/removed-features.rst b/docs/about/removed-features.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/about/removed-features.rst +++ b/docs/about/removed-features.rst @@ -XXX,XX +XXX,XX @@ This machine has been renamed ``fuloong2e``. These machine types were very old and likely could not be used for live migration from old QEMU versions anymore. Use a newer machine type instead. +Raspberry Pi ``raspi2`` and ``raspi3`` machines (removed in 6.2) +'''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The Raspberry Pi machines come in various models (A, A+, B, B+). To be able +to distinguish which model QEMU is implementing, the ``raspi2`` and ``raspi3`` +machines have been renamed ``raspi2b`` and ``raspi3b``. + linux-user mode CPUs -------------------- diff --git a/hw/arm/raspi.c b/hw/arm/raspi.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/raspi.c +++ b/hw/arm/raspi.c @@ -XXX,XX +XXX,XX @@ static void raspi2b_machine_class_init(ObjectClass *oc, void *data) MachineClass *mc = MACHINE_CLASS(oc); RaspiMachineClass *rmc = RASPI_MACHINE_CLASS(oc); - mc->alias = "raspi2"; rmc->board_rev = 0xa21041; raspi_machine_class_common_init(mc, rmc->board_rev); }; @@ -XXX,XX +XXX,XX @@ static void raspi3b_machine_class_init(ObjectClass *oc, void *data) MachineClass *mc = MACHINE_CLASS(oc); RaspiMachineClass *rmc = RASPI_MACHINE_CLASS(oc); - mc->alias = "raspi3"; rmc->board_rev = 0xa02082; raspi_machine_class_common_init(mc, rmc->board_rev); }; -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> QEMU load/store API (docs/devel/loads-stores.rst) uses the 'q' suffix for 64-bit accesses. Rename the current 'll' suffix to have the GIC dist accessors better match the rest of the codebase. Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20210826180704.2131949-2-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gicv3_dist.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/hw/intc/arm_gicv3_dist.c b/hw/intc/arm_gicv3_dist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_dist.c +++ b/hw/intc/arm_gicv3_dist.c @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, } } -static MemTxResult gicd_writell(GICv3State *s, hwaddr offset, - uint64_t value, MemTxAttrs attrs) +static MemTxResult gicd_writeq(GICv3State *s, hwaddr offset, + uint64_t value, MemTxAttrs attrs) { /* Our only 64-bit registers are GICD_IROUTER<n> */ int irq; @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_writell(GICv3State *s, hwaddr offset, } } -static MemTxResult gicd_readll(GICv3State *s, hwaddr offset, - uint64_t *data, MemTxAttrs attrs) +static MemTxResult gicd_readq(GICv3State *s, hwaddr offset, + uint64_t *data, MemTxAttrs attrs) { /* Our only 64-bit registers are GICD_IROUTER<n> */ int irq; @@ -XXX,XX +XXX,XX @@ MemTxResult gicv3_dist_read(void *opaque, hwaddr offset, uint64_t *data, r = gicd_readl(s, offset, data, attrs); break; case 8: - r = gicd_readll(s, offset, data, attrs); + r = gicd_readq(s, offset, data, attrs); break; default: r = MEMTX_ERROR; @@ -XXX,XX +XXX,XX @@ MemTxResult gicv3_dist_write(void *opaque, hwaddr offset, uint64_t data, r = gicd_writel(s, offset, data, attrs); break; case 8: - r = gicd_writell(s, offset, data, attrs); + r = gicd_writeq(s, offset, data, attrs); break; default: r = MEMTX_ERROR; -- 2.20.1 From: Philippe Mathieu-Daudé <philmd@redhat.com> Quoting Peter Maydell: These MEMTX_* aren't from the memory transaction API functions; they're just being used by gicd_readl() and friends as a way to indicate a success/failure so that the actual MemoryRegionOps read/write fns like gicv3_dist_read() can log a guest error. Arguably this is a bit of a misuse of the MEMTX_* constants and perhaps we should have gicd_readl etc return a bool instead. Follow his suggestion and replace the MEMTX_* constants by boolean values, simplifying a bit the gicv3_dist_read() / gicv3_dist_write() handlers. Suggested-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20210826180704.2131949-3-philmd@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gicv3_dist.c | 201 +++++++++++++++++++++------------------ 1 file changed, 106 insertions(+), 95 deletions(-) diff --git a/hw/intc/arm_gicv3_dist.c b/hw/intc/arm_gicv3_dist.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_dist.c +++ b/hw/intc/arm_gicv3_dist.c @@ -XXX,XX +XXX,XX @@ static void gicd_write_irouter(GICv3State *s, MemTxAttrs attrs, int irq, gicv3_update(s, irq, 1); } -static MemTxResult gicd_readb(GICv3State *s, hwaddr offset, - uint64_t *data, MemTxAttrs attrs) +/** + * gicd_readb + * gicd_readw + * gicd_readl + * gicd_readq + * gicd_writeb + * gicd_writew + * gicd_writel + * gicd_writeq + * + * Return %true if the operation succeeded, %false otherwise. + */ + +static bool gicd_readb(GICv3State *s, hwaddr offset, + uint64_t *data, MemTxAttrs attrs) { /* Most GICv3 distributor registers do not support byte accesses. */ switch (offset) { @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_readb(GICv3State *s, hwaddr offset, /* This GIC implementation always has affinity routing enabled, * so these registers are all RAZ/WI. */ - return MEMTX_OK; + return true; case GICD_IPRIORITYR ... GICD_IPRIORITYR + 0x3ff: *data = gicd_read_ipriorityr(s, attrs, offset - GICD_IPRIORITYR); - return MEMTX_OK; + return true; default: - return MEMTX_ERROR; + return false; } } -static MemTxResult gicd_writeb(GICv3State *s, hwaddr offset, - uint64_t value, MemTxAttrs attrs) +static bool gicd_writeb(GICv3State *s, hwaddr offset, + uint64_t value, MemTxAttrs attrs) { /* Most GICv3 distributor registers do not support byte accesses. */ switch (offset) { @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_writeb(GICv3State *s, hwaddr offset, /* This GIC implementation always has affinity routing enabled, * so these registers are all RAZ/WI. */ - return MEMTX_OK; + return true; case GICD_IPRIORITYR ... GICD_IPRIORITYR + 0x3ff: { int irq = offset - GICD_IPRIORITYR; if (irq < GIC_INTERNAL || irq >= s->num_irq) { - return MEMTX_OK; + return true; } gicd_write_ipriorityr(s, attrs, irq, value); gicv3_update(s, irq, 1); - return MEMTX_OK; + return true; } default: - return MEMTX_ERROR; + return false; } } -static MemTxResult gicd_readw(GICv3State *s, hwaddr offset, - uint64_t *data, MemTxAttrs attrs) +static bool gicd_readw(GICv3State *s, hwaddr offset, + uint64_t *data, MemTxAttrs attrs) { /* Only GICD_SETSPI_NSR, GICD_CLRSPI_NSR, GICD_SETSPI_SR and GICD_SETSPI_NSR * support 16 bit accesses, and those registers are all part of the @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_readw(GICv3State *s, hwaddr offset, * implement (ie for us GICD_TYPER.MBIS == 0), so for us they are * reserved. */ - return MEMTX_ERROR; + return false; } -static MemTxResult gicd_writew(GICv3State *s, hwaddr offset, - uint64_t value, MemTxAttrs attrs) +static bool gicd_writew(GICv3State *s, hwaddr offset, + uint64_t value, MemTxAttrs attrs) { /* Only GICD_SETSPI_NSR, GICD_CLRSPI_NSR, GICD_SETSPI_SR and GICD_SETSPI_NSR * support 16 bit accesses, and those registers are all part of the @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_writew(GICv3State *s, hwaddr offset, * implement (ie for us GICD_TYPER.MBIS == 0), so for us they are * reserved. */ - return MEMTX_ERROR; + return false; } -static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, - uint64_t *data, MemTxAttrs attrs) +static bool gicd_readl(GICv3State *s, hwaddr offset, + uint64_t *data, MemTxAttrs attrs) { /* Almost all GICv3 distributor registers are 32-bit. * Note that WO registers must return an UNKNOWN value on reads, @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, } else { *data = s->gicd_ctlr; } - return MEMTX_OK; + return true; case GICD_TYPER: { /* For this implementation: @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, *data = (1 << 25) | (1 << 24) | (sec_extn << 10) | (0xf << 19) | itlinesnumber; - return MEMTX_OK; + return true; } case GICD_IIDR: /* We claim to be an ARM r0p0 with a zero ProductID. * This is the same as an r0p0 GIC-500. */ *data = gicv3_iidr(); - return MEMTX_OK; + return true; case GICD_STATUSR: /* RAZ/WI for us (this is an optional register and our implementation * does not track RO/WO/reserved violations to report them to the guest) */ *data = 0; - return MEMTX_OK; + return true; case GICD_IGROUPR ... GICD_IGROUPR + 0x7f: { int irq; if (!attrs.secure && !(s->gicd_ctlr & GICD_CTLR_DS)) { *data = 0; - return MEMTX_OK; + return true; } /* RAZ/WI for SGIs, PPIs, unimplemented irqs */ irq = (offset - GICD_IGROUPR) * 8; if (irq < GIC_INTERNAL || irq >= s->num_irq) { *data = 0; - return MEMTX_OK; + return true; } *data = *gic_bmp_ptr32(s->group, irq); - return MEMTX_OK; + return true; } case GICD_ISENABLER ... GICD_ISENABLER + 0x7f: *data = gicd_read_bitmap_reg(s, attrs, s->enabled, NULL, offset - GICD_ISENABLER); - return MEMTX_OK; + return true; case GICD_ICENABLER ... GICD_ICENABLER + 0x7f: *data = gicd_read_bitmap_reg(s, attrs, s->enabled, NULL, offset - GICD_ICENABLER); - return MEMTX_OK; + return true; case GICD_ISPENDR ... GICD_ISPENDR + 0x7f: *data = gicd_read_bitmap_reg(s, attrs, s->pending, mask_nsacr_ge1, offset - GICD_ISPENDR); - return MEMTX_OK; + return true; case GICD_ICPENDR ... GICD_ICPENDR + 0x7f: *data = gicd_read_bitmap_reg(s, attrs, s->pending, mask_nsacr_ge2, offset - GICD_ICPENDR); - return MEMTX_OK; + return true; case GICD_ISACTIVER ... GICD_ISACTIVER + 0x7f: *data = gicd_read_bitmap_reg(s, attrs, s->active, mask_nsacr_ge2, offset - GICD_ISACTIVER); - return MEMTX_OK; + return true; case GICD_ICACTIVER ... GICD_ICACTIVER + 0x7f: *data = gicd_read_bitmap_reg(s, attrs, s->active, mask_nsacr_ge2, offset - GICD_ICACTIVER); - return MEMTX_OK; + return true; case GICD_IPRIORITYR ... GICD_IPRIORITYR + 0x3ff: { int i, irq = offset - GICD_IPRIORITYR; @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, value |= gicd_read_ipriorityr(s, attrs, i); } *data = value; - return MEMTX_OK; + return true; } case GICD_ITARGETSR ... GICD_ITARGETSR + 0x3ff: /* RAZ/WI since affinity routing is always enabled */ *data = 0; - return MEMTX_OK; + return true; case GICD_ICFGR ... GICD_ICFGR + 0xff: { /* Here only the even bits are used; odd bits are RES0 */ @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, if (irq < GIC_INTERNAL || irq >= s->num_irq) { *data = 0; - return MEMTX_OK; + return true; } /* Since our edge_trigger bitmap is one bit per irq, we only need @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, value = extract32(value, (irq & 0x1f) ? 16 : 0, 16); value = half_shuffle32(value) << 1; *data = value; - return MEMTX_OK; + return true; } case GICD_IGRPMODR ... GICD_IGRPMODR + 0xff: { @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, * security enabled and this is an NS access */ *data = 0; - return MEMTX_OK; + return true; } /* RAZ/WI for SGIs, PPIs, unimplemented irqs */ irq = (offset - GICD_IGRPMODR) * 8; if (irq < GIC_INTERNAL || irq >= s->num_irq) { *data = 0; - return MEMTX_OK; + return true; } *data = *gic_bmp_ptr32(s->grpmod, irq); - return MEMTX_OK; + return true; } case GICD_NSACR ... GICD_NSACR + 0xff: { @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, if (irq < GIC_INTERNAL || irq >= s->num_irq) { *data = 0; - return MEMTX_OK; + return true; } if ((s->gicd_ctlr & GICD_CTLR_DS) || !attrs.secure) { @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, * security enabled and this is an NS access */ *data = 0; - return MEMTX_OK; + return true; } *data = s->gicd_nsacr[irq / 16]; - return MEMTX_OK; + return true; } case GICD_CPENDSGIR ... GICD_CPENDSGIR + 0xf: case GICD_SPENDSGIR ... GICD_SPENDSGIR + 0xf: /* RAZ/WI since affinity routing is always enabled */ *data = 0; - return MEMTX_OK; + return true; case GICD_IROUTER ... GICD_IROUTER + 0x1fdf: { uint64_t r; @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_readl(GICv3State *s, hwaddr offset, } else { *data = (uint32_t)r; } - return MEMTX_OK; + return true; } case GICD_IDREGS ... GICD_IDREGS + 0x2f: /* ID registers */ *data = gicv3_idreg(offset - GICD_IDREGS); - return MEMTX_OK; + return true; case GICD_SGIR: /* WO registers, return unknown value */ qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid guest read from WO register at offset " TARGET_FMT_plx "\n", __func__, offset); *data = 0; - return MEMTX_OK; + return true; default: - return MEMTX_ERROR; + return false; } } -static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, - uint64_t value, MemTxAttrs attrs) +static bool gicd_writel(GICv3State *s, hwaddr offset, + uint64_t value, MemTxAttrs attrs) { /* Almost all GICv3 distributor registers are 32-bit. Note that * RO registers must ignore writes, not abort. @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, s->gicd_ctlr &= ~(GICD_CTLR_EN_GRP1S | GICD_CTLR_ARE_NS); } gicv3_full_update(s); - return MEMTX_OK; + return true; } case GICD_STATUSR: /* RAZ/WI for our implementation */ - return MEMTX_OK; + return true; case GICD_IGROUPR ... GICD_IGROUPR + 0x7f: { int irq; if (!attrs.secure && !(s->gicd_ctlr & GICD_CTLR_DS)) { - return MEMTX_OK; + return true; } /* RAZ/WI for SGIs, PPIs, unimplemented irqs */ irq = (offset - GICD_IGROUPR) * 8; if (irq < GIC_INTERNAL || irq >= s->num_irq) { - return MEMTX_OK; + return true; } *gic_bmp_ptr32(s->group, irq) = value; gicv3_update(s, irq, 32); - return MEMTX_OK; + return true; } case GICD_ISENABLER ... GICD_ISENABLER + 0x7f: gicd_write_set_bitmap_reg(s, attrs, s->enabled, NULL, offset - GICD_ISENABLER, value); - return MEMTX_OK; + return true; case GICD_ICENABLER ... GICD_ICENABLER + 0x7f: gicd_write_clear_bitmap_reg(s, attrs, s->enabled, NULL, offset - GICD_ICENABLER, value); - return MEMTX_OK; + return true; case GICD_ISPENDR ... GICD_ISPENDR + 0x7f: gicd_write_set_bitmap_reg(s, attrs, s->pending, mask_nsacr_ge1, offset - GICD_ISPENDR, value); - return MEMTX_OK; + return true; case GICD_ICPENDR ... GICD_ICPENDR + 0x7f: gicd_write_clear_bitmap_reg(s, attrs, s->pending, mask_nsacr_ge2, offset - GICD_ICPENDR, value); - return MEMTX_OK; + return true; case GICD_ISACTIVER ... GICD_ISACTIVER + 0x7f: gicd_write_set_bitmap_reg(s, attrs, s->active, NULL, offset - GICD_ISACTIVER, value); - return MEMTX_OK; + return true; case GICD_ICACTIVER ... GICD_ICACTIVER + 0x7f: gicd_write_clear_bitmap_reg(s, attrs, s->active, NULL, offset - GICD_ICACTIVER, value); - return MEMTX_OK; + return true; case GICD_IPRIORITYR ... GICD_IPRIORITYR + 0x3ff: { int i, irq = offset - GICD_IPRIORITYR; if (irq < GIC_INTERNAL || irq + 3 >= s->num_irq) { - return MEMTX_OK; + return true; } for (i = irq; i < irq + 4; i++, value >>= 8) { gicd_write_ipriorityr(s, attrs, i, value); } gicv3_update(s, irq, 4); - return MEMTX_OK; + return true; } case GICD_ITARGETSR ... GICD_ITARGETSR + 0x3ff: /* RAZ/WI since affinity routing is always enabled */ - return MEMTX_OK; + return true; case GICD_ICFGR ... GICD_ICFGR + 0xff: { /* Here only the odd bits are used; even bits are RES0 */ @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, uint32_t mask, oldval; if (irq < GIC_INTERNAL || irq >= s->num_irq) { - return MEMTX_OK; + return true; } /* Since our edge_trigger bitmap is one bit per irq, our input @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, oldval = *gic_bmp_ptr32(s->edge_trigger, (irq & ~0x1f)); value = (oldval & ~mask) | (value & mask); *gic_bmp_ptr32(s->edge_trigger, irq & ~0x1f) = value; - return MEMTX_OK; + return true; } case GICD_IGRPMODR ... GICD_IGRPMODR + 0xff: { @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, /* RAZ/WI if security disabled, or if * security enabled and this is an NS access */ - return MEMTX_OK; + return true; } /* RAZ/WI for SGIs, PPIs, unimplemented irqs */ irq = (offset - GICD_IGRPMODR) * 8; if (irq < GIC_INTERNAL || irq >= s->num_irq) { - return MEMTX_OK; + return true; } *gic_bmp_ptr32(s->grpmod, irq) = value; gicv3_update(s, irq, 32); - return MEMTX_OK; + return true; } case GICD_NSACR ... GICD_NSACR + 0xff: { @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, int irq = (offset - GICD_NSACR) * 4; if (irq < GIC_INTERNAL || irq >= s->num_irq) { - return MEMTX_OK; + return true; } if ((s->gicd_ctlr & GICD_CTLR_DS) || !attrs.secure) { /* RAZ/WI if security disabled, or if * security enabled and this is an NS access */ - return MEMTX_OK; + return true; } s->gicd_nsacr[irq / 16] = value; /* No update required as this only affects access permission checks */ - return MEMTX_OK; + return true; } case GICD_SGIR: /* RES0 if affinity routing is enabled */ - return MEMTX_OK; + return true; case GICD_CPENDSGIR ... GICD_CPENDSGIR + 0xf: case GICD_SPENDSGIR ... GICD_SPENDSGIR + 0xf: /* RAZ/WI since affinity routing is always enabled */ - return MEMTX_OK; + return true; case GICD_IROUTER ... GICD_IROUTER + 0x1fdf: { uint64_t r; int irq = (offset - GICD_IROUTER) / 8; if (irq < GIC_INTERNAL || irq >= s->num_irq) { - return MEMTX_OK; + return true; } /* Write half of the 64-bit register */ r = gicd_read_irouter(s, attrs, irq); r = deposit64(r, (offset & 7) ? 32 : 0, 32, value); gicd_write_irouter(s, attrs, irq, r); - return MEMTX_OK; + return true; } case GICD_IDREGS ... GICD_IDREGS + 0x2f: case GICD_TYPER: @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_writel(GICv3State *s, hwaddr offset, qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid guest write to RO register at offset " TARGET_FMT_plx "\n", __func__, offset); - return MEMTX_OK; + return true; default: - return MEMTX_ERROR; + return false; } } -static MemTxResult gicd_writeq(GICv3State *s, hwaddr offset, - uint64_t value, MemTxAttrs attrs) +static bool gicd_writeq(GICv3State *s, hwaddr offset, + uint64_t value, MemTxAttrs attrs) { /* Our only 64-bit registers are GICD_IROUTER<n> */ int irq; @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_writeq(GICv3State *s, hwaddr offset, case GICD_IROUTER ... GICD_IROUTER + 0x1fdf: irq = (offset - GICD_IROUTER) / 8; gicd_write_irouter(s, attrs, irq, value); - return MEMTX_OK; + return true; default: - return MEMTX_ERROR; + return false; } } -static MemTxResult gicd_readq(GICv3State *s, hwaddr offset, - uint64_t *data, MemTxAttrs attrs) +static bool gicd_readq(GICv3State *s, hwaddr offset, + uint64_t *data, MemTxAttrs attrs) { /* Our only 64-bit registers are GICD_IROUTER<n> */ int irq; @@ -XXX,XX +XXX,XX @@ static MemTxResult gicd_readq(GICv3State *s, hwaddr offset, case GICD_IROUTER ... GICD_IROUTER + 0x1fdf: irq = (offset - GICD_IROUTER) / 8; *data = gicd_read_irouter(s, attrs, irq); - return MEMTX_OK; + return true; default: - return MEMTX_ERROR; + return false; } } @@ -XXX,XX +XXX,XX @@ MemTxResult gicv3_dist_read(void *opaque, hwaddr offset, uint64_t *data, unsigned size, MemTxAttrs attrs) { GICv3State *s = (GICv3State *)opaque; - MemTxResult r; + bool r; switch (size) { case 1: @@ -XXX,XX +XXX,XX @@ MemTxResult gicv3_dist_read(void *opaque, hwaddr offset, uint64_t *data, r = gicd_readq(s, offset, data, attrs); break; default: - r = MEMTX_ERROR; + r = false; break; } - if (r == MEMTX_ERROR) { + if (!r) { qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid guest read at offset " TARGET_FMT_plx "size %u\n", __func__, offset, size); @@ -XXX,XX +XXX,XX @@ MemTxResult gicv3_dist_read(void *opaque, hwaddr offset, uint64_t *data, * trigger the guest-error logging but don't return it to * the caller, or we'll cause a spurious guest data abort. */ - r = MEMTX_OK; *data = 0; } else { trace_gicv3_dist_read(offset, *data, size, attrs.secure); } - return r; + return MEMTX_OK; } MemTxResult gicv3_dist_write(void *opaque, hwaddr offset, uint64_t data, unsigned size, MemTxAttrs attrs) { GICv3State *s = (GICv3State *)opaque; - MemTxResult r; + bool r; switch (size) { case 1: @@ -XXX,XX +XXX,XX @@ MemTxResult gicv3_dist_write(void *opaque, hwaddr offset, uint64_t data, r = gicd_writeq(s, offset, data, attrs); break; default: - r = MEMTX_ERROR; + r = false; break; } - if (r == MEMTX_ERROR) { + if (!r) { qemu_log_mask(LOG_GUEST_ERROR, "%s: invalid guest write at offset " TARGET_FMT_plx "size %u\n", __func__, offset, size); @@ -XXX,XX +XXX,XX @@ MemTxResult gicv3_dist_write(void *opaque, hwaddr offset, uint64_t data, * trigger the guest-error logging but don't return it to * the caller, or we'll cause a spurious guest data abort. */ - r = MEMTX_OK; } else { trace_gicv3_dist_write(offset, data, size, attrs.secure); } - return r; + return MEMTX_OK; } void gicv3_dist_set_irq(GICv3State *s, int irq, int level) -- 2.20.1 From: Yanan Wang <wangyanan55@huawei.com> Add 6.2 machine types for arm/i440fx/q35/s390x/spapr. Signed-off-by: Yanan Wang <wangyanan55@huawei.com> Acked-by: David Gibson <david@gibson.dropbear.id.au> Reviewed-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Cornelia Huck <cohuck@redhat.com> Reviewed-by: Pankaj Gupta <pankaj.gupta@ionos.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/boards.h | 3 +++ include/hw/i386/pc.h | 3 +++ hw/arm/virt.c | 11 +++++++++-- hw/core/machine.c | 3 +++ hw/i386/pc.c | 3 +++ hw/i386/pc_piix.c | 14 +++++++++++++- hw/i386/pc_q35.c | 13 ++++++++++++- hw/ppc/spapr.c | 17 ++++++++++++++--- hw/s390x/s390-virtio-ccw.c | 14 +++++++++++++- 9 files changed, 73 insertions(+), 8 deletions(-) diff --git a/include/hw/boards.h b/include/hw/boards.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/boards.h +++ b/include/hw/boards.h @@ -XXX,XX +XXX,XX @@ struct MachineState { } \ type_init(machine_initfn##_register_types) +extern GlobalProperty hw_compat_6_1[]; +extern const size_t hw_compat_6_1_len; + extern GlobalProperty hw_compat_6_0[]; extern const size_t hw_compat_6_0_len; diff --git a/include/hw/i386/pc.h b/include/hw/i386/pc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/i386/pc.h +++ b/include/hw/i386/pc.h @@ -XXX,XX +XXX,XX @@ void pc_system_parse_ovmf_flash(uint8_t *flash_ptr, size_t flash_size); void pc_madt_cpu_entry(AcpiDeviceIf *adev, int uid, const CPUArchIdList *apic_ids, GArray *entry); +extern GlobalProperty pc_compat_6_1[]; +extern const size_t pc_compat_6_1_len; + extern GlobalProperty pc_compat_6_0[]; extern const size_t pc_compat_6_0_len; diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void machvirt_machine_init(void) } type_init(machvirt_machine_init); -static void virt_machine_6_1_options(MachineClass *mc) +static void virt_machine_6_2_options(MachineClass *mc) { } -DEFINE_VIRT_MACHINE_AS_LATEST(6, 1) +DEFINE_VIRT_MACHINE_AS_LATEST(6, 2) + +static void virt_machine_6_1_options(MachineClass *mc) +{ + virt_machine_6_2_options(mc); + compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len); +} +DEFINE_VIRT_MACHINE(6, 1) static void virt_machine_6_0_options(MachineClass *mc) { diff --git a/hw/core/machine.c b/hw/core/machine.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/machine.c +++ b/hw/core/machine.c @@ -XXX,XX +XXX,XX @@ #include "hw/virtio/virtio.h" #include "hw/virtio/virtio-pci.h" +GlobalProperty hw_compat_6_1[] = {}; +const size_t hw_compat_6_1_len = G_N_ELEMENTS(hw_compat_6_1); + GlobalProperty hw_compat_6_0[] = { { "gpex-pcihost", "allow-unmapped-accesses", "false" }, { "i8042", "extended-state", "false"}, diff --git a/hw/i386/pc.c b/hw/i386/pc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -XXX,XX +XXX,XX @@ #include "trace.h" #include CONFIG_DEVICES +GlobalProperty pc_compat_6_1[] = {}; +const size_t pc_compat_6_1_len = G_N_ELEMENTS(pc_compat_6_1); + GlobalProperty pc_compat_6_0[] = { { "qemu64" "-" TYPE_X86_CPU, "family", "6" }, { "qemu64" "-" TYPE_X86_CPU, "model", "6" }, diff --git a/hw/i386/pc_piix.c b/hw/i386/pc_piix.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i386/pc_piix.c +++ b/hw/i386/pc_piix.c @@ -XXX,XX +XXX,XX @@ static void pc_i440fx_machine_options(MachineClass *m) machine_class_allow_dynamic_sysbus_dev(m, TYPE_VMBUS_BRIDGE); } -static void pc_i440fx_6_1_machine_options(MachineClass *m) +static void pc_i440fx_6_2_machine_options(MachineClass *m) { PCMachineClass *pcmc = PC_MACHINE_CLASS(m); pc_i440fx_machine_options(m); @@ -XXX,XX +XXX,XX @@ static void pc_i440fx_6_1_machine_options(MachineClass *m) pcmc->default_cpu_version = 1; } +DEFINE_I440FX_MACHINE(v6_2, "pc-i440fx-6.2", NULL, + pc_i440fx_6_2_machine_options); + +static void pc_i440fx_6_1_machine_options(MachineClass *m) +{ + pc_i440fx_6_2_machine_options(m); + m->alias = NULL; + m->is_default = false; + compat_props_add(m->compat_props, hw_compat_6_1, hw_compat_6_1_len); + compat_props_add(m->compat_props, pc_compat_6_1, pc_compat_6_1_len); +} + DEFINE_I440FX_MACHINE(v6_1, "pc-i440fx-6.1", NULL, pc_i440fx_6_1_machine_options); diff --git a/hw/i386/pc_q35.c b/hw/i386/pc_q35.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i386/pc_q35.c +++ b/hw/i386/pc_q35.c @@ -XXX,XX +XXX,XX @@ static void pc_q35_machine_options(MachineClass *m) m->max_cpus = 288; } -static void pc_q35_6_1_machine_options(MachineClass *m) +static void pc_q35_6_2_machine_options(MachineClass *m) { PCMachineClass *pcmc = PC_MACHINE_CLASS(m); pc_q35_machine_options(m); @@ -XXX,XX +XXX,XX @@ static void pc_q35_6_1_machine_options(MachineClass *m) pcmc->default_cpu_version = 1; } +DEFINE_Q35_MACHINE(v6_2, "pc-q35-6.2", NULL, + pc_q35_6_2_machine_options); + +static void pc_q35_6_1_machine_options(MachineClass *m) +{ + pc_q35_6_2_machine_options(m); + m->alias = NULL; + compat_props_add(m->compat_props, hw_compat_6_1, hw_compat_6_1_len); + compat_props_add(m->compat_props, pc_compat_6_1, pc_compat_6_1_len); +} + DEFINE_Q35_MACHINE(v6_1, "pc-q35-6.1", NULL, pc_q35_6_1_machine_options); diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/ppc/spapr.c +++ b/hw/ppc/spapr.c @@ -XXX,XX +XXX,XX @@ static void spapr_machine_latest_class_options(MachineClass *mc) type_init(spapr_machine_register_##suffix) /* - * pseries-6.1 + * pseries-6.2 */ -static void spapr_machine_6_1_class_options(MachineClass *mc) +static void spapr_machine_6_2_class_options(MachineClass *mc) { /* Defaults for the latest behaviour inherited from the base class */ } -DEFINE_SPAPR_MACHINE(6_1, "6.1", true); +DEFINE_SPAPR_MACHINE(6_2, "6.2", true); + +/* + * pseries-6.1 + */ +static void spapr_machine_6_1_class_options(MachineClass *mc) +{ + spapr_machine_6_2_class_options(mc); + compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len); +} + +DEFINE_SPAPR_MACHINE(6_1, "6.1", false); /* * pseries-6.0 diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index XXXXXXX..XXXXXXX 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -XXX,XX +XXX,XX @@ bool css_migration_enabled(void) } \ type_init(ccw_machine_register_##suffix) +static void ccw_machine_6_2_instance_options(MachineState *machine) +{ +} + +static void ccw_machine_6_2_class_options(MachineClass *mc) +{ +} +DEFINE_CCW_MACHINE(6_2, "6.2", true); + static void ccw_machine_6_1_instance_options(MachineState *machine) { + ccw_machine_6_2_instance_options(machine); } static void ccw_machine_6_1_class_options(MachineClass *mc) { + ccw_machine_6_2_class_options(mc); + compat_props_add(mc->compat_props, hw_compat_6_1, hw_compat_6_1_len); } -DEFINE_CCW_MACHINE(6_1, "6.1", true); +DEFINE_CCW_MACHINE(6_1, "6.1", false); static void ccw_machine_6_0_instance_options(MachineState *machine) { -- 2.20.1 Implement the MVE VADD (floating-point) insn. Handling of this is similar to the 2-operand integer insns, except that we must take care to only update the floating point exception status if the least significant bit of the predicate mask for each element is active. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-mve.h | 3 +++ target/arm/translate.h | 6 ++++++ target/arm/mve.decode | 10 ++++++++++ target/arm/mve_helper.c | 40 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 17 ++++++++++++++++ target/arm/translate-neon.c | 6 ------ 6 files changed, 76 insertions(+), 6 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vhcadd270b, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vhcadd270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vhcadd270w, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfadds, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vadd_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vadd_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline int rsub_8(DisasContext *s, int x) return 8 - x; } +static inline int neon_3same_fp_size(DisasContext *s, int x) +{ + /* Convert 0==fp32, 1==fp16 into a MO_* value */ + return MO_32 - x; +} + static inline int arm_dc_feature(DisasContext *dc, int feature) { return (dc->features & (1ULL << feature)) != 0; diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ # VQDMULL has size in bit 28: 0 for 16 bit, 1 for 32 bit %size_28 28:1 !function=plus_1 +# 2 operand fp insns have size in bit 20: 1 for 16 bit, 0 for 32 bit, +# like Neon FP insns. +%2op_fp_size 20:1 !function=neon_3same_fp_size + # 1imm format immediate %imm_28_16_0 28:1 16:3 0:4 @@ -XXX,XX +XXX,XX @@ @vmaxv .... .... .... size:2 .. rda:4 .... .... .... &vmaxv qm=%qm +@2op_fp .... .... .... .... .... .... .... .... &2op \ + qd=%qd qn=%qn qm=%qm size=%2op_fp_size + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VCMPGE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 0 0 .... @vcmp_scalar VCMPLT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 0 0 .... @vcmp_scalar VCMPGT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 1 0 .... @vcmp_scalar VCMPLE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 1 0 .... @vcmp_scalar + +# 2-operand FP +VADD_fp 1110 1111 0 . 0 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/cpu_ldst.h" #include "exec/exec-all.h" #include "tcg/tcg.h" +#include "fpu/softfloat.h" static uint16_t mve_eci_mask(CPUARMState *env) { @@ -XXX,XX +XXX,XX @@ DO_VMAXMINA(vmaxaw, 4, int32_t, uint32_t, DO_MAX) DO_VMAXMINA(vminab, 1, int8_t, uint8_t, DO_MIN) DO_VMAXMINA(vminah, 2, int16_t, uint16_t, DO_MIN) DO_VMAXMINA(vminaw, 4, int32_t, uint32_t, DO_MIN) + +/* + * 2-operand floating point. Note that if an element is partially + * predicated we must do the FP operation to update the non-predicated + * bytes, but we must be careful to avoid updating the FP exception + * state unless byte 0 of the element was unpredicated. + */ +#define DO_2OP_FP(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, void *vm) \ + { \ + TYPE *d = vd, *n = vn, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], m[H##ESIZE(e)], fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_2OP_FP_ALL(OP, FN) \ + DO_2OP_FP(OP##h, 2, float16, float16_##FN) \ + DO_2OP_FP(OP##s, 4, float32, float32_##FN) + +DO_2OP_FP_ALL(vfadd, add) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSBCI(DisasContext *s, arg_2op *a) return do_2op(s, a, gen_helper_mve_vsbci); } +#define DO_2OP_FP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_2op *a) \ + { \ + static MVEGenTwoOpFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_2op(s, a, fns[a->size]); \ + } + +DO_2OP_FP(VADD_fp, vfadd) + static bool do_2op_scalar(DisasContext *s, arg_2scalar *a, MVEGenTwoOpScalarFn fn) { diff --git a/target/arm/translate-neon.c b/target/arm/translate-neon.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-neon.c +++ b/target/arm/translate-neon.c @@ -XXX,XX +XXX,XX @@ #include "translate.h" #include "translate-a32.h" -static inline int neon_3same_fp_size(DisasContext *s, int x) -{ - /* Convert 0==fp32, 1==fp16 into a MO_* value */ - return MO_32 - x; -} - /* Include the generated Neon decoder */ #include "decode-neon-dp.c.inc" #include "decode-neon-ls.c.inc" -- 2.20.1 Implement more simple 2-operand floating point MVE insns. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-mve.h | 15 +++++++++++++++ target/arm/mve.decode | 6 ++++++ target/arm/mve_helper.c | 16 ++++++++++++++++ target/arm/translate-mve.c | 5 +++++ 4 files changed, 42 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vhcadd270w, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vfaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vfadds, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfsubh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfsubs, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfmulh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfmuls, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfabdh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfabds, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vmaxnmh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmaxnms, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vminnmh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vminnms, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vadd_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vadd_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VCMPLE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 1 0 .... @vcmp_scalar # 2-operand FP VADD_fp 1110 1111 0 . 0 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp +VSUB_fp 1110 1111 0 . 1 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp +VMUL_fp 1111 1111 0 . 0 . ... 0 ... 0 1101 . 1 . 1 ... 0 @2op_fp +VABD_fp 1111 1111 0 . 1 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp + +VMAXNM 1111 1111 0 . 0 . ... 0 ... 0 1111 . 1 . 1 ... 0 @2op_fp +VMINNM 1111 1111 0 . 1 . ... 0 ... 0 1111 . 1 . 1 ... 0 @2op_fp diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VMAXMINA(vminaw, 4, int32_t, uint32_t, DO_MIN) DO_2OP_FP(OP##s, 4, float32, float32_##FN) DO_2OP_FP_ALL(vfadd, add) +DO_2OP_FP_ALL(vfsub, sub) +DO_2OP_FP_ALL(vfmul, mul) + +static inline float16 float16_abd(float16 a, float16 b, float_status *s) +{ + return float16_abs(float16_sub(a, b, s)); +} + +static inline float32 float32_abd(float32 a, float32 b, float_status *s) +{ + return float32_abs(float32_sub(a, b, s)); +} + +DO_2OP_FP_ALL(vfabd, abd) +DO_2OP_FP_ALL(vmaxnm, maxnum) +DO_2OP_FP_ALL(vminnm, minnum) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSBCI(DisasContext *s, arg_2op *a) } DO_2OP_FP(VADD_fp, vfadd) +DO_2OP_FP(VSUB_fp, vfsub) +DO_2OP_FP(VMUL_fp, vfmul) +DO_2OP_FP(VABD_fp, vfabd) +DO_2OP_FP(VMAXNM, vmaxnm) +DO_2OP_FP(VMINNM, vminnm) static bool do_2op_scalar(DisasContext *s, arg_2scalar *a, MVEGenTwoOpScalarFn fn) -- 2.20.1 Implement the MVE VCADD insn. Note that here the size bit is the opposite sense to the other 2-operand fp insns. We don't check for the sz == 1 && Qd == Qm UNPREDICTABLE case, because that would mean we can't use the DO_2OP_FP macro in translate-mve.c. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-mve.h | 6 ++++++ target/arm/mve.decode | 8 ++++++++ target/arm/mve_helper.c | 40 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 4 +++- 4 files changed, 57 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vmaxnms, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vminnmh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vminnms, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfcadd90h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfcadd90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfcadd270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfcadd270s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vadd_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vadd_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ # 2 operand fp insns have size in bit 20: 1 for 16 bit, 0 for 32 bit, # like Neon FP insns. %2op_fp_size 20:1 !function=neon_3same_fp_size +# VCADD is an exception, where bit 20 is 0 for 16 bit and 1 for 32 bit +%2op_fp_size_rev 20:1 !function=plus_1 # 1imm format immediate %imm_28_16_0 28:1 16:3 0:4 @@ -XXX,XX +XXX,XX @@ @2op_fp .... .... .... .... .... .... .... .... &2op \ qd=%qd qn=%qn qm=%qm size=%2op_fp_size +@2op_fp_size_rev .... .... .... .... .... .... .... .... &2op \ + qd=%qd qn=%qn qm=%qm size=%2op_fp_size_rev + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VABD_fp 1111 1111 0 . 1 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp VMAXNM 1111 1111 0 . 0 . ... 0 ... 0 1111 . 1 . 1 ... 0 @2op_fp VMINNM 1111 1111 0 . 1 . ... 0 ... 0 1111 . 1 . 1 ... 0 @2op_fp + +VCADD90_fp 1111 1100 1 . 0 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev +VCADD270_fp 1111 1101 1 . 0 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static inline float32 float32_abd(float32 a, float32 b, float_status *s) DO_2OP_FP_ALL(vfabd, abd) DO_2OP_FP_ALL(vmaxnm, maxnum) DO_2OP_FP_ALL(vminnm, minnum) + +#define DO_VCADD_FP(OP, ESIZE, TYPE, FN0, FN1) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, void *vm) \ + { \ + TYPE *d = vd, *n = vn, *m = vm; \ + TYPE r[16 / ESIZE]; \ + uint16_t tm, mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + /* Calculate all results first to avoid overwriting inputs */ \ + for (e = 0, tm = mask; e < 16 / ESIZE; e++, tm >>= ESIZE) { \ + if ((tm & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + r[e] = 0; \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(tm & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + if (!(e & 1)) { \ + r[e] = FN0(n[H##ESIZE(e)], m[H##ESIZE(e + 1)], fpst); \ + } else { \ + r[e] = FN1(n[H##ESIZE(e)], m[H##ESIZE(e - 1)], fpst); \ + } \ + } \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], r[e], mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VCADD_FP(vfcadd90h, 2, float16, float16_sub, float16_add) +DO_VCADD_FP(vfcadd90s, 4, float32, float32_sub, float32_add) +DO_VCADD_FP(vfcadd270h, 2, float16, float16_add, float16_sub) +DO_VCADD_FP(vfcadd270s, 4, float32, float32_add, float32_sub) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_FP(VMUL_fp, vfmul) DO_2OP_FP(VABD_fp, vfabd) DO_2OP_FP(VMAXNM, vmaxnm) DO_2OP_FP(VMINNM, vminnm) +DO_2OP_FP(VCADD90_fp, vfcadd90) +DO_2OP_FP(VCADD270_fp, vfcadd270) static bool do_2op_scalar(DisasContext *s, arg_2scalar *a, MVEGenTwoOpScalarFn fn) @@ -XXX,XX +XXX,XX @@ static bool do_2op_scalar(DisasContext *s, arg_2scalar *a, return true; } -#define DO_2OP_SCALAR(INSN, FN) \ +#define DO_2OP_SCALAR(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_2scalar *a) \ { \ static MVEGenTwoOpScalarFn * const fns[] = { \ -- 2.20.1 Implement the MVE VFMA and VFMS insns. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-mve.h | 6 ++++++ target/arm/mve.decode | 3 +++ target/arm/mve_helper.c | 37 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 48 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vfcadd90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vfcadd270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vfcadd270s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfmah, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfmas, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vfmsh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vfmss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vadd_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vadd_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VMINNM 1111 1111 0 . 1 . ... 0 ... 0 1111 . 1 . 1 ... 0 @2op_fp VCADD90_fp 1111 1100 1 . 0 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev VCADD270_fp 1111 1101 1 . 0 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev + +VFMA 1110 1111 0 . 0 . ... 0 ... 0 1100 . 1 . 1 ... 0 @2op_fp +VFMS 1110 1111 0 . 1 . ... 0 ... 0 1100 . 1 . 1 ... 0 @2op_fp diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VCADD_FP(vfcadd90h, 2, float16, float16_sub, float16_add) DO_VCADD_FP(vfcadd90s, 4, float32, float32_sub, float32_add) DO_VCADD_FP(vfcadd270h, 2, float16, float16_add, float16_sub) DO_VCADD_FP(vfcadd270s, 4, float32, float32_add, float32_sub) + +#define DO_VFMA(OP, ESIZE, TYPE, CHS) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, void *vm) \ + { \ + TYPE *d = vd, *n = vn, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = n[H##ESIZE(e)]; \ + if (CHS) { \ + r = TYPE##_chs(r); \ + } \ + r = TYPE##_muladd(r, m[H##ESIZE(e)], d[H##ESIZE(e)], \ + 0, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VFMA(vfmah, 2, float16, false) +DO_VFMA(vfmas, 4, float32, false) +DO_VFMA(vfmsh, 2, float16, true) +DO_VFMA(vfmss, 4, float32, true) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_FP(VMAXNM, vmaxnm) DO_2OP_FP(VMINNM, vminnm) DO_2OP_FP(VCADD90_fp, vfcadd90) DO_2OP_FP(VCADD270_fp, vfcadd270) +DO_2OP_FP(VFMA, vfma) +DO_2OP_FP(VFMS, vfms) static bool do_2op_scalar(DisasContext *s, arg_2scalar *a, MVEGenTwoOpScalarFn fn) -- 2.20.1 Implement the MVE VCMUL and VCMLA insns. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-mve.h | 18 ++++++++ target/arm/mve.decode | 35 ++++++++++++---- target/arm/mve_helper.c | 86 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 8 ++++ 4 files changed, 139 insertions(+), 8 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vfmas, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vfmsh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vfmss, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul0h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul0s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul90h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul180h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul180s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmul270s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vcmla0h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla0s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla90h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla180h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla180s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla270h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcmla270s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vadd_scalarb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vadd_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VQSHL_U 111 1 1111 0 . .. ... 0 ... 0 0100 . 1 . 1 ... 0 @2op_rev VQRSHL_S 111 0 1111 0 . .. ... 0 ... 0 0101 . 1 . 1 ... 0 @2op_rev VQRSHL_U 111 1 1111 0 . .. ... 0 ... 0 0101 . 1 . 1 ... 0 @2op_rev -VQDMLADH 1110 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op -VQDMLADHX 1110 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op -VQRDMLADH 1110 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op -VQRDMLADHX 1110 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op +{ + VCMUL0 111 . 1110 0 . 11 ... 0 ... 0 1110 . 0 . 0 ... 0 @2op_sz28 + VQDMLADH 1110 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op + VQDMLSDH 1111 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op +} -VQDMLSDH 1111 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 0 @2op -VQDMLSDHX 1111 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op -VQRDMLSDH 1111 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op -VQRDMLSDHX 1111 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op +{ + VCMUL180 111 . 1110 0 . 11 ... 0 ... 1 1110 . 0 . 0 ... 0 @2op_sz28 + VQDMLADHX 111 0 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op + VQDMLSDHX 111 1 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 0 @2op +} + +{ + VCMUL90 111 . 1110 0 . 11 ... 0 ... 0 1110 . 0 . 0 ... 1 @2op_sz28 + VQRDMLADH 111 0 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op + VQRDMLSDH 111 1 1110 0 . .. ... 0 ... 0 1110 . 0 . 0 ... 1 @2op +} + +{ + VCMUL270 111 . 1110 0 . 11 ... 0 ... 1 1110 . 0 . 0 ... 1 @2op_sz28 + VQRDMLADHX 111 0 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op + VQRDMLSDHX 111 1 1110 0 . .. ... 0 ... 1 1110 . 0 . 0 ... 1 @2op +} VQDMULLB 111 . 1110 0 . 11 ... 0 ... 0 1111 . 0 . 0 ... 1 @2op_sz28 VQDMULLT 111 . 1110 0 . 11 ... 0 ... 1 1111 . 0 . 0 ... 1 @2op_sz28 @@ -XXX,XX +XXX,XX @@ VCADD270_fp 1111 1101 1 . 0 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_ VFMA 1110 1111 0 . 0 . ... 0 ... 0 1100 . 1 . 1 ... 0 @2op_fp VFMS 1110 1111 0 . 1 . ... 0 ... 0 1100 . 1 . 1 ... 0 @2op_fp + +VCMLA0 1111 110 00 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev +VCMLA90 1111 110 01 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev +VCMLA180 1111 110 10 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev +VCMLA270 1111 110 11 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VFMA(vfmah, 2, float16, false) DO_VFMA(vfmas, 4, float32, false) DO_VFMA(vfmsh, 2, float16, true) DO_VFMA(vfmss, 4, float32, true) + +#define DO_VCMLA(OP, ESIZE, TYPE, ROT, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, void *vm) \ + { \ + TYPE *d = vd, *n = vn, *m = vm; \ + TYPE r0, r1, e1, e2, e3, e4; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst0, *fpst1; \ + float_status scratch_fpst; \ + /* We loop through pairs of elements at a time */ \ + for (e = 0; e < 16 / ESIZE; e += 2, mask >>= ESIZE * 2) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE * 2)) == 0) { \ + continue; \ + } \ + fpst0 = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + fpst1 = fpst0; \ + if (!(mask & 1)) { \ + scratch_fpst = *fpst0; \ + fpst0 = &scratch_fpst; \ + } \ + if (!(mask & (1 << ESIZE))) { \ + scratch_fpst = *fpst1; \ + fpst1 = &scratch_fpst; \ + } \ + switch (ROT) { \ + case 0: \ + e1 = m[H##ESIZE(e)]; \ + e2 = n[H##ESIZE(e)]; \ + e3 = m[H##ESIZE(e + 1)]; \ + e4 = n[H##ESIZE(e)]; \ + break; \ + case 1: \ + e1 = TYPE##_chs(m[H##ESIZE(e + 1)]); \ + e2 = n[H##ESIZE(e + 1)]; \ + e3 = m[H##ESIZE(e)]; \ + e4 = n[H##ESIZE(e + 1)]; \ + break; \ + case 2: \ + e1 = TYPE##_chs(m[H##ESIZE(e)]); \ + e2 = n[H##ESIZE(e)]; \ + e3 = TYPE##_chs(m[H##ESIZE(e + 1)]); \ + e4 = n[H##ESIZE(e)]; \ + break; \ + case 3: \ + e1 = m[H##ESIZE(e + 1)]; \ + e2 = n[H##ESIZE(e + 1)]; \ + e3 = TYPE##_chs(m[H##ESIZE(e)]); \ + e4 = n[H##ESIZE(e + 1)]; \ + break; \ + default: \ + g_assert_not_reached(); \ + } \ + r0 = FN(e2, e1, d[H##ESIZE(e)], fpst0); \ + r1 = FN(e4, e3, d[H##ESIZE(e + 1)], fpst1); \ + mergemask(&d[H##ESIZE(e)], r0, mask); \ + mergemask(&d[H##ESIZE(e + 1)], r1, mask >> ESIZE); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VCMULH(N, M, D, S) float16_mul(N, M, S) +#define DO_VCMULS(N, M, D, S) float32_mul(N, M, S) + +#define DO_VCMLAH(N, M, D, S) float16_muladd(N, M, D, 0, S) +#define DO_VCMLAS(N, M, D, S) float32_muladd(N, M, D, 0, S) + +DO_VCMLA(vcmul0h, 2, float16, 0, DO_VCMULH) +DO_VCMLA(vcmul0s, 4, float32, 0, DO_VCMULS) +DO_VCMLA(vcmul90h, 2, float16, 1, DO_VCMULH) +DO_VCMLA(vcmul90s, 4, float32, 1, DO_VCMULS) +DO_VCMLA(vcmul180h, 2, float16, 2, DO_VCMULH) +DO_VCMLA(vcmul180s, 4, float32, 2, DO_VCMULS) +DO_VCMLA(vcmul270h, 2, float16, 3, DO_VCMULH) +DO_VCMLA(vcmul270s, 4, float32, 3, DO_VCMULS) + +DO_VCMLA(vcmla0h, 2, float16, 0, DO_VCMLAH) +DO_VCMLA(vcmla0s, 4, float32, 0, DO_VCMLAS) +DO_VCMLA(vcmla90h, 2, float16, 1, DO_VCMLAH) +DO_VCMLA(vcmla90s, 4, float32, 1, DO_VCMLAS) +DO_VCMLA(vcmla180h, 2, float16, 2, DO_VCMLAH) +DO_VCMLA(vcmla180s, 4, float32, 2, DO_VCMLAS) +DO_VCMLA(vcmla270h, 2, float16, 3, DO_VCMLAH) +DO_VCMLA(vcmla270s, 4, float32, 3, DO_VCMLAS) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_FP(VCADD90_fp, vfcadd90) DO_2OP_FP(VCADD270_fp, vfcadd270) DO_2OP_FP(VFMA, vfma) DO_2OP_FP(VFMS, vfms) +DO_2OP_FP(VCMUL0, vcmul0) +DO_2OP_FP(VCMUL90, vcmul90) +DO_2OP_FP(VCMUL180, vcmul180) +DO_2OP_FP(VCMUL270, vcmul270) +DO_2OP_FP(VCMLA0, vcmla0) +DO_2OP_FP(VCMLA90, vcmla90) +DO_2OP_FP(VCMLA180, vcmla180) +DO_2OP_FP(VCMLA270, vcmla270) static bool do_2op_scalar(DisasContext *s, arg_2scalar *a, MVEGenTwoOpScalarFn fn) -- 2.20.1 Implement the MVE VMAXNMA and VMINNMA insns; these are 2-operand, but the destination register must be the same as one of the source registers. We defer the decode of the size in bit 28 to the individual insn patterns rather than doing it in the format, because otherwise we would have a single insn pattern that overlapped with two groups (eg VMAXNMA with the VMULH_S and VMULH_U groups). Having two insn patterns per insn seems clearer than a complex multilevel nesting of overlapping and non-overlapping groups. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-mve.h | 6 ++++++ target/arm/mve.decode | 11 +++++++++++ target/arm/mve_helper.c | 23 +++++++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 42 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vmaxnms, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vminnmh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vminnms, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmaxnmah, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmaxnmas, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + +DEF_HELPER_FLAGS_4(mve_vminnmah, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vminnmas, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vfcadd90h, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vfcadd90s, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ @2op_fp_size_rev .... .... .... .... .... .... .... .... &2op \ qd=%qd qn=%qn qm=%qm size=%2op_fp_size_rev +# 2-operand, but Qd and Qn share a field. Size is in bit 28, but we +# don't decode it in this format +@vmaxnma .... .... .... .... .... .... .... .... &2op \ + qd=%qd qn=%qd qm=%qm + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op # The VSHLL T2 encoding is not a @2op pattern, but is here because it # overlaps what would be size=0b11 VMULH/VRMULH { + VMAXNMA 111 0 1110 0 . 11 1111 ... 0 1110 1 0 . 0 ... 1 @vmaxnma size=2 + VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op } { + VMAXNMA 111 1 1110 0 . 11 1111 ... 0 1110 1 0 . 0 ... 1 @vmaxnma size=1 + VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op } { + VMINNMA 111 0 1110 0 . 11 1111 ... 1 1110 1 0 . 0 ... 1 @vmaxnma size=2 VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op } { + VMINNMA 111 1 1110 0 . 11 1111 ... 1 1110 1 0 . 0 ... 1 @vmaxnma size=1 VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2OP_FP_ALL(vfabd, abd) DO_2OP_FP_ALL(vmaxnm, maxnum) DO_2OP_FP_ALL(vminnm, minnum) +static inline float16 float16_maxnuma(float16 a, float16 b, float_status *s) +{ + return float16_maxnum(float16_abs(a), float16_abs(b), s); +} + +static inline float32 float32_maxnuma(float32 a, float32 b, float_status *s) +{ + return float32_maxnum(float32_abs(a), float32_abs(b), s); +} + +static inline float16 float16_minnuma(float16 a, float16 b, float_status *s) +{ + return float16_minnum(float16_abs(a), float16_abs(b), s); +} + +static inline float32 float32_minnuma(float32 a, float32 b, float_status *s) +{ + return float32_minnum(float32_abs(a), float32_abs(b), s); +} + +DO_2OP_FP_ALL(vmaxnma, maxnuma) +DO_2OP_FP_ALL(vminnma, minnuma) + #define DO_VCADD_FP(OP, ESIZE, TYPE, FN0, FN1) \ void HELPER(glue(mve_, OP))(CPUARMState *env, \ void *vd, void *vn, void *vm) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_FP(VCMLA0, vcmla0) DO_2OP_FP(VCMLA90, vcmla90) DO_2OP_FP(VCMLA180, vcmla180) DO_2OP_FP(VCMLA270, vcmla270) +DO_2OP_FP(VMAXNMA, vmaxnma) +DO_2OP_FP(VMINNMA, vminnma) static bool do_2op_scalar(DisasContext *s, arg_2scalar *a, MVEGenTwoOpScalarFn fn) -- 2.20.1 Implement the MVE scalar floating point insns VADD, VSUB and VMUL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 9 +++++++++ target/arm/mve.decode | 27 +++++++++++++++++++++------ target/arm/mve_helper.c | 35 +++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 20 ++++++++++++++++++++ 4 files changed, 85 insertions(+), 6 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vcmple_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vcmple_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vcmple_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfadd_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfsub_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfsub_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfmul_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfmul_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ %2op_fp_size 20:1 !function=neon_3same_fp_size # VCADD is an exception, where bit 20 is 0 for 16 bit and 1 for 32 bit %2op_fp_size_rev 20:1 !function=plus_1 +# FP scalars have size in bit 28, 1 for 16 bit, 0 for 32 bit +%2op_fp_scalar_size 28:1 !function=neon_3same_fp_size # 1imm format immediate %imm_28_16_0 28:1 16:3 0:4 @@ -XXX,XX +XXX,XX @@ @vmaxnma .... .... .... .... .... .... .... .... &2op \ qd=%qd qn=%qd qm=%qm +@2op_fp_scalar .... .... .... .... .... .... .... rm:4 &2scalar \ + qd=%qd qn=%qn size=%2op_fp_scalar_size + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar } -VHADD_S_scalar 1110 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar -VHADD_U_scalar 1111 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar -VHSUB_S_scalar 1110 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar -VHSUB_U_scalar 1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar +{ + VADD_fp_scalar 111 . 1110 0 . 11 ... 0 ... 0 1111 . 100 .... @2op_fp_scalar + VHADD_S_scalar 1110 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar + VHADD_U_scalar 1111 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar +} + +{ + VSUB_fp_scalar 111 . 1110 0 . 11 ... 0 ... 1 1111 . 100 .... @2op_fp_scalar + VHSUB_S_scalar 1110 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar + VHSUB_U_scalar 1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar +} { VQADD_S_scalar 1110 1110 0 . .. ... 0 ... 0 1111 . 110 .... @2scalar @@ -XXX,XX +XXX,XX @@ VHSUB_U_scalar 1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar size=%size_28 } -VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar -VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar +{ + VMUL_fp_scalar 111 . 1110 0 . 11 ... 1 ... 0 1110 . 110 .... @2op_fp_scalar + VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar + VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar +} # The U bit (28) is don't-care because it does not affect the result VMLA 111- 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VCMLA(vcmla180h, 2, float16, 2, DO_VCMLAH) DO_VCMLA(vcmla180s, 4, float32, 2, DO_VCMLAS) DO_VCMLA(vcmla270h, 2, float16, 3, DO_VCMLAH) DO_VCMLA(vcmla270s, 4, float32, 3, DO_VCMLAS) + +#define DO_2OP_FP_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE r, m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], m, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_2OP_FP_SCALAR_ALL(OP, FN) \ + DO_2OP_FP_SCALAR(OP##h, 2, float16, float16_##FN) \ + DO_2OP_FP_SCALAR(OP##s, 4, float32, float32_##FN) + +DO_2OP_FP_SCALAR_ALL(vfadd_scalar, add) +DO_2OP_FP_SCALAR_ALL(vfsub_scalar, sub) +DO_2OP_FP_SCALAR_ALL(vfmul_scalar, mul) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VQDMULLT_scalar(DisasContext *s, arg_2scalar *a) return do_2op_scalar(s, a, fns[a->size]); } + +#define DO_2OP_FP_SCALAR(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_2scalar *a) \ + { \ + static MVEGenTwoOpScalarFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_2op_scalar(s, a, fns[a->size]); \ + } + +DO_2OP_FP_SCALAR(VADD_fp_scalar, vfadd_scalar) +DO_2OP_FP_SCALAR(VSUB_fp_scalar, vfsub_scalar) +DO_2OP_FP_SCALAR(VMUL_fp_scalar, vfmul_scalar) + static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a, MVEGenLongDualAccOpFn *fn) { -- 2.20.1 Implement the MVE fp-with-scalar VFMA and VFMAS insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 6 ++++++ target/arm/mve.decode | 14 +++++++++++--- target/arm/mve_helper.c | 37 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 56 insertions(+), 3 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vfsub_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vfmul_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vfmul_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfma_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfma_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vfmas_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vfmas_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar } -# The U bit (28) is don't-care because it does not affect the result -VMLA 111- 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar -VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar +{ + VFMA_scalar 111 . 1110 0 . 11 ... 1 ... 0 1110 . 100 .... @2op_fp_scalar + # The U bit (28) is don't-care because it does not affect the result + VMLA 111 - 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar +} + +{ + VFMAS_scalar 111 . 1110 0 . 11 ... 1 ... 1 1110 . 100 .... @2op_fp_scalar + # The U bit (28) is don't-care because it does not affect the result + VMLAS 111 - 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar +} VQRDMLAH 1110 1110 0 . .. ... 0 ... 0 1110 . 100 .... @2scalar VQRDMLASH 1110 1110 0 . .. ... 0 ... 1 1110 . 100 .... @2scalar diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VCMLA(vcmla270s, 4, float32, 3, DO_VCMLAS) DO_2OP_FP_SCALAR_ALL(vfadd_scalar, add) DO_2OP_FP_SCALAR_ALL(vfsub_scalar, sub) DO_2OP_FP_SCALAR_ALL(vfmul_scalar, mul) + +#define DO_2OP_FP_ACC_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vn, uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE r, m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], m, d[H##ESIZE(e)], 0, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +/* VFMAS is vector * vector + scalar, so swap op2 and op3 */ +#define DO_VFMAS_SCALARH(N, M, D, F, S) float16_muladd(N, D, M, F, S) +#define DO_VFMAS_SCALARS(N, M, D, F, S) float32_muladd(N, D, M, F, S) + +/* VFMA is vector * scalar + vector */ +DO_2OP_FP_ACC_SCALAR(vfma_scalarh, 2, float16, float16_muladd) +DO_2OP_FP_ACC_SCALAR(vfma_scalars, 4, float32, float32_muladd) +DO_2OP_FP_ACC_SCALAR(vfmas_scalarh, 2, float16, DO_VFMAS_SCALARH) +DO_2OP_FP_ACC_SCALAR(vfmas_scalars, 4, float32, DO_VFMAS_SCALARS) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VQDMULLT_scalar(DisasContext *s, arg_2scalar *a) DO_2OP_FP_SCALAR(VADD_fp_scalar, vfadd_scalar) DO_2OP_FP_SCALAR(VSUB_fp_scalar, vfsub_scalar) DO_2OP_FP_SCALAR(VMUL_fp_scalar, vfmul_scalar) +DO_2OP_FP_SCALAR(VFMA_scalar, vfma_scalar) +DO_2OP_FP_SCALAR(VFMAS_scalar, vfmas_scalar) static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a, MVEGenLongDualAccOpFn *fn) -- 2.20.1 In commit a777d6033447a we added an assertion to parts_silence_nan() that prohibits calling float*_silence_nan() when in default-NaN mode. This ties together a property of the output ("do we generate a default NaN when the result is a NaN?") with an operation on an input ("silence this input NaN"). It's true that most of the time when in default-NaN mode you won't need to silence an input NaN, because you can just produce the default NaN as the result instead. But some functions like float*_maxnum() are defined to be able to work with quiet NaNs, so silencing an input SNaN is still reasonable. In particular, the upcoming implementation of MVE VMAXNMV would fall over this assertion if we didn't delete it. Delete the assertion. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- fpu/softfloat-specialize.c.inc | 1 - 1 file changed, 1 deletion(-) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts128_default_nan(FloatParts128 *p, float_status *status) static uint64_t parts_silence_nan_frac(uint64_t frac, float_status *status) { g_assert(!no_signaling_nans(status)); - g_assert(!status->default_nan_mode); /* The only snan_bit_is_one target without default_nan_mode is HPPA. */ if (snan_bit_is_one(status)) { -- 2.20.1 Implement the MVE VMAXNMV, VMINNMV, VMAXNMAV, VMINNMAV insns. These calculate the maximum or minimum of floating point elements across a vector, starting with a value in a general purpose register and returning the result there. The pseudocode silences a possible SNaN in the accumulating result on every iteration (by calling FPConvertNaN), but we do it only on the input ra, because if none of the inputs to float*_maxnum or float*_minnum are SNaNs then the result can't be an SNaN. Note that we can't use the float*_maxnuma() etc functions we defined earlier for VMAXNMA and VMINNMA, because we mustn't take the absolute value of the starting general-purpose register value, which could be negative. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 12 +++++++++++ target/arm/mve.decode | 32 +++++++++++++++++++++------ target/arm/mve_helper.c | 44 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 20 +++++++++++++++++ 4 files changed, 102 insertions(+), 6 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vminavb, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vminavh, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vminavw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxnmvh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxnmvs, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vminnmvh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminnmvs, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vmaxnmavh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxnmavs, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vminnmavh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminnmavs, TCG_CALL_NO_WG, i32, env, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ @vmaxnma .... .... .... .... .... .... .... .... &2op \ qd=%qd qn=%qd qm=%qm +# Here also we don't decode the bit 28 size in the format to avoid +# awkward nested overlap groups +@vmaxnmv .... .... .... .... rda:4 .... .... .... &vmaxv qm=%qm + @2op_fp_scalar .... .... .... .... .... .... .... rm:4 &2scalar \ qd=%qd qn=%qn size=%2op_fp_scalar_size @@ -XXX,XX +XXX,XX @@ VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz { - VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv - VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv - VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv - VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv + [ + VMAXNMAV 1110 1110 1110 11 00 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=2 + VMINNMAV 1110 1110 1110 11 00 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=2 + VMAXNMV 1110 1110 1110 11 10 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=2 + VMINNMV 1110 1110 1110 11 10 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=2 + ] + [ + VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv + ] VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz } { - VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv - VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + [ + VMAXNMAV 1111 1110 1110 11 00 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=1 + VMINNMAV 1111 1110 1110 11 00 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=1 + VMAXNMV 1111 1110 1110 11 10 .... 1111 0 0 . 0 ... 0 @vmaxnmv size=1 + VMINNMV 1111 1110 1110 11 10 .... 1111 1 0 . 0 ... 0 @vmaxnmv size=1 + ] + [ + VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + ] VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2OP_FP_ACC_SCALAR(vfma_scalarh, 2, float16, float16_muladd) DO_2OP_FP_ACC_SCALAR(vfma_scalars, 4, float32, float32_muladd) DO_2OP_FP_ACC_SCALAR(vfmas_scalarh, 2, float16, DO_VFMAS_SCALARH) DO_2OP_FP_ACC_SCALAR(vfmas_scalars, 4, float32, DO_VFMAS_SCALARS) + +/* Floating point max/min across vector. */ +#define DO_FP_VMAXMINV(OP, ESIZE, TYPE, ABS, FN) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ + uint32_t ra_in) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *m = vm; \ + TYPE ra = (TYPE)ra_in; \ + float_status *fpst = (ESIZE == 2) ? \ + &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + TYPE v = m[H##ESIZE(e)]; \ + if (TYPE##_is_signaling_nan(ra, fpst)) { \ + ra = TYPE##_silence_nan(ra, fpst); \ + float_raise(float_flag_invalid, fpst); \ + } \ + if (TYPE##_is_signaling_nan(v, fpst)) { \ + v = TYPE##_silence_nan(v, fpst); \ + float_raise(float_flag_invalid, fpst); \ + } \ + if (ABS) { \ + v = TYPE##_abs(v); \ + } \ + ra = FN(ra, v, fpst); \ + } \ + } \ + mve_advance_vpt(env); \ + return ra; \ + } \ + +#define NOP(X) (X) + +DO_FP_VMAXMINV(vmaxnmvh, 2, float16, false, float16_maxnum) +DO_FP_VMAXMINV(vmaxnmvs, 4, float32, false, float32_maxnum) +DO_FP_VMAXMINV(vminnmvh, 2, float16, false, float16_minnum) +DO_FP_VMAXMINV(vminnmvs, 4, float32, false, float32_minnum) +DO_FP_VMAXMINV(vmaxnmavh, 2, float16, true, float16_maxnum) +DO_FP_VMAXMINV(vmaxnmavs, 4, float32, true, float32_maxnum) +DO_FP_VMAXMINV(vminnmavh, 2, float16, true, float16_minnum) +DO_FP_VMAXMINV(vminnmavs, 4, float32, true, float32_minnum) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_VMAXV(VMINV_S, vminvs) DO_VMAXV(VMINV_U, vminvu) DO_VMAXV(VMINAV, vminav) +#define DO_VMAXV_FP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vmaxv *a) \ + { \ + static MVEGenVADDVFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_vmaxv(s, a, fns[a->size]); \ + } + +DO_VMAXV_FP(VMAXNMV, vmaxnmv) +DO_VMAXV_FP(VMINNMV, vminnmv) +DO_VMAXV_FP(VMAXNMAV, vmaxnmav) +DO_VMAXV_FP(VMINNMAV, vminnmav) + static bool do_vabav(DisasContext *s, arg_vabav *a, MVEGenVABAVFn *fn) { /* Absolute difference accumulated across vector */ -- 2.20.1 Implement the MVE fp vector comparisons VCMP and VPT. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 18 +++++++++++ target/arm/mve.decode | 39 +++++++++++++++++++---- target/arm/mve_helper.c | 64 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 22 +++++++++++++ 4 files changed, 137 insertions(+), 6 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vcmple_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vcmple_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vcmple_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmpeqh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmpeqs, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmpneh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmpnes, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmpgeh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmpges, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmplth, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmplts, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmpgth, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmpgts, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vfcmpleh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmples, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vfadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vfadd_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ @vcmp_scalar .... .... .. size:2 qn:3 . .... .... .... rm:4 &vcmp_scalar \ mask=%mask_22_13 +@vcmp_fp .... .... .... qn:3 . .... .... .... .... &vcmp \ + qm=%qm size=%2op_fp_scalar_size mask=%mask_22_13 + @vmaxv .... .... .... size:2 .. rda:4 .... .... .... &vmaxv qm=%qm @2op_fp .... .... .... .... .... .... .... .... &2op \ @@ -XXX,XX +XXX,XX @@ VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd # Comparisons. We expand out the conditions which are split across # encodings T1, T2, T3 and the fc bits. These include VPT, which is # effectively "VCMP then VPST". A plain "VCMP" has a mask field of zero. -VCMPEQ 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp -VCMPNE 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp +{ + VCMPEQ_fp 111 . 1110 0 . 11 ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp_fp + VCMPEQ 111 1 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp +} + +{ + VCMPNE_fp 111 . 1110 0 . 11 ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp_fp + VCMPNE 111 1 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp +} + +{ + VCMPGE_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp_fp + VCMPGE 111 1 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp +} + +{ + VCMPLT_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp_fp + VCMPLT 111 1 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp +} + +{ + VCMPGT_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp_fp + VCMPGT 111 1 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp +} + +{ + VCMPLE_fp 111 . 1110 0 . 11 ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp_fp + VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp +} + { VPSEL 1111 1110 0 . 11 ... 1 ... 0 1111 . 0 . 0 ... 1 @2op_nosz VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp } -VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp -VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp -VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp -VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp { VPNOT 1111 1110 0 0 11 000 1 000 0 1111 0100 1101 diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_FP_VMAXMINV(vmaxnmavh, 2, float16, true, float16_maxnum) DO_FP_VMAXMINV(vmaxnmavs, 4, float32, true, float32_maxnum) DO_FP_VMAXMINV(vminnmavh, 2, float16, true, float16_minnum) DO_FP_VMAXMINV(vminnmavs, 4, float32, true, float32_minnum) + +/* FP compares; note that all comparisons signal InvalidOp for QNaNs */ +#define DO_VCMP_FP(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, void *vm) \ + { \ + TYPE *n = vn, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + uint16_t beatpred = 0; \ + uint16_t emask = MAKE_64BIT_MASK(0, ESIZE); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + bool r; \ + for (e = 0; e < 16 / ESIZE; e++, emask <<= ESIZE) { \ + if ((mask & emask) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & (1 << (e * ESIZE)))) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], m[H##ESIZE(e)], fpst); \ + /* Comparison sets 0/1 bits for each byte in the element */ \ + beatpred |= r * emask; \ + } \ + beatpred &= mask; \ + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | \ + (beatpred & eci_mask); \ + mve_advance_vpt(env); \ + } + +/* + * Some care is needed here to get the correct result for the unordered case. + * Architecturally EQ, GE and GT are defined to be false for unordered, but + * the NE, LT and LE comparisons are defined as simple logical inverses of + * EQ, GE and GT and so they must return true for unordered. The softfloat + * comparison functions float*_{eq,le,lt} all return false for unordered. + */ +#define DO_GE16(X, Y, S) float16_le(Y, X, S) +#define DO_GE32(X, Y, S) float32_le(Y, X, S) +#define DO_GT16(X, Y, S) float16_lt(Y, X, S) +#define DO_GT32(X, Y, S) float32_lt(Y, X, S) + +DO_VCMP_FP(vfcmpeqh, 2, float16, float16_eq) +DO_VCMP_FP(vfcmpeqs, 4, float32, float32_eq) + +DO_VCMP_FP(vfcmpneh, 2, float16, !float16_eq) +DO_VCMP_FP(vfcmpnes, 4, float32, !float32_eq) + +DO_VCMP_FP(vfcmpgeh, 2, float16, DO_GE16) +DO_VCMP_FP(vfcmpges, 4, float32, DO_GE32) + +DO_VCMP_FP(vfcmplth, 2, float16, !DO_GE16) +DO_VCMP_FP(vfcmplts, 4, float32, !DO_GE32) + +DO_VCMP_FP(vfcmpgth, 2, float16, DO_GT16) +DO_VCMP_FP(vfcmpgts, 4, float32, DO_GT32) + +DO_VCMP_FP(vfcmpleh, 2, float16, !DO_GT16) +DO_VCMP_FP(vfcmples, 4, float32, !DO_GT32) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_VCMP(VCMPLT, vcmplt) DO_VCMP(VCMPGT, vcmpgt) DO_VCMP(VCMPLE, vcmple) +#define DO_VCMP_FP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vcmp *a) \ + { \ + static MVEGenCmpFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_vcmp(s, a, fns[a->size]); \ + } + +DO_VCMP_FP(VCMPEQ_fp, vfcmpeq) +DO_VCMP_FP(VCMPNE_fp, vfcmpne) +DO_VCMP_FP(VCMPGE_fp, vfcmpge) +DO_VCMP_FP(VCMPLT_fp, vfcmplt) +DO_VCMP_FP(VCMPGT_fp, vfcmpgt) +DO_VCMP_FP(VCMPLE_fp, vfcmple) + static bool do_vmaxv(DisasContext *s, arg_vmaxv *a, MVEGenVADDVFn fn) { /* -- 2.20.1 Implement the MVE fp scalar comparisons VCMP and VPT. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 18 +++++++++++ target/arm/mve.decode | 61 +++++++++++++++++++++++++++++-------- target/arm/mve_helper.c | 62 ++++++++++++++++++++++++++++++-------- target/arm/translate-mve.c | 14 +++++++++ 4 files changed, 131 insertions(+), 24 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vfcmpgts, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfcmpleh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfcmples, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vfcmpeq_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmpeq_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmpne_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmpne_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmpge_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmpge_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmplt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmplt_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmpgt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmpgt_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vfcmple_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vfcmple_scalars, TCG_CALL_NO_WG, void, env, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vfadd_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vfadd_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ @vcmp_fp .... .... .... qn:3 . .... .... .... .... &vcmp \ qm=%qm size=%2op_fp_scalar_size mask=%mask_22_13 +# Bit 28 is a 2op_fp_scalar_size bit, but we do not decode it in this +# format to avoid complicated overlapping-instruction-groups +@vcmp_fp_scalar .... .... .... qn:3 . .... .... .... rm:4 &vcmp_scalar \ + mask=%mask_22_13 + @vmaxv .... .... .... size:2 .. rda:4 .... .... .... &vmaxv qm=%qm @2op_fp .... .... .... .... .... .... .... .... &2op \ @@ -XXX,XX +XXX,XX @@ VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 VIWDUP 1110 1110 0 . .. ... 1 ... 0 1111 . 110 ... . @viwdup } { - VDDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 111 . @vidup - VDWDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 ... . @viwdup + VCMPGT_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 0110 .... @vcmp_fp_scalar size=2 + VCMPLE_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 1110 .... @vcmp_fp_scalar size=2 + VDDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 111 . @vidup + VDWDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 ... . @viwdup } # multiply-add long dual accumulate @@ -XXX,XX +XXX,XX @@ VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz # Scalar operations -VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar -VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar +{ + VCMPEQ_fp_scalar 1110 1110 0 . 11 ... 1 ... 0 1111 0100 .... @vcmp_fp_scalar size=2 + VCMPNE_fp_scalar 1110 1110 0 . 11 ... 1 ... 0 1111 1100 .... @vcmp_fp_scalar size=2 + VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar +} + +{ + VCMPLT_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 1100 .... @vcmp_fp_scalar size=2 + VCMPGE_fp_scalar 1110 1110 0 . 11 ... 1 ... 1 1111 0100 .... @vcmp_fp_scalar size=2 + VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar +} { VSHL_S_scalar 1110 1110 0 . 11 .. 01 ... 1 1110 0110 .... @shl_scalar @@ -XXX,XX +XXX,XX @@ VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd } { - VPNOT 1111 1110 0 0 11 000 1 000 0 1111 0100 1101 - VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 - VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 0 0 .... @vcmp_scalar + VPNOT 1111 1110 0 0 11 000 1 000 0 1111 0100 1101 + VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 + VCMPEQ_fp_scalar 1111 1110 0 . 11 ... 1 ... 0 1111 0100 .... @vcmp_fp_scalar size=1 + VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0100 .... @vcmp_scalar } -VCMPNE_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 0 0 .... @vcmp_scalar + +{ + VCMPNE_fp_scalar 1111 1110 0 . 11 ... 1 ... 0 1111 1100 .... @vcmp_fp_scalar size=1 + VCMPNE_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1100 .... @vcmp_scalar +} + +{ + VCMPGT_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 0110 .... @vcmp_fp_scalar size=1 + VCMPGT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0110 .... @vcmp_scalar +} + +{ + VCMPLE_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 1110 .... @vcmp_fp_scalar size=1 + VCMPLE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1110 .... @vcmp_scalar +} + +{ + VCMPGE_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 0100 .... @vcmp_fp_scalar size=1 + VCMPGE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0100 .... @vcmp_scalar +} +{ + VCMPLT_fp_scalar 1111 1110 0 . 11 ... 1 ... 1 1111 1100 .... @vcmp_fp_scalar size=1 + VCMPLT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1100 .... @vcmp_scalar +} + VCMPCS_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 1 0 .... @vcmp_scalar VCMPHI_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 1 0 .... @vcmp_scalar -VCMPGE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 0 0 .... @vcmp_scalar -VCMPLT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 0 0 .... @vcmp_scalar -VCMPGT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 1 0 .... @vcmp_scalar -VCMPLE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 1 0 .... @vcmp_scalar # 2-operand FP VADD_fp 1110 1111 0 . 0 . ... 0 ... 0 1101 . 1 . 0 ... 0 @2op_fp diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_FP_VMAXMINV(vminnmavs, 4, float32, true, float32_minnum) mve_advance_vpt(env); \ } +#define DO_VCMP_FP_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + uint32_t rm) \ + { \ + TYPE *n = vn; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + uint16_t beatpred = 0; \ + uint16_t emask = MAKE_64BIT_MASK(0, ESIZE); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + bool r; \ + for (e = 0; e < 16 / ESIZE; e++, emask <<= ESIZE) { \ + if ((mask & emask) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & (1 << (e * ESIZE)))) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(n[H##ESIZE(e)], (TYPE)rm, fpst); \ + /* Comparison sets 0/1 bits for each byte in the element */ \ + beatpred |= r * emask; \ + } \ + beatpred &= mask; \ + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | \ + (beatpred & eci_mask); \ + mve_advance_vpt(env); \ + } + +#define DO_VCMP_FP_BOTH(VOP, SOP, ESIZE, TYPE, FN) \ + DO_VCMP_FP(VOP, ESIZE, TYPE, FN) \ + DO_VCMP_FP_SCALAR(SOP, ESIZE, TYPE, FN) + /* * Some care is needed here to get the correct result for the unordered case. * Architecturally EQ, GE and GT are defined to be false for unordered, but @@ -XXX,XX +XXX,XX @@ DO_FP_VMAXMINV(vminnmavs, 4, float32, true, float32_minnum) #define DO_GT16(X, Y, S) float16_lt(Y, X, S) #define DO_GT32(X, Y, S) float32_lt(Y, X, S) -DO_VCMP_FP(vfcmpeqh, 2, float16, float16_eq) -DO_VCMP_FP(vfcmpeqs, 4, float32, float32_eq) +DO_VCMP_FP_BOTH(vfcmpeqh, vfcmpeq_scalarh, 2, float16, float16_eq) +DO_VCMP_FP_BOTH(vfcmpeqs, vfcmpeq_scalars, 4, float32, float32_eq) -DO_VCMP_FP(vfcmpneh, 2, float16, !float16_eq) -DO_VCMP_FP(vfcmpnes, 4, float32, !float32_eq) +DO_VCMP_FP_BOTH(vfcmpneh, vfcmpne_scalarh, 2, float16, !float16_eq) +DO_VCMP_FP_BOTH(vfcmpnes, vfcmpne_scalars, 4, float32, !float32_eq) -DO_VCMP_FP(vfcmpgeh, 2, float16, DO_GE16) -DO_VCMP_FP(vfcmpges, 4, float32, DO_GE32) +DO_VCMP_FP_BOTH(vfcmpgeh, vfcmpge_scalarh, 2, float16, DO_GE16) +DO_VCMP_FP_BOTH(vfcmpges, vfcmpge_scalars, 4, float32, DO_GE32) -DO_VCMP_FP(vfcmplth, 2, float16, !DO_GE16) -DO_VCMP_FP(vfcmplts, 4, float32, !DO_GE32) +DO_VCMP_FP_BOTH(vfcmplth, vfcmplt_scalarh, 2, float16, !DO_GE16) +DO_VCMP_FP_BOTH(vfcmplts, vfcmplt_scalars, 4, float32, !DO_GE32) -DO_VCMP_FP(vfcmpgth, 2, float16, DO_GT16) -DO_VCMP_FP(vfcmpgts, 4, float32, DO_GT32) +DO_VCMP_FP_BOTH(vfcmpgth, vfcmpgt_scalarh, 2, float16, DO_GT16) +DO_VCMP_FP_BOTH(vfcmpgts, vfcmpgt_scalars, 4, float32, DO_GT32) -DO_VCMP_FP(vfcmpleh, 2, float16, !DO_GT16) -DO_VCMP_FP(vfcmples, 4, float32, !DO_GT32) +DO_VCMP_FP_BOTH(vfcmpleh, vfcmple_scalarh, 2, float16, !DO_GT16) +DO_VCMP_FP_BOTH(vfcmples, vfcmple_scalars, 4, float32, !DO_GT32) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_VCMP(VCMPLE, vcmple) return false; \ } \ return do_vcmp(s, a, fns[a->size]); \ + } \ + static bool trans_##INSN##_scalar(DisasContext *s, \ + arg_vcmp_scalar *a) \ + { \ + static MVEGenScalarCmpFn * const fns[] = { \ + NULL, \ + gen_helper_mve_##FN##_scalarh, \ + gen_helper_mve_##FN##_scalars, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_vcmp_scalar(s, a, fns[a->size]); \ } DO_VCMP_FP(VCMPEQ_fp, vfcmpeq) -- 2.20.1 Implement the MVE VCVT insns which convert between floating and fixed point. As with the Neon equivalents, these use essentially the same constant encoding as right-shift-by-immediate. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 9 +++++++++ target/arm/mve.decode | 19 +++++++++++++++++++ target/arm/mve_helper.c | 36 ++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 18 ++++++++++++++++++ 4 files changed, 82 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vfma_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vfmas_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vfmas_scalars, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vcvt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_hs, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_hu, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_sf, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_uf, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_fs, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_fu, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VCMLA0 1111 110 00 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_ VCMLA90 1111 110 01 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev VCMLA180 1111 110 10 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev VCMLA270 1111 110 11 . 1 . ... 0 ... 0 1000 . 1 . 0 ... 0 @2op_fp_size_rev + +# floating-point <-> fixed-point conversions. Naming convention: +# VCVT_<from><to>, S = signed int, U = unsigned int, H = halfprec, F = singleprec +@vcvt .... .... .. 1 ..... .... .. 1 . .... .... &2shift \ + qd=%qd qm=%qm shift=%rshift_i5 size=2 +@vcvt_f16 .... .... .. 11 .... .... .. 0 . .... .... &2shift \ + qd=%qd qm=%qm shift=%rshift_i4 size=1 + +VCVT_SH_fixed 1110 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt_f16 +VCVT_UH_fixed 1111 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt_f16 + +VCVT_HS_fixed 1110 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt_f16 +VCVT_HU_fixed 1111 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt_f16 + +VCVT_SF_fixed 1110 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt +VCVT_UF_fixed 1111 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt + +VCVT_FS_fixed 1110 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt +VCVT_FU_fixed 1111 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VCMP_FP_BOTH(vfcmpgts, vfcmpgt_scalars, 4, float32, DO_GT32) DO_VCMP_FP_BOTH(vfcmpleh, vfcmple_scalarh, 2, float16, !DO_GT16) DO_VCMP_FP_BOTH(vfcmples, vfcmple_scalars, 4, float32, !DO_GT32) + +#define DO_VCVT_FIXED(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vm, \ + uint32_t shift) \ + { \ + TYPE *d = vd, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(m[H##ESIZE(e)], shift, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VCVT_FIXED(vcvt_sh, 2, int16_t, helper_vfp_shtoh) +DO_VCVT_FIXED(vcvt_uh, 2, uint16_t, helper_vfp_uhtoh) +DO_VCVT_FIXED(vcvt_hs, 2, int16_t, helper_vfp_toshh_round_to_zero) +DO_VCVT_FIXED(vcvt_hu, 2, uint16_t, helper_vfp_touhh_round_to_zero) +DO_VCVT_FIXED(vcvt_sf, 4, int32_t, helper_vfp_sltos) +DO_VCVT_FIXED(vcvt_uf, 4, uint32_t, helper_vfp_ultos) +DO_VCVT_FIXED(vcvt_fs, 4, int32_t, helper_vfp_tosls_round_to_zero) +DO_VCVT_FIXED(vcvt_fu, 4, uint32_t, helper_vfp_touls_round_to_zero) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VRSHRI_U, vrshli_u, true) DO_2SHIFT(VSRI, vsri, false) DO_2SHIFT(VSLI, vsli, false) +#define DO_2SHIFT_FP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ + { \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_2shift(s, a, gen_helper_mve_##FN, false); \ + } + +DO_2SHIFT_FP(VCVT_SH_fixed, vcvt_sh) +DO_2SHIFT_FP(VCVT_UH_fixed, vcvt_uh) +DO_2SHIFT_FP(VCVT_HS_fixed, vcvt_hs) +DO_2SHIFT_FP(VCVT_HU_fixed, vcvt_hu) +DO_2SHIFT_FP(VCVT_SF_fixed, vcvt_sf) +DO_2SHIFT_FP(VCVT_UF_fixed, vcvt_uf) +DO_2SHIFT_FP(VCVT_FS_fixed, vcvt_fs) +DO_2SHIFT_FP(VCVT_FU_fixed, vcvt_fu) + static bool do_2shift_scalar(DisasContext *s, arg_shl_scalar *a, MVEGenTwoOpShiftFn *fn) { -- 2.20.1 Implement the MVE "VCVT (between floating-point and integer)" insn. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve.decode | 7 +++++++ target/arm/translate-mve.c | 32 ++++++++++++++++++++++++++++++++ 2 files changed, 39 insertions(+) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VCVT_UF_fixed 1111 1111 1 . ...... ... 0 11 . 0 01 . 1 ... 0 @vcvt VCVT_FS_fixed 1110 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt VCVT_FU_fixed 1111 1111 1 . ...... ... 0 11 . 1 01 . 1 ... 0 @vcvt + +# VCVT between floating point and integer (halfprec and single); +# VCVT_<from><to>, S = signed int, U = unsigned int, F = float +VCVT_SF 1111 1111 1 . 11 .. 11 ... 0 011 00 1 . 0 ... 0 @1op +VCVT_UF 1111 1111 1 . 11 .. 11 ... 0 011 01 1 . 0 ... 0 @1op +VCVT_FS 1111 1111 1 . 11 .. 11 ... 0 011 10 1 . 0 ... 0 @1op +VCVT_FU 1111 1111 1 . 11 .. 11 ... 0 011 11 1 . 0 ... 0 @1op diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_1OP(VQNEG, vqneg) DO_1OP(VMAXA, vmaxa) DO_1OP(VMINA, vmina) +/* + * For simple float/int conversions we use the fixed-point + * conversion helpers with a zero shift count + */ +#define DO_VCVT(INSN, HFN, SFN) \ + static void gen_##INSN##h(TCGv_ptr env, TCGv_ptr qd, TCGv_ptr qm) \ + { \ + gen_helper_mve_##HFN(env, qd, qm, tcg_constant_i32(0)); \ + } \ + static void gen_##INSN##s(TCGv_ptr env, TCGv_ptr qd, TCGv_ptr qm) \ + { \ + gen_helper_mve_##SFN(env, qd, qm, tcg_constant_i32(0)); \ + } \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + static MVEGenOneOpFn * const fns[] = { \ + NULL, \ + gen_##INSN##h, \ + gen_##INSN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_1op(s, a, fns[a->size]); \ + } + +DO_VCVT(VCVT_SF, vcvt_sh, vcvt_sf) +DO_VCVT(VCVT_UF, vcvt_uh, vcvt_uf) +DO_VCVT(VCVT_FS, vcvt_hs, vcvt_fs) +DO_VCVT(VCVT_FU, vcvt_hu, vcvt_fu) + /* Narrowing moves: only size 0 and 1 are valid */ #define DO_VMOVN(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_1op *a) \ -- 2.20.1 Implement the MVE VCVT which converts from floating-point to integer using a rounding mode specified by the instruction. We implement this similarly to the Neon equivalents, by passing the required rounding mode as an extra integer parameter to the helper functions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 5 ++++ target/arm/mve.decode | 10 ++++++++ target/arm/mve_helper.c | 38 ++++++++++++++++++++++++++++ target/arm/translate-mve.c | 52 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 105 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vminab, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vminah, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vminaw, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vcvt_rm_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_rm_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_rm_ss, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vcvt_rm_us, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VCVT_SF 1111 1111 1 . 11 .. 11 ... 0 011 00 1 . 0 ... 0 @1op VCVT_UF 1111 1111 1 . 11 .. 11 ... 0 011 01 1 . 0 ... 0 @1op VCVT_FS 1111 1111 1 . 11 .. 11 ... 0 011 10 1 . 0 ... 0 @1op VCVT_FU 1111 1111 1 . 11 .. 11 ... 0 011 11 1 . 0 ... 0 @1op + +# VCVT from floating point to integer with specified rounding mode +VCVTAS 1111 1111 1 . 11 .. 11 ... 000 00 0 1 . 0 ... 0 @1op +VCVTAU 1111 1111 1 . 11 .. 11 ... 000 00 1 1 . 0 ... 0 @1op +VCVTNS 1111 1111 1 . 11 .. 11 ... 000 01 0 1 . 0 ... 0 @1op +VCVTNU 1111 1111 1 . 11 .. 11 ... 000 01 1 1 . 0 ... 0 @1op +VCVTPS 1111 1111 1 . 11 .. 11 ... 000 10 0 1 . 0 ... 0 @1op +VCVTPU 1111 1111 1 . 11 .. 11 ... 000 10 1 1 . 0 ... 0 @1op +VCVTMS 1111 1111 1 . 11 .. 11 ... 000 11 0 1 . 0 ... 0 @1op +VCVTMU 1111 1111 1 . 11 .. 11 ... 000 11 1 1 . 0 ... 0 @1op diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VCVT_FIXED(vcvt_sf, 4, int32_t, helper_vfp_sltos) DO_VCVT_FIXED(vcvt_uf, 4, uint32_t, helper_vfp_ultos) DO_VCVT_FIXED(vcvt_fs, 4, int32_t, helper_vfp_tosls_round_to_zero) DO_VCVT_FIXED(vcvt_fu, 4, uint32_t, helper_vfp_touls_round_to_zero) + +/* VCVT with specified rmode */ +#define DO_VCVT_RMODE(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, \ + void *vd, void *vm, uint32_t rmode) \ + { \ + TYPE *d = vd, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + float_status *base_fpst = (ESIZE == 2) ? \ + &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + uint32_t prev_rmode = get_float_rounding_mode(base_fpst); \ + set_float_rounding_mode(rmode, base_fpst); \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = base_fpst; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(m[H##ESIZE(e)], 0, fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + set_float_rounding_mode(prev_rmode, base_fpst); \ + mve_advance_vpt(env); \ + } + +DO_VCVT_RMODE(vcvt_rm_sh, 2, uint16_t, helper_vfp_toshh) +DO_VCVT_RMODE(vcvt_rm_uh, 2, uint16_t, helper_vfp_touhh) +DO_VCVT_RMODE(vcvt_rm_ss, 4, uint32_t, helper_vfp_tosls) +DO_VCVT_RMODE(vcvt_rm_us, 4, uint32_t, helper_vfp_touls) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenVABAVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenDualAccOpFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenVCVTRmodeFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ DO_VCVT(VCVT_UF, vcvt_uh, vcvt_uf) DO_VCVT(VCVT_FS, vcvt_hs, vcvt_fs) DO_VCVT(VCVT_FU, vcvt_hu, vcvt_fu) +static bool do_vcvt_rmode(DisasContext *s, arg_1op *a, + enum arm_fprounding rmode, bool u) +{ + /* + * Handle VCVT fp to int with specified rounding mode. + * This is a 1op fn but we must pass the rounding mode as + * an immediate to the helper. + */ + TCGv_ptr qd, qm; + static MVEGenVCVTRmodeFn * const fns[4][2] = { + { NULL, NULL }, + { gen_helper_mve_vcvt_rm_sh, gen_helper_mve_vcvt_rm_uh }, + { gen_helper_mve_vcvt_rm_ss, gen_helper_mve_vcvt_rm_us }, + { NULL, NULL }, + }; + MVEGenVCVTRmodeFn *fn = fns[a->size][u]; + + if (!dc_isar_feature(aa32_mve_fp, s) || + !mve_check_qreg_bank(s, a->qd | a->qm) || + !fn) { + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qd = mve_qreg_ptr(a->qd); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qd, qm, tcg_constant_i32(arm_rmode_to_sf(rmode))); + tcg_temp_free_ptr(qd); + tcg_temp_free_ptr(qm); + mve_update_eci(s); + return true; +} + +#define DO_VCVT_RMODE(INSN, RMODE, U) \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + return do_vcvt_rmode(s, a, RMODE, U); \ + } \ + +DO_VCVT_RMODE(VCVTAS, FPROUNDING_TIEAWAY, false) +DO_VCVT_RMODE(VCVTAU, FPROUNDING_TIEAWAY, true) +DO_VCVT_RMODE(VCVTNS, FPROUNDING_TIEEVEN, false) +DO_VCVT_RMODE(VCVTNU, FPROUNDING_TIEEVEN, true) +DO_VCVT_RMODE(VCVTPS, FPROUNDING_POSINF, false) +DO_VCVT_RMODE(VCVTPU, FPROUNDING_POSINF, true) +DO_VCVT_RMODE(VCVTMS, FPROUNDING_NEGINF, false) +DO_VCVT_RMODE(VCVTMU, FPROUNDING_NEGINF, true) + /* Narrowing moves: only size 0 and 1 are valid */ #define DO_VMOVN(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_1op *a) \ -- 2.20.1 Implement the MVE VCVT instruction which converts between single and half precision floating point. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 5 +++ target/arm/mve.decode | 8 ++++ target/arm/mve_helper.c | 81 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 14 +++++++ 4 files changed, 108 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vcvt_rm_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vcvt_rm_ss, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vcvt_rm_us, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcvtb_sh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcvtt_sh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcvtb_hs, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcvtt_hs, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op # The VSHLL T2 encoding is not a @2op pattern, but is here because it # overlaps what would be size=0b11 VMULH/VRMULH { + VCVTB_SH 111 0 1110 0 . 11 1111 ... 0 1110 0 0 . 0 ... 1 @1op_nosz + VMAXNMA 111 0 1110 0 . 11 1111 ... 0 1110 1 0 . 0 ... 1 @vmaxnma size=2 VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op } { + VCVTB_HS 111 1 1110 0 . 11 1111 ... 0 1110 0 0 . 0 ... 1 @1op_nosz + VMAXNMA 111 1 1110 0 . 11 1111 ... 0 1110 1 0 . 0 ... 1 @vmaxnma size=1 VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op } { + VCVTT_SH 111 0 1110 0 . 11 1111 ... 1 1110 0 0 . 0 ... 1 @1op_nosz + VMINNMA 111 0 1110 0 . 11 1111 ... 1 1110 1 0 . 0 ... 1 @vmaxnma size=2 VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op } { + VCVTT_HS 111 1 1110 0 . 11 1111 ... 1 1110 0 0 . 0 ... 1 @1op_nosz + VMINNMA 111 1 1110 0 . 11 1111 ... 1 1110 1 0 . 0 ... 1 @vmaxnma size=1 VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VCVT_RMODE(vcvt_rm_sh, 2, uint16_t, helper_vfp_toshh) DO_VCVT_RMODE(vcvt_rm_uh, 2, uint16_t, helper_vfp_touhh) DO_VCVT_RMODE(vcvt_rm_ss, 4, uint32_t, helper_vfp_tosls) DO_VCVT_RMODE(vcvt_rm_us, 4, uint32_t, helper_vfp_touls) + +/* + * VCVT between halfprec and singleprec. As usual for halfprec + * conversions, FZ16 is ignored and AHP is observed. + */ +static void do_vcvt_sh(CPUARMState *env, void *vd, void *vm, int top) +{ + uint16_t *d = vd; + uint32_t *m = vm; + uint16_t r; + uint16_t mask = mve_element_mask(env); + bool ieee = !(env->vfp.xregs[ARM_VFP_FPSCR] & FPCR_AHP); + unsigned e; + float_status *fpst; + float_status scratch_fpst; + float_status *base_fpst = &env->vfp.standard_fp_status; + bool old_fz = get_flush_to_zero(base_fpst); + set_flush_to_zero(false, base_fpst); + for (e = 0; e < 16 / 4; e++, mask >>= 4) { + if ((mask & MAKE_64BIT_MASK(0, 4)) == 0) { + continue; + } + fpst = base_fpst; + if (!(mask & 1)) { + /* We need the result but without updating flags */ + scratch_fpst = *fpst; + fpst = &scratch_fpst; + } + r = float32_to_float16(m[H4(e)], ieee, fpst); + mergemask(&d[H2(e * 2 + top)], r, mask >> (top * 2)); + } + set_flush_to_zero(old_fz, base_fpst); + mve_advance_vpt(env); +} + +static void do_vcvt_hs(CPUARMState *env, void *vd, void *vm, int top) +{ + uint32_t *d = vd; + uint16_t *m = vm; + uint32_t r; + uint16_t mask = mve_element_mask(env); + bool ieee = !(env->vfp.xregs[ARM_VFP_FPSCR] & FPCR_AHP); + unsigned e; + float_status *fpst; + float_status scratch_fpst; + float_status *base_fpst = &env->vfp.standard_fp_status; + bool old_fiz = get_flush_inputs_to_zero(base_fpst); + set_flush_inputs_to_zero(false, base_fpst); + for (e = 0; e < 16 / 4; e++, mask >>= 4) { + if ((mask & MAKE_64BIT_MASK(0, 4)) == 0) { + continue; + } + fpst = base_fpst; + if (!(mask & (1 << (top * 2)))) { + /* We need the result but without updating flags */ + scratch_fpst = *fpst; + fpst = &scratch_fpst; + } + r = float16_to_float32(m[H2(e * 2 + top)], ieee, fpst); + mergemask(&d[H4(e)], r, mask); + } + set_flush_inputs_to_zero(old_fiz, base_fpst); + mve_advance_vpt(env); +} + +void HELPER(mve_vcvtb_sh)(CPUARMState *env, void *vd, void *vm) +{ + do_vcvt_sh(env, vd, vm, 0); +} +void HELPER(mve_vcvtt_sh)(CPUARMState *env, void *vd, void *vm) +{ + do_vcvt_sh(env, vd, vm, 1); +} +void HELPER(mve_vcvtb_hs)(CPUARMState *env, void *vd, void *vm) +{ + do_vcvt_hs(env, vd, vm, 0); +} +void HELPER(mve_vcvtt_hs)(CPUARMState *env, void *vd, void *vm) +{ + do_vcvt_hs(env, vd, vm, 1); +} diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_VCVT_RMODE(VCVTPU, FPROUNDING_POSINF, true) DO_VCVT_RMODE(VCVTMS, FPROUNDING_NEGINF, false) DO_VCVT_RMODE(VCVTMU, FPROUNDING_NEGINF, true) +#define DO_VCVT_SH(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_1op(s, a, gen_helper_mve_##FN); \ + } \ + +DO_VCVT_SH(VCVTB_SH, vcvtb_sh) +DO_VCVT_SH(VCVTT_SH, vcvtt_sh) +DO_VCVT_SH(VCVTB_HS, vcvtb_hs) +DO_VCVT_SH(VCVTT_HS, vcvtt_hs) + /* Narrowing moves: only size 0 and 1 are valid */ #define DO_VMOVN(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_1op *a) \ -- 2.20.1 Implement the MVE VRINT insns, which round floating point inputs to integer values, leaving them in floating point format. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 6 +++++ target/arm/mve.decode | 7 ++++++ target/arm/mve_helper.c | 35 +++++++++++++++++++++++++++++ target/arm/translate-mve.c | 45 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 93 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vcvt_sf, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vcvt_uf, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vcvt_fs, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vcvt_fu, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vrint_rm_h, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vrint_rm_s, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vrintx_h, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vrintx_s, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VCVTPS 1111 1111 1 . 11 .. 11 ... 000 10 0 1 . 0 ... 0 @1op VCVTPU 1111 1111 1 . 11 .. 11 ... 000 10 1 1 . 0 ... 0 @1op VCVTMS 1111 1111 1 . 11 .. 11 ... 000 11 0 1 . 0 ... 0 @1op VCVTMU 1111 1111 1 . 11 .. 11 ... 000 11 1 1 . 0 ... 0 @1op + +VRINTN 1111 1111 1 . 11 .. 10 ... 001 000 1 . 0 ... 0 @1op +VRINTX 1111 1111 1 . 11 .. 10 ... 001 001 1 . 0 ... 0 @1op +VRINTA 1111 1111 1 . 11 .. 10 ... 001 010 1 . 0 ... 0 @1op +VRINTZ 1111 1111 1 . 11 .. 10 ... 001 011 1 . 0 ... 0 @1op +VRINTM 1111 1111 1 . 11 .. 10 ... 001 101 1 . 0 ... 0 @1op +VRINTP 1111 1111 1 . 11 .. 10 ... 001 111 1 . 0 ... 0 @1op diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VCVT_RMODE(vcvt_rm_uh, 2, uint16_t, helper_vfp_touhh) DO_VCVT_RMODE(vcvt_rm_ss, 4, uint32_t, helper_vfp_tosls) DO_VCVT_RMODE(vcvt_rm_us, 4, uint32_t, helper_vfp_touls) +#define DO_VRINT_RM_H(M, F, S) helper_rinth(M, S) +#define DO_VRINT_RM_S(M, F, S) helper_rints(M, S) + +DO_VCVT_RMODE(vrint_rm_h, 2, uint16_t, DO_VRINT_RM_H) +DO_VCVT_RMODE(vrint_rm_s, 4, uint32_t, DO_VRINT_RM_S) + /* * VCVT between halfprec and singleprec. As usual for halfprec * conversions, FZ16 is ignored and AHP is observed. @@ -XXX,XX +XXX,XX @@ void HELPER(mve_vcvtt_hs)(CPUARMState *env, void *vd, void *vm) { do_vcvt_hs(env, vd, vm, 1); } + +#define DO_1OP_FP(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vm) \ + { \ + TYPE *d = vd, *m = vm; \ + TYPE r; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + float_status *fpst; \ + float_status scratch_fpst; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if ((mask & MAKE_64BIT_MASK(0, ESIZE)) == 0) { \ + continue; \ + } \ + fpst = (ESIZE == 2) ? &env->vfp.standard_fp_status_f16 : \ + &env->vfp.standard_fp_status; \ + if (!(mask & 1)) { \ + /* We need the result but without updating flags */ \ + scratch_fpst = *fpst; \ + fpst = &scratch_fpst; \ + } \ + r = FN(m[H##ESIZE(e)], fpst); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_1OP_FP(vrintx_h, 2, float16, float16_round_to_int) +DO_1OP_FP(vrintx_s, 4, float32, float32_round_to_int) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_VCVT_SH(VCVTT_SH, vcvtt_sh) DO_VCVT_SH(VCVTB_HS, vcvtb_hs) DO_VCVT_SH(VCVTT_HS, vcvtt_hs) +#define DO_VRINT(INSN, RMODE) \ + static void gen_##INSN##h(TCGv_ptr env, TCGv_ptr qd, TCGv_ptr qm) \ + { \ + gen_helper_mve_vrint_rm_h(env, qd, qm, \ + tcg_constant_i32(arm_rmode_to_sf(RMODE))); \ + } \ + static void gen_##INSN##s(TCGv_ptr env, TCGv_ptr qd, TCGv_ptr qm) \ + { \ + gen_helper_mve_vrint_rm_s(env, qd, qm, \ + tcg_constant_i32(arm_rmode_to_sf(RMODE))); \ + } \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + static MVEGenOneOpFn * const fns[] = { \ + NULL, \ + gen_##INSN##h, \ + gen_##INSN##s, \ + NULL, \ + }; \ + if (!dc_isar_feature(aa32_mve_fp, s)) { \ + return false; \ + } \ + return do_1op(s, a, fns[a->size]); \ + } + +DO_VRINT(VRINTN, FPROUNDING_TIEEVEN) +DO_VRINT(VRINTA, FPROUNDING_TIEAWAY) +DO_VRINT(VRINTZ, FPROUNDING_ZERO) +DO_VRINT(VRINTM, FPROUNDING_NEGINF) +DO_VRINT(VRINTP, FPROUNDING_POSINF) + +static bool trans_VRINTX(DisasContext *s, arg_1op *a) +{ + static MVEGenOneOpFn * const fns[] = { + NULL, + gen_helper_mve_vrintx_h, + gen_helper_mve_vrintx_s, + NULL, + }; + if (!dc_isar_feature(aa32_mve_fp, s)) { + return false; + } + return do_1op(s, a, fns[a->size]); +} + /* Narrowing moves: only size 0 and 1 are valid */ #define DO_VMOVN(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_1op *a) \ -- 2.20.1 We now have a complete MVE emulation, so we can enable it in our Cortex-M55 model by setting the ID registers to match those of a Cortex-M55 with full MVE support. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/cpu_tcg.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ static void cortex_m55_initfn(Object *obj) cpu->revidr = 0; cpu->pmsav7_dregion = 16; cpu->sau_sregion = 8; - /* - * These are the MVFR* values for the FPU, no MVE configuration; - * we will update them later when we implement MVE - */ + /* These are the MVFR* values for the FPU + full MVE configuration */ cpu->isar.mvfr0 = 0x10110221; - cpu->isar.mvfr1 = 0x12100011; + cpu->isar.mvfr1 = 0x12100211; cpu->isar.mvfr2 = 0x00000040; cpu->isar.id_pfr0 = 0x20000030; cpu->isar.id_pfr1 = 0x00000230; -- 2.20.1 From: Shuuichirou Ishii <ishii.shuuichir@fujitsu.com> Add a definition for the Fujitsu A64FX processor. The A64FX processor does not implement the AArch32 Execution state, so there are no associated AArch32 Identification registers. For SVE, the A64FX processor supports only 128,256 and 512bit vector lengths. The Identification register values are defined based on the FX700, and have been tested and confirmed. Signed-off-by: Shuuichirou Ishii <ishii.shuuichir@fujitsu.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 48 insertions(+) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) cpu_max_set_sve_max_vq, NULL, NULL); } +static void aarch64_a64fx_initfn(Object *obj) +{ + ARMCPU *cpu = ARM_CPU(obj); + + cpu->dtb_compatible = "arm,a64fx"; + set_feature(&cpu->env, ARM_FEATURE_V8); + set_feature(&cpu->env, ARM_FEATURE_NEON); + set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); + set_feature(&cpu->env, ARM_FEATURE_AARCH64); + set_feature(&cpu->env, ARM_FEATURE_EL2); + set_feature(&cpu->env, ARM_FEATURE_EL3); + set_feature(&cpu->env, ARM_FEATURE_PMU); + cpu->midr = 0x461f0010; + cpu->revidr = 0x00000000; + cpu->ctr = 0x86668006; + cpu->reset_sctlr = 0x30000180; + cpu->isar.id_aa64pfr0 = 0x0000000101111111; /* No RAS Extensions */ + cpu->isar.id_aa64pfr1 = 0x0000000000000000; + cpu->isar.id_aa64dfr0 = 0x0000000010305408; + cpu->isar.id_aa64dfr1 = 0x0000000000000000; + cpu->id_aa64afr0 = 0x0000000000000000; + cpu->id_aa64afr1 = 0x0000000000000000; + cpu->isar.id_aa64mmfr0 = 0x0000000000001122; + cpu->isar.id_aa64mmfr1 = 0x0000000011212100; + cpu->isar.id_aa64mmfr2 = 0x0000000000001011; + cpu->isar.id_aa64isar0 = 0x0000000010211120; + cpu->isar.id_aa64isar1 = 0x0000000000010001; + cpu->isar.id_aa64zfr0 = 0x0000000000000000; + cpu->clidr = 0x0000000080000023; + cpu->ccsidr[0] = 0x7007e01c; /* 64KB L1 dcache */ + cpu->ccsidr[1] = 0x2007e01c; /* 64KB L1 icache */ + cpu->ccsidr[2] = 0x70ffe07c; /* 8MB L2 cache */ + cpu->dcz_blocksize = 6; /* 256 bytes */ + cpu->gic_num_lrs = 4; + cpu->gic_vpribits = 5; + cpu->gic_vprebits = 5; + + /* Suppport of A64FX's vector length are 128,256 and 512bit only */ + aarch64_add_sve_properties(obj); + bitmap_zero(cpu->sve_vq_supported, ARM_MAX_VQ); + set_bit(0, cpu->sve_vq_supported); /* 128bit */ + set_bit(1, cpu->sve_vq_supported); /* 256bit */ + set_bit(3, cpu->sve_vq_supported); /* 512bit */ + + /* TODO: Add A64FX specific HPC extension registers */ +} + static const ARMCPUInfo aarch64_cpus[] = { { .name = "cortex-a57", .initfn = aarch64_a57_initfn }, { .name = "cortex-a53", .initfn = aarch64_a53_initfn }, { .name = "cortex-a72", .initfn = aarch64_a72_initfn }, + { .name = "a64fx", .initfn = aarch64_a64fx_initfn }, { .name = "max", .initfn = aarch64_max_initfn }, }; -- 2.20.1 From: Shuuichirou Ishii <ishii.shuuichir@fujitsu.com> Add -cpu a64fx to use A64FX processor when -machine virt option is specified. In addition, add a64fx to the Supported guest CPU types in the virt.rst document. Signed-off-by: Shuuichirou Ishii <ishii.shuuichir@fujitsu.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/virt.rst | 1 + hw/arm/virt.c | 1 + 2 files changed, 2 insertions(+) diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/virt.rst +++ b/docs/system/arm/virt.rst @@ -XXX,XX +XXX,XX @@ Supported guest CPU types: - ``cortex-a53`` (64-bit) - ``cortex-a57`` (64-bit) - ``cortex-a72`` (64-bit) +- ``a64fx`` (64-bit) - ``host`` (with KVM only) - ``max`` (same as ``host`` for KVM; best possible emulation with TCG) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static const char *valid_cpus[] = { ARM_CPU_TYPE_NAME("cortex-a53"), ARM_CPU_TYPE_NAME("cortex-a57"), ARM_CPU_TYPE_NAME("cortex-a72"), + ARM_CPU_TYPE_NAME("a64fx"), ARM_CPU_TYPE_NAME("host"), ARM_CPU_TYPE_NAME("max"), }; -- 2.20.1 From: Shuuichirou Ishii <ishii.shuuichir@fujitsu.com> Add tests that the A64FX CPU model exposes the expected features. Signed-off-by: Shuuichirou Ishii <ishii.shuuichir@fujitsu.com> Reviewed-by: Andrew Jones <drjones@redhat.com> [PMM: added commit message body] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/arm-cpu-features.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/tests/qtest/arm-cpu-features.c b/tests/qtest/arm-cpu-features.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/arm-cpu-features.c +++ b/tests/qtest/arm-cpu-features.c @@ -XXX,XX +XXX,XX @@ static void test_query_cpu_model_expansion(const void *data) assert_has_feature_enabled(qts, "cortex-a57", "pmu"); assert_has_feature_enabled(qts, "cortex-a57", "aarch64"); + assert_has_feature_enabled(qts, "a64fx", "pmu"); + assert_has_feature_enabled(qts, "a64fx", "aarch64"); + /* + * A64FX does not support any other vector lengths besides those + * that are enabled by default(128bit, 256bits, 512bit). + */ + assert_has_feature_enabled(qts, "a64fx", "sve"); + assert_sve_vls(qts, "a64fx", 0xb, NULL); + assert_error(qts, "a64fx", "cannot enable sve384", + "{ 'sve384': true }"); + assert_error(qts, "a64fx", "cannot enable sve640", + "{ 'sve640': true }"); + sve_tests_default(qts, "max"); pauth_tests_default(qts, "max"); -- 2.20.1 Currently we implement the RAS register block within the NVIC device. It isn't really very tightly coupled with the NVIC proper, so instead move it out into a sysbus device of its own and have the top level ARMv7M container create it and map it into memory at the right address. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alexandre Iooss <erdnaxe@crans.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc@lmichel.fr> Reviewed-by: Damien Hedde <damien.hedde@greensocs.com> Message-id: 20210812093356.1946-2-peter.maydell@linaro.org --- include/hw/arm/armv7m.h | 2 + include/hw/intc/armv7m_nvic.h | 1 - include/hw/misc/armv7m_ras.h | 37 ++++++++++++++ hw/arm/armv7m.c | 12 +++++ hw/intc/armv7m_nvic.c | 56 --------------------- hw/misc/armv7m_ras.c | 93 +++++++++++++++++++++++++++++++++++ MAINTAINERS | 2 + hw/misc/meson.build | 2 + 8 files changed, 148 insertions(+), 57 deletions(-) create mode 100644 include/hw/misc/armv7m_ras.h create mode 100644 hw/misc/armv7m_ras.c diff --git a/include/hw/arm/armv7m.h b/include/hw/arm/armv7m.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/armv7m.h +++ b/include/hw/arm/armv7m.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/intc/armv7m_nvic.h" +#include "hw/misc/armv7m_ras.h" #include "target/arm/idau.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct ARMv7MState { NVICState nvic; BitBandState bitband[ARMV7M_NUM_BITBANDS]; ARMCPU *cpu; + ARMv7MRAS ras; /* MemoryRegion we pass to the CPU, with our devices layered on * top of the ones the board provides in board_memory. diff --git a/include/hw/intc/armv7m_nvic.h b/include/hw/intc/armv7m_nvic.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/armv7m_nvic.h +++ b/include/hw/intc/armv7m_nvic.h @@ -XXX,XX +XXX,XX @@ struct NVICState { MemoryRegion sysreg_ns_mem; MemoryRegion systickmem; MemoryRegion systick_ns_mem; - MemoryRegion ras_mem; MemoryRegion container; MemoryRegion defaultmem; diff --git a/include/hw/misc/armv7m_ras.h b/include/hw/misc/armv7m_ras.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/armv7m_ras.h @@ -XXX,XX +XXX,XX @@ +/* + * Arm M-profile RAS (Reliability, Availability and Serviceability) block + * + * Copyright (c) 2021 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 or + * (at your option) any later version. + */ + +/* + * This is a model of the RAS register block of an M-profile CPU + * (the registers starting at 0xE0005000 with ERRFRn). + * + * QEMU interface: + * + sysbus MMIO region 0: the register bank + * + * The QEMU implementation currently provides "minimal RAS" only. + */ + +#ifndef HW_MISC_ARMV7M_RAS_H +#define HW_MISC_ARMV7M_RAS_H + +#include "hw/sysbus.h" + +#define TYPE_ARMV7M_RAS "armv7m-ras" +OBJECT_DECLARE_SIMPLE_TYPE(ARMv7MRAS, ARMV7M_RAS) + +struct ARMv7MRAS { + /*< private >*/ + SysBusDevice parent_obj; + + /*< public >*/ + MemoryRegion iomem; +}; + +#endif diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) memory_region_add_subregion(&s->container, 0xe0000000, sysbus_mmio_get_region(sbd, 0)); + /* If the CPU has RAS support, create the RAS register block */ + if (cpu_isar_feature(aa32_ras, s->cpu)) { + object_initialize_child(OBJECT(dev), "armv7m-ras", + &s->ras, TYPE_ARMV7M_RAS); + sbd = SYS_BUS_DEVICE(&s->ras); + if (!sysbus_realize(sbd, errp)) { + return; + } + memory_region_add_subregion_overlap(&s->container, 0xe0005000, + sysbus_mmio_get_region(sbd, 0), 1); + } + for (i = 0; i < ARRAY_SIZE(s->bitband); i++) { if (s->enable_bitband) { Object *obj = OBJECT(&s->bitband[i]); diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps nvic_systick_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; - -static MemTxResult ras_read(void *opaque, hwaddr addr, - uint64_t *data, unsigned size, - MemTxAttrs attrs) -{ - if (attrs.user) { - return MEMTX_ERROR; - } - - switch (addr) { - case 0xe10: /* ERRIIDR */ - /* architect field = Arm; product/variant/revision 0 */ - *data = 0x43b; - break; - case 0xfc8: /* ERRDEVID */ - /* Minimal RAS: we implement 0 error record indexes */ - *data = 0; - break; - default: - qemu_log_mask(LOG_UNIMP, "Read RAS register offset 0x%x\n", - (uint32_t)addr); - *data = 0; - break; - } - return MEMTX_OK; -} - -static MemTxResult ras_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size, - MemTxAttrs attrs) -{ - if (attrs.user) { - return MEMTX_ERROR; - } - - switch (addr) { - default: - qemu_log_mask(LOG_UNIMP, "Write to RAS register offset 0x%x\n", - (uint32_t)addr); - break; - } - return MEMTX_OK; -} - -static const MemoryRegionOps ras_ops = { - .read_with_attrs = ras_read, - .write_with_attrs = ras_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - /* * Unassigned portions of the PPB space are RAZ/WI for privileged * accesses, and fault for non-privileged accesses. @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) &s->systick_ns_mem, 1); } - if (cpu_isar_feature(aa32_ras, s->cpu)) { - memory_region_init_io(&s->ras_mem, OBJECT(s), - &ras_ops, s, "nvic_ras", 0x1000); - memory_region_add_subregion(&s->container, 0x5000, &s->ras_mem); - } - sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->container); } diff --git a/hw/misc/armv7m_ras.c b/hw/misc/armv7m_ras.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/armv7m_ras.c @@ -XXX,XX +XXX,XX @@ +/* + * Arm M-profile RAS (Reliability, Availability and Serviceability) block + * + * Copyright (c) 2021 Linaro Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 or + * (at your option) any later version. + */ + +#include "qemu/osdep.h" +#include "hw/misc/armv7m_ras.h" +#include "qemu/log.h" + +static MemTxResult ras_read(void *opaque, hwaddr addr, + uint64_t *data, unsigned size, + MemTxAttrs attrs) +{ + if (attrs.user) { + return MEMTX_ERROR; + } + + switch (addr) { + case 0xe10: /* ERRIIDR */ + /* architect field = Arm; product/variant/revision 0 */ + *data = 0x43b; + break; + case 0xfc8: /* ERRDEVID */ + /* Minimal RAS: we implement 0 error record indexes */ + *data = 0; + break; + default: + qemu_log_mask(LOG_UNIMP, "Read RAS register offset 0x%x\n", + (uint32_t)addr); + *data = 0; + break; + } + return MEMTX_OK; +} + +static MemTxResult ras_write(void *opaque, hwaddr addr, + uint64_t value, unsigned size, + MemTxAttrs attrs) +{ + if (attrs.user) { + return MEMTX_ERROR; + } + + switch (addr) { + default: + qemu_log_mask(LOG_UNIMP, "Write to RAS register offset 0x%x\n", + (uint32_t)addr); + break; + } + return MEMTX_OK; +} + +static const MemoryRegionOps ras_ops = { + .read_with_attrs = ras_read, + .write_with_attrs = ras_write, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + + +static void armv7m_ras_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + ARMv7MRAS *s = ARMV7M_RAS(obj); + + memory_region_init_io(&s->iomem, obj, &ras_ops, + s, "armv7m-ras", 0x1000); + sysbus_init_mmio(sbd, &s->iomem); +} + +static void armv7m_ras_class_init(ObjectClass *klass, void *data) +{ + /* This device has no state: no need for vmstate or reset */ +} + +static const TypeInfo armv7m_ras_info = { + .name = TYPE_ARMV7M_RAS, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(ARMv7MRAS), + .instance_init = armv7m_ras_init, + .class_init = armv7m_ras_class_init, +}; + +static void armv7m_ras_register_types(void) +{ + type_register_static(&armv7m_ras_info); +} + +type_init(armv7m_ras_register_types); diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/intc/gic_internal.h F: hw/misc/a9scu.c F: hw/misc/arm11scu.c F: hw/misc/arm_l2x0.c +F: hw/misc/armv7m_ras.c F: hw/timer/a9gtimer* F: hw/timer/arm* F: include/hw/arm/arm*.h @@ -XXX,XX +XXX,XX @@ F: include/hw/misc/arm11scu.h F: include/hw/timer/a9gtimer.h F: include/hw/timer/arm_mptimer.h F: include/hw/timer/armv7m_systick.h +F: include/hw/misc/armv7m_ras.h F: tests/qtest/test-arm-mptimer.c Exynos diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_INTEGRATOR_DEBUG', if_true: files('arm_integrator_d softmmu_ss.add(when: 'CONFIG_A9SCU', if_true: files('a9scu.c')) softmmu_ss.add(when: 'CONFIG_ARM11SCU', if_true: files('arm11scu.c')) +softmmu_ss.add(when: 'CONFIG_ARM_V7M', if_true: files('armv7m_ras.c')) + # Mac devices softmmu_ss.add(when: 'CONFIG_MOS6522', if_true: files('mos6522.c')) -- 2.20.1 There's no particular reason why the NVIC should be owning the SysTick device objects; move them into the ARMv7M container object instead, as part of consolidating the "create the devices which are built into an M-profile CPU and map them into their architected locations in the address space" work into one place. This involves temporarily creating a duplicate copy of the nvic_sysreg_ns_ops struct and its read/write functions (renamed as v7m_sysreg_ns_*), but we will delete the NVIC's copy of this code in a subsequent patch. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc@lmichel.fr> Message-id: 20210812093356.1946-3-peter.maydell@linaro.org --- include/hw/arm/armv7m.h | 12 ++++ include/hw/intc/armv7m_nvic.h | 4 -- hw/arm/armv7m.c | 125 ++++++++++++++++++++++++++++++++++ hw/intc/armv7m_nvic.c | 73 -------------------- 4 files changed, 137 insertions(+), 77 deletions(-) diff --git a/include/hw/arm/armv7m.h b/include/hw/arm/armv7m.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/armv7m.h +++ b/include/hw/arm/armv7m.h @@ -XXX,XX +XXX,XX @@ struct ARMv7MState { BitBandState bitband[ARMV7M_NUM_BITBANDS]; ARMCPU *cpu; ARMv7MRAS ras; + SysTickState systick[M_REG_NUM_BANKS]; /* MemoryRegion we pass to the CPU, with our devices layered on * top of the ones the board provides in board_memory. */ MemoryRegion container; + /* + * MemoryRegion which passes the transaction to either the S or the + * NS systick device depending on the transaction attributes + */ + MemoryRegion systickmem; + /* + * MemoryRegion which enforces the S/NS handling of the systick + * device NS alias region and passes the transaction to the + * NS systick device if appropriate. + */ + MemoryRegion systick_ns_mem; /* Properties */ char *cpu_type; diff --git a/include/hw/intc/armv7m_nvic.h b/include/hw/intc/armv7m_nvic.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/armv7m_nvic.h +++ b/include/hw/intc/armv7m_nvic.h @@ -XXX,XX +XXX,XX @@ struct NVICState { MemoryRegion sysregmem; MemoryRegion sysreg_ns_mem; - MemoryRegion systickmem; - MemoryRegion systick_ns_mem; MemoryRegion container; MemoryRegion defaultmem; uint32_t num_irq; qemu_irq excpout; qemu_irq sysresetreq; - - SysTickState systick[M_REG_NUM_BANKS]; }; #endif diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ static const hwaddr bitband_output_addr[ARMV7M_NUM_BITBANDS] = { 0x22000000, 0x42000000 }; +static MemTxResult v7m_sysreg_ns_write(void *opaque, hwaddr addr, + uint64_t value, unsigned size, + MemTxAttrs attrs) +{ + MemoryRegion *mr = opaque; + + if (attrs.secure) { + /* S accesses to the alias act like NS accesses to the real region */ + attrs.secure = 0; + return memory_region_dispatch_write(mr, addr, value, + size_memop(size) | MO_TE, attrs); + } else { + /* NS attrs are RAZ/WI for privileged, and BusFault for user */ + if (attrs.user) { + return MEMTX_ERROR; + } + return MEMTX_OK; + } +} + +static MemTxResult v7m_sysreg_ns_read(void *opaque, hwaddr addr, + uint64_t *data, unsigned size, + MemTxAttrs attrs) +{ + MemoryRegion *mr = opaque; + + if (attrs.secure) { + /* S accesses to the alias act like NS accesses to the real region */ + attrs.secure = 0; + return memory_region_dispatch_read(mr, addr, data, + size_memop(size) | MO_TE, attrs); + } else { + /* NS attrs are RAZ/WI for privileged, and BusFault for user */ + if (attrs.user) { + return MEMTX_ERROR; + } + *data = 0; + return MEMTX_OK; + } +} + +static const MemoryRegionOps v7m_sysreg_ns_ops = { + .read_with_attrs = v7m_sysreg_ns_read, + .write_with_attrs = v7m_sysreg_ns_write, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static MemTxResult v7m_systick_write(void *opaque, hwaddr addr, + uint64_t value, unsigned size, + MemTxAttrs attrs) +{ + ARMv7MState *s = opaque; + MemoryRegion *mr; + + /* Direct the access to the correct systick */ + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->systick[attrs.secure]), 0); + return memory_region_dispatch_write(mr, addr, value, + size_memop(size) | MO_TE, attrs); +} + +static MemTxResult v7m_systick_read(void *opaque, hwaddr addr, + uint64_t *data, unsigned size, + MemTxAttrs attrs) +{ + ARMv7MState *s = opaque; + MemoryRegion *mr; + + /* Direct the access to the correct systick */ + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->systick[attrs.secure]), 0); + return memory_region_dispatch_read(mr, addr, data, size_memop(size) | MO_TE, + attrs); +} + +static const MemoryRegionOps v7m_systick_ops = { + .read_with_attrs = v7m_systick_read, + .write_with_attrs = v7m_systick_write, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + static void armv7m_instance_init(Object *obj) { ARMv7MState *s = ARMV7M(obj); @@ -XXX,XX +XXX,XX @@ static void armv7m_instance_init(Object *obj) object_property_add_alias(obj, "num-irq", OBJECT(&s->nvic), "num-irq"); + object_initialize_child(obj, "systick-reg-ns", &s->systick[M_REG_NS], + TYPE_SYSTICK); + /* + * We can't initialize the secure systick here, as we don't know + * yet if we need it. + */ + for (i = 0; i < ARRAY_SIZE(s->bitband); i++) { object_initialize_child(obj, "bitband[*]", &s->bitband[i], TYPE_BITBAND); @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) memory_region_add_subregion(&s->container, 0xe0000000, sysbus_mmio_get_region(sbd, 0)); + /* Create and map the systick devices */ + if (!sysbus_realize(SYS_BUS_DEVICE(&s->systick[M_REG_NS]), errp)) { + return; + } + sysbus_connect_irq(SYS_BUS_DEVICE(&s->systick[M_REG_NS]), 0, + qdev_get_gpio_in_named(DEVICE(&s->nvic), + "systick-trigger", M_REG_NS)); + + if (arm_feature(&s->cpu->env, ARM_FEATURE_M_SECURITY)) { + /* + * We couldn't init the secure systick device in instance_init + * as we didn't know then if the CPU had the security extensions; + * so we have to do it here. + */ + object_initialize_child(OBJECT(dev), "systick-reg-s", + &s->systick[M_REG_S], TYPE_SYSTICK); + + if (!sysbus_realize(SYS_BUS_DEVICE(&s->systick[M_REG_S]), errp)) { + return; + } + sysbus_connect_irq(SYS_BUS_DEVICE(&s->systick[M_REG_S]), 0, + qdev_get_gpio_in_named(DEVICE(&s->nvic), + "systick-trigger", M_REG_S)); + } + + memory_region_init_io(&s->systickmem, OBJECT(s), + &v7m_systick_ops, s, + "v7m_systick", 0xe0); + + memory_region_add_subregion_overlap(&s->container, 0xe000e010, + &s->systickmem, 1); + if (arm_feature(&s->cpu->env, ARM_FEATURE_V8)) { + memory_region_init_io(&s->systick_ns_mem, OBJECT(s), + &v7m_sysreg_ns_ops, &s->systickmem, + "v7m_systick_ns", 0xe0); + memory_region_add_subregion_overlap(&s->container, 0xe002e010, + &s->systick_ns_mem, 1); + } + /* If the CPU has RAS support, create the RAS register block */ if (cpu_isar_feature(aa32_ras, s->cpu)) { object_initialize_child(OBJECT(dev), "armv7m-ras", diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps nvic_sysreg_ns_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -static MemTxResult nvic_systick_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size, - MemTxAttrs attrs) -{ - NVICState *s = opaque; - MemoryRegion *mr; - - /* Direct the access to the correct systick */ - mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->systick[attrs.secure]), 0); - return memory_region_dispatch_write(mr, addr, value, - size_memop(size) | MO_TE, attrs); -} - -static MemTxResult nvic_systick_read(void *opaque, hwaddr addr, - uint64_t *data, unsigned size, - MemTxAttrs attrs) -{ - NVICState *s = opaque; - MemoryRegion *mr; - - /* Direct the access to the correct systick */ - mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->systick[attrs.secure]), 0); - return memory_region_dispatch_read(mr, addr, data, size_memop(size) | MO_TE, - attrs); -} - -static const MemoryRegionOps nvic_systick_ops = { - .read_with_attrs = nvic_systick_read, - .write_with_attrs = nvic_systick_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - /* * Unassigned portions of the PPB space are RAZ/WI for privileged * accesses, and fault for non-privileged accesses. @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) s->num_prio_bits = arm_feature(&s->cpu->env, ARM_FEATURE_V7) ? 8 : 2; - if (!sysbus_realize(SYS_BUS_DEVICE(&s->systick[M_REG_NS]), errp)) { - return; - } - sysbus_connect_irq(SYS_BUS_DEVICE(&s->systick[M_REG_NS]), 0, - qdev_get_gpio_in_named(dev, "systick-trigger", - M_REG_NS)); - - if (arm_feature(&s->cpu->env, ARM_FEATURE_M_SECURITY)) { - /* We couldn't init the secure systick device in instance_init - * as we didn't know then if the CPU had the security extensions; - * so we have to do it here. - */ - object_initialize_child(OBJECT(dev), "systick-reg-s", - &s->systick[M_REG_S], TYPE_SYSTICK); - - if (!sysbus_realize(SYS_BUS_DEVICE(&s->systick[M_REG_S]), errp)) { - return; - } - sysbus_connect_irq(SYS_BUS_DEVICE(&s->systick[M_REG_S]), 0, - qdev_get_gpio_in_named(dev, "systick-trigger", - M_REG_S)); - } - /* * This device provides a single sysbus memory region which * represents the whole of the "System PPB" space. This is the @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) "nvic_sysregs", 0x1000); memory_region_add_subregion(&s->container, 0xe000, &s->sysregmem); - memory_region_init_io(&s->systickmem, OBJECT(s), - &nvic_systick_ops, s, - "nvic_systick", 0xe0); - - memory_region_add_subregion_overlap(&s->container, 0xe010, - &s->systickmem, 1); - if (arm_feature(&s->cpu->env, ARM_FEATURE_V8)) { memory_region_init_io(&s->sysreg_ns_mem, OBJECT(s), &nvic_sysreg_ns_ops, &s->sysregmem, "nvic_sysregs_ns", 0x1000); memory_region_add_subregion(&s->container, 0x2e000, &s->sysreg_ns_mem); - memory_region_init_io(&s->systick_ns_mem, OBJECT(s), - &nvic_sysreg_ns_ops, &s->systickmem, - "nvic_systick_ns", 0xe0); - memory_region_add_subregion_overlap(&s->container, 0x2e010, - &s->systick_ns_mem, 1); } sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->container); @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_instance_init(Object *obj) NVICState *nvic = NVIC(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - object_initialize_child(obj, "systick-reg-ns", &nvic->systick[M_REG_NS], - TYPE_SYSTICK); - /* We can't initialize the secure systick here, as we don't know - * yet if we need it. - */ - sysbus_init_irq(sbd, &nvic->excpout); qdev_init_gpio_out_named(dev, &nvic->sysresetreq, "SYSRESETREQ", 1); qdev_init_gpio_in_named(dev, nvic_systick_trigger, "systick-trigger", -- 2.20.1 Instead of having the NVIC device provide a single sysbus memory region covering the whole of the "System PPB" space, which implements the default behaviour for unimplemented ranges and provides the NS alias window to the sysregs as well as the main sysreg MR, move this handling to the container armv7m device. The NVIC now provides a single memory region which just implements the system registers. This consolidates all the handling of "map various devices in the PPB" into the armv7m container where it belongs. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alexandre Iooss <erdnaxe@crans.org> Reviewed-by: Luc Michel <luc@lmichel.fr> Message-id: 20210812093356.1946-4-peter.maydell@linaro.org --- include/hw/arm/armv7m.h | 4 + include/hw/intc/armv7m_nvic.h | 3 - hw/arm/armv7m.c | 100 ++++++++++++++++++++++- hw/intc/armv7m_nvic.c | 145 +--------------------------------- 4 files changed, 107 insertions(+), 145 deletions(-) diff --git a/include/hw/arm/armv7m.h b/include/hw/arm/armv7m.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/armv7m.h +++ b/include/hw/arm/armv7m.h @@ -XXX,XX +XXX,XX @@ struct ARMv7MState { * NS systick device if appropriate. */ MemoryRegion systick_ns_mem; + /* Ditto, for the sysregs region provided by the NVIC */ + MemoryRegion sysreg_ns_mem; + /* MR providing default PPB behaviour */ + MemoryRegion defaultmem; /* Properties */ char *cpu_type; diff --git a/include/hw/intc/armv7m_nvic.h b/include/hw/intc/armv7m_nvic.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/armv7m_nvic.h +++ b/include/hw/intc/armv7m_nvic.h @@ -XXX,XX +XXX,XX @@ struct NVICState { int vectpending_prio; /* group prio of the exeception in vectpending */ MemoryRegion sysregmem; - MemoryRegion sysreg_ns_mem; - MemoryRegion container; - MemoryRegion defaultmem; uint32_t num_irq; qemu_irq excpout; diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/reset.h" #include "qemu/error-report.h" #include "qemu/module.h" +#include "qemu/log.h" #include "target/arm/idau.h" /* Bitbanded IO. Each word corresponds to a single bit. */ @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps v7m_systick_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; +/* + * Unassigned portions of the PPB space are RAZ/WI for privileged + * accesses, and fault for non-privileged accesses. + */ +static MemTxResult ppb_default_read(void *opaque, hwaddr addr, + uint64_t *data, unsigned size, + MemTxAttrs attrs) +{ + qemu_log_mask(LOG_UNIMP, "Read of unassigned area of PPB: offset 0x%x\n", + (uint32_t)addr); + if (attrs.user) { + return MEMTX_ERROR; + } + *data = 0; + return MEMTX_OK; +} + +static MemTxResult ppb_default_write(void *opaque, hwaddr addr, + uint64_t value, unsigned size, + MemTxAttrs attrs) +{ + qemu_log_mask(LOG_UNIMP, "Write of unassigned area of PPB: offset 0x%x\n", + (uint32_t)addr); + if (attrs.user) { + return MEMTX_ERROR; + } + return MEMTX_OK; +} + +static const MemoryRegionOps ppb_default_ops = { + .read_with_attrs = ppb_default_read, + .write_with_attrs = ppb_default_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid.min_access_size = 1, + .valid.max_access_size = 8, +}; + static void armv7m_instance_init(Object *obj) { ARMv7MState *s = ARMV7M(obj); @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) qdev_pass_gpios(DEVICE(&s->nvic), dev, "SYSRESETREQ"); qdev_pass_gpios(DEVICE(&s->nvic), dev, "NMI"); + /* + * We map various devices into the container MR at their architected + * addresses. In particular, we map everything corresponding to the + * "System PPB" space. This is the range from 0xe0000000 to 0xe00fffff + * and includes the NVIC, the System Control Space (system registers), + * the systick timer, and for CPUs with the Security extension an NS + * banked version of all of these. + * + * The default behaviour for unimplemented registers/ranges + * (for instance the Data Watchpoint and Trace unit at 0xe0001000) + * is to RAZ/WI for privileged access and BusFault for non-privileged + * access. + * + * The NVIC and System Control Space (SCS) starts at 0xe000e000 + * and looks like this: + * 0x004 - ICTR + * 0x010 - 0xff - systick + * 0x100..0x7ec - NVIC + * 0x7f0..0xcff - Reserved + * 0xd00..0xd3c - SCS registers + * 0xd40..0xeff - Reserved or Not implemented + * 0xf00 - STIR + * + * Some registers within this space are banked between security states. + * In v8M there is a second range 0xe002e000..0xe002efff which is the + * NonSecure alias SCS; secure accesses to this behave like NS accesses + * to the main SCS range, and non-secure accesses (including when + * the security extension is not implemented) are RAZ/WI. + * Note that both the main SCS range and the alias range are defined + * to be exempt from memory attribution (R_BLJT) and so the memory + * transaction attribute always matches the current CPU security + * state (attrs.secure == env->v7m.secure). In the v7m_sysreg_ns_ops + * wrappers we change attrs.secure to indicate the NS access; so + * generally code determining which banked register to use should + * use attrs.secure; code determining actual behaviour of the system + * should use env->v7m.secure. + * + * Within the PPB space, some MRs overlap, and the priority + * of overlapping regions is: + * - default region (for RAZ/WI and BusFault) : -1 + * - system register regions (provided by the NVIC) : 0 + * - systick : 1 + * This is because the systick device is a small block of registers + * in the middle of the other system control registers. + */ + + memory_region_init_io(&s->defaultmem, OBJECT(s), &ppb_default_ops, s, + "nvic-default", 0x100000); + memory_region_add_subregion_overlap(&s->container, 0xe0000000, + &s->defaultmem, -1); + /* Wire the NVIC up to the CPU */ sbd = SYS_BUS_DEVICE(&s->nvic); sysbus_connect_irq(sbd, 0, qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_IRQ)); - memory_region_add_subregion(&s->container, 0xe0000000, + memory_region_add_subregion(&s->container, 0xe000e000, sysbus_mmio_get_region(sbd, 0)); + if (arm_feature(&s->cpu->env, ARM_FEATURE_V8)) { + /* Create the NS alias region for the NVIC sysregs */ + memory_region_init_io(&s->sysreg_ns_mem, OBJECT(s), + &v7m_sysreg_ns_ops, + sysbus_mmio_get_region(sbd, 0), + "nvic_sysregs_ns", 0x1000); + memory_region_add_subregion(&s->container, 0xe002e000, + &s->sysreg_ns_mem); + } /* Create and map the systick devices */ if (!sysbus_realize(SYS_BUS_DEVICE(&s->systick[M_REG_NS]), errp)) { diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps nvic_sysreg_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -static MemTxResult nvic_sysreg_ns_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size, - MemTxAttrs attrs) -{ - MemoryRegion *mr = opaque; - - if (attrs.secure) { - /* S accesses to the alias act like NS accesses to the real region */ - attrs.secure = 0; - return memory_region_dispatch_write(mr, addr, value, - size_memop(size) | MO_TE, attrs); - } else { - /* NS attrs are RAZ/WI for privileged, and BusFault for user */ - if (attrs.user) { - return MEMTX_ERROR; - } - return MEMTX_OK; - } -} - -static MemTxResult nvic_sysreg_ns_read(void *opaque, hwaddr addr, - uint64_t *data, unsigned size, - MemTxAttrs attrs) -{ - MemoryRegion *mr = opaque; - - if (attrs.secure) { - /* S accesses to the alias act like NS accesses to the real region */ - attrs.secure = 0; - return memory_region_dispatch_read(mr, addr, data, - size_memop(size) | MO_TE, attrs); - } else { - /* NS attrs are RAZ/WI for privileged, and BusFault for user */ - if (attrs.user) { - return MEMTX_ERROR; - } - *data = 0; - return MEMTX_OK; - } -} - -static const MemoryRegionOps nvic_sysreg_ns_ops = { - .read_with_attrs = nvic_sysreg_ns_read, - .write_with_attrs = nvic_sysreg_ns_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -/* - * Unassigned portions of the PPB space are RAZ/WI for privileged - * accesses, and fault for non-privileged accesses. - */ -static MemTxResult ppb_default_read(void *opaque, hwaddr addr, - uint64_t *data, unsigned size, - MemTxAttrs attrs) -{ - qemu_log_mask(LOG_UNIMP, "Read of unassigned area of PPB: offset 0x%x\n", - (uint32_t)addr); - if (attrs.user) { - return MEMTX_ERROR; - } - *data = 0; - return MEMTX_OK; -} - -static MemTxResult ppb_default_write(void *opaque, hwaddr addr, - uint64_t value, unsigned size, - MemTxAttrs attrs) -{ - qemu_log_mask(LOG_UNIMP, "Write of unassigned area of PPB: offset 0x%x\n", - (uint32_t)addr); - if (attrs.user) { - return MEMTX_ERROR; - } - return MEMTX_OK; -} - -static const MemoryRegionOps ppb_default_ops = { - .read_with_attrs = ppb_default_read, - .write_with_attrs = ppb_default_write, - .endianness = DEVICE_NATIVE_ENDIAN, - .valid.min_access_size = 1, - .valid.max_access_size = 8, -}; - static int nvic_post_load(void *opaque, int version_id) { NVICState *s = opaque; @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) s->num_prio_bits = arm_feature(&s->cpu->env, ARM_FEATURE_V7) ? 8 : 2; /* - * This device provides a single sysbus memory region which - * represents the whole of the "System PPB" space. This is the - * range from 0xe0000000 to 0xe00fffff and includes the NVIC, - * the System Control Space (system registers), the systick timer, - * and for CPUs with the Security extension an NS banked version - * of all of these. - * - * The default behaviour for unimplemented registers/ranges - * (for instance the Data Watchpoint and Trace unit at 0xe0001000) - * is to RAZ/WI for privileged access and BusFault for non-privileged - * access. - * - * The NVIC and System Control Space (SCS) starts at 0xe000e000 - * and looks like this: - * 0x004 - ICTR - * 0x010 - 0xff - systick - * 0x100..0x7ec - NVIC - * 0x7f0..0xcff - Reserved - * 0xd00..0xd3c - SCS registers - * 0xd40..0xeff - Reserved or Not implemented - * 0xf00 - STIR - * - * Some registers within this space are banked between security states. - * In v8M there is a second range 0xe002e000..0xe002efff which is the - * NonSecure alias SCS; secure accesses to this behave like NS accesses - * to the main SCS range, and non-secure accesses (including when - * the security extension is not implemented) are RAZ/WI. - * Note that both the main SCS range and the alias range are defined - * to be exempt from memory attribution (R_BLJT) and so the memory - * transaction attribute always matches the current CPU security - * state (attrs.secure == env->v7m.secure). In the nvic_sysreg_ns_ops - * wrappers we change attrs.secure to indicate the NS access; so - * generally code determining which banked register to use should - * use attrs.secure; code determining actual behaviour of the system - * should use env->v7m.secure. - * - * The container covers the whole PPB space. Within it the priority - * of overlapping regions is: - * - default region (for RAZ/WI and BusFault) : -1 - * - system register regions : 0 - * - systick : 1 - * This is because the systick device is a small block of registers - * in the middle of the other system control registers. + * This device provides a single memory region which covers the + * sysreg/NVIC registers from 0xE000E000 .. 0xE000EFFF, with the + * exception of the systick timer registers 0xE000E010 .. 0xE000E0FF. */ - memory_region_init(&s->container, OBJECT(s), "nvic", 0x100000); - memory_region_init_io(&s->defaultmem, OBJECT(s), &ppb_default_ops, s, - "nvic-default", 0x100000); - memory_region_add_subregion_overlap(&s->container, 0, &s->defaultmem, -1); memory_region_init_io(&s->sysregmem, OBJECT(s), &nvic_sysreg_ops, s, "nvic_sysregs", 0x1000); - memory_region_add_subregion(&s->container, 0xe000, &s->sysregmem); - - if (arm_feature(&s->cpu->env, ARM_FEATURE_V8)) { - memory_region_init_io(&s->sysreg_ns_mem, OBJECT(s), - &nvic_sysreg_ns_ops, &s->sysregmem, - "nvic_sysregs_ns", 0x1000); - memory_region_add_subregion(&s->container, 0x2e000, &s->sysreg_ns_mem); - } - - sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->container); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->sysregmem); } static void armv7m_nvic_instance_init(Object *obj) -- 2.20.1 Add the usual-style QEMU interface comment documenting what properties, etc, this device exposes. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc@lmichel.fr> Message-id: 20210812093356.1946-5-peter.maydell@linaro.org --- include/hw/timer/armv7m_systick.h | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/include/hw/timer/armv7m_systick.h b/include/hw/timer/armv7m_systick.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/timer/armv7m_systick.h +++ b/include/hw/timer/armv7m_systick.h @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(SysTickState, SYSTICK) +/* + * QEMU interface: + * + sysbus MMIO region 0 is the register interface (covering + * the registers which are mapped at address 0xE000E010) + * + sysbus IRQ 0 is the interrupt line to the NVIC + */ + struct SysTickState { /*< private >*/ SysBusDevice parent_obj; -- 2.20.1 The v7M systick timer can be programmed to run from either of two clocks: * an "external reference clock" (when SYST_CSR.CLKSOURCE == 0) * the main CPU clock (when SYST_CSR.CLKSOURCE == 1) Our implementation currently hardwires the external reference clock to be 1MHz, and allows boards to set the main CPU clock frequency via the global 'system_clock_scale'. (Most boards set that to a constant value; the Stellaris boards allow the guest to reprogram it via the board-specific RCC registers). As the first step in converting this to use the Clock infrastructure, add input clocks to the systick device for the reference clock and the CPU clock. The device implementation ignores them; once we have made all the users of the device correctly wire up the new Clocks we will switch the implementation to use them and ignore the old system_clock_scale. This is a migration compat break for all M-profile boards, because of the addition of the new clock objects to the vmstate struct. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc@lmichel.fr> Message-id: 20210812093356.1946-6-peter.maydell@linaro.org --- include/hw/timer/armv7m_systick.h | 7 +++++++ hw/timer/armv7m_systick.c | 10 ++++++++-- 2 files changed, 15 insertions(+), 2 deletions(-) diff --git a/include/hw/timer/armv7m_systick.h b/include/hw/timer/armv7m_systick.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/timer/armv7m_systick.h +++ b/include/hw/timer/armv7m_systick.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "qom/object.h" #include "hw/ptimer.h" +#include "hw/clock.h" #define TYPE_SYSTICK "armv7m_systick" @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(SysTickState, SYSTICK) * + sysbus MMIO region 0 is the register interface (covering * the registers which are mapped at address 0xE000E010) * + sysbus IRQ 0 is the interrupt line to the NVIC + * + Clock input "refclk" is the external reference clock + * (used when SYST_CSR.CLKSOURCE == 0) + * + Clock input "cpuclk" is the main CPU clock + * (used when SYST_CSR.CLKSOURCE == 1) */ struct SysTickState { @@ -XXX,XX +XXX,XX @@ struct SysTickState { ptimer_state *ptimer; MemoryRegion iomem; qemu_irq irq; + Clock *refclk; + Clock *cpuclk; }; /* diff --git a/hw/timer/armv7m_systick.c b/hw/timer/armv7m_systick.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/armv7m_systick.c +++ b/hw/timer/armv7m_systick.c @@ -XXX,XX +XXX,XX @@ #include "migration/vmstate.h" #include "hw/irq.h" #include "hw/sysbus.h" +#include "hw/qdev-clock.h" #include "qemu/timer.h" #include "qemu/log.h" #include "qemu/module.h" @@ -XXX,XX +XXX,XX @@ static void systick_instance_init(Object *obj) memory_region_init_io(&s->iomem, obj, &systick_ops, s, "systick", 0xe0); sysbus_init_mmio(sbd, &s->iomem); sysbus_init_irq(sbd, &s->irq); + + s->refclk = qdev_init_clock_in(DEVICE(obj), "refclk", NULL, NULL, 0); + s->cpuclk = qdev_init_clock_in(DEVICE(obj), "cpuclk", NULL, NULL, 0); } static void systick_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void systick_realize(DeviceState *dev, Error **errp) static const VMStateDescription vmstate_systick = { .name = "armv7m_systick", - .version_id = 2, - .minimum_version_id = 2, + .version_id = 3, + .minimum_version_id = 3, .fields = (VMStateField[]) { + VMSTATE_CLOCK(refclk, SysTickState), + VMSTATE_CLOCK(cpuclk, SysTickState), VMSTATE_UINT32(control, SysTickState), VMSTATE_INT64(tick, SysTickState), VMSTATE_PTIMER(ptimer, SysTickState), -- 2.20.1 Create input clocks on the armv7m container object which pass through to the systick timers, so that users of the armv7m object can specify the clocks being used. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc@lmichel.fr> Message-id: 20210812093356.1946-7-peter.maydell@linaro.org --- include/hw/arm/armv7m.h | 6 ++++++ hw/arm/armv7m.c | 23 +++++++++++++++++++++++ 2 files changed, 29 insertions(+) diff --git a/include/hw/arm/armv7m.h b/include/hw/arm/armv7m.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/armv7m.h +++ b/include/hw/arm/armv7m.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/armv7m_ras.h" #include "target/arm/idau.h" #include "qom/object.h" +#include "hw/clock.h" #define TYPE_BITBAND "ARM-bitband-memory" OBJECT_DECLARE_SIMPLE_TYPE(BitBandState, BITBAND) @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(ARMv7MState, ARMV7M) * + Property "vfp": enable VFP (forwarded to CPU object) * + Property "dsp": enable DSP (forwarded to CPU object) * + Property "enable-bitband": expose bitbanded IO + * + Clock input "refclk" is the external reference clock for the systick timers + * + Clock input "cpuclk" is the main CPU clock */ struct ARMv7MState { /*< private >*/ @@ -XXX,XX +XXX,XX @@ struct ARMv7MState { /* MR providing default PPB behaviour */ MemoryRegion defaultmem; + Clock *refclk; + Clock *cpuclk; + /* Properties */ char *cpu_type; /* MemoryRegion the board provides to us (with its devices, RAM, etc) */ diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/boot.h" #include "hw/loader.h" #include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" #include "elf.h" #include "sysemu/reset.h" #include "qemu/error-report.h" #include "qemu/module.h" #include "qemu/log.h" #include "target/arm/idau.h" +#include "migration/vmstate.h" /* Bitbanded IO. Each word corresponds to a single bit. */ @@ -XXX,XX +XXX,XX @@ static void armv7m_instance_init(Object *obj) object_initialize_child(obj, "bitband[*]", &s->bitband[i], TYPE_BITBAND); } + + s->refclk = qdev_init_clock_in(DEVICE(obj), "refclk", NULL, NULL, 0); + s->cpuclk = qdev_init_clock_in(DEVICE(obj), "cpuclk", NULL, NULL, 0); } static void armv7m_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) } /* Create and map the systick devices */ + qdev_connect_clock_in(DEVICE(&s->systick[M_REG_NS]), "refclk", s->refclk); + qdev_connect_clock_in(DEVICE(&s->systick[M_REG_NS]), "cpuclk", s->cpuclk); if (!sysbus_realize(SYS_BUS_DEVICE(&s->systick[M_REG_NS]), errp)) { return; } @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) */ object_initialize_child(OBJECT(dev), "systick-reg-s", &s->systick[M_REG_S], TYPE_SYSTICK); + qdev_connect_clock_in(DEVICE(&s->systick[M_REG_S]), "refclk", + s->refclk); + qdev_connect_clock_in(DEVICE(&s->systick[M_REG_S]), "cpuclk", + s->cpuclk); if (!sysbus_realize(SYS_BUS_DEVICE(&s->systick[M_REG_S]), errp)) { return; @@ -XXX,XX +XXX,XX @@ static Property armv7m_properties[] = { DEFINE_PROP_END_OF_LIST(), }; +static const VMStateDescription vmstate_armv7m = { + .name = "armv7m", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_CLOCK(refclk, SysTickState), + VMSTATE_CLOCK(cpuclk, SysTickState), + VMSTATE_END_OF_LIST() + } +}; + static void armv7m_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); dc->realize = armv7m_realize; + dc->vmsd = &vmstate_armv7m; device_class_set_props(dc, armv7m_properties); } -- 2.20.1 Wire up the cpuclk for the systick devices to the SSE object's existing mainclk clock. We do not wire up the refclk because the SSE subsystems do not provide a refclk. (This is documented in the IoTKit and SSE-200 TRMs; the SSE-300 TRM doesn't mention it but we assume it follows the same approach.) When we update the systick device later to honour "no refclk connected" this will fix a minor emulation inaccuracy for the SSE-based boards. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc@lmichel.fr> Message-id: 20210812093356.1946-8-peter.maydell@linaro.org --- hw/arm/armsse.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armsse.c +++ b/hw/arm/armsse.c @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) int j; char *gpioname; + qdev_connect_clock_in(cpudev, "cpuclk", s->mainclk); + /* The SSE subsystems do not wire up a systick refclk */ + qdev_prop_set_uint32(cpudev, "num-irq", s->exp_numirq + NUM_SSE_IRQS); /* * In real hardware the initial Secure VTOR is set from the INITSVTOR* -- 2.20.1 Connect up the armv7m clocks on the mps2-an385/386/500/511. Connect up the armv7m object's clocks on the MPS boards defined in mps2.c. The documentation for these FPGA images doesn't specify what systick reference clock is used (if any), so for the moment we provide a 1MHz refclock, which will result in no behavioural change from the current hardwired 1MHz clock implemented in armv7m_systick.c:systick_scale(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Luc Michel <luc@lmichel.fr> Message-id: 20210812093356.1946-9-peter.maydell@linaro.org --- hw/arm/mps2.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2.c +++ b/hw/arm/mps2.c @@ -XXX,XX +XXX,XX @@ struct MPS2MachineState { CMSDKAPBWatchdog watchdog; CMSDKAPBTimer timer[2]; Clock *sysclk; + Clock *refclk; }; #define TYPE_MPS2_MACHINE "mps2" @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_TYPE(MPS2MachineState, MPS2MachineClass, MPS2_MACHINE) /* Main SYSCLK frequency in Hz */ #define SYSCLK_FRQ 25000000 +/* + * The Application Notes don't say anything about how the + * systick reference clock is configured. (Quite possibly + * they don't have one at all.) This 1MHz clock matches the + * pre-existing behaviour that used to be hardcoded in the + * armv7m_systick implementation. + */ +#define REFCLK_FRQ (1 * 1000 * 1000) + /* Initialize the auxiliary RAM region @mr and map it into * the memory map at @base. */ @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) mms->sysclk = clock_new(OBJECT(machine), "SYSCLK"); clock_set_hz(mms->sysclk, SYSCLK_FRQ); + mms->refclk = clock_new(OBJECT(machine), "REFCLK"); + clock_set_hz(mms->refclk, REFCLK_FRQ); + /* The FPGA images have an odd combination of different RAMs, * because in hardware they are different implementations and * connected to different buses, giving varying performance/size @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) default: g_assert_not_reached(); } + qdev_connect_clock_in(armv7m, "cpuclk", mms->sysclk); + qdev_connect_clock_in(armv7m, "refclk", mms->refclk); qdev_prop_set_string(armv7m, "cpu-type", machine->cpu_type); qdev_prop_set_bit(armv7m, "enable-bitband", true); object_property_set_link(OBJECT(&mms->armv7m), "memory", -- 2.20.1 It is quite common for a clock tree to involve possibly programmable clock multipliers or dividers, where the frequency of a clock is for instance divided by 8 to produce a slower clock to feed to a particular device. Currently we provide no convenient mechanism for modelling this. You can implement it by having an input Clock and an output Clock, and manually setting the period of the output clock in the period-changed callback of the input clock, but that's quite clunky. This patch adds support in the Clock objects themselves for setting a multiplier or divider. The effect of setting this on a clock is that when the clock's period is changed, all the children of the clock are set to period * multiplier / divider, rather than being set to the same period as the parent clock. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alexandre Iooss <erdnaxe@crans.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Luc Michel <luc@lmichel.fr> Reviewed-by: Damien Hedde <damien.hedde@greensocs.com> Message-id: 20210812093356.1946-10-peter.maydell@linaro.org --- docs/devel/clocks.rst | 23 +++++++++++++++++++++++ include/hw/clock.h | 29 +++++++++++++++++++++++++++++ hw/core/clock-vmstate.c | 40 +++++++++++++++++++++++++++++++++++++++- hw/core/clock.c | 31 +++++++++++++++++++++++++++---- hw/core/trace-events | 1 + 5 files changed, 119 insertions(+), 5 deletions(-) diff --git a/docs/devel/clocks.rst b/docs/devel/clocks.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/devel/clocks.rst +++ b/docs/devel/clocks.rst @@ -XXX,XX +XXX,XX @@ clocks get the new clock period value: *Clock 2*, *Clock 3* and *Clock 4*. It is not possible to disconnect a clock or to change the clock connection after it is connected. +Clock multiplier and divider settings +------------------------------------- + +By default, when clocks are connected together, the child +clocks run with the same period as their source (parent) clock. +The Clock API supports a built-in period multiplier/divider +mechanism so you can configure a clock to make its children +run at a different period from its own. If you call the +``clock_set_mul_div()`` function you can specify the clock's +multiplier and divider values. The children of that clock +will all run with a period of ``parent_period * multiplier / divider``. +For instance, if the clock has a frequency of 8MHz and you set its +multiplier to 2 and its divider to 3, the child clocks will run +at 12MHz. + +You can change the multiplier and divider of a clock at runtime, +so you can use this to model clock controller devices which +have guest-programmable frequency multipliers or dividers. + +Note that ``clock_set_mul_div()`` does not automatically call +``clock_propagate()``. If you make a runtime change to the +multiplier or divider you must call clock_propagate() yourself. + Unconnected input clocks ------------------------ diff --git a/include/hw/clock.h b/include/hw/clock.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/clock.h +++ b/include/hw/clock.h @@ -XXX,XX +XXX,XX @@ struct Clock { void *callback_opaque; unsigned int callback_events; + /* Ratio of the parent clock to run the child clocks at */ + uint32_t multiplier; + uint32_t divider; + /* Clocks are organized in a clock tree */ Clock *source; QLIST_HEAD(, Clock) children; @@ -XXX,XX +XXX,XX @@ static inline bool clock_is_enabled(const Clock *clk) */ char *clock_display_freq(Clock *clk); +/** + * clock_set_mul_div: set multiplier/divider for child clocks + * @clk: clock + * @multiplier: multiplier value + * @divider: divider value + * + * By default, a Clock's children will all run with the same period + * as their parent. This function allows you to adjust the multiplier + * and divider used to derive the child clock frequency. + * For example, setting a multiplier of 2 and a divider of 3 + * will run child clocks with a period 2/3 of the parent clock, + * so if the parent clock is an 8MHz clock the children will + * be 12MHz. + * + * Setting the multiplier to 0 will stop the child clocks. + * Setting the divider to 0 is a programming error (diagnosed with + * an assertion failure). + * Setting a multiplier value that results in the child period + * overflowing is not diagnosed. + * + * Note that this function does not call clock_propagate(); the + * caller should do that if necessary. + */ +void clock_set_mul_div(Clock *clk, uint32_t multiplier, uint32_t divider); + #endif /* QEMU_HW_CLOCK_H */ diff --git a/hw/core/clock-vmstate.c b/hw/core/clock-vmstate.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/clock-vmstate.c +++ b/hw/core/clock-vmstate.c @@ -XXX,XX +XXX,XX @@ #include "migration/vmstate.h" #include "hw/clock.h" +static bool muldiv_needed(void *opaque) +{ + Clock *clk = opaque; + + return clk->multiplier != 1 || clk->divider != 1; +} + +static int clock_pre_load(void *opaque) +{ + Clock *clk = opaque; + /* + * The initial out-of-reset settings of the Clock might have been + * configured by the device to be different from what we set + * in clock_initfn(), so we must here set the default values to + * be used if they are not in the inbound migration state. + */ + clk->multiplier = 1; + clk->divider = 1; + + return 0; +} + +const VMStateDescription vmstate_muldiv = { + .name = "clock/muldiv", + .version_id = 1, + .minimum_version_id = 1, + .needed = muldiv_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT32(multiplier, Clock), + VMSTATE_UINT32(divider, Clock), + }, +}; + const VMStateDescription vmstate_clock = { .name = "clock", .version_id = 0, .minimum_version_id = 0, + .pre_load = clock_pre_load, .fields = (VMStateField[]) { VMSTATE_UINT64(period, Clock), VMSTATE_END_OF_LIST() - } + }, + .subsections = (const VMStateDescription*[]) { + &vmstate_muldiv, + NULL + }, }; diff --git a/hw/core/clock.c b/hw/core/clock.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/clock.c +++ b/hw/core/clock.c @@ -XXX,XX +XXX,XX @@ bool clock_set(Clock *clk, uint64_t period) return true; } +static uint64_t clock_get_child_period(Clock *clk) +{ + /* + * Return the period to be used for child clocks, which is the parent + * clock period adjusted for for multiplier and divider effects. + */ + return muldiv64(clk->period, clk->multiplier, clk->divider); +} + static void clock_call_callback(Clock *clk, ClockEvent event) { /* @@ -XXX,XX +XXX,XX @@ static void clock_call_callback(Clock *clk, ClockEvent event) static void clock_propagate_period(Clock *clk, bool call_callbacks) { Clock *child; + uint64_t child_period = clock_get_child_period(clk); QLIST_FOREACH(child, &clk->children, sibling) { - if (child->period != clk->period) { + if (child->period != child_period) { if (call_callbacks) { clock_call_callback(child, ClockPreUpdate); } - child->period = clk->period; + child->period = child_period; trace_clock_update(CLOCK_PATH(child), CLOCK_PATH(clk), - CLOCK_PERIOD_TO_HZ(clk->period), + CLOCK_PERIOD_TO_HZ(child->period), call_callbacks); if (call_callbacks) { clock_call_callback(child, ClockUpdate); @@ -XXX,XX +XXX,XX @@ void clock_set_source(Clock *clk, Clock *src) trace_clock_set_source(CLOCK_PATH(clk), CLOCK_PATH(src)); - clk->period = src->period; + clk->period = clock_get_child_period(src); QLIST_INSERT_HEAD(&src->children, clk, sibling); clk->source = src; clock_propagate_period(clk, false); @@ -XXX,XX +XXX,XX @@ char *clock_display_freq(Clock *clk) return freq_to_str(clock_get_hz(clk)); } +void clock_set_mul_div(Clock *clk, uint32_t multiplier, uint32_t divider) +{ + assert(divider != 0); + + trace_clock_set_mul_div(CLOCK_PATH(clk), clk->multiplier, multiplier, + clk->divider, divider); + clk->multiplier = multiplier; + clk->divider = divider; +} + static void clock_initfn(Object *obj) { Clock *clk = CLOCK(obj); + clk->multiplier = 1; + clk->divider = 1; + QLIST_INIT(&clk->children); } diff --git a/hw/core/trace-events b/hw/core/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/core/trace-events +++ b/hw/core/trace-events @@ -XXX,XX +XXX,XX @@ clock_disconnect(const char *clk) "'%s'" clock_set(const char *clk, uint64_t old, uint64_t new) "'%s', %"PRIu64"Hz->%"PRIu64"Hz" clock_propagate(const char *clk) "'%s'" clock_update(const char *clk, const char *src, uint64_t hz, int cb) "'%s', src='%s', val=%"PRIu64"Hz cb=%d" +clock_set_mul_div(const char *clk, uint32_t oldmul, uint32_t mul, uint32_t olddiv, uint32_t div) "'%s', mul: %u -> %u, div: %u -> %u" -- 2.20.1 In the realize methods of the stm32f100 and stm32f205 SoC objects, we call g_new() to create new MemoryRegion objects for the sram, flash, and flash_alias. This is unnecessary (and leaves open the possibility of leaking the allocations if we exit from realize with an error). Make these MemoryRegions member fields of the device state struct instead, as stm32f405 already does. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alexandre Iooss <erdnaxe@crans.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc@lmichel.fr> Message-id: 20210812093356.1946-11-peter.maydell@linaro.org --- include/hw/arm/stm32f100_soc.h | 4 ++++ include/hw/arm/stm32f205_soc.h | 4 ++++ hw/arm/stm32f100_soc.c | 17 +++++++---------- hw/arm/stm32f205_soc.c | 17 +++++++---------- 4 files changed, 22 insertions(+), 20 deletions(-) diff --git a/include/hw/arm/stm32f100_soc.h b/include/hw/arm/stm32f100_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/stm32f100_soc.h +++ b/include/hw/arm/stm32f100_soc.h @@ -XXX,XX +XXX,XX @@ struct STM32F100State { STM32F2XXUsartState usart[STM_NUM_USARTS]; STM32F2XXSPIState spi[STM_NUM_SPIS]; + + MemoryRegion sram; + MemoryRegion flash; + MemoryRegion flash_alias; }; #endif diff --git a/include/hw/arm/stm32f205_soc.h b/include/hw/arm/stm32f205_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/stm32f205_soc.h +++ b/include/hw/arm/stm32f205_soc.h @@ -XXX,XX +XXX,XX @@ struct STM32F205State { STM32F2XXSPIState spi[STM_NUM_SPIS]; qemu_or_irq *adc_irqs; + + MemoryRegion sram; + MemoryRegion flash; + MemoryRegion flash_alias; }; #endif diff --git a/hw/arm/stm32f100_soc.c b/hw/arm/stm32f100_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32f100_soc.c +++ b/hw/arm/stm32f100_soc.c @@ -XXX,XX +XXX,XX @@ static void stm32f100_soc_realize(DeviceState *dev_soc, Error **errp) int i; MemoryRegion *system_memory = get_system_memory(); - MemoryRegion *sram = g_new(MemoryRegion, 1); - MemoryRegion *flash = g_new(MemoryRegion, 1); - MemoryRegion *flash_alias = g_new(MemoryRegion, 1); /* * Init flash region * Flash starts at 0x08000000 and then is aliased to boot memory at 0x0 */ - memory_region_init_rom(flash, OBJECT(dev_soc), "STM32F100.flash", + memory_region_init_rom(&s->flash, OBJECT(dev_soc), "STM32F100.flash", FLASH_SIZE, &error_fatal); - memory_region_init_alias(flash_alias, OBJECT(dev_soc), - "STM32F100.flash.alias", flash, 0, FLASH_SIZE); - memory_region_add_subregion(system_memory, FLASH_BASE_ADDRESS, flash); - memory_region_add_subregion(system_memory, 0, flash_alias); + memory_region_init_alias(&s->flash_alias, OBJECT(dev_soc), + "STM32F100.flash.alias", &s->flash, 0, FLASH_SIZE); + memory_region_add_subregion(system_memory, FLASH_BASE_ADDRESS, &s->flash); + memory_region_add_subregion(system_memory, 0, &s->flash_alias); /* Init SRAM region */ - memory_region_init_ram(sram, NULL, "STM32F100.sram", SRAM_SIZE, + memory_region_init_ram(&s->sram, NULL, "STM32F100.sram", SRAM_SIZE, &error_fatal); - memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, sram); + memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, &s->sram); /* Init ARMv7m */ armv7m = DEVICE(&s->armv7m); diff --git a/hw/arm/stm32f205_soc.c b/hw/arm/stm32f205_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32f205_soc.c +++ b/hw/arm/stm32f205_soc.c @@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) int i; MemoryRegion *system_memory = get_system_memory(); - MemoryRegion *sram = g_new(MemoryRegion, 1); - MemoryRegion *flash = g_new(MemoryRegion, 1); - MemoryRegion *flash_alias = g_new(MemoryRegion, 1); - memory_region_init_rom(flash, OBJECT(dev_soc), "STM32F205.flash", + memory_region_init_rom(&s->flash, OBJECT(dev_soc), "STM32F205.flash", FLASH_SIZE, &error_fatal); - memory_region_init_alias(flash_alias, OBJECT(dev_soc), - "STM32F205.flash.alias", flash, 0, FLASH_SIZE); + memory_region_init_alias(&s->flash_alias, OBJECT(dev_soc), + "STM32F205.flash.alias", &s->flash, 0, FLASH_SIZE); - memory_region_add_subregion(system_memory, FLASH_BASE_ADDRESS, flash); - memory_region_add_subregion(system_memory, 0, flash_alias); + memory_region_add_subregion(system_memory, FLASH_BASE_ADDRESS, &s->flash); + memory_region_add_subregion(system_memory, 0, &s->flash_alias); - memory_region_init_ram(sram, NULL, "STM32F205.sram", SRAM_SIZE, + memory_region_init_ram(&s->sram, NULL, "STM32F205.sram", SRAM_SIZE, &error_fatal); - memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, sram); + memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, &s->sram); armv7m = DEVICE(&s->armv7m); qdev_prop_set_uint32(armv7m, "num-irq", 96); -- 2.20.1 Wire up the sysclk and refclk for the stm32f100 SoC. This SoC always runs the systick refclk at 1/8 the frequency of the main CPU clock, so the board code only needs to provide a single sysclk clock. Because there is only one board using this SoC, we convert the SoC and the board together, rather than splitting it into "add clock to SoC; connect clock in board; add error check in SoC code that clock is wired up". When the systick device starts honouring its clock inputs, this will fix an emulation inaccuracy in the stm32vldiscovery board where the systick reference clock was running at 1MHz rather than 3MHz. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Alexandre Iooss <erdnaxe@crans.org> Reviewed-by: Luc Michel <luc@lmichel.fr> Message-id: 20210812093356.1946-12-peter.maydell@linaro.org --- include/hw/arm/stm32f100_soc.h | 4 ++++ hw/arm/stm32f100_soc.c | 30 ++++++++++++++++++++++++++++++ hw/arm/stm32vldiscovery.c | 12 +++++++----- 3 files changed, 41 insertions(+), 5 deletions(-) diff --git a/include/hw/arm/stm32f100_soc.h b/include/hw/arm/stm32f100_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/stm32f100_soc.h +++ b/include/hw/arm/stm32f100_soc.h @@ -XXX,XX +XXX,XX @@ #include "hw/ssi/stm32f2xx_spi.h" #include "hw/arm/armv7m.h" #include "qom/object.h" +#include "hw/clock.h" #define TYPE_STM32F100_SOC "stm32f100-soc" OBJECT_DECLARE_SIMPLE_TYPE(STM32F100State, STM32F100_SOC) @@ -XXX,XX +XXX,XX @@ struct STM32F100State { MemoryRegion sram; MemoryRegion flash; MemoryRegion flash_alias; + + Clock *sysclk; + Clock *refclk; }; #endif diff --git a/hw/arm/stm32f100_soc.c b/hw/arm/stm32f100_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32f100_soc.c +++ b/hw/arm/stm32f100_soc.c @@ -XXX,XX +XXX,XX @@ #include "exec/address-spaces.h" #include "hw/arm/stm32f100_soc.h" #include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" #include "hw/misc/unimp.h" #include "sysemu/sysemu.h" @@ -XXX,XX +XXX,XX @@ static void stm32f100_soc_initfn(Object *obj) for (i = 0; i < STM_NUM_SPIS; i++) { object_initialize_child(obj, "spi[*]", &s->spi[i], TYPE_STM32F2XX_SPI); } + + s->sysclk = qdev_init_clock_in(DEVICE(s), "sysclk", NULL, NULL, 0); + s->refclk = qdev_init_clock_in(DEVICE(s), "refclk", NULL, NULL, 0); } static void stm32f100_soc_realize(DeviceState *dev_soc, Error **errp) @@ -XXX,XX +XXX,XX @@ static void stm32f100_soc_realize(DeviceState *dev_soc, Error **errp) MemoryRegion *system_memory = get_system_memory(); + /* + * We use s->refclk internally and only define it with qdev_init_clock_in() + * so it is correctly parented and not leaked on an init/deinit; it is not + * intended as an externally exposed clock. + */ + if (clock_has_source(s->refclk)) { + error_setg(errp, "refclk clock must not be wired up by the board code"); + return; + } + + if (!clock_has_source(s->sysclk)) { + error_setg(errp, "sysclk clock must be wired up by the board code"); + return; + } + + /* + * TODO: ideally we should model the SoC RCC and its ability to + * change the sysclk frequency and define different sysclk sources. + */ + + /* The refclk always runs at frequency HCLK / 8 */ + clock_set_mul_div(s->refclk, 8, 1); + clock_set_source(s->refclk, s->sysclk); + /* * Init flash region * Flash starts at 0x08000000 and then is aliased to boot memory at 0x0 @@ -XXX,XX +XXX,XX @@ static void stm32f100_soc_realize(DeviceState *dev_soc, Error **errp) qdev_prop_set_uint32(armv7m, "num-irq", 61); qdev_prop_set_string(armv7m, "cpu-type", s->cpu_type); qdev_prop_set_bit(armv7m, "enable-bitband", true); + qdev_connect_clock_in(armv7m, "cpuclk", s->sysclk); + qdev_connect_clock_in(armv7m, "refclk", s->refclk); object_property_set_link(OBJECT(&s->armv7m), "memory", OBJECT(get_system_memory()), &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->armv7m), errp)) { diff --git a/hw/arm/stm32vldiscovery.c b/hw/arm/stm32vldiscovery.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32vldiscovery.c +++ b/hw/arm/stm32vldiscovery.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "hw/boards.h" #include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" #include "qemu/error-report.h" #include "hw/arm/stm32f100_soc.h" #include "hw/arm/boot.h" @@ -XXX,XX +XXX,XX @@ static void stm32vldiscovery_init(MachineState *machine) { DeviceState *dev; + Clock *sysclk; - /* - * TODO: ideally we would model the SoC RCC and let it handle - * system_clock_scale, including its ability to define different - * possible SYSCLK sources. - */ system_clock_scale = NANOSECONDS_PER_SECOND / SYSCLK_FRQ; + /* This clock doesn't need migration because it is fixed-frequency */ + sysclk = clock_new(OBJECT(machine), "SYSCLK"); + clock_set_hz(sysclk, SYSCLK_FRQ); + dev = qdev_new(TYPE_STM32F100_SOC); qdev_prop_set_string(dev, "cpu-type", ARM_CPU_TYPE_NAME("cortex-m3")); + qdev_connect_clock_in(dev, "sysclk", sysclk); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); armv7m_load_kernel(ARM_CPU(first_cpu), -- 2.20.1 Wire up the sysclk and refclk for the stm32f205 SoC. This SoC always runs the systick refclk at 1/8 the frequency of the main CPU clock, so the board code only needs to provide a single sysclk clock. Because there is only one board using this SoC, we convert the SoC and the board together, rather than splitting it into "add clock to SoC; connect clock in board; add error check in SoC code that clock is wired up". When the systick device starts honouring its clock inputs, this will fix an emulation inaccuracy in the netduino2 board where the systick reference clock was running at 1MHz rather than 15MHz. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Alexandre Iooss <erdnaxe@crans.org> Reviewed-by: Luc Michel <luc@lmichel.fr> Message-id: 20210812093356.1946-13-peter.maydell@linaro.org --- include/hw/arm/stm32f205_soc.h | 4 ++++ hw/arm/netduino2.c | 12 +++++++----- hw/arm/stm32f205_soc.c | 30 ++++++++++++++++++++++++++++++ 3 files changed, 41 insertions(+), 5 deletions(-) diff --git a/include/hw/arm/stm32f205_soc.h b/include/hw/arm/stm32f205_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/stm32f205_soc.h +++ b/include/hw/arm/stm32f205_soc.h @@ -XXX,XX +XXX,XX @@ #include "hw/or-irq.h" #include "hw/ssi/stm32f2xx_spi.h" #include "hw/arm/armv7m.h" +#include "hw/clock.h" #include "qom/object.h" #define TYPE_STM32F205_SOC "stm32f205-soc" @@ -XXX,XX +XXX,XX @@ struct STM32F205State { MemoryRegion sram; MemoryRegion flash; MemoryRegion flash_alias; + + Clock *sysclk; + Clock *refclk; }; #endif diff --git a/hw/arm/netduino2.c b/hw/arm/netduino2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/netduino2.c +++ b/hw/arm/netduino2.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "hw/boards.h" #include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" #include "qemu/error-report.h" #include "hw/arm/stm32f205_soc.h" #include "hw/arm/boot.h" @@ -XXX,XX +XXX,XX @@ static void netduino2_init(MachineState *machine) { DeviceState *dev; + Clock *sysclk; - /* - * TODO: ideally we would model the SoC RCC and let it handle - * system_clock_scale, including its ability to define different - * possible SYSCLK sources. - */ system_clock_scale = NANOSECONDS_PER_SECOND / SYSCLK_FRQ; + /* This clock doesn't need migration because it is fixed-frequency */ + sysclk = clock_new(OBJECT(machine), "SYSCLK"); + clock_set_hz(sysclk, SYSCLK_FRQ); + dev = qdev_new(TYPE_STM32F205_SOC); qdev_prop_set_string(dev, "cpu-type", ARM_CPU_TYPE_NAME("cortex-m3")); + qdev_connect_clock_in(dev, "sysclk", sysclk); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, diff --git a/hw/arm/stm32f205_soc.c b/hw/arm/stm32f205_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32f205_soc.c +++ b/hw/arm/stm32f205_soc.c @@ -XXX,XX +XXX,XX @@ #include "exec/address-spaces.h" #include "hw/arm/stm32f205_soc.h" #include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" #include "sysemu/sysemu.h" /* At the moment only Timer 2 to 5 are modelled */ @@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_initfn(Object *obj) for (i = 0; i < STM_NUM_SPIS; i++) { object_initialize_child(obj, "spi[*]", &s->spi[i], TYPE_STM32F2XX_SPI); } + + s->sysclk = qdev_init_clock_in(DEVICE(s), "sysclk", NULL, NULL, 0); + s->refclk = qdev_init_clock_in(DEVICE(s), "refclk", NULL, NULL, 0); } static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) @@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) MemoryRegion *system_memory = get_system_memory(); + /* + * We use s->refclk internally and only define it with qdev_init_clock_in() + * so it is correctly parented and not leaked on an init/deinit; it is not + * intended as an externally exposed clock. + */ + if (clock_has_source(s->refclk)) { + error_setg(errp, "refclk clock must not be wired up by the board code"); + return; + } + + if (!clock_has_source(s->sysclk)) { + error_setg(errp, "sysclk clock must be wired up by the board code"); + return; + } + + /* + * TODO: ideally we should model the SoC RCC and its ability to + * change the sysclk frequency and define different sysclk sources. + */ + + /* The refclk always runs at frequency HCLK / 8 */ + clock_set_mul_div(s->refclk, 8, 1); + clock_set_source(s->refclk, s->sysclk); + memory_region_init_rom(&s->flash, OBJECT(dev_soc), "STM32F205.flash", FLASH_SIZE, &error_fatal); memory_region_init_alias(&s->flash_alias, OBJECT(dev_soc), @@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) qdev_prop_set_uint32(armv7m, "num-irq", 96); qdev_prop_set_string(armv7m, "cpu-type", s->cpu_type); qdev_prop_set_bit(armv7m, "enable-bitband", true); + qdev_connect_clock_in(armv7m, "cpuclk", s->sysclk); + qdev_connect_clock_in(armv7m, "refclk", s->refclk); object_property_set_link(OBJECT(&s->armv7m), "memory", OBJECT(get_system_memory()), &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->armv7m), errp)) { -- 2.20.1 Wire up the sysclk and refclk for the stm32f405 SoC. This SoC always runs the systick refclk at 1/8 the frequency of the main CPU clock, so the board code only needs to provide a single sysclk clock. Because there is only one board using this SoC, we convert the SoC and the board together, rather than splitting it into "add clock to SoC; connect clock in board; add error check in SoC code that clock is wired up". When the systick device starts honouring its clock inputs, this will fix an emulation inaccuracy in the netduinoplus2 board where the systick reference clock was running at 1MHz rather than 21MHz. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Alexandre Iooss <erdnaxe@crans.org> Reviewed-by: Luc Michel <luc@lmichel.fr> Message-id: 20210812093356.1946-14-peter.maydell@linaro.org --- include/hw/arm/stm32f405_soc.h | 3 +++ hw/arm/netduinoplus2.c | 12 +++++++----- hw/arm/stm32f405_soc.c | 30 ++++++++++++++++++++++++++++++ 3 files changed, 40 insertions(+), 5 deletions(-) diff --git a/include/hw/arm/stm32f405_soc.h b/include/hw/arm/stm32f405_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/stm32f405_soc.h +++ b/include/hw/arm/stm32f405_soc.h @@ -XXX,XX +XXX,XX @@ struct STM32F405State { MemoryRegion sram; MemoryRegion flash; MemoryRegion flash_alias; + + Clock *sysclk; + Clock *refclk; }; #endif diff --git a/hw/arm/netduinoplus2.c b/hw/arm/netduinoplus2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/netduinoplus2.c +++ b/hw/arm/netduinoplus2.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "hw/boards.h" #include "hw/qdev-properties.h" +#include "hw/qdev-clock.h" #include "qemu/error-report.h" #include "hw/arm/stm32f405_soc.h" #include "hw/arm/boot.h" @@ -XXX,XX +XXX,XX @@ static void netduinoplus2_init(MachineState *machine) { DeviceState *dev; + Clock *sysclk; - /* - * TODO: ideally we would model the SoC RCC and let it handle - * system_clock_scale, including its ability to define different - * possible SYSCLK sources. - */ system_clock_scale = NANOSECONDS_PER_SECOND / SYSCLK_FRQ; + /* This clock doesn't need migration because it is fixed-frequency */ + sysclk = clock_new(OBJECT(machine), "SYSCLK"); + clock_set_hz(sysclk, SYSCLK_FRQ); + dev = qdev_new(TYPE_STM32F405_SOC); qdev_prop_set_string(dev, "cpu-type", ARM_CPU_TYPE_NAME("cortex-m4")); + qdev_connect_clock_in(dev, "sysclk", sysclk); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); armv7m_load_kernel(ARM_CPU(first_cpu), diff --git a/hw/arm/stm32f405_soc.c b/hw/arm/stm32f405_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32f405_soc.c +++ b/hw/arm/stm32f405_soc.c @@ -XXX,XX +XXX,XX @@ #include "exec/address-spaces.h" #include "sysemu/sysemu.h" #include "hw/arm/stm32f405_soc.h" +#include "hw/qdev-clock.h" #include "hw/misc/unimp.h" #define SYSCFG_ADD 0x40013800 @@ -XXX,XX +XXX,XX @@ static void stm32f405_soc_initfn(Object *obj) } object_initialize_child(obj, "exti", &s->exti, TYPE_STM32F4XX_EXTI); + + s->sysclk = qdev_init_clock_in(DEVICE(s), "sysclk", NULL, NULL, 0); + s->refclk = qdev_init_clock_in(DEVICE(s), "refclk", NULL, NULL, 0); } static void stm32f405_soc_realize(DeviceState *dev_soc, Error **errp) @@ -XXX,XX +XXX,XX @@ static void stm32f405_soc_realize(DeviceState *dev_soc, Error **errp) Error *err = NULL; int i; + /* + * We use s->refclk internally and only define it with qdev_init_clock_in() + * so it is correctly parented and not leaked on an init/deinit; it is not + * intended as an externally exposed clock. + */ + if (clock_has_source(s->refclk)) { + error_setg(errp, "refclk clock must not be wired up by the board code"); + return; + } + + if (!clock_has_source(s->sysclk)) { + error_setg(errp, "sysclk clock must be wired up by the board code"); + return; + } + + /* + * TODO: ideally we should model the SoC RCC and its ability to + * change the sysclk frequency and define different sysclk sources. + */ + + /* The refclk always runs at frequency HCLK / 8 */ + clock_set_mul_div(s->refclk, 8, 1); + clock_set_source(s->refclk, s->sysclk); + memory_region_init_rom(&s->flash, OBJECT(dev_soc), "STM32F405.flash", FLASH_SIZE, &err); if (err != NULL) { @@ -XXX,XX +XXX,XX @@ static void stm32f405_soc_realize(DeviceState *dev_soc, Error **errp) qdev_prop_set_uint32(armv7m, "num-irq", 96); qdev_prop_set_string(armv7m, "cpu-type", s->cpu_type); qdev_prop_set_bit(armv7m, "enable-bitband", true); + qdev_connect_clock_in(armv7m, "cpuclk", s->sysclk); + qdev_connect_clock_in(armv7m, "refclk", s->refclk); object_property_set_link(OBJECT(&s->armv7m), "memory", OBJECT(system_memory), &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->armv7m), errp)) { -- 2.20.1 Delete the trailing blank line at the end of the source file. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alexandre Iooss <erdnaxe@crans.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc@lmichel.fr> Message-id: 20210812093356.1946-15-peter.maydell@linaro.org --- hw/arm/stm32vldiscovery.c | 1 - 1 file changed, 1 deletion(-) diff --git a/hw/arm/stm32vldiscovery.c b/hw/arm/stm32vldiscovery.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32vldiscovery.c +++ b/hw/arm/stm32vldiscovery.c @@ -XXX,XX +XXX,XX @@ static void stm32vldiscovery_machine_init(MachineClass *mc) } DEFINE_MACHINE("stm32vldiscovery", stm32vldiscovery_machine_init) - -- 2.20.1 Wire up the sysclk input to the armv7m object. Strictly this SoC should not have a systick device at all, but our armv7m container object doesn't currently support disabling the systick device. For the moment, add a TODO comment, but note that this is why we aren't wiring up a refclk (no need for one). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alexandre Iooss <erdnaxe@crans.org> Message-id: 20210812093356.1946-16-peter.maydell@linaro.org --- include/hw/arm/nrf51_soc.h | 2 ++ hw/arm/nrf51_soc.c | 20 ++++++++++++++++++++ 2 files changed, 22 insertions(+) diff --git a/include/hw/arm/nrf51_soc.h b/include/hw/arm/nrf51_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/nrf51_soc.h +++ b/include/hw/arm/nrf51_soc.h @@ -XXX,XX +XXX,XX @@ #include "hw/gpio/nrf51_gpio.h" #include "hw/nvram/nrf51_nvm.h" #include "hw/timer/nrf51_timer.h" +#include "hw/clock.h" #include "qom/object.h" #define TYPE_NRF51_SOC "nrf51-soc" @@ -XXX,XX +XXX,XX @@ struct NRF51State { MemoryRegion container; + Clock *sysclk; }; #endif diff --git a/hw/arm/nrf51_soc.c b/hw/arm/nrf51_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/nrf51_soc.c +++ b/hw/arm/nrf51_soc.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "hw/arm/boot.h" #include "hw/sysbus.h" +#include "hw/qdev-clock.h" #include "hw/misc/unimp.h" #include "qemu/log.h" @@ -XXX,XX +XXX,XX @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp) return; } + /* + * HCLK on this SoC is fixed, so we set up sysclk ourselves and + * the board shouldn't connect it. + */ + if (clock_has_source(s->sysclk)) { + error_setg(errp, "sysclk clock must not be wired up by the board code"); + return; + } + /* This clock doesn't need migration because it is fixed-frequency */ + clock_set_hz(s->sysclk, HCLK_FRQ); + qdev_connect_clock_in(DEVICE(&s->cpu), "cpuclk", s->sysclk); + /* + * This SoC has no systick device, so don't connect refclk. + * TODO: model the lack of systick (currently the armv7m object + * will always provide one). + */ + system_clock_scale = NANOSECONDS_PER_SECOND / HCLK_FRQ; object_property_set_link(OBJECT(&s->cpu), "memory", OBJECT(&s->container), @@ -XXX,XX +XXX,XX @@ static void nrf51_soc_init(Object *obj) TYPE_NRF51_TIMER); } + + s->sysclk = qdev_init_clock_in(DEVICE(s), "sysclk", NULL, NULL, 0); } static Property nrf51_soc_properties[] = { -- 2.20.1 Currently the stellaris_sys_init() function creates the TYPE_STELLARIS_SYS object, sets its properties, realizes it, maps its MMIO region and connects its IRQ. In order to support wiring the sysclk up to the armv7m object, we need to split this function apart, because to connect the clock output of the STELLARIS_SYS object to the armv7m object we need to create the STELLARIS_SYS object before the armv7m object, but we can't wire up the IRQ until after we've created the armv7m object. Remove the stellaris_sys_init() function, and instead put the create/configure/realize parts before we create the armv7m object and the mmio/irq connection parts afterwards. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alexandre Iooss <erdnaxe@crans.org> Message-id: 20210812093356.1946-17-peter.maydell@linaro.org --- hw/arm/stellaris.c | 56 +++++++++++++++++++++------------------------- 1 file changed, 25 insertions(+), 31 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_sys_instance_init(Object *obj) s->sysclk = qdev_init_clock_out(DEVICE(s), "SYSCLK"); } -static DeviceState *stellaris_sys_init(uint32_t base, qemu_irq irq, - stellaris_board_info *board, - uint8_t *macaddr) -{ - DeviceState *dev = qdev_new(TYPE_STELLARIS_SYS); - SysBusDevice *sbd = SYS_BUS_DEVICE(dev); - - /* Most devices come preprogrammed with a MAC address in the user data. */ - qdev_prop_set_uint32(dev, "user0", - macaddr[0] | (macaddr[1] << 8) | (macaddr[2] << 16)); - qdev_prop_set_uint32(dev, "user1", - macaddr[3] | (macaddr[4] << 8) | (macaddr[5] << 16)); - qdev_prop_set_uint32(dev, "did0", board->did0); - qdev_prop_set_uint32(dev, "did1", board->did1); - qdev_prop_set_uint32(dev, "dc0", board->dc0); - qdev_prop_set_uint32(dev, "dc1", board->dc1); - qdev_prop_set_uint32(dev, "dc2", board->dc2); - qdev_prop_set_uint32(dev, "dc3", board->dc3); - qdev_prop_set_uint32(dev, "dc4", board->dc4); - - sysbus_realize_and_unref(sbd, &error_fatal); - sysbus_mmio_map(sbd, 0, base); - sysbus_connect_irq(sbd, 0, irq); - - return dev; -} - /* I2C controller. */ #define TYPE_STELLARIS_I2C "stellaris-i2c" @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) DeviceState *ssys_dev; int i; int j; + uint8_t *macaddr; MemoryRegion *sram = g_new(MemoryRegion, 1); MemoryRegion *flash = g_new(MemoryRegion, 1); @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) &error_fatal); memory_region_add_subregion(system_memory, 0x20000000, sram); + /* + * Create the system-registers object early, because we will + * need its sysclk output. + */ + ssys_dev = qdev_new(TYPE_STELLARIS_SYS); + /* Most devices come preprogrammed with a MAC address in the user data. */ + macaddr = nd_table[0].macaddr.a; + qdev_prop_set_uint32(ssys_dev, "user0", + macaddr[0] | (macaddr[1] << 8) | (macaddr[2] << 16)); + qdev_prop_set_uint32(ssys_dev, "user1", + macaddr[3] | (macaddr[4] << 8) | (macaddr[5] << 16)); + qdev_prop_set_uint32(ssys_dev, "did0", board->did0); + qdev_prop_set_uint32(ssys_dev, "did1", board->did1); + qdev_prop_set_uint32(ssys_dev, "dc0", board->dc0); + qdev_prop_set_uint32(ssys_dev, "dc1", board->dc1); + qdev_prop_set_uint32(ssys_dev, "dc2", board->dc2); + qdev_prop_set_uint32(ssys_dev, "dc3", board->dc3); + qdev_prop_set_uint32(ssys_dev, "dc4", board->dc4); + sysbus_realize_and_unref(SYS_BUS_DEVICE(ssys_dev), &error_fatal); + nvic = qdev_new(TYPE_ARMV7M); qdev_prop_set_uint32(nvic, "num-irq", NUM_IRQ_LINES); qdev_prop_set_string(nvic, "cpu-type", ms->cpu_type); @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) /* This will exit with an error if the user passed us a bad cpu_type */ sysbus_realize_and_unref(SYS_BUS_DEVICE(nvic), &error_fatal); + /* Now we can wire up the IRQ and MMIO of the system registers */ + sysbus_mmio_map(SYS_BUS_DEVICE(ssys_dev), 0, 0x400fe000); + sysbus_connect_irq(SYS_BUS_DEVICE(ssys_dev), 0, qdev_get_gpio_in(nvic, 28)); + if (board->dc1 & (1 << 16)) { dev = sysbus_create_varargs(TYPE_STELLARIS_ADC, 0x40038000, qdev_get_gpio_in(nvic, 14), @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) } } - ssys_dev = stellaris_sys_init(0x400fe000, qdev_get_gpio_in(nvic, 28), - board, nd_table[0].macaddr.a); - - if (board->dc1 & (1 << 3)) { /* watchdog present */ dev = qdev_new(TYPE_LUMINARY_WATCHDOG); -- 2.20.1 Connect the sysclk to the armv7m object. This board's SoC does not connect up the systick reference clock, so we don't need to connect a refclk. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alexandre Iooss <erdnaxe@crans.org> Message-id: 20210812093356.1946-18-peter.maydell@linaro.org --- hw/arm/stellaris.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) DeviceState *ssys_dev; int i; int j; - uint8_t *macaddr; + const uint8_t *macaddr; MemoryRegion *sram = g_new(MemoryRegion, 1); MemoryRegion *flash = g_new(MemoryRegion, 1); @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) qdev_prop_set_uint32(nvic, "num-irq", NUM_IRQ_LINES); qdev_prop_set_string(nvic, "cpu-type", ms->cpu_type); qdev_prop_set_bit(nvic, "enable-bitband", true); + qdev_connect_clock_in(nvic, "cpuclk", + qdev_get_clock_out(ssys_dev, "SYSCLK")); + /* This SoC does not connect the systick reference clock */ object_property_set_link(OBJECT(nvic), "memory", OBJECT(get_system_memory()), &error_abort); /* This will exit with an error if the user passed us a bad cpu_type */ -- 2.20.1 In the realize method of the msf2-soc SoC object, we call g_new() to create new MemoryRegion objects for the nvm, nvm_alias, and sram. This is unnecessary; make these MemoryRegions member fields of the device state struct instead. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alexandre Iooss <erdnaxe@crans.org> Message-id: 20210812093356.1946-19-peter.maydell@linaro.org --- include/hw/arm/msf2-soc.h | 4 ++++ hw/arm/msf2-soc.c | 17 +++++++---------- 2 files changed, 11 insertions(+), 10 deletions(-) diff --git a/include/hw/arm/msf2-soc.h b/include/hw/arm/msf2-soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/msf2-soc.h +++ b/include/hw/arm/msf2-soc.h @@ -XXX,XX +XXX,XX @@ struct MSF2State { MSSTimerState timer; MSSSpiState spi[MSF2_NUM_SPIS]; MSF2EmacState emac; + + MemoryRegion nvm; + MemoryRegion nvm_alias; + MemoryRegion sram; }; #endif diff --git a/hw/arm/msf2-soc.c b/hw/arm/msf2-soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/msf2-soc.c +++ b/hw/arm/msf2-soc.c @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) int i; MemoryRegion *system_memory = get_system_memory(); - MemoryRegion *nvm = g_new(MemoryRegion, 1); - MemoryRegion *nvm_alias = g_new(MemoryRegion, 1); - MemoryRegion *sram = g_new(MemoryRegion, 1); - memory_region_init_rom(nvm, OBJECT(dev_soc), "MSF2.eNVM", s->envm_size, + memory_region_init_rom(&s->nvm, OBJECT(dev_soc), "MSF2.eNVM", s->envm_size, &error_fatal); /* * On power-on, the eNVM region 0x60000000 is automatically @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) * start address (0x0). We do not support remapping other eNVM, * eSRAM and DDR regions by guest(via Sysreg) currently. */ - memory_region_init_alias(nvm_alias, OBJECT(dev_soc), "MSF2.eNVM", nvm, 0, - s->envm_size); + memory_region_init_alias(&s->nvm_alias, OBJECT(dev_soc), "MSF2.eNVM", + &s->nvm, 0, s->envm_size); - memory_region_add_subregion(system_memory, ENVM_BASE_ADDRESS, nvm); - memory_region_add_subregion(system_memory, 0, nvm_alias); + memory_region_add_subregion(system_memory, ENVM_BASE_ADDRESS, &s->nvm); + memory_region_add_subregion(system_memory, 0, &s->nvm_alias); - memory_region_init_ram(sram, NULL, "MSF2.eSRAM", s->esram_size, + memory_region_init_ram(&s->sram, NULL, "MSF2.eSRAM", s->esram_size, &error_fatal); - memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, sram); + memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, &s->sram); armv7m = DEVICE(&s->armv7m); qdev_prop_set_uint32(armv7m, "num-irq", 81); -- 2.20.1 Instead of passing the MSF2 SoC an integer property specifying the CPU clock rate, pass it a Clock instead. This lets us wire that clock up to the armv7m object. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alexandre Iooss <erdnaxe@crans.org> Message-id: 20210812093356.1946-20-peter.maydell@linaro.org --- include/hw/arm/msf2-soc.h | 3 ++- hw/arm/msf2-soc.c | 28 +++++++++++++++++----------- hw/arm/msf2-som.c | 7 ++++++- 3 files changed, 25 insertions(+), 13 deletions(-) diff --git a/include/hw/arm/msf2-soc.h b/include/hw/arm/msf2-soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/msf2-soc.h +++ b/include/hw/arm/msf2-soc.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/msf2-sysreg.h" #include "hw/ssi/mss-spi.h" #include "hw/net/msf2-emac.h" +#include "hw/clock.h" #include "qom/object.h" #define TYPE_MSF2_SOC "msf2-soc" @@ -XXX,XX +XXX,XX @@ struct MSF2State { uint64_t envm_size; uint64_t esram_size; - uint32_t m3clk; + Clock *m3clk; uint8_t apb0div; uint8_t apb1div; diff --git a/hw/arm/msf2-soc.c b/hw/arm/msf2-soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/msf2-soc.c +++ b/hw/arm/msf2-soc.c @@ -XXX,XX +XXX,XX @@ #include "hw/char/serial.h" #include "hw/arm/msf2-soc.h" #include "hw/misc/unimp.h" +#include "hw/qdev-clock.h" #include "sysemu/sysemu.h" #define MSF2_TIMER_BASE 0x40004000 @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_initfn(Object *obj) } object_initialize_child(obj, "emac", &s->emac, TYPE_MSS_EMAC); + + s->m3clk = qdev_init_clock_in(DEVICE(obj), "m3clk", NULL, NULL, 0); } static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) MemoryRegion *system_memory = get_system_memory(); + if (!clock_has_source(s->m3clk)) { + error_setg(errp, "m3clk must be wired up by the board code"); + return; + } + memory_region_init_rom(&s->nvm, OBJECT(dev_soc), "MSF2.eNVM", s->envm_size, &error_fatal); /* @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) qdev_prop_set_uint32(armv7m, "num-irq", 81); qdev_prop_set_string(armv7m, "cpu-type", s->cpu_type); qdev_prop_set_bit(armv7m, "enable-bitband", true); + qdev_connect_clock_in(armv7m, "cpuclk", s->m3clk); object_property_set_link(OBJECT(&s->armv7m), "memory", OBJECT(get_system_memory()), &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->armv7m), errp)) { return; } - if (!s->m3clk) { - error_setg(errp, "Invalid m3clk value"); - error_append_hint(errp, "m3clk can not be zero\n"); - return; - } - - system_clock_scale = NANOSECONDS_PER_SECOND / s->m3clk; + system_clock_scale = clock_ticks_to_ns(s->m3clk, 1); for (i = 0; i < MSF2_NUM_UARTS; i++) { if (serial_hd(i)) { @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) } dev = DEVICE(&s->timer); - /* APB0 clock is the timer input clock */ - qdev_prop_set_uint32(dev, "clock-frequency", s->m3clk / s->apb0div); + /* + * APB0 clock is the timer input clock. + * TODO: ideally the MSF2 timer device should use a Clock rather than a + * clock-frequency integer property. + */ + qdev_prop_set_uint32(dev, "clock-frequency", + clock_get_hz(s->m3clk) / s->apb0div); if (!sysbus_realize(SYS_BUS_DEVICE(&s->timer), errp)) { return; } @@ -XXX,XX +XXX,XX @@ static Property m2sxxx_soc_properties[] = { DEFINE_PROP_UINT64("eNVM-size", MSF2State, envm_size, MSF2_ENVM_MAX_SIZE), DEFINE_PROP_UINT64("eSRAM-size", MSF2State, esram_size, MSF2_ESRAM_MAX_SIZE), - /* Libero GUI shows 100Mhz as default for clocks */ - DEFINE_PROP_UINT32("m3clk", MSF2State, m3clk, 100 * 1000000), /* default divisors in Libero GUI */ DEFINE_PROP_UINT8("apb0div", MSF2State, apb0div, 2), DEFINE_PROP_UINT8("apb1div", MSF2State, apb1div, 2), diff --git a/hw/arm/msf2-som.c b/hw/arm/msf2-som.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/msf2-som.c +++ b/hw/arm/msf2-som.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "hw/qdev-properties.h" #include "hw/arm/boot.h" +#include "hw/qdev-clock.h" #include "exec/address-spaces.h" #include "hw/arm/msf2-soc.h" @@ -XXX,XX +XXX,XX @@ static void emcraft_sf2_s2s010_init(MachineState *machine) BusState *spi_bus; MemoryRegion *sysmem = get_system_memory(); MemoryRegion *ddr = g_new(MemoryRegion, 1); + Clock *m3clk; if (strcmp(machine->cpu_type, mc->default_cpu_type) != 0) { error_report("This board can only be used with CPU %s", @@ -XXX,XX +XXX,XX @@ static void emcraft_sf2_s2s010_init(MachineState *machine) * in Libero. CPU clock is divided by APB0 and APB1 divisors for * peripherals. Emcraft's SoM kit comes with these settings by default. */ - qdev_prop_set_uint32(dev, "m3clk", 142 * 1000000); + /* This clock doesn't need migration because it is fixed-frequency */ + m3clk = clock_new(OBJECT(machine), "m3clk"); + clock_set_hz(m3clk, 142 * 1000000); + qdev_connect_clock_in(dev, "m3clk", m3clk); qdev_prop_set_uint32(dev, "apb0div", 2); qdev_prop_set_uint32(dev, "apb1div", 2); -- 2.20.1 Wire up the refclk for the msf2 SoC. This SoC runs the refclk at a frequency which is programmably either /4, /8, /16 or /32 of the main CPU clock. We don't currently model the register which allows the guest to set the divisor, so implement the refclk as a fixed /32 of the CPU clock (which is the value of the divisor at reset). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Damien Hedde <damien.hedde@greensocs.com> Message-id: 20210812093356.1946-21-peter.maydell@linaro.org --- include/hw/arm/msf2-soc.h | 1 + hw/arm/msf2-soc.c | 23 +++++++++++++++++++++++ 2 files changed, 24 insertions(+) diff --git a/include/hw/arm/msf2-soc.h b/include/hw/arm/msf2-soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/msf2-soc.h +++ b/include/hw/arm/msf2-soc.h @@ -XXX,XX +XXX,XX @@ struct MSF2State { uint64_t esram_size; Clock *m3clk; + Clock *refclk; uint8_t apb0div; uint8_t apb1div; diff --git a/hw/arm/msf2-soc.c b/hw/arm/msf2-soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/msf2-soc.c +++ b/hw/arm/msf2-soc.c @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_initfn(Object *obj) object_initialize_child(obj, "emac", &s->emac, TYPE_MSS_EMAC); s->m3clk = qdev_init_clock_in(DEVICE(obj), "m3clk", NULL, NULL, 0); + s->refclk = qdev_init_clock_in(DEVICE(obj), "refclk", NULL, NULL, 0); } static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) return; } + /* + * We use s->refclk internally and only define it with qdev_init_clock_in() + * so it is correctly parented and not leaked on an init/deinit; it is not + * intended as an externally exposed clock. + */ + if (clock_has_source(s->refclk)) { + error_setg(errp, "refclk must not be wired up by the board code"); + return; + } + + /* + * TODO: ideally we should model the SoC SYSTICK_CR register at 0xe0042038, + * which allows the guest to program the divisor between the m3clk and + * the systick refclk to either /4, /8, /16 or /32, as well as setting + * the value the guest can read in the STCALIB register. Currently we + * implement the divisor as a fixed /32, which matches the reset value + * of SYSTICK_CR. + */ + clock_set_mul_div(s->refclk, 32, 1); + clock_set_source(s->refclk, s->m3clk); + memory_region_init_rom(&s->nvm, OBJECT(dev_soc), "MSF2.eNVM", s->envm_size, &error_fatal); /* @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) qdev_prop_set_string(armv7m, "cpu-type", s->cpu_type); qdev_prop_set_bit(armv7m, "enable-bitband", true); qdev_connect_clock_in(armv7m, "cpuclk", s->m3clk); + qdev_connect_clock_in(armv7m, "refclk", s->refclk); object_property_set_link(OBJECT(&s->armv7m), "memory", OBJECT(get_system_memory()), &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->armv7m), errp)) { -- 2.20.1 Now that all users of the systick devices wire up the clock inputs, use those instead of the system_clock_scale and the hardwired 1MHz value for the reference clock. This will fix various board models where we were incorrectly providing a 1MHz reference clock instead of some other value or instead of providing no reference clock at all. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Damien Hedde <damien.hedde@greensocs.com> Message-id: 20210812093356.1946-22-peter.maydell@linaro.org --- hw/timer/armv7m_systick.c | 112 ++++++++++++++++++++++++++++---------- 1 file changed, 84 insertions(+), 28 deletions(-) diff --git a/hw/timer/armv7m_systick.c b/hw/timer/armv7m_systick.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/armv7m_systick.c +++ b/hw/timer/armv7m_systick.c @@ -XXX,XX +XXX,XX @@ #include "qemu/timer.h" #include "qemu/log.h" #include "qemu/module.h" +#include "qapi/error.h" #include "trace.h" -/* qemu timers run at 1GHz. We want something closer to 1MHz. */ -#define SYSTICK_SCALE 1000ULL - #define SYSTICK_ENABLE (1 << 0) #define SYSTICK_TICKINT (1 << 1) #define SYSTICK_CLKSOURCE (1 << 2) #define SYSTICK_COUNTFLAG (1 << 16) +#define SYSCALIB_NOREF (1U << 31) +#define SYSCALIB_SKEW (1U << 30) +#define SYSCALIB_TENMS ((1U << 24) - 1) + int system_clock_scale; -/* Conversion factor from qemu timer to SysTick frequencies. */ -static inline int64_t systick_scale(SysTickState *s) +static void systick_set_period_from_clock(SysTickState *s) { + /* + * Set the ptimer period from whichever clock is selected. + * Must be called from within a ptimer transaction block. + */ if (s->control & SYSTICK_CLKSOURCE) { - return system_clock_scale; + ptimer_set_period_from_clock(s->ptimer, s->cpuclk, 1); } else { - return 1000; + ptimer_set_period_from_clock(s->ptimer, s->refclk, 1); } } @@ -XXX,XX +XXX,XX @@ static MemTxResult systick_read(void *opaque, hwaddr addr, uint64_t *data, val = ptimer_get_count(s->ptimer); break; case 0xc: /* SysTick Calibration Value. */ - val = 10000; + /* + * In real hardware it is possible to make this register report + * a different value from what the reference clock is actually + * running at. We don't model that (which usually happens due + * to integration errors in the real hardware) and instead always + * report the theoretical correct value as described in the + * knowledgebase article at + * https://developer.arm.com/documentation/ka001325/latest + * If necessary, we could implement an extra QOM property on this + * device to force the STCALIB value to something different from + * the "correct" value. + */ + if (!clock_has_source(s->refclk)) { + val = SYSCALIB_NOREF; + break; + } + val = clock_ns_to_ticks(s->refclk, 10 * SCALE_MS) - 1; + val &= SYSCALIB_TENMS; + if (clock_ticks_to_ns(s->refclk, val + 1) != 10 * SCALE_MS) { + /* report that tick count does not yield exactly 10ms */ + val |= SYSCALIB_SKEW; + } break; default: val = 0; @@ -XXX,XX +XXX,XX @@ static MemTxResult systick_write(void *opaque, hwaddr addr, { uint32_t oldval; + if (!clock_has_source(s->refclk)) { + /* This bit is always 1 if there is no external refclk */ + value |= SYSTICK_CLKSOURCE; + } + ptimer_transaction_begin(s->ptimer); oldval = s->control; s->control &= 0xfffffff8; @@ -XXX,XX +XXX,XX @@ static MemTxResult systick_write(void *opaque, hwaddr addr, if ((oldval ^ value) & SYSTICK_ENABLE) { if (value & SYSTICK_ENABLE) { - /* - * Always reload the period in case board code has - * changed system_clock_scale. If we ever replace that - * global with a more sensible API then we might be able - * to set the period only when it actually changes. - */ - ptimer_set_period(s->ptimer, systick_scale(s)); ptimer_run(s->ptimer, 0); } else { ptimer_stop(s->ptimer); } - } else if ((oldval ^ value) & SYSTICK_CLKSOURCE) { - ptimer_set_period(s->ptimer, systick_scale(s)); + } + + if ((oldval ^ value) & SYSTICK_CLKSOURCE) { + systick_set_period_from_clock(s); } ptimer_transaction_commit(s->ptimer); break; @@ -XXX,XX +XXX,XX @@ static void systick_reset(DeviceState *dev) { SysTickState *s = SYSTICK(dev); - /* - * Forgetting to set system_clock_scale is always a board code - * bug. We can't check this earlier because for some boards - * (like stellaris) it is not yet configured at the point where - * the systick device is realized. - */ - assert(system_clock_scale != 0); - ptimer_transaction_begin(s->ptimer); s->control = 0; + if (!clock_has_source(s->refclk)) { + /* This bit is always 1 if there is no external refclk */ + s->control |= SYSTICK_CLKSOURCE; + } ptimer_stop(s->ptimer); ptimer_set_count(s->ptimer, 0); ptimer_set_limit(s->ptimer, 0, 0); - ptimer_set_period(s->ptimer, systick_scale(s)); + systick_set_period_from_clock(s); + ptimer_transaction_commit(s->ptimer); +} + +static void systick_cpuclk_update(void *opaque, ClockEvent event) +{ + SysTickState *s = SYSTICK(opaque); + + if (!(s->control & SYSTICK_CLKSOURCE)) { + /* currently using refclk, we can ignore cpuclk changes */ + } + + ptimer_transaction_begin(s->ptimer); + ptimer_set_period_from_clock(s->ptimer, s->cpuclk, 1); + ptimer_transaction_commit(s->ptimer); +} + +static void systick_refclk_update(void *opaque, ClockEvent event) +{ + SysTickState *s = SYSTICK(opaque); + + if (s->control & SYSTICK_CLKSOURCE) { + /* currently using cpuclk, we can ignore refclk changes */ + } + + ptimer_transaction_begin(s->ptimer); + ptimer_set_period_from_clock(s->ptimer, s->refclk, 1); ptimer_transaction_commit(s->ptimer); } @@ -XXX,XX +XXX,XX @@ static void systick_instance_init(Object *obj) sysbus_init_mmio(sbd, &s->iomem); sysbus_init_irq(sbd, &s->irq); - s->refclk = qdev_init_clock_in(DEVICE(obj), "refclk", NULL, NULL, 0); - s->cpuclk = qdev_init_clock_in(DEVICE(obj), "cpuclk", NULL, NULL, 0); + s->refclk = qdev_init_clock_in(DEVICE(obj), "refclk", + systick_refclk_update, s, ClockUpdate); + s->cpuclk = qdev_init_clock_in(DEVICE(obj), "cpuclk", + systick_cpuclk_update, s, ClockUpdate); } static void systick_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void systick_realize(DeviceState *dev, Error **errp) PTIMER_POLICY_NO_COUNTER_ROUND_DOWN | PTIMER_POLICY_NO_IMMEDIATE_RELOAD | PTIMER_POLICY_TRIGGER_ONLY_ON_DECREMENT); + + if (!clock_has_source(s->cpuclk)) { + error_setg(errp, "systick: cpuclk must be connected"); + return; + } + /* It's OK not to connect the refclk */ } static const VMStateDescription vmstate_systick = { -- 2.20.1 Fix the code style issues in the Stellaris general purpose timer module code, so that when we move it to a different file in a following patch checkpatch doesn't complain. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alexandre Iooss <erdnaxe@crans.org> Message-id: 20210812093356.1946-23-peter.maydell@linaro.org --- hw/arm/stellaris.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void gptm_stop(gptm_state *s, int n) static void gptm_reload(gptm_state *s, int n, int reset) { int64_t tick; - if (reset) + if (reset) { tick = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - else + } else { tick = s->tick[n]; + } if (s->config == 0) { /* 32-bit CountDown. */ @@ -XXX,XX +XXX,XX @@ static void gptm_write(void *opaque, hwaddr offset, gptm_state *s = (gptm_state *)opaque; uint32_t oldval; - /* The timers should be disabled before changing the configuration. - We take advantage of this and defer everything until the timer - is enabled. */ + /* + * The timers should be disabled before changing the configuration. + * We take advantage of this and defer everything until the timer + * is enabled. + */ switch (offset) { case 0x00: /* CFG */ s->config = value; -- 2.20.1 The implementation of the Stellaris general purpose timer module device stellaris-gptm is currently in the same source file as the board model. Split it out into its own source file in hw/timer. Apart from the new file comment headers and the Kconfig and meson.build changes, this is just code movement. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Damien Hedde <damien.hedde@greensocs.com> Message-id: 20210812093356.1946-24-peter.maydell@linaro.org --- include/hw/timer/stellaris-gptm.h | 48 +++++ hw/arm/stellaris.c | 321 +----------------------------- hw/timer/stellaris-gptm.c | 314 +++++++++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/timer/Kconfig | 3 + hw/timer/meson.build | 1 + 6 files changed, 368 insertions(+), 320 deletions(-) create mode 100644 include/hw/timer/stellaris-gptm.h create mode 100644 hw/timer/stellaris-gptm.c diff --git a/include/hw/timer/stellaris-gptm.h b/include/hw/timer/stellaris-gptm.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/timer/stellaris-gptm.h @@ -XXX,XX +XXX,XX @@ +/* + * Luminary Micro Stellaris General Purpose Timer Module + * + * Copyright (c) 2006 CodeSourcery. + * Written by Paul Brook + * + * This code is licensed under the GPL. + */ + +#ifndef HW_TIMER_STELLARIS_GPTM_H +#define HW_TIMER_STELLARIS_GPTM_H + +#include "qom/object.h" +#include "hw/sysbus.h" +#include "hw/irq.h" + +#define TYPE_STELLARIS_GPTM "stellaris-gptm" +OBJECT_DECLARE_SIMPLE_TYPE(gptm_state, STELLARIS_GPTM) + +/* + * QEMU interface: + * + sysbus MMIO region 0: register bank + * + sysbus IRQ 0: timer interrupt + * + unnamed GPIO output 0: trigger output for the ADC + */ +struct gptm_state { + SysBusDevice parent_obj; + + MemoryRegion iomem; + uint32_t config; + uint32_t mode[2]; + uint32_t control; + uint32_t state; + uint32_t mask; + uint32_t load[2]; + uint32_t match[2]; + uint32_t prescale[2]; + uint32_t match_prescale[2]; + uint32_t rtc; + int64_t tick[2]; + struct gptm_state *opaque[2]; + QEMUTimer *timer[2]; + /* The timers have an alternate output used to trigger the ADC. */ + qemu_irq trigger; + qemu_irq irq; +}; + +#endif diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ #include "hw/watchdog/cmsdk-apb-watchdog.h" #include "migration/vmstate.h" #include "hw/misc/unimp.h" +#include "hw/timer/stellaris-gptm.h" #include "hw/qdev-clock.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ typedef const struct { uint32_t peripherals; } stellaris_board_info; -/* General purpose timer module. */ - -#define TYPE_STELLARIS_GPTM "stellaris-gptm" -OBJECT_DECLARE_SIMPLE_TYPE(gptm_state, STELLARIS_GPTM) - -struct gptm_state { - SysBusDevice parent_obj; - - MemoryRegion iomem; - uint32_t config; - uint32_t mode[2]; - uint32_t control; - uint32_t state; - uint32_t mask; - uint32_t load[2]; - uint32_t match[2]; - uint32_t prescale[2]; - uint32_t match_prescale[2]; - uint32_t rtc; - int64_t tick[2]; - struct gptm_state *opaque[2]; - QEMUTimer *timer[2]; - /* The timers have an alternate output used to trigger the ADC. */ - qemu_irq trigger; - qemu_irq irq; -}; - -static void gptm_update_irq(gptm_state *s) -{ - int level; - level = (s->state & s->mask) != 0; - qemu_set_irq(s->irq, level); -} - -static void gptm_stop(gptm_state *s, int n) -{ - timer_del(s->timer[n]); -} - -static void gptm_reload(gptm_state *s, int n, int reset) -{ - int64_t tick; - if (reset) { - tick = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - } else { - tick = s->tick[n]; - } - - if (s->config == 0) { - /* 32-bit CountDown. */ - uint32_t count; - count = s->load[0] | (s->load[1] << 16); - tick += (int64_t)count * system_clock_scale; - } else if (s->config == 1) { - /* 32-bit RTC. 1Hz tick. */ - tick += NANOSECONDS_PER_SECOND; - } else if (s->mode[n] == 0xa) { - /* PWM mode. Not implemented. */ - } else { - qemu_log_mask(LOG_UNIMP, - "GPTM: 16-bit timer mode unimplemented: 0x%x\n", - s->mode[n]); - return; - } - s->tick[n] = tick; - timer_mod(s->timer[n], tick); -} - -static void gptm_tick(void *opaque) -{ - gptm_state **p = (gptm_state **)opaque; - gptm_state *s; - int n; - - s = *p; - n = p - s->opaque; - if (s->config == 0) { - s->state |= 1; - if ((s->control & 0x20)) { - /* Output trigger. */ - qemu_irq_pulse(s->trigger); - } - if (s->mode[0] & 1) { - /* One-shot. */ - s->control &= ~1; - } else { - /* Periodic. */ - gptm_reload(s, 0, 0); - } - } else if (s->config == 1) { - /* RTC. */ - uint32_t match; - s->rtc++; - match = s->match[0] | (s->match[1] << 16); - if (s->rtc > match) - s->rtc = 0; - if (s->rtc == 0) { - s->state |= 8; - } - gptm_reload(s, 0, 0); - } else if (s->mode[n] == 0xa) { - /* PWM mode. Not implemented. */ - } else { - qemu_log_mask(LOG_UNIMP, - "GPTM: 16-bit timer mode unimplemented: 0x%x\n", - s->mode[n]); - } - gptm_update_irq(s); -} - -static uint64_t gptm_read(void *opaque, hwaddr offset, - unsigned size) -{ - gptm_state *s = (gptm_state *)opaque; - - switch (offset) { - case 0x00: /* CFG */ - return s->config; - case 0x04: /* TAMR */ - return s->mode[0]; - case 0x08: /* TBMR */ - return s->mode[1]; - case 0x0c: /* CTL */ - return s->control; - case 0x18: /* IMR */ - return s->mask; - case 0x1c: /* RIS */ - return s->state; - case 0x20: /* MIS */ - return s->state & s->mask; - case 0x24: /* CR */ - return 0; - case 0x28: /* TAILR */ - return s->load[0] | ((s->config < 4) ? (s->load[1] << 16) : 0); - case 0x2c: /* TBILR */ - return s->load[1]; - case 0x30: /* TAMARCHR */ - return s->match[0] | ((s->config < 4) ? (s->match[1] << 16) : 0); - case 0x34: /* TBMATCHR */ - return s->match[1]; - case 0x38: /* TAPR */ - return s->prescale[0]; - case 0x3c: /* TBPR */ - return s->prescale[1]; - case 0x40: /* TAPMR */ - return s->match_prescale[0]; - case 0x44: /* TBPMR */ - return s->match_prescale[1]; - case 0x48: /* TAR */ - if (s->config == 1) { - return s->rtc; - } - qemu_log_mask(LOG_UNIMP, - "GPTM: read of TAR but timer read not supported\n"); - return 0; - case 0x4c: /* TBR */ - qemu_log_mask(LOG_UNIMP, - "GPTM: read of TBR but timer read not supported\n"); - return 0; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "GPTM: read at bad offset 0x02%" HWADDR_PRIx "\n", - offset); - return 0; - } -} - -static void gptm_write(void *opaque, hwaddr offset, - uint64_t value, unsigned size) -{ - gptm_state *s = (gptm_state *)opaque; - uint32_t oldval; - - /* - * The timers should be disabled before changing the configuration. - * We take advantage of this and defer everything until the timer - * is enabled. - */ - switch (offset) { - case 0x00: /* CFG */ - s->config = value; - break; - case 0x04: /* TAMR */ - s->mode[0] = value; - break; - case 0x08: /* TBMR */ - s->mode[1] = value; - break; - case 0x0c: /* CTL */ - oldval = s->control; - s->control = value; - /* TODO: Implement pause. */ - if ((oldval ^ value) & 1) { - if (value & 1) { - gptm_reload(s, 0, 1); - } else { - gptm_stop(s, 0); - } - } - if (((oldval ^ value) & 0x100) && s->config >= 4) { - if (value & 0x100) { - gptm_reload(s, 1, 1); - } else { - gptm_stop(s, 1); - } - } - break; - case 0x18: /* IMR */ - s->mask = value & 0x77; - gptm_update_irq(s); - break; - case 0x24: /* CR */ - s->state &= ~value; - break; - case 0x28: /* TAILR */ - s->load[0] = value & 0xffff; - if (s->config < 4) { - s->load[1] = value >> 16; - } - break; - case 0x2c: /* TBILR */ - s->load[1] = value & 0xffff; - break; - case 0x30: /* TAMARCHR */ - s->match[0] = value & 0xffff; - if (s->config < 4) { - s->match[1] = value >> 16; - } - break; - case 0x34: /* TBMATCHR */ - s->match[1] = value >> 16; - break; - case 0x38: /* TAPR */ - s->prescale[0] = value; - break; - case 0x3c: /* TBPR */ - s->prescale[1] = value; - break; - case 0x40: /* TAPMR */ - s->match_prescale[0] = value; - break; - case 0x44: /* TBPMR */ - s->match_prescale[0] = value; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "GPTM: write at bad offset 0x02%" HWADDR_PRIx "\n", - offset); - } - gptm_update_irq(s); -} - -static const MemoryRegionOps gptm_ops = { - .read = gptm_read, - .write = gptm_write, - .endianness = DEVICE_NATIVE_ENDIAN, -}; - -static const VMStateDescription vmstate_stellaris_gptm = { - .name = "stellaris_gptm", - .version_id = 1, - .minimum_version_id = 1, - .fields = (VMStateField[]) { - VMSTATE_UINT32(config, gptm_state), - VMSTATE_UINT32_ARRAY(mode, gptm_state, 2), - VMSTATE_UINT32(control, gptm_state), - VMSTATE_UINT32(state, gptm_state), - VMSTATE_UINT32(mask, gptm_state), - VMSTATE_UNUSED(8), - VMSTATE_UINT32_ARRAY(load, gptm_state, 2), - VMSTATE_UINT32_ARRAY(match, gptm_state, 2), - VMSTATE_UINT32_ARRAY(prescale, gptm_state, 2), - VMSTATE_UINT32_ARRAY(match_prescale, gptm_state, 2), - VMSTATE_UINT32(rtc, gptm_state), - VMSTATE_INT64_ARRAY(tick, gptm_state, 2), - VMSTATE_TIMER_PTR_ARRAY(timer, gptm_state, 2), - VMSTATE_END_OF_LIST() - } -}; - -static void stellaris_gptm_init(Object *obj) -{ - DeviceState *dev = DEVICE(obj); - gptm_state *s = STELLARIS_GPTM(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - - sysbus_init_irq(sbd, &s->irq); - qdev_init_gpio_out(dev, &s->trigger, 1); - - memory_region_init_io(&s->iomem, obj, &gptm_ops, s, - "gptm", 0x1000); - sysbus_init_mmio(sbd, &s->iomem); - - s->opaque[0] = s->opaque[1] = s; -} - -static void stellaris_gptm_realize(DeviceState *dev, Error **errp) -{ - gptm_state *s = STELLARIS_GPTM(dev); - s->timer[0] = timer_new_ns(QEMU_CLOCK_VIRTUAL, gptm_tick, &s->opaque[0]); - s->timer[1] = timer_new_ns(QEMU_CLOCK_VIRTUAL, gptm_tick, &s->opaque[1]); -} - /* System controller. */ #define TYPE_STELLARIS_SYS "stellaris-sys" @@ -XXX,XX +XXX,XX @@ static const TypeInfo stellaris_i2c_info = { .class_init = stellaris_i2c_class_init, }; -static void stellaris_gptm_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->vmsd = &vmstate_stellaris_gptm; - dc->realize = stellaris_gptm_realize; -} - -static const TypeInfo stellaris_gptm_info = { - .name = TYPE_STELLARIS_GPTM, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(gptm_state), - .instance_init = stellaris_gptm_init, - .class_init = stellaris_gptm_class_init, -}; - static void stellaris_adc_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); @@ -XXX,XX +XXX,XX @@ static const TypeInfo stellaris_sys_info = { static void stellaris_register_types(void) { type_register_static(&stellaris_i2c_info); - type_register_static(&stellaris_gptm_info); type_register_static(&stellaris_adc_info); type_register_static(&stellaris_sys_info); } diff --git a/hw/timer/stellaris-gptm.c b/hw/timer/stellaris-gptm.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/timer/stellaris-gptm.c @@ -XXX,XX +XXX,XX @@ +/* + * Luminary Micro Stellaris General Purpose Timer Module + * + * Copyright (c) 2006 CodeSourcery. + * Written by Paul Brook + * + * This code is licensed under the GPL. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/timer.h" +#include "migration/vmstate.h" +#include "hw/timer/stellaris-gptm.h" +#include "hw/timer/armv7m_systick.h" /* Needed only for system_clock_scale */ + +static void gptm_update_irq(gptm_state *s) +{ + int level; + level = (s->state & s->mask) != 0; + qemu_set_irq(s->irq, level); +} + +static void gptm_stop(gptm_state *s, int n) +{ + timer_del(s->timer[n]); +} + +static void gptm_reload(gptm_state *s, int n, int reset) +{ + int64_t tick; + if (reset) { + tick = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + } else { + tick = s->tick[n]; + } + + if (s->config == 0) { + /* 32-bit CountDown. */ + uint32_t count; + count = s->load[0] | (s->load[1] << 16); + tick += (int64_t)count * system_clock_scale; + } else if (s->config == 1) { + /* 32-bit RTC. 1Hz tick. */ + tick += NANOSECONDS_PER_SECOND; + } else if (s->mode[n] == 0xa) { + /* PWM mode. Not implemented. */ + } else { + qemu_log_mask(LOG_UNIMP, + "GPTM: 16-bit timer mode unimplemented: 0x%x\n", + s->mode[n]); + return; + } + s->tick[n] = tick; + timer_mod(s->timer[n], tick); +} + +static void gptm_tick(void *opaque) +{ + gptm_state **p = (gptm_state **)opaque; + gptm_state *s; + int n; + + s = *p; + n = p - s->opaque; + if (s->config == 0) { + s->state |= 1; + if ((s->control & 0x20)) { + /* Output trigger. */ + qemu_irq_pulse(s->trigger); + } + if (s->mode[0] & 1) { + /* One-shot. */ + s->control &= ~1; + } else { + /* Periodic. */ + gptm_reload(s, 0, 0); + } + } else if (s->config == 1) { + /* RTC. */ + uint32_t match; + s->rtc++; + match = s->match[0] | (s->match[1] << 16); + if (s->rtc > match) + s->rtc = 0; + if (s->rtc == 0) { + s->state |= 8; + } + gptm_reload(s, 0, 0); + } else if (s->mode[n] == 0xa) { + /* PWM mode. Not implemented. */ + } else { + qemu_log_mask(LOG_UNIMP, + "GPTM: 16-bit timer mode unimplemented: 0x%x\n", + s->mode[n]); + } + gptm_update_irq(s); +} + +static uint64_t gptm_read(void *opaque, hwaddr offset, + unsigned size) +{ + gptm_state *s = (gptm_state *)opaque; + + switch (offset) { + case 0x00: /* CFG */ + return s->config; + case 0x04: /* TAMR */ + return s->mode[0]; + case 0x08: /* TBMR */ + return s->mode[1]; + case 0x0c: /* CTL */ + return s->control; + case 0x18: /* IMR */ + return s->mask; + case 0x1c: /* RIS */ + return s->state; + case 0x20: /* MIS */ + return s->state & s->mask; + case 0x24: /* CR */ + return 0; + case 0x28: /* TAILR */ + return s->load[0] | ((s->config < 4) ? (s->load[1] << 16) : 0); + case 0x2c: /* TBILR */ + return s->load[1]; + case 0x30: /* TAMARCHR */ + return s->match[0] | ((s->config < 4) ? (s->match[1] << 16) : 0); + case 0x34: /* TBMATCHR */ + return s->match[1]; + case 0x38: /* TAPR */ + return s->prescale[0]; + case 0x3c: /* TBPR */ + return s->prescale[1]; + case 0x40: /* TAPMR */ + return s->match_prescale[0]; + case 0x44: /* TBPMR */ + return s->match_prescale[1]; + case 0x48: /* TAR */ + if (s->config == 1) { + return s->rtc; + } + qemu_log_mask(LOG_UNIMP, + "GPTM: read of TAR but timer read not supported\n"); + return 0; + case 0x4c: /* TBR */ + qemu_log_mask(LOG_UNIMP, + "GPTM: read of TBR but timer read not supported\n"); + return 0; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "GPTM: read at bad offset 0x02%" HWADDR_PRIx "\n", + offset); + return 0; + } +} + +static void gptm_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + gptm_state *s = (gptm_state *)opaque; + uint32_t oldval; + + /* + * The timers should be disabled before changing the configuration. + * We take advantage of this and defer everything until the timer + * is enabled. + */ + switch (offset) { + case 0x00: /* CFG */ + s->config = value; + break; + case 0x04: /* TAMR */ + s->mode[0] = value; + break; + case 0x08: /* TBMR */ + s->mode[1] = value; + break; + case 0x0c: /* CTL */ + oldval = s->control; + s->control = value; + /* TODO: Implement pause. */ + if ((oldval ^ value) & 1) { + if (value & 1) { + gptm_reload(s, 0, 1); + } else { + gptm_stop(s, 0); + } + } + if (((oldval ^ value) & 0x100) && s->config >= 4) { + if (value & 0x100) { + gptm_reload(s, 1, 1); + } else { + gptm_stop(s, 1); + } + } + break; + case 0x18: /* IMR */ + s->mask = value & 0x77; + gptm_update_irq(s); + break; + case 0x24: /* CR */ + s->state &= ~value; + break; + case 0x28: /* TAILR */ + s->load[0] = value & 0xffff; + if (s->config < 4) { + s->load[1] = value >> 16; + } + break; + case 0x2c: /* TBILR */ + s->load[1] = value & 0xffff; + break; + case 0x30: /* TAMARCHR */ + s->match[0] = value & 0xffff; + if (s->config < 4) { + s->match[1] = value >> 16; + } + break; + case 0x34: /* TBMATCHR */ + s->match[1] = value >> 16; + break; + case 0x38: /* TAPR */ + s->prescale[0] = value; + break; + case 0x3c: /* TBPR */ + s->prescale[1] = value; + break; + case 0x40: /* TAPMR */ + s->match_prescale[0] = value; + break; + case 0x44: /* TBPMR */ + s->match_prescale[0] = value; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "GPTM: write at bad offset 0x02%" HWADDR_PRIx "\n", + offset); + } + gptm_update_irq(s); +} + +static const MemoryRegionOps gptm_ops = { + .read = gptm_read, + .write = gptm_write, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static const VMStateDescription vmstate_stellaris_gptm = { + .name = "stellaris_gptm", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(config, gptm_state), + VMSTATE_UINT32_ARRAY(mode, gptm_state, 2), + VMSTATE_UINT32(control, gptm_state), + VMSTATE_UINT32(state, gptm_state), + VMSTATE_UINT32(mask, gptm_state), + VMSTATE_UNUSED(8), + VMSTATE_UINT32_ARRAY(load, gptm_state, 2), + VMSTATE_UINT32_ARRAY(match, gptm_state, 2), + VMSTATE_UINT32_ARRAY(prescale, gptm_state, 2), + VMSTATE_UINT32_ARRAY(match_prescale, gptm_state, 2), + VMSTATE_UINT32(rtc, gptm_state), + VMSTATE_INT64_ARRAY(tick, gptm_state, 2), + VMSTATE_TIMER_PTR_ARRAY(timer, gptm_state, 2), + VMSTATE_END_OF_LIST() + } +}; + +static void stellaris_gptm_init(Object *obj) +{ + DeviceState *dev = DEVICE(obj); + gptm_state *s = STELLARIS_GPTM(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + + sysbus_init_irq(sbd, &s->irq); + qdev_init_gpio_out(dev, &s->trigger, 1); + + memory_region_init_io(&s->iomem, obj, &gptm_ops, s, + "gptm", 0x1000); + sysbus_init_mmio(sbd, &s->iomem); + + s->opaque[0] = s->opaque[1] = s; +} + +static void stellaris_gptm_realize(DeviceState *dev, Error **errp) +{ + gptm_state *s = STELLARIS_GPTM(dev); + s->timer[0] = timer_new_ns(QEMU_CLOCK_VIRTUAL, gptm_tick, &s->opaque[0]); + s->timer[1] = timer_new_ns(QEMU_CLOCK_VIRTUAL, gptm_tick, &s->opaque[1]); +} + +static void stellaris_gptm_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->vmsd = &vmstate_stellaris_gptm; + dc->realize = stellaris_gptm_realize; +} + +static const TypeInfo stellaris_gptm_info = { + .name = TYPE_STELLARIS_GPTM, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(gptm_state), + .instance_init = stellaris_gptm_init, + .class_init = stellaris_gptm_class_init, +}; + +static void stellaris_gptm_register_types(void) +{ + type_register_static(&stellaris_gptm_info); +} + +type_init(stellaris_gptm_register_types) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config STELLARIS select SSI_SD select STELLARIS_INPUT select STELLARIS_ENET # ethernet + select STELLARIS_GPTM # general purpose timer module select UNIMP config STM32VLDISCOVERY diff --git a/hw/timer/Kconfig b/hw/timer/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/Kconfig +++ b/hw/timer/Kconfig @@ -XXX,XX +XXX,XX @@ config SSE_COUNTER config SSE_TIMER bool +config STELLARIS_GPTM + bool + config AVR_TIMER16 bool diff --git a/hw/timer/meson.build b/hw/timer/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/meson.build +++ b/hw/timer/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_SH_TIMER', if_true: files('sh_timer.c')) softmmu_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_timer.c')) softmmu_ss.add(when: 'CONFIG_SSE_COUNTER', if_true: files('sse-counter.c')) softmmu_ss.add(when: 'CONFIG_SSE_TIMER', if_true: files('sse-timer.c')) +softmmu_ss.add(when: 'CONFIG_STELLARIS_GPTM', if_true: files('stellaris-gptm.c')) softmmu_ss.add(when: 'CONFIG_STM32F2XX_TIMER', if_true: files('stm32f2xx_timer.c')) softmmu_ss.add(when: 'CONFIG_XILINX', if_true: files('xilinx_timer.c')) specific_ss.add(when: 'CONFIG_IBEX', if_true: files('ibex_timer.c')) -- 2.20.1 The stellaris-gptm timer currently uses system_clock_scale for one of its timer modes where the timer runs at the CPU clock rate. Make it use a Clock input instead. We don't try to make the timer handle changes in the clock frequency while the downcounter is running. This is not a change in behaviour from the previous system_clock_scale implementation -- we will pick up the new frequency only when the downcounter hits zero. Handling dynamic clock changes when the counter is running would require state that the current gptm implementation doesn't have. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Damien Hedde <damien.hedde@greensocs.com> Message-id: 20210812093356.1946-25-peter.maydell@linaro.org --- include/hw/timer/stellaris-gptm.h | 3 +++ hw/arm/stellaris.c | 12 +++++++++--- hw/timer/stellaris-gptm.c | 26 ++++++++++++++++++++++---- 3 files changed, 34 insertions(+), 7 deletions(-) diff --git a/include/hw/timer/stellaris-gptm.h b/include/hw/timer/stellaris-gptm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/timer/stellaris-gptm.h +++ b/include/hw/timer/stellaris-gptm.h @@ -XXX,XX +XXX,XX @@ #include "qom/object.h" #include "hw/sysbus.h" #include "hw/irq.h" +#include "hw/clock.h" #define TYPE_STELLARIS_GPTM "stellaris-gptm" OBJECT_DECLARE_SIMPLE_TYPE(gptm_state, STELLARIS_GPTM) @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(gptm_state, STELLARIS_GPTM) * + sysbus MMIO region 0: register bank * + sysbus IRQ 0: timer interrupt * + unnamed GPIO output 0: trigger output for the ADC + * + Clock input "clk": the 32-bit countdown timer runs at this speed */ struct gptm_state { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct gptm_state { /* The timers have an alternate output used to trigger the ADC. */ qemu_irq trigger; qemu_irq irq; + Clock *clk; }; #endif diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) } for (i = 0; i < 4; i++) { if (board->dc2 & (0x10000 << i)) { - dev = sysbus_create_simple(TYPE_STELLARIS_GPTM, - 0x40030000 + i * 0x1000, - qdev_get_gpio_in(nvic, timer_irq[i])); + SysBusDevice *sbd; + + dev = qdev_new(TYPE_STELLARIS_GPTM); + sbd = SYS_BUS_DEVICE(dev); + qdev_connect_clock_in(dev, "clk", + qdev_get_clock_out(ssys_dev, "SYSCLK")); + sysbus_realize_and_unref(sbd, &error_fatal); + sysbus_mmio_map(sbd, 0, 0x40030000 + i * 0x1000); + sysbus_connect_irq(sbd, 0, qdev_get_gpio_in(nvic, timer_irq[i])); /* TODO: This is incorrect, but we get away with it because the ADC output is only ever pulsed. */ qdev_connect_gpio_out(dev, 0, adc); diff --git a/hw/timer/stellaris-gptm.c b/hw/timer/stellaris-gptm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/stellaris-gptm.c +++ b/hw/timer/stellaris-gptm.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qemu/log.h" #include "qemu/timer.h" +#include "qapi/error.h" #include "migration/vmstate.h" +#include "hw/qdev-clock.h" #include "hw/timer/stellaris-gptm.h" -#include "hw/timer/armv7m_systick.h" /* Needed only for system_clock_scale */ static void gptm_update_irq(gptm_state *s) { @@ -XXX,XX +XXX,XX @@ static void gptm_reload(gptm_state *s, int n, int reset) /* 32-bit CountDown. */ uint32_t count; count = s->load[0] | (s->load[1] << 16); - tick += (int64_t)count * system_clock_scale; + tick += clock_ticks_to_ns(s->clk, count); } else if (s->config == 1) { /* 32-bit RTC. 1Hz tick. */ tick += NANOSECONDS_PER_SECOND; @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps gptm_ops = { static const VMStateDescription vmstate_stellaris_gptm = { .name = "stellaris_gptm", - .version_id = 1, - .minimum_version_id = 1, + .version_id = 2, + .minimum_version_id = 2, .fields = (VMStateField[]) { VMSTATE_UINT32(config, gptm_state), VMSTATE_UINT32_ARRAY(mode, gptm_state, 2), @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_stellaris_gptm = { VMSTATE_UINT32(rtc, gptm_state), VMSTATE_INT64_ARRAY(tick, gptm_state, 2), VMSTATE_TIMER_PTR_ARRAY(timer, gptm_state, 2), + VMSTATE_CLOCK(clk, gptm_state), VMSTATE_END_OF_LIST() } }; @@ -XXX,XX +XXX,XX @@ static void stellaris_gptm_init(Object *obj) sysbus_init_mmio(sbd, &s->iomem); s->opaque[0] = s->opaque[1] = s; + + /* + * TODO: in an ideal world we would model the effects of changing + * the input clock frequency while the countdown timer is active. + * The best way to do this would be to convert the device to use + * ptimer instead of hand-rolling its own timer. This would also + * make it easy to implement reading the current count from the + * TAR and TBR registers. + */ + s->clk = qdev_init_clock_in(dev, "clk", NULL, NULL, 0); } static void stellaris_gptm_realize(DeviceState *dev, Error **errp) { gptm_state *s = STELLARIS_GPTM(dev); + + if (!clock_has_source(s->clk)) { + error_setg(errp, "stellaris-gptm: clk must be connected"); + return; + } + s->timer[0] = timer_new_ns(QEMU_CLOCK_VIRTUAL, gptm_tick, &s->opaque[0]); s->timer[1] = timer_new_ns(QEMU_CLOCK_VIRTUAL, gptm_tick, &s->opaque[1]); } -- 2.20.1 All the devices that used to use system_clock_scale have now been converted to use Clock inputs instead, so the global is no longer needed; remove it and all the code that sets it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20210812093356.1946-26-peter.maydell@linaro.org --- include/hw/timer/armv7m_systick.h | 22 ---------------------- hw/arm/armsse.c | 17 +---------------- hw/arm/mps2.c | 2 -- hw/arm/msf2-soc.c | 2 -- hw/arm/netduino2.c | 2 -- hw/arm/netduinoplus2.c | 2 -- hw/arm/nrf51_soc.c | 2 -- hw/arm/stellaris.c | 7 ++++--- hw/arm/stm32vldiscovery.c | 2 -- hw/timer/armv7m_systick.c | 2 -- 10 files changed, 5 insertions(+), 55 deletions(-) diff --git a/include/hw/timer/armv7m_systick.h b/include/hw/timer/armv7m_systick.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/timer/armv7m_systick.h +++ b/include/hw/timer/armv7m_systick.h @@ -XXX,XX +XXX,XX @@ struct SysTickState { Clock *cpuclk; }; -/* - * Multiplication factor to convert from system clock ticks to qemu timer - * ticks. This should be set (by board code, usually) to a value - * equal to NANOSECONDS_PER_SECOND / frq, where frq is the clock frequency - * in Hz of the CPU. - * - * This value is used by the systick device when it is running in - * its "use the CPU clock" mode (ie when SYST_CSR.CLKSOURCE == 1) to - * set how fast the timer should tick. - * - * TODO: we should refactor this so that rather than using a global - * we use a device property or something similar. This is complicated - * because (a) the property would need to be plumbed through from the - * board code down through various layers to the systick device - * and (b) the property needs to be modifiable after realize, because - * the stellaris board uses this to implement the behaviour where the - * guest can reprogram the PLL registers to downclock the CPU, and the - * systick device needs to react accordingly. Possibly this should - * be deferred until we have a good API for modelling clock trees. - */ -extern int system_clock_scale; - #endif diff --git a/hw/arm/armsse.c b/hw/arm/armsse.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armsse.c +++ b/hw/arm/armsse.c @@ -XXX,XX +XXX,XX @@ static void armsse_forward_sec_resp_cfg(ARMSSE *s) qdev_connect_gpio_out(dev_splitter, 2, s->sec_resp_cfg_in); } -static void armsse_mainclk_update(void *opaque, ClockEvent event) -{ - ARMSSE *s = ARM_SSE(opaque); - - /* - * Set system_clock_scale from our Clock input; this is what - * controls the tick rate of the CPU SysTick timer. - */ - system_clock_scale = clock_ticks_to_ns(s->mainclk, 1); -} - static void armsse_init(Object *obj) { ARMSSE *s = ARM_SSE(obj); @@ -XXX,XX +XXX,XX @@ static void armsse_init(Object *obj) assert(info->sram_banks <= MAX_SRAM_BANKS); assert(info->num_cpus <= SSE_MAX_CPUS); - s->mainclk = qdev_init_clock_in(DEVICE(s), "MAINCLK", - armsse_mainclk_update, s, ClockUpdate); + s->mainclk = qdev_init_clock_in(DEVICE(s), "MAINCLK", NULL, NULL, 0); s->s32kclk = qdev_init_clock_in(DEVICE(s), "S32KCLK", NULL, NULL, 0); memory_region_init(&s->container, obj, "armsse-container", UINT64_MAX); @@ -XXX,XX +XXX,XX @@ static void armsse_realize(DeviceState *dev, Error **errp) * devices in the ARMSSE. */ sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->container); - - /* Set initial system_clock_scale from MAINCLK */ - armsse_mainclk_update(s, ClockUpdate); } static void armsse_idau_check(IDAUInterface *ii, uint32_t address, diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2.c +++ b/hw/arm/mps2.c @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) qdev_get_gpio_in(armv7m, mmc->fpga_type == FPGA_AN511 ? 47 : 13)); - system_clock_scale = NANOSECONDS_PER_SECOND / SYSCLK_FRQ; - armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, 0x400000); } diff --git a/hw/arm/msf2-soc.c b/hw/arm/msf2-soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/msf2-soc.c +++ b/hw/arm/msf2-soc.c @@ -XXX,XX +XXX,XX @@ static void m2sxxx_soc_realize(DeviceState *dev_soc, Error **errp) return; } - system_clock_scale = clock_ticks_to_ns(s->m3clk, 1); - for (i = 0; i < MSF2_NUM_UARTS; i++) { if (serial_hd(i)) { serial_mm_init(get_system_memory(), uart_addr[i], 2, diff --git a/hw/arm/netduino2.c b/hw/arm/netduino2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/netduino2.c +++ b/hw/arm/netduino2.c @@ -XXX,XX +XXX,XX @@ static void netduino2_init(MachineState *machine) DeviceState *dev; Clock *sysclk; - system_clock_scale = NANOSECONDS_PER_SECOND / SYSCLK_FRQ; - /* This clock doesn't need migration because it is fixed-frequency */ sysclk = clock_new(OBJECT(machine), "SYSCLK"); clock_set_hz(sysclk, SYSCLK_FRQ); diff --git a/hw/arm/netduinoplus2.c b/hw/arm/netduinoplus2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/netduinoplus2.c +++ b/hw/arm/netduinoplus2.c @@ -XXX,XX +XXX,XX @@ static void netduinoplus2_init(MachineState *machine) DeviceState *dev; Clock *sysclk; - system_clock_scale = NANOSECONDS_PER_SECOND / SYSCLK_FRQ; - /* This clock doesn't need migration because it is fixed-frequency */ sysclk = clock_new(OBJECT(machine), "SYSCLK"); clock_set_hz(sysclk, SYSCLK_FRQ); diff --git a/hw/arm/nrf51_soc.c b/hw/arm/nrf51_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/nrf51_soc.c +++ b/hw/arm/nrf51_soc.c @@ -XXX,XX +XXX,XX @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp) * will always provide one). */ - system_clock_scale = NANOSECONDS_PER_SECOND / HCLK_FRQ; - object_property_set_link(OBJECT(&s->cpu), "memory", OBJECT(&s->container), &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->cpu), errp)) { diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static bool ssys_use_rcc2(ssys_state *s) */ static void ssys_calculate_system_clock(ssys_state *s, bool propagate_clock) { + int period_ns; /* * SYSDIV field specifies divisor: 0 == /1, 1 == /2, etc. Input * clock is 200MHz, which is a period of 5 ns. Dividing the clock * frequency by X is the same as multiplying the period by X. */ if (ssys_use_rcc2(s)) { - system_clock_scale = 5 * (((s->rcc2 >> 23) & 0x3f) + 1); + period_ns = 5 * (((s->rcc2 >> 23) & 0x3f) + 1); } else { - system_clock_scale = 5 * (((s->rcc >> 23) & 0xf) + 1); + period_ns = 5 * (((s->rcc >> 23) & 0xf) + 1); } - clock_set_ns(s->sysclk, system_clock_scale); + clock_set_ns(s->sysclk, period_ns); if (propagate_clock) { clock_propagate(s->sysclk); } diff --git a/hw/arm/stm32vldiscovery.c b/hw/arm/stm32vldiscovery.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32vldiscovery.c +++ b/hw/arm/stm32vldiscovery.c @@ -XXX,XX +XXX,XX @@ static void stm32vldiscovery_init(MachineState *machine) DeviceState *dev; Clock *sysclk; - system_clock_scale = NANOSECONDS_PER_SECOND / SYSCLK_FRQ; - /* This clock doesn't need migration because it is fixed-frequency */ sysclk = clock_new(OBJECT(machine), "SYSCLK"); clock_set_hz(sysclk, SYSCLK_FRQ); diff --git a/hw/timer/armv7m_systick.c b/hw/timer/armv7m_systick.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/armv7m_systick.c +++ b/hw/timer/armv7m_systick.c @@ -XXX,XX +XXX,XX @@ #define SYSCALIB_SKEW (1U << 30) #define SYSCALIB_TENMS ((1U << 24) - 1) -int system_clock_scale; - static void systick_set_period_from_clock(SysTickState *s) { /* -- 2.20.1