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 First pullreq for 6.0: mostly my v8.1M work, plus some other bits and pieces. (I still have a lot of stuff in my to-review folder, which I may or may not get to before the Christmas break...) thanks -- PMM The following changes since commit 5e7b204dbfae9a562fc73684986f936b97f63877: Merge remote-tracking branch 'remotes/mst/tags/for_upstream' into staging (2020-12-09 20:08:54 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20201210 for you to fetch changes up to 71f916be1c7e9ede0e37d9cabc781b5a9e8638ff: hw/arm/armv7m: Correct typo in QOM object name (2020-12-10 11:44:56 +0000) ---------------------------------------------------------------- target-arm queue: * hw/arm/smmuv3: Fix up L1STD_SPAN decoding * xlnx-zynqmp: Support Xilinx ZynqMP CAN controllers * sbsa-ref: allow to use Cortex-A53/57/72 cpus * Various minor code cleanups * hw/intc/armv7m_nvic: Make all of system PPB range be RAZWI/BusFault * Implement more pieces of ARMv8.1M support ---------------------------------------------------------------- Alex Chen (4): i.MX25: Fix bad printf format specifiers i.MX31: Fix bad printf format specifiers i.MX6: Fix bad printf format specifiers i.MX6ul: Fix bad printf format specifiers Havard Skinnemoen (1): tests/qtest/npcm7xx_rng-test: dump random data on failure Kunkun Jiang (1): hw/arm/smmuv3: Fix up L1STD_SPAN decoding Marcin Juszkiewicz (1): sbsa-ref: allow to use Cortex-A53/57/72 cpus Peter Maydell (25): hw/intc/armv7m_nvic: Make all of system PPB range be RAZWI/BusFault target/arm: Implement v8.1M PXN extension target/arm: Don't clobber ID_PFR1.Security on M-profile cores target/arm: Implement VSCCLRM insn target/arm: Implement CLRM instruction target/arm: Enforce M-profile VMRS/VMSR register restrictions target/arm: Refactor M-profile VMSR/VMRS handling target/arm: Move general-use constant expanders up in translate.c target/arm: Implement VLDR/VSTR system register target/arm: Implement M-profile FPSCR_nzcvqc target/arm: Use new FPCR_NZCV_MASK constant target/arm: Factor out preserve-fp-state from full_vfp_access_check() target/arm: Implement FPCXT_S fp system register hw/intc/armv7m_nvic: Update FPDSCR masking for v8.1M target/arm: For v8.1M, always clear R0-R3, R12, APSR, EPSR on exception entry target/arm: In v8.1M, don't set HFSR.FORCED on vector table fetch failures target/arm: Implement v8.1M REVIDR register target/arm: Implement new v8.1M NOCP check for exception return target/arm: Implement new v8.1M VLLDM and VLSTM encodings hw/intc/armv7m_nvic: Support v8.1M CCR.TRD bit target/arm: Implement CCR_S.TRD behaviour for SG insns hw/intc/armv7m_nvic: Fix "return from inactive handler" check target/arm: Implement M-profile "minimal RAS implementation" hw/intc/armv7m_nvic: Implement read/write for RAS register block hw/arm/armv7m: Correct typo in QOM object name Vikram Garhwal (4): hw/net/can: Introduce Xilinx ZynqMP CAN controller xlnx-zynqmp: Connect Xilinx ZynqMP CAN controllers tests/qtest: Introduce tests for Xilinx ZynqMP CAN controller MAINTAINERS: Add maintainer entry for Xilinx ZynqMP CAN controller meson.build | 1 + hw/arm/smmuv3-internal.h | 2 +- hw/net/can/trace.h | 1 + include/hw/arm/xlnx-zynqmp.h | 8 + include/hw/intc/armv7m_nvic.h | 2 + include/hw/net/xlnx-zynqmp-can.h | 78 +++ target/arm/cpu.h | 46 ++ target/arm/m-nocp.decode | 10 +- target/arm/t32.decode | 10 +- target/arm/vfp.decode | 14 + hw/arm/armv7m.c | 4 +- hw/arm/sbsa-ref.c | 23 +- hw/arm/xlnx-zcu102.c | 20 + hw/arm/xlnx-zynqmp.c | 34 ++ hw/intc/armv7m_nvic.c | 246 ++++++-- hw/misc/imx25_ccm.c | 12 +- hw/misc/imx31_ccm.c | 14 +- hw/misc/imx6_ccm.c | 20 +- hw/misc/imx6_src.c | 2 +- hw/misc/imx6ul_ccm.c | 4 +- hw/misc/imx_ccm.c | 4 +- hw/net/can/xlnx-zynqmp-can.c | 1161 ++++++++++++++++++++++++++++++++++++++ target/arm/cpu.c | 5 +- target/arm/helper.c | 7 +- target/arm/m_helper.c | 130 ++++- target/arm/translate.c | 105 +++- tests/qtest/npcm7xx_rng-test.c | 12 + tests/qtest/xlnx-can-test.c | 360 ++++++++++++ MAINTAINERS | 8 + hw/Kconfig | 1 + hw/net/can/meson.build | 1 + hw/net/can/trace-events | 9 + target/arm/translate-vfp.c.inc | 511 ++++++++++++++++- tests/qtest/meson.build | 1 + 34 files changed, 2713 insertions(+), 153 deletions(-) create mode 100644 hw/net/can/trace.h create mode 100644 include/hw/net/xlnx-zynqmp-can.h create mode 100644 hw/net/can/xlnx-zynqmp-can.c create mode 100644 tests/qtest/xlnx-can-test.c create mode 100644 hw/net/can/trace-events From: Kunkun Jiang <jiangkunkun@huawei.com> Accroding to the SMMUv3 spec, the SPAN field of Level1 Stream Table Descriptor is 5 bits([4:0]). Fixes: 9bde7f0674f(hw/arm/smmuv3: Implement translate callback) Signed-off-by: Kunkun Jiang <jiangkunkun@huawei.com> Message-id: 20201124023711.1184-1-jiangkunkun@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Acked-by: Eric Auger <eric.auger@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/smmuv3-internal.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/arm/smmuv3-internal.h b/hw/arm/smmuv3-internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3-internal.h +++ b/hw/arm/smmuv3-internal.h @@ -XXX,XX +XXX,XX @@ static inline uint64_t l1std_l2ptr(STEDesc *desc) return hi << 32 | lo; } -#define L1STD_SPAN(stm) (extract32((stm)->word[0], 0, 4)) +#define L1STD_SPAN(stm) (extract32((stm)->word[0], 0, 5)) #endif -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> The Xilinx ZynqMP CAN controller is developed based on SocketCAN, QEMU CAN bus implementation. Bus connection and socketCAN connection for each CAN module can be set through command lines. Example for using single CAN: -object can-bus,id=canbus0 \ -machine xlnx-zcu102.canbus0=canbus0 \ -object can-host-socketcan,id=socketcan0,if=vcan0,canbus=canbus0 Example for connecting both CAN to same virtual CAN on host machine: -object can-bus,id=canbus0 -object can-bus,id=canbus1 \ -machine xlnx-zcu102.canbus0=canbus0 \ -machine xlnx-zcu102.canbus1=canbus1 \ -object can-host-socketcan,id=socketcan0,if=vcan0,canbus=canbus0 \ -object can-host-socketcan,id=socketcan1,if=vcan0,canbus=canbus1 To create virtual CAN on the host machine, please check the QEMU CAN docs: https://github.com/qemu/qemu/blob/master/docs/can.txt Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Message-id: 1605728926-352690-2-git-send-email-fnu.vikram@xilinx.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- meson.build | 1 + hw/net/can/trace.h | 1 + include/hw/net/xlnx-zynqmp-can.h | 78 ++ hw/net/can/xlnx-zynqmp-can.c | 1161 ++++++++++++++++++++++++++++++ hw/Kconfig | 1 + hw/net/can/meson.build | 1 + hw/net/can/trace-events | 9 + 7 files changed, 1252 insertions(+) create mode 100644 hw/net/can/trace.h create mode 100644 include/hw/net/xlnx-zynqmp-can.h create mode 100644 hw/net/can/xlnx-zynqmp-can.c create mode 100644 hw/net/can/trace-events diff --git a/meson.build b/meson.build index XXXXXXX..XXXXXXX 100644 --- a/meson.build +++ b/meson.build @@ -XXX,XX +XXX,XX @@ if have_system 'hw/misc', 'hw/misc/macio', 'hw/net', + 'hw/net/can', 'hw/nvram', 'hw/pci', 'hw/pci-host', diff --git a/hw/net/can/trace.h b/hw/net/can/trace.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/can/trace.h @@ -0,0 +1 @@ +#include "trace/trace-hw_net_can.h" diff --git a/include/hw/net/xlnx-zynqmp-can.h b/include/hw/net/xlnx-zynqmp-can.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/net/xlnx-zynqmp-can.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Xilinx ZynqMP CAN controller. + * + * Copyright (c) 2020 Xilinx Inc. + * + * Written-by: Vikram Garhwal<fnu.vikram@xilinx.com> + * + * Based on QEMU CAN Device emulation implemented by Jin Yang, Deniz Eren and + * Pavel Pisa. + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#ifndef XLNX_ZYNQMP_CAN_H +#define XLNX_ZYNQMP_CAN_H + +#include "hw/register.h" +#include "net/can_emu.h" +#include "net/can_host.h" +#include "qemu/fifo32.h" +#include "hw/ptimer.h" +#include "hw/qdev-clock.h" + +#define TYPE_XLNX_ZYNQMP_CAN "xlnx.zynqmp-can" + +#define XLNX_ZYNQMP_CAN(obj) \ + OBJECT_CHECK(XlnxZynqMPCANState, (obj), TYPE_XLNX_ZYNQMP_CAN) + +#define MAX_CAN_CTRLS 2 +#define XLNX_ZYNQMP_CAN_R_MAX (0x84 / 4) +#define MAILBOX_CAPACITY 64 +#define CAN_TIMER_MAX 0XFFFFUL +#define CAN_DEFAULT_CLOCK (24 * 1000 * 1000) + +/* Each CAN_FRAME will have 4 * 32bit size. */ +#define CAN_FRAME_SIZE 4 +#define RXFIFO_SIZE (MAILBOX_CAPACITY * CAN_FRAME_SIZE) + +typedef struct XlnxZynqMPCANState { + SysBusDevice parent_obj; + MemoryRegion iomem; + + qemu_irq irq; + + CanBusClientState bus_client; + CanBusState *canbus; + + struct { + uint32_t ext_clk_freq; + } cfg; + + RegisterInfo reg_info[XLNX_ZYNQMP_CAN_R_MAX]; + uint32_t regs[XLNX_ZYNQMP_CAN_R_MAX]; + + Fifo32 rx_fifo; + Fifo32 tx_fifo; + Fifo32 txhpb_fifo; + + ptimer_state *can_timer; +} XlnxZynqMPCANState; + +#endif diff --git a/hw/net/can/xlnx-zynqmp-can.c b/hw/net/can/xlnx-zynqmp-can.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/can/xlnx-zynqmp-can.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Xilinx ZynqMP CAN controller. + * This implementation is based on the following datasheet: + * https://www.xilinx.com/support/documentation/user_guides/ug1085-zynq-ultrascale-trm.pdf + * + * Copyright (c) 2020 Xilinx Inc. + * + * Written-by: Vikram Garhwal<fnu.vikram@xilinx.com> + * + * Based on QEMU CAN Device emulation implemented by Jin Yang, Deniz Eren and + * Pavel Pisa + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "hw/sysbus.h" +#include "hw/register.h" +#include "hw/irq.h" +#include "qapi/error.h" +#include "qemu/bitops.h" +#include "qemu/log.h" +#include "qemu/cutils.h" +#include "sysemu/sysemu.h" +#include "migration/vmstate.h" +#include "hw/qdev-properties.h" +#include "net/can_emu.h" +#include "net/can_host.h" +#include "qemu/event_notifier.h" +#include "qom/object_interfaces.h" +#include "hw/net/xlnx-zynqmp-can.h" +#include "trace.h" + +#ifndef XLNX_ZYNQMP_CAN_ERR_DEBUG +#define XLNX_ZYNQMP_CAN_ERR_DEBUG 0 +#endif + +#define MAX_DLC 8 +#undef ERROR + +REG32(SOFTWARE_RESET_REGISTER, 0x0) + FIELD(SOFTWARE_RESET_REGISTER, CEN, 1, 1) + FIELD(SOFTWARE_RESET_REGISTER, SRST, 0, 1) +REG32(MODE_SELECT_REGISTER, 0x4) + FIELD(MODE_SELECT_REGISTER, SNOOP, 2, 1) + FIELD(MODE_SELECT_REGISTER, LBACK, 1, 1) + FIELD(MODE_SELECT_REGISTER, SLEEP, 0, 1) +REG32(ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, 0x8) + FIELD(ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, BRP, 0, 8) +REG32(ARBITRATION_PHASE_BIT_TIMING_REGISTER, 0xc) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, SJW, 7, 2) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, TS2, 4, 3) + FIELD(ARBITRATION_PHASE_BIT_TIMING_REGISTER, TS1, 0, 4) +REG32(ERROR_COUNTER_REGISTER, 0x10) + FIELD(ERROR_COUNTER_REGISTER, REC, 8, 8) + FIELD(ERROR_COUNTER_REGISTER, TEC, 0, 8) +REG32(ERROR_STATUS_REGISTER, 0x14) + FIELD(ERROR_STATUS_REGISTER, ACKER, 4, 1) + FIELD(ERROR_STATUS_REGISTER, BERR, 3, 1) + FIELD(ERROR_STATUS_REGISTER, STER, 2, 1) + FIELD(ERROR_STATUS_REGISTER, FMER, 1, 1) + FIELD(ERROR_STATUS_REGISTER, CRCER, 0, 1) +REG32(STATUS_REGISTER, 0x18) + FIELD(STATUS_REGISTER, SNOOP, 12, 1) + FIELD(STATUS_REGISTER, ACFBSY, 11, 1) + FIELD(STATUS_REGISTER, TXFLL, 10, 1) + FIELD(STATUS_REGISTER, TXBFLL, 9, 1) + FIELD(STATUS_REGISTER, ESTAT, 7, 2) + FIELD(STATUS_REGISTER, ERRWRN, 6, 1) + FIELD(STATUS_REGISTER, BBSY, 5, 1) + FIELD(STATUS_REGISTER, BIDLE, 4, 1) + FIELD(STATUS_REGISTER, NORMAL, 3, 1) + FIELD(STATUS_REGISTER, SLEEP, 2, 1) + FIELD(STATUS_REGISTER, LBACK, 1, 1) + FIELD(STATUS_REGISTER, CONFIG, 0, 1) +REG32(INTERRUPT_STATUS_REGISTER, 0x1c) + FIELD(INTERRUPT_STATUS_REGISTER, TXFEMP, 14, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXFWMEMP, 13, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXFWMFLL, 12, 1) + FIELD(INTERRUPT_STATUS_REGISTER, WKUP, 11, 1) + FIELD(INTERRUPT_STATUS_REGISTER, SLP, 10, 1) + FIELD(INTERRUPT_STATUS_REGISTER, BSOFF, 9, 1) + FIELD(INTERRUPT_STATUS_REGISTER, ERROR, 8, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXNEMP, 7, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXOFLW, 6, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXUFLW, 5, 1) + FIELD(INTERRUPT_STATUS_REGISTER, RXOK, 4, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXBFLL, 3, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXFLL, 2, 1) + FIELD(INTERRUPT_STATUS_REGISTER, TXOK, 1, 1) + FIELD(INTERRUPT_STATUS_REGISTER, ARBLST, 0, 1) +REG32(INTERRUPT_ENABLE_REGISTER, 0x20) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXFEMP, 14, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXFWMEMP, 13, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXFWMFLL, 12, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EWKUP, 11, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ESLP, 10, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EBSOFF, 9, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EERROR, 8, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXNEMP, 7, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXOFLW, 6, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXUFLW, 5, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ERXOK, 4, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXBFLL, 3, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXFLL, 2, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, ETXOK, 1, 1) + FIELD(INTERRUPT_ENABLE_REGISTER, EARBLST, 0, 1) +REG32(INTERRUPT_CLEAR_REGISTER, 0x24) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXFEMP, 14, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXFWMEMP, 13, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXFWMFLL, 12, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CWKUP, 11, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CSLP, 10, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CBSOFF, 9, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CERROR, 8, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXNEMP, 7, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXOFLW, 6, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXUFLW, 5, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CRXOK, 4, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXBFLL, 3, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXFLL, 2, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CTXOK, 1, 1) + FIELD(INTERRUPT_CLEAR_REGISTER, CARBLST, 0, 1) +REG32(TIMESTAMP_REGISTER, 0x28) + FIELD(TIMESTAMP_REGISTER, CTS, 0, 1) +REG32(WIR, 0x2c) + FIELD(WIR, EW, 8, 8) + FIELD(WIR, FW, 0, 8) +REG32(TXFIFO_ID, 0x30) + FIELD(TXFIFO_ID, IDH, 21, 11) + FIELD(TXFIFO_ID, SRRRTR, 20, 1) + FIELD(TXFIFO_ID, IDE, 19, 1) + FIELD(TXFIFO_ID, IDL, 1, 18) + FIELD(TXFIFO_ID, RTR, 0, 1) +REG32(TXFIFO_DLC, 0x34) + FIELD(TXFIFO_DLC, DLC, 28, 4) +REG32(TXFIFO_DATA1, 0x38) + FIELD(TXFIFO_DATA1, DB0, 24, 8) + FIELD(TXFIFO_DATA1, DB1, 16, 8) + FIELD(TXFIFO_DATA1, DB2, 8, 8) + FIELD(TXFIFO_DATA1, DB3, 0, 8) +REG32(TXFIFO_DATA2, 0x3c) + FIELD(TXFIFO_DATA2, DB4, 24, 8) + FIELD(TXFIFO_DATA2, DB5, 16, 8) + FIELD(TXFIFO_DATA2, DB6, 8, 8) + FIELD(TXFIFO_DATA2, DB7, 0, 8) +REG32(TXHPB_ID, 0x40) + FIELD(TXHPB_ID, IDH, 21, 11) + FIELD(TXHPB_ID, SRRRTR, 20, 1) + FIELD(TXHPB_ID, IDE, 19, 1) + FIELD(TXHPB_ID, IDL, 1, 18) + FIELD(TXHPB_ID, RTR, 0, 1) +REG32(TXHPB_DLC, 0x44) + FIELD(TXHPB_DLC, DLC, 28, 4) +REG32(TXHPB_DATA1, 0x48) + FIELD(TXHPB_DATA1, DB0, 24, 8) + FIELD(TXHPB_DATA1, DB1, 16, 8) + FIELD(TXHPB_DATA1, DB2, 8, 8) + FIELD(TXHPB_DATA1, DB3, 0, 8) +REG32(TXHPB_DATA2, 0x4c) + FIELD(TXHPB_DATA2, DB4, 24, 8) + FIELD(TXHPB_DATA2, DB5, 16, 8) + FIELD(TXHPB_DATA2, DB6, 8, 8) + FIELD(TXHPB_DATA2, DB7, 0, 8) +REG32(RXFIFO_ID, 0x50) + FIELD(RXFIFO_ID, IDH, 21, 11) + FIELD(RXFIFO_ID, SRRRTR, 20, 1) + FIELD(RXFIFO_ID, IDE, 19, 1) + FIELD(RXFIFO_ID, IDL, 1, 18) + FIELD(RXFIFO_ID, RTR, 0, 1) +REG32(RXFIFO_DLC, 0x54) + FIELD(RXFIFO_DLC, DLC, 28, 4) + FIELD(RXFIFO_DLC, RXT, 0, 16) +REG32(RXFIFO_DATA1, 0x58) + FIELD(RXFIFO_DATA1, DB0, 24, 8) + FIELD(RXFIFO_DATA1, DB1, 16, 8) + FIELD(RXFIFO_DATA1, DB2, 8, 8) + FIELD(RXFIFO_DATA1, DB3, 0, 8) +REG32(RXFIFO_DATA2, 0x5c) + FIELD(RXFIFO_DATA2, DB4, 24, 8) + FIELD(RXFIFO_DATA2, DB5, 16, 8) + FIELD(RXFIFO_DATA2, DB6, 8, 8) + FIELD(RXFIFO_DATA2, DB7, 0, 8) +REG32(AFR, 0x60) + FIELD(AFR, UAF4, 3, 1) + FIELD(AFR, UAF3, 2, 1) + FIELD(AFR, UAF2, 1, 1) + FIELD(AFR, UAF1, 0, 1) +REG32(AFMR1, 0x64) + FIELD(AFMR1, AMIDH, 21, 11) + FIELD(AFMR1, AMSRR, 20, 1) + FIELD(AFMR1, AMIDE, 19, 1) + FIELD(AFMR1, AMIDL, 1, 18) + FIELD(AFMR1, AMRTR, 0, 1) +REG32(AFIR1, 0x68) + FIELD(AFIR1, AIIDH, 21, 11) + FIELD(AFIR1, AISRR, 20, 1) + FIELD(AFIR1, AIIDE, 19, 1) + FIELD(AFIR1, AIIDL, 1, 18) + FIELD(AFIR1, AIRTR, 0, 1) +REG32(AFMR2, 0x6c) + FIELD(AFMR2, AMIDH, 21, 11) + FIELD(AFMR2, AMSRR, 20, 1) + FIELD(AFMR2, AMIDE, 19, 1) + FIELD(AFMR2, AMIDL, 1, 18) + FIELD(AFMR2, AMRTR, 0, 1) +REG32(AFIR2, 0x70) + FIELD(AFIR2, AIIDH, 21, 11) + FIELD(AFIR2, AISRR, 20, 1) + FIELD(AFIR2, AIIDE, 19, 1) + FIELD(AFIR2, AIIDL, 1, 18) + FIELD(AFIR2, AIRTR, 0, 1) +REG32(AFMR3, 0x74) + FIELD(AFMR3, AMIDH, 21, 11) + FIELD(AFMR3, AMSRR, 20, 1) + FIELD(AFMR3, AMIDE, 19, 1) + FIELD(AFMR3, AMIDL, 1, 18) + FIELD(AFMR3, AMRTR, 0, 1) +REG32(AFIR3, 0x78) + FIELD(AFIR3, AIIDH, 21, 11) + FIELD(AFIR3, AISRR, 20, 1) + FIELD(AFIR3, AIIDE, 19, 1) + FIELD(AFIR3, AIIDL, 1, 18) + FIELD(AFIR3, AIRTR, 0, 1) +REG32(AFMR4, 0x7c) + FIELD(AFMR4, AMIDH, 21, 11) + FIELD(AFMR4, AMSRR, 20, 1) + FIELD(AFMR4, AMIDE, 19, 1) + FIELD(AFMR4, AMIDL, 1, 18) + FIELD(AFMR4, AMRTR, 0, 1) +REG32(AFIR4, 0x80) + FIELD(AFIR4, AIIDH, 21, 11) + FIELD(AFIR4, AISRR, 20, 1) + FIELD(AFIR4, AIIDE, 19, 1) + FIELD(AFIR4, AIIDL, 1, 18) + FIELD(AFIR4, AIRTR, 0, 1) + +static void can_update_irq(XlnxZynqMPCANState *s) +{ + uint32_t irq; + + /* Watermark register interrupts. */ + if ((fifo32_num_free(&s->tx_fifo) / CAN_FRAME_SIZE) > + ARRAY_FIELD_EX32(s->regs, WIR, EW)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXFWMEMP, 1); + } + + if ((fifo32_num_used(&s->rx_fifo) / CAN_FRAME_SIZE) > + ARRAY_FIELD_EX32(s->regs, WIR, FW)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXFWMFLL, 1); + } + + /* RX Interrupts. */ + if (fifo32_num_used(&s->rx_fifo) >= CAN_FRAME_SIZE) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXNEMP, 1); + } + + /* TX interrupts. */ + if (fifo32_is_empty(&s->tx_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXFEMP, 1); + } + + if (fifo32_is_full(&s->tx_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXFLL, 1); + } + + if (fifo32_is_full(&s->txhpb_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXBFLL, 1); + } + + irq = s->regs[R_INTERRUPT_STATUS_REGISTER]; + irq &= s->regs[R_INTERRUPT_ENABLE_REGISTER]; + + trace_xlnx_can_update_irq(s->regs[R_INTERRUPT_STATUS_REGISTER], + s->regs[R_INTERRUPT_ENABLE_REGISTER], irq); + qemu_set_irq(s->irq, irq); +} + +static void can_ier_post_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + can_update_irq(s); +} + +static uint64_t can_icr_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + s->regs[R_INTERRUPT_STATUS_REGISTER] &= ~val; + can_update_irq(s); + + return 0; +} + +static void can_config_reset(XlnxZynqMPCANState *s) +{ + /* Reset all the configuration registers. */ + register_reset(&s->reg_info[R_SOFTWARE_RESET_REGISTER]); + register_reset(&s->reg_info[R_MODE_SELECT_REGISTER]); + register_reset( + &s->reg_info[R_ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER]); + register_reset(&s->reg_info[R_ARBITRATION_PHASE_BIT_TIMING_REGISTER]); + register_reset(&s->reg_info[R_STATUS_REGISTER]); + register_reset(&s->reg_info[R_INTERRUPT_STATUS_REGISTER]); + register_reset(&s->reg_info[R_INTERRUPT_ENABLE_REGISTER]); + register_reset(&s->reg_info[R_INTERRUPT_CLEAR_REGISTER]); + register_reset(&s->reg_info[R_WIR]); +} + +static void can_config_mode(XlnxZynqMPCANState *s) +{ + register_reset(&s->reg_info[R_ERROR_COUNTER_REGISTER]); + register_reset(&s->reg_info[R_ERROR_STATUS_REGISTER]); + + /* Put XlnxZynqMPCAN in configuration mode. */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, CONFIG, 1); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, WKUP, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, SLP, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, BSOFF, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, ERROR, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOFLW, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOK, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXOK, 0); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, ARBLST, 0); + + can_update_irq(s); +} + +static void update_status_register_mode_bits(XlnxZynqMPCANState *s) +{ + bool sleep_status = ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP); + bool sleep_mode = ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SLEEP); + /* Wake up interrupt bit. */ + bool wakeup_irq_val = sleep_status && (sleep_mode == 0); + /* Sleep interrupt bit. */ + bool sleep_irq_val = sleep_mode && (sleep_status == 0); + + /* Clear previous core mode status bits. */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, LBACK, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SLEEP, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SNOOP, 0); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, NORMAL, 0); + + /* set current mode bit and generate irqs accordingly. */ + if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, LBACK)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, LBACK, 1); + } else if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SLEEP)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SLEEP, 1); + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, SLP, + sleep_irq_val); + } else if (ARRAY_FIELD_EX32(s->regs, MODE_SELECT_REGISTER, SNOOP)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, SNOOP, 1); + } else { + /* + * If all bits are zero then XlnxZynqMPCAN is set in normal mode. + */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, NORMAL, 1); + /* Set wakeup interrupt bit. */ + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, WKUP, + wakeup_irq_val); + } + + can_update_irq(s); +} + +static void can_exit_sleep_mode(XlnxZynqMPCANState *s) +{ + ARRAY_FIELD_DP32(s->regs, MODE_SELECT_REGISTER, SLEEP, 0); + update_status_register_mode_bits(s); +} + +static void generate_frame(qemu_can_frame *frame, uint32_t *data) +{ + frame->can_id = data[0]; + frame->can_dlc = FIELD_EX32(data[1], TXFIFO_DLC, DLC); + + frame->data[0] = FIELD_EX32(data[2], TXFIFO_DATA1, DB3); + frame->data[1] = FIELD_EX32(data[2], TXFIFO_DATA1, DB2); + frame->data[2] = FIELD_EX32(data[2], TXFIFO_DATA1, DB1); + frame->data[3] = FIELD_EX32(data[2], TXFIFO_DATA1, DB0); + + frame->data[4] = FIELD_EX32(data[3], TXFIFO_DATA2, DB7); + frame->data[5] = FIELD_EX32(data[3], TXFIFO_DATA2, DB6); + frame->data[6] = FIELD_EX32(data[3], TXFIFO_DATA2, DB5); + frame->data[7] = FIELD_EX32(data[3], TXFIFO_DATA2, DB4); +} + +static bool tx_ready_check(XlnxZynqMPCANState *s) +{ + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, SRST)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer data while" + " data while controller is in reset mode.\n", + path); + return false; + } + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer" + " data while controller is in configuration mode. Reset" + " the core so operations can start fresh.\n", + path); + return false; + } + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SNOOP)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to transfer" + " data while controller is in SNOOP MODE.\n", + path); + return false; + } + + return true; +} + +static void transfer_fifo(XlnxZynqMPCANState *s, Fifo32 *fifo) +{ + qemu_can_frame frame; + uint32_t data[CAN_FRAME_SIZE]; + int i; + bool can_tx = tx_ready_check(s); + + if (!can_tx) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Controller is not enabled for data" + " transfer.\n", path); + can_update_irq(s); + return; + } + + while (!fifo32_is_empty(fifo)) { + for (i = 0; i < CAN_FRAME_SIZE; i++) { + data[i] = fifo32_pop(fifo); + } + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, LBACK)) { + /* + * Controller is in loopback. In Loopback mode, the CAN core + * transmits a recessive bitstream on to the XlnxZynqMPCAN Bus. + * Any message transmitted is looped back to the RX line and + * acknowledged. The XlnxZynqMPCAN core receives any message + * that it transmits. + */ + if (fifo32_is_full(&s->rx_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOFLW, 1); + } else { + for (i = 0; i < CAN_FRAME_SIZE; i++) { + fifo32_push(&s->rx_fifo, data[i]); + } + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOK, 1); + } + } else { + /* Normal mode Tx. */ + generate_frame(&frame, data); + + trace_xlnx_can_tx_data(frame.can_id, frame.can_dlc, + frame.data[0], frame.data[1], + frame.data[2], frame.data[3], + frame.data[4], frame.data[5], + frame.data[6], frame.data[7]); + can_bus_client_send(&s->bus_client, &frame, 1); + } + } + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, TXOK, 1); + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, TXBFLL, 0); + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP)) { + can_exit_sleep_mode(s); + } + + can_update_irq(s); +} + +static uint64_t can_srr_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + ARRAY_FIELD_DP32(s->regs, SOFTWARE_RESET_REGISTER, CEN, + FIELD_EX32(val, SOFTWARE_RESET_REGISTER, CEN)); + + if (FIELD_EX32(val, SOFTWARE_RESET_REGISTER, SRST)) { + trace_xlnx_can_reset(val); + + /* First, core will do software reset then will enter in config mode. */ + can_config_reset(s); + } + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + can_config_mode(s); + } else { + /* + * Leave config mode. Now XlnxZynqMPCAN core will enter normal, + * sleep, snoop or loopback mode depending upon LBACK, SLEEP, SNOOP + * register states. + */ + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, CONFIG, 0); + + ptimer_transaction_begin(s->can_timer); + ptimer_set_count(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); + + /* XlnxZynqMPCAN is out of config mode. It will send pending data. */ + transfer_fifo(s, &s->txhpb_fifo); + transfer_fifo(s, &s->tx_fifo); + } + + update_status_register_mode_bits(s); + + return s->regs[R_SOFTWARE_RESET_REGISTER]; +} + +static uint64_t can_msr_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint8_t multi_mode; + + /* + * Multiple mode set check. This is done to make sure user doesn't set + * multiple modes. + */ + multi_mode = FIELD_EX32(val, MODE_SELECT_REGISTER, LBACK) + + FIELD_EX32(val, MODE_SELECT_REGISTER, SLEEP) + + FIELD_EX32(val, MODE_SELECT_REGISTER, SNOOP); + + if (multi_mode > 1) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to config" + " several modes simultaneously. One mode will be selected" + " according to their priority: LBACK > SLEEP > SNOOP.\n", + path); + } + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN) == 0) { + /* We are in configuration mode, any mode can be selected. */ + s->regs[R_MODE_SELECT_REGISTER] = val; + } else { + bool sleep_mode_bit = FIELD_EX32(val, MODE_SELECT_REGISTER, SLEEP); + + ARRAY_FIELD_DP32(s->regs, MODE_SELECT_REGISTER, SLEEP, sleep_mode_bit); + + if (FIELD_EX32(val, MODE_SELECT_REGISTER, LBACK)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to set" + " LBACK mode without setting CEN bit as 0.\n", + path); + } else if (FIELD_EX32(val, MODE_SELECT_REGISTER, SNOOP)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Attempting to set" + " SNOOP mode without setting CEN bit as 0.\n", + path); + } + + update_status_register_mode_bits(s); + } + + return s->regs[R_MODE_SELECT_REGISTER]; +} + +static uint64_t can_brpr_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + /* Only allow writes when in config mode. */ + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) { + return s->regs[R_ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER]; + } + + return val; +} + +static uint64_t can_btr_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + /* Only allow writes when in config mode. */ + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) { + return s->regs[R_ARBITRATION_PHASE_BIT_TIMING_REGISTER]; + } + + return val; +} + +static uint64_t can_tcr_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + if (FIELD_EX32(val, TIMESTAMP_REGISTER, CTS)) { + ptimer_transaction_begin(s->can_timer); + ptimer_set_count(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); + } + + return 0; +} + +static void update_rx_fifo(XlnxZynqMPCANState *s, const qemu_can_frame *frame) +{ + bool filter_pass = false; + uint16_t timestamp = 0; + + /* If no filter is enabled. Message will be stored in FIFO. */ + if (!((ARRAY_FIELD_EX32(s->regs, AFR, UAF1)) | + (ARRAY_FIELD_EX32(s->regs, AFR, UAF2)) | + (ARRAY_FIELD_EX32(s->regs, AFR, UAF3)) | + (ARRAY_FIELD_EX32(s->regs, AFR, UAF4)))) { + filter_pass = true; + } + + /* + * Messages that pass any of the acceptance filters will be stored in + * the RX FIFO. + */ + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF1)) { + uint32_t id_masked = s->regs[R_AFMR1] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR1] & s->regs[R_AFIR1]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF2)) { + uint32_t id_masked = s->regs[R_AFMR2] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR2] & s->regs[R_AFIR2]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF3)) { + uint32_t id_masked = s->regs[R_AFMR3] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR3] & s->regs[R_AFIR3]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF4)) { + uint32_t id_masked = s->regs[R_AFMR4] & frame->can_id; + uint32_t filter_id_masked = s->regs[R_AFMR4] & s->regs[R_AFIR4]; + + if (filter_id_masked == id_masked) { + filter_pass = true; + } + } + + if (!filter_pass) { + trace_xlnx_can_rx_fifo_filter_reject(frame->can_id, frame->can_dlc); + return; + } + + /* Store the message in fifo if it passed through any of the filters. */ + if (filter_pass && frame->can_dlc <= MAX_DLC) { + + if (fifo32_is_full(&s->rx_fifo)) { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOFLW, 1); + } else { + timestamp = CAN_TIMER_MAX - ptimer_get_count(s->can_timer); + + fifo32_push(&s->rx_fifo, frame->can_id); + + fifo32_push(&s->rx_fifo, deposit32(0, R_RXFIFO_DLC_DLC_SHIFT, + R_RXFIFO_DLC_DLC_LENGTH, + frame->can_dlc) | + deposit32(0, R_RXFIFO_DLC_RXT_SHIFT, + R_RXFIFO_DLC_RXT_LENGTH, + timestamp)); + + /* First 32 bit of the data. */ + fifo32_push(&s->rx_fifo, deposit32(0, R_TXFIFO_DATA1_DB3_SHIFT, + R_TXFIFO_DATA1_DB3_LENGTH, + frame->data[0]) | + deposit32(0, R_TXFIFO_DATA1_DB2_SHIFT, + R_TXFIFO_DATA1_DB2_LENGTH, + frame->data[1]) | + deposit32(0, R_TXFIFO_DATA1_DB1_SHIFT, + R_TXFIFO_DATA1_DB1_LENGTH, + frame->data[2]) | + deposit32(0, R_TXFIFO_DATA1_DB0_SHIFT, + R_TXFIFO_DATA1_DB0_LENGTH, + frame->data[3])); + /* Last 32 bit of the data. */ + fifo32_push(&s->rx_fifo, deposit32(0, R_TXFIFO_DATA2_DB7_SHIFT, + R_TXFIFO_DATA2_DB7_LENGTH, + frame->data[4]) | + deposit32(0, R_TXFIFO_DATA2_DB6_SHIFT, + R_TXFIFO_DATA2_DB6_LENGTH, + frame->data[5]) | + deposit32(0, R_TXFIFO_DATA2_DB5_SHIFT, + R_TXFIFO_DATA2_DB5_LENGTH, + frame->data[6]) | + deposit32(0, R_TXFIFO_DATA2_DB4_SHIFT, + R_TXFIFO_DATA2_DB4_LENGTH, + frame->data[7])); + + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXOK, 1); + trace_xlnx_can_rx_data(frame->can_id, frame->can_dlc, + frame->data[0], frame->data[1], + frame->data[2], frame->data[3], + frame->data[4], frame->data[5], + frame->data[6], frame->data[7]); + } + + can_update_irq(s); + } +} + +static uint64_t can_rxfifo_pre_read(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + if (!fifo32_is_empty(&s->rx_fifo)) { + val = fifo32_pop(&s->rx_fifo); + } else { + ARRAY_FIELD_DP32(s->regs, INTERRUPT_STATUS_REGISTER, RXUFLW, 1); + } + + can_update_irq(s); + return val; +} + +static void can_filter_enable_post_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + if (ARRAY_FIELD_EX32(s->regs, AFR, UAF1) && + ARRAY_FIELD_EX32(s->regs, AFR, UAF2) && + ARRAY_FIELD_EX32(s->regs, AFR, UAF3) && + ARRAY_FIELD_EX32(s->regs, AFR, UAF4)) { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, ACFBSY, 1); + } else { + ARRAY_FIELD_DP32(s->regs, STATUS_REGISTER, ACFBSY, 0); + } +} + +static uint64_t can_filter_mask_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t reg_idx = (reg->access->addr) / 4; + uint32_t filter_number = (reg_idx - R_AFMR1) / 2; + + /* modify an acceptance filter, the corresponding UAF bit should be '0'. */ + if (!(s->regs[R_AFR] & (1 << filter_number))) { + s->regs[reg_idx] = val; + + trace_xlnx_can_filter_mask_pre_write(filter_number, s->regs[reg_idx]); + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Acceptance filter %d" + " mask is not set as corresponding UAF bit is not 0.\n", + path, filter_number + 1); + } + + return s->regs[reg_idx]; +} + +static uint64_t can_filter_id_pre_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + uint32_t reg_idx = (reg->access->addr) / 4; + uint32_t filter_number = (reg_idx - R_AFIR1) / 2; + + if (!(s->regs[R_AFR] & (1 << filter_number))) { + s->regs[reg_idx] = val; + + trace_xlnx_can_filter_id_pre_write(filter_number, s->regs[reg_idx]); + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Acceptance filter %d" + " id is not set as corresponding UAF bit is not 0.\n", + path, filter_number + 1); + } + + return s->regs[reg_idx]; +} + +static void can_tx_post_write(RegisterInfo *reg, uint64_t val) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(reg->opaque); + + bool is_txhpb = reg->access->addr > A_TXFIFO_DATA2; + + bool initiate_transfer = (reg->access->addr == A_TXFIFO_DATA2) || + (reg->access->addr == A_TXHPB_DATA2); + + Fifo32 *f = is_txhpb ? &s->txhpb_fifo : &s->tx_fifo; + + if (!fifo32_is_full(f)) { + fifo32_push(f, val); + } else { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: TX FIFO is full.\n", path); + } + + /* Initiate the message send if TX register is written. */ + if (initiate_transfer && + ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) { + transfer_fifo(s, f); + } + + can_update_irq(s); +} + +static const RegisterAccessInfo can_regs_info[] = { + { .name = "SOFTWARE_RESET_REGISTER", + .addr = A_SOFTWARE_RESET_REGISTER, + .rsvd = 0xfffffffc, + .pre_write = can_srr_pre_write, + },{ .name = "MODE_SELECT_REGISTER", + .addr = A_MODE_SELECT_REGISTER, + .rsvd = 0xfffffff8, + .pre_write = can_msr_pre_write, + },{ .name = "ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER", + .addr = A_ARBITRATION_PHASE_BAUD_RATE_PRESCALER_REGISTER, + .rsvd = 0xffffff00, + .pre_write = can_brpr_pre_write, + },{ .name = "ARBITRATION_PHASE_BIT_TIMING_REGISTER", + .addr = A_ARBITRATION_PHASE_BIT_TIMING_REGISTER, + .rsvd = 0xfffffe00, + .pre_write = can_btr_pre_write, + },{ .name = "ERROR_COUNTER_REGISTER", + .addr = A_ERROR_COUNTER_REGISTER, + .rsvd = 0xffff0000, + .ro = 0xffffffff, + },{ .name = "ERROR_STATUS_REGISTER", + .addr = A_ERROR_STATUS_REGISTER, + .rsvd = 0xffffffe0, + .w1c = 0x1f, + },{ .name = "STATUS_REGISTER", .addr = A_STATUS_REGISTER, + .reset = 0x1, + .rsvd = 0xffffe000, + .ro = 0x1fff, + },{ .name = "INTERRUPT_STATUS_REGISTER", + .addr = A_INTERRUPT_STATUS_REGISTER, + .reset = 0x6000, + .rsvd = 0xffff8000, + .ro = 0x7fff, + },{ .name = "INTERRUPT_ENABLE_REGISTER", + .addr = A_INTERRUPT_ENABLE_REGISTER, + .rsvd = 0xffff8000, + .post_write = can_ier_post_write, + },{ .name = "INTERRUPT_CLEAR_REGISTER", + .addr = A_INTERRUPT_CLEAR_REGISTER, + .rsvd = 0xffff8000, + .pre_write = can_icr_pre_write, + },{ .name = "TIMESTAMP_REGISTER", + .addr = A_TIMESTAMP_REGISTER, + .rsvd = 0xfffffffe, + .pre_write = can_tcr_pre_write, + },{ .name = "WIR", .addr = A_WIR, + .reset = 0x3f3f, + .rsvd = 0xffff0000, + },{ .name = "TXFIFO_ID", .addr = A_TXFIFO_ID, + .post_write = can_tx_post_write, + },{ .name = "TXFIFO_DLC", .addr = A_TXFIFO_DLC, + .rsvd = 0xfffffff, + .post_write = can_tx_post_write, + },{ .name = "TXFIFO_DATA1", .addr = A_TXFIFO_DATA1, + .post_write = can_tx_post_write, + },{ .name = "TXFIFO_DATA2", .addr = A_TXFIFO_DATA2, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_ID", .addr = A_TXHPB_ID, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_DLC", .addr = A_TXHPB_DLC, + .rsvd = 0xfffffff, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_DATA1", .addr = A_TXHPB_DATA1, + .post_write = can_tx_post_write, + },{ .name = "TXHPB_DATA2", .addr = A_TXHPB_DATA2, + .post_write = can_tx_post_write, + },{ .name = "RXFIFO_ID", .addr = A_RXFIFO_ID, + .ro = 0xffffffff, + .post_read = can_rxfifo_pre_read, + },{ .name = "RXFIFO_DLC", .addr = A_RXFIFO_DLC, + .rsvd = 0xfff0000, + .post_read = can_rxfifo_pre_read, + },{ .name = "RXFIFO_DATA1", .addr = A_RXFIFO_DATA1, + .post_read = can_rxfifo_pre_read, + },{ .name = "RXFIFO_DATA2", .addr = A_RXFIFO_DATA2, + .post_read = can_rxfifo_pre_read, + },{ .name = "AFR", .addr = A_AFR, + .rsvd = 0xfffffff0, + .post_write = can_filter_enable_post_write, + },{ .name = "AFMR1", .addr = A_AFMR1, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR1", .addr = A_AFIR1, + .pre_write = can_filter_id_pre_write, + },{ .name = "AFMR2", .addr = A_AFMR2, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR2", .addr = A_AFIR2, + .pre_write = can_filter_id_pre_write, + },{ .name = "AFMR3", .addr = A_AFMR3, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR3", .addr = A_AFIR3, + .pre_write = can_filter_id_pre_write, + },{ .name = "AFMR4", .addr = A_AFMR4, + .pre_write = can_filter_mask_pre_write, + },{ .name = "AFIR4", .addr = A_AFIR4, + .pre_write = can_filter_id_pre_write, + } +}; + +static void xlnx_zynqmp_can_ptimer_cb(void *opaque) +{ + /* No action required on the timer rollover. */ +} + +static const MemoryRegionOps can_ops = { + .read = register_read_memory, + .write = register_write_memory, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void xlnx_zynqmp_can_reset_init(Object *obj, ResetType type) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(obj); + unsigned int i; + + for (i = R_RXFIFO_ID; i < ARRAY_SIZE(s->reg_info); ++i) { + register_reset(&s->reg_info[i]); + } + + ptimer_transaction_begin(s->can_timer); + ptimer_set_count(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); +} + +static void xlnx_zynqmp_can_reset_hold(Object *obj) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(obj); + unsigned int i; + + for (i = 0; i < R_RXFIFO_ID; ++i) { + register_reset(&s->reg_info[i]); + } + + /* + * Reset FIFOs when CAN model is reset. This will clear the fifo writes + * done by post_write which gets called from register_reset function, + * post_write handle will not be able to trigger tx because CAN will be + * disabled when software_reset_register is cleared first. + */ + fifo32_reset(&s->rx_fifo); + fifo32_reset(&s->tx_fifo); + fifo32_reset(&s->txhpb_fifo); +} + +static bool xlnx_zynqmp_can_can_receive(CanBusClientState *client) +{ + XlnxZynqMPCANState *s = container_of(client, XlnxZynqMPCANState, + bus_client); + + if (ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, SRST)) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Controller is in reset state.\n", + path); + return false; + } + + if ((ARRAY_FIELD_EX32(s->regs, SOFTWARE_RESET_REGISTER, CEN)) == 0) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Controller is disabled. Incoming" + " messages will be discarded.\n", path); + return false; + } + + return true; +} + +static ssize_t xlnx_zynqmp_can_receive(CanBusClientState *client, + const qemu_can_frame *buf, size_t buf_size) { + XlnxZynqMPCANState *s = container_of(client, XlnxZynqMPCANState, + bus_client); + const qemu_can_frame *frame = buf; + + if (buf_size <= 0) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + qemu_log_mask(LOG_GUEST_ERROR, "%s: Error in the data received.\n", + path); + return 0; + } + + if (ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SNOOP)) { + /* Snoop Mode: Just keep the data. no response back. */ + update_rx_fifo(s, frame); + } else if ((ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP))) { + /* + * XlnxZynqMPCAN is in sleep mode. Any data on bus will bring it to wake + * up state. + */ + can_exit_sleep_mode(s); + update_rx_fifo(s, frame); + } else if ((ARRAY_FIELD_EX32(s->regs, STATUS_REGISTER, SLEEP)) == 0) { + update_rx_fifo(s, frame); + } else { + /* + * XlnxZynqMPCAN will not participate in normal bus communication + * and will not receive any messages transmitted by other CAN nodes. + */ + trace_xlnx_can_rx_discard(s->regs[R_STATUS_REGISTER]); + } + + return 1; +} + +static CanBusClientInfo can_xilinx_bus_client_info = { + .can_receive = xlnx_zynqmp_can_can_receive, + .receive = xlnx_zynqmp_can_receive, +}; + +static int xlnx_zynqmp_can_connect_to_bus(XlnxZynqMPCANState *s, + CanBusState *bus) +{ + s->bus_client.info = &can_xilinx_bus_client_info; + + if (can_bus_insert_client(bus, &s->bus_client) < 0) { + return -1; + } + return 0; +} + +static void xlnx_zynqmp_can_realize(DeviceState *dev, Error **errp) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(dev); + + if (s->canbus) { + if (xlnx_zynqmp_can_connect_to_bus(s, s->canbus) < 0) { + g_autofree char *path = object_get_canonical_path(OBJECT(s)); + + error_setg(errp, "%s: xlnx_zynqmp_can_connect_to_bus" + " failed.", path); + return; + } + } + + /* Create RX FIFO, TXFIFO, TXHPB storage. */ + fifo32_create(&s->rx_fifo, RXFIFO_SIZE); + fifo32_create(&s->tx_fifo, RXFIFO_SIZE); + fifo32_create(&s->txhpb_fifo, CAN_FRAME_SIZE); + + /* Allocate a new timer. */ + s->can_timer = ptimer_init(xlnx_zynqmp_can_ptimer_cb, s, + PTIMER_POLICY_DEFAULT); + + ptimer_transaction_begin(s->can_timer); + + ptimer_set_freq(s->can_timer, s->cfg.ext_clk_freq); + ptimer_set_limit(s->can_timer, CAN_TIMER_MAX, 1); + ptimer_run(s->can_timer, 0); + ptimer_transaction_commit(s->can_timer); +} + +static void xlnx_zynqmp_can_init(Object *obj) +{ + XlnxZynqMPCANState *s = XLNX_ZYNQMP_CAN(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + + RegisterInfoArray *reg_array; + + memory_region_init(&s->iomem, obj, TYPE_XLNX_ZYNQMP_CAN, + XLNX_ZYNQMP_CAN_R_MAX * 4); + reg_array = register_init_block32(DEVICE(obj), can_regs_info, + ARRAY_SIZE(can_regs_info), + s->reg_info, s->regs, + &can_ops, + XLNX_ZYNQMP_CAN_ERR_DEBUG, + XLNX_ZYNQMP_CAN_R_MAX * 4); + + memory_region_add_subregion(&s->iomem, 0x00, &reg_array->mem); + sysbus_init_mmio(sbd, &s->iomem); + sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq); +} + +static const VMStateDescription vmstate_can = { + .name = TYPE_XLNX_ZYNQMP_CAN, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_FIFO32(rx_fifo, XlnxZynqMPCANState), + VMSTATE_FIFO32(tx_fifo, XlnxZynqMPCANState), + VMSTATE_FIFO32(txhpb_fifo, XlnxZynqMPCANState), + VMSTATE_UINT32_ARRAY(regs, XlnxZynqMPCANState, XLNX_ZYNQMP_CAN_R_MAX), + VMSTATE_PTIMER(can_timer, XlnxZynqMPCANState), + VMSTATE_END_OF_LIST(), + } +}; + +static Property xlnx_zynqmp_can_properties[] = { + DEFINE_PROP_UINT32("ext_clk_freq", XlnxZynqMPCANState, cfg.ext_clk_freq, + CAN_DEFAULT_CLOCK), + DEFINE_PROP_LINK("canbus", XlnxZynqMPCANState, canbus, TYPE_CAN_BUS, + CanBusState *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void xlnx_zynqmp_can_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.enter = xlnx_zynqmp_can_reset_init; + rc->phases.hold = xlnx_zynqmp_can_reset_hold; + dc->realize = xlnx_zynqmp_can_realize; + device_class_set_props(dc, xlnx_zynqmp_can_properties); + dc->vmsd = &vmstate_can; +} + +static const TypeInfo can_info = { + .name = TYPE_XLNX_ZYNQMP_CAN, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(XlnxZynqMPCANState), + .class_init = xlnx_zynqmp_can_class_init, + .instance_init = xlnx_zynqmp_can_init, +}; + +static void can_register_types(void) +{ + type_register_static(&can_info); +} + +type_init(can_register_types) diff --git a/hw/Kconfig b/hw/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/Kconfig +++ b/hw/Kconfig @@ -XXX,XX +XXX,XX @@ config XILINX_AXI config XLNX_ZYNQMP bool select REGISTER + select CAN_BUS diff --git a/hw/net/can/meson.build b/hw/net/can/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/net/can/meson.build +++ b/hw/net/can/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_CAN_PCI', if_true: files('can_pcm3680_pci.c')) softmmu_ss.add(when: 'CONFIG_CAN_PCI', if_true: files('can_mioe3680_pci.c')) softmmu_ss.add(when: 'CONFIG_CAN_CTUCANFD', if_true: files('ctucan_core.c')) softmmu_ss.add(when: 'CONFIG_CAN_CTUCANFD_PCI', if_true: files('ctucan_pci.c')) +softmmu_ss.add(when: 'CONFIG_XLNX_ZYNQMP', if_true: files('xlnx-zynqmp-can.c')) diff --git a/hw/net/can/trace-events b/hw/net/can/trace-events new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/can/trace-events @@ -XXX,XX +XXX,XX @@ +# xlnx-zynqmp-can.c +xlnx_can_update_irq(uint32_t isr, uint32_t ier, uint32_t irq) "ISR: 0x%08x IER: 0x%08x IRQ: 0x%08x" +xlnx_can_reset(uint32_t val) "Resetting controller with value = 0x%08x" +xlnx_can_rx_fifo_filter_reject(uint32_t id, uint8_t dlc) "Frame: ID: 0x%08x DLC: 0x%02x" +xlnx_can_filter_id_pre_write(uint8_t filter_num, uint32_t value) "Filter%d ID: 0x%08x" +xlnx_can_filter_mask_pre_write(uint8_t filter_num, uint32_t value) "Filter%d MASK: 0x%08x" +xlnx_can_tx_data(uint32_t id, uint8_t dlc, uint8_t db0, uint8_t db1, uint8_t db2, uint8_t db3, uint8_t db4, uint8_t db5, uint8_t db6, uint8_t db7) "Frame: ID: 0x%08x DLC: 0x%02x DATA: 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x" +xlnx_can_rx_data(uint32_t id, uint32_t dlc, uint8_t db0, uint8_t db1, uint8_t db2, uint8_t db3, uint8_t db4, uint8_t db5, uint8_t db6, uint8_t db7) "Frame: ID: 0x%08x DLC: 0x%02x DATA: 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x 0x%02x" +xlnx_can_rx_discard(uint32_t status) "Controller is not enabled for bus communication. Status Register: 0x%08x" -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> Connect CAN0 and CAN1 on the ZynqMP. Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Message-id: 1605728926-352690-3-git-send-email-fnu.vikram@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-zynqmp.h | 8 ++++++++ hw/arm/xlnx-zcu102.c | 20 ++++++++++++++++++++ hw/arm/xlnx-zynqmp.c | 34 ++++++++++++++++++++++++++++++++++ 3 files changed, 62 insertions(+) diff --git a/include/hw/arm/xlnx-zynqmp.h b/include/hw/arm/xlnx-zynqmp.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-zynqmp.h +++ b/include/hw/arm/xlnx-zynqmp.h @@ -XXX,XX +XXX,XX @@ #include "hw/intc/arm_gic.h" #include "hw/net/cadence_gem.h" #include "hw/char/cadence_uart.h" +#include "hw/net/xlnx-zynqmp-can.h" #include "hw/ide/ahci.h" #include "hw/sd/sdhci.h" #include "hw/ssi/xilinx_spips.h" @@ -XXX,XX +XXX,XX @@ #include "hw/cpu/cluster.h" #include "target/arm/cpu.h" #include "qom/object.h" +#include "net/can_emu.h" #define TYPE_XLNX_ZYNQMP "xlnx,zynqmp" OBJECT_DECLARE_SIMPLE_TYPE(XlnxZynqMPState, XLNX_ZYNQMP) @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(XlnxZynqMPState, XLNX_ZYNQMP) #define XLNX_ZYNQMP_NUM_RPU_CPUS 2 #define XLNX_ZYNQMP_NUM_GEMS 4 #define XLNX_ZYNQMP_NUM_UARTS 2 +#define XLNX_ZYNQMP_NUM_CAN 2 +#define XLNX_ZYNQMP_CAN_REF_CLK (24 * 1000 * 1000) #define XLNX_ZYNQMP_NUM_SDHCI 2 #define XLNX_ZYNQMP_NUM_SPIS 2 #define XLNX_ZYNQMP_NUM_GDMA_CH 8 @@ -XXX,XX +XXX,XX @@ struct XlnxZynqMPState { CadenceGEMState gem[XLNX_ZYNQMP_NUM_GEMS]; CadenceUARTState uart[XLNX_ZYNQMP_NUM_UARTS]; + XlnxZynqMPCANState can[XLNX_ZYNQMP_NUM_CAN]; SysbusAHCIState sata; SDHCIState sdhci[XLNX_ZYNQMP_NUM_SDHCI]; XilinxSPIPS spi[XLNX_ZYNQMP_NUM_SPIS]; @@ -XXX,XX +XXX,XX @@ struct XlnxZynqMPState { bool virt; /* Has the RPU subsystem? */ bool has_rpu; + + /* CAN bus. */ + CanBusState *canbus[XLNX_ZYNQMP_NUM_CAN]; }; #endif diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zcu102.c +++ b/hw/arm/xlnx-zcu102.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/qtest.h" #include "sysemu/device_tree.h" #include "qom/object.h" +#include "net/can_emu.h" struct XlnxZCU102 { MachineState parent_obj; @@ -XXX,XX +XXX,XX @@ struct XlnxZCU102 { bool secure; bool virt; + CanBusState *canbus[XLNX_ZYNQMP_NUM_CAN]; + struct arm_boot_info binfo; }; @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_init(MachineState *machine) object_property_set_bool(OBJECT(&s->soc), "virtualization", s->virt, &error_fatal); + for (i = 0; i < XLNX_ZYNQMP_NUM_CAN; i++) { + gchar *bus_name = g_strdup_printf("canbus%d", i); + + object_property_set_link(OBJECT(&s->soc), bus_name, + OBJECT(s->canbus[i]), &error_fatal); + g_free(bus_name); + } + qdev_realize(DEVICE(&s->soc), NULL, &error_fatal); /* Create and plug in the SD cards */ @@ -XXX,XX +XXX,XX @@ static void xlnx_zcu102_machine_instance_init(Object *obj) s->secure = false; /* Default to virt (EL2) being disabled */ s->virt = false; + object_property_add_link(obj, "xlnx-zcu102.canbus0", TYPE_CAN_BUS, + (Object **)&s->canbus[0], + object_property_allow_set_link, + 0); + + object_property_add_link(obj, "xlnx-zcu102.canbus1", TYPE_CAN_BUS, + (Object **)&s->canbus[1], + object_property_allow_set_link, + 0); } static void xlnx_zcu102_machine_class_init(ObjectClass *oc, void *data) diff --git a/hw/arm/xlnx-zynqmp.c b/hw/arm/xlnx-zynqmp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-zynqmp.c +++ b/hw/arm/xlnx-zynqmp.c @@ -XXX,XX +XXX,XX @@ static const int uart_intr[XLNX_ZYNQMP_NUM_UARTS] = { 21, 22, }; +static const uint64_t can_addr[XLNX_ZYNQMP_NUM_CAN] = { + 0xFF060000, 0xFF070000, +}; + +static const int can_intr[XLNX_ZYNQMP_NUM_CAN] = { + 23, 24, +}; + static const uint64_t sdhci_addr[XLNX_ZYNQMP_NUM_SDHCI] = { 0xFF160000, 0xFF170000, }; @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_init(Object *obj) TYPE_CADENCE_UART); } + for (i = 0; i < XLNX_ZYNQMP_NUM_CAN; i++) { + object_initialize_child(obj, "can[*]", &s->can[i], + TYPE_XLNX_ZYNQMP_CAN); + } + object_initialize_child(obj, "sata", &s->sata, TYPE_SYSBUS_AHCI); for (i = 0; i < XLNX_ZYNQMP_NUM_SDHCI; i++) { @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp) gic_spi[uart_intr[i]]); } + for (i = 0; i < XLNX_ZYNQMP_NUM_CAN; i++) { + object_property_set_int(OBJECT(&s->can[i]), "ext_clk_freq", + XLNX_ZYNQMP_CAN_REF_CLK, &error_abort); + + object_property_set_link(OBJECT(&s->can[i]), "canbus", + OBJECT(s->canbus[i]), &error_fatal); + + sysbus_realize(SYS_BUS_DEVICE(&s->can[i]), &err); + if (err) { + error_propagate(errp, err); + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->can[i]), 0, can_addr[i]); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->can[i]), 0, + gic_spi[can_intr[i]]); + } + object_property_set_int(OBJECT(&s->sata), "num-ports", SATA_NUM_PORTS, &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->sata), errp)) { @@ -XXX,XX +XXX,XX @@ static Property xlnx_zynqmp_props[] = { DEFINE_PROP_BOOL("has_rpu", XlnxZynqMPState, has_rpu, false), DEFINE_PROP_LINK("ddr-ram", XlnxZynqMPState, ddr_ram, TYPE_MEMORY_REGION, MemoryRegion *), + DEFINE_PROP_LINK("canbus0", XlnxZynqMPState, canbus[0], TYPE_CAN_BUS, + CanBusState *), + DEFINE_PROP_LINK("canbus1", XlnxZynqMPState, canbus[1], TYPE_CAN_BUS, + CanBusState *), DEFINE_PROP_END_OF_LIST() }; -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> The QTests perform five tests on the Xilinx ZynqMP CAN controller: Tests the CAN controller in loopback, sleep and snoop mode. Tests filtering of incoming CAN messages. Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Message-id: 1605728926-352690-4-git-send-email-fnu.vikram@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/xlnx-can-test.c | 360 ++++++++++++++++++++++++++++++++++++ tests/qtest/meson.build | 1 + 2 files changed, 361 insertions(+) create mode 100644 tests/qtest/xlnx-can-test.c diff --git a/tests/qtest/xlnx-can-test.c b/tests/qtest/xlnx-can-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/xlnx-can-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTests for the Xilinx ZynqMP CAN controller. + * + * Copyright (c) 2020 Xilinx Inc. + * + * Written-by: Vikram Garhwal<fnu.vikram@xilinx.com> + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "libqos/libqtest.h" + +/* Base address. */ +#define CAN0_BASE_ADDR 0xFF060000 +#define CAN1_BASE_ADDR 0xFF070000 + +/* Register addresses. */ +#define R_SRR_OFFSET 0x00 +#define R_MSR_OFFSET 0x04 +#define R_SR_OFFSET 0x18 +#define R_ISR_OFFSET 0x1C +#define R_ICR_OFFSET 0x24 +#define R_TXID_OFFSET 0x30 +#define R_TXDLC_OFFSET 0x34 +#define R_TXDATA1_OFFSET 0x38 +#define R_TXDATA2_OFFSET 0x3C +#define R_RXID_OFFSET 0x50 +#define R_RXDLC_OFFSET 0x54 +#define R_RXDATA1_OFFSET 0x58 +#define R_RXDATA2_OFFSET 0x5C +#define R_AFR 0x60 +#define R_AFMR1 0x64 +#define R_AFIR1 0x68 +#define R_AFMR2 0x6C +#define R_AFIR2 0x70 +#define R_AFMR3 0x74 +#define R_AFIR3 0x78 +#define R_AFMR4 0x7C +#define R_AFIR4 0x80 + +/* CAN modes. */ +#define CONFIG_MODE 0x00 +#define NORMAL_MODE 0x00 +#define LOOPBACK_MODE 0x02 +#define SNOOP_MODE 0x04 +#define SLEEP_MODE 0x01 +#define ENABLE_CAN (1 << 1) +#define STATUS_NORMAL_MODE (1 << 3) +#define STATUS_LOOPBACK_MODE (1 << 1) +#define STATUS_SNOOP_MODE (1 << 12) +#define STATUS_SLEEP_MODE (1 << 2) +#define ISR_TXOK (1 << 1) +#define ISR_RXOK (1 << 4) + +static void match_rx_tx_data(const uint32_t *buf_tx, const uint32_t *buf_rx, + uint8_t can_timestamp) +{ + uint16_t size = 0; + uint8_t len = 4; + + while (size < len) { + if (R_RXID_OFFSET + 4 * size == R_RXDLC_OFFSET) { + g_assert_cmpint(buf_rx[size], ==, buf_tx[size] + can_timestamp); + } else { + g_assert_cmpint(buf_rx[size], ==, buf_tx[size]); + } + + size++; + } +} + +static void read_data(QTestState *qts, uint64_t can_base_addr, uint32_t *buf_rx) +{ + uint32_t int_status; + + /* Read the interrupt on CAN rx. */ + int_status = qtest_readl(qts, can_base_addr + R_ISR_OFFSET) & ISR_RXOK; + + g_assert_cmpint(int_status, ==, ISR_RXOK); + + /* Read the RX register data for CAN. */ + buf_rx[0] = qtest_readl(qts, can_base_addr + R_RXID_OFFSET); + buf_rx[1] = qtest_readl(qts, can_base_addr + R_RXDLC_OFFSET); + buf_rx[2] = qtest_readl(qts, can_base_addr + R_RXDATA1_OFFSET); + buf_rx[3] = qtest_readl(qts, can_base_addr + R_RXDATA2_OFFSET); + + /* Clear the RX interrupt. */ + qtest_writel(qts, CAN1_BASE_ADDR + R_ICR_OFFSET, ISR_RXOK); +} + +static void send_data(QTestState *qts, uint64_t can_base_addr, + const uint32_t *buf_tx) +{ + uint32_t int_status; + + /* Write the TX register data for CAN. */ + qtest_writel(qts, can_base_addr + R_TXID_OFFSET, buf_tx[0]); + qtest_writel(qts, can_base_addr + R_TXDLC_OFFSET, buf_tx[1]); + qtest_writel(qts, can_base_addr + R_TXDATA1_OFFSET, buf_tx[2]); + qtest_writel(qts, can_base_addr + R_TXDATA2_OFFSET, buf_tx[3]); + + /* Read the interrupt on CAN for tx. */ + int_status = qtest_readl(qts, can_base_addr + R_ISR_OFFSET) & ISR_TXOK; + + g_assert_cmpint(int_status, ==, ISR_TXOK); + + /* Clear the interrupt for tx. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_ICR_OFFSET, ISR_TXOK); +} + +/* + * This test will be transferring data from CAN0 and CAN1 through canbus. CAN0 + * initiate the data transfer to can-bus, CAN1 receives the data. Test compares + * the data sent from CAN0 with received on CAN1. + */ +static void test_can_bus(void) +{ + const uint32_t buf_tx[4] = { 0xFF, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0 and CAN1. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 and CAN1 are in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + send_data(qts, CAN0_BASE_ADDR, buf_tx); + + read_data(qts, CAN1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +/* + * This test is performing loopback mode on CAN0 and CAN1. Data sent from TX of + * each CAN0 and CAN1 are compared with RX register data for respective CAN. + */ +static void test_can_loopback(void) +{ + uint32_t buf_tx[4] = { 0xFF, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0 in loopback mode. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, LOOPBACK_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + /* Check here if CAN0 is set in loopback mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + + g_assert_cmpint(status, ==, STATUS_LOOPBACK_MODE); + + send_data(qts, CAN0_BASE_ADDR, buf_tx); + read_data(qts, CAN0_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, 0); + + /* Configure the CAN1 in loopback mode. */ + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, LOOPBACK_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + /* Check here if CAN1 is set in loopback mode. */ + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + + g_assert_cmpint(status, ==, STATUS_LOOPBACK_MODE); + + send_data(qts, CAN1_BASE_ADDR, buf_tx); + read_data(qts, CAN1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, 0); + + qtest_quit(qts); +} + +/* + * Enable filters for CAN1. This will filter incoming messages with ID. In this + * test message will pass through filter 2. + */ +static void test_can_filter(void) +{ + uint32_t buf_tx[4] = { 0x14, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0 and CAN1. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 and CAN1 are in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + /* Set filter for CAN1 for incoming messages. */ + qtest_writel(qts, CAN1_BASE_ADDR + R_AFR, 0x0); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR1, 0xF7); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR1, 0x121F); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR2, 0x5431); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR2, 0x14); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR3, 0x1234); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR3, 0x5431); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFMR4, 0xFFF); + qtest_writel(qts, CAN1_BASE_ADDR + R_AFIR4, 0x1234); + + qtest_writel(qts, CAN1_BASE_ADDR + R_AFR, 0xF); + + send_data(qts, CAN0_BASE_ADDR, buf_tx); + + read_data(qts, CAN1_BASE_ADDR, buf_rx); + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +/* Testing sleep mode on CAN0 while CAN1 is in normal mode. */ +static void test_can_sleepmode(void) +{ + uint32_t buf_tx[4] = { 0x14, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, SLEEP_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 is in SLEEP mode and CAN1 in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_SLEEP_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + send_data(qts, CAN1_BASE_ADDR, buf_tx); + + /* + * Once CAN1 sends data on can-bus. CAN0 should exit sleep mode. + * Check the CAN0 status now. It should exit the sleep mode and receive the + * incoming data. + */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + read_data(qts, CAN0_BASE_ADDR, buf_rx); + + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +/* Testing Snoop mode on CAN0 while CAN1 is in normal mode. */ +static void test_can_snoopmode(void) +{ + uint32_t buf_tx[4] = { 0x14, 0x80000000, 0x12345678, 0x87654321 }; + uint32_t buf_rx[4] = { 0x00, 0x00, 0x00, 0x00 }; + uint32_t status = 0; + uint8_t can_timestamp = 1; + + QTestState *qts = qtest_init("-machine xlnx-zcu102" + " -object can-bus,id=canbus0" + " -machine xlnx-zcu102.canbus0=canbus0" + " -machine xlnx-zcu102.canbus1=canbus0" + ); + + /* Configure the CAN0. */ + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, CONFIG_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_MSR_OFFSET, SNOOP_MODE); + qtest_writel(qts, CAN0_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + + qtest_writel(qts, CAN1_BASE_ADDR + R_SRR_OFFSET, ENABLE_CAN); + qtest_writel(qts, CAN1_BASE_ADDR + R_MSR_OFFSET, NORMAL_MODE); + + /* Check here if CAN0 is in SNOOP mode and CAN1 in normal mode. */ + status = qtest_readl(qts, CAN0_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_SNOOP_MODE); + + status = qtest_readl(qts, CAN1_BASE_ADDR + R_SR_OFFSET); + g_assert_cmpint(status, ==, STATUS_NORMAL_MODE); + + send_data(qts, CAN1_BASE_ADDR, buf_tx); + + read_data(qts, CAN0_BASE_ADDR, buf_rx); + + match_rx_tx_data(buf_tx, buf_rx, can_timestamp); + + qtest_quit(qts); +} + +int main(int argc, char **argv) +{ + g_test_init(&argc, &argv, NULL); + + qtest_add_func("/net/can/can_bus", test_can_bus); + qtest_add_func("/net/can/can_loopback", test_can_loopback); + qtest_add_func("/net/can/can_filter", test_can_filter); + qtest_add_func("/net/can/can_test_snoopmode", test_can_snoopmode); + qtest_add_func("/net/can/can_test_sleepmode", test_can_sleepmode); + + return g_test_run(); +} diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qtests_aarch64 = \ ['arm-cpu-features', 'numa-test', 'boot-serial-test', + 'xlnx-can-test', 'migration-test'] qtests_s390x = \ -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Message-id: 1605728926-352690-5-git-send-email-fnu.vikram@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/net/opencores_eth.c Devices ------- +Xilinx CAN +M: Vikram Garhwal <fnu.vikram@xilinx.com> +M: Francisco Iglesias <francisco.iglesias@xilinx.com> +S: Maintained +F: hw/net/can/xlnx-* +F: include/hw/net/xlnx-* +F: tests/qtest/xlnx-can-test* + EDU M: Jiri Slaby <jslaby@suse.cz> S: Maintained -- 2.20.1 From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Trusted Firmware now supports A72 on sbsa-ref by default [1] so enable it for QEMU as well. A53 was already enabled there. 1. https://review.trustedfirmware.org/c/TF-A/trusted-firmware-a/+/7117 Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201120141705.246690-1-marcin.juszkiewicz@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 23 ++++++++++++++++++++--- 1 file changed, 20 insertions(+), 3 deletions(-) diff --git a/hw/arm/sbsa-ref.c b/hw/arm/sbsa-ref.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/sbsa-ref.c +++ b/hw/arm/sbsa-ref.c @@ -XXX,XX +XXX,XX @@ static const int sbsa_ref_irqmap[] = { [SBSA_GWDT] = 16, }; +static const char * const valid_cpus[] = { + ARM_CPU_TYPE_NAME("cortex-a53"), + ARM_CPU_TYPE_NAME("cortex-a57"), + ARM_CPU_TYPE_NAME("cortex-a72"), +}; + +static bool cpu_type_valid(const char *cpu) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(valid_cpus); i++) { + if (strcmp(cpu, valid_cpus[i]) == 0) { + return true; + } + } + return false; +} + static uint64_t sbsa_ref_cpu_mp_affinity(SBSAMachineState *sms, int idx) { uint8_t clustersz = ARM_DEFAULT_CPUS_PER_CLUSTER; @@ -XXX,XX +XXX,XX @@ static void sbsa_ref_init(MachineState *machine) const CPUArchIdList *possible_cpus; int n, sbsa_max_cpus; - if (strcmp(machine->cpu_type, ARM_CPU_TYPE_NAME("cortex-a57"))) { - error_report("sbsa-ref: CPU type other than the built-in " - "cortex-a57 not supported"); + if (!cpu_type_valid(machine->cpu_type)) { + error_report("mach-virt: CPU type %s not supported", machine->cpu_type); exit(1); } -- 2.20.1 From: Havard Skinnemoen <hskinnemoen@google.com> Dump the collected random data after a randomness test failure. Note that this relies on the test having called g_test_set_nonfatal_assertions() so we don't abort immediately on the assertion failure. Signed-off-by: Havard Skinnemoen <hskinnemoen@google.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: minor commit message tweak] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/npcm7xx_rng-test.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) diff --git a/tests/qtest/npcm7xx_rng-test.c b/tests/qtest/npcm7xx_rng-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/npcm7xx_rng-test.c +++ b/tests/qtest/npcm7xx_rng-test.c @@ -XXX,XX +XXX,XX @@ #include "libqtest-single.h" #include "qemu/bitops.h" +#include "qemu-common.h" #define RNG_BASE_ADDR 0xf000b000 @@ -XXX,XX +XXX,XX @@ /* Number of bits to collect for randomness tests. */ #define TEST_INPUT_BITS (128) +static void dump_buf_if_failed(const uint8_t *buf, size_t size) +{ + if (g_test_failed()) { + qemu_hexdump(stderr, "", buf, size); + } +} + static void rng_writeb(unsigned int offset, uint8_t value) { writeb(RNG_BASE_ADDR + offset, value); @@ -XXX,XX +XXX,XX @@ static void test_continuous_monobit(void) } g_assert_cmpfloat(calc_monobit_p(buf, sizeof(buf)), >, 0.01); + dump_buf_if_failed(buf, sizeof(buf)); } /* @@ -XXX,XX +XXX,XX @@ static void test_continuous_runs(void) } g_assert_cmpfloat(calc_runs_p(buf.l, sizeof(buf) * BITS_PER_BYTE), >, 0.01); + dump_buf_if_failed(buf.c, sizeof(buf)); } /* @@ -XXX,XX +XXX,XX @@ static void test_first_byte_monobit(void) } g_assert_cmpfloat(calc_monobit_p(buf, sizeof(buf)), >, 0.01); + dump_buf_if_failed(buf, sizeof(buf)); } /* @@ -XXX,XX +XXX,XX @@ static void test_first_byte_runs(void) } g_assert_cmpfloat(calc_runs_p(buf.l, sizeof(buf) * BITS_PER_BYTE), >, 0.01); + dump_buf_if_failed(buf.c, sizeof(buf)); } int main(int argc, char **argv) -- 2.20.1 From: Alex Chen <alex.chen@huawei.com> We should use printf format specifier "%u" instead of "%d" for argument of type "unsigned int". Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Message-id: 20201126111109.112238-2-alex.chen@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/imx25_ccm.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/hw/misc/imx25_ccm.c b/hw/misc/imx25_ccm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/imx25_ccm.c +++ b/hw/misc/imx25_ccm.c @@ -XXX,XX +XXX,XX @@ static const char *imx25_ccm_reg_name(uint32_t reg) case IMX25_CCM_LPIMR1_REG: return "lpimr1"; default: - sprintf(unknown, "[%d ?]", reg); + sprintf(unknown, "[%u ?]", reg); return unknown; } } @@ -XXX,XX +XXX,XX @@ static uint32_t imx25_ccm_get_mpll_clk(IMXCCMState *dev) freq = imx_ccm_calc_pll(s->reg[IMX25_CCM_MPCTL_REG], CKIH_FREQ); } - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx25_ccm_get_mcu_clk(IMXCCMState *dev) freq = freq / (1 + EXTRACT(s->reg[IMX25_CCM_CCTL_REG], ARM_CLK_DIV)); - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx25_ccm_get_ahb_clk(IMXCCMState *dev) freq = imx25_ccm_get_mcu_clk(dev) / (1 + EXTRACT(s->reg[IMX25_CCM_CCTL_REG], AHB_CLK_DIV)); - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx25_ccm_get_ipg_clk(IMXCCMState *dev) freq = imx25_ccm_get_ahb_clk(dev) / 2; - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx25_ccm_get_clock_frequency(IMXCCMState *dev, IMXClk clock) break; } - DPRINTF("Clock = %d) = %d\n", clock, freq); + DPRINTF("Clock = %d) = %u\n", clock, freq); return freq; } -- 2.20.1 From: Alex Chen <alex.chen@huawei.com> We should use printf format specifier "%u" instead of "%d" for argument of type "unsigned int". Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Message-id: 20201126111109.112238-3-alex.chen@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/imx31_ccm.c | 14 +++++++------- hw/misc/imx_ccm.c | 4 ++-- 2 files changed, 9 insertions(+), 9 deletions(-) diff --git a/hw/misc/imx31_ccm.c b/hw/misc/imx31_ccm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/imx31_ccm.c +++ b/hw/misc/imx31_ccm.c @@ -XXX,XX +XXX,XX @@ static const char *imx31_ccm_reg_name(uint32_t reg) case IMX31_CCM_PDR2_REG: return "PDR2"; default: - sprintf(unknown, "[%d ?]", reg); + sprintf(unknown, "[%u ?]", reg); return unknown; } } @@ -XXX,XX +XXX,XX @@ static uint32_t imx31_ccm_get_pll_ref_clk(IMXCCMState *dev) freq = CKIH_FREQ; } - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx31_ccm_get_mpll_clk(IMXCCMState *dev) freq = imx_ccm_calc_pll(s->reg[IMX31_CCM_MPCTL_REG], imx31_ccm_get_pll_ref_clk(dev)); - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx31_ccm_get_mcu_main_clk(IMXCCMState *dev) freq = imx31_ccm_get_mpll_clk(dev); } - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx31_ccm_get_hclk_clk(IMXCCMState *dev) freq = imx31_ccm_get_mcu_main_clk(dev) / (1 + EXTRACT(s->reg[IMX31_CCM_PDR0_REG], MAX)); - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx31_ccm_get_ipg_clk(IMXCCMState *dev) freq = imx31_ccm_get_hclk_clk(dev) / (1 + EXTRACT(s->reg[IMX31_CCM_PDR0_REG], IPG)); - DPRINTF("freq = %d\n", freq); + DPRINTF("freq = %u\n", freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx31_ccm_get_clock_frequency(IMXCCMState *dev, IMXClk clock) break; } - DPRINTF("Clock = %d) = %d\n", clock, freq); + DPRINTF("Clock = %d) = %u\n", clock, freq); return freq; } diff --git a/hw/misc/imx_ccm.c b/hw/misc/imx_ccm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/imx_ccm.c +++ b/hw/misc/imx_ccm.c @@ -XXX,XX +XXX,XX @@ uint32_t imx_ccm_get_clock_frequency(IMXCCMState *dev, IMXClk clock) freq = klass->get_clock_frequency(dev, clock); } - DPRINTF("(clock = %d) = %d\n", clock, freq); + DPRINTF("(clock = %d) = %u\n", clock, freq); return freq; } @@ -XXX,XX +XXX,XX @@ uint32_t imx_ccm_calc_pll(uint32_t pllreg, uint32_t base_freq) freq = ((2 * (base_freq >> 10) * (mfi * mfd + mfn)) / (mfd * pd)) << 10; - DPRINTF("(pllreg = 0x%08x, base_freq = %d) = %d\n", pllreg, base_freq, + DPRINTF("(pllreg = 0x%08x, base_freq = %u) = %d\n", pllreg, base_freq, freq); return freq; -- 2.20.1 From: Alex Chen <alex.chen@huawei.com> We should use printf format specifier "%u" instead of "%d" for argument of type "unsigned int". Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Message-id: 20201126111109.112238-4-alex.chen@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/imx6_ccm.c | 20 ++++++++++---------- hw/misc/imx6_src.c | 2 +- 2 files changed, 11 insertions(+), 11 deletions(-) diff --git a/hw/misc/imx6_ccm.c b/hw/misc/imx6_ccm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/imx6_ccm.c +++ b/hw/misc/imx6_ccm.c @@ -XXX,XX +XXX,XX @@ static const char *imx6_ccm_reg_name(uint32_t reg) case CCM_CMEOR: return "CMEOR"; default: - sprintf(unknown, "%d ?", reg); + sprintf(unknown, "%u ?", reg); return unknown; } } @@ -XXX,XX +XXX,XX @@ static const char *imx6_analog_reg_name(uint32_t reg) case USB_ANALOG_DIGPROG: return "USB_ANALOG_DIGPROG"; default: - sprintf(unknown, "%d ?", reg); + sprintf(unknown, "%u ?", reg); return unknown; } } @@ -XXX,XX +XXX,XX @@ static uint64_t imx6_analog_get_pll2_clk(IMX6CCMState *dev) freq *= 20; } - DPRINTF("freq = %d\n", (uint32_t)freq); + DPRINTF("freq = %u\n", (uint32_t)freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint64_t imx6_analog_get_pll2_pfd0_clk(IMX6CCMState *dev) freq = imx6_analog_get_pll2_clk(dev) * 18 / EXTRACT(dev->analog[CCM_ANALOG_PFD_528], PFD0_FRAC); - DPRINTF("freq = %d\n", (uint32_t)freq); + DPRINTF("freq = %u\n", (uint32_t)freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint64_t imx6_analog_get_pll2_pfd2_clk(IMX6CCMState *dev) freq = imx6_analog_get_pll2_clk(dev) * 18 / EXTRACT(dev->analog[CCM_ANALOG_PFD_528], PFD2_FRAC); - DPRINTF("freq = %d\n", (uint32_t)freq); + DPRINTF("freq = %u\n", (uint32_t)freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint64_t imx6_analog_get_periph_clk(IMX6CCMState *dev) break; } - DPRINTF("freq = %d\n", (uint32_t)freq); + DPRINTF("freq = %u\n", (uint32_t)freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint64_t imx6_ccm_get_ahb_clk(IMX6CCMState *dev) freq = imx6_analog_get_periph_clk(dev) / (1 + EXTRACT(dev->ccm[CCM_CBCDR], AHB_PODF)); - DPRINTF("freq = %d\n", (uint32_t)freq); + DPRINTF("freq = %u\n", (uint32_t)freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint64_t imx6_ccm_get_ipg_clk(IMX6CCMState *dev) freq = imx6_ccm_get_ahb_clk(dev) / (1 + EXTRACT(dev->ccm[CCM_CBCDR], IPG_PODF)); - DPRINTF("freq = %d\n", (uint32_t)freq); + DPRINTF("freq = %u\n", (uint32_t)freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint64_t imx6_ccm_get_per_clk(IMX6CCMState *dev) freq = imx6_ccm_get_ipg_clk(dev) / (1 + EXTRACT(dev->ccm[CCM_CSCMR1], PERCLK_PODF)); - DPRINTF("freq = %d\n", (uint32_t)freq); + DPRINTF("freq = %u\n", (uint32_t)freq); return freq; } @@ -XXX,XX +XXX,XX @@ static uint32_t imx6_ccm_get_clock_frequency(IMXCCMState *dev, IMXClk clock) break; } - DPRINTF("Clock = %d) = %d\n", clock, freq); + DPRINTF("Clock = %d) = %u\n", clock, freq); return freq; } diff --git a/hw/misc/imx6_src.c b/hw/misc/imx6_src.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/imx6_src.c +++ b/hw/misc/imx6_src.c @@ -XXX,XX +XXX,XX @@ static const char *imx6_src_reg_name(uint32_t reg) case SRC_GPR10: return "SRC_GPR10"; default: - sprintf(unknown, "%d ?", reg); + sprintf(unknown, "%u ?", reg); return unknown; } } -- 2.20.1 From: Alex Chen <alex.chen@huawei.com> We should use printf format specifier "%u" instead of "%d" for argument of type "unsigned int". Reported-by: Euler Robot <euler.robot@huawei.com> Signed-off-by: Alex Chen <alex.chen@huawei.com> Message-id: 20201126111109.112238-5-alex.chen@huawei.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/imx6ul_ccm.c | 4 ++-- 1 file changed, 2 insertions(+), 2 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 @@ static const char *imx6ul_ccm_reg_name(uint32_t reg) case CCM_CMEOR: return "CMEOR"; default: - sprintf(unknown, "%d ?", reg); + sprintf(unknown, "%u ?", reg); return unknown; } } @@ -XXX,XX +XXX,XX @@ static const char *imx6ul_analog_reg_name(uint32_t reg) case USB_ANALOG_DIGPROG: return "USB_ANALOG_DIGPROG"; default: - sprintf(unknown, "%d ?", reg); + sprintf(unknown, "%u ?", reg); return unknown; } } -- 2.20.1 For M-profile CPUs, the range from 0xe0000000 to 0xe00fffff is the Private Peripheral Bus range, which includes all of the memory mapped devices and registers that are part of the CPU itself, including the NVIC, systick timer, and debug and trace components like the Data Watchpoint and Trace unit (DWT). Within this large region, the range 0xe000e000 to 0xe000efff is the System Control Space (NVIC, system registers, systick) and 0xe002e000 to 0exe002efff is its Non-secure alias. The architecture is clear that within the SCS unimplemented registers should be RES0 for privileged accesses and generate BusFault for unprivileged accesses, and we currently implement this. It is less clear about how to handle accesses to unimplemented regions of the wider PPB. Unprivileged accesses should definitely cause BusFaults (R_DQQS), but the behaviour of privileged accesses is not given as a general rule. However, the register definitions of individual registers for components like the DWT all state that they are RES0 if the relevant component is not implemented, so the simplest way to provide that is to provide RAZ/WI for the whole range for privileged accesses. (The v7M Arm ARM does say that reserved registers should be UNK/SBZP.) Expand the container MemoryRegion that the NVIC exposes so that it covers the whole PPB space. This means: * moving the address that the ARMV7M device maps it to down by 0xe000 bytes * moving the off and the offsets within the container of all the subregions forward by 0xe000 bytes * adding a new default MemoryRegion that covers the whole container at a lower priority than anything else and which provides the RAZWI/BusFault behaviour Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-2-peter.maydell@linaro.org --- include/hw/intc/armv7m_nvic.h | 1 + hw/arm/armv7m.c | 2 +- hw/intc/armv7m_nvic.c | 78 ++++++++++++++++++++++++++++++----- 3 files changed, 69 insertions(+), 12 deletions(-) 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 systickmem; MemoryRegion systick_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 @@ static void armv7m_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(sbd, 0, qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_IRQ)); - memory_region_add_subregion(&s->container, 0xe000e000, + memory_region_add_subregion(&s->container, 0xe0000000, sysbus_mmio_get_region(sbd, 0)); for (i = 0; i < ARRAY_SIZE(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, }; +/* + * 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 nvic_systick_trigger(void *opaque, int n, int level) static void armv7m_nvic_realize(DeviceState *dev, Error **errp) { NVICState *s = NVIC(dev); - int regionlen; /* The armv7m container object will have set our CPU pointer */ if (!s->cpu || !arm_feature(&s->cpu->env, ARM_FEATURE_M)) { @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) M_REG_S)); } - /* The NVIC and System Control Space (SCS) starts at 0xe000e000 + /* + * 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 @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) * 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. */ - regionlen = arm_feature(&s->cpu->env, ARM_FEATURE_V8) ? 0x21000 : 0x1000; - memory_region_init(&s->container, OBJECT(s), "nvic", regionlen); - /* The system register region goes at the bottom of the priority - * stack as it covers the whole page. - */ + 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, 0, &s->sysregmem); + 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, 0x10, + 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, 0x20000, &s->sysreg_ns_mem); + 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, 0x20010, + memory_region_add_subregion_overlap(&s->container, 0x2e010, &s->systick_ns_mem, 1); } -- 2.20.1 In v8.1M the PXN architecture extension adds a new PXN bit to the MPU_RLAR registers, which forbids execution of code in the region from a privileged mode. This is another feature which is just in the generic "in v8.1M" set and has no ID register field indicating its presence. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-3-peter.maydell@linaro.org --- target/arm/helper.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, } else { uint32_t ap = extract32(env->pmsav8.rbar[secure][matchregion], 1, 2); uint32_t xn = extract32(env->pmsav8.rbar[secure][matchregion], 0, 1); + bool pxn = false; + + if (arm_feature(env, ARM_FEATURE_V8_1M)) { + pxn = extract32(env->pmsav8.rlar[secure][matchregion], 4, 1); + } if (m_is_system_region(env, address)) { /* System space is always execute never */ @@ -XXX,XX +XXX,XX @@ bool pmsav8_mpu_lookup(CPUARMState *env, uint32_t address, } *prot = simple_ap_to_rw_prot(env, mmu_idx, ap); - if (*prot && !xn) { + if (*prot && !xn && !(pxn && !is_user)) { *prot |= PAGE_EXEC; } /* We don't need to look the attribute up in the MAIR0/MAIR1 -- 2.20.1 In arm_cpu_realizefn() we check whether the board code disabled EL3 via the has_el3 CPU object property, which we create if the CPU starts with the ARM_FEATURE_EL3 feature bit. If it is disabled, then we turn off ARM_FEATURE_EL3 and also zero out the relevant fields in the ID_PFR1 and ID_AA64PFR0 registers. This codepath was incorrectly being taken for M-profile CPUs, which do not have an EL3 and don't set ARM_FEATURE_EL3, but which may have the M-profile Security extension and so should have non-zero values in the ID_PFR1.Security field. Restrict the handling of the feature flag to A/R-profile cores. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-4-peter.maydell@linaro.org --- target/arm/cpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) } } - if (!cpu->has_el3) { + if (!arm_feature(env, ARM_FEATURE_M) && !cpu->has_el3) { /* If the has_el3 CPU property is disabled then we need to disable the * feature. */ -- 2.20.1 Implement the v8.1M VSCCLRM insn, which zeros floating point registers if there is an active floating point context. This requires support in write_neon_element32() for the MO_32 element size, so add it. Because we want to use arm_gen_condlabel(), we need to move the definition of that function up in translate.c so it is before the #include of translate-vfp.c.inc. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-5-peter.maydell@linaro.org --- target/arm/cpu.h | 9 ++++ target/arm/m-nocp.decode | 8 +++- target/arm/translate.c | 21 +++++---- target/arm/translate-vfp.c.inc | 84 ++++++++++++++++++++++++++++++++++ 4 files changed, 111 insertions(+), 11 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_mprofile(const ARMISARegisters *id) return FIELD_EX32(id->id_pfr1, ID_PFR1, MPROGMOD) != 0; } +static inline bool isar_feature_aa32_m_sec_state(const ARMISARegisters *id) +{ + /* + * Return true if M-profile state handling insns + * (VSCCLRM, CLRM, FPCTX access insns) are implemented + */ + return FIELD_EX32(id->id_pfr1, ID_PFR1, SECURITY) >= 3; +} + static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id) { /* Sadly this is encoded differently for A-profile and M-profile */ diff --git a/target/arm/m-nocp.decode b/target/arm/m-nocp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m-nocp.decode +++ b/target/arm/m-nocp.decode @@ -XXX,XX +XXX,XX @@ # If the coprocessor is not present or disabled then we will generate # the NOCP exception; otherwise we let the insn through to the main decode. +%vd_dp 22:1 12:4 +%vd_sp 12:4 22:1 + &nocp cp { # Special cases which do not take an early NOCP: VLLDM and VLSTM VLLDM_VLSTM 1110 1100 001 l:1 rn:4 0000 1010 0000 0000 - # TODO: VSCCLRM (new in v8.1M) is similar: - #VSCCLRM 1110 1100 1-01 1111 ---- 1011 ---- ---0 + # VSCCLRM (new in v8.1M) is similar: + VSCCLRM 1110 1100 1.01 1111 .... 1011 imm:7 0 vd=%vd_dp size=3 + VSCCLRM 1110 1100 1.01 1111 .... 1010 imm:8 vd=%vd_sp size=2 NOCP 111- 1110 ---- ---- ---- cp:4 ---- ---- &nocp NOCP 111- 110- ---- ---- ---- cp:4 ---- ---- &nocp 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 @@ void arm_translate_init(void) a64_translate_init(); } +/* Generate a label used for skipping this instruction */ +static void arm_gen_condlabel(DisasContext *s) +{ + if (!s->condjmp) { + s->condlabel = gen_new_label(); + s->condjmp = 1; + } +} + /* Flags for the disas_set_da_iss info argument: * lower bits hold the Rt register number, higher bits are flags. */ @@ -XXX,XX +XXX,XX @@ static void write_neon_element64(TCGv_i64 src, int reg, int ele, MemOp memop) long off = neon_element_offset(reg, ele, memop); switch (memop) { + case MO_32: + tcg_gen_st32_i64(src, cpu_env, off); + break; case MO_64: tcg_gen_st_i64(src, cpu_env, off); break; @@ -XXX,XX +XXX,XX @@ static void gen_srs(DisasContext *s, s->base.is_jmp = DISAS_UPDATE_EXIT; } -/* Generate a label used for skipping this instruction */ -static void arm_gen_condlabel(DisasContext *s) -{ - if (!s->condjmp) { - s->condlabel = gen_new_label(); - s->condjmp = 1; - } -} - /* Skip this instruction if the ARM condition is false */ static void arm_skip_unless(DisasContext *s, uint32_t cond) { diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VLLDM_VLSTM(DisasContext *s, arg_VLLDM_VLSTM *a) return true; } +static bool trans_VSCCLRM(DisasContext *s, arg_VSCCLRM *a) +{ + int btmreg, topreg; + TCGv_i64 zero; + TCGv_i32 aspen, sfpa; + + if (!dc_isar_feature(aa32_m_sec_state, s)) { + /* Before v8.1M, fall through in decode to NOCP check */ + return false; + } + + /* Explicitly UNDEF because this takes precedence over NOCP */ + if (!arm_dc_feature(s, ARM_FEATURE_M_MAIN) || !s->v8m_secure) { + unallocated_encoding(s); + return true; + } + + if (!dc_isar_feature(aa32_vfp_simd, s)) { + /* NOP if we have neither FP nor MVE */ + return true; + } + + /* + * If FPCCR.ASPEN != 0 && CONTROL_S.SFPA == 0 then there is no + * active floating point context so we must NOP (without doing + * any lazy state preservation or the NOCP check). + */ + aspen = load_cpu_field(v7m.fpccr[M_REG_S]); + sfpa = load_cpu_field(v7m.control[M_REG_S]); + tcg_gen_andi_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); + tcg_gen_xori_i32(aspen, aspen, R_V7M_FPCCR_ASPEN_MASK); + tcg_gen_andi_i32(sfpa, sfpa, R_V7M_CONTROL_SFPA_MASK); + tcg_gen_or_i32(sfpa, sfpa, aspen); + arm_gen_condlabel(s); + tcg_gen_brcondi_i32(TCG_COND_EQ, sfpa, 0, s->condlabel); + + if (s->fp_excp_el != 0) { + gen_exception_insn(s, s->pc_curr, EXCP_NOCP, + syn_uncategorized(), s->fp_excp_el); + return true; + } + + topreg = a->vd + a->imm - 1; + btmreg = a->vd; + + /* Convert to Sreg numbers if the insn specified in Dregs */ + if (a->size == 3) { + topreg = topreg * 2 + 1; + btmreg *= 2; + } + + if (topreg > 63 || (topreg > 31 && !(topreg & 1))) { + /* UNPREDICTABLE: we choose to undef */ + unallocated_encoding(s); + return true; + } + + /* Silently ignore requests to clear D16-D31 if they don't exist */ + if (topreg > 31 && !dc_isar_feature(aa32_simd_r32, s)) { + topreg = 31; + } + + if (!vfp_access_check(s)) { + return true; + } + + /* Zero the Sregs from btmreg to topreg inclusive. */ + zero = tcg_const_i64(0); + if (btmreg & 1) { + write_neon_element64(zero, btmreg >> 1, 1, MO_32); + btmreg++; + } + for (; btmreg + 1 <= topreg; btmreg += 2) { + write_neon_element64(zero, btmreg >> 1, 0, MO_64); + } + if (btmreg == topreg) { + write_neon_element64(zero, btmreg >> 1, 0, MO_32); + btmreg++; + } + assert(btmreg == topreg + 1); + /* TODO: when MVE is implemented, zero VPR here */ + return true; +} + static bool trans_NOCP(DisasContext *s, arg_nocp *a) { /* -- 2.20.1 In v8.1M the new CLRM instruction allows zeroing an arbitrary set of the general-purpose registers and APSR. Implement this. The encoding is a subset of the LDMIA T2 encoding, using what would be Rn=0b1111 (which UNDEFs for LDMIA). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-6-peter.maydell@linaro.org --- target/arm/t32.decode | 6 +++++- target/arm/translate.c | 38 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 43 insertions(+), 1 deletion(-) diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ UXTAB 1111 1010 0101 .... 1111 .... 10.. .... @rrr_rot STM_t32 1110 1000 10.0 .... ................ @ldstm i=1 b=0 STM_t32 1110 1001 00.0 .... ................ @ldstm i=0 b=1 -LDM_t32 1110 1000 10.1 .... ................ @ldstm i=1 b=0 +{ + # Rn=15 UNDEFs for LDM; M-profile CLRM uses that encoding + CLRM 1110 1000 1001 1111 list:16 + LDM_t32 1110 1000 10.1 .... ................ @ldstm i=1 b=0 +} LDM_t32 1110 1001 00.1 .... ................ @ldstm i=0 b=1 &rfe !extern rn w pu 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 bool trans_LDM_t16(DisasContext *s, arg_ldst_block *a) return do_ldm(s, a, 1); } +static bool trans_CLRM(DisasContext *s, arg_CLRM *a) +{ + int i; + TCGv_i32 zero; + + if (!dc_isar_feature(aa32_m_sec_state, s)) { + return false; + } + + if (extract32(a->list, 13, 1)) { + return false; + } + + if (!a->list) { + /* UNPREDICTABLE; we choose to UNDEF */ + return false; + } + + zero = tcg_const_i32(0); + for (i = 0; i < 15; i++) { + if (extract32(a->list, i, 1)) { + /* Clear R[i] */ + tcg_gen_mov_i32(cpu_R[i], zero); + } + } + if (extract32(a->list, 15, 1)) { + /* + * Clear APSR (by calling the MSR helper with the same argument + * as for "MSR APSR_nzcvqg, Rn": mask = 0b1100, SYSM=0) + */ + TCGv_i32 maskreg = tcg_const_i32(0xc << 8); + gen_helper_v7m_msr(cpu_env, maskreg, zero); + tcg_temp_free_i32(maskreg); + } + tcg_temp_free_i32(zero); + return true; +} + /* * Branch, branch with link */ -- 2.20.1 For M-profile before v8.1M, the only valid register for VMSR/VMRS is the FPSCR. We have a comment that states this, but the actual logic to forbid accesses for any other register value is missing, so we would end up with A-profile style behaviour. Add the missing check. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-7-peter.maydell@linaro.org --- target/arm/translate-vfp.c.inc | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) * Accesses to R15 are UNPREDICTABLE; we choose to undef. * (FPSCR -> r15 is a special case which writes to the PSR flags.) */ - if (a->rt == 15 && (!a->l || a->reg != ARM_VFP_FPSCR)) { + if (a->reg != ARM_VFP_FPSCR) { + return false; + } + if (a->rt == 15 && !a->l) { return false; } } -- 2.20.1 Currently M-profile borrows the A-profile code for VMSR and VMRS (access to the FP system registers), because all it needs to support is the FPSCR. In v8.1M things become significantly more complicated in two ways: * there are several new FP system registers; some have side effects on read, and one (FPCXT_NS) needs to avoid the usual vfp_access_check() and the "only if FPU implemented" check * all sysregs are now accessible both by VMRS/VMSR (which reads/writes a general purpose register) and also by VLDR/VSTR (which reads/writes them directly to memory) Refactor the structure of how we handle VMSR/VMRS to cope with this: * keep the M-profile code entirely separate from the A-profile code * abstract out the "read or write the general purpose register" part of the code into a loadfn or storefn function pointer, so we can reuse it for VLDR/VSTR. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-8-peter.maydell@linaro.org --- target/arm/cpu.h | 3 + target/arm/translate-vfp.c.inc | 182 ++++++++++++++++++++++++++++++--- 2 files changed, 171 insertions(+), 14 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ enum arm_cpu_mode { #define ARM_VFP_FPINST 9 #define ARM_VFP_FPINST2 10 +/* QEMU-internal value meaning "FPSCR, but we care only about NZCV" */ +#define QEMU_VFP_FPSCR_NZCV 0xffff + /* iwMMXt coprocessor control registers. */ #define ARM_IWMMXT_wCID 0 #define ARM_IWMMXT_wCon 1 diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VDUP(DisasContext *s, arg_VDUP *a) return true; } +/* + * M-profile provides two different sets of instructions that can + * access floating point system registers: VMSR/VMRS (which move + * to/from a general purpose register) and VLDR/VSTR sysreg (which + * move directly to/from memory). In some cases there are also side + * effects which must happen after any write to memory (which could + * cause an exception). So we implement the common logic for the + * sysreg access in gen_M_fp_sysreg_write() and gen_M_fp_sysreg_read(), + * which take pointers to callback functions which will perform the + * actual "read/write general purpose register" and "read/write + * memory" operations. + */ + +/* + * Emit code to store the sysreg to its final destination; frees the + * TCG temp 'value' it is passed. + */ +typedef void fp_sysreg_storefn(DisasContext *s, void *opaque, TCGv_i32 value); +/* + * Emit code to load the value to be copied to the sysreg; returns + * a new TCG temporary + */ +typedef TCGv_i32 fp_sysreg_loadfn(DisasContext *s, void *opaque); + +/* Common decode/access checks for fp sysreg read/write */ +typedef enum FPSysRegCheckResult { + FPSysRegCheckFailed, /* caller should return false */ + FPSysRegCheckDone, /* caller should return true */ + FPSysRegCheckContinue, /* caller should continue generating code */ +} FPSysRegCheckResult; + +static FPSysRegCheckResult fp_sysreg_checks(DisasContext *s, int regno) +{ + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return FPSysRegCheckFailed; + } + + switch (regno) { + case ARM_VFP_FPSCR: + case QEMU_VFP_FPSCR_NZCV: + break; + default: + return FPSysRegCheckFailed; + } + + if (!vfp_access_check(s)) { + return FPSysRegCheckDone; + } + + return FPSysRegCheckContinue; +} + +static bool gen_M_fp_sysreg_write(DisasContext *s, int regno, + + fp_sysreg_loadfn *loadfn, + void *opaque) +{ + /* Do a write to an M-profile floating point system register */ + TCGv_i32 tmp; + + switch (fp_sysreg_checks(s, regno)) { + case FPSysRegCheckFailed: + return false; + case FPSysRegCheckDone: + return true; + case FPSysRegCheckContinue: + break; + } + + switch (regno) { + case ARM_VFP_FPSCR: + tmp = loadfn(s, opaque); + gen_helper_vfp_set_fpscr(cpu_env, tmp); + tcg_temp_free_i32(tmp); + gen_lookup_tb(s); + break; + default: + g_assert_not_reached(); + } + return true; +} + +static bool gen_M_fp_sysreg_read(DisasContext *s, int regno, + fp_sysreg_storefn *storefn, + void *opaque) +{ + /* Do a read from an M-profile floating point system register */ + TCGv_i32 tmp; + + switch (fp_sysreg_checks(s, regno)) { + case FPSysRegCheckFailed: + return false; + case FPSysRegCheckDone: + return true; + case FPSysRegCheckContinue: + break; + } + + switch (regno) { + case ARM_VFP_FPSCR: + tmp = tcg_temp_new_i32(); + gen_helper_vfp_get_fpscr(tmp, cpu_env); + storefn(s, opaque, tmp); + break; + case QEMU_VFP_FPSCR_NZCV: + /* + * Read just NZCV; this is a special case to avoid the + * helper call for the "VMRS to CPSR.NZCV" insn. + */ + tmp = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]); + tcg_gen_andi_i32(tmp, tmp, 0xf0000000); + storefn(s, opaque, tmp); + break; + default: + g_assert_not_reached(); + } + return true; +} + +static void fp_sysreg_to_gpr(DisasContext *s, void *opaque, TCGv_i32 value) +{ + arg_VMSR_VMRS *a = opaque; + + if (a->rt == 15) { + /* Set the 4 flag bits in the CPSR */ + gen_set_nzcv(value); + tcg_temp_free_i32(value); + } else { + store_reg(s, a->rt, value); + } +} + +static TCGv_i32 gpr_to_fp_sysreg(DisasContext *s, void *opaque) +{ + arg_VMSR_VMRS *a = opaque; + + return load_reg(s, a->rt); +} + +static bool gen_M_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) +{ + /* + * Accesses to R15 are UNPREDICTABLE; we choose to undef. + * FPSCR -> r15 is a special case which writes to the PSR flags; + * set a->reg to a special value to tell gen_M_fp_sysreg_read() + * we only care about the top 4 bits of FPSCR there. + */ + if (a->rt == 15) { + if (a->l && a->reg == ARM_VFP_FPSCR) { + a->reg = QEMU_VFP_FPSCR_NZCV; + } else { + return false; + } + } + + if (a->l) { + /* VMRS, move FP system register to gp register */ + return gen_M_fp_sysreg_read(s, a->reg, fp_sysreg_to_gpr, a); + } else { + /* VMSR, move gp register to FP system register */ + return gen_M_fp_sysreg_write(s, a->reg, gpr_to_fp_sysreg, a); + } +} + static bool trans_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) { TCGv_i32 tmp; bool ignore_vfp_enabled = false; - if (!dc_isar_feature(aa32_fpsp_v2, s)) { - return false; + if (arm_dc_feature(s, ARM_FEATURE_M)) { + return gen_M_VMSR_VMRS(s, a); } - if (arm_dc_feature(s, ARM_FEATURE_M)) { - /* - * The only M-profile VFP vmrs/vmsr sysreg is FPSCR. - * Accesses to R15 are UNPREDICTABLE; we choose to undef. - * (FPSCR -> r15 is a special case which writes to the PSR flags.) - */ - if (a->reg != ARM_VFP_FPSCR) { - return false; - } - if (a->rt == 15 && !a->l) { - return false; - } + if (!dc_isar_feature(aa32_fpsp_v2, s)) { + return false; } switch (a->reg) { -- 2.20.1 The constant-expander functions like negate, plus_2, etc, are generally useful; move them up in translate.c so we can use them in the VFP/Neon decoders as well as in the A32/T32/T16 decoders. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-9-peter.maydell@linaro.org --- target/arm/translate.c | 46 +++++++++++++++++++++++------------------- 1 file changed, 25 insertions(+), 21 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void arm_gen_condlabel(DisasContext *s) } } +/* + * Constant expanders for the decoders. + */ + +static int negate(DisasContext *s, int x) +{ + return -x; +} + +static int plus_2(DisasContext *s, int x) +{ + return x + 2; +} + +static int times_2(DisasContext *s, int x) +{ + return x * 2; +} + +static int times_4(DisasContext *s, int x) +{ + return x * 4; +} + /* Flags for the disas_set_da_iss info argument: * lower bits hold the Rt register number, higher bits are flags. */ @@ -XXX,XX +XXX,XX @@ static void arm_skip_unless(DisasContext *s, uint32_t cond) /* - * Constant expanders for the decoders. + * Constant expanders used by T16/T32 decode */ -static int negate(DisasContext *s, int x) -{ - return -x; -} - -static int plus_2(DisasContext *s, int x) -{ - return x + 2; -} - -static int times_2(DisasContext *s, int x) -{ - return x * 2; -} - -static int times_4(DisasContext *s, int x) -{ - return x * 4; -} - /* Return only the rotation part of T32ExpandImm. */ static int t32_expandimm_rot(DisasContext *s, int x) { -- 2.20.1 Implement the new-in-v8.1M VLDR/VSTR variants which directly read or write FP system registers to memory. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-10-peter.maydell@linaro.org --- target/arm/vfp.decode | 14 ++++++ target/arm/translate-vfp.c.inc | 91 ++++++++++++++++++++++++++++++++++ 2 files changed, 105 insertions(+) diff --git a/target/arm/vfp.decode b/target/arm/vfp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp.decode +++ b/target/arm/vfp.decode @@ -XXX,XX +XXX,XX @@ VLDR_VSTR_hp ---- 1101 u:1 .0 l:1 rn:4 .... 1001 imm:8 vd=%vd_sp VLDR_VSTR_sp ---- 1101 u:1 .0 l:1 rn:4 .... 1010 imm:8 vd=%vd_sp VLDR_VSTR_dp ---- 1101 u:1 .0 l:1 rn:4 .... 1011 imm:8 vd=%vd_dp +# M-profile VLDR/VSTR to sysreg +%vldr_sysreg 22:1 13:3 +%imm7_0x4 0:7 !function=times_4 + +&vldr_sysreg rn reg imm a w p +@vldr_sysreg .... ... . a:1 . . . rn:4 ... . ... .. ....... \ + reg=%vldr_sysreg imm=%imm7_0x4 &vldr_sysreg + +# P=0 W=0 is SEE "Related encodings", so split into two patterns +VLDR_sysreg ---- 110 1 . . w:1 1 .... ... 0 111 11 ....... @vldr_sysreg p=1 +VLDR_sysreg ---- 110 0 . . 1 1 .... ... 0 111 11 ....... @vldr_sysreg p=0 w=1 +VSTR_sysreg ---- 110 1 . . w:1 0 .... ... 0 111 11 ....... @vldr_sysreg p=1 +VSTR_sysreg ---- 110 0 . . 1 0 .... ... 0 111 11 ....... @vldr_sysreg p=0 w=1 + # We split the load/store multiple up into two patterns to avoid # overlap with other insns in the "Advanced SIMD load/store and 64-bit move" # grouping: diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) return true; } +static void fp_sysreg_to_memory(DisasContext *s, void *opaque, TCGv_i32 value) +{ + arg_vldr_sysreg *a = opaque; + uint32_t offset = a->imm; + TCGv_i32 addr; + + if (!a->a) { + offset = - offset; + } + + addr = load_reg(s, a->rn); + if (a->p) { + tcg_gen_addi_i32(addr, addr, offset); + } + + if (s->v8m_stackcheck && a->rn == 13 && a->w) { + gen_helper_v8m_stackcheck(cpu_env, addr); + } + + gen_aa32_st_i32(s, value, addr, get_mem_index(s), + MO_UL | MO_ALIGN | s->be_data); + tcg_temp_free_i32(value); + + if (a->w) { + /* writeback */ + if (!a->p) { + tcg_gen_addi_i32(addr, addr, offset); + } + store_reg(s, a->rn, addr); + } else { + tcg_temp_free_i32(addr); + } +} + +static TCGv_i32 memory_to_fp_sysreg(DisasContext *s, void *opaque) +{ + arg_vldr_sysreg *a = opaque; + uint32_t offset = a->imm; + TCGv_i32 addr; + TCGv_i32 value = tcg_temp_new_i32(); + + if (!a->a) { + offset = - offset; + } + + addr = load_reg(s, a->rn); + if (a->p) { + tcg_gen_addi_i32(addr, addr, offset); + } + + if (s->v8m_stackcheck && a->rn == 13 && a->w) { + gen_helper_v8m_stackcheck(cpu_env, addr); + } + + gen_aa32_ld_i32(s, value, addr, get_mem_index(s), + MO_UL | MO_ALIGN | s->be_data); + + if (a->w) { + /* writeback */ + if (!a->p) { + tcg_gen_addi_i32(addr, addr, offset); + } + store_reg(s, a->rn, addr); + } else { + tcg_temp_free_i32(addr); + } + return value; +} + +static bool trans_VLDR_sysreg(DisasContext *s, arg_vldr_sysreg *a) +{ + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + return false; + } + if (a->rn == 15) { + return false; + } + return gen_M_fp_sysreg_write(s, a->reg, memory_to_fp_sysreg, a); +} + +static bool trans_VSTR_sysreg(DisasContext *s, arg_vldr_sysreg *a) +{ + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + return false; + } + if (a->rn == 15) { + return false; + } + return gen_M_fp_sysreg_read(s, a->reg, fp_sysreg_to_memory, a); +} + static bool trans_VMOV_half(DisasContext *s, arg_VMOV_single *a) { TCGv_i32 tmp; -- 2.20.1 v8.1M defines a new FP system register FPSCR_nzcvqc; this behaves like the existing FPSCR, except that it reads and writes only bits [31:27] of the FPSCR (the N, Z, C, V and QC flag bits). (Unlike the FPSCR, the special case for Rt=15 of writing the CPSR.NZCV is not permitted.) Implement the register. Since we don't yet implement MVE, we handle the QC bit as RES0, with todo comments for where we will need to add support later. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-11-peter.maydell@linaro.org --- target/arm/cpu.h | 13 +++++++++++++ target/arm/translate-vfp.c.inc | 27 +++++++++++++++++++++++++++ 2 files changed, 40 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val); #define FPCR_FZ (1 << 24) /* Flush-to-zero enable bit */ #define FPCR_DN (1 << 25) /* Default NaN enable bit */ #define FPCR_QC (1 << 27) /* Cumulative saturation bit */ +#define FPCR_V (1 << 28) /* FP overflow flag */ +#define FPCR_C (1 << 29) /* FP carry flag */ +#define FPCR_Z (1 << 30) /* FP zero flag */ +#define FPCR_N (1 << 31) /* FP negative flag */ + +#define FPCR_NZCV_MASK (FPCR_N | FPCR_Z | FPCR_C | FPCR_V) +#define FPCR_NZCVQC_MASK (FPCR_NZCV_MASK | FPCR_QC) static inline uint32_t vfp_get_fpsr(CPUARMState *env) { @@ -XXX,XX +XXX,XX @@ enum arm_cpu_mode { #define ARM_VFP_FPEXC 8 #define ARM_VFP_FPINST 9 #define ARM_VFP_FPINST2 10 +/* These ones are M-profile only */ +#define ARM_VFP_FPSCR_NZCVQC 2 +#define ARM_VFP_VPR 12 +#define ARM_VFP_P0 13 +#define ARM_VFP_FPCXT_NS 14 +#define ARM_VFP_FPCXT_S 15 /* QEMU-internal value meaning "FPSCR, but we care only about NZCV" */ #define QEMU_VFP_FPSCR_NZCV 0xffff diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static FPSysRegCheckResult fp_sysreg_checks(DisasContext *s, int regno) case ARM_VFP_FPSCR: case QEMU_VFP_FPSCR_NZCV: break; + case ARM_VFP_FPSCR_NZCVQC: + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + return false; + } + break; default: return FPSysRegCheckFailed; } @@ -XXX,XX +XXX,XX @@ static bool gen_M_fp_sysreg_write(DisasContext *s, int regno, tcg_temp_free_i32(tmp); gen_lookup_tb(s); break; + case ARM_VFP_FPSCR_NZCVQC: + { + TCGv_i32 fpscr; + tmp = loadfn(s, opaque); + /* + * TODO: when we implement MVE, write the QC bit. + * For non-MVE, QC is RES0. + */ + tcg_gen_andi_i32(tmp, tmp, FPCR_NZCV_MASK); + fpscr = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]); + tcg_gen_andi_i32(fpscr, fpscr, ~FPCR_NZCV_MASK); + tcg_gen_or_i32(fpscr, fpscr, tmp); + store_cpu_field(fpscr, vfp.xregs[ARM_VFP_FPSCR]); + tcg_temp_free_i32(tmp); + break; + } default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static bool gen_M_fp_sysreg_read(DisasContext *s, int regno, gen_helper_vfp_get_fpscr(tmp, cpu_env); storefn(s, opaque, tmp); break; + case ARM_VFP_FPSCR_NZCVQC: + /* + * TODO: MVE has a QC bit, which we probably won't store + * in the xregs[] field. For non-MVE, where QC is RES0, + * we can just fall through to the FPSCR_NZCV case. + */ case QEMU_VFP_FPSCR_NZCV: /* * Read just NZCV; this is a special case to avoid the -- 2.20.1 We defined a constant name for the mask of NZCV bits in the FPCR/FPSCR in the previous commit; use it in a couple of places in existing code, where we're masking out everything except NZCV for the "load to Rt=15 sets CPSR.NZCV" special case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-12-peter.maydell@linaro.org --- target/arm/translate-vfp.c.inc | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool gen_M_fp_sysreg_read(DisasContext *s, int regno, * helper call for the "VMRS to CPSR.NZCV" insn. */ tmp = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]); - tcg_gen_andi_i32(tmp, tmp, 0xf0000000); + tcg_gen_andi_i32(tmp, tmp, FPCR_NZCV_MASK); storefn(s, opaque, tmp); break; default: @@ -XXX,XX +XXX,XX @@ static bool trans_VMSR_VMRS(DisasContext *s, arg_VMSR_VMRS *a) case ARM_VFP_FPSCR: if (a->rt == 15) { tmp = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]); - tcg_gen_andi_i32(tmp, tmp, 0xf0000000); + tcg_gen_andi_i32(tmp, tmp, FPCR_NZCV_MASK); } else { tmp = tcg_temp_new_i32(); gen_helper_vfp_get_fpscr(tmp, cpu_env); -- 2.20.1 Factor out the code which handles M-profile lazy FP state preservation from full_vfp_access_check(); accesses to the FPCXT_NS register are a special case which need to do just this part (corresponding in the pseudocode to the PreserveFPState() function), and not the full set of actions matching the pseudocode ExecuteFPCheck() which normal FP instructions need to do. 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> Message-id: 20201119215617.29887-13-peter.maydell@linaro.org --- target/arm/translate-vfp.c.inc | 45 ++++++++++++++++++++-------------- 1 file changed, 27 insertions(+), 18 deletions(-) diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static inline long vfp_f16_offset(unsigned reg, bool top) return offs; } +/* + * Generate code for M-profile lazy FP state preservation if needed; + * this corresponds to the pseudocode PreserveFPState() function. + */ +static void gen_preserve_fp_state(DisasContext *s) +{ + if (s->v7m_lspact) { + /* + * Lazy state saving affects external memory and also the NVIC, + * so we must mark it as an IO operation for icount (and cause + * this to be the last insn in the TB). + */ + if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { + s->base.is_jmp = DISAS_UPDATE_EXIT; + gen_io_start(); + } + gen_helper_v7m_preserve_fp_state(cpu_env); + /* + * If the preserve_fp_state helper doesn't throw an exception + * then it will clear LSPACT; we don't need to repeat this for + * any further FP insns in this TB. + */ + s->v7m_lspact = false; + } +} + /* * Check that VFP access is enabled. If it is, do the necessary * M-profile lazy-FP handling and then return true. @@ -XXX,XX +XXX,XX @@ static bool full_vfp_access_check(DisasContext *s, bool ignore_vfp_enabled) /* Handle M-profile lazy FP state mechanics */ /* Trigger lazy-state preservation if necessary */ - if (s->v7m_lspact) { - /* - * Lazy state saving affects external memory and also the NVIC, - * so we must mark it as an IO operation for icount (and cause - * this to be the last insn in the TB). - */ - if (tb_cflags(s->base.tb) & CF_USE_ICOUNT) { - s->base.is_jmp = DISAS_UPDATE_EXIT; - gen_io_start(); - } - gen_helper_v7m_preserve_fp_state(cpu_env); - /* - * If the preserve_fp_state helper doesn't throw an exception - * then it will clear LSPACT; we don't need to repeat this for - * any further FP insns in this TB. - */ - s->v7m_lspact = false; - } + gen_preserve_fp_state(s); /* Update ownership of FP context: set FPCCR.S to match current state */ if (s->v8m_fpccr_s_wrong) { -- 2.20.1 Implement the new-in-v8.1M FPCXT_S floating point system register. This is for saving and restoring the secure floating point context, and it reads and writes bits [27:0] from the FPSCR and the CONTROL.SFPA bit in bit [31]. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-14-peter.maydell@linaro.org --- target/arm/translate-vfp.c.inc | 58 ++++++++++++++++++++++++++++++++++ 1 file changed, 58 insertions(+) diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static FPSysRegCheckResult fp_sysreg_checks(DisasContext *s, int regno) return false; } break; + case ARM_VFP_FPCXT_S: + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + return false; + } + if (!s->v8m_secure) { + return false; + } + break; default: return FPSysRegCheckFailed; } @@ -XXX,XX +XXX,XX @@ static bool gen_M_fp_sysreg_write(DisasContext *s, int regno, tcg_temp_free_i32(tmp); break; } + case ARM_VFP_FPCXT_S: + { + TCGv_i32 sfpa, control, fpscr; + /* Set FPSCR[27:0] and CONTROL.SFPA from value */ + tmp = loadfn(s, opaque); + sfpa = tcg_temp_new_i32(); + tcg_gen_shri_i32(sfpa, tmp, 31); + control = load_cpu_field(v7m.control[M_REG_S]); + tcg_gen_deposit_i32(control, control, sfpa, + R_V7M_CONTROL_SFPA_SHIFT, 1); + store_cpu_field(control, v7m.control[M_REG_S]); + fpscr = load_cpu_field(vfp.xregs[ARM_VFP_FPSCR]); + tcg_gen_andi_i32(fpscr, fpscr, FPCR_NZCV_MASK); + tcg_gen_andi_i32(tmp, tmp, ~FPCR_NZCV_MASK); + tcg_gen_or_i32(fpscr, fpscr, tmp); + store_cpu_field(fpscr, vfp.xregs[ARM_VFP_FPSCR]); + tcg_temp_free_i32(tmp); + tcg_temp_free_i32(sfpa); + break; + } default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static bool gen_M_fp_sysreg_read(DisasContext *s, int regno, tcg_gen_andi_i32(tmp, tmp, FPCR_NZCV_MASK); storefn(s, opaque, tmp); break; + case ARM_VFP_FPCXT_S: + { + TCGv_i32 control, sfpa, fpscr; + /* Bits [27:0] from FPSCR, bit [31] from CONTROL.SFPA */ + tmp = tcg_temp_new_i32(); + sfpa = tcg_temp_new_i32(); + gen_helper_vfp_get_fpscr(tmp, cpu_env); + tcg_gen_andi_i32(tmp, tmp, ~FPCR_NZCV_MASK); + control = load_cpu_field(v7m.control[M_REG_S]); + tcg_gen_andi_i32(sfpa, control, R_V7M_CONTROL_SFPA_MASK); + tcg_gen_shli_i32(sfpa, sfpa, 31 - R_V7M_CONTROL_SFPA_SHIFT); + tcg_gen_or_i32(tmp, tmp, sfpa); + tcg_temp_free_i32(sfpa); + /* + * Store result before updating FPSCR etc, in case + * it is a memory write which causes an exception. + */ + storefn(s, opaque, tmp); + /* + * Now we must reset FPSCR from FPDSCR_NS, and clear + * CONTROL.SFPA; so we'll end the TB here. + */ + tcg_gen_andi_i32(control, control, ~R_V7M_CONTROL_SFPA_MASK); + store_cpu_field(control, v7m.control[M_REG_S]); + fpscr = load_cpu_field(v7m.fpdscr[M_REG_NS]); + gen_helper_vfp_set_fpscr(cpu_env, fpscr); + tcg_temp_free_i32(fpscr); + gen_lookup_tb(s); + break; + } default: g_assert_not_reached(); } -- 2.20.1 The FPDSCR register has a similar layout to the FPSCR. In v8.1M it gains new fields FZ16 (if half-precision floating point is supported) and LTPSIZE (always reads as 4). Update the reset value and the code that handles writes to this register accordingly. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-16-peter.maydell@linaro.org --- target/arm/cpu.h | 5 +++++ hw/intc/armv7m_nvic.c | 9 ++++++++- target/arm/cpu.c | 3 +++ 3 files changed, 16 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ void vfp_set_fpscr(CPUARMState *env, uint32_t val); #define FPCR_IXE (1 << 12) /* Inexact exception trap enable */ #define FPCR_IDE (1 << 15) /* Input Denormal exception trap enable */ #define FPCR_FZ16 (1 << 19) /* ARMv8.2+, FP16 flush-to-zero */ +#define FPCR_RMODE_MASK (3 << 22) /* Rounding mode */ #define FPCR_FZ (1 << 24) /* Flush-to-zero enable bit */ #define FPCR_DN (1 << 25) /* Default NaN enable bit */ +#define FPCR_AHP (1 << 26) /* Alternative half-precision */ #define FPCR_QC (1 << 27) /* Cumulative saturation bit */ #define FPCR_V (1 << 28) /* FP overflow flag */ #define FPCR_C (1 << 29) /* FP carry flag */ #define FPCR_Z (1 << 30) /* FP zero flag */ #define FPCR_N (1 << 31) /* FP negative flag */ +#define FPCR_LTPSIZE_SHIFT 16 /* LTPSIZE, M-profile only */ +#define FPCR_LTPSIZE_MASK (7 << FPCR_LTPSIZE_SHIFT) + #define FPCR_NZCV_MASK (FPCR_N | FPCR_Z | FPCR_C | FPCR_V) #define FPCR_NZCVQC_MASK (FPCR_NZCV_MASK | FPCR_QC) 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 void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, break; case 0xf3c: /* FPDSCR */ if (cpu_isar_feature(aa32_vfp_simd, cpu)) { - value &= 0x07c00000; + uint32_t mask = FPCR_AHP | FPCR_DN | FPCR_FZ | FPCR_RMODE_MASK; + if (cpu_isar_feature(any_fp16, cpu)) { + mask |= FPCR_FZ16; + } + value &= mask; + if (cpu_isar_feature(aa32_lob, cpu)) { + value |= 4 << FPCR_LTPSIZE_SHIFT; + } cpu->env.v7m.fpdscr[attrs.secure] = value; } break; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(DeviceState *dev) * always reset to 4. */ env->v7m.ltpsize = 4; + /* The LTPSIZE field in FPDSCR is constant and reads as 4. */ + env->v7m.fpdscr[M_REG_NS] = 4 << FPCR_LTPSIZE_SHIFT; + env->v7m.fpdscr[M_REG_S] = 4 << FPCR_LTPSIZE_SHIFT; } if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { -- 2.20.1 In v8.0M, on exception entry the registers R0-R3, R12, APSR and EPSR are zeroed for an exception taken to Non-secure state; for an exception taken to Secure state they become UNKNOWN, and we chose to leave them at their previous values. In v8.1M the behaviour is specified more tightly and these registers are always zeroed regardless of the security state that the exception targets (see rule R_KPZV). Implement this. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-17-peter.maydell@linaro.org --- target/arm/m_helper.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -XXX,XX +XXX,XX @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, * Clear registers if necessary to prevent non-secure exception * code being able to see register values from secure code. * Where register values become architecturally UNKNOWN we leave - * them with their previous values. + * them with their previous values. v8.1M is tighter than v8.0M + * here and always zeroes the caller-saved registers regardless + * of the security state the exception is targeting. */ if (arm_feature(env, ARM_FEATURE_M_SECURITY)) { - if (!targets_secure) { + if (!targets_secure || arm_feature(env, ARM_FEATURE_V8_1M)) { /* * Always clear the caller-saved registers (they have been * pushed to the stack earlier in v7m_push_stack()). @@ -XXX,XX +XXX,XX @@ static void v7m_exception_taken(ARMCPU *cpu, uint32_t lr, bool dotailchain, * v7m_push_callee_stack()). */ int i; + /* + * r4..r11 are callee-saves, zero only if background + * state was Secure (EXCRET.S == 1) and exception + * targets Non-secure state + */ + bool zero_callee_saves = !targets_secure && + (lr & R_V7M_EXCRET_S_MASK); for (i = 0; i < 13; i++) { - /* r4..r11 are callee-saves, zero only if EXCRET.S == 1 */ - if (i < 4 || i > 11 || (lr & R_V7M_EXCRET_S_MASK)) { + if (i < 4 || i > 11 || zero_callee_saves) { env->regs[i] = 0; } } -- 2.20.1 In v8.1M, vector table fetch failures don't set HFSR.FORCED (see rule R_LLRP). (In previous versions of the architecture this was either required or IMPDEF.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-18-peter.maydell@linaro.org --- target/arm/m_helper.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -XXX,XX +XXX,XX @@ load_fail: * The HardFault is Secure if BFHFNMINS is 0 (meaning that all HFs are * secure); otherwise it targets the same security state as the * underlying exception. + * In v8.1M HardFaults from vector table fetch fails don't set FORCED. */ if (!(cpu->env.v7m.aircr & R_V7M_AIRCR_BFHFNMINS_MASK)) { exc_secure = true; } - env->v7m.hfsr |= R_V7M_HFSR_VECTTBL_MASK | R_V7M_HFSR_FORCED_MASK; + env->v7m.hfsr |= R_V7M_HFSR_VECTTBL_MASK; + if (!arm_feature(env, ARM_FEATURE_V8_1M)) { + env->v7m.hfsr |= R_V7M_HFSR_FORCED_MASK; + } armv7m_nvic_set_pending_derived(env->nvic, ARMV7M_EXCP_HARD, exc_secure); return false; } -- 2.20.1 In v8.1M a REVIDR register is defined, which is at address 0xe00ecfc and is a read-only IMPDEF register providing implementation specific minor revision information, like the v8A REVIDR_EL1. Implement this. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-19-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) } return val; } + case 0xcfc: + if (!arm_feature(&cpu->env, ARM_FEATURE_V8_1M)) { + goto bad_offset; + } + return cpu->revidr; case 0xd00: /* CPUID Base. */ return cpu->midr; case 0xd04: /* Interrupt Control State (ICSR) */ -- 2.20.1 In v8.1M a new exception return check is added which may cause a NOCP UsageFault (see rule R_XLTP): before we clear s0..s15 and the FPSCR we must check whether access to CP10 from the Security state of the returning exception is disabled; if it is then we must take a fault. (Note that for our implementation CPPWR is always RAZ/WI and so can never cause CP10 accesses to fail.) The other v8.1M change to this register-clearing code is that if MVE is implemented VPR must also be cleared, so add a TODO comment to that effect. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-20-peter.maydell@linaro.org --- target/arm/m_helper.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -XXX,XX +XXX,XX @@ static void do_v7m_exception_exit(ARMCPU *cpu) v7m_exception_taken(cpu, excret, true, false); return; } else { - /* Clear s0..s15 and FPSCR */ + if (arm_feature(env, ARM_FEATURE_V8_1M)) { + /* v8.1M adds this NOCP check */ + bool nsacr_pass = exc_secure || + extract32(env->v7m.nsacr, 10, 1); + bool cpacr_pass = v7m_cpacr_pass(env, exc_secure, true); + if (!nsacr_pass) { + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, true); + env->v7m.cfsr[M_REG_S] |= R_V7M_CFSR_NOCP_MASK; + qemu_log_mask(CPU_LOG_INT, "...taking UsageFault on existing " + "stackframe: NSACR prevents clearing FPU registers\n"); + v7m_exception_taken(cpu, excret, true, false); + } else if (!cpacr_pass) { + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, + exc_secure); + env->v7m.cfsr[exc_secure] |= R_V7M_CFSR_NOCP_MASK; + qemu_log_mask(CPU_LOG_INT, "...taking UsageFault on existing " + "stackframe: CPACR prevents clearing FPU registers\n"); + v7m_exception_taken(cpu, excret, true, false); + } + } + /* Clear s0..s15 and FPSCR; TODO also VPR when MVE is implemented */ int i; for (i = 0; i < 16; i += 2) { -- 2.20.1 v8.1M adds new encodings of VLLDM and VLSTM (where bit 7 is set). The only difference is that: * the old T1 encodings UNDEF if the implementation implements 32 Dregs (this is currently architecturally impossible for M-profile) * the new T2 encodings have the implementation-defined option to read from memory (discarding the data) or write UNKNOWN values to memory for the stack slots that would be D16-D31 We choose not to make those accesses, so for us the two instructions behave identically assuming they don't UNDEF. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-21-peter.maydell@linaro.org --- target/arm/m-nocp.decode | 2 +- target/arm/translate-vfp.c.inc | 25 +++++++++++++++++++++++++ 2 files changed, 26 insertions(+), 1 deletion(-) diff --git a/target/arm/m-nocp.decode b/target/arm/m-nocp.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m-nocp.decode +++ b/target/arm/m-nocp.decode @@ -XXX,XX +XXX,XX @@ { # Special cases which do not take an early NOCP: VLLDM and VLSTM - VLLDM_VLSTM 1110 1100 001 l:1 rn:4 0000 1010 0000 0000 + VLLDM_VLSTM 1110 1100 001 l:1 rn:4 0000 1010 op:1 000 0000 # VSCCLRM (new in v8.1M) is similar: VSCCLRM 1110 1100 1.01 1111 .... 1011 imm:7 0 vd=%vd_dp size=3 VSCCLRM 1110 1100 1.01 1111 .... 1010 imm:8 vd=%vd_sp size=2 diff --git a/target/arm/translate-vfp.c.inc b/target/arm/translate-vfp.c.inc index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c.inc +++ b/target/arm/translate-vfp.c.inc @@ -XXX,XX +XXX,XX @@ static bool trans_VLLDM_VLSTM(DisasContext *s, arg_VLLDM_VLSTM *a) !arm_dc_feature(s, ARM_FEATURE_V8)) { return false; } + + if (a->op) { + /* + * T2 encoding ({D0-D31} reglist): v8.1M and up. We choose not + * to take the IMPDEF option to make memory accesses to the stack + * slots that correspond to the D16-D31 registers (discarding + * read data and writing UNKNOWN values), so for us the T2 + * encoding behaves identically to the T1 encoding. + */ + if (!arm_dc_feature(s, ARM_FEATURE_V8_1M)) { + return false; + } + } else { + /* + * T1 encoding ({D0-D15} reglist); undef if we have 32 Dregs. + * This is currently architecturally impossible, but we add the + * check to stay in line with the pseudocode. Note that we must + * emit code for the UNDEF so it takes precedence over the NOCP. + */ + if (dc_isar_feature(aa32_simd_r32, s)) { + unallocated_encoding(s); + return true; + } + } + /* * If not secure, UNDEF. We must emit code for this * rather than returning false so that this takes -- 2.20.1 v8.1M introduces a new TRD flag in the CCR register, which enables checking for stack frame integrity signatures on SG instructions. This bit is not banked, and is always RAZ/WI to Non-secure code. Adjust the code for handling CCR reads and writes to handle this. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-23-peter.maydell@linaro.org --- target/arm/cpu.h | 2 ++ hw/intc/armv7m_nvic.c | 26 ++++++++++++++++++-------- 2 files changed, 20 insertions(+), 8 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(V7M_CCR, STKOFHFNMIGN, 10, 1) FIELD(V7M_CCR, DC, 16, 1) FIELD(V7M_CCR, IC, 17, 1) FIELD(V7M_CCR, BP, 18, 1) +FIELD(V7M_CCR, LOB, 19, 1) +FIELD(V7M_CCR, TRD, 20, 1) /* V7M SCR bits */ FIELD(V7M_SCR, SLEEPONEXIT, 1, 1) diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) } return cpu->env.v7m.scr[attrs.secure]; case 0xd14: /* Configuration Control. */ - /* The BFHFNMIGN bit is the only non-banked bit; we - * keep it in the non-secure copy of the register. + /* + * Non-banked bits: BFHFNMIGN (stored in the NS copy of the register) + * and TRD (stored in the S copy of the register) */ val = cpu->env.v7m.ccr[attrs.secure]; val |= cpu->env.v7m.ccr[M_REG_NS] & R_V7M_CCR_BFHFNMIGN_MASK; @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, cpu->env.v7m.scr[attrs.secure] = value; break; case 0xd14: /* Configuration Control. */ + { + uint32_t mask; + if (!arm_feature(&cpu->env, ARM_FEATURE_M_MAIN)) { goto bad_offset; } /* Enforce RAZ/WI on reserved and must-RAZ/WI bits */ - value &= (R_V7M_CCR_STKALIGN_MASK | - R_V7M_CCR_BFHFNMIGN_MASK | - R_V7M_CCR_DIV_0_TRP_MASK | - R_V7M_CCR_UNALIGN_TRP_MASK | - R_V7M_CCR_USERSETMPEND_MASK | - R_V7M_CCR_NONBASETHRDENA_MASK); + mask = R_V7M_CCR_STKALIGN_MASK | + R_V7M_CCR_BFHFNMIGN_MASK | + R_V7M_CCR_DIV_0_TRP_MASK | + R_V7M_CCR_UNALIGN_TRP_MASK | + R_V7M_CCR_USERSETMPEND_MASK | + R_V7M_CCR_NONBASETHRDENA_MASK; + if (arm_feature(&cpu->env, ARM_FEATURE_V8_1M) && attrs.secure) { + /* TRD is always RAZ/WI from NS */ + mask |= R_V7M_CCR_TRD_MASK; + } + value &= mask; if (arm_feature(&cpu->env, ARM_FEATURE_V8)) { /* v8M makes NONBASETHRDENA and STKALIGN be RES1 */ @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, cpu->env.v7m.ccr[attrs.secure] = value; break; + } case 0xd24: /* System Handler Control and State (SHCSR) */ if (!arm_feature(&cpu->env, ARM_FEATURE_V7)) { goto bad_offset; -- 2.20.1 v8.1M introduces a new TRD flag in the CCR register, which enables checking for stack frame integrity signatures on SG instructions. Add the code in the SG insn implementation for the new behaviour. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-24-peter.maydell@linaro.org --- target/arm/m_helper.c | 86 +++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 86 insertions(+) diff --git a/target/arm/m_helper.c b/target/arm/m_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/m_helper.c +++ b/target/arm/m_helper.c @@ -XXX,XX +XXX,XX @@ static bool v7m_read_half_insn(ARMCPU *cpu, ARMMMUIdx mmu_idx, return true; } +static bool v7m_read_sg_stack_word(ARMCPU *cpu, ARMMMUIdx mmu_idx, + uint32_t addr, uint32_t *spdata) +{ + /* + * Read a word of data from the stack for the SG instruction, + * writing the value into *spdata. If the load succeeds, return + * true; otherwise pend an appropriate exception and return false. + * (We can't use data load helpers here that throw an exception + * because of the context we're called in, which is halfway through + * arm_v7m_cpu_do_interrupt().) + */ + CPUState *cs = CPU(cpu); + CPUARMState *env = &cpu->env; + MemTxAttrs attrs = {}; + MemTxResult txres; + target_ulong page_size; + hwaddr physaddr; + int prot; + ARMMMUFaultInfo fi = {}; + ARMCacheAttrs cacheattrs = {}; + uint32_t value; + + if (get_phys_addr(env, addr, MMU_DATA_LOAD, mmu_idx, &physaddr, + &attrs, &prot, &page_size, &fi, &cacheattrs)) { + /* MPU/SAU lookup failed */ + if (fi.type == ARMFault_QEMU_SFault) { + qemu_log_mask(CPU_LOG_INT, + "...SecureFault during stack word read\n"); + env->v7m.sfsr |= R_V7M_SFSR_AUVIOL_MASK | R_V7M_SFSR_SFARVALID_MASK; + env->v7m.sfar = addr; + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SECURE, false); + } else { + qemu_log_mask(CPU_LOG_INT, + "...MemManageFault during stack word read\n"); + env->v7m.cfsr[M_REG_S] |= R_V7M_CFSR_DACCVIOL_MASK | + R_V7M_CFSR_MMARVALID_MASK; + env->v7m.mmfar[M_REG_S] = addr; + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_MEM, false); + } + return false; + } + value = address_space_ldl(arm_addressspace(cs, attrs), physaddr, + attrs, &txres); + if (txres != MEMTX_OK) { + /* BusFault trying to read the data */ + qemu_log_mask(CPU_LOG_INT, + "...BusFault during stack word read\n"); + env->v7m.cfsr[M_REG_NS] |= + (R_V7M_CFSR_PRECISERR_MASK | R_V7M_CFSR_BFARVALID_MASK); + env->v7m.bfar = addr; + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_BUS, false); + return false; + } + + *spdata = value; + return true; +} + static bool v7m_handle_execute_nsc(ARMCPU *cpu) { /* @@ -XXX,XX +XXX,XX @@ static bool v7m_handle_execute_nsc(ARMCPU *cpu) */ qemu_log_mask(CPU_LOG_INT, "...really an SG instruction at 0x%08" PRIx32 ", executing it\n", env->regs[15]); + + if (cpu_isar_feature(aa32_m_sec_state, cpu) && + !arm_v7m_is_handler_mode(env)) { + /* + * v8.1M exception stack frame integrity check. Note that we + * must perform the memory access even if CCR_S.TRD is zero + * and we aren't going to check what the data loaded is. + */ + uint32_t spdata, sp; + + /* + * We know we are currently NS, so the S stack pointers must be + * in other_ss_{psp,msp}, not in regs[13]/other_sp. + */ + sp = v7m_using_psp(env) ? env->v7m.other_ss_psp : env->v7m.other_ss_msp; + if (!v7m_read_sg_stack_word(cpu, mmu_idx, sp, &spdata)) { + /* Stack access failed and an exception has been pended */ + return false; + } + + if (env->v7m.ccr[M_REG_S] & R_V7M_CCR_TRD_MASK) { + if (((spdata & ~1) == 0xfefa125a) || + !(env->v7m.control[M_REG_S] & 1)) { + goto gen_invep; + } + } + } + env->regs[14] &= ~1; env->v7m.control[M_REG_S] &= ~R_V7M_CONTROL_SFPA_MASK; switch_v7m_security_state(env, true); -- 2.20.1 In commit 077d7449100d824a4 we added code to handle the v8M requirement that returns from NMI or HardFault forcibly deactivate those exceptions regardless of what interrupt the guest is trying to deactivate. Unfortunately this broke the handling of the "illegal exception return because the returning exception number is not active" check for those cases. In the pseudocode this test is done on the exception the guest asks to return from, but because our implementation was doing this in armv7m_nvic_complete_irq() after the new "deactivate NMI/HardFault regardless" code we ended up doing the test on the VecInfo for that exception instead, which usually meant failing to raise the illegal exception return fault. In the case for "configurable exception targeting the opposite security state" we detected the illegal-return case but went ahead and deactivated the VecInfo anyway, which is wrong because that is the VecInfo for the other security state. Rearrange the code so that we first identify the illegal return cases, then see if we really need to deactivate NMI or HardFault instead, and finally do the deactivation. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-25-peter.maydell@linaro.org --- hw/intc/armv7m_nvic.c | 59 +++++++++++++++++++++++-------------------- 1 file changed, 32 insertions(+), 27 deletions(-) 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 @@ int armv7m_nvic_complete_irq(void *opaque, int irq, bool secure) { NVICState *s = (NVICState *)opaque; VecInfo *vec = NULL; - int ret; + int ret = 0; assert(irq > ARMV7M_EXCP_RESET && irq < s->num_irq); + trace_nvic_complete_irq(irq, secure); + + if (secure && exc_is_banked(irq)) { + vec = &s->sec_vectors[irq]; + } else { + vec = &s->vectors[irq]; + } + + /* + * Identify illegal exception return cases. We can't immediately + * return at this point because we still need to deactivate + * (either this exception or NMI/HardFault) first. + */ + if (!exc_is_banked(irq) && exc_targets_secure(s, irq) != secure) { + /* + * Return from a configurable exception targeting the opposite + * security state from the one we're trying to complete it for. + * Clear vec because it's not really the VecInfo for this + * (irq, secstate) so we mustn't deactivate it. + */ + ret = -1; + vec = NULL; + } else if (!vec->active) { + /* Return from an inactive interrupt */ + ret = -1; + } else { + /* Legal return, we will return the RETTOBASE bit value to the caller */ + ret = nvic_rettobase(s); + } + /* * For negative priorities, v8M will forcibly deactivate the appropriate * NMI or HardFault regardless of what interrupt we're being asked to @@ -XXX,XX +XXX,XX @@ int armv7m_nvic_complete_irq(void *opaque, int irq, bool secure) } if (!vec) { - if (secure && exc_is_banked(irq)) { - vec = &s->sec_vectors[irq]; - } else { - vec = &s->vectors[irq]; - } - } - - trace_nvic_complete_irq(irq, secure); - - if (!vec->active) { - /* Tell the caller this was an illegal exception return */ - return -1; - } - - /* - * If this is a configurable exception and it is currently - * targeting the opposite security state from the one we're trying - * to complete it for, this counts as an illegal exception return. - * We still need to deactivate whatever vector the logic above has - * selected, though, as it might not be the same as the one for the - * requested exception number. - */ - if (!exc_is_banked(irq) && exc_targets_secure(s, irq) != secure) { - ret = -1; - } else { - ret = nvic_rettobase(s); + return ret; } vec->active = 0; -- 2.20.1 For v8.1M the architecture mandates that CPUs must provide at least the "minimal RAS implementation" from the Reliability, Availability and Serviceability extension. This consists of: * an ESB instruction which is a NOP -- since it is in the HINT space we need only add a comment * an RFSR register which will RAZ/WI * a RAZ/WI AIRCR.IESB bit -- the code which handles writes to AIRCR does not allow setting of RES0 bits, so we already treat this as RAZ/WI; add a comment noting that this is deliberate * minimal implementation of the RAS register block at 0xe0005000 -- this will be in a subsequent commit * setting the ID_PFR0.RAS field to 0b0010 -- we will do this when we add the Cortex-M55 CPU model Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-26-peter.maydell@linaro.org --- target/arm/cpu.h | 14 ++++++++++++++ target/arm/t32.decode | 4 ++++ hw/intc/armv7m_nvic.c | 13 +++++++++++++ 3 files changed, 31 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(ID_MMFR4, LSM, 20, 4) FIELD(ID_MMFR4, CCIDX, 24, 4) FIELD(ID_MMFR4, EVT, 28, 4) +FIELD(ID_PFR0, STATE0, 0, 4) +FIELD(ID_PFR0, STATE1, 4, 4) +FIELD(ID_PFR0, STATE2, 8, 4) +FIELD(ID_PFR0, STATE3, 12, 4) +FIELD(ID_PFR0, CSV2, 16, 4) +FIELD(ID_PFR0, AMU, 20, 4) +FIELD(ID_PFR0, DIT, 24, 4) +FIELD(ID_PFR0, RAS, 28, 4) + FIELD(ID_PFR1, PROGMOD, 0, 4) FIELD(ID_PFR1, SECURITY, 4, 4) FIELD(ID_PFR1, MPROGMOD, 8, 4) @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_predinv(const ARMISARegisters *id) return FIELD_EX32(id->id_isar6, ID_ISAR6, SPECRES) != 0; } +static inline bool isar_feature_aa32_ras(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_pfr0, ID_PFR0, RAS) != 0; +} + static inline bool isar_feature_aa32_mprofile(const ARMISARegisters *id) { return FIELD_EX32(id->id_pfr1, ID_PFR1, MPROGMOD) != 0; diff --git a/target/arm/t32.decode b/target/arm/t32.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/t32.decode +++ b/target/arm/t32.decode @@ -XXX,XX +XXX,XX @@ CLZ 1111 1010 1011 ---- 1111 .... 1000 .... @rdm # SEV 1111 0011 1010 1111 1000 0000 0000 0100 # SEVL 1111 0011 1010 1111 1000 0000 0000 0101 + # For M-profile minimal-RAS ESB can be a NOP, which is the + # default behaviour since it is in the hint space. + # ESB 1111 0011 1010 1111 1000 0000 0001 0000 + # The canonical nop ends in 0000 0000, but the whole rest # of the space is "reserved hint, behaves as nop". NOP 1111 0011 1010 1111 1000 0000 ---- ---- diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) return 0; } return cpu->env.v7m.sfar; + case 0xf04: /* RFSR */ + if (!cpu_isar_feature(aa32_ras, cpu)) { + goto bad_offset; + } + /* We provide minimal-RAS only: RFSR is RAZ/WI */ + return 0; case 0xf34: /* FPCCR */ if (!cpu_isar_feature(aa32_vfp_simd, cpu)) { return 0; @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, R_V7M_AIRCR_PRIGROUP_SHIFT, R_V7M_AIRCR_PRIGROUP_LENGTH); } + /* AIRCR.IESB is RAZ/WI because we implement only minimal RAS */ if (attrs.secure) { /* These bits are only writable by secure */ cpu->env.v7m.aircr = value & @@ -XXX,XX +XXX,XX @@ static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value, } break; } + case 0xf04: /* RFSR */ + if (!cpu_isar_feature(aa32_ras, cpu)) { + goto bad_offset; + } + /* We provide minimal-RAS only: RFSR is RAZ/WI */ + break; case 0xf34: /* FPCCR */ if (cpu_isar_feature(aa32_vfp_simd, cpu)) { /* Not all bits here are banked. */ -- 2.20.1 The RAS feature has a block of memory-mapped registers at offset 0x5000 within the PPB. For a "minimal RAS" implementation we provide no error records and so the only registers that exist in the block are ERRIIDR and ERRDEVID. The "RAZ/WI for privileged, BusFault for nonprivileged" behaviour of the "nvic-default" region is actually valid for minimal-RAS, so the main benefit of providing an explicit implementation of the register block is more accurate LOG_UNIMP messages, and a framework for where we could add a real RAS implementation later if necessary. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-27-peter.maydell@linaro.org --- include/hw/intc/armv7m_nvic.h | 1 + hw/intc/armv7m_nvic.c | 56 +++++++++++++++++++++++++++++++++++ 2 files changed, 57 insertions(+) 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/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); } -- 2.20.1 Correct a typo in the name we give the NVIC object. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201119215617.29887-28-peter.maydell@linaro.org --- hw/arm/armv7m.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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_instance_init(Object *obj) memory_region_init(&s->container, obj, "armv7m-container", UINT64_MAX); - object_initialize_child(obj, "nvnic", &s->nvic, TYPE_NVIC); + object_initialize_child(obj, "nvic", &s->nvic, TYPE_NVIC); object_property_add_alias(obj, "num-irq", OBJECT(&s->nvic), "num-irq"); -- 2.20.1