target-arm queue: I have a lot more still in my to-review queue, but my rule of thumb is when I get to 50 patches or so to send out what I have. thanks -- PMM The following changes since commit 9a7beaad3dbba982f7a461d676b55a5c3851d312: Merge remote-tracking branch 'remotes/alistair/tags/pull-riscv-to-apply-20210304' into staging (2021-03-05 10:47:46 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210305 for you to fetch changes up to 2c669ff88ec6733420a000103a2b8b9e93df4945: hw/arm/mps2: Update old infocenter.arm.com URLs (2021-03-05 15:17:38 +0000) ---------------------------------------------------------------- * sbsa-ref: remove cortex-a53 from list of supported cpus * sbsa-ref: add 'max' to list of allowed cpus * target/arm: Add support for FEAT_SSBS, Speculative Store Bypass Safe * npcm7xx: add EMC model * xlnx-zynqmp: Remove obsolete 'has_rpu' property * target/arm: Speed up aarch64 TBL/TBX * virtio-mmio: improve virtio-mmio get_dev_path alog * target/arm: Use TCF0 and TFSRE0 for unprivileged tag checks * target/arm: Restrict v8M IDAU to TCG * target/arm/cpu: Update coding style to make checkpatch.pl happy * musicpal, tc6393xb, omap_lcdc, tcx: drop dead code for non-32-bit-RGB surfaces * Add new board: mps3-an524 ---------------------------------------------------------------- Doug Evans (3): hw/net: Add npcm7xx emc model hw/arm: Add npcm7xx emc model tests/qtests: Add npcm7xx emc model test Marcin Juszkiewicz (2): sbsa-ref: remove cortex-a53 from list of supported cpus sbsa-ref: add 'max' to list of allowed cpus Peter Collingbourne (1): target/arm: Use TCF0 and TFSRE0 for unprivileged tag checks Peter Maydell (34): hw/arm/musicpal: Remove dead code for non-32-bit-RGB surfaces hw/display/tc6393xb: Remove dead code for handling non-32bpp surfaces hw/display/tc6393xb: Expand out macros in template header hw/display/tc6393xb: Inline tc6393xb_draw_graphic32() at its callsite hw/display/omap_lcdc: Expand out macros in template header hw/display/omap_lcdc: Drop broken bigendian ifdef hw/display/omap_lcdc: Fix coding style issues in template header hw/display/omap_lcdc: Inline template header into C file hw/display/omap_lcdc: Delete unnecessary macro hw/display/tcx: Drop unnecessary code for handling BGR format outputs hw/arm/mps2-tz: Make SYSCLK frequency board-specific hw/misc/mps2-scc: Support configurable number of OSCCLK values hw/arm/mps2-tz: Correct the OSCCLK settings for mps2-an505 and mps2-an511 hw/arm/mps2-tz: Make the OSCCLK settings be configurable per-board hw/misc/mps2-fpgaio: Make number of LEDs configurable by board hw/misc/mps2-fpgaio: Support SWITCH register hw/arm/mps2-tz: Make FPGAIO switch and LED config per-board hw/arm/mps2-tz: Condition IRQ splitting on number of CPUs, not board type hw/arm/mps2-tz: Make number of IRQs board-specific hw/misc/mps2-scc: Implement CFG_REG5 and CFG_REG6 for MPS3 AN524 hw/arm/mps2-tz: Correct wrong interrupt numbers for DMA and SPI hw/arm/mps2-tz: Allow PPCPortInfo structures to specify device interrupts hw/arm/mps2-tz: Move device IRQ info to data structures hw/arm/mps2-tz: Size the uart-irq-orgate based on the number of UARTs hw/arm/mps2-tz: Allow boards to have different PPCInfo data hw/arm/mps2-tz: Make RAM arrangement board-specific hw/arm/mps2-tz: Set MachineClass default_ram info from RAMInfo data hw/arm/mps2-tz: Support ROMs as well as RAMs hw/arm/mps2-tz: Get armv7m_load_kernel() size argument from RAMInfo hw/arm/mps2-tz: Add new mps3-an524 board hw/arm/mps2-tz: Stub out USB controller for mps3-an524 hw/arm/mps2-tz: Provide PL031 RTC on mps3-an524 docs/system/arm/mps2.rst: Document the new mps3-an524 board hw/arm/mps2: Update old infocenter.arm.com URLs Philippe Mathieu-Daudé (4): hw/arm/xlnx-zynqmp: Remove obsolete 'has_rpu' property hw/i2c/npcm7xx_smbus: Simplify npcm7xx_smbus_init() target/arm: Restrict v8M IDAU to TCG target/arm/cpu: Update coding style to make checkpatch.pl happy Rebecca Cran (3): target/arm: Add support for FEAT_SSBS, Speculative Store Bypass Safe target/arm: Enable FEAT_SSBS for "max" AARCH64 CPU target/arm: Set ID_PFR2.SSBS to 1 for "max" 32-bit CPU Richard Henderson (1): target/arm: Speed up aarch64 TBL/TBX schspa (1): virtio-mmio: improve virtio-mmio get_dev_path alog docs/system/arm/mps2.rst | 24 +- docs/system/arm/nuvoton.rst | 3 +- hw/display/omap_lcd_template.h | 169 -------- hw/display/tc6393xb_template.h | 72 ---- include/hw/arm/armsse.h | 4 +- include/hw/arm/npcm7xx.h | 2 + include/hw/arm/xlnx-zynqmp.h | 2 - include/hw/misc/armsse-cpuid.h | 2 +- include/hw/misc/armsse-mhu.h | 2 +- include/hw/misc/iotkit-secctl.h | 2 +- include/hw/misc/iotkit-sysctl.h | 2 +- include/hw/misc/iotkit-sysinfo.h | 2 +- include/hw/misc/mps2-fpgaio.h | 8 +- include/hw/misc/mps2-scc.h | 10 +- include/hw/net/npcm7xx_emc.h | 286 +++++++++++++ include/ui/console.h | 10 - target/arm/cpu.h | 15 +- target/arm/helper-a64.h | 2 +- target/arm/internals.h | 6 + hw/arm/mps2-tz.c | 632 +++++++++++++++++++++++----- hw/arm/mps2.c | 5 + hw/arm/musicpal.c | 64 ++- hw/arm/npcm7xx.c | 50 ++- hw/arm/sbsa-ref.c | 2 +- hw/arm/xlnx-zynqmp.c | 6 - hw/display/omap_lcdc.c | 129 +++++- hw/display/tc6393xb.c | 48 +-- hw/display/tcx.c | 31 +- hw/i2c/npcm7xx_smbus.c | 1 - hw/misc/armsse-cpuid.c | 2 +- hw/misc/armsse-mhu.c | 2 +- hw/misc/iotkit-sysctl.c | 2 +- hw/misc/iotkit-sysinfo.c | 2 +- hw/misc/mps2-fpgaio.c | 43 +- hw/misc/mps2-scc.c | 93 ++++- hw/net/npcm7xx_emc.c | 857 ++++++++++++++++++++++++++++++++++++++ hw/virtio/virtio-mmio.c | 13 +- target/arm/cpu.c | 23 +- target/arm/cpu64.c | 5 + target/arm/cpu_tcg.c | 8 + target/arm/helper-a64.c | 32 -- target/arm/helper.c | 39 +- target/arm/mte_helper.c | 13 +- target/arm/translate-a64.c | 70 +--- target/arm/vec_helper.c | 48 +++ tests/qtest/npcm7xx_emc-test.c | 862 +++++++++++++++++++++++++++++++++++++++ hw/net/meson.build | 1 + hw/net/trace-events | 17 + tests/qtest/meson.build | 3 +- 49 files changed, 3098 insertions(+), 628 deletions(-) delete mode 100644 hw/display/omap_lcd_template.h delete mode 100644 hw/display/tc6393xb_template.h create mode 100644 include/hw/net/npcm7xx_emc.h create mode 100644 hw/net/npcm7xx_emc.c create mode 100644 tests/qtest/npcm7xx_emc-test.c From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Cortex-A53 supports 40bits of address space. sbsa-ref's memory starts above this limit. Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Acked-by: Leif Lindholm <leif@nuviainc.com> Message-id: 20210216150122.3830863-2-marcin.juszkiewicz@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 1 - 1 file changed, 1 deletion(-) 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[] = { }; static const char * const valid_cpus[] = { - ARM_CPU_TYPE_NAME("cortex-a53"), ARM_CPU_TYPE_NAME("cortex-a57"), ARM_CPU_TYPE_NAME("cortex-a72"), }; -- 2.20.1 From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Let add 'max' cpu while work goes on adding newer CPU types than Cortex-A72. This allows us to check SVE etc support. Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Acked-by: Leif Lindholm <leif@nuviainc.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210216150122.3830863-3-marcin.juszkiewicz@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 1 + 1 file changed, 1 insertion(+) 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[] = { static const char * const valid_cpus[] = { ARM_CPU_TYPE_NAME("cortex-a57"), ARM_CPU_TYPE_NAME("cortex-a72"), + ARM_CPU_TYPE_NAME("max"), }; static bool cpu_type_valid(const char *cpu) -- 2.20.1 From: Rebecca Cran <rebecca@nuviainc.com> Add support for FEAT_SSBS. SSBS (Speculative Store Bypass Safe) is an optional feature in ARMv8.0, and mandatory in ARMv8.5. Signed-off-by: Rebecca Cran <rebecca@nuviainc.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210216224543.16142-2-rebecca@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 15 ++++++++++++++- target/arm/internals.h | 6 ++++++ target/arm/helper.c | 37 +++++++++++++++++++++++++++++++++++++ target/arm/translate-a64.c | 12 ++++++++++++ 4 files changed, 69 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 pmu_init(ARMCPU *cpu); #define SCTLR_TE (1U << 30) /* AArch32 only */ #define SCTLR_EnIB (1U << 30) /* v8.3, AArch64 only */ #define SCTLR_EnIA (1U << 31) /* v8.3, AArch64 only */ +#define SCTLR_DSSBS_32 (1U << 31) /* v8.5, AArch32 only */ #define SCTLR_BT0 (1ULL << 35) /* v8.5-BTI */ #define SCTLR_BT1 (1ULL << 36) /* v8.5-BTI */ #define SCTLR_ITFSB (1ULL << 37) /* v8.5-MemTag */ @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define SCTLR_TCF (3ULL << 40) /* v8.5-MemTag */ #define SCTLR_ATA0 (1ULL << 42) /* v8.5-MemTag */ #define SCTLR_ATA (1ULL << 43) /* v8.5-MemTag */ -#define SCTLR_DSSBS (1ULL << 44) /* v8.5 */ +#define SCTLR_DSSBS_64 (1ULL << 44) /* v8.5, AArch64 only */ #define CPTR_TCPAC (1U << 31) #define CPTR_TTA (1U << 20) @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define CPSR_IL (1U << 20) #define CPSR_DIT (1U << 21) #define CPSR_PAN (1U << 22) +#define CPSR_SSBS (1U << 23) #define CPSR_J (1U << 24) #define CPSR_IT_0_1 (3U << 25) #define CPSR_Q (1U << 27) @@ -XXX,XX +XXX,XX @@ void pmu_init(ARMCPU *cpu); #define PSTATE_A (1U << 8) #define PSTATE_D (1U << 9) #define PSTATE_BTYPE (3U << 10) +#define PSTATE_SSBS (1U << 12) #define PSTATE_IL (1U << 20) #define PSTATE_SS (1U << 21) #define PSTATE_PAN (1U << 22) @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_dit(const ARMISARegisters *id) return FIELD_EX32(id->id_pfr0, ID_PFR0, DIT) != 0; } +static inline bool isar_feature_aa32_ssbs(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_pfr2, ID_PFR2, SSBS) != 0; +} + /* * 64-bit feature tests via id registers. */ @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_dit(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, DIT) != 0; } +static inline bool isar_feature_aa64_ssbs(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr1, ID_AA64PFR1, SSBS) != 0; +} + /* * Feature tests for "does this exist in either 32-bit or 64-bit?" */ diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t aarch32_cpsr_valid_mask(uint64_t features, if (isar_feature_aa32_dit(id)) { valid |= CPSR_DIT; } + if (isar_feature_aa32_ssbs(id)) { + valid |= CPSR_SSBS; + } return valid; } @@ -XXX,XX +XXX,XX @@ static inline uint32_t aarch64_pstate_valid_mask(const ARMISARegisters *id) if (isar_feature_aa64_dit(id)) { valid |= PSTATE_DIT; } + if (isar_feature_aa64_ssbs(id)) { + valid |= PSTATE_SSBS; + } if (isar_feature_aa64_mte(id)) { valid |= PSTATE_TCO; } diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo dit_reginfo = { .readfn = aa64_dit_read, .writefn = aa64_dit_write }; +static uint64_t aa64_ssbs_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + return env->pstate & PSTATE_SSBS; +} + +static void aa64_ssbs_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + env->pstate = (env->pstate & ~PSTATE_SSBS) | (value & PSTATE_SSBS); +} + +static const ARMCPRegInfo ssbs_reginfo = { + .name = "SSBS", .state = ARM_CP_STATE_AA64, + .opc0 = 3, .opc1 = 3, .crn = 4, .crm = 2, .opc2 = 6, + .type = ARM_CP_NO_RAW, .access = PL0_RW, + .readfn = aa64_ssbs_read, .writefn = aa64_ssbs_write +}; + static CPAccessResult aa64_cacheop_poc_access(CPUARMState *env, const ARMCPRegInfo *ri, bool isread) @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) if (cpu_isar_feature(aa64_dit, cpu)) { define_one_arm_cp_reg(cpu, &dit_reginfo); } + if (cpu_isar_feature(aa64_ssbs, cpu)) { + define_one_arm_cp_reg(cpu, &ssbs_reginfo); + } if (arm_feature(env, ARM_FEATURE_EL2) && cpu_isar_feature(aa64_vh, cpu)) { define_arm_cp_regs(cpu, vhe_reginfo); @@ -XXX,XX +XXX,XX @@ static void take_aarch32_exception(CPUARMState *env, int new_mode, env->uncached_cpsr &= ~(CPSR_IL | CPSR_J); env->daif |= mask; + if (cpu_isar_feature(aa32_ssbs, env_archcpu(env))) { + if (env->cp15.sctlr_el[new_el] & SCTLR_DSSBS_32) { + env->uncached_cpsr |= CPSR_SSBS; + } else { + env->uncached_cpsr &= ~CPSR_SSBS; + } + } + if (new_mode == ARM_CPU_MODE_HYP) { env->thumb = (env->cp15.sctlr_el[2] & SCTLR_TE) != 0; env->elr_el[2] = env->regs[15]; @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs) new_mode |= PSTATE_TCO; } + if (cpu_isar_feature(aa64_ssbs, cpu)) { + if (env->cp15.sctlr_el[new_el] & SCTLR_DSSBS_64) { + new_mode |= PSTATE_SSBS; + } else { + new_mode &= ~PSTATE_SSBS; + } + } + pstate_write(env, PSTATE_DAIF | new_mode); env->aarch64 = 1; aarch64_restore_sp(env, new_el); diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void handle_msr_i(DisasContext *s, uint32_t insn, tcg_temp_free_i32(t1); break; + case 0x19: /* SSBS */ + if (!dc_isar_feature(aa64_ssbs, s)) { + goto do_unallocated; + } + if (crm & 1) { + set_pstate_bits(PSTATE_SSBS); + } else { + clear_pstate_bits(PSTATE_SSBS); + } + /* Don't need to rebuild hflags since SSBS is a nop */ + break; + case 0x1a: /* DIT */ if (!dc_isar_feature(aa64_dit, s)) { goto do_unallocated; -- 2.20.1 From: Rebecca Cran <rebecca@nuviainc.com> Set ID_AA64PFR1_EL1.SSBS to 2 and ID_PFR2.SSBS to 1. Signed-off-by: Rebecca Cran <rebecca@nuviainc.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210216224543.16142-3-rebecca@nuviainc.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu64.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = cpu->isar.id_aa64pfr1; t = FIELD_DP64(t, ID_AA64PFR1, BT, 1); + t = FIELD_DP64(t, ID_AA64PFR1, SSBS, 2); /* * Begin with full support for MTE. This will be downgraded to MTE=0 * during realize if the board provides no tag memory, much like @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) u = FIELD_DP32(u, ID_PFR0, DIT, 1); cpu->isar.id_pfr0 = u; + u = cpu->isar.id_pfr2; + u = FIELD_DP32(u, ID_PFR2, SSBS, 1); + cpu->isar.id_pfr2 = u; + u = cpu->isar.id_mmfr3; u = FIELD_DP32(u, ID_MMFR3, PAN, 2); /* ATS1E1 */ cpu->isar.id_mmfr3 = u; -- 2.20.1 From: Rebecca Cran <rebecca@nuviainc.com> Enable FEAT_SSBS for the "max" 32-bit CPU. Signed-off-by: Rebecca Cran <rebecca@nuviainc.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210216224543.16142-4-rebecca@nuviainc.com [PMM: fix typo causing compilation failure] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) t = cpu->isar.id_pfr0; t = FIELD_DP32(t, ID_PFR0, DIT, 1); cpu->isar.id_pfr0 = t; + + t = cpu->isar.id_pfr2; + t = FIELD_DP32(t, ID_PFR2, SSBS, 1); + cpu->isar.id_pfr2 = t; } #endif } -- 2.20.1 From: Doug Evans <dje@google.com> This is a 10/100 ethernet device that has several features. Only the ones needed by the Linux driver have been implemented. See npcm7xx_emc.c for a list of unimplemented features. Reviewed-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Avi Fishman <avi.fishman@nuvoton.com> Signed-off-by: Doug Evans <dje@google.com> Message-id: 20210218212453.831406-2-dje@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/net/npcm7xx_emc.h | 286 ++++++++++++ hw/net/npcm7xx_emc.c | 857 +++++++++++++++++++++++++++++++++++ hw/net/meson.build | 1 + hw/net/trace-events | 17 + 4 files changed, 1161 insertions(+) create mode 100644 include/hw/net/npcm7xx_emc.h create mode 100644 hw/net/npcm7xx_emc.c diff --git a/include/hw/net/npcm7xx_emc.h b/include/hw/net/npcm7xx_emc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/net/npcm7xx_emc.h @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx EMC Module + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#ifndef NPCM7XX_EMC_H +#define NPCM7XX_EMC_H + +#include "hw/irq.h" +#include "hw/sysbus.h" +#include "net/net.h" + +/* 32-bit register indices. */ +enum NPCM7xxPWMRegister { + /* Control registers. */ + REG_CAMCMR, + REG_CAMEN, + + /* There are 16 CAMn[ML] registers. */ + REG_CAMM_BASE, + REG_CAML_BASE, + REG_CAMML_LAST = 0x21, + + REG_TXDLSA = 0x22, + REG_RXDLSA, + REG_MCMDR, + REG_MIID, + REG_MIIDA, + REG_FFTCR, + REG_TSDR, + REG_RSDR, + REG_DMARFC, + REG_MIEN, + + /* Status registers. */ + REG_MISTA, + REG_MGSTA, + REG_MPCNT, + REG_MRPC, + REG_MRPCC, + REG_MREPC, + REG_DMARFS, + REG_CTXDSA, + REG_CTXBSA, + REG_CRXDSA, + REG_CRXBSA, + + NPCM7XX_NUM_EMC_REGS, +}; + +/* REG_CAMCMR fields */ +/* Enable CAM Compare */ +#define REG_CAMCMR_ECMP (1 << 4) +/* Complement CAM Compare */ +#define REG_CAMCMR_CCAM (1 << 3) +/* Accept Broadcast Packet */ +#define REG_CAMCMR_ABP (1 << 2) +/* Accept Multicast Packet */ +#define REG_CAMCMR_AMP (1 << 1) +/* Accept Unicast Packet */ +#define REG_CAMCMR_AUP (1 << 0) + +/* REG_MCMDR fields */ +/* Software Reset */ +#define REG_MCMDR_SWR (1 << 24) +/* Internal Loopback Select */ +#define REG_MCMDR_LBK (1 << 21) +/* Operation Mode Select */ +#define REG_MCMDR_OPMOD (1 << 20) +/* Enable MDC Clock Generation */ +#define REG_MCMDR_ENMDC (1 << 19) +/* Full-Duplex Mode Select */ +#define REG_MCMDR_FDUP (1 << 18) +/* Enable SQE Checking */ +#define REG_MCMDR_ENSEQ (1 << 17) +/* Send PAUSE Frame */ +#define REG_MCMDR_SDPZ (1 << 16) +/* No Defer */ +#define REG_MCMDR_NDEF (1 << 9) +/* Frame Transmission On */ +#define REG_MCMDR_TXON (1 << 8) +/* Strip CRC Checksum */ +#define REG_MCMDR_SPCRC (1 << 5) +/* Accept CRC Error Packet */ +#define REG_MCMDR_AEP (1 << 4) +/* Accept Control Packet */ +#define REG_MCMDR_ACP (1 << 3) +/* Accept Runt Packet */ +#define REG_MCMDR_ARP (1 << 2) +/* Accept Long Packet */ +#define REG_MCMDR_ALP (1 << 1) +/* Frame Reception On */ +#define REG_MCMDR_RXON (1 << 0) + +/* REG_MIEN fields */ +/* Enable Transmit Descriptor Unavailable Interrupt */ +#define REG_MIEN_ENTDU (1 << 23) +/* Enable Transmit Completion Interrupt */ +#define REG_MIEN_ENTXCP (1 << 18) +/* Enable Transmit Interrupt */ +#define REG_MIEN_ENTXINTR (1 << 16) +/* Enable Receive Descriptor Unavailable Interrupt */ +#define REG_MIEN_ENRDU (1 << 10) +/* Enable Receive Good Interrupt */ +#define REG_MIEN_ENRXGD (1 << 4) +/* Enable Receive Interrupt */ +#define REG_MIEN_ENRXINTR (1 << 0) + +/* REG_MISTA fields */ +/* TODO: Add error fields and support simulated errors? */ +/* Transmit Bus Error Interrupt */ +#define REG_MISTA_TXBERR (1 << 24) +/* Transmit Descriptor Unavailable Interrupt */ +#define REG_MISTA_TDU (1 << 23) +/* Transmit Completion Interrupt */ +#define REG_MISTA_TXCP (1 << 18) +/* Transmit Interrupt */ +#define REG_MISTA_TXINTR (1 << 16) +/* Receive Bus Error Interrupt */ +#define REG_MISTA_RXBERR (1 << 11) +/* Receive Descriptor Unavailable Interrupt */ +#define REG_MISTA_RDU (1 << 10) +/* DMA Early Notification Interrupt */ +#define REG_MISTA_DENI (1 << 9) +/* Maximum Frame Length Interrupt */ +#define REG_MISTA_DFOI (1 << 8) +/* Receive Good Interrupt */ +#define REG_MISTA_RXGD (1 << 4) +/* Packet Too Long Interrupt */ +#define REG_MISTA_PTLE (1 << 3) +/* Receive Interrupt */ +#define REG_MISTA_RXINTR (1 << 0) + +/* REG_MGSTA fields */ +/* Transmission Halted */ +#define REG_MGSTA_TXHA (1 << 11) +/* Receive Halted */ +#define REG_MGSTA_RXHA (1 << 11) + +/* REG_DMARFC fields */ +/* Maximum Receive Frame Length */ +#define REG_DMARFC_RXMS(word) extract32((word), 0, 16) + +/* REG MIIDA fields */ +/* Busy Bit */ +#define REG_MIIDA_BUSY (1 << 17) + +/* Transmit and receive descriptors */ +typedef struct NPCM7xxEMCTxDesc NPCM7xxEMCTxDesc; +typedef struct NPCM7xxEMCRxDesc NPCM7xxEMCRxDesc; + +struct NPCM7xxEMCTxDesc { + uint32_t flags; + uint32_t txbsa; + uint32_t status_and_length; + uint32_t ntxdsa; +}; + +struct NPCM7xxEMCRxDesc { + uint32_t status_and_length; + uint32_t rxbsa; + uint32_t reserved; + uint32_t nrxdsa; +}; + +/* NPCM7xxEMCTxDesc.flags values */ +/* Owner: 0 = cpu, 1 = emc */ +#define TX_DESC_FLAG_OWNER_MASK (1 << 31) +/* Transmit interrupt enable */ +#define TX_DESC_FLAG_INTEN (1 << 2) +/* CRC append */ +#define TX_DESC_FLAG_CRCAPP (1 << 1) +/* Padding enable */ +#define TX_DESC_FLAG_PADEN (1 << 0) + +/* NPCM7xxEMCTxDesc.status_and_length values */ +/* Collision count */ +#define TX_DESC_STATUS_CCNT_SHIFT 28 +#define TX_DESC_STATUS_CCNT_BITSIZE 4 +/* SQE error */ +#define TX_DESC_STATUS_SQE (1 << 26) +/* Transmission paused */ +#define TX_DESC_STATUS_PAU (1 << 25) +/* P transmission halted */ +#define TX_DESC_STATUS_TXHA (1 << 24) +/* Late collision */ +#define TX_DESC_STATUS_LC (1 << 23) +/* Transmission abort */ +#define TX_DESC_STATUS_TXABT (1 << 22) +/* No carrier sense */ +#define TX_DESC_STATUS_NCS (1 << 21) +/* Defer exceed */ +#define TX_DESC_STATUS_EXDEF (1 << 20) +/* Transmission complete */ +#define TX_DESC_STATUS_TXCP (1 << 19) +/* Transmission deferred */ +#define TX_DESC_STATUS_DEF (1 << 17) +/* Transmit interrupt */ +#define TX_DESC_STATUS_TXINTR (1 << 16) + +#define TX_DESC_PKT_LEN(word) extract32((word), 0, 16) + +/* Transmit buffer start address */ +#define TX_DESC_TXBSA(word) ((uint32_t) (word) & ~3u) + +/* Next transmit descriptor start address */ +#define TX_DESC_NTXDSA(word) ((uint32_t) (word) & ~3u) + +/* NPCM7xxEMCRxDesc.status_and_length values */ +/* Owner: 0b00 = cpu, 0b01 = undefined, 0b10 = emc, 0b11 = undefined */ +#define RX_DESC_STATUS_OWNER_SHIFT 30 +#define RX_DESC_STATUS_OWNER_BITSIZE 2 +#define RX_DESC_STATUS_OWNER_MASK (3 << RX_DESC_STATUS_OWNER_SHIFT) +/* Runt packet */ +#define RX_DESC_STATUS_RP (1 << 22) +/* Alignment error */ +#define RX_DESC_STATUS_ALIE (1 << 21) +/* Frame reception complete */ +#define RX_DESC_STATUS_RXGD (1 << 20) +/* Packet too long */ +#define RX_DESC_STATUS_PTLE (1 << 19) +/* CRC error */ +#define RX_DESC_STATUS_CRCE (1 << 17) +/* Receive interrupt */ +#define RX_DESC_STATUS_RXINTR (1 << 16) + +#define RX_DESC_PKT_LEN(word) extract32((word), 0, 16) + +/* Receive buffer start address */ +#define RX_DESC_RXBSA(word) ((uint32_t) (word) & ~3u) + +/* Next receive descriptor start address */ +#define RX_DESC_NRXDSA(word) ((uint32_t) (word) & ~3u) + +/* Minimum packet length, when TX_DESC_FLAG_PADEN is set. */ +#define MIN_PACKET_LENGTH 64 + +struct NPCM7xxEMCState { + /*< private >*/ + SysBusDevice parent; + /*< public >*/ + + MemoryRegion iomem; + + qemu_irq tx_irq; + qemu_irq rx_irq; + + NICState *nic; + NICConf conf; + + /* 0 or 1, for log messages */ + uint8_t emc_num; + + uint32_t regs[NPCM7XX_NUM_EMC_REGS]; + + /* + * tx is active. Set to true by TSDR and then switches off when out of + * descriptors. If the TXON bit in REG_MCMDR is off then this is off. + */ + bool tx_active; + + /* + * rx is active. Set to true by RSDR and then switches off when out of + * descriptors. If the RXON bit in REG_MCMDR is off then this is off. + */ + bool rx_active; +}; + +typedef struct NPCM7xxEMCState NPCM7xxEMCState; + +#define TYPE_NPCM7XX_EMC "npcm7xx-emc" +#define NPCM7XX_EMC(obj) \ + OBJECT_CHECK(NPCM7xxEMCState, (obj), TYPE_NPCM7XX_EMC) + +#endif /* NPCM7XX_EMC_H */ diff --git a/hw/net/npcm7xx_emc.c b/hw/net/npcm7xx_emc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/npcm7xx_emc.c @@ -XXX,XX +XXX,XX @@ +/* + * Nuvoton NPCM7xx EMC Module + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + * + * Unsupported/unimplemented features: + * - MCMDR.FDUP (full duplex) is ignored, half duplex is not supported + * - Only CAM0 is supported, CAM[1-15] are not + * - writes to CAMEN.[1-15] are ignored, these bits always read as zeroes + * - MII is not implemented, MIIDA.BUSY and MIID always return zero + * - MCMDR.LBK is not implemented + * - MCMDR.{OPMOD,ENSQE,AEP,ARP} are not supported + * - H/W FIFOs are not supported, MCMDR.FFTCR is ignored + * - MGSTA.SQE is not supported + * - pause and control frames are not implemented + * - MGSTA.CCNT is not supported + * - MPCNT, DMARFS are not implemented + */ + +#include "qemu/osdep.h" + +/* For crc32 */ +#include <zlib.h> + +#include "qemu-common.h" +#include "hw/irq.h" +#include "hw/qdev-clock.h" +#include "hw/qdev-properties.h" +#include "hw/net/npcm7xx_emc.h" +#include "net/eth.h" +#include "migration/vmstate.h" +#include "qemu/bitops.h" +#include "qemu/error-report.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/units.h" +#include "sysemu/dma.h" +#include "trace.h" + +#define CRC_LENGTH 4 + +/* + * The maximum size of a (layer 2) ethernet frame as defined by 802.3. + * 1518 = 6(dest macaddr) + 6(src macaddr) + 2(proto) + 4(crc) + 1500(payload) + * This does not include an additional 4 for the vlan field (802.1q). + */ +#define MAX_ETH_FRAME_SIZE 1518 + +static const char *emc_reg_name(int regno) +{ +#define REG(name) case REG_ ## name: return #name; + switch (regno) { + REG(CAMCMR) + REG(CAMEN) + REG(TXDLSA) + REG(RXDLSA) + REG(MCMDR) + REG(MIID) + REG(MIIDA) + REG(FFTCR) + REG(TSDR) + REG(RSDR) + REG(DMARFC) + REG(MIEN) + REG(MISTA) + REG(MGSTA) + REG(MPCNT) + REG(MRPC) + REG(MRPCC) + REG(MREPC) + REG(DMARFS) + REG(CTXDSA) + REG(CTXBSA) + REG(CRXDSA) + REG(CRXBSA) + case REG_CAMM_BASE + 0: return "CAM0M"; + case REG_CAML_BASE + 0: return "CAM0L"; + case REG_CAMM_BASE + 2 ... REG_CAMML_LAST: + /* Only CAM0 is supported, fold the others into something simple. */ + if (regno & 1) { + return "CAM<n>L"; + } else { + return "CAM<n>M"; + } + default: return "UNKNOWN"; + } +#undef REG +} + +static void emc_reset(NPCM7xxEMCState *emc) +{ + trace_npcm7xx_emc_reset(emc->emc_num); + + memset(&emc->regs[0], 0, sizeof(emc->regs)); + + /* These regs have non-zero reset values. */ + emc->regs[REG_TXDLSA] = 0xfffffffc; + emc->regs[REG_RXDLSA] = 0xfffffffc; + emc->regs[REG_MIIDA] = 0x00900000; + emc->regs[REG_FFTCR] = 0x0101; + emc->regs[REG_DMARFC] = 0x0800; + emc->regs[REG_MPCNT] = 0x7fff; + + emc->tx_active = false; + emc->rx_active = false; +} + +static void npcm7xx_emc_reset(DeviceState *dev) +{ + NPCM7xxEMCState *emc = NPCM7XX_EMC(dev); + emc_reset(emc); +} + +static void emc_soft_reset(NPCM7xxEMCState *emc) +{ + /* + * The docs say at least MCMDR.{LBK,OPMOD} bits are not changed during a + * soft reset, but does not go into further detail. For now, KISS. + */ + uint32_t mcmdr = emc->regs[REG_MCMDR]; + emc_reset(emc); + emc->regs[REG_MCMDR] = mcmdr & (REG_MCMDR_LBK | REG_MCMDR_OPMOD); + + qemu_set_irq(emc->tx_irq, 0); + qemu_set_irq(emc->rx_irq, 0); +} + +static void emc_set_link(NetClientState *nc) +{ + /* Nothing to do yet. */ +} + +/* MISTA.TXINTR is the union of the individual bits with their enables. */ +static void emc_update_mista_txintr(NPCM7xxEMCState *emc) +{ + /* Only look at the bits we support. */ + uint32_t mask = (REG_MISTA_TXBERR | + REG_MISTA_TDU | + REG_MISTA_TXCP); + if (emc->regs[REG_MISTA] & emc->regs[REG_MIEN] & mask) { + emc->regs[REG_MISTA] |= REG_MISTA_TXINTR; + } else { + emc->regs[REG_MISTA] &= ~REG_MISTA_TXINTR; + } +} + +/* MISTA.RXINTR is the union of the individual bits with their enables. */ +static void emc_update_mista_rxintr(NPCM7xxEMCState *emc) +{ + /* Only look at the bits we support. */ + uint32_t mask = (REG_MISTA_RXBERR | + REG_MISTA_RDU | + REG_MISTA_RXGD); + if (emc->regs[REG_MISTA] & emc->regs[REG_MIEN] & mask) { + emc->regs[REG_MISTA] |= REG_MISTA_RXINTR; + } else { + emc->regs[REG_MISTA] &= ~REG_MISTA_RXINTR; + } +} + +/* N.B. emc_update_mista_txintr must have already been called. */ +static void emc_update_tx_irq(NPCM7xxEMCState *emc) +{ + int level = !!(emc->regs[REG_MISTA] & + emc->regs[REG_MIEN] & + REG_MISTA_TXINTR); + trace_npcm7xx_emc_update_tx_irq(level); + qemu_set_irq(emc->tx_irq, level); +} + +/* N.B. emc_update_mista_rxintr must have already been called. */ +static void emc_update_rx_irq(NPCM7xxEMCState *emc) +{ + int level = !!(emc->regs[REG_MISTA] & + emc->regs[REG_MIEN] & + REG_MISTA_RXINTR); + trace_npcm7xx_emc_update_rx_irq(level); + qemu_set_irq(emc->rx_irq, level); +} + +/* Update IRQ states due to changes in MIEN,MISTA. */ +static void emc_update_irq_from_reg_change(NPCM7xxEMCState *emc) +{ + emc_update_mista_txintr(emc); + emc_update_tx_irq(emc); + + emc_update_mista_rxintr(emc); + emc_update_rx_irq(emc); +} + +static int emc_read_tx_desc(dma_addr_t addr, NPCM7xxEMCTxDesc *desc) +{ + if (dma_memory_read(&address_space_memory, addr, desc, sizeof(*desc))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Failed to read descriptor @ 0x%" + HWADDR_PRIx "\n", __func__, addr); + return -1; + } + desc->flags = le32_to_cpu(desc->flags); + desc->txbsa = le32_to_cpu(desc->txbsa); + desc->status_and_length = le32_to_cpu(desc->status_and_length); + desc->ntxdsa = le32_to_cpu(desc->ntxdsa); + return 0; +} + +static int emc_write_tx_desc(const NPCM7xxEMCTxDesc *desc, dma_addr_t addr) +{ + NPCM7xxEMCTxDesc le_desc; + + le_desc.flags = cpu_to_le32(desc->flags); + le_desc.txbsa = cpu_to_le32(desc->txbsa); + le_desc.status_and_length = cpu_to_le32(desc->status_and_length); + le_desc.ntxdsa = cpu_to_le32(desc->ntxdsa); + if (dma_memory_write(&address_space_memory, addr, &le_desc, + sizeof(le_desc))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Failed to write descriptor @ 0x%" + HWADDR_PRIx "\n", __func__, addr); + return -1; + } + return 0; +} + +static int emc_read_rx_desc(dma_addr_t addr, NPCM7xxEMCRxDesc *desc) +{ + if (dma_memory_read(&address_space_memory, addr, desc, sizeof(*desc))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Failed to read descriptor @ 0x%" + HWADDR_PRIx "\n", __func__, addr); + return -1; + } + desc->status_and_length = le32_to_cpu(desc->status_and_length); + desc->rxbsa = le32_to_cpu(desc->rxbsa); + desc->reserved = le32_to_cpu(desc->reserved); + desc->nrxdsa = le32_to_cpu(desc->nrxdsa); + return 0; +} + +static int emc_write_rx_desc(const NPCM7xxEMCRxDesc *desc, dma_addr_t addr) +{ + NPCM7xxEMCRxDesc le_desc; + + le_desc.status_and_length = cpu_to_le32(desc->status_and_length); + le_desc.rxbsa = cpu_to_le32(desc->rxbsa); + le_desc.reserved = cpu_to_le32(desc->reserved); + le_desc.nrxdsa = cpu_to_le32(desc->nrxdsa); + if (dma_memory_write(&address_space_memory, addr, &le_desc, + sizeof(le_desc))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Failed to write descriptor @ 0x%" + HWADDR_PRIx "\n", __func__, addr); + return -1; + } + return 0; +} + +static void emc_set_mista(NPCM7xxEMCState *emc, uint32_t flags) +{ + trace_npcm7xx_emc_set_mista(flags); + emc->regs[REG_MISTA] |= flags; + if (extract32(flags, 16, 16)) { + emc_update_mista_txintr(emc); + } + if (extract32(flags, 0, 16)) { + emc_update_mista_rxintr(emc); + } +} + +static void emc_halt_tx(NPCM7xxEMCState *emc, uint32_t mista_flag) +{ + emc->tx_active = false; + emc_set_mista(emc, mista_flag); +} + +static void emc_halt_rx(NPCM7xxEMCState *emc, uint32_t mista_flag) +{ + emc->rx_active = false; + emc_set_mista(emc, mista_flag); +} + +static void emc_set_next_tx_descriptor(NPCM7xxEMCState *emc, + const NPCM7xxEMCTxDesc *tx_desc, + uint32_t desc_addr) +{ + /* Update the current descriptor, if only to reset the owner flag. */ + if (emc_write_tx_desc(tx_desc, desc_addr)) { + /* + * We just read it so this shouldn't generally happen. + * Error already reported. + */ + emc_set_mista(emc, REG_MISTA_TXBERR); + } + emc->regs[REG_CTXDSA] = TX_DESC_NTXDSA(tx_desc->ntxdsa); +} + +static void emc_set_next_rx_descriptor(NPCM7xxEMCState *emc, + const NPCM7xxEMCRxDesc *rx_desc, + uint32_t desc_addr) +{ + /* Update the current descriptor, if only to reset the owner flag. */ + if (emc_write_rx_desc(rx_desc, desc_addr)) { + /* + * We just read it so this shouldn't generally happen. + * Error already reported. + */ + emc_set_mista(emc, REG_MISTA_RXBERR); + } + emc->regs[REG_CRXDSA] = RX_DESC_NRXDSA(rx_desc->nrxdsa); +} + +static void emc_try_send_next_packet(NPCM7xxEMCState *emc) +{ + /* Working buffer for sending out packets. Most packets fit in this. */ +#define TX_BUFFER_SIZE 2048 + uint8_t tx_send_buffer[TX_BUFFER_SIZE]; + uint32_t desc_addr = TX_DESC_NTXDSA(emc->regs[REG_CTXDSA]); + NPCM7xxEMCTxDesc tx_desc; + uint32_t next_buf_addr, length; + uint8_t *buf; + g_autofree uint8_t *malloced_buf = NULL; + + if (emc_read_tx_desc(desc_addr, &tx_desc)) { + /* Error reading descriptor, already reported. */ + emc_halt_tx(emc, REG_MISTA_TXBERR); + emc_update_tx_irq(emc); + return; + } + + /* Nothing we can do if we don't own the descriptor. */ + if (!(tx_desc.flags & TX_DESC_FLAG_OWNER_MASK)) { + trace_npcm7xx_emc_cpu_owned_desc(desc_addr); + emc_halt_tx(emc, REG_MISTA_TDU); + emc_update_tx_irq(emc); + return; + } + + /* Give the descriptor back regardless of what happens. */ + tx_desc.flags &= ~TX_DESC_FLAG_OWNER_MASK; + tx_desc.status_and_length &= 0xffff; + + /* + * Despite the h/w documentation saying the tx buffer is word aligned, + * the linux driver does not word align the buffer. There is value in not + * aligning the buffer: See the description of NET_IP_ALIGN in linux + * kernel sources. + */ + next_buf_addr = tx_desc.txbsa; + emc->regs[REG_CTXBSA] = next_buf_addr; + length = TX_DESC_PKT_LEN(tx_desc.status_and_length); + buf = &tx_send_buffer[0]; + + if (length > sizeof(tx_send_buffer)) { + malloced_buf = g_malloc(length); + buf = malloced_buf; + } + + if (dma_memory_read(&address_space_memory, next_buf_addr, buf, length)) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Failed to read packet @ 0x%x\n", + __func__, next_buf_addr); + emc_set_mista(emc, REG_MISTA_TXBERR); + emc_set_next_tx_descriptor(emc, &tx_desc, desc_addr); + emc_update_tx_irq(emc); + trace_npcm7xx_emc_tx_done(emc->regs[REG_CTXDSA]); + return; + } + + if ((tx_desc.flags & TX_DESC_FLAG_PADEN) && (length < MIN_PACKET_LENGTH)) { + memset(buf + length, 0, MIN_PACKET_LENGTH - length); + length = MIN_PACKET_LENGTH; + } + + /* N.B. emc_receive can get called here. */ + qemu_send_packet(qemu_get_queue(emc->nic), buf, length); + trace_npcm7xx_emc_sent_packet(length); + + tx_desc.status_and_length |= TX_DESC_STATUS_TXCP; + if (tx_desc.flags & TX_DESC_FLAG_INTEN) { + emc_set_mista(emc, REG_MISTA_TXCP); + } + if (emc->regs[REG_MISTA] & emc->regs[REG_MIEN] & REG_MISTA_TXINTR) { + tx_desc.status_and_length |= TX_DESC_STATUS_TXINTR; + } + + emc_set_next_tx_descriptor(emc, &tx_desc, desc_addr); + emc_update_tx_irq(emc); + trace_npcm7xx_emc_tx_done(emc->regs[REG_CTXDSA]); +} + +static bool emc_can_receive(NetClientState *nc) +{ + NPCM7xxEMCState *emc = NPCM7XX_EMC(qemu_get_nic_opaque(nc)); + + bool can_receive = emc->rx_active; + trace_npcm7xx_emc_can_receive(can_receive); + return can_receive; +} + +/* If result is false then *fail_reason contains the reason. */ +static bool emc_receive_filter1(NPCM7xxEMCState *emc, const uint8_t *buf, + size_t len, const char **fail_reason) +{ + eth_pkt_types_e pkt_type = get_eth_packet_type(PKT_GET_ETH_HDR(buf)); + + switch (pkt_type) { + case ETH_PKT_BCAST: + if (emc->regs[REG_CAMCMR] & REG_CAMCMR_CCAM) { + return true; + } else { + *fail_reason = "Broadcast packet disabled"; + return !!(emc->regs[REG_CAMCMR] & REG_CAMCMR_ABP); + } + case ETH_PKT_MCAST: + if (emc->regs[REG_CAMCMR] & REG_CAMCMR_CCAM) { + return true; + } else { + *fail_reason = "Multicast packet disabled"; + return !!(emc->regs[REG_CAMCMR] & REG_CAMCMR_AMP); + } + case ETH_PKT_UCAST: { + bool matches; + if (emc->regs[REG_CAMCMR] & REG_CAMCMR_AUP) { + return true; + } + matches = ((emc->regs[REG_CAMCMR] & REG_CAMCMR_ECMP) && + /* We only support one CAM register, CAM0. */ + (emc->regs[REG_CAMEN] & (1 << 0)) && + memcmp(buf, emc->conf.macaddr.a, ETH_ALEN) == 0); + if (emc->regs[REG_CAMCMR] & REG_CAMCMR_CCAM) { + *fail_reason = "MACADDR matched, comparison complemented"; + return !matches; + } else { + *fail_reason = "MACADDR didn't match"; + return matches; + } + } + default: + g_assert_not_reached(); + } +} + +static bool emc_receive_filter(NPCM7xxEMCState *emc, const uint8_t *buf, + size_t len) +{ + const char *fail_reason = NULL; + bool ok = emc_receive_filter1(emc, buf, len, &fail_reason); + if (!ok) { + trace_npcm7xx_emc_packet_filtered_out(fail_reason); + } + return ok; +} + +static ssize_t emc_receive(NetClientState *nc, const uint8_t *buf, size_t len1) +{ + NPCM7xxEMCState *emc = NPCM7XX_EMC(qemu_get_nic_opaque(nc)); + const uint32_t len = len1; + size_t max_frame_len; + bool long_frame; + uint32_t desc_addr; + NPCM7xxEMCRxDesc rx_desc; + uint32_t crc; + uint8_t *crc_ptr; + uint32_t buf_addr; + + trace_npcm7xx_emc_receiving_packet(len); + + if (!emc_can_receive(nc)) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Unexpected packet\n", __func__); + return -1; + } + + if (len < ETH_HLEN || + /* Defensive programming: drop unsupportable large packets. */ + len > 0xffff - CRC_LENGTH) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Dropped frame of %u bytes\n", + __func__, len); + return len; + } + + /* + * DENI is set if EMC received the Length/Type field of the incoming + * packet, so it will be set regardless of what happens next. + */ + emc_set_mista(emc, REG_MISTA_DENI); + + if (!emc_receive_filter(emc, buf, len)) { + emc_update_rx_irq(emc); + return len; + } + + /* Huge frames (> DMARFC) are dropped. */ + max_frame_len = REG_DMARFC_RXMS(emc->regs[REG_DMARFC]); + if (len + CRC_LENGTH > max_frame_len) { + trace_npcm7xx_emc_packet_dropped(len); + emc_set_mista(emc, REG_MISTA_DFOI); + emc_update_rx_irq(emc); + return len; + } + + /* + * Long Frames (> MAX_ETH_FRAME_SIZE) are also dropped, unless MCMDR.ALP + * is set. + */ + long_frame = false; + if (len + CRC_LENGTH > MAX_ETH_FRAME_SIZE) { + if (emc->regs[REG_MCMDR] & REG_MCMDR_ALP) { + long_frame = true; + } else { + trace_npcm7xx_emc_packet_dropped(len); + emc_set_mista(emc, REG_MISTA_PTLE); + emc_update_rx_irq(emc); + return len; + } + } + + desc_addr = RX_DESC_NRXDSA(emc->regs[REG_CRXDSA]); + if (emc_read_rx_desc(desc_addr, &rx_desc)) { + /* Error reading descriptor, already reported. */ + emc_halt_rx(emc, REG_MISTA_RXBERR); + emc_update_rx_irq(emc); + return len; + } + + /* Nothing we can do if we don't own the descriptor. */ + if (!(rx_desc.status_and_length & RX_DESC_STATUS_OWNER_MASK)) { + trace_npcm7xx_emc_cpu_owned_desc(desc_addr); + emc_halt_rx(emc, REG_MISTA_RDU); + emc_update_rx_irq(emc); + return len; + } + + crc = 0; + crc_ptr = (uint8_t *) &crc; + if (!(emc->regs[REG_MCMDR] & REG_MCMDR_SPCRC)) { + crc = cpu_to_be32(crc32(~0, buf, len)); + } + + /* Give the descriptor back regardless of what happens. */ + rx_desc.status_and_length &= ~RX_DESC_STATUS_OWNER_MASK; + + buf_addr = rx_desc.rxbsa; + emc->regs[REG_CRXBSA] = buf_addr; + if (dma_memory_write(&address_space_memory, buf_addr, buf, len) || + (!(emc->regs[REG_MCMDR] & REG_MCMDR_SPCRC) && + dma_memory_write(&address_space_memory, buf_addr + len, crc_ptr, + 4))) { + qemu_log_mask(LOG_GUEST_ERROR, "%s: Bus error writing packet\n", + __func__); + emc_set_mista(emc, REG_MISTA_RXBERR); + emc_set_next_rx_descriptor(emc, &rx_desc, desc_addr); + emc_update_rx_irq(emc); + trace_npcm7xx_emc_rx_done(emc->regs[REG_CRXDSA]); + return len; + } + + trace_npcm7xx_emc_received_packet(len); + + /* Note: We've already verified len+4 <= 0xffff. */ + rx_desc.status_and_length = len; + if (!(emc->regs[REG_MCMDR] & REG_MCMDR_SPCRC)) { + rx_desc.status_and_length += 4; + } + rx_desc.status_and_length |= RX_DESC_STATUS_RXGD; + emc_set_mista(emc, REG_MISTA_RXGD); + + if (emc->regs[REG_MISTA] & emc->regs[REG_MIEN] & REG_MISTA_RXINTR) { + rx_desc.status_and_length |= RX_DESC_STATUS_RXINTR; + } + if (long_frame) { + rx_desc.status_and_length |= RX_DESC_STATUS_PTLE; + } + + emc_set_next_rx_descriptor(emc, &rx_desc, desc_addr); + emc_update_rx_irq(emc); + trace_npcm7xx_emc_rx_done(emc->regs[REG_CRXDSA]); + return len; +} + +static void emc_try_receive_next_packet(NPCM7xxEMCState *emc) +{ + if (emc_can_receive(qemu_get_queue(emc->nic))) { + qemu_flush_queued_packets(qemu_get_queue(emc->nic)); + } +} + +static uint64_t npcm7xx_emc_read(void *opaque, hwaddr offset, unsigned size) +{ + NPCM7xxEMCState *emc = opaque; + uint32_t reg = offset / sizeof(uint32_t); + uint32_t result; + + if (reg >= NPCM7XX_NUM_EMC_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Invalid offset 0x%04" HWADDR_PRIx "\n", + __func__, offset); + return 0; + } + + switch (reg) { + case REG_MIID: + /* + * We don't implement MII. For determinism, always return zero as + * writes record the last value written for debugging purposes. + */ + qemu_log_mask(LOG_UNIMP, "%s: Read of MIID, returning 0\n", __func__); + result = 0; + break; + case REG_TSDR: + case REG_RSDR: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Read of write-only reg, %s/%d\n", + __func__, emc_reg_name(reg), reg); + return 0; + default: + result = emc->regs[reg]; + break; + } + + trace_npcm7xx_emc_reg_read(emc->emc_num, result, emc_reg_name(reg), reg); + return result; +} + +static void npcm7xx_emc_write(void *opaque, hwaddr offset, + uint64_t v, unsigned size) +{ + NPCM7xxEMCState *emc = opaque; + uint32_t reg = offset / sizeof(uint32_t); + uint32_t value = v; + + g_assert(size == sizeof(uint32_t)); + + if (reg >= NPCM7XX_NUM_EMC_REGS) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Invalid offset 0x%04" HWADDR_PRIx "\n", + __func__, offset); + return; + } + + trace_npcm7xx_emc_reg_write(emc->emc_num, emc_reg_name(reg), reg, value); + + switch (reg) { + case REG_CAMCMR: + emc->regs[reg] = value; + break; + case REG_CAMEN: + /* Only CAM0 is supported, don't pretend otherwise. */ + if (value & ~1) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Only CAM0 is supported, cannot enable others" + ": 0x%x\n", + __func__, value); + } + emc->regs[reg] = value & 1; + break; + case REG_CAMM_BASE + 0: + emc->regs[reg] = value; + emc->conf.macaddr.a[0] = value >> 24; + emc->conf.macaddr.a[1] = value >> 16; + emc->conf.macaddr.a[2] = value >> 8; + emc->conf.macaddr.a[3] = value >> 0; + break; + case REG_CAML_BASE + 0: + emc->regs[reg] = value; + emc->conf.macaddr.a[4] = value >> 24; + emc->conf.macaddr.a[5] = value >> 16; + break; + case REG_MCMDR: { + uint32_t prev; + if (value & REG_MCMDR_SWR) { + emc_soft_reset(emc); + /* On h/w the reset happens over multiple cycles. For now KISS. */ + break; + } + prev = emc->regs[reg]; + emc->regs[reg] = value; + /* Update tx state. */ + if (!(prev & REG_MCMDR_TXON) && + (value & REG_MCMDR_TXON)) { + emc->regs[REG_CTXDSA] = emc->regs[REG_TXDLSA]; + /* + * Linux kernel turns TX on with CPU still holding descriptor, + * which suggests we should wait for a write to TSDR before trying + * to send a packet: so we don't send one here. + */ + } else if ((prev & REG_MCMDR_TXON) && + !(value & REG_MCMDR_TXON)) { + emc->regs[REG_MGSTA] |= REG_MGSTA_TXHA; + } + if (!(value & REG_MCMDR_TXON)) { + emc_halt_tx(emc, 0); + } + /* Update rx state. */ + if (!(prev & REG_MCMDR_RXON) && + (value & REG_MCMDR_RXON)) { + emc->regs[REG_CRXDSA] = emc->regs[REG_RXDLSA]; + } else if ((prev & REG_MCMDR_RXON) && + !(value & REG_MCMDR_RXON)) { + emc->regs[REG_MGSTA] |= REG_MGSTA_RXHA; + } + if (!(value & REG_MCMDR_RXON)) { + emc_halt_rx(emc, 0); + } + break; + } + case REG_TXDLSA: + case REG_RXDLSA: + case REG_DMARFC: + case REG_MIID: + emc->regs[reg] = value; + break; + case REG_MIEN: + emc->regs[reg] = value; + emc_update_irq_from_reg_change(emc); + break; + case REG_MISTA: + /* Clear the bits that have 1 in "value". */ + emc->regs[reg] &= ~value; + emc_update_irq_from_reg_change(emc); + break; + case REG_MGSTA: + /* Clear the bits that have 1 in "value". */ + emc->regs[reg] &= ~value; + break; + case REG_TSDR: + if (emc->regs[REG_MCMDR] & REG_MCMDR_TXON) { + emc->tx_active = true; + /* Keep trying to send packets until we run out. */ + while (emc->tx_active) { + emc_try_send_next_packet(emc); + } + } + break; + case REG_RSDR: + if (emc->regs[REG_MCMDR] & REG_MCMDR_RXON) { + emc->rx_active = true; + emc_try_receive_next_packet(emc); + } + break; + case REG_MIIDA: + emc->regs[reg] = value & ~REG_MIIDA_BUSY; + break; + case REG_MRPC: + case REG_MRPCC: + case REG_MREPC: + case REG_CTXDSA: + case REG_CTXBSA: + case REG_CRXDSA: + case REG_CRXBSA: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Write to read-only reg %s/%d\n", + __func__, emc_reg_name(reg), reg); + break; + default: + qemu_log_mask(LOG_UNIMP, "%s: Write to unimplemented reg %s/%d\n", + __func__, emc_reg_name(reg), reg); + break; + } +} + +static const struct MemoryRegionOps npcm7xx_emc_ops = { + .read = npcm7xx_emc_read, + .write = npcm7xx_emc_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + .unaligned = false, + }, +}; + +static void emc_cleanup(NetClientState *nc) +{ + /* Nothing to do yet. */ +} + +static NetClientInfo net_npcm7xx_emc_info = { + .type = NET_CLIENT_DRIVER_NIC, + .size = sizeof(NICState), + .can_receive = emc_can_receive, + .receive = emc_receive, + .cleanup = emc_cleanup, + .link_status_changed = emc_set_link, +}; + +static void npcm7xx_emc_realize(DeviceState *dev, Error **errp) +{ + NPCM7xxEMCState *emc = NPCM7XX_EMC(dev); + SysBusDevice *sbd = SYS_BUS_DEVICE(emc); + + memory_region_init_io(&emc->iomem, OBJECT(emc), &npcm7xx_emc_ops, emc, + TYPE_NPCM7XX_EMC, 4 * KiB); + sysbus_init_mmio(sbd, &emc->iomem); + sysbus_init_irq(sbd, &emc->tx_irq); + sysbus_init_irq(sbd, &emc->rx_irq); + + qemu_macaddr_default_if_unset(&emc->conf.macaddr); + emc->nic = qemu_new_nic(&net_npcm7xx_emc_info, &emc->conf, + object_get_typename(OBJECT(dev)), dev->id, emc); + qemu_format_nic_info_str(qemu_get_queue(emc->nic), emc->conf.macaddr.a); +} + +static void npcm7xx_emc_unrealize(DeviceState *dev) +{ + NPCM7xxEMCState *emc = NPCM7XX_EMC(dev); + + qemu_del_nic(emc->nic); +} + +static const VMStateDescription vmstate_npcm7xx_emc = { + .name = TYPE_NPCM7XX_EMC, + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_UINT8(emc_num, NPCM7xxEMCState), + VMSTATE_UINT32_ARRAY(regs, NPCM7xxEMCState, NPCM7XX_NUM_EMC_REGS), + VMSTATE_BOOL(tx_active, NPCM7xxEMCState), + VMSTATE_BOOL(rx_active, NPCM7xxEMCState), + VMSTATE_END_OF_LIST(), + }, +}; + +static Property npcm7xx_emc_properties[] = { + DEFINE_NIC_PROPERTIES(NPCM7xxEMCState, conf), + DEFINE_PROP_END_OF_LIST(), +}; + +static void npcm7xx_emc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + set_bit(DEVICE_CATEGORY_NETWORK, dc->categories); + dc->desc = "NPCM7xx EMC Controller"; + dc->realize = npcm7xx_emc_realize; + dc->unrealize = npcm7xx_emc_unrealize; + dc->reset = npcm7xx_emc_reset; + dc->vmsd = &vmstate_npcm7xx_emc; + device_class_set_props(dc, npcm7xx_emc_properties); +} + +static const TypeInfo npcm7xx_emc_info = { + .name = TYPE_NPCM7XX_EMC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(NPCM7xxEMCState), + .class_init = npcm7xx_emc_class_init, +}; + +static void npcm7xx_emc_register_type(void) +{ + type_register_static(&npcm7xx_emc_info); +} + +type_init(npcm7xx_emc_register_type) diff --git a/hw/net/meson.build b/hw/net/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/net/meson.build +++ b/hw/net/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_I82596_COMMON', if_true: files('i82596.c')) softmmu_ss.add(when: 'CONFIG_SUNHME', if_true: files('sunhme.c')) softmmu_ss.add(when: 'CONFIG_FTGMAC100', if_true: files('ftgmac100.c')) softmmu_ss.add(when: 'CONFIG_SUNGEM', if_true: files('sungem.c')) +softmmu_ss.add(when: 'CONFIG_NPCM7XX', if_true: files('npcm7xx_emc.c')) softmmu_ss.add(when: 'CONFIG_ETRAXFS', if_true: files('etraxfs_eth.c')) softmmu_ss.add(when: 'CONFIG_COLDFIRE', if_true: files('mcf_fec.c')) 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 @@ 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" + +# npcm7xx_emc.c +npcm7xx_emc_reset(int emc_num) "Resetting emc%d" +npcm7xx_emc_update_tx_irq(int level) "Setting tx irq to %d" +npcm7xx_emc_update_rx_irq(int level) "Setting rx irq to %d" +npcm7xx_emc_set_mista(uint32_t flags) "ORing 0x%x into MISTA" +npcm7xx_emc_cpu_owned_desc(uint32_t addr) "Can't process cpu-owned descriptor @0x%x" +npcm7xx_emc_sent_packet(uint32_t len) "Sent %u byte packet" +npcm7xx_emc_tx_done(uint32_t ctxdsa) "TX done, CTXDSA=0x%x" +npcm7xx_emc_can_receive(int can_receive) "Can receive: %d" +npcm7xx_emc_packet_filtered_out(const char* fail_reason) "Packet filtered out: %s" +npcm7xx_emc_packet_dropped(uint32_t len) "%u byte packet dropped" +npcm7xx_emc_receiving_packet(uint32_t len) "Receiving %u byte packet" +npcm7xx_emc_received_packet(uint32_t len) "Received %u byte packet" +npcm7xx_emc_rx_done(uint32_t crxdsa) "RX done, CRXDSA=0x%x" +npcm7xx_emc_reg_read(int emc_num, uint32_t result, const char *name, int regno) "emc%d: 0x%x = reg[%s/%d]" +npcm7xx_emc_reg_write(int emc_num, const char *name, int regno, uint32_t value) "emc%d: reg[%s/%d] = 0x%x" -- 2.20.1 From: Doug Evans <dje@google.com> This is a 10/100 ethernet device that has several features. Only the ones needed by the Linux driver have been implemented. See npcm7xx_emc.c for a list of unimplemented features. Reviewed-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Avi Fishman <avi.fishman@nuvoton.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Doug Evans <dje@google.com> Message-id: 20210218212453.831406-3-dje@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/nuvoton.rst | 3 ++- include/hw/arm/npcm7xx.h | 2 ++ hw/arm/npcm7xx.c | 50 +++++++++++++++++++++++++++++++++++-- 3 files changed, 52 insertions(+), 3 deletions(-) diff --git a/docs/system/arm/nuvoton.rst b/docs/system/arm/nuvoton.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/nuvoton.rst +++ b/docs/system/arm/nuvoton.rst @@ -XXX,XX +XXX,XX @@ Supported devices * Analog to Digital Converter (ADC) * Pulse Width Modulation (PWM) * SMBus controller (SMBF) + * Ethernet controller (EMC) Missing devices --------------- @@ -XXX,XX +XXX,XX @@ Missing devices * Shared memory (SHM) * eSPI slave interface - * Ethernet controllers (GMAC and EMC) + * Ethernet controller (GMAC) * USB device (USBD) * Peripheral SPI controller (PSPI) * SD/MMC host diff --git a/include/hw/arm/npcm7xx.h b/include/hw/arm/npcm7xx.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/npcm7xx.h +++ b/include/hw/arm/npcm7xx.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/npcm7xx_gcr.h" #include "hw/misc/npcm7xx_pwm.h" #include "hw/misc/npcm7xx_rng.h" +#include "hw/net/npcm7xx_emc.h" #include "hw/nvram/npcm7xx_otp.h" #include "hw/timer/npcm7xx_timer.h" #include "hw/ssi/npcm7xx_fiu.h" @@ -XXX,XX +XXX,XX @@ typedef struct NPCM7xxState { EHCISysBusState ehci; OHCISysBusState ohci; NPCM7xxFIUState fiu[2]; + NPCM7xxEMCState emc[2]; } NPCM7xxState; #define TYPE_NPCM7XX "npcm7xx" diff --git a/hw/arm/npcm7xx.c b/hw/arm/npcm7xx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx.c +++ b/hw/arm/npcm7xx.c @@ -XXX,XX +XXX,XX @@ enum NPCM7xxInterrupt { NPCM7XX_UART1_IRQ, NPCM7XX_UART2_IRQ, NPCM7XX_UART3_IRQ, + NPCM7XX_EMC1RX_IRQ = 15, + NPCM7XX_EMC1TX_IRQ, NPCM7XX_TIMER0_IRQ = 32, /* Timer Module 0 */ NPCM7XX_TIMER1_IRQ, NPCM7XX_TIMER2_IRQ, @@ -XXX,XX +XXX,XX @@ enum NPCM7xxInterrupt { NPCM7XX_SMBUS15_IRQ, NPCM7XX_PWM0_IRQ = 93, /* PWM module 0 */ NPCM7XX_PWM1_IRQ, /* PWM module 1 */ + NPCM7XX_EMC2RX_IRQ = 114, + NPCM7XX_EMC2TX_IRQ, NPCM7XX_GPIO0_IRQ = 116, NPCM7XX_GPIO1_IRQ, NPCM7XX_GPIO2_IRQ, @@ -XXX,XX +XXX,XX @@ static const hwaddr npcm7xx_smbus_addr[] = { 0xf008f000, }; +/* Register base address for each EMC Module */ +static const hwaddr npcm7xx_emc_addr[] = { + 0xf0825000, + 0xf0826000, +}; + static const struct { hwaddr regs_addr; uint32_t unconnected_pins; @@ -XXX,XX +XXX,XX @@ static void npcm7xx_init(Object *obj) for (i = 0; i < ARRAY_SIZE(s->pwm); i++) { object_initialize_child(obj, "pwm[*]", &s->pwm[i], TYPE_NPCM7XX_PWM); } + + for (i = 0; i < ARRAY_SIZE(s->emc); i++) { + object_initialize_child(obj, "emc[*]", &s->emc[i], TYPE_NPCM7XX_EMC); + } } static void npcm7xx_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(sbd, i, npcm7xx_irq(s, NPCM7XX_PWM0_IRQ + i)); } + /* + * EMC Modules. Cannot fail. + * The mapping of the device to its netdev backend works as follows: + * emc[i] = nd_table[i] + * This works around the inability to specify the netdev property for the + * emc device: it's not pluggable and thus the -device option can't be + * used. + */ + QEMU_BUILD_BUG_ON(ARRAY_SIZE(npcm7xx_emc_addr) != ARRAY_SIZE(s->emc)); + QEMU_BUILD_BUG_ON(ARRAY_SIZE(s->emc) != 2); + for (i = 0; i < ARRAY_SIZE(s->emc); i++) { + s->emc[i].emc_num = i; + SysBusDevice *sbd = SYS_BUS_DEVICE(&s->emc[i]); + if (nd_table[i].used) { + qemu_check_nic_model(&nd_table[i], TYPE_NPCM7XX_EMC); + qdev_set_nic_properties(DEVICE(sbd), &nd_table[i]); + } + /* + * The device exists regardless of whether it's connected to a QEMU + * netdev backend. So always instantiate it even if there is no + * backend. + */ + sysbus_realize(sbd, &error_abort); + sysbus_mmio_map(sbd, 0, npcm7xx_emc_addr[i]); + int tx_irq = i == 0 ? NPCM7XX_EMC1TX_IRQ : NPCM7XX_EMC2TX_IRQ; + int rx_irq = i == 0 ? NPCM7XX_EMC1RX_IRQ : NPCM7XX_EMC2RX_IRQ; + /* + * N.B. The values for the second argument sysbus_connect_irq are + * chosen to match the registration order in npcm7xx_emc_realize. + */ + sysbus_connect_irq(sbd, 0, npcm7xx_irq(s, tx_irq)); + sysbus_connect_irq(sbd, 1, npcm7xx_irq(s, rx_irq)); + } + /* * Flash Interface Unit (FIU). Can fail if incorrect number of chip selects * specified, but this is a programming error. @@ -XXX,XX +XXX,XX @@ static void npcm7xx_realize(DeviceState *dev, Error **errp) create_unimplemented_device("npcm7xx.vcd", 0xf0810000, 64 * KiB); create_unimplemented_device("npcm7xx.ece", 0xf0820000, 8 * KiB); create_unimplemented_device("npcm7xx.vdma", 0xf0822000, 8 * KiB); - create_unimplemented_device("npcm7xx.emc1", 0xf0825000, 4 * KiB); - create_unimplemented_device("npcm7xx.emc2", 0xf0826000, 4 * KiB); create_unimplemented_device("npcm7xx.usbd[0]", 0xf0830000, 4 * KiB); create_unimplemented_device("npcm7xx.usbd[1]", 0xf0831000, 4 * KiB); create_unimplemented_device("npcm7xx.usbd[2]", 0xf0832000, 4 * KiB); -- 2.20.1 From: Doug Evans <dje@google.com> Reviewed-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Avi Fishman <avi.fishman@nuvoton.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Doug Evans <dje@google.com> Message-id: 20210218212453.831406-4-dje@google.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/npcm7xx_emc-test.c | 862 +++++++++++++++++++++++++++++++++ tests/qtest/meson.build | 3 +- 2 files changed, 864 insertions(+), 1 deletion(-) create mode 100644 tests/qtest/npcm7xx_emc-test.c diff --git a/tests/qtest/npcm7xx_emc-test.c b/tests/qtest/npcm7xx_emc-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/npcm7xx_emc-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTests for Nuvoton NPCM7xx EMC Modules. + * + * Copyright 2020 Google LLC + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License + * for more details. + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "libqos/libqos.h" +#include "qapi/qmp/qdict.h" +#include "qapi/qmp/qnum.h" +#include "qemu/bitops.h" +#include "qemu/iov.h" + +/* Name of the emc device. */ +#define TYPE_NPCM7XX_EMC "npcm7xx-emc" + +/* Timeout for various operations, in seconds. */ +#define TIMEOUT_SECONDS 10 + +/* Address in memory of the descriptor. */ +#define DESC_ADDR (1 << 20) /* 1 MiB */ + +/* Address in memory of the data packet. */ +#define DATA_ADDR (DESC_ADDR + 4096) + +#define CRC_LENGTH 4 + +#define NUM_TX_DESCRIPTORS 3 +#define NUM_RX_DESCRIPTORS 2 + +/* Size of tx,rx test buffers. */ +#define TX_DATA_LEN 64 +#define RX_DATA_LEN 64 + +#define TX_STEP_COUNT 10000 +#define RX_STEP_COUNT 10000 + +/* 32-bit register indices. */ +typedef enum NPCM7xxPWMRegister { + /* Control registers. */ + REG_CAMCMR, + REG_CAMEN, + + /* There are 16 CAMn[ML] registers. */ + REG_CAMM_BASE, + REG_CAML_BASE, + + REG_TXDLSA = 0x22, + REG_RXDLSA, + REG_MCMDR, + REG_MIID, + REG_MIIDA, + REG_FFTCR, + REG_TSDR, + REG_RSDR, + REG_DMARFC, + REG_MIEN, + + /* Status registers. */ + REG_MISTA, + REG_MGSTA, + REG_MPCNT, + REG_MRPC, + REG_MRPCC, + REG_MREPC, + REG_DMARFS, + REG_CTXDSA, + REG_CTXBSA, + REG_CRXDSA, + REG_CRXBSA, + + NPCM7XX_NUM_EMC_REGS, +} NPCM7xxPWMRegister; + +enum { NUM_CAMML_REGS = 16 }; + +/* REG_CAMCMR fields */ +/* Enable CAM Compare */ +#define REG_CAMCMR_ECMP (1 << 4) +/* Accept Unicast Packet */ +#define REG_CAMCMR_AUP (1 << 0) + +/* REG_MCMDR fields */ +/* Software Reset */ +#define REG_MCMDR_SWR (1 << 24) +/* Frame Transmission On */ +#define REG_MCMDR_TXON (1 << 8) +/* Accept Long Packet */ +#define REG_MCMDR_ALP (1 << 1) +/* Frame Reception On */ +#define REG_MCMDR_RXON (1 << 0) + +/* REG_MIEN fields */ +/* Enable Transmit Completion Interrupt */ +#define REG_MIEN_ENTXCP (1 << 18) +/* Enable Transmit Interrupt */ +#define REG_MIEN_ENTXINTR (1 << 16) +/* Enable Receive Good Interrupt */ +#define REG_MIEN_ENRXGD (1 << 4) +/* ENable Receive Interrupt */ +#define REG_MIEN_ENRXINTR (1 << 0) + +/* REG_MISTA fields */ +/* Transmit Bus Error Interrupt */ +#define REG_MISTA_TXBERR (1 << 24) +/* Transmit Descriptor Unavailable Interrupt */ +#define REG_MISTA_TDU (1 << 23) +/* Transmit Completion Interrupt */ +#define REG_MISTA_TXCP (1 << 18) +/* Transmit Interrupt */ +#define REG_MISTA_TXINTR (1 << 16) +/* Receive Bus Error Interrupt */ +#define REG_MISTA_RXBERR (1 << 11) +/* Receive Descriptor Unavailable Interrupt */ +#define REG_MISTA_RDU (1 << 10) +/* DMA Early Notification Interrupt */ +#define REG_MISTA_DENI (1 << 9) +/* Maximum Frame Length Interrupt */ +#define REG_MISTA_DFOI (1 << 8) +/* Receive Good Interrupt */ +#define REG_MISTA_RXGD (1 << 4) +/* Packet Too Long Interrupt */ +#define REG_MISTA_PTLE (1 << 3) +/* Receive Interrupt */ +#define REG_MISTA_RXINTR (1 << 0) + +typedef struct NPCM7xxEMCTxDesc NPCM7xxEMCTxDesc; +typedef struct NPCM7xxEMCRxDesc NPCM7xxEMCRxDesc; + +struct NPCM7xxEMCTxDesc { + uint32_t flags; + uint32_t txbsa; + uint32_t status_and_length; + uint32_t ntxdsa; +}; + +struct NPCM7xxEMCRxDesc { + uint32_t status_and_length; + uint32_t rxbsa; + uint32_t reserved; + uint32_t nrxdsa; +}; + +/* NPCM7xxEMCTxDesc.flags values */ +/* Owner: 0 = cpu, 1 = emc */ +#define TX_DESC_FLAG_OWNER_MASK (1 << 31) +/* Transmit interrupt enable */ +#define TX_DESC_FLAG_INTEN (1 << 2) + +/* NPCM7xxEMCTxDesc.status_and_length values */ +/* Transmission complete */ +#define TX_DESC_STATUS_TXCP (1 << 19) +/* Transmit interrupt */ +#define TX_DESC_STATUS_TXINTR (1 << 16) + +/* NPCM7xxEMCRxDesc.status_and_length values */ +/* Owner: 0b00 = cpu, 0b10 = emc */ +#define RX_DESC_STATUS_OWNER_SHIFT 30 +#define RX_DESC_STATUS_OWNER_MASK 0xc0000000 +/* Frame Reception Complete */ +#define RX_DESC_STATUS_RXGD (1 << 20) +/* Packet too long */ +#define RX_DESC_STATUS_PTLE (1 << 19) +/* Receive Interrupt */ +#define RX_DESC_STATUS_RXINTR (1 << 16) + +#define RX_DESC_PKT_LEN(word) ((uint32_t) (word) & 0xffff) + +typedef struct EMCModule { + int rx_irq; + int tx_irq; + uint64_t base_addr; +} EMCModule; + +typedef struct TestData { + const EMCModule *module; +} TestData; + +static const EMCModule emc_module_list[] = { + { + .rx_irq = 15, + .tx_irq = 16, + .base_addr = 0xf0825000 + }, + { + .rx_irq = 114, + .tx_irq = 115, + .base_addr = 0xf0826000 + } +}; + +/* Returns the index of the EMC module. */ +static int emc_module_index(const EMCModule *mod) +{ + ptrdiff_t diff = mod - emc_module_list; + + g_assert_true(diff >= 0 && diff < ARRAY_SIZE(emc_module_list)); + + return diff; +} + +static void packet_test_clear(void *sockets) +{ + int *test_sockets = sockets; + + close(test_sockets[0]); + g_free(test_sockets); +} + +static int *packet_test_init(int module_num, GString *cmd_line) +{ + int *test_sockets = g_new(int, 2); + int ret = socketpair(PF_UNIX, SOCK_STREAM, 0, test_sockets); + g_assert_cmpint(ret, != , -1); + + /* + * KISS and use -nic. We specify two nics (both emc{0,1}) because there's + * currently no way to specify only emc1: The driver implicitly relies on + * emc[i] == nd_table[i]. + */ + if (module_num == 0) { + g_string_append_printf(cmd_line, + " -nic socket,fd=%d,model=" TYPE_NPCM7XX_EMC " " + " -nic user,model=" TYPE_NPCM7XX_EMC " ", + test_sockets[1]); + } else { + g_string_append_printf(cmd_line, + " -nic user,model=" TYPE_NPCM7XX_EMC " " + " -nic socket,fd=%d,model=" TYPE_NPCM7XX_EMC " ", + test_sockets[1]); + } + + g_test_queue_destroy(packet_test_clear, test_sockets); + return test_sockets; +} + +static uint32_t emc_read(QTestState *qts, const EMCModule *mod, + NPCM7xxPWMRegister regno) +{ + return qtest_readl(qts, mod->base_addr + regno * sizeof(uint32_t)); +} + +static void emc_write(QTestState *qts, const EMCModule *mod, + NPCM7xxPWMRegister regno, uint32_t value) +{ + qtest_writel(qts, mod->base_addr + regno * sizeof(uint32_t), value); +} + +static void emc_read_tx_desc(QTestState *qts, uint32_t addr, + NPCM7xxEMCTxDesc *desc) +{ + qtest_memread(qts, addr, desc, sizeof(*desc)); + desc->flags = le32_to_cpu(desc->flags); + desc->txbsa = le32_to_cpu(desc->txbsa); + desc->status_and_length = le32_to_cpu(desc->status_and_length); + desc->ntxdsa = le32_to_cpu(desc->ntxdsa); +} + +static void emc_write_tx_desc(QTestState *qts, const NPCM7xxEMCTxDesc *desc, + uint32_t addr) +{ + NPCM7xxEMCTxDesc le_desc; + + le_desc.flags = cpu_to_le32(desc->flags); + le_desc.txbsa = cpu_to_le32(desc->txbsa); + le_desc.status_and_length = cpu_to_le32(desc->status_and_length); + le_desc.ntxdsa = cpu_to_le32(desc->ntxdsa); + qtest_memwrite(qts, addr, &le_desc, sizeof(le_desc)); +} + +static void emc_read_rx_desc(QTestState *qts, uint32_t addr, + NPCM7xxEMCRxDesc *desc) +{ + qtest_memread(qts, addr, desc, sizeof(*desc)); + desc->status_and_length = le32_to_cpu(desc->status_and_length); + desc->rxbsa = le32_to_cpu(desc->rxbsa); + desc->reserved = le32_to_cpu(desc->reserved); + desc->nrxdsa = le32_to_cpu(desc->nrxdsa); +} + +static void emc_write_rx_desc(QTestState *qts, const NPCM7xxEMCRxDesc *desc, + uint32_t addr) +{ + NPCM7xxEMCRxDesc le_desc; + + le_desc.status_and_length = cpu_to_le32(desc->status_and_length); + le_desc.rxbsa = cpu_to_le32(desc->rxbsa); + le_desc.reserved = cpu_to_le32(desc->reserved); + le_desc.nrxdsa = cpu_to_le32(desc->nrxdsa); + qtest_memwrite(qts, addr, &le_desc, sizeof(le_desc)); +} + +/* + * Reset the EMC module. + * The module must be reset before, e.g., TXDLSA,RXDLSA are changed. + */ +static bool emc_soft_reset(QTestState *qts, const EMCModule *mod) +{ + uint32_t val; + uint64_t end_time; + + emc_write(qts, mod, REG_MCMDR, REG_MCMDR_SWR); + + /* + * Wait for device to reset as the linux driver does. + * During reset the AHB reads 0 for all registers. So first wait for + * something that resets to non-zero, and then wait for SWR becoming 0. + */ + end_time = g_get_monotonic_time() + TIMEOUT_SECONDS * G_TIME_SPAN_SECOND; + + do { + qtest_clock_step(qts, 100); + val = emc_read(qts, mod, REG_FFTCR); + } while (val == 0 && g_get_monotonic_time() < end_time); + if (val != 0) { + do { + qtest_clock_step(qts, 100); + val = emc_read(qts, mod, REG_MCMDR); + if ((val & REG_MCMDR_SWR) == 0) { + /* + * N.B. The CAMs have been reset here, so macaddr matching of + * incoming packets will not work. + */ + return true; + } + } while (g_get_monotonic_time() < end_time); + } + + g_message("%s: Timeout expired", __func__); + return false; +} + +/* Check emc registers are reset to default value. */ +static void test_init(gconstpointer test_data) +{ + const TestData *td = test_data; + const EMCModule *mod = td->module; + QTestState *qts = qtest_init("-machine quanta-gsj"); + int i; + +#define CHECK_REG(regno, value) \ + do { \ + g_assert_cmphex(emc_read(qts, mod, (regno)), ==, (value)); \ + } while (0) + + CHECK_REG(REG_CAMCMR, 0); + CHECK_REG(REG_CAMEN, 0); + CHECK_REG(REG_TXDLSA, 0xfffffffc); + CHECK_REG(REG_RXDLSA, 0xfffffffc); + CHECK_REG(REG_MCMDR, 0); + CHECK_REG(REG_MIID, 0); + CHECK_REG(REG_MIIDA, 0x00900000); + CHECK_REG(REG_FFTCR, 0x0101); + CHECK_REG(REG_DMARFC, 0x0800); + CHECK_REG(REG_MIEN, 0); + CHECK_REG(REG_MISTA, 0); + CHECK_REG(REG_MGSTA, 0); + CHECK_REG(REG_MPCNT, 0x7fff); + CHECK_REG(REG_MRPC, 0); + CHECK_REG(REG_MRPCC, 0); + CHECK_REG(REG_MREPC, 0); + CHECK_REG(REG_DMARFS, 0); + CHECK_REG(REG_CTXDSA, 0); + CHECK_REG(REG_CTXBSA, 0); + CHECK_REG(REG_CRXDSA, 0); + CHECK_REG(REG_CRXBSA, 0); + +#undef CHECK_REG + + for (i = 0; i < NUM_CAMML_REGS; ++i) { + g_assert_cmpuint(emc_read(qts, mod, REG_CAMM_BASE + i * 2), ==, + 0); + g_assert_cmpuint(emc_read(qts, mod, REG_CAML_BASE + i * 2), ==, + 0); + } + + qtest_quit(qts); +} + +static bool emc_wait_irq(QTestState *qts, const EMCModule *mod, int step, + bool is_tx) +{ + uint64_t end_time = + g_get_monotonic_time() + TIMEOUT_SECONDS * G_TIME_SPAN_SECOND; + + do { + if (qtest_get_irq(qts, is_tx ? mod->tx_irq : mod->rx_irq)) { + return true; + } + qtest_clock_step(qts, step); + } while (g_get_monotonic_time() < end_time); + + g_message("%s: Timeout expired", __func__); + return false; +} + +static bool emc_wait_mista(QTestState *qts, const EMCModule *mod, int step, + uint32_t flag) +{ + uint64_t end_time = + g_get_monotonic_time() + TIMEOUT_SECONDS * G_TIME_SPAN_SECOND; + + do { + uint32_t mista = emc_read(qts, mod, REG_MISTA); + if (mista & flag) { + return true; + } + qtest_clock_step(qts, step); + } while (g_get_monotonic_time() < end_time); + + g_message("%s: Timeout expired", __func__); + return false; +} + +static bool wait_socket_readable(int fd) +{ + fd_set read_fds; + struct timeval tv; + int rv; + + FD_ZERO(&read_fds); + FD_SET(fd, &read_fds); + tv.tv_sec = TIMEOUT_SECONDS; + tv.tv_usec = 0; + rv = select(fd + 1, &read_fds, NULL, NULL, &tv); + if (rv == -1) { + perror("select"); + } else if (rv == 0) { + g_message("%s: Timeout expired", __func__); + } + return rv == 1; +} + +/* Initialize *desc (in host endian format). */ +static void init_tx_desc(NPCM7xxEMCTxDesc *desc, size_t count, + uint32_t desc_addr) +{ + g_assert(count >= 2); + memset(&desc[0], 0, sizeof(*desc) * count); + /* Leave the last one alone, owned by the cpu -> stops transmission. */ + for (size_t i = 0; i < count - 1; ++i) { + desc[i].flags = + (TX_DESC_FLAG_OWNER_MASK | /* owner = 1: emc */ + TX_DESC_FLAG_INTEN | + 0 | /* crc append = 0 */ + 0 /* padding enable = 0 */); + desc[i].status_and_length = + (0 | /* collision count = 0 */ + 0 | /* SQE = 0 */ + 0 | /* PAU = 0 */ + 0 | /* TXHA = 0 */ + 0 | /* LC = 0 */ + 0 | /* TXABT = 0 */ + 0 | /* NCS = 0 */ + 0 | /* EXDEF = 0 */ + 0 | /* TXCP = 0 */ + 0 | /* DEF = 0 */ + 0 | /* TXINTR = 0 */ + 0 /* length filled in later */); + desc[i].ntxdsa = desc_addr + (i + 1) * sizeof(*desc); + } +} + +static void enable_tx(QTestState *qts, const EMCModule *mod, + const NPCM7xxEMCTxDesc *desc, size_t count, + uint32_t desc_addr, uint32_t mien_flags) +{ + /* Write the descriptors to guest memory. */ + for (size_t i = 0; i < count; ++i) { + emc_write_tx_desc(qts, desc + i, desc_addr + i * sizeof(*desc)); + } + + /* Trigger sending the packet. */ + /* The module must be reset before changing TXDLSA. */ + g_assert(emc_soft_reset(qts, mod)); + emc_write(qts, mod, REG_TXDLSA, desc_addr); + emc_write(qts, mod, REG_CTXDSA, ~0); + emc_write(qts, mod, REG_MIEN, REG_MIEN_ENTXCP | mien_flags); + { + uint32_t mcmdr = emc_read(qts, mod, REG_MCMDR); + mcmdr |= REG_MCMDR_TXON; + emc_write(qts, mod, REG_MCMDR, mcmdr); + } + + /* Prod the device to send the packet. */ + emc_write(qts, mod, REG_TSDR, 1); +} + +static void emc_send_verify1(QTestState *qts, const EMCModule *mod, int fd, + bool with_irq, uint32_t desc_addr, + uint32_t next_desc_addr, + const char *test_data, int test_size) +{ + NPCM7xxEMCTxDesc result_desc; + uint32_t expected_mask, expected_value, recv_len; + int ret; + char buffer[TX_DATA_LEN]; + + g_assert(wait_socket_readable(fd)); + + /* Read the descriptor back. */ + emc_read_tx_desc(qts, desc_addr, &result_desc); + /* Descriptor should be owned by cpu now. */ + g_assert((result_desc.flags & TX_DESC_FLAG_OWNER_MASK) == 0); + /* Test the status bits, ignoring the length field. */ + expected_mask = 0xffff << 16; + expected_value = TX_DESC_STATUS_TXCP; + if (with_irq) { + expected_value |= TX_DESC_STATUS_TXINTR; + } + g_assert_cmphex((result_desc.status_and_length & expected_mask), ==, + expected_value); + + /* Check data sent to the backend. */ + recv_len = ~0; + ret = qemu_recv(fd, &recv_len, sizeof(recv_len), MSG_DONTWAIT); + g_assert_cmpint(ret, == , sizeof(recv_len)); + + g_assert(wait_socket_readable(fd)); + memset(buffer, 0xff, sizeof(buffer)); + ret = qemu_recv(fd, buffer, test_size, MSG_DONTWAIT); + g_assert_cmpmem(buffer, ret, test_data, test_size); +} + +static void emc_send_verify(QTestState *qts, const EMCModule *mod, int fd, + bool with_irq) +{ + NPCM7xxEMCTxDesc desc[NUM_TX_DESCRIPTORS]; + uint32_t desc_addr = DESC_ADDR; + static const char test1_data[] = "TEST1"; + static const char test2_data[] = "Testing 1 2 3 ..."; + uint32_t data1_addr = DATA_ADDR; + uint32_t data2_addr = data1_addr + sizeof(test1_data); + bool got_tdu; + uint32_t end_desc_addr; + + /* Prepare test data buffer. */ + qtest_memwrite(qts, data1_addr, test1_data, sizeof(test1_data)); + qtest_memwrite(qts, data2_addr, test2_data, sizeof(test2_data)); + + init_tx_desc(&desc[0], NUM_TX_DESCRIPTORS, desc_addr); + desc[0].txbsa = data1_addr; + desc[0].status_and_length |= sizeof(test1_data); + desc[1].txbsa = data2_addr; + desc[1].status_and_length |= sizeof(test2_data); + + enable_tx(qts, mod, &desc[0], NUM_TX_DESCRIPTORS, desc_addr, + with_irq ? REG_MIEN_ENTXINTR : 0); + + /* + * It's problematic to observe the interrupt for each packet. + * Instead just wait until all the packets go out. + */ + got_tdu = false; + while (!got_tdu) { + if (with_irq) { + g_assert_true(emc_wait_irq(qts, mod, TX_STEP_COUNT, + /*is_tx=*/true)); + } else { + g_assert_true(emc_wait_mista(qts, mod, TX_STEP_COUNT, + REG_MISTA_TXINTR)); + } + got_tdu = !!(emc_read(qts, mod, REG_MISTA) & REG_MISTA_TDU); + /* If we don't have TDU yet, reset the interrupt. */ + if (!got_tdu) { + emc_write(qts, mod, REG_MISTA, + emc_read(qts, mod, REG_MISTA) & 0xffff0000); + } + } + + end_desc_addr = desc_addr + 2 * sizeof(desc[0]); + g_assert_cmphex(emc_read(qts, mod, REG_CTXDSA), ==, end_desc_addr); + g_assert_cmphex(emc_read(qts, mod, REG_MISTA), ==, + REG_MISTA_TXCP | REG_MISTA_TXINTR | REG_MISTA_TDU); + + emc_send_verify1(qts, mod, fd, with_irq, + desc_addr, end_desc_addr, + test1_data, sizeof(test1_data)); + emc_send_verify1(qts, mod, fd, with_irq, + desc_addr + sizeof(desc[0]), end_desc_addr, + test2_data, sizeof(test2_data)); +} + +/* Initialize *desc (in host endian format). */ +static void init_rx_desc(NPCM7xxEMCRxDesc *desc, size_t count, + uint32_t desc_addr, uint32_t data_addr) +{ + g_assert_true(count >= 2); + memset(desc, 0, sizeof(*desc) * count); + desc[0].rxbsa = data_addr; + desc[0].status_and_length = + (0b10 << RX_DESC_STATUS_OWNER_SHIFT | /* owner = 10: emc */ + 0 | /* RP = 0 */ + 0 | /* ALIE = 0 */ + 0 | /* RXGD = 0 */ + 0 | /* PTLE = 0 */ + 0 | /* CRCE = 0 */ + 0 | /* RXINTR = 0 */ + 0 /* length (filled in later) */); + /* Leave the last one alone, owned by the cpu -> stops transmission. */ + desc[0].nrxdsa = desc_addr + sizeof(*desc); +} + +static void enable_rx(QTestState *qts, const EMCModule *mod, + const NPCM7xxEMCRxDesc *desc, size_t count, + uint32_t desc_addr, uint32_t mien_flags, + uint32_t mcmdr_flags) +{ + /* + * Write the descriptor to guest memory. + * FWIW, IWBN if the docs said the buffer needs to be at least DMARFC + * bytes. + */ + for (size_t i = 0; i < count; ++i) { + emc_write_rx_desc(qts, desc + i, desc_addr + i * sizeof(*desc)); + } + + /* Trigger receiving the packet. */ + /* The module must be reset before changing RXDLSA. */ + g_assert(emc_soft_reset(qts, mod)); + emc_write(qts, mod, REG_RXDLSA, desc_addr); + emc_write(qts, mod, REG_MIEN, REG_MIEN_ENRXGD | mien_flags); + + /* + * We don't know what the device's macaddr is, so just accept all + * unicast packets (AUP). + */ + emc_write(qts, mod, REG_CAMCMR, REG_CAMCMR_AUP); + emc_write(qts, mod, REG_CAMEN, 1 << 0); + { + uint32_t mcmdr = emc_read(qts, mod, REG_MCMDR); + mcmdr |= REG_MCMDR_RXON | mcmdr_flags; + emc_write(qts, mod, REG_MCMDR, mcmdr); + } + + /* Prod the device to accept a packet. */ + emc_write(qts, mod, REG_RSDR, 1); +} + +static void emc_recv_verify(QTestState *qts, const EMCModule *mod, int fd, + bool with_irq) +{ + NPCM7xxEMCRxDesc desc[NUM_RX_DESCRIPTORS]; + uint32_t desc_addr = DESC_ADDR; + uint32_t data_addr = DATA_ADDR; + int ret; + uint32_t expected_mask, expected_value; + NPCM7xxEMCRxDesc result_desc; + + /* Prepare test data buffer. */ + const char test[RX_DATA_LEN] = "TEST"; + int len = htonl(sizeof(test)); + const struct iovec iov[] = { + { + .iov_base = &len, + .iov_len = sizeof(len), + },{ + .iov_base = (char *) test, + .iov_len = sizeof(test), + }, + }; + + /* + * Reset the device BEFORE sending a test packet, otherwise the packet + * may get swallowed by an active device of an earlier test. + */ + init_rx_desc(&desc[0], NUM_RX_DESCRIPTORS, desc_addr, data_addr); + enable_rx(qts, mod, &desc[0], NUM_RX_DESCRIPTORS, desc_addr, + with_irq ? REG_MIEN_ENRXINTR : 0, 0); + + /* Send test packet to device's socket. */ + ret = iov_send(fd, iov, 2, 0, sizeof(len) + sizeof(test)); + g_assert_cmpint(ret, == , sizeof(test) + sizeof(len)); + + /* Wait for RX interrupt. */ + if (with_irq) { + g_assert_true(emc_wait_irq(qts, mod, RX_STEP_COUNT, /*is_tx=*/false)); + } else { + g_assert_true(emc_wait_mista(qts, mod, RX_STEP_COUNT, REG_MISTA_RXGD)); + } + + g_assert_cmphex(emc_read(qts, mod, REG_CRXDSA), ==, + desc_addr + sizeof(desc[0])); + + expected_mask = 0xffff; + expected_value = (REG_MISTA_DENI | + REG_MISTA_RXGD | + REG_MISTA_RXINTR); + g_assert_cmphex((emc_read(qts, mod, REG_MISTA) & expected_mask), + ==, expected_value); + + /* Read the descriptor back. */ + emc_read_rx_desc(qts, desc_addr, &result_desc); + /* Descriptor should be owned by cpu now. */ + g_assert((result_desc.status_and_length & RX_DESC_STATUS_OWNER_MASK) == 0); + /* Test the status bits, ignoring the length field. */ + expected_mask = 0xffff << 16; + expected_value = RX_DESC_STATUS_RXGD; + if (with_irq) { + expected_value |= RX_DESC_STATUS_RXINTR; + } + g_assert_cmphex((result_desc.status_and_length & expected_mask), ==, + expected_value); + g_assert_cmpint(RX_DESC_PKT_LEN(result_desc.status_and_length), ==, + RX_DATA_LEN + CRC_LENGTH); + + { + char buffer[RX_DATA_LEN]; + qtest_memread(qts, data_addr, buffer, sizeof(buffer)); + g_assert_cmpstr(buffer, == , "TEST"); + } +} + +static void emc_test_ptle(QTestState *qts, const EMCModule *mod, int fd) +{ + NPCM7xxEMCRxDesc desc[NUM_RX_DESCRIPTORS]; + uint32_t desc_addr = DESC_ADDR; + uint32_t data_addr = DATA_ADDR; + int ret; + NPCM7xxEMCRxDesc result_desc; + uint32_t expected_mask, expected_value; + + /* Prepare test data buffer. */ +#define PTLE_DATA_LEN 1600 + char test_data[PTLE_DATA_LEN]; + int len = htonl(sizeof(test_data)); + const struct iovec iov[] = { + { + .iov_base = &len, + .iov_len = sizeof(len), + },{ + .iov_base = (char *) test_data, + .iov_len = sizeof(test_data), + }, + }; + memset(test_data, 42, sizeof(test_data)); + + /* + * Reset the device BEFORE sending a test packet, otherwise the packet + * may get swallowed by an active device of an earlier test. + */ + init_rx_desc(&desc[0], NUM_RX_DESCRIPTORS, desc_addr, data_addr); + enable_rx(qts, mod, &desc[0], NUM_RX_DESCRIPTORS, desc_addr, + REG_MIEN_ENRXINTR, REG_MCMDR_ALP); + + /* Send test packet to device's socket. */ + ret = iov_send(fd, iov, 2, 0, sizeof(len) + sizeof(test_data)); + g_assert_cmpint(ret, == , sizeof(test_data) + sizeof(len)); + + /* Wait for RX interrupt. */ + g_assert_true(emc_wait_irq(qts, mod, RX_STEP_COUNT, /*is_tx=*/false)); + + /* Read the descriptor back. */ + emc_read_rx_desc(qts, desc_addr, &result_desc); + /* Descriptor should be owned by cpu now. */ + g_assert((result_desc.status_and_length & RX_DESC_STATUS_OWNER_MASK) == 0); + /* Test the status bits, ignoring the length field. */ + expected_mask = 0xffff << 16; + expected_value = (RX_DESC_STATUS_RXGD | + RX_DESC_STATUS_PTLE | + RX_DESC_STATUS_RXINTR); + g_assert_cmphex((result_desc.status_and_length & expected_mask), ==, + expected_value); + g_assert_cmpint(RX_DESC_PKT_LEN(result_desc.status_and_length), ==, + PTLE_DATA_LEN + CRC_LENGTH); + + { + char buffer[PTLE_DATA_LEN]; + qtest_memread(qts, data_addr, buffer, sizeof(buffer)); + g_assert(memcmp(buffer, test_data, PTLE_DATA_LEN) == 0); + } +} + +static void test_tx(gconstpointer test_data) +{ + const TestData *td = test_data; + GString *cmd_line = g_string_new("-machine quanta-gsj"); + int *test_sockets = packet_test_init(emc_module_index(td->module), + cmd_line); + QTestState *qts = qtest_init(cmd_line->str); + + /* + * TODO: For pedantic correctness test_sockets[0] should be closed after + * the fork and before the exec, but that will require some harness + * improvements. + */ + close(test_sockets[1]); + /* Defensive programming */ + test_sockets[1] = -1; + + qtest_irq_intercept_in(qts, "/machine/soc/a9mpcore/gic"); + + emc_send_verify(qts, td->module, test_sockets[0], /*with_irq=*/false); + emc_send_verify(qts, td->module, test_sockets[0], /*with_irq=*/true); + + qtest_quit(qts); +} + +static void test_rx(gconstpointer test_data) +{ + const TestData *td = test_data; + GString *cmd_line = g_string_new("-machine quanta-gsj"); + int *test_sockets = packet_test_init(emc_module_index(td->module), + cmd_line); + QTestState *qts = qtest_init(cmd_line->str); + + /* + * TODO: For pedantic correctness test_sockets[0] should be closed after + * the fork and before the exec, but that will require some harness + * improvements. + */ + close(test_sockets[1]); + /* Defensive programming */ + test_sockets[1] = -1; + + qtest_irq_intercept_in(qts, "/machine/soc/a9mpcore/gic"); + + emc_recv_verify(qts, td->module, test_sockets[0], /*with_irq=*/false); + emc_recv_verify(qts, td->module, test_sockets[0], /*with_irq=*/true); + emc_test_ptle(qts, td->module, test_sockets[0]); + + qtest_quit(qts); +} + +static void emc_add_test(const char *name, const TestData* td, + GTestDataFunc fn) +{ + g_autofree char *full_name = g_strdup_printf( + "npcm7xx_emc/emc[%d]/%s", emc_module_index(td->module), name); + qtest_add_data_func(full_name, td, fn); +} +#define add_test(name, td) emc_add_test(#name, td, test_##name) + +int main(int argc, char **argv) +{ + TestData test_data_list[ARRAY_SIZE(emc_module_list)]; + + g_test_init(&argc, &argv, NULL); + + for (int i = 0; i < ARRAY_SIZE(emc_module_list); ++i) { + TestData *td = &test_data_list[i]; + + td->module = &emc_module_list[i]; + + add_test(init, td); + add_test(tx, td); + add_test(rx, td); + } + + 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_npcm7xx = \ 'npcm7xx_rng-test', 'npcm7xx_smbus-test', 'npcm7xx_timer-test', - 'npcm7xx_watchdog_timer-test'] + 'npcm7xx_watchdog_timer-test'] + \ + (slirp.found() ? ['npcm7xx_emc-test'] : []) qtests_arm = \ (config_all_devices.has_key('CONFIG_CMSDK_APB_DUALTIMER') ? ['cmsdk-apb-dualtimer-test'] : []) + \ (config_all_devices.has_key('CONFIG_CMSDK_APB_TIMER') ? ['cmsdk-apb-timer-test'] : []) + \ -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> We hint the 'has_rpu' property is no longer required since commit 6908ec448b4 ("xlnx-zynqmp: Properly support the smp command line option") which was released in QEMU v2.11.0. Beside, this device is marked 'user_creatable = false', so the only thing that could be setting the property is the board code that creates the device. Since the property is not user-facing, we can remove it without going through the deprecation process. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210219144350.1979905-1-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-zynqmp.h | 2 -- hw/arm/xlnx-zynqmp.c | 6 ------ 2 files changed, 8 deletions(-) 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 @@ struct XlnxZynqMPState { bool secure; /* Has the ARM Virtualization extensions? */ bool virt; - /* Has the RPU subsystem? */ - bool has_rpu; /* CAN bus. */ CanBusState *canbus[XLNX_ZYNQMP_NUM_CAN]; 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 void xlnx_zynqmp_realize(DeviceState *dev, Error **errp) } } - if (s->has_rpu) { - info_report("The 'has_rpu' property is no longer required, to use the " - "RPUs just use -smp 6."); - } - xlnx_zynqmp_create_rpu(ms, s, boot_cpu, &err); if (err) { error_propagate(errp, err); @@ -XXX,XX +XXX,XX @@ static Property xlnx_zynqmp_props[] = { DEFINE_PROP_STRING("boot-cpu", XlnxZynqMPState, boot_cpu), DEFINE_PROP_BOOL("secure", XlnxZynqMPState, secure, false), DEFINE_PROP_BOOL("virtualization", XlnxZynqMPState, virt, false), - 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, -- 2.20.1 From: Richard Henderson <richard.henderson@linaro.org> Always perform one call instead of two for 16-byte operands. Use byte loads/stores directly into the vector register file instead of extractions and deposits to a 64-bit local variable. In order to easily receive pointers into the vector register file, convert the helper to the gvec out-of-line signature. Move the helper into vec_helper.c, where it can make use of H1 and clear_tail. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Tested-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20210224230532.276878-1-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-a64.h | 2 +- target/arm/helper-a64.c | 32 --------------------- target/arm/translate-a64.c | 58 +++++--------------------------------- target/arm/vec_helper.c | 48 +++++++++++++++++++++++++++++++ 4 files changed, 56 insertions(+), 84 deletions(-) diff --git a/target/arm/helper-a64.h b/target/arm/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.h +++ b/target/arm/helper-a64.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(vfp_cmps_a64, i64, f32, f32, ptr) DEF_HELPER_3(vfp_cmpes_a64, i64, f32, f32, ptr) DEF_HELPER_3(vfp_cmpd_a64, i64, f64, f64, ptr) DEF_HELPER_3(vfp_cmped_a64, i64, f64, f64, ptr) -DEF_HELPER_FLAGS_5(simd_tbl, TCG_CALL_NO_RWG_SE, i64, env, i64, i64, i32, i32) +DEF_HELPER_FLAGS_4(simd_tblx, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_3(vfp_mulxs, TCG_CALL_NO_RWG, f32, f32, f32, ptr) DEF_HELPER_FLAGS_3(vfp_mulxd, TCG_CALL_NO_RWG, f64, f64, f64, ptr) DEF_HELPER_FLAGS_3(neon_ceq_f64, TCG_CALL_NO_RWG, i64, i64, i64, ptr) diff --git a/target/arm/helper-a64.c b/target/arm/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-a64.c +++ b/target/arm/helper-a64.c @@ -XXX,XX +XXX,XX @@ float64 HELPER(vfp_mulxd)(float64 a, float64 b, void *fpstp) return float64_mul(a, b, fpst); } -uint64_t HELPER(simd_tbl)(CPUARMState *env, uint64_t result, uint64_t indices, - uint32_t rn, uint32_t numregs) -{ - /* Helper function for SIMD TBL and TBX. We have to do the table - * lookup part for the 64 bits worth of indices we're passed in. - * result is the initial results vector (either zeroes for TBL - * or some guest values for TBX), rn the register number where - * the table starts, and numregs the number of registers in the table. - * We return the results of the lookups. - */ - int shift; - - for (shift = 0; shift < 64; shift += 8) { - int index = extract64(indices, shift, 8); - if (index < 16 * numregs) { - /* Convert index (a byte offset into the virtual table - * which is a series of 128-bit vectors concatenated) - * into the correct register element plus a bit offset - * into that element, bearing in mind that the table - * can wrap around from V31 to V0. - */ - int elt = (rn * 2 + (index >> 3)) % 64; - int bitidx = (index & 7) * 8; - uint64_t *q = aa64_vfp_qreg(env, elt >> 1); - uint64_t val = extract64(q[elt & 1], bitidx, 8); - - result = deposit64(result, shift, 8, val); - } - } - return result; -} - /* 64bit/double versions of the neon float compare functions */ uint64_t HELPER(neon_ceq_f64)(float64 a, float64 b, void *fpstp) { diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_tb(DisasContext *s, uint32_t insn) int rm = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - int is_tblx = extract32(insn, 12, 1); - int len = extract32(insn, 13, 2); - TCGv_i64 tcg_resl, tcg_resh, tcg_idx; - TCGv_i32 tcg_regno, tcg_numregs; + int is_tbx = extract32(insn, 12, 1); + int len = (extract32(insn, 13, 2) + 1) * 16; if (op2 != 0) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_tb(DisasContext *s, uint32_t insn) return; } - /* This does a table lookup: for every byte element in the input - * we index into a table formed from up to four vector registers, - * and then the output is the result of the lookups. Our helper - * function does the lookup operation for a single 64 bit part of - * the input. - */ - tcg_resl = tcg_temp_new_i64(); - tcg_resh = NULL; - - if (is_tblx) { - read_vec_element(s, tcg_resl, rd, 0, MO_64); - } else { - tcg_gen_movi_i64(tcg_resl, 0); - } - - if (is_q) { - tcg_resh = tcg_temp_new_i64(); - if (is_tblx) { - read_vec_element(s, tcg_resh, rd, 1, MO_64); - } else { - tcg_gen_movi_i64(tcg_resh, 0); - } - } - - tcg_idx = tcg_temp_new_i64(); - tcg_regno = tcg_const_i32(rn); - tcg_numregs = tcg_const_i32(len + 1); - read_vec_element(s, tcg_idx, rm, 0, MO_64); - gen_helper_simd_tbl(tcg_resl, cpu_env, tcg_resl, tcg_idx, - tcg_regno, tcg_numregs); - if (is_q) { - read_vec_element(s, tcg_idx, rm, 1, MO_64); - gen_helper_simd_tbl(tcg_resh, cpu_env, tcg_resh, tcg_idx, - tcg_regno, tcg_numregs); - } - tcg_temp_free_i64(tcg_idx); - tcg_temp_free_i32(tcg_regno); - tcg_temp_free_i32(tcg_numregs); - - write_vec_element(s, tcg_resl, rd, 0, MO_64); - tcg_temp_free_i64(tcg_resl); - - if (is_q) { - write_vec_element(s, tcg_resh, rd, 1, MO_64); - tcg_temp_free_i64(tcg_resh); - } - clear_vec_high(s, is_q, rd); + tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, rd), + vec_full_reg_offset(s, rm), cpu_env, + is_q ? 16 : 8, vec_full_reg_size(s), + (len << 6) | (is_tbx << 5) | rn, + gen_helper_simd_tblx); } /* ZIP/UZP/TRN diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ DO_VRINT_RMODE(gvec_vrint_rm_h, helper_rinth, uint16_t) DO_VRINT_RMODE(gvec_vrint_rm_s, helper_rints, uint32_t) #undef DO_VRINT_RMODE + +#ifdef TARGET_AARCH64 +void HELPER(simd_tblx)(void *vd, void *vm, void *venv, uint32_t desc) +{ + const uint8_t *indices = vm; + CPUARMState *env = venv; + size_t oprsz = simd_oprsz(desc); + uint32_t rn = extract32(desc, SIMD_DATA_SHIFT, 5); + bool is_tbx = extract32(desc, SIMD_DATA_SHIFT + 5, 1); + uint32_t table_len = desc >> (SIMD_DATA_SHIFT + 6); + union { + uint8_t b[16]; + uint64_t d[2]; + } result; + + /* + * We must construct the final result in a temp, lest the output + * overlaps the input table. For TBL, begin with zero; for TBX, + * begin with the original register contents. Note that we always + * copy 16 bytes here to avoid an extra branch; clearing the high + * bits of the register for oprsz == 8 is handled below. + */ + if (is_tbx) { + memcpy(&result, vd, 16); + } else { + memset(&result, 0, 16); + } + + for (size_t i = 0; i < oprsz; ++i) { + uint32_t index = indices[H1(i)]; + + if (index < table_len) { + /* + * Convert index (a byte offset into the virtual table + * which is a series of 128-bit vectors concatenated) + * into the correct register element, bearing in mind + * that the table can wrap around from V31 to V0. + */ + const uint8_t *table = (const uint8_t *) + aa64_vfp_qreg(env, (rn + (index >> 4)) % 32); + result.b[H1(i)] = table[H1(index % 16)]; + } + } + + memcpy(vd, &result, 16); + clear_tail(vd, oprsz, simd_maxsz(desc)); +} +#endif -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> The STATUS register will be reset to IDLE in cnpcm7xx_smbus_enter_reset(), no need to preset it in instance_init(). Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Hao Wu <wuhaotsh@google.com> Message-id: 20210228224813.312532-1-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/i2c/npcm7xx_smbus.c | 1 - 1 file changed, 1 deletion(-) diff --git a/hw/i2c/npcm7xx_smbus.c b/hw/i2c/npcm7xx_smbus.c index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/npcm7xx_smbus.c +++ b/hw/i2c/npcm7xx_smbus.c @@ -XXX,XX +XXX,XX @@ static void npcm7xx_smbus_init(Object *obj) sysbus_init_mmio(sbd, &s->iomem); s->bus = i2c_init_bus(DEVICE(s), "i2c-bus"); - s->status = NPCM7XX_SMBUS_STATUS_IDLE; } static const VMStateDescription vmstate_npcm7xx_smbus = { -- 2.20.1 From: schspa <schspa@gmail.com> At the moment the following QEMU command line triggers an assertion failure On xlnx-versal SOC: qemu-system-aarch64 \ -machine xlnx-versal-virt -nographic -smp 2 -m 128 \ -fsdev local,id=shareid,path=${HOME}/work,security_model=none \ -device virtio-9p-device,fsdev=shareid,mount_tag=share \ -fsdev local,id=shareid1,path=${HOME}/Music,security_model=none \ -device virtio-9p-device,fsdev=shareid1,mount_tag=share1 qemu-system-aarch64: ../migration/savevm.c:860: vmstate_register_with_alias_id: Assertion `!se->compat || se->instance_id == 0' failed. This problem was fixed on arm virt platform in commit f58b39d2d5b ("virtio-mmio: format transport base address in BusClass.get_dev_path") It works perfectly on arm virt platform. but there is still there on xlnx-versal SOC. The main difference between arm virt and xlnx-versal is they use different way to create virtio-mmio qdev. on arm virt, it calls sysbus_create_simple("virtio-mmio", base, pic[irq]); which will call sysbus_mmio_map internally and assign base address to subsys device mmio correctly. but xlnx-versal's implements won't do this. However, xlnx-versal can't switch to sysbus_create_simple() to create virtio-mmio device. It's because xlnx-versal's cpu use VersalVirt.soc.fpd.apu.mr as it's memory. which is subregion of system_memory. sysbus_create_simple will add virtio to system_memory, which can't be accessed by cpu. Besides, xlnx-versal can't add sysbus_mmio_map api call too, because this will add memory region to system_memory, and it can't be added to VersalVirt.soc.fpd.apu.mr again. We can solve this by assign correct base address offset on dev_path. This path was test on aarch64 virt & xlnx-versal platform. Signed-off-by: schspa <schspa@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/virtio/virtio-mmio.c | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/hw/virtio/virtio-mmio.c b/hw/virtio/virtio-mmio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/virtio/virtio-mmio.c +++ b/hw/virtio/virtio-mmio.c @@ -XXX,XX +XXX,XX @@ static char *virtio_mmio_bus_get_dev_path(DeviceState *dev) BusState *virtio_mmio_bus; VirtIOMMIOProxy *virtio_mmio_proxy; char *proxy_path; - SysBusDevice *proxy_sbd; char *path; + MemoryRegionSection section; virtio_mmio_bus = qdev_get_parent_bus(dev); virtio_mmio_proxy = VIRTIO_MMIO(virtio_mmio_bus->parent); @@ -XXX,XX +XXX,XX @@ static char *virtio_mmio_bus_get_dev_path(DeviceState *dev) } /* Otherwise, we append the base address of the transport. */ - proxy_sbd = SYS_BUS_DEVICE(virtio_mmio_proxy); - assert(proxy_sbd->num_mmio == 1); - assert(proxy_sbd->mmio[0].memory == &virtio_mmio_proxy->iomem); + section = memory_region_find(&virtio_mmio_proxy->iomem, 0, 0x200); + assert(section.mr); if (proxy_path) { path = g_strdup_printf("%s/virtio-mmio@" TARGET_FMT_plx, proxy_path, - proxy_sbd->mmio[0].addr); + section.offset_within_address_space); } else { path = g_strdup_printf("virtio-mmio@" TARGET_FMT_plx, - proxy_sbd->mmio[0].addr); + section.offset_within_address_space); } + memory_region_unref(section.mr); + g_free(proxy_path); return path; } -- 2.20.1 From: Peter Collingbourne <pcc@google.com> Section D6.7 of the ARM ARM states: For the purpose of determining Tag Check Fault handling, unprivileged load and store instructions are treated as if executed at EL0 when executed at either: - EL1, when the Effective value of PSTATE.UAO is 0. - EL2, when both the Effective value of HCR_EL2.{E2H, TGE} is {1, 1} and the Effective value of PSTATE.UAO is 0. ARM has confirmed a defect in the pseudocode function AArch64.TagCheckFault that makes it inconsistent with the above wording. The remedy is to adjust references to PSTATE.EL in that function to instead refer to AArch64.AccessUsesEL(acctype), so that unprivileged instructions use SCTLR_EL1.TCF0 and TFSRE0_EL1. The exception type for synchronous tag check faults remains unchanged. This patch implements the described change by partially reverting commits 50244cc76abc and cc97b0019bb5. Signed-off-by: Peter Collingbourne <pcc@google.com> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210219201820.2672077-1-pcc@google.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 2 +- target/arm/mte_helper.c | 13 +++++++++---- 2 files changed, 10 insertions(+), 5 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint32_t rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, if (FIELD_EX32(flags, TBFLAG_A64, UNPRIV) && tbid && !(env->pstate & PSTATE_TCO) - && (sctlr & SCTLR_TCF) + && (sctlr & SCTLR_TCF0) && allocation_tag_access_enabled(env, 0, sctlr)) { flags = FIELD_DP32(flags, TBFLAG_A64, MTE0_ACTIVE, 1); } diff --git a/target/arm/mte_helper.c b/target/arm/mte_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mte_helper.c +++ b/target/arm/mte_helper.c @@ -XXX,XX +XXX,XX @@ static void mte_check_fail(CPUARMState *env, uint32_t desc, reg_el = regime_el(env, arm_mmu_idx); sctlr = env->cp15.sctlr_el[reg_el]; - el = arm_current_el(env); - if (el == 0) { + switch (arm_mmu_idx) { + case ARMMMUIdx_E10_0: + case ARMMMUIdx_E20_0: + el = 0; tcf = extract64(sctlr, 38, 2); - } else { + break; + default: + el = reg_el; tcf = extract64(sctlr, 40, 2); } @@ -XXX,XX +XXX,XX @@ static void mte_check_fail(CPUARMState *env, uint32_t desc, env->exception.vaddress = dirty_ptr; is_write = FIELD_EX32(desc, MTEDESC, WRITE); - syn = syn_data_abort_no_iss(el != 0, 0, 0, 0, 0, is_write, 0x11); + syn = syn_data_abort_no_iss(arm_current_el(env) != 0, 0, 0, 0, 0, + is_write, 0x11); raise_exception(env, EXCP_DATA_ABORT, syn, exception_target_el(env)); /* noreturn, but fall through to the assert anyway */ -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> IDAU is specific to M-profile. KVM only supports A-profile. Restrict this interface to TCG, as it is pointless (and confusing) on a KVM-only build. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210221222617.2579610-2-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 7 ------- target/arm/cpu_tcg.c | 8 ++++++++ 2 files changed, 8 insertions(+), 7 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 @@ static const TypeInfo arm_cpu_type_info = { .class_init = arm_cpu_class_init, }; -static const TypeInfo idau_interface_type_info = { - .name = TYPE_IDAU_INTERFACE, - .parent = TYPE_INTERFACE, - .class_size = sizeof(IDAUInterfaceClass), -}; - static void arm_cpu_register_types(void) { const size_t cpu_count = ARRAY_SIZE(arm_cpus); @@ -XXX,XX +XXX,XX @@ static void arm_cpu_register_types(void) if (cpu_count) { size_t i; - type_register_static(&idau_interface_type_info); for (i = 0; i < cpu_count; ++i) { arm_cpu_register(&arm_cpus[i]); } diff --git a/target/arm/cpu_tcg.c b/target/arm/cpu_tcg.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu_tcg.c +++ b/target/arm/cpu_tcg.c @@ -XXX,XX +XXX,XX @@ #include "hw/core/tcg-cpu-ops.h" #endif /* CONFIG_TCG */ #include "internals.h" +#include "target/arm/idau.h" /* CPU models. These are not needed for the AArch64 linux-user build. */ #if !defined(CONFIG_USER_ONLY) || !defined(TARGET_AARCH64) @@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo arm_tcg_cpus[] = { { .name = "pxa270-c5", .initfn = pxa270c5_initfn }, }; +static const TypeInfo idau_interface_type_info = { + .name = TYPE_IDAU_INTERFACE, + .parent = TYPE_INTERFACE, + .class_size = sizeof(IDAUInterfaceClass), +}; + static void arm_tcg_cpu_register_types(void) { size_t i; + type_register_static(&idau_interface_type_info); for (i = 0; i < ARRAY_SIZE(arm_tcg_cpus); ++i) { arm_cpu_register(&arm_tcg_cpus[i]); } -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> We will move this code in the next commit. Clean it up first to avoid checkpatch.pl errors. Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20210221222617.2579610-3-f4bug@amsat.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 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 @@ static void cortex_a8_initfn(Object *obj) } static const ARMCPRegInfo cortexa9_cp_reginfo[] = { - /* power_control should be set to maximum latency. Again, + /* + * power_control should be set to maximum latency. Again, * default to 0 and set by private hook */ { .name = "A9_PWRCTL", .cp = 15, .crn = 15, .crm = 0, .opc1 = 0, .opc2 = 0, @@ -XXX,XX +XXX,XX @@ static void cortex_a9_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_NEON); set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_EL3); - /* Note that A9 supports the MP extensions even for + /* + * Note that A9 supports the MP extensions even for * A9UP and single-core A9MP (which are both different * and valid configurations; we don't model A9UP). */ @@ -XXX,XX +XXX,XX @@ static uint64_t a15_l2ctlr_read(CPUARMState *env, const ARMCPRegInfo *ri) { MachineState *ms = MACHINE(qdev_get_machine()); - /* Linux wants the number of processors from here. + /* + * Linux wants the number of processors from here. * Might as well set the interrupt-controller bit too. */ return ((ms->smp.cpus - 1) << 24) | (1 << 23); @@ -XXX,XX +XXX,XX @@ static void cortex_a7_initfn(Object *obj) cpu->isar.id_mmfr1 = 0x40000000; cpu->isar.id_mmfr2 = 0x01240000; cpu->isar.id_mmfr3 = 0x02102211; - /* a7_mpcore_r0p5_trm, page 4-4 gives 0x01101110; but + /* + * a7_mpcore_r0p5_trm, page 4-4 gives 0x01101110; but * table 4-41 gives 0x02101110, which includes the arm div insns. */ cpu->isar.id_isar0 = 0x02101110; -- 2.20.1 For a long time now the UI layer has guaranteed that the console surface is always 32 bits per pixel RGB. Remove the legacy dead code from the milkymist display device which was handling the possibility that the console surface was some other format. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215103215.4944-2-peter.maydell@linaro.org --- hw/arm/musicpal.c | 64 ++++++++++++++++++----------------------------- 1 file changed, 24 insertions(+), 40 deletions(-) diff --git a/hw/arm/musicpal.c b/hw/arm/musicpal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/musicpal.c +++ b/hw/arm/musicpal.c @@ -XXX,XX +XXX,XX @@ static uint8_t scale_lcd_color(musicpal_lcd_state *s, uint8_t col) } } -#define SET_LCD_PIXEL(depth, type) \ -static inline void glue(set_lcd_pixel, depth) \ - (musicpal_lcd_state *s, int x, int y, type col) \ -{ \ - int dx, dy; \ - DisplaySurface *surface = qemu_console_surface(s->con); \ - type *pixel = &((type *) surface_data(surface))[(y * 128 * 3 + x) * 3]; \ -\ - for (dy = 0; dy < 3; dy++, pixel += 127 * 3) \ - for (dx = 0; dx < 3; dx++, pixel++) \ - *pixel = col; \ +static inline void set_lcd_pixel32(musicpal_lcd_state *s, + int x, int y, uint32_t col) +{ + int dx, dy; + DisplaySurface *surface = qemu_console_surface(s->con); + uint32_t *pixel = + &((uint32_t *) surface_data(surface))[(y * 128 * 3 + x) * 3]; + + for (dy = 0; dy < 3; dy++, pixel += 127 * 3) { + for (dx = 0; dx < 3; dx++, pixel++) { + *pixel = col; + } + } } -SET_LCD_PIXEL(8, uint8_t) -SET_LCD_PIXEL(16, uint16_t) -SET_LCD_PIXEL(32, uint32_t) static void lcd_refresh(void *opaque) { musicpal_lcd_state *s = opaque; - DisplaySurface *surface = qemu_console_surface(s->con); int x, y, col; - switch (surface_bits_per_pixel(surface)) { - case 0: - return; -#define LCD_REFRESH(depth, func) \ - case depth: \ - col = func(scale_lcd_color(s, (MP_LCD_TEXTCOLOR >> 16) & 0xff), \ - scale_lcd_color(s, (MP_LCD_TEXTCOLOR >> 8) & 0xff), \ - scale_lcd_color(s, MP_LCD_TEXTCOLOR & 0xff)); \ - for (x = 0; x < 128; x++) { \ - for (y = 0; y < 64; y++) { \ - if (s->video_ram[x + (y/8)*128] & (1 << (y % 8))) { \ - glue(set_lcd_pixel, depth)(s, x, y, col); \ - } else { \ - glue(set_lcd_pixel, depth)(s, x, y, 0); \ - } \ - } \ - } \ - break; - LCD_REFRESH(8, rgb_to_pixel8) - LCD_REFRESH(16, rgb_to_pixel16) - LCD_REFRESH(32, (is_surface_bgr(surface) ? - rgb_to_pixel32bgr : rgb_to_pixel32)) - default: - hw_error("unsupported colour depth %i\n", - surface_bits_per_pixel(surface)); + col = rgb_to_pixel32(scale_lcd_color(s, (MP_LCD_TEXTCOLOR >> 16) & 0xff), + scale_lcd_color(s, (MP_LCD_TEXTCOLOR >> 8) & 0xff), + scale_lcd_color(s, MP_LCD_TEXTCOLOR & 0xff)); + for (x = 0; x < 128; x++) { + for (y = 0; y < 64; y++) { + if (s->video_ram[x + (y / 8) * 128] & (1 << (y % 8))) { + set_lcd_pixel32(s, x, y, col); + } else { + set_lcd_pixel32(s, x, y, 0); + } + } } dpy_gfx_update(s->con, 0, 0, 128*3, 64*3); -- 2.20.1 For a long time now the UI layer has guaranteed that the console surface is always 32 bits per pixel RGB. Remove the legacy dead code from the tc6393xb display device which was handling the possibility that the console surface was some other format. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215103215.4944-3-peter.maydell@linaro.org --- include/ui/console.h | 10 ---------- hw/display/tc6393xb.c | 33 +-------------------------------- 2 files changed, 1 insertion(+), 42 deletions(-) diff --git a/include/ui/console.h b/include/ui/console.h index XXXXXXX..XXXXXXX 100644 --- a/include/ui/console.h +++ b/include/ui/console.h @@ -XXX,XX +XXX,XX @@ PixelFormat qemu_default_pixelformat(int bpp); DisplaySurface *qemu_create_displaysurface(int width, int height); void qemu_free_displaysurface(DisplaySurface *surface); -static inline int is_surface_bgr(DisplaySurface *surface) -{ - if (PIXMAN_FORMAT_BPP(surface->format) == 32 && - PIXMAN_FORMAT_TYPE(surface->format) == PIXMAN_TYPE_ABGR) { - return 1; - } else { - return 0; - } -} - static inline int is_buffer_shared(DisplaySurface *surface) { return !(surface->flags & QEMU_ALLOCATED_FLAG); diff --git a/hw/display/tc6393xb.c b/hw/display/tc6393xb.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/tc6393xb.c +++ b/hw/display/tc6393xb.c @@ -XXX,XX +XXX,XX @@ static void tc6393xb_nand_writeb(TC6393xbState *s, hwaddr addr, uint32_t value) (uint32_t) addr, value & 0xff); } -#define BITS 8 -#include "tc6393xb_template.h" -#define BITS 15 -#include "tc6393xb_template.h" -#define BITS 16 -#include "tc6393xb_template.h" -#define BITS 24 -#include "tc6393xb_template.h" #define BITS 32 #include "tc6393xb_template.h" static void tc6393xb_draw_graphic(TC6393xbState *s, int full_update) { - DisplaySurface *surface = qemu_console_surface(s->con); - - switch (surface_bits_per_pixel(surface)) { - case 8: - tc6393xb_draw_graphic8(s); - break; - case 15: - tc6393xb_draw_graphic15(s); - break; - case 16: - tc6393xb_draw_graphic16(s); - break; - case 24: - tc6393xb_draw_graphic24(s); - break; - case 32: - tc6393xb_draw_graphic32(s); - break; - default: - printf("tc6393xb: unknown depth %d\n", - surface_bits_per_pixel(surface)); - return; - } - + tc6393xb_draw_graphic32(s); dpy_gfx_update_full(s->con); } -- 2.20.1 Now the template header is included only for BITS==32, expand out all the macros that depended on the BITS setting. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215103215.4944-4-peter.maydell@linaro.org --- hw/display/tc6393xb_template.h | 35 ++++------------------------------ 1 file changed, 4 insertions(+), 31 deletions(-) diff --git a/hw/display/tc6393xb_template.h b/hw/display/tc6393xb_template.h index XXXXXXX..XXXXXXX 100644 --- a/hw/display/tc6393xb_template.h +++ b/hw/display/tc6393xb_template.h @@ -XXX,XX +XXX,XX @@ * with this program; if not, see <http://www.gnu.org/licenses/>. */ -#if BITS == 8 -# define SET_PIXEL(addr, color) (*(uint8_t *)addr = color) -#elif BITS == 15 || BITS == 16 -# define SET_PIXEL(addr, color) (*(uint16_t *)addr = color) -#elif BITS == 24 -# define SET_PIXEL(addr, color) \ - do { \ - addr[0] = color; \ - addr[1] = (color) >> 8; \ - addr[2] = (color) >> 16; \ - } while (0) -#elif BITS == 32 -# define SET_PIXEL(addr, color) (*(uint32_t *)addr = color) -#else -# error unknown bit depth -#endif - - -static void glue(tc6393xb_draw_graphic, BITS)(TC6393xbState *s) +static void tc6393xb_draw_graphic32(TC6393xbState *s) { DisplaySurface *surface = qemu_console_surface(s->con); int i; @@ -XXX,XX +XXX,XX @@ static void glue(tc6393xb_draw_graphic, BITS)(TC6393xbState *s) data_buffer = s->vram_ptr; data_display = surface_data(surface); for(i = 0; i < s->scr_height; i++) { -#if (BITS == 16) - memcpy(data_display, data_buffer, s->scr_width * 2); - data_buffer += s->scr_width; - data_display += surface_stride(surface); -#else int j; - for (j = 0; j < s->scr_width; j++, data_display += BITS / 8, data_buffer++) { + for (j = 0; j < s->scr_width; j++, data_display += 4, data_buffer++) { uint16_t color = *data_buffer; - uint32_t dest_color = glue(rgb_to_pixel, BITS)( + uint32_t dest_color = rgb_to_pixel32( ((color & 0xf800) * 0x108) >> 11, ((color & 0x7e0) * 0x41) >> 9, ((color & 0x1f) * 0x21) >> 2 ); - SET_PIXEL(data_display, dest_color); + *(uint32_t *)data_display = dest_color; } -#endif } } - -#undef BITS -#undef SET_PIXEL -- 2.20.1 The function tc6393xb_draw_graphic32() is called in exactly one place, so just inline the function body at its callsite. This allows us to drop the template header entirely. The code move includes a single added space after 'for' to fix the coding style. 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: 20210215103215.4944-5-peter.maydell@linaro.org --- hw/display/tc6393xb_template.h | 45 ---------------------------------- hw/display/tc6393xb.c | 23 ++++++++++++++--- 2 files changed, 19 insertions(+), 49 deletions(-) delete mode 100644 hw/display/tc6393xb_template.h diff --git a/hw/display/tc6393xb_template.h b/hw/display/tc6393xb_template.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/display/tc6393xb_template.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Toshiba TC6393XB I/O Controller. - * Found in Sharp Zaurus SL-6000 (tosa) or some - * Toshiba e-Series PDAs. - * - * FB support code. Based on G364 fb emulator - * - * Copyright (c) 2007 Hervé Poussineau - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License as - * published by the Free Software Foundation; either version 2 of - * the License, or (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along - * with this program; if not, see <http://www.gnu.org/licenses/>. - */ - -static void tc6393xb_draw_graphic32(TC6393xbState *s) -{ - DisplaySurface *surface = qemu_console_surface(s->con); - int i; - uint16_t *data_buffer; - uint8_t *data_display; - - data_buffer = s->vram_ptr; - data_display = surface_data(surface); - for(i = 0; i < s->scr_height; i++) { - int j; - for (j = 0; j < s->scr_width; j++, data_display += 4, data_buffer++) { - uint16_t color = *data_buffer; - uint32_t dest_color = rgb_to_pixel32( - ((color & 0xf800) * 0x108) >> 11, - ((color & 0x7e0) * 0x41) >> 9, - ((color & 0x1f) * 0x21) >> 2 - ); - *(uint32_t *)data_display = dest_color; - } - } -} diff --git a/hw/display/tc6393xb.c b/hw/display/tc6393xb.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/tc6393xb.c +++ b/hw/display/tc6393xb.c @@ -XXX,XX +XXX,XX @@ static void tc6393xb_nand_writeb(TC6393xbState *s, hwaddr addr, uint32_t value) (uint32_t) addr, value & 0xff); } -#define BITS 32 -#include "tc6393xb_template.h" - static void tc6393xb_draw_graphic(TC6393xbState *s, int full_update) { - tc6393xb_draw_graphic32(s); + DisplaySurface *surface = qemu_console_surface(s->con); + int i; + uint16_t *data_buffer; + uint8_t *data_display; + + data_buffer = s->vram_ptr; + data_display = surface_data(surface); + for (i = 0; i < s->scr_height; i++) { + int j; + for (j = 0; j < s->scr_width; j++, data_display += 4, data_buffer++) { + uint16_t color = *data_buffer; + uint32_t dest_color = rgb_to_pixel32( + ((color & 0xf800) * 0x108) >> 11, + ((color & 0x7e0) * 0x41) >> 9, + ((color & 0x1f) * 0x21) >> 2 + ); + *(uint32_t *)data_display = dest_color; + } + } dpy_gfx_update_full(s->con); } -- 2.20.1 The omap_lcdc template header is already only included once, for DEPTH==32, but it still has all the macro-driven parameterization for other depths. Expand out all the macros in the header. 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: 20210215103215.4944-6-peter.maydell@linaro.org --- hw/display/omap_lcd_template.h | 67 ++++++++++++++-------------------- 1 file changed, 28 insertions(+), 39 deletions(-) diff --git a/hw/display/omap_lcd_template.h b/hw/display/omap_lcd_template.h index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcd_template.h +++ b/hw/display/omap_lcd_template.h @@ -XXX,XX +XXX,XX @@ * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ -#if DEPTH == 32 -# define BPP 4 -# define PIXEL_TYPE uint32_t -#else -# error unsupport depth -#endif - /* * 2-bit colour */ -static void glue(draw_line2_, DEPTH)(void *opaque, - uint8_t *d, const uint8_t *s, int width, int deststep) +static void draw_line2_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) { uint16_t *pal = opaque; uint8_t v, r, g, b; @@ -XXX,XX +XXX,XX @@ static void glue(draw_line2_, DEPTH)(void *opaque, r = (pal[v & 3] >> 4) & 0xf0; g = pal[v & 3] & 0xf0; b = (pal[v & 3] << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); - d += BPP; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; v >>= 2; r = (pal[v & 3] >> 4) & 0xf0; g = pal[v & 3] & 0xf0; b = (pal[v & 3] << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); - d += BPP; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; v >>= 2; r = (pal[v & 3] >> 4) & 0xf0; g = pal[v & 3] & 0xf0; b = (pal[v & 3] << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); - d += BPP; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; v >>= 2; r = (pal[v & 3] >> 4) & 0xf0; g = pal[v & 3] & 0xf0; b = (pal[v & 3] << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); - d += BPP; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; s ++; width -= 4; } while (width > 0); @@ -XXX,XX +XXX,XX @@ static void glue(draw_line2_, DEPTH)(void *opaque, /* * 4-bit colour */ -static void glue(draw_line4_, DEPTH)(void *opaque, - uint8_t *d, const uint8_t *s, int width, int deststep) +static void draw_line4_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) { uint16_t *pal = opaque; uint8_t v, r, g, b; @@ -XXX,XX +XXX,XX @@ static void glue(draw_line4_, DEPTH)(void *opaque, r = (pal[v & 0xf] >> 4) & 0xf0; g = pal[v & 0xf] & 0xf0; b = (pal[v & 0xf] << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); - d += BPP; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; v >>= 4; r = (pal[v & 0xf] >> 4) & 0xf0; g = pal[v & 0xf] & 0xf0; b = (pal[v & 0xf] << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); - d += BPP; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; s ++; width -= 2; } while (width > 0); @@ -XXX,XX +XXX,XX @@ static void glue(draw_line4_, DEPTH)(void *opaque, /* * 8-bit colour */ -static void glue(draw_line8_, DEPTH)(void *opaque, - uint8_t *d, const uint8_t *s, int width, int deststep) +static void draw_line8_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) { uint16_t *pal = opaque; uint8_t v, r, g, b; @@ -XXX,XX +XXX,XX @@ static void glue(draw_line8_, DEPTH)(void *opaque, r = (pal[v] >> 4) & 0xf0; g = pal[v] & 0xf0; b = (pal[v] << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); s ++; - d += BPP; + d += 4; } while (-- width != 0); } /* * 12-bit colour */ -static void glue(draw_line12_, DEPTH)(void *opaque, - uint8_t *d, const uint8_t *s, int width, int deststep) +static void draw_line12_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) { uint16_t v; uint8_t r, g, b; @@ -XXX,XX +XXX,XX @@ static void glue(draw_line12_, DEPTH)(void *opaque, r = (v >> 4) & 0xf0; g = v & 0xf0; b = (v << 4) & 0xf0; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); s += 2; - d += BPP; + d += 4; } while (-- width != 0); } /* * 16-bit colour */ -static void glue(draw_line16_, DEPTH)(void *opaque, - uint8_t *d, const uint8_t *s, int width, int deststep) +static void draw_line16_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) { #if defined(HOST_WORDS_BIGENDIAN) == defined(TARGET_WORDS_BIGENDIAN) memcpy(d, s, width * 2); @@ -XXX,XX +XXX,XX @@ static void glue(draw_line16_, DEPTH)(void *opaque, r = (v >> 8) & 0xf8; g = (v >> 3) & 0xfc; b = (v << 3) & 0xf8; - ((PIXEL_TYPE *) d)[0] = glue(rgb_to_pixel, DEPTH)(r, g, b); + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); s += 2; - d += BPP; + d += 4; } while (-- width != 0); #endif } - -#undef DEPTH -#undef BPP -#undef PIXEL_TYPE -- 2.20.1 The draw_line16_32() function in the omap_lcdc template header includes an ifdef for the case where HOST_WORDS_BIGENDIAN matches TARGET_WORDS_BIGENDIAN. This is trying to optimise for "source bitmap and destination bitmap format match", but it is broken, because in this function the formats don't match: the source is 16-bit colour and the destination is 32-bit colour, so a memcpy() will produce corrupted graphics output. Drop the bogus ifdef. This bug was introduced in commit ea644cf343129, when we dropped support for DEPTH values other than 32 from the template header. The old #if line was #if DEPTH == 16 && defined(HOST_WORDS_BIGENDIAN) == defined(TARGET_WORDS_BIGENDIAN) and this was mistakenly changed to #if defined(HOST_WORDS_BIGENDIAN) == defined(TARGET_WORDS_BIGENDIAN) rather than deleting the #if as now having an always-false condition. Fixes: ea644cf343129 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: 20210215103215.4944-7-peter.maydell@linaro.org --- hw/display/omap_lcd_template.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/hw/display/omap_lcd_template.h b/hw/display/omap_lcd_template.h index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcd_template.h +++ b/hw/display/omap_lcd_template.h @@ -XXX,XX +XXX,XX @@ static void draw_line12_32(void *opaque, uint8_t *d, const uint8_t *s, static void draw_line16_32(void *opaque, uint8_t *d, const uint8_t *s, int width, int deststep) { -#if defined(HOST_WORDS_BIGENDIAN) == defined(TARGET_WORDS_BIGENDIAN) - memcpy(d, s, width * 2); -#else uint16_t v; uint8_t r, g, b; @@ -XXX,XX +XXX,XX @@ static void draw_line16_32(void *opaque, uint8_t *d, const uint8_t *s, s += 2; d += 4; } while (-- width != 0); -#endif } -- 2.20.1 Fix some minor coding style issues in the template header, so checkpatch doesn't complain when we move the 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> Message-id: 20210215103215.4944-8-peter.maydell@linaro.org --- hw/display/omap_lcd_template.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/hw/display/omap_lcd_template.h b/hw/display/omap_lcd_template.h index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcd_template.h +++ b/hw/display/omap_lcd_template.h @@ -XXX,XX +XXX,XX @@ static void draw_line2_32(void *opaque, uint8_t *d, const uint8_t *s, b = (pal[v & 3] << 4) & 0xf0; ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); d += 4; - s ++; + s++; width -= 4; } while (width > 0); } @@ -XXX,XX +XXX,XX @@ static void draw_line4_32(void *opaque, uint8_t *d, const uint8_t *s, b = (pal[v & 0xf] << 4) & 0xf0; ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); d += 4; - s ++; + s++; width -= 2; } while (width > 0); } @@ -XXX,XX +XXX,XX @@ static void draw_line8_32(void *opaque, uint8_t *d, const uint8_t *s, g = pal[v] & 0xf0; b = (pal[v] << 4) & 0xf0; ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - s ++; + s++; d += 4; } while (-- width != 0); } -- 2.20.1 We only include the template header once, so just inline it into the source file for the device. 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: 20210215103215.4944-9-peter.maydell@linaro.org --- hw/display/omap_lcd_template.h | 154 --------------------------------- hw/display/omap_lcdc.c | 127 ++++++++++++++++++++++++++- 2 files changed, 125 insertions(+), 156 deletions(-) delete mode 100644 hw/display/omap_lcd_template.h diff --git a/hw/display/omap_lcd_template.h b/hw/display/omap_lcd_template.h deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/display/omap_lcd_template.h +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * QEMU OMAP LCD Emulator templates - * - * Copyright (c) 2006 Andrzej Zaborowski <balrog@zabor.org> - * - * Redistribution and use in source and binary forms, with or without - * modification, are permitted provided that the following conditions - * are met: - * - * 1. Redistributions of source code must retain the above copyright - * notice, this list of conditions and the following disclaimer. - * 2. Redistributions in binary form must reproduce the above copyright - * notice, this list of conditions and the following disclaimer in - * the documentation and/or other materials provided with the - * distribution. - * - * THIS SOFTWARE IS PROVIDED BY THE AUTHOR AND CONTRIBUTORS ``AS IS'' - * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, - * THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A - * PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE AUTHOR OR - * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, - * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, - * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR - * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY - * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT - * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE - * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. - */ - -/* - * 2-bit colour - */ -static void draw_line2_32(void *opaque, uint8_t *d, const uint8_t *s, - int width, int deststep) -{ - uint16_t *pal = opaque; - uint8_t v, r, g, b; - - do { - v = ldub_p((void *) s); - r = (pal[v & 3] >> 4) & 0xf0; - g = pal[v & 3] & 0xf0; - b = (pal[v & 3] << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - d += 4; - v >>= 2; - r = (pal[v & 3] >> 4) & 0xf0; - g = pal[v & 3] & 0xf0; - b = (pal[v & 3] << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - d += 4; - v >>= 2; - r = (pal[v & 3] >> 4) & 0xf0; - g = pal[v & 3] & 0xf0; - b = (pal[v & 3] << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - d += 4; - v >>= 2; - r = (pal[v & 3] >> 4) & 0xf0; - g = pal[v & 3] & 0xf0; - b = (pal[v & 3] << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - d += 4; - s++; - width -= 4; - } while (width > 0); -} - -/* - * 4-bit colour - */ -static void draw_line4_32(void *opaque, uint8_t *d, const uint8_t *s, - int width, int deststep) -{ - uint16_t *pal = opaque; - uint8_t v, r, g, b; - - do { - v = ldub_p((void *) s); - r = (pal[v & 0xf] >> 4) & 0xf0; - g = pal[v & 0xf] & 0xf0; - b = (pal[v & 0xf] << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - d += 4; - v >>= 4; - r = (pal[v & 0xf] >> 4) & 0xf0; - g = pal[v & 0xf] & 0xf0; - b = (pal[v & 0xf] << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - d += 4; - s++; - width -= 2; - } while (width > 0); -} - -/* - * 8-bit colour - */ -static void draw_line8_32(void *opaque, uint8_t *d, const uint8_t *s, - int width, int deststep) -{ - uint16_t *pal = opaque; - uint8_t v, r, g, b; - - do { - v = ldub_p((void *) s); - r = (pal[v] >> 4) & 0xf0; - g = pal[v] & 0xf0; - b = (pal[v] << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - s++; - d += 4; - } while (-- width != 0); -} - -/* - * 12-bit colour - */ -static void draw_line12_32(void *opaque, uint8_t *d, const uint8_t *s, - int width, int deststep) -{ - uint16_t v; - uint8_t r, g, b; - - do { - v = lduw_le_p((void *) s); - r = (v >> 4) & 0xf0; - g = v & 0xf0; - b = (v << 4) & 0xf0; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - s += 2; - d += 4; - } while (-- width != 0); -} - -/* - * 16-bit colour - */ -static void draw_line16_32(void *opaque, uint8_t *d, const uint8_t *s, - int width, int deststep) -{ - uint16_t v; - uint8_t r, g, b; - - do { - v = lduw_le_p((void *) s); - r = (v >> 8) & 0xf8; - g = (v >> 3) & 0xfc; - b = (v << 3) & 0xf8; - ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); - s += 2; - d += 4; - } while (-- width != 0); -} diff --git a/hw/display/omap_lcdc.c b/hw/display/omap_lcdc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcdc.c +++ b/hw/display/omap_lcdc.c @@ -XXX,XX +XXX,XX @@ static void omap_lcd_interrupts(struct omap_lcd_panel_s *s) #define draw_line_func drawfn -#define DEPTH 32 -#include "omap_lcd_template.h" +/* + * 2-bit colour + */ +static void draw_line2_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) +{ + uint16_t *pal = opaque; + uint8_t v, r, g, b; + + do { + v = ldub_p((void *) s); + r = (pal[v & 3] >> 4) & 0xf0; + g = pal[v & 3] & 0xf0; + b = (pal[v & 3] << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; + v >>= 2; + r = (pal[v & 3] >> 4) & 0xf0; + g = pal[v & 3] & 0xf0; + b = (pal[v & 3] << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; + v >>= 2; + r = (pal[v & 3] >> 4) & 0xf0; + g = pal[v & 3] & 0xf0; + b = (pal[v & 3] << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; + v >>= 2; + r = (pal[v & 3] >> 4) & 0xf0; + g = pal[v & 3] & 0xf0; + b = (pal[v & 3] << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; + s++; + width -= 4; + } while (width > 0); +} + +/* + * 4-bit colour + */ +static void draw_line4_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) +{ + uint16_t *pal = opaque; + uint8_t v, r, g, b; + + do { + v = ldub_p((void *) s); + r = (pal[v & 0xf] >> 4) & 0xf0; + g = pal[v & 0xf] & 0xf0; + b = (pal[v & 0xf] << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; + v >>= 4; + r = (pal[v & 0xf] >> 4) & 0xf0; + g = pal[v & 0xf] & 0xf0; + b = (pal[v & 0xf] << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + d += 4; + s++; + width -= 2; + } while (width > 0); +} + +/* + * 8-bit colour + */ +static void draw_line8_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) +{ + uint16_t *pal = opaque; + uint8_t v, r, g, b; + + do { + v = ldub_p((void *) s); + r = (pal[v] >> 4) & 0xf0; + g = pal[v] & 0xf0; + b = (pal[v] << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + s++; + d += 4; + } while (-- width != 0); +} + +/* + * 12-bit colour + */ +static void draw_line12_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) +{ + uint16_t v; + uint8_t r, g, b; + + do { + v = lduw_le_p((void *) s); + r = (v >> 4) & 0xf0; + g = v & 0xf0; + b = (v << 4) & 0xf0; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + s += 2; + d += 4; + } while (-- width != 0); +} + +/* + * 16-bit colour + */ +static void draw_line16_32(void *opaque, uint8_t *d, const uint8_t *s, + int width, int deststep) +{ + uint16_t v; + uint8_t r, g, b; + + do { + v = lduw_le_p((void *) s); + r = (v >> 8) & 0xf8; + g = (v >> 3) & 0xfc; + b = (v << 3) & 0xf8; + ((uint32_t *) d)[0] = rgb_to_pixel32(r, g, b); + s += 2; + d += 4; + } while (-- width != 0); +} static void omap_update_display(void *opaque) { -- 2.20.1 The macro draw_line_func is used only once; just expand it. 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: 20210215103215.4944-10-peter.maydell@linaro.org --- hw/display/omap_lcdc.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) diff --git a/hw/display/omap_lcdc.c b/hw/display/omap_lcdc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/omap_lcdc.c +++ b/hw/display/omap_lcdc.c @@ -XXX,XX +XXX,XX @@ static void omap_lcd_interrupts(struct omap_lcd_panel_s *s) qemu_irq_lower(s->irq); } -#define draw_line_func drawfn - /* * 2-bit colour */ @@ -XXX,XX +XXX,XX @@ static void omap_update_display(void *opaque) { struct omap_lcd_panel_s *omap_lcd = (struct omap_lcd_panel_s *) opaque; DisplaySurface *surface; - draw_line_func draw_line; + drawfn draw_line; int size, height, first, last; int width, linesize, step, bpp, frame_offset; hwaddr frame_base; -- 2.20.1 For a long time now the UI layer has guaranteed that the console surface is always 32 bits per pixel, RGB. The TCX code already assumes 32bpp, but it still has some checks of is_surface_bgr() in an attempt to support 32bpp BGR. is_surface_bgr() will always return false for the qemu_console_surface(), unless the display device itself has deliberately created an alternate-format surface via a function like qemu_create_displaysurface_from(). Drop the never-used BGR-handling code, and assert that we have a 32-bit surface rather than just doing nothing if it isn't. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215102149.20513-1-peter.maydell@linaro.org --- hw/display/tcx.c | 31 ++++++++----------------------- 1 file changed, 8 insertions(+), 23 deletions(-) diff --git a/hw/display/tcx.c b/hw/display/tcx.c index XXXXXXX..XXXXXXX 100644 --- a/hw/display/tcx.c +++ b/hw/display/tcx.c @@ -XXX,XX +XXX,XX @@ static int tcx_check_dirty(TCXState *s, DirtyBitmapSnapshot *snap, static void update_palette_entries(TCXState *s, int start, int end) { - DisplaySurface *surface = qemu_console_surface(s->con); int i; for (i = start; i < end; i++) { - if (is_surface_bgr(surface)) { - s->palette[i] = rgb_to_pixel32bgr(s->r[i], s->g[i], s->b[i]); - } else { - s->palette[i] = rgb_to_pixel32(s->r[i], s->g[i], s->b[i]); - } + s->palette[i] = rgb_to_pixel32(s->r[i], s->g[i], s->b[i]); } tcx_set_dirty(s, 0, memory_region_size(&s->vram_mem)); } @@ -XXX,XX +XXX,XX @@ static void tcx_draw_cursor32(TCXState *s1, uint8_t *d, } /* - XXX Could be much more optimal: - * detect if line/page/whole screen is in 24 bit mode - * if destination is also BGR, use memcpy - */ + * XXX Could be much more optimal: + * detect if line/page/whole screen is in 24 bit mode + */ static inline void tcx24_draw_line32(TCXState *s1, uint8_t *d, const uint8_t *s, int width, const uint32_t *cplane, const uint32_t *s24) { - DisplaySurface *surface = qemu_console_surface(s1->con); - int x, bgr, r, g, b; + int x, r, g, b; uint8_t val, *p8; uint32_t *p = (uint32_t *)d; uint32_t dval; - bgr = is_surface_bgr(surface); for(x = 0; x < width; x++, s++, s24++) { if (be32_to_cpu(*cplane) & 0x03000000) { /* 24-bit direct, BGR order */ @@ -XXX,XX +XXX,XX @@ static inline void tcx24_draw_line32(TCXState *s1, uint8_t *d, b = *p8++; g = *p8++; r = *p8; - if (bgr) - dval = rgb_to_pixel32bgr(r, g, b); - else - dval = rgb_to_pixel32(r, g, b); + dval = rgb_to_pixel32(r, g, b); } else { /* 8-bit pseudocolor */ val = *s; @@ -XXX,XX +XXX,XX @@ static void tcx_update_display(void *opaque) int y, y_start, dd, ds; uint8_t *d, *s; - if (surface_bits_per_pixel(surface) != 32) { - return; - } + assert(surface_bits_per_pixel(surface) == 32); page = 0; y_start = -1; @@ -XXX,XX +XXX,XX @@ static void tcx24_update_display(void *opaque) uint8_t *d, *s; uint32_t *cptr, *s24; - if (surface_bits_per_pixel(surface) != 32) { - return; - } + assert(surface_bits_per_pixel(surface) == 32); page = 0; y_start = -1; -- 2.20.1 The AN524 has a different SYSCLK frequency from the AN505 and AN521; make the SYSCLK frequency a field in the MPS2TZMachineClass rather than a compile-time constant so we can support the AN524. 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: 20210215115138.20465-2-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass { MachineClass parent; MPS2TZFPGAType fpga_type; uint32_t scc_id; + uint32_t sysclk_frq; /* Main SYSCLK frequency in Hz */ const char *armsse_type; }; @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { OBJECT_DECLARE_TYPE(MPS2TZMachineState, MPS2TZMachineClass, MPS2TZ_MACHINE) -/* Main SYSCLK frequency in Hz */ -#define SYSCLK_FRQ 20000000 /* Slow 32Khz S32KCLK frequency in Hz */ #define S32KCLK_FRQ (32 * 1000) @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_unimp_dev(MPS2TZMachineState *mms, static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size) { + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); CMSDKAPBUART *uart = opaque; int i = uart - &mms->uart[0]; int rxirqno = i * 2; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, object_initialize_child(OBJECT(mms), name, uart, TYPE_CMSDK_APB_UART); qdev_prop_set_chr(DEVICE(uart), "chardev", serial_hd(i)); - qdev_prop_set_uint32(DEVICE(uart), "pclk-frq", SYSCLK_FRQ); + qdev_prop_set_uint32(DEVICE(uart), "pclk-frq", mmc->sysclk_frq); sysbus_realize(SYS_BUS_DEVICE(uart), &error_fatal); s = SYS_BUS_DEVICE(uart); sysbus_connect_irq(s, 0, get_sse_irq_in(mms, txirqno)); @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) /* These clocks don't need migration because they are fixed-frequency */ mms->sysclk = clock_new(OBJECT(machine), "SYSCLK"); - clock_set_hz(mms->sysclk, SYSCLK_FRQ); + clock_set_hz(mms->sysclk, mmc->sysclk_frq); mms->s32kclk = clock_new(OBJECT(machine), "S32KCLK"); clock_set_hz(mms->s32kclk, S32KCLK_FRQ); @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mmc->fpga_type = FPGA_AN505; mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"); mmc->scc_id = 0x41045050; + mmc->sysclk_frq = 20 * 1000 * 1000; /* 20MHz */ mmc->armsse_type = TYPE_IOTKIT; } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mmc->fpga_type = FPGA_AN521; mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"); mmc->scc_id = 0x41045210; + mmc->sysclk_frq = 20 * 1000 * 1000; /* 20MHz */ mmc->armsse_type = TYPE_SSE200; } -- 2.20.1 Currently the MPS2 SCC device implements a fixed number of OSCCLK values (3). The variant of this device in the MPS3 AN524 board has 6 OSCCLK values. Switch to using a PROP_ARRAY, which allows board code to specify how large the OSCCLK array should be as well as its values. With a variable-length property array, the SCC no longer specifies default values for the OSCCLKs, so we must set them explicitly in the board code. This defaults are actually incorrect for the an521 and an505; we will correct this bug in a following patch. This is a migration compatibility break for all the mps boards. 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: 20210215115138.20465-3-peter.maydell@linaro.org --- include/hw/misc/mps2-scc.h | 7 +++---- hw/arm/mps2-tz.c | 5 +++++ hw/arm/mps2.c | 5 +++++ hw/misc/mps2-scc.c | 24 +++++++++++++----------- 4 files changed, 26 insertions(+), 15 deletions(-) diff --git a/include/hw/misc/mps2-scc.h b/include/hw/misc/mps2-scc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/mps2-scc.h +++ b/include/hw/misc/mps2-scc.h @@ -XXX,XX +XXX,XX @@ #define TYPE_MPS2_SCC "mps2-scc" OBJECT_DECLARE_SIMPLE_TYPE(MPS2SCC, MPS2_SCC) -#define NUM_OSCCLK 3 - struct MPS2SCC { /*< private >*/ SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct MPS2SCC { uint32_t dll; uint32_t aid; uint32_t id; - uint32_t oscclk[NUM_OSCCLK]; - uint32_t oscclk_reset[NUM_OSCCLK]; + uint32_t num_oscclk; + uint32_t *oscclk; + uint32_t *oscclk_reset; }; #endif diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, qdev_prop_set_uint32(sccdev, "scc-cfg4", 0x2); qdev_prop_set_uint32(sccdev, "scc-aid", 0x00200008); qdev_prop_set_uint32(sccdev, "scc-id", mmc->scc_id); + /* This will need to be per-FPGA image eventually */ + qdev_prop_set_uint32(sccdev, "len-oscclk", 3); + qdev_prop_set_uint32(sccdev, "oscclk[0]", 50000000); + qdev_prop_set_uint32(sccdev, "oscclk[1]", 24576000); + qdev_prop_set_uint32(sccdev, "oscclk[2]", 25000000); sysbus_realize(SYS_BUS_DEVICE(scc), &error_fatal); return sysbus_mmio_get_region(SYS_BUS_DEVICE(sccdev), 0); } diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2.c +++ b/hw/arm/mps2.c @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) qdev_prop_set_uint32(sccdev, "scc-cfg4", 0x2); qdev_prop_set_uint32(sccdev, "scc-aid", 0x00200008); qdev_prop_set_uint32(sccdev, "scc-id", mmc->scc_id); + /* All these FPGA images have the same OSCCLK configuration */ + qdev_prop_set_uint32(sccdev, "len-oscclk", 3); + qdev_prop_set_uint32(sccdev, "oscclk[0]", 50000000); + qdev_prop_set_uint32(sccdev, "oscclk[1]", 24576000); + qdev_prop_set_uint32(sccdev, "oscclk[2]", 25000000); sysbus_realize(SYS_BUS_DEVICE(&mms->scc), &error_fatal); sysbus_mmio_map(SYS_BUS_DEVICE(sccdev), 0, 0x4002f000); object_initialize_child(OBJECT(mms), "fpgaio", diff --git a/hw/misc/mps2-scc.c b/hw/misc/mps2-scc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mps2-scc.c +++ b/hw/misc/mps2-scc.c @@ -XXX,XX +XXX,XX @@ static bool scc_cfg_write(MPS2SCC *s, unsigned function, { trace_mps2_scc_cfg_write(function, device, value); - if (function != 1 || device >= NUM_OSCCLK) { + if (function != 1 || device >= s->num_oscclk) { qemu_log_mask(LOG_GUEST_ERROR, "MPS2 SCC config write: bad function %d device %d\n", function, device); @@ -XXX,XX +XXX,XX @@ static bool scc_cfg_write(MPS2SCC *s, unsigned function, static bool scc_cfg_read(MPS2SCC *s, unsigned function, unsigned device, uint32_t *value) { - if (function != 1 || device >= NUM_OSCCLK) { + if (function != 1 || device >= s->num_oscclk) { qemu_log_mask(LOG_GUEST_ERROR, "MPS2 SCC config read: bad function %d device %d\n", function, device); @@ -XXX,XX +XXX,XX @@ static void mps2_scc_reset(DeviceState *dev) s->cfgctrl = 0x100000; s->cfgstat = 0; s->dll = 0xffff0001; - for (i = 0; i < NUM_OSCCLK; i++) { + for (i = 0; i < s->num_oscclk; i++) { s->oscclk[i] = s->oscclk_reset[i]; } for (i = 0; i < ARRAY_SIZE(s->led); i++) { @@ -XXX,XX +XXX,XX @@ static void mps2_scc_realize(DeviceState *dev, Error **errp) LED_COLOR_GREEN, name); g_free(name); } + + s->oscclk = g_new0(uint32_t, s->num_oscclk); } static const VMStateDescription mps2_scc_vmstate = { .name = "mps2-scc", - .version_id = 1, - .minimum_version_id = 1, + .version_id = 2, + .minimum_version_id = 2, .fields = (VMStateField[]) { VMSTATE_UINT32(cfg0, MPS2SCC), VMSTATE_UINT32(cfg1, MPS2SCC), @@ -XXX,XX +XXX,XX @@ static const VMStateDescription mps2_scc_vmstate = { VMSTATE_UINT32(cfgctrl, MPS2SCC), VMSTATE_UINT32(cfgstat, MPS2SCC), VMSTATE_UINT32(dll, MPS2SCC), - VMSTATE_UINT32_ARRAY(oscclk, MPS2SCC, NUM_OSCCLK), + VMSTATE_VARRAY_UINT32(oscclk, MPS2SCC, num_oscclk, + 0, vmstate_info_uint32, uint32_t), VMSTATE_END_OF_LIST() } }; @@ -XXX,XX +XXX,XX @@ static Property mps2_scc_properties[] = { DEFINE_PROP_UINT32("scc-cfg4", MPS2SCC, cfg4, 0), DEFINE_PROP_UINT32("scc-aid", MPS2SCC, aid, 0), DEFINE_PROP_UINT32("scc-id", MPS2SCC, id, 0), - /* These are the initial settings for the source clocks on the board. + /* + * These are the initial settings for the source clocks on the board. * In hardware they can be configured via a config file read by the * motherboard configuration controller to suit the FPGA image. - * These default values are used by most of the standard FPGA images. */ - DEFINE_PROP_UINT32("oscclk0", MPS2SCC, oscclk_reset[0], 50000000), - DEFINE_PROP_UINT32("oscclk1", MPS2SCC, oscclk_reset[1], 24576000), - DEFINE_PROP_UINT32("oscclk2", MPS2SCC, oscclk_reset[2], 25000000), + DEFINE_PROP_ARRAY("oscclk", MPS2SCC, num_oscclk, oscclk_reset, + qdev_prop_uint32, uint32_t), DEFINE_PROP_END_OF_LIST(), }; -- 2.20.1 We were previously using the default OSCCLK settings, which are correct for the older MPS2 boards (mps2-an385, mps2-an386, mps2-an500, mps2-an511), but wrong for the mps2-an505 and mps2-511 implemented in mps2-tz.c. Now we're setting the values explicitly we can fix them to be correct. 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: 20210215115138.20465-4-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, qdev_prop_set_uint32(sccdev, "scc-id", mmc->scc_id); /* This will need to be per-FPGA image eventually */ qdev_prop_set_uint32(sccdev, "len-oscclk", 3); - qdev_prop_set_uint32(sccdev, "oscclk[0]", 50000000); - qdev_prop_set_uint32(sccdev, "oscclk[1]", 24576000); + qdev_prop_set_uint32(sccdev, "oscclk[0]", 40000000); + qdev_prop_set_uint32(sccdev, "oscclk[1]", 24580000); qdev_prop_set_uint32(sccdev, "oscclk[2]", 25000000); sysbus_realize(SYS_BUS_DEVICE(scc), &error_fatal); return sysbus_mmio_get_region(SYS_BUS_DEVICE(sccdev), 0); -- 2.20.1 The AN505 and AN511 happen to share the same OSCCLK values, but the AN524 will have a different set (and more of them), so split the settings out to be per-board. 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: 20210215115138.20465-5-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 23 ++++++++++++++++++----- 1 file changed, 18 insertions(+), 5 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass { MPS2TZFPGAType fpga_type; uint32_t scc_id; uint32_t sysclk_frq; /* Main SYSCLK frequency in Hz */ + uint32_t len_oscclk; + const uint32_t *oscclk; const char *armsse_type; }; @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_TYPE(MPS2TZMachineState, MPS2TZMachineClass, MPS2TZ_MACHINE) /* Slow 32Khz S32KCLK frequency in Hz */ #define S32KCLK_FRQ (32 * 1000) +static const uint32_t an505_oscclk[] = { + 40000000, + 24580000, + 25000000, +}; + /* Create an alias of an entire original MemoryRegion @orig * located at @base in the memory map. */ @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, MPS2SCC *scc = opaque; DeviceState *sccdev; MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + uint32_t i; object_initialize_child(OBJECT(mms), "scc", scc, TYPE_MPS2_SCC); sccdev = DEVICE(scc); qdev_prop_set_uint32(sccdev, "scc-cfg4", 0x2); qdev_prop_set_uint32(sccdev, "scc-aid", 0x00200008); qdev_prop_set_uint32(sccdev, "scc-id", mmc->scc_id); - /* This will need to be per-FPGA image eventually */ - qdev_prop_set_uint32(sccdev, "len-oscclk", 3); - qdev_prop_set_uint32(sccdev, "oscclk[0]", 40000000); - qdev_prop_set_uint32(sccdev, "oscclk[1]", 24580000); - qdev_prop_set_uint32(sccdev, "oscclk[2]", 25000000); + qdev_prop_set_uint32(sccdev, "len-oscclk", mmc->len_oscclk); + for (i = 0; i < mmc->len_oscclk; i++) { + g_autofree char *propname = g_strdup_printf("oscclk[%u]", i); + qdev_prop_set_uint32(sccdev, propname, mmc->oscclk[i]); + } sysbus_realize(SYS_BUS_DEVICE(scc), &error_fatal); return sysbus_mmio_get_region(SYS_BUS_DEVICE(sccdev), 0); } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"); mmc->scc_id = 0x41045050; mmc->sysclk_frq = 20 * 1000 * 1000; /* 20MHz */ + mmc->oscclk = an505_oscclk; + mmc->len_oscclk = ARRAY_SIZE(an505_oscclk); mmc->armsse_type = TYPE_IOTKIT; } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"); mmc->scc_id = 0x41045210; mmc->sysclk_frq = 20 * 1000 * 1000; /* 20MHz */ + mmc->oscclk = an505_oscclk; /* AN521 is the same as AN505 here */ + mmc->len_oscclk = ARRAY_SIZE(an505_oscclk); mmc->armsse_type = TYPE_SSE200; } -- 2.20.1 The MPS2 board has 2 LEDs, but the MPS3 board has 10 LEDs. The FPGAIO device is similar on both sets of boards, but the LED0 register has correspondingly more bits that have an effect. Add a device property for number of LEDs. 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: 20210215115138.20465-6-peter.maydell@linaro.org --- include/hw/misc/mps2-fpgaio.h | 5 ++++- hw/misc/mps2-fpgaio.c | 31 +++++++++++++++++++++++-------- 2 files changed, 27 insertions(+), 9 deletions(-) diff --git a/include/hw/misc/mps2-fpgaio.h b/include/hw/misc/mps2-fpgaio.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/mps2-fpgaio.h +++ b/include/hw/misc/mps2-fpgaio.h @@ -XXX,XX +XXX,XX @@ #define TYPE_MPS2_FPGAIO "mps2-fpgaio" OBJECT_DECLARE_SIMPLE_TYPE(MPS2FPGAIO, MPS2_FPGAIO) +#define MPS2FPGAIO_MAX_LEDS 32 + struct MPS2FPGAIO { /*< private >*/ SysBusDevice parent_obj; /*< public >*/ MemoryRegion iomem; - LEDState *led[2]; + LEDState *led[MPS2FPGAIO_MAX_LEDS]; + uint32_t num_leds; uint32_t led0; uint32_t prescale; diff --git a/hw/misc/mps2-fpgaio.c b/hw/misc/mps2-fpgaio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mps2-fpgaio.c +++ b/hw/misc/mps2-fpgaio.c @@ -XXX,XX +XXX,XX @@ static void mps2_fpgaio_write(void *opaque, hwaddr offset, uint64_t value, switch (offset) { case A_LED0: - s->led0 = value & 0x3; - led_set_state(s->led[0], value & 0x01); - led_set_state(s->led[1], value & 0x02); + if (s->num_leds != 0) { + uint32_t i; + + s->led0 = value & MAKE_64BIT_MASK(0, s->num_leds); + for (i = 0; i < s->num_leds; i++) { + led_set_state(s->led[i], value & (1 << i)); + } + } break; case A_PRESCALE: resync_counter(s); @@ -XXX,XX +XXX,XX @@ static void mps2_fpgaio_reset(DeviceState *dev) s->pscntr = 0; s->pscntr_sync_ticks = now; - for (size_t i = 0; i < ARRAY_SIZE(s->led); i++) { + for (size_t i = 0; i < s->num_leds; i++) { device_cold_reset(DEVICE(s->led[i])); } } @@ -XXX,XX +XXX,XX @@ static void mps2_fpgaio_init(Object *obj) static void mps2_fpgaio_realize(DeviceState *dev, Error **errp) { MPS2FPGAIO *s = MPS2_FPGAIO(dev); + uint32_t i; - s->led[0] = led_create_simple(OBJECT(dev), GPIO_POLARITY_ACTIVE_HIGH, - LED_COLOR_GREEN, "USERLED0"); - s->led[1] = led_create_simple(OBJECT(dev), GPIO_POLARITY_ACTIVE_HIGH, - LED_COLOR_GREEN, "USERLED1"); + if (s->num_leds > MPS2FPGAIO_MAX_LEDS) { + error_setg(errp, "num-leds cannot be greater than %d", + MPS2FPGAIO_MAX_LEDS); + return; + } + + for (i = 0; i < s->num_leds; i++) { + g_autofree char *ledname = g_strdup_printf("USERLED%d", i); + s->led[i] = led_create_simple(OBJECT(dev), GPIO_POLARITY_ACTIVE_HIGH, + LED_COLOR_GREEN, ledname); + } } static bool mps2_fpgaio_counters_needed(void *opaque) @@ -XXX,XX +XXX,XX @@ static const VMStateDescription mps2_fpgaio_vmstate = { static Property mps2_fpgaio_properties[] = { /* Frequency of the prescale counter */ DEFINE_PROP_UINT32("prescale-clk", MPS2FPGAIO, prescale_clk, 20000000), + /* Number of LEDs controlled by LED0 register */ + DEFINE_PROP_UINT32("num-leds", MPS2FPGAIO, num_leds, 2), DEFINE_PROP_END_OF_LIST(), }; -- 2.20.1 MPS3 boards have an extra SWITCH register in the FPGAIO block which reports the value of some switches. Implement this, governed by a property the board code can use to specify whether whether it exists. 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: 20210215115138.20465-7-peter.maydell@linaro.org --- include/hw/misc/mps2-fpgaio.h | 1 + hw/misc/mps2-fpgaio.c | 10 ++++++++++ 2 files changed, 11 insertions(+) diff --git a/include/hw/misc/mps2-fpgaio.h b/include/hw/misc/mps2-fpgaio.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/mps2-fpgaio.h +++ b/include/hw/misc/mps2-fpgaio.h @@ -XXX,XX +XXX,XX @@ struct MPS2FPGAIO { MemoryRegion iomem; LEDState *led[MPS2FPGAIO_MAX_LEDS]; uint32_t num_leds; + bool has_switches; uint32_t led0; uint32_t prescale; diff --git a/hw/misc/mps2-fpgaio.c b/hw/misc/mps2-fpgaio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mps2-fpgaio.c +++ b/hw/misc/mps2-fpgaio.c @@ -XXX,XX +XXX,XX @@ REG32(CLK100HZ, 0x14) REG32(COUNTER, 0x18) REG32(PRESCALE, 0x1c) REG32(PSCNTR, 0x20) +REG32(SWITCH, 0x28) REG32(MISC, 0x4c) static uint32_t counter_from_tickoff(int64_t now, int64_t tick_offset, int frq) @@ -XXX,XX +XXX,XX @@ static uint64_t mps2_fpgaio_read(void *opaque, hwaddr offset, unsigned size) resync_counter(s); r = s->pscntr; break; + case A_SWITCH: + if (!s->has_switches) { + goto bad_offset; + } + /* User-togglable board switches. We don't model that, so report 0. */ + r = 0; + break; default: + bad_offset: qemu_log_mask(LOG_GUEST_ERROR, "MPS2 FPGAIO read: bad offset %x\n", (int) offset); r = 0; @@ -XXX,XX +XXX,XX @@ static Property mps2_fpgaio_properties[] = { DEFINE_PROP_UINT32("prescale-clk", MPS2FPGAIO, prescale_clk, 20000000), /* Number of LEDs controlled by LED0 register */ DEFINE_PROP_UINT32("num-leds", MPS2FPGAIO, num_leds, 2), + DEFINE_PROP_BOOL("has-switches", MPS2FPGAIO, has_switches, false), DEFINE_PROP_END_OF_LIST(), }; -- 2.20.1 Set the FPGAIO num-leds and have-switches properties explicitly per-board, rather than relying on the defaults. The AN505 and AN521 both have the same settings as the default values, but the AN524 will be different. 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: 20210215115138.20465-8-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass { uint32_t sysclk_frq; /* Main SYSCLK frequency in Hz */ uint32_t len_oscclk; const uint32_t *oscclk; + uint32_t fpgaio_num_leds; /* Number of LEDs in FPGAIO LED0 register */ + bool fpgaio_has_switches; /* Does FPGAIO have SWITCH register? */ const char *armsse_type; }; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_fpgaio(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size) { MPS2FPGAIO *fpgaio = opaque; + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); object_initialize_child(OBJECT(mms), "fpgaio", fpgaio, TYPE_MPS2_FPGAIO); + qdev_prop_set_uint32(DEVICE(fpgaio), "num-leds", mmc->fpgaio_num_leds); + qdev_prop_set_bit(DEVICE(fpgaio), "has-switches", mmc->fpgaio_has_switches); sysbus_realize(SYS_BUS_DEVICE(fpgaio), &error_fatal); return sysbus_mmio_get_region(SYS_BUS_DEVICE(fpgaio), 0); } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mmc->sysclk_frq = 20 * 1000 * 1000; /* 20MHz */ mmc->oscclk = an505_oscclk; mmc->len_oscclk = ARRAY_SIZE(an505_oscclk); + mmc->fpgaio_num_leds = 2; + mmc->fpgaio_has_switches = false; mmc->armsse_type = TYPE_IOTKIT; } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mmc->sysclk_frq = 20 * 1000 * 1000; /* 20MHz */ mmc->oscclk = an505_oscclk; /* AN521 is the same as AN505 here */ mmc->len_oscclk = ARRAY_SIZE(an505_oscclk); + mmc->fpgaio_num_leds = 2; + mmc->fpgaio_has_switches = false; mmc->armsse_type = TYPE_SSE200; } -- 2.20.1 In the mps2-tz board code, we handle devices whose interrupt lines must be wired to all CPUs by creating IRQ splitter devices for the AN521, because it has 2 CPUs, but wiring the device IRQ directly to the SSE/IoTKit input for the AN505, which has only 1 CPU. We can avoid making an explicit check on the board type constant by instead creating and using the IRQ splitters for any board with more than 1 CPU. This avoids having to add extra cases to the conditionals every time we add new boards. 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: 20210215115138.20465-9-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void make_ram_alias(MemoryRegion *mr, const char *name, static qemu_irq get_sse_irq_in(MPS2TZMachineState *mms, int irqno) { /* Return a qemu_irq which will signal IRQ n to all CPUs in the SSE. */ - MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + MachineClass *mc = MACHINE_GET_CLASS(mms); assert(irqno < MPS2TZ_NUMIRQ); - switch (mmc->fpga_type) { - case FPGA_AN505: - return qdev_get_gpio_in_named(DEVICE(&mms->iotkit), "EXP_IRQ", irqno); - case FPGA_AN521: + if (mc->max_cpus > 1) { return qdev_get_gpio_in(DEVICE(&mms->cpu_irq_splitter[irqno]), 0); - default: - g_assert_not_reached(); + } else { + return qdev_get_gpio_in_named(DEVICE(&mms->iotkit), "EXP_IRQ", irqno); } } @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) sysbus_realize(SYS_BUS_DEVICE(&mms->iotkit), &error_fatal); /* - * The AN521 needs us to create splitters to feed the IRQ inputs - * for each CPU in the SSE-200 from each device in the board. + * If this board has more than one CPU, then we need to create splitters + * to feed the IRQ inputs for each CPU in the SSE from each device in the + * board. If there is only one CPU, we can just wire the device IRQ + * directly to the SSE's IRQ input. */ - if (mmc->fpga_type == FPGA_AN521) { + if (mc->max_cpus > 1) { for (i = 0; i < MPS2TZ_NUMIRQ; i++) { char *name = g_strdup_printf("mps2-irq-splitter%d", i); SplitIRQ *splitter = &mms->cpu_irq_splitter[i]; -- 2.20.1 The AN524 has more interrupt lines than the AN505 and AN521; make numirq board-specific rather than a compile-time constant. Since the difference is small (92 on the current boards and 95 on the new one) we don't dynamically allocate the cpu_irq_splitter[] array but leave it as a fixed length array whose size is the maximum needed for any of the boards. 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: 20210215115138.20465-10-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-clock.h" #include "qom/object.h" -#define MPS2TZ_NUMIRQ 92 +#define MPS2TZ_NUMIRQ_MAX 92 typedef enum MPS2TZFPGAType { FPGA_AN505, @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass { const uint32_t *oscclk; uint32_t fpgaio_num_leds; /* Number of LEDs in FPGAIO LED0 register */ bool fpgaio_has_switches; /* Does FPGAIO have SWITCH register? */ + int numirq; /* Number of external interrupts */ const char *armsse_type; }; @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { SplitIRQ sec_resp_splitter; qemu_or_irq uart_irq_orgate; DeviceState *lan9118; - SplitIRQ cpu_irq_splitter[MPS2TZ_NUMIRQ]; + SplitIRQ cpu_irq_splitter[MPS2TZ_NUMIRQ_MAX]; Clock *sysclk; Clock *s32kclk; }; @@ -XXX,XX +XXX,XX @@ static qemu_irq get_sse_irq_in(MPS2TZMachineState *mms, int irqno) { /* Return a qemu_irq which will signal IRQ n to all CPUs in the SSE. */ MachineClass *mc = MACHINE_GET_CLASS(mms); + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); - assert(irqno < MPS2TZ_NUMIRQ); + assert(irqno < mmc->numirq); if (mc->max_cpus > 1) { return qdev_get_gpio_in(DEVICE(&mms->cpu_irq_splitter[irqno]), 0); @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) iotkitdev = DEVICE(&mms->iotkit); object_property_set_link(OBJECT(&mms->iotkit), "memory", OBJECT(system_memory), &error_abort); - qdev_prop_set_uint32(iotkitdev, "EXP_NUMIRQ", MPS2TZ_NUMIRQ); + qdev_prop_set_uint32(iotkitdev, "EXP_NUMIRQ", mmc->numirq); qdev_connect_clock_in(iotkitdev, "MAINCLK", mms->sysclk); qdev_connect_clock_in(iotkitdev, "S32KCLK", mms->s32kclk); sysbus_realize(SYS_BUS_DEVICE(&mms->iotkit), &error_fatal); @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) * board. If there is only one CPU, we can just wire the device IRQ * directly to the SSE's IRQ input. */ + assert(mmc->numirq <= MPS2TZ_NUMIRQ_MAX); if (mc->max_cpus > 1) { - for (i = 0; i < MPS2TZ_NUMIRQ; i++) { + for (i = 0; i < mmc->numirq; i++) { char *name = g_strdup_printf("mps2-irq-splitter%d", i); SplitIRQ *splitter = &mms->cpu_irq_splitter[i]; @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mmc->len_oscclk = ARRAY_SIZE(an505_oscclk); mmc->fpgaio_num_leds = 2; mmc->fpgaio_has_switches = false; + mmc->numirq = 92; mmc->armsse_type = TYPE_IOTKIT; } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mmc->len_oscclk = ARRAY_SIZE(an505_oscclk); mmc->fpgaio_num_leds = 2; mmc->fpgaio_has_switches = false; + mmc->numirq = 92; mmc->armsse_type = TYPE_SSE200; } -- 2.20.1 The AN524 version of the SCC interface has different behaviour for some of the CFG registers; implement it. Each board in this family can have minor differences in the meaning of the CFG registers, so rather than trying to specify all the possible semantics via individual device properties, we make the behaviour conditional on the part-number field of the SCC_ID register which the board code already passes us. For the AN524, the differences are: * CFG3 is reserved rather than being board switches * CFG5 is a new register ("ACLK Frequency in Hz") * CFG6 is a new register ("Clock divider for BRAM") We implement both of the new registers as reads-as-written. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-11-peter.maydell@linaro.org --- include/hw/misc/mps2-scc.h | 3 ++ hw/misc/mps2-scc.c | 71 ++++++++++++++++++++++++++++++++++++-- 2 files changed, 72 insertions(+), 2 deletions(-) diff --git a/include/hw/misc/mps2-scc.h b/include/hw/misc/mps2-scc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/mps2-scc.h +++ b/include/hw/misc/mps2-scc.h @@ -XXX,XX +XXX,XX @@ struct MPS2SCC { uint32_t cfg0; uint32_t cfg1; + uint32_t cfg2; uint32_t cfg4; + uint32_t cfg5; + uint32_t cfg6; uint32_t cfgdata_rtn; uint32_t cfgdata_out; uint32_t cfgctrl; diff --git a/hw/misc/mps2-scc.c b/hw/misc/mps2-scc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mps2-scc.c +++ b/hw/misc/mps2-scc.c @@ -XXX,XX +XXX,XX @@ REG32(CFG0, 0) REG32(CFG1, 4) +REG32(CFG2, 8) REG32(CFG3, 0xc) REG32(CFG4, 0x10) +REG32(CFG5, 0x14) +REG32(CFG6, 0x18) REG32(CFGDATA_RTN, 0xa0) REG32(CFGDATA_OUT, 0xa4) REG32(CFGCTRL, 0xa8) @@ -XXX,XX +XXX,XX @@ REG32(DLL, 0x100) REG32(AID, 0xFF8) REG32(ID, 0xFFC) +static int scc_partno(MPS2SCC *s) +{ + /* Return the partno field of the SCC_ID (0x524, 0x511, etc) */ + return extract32(s->id, 4, 8); +} + /* Handle a write via the SYS_CFG channel to the specified function/device. * Return false on error (reported to guest via SYS_CFGCTRL ERROR bit). */ @@ -XXX,XX +XXX,XX @@ static uint64_t mps2_scc_read(void *opaque, hwaddr offset, unsigned size) case A_CFG1: r = s->cfg1; break; + case A_CFG2: + if (scc_partno(s) != 0x524) { + /* CFG2 reserved on other boards */ + goto bad_offset; + } + r = s->cfg2; + break; case A_CFG3: + if (scc_partno(s) == 0x524) { + /* CFG3 reserved on AN524 */ + goto bad_offset; + } /* These are user-settable DIP switches on the board. We don't * model that, so just return zeroes. */ @@ -XXX,XX +XXX,XX @@ static uint64_t mps2_scc_read(void *opaque, hwaddr offset, unsigned size) case A_CFG4: r = s->cfg4; break; + case A_CFG5: + if (scc_partno(s) != 0x524) { + /* CFG5 reserved on other boards */ + goto bad_offset; + } + r = s->cfg5; + break; + case A_CFG6: + if (scc_partno(s) != 0x524) { + /* CFG6 reserved on other boards */ + goto bad_offset; + } + r = s->cfg6; + break; case A_CFGDATA_RTN: r = s->cfgdata_rtn; break; @@ -XXX,XX +XXX,XX @@ static uint64_t mps2_scc_read(void *opaque, hwaddr offset, unsigned size) r = s->id; break; default: + bad_offset: qemu_log_mask(LOG_GUEST_ERROR, "MPS2 SCC read: bad offset %x\n", (int) offset); r = 0; @@ -XXX,XX +XXX,XX @@ static void mps2_scc_write(void *opaque, hwaddr offset, uint64_t value, led_set_state(s->led[i], extract32(value, i, 1)); } break; + case A_CFG2: + if (scc_partno(s) != 0x524) { + /* CFG2 reserved on other boards */ + goto bad_offset; + } + /* AN524: QSPI Select signal */ + s->cfg2 = value; + break; + case A_CFG5: + if (scc_partno(s) != 0x524) { + /* CFG5 reserved on other boards */ + goto bad_offset; + } + /* AN524: ACLK frequency in Hz */ + s->cfg5 = value; + break; + case A_CFG6: + if (scc_partno(s) != 0x524) { + /* CFG6 reserved on other boards */ + goto bad_offset; + } + /* AN524: Clock divider for BRAM */ + s->cfg6 = value; + break; case A_CFGDATA_OUT: s->cfgdata_out = value; break; @@ -XXX,XX +XXX,XX @@ static void mps2_scc_write(void *opaque, hwaddr offset, uint64_t value, s->dll = deposit32(s->dll, 24, 8, extract32(value, 24, 8)); break; default: + bad_offset: qemu_log_mask(LOG_GUEST_ERROR, "MPS2 SCC write: bad offset 0x%x\n", (int) offset); break; @@ -XXX,XX +XXX,XX @@ static void mps2_scc_reset(DeviceState *dev) trace_mps2_scc_reset(); s->cfg0 = 0; s->cfg1 = 0; + s->cfg2 = 0; + s->cfg5 = 0; + s->cfg6 = 0; s->cfgdata_rtn = 0; s->cfgdata_out = 0; s->cfgctrl = 0x100000; @@ -XXX,XX +XXX,XX @@ static void mps2_scc_realize(DeviceState *dev, Error **errp) static const VMStateDescription mps2_scc_vmstate = { .name = "mps2-scc", - .version_id = 2, - .minimum_version_id = 2, + .version_id = 3, + .minimum_version_id = 3, .fields = (VMStateField[]) { VMSTATE_UINT32(cfg0, MPS2SCC), VMSTATE_UINT32(cfg1, MPS2SCC), + VMSTATE_UINT32(cfg2, MPS2SCC), + /* cfg3, cfg4 are read-only so need not be migrated */ + VMSTATE_UINT32(cfg5, MPS2SCC), + VMSTATE_UINT32(cfg6, MPS2SCC), VMSTATE_UINT32(cfgdata_rtn, MPS2SCC), VMSTATE_UINT32(cfgdata_out, MPS2SCC), VMSTATE_UINT32(cfgctrl, MPS2SCC), -- 2.20.1 On the MPS2 boards, the first 32 interrupt lines are entirely internal to the SSE; interrupt lines for devices outside the SSE start at 32. In the application notes that document each FPGA image, the interrupt wiring is documented from the point of view of the CPU, so '0' is the first of the SSE's interrupts and the devices in the FPGA image itself are '32' and up: so the UART 0 Receive interrupt is 32, the SPI #0 interrupt is 51, and so on. Within our implementation, because the external interrupts must be connected to the EXP_IRQ[0...n] lines of the SSE object, we made the get_sse_irq_in() function take an irqno whose values start at 0 for the first FPGA device interrupt. In this numbering scheme the UART 0 Receive interrupt is 0, the SPI #0 interrupt is 19, and so on. The result of these two different numbering schemes has been that half of the devices were wired up to the wrong IRQs: the UART IRQs are wired up correctly, but the DMA and SPI devices were passing start-at-32 values to get_sse_irq_in() and so being mis-connected. Fix the bug by making get_sse_irq_in() take values specified with the same scheme that the hardware manuals use, to avoid confusion. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-12-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void make_ram_alias(MemoryRegion *mr, const char *name, static qemu_irq get_sse_irq_in(MPS2TZMachineState *mms, int irqno) { - /* Return a qemu_irq which will signal IRQ n to all CPUs in the SSE. */ + /* + * Return a qemu_irq which will signal IRQ n to all CPUs in the + * SSE. The irqno should be as the CPU sees it, so the first + * external-to-the-SSE interrupt is 32. + */ MachineClass *mc = MACHINE_GET_CLASS(mms); MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); - assert(irqno < mmc->numirq); + assert(irqno >= 32 && irqno < (mmc->numirq + 32)); + + /* + * Convert from "CPU irq number" (as listed in the FPGA image + * documentation) to the SSE external-interrupt number. + */ + irqno -= 32; if (mc->max_cpus > 1) { return qdev_get_gpio_in(DEVICE(&mms->cpu_irq_splitter[irqno]), 0); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); CMSDKAPBUART *uart = opaque; int i = uart - &mms->uart[0]; - int rxirqno = i * 2; - int txirqno = i * 2 + 1; - int combirqno = i + 10; + int rxirqno = i * 2 + 32; + int txirqno = i * 2 + 33; + int combirqno = i + 42; SysBusDevice *s; DeviceState *orgate_dev = DEVICE(&mms->uart_irq_orgate); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, s = SYS_BUS_DEVICE(mms->lan9118); sysbus_realize_and_unref(s, &error_fatal); - sysbus_connect_irq(s, 0, get_sse_irq_in(mms, 16)); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, 48)); return sysbus_mmio_get_region(s, 0); } @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) &error_fatal); qdev_realize(DEVICE(&mms->uart_irq_orgate), NULL, &error_fatal); qdev_connect_gpio_out(DEVICE(&mms->uart_irq_orgate), 0, - get_sse_irq_in(mms, 15)); + get_sse_irq_in(mms, 47)); /* Most of the devices in the FPGA are behind Peripheral Protection * Controllers. The required order for initializing things is: -- 2.20.1 The mps2-tz code uses PPCPortInfo data structures to define what devices are present and how they are wired up. Currently we use these to specify device types and addresses, but hard-code the interrupt line wiring in each make_* helper function. This works for the two boards we have at the moment, but the AN524 has some devices with different interrupt assignments. This commit adds the framework to allow PPCPortInfo structures to specify interrupt numbers. We add an array of interrupt numbers to the PPCPortInfo struct, and pass it through to the make_* helpers. The following commit will change the make_* helpers over to using the framework. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-13-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 36 ++++++++++++++++++++++++------------ 1 file changed, 24 insertions(+), 12 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static qemu_irq get_sse_irq_in(MPS2TZMachineState *mms, int irqno) * needs to be plugged into the downstream end of the PPC port. */ typedef MemoryRegion *MakeDevFn(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size); + const char *name, hwaddr size, + const int *irqs); typedef struct PPCPortInfo { const char *name; @@ -XXX,XX +XXX,XX @@ typedef struct PPCPortInfo { void *opaque; hwaddr addr; hwaddr size; + int irqs[3]; /* currently no device needs more IRQ lines than this */ } PPCPortInfo; typedef struct PPCInfo { @@ -XXX,XX +XXX,XX @@ typedef struct PPCInfo { } PPCInfo; static MemoryRegion *make_unimp_dev(MPS2TZMachineState *mms, - void *opaque, - const char *name, hwaddr size) + void *opaque, + const char *name, hwaddr size, + const int *irqs) { /* Initialize, configure and realize a TYPE_UNIMPLEMENTED_DEVICE, * and return a pointer to its MemoryRegion. @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_unimp_dev(MPS2TZMachineState *mms, } static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); CMSDKAPBUART *uart = opaque; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, } static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { MPS2SCC *scc = opaque; DeviceState *sccdev; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_scc(MPS2TZMachineState *mms, void *opaque, } static MemoryRegion *make_fpgaio(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { MPS2FPGAIO *fpgaio = opaque; MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_fpgaio(MPS2TZMachineState *mms, void *opaque, } static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { SysBusDevice *s; NICInfo *nd = &nd_table[0]; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, } static MemoryRegion *make_mpc(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { TZMPC *mpc = opaque; int i = mpc - &mms->ssram_mpc[0]; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_mpc(MPS2TZMachineState *mms, void *opaque, } static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { PL080State *dma = opaque; int i = dma - &mms->dma[0]; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, } static MemoryRegion *make_spi(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { /* * The AN505 has five PL022 SPI controllers. @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_spi(MPS2TZMachineState *mms, void *opaque, } static MemoryRegion *make_i2c(MPS2TZMachineState *mms, void *opaque, - const char *name, hwaddr size) + const char *name, hwaddr size, + const int *irqs) { ArmSbconI2CState *i2c = opaque; SysBusDevice *s; @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) continue; } - mr = pinfo->devfn(mms, pinfo->opaque, pinfo->name, pinfo->size); + mr = pinfo->devfn(mms, pinfo->opaque, pinfo->name, pinfo->size, + pinfo->irqs); portname = g_strdup_printf("port[%d]", port); object_property_set_link(OBJECT(ppc), portname, OBJECT(mr), &error_fatal); -- 2.20.1 Move the specification of the IRQ information for the uart, ethernet, dma and spi devices to the data structures. (The other devices handled by the PPCPortInfo structures don't have any interrupt lines we need to wire up.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-14-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 52 +++++++++++++++++++++++------------------------- 1 file changed, 25 insertions(+), 27 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, const int *irqs) { + /* The irq[] array is tx, rx, combined, in that order */ MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); CMSDKAPBUART *uart = opaque; int i = uart - &mms->uart[0]; - int rxirqno = i * 2 + 32; - int txirqno = i * 2 + 33; - int combirqno = i + 42; SysBusDevice *s; DeviceState *orgate_dev = DEVICE(&mms->uart_irq_orgate); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_uart(MPS2TZMachineState *mms, void *opaque, qdev_prop_set_uint32(DEVICE(uart), "pclk-frq", mmc->sysclk_frq); sysbus_realize(SYS_BUS_DEVICE(uart), &error_fatal); s = SYS_BUS_DEVICE(uart); - sysbus_connect_irq(s, 0, get_sse_irq_in(mms, txirqno)); - sysbus_connect_irq(s, 1, get_sse_irq_in(mms, rxirqno)); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqs[0])); + sysbus_connect_irq(s, 1, get_sse_irq_in(mms, irqs[1])); sysbus_connect_irq(s, 2, qdev_get_gpio_in(orgate_dev, i * 2)); sysbus_connect_irq(s, 3, qdev_get_gpio_in(orgate_dev, i * 2 + 1)); - sysbus_connect_irq(s, 4, get_sse_irq_in(mms, combirqno)); + sysbus_connect_irq(s, 4, get_sse_irq_in(mms, irqs[2])); return sysbus_mmio_get_region(SYS_BUS_DEVICE(uart), 0); } @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, s = SYS_BUS_DEVICE(mms->lan9118); sysbus_realize_and_unref(s, &error_fatal); - sysbus_connect_irq(s, 0, get_sse_irq_in(mms, 48)); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqs[0])); return sysbus_mmio_get_region(s, 0); } @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, const int *irqs) { + /* The irq[] array is DMACINTR, DMACINTERR, DMACINTTC, in that order */ PL080State *dma = opaque; int i = dma - &mms->dma[0]; SysBusDevice *s; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_dma(MPS2TZMachineState *mms, void *opaque, s = SYS_BUS_DEVICE(dma); /* Wire up DMACINTR, DMACINTERR, DMACINTTC */ - sysbus_connect_irq(s, 0, get_sse_irq_in(mms, 58 + i * 3)); - sysbus_connect_irq(s, 1, get_sse_irq_in(mms, 56 + i * 3)); - sysbus_connect_irq(s, 2, get_sse_irq_in(mms, 57 + i * 3)); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqs[0])); + sysbus_connect_irq(s, 1, get_sse_irq_in(mms, irqs[1])); + sysbus_connect_irq(s, 2, get_sse_irq_in(mms, irqs[2])); g_free(mscname); return sysbus_mmio_get_region(s, 0); @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_spi(MPS2TZMachineState *mms, void *opaque, * lines are set via the "MISC" register in the MPS2 FPGAIO device. */ PL022State *spi = opaque; - int i = spi - &mms->spi[0]; SysBusDevice *s; object_initialize_child(OBJECT(mms), name, spi, TYPE_PL022); sysbus_realize(SYS_BUS_DEVICE(spi), &error_fatal); s = SYS_BUS_DEVICE(spi); - sysbus_connect_irq(s, 0, get_sse_irq_in(mms, 51 + i)); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqs[0])); return sysbus_mmio_get_region(s, 0); } @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) }, { .name = "apb_ppcexp1", .ports = { - { "spi0", make_spi, &mms->spi[0], 0x40205000, 0x1000 }, - { "spi1", make_spi, &mms->spi[1], 0x40206000, 0x1000 }, - { "spi2", make_spi, &mms->spi[2], 0x40209000, 0x1000 }, - { "spi3", make_spi, &mms->spi[3], 0x4020a000, 0x1000 }, - { "spi4", make_spi, &mms->spi[4], 0x4020b000, 0x1000 }, - { "uart0", make_uart, &mms->uart[0], 0x40200000, 0x1000 }, - { "uart1", make_uart, &mms->uart[1], 0x40201000, 0x1000 }, - { "uart2", make_uart, &mms->uart[2], 0x40202000, 0x1000 }, - { "uart3", make_uart, &mms->uart[3], 0x40203000, 0x1000 }, - { "uart4", make_uart, &mms->uart[4], 0x40204000, 0x1000 }, + { "spi0", make_spi, &mms->spi[0], 0x40205000, 0x1000, { 51 } }, + { "spi1", make_spi, &mms->spi[1], 0x40206000, 0x1000, { 52 } }, + { "spi2", make_spi, &mms->spi[2], 0x40209000, 0x1000, { 53 } }, + { "spi3", make_spi, &mms->spi[3], 0x4020a000, 0x1000, { 54 } }, + { "spi4", make_spi, &mms->spi[4], 0x4020b000, 0x1000, { 55 } }, + { "uart0", make_uart, &mms->uart[0], 0x40200000, 0x1000, { 32, 33, 42 } }, + { "uart1", make_uart, &mms->uart[1], 0x40201000, 0x1000, { 34, 35, 43 } }, + { "uart2", make_uart, &mms->uart[2], 0x40202000, 0x1000, { 36, 37, 44 } }, + { "uart3", make_uart, &mms->uart[3], 0x40203000, 0x1000, { 38, 39, 45 } }, + { "uart4", make_uart, &mms->uart[4], 0x40204000, 0x1000, { 40, 41, 46 } }, { "i2c0", make_i2c, &mms->i2c[0], 0x40207000, 0x1000 }, { "i2c1", make_i2c, &mms->i2c[1], 0x40208000, 0x1000 }, { "i2c2", make_i2c, &mms->i2c[2], 0x4020c000, 0x1000 }, @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) { "gpio1", make_unimp_dev, &mms->gpio[1], 0x40101000, 0x1000 }, { "gpio2", make_unimp_dev, &mms->gpio[2], 0x40102000, 0x1000 }, { "gpio3", make_unimp_dev, &mms->gpio[3], 0x40103000, 0x1000 }, - { "eth", make_eth_dev, NULL, 0x42000000, 0x100000 }, + { "eth", make_eth_dev, NULL, 0x42000000, 0x100000, { 48 } }, }, }, { .name = "ahb_ppcexp1", .ports = { - { "dma0", make_dma, &mms->dma[0], 0x40110000, 0x1000 }, - { "dma1", make_dma, &mms->dma[1], 0x40111000, 0x1000 }, - { "dma2", make_dma, &mms->dma[2], 0x40112000, 0x1000 }, - { "dma3", make_dma, &mms->dma[3], 0x40113000, 0x1000 }, + { "dma0", make_dma, &mms->dma[0], 0x40110000, 0x1000, { 58, 56, 57 } }, + { "dma1", make_dma, &mms->dma[1], 0x40111000, 0x1000, { 61, 59, 60 } }, + { "dma2", make_dma, &mms->dma[2], 0x40112000, 0x1000, { 64, 62, 63 } }, + { "dma3", make_dma, &mms->dma[3], 0x40113000, 0x1000, { 67, 65, 66 } }, }, }, }; -- 2.20.1 We create an OR gate to wire together the overflow IRQs for all the UARTs on the board; this has to have twice the number of inputs as there are UARTs, since each UART feeds it a TX overflow and an RX overflow interrupt line. Replace the hardcoded '10' with a calculation based on the size of the uart[] array in the MPS2TZMachineState. (We rely on OR gate inputs that are never wired up or asserted being treated as always-zero.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-15-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 11 ++++++++--- 1 file changed, 8 insertions(+), 3 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) */ memory_region_add_subregion(system_memory, 0x80000000, machine->ram); - /* The overflow IRQs for all UARTs are ORed together. + /* + * The overflow IRQs for all UARTs are ORed together. * Tx, Rx and "combined" IRQs are sent to the NVIC separately. - * Create the OR gate for this. + * Create the OR gate for this: it has one input for the TX overflow + * and one for the RX overflow for each UART we might have. + * (If the board has fewer than the maximum possible number of UARTs + * those inputs are never wired up and are treated as always-zero.) */ object_initialize_child(OBJECT(mms), "uart-irq-orgate", &mms->uart_irq_orgate, TYPE_OR_IRQ); - object_property_set_int(OBJECT(&mms->uart_irq_orgate), "num-lines", 10, + object_property_set_int(OBJECT(&mms->uart_irq_orgate), "num-lines", + 2 * ARRAY_SIZE(mms->uart), &error_fatal); qdev_realize(DEVICE(&mms->uart_irq_orgate), NULL, &error_fatal); qdev_connect_gpio_out(DEVICE(&mms->uart_irq_orgate), 0, -- 2.20.1 The AN505 and AN521 have the same device layout, but the AN524 is somewhat different. Allow for more than one PPCInfo array, which can be selected based on the board type. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-16-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) MemoryRegion *system_memory = get_system_memory(); DeviceState *iotkitdev; DeviceState *dev_splitter; + const PPCInfo *ppcs; + int num_ppcs; int i; if (strcmp(machine->cpu_type, mc->default_cpu_type) != 0) { @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) * + wire up the PPC's control lines to the IoTKit object */ - const PPCInfo ppcs[] = { { + const PPCInfo an505_ppcs[] = { { .name = "apb_ppcexp0", .ports = { { "ssram-0", make_mpc, &mms->ssram_mpc[0], 0x58007000, 0x1000 }, @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) }, }; - for (i = 0; i < ARRAY_SIZE(ppcs); i++) { + switch (mmc->fpga_type) { + case FPGA_AN505: + case FPGA_AN521: + ppcs = an505_ppcs; + num_ppcs = ARRAY_SIZE(an505_ppcs); + break; + default: + g_assert_not_reached(); + } + + for (i = 0; i < num_ppcs; i++) { const PPCInfo *ppcinfo = &ppcs[i]; TZPPC *ppc = &mms->ppc[i]; DeviceState *ppcdev; -- 2.20.1 The AN505 and AN521 have the same layout of RAM; the AN524 does not. Replace the current hard-coding of where the RAM is and which parts of it are behind which MPCs with a data-driven approach. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-17-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 175 +++++++++++++++++++++++++++++++++++++---------- 1 file changed, 138 insertions(+), 37 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ #include "qom/object.h" #define MPS2TZ_NUMIRQ_MAX 92 +#define MPS2TZ_RAM_MAX 4 typedef enum MPS2TZFPGAType { FPGA_AN505, FPGA_AN521, } MPS2TZFPGAType; +/* + * Define the layout of RAM in a board, including which parts are + * behind which MPCs. + * mrindex specifies the index into mms->ram[] to use for the backing RAM; + * -1 means "use the system RAM". + */ +typedef struct RAMInfo { + const char *name; + uint32_t base; + uint32_t size; + int mpc; /* MPC number, -1 for "not behind an MPC" */ + int mrindex; + int flags; +} RAMInfo; + +/* + * Flag values: + * IS_ALIAS: this RAM area is an alias to the upstream end of the + * MPC specified by its .mpc value + */ +#define IS_ALIAS 1 + struct MPS2TZMachineClass { MachineClass parent; MPS2TZFPGAType fpga_type; @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineClass { uint32_t fpgaio_num_leds; /* Number of LEDs in FPGAIO LED0 register */ bool fpgaio_has_switches; /* Does FPGAIO have SWITCH register? */ int numirq; /* Number of external interrupts */ + const RAMInfo *raminfo; const char *armsse_type; }; @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { MachineState parent; ARMSSE iotkit; - MemoryRegion ssram[3]; - MemoryRegion ssram1_m; + MemoryRegion ram[MPS2TZ_RAM_MAX]; MPS2SCC scc; MPS2FPGAIO fpgaio; TZPPC ppc[5]; - TZMPC ssram_mpc[3]; + TZMPC mpc[3]; PL022State spi[5]; ArmSbconI2CState i2c[4]; UnimplementedDeviceState i2s_audio; @@ -XXX,XX +XXX,XX @@ static const uint32_t an505_oscclk[] = { 25000000, }; +static const RAMInfo an505_raminfo[] = { { + .name = "ssram-0", + .base = 0x00000000, + .size = 0x00400000, + .mpc = 0, + .mrindex = 0, + }, { + .name = "ssram-1", + .base = 0x28000000, + .size = 0x00200000, + .mpc = 1, + .mrindex = 1, + }, { + .name = "ssram-2", + .base = 0x28200000, + .size = 0x00200000, + .mpc = 2, + .mrindex = 2, + }, { + .name = "ssram-0-alias", + .base = 0x00400000, + .size = 0x00400000, + .mpc = 0, + .mrindex = 3, + .flags = IS_ALIAS, + }, { + /* Use the largest bit of contiguous RAM as our "system memory" */ + .name = "mps.ram", + .base = 0x80000000, + .size = 16 * MiB, + .mpc = -1, + .mrindex = -1, + }, { + .name = NULL, + }, +}; + +static const RAMInfo *find_raminfo_for_mpc(MPS2TZMachineState *mms, int mpc) +{ + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + const RAMInfo *p; + + for (p = mmc->raminfo; p->name; p++) { + if (p->mpc == mpc && !(p->flags & IS_ALIAS)) { + return p; + } + } + /* if raminfo array doesn't have an entry for each MPC this is a bug */ + g_assert_not_reached(); +} + +static MemoryRegion *mr_for_raminfo(MPS2TZMachineState *mms, + const RAMInfo *raminfo) +{ + /* Return an initialized MemoryRegion for the RAMInfo. */ + MemoryRegion *ram; + + if (raminfo->mrindex < 0) { + /* Means this RAMInfo is for QEMU's "system memory" */ + MachineState *machine = MACHINE(mms); + return machine->ram; + } + + assert(raminfo->mrindex < MPS2TZ_RAM_MAX); + ram = &mms->ram[raminfo->mrindex]; + + memory_region_init_ram(ram, NULL, raminfo->name, + raminfo->size, &error_fatal); + return ram; +} + /* Create an alias of an entire original MemoryRegion @orig * located at @base in the memory map. */ @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_mpc(MPS2TZMachineState *mms, void *opaque, const int *irqs) { TZMPC *mpc = opaque; - int i = mpc - &mms->ssram_mpc[0]; - MemoryRegion *ssram = &mms->ssram[i]; + int i = mpc - &mms->mpc[0]; MemoryRegion *upstream; - char *mpcname = g_strdup_printf("%s-mpc", name); - static uint32_t ramsize[] = { 0x00400000, 0x00200000, 0x00200000 }; - static uint32_t rambase[] = { 0x00000000, 0x28000000, 0x28200000 }; + const RAMInfo *raminfo = find_raminfo_for_mpc(mms, i); + MemoryRegion *ram = mr_for_raminfo(mms, raminfo); - memory_region_init_ram(ssram, NULL, name, ramsize[i], &error_fatal); - - object_initialize_child(OBJECT(mms), mpcname, mpc, TYPE_TZ_MPC); - object_property_set_link(OBJECT(mpc), "downstream", OBJECT(ssram), + object_initialize_child(OBJECT(mms), name, mpc, TYPE_TZ_MPC); + object_property_set_link(OBJECT(mpc), "downstream", OBJECT(ram), &error_fatal); sysbus_realize(SYS_BUS_DEVICE(mpc), &error_fatal); /* Map the upstream end of the MPC into system memory */ upstream = sysbus_mmio_get_region(SYS_BUS_DEVICE(mpc), 1); - memory_region_add_subregion(get_system_memory(), rambase[i], upstream); + memory_region_add_subregion(get_system_memory(), raminfo->base, upstream); /* and connect its interrupt to the IoTKit */ qdev_connect_gpio_out_named(DEVICE(mpc), "irq", 0, qdev_get_gpio_in_named(DEVICE(&mms->iotkit), "mpcexp_status", i)); - /* The first SSRAM is a special case as it has an alias; accesses to - * the alias region at 0x00400000 must also go to the MPC upstream. - */ - if (i == 0) { - make_ram_alias(&mms->ssram1_m, "mps.ssram1_m", upstream, 0x00400000); - } - - g_free(mpcname); /* Return the register interface MR for our caller to map behind the PPC */ return sysbus_mmio_get_region(SYS_BUS_DEVICE(mpc), 0); } @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_i2c(MPS2TZMachineState *mms, void *opaque, return sysbus_mmio_get_region(s, 0); } +static void create_non_mpc_ram(MPS2TZMachineState *mms) +{ + /* + * Handle the RAMs which are either not behind MPCs or which are + * aliases to another MPC. + */ + const RAMInfo *p; + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + + for (p = mmc->raminfo; p->name; p++) { + if (p->flags & IS_ALIAS) { + SysBusDevice *mpc_sbd = SYS_BUS_DEVICE(&mms->mpc[p->mpc]); + MemoryRegion *upstream = sysbus_mmio_get_region(mpc_sbd, 1); + make_ram_alias(&mms->ram[p->mrindex], p->name, upstream, p->base); + } else if (p->mpc == -1) { + /* RAM not behind an MPC */ + MemoryRegion *mr = mr_for_raminfo(mms, p); + memory_region_add_subregion(get_system_memory(), p->base, mr); + } + } +} + static void mps2tz_common_init(MachineState *machine) { MPS2TZMachineState *mms = MPS2TZ_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) qdev_connect_gpio_out_named(iotkitdev, "sec_resp_cfg", 0, qdev_get_gpio_in(dev_splitter, 0)); - /* The IoTKit sets up much of the memory layout, including + /* + * The IoTKit sets up much of the memory layout, including * the aliases between secure and non-secure regions in the - * address space. The FPGA itself contains: - * - * 0x00000000..0x003fffff SSRAM1 - * 0x00400000..0x007fffff alias of SSRAM1 - * 0x28000000..0x283fffff 4MB SSRAM2 + SSRAM3 - * 0x40100000..0x4fffffff AHB Master Expansion 1 interface devices - * 0x80000000..0x80ffffff 16MB PSRAM - */ - - /* The FPGA images have an odd combination of different RAMs, + * address space, and also most of the devices in the system. + * The FPGA itself contains various RAMs and some additional devices. + * The FPGA images have an odd combination of different RAMs, * because in hardware they are different implementations and * connected to different buses, giving varying performance/size * tradeoffs. For QEMU they're all just RAM, though. We arbitrarily - * call the 16MB our "system memory", as it's the largest lump. + * call the largest lump our "system memory". */ - memory_region_add_subregion(system_memory, 0x80000000, machine->ram); /* * The overflow IRQs for all UARTs are ORed together. @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) const PPCInfo an505_ppcs[] = { { .name = "apb_ppcexp0", .ports = { - { "ssram-0", make_mpc, &mms->ssram_mpc[0], 0x58007000, 0x1000 }, - { "ssram-1", make_mpc, &mms->ssram_mpc[1], 0x58008000, 0x1000 }, - { "ssram-2", make_mpc, &mms->ssram_mpc[2], 0x58009000, 0x1000 }, + { "ssram-0-mpc", make_mpc, &mms->mpc[0], 0x58007000, 0x1000 }, + { "ssram-1-mpc", make_mpc, &mms->mpc[1], 0x58008000, 0x1000 }, + { "ssram-2-mpc", make_mpc, &mms->mpc[2], 0x58009000, 0x1000 }, }, }, { .name = "apb_ppcexp1", @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) create_unimplemented_device("FPGA NS PC", 0x48007000, 0x1000); + create_non_mpc_ram(mms); + armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, 0x400000); } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mmc->fpgaio_num_leds = 2; mmc->fpgaio_has_switches = false; mmc->numirq = 92; + mmc->raminfo = an505_raminfo; mmc->armsse_type = TYPE_IOTKIT; } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mmc->fpgaio_num_leds = 2; mmc->fpgaio_has_switches = false; mmc->numirq = 92; + mmc->raminfo = an505_raminfo; /* AN521 is the same as AN505 here */ mmc->armsse_type = TYPE_SSE200; } -- 2.20.1 Instead of hardcoding the MachineClass default_ram_size and default_ram_id fields, set them on class creation by finding the entry in the RAMInfo array which is marked as being the QEMU system RAM. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-18-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 24 ++++++++++++++++++++++-- 1 file changed, 22 insertions(+), 2 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void mps2tz_class_init(ObjectClass *oc, void *data) mc->init = mps2tz_common_init; iic->check = mps2_tz_idau_check; - mc->default_ram_size = 16 * MiB; - mc->default_ram_id = "mps.ram"; +} + +static void mps2tz_set_default_ram_info(MPS2TZMachineClass *mmc) +{ + /* + * Set mc->default_ram_size and default_ram_id from the + * information in mmc->raminfo. + */ + MachineClass *mc = MACHINE_CLASS(mmc); + const RAMInfo *p; + + for (p = mmc->raminfo; p->name; p++) { + if (p->mrindex < 0) { + /* Found the entry for "system memory" */ + mc->default_ram_size = p->size; + mc->default_ram_id = p->name; + return; + } + } + g_assert_not_reached(); } static void mps2tz_an505_class_init(ObjectClass *oc, void *data) @@ -XXX,XX +XXX,XX @@ static void mps2tz_an505_class_init(ObjectClass *oc, void *data) mmc->numirq = 92; mmc->raminfo = an505_raminfo; mmc->armsse_type = TYPE_IOTKIT; + mps2tz_set_default_ram_info(mmc); } static void mps2tz_an521_class_init(ObjectClass *oc, void *data) @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mmc->numirq = 92; mmc->raminfo = an505_raminfo; /* AN521 is the same as AN505 here */ mmc->armsse_type = TYPE_SSE200; + mps2tz_set_default_ram_info(mmc); } static const TypeInfo mps2tz_info = { -- 2.20.1 The AN505 and AN521 don't have any read-only memory, but the AN524 does; add a flag to ROMInfo to mark a region as ROM. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-19-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ typedef struct RAMInfo { * Flag values: * IS_ALIAS: this RAM area is an alias to the upstream end of the * MPC specified by its .mpc value + * IS_ROM: this RAM area is read-only */ #define IS_ALIAS 1 +#define IS_ROM 2 struct MPS2TZMachineClass { MachineClass parent; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *mr_for_raminfo(MPS2TZMachineState *mms, if (raminfo->mrindex < 0) { /* Means this RAMInfo is for QEMU's "system memory" */ MachineState *machine = MACHINE(mms); + assert(!(raminfo->flags & IS_ROM)); return machine->ram; } @@ -XXX,XX +XXX,XX @@ static MemoryRegion *mr_for_raminfo(MPS2TZMachineState *mms, memory_region_init_ram(ram, NULL, raminfo->name, raminfo->size, &error_fatal); + if (raminfo->flags & IS_ROM) { + memory_region_set_readonly(ram, true); + } return ram; } -- 2.20.1 The armv7m_load_kernel() function takes a mem_size argument which it expects to be the size of the memory region at guest address 0. (It uses this argument only as a limit on how large a raw image file it can load at address zero). Instead of hardcoding this value, find the RAMInfo corresponding to the 0 address and extract its size. 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: 20210215115138.20465-20-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void create_non_mpc_ram(MPS2TZMachineState *mms) } } +static uint32_t boot_ram_size(MPS2TZMachineState *mms) +{ + /* Return the size of the RAM block at guest address zero */ + const RAMInfo *p; + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); + + for (p = mmc->raminfo; p->name; p++) { + if (p->base == 0) { + return p->size; + } + } + g_assert_not_reached(); +} + static void mps2tz_common_init(MachineState *machine) { MPS2TZMachineState *mms = MPS2TZ_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) create_non_mpc_ram(mms); - armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, 0x400000); + armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, + boot_ram_size(mms)); } static void mps2_tz_idau_check(IDAUInterface *ii, uint32_t address, -- 2.20.1 Add support for the mps3-an524 board; this is an SSE-200 based FPGA image, like the existing mps2-an521. It has a usefully larger amount of RAM, and a PL031 RTC, as well as some more minor differences. In real hardware this image runs on a newer generation of the FPGA board, the MPS3 rather than the older MPS2. Architecturally the two boards are similar, so we implement the MPS3 boards in the mps2-tz.c file as variations of the existing MPS2 boards. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-21-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 139 +++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 135 insertions(+), 4 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ * This source file covers the following FPGA images, for TrustZone cores: * "mps2-an505" -- Cortex-M33 as documented in ARM Application Note AN505 * "mps2-an521" -- Dual Cortex-M33 as documented in Application Note AN521 + * "mps2-an524" -- Dual Cortex-M33 as documented in Application Note AN524 * * Links to the TRM for the board itself and to the various Application * Notes which document the FPGA images can be found here: @@ -XXX,XX +XXX,XX @@ * http://infocenter.arm.com/help/topic/com.arm.doc.dai0505b/index.html * Application Note AN521: * http://infocenter.arm.com/help/topic/com.arm.doc.dai0521c/index.html + * Application Note AN524: + * https://developer.arm.com/documentation/dai0524/latest/ * * The AN505 defers to the Cortex-M33 processor ARMv8M IoT Kit FVP User Guide * (ARM ECM0601256) for the details of some of the device layout: * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html - * Similarly, the AN521 uses the SSE-200, and the SSE-200 TRM defines + * Similarly, the AN521 and AN524 use the SSE-200, and the SSE-200 TRM defines * most of the device layout: * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf * @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-clock.h" #include "qom/object.h" -#define MPS2TZ_NUMIRQ_MAX 92 +#define MPS2TZ_NUMIRQ_MAX 95 #define MPS2TZ_RAM_MAX 4 typedef enum MPS2TZFPGAType { FPGA_AN505, FPGA_AN521, + FPGA_AN524, } MPS2TZFPGAType; /* @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { TZPPC ppc[5]; TZMPC mpc[3]; PL022State spi[5]; - ArmSbconI2CState i2c[4]; + ArmSbconI2CState i2c[5]; UnimplementedDeviceState i2s_audio; UnimplementedDeviceState gpio[4]; UnimplementedDeviceState gfx; + UnimplementedDeviceState cldc; + UnimplementedDeviceState rtc; PL080State dma[4]; TZMSC msc[4]; - CMSDKAPBUART uart[5]; + CMSDKAPBUART uart[6]; SplitIRQ sec_resp_splitter; qemu_or_irq uart_irq_orgate; DeviceState *lan9118; @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { #define TYPE_MPS2TZ_MACHINE "mps2tz" #define TYPE_MPS2TZ_AN505_MACHINE MACHINE_TYPE_NAME("mps2-an505") #define TYPE_MPS2TZ_AN521_MACHINE MACHINE_TYPE_NAME("mps2-an521") +#define TYPE_MPS3TZ_AN524_MACHINE MACHINE_TYPE_NAME("mps3-an524") OBJECT_DECLARE_TYPE(MPS2TZMachineState, MPS2TZMachineClass, MPS2TZ_MACHINE) @@ -XXX,XX +XXX,XX @@ static const uint32_t an505_oscclk[] = { 25000000, }; +static const uint32_t an524_oscclk[] = { + 24000000, + 32000000, + 50000000, + 50000000, + 24576000, + 23750000, +}; + static const RAMInfo an505_raminfo[] = { { .name = "ssram-0", .base = 0x00000000, @@ -XXX,XX +XXX,XX @@ static const RAMInfo an505_raminfo[] = { { }, }; +static const RAMInfo an524_raminfo[] = { { + .name = "bram", + .base = 0x00000000, + .size = 512 * KiB, + .mpc = 0, + .mrindex = 0, + }, { + .name = "sram", + .base = 0x20000000, + .size = 32 * 4 * KiB, + .mpc = 1, + .mrindex = 1, + }, { + /* We don't model QSPI flash yet; for now expose it as simple ROM */ + .name = "QSPI", + .base = 0x28000000, + .size = 8 * MiB, + .mpc = 1, + .mrindex = 2, + .flags = IS_ROM, + }, { + .name = "DDR", + .base = 0x60000000, + .size = 2 * GiB, + .mpc = 2, + .mrindex = -1, + }, { + .name = NULL, + }, +}; + static const RAMInfo *find_raminfo_for_mpc(MPS2TZMachineState *mms, int mpc) { MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_GET_CLASS(mms); @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) }, }; + const PPCInfo an524_ppcs[] = { { + .name = "apb_ppcexp0", + .ports = { + { "bram-mpc", make_mpc, &mms->mpc[0], 0x58007000, 0x1000 }, + { "qspi-mpc", make_mpc, &mms->mpc[1], 0x58008000, 0x1000 }, + { "ddr-mpc", make_mpc, &mms->mpc[2], 0x58009000, 0x1000 }, + }, + }, { + .name = "apb_ppcexp1", + .ports = { + { "i2c0", make_i2c, &mms->i2c[0], 0x41200000, 0x1000 }, + { "i2c1", make_i2c, &mms->i2c[1], 0x41201000, 0x1000 }, + { "spi0", make_spi, &mms->spi[0], 0x41202000, 0x1000, { 52 } }, + { "spi1", make_spi, &mms->spi[1], 0x41203000, 0x1000, { 53 } }, + { "spi2", make_spi, &mms->spi[2], 0x41204000, 0x1000, { 54 } }, + { "i2c2", make_i2c, &mms->i2c[2], 0x41205000, 0x1000 }, + { "i2c3", make_i2c, &mms->i2c[3], 0x41206000, 0x1000 }, + { /* port 7 reserved */ }, + { "i2c4", make_i2c, &mms->i2c[4], 0x41208000, 0x1000 }, + }, + }, { + .name = "apb_ppcexp2", + .ports = { + { "scc", make_scc, &mms->scc, 0x41300000, 0x1000 }, + { "i2s-audio", make_unimp_dev, &mms->i2s_audio, + 0x41301000, 0x1000 }, + { "fpgaio", make_fpgaio, &mms->fpgaio, 0x41302000, 0x1000 }, + { "uart0", make_uart, &mms->uart[0], 0x41303000, 0x1000, { 32, 33, 42 } }, + { "uart1", make_uart, &mms->uart[1], 0x41304000, 0x1000, { 34, 35, 43 } }, + { "uart2", make_uart, &mms->uart[2], 0x41305000, 0x1000, { 36, 37, 44 } }, + { "uart3", make_uart, &mms->uart[3], 0x41306000, 0x1000, { 38, 39, 45 } }, + { "uart4", make_uart, &mms->uart[4], 0x41307000, 0x1000, { 40, 41, 46 } }, + { "uart5", make_uart, &mms->uart[5], 0x41308000, 0x1000, { 124, 125, 126 } }, + + { /* port 9 reserved */ }, + { "clcd", make_unimp_dev, &mms->cldc, 0x4130a000, 0x1000 }, + { "rtc", make_unimp_dev, &mms->rtc, 0x4130b000, 0x1000 }, + }, + }, { + .name = "ahb_ppcexp0", + .ports = { + { "gpio0", make_unimp_dev, &mms->gpio[0], 0x41100000, 0x1000 }, + { "gpio1", make_unimp_dev, &mms->gpio[1], 0x41101000, 0x1000 }, + { "gpio2", make_unimp_dev, &mms->gpio[2], 0x41102000, 0x1000 }, + { "gpio3", make_unimp_dev, &mms->gpio[3], 0x41103000, 0x1000 }, + { "eth", make_eth_dev, NULL, 0x41400000, 0x100000, { 48 } }, + }, + }, + }; + switch (mmc->fpga_type) { case FPGA_AN505: case FPGA_AN521: ppcs = an505_ppcs; num_ppcs = ARRAY_SIZE(an505_ppcs); break; + case FPGA_AN524: + ppcs = an524_ppcs; + num_ppcs = ARRAY_SIZE(an524_ppcs); + break; default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static void mps2tz_an521_class_init(ObjectClass *oc, void *data) mps2tz_set_default_ram_info(mmc); } +static void mps3tz_an524_class_init(ObjectClass *oc, void *data) +{ + MachineClass *mc = MACHINE_CLASS(oc); + MPS2TZMachineClass *mmc = MPS2TZ_MACHINE_CLASS(oc); + + mc->desc = "ARM MPS3 with AN524 FPGA image for dual Cortex-M33"; + mc->default_cpus = 2; + mc->min_cpus = mc->default_cpus; + mc->max_cpus = mc->default_cpus; + mmc->fpga_type = FPGA_AN524; + mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-m33"); + mmc->scc_id = 0x41045240; + mmc->sysclk_frq = 32 * 1000 * 1000; /* 32MHz */ + mmc->oscclk = an524_oscclk; + mmc->len_oscclk = ARRAY_SIZE(an524_oscclk); + mmc->fpgaio_num_leds = 10; + mmc->fpgaio_has_switches = true; + mmc->numirq = 95; + mmc->raminfo = an524_raminfo; + mmc->armsse_type = TYPE_SSE200; + mps2tz_set_default_ram_info(mmc); +} + static const TypeInfo mps2tz_info = { .name = TYPE_MPS2TZ_MACHINE, .parent = TYPE_MACHINE, @@ -XXX,XX +XXX,XX @@ static const TypeInfo mps2tz_an521_info = { .class_init = mps2tz_an521_class_init, }; +static const TypeInfo mps3tz_an524_info = { + .name = TYPE_MPS3TZ_AN524_MACHINE, + .parent = TYPE_MPS2TZ_MACHINE, + .class_init = mps3tz_an524_class_init, +}; + static void mps2tz_machine_init(void) { type_register_static(&mps2tz_info); type_register_static(&mps2tz_an505_info); type_register_static(&mps2tz_an521_info); + type_register_static(&mps3tz_an524_info); } type_init(mps2tz_machine_init); -- 2.20.1 The AN524 has a USB controller (an ISP1763); we don't have a model of it but we should provide a stub "unimplemented-device" for it. This is slightly complicated because the USB controller shares a PPC port with the ethernet controller. Implement a make_* function which provides creates a container MemoryRegion with both the ethernet controller and an unimplemented-device stub for the USB controller. 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: 20210215115138.20465-22-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 48 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 47 insertions(+), 1 deletion(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { ARMSSE iotkit; MemoryRegion ram[MPS2TZ_RAM_MAX]; + MemoryRegion eth_usb_container; + MPS2SCC scc; MPS2FPGAIO fpgaio; TZPPC ppc[5]; @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { UnimplementedDeviceState gfx; UnimplementedDeviceState cldc; UnimplementedDeviceState rtc; + UnimplementedDeviceState usb; PL080State dma[4]; TZMSC msc[4]; CMSDKAPBUART uart[6]; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_eth_dev(MPS2TZMachineState *mms, void *opaque, return sysbus_mmio_get_region(s, 0); } +static MemoryRegion *make_eth_usb(MPS2TZMachineState *mms, void *opaque, + const char *name, hwaddr size, + const int *irqs) +{ + /* + * The AN524 makes the ethernet and USB share a PPC port. + * irqs[] is the ethernet IRQ. + */ + SysBusDevice *s; + NICInfo *nd = &nd_table[0]; + + memory_region_init(&mms->eth_usb_container, OBJECT(mms), + "mps2-tz-eth-usb-container", 0x200000); + + /* + * In hardware this is a LAN9220; the LAN9118 is software compatible + * except that it doesn't support the checksum-offload feature. + */ + qemu_check_nic_model(nd, "lan9118"); + mms->lan9118 = qdev_new(TYPE_LAN9118); + qdev_set_nic_properties(mms->lan9118, nd); + + s = SYS_BUS_DEVICE(mms->lan9118); + sysbus_realize_and_unref(s, &error_fatal); + sysbus_connect_irq(s, 0, get_sse_irq_in(mms, irqs[0])); + + memory_region_add_subregion(&mms->eth_usb_container, + 0, sysbus_mmio_get_region(s, 0)); + + /* The USB OTG controller is an ISP1763; we don't have a model of it. */ + object_initialize_child(OBJECT(mms), "usb-otg", + &mms->usb, TYPE_UNIMPLEMENTED_DEVICE); + qdev_prop_set_string(DEVICE(&mms->usb), "name", "usb-otg"); + qdev_prop_set_uint64(DEVICE(&mms->usb), "size", 0x100000); + s = SYS_BUS_DEVICE(&mms->usb); + sysbus_realize(s, &error_fatal); + + memory_region_add_subregion(&mms->eth_usb_container, + 0x100000, sysbus_mmio_get_region(s, 0)); + + return &mms->eth_usb_container; +} + static MemoryRegion *make_mpc(MPS2TZMachineState *mms, void *opaque, const char *name, hwaddr size, const int *irqs) @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) { "gpio1", make_unimp_dev, &mms->gpio[1], 0x41101000, 0x1000 }, { "gpio2", make_unimp_dev, &mms->gpio[2], 0x41102000, 0x1000 }, { "gpio3", make_unimp_dev, &mms->gpio[3], 0x41103000, 0x1000 }, - { "eth", make_eth_dev, NULL, 0x41400000, 0x100000, { 48 } }, + { "eth-usb", make_eth_usb, NULL, 0x41400000, 0x200000, { 48 } }, }, }, }; -- 2.20.1 The AN524 has a PL031 RTC, which we have a model of; provide it rather than an unimplemented-device stub. 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: 20210215115138.20465-23-peter.maydell@linaro.org --- hw/arm/mps2-tz.c | 22 ++++++++++++++++++++-- 1 file changed, 20 insertions(+), 2 deletions(-) diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ #include "hw/misc/tz-msc.h" #include "hw/arm/armsse.h" #include "hw/dma/pl080.h" +#include "hw/rtc/pl031.h" #include "hw/ssi/pl022.h" #include "hw/i2c/arm_sbcon_i2c.h" #include "hw/net/lan9118.h" @@ -XXX,XX +XXX,XX @@ struct MPS2TZMachineState { UnimplementedDeviceState gpio[4]; UnimplementedDeviceState gfx; UnimplementedDeviceState cldc; - UnimplementedDeviceState rtc; UnimplementedDeviceState usb; + PL031State rtc; PL080State dma[4]; TZMSC msc[4]; CMSDKAPBUART uart[6]; @@ -XXX,XX +XXX,XX @@ static MemoryRegion *make_i2c(MPS2TZMachineState *mms, void *opaque, return sysbus_mmio_get_region(s, 0); } +static MemoryRegion *make_rtc(MPS2TZMachineState *mms, void *opaque, + const char *name, hwaddr size, + const int *irqs) +{ + PL031State *pl031 = opaque; + SysBusDevice *s; + + object_initialize_child(OBJECT(mms), name, pl031, TYPE_PL031); + s = SYS_BUS_DEVICE(pl031); + sysbus_realize(s, &error_fatal); + /* + * The board docs don't give an IRQ number for the PL031, so + * presumably it is not connected. + */ + return sysbus_mmio_get_region(s, 0); +} + static void create_non_mpc_ram(MPS2TZMachineState *mms) { /* @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) { /* port 9 reserved */ }, { "clcd", make_unimp_dev, &mms->cldc, 0x4130a000, 0x1000 }, - { "rtc", make_unimp_dev, &mms->rtc, 0x4130b000, 0x1000 }, + { "rtc", make_rtc, &mms->rtc, 0x4130b000, 0x1000 }, }, }, { .name = "ahb_ppcexp0", -- 2.20.1 Add brief documentation of the new mps3-an524 board. 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: 20210215115138.20465-24-peter.maydell@linaro.org --- docs/system/arm/mps2.rst | 24 ++++++++++++++++++------ 1 file changed, 18 insertions(+), 6 deletions(-) diff --git a/docs/system/arm/mps2.rst b/docs/system/arm/mps2.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/mps2.rst +++ b/docs/system/arm/mps2.rst @@ -XXX,XX +XXX,XX @@ -Arm MPS2 boards (``mps2-an385``, ``mps2-an386``, ``mps2-an500``, ``mps2-an505``, ``mps2-an511``, ``mps2-an521``) -================================================================================================================ +Arm MPS2 and MPS3 boards (``mps2-an385``, ``mps2-an386``, ``mps2-an500``, ``mps2-an505``, ``mps2-an511``, ``mps2-an521``, ``mps3-an524``) +========================================================================================================================================= These board models all use Arm M-profile CPUs. -The Arm MPS2 and MPS2+ dev boards are FPGA based (the 2+ has a bigger -FPGA but is otherwise the same as the 2). Since the CPU itself -and most of the devices are in the FPGA, the details of the board -as seen by the guest depend significantly on the FPGA image. +The Arm MPS2, MPS2+ and MPS3 dev boards are FPGA based (the 2+ has a +bigger FPGA but is otherwise the same as the 2; the 3 has a bigger +FPGA again, can handle 4GB of RAM and has a USB controller and QSPI flash). + +Since the CPU itself and most of the devices are in the FPGA, the +details of the board as seen by the guest depend significantly on the +FPGA image. QEMU models the following FPGA images: @@ -XXX,XX +XXX,XX @@ QEMU models the following FPGA images: Cortex-M3 'DesignStart' as documented in Arm Application Note AN511 ``mps2-an521`` Dual Cortex-M33 as documented in Arm Application Note AN521 +``mps3-an524`` + Dual Cortex-M33 on an MPS3, as documented in Arm Application Note AN524 Differences between QEMU and real hardware: - AN385/AN386 remapping of low 16K of memory to either ZBT SSRAM1 or to block RAM is unimplemented (QEMU always maps this to ZBT SSRAM1, as if zbt_boot_ctrl is always zero) +- AN524 remapping of low memory to either BRAM or to QSPI flash is + unimplemented (QEMU always maps this to BRAM, ignoring the + SCC CFG_REG0 memory-remap bit) - QEMU provides a LAN9118 ethernet rather than LAN9220; the only guest visible difference is that the LAN9118 doesn't support checksum offloading +- QEMU does not model the QSPI flash in MPS3 boards as real QSPI + flash, but only as simple ROM, so attempting to rewrite the flash + from the guest will fail +- QEMU does not model the USB controller in MPS3 boards -- 2.20.1 Update old infocenter.arm.com URLs to the equivalent developer.arm.com ones (the old URLs should redirect, but we might as well avoid the redirection notice, and the new URLs are pleasantly shorter). This commit covers the links to the MPS2 board TRM, the various Application Notes, the IoTKit and SSE-200 documents. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210215115138.20465-25-peter.maydell@linaro.org --- include/hw/arm/armsse.h | 4 ++-- include/hw/misc/armsse-cpuid.h | 2 +- include/hw/misc/armsse-mhu.h | 2 +- include/hw/misc/iotkit-secctl.h | 2 +- include/hw/misc/iotkit-sysctl.h | 2 +- include/hw/misc/iotkit-sysinfo.h | 2 +- include/hw/misc/mps2-fpgaio.h | 2 +- hw/arm/mps2-tz.c | 11 +++++------ hw/misc/armsse-cpuid.c | 2 +- hw/misc/armsse-mhu.c | 2 +- hw/misc/iotkit-sysctl.c | 2 +- hw/misc/iotkit-sysinfo.c | 2 +- hw/misc/mps2-fpgaio.c | 2 +- hw/misc/mps2-scc.c | 2 +- 14 files changed, 19 insertions(+), 20 deletions(-) diff --git a/include/hw/arm/armsse.h b/include/hw/arm/armsse.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/armsse.h +++ b/include/hw/arm/armsse.h @@ -XXX,XX +XXX,XX @@ * hardware, which include the IoT Kit and the SSE-050, SSE-100 and * SSE-200. Currently we model: * - the Arm IoT Kit which is documented in - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * https://developer.arm.com/documentation/ecm0601256/latest * - the SSE-200 which is documented in - * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf + * https://developer.arm.com/documentation/101104/latest/ * * The IoTKit contains: * a Cortex-M33 diff --git a/include/hw/misc/armsse-cpuid.h b/include/hw/misc/armsse-cpuid.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/armsse-cpuid.h +++ b/include/hw/misc/armsse-cpuid.h @@ -XXX,XX +XXX,XX @@ /* * This is a model of the "CPU_IDENTITY" register block which is part of the * Arm SSE-200 and documented in - * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf + * https://developer.arm.com/documentation/101104/latest/ * * QEMU interface: * + QOM property "CPUID": the value to use for the CPUID register diff --git a/include/hw/misc/armsse-mhu.h b/include/hw/misc/armsse-mhu.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/armsse-mhu.h +++ b/include/hw/misc/armsse-mhu.h @@ -XXX,XX +XXX,XX @@ /* * This is a model of the Message Handling Unit (MHU) which is part of the * Arm SSE-200 and documented in - * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf + * https://developer.arm.com/documentation/101104/latest/ * * QEMU interface: * + sysbus MMIO region 0: the system information register bank diff --git a/include/hw/misc/iotkit-secctl.h b/include/hw/misc/iotkit-secctl.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/iotkit-secctl.h +++ b/include/hw/misc/iotkit-secctl.h @@ -XXX,XX +XXX,XX @@ /* This is a model of the security controller which is part of the * Arm IoT Kit and documented in - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * https://developer.arm.com/documentation/ecm0601256/latest * * QEMU interface: * + sysbus MMIO region 0 is the "secure privilege control block" registers diff --git a/include/hw/misc/iotkit-sysctl.h b/include/hw/misc/iotkit-sysctl.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/iotkit-sysctl.h +++ b/include/hw/misc/iotkit-sysctl.h @@ -XXX,XX +XXX,XX @@ /* * This is a model of the "system control element" which is part of the * Arm IoTKit and documented in - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * https://developer.arm.com/documentation/ecm0601256/latest * Specifically, it implements the "system information block" and * "system control register" blocks. * diff --git a/include/hw/misc/iotkit-sysinfo.h b/include/hw/misc/iotkit-sysinfo.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/iotkit-sysinfo.h +++ b/include/hw/misc/iotkit-sysinfo.h @@ -XXX,XX +XXX,XX @@ /* * This is a model of the "system information block" which is part of the * Arm IoTKit and documented in - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * https://developer.arm.com/documentation/ecm0601256/latest * QEMU interface: * + QOM property "SYS_VERSION": value to use for SYS_VERSION register * + QOM property "SYS_CONFIG": value to use for SYS_CONFIG register diff --git a/include/hw/misc/mps2-fpgaio.h b/include/hw/misc/mps2-fpgaio.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/mps2-fpgaio.h +++ b/include/hw/misc/mps2-fpgaio.h @@ -XXX,XX +XXX,XX @@ /* This is a model of the FPGAIO register block in the AN505 * FPGA image for the MPS2 dev board; it is documented in the * application note: - * http://infocenter.arm.com/help/topic/com.arm.doc.dai0505b/index.html + * https://developer.arm.com/documentation/dai0505/latest/ * * QEMU interface: * + sysbus MMIO region 0: the register bank diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ * https://developer.arm.com/products/system-design/development-boards/fpga-prototyping-boards/mps2 * * Board TRM: - * http://infocenter.arm.com/help/topic/com.arm.doc.100112_0200_06_en/versatile_express_cortex_m_prototyping_systems_v2m_mps2_and_v2m_mps2plus_technical_reference_100112_0200_06_en.pdf + * https://developer.arm.com/documentation/100112/latest/ * Application Note AN505: - * http://infocenter.arm.com/help/topic/com.arm.doc.dai0505b/index.html + * https://developer.arm.com/documentation/dai0505/latest/ * Application Note AN521: - * http://infocenter.arm.com/help/topic/com.arm.doc.dai0521c/index.html + * https://developer.arm.com/documentation/dai0521/latest/ * Application Note AN524: * https://developer.arm.com/documentation/dai0524/latest/ * * The AN505 defers to the Cortex-M33 processor ARMv8M IoT Kit FVP User Guide * (ARM ECM0601256) for the details of some of the device layout: - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * https://developer.arm.com/documentation/ecm0601256/latest * Similarly, the AN521 and AN524 use the SSE-200, and the SSE-200 TRM defines * most of the device layout: - * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf - * + * https://developer.arm.com/documentation/101104/latest/ */ #include "qemu/osdep.h" diff --git a/hw/misc/armsse-cpuid.c b/hw/misc/armsse-cpuid.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/armsse-cpuid.c +++ b/hw/misc/armsse-cpuid.c @@ -XXX,XX +XXX,XX @@ /* * This is a model of the "CPU_IDENTITY" register block which is part of the * Arm SSE-200 and documented in - * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf + * https://developer.arm.com/documentation/101104/latest/ * * It consists of one read-only CPUID register (set by QOM property), plus the * usual ID registers. diff --git a/hw/misc/armsse-mhu.c b/hw/misc/armsse-mhu.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/armsse-mhu.c +++ b/hw/misc/armsse-mhu.c @@ -XXX,XX +XXX,XX @@ /* * This is a model of the Message Handling Unit (MHU) which is part of the * Arm SSE-200 and documented in - * http://infocenter.arm.com/help/topic/com.arm.doc.101104_0100_00_en/corelink_sse200_subsystem_for_embedded_technical_reference_manual_101104_0100_00_en.pdf + * https://developer.arm.com/documentation/101104/latest/ */ #include "qemu/osdep.h" diff --git a/hw/misc/iotkit-sysctl.c b/hw/misc/iotkit-sysctl.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/iotkit-sysctl.c +++ b/hw/misc/iotkit-sysctl.c @@ -XXX,XX +XXX,XX @@ /* * This is a model of the "system control element" which is part of the * Arm IoTKit and documented in - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * https://developer.arm.com/documentation/ecm0601256/latest * Specifically, it implements the "system control register" blocks. */ diff --git a/hw/misc/iotkit-sysinfo.c b/hw/misc/iotkit-sysinfo.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/iotkit-sysinfo.c +++ b/hw/misc/iotkit-sysinfo.c @@ -XXX,XX +XXX,XX @@ /* * This is a model of the "system information block" which is part of the * Arm IoTKit and documented in - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.ecm0601256/index.html + * https://developer.arm.com/documentation/ecm0601256/latest * It consists of 2 read-only version/config registers, plus the * usual ID registers. */ diff --git a/hw/misc/mps2-fpgaio.c b/hw/misc/mps2-fpgaio.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mps2-fpgaio.c +++ b/hw/misc/mps2-fpgaio.c @@ -XXX,XX +XXX,XX @@ /* This is a model of the "FPGA system control and I/O" block found * in the AN505 FPGA image for the MPS2 devboard. * It is documented in AN505: - * http://infocenter.arm.com/help/topic/com.arm.doc.dai0505b/index.html + * https://developer.arm.com/documentation/dai0505/latest/ */ #include "qemu/osdep.h" diff --git a/hw/misc/mps2-scc.c b/hw/misc/mps2-scc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/mps2-scc.c +++ b/hw/misc/mps2-scc.c @@ -XXX,XX +XXX,XX @@ * found in the FPGA images of MPS2 development boards. * * Documentation of it can be found in the MPS2 TRM: - * http://infocenter.arm.com/help/index.jsp?topic=/com.arm.doc.100112_0100_03_en/index.html + * https://developer.arm.com/documentation/100112/latest/ * and also in the Application Notes documenting individual FPGA images. */ -- 2.20.1 First set of arm patches for 6.2. I have a lot more in my to-review queue still... -- PMM The following changes since commit d42685765653ec155fdf60910662f8830bdb2cef: Open 6.2 development tree (2021-08-25 10:25:12 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20210825 for you to fetch changes up to 24b1a6aa43615be22c7ee66bd68ec5675f6a6a9a: docs: Document how to use gdb with unix sockets (2021-08-25 10:48:51 +0100) ---------------------------------------------------------------- target-arm queue: * More MVE emulation work * Implement M-profile trapping on division by zero * kvm: use RCU_READ_LOCK_GUARD() in kvm_arch_fixup_msi_route() * hw/char/pl011: add support for sending break * fsl-imx6ul: Instantiate SAI1/2/3 and ASRC as unimplemented devices * hw/dma/pl330: Add memory region to replace default * sbsa-ref: Rename SBSA_GWDT enum value * fsl-imx7: Instantiate SAI1/2/3 as unimplemented devices * docs: Document how to use gdb with unix sockets ---------------------------------------------------------------- Eduardo Habkost (1): sbsa-ref: Rename SBSA_GWDT enum value Guenter Roeck (2): fsl-imx6ul: Instantiate SAI1/2/3 and ASRC as unimplemented devices fsl-imx7: Instantiate SAI1/2/3 as unimplemented devices Hamza Mahfooz (1): target/arm: kvm: use RCU_READ_LOCK_GUARD() in kvm_arch_fixup_msi_route() Jan Luebbe (1): hw/char/pl011: add support for sending break Peter Maydell (37): target/arm: Note that we handle VMOVL as a special case of VSHLL target/arm: Print MVE VPR in CPU dumps target/arm: Fix MVE VSLI by 0 and VSRI by <dt> target/arm: Fix signed VADDV target/arm: Fix mask handling for MVE narrowing operations target/arm: Fix 48-bit saturating shifts target/arm: Fix MVE 48-bit SQRSHRL for small right shifts target/arm: Fix calculation of LTP mask when LR is 0 target/arm: Factor out mve_eci_mask() target/arm: Fix VPT advance when ECI is non-zero target/arm: Fix VLDRB/H/W for predicated elements target/arm: Implement MVE VMULL (polynomial) target/arm: Implement MVE incrementing/decrementing dup insns target/arm: Factor out gen_vpst() target/arm: Implement MVE integer vector comparisons target/arm: Implement MVE integer vector-vs-scalar comparisons target/arm: Implement MVE VPSEL target/arm: Implement MVE VMLAS target/arm: Implement MVE shift-by-scalar target/arm: Move 'x' and 'a' bit definitions into vmlaldav formats target/arm: Implement MVE integer min/max across vector target/arm: Implement MVE VABAV target/arm: Implement MVE narrowing moves target/arm: Rename MVEGenDualAccOpFn to MVEGenLongDualAccOpFn target/arm: Implement MVE VMLADAV and VMLSLDAV target/arm: Implement MVE VMLA target/arm: Implement MVE saturating doubling multiply accumulates target/arm: Implement MVE VQABS, VQNEG target/arm: Implement MVE VMAXA, VMINA target/arm: Implement MVE VMOV to/from 2 general-purpose registers target/arm: Implement MVE VPNOT target/arm: Implement MVE VCTP target/arm: Implement MVE scatter-gather insns target/arm: Implement MVE scatter-gather immediate forms target/arm: Implement MVE interleaving loads/stores target/arm: Re-indent sdiv and udiv helpers target/arm: Implement M-profile trapping on division by zero Sebastian Meyer (1): docs: Document how to use gdb with unix sockets Wen, Jianxian (1): hw/dma/pl330: Add memory region to replace default docs/system/gdb.rst | 26 +- include/hw/arm/fsl-imx7.h | 5 + target/arm/cpu.h | 1 + target/arm/helper-mve.h | 283 ++++++++++ target/arm/helper.h | 4 +- target/arm/translate-a32.h | 2 + target/arm/vec_internal.h | 11 + target/arm/mve.decode | 226 +++++++- target/arm/t32.decode | 1 + hw/arm/exynos4210.c | 3 + hw/arm/fsl-imx6ul.c | 12 + hw/arm/fsl-imx7.c | 7 + hw/arm/sbsa-ref.c | 6 +- hw/arm/xilinx_zynq.c | 3 + hw/char/pl011.c | 6 + hw/dma/pl330.c | 26 +- target/arm/cpu.c | 3 + target/arm/helper.c | 34 +- target/arm/kvm.c | 17 +- target/arm/m_helper.c | 4 + target/arm/mve_helper.c | 1254 ++++++++++++++++++++++++++++++++++++++++++-- target/arm/translate-mve.c | 877 ++++++++++++++++++++++++++++++- target/arm/translate-vfp.c | 2 +- target/arm/translate.c | 37 +- target/arm/vec_helper.c | 14 +- 25 files changed, 2746 insertions(+), 118 deletions(-) Although the architecture doesn't define it as an alias, VMOVL (vector move long) is encoded as a VSHLL with a zero shift. Add a comment in the decode file noting that we handle VMOVL as part of VSHLL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve.decode | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_h VRSHRI_U 111 1 1111 1 . ... ... ... 0 0010 0 1 . 1 ... 0 @2_shr_w # VSHLL T1 encoding; the T2 VSHLL encoding is elsewhere in this file +# Note that VMOVL is encoded as "VSHLL with a zero shift count"; we +# implement it that way rather than special-casing it in the decode. VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_b VSHLL_BS 111 0 1110 1 . 1 .. ... ... 0 1111 0 1 . 0 ... 0 @2_shll_h -- 2.20.1 Include the MVE VPR register value in the CPU dumps produced by arm_cpu_dump_state() if we are printing FPU information. This makes it easier to interpret debug logs when predication is active. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/cpu.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_dump_state(CPUState *cs, FILE *f, int flags) i, v); } qemu_fprintf(f, "FPSCR: %08x\n", vfp_get_fpscr(env)); + if (cpu_isar_feature(aa32_mve, cpu)) { + qemu_fprintf(f, "VPR: %08x\n", env->v7m.vpr); + } } } -- 2.20.1 In the MVE shift-and-insert insns, we special case VSLI by 0 and VSRI by <dt>. VSRI by <dt> means "don't update the destination", which is what we've implemented. However VSLI by 0 is "set destination to the input", so we don't want to use the same special-casing that we do for VSRI by <dt>. Since the generic logic gives the right answer for a shift by 0, just use that. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_S(vrshli_s, DO_VRSHLS) uint16_t mask; \ uint64_t shiftmask; \ unsigned e; \ - if (shift == 0 || shift == ESIZE * 8) { \ + if (shift == ESIZE * 8) { \ /* \ - * Only VSLI can shift by 0; only VSRI can shift by <dt>. \ - * The generic logic would give the right answer for 0 but \ - * fails for <dt>. \ + * Only VSRI can shift by <dt>; it should mean "don't \ + * update the destination". The generic logic can't handle \ + * this because it would try to shift by an out-of-range \ + * amount, so special case it here. \ */ \ goto done; \ } \ -- 2.20.1 A cut-and-paste error meant we handled signed VADDV like unsigned VADDV; fix the type used. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_LDAVH(vrmlsldavhxsw, int32_t, int64_t, true, true) return ra; \ } \ -DO_VADDV(vaddvsb, 1, uint8_t) -DO_VADDV(vaddvsh, 2, uint16_t) -DO_VADDV(vaddvsw, 4, uint32_t) +DO_VADDV(vaddvsb, 1, int8_t) +DO_VADDV(vaddvsh, 2, int16_t) +DO_VADDV(vaddvsw, 4, int32_t) DO_VADDV(vaddvub, 1, uint8_t) DO_VADDV(vaddvuh, 2, uint16_t) DO_VADDV(vaddvuw, 4, uint32_t) -- 2.20.1 In the MVE helpers for the narrowing operations (DO_VSHRN and DO_VSHRN_SAT) we were using the wrong bits of the predicate mask for the 'top' versions of the insn. This is because the loop works over the double-sized input elements and shifts the predicate mask by that many bits each time, but when we write out the half-sized output we must look at the mask bits for whichever half of the element we are writing to. Correct this by shifting the whole mask right by ESIZE bits for the 'top' insns. This allows us also to simplify the saturation bit checking (where we had noticed that we needed to look at a different mask bit for the 'top' insn.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSHLL_ALL(vshllt, true) TYPE *d = vd; \ uint16_t mask = mve_element_mask(env); \ unsigned le; \ + mask >>= ESIZE * TOP; \ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ TYPE r = FN(m[H##LESIZE(le)], shift); \ mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ @@ -XXX,XX +XXX,XX @@ static inline int32_t do_sat_bhs(int64_t val, int64_t min, int64_t max, uint16_t mask = mve_element_mask(env); \ bool qc = false; \ unsigned le; \ + mask >>= ESIZE * TOP; \ for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ bool sat = false; \ TYPE r = FN(m[H##LESIZE(le)], shift, &sat); \ mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ - qc |= sat && (mask & 1 << (TOP * ESIZE)); \ + qc |= sat & mask & 1; \ } \ if (qc) { \ env->vfp.qc[0] = qc; \ -- 2.20.1 In do_sqrshl48_d() and do_uqrshl48_d() we got some of the edge cases wrong and failed to saturate correctly: (1) In do_sqrshl48_d() we used the same code that do_shrshl_bhs() does to obtain the saturated most-negative and most-positive 48-bit signed values for the large-shift-left case. This gives (1 << 47) for saturate-to-most-negative, but we weren't sign-extending this value to the 64-bit output as the pseudocode requires. (2) For left shifts by less than 48, we copied the "8/16 bit" code from do_sqrshl_bhs() and do_uqrshl_bhs(). This doesn't do the right thing because it assumes the C type we're working with is at least twice the number of bits we're saturating to (so that a shift left by bits-1 can't shift anything off the top of the value). This isn't true for bits == 48, so we would incorrectly return 0 rather than the most-positive value for situations like "shift (1 << 44) right by 20". Instead check for saturation by doing the shift and signextend and then testing whether shifting back left again gives the original value. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 12 +++++------- 1 file changed, 5 insertions(+), 7 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, } return src >> -shift; } else if (shift < 48) { - int64_t val = src << shift; - int64_t extval = sextract64(val, 0, 48); - if (!sat || val == extval) { + int64_t extval = sextract64(src << shift, 0, 48); + if (!sat || src == (extval >> shift)) { return extval; } } else if (!sat || src == 0) { @@ -XXX,XX +XXX,XX @@ static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, } *sat = 1; - return (1ULL << 47) - (src >= 0); + return src >= 0 ? MAKE_64BIT_MASK(0, 47) : MAKE_64BIT_MASK(47, 17); } /* Operate on 64-bit values, but saturate at 48 bits */ @@ -XXX,XX +XXX,XX @@ static inline uint64_t do_uqrshl48_d(uint64_t src, int64_t shift, return extval; } } else if (shift < 48) { - uint64_t val = src << shift; - uint64_t extval = extract64(val, 0, 48); - if (!sat || val == extval) { + uint64_t extval = extract64(src << shift, 0, 48); + if (!sat || src == (extval >> shift)) { return extval; } } else if (!sat || src == 0) { -- 2.20.1 We got an edge case wrong in the 48-bit SQRSHRL implementation: if the shift is to the right, although it always makes the result smaller than the input value it might not be within the 48-bit range the result is supposed to be if the input had some bits in [63..48] set and the shift didn't bring all of those within the [47..0] range. Handle this similarly to the way we already do for this case in do_uqrshl48_d(): extend the calculated result from 48 bits, and return that if not saturating or if it doesn't change the result; otherwise fall through to return a saturated value. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(mve_uqrshll)(CPUARMState *env, uint64_t n, uint32_t shift) static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, bool round, uint32_t *sat) { + int64_t val, extval; + if (shift <= -48) { /* Rounding the sign bit always produces 0. */ if (round) { @@ -XXX,XX +XXX,XX @@ static inline int64_t do_sqrshl48_d(int64_t src, int64_t shift, } else if (shift < 0) { if (round) { src >>= -shift - 1; - return (src >> 1) + (src & 1); + val = (src >> 1) + (src & 1); + } else { + val = src >> -shift; + } + extval = sextract64(val, 0, 48); + if (!sat || val == extval) { + return extval; } - return src >> -shift; } else if (shift < 48) { int64_t extval = sextract64(src << shift, 0, 48); if (!sat || src == (extval >> shift)) { -- 2.20.1 In mve_element_mask(), we calculate a mask for tail predication which should have a number of 1 bits based on the value of LR. However, our MAKE_64BIT_MASK() macro has undefined behaviour when passed a zero length. Special case this to give the all-zeroes mask we require. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static uint16_t mve_element_mask(CPUARMState *env) */ int masklen = env->regs[14] << env->v7m.ltpsize; assert(masklen <= 16); - mask &= MAKE_64BIT_MASK(0, masklen); + uint16_t ltpmask = masklen ? MAKE_64BIT_MASK(0, masklen) : 0; + mask &= ltpmask; } if ((env->condexec_bits & 0xf) == 0) { -- 2.20.1 In some situations we need a mask telling us which parts of the vector correspond to beats that are not being executed because of ECI, separately from the combined "which bytes are predicated away" mask. Factor this mask calculation out of mve_element_mask() into its own function. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 58 ++++++++++++++++++++++++----------------- 1 file changed, 34 insertions(+), 24 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/exec-all.h" #include "tcg/tcg.h" +static uint16_t mve_eci_mask(CPUARMState *env) +{ + /* + * Return the mask of which elements in the MVE vector correspond + * to beats being executed. The mask has 1 bits for executed lanes + * and 0 bits where ECI says this beat was already executed. + */ + int eci; + + if ((env->condexec_bits & 0xf) != 0) { + return 0xffff; + } + + eci = env->condexec_bits >> 4; + switch (eci) { + case ECI_NONE: + return 0xffff; + case ECI_A0: + return 0xfff0; + case ECI_A0A1: + return 0xff00; + case ECI_A0A1A2: + case ECI_A0A1A2B0: + return 0xf000; + default: + g_assert_not_reached(); + } +} + static uint16_t mve_element_mask(CPUARMState *env) { /* @@ -XXX,XX +XXX,XX @@ static uint16_t mve_element_mask(CPUARMState *env) mask &= ltpmask; } - if ((env->condexec_bits & 0xf) == 0) { - /* - * ECI bits indicate which beats are already executed; - * we handle this by effectively predicating them out. - */ - int eci = env->condexec_bits >> 4; - switch (eci) { - case ECI_NONE: - break; - case ECI_A0: - mask &= 0xfff0; - break; - case ECI_A0A1: - mask &= 0xff00; - break; - case ECI_A0A1A2: - case ECI_A0A1A2B0: - mask &= 0xf000; - break; - default: - g_assert_not_reached(); - } - } - + /* + * ECI bits indicate which beats are already executed; + * we handle this by effectively predicating them out. + */ + mask &= mve_eci_mask(env); return mask; } -- 2.20.1 We were not paying attention to the ECI state when advancing the VPT state. Architecturally, VPT state advance happens for every beat (see the pseudocode VPTAdvance()), so on every beat the 4 bits of VPR.P0 corresponding to the current beat are inverted if required, and at the end of beats 1 and 3 the VPR MASK fields are updated. This means that if the ECI state says we should not be executing all 4 beats then we need to skip some of the updating of the VPR that we currently do in mve_advance_vpt(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) /* Advance the VPT and ECI state if necessary */ uint32_t vpr = env->v7m.vpr; unsigned mask01, mask23; + uint16_t inv_mask; + uint16_t eci_mask = mve_eci_mask(env); if ((env->condexec_bits & 0xf) == 0) { env->condexec_bits = (env->condexec_bits == (ECI_A0A1A2B0 << 4)) ? @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) return; } + /* Invert P0 bits if needed, but only for beats we actually executed */ mask01 = FIELD_EX32(vpr, V7M_VPR, MASK01); mask23 = FIELD_EX32(vpr, V7M_VPR, MASK23); - if (mask01 > 8) { - /* high bit set, but not 0b1000: invert the relevant half of P0 */ - vpr ^= 0xff; + /* Start by assuming we invert all bits corresponding to executed beats */ + inv_mask = eci_mask; + if (mask01 <= 8) { + /* MASK01 says don't invert low half of P0 */ + inv_mask &= ~0xff; } - if (mask23 > 8) { - /* high bit set, but not 0b1000: invert the relevant half of P0 */ - vpr ^= 0xff00; + if (mask23 <= 8) { + /* MASK23 says don't invert high half of P0 */ + inv_mask &= ~0xff00; } - vpr = FIELD_DP32(vpr, V7M_VPR, MASK01, mask01 << 1); + vpr ^= inv_mask; + /* Only update MASK01 if beat 1 executed */ + if (eci_mask & 0xf0) { + vpr = FIELD_DP32(vpr, V7M_VPR, MASK01, mask01 << 1); + } + /* Beat 3 always executes, so update MASK23 */ vpr = FIELD_DP32(vpr, V7M_VPR, MASK23, mask23 << 1); env->v7m.vpr = vpr; } -- 2.20.1 For vector loads, predicated elements are zeroed, instead of retaining their previous values (as happens for most data processing operations). This means we need to distinguish "beat not executed due to ECI" (don't touch destination element) from "beat executed but predicated out" (zero destination element). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve_helper.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) env->v7m.vpr = vpr; } - +/* For loads, predicated lanes are zeroed instead of keeping their old values */ #define DO_VLDR(OP, MSIZE, LDTYPE, ESIZE, TYPE) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, uint32_t addr) \ { \ TYPE *d = vd; \ uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ unsigned b, e; \ /* \ * R_SXTM allows the dest reg to become UNKNOWN for abandoned \ @@ -XXX,XX +XXX,XX @@ static void mve_advance_vpt(CPUARMState *env) * then take an exception. \ */ \ for (b = 0, e = 0; b < 16; b += ESIZE, e++) { \ - if (mask & (1 << b)) { \ - d[H##ESIZE(e)] = cpu_##LDTYPE##_data_ra(env, addr, GETPC()); \ + if (eci_mask & (1 << b)) { \ + d[H##ESIZE(e)] = (mask & (1 << b)) ? \ + cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ } \ addr += MSIZE; \ } \ -- 2.20.1 Implement the MVE VMULL (polynomial) insn. Unlike Neon, this comes in two flavours: 8x8->16 and a 16x16->32. Also unlike Neon, the inputs are in either the low or the high half of each double-width element. The assembler for this insn indicates the size with "P8" or "P16", encoded into bit 28 as size = 0 or 1. We choose to follow the same encoding as VQDMULL and decode this into a->size as MO_16 or MO_32 indicating the size of the result elements. This then carries through to the helper function names where it then matches up with the existing pmull_h() which does an 8x8->16 operation and a new pmull_w() which does the 16x16->32. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 5 +++++ target/arm/vec_internal.h | 11 +++++++++++ target/arm/mve.decode | 14 ++++++++++---- target/arm/mve_helper.c | 16 ++++++++++++++++ target/arm/translate-mve.c | 28 ++++++++++++++++++++++++++++ target/arm/vec_helper.c | 14 +++++++++++++- 6 files changed, 83 insertions(+), 5 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vmulltub, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vmulltuh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vmulltuw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullpbh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullpth, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullpbw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vmullptw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vqdmulhb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vqdmulhh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vqdmulhw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/vec_internal.h b/target/arm/vec_internal.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_internal.h +++ b/target/arm/vec_internal.h @@ -XXX,XX +XXX,XX @@ int16_t do_sqrdmlah_h(int16_t, int16_t, int16_t, bool, bool, uint32_t *); int32_t do_sqrdmlah_s(int32_t, int32_t, int32_t, bool, bool, uint32_t *); int64_t do_sqrdmlah_d(int64_t, int64_t, int64_t, bool, bool); +/* + * 8 x 8 -> 16 vector polynomial multiply where the inputs are + * in the low 8 bits of each 16-bit element +*/ +uint64_t pmull_h(uint64_t op1, uint64_t op2); +/* + * 16 x 16 -> 32 vector polynomial multiply where the inputs are + * in the low 16 bits of each 32-bit element + */ +uint64_t pmull_w(uint64_t op1, uint64_t op2); + #endif /* TARGET_ARM_VEC_INTERNALS_H */ diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VHADD_U 111 1 1111 0 . .. ... 0 ... 0 0000 . 1 . 0 ... 0 @2op VHSUB_S 111 0 1111 0 . .. ... 0 ... 0 0010 . 1 . 0 ... 0 @2op VHSUB_U 111 1 1111 0 . .. ... 0 ... 0 0010 . 1 . 0 ... 0 @2op -VMULL_BS 111 0 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op -VMULL_BU 111 1 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op -VMULL_TS 111 0 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op -VMULL_TU 111 1 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op +{ + VMULLP_B 111 . 1110 0 . 11 ... 1 ... 0 1110 . 0 . 0 ... 0 @2op_sz28 + VMULL_BS 111 0 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op + VMULL_BU 111 1 1110 0 . .. ... 1 ... 0 1110 . 0 . 0 ... 0 @2op +} +{ + VMULLP_T 111 . 1110 0 . 11 ... 1 ... 1 1110 . 0 . 0 ... 0 @2op_sz28 + VMULL_TS 111 0 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op + VMULL_TU 111 1 1110 0 . .. ... 1 ... 1 1110 . 0 . 0 ... 0 @2op +} VQDMULH 1110 1111 0 . .. ... 0 ... 0 1011 . 1 . 0 ... 0 @2op VQRDMULH 1111 1111 0 . .. ... 0 ... 0 1011 . 1 . 0 ... 0 @2op diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2OP_L(vmulltub, 1, 1, uint8_t, 2, uint16_t, DO_MUL) DO_2OP_L(vmulltuh, 1, 2, uint16_t, 4, uint32_t, DO_MUL) DO_2OP_L(vmulltuw, 1, 4, uint32_t, 8, uint64_t, DO_MUL) +/* + * Polynomial multiply. We can always do this generating 64 bits + * of the result at a time, so we don't need to use DO_2OP_L. + */ +#define VMULLPH_MASK 0x00ff00ff00ff00ffULL +#define VMULLPW_MASK 0x0000ffff0000ffffULL +#define DO_VMULLPBH(N, M) pmull_h((N) & VMULLPH_MASK, (M) & VMULLPH_MASK) +#define DO_VMULLPTH(N, M) DO_VMULLPBH((N) >> 8, (M) >> 8) +#define DO_VMULLPBW(N, M) pmull_w((N) & VMULLPW_MASK, (M) & VMULLPW_MASK) +#define DO_VMULLPTW(N, M) DO_VMULLPBW((N) >> 16, (M) >> 16) + +DO_2OP(vmullpbh, 8, uint64_t, DO_VMULLPBH) +DO_2OP(vmullpth, 8, uint64_t, DO_VMULLPTH) +DO_2OP(vmullpbw, 8, uint64_t, DO_VMULLPBW) +DO_2OP(vmullptw, 8, uint64_t, DO_VMULLPTW) + /* * Because the computation type is at least twice as large as required, * these work for both signed and unsigned source types. diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VQDMULLT(DisasContext *s, arg_2op *a) return do_2op(s, a, fns[a->size]); } +static bool trans_VMULLP_B(DisasContext *s, arg_2op *a) +{ + /* + * Note that a->size indicates the output size, ie VMULL.P8 + * is the 8x8->16 operation and a->size is MO_16; VMULL.P16 + * is the 16x16->32 operation and a->size is MO_32. + */ + static MVEGenTwoOpFn * const fns[] = { + NULL, + gen_helper_mve_vmullpbh, + gen_helper_mve_vmullpbw, + NULL, + }; + return do_2op(s, a, fns[a->size]); +} + +static bool trans_VMULLP_T(DisasContext *s, arg_2op *a) +{ + /* a->size is as for trans_VMULLP_B */ + static MVEGenTwoOpFn * const fns[] = { + NULL, + gen_helper_mve_vmullpth, + gen_helper_mve_vmullptw, + NULL, + }; + return do_2op(s, a, fns[a->size]); +} + /* * VADC and VSBC: these perform an add-with-carry or subtract-with-carry * of the 32-bit elements in each lane of the input vectors, where the diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t expand_byte_to_half(uint64_t x) | ((x & 0xff000000) << 24); } -static uint64_t pmull_h(uint64_t op1, uint64_t op2) +uint64_t pmull_w(uint64_t op1, uint64_t op2) { uint64_t result = 0; int i; + for (i = 0; i < 16; ++i) { + uint64_t mask = (op1 & 0x0000000100000001ull) * 0xffffffff; + result ^= op2 & mask; + op1 >>= 1; + op2 <<= 1; + } + return result; +} +uint64_t pmull_h(uint64_t op1, uint64_t op2) +{ + uint64_t result = 0; + int i; for (i = 0; i < 8; ++i) { uint64_t mask = (op1 & 0x0001000100010001ull) * 0xffff; result ^= op2 & mask; -- 2.20.1 Implement the MVE incrementing/decrementing dup insns VIDUP, VDDUP, VIWDUP and VDWDUP. These fill the elements of a vector with successively incrementing values, starting at the offset specified in a general purpose register. The final value of the offset is written back to this register. The wrapping variants take a second general purpose register which specifies the point where the count should wrap back to 0. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 12 ++++ target/arm/mve.decode | 25 ++++++++ target/arm/mve_helper.c | 63 +++++++++++++++++++ target/arm/translate-mve.c | 120 +++++++++++++++++++++++++++++++++++++ 4 files changed, 220 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vstrh_w, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) +DEF_HELPER_FLAGS_4(mve_viduph, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) +DEF_HELPER_FLAGS_4(mve_vidupw, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) + +DEF_HELPER_FLAGS_5(mve_viwdupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_viwduph, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_viwdupw, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) + +DEF_HELPER_FLAGS_5(mve_vdwdupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_vdwduph, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) +DEF_HELPER_FLAGS_5(mve_vdwdupw, TCG_CALL_NO_WG, i32, env, ptr, i32, i32, i32) + DEF_HELPER_FLAGS_3(mve_vclsb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vclsh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vclsw, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &2scalar qd qn rm size &1imm qd imm cmode op &2shift qd qm shift size +&vidup qd rn size imm +&viwdup qd rn rm size imm @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ VDUP 1110 1110 1 1 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=0 VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 1 1 0000 @vdup size=1 VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 +# Incrementing and decrementing dup + +# VIDUP, VDDUP format immediate: 1 << (immh:imml) +%imm_vidup 7:1 0:1 !function=vidup_imm + +# VIDUP, VDDUP registers: Rm bits [3:1] from insn, bit 0 is 1; +# Rn bits [3:1] from insn, bit 0 is 0 +%vidup_rm 1:3 !function=times_2_plus_1 +%vidup_rn 17:3 !function=times_2 + +@vidup .... .... . . size:2 .... .... .... .... .... \ + qd=%qd imm=%imm_vidup rn=%vidup_rn &vidup +@viwdup .... .... . . size:2 .... .... .... .... .... \ + qd=%qd imm=%imm_vidup rm=%vidup_rm rn=%vidup_rn &viwdup +{ + VIDUP 1110 1110 0 . .. ... 1 ... 0 1111 . 110 111 . @vidup + VIWDUP 1110 1110 0 . .. ... 1 ... 0 1111 . 110 ... . @viwdup +} +{ + VDDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 111 . @vidup + VDWDUP 1110 1110 0 . .. ... 1 ... 1 1111 . 110 ... . @viwdup +} + # multiply-add long dual accumulate # rdahi: bits [3:1] from insn, bit 0 is 1 # rdalo: bits [3:1] from insn, bit 0 is 0 diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(mve_sqrshr)(CPUARMState *env, uint32_t n, uint32_t shift) { return do_sqrshl_bhs(n, -(int8_t)shift, 32, true, &env->QF); } + +#define DO_VIDUP(OP, ESIZE, TYPE, FN) \ + uint32_t HELPER(mve_##OP)(CPUARMState *env, void *vd, \ + uint32_t offset, uint32_t imm) \ + { \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], offset, mask); \ + offset = FN(offset, imm); \ + } \ + mve_advance_vpt(env); \ + return offset; \ + } + +#define DO_VIWDUP(OP, ESIZE, TYPE, FN) \ + uint32_t HELPER(mve_##OP)(CPUARMState *env, void *vd, \ + uint32_t offset, uint32_t wrap, \ + uint32_t imm) \ + { \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], offset, mask); \ + offset = FN(offset, wrap, imm); \ + } \ + mve_advance_vpt(env); \ + return offset; \ + } + +#define DO_VIDUP_ALL(OP, FN) \ + DO_VIDUP(OP##b, 1, int8_t, FN) \ + DO_VIDUP(OP##h, 2, int16_t, FN) \ + DO_VIDUP(OP##w, 4, int32_t, FN) + +#define DO_VIWDUP_ALL(OP, FN) \ + DO_VIWDUP(OP##b, 1, int8_t, FN) \ + DO_VIWDUP(OP##h, 2, int16_t, FN) \ + DO_VIWDUP(OP##w, 4, int32_t, FN) + +static uint32_t do_add_wrap(uint32_t offset, uint32_t wrap, uint32_t imm) +{ + offset += imm; + if (offset == wrap) { + offset = 0; + } + return offset; +} + +static uint32_t do_sub_wrap(uint32_t offset, uint32_t wrap, uint32_t imm) +{ + if (offset == 0) { + offset = wrap; + } + offset -= imm; + return offset; +} + +DO_VIDUP_ALL(vidup, DO_ADD) +DO_VIWDUP_ALL(viwdup, do_add_wrap) +DO_VIWDUP_ALL(vdwdup, do_sub_wrap) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ #include "translate.h" #include "translate-a32.h" +static inline int vidup_imm(DisasContext *s, int x) +{ + return 1 << x; +} + /* Include the generated decoder */ #include "decode-mve.c.inc" @@ -XXX,XX +XXX,XX @@ typedef void MVEGenTwoOpShiftFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); +typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); +typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool trans_VSHLC(DisasContext *s, arg_VSHLC *a) mve_update_eci(s); return true; } + +static bool do_vidup(DisasContext *s, arg_vidup *a, MVEGenVIDUPFn *fn) +{ + TCGv_ptr qd; + TCGv_i32 rn; + + /* + * Vector increment/decrement with wrap and duplicate (VIDUP, VDDUP). + * This fills the vector with elements of successively increasing + * or decreasing values, starting from Rn. + */ + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) { + return false; + } + if (a->size == MO_64) { + /* size 0b11 is another encoding */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qd = mve_qreg_ptr(a->qd); + rn = load_reg(s, a->rn); + fn(rn, cpu_env, qd, rn, tcg_constant_i32(a->imm)); + store_reg(s, a->rn, rn); + tcg_temp_free_ptr(qd); + mve_update_eci(s); + return true; +} + +static bool do_viwdup(DisasContext *s, arg_viwdup *a, MVEGenVIWDUPFn *fn) +{ + TCGv_ptr qd; + TCGv_i32 rn, rm; + + /* + * Vector increment/decrement with wrap and duplicate (VIWDUp, VDWDUP) + * This fills the vector with elements of successively increasing + * or decreasing values, starting from Rn. Rm specifies a point where + * the count wraps back around to 0. The updated offset is written back + * to Rn. + */ + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd)) { + return false; + } + if (!fn || a->rm == 13 || a->rm == 15) { + /* + * size 0b11 is another encoding; Rm == 13 is UNPREDICTABLE; + * Rm == 13 is VIWDUP, VDWDUP. + */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qd = mve_qreg_ptr(a->qd); + rn = load_reg(s, a->rn); + rm = load_reg(s, a->rm); + fn(rn, cpu_env, qd, rn, rm, tcg_constant_i32(a->imm)); + store_reg(s, a->rn, rn); + tcg_temp_free_ptr(qd); + tcg_temp_free_i32(rm); + mve_update_eci(s); + return true; +} + +static bool trans_VIDUP(DisasContext *s, arg_vidup *a) +{ + static MVEGenVIDUPFn * const fns[] = { + gen_helper_mve_vidupb, + gen_helper_mve_viduph, + gen_helper_mve_vidupw, + NULL, + }; + return do_vidup(s, a, fns[a->size]); +} + +static bool trans_VDDUP(DisasContext *s, arg_vidup *a) +{ + static MVEGenVIDUPFn * const fns[] = { + gen_helper_mve_vidupb, + gen_helper_mve_viduph, + gen_helper_mve_vidupw, + NULL, + }; + /* VDDUP is just like VIDUP but with a negative immediate */ + a->imm = -a->imm; + return do_vidup(s, a, fns[a->size]); +} + +static bool trans_VIWDUP(DisasContext *s, arg_viwdup *a) +{ + static MVEGenVIWDUPFn * const fns[] = { + gen_helper_mve_viwdupb, + gen_helper_mve_viwduph, + gen_helper_mve_viwdupw, + NULL, + }; + return do_viwdup(s, a, fns[a->size]); +} + +static bool trans_VDWDUP(DisasContext *s, arg_viwdup *a) +{ + static MVEGenVIWDUPFn * const fns[] = { + gen_helper_mve_vdwdupb, + gen_helper_mve_vdwduph, + gen_helper_mve_vdwdupw, + NULL, + }; + return do_viwdup(s, a, fns[a->size]); +} -- 2.20.1 Factor out the "generate code to update VPR.MASK01/MASK23" part of trans_VPST(); we are going to want to reuse it for the VPT insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-mve.c | 31 +++++++++++++++++-------------- 1 file changed, 17 insertions(+), 14 deletions(-) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLSLDAVH(DisasContext *s, arg_vmlaldav *a) return do_long_dual_acc(s, a, fns[a->x]); } -static bool trans_VPST(DisasContext *s, arg_VPST *a) +static void gen_vpst(DisasContext *s, uint32_t mask) { - TCGv_i32 vpr; - - /* mask == 0 is a "related encoding" */ - if (!dc_isar_feature(aa32_mve, s) || !a->mask) { - return false; - } - if (!mve_eci_check(s) || !vfp_access_check(s)) { - return true; - } /* * Set the VPR mask fields. We take advantage of MASK01 and MASK23 * being adjacent fields in the register. * - * This insn is not predicated, but it is subject to beat-wise + * Updating the masks is not predicated, but it is subject to beat-wise * execution, and the mask is updated on the odd-numbered beats. * So if PSR.ECI says we should skip beat 1, we mustn't update the * 01 mask field. */ - vpr = load_cpu_field(v7m.vpr); + TCGv_i32 vpr = load_cpu_field(v7m.vpr); switch (s->eci) { case ECI_NONE: case ECI_A0: /* Update both 01 and 23 fields */ tcg_gen_deposit_i32(vpr, vpr, - tcg_constant_i32(a->mask | (a->mask << 4)), + tcg_constant_i32(mask | (mask << 4)), R_V7M_VPR_MASK01_SHIFT, R_V7M_VPR_MASK01_LENGTH + R_V7M_VPR_MASK23_LENGTH); break; @@ -XXX,XX +XXX,XX @@ static bool trans_VPST(DisasContext *s, arg_VPST *a) case ECI_A0A1A2B0: /* Update only the 23 mask field */ tcg_gen_deposit_i32(vpr, vpr, - tcg_constant_i32(a->mask), + tcg_constant_i32(mask), R_V7M_VPR_MASK23_SHIFT, R_V7M_VPR_MASK23_LENGTH); break; default: g_assert_not_reached(); } store_cpu_field(vpr, v7m.vpr); +} + +static bool trans_VPST(DisasContext *s, arg_VPST *a) +{ + /* mask == 0 is a "related encoding" */ + if (!dc_isar_feature(aa32_mve, s) || !a->mask) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + gen_vpst(s, a->mask); mve_update_and_store_eci(s); return true; } -- 2.20.1 Implement the MVE integer vector comparison instructions. These are "VCMP (vector)" encodings T1, T2 and T3, and "VPT (vector)" encodings T1, T2 and T3. These insns compare corresponding elements in each vector, and update the VPR.P0 predicate bits with the results of the comparison. VPT also sets the VPR.MASK01 and VPR.MASK23 fields -- it is effectively "VCMP then VPST". Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 32 ++++++++++++++++++++++ target/arm/mve.decode | 18 +++++++++++- target/arm/mve_helper.c | 56 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 47 ++++++++++++++++++++++++++++++++ 4 files changed, 152 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_uqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(mve_sqshl, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(mve_uqrshl, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_3(mve_sqrshr, TCG_CALL_NO_RWG, i32, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpeqb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpeqh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpeqw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpneb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpneh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpnew, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpcsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpcsh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpcsw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmphib, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmphih, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmphiw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpgeb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgeh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgew, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpltb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmplth, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpltw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpgtb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgth, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpgtw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpleb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmpleh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vcmplew, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &2shift qd qm shift size &vidup qd rn size imm &viwdup qd rn rm size imm +&vcmp qm qn size mask @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @2_shr_w .... .... .. 1 ..... .... .... .... .... &2shift qd=%qd qm=%qm \ size=2 shift=%rshift_i5 +# Vector comparison; 4-bit Qm but 3-bit Qn +%mask_22_13 22:1 13:3 +@vcmp .... .... .. size:2 qn:3 . .... .... .... .... &vcmp qm=%qm mask=%mask_22_13 + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar } # Predicate operations -%mask_22_13 22:1 13:3 VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 # Logical immediate operations (1 reg and modified-immediate) @@ -XXX,XX +XXX,XX @@ VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_b VQRSHRUNT 111 1 1110 1 . ... ... ... 1 1111 1 1 . 0 ... 0 @2_shr_h VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd + +# Comparisons. We expand out the conditions which are split across +# encodings T1, T2, T3 and the fc bits. These include VPT, which is +# effectively "VCMP then VPST". A plain "VCMP" has a mask field of zero. +VCMPEQ 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp +VCMPNE 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp +VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp +VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp +VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp +VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp +VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp +VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ static uint32_t do_sub_wrap(uint32_t offset, uint32_t wrap, uint32_t imm) DO_VIDUP_ALL(vidup, DO_ADD) DO_VIWDUP_ALL(viwdup, do_add_wrap) DO_VIWDUP_ALL(vdwdup, do_sub_wrap) + +/* + * Vector comparison. + * P0 bits for non-executed beats (where eci_mask is 0) are unchanged. + * P0 bits for predicated lanes in executed beats (where mask is 0) are 0. + * P0 bits otherwise are updated with the results of the comparisons. + * We must also keep unchanged the MASK fields at the top of v7m.vpr. + */ +#define DO_VCMP(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, void *vm) \ + { \ + TYPE *n = vn, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + uint16_t beatpred = 0; \ + uint16_t emask = MAKE_64BIT_MASK(0, ESIZE); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++) { \ + bool r = FN(n[H##ESIZE(e)], m[H##ESIZE(e)]); \ + /* Comparison sets 0/1 bits for each byte in the element */ \ + beatpred |= r * emask; \ + emask <<= ESIZE; \ + } \ + beatpred &= mask; \ + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | \ + (beatpred & eci_mask); \ + mve_advance_vpt(env); \ + } + +#define DO_VCMP_S(OP, FN) \ + DO_VCMP(OP##b, 1, int8_t, FN) \ + DO_VCMP(OP##h, 2, int16_t, FN) \ + DO_VCMP(OP##w, 4, int32_t, FN) + +#define DO_VCMP_U(OP, FN) \ + DO_VCMP(OP##b, 1, uint8_t, FN) \ + DO_VCMP(OP##h, 2, uint16_t, FN) \ + DO_VCMP(OP##w, 4, uint32_t, FN) + +#define DO_EQ(N, M) ((N) == (M)) +#define DO_NE(N, M) ((N) != (M)) +#define DO_EQ(N, M) ((N) == (M)) +#define DO_EQ(N, M) ((N) == (M)) +#define DO_GE(N, M) ((N) >= (M)) +#define DO_LT(N, M) ((N) < (M)) +#define DO_GT(N, M) ((N) > (M)) +#define DO_LE(N, M) ((N) <= (M)) + +DO_VCMP_U(vcmpeq, DO_EQ) +DO_VCMP_U(vcmpne, DO_NE) +DO_VCMP_U(vcmpcs, DO_GE) +DO_VCMP_U(vcmphi, DO_GT) +DO_VCMP_S(vcmpge, DO_GE) +DO_VCMP_S(vcmplt, DO_LT) +DO_VCMP_S(vcmpgt, DO_GT) +DO_VCMP_S(vcmple, DO_LE) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); +typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool trans_VDWDUP(DisasContext *s, arg_viwdup *a) }; return do_viwdup(s, a, fns[a->size]); } + +static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn) +{ + TCGv_ptr qn, qm; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qm) || + !fn) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qn = mve_qreg_ptr(a->qn); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qn, qm); + tcg_temp_free_ptr(qn); + tcg_temp_free_ptr(qm); + if (a->mask) { + /* VPT */ + gen_vpst(s, a->mask); + } + mve_update_eci(s); + return true; +} + +#define DO_VCMP(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vcmp *a) \ + { \ + static MVEGenCmpFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_vcmp(s, a, fns[a->size]); \ + } + +DO_VCMP(VCMPEQ, vcmpeq) +DO_VCMP(VCMPNE, vcmpne) +DO_VCMP(VCMPCS, vcmpcs) +DO_VCMP(VCMPHI, vcmphi) +DO_VCMP(VCMPGE, vcmpge) +DO_VCMP(VCMPLT, vcmplt) +DO_VCMP(VCMPGT, vcmpgt) +DO_VCMP(VCMPLE, vcmple) -- 2.20.1 Implement the MVE integer vector comparison instructions that compare each element against a scalar from a general purpose register. These are "VCMP (vector)" encodings T4, T5 and T6 and "VPT (vector)" encodings T4, T5 and T6. We have to move the decodetree pattern for VPST, because it overlaps with VCMP T4 with size = 0b11. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 32 +++++++++++++++++++++++++++ target/arm/mve.decode | 18 +++++++++++++--- target/arm/mve_helper.c | 44 +++++++++++++++++++++++++++++++------- target/arm/translate-mve.c | 43 +++++++++++++++++++++++++++++++++++++ 4 files changed, 126 insertions(+), 11 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vcmpgtw, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vcmpleb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vcmpleh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vcmplew, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpeq_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpne_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpne_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpne_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpcs_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmphi_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmphi_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmphi_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpge_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpge_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpge_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmplt_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmplt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmplt_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmpgt_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vcmple_scalarb, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmple_scalarh, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vcmple_scalarw, TCG_CALL_NO_WG, void, env, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vidup qd rn size imm &viwdup qd rn rm size imm &vcmp qm qn size mask +&vcmp_scalar qn rm size mask @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ # Vector comparison; 4-bit Qm but 3-bit Qn %mask_22_13 22:1 13:3 @vcmp .... .... .. size:2 qn:3 . .... .... .... .... &vcmp qm=%qm mask=%mask_22_13 +@vcmp_scalar .... .... .. size:2 qn:3 . .... .... .... rm:4 &vcmp_scalar \ + mask=%mask_22_13 # Vector loads and stores @@ -XXX,XX +XXX,XX @@ VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar rdahi=%rdahi rdalo=%rdalo } -# Predicate operations -VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 - # Logical immediate operations (1 reg and modified-immediate) # The cmode/op bits here decode VORR/VBIC/VMOV/VMVN, but @@ -XXX,XX +XXX,XX @@ VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp + +{ + VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 + VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 0 0 .... @vcmp_scalar +} +VCMPNE_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 0 0 .... @vcmp_scalar +VCMPCS_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 1 0 .... @vcmp_scalar +VCMPHI_scalar 1111 1110 0 . .. ... 1 ... 0 1111 1 1 1 0 .... @vcmp_scalar +VCMPGE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 0 0 .... @vcmp_scalar +VCMPLT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 0 0 .... @vcmp_scalar +VCMPGT_scalar 1111 1110 0 . .. ... 1 ... 1 1111 0 1 1 0 .... @vcmp_scalar +VCMPLE_scalar 1111 1110 0 . .. ... 1 ... 1 1111 1 1 1 0 .... @vcmp_scalar diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VIWDUP_ALL(vdwdup, do_sub_wrap) mve_advance_vpt(env); \ } -#define DO_VCMP_S(OP, FN) \ - DO_VCMP(OP##b, 1, int8_t, FN) \ - DO_VCMP(OP##h, 2, int16_t, FN) \ - DO_VCMP(OP##w, 4, int32_t, FN) +#define DO_VCMP_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + uint32_t rm) \ + { \ + TYPE *n = vn; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + uint16_t beatpred = 0; \ + uint16_t emask = MAKE_64BIT_MASK(0, ESIZE); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++) { \ + bool r = FN(n[H##ESIZE(e)], (TYPE)rm); \ + /* Comparison sets 0/1 bits for each byte in the element */ \ + beatpred |= r * emask; \ + emask <<= ESIZE; \ + } \ + beatpred &= mask; \ + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | \ + (beatpred & eci_mask); \ + mve_advance_vpt(env); \ + } -#define DO_VCMP_U(OP, FN) \ - DO_VCMP(OP##b, 1, uint8_t, FN) \ - DO_VCMP(OP##h, 2, uint16_t, FN) \ - DO_VCMP(OP##w, 4, uint32_t, FN) +#define DO_VCMP_S(OP, FN) \ + DO_VCMP(OP##b, 1, int8_t, FN) \ + DO_VCMP(OP##h, 2, int16_t, FN) \ + DO_VCMP(OP##w, 4, int32_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarb, 1, int8_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarh, 2, int16_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarw, 4, int32_t, FN) + +#define DO_VCMP_U(OP, FN) \ + DO_VCMP(OP##b, 1, uint8_t, FN) \ + DO_VCMP(OP##h, 2, uint16_t, FN) \ + DO_VCMP(OP##w, 4, uint32_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarb, 1, uint8_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarh, 2, uint16_t, FN) \ + DO_VCMP_SCALAR(OP##_scalarw, 4, uint32_t, FN) #define DO_EQ(N, M) ((N) == (M)) #define DO_NE(N, M) ((N) != (M)) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); +typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn) return true; } +static bool do_vcmp_scalar(DisasContext *s, arg_vcmp_scalar *a, + MVEGenScalarCmpFn *fn) +{ + TCGv_ptr qn; + TCGv_i32 rm; + + if (!dc_isar_feature(aa32_mve, s) || !fn || a->rm == 13) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qn = mve_qreg_ptr(a->qn); + if (a->rm == 15) { + /* Encoding Rm=0b1111 means "constant zero" */ + rm = tcg_constant_i32(0); + } else { + rm = load_reg(s, a->rm); + } + fn(cpu_env, qn, rm); + tcg_temp_free_ptr(qn); + tcg_temp_free_i32(rm); + if (a->mask) { + /* VPT */ + gen_vpst(s, a->mask); + } + mve_update_eci(s); + return true; +} + #define DO_VCMP(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_vcmp *a) \ { \ @@ -XXX,XX +XXX,XX @@ static bool do_vcmp(DisasContext *s, arg_vcmp *a, MVEGenCmpFn *fn) NULL, \ }; \ return do_vcmp(s, a, fns[a->size]); \ + } \ + static bool trans_##INSN##_scalar(DisasContext *s, \ + arg_vcmp_scalar *a) \ + { \ + static MVEGenScalarCmpFn * const fns[] = { \ + gen_helper_mve_##FN##_scalarb, \ + gen_helper_mve_##FN##_scalarh, \ + gen_helper_mve_##FN##_scalarw, \ + NULL, \ + }; \ + return do_vcmp_scalar(s, a, fns[a->size]); \ } DO_VCMP(VCMPEQ, vcmpeq) -- 2.20.1 Implement the MVE VPSEL insn, which sets each byte of the destination vector Qd to the byte from either Qn or Qm depending on the value of the corresponding bit in VPR.P0. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 2 ++ target/arm/mve.decode | 7 +++++-- target/arm/mve_helper.c | 19 +++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 28 insertions(+), 2 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vorr, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vorn, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_veor, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_4(mve_vpsel, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vaddb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VSHLC 111 0 1110 1 . 1 imm:5 ... 0 1111 1100 rdm:4 qd=%qd # effectively "VCMP then VPST". A plain "VCMP" has a mask field of zero. VCMPEQ 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 0 @vcmp VCMPNE 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 0 @vcmp -VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp -VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp +{ + VPSEL 1111 1110 0 . 11 ... 1 ... 0 1111 . 0 . 0 ... 1 @2op_nosz + VCMPCS 1111 1110 0 . .. ... 1 ... 0 1111 0 0 . 0 ... 1 @vcmp + VCMPHI 1111 1110 0 . .. ... 1 ... 0 1111 1 0 . 0 ... 1 @vcmp +} VCMPGE 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 0 @vcmp VCMPLT 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 0 @vcmp VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VCMP_S(vcmpge, DO_GE) DO_VCMP_S(vcmplt, DO_LT) DO_VCMP_S(vcmpgt, DO_GT) DO_VCMP_S(vcmple, DO_LE) + +void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void *vn, void *vm) +{ + /* + * Qd[n] = VPR.P0[n] ? Qn[n] : Qm[n] + * but note that whether bytes are written to Qd is still subject + * to (all forms of) predication in the usual way. + */ + uint64_t *d = vd, *n = vn, *m = vm; + uint16_t mask = mve_element_mask(env); + uint16_t p0 = FIELD_EX32(env->v7m.vpr, V7M_VPR, P0); + unsigned e; + for (e = 0; e < 16 / 8; e++, mask >>= 8, p0 >>= 8) { + uint64_t r = m[H8(e)]; + mergemask(&r, n[H8(e)], p0); + mergemask(&d[H8(e)], r, mask); + } + mve_advance_vpt(env); +} diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_LOGIC(VORR, gen_helper_mve_vorr) DO_LOGIC(VORN, gen_helper_mve_vorn) DO_LOGIC(VEOR, gen_helper_mve_veor) +DO_LOGIC(VPSEL, gen_helper_mve_vpsel) + #define DO_2OP(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_2op *a) \ { \ -- 2.20.1 Implement the MVE VMLAS insn, which multiplies a vector by a vector and adds a scalar. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 4 ++++ target/arm/mve.decode | 3 +++ target/arm/mve_helper.c | 26 ++++++++++++++++++++++++++ target/arm/translate-mve.c | 1 + 4 files changed, 34 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqdmullb_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i3 DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlasb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlash, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlasw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vmlaldavsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavxsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar +# The U bit (28) is don't-care because it does not affect the result +VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar + # Vector add across vector { VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w) mve_advance_vpt(env); \ } +/* "accumulating" version where FN takes d as well as n and m */ +#define DO_2OP_ACC_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vn, \ + uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + mergemask(&d[H##ESIZE(e)], \ + FN(d[H##ESIZE(e)], n[H##ESIZE(e)], m), mask); \ + } \ + mve_advance_vpt(env); \ + } + /* provide unsigned 2-op scalar helpers for all sizes */ #define DO_2OP_SCALAR_U(OP, FN) \ DO_2OP_SCALAR(OP##b, 1, uint8_t, FN) \ @@ -XXX,XX +XXX,XX @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w) DO_2OP_SCALAR(OP##h, 2, int16_t, FN) \ DO_2OP_SCALAR(OP##w, 4, int32_t, FN) +#define DO_2OP_ACC_SCALAR_U(OP, FN) \ + DO_2OP_ACC_SCALAR(OP##b, 1, uint8_t, FN) \ + DO_2OP_ACC_SCALAR(OP##h, 2, uint16_t, FN) \ + DO_2OP_ACC_SCALAR(OP##w, 4, uint32_t, FN) + DO_2OP_SCALAR_U(vadd_scalar, DO_ADD) DO_2OP_SCALAR_U(vsub_scalar, DO_SUB) DO_2OP_SCALAR_U(vmul_scalar, DO_MUL) @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, DO_QRDMULH_B) DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H) DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W) +/* Vector by vector plus scalar */ +#define DO_VMLAS(D, N, M) ((N) * (D) + (M)) + +DO_2OP_ACC_SCALAR_U(vmlas, DO_VMLAS) + /* * Long saturating scalar ops. As with DO_2OP_L, TYPE and H are for the * input (smaller) type and LESIZE, LTYPE, LH for the output (long) type. diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SCALAR(VQSUB_U_scalar, vqsubu_scalar) DO_2OP_SCALAR(VQDMULH_scalar, vqdmulh_scalar) DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar) DO_2OP_SCALAR(VBRSR, vbrsr) +DO_2OP_SCALAR(VMLAS, vmlas) static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a) { -- 2.20.1 Implement the MVE instructions which perform shifts by a scalar. These are VSHL T2, VRSHL T2, VQSHL T1 and VQRSHL T2. They take the shift amount in a general purpose register and shift every element in the vector by that amount. Mostly we can reuse the helper functions for shift-by-immediate; we do need two new helpers for VQRSHL. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 8 +++++++ target/arm/mve.decode | 23 ++++++++++++++++--- target/arm/mve_helper.c | 2 ++ target/arm/translate-mve.c | 46 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 76 insertions(+), 3 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_sb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrshli_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrshli_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vshllbsb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshllbsh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vshllbub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &viwdup qd rn rm size imm &vcmp qm qn size mask &vcmp_scalar qn rm size mask +&shl_scalar qda rm size @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @2_shr_w .... .... .. 1 ..... .... .... .... .... &2shift qd=%qd qm=%qm \ size=2 shift=%rshift_i5 +@shl_scalar .... .... .... size:2 .. .... .... .... rm:4 &shl_scalar qda=%qd + # Vector comparison; 4-bit Qm but 3-bit Qn %mask_22_13 22:1 13:3 @vcmp .... .... .. size:2 qn:3 . .... .... .... .... &vcmp qm=%qm mask=%mask_22_13 @@ -XXX,XX +XXX,XX @@ VRMLSLDAVH 1111 1110 1 ... ... 0 ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav_no VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar VSUB_scalar 1110 1110 0 . .. ... 1 ... 1 1111 . 100 .... @2scalar -VMUL_scalar 1110 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar + +{ + VSHL_S_scalar 1110 1110 0 . 11 .. 01 ... 1 1110 0110 .... @shl_scalar + VRSHL_S_scalar 1110 1110 0 . 11 .. 11 ... 1 1110 0110 .... @shl_scalar + VQSHL_S_scalar 1110 1110 0 . 11 .. 01 ... 1 1110 1110 .... @shl_scalar + VQRSHL_S_scalar 1110 1110 0 . 11 .. 11 ... 1 1110 1110 .... @shl_scalar + VMUL_scalar 1110 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar +} + +{ + VSHL_U_scalar 1111 1110 0 . 11 .. 01 ... 1 1110 0110 .... @shl_scalar + VRSHL_U_scalar 1111 1110 0 . 11 .. 11 ... 1 1110 0110 .... @shl_scalar + VQSHL_U_scalar 1111 1110 0 . 11 .. 01 ... 1 1110 1110 .... @shl_scalar + VQRSHL_U_scalar 1111 1110 0 . 11 .. 11 ... 1 1110 1110 .... @shl_scalar + VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar +} + VHADD_S_scalar 1110 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar VHADD_U_scalar 1111 1110 0 . .. ... 0 ... 0 1111 . 100 .... @2scalar VHSUB_S_scalar 1110 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar @@ -XXX,XX +XXX,XX @@ VHSUB_U_scalar 1111 1110 0 . .. ... 0 ... 1 1111 . 100 .... @2scalar size=%size_28 } -VBRSR 1111 1110 0 . .. ... 1 ... 1 1110 . 110 .... @2scalar - VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT_SAT_S(vqshli_s, DO_SQSHL_OP) DO_2SHIFT_SAT_S(vqshlui_s, DO_SUQSHL_OP) DO_2SHIFT_U(vrshli_u, DO_VRSHLU) DO_2SHIFT_S(vrshli_s, DO_VRSHLS) +DO_2SHIFT_SAT_U(vqrshli_u, DO_UQRSHL_OP) +DO_2SHIFT_SAT_S(vqrshli_s, DO_SQRSHL_OP) /* Shift-and-insert; we always work with 64 bits at a time */ #define DO_2SHIFT_INSERT(OP, ESIZE, SHIFTFN, MASKFN) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2SHIFT(VRSHRI_U, vrshli_u, true) DO_2SHIFT(VSRI, vsri, false) DO_2SHIFT(VSLI, vsli, false) +static bool do_2shift_scalar(DisasContext *s, arg_shl_scalar *a, + MVEGenTwoOpShiftFn *fn) +{ + TCGv_ptr qda; + TCGv_i32 rm; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qda) || + a->rm == 13 || a->rm == 15 || !fn) { + /* Rm cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qda = mve_qreg_ptr(a->qda); + rm = load_reg(s, a->rm); + fn(cpu_env, qda, qda, rm); + tcg_temp_free_ptr(qda); + tcg_temp_free_i32(rm); + mve_update_eci(s); + return true; +} + +#define DO_2SHIFT_SCALAR(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_shl_scalar *a) \ + { \ + static MVEGenTwoOpShiftFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_2shift_scalar(s, a, fns[a->size]); \ + } + +DO_2SHIFT_SCALAR(VSHL_S_scalar, vshli_s) +DO_2SHIFT_SCALAR(VSHL_U_scalar, vshli_u) +DO_2SHIFT_SCALAR(VRSHL_S_scalar, vrshli_s) +DO_2SHIFT_SCALAR(VRSHL_U_scalar, vrshli_u) +DO_2SHIFT_SCALAR(VQSHL_S_scalar, vqshli_s) +DO_2SHIFT_SCALAR(VQSHL_U_scalar, vqshli_u) +DO_2SHIFT_SCALAR(VQRSHL_S_scalar, vqrshli_s) +DO_2SHIFT_SCALAR(VQRSHL_U_scalar, vqrshli_u) + #define DO_VSHLL(INSN, FN) \ static bool trans_##INSN(DisasContext *s, arg_2shift *a) \ { \ -- 2.20.1 All the users of the vmlaldav formats have an 'x bit in bit 12 and an 'a' bit in bit 5; move these to the format rather than specifying them in each insn pattern. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/mve.decode | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 &vmlaldav rdahi rdalo size qn qm x a -@vmlaldav .... .... . ... ... . ... . .... .... qm:3 . \ +@vmlaldav .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=%size_16 &vmlaldav -@vmlaldav_nosz .... .... . ... ... . ... . .... .... qm:3 . \ +@vmlaldav_nosz .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=0 &vmlaldav -VMLALDAV_S 1110 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 0 @vmlaldav -VMLALDAV_U 1111 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 0 @vmlaldav +VMLALDAV_S 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav -VMLSLDAV 1110 1110 1 ... ... . ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav +VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav -VRMLALDAVH_S 1110 1110 1 ... ... 0 ... x:1 1111 . 0 a:1 0 ... 0 @vmlaldav_nosz -VRMLALDAVH_U 1111 1110 1 ... ... 0 ... x:1 1111 . 0 a:1 0 ... 0 @vmlaldav_nosz +VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz -VRMLSLDAVH 1111 1110 1 ... ... 0 ... x:1 1110 . 0 a:1 0 ... 1 @vmlaldav_nosz +VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz # Scalar operations -- 2.20.1 Implement the MVE integer min/max across vector insns VMAXV, VMINV, VMAXAV and VMINAV, which find the maximum from the vector elements and a general purpose register, and store the maximum back into the general purpose register. These insns overlap with VRMLALDAVH (they use what would be RdaHi=0b110). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 20 ++++++++++++ target/arm/mve.decode | 18 +++++++++-- target/arm/mve_helper.c | 66 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 48 +++++++++++++++++++++++++++ 4 files changed, 150 insertions(+), 2 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vaddvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvsb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvsh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvub, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxavb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxavh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vmaxavw, TCG_CALL_NO_WG, i32, env, ptr, i32) + +DEF_HELPER_FLAGS_3(mve_vminvsb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvsh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvsw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvub, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvuh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminvuw, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminavb, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminavh, TCG_CALL_NO_WG, i32, env, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vminavw, TCG_CALL_NO_WG, i32, env, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vcmp qm qn size mask &vcmp_scalar qn rm size mask &shl_scalar qda rm size +&vmaxv qm rda size @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ @vcmp_scalar .... .... .. size:2 qn:3 . .... .... .... rm:4 &vcmp_scalar \ mask=%mask_22_13 +@vmaxv .... .... .... size:2 .. rda:4 .... .... .... &vmaxv qm=%qm + # Vector loads and stores # Widening loads and narrowing stores: @@ -XXX,XX +XXX,XX @@ VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav -VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz -VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +{ + VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv + VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +} + +{ + VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv + VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz +} VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VADDV(vaddvub, 1, uint8_t) DO_VADDV(vaddvuh, 2, uint16_t) DO_VADDV(vaddvuw, 4, uint32_t) +/* + * Vector max/min across vector. Unlike VADDV, we must + * read ra as the element size, not its full width. + * We work with int64_t internally for simplicity. + */ +#define DO_VMAXMINV(OP, ESIZE, TYPE, RATYPE, FN) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ + uint32_t ra_in) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *m = vm; \ + int64_t ra = (RATYPE)ra_in; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + ra = FN(ra, m[H##ESIZE(e)]); \ + } \ + } \ + mve_advance_vpt(env); \ + return ra; \ + } \ + +#define DO_VMAXMINV_U(INSN, FN) \ + DO_VMAXMINV(INSN##b, 1, uint8_t, uint8_t, FN) \ + DO_VMAXMINV(INSN##h, 2, uint16_t, uint16_t, FN) \ + DO_VMAXMINV(INSN##w, 4, uint32_t, uint32_t, FN) +#define DO_VMAXMINV_S(INSN, FN) \ + DO_VMAXMINV(INSN##b, 1, int8_t, int8_t, FN) \ + DO_VMAXMINV(INSN##h, 2, int16_t, int16_t, FN) \ + DO_VMAXMINV(INSN##w, 4, int32_t, int32_t, FN) + +/* + * Helpers for max and min of absolute values across vector: + * note that we only take the absolute value of 'm', not 'n' + */ +static int64_t do_maxa(int64_t n, int64_t m) +{ + if (m < 0) { + m = -m; + } + return MAX(n, m); +} + +static int64_t do_mina(int64_t n, int64_t m) +{ + if (m < 0) { + m = -m; + } + return MIN(n, m); +} + +DO_VMAXMINV_S(vmaxvs, DO_MAX) +DO_VMAXMINV_U(vmaxvu, DO_MAX) +DO_VMAXMINV_S(vminvs, DO_MIN) +DO_VMAXMINV_U(vminvu, DO_MIN) +/* + * VMAXAV, VMINAV treat the general purpose input as unsigned + * and the vector elements as signed. + */ +DO_VMAXMINV(vmaxavb, 1, int8_t, uint8_t, do_maxa) +DO_VMAXMINV(vmaxavh, 2, int16_t, uint16_t, do_maxa) +DO_VMAXMINV(vmaxavw, 4, int32_t, uint32_t, do_maxa) +DO_VMAXMINV(vminavb, 1, int8_t, uint8_t, do_mina) +DO_VMAXMINV(vminavh, 2, int16_t, uint16_t, do_mina) +DO_VMAXMINV(vminavw, 4, int32_t, uint32_t, do_mina) + #define DO_VADDLV(OP, TYPE, LTYPE) \ uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ uint64_t ra) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_VCMP(VCMPGE, vcmpge) DO_VCMP(VCMPLT, vcmplt) DO_VCMP(VCMPGT, vcmpgt) DO_VCMP(VCMPLE, vcmple) + +static bool do_vmaxv(DisasContext *s, arg_vmaxv *a, MVEGenVADDVFn fn) +{ + /* + * MIN/MAX operations across a vector: compute the min or + * max of the initial value in a general purpose register + * and all the elements in the vector, and store it back + * into the general purpose register. + */ + TCGv_ptr qm; + TCGv_i32 rda; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qm) || + !fn || a->rda == 13 || a->rda == 15) { + /* Rda cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qm = mve_qreg_ptr(a->qm); + rda = load_reg(s, a->rda); + fn(rda, cpu_env, qm, rda); + store_reg(s, a->rda, rda); + tcg_temp_free_ptr(qm); + mve_update_eci(s); + return true; +} + +#define DO_VMAXV(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vmaxv *a) \ + { \ + static MVEGenVADDVFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_vmaxv(s, a, fns[a->size]); \ + } + +DO_VMAXV(VMAXV_S, vmaxvs) +DO_VMAXV(VMAXV_U, vmaxvu) +DO_VMAXV(VMAXAV, vmaxav) +DO_VMAXV(VMINV_S, vminvs) +DO_VMAXV(VMINV_U, vminvu) +DO_VMAXV(VMINAV, vminav) -- 2.20.1 Implement the MVE VABAV insn, which computes absolute differences between elements of two vectors and accumulates the result into a general purpose register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 7 +++++++ target/arm/mve.decode | 6 ++++++ target/arm/mve_helper.c | 26 +++++++++++++++++++++++ target/arm/translate-mve.c | 43 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 82 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vminavw, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddlv_s, TCG_CALL_NO_WG, i64, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vaddlv_u, TCG_CALL_NO_WG, i64, env, ptr, i64) +DEF_HELPER_FLAGS_4(mve_vabavsb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavsh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavsw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavub, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavuh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vabavuw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vmovi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vandi, TCG_CALL_NO_WG, void, env, ptr, i64) DEF_HELPER_FLAGS_3(mve_vorri, TCG_CALL_NO_WG, void, env, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vcmp_scalar qn rm size mask &shl_scalar qda rm size &vmaxv qm rda size +&vabav qn qm rda size @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @@ -XXX,XX +XXX,XX @@ VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar rdahi=%rdahi rdalo=%rdalo } +@vabav .... .... .. size:2 .... rda:4 .... .... .... &vabav qn=%qn qm=%qm + +VABAV_S 111 0 1110 10 .. ... 0 .... 1111 . 0 . 0 ... 1 @vabav +VABAV_U 111 1 1110 10 .. ... 0 .... 1111 . 0 . 0 ... 1 @vabav + # Logical immediate operations (1 reg and modified-immediate) # The cmode/op bits here decode VORR/VBIC/VMOV/VMVN, but diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VMAXMINV(vminavb, 1, int8_t, uint8_t, do_mina) DO_VMAXMINV(vminavh, 2, int16_t, uint16_t, do_mina) DO_VMAXMINV(vminavw, 4, int32_t, uint32_t, do_mina) +#define DO_VABAV(OP, ESIZE, TYPE) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + void *vm, uint32_t ra) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *m = vm, *n = vn; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + int64_t n0 = n[H##ESIZE(e)]; \ + int64_t m0 = m[H##ESIZE(e)]; \ + uint32_t r = n0 >= m0 ? (n0 - m0) : (m0 - n0); \ + ra += r; \ + } \ + } \ + mve_advance_vpt(env); \ + return ra; \ + } + +DO_VABAV(vabavsb, 1, int8_t) +DO_VABAV(vabavsh, 2, int16_t) +DO_VABAV(vabavsw, 4, int32_t) +DO_VABAV(vabavub, 1, uint8_t) +DO_VABAV(vabavuh, 2, uint16_t) +DO_VABAV(vabavuw, 4, uint32_t) + #define DO_VADDLV(OP, TYPE, LTYPE) \ uint64_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vm, \ uint64_t ra) \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TCGv_i32); typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenVABAVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ DO_VMAXV(VMAXAV, vmaxav) DO_VMAXV(VMINV_S, vminvs) DO_VMAXV(VMINV_U, vminvu) DO_VMAXV(VMINAV, vminav) + +static bool do_vabav(DisasContext *s, arg_vabav *a, MVEGenVABAVFn *fn) +{ + /* Absolute difference accumulated across vector */ + TCGv_ptr qn, qm; + TCGv_i32 rda; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qm | a->qn) || + !fn || a->rda == 13 || a->rda == 15) { + /* Rda cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qm = mve_qreg_ptr(a->qm); + qn = mve_qreg_ptr(a->qn); + rda = load_reg(s, a->rda); + fn(rda, cpu_env, qn, qm, rda); + store_reg(s, a->rda, rda); + tcg_temp_free_ptr(qm); + tcg_temp_free_ptr(qn); + mve_update_eci(s); + return true; +} + +#define DO_VABAV(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vabav *a) \ + { \ + static MVEGenVABAVFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + gen_helper_mve_##FN##w, \ + NULL, \ + }; \ + return do_vabav(s, a, fns[a->size]); \ + } + +DO_VABAV(VABAV_S, vabavs) +DO_VABAV(VABAV_U, vabavu) -- 2.20.1 Implement the MVE narrowing move insns VMOVN, VQMOVN and VQMOVUN. These take a double-width input, narrow it (possibly saturating) and store the result to either the top or bottom half of the output element. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 20 ++++++++++ target/arm/mve.decode | 12 ++++++ target/arm/mve_helper.c | 78 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 22 +++++++++++ 4 files changed, 132 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegs, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmovnth, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqmovunbb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovunbh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovuntb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovunth, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqmovnbsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovnbsh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntsh, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqmovnbub, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovnbuh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntub, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqmovntuh, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_4(mve_vand, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vbic, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vorr, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_BS 111 0 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h + VQMOVUNB 111 0 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op + VQMOVN_BS 111 0 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op + VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_BU 111 1 1110 0 . 11 .. 01 ... 0 1110 0 0 . 0 ... 1 @2_shll_esize_h + VMOVNB 111 1 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op + VQMOVN_BU 111 1 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op + VMULH_U 111 1 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TS 111 0 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h + VQMOVUNT 111 0 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op + VQMOVN_TS 111 0 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op + VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_b VSHLL_TU 111 1 1110 0 . 11 .. 01 ... 1 1110 0 0 . 0 ... 1 @2_shll_esize_h + VMOVNT 111 1 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op + VQMOVN_TU 111 1 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op + VRMULH_U 111 1 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSHRN_SAT_UH(vqrshrnb_uh, vqrshrnt_uh, DO_RSHRN_UH) DO_VSHRN_SAT_SB(vqrshrunbb, vqrshruntb, DO_RSHRUN_B) DO_VSHRN_SAT_SH(vqrshrunbh, vqrshrunth, DO_RSHRUN_H) +#define DO_VMOVN(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + LTYPE *m = vm; \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + unsigned le; \ + mask >>= ESIZE * TOP; \ + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ + mergemask(&d[H##ESIZE(le * 2 + TOP)], \ + m[H##LESIZE(le)], mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VMOVN(vmovnbb, false, 1, uint8_t, 2, uint16_t) +DO_VMOVN(vmovnbh, false, 2, uint16_t, 4, uint32_t) +DO_VMOVN(vmovntb, true, 1, uint8_t, 2, uint16_t) +DO_VMOVN(vmovnth, true, 2, uint16_t, 4, uint32_t) + +#define DO_VMOVN_SAT(OP, TOP, ESIZE, TYPE, LESIZE, LTYPE, FN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + LTYPE *m = vm; \ + TYPE *d = vd; \ + uint16_t mask = mve_element_mask(env); \ + bool qc = false; \ + unsigned le; \ + mask >>= ESIZE * TOP; \ + for (le = 0; le < 16 / LESIZE; le++, mask >>= LESIZE) { \ + bool sat = false; \ + TYPE r = FN(m[H##LESIZE(le)], &sat); \ + mergemask(&d[H##ESIZE(le * 2 + TOP)], r, mask); \ + qc |= sat & mask & 1; \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VMOVN_SAT_UB(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 1, uint8_t, 2, uint16_t, FN) \ + DO_VMOVN_SAT(TOP, true, 1, uint8_t, 2, uint16_t, FN) + +#define DO_VMOVN_SAT_UH(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 2, uint16_t, 4, uint32_t, FN) \ + DO_VMOVN_SAT(TOP, true, 2, uint16_t, 4, uint32_t, FN) + +#define DO_VMOVN_SAT_SB(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 1, int8_t, 2, int16_t, FN) \ + DO_VMOVN_SAT(TOP, true, 1, int8_t, 2, int16_t, FN) + +#define DO_VMOVN_SAT_SH(BOP, TOP, FN) \ + DO_VMOVN_SAT(BOP, false, 2, int16_t, 4, int32_t, FN) \ + DO_VMOVN_SAT(TOP, true, 2, int16_t, 4, int32_t, FN) + +#define DO_VQMOVN_SB(N, SATP) \ + do_sat_bhs((int64_t)(N), INT8_MIN, INT8_MAX, SATP) +#define DO_VQMOVN_UB(N, SATP) \ + do_sat_bhs((uint64_t)(N), 0, UINT8_MAX, SATP) +#define DO_VQMOVUN_B(N, SATP) \ + do_sat_bhs((int64_t)(N), 0, UINT8_MAX, SATP) + +#define DO_VQMOVN_SH(N, SATP) \ + do_sat_bhs((int64_t)(N), INT16_MIN, INT16_MAX, SATP) +#define DO_VQMOVN_UH(N, SATP) \ + do_sat_bhs((uint64_t)(N), 0, UINT16_MAX, SATP) +#define DO_VQMOVUN_H(N, SATP) \ + do_sat_bhs((int64_t)(N), 0, UINT16_MAX, SATP) + +DO_VMOVN_SAT_SB(vqmovnbsb, vqmovntsb, DO_VQMOVN_SB) +DO_VMOVN_SAT_SH(vqmovnbsh, vqmovntsh, DO_VQMOVN_SH) +DO_VMOVN_SAT_UB(vqmovnbub, vqmovntub, DO_VQMOVN_UB) +DO_VMOVN_SAT_UH(vqmovnbuh, vqmovntuh, DO_VQMOVN_UH) +DO_VMOVN_SAT_SB(vqmovunbb, vqmovuntb, DO_VQMOVUN_B) +DO_VMOVN_SAT_SH(vqmovunbh, vqmovunth, DO_VQMOVUN_H) + uint32_t HELPER(mve_vshlc)(CPUARMState *env, void *vd, uint32_t rdm, uint32_t shift) { diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_1OP(VCLS, vcls) DO_1OP(VABS, vabs) DO_1OP(VNEG, vneg) +/* Narrowing moves: only size 0 and 1 are valid */ +#define DO_VMOVN(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_1op *a) \ + { \ + static MVEGenOneOpFn * const fns[] = { \ + gen_helper_mve_##FN##b, \ + gen_helper_mve_##FN##h, \ + NULL, \ + NULL, \ + }; \ + return do_1op(s, a, fns[a->size]); \ + } + +DO_VMOVN(VMOVNB, vmovnb) +DO_VMOVN(VMOVNT, vmovnt) +DO_VMOVN(VQMOVUNB, vqmovunb) +DO_VMOVN(VQMOVUNT, vqmovunt) +DO_VMOVN(VQMOVN_BS, vqmovnbs) +DO_VMOVN(VQMOVN_TS, vqmovnts) +DO_VMOVN(VQMOVN_BU, vqmovnbu) +DO_VMOVN(VQMOVN_TU, vqmovntu) + static bool trans_VREV16(DisasContext *s, arg_1op *a) { static MVEGenOneOpFn * const fns[] = { -- 2.20.1 The MVEGenDualAccOpFn is a bit misnamed, since it is used for the "long dual accumulate" operations that use a 64-bit accumulator. Rename it to MVEGenLongDualAccOpFn so we can use the former name for the 32-bit accumulator insns. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-mve.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenTwoOpShiftFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); -typedef void MVEGenDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); +typedef void MVEGenLongDualAccOpFn(TCGv_i64, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVADDVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpImmFn(TCGv_ptr, TCGv_ptr, TCGv_i64); typedef void MVEGenVIDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32); @@ -XXX,XX +XXX,XX @@ static bool trans_VQDMULLT_scalar(DisasContext *s, arg_2scalar *a) } static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a, - MVEGenDualAccOpFn *fn) + MVEGenLongDualAccOpFn *fn) { TCGv_ptr qn, qm; TCGv_i64 rda; @@ -XXX,XX +XXX,XX @@ static bool do_long_dual_acc(DisasContext *s, arg_vmlaldav *a, static bool trans_VMLALDAV_S(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[4][2] = { + static MVEGenLongDualAccOpFn * const fns[4][2] = { { NULL, NULL }, { gen_helper_mve_vmlaldavsh, gen_helper_mve_vmlaldavxsh }, { gen_helper_mve_vmlaldavsw, gen_helper_mve_vmlaldavxsw }, @@ -XXX,XX +XXX,XX @@ static bool trans_VMLALDAV_S(DisasContext *s, arg_vmlaldav *a) static bool trans_VMLALDAV_U(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[4][2] = { + static MVEGenLongDualAccOpFn * const fns[4][2] = { { NULL, NULL }, { gen_helper_mve_vmlaldavuh, NULL }, { gen_helper_mve_vmlaldavuw, NULL }, @@ -XXX,XX +XXX,XX @@ static bool trans_VMLALDAV_U(DisasContext *s, arg_vmlaldav *a) static bool trans_VMLSLDAV(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[4][2] = { + static MVEGenLongDualAccOpFn * const fns[4][2] = { { NULL, NULL }, { gen_helper_mve_vmlsldavsh, gen_helper_mve_vmlsldavxsh }, { gen_helper_mve_vmlsldavsw, gen_helper_mve_vmlsldavxsw }, @@ -XXX,XX +XXX,XX @@ static bool trans_VMLSLDAV(DisasContext *s, arg_vmlaldav *a) static bool trans_VRMLALDAVH_S(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[] = { + static MVEGenLongDualAccOpFn * const fns[] = { gen_helper_mve_vrmlaldavhsw, gen_helper_mve_vrmlaldavhxsw, }; return do_long_dual_acc(s, a, fns[a->x]); @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLALDAVH_S(DisasContext *s, arg_vmlaldav *a) static bool trans_VRMLALDAVH_U(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[] = { + static MVEGenLongDualAccOpFn * const fns[] = { gen_helper_mve_vrmlaldavhuw, NULL, }; return do_long_dual_acc(s, a, fns[a->x]); @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLALDAVH_U(DisasContext *s, arg_vmlaldav *a) static bool trans_VRMLSLDAVH(DisasContext *s, arg_vmlaldav *a) { - static MVEGenDualAccOpFn * const fns[] = { + static MVEGenLongDualAccOpFn * const fns[] = { gen_helper_mve_vrmlsldavhsw, gen_helper_mve_vrmlsldavhxsw, }; return do_long_dual_acc(s, a, fns[a->x]); -- 2.20.1 Implement the MVE VMLADAV and VMLSLDAV insns. Like the VMLALDAV and VMLSLDAV insns already implemented, these accumulate multiplied vector elements; but they accumulate a 32-bit result rather than a 64-bit one. Note that these encodings overlap with what would be RdaHi=0b111 for VMLALDAV, VMLSLDAV, VRMLALDAVH and VRMLSLDAVH. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 17 ++++++++++ target/arm/mve.decode | 33 +++++++++++++++++--- target/arm/mve_helper.c | 41 ++++++++++++++++++++++++ target/arm/translate-mve.c | 64 ++++++++++++++++++++++++++++++++++++++ 4 files changed, 150 insertions(+), 5 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vrmlaldavhuw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vrmlsldavhsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vrmlsldavhxsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) +DEF_HELPER_FLAGS_4(mve_vmladavsb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavub, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavuh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavuw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vmladavsxb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsxh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmladavsxw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavxb, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavxh, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlsdavxw, TCG_CALL_NO_WG, i32, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vaddvsb, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvub, TCG_CALL_NO_WG, i32, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vaddvsh, TCG_CALL_NO_WG, i32, env, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VDUP 1110 1110 1 0 10 ... 0 .... 1011 . 0 0 1 0000 @vdup size=2 %size_16 16:1 !function=plus_1 &vmlaldav rdahi rdalo size qn qm x a +&vmladav rda size qn qm x a @vmlaldav .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=%size_16 &vmlaldav @vmlaldav_nosz .... .... . ... ... . ... x:1 .... .. a:1 . qm:3 . \ qn=%qn rdahi=%rdahi rdalo=%rdalo size=0 &vmlaldav -VMLALDAV_S 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav -VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +@vmladav .... .... .... ... . ... x:1 .... . . a:1 . qm:3 . \ + qn=%qn rda=%rdalo size=%size_16 &vmladav +@vmladav_nosz .... .... .... ... . ... x:1 .... . . a:1 . qm:3 . \ + qn=%qn rda=%rdalo size=0 &vmladav -VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav +{ + VMLADAV_S 1110 1110 1111 ... . ... . 1110 . 0 . 0 ... 0 @vmladav + VMLALDAV_S 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +} +{ + VMLADAV_U 1111 1110 1111 ... . ... . 1110 . 0 . 0 ... 0 @vmladav + VMLALDAV_U 1111 1110 1 ... ... . ... . 1110 . 0 . 0 ... 0 @vmlaldav +} + +{ + VMLSDAV 1110 1110 1111 ... . ... . 1110 . 0 . 0 ... 1 @vmladav + VMLSLDAV 1110 1110 1 ... ... . ... . 1110 . 0 . 0 ... 1 @vmlaldav +} + +{ + VMLSDAV 1111 1110 1111 ... 0 ... . 1110 . 0 . 0 ... 1 @vmladav_nosz + VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz +} + +VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz +VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 1 @vmladav_nosz { VMAXV_S 1110 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv VMINV_S 1110 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv VMAXAV 1110 1110 1110 .. 00 .... 1111 0 0 . 0 ... 0 @vmaxv VMINAV 1110 1110 1110 .. 00 .... 1111 1 0 . 0 ... 0 @vmaxv + VMLADAV_S 1110 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz VRMLALDAVH_S 1110 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz } { VMAXV_U 1111 1110 1110 .. 10 .... 1111 0 0 . 0 ... 0 @vmaxv VMINV_U 1111 1110 1110 .. 10 .... 1111 1 0 . 0 ... 0 @vmaxv + VMLADAV_U 1111 1110 1111 ... 0 ... . 1111 . 0 . 0 ... 0 @vmladav_nosz VRMLALDAVH_U 1111 1110 1 ... ... 0 ... . 1111 . 0 . 0 ... 0 @vmlaldav_nosz } -VRMLSLDAVH 1111 1110 1 ... ... 0 ... . 1110 . 0 . 0 ... 1 @vmlaldav_nosz - # Scalar operations VADD_scalar 1110 1110 0 . .. ... 1 ... 0 1111 . 100 .... @2scalar diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_LDAV(vmlsldavxsh, 2, int16_t, true, +=, -=) DO_LDAV(vmlsldavsw, 4, int32_t, false, +=, -=) DO_LDAV(vmlsldavxsw, 4, int32_t, true, +=, -=) +/* + * Multiply add dual accumulate ops + */ +#define DO_DAV(OP, ESIZE, TYPE, XCHG, EVENACC, ODDACC) \ + uint32_t HELPER(glue(mve_, OP))(CPUARMState *env, void *vn, \ + void *vm, uint32_t a) \ + { \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + TYPE *n = vn, *m = vm; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + if (mask & 1) { \ + if (e & 1) { \ + a ODDACC \ + n[H##ESIZE(e - 1 * XCHG)] * m[H##ESIZE(e)]; \ + } else { \ + a EVENACC \ + n[H##ESIZE(e + 1 * XCHG)] * m[H##ESIZE(e)]; \ + } \ + } \ + } \ + mve_advance_vpt(env); \ + return a; \ + } + +#define DO_DAV_S(INSN, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##b, 1, int8_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##h, 2, int16_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##w, 4, int32_t, XCHG, EVENACC, ODDACC) + +#define DO_DAV_U(INSN, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##b, 1, uint8_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##h, 2, uint16_t, XCHG, EVENACC, ODDACC) \ + DO_DAV(INSN##w, 4, uint32_t, XCHG, EVENACC, ODDACC) + +DO_DAV_S(vmladavs, false, +=, +=) +DO_DAV_U(vmladavu, false, +=, +=) +DO_DAV_S(vmlsdav, false, +=, -=) +DO_DAV_S(vmladavsx, true, +=, +=) +DO_DAV_S(vmlsdavx, true, +=, -=) + /* * Rounding multiply add long dual accumulate high. In the pseudocode * this is implemented with a 72-bit internal accumulator value of which diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ typedef void MVEGenVIWDUPFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_i32, TCGv_i32, TC typedef void MVEGenCmpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenScalarCmpFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenVABAVFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenDualAccOpFn(TCGv_i32, TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); /* Return the offset of a Qn register (same semantics as aa32_vfp_qreg()) */ static inline long mve_qreg_offset(unsigned reg) @@ -XXX,XX +XXX,XX @@ static bool trans_VRMLSLDAVH(DisasContext *s, arg_vmlaldav *a) return do_long_dual_acc(s, a, fns[a->x]); } +static bool do_dual_acc(DisasContext *s, arg_vmladav *a, MVEGenDualAccOpFn *fn) +{ + TCGv_ptr qn, qm; + TCGv_i32 rda; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qn) || + !fn) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + qn = mve_qreg_ptr(a->qn); + qm = mve_qreg_ptr(a->qm); + + /* + * This insn is subject to beat-wise execution. Partial execution + * of an A=0 (no-accumulate) insn which does not execute the first + * beat must start with the current rda value, not 0. + */ + if (a->a || mve_skip_first_beat(s)) { + rda = load_reg(s, a->rda); + } else { + rda = tcg_const_i32(0); + } + + fn(rda, cpu_env, qn, qm, rda); + store_reg(s, a->rda, rda); + tcg_temp_free_ptr(qn); + tcg_temp_free_ptr(qm); + + mve_update_eci(s); + return true; +} + +#define DO_DUAL_ACC(INSN, FN) \ + static bool trans_##INSN(DisasContext *s, arg_vmladav *a) \ + { \ + static MVEGenDualAccOpFn * const fns[4][2] = { \ + { gen_helper_mve_##FN##b, gen_helper_mve_##FN##xb }, \ + { gen_helper_mve_##FN##h, gen_helper_mve_##FN##xh }, \ + { gen_helper_mve_##FN##w, gen_helper_mve_##FN##xw }, \ + { NULL, NULL }, \ + }; \ + return do_dual_acc(s, a, fns[a->size][a->x]); \ + } + +DO_DUAL_ACC(VMLADAV_S, vmladavs) +DO_DUAL_ACC(VMLSDAV, vmlsdav) + +static bool trans_VMLADAV_U(DisasContext *s, arg_vmladav *a) +{ + static MVEGenDualAccOpFn * const fns[4][2] = { + { gen_helper_mve_vmladavub, NULL }, + { gen_helper_mve_vmladavuh, NULL }, + { gen_helper_mve_vmladavuw, NULL }, + { NULL, NULL }, + }; + return do_dual_acc(s, a, fns[a->size][a->x]); +} + static void gen_vpst(DisasContext *s, uint32_t mask) { /* -- 2.20.1 Implement the MVE VMLA insn, which multiplies a vector by a scalar and accumulates into another vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 4 ++++ target/arm/mve.decode | 1 + target/arm/mve_helper.c | 5 +++++ target/arm/translate-mve.c | 1 + 4 files changed, 11 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vqdmullb_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i3 DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vqdmullt_scalarw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlab, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlah, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vmlaw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vmlasb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlash, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlasw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VQDMULH_scalar 1110 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar # The U bit (28) is don't-care because it does not affect the result +VMLA 111- 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar # Vector add across vector diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, DO_QRDMULH_B) DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H) DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W) +/* Vector by scalar plus vector */ +#define DO_VMLA(D, N, M) ((N) * (M) + (D)) + +DO_2OP_ACC_SCALAR_U(vmla, DO_VMLA) + /* Vector by vector plus scalar */ #define DO_VMLAS(D, N, M) ((N) * (D) + (M)) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SCALAR(VQSUB_U_scalar, vqsubu_scalar) DO_2OP_SCALAR(VQDMULH_scalar, vqdmulh_scalar) DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar) DO_2OP_SCALAR(VBRSR, vbrsr) +DO_2OP_SCALAR(VMLA, vmla) DO_2OP_SCALAR(VMLAS, vmlas) static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a) -- 2.20.1 Implement the MVE saturating doubling multiply accumulate insns VQDMLAH, VQRDMLAH, VQDMLASH and VQRDMLASH. These perform a multiply, double, add the accumulator shifted by the element size, possibly round, saturate to twice the element size, then take the high half of the result. The *MLAH insns do vector * scalar + vector, and the *MLASH insns do vector * vector + scalar. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 16 +++++++ target/arm/mve.decode | 5 ++ target/arm/mve_helper.c | 95 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 4 ++ 4 files changed, 120 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vmlasb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlash, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vmlasw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlahb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlahh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlahw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrdmlahb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlahh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlahw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqdmlashb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlashh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqdmlashw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vqrdmlashb, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlashh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vqrdmlashw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(mve_vmlaldavsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavsw, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) DEF_HELPER_FLAGS_4(mve_vmlaldavxsh, TCG_CALL_NO_WG, i64, env, ptr, ptr, i64) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VQRDMULH_scalar 1111 1110 0 . .. ... 1 ... 0 1110 . 110 .... @2scalar VMLA 111- 1110 0 . .. ... 1 ... 0 1110 . 100 .... @2scalar VMLAS 111- 1110 0 . .. ... 1 ... 1 1110 . 100 .... @2scalar +VQRDMLAH 1110 1110 0 . .. ... 0 ... 0 1110 . 100 .... @2scalar +VQRDMLASH 1110 1110 0 . .. ... 0 ... 1 1110 . 100 .... @2scalar +VQDMLAH 1110 1110 0 . .. ... 0 ... 0 1110 . 110 .... @2scalar +VQDMLASH 1110 1110 0 . .. ... 0 ... 1 1110 . 110 .... @2scalar + # Vector add across vector { VADDV 111 u:1 1110 1111 size:2 01 ... 0 1111 0 0 a:1 0 qm:3 0 rda=%rdalo diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VQDMLADH_OP(vqrdmlsdhxw, 4, int32_t, 1, 1, do_vqdmlsdh_w) mve_advance_vpt(env); \ } +#define DO_2OP_SAT_ACC_SCALAR(OP, ESIZE, TYPE, FN) \ + void HELPER(glue(mve_, OP))(CPUARMState *env, void *vd, void *vn, \ + uint32_t rm) \ + { \ + TYPE *d = vd, *n = vn; \ + TYPE m = rm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + bool qc = false; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + bool sat = false; \ + mergemask(&d[H##ESIZE(e)], \ + FN(d[H##ESIZE(e)], n[H##ESIZE(e)], m, &sat), \ + mask); \ + qc |= sat & mask & 1; \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + /* provide unsigned 2-op scalar helpers for all sizes */ #define DO_2OP_SCALAR_U(OP, FN) \ DO_2OP_SCALAR(OP##b, 1, uint8_t, FN) \ @@ -XXX,XX +XXX,XX @@ DO_2OP_SAT_SCALAR(vqrdmulh_scalarb, 1, int8_t, DO_QRDMULH_B) DO_2OP_SAT_SCALAR(vqrdmulh_scalarh, 2, int16_t, DO_QRDMULH_H) DO_2OP_SAT_SCALAR(vqrdmulh_scalarw, 4, int32_t, DO_QRDMULH_W) +static int8_t do_vqdmlah_b(int8_t a, int8_t b, int8_t c, int round, bool *sat) +{ + int64_t r = (int64_t)a * b * 2 + ((int64_t)c << 8) + (round << 7); + return do_sat_bhw(r, INT16_MIN, INT16_MAX, sat) >> 8; +} + +static int16_t do_vqdmlah_h(int16_t a, int16_t b, int16_t c, + int round, bool *sat) +{ + int64_t r = (int64_t)a * b * 2 + ((int64_t)c << 16) + (round << 15); + return do_sat_bhw(r, INT32_MIN, INT32_MAX, sat) >> 16; +} + +static int32_t do_vqdmlah_w(int32_t a, int32_t b, int32_t c, + int round, bool *sat) +{ + /* + * Architecturally we should do the entire add, double, round + * and then check for saturation. We do three saturating adds, + * but we need to be careful about the order. If the first + * m1 + m2 saturates then it's impossible for the *2+rc to + * bring it back into the non-saturated range. However, if + * m1 + m2 is negative then it's possible that doing the doubling + * would take the intermediate result below INT64_MAX and the + * addition of the rounding constant then brings it back in range. + * So we add half the rounding constant and half the "c << esize" + * before doubling rather than adding the rounding constant after + * the doubling. + */ + int64_t m1 = (int64_t)a * b; + int64_t m2 = (int64_t)c << 31; + int64_t r; + if (sadd64_overflow(m1, m2, &r) || + sadd64_overflow(r, (round << 30), &r) || + sadd64_overflow(r, r, &r)) { + *sat = true; + return r < 0 ? INT32_MAX : INT32_MIN; + } + return r >> 32; +} + +/* + * The *MLAH insns are vector * scalar + vector; + * the *MLASH insns are vector * vector + scalar + */ +#define DO_VQDMLAH_B(D, N, M, S) do_vqdmlah_b(N, M, D, 0, S) +#define DO_VQDMLAH_H(D, N, M, S) do_vqdmlah_h(N, M, D, 0, S) +#define DO_VQDMLAH_W(D, N, M, S) do_vqdmlah_w(N, M, D, 0, S) +#define DO_VQRDMLAH_B(D, N, M, S) do_vqdmlah_b(N, M, D, 1, S) +#define DO_VQRDMLAH_H(D, N, M, S) do_vqdmlah_h(N, M, D, 1, S) +#define DO_VQRDMLAH_W(D, N, M, S) do_vqdmlah_w(N, M, D, 1, S) + +#define DO_VQDMLASH_B(D, N, M, S) do_vqdmlah_b(N, D, M, 0, S) +#define DO_VQDMLASH_H(D, N, M, S) do_vqdmlah_h(N, D, M, 0, S) +#define DO_VQDMLASH_W(D, N, M, S) do_vqdmlah_w(N, D, M, 0, S) +#define DO_VQRDMLASH_B(D, N, M, S) do_vqdmlah_b(N, D, M, 1, S) +#define DO_VQRDMLASH_H(D, N, M, S) do_vqdmlah_h(N, D, M, 1, S) +#define DO_VQRDMLASH_W(D, N, M, S) do_vqdmlah_w(N, D, M, 1, S) + +DO_2OP_SAT_ACC_SCALAR(vqdmlahb, 1, int8_t, DO_VQDMLAH_B) +DO_2OP_SAT_ACC_SCALAR(vqdmlahh, 2, int16_t, DO_VQDMLAH_H) +DO_2OP_SAT_ACC_SCALAR(vqdmlahw, 4, int32_t, DO_VQDMLAH_W) +DO_2OP_SAT_ACC_SCALAR(vqrdmlahb, 1, int8_t, DO_VQRDMLAH_B) +DO_2OP_SAT_ACC_SCALAR(vqrdmlahh, 2, int16_t, DO_VQRDMLAH_H) +DO_2OP_SAT_ACC_SCALAR(vqrdmlahw, 4, int32_t, DO_VQRDMLAH_W) + +DO_2OP_SAT_ACC_SCALAR(vqdmlashb, 1, int8_t, DO_VQDMLASH_B) +DO_2OP_SAT_ACC_SCALAR(vqdmlashh, 2, int16_t, DO_VQDMLASH_H) +DO_2OP_SAT_ACC_SCALAR(vqdmlashw, 4, int32_t, DO_VQDMLASH_W) +DO_2OP_SAT_ACC_SCALAR(vqrdmlashb, 1, int8_t, DO_VQRDMLASH_B) +DO_2OP_SAT_ACC_SCALAR(vqrdmlashh, 2, int16_t, DO_VQRDMLASH_H) +DO_2OP_SAT_ACC_SCALAR(vqrdmlashw, 4, int32_t, DO_VQRDMLASH_W) + /* Vector by scalar plus vector */ #define DO_VMLA(D, N, M) ((N) * (M) + (D)) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_2OP_SCALAR(VQRDMULH_scalar, vqrdmulh_scalar) DO_2OP_SCALAR(VBRSR, vbrsr) DO_2OP_SCALAR(VMLA, vmla) DO_2OP_SCALAR(VMLAS, vmlas) +DO_2OP_SCALAR(VQDMLAH, vqdmlah) +DO_2OP_SCALAR(VQRDMLAH, vqrdmlah) +DO_2OP_SCALAR(VQDMLASH, vqdmlash) +DO_2OP_SCALAR(VQRDMLASH, vqrdmlash) static bool trans_VQDMULLB_scalar(DisasContext *s, arg_2scalar *a) { -- 2.20.1 Implement the MVE 1-operand saturating operations VQABS and VQNEG. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 8 ++++++++ target/arm/mve.decode | 3 +++ target/arm/mve_helper.c | 37 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 50 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vfnegs, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqabsb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqabsh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqabsw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vqnegb, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vqnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VABS_fp 1111 1111 1 . 11 .. 01 ... 0 0111 01 . 0 ... 0 @1op VNEG 1111 1111 1 . 11 .. 01 ... 0 0011 11 . 0 ... 0 @1op VNEG_fp 1111 1111 1 . 11 .. 01 ... 0 0111 11 . 0 ... 0 @1op +VQABS 1111 1111 1 . 11 .. 00 ... 0 0111 01 . 0 ... 0 @1op +VQNEG 1111 1111 1 . 11 .. 00 ... 0 0111 11 . 0 ... 0 @1op + &vdup qd rt size # Qd is in the fields usually named Qn @vdup .... .... . . .. ... . rt:4 .... . . . . .... qd=%qn &vdup diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void *vn, void *vm) } mve_advance_vpt(env); } + +#define DO_1OP_SAT(OP, ESIZE, TYPE, FN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + TYPE *d = vd, *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + bool qc = false; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + bool sat = false; \ + mergemask(&d[H##ESIZE(e)], FN(m[H##ESIZE(e)], &sat), mask); \ + qc |= sat & mask & 1; \ + } \ + if (qc) { \ + env->vfp.qc[0] = qc; \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VQABS_B(N, SATP) \ + do_sat_bhs(DO_ABS((int64_t)N), INT8_MIN, INT8_MAX, SATP) +#define DO_VQABS_H(N, SATP) \ + do_sat_bhs(DO_ABS((int64_t)N), INT16_MIN, INT16_MAX, SATP) +#define DO_VQABS_W(N, SATP) \ + do_sat_bhs(DO_ABS((int64_t)N), INT32_MIN, INT32_MAX, SATP) + +#define DO_VQNEG_B(N, SATP) do_sat_bhs(-(int64_t)N, INT8_MIN, INT8_MAX, SATP) +#define DO_VQNEG_H(N, SATP) do_sat_bhs(-(int64_t)N, INT16_MIN, INT16_MAX, SATP) +#define DO_VQNEG_W(N, SATP) do_sat_bhs(-(int64_t)N, INT32_MIN, INT32_MAX, SATP) + +DO_1OP_SAT(vqabsb, 1, int8_t, DO_VQABS_B) +DO_1OP_SAT(vqabsh, 2, int16_t, DO_VQABS_H) +DO_1OP_SAT(vqabsw, 4, int32_t, DO_VQABS_W) + +DO_1OP_SAT(vqnegb, 1, int8_t, DO_VQNEG_B) +DO_1OP_SAT(vqnegh, 2, int16_t, DO_VQNEG_H) +DO_1OP_SAT(vqnegw, 4, int32_t, DO_VQNEG_W) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_1OP(VCLZ, vclz) DO_1OP(VCLS, vcls) DO_1OP(VABS, vabs) DO_1OP(VNEG, vneg) +DO_1OP(VQABS, vqabs) +DO_1OP(VQNEG, vqneg) /* Narrowing moves: only size 0 and 1 are valid */ #define DO_VMOVN(INSN, FN) \ -- 2.20.1 Implement the MVE VMAXA and VMINA insns, which take the absolute value of the signed elements in the input vector and then accumulate the unsigned max or min into the destination vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 8 ++++++++ target/arm/mve.decode | 4 ++++ target/arm/mve_helper.c | 26 ++++++++++++++++++++++++++ target/arm/translate-mve.c | 2 ++ 4 files changed, 40 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vqnegb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vqnegh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vqnegw, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmaxab, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmaxah, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vmaxaw, TCG_CALL_NO_WG, void, env, ptr, ptr) + +DEF_HELPER_FLAGS_3(mve_vminab, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vminah, TCG_CALL_NO_WG, void, env, ptr, ptr) +DEF_HELPER_FLAGS_3(mve_vminaw, TCG_CALL_NO_WG, void, env, ptr, ptr) + DEF_HELPER_FLAGS_3(mve_vmovnbb, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovnbh, TCG_CALL_NO_WG, void, env, ptr, ptr) DEF_HELPER_FLAGS_3(mve_vmovntb, TCG_CALL_NO_WG, void, env, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VQMOVUNB 111 0 1110 0 . 11 .. 01 ... 0 1110 1 0 . 0 ... 1 @1op VQMOVN_BS 111 0 1110 0 . 11 .. 11 ... 0 1110 0 0 . 0 ... 1 @1op + VMAXA 111 0 1110 0 . 11 .. 11 ... 0 1110 1 0 . 0 ... 1 @1op + VMULH_S 111 0 1110 0 . .. ...1 ... 0 1110 . 0 . 0 ... 1 @2op } @@ -XXX,XX +XXX,XX @@ VMUL 1110 1111 0 . .. ... 0 ... 0 1001 . 1 . 1 ... 0 @2op VQMOVUNT 111 0 1110 0 . 11 .. 01 ... 1 1110 1 0 . 0 ... 1 @1op VQMOVN_TS 111 0 1110 0 . 11 .. 11 ... 1 1110 0 0 . 0 ... 1 @1op + VMINA 111 0 1110 0 . 11 .. 11 ... 1 1110 1 0 . 0 ... 1 @1op + VRMULH_S 111 0 1110 0 . .. ...1 ... 1 1110 . 0 . 0 ... 1 @2op } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_1OP_SAT(vqabsw, 4, int32_t, DO_VQABS_W) DO_1OP_SAT(vqnegb, 1, int8_t, DO_VQNEG_B) DO_1OP_SAT(vqnegh, 2, int16_t, DO_VQNEG_H) DO_1OP_SAT(vqnegw, 4, int32_t, DO_VQNEG_W) + +/* + * VMAXA, VMINA: vd is unsigned; vm is signed, and we take its + * absolute value; we then do an unsigned comparison. + */ +#define DO_VMAXMINA(OP, ESIZE, STYPE, UTYPE, FN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ + { \ + UTYPE *d = vd; \ + STYPE *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + UTYPE r = DO_ABS(m[H##ESIZE(e)]); \ + r = FN(d[H##ESIZE(e)], r); \ + mergemask(&d[H##ESIZE(e)], r, mask); \ + } \ + mve_advance_vpt(env); \ + } + +DO_VMAXMINA(vmaxab, 1, int8_t, uint8_t, DO_MAX) +DO_VMAXMINA(vmaxah, 2, int16_t, uint16_t, DO_MAX) +DO_VMAXMINA(vmaxaw, 4, int32_t, uint32_t, DO_MAX) +DO_VMAXMINA(vminab, 1, int8_t, uint8_t, DO_MIN) +DO_VMAXMINA(vminah, 2, int16_t, uint16_t, DO_MIN) +DO_VMAXMINA(vminaw, 4, int32_t, uint32_t, DO_MIN) diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ DO_1OP(VABS, vabs) DO_1OP(VNEG, vneg) DO_1OP(VQABS, vqabs) DO_1OP(VQNEG, vqneg) +DO_1OP(VMAXA, vmaxa) +DO_1OP(VMINA, vmina) /* Narrowing moves: only size 0 and 1 are valid */ #define DO_VMOVN(INSN, FN) \ -- 2.20.1 Implement the MVE VMOV forms that move data between 2 general-purpose registers and 2 32-bit lanes in a vector register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/translate-a32.h | 1 + target/arm/mve.decode | 4 ++ target/arm/translate-mve.c | 85 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-vfp.c | 2 +- 4 files changed, 91 insertions(+), 1 deletion(-) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ void gen_rev16(TCGv_i32 dest, TCGv_i32 var); void clear_eci_state(DisasContext *s); bool mve_eci_check(DisasContext *s); void mve_update_and_store_eci(DisasContext *s); +bool mve_skip_vmov(DisasContext *s, int vn, int index, int size); static inline TCGv_i32 load_cpu_offset(int offset) { diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111101 ....... @vldr_vstr \ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111110 ....... @vldr_vstr \ size=2 p=1 +# Moves between 2 32-bit vector lanes and 2 general purpose registers +VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd +VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd + # Vector 2-op VAND 1110 1111 0 . 00 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz VBIC 1110 1111 0 . 01 ... 0 ... 0 0001 . 1 . 1 ... 0 @2op_nosz diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool do_vabav(DisasContext *s, arg_vabav *a, MVEGenVABAVFn *fn) DO_VABAV(VABAV_S, vabavs) DO_VABAV(VABAV_U, vabavu) + +static bool trans_VMOV_to_2gp(DisasContext *s, arg_VMOV_to_2gp *a) +{ + /* + * VMOV two 32-bit vector lanes to two general-purpose registers. + * This insn is not predicated but it is subject to beat-wise + * execution if it is not in an IT block. For us this means + * only that if PSR.ECI says we should not be executing the beat + * corresponding to the lane of the vector register being accessed + * then we should skip perfoming the move, and that we need to do + * the usual check for bad ECI state and advance of ECI state. + * (If PSR.ECI is non-zero then we cannot be in an IT block.) + */ + TCGv_i32 tmp; + int vd; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd) || + a->rt == 13 || a->rt == 15 || a->rt2 == 13 || a->rt2 == 15 || + a->rt == a->rt2) { + /* Rt/Rt2 cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* Convert Qreg index to Dreg for read_neon_element32() etc */ + vd = a->qd * 2; + + if (!mve_skip_vmov(s, vd, a->idx, MO_32)) { + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, vd, a->idx, MO_32); + store_reg(s, a->rt, tmp); + } + if (!mve_skip_vmov(s, vd + 1, a->idx, MO_32)) { + tmp = tcg_temp_new_i32(); + read_neon_element32(tmp, vd + 1, a->idx, MO_32); + store_reg(s, a->rt2, tmp); + } + + mve_update_and_store_eci(s); + return true; +} + +static bool trans_VMOV_from_2gp(DisasContext *s, arg_VMOV_to_2gp *a) +{ + /* + * VMOV two general-purpose registers to two 32-bit vector lanes. + * This insn is not predicated but it is subject to beat-wise + * execution if it is not in an IT block. For us this means + * only that if PSR.ECI says we should not be executing the beat + * corresponding to the lane of the vector register being accessed + * then we should skip perfoming the move, and that we need to do + * the usual check for bad ECI state and advance of ECI state. + * (If PSR.ECI is non-zero then we cannot be in an IT block.) + */ + TCGv_i32 tmp; + int vd; + + if (!dc_isar_feature(aa32_mve, s) || !mve_check_qreg_bank(s, a->qd) || + a->rt == 13 || a->rt == 15 || a->rt2 == 13 || a->rt2 == 15) { + /* Rt/Rt2 cases are UNPREDICTABLE */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* Convert Qreg idx to Dreg for read_neon_element32() etc */ + vd = a->qd * 2; + + if (!mve_skip_vmov(s, vd, a->idx, MO_32)) { + tmp = load_reg(s, a->rt); + write_neon_element32(tmp, vd, a->idx, MO_32); + tcg_temp_free_i32(tmp); + } + if (!mve_skip_vmov(s, vd + 1, a->idx, MO_32)) { + tmp = load_reg(s, a->rt2); + write_neon_element32(tmp, vd + 1, a->idx, MO_32); + tcg_temp_free_i32(tmp); + } + + mve_update_and_store_eci(s); + return true; +} diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c +++ b/target/arm/translate-vfp.c @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) return true; } -static bool mve_skip_vmov(DisasContext *s, int vn, int index, int size) +bool mve_skip_vmov(DisasContext *s, int vn, int index, int size) { /* * In a CPU with MVE, the VMOV (vector lane to general-purpose register) -- 2.20.1 Implement the MVE VPNOT insn, which inverts the bits in VPR.P0 (subject to both predication and to beatwise execution). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 1 + target/arm/mve.decode | 1 + target/arm/mve_helper.c | 17 +++++++++++++++++ target/arm/translate-mve.c | 19 +++++++++++++++++++ 4 files changed, 38 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vorn, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_veor, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vpsel, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) +DEF_HELPER_FLAGS_1(mve_vpnot, TCG_CALL_NO_WG, void, env) DEF_HELPER_FLAGS_4(mve_vaddb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ VCMPGT 1111 1110 0 . .. ... 1 ... 1 1111 0 0 . 0 ... 1 @vcmp VCMPLE 1111 1110 0 . .. ... 1 ... 1 1111 1 0 . 0 ... 1 @vcmp { + VPNOT 1111 1110 0 0 11 000 1 000 0 1111 0100 1101 VPST 1111 1110 0 . 11 000 1 ... 0 1111 0100 1101 mask=%mask_22_13 VCMPEQ_scalar 1111 1110 0 . .. ... 1 ... 0 1111 0 1 0 0 .... @vcmp_scalar } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(mve_vpsel)(CPUARMState *env, void *vd, void *vn, void *vm) mve_advance_vpt(env); } +void HELPER(mve_vpnot)(CPUARMState *env) +{ + /* + * P0 bits for unexecuted beats (where eci_mask is 0) are unchanged. + * P0 bits for predicated lanes in executed bits (where mask is 0) are 0. + * P0 bits otherwise are inverted. + * (This is the same logic as VCMP.) + * This insn is itself subject to predication and to beat-wise execution, + * and after it executes VPT state advances in the usual way. + */ + uint16_t mask = mve_element_mask(env); + uint16_t eci_mask = mve_eci_mask(env); + uint16_t beatpred = ~env->v7m.vpr & mask; + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | (beatpred & eci_mask); + mve_advance_vpt(env); +} + #define DO_1OP_SAT(OP, ESIZE, TYPE, FN) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ { \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VPST(DisasContext *s, arg_VPST *a) return true; } +static bool trans_VPNOT(DisasContext *s, arg_VPNOT *a) +{ + /* + * Invert the predicate in VPR.P0. We have call out to + * a helper because this insn itself is beatwise and can + * be predicated. + */ + if (!dc_isar_feature(aa32_mve, s)) { + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + gen_helper_mve_vpnot(cpu_env); + mve_update_eci(s); + return true; +} + static bool trans_VADDV(DisasContext *s, arg_VADDV *a) { /* VADDV: vector add across vector */ -- 2.20.1 Implement the MVE VCTP insn, which sets the VPR.P0 predicate bits so as to predicate any element at index Rn or greater is predicated. As with VPNOT, this insn itself is predicable and subject to beatwise execution. The calculation of the mask is the same as is used to determine ltpmask in mve_element_mask(), but we precalculate masklen in generated code to avoid having to have 4 helpers specialized by size. We put the decode line in with the low-overhead-loop insns in t32.decode because it's logically part of that collection of insn patterns, even though it is an MVE only insn. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 2 ++ target/arm/translate-a32.h | 1 + target/arm/t32.decode | 1 + target/arm/mve_helper.c | 20 ++++++++++++++++++++ target/arm/translate-mve.c | 2 +- target/arm/translate.c | 33 +++++++++++++++++++++++++++++++++ 6 files changed, 58 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_veor, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vpsel, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_1(mve_vpnot, TCG_CALL_NO_WG, void, env) +DEF_HELPER_FLAGS_2(mve_vctp, TCG_CALL_NO_WG, void, env, i32) + DEF_HELPER_FLAGS_4(mve_vaddb, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddh, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) DEF_HELPER_FLAGS_4(mve_vaddw, TCG_CALL_NO_WG, void, env, ptr, ptr, ptr) diff --git a/target/arm/translate-a32.h b/target/arm/translate-a32.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a32.h +++ b/target/arm/translate-a32.h @@ -XXX,XX +XXX,XX @@ long neon_element_offset(int reg, int element, MemOp memop); void gen_rev16(TCGv_i32 dest, TCGv_i32 var); void clear_eci_state(DisasContext *s); bool mve_eci_check(DisasContext *s); +void mve_update_eci(DisasContext *s); void mve_update_and_store_eci(DisasContext *s); bool mve_skip_vmov(DisasContext *s, int vn, int index, int size); 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 @@ BL 1111 0. .......... 11.1 ............ @branch24 # This is DLSTP DLS 1111 0 0000 0 size:2 rn:4 1110 0000 0000 0001 } + VCTP 1111 0 0000 0 size:2 rn:4 1110 1000 0000 0001 ] } diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(mve_vpnot)(CPUARMState *env) mve_advance_vpt(env); } +/* + * VCTP: P0 unexecuted bits unchanged, predicated bits zeroed, + * otherwise set according to value of Rn. The calculation of + * newmask here works in the same way as the calculation of the + * ltpmask in mve_element_mask(), but we have pre-calculated + * the masklen in the generated code. + */ +void HELPER(mve_vctp)(CPUARMState *env, uint32_t masklen) +{ + uint16_t mask = mve_element_mask(env); + uint16_t eci_mask = mve_eci_mask(env); + uint16_t newmask; + + assert(masklen <= 16); + newmask = masklen ? MAKE_64BIT_MASK(0, masklen) : 0; + newmask &= mask; + env->v7m.vpr = (env->v7m.vpr & ~(uint32_t)eci_mask) | (newmask & eci_mask); + mve_advance_vpt(env); +} + #define DO_1OP_SAT(OP, ESIZE, TYPE, FN) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm) \ { \ diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ bool mve_eci_check(DisasContext *s) } } -static void mve_update_eci(DisasContext *s) +void mve_update_eci(DisasContext *s) { /* * The helper function will always update the CPUState field, 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_LCTP(DisasContext *s, arg_LCTP *a) return true; } +static bool trans_VCTP(DisasContext *s, arg_VCTP *a) +{ + /* + * M-profile Create Vector Tail Predicate. This insn is itself + * predicated and is subject to beatwise execution. + */ + TCGv_i32 rn_shifted, masklen; + + if (!dc_isar_feature(aa32_mve, s) || a->rn == 13 || a->rn == 15) { + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + /* + * We pre-calculate the mask length here to avoid having + * to have multiple helpers specialized for size. + * We pass the helper "rn <= (1 << (4 - size)) ? (rn << size) : 16". + */ + rn_shifted = tcg_temp_new_i32(); + masklen = load_reg(s, a->rn); + tcg_gen_shli_i32(rn_shifted, masklen, a->size); + tcg_gen_movcond_i32(TCG_COND_LEU, masklen, + masklen, tcg_constant_i32(1 << (4 - a->size)), + rn_shifted, tcg_constant_i32(16)); + gen_helper_mve_vctp(cpu_env, masklen); + tcg_temp_free_i32(masklen); + tcg_temp_free_i32(rn_shifted); + mve_update_eci(s); + return true; +} static bool op_tbranch(DisasContext *s, arg_tbranch *a, bool half) { -- 2.20.1 Implement the MVE gather-loads and scatter-stores which form the address by adding a base value from a scalar register to an offset in each element of a vector. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 32 +++++++++ target/arm/mve.decode | 12 ++++ target/arm/mve_helper.c | 129 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 97 ++++++++++++++++++++++++++++ 4 files changed, 270 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(mve_vstrb_h, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vstrb_w, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_3(mve_vstrh_w, TCG_CALL_NO_WG, void, env, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_sh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vldrb_sg_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrb_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrw_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrd_sg_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vstrb_sg_ub, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrb_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrb_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrh_sg_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrh_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrw_sg_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrd_sg_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vldrh_sg_os_sw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vldrh_sg_os_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrh_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrw_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrd_sg_os_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + +DEF_HELPER_FLAGS_4(mve_vstrh_sg_os_uh, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrh_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrw_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrd_sg_os_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &shl_scalar qda rm size &vmaxv qm rda size &vabav qn qm rda size +&vldst_sg qd qm rn size msize os + +# scatter-gather memory size is in bits 6:4 +%sg_msize 6:1 4:1 @vldr_vstr ....... . . . . l:1 rn:4 ... ...... imm:7 &vldr_vstr qd=%qd u=0 # Note that both Rn and Qd are 3 bits only (no D bit) @vldst_wn ... u:1 ... . . . . l:1 . rn:3 qd:3 . ... .. imm:7 &vldr_vstr +@vldst_sg .... .... .... rn:4 .... ... size:2 ... ... os:1 &vldst_sg \ + qd=%qd qm=%qm msize=%sg_msize + @1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm @1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0 @2op .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn @@ -XXX,XX +XXX,XX @@ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111101 ....... @vldr_vstr \ VLDR_VSTR 1110110 1 a:1 . w:1 . .... ... 111110 ....... @vldr_vstr \ size=2 p=1 +# gather loads/scatter stores +VLDR_S_sg 111 0 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg +VLDR_U_sg 111 1 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg +VSTR_sg 111 0 1100 1 . 00 .... ... 0 111 . .... .... @vldst_sg + # Moves between 2 32-bit vector lanes and 2 general purpose registers VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) #undef DO_VLDR #undef DO_VSTR +/* + * Gather loads/scatter stores. Here each element of Qm specifies + * an offset to use from the base register Rm. In the _os_ versions + * that offset is scaled by the element size. + * For loads, predicated lanes are zeroed instead of retaining + * their previous values. + */ +#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + TYPE *d = vd; \ + OFFTYPE *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ + addr = ADDRFN(base, m[H##ESIZE(e)]); \ + d[H##ESIZE(e)] = (mask & 1) ? \ + cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ + } \ + mve_advance_vpt(env); \ + } + +/* We know here TYPE is unsigned so always the same as the offset type */ +#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + TYPE *d = vd; \ + TYPE *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + addr = ADDRFN(base, m[H##ESIZE(e)]); \ + if (mask & 1) { \ + cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \ + } \ + } \ + mve_advance_vpt(env); \ + } + +/* + * 64-bit accesses are slightly different: they are done as two 32-bit + * accesses, controlled by the predicate mask for the relevant beat, + * and with a single 32-bit offset in the first of the two Qm elements. + * Note that for QEMU our IMPDEF AIRCR.ENDIANNESS is always 0 (little). + */ +#define DO_VLDR64_SG(OP, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + uint32_t *d = vd; \ + uint32_t *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ + addr = ADDRFN(base, m[H4(e & ~1)]); \ + addr += 4 * (e & 1); \ + d[H4(e)] = (mask & 1) ? cpu_ldl_data_ra(env, addr, GETPC()) : 0; \ + } \ + mve_advance_vpt(env); \ + } + +#define DO_VSTR64_SG(OP, ADDRFN) \ + void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ + uint32_t base) \ + { \ + uint32_t *d = vd; \ + uint32_t *m = vm; \ + uint16_t mask = mve_element_mask(env); \ + unsigned e; \ + uint32_t addr; \ + for (e = 0; e < 16 / 4; e++, mask >>= 4) { \ + addr = ADDRFN(base, m[H4(e & ~1)]); \ + addr += 4 * (e & 1); \ + if (mask & 1) { \ + cpu_stl_data_ra(env, addr, d[H4(e)], GETPC()); \ + } \ + } \ + mve_advance_vpt(env); \ + } + +#define ADDR_ADD(BASE, OFFSET) ((BASE) + (OFFSET)) +#define ADDR_ADD_OSH(BASE, OFFSET) ((BASE) + ((OFFSET) << 1)) +#define ADDR_ADD_OSW(BASE, OFFSET) ((BASE) + ((OFFSET) << 2)) +#define ADDR_ADD_OSD(BASE, OFFSET) ((BASE) + ((OFFSET) << 3)) + +DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD) + +DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD) +DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD) +DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD) + +DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH) +DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH) +DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH) +DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW) +DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD) + +DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD) +DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD) +DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD) +DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD) +DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD) +DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD) +DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD) + +DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH) +DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH) +DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW) +DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD) + /* * The mergemask(D, R, M) macro performs the operation "*D = R" but * storing only the bytes which correspond to 1 bits in M, diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static inline int vidup_imm(DisasContext *s, int x) #include "decode-mve.c.inc" typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenLdStSGFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); @@ -XXX,XX +XXX,XX @@ DO_VLDST_WIDE_NARROW(VLDSTB_H, vldrb_sh, vldrb_uh, vstrb_h, MO_8) DO_VLDST_WIDE_NARROW(VLDSTB_W, vldrb_sw, vldrb_uw, vstrb_w, MO_8) DO_VLDST_WIDE_NARROW(VLDSTH_W, vldrh_sw, vldrh_uw, vstrh_w, MO_16) +static bool do_ldst_sg(DisasContext *s, arg_vldst_sg *a, MVEGenLdStSGFn fn) +{ + TCGv_i32 addr; + TCGv_ptr qd, qm; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd | a->qm) || + !fn || a->rn == 15) { + /* Rn case is UNPREDICTABLE */ + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + addr = load_reg(s, a->rn); + + qd = mve_qreg_ptr(a->qd); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qd, qm, addr); + tcg_temp_free_ptr(qd); + tcg_temp_free_ptr(qm); + tcg_temp_free_i32(addr); + mve_update_eci(s); + return true; +} + +/* + * The naming scheme here is "vldrb_sg_sh == in-memory byte loads + * signextended to halfword elements in register". _os_ indicates that + * the offsets in Qm should be scaled by the element size. + */ +/* This macro is just to make the arrays more compact in these functions */ +#define F(N) gen_helper_mve_##N + +/* VLDRB/VSTRB (ie msize 1) with OS=1 is UNPREDICTABLE; we UNDEF */ +static bool trans_VLDR_S_sg(DisasContext *s, arg_vldst_sg *a) +{ + static MVEGenLdStSGFn * const fns[2][4][4] = { { + { NULL, F(vldrb_sg_sh), F(vldrb_sg_sw), NULL }, + { NULL, NULL, F(vldrh_sg_sw), NULL }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL } + }, { + { NULL, NULL, NULL, NULL }, + { NULL, NULL, F(vldrh_sg_os_sw), NULL }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL } + } + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]); +} + +static bool trans_VLDR_U_sg(DisasContext *s, arg_vldst_sg *a) +{ + static MVEGenLdStSGFn * const fns[2][4][4] = { { + { F(vldrb_sg_ub), F(vldrb_sg_uh), F(vldrb_sg_uw), NULL }, + { NULL, F(vldrh_sg_uh), F(vldrh_sg_uw), NULL }, + { NULL, NULL, F(vldrw_sg_uw), NULL }, + { NULL, NULL, NULL, F(vldrd_sg_ud) } + }, { + { NULL, NULL, NULL, NULL }, + { NULL, F(vldrh_sg_os_uh), F(vldrh_sg_os_uw), NULL }, + { NULL, NULL, F(vldrw_sg_os_uw), NULL }, + { NULL, NULL, NULL, F(vldrd_sg_os_ud) } + } + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]); +} + +static bool trans_VSTR_sg(DisasContext *s, arg_vldst_sg *a) +{ + static MVEGenLdStSGFn * const fns[2][4][4] = { { + { F(vstrb_sg_ub), F(vstrb_sg_uh), F(vstrb_sg_uw), NULL }, + { NULL, F(vstrh_sg_uh), F(vstrh_sg_uw), NULL }, + { NULL, NULL, F(vstrw_sg_uw), NULL }, + { NULL, NULL, NULL, F(vstrd_sg_ud) } + }, { + { NULL, NULL, NULL, NULL }, + { NULL, F(vstrh_sg_os_uh), F(vstrh_sg_os_uw), NULL }, + { NULL, NULL, F(vstrw_sg_os_uw), NULL }, + { NULL, NULL, NULL, F(vstrd_sg_os_ud) } + } + }; + return do_ldst_sg(s, a, fns[a->os][a->msize][a->size]); +} + +#undef F + static bool trans_VDUP(DisasContext *s, arg_VDUP *a) { TCGv_ptr qd; -- 2.20.1 Implement the MVE VLDR/VSTR insns which do scatter-gather using base addresses from Qm plus or minus an immediate offset (possibly with writeback). Note that writeback is not predicated but it does have to honour ECI state, so we have to add an eci_mask check to the VSTR_SG macros (the VLDR_SG macros already needed this to be able to distinguish "skip beat" from "set predicated element to 0"). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 5 +++ target/arm/mve.decode | 10 +++++ target/arm/mve_helper.c | 91 ++++++++++++++++++++++++-------------- target/arm/translate-mve.c | 72 ++++++++++++++++++++++++++++++ 4 files changed, 146 insertions(+), 32 deletions(-) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vstrh_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrw_sg_os_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrd_sg_os_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrw_sg_wb_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vldrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrw_sg_wb_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(mve_vstrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) + DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vmaxv qm rda size &vabav qn qm rda size &vldst_sg qd qm rn size msize os +&vldst_sg_imm qd qm a w imm # scatter-gather memory size is in bits 6:4 %sg_msize 6:1 4:1 @@ -XXX,XX +XXX,XX @@ @vldst_sg .... .... .... rn:4 .... ... size:2 ... ... os:1 &vldst_sg \ qd=%qd qm=%qm msize=%sg_msize +# Qm is in the fields usually labeled Qn +@vldst_sg_imm .... .... a:1 . w:1 . .... .... .... . imm:7 &vldst_sg_imm \ + qd=%qd qm=%qn + @1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm @1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0 @2op .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn @@ -XXX,XX +XXX,XX @@ VLDR_S_sg 111 0 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg VLDR_U_sg 111 1 1100 1 . 01 .... ... 0 111 . .... .... @vldst_sg VSTR_sg 111 0 1100 1 . 00 .... ... 0 111 . .... .... @vldst_sg +VLDRW_sg_imm 111 1 1101 ... 1 ... 0 ... 1 1110 .... .... @vldst_sg_imm +VLDRD_sg_imm 111 1 1101 ... 1 ... 0 ... 1 1111 .... .... @vldst_sg_imm +VSTRW_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1110 .... .... @vldst_sg_imm +VSTRD_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1111 .... .... @vldst_sg_imm + # Moves between 2 32-bit vector lanes and 2 general purpose registers VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) * For loads, predicated lanes are zeroed instead of retaining * their previous values. */ -#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN) \ +#define DO_VLDR_SG(OP, LDTYPE, ESIZE, TYPE, OFFTYPE, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) addr = ADDRFN(base, m[H##ESIZE(e)]); \ d[H##ESIZE(e)] = (mask & 1) ? \ cpu_##LDTYPE##_data_ra(env, addr, GETPC()) : 0; \ + if (WB) { \ + m[H##ESIZE(e)] = addr; \ + } \ } \ mve_advance_vpt(env); \ } /* We know here TYPE is unsigned so always the same as the offset type */ -#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN) \ +#define DO_VSTR_SG(OP, STTYPE, ESIZE, TYPE, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ TYPE *d = vd; \ TYPE *m = vm; \ uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ - for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE) { \ + for (e = 0; e < 16 / ESIZE; e++, mask >>= ESIZE, eci_mask >>= ESIZE) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ addr = ADDRFN(base, m[H##ESIZE(e)]); \ if (mask & 1) { \ cpu_##STTYPE##_data_ra(env, addr, d[H##ESIZE(e)], GETPC()); \ } \ + if (WB) { \ + m[H##ESIZE(e)] = addr; \ + } \ } \ mve_advance_vpt(env); \ } @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) * accesses, controlled by the predicate mask for the relevant beat, * and with a single 32-bit offset in the first of the two Qm elements. * Note that for QEMU our IMPDEF AIRCR.ENDIANNESS is always 0 (little). + * Address writeback happens on the odd beats and updates the address + * stored in the even-beat element. */ -#define DO_VLDR64_SG(OP, ADDRFN) \ +#define DO_VLDR64_SG(OP, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) addr = ADDRFN(base, m[H4(e & ~1)]); \ addr += 4 * (e & 1); \ d[H4(e)] = (mask & 1) ? cpu_ldl_data_ra(env, addr, GETPC()) : 0; \ + if (WB && (e & 1)) { \ + m[H4(e & ~1)] = addr - 4; \ + } \ } \ mve_advance_vpt(env); \ } -#define DO_VSTR64_SG(OP, ADDRFN) \ +#define DO_VSTR64_SG(OP, ADDRFN, WB) \ void HELPER(mve_##OP)(CPUARMState *env, void *vd, void *vm, \ uint32_t base) \ { \ uint32_t *d = vd; \ uint32_t *m = vm; \ uint16_t mask = mve_element_mask(env); \ + uint16_t eci_mask = mve_eci_mask(env); \ unsigned e; \ uint32_t addr; \ - for (e = 0; e < 16 / 4; e++, mask >>= 4) { \ + for (e = 0; e < 16 / 4; e++, mask >>= 4, eci_mask >>= 4) { \ + if (!(eci_mask & 1)) { \ + continue; \ + } \ addr = ADDRFN(base, m[H4(e & ~1)]); \ addr += 4 * (e & 1); \ if (mask & 1) { \ cpu_stl_data_ra(env, addr, d[H4(e)], GETPC()); \ } \ + if (WB && (e & 1)) { \ + m[H4(e & ~1)] = addr - 4; \ + } \ } \ mve_advance_vpt(env); \ } @@ -XXX,XX +XXX,XX @@ DO_VSTR(vstrh_w, 2, stw, 4, int32_t) #define ADDR_ADD_OSW(BASE, OFFSET) ((BASE) + ((OFFSET) << 2)) #define ADDR_ADD_OSD(BASE, OFFSET) ((BASE) + ((OFFSET) << 3)) -DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD) -DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD) -DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_sh, ldsb, 2, int16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_sw, ldsb, 4, int32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD, false) -DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD) -DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD) -DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD) -DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD) -DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD) -DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD) -DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD) +DO_VLDR_SG(vldrb_sg_ub, ldub, 1, uint8_t, uint8_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_uh, ldub, 2, uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrb_sg_uw, ldub, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD, false) +DO_VLDR_SG(vldrh_sg_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR_SG(vldrw_sg_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, false) +DO_VLDR64_SG(vldrd_sg_ud, ADDR_ADD, false) -DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH) -DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH) -DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH) -DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW) -DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD) +DO_VLDR_SG(vldrh_sg_os_sw, ldsw, 4, int32_t, uint32_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrh_sg_os_uh, lduw, 2, uint16_t, uint16_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrh_sg_os_uw, lduw, 4, uint32_t, uint32_t, ADDR_ADD_OSH, false) +DO_VLDR_SG(vldrw_sg_os_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD_OSW, false) +DO_VLDR64_SG(vldrd_sg_os_ud, ADDR_ADD_OSD, false) -DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD) -DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD) -DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD) -DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD) -DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD) -DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD) -DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD) +DO_VSTR_SG(vstrb_sg_ub, stb, 1, uint8_t, ADDR_ADD, false) +DO_VSTR_SG(vstrb_sg_uh, stb, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrb_sg_uw, stb, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uh, stw, 2, uint16_t, ADDR_ADD, false) +DO_VSTR_SG(vstrh_sg_uw, stw, 4, uint32_t, ADDR_ADD, false) +DO_VSTR_SG(vstrw_sg_uw, stl, 4, uint32_t, ADDR_ADD, false) +DO_VSTR64_SG(vstrd_sg_ud, ADDR_ADD, false) -DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH) -DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH) -DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW) -DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD) +DO_VSTR_SG(vstrh_sg_os_uh, stw, 2, uint16_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrh_sg_os_uw, stw, 4, uint32_t, ADDR_ADD_OSH, false) +DO_VSTR_SG(vstrw_sg_os_uw, stl, 4, uint32_t, ADDR_ADD_OSW, false) +DO_VSTR64_SG(vstrd_sg_os_ud, ADDR_ADD_OSD, false) + +DO_VLDR_SG(vldrw_sg_wb_uw, ldl, 4, uint32_t, uint32_t, ADDR_ADD, true) +DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) +DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true) +DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) /* * The mergemask(D, R, M) macro performs the operation "*D = R" but diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static bool trans_VSTR_sg(DisasContext *s, arg_vldst_sg *a) #undef F +static bool do_ldst_sg_imm(DisasContext *s, arg_vldst_sg_imm *a, + MVEGenLdStSGFn *fn, unsigned msize) +{ + uint32_t offset; + TCGv_ptr qd, qm; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd | a->qm) || + !fn) { + return false; + } + + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + offset = a->imm << msize; + if (!a->a) { + offset = -offset; + } + + qd = mve_qreg_ptr(a->qd); + qm = mve_qreg_ptr(a->qm); + fn(cpu_env, qd, qm, tcg_constant_i32(offset)); + tcg_temp_free_ptr(qd); + tcg_temp_free_ptr(qm); + mve_update_eci(s); + return true; +} + +static bool trans_VLDRW_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vldrw_sg_uw, + gen_helper_mve_vldrw_sg_wb_uw, + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg_imm(s, a, fns[a->w], MO_32); +} + +static bool trans_VLDRD_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vldrd_sg_ud, + gen_helper_mve_vldrd_sg_wb_ud, + }; + if (a->qd == a->qm) { + return false; /* UNPREDICTABLE */ + } + return do_ldst_sg_imm(s, a, fns[a->w], MO_64); +} + +static bool trans_VSTRW_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vstrw_sg_uw, + gen_helper_mve_vstrw_sg_wb_uw, + }; + return do_ldst_sg_imm(s, a, fns[a->w], MO_32); +} + +static bool trans_VSTRD_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) +{ + static MVEGenLdStSGFn * const fns[] = { + gen_helper_mve_vstrd_sg_ud, + gen_helper_mve_vstrd_sg_wb_ud, + }; + return do_ldst_sg_imm(s, a, fns[a->w], MO_64); +} + static bool trans_VDUP(DisasContext *s, arg_VDUP *a) { TCGv_ptr qd; -- 2.20.1 Implement the MVE interleaving load/store functions VLD2, VLD4, VST2 and VST4. VLD2 loads 16 bytes of data from memory and writes to 2 consecutive Qregs; VLD4 loads 16 bytes of data from memory and writes to 4 consecutive Qregs. The 'pattern' field in the encoding determines the offset into memory which is accessed and also which elements in the Qregs are written to. (The intention is that a sequence of four consecutive VLD4 with different pattern values performs a complete de-interleaving load of 64 bytes into all elements of the 4 Qregs.) VST2 and VST4 do the same, but for stores. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/helper-mve.h | 48 ++++++ target/arm/mve.decode | 11 ++ target/arm/mve_helper.c | 342 +++++++++++++++++++++++++++++++++++++ target/arm/translate-mve.c | 94 ++++++++++ 4 files changed, 495 insertions(+) diff --git a/target/arm/helper-mve.h b/target/arm/helper-mve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-mve.h +++ b/target/arm/helper-mve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(mve_vldrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrw_sg_wb_uw, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) DEF_HELPER_FLAGS_4(mve_vstrd_sg_wb_ud, TCG_CALL_NO_WG, void, env, ptr, ptr, i32) +DEF_HELPER_FLAGS_3(mve_vld20b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld20h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld20w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld21b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld21h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld21w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld40b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld40h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld40w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld41b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld41h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld41w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld42b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld42h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld42w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vld43b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld43h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vld43w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst20b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst20h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst20w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst21b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst21h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst21w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst40b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst40h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst40w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst41b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst41h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst41w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst42b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst42h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst42w, TCG_CALL_NO_WG, void, env, i32, i32) + +DEF_HELPER_FLAGS_3(mve_vst43b, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst43h, TCG_CALL_NO_WG, void, env, i32, i32) +DEF_HELPER_FLAGS_3(mve_vst43w, TCG_CALL_NO_WG, void, env, i32, i32) + DEF_HELPER_FLAGS_3(mve_vdup, TCG_CALL_NO_WG, void, env, ptr, i32) DEF_HELPER_FLAGS_4(mve_vidupb, TCG_CALL_NO_WG, i32, env, ptr, i32, i32) diff --git a/target/arm/mve.decode b/target/arm/mve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve.decode +++ b/target/arm/mve.decode @@ -XXX,XX +XXX,XX @@ &vabav qn qm rda size &vldst_sg qd qm rn size msize os &vldst_sg_imm qd qm a w imm +&vldst_il qd rn size pat w # scatter-gather memory size is in bits 6:4 %sg_msize 6:1 4:1 @@ -XXX,XX +XXX,XX @@ @vldst_sg_imm .... .... a:1 . w:1 . .... .... .... . imm:7 &vldst_sg_imm \ qd=%qd qm=%qn +# Deinterleaving load/interleaving store +@vldst_il .... .... .. w:1 . rn:4 .... ... size:2 pat:2 ..... &vldst_il \ + qd=%qd + @1op .... .... .... size:2 .. .... .... .... .... &1op qd=%qd qm=%qm @1op_nosz .... .... .... .... .... .... .... .... &1op qd=%qd qm=%qm size=0 @2op .... .... .. size:2 .... .... .... .... .... &2op qd=%qd qm=%qm qn=%qn @@ -XXX,XX +XXX,XX @@ VLDRD_sg_imm 111 1 1101 ... 1 ... 0 ... 1 1111 .... .... @vldst_sg_imm VSTRW_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1110 .... .... @vldst_sg_imm VSTRD_sg_imm 111 1 1101 ... 0 ... 0 ... 1 1111 .... .... @vldst_sg_imm +# deinterleaving loads/interleaving stores +VLD2 1111 1100 1 .. 1 .... ... 1 111 .. .. 00000 @vldst_il +VLD4 1111 1100 1 .. 1 .... ... 1 111 .. .. 00001 @vldst_il +VST2 1111 1100 1 .. 0 .... ... 1 111 .. .. 00000 @vldst_il +VST4 1111 1100 1 .. 0 .... ... 1 111 .. .. 00001 @vldst_il + # Moves between 2 32-bit vector lanes and 2 general purpose registers VMOV_to_2gp 1110 1100 0 . 00 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd VMOV_from_2gp 1110 1100 0 . 01 rt2:4 ... 0 1111 000 idx:1 rt:4 qd=%qd diff --git a/target/arm/mve_helper.c b/target/arm/mve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/mve_helper.c +++ b/target/arm/mve_helper.c @@ -XXX,XX +XXX,XX @@ DO_VLDR64_SG(vldrd_sg_wb_ud, ADDR_ADD, true) DO_VSTR_SG(vstrw_sg_wb_uw, stl, 4, uint32_t, ADDR_ADD, true) DO_VSTR64_SG(vstrd_sg_wb_ud, ADDR_ADD, true) +/* + * Deinterleaving loads/interleaving stores. + * + * For these helpers we are passed the index of the first Qreg + * (VLD2/VST2 will also access Qn+1, VLD4/VST4 access Qn .. Qn+3) + * and the value of the base address register Rn. + * The helpers are specialized for pattern and element size, so + * for instance vld42h is VLD4 with pattern 2, element size MO_16. + * + * These insns are beatwise but not predicated, so we must honour ECI, + * but need not look at mve_element_mask(). + * + * The pseudocode implements these insns with multiple memory accesses + * of the element size, but rules R_VVVG and R_FXDM permit us to make + * one 32-bit memory access per beat. + */ +#define DO_VLD4B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + for (e = 0; e < 4; e++, data >>= 8) { \ + uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \ + qd[H1(off[beat])] = data; \ + } \ + } \ + } + +#define DO_VLD4H(OP, O1, O2) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O1, O2, O2 }; \ + uint32_t addr, data; \ + int y; /* y counts 0 2 0 2 */ \ + uint16_t *qd; \ + for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 8 + (beat & 1) * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y); \ + qd[H2(off[beat])] = data; \ + data >>= 16; \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y + 1); \ + qd[H2(off[beat])] = data; \ + } \ + } + +#define DO_VLD4W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + int y; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + y = (beat + (O1 & 2)) & 3; \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y); \ + qd[H4(off[beat] >> 2)] = data; \ + } \ + } + +DO_VLD4B(vld40b, 0, 1, 10, 11) +DO_VLD4B(vld41b, 2, 3, 12, 13) +DO_VLD4B(vld42b, 4, 5, 14, 15) +DO_VLD4B(vld43b, 6, 7, 8, 9) + +DO_VLD4H(vld40h, 0, 5) +DO_VLD4H(vld41h, 1, 6) +DO_VLD4H(vld42h, 2, 7) +DO_VLD4H(vld43h, 3, 4) + +DO_VLD4W(vld40w, 0, 1, 10, 11) +DO_VLD4W(vld41w, 2, 3, 12, 13) +DO_VLD4W(vld42w, 4, 5, 14, 15) +DO_VLD4W(vld43w, 6, 7, 8, 9) + +#define DO_VLD2B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint8_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 2; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + for (e = 0; e < 4; e++, data >>= 8) { \ + qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1)); \ + qd[H1(off[beat] + (e >> 1))] = data; \ + } \ + } \ + } + +#define DO_VLD2H(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + int e; \ + uint16_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + for (e = 0; e < 2; e++, data >>= 16) { \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e); \ + qd[H2(off[beat])] = data; \ + } \ + } \ + } + +#define DO_VLD2W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat]; \ + data = cpu_ldl_le_data_ra(env, addr, GETPC()); \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1)); \ + qd[H4(off[beat] >> 3)] = data; \ + } \ + } + +DO_VLD2B(vld20b, 0, 2, 12, 14) +DO_VLD2B(vld21b, 4, 6, 8, 10) + +DO_VLD2H(vld20h, 0, 1, 6, 7) +DO_VLD2H(vld21h, 2, 3, 4, 5) + +DO_VLD2W(vld20w, 0, 4, 24, 28) +DO_VLD2W(vld21w, 8, 12, 16, 20) + +#define DO_VST4B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = 0; \ + for (e = 3; e >= 0; e--) { \ + uint8_t *qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + e); \ + data = (data << 8) | qd[H1(off[beat])]; \ + } \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST4H(OP, O1, O2) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O1, O2, O2 }; \ + uint32_t addr, data; \ + int y; /* y counts 0 2 0 2 */ \ + uint16_t *qd; \ + for (beat = 0, y = 0; beat < 4; beat++, mask >>= 4, y ^= 2) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 8 + (beat & 1) * 4; \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y); \ + data = qd[H2(off[beat])]; \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + y + 1); \ + data |= qd[H2(off[beat])] << 16; \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST4W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + int y; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + y = (beat + (O1 & 2)) & 3; \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + y); \ + data = qd[H4(off[beat] >> 2)]; \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +DO_VST4B(vst40b, 0, 1, 10, 11) +DO_VST4B(vst41b, 2, 3, 12, 13) +DO_VST4B(vst42b, 4, 5, 14, 15) +DO_VST4B(vst43b, 6, 7, 8, 9) + +DO_VST4H(vst40h, 0, 5) +DO_VST4H(vst41h, 1, 6) +DO_VST4H(vst42h, 2, 7) +DO_VST4H(vst43h, 3, 4) + +DO_VST4W(vst40w, 0, 1, 10, 11) +DO_VST4W(vst41w, 2, 3, 12, 13) +DO_VST4W(vst42w, 4, 5, 14, 15) +DO_VST4W(vst43w, 6, 7, 8, 9) + +#define DO_VST2B(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat, e; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint8_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 2; \ + data = 0; \ + for (e = 3; e >= 0; e--) { \ + qd = (uint8_t *)aa32_vfp_qreg(env, qnidx + (e & 1)); \ + data = (data << 8) | qd[H1(off[beat] + (e >> 1))]; \ + } \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST2H(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + int e; \ + uint16_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat] * 4; \ + data = 0; \ + for (e = 1; e >= 0; e--) { \ + qd = (uint16_t *)aa32_vfp_qreg(env, qnidx + e); \ + data = (data << 16) | qd[H2(off[beat])]; \ + } \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +#define DO_VST2W(OP, O1, O2, O3, O4) \ + void HELPER(mve_##OP)(CPUARMState *env, uint32_t qnidx, \ + uint32_t base) \ + { \ + int beat; \ + uint16_t mask = mve_eci_mask(env); \ + static const uint8_t off[4] = { O1, O2, O3, O4 }; \ + uint32_t addr, data; \ + uint32_t *qd; \ + for (beat = 0; beat < 4; beat++, mask >>= 4) { \ + if ((mask & 1) == 0) { \ + /* ECI says skip this beat */ \ + continue; \ + } \ + addr = base + off[beat]; \ + qd = (uint32_t *)aa32_vfp_qreg(env, qnidx + (beat & 1)); \ + data = qd[H4(off[beat] >> 3)]; \ + cpu_stl_le_data_ra(env, addr, data, GETPC()); \ + } \ + } + +DO_VST2B(vst20b, 0, 2, 12, 14) +DO_VST2B(vst21b, 4, 6, 8, 10) + +DO_VST2H(vst20h, 0, 1, 6, 7) +DO_VST2H(vst21h, 2, 3, 4, 5) + +DO_VST2W(vst20w, 0, 4, 24, 28) +DO_VST2W(vst21w, 8, 12, 16, 20) + /* * The mergemask(D, R, M) macro performs the operation "*D = R" but * storing only the bytes which correspond to 1 bits in M, diff --git a/target/arm/translate-mve.c b/target/arm/translate-mve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-mve.c +++ b/target/arm/translate-mve.c @@ -XXX,XX +XXX,XX @@ static inline int vidup_imm(DisasContext *s, int x) typedef void MVEGenLdStFn(TCGv_ptr, TCGv_ptr, TCGv_i32); typedef void MVEGenLdStSGFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); +typedef void MVEGenLdStIlFn(TCGv_ptr, TCGv_i32, TCGv_i32); typedef void MVEGenOneOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_ptr); typedef void MVEGenTwoOpScalarFn(TCGv_ptr, TCGv_ptr, TCGv_ptr, TCGv_i32); @@ -XXX,XX +XXX,XX @@ static bool trans_VSTRD_sg_imm(DisasContext *s, arg_vldst_sg_imm *a) return do_ldst_sg_imm(s, a, fns[a->w], MO_64); } +static bool do_vldst_il(DisasContext *s, arg_vldst_il *a, MVEGenLdStIlFn *fn, + int addrinc) +{ + TCGv_i32 rn; + + if (!dc_isar_feature(aa32_mve, s) || + !mve_check_qreg_bank(s, a->qd) || + !fn || (a->rn == 13 && a->w) || a->rn == 15) { + /* Variously UNPREDICTABLE or UNDEF or related-encoding */ + return false; + } + if (!mve_eci_check(s) || !vfp_access_check(s)) { + return true; + } + + rn = load_reg(s, a->rn); + /* + * We pass the index of Qd, not a pointer, because the helper must + * access multiple Q registers starting at Qd and working up. + */ + fn(cpu_env, tcg_constant_i32(a->qd), rn); + + if (a->w) { + tcg_gen_addi_i32(rn, rn, addrinc); + store_reg(s, a->rn, rn); + } else { + tcg_temp_free_i32(rn); + } + mve_update_and_store_eci(s); + return true; +} + +/* This macro is just to make the arrays more compact in these functions */ +#define F(N) gen_helper_mve_##N + +static bool trans_VLD2(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vld20b), F(vld20h), F(vld20w), NULL, }, + { F(vld21b), F(vld21h), F(vld21w), NULL, }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL }, + }; + if (a->qd > 6) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 32); +} + +static bool trans_VLD4(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vld40b), F(vld40h), F(vld40w), NULL, }, + { F(vld41b), F(vld41h), F(vld41w), NULL, }, + { F(vld42b), F(vld42h), F(vld42w), NULL, }, + { F(vld43b), F(vld43h), F(vld43w), NULL, }, + }; + if (a->qd > 4) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 64); +} + +static bool trans_VST2(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vst20b), F(vst20h), F(vst20w), NULL, }, + { F(vst21b), F(vst21h), F(vst21w), NULL, }, + { NULL, NULL, NULL, NULL }, + { NULL, NULL, NULL, NULL }, + }; + if (a->qd > 6) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 32); +} + +static bool trans_VST4(DisasContext *s, arg_vldst_il *a) +{ + static MVEGenLdStIlFn * const fns[4][4] = { + { F(vst40b), F(vst40h), F(vst40w), NULL, }, + { F(vst41b), F(vst41h), F(vst41w), NULL, }, + { F(vst42b), F(vst42h), F(vst42w), NULL, }, + { F(vst43b), F(vst43h), F(vst43w), NULL, }, + }; + if (a->qd > 4) { + return false; + } + return do_vldst_il(s, a, fns[a->pat][a->size], 64); +} + +#undef F + static bool trans_VDUP(DisasContext *s, arg_VDUP *a) { TCGv_ptr qd; -- 2.20.1 We're about to make a code change to the sdiv and udiv helper functions, so first fix their indentation and coding style. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210730151636.17254-2-peter.maydell@linaro.org --- target/arm/helper.c | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(uxtb16)(uint32_t x) int32_t HELPER(sdiv)(int32_t num, int32_t den) { - if (den == 0) - return 0; - if (num == INT_MIN && den == -1) - return INT_MIN; + if (den == 0) { + return 0; + } + if (num == INT_MIN && den == -1) { + return INT_MIN; + } return num / den; } uint32_t HELPER(udiv)(uint32_t num, uint32_t den) { - if (den == 0) - return 0; + if (den == 0) { + return 0; + } return num / den; } -- 2.20.1 Unlike A-profile, for M-profile the UDIV and SDIV insns can be configured to raise an exception on division by zero, using the CCR DIV_0_TRP bit. Implement support for setting this bit by making the helper functions raise the appropriate exception. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20210730151636.17254-3-peter.maydell@linaro.org --- target/arm/cpu.h | 1 + target/arm/helper.h | 4 ++-- target/arm/helper.c | 19 +++++++++++++++++-- target/arm/m_helper.c | 4 ++++ target/arm/translate.c | 4 ++-- 5 files changed, 26 insertions(+), 6 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 @@ #define EXCP_LAZYFP 20 /* v7M fault during lazy FP stacking */ #define EXCP_LSERR 21 /* v8M LSERR SecureFault */ #define EXCP_UNALIGNED 22 /* v7M UNALIGNED UsageFault */ +#define EXCP_DIVBYZERO 23 /* v7M DIVBYZERO UsageFault */ /* NB: add new EXCP_ defines to the array in arm_log_exception() too */ #define ARMV7M_EXCP_RESET 1 diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_3(add_saturate, i32, env, i32, i32) DEF_HELPER_3(sub_saturate, i32, env, i32, i32) DEF_HELPER_3(add_usaturate, i32, env, i32, i32) DEF_HELPER_3(sub_usaturate, i32, env, i32, i32) -DEF_HELPER_FLAGS_2(sdiv, TCG_CALL_NO_RWG_SE, s32, s32, s32) -DEF_HELPER_FLAGS_2(udiv, TCG_CALL_NO_RWG_SE, i32, i32, i32) +DEF_HELPER_FLAGS_3(sdiv, TCG_CALL_NO_RWG, s32, env, s32, s32) +DEF_HELPER_FLAGS_3(udiv, TCG_CALL_NO_RWG, i32, env, i32, i32) DEF_HELPER_FLAGS_1(rbit, TCG_CALL_NO_RWG_SE, i32, i32) #define PAS_OP(pfx) \ 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 @@ uint32_t HELPER(sxtb16)(uint32_t x) return res; } +static void handle_possible_div0_trap(CPUARMState *env, uintptr_t ra) +{ + /* + * Take a division-by-zero exception if necessary; otherwise return + * to get the usual non-trapping division behaviour (result of 0) + */ + if (arm_feature(env, ARM_FEATURE_M) + && (env->v7m.ccr[env->v7m.secure] & R_V7M_CCR_DIV_0_TRP_MASK)) { + raise_exception_ra(env, EXCP_DIVBYZERO, 0, 1, ra); + } +} + uint32_t HELPER(uxtb16)(uint32_t x) { uint32_t res; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(uxtb16)(uint32_t x) return res; } -int32_t HELPER(sdiv)(int32_t num, int32_t den) +int32_t HELPER(sdiv)(CPUARMState *env, int32_t num, int32_t den) { if (den == 0) { + handle_possible_div0_trap(env, GETPC()); return 0; } if (num == INT_MIN && den == -1) { @@ -XXX,XX +XXX,XX @@ int32_t HELPER(sdiv)(int32_t num, int32_t den) return num / den; } -uint32_t HELPER(udiv)(uint32_t num, uint32_t den) +uint32_t HELPER(udiv)(CPUARMState *env, uint32_t num, uint32_t den) { if (den == 0) { + handle_possible_div0_trap(env, GETPC()); return 0; } return num / den; @@ -XXX,XX +XXX,XX @@ void arm_log_exception(int idx) [EXCP_LAZYFP] = "v7M exception during lazy FP stacking", [EXCP_LSERR] = "v8M LSERR UsageFault", [EXCP_UNALIGNED] = "v7M UNALIGNED UsageFault", + [EXCP_DIVBYZERO] = "v7M DIVBYZERO UsageFault", }; if (idx >= 0 && idx < ARRAY_SIZE(excnames)) { 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 @@ void arm_v7m_cpu_do_interrupt(CPUState *cs) armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_UNALIGNED_MASK; break; + case EXCP_DIVBYZERO: + armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_USAGE, env->v7m.secure); + env->v7m.cfsr[env->v7m.secure] |= R_V7M_CFSR_DIVBYZERO_MASK; + break; case EXCP_SWI: /* The PC already points to the next instruction. */ armv7m_nvic_set_pending(env->nvic, ARMV7M_EXCP_SVC, env->v7m.secure); 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 op_div(DisasContext *s, arg_rrr *a, bool u) t1 = load_reg(s, a->rn); t2 = load_reg(s, a->rm); if (u) { - gen_helper_udiv(t1, t1, t2); + gen_helper_udiv(t1, cpu_env, t1, t2); } else { - gen_helper_sdiv(t1, t1, t2); + gen_helper_sdiv(t1, cpu_env, t1, t2); } tcg_temp_free_i32(t2); store_reg(s, a->rd, t1); -- 2.20.1 From: Hamza Mahfooz <someguy@effective-light.com> As per commit 5626f8c6d468 ("rcu: Add automatically released rcu_read_lock variants"), RCU_READ_LOCK_GUARD() should be used instead of rcu_read_{un}lock(). Signed-off-by: Hamza Mahfooz <someguy@effective-light.com> Reviewed-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 20210727235201.11491-1-someguy@effective-light.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/kvm.c | 17 ++++++++--------- 1 file changed, 8 insertions(+), 9 deletions(-) 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 @@ int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route, hwaddr xlat, len, doorbell_gpa; MemoryRegionSection mrs; MemoryRegion *mr; - int ret = 1; if (as == &address_space_memory) { return 0; @@ -XXX,XX +XXX,XX @@ int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route, /* MSI doorbell address is translated by an IOMMU */ - rcu_read_lock(); + RCU_READ_LOCK_GUARD(); + mr = address_space_translate(as, address, &xlat, &len, true, MEMTXATTRS_UNSPECIFIED); + if (!mr) { - goto unlock; + return 1; } + mrs = memory_region_find(mr, xlat, 1); + if (!mrs.mr) { - goto unlock; + return 1; } doorbell_gpa = mrs.offset_within_address_space; @@ -XXX,XX +XXX,XX @@ int kvm_arch_fixup_msi_route(struct kvm_irq_routing_entry *route, trace_kvm_arm_fixup_msi_route(address, doorbell_gpa); - ret = 0; - -unlock: - rcu_read_unlock(); - return ret; + return 0; } int kvm_arch_add_msi_route_post(struct kvm_irq_routing_entry *route, -- 2.20.1 From: Jan Luebbe <jlu@pengutronix.de> Break events are currently only handled by chardev/char-serial.c, so we just ignore errors, which results in no behaviour change for other chardevs. Signed-off-by: Jan Luebbe <jlu@pengutronix.de> Message-id: 20210806144700.3751979-1-jlu@pengutronix.de Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/pl011.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/hw/char/pl011.c b/hw/char/pl011.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/pl011.c +++ b/hw/char/pl011.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-properties-system.h" #include "migration/vmstate.h" #include "chardev/char-fe.h" +#include "chardev/char-serial.h" #include "qemu/log.h" #include "qemu/module.h" #include "trace.h" @@ -XXX,XX +XXX,XX @@ static void pl011_write(void *opaque, hwaddr offset, s->read_count = 0; s->read_pos = 0; } + if ((s->lcr ^ value) & 0x1) { + int break_enable = value & 0x1; + qemu_chr_fe_ioctl(&s->chr, CHR_IOCTL_SERIAL_SET_BREAK, + &break_enable); + } s->lcr = value; pl011_set_read_trigger(s); break; -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> Instantiate SAI1/2/3 and ASRC as unimplemented devices to avoid random Linux kernel crashes, such as Unhandled fault: external abort on non-linefetch (0x808) at 0xd1580010 pgd = (ptrval) [d1580010] *pgd=8231b811, *pte=02034653, *ppte=02034453 Internal error: : 808 [#1] SMP ARM ... [<c095e974>] (regmap_mmio_write32le) from [<c095eb48>] (regmap_mmio_write+0x3c/0x54) [<c095eb48>] (regmap_mmio_write) from [<c09580f4>] (_regmap_write+0x4c/0x1f0) [<c09580f4>] (_regmap_write) from [<c095837c>] (_regmap_update_bits+0xe4/0xec) [<c095837c>] (_regmap_update_bits) from [<c09599b4>] (regmap_update_bits_base+0x50/0x74) [<c09599b4>] (regmap_update_bits_base) from [<c0d3e9e4>] (fsl_asrc_runtime_resume+0x1e4/0x21c) [<c0d3e9e4>] (fsl_asrc_runtime_resume) from [<c0942464>] (__rpm_callback+0x3c/0x108) [<c0942464>] (__rpm_callback) from [<c0942590>] (rpm_callback+0x60/0x64) [<c0942590>] (rpm_callback) from [<c0942b60>] (rpm_resume+0x5cc/0x808) [<c0942b60>] (rpm_resume) from [<c0942dfc>] (__pm_runtime_resume+0x60/0xa0) [<c0942dfc>] (__pm_runtime_resume) from [<c0d3ecc4>] (fsl_asrc_probe+0x2a8/0x708) [<c0d3ecc4>] (fsl_asrc_probe) from [<c0935b08>] (platform_probe+0x58/0xb8) [<c0935b08>] (platform_probe) from [<c0933264>] (really_probe.part.0+0x9c/0x334) [<c0933264>] (really_probe.part.0) from [<c093359c>] (__driver_probe_device+0xa0/0x138) [<c093359c>] (__driver_probe_device) from [<c0933664>] (driver_probe_device+0x30/0xc8) [<c0933664>] (driver_probe_device) from [<c0933c88>] (__driver_attach+0x90/0x130) [<c0933c88>] (__driver_attach) from [<c0931060>] (bus_for_each_dev+0x78/0xb8) [<c0931060>] (bus_for_each_dev) from [<c093254c>] (bus_add_driver+0xf0/0x1d8) [<c093254c>] (bus_add_driver) from [<c0934a30>] (driver_register+0x88/0x118) [<c0934a30>] (driver_register) from [<c01022c0>] (do_one_initcall+0x7c/0x3a4) [<c01022c0>] (do_one_initcall) from [<c1601204>] (kernel_init_freeable+0x198/0x22c) [<c1601204>] (kernel_init_freeable) from [<c0f5ff2c>] (kernel_init+0x10/0x128) [<c0f5ff2c>] (kernel_init) from [<c010013c>] (ret_from_fork+0x14/0x38) or Unhandled fault: external abort on non-linefetch (0x808) at 0xd19b0000 pgd = (ptrval) [d19b0000] *pgd=82711811, *pte=308a0653, *ppte=308a0453 Internal error: : 808 [#1] SMP ARM ... [<c095e974>] (regmap_mmio_write32le) from [<c095eb48>] (regmap_mmio_write+0x3c/0x54) [<c095eb48>] (regmap_mmio_write) from [<c09580f4>] (_regmap_write+0x4c/0x1f0) [<c09580f4>] (_regmap_write) from [<c0959b28>] (regmap_write+0x3c/0x60) [<c0959b28>] (regmap_write) from [<c0d41130>] (fsl_sai_runtime_resume+0x9c/0x1ec) [<c0d41130>] (fsl_sai_runtime_resume) from [<c0942464>] (__rpm_callback+0x3c/0x108) [<c0942464>] (__rpm_callback) from [<c0942590>] (rpm_callback+0x60/0x64) [<c0942590>] (rpm_callback) from [<c0942b60>] (rpm_resume+0x5cc/0x808) [<c0942b60>] (rpm_resume) from [<c0942dfc>] (__pm_runtime_resume+0x60/0xa0) [<c0942dfc>] (__pm_runtime_resume) from [<c0d4231c>] (fsl_sai_probe+0x2b8/0x65c) [<c0d4231c>] (fsl_sai_probe) from [<c0935b08>] (platform_probe+0x58/0xb8) [<c0935b08>] (platform_probe) from [<c0933264>] (really_probe.part.0+0x9c/0x334) [<c0933264>] (really_probe.part.0) from [<c093359c>] (__driver_probe_device+0xa0/0x138) [<c093359c>] (__driver_probe_device) from [<c0933664>] (driver_probe_device+0x30/0xc8) [<c0933664>] (driver_probe_device) from [<c0933c88>] (__driver_attach+0x90/0x130) [<c0933c88>] (__driver_attach) from [<c0931060>] (bus_for_each_dev+0x78/0xb8) [<c0931060>] (bus_for_each_dev) from [<c093254c>] (bus_add_driver+0xf0/0x1d8) [<c093254c>] (bus_add_driver) from [<c0934a30>] (driver_register+0x88/0x118) [<c0934a30>] (driver_register) from [<c01022c0>] (do_one_initcall+0x7c/0x3a4) [<c01022c0>] (do_one_initcall) from [<c1601204>] (kernel_init_freeable+0x198/0x22c) [<c1601204>] (kernel_init_freeable) from [<c0f5ff2c>] (kernel_init+0x10/0x128) [<c0f5ff2c>] (kernel_init) from [<c010013c>] (ret_from_fork+0x14/0x38) Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Signed-off-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20210810160318.87376-1-linux@roeck-us.net Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx6ul.c | 12 ++++++++++++ 1 file changed, 12 insertions(+) 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) */ create_unimplemented_device("sdma", FSL_IMX6UL_SDMA_ADDR, 0x4000); + /* + * SAI (Audio SSI (Synchronous Serial Interface)) + */ + create_unimplemented_device("sai1", FSL_IMX6UL_SAI1_ADDR, 0x4000); + create_unimplemented_device("sai2", FSL_IMX6UL_SAI2_ADDR, 0x4000); + create_unimplemented_device("sai3", FSL_IMX6UL_SAI3_ADDR, 0x4000); + /* * PWM */ @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) create_unimplemented_device("pwm3", FSL_IMX6UL_PWM3_ADDR, 0x4000); create_unimplemented_device("pwm4", FSL_IMX6UL_PWM4_ADDR, 0x4000); + /* + * Audio ASRC (asynchronous sample rate converter) + */ + create_unimplemented_device("asrc", FSL_IMX6UL_ASRC_ADDR, 0x4000); + /* * CAN */ -- 2.20.1 From: "Wen, Jianxian" <Jianxian.Wen@verisilicon.com> Add property memory region which can connect with IOMMU region to support SMMU translate. Signed-off-by: Jianxian Wen <jianxian.wen@verisilicon.com> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 4C23C17B8E87E74E906A25A3254A03F4FA1FEC31@SHASXM03.verisilicon.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/exynos4210.c | 3 +++ hw/arm/xilinx_zynq.c | 3 +++ hw/dma/pl330.c | 26 ++++++++++++++++++++++---- 3 files changed, 28 insertions(+), 4 deletions(-) diff --git a/hw/arm/exynos4210.c b/hw/arm/exynos4210.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/exynos4210.c +++ b/hw/arm/exynos4210.c @@ -XXX,XX +XXX,XX @@ static DeviceState *pl330_create(uint32_t base, qemu_or_irq *orgate, int i; dev = qdev_new("pl330"); + object_property_set_link(OBJECT(dev), "memory", + OBJECT(get_system_memory()), + &error_fatal); qdev_prop_set_uint8(dev, "num_events", nevents); qdev_prop_set_uint8(dev, "num_chnls", 8); qdev_prop_set_uint8(dev, "num_periph_req", nreq); diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[39-IRQ_OFFSET]); dev = qdev_new("pl330"); + object_property_set_link(OBJECT(dev), "memory", + OBJECT(address_space_mem), + &error_fatal); qdev_prop_set_uint8(dev, "num_chnls", 8); qdev_prop_set_uint8(dev, "num_periph_req", 4); qdev_prop_set_uint8(dev, "num_events", 16); diff --git a/hw/dma/pl330.c b/hw/dma/pl330.c index XXXXXXX..XXXXXXX 100644 --- a/hw/dma/pl330.c +++ b/hw/dma/pl330.c @@ -XXX,XX +XXX,XX @@ struct PL330State { uint8_t num_faulting; uint8_t periph_busy[PL330_PERIPH_NUM]; + /* Memory region that DMA operation access */ + MemoryRegion *mem_mr; + AddressSpace *mem_as; }; #define TYPE_PL330 "pl330" @@ -XXX,XX +XXX,XX @@ static inline const PL330InsnDesc *pl330_fetch_insn(PL330Chan *ch) uint8_t opcode; int i; - dma_memory_read(&address_space_memory, ch->pc, &opcode, 1); + dma_memory_read(ch->parent->mem_as, ch->pc, &opcode, 1); for (i = 0; insn_desc[i].size; i++) { if ((opcode & insn_desc[i].opmask) == insn_desc[i].opcode) { return &insn_desc[i]; @@ -XXX,XX +XXX,XX @@ static inline void pl330_exec_insn(PL330Chan *ch, const PL330InsnDesc *insn) uint8_t buf[PL330_INSN_MAXSIZE]; assert(insn->size <= PL330_INSN_MAXSIZE); - dma_memory_read(&address_space_memory, ch->pc, buf, insn->size); + dma_memory_read(ch->parent->mem_as, ch->pc, buf, insn->size); insn->exec(ch, buf[0], &buf[1], insn->size - 1); } @@ -XXX,XX +XXX,XX @@ static int pl330_exec_cycle(PL330Chan *channel) if (q != NULL && q->len <= pl330_fifo_num_free(&s->fifo)) { int len = q->len - (q->addr & (q->len - 1)); - dma_memory_read(&address_space_memory, q->addr, buf, len); + dma_memory_read(s->mem_as, q->addr, buf, len); trace_pl330_exec_cycle(q->addr, len); if (trace_event_get_state_backends(TRACE_PL330_HEXDUMP)) { pl330_hexdump(buf, len); @@ -XXX,XX +XXX,XX @@ static int pl330_exec_cycle(PL330Chan *channel) fifo_res = pl330_fifo_get(&s->fifo, buf, len, q->tag); } if (fifo_res == PL330_FIFO_OK || q->z) { - dma_memory_write(&address_space_memory, q->addr, buf, len); + dma_memory_write(s->mem_as, q->addr, buf, len); trace_pl330_exec_cycle(q->addr, len); if (trace_event_get_state_backends(TRACE_PL330_HEXDUMP)) { pl330_hexdump(buf, len); @@ -XXX,XX +XXX,XX @@ static void pl330_realize(DeviceState *dev, Error **errp) "dma", PL330_IOMEM_SIZE); sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); + if (!s->mem_mr) { + error_setg(errp, "'memory' link is not set"); + return; + } else if (s->mem_mr == get_system_memory()) { + /* Avoid creating new AS for system memory. */ + s->mem_as = &address_space_memory; + } else { + s->mem_as = g_new0(AddressSpace, 1); + address_space_init(s->mem_as, s->mem_mr, + memory_region_name(s->mem_mr)); + } + s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, pl330_exec_cycle_timer, s); s->cfg[0] = (s->mgr_ns_at_rst ? 0x4 : 0) | @@ -XXX,XX +XXX,XX @@ static Property pl330_properties[] = { DEFINE_PROP_UINT8("rd_q_dep", PL330State, rd_q_dep, 16), DEFINE_PROP_UINT16("data_buffer_dep", PL330State, data_buffer_dep, 256), + DEFINE_PROP_LINK("memory", PL330State, mem_mr, + TYPE_MEMORY_REGION, MemoryRegion *), + DEFINE_PROP_END_OF_LIST(), }; -- 2.20.1 From: Eduardo Habkost <ehabkost@redhat.com> The SBSA_GWDT enum value conflicts with the SBSA_GWDT() QOM type checking helper, preventing us from using a OBJECT_DEFINE* or DEFINE_INSTANCE_CHECKER macro for the SBSA_GWDT() wrapper. If I understand the SBSA 6.0 specification correctly, the signal being connected to IRQ 16 is the WS0 output signal from the Generic Watchdog. Rename the enum value to SBSA_GWDT_WS0 to be more explicit and avoid the name conflict. Signed-off-by: Eduardo Habkost <ehabkost@redhat.com> Message-id: 20210806023119.431680-1-ehabkost@redhat.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/sbsa-ref.c | 6 +++--- 1 file changed, 3 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 @@ enum { SBSA_GIC_DIST, SBSA_GIC_REDIST, SBSA_SECURE_EC, - SBSA_GWDT, + SBSA_GWDT_WS0, SBSA_GWDT_REFRESH, SBSA_GWDT_CONTROL, SBSA_SMMU, @@ -XXX,XX +XXX,XX @@ static const int sbsa_ref_irqmap[] = { [SBSA_AHCI] = 10, [SBSA_EHCI] = 11, [SBSA_SMMU] = 12, /* ... to 15 */ - [SBSA_GWDT] = 16, + [SBSA_GWDT_WS0] = 16, }; static const char * const valid_cpus[] = { @@ -XXX,XX +XXX,XX @@ static void create_wdt(const SBSAMachineState *sms) hwaddr cbase = sbsa_ref_memmap[SBSA_GWDT_CONTROL].base; DeviceState *dev = qdev_new(TYPE_WDT_SBSA); SysBusDevice *s = SYS_BUS_DEVICE(dev); - int irq = sbsa_ref_irqmap[SBSA_GWDT]; + int irq = sbsa_ref_irqmap[SBSA_GWDT_WS0]; sysbus_realize_and_unref(s, &error_fatal); sysbus_mmio_map(s, 0, rbase); -- 2.20.1 From: Guenter Roeck <linux@roeck-us.net> Instantiate SAI1/2/3 as unimplemented devices to avoid Linux kernel crashes such as the following. Unhandled fault: external abort on non-linefetch (0x808) at 0xd19b0000 pgd = (ptrval) [d19b0000] *pgd=82711811, *pte=308a0653, *ppte=308a0453 Internal error: : 808 [#1] SMP ARM Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.14.0-rc5 #1 ... [<c095e974>] (regmap_mmio_write32le) from [<c095eb48>] (regmap_mmio_write+0x3c/0x54) [<c095eb48>] (regmap_mmio_write) from [<c09580f4>] (_regmap_write+0x4c/0x1f0) [<c09580f4>] (_regmap_write) from [<c0959b28>] (regmap_write+0x3c/0x60) [<c0959b28>] (regmap_write) from [<c0d41130>] (fsl_sai_runtime_resume+0x9c/0x1ec) [<c0d41130>] (fsl_sai_runtime_resume) from [<c0942464>] (__rpm_callback+0x3c/0x108) [<c0942464>] (__rpm_callback) from [<c0942590>] (rpm_callback+0x60/0x64) [<c0942590>] (rpm_callback) from [<c0942b60>] (rpm_resume+0x5cc/0x808) [<c0942b60>] (rpm_resume) from [<c0942dfc>] (__pm_runtime_resume+0x60/0xa0) [<c0942dfc>] (__pm_runtime_resume) from [<c0d4231c>] (fsl_sai_probe+0x2b8/0x65c) [<c0d4231c>] (fsl_sai_probe) from [<c0935b08>] (platform_probe+0x58/0xb8) [<c0935b08>] (platform_probe) from [<c0933264>] (really_probe.part.0+0x9c/0x334) [<c0933264>] (really_probe.part.0) from [<c093359c>] (__driver_probe_device+0xa0/0x138) [<c093359c>] (__driver_probe_device) from [<c0933664>] (driver_probe_device+0x30/0xc8) [<c0933664>] (driver_probe_device) from [<c0933c88>] (__driver_attach+0x90/0x130) [<c0933c88>] (__driver_attach) from [<c0931060>] (bus_for_each_dev+0x78/0xb8) [<c0931060>] (bus_for_each_dev) from [<c093254c>] (bus_add_driver+0xf0/0x1d8) [<c093254c>] (bus_add_driver) from [<c0934a30>] (driver_register+0x88/0x118) [<c0934a30>] (driver_register) from [<c01022c0>] (do_one_initcall+0x7c/0x3a4) [<c01022c0>] (do_one_initcall) from [<c1601204>] (kernel_init_freeable+0x198/0x22c) [<c1601204>] (kernel_init_freeable) from [<c0f5ff2c>] (kernel_init+0x10/0x128) [<c0f5ff2c>] (kernel_init) from [<c010013c>] (ret_from_fork+0x14/0x38) Signed-off-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20210810175607.538090-1-linux@roeck-us.net Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx7.h | 5 +++++ hw/arm/fsl-imx7.c | 7 +++++++ 2 files changed, 12 insertions(+) diff --git a/include/hw/arm/fsl-imx7.h b/include/hw/arm/fsl-imx7.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx7.h +++ b/include/hw/arm/fsl-imx7.h @@ -XXX,XX +XXX,XX @@ enum FslIMX7MemoryMap { FSL_IMX7_UART6_ADDR = 0x30A80000, FSL_IMX7_UART7_ADDR = 0x30A90000, + FSL_IMX7_SAI1_ADDR = 0x308A0000, + FSL_IMX7_SAI2_ADDR = 0x308B0000, + FSL_IMX7_SAI3_ADDR = 0x308C0000, + FSL_IMX7_SAIn_SIZE = 0x10000, + FSL_IMX7_ENET1_ADDR = 0x30BE0000, FSL_IMX7_ENET2_ADDR = 0x30BF0000, 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) create_unimplemented_device("can1", FSL_IMX7_CAN1_ADDR, FSL_IMX7_CANn_SIZE); create_unimplemented_device("can2", FSL_IMX7_CAN2_ADDR, FSL_IMX7_CANn_SIZE); + /* + * SAI (Audio SSI (Synchronous Serial Interface)) + */ + create_unimplemented_device("sai1", FSL_IMX7_SAI1_ADDR, FSL_IMX7_SAIn_SIZE); + create_unimplemented_device("sai2", FSL_IMX7_SAI2_ADDR, FSL_IMX7_SAIn_SIZE); + create_unimplemented_device("sai2", FSL_IMX7_SAI3_ADDR, FSL_IMX7_SAIn_SIZE); + /* * OCOTP */ -- 2.20.1 From: Sebastian Meyer <meyer@absint.com> With gdb 9.0 and better it is possible to connect to a gdbstub over unix sockets, which is better than a TCP socket connection in some situations. The QEMU command line to set this up is non-obvious; document it. Signed-off-by: Sebastian Meyer <meyer@absint.com> Message-id: 162867284829.27377.4784930719350564918-0@git.sr.ht [PMM: Tweaked commit message; adjusted wording in a couple of places; fixed rST formatting issue; moved section up out of the 'advanced debugging options' subsection] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/gdb.rst | 26 +++++++++++++++++++++++++- 1 file changed, 25 insertions(+), 1 deletion(-) diff --git a/docs/system/gdb.rst b/docs/system/gdb.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/gdb.rst +++ b/docs/system/gdb.rst @@ -XXX,XX +XXX,XX @@ The ``-s`` option will make QEMU listen for an incoming connection from gdb on TCP port 1234, and ``-S`` will make QEMU not start the guest until you tell it to from gdb. (If you want to specify which TCP port to use or to use something other than TCP for the gdbstub -connection, use the ``-gdb dev`` option instead of ``-s``.) +connection, use the ``-gdb dev`` option instead of ``-s``. See +`Using unix sockets`_ for an example.) .. parsed-literal:: @@ -XXX,XX +XXX,XX @@ not just those in the cluster you are currently working on:: (gdb) set schedule-multiple on +Using unix sockets +================== + +An alternate method for connecting gdb to the QEMU gdbstub is to use +a unix socket (if supported by your operating system). This is useful when +running several tests in parallel, or if you do not have a known free TCP +port (e.g. when running automated tests). + +First create a chardev with the appropriate options, then +instruct the gdbserver to use that device: + +.. parsed-literal:: + + |qemu_system| -chardev socket,path=/tmp/gdb-socket,server=on,wait=off,id=gdb0 -gdb chardev:gdb0 -S ... + +Start gdb as before, but this time connect using the path to +the socket:: + + (gdb) target remote /tmp/gdb-socket + +Note that to use a unix socket for the connection you will need +gdb version 9.0 or newer. + Advanced debugging options ========================== -- 2.20.1