As promised, another pullreq... This one's mostly RTH's patches. thanks -- PMM The following changes since commit 784c2e4f232adf5ef47a84a262ec72a07d068d6a: Merge remote-tracking branch 'remotes/jasowang/tags/net-pull-request' into staging (2018-10-19 15:30:40 +0100) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20181019 for you to fetch changes up to 88c9add25e7120e8622796c81ad3f3fb7f8d40e7: target/arm: Only flush tlb if ASID changes (2018-10-19 17:38:48 +0100) ---------------------------------------------------------------- target-arm queue: * ssi-sd: Make devices picking up backends unavailable with -device * Add support for VCPU event states * Move towards making ID registers the source of truth for whether a guest CPU implements a feature, rather than having parallel ID registers and feature bit flags * Implement various HCR hypervisor trap/config bits * Get IL bit correct for v7 syndrome values * Report correct syndrome for FP/SIMD traps to Hyp mode * hw/arm/boot: Increase compliance with kernel arm64 boot protocol * Refactor A32 Neon to use generic vector infrastructure * Fix a bug in A32 VLD2 "(multiple 2-element structures)" insn * net: cadence_gem: Report features correctly in ID register * Avoid some unnecessary TLB flushes on TTBR register writes ---------------------------------------------------------------- Dongjiu Geng (1): target/arm: Add support for VCPU event states Edgar E. Iglesias (2): net: cadence_gem: Announce availability of priority queues net: cadence_gem: Announce 64bit addressing support Markus Armbruster (1): ssi-sd: Make devices picking up backends unavailable with -device Peter Maydell (10): target/arm: Improve debug logging of AArch32 exception return target/arm: Make switch_mode() file-local target/arm: Implement HCR.FB target/arm: Implement HCR.DC target/arm: ISR_EL1 bits track virtual interrupts if IMO/FMO set target/arm: Implement HCR.VI and VF target/arm: Implement HCR.PTW target/arm: New utility function to extract EC from syndrome target/arm: Get IL bit correct for v7 syndrome values target/arm: Report correct syndrome for FP/SIMD traps to Hyp mode Richard Henderson (30): target/arm: Move some system registers into a substructure target/arm: V8M should not imply V7VE target/arm: Convert v8 extensions from feature bits to isar tests target/arm: Convert division from feature bits to isar0 tests target/arm: Convert jazelle from feature bit to isar1 test target/arm: Convert t32ee from feature bit to isar3 test target/arm: Convert sve from feature bit to aa64pfr0 test target/arm: Convert v8.2-fp16 from feature bit to aa64pfr0 test target/arm: Hoist address increment for vector memory ops target/arm: Don't call tcg_clear_temp_count target/arm: Use tcg_gen_gvec_dup_i64 for LD[1-4]R target/arm: Promote consecutive memory ops for aa64 target/arm: Mark some arrays const target/arm: Use gvec for NEON VDUP target/arm: Use gvec for NEON VMOV, VMVN, VBIC & VORR (immediate) target/arm: Use gvec for NEON_3R_LOGIC insns target/arm: Use gvec for NEON_3R_VADD_VSUB insns target/arm: Use gvec for NEON_2RM_VMN, NEON_2RM_VNEG target/arm: Use gvec for NEON_3R_VMUL target/arm: Use gvec for VSHR, VSHL target/arm: Use gvec for VSRA target/arm: Use gvec for VSRI, VSLI target/arm: Use gvec for NEON_3R_VML target/arm: Use gvec for NEON_3R_VTST_VCEQ, NEON_3R_VCGT, NEON_3R_VCGE target/arm: Use gvec for NEON VLD all lanes target/arm: Reorg NEON VLD/VST all elements target/arm: Promote consecutive memory ops for aa32 target/arm: Reorg NEON VLD/VST single element to one lane target/arm: Remove writefn from TTBR0_EL3 target/arm: Only flush tlb if ASID changes Stewart Hildebrand (1): hw/arm/boot: Increase compliance with kernel arm64 boot protocol target/arm/cpu.h | 227 ++++++- target/arm/internals.h | 45 +- target/arm/kvm_arm.h | 24 + target/arm/translate.h | 21 + hw/arm/boot.c | 18 + hw/intc/armv7m_nvic.c | 12 +- hw/net/cadence_gem.c | 9 +- hw/sd/ssi-sd.c | 2 + linux-user/aarch64/signal.c | 4 +- linux-user/elfload.c | 60 +- linux-user/syscall.c | 10 +- target/arm/cpu.c | 242 ++++---- target/arm/cpu64.c | 148 +++-- target/arm/helper.c | 397 ++++++++---- target/arm/kvm.c | 60 ++ target/arm/kvm32.c | 13 + target/arm/kvm64.c | 15 +- target/arm/machine.c | 28 +- target/arm/op_helper.c | 2 +- target/arm/translate-a64.c | 715 ++++----------------- target/arm/translate.c | 1451 ++++++++++++++++++++++++++++--------------- 21 files changed, 2021 insertions(+), 1482 deletions(-) From: Markus Armbruster <armbru@redhat.com> Device models aren't supposed to go on fishing expeditions for backends. They should expose suitable properties for the user to set. For onboard devices, board code sets them. Device ssi-sd picks up its block backend in its init() method with drive_get_next() instead. This mistake is already marked FIXME since commit af9e40a. Unset user_creatable to remove the mistake from our external interface. Since the SSI bus doesn't support hotplug, only -device can be affected. Only certain ARM machines have ssi-sd and provide an SSI bus for it; this patch breaks -device ssi-sd for these machines. No actual use of -device ssi-sd is known. Signed-off-by: Markus Armbruster <armbru@redhat.com> Acked-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Acked-by: Thomas Huth <thuth@redhat.com> Message-id: 20181009060835.4608-1-armbru@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/ssi-sd.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/hw/sd/ssi-sd.c b/hw/sd/ssi-sd.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/ssi-sd.c +++ b/hw/sd/ssi-sd.c @@ -XXX,XX +XXX,XX @@ static void ssi_sd_class_init(ObjectClass *klass, void *data) k->cs_polarity = SSI_CS_LOW; dc->vmsd = &vmstate_ssi_sd; dc->reset = ssi_sd_reset; + /* Reason: init() method uses drive_get_next() */ + dc->user_creatable = false; } static const TypeInfo ssi_sd_info = { -- 2.19.1 From: Dongjiu Geng <gengdongjiu@huawei.com> This patch extends the qemu-kvm state sync logic with support for KVM_GET/SET_VCPU_EVENTS, giving access to yet missing SError exception. And also it can support the exception state migration. The SError exception states include SError pending state and ESR value, the kvm_put/get_vcpu_events() will be called when set or get system registers. When do migration, if source machine has SError pending, QEMU will do this migration regardless whether the target machine supports to specify guest ESR value, because if target machine does not support that, it can also inject the SError with zero ESR value. Signed-off-by: Dongjiu Geng <gengdongjiu@huawei.com> Reviewed-by: Andrew Jones <drjones@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1538067351-23931-3-git-send-email-gengdongjiu@huawei.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 7 ++++++ target/arm/kvm_arm.h | 24 ++++++++++++++++++ target/arm/kvm.c | 60 ++++++++++++++++++++++++++++++++++++++++++++ target/arm/kvm32.c | 13 ++++++++++ target/arm/kvm64.c | 13 ++++++++++ target/arm/machine.c | 22 ++++++++++++++++ 6 files changed, 139 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUARMState { */ } exception; + /* Information associated with an SError */ + struct { + uint8_t pending; + uint8_t has_esr; + uint64_t esr; + } serror; + /* Thumb-2 EE state. */ uint32_t teecr; uint32_t teehbr; diff --git a/target/arm/kvm_arm.h b/target/arm/kvm_arm.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm_arm.h +++ b/target/arm/kvm_arm.h @@ -XXX,XX +XXX,XX @@ bool write_kvmstate_to_list(ARMCPU *cpu); */ void kvm_arm_reset_vcpu(ARMCPU *cpu); +/** + * kvm_arm_init_serror_injection: + * @cs: CPUState + * + * Check whether KVM can set guest SError syndrome. + */ +void kvm_arm_init_serror_injection(CPUState *cs); + +/** + * kvm_get_vcpu_events: + * @cpu: ARMCPU + * + * Get VCPU related state from kvm. + */ +int kvm_get_vcpu_events(ARMCPU *cpu); + +/** + * kvm_put_vcpu_events: + * @cpu: ARMCPU + * + * Put VCPU related state to kvm. + */ +int kvm_put_vcpu_events(ARMCPU *cpu); + #ifdef CONFIG_KVM /** * kvm_arm_create_scratch_host_vcpu: 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 @@ const KVMCapabilityInfo kvm_arch_required_capabilities[] = { }; static bool cap_has_mp_state; +static bool cap_has_inject_serror_esr; static ARMHostCPUFeatures arm_host_cpu_features; @@ -XXX,XX +XXX,XX @@ int kvm_arm_vcpu_init(CPUState *cs) return kvm_vcpu_ioctl(cs, KVM_ARM_VCPU_INIT, &init); } +void kvm_arm_init_serror_injection(CPUState *cs) +{ + cap_has_inject_serror_esr = kvm_check_extension(cs->kvm_state, + KVM_CAP_ARM_INJECT_SERROR_ESR); +} + bool kvm_arm_create_scratch_host_vcpu(const uint32_t *cpus_to_try, int *fdarray, struct kvm_vcpu_init *init) @@ -XXX,XX +XXX,XX @@ int kvm_arm_sync_mpstate_to_qemu(ARMCPU *cpu) return 0; } +int kvm_put_vcpu_events(ARMCPU *cpu) +{ + CPUARMState *env = &cpu->env; + struct kvm_vcpu_events events; + int ret; + + if (!kvm_has_vcpu_events()) { + return 0; + } + + memset(&events, 0, sizeof(events)); + events.exception.serror_pending = env->serror.pending; + + /* Inject SError to guest with specified syndrome if host kernel + * supports it, otherwise inject SError without syndrome. + */ + if (cap_has_inject_serror_esr) { + events.exception.serror_has_esr = env->serror.has_esr; + events.exception.serror_esr = env->serror.esr; + } + + ret = kvm_vcpu_ioctl(CPU(cpu), KVM_SET_VCPU_EVENTS, &events); + if (ret) { + error_report("failed to put vcpu events"); + } + + return ret; +} + +int kvm_get_vcpu_events(ARMCPU *cpu) +{ + CPUARMState *env = &cpu->env; + struct kvm_vcpu_events events; + int ret; + + if (!kvm_has_vcpu_events()) { + return 0; + } + + memset(&events, 0, sizeof(events)); + ret = kvm_vcpu_ioctl(CPU(cpu), KVM_GET_VCPU_EVENTS, &events); + if (ret) { + error_report("failed to get vcpu events"); + return ret; + } + + env->serror.pending = events.exception.serror_pending; + env->serror.has_esr = events.exception.serror_has_esr; + env->serror.esr = events.exception.serror_esr; + + return 0; +} + void kvm_arch_pre_run(CPUState *cs, struct kvm_run *run) { } diff --git a/target/arm/kvm32.c b/target/arm/kvm32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm32.c +++ b/target/arm/kvm32.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_init_vcpu(CPUState *cs) } cpu->mp_affinity = mpidr & ARM32_AFFINITY_MASK; + /* Check whether userspace can specify guest syndrome value */ + kvm_arm_init_serror_injection(cs); + return kvm_arm_init_cpreg_list(cpu); } @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) return ret; } + ret = kvm_put_vcpu_events(cpu); + if (ret) { + return ret; + } + /* Note that we do not call write_cpustate_to_list() * here, so we are only writing the tuple list back to * KVM. This is safe because nothing can change the @@ -XXX,XX +XXX,XX @@ int kvm_arch_get_registers(CPUState *cs) } vfp_set_fpscr(env, fpscr); + ret = kvm_get_vcpu_events(cpu); + if (ret) { + return ret; + } + if (!write_kvmstate_to_list(cpu)) { return EINVAL; } diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_init_vcpu(CPUState *cs) kvm_arm_init_debug(cs); + /* Check whether user space can specify guest syndrome value */ + kvm_arm_init_serror_injection(cs); + return kvm_arm_init_cpreg_list(cpu); } @@ -XXX,XX +XXX,XX @@ int kvm_arch_put_registers(CPUState *cs, int level) return ret; } + ret = kvm_put_vcpu_events(cpu); + if (ret) { + return ret; + } + if (!write_list_to_kvmstate(cpu, level)) { return EINVAL; } @@ -XXX,XX +XXX,XX @@ int kvm_arch_get_registers(CPUState *cs) } vfp_set_fpcr(env, fpr); + ret = kvm_get_vcpu_events(cpu); + if (ret) { + return ret; + } + if (!write_kvmstate_to_list(cpu)) { return EINVAL; } diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_sve = { }; #endif /* AARCH64 */ +static bool serror_needed(void *opaque) +{ + ARMCPU *cpu = opaque; + CPUARMState *env = &cpu->env; + + return env->serror.pending != 0; +} + +static const VMStateDescription vmstate_serror = { + .name = "cpu/serror", + .version_id = 1, + .minimum_version_id = 1, + .needed = serror_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT8(env.serror.pending, ARMCPU), + VMSTATE_UINT8(env.serror.has_esr, ARMCPU), + VMSTATE_UINT64(env.serror.esr, ARMCPU), + VMSTATE_END_OF_LIST() + } +}; + static bool m_needed(void *opaque) { ARMCPU *cpu = opaque; @@ -XXX,XX +XXX,XX @@ const VMStateDescription vmstate_arm_cpu = { #ifdef TARGET_AARCH64 &vmstate_sve, #endif + &vmstate_serror, NULL } }; -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Create struct ARMISARegisters, to be accessed during translation. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 32 ++++---- hw/intc/armv7m_nvic.c | 12 +-- target/arm/cpu.c | 178 +++++++++++++++++++++--------------------- target/arm/cpu64.c | 70 ++++++++--------- target/arm/helper.c | 28 +++---- 5 files changed, 162 insertions(+), 158 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ struct ARMCPU { * ARMv7AR ARM Architecture Reference Manual. A reset_ prefix * is used for reset values of non-constant registers; no reset_ * prefix means a constant register. + * Some of these registers are split out into a substructure that + * is shared with the translators to control the ISA. */ + struct ARMISARegisters { + uint32_t id_isar0; + uint32_t id_isar1; + uint32_t id_isar2; + uint32_t id_isar3; + uint32_t id_isar4; + uint32_t id_isar5; + uint32_t id_isar6; + uint32_t mvfr0; + uint32_t mvfr1; + uint32_t mvfr2; + uint64_t id_aa64isar0; + uint64_t id_aa64isar1; + uint64_t id_aa64pfr0; + uint64_t id_aa64pfr1; + } isar; uint32_t midr; uint32_t revidr; uint32_t reset_fpsid; - uint32_t mvfr0; - uint32_t mvfr1; - uint32_t mvfr2; uint32_t ctr; uint32_t reset_sctlr; uint32_t id_pfr0; @@ -XXX,XX +XXX,XX @@ struct ARMCPU { uint32_t id_mmfr2; uint32_t id_mmfr3; uint32_t id_mmfr4; - uint32_t id_isar0; - uint32_t id_isar1; - uint32_t id_isar2; - uint32_t id_isar3; - uint32_t id_isar4; - uint32_t id_isar5; - uint32_t id_isar6; - uint64_t id_aa64pfr0; - uint64_t id_aa64pfr1; uint64_t id_aa64dfr0; uint64_t id_aa64dfr1; uint64_t id_aa64afr0; uint64_t id_aa64afr1; - uint64_t id_aa64isar0; - uint64_t id_aa64isar1; uint64_t id_aa64mmfr0; uint64_t id_aa64mmfr1; uint32_t dbgdidr; diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset, MemTxAttrs attrs) case 0xd5c: /* MMFR3. */ return cpu->id_mmfr3; case 0xd60: /* ISAR0. */ - return cpu->id_isar0; + return cpu->isar.id_isar0; case 0xd64: /* ISAR1. */ - return cpu->id_isar1; + return cpu->isar.id_isar1; case 0xd68: /* ISAR2. */ - return cpu->id_isar2; + return cpu->isar.id_isar2; case 0xd6c: /* ISAR3. */ - return cpu->id_isar3; + return cpu->isar.id_isar3; case 0xd70: /* ISAR4. */ - return cpu->id_isar4; + return cpu->isar.id_isar4; case 0xd74: /* ISAR5. */ - return cpu->id_isar5; + return cpu->isar.id_isar5; case 0xd78: /* CLIDR */ return cpu->clidr; case 0xd7c: /* CTR */ diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(CPUState *s) g_hash_table_foreach(cpu->cp_regs, cp_reg_check_reset, cpu); env->vfp.xregs[ARM_VFP_FPSID] = cpu->reset_fpsid; - env->vfp.xregs[ARM_VFP_MVFR0] = cpu->mvfr0; - env->vfp.xregs[ARM_VFP_MVFR1] = cpu->mvfr1; - env->vfp.xregs[ARM_VFP_MVFR2] = cpu->mvfr2; + env->vfp.xregs[ARM_VFP_MVFR0] = cpu->isar.mvfr0; + env->vfp.xregs[ARM_VFP_MVFR1] = cpu->isar.mvfr1; + env->vfp.xregs[ARM_VFP_MVFR2] = cpu->isar.mvfr2; cpu->power_state = cpu->start_powered_off ? PSCI_OFF : PSCI_ON; s->halted = cpu->start_powered_off; @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) * registers as well. These are id_pfr1[7:4] and id_aa64pfr0[15:12]. */ cpu->id_pfr1 &= ~0xf0; - cpu->id_aa64pfr0 &= ~0xf000; + cpu->isar.id_aa64pfr0 &= ~0xf000; } if (!cpu->has_el2) { @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) * registers if we don't have EL2. These are id_pfr1[15:12] and * id_aa64pfr0_el1[11:8]. */ - cpu->id_aa64pfr0 &= ~0xf00; + cpu->isar.id_aa64pfr0 &= ~0xf00; cpu->id_pfr1 &= ~0xf000; } @@ -XXX,XX +XXX,XX @@ static void arm1136_r2_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_CACHE_BLOCK_OPS); cpu->midr = 0x4107b362; cpu->reset_fpsid = 0x410120b4; - cpu->mvfr0 = 0x11111111; - cpu->mvfr1 = 0x00000000; + cpu->isar.mvfr0 = 0x11111111; + cpu->isar.mvfr1 = 0x00000000; cpu->ctr = 0x1dd20d2; cpu->reset_sctlr = 0x00050078; cpu->id_pfr0 = 0x111; @@ -XXX,XX +XXX,XX @@ static void arm1136_r2_initfn(Object *obj) cpu->id_mmfr0 = 0x01130003; cpu->id_mmfr1 = 0x10030302; cpu->id_mmfr2 = 0x01222110; - cpu->id_isar0 = 0x00140011; - cpu->id_isar1 = 0x12002111; - cpu->id_isar2 = 0x11231111; - cpu->id_isar3 = 0x01102131; - cpu->id_isar4 = 0x141; + cpu->isar.id_isar0 = 0x00140011; + cpu->isar.id_isar1 = 0x12002111; + cpu->isar.id_isar2 = 0x11231111; + cpu->isar.id_isar3 = 0x01102131; + cpu->isar.id_isar4 = 0x141; cpu->reset_auxcr = 7; } @@ -XXX,XX +XXX,XX @@ static void arm1136_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_CACHE_BLOCK_OPS); cpu->midr = 0x4117b363; cpu->reset_fpsid = 0x410120b4; - cpu->mvfr0 = 0x11111111; - cpu->mvfr1 = 0x00000000; + cpu->isar.mvfr0 = 0x11111111; + cpu->isar.mvfr1 = 0x00000000; cpu->ctr = 0x1dd20d2; cpu->reset_sctlr = 0x00050078; cpu->id_pfr0 = 0x111; @@ -XXX,XX +XXX,XX @@ static void arm1136_initfn(Object *obj) cpu->id_mmfr0 = 0x01130003; cpu->id_mmfr1 = 0x10030302; cpu->id_mmfr2 = 0x01222110; - cpu->id_isar0 = 0x00140011; - cpu->id_isar1 = 0x12002111; - cpu->id_isar2 = 0x11231111; - cpu->id_isar3 = 0x01102131; - cpu->id_isar4 = 0x141; + cpu->isar.id_isar0 = 0x00140011; + cpu->isar.id_isar1 = 0x12002111; + cpu->isar.id_isar2 = 0x11231111; + cpu->isar.id_isar3 = 0x01102131; + cpu->isar.id_isar4 = 0x141; cpu->reset_auxcr = 7; } @@ -XXX,XX +XXX,XX @@ static void arm1176_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_EL3); cpu->midr = 0x410fb767; cpu->reset_fpsid = 0x410120b5; - cpu->mvfr0 = 0x11111111; - cpu->mvfr1 = 0x00000000; + cpu->isar.mvfr0 = 0x11111111; + cpu->isar.mvfr1 = 0x00000000; cpu->ctr = 0x1dd20d2; cpu->reset_sctlr = 0x00050078; cpu->id_pfr0 = 0x111; @@ -XXX,XX +XXX,XX @@ static void arm1176_initfn(Object *obj) cpu->id_mmfr0 = 0x01130003; cpu->id_mmfr1 = 0x10030302; cpu->id_mmfr2 = 0x01222100; - cpu->id_isar0 = 0x0140011; - cpu->id_isar1 = 0x12002111; - cpu->id_isar2 = 0x11231121; - cpu->id_isar3 = 0x01102131; - cpu->id_isar4 = 0x01141; + cpu->isar.id_isar0 = 0x0140011; + cpu->isar.id_isar1 = 0x12002111; + cpu->isar.id_isar2 = 0x11231121; + cpu->isar.id_isar3 = 0x01102131; + cpu->isar.id_isar4 = 0x01141; cpu->reset_auxcr = 7; } @@ -XXX,XX +XXX,XX @@ static void arm11mpcore_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); cpu->midr = 0x410fb022; cpu->reset_fpsid = 0x410120b4; - cpu->mvfr0 = 0x11111111; - cpu->mvfr1 = 0x00000000; + cpu->isar.mvfr0 = 0x11111111; + cpu->isar.mvfr1 = 0x00000000; cpu->ctr = 0x1d192992; /* 32K icache 32K dcache */ cpu->id_pfr0 = 0x111; cpu->id_pfr1 = 0x1; @@ -XXX,XX +XXX,XX @@ static void arm11mpcore_initfn(Object *obj) cpu->id_mmfr0 = 0x01100103; cpu->id_mmfr1 = 0x10020302; cpu->id_mmfr2 = 0x01222000; - cpu->id_isar0 = 0x00100011; - cpu->id_isar1 = 0x12002111; - cpu->id_isar2 = 0x11221011; - cpu->id_isar3 = 0x01102131; - cpu->id_isar4 = 0x141; + cpu->isar.id_isar0 = 0x00100011; + cpu->isar.id_isar1 = 0x12002111; + cpu->isar.id_isar2 = 0x11221011; + cpu->isar.id_isar3 = 0x01102131; + cpu->isar.id_isar4 = 0x141; cpu->reset_auxcr = 1; } @@ -XXX,XX +XXX,XX @@ static void cortex_m3_initfn(Object *obj) cpu->id_mmfr1 = 0x00000000; cpu->id_mmfr2 = 0x00000000; cpu->id_mmfr3 = 0x00000000; - cpu->id_isar0 = 0x01141110; - cpu->id_isar1 = 0x02111000; - cpu->id_isar2 = 0x21112231; - cpu->id_isar3 = 0x01111110; - cpu->id_isar4 = 0x01310102; - cpu->id_isar5 = 0x00000000; - cpu->id_isar6 = 0x00000000; + cpu->isar.id_isar0 = 0x01141110; + cpu->isar.id_isar1 = 0x02111000; + cpu->isar.id_isar2 = 0x21112231; + cpu->isar.id_isar3 = 0x01111110; + cpu->isar.id_isar4 = 0x01310102; + cpu->isar.id_isar5 = 0x00000000; + cpu->isar.id_isar6 = 0x00000000; } static void cortex_m4_initfn(Object *obj) @@ -XXX,XX +XXX,XX @@ static void cortex_m4_initfn(Object *obj) cpu->id_mmfr1 = 0x00000000; cpu->id_mmfr2 = 0x00000000; cpu->id_mmfr3 = 0x00000000; - cpu->id_isar0 = 0x01141110; - cpu->id_isar1 = 0x02111000; - cpu->id_isar2 = 0x21112231; - cpu->id_isar3 = 0x01111110; - cpu->id_isar4 = 0x01310102; - cpu->id_isar5 = 0x00000000; - cpu->id_isar6 = 0x00000000; + cpu->isar.id_isar0 = 0x01141110; + cpu->isar.id_isar1 = 0x02111000; + cpu->isar.id_isar2 = 0x21112231; + cpu->isar.id_isar3 = 0x01111110; + cpu->isar.id_isar4 = 0x01310102; + cpu->isar.id_isar5 = 0x00000000; + cpu->isar.id_isar6 = 0x00000000; } static void cortex_m33_initfn(Object *obj) @@ -XXX,XX +XXX,XX @@ static void cortex_m33_initfn(Object *obj) cpu->id_mmfr1 = 0x00000000; cpu->id_mmfr2 = 0x01000000; cpu->id_mmfr3 = 0x00000000; - cpu->id_isar0 = 0x01101110; - cpu->id_isar1 = 0x02212000; - cpu->id_isar2 = 0x20232232; - cpu->id_isar3 = 0x01111131; - cpu->id_isar4 = 0x01310132; - cpu->id_isar5 = 0x00000000; - cpu->id_isar6 = 0x00000000; + cpu->isar.id_isar0 = 0x01101110; + cpu->isar.id_isar1 = 0x02212000; + cpu->isar.id_isar2 = 0x20232232; + cpu->isar.id_isar3 = 0x01111131; + cpu->isar.id_isar4 = 0x01310132; + cpu->isar.id_isar5 = 0x00000000; + cpu->isar.id_isar6 = 0x00000000; cpu->clidr = 0x00000000; cpu->ctr = 0x8000c000; } @@ -XXX,XX +XXX,XX @@ static void cortex_r5_initfn(Object *obj) cpu->id_mmfr1 = 0x00000000; cpu->id_mmfr2 = 0x01200000; cpu->id_mmfr3 = 0x0211; - cpu->id_isar0 = 0x02101111; - cpu->id_isar1 = 0x13112111; - cpu->id_isar2 = 0x21232141; - cpu->id_isar3 = 0x01112131; - cpu->id_isar4 = 0x0010142; - cpu->id_isar5 = 0x0; - cpu->id_isar6 = 0x0; + cpu->isar.id_isar0 = 0x02101111; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232141; + cpu->isar.id_isar3 = 0x01112131; + cpu->isar.id_isar4 = 0x0010142; + cpu->isar.id_isar5 = 0x0; + cpu->isar.id_isar6 = 0x0; cpu->mp_is_up = true; cpu->pmsav7_dregion = 16; define_arm_cp_regs(cpu, cortexr5_cp_reginfo); @@ -XXX,XX +XXX,XX @@ static void cortex_a8_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_EL3); cpu->midr = 0x410fc080; cpu->reset_fpsid = 0x410330c0; - cpu->mvfr0 = 0x11110222; - cpu->mvfr1 = 0x00011111; + cpu->isar.mvfr0 = 0x11110222; + cpu->isar.mvfr1 = 0x00011111; cpu->ctr = 0x82048004; cpu->reset_sctlr = 0x00c50078; cpu->id_pfr0 = 0x1031; @@ -XXX,XX +XXX,XX @@ static void cortex_a8_initfn(Object *obj) cpu->id_mmfr1 = 0x20000000; cpu->id_mmfr2 = 0x01202000; cpu->id_mmfr3 = 0x11; - cpu->id_isar0 = 0x00101111; - cpu->id_isar1 = 0x12112111; - cpu->id_isar2 = 0x21232031; - cpu->id_isar3 = 0x11112131; - cpu->id_isar4 = 0x00111142; + cpu->isar.id_isar0 = 0x00101111; + cpu->isar.id_isar1 = 0x12112111; + cpu->isar.id_isar2 = 0x21232031; + cpu->isar.id_isar3 = 0x11112131; + cpu->isar.id_isar4 = 0x00111142; cpu->dbgdidr = 0x15141000; cpu->clidr = (1 << 27) | (2 << 24) | 3; cpu->ccsidr[0] = 0xe007e01a; /* 16k L1 dcache. */ @@ -XXX,XX +XXX,XX @@ static void cortex_a9_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_CBAR); cpu->midr = 0x410fc090; cpu->reset_fpsid = 0x41033090; - cpu->mvfr0 = 0x11110222; - cpu->mvfr1 = 0x01111111; + cpu->isar.mvfr0 = 0x11110222; + cpu->isar.mvfr1 = 0x01111111; cpu->ctr = 0x80038003; cpu->reset_sctlr = 0x00c50078; cpu->id_pfr0 = 0x1031; @@ -XXX,XX +XXX,XX @@ static void cortex_a9_initfn(Object *obj) cpu->id_mmfr1 = 0x20000000; cpu->id_mmfr2 = 0x01230000; cpu->id_mmfr3 = 0x00002111; - cpu->id_isar0 = 0x00101111; - cpu->id_isar1 = 0x13112111; - cpu->id_isar2 = 0x21232041; - cpu->id_isar3 = 0x11112131; - cpu->id_isar4 = 0x00111142; + cpu->isar.id_isar0 = 0x00101111; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232041; + cpu->isar.id_isar3 = 0x11112131; + cpu->isar.id_isar4 = 0x00111142; cpu->dbgdidr = 0x35141000; cpu->clidr = (1 << 27) | (1 << 24) | 3; cpu->ccsidr[0] = 0xe00fe019; /* 16k L1 dcache. */ @@ -XXX,XX +XXX,XX @@ static void cortex_a7_initfn(Object *obj) cpu->kvm_target = QEMU_KVM_ARM_TARGET_CORTEX_A7; cpu->midr = 0x410fc075; cpu->reset_fpsid = 0x41023075; - cpu->mvfr0 = 0x10110222; - cpu->mvfr1 = 0x11111111; + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x11111111; cpu->ctr = 0x84448003; cpu->reset_sctlr = 0x00c50078; cpu->id_pfr0 = 0x00001131; @@ -XXX,XX +XXX,XX @@ static void cortex_a7_initfn(Object *obj) /* a7_mpcore_r0p5_trm, page 4-4 gives 0x01101110; but * table 4-41 gives 0x02101110, which includes the arm div insns. */ - cpu->id_isar0 = 0x02101110; - cpu->id_isar1 = 0x13112111; - cpu->id_isar2 = 0x21232041; - cpu->id_isar3 = 0x11112131; - cpu->id_isar4 = 0x10011142; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232041; + cpu->isar.id_isar3 = 0x11112131; + cpu->isar.id_isar4 = 0x10011142; cpu->dbgdidr = 0x3515f005; cpu->clidr = 0x0a200023; cpu->ccsidr[0] = 0x701fe00a; /* 32K L1 dcache */ @@ -XXX,XX +XXX,XX @@ static void cortex_a15_initfn(Object *obj) cpu->kvm_target = QEMU_KVM_ARM_TARGET_CORTEX_A15; cpu->midr = 0x412fc0f1; cpu->reset_fpsid = 0x410430f0; - cpu->mvfr0 = 0x10110222; - cpu->mvfr1 = 0x11111111; + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x11111111; cpu->ctr = 0x8444c004; cpu->reset_sctlr = 0x00c50078; cpu->id_pfr0 = 0x00001131; @@ -XXX,XX +XXX,XX @@ static void cortex_a15_initfn(Object *obj) cpu->id_mmfr1 = 0x20000000; cpu->id_mmfr2 = 0x01240000; cpu->id_mmfr3 = 0x02102211; - cpu->id_isar0 = 0x02101110; - cpu->id_isar1 = 0x13112111; - cpu->id_isar2 = 0x21232041; - cpu->id_isar3 = 0x11112131; - cpu->id_isar4 = 0x10011142; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232041; + cpu->isar.id_isar3 = 0x11112131; + cpu->isar.id_isar4 = 0x10011142; cpu->dbgdidr = 0x3515f021; cpu->clidr = 0x0a200023; cpu->ccsidr[0] = 0x701fe00a; /* 32K L1 dcache */ diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_a57_initfn(Object *obj) cpu->midr = 0x411fd070; cpu->revidr = 0x00000000; cpu->reset_fpsid = 0x41034070; - cpu->mvfr0 = 0x10110222; - cpu->mvfr1 = 0x12111111; - cpu->mvfr2 = 0x00000043; + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x12111111; + cpu->isar.mvfr2 = 0x00000043; cpu->ctr = 0x8444c004; cpu->reset_sctlr = 0x00c50838; cpu->id_pfr0 = 0x00000131; @@ -XXX,XX +XXX,XX @@ static void aarch64_a57_initfn(Object *obj) cpu->id_mmfr1 = 0x40000000; cpu->id_mmfr2 = 0x01260000; cpu->id_mmfr3 = 0x02102211; - cpu->id_isar0 = 0x02101110; - cpu->id_isar1 = 0x13112111; - cpu->id_isar2 = 0x21232042; - cpu->id_isar3 = 0x01112131; - cpu->id_isar4 = 0x00011142; - cpu->id_isar5 = 0x00011121; - cpu->id_isar6 = 0; - cpu->id_aa64pfr0 = 0x00002222; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232042; + cpu->isar.id_isar3 = 0x01112131; + cpu->isar.id_isar4 = 0x00011142; + cpu->isar.id_isar5 = 0x00011121; + cpu->isar.id_isar6 = 0; + cpu->isar.id_aa64pfr0 = 0x00002222; cpu->id_aa64dfr0 = 0x10305106; cpu->pmceid0 = 0x00000000; cpu->pmceid1 = 0x00000000; - cpu->id_aa64isar0 = 0x00011120; + cpu->isar.id_aa64isar0 = 0x00011120; cpu->id_aa64mmfr0 = 0x00001124; cpu->dbgdidr = 0x3516d000; cpu->clidr = 0x0a200023; @@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj) cpu->midr = 0x410fd034; cpu->revidr = 0x00000000; cpu->reset_fpsid = 0x41034070; - cpu->mvfr0 = 0x10110222; - cpu->mvfr1 = 0x12111111; - cpu->mvfr2 = 0x00000043; + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x12111111; + cpu->isar.mvfr2 = 0x00000043; cpu->ctr = 0x84448004; /* L1Ip = VIPT */ cpu->reset_sctlr = 0x00c50838; cpu->id_pfr0 = 0x00000131; @@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj) cpu->id_mmfr1 = 0x40000000; cpu->id_mmfr2 = 0x01260000; cpu->id_mmfr3 = 0x02102211; - cpu->id_isar0 = 0x02101110; - cpu->id_isar1 = 0x13112111; - cpu->id_isar2 = 0x21232042; - cpu->id_isar3 = 0x01112131; - cpu->id_isar4 = 0x00011142; - cpu->id_isar5 = 0x00011121; - cpu->id_isar6 = 0; - cpu->id_aa64pfr0 = 0x00002222; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232042; + cpu->isar.id_isar3 = 0x01112131; + cpu->isar.id_isar4 = 0x00011142; + cpu->isar.id_isar5 = 0x00011121; + cpu->isar.id_isar6 = 0; + cpu->isar.id_aa64pfr0 = 0x00002222; cpu->id_aa64dfr0 = 0x10305106; - cpu->id_aa64isar0 = 0x00011120; + cpu->isar.id_aa64isar0 = 0x00011120; cpu->id_aa64mmfr0 = 0x00001122; /* 40 bit physical addr */ cpu->dbgdidr = 0x3516d000; cpu->clidr = 0x0a200023; @@ -XXX,XX +XXX,XX @@ static void aarch64_a72_initfn(Object *obj) cpu->midr = 0x410fd083; cpu->revidr = 0x00000000; cpu->reset_fpsid = 0x41034080; - cpu->mvfr0 = 0x10110222; - cpu->mvfr1 = 0x12111111; - cpu->mvfr2 = 0x00000043; + cpu->isar.mvfr0 = 0x10110222; + cpu->isar.mvfr1 = 0x12111111; + cpu->isar.mvfr2 = 0x00000043; cpu->ctr = 0x8444c004; cpu->reset_sctlr = 0x00c50838; cpu->id_pfr0 = 0x00000131; @@ -XXX,XX +XXX,XX @@ static void aarch64_a72_initfn(Object *obj) cpu->id_mmfr1 = 0x40000000; cpu->id_mmfr2 = 0x01260000; cpu->id_mmfr3 = 0x02102211; - cpu->id_isar0 = 0x02101110; - cpu->id_isar1 = 0x13112111; - cpu->id_isar2 = 0x21232042; - cpu->id_isar3 = 0x01112131; - cpu->id_isar4 = 0x00011142; - cpu->id_isar5 = 0x00011121; - cpu->id_aa64pfr0 = 0x00002222; + cpu->isar.id_isar0 = 0x02101110; + cpu->isar.id_isar1 = 0x13112111; + cpu->isar.id_isar2 = 0x21232042; + cpu->isar.id_isar3 = 0x01112131; + cpu->isar.id_isar4 = 0x00011142; + cpu->isar.id_isar5 = 0x00011121; + cpu->isar.id_aa64pfr0 = 0x00002222; cpu->id_aa64dfr0 = 0x10305106; cpu->pmceid0 = 0x00000000; cpu->pmceid1 = 0x00000000; - cpu->id_aa64isar0 = 0x00011120; + cpu->isar.id_aa64isar0 = 0x00011120; cpu->id_aa64mmfr0 = 0x00001124; cpu->dbgdidr = 0x3516d000; cpu->clidr = 0x0a200023; 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 uint64_t id_pfr1_read(CPUARMState *env, const ARMCPRegInfo *ri) static uint64_t id_aa64pfr0_read(CPUARMState *env, const ARMCPRegInfo *ri) { ARMCPU *cpu = arm_env_get_cpu(env); - uint64_t pfr0 = cpu->id_aa64pfr0; + uint64_t pfr0 = cpu->isar.id_aa64pfr0; if (env->gicv3state) { pfr0 |= 1 << 24; @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "ID_ISAR0", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 0, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_isar0 }, + .resetvalue = cpu->isar.id_isar0 }, { .name = "ID_ISAR1", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 1, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_isar1 }, + .resetvalue = cpu->isar.id_isar1 }, { .name = "ID_ISAR2", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 2, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_isar2 }, + .resetvalue = cpu->isar.id_isar2 }, { .name = "ID_ISAR3", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 3, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_isar3 }, + .resetvalue = cpu->isar.id_isar3 }, { .name = "ID_ISAR4", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 4, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_isar4 }, + .resetvalue = cpu->isar.id_isar4 }, { .name = "ID_ISAR5", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 5, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_isar5 }, + .resetvalue = cpu->isar.id_isar5 }, { .name = "ID_MMFR4", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 6, .access = PL1_R, .type = ARM_CP_CONST, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "ID_ISAR6", .state = ARM_CP_STATE_BOTH, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 2, .opc2 = 7, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_isar6 }, + .resetvalue = cpu->isar.id_isar6 }, REGINFO_SENTINEL }; define_arm_cp_regs(cpu, v6_idregs); @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "ID_AA64PFR1_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 1, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_aa64pfr1}, + .resetvalue = cpu->isar.id_aa64pfr1}, { .name = "ID_AA64PFR2_EL1_RESERVED", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 4, .opc2 = 2, .access = PL1_R, .type = ARM_CP_CONST, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "ID_AA64ISAR0_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 6, .opc2 = 0, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_aa64isar0 }, + .resetvalue = cpu->isar.id_aa64isar0 }, { .name = "ID_AA64ISAR1_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 6, .opc2 = 1, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->id_aa64isar1 }, + .resetvalue = cpu->isar.id_aa64isar1 }, { .name = "ID_AA64ISAR2_EL1_RESERVED", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 6, .opc2 = 2, .access = PL1_R, .type = ARM_CP_CONST, @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) { .name = "MVFR0_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 3, .opc2 = 0, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->mvfr0 }, + .resetvalue = cpu->isar.mvfr0 }, { .name = "MVFR1_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 3, .opc2 = 1, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->mvfr1 }, + .resetvalue = cpu->isar.mvfr1 }, { .name = "MVFR2_EL1", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 3, .opc2 = 2, .access = PL1_R, .type = ARM_CP_CONST, - .resetvalue = cpu->mvfr2 }, + .resetvalue = cpu->isar.mvfr2 }, { .name = "MVFR3_EL1_RESERVED", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 0, .crn = 0, .crm = 3, .opc2 = 3, .access = PL1_R, .type = ARM_CP_CONST, -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Instantiating mps2-an505 (cortex-m33) will fail make check when V7VE asserts that ID_ISAR0.Divide includes ARM division. It is also wrong to include ARM_FEATURE_LPAE. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) /* Some features automatically imply others: */ if (arm_feature(env, ARM_FEATURE_V8)) { - set_feature(env, ARM_FEATURE_V7VE); + if (arm_feature(env, ARM_FEATURE_M)) { + set_feature(env, ARM_FEATURE_V7); + } else { + set_feature(env, ARM_FEATURE_V7VE); + } } if (arm_feature(env, ARM_FEATURE_V7VE)) { /* v7 Virtualization Extensions. In real hardware this implies -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Most of the v8 extensions are self-contained within the ISAR registers and are not implied by other feature bits, which makes them the easiest to convert. Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-4-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 131 +++++++++++++++++++++++++++++++++---- target/arm/translate.h | 7 ++ linux-user/elfload.c | 46 ++++++++----- target/arm/cpu.c | 27 +++++--- target/arm/cpu64.c | 57 +++++++++------- target/arm/translate-a64.c | 101 ++++++++++++++-------------- target/arm/translate.c | 36 +++++----- 7 files changed, 273 insertions(+), 132 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef enum ARMPSCIState { PSCI_ON_PENDING = 2 } ARMPSCIState; +typedef struct ARMISARegisters ARMISARegisters; + /** * ARMCPU: * @env: #CPUARMState @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_LPAE, /* has Large Physical Address Extension */ ARM_FEATURE_V8, ARM_FEATURE_AARCH64, /* supports 64 bit mode */ - ARM_FEATURE_V8_AES, /* implements AES part of v8 Crypto Extensions */ ARM_FEATURE_CBAR, /* has cp15 CBAR */ ARM_FEATURE_CRC, /* ARMv8 CRC instructions */ ARM_FEATURE_CBAR_RO, /* has cp15 CBAR and it is read-only */ ARM_FEATURE_EL2, /* has EL2 Virtualization support */ ARM_FEATURE_EL3, /* has EL3 Secure monitor support */ - ARM_FEATURE_V8_SHA1, /* implements SHA1 part of v8 Crypto Extensions */ - ARM_FEATURE_V8_SHA256, /* implements SHA256 part of v8 Crypto Extensions */ - ARM_FEATURE_V8_PMULL, /* implements PMULL part of v8 Crypto Extensions */ ARM_FEATURE_THUMB_DSP, /* DSP insns supported in the Thumb encodings */ ARM_FEATURE_PMU, /* has PMU support */ ARM_FEATURE_VBAR, /* has cp15 VBAR */ ARM_FEATURE_M_SECURITY, /* M profile Security Extension */ ARM_FEATURE_JAZELLE, /* has (trivial) Jazelle implementation */ ARM_FEATURE_SVE, /* has Scalable Vector Extension */ - ARM_FEATURE_V8_SHA512, /* implements SHA512 part of v8 Crypto Extensions */ - ARM_FEATURE_V8_SHA3, /* implements SHA3 part of v8 Crypto Extensions */ - ARM_FEATURE_V8_SM3, /* implements SM3 part of v8 Crypto Extensions */ - ARM_FEATURE_V8_SM4, /* implements SM4 part of v8 Crypto Extensions */ - ARM_FEATURE_V8_ATOMICS, /* ARMv8.1-Atomics feature */ - ARM_FEATURE_V8_RDM, /* implements v8.1 simd round multiply */ - ARM_FEATURE_V8_DOTPROD, /* implements v8.2 simd dot product */ ARM_FEATURE_V8_FP16, /* implements v8.2 half-precision float */ - ARM_FEATURE_V8_FCMA, /* has complex number part of v8.3 extensions. */ ARM_FEATURE_M_MAIN, /* M profile Main Extension */ }; @@ -XXX,XX +XXX,XX @@ static inline uint64_t *aa64_vfp_qreg(CPUARMState *env, unsigned regno) /* Shared between translate-sve.c and sve_helper.c. */ extern const uint64_t pred_esz_masks[4]; +/* + * 32-bit feature tests via id registers. + */ +static inline bool isar_feature_aa32_aes(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) != 0; +} + +static inline bool isar_feature_aa32_pmull(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) > 1; +} + +static inline bool isar_feature_aa32_sha1(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, SHA1) != 0; +} + +static inline bool isar_feature_aa32_sha2(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, SHA2) != 0; +} + +static inline bool isar_feature_aa32_crc32(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, CRC32) != 0; +} + +static inline bool isar_feature_aa32_rdm(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, RDM) != 0; +} + +static inline bool isar_feature_aa32_vcma(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar5, ID_ISAR5, VCMA) != 0; +} + +static inline bool isar_feature_aa32_dp(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar6, ID_ISAR6, DP) != 0; +} + +/* + * 64-bit feature tests via id registers. + */ +static inline bool isar_feature_aa64_aes(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, AES) != 0; +} + +static inline bool isar_feature_aa64_pmull(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, AES) > 1; +} + +static inline bool isar_feature_aa64_sha1(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA1) != 0; +} + +static inline bool isar_feature_aa64_sha256(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA2) != 0; +} + +static inline bool isar_feature_aa64_sha512(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA2) > 1; +} + +static inline bool isar_feature_aa64_crc32(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, CRC32) != 0; +} + +static inline bool isar_feature_aa64_atomics(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, ATOMIC) != 0; +} + +static inline bool isar_feature_aa64_rdm(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, RDM) != 0; +} + +static inline bool isar_feature_aa64_sha3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SHA3) != 0; +} + +static inline bool isar_feature_aa64_sm3(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SM3) != 0; +} + +static inline bool isar_feature_aa64_sm4(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, SM4) != 0; +} + +static inline bool isar_feature_aa64_dp(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar0, ID_AA64ISAR0, DP) != 0; +} + +static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; +} + +/* + * Forward to the above feature tests given an ARMCPU pointer. + */ +#define cpu_isar_feature(name, cpu) \ + ({ ARMCPU *cpu_ = (cpu); isar_feature_##name(&cpu_->isar); }) + #endif diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ /* internal defines */ typedef struct DisasContext { DisasContextBase base; + const ARMISARegisters *isar; target_ulong pc; target_ulong page_start; @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 get_ahp_flag(void) return ret; } +/* + * Forward to the isar_feature_* tests given a DisasContext pointer. + */ +#define dc_isar_feature(name, ctx) \ + ({ DisasContext *ctx_ = (ctx); isar_feature_##name(ctx_->isar); }) + #endif /* TARGET_ARM_TRANSLATE_H */ diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) /* probe for the extra features */ #define GET_FEATURE(feat, hwcap) \ do { if (arm_feature(&cpu->env, feat)) { hwcaps |= hwcap; } } while (0) + +#define GET_FEATURE_ID(feat, hwcap) \ + do { if (cpu_isar_feature(feat, cpu)) { hwcaps |= hwcap; } } while (0) + /* EDSP is in v5TE and above, but all our v5 CPUs are v5TE */ GET_FEATURE(ARM_FEATURE_V5, ARM_HWCAP_ARM_EDSP); GET_FEATURE(ARM_FEATURE_VFP, ARM_HWCAP_ARM_VFP); @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap2(void) ARMCPU *cpu = ARM_CPU(thread_cpu); uint32_t hwcaps = 0; - GET_FEATURE(ARM_FEATURE_V8_AES, ARM_HWCAP2_ARM_AES); - GET_FEATURE(ARM_FEATURE_V8_PMULL, ARM_HWCAP2_ARM_PMULL); - GET_FEATURE(ARM_FEATURE_V8_SHA1, ARM_HWCAP2_ARM_SHA1); - GET_FEATURE(ARM_FEATURE_V8_SHA256, ARM_HWCAP2_ARM_SHA2); - GET_FEATURE(ARM_FEATURE_CRC, ARM_HWCAP2_ARM_CRC32); + GET_FEATURE_ID(aa32_aes, ARM_HWCAP2_ARM_AES); + GET_FEATURE_ID(aa32_pmull, ARM_HWCAP2_ARM_PMULL); + GET_FEATURE_ID(aa32_sha1, ARM_HWCAP2_ARM_SHA1); + GET_FEATURE_ID(aa32_sha2, ARM_HWCAP2_ARM_SHA2); + GET_FEATURE_ID(aa32_crc32, ARM_HWCAP2_ARM_CRC32); return hwcaps; } #undef GET_FEATURE +#undef GET_FEATURE_ID #else /* 64 bit ARM definitions */ @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) /* probe for the extra features */ #define GET_FEATURE(feat, hwcap) \ do { if (arm_feature(&cpu->env, feat)) { hwcaps |= hwcap; } } while (0) - GET_FEATURE(ARM_FEATURE_V8_AES, ARM_HWCAP_A64_AES); - GET_FEATURE(ARM_FEATURE_V8_PMULL, ARM_HWCAP_A64_PMULL); - GET_FEATURE(ARM_FEATURE_V8_SHA1, ARM_HWCAP_A64_SHA1); - GET_FEATURE(ARM_FEATURE_V8_SHA256, ARM_HWCAP_A64_SHA2); - GET_FEATURE(ARM_FEATURE_CRC, ARM_HWCAP_A64_CRC32); - GET_FEATURE(ARM_FEATURE_V8_SHA3, ARM_HWCAP_A64_SHA3); - GET_FEATURE(ARM_FEATURE_V8_SM3, ARM_HWCAP_A64_SM3); - GET_FEATURE(ARM_FEATURE_V8_SM4, ARM_HWCAP_A64_SM4); - GET_FEATURE(ARM_FEATURE_V8_SHA512, ARM_HWCAP_A64_SHA512); +#define GET_FEATURE_ID(feat, hwcap) \ + do { if (cpu_isar_feature(feat, cpu)) { hwcaps |= hwcap; } } while (0) + + GET_FEATURE_ID(aa64_aes, ARM_HWCAP_A64_AES); + GET_FEATURE_ID(aa64_pmull, ARM_HWCAP_A64_PMULL); + GET_FEATURE_ID(aa64_sha1, ARM_HWCAP_A64_SHA1); + GET_FEATURE_ID(aa64_sha256, ARM_HWCAP_A64_SHA2); + GET_FEATURE_ID(aa64_sha512, ARM_HWCAP_A64_SHA512); + GET_FEATURE_ID(aa64_crc32, ARM_HWCAP_A64_CRC32); + GET_FEATURE_ID(aa64_sha3, ARM_HWCAP_A64_SHA3); + GET_FEATURE_ID(aa64_sm3, ARM_HWCAP_A64_SM3); + GET_FEATURE_ID(aa64_sm4, ARM_HWCAP_A64_SM4); GET_FEATURE(ARM_FEATURE_V8_FP16, ARM_HWCAP_A64_FPHP | ARM_HWCAP_A64_ASIMDHP); - GET_FEATURE(ARM_FEATURE_V8_ATOMICS, ARM_HWCAP_A64_ATOMICS); - GET_FEATURE(ARM_FEATURE_V8_RDM, ARM_HWCAP_A64_ASIMDRDM); - GET_FEATURE(ARM_FEATURE_V8_DOTPROD, ARM_HWCAP_A64_ASIMDDP); - GET_FEATURE(ARM_FEATURE_V8_FCMA, ARM_HWCAP_A64_FCMA); + GET_FEATURE_ID(aa64_atomics, ARM_HWCAP_A64_ATOMICS); + GET_FEATURE_ID(aa64_rdm, ARM_HWCAP_A64_ASIMDRDM); + GET_FEATURE_ID(aa64_dp, ARM_HWCAP_A64_ASIMDDP); + GET_FEATURE_ID(aa64_fcma, ARM_HWCAP_A64_FCMA); GET_FEATURE(ARM_FEATURE_SVE, ARM_HWCAP_A64_SVE); + #undef GET_FEATURE +#undef GET_FEATURE_ID return hwcaps; } 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) cortex_a15_initfn(obj); #ifdef CONFIG_USER_ONLY /* We don't set these in system emulation mode for the moment, - * since we don't correctly set the ID registers to advertise them, + * since we don't correctly set (all of) the ID registers to + * advertise them. */ set_feature(&cpu->env, ARM_FEATURE_V8); - set_feature(&cpu->env, ARM_FEATURE_V8_AES); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA1); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA256); - set_feature(&cpu->env, ARM_FEATURE_V8_PMULL); - set_feature(&cpu->env, ARM_FEATURE_CRC); - set_feature(&cpu->env, ARM_FEATURE_V8_RDM); - set_feature(&cpu->env, ARM_FEATURE_V8_DOTPROD); - set_feature(&cpu->env, ARM_FEATURE_V8_FCMA); + { + uint32_t t; + + t = cpu->isar.id_isar5; + t = FIELD_DP32(t, ID_ISAR5, AES, 2); + t = FIELD_DP32(t, ID_ISAR5, SHA1, 1); + t = FIELD_DP32(t, ID_ISAR5, SHA2, 1); + t = FIELD_DP32(t, ID_ISAR5, CRC32, 1); + t = FIELD_DP32(t, ID_ISAR5, RDM, 1); + t = FIELD_DP32(t, ID_ISAR5, VCMA, 1); + cpu->isar.id_isar5 = t; + + t = cpu->isar.id_isar6; + t = FIELD_DP32(t, ID_ISAR6, DP, 1); + cpu->isar.id_isar6 = t; + } #endif } } diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_a57_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_V8_AES); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA1); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA256); - set_feature(&cpu->env, ARM_FEATURE_V8_PMULL); - set_feature(&cpu->env, ARM_FEATURE_CRC); set_feature(&cpu->env, ARM_FEATURE_EL2); set_feature(&cpu->env, ARM_FEATURE_EL3); set_feature(&cpu->env, ARM_FEATURE_PMU); @@ -XXX,XX +XXX,XX @@ static void aarch64_a53_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_V8_AES); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA1); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA256); - set_feature(&cpu->env, ARM_FEATURE_V8_PMULL); - set_feature(&cpu->env, ARM_FEATURE_CRC); set_feature(&cpu->env, ARM_FEATURE_EL2); set_feature(&cpu->env, ARM_FEATURE_EL3); set_feature(&cpu->env, ARM_FEATURE_PMU); @@ -XXX,XX +XXX,XX @@ static void aarch64_a72_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_AARCH64); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); - set_feature(&cpu->env, ARM_FEATURE_V8_AES); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA1); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA256); - set_feature(&cpu->env, ARM_FEATURE_V8_PMULL); - set_feature(&cpu->env, ARM_FEATURE_CRC); set_feature(&cpu->env, ARM_FEATURE_EL2); set_feature(&cpu->env, ARM_FEATURE_EL3); set_feature(&cpu->env, ARM_FEATURE_PMU); @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) if (kvm_enabled()) { kvm_arm_set_cpu_features_from_host(cpu); } else { + uint64_t t; + uint32_t u; aarch64_a57_initfn(obj); + + t = cpu->isar.id_aa64isar0; + t = FIELD_DP64(t, ID_AA64ISAR0, AES, 2); /* AES + PMULL */ + t = FIELD_DP64(t, ID_AA64ISAR0, SHA1, 1); + t = FIELD_DP64(t, ID_AA64ISAR0, SHA2, 2); /* SHA512 */ + t = FIELD_DP64(t, ID_AA64ISAR0, CRC32, 1); + t = FIELD_DP64(t, ID_AA64ISAR0, ATOMIC, 2); + t = FIELD_DP64(t, ID_AA64ISAR0, RDM, 1); + t = FIELD_DP64(t, ID_AA64ISAR0, SHA3, 1); + t = FIELD_DP64(t, ID_AA64ISAR0, SM3, 1); + t = FIELD_DP64(t, ID_AA64ISAR0, SM4, 1); + t = FIELD_DP64(t, ID_AA64ISAR0, DP, 1); + cpu->isar.id_aa64isar0 = t; + + t = cpu->isar.id_aa64isar1; + t = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); + cpu->isar.id_aa64isar1 = t; + + /* Replicate the same data to the 32-bit id registers. */ + u = cpu->isar.id_isar5; + u = FIELD_DP32(u, ID_ISAR5, AES, 2); /* AES + PMULL */ + u = FIELD_DP32(u, ID_ISAR5, SHA1, 1); + u = FIELD_DP32(u, ID_ISAR5, SHA2, 1); + u = FIELD_DP32(u, ID_ISAR5, CRC32, 1); + u = FIELD_DP32(u, ID_ISAR5, RDM, 1); + u = FIELD_DP32(u, ID_ISAR5, VCMA, 1); + cpu->isar.id_isar5 = u; + + u = cpu->isar.id_isar6; + u = FIELD_DP32(u, ID_ISAR6, DP, 1); + cpu->isar.id_isar6 = u; + #ifdef CONFIG_USER_ONLY /* We don't set these in system emulation mode for the moment, * since we don't correctly set the ID registers to advertise them, @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) * whereas the architecture requires them to be present in both if * present in either. */ - set_feature(&cpu->env, ARM_FEATURE_V8_SHA512); - set_feature(&cpu->env, ARM_FEATURE_V8_SHA3); - set_feature(&cpu->env, ARM_FEATURE_V8_SM3); - set_feature(&cpu->env, ARM_FEATURE_V8_SM4); - set_feature(&cpu->env, ARM_FEATURE_V8_ATOMICS); - set_feature(&cpu->env, ARM_FEATURE_V8_RDM); - set_feature(&cpu->env, ARM_FEATURE_V8_DOTPROD); set_feature(&cpu->env, ARM_FEATURE_V8_FP16); - set_feature(&cpu->env, ARM_FEATURE_V8_FCMA); set_feature(&cpu->env, ARM_FEATURE_SVE); /* For usermode -cpu max we can use a larger and more efficient DCZ * blocksize since we don't have to follow what the hardware does. diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) } if (rt2 == 31 && ((rt | rs) & 1) == 0 - && arm_dc_feature(s, ARM_FEATURE_V8_ATOMICS)) { + && dc_isar_feature(aa64_atomics, s)) { /* CASP / CASPL */ gen_compare_and_swap_pair(s, rs, rt, rn, size | 2); return; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) } if (rt2 == 31 && ((rt | rs) & 1) == 0 - && arm_dc_feature(s, ARM_FEATURE_V8_ATOMICS)) { + && dc_isar_feature(aa64_atomics, s)) { /* CASPA / CASPAL */ gen_compare_and_swap_pair(s, rs, rt, rn, size | 2); return; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) case 0xb: /* CASL */ case 0xe: /* CASA */ case 0xf: /* CASAL */ - if (rt2 == 31 && arm_dc_feature(s, ARM_FEATURE_V8_ATOMICS)) { + if (rt2 == 31 && dc_isar_feature(aa64_atomics, s)) { gen_compare_and_swap(s, rs, rt, rn, size); return; } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, int rs = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int o3_opc = extract32(insn, 12, 4); - int feature = ARM_FEATURE_V8_ATOMICS; TCGv_i64 tcg_rn, tcg_rs; AtomicThreeOpFn *fn; - if (is_vector) { + if (is_vector || !dc_isar_feature(aa64_atomics, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, unallocated_encoding(s); return; } - if (!arm_dc_feature(s, feature)) { - unallocated_encoding(s); - return; - } if (rn == 31) { gen_check_sp_alignment(s); @@ -XXX,XX +XXX,XX @@ static void handle_crc32(DisasContext *s, TCGv_i64 tcg_acc, tcg_val; TCGv_i32 tcg_bytes; - if (!arm_dc_feature(s, ARM_FEATURE_CRC) + if (!dc_isar_feature(aa64_crc32, s) || (sf == 1 && sz != 3) || (sf == 0 && sz == 3)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same_extra(DisasContext *s, bool u = extract32(insn, 29, 1); TCGv_i32 ele1, ele2, ele3; TCGv_i64 res; - int feature; + bool feature; switch (u * 16 + opcode) { case 0x10: /* SQRDMLAH (vector) */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same_extra(DisasContext *s, unallocated_encoding(s); return; } - feature = ARM_FEATURE_V8_RDM; + feature = dc_isar_feature(aa64_rdm, s); break; default: unallocated_encoding(s); return; } - if (!arm_dc_feature(s, feature)) { + if (!feature) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn) return; } if (size == 3) { - if (!arm_dc_feature(s, ARM_FEATURE_V8_PMULL)) { + if (!dc_isar_feature(aa64_pmull, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) int size = extract32(insn, 22, 2); bool u = extract32(insn, 29, 1); bool is_q = extract32(insn, 30, 1); - int feature, rot; + bool feature; + int rot; switch (u * 16 + opcode) { case 0x10: /* SQRDMLAH (vector) */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - feature = ARM_FEATURE_V8_RDM; + feature = dc_isar_feature(aa64_rdm, s); break; case 0x02: /* SDOT (vector) */ case 0x12: /* UDOT (vector) */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - feature = ARM_FEATURE_V8_DOTPROD; + feature = dc_isar_feature(aa64_dp, s); break; case 0x18: /* FCMLA, #0 */ case 0x19: /* FCMLA, #90 */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - feature = ARM_FEATURE_V8_FCMA; + feature = dc_isar_feature(aa64_fcma, s); break; default: unallocated_encoding(s); return; } - if (!arm_dc_feature(s, feature)) { + if (!feature) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) break; case 0x1d: /* SQRDMLAH */ case 0x1f: /* SQRDMLSH */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_RDM)) { + if (!dc_isar_feature(aa64_rdm, s)) { unallocated_encoding(s); return; } break; case 0x0e: /* SDOT */ case 0x1e: /* UDOT */ - if (size != MO_32 || !arm_dc_feature(s, ARM_FEATURE_V8_DOTPROD)) { + if (size != MO_32 || !dc_isar_feature(aa64_dp, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x13: /* FCMLA #90 */ case 0x15: /* FCMLA #180 */ case 0x17: /* FCMLA #270 */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_FCMA)) { + if (!dc_isar_feature(aa64_fcma, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_aes(DisasContext *s, uint32_t insn) TCGv_i32 tcg_decrypt; CryptoThreeOpIntFn *genfn; - if (!arm_dc_feature(s, ARM_FEATURE_V8_AES) - || size != 0) { + if (!dc_isar_feature(aa64_aes, s) || size != 0) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha(DisasContext *s, uint32_t insn) int rd = extract32(insn, 0, 5); CryptoThreeOpFn *genfn; TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; - int feature = ARM_FEATURE_V8_SHA256; + bool feature; if (size != 0) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha(DisasContext *s, uint32_t insn) case 2: /* SHA1M */ case 3: /* SHA1SU0 */ genfn = NULL; - feature = ARM_FEATURE_V8_SHA1; + feature = dc_isar_feature(aa64_sha1, s); break; case 4: /* SHA256H */ genfn = gen_helper_crypto_sha256h; + feature = dc_isar_feature(aa64_sha256, s); break; case 5: /* SHA256H2 */ genfn = gen_helper_crypto_sha256h2; + feature = dc_isar_feature(aa64_sha256, s); break; case 6: /* SHA256SU1 */ genfn = gen_helper_crypto_sha256su1; + feature = dc_isar_feature(aa64_sha256, s); break; default: unallocated_encoding(s); return; } - if (!arm_dc_feature(s, feature)) { + if (!feature) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn) int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); CryptoTwoOpFn *genfn; - int feature; + bool feature; TCGv_ptr tcg_rd_ptr, tcg_rn_ptr; if (size != 0) { @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn) switch (opcode) { case 0: /* SHA1H */ - feature = ARM_FEATURE_V8_SHA1; + feature = dc_isar_feature(aa64_sha1, s); genfn = gen_helper_crypto_sha1h; break; case 1: /* SHA1SU1 */ - feature = ARM_FEATURE_V8_SHA1; + feature = dc_isar_feature(aa64_sha1, s); genfn = gen_helper_crypto_sha1su1; break; case 2: /* SHA256SU0 */ - feature = ARM_FEATURE_V8_SHA256; + feature = dc_isar_feature(aa64_sha256, s); genfn = gen_helper_crypto_sha256su0; break; default: @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha(DisasContext *s, uint32_t insn) return; } - if (!arm_dc_feature(s, feature)) { + if (!feature) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) int rm = extract32(insn, 16, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - int feature; + bool feature; CryptoThreeOpFn *genfn; if (o == 0) { switch (opcode) { case 0: /* SHA512H */ - feature = ARM_FEATURE_V8_SHA512; + feature = dc_isar_feature(aa64_sha512, s); genfn = gen_helper_crypto_sha512h; break; case 1: /* SHA512H2 */ - feature = ARM_FEATURE_V8_SHA512; + feature = dc_isar_feature(aa64_sha512, s); genfn = gen_helper_crypto_sha512h2; break; case 2: /* SHA512SU1 */ - feature = ARM_FEATURE_V8_SHA512; + feature = dc_isar_feature(aa64_sha512, s); genfn = gen_helper_crypto_sha512su1; break; case 3: /* RAX1 */ - feature = ARM_FEATURE_V8_SHA3; + feature = dc_isar_feature(aa64_sha3, s); genfn = NULL; break; } } else { switch (opcode) { case 0: /* SM3PARTW1 */ - feature = ARM_FEATURE_V8_SM3; + feature = dc_isar_feature(aa64_sm3, s); genfn = gen_helper_crypto_sm3partw1; break; case 1: /* SM3PARTW2 */ - feature = ARM_FEATURE_V8_SM3; + feature = dc_isar_feature(aa64_sm3, s); genfn = gen_helper_crypto_sm3partw2; break; case 2: /* SM4EKEY */ - feature = ARM_FEATURE_V8_SM4; + feature = dc_isar_feature(aa64_sm4, s); genfn = gen_helper_crypto_sm4ekey; break; default: @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_sha512(DisasContext *s, uint32_t insn) } } - if (!arm_dc_feature(s, feature)) { + if (!feature) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); TCGv_ptr tcg_rd_ptr, tcg_rn_ptr; - int feature; + bool feature; CryptoTwoOpFn *genfn; switch (opcode) { case 0: /* SHA512SU0 */ - feature = ARM_FEATURE_V8_SHA512; + feature = dc_isar_feature(aa64_sha512, s); genfn = gen_helper_crypto_sha512su0; break; case 1: /* SM4E */ - feature = ARM_FEATURE_V8_SM4; + feature = dc_isar_feature(aa64_sm4, s); genfn = gen_helper_crypto_sm4e; break; default: @@ -XXX,XX +XXX,XX @@ static void disas_crypto_two_reg_sha512(DisasContext *s, uint32_t insn) return; } - if (!arm_dc_feature(s, feature)) { + if (!feature) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_four_reg(DisasContext *s, uint32_t insn) int ra = extract32(insn, 10, 5); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - int feature; + bool feature; switch (op0) { case 0: /* EOR3 */ case 1: /* BCAX */ - feature = ARM_FEATURE_V8_SHA3; + feature = dc_isar_feature(aa64_sha3, s); break; case 2: /* SM3SS1 */ - feature = ARM_FEATURE_V8_SM3; + feature = dc_isar_feature(aa64_sm3, s); break; default: unallocated_encoding(s); return; } - if (!arm_dc_feature(s, feature)) { + if (!feature) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_xar(DisasContext *s, uint32_t insn) TCGv_i64 tcg_op1, tcg_op2, tcg_res[2]; int pass; - if (!arm_dc_feature(s, ARM_FEATURE_V8_SHA3)) { + if (!dc_isar_feature(aa64_sha3, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_crypto_three_reg_imm2(DisasContext *s, uint32_t insn) TCGv_ptr tcg_rd_ptr, tcg_rn_ptr, tcg_rm_ptr; TCGv_i32 tcg_imm2, tcg_opcode; - if (!arm_dc_feature(s, ARM_FEATURE_V8_SM3)) { + if (!dc_isar_feature(aa64_sm3, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, ARMCPU *arm_cpu = arm_env_get_cpu(env); int bound; + dc->isar = &arm_cpu->isar; dc->pc = dc->base.pc_first; dc->condjmp = 0; 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 const uint8_t neon_2rm_sizes[] = { static int do_v81_helper(DisasContext *s, gen_helper_gvec_3_ptr *fn, int q, int rd, int rn, int rm) { - if (arm_dc_feature(s, ARM_FEATURE_V8_RDM)) { + if (dc_isar_feature(aa32_rdm, s)) { int opr_sz = (1 + q) * 8; tcg_gen_gvec_3_ptr(vfp_reg_offset(1, rd), vfp_reg_offset(1, rn), @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } if (!u) { /* SHA-1 */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_SHA1)) { + if (!dc_isar_feature(aa32_sha1, s)) { return 1; } ptr1 = vfp_reg_ptr(true, rd); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) gen_helper_crypto_sha1_3reg(ptr1, ptr2, ptr3, tmp4); tcg_temp_free_i32(tmp4); } else { /* SHA-256 */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_SHA256) || size == 3) { + if (!dc_isar_feature(aa32_sha2, s) || size == 3) { return 1; } ptr1 = vfp_reg_ptr(true, rd); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) if (op == 14 && size == 2) { TCGv_i64 tcg_rn, tcg_rm, tcg_rd; - if (!arm_dc_feature(s, ARM_FEATURE_V8_PMULL)) { + if (!dc_isar_feature(aa32_pmull, s)) { return 1; } tcg_rn = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) { NeonGenThreeOpEnvFn *fn; - if (!arm_dc_feature(s, ARM_FEATURE_V8_RDM)) { + if (!dc_isar_feature(aa32_rdm, s)) { return 1; } if (u && ((rd | rn) & 1)) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) break; } case NEON_2RM_AESE: case NEON_2RM_AESMC: - if (!arm_dc_feature(s, ARM_FEATURE_V8_AES) - || ((rm | rd) & 1)) { + if (!dc_isar_feature(aa32_aes, s) || ((rm | rd) & 1)) { return 1; } ptr1 = vfp_reg_ptr(true, rd); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_temp_free_i32(tmp3); break; case NEON_2RM_SHA1H: - if (!arm_dc_feature(s, ARM_FEATURE_V8_SHA1) - || ((rm | rd) & 1)) { + if (!dc_isar_feature(aa32_sha1, s) || ((rm | rd) & 1)) { return 1; } ptr1 = vfp_reg_ptr(true, rd); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } /* bit 6 (q): set -> SHA256SU0, cleared -> SHA1SU1 */ if (q) { - if (!arm_dc_feature(s, ARM_FEATURE_V8_SHA256)) { + if (!dc_isar_feature(aa32_sha2, s)) { return 1; } - } else if (!arm_dc_feature(s, ARM_FEATURE_V8_SHA1)) { + } else if (!dc_isar_feature(aa32_sha1, s)) { return 1; } ptr1 = vfp_reg_ptr(true, rd); @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) /* VCMLA -- 1111 110R R.1S .... .... 1000 ...0 .... */ int size = extract32(insn, 20, 1); data = extract32(insn, 23, 2); /* rot */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_FCMA) + if (!dc_isar_feature(aa32_vcma, s) || (!size && !arm_dc_feature(s, ARM_FEATURE_V8_FP16))) { return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) /* VCADD -- 1111 110R 1.0S .... .... 1000 ...0 .... */ int size = extract32(insn, 20, 1); data = extract32(insn, 24, 1); /* rot */ - if (!arm_dc_feature(s, ARM_FEATURE_V8_FCMA) + if (!dc_isar_feature(aa32_vcma, s) || (!size && !arm_dc_feature(s, ARM_FEATURE_V8_FP16))) { return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) } else if ((insn & 0xfeb00f00) == 0xfc200d00) { /* V[US]DOT -- 1111 1100 0.10 .... .... 1101 .Q.U .... */ bool u = extract32(insn, 4, 1); - if (!arm_dc_feature(s, ARM_FEATURE_V8_DOTPROD)) { + if (!dc_isar_feature(aa32_dp, s)) { return 1; } fn_gvec = u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b; @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) int size = extract32(insn, 23, 1); int index; - if (!arm_dc_feature(s, ARM_FEATURE_V8_FCMA)) { + if (!dc_isar_feature(aa32_vcma, s)) { return 1; } if (size == 0) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) } else if ((insn & 0xffb00f00) == 0xfe200d00) { /* V[US]DOT -- 1111 1110 0.10 .... .... 1101 .Q.U .... */ int u = extract32(insn, 4, 1); - if (!arm_dc_feature(s, ARM_FEATURE_V8_DOTPROD)) { + if (!dc_isar_feature(aa32_dp, s)) { return 1; } fn_gvec = u ? gen_helper_gvec_udot_idx_b : gen_helper_gvec_sdot_idx_b; @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) * op1 == 3 is UNPREDICTABLE but handle as UNDEFINED. * Bits 8, 10 and 11 should be zero. */ - if (!arm_dc_feature(s, ARM_FEATURE_CRC) || op1 == 0x3 || - (c & 0xd) != 0) { + if (!dc_isar_feature(aa32_crc32, s) || op1 == 0x3 || (c & 0xd) != 0) { goto illegal_op; } @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) case 0x28: case 0x29: case 0x2a: - if (!arm_dc_feature(s, ARM_FEATURE_CRC)) { + if (!dc_isar_feature(aa32_crc32, s)) { goto illegal_op; } break; @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) CPUARMState *env = cs->env_ptr; ARMCPU *cpu = arm_env_get_cpu(env); + dc->isar = &cpu->isar; dc->pc = dc->base.pc_first; dc->condjmp = 0; -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Both arm and thumb2 division are controlled by the same ISAR field, which takes care of the arm implies thumb case. Having M imply thumb2 division was wrong for cortex-m0, which is v6m and does not have thumb2 at all, much less thumb2 division. Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 12 ++++++++++-- linux-user/elfload.c | 4 ++-- target/arm/cpu.c | 10 +--------- target/arm/translate.c | 4 ++-- 4 files changed, 15 insertions(+), 15 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_VFP3, ARM_FEATURE_VFP_FP16, ARM_FEATURE_NEON, - ARM_FEATURE_THUMB_DIV, /* divide supported in Thumb encoding */ ARM_FEATURE_M, /* Microcontroller profile. */ ARM_FEATURE_OMAPCP, /* OMAP specific CP15 ops handling. */ ARM_FEATURE_THUMB2EE, @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_V5, ARM_FEATURE_STRONGARM, ARM_FEATURE_VAPA, /* cp15 VA to PA lookups */ - ARM_FEATURE_ARM_DIV, /* divide supported in ARM encoding */ ARM_FEATURE_VFP4, /* VFPv4 (implies that NEON is v2) */ ARM_FEATURE_GENERIC_TIMER, ARM_FEATURE_MVFR, /* Media and VFP Feature Registers 0 and 1 */ @@ -XXX,XX +XXX,XX @@ extern const uint64_t pred_esz_masks[4]; /* * 32-bit feature tests via id registers. */ +static inline bool isar_feature_thumb_div(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) != 0; +} + +static inline bool isar_feature_arm_div(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) > 1; +} + static inline bool isar_feature_aa32_aes(const ARMISARegisters *id) { return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) != 0; diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) GET_FEATURE(ARM_FEATURE_VFP3, ARM_HWCAP_ARM_VFPv3); GET_FEATURE(ARM_FEATURE_V6K, ARM_HWCAP_ARM_TLS); GET_FEATURE(ARM_FEATURE_VFP4, ARM_HWCAP_ARM_VFPv4); - GET_FEATURE(ARM_FEATURE_ARM_DIV, ARM_HWCAP_ARM_IDIVA); - GET_FEATURE(ARM_FEATURE_THUMB_DIV, ARM_HWCAP_ARM_IDIVT); + GET_FEATURE_ID(arm_div, ARM_HWCAP_ARM_IDIVA); + GET_FEATURE_ID(thumb_div, ARM_HWCAP_ARM_IDIVT); /* All QEMU's VFPv3 CPUs have 32 registers, see VFP_DREG in translate.c. * Note that the ARM_HWCAP_ARM_VFPv3D16 bit is always the inverse of * ARM_HWCAP_ARM_VFPD32 (and so always clear for QEMU); it is unrelated diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) * Presence of EL2 itself is ARM_FEATURE_EL2, and of the * Security Extensions is ARM_FEATURE_EL3. */ - set_feature(env, ARM_FEATURE_ARM_DIV); + assert(cpu_isar_feature(arm_div, cpu)); set_feature(env, ARM_FEATURE_LPAE); set_feature(env, ARM_FEATURE_V7); } @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) if (arm_feature(env, ARM_FEATURE_V5)) { set_feature(env, ARM_FEATURE_V4T); } - if (arm_feature(env, ARM_FEATURE_M)) { - set_feature(env, ARM_FEATURE_THUMB_DIV); - } - if (arm_feature(env, ARM_FEATURE_ARM_DIV)) { - set_feature(env, ARM_FEATURE_THUMB_DIV); - } if (arm_feature(env, ARM_FEATURE_VFP4)) { set_feature(env, ARM_FEATURE_VFP3); set_feature(env, ARM_FEATURE_VFP_FP16); @@ -XXX,XX +XXX,XX @@ static void cortex_r5_initfn(Object *obj) ARMCPU *cpu = ARM_CPU(obj); set_feature(&cpu->env, ARM_FEATURE_V7); - set_feature(&cpu->env, ARM_FEATURE_THUMB_DIV); - set_feature(&cpu->env, ARM_FEATURE_ARM_DIV); set_feature(&cpu->env, ARM_FEATURE_V7MP); set_feature(&cpu->env, ARM_FEATURE_PMSA); cpu->midr = 0x411fc153; /* r1p3 */ diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) case 1: case 3: /* SDIV, UDIV */ - if (!arm_dc_feature(s, ARM_FEATURE_ARM_DIV)) { + if (!dc_isar_feature(arm_div, s)) { goto illegal_op; } if (((insn >> 5) & 7) || (rd != 15)) { @@ -XXX,XX +XXX,XX @@ static void disas_thumb2_insn(DisasContext *s, uint32_t insn) tmp2 = load_reg(s, rm); if ((op & 0x50) == 0x10) { /* sdiv, udiv */ - if (!arm_dc_feature(s, ARM_FEATURE_THUMB_DIV)) { + if (!dc_isar_feature(thumb_div, s)) { goto illegal_op; } if (op & 0x20) -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Having V6 alone imply jazelle was wrong for cortex-m0. Change to an assertion for V6 & !M. This was harmless, because the only place we tested ARM_FEATURE_JAZELLE was for 'bxj' in disas_arm(), which is unreachable for M-profile cores. Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-6-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 6 +++++- target/arm/cpu.c | 17 ++++++++++++++--- target/arm/translate.c | 2 +- 3 files changed, 20 insertions(+), 5 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_PMU, /* has PMU support */ ARM_FEATURE_VBAR, /* has cp15 VBAR */ ARM_FEATURE_M_SECURITY, /* M profile Security Extension */ - ARM_FEATURE_JAZELLE, /* has (trivial) Jazelle implementation */ ARM_FEATURE_SVE, /* has Scalable Vector Extension */ ARM_FEATURE_V8_FP16, /* implements v8.2 half-precision float */ ARM_FEATURE_M_MAIN, /* M profile Main Extension */ @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_arm_div(const ARMISARegisters *id) return FIELD_EX32(id->id_isar0, ID_ISAR0, DIVIDE) > 1; } +static inline bool isar_feature_jazelle(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar1, ID_ISAR1, JAZELLE) != 0; +} + static inline bool isar_feature_aa32_aes(const ARMISARegisters *id) { return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) != 0; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) } if (arm_feature(env, ARM_FEATURE_V6)) { set_feature(env, ARM_FEATURE_V5); - set_feature(env, ARM_FEATURE_JAZELLE); if (!arm_feature(env, ARM_FEATURE_M)) { + assert(cpu_isar_feature(jazelle, cpu)); set_feature(env, ARM_FEATURE_AUXCR); } } @@ -XXX,XX +XXX,XX @@ static void arm926_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_VFP); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CACHE_TEST_CLEAN); - set_feature(&cpu->env, ARM_FEATURE_JAZELLE); cpu->midr = 0x41069265; cpu->reset_fpsid = 0x41011090; cpu->ctr = 0x1dd20d2; cpu->reset_sctlr = 0x00090078; + + /* + * ARMv5 does not have the ID_ISAR registers, but we can still + * set the field to indicate Jazelle support within QEMU. + */ + cpu->isar.id_isar1 = FIELD_DP32(cpu->isar.id_isar1, ID_ISAR1, JAZELLE, 1); } static void arm946_initfn(Object *obj) @@ -XXX,XX +XXX,XX @@ static void arm1026_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_AUXCR); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CACHE_TEST_CLEAN); - set_feature(&cpu->env, ARM_FEATURE_JAZELLE); cpu->midr = 0x4106a262; cpu->reset_fpsid = 0x410110a0; cpu->ctr = 0x1dd20d2; cpu->reset_sctlr = 0x00090078; cpu->reset_auxcr = 1; + + /* + * ARMv5 does not have the ID_ISAR registers, but we can still + * set the field to indicate Jazelle support within QEMU. + */ + cpu->isar.id_isar1 = FIELD_DP32(cpu->isar.id_isar1, ID_ISAR1, JAZELLE, 1); + { /* The 1026 had an IFAR at c6,c0,0,1 rather than the ARMv6 c6,c0,0,2 */ ARMCPRegInfo ifar = { 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 @@ #define ENABLE_ARCH_5 arm_dc_feature(s, ARM_FEATURE_V5) /* currently all emulated v5 cores are also v5TE, so don't bother */ #define ENABLE_ARCH_5TE arm_dc_feature(s, ARM_FEATURE_V5) -#define ENABLE_ARCH_5J arm_dc_feature(s, ARM_FEATURE_JAZELLE) +#define ENABLE_ARCH_5J dc_isar_feature(jazelle, s) #define ENABLE_ARCH_6 arm_dc_feature(s, ARM_FEATURE_V6) #define ENABLE_ARCH_6K arm_dc_feature(s, ARM_FEATURE_V6K) #define ENABLE_ARCH_6T2 arm_dc_feature(s, ARM_FEATURE_THUMB2) -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-7-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 6 +++++- linux-user/elfload.c | 2 +- target/arm/cpu.c | 4 ---- target/arm/helper.c | 2 +- target/arm/machine.c | 3 +-- 5 files changed, 8 insertions(+), 9 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_NEON, ARM_FEATURE_M, /* Microcontroller profile. */ ARM_FEATURE_OMAPCP, /* OMAP specific CP15 ops handling. */ - ARM_FEATURE_THUMB2EE, ARM_FEATURE_V7MP, /* v7 Multiprocessing Extensions */ ARM_FEATURE_V7VE, /* v7 Virtualization Extensions (non-EL2 parts) */ ARM_FEATURE_V4T, @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_jazelle(const ARMISARegisters *id) return FIELD_EX32(id->id_isar1, ID_ISAR1, JAZELLE) != 0; } +static inline bool isar_feature_t32ee(const ARMISARegisters *id) +{ + return FIELD_EX32(id->id_isar3, ID_ISAR3, T32EE) != 0; +} + static inline bool isar_feature_aa32_aes(const ARMISARegisters *id) { return FIELD_EX32(id->id_isar5, ID_ISAR5, AES) != 0; diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) GET_FEATURE(ARM_FEATURE_V5, ARM_HWCAP_ARM_EDSP); GET_FEATURE(ARM_FEATURE_VFP, ARM_HWCAP_ARM_VFP); GET_FEATURE(ARM_FEATURE_IWMMXT, ARM_HWCAP_ARM_IWMMXT); - GET_FEATURE(ARM_FEATURE_THUMB2EE, ARM_HWCAP_ARM_THUMBEE); + GET_FEATURE_ID(t32ee, ARM_HWCAP_ARM_THUMBEE); GET_FEATURE(ARM_FEATURE_NEON, ARM_HWCAP_ARM_NEON); GET_FEATURE(ARM_FEATURE_VFP3, ARM_HWCAP_ARM_VFPv3); GET_FEATURE(ARM_FEATURE_V6K, ARM_HWCAP_ARM_TLS); 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) set_feature(&cpu->env, ARM_FEATURE_V7); set_feature(&cpu->env, ARM_FEATURE_VFP3); set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_EL3); cpu->midr = 0x410fc080; @@ -XXX,XX +XXX,XX @@ static void cortex_a9_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_VFP3); set_feature(&cpu->env, ARM_FEATURE_VFP_FP16); 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 * A9UP and single-core A9MP (which are both different @@ -XXX,XX +XXX,XX @@ static void cortex_a7_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V7VE); set_feature(&cpu->env, ARM_FEATURE_VFP4); set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); @@ -XXX,XX +XXX,XX @@ static void cortex_a15_initfn(Object *obj) set_feature(&cpu->env, ARM_FEATURE_V7VE); set_feature(&cpu->env, ARM_FEATURE_VFP4); set_feature(&cpu->env, ARM_FEATURE_NEON); - set_feature(&cpu->env, ARM_FEATURE_THUMB2EE); set_feature(&cpu->env, ARM_FEATURE_GENERIC_TIMER); set_feature(&cpu->env, ARM_FEATURE_DUMMY_C15_REGS); set_feature(&cpu->env, ARM_FEATURE_CBAR_RO); diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) define_arm_cp_regs(cpu, vmsa_pmsa_cp_reginfo); define_arm_cp_regs(cpu, vmsa_cp_reginfo); } - if (arm_feature(env, ARM_FEATURE_THUMB2EE)) { + if (cpu_isar_feature(t32ee, cpu)) { define_arm_cp_regs(cpu, t2ee_cp_reginfo); } if (arm_feature(env, ARM_FEATURE_GENERIC_TIMER)) { diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_m = { static bool thumb2ee_needed(void *opaque) { ARMCPU *cpu = opaque; - CPUARMState *env = &cpu->env; - return arm_feature(env, ARM_FEATURE_THUMB2EE); + return cpu_isar_feature(t32ee, cpu); } static const VMStateDescription vmstate_thumb2ee = { -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-8-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 16 +++++++++++++++- linux-user/aarch64/signal.c | 4 ++-- linux-user/elfload.c | 2 +- linux-user/syscall.c | 10 ++++++---- target/arm/cpu64.c | 5 ++++- target/arm/helper.c | 9 ++++++--- target/arm/machine.c | 3 +-- target/arm/translate-a64.c | 4 ++-- 8 files changed, 37 insertions(+), 16 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(ID_AA64ISAR1, FRINTTS, 32, 4) FIELD(ID_AA64ISAR1, SB, 36, 4) FIELD(ID_AA64ISAR1, SPECRES, 40, 4) +FIELD(ID_AA64PFR0, EL0, 0, 4) +FIELD(ID_AA64PFR0, EL1, 4, 4) +FIELD(ID_AA64PFR0, EL2, 8, 4) +FIELD(ID_AA64PFR0, EL3, 12, 4) +FIELD(ID_AA64PFR0, FP, 16, 4) +FIELD(ID_AA64PFR0, ADVSIMD, 20, 4) +FIELD(ID_AA64PFR0, GIC, 24, 4) +FIELD(ID_AA64PFR0, RAS, 28, 4) +FIELD(ID_AA64PFR0, SVE, 32, 4) + QEMU_BUILD_BUG_ON(ARRAY_SIZE(((ARMCPU *)0)->ccsidr) <= R_V7M_CSSELR_INDEX_MASK); /* If adding a feature bit which corresponds to a Linux ELF @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_PMU, /* has PMU support */ ARM_FEATURE_VBAR, /* has cp15 VBAR */ ARM_FEATURE_M_SECURITY, /* M profile Security Extension */ - ARM_FEATURE_SVE, /* has Scalable Vector Extension */ ARM_FEATURE_V8_FP16, /* implements v8.2 half-precision float */ ARM_FEATURE_M_MAIN, /* M profile Main Extension */ }; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; } +static inline bool isar_feature_aa64_sve(const ARMISARegisters *id) +{ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, SVE) != 0; +} + /* * Forward to the above feature tests given an ARMCPU pointer. */ diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, break; case TARGET_SVE_MAGIC: - if (arm_feature(env, ARM_FEATURE_SVE)) { + if (cpu_isar_feature(aa64_sve, arm_env_get_cpu(env))) { vq = (env->vfp.zcr_el[1] & 0xf) + 1; sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(vq), 16); if (!sve && size == sve_size) { @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, &layout); /* SVE state needs saving only if it exists. */ - if (arm_feature(env, ARM_FEATURE_SVE)) { + if (cpu_isar_feature(aa64_sve, arm_env_get_cpu(env))) { vq = (env->vfp.zcr_el[1] & 0xf) + 1; sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(vq), 16); sve_ofs = alloc_sigframe_space(sve_size, &layout); diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) GET_FEATURE_ID(aa64_rdm, ARM_HWCAP_A64_ASIMDRDM); GET_FEATURE_ID(aa64_dp, ARM_HWCAP_A64_ASIMDDP); GET_FEATURE_ID(aa64_fcma, ARM_HWCAP_A64_FCMA); - GET_FEATURE(ARM_FEATURE_SVE, ARM_HWCAP_A64_SVE); + GET_FEATURE_ID(aa64_sve, ARM_HWCAP_A64_SVE); #undef GET_FEATURE #undef GET_FEATURE_ID diff --git a/linux-user/syscall.c b/linux-user/syscall.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -XXX,XX +XXX,XX @@ static abi_long do_syscall1(void *cpu_env, int num, abi_long arg1, * even though the current architectural maximum is VQ=16. */ ret = -TARGET_EINVAL; - if (arm_feature(cpu_env, ARM_FEATURE_SVE) + if (cpu_isar_feature(aa64_sve, arm_env_get_cpu(cpu_env)) && arg2 >= 0 && arg2 <= 512 * 16 && !(arg2 & 15)) { CPUARMState *env = cpu_env; ARMCPU *cpu = arm_env_get_cpu(env); @@ -XXX,XX +XXX,XX @@ static abi_long do_syscall1(void *cpu_env, int num, abi_long arg1, return ret; case TARGET_PR_SVE_GET_VL: ret = -TARGET_EINVAL; - if (arm_feature(cpu_env, ARM_FEATURE_SVE)) { - CPUARMState *env = cpu_env; - ret = ((env->vfp.zcr_el[1] & 0xf) + 1) * 16; + { + ARMCPU *cpu = arm_env_get_cpu(cpu_env); + if (cpu_isar_feature(aa64_sve, cpu)) { + ret = ((cpu->env.vfp.zcr_el[1] & 0xf) + 1) * 16; + } } return ret; #endif /* AARCH64 */ 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 = FIELD_DP64(t, ID_AA64ISAR1, FCMA, 1); cpu->isar.id_aa64isar1 = t; + t = cpu->isar.id_aa64pfr0; + t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1); + cpu->isar.id_aa64pfr0 = t; + /* Replicate the same data to the 32-bit id registers. */ u = cpu->isar.id_isar5; u = FIELD_DP32(u, ID_ISAR5, AES, 2); /* AES + PMULL */ @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) * present in either. */ set_feature(&cpu->env, ARM_FEATURE_V8_FP16); - set_feature(&cpu->env, ARM_FEATURE_SVE); /* For usermode -cpu max we can use a larger and more efficient DCZ * blocksize since we don't have to follow what the hardware does. */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void register_cp_regs_for_features(ARMCPU *cpu) define_one_arm_cp_reg(cpu, &sctlr); } - if (arm_feature(env, ARM_FEATURE_SVE)) { + if (cpu_isar_feature(aa64_sve, cpu)) { define_one_arm_cp_reg(cpu, &zcr_el1_reginfo); if (arm_feature(env, ARM_FEATURE_EL2)) { define_one_arm_cp_reg(cpu, &zcr_el2_reginfo); @@ -XXX,XX +XXX,XX @@ void cpu_get_tb_cpu_state(CPUARMState *env, target_ulong *pc, uint32_t flags; if (is_a64(env)) { + ARMCPU *cpu = arm_env_get_cpu(env); + *pc = env->pc; flags = ARM_TBFLAG_AARCH64_STATE_MASK; /* Get control bits for tagged addresses */ flags |= (arm_regime_tbi0(env, mmu_idx) << ARM_TBFLAG_TBI0_SHIFT); flags |= (arm_regime_tbi1(env, mmu_idx) << ARM_TBFLAG_TBI1_SHIFT); - if (arm_feature(env, ARM_FEATURE_SVE)) { + if (cpu_isar_feature(aa64_sve, cpu)) { int sve_el = sve_exception_el(env, current_el); uint32_t zcr_len; @@ -XXX,XX +XXX,XX @@ void aarch64_sve_narrow_vq(CPUARMState *env, unsigned vq) void aarch64_sve_change_el(CPUARMState *env, int old_el, int new_el, bool el0_a64) { + ARMCPU *cpu = arm_env_get_cpu(env); int old_len, new_len; bool old_a64, new_a64; /* Nothing to do if no SVE. */ - if (!arm_feature(env, ARM_FEATURE_SVE)) { + if (!cpu_isar_feature(aa64_sve, cpu)) { return; } diff --git a/target/arm/machine.c b/target/arm/machine.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/machine.c +++ b/target/arm/machine.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_iwmmxt = { static bool sve_needed(void *opaque) { ARMCPU *cpu = opaque; - CPUARMState *env = &cpu->env; - return arm_feature(env, ARM_FEATURE_SVE); + return cpu_isar_feature(aa64_sve, cpu); } /* The first two words of each Zreg is stored in VFP state. */ diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ void aarch64_cpu_dump_state(CPUState *cs, FILE *f, cpu_fprintf(f, " FPCR=%08x FPSR=%08x\n", vfp_get_fpcr(env), vfp_get_fpsr(env)); - if (arm_feature(env, ARM_FEATURE_SVE) && sve_exception_el(env, el) == 0) { + if (cpu_isar_feature(aa64_sve, cpu) && sve_exception_el(env, el) == 0) { int j, zcr_len = sve_zcr_len_for_el(env, el); for (i = 0; i <= FFR_PRED_NUM; i++) { @@ -XXX,XX +XXX,XX @@ static void disas_a64_insn(CPUARMState *env, DisasContext *s) unallocated_encoding(s); break; case 0x2: - if (!arm_dc_feature(s, ARM_FEATURE_SVE) || !disas_sve(s, insn)) { + if (!dc_isar_feature(aa64_sve, s) || !disas_sve(s, insn)) { unallocated_encoding(s); } break; -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181016223115.24100-9-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 17 +++++++++++++++- linux-user/elfload.c | 6 +----- target/arm/cpu64.c | 16 ++++++++------- target/arm/helper.c | 2 +- target/arm/translate-a64.c | 40 +++++++++++++++++++------------------- target/arm/translate.c | 6 +++--- 6 files changed, 50 insertions(+), 37 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ enum arm_features { ARM_FEATURE_PMU, /* has PMU support */ ARM_FEATURE_VBAR, /* has cp15 VBAR */ ARM_FEATURE_M_SECURITY, /* M profile Security Extension */ - ARM_FEATURE_V8_FP16, /* implements v8.2 half-precision float */ ARM_FEATURE_M_MAIN, /* M profile Main Extension */ }; @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa32_dp(const ARMISARegisters *id) return FIELD_EX32(id->id_isar6, ID_ISAR6, DP) != 0; } +static inline bool isar_feature_aa32_fp16_arith(const ARMISARegisters *id) +{ + /* + * This is a placeholder for use by VCMA until the rest of + * the ARMv8.2-FP16 extension is implemented for aa32 mode. + * At which point we can properly set and check MVFR1.FPHP. + */ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) == 1; +} + /* * 64-bit feature tests via id registers. */ @@ -XXX,XX +XXX,XX @@ static inline bool isar_feature_aa64_fcma(const ARMISARegisters *id) return FIELD_EX64(id->id_aa64isar1, ID_AA64ISAR1, FCMA) != 0; } +static inline bool isar_feature_aa64_fp16(const ARMISARegisters *id) +{ + /* We always set the AdvSIMD and FP fields identically wrt FP16. */ + return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, FP) == 1; +} + static inline bool isar_feature_aa64_sve(const ARMISARegisters *id) { return FIELD_EX64(id->id_aa64pfr0, ID_AA64PFR0, SVE) != 0; diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) hwcaps |= ARM_HWCAP_A64_ASIMD; /* probe for the extra features */ -#define GET_FEATURE(feat, hwcap) \ - do { if (arm_feature(&cpu->env, feat)) { hwcaps |= hwcap; } } while (0) #define GET_FEATURE_ID(feat, hwcap) \ do { if (cpu_isar_feature(feat, cpu)) { hwcaps |= hwcap; } } while (0) @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap(void) GET_FEATURE_ID(aa64_sha3, ARM_HWCAP_A64_SHA3); GET_FEATURE_ID(aa64_sm3, ARM_HWCAP_A64_SM3); GET_FEATURE_ID(aa64_sm4, ARM_HWCAP_A64_SM4); - GET_FEATURE(ARM_FEATURE_V8_FP16, - ARM_HWCAP_A64_FPHP | ARM_HWCAP_A64_ASIMDHP); + GET_FEATURE_ID(aa64_fp16, ARM_HWCAP_A64_FPHP | ARM_HWCAP_A64_ASIMDHP); GET_FEATURE_ID(aa64_atomics, ARM_HWCAP_A64_ATOMICS); GET_FEATURE_ID(aa64_rdm, ARM_HWCAP_A64_ASIMDRDM); GET_FEATURE_ID(aa64_dp, ARM_HWCAP_A64_ASIMDDP); GET_FEATURE_ID(aa64_fcma, ARM_HWCAP_A64_FCMA); GET_FEATURE_ID(aa64_sve, ARM_HWCAP_A64_SVE); -#undef GET_FEATURE #undef GET_FEATURE_ID return hwcaps; 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_aa64pfr0; t = FIELD_DP64(t, ID_AA64PFR0, SVE, 1); + t = FIELD_DP64(t, ID_AA64PFR0, FP, 1); + t = FIELD_DP64(t, ID_AA64PFR0, ADVSIMD, 1); cpu->isar.id_aa64pfr0 = t; /* Replicate the same data to the 32-bit id registers. */ @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) u = FIELD_DP32(u, ID_ISAR6, DP, 1); cpu->isar.id_isar6 = u; -#ifdef CONFIG_USER_ONLY - /* We don't set these in system emulation mode for the moment, - * since we don't correctly set the ID registers to advertise them, - * and in some cases they're only available in AArch64 and not AArch32, - * whereas the architecture requires them to be present in both if - * present in either. + /* + * FIXME: We do not yet support ARMv8.2-fp16 for AArch32 yet, + * so do not set MVFR1.FPHP. Strictly speaking this is not legal, + * but it is also not legal to enable SVE without support for FP16, + * and enabling SVE in system mode is more useful in the short term. */ - set_feature(&cpu->env, ARM_FEATURE_V8_FP16); + +#ifdef CONFIG_USER_ONLY /* For usermode -cpu max we can use a larger and more efficient DCZ * blocksize since we don't have to follow what the hardware does. */ diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(vfp_set_fpscr)(CPUARMState *env, uint32_t val) uint32_t changed; /* When ARMv8.2-FP16 is not supported, FZ16 is RES0. */ - if (!arm_feature(env, ARM_FEATURE_V8_FP16)) { + if (!cpu_isar_feature(aa64_fp16, arm_env_get_cpu(env))) { val &= ~FPCR_FZ16; } diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_fp_compare(DisasContext *s, uint32_t insn) break; case 3: size = MO_16; - if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (dc_isar_feature(aa64_fp16, s)) { break; } /* fallthru */ @@ -XXX,XX +XXX,XX @@ static void disas_fp_ccomp(DisasContext *s, uint32_t insn) break; case 3: size = MO_16; - if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (dc_isar_feature(aa64_fp16, s)) { break; } /* fallthru */ @@ -XXX,XX +XXX,XX @@ static void disas_fp_csel(DisasContext *s, uint32_t insn) break; case 3: sz = MO_16; - if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (dc_isar_feature(aa64_fp16, s)) { break; } /* fallthru */ @@ -XXX,XX +XXX,XX @@ static void disas_fp_1src(DisasContext *s, uint32_t insn) handle_fp_1src_double(s, opcode, rd, rn); break; case 3: - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_fp_2src(DisasContext *s, uint32_t insn) handle_fp_2src_double(s, opcode, rd, rn, rm); break; case 3: - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_fp_3src(DisasContext *s, uint32_t insn) handle_fp_3src_double(s, o0, o1, rd, rn, rm, ra); break; case 3: - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_fp_imm(DisasContext *s, uint32_t insn) break; case 3: sz = MO_16; - if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (dc_isar_feature(aa64_fp16, s)) { break; } /* fallthru */ @@ -XXX,XX +XXX,XX @@ static void disas_fp_fixed_conv(DisasContext *s, uint32_t insn) case 1: /* float64 */ break; case 3: /* float16 */ - if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (dc_isar_feature(aa64_fp16, s)) { break; } /* fallthru */ @@ -XXX,XX +XXX,XX @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) break; case 0x6: /* 16-bit float, 32-bit int */ case 0xe: /* 16-bit float, 64-bit int */ - if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (dc_isar_feature(aa64_fp16, s)) { break; } /* fallthru */ @@ -XXX,XX +XXX,XX @@ static void disas_fp_int_conv(DisasContext *s, uint32_t insn) case 1: /* float64 */ break; case 3: /* float16 */ - if (arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (dc_isar_feature(aa64_fp16, s)) { break; } /* fallthru */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_across_lanes(DisasContext *s, uint32_t insn) */ is_min = extract32(size, 1, 1); is_fp = true; - if (!is_u && arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!is_u && dc_isar_feature(aa64_fp16, s)) { size = 1; } else if (!is_u || !is_q || extract32(size, 0, 1)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_mod_imm(DisasContext *s, uint32_t insn) if (o2 != 0 || ((cmode == 0xf) && is_neg && !is_q)) { /* Check for FMOV (vector, immediate) - half-precision */ - if (!(arm_dc_feature(s, ARM_FEATURE_V8_FP16) && o2 && cmode == 0xf)) { + if (!(dc_isar_feature(aa64_fp16, s) && o2 && cmode == 0xf)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_pairwise(DisasContext *s, uint32_t insn) case 0x2f: /* FMINP */ /* FP op, size[0] is 32 or 64 bit*/ if (!u) { - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } else { @@ -XXX,XX +XXX,XX @@ static void handle_simd_shift_intfp_conv(DisasContext *s, bool is_scalar, size = MO_32; } else if (immh & 2) { size = MO_16; - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void handle_simd_shift_fpint_conv(DisasContext *s, bool is_scalar, size = MO_32; } else if (immh & 0x2) { size = MO_16; - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_same_fp16(DisasContext *s, return; } - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); } @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_fp16(DisasContext *s, uint32_t insn) TCGv_ptr fpst; bool pairwise = false; - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) case 0x1c: /* FCADD, #90 */ case 0x1e: /* FCADD, #270 */ if (size == 0 - || (size == 1 && !arm_dc_feature(s, ARM_FEATURE_V8_FP16)) + || (size == 1 && !dc_isar_feature(aa64_fp16, s)) || (size == 3 && !is_q)) { unallocated_encoding(s); return; @@ -XXX,XX +XXX,XX @@ static void disas_simd_two_reg_misc_fp16(DisasContext *s, uint32_t insn) bool need_fpst = true; int rmode; - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } break; } - if (is_fp16 && !arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (is_fp16 && !dc_isar_feature(aa64_fp16, s)) { unallocated_encoding(s); return; } diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) int size = extract32(insn, 20, 1); data = extract32(insn, 23, 2); /* rot */ if (!dc_isar_feature(aa32_vcma, s) - || (!size && !arm_dc_feature(s, ARM_FEATURE_V8_FP16))) { + || (!size && !dc_isar_feature(aa32_fp16_arith, s))) { return 1; } fn_gvec_ptr = size ? gen_helper_gvec_fcmlas : gen_helper_gvec_fcmlah; @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) int size = extract32(insn, 20, 1); data = extract32(insn, 24, 1); /* rot */ if (!dc_isar_feature(aa32_vcma, s) - || (!size && !arm_dc_feature(s, ARM_FEATURE_V8_FP16))) { + || (!size && !dc_isar_feature(aa32_fp16_arith, s))) { return 1; } fn_gvec_ptr = size ? gen_helper_gvec_fcadds : gen_helper_gvec_fcaddh; @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) return 1; } if (size == 0) { - if (!arm_dc_feature(s, ARM_FEATURE_V8_FP16)) { + if (!dc_isar_feature(aa32_fp16_arith, s)) { return 1; } /* For fp16, rm is just Vm, and index is M. */ -- 2.19.1 For AArch32, exception return happens through certain kinds of CPSR write. We don't currently have any CPU_LOG_INT logging of these events (unlike AArch64, where we log in the ERET instruction). Add some suitable logging. This will log exception returns like this: Exception return from AArch32 hyp to usr PC 0x80100374 paralleling the existing logging in the exception_return helper for AArch64 exception returns: Exception return from AArch64 EL2 to AArch64 EL0 PC 0x8003045c Exception return from AArch64 EL2 to AArch32 EL0 PC 0x8003045c (Note that an AArch32 exception return can only be AArch32->AArch32, never to AArch64.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-2-peter.maydell@linaro.org --- target/arm/internals.h | 18 ++++++++++++++++++ target/arm/helper.c | 10 ++++++++++ target/arm/translate.c | 7 +------ 3 files changed, 29 insertions(+), 6 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t v7m_sp_limit(CPUARMState *env) } } +/** + * aarch32_mode_name(): Return name of the AArch32 CPU mode + * @psr: Program Status Register indicating CPU mode + * + * Returns, for debug logging purposes, a printable representation + * of the AArch32 CPU mode ("svc", "usr", etc) as indicated by + * the low bits of the specified PSR. + */ +static inline const char *aarch32_mode_name(uint32_t psr) +{ + static const char cpu_mode_names[16][4] = { + "usr", "fiq", "irq", "svc", "???", "???", "mon", "abt", + "???", "???", "hyp", "und", "???", "???", "???", "sys" + }; + + return cpu_mode_names[psr & 0xf]; +} + #endif diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void cpsr_write(CPUARMState *env, uint32_t val, uint32_t mask, mask |= CPSR_IL; val |= CPSR_IL; } + qemu_log_mask(LOG_GUEST_ERROR, + "Illegal AArch32 mode switch attempt from %s to %s\n", + aarch32_mode_name(env->uncached_cpsr), + aarch32_mode_name(val)); } else { + qemu_log_mask(CPU_LOG_INT, "%s %s to %s PC 0x%" PRIx32 "\n", + write_type == CPSRWriteExceptionReturn ? + "Exception return from AArch32" : + "AArch32 mode switch from", + aarch32_mode_name(env->uncached_cpsr), + aarch32_mode_name(val), env->regs[15]); switch_mode(env, val & CPSR_M); } } diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUState *cpu, TranslationBlock *tb) translator_loop(ops, &dc.base, cpu, tb); } -static const char *cpu_mode_names[16] = { - "usr", "fiq", "irq", "svc", "???", "???", "mon", "abt", - "???", "???", "hyp", "und", "???", "???", "???", "sys" -}; - void arm_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf, int flags) { @@ -XXX,XX +XXX,XX @@ void arm_cpu_dump_state(CPUState *cs, FILE *f, fprintf_function cpu_fprintf, psr & CPSR_V ? 'V' : '-', psr & CPSR_T ? 'T' : 'A', ns_status, - cpu_mode_names[psr & 0xf], (psr & 0x10) ? 32 : 26); + aarch32_mode_name(psr), (psr & 0x10) ? 32 : 26); } if (flags & CPU_DUMP_FPU) { -- 2.19.1 The switch_mode() function is defined in target/arm/helper.c and used only in that file and nowhere else, so we can make it file-local rather than global. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-3-peter.maydell@linaro.org --- target/arm/internals.h | 1 - target/arm/helper.c | 6 ++++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline int bank_number(int mode) g_assert_not_reached(); } -void switch_mode(CPUARMState *, int); void arm_cpu_register_gdb_regs_for_features(ARMCPU *cpu); void arm_translate_init(void); diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void v8m_security_lookup(CPUARMState *env, uint32_t address, V8M_SAttributes *sattrs); #endif +static void switch_mode(CPUARMState *env, int mode); + static int vfp_gdb_get_reg(CPUARMState *env, uint8_t *buf, int reg) { int nregs; @@ -XXX,XX +XXX,XX @@ uint32_t HELPER(v7m_tt)(CPUARMState *env, uint32_t addr, uint32_t op) return 0; } -void switch_mode(CPUARMState *env, int mode) +static void switch_mode(CPUARMState *env, int mode) { ARMCPU *cpu = arm_env_get_cpu(env); @@ -XXX,XX +XXX,XX @@ void aarch64_sync_64_to_32(CPUARMState *env) #else -void switch_mode(CPUARMState *env, int mode) +static void switch_mode(CPUARMState *env, int mode) { int old_mode; int i; -- 2.19.1 The HCR.FB virtualization configuration register bit requests that TLB maintenance, branch predictor invalidate-all and icache invalidate-all operations performed in NS EL1 should be upgraded from "local CPU only to "broadcast within Inner Shareable domain". For QEMU we NOP the branch predictor and icache operations, so we only need to upgrade the TLB invalidates: AArch32 TLBIALL, TLBIMVA, TLBIASID, DTLBIALL, DTLBIMVA, DTLBIASID, ITLBIALL, ITLBIMVA, ITLBIASID, TLBIMVAA, TLBIMVAL, TLBIMVAAL AArch64 TLBI VMALLE1, TLBI VAE1, TLBI ASIDE1, TLBI VAAE1, TLBI VALE1, TLBI VAALE1 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-4-peter.maydell@linaro.org --- target/arm/helper.c | 191 +++++++++++++++++++++++++++----------------- 1 file changed, 116 insertions(+), 75 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 void contextidr_write(CPUARMState *env, const ARMCPRegInfo *ri, raw_write(env, ri, value); } -static void tlbiall_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate all (TLBIALL) */ - ARMCPU *cpu = arm_env_get_cpu(env); - - tlb_flush(CPU(cpu)); -} - -static void tlbimva_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate single TLB entry by MVA and ASID (TLBIMVA) */ - ARMCPU *cpu = arm_env_get_cpu(env); - - tlb_flush_page(CPU(cpu), value & TARGET_PAGE_MASK); -} - -static void tlbiasid_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate by ASID (TLBIASID) */ - ARMCPU *cpu = arm_env_get_cpu(env); - - tlb_flush(CPU(cpu)); -} - -static void tlbimvaa_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate single entry by MVA, all ASIDs (TLBIMVAA) */ - ARMCPU *cpu = arm_env_get_cpu(env); - - tlb_flush_page(CPU(cpu), value & TARGET_PAGE_MASK); -} - /* IS variants of TLB operations must affect all cores */ static void tlbiall_is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) @@ -XXX,XX +XXX,XX @@ static void tlbimvaa_is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_page_all_cpus_synced(cs, value & TARGET_PAGE_MASK); } +/* + * Non-IS variants of TLB operations are upgraded to + * IS versions if we are at NS EL1 and HCR_EL2.FB is set to + * force broadcast of these operations. + */ +static bool tlb_force_broadcast(CPUARMState *env) +{ + return (env->cp15.hcr_el2 & HCR_FB) && + arm_current_el(env) == 1 && arm_is_secure_below_el3(env); +} + +static void tlbiall_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Invalidate all (TLBIALL) */ + ARMCPU *cpu = arm_env_get_cpu(env); + + if (tlb_force_broadcast(env)) { + tlbiall_is_write(env, NULL, value); + return; + } + + tlb_flush(CPU(cpu)); +} + +static void tlbimva_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Invalidate single TLB entry by MVA and ASID (TLBIMVA) */ + ARMCPU *cpu = arm_env_get_cpu(env); + + if (tlb_force_broadcast(env)) { + tlbimva_is_write(env, NULL, value); + return; + } + + tlb_flush_page(CPU(cpu), value & TARGET_PAGE_MASK); +} + +static void tlbiasid_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Invalidate by ASID (TLBIASID) */ + ARMCPU *cpu = arm_env_get_cpu(env); + + if (tlb_force_broadcast(env)) { + tlbiasid_is_write(env, NULL, value); + return; + } + + tlb_flush(CPU(cpu)); +} + +static void tlbimvaa_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Invalidate single entry by MVA, all ASIDs (TLBIMVAA) */ + ARMCPU *cpu = arm_env_get_cpu(env); + + if (tlb_force_broadcast(env)) { + tlbimvaa_is_write(env, NULL, value); + return; + } + + tlb_flush_page(CPU(cpu), value & TARGET_PAGE_MASK); +} + static void tlbiall_nsnh_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ static CPAccessResult aa64_cacheop_access(CPUARMState *env, * Page D4-1736 (DDI0487A.b) */ -static void tlbi_aa64_vmalle1_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - CPUState *cs = ENV_GET_CPU(env); - - if (arm_is_secure_below_el3(env)) { - tlb_flush_by_mmuidx(cs, - ARMMMUIdxBit_S1SE1 | - ARMMMUIdxBit_S1SE0); - } else { - tlb_flush_by_mmuidx(cs, - ARMMMUIdxBit_S12NSE1 | - ARMMMUIdxBit_S12NSE0); - } -} - static void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vmalle1is_write(CPUARMState *env, const ARMCPRegInfo *ri, } } +static void tlbi_aa64_vmalle1_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + CPUState *cs = ENV_GET_CPU(env); + + if (tlb_force_broadcast(env)) { + tlbi_aa64_vmalle1_write(env, NULL, value); + return; + } + + if (arm_is_secure_below_el3(env)) { + tlb_flush_by_mmuidx(cs, + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); + } else { + tlb_flush_by_mmuidx(cs, + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); + } +} + static void tlbi_aa64_alle1_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_alle3is_write(CPUARMState *env, const ARMCPRegInfo *ri, tlb_flush_by_mmuidx_all_cpus_synced(cs, ARMMMUIdxBit_S1E3); } -static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri, - uint64_t value) -{ - /* Invalidate by VA, EL1&0 (AArch64 version). - * Currently handles all of VAE1, VAAE1, VAALE1 and VALE1, - * since we don't support flush-for-specific-ASID-only or - * flush-last-level-only. - */ - ARMCPU *cpu = arm_env_get_cpu(env); - CPUState *cs = CPU(cpu); - uint64_t pageaddr = sextract64(value << 12, 0, 56); - - if (arm_is_secure_below_el3(env)) { - tlb_flush_page_by_mmuidx(cs, pageaddr, - ARMMMUIdxBit_S1SE1 | - ARMMMUIdxBit_S1SE0); - } else { - tlb_flush_page_by_mmuidx(cs, pageaddr, - ARMMMUIdxBit_S12NSE1 | - ARMMMUIdxBit_S12NSE0); - } -} - static void tlbi_aa64_vae2_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { @@ -XXX,XX +XXX,XX @@ static void tlbi_aa64_vae1is_write(CPUARMState *env, const ARMCPRegInfo *ri, } } +static void tlbi_aa64_vae1_write(CPUARMState *env, const ARMCPRegInfo *ri, + uint64_t value) +{ + /* Invalidate by VA, EL1&0 (AArch64 version). + * Currently handles all of VAE1, VAAE1, VAALE1 and VALE1, + * since we don't support flush-for-specific-ASID-only or + * flush-last-level-only. + */ + ARMCPU *cpu = arm_env_get_cpu(env); + CPUState *cs = CPU(cpu); + uint64_t pageaddr = sextract64(value << 12, 0, 56); + + if (tlb_force_broadcast(env)) { + tlbi_aa64_vae1is_write(env, NULL, value); + return; + } + + if (arm_is_secure_below_el3(env)) { + tlb_flush_page_by_mmuidx(cs, pageaddr, + ARMMMUIdxBit_S1SE1 | + ARMMMUIdxBit_S1SE0); + } else { + tlb_flush_page_by_mmuidx(cs, pageaddr, + ARMMMUIdxBit_S12NSE1 | + ARMMMUIdxBit_S12NSE0); + } +} + static void tlbi_aa64_vae2is_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { -- 2.19.1 The HCR.DC virtualization configuration register bit has the following effects: * SCTLR.M behaves as if it is 0 for all purposes except direct reads of the bit * HCR.VM behaves as if it is 1 for all purposes except direct reads of the bit * the memory type produced by the first stage of the EL1&EL0 translation regime is Normal Non-Shareable, Inner Write-Back Read-Allocate Write-Allocate, Outer Write-Back Read-Allocate Write-Allocate. Implement this behaviour. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-5-peter.maydell@linaro.org --- target/arm/helper.c | 23 +++++++++++++++++++++-- 1 file changed, 21 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static uint64_t do_ats_write(CPUARMState *env, uint64_t value, * * The Non-secure TTBCR.EAE bit is set to 1 * * The implementation includes EL2, and the value of HCR.VM is 1 * + * (Note that HCR.DC makes HCR.VM behave as if it is 1.) + * * ATS1Hx always uses the 64bit format (not supported yet). */ format64 = arm_s1_regime_using_lpae_format(env, mmu_idx); if (arm_feature(env, ARM_FEATURE_EL2)) { if (mmu_idx == ARMMMUIdx_S12NSE0 || mmu_idx == ARMMMUIdx_S12NSE1) { - format64 |= env->cp15.hcr_el2 & HCR_VM; + format64 |= env->cp15.hcr_el2 & (HCR_VM | HCR_DC); } else { format64 |= arm_current_el(env) == 2; } @@ -XXX,XX +XXX,XX @@ static inline bool regime_translation_disabled(CPUARMState *env, } if (mmu_idx == ARMMMUIdx_S2NS) { - return (env->cp15.hcr_el2 & HCR_VM) == 0; + /* HCR.DC means HCR.VM behaves as 1 */ + return (env->cp15.hcr_el2 & (HCR_DC | HCR_VM)) == 0; } if (env->cp15.hcr_el2 & HCR_TGE) { @@ -XXX,XX +XXX,XX @@ static inline bool regime_translation_disabled(CPUARMState *env, } } + if ((env->cp15.hcr_el2 & HCR_DC) && + (mmu_idx == ARMMMUIdx_S1NSE0 || mmu_idx == ARMMMUIdx_S1NSE1)) { + /* HCR.DC means SCTLR_EL1.M behaves as 0 */ + return true; + } + return (regime_sctlr(env, mmu_idx) & SCTLR_M) == 0; } @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr(CPUARMState *env, target_ulong address, /* Combine the S1 and S2 cache attributes, if needed */ if (!ret && cacheattrs != NULL) { + if (env->cp15.hcr_el2 & HCR_DC) { + /* + * HCR.DC forces the first stage attributes to + * Normal Non-Shareable, + * Inner Write-Back Read-Allocate Write-Allocate, + * Outer Write-Back Read-Allocate Write-Allocate. + */ + cacheattrs->attrs = 0xff; + cacheattrs->shareability = 0; + } *cacheattrs = combine_cacheattrs(*cacheattrs, cacheattrs2); } -- 2.19.1 The A/I/F bits in ISR_EL1 should track the virtual interrupt status, not the physical interrupt status, if the associated HCR_EL2.AMO/IMO/FMO bit is set. Implement this, rather than always showing the physical interrupt status. We don't currently implement anything to do with external aborts, so this applies only to the I and F bits (though it ought to be possible for the outer guest to present a virtual external abort to the inner guest, even if QEMU doesn't emulate physical external aborts, so there is missing functionality in this area). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-6-peter.maydell@linaro.org --- target/arm/helper.c | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 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 uint64_t isr_read(CPUARMState *env, const ARMCPRegInfo *ri) CPUState *cs = ENV_GET_CPU(env); uint64_t ret = 0; - if (cs->interrupt_request & CPU_INTERRUPT_HARD) { - ret |= CPSR_I; + if (arm_hcr_el2_imo(env)) { + if (cs->interrupt_request & CPU_INTERRUPT_VIRQ) { + ret |= CPSR_I; + } + } else { + if (cs->interrupt_request & CPU_INTERRUPT_HARD) { + ret |= CPSR_I; + } } - if (cs->interrupt_request & CPU_INTERRUPT_FIQ) { - ret |= CPSR_F; + + if (arm_hcr_el2_fmo(env)) { + if (cs->interrupt_request & CPU_INTERRUPT_VFIQ) { + ret |= CPSR_F; + } + } else { + if (cs->interrupt_request & CPU_INTERRUPT_FIQ) { + ret |= CPSR_F; + } } + /* External aborts are not possible in QEMU so A bit is always clear */ return ret; } -- 2.19.1 The HCR_EL2 VI and VF bits are supposed to track whether there is a pending virtual IRQ or virtual FIQ. For QEMU we store the pending VIRQ/VFIQ status in cs->interrupt_request, so this means: * if the register is read we must get these bit values from cs->interrupt_request * if the register is written then we must write the bit values back into cs->interrupt_request Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-7-peter.maydell@linaro.org --- target/arm/helper.c | 47 +++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 43 insertions(+), 4 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo el3_no_el2_v8_cp_reginfo[] = { static void hcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { ARMCPU *cpu = arm_env_get_cpu(env); + CPUState *cs = ENV_GET_CPU(env); uint64_t valid_mask = HCR_MASK; if (arm_feature(env, ARM_FEATURE_EL3)) { @@ -XXX,XX +XXX,XX @@ static void hcr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) /* Clear RES0 bits. */ value &= valid_mask; + /* + * VI and VF are kept in cs->interrupt_request. Modifying that + * requires that we have the iothread lock, which is done by + * marking the reginfo structs as ARM_CP_IO. + * Note that if a write to HCR pends a VIRQ or VFIQ it is never + * possible for it to be taken immediately, because VIRQ and + * VFIQ are masked unless running at EL0 or EL1, and HCR + * can only be written at EL2. + */ + g_assert(qemu_mutex_iothread_locked()); + if (value & HCR_VI) { + cs->interrupt_request |= CPU_INTERRUPT_VIRQ; + } else { + cs->interrupt_request &= ~CPU_INTERRUPT_VIRQ; + } + if (value & HCR_VF) { + cs->interrupt_request |= CPU_INTERRUPT_VFIQ; + } else { + cs->interrupt_request &= ~CPU_INTERRUPT_VFIQ; + } + value &= ~(HCR_VI | HCR_VF); + /* These bits change the MMU setup: * HCR_VM enables stage 2 translation * HCR_PTW forbids certain page-table setups @@ -XXX,XX +XXX,XX @@ static void hcr_writelow(CPUARMState *env, const ARMCPRegInfo *ri, hcr_write(env, NULL, value); } +static uint64_t hcr_read(CPUARMState *env, const ARMCPRegInfo *ri) +{ + /* The VI and VF bits live in cs->interrupt_request */ + uint64_t ret = env->cp15.hcr_el2 & ~(HCR_VI | HCR_VF); + CPUState *cs = ENV_GET_CPU(env); + + if (cs->interrupt_request & CPU_INTERRUPT_VIRQ) { + ret |= HCR_VI; + } + if (cs->interrupt_request & CPU_INTERRUPT_VFIQ) { + ret |= HCR_VF; + } + return ret; +} + static const ARMCPRegInfo el2_cp_reginfo[] = { { .name = "HCR_EL2", .state = ARM_CP_STATE_AA64, + .type = ARM_CP_IO, .opc0 = 3, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 0, .access = PL2_RW, .fieldoffset = offsetof(CPUARMState, cp15.hcr_el2), - .writefn = hcr_write }, + .writefn = hcr_write, .readfn = hcr_read }, { .name = "HCR", .state = ARM_CP_STATE_AA32, - .type = ARM_CP_ALIAS, + .type = ARM_CP_ALIAS | ARM_CP_IO, .cp = 15, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 0, .access = PL2_RW, .fieldoffset = offsetof(CPUARMState, cp15.hcr_el2), - .writefn = hcr_writelow }, + .writefn = hcr_writelow, .readfn = hcr_read }, { .name = "ELR_EL2", .state = ARM_CP_STATE_AA64, .type = ARM_CP_ALIAS, .opc0 = 3, .opc1 = 4, .crn = 4, .crm = 0, .opc2 = 1, @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo el2_cp_reginfo[] = { static const ARMCPRegInfo el2_v8_cp_reginfo[] = { { .name = "HCR2", .state = ARM_CP_STATE_AA32, - .type = ARM_CP_ALIAS, + .type = ARM_CP_ALIAS | ARM_CP_IO, .cp = 15, .opc1 = 4, .crn = 1, .crm = 1, .opc2 = 4, .access = PL2_RW, .fieldoffset = offsetofhigh32(CPUARMState, cp15.hcr_el2), -- 2.19.1 If the HCR_EL2 PTW virtualizaiton configuration register bit is set, then this means that a stage 2 Permission fault must be generated if a stage 1 translation table access is made to an address that is mapped as Device memory in stage 2. Implement this. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-8-peter.maydell@linaro.org --- target/arm/helper.c | 21 ++++++++++++++++++++- 1 file changed, 20 insertions(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx, hwaddr s2pa; int s2prot; int ret; + ARMCacheAttrs cacheattrs = {}; + ARMCacheAttrs *pcacheattrs = NULL; + + if (env->cp15.hcr_el2 & HCR_PTW) { + /* + * PTW means we must fault if this S1 walk touches S2 Device + * memory; otherwise we don't care about the attributes and can + * save the S2 translation the effort of computing them. + */ + pcacheattrs = &cacheattrs; + } ret = get_phys_addr_lpae(env, addr, 0, ARMMMUIdx_S2NS, &s2pa, - &txattrs, &s2prot, &s2size, fi, NULL); + &txattrs, &s2prot, &s2size, fi, pcacheattrs); if (ret) { assert(fi->type != ARMFault_None); fi->s2addr = addr; @@ -XXX,XX +XXX,XX @@ static hwaddr S1_ptw_translate(CPUARMState *env, ARMMMUIdx mmu_idx, fi->s1ptw = true; return ~0; } + if (pcacheattrs && (pcacheattrs->attrs & 0xf0) == 0) { + /* Access was to Device memory: generate Permission fault */ + fi->type = ARMFault_Permission; + fi->s2addr = addr; + fi->stage2 = true; + fi->s1ptw = true; + return ~0; + } addr = s2pa; } return addr; -- 2.19.1 Create and use a utility function to extract the EC field from a syndrome, rather than open-coding the shift. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-9-peter.maydell@linaro.org --- target/arm/internals.h | 5 +++++ target/arm/helper.c | 4 ++-- target/arm/kvm64.c | 2 +- target/arm/op_helper.c | 2 +- 4 files changed, 9 insertions(+), 4 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ enum arm_exception_class { #define ARM_EL_IL (1 << ARM_EL_IL_SHIFT) #define ARM_EL_ISV (1 << ARM_EL_ISV_SHIFT) +static inline uint32_t syn_get_ec(uint32_t syn) +{ + return syn >> ARM_EL_EC_SHIFT; +} + /* Utility functions for constructing various kinds of syndrome value. * Note that in general we follow the AArch64 syndrome values; in a * few cases the value in HSR for exceptions taken to AArch32 Hyp diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch32(CPUState *cs) uint32_t moe; /* If this is a debug exception we must update the DBGDSCR.MOE bits */ - switch (env->exception.syndrome >> ARM_EL_EC_SHIFT) { + switch (syn_get_ec(env->exception.syndrome)) { case EC_BREAKPOINT: case EC_BREAKPOINT_SAME_EL: moe = 1; @@ -XXX,XX +XXX,XX @@ void arm_cpu_do_interrupt(CPUState *cs) if (qemu_loglevel_mask(CPU_LOG_INT) && !excp_is_internal(cs->exception_index)) { qemu_log_mask(CPU_LOG_INT, "...with ESR 0x%x/0x%" PRIx32 "\n", - env->exception.syndrome >> ARM_EL_EC_SHIFT, + syn_get_ec(env->exception.syndrome), env->exception.syndrome); } diff --git a/target/arm/kvm64.c b/target/arm/kvm64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/kvm64.c +++ b/target/arm/kvm64.c @@ -XXX,XX +XXX,XX @@ int kvm_arch_remove_sw_breakpoint(CPUState *cs, struct kvm_sw_breakpoint *bp) bool kvm_arm_handle_debug(CPUState *cs, struct kvm_debug_exit_arch *debug_exit) { - int hsr_ec = debug_exit->hsr >> ARM_EL_EC_SHIFT; + int hsr_ec = syn_get_ec(debug_exit->hsr); ARMCPU *cpu = ARM_CPU(cs); CPUClass *cc = CPU_GET_CLASS(cs); CPUARMState *env = &cpu->env; diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ void raise_exception(CPUARMState *env, uint32_t excp, * (see DDI0478C.a D1.10.4) */ target_el = 2; - if (syndrome >> ARM_EL_EC_SHIFT == EC_ADVSIMDFPACCESSTRAP) { + if (syn_get_ec(syndrome) == EC_ADVSIMDFPACCESSTRAP) { syndrome = syn_uncategorized(); } } -- 2.19.1 For the v7 version of the Arm architecture, the IL bit in syndrome register values where the field is not valid was defined to be UNK/SBZP. In v8 this is RES1, which is what QEMU currently implements. Handle the desired v7 behaviour by squashing the IL bit for the affected cases: * EC == EC_UNCATEGORIZED * prefetch aborts * data aborts where ISV is 0 (The fourth case listed in the v8 Arm ARM DDI 0487C.a in section G7.2.70, "illegal state exception", can't happen on a v7 CPU.) This deals with a corner case noted in a comment. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-10-peter.maydell@linaro.org --- target/arm/internals.h | 7 ++----- target/arm/helper.c | 13 +++++++++++++ 2 files changed, 15 insertions(+), 5 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_get_ec(uint32_t syn) /* Utility functions for constructing various kinds of syndrome value. * Note that in general we follow the AArch64 syndrome values; in a * few cases the value in HSR for exceptions taken to AArch32 Hyp - * mode differs slightly, so if we ever implemented Hyp mode then the - * syndrome value would need some massaging on exception entry. - * (One example of this is that AArch64 defaults to IL bit set for - * exceptions which don't specifically indicate information about the - * trapping instruction, whereas AArch32 defaults to IL bit clear.) + * mode differs slightly, and we fix this up when populating HSR in + * arm_cpu_do_interrupt_aarch32_hyp(). */ static inline uint32_t syn_uncategorized(void) { diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch32_hyp(CPUState *cs) } if (cs->exception_index != EXCP_IRQ && cs->exception_index != EXCP_FIQ) { + if (!arm_feature(env, ARM_FEATURE_V8)) { + /* + * QEMU syndrome values are v8-style. v7 has the IL bit + * UNK/SBZP for "field not valid" cases, where v8 uses RES1. + * If this is a v7 CPU, squash the IL bit in those cases. + */ + if (cs->exception_index == EXCP_PREFETCH_ABORT || + (cs->exception_index == EXCP_DATA_ABORT && + !(env->exception.syndrome & ARM_EL_ISV)) || + syn_get_ec(env->exception.syndrome) == EC_UNCATEGORIZED) { + env->exception.syndrome &= ~ARM_EL_IL; + } + } env->cp15.esr_el[2] = env->exception.syndrome; } -- 2.19.1 For traps of FP/SIMD instructions to AArch32 Hyp mode, the syndrome provided in HSR has more information than is reported to AArch64. Specifically, there are extra fields TA and coproc which indicate whether the trapped instruction was FP or SIMD. Add this extra information to the syndromes we construct, and mask it out when taking the exception to AArch64. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181012144235.19646-11-peter.maydell@linaro.org --- target/arm/internals.h | 14 +++++++++++++- target/arm/helper.c | 9 +++++++++ target/arm/translate.c | 8 ++++---- 3 files changed, 26 insertions(+), 5 deletions(-) diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_get_ec(uint32_t syn) * few cases the value in HSR for exceptions taken to AArch32 Hyp * mode differs slightly, and we fix this up when populating HSR in * arm_cpu_do_interrupt_aarch32_hyp(). + * The exception is FP/SIMD access traps -- these report extra information + * when taking an exception to AArch32. For those we include the extra coproc + * and TA fields, and mask them out when taking the exception to AArch64. */ static inline uint32_t syn_uncategorized(void) { @@ -XXX,XX +XXX,XX @@ static inline uint32_t syn_cp15_rrt_trap(int cv, int cond, int opc1, int crm, static inline uint32_t syn_fp_access_trap(int cv, int cond, bool is_16bit) { + /* AArch32 FP trap or any AArch64 FP/SIMD trap: TA == 0 coproc == 0xa */ return (EC_ADVSIMDFPACCESSTRAP << ARM_EL_EC_SHIFT) | (is_16bit ? 0 : ARM_EL_IL) - | (cv << 24) | (cond << 20); + | (cv << 24) | (cond << 20) | 0xa; +} + +static inline uint32_t syn_simd_access_trap(int cv, int cond, bool is_16bit) +{ + /* AArch32 SIMD trap: TA == 1 coproc == 0 */ + return (EC_ADVSIMDFPACCESSTRAP << ARM_EL_EC_SHIFT) + | (is_16bit ? 0 : ARM_EL_IL) + | (cv << 24) | (cond << 20) | (1 << 5); } static inline uint32_t syn_sve_access_trap(void) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_do_interrupt_aarch64(CPUState *cs) case EXCP_HVC: case EXCP_HYP_TRAP: case EXCP_SMC: + if (syn_get_ec(env->exception.syndrome) == EC_ADVSIMDFPACCESSTRAP) { + /* + * QEMU internal FP/SIMD syndromes from AArch32 include the + * TA and coproc fields which are only exposed if the exception + * is taken to AArch32 Hyp mode. Mask them out to get a valid + * AArch64 format syndrome. + */ + env->exception.syndrome &= ~MAKE_64BIT_MASK(0, 20); + } env->cp15.esr_el[new_el] = env->exception.syndrome; break; case EXCP_IRQ: diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) */ if (s->fp_excp_el) { gen_exception_insn(s, 4, EXCP_UDEF, - syn_fp_access_trap(1, 0xe, false), s->fp_excp_el); + syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); return 0; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) */ if (s->fp_excp_el) { gen_exception_insn(s, 4, EXCP_UDEF, - syn_fp_access_trap(1, 0xe, false), s->fp_excp_el); + syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); return 0; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_3same_ext(DisasContext *s, uint32_t insn) if (s->fp_excp_el) { gen_exception_insn(s, 4, EXCP_UDEF, - syn_fp_access_trap(1, 0xe, false), s->fp_excp_el); + syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); return 0; } if (!s->vfp_enabled) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_insn_2reg_scalar_ext(DisasContext *s, uint32_t insn) if (s->fp_excp_el) { gen_exception_insn(s, 4, EXCP_UDEF, - syn_fp_access_trap(1, 0xe, false), s->fp_excp_el); + syn_simd_access_trap(1, 0xe, false), s->fp_excp_el); return 0; } if (!s->vfp_enabled) { -- 2.19.1 From: Stewart Hildebrand <Stewart.Hildebrand@dornerworks.com> "The Image must be placed text_offset bytes from a 2MB aligned base address anywhere in usable system RAM and called there." For the virt board, we write our startup bootloader at the very bottom of RAM, so that bit can't be used for the image. To avoid overlap in case the image requests to be loaded at an offset smaller than our bootloader, we increment the load offset to the next 2MB. This fixes a boot failure for Xen AArch64. Signed-off-by: Stewart Hildebrand <stewart.hildebrand@dornerworks.com> Tested-by: Andre Przywara <andre.przywara@arm.com> Message-id: b8a89518794b4436af0c151ed10de4fa@dornerworks.com [PMM: Rephrased a comment a bit] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/boot.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ #include "qemu/config-file.h" #include "qemu/option.h" #include "exec/address-spaces.h" +#include "qemu/units.h" /* Kernel boot protocol is specified in the kernel docs * Documentation/arm/Booting and Documentation/arm64/booting.txt @@ -XXX,XX +XXX,XX @@ #define ARM64_TEXT_OFFSET_OFFSET 8 #define ARM64_MAGIC_OFFSET 56 +#define BOOTLOADER_MAX_SIZE (4 * KiB) + AddressSpace *arm_boot_address_space(ARMCPU *cpu, const struct arm_boot_info *info) { @@ -XXX,XX +XXX,XX @@ static void write_bootloader(const char *name, hwaddr addr, code[i] = tswap32(insn); } + assert((len * sizeof(uint32_t)) < BOOTLOADER_MAX_SIZE); + rom_add_blob_fixed_as(name, code, len * sizeof(uint32_t), addr, as); g_free(code); @@ -XXX,XX +XXX,XX @@ static uint64_t load_aarch64_image(const char *filename, hwaddr mem_base, memcpy(&hdrvals, buffer + ARM64_TEXT_OFFSET_OFFSET, sizeof(hdrvals)); if (hdrvals[1] != 0) { kernel_load_offset = le64_to_cpu(hdrvals[0]); + + /* + * We write our startup "bootloader" at the very bottom of RAM, + * so that bit can't be used for the image. Luckily the Image + * format specification is that the image requests only an offset + * from a 2MB boundary, not an absolute load address. So if the + * image requests an offset that might mean it overlaps with the + * bootloader, we can just load it starting at 2MB+offset rather + * than 0MB + offset. + */ + if (kernel_load_offset < BOOTLOADER_MAX_SIZE) { + kernel_load_offset += 2 * MiB; + } } } -- 2.19.1 From: Richard Henderson <rth@twiddle.net> This can reduce the number of opcodes required for certain complex forms of load-multiple (e.g. ld4.16b). Signed-off-by: Richard Henderson <rth@twiddle.net> Message-id: 20181011205206.3552-2-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) bool is_store = !extract32(insn, 22, 1); bool is_postidx = extract32(insn, 23, 1); bool is_q = extract32(insn, 30, 1); - TCGv_i64 tcg_addr, tcg_rn; + TCGv_i64 tcg_addr, tcg_rn, tcg_ebytes; int ebytes = 1 << size; int elements = (is_q ? 128 : 64) / (8 << size); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) tcg_rn = cpu_reg_sp(s, rn); tcg_addr = tcg_temp_new_i64(); tcg_gen_mov_i64(tcg_addr, tcg_rn); + tcg_ebytes = tcg_const_i64(ebytes); for (r = 0; r < rpt; r++) { int e; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) clear_vec_high(s, is_q, tt); } } - tcg_gen_addi_i64(tcg_addr, tcg_addr, ebytes); + tcg_gen_add_i64(tcg_addr, tcg_addr, tcg_ebytes); tt = (tt + 1) % 32; } } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm)); } } + tcg_temp_free_i64(tcg_ebytes); tcg_temp_free_i64(tcg_addr); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) bool replicate = false; int index = is_q << 3 | S << 2 | size; int ebytes, xs; - TCGv_i64 tcg_addr, tcg_rn; + TCGv_i64 tcg_addr, tcg_rn, tcg_ebytes; switch (scale) { case 3: @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) tcg_rn = cpu_reg_sp(s, rn); tcg_addr = tcg_temp_new_i64(); tcg_gen_mov_i64(tcg_addr, tcg_rn); + tcg_ebytes = tcg_const_i64(ebytes); for (xs = 0; xs < selem; xs++) { if (replicate) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) do_vec_st(s, rt, index, tcg_addr, scale); } } - tcg_gen_addi_i64(tcg_addr, tcg_addr, ebytes); + tcg_gen_add_i64(tcg_addr, tcg_addr, tcg_ebytes); rt = (rt + 1) % 32; } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm)); } } + tcg_temp_free_i64(tcg_ebytes); tcg_temp_free_i64(tcg_addr); } -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> This is done generically in translator_loop. Reported-by: Laurent Desnogues <laurent.desnogues@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20181011205206.3552-3-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 1 - target/arm/translate.c | 1 - 2 files changed, 2 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, static void aarch64_tr_tb_start(DisasContextBase *db, CPUState *cpu) { - tcg_clear_temp_count(); } static void aarch64_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void arm_tr_tb_start(DisasContextBase *dcbase, CPUState *cpu) tcg_gen_movi_i32(tmp, 0); store_cpu_field(tmp, condexec_bits); } - tcg_clear_temp_count(); } static void arm_tr_insn_start(DisasContextBase *dcbase, CPUState *cpu) -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-4-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 28 +++------------------------- 1 file changed, 3 insertions(+), 25 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) for (xs = 0; xs < selem; xs++) { if (replicate) { /* Load and replicate to all elements */ - uint64_t mulconst; TCGv_i64 tcg_tmp = tcg_temp_new_i64(); tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr, get_mem_index(s), s->be_data + scale); - switch (scale) { - case 0: - mulconst = 0x0101010101010101ULL; - break; - case 1: - mulconst = 0x0001000100010001ULL; - break; - case 2: - mulconst = 0x0000000100000001ULL; - break; - case 3: - mulconst = 0; - break; - default: - g_assert_not_reached(); - } - if (mulconst) { - tcg_gen_muli_i64(tcg_tmp, tcg_tmp, mulconst); - } - write_vec_element(s, tcg_tmp, rt, 0, MO_64); - if (is_q) { - write_vec_element(s, tcg_tmp, rt, 1, MO_64); - } + tcg_gen_gvec_dup_i64(scale, vec_full_reg_offset(s, rt), + (is_q + 1) * 8, vec_full_reg_size(s), + tcg_tmp); tcg_temp_free_i64(tcg_tmp); - clear_vec_high(s, is_q, rt); } else { /* Load/store one element per register */ if (is_load) { -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> For a sequence of loads or stores from a single register, little-endian operations can be promoted to an 8-byte op. This can reduce the number of operations by a factor of 8. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-5-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 66 +++++++++++++++++++++++--------------- 1 file changed, 40 insertions(+), 26 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void write_vec_element_i32(DisasContext *s, TCGv_i32 tcg_src, /* Store from vector register to memory */ static void do_vec_st(DisasContext *s, int srcidx, int element, - TCGv_i64 tcg_addr, int size) + TCGv_i64 tcg_addr, int size, TCGMemOp endian) { - TCGMemOp memop = s->be_data + size; TCGv_i64 tcg_tmp = tcg_temp_new_i64(); read_vec_element(s, tcg_tmp, srcidx, element, size); - tcg_gen_qemu_st_i64(tcg_tmp, tcg_addr, get_mem_index(s), memop); + tcg_gen_qemu_st_i64(tcg_tmp, tcg_addr, get_mem_index(s), endian | size); tcg_temp_free_i64(tcg_tmp); } /* Load from memory to vector register */ static void do_vec_ld(DisasContext *s, int destidx, int element, - TCGv_i64 tcg_addr, int size) + TCGv_i64 tcg_addr, int size, TCGMemOp endian) { - TCGMemOp memop = s->be_data + size; TCGv_i64 tcg_tmp = tcg_temp_new_i64(); - tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr, get_mem_index(s), memop); + tcg_gen_qemu_ld_i64(tcg_tmp, tcg_addr, get_mem_index(s), endian | size); write_vec_element(s, tcg_tmp, destidx, element, size); tcg_temp_free_i64(tcg_tmp); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) bool is_postidx = extract32(insn, 23, 1); bool is_q = extract32(insn, 30, 1); TCGv_i64 tcg_addr, tcg_rn, tcg_ebytes; + TCGMemOp endian = s->be_data; - int ebytes = 1 << size; - int elements = (is_q ? 128 : 64) / (8 << size); + int ebytes; /* bytes per element */ + int elements; /* elements per vector */ int rpt; /* num iterations */ int selem; /* structure elements */ int r; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) gen_check_sp_alignment(s); } + /* For our purposes, bytes are always little-endian. */ + if (size == 0) { + endian = MO_LE; + } + + /* Consecutive little-endian elements from a single register + * can be promoted to a larger little-endian operation. + */ + if (selem == 1 && endian == MO_LE) { + size = 3; + } + ebytes = 1 << size; + elements = (is_q ? 16 : 8) / ebytes; + tcg_rn = cpu_reg_sp(s, rn); tcg_addr = tcg_temp_new_i64(); tcg_gen_mov_i64(tcg_addr, tcg_rn); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) for (r = 0; r < rpt; r++) { int e; for (e = 0; e < elements; e++) { - int tt = (rt + r) % 32; int xs; for (xs = 0; xs < selem; xs++) { + int tt = (rt + r + xs) % 32; if (is_store) { - do_vec_st(s, tt, e, tcg_addr, size); + do_vec_st(s, tt, e, tcg_addr, size, endian); } else { - do_vec_ld(s, tt, e, tcg_addr, size); - - /* For non-quad operations, setting a slice of the low - * 64 bits of the register clears the high 64 bits (in - * the ARM ARM pseudocode this is implicit in the fact - * that 'rval' is a 64 bit wide variable). - * For quad operations, we might still need to zero the - * high bits of SVE. We optimize by noticing that we only - * need to do this the first time we touch a register. - */ - if (e == 0 && (r == 0 || xs == selem - 1)) { - clear_vec_high(s, is_q, tt); - } + do_vec_ld(s, tt, e, tcg_addr, size, endian); } tcg_gen_add_i64(tcg_addr, tcg_addr, tcg_ebytes); - tt = (tt + 1) % 32; } } } + if (!is_store) { + /* For non-quad operations, setting a slice of the low + * 64 bits of the register clears the high 64 bits (in + * the ARM ARM pseudocode this is implicit in the fact + * that 'rval' is a 64 bit wide variable). + * For quad operations, we might still need to zero the + * high bits of SVE. + */ + for (r = 0; r < rpt * selem; r++) { + int tt = (rt + r) % 32; + clear_vec_high(s, is_q, tt); + } + } + if (is_postidx) { int rm = extract32(insn, 16, 5); if (rm == 31) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) } else { /* Load/store one element per register */ if (is_load) { - do_vec_ld(s, rt, index, tcg_addr, scale); + do_vec_ld(s, rt, index, tcg_addr, scale, s->be_data); } else { - do_vec_st(s, rt, index, tcg_addr, scale); + do_vec_st(s, rt, index, tcg_addr, scale, s->be_data); } } tcg_gen_add_i64(tcg_addr, tcg_addr, tcg_ebytes); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20181011205206.3552-6-richard.henderson@linaro.org [PMM: drop change to now-deleted cpu_mode_names array] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv_i64 cpu_F0d, cpu_F1d; #include "exec/gen-icount.h" -static const char *regnames[] = +static const char * const regnames[] = { "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r8", "r9", "r10", "r11", "r12", "r13", "r14", "pc" }; @@ -XXX,XX +XXX,XX @@ static struct { int nregs; int interleave; int spacing; -} neon_ls_element_type[11] = { +} const neon_ls_element_type[11] = { {4, 4, 1}, {4, 4, 2}, {4, 1, 1}, -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Also introduces neon_element_offset to find the env offset of a specific element within a neon register. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-7-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 63 ++++++++++++++++++++++++------------------ 1 file changed, 36 insertions(+), 27 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ neon_reg_offset (int reg, int n) return vfp_reg_offset(0, sreg); } +/* Return the offset of a 2**SIZE piece of a NEON register, at index ELE, + * where 0 is the least significant end of the register. + */ +static inline long +neon_element_offset(int reg, int element, TCGMemOp size) +{ + int element_size = 1 << size; + int ofs = element * element_size; +#ifdef HOST_WORDS_BIGENDIAN + /* Calculate the offset assuming fully little-endian, + * then XOR to account for the order of the 8-byte units. + */ + if (element_size < 8) { + ofs ^= 8 - element_size; + } +#endif + return neon_reg_offset(reg, 0) + ofs; +} + static TCGv_i32 neon_load_reg(int reg, int pass) { TCGv_i32 tmp = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static int disas_vfp_insn(DisasContext *s, uint32_t insn) tmp = load_reg(s, rd); if (insn & (1 << 23)) { /* VDUP */ - if (size == 0) { - gen_neon_dup_u8(tmp, 0); - } else if (size == 1) { - gen_neon_dup_low16(tmp); - } - for (n = 0; n <= pass * 2; n++) { - tmp2 = tcg_temp_new_i32(); - tcg_gen_mov_i32(tmp2, tmp); - neon_store_reg(rn, n, tmp2); - } - neon_store_reg(rn, n, tmp); + int vec_size = pass ? 16 : 8; + tcg_gen_gvec_dup_i32(size, neon_reg_offset(rn, 0), + vec_size, vec_size, tmp); + tcg_temp_free_i32(tmp); } else { /* VMOV */ switch (size) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_temp_free_i32(tmp); } else if ((insn & 0x380) == 0) { /* VDUP */ + int element; + TCGMemOp size; + if ((insn & (7 << 16)) == 0 || (q && (rd & 1))) { return 1; } - if (insn & (1 << 19)) { - tmp = neon_load_reg(rm, 1); - } else { - tmp = neon_load_reg(rm, 0); - } if (insn & (1 << 16)) { - gen_neon_dup_u8(tmp, ((insn >> 17) & 3) * 8); + size = MO_8; + element = (insn >> 17) & 7; } else if (insn & (1 << 17)) { - if ((insn >> 18) & 1) - gen_neon_dup_high16(tmp); - else - gen_neon_dup_low16(tmp); + size = MO_16; + element = (insn >> 18) & 3; + } else { + size = MO_32; + element = (insn >> 19) & 1; } - for (pass = 0; pass < (q ? 4 : 2); pass++) { - tmp2 = tcg_temp_new_i32(); - tcg_gen_mov_i32(tmp2, tmp); - neon_store_reg(rd, pass, tmp2); - } - tcg_temp_free_i32(tmp); + tcg_gen_gvec_dup_mem(size, neon_reg_offset(rd, 0), + neon_element_offset(rm, element, size), + q ? 16 : 8, q ? 16 : 8); } else { return 1; } -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-8-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 67 ++++++++++++++++++++++++------------------ 1 file changed, 39 insertions(+), 28 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } } else { /* (insn & 0x00380080) == 0 */ - int invert; + int invert, reg_ofs, vec_size; + if (q && (rd & 1)) { return 1; } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) break; case 14: imm |= (imm << 8) | (imm << 16) | (imm << 24); - if (invert) + if (invert) { imm = ~imm; + } break; case 15: if (invert) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) | ((imm & 0x40) ? (0x1f << 25) : (1 << 30)); break; } - if (invert) + if (invert) { imm = ~imm; + } - for (pass = 0; pass < (q ? 4 : 2); pass++) { - if (op & 1 && op < 12) { - tmp = neon_load_reg(rd, pass); - if (invert) { - /* The immediate value has already been inverted, so - BIC becomes AND. */ - tcg_gen_andi_i32(tmp, tmp, imm); - } else { - tcg_gen_ori_i32(tmp, tmp, imm); - } + reg_ofs = neon_reg_offset(rd, 0); + vec_size = q ? 16 : 8; + + if (op & 1 && op < 12) { + if (invert) { + /* The immediate value has already been inverted, + * so BIC becomes AND. + */ + tcg_gen_gvec_andi(MO_32, reg_ofs, reg_ofs, imm, + vec_size, vec_size); } else { - /* VMOV, VMVN. */ - tmp = tcg_temp_new_i32(); - if (op == 14 && invert) { - int n; - uint32_t val; - val = 0; - for (n = 0; n < 4; n++) { - if (imm & (1 << (n + (pass & 1) * 4))) - val |= 0xff << (n * 8); - } - tcg_gen_movi_i32(tmp, val); - } else { - tcg_gen_movi_i32(tmp, imm); - } + tcg_gen_gvec_ori(MO_32, reg_ofs, reg_ofs, imm, + vec_size, vec_size); + } + } else { + /* VMOV, VMVN. */ + if (op == 14 && invert) { + TCGv_i64 t64 = tcg_temp_new_i64(); + + for (pass = 0; pass <= q; ++pass) { + uint64_t val = 0; + int n; + + for (n = 0; n < 8; n++) { + if (imm & (1 << (n + pass * 8))) { + val |= 0xffull << (n * 8); + } + } + tcg_gen_movi_i64(t64, val); + neon_store_reg64(t64, rd + pass); + } + tcg_temp_free_i64(t64); + } else { + tcg_gen_gvec_dup32i(reg_ofs, vec_size, vec_size, imm); } - neon_store_reg(rd, pass, tmp); } } } else { /* (insn & 0x00800010 == 0x00800000) */ -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Move expanders for VBSL, VBIT, and VBIF from translate-a64.c. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-9-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 6 ++ target/arm/translate-a64.c | 61 -------------- target/arm/translate.c | 162 +++++++++++++++++++++++++++---------- 3 files changed, 124 insertions(+), 105 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 get_ahp_flag(void) return ret; } + +/* Vector operations shared between ARM and AArch64. */ +extern const GVecGen3 bsl_op; +extern const GVecGen3 bit_op; +extern const GVecGen3 bif_op; + /* * Forward to the isar_feature_* tests given a DisasContext pointer. */ 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_three_reg_diff(DisasContext *s, uint32_t insn) } } -static void gen_bsl_i64(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) -{ - tcg_gen_xor_i64(rn, rn, rm); - tcg_gen_and_i64(rn, rn, rd); - tcg_gen_xor_i64(rd, rm, rn); -} - -static void gen_bit_i64(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) -{ - tcg_gen_xor_i64(rn, rn, rd); - tcg_gen_and_i64(rn, rn, rm); - tcg_gen_xor_i64(rd, rd, rn); -} - -static void gen_bif_i64(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) -{ - tcg_gen_xor_i64(rn, rn, rd); - tcg_gen_andc_i64(rn, rn, rm); - tcg_gen_xor_i64(rd, rd, rn); -} - -static void gen_bsl_vec(unsigned vece, TCGv_vec rd, TCGv_vec rn, TCGv_vec rm) -{ - tcg_gen_xor_vec(vece, rn, rn, rm); - tcg_gen_and_vec(vece, rn, rn, rd); - tcg_gen_xor_vec(vece, rd, rm, rn); -} - -static void gen_bit_vec(unsigned vece, TCGv_vec rd, TCGv_vec rn, TCGv_vec rm) -{ - tcg_gen_xor_vec(vece, rn, rn, rd); - tcg_gen_and_vec(vece, rn, rn, rm); - tcg_gen_xor_vec(vece, rd, rd, rn); -} - -static void gen_bif_vec(unsigned vece, TCGv_vec rd, TCGv_vec rn, TCGv_vec rm) -{ - tcg_gen_xor_vec(vece, rn, rn, rd); - tcg_gen_andc_vec(vece, rn, rn, rm); - tcg_gen_xor_vec(vece, rd, rd, rn); -} - /* Logic op (opcode == 3) subgroup of C3.6.16. */ static void disas_simd_3same_logic(DisasContext *s, uint32_t insn) { - static const GVecGen3 bsl_op = { - .fni8 = gen_bsl_i64, - .fniv = gen_bsl_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true - }; - static const GVecGen3 bit_op = { - .fni8 = gen_bit_i64, - .fniv = gen_bit_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true - }; - static const GVecGen3 bif_op = { - .fni8 = gen_bif_i64, - .fniv = gen_bif_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true - }; - int rd = extract32(insn, 0, 5); int rn = extract32(insn, 5, 5); int rm = extract32(insn, 16, 5); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) return 0; } -/* Bitwise select. dest = c ? t : f. Clobbers T and F. */ -static void gen_neon_bsl(TCGv_i32 dest, TCGv_i32 t, TCGv_i32 f, TCGv_i32 c) -{ - tcg_gen_and_i32(t, t, c); - tcg_gen_andc_i32(f, f, c); - tcg_gen_or_i32(dest, t, f); -} - static inline void gen_neon_narrow(int size, TCGv_i32 dest, TCGv_i64 src) { switch (size) { @@ -XXX,XX +XXX,XX @@ static int do_v81_helper(DisasContext *s, gen_helper_gvec_3_ptr *fn, return 1; } +/* + * Expanders for VBitOps_VBIF, VBIT, VBSL. + */ +static void gen_bsl_i64(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) +{ + tcg_gen_xor_i64(rn, rn, rm); + tcg_gen_and_i64(rn, rn, rd); + tcg_gen_xor_i64(rd, rm, rn); +} + +static void gen_bit_i64(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) +{ + tcg_gen_xor_i64(rn, rn, rd); + tcg_gen_and_i64(rn, rn, rm); + tcg_gen_xor_i64(rd, rd, rn); +} + +static void gen_bif_i64(TCGv_i64 rd, TCGv_i64 rn, TCGv_i64 rm) +{ + tcg_gen_xor_i64(rn, rn, rd); + tcg_gen_andc_i64(rn, rn, rm); + tcg_gen_xor_i64(rd, rd, rn); +} + +static void gen_bsl_vec(unsigned vece, TCGv_vec rd, TCGv_vec rn, TCGv_vec rm) +{ + tcg_gen_xor_vec(vece, rn, rn, rm); + tcg_gen_and_vec(vece, rn, rn, rd); + tcg_gen_xor_vec(vece, rd, rm, rn); +} + +static void gen_bit_vec(unsigned vece, TCGv_vec rd, TCGv_vec rn, TCGv_vec rm) +{ + tcg_gen_xor_vec(vece, rn, rn, rd); + tcg_gen_and_vec(vece, rn, rn, rm); + tcg_gen_xor_vec(vece, rd, rd, rn); +} + +static void gen_bif_vec(unsigned vece, TCGv_vec rd, TCGv_vec rn, TCGv_vec rm) +{ + tcg_gen_xor_vec(vece, rn, rn, rd); + tcg_gen_andc_vec(vece, rn, rn, rm); + tcg_gen_xor_vec(vece, rd, rd, rn); +} + +const GVecGen3 bsl_op = { + .fni8 = gen_bsl_i64, + .fniv = gen_bsl_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true +}; + +const GVecGen3 bit_op = { + .fni8 = gen_bit_i64, + .fniv = gen_bit_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true +}; + +const GVecGen3 bif_op = { + .fni8 = gen_bif_i64, + .fniv = gen_bif_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true +}; + + /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. We process data in a mixture of 32-bit and 64-bit chunks. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) { int op; int q; - int rd, rn, rm; + int rd, rn, rm, rd_ofs, rn_ofs, rm_ofs; int size; int shift; int pass; int count; int pairwise; int u; + int vec_size; uint32_t imm, mask; TCGv_i32 tmp, tmp2, tmp3, tmp4, tmp5; TCGv_ptr ptr1, ptr2, ptr3; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) VFP_DREG_N(rn, insn); VFP_DREG_M(rm, insn); size = (insn >> 20) & 3; + vec_size = q ? 16 : 8; + rd_ofs = neon_reg_offset(rd, 0); + rn_ofs = neon_reg_offset(rn, 0); + rm_ofs = neon_reg_offset(rm, 0); + if ((insn & (1 << 23)) == 0) { /* Three register same length. */ op = ((insn >> 7) & 0x1e) | ((insn >> 4) & 1); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) q, rd, rn, rm); } return 1; + + case NEON_3R_LOGIC: /* Logic ops. */ + switch ((u << 2) | size) { + case 0: /* VAND */ + tcg_gen_gvec_and(0, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + break; + case 1: /* VBIC */ + tcg_gen_gvec_andc(0, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + break; + case 2: + if (rn == rm) { + /* VMOV */ + tcg_gen_gvec_mov(0, rd_ofs, rn_ofs, vec_size, vec_size); + } else { + /* VORR */ + tcg_gen_gvec_or(0, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } + break; + case 3: /* VORN */ + tcg_gen_gvec_orc(0, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + break; + case 4: /* VEOR */ + tcg_gen_gvec_xor(0, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + break; + case 5: /* VBSL */ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size, &bsl_op); + break; + case 6: /* VBIT */ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size, &bit_op); + break; + case 7: /* VBIF */ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size, &bif_op); + break; + } + return 0; } - if (size == 3 && op != NEON_3R_LOGIC) { + if (size == 3) { /* 64-bit element instructions. */ for (pass = 0; pass < (q ? 2 : 1); pass++) { neon_load_reg64(cpu_V0, rn + pass); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VRHADD: GEN_NEON_INTEGER_OP(rhadd); break; - case NEON_3R_LOGIC: /* Logic ops. */ - switch ((u << 2) | size) { - case 0: /* VAND */ - tcg_gen_and_i32(tmp, tmp, tmp2); - break; - case 1: /* BIC */ - tcg_gen_andc_i32(tmp, tmp, tmp2); - break; - case 2: /* VORR */ - tcg_gen_or_i32(tmp, tmp, tmp2); - break; - case 3: /* VORN */ - tcg_gen_orc_i32(tmp, tmp, tmp2); - break; - case 4: /* VEOR */ - tcg_gen_xor_i32(tmp, tmp, tmp2); - break; - case 5: /* VBSL */ - tmp3 = neon_load_reg(rd, pass); - gen_neon_bsl(tmp, tmp, tmp2, tmp3); - tcg_temp_free_i32(tmp3); - break; - case 6: /* VBIT */ - tmp3 = neon_load_reg(rd, pass); - gen_neon_bsl(tmp, tmp, tmp3, tmp2); - tcg_temp_free_i32(tmp3); - break; - case 7: /* VBIF */ - tmp3 = neon_load_reg(rd, pass); - gen_neon_bsl(tmp, tmp3, tmp, tmp2); - tcg_temp_free_i32(tmp3); - break; - } - break; case NEON_3R_VHSUB: GEN_NEON_INTEGER_OP(hsub); break; -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-10-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 29 ++++++++++------------------- 1 file changed, 10 insertions(+), 19 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) break; } return 0; + + case NEON_3R_VADD_VSUB: + if (u) { + tcg_gen_gvec_sub(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } else { + tcg_gen_gvec_add(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } + return 0; } if (size == 3) { /* 64-bit element instructions. */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) cpu_V1, cpu_V0); } break; - case NEON_3R_VADD_VSUB: - if (u) { - tcg_gen_sub_i64(CPU_V001); - } else { - tcg_gen_add_i64(CPU_V001); - } - break; default: abort(); } @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = neon_load_reg(rd, pass); gen_neon_add(size, tmp, tmp2); break; - case NEON_3R_VADD_VSUB: - if (!u) { /* VADD */ - gen_neon_add(size, tmp, tmp2); - } else { /* VSUB */ - switch (size) { - case 0: gen_helper_neon_sub_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_sub_u16(tmp, tmp, tmp2); break; - case 2: tcg_gen_sub_i32(tmp, tmp, tmp2); break; - default: abort(); - } - } - break; case NEON_3R_VTST_VCEQ: if (!u) { /* VTST */ switch (size) { -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-11-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_temp_free_ptr(ptr1); tcg_temp_free_ptr(ptr2); break; + + case NEON_2RM_VMVN: + tcg_gen_gvec_not(0, rd_ofs, rm_ofs, vec_size, vec_size); + break; + case NEON_2RM_VNEG: + tcg_gen_gvec_neg(size, rd_ofs, rm_ofs, vec_size, vec_size); + break; + default: elementwise: for (pass = 0; pass < (q ? 4 : 2); pass++) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_2RM_VCNT: gen_helper_neon_cnt_u8(tmp, tmp); break; - case NEON_2RM_VMVN: - tcg_gen_not_i32(tmp, tmp); - break; case NEON_2RM_VQABS: switch (size) { case 0: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) default: abort(); } break; - case NEON_2RM_VNEG: - tmp2 = tcg_const_i32(0); - gen_neon_rsb(size, tmp, tmp2); - tcg_temp_free_i32(tmp2); - break; case NEON_2RM_VCGT0_F: { TCGv_ptr fpstatus = get_fpstatus_ptr(1); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-12-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 31 +++++++++++++++---------------- 1 file changed, 15 insertions(+), 16 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) vec_size, vec_size); } return 0; + + case NEON_3R_VMUL: /* VMUL */ + if (u) { + /* Polynomial case allows only P8 and is handled below. */ + if (size != 0) { + return 1; + } + } else { + tcg_gen_gvec_mul(size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + return 0; + } + break; } if (size == 3) { /* 64-bit element instructions. */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 1; } break; - case NEON_3R_VMUL: - if (u && (size != 0)) { - /* UNDEF on invalid size for polynomial subcase */ - return 1; - } - break; case NEON_3R_VFM_VQRDMLSH: if (!arm_dc_feature(s, ARM_FEATURE_VFP4)) { return 1; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } break; case NEON_3R_VMUL: - if (u) { /* polynomial */ - gen_helper_neon_mul_p8(tmp, tmp, tmp2); - } else { /* Integer */ - switch (size) { - case 0: gen_helper_neon_mul_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_mul_u16(tmp, tmp, tmp2); break; - case 2: tcg_gen_mul_i32(tmp, tmp, tmp2); break; - default: abort(); - } - } + /* VMUL.P8; other cases already eliminated. */ + gen_helper_neon_mul_p8(tmp, tmp, tmp2); break; case NEON_3R_VPMAX: GEN_NEON_INTEGER_OP(pmax); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-13-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 70 +++++++++++++++++++++++++++++------------- 1 file changed, 48 insertions(+), 22 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) size--; } shift = (insn >> 16) & ((1 << (3 + size)) - 1); - /* To avoid excessive duplication of ops we implement shift - by immediate using the variable shift operations. */ if (op < 8) { /* Shift by immediate: VSHR, VSRA, VRSHR, VRSRA, VSRI, VSHL, VQSHL, VQSHLU. */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } /* Right shifts are encoded as N - shift, where N is the element size in bits. */ - if (op <= 4) + if (op <= 4) { shift = shift - (1 << (size + 3)); + } + + switch (op) { + case 0: /* VSHR */ + /* Right shift comes here negative. */ + shift = -shift; + /* Shifts larger than the element size are architecturally + * valid. Unsigned results in all zeros; signed results + * in all sign bits. + */ + if (!u) { + tcg_gen_gvec_sari(size, rd_ofs, rm_ofs, + MIN(shift, (8 << size) - 1), + vec_size, vec_size); + } else if (shift >= 8 << size) { + tcg_gen_gvec_dup8i(rd_ofs, vec_size, vec_size, 0); + } else { + tcg_gen_gvec_shri(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); + } + return 0; + + case 5: /* VSHL, VSLI */ + if (!u) { /* VSHL */ + /* Shifts larger than the element size are + * architecturally valid and results in zero. + */ + if (shift >= 8 << size) { + tcg_gen_gvec_dup8i(rd_ofs, vec_size, vec_size, 0); + } else { + tcg_gen_gvec_shli(size, rd_ofs, rm_ofs, shift, + vec_size, vec_size); + } + return 0; + } + break; + } + if (size == 3) { count = q + 1; } else { count = q ? 4: 2; } - switch (size) { - case 0: - imm = (uint8_t) shift; - imm |= imm << 8; - imm |= imm << 16; - break; - case 1: - imm = (uint16_t) shift; - imm |= imm << 16; - break; - case 2: - case 3: - imm = shift; - break; - default: - abort(); - } + + /* To avoid excessive duplication of ops we implement shift + * by immediate using the variable shift operations. + */ + imm = dup_const(size, shift); for (pass = 0; pass < count; pass++) { if (size == 3) { neon_load_reg64(cpu_V0, rm + pass); tcg_gen_movi_i64(cpu_V1, imm); switch (op) { - case 0: /* VSHR */ case 1: /* VSRA */ if (u) gen_helper_neon_shl_u64(cpu_V0, cpu_V0, cpu_V1); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) cpu_V0, cpu_V1); } break; + default: + g_assert_not_reached(); } if (op == 1 || op == 3) { /* Accumulate. */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp2, imm); switch (op) { - case 0: /* VSHR */ case 1: /* VSRA */ GEN_NEON_INTEGER_OP(shl); break; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 7: /* VQSHL */ GEN_NEON_INTEGER_OP_ENV(qshl); break; + default: + g_assert_not_reached(); } tcg_temp_free_i32(tmp2); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Move ssra_op and usra_op expanders from translate-a64.c. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-14-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 2 + target/arm/translate-a64.c | 106 ---------------------------- target/arm/translate.c | 139 ++++++++++++++++++++++++++++++++++--- 3 files changed, 130 insertions(+), 117 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 get_ahp_flag(void) extern const GVecGen3 bsl_op; extern const GVecGen3 bit_op; extern const GVecGen3 bif_op; +extern const GVecGen2i ssra_op[4]; +extern const GVecGen2i usra_op[4]; /* * Forward to the isar_feature_* tests given a DisasContext pointer. 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_scalar_two_reg_misc(DisasContext *s, uint32_t insn) } } -static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_vec_sar8i_i64(a, a, shift); - tcg_gen_vec_add8_i64(d, d, a); -} - -static void gen_ssra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_vec_sar16i_i64(a, a, shift); - tcg_gen_vec_add16_i64(d, d, a); -} - -static void gen_ssra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) -{ - tcg_gen_sari_i32(a, a, shift); - tcg_gen_add_i32(d, d, a); -} - -static void gen_ssra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_sari_i64(a, a, shift); - tcg_gen_add_i64(d, d, a); -} - -static void gen_ssra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - tcg_gen_sari_vec(vece, a, a, sh); - tcg_gen_add_vec(vece, d, d, a); -} - -static void gen_usra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_vec_shr8i_i64(a, a, shift); - tcg_gen_vec_add8_i64(d, d, a); -} - -static void gen_usra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_vec_shr16i_i64(a, a, shift); - tcg_gen_vec_add16_i64(d, d, a); -} - -static void gen_usra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) -{ - tcg_gen_shri_i32(a, a, shift); - tcg_gen_add_i32(d, d, a); -} - -static void gen_usra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_shri_i64(a, a, shift); - tcg_gen_add_i64(d, d, a); -} - -static void gen_usra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - tcg_gen_shri_vec(vece, a, a, sh); - tcg_gen_add_vec(vece, d, d, a); -} - static void gen_shr8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) { uint64_t mask = dup_const(MO_8, 0xff >> shift); @@ -XXX,XX +XXX,XX @@ static void gen_shr_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, int immh, int immb, int opcode, int rn, int rd) { - static const GVecGen2i ssra_op[4] = { - { .fni8 = gen_ssra8_i64, - .fniv = gen_ssra_vec, - .load_dest = true, - .opc = INDEX_op_sari_vec, - .vece = MO_8 }, - { .fni8 = gen_ssra16_i64, - .fniv = gen_ssra_vec, - .load_dest = true, - .opc = INDEX_op_sari_vec, - .vece = MO_16 }, - { .fni4 = gen_ssra32_i32, - .fniv = gen_ssra_vec, - .load_dest = true, - .opc = INDEX_op_sari_vec, - .vece = MO_32 }, - { .fni8 = gen_ssra64_i64, - .fniv = gen_ssra_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opc = INDEX_op_sari_vec, - .vece = MO_64 }, - }; - static const GVecGen2i usra_op[4] = { - { .fni8 = gen_usra8_i64, - .fniv = gen_usra_vec, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_8, }, - { .fni8 = gen_usra16_i64, - .fniv = gen_usra_vec, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_16, }, - { .fni4 = gen_usra32_i32, - .fniv = gen_usra_vec, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_32, }, - { .fni8 = gen_usra64_i64, - .fniv = gen_usra_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_64, }, - }; static const GVecGen2i sri_op[4] = { { .fni8 = gen_shr8_ins_i64, .fniv = gen_shr_ins_vec, 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 @@ const GVecGen3 bif_op = { .load_dest = true }; +static void gen_ssra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_vec_sar8i_i64(a, a, shift); + tcg_gen_vec_add8_i64(d, d, a); +} + +static void gen_ssra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_vec_sar16i_i64(a, a, shift); + tcg_gen_vec_add16_i64(d, d, a); +} + +static void gen_ssra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) +{ + tcg_gen_sari_i32(a, a, shift); + tcg_gen_add_i32(d, d, a); +} + +static void gen_ssra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_sari_i64(a, a, shift); + tcg_gen_add_i64(d, d, a); +} + +static void gen_ssra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + tcg_gen_sari_vec(vece, a, a, sh); + tcg_gen_add_vec(vece, d, d, a); +} + +const GVecGen2i ssra_op[4] = { + { .fni8 = gen_ssra8_i64, + .fniv = gen_ssra_vec, + .load_dest = true, + .opc = INDEX_op_sari_vec, + .vece = MO_8 }, + { .fni8 = gen_ssra16_i64, + .fniv = gen_ssra_vec, + .load_dest = true, + .opc = INDEX_op_sari_vec, + .vece = MO_16 }, + { .fni4 = gen_ssra32_i32, + .fniv = gen_ssra_vec, + .load_dest = true, + .opc = INDEX_op_sari_vec, + .vece = MO_32 }, + { .fni8 = gen_ssra64_i64, + .fniv = gen_ssra_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opc = INDEX_op_sari_vec, + .vece = MO_64 }, +}; + +static void gen_usra8_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_vec_shr8i_i64(a, a, shift); + tcg_gen_vec_add8_i64(d, d, a); +} + +static void gen_usra16_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_vec_shr16i_i64(a, a, shift); + tcg_gen_vec_add16_i64(d, d, a); +} + +static void gen_usra32_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) +{ + tcg_gen_shri_i32(a, a, shift); + tcg_gen_add_i32(d, d, a); +} + +static void gen_usra64_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_shri_i64(a, a, shift); + tcg_gen_add_i64(d, d, a); +} + +static void gen_usra_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + tcg_gen_shri_vec(vece, a, a, sh); + tcg_gen_add_vec(vece, d, d, a); +} + +const GVecGen2i usra_op[4] = { + { .fni8 = gen_usra8_i64, + .fniv = gen_usra_vec, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_8, }, + { .fni8 = gen_usra16_i64, + .fniv = gen_usra_vec, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_16, }, + { .fni4 = gen_usra32_i32, + .fniv = gen_usra_vec, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_32, }, + { .fni8 = gen_usra64_i64, + .fniv = gen_usra_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_64, }, +}; /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } return 0; + case 1: /* VSRA */ + /* Right shift comes here negative. */ + shift = -shift; + /* Shifts larger than the element size are architecturally + * valid. Unsigned results in all zeros; signed results + * in all sign bits. + */ + if (!u) { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, vec_size, vec_size, + MIN(shift, (8 << size) - 1), + &ssra_op[size]); + } else if (shift >= 8 << size) { + /* rd += 0 */ + } else { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, vec_size, vec_size, + shift, &usra_op[size]); + } + return 0; + case 5: /* VSHL, VSLI */ if (!u) { /* VSHL */ /* Shifts larger than the element size are @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) neon_load_reg64(cpu_V0, rm + pass); tcg_gen_movi_i64(cpu_V1, imm); switch (op) { - case 1: /* VSRA */ - if (u) - gen_helper_neon_shl_u64(cpu_V0, cpu_V0, cpu_V1); - else - gen_helper_neon_shl_s64(cpu_V0, cpu_V0, cpu_V1); - break; case 2: /* VRSHR */ case 3: /* VRSRA */ if (u) @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) default: g_assert_not_reached(); } - if (op == 1 || op == 3) { + if (op == 3) { /* Accumulate. */ neon_load_reg64(cpu_V1, rd + pass); tcg_gen_add_i64(cpu_V0, cpu_V0, cpu_V1); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = tcg_temp_new_i32(); tcg_gen_movi_i32(tmp2, imm); switch (op) { - case 1: /* VSRA */ - GEN_NEON_INTEGER_OP(shl); - break; case 2: /* VRSHR */ case 3: /* VRSRA */ GEN_NEON_INTEGER_OP(rshl); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } tcg_temp_free_i32(tmp2); - if (op == 1 || op == 3) { + if (op == 3) { /* Accumulate. */ tmp2 = neon_load_reg(rd, pass); gen_neon_add(size, tmp, tmp2); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Move shi_op and sli_op expanders from translate-a64.c. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-15-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 2 + target/arm/translate-a64.c | 152 +---------------------- target/arm/translate.c | 244 ++++++++++++++++++++++++++----------- 3 files changed, 179 insertions(+), 219 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ extern const GVecGen3 bit_op; extern const GVecGen3 bif_op; extern const GVecGen2i ssra_op[4]; extern const GVecGen2i usra_op[4]; +extern const GVecGen2i sri_op[4]; +extern const GVecGen2i sli_op[4]; /* * Forward to the isar_feature_* tests given a DisasContext pointer. 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_scalar_two_reg_misc(DisasContext *s, uint32_t insn) } } -static void gen_shr8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - uint64_t mask = dup_const(MO_8, 0xff >> shift); - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shri_i64(t, a, shift); - tcg_gen_andi_i64(t, t, mask); - tcg_gen_andi_i64(d, d, ~mask); - tcg_gen_or_i64(d, d, t); - tcg_temp_free_i64(t); -} - -static void gen_shr16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - uint64_t mask = dup_const(MO_16, 0xffff >> shift); - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shri_i64(t, a, shift); - tcg_gen_andi_i64(t, t, mask); - tcg_gen_andi_i64(d, d, ~mask); - tcg_gen_or_i64(d, d, t); - tcg_temp_free_i64(t); -} - -static void gen_shr32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) -{ - tcg_gen_shri_i32(a, a, shift); - tcg_gen_deposit_i32(d, d, a, 0, 32 - shift); -} - -static void gen_shr64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_shri_i64(a, a, shift); - tcg_gen_deposit_i64(d, d, a, 0, 64 - shift); -} - -static void gen_shr_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - uint64_t mask = (2ull << ((8 << vece) - 1)) - 1; - TCGv_vec t = tcg_temp_new_vec_matching(d); - TCGv_vec m = tcg_temp_new_vec_matching(d); - - tcg_gen_dupi_vec(vece, m, mask ^ (mask >> sh)); - tcg_gen_shri_vec(vece, t, a, sh); - tcg_gen_and_vec(vece, d, d, m); - tcg_gen_or_vec(vece, d, d, t); - - tcg_temp_free_vec(t); - tcg_temp_free_vec(m); -} - /* SSHR[RA]/USHR[RA] - Vector shift right (optional rounding/accumulate) */ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, int immh, int immb, int opcode, int rn, int rd) { - static const GVecGen2i sri_op[4] = { - { .fni8 = gen_shr8_ins_i64, - .fniv = gen_shr_ins_vec, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_8 }, - { .fni8 = gen_shr16_ins_i64, - .fniv = gen_shr_ins_vec, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_16 }, - { .fni4 = gen_shr32_ins_i32, - .fniv = gen_shr_ins_vec, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_32 }, - { .fni8 = gen_shr64_ins_i64, - .fniv = gen_shr_ins_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .opc = INDEX_op_shri_vec, - .vece = MO_64 }, - }; - int size = 32 - clz32(immh) - 1; int immhb = immh << 3 | immb; int shift = 2 * (8 << size) - immhb; @@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shri(DisasContext *s, bool is_q, bool is_u, clear_vec_high(s, is_q, rd); } -static void gen_shl8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - uint64_t mask = dup_const(MO_8, 0xff << shift); - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shli_i64(t, a, shift); - tcg_gen_andi_i64(t, t, mask); - tcg_gen_andi_i64(d, d, ~mask); - tcg_gen_or_i64(d, d, t); - tcg_temp_free_i64(t); -} - -static void gen_shl16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - uint64_t mask = dup_const(MO_16, 0xffff << shift); - TCGv_i64 t = tcg_temp_new_i64(); - - tcg_gen_shli_i64(t, a, shift); - tcg_gen_andi_i64(t, t, mask); - tcg_gen_andi_i64(d, d, ~mask); - tcg_gen_or_i64(d, d, t); - tcg_temp_free_i64(t); -} - -static void gen_shl32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) -{ - tcg_gen_deposit_i32(d, d, a, shift, 32 - shift); -} - -static void gen_shl64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) -{ - tcg_gen_deposit_i64(d, d, a, shift, 64 - shift); -} - -static void gen_shl_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) -{ - uint64_t mask = (1ull << sh) - 1; - TCGv_vec t = tcg_temp_new_vec_matching(d); - TCGv_vec m = tcg_temp_new_vec_matching(d); - - tcg_gen_dupi_vec(vece, m, mask); - tcg_gen_shli_vec(vece, t, a, sh); - tcg_gen_and_vec(vece, d, d, m); - tcg_gen_or_vec(vece, d, d, t); - - tcg_temp_free_vec(t); - tcg_temp_free_vec(m); -} - /* SHL/SLI - Vector shift left */ static void handle_vec_simd_shli(DisasContext *s, bool is_q, bool insert, int immh, int immb, int opcode, int rn, int rd) { - static const GVecGen2i shi_op[4] = { - { .fni8 = gen_shl8_ins_i64, - .fniv = gen_shl_ins_vec, - .opc = INDEX_op_shli_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .vece = MO_8 }, - { .fni8 = gen_shl16_ins_i64, - .fniv = gen_shl_ins_vec, - .opc = INDEX_op_shli_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .vece = MO_16 }, - { .fni4 = gen_shl32_ins_i32, - .fniv = gen_shl_ins_vec, - .opc = INDEX_op_shli_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .vece = MO_32 }, - { .fni8 = gen_shl64_ins_i64, - .fniv = gen_shl_ins_vec, - .opc = INDEX_op_shli_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .vece = MO_64 }, - }; int size = 32 - clz32(immh) - 1; int immhb = immh << 3 | immb; int shift = immhb - (8 << size); @@ -XXX,XX +XXX,XX @@ static void handle_vec_simd_shli(DisasContext *s, bool is_q, bool insert, } if (insert) { - gen_gvec_op2i(s, is_q, rd, rn, shift, &shi_op[size]); + gen_gvec_op2i(s, is_q, rd, rn, shift, &sli_op[size]); } else { gen_gvec_fn2i(s, is_q, rd, rn, shift, tcg_gen_gvec_shli, size); } diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ const GVecGen2i usra_op[4] = { .vece = MO_64, }, }; +static void gen_shr8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + uint64_t mask = dup_const(MO_8, 0xff >> shift); + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shri_i64(t, a, shift); + tcg_gen_andi_i64(t, t, mask); + tcg_gen_andi_i64(d, d, ~mask); + tcg_gen_or_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_shr16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + uint64_t mask = dup_const(MO_16, 0xffff >> shift); + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shri_i64(t, a, shift); + tcg_gen_andi_i64(t, t, mask); + tcg_gen_andi_i64(d, d, ~mask); + tcg_gen_or_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_shr32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) +{ + tcg_gen_shri_i32(a, a, shift); + tcg_gen_deposit_i32(d, d, a, 0, 32 - shift); +} + +static void gen_shr64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_shri_i64(a, a, shift); + tcg_gen_deposit_i64(d, d, a, 0, 64 - shift); +} + +static void gen_shr_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + if (sh == 0) { + tcg_gen_mov_vec(d, a); + } else { + TCGv_vec t = tcg_temp_new_vec_matching(d); + TCGv_vec m = tcg_temp_new_vec_matching(d); + + tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK((8 << vece) - sh, sh)); + tcg_gen_shri_vec(vece, t, a, sh); + tcg_gen_and_vec(vece, d, d, m); + tcg_gen_or_vec(vece, d, d, t); + + tcg_temp_free_vec(t); + tcg_temp_free_vec(m); + } +} + +const GVecGen2i sri_op[4] = { + { .fni8 = gen_shr8_ins_i64, + .fniv = gen_shr_ins_vec, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_8 }, + { .fni8 = gen_shr16_ins_i64, + .fniv = gen_shr_ins_vec, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_16 }, + { .fni4 = gen_shr32_ins_i32, + .fniv = gen_shr_ins_vec, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_32 }, + { .fni8 = gen_shr64_ins_i64, + .fniv = gen_shr_ins_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opc = INDEX_op_shri_vec, + .vece = MO_64 }, +}; + +static void gen_shl8_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + uint64_t mask = dup_const(MO_8, 0xff << shift); + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shli_i64(t, a, shift); + tcg_gen_andi_i64(t, t, mask); + tcg_gen_andi_i64(d, d, ~mask); + tcg_gen_or_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_shl16_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + uint64_t mask = dup_const(MO_16, 0xffff << shift); + TCGv_i64 t = tcg_temp_new_i64(); + + tcg_gen_shli_i64(t, a, shift); + tcg_gen_andi_i64(t, t, mask); + tcg_gen_andi_i64(d, d, ~mask); + tcg_gen_or_i64(d, d, t); + tcg_temp_free_i64(t); +} + +static void gen_shl32_ins_i32(TCGv_i32 d, TCGv_i32 a, int32_t shift) +{ + tcg_gen_deposit_i32(d, d, a, shift, 32 - shift); +} + +static void gen_shl64_ins_i64(TCGv_i64 d, TCGv_i64 a, int64_t shift) +{ + tcg_gen_deposit_i64(d, d, a, shift, 64 - shift); +} + +static void gen_shl_ins_vec(unsigned vece, TCGv_vec d, TCGv_vec a, int64_t sh) +{ + if (sh == 0) { + tcg_gen_mov_vec(d, a); + } else { + TCGv_vec t = tcg_temp_new_vec_matching(d); + TCGv_vec m = tcg_temp_new_vec_matching(d); + + tcg_gen_dupi_vec(vece, m, MAKE_64BIT_MASK(0, sh)); + tcg_gen_shli_vec(vece, t, a, sh); + tcg_gen_and_vec(vece, d, d, m); + tcg_gen_or_vec(vece, d, d, t); + + tcg_temp_free_vec(t); + tcg_temp_free_vec(m); + } +} + +const GVecGen2i sli_op[4] = { + { .fni8 = gen_shl8_ins_i64, + .fniv = gen_shl_ins_vec, + .load_dest = true, + .opc = INDEX_op_shli_vec, + .vece = MO_8 }, + { .fni8 = gen_shl16_ins_i64, + .fniv = gen_shl_ins_vec, + .load_dest = true, + .opc = INDEX_op_shli_vec, + .vece = MO_16 }, + { .fni4 = gen_shl32_ins_i32, + .fniv = gen_shl_ins_vec, + .load_dest = true, + .opc = INDEX_op_shli_vec, + .vece = MO_32 }, + { .fni8 = gen_shl64_ins_i64, + .fniv = gen_shl_ins_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .opc = INDEX_op_shli_vec, + .vece = MO_64 }, +}; + /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. We process data in a mixture of 32-bit and 64-bit chunks. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) int pairwise; int u; int vec_size; - uint32_t imm, mask; + uint32_t imm; TCGv_i32 tmp, tmp2, tmp3, tmp4, tmp5; TCGv_ptr ptr1, ptr2, ptr3; TCGv_i64 tmp64; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } return 0; + case 4: /* VSRI */ + if (!u) { + return 1; + } + /* Right shift comes here negative. */ + shift = -shift; + /* Shift out of range leaves destination unchanged. */ + if (shift < 8 << size) { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, vec_size, vec_size, + shift, &sri_op[size]); + } + return 0; + case 5: /* VSHL, VSLI */ - if (!u) { /* VSHL */ + if (u) { /* VSLI */ + /* Shift out of range leaves destination unchanged. */ + if (shift < 8 << size) { + tcg_gen_gvec_2i(rd_ofs, rm_ofs, vec_size, + vec_size, shift, &sli_op[size]); + } + } else { /* VSHL */ /* Shifts larger than the element size are * architecturally valid and results in zero. */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_gen_gvec_shli(size, rd_ofs, rm_ofs, shift, vec_size, vec_size); } - return 0; } - break; + return 0; } if (size == 3) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) else gen_helper_neon_rshl_s64(cpu_V0, cpu_V0, cpu_V1); break; - case 4: /* VSRI */ - case 5: /* VSHL, VSLI */ - gen_helper_neon_shl_u64(cpu_V0, cpu_V0, cpu_V1); - break; case 6: /* VQSHLU */ gen_helper_neon_qshlu_s64(cpu_V0, cpu_env, cpu_V0, cpu_V1); @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) /* Accumulate. */ neon_load_reg64(cpu_V1, rd + pass); tcg_gen_add_i64(cpu_V0, cpu_V0, cpu_V1); - } else if (op == 4 || (op == 5 && u)) { - /* Insert */ - neon_load_reg64(cpu_V1, rd + pass); - uint64_t mask; - if (shift < -63 || shift > 63) { - mask = 0; - } else { - if (op == 4) { - mask = 0xffffffffffffffffull >> -shift; - } else { - mask = 0xffffffffffffffffull << shift; - } - } - tcg_gen_andi_i64(cpu_V1, cpu_V1, ~mask); - tcg_gen_or_i64(cpu_V0, cpu_V0, cpu_V1); } neon_store_reg64(cpu_V0, rd + pass); } else { /* size < 3 */ @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case 3: /* VRSRA */ GEN_NEON_INTEGER_OP(rshl); break; - case 4: /* VSRI */ - case 5: /* VSHL, VSLI */ - switch (size) { - case 0: gen_helper_neon_shl_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_shl_u16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_shl_u32(tmp, tmp, tmp2); break; - default: abort(); - } - break; case 6: /* VQSHLU */ switch (size) { case 0: @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = neon_load_reg(rd, pass); gen_neon_add(size, tmp, tmp2); tcg_temp_free_i32(tmp2); - } else if (op == 4 || (op == 5 && u)) { - /* Insert */ - switch (size) { - case 0: - if (op == 4) - mask = 0xff >> -shift; - else - mask = (uint8_t)(0xff << shift); - mask |= mask << 8; - mask |= mask << 16; - break; - case 1: - if (op == 4) - mask = 0xffff >> -shift; - else - mask = (uint16_t)(0xffff << shift); - mask |= mask << 16; - break; - case 2: - if (shift < -31 || shift > 31) { - mask = 0; - } else { - if (op == 4) - mask = 0xffffffffu >> -shift; - else - mask = 0xffffffffu << shift; - } - break; - default: - abort(); - } - tmp2 = neon_load_reg(rd, pass); - tcg_gen_andi_i32(tmp, tmp, mask); - tcg_gen_andi_i32(tmp2, tmp2, ~mask); - tcg_gen_or_i32(tmp, tmp, tmp2); - tcg_temp_free_i32(tmp2); } neon_store_reg(rd, pass, tmp); } -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Move mla_op and mls_op expanders from translate-a64.c. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-16-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 2 + target/arm/translate-a64.c | 106 ----------------------------- target/arm/translate.c | 134 ++++++++++++++++++++++++++++++++----- 3 files changed, 120 insertions(+), 122 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline TCGv_i32 get_ahp_flag(void) extern const GVecGen3 bsl_op; extern const GVecGen3 bit_op; extern const GVecGen3 bif_op; +extern const GVecGen3 mla_op[4]; +extern const GVecGen3 mls_op[4]; extern const GVecGen2i ssra_op[4]; extern const GVecGen2i usra_op[4]; extern const GVecGen2i sri_op[4]; 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_3same_float(DisasContext *s, uint32_t insn) } } -static void gen_mla8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - gen_helper_neon_mul_u8(a, a, b); - gen_helper_neon_add_u8(d, d, a); -} - -static void gen_mla16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - gen_helper_neon_mul_u16(a, a, b); - gen_helper_neon_add_u16(d, d, a); -} - -static void gen_mla32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - tcg_gen_mul_i32(a, a, b); - tcg_gen_add_i32(d, d, a); -} - -static void gen_mla64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) -{ - tcg_gen_mul_i64(a, a, b); - tcg_gen_add_i64(d, d, a); -} - -static void gen_mla_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) -{ - tcg_gen_mul_vec(vece, a, a, b); - tcg_gen_add_vec(vece, d, d, a); -} - -static void gen_mls8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - gen_helper_neon_mul_u8(a, a, b); - gen_helper_neon_sub_u8(d, d, a); -} - -static void gen_mls16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - gen_helper_neon_mul_u16(a, a, b); - gen_helper_neon_sub_u16(d, d, a); -} - -static void gen_mls32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - tcg_gen_mul_i32(a, a, b); - tcg_gen_sub_i32(d, d, a); -} - -static void gen_mls64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) -{ - tcg_gen_mul_i64(a, a, b); - tcg_gen_sub_i64(d, d, a); -} - -static void gen_mls_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) -{ - tcg_gen_mul_vec(vece, a, a, b); - tcg_gen_sub_vec(vece, d, d, a); -} - /* Integer op subgroup of C3.6.16. */ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) .prefer_i64 = TCG_TARGET_REG_BITS == 64, .vece = MO_64 }, }; - static const GVecGen3 mla_op[4] = { - { .fni4 = gen_mla8_i32, - .fniv = gen_mla_vec, - .opc = INDEX_op_mul_vec, - .load_dest = true, - .vece = MO_8 }, - { .fni4 = gen_mla16_i32, - .fniv = gen_mla_vec, - .opc = INDEX_op_mul_vec, - .load_dest = true, - .vece = MO_16 }, - { .fni4 = gen_mla32_i32, - .fniv = gen_mla_vec, - .opc = INDEX_op_mul_vec, - .load_dest = true, - .vece = MO_32 }, - { .fni8 = gen_mla64_i64, - .fniv = gen_mla_vec, - .opc = INDEX_op_mul_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .vece = MO_64 }, - }; - static const GVecGen3 mls_op[4] = { - { .fni4 = gen_mls8_i32, - .fniv = gen_mls_vec, - .opc = INDEX_op_mul_vec, - .load_dest = true, - .vece = MO_8 }, - { .fni4 = gen_mls16_i32, - .fniv = gen_mls_vec, - .opc = INDEX_op_mul_vec, - .load_dest = true, - .vece = MO_16 }, - { .fni4 = gen_mls32_i32, - .fniv = gen_mls_vec, - .opc = INDEX_op_mul_vec, - .load_dest = true, - .vece = MO_32 }, - { .fni8 = gen_mls64_i64, - .fniv = gen_mls_vec, - .opc = INDEX_op_mul_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .load_dest = true, - .vece = MO_64 }, - }; int is_q = extract32(insn, 30, 1); int u = extract32(insn, 29, 1); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_neon_narrow_op(int op, int u, int size, #define NEON_3R_VABA 15 #define NEON_3R_VADD_VSUB 16 #define NEON_3R_VTST_VCEQ 17 -#define NEON_3R_VML 18 /* VMLA, VMLAL, VMLS, VMLSL */ +#define NEON_3R_VML 18 /* VMLA, VMLS */ #define NEON_3R_VMUL 19 #define NEON_3R_VPMAX 20 #define NEON_3R_VPMIN 21 @@ -XXX,XX +XXX,XX @@ const GVecGen2i sli_op[4] = { .vece = MO_64 }, }; +static void gen_mla8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + gen_helper_neon_mul_u8(a, a, b); + gen_helper_neon_add_u8(d, d, a); +} + +static void gen_mls8_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + gen_helper_neon_mul_u8(a, a, b); + gen_helper_neon_sub_u8(d, d, a); +} + +static void gen_mla16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + gen_helper_neon_mul_u16(a, a, b); + gen_helper_neon_add_u16(d, d, a); +} + +static void gen_mls16_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + gen_helper_neon_mul_u16(a, a, b); + gen_helper_neon_sub_u16(d, d, a); +} + +static void gen_mla32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + tcg_gen_mul_i32(a, a, b); + tcg_gen_add_i32(d, d, a); +} + +static void gen_mls32_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + tcg_gen_mul_i32(a, a, b); + tcg_gen_sub_i32(d, d, a); +} + +static void gen_mla64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + tcg_gen_mul_i64(a, a, b); + tcg_gen_add_i64(d, d, a); +} + +static void gen_mls64_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + tcg_gen_mul_i64(a, a, b); + tcg_gen_sub_i64(d, d, a); +} + +static void gen_mla_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + tcg_gen_mul_vec(vece, a, a, b); + tcg_gen_add_vec(vece, d, d, a); +} + +static void gen_mls_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + tcg_gen_mul_vec(vece, a, a, b); + tcg_gen_sub_vec(vece, d, d, a); +} + +/* Note that while NEON does not support VMLA and VMLS as 64-bit ops, + * these tables are shared with AArch64 which does support them. + */ +const GVecGen3 mla_op[4] = { + { .fni4 = gen_mla8_i32, + .fniv = gen_mla_vec, + .opc = INDEX_op_mul_vec, + .load_dest = true, + .vece = MO_8 }, + { .fni4 = gen_mla16_i32, + .fniv = gen_mla_vec, + .opc = INDEX_op_mul_vec, + .load_dest = true, + .vece = MO_16 }, + { .fni4 = gen_mla32_i32, + .fniv = gen_mla_vec, + .opc = INDEX_op_mul_vec, + .load_dest = true, + .vece = MO_32 }, + { .fni8 = gen_mla64_i64, + .fniv = gen_mla_vec, + .opc = INDEX_op_mul_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .vece = MO_64 }, +}; + +const GVecGen3 mls_op[4] = { + { .fni4 = gen_mls8_i32, + .fniv = gen_mls_vec, + .opc = INDEX_op_mul_vec, + .load_dest = true, + .vece = MO_8 }, + { .fni4 = gen_mls16_i32, + .fniv = gen_mls_vec, + .opc = INDEX_op_mul_vec, + .load_dest = true, + .vece = MO_16 }, + { .fni4 = gen_mls32_i32, + .fniv = gen_mls_vec, + .opc = INDEX_op_mul_vec, + .load_dest = true, + .vece = MO_32 }, + { .fni8 = gen_mls64_i64, + .fniv = gen_mls_vec, + .opc = INDEX_op_mul_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .load_dest = true, + .vece = MO_64 }, +}; + /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. We process data in a mixture of 32-bit and 64-bit chunks. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) return 0; } break; + + case NEON_3R_VML: /* VMLA, VMLS */ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size, + u ? &mls_op[size] : &mla_op[size]); + return 0; } + if (size == 3) { /* 64-bit element instructions. */ for (pass = 0; pass < (q ? 2 : 1); pass++) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) } } break; - case NEON_3R_VML: /* VMLA, VMLAL, VMLS,VMLSL */ - switch (size) { - case 0: gen_helper_neon_mul_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_mul_u16(tmp, tmp, tmp2); break; - case 2: tcg_gen_mul_i32(tmp, tmp, tmp2); break; - default: abort(); - } - tcg_temp_free_i32(tmp2); - tmp2 = neon_load_reg(rd, pass); - if (u) { /* VMLS */ - gen_neon_rsb(size, tmp, tmp2); - } else { /* VMLA */ - gen_neon_add(size, tmp, tmp2); - } - break; case NEON_3R_VMUL: /* VMUL.P8; other cases already eliminated. */ gen_helper_neon_mul_p8(tmp, tmp, tmp2); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Move cmtst_op expanders from translate-a64.c. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-17-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 2 + target/arm/translate-a64.c | 38 ------------------ target/arm/translate.c | 81 +++++++++++++++++++++++++++----------- 3 files changed, 60 insertions(+), 61 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ extern const GVecGen3 bit_op; extern const GVecGen3 bif_op; extern const GVecGen3 mla_op[4]; extern const GVecGen3 mls_op[4]; +extern const GVecGen3 cmtst_op[4]; extern const GVecGen2i ssra_op[4]; extern const GVecGen2i usra_op[4]; extern const GVecGen2i sri_op[4]; extern const GVecGen2i sli_op[4]; +void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b); /* * Forward to the isar_feature_* tests given a DisasContext pointer. 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_scalar_three_reg_diff(DisasContext *s, uint32_t insn) } } -/* CMTST : test is "if (X & Y != 0)". */ -static void gen_cmtst_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) -{ - tcg_gen_and_i32(d, a, b); - tcg_gen_setcondi_i32(TCG_COND_NE, d, d, 0); - tcg_gen_neg_i32(d, d); -} - -static void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) -{ - tcg_gen_and_i64(d, a, b); - tcg_gen_setcondi_i64(TCG_COND_NE, d, d, 0); - tcg_gen_neg_i64(d, d); -} - -static void gen_cmtst_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) -{ - tcg_gen_and_vec(vece, d, a, b); - tcg_gen_dupi_vec(vece, a, 0); - tcg_gen_cmp_vec(TCG_COND_NE, vece, d, d, a); -} - static void handle_3same_64(DisasContext *s, int opcode, bool u, TCGv_i64 tcg_rd, TCGv_i64 tcg_rn, TCGv_i64 tcg_rm) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_3same_float(DisasContext *s, uint32_t insn) /* Integer op subgroup of C3.6.16. */ static void disas_simd_3same_int(DisasContext *s, uint32_t insn) { - static const GVecGen3 cmtst_op[4] = { - { .fni4 = gen_helper_neon_tst_u8, - .fniv = gen_cmtst_vec, - .vece = MO_8 }, - { .fni4 = gen_helper_neon_tst_u16, - .fniv = gen_cmtst_vec, - .vece = MO_16 }, - { .fni4 = gen_cmtst_i32, - .fniv = gen_cmtst_vec, - .vece = MO_32 }, - { .fni8 = gen_cmtst_i64, - .fniv = gen_cmtst_vec, - .prefer_i64 = TCG_TARGET_REG_BITS == 64, - .vece = MO_64 }, - }; - int is_q = extract32(insn, 30, 1); int u = extract32(insn, 29, 1); int size = extract32(insn, 22, 2); 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 @@ const GVecGen3 mls_op[4] = { .vece = MO_64 }, }; +/* CMTST : test is "if (X & Y != 0)". */ +static void gen_cmtst_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b) +{ + tcg_gen_and_i32(d, a, b); + tcg_gen_setcondi_i32(TCG_COND_NE, d, d, 0); + tcg_gen_neg_i32(d, d); +} + +void gen_cmtst_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b) +{ + tcg_gen_and_i64(d, a, b); + tcg_gen_setcondi_i64(TCG_COND_NE, d, d, 0); + tcg_gen_neg_i64(d, d); +} + +static void gen_cmtst_vec(unsigned vece, TCGv_vec d, TCGv_vec a, TCGv_vec b) +{ + tcg_gen_and_vec(vece, d, a, b); + tcg_gen_dupi_vec(vece, a, 0); + tcg_gen_cmp_vec(TCG_COND_NE, vece, d, d, a); +} + +const GVecGen3 cmtst_op[4] = { + { .fni4 = gen_helper_neon_tst_u8, + .fniv = gen_cmtst_vec, + .vece = MO_8 }, + { .fni4 = gen_helper_neon_tst_u16, + .fniv = gen_cmtst_vec, + .vece = MO_16 }, + { .fni4 = gen_cmtst_i32, + .fniv = gen_cmtst_vec, + .vece = MO_32 }, + { .fni8 = gen_cmtst_i64, + .fniv = gen_cmtst_vec, + .prefer_i64 = TCG_TARGET_REG_BITS == 64, + .vece = MO_64 }, +}; + /* Translate a NEON data processing instruction. Return nonzero if the instruction is invalid. We process data in a mixture of 32-bit and 64-bit chunks. @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size, u ? &mls_op[size] : &mla_op[size]); return 0; + + case NEON_3R_VTST_VCEQ: + if (u) { /* VCEQ */ + tcg_gen_gvec_cmp(TCG_COND_EQ, size, rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size); + } else { /* VTST */ + tcg_gen_gvec_3(rd_ofs, rn_ofs, rm_ofs, + vec_size, vec_size, &cmtst_op[size]); + } + return 0; + + case NEON_3R_VCGT: + tcg_gen_gvec_cmp(u ? TCG_COND_GTU : TCG_COND_GT, size, + rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); + return 0; + + case NEON_3R_VCGE: + tcg_gen_gvec_cmp(u ? TCG_COND_GEU : TCG_COND_GE, size, + rd_ofs, rn_ofs, rm_ofs, vec_size, vec_size); + return 0; } if (size == 3) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) case NEON_3R_VQSUB: GEN_NEON_INTEGER_OP_ENV(qsub); break; - case NEON_3R_VCGT: - GEN_NEON_INTEGER_OP(cgt); - break; - case NEON_3R_VCGE: - GEN_NEON_INTEGER_OP(cge); - break; case NEON_3R_VSHL: GEN_NEON_INTEGER_OP(shl); break; @@ -XXX,XX +XXX,XX @@ static int disas_neon_data_insn(DisasContext *s, uint32_t insn) tmp2 = neon_load_reg(rd, pass); gen_neon_add(size, tmp, tmp2); break; - case NEON_3R_VTST_VCEQ: - if (!u) { /* VTST */ - switch (size) { - case 0: gen_helper_neon_tst_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_tst_u16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_tst_u32(tmp, tmp, tmp2); break; - default: abort(); - } - } else { /* VCEQ */ - switch (size) { - case 0: gen_helper_neon_ceq_u8(tmp, tmp, tmp2); break; - case 1: gen_helper_neon_ceq_u16(tmp, tmp, tmp2); break; - case 2: gen_helper_neon_ceq_u32(tmp, tmp, tmp2); break; - default: abort(); - } - } - break; case NEON_3R_VMUL: /* VMUL.P8; other cases already eliminated. */ gen_helper_neon_mul_p8(tmp, tmp, tmp2); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-18-richard.henderson@linaro.org [PMM: added parens in ?: expression] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 81 ++++++++++++++---------------------------- 1 file changed, 26 insertions(+), 55 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void gen_vfp_msr(TCGv_i32 tmp) tcg_temp_free_i32(tmp); } -static void gen_neon_dup_u8(TCGv_i32 var, int shift) -{ - TCGv_i32 tmp = tcg_temp_new_i32(); - if (shift) - tcg_gen_shri_i32(var, var, shift); - tcg_gen_ext8u_i32(var, var); - tcg_gen_shli_i32(tmp, var, 8); - tcg_gen_or_i32(var, var, tmp); - tcg_gen_shli_i32(tmp, var, 16); - tcg_gen_or_i32(var, var, tmp); - tcg_temp_free_i32(tmp); -} - static void gen_neon_dup_low16(TCGv_i32 var) { TCGv_i32 tmp = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static void gen_neon_dup_high16(TCGv_i32 var) tcg_temp_free_i32(tmp); } -static TCGv_i32 gen_load_and_replicate(DisasContext *s, TCGv_i32 addr, int size) -{ - /* Load a single Neon element and replicate into a 32 bit TCG reg */ - TCGv_i32 tmp = tcg_temp_new_i32(); - switch (size) { - case 0: - gen_aa32_ld8u(s, tmp, addr, get_mem_index(s)); - gen_neon_dup_u8(tmp, 0); - break; - case 1: - gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); - gen_neon_dup_low16(tmp); - break; - case 2: - gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); - break; - default: /* Avoid compiler warnings. */ - abort(); - } - return tmp; -} - static int handle_vsel(uint32_t insn, uint32_t rd, uint32_t rn, uint32_t rm, uint32_t dp) { @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) int load; int shift; int n; + int vec_size; TCGv_i32 addr; TCGv_i32 tmp; TCGv_i32 tmp2; @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) } addr = tcg_temp_new_i32(); load_reg_var(s, addr, rn); - if (nregs == 1) { - /* VLD1 to all lanes: bit 5 indicates how many Dregs to write */ - tmp = gen_load_and_replicate(s, addr, size); - tcg_gen_st_i32(tmp, cpu_env, neon_reg_offset(rd, 0)); - tcg_gen_st_i32(tmp, cpu_env, neon_reg_offset(rd, 1)); - if (insn & (1 << 5)) { - tcg_gen_st_i32(tmp, cpu_env, neon_reg_offset(rd + 1, 0)); - tcg_gen_st_i32(tmp, cpu_env, neon_reg_offset(rd + 1, 1)); - } - tcg_temp_free_i32(tmp); - } else { - /* VLD2/3/4 to all lanes: bit 5 indicates register stride */ - stride = (insn & (1 << 5)) ? 2 : 1; - for (reg = 0; reg < nregs; reg++) { - tmp = gen_load_and_replicate(s, addr, size); - tcg_gen_st_i32(tmp, cpu_env, neon_reg_offset(rd, 0)); - tcg_gen_st_i32(tmp, cpu_env, neon_reg_offset(rd, 1)); - tcg_temp_free_i32(tmp); - tcg_gen_addi_i32(addr, addr, 1 << size); - rd += stride; + + /* VLD1 to all lanes: bit 5 indicates how many Dregs to write. + * VLD2/3/4 to all lanes: bit 5 indicates register stride. + */ + stride = (insn & (1 << 5)) ? 2 : 1; + vec_size = nregs == 1 ? stride * 8 : 8; + + tmp = tcg_temp_new_i32(); + for (reg = 0; reg < nregs; reg++) { + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), + s->be_data | size); + if ((rd & 1) && vec_size == 16) { + /* We cannot write 16 bytes at once because the + * destination is unaligned. + */ + tcg_gen_gvec_dup_i32(size, neon_reg_offset(rd, 0), + 8, 8, tmp); + tcg_gen_gvec_mov(0, neon_reg_offset(rd + 1, 0), + neon_reg_offset(rd, 0), 8, 8); + } else { + tcg_gen_gvec_dup_i32(size, neon_reg_offset(rd, 0), + vec_size, vec_size, tmp); } + tcg_gen_addi_i32(addr, addr, 1 << size); + rd += stride; } + tcg_temp_free_i32(tmp); tcg_temp_free_i32(addr); stride = (1 << size) * nregs; } else { -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Instead of shifts and masks, use direct loads and stores from the neon register file. Mirror the iteration structure of the ARM pseudocode more closely. Correct the parameters of the VLD2 A2 insn. Note that this includes a bugfix for handling of the insn "VLD2 (multiple 2-element structures)" -- we were using an incorrect stride value. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-19-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 170 ++++++++++++++++++----------------------- 1 file changed, 74 insertions(+), 96 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv_i32 neon_load_reg(int reg, int pass) return tmp; } +static void neon_load_element64(TCGv_i64 var, int reg, int ele, TCGMemOp mop) +{ + long offset = neon_element_offset(reg, ele, mop & MO_SIZE); + + switch (mop) { + case MO_UB: + tcg_gen_ld8u_i64(var, cpu_env, offset); + break; + case MO_UW: + tcg_gen_ld16u_i64(var, cpu_env, offset); + break; + case MO_UL: + tcg_gen_ld32u_i64(var, cpu_env, offset); + break; + case MO_Q: + tcg_gen_ld_i64(var, cpu_env, offset); + break; + default: + g_assert_not_reached(); + } +} + static void neon_store_reg(int reg, int pass, TCGv_i32 var) { tcg_gen_st_i32(var, cpu_env, neon_reg_offset(reg, pass)); tcg_temp_free_i32(var); } +static void neon_store_element64(int reg, int ele, TCGMemOp size, TCGv_i64 var) +{ + long offset = neon_element_offset(reg, ele, size); + + switch (size) { + case MO_8: + tcg_gen_st8_i64(var, cpu_env, offset); + break; + case MO_16: + tcg_gen_st16_i64(var, cpu_env, offset); + break; + case MO_32: + tcg_gen_st32_i64(var, cpu_env, offset); + break; + case MO_64: + tcg_gen_st_i64(var, cpu_env, offset); + break; + default: + g_assert_not_reached(); + } +} + static inline void neon_load_reg64(TCGv_i64 var, int reg) { tcg_gen_ld_i64(var, cpu_env, vfp_reg_offset(1, reg)); @@ -XXX,XX +XXX,XX @@ static struct { int interleave; int spacing; } const neon_ls_element_type[11] = { - {4, 4, 1}, - {4, 4, 2}, + {1, 4, 1}, + {1, 4, 2}, {4, 1, 1}, - {4, 2, 1}, - {3, 3, 1}, - {3, 3, 2}, + {2, 2, 2}, + {1, 3, 1}, + {1, 3, 2}, {3, 1, 1}, {1, 1, 1}, - {2, 2, 1}, - {2, 2, 2}, + {1, 2, 1}, + {1, 2, 2}, {2, 1, 1} }; @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) int shift; int n; int vec_size; + int mmu_idx; + TCGMemOp endian; TCGv_i32 addr; TCGv_i32 tmp; TCGv_i32 tmp2; @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) rn = (insn >> 16) & 0xf; rm = insn & 0xf; load = (insn & (1 << 21)) != 0; + endian = s->be_data; + mmu_idx = get_mem_index(s); if ((insn & (1 << 23)) == 0) { /* Load store all elements. */ op = (insn >> 8) & 0xf; @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) nregs = neon_ls_element_type[op].nregs; interleave = neon_ls_element_type[op].interleave; spacing = neon_ls_element_type[op].spacing; - if (size == 3 && (interleave | spacing) != 1) + if (size == 3 && (interleave | spacing) != 1) { return 1; + } + tmp64 = tcg_temp_new_i64(); addr = tcg_temp_new_i32(); + tmp2 = tcg_const_i32(1 << size); load_reg_var(s, addr, rn); - stride = (1 << size) * interleave; for (reg = 0; reg < nregs; reg++) { - if (interleave > 2 || (interleave == 2 && nregs == 2)) { - load_reg_var(s, addr, rn); - tcg_gen_addi_i32(addr, addr, (1 << size) * reg); - } else if (interleave == 2 && nregs == 4 && reg == 2) { - load_reg_var(s, addr, rn); - tcg_gen_addi_i32(addr, addr, 1 << size); - } - if (size == 3) { - tmp64 = tcg_temp_new_i64(); - if (load) { - gen_aa32_ld64(s, tmp64, addr, get_mem_index(s)); - neon_store_reg64(tmp64, rd); - } else { - neon_load_reg64(tmp64, rd); - gen_aa32_st64(s, tmp64, addr, get_mem_index(s)); - } - tcg_temp_free_i64(tmp64); - tcg_gen_addi_i32(addr, addr, stride); - } else { - for (pass = 0; pass < 2; pass++) { - if (size == 2) { - if (load) { - tmp = tcg_temp_new_i32(); - gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); - neon_store_reg(rd, pass, tmp); - } else { - tmp = neon_load_reg(rd, pass); - gen_aa32_st32(s, tmp, addr, get_mem_index(s)); - tcg_temp_free_i32(tmp); - } - tcg_gen_addi_i32(addr, addr, stride); - } else if (size == 1) { - if (load) { - tmp = tcg_temp_new_i32(); - gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); - tcg_gen_addi_i32(addr, addr, stride); - tmp2 = tcg_temp_new_i32(); - gen_aa32_ld16u(s, tmp2, addr, get_mem_index(s)); - tcg_gen_addi_i32(addr, addr, stride); - tcg_gen_shli_i32(tmp2, tmp2, 16); - tcg_gen_or_i32(tmp, tmp, tmp2); - tcg_temp_free_i32(tmp2); - neon_store_reg(rd, pass, tmp); - } else { - tmp = neon_load_reg(rd, pass); - tmp2 = tcg_temp_new_i32(); - tcg_gen_shri_i32(tmp2, tmp, 16); - gen_aa32_st16(s, tmp, addr, get_mem_index(s)); - tcg_temp_free_i32(tmp); - tcg_gen_addi_i32(addr, addr, stride); - gen_aa32_st16(s, tmp2, addr, get_mem_index(s)); - tcg_temp_free_i32(tmp2); - tcg_gen_addi_i32(addr, addr, stride); - } - } else /* size == 0 */ { - if (load) { - tmp2 = NULL; - for (n = 0; n < 4; n++) { - tmp = tcg_temp_new_i32(); - gen_aa32_ld8u(s, tmp, addr, get_mem_index(s)); - tcg_gen_addi_i32(addr, addr, stride); - if (n == 0) { - tmp2 = tmp; - } else { - tcg_gen_shli_i32(tmp, tmp, n * 8); - tcg_gen_or_i32(tmp2, tmp2, tmp); - tcg_temp_free_i32(tmp); - } - } - neon_store_reg(rd, pass, tmp2); - } else { - tmp2 = neon_load_reg(rd, pass); - for (n = 0; n < 4; n++) { - tmp = tcg_temp_new_i32(); - if (n == 0) { - tcg_gen_mov_i32(tmp, tmp2); - } else { - tcg_gen_shri_i32(tmp, tmp2, n * 8); - } - gen_aa32_st8(s, tmp, addr, get_mem_index(s)); - tcg_temp_free_i32(tmp); - tcg_gen_addi_i32(addr, addr, stride); - } - tcg_temp_free_i32(tmp2); - } + for (n = 0; n < 8 >> size; n++) { + int xs; + for (xs = 0; xs < interleave; xs++) { + int tt = rd + reg + spacing * xs; + + if (load) { + gen_aa32_ld_i64(s, tmp64, addr, mmu_idx, endian | size); + neon_store_element64(tt, n, size, tmp64); + } else { + neon_load_element64(tmp64, tt, n, size); + gen_aa32_st_i64(s, tmp64, addr, mmu_idx, endian | size); } + tcg_gen_add_i32(addr, addr, tmp2); } } - rd += spacing; } tcg_temp_free_i32(addr); - stride = nregs * 8; + tcg_temp_free_i32(tmp2); + tcg_temp_free_i64(tmp64); + stride = nregs * interleave * 8; } else { size = (insn >> 10) & 3; if (size == 3) { -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> For a sequence of loads or stores from a single register, little-endian operations can be promoted to an 8-byte op. This can reduce the number of operations by a factor of 8. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-20-richard.henderson@linaro.org Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) if (size == 3 && (interleave | spacing) != 1) { return 1; } + /* For our purposes, bytes are always little-endian. */ + if (size == 0) { + endian = MO_LE; + } + /* Consecutive little-endian elements from a single register + * can be promoted to a larger little-endian operation. + */ + if (interleave == 1 && endian == MO_LE) { + size = 3; + } tmp64 = tcg_temp_new_i64(); addr = tcg_temp_new_i32(); tmp2 = tcg_const_i32(1 << size); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Instead of shifts and masks, use direct loads and stores from the neon register file. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20181011205206.3552-21-richard.henderson@linaro.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.c | 92 +++++++++++++++++++++++------------------- 1 file changed, 50 insertions(+), 42 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static TCGv_i32 neon_load_reg(int reg, int pass) return tmp; } +static void neon_load_element(TCGv_i32 var, int reg, int ele, TCGMemOp mop) +{ + long offset = neon_element_offset(reg, ele, mop & MO_SIZE); + + switch (mop) { + case MO_UB: + tcg_gen_ld8u_i32(var, cpu_env, offset); + break; + case MO_UW: + tcg_gen_ld16u_i32(var, cpu_env, offset); + break; + case MO_UL: + tcg_gen_ld_i32(var, cpu_env, offset); + break; + default: + g_assert_not_reached(); + } +} + static void neon_load_element64(TCGv_i64 var, int reg, int ele, TCGMemOp mop) { long offset = neon_element_offset(reg, ele, mop & MO_SIZE); @@ -XXX,XX +XXX,XX @@ static void neon_store_reg(int reg, int pass, TCGv_i32 var) tcg_temp_free_i32(var); } +static void neon_store_element(int reg, int ele, TCGMemOp size, TCGv_i32 var) +{ + long offset = neon_element_offset(reg, ele, size); + + switch (size) { + case MO_8: + tcg_gen_st8_i32(var, cpu_env, offset); + break; + case MO_16: + tcg_gen_st16_i32(var, cpu_env, offset); + break; + case MO_32: + tcg_gen_st_i32(var, cpu_env, offset); + break; + default: + g_assert_not_reached(); + } +} + static void neon_store_element64(int reg, int ele, TCGMemOp size, TCGv_i64 var) { long offset = neon_element_offset(reg, ele, size); @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) int stride; int size; int reg; - int pass; int load; - int shift; int n; int vec_size; int mmu_idx; @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) } else { /* Single element. */ int idx = (insn >> 4) & 0xf; - pass = (insn >> 7) & 1; + int reg_idx; switch (size) { case 0: - shift = ((insn >> 5) & 3) * 8; + reg_idx = (insn >> 5) & 7; stride = 1; break; case 1: - shift = ((insn >> 6) & 1) * 16; + reg_idx = (insn >> 6) & 3; stride = (insn & (1 << 5)) ? 2 : 1; break; case 2: - shift = 0; + reg_idx = (insn >> 7) & 1; stride = (insn & (1 << 6)) ? 2 : 1; break; default: @@ -XXX,XX +XXX,XX @@ static int disas_neon_ls_insn(DisasContext *s, uint32_t insn) */ return 1; } + tmp = tcg_temp_new_i32(); addr = tcg_temp_new_i32(); load_reg_var(s, addr, rn); for (reg = 0; reg < nregs; reg++) { if (load) { - tmp = tcg_temp_new_i32(); - switch (size) { - case 0: - gen_aa32_ld8u(s, tmp, addr, get_mem_index(s)); - break; - case 1: - gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); - break; - case 2: - gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); - break; - default: /* Avoid compiler warnings. */ - abort(); - } - if (size != 2) { - tmp2 = neon_load_reg(rd, pass); - tcg_gen_deposit_i32(tmp, tmp2, tmp, - shift, size ? 16 : 8); - tcg_temp_free_i32(tmp2); - } - neon_store_reg(rd, pass, tmp); + gen_aa32_ld_i32(s, tmp, addr, get_mem_index(s), + s->be_data | size); + neon_store_element(rd, reg_idx, size, tmp); } else { /* Store */ - tmp = neon_load_reg(rd, pass); - if (shift) - tcg_gen_shri_i32(tmp, tmp, shift); - switch (size) { - case 0: - gen_aa32_st8(s, tmp, addr, get_mem_index(s)); - break; - case 1: - gen_aa32_st16(s, tmp, addr, get_mem_index(s)); - break; - case 2: - gen_aa32_st32(s, tmp, addr, get_mem_index(s)); - break; - } - tcg_temp_free_i32(tmp); + neon_load_element(tmp, rd, reg_idx, size); + gen_aa32_st_i32(s, tmp, addr, get_mem_index(s), + s->be_data | size); } rd += stride; tcg_gen_addi_i32(addr, addr, 1 << size); } tcg_temp_free_i32(addr); + tcg_temp_free_i32(tmp); stride = nregs * (1 << size); } } -- 2.19.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Announce the availability of the various priority queues. This fixes an issue where guest kernels would miss to configure secondary queues due to inproper feature bits. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20181017213932.19973-2-edgar.iglesias@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 8 +++++++- 1 file changed, 7 insertions(+), 1 deletion(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static void gem_reset(DeviceState *d) int i; CadenceGEMState *s = CADENCE_GEM(d); const uint8_t *a; + uint32_t queues_mask = 0; DB_PRINT("\n"); @@ -XXX,XX +XXX,XX @@ static void gem_reset(DeviceState *d) s->regs[GEM_DESCONF] = 0x02500111; s->regs[GEM_DESCONF2] = 0x2ab13fff; s->regs[GEM_DESCONF5] = 0x002f2045; - s->regs[GEM_DESCONF6] = 0x00000200; + s->regs[GEM_DESCONF6] = 0x0; + + if (s->num_priority_queues > 1) { + queues_mask = MAKE_64BIT_MASK(1, s->num_priority_queues - 1); + s->regs[GEM_DESCONF6] |= queues_mask; + } /* Set MAC address */ a = &s->conf.macaddr.a[0]; -- 2.19.1 From: "Edgar E. Iglesias" <edgar.iglesias@xilinx.com> Announce 64bit addressing support. Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Signed-off-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 20181017213932.19973-3-edgar.iglesias@gmail.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ #define GEM_DESCONF4 (0x0000028C/4) #define GEM_DESCONF5 (0x00000290/4) #define GEM_DESCONF6 (0x00000294/4) +#define GEM_DESCONF6_64B_MASK (1U << 23) #define GEM_DESCONF7 (0x00000298/4) #define GEM_INT_Q1_STATUS (0x00000400 / 4) @@ -XXX,XX +XXX,XX @@ static void gem_reset(DeviceState *d) s->regs[GEM_DESCONF] = 0x02500111; s->regs[GEM_DESCONF2] = 0x2ab13fff; s->regs[GEM_DESCONF5] = 0x002f2045; - s->regs[GEM_DESCONF6] = 0x0; + s->regs[GEM_DESCONF6] = GEM_DESCONF6_64B_MASK; if (s->num_priority_queues > 1) { queues_mask = MAKE_64BIT_MASK(1, s->num_priority_queues - 1); -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> The EL3 version of this register does not include an ASID, and so the tlb_flush performed by vmsa_ttbr_write is not needed. Reviewed-by: Aaron Lindsay <aaron@os.amperecomputing.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20181019015617.22583-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static const ARMCPRegInfo el3_cp_reginfo[] = { .fieldoffset = offsetof(CPUARMState, cp15.mvbar) }, { .name = "TTBR0_EL3", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 6, .crn = 2, .crm = 0, .opc2 = 0, - .access = PL3_RW, .writefn = vmsa_ttbr_write, .resetvalue = 0, + .access = PL3_RW, .resetvalue = 0, .fieldoffset = offsetof(CPUARMState, cp15.ttbr0_el[3]) }, { .name = "TCR_EL3", .state = ARM_CP_STATE_AA64, .opc0 = 3, .opc1 = 6, .crn = 2, .crm = 0, .opc2 = 2, -- 2.19.1 From: Richard Henderson <richard.henderson@linaro.org> Since QEMU does not implement ASIDs, changes to the ASID must flush the tlb. However, if the ASID does not change there is no reason to flush. In testing a boot of the Ubuntu installer to the first menu, this reduces the number of flushes by 30%, or nearly 600k instances. Reviewed-by: Aaron Lindsay <aaron@os.amperecomputing.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Message-id: 20181019015617.22583-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 8 +++----- 1 file changed, 3 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 void vmsa_tcr_el1_write(CPUARMState *env, const ARMCPRegInfo *ri, static void vmsa_ttbr_write(CPUARMState *env, const ARMCPRegInfo *ri, uint64_t value) { - /* 64 bit accesses to the TTBRs can change the ASID and so we - * must flush the TLB. - */ - if (cpreg_field_is_64bit(ri)) { + /* If the ASID changes (with a 64-bit write), we must flush the TLB. */ + if (cpreg_field_is_64bit(ri) && + extract64(raw_read(env, ri) ^ value, 48, 16) != 0) { ARMCPU *cpu = arm_env_get_cpu(env); - tlb_flush(CPU(cpu)); } raw_write(env, ri, value); -- 2.19.1 First arm pullreq for 7.1. The bulk of this is the qemu_split_irq removal. I have enough stuff in my to-review queue that I expect to do another pullreq early next week, but 31 patches is enough to not hang on to. thanks -- PMM The following changes since commit 9c125d17e9402c232c46610802e5931b3639d77b: Merge tag 'pull-tcg-20220420' of https://gitlab.com/rth7680/qemu into staging (2022-04-20 16:43:11 -0700) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20220421 for you to fetch changes up to 5b415dd61bdbf61fb4be0e9f1a7172b8bce682c6: hw/arm: Use bit fields for NPCM7XX PWRON STRAPs (2022-04-21 11:37:05 +0100) ---------------------------------------------------------------- target-arm queue: * hw/arm/virt: Check for attempt to use TrustZone with KVM or HVF * versal: Add the Cortex-R5s in the Real-Time Processing Unit (RPU) subsystem * versal: model enough of the Clock/Reset Low-power domain (CRL) to allow control of the Cortex-R5s * xlnx-zynqmp: Connect 4 TTC timers * exynos4210: Refactor GIC/combiner code to stop using qemu_split_irq * realview: replace 'qemu_split_irq' with 'TYPE_SPLIT_IRQ' * stellaris: replace 'qemu_split_irq' with 'TYPE_SPLIT_IRQ' * hw/core/irq: remove unused 'qemu_irq_split' function * npcm7xx: use symbolic constants for PWRON STRAP bit fields * virt: document impact of gic-version on max CPUs ---------------------------------------------------------------- Edgar E. Iglesias (6): timer: cadence_ttc: Break out header file to allow embedding hw/arm/xlnx-zynqmp: Connect 4 TTC timers hw/arm: versal: Create an APU CPU Cluster hw/arm: versal: Add the Cortex-R5Fs hw/misc: Add a model of the Xilinx Versal CRL hw/arm: versal: Connect the CRL Hao Wu (2): hw/misc: Add PWRON STRAP bit fields in GCR module hw/arm: Use bit fields for NPCM7XX PWRON STRAPs Heinrich Schuchardt (1): hw/arm/virt: impact of gic-version on max CPUs Peter Maydell (19): hw/arm/virt: Check for attempt to use TrustZone with KVM or HVF hw/arm/exynos4210: Use TYPE_OR_IRQ instead of custom OR-gate device hw/intc/exynos4210_gic: Remove unused TYPE_EXYNOS4210_IRQ_GATE hw/arm/exynos4210: Put a9mpcore device into state struct hw/arm/exynos4210: Drop int_gic_irq[] from Exynos4210Irq struct hw/arm/exynos4210: Coalesce board_irqs and irq_table hw/arm/exynos4210: Fix code style nit in combiner_grp_to_gic_id[] hw/arm/exynos4210: Move exynos4210_init_board_irqs() into exynos4210.c hw/arm/exynos4210: Put external GIC into state struct hw/arm/exynos4210: Drop ext_gic_irq[] from Exynos4210Irq struct hw/arm/exynos4210: Move exynos4210_combiner_get_gpioin() into exynos4210.c hw/arm/exynos4210: Delete unused macro definitions hw/arm/exynos4210: Use TYPE_SPLIT_IRQ in exynos4210_init_board_irqs() hw/arm/exynos4210: Fill in irq_table[] for internal-combiner-only IRQ lines hw/arm/exynos4210: Connect MCT_G0 and MCT_G1 to both combiners hw/arm/exynos4210: Don't connect multiple lines to external GIC inputs hw/arm/exynos4210: Fold combiner splits into exynos4210_init_board_irqs() hw/arm/exynos4210: Put combiners into state struct hw/arm/exynos4210: Drop Exynos4210Irq struct Zongyuan Li (3): hw/arm/realview: replace 'qemu_split_irq' with 'TYPE_SPLIT_IRQ' hw/arm/stellaris: replace 'qemu_split_irq' with 'TYPE_SPLIT_IRQ' hw/core/irq: remove unused 'qemu_irq_split' function docs/system/arm/virt.rst | 4 +- include/hw/arm/exynos4210.h | 50 ++-- include/hw/arm/xlnx-versal.h | 16 ++ include/hw/arm/xlnx-zynqmp.h | 4 + include/hw/intc/exynos4210_combiner.h | 57 +++++ include/hw/intc/exynos4210_gic.h | 43 ++++ include/hw/irq.h | 5 - include/hw/misc/npcm7xx_gcr.h | 30 +++ include/hw/misc/xlnx-versal-crl.h | 235 +++++++++++++++++++ include/hw/timer/cadence_ttc.h | 54 +++++ hw/arm/exynos4210.c | 430 ++++++++++++++++++++++++++++++---- hw/arm/npcm7xx_boards.c | 24 +- hw/arm/realview.c | 33 ++- hw/arm/stellaris.c | 15 +- hw/arm/virt.c | 7 + hw/arm/xlnx-versal-virt.c | 6 +- hw/arm/xlnx-versal.c | 99 +++++++- hw/arm/xlnx-zynqmp.c | 22 ++ hw/core/irq.c | 15 -- hw/intc/exynos4210_combiner.c | 108 +-------- hw/intc/exynos4210_gic.c | 344 +-------------------------- hw/misc/xlnx-versal-crl.c | 421 +++++++++++++++++++++++++++++++++ hw/timer/cadence_ttc.c | 32 +-- MAINTAINERS | 2 +- hw/misc/meson.build | 1 + 25 files changed, 1457 insertions(+), 600 deletions(-) create mode 100644 include/hw/intc/exynos4210_combiner.h create mode 100644 include/hw/intc/exynos4210_gic.h create mode 100644 include/hw/misc/xlnx-versal-crl.h create mode 100644 include/hw/timer/cadence_ttc.h create mode 100644 hw/misc/xlnx-versal-crl.c It's not possible to provide the guest with the Security extensions (TrustZone) when using KVM or HVF, because the hardware virtualization extensions don't permit running EL3 guest code. However, we weren't checking for this combination, with the result that QEMU would assert if you tried it: $ qemu-system-aarch64 -enable-kvm -machine virt,secure=on -cpu host -display none Unexpected error in object_property_find_err() at ../../qom/object.c:1304: qemu-system-aarch64: Property 'host-arm-cpu.secure-memory' not found Aborted Check for this combination of options and report an error, in the same way we already do for attempts to give a KVM or HVF guest the Virtualization or MTE extensions. Now we will report: qemu-system-aarch64: mach-virt: KVM does not support providing Security extensions (TrustZone) to the guest CPU Resolves: https://gitlab.com/qemu-project/qemu/-/issues/961 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404155301.566542-1-peter.maydell@linaro.org --- hw/arm/virt.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ static void machvirt_init(MachineState *machine) exit(1); } + if (vms->secure && (kvm_enabled() || hvf_enabled())) { + error_report("mach-virt: %s does not support providing " + "Security extensions (TrustZone) to the guest CPU", + kvm_enabled() ? "KVM" : "HVF"); + exit(1); + } + if (vms->virt && (kvm_enabled() || hvf_enabled())) { error_report("mach-virt: %s does not support providing " "Virtualization extensions to the guest CPU", -- 2.25.1 From: "Edgar E. Iglesias" <edgar.iglesias@amd.com> Break out header file to allow embedding of the the TTC. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc@lmichel.fr> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Message-id: 20220331222017.2914409-2-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/timer/cadence_ttc.h | 54 ++++++++++++++++++++++++++++++++++ hw/timer/cadence_ttc.c | 32 ++------------------ 2 files changed, 56 insertions(+), 30 deletions(-) create mode 100644 include/hw/timer/cadence_ttc.h diff --git a/include/hw/timer/cadence_ttc.h b/include/hw/timer/cadence_ttc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/timer/cadence_ttc.h @@ -XXX,XX +XXX,XX @@ +/* + * Xilinx Zynq cadence TTC model + * + * Copyright (c) 2011 Xilinx Inc. + * Copyright (c) 2012 Peter A.G. Crosthwaite (peter.crosthwaite@petalogix.com) + * Copyright (c) 2012 PetaLogix Pty Ltd. + * Written By Haibing Ma + * M. Habib + * + * 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. + * + * You should have received a copy of the GNU General Public License along + * with this program; if not, see <http://www.gnu.org/licenses/>. + */ +#ifndef HW_TIMER_CADENCE_TTC_H +#define HW_TIMER_CADENCE_TTC_H + +#include "hw/sysbus.h" +#include "qemu/timer.h" + +typedef struct { + QEMUTimer *timer; + int freq; + + uint32_t reg_clock; + uint32_t reg_count; + uint32_t reg_value; + uint16_t reg_interval; + uint16_t reg_match[3]; + uint32_t reg_intr; + uint32_t reg_intr_en; + uint32_t reg_event_ctrl; + uint32_t reg_event; + + uint64_t cpu_time; + unsigned int cpu_time_valid; + + qemu_irq irq; +} CadenceTimerState; + +#define TYPE_CADENCE_TTC "cadence_ttc" +OBJECT_DECLARE_SIMPLE_TYPE(CadenceTTCState, CADENCE_TTC) + +struct CadenceTTCState { + SysBusDevice parent_obj; + + MemoryRegion iomem; + CadenceTimerState timer[3]; +}; + +#endif diff --git a/hw/timer/cadence_ttc.c b/hw/timer/cadence_ttc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/cadence_ttc.c +++ b/hw/timer/cadence_ttc.c @@ -XXX,XX +XXX,XX @@ #include "qemu/timer.h" #include "qom/object.h" +#include "hw/timer/cadence_ttc.h" + #ifdef CADENCE_TTC_ERR_DEBUG #define DB_PRINT(...) do { \ fprintf(stderr, ": %s: ", __func__); \ @@ -XXX,XX +XXX,XX @@ #define CLOCK_CTRL_PS_EN 0x00000001 #define CLOCK_CTRL_PS_V 0x0000001e -typedef struct { - QEMUTimer *timer; - int freq; - - uint32_t reg_clock; - uint32_t reg_count; - uint32_t reg_value; - uint16_t reg_interval; - uint16_t reg_match[3]; - uint32_t reg_intr; - uint32_t reg_intr_en; - uint32_t reg_event_ctrl; - uint32_t reg_event; - - uint64_t cpu_time; - unsigned int cpu_time_valid; - - qemu_irq irq; -} CadenceTimerState; - -#define TYPE_CADENCE_TTC "cadence_ttc" -OBJECT_DECLARE_SIMPLE_TYPE(CadenceTTCState, CADENCE_TTC) - -struct CadenceTTCState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - CadenceTimerState timer[3]; -}; - static void cadence_timer_update(CadenceTimerState *s) { qemu_set_irq(s->irq, !!(s->reg_intr & s->reg_intr_en)); -- 2.25.1 From: "Edgar E. Iglesias" <edgar.iglesias@amd.com> Connect the 4 TTC timers on the ZynqMP. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Luc Michel <luc@lmichel.fr> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Message-id: 20220331222017.2914409-3-edgar.iglesias@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-zynqmp.h | 4 ++++ hw/arm/xlnx-zynqmp.c | 22 ++++++++++++++++++++++ 2 files changed, 26 insertions(+) diff --git a/include/hw/arm/xlnx-zynqmp.h b/include/hw/arm/xlnx-zynqmp.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-zynqmp.h +++ b/include/hw/arm/xlnx-zynqmp.h @@ -XXX,XX +XXX,XX @@ #include "hw/or-irq.h" #include "hw/misc/xlnx-zynqmp-apu-ctrl.h" #include "hw/misc/xlnx-zynqmp-crf.h" +#include "hw/timer/cadence_ttc.h" #define TYPE_XLNX_ZYNQMP "xlnx-zynqmp" OBJECT_DECLARE_SIMPLE_TYPE(XlnxZynqMPState, XLNX_ZYNQMP) @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(XlnxZynqMPState, XLNX_ZYNQMP) #define XLNX_ZYNQMP_MAX_RAM_SIZE (XLNX_ZYNQMP_MAX_LOW_RAM_SIZE + \ XLNX_ZYNQMP_MAX_HIGH_RAM_SIZE) +#define XLNX_ZYNQMP_NUM_TTC 4 + /* * Unimplemented mmio regions needed to boot some images. */ @@ -XXX,XX +XXX,XX @@ struct XlnxZynqMPState { qemu_or_irq qspi_irq_orgate; XlnxZynqMPAPUCtrl apu_ctrl; XlnxZynqMPCRF crf; + CadenceTTCState ttc[XLNX_ZYNQMP_NUM_TTC]; char *boot_cpu; ARMCPU *boot_cpu_ptr; 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 @@ #define APU_ADDR 0xfd5c0000 #define APU_IRQ 153 +#define TTC0_ADDR 0xFF110000 +#define TTC0_IRQ 36 + #define IPI_ADDR 0xFF300000 #define IPI_IRQ 64 @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_create_crf(XlnxZynqMPState *s, qemu_irq *gic) sysbus_connect_irq(sbd, 0, gic[CRF_IRQ]); } +static void xlnx_zynqmp_create_ttc(XlnxZynqMPState *s, qemu_irq *gic) +{ + SysBusDevice *sbd; + int i, irq; + + for (i = 0; i < XLNX_ZYNQMP_NUM_TTC; i++) { + object_initialize_child(OBJECT(s), "ttc[*]", &s->ttc[i], + TYPE_CADENCE_TTC); + sbd = SYS_BUS_DEVICE(&s->ttc[i]); + + sysbus_realize(sbd, &error_fatal); + sysbus_mmio_map(sbd, 0, TTC0_ADDR + i * 0x10000); + for (irq = 0; irq < 3; irq++) { + sysbus_connect_irq(sbd, irq, gic[TTC0_IRQ + i * 3 + irq]); + } + } +} + static void xlnx_zynqmp_create_unimp_mmio(XlnxZynqMPState *s) { static const struct UnimpInfo { @@ -XXX,XX +XXX,XX @@ static void xlnx_zynqmp_realize(DeviceState *dev, Error **errp) xlnx_zynqmp_create_efuse(s, gic_spi); xlnx_zynqmp_create_apu_ctrl(s, gic_spi); xlnx_zynqmp_create_crf(s, gic_spi); + xlnx_zynqmp_create_ttc(s, gic_spi); xlnx_zynqmp_create_unimp_mmio(s); for (i = 0; i < XLNX_ZYNQMP_NUM_GDMA_CH; i++) { -- 2.25.1 From: "Edgar E. Iglesias" <edgar.iglesias@amd.com> Create an APU CPU Cluster. This is in preparation to add the RPU. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20220406174303.2022038-2-edgar.iglesias@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 2 ++ hw/arm/xlnx-versal.c | 9 ++++++++- 2 files changed, 10 insertions(+), 1 deletion(-) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/arm/boot.h" +#include "hw/cpu/cluster.h" #include "hw/or-irq.h" #include "hw/sd/sdhci.h" #include "hw/intc/arm_gicv3.h" @@ -XXX,XX +XXX,XX @@ struct Versal { struct { struct { MemoryRegion mr; + CPUClusterState cluster; ARMCPU cpu[XLNX_VERSAL_NR_ACPUS]; GICv3State gic; } apu; diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s) { int i; + object_initialize_child(OBJECT(s), "apu-cluster", &s->fpd.apu.cluster, + TYPE_CPU_CLUSTER); + qdev_prop_set_uint32(DEVICE(&s->fpd.apu.cluster), "cluster-id", 0); + for (i = 0; i < ARRAY_SIZE(s->fpd.apu.cpu); i++) { Object *obj; - object_initialize_child(OBJECT(s), "apu-cpu[*]", &s->fpd.apu.cpu[i], + object_initialize_child(OBJECT(&s->fpd.apu.cluster), + "apu-cpu[*]", &s->fpd.apu.cpu[i], XLNX_VERSAL_ACPU_TYPE); obj = OBJECT(&s->fpd.apu.cpu[i]); if (i) { @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_cpus(Versal *s) &error_abort); qdev_realize(DEVICE(obj), NULL, &error_fatal); } + + qdev_realize(DEVICE(&s->fpd.apu.cluster), NULL, &error_fatal); } static void versal_create_apu_gic(Versal *s, qemu_irq *pic) -- 2.25.1 From: "Edgar E. Iglesias" <edgar.iglesias@amd.com> Add the Cortex-R5Fs of the Versal RPU (Real-time Processing Unit) subsystem. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20220406174303.2022038-3-edgar.iglesias@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 10 ++++++++++ hw/arm/xlnx-versal-virt.c | 6 +++--- hw/arm/xlnx-versal.c | 36 ++++++++++++++++++++++++++++++++++++ 3 files changed, 49 insertions(+), 3 deletions(-) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(Versal, XLNX_VERSAL) #define XLNX_VERSAL_NR_ACPUS 2 +#define XLNX_VERSAL_NR_RCPUS 2 #define XLNX_VERSAL_NR_UARTS 2 #define XLNX_VERSAL_NR_GEMS 2 #define XLNX_VERSAL_NR_ADMAS 8 @@ -XXX,XX +XXX,XX @@ struct Versal { VersalUsb2 usb; } iou; + /* Real-time Processing Unit. */ + struct { + MemoryRegion mr; + MemoryRegion mr_ps_alias; + + CPUClusterState cluster; + ARMCPU cpu[XLNX_VERSAL_NR_RCPUS]; + } rpu; + struct { qemu_or_irq irq_orgate; XlnxXramCtrl ctrl[XLNX_VERSAL_NR_XRAM]; diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal-virt.c +++ b/hw/arm/xlnx-versal-virt.c @@ -XXX,XX +XXX,XX @@ static void versal_virt_machine_class_init(ObjectClass *oc, void *data) mc->desc = "Xilinx Versal Virtual development board"; mc->init = versal_virt_init; - mc->min_cpus = XLNX_VERSAL_NR_ACPUS; - mc->max_cpus = XLNX_VERSAL_NR_ACPUS; - mc->default_cpus = XLNX_VERSAL_NR_ACPUS; + mc->min_cpus = XLNX_VERSAL_NR_ACPUS + XLNX_VERSAL_NR_RCPUS; + mc->max_cpus = XLNX_VERSAL_NR_ACPUS + XLNX_VERSAL_NR_RCPUS; + mc->default_cpus = XLNX_VERSAL_NR_ACPUS + XLNX_VERSAL_NR_RCPUS; mc->no_cdrom = true; mc->default_ram_id = "ddr"; } diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #define XLNX_VERSAL_ACPU_TYPE ARM_CPU_TYPE_NAME("cortex-a72") +#define XLNX_VERSAL_RCPU_TYPE ARM_CPU_TYPE_NAME("cortex-r5f") #define GEM_REVISION 0x40070106 #define VERSAL_NUM_PMC_APB_IRQS 3 @@ -XXX,XX +XXX,XX @@ static void versal_create_apu_gic(Versal *s, qemu_irq *pic) } } +static void versal_create_rpu_cpus(Versal *s) +{ + int i; + + object_initialize_child(OBJECT(s), "rpu-cluster", &s->lpd.rpu.cluster, + TYPE_CPU_CLUSTER); + qdev_prop_set_uint32(DEVICE(&s->lpd.rpu.cluster), "cluster-id", 1); + + for (i = 0; i < ARRAY_SIZE(s->lpd.rpu.cpu); i++) { + Object *obj; + + object_initialize_child(OBJECT(&s->lpd.rpu.cluster), + "rpu-cpu[*]", &s->lpd.rpu.cpu[i], + XLNX_VERSAL_RCPU_TYPE); + obj = OBJECT(&s->lpd.rpu.cpu[i]); + object_property_set_bool(obj, "start-powered-off", true, + &error_abort); + + object_property_set_int(obj, "mp-affinity", 0x100 | i, &error_abort); + object_property_set_int(obj, "core-count", ARRAY_SIZE(s->lpd.rpu.cpu), + &error_abort); + object_property_set_link(obj, "memory", OBJECT(&s->lpd.rpu.mr), + &error_abort); + qdev_realize(DEVICE(obj), NULL, &error_fatal); + } + + qdev_realize(DEVICE(&s->lpd.rpu.cluster), NULL, &error_fatal); +} + static void versal_create_uarts(Versal *s, qemu_irq *pic) { int i; @@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp) versal_create_apu_cpus(s); versal_create_apu_gic(s, pic); + versal_create_rpu_cpus(s); versal_create_uarts(s, pic); versal_create_usbs(s, pic); versal_create_gems(s, pic); @@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp) memory_region_add_subregion_overlap(&s->mr_ps, MM_OCM, &s->lpd.mr_ocm, 0); memory_region_add_subregion_overlap(&s->fpd.apu.mr, 0, &s->mr_ps, 0); + memory_region_add_subregion_overlap(&s->lpd.rpu.mr, 0, + &s->lpd.rpu.mr_ps_alias, 0); } static void versal_init(Object *obj) @@ -XXX,XX +XXX,XX @@ static void versal_init(Object *obj) Versal *s = XLNX_VERSAL(obj); memory_region_init(&s->fpd.apu.mr, obj, "mr-apu", UINT64_MAX); + memory_region_init(&s->lpd.rpu.mr, obj, "mr-rpu", UINT64_MAX); memory_region_init(&s->mr_ps, obj, "mr-ps-switch", UINT64_MAX); + memory_region_init_alias(&s->lpd.rpu.mr_ps_alias, OBJECT(s), + "mr-rpu-ps-alias", &s->mr_ps, 0, UINT64_MAX); } static Property versal_properties[] = { -- 2.25.1 From: "Edgar E. Iglesias" <edgar.iglesias@amd.com> Add a model of the Xilinx Versal CRL. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Frederic Konrad <fkonrad@amd.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20220406174303.2022038-4-edgar.iglesias@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/xlnx-versal-crl.h | 235 +++++++++++++++++ hw/misc/xlnx-versal-crl.c | 421 ++++++++++++++++++++++++++++++ hw/misc/meson.build | 1 + 3 files changed, 657 insertions(+) create mode 100644 include/hw/misc/xlnx-versal-crl.h create mode 100644 hw/misc/xlnx-versal-crl.c diff --git a/include/hw/misc/xlnx-versal-crl.h b/include/hw/misc/xlnx-versal-crl.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/xlnx-versal-crl.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Clock-Reset-LPD (CRL). + * + * Copyright (c) 2022 Xilinx Inc. + * SPDX-License-Identifier: GPL-2.0-or-later + * + * Written by Edgar E. Iglesias <edgar.iglesias@xilinx.com> + */ +#ifndef HW_MISC_XLNX_VERSAL_CRL_H +#define HW_MISC_XLNX_VERSAL_CRL_H + +#include "hw/sysbus.h" +#include "hw/register.h" +#include "target/arm/cpu.h" + +#define TYPE_XLNX_VERSAL_CRL "xlnx,versal-crl" +OBJECT_DECLARE_SIMPLE_TYPE(XlnxVersalCRL, XLNX_VERSAL_CRL) + +REG32(ERR_CTRL, 0x0) + FIELD(ERR_CTRL, SLVERR_ENABLE, 0, 1) +REG32(IR_STATUS, 0x4) + FIELD(IR_STATUS, ADDR_DECODE_ERR, 0, 1) +REG32(IR_MASK, 0x8) + FIELD(IR_MASK, ADDR_DECODE_ERR, 0, 1) +REG32(IR_ENABLE, 0xc) + FIELD(IR_ENABLE, ADDR_DECODE_ERR, 0, 1) +REG32(IR_DISABLE, 0x10) + FIELD(IR_DISABLE, ADDR_DECODE_ERR, 0, 1) +REG32(WPROT, 0x1c) + FIELD(WPROT, ACTIVE, 0, 1) +REG32(PLL_CLK_OTHER_DMN, 0x20) + FIELD(PLL_CLK_OTHER_DMN, APLL_BYPASS, 0, 1) +REG32(RPLL_CTRL, 0x40) + FIELD(RPLL_CTRL, POST_SRC, 24, 3) + FIELD(RPLL_CTRL, PRE_SRC, 20, 3) + FIELD(RPLL_CTRL, CLKOUTDIV, 16, 2) + FIELD(RPLL_CTRL, FBDIV, 8, 8) + FIELD(RPLL_CTRL, BYPASS, 3, 1) + FIELD(RPLL_CTRL, RESET, 0, 1) +REG32(RPLL_CFG, 0x44) + FIELD(RPLL_CFG, LOCK_DLY, 25, 7) + FIELD(RPLL_CFG, LOCK_CNT, 13, 10) + FIELD(RPLL_CFG, LFHF, 10, 2) + FIELD(RPLL_CFG, CP, 5, 4) + FIELD(RPLL_CFG, RES, 0, 4) +REG32(RPLL_FRAC_CFG, 0x48) + FIELD(RPLL_FRAC_CFG, ENABLED, 31, 1) + FIELD(RPLL_FRAC_CFG, SEED, 22, 3) + FIELD(RPLL_FRAC_CFG, ALGRTHM, 19, 1) + FIELD(RPLL_FRAC_CFG, ORDER, 18, 1) + FIELD(RPLL_FRAC_CFG, DATA, 0, 16) +REG32(PLL_STATUS, 0x50) + FIELD(PLL_STATUS, RPLL_STABLE, 2, 1) + FIELD(PLL_STATUS, RPLL_LOCK, 0, 1) +REG32(RPLL_TO_XPD_CTRL, 0x100) + FIELD(RPLL_TO_XPD_CTRL, CLKACT, 25, 1) + FIELD(RPLL_TO_XPD_CTRL, DIVISOR0, 8, 10) +REG32(LPD_TOP_SWITCH_CTRL, 0x104) + FIELD(LPD_TOP_SWITCH_CTRL, CLKACT_ADMA, 26, 1) + FIELD(LPD_TOP_SWITCH_CTRL, CLKACT, 25, 1) + FIELD(LPD_TOP_SWITCH_CTRL, DIVISOR0, 8, 10) + FIELD(LPD_TOP_SWITCH_CTRL, SRCSEL, 0, 3) +REG32(LPD_LSBUS_CTRL, 0x108) + FIELD(LPD_LSBUS_CTRL, CLKACT, 25, 1) + FIELD(LPD_LSBUS_CTRL, DIVISOR0, 8, 10) + FIELD(LPD_LSBUS_CTRL, SRCSEL, 0, 3) +REG32(CPU_R5_CTRL, 0x10c) + FIELD(CPU_R5_CTRL, CLKACT_OCM2, 28, 1) + FIELD(CPU_R5_CTRL, CLKACT_OCM, 27, 1) + FIELD(CPU_R5_CTRL, CLKACT_CORE, 26, 1) + FIELD(CPU_R5_CTRL, CLKACT, 25, 1) + FIELD(CPU_R5_CTRL, DIVISOR0, 8, 10) + FIELD(CPU_R5_CTRL, SRCSEL, 0, 3) +REG32(IOU_SWITCH_CTRL, 0x114) + FIELD(IOU_SWITCH_CTRL, CLKACT, 25, 1) + FIELD(IOU_SWITCH_CTRL, DIVISOR0, 8, 10) + FIELD(IOU_SWITCH_CTRL, SRCSEL, 0, 3) +REG32(GEM0_REF_CTRL, 0x118) + FIELD(GEM0_REF_CTRL, CLKACT_RX, 27, 1) + FIELD(GEM0_REF_CTRL, CLKACT_TX, 26, 1) + FIELD(GEM0_REF_CTRL, CLKACT, 25, 1) + FIELD(GEM0_REF_CTRL, DIVISOR0, 8, 10) + FIELD(GEM0_REF_CTRL, SRCSEL, 0, 3) +REG32(GEM1_REF_CTRL, 0x11c) + FIELD(GEM1_REF_CTRL, CLKACT_RX, 27, 1) + FIELD(GEM1_REF_CTRL, CLKACT_TX, 26, 1) + FIELD(GEM1_REF_CTRL, CLKACT, 25, 1) + FIELD(GEM1_REF_CTRL, DIVISOR0, 8, 10) + FIELD(GEM1_REF_CTRL, SRCSEL, 0, 3) +REG32(GEM_TSU_REF_CTRL, 0x120) + FIELD(GEM_TSU_REF_CTRL, CLKACT, 25, 1) + FIELD(GEM_TSU_REF_CTRL, DIVISOR0, 8, 10) + FIELD(GEM_TSU_REF_CTRL, SRCSEL, 0, 3) +REG32(USB0_BUS_REF_CTRL, 0x124) + FIELD(USB0_BUS_REF_CTRL, CLKACT, 25, 1) + FIELD(USB0_BUS_REF_CTRL, DIVISOR0, 8, 10) + FIELD(USB0_BUS_REF_CTRL, SRCSEL, 0, 3) +REG32(UART0_REF_CTRL, 0x128) + FIELD(UART0_REF_CTRL, CLKACT, 25, 1) + FIELD(UART0_REF_CTRL, DIVISOR0, 8, 10) + FIELD(UART0_REF_CTRL, SRCSEL, 0, 3) +REG32(UART1_REF_CTRL, 0x12c) + FIELD(UART1_REF_CTRL, CLKACT, 25, 1) + FIELD(UART1_REF_CTRL, DIVISOR0, 8, 10) + FIELD(UART1_REF_CTRL, SRCSEL, 0, 3) +REG32(SPI0_REF_CTRL, 0x130) + FIELD(SPI0_REF_CTRL, CLKACT, 25, 1) + FIELD(SPI0_REF_CTRL, DIVISOR0, 8, 10) + FIELD(SPI0_REF_CTRL, SRCSEL, 0, 3) +REG32(SPI1_REF_CTRL, 0x134) + FIELD(SPI1_REF_CTRL, CLKACT, 25, 1) + FIELD(SPI1_REF_CTRL, DIVISOR0, 8, 10) + FIELD(SPI1_REF_CTRL, SRCSEL, 0, 3) +REG32(CAN0_REF_CTRL, 0x138) + FIELD(CAN0_REF_CTRL, CLKACT, 25, 1) + FIELD(CAN0_REF_CTRL, DIVISOR0, 8, 10) + FIELD(CAN0_REF_CTRL, SRCSEL, 0, 3) +REG32(CAN1_REF_CTRL, 0x13c) + FIELD(CAN1_REF_CTRL, CLKACT, 25, 1) + FIELD(CAN1_REF_CTRL, DIVISOR0, 8, 10) + FIELD(CAN1_REF_CTRL, SRCSEL, 0, 3) +REG32(I2C0_REF_CTRL, 0x140) + FIELD(I2C0_REF_CTRL, CLKACT, 25, 1) + FIELD(I2C0_REF_CTRL, DIVISOR0, 8, 10) + FIELD(I2C0_REF_CTRL, SRCSEL, 0, 3) +REG32(I2C1_REF_CTRL, 0x144) + FIELD(I2C1_REF_CTRL, CLKACT, 25, 1) + FIELD(I2C1_REF_CTRL, DIVISOR0, 8, 10) + FIELD(I2C1_REF_CTRL, SRCSEL, 0, 3) +REG32(DBG_LPD_CTRL, 0x148) + FIELD(DBG_LPD_CTRL, CLKACT, 25, 1) + FIELD(DBG_LPD_CTRL, DIVISOR0, 8, 10) + FIELD(DBG_LPD_CTRL, SRCSEL, 0, 3) +REG32(TIMESTAMP_REF_CTRL, 0x14c) + FIELD(TIMESTAMP_REF_CTRL, CLKACT, 25, 1) + FIELD(TIMESTAMP_REF_CTRL, DIVISOR0, 8, 10) + FIELD(TIMESTAMP_REF_CTRL, SRCSEL, 0, 3) +REG32(CRL_SAFETY_CHK, 0x150) +REG32(PSM_REF_CTRL, 0x154) + FIELD(PSM_REF_CTRL, DIVISOR0, 8, 10) + FIELD(PSM_REF_CTRL, SRCSEL, 0, 3) +REG32(DBG_TSTMP_CTRL, 0x158) + FIELD(DBG_TSTMP_CTRL, CLKACT, 25, 1) + FIELD(DBG_TSTMP_CTRL, DIVISOR0, 8, 10) + FIELD(DBG_TSTMP_CTRL, SRCSEL, 0, 3) +REG32(CPM_TOPSW_REF_CTRL, 0x15c) + FIELD(CPM_TOPSW_REF_CTRL, CLKACT, 25, 1) + FIELD(CPM_TOPSW_REF_CTRL, DIVISOR0, 8, 10) + FIELD(CPM_TOPSW_REF_CTRL, SRCSEL, 0, 3) +REG32(USB3_DUAL_REF_CTRL, 0x160) + FIELD(USB3_DUAL_REF_CTRL, CLKACT, 25, 1) + FIELD(USB3_DUAL_REF_CTRL, DIVISOR0, 8, 10) + FIELD(USB3_DUAL_REF_CTRL, SRCSEL, 0, 3) +REG32(RST_CPU_R5, 0x300) + FIELD(RST_CPU_R5, RESET_PGE, 4, 1) + FIELD(RST_CPU_R5, RESET_AMBA, 2, 1) + FIELD(RST_CPU_R5, RESET_CPU1, 1, 1) + FIELD(RST_CPU_R5, RESET_CPU0, 0, 1) +REG32(RST_ADMA, 0x304) + FIELD(RST_ADMA, RESET, 0, 1) +REG32(RST_GEM0, 0x308) + FIELD(RST_GEM0, RESET, 0, 1) +REG32(RST_GEM1, 0x30c) + FIELD(RST_GEM1, RESET, 0, 1) +REG32(RST_SPARE, 0x310) + FIELD(RST_SPARE, RESET, 0, 1) +REG32(RST_USB0, 0x314) + FIELD(RST_USB0, RESET, 0, 1) +REG32(RST_UART0, 0x318) + FIELD(RST_UART0, RESET, 0, 1) +REG32(RST_UART1, 0x31c) + FIELD(RST_UART1, RESET, 0, 1) +REG32(RST_SPI0, 0x320) + FIELD(RST_SPI0, RESET, 0, 1) +REG32(RST_SPI1, 0x324) + FIELD(RST_SPI1, RESET, 0, 1) +REG32(RST_CAN0, 0x328) + FIELD(RST_CAN0, RESET, 0, 1) +REG32(RST_CAN1, 0x32c) + FIELD(RST_CAN1, RESET, 0, 1) +REG32(RST_I2C0, 0x330) + FIELD(RST_I2C0, RESET, 0, 1) +REG32(RST_I2C1, 0x334) + FIELD(RST_I2C1, RESET, 0, 1) +REG32(RST_DBG_LPD, 0x338) + FIELD(RST_DBG_LPD, RPU_DBG1_RESET, 5, 1) + FIELD(RST_DBG_LPD, RPU_DBG0_RESET, 4, 1) + FIELD(RST_DBG_LPD, RESET_HSDP, 1, 1) + FIELD(RST_DBG_LPD, RESET, 0, 1) +REG32(RST_GPIO, 0x33c) + FIELD(RST_GPIO, RESET, 0, 1) +REG32(RST_TTC, 0x344) + FIELD(RST_TTC, TTC3_RESET, 3, 1) + FIELD(RST_TTC, TTC2_RESET, 2, 1) + FIELD(RST_TTC, TTC1_RESET, 1, 1) + FIELD(RST_TTC, TTC0_RESET, 0, 1) +REG32(RST_TIMESTAMP, 0x348) + FIELD(RST_TIMESTAMP, RESET, 0, 1) +REG32(RST_SWDT, 0x34c) + FIELD(RST_SWDT, RESET, 0, 1) +REG32(RST_OCM, 0x350) + FIELD(RST_OCM, RESET, 0, 1) +REG32(RST_IPI, 0x354) + FIELD(RST_IPI, RESET, 0, 1) +REG32(RST_SYSMON, 0x358) + FIELD(RST_SYSMON, SEQ_RST, 1, 1) + FIELD(RST_SYSMON, CFG_RST, 0, 1) +REG32(RST_FPD, 0x360) + FIELD(RST_FPD, SRST, 1, 1) + FIELD(RST_FPD, POR, 0, 1) +REG32(PSM_RST_MODE, 0x370) + FIELD(PSM_RST_MODE, WAKEUP, 2, 1) + FIELD(PSM_RST_MODE, RST_MODE, 0, 2) + +#define CRL_R_MAX (R_PSM_RST_MODE + 1) + +#define RPU_MAX_CPU 2 + +struct XlnxVersalCRL { + SysBusDevice parent_obj; + qemu_irq irq; + + struct { + ARMCPU *cpu_r5[RPU_MAX_CPU]; + DeviceState *adma[8]; + DeviceState *uart[2]; + DeviceState *gem[2]; + DeviceState *usb; + } cfg; + + RegisterInfoArray *reg_array; + uint32_t regs[CRL_R_MAX]; + RegisterInfo regs_info[CRL_R_MAX]; +}; +#endif diff --git a/hw/misc/xlnx-versal-crl.c b/hw/misc/xlnx-versal-crl.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/xlnx-versal-crl.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Clock-Reset-LPD (CRL). + * + * Copyright (c) 2022 Advanced Micro Devices, Inc. + * SPDX-License-Identifier: GPL-2.0-or-later + * + * Written by Edgar E. Iglesias <edgar.iglesias@amd.com> + */ + +#include "qemu/osdep.h" +#include "qapi/error.h" +#include "qemu/log.h" +#include "qemu/bitops.h" +#include "migration/vmstate.h" +#include "hw/qdev-properties.h" +#include "hw/sysbus.h" +#include "hw/irq.h" +#include "hw/register.h" +#include "hw/resettable.h" + +#include "target/arm/arm-powerctl.h" +#include "hw/misc/xlnx-versal-crl.h" + +#ifndef XLNX_VERSAL_CRL_ERR_DEBUG +#define XLNX_VERSAL_CRL_ERR_DEBUG 0 +#endif + +static void crl_update_irq(XlnxVersalCRL *s) +{ + bool pending = s->regs[R_IR_STATUS] & ~s->regs[R_IR_MASK]; + qemu_set_irq(s->irq, pending); +} + +static void crl_status_postw(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + crl_update_irq(s); +} + +static uint64_t crl_enable_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + uint32_t val = val64; + + s->regs[R_IR_MASK] &= ~val; + crl_update_irq(s); + return 0; +} + +static uint64_t crl_disable_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + uint32_t val = val64; + + s->regs[R_IR_MASK] |= val; + crl_update_irq(s); + return 0; +} + +static void crl_reset_dev(XlnxVersalCRL *s, DeviceState *dev, + bool rst_old, bool rst_new) +{ + device_cold_reset(dev); +} + +static void crl_reset_cpu(XlnxVersalCRL *s, ARMCPU *armcpu, + bool rst_old, bool rst_new) +{ + if (rst_new) { + arm_set_cpu_off(armcpu->mp_affinity); + } else { + arm_set_cpu_on_and_reset(armcpu->mp_affinity); + } +} + +#define REGFIELD_RESET(type, s, reg, f, new_val, dev) { \ + bool old_f = ARRAY_FIELD_EX32((s)->regs, reg, f); \ + bool new_f = FIELD_EX32(new_val, reg, f); \ + \ + /* Detect edges. */ \ + if (dev && old_f != new_f) { \ + crl_reset_ ## type(s, dev, old_f, new_f); \ + } \ +} + +static uint64_t crl_rst_r5_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + + REGFIELD_RESET(cpu, s, RST_CPU_R5, RESET_CPU0, val64, s->cfg.cpu_r5[0]); + REGFIELD_RESET(cpu, s, RST_CPU_R5, RESET_CPU1, val64, s->cfg.cpu_r5[1]); + return val64; +} + +static uint64_t crl_rst_adma_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + int i; + + /* A single register fans out to all ADMA reset inputs. */ + for (i = 0; i < ARRAY_SIZE(s->cfg.adma); i++) { + REGFIELD_RESET(dev, s, RST_ADMA, RESET, val64, s->cfg.adma[i]); + } + return val64; +} + +static uint64_t crl_rst_uart0_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + + REGFIELD_RESET(dev, s, RST_UART0, RESET, val64, s->cfg.uart[0]); + return val64; +} + +static uint64_t crl_rst_uart1_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + + REGFIELD_RESET(dev, s, RST_UART1, RESET, val64, s->cfg.uart[1]); + return val64; +} + +static uint64_t crl_rst_gem0_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + + REGFIELD_RESET(dev, s, RST_GEM0, RESET, val64, s->cfg.gem[0]); + return val64; +} + +static uint64_t crl_rst_gem1_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + + REGFIELD_RESET(dev, s, RST_GEM1, RESET, val64, s->cfg.gem[1]); + return val64; +} + +static uint64_t crl_rst_usb_prew(RegisterInfo *reg, uint64_t val64) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(reg->opaque); + + REGFIELD_RESET(dev, s, RST_USB0, RESET, val64, s->cfg.usb); + return val64; +} + +static const RegisterAccessInfo crl_regs_info[] = { + { .name = "ERR_CTRL", .addr = A_ERR_CTRL, + },{ .name = "IR_STATUS", .addr = A_IR_STATUS, + .w1c = 0x1, + .post_write = crl_status_postw, + },{ .name = "IR_MASK", .addr = A_IR_MASK, + .reset = 0x1, + .ro = 0x1, + },{ .name = "IR_ENABLE", .addr = A_IR_ENABLE, + .pre_write = crl_enable_prew, + },{ .name = "IR_DISABLE", .addr = A_IR_DISABLE, + .pre_write = crl_disable_prew, + },{ .name = "WPROT", .addr = A_WPROT, + },{ .name = "PLL_CLK_OTHER_DMN", .addr = A_PLL_CLK_OTHER_DMN, + .reset = 0x1, + .rsvd = 0xe, + },{ .name = "RPLL_CTRL", .addr = A_RPLL_CTRL, + .reset = 0x24809, + .rsvd = 0xf88c00f6, + },{ .name = "RPLL_CFG", .addr = A_RPLL_CFG, + .reset = 0x2000000, + .rsvd = 0x1801210, + },{ .name = "RPLL_FRAC_CFG", .addr = A_RPLL_FRAC_CFG, + .rsvd = 0x7e330000, + },{ .name = "PLL_STATUS", .addr = A_PLL_STATUS, + .reset = R_PLL_STATUS_RPLL_STABLE_MASK | + R_PLL_STATUS_RPLL_LOCK_MASK, + .rsvd = 0xfa, + .ro = 0x5, + },{ .name = "RPLL_TO_XPD_CTRL", .addr = A_RPLL_TO_XPD_CTRL, + .reset = 0x2000100, + .rsvd = 0xfdfc00ff, + },{ .name = "LPD_TOP_SWITCH_CTRL", .addr = A_LPD_TOP_SWITCH_CTRL, + .reset = 0x6000300, + .rsvd = 0xf9fc00f8, + },{ .name = "LPD_LSBUS_CTRL", .addr = A_LPD_LSBUS_CTRL, + .reset = 0x2000800, + .rsvd = 0xfdfc00f8, + },{ .name = "CPU_R5_CTRL", .addr = A_CPU_R5_CTRL, + .reset = 0xe000300, + .rsvd = 0xe1fc00f8, + },{ .name = "IOU_SWITCH_CTRL", .addr = A_IOU_SWITCH_CTRL, + .reset = 0x2000500, + .rsvd = 0xfdfc00f8, + },{ .name = "GEM0_REF_CTRL", .addr = A_GEM0_REF_CTRL, + .reset = 0xe000a00, + .rsvd = 0xf1fc00f8, + },{ .name = "GEM1_REF_CTRL", .addr = A_GEM1_REF_CTRL, + .reset = 0xe000a00, + .rsvd = 0xf1fc00f8, + },{ .name = "GEM_TSU_REF_CTRL", .addr = A_GEM_TSU_REF_CTRL, + .reset = 0x300, + .rsvd = 0xfdfc00f8, + },{ .name = "USB0_BUS_REF_CTRL", .addr = A_USB0_BUS_REF_CTRL, + .reset = 0x2001900, + .rsvd = 0xfdfc00f8, + },{ .name = "UART0_REF_CTRL", .addr = A_UART0_REF_CTRL, + .reset = 0xc00, + .rsvd = 0xfdfc00f8, + },{ .name = "UART1_REF_CTRL", .addr = A_UART1_REF_CTRL, + .reset = 0xc00, + .rsvd = 0xfdfc00f8, + },{ .name = "SPI0_REF_CTRL", .addr = A_SPI0_REF_CTRL, + .reset = 0x600, + .rsvd = 0xfdfc00f8, + },{ .name = "SPI1_REF_CTRL", .addr = A_SPI1_REF_CTRL, + .reset = 0x600, + .rsvd = 0xfdfc00f8, + },{ .name = "CAN0_REF_CTRL", .addr = A_CAN0_REF_CTRL, + .reset = 0xc00, + .rsvd = 0xfdfc00f8, + },{ .name = "CAN1_REF_CTRL", .addr = A_CAN1_REF_CTRL, + .reset = 0xc00, + .rsvd = 0xfdfc00f8, + },{ .name = "I2C0_REF_CTRL", .addr = A_I2C0_REF_CTRL, + .reset = 0xc00, + .rsvd = 0xfdfc00f8, + },{ .name = "I2C1_REF_CTRL", .addr = A_I2C1_REF_CTRL, + .reset = 0xc00, + .rsvd = 0xfdfc00f8, + },{ .name = "DBG_LPD_CTRL", .addr = A_DBG_LPD_CTRL, + .reset = 0x300, + .rsvd = 0xfdfc00f8, + },{ .name = "TIMESTAMP_REF_CTRL", .addr = A_TIMESTAMP_REF_CTRL, + .reset = 0x2000c00, + .rsvd = 0xfdfc00f8, + },{ .name = "CRL_SAFETY_CHK", .addr = A_CRL_SAFETY_CHK, + },{ .name = "PSM_REF_CTRL", .addr = A_PSM_REF_CTRL, + .reset = 0xf04, + .rsvd = 0xfffc00f8, + },{ .name = "DBG_TSTMP_CTRL", .addr = A_DBG_TSTMP_CTRL, + .reset = 0x300, + .rsvd = 0xfdfc00f8, + },{ .name = "CPM_TOPSW_REF_CTRL", .addr = A_CPM_TOPSW_REF_CTRL, + .reset = 0x300, + .rsvd = 0xfdfc00f8, + },{ .name = "USB3_DUAL_REF_CTRL", .addr = A_USB3_DUAL_REF_CTRL, + .reset = 0x3c00, + .rsvd = 0xfdfc00f8, + },{ .name = "RST_CPU_R5", .addr = A_RST_CPU_R5, + .reset = 0x17, + .rsvd = 0x8, + .pre_write = crl_rst_r5_prew, + },{ .name = "RST_ADMA", .addr = A_RST_ADMA, + .reset = 0x1, + .pre_write = crl_rst_adma_prew, + },{ .name = "RST_GEM0", .addr = A_RST_GEM0, + .reset = 0x1, + .pre_write = crl_rst_gem0_prew, + },{ .name = "RST_GEM1", .addr = A_RST_GEM1, + .reset = 0x1, + .pre_write = crl_rst_gem1_prew, + },{ .name = "RST_SPARE", .addr = A_RST_SPARE, + .reset = 0x1, + },{ .name = "RST_USB0", .addr = A_RST_USB0, + .reset = 0x1, + .pre_write = crl_rst_usb_prew, + },{ .name = "RST_UART0", .addr = A_RST_UART0, + .reset = 0x1, + .pre_write = crl_rst_uart0_prew, + },{ .name = "RST_UART1", .addr = A_RST_UART1, + .reset = 0x1, + .pre_write = crl_rst_uart1_prew, + },{ .name = "RST_SPI0", .addr = A_RST_SPI0, + .reset = 0x1, + },{ .name = "RST_SPI1", .addr = A_RST_SPI1, + .reset = 0x1, + },{ .name = "RST_CAN0", .addr = A_RST_CAN0, + .reset = 0x1, + },{ .name = "RST_CAN1", .addr = A_RST_CAN1, + .reset = 0x1, + },{ .name = "RST_I2C0", .addr = A_RST_I2C0, + .reset = 0x1, + },{ .name = "RST_I2C1", .addr = A_RST_I2C1, + .reset = 0x1, + },{ .name = "RST_DBG_LPD", .addr = A_RST_DBG_LPD, + .reset = 0x33, + .rsvd = 0xcc, + },{ .name = "RST_GPIO", .addr = A_RST_GPIO, + .reset = 0x1, + },{ .name = "RST_TTC", .addr = A_RST_TTC, + .reset = 0xf, + },{ .name = "RST_TIMESTAMP", .addr = A_RST_TIMESTAMP, + .reset = 0x1, + },{ .name = "RST_SWDT", .addr = A_RST_SWDT, + .reset = 0x1, + },{ .name = "RST_OCM", .addr = A_RST_OCM, + },{ .name = "RST_IPI", .addr = A_RST_IPI, + },{ .name = "RST_FPD", .addr = A_RST_FPD, + .reset = 0x3, + },{ .name = "PSM_RST_MODE", .addr = A_PSM_RST_MODE, + .reset = 0x1, + .rsvd = 0xf8, + } +}; + +static void crl_reset_enter(Object *obj, ResetType type) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(obj); + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(s->regs_info); ++i) { + register_reset(&s->regs_info[i]); + } +} + +static void crl_reset_hold(Object *obj) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(obj); + + crl_update_irq(s); +} + +static const MemoryRegionOps crl_ops = { + .read = register_read_memory, + .write = register_write_memory, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void crl_init(Object *obj) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + int i; + + s->reg_array = + register_init_block32(DEVICE(obj), crl_regs_info, + ARRAY_SIZE(crl_regs_info), + s->regs_info, s->regs, + &crl_ops, + XLNX_VERSAL_CRL_ERR_DEBUG, + CRL_R_MAX * 4); + sysbus_init_mmio(sbd, &s->reg_array->mem); + sysbus_init_irq(sbd, &s->irq); + + for (i = 0; i < ARRAY_SIZE(s->cfg.cpu_r5); ++i) { + object_property_add_link(obj, "cpu_r5[*]", TYPE_ARM_CPU, + (Object **)&s->cfg.cpu_r5[i], + qdev_prop_allow_set_link_before_realize, + OBJ_PROP_LINK_STRONG); + } + + for (i = 0; i < ARRAY_SIZE(s->cfg.adma); ++i) { + object_property_add_link(obj, "adma[*]", TYPE_DEVICE, + (Object **)&s->cfg.adma[i], + qdev_prop_allow_set_link_before_realize, + OBJ_PROP_LINK_STRONG); + } + + for (i = 0; i < ARRAY_SIZE(s->cfg.uart); ++i) { + object_property_add_link(obj, "uart[*]", TYPE_DEVICE, + (Object **)&s->cfg.uart[i], + qdev_prop_allow_set_link_before_realize, + OBJ_PROP_LINK_STRONG); + } + + for (i = 0; i < ARRAY_SIZE(s->cfg.gem); ++i) { + object_property_add_link(obj, "gem[*]", TYPE_DEVICE, + (Object **)&s->cfg.gem[i], + qdev_prop_allow_set_link_before_realize, + OBJ_PROP_LINK_STRONG); + } + + object_property_add_link(obj, "usb", TYPE_DEVICE, + (Object **)&s->cfg.gem[i], + qdev_prop_allow_set_link_before_realize, + OBJ_PROP_LINK_STRONG); +} + +static void crl_finalize(Object *obj) +{ + XlnxVersalCRL *s = XLNX_VERSAL_CRL(obj); + register_finalize_block(s->reg_array); +} + +static const VMStateDescription vmstate_crl = { + .name = TYPE_XLNX_VERSAL_CRL, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, XlnxVersalCRL, CRL_R_MAX), + VMSTATE_END_OF_LIST(), + } +}; + +static void crl_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->vmsd = &vmstate_crl; + + rc->phases.enter = crl_reset_enter; + rc->phases.hold = crl_reset_hold; +} + +static const TypeInfo crl_info = { + .name = TYPE_XLNX_VERSAL_CRL, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(XlnxVersalCRL), + .class_init = crl_class_init, + .instance_init = crl_init, + .instance_finalize = crl_finalize, +}; + +static void crl_register_types(void) +{ + type_register_static(&crl_info); +} + +type_init(crl_register_types) diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_SLAVIO', if_true: files('slavio_misc.c')) softmmu_ss.add(when: 'CONFIG_ZYNQ', if_true: files('zynq_slcr.c')) specific_ss.add(when: 'CONFIG_XLNX_ZYNQMP_ARM', if_true: files('xlnx-zynqmp-crf.c')) specific_ss.add(when: 'CONFIG_XLNX_ZYNQMP_ARM', if_true: files('xlnx-zynqmp-apu-ctrl.c')) +specific_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files('xlnx-versal-crl.c')) softmmu_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files( 'xlnx-versal-xramc.c', 'xlnx-versal-pmc-iou-slcr.c', -- 2.25.1 From: "Edgar E. Iglesias" <edgar.iglesias@amd.com> Connect the CRL (Clock Reset LPD) to the Versal SoC. Signed-off-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Frederic Konrad <fkonrad@amd.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20220406174303.2022038-5-edgar.iglesias@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 4 +++ hw/arm/xlnx-versal.c | 54 ++++++++++++++++++++++++++++++++++-- 2 files changed, 56 insertions(+), 2 deletions(-) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ #include "hw/nvram/xlnx-versal-efuse.h" #include "hw/ssi/xlnx-versal-ospi.h" #include "hw/dma/xlnx_csu_dma.h" +#include "hw/misc/xlnx-versal-crl.h" #include "hw/misc/xlnx-versal-pmc-iou-slcr.h" #define TYPE_XLNX_VERSAL "xlnx-versal" @@ -XXX,XX +XXX,XX @@ struct Versal { qemu_or_irq irq_orgate; XlnxXramCtrl ctrl[XLNX_VERSAL_NR_XRAM]; } xram; + + XlnxVersalCRL crl; } lpd; /* The Platform Management Controller subsystem. */ @@ -XXX,XX +XXX,XX @@ struct Versal { #define VERSAL_TIMER_NS_EL1_IRQ 14 #define VERSAL_TIMER_NS_EL2_IRQ 10 +#define VERSAL_CRL_IRQ 10 #define VERSAL_UART0_IRQ_0 18 #define VERSAL_UART1_IRQ_0 19 #define VERSAL_USB0_IRQ_0 22 diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ static void versal_create_ospi(Versal *s, qemu_irq *pic) qdev_connect_gpio_out(orgate, 0, pic[VERSAL_OSPI_IRQ]); } +static void versal_create_crl(Versal *s, qemu_irq *pic) +{ + SysBusDevice *sbd; + int i; + + object_initialize_child(OBJECT(s), "crl", &s->lpd.crl, + TYPE_XLNX_VERSAL_CRL); + sbd = SYS_BUS_DEVICE(&s->lpd.crl); + + for (i = 0; i < ARRAY_SIZE(s->lpd.rpu.cpu); i++) { + g_autofree gchar *name = g_strdup_printf("cpu_r5[%d]", i); + + object_property_set_link(OBJECT(&s->lpd.crl), + name, OBJECT(&s->lpd.rpu.cpu[i]), + &error_abort); + } + + for (i = 0; i < ARRAY_SIZE(s->lpd.iou.gem); i++) { + g_autofree gchar *name = g_strdup_printf("gem[%d]", i); + + object_property_set_link(OBJECT(&s->lpd.crl), + name, OBJECT(&s->lpd.iou.gem[i]), + &error_abort); + } + + for (i = 0; i < ARRAY_SIZE(s->lpd.iou.adma); i++) { + g_autofree gchar *name = g_strdup_printf("adma[%d]", i); + + object_property_set_link(OBJECT(&s->lpd.crl), + name, OBJECT(&s->lpd.iou.adma[i]), + &error_abort); + } + + for (i = 0; i < ARRAY_SIZE(s->lpd.iou.uart); i++) { + g_autofree gchar *name = g_strdup_printf("uart[%d]", i); + + object_property_set_link(OBJECT(&s->lpd.crl), + name, OBJECT(&s->lpd.iou.uart[i]), + &error_abort); + } + + object_property_set_link(OBJECT(&s->lpd.crl), + "usb", OBJECT(&s->lpd.iou.usb), + &error_abort); + + sysbus_realize(sbd, &error_fatal); + memory_region_add_subregion(&s->mr_ps, MM_CRL, + sysbus_mmio_get_region(sbd, 0)); + sysbus_connect_irq(sbd, 0, pic[VERSAL_CRL_IRQ]); +} + /* This takes the board allocated linear DDR memory and creates aliases * for each split DDR range/aperture on the Versal address map. */ @@ -XXX,XX +XXX,XX @@ static void versal_unimp(Versal *s) versal_unimp_area(s, "psm", &s->mr_ps, MM_PSM_START, MM_PSM_END - MM_PSM_START); - versal_unimp_area(s, "crl", &s->mr_ps, - MM_CRL, MM_CRL_SIZE); versal_unimp_area(s, "crf", &s->mr_ps, MM_FPD_CRF, MM_FPD_CRF_SIZE); versal_unimp_area(s, "apu", &s->mr_ps, @@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp) versal_create_efuse(s, pic); versal_create_pmc_iou_slcr(s, pic); versal_create_ospi(s, pic); + versal_create_crl(s, pic); versal_map_ddr(s); versal_unimp(s); -- 2.25.1 The Exynos4210 SoC device currently uses a custom device "exynos4210.irq_gate" to model the OR gate that feeds each CPU's IRQ line. We have a standard TYPE_OR_IRQ device for this now, so use that instead. (This is a migration compatibility break, but that is OK for this machine type.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-2-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 1 + hw/arm/exynos4210.c | 31 ++++++++++++++++--------------- 2 files changed, 17 insertions(+), 15 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ struct Exynos4210State { MemoryRegion bootreg_mem; I2CBus *i2c_if[EXYNOS4210_I2C_NUMBER]; qemu_or_irq pl330_irq_orgate[EXYNOS4210_NUM_DMA]; + qemu_or_irq cpu_irq_orgate[EXYNOS4210_NCPUS]; }; #define TYPE_EXYNOS4210_SOC "exynos4210" 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 void exynos4210_realize(DeviceState *socdev, Error **errp) { Exynos4210State *s = EXYNOS4210_SOC(socdev); MemoryRegion *system_mem = get_system_memory(); - qemu_irq gate_irq[EXYNOS4210_NCPUS][EXYNOS4210_IRQ_GATE_NINPUTS]; SysBusDevice *busdev; DeviceState *dev, *uart[4], *pl330[3]; int i, n; @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) /* IRQ Gate */ for (i = 0; i < EXYNOS4210_NCPUS; i++) { - dev = qdev_new("exynos4210.irq_gate"); - qdev_prop_set_uint32(dev, "n_in", EXYNOS4210_IRQ_GATE_NINPUTS); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - /* Get IRQ Gate input in gate_irq */ - for (n = 0; n < EXYNOS4210_IRQ_GATE_NINPUTS; n++) { - gate_irq[i][n] = qdev_get_gpio_in(dev, n); - } - busdev = SYS_BUS_DEVICE(dev); - - /* Connect IRQ Gate output to CPU's IRQ line */ - sysbus_connect_irq(busdev, 0, - qdev_get_gpio_in(DEVICE(s->cpu[i]), ARM_CPU_IRQ)); + DeviceState *orgate = DEVICE(&s->cpu_irq_orgate[i]); + object_property_set_int(OBJECT(orgate), "num-lines", + EXYNOS4210_IRQ_GATE_NINPUTS, + &error_abort); + qdev_realize(orgate, NULL, &error_abort); + qdev_connect_gpio_out(orgate, 0, + qdev_get_gpio_in(DEVICE(s->cpu[i]), ARM_CPU_IRQ)); } /* Private memory region and Internal GIC */ @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) sysbus_realize_and_unref(busdev, &error_fatal); sysbus_mmio_map(busdev, 0, EXYNOS4210_SMP_PRIVATE_BASE_ADDR); for (n = 0; n < EXYNOS4210_NCPUS; n++) { - sysbus_connect_irq(busdev, n, gate_irq[n][0]); + sysbus_connect_irq(busdev, n, + qdev_get_gpio_in(DEVICE(&s->cpu_irq_orgate[n]), 0)); } for (n = 0; n < EXYNOS4210_INT_GIC_NIRQ; n++) { s->irqs.int_gic_irq[n] = qdev_get_gpio_in(dev, n); @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) /* Map Distributer interface */ sysbus_mmio_map(busdev, 1, EXYNOS4210_EXT_GIC_DIST_BASE_ADDR); for (n = 0; n < EXYNOS4210_NCPUS; n++) { - sysbus_connect_irq(busdev, n, gate_irq[n][1]); + sysbus_connect_irq(busdev, n, + qdev_get_gpio_in(DEVICE(&s->cpu_irq_orgate[n]), 1)); } for (n = 0; n < EXYNOS4210_EXT_GIC_NIRQ; n++) { s->irqs.ext_gic_irq[n] = qdev_get_gpio_in(dev, n); @@ -XXX,XX +XXX,XX @@ static void exynos4210_init(Object *obj) object_initialize_child(obj, name, orgate, TYPE_OR_IRQ); g_free(name); } + + for (i = 0; i < ARRAY_SIZE(s->cpu_irq_orgate); i++) { + g_autofree char *name = g_strdup_printf("cpu-irq-orgate%d", i); + object_initialize_child(obj, name, &s->cpu_irq_orgate[i], TYPE_OR_IRQ); + } } static void exynos4210_class_init(ObjectClass *klass, void *data) -- 2.25.1 Now we have removed the only use of TYPE_EXYNOS4210_IRQ_GATE we can delete the device entirely. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Francisco Iglesias <frasse.iglesias@gmail.com> Message-id: 20220404154658.565020-3-peter.maydell@linaro.org --- hw/intc/exynos4210_gic.c | 107 --------------------------------------- 1 file changed, 107 deletions(-) diff --git a/hw/intc/exynos4210_gic.c b/hw/intc/exynos4210_gic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/exynos4210_gic.c +++ b/hw/intc/exynos4210_gic.c @@ -XXX,XX +XXX,XX @@ static void exynos4210_gic_register_types(void) } type_init(exynos4210_gic_register_types) - -/* IRQ OR Gate struct. - * - * This device models an OR gate. There are n_in input qdev gpio lines and one - * output sysbus IRQ line. The output IRQ level is formed as OR between all - * gpio inputs. - */ - -#define TYPE_EXYNOS4210_IRQ_GATE "exynos4210.irq_gate" -OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210IRQGateState, EXYNOS4210_IRQ_GATE) - -struct Exynos4210IRQGateState { - SysBusDevice parent_obj; - - uint32_t n_in; /* inputs amount */ - uint32_t *level; /* input levels */ - qemu_irq out; /* output IRQ */ -}; - -static Property exynos4210_irq_gate_properties[] = { - DEFINE_PROP_UINT32("n_in", Exynos4210IRQGateState, n_in, 1), - DEFINE_PROP_END_OF_LIST(), -}; - -static const VMStateDescription vmstate_exynos4210_irq_gate = { - .name = "exynos4210.irq_gate", - .version_id = 2, - .minimum_version_id = 2, - .fields = (VMStateField[]) { - VMSTATE_VBUFFER_UINT32(level, Exynos4210IRQGateState, 1, NULL, n_in), - VMSTATE_END_OF_LIST() - } -}; - -/* Process a change in IRQ input. */ -static void exynos4210_irq_gate_handler(void *opaque, int irq, int level) -{ - Exynos4210IRQGateState *s = (Exynos4210IRQGateState *)opaque; - uint32_t i; - - assert(irq < s->n_in); - - s->level[irq] = level; - - for (i = 0; i < s->n_in; i++) { - if (s->level[i] >= 1) { - qemu_irq_raise(s->out); - return; - } - } - - qemu_irq_lower(s->out); -} - -static void exynos4210_irq_gate_reset(DeviceState *d) -{ - Exynos4210IRQGateState *s = EXYNOS4210_IRQ_GATE(d); - - memset(s->level, 0, s->n_in * sizeof(*s->level)); -} - -/* - * IRQ Gate initialization. - */ -static void exynos4210_irq_gate_init(Object *obj) -{ - Exynos4210IRQGateState *s = EXYNOS4210_IRQ_GATE(obj); - SysBusDevice *sbd = SYS_BUS_DEVICE(obj); - - sysbus_init_irq(sbd, &s->out); -} - -static void exynos4210_irq_gate_realize(DeviceState *dev, Error **errp) -{ - Exynos4210IRQGateState *s = EXYNOS4210_IRQ_GATE(dev); - - /* Allocate general purpose input signals and connect a handler to each of - * them */ - qdev_init_gpio_in(dev, exynos4210_irq_gate_handler, s->n_in); - - s->level = g_malloc0(s->n_in * sizeof(*s->level)); -} - -static void exynos4210_irq_gate_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - dc->reset = exynos4210_irq_gate_reset; - dc->vmsd = &vmstate_exynos4210_irq_gate; - device_class_set_props(dc, exynos4210_irq_gate_properties); - dc->realize = exynos4210_irq_gate_realize; -} - -static const TypeInfo exynos4210_irq_gate_info = { - .name = TYPE_EXYNOS4210_IRQ_GATE, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(Exynos4210IRQGateState), - .instance_init = exynos4210_irq_gate_init, - .class_init = exynos4210_irq_gate_class_init, -}; - -static void exynos4210_irq_gate_register_types(void) -{ - type_register_static(&exynos4210_irq_gate_info); -} - -type_init(exynos4210_irq_gate_register_types) -- 2.25.1 The exynos4210 SoC mostly creates its child devices as if it were board code. This includes the a9mpcore object. Switch that to a new-style "embedded in the state struct" creation, because in the next commit we're going to want to refer to the object again further down in the exynos4210_realize() function. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-4-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 2 ++ hw/arm/exynos4210.c | 11 ++++++----- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ #include "hw/or-irq.h" #include "hw/sysbus.h" +#include "hw/cpu/a9mpcore.h" #include "target/arm/cpu-qom.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct Exynos4210State { I2CBus *i2c_if[EXYNOS4210_I2C_NUMBER]; qemu_or_irq pl330_irq_orgate[EXYNOS4210_NUM_DMA]; qemu_or_irq cpu_irq_orgate[EXYNOS4210_NCPUS]; + A9MPPrivState a9mpcore; }; #define TYPE_EXYNOS4210_SOC "exynos4210" 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 void exynos4210_realize(DeviceState *socdev, Error **errp) } /* Private memory region and Internal GIC */ - dev = qdev_new(TYPE_A9MPCORE_PRIV); - qdev_prop_set_uint32(dev, "num-cpu", EXYNOS4210_NCPUS); - busdev = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(busdev, &error_fatal); + qdev_prop_set_uint32(DEVICE(&s->a9mpcore), "num-cpu", EXYNOS4210_NCPUS); + busdev = SYS_BUS_DEVICE(&s->a9mpcore); + sysbus_realize(busdev, &error_fatal); sysbus_mmio_map(busdev, 0, EXYNOS4210_SMP_PRIVATE_BASE_ADDR); for (n = 0; n < EXYNOS4210_NCPUS; n++) { sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->cpu_irq_orgate[n]), 0)); } for (n = 0; n < EXYNOS4210_INT_GIC_NIRQ; n++) { - s->irqs.int_gic_irq[n] = qdev_get_gpio_in(dev, n); + s->irqs.int_gic_irq[n] = qdev_get_gpio_in(DEVICE(&s->a9mpcore), n); } /* Cache controller */ @@ -XXX,XX +XXX,XX @@ static void exynos4210_init(Object *obj) g_autofree char *name = g_strdup_printf("cpu-irq-orgate%d", i); object_initialize_child(obj, name, &s->cpu_irq_orgate[i], TYPE_OR_IRQ); } + + object_initialize_child(obj, "a9mpcore", &s->a9mpcore, TYPE_A9MPCORE_PRIV); } static void exynos4210_class_init(ObjectClass *klass, void *data) -- 2.25.1 The only time we use the int_gic_irq[] array in the Exynos4210Irq struct is in the exynos4210_realize() function: we initialize it with the GPIO inputs of the a9mpcore device, and then a bit later on we connect those to the outputs of the internal combiner. Now that the a9mpcore object is easily accessible as s->a9mpcore we can make the connection directly from one device to the other without going via this array. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-5-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 1 - hw/arm/exynos4210.c | 6 ++---- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ typedef struct Exynos4210Irq { qemu_irq int_combiner_irq[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; qemu_irq ext_combiner_irq[EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ]; - qemu_irq int_gic_irq[EXYNOS4210_INT_GIC_NIRQ]; qemu_irq ext_gic_irq[EXYNOS4210_EXT_GIC_NIRQ]; qemu_irq board_irqs[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; } Exynos4210Irq; 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 void exynos4210_realize(DeviceState *socdev, Error **errp) sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->cpu_irq_orgate[n]), 0)); } - for (n = 0; n < EXYNOS4210_INT_GIC_NIRQ; n++) { - s->irqs.int_gic_irq[n] = qdev_get_gpio_in(DEVICE(&s->a9mpcore), n); - } /* Cache controller */ sysbus_create_simple("l2x0", EXYNOS4210_L2X0_BASE_ADDR, NULL); @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) busdev = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(busdev, &error_fatal); for (n = 0; n < EXYNOS4210_MAX_INT_COMBINER_OUT_IRQ; n++) { - sysbus_connect_irq(busdev, n, s->irqs.int_gic_irq[n]); + sysbus_connect_irq(busdev, n, + qdev_get_gpio_in(DEVICE(&s->a9mpcore), n)); } exynos4210_combiner_get_gpioin(&s->irqs, dev, 0); sysbus_mmio_map(busdev, 0, EXYNOS4210_INT_COMBINER_BASE_ADDR); -- 2.25.1 The exynos4210 code currently has two very similar arrays of IRQs: * board_irqs is a field of the Exynos4210Irq struct which is filled in by exynos4210_init_board_irqs() with the appropriate qemu_irqs for each IRQ the board/SoC can assert * irq_table is a set of qemu_irqs pointed to from the Exynos4210State struct. It's allocated in exynos4210_init_irq, and the only behaviour these irqs have is that they pass on the level to the equivalent board_irqs[] irq The extra indirection through irq_table is unnecessary, so coalesce these into a single irq_table[] array as a direct field in Exynos4210State which exynos4210_init_board_irqs() fills in. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-6-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 8 ++------ hw/arm/exynos4210.c | 6 +----- hw/intc/exynos4210_gic.c | 32 ++++++++------------------------ 3 files changed, 11 insertions(+), 35 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ typedef struct Exynos4210Irq { qemu_irq int_combiner_irq[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; qemu_irq ext_combiner_irq[EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ]; qemu_irq ext_gic_irq[EXYNOS4210_EXT_GIC_NIRQ]; - qemu_irq board_irqs[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; } Exynos4210Irq; struct Exynos4210State { @@ -XXX,XX +XXX,XX @@ struct Exynos4210State { /*< public >*/ ARMCPU *cpu[EXYNOS4210_NCPUS]; Exynos4210Irq irqs; - qemu_irq *irq_table; + qemu_irq irq_table[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; MemoryRegion chipid_mem; MemoryRegion iram_mem; @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210State, EXYNOS4210_SOC) void exynos4210_write_secondary(ARMCPU *cpu, const struct arm_boot_info *info); -/* Initialize exynos4210 IRQ subsystem stub */ -qemu_irq *exynos4210_init_irq(Exynos4210Irq *env); - /* Initialize board IRQs. * These IRQs contain splitted Int/External Combiner and External Gic IRQs */ -void exynos4210_init_board_irqs(Exynos4210Irq *s); +void exynos4210_init_board_irqs(Exynos4210State *s); /* Get IRQ number from exynos4210 IRQ subsystem stub. * To identify IRQ source use internal combiner group and bit number 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 void exynos4210_realize(DeviceState *socdev, Error **errp) qdev_realize(DEVICE(cpuobj), NULL, &error_fatal); } - /*** IRQs ***/ - - s->irq_table = exynos4210_init_irq(&s->irqs); - /* IRQ Gate */ for (i = 0; i < EXYNOS4210_NCPUS; i++) { DeviceState *orgate = DEVICE(&s->cpu_irq_orgate[i]); @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) sysbus_mmio_map(busdev, 0, EXYNOS4210_EXT_COMBINER_BASE_ADDR); /* Initialize board IRQs. */ - exynos4210_init_board_irqs(&s->irqs); + exynos4210_init_board_irqs(s); /*** Memory ***/ diff --git a/hw/intc/exynos4210_gic.c b/hw/intc/exynos4210_gic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/exynos4210_gic.c +++ b/hw/intc/exynos4210_gic.c @@ -XXX,XX +XXX,XX @@ combiner_grp_to_gic_id[64-EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { #define EXYNOS4210_GIC_CPU_REGION_SIZE 0x100 #define EXYNOS4210_GIC_DIST_REGION_SIZE 0x1000 -static void exynos4210_irq_handler(void *opaque, int irq, int level) -{ - Exynos4210Irq *s = (Exynos4210Irq *)opaque; - - /* Bypass */ - qemu_set_irq(s->board_irqs[irq], level); -} - -/* - * Initialize exynos4210 IRQ subsystem stub. - */ -qemu_irq *exynos4210_init_irq(Exynos4210Irq *s) -{ - return qemu_allocate_irqs(exynos4210_irq_handler, s, - EXYNOS4210_MAX_INT_COMBINER_IN_IRQ); -} - /* * Initialize board IRQs. * These IRQs contain splitted Int/External Combiner and External Gic IRQs. */ -void exynos4210_init_board_irqs(Exynos4210Irq *s) +void exynos4210_init_board_irqs(Exynos4210State *s) { uint32_t grp, bit, irq_id, n; + Exynos4210Irq *is = &s->irqs; for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { irq_id = 0; @@ -XXX,XX +XXX,XX @@ void exynos4210_init_board_irqs(Exynos4210Irq *s) irq_id = EXT_GIC_ID_MCT_G1; } if (irq_id) { - s->board_irqs[n] = qemu_irq_split(s->int_combiner_irq[n], - s->ext_gic_irq[irq_id-32]); + s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], + is->ext_gic_irq[irq_id - 32]); } else { - s->board_irqs[n] = qemu_irq_split(s->int_combiner_irq[n], - s->ext_combiner_irq[n]); + s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], + is->ext_combiner_irq[n]); } } for (; n < EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; n++) { @@ -XXX,XX +XXX,XX @@ void exynos4210_init_board_irqs(Exynos4210Irq *s) EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][bit]; if (irq_id) { - s->board_irqs[n] = qemu_irq_split(s->int_combiner_irq[n], - s->ext_gic_irq[irq_id-32]); + s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], + is->ext_gic_irq[irq_id - 32]); } } } -- 2.25.1 Fix a missing set of spaces around '-' in the definition of combiner_grp_to_gic_id[]. We're about to move this code, so fix the style issue first to keep checkpatch happy with the code-motion patch. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-7-peter.maydell@linaro.org --- hw/intc/exynos4210_gic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/intc/exynos4210_gic.c b/hw/intc/exynos4210_gic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/exynos4210_gic.c +++ b/hw/intc/exynos4210_gic.c @@ -XXX,XX +XXX,XX @@ enum ExtInt { */ static const uint32_t -combiner_grp_to_gic_id[64-EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { +combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { /* int combiner groups 16-19 */ { }, { }, { }, { }, /* int combiner group 20 */ -- 2.25.1 The function exynos4210_init_board_irqs() currently lives in exynos4210_gic.c, but it isn't really part of the exynos4210.gic device -- it is a function that implements (some of) the wiring up of interrupts between the SoC's GIC and combiner components. This means it fits better in exynos4210.c, which is the SoC-level code. Move it there. Similarly, exynos4210_git_irq() is used almost only in the SoC-level code, so move it too. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-8-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 4 - hw/arm/exynos4210.c | 202 +++++++++++++++++++++++++++++++++++ hw/intc/exynos4210_gic.c | 204 ------------------------------------ 3 files changed, 202 insertions(+), 208 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210State, EXYNOS4210_SOC) void exynos4210_write_secondary(ARMCPU *cpu, const struct arm_boot_info *info); -/* Initialize board IRQs. - * These IRQs contain splitted Int/External Combiner and External Gic IRQs */ -void exynos4210_init_board_irqs(Exynos4210State *s); - /* Get IRQ number from exynos4210 IRQ subsystem stub. * To identify IRQ source use internal combiner group and bit number * grp - group number 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 @@ #define EXYNOS4210_PL330_BASE1_ADDR 0x12690000 #define EXYNOS4210_PL330_BASE2_ADDR 0x12850000 +enum ExtGicId { + EXT_GIC_ID_MDMA_LCD0 = 66, + EXT_GIC_ID_PDMA0, + EXT_GIC_ID_PDMA1, + EXT_GIC_ID_TIMER0, + EXT_GIC_ID_TIMER1, + EXT_GIC_ID_TIMER2, + EXT_GIC_ID_TIMER3, + EXT_GIC_ID_TIMER4, + EXT_GIC_ID_MCT_L0, + EXT_GIC_ID_WDT, + EXT_GIC_ID_RTC_ALARM, + EXT_GIC_ID_RTC_TIC, + EXT_GIC_ID_GPIO_XB, + EXT_GIC_ID_GPIO_XA, + EXT_GIC_ID_MCT_L1, + EXT_GIC_ID_IEM_APC, + EXT_GIC_ID_IEM_IEC, + EXT_GIC_ID_NFC, + EXT_GIC_ID_UART0, + EXT_GIC_ID_UART1, + EXT_GIC_ID_UART2, + EXT_GIC_ID_UART3, + EXT_GIC_ID_UART4, + EXT_GIC_ID_MCT_G0, + EXT_GIC_ID_I2C0, + EXT_GIC_ID_I2C1, + EXT_GIC_ID_I2C2, + EXT_GIC_ID_I2C3, + EXT_GIC_ID_I2C4, + EXT_GIC_ID_I2C5, + EXT_GIC_ID_I2C6, + EXT_GIC_ID_I2C7, + EXT_GIC_ID_SPI0, + EXT_GIC_ID_SPI1, + EXT_GIC_ID_SPI2, + EXT_GIC_ID_MCT_G1, + EXT_GIC_ID_USB_HOST, + EXT_GIC_ID_USB_DEVICE, + EXT_GIC_ID_MODEMIF, + EXT_GIC_ID_HSMMC0, + EXT_GIC_ID_HSMMC1, + EXT_GIC_ID_HSMMC2, + EXT_GIC_ID_HSMMC3, + EXT_GIC_ID_SDMMC, + EXT_GIC_ID_MIPI_CSI_4LANE, + EXT_GIC_ID_MIPI_DSI_4LANE, + EXT_GIC_ID_MIPI_CSI_2LANE, + EXT_GIC_ID_MIPI_DSI_2LANE, + EXT_GIC_ID_ONENAND_AUDI, + EXT_GIC_ID_ROTATOR, + EXT_GIC_ID_FIMC0, + EXT_GIC_ID_FIMC1, + EXT_GIC_ID_FIMC2, + EXT_GIC_ID_FIMC3, + EXT_GIC_ID_JPEG, + EXT_GIC_ID_2D, + EXT_GIC_ID_PCIe, + EXT_GIC_ID_MIXER, + EXT_GIC_ID_HDMI, + EXT_GIC_ID_HDMI_I2C, + EXT_GIC_ID_MFC, + EXT_GIC_ID_TVENC, +}; + +enum ExtInt { + EXT_GIC_ID_EXTINT0 = 48, + EXT_GIC_ID_EXTINT1, + EXT_GIC_ID_EXTINT2, + EXT_GIC_ID_EXTINT3, + EXT_GIC_ID_EXTINT4, + EXT_GIC_ID_EXTINT5, + EXT_GIC_ID_EXTINT6, + EXT_GIC_ID_EXTINT7, + EXT_GIC_ID_EXTINT8, + EXT_GIC_ID_EXTINT9, + EXT_GIC_ID_EXTINT10, + EXT_GIC_ID_EXTINT11, + EXT_GIC_ID_EXTINT12, + EXT_GIC_ID_EXTINT13, + EXT_GIC_ID_EXTINT14, + EXT_GIC_ID_EXTINT15 +}; + +/* + * External GIC sources which are not from External Interrupt Combiner or + * External Interrupts are starting from EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ, + * which is INTG16 in Internal Interrupt Combiner. + */ + +static const uint32_t +combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { + /* int combiner groups 16-19 */ + { }, { }, { }, { }, + /* int combiner group 20 */ + { 0, EXT_GIC_ID_MDMA_LCD0 }, + /* int combiner group 21 */ + { EXT_GIC_ID_PDMA0, EXT_GIC_ID_PDMA1 }, + /* int combiner group 22 */ + { EXT_GIC_ID_TIMER0, EXT_GIC_ID_TIMER1, EXT_GIC_ID_TIMER2, + EXT_GIC_ID_TIMER3, EXT_GIC_ID_TIMER4 }, + /* int combiner group 23 */ + { EXT_GIC_ID_RTC_ALARM, EXT_GIC_ID_RTC_TIC }, + /* int combiner group 24 */ + { EXT_GIC_ID_GPIO_XB, EXT_GIC_ID_GPIO_XA }, + /* int combiner group 25 */ + { EXT_GIC_ID_IEM_APC, EXT_GIC_ID_IEM_IEC }, + /* int combiner group 26 */ + { EXT_GIC_ID_UART0, EXT_GIC_ID_UART1, EXT_GIC_ID_UART2, EXT_GIC_ID_UART3, + EXT_GIC_ID_UART4 }, + /* int combiner group 27 */ + { EXT_GIC_ID_I2C0, EXT_GIC_ID_I2C1, EXT_GIC_ID_I2C2, EXT_GIC_ID_I2C3, + EXT_GIC_ID_I2C4, EXT_GIC_ID_I2C5, EXT_GIC_ID_I2C6, + EXT_GIC_ID_I2C7 }, + /* int combiner group 28 */ + { EXT_GIC_ID_SPI0, EXT_GIC_ID_SPI1, EXT_GIC_ID_SPI2 , EXT_GIC_ID_USB_HOST}, + /* int combiner group 29 */ + { EXT_GIC_ID_HSMMC0, EXT_GIC_ID_HSMMC1, EXT_GIC_ID_HSMMC2, + EXT_GIC_ID_HSMMC3, EXT_GIC_ID_SDMMC }, + /* int combiner group 30 */ + { EXT_GIC_ID_MIPI_CSI_4LANE, EXT_GIC_ID_MIPI_CSI_2LANE }, + /* int combiner group 31 */ + { EXT_GIC_ID_MIPI_DSI_4LANE, EXT_GIC_ID_MIPI_DSI_2LANE }, + /* int combiner group 32 */ + { EXT_GIC_ID_FIMC0, EXT_GIC_ID_FIMC1 }, + /* int combiner group 33 */ + { EXT_GIC_ID_FIMC2, EXT_GIC_ID_FIMC3 }, + /* int combiner group 34 */ + { EXT_GIC_ID_ONENAND_AUDI, EXT_GIC_ID_NFC }, + /* int combiner group 35 */ + { 0, 0, 0, EXT_GIC_ID_MCT_L1, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, + /* int combiner group 36 */ + { EXT_GIC_ID_MIXER }, + /* int combiner group 37 */ + { EXT_GIC_ID_EXTINT4, EXT_GIC_ID_EXTINT5, EXT_GIC_ID_EXTINT6, + EXT_GIC_ID_EXTINT7 }, + /* groups 38-50 */ + { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, + /* int combiner group 51 */ + { EXT_GIC_ID_MCT_L0, 0, 0, 0, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, + /* group 52 */ + { }, + /* int combiner group 53 */ + { EXT_GIC_ID_WDT, 0, 0, 0, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, + /* groups 54-63 */ + { }, { }, { }, { }, { }, { }, { }, { }, { }, { } +}; + +/* + * Initialize board IRQs. + * These IRQs contain splitted Int/External Combiner and External Gic IRQs. + */ +static void exynos4210_init_board_irqs(Exynos4210State *s) +{ + uint32_t grp, bit, irq_id, n; + Exynos4210Irq *is = &s->irqs; + + for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { + irq_id = 0; + if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 4) || + n == EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 4)) { + /* MCT_G0 is passed to External GIC */ + irq_id = EXT_GIC_ID_MCT_G0; + } + if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 5) || + n == EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 5)) { + /* MCT_G1 is passed to External and GIC */ + irq_id = EXT_GIC_ID_MCT_G1; + } + if (irq_id) { + s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], + is->ext_gic_irq[irq_id - 32]); + } else { + s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], + is->ext_combiner_irq[n]); + } + } + for (; n < EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; n++) { + /* these IDs are passed to Internal Combiner and External GIC */ + grp = EXYNOS4210_COMBINER_GET_GRP_NUM(n); + bit = EXYNOS4210_COMBINER_GET_BIT_NUM(n); + irq_id = combiner_grp_to_gic_id[grp - + EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][bit]; + + if (irq_id) { + s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], + is->ext_gic_irq[irq_id - 32]); + } + } +} + +/* + * Get IRQ number from exynos4210 IRQ subsystem stub. + * To identify IRQ source use internal combiner group and bit number + * grp - group number + * bit - bit number inside group + */ +uint32_t exynos4210_get_irq(uint32_t grp, uint32_t bit) +{ + return EXYNOS4210_COMBINER_GET_IRQ_NUM(grp, bit); +} + static uint8_t chipid_and_omr[] = { 0x11, 0x02, 0x21, 0x43, 0x09, 0x00, 0x00, 0x00 }; diff --git a/hw/intc/exynos4210_gic.c b/hw/intc/exynos4210_gic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/exynos4210_gic.c +++ b/hw/intc/exynos4210_gic.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/exynos4210.h" #include "qom/object.h" -enum ExtGicId { - EXT_GIC_ID_MDMA_LCD0 = 66, - EXT_GIC_ID_PDMA0, - EXT_GIC_ID_PDMA1, - EXT_GIC_ID_TIMER0, - EXT_GIC_ID_TIMER1, - EXT_GIC_ID_TIMER2, - EXT_GIC_ID_TIMER3, - EXT_GIC_ID_TIMER4, - EXT_GIC_ID_MCT_L0, - EXT_GIC_ID_WDT, - EXT_GIC_ID_RTC_ALARM, - EXT_GIC_ID_RTC_TIC, - EXT_GIC_ID_GPIO_XB, - EXT_GIC_ID_GPIO_XA, - EXT_GIC_ID_MCT_L1, - EXT_GIC_ID_IEM_APC, - EXT_GIC_ID_IEM_IEC, - EXT_GIC_ID_NFC, - EXT_GIC_ID_UART0, - EXT_GIC_ID_UART1, - EXT_GIC_ID_UART2, - EXT_GIC_ID_UART3, - EXT_GIC_ID_UART4, - EXT_GIC_ID_MCT_G0, - EXT_GIC_ID_I2C0, - EXT_GIC_ID_I2C1, - EXT_GIC_ID_I2C2, - EXT_GIC_ID_I2C3, - EXT_GIC_ID_I2C4, - EXT_GIC_ID_I2C5, - EXT_GIC_ID_I2C6, - EXT_GIC_ID_I2C7, - EXT_GIC_ID_SPI0, - EXT_GIC_ID_SPI1, - EXT_GIC_ID_SPI2, - EXT_GIC_ID_MCT_G1, - EXT_GIC_ID_USB_HOST, - EXT_GIC_ID_USB_DEVICE, - EXT_GIC_ID_MODEMIF, - EXT_GIC_ID_HSMMC0, - EXT_GIC_ID_HSMMC1, - EXT_GIC_ID_HSMMC2, - EXT_GIC_ID_HSMMC3, - EXT_GIC_ID_SDMMC, - EXT_GIC_ID_MIPI_CSI_4LANE, - EXT_GIC_ID_MIPI_DSI_4LANE, - EXT_GIC_ID_MIPI_CSI_2LANE, - EXT_GIC_ID_MIPI_DSI_2LANE, - EXT_GIC_ID_ONENAND_AUDI, - EXT_GIC_ID_ROTATOR, - EXT_GIC_ID_FIMC0, - EXT_GIC_ID_FIMC1, - EXT_GIC_ID_FIMC2, - EXT_GIC_ID_FIMC3, - EXT_GIC_ID_JPEG, - EXT_GIC_ID_2D, - EXT_GIC_ID_PCIe, - EXT_GIC_ID_MIXER, - EXT_GIC_ID_HDMI, - EXT_GIC_ID_HDMI_I2C, - EXT_GIC_ID_MFC, - EXT_GIC_ID_TVENC, -}; - -enum ExtInt { - EXT_GIC_ID_EXTINT0 = 48, - EXT_GIC_ID_EXTINT1, - EXT_GIC_ID_EXTINT2, - EXT_GIC_ID_EXTINT3, - EXT_GIC_ID_EXTINT4, - EXT_GIC_ID_EXTINT5, - EXT_GIC_ID_EXTINT6, - EXT_GIC_ID_EXTINT7, - EXT_GIC_ID_EXTINT8, - EXT_GIC_ID_EXTINT9, - EXT_GIC_ID_EXTINT10, - EXT_GIC_ID_EXTINT11, - EXT_GIC_ID_EXTINT12, - EXT_GIC_ID_EXTINT13, - EXT_GIC_ID_EXTINT14, - EXT_GIC_ID_EXTINT15 -}; - -/* - * External GIC sources which are not from External Interrupt Combiner or - * External Interrupts are starting from EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ, - * which is INTG16 in Internal Interrupt Combiner. - */ - -static const uint32_t -combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { - /* int combiner groups 16-19 */ - { }, { }, { }, { }, - /* int combiner group 20 */ - { 0, EXT_GIC_ID_MDMA_LCD0 }, - /* int combiner group 21 */ - { EXT_GIC_ID_PDMA0, EXT_GIC_ID_PDMA1 }, - /* int combiner group 22 */ - { EXT_GIC_ID_TIMER0, EXT_GIC_ID_TIMER1, EXT_GIC_ID_TIMER2, - EXT_GIC_ID_TIMER3, EXT_GIC_ID_TIMER4 }, - /* int combiner group 23 */ - { EXT_GIC_ID_RTC_ALARM, EXT_GIC_ID_RTC_TIC }, - /* int combiner group 24 */ - { EXT_GIC_ID_GPIO_XB, EXT_GIC_ID_GPIO_XA }, - /* int combiner group 25 */ - { EXT_GIC_ID_IEM_APC, EXT_GIC_ID_IEM_IEC }, - /* int combiner group 26 */ - { EXT_GIC_ID_UART0, EXT_GIC_ID_UART1, EXT_GIC_ID_UART2, EXT_GIC_ID_UART3, - EXT_GIC_ID_UART4 }, - /* int combiner group 27 */ - { EXT_GIC_ID_I2C0, EXT_GIC_ID_I2C1, EXT_GIC_ID_I2C2, EXT_GIC_ID_I2C3, - EXT_GIC_ID_I2C4, EXT_GIC_ID_I2C5, EXT_GIC_ID_I2C6, - EXT_GIC_ID_I2C7 }, - /* int combiner group 28 */ - { EXT_GIC_ID_SPI0, EXT_GIC_ID_SPI1, EXT_GIC_ID_SPI2 , EXT_GIC_ID_USB_HOST}, - /* int combiner group 29 */ - { EXT_GIC_ID_HSMMC0, EXT_GIC_ID_HSMMC1, EXT_GIC_ID_HSMMC2, - EXT_GIC_ID_HSMMC3, EXT_GIC_ID_SDMMC }, - /* int combiner group 30 */ - { EXT_GIC_ID_MIPI_CSI_4LANE, EXT_GIC_ID_MIPI_CSI_2LANE }, - /* int combiner group 31 */ - { EXT_GIC_ID_MIPI_DSI_4LANE, EXT_GIC_ID_MIPI_DSI_2LANE }, - /* int combiner group 32 */ - { EXT_GIC_ID_FIMC0, EXT_GIC_ID_FIMC1 }, - /* int combiner group 33 */ - { EXT_GIC_ID_FIMC2, EXT_GIC_ID_FIMC3 }, - /* int combiner group 34 */ - { EXT_GIC_ID_ONENAND_AUDI, EXT_GIC_ID_NFC }, - /* int combiner group 35 */ - { 0, 0, 0, EXT_GIC_ID_MCT_L1, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, - /* int combiner group 36 */ - { EXT_GIC_ID_MIXER }, - /* int combiner group 37 */ - { EXT_GIC_ID_EXTINT4, EXT_GIC_ID_EXTINT5, EXT_GIC_ID_EXTINT6, - EXT_GIC_ID_EXTINT7 }, - /* groups 38-50 */ - { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, - /* int combiner group 51 */ - { EXT_GIC_ID_MCT_L0, 0, 0, 0, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, - /* group 52 */ - { }, - /* int combiner group 53 */ - { EXT_GIC_ID_WDT, 0, 0, 0, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, - /* groups 54-63 */ - { }, { }, { }, { }, { }, { }, { }, { }, { }, { } -}; - #define EXYNOS4210_GIC_NIRQ 160 #define EXYNOS4210_EXT_GIC_CPU_REGION_SIZE 0x10000 @@ -XXX,XX +XXX,XX @@ combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { #define EXYNOS4210_GIC_CPU_REGION_SIZE 0x100 #define EXYNOS4210_GIC_DIST_REGION_SIZE 0x1000 -/* - * Initialize board IRQs. - * These IRQs contain splitted Int/External Combiner and External Gic IRQs. - */ -void exynos4210_init_board_irqs(Exynos4210State *s) -{ - uint32_t grp, bit, irq_id, n; - Exynos4210Irq *is = &s->irqs; - - for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { - irq_id = 0; - if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 4) || - n == EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 4)) { - /* MCT_G0 is passed to External GIC */ - irq_id = EXT_GIC_ID_MCT_G0; - } - if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 5) || - n == EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 5)) { - /* MCT_G1 is passed to External and GIC */ - irq_id = EXT_GIC_ID_MCT_G1; - } - if (irq_id) { - s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - is->ext_gic_irq[irq_id - 32]); - } else { - s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - is->ext_combiner_irq[n]); - } - } - for (; n < EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; n++) { - /* these IDs are passed to Internal Combiner and External GIC */ - grp = EXYNOS4210_COMBINER_GET_GRP_NUM(n); - bit = EXYNOS4210_COMBINER_GET_BIT_NUM(n); - irq_id = combiner_grp_to_gic_id[grp - - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][bit]; - - if (irq_id) { - s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - is->ext_gic_irq[irq_id - 32]); - } - } -} - -/* - * Get IRQ number from exynos4210 IRQ subsystem stub. - * To identify IRQ source use internal combiner group and bit number - * grp - group number - * bit - bit number inside group - */ -uint32_t exynos4210_get_irq(uint32_t grp, uint32_t bit) -{ - return EXYNOS4210_COMBINER_GET_IRQ_NUM(grp, bit); -} - -/********* GIC part *********/ - #define TYPE_EXYNOS4210_GIC "exynos4210.gic" OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210GicState, EXYNOS4210_GIC) -- 2.25.1 Switch the creation of the external GIC to the new-style "embedded in state struct" approach, so we can easily refer to the object elsewhere during realize. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-9-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 2 ++ include/hw/intc/exynos4210_gic.h | 43 ++++++++++++++++++++++++++++++++ hw/arm/exynos4210.c | 10 ++++---- hw/intc/exynos4210_gic.c | 17 ++----------- MAINTAINERS | 2 +- 5 files changed, 53 insertions(+), 21 deletions(-) create mode 100644 include/hw/intc/exynos4210_gic.h diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ #include "hw/or-irq.h" #include "hw/sysbus.h" #include "hw/cpu/a9mpcore.h" +#include "hw/intc/exynos4210_gic.h" #include "target/arm/cpu-qom.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct Exynos4210State { qemu_or_irq pl330_irq_orgate[EXYNOS4210_NUM_DMA]; qemu_or_irq cpu_irq_orgate[EXYNOS4210_NCPUS]; A9MPPrivState a9mpcore; + Exynos4210GicState ext_gic; }; #define TYPE_EXYNOS4210_SOC "exynos4210" diff --git a/include/hw/intc/exynos4210_gic.h b/include/hw/intc/exynos4210_gic.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/intc/exynos4210_gic.h @@ -XXX,XX +XXX,XX @@ +/* + * Samsung exynos4210 GIC implementation. Based on hw/arm_gic.c + * + * Copyright (c) 2000 - 2011 Samsung Electronics Co., Ltd. + * All rights reserved. + * + * Evgeny Voevodin <e.voevodin@samsung.com> + * + * 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/>. + */ +#ifndef HW_INTC_EXYNOS4210_GIC_H +#define HW_INTC_EXYNOS4210_GIC_H + +#include "hw/sysbus.h" + +#define TYPE_EXYNOS4210_GIC "exynos4210.gic" +OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210GicState, EXYNOS4210_GIC) + +#define EXYNOS4210_GIC_NCPUS 2 + +struct Exynos4210GicState { + SysBusDevice parent_obj; + + MemoryRegion cpu_container; + MemoryRegion dist_container; + MemoryRegion cpu_alias[EXYNOS4210_GIC_NCPUS]; + MemoryRegion dist_alias[EXYNOS4210_GIC_NCPUS]; + uint32_t num_cpu; + DeviceState *gic; +}; + +#endif 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 void exynos4210_realize(DeviceState *socdev, Error **errp) sysbus_create_simple("l2x0", EXYNOS4210_L2X0_BASE_ADDR, NULL); /* External GIC */ - dev = qdev_new("exynos4210.gic"); - qdev_prop_set_uint32(dev, "num-cpu", EXYNOS4210_NCPUS); - busdev = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(busdev, &error_fatal); + qdev_prop_set_uint32(DEVICE(&s->ext_gic), "num-cpu", EXYNOS4210_NCPUS); + busdev = SYS_BUS_DEVICE(&s->ext_gic); + sysbus_realize(busdev, &error_fatal); /* Map CPU interface */ sysbus_mmio_map(busdev, 0, EXYNOS4210_EXT_GIC_CPU_BASE_ADDR); /* Map Distributer interface */ @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) qdev_get_gpio_in(DEVICE(&s->cpu_irq_orgate[n]), 1)); } for (n = 0; n < EXYNOS4210_EXT_GIC_NIRQ; n++) { - s->irqs.ext_gic_irq[n] = qdev_get_gpio_in(dev, n); + s->irqs.ext_gic_irq[n] = qdev_get_gpio_in(DEVICE(&s->ext_gic), n); } /* Internal Interrupt Combiner */ @@ -XXX,XX +XXX,XX @@ static void exynos4210_init(Object *obj) } object_initialize_child(obj, "a9mpcore", &s->a9mpcore, TYPE_A9MPCORE_PRIV); + object_initialize_child(obj, "ext-gic", &s->ext_gic, TYPE_EXYNOS4210_GIC); } static void exynos4210_class_init(ObjectClass *klass, void *data) diff --git a/hw/intc/exynos4210_gic.c b/hw/intc/exynos4210_gic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/exynos4210_gic.c +++ b/hw/intc/exynos4210_gic.c @@ -XXX,XX +XXX,XX @@ #include "qemu/module.h" #include "hw/irq.h" #include "hw/qdev-properties.h" +#include "hw/intc/exynos4210_gic.h" #include "hw/arm/exynos4210.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ #define EXYNOS4210_GIC_CPU_REGION_SIZE 0x100 #define EXYNOS4210_GIC_DIST_REGION_SIZE 0x1000 -#define TYPE_EXYNOS4210_GIC "exynos4210.gic" -OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210GicState, EXYNOS4210_GIC) - -struct Exynos4210GicState { - SysBusDevice parent_obj; - - MemoryRegion cpu_container; - MemoryRegion dist_container; - MemoryRegion cpu_alias[EXYNOS4210_NCPUS]; - MemoryRegion dist_alias[EXYNOS4210_NCPUS]; - uint32_t num_cpu; - DeviceState *gic; -}; - static void exynos4210_gic_set_irq(void *opaque, int irq, int level) { Exynos4210GicState *s = (Exynos4210GicState *)opaque; @@ -XXX,XX +XXX,XX @@ static void exynos4210_gic_realize(DeviceState *dev, Error **errp) * enough room for the cpu numbers. gcc 9.2.1 on 32-bit x86 * doesn't figure this out, otherwise and gives spurious warnings. */ - assert(n <= EXYNOS4210_NCPUS); + assert(n <= EXYNOS4210_GIC_NCPUS); for (i = 0; i < n; i++) { /* Map CPU interface per SMP Core */ sprintf(cpu_alias_name, "%s%x", cpu_prefix, i); diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Peter Maydell <peter.maydell@linaro.org> L: qemu-arm@nongnu.org S: Odd Fixes F: hw/*/exynos* -F: include/hw/arm/exynos4210.h +F: include/hw/*/exynos* Calxeda Highbank M: Rob Herring <robh@kernel.org> -- 2.25.1 The only time we use the ext_gic_irq[] array in the Exynos4210Irq struct is during realize of the SoC -- we initialize it with the input IRQs of the external GIC device, and then connect those to outputs of other devices further on in realize (including in the exynos4210_init_board_irqs() function). Now that the ext_gic object is easily accessible as s->ext_gic we can make the connections directly from one device to the other without going via this array. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-10-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 1 - hw/arm/exynos4210.c | 12 ++++++------ 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ typedef struct Exynos4210Irq { qemu_irq int_combiner_irq[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; qemu_irq ext_combiner_irq[EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ]; - qemu_irq ext_gic_irq[EXYNOS4210_EXT_GIC_NIRQ]; } Exynos4210Irq; struct Exynos4210State { 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 void exynos4210_init_board_irqs(Exynos4210State *s) { uint32_t grp, bit, irq_id, n; Exynos4210Irq *is = &s->irqs; + DeviceState *extgicdev = DEVICE(&s->ext_gic); for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { irq_id = 0; @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) } if (irq_id) { s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - is->ext_gic_irq[irq_id - 32]); + qdev_get_gpio_in(extgicdev, + irq_id - 32)); } else { s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], is->ext_combiner_irq[n]); @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) if (irq_id) { s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - is->ext_gic_irq[irq_id - 32]); + qdev_get_gpio_in(extgicdev, + irq_id - 32)); } } } @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->cpu_irq_orgate[n]), 1)); } - for (n = 0; n < EXYNOS4210_EXT_GIC_NIRQ; n++) { - s->irqs.ext_gic_irq[n] = qdev_get_gpio_in(DEVICE(&s->ext_gic), n); - } /* Internal Interrupt Combiner */ dev = qdev_new("exynos4210.combiner"); @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) busdev = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(busdev, &error_fatal); for (n = 0; n < EXYNOS4210_MAX_INT_COMBINER_OUT_IRQ; n++) { - sysbus_connect_irq(busdev, n, s->irqs.ext_gic_irq[n]); + sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->ext_gic), n)); } exynos4210_combiner_get_gpioin(&s->irqs, dev, 1); sysbus_mmio_map(busdev, 0, EXYNOS4210_EXT_COMBINER_BASE_ADDR); -- 2.25.1 The function exynos4210_combiner_get_gpioin() currently lives in exynos4210_combiner.c, but it isn't really part of the combiner device itself -- it is a function that implements the wiring up of some interrupt sources to multiple combiner inputs. Move it to live with the other SoC-level code in exynos4210.c, along with a few macros previously defined in exynos4210.h which are now used only in exynos4210.c. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-11-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 11 ----- hw/arm/exynos4210.c | 82 +++++++++++++++++++++++++++++++++++ hw/intc/exynos4210_combiner.c | 77 -------------------------------- 3 files changed, 82 insertions(+), 88 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ #define EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ \ (EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ * 8) -#define EXYNOS4210_COMBINER_GET_IRQ_NUM(grp, bit) ((grp)*8 + (bit)) -#define EXYNOS4210_COMBINER_GET_GRP_NUM(irq) ((irq) / 8) -#define EXYNOS4210_COMBINER_GET_BIT_NUM(irq) \ - ((irq) - 8 * EXYNOS4210_COMBINER_GET_GRP_NUM(irq)) - /* IRQs number for external and internal GIC */ #define EXYNOS4210_EXT_GIC_NIRQ (160-32) #define EXYNOS4210_INT_GIC_NIRQ 64 @@ -XXX,XX +XXX,XX @@ void exynos4210_write_secondary(ARMCPU *cpu, * bit - bit number inside group */ uint32_t exynos4210_get_irq(uint32_t grp, uint32_t bit); -/* - * Get Combiner input GPIO into irqs structure - */ -void exynos4210_combiner_get_gpioin(Exynos4210Irq *irqs, DeviceState *dev, - int ext); - /* * exynos4210 UART */ 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 @@ combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { { }, { }, { }, { }, { }, { }, { }, { }, { }, { } }; +#define EXYNOS4210_COMBINER_GET_IRQ_NUM(grp, bit) ((grp) * 8 + (bit)) +#define EXYNOS4210_COMBINER_GET_GRP_NUM(irq) ((irq) / 8) +#define EXYNOS4210_COMBINER_GET_BIT_NUM(irq) \ + ((irq) - 8 * EXYNOS4210_COMBINER_GET_GRP_NUM(irq)) + /* * Initialize board IRQs. * These IRQs contain splitted Int/External Combiner and External Gic IRQs. @@ -XXX,XX +XXX,XX @@ uint32_t exynos4210_get_irq(uint32_t grp, uint32_t bit) return EXYNOS4210_COMBINER_GET_IRQ_NUM(grp, bit); } +/* + * Get Combiner input GPIO into irqs structure + */ +static void exynos4210_combiner_get_gpioin(Exynos4210Irq *irqs, + DeviceState *dev, int ext) +{ + int n; + int bit; + int max; + qemu_irq *irq; + + max = ext ? EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ : + EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; + irq = ext ? irqs->ext_combiner_irq : irqs->int_combiner_irq; + + /* + * Some IRQs of Int/External Combiner are going to two Combiners groups, + * so let split them. + */ + for (n = 0; n < max; n++) { + + bit = EXYNOS4210_COMBINER_GET_BIT_NUM(n); + + switch (n) { + /* MDNIE_LCD1 INTG1 */ + case EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 0) ... + EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 3): + irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), + irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(0, bit + 4)]); + continue; + + /* TMU INTG3 */ + case EXYNOS4210_COMBINER_GET_IRQ_NUM(3, 4): + irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), + irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(2, bit)]); + continue; + + /* LCD1 INTG12 */ + case EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 0) ... + EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 3): + irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), + irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(11, bit + 4)]); + continue; + + /* Multi-Core Timer INTG12 */ + case EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 4) ... + EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 8): + irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), + irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); + continue; + + /* Multi-Core Timer INTG35 */ + case EXYNOS4210_COMBINER_GET_IRQ_NUM(35, 4) ... + EXYNOS4210_COMBINER_GET_IRQ_NUM(35, 8): + irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), + irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); + continue; + + /* Multi-Core Timer INTG51 */ + case EXYNOS4210_COMBINER_GET_IRQ_NUM(51, 4) ... + EXYNOS4210_COMBINER_GET_IRQ_NUM(51, 8): + irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), + irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); + continue; + + /* Multi-Core Timer INTG53 */ + case EXYNOS4210_COMBINER_GET_IRQ_NUM(53, 4) ... + EXYNOS4210_COMBINER_GET_IRQ_NUM(53, 8): + irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), + irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); + continue; + } + + irq[n] = qdev_get_gpio_in(dev, n); + } +} + static uint8_t chipid_and_omr[] = { 0x11, 0x02, 0x21, 0x43, 0x09, 0x00, 0x00, 0x00 }; diff --git a/hw/intc/exynos4210_combiner.c b/hw/intc/exynos4210_combiner.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/exynos4210_combiner.c +++ b/hw/intc/exynos4210_combiner.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_exynos4210_combiner = { } }; -/* - * Get Combiner input GPIO into irqs structure - */ -void exynos4210_combiner_get_gpioin(Exynos4210Irq *irqs, DeviceState *dev, - int ext) -{ - int n; - int bit; - int max; - qemu_irq *irq; - - max = ext ? EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ : - EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; - irq = ext ? irqs->ext_combiner_irq : irqs->int_combiner_irq; - - /* - * Some IRQs of Int/External Combiner are going to two Combiners groups, - * so let split them. - */ - for (n = 0; n < max; n++) { - - bit = EXYNOS4210_COMBINER_GET_BIT_NUM(n); - - switch (n) { - /* MDNIE_LCD1 INTG1 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 0) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 3): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(0, bit + 4)]); - continue; - - /* TMU INTG3 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(3, 4): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(2, bit)]); - continue; - - /* LCD1 INTG12 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 0) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 3): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(11, bit + 4)]); - continue; - - /* Multi-Core Timer INTG12 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - - /* Multi-Core Timer INTG35 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(35, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(35, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - - /* Multi-Core Timer INTG51 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(51, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(51, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - - /* Multi-Core Timer INTG53 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(53, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(53, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - } - - irq[n] = qdev_get_gpio_in(dev, n); - } -} - static uint64_t exynos4210_combiner_read(void *opaque, hwaddr offset, unsigned size) { -- 2.25.1 Delete a couple of #defines which are never used. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-12-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 4 ---- 1 file changed, 4 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ #define EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ \ (EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ * 8) -/* IRQs number for external and internal GIC */ -#define EXYNOS4210_EXT_GIC_NIRQ (160-32) -#define EXYNOS4210_INT_GIC_NIRQ 64 - #define EXYNOS4210_I2C_NUMBER 9 #define EXYNOS4210_NUM_DMA 3 -- 2.25.1 In exynos4210_init_board_irqs(), use the TYPE_SPLIT_IRQ device instead of qemu_irq_split(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-13-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 9 ++++++++ hw/arm/exynos4210.c | 41 +++++++++++++++++++++++++++++-------- 2 files changed, 42 insertions(+), 8 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/cpu/a9mpcore.h" #include "hw/intc/exynos4210_gic.h" +#include "hw/core/split-irq.h" #include "target/arm/cpu-qom.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ #define EXYNOS4210_NUM_DMA 3 +/* + * We need one splitter for every external combiner input, plus + * one for every non-zero entry in combiner_grp_to_gic_id[]. + * We'll assert in exynos4210_init_board_irqs() if this is wrong. + */ +#define EXYNOS4210_NUM_SPLITTERS (EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ + 60) + typedef struct Exynos4210Irq { qemu_irq int_combiner_irq[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; qemu_irq ext_combiner_irq[EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ]; @@ -XXX,XX +XXX,XX @@ struct Exynos4210State { qemu_or_irq cpu_irq_orgate[EXYNOS4210_NCPUS]; A9MPPrivState a9mpcore; Exynos4210GicState ext_gic; + SplitIRQ splitter[EXYNOS4210_NUM_SPLITTERS]; }; #define TYPE_EXYNOS4210_SOC "exynos4210" 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 void exynos4210_init_board_irqs(Exynos4210State *s) uint32_t grp, bit, irq_id, n; Exynos4210Irq *is = &s->irqs; DeviceState *extgicdev = DEVICE(&s->ext_gic); + int splitcount = 0; + DeviceState *splitter; for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { irq_id = 0; @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) /* MCT_G1 is passed to External and GIC */ irq_id = EXT_GIC_ID_MCT_G1; } + + assert(splitcount < EXYNOS4210_NUM_SPLITTERS); + splitter = DEVICE(&s->splitter[splitcount]); + qdev_prop_set_uint16(splitter, "num-lines", 2); + qdev_realize(splitter, NULL, &error_abort); + splitcount++; + s->irq_table[n] = qdev_get_gpio_in(splitter, 0); + qdev_connect_gpio_out(splitter, 0, is->int_combiner_irq[n]); if (irq_id) { - s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - qdev_get_gpio_in(extgicdev, - irq_id - 32)); + qdev_connect_gpio_out(splitter, 1, + qdev_get_gpio_in(extgicdev, irq_id - 32)); } else { - s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - is->ext_combiner_irq[n]); + qdev_connect_gpio_out(splitter, 1, is->ext_combiner_irq[n]); } } for (; n < EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; n++) { @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][bit]; if (irq_id) { - s->irq_table[n] = qemu_irq_split(is->int_combiner_irq[n], - qdev_get_gpio_in(extgicdev, - irq_id - 32)); + assert(splitcount < EXYNOS4210_NUM_SPLITTERS); + splitter = DEVICE(&s->splitter[splitcount]); + qdev_prop_set_uint16(splitter, "num-lines", 2); + qdev_realize(splitter, NULL, &error_abort); + splitcount++; + s->irq_table[n] = qdev_get_gpio_in(splitter, 0); + qdev_connect_gpio_out(splitter, 0, is->int_combiner_irq[n]); + qdev_connect_gpio_out(splitter, 1, + qdev_get_gpio_in(extgicdev, irq_id - 32)); } } + /* + * We check this here to avoid a more obscure assert later when + * qdev_assert_realized_properly() checks that we realized every + * child object we initialized. + */ + assert(splitcount == EXYNOS4210_NUM_SPLITTERS); } /* @@ -XXX,XX +XXX,XX @@ static void exynos4210_init(Object *obj) object_initialize_child(obj, name, &s->cpu_irq_orgate[i], TYPE_OR_IRQ); } + for (i = 0; i < ARRAY_SIZE(s->splitter); i++) { + g_autofree char *name = g_strdup_printf("irq-splitter%d", i); + object_initialize_child(obj, name, &s->splitter[i], TYPE_SPLIT_IRQ); + } + object_initialize_child(obj, "a9mpcore", &s->a9mpcore, TYPE_A9MPCORE_PRIV); object_initialize_child(obj, "ext-gic", &s->ext_gic, TYPE_EXYNOS4210_GIC); } -- 2.25.1 In exynos4210_init_board_irqs(), the loop that handles IRQ lines that are in a range that applies to the internal combiner only creates a splitter for those interrupts which go to both the internal combiner and to the external GIC, but it does nothing at all for the interrupts which don't go to the external GIC, leaving the irq_table[] array element empty for those. (This will result in those interrupts simply being lost, not in a QEMU crash.) I don't have a reliable datasheet for this SoC, but since we do wire up one interrupt line in this category (the HDMI I2C device on interrupt 16,1), this seems like it must be a bug in the existing QEMU code. Fill in the irq_table[] entries where we're not splitting the IRQ to both the internal combiner and the external GIC with the IRQ line of the internal combiner. (That is, these IRQ lines go to just one device, not multiple.) This bug didn't have any visible guest effects because the only implemented device that was affected was the HDMI I2C controller, and we never connect any I2C devices to that bus. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-14-peter.maydell@linaro.org --- hw/arm/exynos4210.c | 2 ++ 1 file changed, 2 insertions(+) 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 void exynos4210_init_board_irqs(Exynos4210State *s) qdev_connect_gpio_out(splitter, 0, is->int_combiner_irq[n]); qdev_connect_gpio_out(splitter, 1, qdev_get_gpio_in(extgicdev, irq_id - 32)); + } else { + s->irq_table[n] = is->int_combiner_irq[n]; } } /* -- 2.25.1 Currently for the interrupts MCT_G0 and MCT_G1 which are the only ones in the input range of the external combiner and which are also wired to the external GIC, we connect them only to the internal combiner and the external GIC. This seems likely to be a bug, as all other interrupts which are in the input range of both combiners are connected to both combiners. (The fact that the code in exynos4210_combiner_get_gpioin() is also trying to wire up these inputs on both combiners also suggests this.) Wire these interrupts up to both combiners, like the rest. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-15-peter.maydell@linaro.org --- hw/arm/exynos4210.c | 7 +++---- 1 file changed, 3 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 void exynos4210_init_board_irqs(Exynos4210State *s) assert(splitcount < EXYNOS4210_NUM_SPLITTERS); splitter = DEVICE(&s->splitter[splitcount]); - qdev_prop_set_uint16(splitter, "num-lines", 2); + qdev_prop_set_uint16(splitter, "num-lines", irq_id ? 3 : 2); qdev_realize(splitter, NULL, &error_abort); splitcount++; s->irq_table[n] = qdev_get_gpio_in(splitter, 0); qdev_connect_gpio_out(splitter, 0, is->int_combiner_irq[n]); + qdev_connect_gpio_out(splitter, 1, is->ext_combiner_irq[n]); if (irq_id) { - qdev_connect_gpio_out(splitter, 1, + qdev_connect_gpio_out(splitter, 2, qdev_get_gpio_in(extgicdev, irq_id - 32)); - } else { - qdev_connect_gpio_out(splitter, 1, is->ext_combiner_irq[n]); } } for (; n < EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; n++) { -- 2.25.1 The combiner_grp_to_gic_id[] array includes the EXT_GIC_ID_MCT_G0 and EXT_GIC_ID_MCT_G1 multiple times. This means that we will connect multiple IRQs up to the same external GIC input, which is not permitted. We do the same thing in the code in exynos4210_init_board_irqs() because the conditionals selecting an irq_id in the first loop match multiple interrupt IDs. Overall we do this for interrupt IDs (1, 4), (12, 4), (35, 4), (51, 4), (53, 4) for EXT_GIC_ID_MCT_G0 and (1, 5), (12, 5), (35, 5), (51, 5), (53, 5) for EXT_GIC_ID_MCT_G1 These correspond to the cases for the multi-core timer that we are wiring up to multiple inputs on the combiner in exynos4210_combiner_get_gpioin(). That code already deals with all these interrupt IDs being the same input source, so we don't need to connect the external GIC interrupt for any of them except the first (1, 4) and (1, 5). Remove the array entries and conditionals which were incorrectly causing us to wire up extra lines. This bug didn't cause any visible effects, because we only connect up a device to the "primary" ID values (1, 4) and (1, 5), so the extra lines would never be set to a level. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-16-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 2 +- hw/arm/exynos4210.c | 12 +++++------- 2 files changed, 6 insertions(+), 8 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ * one for every non-zero entry in combiner_grp_to_gic_id[]. * We'll assert in exynos4210_init_board_irqs() if this is wrong. */ -#define EXYNOS4210_NUM_SPLITTERS (EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ + 60) +#define EXYNOS4210_NUM_SPLITTERS (EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ + 54) typedef struct Exynos4210Irq { qemu_irq int_combiner_irq[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; 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 @@ combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { /* int combiner group 34 */ { EXT_GIC_ID_ONENAND_AUDI, EXT_GIC_ID_NFC }, /* int combiner group 35 */ - { 0, 0, 0, EXT_GIC_ID_MCT_L1, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, + { 0, 0, 0, EXT_GIC_ID_MCT_L1 }, /* int combiner group 36 */ { EXT_GIC_ID_MIXER }, /* int combiner group 37 */ @@ -XXX,XX +XXX,XX @@ combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { /* groups 38-50 */ { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, { }, /* int combiner group 51 */ - { EXT_GIC_ID_MCT_L0, 0, 0, 0, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, + { EXT_GIC_ID_MCT_L0 }, /* group 52 */ { }, /* int combiner group 53 */ - { EXT_GIC_ID_WDT, 0, 0, 0, EXT_GIC_ID_MCT_G0, EXT_GIC_ID_MCT_G1 }, + { EXT_GIC_ID_WDT }, /* groups 54-63 */ { }, { }, { }, { }, { }, { }, { }, { }, { }, { } }; @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { irq_id = 0; - if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 4) || - n == EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 4)) { + if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 4)) { /* MCT_G0 is passed to External GIC */ irq_id = EXT_GIC_ID_MCT_G0; } - if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 5) || - n == EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 5)) { + if (n == EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 5)) { /* MCT_G1 is passed to External and GIC */ irq_id = EXT_GIC_ID_MCT_G1; } -- 2.25.1 At this point, the function exynos4210_init_board_irqs() splits input IRQ lines to connect them to the input combiner, output combiner and external GIC. The function exynos4210_combiner_get_gpioin() splits some of the combiner input lines further to connect them to multiple different inputs on the combiner. Because (unlike qemu_irq_split()) the TYPE_SPLIT_IRQ device has a configurable number of outputs, we can do all this in one place, by making exynos4210_init_board_irqs() add extra outputs to the splitter device when it must be connected to more than one input on each combiner. We do this with a new data structure, the combinermap, which is an array each of whose elements is a list of the interrupt IDs on the combiner which must be tied together. As we loop through each interrupt ID, if we find that it is the first one in one of these lists, we configure the splitter device with eonugh extra outputs and wire them up to the other interrupt IDs in the list. Conveniently, for all the cases where this is necessary, the lowest-numbered interrupt ID in each group is in the range of the external combiner, so we only need to code for this in the first of the two loops in exynos4210_init_board_irqs(). The old code in exynos4210_combiner_get_gpioin() which is being deleted here had several problems which don't exist in the new code in its handling of the multi-core timer interrupts: (1) the case labels specified bits 4 ... 8, but bit '8' doesn't exist; these should have been 4 ... 7 (2) it used the input irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)] multiple times as the input of several different splitters, which isn't allowed (3) in an apparent cut-and-paste error, the cases for all the multi-core timer inputs used "bit + 4" even though the bit range for the case was (intended to be) 4 ... 7, which meant it was looking at non-existent bits 8 ... 11. None of these exist in the new code. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-17-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 6 +- hw/arm/exynos4210.c | 178 +++++++++++++++++++++++------------- 2 files changed, 119 insertions(+), 65 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ /* * We need one splitter for every external combiner input, plus - * one for every non-zero entry in combiner_grp_to_gic_id[]. + * one for every non-zero entry in combiner_grp_to_gic_id[], + * minus one for every external combiner ID in second or later + * places in a combinermap[] line. * We'll assert in exynos4210_init_board_irqs() if this is wrong. */ -#define EXYNOS4210_NUM_SPLITTERS (EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ + 54) +#define EXYNOS4210_NUM_SPLITTERS (EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ + 38) typedef struct Exynos4210Irq { qemu_irq int_combiner_irq[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; 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 @@ combiner_grp_to_gic_id[64 - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][8] = { #define EXYNOS4210_COMBINER_GET_BIT_NUM(irq) \ ((irq) - 8 * EXYNOS4210_COMBINER_GET_GRP_NUM(irq)) +/* + * Some interrupt lines go to multiple combiner inputs. + * This data structure defines those: each array element is + * a list of combiner inputs which are connected together; + * the one with the smallest interrupt ID value must be first. + * As with combiner_grp_to_gic_id[], we rely on (0, 0) not being + * wired to anything so we can use 0 as a terminator. + */ +#define IRQNO(G, B) EXYNOS4210_COMBINER_GET_IRQ_NUM(G, B) +#define IRQNONE 0 + +#define COMBINERMAP_SIZE 16 + +static const int combinermap[COMBINERMAP_SIZE][6] = { + /* MDNIE_LCD1 */ + { IRQNO(0, 4), IRQNO(1, 0), IRQNONE }, + { IRQNO(0, 5), IRQNO(1, 1), IRQNONE }, + { IRQNO(0, 6), IRQNO(1, 2), IRQNONE }, + { IRQNO(0, 7), IRQNO(1, 3), IRQNONE }, + /* TMU */ + { IRQNO(2, 4), IRQNO(3, 4), IRQNONE }, + { IRQNO(2, 5), IRQNO(3, 5), IRQNONE }, + { IRQNO(2, 6), IRQNO(3, 6), IRQNONE }, + { IRQNO(2, 7), IRQNO(3, 7), IRQNONE }, + /* LCD1 */ + { IRQNO(11, 4), IRQNO(12, 0), IRQNONE }, + { IRQNO(11, 5), IRQNO(12, 1), IRQNONE }, + { IRQNO(11, 6), IRQNO(12, 2), IRQNONE }, + { IRQNO(11, 7), IRQNO(12, 3), IRQNONE }, + /* Multi-core timer */ + { IRQNO(1, 4), IRQNO(12, 4), IRQNO(35, 4), IRQNO(51, 4), IRQNO(53, 4), IRQNONE }, + { IRQNO(1, 5), IRQNO(12, 5), IRQNO(35, 5), IRQNO(51, 5), IRQNO(53, 5), IRQNONE }, + { IRQNO(1, 6), IRQNO(12, 6), IRQNO(35, 6), IRQNO(51, 6), IRQNO(53, 6), IRQNONE }, + { IRQNO(1, 7), IRQNO(12, 7), IRQNO(35, 7), IRQNO(51, 7), IRQNO(53, 7), IRQNONE }, +}; + +#undef IRQNO + +static const int *combinermap_entry(int irq) +{ + /* + * If the interrupt number passed in is the first entry in some + * line of the combinermap, return a pointer to that line; + * otherwise return NULL. + */ + int i; + for (i = 0; i < COMBINERMAP_SIZE; i++) { + if (combinermap[i][0] == irq) { + return combinermap[i]; + } + } + return NULL; +} + +static int mapline_size(const int *mapline) +{ + /* Return number of entries in this mapline in total */ + int i = 0; + + if (!mapline) { + /* Not in the map? IRQ goes to exactly one combiner input */ + return 1; + } + while (*mapline != IRQNONE) { + mapline++; + i++; + } + return i; +} + /* * Initialize board IRQs. * These IRQs contain splitted Int/External Combiner and External Gic IRQs. @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) DeviceState *extgicdev = DEVICE(&s->ext_gic); int splitcount = 0; DeviceState *splitter; + const int *mapline; + int numlines, splitin, in; for (n = 0; n < EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ; n++) { irq_id = 0; @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) irq_id = EXT_GIC_ID_MCT_G1; } + if (s->irq_table[n]) { + /* + * This must be some non-first entry in a combinermap line, + * and we've already filled it in. + */ + continue; + } + mapline = combinermap_entry(n); + /* + * We need to connect the IRQ to multiple inputs on both combiners + * and possibly also to the external GIC. + */ + numlines = 2 * mapline_size(mapline); + if (irq_id) { + numlines++; + } assert(splitcount < EXYNOS4210_NUM_SPLITTERS); splitter = DEVICE(&s->splitter[splitcount]); - qdev_prop_set_uint16(splitter, "num-lines", irq_id ? 3 : 2); + qdev_prop_set_uint16(splitter, "num-lines", numlines); qdev_realize(splitter, NULL, &error_abort); splitcount++; - s->irq_table[n] = qdev_get_gpio_in(splitter, 0); - qdev_connect_gpio_out(splitter, 0, is->int_combiner_irq[n]); - qdev_connect_gpio_out(splitter, 1, is->ext_combiner_irq[n]); + + in = n; + splitin = 0; + for (;;) { + s->irq_table[in] = qdev_get_gpio_in(splitter, 0); + qdev_connect_gpio_out(splitter, splitin, is->int_combiner_irq[in]); + qdev_connect_gpio_out(splitter, splitin + 1, is->ext_combiner_irq[in]); + splitin += 2; + if (!mapline) { + break; + } + mapline++; + in = *mapline; + if (in == IRQNONE) { + break; + } + } if (irq_id) { - qdev_connect_gpio_out(splitter, 2, + qdev_connect_gpio_out(splitter, splitin, qdev_get_gpio_in(extgicdev, irq_id - 32)); } } @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) irq_id = combiner_grp_to_gic_id[grp - EXYNOS4210_MAX_EXT_COMBINER_OUT_IRQ][bit]; + if (s->irq_table[n]) { + /* + * This must be some non-first entry in a combinermap line, + * and we've already filled it in. + */ + continue; + } + if (irq_id) { assert(splitcount < EXYNOS4210_NUM_SPLITTERS); splitter = DEVICE(&s->splitter[splitcount]); @@ -XXX,XX +XXX,XX @@ static void exynos4210_combiner_get_gpioin(Exynos4210Irq *irqs, DeviceState *dev, int ext) { int n; - int bit; int max; qemu_irq *irq; @@ -XXX,XX +XXX,XX @@ static void exynos4210_combiner_get_gpioin(Exynos4210Irq *irqs, EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; irq = ext ? irqs->ext_combiner_irq : irqs->int_combiner_irq; - /* - * Some IRQs of Int/External Combiner are going to two Combiners groups, - * so let split them. - */ for (n = 0; n < max; n++) { - - bit = EXYNOS4210_COMBINER_GET_BIT_NUM(n); - - switch (n) { - /* MDNIE_LCD1 INTG1 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 0) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(1, 3): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(0, bit + 4)]); - continue; - - /* TMU INTG3 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(3, 4): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(2, bit)]); - continue; - - /* LCD1 INTG12 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 0) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 3): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(11, bit + 4)]); - continue; - - /* Multi-Core Timer INTG12 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(12, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - - /* Multi-Core Timer INTG35 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(35, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(35, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - - /* Multi-Core Timer INTG51 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(51, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(51, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - - /* Multi-Core Timer INTG53 */ - case EXYNOS4210_COMBINER_GET_IRQ_NUM(53, 4) ... - EXYNOS4210_COMBINER_GET_IRQ_NUM(53, 8): - irq[n] = qemu_irq_split(qdev_get_gpio_in(dev, n), - irq[EXYNOS4210_COMBINER_GET_IRQ_NUM(1, bit + 4)]); - continue; - } - irq[n] = qdev_get_gpio_in(dev, n); } } -- 2.25.1 Switch the creation of the combiner devices to the new-style "embedded in state struct" approach, so we can easily refer to the object elsewhere during realize. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-18-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 3 ++ include/hw/intc/exynos4210_combiner.h | 57 +++++++++++++++++++++++++++ hw/arm/exynos4210.c | 20 +++++----- hw/intc/exynos4210_combiner.c | 31 +-------------- 4 files changed, 72 insertions(+), 39 deletions(-) create mode 100644 include/hw/intc/exynos4210_combiner.h diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/cpu/a9mpcore.h" #include "hw/intc/exynos4210_gic.h" +#include "hw/intc/exynos4210_combiner.h" #include "hw/core/split-irq.h" #include "target/arm/cpu-qom.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct Exynos4210State { qemu_or_irq cpu_irq_orgate[EXYNOS4210_NCPUS]; A9MPPrivState a9mpcore; Exynos4210GicState ext_gic; + Exynos4210CombinerState int_combiner; + Exynos4210CombinerState ext_combiner; SplitIRQ splitter[EXYNOS4210_NUM_SPLITTERS]; }; diff --git a/include/hw/intc/exynos4210_combiner.h b/include/hw/intc/exynos4210_combiner.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/intc/exynos4210_combiner.h @@ -XXX,XX +XXX,XX @@ +/* + * Samsung exynos4210 Interrupt Combiner + * + * Copyright (c) 2000 - 2011 Samsung Electronics Co., Ltd. + * All rights reserved. + * + * Evgeny Voevodin <e.voevodin@samsung.com> + * + * 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/>. + */ + +#ifndef HW_INTC_EXYNOS4210_COMBINER +#define HW_INTC_EXYNOS4210_COMBINER + +#include "hw/sysbus.h" + +/* + * State for each output signal of internal combiner + */ +typedef struct CombinerGroupState { + uint8_t src_mask; /* 1 - source enabled, 0 - disabled */ + uint8_t src_pending; /* Pending source interrupts before masking */ +} CombinerGroupState; + +#define TYPE_EXYNOS4210_COMBINER "exynos4210.combiner" +OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210CombinerState, EXYNOS4210_COMBINER) + +/* Number of groups and total number of interrupts for the internal combiner */ +#define IIC_NGRP 64 +#define IIC_NIRQ (IIC_NGRP * 8) +#define IIC_REGSET_SIZE 0x41 + +struct Exynos4210CombinerState { + SysBusDevice parent_obj; + + MemoryRegion iomem; + + struct CombinerGroupState group[IIC_NGRP]; + uint32_t reg_set[IIC_REGSET_SIZE]; + uint32_t icipsr[2]; + uint32_t external; /* 1 means that this combiner is external */ + + qemu_irq output_irq[IIC_NGRP]; +}; + +#endif 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 void exynos4210_realize(DeviceState *socdev, Error **errp) } /* Internal Interrupt Combiner */ - dev = qdev_new("exynos4210.combiner"); - busdev = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(busdev, &error_fatal); + busdev = SYS_BUS_DEVICE(&s->int_combiner); + sysbus_realize(busdev, &error_fatal); for (n = 0; n < EXYNOS4210_MAX_INT_COMBINER_OUT_IRQ; n++) { sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->a9mpcore), n)); } - exynos4210_combiner_get_gpioin(&s->irqs, dev, 0); + exynos4210_combiner_get_gpioin(&s->irqs, DEVICE(&s->int_combiner), 0); sysbus_mmio_map(busdev, 0, EXYNOS4210_INT_COMBINER_BASE_ADDR); /* External Interrupt Combiner */ - dev = qdev_new("exynos4210.combiner"); - qdev_prop_set_uint32(dev, "external", 1); - busdev = SYS_BUS_DEVICE(dev); - sysbus_realize_and_unref(busdev, &error_fatal); + qdev_prop_set_uint32(DEVICE(&s->ext_combiner), "external", 1); + busdev = SYS_BUS_DEVICE(&s->ext_combiner); + sysbus_realize(busdev, &error_fatal); for (n = 0; n < EXYNOS4210_MAX_INT_COMBINER_OUT_IRQ; n++) { sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->ext_gic), n)); } - exynos4210_combiner_get_gpioin(&s->irqs, dev, 1); + exynos4210_combiner_get_gpioin(&s->irqs, DEVICE(&s->ext_combiner), 1); sysbus_mmio_map(busdev, 0, EXYNOS4210_EXT_COMBINER_BASE_ADDR); /* Initialize board IRQs. */ @@ -XXX,XX +XXX,XX @@ static void exynos4210_init(Object *obj) object_initialize_child(obj, "a9mpcore", &s->a9mpcore, TYPE_A9MPCORE_PRIV); object_initialize_child(obj, "ext-gic", &s->ext_gic, TYPE_EXYNOS4210_GIC); + object_initialize_child(obj, "int-combiner", &s->int_combiner, + TYPE_EXYNOS4210_COMBINER); + object_initialize_child(obj, "ext-combiner", &s->ext_combiner, + TYPE_EXYNOS4210_COMBINER); } static void exynos4210_class_init(ObjectClass *klass, void *data) diff --git a/hw/intc/exynos4210_combiner.c b/hw/intc/exynos4210_combiner.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/exynos4210_combiner.c +++ b/hw/intc/exynos4210_combiner.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "migration/vmstate.h" #include "qemu/module.h" - +#include "hw/intc/exynos4210_combiner.h" #include "hw/arm/exynos4210.h" #include "hw/hw.h" #include "hw/irq.h" @@ -XXX,XX +XXX,XX @@ #define DPRINTF(fmt, ...) do {} while (0) #endif -#define IIC_NGRP 64 /* Internal Interrupt Combiner - Groups number */ -#define IIC_NIRQ (IIC_NGRP * 8)/* Internal Interrupt Combiner - Interrupts number */ #define IIC_REGION_SIZE 0x108 /* Size of memory mapped region */ -#define IIC_REGSET_SIZE 0x41 - -/* - * State for each output signal of internal combiner - */ -typedef struct CombinerGroupState { - uint8_t src_mask; /* 1 - source enabled, 0 - disabled */ - uint8_t src_pending; /* Pending source interrupts before masking */ -} CombinerGroupState; - -#define TYPE_EXYNOS4210_COMBINER "exynos4210.combiner" -OBJECT_DECLARE_SIMPLE_TYPE(Exynos4210CombinerState, EXYNOS4210_COMBINER) - -struct Exynos4210CombinerState { - SysBusDevice parent_obj; - - MemoryRegion iomem; - - struct CombinerGroupState group[IIC_NGRP]; - uint32_t reg_set[IIC_REGSET_SIZE]; - uint32_t icipsr[2]; - uint32_t external; /* 1 means that this combiner is external */ - - qemu_irq output_irq[IIC_NGRP]; -}; static const VMStateDescription vmstate_exynos4210_combiner_group_state = { .name = "exynos4210.combiner.groupstate", -- 2.25.1 The only time we use the int_combiner_irq[] and ext_combiner_irq[] arrays in the Exynos4210Irq struct is during realize of the SoC -- we initialize them with the input IRQs of the combiner devices, and then connect those to outputs of other devices in exynos4210_init_board_irqs(). Now that the combiner objects are easily accessible as s->int_combiner and s->ext_combiner we can make the connections directly from one device to the other without going via these arrays. Since these are the only two remaining elements of Exynos4210Irq, we can remove that struct entirely. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220404154658.565020-19-peter.maydell@linaro.org --- include/hw/arm/exynos4210.h | 6 ------ hw/arm/exynos4210.c | 34 ++++++++-------------------------- 2 files changed, 8 insertions(+), 32 deletions(-) diff --git a/include/hw/arm/exynos4210.h b/include/hw/arm/exynos4210.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/exynos4210.h +++ b/include/hw/arm/exynos4210.h @@ -XXX,XX +XXX,XX @@ */ #define EXYNOS4210_NUM_SPLITTERS (EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ + 38) -typedef struct Exynos4210Irq { - qemu_irq int_combiner_irq[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; - qemu_irq ext_combiner_irq[EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ]; -} Exynos4210Irq; - struct Exynos4210State { /*< private >*/ SysBusDevice parent_obj; /*< public >*/ ARMCPU *cpu[EXYNOS4210_NCPUS]; - Exynos4210Irq irqs; qemu_irq irq_table[EXYNOS4210_MAX_INT_COMBINER_IN_IRQ]; MemoryRegion chipid_mem; 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 int mapline_size(const int *mapline) static void exynos4210_init_board_irqs(Exynos4210State *s) { uint32_t grp, bit, irq_id, n; - Exynos4210Irq *is = &s->irqs; DeviceState *extgicdev = DEVICE(&s->ext_gic); + DeviceState *intcdev = DEVICE(&s->int_combiner); + DeviceState *extcdev = DEVICE(&s->ext_combiner); int splitcount = 0; DeviceState *splitter; const int *mapline; @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) splitin = 0; for (;;) { s->irq_table[in] = qdev_get_gpio_in(splitter, 0); - qdev_connect_gpio_out(splitter, splitin, is->int_combiner_irq[in]); - qdev_connect_gpio_out(splitter, splitin + 1, is->ext_combiner_irq[in]); + qdev_connect_gpio_out(splitter, splitin, + qdev_get_gpio_in(intcdev, in)); + qdev_connect_gpio_out(splitter, splitin + 1, + qdev_get_gpio_in(extcdev, in)); splitin += 2; if (!mapline) { break; @@ -XXX,XX +XXX,XX @@ static void exynos4210_init_board_irqs(Exynos4210State *s) qdev_realize(splitter, NULL, &error_abort); splitcount++; s->irq_table[n] = qdev_get_gpio_in(splitter, 0); - qdev_connect_gpio_out(splitter, 0, is->int_combiner_irq[n]); + qdev_connect_gpio_out(splitter, 0, qdev_get_gpio_in(intcdev, n)); qdev_connect_gpio_out(splitter, 1, qdev_get_gpio_in(extgicdev, irq_id - 32)); } else { - s->irq_table[n] = is->int_combiner_irq[n]; + s->irq_table[n] = qdev_get_gpio_in(intcdev, n); } } /* @@ -XXX,XX +XXX,XX @@ uint32_t exynos4210_get_irq(uint32_t grp, uint32_t bit) return EXYNOS4210_COMBINER_GET_IRQ_NUM(grp, bit); } -/* - * Get Combiner input GPIO into irqs structure - */ -static void exynos4210_combiner_get_gpioin(Exynos4210Irq *irqs, - DeviceState *dev, int ext) -{ - int n; - int max; - qemu_irq *irq; - - max = ext ? EXYNOS4210_MAX_EXT_COMBINER_IN_IRQ : - EXYNOS4210_MAX_INT_COMBINER_IN_IRQ; - irq = ext ? irqs->ext_combiner_irq : irqs->int_combiner_irq; - - for (n = 0; n < max; n++) { - irq[n] = qdev_get_gpio_in(dev, n); - } -} - static uint8_t chipid_and_omr[] = { 0x11, 0x02, 0x21, 0x43, 0x09, 0x00, 0x00, 0x00 }; @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->a9mpcore), n)); } - exynos4210_combiner_get_gpioin(&s->irqs, DEVICE(&s->int_combiner), 0); sysbus_mmio_map(busdev, 0, EXYNOS4210_INT_COMBINER_BASE_ADDR); /* External Interrupt Combiner */ @@ -XXX,XX +XXX,XX @@ static void exynos4210_realize(DeviceState *socdev, Error **errp) for (n = 0; n < EXYNOS4210_MAX_INT_COMBINER_OUT_IRQ; n++) { sysbus_connect_irq(busdev, n, qdev_get_gpio_in(DEVICE(&s->ext_gic), n)); } - exynos4210_combiner_get_gpioin(&s->irqs, DEVICE(&s->ext_combiner), 1); sysbus_mmio_map(busdev, 0, EXYNOS4210_EXT_COMBINER_BASE_ADDR); /* Initialize board IRQs. */ -- 2.25.1 From: Zongyuan Li <zongyuan.li@smartx.com> Signed-off-by: Zongyuan Li <zongyuan.li@smartx.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20220324181557.203805-2-zongyuan.li@smartx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/realview.c | 33 ++++++++++++++++++++++++--------- 1 file changed, 24 insertions(+), 9 deletions(-) diff --git a/hw/arm/realview.c b/hw/arm/realview.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/realview.c +++ b/hw/arm/realview.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "hw/arm/boot.h" #include "hw/arm/primecell.h" +#include "hw/core/split-irq.h" #include "hw/net/lan9118.h" #include "hw/net/smc91c111.h" #include "hw/pci/pci.h" +#include "hw/qdev-core.h" #include "net/net.h" #include "sysemu/sysemu.h" #include "hw/boards.h" @@ -XXX,XX +XXX,XX @@ static const int realview_board_id[] = { 0x76d }; +static void split_irq_from_named(DeviceState *src, const char* outname, + qemu_irq out1, qemu_irq out2) { + DeviceState *splitter = qdev_new(TYPE_SPLIT_IRQ); + + qdev_prop_set_uint32(splitter, "num-lines", 2); + + qdev_realize_and_unref(splitter, NULL, &error_fatal); + + qdev_connect_gpio_out(splitter, 0, out1); + qdev_connect_gpio_out(splitter, 1, out2); + qdev_connect_gpio_out_named(src, outname, 0, + qdev_get_gpio_in(splitter, 0)); +} + static void realview_init(MachineState *machine, enum realview_board_type board_type) { @@ -XXX,XX +XXX,XX @@ static void realview_init(MachineState *machine, DeviceState *dev, *sysctl, *gpio2, *pl041; SysBusDevice *busdev; qemu_irq pic[64]; - qemu_irq mmc_irq[2]; PCIBus *pci_bus = NULL; NICInfo *nd; DriveInfo *dinfo; @@ -XXX,XX +XXX,XX @@ static void realview_init(MachineState *machine, * and the PL061 has them the other way about. Also the card * detect line is inverted. */ - mmc_irq[0] = qemu_irq_split( - qdev_get_gpio_in(sysctl, ARM_SYSCTL_GPIO_MMC_WPROT), - qdev_get_gpio_in(gpio2, 1)); - mmc_irq[1] = qemu_irq_split( - qdev_get_gpio_in(sysctl, ARM_SYSCTL_GPIO_MMC_CARDIN), - qemu_irq_invert(qdev_get_gpio_in(gpio2, 0))); - qdev_connect_gpio_out_named(dev, "card-read-only", 0, mmc_irq[0]); - qdev_connect_gpio_out_named(dev, "card-inserted", 0, mmc_irq[1]); + split_irq_from_named(dev, "card-read-only", + qdev_get_gpio_in(sysctl, ARM_SYSCTL_GPIO_MMC_WPROT), + qdev_get_gpio_in(gpio2, 1)); + + split_irq_from_named(dev, "card-inserted", + qdev_get_gpio_in(sysctl, ARM_SYSCTL_GPIO_MMC_CARDIN), + qemu_irq_invert(qdev_get_gpio_in(gpio2, 0))); + dinfo = drive_get(IF_SD, 0, 0); if (dinfo) { DeviceState *card; -- 2.25.1 From: Zongyuan Li <zongyuan.li@smartx.com> Signed-off-by: Zongyuan Li <zongyuan.li@smartx.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20220324181557.203805-3-zongyuan.li@smartx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "qapi/error.h" +#include "hw/core/split-irq.h" #include "hw/sysbus.h" #include "hw/sd/sd.h" #include "hw/ssi/ssi.h" @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) DeviceState *ssddev; DriveInfo *dinfo; DeviceState *carddev; + DeviceState *gpio_d_splitter; BlockBackend *blk; /* @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) &error_fatal); ssddev = ssi_create_peripheral(bus, "ssd0323"); - gpio_out[GPIO_D][0] = qemu_irq_split( - qdev_get_gpio_in_named(sddev, SSI_GPIO_CS, 0), + + gpio_d_splitter = qdev_new(TYPE_SPLIT_IRQ); + qdev_prop_set_uint32(gpio_d_splitter, "num-lines", 2); + qdev_realize_and_unref(gpio_d_splitter, NULL, &error_fatal); + qdev_connect_gpio_out( + gpio_d_splitter, 0, + qdev_get_gpio_in_named(sddev, SSI_GPIO_CS, 0)); + qdev_connect_gpio_out( + gpio_d_splitter, 1, qdev_get_gpio_in_named(ssddev, SSI_GPIO_CS, 0)); + gpio_out[GPIO_D][0] = qdev_get_gpio_in(gpio_d_splitter, 0); + gpio_out[GPIO_C][7] = qdev_get_gpio_in(ssddev, 0); /* Make sure the select pin is high. */ -- 2.25.1 From: Zongyuan Li <zongyuan.li@smartx.com> Signed-off-by: Zongyuan Li <zongyuan.li@smartx.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20220324181557.203805-5-zongyuan.li@smartx.com Resolves: https://gitlab.com/qemu-project/qemu/-/issues/811 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/irq.h | 5 ----- hw/core/irq.c | 15 --------------- 2 files changed, 20 deletions(-) diff --git a/include/hw/irq.h b/include/hw/irq.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/irq.h +++ b/include/hw/irq.h @@ -XXX,XX +XXX,XX @@ void qemu_free_irq(qemu_irq irq); /* Returns a new IRQ with opposite polarity. */ qemu_irq qemu_irq_invert(qemu_irq irq); -/* Returns a new IRQ which feeds into both the passed IRQs. - * It's probably better to use the TYPE_SPLIT_IRQ device instead. - */ -qemu_irq qemu_irq_split(qemu_irq irq1, qemu_irq irq2); - /* For internal use in qtest. Similar to qemu_irq_split, but operating on an existing vector of qemu_irq. */ void qemu_irq_intercept_in(qemu_irq *gpio_in, qemu_irq_handler handler, int n); diff --git a/hw/core/irq.c b/hw/core/irq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/irq.c +++ b/hw/core/irq.c @@ -XXX,XX +XXX,XX @@ qemu_irq qemu_irq_invert(qemu_irq irq) return qemu_allocate_irq(qemu_notirq, irq, 0); } -static void qemu_splitirq(void *opaque, int line, int level) -{ - struct IRQState **irq = opaque; - irq[0]->handler(irq[0]->opaque, irq[0]->n, level); - irq[1]->handler(irq[1]->opaque, irq[1]->n, level); -} - -qemu_irq qemu_irq_split(qemu_irq irq1, qemu_irq irq2) -{ - qemu_irq *s = g_new0(qemu_irq, 2); - s[0] = irq1; - s[1] = irq2; - return qemu_allocate_irq(qemu_splitirq, s, 0); -} - void qemu_irq_intercept_in(qemu_irq *gpio_in, qemu_irq_handler handler, int n) { int i; -- 2.25.1 From: Heinrich Schuchardt <heinrich.schuchardt@canonical.com> Describe that the gic-version influences the maximum number of CPUs. Signed-off-by: Heinrich Schuchardt <heinrich.schuchardt@canonical.com> Message-id: 20220413231456.35811-1-heinrich.schuchardt@canonical.com [PMM: minor punctuation tweaks] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/virt.rst | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/system/arm/virt.rst b/docs/system/arm/virt.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/virt.rst +++ b/docs/system/arm/virt.rst @@ -XXX,XX +XXX,XX @@ gic-version Valid values are: ``2`` - GICv2 + GICv2. Note that this limits the number of CPUs to 8. ``3`` - GICv3 + GICv3. This allows up to 512 CPUs. ``host`` Use the same GIC version the host provides, when using KVM ``max`` -- 2.25.1 From: Hao Wu <wuhaotsh@google.com> Similar to the Aspeed code in include/misc/aspeed_scu.h, we define the PWRON STRAP fields in their corresponding module for NPCM7XX. Signed-off-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Patrick Venture <venture@google.com> Message-id: 20220411165842.3912945-2-wuhaotsh@google.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/npcm7xx_gcr.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) diff --git a/include/hw/misc/npcm7xx_gcr.h b/include/hw/misc/npcm7xx_gcr.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/npcm7xx_gcr.h +++ b/include/hw/misc/npcm7xx_gcr.h @@ -XXX,XX +XXX,XX @@ #include "exec/memory.h" #include "hw/sysbus.h" +/* + * NPCM7XX PWRON STRAP bit fields + * 12: SPI0 powered by VSBV3 at 1.8V + * 11: System flash attached to BMC + * 10: BSP alternative pins. + * 9:8: Flash UART command route enabled. + * 7: Security enabled. + * 6: HI-Z state control. + * 5: ECC disabled. + * 4: Reserved + * 3: JTAG2 enabled. + * 2:0: CPU and DRAM clock frequency. + */ +#define NPCM7XX_PWRON_STRAP_SPI0F18 BIT(12) +#define NPCM7XX_PWRON_STRAP_SFAB BIT(11) +#define NPCM7XX_PWRON_STRAP_BSPA BIT(10) +#define NPCM7XX_PWRON_STRAP_FUP(x) ((x) << 8) +#define FUP_NORM_UART2 3 +#define FUP_PROG_UART3 2 +#define FUP_PROG_UART2 1 +#define FUP_NORM_UART3 0 +#define NPCM7XX_PWRON_STRAP_SECEN BIT(7) +#define NPCM7XX_PWRON_STRAP_HIZ BIT(6) +#define NPCM7XX_PWRON_STRAP_ECC BIT(5) +#define NPCM7XX_PWRON_STRAP_RESERVE1 BIT(4) +#define NPCM7XX_PWRON_STRAP_J2EN BIT(3) +#define NPCM7XX_PWRON_STRAP_CKFRQ(x) (x) +#define CKFRQ_SKIPINIT 0x000 +#define CKFRQ_DEFAULT 0x111 + /* * Number of registers in our device state structure. Don't change this without * incrementing the version_id in the vmstate. -- 2.25.1 From: Hao Wu <wuhaotsh@google.com> This patch uses the defined fields to describe PWRON STRAPs for better readability. Signed-off-by: Hao Wu <wuhaotsh@google.com> Reviewed-by: Patrick Venture <venture@google.com> Message-id: 20220411165842.3912945-3-wuhaotsh@google.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/npcm7xx_boards.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) diff --git a/hw/arm/npcm7xx_boards.c b/hw/arm/npcm7xx_boards.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/npcm7xx_boards.c +++ b/hw/arm/npcm7xx_boards.c @@ -XXX,XX +XXX,XX @@ #include "sysemu/sysemu.h" #include "sysemu/block-backend.h" -#define NPCM750_EVB_POWER_ON_STRAPS 0x00001ff7 -#define QUANTA_GSJ_POWER_ON_STRAPS 0x00001fff -#define QUANTA_GBS_POWER_ON_STRAPS 0x000017ff -#define KUDO_BMC_POWER_ON_STRAPS 0x00001fff -#define MORI_BMC_POWER_ON_STRAPS 0x00001fff +#define NPCM7XX_POWER_ON_STRAPS_DEFAULT ( \ + NPCM7XX_PWRON_STRAP_SPI0F18 | \ + NPCM7XX_PWRON_STRAP_SFAB | \ + NPCM7XX_PWRON_STRAP_BSPA | \ + NPCM7XX_PWRON_STRAP_FUP(FUP_NORM_UART2) | \ + NPCM7XX_PWRON_STRAP_SECEN | \ + NPCM7XX_PWRON_STRAP_HIZ | \ + NPCM7XX_PWRON_STRAP_ECC | \ + NPCM7XX_PWRON_STRAP_RESERVE1 | \ + NPCM7XX_PWRON_STRAP_J2EN | \ + NPCM7XX_PWRON_STRAP_CKFRQ(CKFRQ_DEFAULT)) + +#define NPCM750_EVB_POWER_ON_STRAPS ( \ + NPCM7XX_POWER_ON_STRAPS_DEFAULT & ~NPCM7XX_PWRON_STRAP_J2EN) +#define QUANTA_GSJ_POWER_ON_STRAPS NPCM7XX_POWER_ON_STRAPS_DEFAULT +#define QUANTA_GBS_POWER_ON_STRAPS ( \ + NPCM7XX_POWER_ON_STRAPS_DEFAULT & ~NPCM7XX_PWRON_STRAP_SFAB) +#define KUDO_BMC_POWER_ON_STRAPS NPCM7XX_POWER_ON_STRAPS_DEFAULT +#define MORI_BMC_POWER_ON_STRAPS NPCM7XX_POWER_ON_STRAPS_DEFAULT static const char npcm7xx_default_bootrom[] = "npcm7xx_bootrom.bin"; -- 2.25.1