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 Hi; here's a target-arm pullreq. Mostly this is some decodetree conversion patches from me, plus a scattering of other bug fixes. thanks -- PMM The following changes since commit e3660cc1e3cb136af50c0eaaeac27943c2438d1d: Merge tag 'pull-loongarch-20230616' of https://gitlab.com/gaosong/qemu into staging (2023-06-16 12:30:16 +0200) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20230619 for you to fetch changes up to 074259c0f2ac40042dce766d870318cc22f388eb: hw/misc/bcm2835_property: Handle CORE_CLK_ID firmware property (2023-06-19 15:27:21 +0100) ---------------------------------------------------------------- target-arm queue: * Fix return value from LDSMIN/LDSMAX 8/16 bit atomics * Return correct result for LDG when ATA=0 * Conversion of system insns, loads and stores to decodetree * hw/intc/allwinner-a10-pic: Handle IRQ levels other than 0 or 1 * hw/sd/allwinner-sdhost: Don't send non-boolean IRQ line levels * hw/timer/nrf51_timer: Don't lose time when timer is queried in tight loop * hw/arm/Kconfig: sbsa-ref uses Bochs display * imx_serial: set wake bit when we receive a data byte * docs: sbsa: document board to firmware interface * hw/misc/bcm2835_property: avoid hard-coded constants ---------------------------------------------------------------- Marcin Juszkiewicz (2): hw/arm/Kconfig: sbsa-ref uses Bochs display docs: sbsa: document board to firmware interface Martin Kaiser (1): imx_serial: set wake bit when we receive a data byte Peter Maydell (26): target/arm: Fix return value from LDSMIN/LDSMAX 8/16 bit atomics target/arm: Return correct result for LDG when ATA=0 target/arm: Pass memop to gen_mte_check1_mmuidx() in reg_imm9 decode target/arm: Consistently use finalize_memop_asimd() for ASIMD loads/stores target/arm: Convert hint instruction space to decodetree target/arm: Convert barrier insns to decodetree target/arm: Convert CFINV, XAFLAG and AXFLAG to decodetree target/arm: Convert MSR (immediate) to decodetree target/arm: Convert MSR (reg), MRS, SYS, SYSL to decodetree target/arm: Convert exception generation instructions to decodetree target/arm: Convert load/store exclusive and ordered to decodetree target/arm: Convert LDXP, STXP, CASP, CAS to decodetree target/arm: Convert load reg (literal) group to decodetree target/arm: Convert load/store-pair to decodetree target/arm: Convert ld/st reg+imm9 insns to decodetree target/arm: Convert LDR/STR with 12-bit immediate to decodetree target/arm: Convert LDR/STR reg+reg to decodetree target/arm: Convert atomic memory ops to decodetree target/arm: Convert load (pointer auth) insns to decodetree target/arm: Convert LDAPR/STLR (imm) to decodetree target/arm: Convert load/store (multiple structures) to decodetree target/arm: Convert load/store single structure to decodetree target/arm: Convert load/store tags insns to decodetree hw/intc/allwinner-a10-pic: Handle IRQ levels other than 0 or 1 hw/sd/allwinner-sdhost: Don't send non-boolean IRQ line levels hw/timer/nrf51_timer: Don't lose time when timer is queried in tight loop Sergey Kambalin (4): hw/arm/raspi: Import Linux raspi definitions as 'raspberrypi-fw-defs.h' hw/misc/bcm2835_property: Use 'raspberrypi-fw-defs.h' definitions hw/misc/bcm2835_property: Replace magic frequency values by definitions hw/misc/bcm2835_property: Handle CORE_CLK_ID firmware property docs/system/arm/sbsa.rst | 38 +- include/hw/arm/raspi_platform.h | 10 + include/hw/char/imx_serial.h | 1 + include/hw/misc/raspberrypi-fw-defs.h | 163 ++ target/arm/tcg/a64.decode | 403 ++++ hw/char/imx_serial.c | 5 +- hw/intc/allwinner-a10-pic.c | 2 +- hw/misc/bcm2835_property.c | 112 +- hw/sd/allwinner-sdhost.c | 2 +- hw/timer/nrf51_timer.c | 7 +- target/arm/tcg/translate-a64.c | 3319 +++++++++++++++------------------ hw/arm/Kconfig | 1 + 12 files changed, 2157 insertions(+), 1906 deletions(-) create mode 100644 include/hw/misc/raspberrypi-fw-defs.h The atomic memory operations are supposed to return the old memory data value in the destination register. This value is not sign-extended, even if the operation is the signed minimum or maximum. (In the pseudocode for the instructions the returned data value is passed to ZeroExtend() to create the value in the register.) We got this wrong because we were doing a 32-to-64 zero extend on the result for 8 and 16 bit data values, rather than the correct amount of zero extension. Fix the bug by using ext8u and ext16u for the MO_8 and MO_16 data sizes rather than ext32u. Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-2-peter.maydell@linaro.org --- target/arm/tcg/translate-a64.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, */ fn(tcg_rt, clean_addr, tcg_rs, get_mem_index(s), mop); - if ((mop & MO_SIGN) && size != MO_64) { - tcg_gen_ext32u_i64(tcg_rt, tcg_rt); + if (mop & MO_SIGN) { + switch (size) { + case MO_8: + tcg_gen_ext8u_i64(tcg_rt, tcg_rt); + break; + case MO_16: + tcg_gen_ext16u_i64(tcg_rt, tcg_rt); + break; + case MO_32: + tcg_gen_ext32u_i64(tcg_rt, tcg_rt); + break; + case MO_64: + break; + default: + g_assert_not_reached(); + } } } -- 2.34.1 The LDG instruction loads the tag from a memory address (identified by [Xn + offset]), and then merges that tag into the destination register Xt. We implemented this correctly for the case when allocation tags are enabled, but didn't get it right when ATA=0: instead of merging the tag bits into Xt, we merged them into the memory address [Xn + offset] and then set Xt to that. Merge the tag bits into the old Xt value, as they should be. Cc: qemu-stable@nongnu.org Fixes: c15294c1e36a7dd9b25 ("target/arm: Implement LDG, STG, ST2G instructions") Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_tag(DisasContext *s, uint32_t insn) if (s->ata) { gen_helper_ldg(tcg_rt, cpu_env, addr, tcg_rt); } else { + /* + * Tag access disabled: we must check for aborts on the load + * load from [rn+offset], and then insert a 0 tag into rt. + */ clean_addr = clean_data_tbi(s, addr); gen_probe_access(s, clean_addr, MMU_DATA_LOAD, MO_8); - gen_address_with_allocation_tag0(tcg_rt, addr); + gen_address_with_allocation_tag0(tcg_rt, tcg_rt); } } else { tcg_rt = cpu_reg_sp(s, rt); -- 2.34.1 In disas_ldst_reg_imm9() we missed one place where a call to a gen_mte_check* function should now be passed the memop we have created rather than just being passed the size. Fix this. Fixes: 0a9091424d ("target/arm: Pass memop to gen_mte_check1*") Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> --- target/arm/tcg/translate-a64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, clean_addr = gen_mte_check1_mmuidx(s, dirty_addr, is_store, writeback || rn != 31, - size, is_unpriv, memidx); + memop, is_unpriv, memidx); if (is_vector) { if (is_store) { -- 2.34.1 In the recent refactoring we missed a few places which should be calling finalize_memop_asimd() for ASIMD loads and stores but instead are just calling finalize_memop(); fix these. For the disas_ldst_single_struct() and disas_ldst_multiple_struct() cases, this is not a behaviour change because there the size is never MO_128 and the two finalize functions do the same thing. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/tcg/translate-a64.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, if (!fp_access_check(s)) { return; } + memop = finalize_memop_asimd(s, size); } else { if (size == 3 && opc == 2) { /* PRFM - prefetch */ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, is_store = (opc == 0); is_signed = !is_store && extract32(opc, 1, 1); is_extended = (size < 3) && extract32(opc, 0, 1); + memop = finalize_memop(s, size + is_signed * MO_SIGN); } if (rn == 31) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, tcg_gen_add_i64(dirty_addr, dirty_addr, tcg_rm); - memop = finalize_memop(s, size + is_signed * MO_SIGN); clean_addr = gen_mte_check1(s, dirty_addr, is_store, true, memop); if (is_vector) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn, if (!fp_access_check(s)) { return; } + memop = finalize_memop_asimd(s, size); } else { if (size == 3 && opc == 2) { /* PRFM - prefetch */ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn, is_store = (opc == 0); is_signed = !is_store && extract32(opc, 1, 1); is_extended = (size < 3) && extract32(opc, 0, 1); + memop = finalize_memop(s, size + is_signed * MO_SIGN); } if (rn == 31) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn, offset = imm12 << size; tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); - memop = finalize_memop(s, size + is_signed * MO_SIGN); clean_addr = gen_mte_check1(s, dirty_addr, is_store, rn != 31, memop); if (is_vector) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) * promote consecutive little-endian elements below. */ clean_addr = gen_mte_checkN(s, tcg_rn, is_store, is_postidx || rn != 31, - total, finalize_memop(s, size)); + total, finalize_memop_asimd(s, size)); /* * Consecutive little-endian elements from a single register @@ -XXX,XX +XXX,XX @@ static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) total = selem << scale; tcg_rn = cpu_reg_sp(s, rn); - mop = finalize_memop(s, scale); + mop = finalize_memop_asimd(s, scale); clean_addr = gen_mte_checkN(s, tcg_rn, !is_load, is_postidx || rn != 31, total, mop); -- 2.34.1 Convert the various instructions in the hint instruction space to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-3-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 31 ++++ target/arm/tcg/translate-a64.c | 277 ++++++++++++++++++--------------- 2 files changed, 185 insertions(+), 123 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ ERETA 1101011 0100 11111 00001 m:1 11111 11111 &reta # ERETAA, ERETAB # the processor is in halting debug state (which we don't implement). # The pattern is listed here as documentation. # DRPS 1101011 0101 11111 000000 11111 00000 + +# Hint instruction group +{ + [ + YIELD 1101 0101 0000 0011 0010 0000 001 11111 + WFE 1101 0101 0000 0011 0010 0000 010 11111 + WFI 1101 0101 0000 0011 0010 0000 011 11111 + # We implement WFE to never block, so our SEV/SEVL are NOPs + # SEV 1101 0101 0000 0011 0010 0000 100 11111 + # SEVL 1101 0101 0000 0011 0010 0000 101 11111 + # Our DGL is a NOP because we don't merge memory accesses anyway. + # DGL 1101 0101 0000 0011 0010 0000 110 11111 + XPACLRI 1101 0101 0000 0011 0010 0000 111 11111 + PACIA1716 1101 0101 0000 0011 0010 0001 000 11111 + PACIB1716 1101 0101 0000 0011 0010 0001 010 11111 + AUTIA1716 1101 0101 0000 0011 0010 0001 100 11111 + AUTIB1716 1101 0101 0000 0011 0010 0001 110 11111 + ESB 1101 0101 0000 0011 0010 0010 000 11111 + PACIAZ 1101 0101 0000 0011 0010 0011 000 11111 + PACIASP 1101 0101 0000 0011 0010 0011 001 11111 + PACIBZ 1101 0101 0000 0011 0010 0011 010 11111 + PACIBSP 1101 0101 0000 0011 0010 0011 011 11111 + AUTIAZ 1101 0101 0000 0011 0010 0011 100 11111 + AUTIASP 1101 0101 0000 0011 0010 0011 101 11111 + AUTIBZ 1101 0101 0000 0011 0010 0011 110 11111 + AUTIBSP 1101 0101 0000 0011 0010 0011 111 11111 + ] + # The canonical NOP has CRm == op2 == 0, but all of the space + # that isn't specifically allocated to an instruction must NOP + NOP 1101 0101 0000 0011 0010 ---- --- 11111 +} diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_ERETA(DisasContext *s, arg_reta *a) return true; } -/* HINT instruction group, including various allocated HINTs */ -static void handle_hint(DisasContext *s, uint32_t insn, - unsigned int op1, unsigned int op2, unsigned int crm) +static bool trans_NOP(DisasContext *s, arg_NOP *a) { - unsigned int selector = crm << 3 | op2; + return true; +} - if (op1 != 3) { - unallocated_encoding(s); - return; +static bool trans_YIELD(DisasContext *s, arg_YIELD *a) +{ + /* + * When running in MTTCG we don't generate jumps to the yield and + * WFE helpers as it won't affect the scheduling of other vCPUs. + * If we wanted to more completely model WFE/SEV so we don't busy + * spin unnecessarily we would need to do something more involved. + */ + if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) { + s->base.is_jmp = DISAS_YIELD; } + return true; +} - switch (selector) { - case 0b00000: /* NOP */ - break; - case 0b00011: /* WFI */ - s->base.is_jmp = DISAS_WFI; - break; - case 0b00001: /* YIELD */ - /* When running in MTTCG we don't generate jumps to the yield and - * WFE helpers as it won't affect the scheduling of other vCPUs. - * If we wanted to more completely model WFE/SEV so we don't busy - * spin unnecessarily we would need to do something more involved. +static bool trans_WFI(DisasContext *s, arg_WFI *a) +{ + s->base.is_jmp = DISAS_WFI; + return true; +} + +static bool trans_WFE(DisasContext *s, arg_WFI *a) +{ + /* + * When running in MTTCG we don't generate jumps to the yield and + * WFE helpers as it won't affect the scheduling of other vCPUs. + * If we wanted to more completely model WFE/SEV so we don't busy + * spin unnecessarily we would need to do something more involved. + */ + if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) { + s->base.is_jmp = DISAS_WFE; + } + return true; +} + +static bool trans_XPACLRI(DisasContext *s, arg_XPACLRI *a) +{ + if (s->pauth_active) { + gen_helper_xpaci(cpu_X[30], cpu_env, cpu_X[30]); + } + return true; +} + +static bool trans_PACIA1716(DisasContext *s, arg_PACIA1716 *a) +{ + if (s->pauth_active) { + gen_helper_pacia(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); + } + return true; +} + +static bool trans_PACIB1716(DisasContext *s, arg_PACIB1716 *a) +{ + if (s->pauth_active) { + gen_helper_pacib(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); + } + return true; +} + +static bool trans_AUTIA1716(DisasContext *s, arg_AUTIA1716 *a) +{ + if (s->pauth_active) { + gen_helper_autia(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); + } + return true; +} + +static bool trans_AUTIB1716(DisasContext *s, arg_AUTIB1716 *a) +{ + if (s->pauth_active) { + gen_helper_autib(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); + } + return true; +} + +static bool trans_ESB(DisasContext *s, arg_ESB *a) +{ + /* Without RAS, we must implement this as NOP. */ + if (dc_isar_feature(aa64_ras, s)) { + /* + * QEMU does not have a source of physical SErrors, + * so we are only concerned with virtual SErrors. + * The pseudocode in the ARM for this case is + * if PSTATE.EL IN {EL0, EL1} && EL2Enabled() then + * AArch64.vESBOperation(); + * Most of the condition can be evaluated at translation time. + * Test for EL2 present, and defer test for SEL2 to runtime. */ - if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) { - s->base.is_jmp = DISAS_YIELD; + if (s->current_el <= 1 && arm_dc_feature(s, ARM_FEATURE_EL2)) { + gen_helper_vesb(cpu_env); } - break; - case 0b00010: /* WFE */ - if (!(tb_cflags(s->base.tb) & CF_PARALLEL)) { - s->base.is_jmp = DISAS_WFE; - } - break; - case 0b00100: /* SEV */ - case 0b00101: /* SEVL */ - case 0b00110: /* DGH */ - /* we treat all as NOP at least for now */ - break; - case 0b00111: /* XPACLRI */ - if (s->pauth_active) { - gen_helper_xpaci(cpu_X[30], cpu_env, cpu_X[30]); - } - break; - case 0b01000: /* PACIA1716 */ - if (s->pauth_active) { - gen_helper_pacia(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); - } - break; - case 0b01010: /* PACIB1716 */ - if (s->pauth_active) { - gen_helper_pacib(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); - } - break; - case 0b01100: /* AUTIA1716 */ - if (s->pauth_active) { - gen_helper_autia(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); - } - break; - case 0b01110: /* AUTIB1716 */ - if (s->pauth_active) { - gen_helper_autib(cpu_X[17], cpu_env, cpu_X[17], cpu_X[16]); - } - break; - case 0b10000: /* ESB */ - /* Without RAS, we must implement this as NOP. */ - if (dc_isar_feature(aa64_ras, s)) { - /* - * QEMU does not have a source of physical SErrors, - * so we are only concerned with virtual SErrors. - * The pseudocode in the ARM for this case is - * if PSTATE.EL IN {EL0, EL1} && EL2Enabled() then - * AArch64.vESBOperation(); - * Most of the condition can be evaluated at translation time. - * Test for EL2 present, and defer test for SEL2 to runtime. - */ - if (s->current_el <= 1 && arm_dc_feature(s, ARM_FEATURE_EL2)) { - gen_helper_vesb(cpu_env); - } - } - break; - case 0b11000: /* PACIAZ */ - if (s->pauth_active) { - gen_helper_pacia(cpu_X[30], cpu_env, cpu_X[30], - tcg_constant_i64(0)); - } - break; - case 0b11001: /* PACIASP */ - if (s->pauth_active) { - gen_helper_pacia(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); - } - break; - case 0b11010: /* PACIBZ */ - if (s->pauth_active) { - gen_helper_pacib(cpu_X[30], cpu_env, cpu_X[30], - tcg_constant_i64(0)); - } - break; - case 0b11011: /* PACIBSP */ - if (s->pauth_active) { - gen_helper_pacib(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); - } - break; - case 0b11100: /* AUTIAZ */ - if (s->pauth_active) { - gen_helper_autia(cpu_X[30], cpu_env, cpu_X[30], - tcg_constant_i64(0)); - } - break; - case 0b11101: /* AUTIASP */ - if (s->pauth_active) { - gen_helper_autia(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); - } - break; - case 0b11110: /* AUTIBZ */ - if (s->pauth_active) { - gen_helper_autib(cpu_X[30], cpu_env, cpu_X[30], - tcg_constant_i64(0)); - } - break; - case 0b11111: /* AUTIBSP */ - if (s->pauth_active) { - gen_helper_autib(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); - } - break; - default: - /* default specified as NOP equivalent */ - break; } + return true; +} + +static bool trans_PACIAZ(DisasContext *s, arg_PACIAZ *a) +{ + if (s->pauth_active) { + gen_helper_pacia(cpu_X[30], cpu_env, cpu_X[30], tcg_constant_i64(0)); + } + return true; +} + +static bool trans_PACIASP(DisasContext *s, arg_PACIASP *a) +{ + if (s->pauth_active) { + gen_helper_pacia(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); + } + return true; +} + +static bool trans_PACIBZ(DisasContext *s, arg_PACIBZ *a) +{ + if (s->pauth_active) { + gen_helper_pacib(cpu_X[30], cpu_env, cpu_X[30], tcg_constant_i64(0)); + } + return true; +} + +static bool trans_PACIBSP(DisasContext *s, arg_PACIBSP *a) +{ + if (s->pauth_active) { + gen_helper_pacib(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); + } + return true; +} + +static bool trans_AUTIAZ(DisasContext *s, arg_AUTIAZ *a) +{ + if (s->pauth_active) { + gen_helper_autia(cpu_X[30], cpu_env, cpu_X[30], tcg_constant_i64(0)); + } + return true; +} + +static bool trans_AUTIASP(DisasContext *s, arg_AUTIASP *a) +{ + if (s->pauth_active) { + gen_helper_autia(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); + } + return true; +} + +static bool trans_AUTIBZ(DisasContext *s, arg_AUTIBZ *a) +{ + if (s->pauth_active) { + gen_helper_autib(cpu_X[30], cpu_env, cpu_X[30], tcg_constant_i64(0)); + } + return true; +} + +static bool trans_AUTIBSP(DisasContext *s, arg_AUTIBSP *a) +{ + if (s->pauth_active) { + gen_helper_autib(cpu_X[30], cpu_env, cpu_X[30], cpu_X[31]); + } + return true; } static void gen_clrex(DisasContext *s, uint32_t insn) @@ -XXX,XX +XXX,XX @@ static void disas_system(DisasContext *s, uint32_t insn) return; } switch (crn) { - case 2: /* HINT (including allocated hints like NOP, YIELD, etc) */ - handle_hint(s, insn, op1, op2, crm); - break; case 3: /* CLREX, DSB, DMB, ISB */ handle_sync(s, insn, op1, op2, crm); break; -- 2.34.1 Convert the insns in the "Barriers" instruction class to decodetree: CLREX, DSB, DMB, ISB and SB. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-4-peter.maydell@linaro.org Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> --- target/arm/tcg/a64.decode | 7 +++ target/arm/tcg/translate-a64.c | 92 ++++++++++++++-------------------- 2 files changed, 46 insertions(+), 53 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ ERETA 1101011 0100 11111 00001 m:1 11111 11111 &reta # ERETAA, ERETAB # that isn't specifically allocated to an instruction must NOP NOP 1101 0101 0000 0011 0010 ---- --- 11111 } + +# Barriers + +CLREX 1101 0101 0000 0011 0011 ---- 010 11111 +DSB_DMB 1101 0101 0000 0011 0011 domain:2 types:2 10- 11111 +ISB 1101 0101 0000 0011 0011 ---- 110 11111 +SB 1101 0101 0000 0011 0011 0000 111 11111 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_AUTIBSP(DisasContext *s, arg_AUTIBSP *a) return true; } -static void gen_clrex(DisasContext *s, uint32_t insn) +static bool trans_CLREX(DisasContext *s, arg_CLREX *a) { tcg_gen_movi_i64(cpu_exclusive_addr, -1); + return true; } -/* CLREX, DSB, DMB, ISB */ -static void handle_sync(DisasContext *s, uint32_t insn, - unsigned int op1, unsigned int op2, unsigned int crm) +static bool trans_DSB_DMB(DisasContext *s, arg_DSB_DMB *a) { + /* We handle DSB and DMB the same way */ TCGBar bar; - if (op1 != 3) { - unallocated_encoding(s); - return; + switch (a->types) { + case 1: /* MBReqTypes_Reads */ + bar = TCG_BAR_SC | TCG_MO_LD_LD | TCG_MO_LD_ST; + break; + case 2: /* MBReqTypes_Writes */ + bar = TCG_BAR_SC | TCG_MO_ST_ST; + break; + default: /* MBReqTypes_All */ + bar = TCG_BAR_SC | TCG_MO_ALL; + break; } + tcg_gen_mb(bar); + return true; +} - switch (op2) { - case 2: /* CLREX */ - gen_clrex(s, insn); - return; - case 4: /* DSB */ - case 5: /* DMB */ - switch (crm & 3) { - case 1: /* MBReqTypes_Reads */ - bar = TCG_BAR_SC | TCG_MO_LD_LD | TCG_MO_LD_ST; - break; - case 2: /* MBReqTypes_Writes */ - bar = TCG_BAR_SC | TCG_MO_ST_ST; - break; - default: /* MBReqTypes_All */ - bar = TCG_BAR_SC | TCG_MO_ALL; - break; - } - tcg_gen_mb(bar); - return; - case 6: /* ISB */ - /* We need to break the TB after this insn to execute - * a self-modified code correctly and also to take - * any pending interrupts immediately. - */ - reset_btype(s); - gen_goto_tb(s, 0, 4); - return; +static bool trans_ISB(DisasContext *s, arg_ISB *a) +{ + /* + * We need to break the TB after this insn to execute + * self-modifying code correctly and also to take + * any pending interrupts immediately. + */ + reset_btype(s); + gen_goto_tb(s, 0, 4); + return true; +} - case 7: /* SB */ - if (crm != 0 || !dc_isar_feature(aa64_sb, s)) { - goto do_unallocated; - } - /* - * TODO: There is no speculation barrier opcode for TCG; - * MB and end the TB instead. - */ - tcg_gen_mb(TCG_MO_ALL | TCG_BAR_SC); - gen_goto_tb(s, 0, 4); - return; - - default: - do_unallocated: - unallocated_encoding(s); - return; +static bool trans_SB(DisasContext *s, arg_SB *a) +{ + if (!dc_isar_feature(aa64_sb, s)) { + return false; } + /* + * TODO: There is no speculation barrier opcode for TCG; + * MB and end the TB instead. + */ + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_SC); + gen_goto_tb(s, 0, 4); + return true; } static void gen_xaflag(void) @@ -XXX,XX +XXX,XX @@ static void disas_system(DisasContext *s, uint32_t insn) return; } switch (crn) { - case 3: /* CLREX, DSB, DMB, ISB */ - handle_sync(s, insn, op1, op2, crm); - break; case 4: /* MSR (immediate) */ handle_msr_i(s, insn, op1, op2, crm); break; -- 2.34.1 Convert the CFINV, XAFLAG and AXFLAG insns to decodetree. The old decoder handles these in handle_msr_i(), but the architecture defines them as separate instructions from MSR (immediate). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-5-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 6 ++++ target/arm/tcg/translate-a64.c | 53 +++++++++++++++++----------------- 2 files changed, 32 insertions(+), 27 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ CLREX 1101 0101 0000 0011 0011 ---- 010 11111 DSB_DMB 1101 0101 0000 0011 0011 domain:2 types:2 10- 11111 ISB 1101 0101 0000 0011 0011 ---- 110 11111 SB 1101 0101 0000 0011 0011 0000 111 11111 + +# PSTATE + +CFINV 1101 0101 0000 0 000 0100 0000 000 11111 +XAFLAG 1101 0101 0000 0 000 0100 0000 001 11111 +AXFLAG 1101 0101 0000 0 000 0100 0000 010 11111 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_SB(DisasContext *s, arg_SB *a) return true; } -static void gen_xaflag(void) +static bool trans_CFINV(DisasContext *s, arg_CFINV *a) { - TCGv_i32 z = tcg_temp_new_i32(); + if (!dc_isar_feature(aa64_condm_4, s)) { + return false; + } + tcg_gen_xori_i32(cpu_CF, cpu_CF, 1); + return true; +} + +static bool trans_XAFLAG(DisasContext *s, arg_XAFLAG *a) +{ + TCGv_i32 z; + + if (!dc_isar_feature(aa64_condm_5, s)) { + return false; + } + + z = tcg_temp_new_i32(); tcg_gen_setcondi_i32(TCG_COND_EQ, z, cpu_ZF, 0); @@ -XXX,XX +XXX,XX @@ static void gen_xaflag(void) /* C | Z */ tcg_gen_or_i32(cpu_CF, cpu_CF, z); + + return true; } -static void gen_axflag(void) +static bool trans_AXFLAG(DisasContext *s, arg_AXFLAG *a) { + if (!dc_isar_feature(aa64_condm_5, s)) { + return false; + } + tcg_gen_sari_i32(cpu_VF, cpu_VF, 31); /* V ? -1 : 0 */ tcg_gen_andc_i32(cpu_CF, cpu_CF, cpu_VF); /* C & !V */ @@ -XXX,XX +XXX,XX @@ static void gen_axflag(void) tcg_gen_movi_i32(cpu_NF, 0); tcg_gen_movi_i32(cpu_VF, 0); + + return true; } /* MSR (immediate) - move immediate to processor state field */ @@ -XXX,XX +XXX,XX @@ static void handle_msr_i(DisasContext *s, uint32_t insn, s->base.is_jmp = DISAS_TOO_MANY; switch (op) { - case 0x00: /* CFINV */ - if (crm != 0 || !dc_isar_feature(aa64_condm_4, s)) { - goto do_unallocated; - } - tcg_gen_xori_i32(cpu_CF, cpu_CF, 1); - s->base.is_jmp = DISAS_NEXT; - break; - - case 0x01: /* XAFlag */ - if (crm != 0 || !dc_isar_feature(aa64_condm_5, s)) { - goto do_unallocated; - } - gen_xaflag(); - s->base.is_jmp = DISAS_NEXT; - break; - - case 0x02: /* AXFlag */ - if (crm != 0 || !dc_isar_feature(aa64_condm_5, s)) { - goto do_unallocated; - } - gen_axflag(); - s->base.is_jmp = DISAS_NEXT; - break; - case 0x03: /* UAO */ if (!dc_isar_feature(aa64_uao, s) || s->current_el == 0) { goto do_unallocated; -- 2.34.1 Convert the MSR (immediate) insn to decodetree. Our implementation has basically no commonality between the different destinations, so we decode the destination register in a64.decode. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-6-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 13 ++ target/arm/tcg/translate-a64.c | 251 ++++++++++++++++----------------- 2 files changed, 136 insertions(+), 128 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ SB 1101 0101 0000 0011 0011 0000 111 11111 CFINV 1101 0101 0000 0 000 0100 0000 000 11111 XAFLAG 1101 0101 0000 0 000 0100 0000 001 11111 AXFLAG 1101 0101 0000 0 000 0100 0000 010 11111 + +# These are architecturally all "MSR (immediate)"; we decode the destination +# register too because there is no commonality in our implementation. +@msr_i .... .... .... . ... .... imm:4 ... ..... +MSR_i_UAO 1101 0101 0000 0 000 0100 .... 011 11111 @msr_i +MSR_i_PAN 1101 0101 0000 0 000 0100 .... 100 11111 @msr_i +MSR_i_SPSEL 1101 0101 0000 0 000 0100 .... 101 11111 @msr_i +MSR_i_SBSS 1101 0101 0000 0 011 0100 .... 001 11111 @msr_i +MSR_i_DIT 1101 0101 0000 0 011 0100 .... 010 11111 @msr_i +MSR_i_TCO 1101 0101 0000 0 011 0100 .... 100 11111 @msr_i +MSR_i_DAIFSET 1101 0101 0000 0 011 0100 .... 110 11111 @msr_i +MSR_i_DAIFCLEAR 1101 0101 0000 0 011 0100 .... 111 11111 @msr_i +MSR_i_SVCR 1101 0101 0000 0 011 0100 0 mask:2 imm:1 011 11111 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_AXFLAG(DisasContext *s, arg_AXFLAG *a) return true; } -/* MSR (immediate) - move immediate to processor state field */ -static void handle_msr_i(DisasContext *s, uint32_t insn, - unsigned int op1, unsigned int op2, unsigned int crm) +static bool trans_MSR_i_UAO(DisasContext *s, arg_i *a) { - int op = op1 << 3 | op2; - - /* End the TB by default, chaining is ok. */ - s->base.is_jmp = DISAS_TOO_MANY; - - switch (op) { - case 0x03: /* UAO */ - if (!dc_isar_feature(aa64_uao, s) || s->current_el == 0) { - goto do_unallocated; - } - if (crm & 1) { - set_pstate_bits(PSTATE_UAO); - } else { - clear_pstate_bits(PSTATE_UAO); - } - gen_rebuild_hflags(s); - break; - - case 0x04: /* PAN */ - if (!dc_isar_feature(aa64_pan, s) || s->current_el == 0) { - goto do_unallocated; - } - if (crm & 1) { - set_pstate_bits(PSTATE_PAN); - } else { - clear_pstate_bits(PSTATE_PAN); - } - gen_rebuild_hflags(s); - break; - - case 0x05: /* SPSel */ - if (s->current_el == 0) { - goto do_unallocated; - } - gen_helper_msr_i_spsel(cpu_env, tcg_constant_i32(crm & PSTATE_SP)); - break; - - case 0x19: /* SSBS */ - if (!dc_isar_feature(aa64_ssbs, s)) { - goto do_unallocated; - } - if (crm & 1) { - set_pstate_bits(PSTATE_SSBS); - } else { - clear_pstate_bits(PSTATE_SSBS); - } - /* Don't need to rebuild hflags since SSBS is a nop */ - break; - - case 0x1a: /* DIT */ - if (!dc_isar_feature(aa64_dit, s)) { - goto do_unallocated; - } - if (crm & 1) { - set_pstate_bits(PSTATE_DIT); - } else { - clear_pstate_bits(PSTATE_DIT); - } - /* There's no need to rebuild hflags because DIT is a nop */ - break; - - case 0x1e: /* DAIFSet */ - gen_helper_msr_i_daifset(cpu_env, tcg_constant_i32(crm)); - break; - - case 0x1f: /* DAIFClear */ - gen_helper_msr_i_daifclear(cpu_env, tcg_constant_i32(crm)); - /* For DAIFClear, exit the cpu loop to re-evaluate pending IRQs. */ - s->base.is_jmp = DISAS_UPDATE_EXIT; - break; - - case 0x1c: /* TCO */ - if (dc_isar_feature(aa64_mte, s)) { - /* Full MTE is enabled -- set the TCO bit as directed. */ - if (crm & 1) { - set_pstate_bits(PSTATE_TCO); - } else { - clear_pstate_bits(PSTATE_TCO); - } - gen_rebuild_hflags(s); - /* Many factors, including TCO, go into MTE_ACTIVE. */ - s->base.is_jmp = DISAS_UPDATE_NOCHAIN; - } else if (dc_isar_feature(aa64_mte_insn_reg, s)) { - /* Only "instructions accessible at EL0" -- PSTATE.TCO is WI. */ - s->base.is_jmp = DISAS_NEXT; - } else { - goto do_unallocated; - } - break; - - case 0x1b: /* SVCR* */ - if (!dc_isar_feature(aa64_sme, s) || crm < 2 || crm > 7) { - goto do_unallocated; - } - if (sme_access_check(s)) { - int old = s->pstate_sm | (s->pstate_za << 1); - int new = (crm & 1) * 3; - int msk = (crm >> 1) & 3; - - if ((old ^ new) & msk) { - /* At least one bit changes. */ - gen_helper_set_svcr(cpu_env, tcg_constant_i32(new), - tcg_constant_i32(msk)); - } else { - s->base.is_jmp = DISAS_NEXT; - } - } - break; - - default: - do_unallocated: - unallocated_encoding(s); - return; + if (!dc_isar_feature(aa64_uao, s) || s->current_el == 0) { + return false; } + if (a->imm & 1) { + set_pstate_bits(PSTATE_UAO); + } else { + clear_pstate_bits(PSTATE_UAO); + } + gen_rebuild_hflags(s); + s->base.is_jmp = DISAS_TOO_MANY; + return true; +} + +static bool trans_MSR_i_PAN(DisasContext *s, arg_i *a) +{ + if (!dc_isar_feature(aa64_pan, s) || s->current_el == 0) { + return false; + } + if (a->imm & 1) { + set_pstate_bits(PSTATE_PAN); + } else { + clear_pstate_bits(PSTATE_PAN); + } + gen_rebuild_hflags(s); + s->base.is_jmp = DISAS_TOO_MANY; + return true; +} + +static bool trans_MSR_i_SPSEL(DisasContext *s, arg_i *a) +{ + if (s->current_el == 0) { + return false; + } + gen_helper_msr_i_spsel(cpu_env, tcg_constant_i32(a->imm & PSTATE_SP)); + s->base.is_jmp = DISAS_TOO_MANY; + return true; +} + +static bool trans_MSR_i_SBSS(DisasContext *s, arg_i *a) +{ + if (!dc_isar_feature(aa64_ssbs, s)) { + return false; + } + if (a->imm & 1) { + set_pstate_bits(PSTATE_SSBS); + } else { + clear_pstate_bits(PSTATE_SSBS); + } + /* Don't need to rebuild hflags since SSBS is a nop */ + s->base.is_jmp = DISAS_TOO_MANY; + return true; +} + +static bool trans_MSR_i_DIT(DisasContext *s, arg_i *a) +{ + if (!dc_isar_feature(aa64_dit, s)) { + return false; + } + if (a->imm & 1) { + set_pstate_bits(PSTATE_DIT); + } else { + clear_pstate_bits(PSTATE_DIT); + } + /* There's no need to rebuild hflags because DIT is a nop */ + s->base.is_jmp = DISAS_TOO_MANY; + return true; +} + +static bool trans_MSR_i_TCO(DisasContext *s, arg_i *a) +{ + if (dc_isar_feature(aa64_mte, s)) { + /* Full MTE is enabled -- set the TCO bit as directed. */ + if (a->imm & 1) { + set_pstate_bits(PSTATE_TCO); + } else { + clear_pstate_bits(PSTATE_TCO); + } + gen_rebuild_hflags(s); + /* Many factors, including TCO, go into MTE_ACTIVE. */ + s->base.is_jmp = DISAS_UPDATE_NOCHAIN; + return true; + } else if (dc_isar_feature(aa64_mte_insn_reg, s)) { + /* Only "instructions accessible at EL0" -- PSTATE.TCO is WI. */ + return true; + } else { + /* Insn not present */ + return false; + } +} + +static bool trans_MSR_i_DAIFSET(DisasContext *s, arg_i *a) +{ + gen_helper_msr_i_daifset(cpu_env, tcg_constant_i32(a->imm)); + s->base.is_jmp = DISAS_TOO_MANY; + return true; +} + +static bool trans_MSR_i_DAIFCLEAR(DisasContext *s, arg_i *a) +{ + gen_helper_msr_i_daifclear(cpu_env, tcg_constant_i32(a->imm)); + /* Exit the cpu loop to re-evaluate pending IRQs. */ + s->base.is_jmp = DISAS_UPDATE_EXIT; + return true; +} + +static bool trans_MSR_i_SVCR(DisasContext *s, arg_MSR_i_SVCR *a) +{ + if (!dc_isar_feature(aa64_sme, s) || a->mask == 0) { + return false; + } + if (sme_access_check(s)) { + int old = s->pstate_sm | (s->pstate_za << 1); + int new = a->imm * 3; + + if ((old ^ new) & a->mask) { + /* At least one bit changes. */ + gen_helper_set_svcr(cpu_env, tcg_constant_i32(new), + tcg_constant_i32(a->mask)); + s->base.is_jmp = DISAS_TOO_MANY; + } + } + return true; } static void gen_get_nzcv(TCGv_i64 tcg_rt) @@ -XXX,XX +XXX,XX @@ static void disas_system(DisasContext *s, uint32_t insn) rt = extract32(insn, 0, 5); if (op0 == 0) { - if (l || rt != 31) { - unallocated_encoding(s); - return; - } - switch (crn) { - case 4: /* MSR (immediate) */ - handle_msr_i(s, insn, op1, op2, crm); - break; - default: - unallocated_encoding(s); - break; - } + unallocated_encoding(s); return; } handle_sys(s, insn, l, op0, op1, op2, crn, crm, rt); -- 2.34.1 Convert MSR (reg), MRS, SYS, SYSL to decodetree. For QEMU these are all essentially the same instruction (system register access). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-7-peter.maydell@linaro.org Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> --- target/arm/tcg/a64.decode | 8 ++++++++ target/arm/tcg/translate-a64.c | 32 +++++--------------------------- 2 files changed, 13 insertions(+), 27 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ MSR_i_TCO 1101 0101 0000 0 011 0100 .... 100 11111 @msr_i MSR_i_DAIFSET 1101 0101 0000 0 011 0100 .... 110 11111 @msr_i MSR_i_DAIFCLEAR 1101 0101 0000 0 011 0100 .... 111 11111 @msr_i MSR_i_SVCR 1101 0101 0000 0 011 0100 0 mask:2 imm:1 011 11111 + +# MRS, MSR (register), SYS, SYSL. These are all essentially the +# same instruction as far as QEMU is concerned. +# NB: op0 is bits [20:19], but op0=0b00 is other insns, so we have +# to hand-decode it. +SYS 1101 0101 00 l:1 01 op1:3 crn:4 crm:4 op2:3 rt:5 op0=1 +SYS 1101 0101 00 l:1 10 op1:3 crn:4 crm:4 op2:3 rt:5 op0=2 +SYS 1101 0101 00 l:1 11 op1:3 crn:4 crm:4 op2:3 rt:5 op0=3 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_sysreg_undef(DisasContext *s, bool isread, * These are all essentially the same insn in 'read' and 'write' * versions, with varying op0 fields. */ -static void handle_sys(DisasContext *s, uint32_t insn, bool isread, +static void handle_sys(DisasContext *s, bool isread, unsigned int op0, unsigned int op1, unsigned int op2, unsigned int crn, unsigned int crm, unsigned int rt) { @@ -XXX,XX +XXX,XX @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, } } -/* System - * 31 22 21 20 19 18 16 15 12 11 8 7 5 4 0 - * +---------------------+---+-----+-----+-------+-------+-----+------+ - * | 1 1 0 1 0 1 0 1 0 0 | L | op0 | op1 | CRn | CRm | op2 | Rt | - * +---------------------+---+-----+-----+-------+-------+-----+------+ - */ -static void disas_system(DisasContext *s, uint32_t insn) +static bool trans_SYS(DisasContext *s, arg_SYS *a) { - unsigned int l, op0, op1, crn, crm, op2, rt; - l = extract32(insn, 21, 1); - op0 = extract32(insn, 19, 2); - op1 = extract32(insn, 16, 3); - crn = extract32(insn, 12, 4); - crm = extract32(insn, 8, 4); - op2 = extract32(insn, 5, 3); - rt = extract32(insn, 0, 5); - - if (op0 == 0) { - unallocated_encoding(s); - return; - } - handle_sys(s, insn, l, op0, op1, op2, crn, crm, rt); + handle_sys(s, a->l, a->op0, a->op1, a->op2, a->crn, a->crm, a->rt); + return true; } /* Exception generation @@ -XXX,XX +XXX,XX @@ static void disas_b_exc_sys(DisasContext *s, uint32_t insn) switch (extract32(insn, 25, 7)) { case 0x6a: /* Exception generation / System */ if (insn & (1 << 24)) { - if (extract32(insn, 22, 2) == 0) { - disas_system(s, insn); - } else { - unallocated_encoding(s); - } + unallocated_encoding(s); } else { disas_exc(s, insn); } -- 2.34.1 Convert the exception generation instructions SVC, HVC, SMC, BRK and HLT to decodetree. The old decoder decoded the halting-debug insnns DCPS1, DCPS2 and DCPS3 just in order to then make them UNDEF; as with DRPS, we don't bother to decode them, but document the patterns in a64.decode. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-8-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 15 +++ target/arm/tcg/translate-a64.c | 173 ++++++++++++--------------------- 2 files changed, 79 insertions(+), 109 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ MSR_i_SVCR 1101 0101 0000 0 011 0100 0 mask:2 imm:1 011 11111 SYS 1101 0101 00 l:1 01 op1:3 crn:4 crm:4 op2:3 rt:5 op0=1 SYS 1101 0101 00 l:1 10 op1:3 crn:4 crm:4 op2:3 rt:5 op0=2 SYS 1101 0101 00 l:1 11 op1:3 crn:4 crm:4 op2:3 rt:5 op0=3 + +# Exception generation + +@i16 .... .... ... imm:16 ... .. &i +SVC 1101 0100 000 ................ 000 01 @i16 +HVC 1101 0100 000 ................ 000 10 @i16 +SMC 1101 0100 000 ................ 000 11 @i16 +BRK 1101 0100 001 ................ 000 00 @i16 +HLT 1101 0100 010 ................ 000 00 @i16 +# These insns always UNDEF unless in halting debug state, which +# we don't implement. So we don't need to decode them. The patterns +# are listed here as documentation. +# DCPS1 1101 0100 101 ................ 000 01 @i16 +# DCPS2 1101 0100 101 ................ 000 10 @i16 +# DCPS3 1101 0100 101 ................ 000 11 @i16 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_SYS(DisasContext *s, arg_SYS *a) return true; } -/* Exception generation - * - * 31 24 23 21 20 5 4 2 1 0 - * +-----------------+-----+------------------------+-----+----+ - * | 1 1 0 1 0 1 0 0 | opc | imm16 | op2 | LL | - * +-----------------------+------------------------+----------+ - */ -static void disas_exc(DisasContext *s, uint32_t insn) +static bool trans_SVC(DisasContext *s, arg_i *a) { - int opc = extract32(insn, 21, 3); - int op2_ll = extract32(insn, 0, 5); - int imm16 = extract32(insn, 5, 16); - uint32_t syndrome; - - switch (opc) { - case 0: - /* For SVC, HVC and SMC we advance the single-step state - * machine before taking the exception. This is architecturally - * mandated, to ensure that single-stepping a system call - * instruction works properly. - */ - switch (op2_ll) { - case 1: /* SVC */ - syndrome = syn_aa64_svc(imm16); - if (s->fgt_svc) { - gen_exception_insn_el(s, 0, EXCP_UDEF, syndrome, 2); - break; - } - gen_ss_advance(s); - gen_exception_insn(s, 4, EXCP_SWI, syndrome); - break; - case 2: /* HVC */ - if (s->current_el == 0) { - unallocated_encoding(s); - break; - } - /* The pre HVC helper handles cases when HVC gets trapped - * as an undefined insn by runtime configuration. - */ - gen_a64_update_pc(s, 0); - gen_helper_pre_hvc(cpu_env); - gen_ss_advance(s); - gen_exception_insn_el(s, 4, EXCP_HVC, syn_aa64_hvc(imm16), 2); - break; - case 3: /* SMC */ - if (s->current_el == 0) { - unallocated_encoding(s); - break; - } - gen_a64_update_pc(s, 0); - gen_helper_pre_smc(cpu_env, tcg_constant_i32(syn_aa64_smc(imm16))); - gen_ss_advance(s); - gen_exception_insn_el(s, 4, EXCP_SMC, syn_aa64_smc(imm16), 3); - break; - default: - unallocated_encoding(s); - break; - } - break; - case 1: - if (op2_ll != 0) { - unallocated_encoding(s); - break; - } - /* BRK */ - gen_exception_bkpt_insn(s, syn_aa64_bkpt(imm16)); - break; - case 2: - if (op2_ll != 0) { - unallocated_encoding(s); - break; - } - /* HLT. This has two purposes. - * Architecturally, it is an external halting debug instruction. - * Since QEMU doesn't implement external debug, we treat this as - * it is required for halting debug disabled: it will UNDEF. - * Secondly, "HLT 0xf000" is the A64 semihosting syscall instruction. - */ - if (semihosting_enabled(s->current_el == 0) && imm16 == 0xf000) { - gen_exception_internal_insn(s, EXCP_SEMIHOST); - } else { - unallocated_encoding(s); - } - break; - case 5: - if (op2_ll < 1 || op2_ll > 3) { - unallocated_encoding(s); - break; - } - /* DCPS1, DCPS2, DCPS3 */ - unallocated_encoding(s); - break; - default: - unallocated_encoding(s); - break; + /* + * For SVC, HVC and SMC we advance the single-step state + * machine before taking the exception. This is architecturally + * mandated, to ensure that single-stepping a system call + * instruction works properly. + */ + uint32_t syndrome = syn_aa64_svc(a->imm); + if (s->fgt_svc) { + gen_exception_insn_el(s, 0, EXCP_UDEF, syndrome, 2); + return true; } + gen_ss_advance(s); + gen_exception_insn(s, 4, EXCP_SWI, syndrome); + return true; } -/* Branches, exception generating and system instructions */ -static void disas_b_exc_sys(DisasContext *s, uint32_t insn) +static bool trans_HVC(DisasContext *s, arg_i *a) { - switch (extract32(insn, 25, 7)) { - case 0x6a: /* Exception generation / System */ - if (insn & (1 << 24)) { - unallocated_encoding(s); - } else { - disas_exc(s, insn); - } - break; - default: + if (s->current_el == 0) { unallocated_encoding(s); - break; + return true; } + /* + * The pre HVC helper handles cases when HVC gets trapped + * as an undefined insn by runtime configuration. + */ + gen_a64_update_pc(s, 0); + gen_helper_pre_hvc(cpu_env); + /* Architecture requires ss advance before we do the actual work */ + gen_ss_advance(s); + gen_exception_insn_el(s, 4, EXCP_HVC, syn_aa64_hvc(a->imm), 2); + return true; +} + +static bool trans_SMC(DisasContext *s, arg_i *a) +{ + if (s->current_el == 0) { + unallocated_encoding(s); + return true; + } + gen_a64_update_pc(s, 0); + gen_helper_pre_smc(cpu_env, tcg_constant_i32(syn_aa64_smc(a->imm))); + /* Architecture requires ss advance before we do the actual work */ + gen_ss_advance(s); + gen_exception_insn_el(s, 4, EXCP_SMC, syn_aa64_smc(a->imm), 3); + return true; +} + +static bool trans_BRK(DisasContext *s, arg_i *a) +{ + gen_exception_bkpt_insn(s, syn_aa64_bkpt(a->imm)); + return true; +} + +static bool trans_HLT(DisasContext *s, arg_i *a) +{ + /* + * HLT. This has two purposes. + * Architecturally, it is an external halting debug instruction. + * Since QEMU doesn't implement external debug, we treat this as + * it is required for halting debug disabled: it will UNDEF. + * Secondly, "HLT 0xf000" is the A64 semihosting syscall instruction. + */ + if (semihosting_enabled(s->current_el == 0) && a->imm == 0xf000) { + gen_exception_internal_insn(s, EXCP_SEMIHOST); + } else { + unallocated_encoding(s); + } + return true; } /* @@ -XXX,XX +XXX,XX @@ static bool btype_destination_ok(uint32_t insn, bool bt, int btype) static void disas_a64_legacy(DisasContext *s, uint32_t insn) { switch (extract32(insn, 25, 4)) { - case 0xa: case 0xb: /* Branch, exception generation and system insns */ - disas_b_exc_sys(s, insn); - break; case 0x4: case 0x6: case 0xc: -- 2.34.1 Convert the instructions in the load/store exclusive (STXR, STLXR, LDXR, LDAXR) and load/store ordered (STLR, STLLR, LDAR, LDLAR) to decodetree. Note that for STLR, STLLR, LDAR, LDLAR this fixes an under-decoding in the legacy decoder where we were not checking that the RES1 bits in the Rs and Rt2 fields were set. The new function ldst_iss_sf() is equivalent to the existing disas_ldst_compute_iss_sf(), but it takes the pre-decoded 'ext' field rather than taking an undecoded two-bit opc field and extracting 'ext' from it. Once all the loads and stores have been converted to decodetree disas_ldst_compute_iss_sf() will be unused and can be deleted. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-9-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 11 +++ target/arm/tcg/translate-a64.c | 154 ++++++++++++++++++++------------- 2 files changed, 103 insertions(+), 62 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ HLT 1101 0100 010 ................ 000 00 @i16 # DCPS1 1101 0100 101 ................ 000 01 @i16 # DCPS2 1101 0100 101 ................ 000 10 @i16 # DCPS3 1101 0100 101 ................ 000 11 @i16 + +# Loads and stores + +&stxr rn rt rt2 rs sz lasr +&stlr rn rt sz lasr +@stxr sz:2 ...... ... rs:5 lasr:1 rt2:5 rn:5 rt:5 &stxr +@stlr sz:2 ...... ... ..... lasr:1 ..... rn:5 rt:5 &stlr +STXR .. 001000 000 ..... . ..... ..... ..... @stxr # inc STLXR +LDXR .. 001000 010 ..... . ..... ..... ..... @stxr # inc LDAXR +STLR .. 001000 100 11111 . 11111 ..... ..... @stlr # inc STLLR +LDAR .. 001000 110 11111 . 11111 ..... ..... @stlr # inc LDLAR diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool disas_ldst_compute_iss_sf(int size, bool is_signed, int opc) return regsize == 64; } +static bool ldst_iss_sf(int size, bool sign, bool ext) +{ + + if (sign) { + /* + * Signed loads are 64 bit results if we are not going to + * do a zero-extend from 32 to 64 after the load. + * (For a store, sign and ext are always false.) + */ + return !ext; + } else { + /* Unsigned loads/stores work at the specified size */ + return size == MO_64; + } +} + +static bool trans_STXR(DisasContext *s, arg_stxr *a) +{ + if (a->rn == 31) { + gen_check_sp_alignment(s); + } + if (a->lasr) { + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); + } + gen_store_exclusive(s, a->rs, a->rt, a->rt2, a->rn, a->sz, false); + return true; +} + +static bool trans_LDXR(DisasContext *s, arg_stxr *a) +{ + if (a->rn == 31) { + gen_check_sp_alignment(s); + } + gen_load_exclusive(s, a->rt, a->rt2, a->rn, a->sz, false); + if (a->lasr) { + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); + } + return true; +} + +static bool trans_STLR(DisasContext *s, arg_stlr *a) +{ + TCGv_i64 clean_addr; + MemOp memop; + bool iss_sf = ldst_iss_sf(a->sz, false, false); + + /* + * StoreLORelease is the same as Store-Release for QEMU, but + * needs the feature-test. + */ + if (!a->lasr && !dc_isar_feature(aa64_lor, s)) { + return false; + } + /* Generate ISS for non-exclusive accesses including LASR. */ + if (a->rn == 31) { + gen_check_sp_alignment(s); + } + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); + memop = check_ordered_align(s, a->rn, 0, true, a->sz); + clean_addr = gen_mte_check1(s, cpu_reg_sp(s, a->rn), + true, a->rn != 31, memop); + do_gpr_st(s, cpu_reg(s, a->rt), clean_addr, memop, true, a->rt, + iss_sf, a->lasr); + return true; +} + +static bool trans_LDAR(DisasContext *s, arg_stlr *a) +{ + TCGv_i64 clean_addr; + MemOp memop; + bool iss_sf = ldst_iss_sf(a->sz, false, false); + + /* LoadLOAcquire is the same as Load-Acquire for QEMU. */ + if (!a->lasr && !dc_isar_feature(aa64_lor, s)) { + return false; + } + /* Generate ISS for non-exclusive accesses including LASR. */ + if (a->rn == 31) { + gen_check_sp_alignment(s); + } + memop = check_ordered_align(s, a->rn, 0, false, a->sz); + clean_addr = gen_mte_check1(s, cpu_reg_sp(s, a->rn), + false, a->rn != 31, memop); + do_gpr_ld(s, cpu_reg(s, a->rt), clean_addr, memop, false, true, + a->rt, iss_sf, a->lasr); + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); + return true; +} + /* Load/store exclusive * * 31 30 29 24 23 22 21 20 16 15 14 10 9 5 4 0 @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) int is_lasr = extract32(insn, 15, 1); int o2_L_o1_o0 = extract32(insn, 21, 3) * 2 | is_lasr; int size = extract32(insn, 30, 2); - TCGv_i64 clean_addr; - MemOp memop; switch (o2_L_o1_o0) { - case 0x0: /* STXR */ - case 0x1: /* STLXR */ - if (rn == 31) { - gen_check_sp_alignment(s); - } - if (is_lasr) { - tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); - } - gen_store_exclusive(s, rs, rt, rt2, rn, size, false); - return; - - case 0x4: /* LDXR */ - case 0x5: /* LDAXR */ - if (rn == 31) { - gen_check_sp_alignment(s); - } - gen_load_exclusive(s, rt, rt2, rn, size, false); - if (is_lasr) { - tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); - } - return; - - case 0x8: /* STLLR */ - if (!dc_isar_feature(aa64_lor, s)) { - break; - } - /* StoreLORelease is the same as Store-Release for QEMU. */ - /* fall through */ - case 0x9: /* STLR */ - /* Generate ISS for non-exclusive accesses including LASR. */ - if (rn == 31) { - gen_check_sp_alignment(s); - } - tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); - memop = check_ordered_align(s, rn, 0, true, size); - clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), - true, rn != 31, memop); - do_gpr_st(s, cpu_reg(s, rt), clean_addr, memop, true, rt, - disas_ldst_compute_iss_sf(size, false, 0), is_lasr); - return; - - case 0xc: /* LDLAR */ - if (!dc_isar_feature(aa64_lor, s)) { - break; - } - /* LoadLOAcquire is the same as Load-Acquire for QEMU. */ - /* fall through */ - case 0xd: /* LDAR */ - /* Generate ISS for non-exclusive accesses including LASR. */ - if (rn == 31) { - gen_check_sp_alignment(s); - } - memop = check_ordered_align(s, rn, 0, false, size); - clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), - false, rn != 31, memop); - do_gpr_ld(s, cpu_reg(s, rt), clean_addr, memop, false, true, - rt, disas_ldst_compute_iss_sf(size, false, 0), is_lasr); - tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); - return; - case 0x2: case 0x3: /* CASP / STXP */ if (size & 2) { /* STXP / STLXP */ if (rn == 31) { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_excl(DisasContext *s, uint32_t insn) return; } break; + default: + /* Handled in decodetree */ + break; } unallocated_encoding(s); } -- 2.34.1 Convert the load/store exclusive pair (LDXP, STXP, LDAXP, STLXP), compare-and-swap pair (CASP, CASPA, CASPAL, CASPL), and compare-and swap (CAS, CASA, CASAL, CASL) instructions to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-10-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 11 +++ target/arm/tcg/translate-a64.c | 121 ++++++++++++--------------------- 2 files changed, 53 insertions(+), 79 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ HLT 1101 0100 010 ................ 000 00 @i16 &stlr rn rt sz lasr @stxr sz:2 ...... ... rs:5 lasr:1 rt2:5 rn:5 rt:5 &stxr @stlr sz:2 ...... ... ..... lasr:1 ..... rn:5 rt:5 &stlr +%imm1_30_p2 30:1 !function=plus_2 +@stxp .. ...... ... rs:5 lasr:1 rt2:5 rn:5 rt:5 &stxr sz=%imm1_30_p2 STXR .. 001000 000 ..... . ..... ..... ..... @stxr # inc STLXR LDXR .. 001000 010 ..... . ..... ..... ..... @stxr # inc LDAXR STLR .. 001000 100 11111 . 11111 ..... ..... @stlr # inc STLLR LDAR .. 001000 110 11111 . 11111 ..... ..... @stlr # inc LDLAR + +STXP 1 . 001000 001 ..... . ..... ..... ..... @stxp # inc STLXP +LDXP 1 . 001000 011 ..... . ..... ..... ..... @stxp # inc LDAXP + +# CASP, CASPA, CASPAL, CASPL (we don't decode the bits that determine +# acquire/release semantics because QEMU's cmpxchg always has those) +CASP 0 . 001000 0 - 1 rs:5 - 11111 rn:5 rt:5 sz=%imm1_30_p2 +# CAS, CASA, CASAL, CASL +CAS sz:2 001000 1 - 1 rs:5 - 11111 rn:5 rt:5 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_LDAR(DisasContext *s, arg_stlr *a) return true; } -/* Load/store exclusive - * - * 31 30 29 24 23 22 21 20 16 15 14 10 9 5 4 0 - * +-----+-------------+----+---+----+------+----+-------+------+------+ - * | sz | 0 0 1 0 0 0 | o2 | L | o1 | Rs | o0 | Rt2 | Rn | Rt | - * +-----+-------------+----+---+----+------+----+-------+------+------+ - * - * sz: 00 -> 8 bit, 01 -> 16 bit, 10 -> 32 bit, 11 -> 64 bit - * L: 0 -> store, 1 -> load - * o2: 0 -> exclusive, 1 -> not - * o1: 0 -> single register, 1 -> register pair - * o0: 1 -> load-acquire/store-release, 0 -> not - */ -static void disas_ldst_excl(DisasContext *s, uint32_t insn) +static bool trans_STXP(DisasContext *s, arg_stxr *a) { - int rt = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int rt2 = extract32(insn, 10, 5); - int rs = extract32(insn, 16, 5); - int is_lasr = extract32(insn, 15, 1); - int o2_L_o1_o0 = extract32(insn, 21, 3) * 2 | is_lasr; - int size = extract32(insn, 30, 2); - - switch (o2_L_o1_o0) { - case 0x2: case 0x3: /* CASP / STXP */ - if (size & 2) { /* STXP / STLXP */ - if (rn == 31) { - gen_check_sp_alignment(s); - } - if (is_lasr) { - tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); - } - gen_store_exclusive(s, rs, rt, rt2, rn, size, true); - return; - } - if (rt2 == 31 - && ((rt | rs) & 1) == 0 - && dc_isar_feature(aa64_atomics, s)) { - /* CASP / CASPL */ - gen_compare_and_swap_pair(s, rs, rt, rn, size | 2); - return; - } - break; - - case 0x6: case 0x7: /* CASPA / LDXP */ - if (size & 2) { /* LDXP / LDAXP */ - if (rn == 31) { - gen_check_sp_alignment(s); - } - gen_load_exclusive(s, rt, rt2, rn, size, true); - if (is_lasr) { - tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); - } - return; - } - if (rt2 == 31 - && ((rt | rs) & 1) == 0 - && dc_isar_feature(aa64_atomics, s)) { - /* CASPA / CASPAL */ - gen_compare_and_swap_pair(s, rs, rt, rn, size | 2); - return; - } - break; - - case 0xa: /* CAS */ - case 0xb: /* CASL */ - case 0xe: /* CASA */ - case 0xf: /* CASAL */ - if (rt2 == 31 && dc_isar_feature(aa64_atomics, s)) { - gen_compare_and_swap(s, rs, rt, rn, size); - return; - } - break; - default: - /* Handled in decodetree */ - break; + if (a->rn == 31) { + gen_check_sp_alignment(s); } - unallocated_encoding(s); + if (a->lasr) { + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); + } + gen_store_exclusive(s, a->rs, a->rt, a->rt2, a->rn, a->sz, true); + return true; +} + +static bool trans_LDXP(DisasContext *s, arg_stxr *a) +{ + if (a->rn == 31) { + gen_check_sp_alignment(s); + } + gen_load_exclusive(s, a->rt, a->rt2, a->rn, a->sz, true); + if (a->lasr) { + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); + } + return true; +} + +static bool trans_CASP(DisasContext *s, arg_CASP *a) +{ + if (!dc_isar_feature(aa64_atomics, s)) { + return false; + } + if (((a->rt | a->rs) & 1) != 0) { + return false; + } + + gen_compare_and_swap_pair(s, a->rs, a->rt, a->rn, a->sz); + return true; +} + +static bool trans_CAS(DisasContext *s, arg_CAS *a) +{ + if (!dc_isar_feature(aa64_atomics, s)) { + return false; + } + gen_compare_and_swap(s, a->rs, a->rt, a->rn, a->sz); + return true; } /* @@ -XXX,XX +XXX,XX @@ static void disas_ldst_tag(DisasContext *s, uint32_t insn) static void disas_ldst(DisasContext *s, uint32_t insn) { switch (extract32(insn, 24, 6)) { - case 0x08: /* Load/store exclusive */ - disas_ldst_excl(s, insn); - break; case 0x18: case 0x1c: /* Load register (literal) */ disas_ld_lit(s, insn); break; -- 2.34.1 Convert the "Load register (literal)" instruction class to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-11-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 13 ++++++ target/arm/tcg/translate-a64.c | 76 ++++++++++------------------------ 2 files changed, 35 insertions(+), 54 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ LDXP 1 . 001000 011 ..... . ..... ..... ..... @stxp # inc LDAXP CASP 0 . 001000 0 - 1 rs:5 - 11111 rn:5 rt:5 sz=%imm1_30_p2 # CAS, CASA, CASAL, CASL CAS sz:2 001000 1 - 1 rs:5 - 11111 rn:5 rt:5 + +&ldlit rt imm sz sign +@ldlit .. ... . .. ................... rt:5 &ldlit imm=%imm19 + +LD_lit 00 011 0 00 ................... ..... @ldlit sz=2 sign=0 +LD_lit 01 011 0 00 ................... ..... @ldlit sz=3 sign=0 +LD_lit 10 011 0 00 ................... ..... @ldlit sz=2 sign=1 +LD_lit_v 00 011 1 00 ................... ..... @ldlit sz=2 sign=0 +LD_lit_v 01 011 1 00 ................... ..... @ldlit sz=3 sign=0 +LD_lit_v 10 011 1 00 ................... ..... @ldlit sz=4 sign=0 + +# PRFM +NOP 11 011 0 00 ------------------- ----- diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_CAS(DisasContext *s, arg_CAS *a) return true; } -/* - * Load register (literal) - * - * 31 30 29 27 26 25 24 23 5 4 0 - * +-----+-------+---+-----+-------------------+-------+ - * | opc | 0 1 1 | V | 0 0 | imm19 | Rt | - * +-----+-------+---+-----+-------------------+-------+ - * - * V: 1 -> vector (simd/fp) - * opc (non-vector): 00 -> 32 bit, 01 -> 64 bit, - * 10-> 32 bit signed, 11 -> prefetch - * opc (vector): 00 -> 32 bit, 01 -> 64 bit, 10 -> 128 bit (11 unallocated) - */ -static void disas_ld_lit(DisasContext *s, uint32_t insn) +static bool trans_LD_lit(DisasContext *s, arg_ldlit *a) { - int rt = extract32(insn, 0, 5); - int64_t imm = sextract32(insn, 5, 19) << 2; - bool is_vector = extract32(insn, 26, 1); - int opc = extract32(insn, 30, 2); - bool is_signed = false; - int size = 2; - TCGv_i64 tcg_rt, clean_addr; + bool iss_sf = ldst_iss_sf(a->sz, a->sign, false); + TCGv_i64 tcg_rt = cpu_reg(s, a->rt); + TCGv_i64 clean_addr = tcg_temp_new_i64(); + MemOp memop = finalize_memop(s, a->sz + a->sign * MO_SIGN); + + gen_pc_plus_diff(s, clean_addr, a->imm); + do_gpr_ld(s, tcg_rt, clean_addr, memop, + false, true, a->rt, iss_sf, false); + return true; +} + +static bool trans_LD_lit_v(DisasContext *s, arg_ldlit *a) +{ + /* Load register (literal), vector version */ + TCGv_i64 clean_addr; MemOp memop; - if (is_vector) { - if (opc == 3) { - unallocated_encoding(s); - return; - } - size = 2 + opc; - if (!fp_access_check(s)) { - return; - } - memop = finalize_memop_asimd(s, size); - } else { - if (opc == 3) { - /* PRFM (literal) : prefetch */ - return; - } - size = 2 + extract32(opc, 0, 1); - is_signed = extract32(opc, 1, 1); - memop = finalize_memop(s, size + is_signed * MO_SIGN); + if (!fp_access_check(s)) { + return true; } - - tcg_rt = cpu_reg(s, rt); - + memop = finalize_memop_asimd(s, a->sz); clean_addr = tcg_temp_new_i64(); - gen_pc_plus_diff(s, clean_addr, imm); - - if (is_vector) { - do_fp_ld(s, rt, clean_addr, memop); - } else { - /* Only unsigned 32bit loads target 32bit registers. */ - bool iss_sf = opc != 0; - do_gpr_ld(s, tcg_rt, clean_addr, memop, false, true, rt, iss_sf, false); - } + gen_pc_plus_diff(s, clean_addr, a->imm); + do_fp_ld(s, a->rt, clean_addr, memop); + return true; } /* @@ -XXX,XX +XXX,XX @@ static void disas_ldst_tag(DisasContext *s, uint32_t insn) static void disas_ldst(DisasContext *s, uint32_t insn) { switch (extract32(insn, 24, 6)) { - case 0x18: case 0x1c: /* Load register (literal) */ - disas_ld_lit(s, insn); - break; case 0x28: case 0x29: case 0x2c: case 0x2d: /* Load/store pair (all forms) */ disas_ldst_pair(s, insn); -- 2.34.1 Convert the load/store register pair insns (LDP, STP, LDNP, STNP, LDPSW, STGP) to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20230602155223.2040685-12-peter.maydell@linaro.org Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/tcg/a64.decode | 61 +++++ target/arm/tcg/translate-a64.c | 422 ++++++++++++++++----------------- 2 files changed, 268 insertions(+), 215 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ LD_lit_v 10 011 1 00 ................... ..... @ldlit sz=4 sign=0 # PRFM NOP 11 011 0 00 ------------------- ----- + +&ldstpair rt2 rt rn imm sz sign w p +@ldstpair .. ... . ... . imm:s7 rt2:5 rn:5 rt:5 &ldstpair + +# STNP, LDNP: Signed offset, non-temporal hint. We don't emulate caches +# so we ignore hints about data access patterns, and handle these like +# plain signed offset. +STP 00 101 0 000 0 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=0 w=0 +LDP 00 101 0 000 1 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=0 w=0 +STP 10 101 0 000 0 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=0 +LDP 10 101 0 000 1 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=0 +STP_v 00 101 1 000 0 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=0 w=0 +LDP_v 00 101 1 000 1 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=0 w=0 +STP_v 01 101 1 000 0 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=0 +LDP_v 01 101 1 000 1 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=0 +STP_v 10 101 1 000 0 ....... ..... ..... ..... @ldstpair sz=4 sign=0 p=0 w=0 +LDP_v 10 101 1 000 1 ....... ..... ..... ..... @ldstpair sz=4 sign=0 p=0 w=0 + +# STP and LDP: post-indexed +STP 00 101 0 001 0 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=1 w=1 +LDP 00 101 0 001 1 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=1 w=1 +LDP 01 101 0 001 1 ....... ..... ..... ..... @ldstpair sz=2 sign=1 p=1 w=1 +STP 10 101 0 001 0 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=1 w=1 +LDP 10 101 0 001 1 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=1 w=1 +STP_v 00 101 1 001 0 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=1 w=1 +LDP_v 00 101 1 001 1 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=1 w=1 +STP_v 01 101 1 001 0 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=1 w=1 +LDP_v 01 101 1 001 1 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=1 w=1 +STP_v 10 101 1 001 0 ....... ..... ..... ..... @ldstpair sz=4 sign=0 p=1 w=1 +LDP_v 10 101 1 001 1 ....... ..... ..... ..... @ldstpair sz=4 sign=0 p=1 w=1 + +# STP and LDP: offset +STP 00 101 0 010 0 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=0 w=0 +LDP 00 101 0 010 1 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=0 w=0 +LDP 01 101 0 010 1 ....... ..... ..... ..... @ldstpair sz=2 sign=1 p=0 w=0 +STP 10 101 0 010 0 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=0 +LDP 10 101 0 010 1 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=0 +STP_v 00 101 1 010 0 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=0 w=0 +LDP_v 00 101 1 010 1 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=0 w=0 +STP_v 01 101 1 010 0 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=0 +LDP_v 01 101 1 010 1 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=0 +STP_v 10 101 1 010 0 ....... ..... ..... ..... @ldstpair sz=4 sign=0 p=0 w=0 +LDP_v 10 101 1 010 1 ....... ..... ..... ..... @ldstpair sz=4 sign=0 p=0 w=0 + +# STP and LDP: pre-indexed +STP 00 101 0 011 0 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=0 w=1 +LDP 00 101 0 011 1 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=0 w=1 +LDP 01 101 0 011 1 ....... ..... ..... ..... @ldstpair sz=2 sign=1 p=0 w=1 +STP 10 101 0 011 0 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=1 +LDP 10 101 0 011 1 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=1 +STP_v 00 101 1 011 0 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=0 w=1 +LDP_v 00 101 1 011 1 ....... ..... ..... ..... @ldstpair sz=2 sign=0 p=0 w=1 +STP_v 01 101 1 011 0 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=1 +LDP_v 01 101 1 011 1 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=1 +STP_v 10 101 1 011 0 ....... ..... ..... ..... @ldstpair sz=4 sign=0 p=0 w=1 +LDP_v 10 101 1 011 1 ....... ..... ..... ..... @ldstpair sz=4 sign=0 p=0 w=1 + +# STGP: store tag and pair +STGP 01 101 0 001 0 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=1 w=1 +STGP 01 101 0 010 0 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=0 +STGP 01 101 0 011 0 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=1 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_LD_lit_v(DisasContext *s, arg_ldlit *a) return true; } -/* - * LDNP (Load Pair - non-temporal hint) - * LDP (Load Pair - non vector) - * LDPSW (Load Pair Signed Word - non vector) - * STNP (Store Pair - non-temporal hint) - * STP (Store Pair - non vector) - * LDNP (Load Pair of SIMD&FP - non-temporal hint) - * LDP (Load Pair of SIMD&FP) - * STNP (Store Pair of SIMD&FP - non-temporal hint) - * STP (Store Pair of SIMD&FP) - * - * 31 30 29 27 26 25 24 23 22 21 15 14 10 9 5 4 0 - * +-----+-------+---+---+-------+---+-----------------------------+ - * | opc | 1 0 1 | V | 0 | index | L | imm7 | Rt2 | Rn | Rt | - * +-----+-------+---+---+-------+---+-------+-------+------+------+ - * - * opc: LDP/STP/LDNP/STNP 00 -> 32 bit, 10 -> 64 bit - * LDPSW/STGP 01 - * LDP/STP/LDNP/STNP (SIMD) 00 -> 32 bit, 01 -> 64 bit, 10 -> 128 bit - * V: 0 -> GPR, 1 -> Vector - * idx: 00 -> signed offset with non-temporal hint, 01 -> post-index, - * 10 -> signed offset, 11 -> pre-index - * L: 0 -> Store 1 -> Load - * - * Rt, Rt2 = GPR or SIMD registers to be stored - * Rn = general purpose register containing address - * imm7 = signed offset (multiple of 4 or 8 depending on size) - */ -static void disas_ldst_pair(DisasContext *s, uint32_t insn) +static void op_addr_ldstpair_pre(DisasContext *s, arg_ldstpair *a, + TCGv_i64 *clean_addr, TCGv_i64 *dirty_addr, + uint64_t offset, bool is_store, MemOp mop) { - int rt = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int rt2 = extract32(insn, 10, 5); - uint64_t offset = sextract64(insn, 15, 7); - int index = extract32(insn, 23, 2); - bool is_vector = extract32(insn, 26, 1); - bool is_load = extract32(insn, 22, 1); - int opc = extract32(insn, 30, 2); - bool is_signed = false; - bool postindex = false; - bool wback = false; - bool set_tag = false; - TCGv_i64 clean_addr, dirty_addr; - MemOp mop; - int size; - - if (opc == 3) { - unallocated_encoding(s); - return; - } - - if (is_vector) { - size = 2 + opc; - } else if (opc == 1 && !is_load) { - /* STGP */ - if (!dc_isar_feature(aa64_mte_insn_reg, s) || index == 0) { - unallocated_encoding(s); - return; - } - size = 3; - set_tag = true; - } else { - size = 2 + extract32(opc, 1, 1); - is_signed = extract32(opc, 0, 1); - if (!is_load && is_signed) { - unallocated_encoding(s); - return; - } - } - - switch (index) { - case 1: /* post-index */ - postindex = true; - wback = true; - break; - case 0: - /* signed offset with "non-temporal" hint. Since we don't emulate - * caches we don't care about hints to the cache system about - * data access patterns, and handle this identically to plain - * signed offset. - */ - if (is_signed) { - /* There is no non-temporal-hint version of LDPSW */ - unallocated_encoding(s); - return; - } - postindex = false; - break; - case 2: /* signed offset, rn not updated */ - postindex = false; - break; - case 3: /* pre-index */ - postindex = false; - wback = true; - break; - } - - if (is_vector && !fp_access_check(s)) { - return; - } - - offset <<= (set_tag ? LOG2_TAG_GRANULE : size); - - if (rn == 31) { + if (a->rn == 31) { gen_check_sp_alignment(s); } - dirty_addr = read_cpu_reg_sp(s, rn, 1); - if (!postindex) { + *dirty_addr = read_cpu_reg_sp(s, a->rn, 1); + if (!a->p) { + tcg_gen_addi_i64(*dirty_addr, *dirty_addr, offset); + } + + *clean_addr = gen_mte_checkN(s, *dirty_addr, is_store, + (a->w || a->rn != 31), 2 << a->sz, mop); +} + +static void op_addr_ldstpair_post(DisasContext *s, arg_ldstpair *a, + TCGv_i64 dirty_addr, uint64_t offset) +{ + if (a->w) { + if (a->p) { + tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); + } + tcg_gen_mov_i64(cpu_reg_sp(s, a->rn), dirty_addr); + } +} + +static bool trans_STP(DisasContext *s, arg_ldstpair *a) +{ + uint64_t offset = a->imm << a->sz; + TCGv_i64 clean_addr, dirty_addr, tcg_rt, tcg_rt2; + MemOp mop = finalize_memop(s, a->sz); + + op_addr_ldstpair_pre(s, a, &clean_addr, &dirty_addr, offset, true, mop); + tcg_rt = cpu_reg(s, a->rt); + tcg_rt2 = cpu_reg(s, a->rt2); + /* + * We built mop above for the single logical access -- rebuild it + * now for the paired operation. + * + * With LSE2, non-sign-extending pairs are treated atomically if + * aligned, and if unaligned one of the pair will be completely + * within a 16-byte block and that element will be atomic. + * Otherwise each element is separately atomic. + * In all cases, issue one operation with the correct atomicity. + */ + mop = a->sz + 1; + if (s->align_mem) { + mop |= (a->sz == 2 ? MO_ALIGN_4 : MO_ALIGN_8); + } + mop = finalize_memop_pair(s, mop); + if (a->sz == 2) { + TCGv_i64 tmp = tcg_temp_new_i64(); + + if (s->be_data == MO_LE) { + tcg_gen_concat32_i64(tmp, tcg_rt, tcg_rt2); + } else { + tcg_gen_concat32_i64(tmp, tcg_rt2, tcg_rt); + } + tcg_gen_qemu_st_i64(tmp, clean_addr, get_mem_index(s), mop); + } else { + TCGv_i128 tmp = tcg_temp_new_i128(); + + if (s->be_data == MO_LE) { + tcg_gen_concat_i64_i128(tmp, tcg_rt, tcg_rt2); + } else { + tcg_gen_concat_i64_i128(tmp, tcg_rt2, tcg_rt); + } + tcg_gen_qemu_st_i128(tmp, clean_addr, get_mem_index(s), mop); + } + op_addr_ldstpair_post(s, a, dirty_addr, offset); + return true; +} + +static bool trans_LDP(DisasContext *s, arg_ldstpair *a) +{ + uint64_t offset = a->imm << a->sz; + TCGv_i64 clean_addr, dirty_addr, tcg_rt, tcg_rt2; + MemOp mop = finalize_memop(s, a->sz); + + op_addr_ldstpair_pre(s, a, &clean_addr, &dirty_addr, offset, false, mop); + tcg_rt = cpu_reg(s, a->rt); + tcg_rt2 = cpu_reg(s, a->rt2); + + /* + * We built mop above for the single logical access -- rebuild it + * now for the paired operation. + * + * With LSE2, non-sign-extending pairs are treated atomically if + * aligned, and if unaligned one of the pair will be completely + * within a 16-byte block and that element will be atomic. + * Otherwise each element is separately atomic. + * In all cases, issue one operation with the correct atomicity. + * + * This treats sign-extending loads like zero-extending loads, + * since that reuses the most code below. + */ + mop = a->sz + 1; + if (s->align_mem) { + mop |= (a->sz == 2 ? MO_ALIGN_4 : MO_ALIGN_8); + } + mop = finalize_memop_pair(s, mop); + if (a->sz == 2) { + int o2 = s->be_data == MO_LE ? 32 : 0; + int o1 = o2 ^ 32; + + tcg_gen_qemu_ld_i64(tcg_rt, clean_addr, get_mem_index(s), mop); + if (a->sign) { + tcg_gen_sextract_i64(tcg_rt2, tcg_rt, o2, 32); + tcg_gen_sextract_i64(tcg_rt, tcg_rt, o1, 32); + } else { + tcg_gen_extract_i64(tcg_rt2, tcg_rt, o2, 32); + tcg_gen_extract_i64(tcg_rt, tcg_rt, o1, 32); + } + } else { + TCGv_i128 tmp = tcg_temp_new_i128(); + + tcg_gen_qemu_ld_i128(tmp, clean_addr, get_mem_index(s), mop); + if (s->be_data == MO_LE) { + tcg_gen_extr_i128_i64(tcg_rt, tcg_rt2, tmp); + } else { + tcg_gen_extr_i128_i64(tcg_rt2, tcg_rt, tmp); + } + } + op_addr_ldstpair_post(s, a, dirty_addr, offset); + return true; +} + +static bool trans_STP_v(DisasContext *s, arg_ldstpair *a) +{ + uint64_t offset = a->imm << a->sz; + TCGv_i64 clean_addr, dirty_addr; + MemOp mop; + + if (!fp_access_check(s)) { + return true; + } + + /* LSE2 does not merge FP pairs; leave these as separate operations. */ + mop = finalize_memop_asimd(s, a->sz); + op_addr_ldstpair_pre(s, a, &clean_addr, &dirty_addr, offset, true, mop); + do_fp_st(s, a->rt, clean_addr, mop); + tcg_gen_addi_i64(clean_addr, clean_addr, 1 << a->sz); + do_fp_st(s, a->rt2, clean_addr, mop); + op_addr_ldstpair_post(s, a, dirty_addr, offset); + return true; +} + +static bool trans_LDP_v(DisasContext *s, arg_ldstpair *a) +{ + uint64_t offset = a->imm << a->sz; + TCGv_i64 clean_addr, dirty_addr; + MemOp mop; + + if (!fp_access_check(s)) { + return true; + } + + /* LSE2 does not merge FP pairs; leave these as separate operations. */ + mop = finalize_memop_asimd(s, a->sz); + op_addr_ldstpair_pre(s, a, &clean_addr, &dirty_addr, offset, false, mop); + do_fp_ld(s, a->rt, clean_addr, mop); + tcg_gen_addi_i64(clean_addr, clean_addr, 1 << a->sz); + do_fp_ld(s, a->rt2, clean_addr, mop); + op_addr_ldstpair_post(s, a, dirty_addr, offset); + return true; +} + +static bool trans_STGP(DisasContext *s, arg_ldstpair *a) +{ + TCGv_i64 clean_addr, dirty_addr, tcg_rt, tcg_rt2; + uint64_t offset = a->imm << LOG2_TAG_GRANULE; + MemOp mop; + TCGv_i128 tmp; + + if (!dc_isar_feature(aa64_mte_insn_reg, s)) { + return false; + } + + if (a->rn == 31) { + gen_check_sp_alignment(s); + } + + dirty_addr = read_cpu_reg_sp(s, a->rn, 1); + if (!a->p) { tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); } - if (set_tag) { - if (!s->ata) { - /* - * TODO: We could rely on the stores below, at least for - * system mode, if we arrange to add MO_ALIGN_16. - */ - gen_helper_stg_stub(cpu_env, dirty_addr); - } else if (tb_cflags(s->base.tb) & CF_PARALLEL) { - gen_helper_stg_parallel(cpu_env, dirty_addr, dirty_addr); - } else { - gen_helper_stg(cpu_env, dirty_addr, dirty_addr); - } - } - - if (is_vector) { - mop = finalize_memop_asimd(s, size); - } else { - mop = finalize_memop(s, size); - } - clean_addr = gen_mte_checkN(s, dirty_addr, !is_load, - (wback || rn != 31) && !set_tag, - 2 << size, mop); - - if (is_vector) { - /* LSE2 does not merge FP pairs; leave these as separate operations. */ - if (is_load) { - do_fp_ld(s, rt, clean_addr, mop); - } else { - do_fp_st(s, rt, clean_addr, mop); - } - tcg_gen_addi_i64(clean_addr, clean_addr, 1 << size); - if (is_load) { - do_fp_ld(s, rt2, clean_addr, mop); - } else { - do_fp_st(s, rt2, clean_addr, mop); - } - } else { - TCGv_i64 tcg_rt = cpu_reg(s, rt); - TCGv_i64 tcg_rt2 = cpu_reg(s, rt2); - + if (!s->ata) { /* - * We built mop above for the single logical access -- rebuild it - * now for the paired operation. - * - * With LSE2, non-sign-extending pairs are treated atomically if - * aligned, and if unaligned one of the pair will be completely - * within a 16-byte block and that element will be atomic. - * Otherwise each element is separately atomic. - * In all cases, issue one operation with the correct atomicity. - * - * This treats sign-extending loads like zero-extending loads, - * since that reuses the most code below. + * TODO: We could rely on the stores below, at least for + * system mode, if we arrange to add MO_ALIGN_16. */ - mop = size + 1; - if (s->align_mem) { - mop |= (size == 2 ? MO_ALIGN_4 : MO_ALIGN_8); - } - mop = finalize_memop_pair(s, mop); - - if (is_load) { - if (size == 2) { - int o2 = s->be_data == MO_LE ? 32 : 0; - int o1 = o2 ^ 32; - - tcg_gen_qemu_ld_i64(tcg_rt, clean_addr, get_mem_index(s), mop); - if (is_signed) { - tcg_gen_sextract_i64(tcg_rt2, tcg_rt, o2, 32); - tcg_gen_sextract_i64(tcg_rt, tcg_rt, o1, 32); - } else { - tcg_gen_extract_i64(tcg_rt2, tcg_rt, o2, 32); - tcg_gen_extract_i64(tcg_rt, tcg_rt, o1, 32); - } - } else { - TCGv_i128 tmp = tcg_temp_new_i128(); - - tcg_gen_qemu_ld_i128(tmp, clean_addr, get_mem_index(s), mop); - if (s->be_data == MO_LE) { - tcg_gen_extr_i128_i64(tcg_rt, tcg_rt2, tmp); - } else { - tcg_gen_extr_i128_i64(tcg_rt2, tcg_rt, tmp); - } - } - } else { - if (size == 2) { - TCGv_i64 tmp = tcg_temp_new_i64(); - - if (s->be_data == MO_LE) { - tcg_gen_concat32_i64(tmp, tcg_rt, tcg_rt2); - } else { - tcg_gen_concat32_i64(tmp, tcg_rt2, tcg_rt); - } - tcg_gen_qemu_st_i64(tmp, clean_addr, get_mem_index(s), mop); - } else { - TCGv_i128 tmp = tcg_temp_new_i128(); - - if (s->be_data == MO_LE) { - tcg_gen_concat_i64_i128(tmp, tcg_rt, tcg_rt2); - } else { - tcg_gen_concat_i64_i128(tmp, tcg_rt2, tcg_rt); - } - tcg_gen_qemu_st_i128(tmp, clean_addr, get_mem_index(s), mop); - } - } + gen_helper_stg_stub(cpu_env, dirty_addr); + } else if (tb_cflags(s->base.tb) & CF_PARALLEL) { + gen_helper_stg_parallel(cpu_env, dirty_addr, dirty_addr); + } else { + gen_helper_stg(cpu_env, dirty_addr, dirty_addr); } - if (wback) { - if (postindex) { - tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); - } - tcg_gen_mov_i64(cpu_reg_sp(s, rn), dirty_addr); + mop = finalize_memop(s, a->sz); + clean_addr = gen_mte_checkN(s, dirty_addr, true, false, 2 << a->sz, mop); + + tcg_rt = cpu_reg(s, a->rt); + tcg_rt2 = cpu_reg(s, a->rt2); + + assert(a->sz == 3); + + tmp = tcg_temp_new_i128(); + if (s->be_data == MO_LE) { + tcg_gen_concat_i64_i128(tmp, tcg_rt, tcg_rt2); + } else { + tcg_gen_concat_i64_i128(tmp, tcg_rt2, tcg_rt); } + tcg_gen_qemu_st_i128(tmp, clean_addr, get_mem_index(s), mop); + + op_addr_ldstpair_post(s, a, dirty_addr, offset); + return true; } /* @@ -XXX,XX +XXX,XX @@ static void disas_ldst_tag(DisasContext *s, uint32_t insn) static void disas_ldst(DisasContext *s, uint32_t insn) { switch (extract32(insn, 24, 6)) { - case 0x28: case 0x29: - case 0x2c: case 0x2d: /* Load/store pair (all forms) */ - disas_ldst_pair(s, insn); - break; case 0x38: case 0x39: case 0x3c: case 0x3d: /* Load/store register (all forms) */ disas_ldst_reg(s, insn); -- 2.34.1 Convert the load and store instructions which use a 9-bit immediate offset to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-13-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 69 +++++++++++ target/arm/tcg/translate-a64.c | 206 ++++++++++++++------------------- 2 files changed, 153 insertions(+), 122 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ LDP_v 10 101 1 011 1 ....... ..... ..... ..... @ldstpair sz=4 sign=0 p STGP 01 101 0 001 0 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=1 w=1 STGP 01 101 0 010 0 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=0 STGP 01 101 0 011 0 ....... ..... ..... ..... @ldstpair sz=3 sign=0 p=0 w=1 + +# Load/store register (unscaled immediate) +&ldst_imm rt rn imm sz sign w p unpriv ext +@ldst_imm .. ... . .. .. . imm:s9 .. rn:5 rt:5 &ldst_imm unpriv=0 p=0 w=0 +@ldst_imm_pre .. ... . .. .. . imm:s9 .. rn:5 rt:5 &ldst_imm unpriv=0 p=0 w=1 +@ldst_imm_post .. ... . .. .. . imm:s9 .. rn:5 rt:5 &ldst_imm unpriv=0 p=1 w=1 +@ldst_imm_user .. ... . .. .. . imm:s9 .. rn:5 rt:5 &ldst_imm unpriv=1 p=0 w=0 + +STR_i sz:2 111 0 00 00 0 ......... 00 ..... ..... @ldst_imm sign=0 ext=0 +LDR_i 00 111 0 00 01 0 ......... 00 ..... ..... @ldst_imm sign=0 ext=1 sz=0 +LDR_i 01 111 0 00 01 0 ......... 00 ..... ..... @ldst_imm sign=0 ext=1 sz=1 +LDR_i 10 111 0 00 01 0 ......... 00 ..... ..... @ldst_imm sign=0 ext=1 sz=2 +LDR_i 11 111 0 00 01 0 ......... 00 ..... ..... @ldst_imm sign=0 ext=0 sz=3 +LDR_i 00 111 0 00 10 0 ......... 00 ..... ..... @ldst_imm sign=1 ext=0 sz=0 +LDR_i 01 111 0 00 10 0 ......... 00 ..... ..... @ldst_imm sign=1 ext=0 sz=1 +LDR_i 10 111 0 00 10 0 ......... 00 ..... ..... @ldst_imm sign=1 ext=0 sz=2 +LDR_i 00 111 0 00 11 0 ......... 00 ..... ..... @ldst_imm sign=1 ext=1 sz=0 +LDR_i 01 111 0 00 11 0 ......... 00 ..... ..... @ldst_imm sign=1 ext=1 sz=1 + +STR_i sz:2 111 0 00 00 0 ......... 01 ..... ..... @ldst_imm_post sign=0 ext=0 +LDR_i 00 111 0 00 01 0 ......... 01 ..... ..... @ldst_imm_post sign=0 ext=1 sz=0 +LDR_i 01 111 0 00 01 0 ......... 01 ..... ..... @ldst_imm_post sign=0 ext=1 sz=1 +LDR_i 10 111 0 00 01 0 ......... 01 ..... ..... @ldst_imm_post sign=0 ext=1 sz=2 +LDR_i 11 111 0 00 01 0 ......... 01 ..... ..... @ldst_imm_post sign=0 ext=0 sz=3 +LDR_i 00 111 0 00 10 0 ......... 01 ..... ..... @ldst_imm_post sign=1 ext=0 sz=0 +LDR_i 01 111 0 00 10 0 ......... 01 ..... ..... @ldst_imm_post sign=1 ext=0 sz=1 +LDR_i 10 111 0 00 10 0 ......... 01 ..... ..... @ldst_imm_post sign=1 ext=0 sz=2 +LDR_i 00 111 0 00 11 0 ......... 01 ..... ..... @ldst_imm_post sign=1 ext=1 sz=0 +LDR_i 01 111 0 00 11 0 ......... 01 ..... ..... @ldst_imm_post sign=1 ext=1 sz=1 + +STR_i sz:2 111 0 00 00 0 ......... 10 ..... ..... @ldst_imm_user sign=0 ext=0 +LDR_i 00 111 0 00 01 0 ......... 10 ..... ..... @ldst_imm_user sign=0 ext=1 sz=0 +LDR_i 01 111 0 00 01 0 ......... 10 ..... ..... @ldst_imm_user sign=0 ext=1 sz=1 +LDR_i 10 111 0 00 01 0 ......... 10 ..... ..... @ldst_imm_user sign=0 ext=1 sz=2 +LDR_i 11 111 0 00 01 0 ......... 10 ..... ..... @ldst_imm_user sign=0 ext=0 sz=3 +LDR_i 00 111 0 00 10 0 ......... 10 ..... ..... @ldst_imm_user sign=1 ext=0 sz=0 +LDR_i 01 111 0 00 10 0 ......... 10 ..... ..... @ldst_imm_user sign=1 ext=0 sz=1 +LDR_i 10 111 0 00 10 0 ......... 10 ..... ..... @ldst_imm_user sign=1 ext=0 sz=2 +LDR_i 00 111 0 00 11 0 ......... 10 ..... ..... @ldst_imm_user sign=1 ext=1 sz=0 +LDR_i 01 111 0 00 11 0 ......... 10 ..... ..... @ldst_imm_user sign=1 ext=1 sz=1 + +STR_i sz:2 111 0 00 00 0 ......... 11 ..... ..... @ldst_imm_pre sign=0 ext=0 +LDR_i 00 111 0 00 01 0 ......... 11 ..... ..... @ldst_imm_pre sign=0 ext=1 sz=0 +LDR_i 01 111 0 00 01 0 ......... 11 ..... ..... @ldst_imm_pre sign=0 ext=1 sz=1 +LDR_i 10 111 0 00 01 0 ......... 11 ..... ..... @ldst_imm_pre sign=0 ext=1 sz=2 +LDR_i 11 111 0 00 01 0 ......... 11 ..... ..... @ldst_imm_pre sign=0 ext=0 sz=3 +LDR_i 00 111 0 00 10 0 ......... 11 ..... ..... @ldst_imm_pre sign=1 ext=0 sz=0 +LDR_i 01 111 0 00 10 0 ......... 11 ..... ..... @ldst_imm_pre sign=1 ext=0 sz=1 +LDR_i 10 111 0 00 10 0 ......... 11 ..... ..... @ldst_imm_pre sign=1 ext=0 sz=2 +LDR_i 00 111 0 00 11 0 ......... 11 ..... ..... @ldst_imm_pre sign=1 ext=1 sz=0 +LDR_i 01 111 0 00 11 0 ......... 11 ..... ..... @ldst_imm_pre sign=1 ext=1 sz=1 + +# PRFM : prefetch memory: a no-op for QEMU +NOP 11 111 0 00 10 0 --------- 00 ----- ----- + +STR_v_i sz:2 111 1 00 00 0 ......... 00 ..... ..... @ldst_imm sign=0 ext=0 +STR_v_i 00 111 1 00 10 0 ......... 00 ..... ..... @ldst_imm sign=0 ext=0 sz=4 +LDR_v_i sz:2 111 1 00 01 0 ......... 00 ..... ..... @ldst_imm sign=0 ext=0 +LDR_v_i 00 111 1 00 11 0 ......... 00 ..... ..... @ldst_imm sign=0 ext=0 sz=4 + +STR_v_i sz:2 111 1 00 00 0 ......... 01 ..... ..... @ldst_imm_post sign=0 ext=0 +STR_v_i 00 111 1 00 10 0 ......... 01 ..... ..... @ldst_imm_post sign=0 ext=0 sz=4 +LDR_v_i sz:2 111 1 00 01 0 ......... 01 ..... ..... @ldst_imm_post sign=0 ext=0 +LDR_v_i 00 111 1 00 11 0 ......... 01 ..... ..... @ldst_imm_post sign=0 ext=0 sz=4 + +STR_v_i sz:2 111 1 00 00 0 ......... 11 ..... ..... @ldst_imm_pre sign=0 ext=0 +STR_v_i 00 111 1 00 10 0 ......... 11 ..... ..... @ldst_imm_pre sign=0 ext=0 sz=4 +LDR_v_i sz:2 111 1 00 01 0 ......... 11 ..... ..... @ldst_imm_pre sign=0 ext=0 +LDR_v_i 00 111 1 00 11 0 ......... 11 ..... ..... @ldst_imm_pre sign=0 ext=0 sz=4 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_STGP(DisasContext *s, arg_ldstpair *a) return true; } -/* - * Load/store (immediate post-indexed) - * Load/store (immediate pre-indexed) - * Load/store (unscaled immediate) - * - * 31 30 29 27 26 25 24 23 22 21 20 12 11 10 9 5 4 0 - * +----+-------+---+-----+-----+---+--------+-----+------+------+ - * |size| 1 1 1 | V | 0 0 | opc | 0 | imm9 | idx | Rn | Rt | - * +----+-------+---+-----+-----+---+--------+-----+------+------+ - * - * idx = 01 -> post-indexed, 11 pre-indexed, 00 unscaled imm. (no writeback) - 10 -> unprivileged - * V = 0 -> non-vector - * size: 00 -> 8 bit, 01 -> 16 bit, 10 -> 32 bit, 11 -> 64bit - * opc: 00 -> store, 01 -> loadu, 10 -> loads 64, 11 -> loads 32 - */ -static void disas_ldst_reg_imm9(DisasContext *s, uint32_t insn, - int opc, - int size, - int rt, - bool is_vector) +static void op_addr_ldst_imm_pre(DisasContext *s, arg_ldst_imm *a, + TCGv_i64 *clean_addr, TCGv_i64 *dirty_addr, + uint64_t offset, bool is_store, MemOp mop) { - int rn = extract32(insn, 5, 5); - int imm9 = sextract32(insn, 12, 9); - int idx = extract32(insn, 10, 2); - bool is_signed = false; - bool is_store = false; - bool is_extended = false; - bool is_unpriv = (idx == 2); - bool iss_valid; - bool post_index; - bool writeback; int memidx; - MemOp memop; - TCGv_i64 clean_addr, dirty_addr; - if (is_vector) { - size |= (opc & 2) << 1; - if (size > 4 || is_unpriv) { - unallocated_encoding(s); - return; - } - is_store = ((opc & 1) == 0); - if (!fp_access_check(s)) { - return; - } - memop = finalize_memop_asimd(s, size); - } else { - if (size == 3 && opc == 2) { - /* PRFM - prefetch */ - if (idx != 0) { - unallocated_encoding(s); - return; - } - return; - } - if (opc == 3 && size > 1) { - unallocated_encoding(s); - return; - } - is_store = (opc == 0); - is_signed = !is_store && extract32(opc, 1, 1); - is_extended = (size < 3) && extract32(opc, 0, 1); - memop = finalize_memop(s, size + is_signed * MO_SIGN); - } - - switch (idx) { - case 0: - case 2: - post_index = false; - writeback = false; - break; - case 1: - post_index = true; - writeback = true; - break; - case 3: - post_index = false; - writeback = true; - break; - default: - g_assert_not_reached(); - } - - iss_valid = !is_vector && !writeback; - - if (rn == 31) { + if (a->rn == 31) { gen_check_sp_alignment(s); } - dirty_addr = read_cpu_reg_sp(s, rn, 1); - if (!post_index) { - tcg_gen_addi_i64(dirty_addr, dirty_addr, imm9); + *dirty_addr = read_cpu_reg_sp(s, a->rn, 1); + if (!a->p) { + tcg_gen_addi_i64(*dirty_addr, *dirty_addr, offset); } + memidx = a->unpriv ? get_a64_user_mem_index(s) : get_mem_index(s); + *clean_addr = gen_mte_check1_mmuidx(s, *dirty_addr, is_store, + a->w || a->rn != 31, + mop, a->unpriv, memidx); +} - memidx = is_unpriv ? get_a64_user_mem_index(s) : get_mem_index(s); - - clean_addr = gen_mte_check1_mmuidx(s, dirty_addr, is_store, - writeback || rn != 31, - memop, is_unpriv, memidx); - - if (is_vector) { - if (is_store) { - do_fp_st(s, rt, clean_addr, memop); - } else { - do_fp_ld(s, rt, clean_addr, memop); - } - } else { - TCGv_i64 tcg_rt = cpu_reg(s, rt); - bool iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc); - - if (is_store) { - do_gpr_st_memidx(s, tcg_rt, clean_addr, memop, memidx, - iss_valid, rt, iss_sf, false); - } else { - do_gpr_ld_memidx(s, tcg_rt, clean_addr, memop, - is_extended, memidx, - iss_valid, rt, iss_sf, false); +static void op_addr_ldst_imm_post(DisasContext *s, arg_ldst_imm *a, + TCGv_i64 dirty_addr, uint64_t offset) +{ + if (a->w) { + if (a->p) { + tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); } + tcg_gen_mov_i64(cpu_reg_sp(s, a->rn), dirty_addr); } +} - if (writeback) { - TCGv_i64 tcg_rn = cpu_reg_sp(s, rn); - if (post_index) { - tcg_gen_addi_i64(dirty_addr, dirty_addr, imm9); - } - tcg_gen_mov_i64(tcg_rn, dirty_addr); +static bool trans_STR_i(DisasContext *s, arg_ldst_imm *a) +{ + bool iss_sf, iss_valid = !a->w; + TCGv_i64 clean_addr, dirty_addr, tcg_rt; + int memidx = a->unpriv ? get_a64_user_mem_index(s) : get_mem_index(s); + MemOp mop = finalize_memop(s, a->sz + a->sign * MO_SIGN); + + op_addr_ldst_imm_pre(s, a, &clean_addr, &dirty_addr, a->imm, true, mop); + + tcg_rt = cpu_reg(s, a->rt); + iss_sf = ldst_iss_sf(a->sz, a->sign, a->ext); + + do_gpr_st_memidx(s, tcg_rt, clean_addr, mop, memidx, + iss_valid, a->rt, iss_sf, false); + op_addr_ldst_imm_post(s, a, dirty_addr, a->imm); + return true; +} + +static bool trans_LDR_i(DisasContext *s, arg_ldst_imm *a) +{ + bool iss_sf, iss_valid = !a->w; + TCGv_i64 clean_addr, dirty_addr, tcg_rt; + int memidx = a->unpriv ? get_a64_user_mem_index(s) : get_mem_index(s); + MemOp mop = finalize_memop(s, a->sz + a->sign * MO_SIGN); + + op_addr_ldst_imm_pre(s, a, &clean_addr, &dirty_addr, a->imm, false, mop); + + tcg_rt = cpu_reg(s, a->rt); + iss_sf = ldst_iss_sf(a->sz, a->sign, a->ext); + + do_gpr_ld_memidx(s, tcg_rt, clean_addr, mop, + a->ext, memidx, iss_valid, a->rt, iss_sf, false); + op_addr_ldst_imm_post(s, a, dirty_addr, a->imm); + return true; +} + +static bool trans_STR_v_i(DisasContext *s, arg_ldst_imm *a) +{ + TCGv_i64 clean_addr, dirty_addr; + MemOp mop; + + if (!fp_access_check(s)) { + return true; } + mop = finalize_memop_asimd(s, a->sz); + op_addr_ldst_imm_pre(s, a, &clean_addr, &dirty_addr, a->imm, true, mop); + do_fp_st(s, a->rt, clean_addr, mop); + op_addr_ldst_imm_post(s, a, dirty_addr, a->imm); + return true; +} + +static bool trans_LDR_v_i(DisasContext *s, arg_ldst_imm *a) +{ + TCGv_i64 clean_addr, dirty_addr; + MemOp mop; + + if (!fp_access_check(s)) { + return true; + } + mop = finalize_memop_asimd(s, a->sz); + op_addr_ldst_imm_pre(s, a, &clean_addr, &dirty_addr, a->imm, false, mop); + do_fp_ld(s, a->rt, clean_addr, mop); + op_addr_ldst_imm_post(s, a, dirty_addr, a->imm); + return true; } /* @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg(DisasContext *s, uint32_t insn) switch (extract32(insn, 24, 2)) { case 0: if (extract32(insn, 21, 1) == 0) { - /* Load/store register (unscaled immediate) - * Load/store immediate pre/post-indexed - * Load/store register unprivileged - */ - disas_ldst_reg_imm9(s, insn, opc, size, rt, is_vector); - return; + break; } switch (extract32(insn, 10, 2)) { case 0: -- 2.34.1 Convert the LDR and STR instructions which use a 12-bit immediate offset to decodetree. We can reuse the existing LDR and STR trans functions for these. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-14-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 25 ++++++++ target/arm/tcg/translate-a64.c | 104 +++++---------------------------- 2 files changed, 41 insertions(+), 88 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ STR_v_i sz:2 111 1 00 00 0 ......... 11 ..... ..... @ldst_imm_pre sign=0 STR_v_i 00 111 1 00 10 0 ......... 11 ..... ..... @ldst_imm_pre sign=0 ext=0 sz=4 LDR_v_i sz:2 111 1 00 01 0 ......... 11 ..... ..... @ldst_imm_pre sign=0 ext=0 LDR_v_i 00 111 1 00 11 0 ......... 11 ..... ..... @ldst_imm_pre sign=0 ext=0 sz=4 + +# Load/store with an unsigned 12 bit immediate, which is scaled by the +# element size. The function gets the sz:imm and returns the scaled immediate. +%uimm_scaled 10:12 sz:3 !function=uimm_scaled + +@ldst_uimm .. ... . .. .. ............ rn:5 rt:5 &ldst_imm unpriv=0 p=0 w=0 imm=%uimm_scaled + +STR_i sz:2 111 0 01 00 ............ ..... ..... @ldst_uimm sign=0 ext=0 +LDR_i 00 111 0 01 01 ............ ..... ..... @ldst_uimm sign=0 ext=1 sz=0 +LDR_i 01 111 0 01 01 ............ ..... ..... @ldst_uimm sign=0 ext=1 sz=1 +LDR_i 10 111 0 01 01 ............ ..... ..... @ldst_uimm sign=0 ext=1 sz=2 +LDR_i 11 111 0 01 01 ............ ..... ..... @ldst_uimm sign=0 ext=0 sz=3 +LDR_i 00 111 0 01 10 ............ ..... ..... @ldst_uimm sign=1 ext=0 sz=0 +LDR_i 01 111 0 01 10 ............ ..... ..... @ldst_uimm sign=1 ext=0 sz=1 +LDR_i 10 111 0 01 10 ............ ..... ..... @ldst_uimm sign=1 ext=0 sz=2 +LDR_i 00 111 0 01 11 ............ ..... ..... @ldst_uimm sign=1 ext=1 sz=0 +LDR_i 01 111 0 01 11 ............ ..... ..... @ldst_uimm sign=1 ext=1 sz=1 + +# PRFM +NOP 11 111 0 01 10 ------------ ----- ----- + +STR_v_i sz:2 111 1 01 00 ............ ..... ..... @ldst_uimm sign=0 ext=0 +STR_v_i 00 111 1 01 10 ............ ..... ..... @ldst_uimm sign=0 ext=0 sz=4 +LDR_v_i sz:2 111 1 01 01 ............ ..... ..... @ldst_uimm sign=0 ext=0 +LDR_v_i 00 111 1 01 11 ............ ..... ..... @ldst_uimm sign=0 ext=0 sz=4 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ enum a64_shift_type { A64_SHIFT_TYPE_ROR = 3 }; +/* + * Helpers for extracting complex instruction fields + */ + +/* + * For load/store with an unsigned 12 bit immediate scaled by the element + * size. The input has the immediate field in bits [14:3] and the element + * size in [2:0]. + */ +static int uimm_scaled(DisasContext *s, int x) +{ + unsigned imm = x >> 3; + unsigned scale = extract32(x, 0, 3); + return imm << scale; +} + /* * Include the generated decoders. */ @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, } } -/* - * Load/store (unsigned immediate) - * - * 31 30 29 27 26 25 24 23 22 21 10 9 5 - * +----+-------+---+-----+-----+------------+-------+------+ - * |size| 1 1 1 | V | 0 1 | opc | imm12 | Rn | Rt | - * +----+-------+---+-----+-----+------------+-------+------+ - * - * For non-vector: - * size: 00-> byte, 01 -> 16 bit, 10 -> 32bit, 11 -> 64bit - * opc: 00 -> store, 01 -> loadu, 10 -> loads 64, 11 -> loads 32 - * For vector: - * size is opc<1>:size<1:0> so 100 -> 128 bit; 110 and 111 unallocated - * opc<0>: 0 -> store, 1 -> load - * Rn: base address register (inc SP) - * Rt: target register - */ -static void disas_ldst_reg_unsigned_imm(DisasContext *s, uint32_t insn, - int opc, - int size, - int rt, - bool is_vector) -{ - int rn = extract32(insn, 5, 5); - unsigned int imm12 = extract32(insn, 10, 12); - unsigned int offset; - TCGv_i64 clean_addr, dirty_addr; - bool is_store; - bool is_signed = false; - bool is_extended = false; - MemOp memop; - - if (is_vector) { - size |= (opc & 2) << 1; - if (size > 4) { - unallocated_encoding(s); - return; - } - is_store = !extract32(opc, 0, 1); - if (!fp_access_check(s)) { - return; - } - memop = finalize_memop_asimd(s, size); - } else { - if (size == 3 && opc == 2) { - /* PRFM - prefetch */ - return; - } - if (opc == 3 && size > 1) { - unallocated_encoding(s); - return; - } - is_store = (opc == 0); - is_signed = !is_store && extract32(opc, 1, 1); - is_extended = (size < 3) && extract32(opc, 0, 1); - memop = finalize_memop(s, size + is_signed * MO_SIGN); - } - - if (rn == 31) { - gen_check_sp_alignment(s); - } - dirty_addr = read_cpu_reg_sp(s, rn, 1); - offset = imm12 << size; - tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); - - clean_addr = gen_mte_check1(s, dirty_addr, is_store, rn != 31, memop); - - if (is_vector) { - if (is_store) { - do_fp_st(s, rt, clean_addr, memop); - } else { - do_fp_ld(s, rt, clean_addr, memop); - } - } else { - TCGv_i64 tcg_rt = cpu_reg(s, rt); - bool iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc); - if (is_store) { - do_gpr_st(s, tcg_rt, clean_addr, memop, true, rt, iss_sf, false); - } else { - do_gpr_ld(s, tcg_rt, clean_addr, memop, - is_extended, true, rt, iss_sf, false); - } - } -} - /* Atomic memory operations * * 31 30 27 26 24 22 21 16 15 12 10 5 0 @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg(DisasContext *s, uint32_t insn) return; } break; - case 1: - disas_ldst_reg_unsigned_imm(s, insn, opc, size, rt, is_vector); - return; } unallocated_encoding(s); } -- 2.34.1 Convert the LDR and STR instructions which take a register plus register offset to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-15-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 22 +++++ target/arm/tcg/translate-a64.c | 173 +++++++++++++++------------------ 2 files changed, 103 insertions(+), 92 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ STR_v_i sz:2 111 1 01 00 ............ ..... ..... @ldst_uimm sign=0 ext= STR_v_i 00 111 1 01 10 ............ ..... ..... @ldst_uimm sign=0 ext=0 sz=4 LDR_v_i sz:2 111 1 01 01 ............ ..... ..... @ldst_uimm sign=0 ext=0 LDR_v_i 00 111 1 01 11 ............ ..... ..... @ldst_uimm sign=0 ext=0 sz=4 + +# Load/store with register offset +&ldst rm rn rt sign ext sz opt s +@ldst .. ... . .. .. . rm:5 opt:3 s:1 .. rn:5 rt:5 &ldst +STR sz:2 111 0 00 00 1 ..... ... . 10 ..... ..... @ldst sign=0 ext=0 +LDR 00 111 0 00 01 1 ..... ... . 10 ..... ..... @ldst sign=0 ext=1 sz=0 +LDR 01 111 0 00 01 1 ..... ... . 10 ..... ..... @ldst sign=0 ext=1 sz=1 +LDR 10 111 0 00 01 1 ..... ... . 10 ..... ..... @ldst sign=0 ext=1 sz=2 +LDR 11 111 0 00 01 1 ..... ... . 10 ..... ..... @ldst sign=0 ext=0 sz=3 +LDR 00 111 0 00 10 1 ..... ... . 10 ..... ..... @ldst sign=1 ext=0 sz=0 +LDR 01 111 0 00 10 1 ..... ... . 10 ..... ..... @ldst sign=1 ext=0 sz=1 +LDR 10 111 0 00 10 1 ..... ... . 10 ..... ..... @ldst sign=1 ext=0 sz=2 +LDR 00 111 0 00 11 1 ..... ... . 10 ..... ..... @ldst sign=1 ext=1 sz=0 +LDR 01 111 0 00 11 1 ..... ... . 10 ..... ..... @ldst sign=1 ext=1 sz=1 + +# PRFM +NOP 11 111 0 00 10 1 ----- -1- - 10 ----- ----- + +STR_v sz:2 111 1 00 00 1 ..... ... . 10 ..... ..... @ldst sign=0 ext=0 +STR_v 00 111 1 00 10 1 ..... ... . 10 ..... ..... @ldst sign=0 ext=0 sz=4 +LDR_v sz:2 111 1 00 01 1 ..... ... . 10 ..... ..... @ldst sign=0 ext=0 +LDR_v 00 111 1 00 11 1 ..... ... . 10 ..... ..... @ldst sign=0 ext=0 sz=4 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_LDR_v_i(DisasContext *s, arg_ldst_imm *a) return true; } -/* - * Load/store (register offset) - * - * 31 30 29 27 26 25 24 23 22 21 20 16 15 13 12 11 10 9 5 4 0 - * +----+-------+---+-----+-----+---+------+-----+--+-----+----+----+ - * |size| 1 1 1 | V | 0 0 | opc | 1 | Rm | opt | S| 1 0 | Rn | Rt | - * +----+-------+---+-----+-----+---+------+-----+--+-----+----+----+ - * - * For non-vector: - * size: 00-> byte, 01 -> 16 bit, 10 -> 32bit, 11 -> 64bit - * opc: 00 -> store, 01 -> loadu, 10 -> loads 64, 11 -> loads 32 - * For vector: - * size is opc<1>:size<1:0> so 100 -> 128 bit; 110 and 111 unallocated - * opc<0>: 0 -> store, 1 -> load - * V: 1 -> vector/simd - * opt: extend encoding (see DecodeRegExtend) - * S: if S=1 then scale (essentially index by sizeof(size)) - * Rt: register to transfer into/out of - * Rn: address register or SP for base - * Rm: offset register or ZR for offset - */ -static void disas_ldst_reg_roffset(DisasContext *s, uint32_t insn, - int opc, - int size, - int rt, - bool is_vector) +static void op_addr_ldst_pre(DisasContext *s, arg_ldst *a, + TCGv_i64 *clean_addr, TCGv_i64 *dirty_addr, + bool is_store, MemOp memop) { - int rn = extract32(insn, 5, 5); - int shift = extract32(insn, 12, 1); - int rm = extract32(insn, 16, 5); - int opt = extract32(insn, 13, 3); - bool is_signed = false; - bool is_store = false; - bool is_extended = false; - TCGv_i64 tcg_rm, clean_addr, dirty_addr; - MemOp memop; + TCGv_i64 tcg_rm; - if (extract32(opt, 1, 1) == 0) { - unallocated_encoding(s); - return; - } - - if (is_vector) { - size |= (opc & 2) << 1; - if (size > 4) { - unallocated_encoding(s); - return; - } - is_store = !extract32(opc, 0, 1); - if (!fp_access_check(s)) { - return; - } - memop = finalize_memop_asimd(s, size); - } else { - if (size == 3 && opc == 2) { - /* PRFM - prefetch */ - return; - } - if (opc == 3 && size > 1) { - unallocated_encoding(s); - return; - } - is_store = (opc == 0); - is_signed = !is_store && extract32(opc, 1, 1); - is_extended = (size < 3) && extract32(opc, 0, 1); - memop = finalize_memop(s, size + is_signed * MO_SIGN); - } - - if (rn == 31) { + if (a->rn == 31) { gen_check_sp_alignment(s); } - dirty_addr = read_cpu_reg_sp(s, rn, 1); + *dirty_addr = read_cpu_reg_sp(s, a->rn, 1); - tcg_rm = read_cpu_reg(s, rm, 1); - ext_and_shift_reg(tcg_rm, tcg_rm, opt, shift ? size : 0); + tcg_rm = read_cpu_reg(s, a->rm, 1); + ext_and_shift_reg(tcg_rm, tcg_rm, a->opt, a->s ? a->sz : 0); - tcg_gen_add_i64(dirty_addr, dirty_addr, tcg_rm); + tcg_gen_add_i64(*dirty_addr, *dirty_addr, tcg_rm); + *clean_addr = gen_mte_check1(s, *dirty_addr, is_store, true, memop); +} - clean_addr = gen_mte_check1(s, dirty_addr, is_store, true, memop); +static bool trans_LDR(DisasContext *s, arg_ldst *a) +{ + TCGv_i64 clean_addr, dirty_addr, tcg_rt; + bool iss_sf = ldst_iss_sf(a->sz, a->sign, a->ext); + MemOp memop; - if (is_vector) { - if (is_store) { - do_fp_st(s, rt, clean_addr, memop); - } else { - do_fp_ld(s, rt, clean_addr, memop); - } - } else { - TCGv_i64 tcg_rt = cpu_reg(s, rt); - bool iss_sf = disas_ldst_compute_iss_sf(size, is_signed, opc); - - if (is_store) { - do_gpr_st(s, tcg_rt, clean_addr, memop, - true, rt, iss_sf, false); - } else { - do_gpr_ld(s, tcg_rt, clean_addr, memop, - is_extended, true, rt, iss_sf, false); - } + if (extract32(a->opt, 1, 1) == 0) { + return false; } + + memop = finalize_memop(s, a->sz + a->sign * MO_SIGN); + op_addr_ldst_pre(s, a, &clean_addr, &dirty_addr, false, memop); + tcg_rt = cpu_reg(s, a->rt); + do_gpr_ld(s, tcg_rt, clean_addr, memop, + a->ext, true, a->rt, iss_sf, false); + return true; +} + +static bool trans_STR(DisasContext *s, arg_ldst *a) +{ + TCGv_i64 clean_addr, dirty_addr, tcg_rt; + bool iss_sf = ldst_iss_sf(a->sz, a->sign, a->ext); + MemOp memop; + + if (extract32(a->opt, 1, 1) == 0) { + return false; + } + + memop = finalize_memop(s, a->sz); + op_addr_ldst_pre(s, a, &clean_addr, &dirty_addr, true, memop); + tcg_rt = cpu_reg(s, a->rt); + do_gpr_st(s, tcg_rt, clean_addr, memop, true, a->rt, iss_sf, false); + return true; +} + +static bool trans_LDR_v(DisasContext *s, arg_ldst *a) +{ + TCGv_i64 clean_addr, dirty_addr; + MemOp memop; + + if (extract32(a->opt, 1, 1) == 0) { + return false; + } + + if (!fp_access_check(s)) { + return true; + } + + memop = finalize_memop_asimd(s, a->sz); + op_addr_ldst_pre(s, a, &clean_addr, &dirty_addr, false, memop); + do_fp_ld(s, a->rt, clean_addr, memop); + return true; +} + +static bool trans_STR_v(DisasContext *s, arg_ldst *a) +{ + TCGv_i64 clean_addr, dirty_addr; + MemOp memop; + + if (extract32(a->opt, 1, 1) == 0) { + return false; + } + + if (!fp_access_check(s)) { + return true; + } + + memop = finalize_memop_asimd(s, a->sz); + op_addr_ldst_pre(s, a, &clean_addr, &dirty_addr, true, memop); + do_fp_st(s, a->rt, clean_addr, memop); + return true; } /* Atomic memory operations @@ -XXX,XX +XXX,XX @@ static void disas_ldst_ldapr_stlr(DisasContext *s, uint32_t insn) static void disas_ldst_reg(DisasContext *s, uint32_t insn) { int rt = extract32(insn, 0, 5); - int opc = extract32(insn, 22, 2); bool is_vector = extract32(insn, 26, 1); int size = extract32(insn, 30, 2); @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg(DisasContext *s, uint32_t insn) disas_ldst_atomic(s, insn, size, rt, is_vector); return; case 2: - disas_ldst_reg_roffset(s, insn, opc, size, rt, is_vector); - return; + break; default: disas_ldst_pac(s, insn, size, rt, is_vector); return; -- 2.34.1 Convert the insns in the atomic memory operations group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-16-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 15 ++++ target/arm/tcg/translate-a64.c | 153 ++++++++++++--------------------- 2 files changed, 70 insertions(+), 98 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ STR_v sz:2 111 1 00 00 1 ..... ... . 10 ..... ..... @ldst sign=0 ext=0 STR_v 00 111 1 00 10 1 ..... ... . 10 ..... ..... @ldst sign=0 ext=0 sz=4 LDR_v sz:2 111 1 00 01 1 ..... ... . 10 ..... ..... @ldst sign=0 ext=0 LDR_v 00 111 1 00 11 1 ..... ... . 10 ..... ..... @ldst sign=0 ext=0 sz=4 + +# Atomic memory operations +&atomic rs rn rt a r sz +@atomic sz:2 ... . .. a:1 r:1 . rs:5 . ... .. rn:5 rt:5 &atomic +LDADD .. 111 0 00 . . 1 ..... 0000 00 ..... ..... @atomic +LDCLR .. 111 0 00 . . 1 ..... 0001 00 ..... ..... @atomic +LDEOR .. 111 0 00 . . 1 ..... 0010 00 ..... ..... @atomic +LDSET .. 111 0 00 . . 1 ..... 0011 00 ..... ..... @atomic +LDSMAX .. 111 0 00 . . 1 ..... 0100 00 ..... ..... @atomic +LDSMIN .. 111 0 00 . . 1 ..... 0101 00 ..... ..... @atomic +LDUMAX .. 111 0 00 . . 1 ..... 0110 00 ..... ..... @atomic +LDUMIN .. 111 0 00 . . 1 ..... 0111 00 ..... ..... @atomic +SWP .. 111 0 00 . . 1 ..... 1000 00 ..... ..... @atomic + +LDAPR sz:2 111 0 00 1 0 1 11111 1100 00 rn:5 rt:5 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_STR_v(DisasContext *s, arg_ldst *a) return true; } -/* Atomic memory operations - * - * 31 30 27 26 24 22 21 16 15 12 10 5 0 - * +------+-------+---+-----+-----+---+----+----+-----+-----+----+-----+ - * | size | 1 1 1 | V | 0 0 | A R | 1 | Rs | o3 | opc | 0 0 | Rn | Rt | - * +------+-------+---+-----+-----+--------+----+-----+-----+----+-----+ - * - * Rt: the result register - * Rn: base address or SP - * Rs: the source register for the operation - * V: vector flag (always 0 as of v8.3) - * A: acquire flag - * R: release flag - */ -static void disas_ldst_atomic(DisasContext *s, uint32_t insn, - int size, int rt, bool is_vector) + +static bool do_atomic_ld(DisasContext *s, arg_atomic *a, AtomicThreeOpFn *fn, + int sign, bool invert) { - int rs = extract32(insn, 16, 5); - int rn = extract32(insn, 5, 5); - int o3_opc = extract32(insn, 12, 4); - bool r = extract32(insn, 22, 1); - bool a = extract32(insn, 23, 1); - TCGv_i64 tcg_rs, tcg_rt, clean_addr; - AtomicThreeOpFn *fn = NULL; - MemOp mop = size; + MemOp mop = a->sz | sign; + TCGv_i64 clean_addr, tcg_rs, tcg_rt; - if (is_vector || !dc_isar_feature(aa64_atomics, s)) { - unallocated_encoding(s); - return; - } - switch (o3_opc) { - case 000: /* LDADD */ - fn = tcg_gen_atomic_fetch_add_i64; - break; - case 001: /* LDCLR */ - fn = tcg_gen_atomic_fetch_and_i64; - break; - case 002: /* LDEOR */ - fn = tcg_gen_atomic_fetch_xor_i64; - break; - case 003: /* LDSET */ - fn = tcg_gen_atomic_fetch_or_i64; - break; - case 004: /* LDSMAX */ - fn = tcg_gen_atomic_fetch_smax_i64; - mop |= MO_SIGN; - break; - case 005: /* LDSMIN */ - fn = tcg_gen_atomic_fetch_smin_i64; - mop |= MO_SIGN; - break; - case 006: /* LDUMAX */ - fn = tcg_gen_atomic_fetch_umax_i64; - break; - case 007: /* LDUMIN */ - fn = tcg_gen_atomic_fetch_umin_i64; - break; - case 010: /* SWP */ - fn = tcg_gen_atomic_xchg_i64; - break; - case 014: /* LDAPR, LDAPRH, LDAPRB */ - if (!dc_isar_feature(aa64_rcpc_8_3, s) || - rs != 31 || a != 1 || r != 0) { - unallocated_encoding(s); - return; - } - break; - default: - unallocated_encoding(s); - return; - } - - if (rn == 31) { + if (a->rn == 31) { gen_check_sp_alignment(s); } - - mop = check_atomic_align(s, rn, mop); - clean_addr = gen_mte_check1(s, cpu_reg_sp(s, rn), false, rn != 31, mop); - - if (o3_opc == 014) { - /* - * LDAPR* are a special case because they are a simple load, not a - * fetch-and-do-something op. - * The architectural consistency requirements here are weaker than - * full load-acquire (we only need "load-acquire processor consistent"), - * but we choose to implement them as full LDAQ. - */ - do_gpr_ld(s, cpu_reg(s, rt), clean_addr, mop, false, - true, rt, disas_ldst_compute_iss_sf(size, false, 0), true); - tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); - return; - } - - tcg_rs = read_cpu_reg(s, rs, true); - tcg_rt = cpu_reg(s, rt); - - if (o3_opc == 1) { /* LDCLR */ + mop = check_atomic_align(s, a->rn, mop); + clean_addr = gen_mte_check1(s, cpu_reg_sp(s, a->rn), false, + a->rn != 31, mop); + tcg_rs = read_cpu_reg(s, a->rs, true); + tcg_rt = cpu_reg(s, a->rt); + if (invert) { tcg_gen_not_i64(tcg_rs, tcg_rs); } - - /* The tcg atomic primitives are all full barriers. Therefore we + /* + * The tcg atomic primitives are all full barriers. Therefore we * can ignore the Acquire and Release bits of this instruction. */ fn(tcg_rt, clean_addr, tcg_rs, get_mem_index(s), mop); if (mop & MO_SIGN) { - switch (size) { + switch (a->sz) { case MO_8: tcg_gen_ext8u_i64(tcg_rt, tcg_rt); break; @@ -XXX,XX +XXX,XX @@ static void disas_ldst_atomic(DisasContext *s, uint32_t insn, g_assert_not_reached(); } } + return true; +} + +TRANS_FEAT(LDADD, aa64_atomics, do_atomic_ld, a, tcg_gen_atomic_fetch_add_i64, 0, false) +TRANS_FEAT(LDCLR, aa64_atomics, do_atomic_ld, a, tcg_gen_atomic_fetch_and_i64, 0, true) +TRANS_FEAT(LDEOR, aa64_atomics, do_atomic_ld, a, tcg_gen_atomic_fetch_xor_i64, 0, false) +TRANS_FEAT(LDSET, aa64_atomics, do_atomic_ld, a, tcg_gen_atomic_fetch_or_i64, 0, false) +TRANS_FEAT(LDSMAX, aa64_atomics, do_atomic_ld, a, tcg_gen_atomic_fetch_smax_i64, MO_SIGN, false) +TRANS_FEAT(LDSMIN, aa64_atomics, do_atomic_ld, a, tcg_gen_atomic_fetch_smin_i64, MO_SIGN, false) +TRANS_FEAT(LDUMAX, aa64_atomics, do_atomic_ld, a, tcg_gen_atomic_fetch_umax_i64, 0, false) +TRANS_FEAT(LDUMIN, aa64_atomics, do_atomic_ld, a, tcg_gen_atomic_fetch_umin_i64, 0, false) +TRANS_FEAT(SWP, aa64_atomics, do_atomic_ld, a, tcg_gen_atomic_xchg_i64, 0, false) + +static bool trans_LDAPR(DisasContext *s, arg_LDAPR *a) +{ + bool iss_sf = ldst_iss_sf(a->sz, false, false); + TCGv_i64 clean_addr; + MemOp mop; + + if (!dc_isar_feature(aa64_atomics, s) || + !dc_isar_feature(aa64_rcpc_8_3, s)) { + return false; + } + if (a->rn == 31) { + gen_check_sp_alignment(s); + } + mop = check_atomic_align(s, a->rn, a->sz); + clean_addr = gen_mte_check1(s, cpu_reg_sp(s, a->rn), false, + a->rn != 31, mop); + /* + * LDAPR* are a special case because they are a simple load, not a + * fetch-and-do-something op. + * The architectural consistency requirements here are weaker than + * full load-acquire (we only need "load-acquire processor consistent"), + * but we choose to implement them as full LDAQ. + */ + do_gpr_ld(s, cpu_reg(s, a->rt), clean_addr, mop, false, + true, a->rt, iss_sf, true); + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); + return true; } /* @@ -XXX,XX +XXX,XX @@ static void disas_ldst_reg(DisasContext *s, uint32_t insn) } switch (extract32(insn, 10, 2)) { case 0: - disas_ldst_atomic(s, insn, size, rt, is_vector); - return; case 2: break; default: -- 2.34.1 Convert the instructions in the load/store register (pointer authentication) group ot decodetree: LDRAA, LDRAB. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-17-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 7 +++ target/arm/tcg/translate-a64.c | 83 +++++++--------------------------- 2 files changed, 23 insertions(+), 67 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ LDUMIN .. 111 0 00 . . 1 ..... 0111 00 ..... ..... @atomic SWP .. 111 0 00 . . 1 ..... 1000 00 ..... ..... @atomic LDAPR sz:2 111 0 00 1 0 1 11111 1100 00 rn:5 rt:5 + +# Load/store register (pointer authentication) + +# LDRA immediate is 10 bits signed and scaled, but the bits aren't all contiguous +%ldra_imm 22:s1 12:9 !function=times_2 + +LDRA 11 111 0 00 m:1 . 1 ......... w:1 1 rn:5 rt:5 imm=%ldra_imm diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_LDAPR(DisasContext *s, arg_LDAPR *a) return true; } -/* - * PAC memory operations - * - * 31 30 27 26 24 22 21 12 11 10 5 0 - * +------+-------+---+-----+-----+---+--------+---+---+----+-----+ - * | size | 1 1 1 | V | 0 0 | M S | 1 | imm9 | W | 1 | Rn | Rt | - * +------+-------+---+-----+-----+---+--------+---+---+----+-----+ - * - * Rt: the result register - * Rn: base address or SP - * V: vector flag (always 0 as of v8.3) - * M: clear for key DA, set for key DB - * W: pre-indexing flag - * S: sign for imm9. - */ -static void disas_ldst_pac(DisasContext *s, uint32_t insn, - int size, int rt, bool is_vector) +static bool trans_LDRA(DisasContext *s, arg_LDRA *a) { - int rn = extract32(insn, 5, 5); - bool is_wback = extract32(insn, 11, 1); - bool use_key_a = !extract32(insn, 23, 1); - int offset; TCGv_i64 clean_addr, dirty_addr, tcg_rt; MemOp memop; - if (size != 3 || is_vector || !dc_isar_feature(aa64_pauth, s)) { - unallocated_encoding(s); - return; + /* Load with pointer authentication */ + if (!dc_isar_feature(aa64_pauth, s)) { + return false; } - if (rn == 31) { + if (a->rn == 31) { gen_check_sp_alignment(s); } - dirty_addr = read_cpu_reg_sp(s, rn, 1); + dirty_addr = read_cpu_reg_sp(s, a->rn, 1); if (s->pauth_active) { - if (use_key_a) { + if (!a->m) { gen_helper_autda(dirty_addr, cpu_env, dirty_addr, tcg_constant_i64(0)); } else { @@ -XXX,XX +XXX,XX @@ static void disas_ldst_pac(DisasContext *s, uint32_t insn, } } - /* Form the 10-bit signed, scaled offset. */ - offset = (extract32(insn, 22, 1) << 9) | extract32(insn, 12, 9); - offset = sextract32(offset << size, 0, 10 + size); - tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); + tcg_gen_addi_i64(dirty_addr, dirty_addr, a->imm); - memop = finalize_memop(s, size); + memop = finalize_memop(s, MO_64); /* Note that "clean" and "dirty" here refer to TBI not PAC. */ clean_addr = gen_mte_check1(s, dirty_addr, false, - is_wback || rn != 31, memop); + a->w || a->rn != 31, memop); - tcg_rt = cpu_reg(s, rt); + tcg_rt = cpu_reg(s, a->rt); do_gpr_ld(s, tcg_rt, clean_addr, memop, - /* extend */ false, /* iss_valid */ !is_wback, - /* iss_srt */ rt, /* iss_sf */ true, /* iss_ar */ false); + /* extend */ false, /* iss_valid */ !a->w, + /* iss_srt */ a->rt, /* iss_sf */ true, /* iss_ar */ false); - if (is_wback) { - tcg_gen_mov_i64(cpu_reg_sp(s, rn), dirty_addr); + if (a->w) { + tcg_gen_mov_i64(cpu_reg_sp(s, a->rn), dirty_addr); } + return true; } /* @@ -XXX,XX +XXX,XX @@ static void disas_ldst_ldapr_stlr(DisasContext *s, uint32_t insn) } } -/* Load/store register (all forms) */ -static void disas_ldst_reg(DisasContext *s, uint32_t insn) -{ - int rt = extract32(insn, 0, 5); - bool is_vector = extract32(insn, 26, 1); - int size = extract32(insn, 30, 2); - - switch (extract32(insn, 24, 2)) { - case 0: - if (extract32(insn, 21, 1) == 0) { - break; - } - switch (extract32(insn, 10, 2)) { - case 0: - case 2: - break; - default: - disas_ldst_pac(s, insn, size, rt, is_vector); - return; - } - break; - } - unallocated_encoding(s); -} - /* AdvSIMD load/store multiple structures * * 31 30 29 23 22 21 16 15 12 11 10 9 5 4 0 @@ -XXX,XX +XXX,XX @@ static void disas_ldst_tag(DisasContext *s, uint32_t insn) static void disas_ldst(DisasContext *s, uint32_t insn) { switch (extract32(insn, 24, 6)) { - case 0x38: case 0x39: - case 0x3c: case 0x3d: /* Load/store register (all forms) */ - disas_ldst_reg(s, insn); - break; case 0x0c: /* AdvSIMD load/store multiple structures */ disas_ldst_multiple_struct(s, insn); break; -- 2.34.1 Convert the instructions in the LDAPR/STLR (unscaled immediate) group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-18-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 10 +++ target/arm/tcg/translate-a64.c | 132 ++++++++++++--------------------- 2 files changed, 56 insertions(+), 86 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ LDAPR sz:2 111 0 00 1 0 1 11111 1100 00 rn:5 rt:5 %ldra_imm 22:s1 12:9 !function=times_2 LDRA 11 111 0 00 m:1 . 1 ......... w:1 1 rn:5 rt:5 imm=%ldra_imm + +&ldapr_stlr_i rn rt imm sz sign ext +@ldapr_stlr_i .. ...... .. . imm:9 .. rn:5 rt:5 &ldapr_stlr_i +STLR_i sz:2 011001 00 0 ......... 00 ..... ..... @ldapr_stlr_i sign=0 ext=0 +LDAPR_i sz:2 011001 01 0 ......... 00 ..... ..... @ldapr_stlr_i sign=0 ext=0 +LDAPR_i 00 011001 10 0 ......... 00 ..... ..... @ldapr_stlr_i sign=1 ext=0 sz=0 +LDAPR_i 01 011001 10 0 ......... 00 ..... ..... @ldapr_stlr_i sign=1 ext=0 sz=1 +LDAPR_i 10 011001 10 0 ......... 00 ..... ..... @ldapr_stlr_i sign=1 ext=0 sz=2 +LDAPR_i 00 011001 11 0 ......... 00 ..... ..... @ldapr_stlr_i sign=1 ext=1 sz=0 +LDAPR_i 01 011001 11 0 ......... 00 ..... ..... @ldapr_stlr_i sign=1 ext=1 sz=1 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_compare_and_swap_pair(DisasContext *s, int rs, int rt, } } -/* Update the Sixty-Four bit (SF) registersize. This logic is derived +/* + * Compute the ISS.SF bit for syndrome information if an exception + * is taken on a load or store. This indicates whether the instruction + * is accessing a 32-bit or 64-bit register. This logic is derived * from the ARMv8 specs for LDR (Shared decode for all encodings). */ -static bool disas_ldst_compute_iss_sf(int size, bool is_signed, int opc) -{ - int opc0 = extract32(opc, 0, 1); - int regsize; - - if (is_signed) { - regsize = opc0 ? 32 : 64; - } else { - regsize = size == 3 ? 64 : 32; - } - return regsize == 64; -} - static bool ldst_iss_sf(int size, bool sign, bool ext) { @@ -XXX,XX +XXX,XX @@ static bool trans_LDRA(DisasContext *s, arg_LDRA *a) return true; } -/* - * LDAPR/STLR (unscaled immediate) - * - * 31 30 24 22 21 12 10 5 0 - * +------+-------------+-----+---+--------+-----+----+-----+ - * | size | 0 1 1 0 0 1 | opc | 0 | imm9 | 0 0 | Rn | Rt | - * +------+-------------+-----+---+--------+-----+----+-----+ - * - * Rt: source or destination register - * Rn: base register - * imm9: unscaled immediate offset - * opc: 00: STLUR*, 01/10/11: various LDAPUR* - * size: size of load/store - */ -static void disas_ldst_ldapr_stlr(DisasContext *s, uint32_t insn) +static bool trans_LDAPR_i(DisasContext *s, arg_ldapr_stlr_i *a) { - int rt = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int offset = sextract32(insn, 12, 9); - int opc = extract32(insn, 22, 2); - int size = extract32(insn, 30, 2); TCGv_i64 clean_addr, dirty_addr; - bool is_store = false; - bool extend = false; - bool iss_sf; - MemOp mop = size; + MemOp mop = a->sz | (a->sign ? MO_SIGN : 0); + bool iss_sf = ldst_iss_sf(a->sz, a->sign, a->ext); if (!dc_isar_feature(aa64_rcpc_8_4, s)) { - unallocated_encoding(s); - return; + return false; } - switch (opc) { - case 0: /* STLURB */ - is_store = true; - break; - case 1: /* LDAPUR* */ - break; - case 2: /* LDAPURS* 64-bit variant */ - if (size == 3) { - unallocated_encoding(s); - return; - } - mop |= MO_SIGN; - break; - case 3: /* LDAPURS* 32-bit variant */ - if (size > 1) { - unallocated_encoding(s); - return; - } - mop |= MO_SIGN; - extend = true; /* zero-extend 32->64 after signed load */ - break; - default: - g_assert_not_reached(); - } - - iss_sf = disas_ldst_compute_iss_sf(size, (mop & MO_SIGN) != 0, opc); - - if (rn == 31) { + if (a->rn == 31) { gen_check_sp_alignment(s); } - mop = check_ordered_align(s, rn, offset, is_store, mop); - - dirty_addr = read_cpu_reg_sp(s, rn, 1); - tcg_gen_addi_i64(dirty_addr, dirty_addr, offset); + mop = check_ordered_align(s, a->rn, a->imm, false, mop); + dirty_addr = read_cpu_reg_sp(s, a->rn, 1); + tcg_gen_addi_i64(dirty_addr, dirty_addr, a->imm); clean_addr = clean_data_tbi(s, dirty_addr); - if (is_store) { - /* Store-Release semantics */ - tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); - do_gpr_st(s, cpu_reg(s, rt), clean_addr, mop, true, rt, iss_sf, true); - } else { - /* - * Load-AcquirePC semantics; we implement as the slightly more - * restrictive Load-Acquire. - */ - do_gpr_ld(s, cpu_reg(s, rt), clean_addr, mop, - extend, true, rt, iss_sf, true); - tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); + /* + * Load-AcquirePC semantics; we implement as the slightly more + * restrictive Load-Acquire. + */ + do_gpr_ld(s, cpu_reg(s, a->rt), clean_addr, mop, a->ext, true, + a->rt, iss_sf, true); + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_LDAQ); + return true; +} + +static bool trans_STLR_i(DisasContext *s, arg_ldapr_stlr_i *a) +{ + TCGv_i64 clean_addr, dirty_addr; + MemOp mop = a->sz; + bool iss_sf = ldst_iss_sf(a->sz, a->sign, a->ext); + + if (!dc_isar_feature(aa64_rcpc_8_4, s)) { + return false; } + + /* TODO: ARMv8.4-LSE SCTLR.nAA */ + + if (a->rn == 31) { + gen_check_sp_alignment(s); + } + + mop = check_ordered_align(s, a->rn, a->imm, true, mop); + dirty_addr = read_cpu_reg_sp(s, a->rn, 1); + tcg_gen_addi_i64(dirty_addr, dirty_addr, a->imm); + clean_addr = clean_data_tbi(s, dirty_addr); + + /* Store-Release semantics */ + tcg_gen_mb(TCG_MO_ALL | TCG_BAR_STRL); + do_gpr_st(s, cpu_reg(s, a->rt), clean_addr, mop, true, a->rt, iss_sf, true); + return true; } /* AdvSIMD load/store multiple structures @@ -XXX,XX +XXX,XX @@ static void disas_ldst(DisasContext *s, uint32_t insn) case 0x19: if (extract32(insn, 21, 1) != 0) { disas_ldst_tag(s, insn); - } else if (extract32(insn, 10, 2) == 0) { - disas_ldst_ldapr_stlr(s, insn); } else { unallocated_encoding(s); } -- 2.34.1 Convert the instructions in the ASIMD load/store multiple structures instruction classes to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-19-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 20 +++ target/arm/tcg/translate-a64.c | 222 ++++++++++++++++----------------- 2 files changed, 131 insertions(+), 111 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ LDAPR_i 01 011001 10 0 ......... 00 ..... ..... @ldapr_stlr_i sign=1 ext LDAPR_i 10 011001 10 0 ......... 00 ..... ..... @ldapr_stlr_i sign=1 ext=0 sz=2 LDAPR_i 00 011001 11 0 ......... 00 ..... ..... @ldapr_stlr_i sign=1 ext=1 sz=0 LDAPR_i 01 011001 11 0 ......... 00 ..... ..... @ldapr_stlr_i sign=1 ext=1 sz=1 + +# Load/store multiple structures +# The 4-bit opcode in [15:12] encodes repeat count and structure elements +&ldst_mult rm rn rt sz q p rpt selem +@ldst_mult . q:1 ...... p:1 . . rm:5 .... sz:2 rn:5 rt:5 &ldst_mult +ST_mult 0 . 001100 . 0 0 ..... 0000 .. ..... ..... @ldst_mult rpt=1 selem=4 +ST_mult 0 . 001100 . 0 0 ..... 0010 .. ..... ..... @ldst_mult rpt=4 selem=1 +ST_mult 0 . 001100 . 0 0 ..... 0100 .. ..... ..... @ldst_mult rpt=1 selem=3 +ST_mult 0 . 001100 . 0 0 ..... 0110 .. ..... ..... @ldst_mult rpt=3 selem=1 +ST_mult 0 . 001100 . 0 0 ..... 0111 .. ..... ..... @ldst_mult rpt=1 selem=1 +ST_mult 0 . 001100 . 0 0 ..... 1000 .. ..... ..... @ldst_mult rpt=1 selem=2 +ST_mult 0 . 001100 . 0 0 ..... 1010 .. ..... ..... @ldst_mult rpt=2 selem=1 + +LD_mult 0 . 001100 . 1 0 ..... 0000 .. ..... ..... @ldst_mult rpt=1 selem=4 +LD_mult 0 . 001100 . 1 0 ..... 0010 .. ..... ..... @ldst_mult rpt=4 selem=1 +LD_mult 0 . 001100 . 1 0 ..... 0100 .. ..... ..... @ldst_mult rpt=1 selem=3 +LD_mult 0 . 001100 . 1 0 ..... 0110 .. ..... ..... @ldst_mult rpt=3 selem=1 +LD_mult 0 . 001100 . 1 0 ..... 0111 .. ..... ..... @ldst_mult rpt=1 selem=1 +LD_mult 0 . 001100 . 1 0 ..... 1000 .. ..... ..... @ldst_mult rpt=1 selem=2 +LD_mult 0 . 001100 . 1 0 ..... 1010 .. ..... ..... @ldst_mult rpt=2 selem=1 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_STLR_i(DisasContext *s, arg_ldapr_stlr_i *a) return true; } -/* AdvSIMD load/store multiple structures - * - * 31 30 29 23 22 21 16 15 12 11 10 9 5 4 0 - * +---+---+---------------+---+-------------+--------+------+------+------+ - * | 0 | Q | 0 0 1 1 0 0 0 | L | 0 0 0 0 0 0 | opcode | size | Rn | Rt | - * +---+---+---------------+---+-------------+--------+------+------+------+ - * - * AdvSIMD load/store multiple structures (post-indexed) - * - * 31 30 29 23 22 21 20 16 15 12 11 10 9 5 4 0 - * +---+---+---------------+---+---+---------+--------+------+------+------+ - * | 0 | Q | 0 0 1 1 0 0 1 | L | 0 | Rm | opcode | size | Rn | Rt | - * +---+---+---------------+---+---+---------+--------+------+------+------+ - * - * Rt: first (or only) SIMD&FP register to be transferred - * Rn: base address or SP - * Rm (post-index only): post-index register (when !31) or size dependent #imm - */ -static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) +static bool trans_LD_mult(DisasContext *s, arg_ldst_mult *a) { - int rt = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int rm = extract32(insn, 16, 5); - int size = extract32(insn, 10, 2); - int opcode = extract32(insn, 12, 4); - bool is_store = !extract32(insn, 22, 1); - bool is_postidx = extract32(insn, 23, 1); - bool is_q = extract32(insn, 30, 1); TCGv_i64 clean_addr, tcg_rn, tcg_ebytes; MemOp endian, align, mop; int total; /* total bytes */ int elements; /* elements per vector */ - int rpt; /* num iterations */ - int selem; /* structure elements */ int r; + int size = a->sz; - if (extract32(insn, 31, 1) || extract32(insn, 21, 1)) { - unallocated_encoding(s); - return; + if (!a->p && a->rm != 0) { + /* For non-postindexed accesses the Rm field must be 0 */ + return false; } - - if (!is_postidx && rm != 0) { - unallocated_encoding(s); - return; + if (size == 3 && !a->q && a->selem != 1) { + return false; } - - /* From the shared decode logic */ - switch (opcode) { - case 0x0: - rpt = 1; - selem = 4; - break; - case 0x2: - rpt = 4; - selem = 1; - break; - case 0x4: - rpt = 1; - selem = 3; - break; - case 0x6: - rpt = 3; - selem = 1; - break; - case 0x7: - rpt = 1; - selem = 1; - break; - case 0x8: - rpt = 1; - selem = 2; - break; - case 0xa: - rpt = 2; - selem = 1; - break; - default: - unallocated_encoding(s); - return; - } - - if (size == 3 && !is_q && selem != 1) { - /* reserved */ - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; + return true; } - if (rn == 31) { + if (a->rn == 31) { gen_check_sp_alignment(s); } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) endian = MO_LE; } - total = rpt * selem * (is_q ? 16 : 8); - tcg_rn = cpu_reg_sp(s, rn); + total = a->rpt * a->selem * (a->q ? 16 : 8); + tcg_rn = cpu_reg_sp(s, a->rn); /* * Issue the MTE check vs the logical repeat count, before we * promote consecutive little-endian elements below. */ - clean_addr = gen_mte_checkN(s, tcg_rn, is_store, is_postidx || rn != 31, - total, finalize_memop_asimd(s, size)); + clean_addr = gen_mte_checkN(s, tcg_rn, false, a->p || a->rn != 31, total, + finalize_memop_asimd(s, size)); /* * Consecutive little-endian elements from a single register * can be promoted to a larger little-endian operation. */ align = MO_ALIGN; - if (selem == 1 && endian == MO_LE) { + if (a->selem == 1 && endian == MO_LE) { align = pow2_align(size); size = 3; } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_multiple_struct(DisasContext *s, uint32_t insn) } mop = endian | size | align; - elements = (is_q ? 16 : 8) >> size; + elements = (a->q ? 16 : 8) >> size; tcg_ebytes = tcg_constant_i64(1 << size); - for (r = 0; r < rpt; r++) { + for (r = 0; r < a->rpt; r++) { int e; for (e = 0; e < elements; e++) { int xs; - for (xs = 0; xs < selem; xs++) { - int tt = (rt + r + xs) % 32; - if (is_store) { - do_vec_st(s, tt, e, clean_addr, mop); - } else { - do_vec_ld(s, tt, e, clean_addr, mop); - } + for (xs = 0; xs < a->selem; xs++) { + int tt = (a->rt + r + xs) % 32; + do_vec_ld(s, tt, e, clean_addr, mop); tcg_gen_add_i64(clean_addr, clean_addr, tcg_ebytes); } } } - 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); + /* + * 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 < a->rpt * a->selem; r++) { + int tt = (a->rt + r) % 32; + clear_vec_high(s, a->q, tt); + } + + if (a->p) { + if (a->rm == 31) { + tcg_gen_addi_i64(tcg_rn, tcg_rn, total); + } else { + tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, a->rm)); + } + } + return true; +} + +static bool trans_ST_mult(DisasContext *s, arg_ldst_mult *a) +{ + TCGv_i64 clean_addr, tcg_rn, tcg_ebytes; + MemOp endian, align, mop; + + int total; /* total bytes */ + int elements; /* elements per vector */ + int r; + int size = a->sz; + + if (!a->p && a->rm != 0) { + /* For non-postindexed accesses the Rm field must be 0 */ + return false; + } + if (size == 3 && !a->q && a->selem != 1) { + return false; + } + if (!fp_access_check(s)) { + return true; + } + + if (a->rn == 31) { + gen_check_sp_alignment(s); + } + + /* For our purposes, bytes are always little-endian. */ + endian = s->be_data; + if (size == 0) { + endian = MO_LE; + } + + total = a->rpt * a->selem * (a->q ? 16 : 8); + tcg_rn = cpu_reg_sp(s, a->rn); + + /* + * Issue the MTE check vs the logical repeat count, before we + * promote consecutive little-endian elements below. + */ + clean_addr = gen_mte_checkN(s, tcg_rn, true, a->p || a->rn != 31, total, + finalize_memop_asimd(s, size)); + + /* + * Consecutive little-endian elements from a single register + * can be promoted to a larger little-endian operation. + */ + align = MO_ALIGN; + if (a->selem == 1 && endian == MO_LE) { + align = pow2_align(size); + size = 3; + } + if (!s->align_mem) { + align = 0; + } + mop = endian | size | align; + + elements = (a->q ? 16 : 8) >> size; + tcg_ebytes = tcg_constant_i64(1 << size); + for (r = 0; r < a->rpt; r++) { + int e; + for (e = 0; e < elements; e++) { + int xs; + for (xs = 0; xs < a->selem; xs++) { + int tt = (a->rt + r + xs) % 32; + do_vec_st(s, tt, e, clean_addr, mop); + tcg_gen_add_i64(clean_addr, clean_addr, tcg_ebytes); + } } } - if (is_postidx) { - if (rm == 31) { + if (a->p) { + if (a->rm == 31) { tcg_gen_addi_i64(tcg_rn, tcg_rn, total); } else { - tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm)); + tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, a->rm)); } } + return true; } /* AdvSIMD load/store single structure @@ -XXX,XX +XXX,XX @@ static void disas_ldst_tag(DisasContext *s, uint32_t insn) static void disas_ldst(DisasContext *s, uint32_t insn) { switch (extract32(insn, 24, 6)) { - case 0x0c: /* AdvSIMD load/store multiple structures */ - disas_ldst_multiple_struct(s, insn); - break; case 0x0d: /* AdvSIMD load/store single structure */ disas_ldst_single_struct(s, insn); break; -- 2.34.1 Convert the ASIMD load/store single structure insns to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20230602155223.2040685-20-peter.maydell@linaro.org Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/tcg/a64.decode | 34 +++++ target/arm/tcg/translate-a64.c | 219 +++++++++++++++------------------ 2 files changed, 136 insertions(+), 117 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ LD_mult 0 . 001100 . 1 0 ..... 0110 .. ..... ..... @ldst_mult rpt=3 sele LD_mult 0 . 001100 . 1 0 ..... 0111 .. ..... ..... @ldst_mult rpt=1 selem=1 LD_mult 0 . 001100 . 1 0 ..... 1000 .. ..... ..... @ldst_mult rpt=1 selem=2 LD_mult 0 . 001100 . 1 0 ..... 1010 .. ..... ..... @ldst_mult rpt=2 selem=1 + +# Load/store single structure +&ldst_single rm rn rt p selem index scale + +%ldst_single_selem 13:1 21:1 !function=plus_1 + +%ldst_single_index_b 30:1 10:3 +%ldst_single_index_h 30:1 11:2 +%ldst_single_index_s 30:1 12:1 + +@ldst_single_b .. ...... p:1 .. rm:5 ...... rn:5 rt:5 \ + &ldst_single scale=0 selem=%ldst_single_selem \ + index=%ldst_single_index_b +@ldst_single_h .. ...... p:1 .. rm:5 ...... rn:5 rt:5 \ + &ldst_single scale=1 selem=%ldst_single_selem \ + index=%ldst_single_index_h +@ldst_single_s .. ...... p:1 .. rm:5 ...... rn:5 rt:5 \ + &ldst_single scale=2 selem=%ldst_single_selem \ + index=%ldst_single_index_s +@ldst_single_d . index:1 ...... p:1 .. rm:5 ...... rn:5 rt:5 \ + &ldst_single scale=3 selem=%ldst_single_selem + +ST_single 0 . 001101 . 0 . ..... 00 . ... ..... ..... @ldst_single_b +ST_single 0 . 001101 . 0 . ..... 01 . ..0 ..... ..... @ldst_single_h +ST_single 0 . 001101 . 0 . ..... 10 . .00 ..... ..... @ldst_single_s +ST_single 0 . 001101 . 0 . ..... 10 . 001 ..... ..... @ldst_single_d + +LD_single 0 . 001101 . 1 . ..... 00 . ... ..... ..... @ldst_single_b +LD_single 0 . 001101 . 1 . ..... 01 . ..0 ..... ..... @ldst_single_h +LD_single 0 . 001101 . 1 . ..... 10 . .00 ..... ..... @ldst_single_s +LD_single 0 . 001101 . 1 . ..... 10 . 001 ..... ..... @ldst_single_d + +# Replicating load case +LD_single_repl 0 q:1 001101 p:1 1 . rm:5 11 . 0 scale:2 rn:5 rt:5 selem=%ldst_single_selem diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_ST_mult(DisasContext *s, arg_ldst_mult *a) return true; } -/* AdvSIMD load/store single structure - * - * 31 30 29 23 22 21 20 16 15 13 12 11 10 9 5 4 0 - * +---+---+---------------+-----+-----------+-----+---+------+------+------+ - * | 0 | Q | 0 0 1 1 0 1 0 | L R | 0 0 0 0 0 | opc | S | size | Rn | Rt | - * +---+---+---------------+-----+-----------+-----+---+------+------+------+ - * - * AdvSIMD load/store single structure (post-indexed) - * - * 31 30 29 23 22 21 20 16 15 13 12 11 10 9 5 4 0 - * +---+---+---------------+-----+-----------+-----+---+------+------+------+ - * | 0 | Q | 0 0 1 1 0 1 1 | L R | Rm | opc | S | size | Rn | Rt | - * +---+---+---------------+-----+-----------+-----+---+------+------+------+ - * - * Rt: first (or only) SIMD&FP register to be transferred - * Rn: base address or SP - * Rm (post-index only): post-index register (when !31) or size dependent #imm - * index = encoded in Q:S:size dependent on size - * - * lane_size = encoded in R, opc - * transfer width = encoded in opc, S, size - */ -static void disas_ldst_single_struct(DisasContext *s, uint32_t insn) +static bool trans_ST_single(DisasContext *s, arg_ldst_single *a) { - int rt = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int rm = extract32(insn, 16, 5); - int size = extract32(insn, 10, 2); - int S = extract32(insn, 12, 1); - int opc = extract32(insn, 13, 3); - int R = extract32(insn, 21, 1); - int is_load = extract32(insn, 22, 1); - int is_postidx = extract32(insn, 23, 1); - int is_q = extract32(insn, 30, 1); - - int scale = extract32(opc, 1, 2); - int selem = (extract32(opc, 0, 1) << 1 | R) + 1; - bool replicate = false; - int index = is_q << 3 | S << 2 | size; - int xs, total; + int xs, total, rt; TCGv_i64 clean_addr, tcg_rn, tcg_ebytes; MemOp mop; - if (extract32(insn, 31, 1)) { - unallocated_encoding(s); - return; + if (!a->p && a->rm != 0) { + return false; } - if (!is_postidx && rm != 0) { - unallocated_encoding(s); - return; - } - - switch (scale) { - case 3: - if (!is_load || S) { - unallocated_encoding(s); - return; - } - scale = size; - replicate = true; - break; - case 0: - break; - case 1: - if (extract32(size, 0, 1)) { - unallocated_encoding(s); - return; - } - index >>= 1; - break; - case 2: - if (extract32(size, 1, 1)) { - unallocated_encoding(s); - return; - } - if (!extract32(size, 0, 1)) { - index >>= 2; - } else { - if (S) { - unallocated_encoding(s); - return; - } - index >>= 3; - scale = 3; - } - break; - default: - g_assert_not_reached(); - } - if (!fp_access_check(s)) { - return; + return true; } - if (rn == 31) { + if (a->rn == 31) { gen_check_sp_alignment(s); } - total = selem << scale; - tcg_rn = cpu_reg_sp(s, rn); + total = a->selem << a->scale; + tcg_rn = cpu_reg_sp(s, a->rn); - mop = finalize_memop_asimd(s, scale); - - clean_addr = gen_mte_checkN(s, tcg_rn, !is_load, is_postidx || rn != 31, + mop = finalize_memop_asimd(s, a->scale); + clean_addr = gen_mte_checkN(s, tcg_rn, true, a->p || a->rn != 31, total, mop); - tcg_ebytes = tcg_constant_i64(1 << scale); - for (xs = 0; xs < selem; xs++) { - if (replicate) { - /* Load and replicate to all elements */ - TCGv_i64 tcg_tmp = tcg_temp_new_i64(); - - tcg_gen_qemu_ld_i64(tcg_tmp, clean_addr, get_mem_index(s), mop); - tcg_gen_gvec_dup_i64(scale, vec_full_reg_offset(s, rt), - (is_q + 1) * 8, vec_full_reg_size(s), - tcg_tmp); - } else { - /* Load/store one element per register */ - if (is_load) { - do_vec_ld(s, rt, index, clean_addr, mop); - } else { - do_vec_st(s, rt, index, clean_addr, mop); - } - } + tcg_ebytes = tcg_constant_i64(1 << a->scale); + for (xs = 0, rt = a->rt; xs < a->selem; xs++, rt = (rt + 1) % 32) { + do_vec_st(s, rt, a->index, clean_addr, mop); tcg_gen_add_i64(clean_addr, clean_addr, tcg_ebytes); - rt = (rt + 1) % 32; } - if (is_postidx) { - if (rm == 31) { + if (a->p) { + if (a->rm == 31) { tcg_gen_addi_i64(tcg_rn, tcg_rn, total); } else { - tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, rm)); + tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, a->rm)); } } + return true; +} + +static bool trans_LD_single(DisasContext *s, arg_ldst_single *a) +{ + int xs, total, rt; + TCGv_i64 clean_addr, tcg_rn, tcg_ebytes; + MemOp mop; + + if (!a->p && a->rm != 0) { + return false; + } + if (!fp_access_check(s)) { + return true; + } + + if (a->rn == 31) { + gen_check_sp_alignment(s); + } + + total = a->selem << a->scale; + tcg_rn = cpu_reg_sp(s, a->rn); + + mop = finalize_memop_asimd(s, a->scale); + clean_addr = gen_mte_checkN(s, tcg_rn, false, a->p || a->rn != 31, + total, mop); + + tcg_ebytes = tcg_constant_i64(1 << a->scale); + for (xs = 0, rt = a->rt; xs < a->selem; xs++, rt = (rt + 1) % 32) { + do_vec_ld(s, rt, a->index, clean_addr, mop); + tcg_gen_add_i64(clean_addr, clean_addr, tcg_ebytes); + } + + if (a->p) { + if (a->rm == 31) { + tcg_gen_addi_i64(tcg_rn, tcg_rn, total); + } else { + tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, a->rm)); + } + } + return true; +} + +static bool trans_LD_single_repl(DisasContext *s, arg_LD_single_repl *a) +{ + int xs, total, rt; + TCGv_i64 clean_addr, tcg_rn, tcg_ebytes; + MemOp mop; + + if (!a->p && a->rm != 0) { + return false; + } + if (!fp_access_check(s)) { + return true; + } + + if (a->rn == 31) { + gen_check_sp_alignment(s); + } + + total = a->selem << a->scale; + tcg_rn = cpu_reg_sp(s, a->rn); + + mop = finalize_memop_asimd(s, a->scale); + clean_addr = gen_mte_checkN(s, tcg_rn, false, a->p || a->rn != 31, + total, mop); + + tcg_ebytes = tcg_constant_i64(1 << a->scale); + for (xs = 0, rt = a->rt; xs < a->selem; xs++, rt = (rt + 1) % 32) { + /* Load and replicate to all elements */ + TCGv_i64 tcg_tmp = tcg_temp_new_i64(); + + tcg_gen_qemu_ld_i64(tcg_tmp, clean_addr, get_mem_index(s), mop); + tcg_gen_gvec_dup_i64(a->scale, vec_full_reg_offset(s, rt), + (a->q + 1) * 8, vec_full_reg_size(s), tcg_tmp); + tcg_gen_add_i64(clean_addr, clean_addr, tcg_ebytes); + } + + if (a->p) { + if (a->rm == 31) { + tcg_gen_addi_i64(tcg_rn, tcg_rn, total); + } else { + tcg_gen_add_i64(tcg_rn, tcg_rn, cpu_reg(s, a->rm)); + } + } + return true; } /* @@ -XXX,XX +XXX,XX @@ static void disas_ldst_tag(DisasContext *s, uint32_t insn) static void disas_ldst(DisasContext *s, uint32_t insn) { switch (extract32(insn, 24, 6)) { - case 0x0d: /* AdvSIMD load/store single structure */ - disas_ldst_single_struct(s, insn); - break; case 0x19: if (extract32(insn, 21, 1) != 0) { disas_ldst_tag(s, insn); -- 2.34.1 Convert the instructions in the load/store memory tags instruction group to decodetree. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230602155223.2040685-21-peter.maydell@linaro.org --- target/arm/tcg/a64.decode | 25 +++ target/arm/tcg/translate-a64.c | 360 ++++++++++++++++----------------- 2 files changed, 199 insertions(+), 186 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ LD_single 0 . 001101 . 1 . ..... 10 . 001 ..... ..... @ldst_single_d # Replicating load case LD_single_repl 0 q:1 001101 p:1 1 . rm:5 11 . 0 scale:2 rn:5 rt:5 selem=%ldst_single_selem + +%tag_offset 12:s9 !function=scale_by_log2_tag_granule +&ldst_tag rn rt imm p w +@ldst_tag ........ .. . ......... .. rn:5 rt:5 &ldst_tag imm=%tag_offset +@ldst_tag_mult ........ .. . 000000000 .. rn:5 rt:5 &ldst_tag imm=0 + +STZGM 11011001 00 1 ......... 00 ..... ..... @ldst_tag_mult p=0 w=0 +STG 11011001 00 1 ......... 01 ..... ..... @ldst_tag p=1 w=1 +STG 11011001 00 1 ......... 10 ..... ..... @ldst_tag p=0 w=0 +STG 11011001 00 1 ......... 11 ..... ..... @ldst_tag p=0 w=1 + +LDG 11011001 01 1 ......... 00 ..... ..... @ldst_tag p=0 w=0 +STZG 11011001 01 1 ......... 01 ..... ..... @ldst_tag p=1 w=1 +STZG 11011001 01 1 ......... 10 ..... ..... @ldst_tag p=0 w=0 +STZG 11011001 01 1 ......... 11 ..... ..... @ldst_tag p=0 w=1 + +STGM 11011001 10 1 ......... 00 ..... ..... @ldst_tag_mult p=0 w=0 +ST2G 11011001 10 1 ......... 01 ..... ..... @ldst_tag p=1 w=1 +ST2G 11011001 10 1 ......... 10 ..... ..... @ldst_tag p=0 w=0 +ST2G 11011001 10 1 ......... 11 ..... ..... @ldst_tag p=0 w=1 + +LDGM 11011001 11 1 ......... 00 ..... ..... @ldst_tag_mult p=0 w=0 +STZ2G 11011001 11 1 ......... 01 ..... ..... @ldst_tag p=1 w=1 +STZ2G 11011001 11 1 ......... 10 ..... ..... @ldst_tag p=0 w=0 +STZ2G 11011001 11 1 ......... 11 ..... ..... @ldst_tag p=0 w=1 diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static int uimm_scaled(DisasContext *s, int x) return imm << scale; } +/* For load/store memory tags: scale offset by LOG2_TAG_GRANULE */ +static int scale_by_log2_tag_granule(DisasContext *s, int x) +{ + return x << LOG2_TAG_GRANULE; +} + /* * Include the generated decoders. */ @@ -XXX,XX +XXX,XX @@ static bool trans_LD_single_repl(DisasContext *s, arg_LD_single_repl *a) return true; } -/* - * Load/Store memory tags - * - * 31 30 29 24 22 21 12 10 5 0 - * +-----+-------------+-----+---+------+-----+------+------+ - * | 1 1 | 0 1 1 0 0 1 | op1 | 1 | imm9 | op2 | Rn | Rt | - * +-----+-------------+-----+---+------+-----+------+------+ - */ -static void disas_ldst_tag(DisasContext *s, uint32_t insn) +static bool trans_STZGM(DisasContext *s, arg_ldst_tag *a) { - int rt = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - uint64_t offset = sextract64(insn, 12, 9) << LOG2_TAG_GRANULE; - int op2 = extract32(insn, 10, 2); - int op1 = extract32(insn, 22, 2); - bool is_load = false, is_pair = false, is_zero = false, is_mult = false; - int index = 0; TCGv_i64 addr, clean_addr, tcg_rt; + int size = 4 << s->dcz_blocksize; - /* We checked insn bits [29:24,21] in the caller. */ - if (extract32(insn, 30, 2) != 3) { - goto do_unallocated; + if (!dc_isar_feature(aa64_mte, s)) { + return false; + } + if (s->current_el == 0) { + return false; } - /* - * @index is a tri-state variable which has 3 states: - * < 0 : post-index, writeback - * = 0 : signed offset - * > 0 : pre-index, writeback - */ - switch (op1) { - case 0: - if (op2 != 0) { - /* STG */ - index = op2 - 2; - } else { - /* STZGM */ - if (s->current_el == 0 || offset != 0) { - goto do_unallocated; - } - is_mult = is_zero = true; - } - break; - case 1: - if (op2 != 0) { - /* STZG */ - is_zero = true; - index = op2 - 2; - } else { - /* LDG */ - is_load = true; - } - break; - case 2: - if (op2 != 0) { - /* ST2G */ - is_pair = true; - index = op2 - 2; - } else { - /* STGM */ - if (s->current_el == 0 || offset != 0) { - goto do_unallocated; - } - is_mult = true; - } - break; - case 3: - if (op2 != 0) { - /* STZ2G */ - is_pair = is_zero = true; - index = op2 - 2; - } else { - /* LDGM */ - if (s->current_el == 0 || offset != 0) { - goto do_unallocated; - } - is_mult = is_load = true; - } - break; - - default: - do_unallocated: - unallocated_encoding(s); - return; - } - - if (is_mult - ? !dc_isar_feature(aa64_mte, s) - : !dc_isar_feature(aa64_mte_insn_reg, s)) { - goto do_unallocated; - } - - if (rn == 31) { + if (a->rn == 31) { gen_check_sp_alignment(s); } - addr = read_cpu_reg_sp(s, rn, true); - if (index >= 0) { + addr = read_cpu_reg_sp(s, a->rn, true); + tcg_gen_addi_i64(addr, addr, a->imm); + tcg_rt = cpu_reg(s, a->rt); + + if (s->ata) { + gen_helper_stzgm_tags(cpu_env, addr, tcg_rt); + } + /* + * The non-tags portion of STZGM is mostly like DC_ZVA, + * except the alignment happens before the access. + */ + clean_addr = clean_data_tbi(s, addr); + tcg_gen_andi_i64(clean_addr, clean_addr, -size); + gen_helper_dc_zva(cpu_env, clean_addr); + return true; +} + +static bool trans_STGM(DisasContext *s, arg_ldst_tag *a) +{ + TCGv_i64 addr, clean_addr, tcg_rt; + + if (!dc_isar_feature(aa64_mte, s)) { + return false; + } + if (s->current_el == 0) { + return false; + } + + if (a->rn == 31) { + gen_check_sp_alignment(s); + } + + addr = read_cpu_reg_sp(s, a->rn, true); + tcg_gen_addi_i64(addr, addr, a->imm); + tcg_rt = cpu_reg(s, a->rt); + + if (s->ata) { + gen_helper_stgm(cpu_env, addr, tcg_rt); + } else { + MMUAccessType acc = MMU_DATA_STORE; + int size = 4 << GMID_EL1_BS; + + clean_addr = clean_data_tbi(s, addr); + tcg_gen_andi_i64(clean_addr, clean_addr, -size); + gen_probe_access(s, clean_addr, acc, size); + } + return true; +} + +static bool trans_LDGM(DisasContext *s, arg_ldst_tag *a) +{ + TCGv_i64 addr, clean_addr, tcg_rt; + + if (!dc_isar_feature(aa64_mte, s)) { + return false; + } + if (s->current_el == 0) { + return false; + } + + if (a->rn == 31) { + gen_check_sp_alignment(s); + } + + addr = read_cpu_reg_sp(s, a->rn, true); + tcg_gen_addi_i64(addr, addr, a->imm); + tcg_rt = cpu_reg(s, a->rt); + + if (s->ata) { + gen_helper_ldgm(tcg_rt, cpu_env, addr); + } else { + MMUAccessType acc = MMU_DATA_LOAD; + int size = 4 << GMID_EL1_BS; + + clean_addr = clean_data_tbi(s, addr); + tcg_gen_andi_i64(clean_addr, clean_addr, -size); + gen_probe_access(s, clean_addr, acc, size); + /* The result tags are zeros. */ + tcg_gen_movi_i64(tcg_rt, 0); + } + return true; +} + +static bool trans_LDG(DisasContext *s, arg_ldst_tag *a) +{ + TCGv_i64 addr, clean_addr, tcg_rt; + + if (!dc_isar_feature(aa64_mte_insn_reg, s)) { + return false; + } + + if (a->rn == 31) { + gen_check_sp_alignment(s); + } + + addr = read_cpu_reg_sp(s, a->rn, true); + if (!a->p) { /* pre-index or signed offset */ - tcg_gen_addi_i64(addr, addr, offset); + tcg_gen_addi_i64(addr, addr, a->imm); } - if (is_mult) { - tcg_rt = cpu_reg(s, rt); + tcg_gen_andi_i64(addr, addr, -TAG_GRANULE); + tcg_rt = cpu_reg(s, a->rt); + if (s->ata) { + gen_helper_ldg(tcg_rt, cpu_env, addr, tcg_rt); + } else { + /* + * Tag access disabled: we must check for aborts on the load + * load from [rn+offset], and then insert a 0 tag into rt. + */ + clean_addr = clean_data_tbi(s, addr); + gen_probe_access(s, clean_addr, MMU_DATA_LOAD, MO_8); + gen_address_with_allocation_tag0(tcg_rt, tcg_rt); + } - if (is_zero) { - int size = 4 << s->dcz_blocksize; - - if (s->ata) { - gen_helper_stzgm_tags(cpu_env, addr, tcg_rt); - } - /* - * The non-tags portion of STZGM is mostly like DC_ZVA, - * except the alignment happens before the access. - */ - clean_addr = clean_data_tbi(s, addr); - tcg_gen_andi_i64(clean_addr, clean_addr, -size); - gen_helper_dc_zva(cpu_env, clean_addr); - } else if (s->ata) { - if (is_load) { - gen_helper_ldgm(tcg_rt, cpu_env, addr); - } else { - gen_helper_stgm(cpu_env, addr, tcg_rt); - } - } else { - MMUAccessType acc = is_load ? MMU_DATA_LOAD : MMU_DATA_STORE; - int size = 4 << GMID_EL1_BS; - - clean_addr = clean_data_tbi(s, addr); - tcg_gen_andi_i64(clean_addr, clean_addr, -size); - gen_probe_access(s, clean_addr, acc, size); - - if (is_load) { - /* The result tags are zeros. */ - tcg_gen_movi_i64(tcg_rt, 0); - } + if (a->w) { + /* pre-index or post-index */ + if (a->p) { + /* post-index */ + tcg_gen_addi_i64(addr, addr, a->imm); } - return; + tcg_gen_mov_i64(cpu_reg_sp(s, a->rn), addr); + } + return true; +} + +static bool do_STG(DisasContext *s, arg_ldst_tag *a, bool is_zero, bool is_pair) +{ + TCGv_i64 addr, tcg_rt; + + if (a->rn == 31) { + gen_check_sp_alignment(s); } - if (is_load) { - tcg_gen_andi_i64(addr, addr, -TAG_GRANULE); - tcg_rt = cpu_reg(s, rt); - if (s->ata) { - gen_helper_ldg(tcg_rt, cpu_env, addr, tcg_rt); + addr = read_cpu_reg_sp(s, a->rn, true); + if (!a->p) { + /* pre-index or signed offset */ + tcg_gen_addi_i64(addr, addr, a->imm); + } + tcg_rt = cpu_reg_sp(s, a->rt); + if (!s->ata) { + /* + * For STG and ST2G, we need to check alignment and probe memory. + * TODO: For STZG and STZ2G, we could rely on the stores below, + * at least for system mode; user-only won't enforce alignment. + */ + if (is_pair) { + gen_helper_st2g_stub(cpu_env, addr); } else { - /* - * Tag access disabled: we must check for aborts on the load - * load from [rn+offset], and then insert a 0 tag into rt. - */ - clean_addr = clean_data_tbi(s, addr); - gen_probe_access(s, clean_addr, MMU_DATA_LOAD, MO_8); - gen_address_with_allocation_tag0(tcg_rt, tcg_rt); + gen_helper_stg_stub(cpu_env, addr); + } + } else if (tb_cflags(s->base.tb) & CF_PARALLEL) { + if (is_pair) { + gen_helper_st2g_parallel(cpu_env, addr, tcg_rt); + } else { + gen_helper_stg_parallel(cpu_env, addr, tcg_rt); } } else { - tcg_rt = cpu_reg_sp(s, rt); - if (!s->ata) { - /* - * For STG and ST2G, we need to check alignment and probe memory. - * TODO: For STZG and STZ2G, we could rely on the stores below, - * at least for system mode; user-only won't enforce alignment. - */ - if (is_pair) { - gen_helper_st2g_stub(cpu_env, addr); - } else { - gen_helper_stg_stub(cpu_env, addr); - } - } else if (tb_cflags(s->base.tb) & CF_PARALLEL) { - if (is_pair) { - gen_helper_st2g_parallel(cpu_env, addr, tcg_rt); - } else { - gen_helper_stg_parallel(cpu_env, addr, tcg_rt); - } + if (is_pair) { + gen_helper_st2g(cpu_env, addr, tcg_rt); } else { - if (is_pair) { - gen_helper_st2g(cpu_env, addr, tcg_rt); - } else { - gen_helper_stg(cpu_env, addr, tcg_rt); - } + gen_helper_stg(cpu_env, addr, tcg_rt); } } @@ -XXX,XX +XXX,XX @@ static void disas_ldst_tag(DisasContext *s, uint32_t insn) } } - if (index != 0) { + if (a->w) { /* pre-index or post-index */ - if (index < 0) { + if (a->p) { /* post-index */ - tcg_gen_addi_i64(addr, addr, offset); + tcg_gen_addi_i64(addr, addr, a->imm); } - tcg_gen_mov_i64(cpu_reg_sp(s, rn), addr); + tcg_gen_mov_i64(cpu_reg_sp(s, a->rn), addr); } + return true; } -/* Loads and stores */ -static void disas_ldst(DisasContext *s, uint32_t insn) -{ - switch (extract32(insn, 24, 6)) { - case 0x19: - if (extract32(insn, 21, 1) != 0) { - disas_ldst_tag(s, insn); - } else { - unallocated_encoding(s); - } - break; - default: - unallocated_encoding(s); - break; - } -} +TRANS_FEAT(STG, aa64_mte_insn_reg, do_STG, a, false, false) +TRANS_FEAT(STZG, aa64_mte_insn_reg, do_STG, a, true, false) +TRANS_FEAT(ST2G, aa64_mte_insn_reg, do_STG, a, false, true) +TRANS_FEAT(STZ2G, aa64_mte_insn_reg, do_STG, a, true, true) typedef void ArithTwoOp(TCGv_i64, TCGv_i64, TCGv_i64); @@ -XXX,XX +XXX,XX @@ static bool btype_destination_ok(uint32_t insn, bool bt, int btype) static void disas_a64_legacy(DisasContext *s, uint32_t insn) { switch (extract32(insn, 25, 4)) { - case 0x4: - case 0x6: - case 0xc: - case 0xe: /* Loads and stores */ - disas_ldst(s, insn); - break; case 0x5: case 0xd: /* Data processing - register */ disas_data_proc_reg(s, insn); -- 2.34.1 In commit 2c5fa0778c3b430 we fixed an endianness bug in the Allwinner A10 PIC model; however in the process we introduced a regression. This is because the old code was robust against the incoming 'level' argument being something other than 0 or 1, whereas the new code was not. In particular, the allwinner-sdhost code treats its IRQ line as 0-vs-non-0 rather than 0-vs-1, so when the SD controller set its IRQ line for any reason other than transmit the interrupt controller would ignore it. The observed effect was a guest timeout when rebooting the guest kernel. Handle level values other than 0 or 1, to restore the old behaviour. Fixes: 2c5fa0778c3b430 ("hw/intc/allwinner-a10-pic: Don't use set_bit()/clear_bit()") Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20230606104609.3692557-2-peter.maydell@linaro.org --- hw/intc/allwinner-a10-pic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/intc/allwinner-a10-pic.c b/hw/intc/allwinner-a10-pic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/allwinner-a10-pic.c +++ b/hw/intc/allwinner-a10-pic.c @@ -XXX,XX +XXX,XX @@ static void aw_a10_pic_set_irq(void *opaque, int irq, int level) AwA10PICState *s = opaque; uint32_t *pending_reg = &s->irq_pending[irq / 32]; - *pending_reg = deposit32(*pending_reg, irq % 32, 1, level); + *pending_reg = deposit32(*pending_reg, irq % 32, 1, !!level); aw_a10_pic_update(s); } -- 2.34.1 QEMU allows qemu_irq lines to transfer arbitrary integers. However the convention is that for a simple IRQ line the values transferred are always 0 and 1. The A10 SD controller device instead assumes a 0-vs-non-0 convention, which happens to work with the interrupt controller it is wired up to. Coerce the value to boolean to follow our usual convention. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20230606104609.3692557-3-peter.maydell@linaro.org --- hw/sd/allwinner-sdhost.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/sd/allwinner-sdhost.c b/hw/sd/allwinner-sdhost.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/allwinner-sdhost.c +++ b/hw/sd/allwinner-sdhost.c @@ -XXX,XX +XXX,XX @@ static void allwinner_sdhost_update_irq(AwSdHostState *s) } trace_allwinner_sdhost_update_irq(irq); - qemu_set_irq(s->irq, irq); + qemu_set_irq(s->irq, !!irq); } static void allwinner_sdhost_update_transfer_cnt(AwSdHostState *s, -- 2.34.1 The nrf51_timer has a free-running counter which we implement using the pattern of using two fields (update_counter_ns, counter) to track the last point at which we calculated the counter value, and the counter value at that time. Then we can find the current counter value by converting the difference in wall-clock time between then and now to a tick count that we need to add to the counter value. Unfortunately the nrf51_timer's implementation of this has a bug which means it loses time every time update_counter() is called. After updating s->counter it always sets s->update_counter_ns to 'now', even though the actual point when s->counter hit the new value will be some point in the past (half a tick, say). In the worst case (guest code in a tight loop reading the counter, icount mode) the counter is continually queried less than a tick after it was last read, so s->counter never advances but s->update_counter_ns does, and the guest never makes forward progress. The fix for this is to only advance update_counter_ns to the timestamp of the last tick, not all the way to 'now'. (This is the pattern used in hw/misc/mps2-fpgaio.c's counter.) Cc: qemu-stable@nongnu.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Message-id: 20230606134917.3782215-1-peter.maydell@linaro.org --- hw/timer/nrf51_timer.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/hw/timer/nrf51_timer.c b/hw/timer/nrf51_timer.c index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/nrf51_timer.c +++ b/hw/timer/nrf51_timer.c @@ -XXX,XX +XXX,XX @@ static uint32_t update_counter(NRF51TimerState *s, int64_t now) uint32_t ticks = ns_to_ticks(s, now - s->update_counter_ns); s->counter = (s->counter + ticks) % BIT(bitwidths[s->bitmode]); - s->update_counter_ns = now; + /* + * Only advance the sync time to the timestamp of the last tick, + * not all the way to 'now', so we don't lose time if we do + * multiple resyncs in a single tick. + */ + s->update_counter_ns += ticks_to_ns(s, ticks); return ticks; } -- 2.34.1 From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Reviewed-by: Thomas Huth <thuth@redhat.com> Message-id: 20230607092112.655098-1-marcin.juszkiewicz@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/Kconfig | 1 + 1 file changed, 1 insertion(+) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config SBSA_REF select PL061 # GPIO select USB_EHCI_SYSBUS select WDT_SBSA + select BOCHS_DISPLAY config SABRELITE bool -- 2.34.1 From: Martin Kaiser <martin@kaiser.cx> The Linux kernel added a flood check for RX data recently in commit 496a4471b7c3 ("serial: imx: work-around for hardware RX flood"). This check uses the wake bit in the UART status register 2. The wake bit indicates that the receiver detected a start bit on the RX line. If the kernel sees a number of RX interrupts without the wake bit being set, it treats this as spurious data and resets the UART port. imx_serial does never set the wake bit and triggers the kernel's flood check. This patch adds support for the wake bit. wake is set when we receive a new character (it's not set for break events). It seems that wake is cleared by the kernel driver, the hardware does not have to clear it automatically after data was read. The wake bit can be configured as an interrupt source. Support this mechanism as well. Co-developed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Martin Kaiser <martin@kaiser.cx> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/char/imx_serial.h | 1 + hw/char/imx_serial.c | 5 ++++- 2 files changed, 5 insertions(+), 1 deletion(-) diff --git a/include/hw/char/imx_serial.h b/include/hw/char/imx_serial.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/char/imx_serial.h +++ b/include/hw/char/imx_serial.h @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(IMXSerialState, IMX_SERIAL) #define UCR4_DREN BIT(0) /* Receive Data Ready interrupt enable */ #define UCR4_TCEN BIT(3) /* TX complete interrupt enable */ +#define UCR4_WKEN BIT(7) /* WAKE interrupt enable */ #define UTS1_TXEMPTY (1<<6) #define UTS1_RXEMPTY (1<<5) diff --git a/hw/char/imx_serial.c b/hw/char/imx_serial.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/imx_serial.c +++ b/hw/char/imx_serial.c @@ -XXX,XX +XXX,XX @@ static void imx_update(IMXSerialState *s) * TCEN and TXDC are both bit 3 * RDR and DREN are both bit 0 */ - mask |= s->ucr4 & (UCR4_TCEN | UCR4_DREN); + mask |= s->ucr4 & (UCR4_WKEN | UCR4_TCEN | UCR4_DREN); usr2 = s->usr2 & mask; @@ -XXX,XX +XXX,XX @@ static void imx_put_data(void *opaque, uint32_t value) static void imx_receive(void *opaque, const uint8_t *buf, int size) { + IMXSerialState *s = (IMXSerialState *)opaque; + + s->usr2 |= USR2_WAKE; imx_put_data(opaque, *buf); } -- 2.34.1 From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> We plan to add more hardware information into DeviceTree to limit amount of hardcoded values in firmware. Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Message-id: 20230531171834.236569-1-marcin.juszkiewicz@linaro.org [PMM: fix format nits, add text about platform version fields from a comment in the C source file] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/sbsa.rst | 38 +++++++++++++++++++++++++++++++------- 1 file changed, 31 insertions(+), 7 deletions(-) diff --git a/docs/system/arm/sbsa.rst b/docs/system/arm/sbsa.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/sbsa.rst +++ b/docs/system/arm/sbsa.rst @@ -XXX,XX +XXX,XX @@ any real hardware the ``sbsa-ref`` board intends to look like real hardware. The `Server Base System Architecture <https://developer.arm.com/documentation/den0029/latest>`_ defines a minimum base line of hardware support and importantly how the firmware -reports that to any operating system. It is a static system that -reports a very minimal DT to the firmware for non-discoverable -information about components affected by the qemu command line (i.e. -cpus and memory). As a result it must have a firmware specifically -built to expect a certain hardware layout (as you would in a real -machine). +reports that to any operating system. It is intended to be a machine for developing firmware and testing standards compliance with operating systems. @@ -XXX,XX +XXX,XX @@ standards compliance with operating systems. Supported devices """"""""""""""""" -The sbsa-ref board supports: +The ``sbsa-ref`` board supports: - A configurable number of AArch64 CPUs - GIC version 3 @@ -XXX,XX +XXX,XX @@ The sbsa-ref board supports: - Bochs display adapter on PCIe bus - A generic SBSA watchdog device + +Board to firmware interface +""""""""""""""""""""""""""" + +``sbsa-ref`` is a static system that reports a very minimal devicetree to the +firmware for non-discoverable information about system components. This +includes both internal hardware and parts affected by the qemu command line +(i.e. CPUs and memory). As a result it must have a firmware specifically built +to expect a certain hardware layout (as you would in a real machine). + +DeviceTree information +'''''''''''''''''''''' + +The devicetree provided by the board model to the firmware is not intended +to be a complete compliant DT. It currently reports: + + - CPUs + - memory + - platform version + - GIC addresses + +The platform version is only for informing platform firmware about +what kind of ``sbsa-ref`` board it is running on. It is neither +a QEMU versioned machine type nor a reflection of the level of the +SBSA/SystemReady SR support provided. + +The ``machine-version-major`` value is updated when changes breaking +fw compatibility are introduced. The ``machine-version-minor`` value +is updated when features are added that don't break fw compatibility. -- 2.34.1 From: Sergey Kambalin <sergey.kambalin@auriga.com> Signed-off-by: Sergey Kambalin <sergey.kambalin@auriga.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Acked-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230612223456.33824-2-philmd@linaro.org Message-Id: <20230531155258.8361-1-sergey.kambalin@auriga.com> [PMD: Split from bigger patch: 1/4] Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/raspberrypi-fw-defs.h | 163 ++++++++++++++++++++++++++ 1 file changed, 163 insertions(+) create mode 100644 include/hw/misc/raspberrypi-fw-defs.h diff --git a/include/hw/misc/raspberrypi-fw-defs.h b/include/hw/misc/raspberrypi-fw-defs.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/raspberrypi-fw-defs.h @@ -XXX,XX +XXX,XX @@ +/* + * Raspberry Pi firmware definitions + * + * Copyright (C) 2022 Auriga LLC, based on Linux kernel + * `include/soc/bcm2835/raspberrypi-firmware.h` (Copyright © 2015 Broadcom) + * + * SPDX-License-Identifier: GPL-2.0-or-later + */ + +#ifndef INCLUDE_HW_MISC_RASPBERRYPI_FW_DEFS_H_ +#define INCLUDE_HW_MISC_RASPBERRYPI_FW_DEFS_H_ + +#include "qemu/osdep.h" + +enum rpi_firmware_property_tag { + RPI_FWREQ_PROPERTY_END = 0, + RPI_FWREQ_GET_FIRMWARE_REVISION = 0x00000001, + RPI_FWREQ_GET_FIRMWARE_VARIANT = 0x00000002, + RPI_FWREQ_GET_FIRMWARE_HASH = 0x00000003, + + RPI_FWREQ_SET_CURSOR_INFO = 0x00008010, + RPI_FWREQ_SET_CURSOR_STATE = 0x00008011, + + RPI_FWREQ_GET_BOARD_MODEL = 0x00010001, + RPI_FWREQ_GET_BOARD_REVISION = 0x00010002, + RPI_FWREQ_GET_BOARD_MAC_ADDRESS = 0x00010003, + RPI_FWREQ_GET_BOARD_SERIAL = 0x00010004, + RPI_FWREQ_GET_ARM_MEMORY = 0x00010005, + RPI_FWREQ_GET_VC_MEMORY = 0x00010006, + RPI_FWREQ_GET_CLOCKS = 0x00010007, + RPI_FWREQ_GET_POWER_STATE = 0x00020001, + RPI_FWREQ_GET_TIMING = 0x00020002, + RPI_FWREQ_SET_POWER_STATE = 0x00028001, + RPI_FWREQ_GET_CLOCK_STATE = 0x00030001, + RPI_FWREQ_GET_CLOCK_RATE = 0x00030002, + RPI_FWREQ_GET_VOLTAGE = 0x00030003, + RPI_FWREQ_GET_MAX_CLOCK_RATE = 0x00030004, + RPI_FWREQ_GET_MAX_VOLTAGE = 0x00030005, + RPI_FWREQ_GET_TEMPERATURE = 0x00030006, + RPI_FWREQ_GET_MIN_CLOCK_RATE = 0x00030007, + RPI_FWREQ_GET_MIN_VOLTAGE = 0x00030008, + RPI_FWREQ_GET_TURBO = 0x00030009, + RPI_FWREQ_GET_MAX_TEMPERATURE = 0x0003000a, + RPI_FWREQ_GET_STC = 0x0003000b, + RPI_FWREQ_ALLOCATE_MEMORY = 0x0003000c, + RPI_FWREQ_LOCK_MEMORY = 0x0003000d, + RPI_FWREQ_UNLOCK_MEMORY = 0x0003000e, + RPI_FWREQ_RELEASE_MEMORY = 0x0003000f, + RPI_FWREQ_EXECUTE_CODE = 0x00030010, + RPI_FWREQ_EXECUTE_QPU = 0x00030011, + RPI_FWREQ_SET_ENABLE_QPU = 0x00030012, + RPI_FWREQ_GET_DISPMANX_RESOURCE_MEM_HANDLE = 0x00030014, + RPI_FWREQ_GET_EDID_BLOCK = 0x00030020, + RPI_FWREQ_GET_CUSTOMER_OTP = 0x00030021, + RPI_FWREQ_GET_EDID_BLOCK_DISPLAY = 0x00030023, + RPI_FWREQ_GET_DOMAIN_STATE = 0x00030030, + RPI_FWREQ_GET_THROTTLED = 0x00030046, + RPI_FWREQ_GET_CLOCK_MEASURED = 0x00030047, + RPI_FWREQ_NOTIFY_REBOOT = 0x00030048, + RPI_FWREQ_SET_CLOCK_STATE = 0x00038001, + RPI_FWREQ_SET_CLOCK_RATE = 0x00038002, + RPI_FWREQ_SET_VOLTAGE = 0x00038003, + RPI_FWREQ_SET_MAX_CLOCK_RATE = 0x00038004, + RPI_FWREQ_SET_MIN_CLOCK_RATE = 0x00038007, + RPI_FWREQ_SET_TURBO = 0x00038009, + RPI_FWREQ_SET_CUSTOMER_OTP = 0x00038021, + RPI_FWREQ_SET_DOMAIN_STATE = 0x00038030, + RPI_FWREQ_GET_GPIO_STATE = 0x00030041, + RPI_FWREQ_SET_GPIO_STATE = 0x00038041, + RPI_FWREQ_SET_SDHOST_CLOCK = 0x00038042, + RPI_FWREQ_GET_GPIO_CONFIG = 0x00030043, + RPI_FWREQ_SET_GPIO_CONFIG = 0x00038043, + RPI_FWREQ_GET_PERIPH_REG = 0x00030045, + RPI_FWREQ_SET_PERIPH_REG = 0x00038045, + RPI_FWREQ_GET_POE_HAT_VAL = 0x00030049, + RPI_FWREQ_SET_POE_HAT_VAL = 0x00038049, + RPI_FWREQ_SET_POE_HAT_VAL_OLD = 0x00030050, + RPI_FWREQ_NOTIFY_XHCI_RESET = 0x00030058, + RPI_FWREQ_GET_REBOOT_FLAGS = 0x00030064, + RPI_FWREQ_SET_REBOOT_FLAGS = 0x00038064, + RPI_FWREQ_NOTIFY_DISPLAY_DONE = 0x00030066, + + /* Dispmanx TAGS */ + RPI_FWREQ_FRAMEBUFFER_ALLOCATE = 0x00040001, + RPI_FWREQ_FRAMEBUFFER_BLANK = 0x00040002, + RPI_FWREQ_FRAMEBUFFER_GET_PHYSICAL_WIDTH_HEIGHT = 0x00040003, + RPI_FWREQ_FRAMEBUFFER_GET_VIRTUAL_WIDTH_HEIGHT = 0x00040004, + RPI_FWREQ_FRAMEBUFFER_GET_DEPTH = 0x00040005, + RPI_FWREQ_FRAMEBUFFER_GET_PIXEL_ORDER = 0x00040006, + RPI_FWREQ_FRAMEBUFFER_GET_ALPHA_MODE = 0x00040007, + RPI_FWREQ_FRAMEBUFFER_GET_PITCH = 0x00040008, + RPI_FWREQ_FRAMEBUFFER_GET_VIRTUAL_OFFSET = 0x00040009, + RPI_FWREQ_FRAMEBUFFER_GET_OVERSCAN = 0x0004000a, + RPI_FWREQ_FRAMEBUFFER_GET_PALETTE = 0x0004000b, + RPI_FWREQ_FRAMEBUFFER_GET_LAYER = 0x0004000c, + RPI_FWREQ_FRAMEBUFFER_GET_TRANSFORM = 0x0004000d, + RPI_FWREQ_FRAMEBUFFER_GET_VSYNC = 0x0004000e, + RPI_FWREQ_FRAMEBUFFER_GET_TOUCHBUF = 0x0004000f, + RPI_FWREQ_FRAMEBUFFER_GET_GPIOVIRTBUF = 0x00040010, + RPI_FWREQ_FRAMEBUFFER_RELEASE = 0x00048001, + RPI_FWREQ_FRAMEBUFFER_GET_DISPLAY_ID = 0x00040016, + RPI_FWREQ_FRAMEBUFFER_SET_DISPLAY_NUM = 0x00048013, + RPI_FWREQ_FRAMEBUFFER_GET_NUM_DISPLAYS = 0x00040013, + RPI_FWREQ_FRAMEBUFFER_GET_DISPLAY_SETTINGS = 0x00040014, + RPI_FWREQ_FRAMEBUFFER_TEST_PHYSICAL_WIDTH_HEIGHT = 0x00044003, + RPI_FWREQ_FRAMEBUFFER_TEST_VIRTUAL_WIDTH_HEIGHT = 0x00044004, + RPI_FWREQ_FRAMEBUFFER_TEST_DEPTH = 0x00044005, + RPI_FWREQ_FRAMEBUFFER_TEST_PIXEL_ORDER = 0x00044006, + RPI_FWREQ_FRAMEBUFFER_TEST_ALPHA_MODE = 0x00044007, + RPI_FWREQ_FRAMEBUFFER_TEST_VIRTUAL_OFFSET = 0x00044009, + RPI_FWREQ_FRAMEBUFFER_TEST_OVERSCAN = 0x0004400a, + RPI_FWREQ_FRAMEBUFFER_TEST_PALETTE = 0x0004400b, + RPI_FWREQ_FRAMEBUFFER_TEST_LAYER = 0x0004400c, + RPI_FWREQ_FRAMEBUFFER_TEST_TRANSFORM = 0x0004400d, + RPI_FWREQ_FRAMEBUFFER_TEST_VSYNC = 0x0004400e, + RPI_FWREQ_FRAMEBUFFER_SET_PHYSICAL_WIDTH_HEIGHT = 0x00048003, + RPI_FWREQ_FRAMEBUFFER_SET_VIRTUAL_WIDTH_HEIGHT = 0x00048004, + RPI_FWREQ_FRAMEBUFFER_SET_DEPTH = 0x00048005, + RPI_FWREQ_FRAMEBUFFER_SET_PIXEL_ORDER = 0x00048006, + RPI_FWREQ_FRAMEBUFFER_SET_ALPHA_MODE = 0x00048007, + RPI_FWREQ_FRAMEBUFFER_SET_PITCH = 0x00048008, + RPI_FWREQ_FRAMEBUFFER_SET_VIRTUAL_OFFSET = 0x00048009, + RPI_FWREQ_FRAMEBUFFER_SET_OVERSCAN = 0x0004800a, + RPI_FWREQ_FRAMEBUFFER_SET_PALETTE = 0x0004800b, + + RPI_FWREQ_FRAMEBUFFER_SET_TOUCHBUF = 0x0004801f, + RPI_FWREQ_FRAMEBUFFER_SET_GPIOVIRTBUF = 0x00048020, + RPI_FWREQ_FRAMEBUFFER_SET_VSYNC = 0x0004800e, + RPI_FWREQ_FRAMEBUFFER_SET_LAYER = 0x0004800c, + RPI_FWREQ_FRAMEBUFFER_SET_TRANSFORM = 0x0004800d, + RPI_FWREQ_FRAMEBUFFER_SET_BACKLIGHT = 0x0004800f, + + RPI_FWREQ_VCHIQ_INIT = 0x00048010, + + RPI_FWREQ_SET_PLANE = 0x00048015, + RPI_FWREQ_GET_DISPLAY_TIMING = 0x00040017, + RPI_FWREQ_SET_TIMING = 0x00048017, + RPI_FWREQ_GET_DISPLAY_CFG = 0x00040018, + RPI_FWREQ_SET_DISPLAY_POWER = 0x00048019, + RPI_FWREQ_GET_COMMAND_LINE = 0x00050001, + RPI_FWREQ_GET_DMA_CHANNELS = 0x00060001, +}; + +enum rpi_firmware_clk_id { + RPI_FIRMWARE_EMMC_CLK_ID = 1, + RPI_FIRMWARE_UART_CLK_ID, + RPI_FIRMWARE_ARM_CLK_ID, + RPI_FIRMWARE_CORE_CLK_ID, + RPI_FIRMWARE_V3D_CLK_ID, + RPI_FIRMWARE_H264_CLK_ID, + RPI_FIRMWARE_ISP_CLK_ID, + RPI_FIRMWARE_SDRAM_CLK_ID, + RPI_FIRMWARE_PIXEL_CLK_ID, + RPI_FIRMWARE_PWM_CLK_ID, + RPI_FIRMWARE_HEVC_CLK_ID, + RPI_FIRMWARE_EMMC2_CLK_ID, + RPI_FIRMWARE_M2MC_CLK_ID, + RPI_FIRMWARE_PIXEL_BVB_CLK_ID, + RPI_FIRMWARE_VEC_CLK_ID, + RPI_FIRMWARE_NUM_CLK_ID, +}; + +#endif /* INCLUDE_HW_MISC_RASPBERRYPI_FW_DEFS_H_ */ -- 2.34.1 From: Sergey Kambalin <sergey.kambalin@auriga.com> Replace magic property values by a proper definition, removing redundant comments. Signed-off-by: Sergey Kambalin <sergey.kambalin@auriga.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230612223456.33824-3-philmd@linaro.org Message-Id: <20230531155258.8361-1-sergey.kambalin@auriga.com> [PMD: Split from bigger patch: 2/4] Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/bcm2835_property.c | 101 +++++++++++++++++++------------------ 1 file changed, 51 insertions(+), 50 deletions(-) diff --git a/hw/misc/bcm2835_property.c b/hw/misc/bcm2835_property.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/bcm2835_property.c +++ b/hw/misc/bcm2835_property.c @@ -XXX,XX +XXX,XX @@ #include "migration/vmstate.h" #include "hw/irq.h" #include "hw/misc/bcm2835_mbox_defs.h" +#include "hw/misc/raspberrypi-fw-defs.h" #include "sysemu/dma.h" #include "qemu/log.h" #include "qemu/module.h" @@ -XXX,XX +XXX,XX @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value) /* @(value + 8) : Request/response indicator */ resplen = 0; switch (tag) { - case 0x00000000: /* End tag */ + case RPI_FWREQ_PROPERTY_END: break; - case 0x00000001: /* Get firmware revision */ + case RPI_FWREQ_GET_FIRMWARE_REVISION: stl_le_phys(&s->dma_as, value + 12, 346337); resplen = 4; break; - case 0x00010001: /* Get board model */ + case RPI_FWREQ_GET_BOARD_MODEL: qemu_log_mask(LOG_UNIMP, "bcm2835_property: 0x%08x get board model NYI\n", tag); resplen = 4; break; - case 0x00010002: /* Get board revision */ + case RPI_FWREQ_GET_BOARD_REVISION: stl_le_phys(&s->dma_as, value + 12, s->board_rev); resplen = 4; break; - case 0x00010003: /* Get board MAC address */ + case RPI_FWREQ_GET_BOARD_MAC_ADDRESS: resplen = sizeof(s->macaddr.a); dma_memory_write(&s->dma_as, value + 12, s->macaddr.a, resplen, MEMTXATTRS_UNSPECIFIED); break; - case 0x00010004: /* Get board serial */ + case RPI_FWREQ_GET_BOARD_SERIAL: qemu_log_mask(LOG_UNIMP, "bcm2835_property: 0x%08x get board serial NYI\n", tag); resplen = 8; break; - case 0x00010005: /* Get ARM memory */ + case RPI_FWREQ_GET_ARM_MEMORY: /* base */ stl_le_phys(&s->dma_as, value + 12, 0); /* size */ stl_le_phys(&s->dma_as, value + 16, s->fbdev->vcram_base); resplen = 8; break; - case 0x00010006: /* Get VC memory */ + case RPI_FWREQ_GET_VC_MEMORY: /* base */ stl_le_phys(&s->dma_as, value + 12, s->fbdev->vcram_base); /* size */ stl_le_phys(&s->dma_as, value + 16, s->fbdev->vcram_size); resplen = 8; break; - case 0x00028001: /* Set power state */ + case RPI_FWREQ_SET_POWER_STATE: /* Assume that whatever device they asked for exists, * and we'll just claim we set it to the desired state */ @@ -XXX,XX +XXX,XX @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value) /* Clocks */ - case 0x00030001: /* Get clock state */ + case RPI_FWREQ_GET_CLOCK_STATE: stl_le_phys(&s->dma_as, value + 16, 0x1); resplen = 8; break; - case 0x00038001: /* Set clock state */ + case RPI_FWREQ_SET_CLOCK_STATE: qemu_log_mask(LOG_UNIMP, "bcm2835_property: 0x%08x set clock state NYI\n", tag); resplen = 8; break; - case 0x00030002: /* Get clock rate */ - case 0x00030004: /* Get max clock rate */ - case 0x00030007: /* Get min clock rate */ + case RPI_FWREQ_GET_CLOCK_RATE: + case RPI_FWREQ_GET_MAX_CLOCK_RATE: + case RPI_FWREQ_GET_MIN_CLOCK_RATE: switch (ldl_le_phys(&s->dma_as, value + 12)) { - case 1: /* EMMC */ + case RPI_FIRMWARE_EMMC_CLK_ID: stl_le_phys(&s->dma_as, value + 16, 50000000); break; - case 2: /* UART */ + case RPI_FIRMWARE_UART_CLK_ID: stl_le_phys(&s->dma_as, value + 16, 3000000); break; default: @@ -XXX,XX +XXX,XX @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value) resplen = 8; break; - case 0x00038002: /* Set clock rate */ - case 0x00038004: /* Set max clock rate */ - case 0x00038007: /* Set min clock rate */ + case RPI_FWREQ_SET_CLOCK_RATE: + case RPI_FWREQ_SET_MAX_CLOCK_RATE: + case RPI_FWREQ_SET_MIN_CLOCK_RATE: qemu_log_mask(LOG_UNIMP, "bcm2835_property: 0x%08x set clock rate NYI\n", tag); @@ -XXX,XX +XXX,XX @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value) /* Temperature */ - case 0x00030006: /* Get temperature */ + case RPI_FWREQ_GET_TEMPERATURE: stl_le_phys(&s->dma_as, value + 16, 25000); resplen = 8; break; - case 0x0003000A: /* Get max temperature */ + case RPI_FWREQ_GET_MAX_TEMPERATURE: stl_le_phys(&s->dma_as, value + 16, 99000); resplen = 8; break; /* Frame buffer */ - case 0x00040001: /* Allocate buffer */ + case RPI_FWREQ_FRAMEBUFFER_ALLOCATE: stl_le_phys(&s->dma_as, value + 12, fbconfig.base); stl_le_phys(&s->dma_as, value + 16, bcm2835_fb_get_size(&fbconfig)); resplen = 8; break; - case 0x00048001: /* Release buffer */ + case RPI_FWREQ_FRAMEBUFFER_RELEASE: resplen = 0; break; - case 0x00040002: /* Blank screen */ + case RPI_FWREQ_FRAMEBUFFER_BLANK: resplen = 4; break; - case 0x00044003: /* Test physical display width/height */ - case 0x00044004: /* Test virtual display width/height */ + case RPI_FWREQ_FRAMEBUFFER_TEST_PHYSICAL_WIDTH_HEIGHT: + case RPI_FWREQ_FRAMEBUFFER_TEST_VIRTUAL_WIDTH_HEIGHT: resplen = 8; break; - case 0x00048003: /* Set physical display width/height */ + case RPI_FWREQ_FRAMEBUFFER_SET_PHYSICAL_WIDTH_HEIGHT: fbconfig.xres = ldl_le_phys(&s->dma_as, value + 12); fbconfig.yres = ldl_le_phys(&s->dma_as, value + 16); bcm2835_fb_validate_config(&fbconfig); fbconfig_updated = true; /* fall through */ - case 0x00040003: /* Get physical display width/height */ + case RPI_FWREQ_FRAMEBUFFER_GET_PHYSICAL_WIDTH_HEIGHT: stl_le_phys(&s->dma_as, value + 12, fbconfig.xres); stl_le_phys(&s->dma_as, value + 16, fbconfig.yres); resplen = 8; break; - case 0x00048004: /* Set virtual display width/height */ + case RPI_FWREQ_FRAMEBUFFER_SET_VIRTUAL_WIDTH_HEIGHT: fbconfig.xres_virtual = ldl_le_phys(&s->dma_as, value + 12); fbconfig.yres_virtual = ldl_le_phys(&s->dma_as, value + 16); bcm2835_fb_validate_config(&fbconfig); fbconfig_updated = true; /* fall through */ - case 0x00040004: /* Get virtual display width/height */ + case RPI_FWREQ_FRAMEBUFFER_GET_VIRTUAL_WIDTH_HEIGHT: stl_le_phys(&s->dma_as, value + 12, fbconfig.xres_virtual); stl_le_phys(&s->dma_as, value + 16, fbconfig.yres_virtual); resplen = 8; break; - case 0x00044005: /* Test depth */ + case RPI_FWREQ_FRAMEBUFFER_TEST_DEPTH: resplen = 4; break; - case 0x00048005: /* Set depth */ + case RPI_FWREQ_FRAMEBUFFER_SET_DEPTH: fbconfig.bpp = ldl_le_phys(&s->dma_as, value + 12); bcm2835_fb_validate_config(&fbconfig); fbconfig_updated = true; /* fall through */ - case 0x00040005: /* Get depth */ + case RPI_FWREQ_FRAMEBUFFER_GET_DEPTH: stl_le_phys(&s->dma_as, value + 12, fbconfig.bpp); resplen = 4; break; - case 0x00044006: /* Test pixel order */ + case RPI_FWREQ_FRAMEBUFFER_TEST_PIXEL_ORDER: resplen = 4; break; - case 0x00048006: /* Set pixel order */ + case RPI_FWREQ_FRAMEBUFFER_SET_PIXEL_ORDER: fbconfig.pixo = ldl_le_phys(&s->dma_as, value + 12); bcm2835_fb_validate_config(&fbconfig); fbconfig_updated = true; /* fall through */ - case 0x00040006: /* Get pixel order */ + case RPI_FWREQ_FRAMEBUFFER_GET_PIXEL_ORDER: stl_le_phys(&s->dma_as, value + 12, fbconfig.pixo); resplen = 4; break; - case 0x00044007: /* Test pixel alpha */ + case RPI_FWREQ_FRAMEBUFFER_TEST_ALPHA_MODE: resplen = 4; break; - case 0x00048007: /* Set alpha */ + case RPI_FWREQ_FRAMEBUFFER_SET_ALPHA_MODE: fbconfig.alpha = ldl_le_phys(&s->dma_as, value + 12); bcm2835_fb_validate_config(&fbconfig); fbconfig_updated = true; /* fall through */ - case 0x00040007: /* Get alpha */ + case RPI_FWREQ_FRAMEBUFFER_GET_ALPHA_MODE: stl_le_phys(&s->dma_as, value + 12, fbconfig.alpha); resplen = 4; break; - case 0x00040008: /* Get pitch */ + case RPI_FWREQ_FRAMEBUFFER_GET_PITCH: stl_le_phys(&s->dma_as, value + 12, bcm2835_fb_get_pitch(&fbconfig)); resplen = 4; break; - case 0x00044009: /* Test virtual offset */ + case RPI_FWREQ_FRAMEBUFFER_TEST_VIRTUAL_OFFSET: resplen = 8; break; - case 0x00048009: /* Set virtual offset */ + case RPI_FWREQ_FRAMEBUFFER_SET_VIRTUAL_OFFSET: fbconfig.xoffset = ldl_le_phys(&s->dma_as, value + 12); fbconfig.yoffset = ldl_le_phys(&s->dma_as, value + 16); bcm2835_fb_validate_config(&fbconfig); fbconfig_updated = true; /* fall through */ - case 0x00040009: /* Get virtual offset */ + case RPI_FWREQ_FRAMEBUFFER_GET_VIRTUAL_OFFSET: stl_le_phys(&s->dma_as, value + 12, fbconfig.xoffset); stl_le_phys(&s->dma_as, value + 16, fbconfig.yoffset); resplen = 8; break; - case 0x0004000a: /* Get/Test/Set overscan */ - case 0x0004400a: - case 0x0004800a: + case RPI_FWREQ_FRAMEBUFFER_GET_OVERSCAN: + case RPI_FWREQ_FRAMEBUFFER_TEST_OVERSCAN: + case RPI_FWREQ_FRAMEBUFFER_SET_OVERSCAN: stl_le_phys(&s->dma_as, value + 12, 0); stl_le_phys(&s->dma_as, value + 16, 0); stl_le_phys(&s->dma_as, value + 20, 0); stl_le_phys(&s->dma_as, value + 24, 0); resplen = 16; break; - case 0x0004800b: /* Set palette */ + case RPI_FWREQ_FRAMEBUFFER_SET_PALETTE: offset = ldl_le_phys(&s->dma_as, value + 12); length = ldl_le_phys(&s->dma_as, value + 16); n = 0; @@ -XXX,XX +XXX,XX @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value) stl_le_phys(&s->dma_as, value + 12, 0); resplen = 4; break; - case 0x00040013: /* Get number of displays */ + case RPI_FWREQ_FRAMEBUFFER_GET_NUM_DISPLAYS: stl_le_phys(&s->dma_as, value + 12, 1); resplen = 4; break; - case 0x00060001: /* Get DMA channels */ + case RPI_FWREQ_GET_DMA_CHANNELS: /* channels 2-5 */ stl_le_phys(&s->dma_as, value + 12, 0x003C); resplen = 4; break; - case 0x00050001: /* Get command line */ + case RPI_FWREQ_GET_COMMAND_LINE: /* * We follow the firmware behaviour: no NUL terminator is * written to the buffer, and if the buffer is too short -- 2.34.1 From: Sergey Kambalin <sergey.kambalin@auriga.com> Signed-off-by: Sergey Kambalin <sergey.kambalin@auriga.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20230612223456.33824-4-philmd@linaro.org Message-Id: <20230531155258.8361-1-sergey.kambalin@auriga.com> [PMD: Split from bigger patch: 4/4] Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/raspi_platform.h | 5 +++++ hw/misc/bcm2835_property.c | 8 +++++--- 2 files changed, 10 insertions(+), 3 deletions(-) diff --git a/include/hw/arm/raspi_platform.h b/include/hw/arm/raspi_platform.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/raspi_platform.h +++ b/include/hw/arm/raspi_platform.h @@ -XXX,XX +XXX,XX @@ #define INTERRUPT_ILLEGAL_TYPE0 6 #define INTERRUPT_ILLEGAL_TYPE1 7 +/* Clock rates */ +#define RPI_FIRMWARE_EMMC_CLK_RATE 50000000 +#define RPI_FIRMWARE_UART_CLK_RATE 3000000 +#define RPI_FIRMWARE_DEFAULT_CLK_RATE 700000000 + #endif diff --git a/hw/misc/bcm2835_property.c b/hw/misc/bcm2835_property.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/bcm2835_property.c +++ b/hw/misc/bcm2835_property.c @@ -XXX,XX +XXX,XX @@ #include "qemu/log.h" #include "qemu/module.h" #include "trace.h" +#include "hw/arm/raspi_platform.h" /* https://github.com/raspberrypi/firmware/wiki/Mailbox-property-interface */ @@ -XXX,XX +XXX,XX @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value) case RPI_FWREQ_GET_MIN_CLOCK_RATE: switch (ldl_le_phys(&s->dma_as, value + 12)) { case RPI_FIRMWARE_EMMC_CLK_ID: - stl_le_phys(&s->dma_as, value + 16, 50000000); + stl_le_phys(&s->dma_as, value + 16, RPI_FIRMWARE_EMMC_CLK_RATE); break; case RPI_FIRMWARE_UART_CLK_ID: - stl_le_phys(&s->dma_as, value + 16, 3000000); + stl_le_phys(&s->dma_as, value + 16, RPI_FIRMWARE_UART_CLK_RATE); break; default: - stl_le_phys(&s->dma_as, value + 16, 700000000); + stl_le_phys(&s->dma_as, value + 16, + RPI_FIRMWARE_DEFAULT_CLK_RATE); break; } resplen = 8; -- 2.34.1 From: Sergey Kambalin <sergey.kambalin@auriga.com> Signed-off-by: Sergey Kambalin <sergey.kambalin@auriga.com> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20230612223456.33824-5-philmd@linaro.org Message-Id: <20230531155258.8361-1-sergey.kambalin@auriga.com> [PMD: Split from bigger patch: 3/4] Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> [PMM: added a comment about RPI_FIRMWARE_CORE_CLK_RATE really being SoC-specific] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/raspi_platform.h | 5 +++++ hw/misc/bcm2835_property.c | 3 +++ 2 files changed, 8 insertions(+) diff --git a/include/hw/arm/raspi_platform.h b/include/hw/arm/raspi_platform.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/raspi_platform.h +++ b/include/hw/arm/raspi_platform.h @@ -XXX,XX +XXX,XX @@ /* Clock rates */ #define RPI_FIRMWARE_EMMC_CLK_RATE 50000000 #define RPI_FIRMWARE_UART_CLK_RATE 3000000 +/* + * TODO: this is really SoC-specific; we might want to + * set it per-SoC if it turns out any guests care. + */ +#define RPI_FIRMWARE_CORE_CLK_RATE 350000000 #define RPI_FIRMWARE_DEFAULT_CLK_RATE 700000000 #endif diff --git a/hw/misc/bcm2835_property.c b/hw/misc/bcm2835_property.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/bcm2835_property.c +++ b/hw/misc/bcm2835_property.c @@ -XXX,XX +XXX,XX @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value) case RPI_FIRMWARE_UART_CLK_ID: stl_le_phys(&s->dma_as, value + 16, RPI_FIRMWARE_UART_CLK_RATE); break; + case RPI_FIRMWARE_CORE_CLK_ID: + stl_le_phys(&s->dma_as, value + 16, RPI_FIRMWARE_CORE_CLK_RATE); + break; default: stl_le_phys(&s->dma_as, value + 16, RPI_FIRMWARE_DEFAULT_CLK_RATE); -- 2.34.1