Second lot of ARM changes to sneak in before freeze: * fixed version of the raspi2 sd controller patches * GICv3 save/restore * v7M QOMify I've also included the Linux header update patches stolen from Paolo's pullreq since it hasn't quite hit master yet. thanks -- PMM The following changes since commit 1bbe5dc66b770d7bedd1d51d7935da948a510dd6: Merge remote-tracking branch 'remotes/pmaydell/tags/pull-target-arm-20170228' into staging (2017-02-28 14:50:17 +0000) are available in the git repository at: git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20170228-1 for you to fetch changes up to 1eeb5c7deacbfb4d4cad17590a16a99f3d85eabb: bcm2835: add sdhost and gpio controllers (2017-02-28 17:10:00 +0000) ---------------------------------------------------------------- target-arm queue: * raspi2: add gpio controller and sdhost controller, with the wiring so the guest can switch which controller the SD card is attached to (this is sufficient to get raspbian kernels to boot) * GICv3: support state save/restore from KVM * update Linux headers to 4.11 * refactor and QOMify the ARMv7M container object ---------------------------------------------------------------- Clement Deschamps (3): hw/sd: add card-reparenting function bcm2835_gpio: add bcm2835 gpio controller bcm2835: add sdhost and gpio controllers Paolo Bonzini (2): update-linux-headers: update for 4.11 update Linux headers to 4.11 Peter Maydell (12): armv7m: Abstract out the "load kernel" code armv7m: Move NVICState struct definition into header armv7m: QOMify the armv7m container armv7m: Use QOMified armv7m object in armv7m_init() armv7m: Make ARMv7M object take memory region link armv7m: Make NVIC expose a memory region rather than mapping itself armv7m: Make bitband device take the address space to access armv7m: Don't put core v7M devices under CONFIG_STELLARIS armv7m: Split systick out from NVIC stm32f205: Create armv7m object without using armv7m_init() stm32f205: Rename 'nvic' local to 'armv7m' qdev: Have qdev_set_parent_bus() handle devices already on a bus Vijaya Kumar K (4): hw/intc/arm_gicv3_kvm: Add ICC_SRE_EL1 register to vmstate hw/intc/arm_gicv3_kvm: Implement get/put functions target-arm: Add GICv3CPUState in CPUARMState struct hw/intc/arm_gicv3_kvm: Reset GICv3 cpu interface registers hw/gpio/Makefile.objs | 1 + hw/intc/Makefile.objs | 2 +- hw/timer/Makefile.objs | 1 + hw/intc/gicv3_internal.h | 3 + include/hw/arm/arm.h | 12 + include/hw/arm/armv7m.h | 63 +++ include/hw/arm/armv7m_nvic.h | 62 ++ include/hw/arm/bcm2835_peripherals.h | 4 + include/hw/arm/stm32f205_soc.h | 4 +- include/hw/gpio/bcm2835_gpio.h | 39 ++ include/hw/intc/arm_gicv3_common.h | 1 + include/hw/sd/sd.h | 11 + include/hw/timer/armv7m_systick.h | 34 ++ include/standard-headers/asm-x86/hyperv.h | 8 + include/standard-headers/linux/input-event-codes.h | 2 +- include/standard-headers/linux/pci_regs.h | 25 + include/standard-headers/linux/virtio_ids.h | 1 + linux-headers/asm-arm/kvm.h | 15 + linux-headers/asm-arm/unistd-common.h | 357 ++++++++++++ linux-headers/asm-arm/unistd-eabi.h | 5 + linux-headers/asm-arm/unistd-oabi.h | 17 + linux-headers/asm-arm/unistd.h | 419 +------------- linux-headers/asm-arm64/kvm.h | 13 + linux-headers/asm-powerpc/kvm.h | 27 + linux-headers/asm-powerpc/unistd.h | 1 + linux-headers/asm-x86/kvm_para.h | 13 +- linux-headers/linux/kvm.h | 24 +- linux-headers/linux/kvm_para.h | 2 + linux-headers/linux/userfaultfd.h | 67 ++- linux-headers/linux/vfio.h | 10 + target/arm/cpu.h | 2 + hw/arm/armv7m.c | 379 ++++++++----- hw/arm/bcm2835_peripherals.c | 43 +- hw/arm/netduino2.c | 7 +- hw/arm/stm32f205_soc.c | 28 +- hw/core/qdev.c | 14 + hw/gpio/bcm2835_gpio.c | 353 ++++++++++++ hw/intc/arm_gicv3_common.c | 38 ++ hw/intc/arm_gicv3_cpuif.c | 8 + hw/intc/arm_gicv3_kvm.c | 629 ++++++++++++++++++++- hw/intc/armv7m_nvic.c | 214 ++----- hw/sd/core.c | 27 + hw/timer/armv7m_systick.c | 240 ++++++++ default-configs/arm-softmmu.mak | 2 + hw/timer/trace-events | 6 + scripts/update-linux-headers.sh | 13 +- 46 files changed, 2479 insertions(+), 767 deletions(-) create mode 100644 include/hw/arm/armv7m.h create mode 100644 include/hw/arm/armv7m_nvic.h create mode 100644 include/hw/gpio/bcm2835_gpio.h create mode 100644 include/hw/timer/armv7m_systick.h create mode 100644 linux-headers/asm-arm/unistd-common.h create mode 100644 linux-headers/asm-arm/unistd-eabi.h create mode 100644 linux-headers/asm-arm/unistd-oabi.h create mode 100644 hw/gpio/bcm2835_gpio.c create mode 100644 hw/timer/armv7m_systick.c Abstract the "load kernel" code out of armv7m_init() into its own function. This includes the registration of the CPU reset function, to parallel how we handle this for A profile cores. We make the function public so that boards which choose to directly instantiate an ARMv7M device object can call it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 1487604965-23220-2-git-send-email-peter.maydell@linaro.org --- include/hw/arm/arm.h | 12 ++++++++++++ hw/arm/armv7m.c | 23 ++++++++++++++++++----- 2 files changed, 30 insertions(+), 5 deletions(-) diff --git a/include/hw/arm/arm.h b/include/hw/arm/arm.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/arm.h +++ b/include/hw/arm/arm.h @@ -XXX,XX +XXX,XX @@ typedef enum { /* armv7m.c */ DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq, const char *kernel_filename, const char *cpu_model); +/** + * armv7m_load_kernel: + * @cpu: CPU + * @kernel_filename: file to load + * @mem_size: mem_size: maximum image size to load + * + * Load the guest image for an ARMv7M system. This must be called by + * any ARMv7M board, either directly or via armv7m_init(). (This is + * necessary to ensure that the CPU resets correctly on system reset, + * as well as for kernel loading.) + */ +void armv7m_load_kernel(ARMCPU *cpu, const char *kernel_filename, int mem_size); /* * struct used as a parameter of the arm_load_kernel machine init diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq, ARMCPU *cpu; CPUARMState *env; DeviceState *nvic; - int image_size; - uint64_t entry; - uint64_t lowaddr; - int big_endian; if (cpu_model == NULL) { cpu_model = "cortex-m3"; @@ -XXX,XX +XXX,XX @@ DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq, qdev_init_nofail(nvic); sysbus_connect_irq(SYS_BUS_DEVICE(nvic), 0, qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ)); + armv7m_load_kernel(cpu, kernel_filename, mem_size); + return nvic; +} + +void armv7m_load_kernel(ARMCPU *cpu, const char *kernel_filename, int mem_size) +{ + int image_size; + uint64_t entry; + uint64_t lowaddr; + int big_endian; #ifdef TARGET_WORDS_BIGENDIAN big_endian = 1; @@ -XXX,XX +XXX,XX @@ DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq, } } + /* CPU objects (unlike devices) are not automatically reset on system + * reset, so we must always register a handler to do so. Unlike + * A-profile CPUs, we don't need to do anything special in the + * handler to arrange that it starts correctly. + * This is arguably the wrong place to do this, but it matches the + * way A-profile does it. Note that this means that every M profile + * board must call this function! + */ qemu_register_reset(armv7m_reset, cpu); - return nvic; } static Property bitband_properties[] = { -- 2.7.4 Move the NVICState struct definition into a header, so we can embed it into other QOM objects like SoCs. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 1487604965-23220-3-git-send-email-peter.maydell@linaro.org --- include/hw/arm/armv7m_nvic.h | 66 ++++++++++++++++++++++++++++++++++++++++++++ hw/intc/armv7m_nvic.c | 49 +------------------------------- 2 files changed, 67 insertions(+), 48 deletions(-) create mode 100644 include/hw/arm/armv7m_nvic.h diff --git a/include/hw/arm/armv7m_nvic.h b/include/hw/arm/armv7m_nvic.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/arm/armv7m_nvic.h @@ -XXX,XX +XXX,XX @@ +/* + * ARMv7M NVIC object + * + * Copyright (c) 2017 Linaro Ltd + * Written by Peter Maydell <peter.maydell@linaro.org> + * + * This code is licensed under the GPL version 2 or later. + */ + +#ifndef HW_ARM_ARMV7M_NVIC_H +#define HW_ARM_ARMV7M_NVIC_H + +#include "target/arm/cpu.h" +#include "hw/sysbus.h" + +#define TYPE_NVIC "armv7m_nvic" + +#define NVIC(obj) \ + OBJECT_CHECK(NVICState, (obj), TYPE_NVIC) + +/* Highest permitted number of exceptions (architectural limit) */ +#define NVIC_MAX_VECTORS 512 + +typedef struct VecInfo { + /* Exception priorities can range from -3 to 255; only the unmodifiable + * priority values for RESET, NMI and HardFault can be negative. + */ + int16_t prio; + uint8_t enabled; + uint8_t pending; + uint8_t active; + uint8_t level; /* exceptions <=15 never set level */ +} VecInfo; + +typedef struct NVICState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + ARMCPU *cpu; + + VecInfo vectors[NVIC_MAX_VECTORS]; + uint32_t prigroup; + + /* vectpending and exception_prio are both cached state that can + * be recalculated from the vectors[] array and the prigroup field. + */ + unsigned int vectpending; /* highest prio pending enabled exception */ + int exception_prio; /* group prio of the highest prio active exception */ + + struct { + uint32_t control; + uint32_t reload; + int64_t tick; + QEMUTimer *timer; + } systick; + + MemoryRegion sysregmem; + MemoryRegion container; + + uint32_t num_irq; + qemu_irq excpout; + qemu_irq sysresetreq; +} NVICState; + +#endif diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "qemu/timer.h" #include "hw/arm/arm.h" +#include "hw/arm/armv7m_nvic.h" #include "target/arm/cpu.h" #include "exec/address-spaces.h" #include "qemu/log.h" @@ -XXX,XX +XXX,XX @@ * "exception" more or less interchangeably. */ #define NVIC_FIRST_IRQ 16 -#define NVIC_MAX_VECTORS 512 #define NVIC_MAX_IRQ (NVIC_MAX_VECTORS - NVIC_FIRST_IRQ) /* Effective running priority of the CPU when no exception is active @@ -XXX,XX +XXX,XX @@ */ #define NVIC_NOEXC_PRIO 0x100 -typedef struct VecInfo { - /* Exception priorities can range from -3 to 255; only the unmodifiable - * priority values for RESET, NMI and HardFault can be negative. - */ - int16_t prio; - uint8_t enabled; - uint8_t pending; - uint8_t active; - uint8_t level; /* exceptions <=15 never set level */ -} VecInfo; - -typedef struct NVICState { - /*< private >*/ - SysBusDevice parent_obj; - /*< public >*/ - - ARMCPU *cpu; - - VecInfo vectors[NVIC_MAX_VECTORS]; - uint32_t prigroup; - - /* vectpending and exception_prio are both cached state that can - * be recalculated from the vectors[] array and the prigroup field. - */ - unsigned int vectpending; /* highest prio pending enabled exception */ - int exception_prio; /* group prio of the highest prio active exception */ - - struct { - uint32_t control; - uint32_t reload; - int64_t tick; - QEMUTimer *timer; - } systick; - - MemoryRegion sysregmem; - MemoryRegion container; - - uint32_t num_irq; - qemu_irq excpout; - qemu_irq sysresetreq; -} NVICState; - -#define TYPE_NVIC "armv7m_nvic" - -#define NVIC(obj) \ - OBJECT_CHECK(NVICState, (obj), TYPE_NVIC) - static const uint8_t nvic_id[] = { 0x00, 0xb0, 0x1b, 0x00, 0x0d, 0xe0, 0x05, 0xb1 }; -- 2.7.4 Create a proper QOM object for the armv7m container, which holds the CPU, the NVIC and the bitband regions. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 1487604965-23220-4-git-send-email-peter.maydell@linaro.org --- include/hw/arm/armv7m.h | 51 ++++++++++++++++++ hw/arm/armv7m.c | 139 +++++++++++++++++++++++++++++++++++++++++++----- 2 files changed, 178 insertions(+), 12 deletions(-) create mode 100644 include/hw/arm/armv7m.h diff --git a/include/hw/arm/armv7m.h b/include/hw/arm/armv7m.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/arm/armv7m.h @@ -XXX,XX +XXX,XX @@ +/* + * ARMv7M CPU object + * + * Copyright (c) 2017 Linaro Ltd + * Written by Peter Maydell <peter.maydell@linaro.org> + * + * This code is licensed under the GPL version 2 or later. + */ + +#ifndef HW_ARM_ARMV7M_H +#define HW_ARM_ARMV7M_H + +#include "hw/sysbus.h" +#include "hw/arm/armv7m_nvic.h" + +#define TYPE_BITBAND "ARM,bitband-memory" +#define BITBAND(obj) OBJECT_CHECK(BitBandState, (obj), TYPE_BITBAND) + +typedef struct { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + MemoryRegion iomem; + uint32_t base; +} BitBandState; + +#define TYPE_ARMV7M "armv7m" +#define ARMV7M(obj) OBJECT_CHECK(ARMv7MState, (obj), TYPE_ARMV7M) + +#define ARMV7M_NUM_BITBANDS 2 + +/* ARMv7M container object. + * + Unnamed GPIO input lines: external IRQ lines for the NVIC + * + Named GPIO output SYSRESETREQ: signalled for guest AIRCR.SYSRESETREQ + * + Property "cpu-model": CPU model to instantiate + * + Property "num-irq": number of external IRQ lines + */ +typedef struct ARMv7MState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + NVICState nvic; + BitBandState bitband[ARMV7M_NUM_BITBANDS]; + ARMCPU *cpu; + + /* Properties */ + char *cpu_model; +} ARMv7MState; + +#endif diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "hw/arm/armv7m.h" #include "qapi/error.h" #include "qemu-common.h" #include "cpu.h" @@ -XXX,XX +XXX,XX @@ static const MemoryRegionOps bitband_ops = { .endianness = DEVICE_NATIVE_ENDIAN, }; -#define TYPE_BITBAND "ARM,bitband-memory" -#define BITBAND(obj) OBJECT_CHECK(BitBandState, (obj), TYPE_BITBAND) - -typedef struct { - /*< private >*/ - SysBusDevice parent_obj; - /*< public >*/ - - MemoryRegion iomem; - uint32_t base; -} BitBandState; - static void bitband_init(Object *obj) { BitBandState *s = BITBAND(obj); @@ -XXX,XX +XXX,XX @@ static void armv7m_bitband_init(void) /* Board init. */ +static const hwaddr bitband_input_addr[ARMV7M_NUM_BITBANDS] = { + 0x20000000, 0x40000000 +}; + +static const hwaddr bitband_output_addr[ARMV7M_NUM_BITBANDS] = { + 0x22000000, 0x42000000 +}; + +static void armv7m_instance_init(Object *obj) +{ + ARMv7MState *s = ARMV7M(obj); + int i; + + /* Can't init the cpu here, we don't yet know which model to use */ + + object_initialize(&s->nvic, sizeof(s->nvic), "armv7m_nvic"); + qdev_set_parent_bus(DEVICE(&s->nvic), sysbus_get_default()); + object_property_add_alias(obj, "num-irq", + OBJECT(&s->nvic), "num-irq", &error_abort); + + for (i = 0; i < ARRAY_SIZE(s->bitband); i++) { + object_initialize(&s->bitband[i], sizeof(s->bitband[i]), TYPE_BITBAND); + qdev_set_parent_bus(DEVICE(&s->bitband[i]), sysbus_get_default()); + } +} + +static void armv7m_realize(DeviceState *dev, Error **errp) +{ + ARMv7MState *s = ARMV7M(dev); + Error *err = NULL; + int i; + char **cpustr; + ObjectClass *oc; + const char *typename; + CPUClass *cc; + + cpustr = g_strsplit(s->cpu_model, ",", 2); + + oc = cpu_class_by_name(TYPE_ARM_CPU, cpustr[0]); + if (!oc) { + error_setg(errp, "Unknown CPU model %s", cpustr[0]); + g_strfreev(cpustr); + return; + } + + cc = CPU_CLASS(oc); + typename = object_class_get_name(oc); + cc->parse_features(typename, cpustr[1], &err); + g_strfreev(cpustr); + if (err) { + error_propagate(errp, err); + return; + } + + s->cpu = ARM_CPU(object_new(typename)); + if (!s->cpu) { + error_setg(errp, "Unknown CPU model %s", s->cpu_model); + return; + } + + object_property_set_bool(OBJECT(s->cpu), true, "realized", &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + + /* Note that we must realize the NVIC after the CPU */ + object_property_set_bool(OBJECT(&s->nvic), true, "realized", &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + + /* Alias the NVIC's input and output GPIOs as our own so the board + * code can wire them up. (We do this in realize because the + * NVIC doesn't create the input GPIO array until realize.) + */ + qdev_pass_gpios(DEVICE(&s->nvic), dev, NULL); + qdev_pass_gpios(DEVICE(&s->nvic), dev, "SYSRESETREQ"); + + /* Wire the NVIC up to the CPU */ + sysbus_connect_irq(SYS_BUS_DEVICE(&s->nvic), 0, + qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_IRQ)); + s->cpu->env.nvic = &s->nvic; + + for (i = 0; i < ARRAY_SIZE(s->bitband); i++) { + Object *obj = OBJECT(&s->bitband[i]); + SysBusDevice *sbd = SYS_BUS_DEVICE(&s->bitband[i]); + + object_property_set_int(obj, bitband_input_addr[i], "base", &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + object_property_set_bool(obj, true, "realized", &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + + sysbus_mmio_map(sbd, 0, bitband_output_addr[i]); + } +} + +static Property armv7m_properties[] = { + DEFINE_PROP_STRING("cpu-model", ARMv7MState, cpu_model), + DEFINE_PROP_END_OF_LIST(), +}; + +static void armv7m_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = armv7m_realize; + dc->props = armv7m_properties; +} + +static const TypeInfo armv7m_info = { + .name = TYPE_ARMV7M, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(ARMv7MState), + .instance_init = armv7m_instance_init, + .class_init = armv7m_class_init, +}; + static void armv7m_reset(void *opaque) { ARMCPU *cpu = opaque; @@ -XXX,XX +XXX,XX @@ static const TypeInfo bitband_info = { static void armv7m_register_types(void) { type_register_static(&bitband_info); + type_register_static(&armv7m_info); } type_init(armv7m_register_types) -- 2.7.4 Make the legacy armv7m_init() function use the newly QOMified armv7m object rather than doing everything by hand. We can return the armv7m object rather than the NVIC from armv7m_init() because its interface to the rest of the board (GPIOs, etc) is identical. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 1487604965-23220-5-git-send-email-peter.maydell@linaro.org --- hw/arm/armv7m.c | 49 ++++++++++++------------------------------------- 1 file changed, 12 insertions(+), 37 deletions(-) diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ static void bitband_init(Object *obj) sysbus_init_mmio(dev, &s->iomem); } -static void armv7m_bitband_init(void) -{ - DeviceState *dev; - - dev = qdev_create(NULL, TYPE_BITBAND); - qdev_prop_set_uint32(dev, "base", 0x20000000); - qdev_init_nofail(dev); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, 0x22000000); - - dev = qdev_create(NULL, TYPE_BITBAND); - qdev_prop_set_uint32(dev, "base", 0x40000000); - qdev_init_nofail(dev); - sysbus_mmio_map(SYS_BUS_DEVICE(dev), 0, 0x42000000); -} - /* Board init. */ static const hwaddr bitband_input_addr[ARMV7M_NUM_BITBANDS] = { @@ -XXX,XX +XXX,XX @@ static void armv7m_reset(void *opaque) /* Init CPU and memory for a v7-M based board. mem_size is in bytes. - Returns the NVIC array. */ + Returns the ARMv7M device. */ DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq, const char *kernel_filename, const char *cpu_model) { - ARMCPU *cpu; - CPUARMState *env; - DeviceState *nvic; + DeviceState *armv7m; if (cpu_model == NULL) { - cpu_model = "cortex-m3"; + cpu_model = "cortex-m3"; } - cpu = cpu_arm_init(cpu_model); - if (cpu == NULL) { - fprintf(stderr, "Unable to find CPU definition\n"); - exit(1); - } - env = &cpu->env; - - armv7m_bitband_init(); - - nvic = qdev_create(NULL, "armv7m_nvic"); - qdev_prop_set_uint32(nvic, "num-irq", num_irq); - env->nvic = nvic; - qdev_init_nofail(nvic); - sysbus_connect_irq(SYS_BUS_DEVICE(nvic), 0, - qdev_get_gpio_in(DEVICE(cpu), ARM_CPU_IRQ)); - armv7m_load_kernel(cpu, kernel_filename, mem_size); - return nvic; + + armv7m = qdev_create(NULL, "armv7m"); + qdev_prop_set_uint32(armv7m, "num-irq", num_irq); + qdev_prop_set_string(armv7m, "cpu-model", cpu_model); + /* This will exit with an error if the user passed us a bad cpu_model */ + qdev_init_nofail(armv7m); + + armv7m_load_kernel(ARM_CPU(first_cpu), kernel_filename, mem_size); + return armv7m; } void armv7m_load_kernel(ARMCPU *cpu, const char *kernel_filename, int mem_size) -- 2.7.4 Make the ARMv7M object take a memory region link which it uses to wire up the bitband rather than having them always put themselves in the system address space. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 1487604965-23220-6-git-send-email-peter.maydell@linaro.org --- include/hw/arm/armv7m.h | 10 ++++++++++ hw/arm/armv7m.c | 23 ++++++++++++++++++++++- 2 files changed, 32 insertions(+), 1 deletion(-) diff --git a/include/hw/arm/armv7m.h b/include/hw/arm/armv7m.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/armv7m.h +++ b/include/hw/arm/armv7m.h @@ -XXX,XX +XXX,XX @@ typedef struct { * + Named GPIO output SYSRESETREQ: signalled for guest AIRCR.SYSRESETREQ * + Property "cpu-model": CPU model to instantiate * + Property "num-irq": number of external IRQ lines + * + Property "memory": MemoryRegion defining the physical address space + * that CPU accesses see. (The NVIC, bitbanding and other CPU-internal + * devices will be automatically layered on top of this view.) */ typedef struct ARMv7MState { /*< private >*/ @@ -XXX,XX +XXX,XX @@ typedef struct ARMv7MState { BitBandState bitband[ARMV7M_NUM_BITBANDS]; ARMCPU *cpu; + /* MemoryRegion we pass to the CPU, with our devices layered on + * top of the ones the board provides in board_memory. + */ + MemoryRegion container; + /* Properties */ char *cpu_model; + /* MemoryRegion the board provides to us (with its devices, RAM, etc) */ + MemoryRegion *board_memory; } ARMv7MState; #endif diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ #include "elf.h" #include "sysemu/qtest.h" #include "qemu/error-report.h" +#include "exec/address-spaces.h" /* Bitbanded IO. Each word corresponds to a single bit. */ @@ -XXX,XX +XXX,XX @@ static void armv7m_instance_init(Object *obj) /* Can't init the cpu here, we don't yet know which model to use */ + object_property_add_link(obj, "memory", + TYPE_MEMORY_REGION, + (Object **)&s->board_memory, + qdev_prop_allow_set_link_before_realize, + OBJ_PROP_LINK_UNREF_ON_RELEASE, + &error_abort); + memory_region_init(&s->container, obj, "armv7m-container", UINT64_MAX); + object_initialize(&s->nvic, sizeof(s->nvic), "armv7m_nvic"); qdev_set_parent_bus(DEVICE(&s->nvic), sysbus_get_default()); object_property_add_alias(obj, "num-irq", @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) const char *typename; CPUClass *cc; + if (!s->board_memory) { + error_setg(errp, "memory property was not set"); + return; + } + + memory_region_add_subregion_overlap(&s->container, 0, s->board_memory, -1); + cpustr = g_strsplit(s->cpu_model, ",", 2); oc = cpu_class_by_name(TYPE_ARM_CPU, cpustr[0]); @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) return; } + object_property_set_link(OBJECT(s->cpu), OBJECT(&s->container), "memory", + &error_abort); object_property_set_bool(OBJECT(s->cpu), true, "realized", &err); if (err != NULL) { error_propagate(errp, err); @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) return; } - sysbus_mmio_map(sbd, 0, bitband_output_addr[i]); + memory_region_add_subregion(&s->container, bitband_output_addr[i], + sysbus_mmio_get_region(sbd, 0)); } } @@ -XXX,XX +XXX,XX @@ DeviceState *armv7m_init(MemoryRegion *system_memory, int mem_size, int num_irq, armv7m = qdev_create(NULL, "armv7m"); qdev_prop_set_uint32(armv7m, "num-irq", num_irq); qdev_prop_set_string(armv7m, "cpu-model", cpu_model); + object_property_set_link(OBJECT(armv7m), OBJECT(get_system_memory()), + "memory", &error_abort); /* This will exit with an error if the user passed us a bad cpu_model */ qdev_init_nofail(armv7m); -- 2.7.4 Make the NVIC device expose a memory region for its users to map, rather than mapping itself into the system memory space on realize, and get the one user (the ARMv7M object) to do this. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 1487604965-23220-7-git-send-email-peter.maydell@linaro.org --- hw/arm/armv7m.c | 7 ++++++- hw/intc/armv7m_nvic.c | 7 ++----- 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ static void armv7m_instance_init(Object *obj) static void armv7m_realize(DeviceState *dev, Error **errp) { ARMv7MState *s = ARMV7M(dev); + SysBusDevice *sbd; Error *err = NULL; int i; char **cpustr; @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) qdev_pass_gpios(DEVICE(&s->nvic), dev, "SYSRESETREQ"); /* Wire the NVIC up to the CPU */ - sysbus_connect_irq(SYS_BUS_DEVICE(&s->nvic), 0, + sbd = SYS_BUS_DEVICE(&s->nvic); + sysbus_connect_irq(sbd, 0, qdev_get_gpio_in(DEVICE(s->cpu), ARM_CPU_IRQ)); s->cpu->env.nvic = &s->nvic; + memory_region_add_subregion(&s->container, 0xe000e000, + sysbus_mmio_get_region(sbd, 0)); + for (i = 0; i < ARRAY_SIZE(s->bitband); i++) { Object *obj = OBJECT(&s->bitband[i]); SysBusDevice *sbd = SYS_BUS_DEVICE(&s->bitband[i]); diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ #include "hw/arm/arm.h" #include "hw/arm/armv7m_nvic.h" #include "target/arm/cpu.h" -#include "exec/address-spaces.h" #include "qemu/log.h" #include "trace.h" @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) "nvic_sysregs", 0x1000); memory_region_add_subregion(&s->container, 0, &s->sysregmem); - /* Map the whole thing into system memory at the location required - * by the v7M architecture. - */ - memory_region_add_subregion(get_system_memory(), 0xe000e000, &s->container); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->container); + s->systick.timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, systick_timer_tick, s); } -- 2.7.4 Instead of the bitband device doing a cpu_physical_memory_read/write, make it take a MemoryRegion which specifies where it should be accessing, and use address_space_read/write to access the corresponding AddressSpace. Since this entails pretty much a rewrite, convert away from old_mmio in the process. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 1487604965-23220-8-git-send-email-peter.maydell@linaro.org --- include/hw/arm/armv7m.h | 2 + hw/arm/armv7m.c | 166 +++++++++++++++++++++++------------------------- 2 files changed, 81 insertions(+), 87 deletions(-) diff --git a/include/hw/arm/armv7m.h b/include/hw/arm/armv7m.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/armv7m.h +++ b/include/hw/arm/armv7m.h @@ -XXX,XX +XXX,XX @@ typedef struct { SysBusDevice parent_obj; /*< public >*/ + AddressSpace *source_as; MemoryRegion iomem; uint32_t base; + MemoryRegion *source_memory; } BitBandState; #define TYPE_ARMV7M "armv7m" diff --git a/hw/arm/armv7m.c b/hw/arm/armv7m.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/armv7m.c +++ b/hw/arm/armv7m.c @@ -XXX,XX +XXX,XX @@ /* Bitbanded IO. Each word corresponds to a single bit. */ /* Get the byte address of the real memory for a bitband access. */ -static inline uint32_t bitband_addr(void * opaque, uint32_t addr) +static inline hwaddr bitband_addr(BitBandState *s, hwaddr offset) { - uint32_t res; - - res = *(uint32_t *)opaque; - res |= (addr & 0x1ffffff) >> 5; - return res; - -} - -static uint32_t bitband_readb(void *opaque, hwaddr offset) -{ - uint8_t v; - cpu_physical_memory_read(bitband_addr(opaque, offset), &v, 1); - return (v & (1 << ((offset >> 2) & 7))) != 0; -} - -static void bitband_writeb(void *opaque, hwaddr offset, - uint32_t value) -{ - uint32_t addr; - uint8_t mask; - uint8_t v; - addr = bitband_addr(opaque, offset); - mask = (1 << ((offset >> 2) & 7)); - cpu_physical_memory_read(addr, &v, 1); - if (value & 1) - v |= mask; - else - v &= ~mask; - cpu_physical_memory_write(addr, &v, 1); -} - -static uint32_t bitband_readw(void *opaque, hwaddr offset) -{ - uint32_t addr; - uint16_t mask; - uint16_t v; - addr = bitband_addr(opaque, offset) & ~1; - mask = (1 << ((offset >> 2) & 15)); - mask = tswap16(mask); - cpu_physical_memory_read(addr, &v, 2); - return (v & mask) != 0; -} - -static void bitband_writew(void *opaque, hwaddr offset, - uint32_t value) -{ - uint32_t addr; - uint16_t mask; - uint16_t v; - addr = bitband_addr(opaque, offset) & ~1; - mask = (1 << ((offset >> 2) & 15)); - mask = tswap16(mask); - cpu_physical_memory_read(addr, &v, 2); - if (value & 1) - v |= mask; - else - v &= ~mask; - cpu_physical_memory_write(addr, &v, 2); + return s->base | (offset & 0x1ffffff) >> 5; } -static uint32_t bitband_readl(void *opaque, hwaddr offset) +static MemTxResult bitband_read(void *opaque, hwaddr offset, + uint64_t *data, unsigned size, MemTxAttrs attrs) { - uint32_t addr; - uint32_t mask; - uint32_t v; - addr = bitband_addr(opaque, offset) & ~3; - mask = (1 << ((offset >> 2) & 31)); - mask = tswap32(mask); - cpu_physical_memory_read(addr, &v, 4); - return (v & mask) != 0; + BitBandState *s = opaque; + uint8_t buf[4]; + MemTxResult res; + int bitpos, bit; + hwaddr addr; + + assert(size <= 4); + + /* Find address in underlying memory and round down to multiple of size */ + addr = bitband_addr(s, offset) & (-size); + res = address_space_read(s->source_as, addr, attrs, buf, size); + if (res) { + return res; + } + /* Bit position in the N bytes read... */ + bitpos = (offset >> 2) & ((size * 8) - 1); + /* ...converted to byte in buffer and bit in byte */ + bit = (buf[bitpos >> 3] >> (bitpos & 7)) & 1; + *data = bit; + return MEMTX_OK; } -static void bitband_writel(void *opaque, hwaddr offset, - uint32_t value) +static MemTxResult bitband_write(void *opaque, hwaddr offset, uint64_t value, + unsigned size, MemTxAttrs attrs) { - uint32_t addr; - uint32_t mask; - uint32_t v; - addr = bitband_addr(opaque, offset) & ~3; - mask = (1 << ((offset >> 2) & 31)); - mask = tswap32(mask); - cpu_physical_memory_read(addr, &v, 4); - if (value & 1) - v |= mask; - else - v &= ~mask; - cpu_physical_memory_write(addr, &v, 4); + BitBandState *s = opaque; + uint8_t buf[4]; + MemTxResult res; + int bitpos, bit; + hwaddr addr; + + assert(size <= 4); + + /* Find address in underlying memory and round down to multiple of size */ + addr = bitband_addr(s, offset) & (-size); + res = address_space_read(s->source_as, addr, attrs, buf, size); + if (res) { + return res; + } + /* Bit position in the N bytes read... */ + bitpos = (offset >> 2) & ((size * 8) - 1); + /* ...converted to byte in buffer and bit in byte */ + bit = 1 << (bitpos & 7); + if (value & 1) { + buf[bitpos >> 3] |= bit; + } else { + buf[bitpos >> 3] &= ~bit; + } + return address_space_write(s->source_as, addr, attrs, buf, size); } static const MemoryRegionOps bitband_ops = { - .old_mmio = { - .read = { bitband_readb, bitband_readw, bitband_readl, }, - .write = { bitband_writeb, bitband_writew, bitband_writel, }, - }, + .read_with_attrs = bitband_read, + .write_with_attrs = bitband_write, .endianness = DEVICE_NATIVE_ENDIAN, + .impl.min_access_size = 1, + .impl.max_access_size = 4, + .valid.min_access_size = 1, + .valid.max_access_size = 4, }; static void bitband_init(Object *obj) @@ -XXX,XX +XXX,XX @@ static void bitband_init(Object *obj) BitBandState *s = BITBAND(obj); SysBusDevice *dev = SYS_BUS_DEVICE(obj); - memory_region_init_io(&s->iomem, obj, &bitband_ops, &s->base, + object_property_add_link(obj, "source-memory", + TYPE_MEMORY_REGION, + (Object **)&s->source_memory, + qdev_prop_allow_set_link_before_realize, + OBJ_PROP_LINK_UNREF_ON_RELEASE, + &error_abort); + memory_region_init_io(&s->iomem, obj, &bitband_ops, s, "bitband", 0x02000000); sysbus_init_mmio(dev, &s->iomem); } +static void bitband_realize(DeviceState *dev, Error **errp) +{ + BitBandState *s = BITBAND(dev); + + if (!s->source_memory) { + error_setg(errp, "source-memory property not set"); + return; + } + + s->source_as = address_space_init_shareable(s->source_memory, + "bitband-source"); +} + /* Board init. */ static const hwaddr bitband_input_addr[ARMV7M_NUM_BITBANDS] = { @@ -XXX,XX +XXX,XX @@ static void armv7m_realize(DeviceState *dev, Error **errp) error_propagate(errp, err); return; } + object_property_set_link(obj, OBJECT(s->board_memory), + "source-memory", &error_abort); object_property_set_bool(obj, true, "realized", &err); if (err != NULL) { error_propagate(errp, err); @@ -XXX,XX +XXX,XX @@ static void bitband_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + dc->realize = bitband_realize; dc->props = bitband_properties; } -- 2.7.4 The NVIC is a core v7M device that exists for all v7M CPUs; put it under a CONFIG_ARM_V7M rather than hiding it under CONFIG_STELLARIS. (We'll use CONFIG_ARM_V7M for the SysTick device too when we split it out of the NVIC.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 1487604965-23220-9-git-send-email-peter.maydell@linaro.org --- hw/intc/Makefile.objs | 2 +- default-configs/arm-softmmu.mak | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/hw/intc/Makefile.objs b/hw/intc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/Makefile.objs +++ b/hw/intc/Makefile.objs @@ -XXX,XX +XXX,XX @@ obj-$(CONFIG_APIC) += apic.o apic_common.o obj-$(CONFIG_ARM_GIC_KVM) += arm_gic_kvm.o obj-$(call land,$(CONFIG_ARM_GIC_KVM),$(TARGET_AARCH64)) += arm_gicv3_kvm.o obj-$(call land,$(CONFIG_ARM_GIC_KVM),$(TARGET_AARCH64)) += arm_gicv3_its_kvm.o -obj-$(CONFIG_STELLARIS) += armv7m_nvic.o +obj-$(CONFIG_ARM_V7M) += armv7m_nvic.o obj-$(CONFIG_EXYNOS4) += exynos4210_gic.o exynos4210_combiner.o obj-$(CONFIG_GRLIB) += grlib_irqmp.o obj-$(CONFIG_IOAPIC) += ioapic.o diff --git a/default-configs/arm-softmmu.mak b/default-configs/arm-softmmu.mak index XXXXXXX..XXXXXXX 100644 --- a/default-configs/arm-softmmu.mak +++ b/default-configs/arm-softmmu.mak @@ -XXX,XX +XXX,XX @@ CONFIG_ARM11MPCORE=y CONFIG_A9MPCORE=y CONFIG_A15MPCORE=y +CONFIG_ARM_V7M=y + CONFIG_ARM_GIC=y CONFIG_ARM_GIC_KVM=$(CONFIG_KVM) CONFIG_ARM_TIMER=y -- 2.7.4 The SysTick timer isn't really part of the NVIC proper; we just modelled it that way back when we couldn't easily have devices that only occupied a small chunk of a memory region. Split it out into its own device. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1487604965-23220-10-git-send-email-peter.maydell@linaro.org Reviewed-by: Alex Bennée <alex.bennee@linaro.org> --- hw/timer/Makefile.objs | 1 + include/hw/arm/armv7m_nvic.h | 10 +- include/hw/timer/armv7m_systick.h | 34 ++++++ hw/intc/armv7m_nvic.c | 160 ++++++------------------- hw/timer/armv7m_systick.c | 240 ++++++++++++++++++++++++++++++++++++++ hw/timer/trace-events | 6 + 6 files changed, 318 insertions(+), 133 deletions(-) create mode 100644 include/hw/timer/armv7m_systick.h create mode 100644 hw/timer/armv7m_systick.c diff --git a/hw/timer/Makefile.objs b/hw/timer/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/Makefile.objs +++ b/hw/timer/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_ARM_TIMER) += arm_timer.o common-obj-$(CONFIG_ARM_MPTIMER) += arm_mptimer.o +common-obj-$(CONFIG_ARM_V7M) += armv7m_systick.o common-obj-$(CONFIG_A9_GTIMER) += a9gtimer.o common-obj-$(CONFIG_CADENCE) += cadence_ttc.o common-obj-$(CONFIG_DS1338) += ds1338.o diff --git a/include/hw/arm/armv7m_nvic.h b/include/hw/arm/armv7m_nvic.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/armv7m_nvic.h +++ b/include/hw/arm/armv7m_nvic.h @@ -XXX,XX +XXX,XX @@ #include "target/arm/cpu.h" #include "hw/sysbus.h" +#include "hw/timer/armv7m_systick.h" #define TYPE_NVIC "armv7m_nvic" @@ -XXX,XX +XXX,XX @@ typedef struct NVICState { unsigned int vectpending; /* highest prio pending enabled exception */ int exception_prio; /* group prio of the highest prio active exception */ - struct { - uint32_t control; - uint32_t reload; - int64_t tick; - QEMUTimer *timer; - } systick; - MemoryRegion sysregmem; MemoryRegion container; uint32_t num_irq; qemu_irq excpout; qemu_irq sysresetreq; + + SysTickState systick; } NVICState; #endif diff --git a/include/hw/timer/armv7m_systick.h b/include/hw/timer/armv7m_systick.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/timer/armv7m_systick.h @@ -XXX,XX +XXX,XX @@ +/* + * ARMv7M SysTick timer + * + * Copyright (c) 2006-2007 CodeSourcery. + * Written by Paul Brook + * Copyright (c) 2017 Linaro Ltd + * Written by Peter Maydell + * + * This code is licensed under the GPL (version 2 or later). + */ + +#ifndef HW_TIMER_ARMV7M_SYSTICK_H +#define HW_TIMER_ARMV7M_SYSTICK_H + +#include "hw/sysbus.h" + +#define TYPE_SYSTICK "armv7m_systick" + +#define SYSTICK(obj) OBJECT_CHECK(SysTickState, (obj), TYPE_SYSTICK) + +typedef struct SysTickState { + /*< private >*/ + SysBusDevice parent_obj; + /*< public >*/ + + uint32_t control; + uint32_t reload; + int64_t tick; + QEMUTimer *timer; + MemoryRegion iomem; + qemu_irq irq; +} SysTickState; + +#endif diff --git a/hw/intc/armv7m_nvic.c b/hw/intc/armv7m_nvic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/armv7m_nvic.c +++ b/hw/intc/armv7m_nvic.c @@ -XXX,XX +XXX,XX @@ static const uint8_t nvic_id[] = { 0x00, 0xb0, 0x1b, 0x00, 0x0d, 0xe0, 0x05, 0xb1 }; -/* qemu timers run at 1GHz. We want something closer to 1MHz. */ -#define SYSTICK_SCALE 1000ULL - -#define SYSTICK_ENABLE (1 << 0) -#define SYSTICK_TICKINT (1 << 1) -#define SYSTICK_CLKSOURCE (1 << 2) -#define SYSTICK_COUNTFLAG (1 << 16) - -int system_clock_scale; - -/* Conversion factor from qemu timer to SysTick frequencies. */ -static inline int64_t systick_scale(NVICState *s) -{ - if (s->systick.control & SYSTICK_CLKSOURCE) - return system_clock_scale; - else - return 1000; -} - -static void systick_reload(NVICState *s, int reset) -{ - /* The Cortex-M3 Devices Generic User Guide says that "When the - * ENABLE bit is set to 1, the counter loads the RELOAD value from the - * SYST RVR register and then counts down". So, we need to check the - * ENABLE bit before reloading the value. - */ - if ((s->systick.control & SYSTICK_ENABLE) == 0) { - return; - } - - if (reset) - s->systick.tick = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - s->systick.tick += (s->systick.reload + 1) * systick_scale(s); - timer_mod(s->systick.timer, s->systick.tick); -} - -static void systick_timer_tick(void * opaque) -{ - NVICState *s = (NVICState *)opaque; - s->systick.control |= SYSTICK_COUNTFLAG; - if (s->systick.control & SYSTICK_TICKINT) { - /* Trigger the interrupt. */ - armv7m_nvic_set_pending(s, ARMV7M_EXCP_SYSTICK); - } - if (s->systick.reload == 0) { - s->systick.control &= ~SYSTICK_ENABLE; - } else { - systick_reload(s, 0); - } -} - -static void systick_reset(NVICState *s) -{ - s->systick.control = 0; - s->systick.reload = 0; - s->systick.tick = 0; - timer_del(s->systick.timer); -} - static int nvic_pending_prio(NVICState *s) { /* return the priority of the current pending interrupt, @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset) switch (offset) { case 4: /* Interrupt Control Type. */ return ((s->num_irq - NVIC_FIRST_IRQ) / 32) - 1; - case 0x10: /* SysTick Control and Status. */ - val = s->systick.control; - s->systick.control &= ~SYSTICK_COUNTFLAG; - return val; - case 0x14: /* SysTick Reload Value. */ - return s->systick.reload; - case 0x18: /* SysTick Current Value. */ - { - int64_t t; - if ((s->systick.control & SYSTICK_ENABLE) == 0) - return 0; - t = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - if (t >= s->systick.tick) - return 0; - val = ((s->systick.tick - (t + 1)) / systick_scale(s)) + 1; - /* The interrupt in triggered when the timer reaches zero. - However the counter is not reloaded until the next clock - tick. This is a hack to return zero during the first tick. */ - if (val > s->systick.reload) - val = 0; - return val; - } - case 0x1c: /* SysTick Calibration Value. */ - return 10000; case 0xd00: /* CPUID Base. */ return cpu->midr; case 0xd04: /* Interrupt Control State. */ @@ -XXX,XX +XXX,XX @@ static uint32_t nvic_readl(NVICState *s, uint32_t offset) static void nvic_writel(NVICState *s, uint32_t offset, uint32_t value) { ARMCPU *cpu = s->cpu; - uint32_t oldval; + switch (offset) { - case 0x10: /* SysTick Control and Status. */ - oldval = s->systick.control; - s->systick.control &= 0xfffffff8; - s->systick.control |= value & 7; - if ((oldval ^ value) & SYSTICK_ENABLE) { - int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); - if (value & SYSTICK_ENABLE) { - if (s->systick.tick) { - s->systick.tick += now; - timer_mod(s->systick.timer, s->systick.tick); - } else { - systick_reload(s, 1); - } - } else { - timer_del(s->systick.timer); - s->systick.tick -= now; - if (s->systick.tick < 0) - s->systick.tick = 0; - } - } else if ((oldval ^ value) & SYSTICK_CLKSOURCE) { - /* This is a hack. Force the timer to be reloaded - when the reference clock is changed. */ - systick_reload(s, 1); - } - break; - case 0x14: /* SysTick Reload Value. */ - s->systick.reload = value; - break; - case 0x18: /* SysTick Current Value. Writes reload the timer. */ - systick_reload(s, 1); - s->systick.control &= ~SYSTICK_COUNTFLAG; - break; case 0xd04: /* Interrupt Control State. */ if (value & (1 << 31)) { armv7m_nvic_set_pending(s, ARMV7M_EXCP_NMI); @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_VecInfo = { static const VMStateDescription vmstate_nvic = { .name = "armv7m_nvic", - .version_id = 3, - .minimum_version_id = 3, + .version_id = 4, + .minimum_version_id = 4, .post_load = &nvic_post_load, .fields = (VMStateField[]) { VMSTATE_STRUCT_ARRAY(vectors, NVICState, NVIC_MAX_VECTORS, 1, vmstate_VecInfo, VecInfo), - VMSTATE_UINT32(systick.control, NVICState), - VMSTATE_UINT32(systick.reload, NVICState), - VMSTATE_INT64(systick.tick, NVICState), - VMSTATE_TIMER_PTR(systick.timer, NVICState), VMSTATE_UINT32(prigroup, NVICState), VMSTATE_END_OF_LIST() } @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_reset(DeviceState *dev) s->exception_prio = NVIC_NOEXC_PRIO; s->vectpending = 0; +} - systick_reset(s); +static void nvic_systick_trigger(void *opaque, int n, int level) +{ + NVICState *s = opaque; + + if (level) { + /* SysTick just asked us to pend its exception. + * (This is different from an external interrupt line's + * behaviour.) + */ + armv7m_nvic_set_pending(s, ARMV7M_EXCP_SYSTICK); + } } static void armv7m_nvic_realize(DeviceState *dev, Error **errp) { NVICState *s = NVIC(dev); + SysBusDevice *systick_sbd; + Error *err = NULL; s->cpu = ARM_CPU(qemu_get_cpu(0)); assert(s->cpu); @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) /* include space for internal exception vectors */ s->num_irq += NVIC_FIRST_IRQ; + object_property_set_bool(OBJECT(&s->systick), true, "realized", &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } + systick_sbd = SYS_BUS_DEVICE(&s->systick); + sysbus_connect_irq(systick_sbd, 0, + qdev_get_gpio_in_named(dev, "systick-trigger", 0)); + /* The NVIC and System Control Space (SCS) starts at 0xe000e000 * and looks like this: * 0x004 - ICTR - * 0x010 - 0x1c - systick + * 0x010 - 0xff - systick * 0x100..0x7ec - NVIC * 0x7f0..0xcff - Reserved * 0xd00..0xd3c - SCS registers @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_realize(DeviceState *dev, Error **errp) memory_region_init_io(&s->sysregmem, OBJECT(s), &nvic_sysreg_ops, s, "nvic_sysregs", 0x1000); memory_region_add_subregion(&s->container, 0, &s->sysregmem); + memory_region_add_subregion_overlap(&s->container, 0x10, + sysbus_mmio_get_region(systick_sbd, 0), + 1); sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->container); - - s->systick.timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, systick_timer_tick, s); } static void armv7m_nvic_instance_init(Object *obj) @@ -XXX,XX +XXX,XX @@ static void armv7m_nvic_instance_init(Object *obj) NVICState *nvic = NVIC(obj); SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + object_initialize(&nvic->systick, sizeof(nvic->systick), TYPE_SYSTICK); + qdev_set_parent_bus(DEVICE(&nvic->systick), sysbus_get_default()); + sysbus_init_irq(sbd, &nvic->excpout); qdev_init_gpio_out_named(dev, &nvic->sysresetreq, "SYSRESETREQ", 1); + qdev_init_gpio_in_named(dev, nvic_systick_trigger, "systick-trigger", 1); } static void armv7m_nvic_class_init(ObjectClass *klass, void *data) diff --git a/hw/timer/armv7m_systick.c b/hw/timer/armv7m_systick.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/timer/armv7m_systick.c @@ -XXX,XX +XXX,XX @@ +/* + * ARMv7M SysTick timer + * + * Copyright (c) 2006-2007 CodeSourcery. + * Written by Paul Brook + * Copyright (c) 2017 Linaro Ltd + * Written by Peter Maydell + * + * This code is licensed under the GPL (version 2 or later). + */ + +#include "qemu/osdep.h" +#include "hw/timer/armv7m_systick.h" +#include "qemu-common.h" +#include "hw/sysbus.h" +#include "qemu/timer.h" +#include "qemu/log.h" +#include "trace.h" + +/* qemu timers run at 1GHz. We want something closer to 1MHz. */ +#define SYSTICK_SCALE 1000ULL + +#define SYSTICK_ENABLE (1 << 0) +#define SYSTICK_TICKINT (1 << 1) +#define SYSTICK_CLKSOURCE (1 << 2) +#define SYSTICK_COUNTFLAG (1 << 16) + +int system_clock_scale; + +/* Conversion factor from qemu timer to SysTick frequencies. */ +static inline int64_t systick_scale(SysTickState *s) +{ + if (s->control & SYSTICK_CLKSOURCE) { + return system_clock_scale; + } else { + return 1000; + } +} + +static void systick_reload(SysTickState *s, int reset) +{ + /* The Cortex-M3 Devices Generic User Guide says that "When the + * ENABLE bit is set to 1, the counter loads the RELOAD value from the + * SYST RVR register and then counts down". So, we need to check the + * ENABLE bit before reloading the value. + */ + trace_systick_reload(); + + if ((s->control & SYSTICK_ENABLE) == 0) { + return; + } + + if (reset) { + s->tick = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + } + s->tick += (s->reload + 1) * systick_scale(s); + timer_mod(s->timer, s->tick); +} + +static void systick_timer_tick(void *opaque) +{ + SysTickState *s = (SysTickState *)opaque; + + trace_systick_timer_tick(); + + s->control |= SYSTICK_COUNTFLAG; + if (s->control & SYSTICK_TICKINT) { + /* Tell the NVIC to pend the SysTick exception */ + qemu_irq_pulse(s->irq); + } + if (s->reload == 0) { + s->control &= ~SYSTICK_ENABLE; + } else { + systick_reload(s, 0); + } +} + +static uint64_t systick_read(void *opaque, hwaddr addr, unsigned size) +{ + SysTickState *s = opaque; + uint32_t val; + + switch (addr) { + case 0x0: /* SysTick Control and Status. */ + val = s->control; + s->control &= ~SYSTICK_COUNTFLAG; + break; + case 0x4: /* SysTick Reload Value. */ + val = s->reload; + break; + case 0x8: /* SysTick Current Value. */ + { + int64_t t; + + if ((s->control & SYSTICK_ENABLE) == 0) { + val = 0; + break; + } + t = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + if (t >= s->tick) { + val = 0; + break; + } + val = ((s->tick - (t + 1)) / systick_scale(s)) + 1; + /* The interrupt in triggered when the timer reaches zero. + However the counter is not reloaded until the next clock + tick. This is a hack to return zero during the first tick. */ + if (val > s->reload) { + val = 0; + } + break; + } + case 0xc: /* SysTick Calibration Value. */ + val = 10000; + break; + default: + val = 0; + qemu_log_mask(LOG_GUEST_ERROR, + "SysTick: Bad read offset 0x%" HWADDR_PRIx "\n", addr); + break; + } + + trace_systick_read(addr, val, size); + return val; +} + +static void systick_write(void *opaque, hwaddr addr, + uint64_t value, unsigned size) +{ + SysTickState *s = opaque; + + trace_systick_write(addr, value, size); + + switch (addr) { + case 0x0: /* SysTick Control and Status. */ + { + uint32_t oldval = s->control; + + s->control &= 0xfffffff8; + s->control |= value & 7; + if ((oldval ^ value) & SYSTICK_ENABLE) { + int64_t now = qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL); + if (value & SYSTICK_ENABLE) { + if (s->tick) { + s->tick += now; + timer_mod(s->timer, s->tick); + } else { + systick_reload(s, 1); + } + } else { + timer_del(s->timer); + s->tick -= now; + if (s->tick < 0) { + s->tick = 0; + } + } + } else if ((oldval ^ value) & SYSTICK_CLKSOURCE) { + /* This is a hack. Force the timer to be reloaded + when the reference clock is changed. */ + systick_reload(s, 1); + } + break; + } + case 0x4: /* SysTick Reload Value. */ + s->reload = value; + break; + case 0x8: /* SysTick Current Value. Writes reload the timer. */ + systick_reload(s, 1); + s->control &= ~SYSTICK_COUNTFLAG; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "SysTick: Bad write offset 0x%" HWADDR_PRIx "\n", addr); + } +} + +static const MemoryRegionOps systick_ops = { + .read = systick_read, + .write = systick_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid.min_access_size = 4, + .valid.max_access_size = 4, +}; + +static void systick_reset(DeviceState *dev) +{ + SysTickState *s = SYSTICK(dev); + + s->control = 0; + s->reload = 0; + s->tick = 0; + timer_del(s->timer); +} + +static void systick_instance_init(Object *obj) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + SysTickState *s = SYSTICK(obj); + + memory_region_init_io(&s->iomem, obj, &systick_ops, s, "systick", 0xe0); + sysbus_init_mmio(sbd, &s->iomem); + sysbus_init_irq(sbd, &s->irq); + s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, systick_timer_tick, s); +} + +static const VMStateDescription vmstate_systick = { + .name = "armv7m_systick", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(control, SysTickState), + VMSTATE_UINT32(reload, SysTickState), + VMSTATE_INT64(tick, SysTickState), + VMSTATE_TIMER_PTR(timer, SysTickState), + VMSTATE_END_OF_LIST() + } +}; + +static void systick_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->vmsd = &vmstate_systick; + dc->reset = systick_reset; +} + +static const TypeInfo armv7m_systick_info = { + .name = TYPE_SYSTICK, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_init = systick_instance_init, + .instance_size = sizeof(SysTickState), + .class_init = systick_class_init, +}; + +static void armv7m_systick_register_types(void) +{ + type_register_static(&armv7m_systick_info); +} + +type_init(armv7m_systick_register_types) diff --git a/hw/timer/trace-events b/hw/timer/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/timer/trace-events +++ b/hw/timer/trace-events @@ -XXX,XX +XXX,XX @@ aspeed_timer_ctrl_pulse_enable(uint8_t i, bool enable) "Timer %" PRIu8 ": %d" aspeed_timer_set_ctrl2(uint32_t value) "Value: 0x%" PRIx32 aspeed_timer_set_value(int timer, int reg, uint32_t value) "Timer %d register %d: 0x%" PRIx32 aspeed_timer_read(uint64_t offset, unsigned size, uint64_t value) "From 0x%" PRIx64 ": of size %u: 0x%" PRIx64 + +# hw/timer/armv7m_systick.c +systick_reload(void) "systick reload" +systick_timer_tick(void) "systick reload" +systick_read(uint64_t addr, uint32_t value, unsigned size) "systick read addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u" +systick_write(uint64_t addr, uint32_t value, unsigned size) "systick write addr 0x%" PRIx64 " data 0x%" PRIx32 " size %u" -- 2.7.4 Switch the stm32f205 SoC to create the armv7m object directly rather than via the armv7m_init() wrapper. This fits better with the SoC model's very QOMified design. In particular this means we can push loading the guest image out to the top level board code where it belongs, rather than the SoC object having a QOM property for the filename to load. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 1487604965-23220-11-git-send-email-peter.maydell@linaro.org --- include/hw/arm/stm32f205_soc.h | 4 +++- hw/arm/netduino2.c | 7 ++++--- hw/arm/stm32f205_soc.c | 16 +++++++++++++--- 3 files changed, 20 insertions(+), 7 deletions(-) diff --git a/include/hw/arm/stm32f205_soc.h b/include/hw/arm/stm32f205_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/stm32f205_soc.h +++ b/include/hw/arm/stm32f205_soc.h @@ -XXX,XX +XXX,XX @@ #include "hw/adc/stm32f2xx_adc.h" #include "hw/or-irq.h" #include "hw/ssi/stm32f2xx_spi.h" +#include "hw/arm/armv7m.h" #define TYPE_STM32F205_SOC "stm32f205-soc" #define STM32F205_SOC(obj) \ @@ -XXX,XX +XXX,XX @@ typedef struct STM32F205State { SysBusDevice parent_obj; /*< public >*/ - char *kernel_filename; char *cpu_model; + ARMv7MState armv7m; + STM32F2XXSyscfgState syscfg; STM32F2XXUsartState usart[STM_NUM_USARTS]; STM32F2XXTimerState timer[STM_NUM_TIMERS]; diff --git a/hw/arm/netduino2.c b/hw/arm/netduino2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/netduino2.c +++ b/hw/arm/netduino2.c @@ -XXX,XX +XXX,XX @@ #include "hw/boards.h" #include "qemu/error-report.h" #include "hw/arm/stm32f205_soc.h" +#include "hw/arm/arm.h" static void netduino2_init(MachineState *machine) { DeviceState *dev; dev = qdev_create(NULL, TYPE_STM32F205_SOC); - if (machine->kernel_filename) { - qdev_prop_set_string(dev, "kernel-filename", machine->kernel_filename); - } qdev_prop_set_string(dev, "cpu-model", "cortex-m3"); object_property_set_bool(OBJECT(dev), true, "realized", &error_fatal); + + armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, + FLASH_SIZE); } static void netduino2_machine_init(MachineClass *mc) diff --git a/hw/arm/stm32f205_soc.c b/hw/arm/stm32f205_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32f205_soc.c +++ b/hw/arm/stm32f205_soc.c @@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_initfn(Object *obj) STM32F205State *s = STM32F205_SOC(obj); int i; + object_initialize(&s->armv7m, sizeof(s->armv7m), TYPE_ARMV7M); + qdev_set_parent_bus(DEVICE(&s->armv7m), sysbus_get_default()); + object_initialize(&s->syscfg, sizeof(s->syscfg), TYPE_STM32F2XX_SYSCFG); qdev_set_parent_bus(DEVICE(&s->syscfg), sysbus_get_default()); @@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) vmstate_register_ram_global(sram); memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, sram); - nvic = armv7m_init(get_system_memory(), FLASH_SIZE, 96, - s->kernel_filename, s->cpu_model); + nvic = DEVICE(&s->armv7m); + qdev_prop_set_uint32(nvic, "num-irq", 96); + qdev_prop_set_string(nvic, "cpu-model", s->cpu_model); + object_property_set_link(OBJECT(&s->armv7m), OBJECT(get_system_memory()), + "memory", &error_abort); + object_property_set_bool(OBJECT(&s->armv7m), true, "realized", &err); + if (err != NULL) { + error_propagate(errp, err); + return; + } /* System configuration controller */ dev = DEVICE(&s->syscfg); @@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) } static Property stm32f205_soc_properties[] = { - DEFINE_PROP_STRING("kernel-filename", STM32F205State, kernel_filename), DEFINE_PROP_STRING("cpu-model", STM32F205State, cpu_model), DEFINE_PROP_END_OF_LIST(), }; -- 2.7.4 The local variable 'nvic' in stm32f205_soc_realize() no longer holds a direct pointer to the NVIC device; it is a pointer to the ARMv7M container object. Rename it 'armv7m' accordingly. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@xilinx.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 1487604965-23220-12-git-send-email-peter.maydell@linaro.org --- hw/arm/stm32f205_soc.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) diff --git a/hw/arm/stm32f205_soc.c b/hw/arm/stm32f205_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32f205_soc.c +++ b/hw/arm/stm32f205_soc.c @@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_initfn(Object *obj) static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) { STM32F205State *s = STM32F205_SOC(dev_soc); - DeviceState *dev, *nvic; + DeviceState *dev, *armv7m; SysBusDevice *busdev; Error *err = NULL; int i; @@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) vmstate_register_ram_global(sram); memory_region_add_subregion(system_memory, SRAM_BASE_ADDRESS, sram); - nvic = DEVICE(&s->armv7m); - qdev_prop_set_uint32(nvic, "num-irq", 96); - qdev_prop_set_string(nvic, "cpu-model", s->cpu_model); + armv7m = DEVICE(&s->armv7m); + qdev_prop_set_uint32(armv7m, "num-irq", 96); + qdev_prop_set_string(armv7m, "cpu-model", s->cpu_model); object_property_set_link(OBJECT(&s->armv7m), OBJECT(get_system_memory()), "memory", &error_abort); object_property_set_bool(OBJECT(&s->armv7m), true, "realized", &err); @@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) } busdev = SYS_BUS_DEVICE(dev); sysbus_mmio_map(busdev, 0, 0x40013800); - sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(nvic, 71)); + sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, 71)); /* Attach UART (uses USART registers) and USART controllers */ for (i = 0; i < STM_NUM_USARTS; i++) { @@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) } busdev = SYS_BUS_DEVICE(dev); sysbus_mmio_map(busdev, 0, usart_addr[i]); - sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(nvic, usart_irq[i])); + sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, usart_irq[i])); } /* Timer 2 to 5 */ @@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) } busdev = SYS_BUS_DEVICE(dev); sysbus_mmio_map(busdev, 0, timer_addr[i]); - sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(nvic, timer_irq[i])); + sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, timer_irq[i])); } /* ADC 1 to 3 */ @@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) return; } qdev_connect_gpio_out(DEVICE(s->adc_irqs), 0, - qdev_get_gpio_in(nvic, ADC_IRQ)); + qdev_get_gpio_in(armv7m, ADC_IRQ)); for (i = 0; i < STM_NUM_ADCS; i++) { dev = DEVICE(&(s->adc[i])); @@ -XXX,XX +XXX,XX @@ static void stm32f205_soc_realize(DeviceState *dev_soc, Error **errp) } busdev = SYS_BUS_DEVICE(dev); sysbus_mmio_map(busdev, 0, spi_addr[i]); - sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(nvic, spi_irq[i])); + sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, spi_irq[i])); } } -- 2.7.4 From: Paolo Bonzini <pbonzini@redhat.com> The linux-headers/asm-arm/unistd.h file has been split in three sub-files, copy them along. However, building them requires setting ARCH rather than SRCARCH. SRCARCH defaults to $(ARCH) anyway; to avoid future occurrence of the same problem use ARCH for all architectures where SRCARCH=ARCH. Currently these are all except x86, sparc, sh and tile. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Message-id: 20170221122920.16245-2-pbonzini@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- scripts/update-linux-headers.sh | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/scripts/update-linux-headers.sh b/scripts/update-linux-headers.sh index XXXXXXX..XXXXXXX 100755 --- a/scripts/update-linux-headers.sh +++ b/scripts/update-linux-headers.sh @@ -XXX,XX +XXX,XX @@ for arch in $ARCHLIST; do continue fi - make -C "$linux" INSTALL_HDR_PATH="$tmpdir" SRCARCH=$arch headers_install + if [ "$arch" = x86 ]; then + arch_var=SRCARCH + else + arch_var=ARCH + fi + + make -C "$linux" INSTALL_HDR_PATH="$tmpdir" $arch_var=$arch headers_install rm -rf "$output/linux-headers/asm-$arch" mkdir -p "$output/linux-headers/asm-$arch" @@ -XXX,XX +XXX,XX @@ for arch in $ARCHLIST; do cp_portable "$tmpdir/include/asm/kvm_virtio.h" "$output/include/standard-headers/asm-s390/" cp_portable "$tmpdir/include/asm/virtio-ccw.h" "$output/include/standard-headers/asm-s390/" fi + if [ $arch = arm ]; then + cp "$tmpdir/include/asm/unistd-eabi.h" "$output/linux-headers/asm-arm/" + cp "$tmpdir/include/asm/unistd-oabi.h" "$output/linux-headers/asm-arm/" + cp "$tmpdir/include/asm/unistd-common.h" "$output/linux-headers/asm-arm/" + fi if [ $arch = x86 ]; then cp_portable "$tmpdir/include/asm/hyperv.h" "$output/include/standard-headers/asm-x86/" cp "$tmpdir/include/asm/unistd_32.h" "$output/linux-headers/asm-x86/" -- 2.7.4 From: Paolo Bonzini <pbonzini@redhat.com> virtio_mmio.h would be deleted; I am leaving it in though it was a mistake to add it. Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/standard-headers/asm-x86/hyperv.h | 8 + include/standard-headers/linux/input-event-codes.h | 2 +- include/standard-headers/linux/pci_regs.h | 25 ++ include/standard-headers/linux/virtio_ids.h | 1 + linux-headers/asm-arm/kvm.h | 15 + linux-headers/asm-arm/unistd-common.h | 357 ++++++++++++++++++ linux-headers/asm-arm/unistd-eabi.h | 5 + linux-headers/asm-arm/unistd-oabi.h | 17 + linux-headers/asm-arm/unistd.h | 419 +-------------------- linux-headers/asm-arm64/kvm.h | 13 + linux-headers/asm-powerpc/kvm.h | 27 ++ linux-headers/asm-powerpc/unistd.h | 1 + linux-headers/asm-x86/kvm_para.h | 13 +- linux-headers/linux/kvm.h | 24 +- linux-headers/linux/kvm_para.h | 2 + linux-headers/linux/userfaultfd.h | 67 +++- linux-headers/linux/vfio.h | 10 + 17 files changed, 577 insertions(+), 429 deletions(-) create mode 100644 linux-headers/asm-arm/unistd-common.h create mode 100644 linux-headers/asm-arm/unistd-eabi.h create mode 100644 linux-headers/asm-arm/unistd-oabi.h diff --git a/include/standard-headers/asm-x86/hyperv.h b/include/standard-headers/asm-x86/hyperv.h index XXXXXXX..XXXXXXX 100644 --- a/include/standard-headers/asm-x86/hyperv.h +++ b/include/standard-headers/asm-x86/hyperv.h @@ -XXX,XX +XXX,XX @@ */ #define HV_X64_MSR_STAT_PAGES_AVAILABLE (1 << 8) +/* Crash MSR available */ +#define HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE (1 << 10) + /* * Feature identification: EBX indicates which flags were specified at * partition creation. The format is the same as the partition creation @@ -XXX,XX +XXX,XX @@ */ #define HV_X64_RELAXED_TIMING_RECOMMENDED (1 << 5) +/* + * Crash notification flag. + */ +#define HV_CRASH_CTL_CRASH_NOTIFY (1ULL << 63) + /* MSR used to identify the guest OS. */ #define HV_X64_MSR_GUEST_OS_ID 0x40000000 diff --git a/include/standard-headers/linux/input-event-codes.h b/include/standard-headers/linux/input-event-codes.h index XXXXXXX..XXXXXXX 100644 --- a/include/standard-headers/linux/input-event-codes.h +++ b/include/standard-headers/linux/input-event-codes.h @@ -XXX,XX +XXX,XX @@ * Control a data application associated with the currently viewed channel, * e.g. teletext or data broadcast application (MHEG, MHP, HbbTV, etc.) */ -#define KEY_DATA 0x275 +#define KEY_DATA 0x277 #define BTN_TRIGGER_HAPPY 0x2c0 #define BTN_TRIGGER_HAPPY1 0x2c0 diff --git a/include/standard-headers/linux/pci_regs.h b/include/standard-headers/linux/pci_regs.h index XXXXXXX..XXXXXXX 100644 --- a/include/standard-headers/linux/pci_regs.h +++ b/include/standard-headers/linux/pci_regs.h @@ -XXX,XX +XXX,XX @@ #define LINUX_PCI_REGS_H /* + * Conventional PCI and PCI-X Mode 1 devices have 256 bytes of + * configuration space. PCI-X Mode 2 and PCIe devices have 4096 bytes of + * configuration space. + */ +#define PCI_CFG_SPACE_SIZE 256 +#define PCI_CFG_SPACE_EXP_SIZE 4096 + +/* * Under PCI, each device has 256 bytes of configuration address space, * of which the first 64 bytes are standardized as follows: */ @@ -XXX,XX +XXX,XX @@ #define PCI_EXT_CAP_ID_PMUX 0x1A /* Protocol Multiplexing */ #define PCI_EXT_CAP_ID_PASID 0x1B /* Process Address Space ID */ #define PCI_EXT_CAP_ID_DPC 0x1D /* Downstream Port Containment */ +#define PCI_EXT_CAP_ID_L1SS 0x1E /* L1 PM Substates */ #define PCI_EXT_CAP_ID_PTM 0x1F /* Precision Time Measurement */ #define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_PTM @@ -XXX,XX +XXX,XX @@ #define PCI_EXP_DPC_STATUS 8 /* DPC Status */ #define PCI_EXP_DPC_STATUS_TRIGGER 0x01 /* Trigger Status */ #define PCI_EXP_DPC_STATUS_INTERRUPT 0x08 /* Interrupt Status */ +#define PCI_EXP_DPC_RP_BUSY 0x10 /* Root Port Busy */ #define PCI_EXP_DPC_SOURCE_ID 10 /* DPC Source Identifier */ @@ -XXX,XX +XXX,XX @@ #define PCI_PTM_CTRL_ENABLE 0x00000001 /* PTM enable */ #define PCI_PTM_CTRL_ROOT 0x00000002 /* Root select */ +/* L1 PM Substates */ +#define PCI_L1SS_CAP 4 /* capability register */ +#define PCI_L1SS_CAP_PCIPM_L1_2 1 /* PCI PM L1.2 Support */ +#define PCI_L1SS_CAP_PCIPM_L1_1 2 /* PCI PM L1.1 Support */ +#define PCI_L1SS_CAP_ASPM_L1_2 4 /* ASPM L1.2 Support */ +#define PCI_L1SS_CAP_ASPM_L1_1 8 /* ASPM L1.1 Support */ +#define PCI_L1SS_CAP_L1_PM_SS 16 /* L1 PM Substates Support */ +#define PCI_L1SS_CTL1 8 /* Control Register 1 */ +#define PCI_L1SS_CTL1_PCIPM_L1_2 1 /* PCI PM L1.2 Enable */ +#define PCI_L1SS_CTL1_PCIPM_L1_1 2 /* PCI PM L1.1 Support */ +#define PCI_L1SS_CTL1_ASPM_L1_2 4 /* ASPM L1.2 Support */ +#define PCI_L1SS_CTL1_ASPM_L1_1 8 /* ASPM L1.1 Support */ +#define PCI_L1SS_CTL1_L1SS_MASK 0x0000000F +#define PCI_L1SS_CTL2 0xC /* Control Register 2 */ + #endif /* LINUX_PCI_REGS_H */ diff --git a/include/standard-headers/linux/virtio_ids.h b/include/standard-headers/linux/virtio_ids.h index XXXXXXX..XXXXXXX 100644 --- a/include/standard-headers/linux/virtio_ids.h +++ b/include/standard-headers/linux/virtio_ids.h @@ -XXX,XX +XXX,XX @@ #define VIRTIO_ID_INPUT 18 /* virtio input */ #define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ #define VIRTIO_ID_CRYPTO 20 /* virtio crypto */ + #endif /* _LINUX_VIRTIO_IDS_H */ diff --git a/linux-headers/asm-arm/kvm.h b/linux-headers/asm-arm/kvm.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/asm-arm/kvm.h +++ b/linux-headers/asm-arm/kvm.h @@ -XXX,XX +XXX,XX @@ struct kvm_regs { /* Supported VGICv3 address types */ #define KVM_VGIC_V3_ADDR_TYPE_DIST 2 #define KVM_VGIC_V3_ADDR_TYPE_REDIST 3 +#define KVM_VGIC_ITS_ADDR_TYPE 4 #define KVM_VGIC_V3_DIST_SIZE SZ_64K #define KVM_VGIC_V3_REDIST_SIZE (2 * SZ_64K) +#define KVM_VGIC_V3_ITS_SIZE (2 * SZ_64K) #define KVM_ARM_VCPU_POWER_OFF 0 /* CPU is started in OFF state */ #define KVM_ARM_VCPU_PSCI_0_2 1 /* CPU uses PSCI v0.2 */ @@ -XXX,XX +XXX,XX @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2 #define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32 #define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT) +#define KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32 +#define KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \ + (0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT) #define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0 #define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT) +#define KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff) #define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3 #define KVM_DEV_ARM_VGIC_GRP_CTRL 4 +#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5 +#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6 +#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7 +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10 +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \ + (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff +#define VGIC_LEVEL_INFO_LINE_LEVEL 0 + #define KVM_DEV_ARM_VGIC_CTRL_INIT 0 /* KVM_IRQ_LINE irq field index values */ diff --git a/linux-headers/asm-arm/unistd-common.h b/linux-headers/asm-arm/unistd-common.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/linux-headers/asm-arm/unistd-common.h @@ -XXX,XX +XXX,XX @@ +#ifndef _ASM_ARM_UNISTD_COMMON_H +#define _ASM_ARM_UNISTD_COMMON_H 1 + +#define __NR_restart_syscall (__NR_SYSCALL_BASE + 0) +#define __NR_exit (__NR_SYSCALL_BASE + 1) +#define __NR_fork (__NR_SYSCALL_BASE + 2) +#define __NR_read (__NR_SYSCALL_BASE + 3) +#define __NR_write (__NR_SYSCALL_BASE + 4) +#define __NR_open (__NR_SYSCALL_BASE + 5) +#define __NR_close (__NR_SYSCALL_BASE + 6) +#define __NR_creat (__NR_SYSCALL_BASE + 8) +#define __NR_link (__NR_SYSCALL_BASE + 9) +#define __NR_unlink (__NR_SYSCALL_BASE + 10) +#define __NR_execve (__NR_SYSCALL_BASE + 11) +#define __NR_chdir (__NR_SYSCALL_BASE + 12) +#define __NR_mknod (__NR_SYSCALL_BASE + 14) +#define __NR_chmod (__NR_SYSCALL_BASE + 15) +#define __NR_lchown (__NR_SYSCALL_BASE + 16) +#define __NR_lseek (__NR_SYSCALL_BASE + 19) +#define __NR_getpid (__NR_SYSCALL_BASE + 20) +#define __NR_mount (__NR_SYSCALL_BASE + 21) +#define __NR_setuid (__NR_SYSCALL_BASE + 23) +#define __NR_getuid (__NR_SYSCALL_BASE + 24) +#define __NR_ptrace (__NR_SYSCALL_BASE + 26) +#define __NR_pause (__NR_SYSCALL_BASE + 29) +#define __NR_access (__NR_SYSCALL_BASE + 33) +#define __NR_nice (__NR_SYSCALL_BASE + 34) +#define __NR_sync (__NR_SYSCALL_BASE + 36) +#define __NR_kill (__NR_SYSCALL_BASE + 37) +#define __NR_rename (__NR_SYSCALL_BASE + 38) +#define __NR_mkdir (__NR_SYSCALL_BASE + 39) +#define __NR_rmdir (__NR_SYSCALL_BASE + 40) +#define __NR_dup (__NR_SYSCALL_BASE + 41) +#define __NR_pipe (__NR_SYSCALL_BASE + 42) +#define __NR_times (__NR_SYSCALL_BASE + 43) +#define __NR_brk (__NR_SYSCALL_BASE + 45) +#define __NR_setgid (__NR_SYSCALL_BASE + 46) +#define __NR_getgid (__NR_SYSCALL_BASE + 47) +#define __NR_geteuid (__NR_SYSCALL_BASE + 49) +#define __NR_getegid (__NR_SYSCALL_BASE + 50) +#define __NR_acct (__NR_SYSCALL_BASE + 51) +#define __NR_umount2 (__NR_SYSCALL_BASE + 52) +#define __NR_ioctl (__NR_SYSCALL_BASE + 54) +#define __NR_fcntl (__NR_SYSCALL_BASE + 55) +#define __NR_setpgid (__NR_SYSCALL_BASE + 57) +#define __NR_umask (__NR_SYSCALL_BASE + 60) +#define __NR_chroot (__NR_SYSCALL_BASE + 61) +#define __NR_ustat (__NR_SYSCALL_BASE + 62) +#define __NR_dup2 (__NR_SYSCALL_BASE + 63) +#define __NR_getppid (__NR_SYSCALL_BASE + 64) +#define __NR_getpgrp (__NR_SYSCALL_BASE + 65) +#define __NR_setsid (__NR_SYSCALL_BASE + 66) +#define __NR_sigaction (__NR_SYSCALL_BASE + 67) +#define __NR_setreuid (__NR_SYSCALL_BASE + 70) +#define __NR_setregid (__NR_SYSCALL_BASE + 71) +#define __NR_sigsuspend (__NR_SYSCALL_BASE + 72) +#define __NR_sigpending (__NR_SYSCALL_BASE + 73) +#define __NR_sethostname (__NR_SYSCALL_BASE + 74) +#define __NR_setrlimit (__NR_SYSCALL_BASE + 75) +#define __NR_getrusage (__NR_SYSCALL_BASE + 77) +#define __NR_gettimeofday (__NR_SYSCALL_BASE + 78) +#define __NR_settimeofday (__NR_SYSCALL_BASE + 79) +#define __NR_getgroups (__NR_SYSCALL_BASE + 80) +#define __NR_setgroups (__NR_SYSCALL_BASE + 81) +#define __NR_symlink (__NR_SYSCALL_BASE + 83) +#define __NR_readlink (__NR_SYSCALL_BASE + 85) +#define __NR_uselib (__NR_SYSCALL_BASE + 86) +#define __NR_swapon (__NR_SYSCALL_BASE + 87) +#define __NR_reboot (__NR_SYSCALL_BASE + 88) +#define __NR_munmap (__NR_SYSCALL_BASE + 91) +#define __NR_truncate (__NR_SYSCALL_BASE + 92) +#define __NR_ftruncate (__NR_SYSCALL_BASE + 93) +#define __NR_fchmod (__NR_SYSCALL_BASE + 94) +#define __NR_fchown (__NR_SYSCALL_BASE + 95) +#define __NR_getpriority (__NR_SYSCALL_BASE + 96) +#define __NR_setpriority (__NR_SYSCALL_BASE + 97) +#define __NR_statfs (__NR_SYSCALL_BASE + 99) +#define __NR_fstatfs (__NR_SYSCALL_BASE + 100) +#define __NR_syslog (__NR_SYSCALL_BASE + 103) +#define __NR_setitimer (__NR_SYSCALL_BASE + 104) +#define __NR_getitimer (__NR_SYSCALL_BASE + 105) +#define __NR_stat (__NR_SYSCALL_BASE + 106) +#define __NR_lstat (__NR_SYSCALL_BASE + 107) +#define __NR_fstat (__NR_SYSCALL_BASE + 108) +#define __NR_vhangup (__NR_SYSCALL_BASE + 111) +#define __NR_wait4 (__NR_SYSCALL_BASE + 114) +#define __NR_swapoff (__NR_SYSCALL_BASE + 115) +#define __NR_sysinfo (__NR_SYSCALL_BASE + 116) +#define __NR_fsync (__NR_SYSCALL_BASE + 118) +#define __NR_sigreturn (__NR_SYSCALL_BASE + 119) +#define __NR_clone (__NR_SYSCALL_BASE + 120) +#define __NR_setdomainname (__NR_SYSCALL_BASE + 121) +#define __NR_uname (__NR_SYSCALL_BASE + 122) +#define __NR_adjtimex (__NR_SYSCALL_BASE + 124) +#define __NR_mprotect (__NR_SYSCALL_BASE + 125) +#define __NR_sigprocmask (__NR_SYSCALL_BASE + 126) +#define __NR_init_module (__NR_SYSCALL_BASE + 128) +#define __NR_delete_module (__NR_SYSCALL_BASE + 129) +#define __NR_quotactl (__NR_SYSCALL_BASE + 131) +#define __NR_getpgid (__NR_SYSCALL_BASE + 132) +#define __NR_fchdir (__NR_SYSCALL_BASE + 133) +#define __NR_bdflush (__NR_SYSCALL_BASE + 134) +#define __NR_sysfs (__NR_SYSCALL_BASE + 135) +#define __NR_personality (__NR_SYSCALL_BASE + 136) +#define __NR_setfsuid (__NR_SYSCALL_BASE + 138) +#define __NR_setfsgid (__NR_SYSCALL_BASE + 139) +#define __NR__llseek (__NR_SYSCALL_BASE + 140) +#define __NR_getdents (__NR_SYSCALL_BASE + 141) +#define __NR__newselect (__NR_SYSCALL_BASE + 142) +#define __NR_flock (__NR_SYSCALL_BASE + 143) +#define __NR_msync (__NR_SYSCALL_BASE + 144) +#define __NR_readv (__NR_SYSCALL_BASE + 145) +#define __NR_writev (__NR_SYSCALL_BASE + 146) +#define __NR_getsid (__NR_SYSCALL_BASE + 147) +#define __NR_fdatasync (__NR_SYSCALL_BASE + 148) +#define __NR__sysctl (__NR_SYSCALL_BASE + 149) +#define __NR_mlock (__NR_SYSCALL_BASE + 150) +#define __NR_munlock (__NR_SYSCALL_BASE + 151) +#define __NR_mlockall (__NR_SYSCALL_BASE + 152) +#define __NR_munlockall (__NR_SYSCALL_BASE + 153) +#define __NR_sched_setparam (__NR_SYSCALL_BASE + 154) +#define __NR_sched_getparam (__NR_SYSCALL_BASE + 155) +#define __NR_sched_setscheduler (__NR_SYSCALL_BASE + 156) +#define __NR_sched_getscheduler (__NR_SYSCALL_BASE + 157) +#define __NR_sched_yield (__NR_SYSCALL_BASE + 158) +#define __NR_sched_get_priority_max (__NR_SYSCALL_BASE + 159) +#define __NR_sched_get_priority_min (__NR_SYSCALL_BASE + 160) +#define __NR_sched_rr_get_interval (__NR_SYSCALL_BASE + 161) +#define __NR_nanosleep (__NR_SYSCALL_BASE + 162) +#define __NR_mremap (__NR_SYSCALL_BASE + 163) +#define __NR_setresuid (__NR_SYSCALL_BASE + 164) +#define __NR_getresuid (__NR_SYSCALL_BASE + 165) +#define __NR_poll (__NR_SYSCALL_BASE + 168) +#define __NR_nfsservctl (__NR_SYSCALL_BASE + 169) +#define __NR_setresgid (__NR_SYSCALL_BASE + 170) +#define __NR_getresgid (__NR_SYSCALL_BASE + 171) +#define __NR_prctl (__NR_SYSCALL_BASE + 172) +#define __NR_rt_sigreturn (__NR_SYSCALL_BASE + 173) +#define __NR_rt_sigaction (__NR_SYSCALL_BASE + 174) +#define __NR_rt_sigprocmask (__NR_SYSCALL_BASE + 175) +#define __NR_rt_sigpending (__NR_SYSCALL_BASE + 176) +#define __NR_rt_sigtimedwait (__NR_SYSCALL_BASE + 177) +#define __NR_rt_sigqueueinfo (__NR_SYSCALL_BASE + 178) +#define __NR_rt_sigsuspend (__NR_SYSCALL_BASE + 179) +#define __NR_pread64 (__NR_SYSCALL_BASE + 180) +#define __NR_pwrite64 (__NR_SYSCALL_BASE + 181) +#define __NR_chown (__NR_SYSCALL_BASE + 182) +#define __NR_getcwd (__NR_SYSCALL_BASE + 183) +#define __NR_capget (__NR_SYSCALL_BASE + 184) +#define __NR_capset (__NR_SYSCALL_BASE + 185) +#define __NR_sigaltstack (__NR_SYSCALL_BASE + 186) +#define __NR_sendfile (__NR_SYSCALL_BASE + 187) +#define __NR_vfork (__NR_SYSCALL_BASE + 190) +#define __NR_ugetrlimit (__NR_SYSCALL_BASE + 191) +#define __NR_mmap2 (__NR_SYSCALL_BASE + 192) +#define __NR_truncate64 (__NR_SYSCALL_BASE + 193) +#define __NR_ftruncate64 (__NR_SYSCALL_BASE + 194) +#define __NR_stat64 (__NR_SYSCALL_BASE + 195) +#define __NR_lstat64 (__NR_SYSCALL_BASE + 196) +#define __NR_fstat64 (__NR_SYSCALL_BASE + 197) +#define __NR_lchown32 (__NR_SYSCALL_BASE + 198) +#define __NR_getuid32 (__NR_SYSCALL_BASE + 199) +#define __NR_getgid32 (__NR_SYSCALL_BASE + 200) +#define __NR_geteuid32 (__NR_SYSCALL_BASE + 201) +#define __NR_getegid32 (__NR_SYSCALL_BASE + 202) +#define __NR_setreuid32 (__NR_SYSCALL_BASE + 203) +#define __NR_setregid32 (__NR_SYSCALL_BASE + 204) +#define __NR_getgroups32 (__NR_SYSCALL_BASE + 205) +#define __NR_setgroups32 (__NR_SYSCALL_BASE + 206) +#define __NR_fchown32 (__NR_SYSCALL_BASE + 207) +#define __NR_setresuid32 (__NR_SYSCALL_BASE + 208) +#define __NR_getresuid32 (__NR_SYSCALL_BASE + 209) +#define __NR_setresgid32 (__NR_SYSCALL_BASE + 210) +#define __NR_getresgid32 (__NR_SYSCALL_BASE + 211) +#define __NR_chown32 (__NR_SYSCALL_BASE + 212) +#define __NR_setuid32 (__NR_SYSCALL_BASE + 213) +#define __NR_setgid32 (__NR_SYSCALL_BASE + 214) +#define __NR_setfsuid32 (__NR_SYSCALL_BASE + 215) +#define __NR_setfsgid32 (__NR_SYSCALL_BASE + 216) +#define __NR_getdents64 (__NR_SYSCALL_BASE + 217) +#define __NR_pivot_root (__NR_SYSCALL_BASE + 218) +#define __NR_mincore (__NR_SYSCALL_BASE + 219) +#define __NR_madvise (__NR_SYSCALL_BASE + 220) +#define __NR_fcntl64 (__NR_SYSCALL_BASE + 221) +#define __NR_gettid (__NR_SYSCALL_BASE + 224) +#define __NR_readahead (__NR_SYSCALL_BASE + 225) +#define __NR_setxattr (__NR_SYSCALL_BASE + 226) +#define __NR_lsetxattr (__NR_SYSCALL_BASE + 227) +#define __NR_fsetxattr (__NR_SYSCALL_BASE + 228) +#define __NR_getxattr (__NR_SYSCALL_BASE + 229) +#define __NR_lgetxattr (__NR_SYSCALL_BASE + 230) +#define __NR_fgetxattr (__NR_SYSCALL_BASE + 231) +#define __NR_listxattr (__NR_SYSCALL_BASE + 232) +#define __NR_llistxattr (__NR_SYSCALL_BASE + 233) +#define __NR_flistxattr (__NR_SYSCALL_BASE + 234) +#define __NR_removexattr (__NR_SYSCALL_BASE + 235) +#define __NR_lremovexattr (__NR_SYSCALL_BASE + 236) +#define __NR_fremovexattr (__NR_SYSCALL_BASE + 237) +#define __NR_tkill (__NR_SYSCALL_BASE + 238) +#define __NR_sendfile64 (__NR_SYSCALL_BASE + 239) +#define __NR_futex (__NR_SYSCALL_BASE + 240) +#define __NR_sched_setaffinity (__NR_SYSCALL_BASE + 241) +#define __NR_sched_getaffinity (__NR_SYSCALL_BASE + 242) +#define __NR_io_setup (__NR_SYSCALL_BASE + 243) +#define __NR_io_destroy (__NR_SYSCALL_BASE + 244) +#define __NR_io_getevents (__NR_SYSCALL_BASE + 245) +#define __NR_io_submit (__NR_SYSCALL_BASE + 246) +#define __NR_io_cancel (__NR_SYSCALL_BASE + 247) +#define __NR_exit_group (__NR_SYSCALL_BASE + 248) +#define __NR_lookup_dcookie (__NR_SYSCALL_BASE + 249) +#define __NR_epoll_create (__NR_SYSCALL_BASE + 250) +#define __NR_epoll_ctl (__NR_SYSCALL_BASE + 251) +#define __NR_epoll_wait (__NR_SYSCALL_BASE + 252) +#define __NR_remap_file_pages (__NR_SYSCALL_BASE + 253) +#define __NR_set_tid_address (__NR_SYSCALL_BASE + 256) +#define __NR_timer_create (__NR_SYSCALL_BASE + 257) +#define __NR_timer_settime (__NR_SYSCALL_BASE + 258) +#define __NR_timer_gettime (__NR_SYSCALL_BASE + 259) +#define __NR_timer_getoverrun (__NR_SYSCALL_BASE + 260) +#define __NR_timer_delete (__NR_SYSCALL_BASE + 261) +#define __NR_clock_settime (__NR_SYSCALL_BASE + 262) +#define __NR_clock_gettime (__NR_SYSCALL_BASE + 263) +#define __NR_clock_getres (__NR_SYSCALL_BASE + 264) +#define __NR_clock_nanosleep (__NR_SYSCALL_BASE + 265) +#define __NR_statfs64 (__NR_SYSCALL_BASE + 266) +#define __NR_fstatfs64 (__NR_SYSCALL_BASE + 267) +#define __NR_tgkill (__NR_SYSCALL_BASE + 268) +#define __NR_utimes (__NR_SYSCALL_BASE + 269) +#define __NR_arm_fadvise64_64 (__NR_SYSCALL_BASE + 270) +#define __NR_pciconfig_iobase (__NR_SYSCALL_BASE + 271) +#define __NR_pciconfig_read (__NR_SYSCALL_BASE + 272) +#define __NR_pciconfig_write (__NR_SYSCALL_BASE + 273) +#define __NR_mq_open (__NR_SYSCALL_BASE + 274) +#define __NR_mq_unlink (__NR_SYSCALL_BASE + 275) +#define __NR_mq_timedsend (__NR_SYSCALL_BASE + 276) +#define __NR_mq_timedreceive (__NR_SYSCALL_BASE + 277) +#define __NR_mq_notify (__NR_SYSCALL_BASE + 278) +#define __NR_mq_getsetattr (__NR_SYSCALL_BASE + 279) +#define __NR_waitid (__NR_SYSCALL_BASE + 280) +#define __NR_socket (__NR_SYSCALL_BASE + 281) +#define __NR_bind (__NR_SYSCALL_BASE + 282) +#define __NR_connect (__NR_SYSCALL_BASE + 283) +#define __NR_listen (__NR_SYSCALL_BASE + 284) +#define __NR_accept (__NR_SYSCALL_BASE + 285) +#define __NR_getsockname (__NR_SYSCALL_BASE + 286) +#define __NR_getpeername (__NR_SYSCALL_BASE + 287) +#define __NR_socketpair (__NR_SYSCALL_BASE + 288) +#define __NR_send (__NR_SYSCALL_BASE + 289) +#define __NR_sendto (__NR_SYSCALL_BASE + 290) +#define __NR_recv (__NR_SYSCALL_BASE + 291) +#define __NR_recvfrom (__NR_SYSCALL_BASE + 292) +#define __NR_shutdown (__NR_SYSCALL_BASE + 293) +#define __NR_setsockopt (__NR_SYSCALL_BASE + 294) +#define __NR_getsockopt (__NR_SYSCALL_BASE + 295) +#define __NR_sendmsg (__NR_SYSCALL_BASE + 296) +#define __NR_recvmsg (__NR_SYSCALL_BASE + 297) +#define __NR_semop (__NR_SYSCALL_BASE + 298) +#define __NR_semget (__NR_SYSCALL_BASE + 299) +#define __NR_semctl (__NR_SYSCALL_BASE + 300) +#define __NR_msgsnd (__NR_SYSCALL_BASE + 301) +#define __NR_msgrcv (__NR_SYSCALL_BASE + 302) +#define __NR_msgget (__NR_SYSCALL_BASE + 303) +#define __NR_msgctl (__NR_SYSCALL_BASE + 304) +#define __NR_shmat (__NR_SYSCALL_BASE + 305) +#define __NR_shmdt (__NR_SYSCALL_BASE + 306) +#define __NR_shmget (__NR_SYSCALL_BASE + 307) +#define __NR_shmctl (__NR_SYSCALL_BASE + 308) +#define __NR_add_key (__NR_SYSCALL_BASE + 309) +#define __NR_request_key (__NR_SYSCALL_BASE + 310) +#define __NR_keyctl (__NR_SYSCALL_BASE + 311) +#define __NR_semtimedop (__NR_SYSCALL_BASE + 312) +#define __NR_vserver (__NR_SYSCALL_BASE + 313) +#define __NR_ioprio_set (__NR_SYSCALL_BASE + 314) +#define __NR_ioprio_get (__NR_SYSCALL_BASE + 315) +#define __NR_inotify_init (__NR_SYSCALL_BASE + 316) +#define __NR_inotify_add_watch (__NR_SYSCALL_BASE + 317) +#define __NR_inotify_rm_watch (__NR_SYSCALL_BASE + 318) +#define __NR_mbind (__NR_SYSCALL_BASE + 319) +#define __NR_get_mempolicy (__NR_SYSCALL_BASE + 320) +#define __NR_set_mempolicy (__NR_SYSCALL_BASE + 321) +#define __NR_openat (__NR_SYSCALL_BASE + 322) +#define __NR_mkdirat (__NR_SYSCALL_BASE + 323) +#define __NR_mknodat (__NR_SYSCALL_BASE + 324) +#define __NR_fchownat (__NR_SYSCALL_BASE + 325) +#define __NR_futimesat (__NR_SYSCALL_BASE + 326) +#define __NR_fstatat64 (__NR_SYSCALL_BASE + 327) +#define __NR_unlinkat (__NR_SYSCALL_BASE + 328) +#define __NR_renameat (__NR_SYSCALL_BASE + 329) +#define __NR_linkat (__NR_SYSCALL_BASE + 330) +#define __NR_symlinkat (__NR_SYSCALL_BASE + 331) +#define __NR_readlinkat (__NR_SYSCALL_BASE + 332) +#define __NR_fchmodat (__NR_SYSCALL_BASE + 333) +#define __NR_faccessat (__NR_SYSCALL_BASE + 334) +#define __NR_pselect6 (__NR_SYSCALL_BASE + 335) +#define __NR_ppoll (__NR_SYSCALL_BASE + 336) +#define __NR_unshare (__NR_SYSCALL_BASE + 337) +#define __NR_set_robust_list (__NR_SYSCALL_BASE + 338) +#define __NR_get_robust_list (__NR_SYSCALL_BASE + 339) +#define __NR_splice (__NR_SYSCALL_BASE + 340) +#define __NR_arm_sync_file_range (__NR_SYSCALL_BASE + 341) +#define __NR_tee (__NR_SYSCALL_BASE + 342) +#define __NR_vmsplice (__NR_SYSCALL_BASE + 343) +#define __NR_move_pages (__NR_SYSCALL_BASE + 344) +#define __NR_getcpu (__NR_SYSCALL_BASE + 345) +#define __NR_epoll_pwait (__NR_SYSCALL_BASE + 346) +#define __NR_kexec_load (__NR_SYSCALL_BASE + 347) +#define __NR_utimensat (__NR_SYSCALL_BASE + 348) +#define __NR_signalfd (__NR_SYSCALL_BASE + 349) +#define __NR_timerfd_create (__NR_SYSCALL_BASE + 350) +#define __NR_eventfd (__NR_SYSCALL_BASE + 351) +#define __NR_fallocate (__NR_SYSCALL_BASE + 352) +#define __NR_timerfd_settime (__NR_SYSCALL_BASE + 353) +#define __NR_timerfd_gettime (__NR_SYSCALL_BASE + 354) +#define __NR_signalfd4 (__NR_SYSCALL_BASE + 355) +#define __NR_eventfd2 (__NR_SYSCALL_BASE + 356) +#define __NR_epoll_create1 (__NR_SYSCALL_BASE + 357) +#define __NR_dup3 (__NR_SYSCALL_BASE + 358) +#define __NR_pipe2 (__NR_SYSCALL_BASE + 359) +#define __NR_inotify_init1 (__NR_SYSCALL_BASE + 360) +#define __NR_preadv (__NR_SYSCALL_BASE + 361) +#define __NR_pwritev (__NR_SYSCALL_BASE + 362) +#define __NR_rt_tgsigqueueinfo (__NR_SYSCALL_BASE + 363) +#define __NR_perf_event_open (__NR_SYSCALL_BASE + 364) +#define __NR_recvmmsg (__NR_SYSCALL_BASE + 365) +#define __NR_accept4 (__NR_SYSCALL_BASE + 366) +#define __NR_fanotify_init (__NR_SYSCALL_BASE + 367) +#define __NR_fanotify_mark (__NR_SYSCALL_BASE + 368) +#define __NR_prlimit64 (__NR_SYSCALL_BASE + 369) +#define __NR_name_to_handle_at (__NR_SYSCALL_BASE + 370) +#define __NR_open_by_handle_at (__NR_SYSCALL_BASE + 371) +#define __NR_clock_adjtime (__NR_SYSCALL_BASE + 372) +#define __NR_syncfs (__NR_SYSCALL_BASE + 373) +#define __NR_sendmmsg (__NR_SYSCALL_BASE + 374) +#define __NR_setns (__NR_SYSCALL_BASE + 375) +#define __NR_process_vm_readv (__NR_SYSCALL_BASE + 376) +#define __NR_process_vm_writev (__NR_SYSCALL_BASE + 377) +#define __NR_kcmp (__NR_SYSCALL_BASE + 378) +#define __NR_finit_module (__NR_SYSCALL_BASE + 379) +#define __NR_sched_setattr (__NR_SYSCALL_BASE + 380) +#define __NR_sched_getattr (__NR_SYSCALL_BASE + 381) +#define __NR_renameat2 (__NR_SYSCALL_BASE + 382) +#define __NR_seccomp (__NR_SYSCALL_BASE + 383) +#define __NR_getrandom (__NR_SYSCALL_BASE + 384) +#define __NR_memfd_create (__NR_SYSCALL_BASE + 385) +#define __NR_bpf (__NR_SYSCALL_BASE + 386) +#define __NR_execveat (__NR_SYSCALL_BASE + 387) +#define __NR_userfaultfd (__NR_SYSCALL_BASE + 388) +#define __NR_membarrier (__NR_SYSCALL_BASE + 389) +#define __NR_mlock2 (__NR_SYSCALL_BASE + 390) +#define __NR_copy_file_range (__NR_SYSCALL_BASE + 391) +#define __NR_preadv2 (__NR_SYSCALL_BASE + 392) +#define __NR_pwritev2 (__NR_SYSCALL_BASE + 393) +#define __NR_pkey_mprotect (__NR_SYSCALL_BASE + 394) +#define __NR_pkey_alloc (__NR_SYSCALL_BASE + 395) +#define __NR_pkey_free (__NR_SYSCALL_BASE + 396) + +#endif /* _ASM_ARM_UNISTD_COMMON_H */ diff --git a/linux-headers/asm-arm/unistd-eabi.h b/linux-headers/asm-arm/unistd-eabi.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/linux-headers/asm-arm/unistd-eabi.h @@ -XXX,XX +XXX,XX @@ +#ifndef _ASM_ARM_UNISTD_EABI_H +#define _ASM_ARM_UNISTD_EABI_H 1 + + +#endif /* _ASM_ARM_UNISTD_EABI_H */ diff --git a/linux-headers/asm-arm/unistd-oabi.h b/linux-headers/asm-arm/unistd-oabi.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/linux-headers/asm-arm/unistd-oabi.h @@ -XXX,XX +XXX,XX @@ +#ifndef _ASM_ARM_UNISTD_OABI_H +#define _ASM_ARM_UNISTD_OABI_H 1 + +#define __NR_time (__NR_SYSCALL_BASE + 13) +#define __NR_umount (__NR_SYSCALL_BASE + 22) +#define __NR_stime (__NR_SYSCALL_BASE + 25) +#define __NR_alarm (__NR_SYSCALL_BASE + 27) +#define __NR_utime (__NR_SYSCALL_BASE + 30) +#define __NR_getrlimit (__NR_SYSCALL_BASE + 76) +#define __NR_select (__NR_SYSCALL_BASE + 82) +#define __NR_readdir (__NR_SYSCALL_BASE + 89) +#define __NR_mmap (__NR_SYSCALL_BASE + 90) +#define __NR_socketcall (__NR_SYSCALL_BASE + 102) +#define __NR_syscall (__NR_SYSCALL_BASE + 113) +#define __NR_ipc (__NR_SYSCALL_BASE + 117) + +#endif /* _ASM_ARM_UNISTD_OABI_H */ diff --git a/linux-headers/asm-arm/unistd.h b/linux-headers/asm-arm/unistd.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/asm-arm/unistd.h +++ b/linux-headers/asm-arm/unistd.h @@ -XXX,XX +XXX,XX @@ #if defined(__thumb__) || defined(__ARM_EABI__) #define __NR_SYSCALL_BASE 0 +#include <asm/unistd-eabi.h> #else #define __NR_SYSCALL_BASE __NR_OABI_SYSCALL_BASE +#include <asm/unistd-oabi.h> #endif -/* - * This file contains the system call numbers. - */ - -#define __NR_restart_syscall (__NR_SYSCALL_BASE+ 0) -#define __NR_exit (__NR_SYSCALL_BASE+ 1) -#define __NR_fork (__NR_SYSCALL_BASE+ 2) -#define __NR_read (__NR_SYSCALL_BASE+ 3) -#define __NR_write (__NR_SYSCALL_BASE+ 4) -#define __NR_open (__NR_SYSCALL_BASE+ 5) -#define __NR_close (__NR_SYSCALL_BASE+ 6) - /* 7 was sys_waitpid */ -#define __NR_creat (__NR_SYSCALL_BASE+ 8) -#define __NR_link (__NR_SYSCALL_BASE+ 9) -#define __NR_unlink (__NR_SYSCALL_BASE+ 10) -#define __NR_execve (__NR_SYSCALL_BASE+ 11) -#define __NR_chdir (__NR_SYSCALL_BASE+ 12) -#define __NR_time (__NR_SYSCALL_BASE+ 13) -#define __NR_mknod (__NR_SYSCALL_BASE+ 14) -#define __NR_chmod (__NR_SYSCALL_BASE+ 15) -#define __NR_lchown (__NR_SYSCALL_BASE+ 16) - /* 17 was sys_break */ - /* 18 was sys_stat */ -#define __NR_lseek (__NR_SYSCALL_BASE+ 19) -#define __NR_getpid (__NR_SYSCALL_BASE+ 20) -#define __NR_mount (__NR_SYSCALL_BASE+ 21) -#define __NR_umount (__NR_SYSCALL_BASE+ 22) -#define __NR_setuid (__NR_SYSCALL_BASE+ 23) -#define __NR_getuid (__NR_SYSCALL_BASE+ 24) -#define __NR_stime (__NR_SYSCALL_BASE+ 25) -#define __NR_ptrace (__NR_SYSCALL_BASE+ 26) -#define __NR_alarm (__NR_SYSCALL_BASE+ 27) - /* 28 was sys_fstat */ -#define __NR_pause (__NR_SYSCALL_BASE+ 29) -#define __NR_utime (__NR_SYSCALL_BASE+ 30) - /* 31 was sys_stty */ - /* 32 was sys_gtty */ -#define __NR_access (__NR_SYSCALL_BASE+ 33) -#define __NR_nice (__NR_SYSCALL_BASE+ 34) - /* 35 was sys_ftime */ -#define __NR_sync (__NR_SYSCALL_BASE+ 36) -#define __NR_kill (__NR_SYSCALL_BASE+ 37) -#define __NR_rename (__NR_SYSCALL_BASE+ 38) -#define __NR_mkdir (__NR_SYSCALL_BASE+ 39) -#define __NR_rmdir (__NR_SYSCALL_BASE+ 40) -#define __NR_dup (__NR_SYSCALL_BASE+ 41) -#define __NR_pipe (__NR_SYSCALL_BASE+ 42) -#define __NR_times (__NR_SYSCALL_BASE+ 43) - /* 44 was sys_prof */ -#define __NR_brk (__NR_SYSCALL_BASE+ 45) -#define __NR_setgid (__NR_SYSCALL_BASE+ 46) -#define __NR_getgid (__NR_SYSCALL_BASE+ 47) - /* 48 was sys_signal */ -#define __NR_geteuid (__NR_SYSCALL_BASE+ 49) -#define __NR_getegid (__NR_SYSCALL_BASE+ 50) -#define __NR_acct (__NR_SYSCALL_BASE+ 51) -#define __NR_umount2 (__NR_SYSCALL_BASE+ 52) - /* 53 was sys_lock */ -#define __NR_ioctl (__NR_SYSCALL_BASE+ 54) -#define __NR_fcntl (__NR_SYSCALL_BASE+ 55) - /* 56 was sys_mpx */ -#define __NR_setpgid (__NR_SYSCALL_BASE+ 57) - /* 58 was sys_ulimit */ - /* 59 was sys_olduname */ -#define __NR_umask (__NR_SYSCALL_BASE+ 60) -#define __NR_chroot (__NR_SYSCALL_BASE+ 61) -#define __NR_ustat (__NR_SYSCALL_BASE+ 62) -#define __NR_dup2 (__NR_SYSCALL_BASE+ 63) -#define __NR_getppid (__NR_SYSCALL_BASE+ 64) -#define __NR_getpgrp (__NR_SYSCALL_BASE+ 65) -#define __NR_setsid (__NR_SYSCALL_BASE+ 66) -#define __NR_sigaction (__NR_SYSCALL_BASE+ 67) - /* 68 was sys_sgetmask */ - /* 69 was sys_ssetmask */ -#define __NR_setreuid (__NR_SYSCALL_BASE+ 70) -#define __NR_setregid (__NR_SYSCALL_BASE+ 71) -#define __NR_sigsuspend (__NR_SYSCALL_BASE+ 72) -#define __NR_sigpending (__NR_SYSCALL_BASE+ 73) -#define __NR_sethostname (__NR_SYSCALL_BASE+ 74) -#define __NR_setrlimit (__NR_SYSCALL_BASE+ 75) -#define __NR_getrlimit (__NR_SYSCALL_BASE+ 76) /* Back compat 2GB limited rlimit */ -#define __NR_getrusage (__NR_SYSCALL_BASE+ 77) -#define __NR_gettimeofday (__NR_SYSCALL_BASE+ 78) -#define __NR_settimeofday (__NR_SYSCALL_BASE+ 79) -#define __NR_getgroups (__NR_SYSCALL_BASE+ 80) -#define __NR_setgroups (__NR_SYSCALL_BASE+ 81) -#define __NR_select (__NR_SYSCALL_BASE+ 82) -#define __NR_symlink (__NR_SYSCALL_BASE+ 83) - /* 84 was sys_lstat */ -#define __NR_readlink (__NR_SYSCALL_BASE+ 85) -#define __NR_uselib (__NR_SYSCALL_BASE+ 86) -#define __NR_swapon (__NR_SYSCALL_BASE+ 87) -#define __NR_reboot (__NR_SYSCALL_BASE+ 88) -#define __NR_readdir (__NR_SYSCALL_BASE+ 89) -#define __NR_mmap (__NR_SYSCALL_BASE+ 90) -#define __NR_munmap (__NR_SYSCALL_BASE+ 91) -#define __NR_truncate (__NR_SYSCALL_BASE+ 92) -#define __NR_ftruncate (__NR_SYSCALL_BASE+ 93) -#define __NR_fchmod (__NR_SYSCALL_BASE+ 94) -#define __NR_fchown (__NR_SYSCALL_BASE+ 95) -#define __NR_getpriority (__NR_SYSCALL_BASE+ 96) -#define __NR_setpriority (__NR_SYSCALL_BASE+ 97) - /* 98 was sys_profil */ -#define __NR_statfs (__NR_SYSCALL_BASE+ 99) -#define __NR_fstatfs (__NR_SYSCALL_BASE+100) - /* 101 was sys_ioperm */ -#define __NR_socketcall (__NR_SYSCALL_BASE+102) -#define __NR_syslog (__NR_SYSCALL_BASE+103) -#define __NR_setitimer (__NR_SYSCALL_BASE+104) -#define __NR_getitimer (__NR_SYSCALL_BASE+105) -#define __NR_stat (__NR_SYSCALL_BASE+106) -#define __NR_lstat (__NR_SYSCALL_BASE+107) -#define __NR_fstat (__NR_SYSCALL_BASE+108) - /* 109 was sys_uname */ - /* 110 was sys_iopl */ -#define __NR_vhangup (__NR_SYSCALL_BASE+111) - /* 112 was sys_idle */ -#define __NR_syscall (__NR_SYSCALL_BASE+113) /* syscall to call a syscall! */ -#define __NR_wait4 (__NR_SYSCALL_BASE+114) -#define __NR_swapoff (__NR_SYSCALL_BASE+115) -#define __NR_sysinfo (__NR_SYSCALL_BASE+116) -#define __NR_ipc (__NR_SYSCALL_BASE+117) -#define __NR_fsync (__NR_SYSCALL_BASE+118) -#define __NR_sigreturn (__NR_SYSCALL_BASE+119) -#define __NR_clone (__NR_SYSCALL_BASE+120) -#define __NR_setdomainname (__NR_SYSCALL_BASE+121) -#define __NR_uname (__NR_SYSCALL_BASE+122) - /* 123 was sys_modify_ldt */ -#define __NR_adjtimex (__NR_SYSCALL_BASE+124) -#define __NR_mprotect (__NR_SYSCALL_BASE+125) -#define __NR_sigprocmask (__NR_SYSCALL_BASE+126) - /* 127 was sys_create_module */ -#define __NR_init_module (__NR_SYSCALL_BASE+128) -#define __NR_delete_module (__NR_SYSCALL_BASE+129) - /* 130 was sys_get_kernel_syms */ -#define __NR_quotactl (__NR_SYSCALL_BASE+131) -#define __NR_getpgid (__NR_SYSCALL_BASE+132) -#define __NR_fchdir (__NR_SYSCALL_BASE+133) -#define __NR_bdflush (__NR_SYSCALL_BASE+134) -#define __NR_sysfs (__NR_SYSCALL_BASE+135) -#define __NR_personality (__NR_SYSCALL_BASE+136) - /* 137 was sys_afs_syscall */ -#define __NR_setfsuid (__NR_SYSCALL_BASE+138) -#define __NR_setfsgid (__NR_SYSCALL_BASE+139) -#define __NR__llseek (__NR_SYSCALL_BASE+140) -#define __NR_getdents (__NR_SYSCALL_BASE+141) -#define __NR__newselect (__NR_SYSCALL_BASE+142) -#define __NR_flock (__NR_SYSCALL_BASE+143) -#define __NR_msync (__NR_SYSCALL_BASE+144) -#define __NR_readv (__NR_SYSCALL_BASE+145) -#define __NR_writev (__NR_SYSCALL_BASE+146) -#define __NR_getsid (__NR_SYSCALL_BASE+147) -#define __NR_fdatasync (__NR_SYSCALL_BASE+148) -#define __NR__sysctl (__NR_SYSCALL_BASE+149) -#define __NR_mlock (__NR_SYSCALL_BASE+150) -#define __NR_munlock (__NR_SYSCALL_BASE+151) -#define __NR_mlockall (__NR_SYSCALL_BASE+152) -#define __NR_munlockall (__NR_SYSCALL_BASE+153) -#define __NR_sched_setparam (__NR_SYSCALL_BASE+154) -#define __NR_sched_getparam (__NR_SYSCALL_BASE+155) -#define __NR_sched_setscheduler (__NR_SYSCALL_BASE+156) -#define __NR_sched_getscheduler (__NR_SYSCALL_BASE+157) -#define __NR_sched_yield (__NR_SYSCALL_BASE+158) -#define __NR_sched_get_priority_max (__NR_SYSCALL_BASE+159) -#define __NR_sched_get_priority_min (__NR_SYSCALL_BASE+160) -#define __NR_sched_rr_get_interval (__NR_SYSCALL_BASE+161) -#define __NR_nanosleep (__NR_SYSCALL_BASE+162) -#define __NR_mremap (__NR_SYSCALL_BASE+163) -#define __NR_setresuid (__NR_SYSCALL_BASE+164) -#define __NR_getresuid (__NR_SYSCALL_BASE+165) - /* 166 was sys_vm86 */ - /* 167 was sys_query_module */ -#define __NR_poll (__NR_SYSCALL_BASE+168) -#define __NR_nfsservctl (__NR_SYSCALL_BASE+169) -#define __NR_setresgid (__NR_SYSCALL_BASE+170) -#define __NR_getresgid (__NR_SYSCALL_BASE+171) -#define __NR_prctl (__NR_SYSCALL_BASE+172) -#define __NR_rt_sigreturn (__NR_SYSCALL_BASE+173) -#define __NR_rt_sigaction (__NR_SYSCALL_BASE+174) -#define __NR_rt_sigprocmask (__NR_SYSCALL_BASE+175) -#define __NR_rt_sigpending (__NR_SYSCALL_BASE+176) -#define __NR_rt_sigtimedwait (__NR_SYSCALL_BASE+177) -#define __NR_rt_sigqueueinfo (__NR_SYSCALL_BASE+178) -#define __NR_rt_sigsuspend (__NR_SYSCALL_BASE+179) -#define __NR_pread64 (__NR_SYSCALL_BASE+180) -#define __NR_pwrite64 (__NR_SYSCALL_BASE+181) -#define __NR_chown (__NR_SYSCALL_BASE+182) -#define __NR_getcwd (__NR_SYSCALL_BASE+183) -#define __NR_capget (__NR_SYSCALL_BASE+184) -#define __NR_capset (__NR_SYSCALL_BASE+185) -#define __NR_sigaltstack (__NR_SYSCALL_BASE+186) -#define __NR_sendfile (__NR_SYSCALL_BASE+187) - /* 188 reserved */ - /* 189 reserved */ -#define __NR_vfork (__NR_SYSCALL_BASE+190) -#define __NR_ugetrlimit (__NR_SYSCALL_BASE+191) /* SuS compliant getrlimit */ -#define __NR_mmap2 (__NR_SYSCALL_BASE+192) -#define __NR_truncate64 (__NR_SYSCALL_BASE+193) -#define __NR_ftruncate64 (__NR_SYSCALL_BASE+194) -#define __NR_stat64 (__NR_SYSCALL_BASE+195) -#define __NR_lstat64 (__NR_SYSCALL_BASE+196) -#define __NR_fstat64 (__NR_SYSCALL_BASE+197) -#define __NR_lchown32 (__NR_SYSCALL_BASE+198) -#define __NR_getuid32 (__NR_SYSCALL_BASE+199) -#define __NR_getgid32 (__NR_SYSCALL_BASE+200) -#define __NR_geteuid32 (__NR_SYSCALL_BASE+201) -#define __NR_getegid32 (__NR_SYSCALL_BASE+202) -#define __NR_setreuid32 (__NR_SYSCALL_BASE+203) -#define __NR_setregid32 (__NR_SYSCALL_BASE+204) -#define __NR_getgroups32 (__NR_SYSCALL_BASE+205) -#define __NR_setgroups32 (__NR_SYSCALL_BASE+206) -#define __NR_fchown32 (__NR_SYSCALL_BASE+207) -#define __NR_setresuid32 (__NR_SYSCALL_BASE+208) -#define __NR_getresuid32 (__NR_SYSCALL_BASE+209) -#define __NR_setresgid32 (__NR_SYSCALL_BASE+210) -#define __NR_getresgid32 (__NR_SYSCALL_BASE+211) -#define __NR_chown32 (__NR_SYSCALL_BASE+212) -#define __NR_setuid32 (__NR_SYSCALL_BASE+213) -#define __NR_setgid32 (__NR_SYSCALL_BASE+214) -#define __NR_setfsuid32 (__NR_SYSCALL_BASE+215) -#define __NR_setfsgid32 (__NR_SYSCALL_BASE+216) -#define __NR_getdents64 (__NR_SYSCALL_BASE+217) -#define __NR_pivot_root (__NR_SYSCALL_BASE+218) -#define __NR_mincore (__NR_SYSCALL_BASE+219) -#define __NR_madvise (__NR_SYSCALL_BASE+220) -#define __NR_fcntl64 (__NR_SYSCALL_BASE+221) - /* 222 for tux */ - /* 223 is unused */ -#define __NR_gettid (__NR_SYSCALL_BASE+224) -#define __NR_readahead (__NR_SYSCALL_BASE+225) -#define __NR_setxattr (__NR_SYSCALL_BASE+226) -#define __NR_lsetxattr (__NR_SYSCALL_BASE+227) -#define __NR_fsetxattr (__NR_SYSCALL_BASE+228) -#define __NR_getxattr (__NR_SYSCALL_BASE+229) -#define __NR_lgetxattr (__NR_SYSCALL_BASE+230) -#define __NR_fgetxattr (__NR_SYSCALL_BASE+231) -#define __NR_listxattr (__NR_SYSCALL_BASE+232) -#define __NR_llistxattr (__NR_SYSCALL_BASE+233) -#define __NR_flistxattr (__NR_SYSCALL_BASE+234) -#define __NR_removexattr (__NR_SYSCALL_BASE+235) -#define __NR_lremovexattr (__NR_SYSCALL_BASE+236) -#define __NR_fremovexattr (__NR_SYSCALL_BASE+237) -#define __NR_tkill (__NR_SYSCALL_BASE+238) -#define __NR_sendfile64 (__NR_SYSCALL_BASE+239) -#define __NR_futex (__NR_SYSCALL_BASE+240) -#define __NR_sched_setaffinity (__NR_SYSCALL_BASE+241) -#define __NR_sched_getaffinity (__NR_SYSCALL_BASE+242) -#define __NR_io_setup (__NR_SYSCALL_BASE+243) -#define __NR_io_destroy (__NR_SYSCALL_BASE+244) -#define __NR_io_getevents (__NR_SYSCALL_BASE+245) -#define __NR_io_submit (__NR_SYSCALL_BASE+246) -#define __NR_io_cancel (__NR_SYSCALL_BASE+247) -#define __NR_exit_group (__NR_SYSCALL_BASE+248) -#define __NR_lookup_dcookie (__NR_SYSCALL_BASE+249) -#define __NR_epoll_create (__NR_SYSCALL_BASE+250) -#define __NR_epoll_ctl (__NR_SYSCALL_BASE+251) -#define __NR_epoll_wait (__NR_SYSCALL_BASE+252) -#define __NR_remap_file_pages (__NR_SYSCALL_BASE+253) - /* 254 for set_thread_area */ - /* 255 for get_thread_area */ -#define __NR_set_tid_address (__NR_SYSCALL_BASE+256) -#define __NR_timer_create (__NR_SYSCALL_BASE+257) -#define __NR_timer_settime (__NR_SYSCALL_BASE+258) -#define __NR_timer_gettime (__NR_SYSCALL_BASE+259) -#define __NR_timer_getoverrun (__NR_SYSCALL_BASE+260) -#define __NR_timer_delete (__NR_SYSCALL_BASE+261) -#define __NR_clock_settime (__NR_SYSCALL_BASE+262) -#define __NR_clock_gettime (__NR_SYSCALL_BASE+263) -#define __NR_clock_getres (__NR_SYSCALL_BASE+264) -#define __NR_clock_nanosleep (__NR_SYSCALL_BASE+265) -#define __NR_statfs64 (__NR_SYSCALL_BASE+266) -#define __NR_fstatfs64 (__NR_SYSCALL_BASE+267) -#define __NR_tgkill (__NR_SYSCALL_BASE+268) -#define __NR_utimes (__NR_SYSCALL_BASE+269) -#define __NR_arm_fadvise64_64 (__NR_SYSCALL_BASE+270) -#define __NR_pciconfig_iobase (__NR_SYSCALL_BASE+271) -#define __NR_pciconfig_read (__NR_SYSCALL_BASE+272) -#define __NR_pciconfig_write (__NR_SYSCALL_BASE+273) -#define __NR_mq_open (__NR_SYSCALL_BASE+274) -#define __NR_mq_unlink (__NR_SYSCALL_BASE+275) -#define __NR_mq_timedsend (__NR_SYSCALL_BASE+276) -#define __NR_mq_timedreceive (__NR_SYSCALL_BASE+277) -#define __NR_mq_notify (__NR_SYSCALL_BASE+278) -#define __NR_mq_getsetattr (__NR_SYSCALL_BASE+279) -#define __NR_waitid (__NR_SYSCALL_BASE+280) -#define __NR_socket (__NR_SYSCALL_BASE+281) -#define __NR_bind (__NR_SYSCALL_BASE+282) -#define __NR_connect (__NR_SYSCALL_BASE+283) -#define __NR_listen (__NR_SYSCALL_BASE+284) -#define __NR_accept (__NR_SYSCALL_BASE+285) -#define __NR_getsockname (__NR_SYSCALL_BASE+286) -#define __NR_getpeername (__NR_SYSCALL_BASE+287) -#define __NR_socketpair (__NR_SYSCALL_BASE+288) -#define __NR_send (__NR_SYSCALL_BASE+289) -#define __NR_sendto (__NR_SYSCALL_BASE+290) -#define __NR_recv (__NR_SYSCALL_BASE+291) -#define __NR_recvfrom (__NR_SYSCALL_BASE+292) -#define __NR_shutdown (__NR_SYSCALL_BASE+293) -#define __NR_setsockopt (__NR_SYSCALL_BASE+294) -#define __NR_getsockopt (__NR_SYSCALL_BASE+295) -#define __NR_sendmsg (__NR_SYSCALL_BASE+296) -#define __NR_recvmsg (__NR_SYSCALL_BASE+297) -#define __NR_semop (__NR_SYSCALL_BASE+298) -#define __NR_semget (__NR_SYSCALL_BASE+299) -#define __NR_semctl (__NR_SYSCALL_BASE+300) -#define __NR_msgsnd (__NR_SYSCALL_BASE+301) -#define __NR_msgrcv (__NR_SYSCALL_BASE+302) -#define __NR_msgget (__NR_SYSCALL_BASE+303) -#define __NR_msgctl (__NR_SYSCALL_BASE+304) -#define __NR_shmat (__NR_SYSCALL_BASE+305) -#define __NR_shmdt (__NR_SYSCALL_BASE+306) -#define __NR_shmget (__NR_SYSCALL_BASE+307) -#define __NR_shmctl (__NR_SYSCALL_BASE+308) -#define __NR_add_key (__NR_SYSCALL_BASE+309) -#define __NR_request_key (__NR_SYSCALL_BASE+310) -#define __NR_keyctl (__NR_SYSCALL_BASE+311) -#define __NR_semtimedop (__NR_SYSCALL_BASE+312) -#define __NR_vserver (__NR_SYSCALL_BASE+313) -#define __NR_ioprio_set (__NR_SYSCALL_BASE+314) -#define __NR_ioprio_get (__NR_SYSCALL_BASE+315) -#define __NR_inotify_init (__NR_SYSCALL_BASE+316) -#define __NR_inotify_add_watch (__NR_SYSCALL_BASE+317) -#define __NR_inotify_rm_watch (__NR_SYSCALL_BASE+318) -#define __NR_mbind (__NR_SYSCALL_BASE+319) -#define __NR_get_mempolicy (__NR_SYSCALL_BASE+320) -#define __NR_set_mempolicy (__NR_SYSCALL_BASE+321) -#define __NR_openat (__NR_SYSCALL_BASE+322) -#define __NR_mkdirat (__NR_SYSCALL_BASE+323) -#define __NR_mknodat (__NR_SYSCALL_BASE+324) -#define __NR_fchownat (__NR_SYSCALL_BASE+325) -#define __NR_futimesat (__NR_SYSCALL_BASE+326) -#define __NR_fstatat64 (__NR_SYSCALL_BASE+327) -#define __NR_unlinkat (__NR_SYSCALL_BASE+328) -#define __NR_renameat (__NR_SYSCALL_BASE+329) -#define __NR_linkat (__NR_SYSCALL_BASE+330) -#define __NR_symlinkat (__NR_SYSCALL_BASE+331) -#define __NR_readlinkat (__NR_SYSCALL_BASE+332) -#define __NR_fchmodat (__NR_SYSCALL_BASE+333) -#define __NR_faccessat (__NR_SYSCALL_BASE+334) -#define __NR_pselect6 (__NR_SYSCALL_BASE+335) -#define __NR_ppoll (__NR_SYSCALL_BASE+336) -#define __NR_unshare (__NR_SYSCALL_BASE+337) -#define __NR_set_robust_list (__NR_SYSCALL_BASE+338) -#define __NR_get_robust_list (__NR_SYSCALL_BASE+339) -#define __NR_splice (__NR_SYSCALL_BASE+340) -#define __NR_arm_sync_file_range (__NR_SYSCALL_BASE+341) +#include <asm/unistd-common.h> #define __NR_sync_file_range2 __NR_arm_sync_file_range -#define __NR_tee (__NR_SYSCALL_BASE+342) -#define __NR_vmsplice (__NR_SYSCALL_BASE+343) -#define __NR_move_pages (__NR_SYSCALL_BASE+344) -#define __NR_getcpu (__NR_SYSCALL_BASE+345) -#define __NR_epoll_pwait (__NR_SYSCALL_BASE+346) -#define __NR_kexec_load (__NR_SYSCALL_BASE+347) -#define __NR_utimensat (__NR_SYSCALL_BASE+348) -#define __NR_signalfd (__NR_SYSCALL_BASE+349) -#define __NR_timerfd_create (__NR_SYSCALL_BASE+350) -#define __NR_eventfd (__NR_SYSCALL_BASE+351) -#define __NR_fallocate (__NR_SYSCALL_BASE+352) -#define __NR_timerfd_settime (__NR_SYSCALL_BASE+353) -#define __NR_timerfd_gettime (__NR_SYSCALL_BASE+354) -#define __NR_signalfd4 (__NR_SYSCALL_BASE+355) -#define __NR_eventfd2 (__NR_SYSCALL_BASE+356) -#define __NR_epoll_create1 (__NR_SYSCALL_BASE+357) -#define __NR_dup3 (__NR_SYSCALL_BASE+358) -#define __NR_pipe2 (__NR_SYSCALL_BASE+359) -#define __NR_inotify_init1 (__NR_SYSCALL_BASE+360) -#define __NR_preadv (__NR_SYSCALL_BASE+361) -#define __NR_pwritev (__NR_SYSCALL_BASE+362) -#define __NR_rt_tgsigqueueinfo (__NR_SYSCALL_BASE+363) -#define __NR_perf_event_open (__NR_SYSCALL_BASE+364) -#define __NR_recvmmsg (__NR_SYSCALL_BASE+365) -#define __NR_accept4 (__NR_SYSCALL_BASE+366) -#define __NR_fanotify_init (__NR_SYSCALL_BASE+367) -#define __NR_fanotify_mark (__NR_SYSCALL_BASE+368) -#define __NR_prlimit64 (__NR_SYSCALL_BASE+369) -#define __NR_name_to_handle_at (__NR_SYSCALL_BASE+370) -#define __NR_open_by_handle_at (__NR_SYSCALL_BASE+371) -#define __NR_clock_adjtime (__NR_SYSCALL_BASE+372) -#define __NR_syncfs (__NR_SYSCALL_BASE+373) -#define __NR_sendmmsg (__NR_SYSCALL_BASE+374) -#define __NR_setns (__NR_SYSCALL_BASE+375) -#define __NR_process_vm_readv (__NR_SYSCALL_BASE+376) -#define __NR_process_vm_writev (__NR_SYSCALL_BASE+377) -#define __NR_kcmp (__NR_SYSCALL_BASE+378) -#define __NR_finit_module (__NR_SYSCALL_BASE+379) -#define __NR_sched_setattr (__NR_SYSCALL_BASE+380) -#define __NR_sched_getattr (__NR_SYSCALL_BASE+381) -#define __NR_renameat2 (__NR_SYSCALL_BASE+382) -#define __NR_seccomp (__NR_SYSCALL_BASE+383) -#define __NR_getrandom (__NR_SYSCALL_BASE+384) -#define __NR_memfd_create (__NR_SYSCALL_BASE+385) -#define __NR_bpf (__NR_SYSCALL_BASE+386) -#define __NR_execveat (__NR_SYSCALL_BASE+387) -#define __NR_userfaultfd (__NR_SYSCALL_BASE+388) -#define __NR_membarrier (__NR_SYSCALL_BASE+389) -#define __NR_mlock2 (__NR_SYSCALL_BASE+390) -#define __NR_copy_file_range (__NR_SYSCALL_BASE+391) -#define __NR_preadv2 (__NR_SYSCALL_BASE+392) -#define __NR_pwritev2 (__NR_SYSCALL_BASE+393) /* * The following SWIs are ARM private. @@ -XXX,XX +XXX,XX @@ #define __ARM_NR_usr32 (__ARM_NR_BASE+4) #define __ARM_NR_set_tls (__ARM_NR_BASE+5) -/* - * The following syscalls are obsolete and no longer available for EABI. - */ -#if defined(__ARM_EABI__) -#undef __NR_time -#undef __NR_umount -#undef __NR_stime -#undef __NR_alarm -#undef __NR_utime -#undef __NR_getrlimit -#undef __NR_select -#undef __NR_readdir -#undef __NR_mmap -#undef __NR_socketcall -#undef __NR_syscall -#undef __NR_ipc -#endif - #endif /* __ASM_ARM_UNISTD_H */ diff --git a/linux-headers/asm-arm64/kvm.h b/linux-headers/asm-arm64/kvm.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/asm-arm64/kvm.h +++ b/linux-headers/asm-arm64/kvm.h @@ -XXX,XX +XXX,XX @@ struct kvm_arch_memory_slot { #define KVM_DEV_ARM_VGIC_GRP_CPU_REGS 2 #define KVM_DEV_ARM_VGIC_CPUID_SHIFT 32 #define KVM_DEV_ARM_VGIC_CPUID_MASK (0xffULL << KVM_DEV_ARM_VGIC_CPUID_SHIFT) +#define KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT 32 +#define KVM_DEV_ARM_VGIC_V3_MPIDR_MASK \ + (0xffffffffULL << KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT) #define KVM_DEV_ARM_VGIC_OFFSET_SHIFT 0 #define KVM_DEV_ARM_VGIC_OFFSET_MASK (0xffffffffULL << KVM_DEV_ARM_VGIC_OFFSET_SHIFT) +#define KVM_DEV_ARM_VGIC_SYSREG_INSTR_MASK (0xffff) #define KVM_DEV_ARM_VGIC_GRP_NR_IRQS 3 #define KVM_DEV_ARM_VGIC_GRP_CTRL 4 +#define KVM_DEV_ARM_VGIC_GRP_REDIST_REGS 5 +#define KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS 6 +#define KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO 7 +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT 10 +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK \ + (0x3fffffULL << KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) +#define KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK 0x3ff +#define VGIC_LEVEL_INFO_LINE_LEVEL 0 + #define KVM_DEV_ARM_VGIC_CTRL_INIT 0 /* Device Control API on vcpu fd */ diff --git a/linux-headers/asm-powerpc/kvm.h b/linux-headers/asm-powerpc/kvm.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/asm-powerpc/kvm.h +++ b/linux-headers/asm-powerpc/kvm.h @@ -XXX,XX +XXX,XX @@ struct kvm_get_htab_header { __u16 n_invalid; }; +/* For KVM_PPC_CONFIGURE_V3_MMU */ +struct kvm_ppc_mmuv3_cfg { + __u64 flags; + __u64 process_table; /* second doubleword of partition table entry */ +}; + +/* Flag values for KVM_PPC_CONFIGURE_V3_MMU */ +#define KVM_PPC_MMUV3_RADIX 1 /* 1 = radix mode, 0 = HPT */ +#define KVM_PPC_MMUV3_GTSE 2 /* global translation shootdown enb. */ + +/* For KVM_PPC_GET_RMMU_INFO */ +struct kvm_ppc_rmmu_info { + struct kvm_ppc_radix_geom { + __u8 page_shift; + __u8 level_bits[4]; + __u8 pad[3]; + } geometries[8]; + __u32 ap_encodings[8]; +}; + /* Per-vcpu XICS interrupt controller state */ #define KVM_REG_PPC_ICP_STATE (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0x8c) @@ -XXX,XX +XXX,XX @@ struct kvm_get_htab_header { #define KVM_REG_PPC_SPRG9 (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xba) #define KVM_REG_PPC_DBSR (KVM_REG_PPC | KVM_REG_SIZE_U32 | 0xbb) +/* POWER9 registers */ +#define KVM_REG_PPC_TIDR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc) +#define KVM_REG_PPC_PSSCR (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd) + /* Transactional Memory checkpointed state: * This is all GPRs, all VSX regs and a subset of SPRs */ @@ -XXX,XX +XXX,XX @@ struct kvm_get_htab_header { #define KVM_REG_PPC_TM_VSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U32 | 0x67) #define KVM_REG_PPC_TM_DSCR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x68) #define KVM_REG_PPC_TM_TAR (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x69) +#define KVM_REG_PPC_TM_XER (KVM_REG_PPC_TM | KVM_REG_SIZE_U64 | 0x6a) /* PPC64 eXternal Interrupt Controller Specification */ #define KVM_DEV_XICS_GRP_SOURCES 1 /* 64-bit source attributes */ @@ -XXX,XX +XXX,XX @@ struct kvm_get_htab_header { #define KVM_XICS_LEVEL_SENSITIVE (1ULL << 40) #define KVM_XICS_MASKED (1ULL << 41) #define KVM_XICS_PENDING (1ULL << 42) +#define KVM_XICS_PRESENTED (1ULL << 43) +#define KVM_XICS_QUEUED (1ULL << 44) #endif /* __LINUX_KVM_POWERPC_H */ diff --git a/linux-headers/asm-powerpc/unistd.h b/linux-headers/asm-powerpc/unistd.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/asm-powerpc/unistd.h +++ b/linux-headers/asm-powerpc/unistd.h @@ -XXX,XX +XXX,XX @@ #define __NR_copy_file_range 379 #define __NR_preadv2 380 #define __NR_pwritev2 381 +#define __NR_kexec_file_load 382 #endif /* _ASM_POWERPC_UNISTD_H_ */ diff --git a/linux-headers/asm-x86/kvm_para.h b/linux-headers/asm-x86/kvm_para.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/asm-x86/kvm_para.h +++ b/linux-headers/asm-x86/kvm_para.h @@ -XXX,XX +XXX,XX @@ struct kvm_steal_time { __u64 steal; __u32 version; __u32 flags; - __u32 pad[12]; + __u8 preempted; + __u8 u8_pad[3]; + __u32 pad[11]; +}; + +#define KVM_CLOCK_PAIRING_WALLCLOCK 0 +struct kvm_clock_pairing { + __s64 sec; + __s64 nsec; + __u64 tsc; + __u32 flags; + __u32 pad[9]; }; #define KVM_STEAL_ALIGNMENT_BITS 5 diff --git a/linux-headers/linux/kvm.h b/linux-headers/linux/kvm.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/linux/kvm.h +++ b/linux-headers/linux/kvm.h @@ -XXX,XX +XXX,XX @@ struct kvm_hyperv_exit { struct kvm_run { /* in */ __u8 request_interrupt_window; - __u8 padding1[7]; + __u8 immediate_exit; + __u8 padding1[6]; /* out */ __u32 exit_reason; @@ -XXX,XX +XXX,XX @@ struct kvm_enable_cap { }; /* for KVM_PPC_GET_PVINFO */ + +#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) + struct kvm_ppc_pvinfo { /* out */ __u32 flags; @@ -XXX,XX +XXX,XX @@ struct kvm_ppc_smmu_info { struct kvm_ppc_one_seg_page_size sps[KVM_PPC_PAGE_SIZES_MAX_SZ]; }; -#define KVM_PPC_PVINFO_FLAGS_EV_IDLE (1<<0) +/* for KVM_PPC_RESIZE_HPT_{PREPARE,COMMIT} */ +struct kvm_ppc_resize_hpt { + __u64 flags; + __u32 shift; + __u32 pad; +}; #define KVMIO 0xAE @@ -XXX,XX +XXX,XX @@ struct kvm_ppc_smmu_info { #define KVM_CAP_S390_USER_INSTR0 130 #define KVM_CAP_MSI_DEVID 131 #define KVM_CAP_PPC_HTM 132 +#define KVM_CAP_SPAPR_RESIZE_HPT 133 +#define KVM_CAP_PPC_MMU_RADIX 134 +#define KVM_CAP_PPC_MMU_HASH_V3 135 +#define KVM_CAP_IMMEDIATE_EXIT 136 #ifdef KVM_CAP_IRQ_ROUTING @@ -XXX,XX +XXX,XX @@ struct kvm_s390_ucas_mapping { #define KVM_ARM_SET_DEVICE_ADDR _IOW(KVMIO, 0xab, struct kvm_arm_device_addr) /* Available with KVM_CAP_PPC_RTAS */ #define KVM_PPC_RTAS_DEFINE_TOKEN _IOW(KVMIO, 0xac, struct kvm_rtas_token_args) +/* Available with KVM_CAP_SPAPR_RESIZE_HPT */ +#define KVM_PPC_RESIZE_HPT_PREPARE _IOR(KVMIO, 0xad, struct kvm_ppc_resize_hpt) +#define KVM_PPC_RESIZE_HPT_COMMIT _IOR(KVMIO, 0xae, struct kvm_ppc_resize_hpt) +/* Available with KVM_CAP_PPC_RADIX_MMU or KVM_CAP_PPC_HASH_MMU_V3 */ +#define KVM_PPC_CONFIGURE_V3_MMU _IOW(KVMIO, 0xaf, struct kvm_ppc_mmuv3_cfg) +/* Available with KVM_CAP_PPC_RADIX_MMU */ +#define KVM_PPC_GET_RMMU_INFO _IOW(KVMIO, 0xb0, struct kvm_ppc_rmmu_info) /* ioctl for vm fd */ #define KVM_CREATE_DEVICE _IOWR(KVMIO, 0xe0, struct kvm_create_device) diff --git a/linux-headers/linux/kvm_para.h b/linux-headers/linux/kvm_para.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/linux/kvm_para.h +++ b/linux-headers/linux/kvm_para.h @@ -XXX,XX +XXX,XX @@ #define KVM_EFAULT EFAULT #define KVM_E2BIG E2BIG #define KVM_EPERM EPERM +#define KVM_EOPNOTSUPP 95 #define KVM_HC_VAPIC_POLL_IRQ 1 #define KVM_HC_MMU_OP 2 @@ -XXX,XX +XXX,XX @@ #define KVM_HC_MIPS_GET_CLOCK_FREQ 6 #define KVM_HC_MIPS_EXIT_VM 7 #define KVM_HC_MIPS_CONSOLE_OUTPUT 8 +#define KVM_HC_CLOCK_PAIRING 9 /* * hypercalls use architecture specific diff --git a/linux-headers/linux/userfaultfd.h b/linux-headers/linux/userfaultfd.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/linux/userfaultfd.h +++ b/linux-headers/linux/userfaultfd.h @@ -XXX,XX +XXX,XX @@ #include <linux/types.h> -#define UFFD_API ((__u64)0xAA) /* - * After implementing the respective features it will become: - * #define UFFD_API_FEATURES (UFFD_FEATURE_PAGEFAULT_FLAG_WP | \ - * UFFD_FEATURE_EVENT_FORK) + * If the UFFDIO_API is upgraded someday, the UFFDIO_UNREGISTER and + * UFFDIO_WAKE ioctls should be defined as _IOW and not as _IOR. In + * userfaultfd.h we assumed the kernel was reading (instead _IOC_READ + * means the userland is reading). */ -#define UFFD_API_FEATURES (0) +#define UFFD_API ((__u64)0xAA) +#define UFFD_API_FEATURES (UFFD_FEATURE_EVENT_FORK | \ + UFFD_FEATURE_EVENT_REMAP | \ + UFFD_FEATURE_EVENT_MADVDONTNEED | \ + UFFD_FEATURE_MISSING_HUGETLBFS | \ + UFFD_FEATURE_MISSING_SHMEM) #define UFFD_API_IOCTLS \ ((__u64)1 << _UFFDIO_REGISTER | \ (__u64)1 << _UFFDIO_UNREGISTER | \ @@ -XXX,XX +XXX,XX @@ ((__u64)1 << _UFFDIO_WAKE | \ (__u64)1 << _UFFDIO_COPY | \ (__u64)1 << _UFFDIO_ZEROPAGE) +#define UFFD_API_RANGE_IOCTLS_BASIC \ + ((__u64)1 << _UFFDIO_WAKE | \ + (__u64)1 << _UFFDIO_COPY) /* * Valid ioctl command number range with this API is from 0x00 to @@ -XXX,XX +XXX,XX @@ struct uffd_msg { } pagefault; struct { + __u32 ufd; + } fork; + + struct { + __u64 from; + __u64 to; + __u64 len; + } remap; + + struct { + __u64 start; + __u64 end; + } madv_dn; + + struct { /* unused reserved fields */ __u64 reserved1; __u64 reserved2; @@ -XXX,XX +XXX,XX @@ struct uffd_msg { * Start at 0x12 and not at 0 to be more strict against bugs. */ #define UFFD_EVENT_PAGEFAULT 0x12 -#if 0 /* not available yet */ #define UFFD_EVENT_FORK 0x13 -#endif +#define UFFD_EVENT_REMAP 0x14 +#define UFFD_EVENT_MADVDONTNEED 0x15 /* flags for UFFD_EVENT_PAGEFAULT */ #define UFFD_PAGEFAULT_FLAG_WRITE (1<<0) /* If this was a write fault */ @@ -XXX,XX +XXX,XX @@ struct uffdio_api { * Note: UFFD_EVENT_PAGEFAULT and UFFD_PAGEFAULT_FLAG_WRITE * are to be considered implicitly always enabled in all kernels as * long as the uffdio_api.api requested matches UFFD_API. + * + * UFFD_FEATURE_MISSING_HUGETLBFS means an UFFDIO_REGISTER + * with UFFDIO_REGISTER_MODE_MISSING mode will succeed on + * hugetlbfs virtual memory ranges. Adding or not adding + * UFFD_FEATURE_MISSING_HUGETLBFS to uffdio_api.features has + * no real functional effect after UFFDIO_API returns, but + * it's only useful for an initial feature set probe at + * UFFDIO_API time. There are two ways to use it: + * + * 1) by adding UFFD_FEATURE_MISSING_HUGETLBFS to the + * uffdio_api.features before calling UFFDIO_API, an error + * will be returned by UFFDIO_API on a kernel without + * hugetlbfs missing support + * + * 2) the UFFD_FEATURE_MISSING_HUGETLBFS can not be added in + * uffdio_api.features and instead it will be set by the + * kernel in the uffdio_api.features if the kernel supports + * it, so userland can later check if the feature flag is + * present in uffdio_api.features after UFFDIO_API + * succeeded. + * + * UFFD_FEATURE_MISSING_SHMEM works the same as + * UFFD_FEATURE_MISSING_HUGETLBFS, but it applies to shmem + * (i.e. tmpfs and other shmem based APIs). */ -#if 0 /* not available yet */ #define UFFD_FEATURE_PAGEFAULT_FLAG_WP (1<<0) #define UFFD_FEATURE_EVENT_FORK (1<<1) -#endif +#define UFFD_FEATURE_EVENT_REMAP (1<<2) +#define UFFD_FEATURE_EVENT_MADVDONTNEED (1<<3) +#define UFFD_FEATURE_MISSING_HUGETLBFS (1<<4) +#define UFFD_FEATURE_MISSING_SHMEM (1<<5) __u64 features; __u64 ioctls; diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h index XXXXXXX..XXXXXXX 100644 --- a/linux-headers/linux/vfio.h +++ b/linux-headers/linux/vfio.h @@ -XXX,XX +XXX,XX @@ struct vfio_device_info { }; #define VFIO_DEVICE_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 7) +/* + * Vendor driver using Mediated device framework should provide device_api + * attribute in supported type attribute groups. Device API string should be one + * of the following corresponding to device flags in vfio_device_info structure. + */ + +#define VFIO_DEVICE_API_PCI_STRING "vfio-pci" +#define VFIO_DEVICE_API_PLATFORM_STRING "vfio-platform" +#define VFIO_DEVICE_API_AMBA_STRING "vfio-amba" + /** * VFIO_DEVICE_GET_REGION_INFO - _IOWR(VFIO_TYPE, VFIO_BASE + 8, * struct vfio_region_info) -- 2.7.4 From: Vijaya Kumar K <Vijaya.Kumar@cavium.com> To Save and Restore ICC_SRE_EL1 register introduce vmstate subsection and load only if non-zero. Also initialize icc_sre_el1 with to 0x7 in pre_load function. Signed-off-by: Vijaya Kumar K <Vijaya.Kumar@cavium.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 1487850673-26455-3-git-send-email-vijay.kilari@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/intc/arm_gicv3_common.h | 1 + hw/intc/arm_gicv3_common.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 37 insertions(+) diff --git a/include/hw/intc/arm_gicv3_common.h b/include/hw/intc/arm_gicv3_common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/intc/arm_gicv3_common.h +++ b/include/hw/intc/arm_gicv3_common.h @@ -XXX,XX +XXX,XX @@ struct GICv3CPUState { uint8_t gicr_ipriorityr[GIC_INTERNAL]; /* CPU interface */ + uint64_t icc_sre_el1; uint64_t icc_ctlr_el1[2]; uint64_t icc_pmr_el1; uint64_t icc_bpr[3]; diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_gicv3_cpu_virt = { } }; +static int icc_sre_el1_reg_pre_load(void *opaque) +{ + GICv3CPUState *cs = opaque; + + /* + * If the sre_el1 subsection is not transferred this + * means SRE_EL1 is 0x7 (which might not be the same as + * our reset value). + */ + cs->icc_sre_el1 = 0x7; + return 0; +} + +static bool icc_sre_el1_reg_needed(void *opaque) +{ + GICv3CPUState *cs = opaque; + + return cs->icc_sre_el1 != 7; +} + +const VMStateDescription vmstate_gicv3_cpu_sre_el1 = { + .name = "arm_gicv3_cpu/sre_el1", + .version_id = 1, + .minimum_version_id = 1, + .pre_load = icc_sre_el1_reg_pre_load, + .needed = icc_sre_el1_reg_needed, + .fields = (VMStateField[]) { + VMSTATE_UINT64(icc_sre_el1, GICv3CPUState), + VMSTATE_END_OF_LIST() + } +}; + static const VMStateDescription vmstate_gicv3_cpu = { .name = "arm_gicv3_cpu", .version_id = 1, @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_gicv3_cpu = { .subsections = (const VMStateDescription * []) { &vmstate_gicv3_cpu_virt, NULL + }, + .subsections = (const VMStateDescription * []) { + &vmstate_gicv3_cpu_sre_el1, + NULL } }; -- 2.7.4 From: Vijaya Kumar K <Vijaya.Kumar@cavium.com> This actually implements pre_save and post_load methods for in-kernel vGICv3. Signed-off-by: Pavel Fedin <p.fedin@samsung.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Vijaya Kumar K <Vijaya.Kumar@cavium.com> Message-id: 1487850673-26455-4-git-send-email-vijay.kilari@gmail.com [PMM: * use decimal, not 0bnnn * fixed typo in names of ICC_APR0R_EL1 and ICC_AP1R_EL1 * completely rearranged the get and put functions to read and write the state in a natural order, rather than mixing distributor and redistributor state together] Signed-off-by: Vijaya Kumar K <Vijaya.Kumar@cavium.com> [Vijay: * Update macro KVM_VGIC_ATTR * Use 32 bit access for gicd and gicr * GICD_IROUTER, GICD_TYPER, GICR_PROPBASER and GICR_PENDBASER reg access are changed from 64-bit to 32-bit access * Add ICC_SRE_EL1 save and restore * Dropped translate_fn mechanism and coded functions to handle save and restore of edge_trigger and priority * Number of APnR register saved/restored based on number of priority bits supported] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/gicv3_internal.h | 1 + hw/intc/arm_gicv3_kvm.c | 573 +++++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 558 insertions(+), 16 deletions(-) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ #define ICC_CTLR_EL1_EOIMODE (1U << 1) #define ICC_CTLR_EL1_PMHE (1U << 6) #define ICC_CTLR_EL1_PRIBITS_SHIFT 8 +#define ICC_CTLR_EL1_PRIBITS_MASK (7U << ICC_CTLR_EL1_PRIBITS_SHIFT) #define ICC_CTLR_EL1_IDBITS_SHIFT 11 #define ICC_CTLR_EL1_SEIS (1U << 14) #define ICC_CTLR_EL1_A3V (1U << 15) diff --git a/hw/intc/arm_gicv3_kvm.c b/hw/intc/arm_gicv3_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_kvm.c +++ b/hw/intc/arm_gicv3_kvm.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "hw/intc/arm_gicv3_common.h" #include "hw/sysbus.h" +#include "qemu/error-report.h" #include "sysemu/kvm.h" #include "kvm_arm.h" +#include "gicv3_internal.h" #include "vgic_common.h" #include "migration/migration.h" @@ -XXX,XX +XXX,XX @@ #define KVM_ARM_GICV3_GET_CLASS(obj) \ OBJECT_GET_CLASS(KVMARMGICv3Class, (obj), TYPE_KVM_ARM_GICV3) +#define KVM_DEV_ARM_VGIC_SYSREG(op0, op1, crn, crm, op2) \ + (ARM64_SYS_REG_SHIFT_MASK(op0, OP0) | \ + ARM64_SYS_REG_SHIFT_MASK(op1, OP1) | \ + ARM64_SYS_REG_SHIFT_MASK(crn, CRN) | \ + ARM64_SYS_REG_SHIFT_MASK(crm, CRM) | \ + ARM64_SYS_REG_SHIFT_MASK(op2, OP2)) + +#define ICC_PMR_EL1 \ + KVM_DEV_ARM_VGIC_SYSREG(3, 0, 4, 6, 0) +#define ICC_BPR0_EL1 \ + KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 8, 3) +#define ICC_AP0R_EL1(n) \ + KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 8, 4 | n) +#define ICC_AP1R_EL1(n) \ + KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 9, n) +#define ICC_BPR1_EL1 \ + KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 12, 3) +#define ICC_CTLR_EL1 \ + KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 12, 4) +#define ICC_SRE_EL1 \ + KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 12, 5) +#define ICC_IGRPEN0_EL1 \ + KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 12, 6) +#define ICC_IGRPEN1_EL1 \ + KVM_DEV_ARM_VGIC_SYSREG(3, 0, 12, 12, 7) + typedef struct KVMARMGICv3Class { ARMGICv3CommonClass parent_class; DeviceRealize parent_realize; @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gicv3_set_irq(void *opaque, int irq, int level) kvm_arm_gic_set_irq(s->num_irq, irq, level); } +#define KVM_VGIC_ATTR(reg, typer) \ + ((typer & KVM_DEV_ARM_VGIC_V3_MPIDR_MASK) | (reg)) + +static inline void kvm_gicd_access(GICv3State *s, int offset, + uint32_t *val, bool write) +{ + kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_DIST_REGS, + KVM_VGIC_ATTR(offset, 0), + val, write); +} + +static inline void kvm_gicr_access(GICv3State *s, int offset, int cpu, + uint32_t *val, bool write) +{ + kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_REDIST_REGS, + KVM_VGIC_ATTR(offset, s->cpu[cpu].gicr_typer), + val, write); +} + +static inline void kvm_gicc_access(GICv3State *s, uint64_t reg, int cpu, + uint64_t *val, bool write) +{ + kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS, + KVM_VGIC_ATTR(reg, s->cpu[cpu].gicr_typer), + val, write); +} + +static inline void kvm_gic_line_level_access(GICv3State *s, int irq, int cpu, + uint32_t *val, bool write) +{ + kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO, + KVM_VGIC_ATTR(irq, s->cpu[cpu].gicr_typer) | + (VGIC_LEVEL_INFO_LINE_LEVEL << + KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT), + val, write); +} + +/* Loop through each distributor IRQ related register; since bits + * corresponding to SPIs and PPIs are RAZ/WI when affinity routing + * is enabled, we skip those. + */ +#define for_each_dist_irq_reg(_irq, _max, _field_width) \ + for (_irq = GIC_INTERNAL; _irq < _max; _irq += (32 / _field_width)) + +static void kvm_dist_get_priority(GICv3State *s, uint32_t offset, uint8_t *bmp) +{ + uint32_t reg, *field; + int irq; + + field = (uint32_t *)bmp; + for_each_dist_irq_reg(irq, s->num_irq, 8) { + kvm_gicd_access(s, offset, &reg, false); + *field = reg; + offset += 4; + field++; + } +} + +static void kvm_dist_put_priority(GICv3State *s, uint32_t offset, uint8_t *bmp) +{ + uint32_t reg, *field; + int irq; + + field = (uint32_t *)bmp; + for_each_dist_irq_reg(irq, s->num_irq, 8) { + reg = *field; + kvm_gicd_access(s, offset, &reg, true); + offset += 4; + field++; + } +} + +static void kvm_dist_get_edge_trigger(GICv3State *s, uint32_t offset, + uint32_t *bmp) +{ + uint32_t reg; + int irq; + + for_each_dist_irq_reg(irq, s->num_irq, 2) { + kvm_gicd_access(s, offset, &reg, false); + reg = half_unshuffle32(reg >> 1); + if (irq % 32 != 0) { + reg = (reg << 16); + } + *gic_bmp_ptr32(bmp, irq) |= reg; + offset += 4; + } +} + +static void kvm_dist_put_edge_trigger(GICv3State *s, uint32_t offset, + uint32_t *bmp) +{ + uint32_t reg; + int irq; + + for_each_dist_irq_reg(irq, s->num_irq, 2) { + reg = *gic_bmp_ptr32(bmp, irq); + if (irq % 32 != 0) { + reg = (reg & 0xffff0000) >> 16; + } else { + reg = reg & 0xffff; + } + reg = half_shuffle32(reg) << 1; + kvm_gicd_access(s, offset, &reg, true); + offset += 4; + } +} + +static void kvm_gic_get_line_level_bmp(GICv3State *s, uint32_t *bmp) +{ + uint32_t reg; + int irq; + + for_each_dist_irq_reg(irq, s->num_irq, 1) { + kvm_gic_line_level_access(s, irq, 0, &reg, false); + *gic_bmp_ptr32(bmp, irq) = reg; + } +} + +static void kvm_gic_put_line_level_bmp(GICv3State *s, uint32_t *bmp) +{ + uint32_t reg; + int irq; + + for_each_dist_irq_reg(irq, s->num_irq, 1) { + reg = *gic_bmp_ptr32(bmp, irq); + kvm_gic_line_level_access(s, irq, 0, &reg, true); + } +} + +/* Read a bitmap register group from the kernel VGIC. */ +static void kvm_dist_getbmp(GICv3State *s, uint32_t offset, uint32_t *bmp) +{ + uint32_t reg; + int irq; + + for_each_dist_irq_reg(irq, s->num_irq, 1) { + kvm_gicd_access(s, offset, &reg, false); + *gic_bmp_ptr32(bmp, irq) = reg; + offset += 4; + } +} + +static void kvm_dist_putbmp(GICv3State *s, uint32_t offset, + uint32_t clroffset, uint32_t *bmp) +{ + uint32_t reg; + int irq; + + for_each_dist_irq_reg(irq, s->num_irq, 1) { + /* If this bitmap is a set/clear register pair, first write to the + * clear-reg to clear all bits before using the set-reg to write + * the 1 bits. + */ + if (clroffset != 0) { + reg = 0; + kvm_gicd_access(s, clroffset, &reg, true); + } + reg = *gic_bmp_ptr32(bmp, irq); + kvm_gicd_access(s, offset, &reg, true); + offset += 4; + } +} + +static void kvm_arm_gicv3_check(GICv3State *s) +{ + uint32_t reg; + uint32_t num_irq; + + /* Sanity checking s->num_irq */ + kvm_gicd_access(s, GICD_TYPER, &reg, false); + num_irq = ((reg & 0x1f) + 1) * 32; + + if (num_irq < s->num_irq) { + error_report("Model requests %u IRQs, but kernel supports max %u", + s->num_irq, num_irq); + abort(); + } +} + static void kvm_arm_gicv3_put(GICv3State *s) { - /* TODO */ - DPRINTF("Cannot put kernel gic state, no kernel interface\n"); + uint32_t regl, regh, reg; + uint64_t reg64, redist_typer; + int ncpu, i; + + kvm_arm_gicv3_check(s); + + kvm_gicr_access(s, GICR_TYPER, 0, &regl, false); + kvm_gicr_access(s, GICR_TYPER + 4, 0, &regh, false); + redist_typer = ((uint64_t)regh << 32) | regl; + + reg = s->gicd_ctlr; + kvm_gicd_access(s, GICD_CTLR, &reg, true); + + if (redist_typer & GICR_TYPER_PLPIS) { + /* Set base addresses before LPIs are enabled by GICR_CTLR write */ + for (ncpu = 0; ncpu < s->num_cpu; ncpu++) { + GICv3CPUState *c = &s->cpu[ncpu]; + + reg64 = c->gicr_propbaser; + regl = (uint32_t)reg64; + kvm_gicr_access(s, GICR_PROPBASER, ncpu, &regl, true); + regh = (uint32_t)(reg64 >> 32); + kvm_gicr_access(s, GICR_PROPBASER + 4, ncpu, &regh, true); + + reg64 = c->gicr_pendbaser; + if (!c->gicr_ctlr & GICR_CTLR_ENABLE_LPIS) { + /* Setting PTZ is advised if LPIs are disabled, to reduce + * GIC initialization time. + */ + reg64 |= GICR_PENDBASER_PTZ; + } + regl = (uint32_t)reg64; + kvm_gicr_access(s, GICR_PENDBASER, ncpu, &regl, true); + regh = (uint32_t)(reg64 >> 32); + kvm_gicr_access(s, GICR_PENDBASER + 4, ncpu, &regh, true); + } + } + + /* Redistributor state (one per CPU) */ + + for (ncpu = 0; ncpu < s->num_cpu; ncpu++) { + GICv3CPUState *c = &s->cpu[ncpu]; + + reg = c->gicr_ctlr; + kvm_gicr_access(s, GICR_CTLR, ncpu, &reg, true); + + reg = c->gicr_statusr[GICV3_NS]; + kvm_gicr_access(s, GICR_STATUSR, ncpu, &reg, true); + + reg = c->gicr_waker; + kvm_gicr_access(s, GICR_WAKER, ncpu, &reg, true); + + reg = c->gicr_igroupr0; + kvm_gicr_access(s, GICR_IGROUPR0, ncpu, &reg, true); + + reg = ~0; + kvm_gicr_access(s, GICR_ICENABLER0, ncpu, &reg, true); + reg = c->gicr_ienabler0; + kvm_gicr_access(s, GICR_ISENABLER0, ncpu, &reg, true); + + /* Restore config before pending so we treat level/edge correctly */ + reg = half_shuffle32(c->edge_trigger >> 16) << 1; + kvm_gicr_access(s, GICR_ICFGR1, ncpu, &reg, true); + + reg = c->level; + kvm_gic_line_level_access(s, 0, ncpu, &reg, true); + + reg = ~0; + kvm_gicr_access(s, GICR_ICPENDR0, ncpu, &reg, true); + reg = c->gicr_ipendr0; + kvm_gicr_access(s, GICR_ISPENDR0, ncpu, &reg, true); + + reg = ~0; + kvm_gicr_access(s, GICR_ICACTIVER0, ncpu, &reg, true); + reg = c->gicr_iactiver0; + kvm_gicr_access(s, GICR_ISACTIVER0, ncpu, &reg, true); + + for (i = 0; i < GIC_INTERNAL; i += 4) { + reg = c->gicr_ipriorityr[i] | + (c->gicr_ipriorityr[i + 1] << 8) | + (c->gicr_ipriorityr[i + 2] << 16) | + (c->gicr_ipriorityr[i + 3] << 24); + kvm_gicr_access(s, GICR_IPRIORITYR + i, ncpu, &reg, true); + } + } + + /* Distributor state (shared between all CPUs */ + reg = s->gicd_statusr[GICV3_NS]; + kvm_gicd_access(s, GICD_STATUSR, &reg, true); + + /* s->enable bitmap -> GICD_ISENABLERn */ + kvm_dist_putbmp(s, GICD_ISENABLER, GICD_ICENABLER, s->enabled); + + /* s->group bitmap -> GICD_IGROUPRn */ + kvm_dist_putbmp(s, GICD_IGROUPR, 0, s->group); + + /* Restore targets before pending to ensure the pending state is set on + * the appropriate CPU interfaces in the kernel + */ + + /* s->gicd_irouter[irq] -> GICD_IROUTERn + * We can't use kvm_dist_put() here because the registers are 64-bit + */ + for (i = GIC_INTERNAL; i < s->num_irq; i++) { + uint32_t offset; + + offset = GICD_IROUTER + (sizeof(uint32_t) * i); + reg = (uint32_t)s->gicd_irouter[i]; + kvm_gicd_access(s, offset, &reg, true); + + offset = GICD_IROUTER + (sizeof(uint32_t) * i) + 4; + reg = (uint32_t)(s->gicd_irouter[i] >> 32); + kvm_gicd_access(s, offset, &reg, true); + } + + /* s->trigger bitmap -> GICD_ICFGRn + * (restore configuration registers before pending IRQs so we treat + * level/edge correctly) + */ + kvm_dist_put_edge_trigger(s, GICD_ICFGR, s->edge_trigger); + + /* s->level bitmap -> line_level */ + kvm_gic_put_line_level_bmp(s, s->level); + + /* s->pending bitmap -> GICD_ISPENDRn */ + kvm_dist_putbmp(s, GICD_ISPENDR, GICD_ICPENDR, s->pending); + + /* s->active bitmap -> GICD_ISACTIVERn */ + kvm_dist_putbmp(s, GICD_ISACTIVER, GICD_ICACTIVER, s->active); + + /* s->gicd_ipriority[] -> GICD_IPRIORITYRn */ + kvm_dist_put_priority(s, GICD_IPRIORITYR, s->gicd_ipriority); + + /* CPU Interface state (one per CPU) */ + + for (ncpu = 0; ncpu < s->num_cpu; ncpu++) { + GICv3CPUState *c = &s->cpu[ncpu]; + int num_pri_bits; + + kvm_gicc_access(s, ICC_SRE_EL1, ncpu, &c->icc_sre_el1, true); + kvm_gicc_access(s, ICC_CTLR_EL1, ncpu, + &c->icc_ctlr_el1[GICV3_NS], true); + kvm_gicc_access(s, ICC_IGRPEN0_EL1, ncpu, + &c->icc_igrpen[GICV3_G0], true); + kvm_gicc_access(s, ICC_IGRPEN1_EL1, ncpu, + &c->icc_igrpen[GICV3_G1NS], true); + kvm_gicc_access(s, ICC_PMR_EL1, ncpu, &c->icc_pmr_el1, true); + kvm_gicc_access(s, ICC_BPR0_EL1, ncpu, &c->icc_bpr[GICV3_G0], true); + kvm_gicc_access(s, ICC_BPR1_EL1, ncpu, &c->icc_bpr[GICV3_G1NS], true); + + num_pri_bits = ((c->icc_ctlr_el1[GICV3_NS] & + ICC_CTLR_EL1_PRIBITS_MASK) >> + ICC_CTLR_EL1_PRIBITS_SHIFT) + 1; + + switch (num_pri_bits) { + case 7: + reg64 = c->icc_apr[GICV3_G0][3]; + kvm_gicc_access(s, ICC_AP0R_EL1(3), ncpu, &reg64, true); + reg64 = c->icc_apr[GICV3_G0][2]; + kvm_gicc_access(s, ICC_AP0R_EL1(2), ncpu, &reg64, true); + case 6: + reg64 = c->icc_apr[GICV3_G0][1]; + kvm_gicc_access(s, ICC_AP0R_EL1(1), ncpu, &reg64, true); + default: + reg64 = c->icc_apr[GICV3_G0][0]; + kvm_gicc_access(s, ICC_AP0R_EL1(0), ncpu, &reg64, true); + } + + switch (num_pri_bits) { + case 7: + reg64 = c->icc_apr[GICV3_G1NS][3]; + kvm_gicc_access(s, ICC_AP1R_EL1(3), ncpu, &reg64, true); + reg64 = c->icc_apr[GICV3_G1NS][2]; + kvm_gicc_access(s, ICC_AP1R_EL1(2), ncpu, &reg64, true); + case 6: + reg64 = c->icc_apr[GICV3_G1NS][1]; + kvm_gicc_access(s, ICC_AP1R_EL1(1), ncpu, &reg64, true); + default: + reg64 = c->icc_apr[GICV3_G1NS][0]; + kvm_gicc_access(s, ICC_AP1R_EL1(0), ncpu, &reg64, true); + } + } } static void kvm_arm_gicv3_get(GICv3State *s) { - /* TODO */ - DPRINTF("Cannot get kernel gic state, no kernel interface\n"); + uint32_t regl, regh, reg; + uint64_t reg64, redist_typer; + int ncpu, i; + + kvm_arm_gicv3_check(s); + + kvm_gicr_access(s, GICR_TYPER, 0, &regl, false); + kvm_gicr_access(s, GICR_TYPER + 4, 0, &regh, false); + redist_typer = ((uint64_t)regh << 32) | regl; + + kvm_gicd_access(s, GICD_CTLR, &reg, false); + s->gicd_ctlr = reg; + + /* Redistributor state (one per CPU) */ + + for (ncpu = 0; ncpu < s->num_cpu; ncpu++) { + GICv3CPUState *c = &s->cpu[ncpu]; + + kvm_gicr_access(s, GICR_CTLR, ncpu, &reg, false); + c->gicr_ctlr = reg; + + kvm_gicr_access(s, GICR_STATUSR, ncpu, &reg, false); + c->gicr_statusr[GICV3_NS] = reg; + + kvm_gicr_access(s, GICR_WAKER, ncpu, &reg, false); + c->gicr_waker = reg; + + kvm_gicr_access(s, GICR_IGROUPR0, ncpu, &reg, false); + c->gicr_igroupr0 = reg; + kvm_gicr_access(s, GICR_ISENABLER0, ncpu, &reg, false); + c->gicr_ienabler0 = reg; + kvm_gicr_access(s, GICR_ICFGR1, ncpu, &reg, false); + c->edge_trigger = half_unshuffle32(reg >> 1) << 16; + kvm_gic_line_level_access(s, 0, ncpu, &reg, false); + c->level = reg; + kvm_gicr_access(s, GICR_ISPENDR0, ncpu, &reg, false); + c->gicr_ipendr0 = reg; + kvm_gicr_access(s, GICR_ISACTIVER0, ncpu, &reg, false); + c->gicr_iactiver0 = reg; + + for (i = 0; i < GIC_INTERNAL; i += 4) { + kvm_gicr_access(s, GICR_IPRIORITYR + i, ncpu, &reg, false); + c->gicr_ipriorityr[i] = extract32(reg, 0, 8); + c->gicr_ipriorityr[i + 1] = extract32(reg, 8, 8); + c->gicr_ipriorityr[i + 2] = extract32(reg, 16, 8); + c->gicr_ipriorityr[i + 3] = extract32(reg, 24, 8); + } + } + + if (redist_typer & GICR_TYPER_PLPIS) { + for (ncpu = 0; ncpu < s->num_cpu; ncpu++) { + GICv3CPUState *c = &s->cpu[ncpu]; + + kvm_gicr_access(s, GICR_PROPBASER, ncpu, &regl, false); + kvm_gicr_access(s, GICR_PROPBASER + 4, ncpu, &regh, false); + c->gicr_propbaser = ((uint64_t)regh << 32) | regl; + + kvm_gicr_access(s, GICR_PENDBASER, ncpu, &regl, false); + kvm_gicr_access(s, GICR_PENDBASER + 4, ncpu, &regh, false); + c->gicr_pendbaser = ((uint64_t)regh << 32) | regl; + } + } + + /* Distributor state (shared between all CPUs */ + + kvm_gicd_access(s, GICD_STATUSR, &reg, false); + s->gicd_statusr[GICV3_NS] = reg; + + /* GICD_IGROUPRn -> s->group bitmap */ + kvm_dist_getbmp(s, GICD_IGROUPR, s->group); + + /* GICD_ISENABLERn -> s->enabled bitmap */ + kvm_dist_getbmp(s, GICD_ISENABLER, s->enabled); + + /* Line level of irq */ + kvm_gic_get_line_level_bmp(s, s->level); + /* GICD_ISPENDRn -> s->pending bitmap */ + kvm_dist_getbmp(s, GICD_ISPENDR, s->pending); + + /* GICD_ISACTIVERn -> s->active bitmap */ + kvm_dist_getbmp(s, GICD_ISACTIVER, s->active); + + /* GICD_ICFGRn -> s->trigger bitmap */ + kvm_dist_get_edge_trigger(s, GICD_ICFGR, s->edge_trigger); + + /* GICD_IPRIORITYRn -> s->gicd_ipriority[] */ + kvm_dist_get_priority(s, GICD_IPRIORITYR, s->gicd_ipriority); + + /* GICD_IROUTERn -> s->gicd_irouter[irq] */ + for (i = GIC_INTERNAL; i < s->num_irq; i++) { + uint32_t offset; + + offset = GICD_IROUTER + (sizeof(uint32_t) * i); + kvm_gicd_access(s, offset, &regl, false); + offset = GICD_IROUTER + (sizeof(uint32_t) * i) + 4; + kvm_gicd_access(s, offset, &regh, false); + s->gicd_irouter[i] = ((uint64_t)regh << 32) | regl; + } + + /***************************************************************** + * CPU Interface(s) State + */ + + for (ncpu = 0; ncpu < s->num_cpu; ncpu++) { + GICv3CPUState *c = &s->cpu[ncpu]; + int num_pri_bits; + + kvm_gicc_access(s, ICC_SRE_EL1, ncpu, &c->icc_sre_el1, false); + kvm_gicc_access(s, ICC_CTLR_EL1, ncpu, + &c->icc_ctlr_el1[GICV3_NS], false); + kvm_gicc_access(s, ICC_IGRPEN0_EL1, ncpu, + &c->icc_igrpen[GICV3_G0], false); + kvm_gicc_access(s, ICC_IGRPEN1_EL1, ncpu, + &c->icc_igrpen[GICV3_G1NS], false); + kvm_gicc_access(s, ICC_PMR_EL1, ncpu, &c->icc_pmr_el1, false); + kvm_gicc_access(s, ICC_BPR0_EL1, ncpu, &c->icc_bpr[GICV3_G0], false); + kvm_gicc_access(s, ICC_BPR1_EL1, ncpu, &c->icc_bpr[GICV3_G1NS], false); + num_pri_bits = ((c->icc_ctlr_el1[GICV3_NS] & + ICC_CTLR_EL1_PRIBITS_MASK) >> + ICC_CTLR_EL1_PRIBITS_SHIFT) + 1; + + switch (num_pri_bits) { + case 7: + kvm_gicc_access(s, ICC_AP0R_EL1(3), ncpu, &reg64, false); + c->icc_apr[GICV3_G0][3] = reg64; + kvm_gicc_access(s, ICC_AP0R_EL1(2), ncpu, &reg64, false); + c->icc_apr[GICV3_G0][2] = reg64; + case 6: + kvm_gicc_access(s, ICC_AP0R_EL1(1), ncpu, &reg64, false); + c->icc_apr[GICV3_G0][1] = reg64; + default: + kvm_gicc_access(s, ICC_AP0R_EL1(0), ncpu, &reg64, false); + c->icc_apr[GICV3_G0][0] = reg64; + } + + switch (num_pri_bits) { + case 7: + kvm_gicc_access(s, ICC_AP1R_EL1(3), ncpu, &reg64, false); + c->icc_apr[GICV3_G1NS][3] = reg64; + kvm_gicc_access(s, ICC_AP1R_EL1(2), ncpu, &reg64, false); + c->icc_apr[GICV3_G1NS][2] = reg64; + case 6: + kvm_gicc_access(s, ICC_AP1R_EL1(1), ncpu, &reg64, false); + c->icc_apr[GICV3_G1NS][1] = reg64; + default: + kvm_gicc_access(s, ICC_AP1R_EL1(0), ncpu, &reg64, false); + c->icc_apr[GICV3_G1NS][0] = reg64; + } + } } static void kvm_arm_gicv3_reset(DeviceState *dev) @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gicv3_reset(DeviceState *dev) DPRINTF("Reset\n"); kgc->parent_reset(dev); + + if (s->migration_blocker) { + DPRINTF("Cannot put kernel gic state, no kernel interface\n"); + return; + } + kvm_arm_gicv3_put(s); } @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gicv3_realize(DeviceState *dev, Error **errp) gicv3_init_irqs_and_mmio(s, kvm_arm_gicv3_set_irq, NULL); - /* Block migration of a KVM GICv3 device: the API for saving and restoring - * the state in the kernel is not yet finalised in the kernel or - * implemented in QEMU. - */ - error_setg(&s->migration_blocker, "vGICv3 migration is not implemented"); - migrate_add_blocker(s->migration_blocker, &local_err); - if (local_err) { - error_propagate(errp, local_err); - error_free(s->migration_blocker); - return; - } - /* Try to create the device via the device control API */ s->dev_fd = kvm_create_device(kvm_state, KVM_DEV_TYPE_ARM_VGIC_V3, false); if (s->dev_fd < 0) { @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gicv3_realize(DeviceState *dev, Error **errp) kvm_irqchip_commit_routes(kvm_state); } + + if (!kvm_device_check_attr(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_DIST_REGS, + GICD_CTLR)) { + error_setg(&s->migration_blocker, "This operating system kernel does " + "not support vGICv3 migration"); + migrate_add_blocker(s->migration_blocker, &local_err); + if (local_err) { + error_propagate(errp, local_err); + error_free(s->migration_blocker); + return; + } + } } static void kvm_arm_gicv3_class_init(ObjectClass *klass, void *data) -- 2.7.4 From: Vijaya Kumar K <Vijaya.Kumar@cavium.com> Add gicv3state void pointer to CPUARMState struct to store GICv3CPUState. In case of usecase like CPU reset, we need to reset GICv3CPUState of the CPU. In such scenario, this pointer becomes handy. Signed-off-by: Vijaya Kumar K <Vijaya.Kumar@cavium.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 1487850673-26455-5-git-send-email-vijay.kilari@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/gicv3_internal.h | 2 ++ target/arm/cpu.h | 2 ++ hw/intc/arm_gicv3_common.c | 2 ++ hw/intc/arm_gicv3_cpuif.c | 8 ++++++++ 4 files changed, 14 insertions(+) diff --git a/hw/intc/gicv3_internal.h b/hw/intc/gicv3_internal.h index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/gicv3_internal.h +++ b/hw/intc/gicv3_internal.h @@ -XXX,XX +XXX,XX @@ static inline void gicv3_cache_all_target_cpustates(GICv3State *s) } } +void gicv3_set_gicv3state(CPUState *cpu, GICv3CPUState *s); + #endif /* QEMU_ARM_GICV3_INTERNAL_H */ diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUARMState { void *nvic; const struct arm_boot_info *boot_info; + /* Store GICv3CPUState to access from this struct */ + void *gicv3state; } CPUARMState; /** diff --git a/hw/intc/arm_gicv3_common.c b/hw/intc/arm_gicv3_common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_common.c +++ b/hw/intc/arm_gicv3_common.c @@ -XXX,XX +XXX,XX @@ static void arm_gicv3_common_realize(DeviceState *dev, Error **errp) s->cpu[i].cpu = cpu; s->cpu[i].gic = s; + /* Store GICv3CPUState in CPUARMState gicv3state pointer */ + gicv3_set_gicv3state(cpu, &s->cpu[i]); /* Pre-construct the GICR_TYPER: * For our implementation: diff --git a/hw/intc/arm_gicv3_cpuif.c b/hw/intc/arm_gicv3_cpuif.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_cpuif.c +++ b/hw/intc/arm_gicv3_cpuif.c @@ -XXX,XX +XXX,XX @@ #include "gicv3_internal.h" #include "cpu.h" +void gicv3_set_gicv3state(CPUState *cpu, GICv3CPUState *s) +{ + ARMCPU *arm_cpu = ARM_CPU(cpu); + CPUARMState *env = &arm_cpu->env; + + env->gicv3state = (void *)s; +}; + static GICv3CPUState *icc_cs_from_env(CPUARMState *env) { /* Given the CPU, find the right GICv3CPUState struct. -- 2.7.4 From: Vijaya Kumar K <Vijaya.Kumar@cavium.com> Reset CPU interface registers of GICv3 when CPU is reset. For this, ARMCPRegInfo struct is registered with one ICC register whose resetfn is called when cpu is reset. All the ICC registers are reset under one single register reset function instead of calling resetfn for each ICC register. Signed-off-by: Vijaya Kumar K <Vijaya.Kumar@cavium.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Eric Auger <eric.auger@redhat.com> Message-id: 1487850673-26455-6-git-send-email-vijay.kilari@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/intc/arm_gicv3_kvm.c | 60 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 60 insertions(+) diff --git a/hw/intc/arm_gicv3_kvm.c b/hw/intc/arm_gicv3_kvm.c index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/arm_gicv3_kvm.c +++ b/hw/intc/arm_gicv3_kvm.c @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gicv3_get(GICv3State *s) } } +static void arm_gicv3_icc_reset(CPUARMState *env, const ARMCPRegInfo *ri) +{ + ARMCPU *cpu; + GICv3State *s; + GICv3CPUState *c; + + c = (GICv3CPUState *)env->gicv3state; + s = c->gic; + cpu = ARM_CPU(c->cpu); + + /* Initialize to actual HW supported configuration */ + kvm_device_access(s->dev_fd, KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS, + KVM_VGIC_ATTR(ICC_CTLR_EL1, cpu->mp_affinity), + &c->icc_ctlr_el1[GICV3_NS], false); + + c->icc_ctlr_el1[GICV3_S] = c->icc_ctlr_el1[GICV3_NS]; + c->icc_pmr_el1 = 0; + c->icc_bpr[GICV3_G0] = GIC_MIN_BPR; + c->icc_bpr[GICV3_G1] = GIC_MIN_BPR; + c->icc_bpr[GICV3_G1NS] = GIC_MIN_BPR; + + c->icc_sre_el1 = 0x7; + memset(c->icc_apr, 0, sizeof(c->icc_apr)); + memset(c->icc_igrpen, 0, sizeof(c->icc_igrpen)); +} + static void kvm_arm_gicv3_reset(DeviceState *dev) { GICv3State *s = ARM_GICV3_COMMON(dev); @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gicv3_reset(DeviceState *dev) kvm_arm_gicv3_put(s); } +/* + * CPU interface registers of GIC needs to be reset on CPU reset. + * For the calling arm_gicv3_icc_reset() on CPU reset, we register + * below ARMCPRegInfo. As we reset the whole cpu interface under single + * register reset, we define only one register of CPU interface instead + * of defining all the registers. + */ +static const ARMCPRegInfo gicv3_cpuif_reginfo[] = { + { .name = "ICC_CTLR_EL1", .state = ARM_CP_STATE_BOTH, + .opc0 = 3, .opc1 = 0, .crn = 12, .crm = 12, .opc2 = 4, + /* + * If ARM_CP_NOP is used, resetfn is not called, + * So ARM_CP_NO_RAW is appropriate type. + */ + .type = ARM_CP_NO_RAW, + .access = PL1_RW, + .readfn = arm_cp_read_zero, + .writefn = arm_cp_write_ignore, + /* + * We hang the whole cpu interface reset routine off here + * rather than parcelling it out into one little function + * per register + */ + .resetfn = arm_gicv3_icc_reset, + }, + REGINFO_SENTINEL +}; + static void kvm_arm_gicv3_realize(DeviceState *dev, Error **errp) { GICv3State *s = KVM_ARM_GICV3(dev); @@ -XXX,XX +XXX,XX @@ static void kvm_arm_gicv3_realize(DeviceState *dev, Error **errp) gicv3_init_irqs_and_mmio(s, kvm_arm_gicv3_set_irq, NULL); + for (i = 0; i < s->num_cpu; i++) { + ARMCPU *cpu = ARM_CPU(qemu_get_cpu(i)); + + define_arm_cp_regs(cpu, gicv3_cpuif_reginfo); + } + /* Try to create the device via the device control API */ s->dev_fd = kvm_create_device(kvm_state, KVM_DEV_TYPE_ARM_VGIC_V3, false); if (s->dev_fd < 0) { -- 2.7.4 Instead of qdev_set_parent_bus() silently doing the wrong thing if it's handed a device that's already on a bus, have it remove the device from the old bus and add it to the new one. This is useful for the raspi2 sdcard. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Igor Mammedov <imammedo@redhat.com> Message-id: 1488293711-14195-2-git-send-email-peter.maydell@linaro.org --- hw/core/qdev.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/hw/core/qdev.c b/hw/core/qdev.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/qdev.c +++ b/hw/core/qdev.c @@ -XXX,XX +XXX,XX @@ static void bus_add_child(BusState *bus, DeviceState *child) void qdev_set_parent_bus(DeviceState *dev, BusState *bus) { + bool replugging = dev->parent_bus != NULL; + + if (replugging) { + /* Keep a reference to the device while it's not plugged into + * any bus, to avoid it potentially evaporating when it is + * dereffed in bus_remove_child(). + */ + object_ref(OBJECT(dev)); + bus_remove_child(dev->parent_bus, dev); + object_unref(OBJECT(dev->parent_bus)); + } dev->parent_bus = bus; object_ref(OBJECT(bus)); bus_add_child(bus, dev); + if (replugging) { + object_unref(OBJECT(dev)); + } } /* Create a new device. This only initializes the device state -- 2.7.4 From: Clement Deschamps <clement.deschamps@antfield.fr> Provide a new function sdbus_reparent_card() in sd core for reparenting a card from a SDBus to another one. This function is required by the raspi platform, where the two SD controllers can be dynamically switched. Signed-off-by: Clement Deschamps <clement.deschamps@antfield.fr> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1488293711-14195-3-git-send-email-peter.maydell@linaro.org Message-id: 20170224164021.9066-3-clement.deschamps@antfield.fr Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: added a doc comment to the header file; changed to use new behaviour of qdev_set_parent_bus()] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/sd/sd.h | 11 +++++++++++ hw/sd/core.c | 27 +++++++++++++++++++++++++++ 2 files changed, 38 insertions(+) diff --git a/include/hw/sd/sd.h b/include/hw/sd/sd.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/sd/sd.h +++ b/include/hw/sd/sd.h @@ -XXX,XX +XXX,XX @@ uint8_t sdbus_read_data(SDBus *sd); bool sdbus_data_ready(SDBus *sd); bool sdbus_get_inserted(SDBus *sd); bool sdbus_get_readonly(SDBus *sd); +/** + * sdbus_reparent_card: Reparent an SD card from one controller to another + * @from: controller bus to remove card from + * @to: controller bus to move card to + * + * Reparent an SD card, effectively unplugging it from one controller + * and inserting it into another. This is useful for SoCs like the + * bcm2835 which have two SD controllers and connect a single SD card + * to them, selected by the guest reprogramming GPIO line routing. + */ +void sdbus_reparent_card(SDBus *from, SDBus *to); /* Functions to be used by SD devices to report back to qdevified controllers */ void sdbus_set_inserted(SDBus *sd, bool inserted); diff --git a/hw/sd/core.c b/hw/sd/core.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/core.c +++ b/hw/sd/core.c @@ -XXX,XX +XXX,XX @@ void sdbus_set_readonly(SDBus *sdbus, bool readonly) } } +void sdbus_reparent_card(SDBus *from, SDBus *to) +{ + SDState *card = get_card(from); + SDCardClass *sc; + bool readonly; + + /* We directly reparent the card object rather than implementing this + * as a hotpluggable connection because we don't want to expose SD cards + * to users as being hotpluggable, and we can get away with it in this + * limited use case. This could perhaps be implemented more cleanly in + * future by adding support to the hotplug infrastructure for "device + * can be hotplugged only via code, not by user". + */ + + if (!card) { + return; + } + + sc = SD_CARD_GET_CLASS(card); + readonly = sc->get_readonly(card); + + sdbus_set_inserted(from, false); + qdev_set_parent_bus(DEVICE(card), &to->qbus); + sdbus_set_inserted(to, true); + sdbus_set_readonly(to, readonly); +} + static const TypeInfo sd_bus_info = { .name = TYPE_SD_BUS, .parent = TYPE_BUS, -- 2.7.4 From: Clement Deschamps <clement.deschamps@antfield.fr> This adds the BCM2835 GPIO controller. It currently implements: - The 54 GPIOs as outputs (qemu_irq) - The SD controller selection via alternate function of GPIOs 48-53 Signed-off-by: Clement Deschamps <clement.deschamps@antfield.fr> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1488293711-14195-4-git-send-email-peter.maydell@linaro.org Message-id: 20170224164021.9066-4-clement.deschamps@antfield.fr Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/gpio/Makefile.objs | 1 + include/hw/gpio/bcm2835_gpio.h | 39 +++++ hw/gpio/bcm2835_gpio.c | 353 +++++++++++++++++++++++++++++++++++++++++ 3 files changed, 393 insertions(+) create mode 100644 include/hw/gpio/bcm2835_gpio.h create mode 100644 hw/gpio/bcm2835_gpio.c diff --git a/hw/gpio/Makefile.objs b/hw/gpio/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/gpio/Makefile.objs +++ b/hw/gpio/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_GPIO_KEY) += gpio_key.o obj-$(CONFIG_OMAP) += omap_gpio.o obj-$(CONFIG_IMX) += imx_gpio.o +obj-$(CONFIG_RASPI) += bcm2835_gpio.o diff --git a/include/hw/gpio/bcm2835_gpio.h b/include/hw/gpio/bcm2835_gpio.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/gpio/bcm2835_gpio.h @@ -XXX,XX +XXX,XX @@ +/* + * Raspberry Pi (BCM2835) GPIO Controller + * + * Copyright (c) 2017 Antfield SAS + * + * Authors: + * Clement Deschamps <clement.deschamps@antfield.fr> + * Luc Michel <luc.michel@antfield.fr> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef BCM2835_GPIO_H +#define BCM2835_GPIO_H + +#include "hw/sd/sd.h" + +typedef struct BCM2835GpioState { + SysBusDevice parent_obj; + + MemoryRegion iomem; + + /* SDBus selector */ + SDBus sdbus; + SDBus *sdbus_sdhci; + SDBus *sdbus_sdhost; + + uint8_t fsel[54]; + uint32_t lev0, lev1; + uint8_t sd_fsel; + qemu_irq out[54]; +} BCM2835GpioState; + +#define TYPE_BCM2835_GPIO "bcm2835_gpio" +#define BCM2835_GPIO(obj) \ + OBJECT_CHECK(BCM2835GpioState, (obj), TYPE_BCM2835_GPIO) + +#endif diff --git a/hw/gpio/bcm2835_gpio.c b/hw/gpio/bcm2835_gpio.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/gpio/bcm2835_gpio.c @@ -XXX,XX +XXX,XX @@ +/* + * Raspberry Pi (BCM2835) GPIO Controller + * + * Copyright (c) 2017 Antfield SAS + * + * Authors: + * Clement Deschamps <clement.deschamps@antfield.fr> + * Luc Michel <luc.michel@antfield.fr> + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/timer.h" +#include "qapi/error.h" +#include "hw/sysbus.h" +#include "hw/sd/sd.h" +#include "hw/gpio/bcm2835_gpio.h" + +#define GPFSEL0 0x00 +#define GPFSEL1 0x04 +#define GPFSEL2 0x08 +#define GPFSEL3 0x0C +#define GPFSEL4 0x10 +#define GPFSEL5 0x14 +#define GPSET0 0x1C +#define GPSET1 0x20 +#define GPCLR0 0x28 +#define GPCLR1 0x2C +#define GPLEV0 0x34 +#define GPLEV1 0x38 +#define GPEDS0 0x40 +#define GPEDS1 0x44 +#define GPREN0 0x4C +#define GPREN1 0x50 +#define GPFEN0 0x58 +#define GPFEN1 0x5C +#define GPHEN0 0x64 +#define GPHEN1 0x68 +#define GPLEN0 0x70 +#define GPLEN1 0x74 +#define GPAREN0 0x7C +#define GPAREN1 0x80 +#define GPAFEN0 0x88 +#define GPAFEN1 0x8C +#define GPPUD 0x94 +#define GPPUDCLK0 0x98 +#define GPPUDCLK1 0x9C + +static uint32_t gpfsel_get(BCM2835GpioState *s, uint8_t reg) +{ + int i; + uint32_t value = 0; + for (i = 0; i < 10; i++) { + uint32_t index = 10 * reg + i; + if (index < sizeof(s->fsel)) { + value |= (s->fsel[index] & 0x7) << (3 * i); + } + } + return value; +} + +static void gpfsel_set(BCM2835GpioState *s, uint8_t reg, uint32_t value) +{ + int i; + for (i = 0; i < 10; i++) { + uint32_t index = 10 * reg + i; + if (index < sizeof(s->fsel)) { + int fsel = (value >> (3 * i)) & 0x7; + s->fsel[index] = fsel; + } + } + + /* SD controller selection (48-53) */ + if (s->sd_fsel != 0 + && (s->fsel[48] == 0) /* SD_CLK_R */ + && (s->fsel[49] == 0) /* SD_CMD_R */ + && (s->fsel[50] == 0) /* SD_DATA0_R */ + && (s->fsel[51] == 0) /* SD_DATA1_R */ + && (s->fsel[52] == 0) /* SD_DATA2_R */ + && (s->fsel[53] == 0) /* SD_DATA3_R */ + ) { + /* SDHCI controller selected */ + sdbus_reparent_card(s->sdbus_sdhost, s->sdbus_sdhci); + s->sd_fsel = 0; + } else if (s->sd_fsel != 4 + && (s->fsel[48] == 4) /* SD_CLK_R */ + && (s->fsel[49] == 4) /* SD_CMD_R */ + && (s->fsel[50] == 4) /* SD_DATA0_R */ + && (s->fsel[51] == 4) /* SD_DATA1_R */ + && (s->fsel[52] == 4) /* SD_DATA2_R */ + && (s->fsel[53] == 4) /* SD_DATA3_R */ + ) { + /* SDHost controller selected */ + sdbus_reparent_card(s->sdbus_sdhci, s->sdbus_sdhost); + s->sd_fsel = 4; + } +} + +static int gpfsel_is_out(BCM2835GpioState *s, int index) +{ + if (index >= 0 && index < 54) { + return s->fsel[index] == 1; + } + return 0; +} + +static void gpset(BCM2835GpioState *s, + uint32_t val, uint8_t start, uint8_t count, uint32_t *lev) +{ + uint32_t changes = val & ~*lev; + uint32_t cur = 1; + + int i; + for (i = 0; i < count; i++) { + if ((changes & cur) && (gpfsel_is_out(s, start + i))) { + qemu_set_irq(s->out[start + i], 1); + } + cur <<= 1; + } + + *lev |= val; +} + +static void gpclr(BCM2835GpioState *s, + uint32_t val, uint8_t start, uint8_t count, uint32_t *lev) +{ + uint32_t changes = val & *lev; + uint32_t cur = 1; + + int i; + for (i = 0; i < count; i++) { + if ((changes & cur) && (gpfsel_is_out(s, start + i))) { + qemu_set_irq(s->out[start + i], 0); + } + cur <<= 1; + } + + *lev &= ~val; +} + +static uint64_t bcm2835_gpio_read(void *opaque, hwaddr offset, + unsigned size) +{ + BCM2835GpioState *s = (BCM2835GpioState *)opaque; + + switch (offset) { + case GPFSEL0: + case GPFSEL1: + case GPFSEL2: + case GPFSEL3: + case GPFSEL4: + case GPFSEL5: + return gpfsel_get(s, offset / 4); + case GPSET0: + case GPSET1: + /* Write Only */ + return 0; + case GPCLR0: + case GPCLR1: + /* Write Only */ + return 0; + case GPLEV0: + return s->lev0; + case GPLEV1: + return s->lev1; + case GPEDS0: + case GPEDS1: + case GPREN0: + case GPREN1: + case GPFEN0: + case GPFEN1: + case GPHEN0: + case GPHEN1: + case GPLEN0: + case GPLEN1: + case GPAREN0: + case GPAREN1: + case GPAFEN0: + case GPAFEN1: + case GPPUD: + case GPPUDCLK0: + case GPPUDCLK1: + /* Not implemented */ + return 0; + default: + qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset %"HWADDR_PRIx"\n", + __func__, offset); + break; + } + + return 0; +} + +static void bcm2835_gpio_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + BCM2835GpioState *s = (BCM2835GpioState *)opaque; + + switch (offset) { + case GPFSEL0: + case GPFSEL1: + case GPFSEL2: + case GPFSEL3: + case GPFSEL4: + case GPFSEL5: + gpfsel_set(s, offset / 4, value); + break; + case GPSET0: + gpset(s, value, 0, 32, &s->lev0); + break; + case GPSET1: + gpset(s, value, 32, 22, &s->lev1); + break; + case GPCLR0: + gpclr(s, value, 0, 32, &s->lev0); + break; + case GPCLR1: + gpclr(s, value, 32, 22, &s->lev1); + break; + case GPLEV0: + case GPLEV1: + /* Read Only */ + break; + case GPEDS0: + case GPEDS1: + case GPREN0: + case GPREN1: + case GPFEN0: + case GPFEN1: + case GPHEN0: + case GPHEN1: + case GPLEN0: + case GPLEN1: + case GPAREN0: + case GPAREN1: + case GPAFEN0: + case GPAFEN1: + case GPPUD: + case GPPUDCLK0: + case GPPUDCLK1: + /* Not implemented */ + break; + default: + goto err_out; + } + return; + +err_out: + qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad offset %"HWADDR_PRIx"\n", + __func__, offset); +} + +static void bcm2835_gpio_reset(DeviceState *dev) +{ + BCM2835GpioState *s = BCM2835_GPIO(dev); + + int i; + for (i = 0; i < 6; i++) { + gpfsel_set(s, i, 0); + } + + s->sd_fsel = 0; + + /* SDHCI is selected by default */ + sdbus_reparent_card(&s->sdbus, s->sdbus_sdhci); + + s->lev0 = 0; + s->lev1 = 0; +} + +static const MemoryRegionOps bcm2835_gpio_ops = { + .read = bcm2835_gpio_read, + .write = bcm2835_gpio_write, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static const VMStateDescription vmstate_bcm2835_gpio = { + .name = "bcm2835_gpio", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT8_ARRAY(fsel, BCM2835GpioState, 54), + VMSTATE_UINT32(lev0, BCM2835GpioState), + VMSTATE_UINT32(lev1, BCM2835GpioState), + VMSTATE_UINT8(sd_fsel, BCM2835GpioState), + VMSTATE_END_OF_LIST() + } +}; + +static void bcm2835_gpio_init(Object *obj) +{ + BCM2835GpioState *s = BCM2835_GPIO(obj); + DeviceState *dev = DEVICE(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + + qbus_create_inplace(&s->sdbus, sizeof(s->sdbus), + TYPE_SD_BUS, DEVICE(s), "sd-bus"); + + memory_region_init_io(&s->iomem, obj, + &bcm2835_gpio_ops, s, "bcm2835_gpio", 0x1000); + sysbus_init_mmio(sbd, &s->iomem); + qdev_init_gpio_out(dev, s->out, 54); +} + +static void bcm2835_gpio_realize(DeviceState *dev, Error **errp) +{ + BCM2835GpioState *s = BCM2835_GPIO(dev); + Object *obj; + Error *err = NULL; + + obj = object_property_get_link(OBJECT(dev), "sdbus-sdhci", &err); + if (obj == NULL) { + error_setg(errp, "%s: required sdhci link not found: %s", + __func__, error_get_pretty(err)); + return; + } + s->sdbus_sdhci = SD_BUS(obj); + + obj = object_property_get_link(OBJECT(dev), "sdbus-sdhost", &err); + if (obj == NULL) { + error_setg(errp, "%s: required sdhost link not found: %s", + __func__, error_get_pretty(err)); + return; + } + s->sdbus_sdhost = SD_BUS(obj); +} + +static void bcm2835_gpio_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->vmsd = &vmstate_bcm2835_gpio; + dc->realize = &bcm2835_gpio_realize; + dc->reset = &bcm2835_gpio_reset; +} + +static const TypeInfo bcm2835_gpio_info = { + .name = TYPE_BCM2835_GPIO, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(BCM2835GpioState), + .instance_init = bcm2835_gpio_init, + .class_init = bcm2835_gpio_class_init, +}; + +static void bcm2835_gpio_register_types(void) +{ + type_register_static(&bcm2835_gpio_info); +} + +type_init(bcm2835_gpio_register_types) -- 2.7.4 From: Clement Deschamps <clement.deschamps@antfield.fr> This adds the bcm2835_sdhost and bcm2835_gpio to the BCM2835 platform. For supporting the SD controller selection (alternate function of GPIOs 48-53), the bcm2835_gpio now exposes an sdbus. It also has a link to both the sdbus of sdhci and sdhost controllers, and the card is reparented from one bus to another when the alternate function of GPIOs 48-53 is modified. Signed-off-by: Clement Deschamps <clement.deschamps@antfield.fr> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1488293711-14195-5-git-send-email-peter.maydell@linaro.org Message-id: 20170224164021.9066-5-clement.deschamps@antfield.fr Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/bcm2835_peripherals.h | 4 ++++ hw/arm/bcm2835_peripherals.c | 43 ++++++++++++++++++++++++++++++++++-- 2 files changed, 45 insertions(+), 2 deletions(-) diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/bcm2835_peripherals.h +++ b/include/hw/arm/bcm2835_peripherals.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/bcm2835_rng.h" #include "hw/misc/bcm2835_mbox.h" #include "hw/sd/sdhci.h" +#include "hw/sd/bcm2835_sdhost.h" +#include "hw/gpio/bcm2835_gpio.h" #define TYPE_BCM2835_PERIPHERALS "bcm2835-peripherals" #define BCM2835_PERIPHERALS(obj) \ @@ -XXX,XX +XXX,XX @@ typedef struct BCM2835PeripheralState { BCM2835RngState rng; BCM2835MboxState mboxes; SDHCIState sdhci; + BCM2835SDHostState sdhost; + BCM2835GpioState gpio; } BCM2835PeripheralState; #endif /* BCM2835_PERIPHERALS_H */ diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj) object_property_add_child(obj, "sdhci", OBJECT(&s->sdhci), NULL); qdev_set_parent_bus(DEVICE(&s->sdhci), sysbus_get_default()); + /* SDHOST */ + object_initialize(&s->sdhost, sizeof(s->sdhost), TYPE_BCM2835_SDHOST); + object_property_add_child(obj, "sdhost", OBJECT(&s->sdhost), NULL); + qdev_set_parent_bus(DEVICE(&s->sdhost), sysbus_get_default()); + /* DMA Channels */ object_initialize(&s->dma, sizeof(s->dma), TYPE_BCM2835_DMA); object_property_add_child(obj, "dma", OBJECT(&s->dma), NULL); @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_init(Object *obj) object_property_add_const_link(OBJECT(&s->dma), "dma-mr", OBJECT(&s->gpu_bus_mr), &error_abort); + + /* GPIO */ + object_initialize(&s->gpio, sizeof(s->gpio), TYPE_BCM2835_GPIO); + object_property_add_child(obj, "gpio", OBJECT(&s->gpio), NULL); + qdev_set_parent_bus(DEVICE(&s->gpio), sysbus_get_default()); + + object_property_add_const_link(OBJECT(&s->gpio), "sdbus-sdhci", + OBJECT(&s->sdhci.sdbus), &error_abort); + object_property_add_const_link(OBJECT(&s->gpio), "sdbus-sdhost", + OBJECT(&s->sdhost.sdbus), &error_abort); } static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->sdhci), 0, qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ, INTERRUPT_ARASANSDIO)); - object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->sdhci), "sd-bus", - &err); + + /* SDHOST */ + object_property_set_bool(OBJECT(&s->sdhost), true, "realized", &err); if (err) { error_propagate(errp, err); return; } + memory_region_add_subregion(&s->peri_mr, MMCI0_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->sdhost), 0)); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->sdhost), 0, + qdev_get_gpio_in_named(DEVICE(&s->ic), BCM2835_IC_GPU_IRQ, + INTERRUPT_SDIO)); + /* DMA Channels */ object_property_set_bool(OBJECT(&s->dma), true, "realized", &err); if (err) { @@ -XXX,XX +XXX,XX @@ static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) BCM2835_IC_GPU_IRQ, INTERRUPT_DMA0 + n)); } + + /* GPIO */ + object_property_set_bool(OBJECT(&s->gpio), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + + memory_region_add_subregion(&s->peri_mr, GPIO_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->gpio), 0)); + + object_property_add_alias(OBJECT(s), "sd-bus", OBJECT(&s->gpio), "sd-bus", + &err); + if (err) { + error_propagate(errp, err); + return; + } } static void bcm2835_peripherals_class_init(ObjectClass *oc, void *data) -- 2.7.4 I don't have anything else queued up at the moment, so this is just Richard's SME patches. -- PMM The following changes since commit 63b38f6c85acd312c2cab68554abf33adf4ee2b3: Merge tag 'pull-target-arm-20220707' of https://git.linaro.org/people/pmaydell/qemu-arm into staging (2022-07-08 06:17:11 +0530) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20220711 for you to fetch changes up to f9982ceaf26df27d15547a3a7990a95019e9e3a8: linux-user/aarch64: Add SME related hwcap entries (2022-07-11 13:43:52 +0100) ---------------------------------------------------------------- target-arm: * Implement SME emulation, for both system and linux-user ---------------------------------------------------------------- Richard Henderson (45): target/arm: Handle SME in aarch64_cpu_dump_state target/arm: Add infrastructure for disas_sme target/arm: Trap non-streaming usage when Streaming SVE is active target/arm: Mark ADR as non-streaming target/arm: Mark RDFFR, WRFFR, SETFFR as non-streaming target/arm: Mark BDEP, BEXT, BGRP, COMPACT, FEXPA, FTSSEL as non-streaming target/arm: Mark PMULL, FMMLA as non-streaming target/arm: Mark FTSMUL, FTMAD, FADDA as non-streaming target/arm: Mark SMMLA, UMMLA, USMMLA as non-streaming target/arm: Mark string/histo/crypto as non-streaming target/arm: Mark gather/scatter load/store as non-streaming target/arm: Mark gather prefetch as non-streaming target/arm: Mark LDFF1 and LDNF1 as non-streaming target/arm: Mark LD1RO as non-streaming target/arm: Add SME enablement checks target/arm: Handle SME in sve_access_check target/arm: Implement SME RDSVL, ADDSVL, ADDSPL target/arm: Implement SME ZERO target/arm: Implement SME MOVA target/arm: Implement SME LD1, ST1 target/arm: Export unpredicated ld/st from translate-sve.c target/arm: Implement SME LDR, STR target/arm: Implement SME ADDHA, ADDVA target/arm: Implement FMOPA, FMOPS (non-widening) target/arm: Implement BFMOPA, BFMOPS target/arm: Implement FMOPA, FMOPS (widening) target/arm: Implement SME integer outer product target/arm: Implement PSEL target/arm: Implement REVD target/arm: Implement SCLAMP, UCLAMP target/arm: Reset streaming sve state on exception boundaries target/arm: Enable SME for -cpu max linux-user/aarch64: Clear tpidr2_el0 if CLONE_SETTLS linux-user/aarch64: Reset PSTATE.SM on syscalls linux-user/aarch64: Add SM bit to SVE signal context linux-user/aarch64: Tidy target_restore_sigframe error return linux-user/aarch64: Do not allow duplicate or short sve records linux-user/aarch64: Verify extra record lock succeeded linux-user/aarch64: Move sve record checks into restore linux-user/aarch64: Implement SME signal handling linux-user: Rename sve prctls linux-user/aarch64: Implement PR_SME_GET_VL, PR_SME_SET_VL target/arm: Only set ZEN in reset if SVE present target/arm: Enable SME for user-only linux-user/aarch64: Add SME related hwcap entries docs/system/arm/emulation.rst | 4 + linux-user/aarch64/target_cpu.h | 5 +- linux-user/aarch64/target_prctl.h | 62 +- target/arm/cpu.h | 7 + target/arm/helper-sme.h | 126 ++++ target/arm/helper-sve.h | 4 + target/arm/helper.h | 18 + target/arm/translate-a64.h | 45 ++ target/arm/translate.h | 16 + target/arm/sme-fa64.decode | 60 ++ target/arm/sme.decode | 88 +++ target/arm/sve.decode | 41 +- linux-user/aarch64/cpu_loop.c | 9 + linux-user/aarch64/signal.c | 243 ++++++-- linux-user/elfload.c | 20 + linux-user/syscall.c | 28 +- target/arm/cpu.c | 35 +- target/arm/cpu64.c | 11 + target/arm/helper.c | 56 +- target/arm/sme_helper.c | 1140 +++++++++++++++++++++++++++++++++++++ target/arm/sve_helper.c | 28 + target/arm/translate-a64.c | 103 +++- target/arm/translate-sme.c | 373 ++++++++++++ target/arm/translate-sve.c | 393 ++++++++++--- target/arm/translate-vfp.c | 12 + target/arm/translate.c | 2 + target/arm/vec_helper.c | 24 + target/arm/meson.build | 3 + 28 files changed, 2821 insertions(+), 135 deletions(-) create mode 100644 target/arm/sme-fa64.decode create mode 100644 target/arm/sme.decode create mode 100644 target/arm/translate-sme.c From: Richard Henderson <richard.henderson@linaro.org> Dump SVCR, plus use the correct access check for Streaming Mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 17 ++++++++++++++++- 1 file changed, 16 insertions(+), 1 deletion(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) int i; int el = arm_current_el(env); const char *ns_status; + bool sve; qemu_fprintf(f, " PC=%016" PRIx64 " ", env->pc); for (i = 0; i < 32; i++) { @@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) el, psr & PSTATE_SP ? 'h' : 't'); + if (cpu_isar_feature(aa64_sme, cpu)) { + qemu_fprintf(f, " SVCR=%08" PRIx64 " %c%c", + env->svcr, + (FIELD_EX64(env->svcr, SVCR, ZA) ? 'Z' : '-'), + (FIELD_EX64(env->svcr, SVCR, SM) ? 'S' : '-')); + } if (cpu_isar_feature(aa64_bti, cpu)) { qemu_fprintf(f, " BTYPE=%d", (psr & PSTATE_BTYPE) >> 10); } @@ -XXX,XX +XXX,XX @@ static void aarch64_cpu_dump_state(CPUState *cs, FILE *f, int flags) qemu_fprintf(f, " FPCR=%08x FPSR=%08x\n", vfp_get_fpcr(env), vfp_get_fpsr(env)); - if (cpu_isar_feature(aa64_sve, cpu) && sve_exception_el(env, el) == 0) { + if (cpu_isar_feature(aa64_sme, cpu) && FIELD_EX64(env->svcr, SVCR, SM)) { + sve = sme_exception_el(env, el) == 0; + } else if (cpu_isar_feature(aa64_sve, cpu)) { + sve = sve_exception_el(env, el) == 0; + } else { + sve = false; + } + + if (sve) { int j, zcr_len = sve_vqm1_for_el(env, el); for (i = 0; i <= FFR_PRED_NUM; i++) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This includes the build rules for the decoder, and the new file for translation, but excludes any instructions. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 1 + target/arm/sme.decode | 20 ++++++++++++++++++++ target/arm/translate-a64.c | 7 ++++++- target/arm/translate-sme.c | 35 +++++++++++++++++++++++++++++++++++ target/arm/meson.build | 2 ++ 5 files changed, 64 insertions(+), 1 deletion(-) create mode 100644 target/arm/sme.decode create mode 100644 target/arm/translate-sme.c diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ static inline int pred_gvec_reg_size(DisasContext *s) } bool disas_sve(DisasContext *, uint32_t); +bool disas_sme(DisasContext *, uint32_t); void gen_gvec_rax1(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, uint32_t opr_sz, uint32_t max_sz); diff --git a/target/arm/sme.decode b/target/arm/sme.decode new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ +# AArch64 SME instruction descriptions +# +# Copyright (c) 2022 Linaro, Ltd +# +# This library is free software; you can redistribute it and/or +# modify it under the terms of the GNU Lesser General Public +# License as published by the Free Software Foundation; either +# version 2.1 of the License, or (at your option) any later version. +# +# This library 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 +# Lesser General Public License for more details. +# +# You should have received a copy of the GNU Lesser General Public +# License along with this library; if not, see <http://www.gnu.org/licenses/>. + +# +# This file is processed by scripts/decodetree.py +# diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) } switch (extract32(insn, 25, 4)) { - case 0x0: case 0x1: case 0x3: /* UNALLOCATED */ + case 0x0: + if (!extract32(insn, 31, 1) || !disas_sme(s, insn)) { + unallocated_encoding(s); + } + break; + case 0x1: case 0x3: /* UNALLOCATED */ unallocated_encoding(s); break; case 0x2: diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ +/* + * AArch64 SME translation + * + * Copyright (c) 2022 Linaro, Ltd + * + * This library is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * This library 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 + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with this library; if not, see <http://www.gnu.org/licenses/>. + */ + +#include "qemu/osdep.h" +#include "cpu.h" +#include "tcg/tcg-op.h" +#include "tcg/tcg-op-gvec.h" +#include "tcg/tcg-gvec-desc.h" +#include "translate.h" +#include "exec/helper-gen.h" +#include "translate-a64.h" +#include "fpu/softfloat.h" + + +/* + * Include the generated decoder. + */ + +#include "decode-sme.c.inc" diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ gen = [ decodetree.process('sve.decode', extra_args: '--decode=disas_sve'), + decodetree.process('sme.decode', extra_args: '--decode=disas_sme'), decodetree.process('neon-shared.decode', extra_args: '--decode=disas_neon_shared'), decodetree.process('neon-dp.decode', extra_args: '--decode=disas_neon_dp'), decodetree.process('neon-ls.decode', extra_args: '--decode=disas_neon_ls'), @@ -XXX,XX +XXX,XX @@ arm_ss.add(when: 'TARGET_AARCH64', if_true: files( 'sme_helper.c', 'translate-a64.c', 'translate-sve.c', + 'translate-sme.c', )) arm_softmmu_ss = ss.source_set() -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This new behaviour is in the ARM pseudocode function AArch64.CheckFPAdvSIMDEnabled, which applies to AArch32 via AArch32.CheckAdvSIMDOrFPEnabled when the EL to which the trap would be delivered is in AArch64 mode. Given that ARMv9 drops support for AArch32 outside EL0, the trap EL detection ought to be trivially true, but the pseudocode still contains a number of conditions, and QEMU has not yet committed to dropping A32 support for EL[12] when v9 features are present. Since the computation of SME_TRAP_NONSTREAMING is necessarily different for the two modes, we might as well preserve bits within TBFLAG_ANY and allocate separate bits within TBFLAG_A32 and TBFLAG_A64 instead. Note that DDI0616A.a has typos for bits [22:21] of LD1RO in the table of instructions illegal in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 7 +++ target/arm/translate.h | 4 ++ target/arm/sme-fa64.decode | 90 ++++++++++++++++++++++++++++++++++++++ target/arm/helper.c | 41 +++++++++++++++++ target/arm/translate-a64.c | 40 ++++++++++++++++- target/arm/translate-vfp.c | 12 +++++ target/arm/translate.c | 2 + target/arm/meson.build | 1 + 8 files changed, 195 insertions(+), 2 deletions(-) create mode 100644 target/arm/sme-fa64.decode diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A32, HSTR_ACTIVE, 9, 1) * the same thing as the current security state of the processor! */ FIELD(TBFLAG_A32, NS, 10, 1) +/* + * Indicates that SME Streaming mode is active, and SMCR_ELx.FA64 is not. + * This requires an SME trap from AArch32 mode when using NEON. + */ +FIELD(TBFLAG_A32, SME_TRAP_NONSTREAMING, 11, 1) /* * Bit usage when in AArch32 state, for M-profile only. @@ -XXX,XX +XXX,XX @@ FIELD(TBFLAG_A64, SMEEXC_EL, 20, 2) FIELD(TBFLAG_A64, PSTATE_SM, 22, 1) FIELD(TBFLAG_A64, PSTATE_ZA, 23, 1) FIELD(TBFLAG_A64, SVL, 24, 4) +/* Indicates that SME Streaming mode is active, and SMCR_ELx.FA64 is not. */ +FIELD(TBFLAG_A64, SME_TRAP_NONSTREAMING, 28, 1) /* * Helpers for using the above. diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ typedef struct DisasContext { bool pstate_sm; /* True if PSTATE.ZA is set. */ bool pstate_za; + /* True if non-streaming insns should raise an SME Streaming exception. */ + bool sme_trap_nonstreaming; + /* True if the current instruction is non-streaming. */ + bool is_nonstreaming; /* True if MVE insns are definitely not predicated by VPR or LTPSIZE */ bool mve_no_pred; /* diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ +# AArch64 SME allowed instruction decoding +# +# Copyright (c) 2022 Linaro, Ltd +# +# This library is free software; you can redistribute it and/or +# modify it under the terms of the GNU Lesser General Public +# License as published by the Free Software Foundation; either +# version 2.1 of the License, or (at your option) any later version. +# +# This library 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 +# Lesser General Public License for more details. +# +# You should have received a copy of the GNU Lesser General Public +# License along with this library; if not, see <http://www.gnu.org/licenses/>. + +# +# This file is processed by scripts/decodetree.py +# + +# These patterns are taken from Appendix E1.1 of DDI0616 A.a, +# Arm Architecture Reference Manual Supplement, +# The Scalable Matrix Extension (SME), for Armv9-A + +{ + [ + OK 0-00 1110 0000 0001 0010 11-- ---- ---- # SMOV W|Xd,Vn.B[0] + OK 0-00 1110 0000 0010 0010 11-- ---- ---- # SMOV W|Xd,Vn.H[0] + OK 0100 1110 0000 0100 0010 11-- ---- ---- # SMOV Xd,Vn.S[0] + OK 0000 1110 0000 0001 0011 11-- ---- ---- # UMOV Wd,Vn.B[0] + OK 0000 1110 0000 0010 0011 11-- ---- ---- # UMOV Wd,Vn.H[0] + OK 0000 1110 0000 0100 0011 11-- ---- ---- # UMOV Wd,Vn.S[0] + OK 0100 1110 0000 1000 0011 11-- ---- ---- # UMOV Xd,Vn.D[0] + ] + FAIL 0--0 111- ---- ---- ---- ---- ---- ---- # Advanced SIMD vector operations +} + +{ + [ + OK 0101 1110 --1- ---- 11-1 11-- ---- ---- # FMULX/FRECPS/FRSQRTS (scalar) + OK 0101 1110 -10- ---- 00-1 11-- ---- ---- # FMULX/FRECPS/FRSQRTS (scalar, FP16) + OK 01-1 1110 1-10 0001 11-1 10-- ---- ---- # FRECPE/FRSQRTE/FRECPX (scalar) + OK 01-1 1110 1111 1001 11-1 10-- ---- ---- # FRECPE/FRSQRTE/FRECPX (scalar, FP16) + ] + FAIL 01-1 111- ---- ---- ---- ---- ---- ---- # Advanced SIMD single-element operations +} + +FAIL 0-00 110- ---- ---- ---- ---- ---- ---- # Advanced SIMD structure load/store +FAIL 1100 1110 ---- ---- ---- ---- ---- ---- # Advanced SIMD cryptography extensions +FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS + +# These are the "avoidance of doubt" final table of Illegal Advanced SIMD instructions +# We don't actually need to include these, as the default is OK. +# -001 111- ---- ---- ---- ---- ---- ---- # Scalar floating-point operations +# --10 110- ---- ---- ---- ---- ---- ---- # Load/store pair of FP registers +# --01 1100 ---- ---- ---- ---- ---- ---- # Load FP register (PC-relative literal) +# --11 1100 --0- ---- ---- ---- ---- ---- # Load/store FP register (unscaled imm) +# --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) +# --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) + +FAIL 0000 0100 --1- ---- 1010 ---- ---- ---- # ADR +FAIL 0000 0100 --1- ---- 1011 -0-- ---- ---- # FTSSEL, FEXPA +FAIL 0000 0101 --10 0001 100- ---- ---- ---- # COMPACT +FAIL 0010 0101 --01 100- 1111 000- ---0 ---- # RDFFR, RDFFRS +FAIL 0010 0101 --10 1--- 1001 ---- ---- ---- # WRFFR, SETFFR +FAIL 0100 0101 --0- ---- 1011 ---- ---- ---- # BDEP, BEXT, BGRP +FAIL 0100 0101 000- ---- 0110 1--- ---- ---- # PMULLB, PMULLT (128b result) +FAIL 0110 0100 --1- ---- 1110 01-- ---- ---- # FMMLA, BFMMLA +FAIL 0110 0101 --0- ---- 0000 11-- ---- ---- # FTSMUL +FAIL 0110 0101 --01 0--- 100- ---- ---- ---- # FTMAD +FAIL 0110 0101 --01 1--- 001- ---- ---- ---- # FADDA +FAIL 0100 0101 --0- ---- 1001 10-- ---- ---- # SMMLA, UMMLA, USMMLA +FAIL 0100 0101 --1- ---- 1--- ---- ---- ---- # SVE2 string/histo/crypto instructions +FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) +FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) +FAIL 1000 0100 0-1- ---- 0--- ---- ---- ---- # SVE 32-bit gather prefetch (scalar+vector) +FAIL 1000 010- -01- ---- 1--- ---- ---- ---- # SVE 32-bit gather load (vector+imm) +FAIL 1000 0100 0-0- ---- 0--- ---- ---- ---- # SVE 32-bit gather load byte (scalar+vector) +FAIL 1000 0100 1--- ---- 0--- ---- ---- ---- # SVE 32-bit gather load half (scalar+vector) +FAIL 1000 0101 0--- ---- 0--- ---- ---- ---- # SVE 32-bit gather load word (scalar+vector) +FAIL 1010 010- ---- ---- 011- ---- ---- ---- # SVE contiguous FF load (scalar+scalar) +FAIL 1010 010- ---1 ---- 101- ---- ---- ---- # SVE contiguous NF load (scalar+imm) +FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) +FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) +FAIL 1100 010- ---- ---- ---- ---- ---- ---- # SVE 64-bit gather load/prefetch +FAIL 1110 010- -00- ---- 001- ---- ---- ---- # SVE2 64-bit scatter NT store (vector+scalar) +FAIL 1110 010- -10- ---- 001- ---- ---- ---- # SVE2 32-bit scatter NT store (vector+scalar) +FAIL 1110 010- ---- ---- 1-0- ---- ---- ---- # SVE scatter store (scalar+32-bit vector) +FAIL 1110 010- ---- ---- 101- ---- ---- ---- # SVE scatter store (misc) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ int sme_exception_el(CPUARMState *env, int el) return 0; } +/* This corresponds to the ARM pseudocode function IsFullA64Enabled(). */ +static bool sme_fa64(CPUARMState *env, int el) +{ + if (!cpu_isar_feature(aa64_sme_fa64, env_archcpu(env))) { + return false; + } + + if (el <= 1 && !el_is_in_host(env, el)) { + if (!FIELD_EX64(env->vfp.smcr_el[1], SMCR, FA64)) { + return false; + } + } + if (el <= 2 && arm_is_el2_enabled(env)) { + if (!FIELD_EX64(env->vfp.smcr_el[2], SMCR, FA64)) { + return false; + } + } + if (arm_feature(env, ARM_FEATURE_EL3)) { + if (!FIELD_EX64(env->vfp.smcr_el[3], SMCR, FA64)) { + return false; + } + } + + return true; +} + /* * Given that SVE is enabled, return the vector length for EL. */ @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el, DP_TBFLAG_ANY(flags, PSTATE__IL, 1); } + /* + * The SME exception we are testing for is raised via + * AArch64.CheckFPAdvSIMDEnabled(), as called from + * AArch32.CheckAdvSIMDOrFPEnabled(). + */ + if (el == 0 + && FIELD_EX64(env->svcr, SVCR, SM) + && (!arm_is_el2_enabled(env) + || (arm_el_is_aa64(env, 2) && !(env->cp15.hcr_el2 & HCR_TGE))) + && arm_el_is_aa64(env, 1) + && !sme_fa64(env, el)) { + DP_TBFLAG_A32(flags, SME_TRAP_NONSTREAMING, 1); + } + return rebuild_hflags_common_32(env, fp_el, mmu_idx, flags); } @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, } if (FIELD_EX64(env->svcr, SVCR, SM)) { DP_TBFLAG_A64(flags, PSTATE_SM, 1); + DP_TBFLAG_A64(flags, SME_TRAP_NONSTREAMING, !sme_fa64(env, el)); } DP_TBFLAG_A64(flags, PSTATE_ZA, FIELD_EX64(env->svcr, SVCR, ZA)); } diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void do_vec_ld(DisasContext *s, int destidx, int element, * unallocated-encoding checks (otherwise the syndrome information * for the resulting exception will be incorrect). */ -static bool fp_access_check(DisasContext *s) +static bool fp_access_check_only(DisasContext *s) { if (s->fp_excp_el) { assert(!s->fp_access_checked); @@ -XXX,XX +XXX,XX @@ static bool fp_access_check(DisasContext *s) return true; } +static bool fp_access_check(DisasContext *s) +{ + if (!fp_access_check_only(s)) { + return false; + } + if (s->sme_trap_nonstreaming && s->is_nonstreaming) { + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_smetrap(SME_ET_Streaming, false)); + return false; + } + return true; +} + /* Check that SVE access is enabled. If it is, return true. * If not, emit code to generate an appropriate exception and return false. */ @@ -XXX,XX +XXX,XX @@ static void handle_sys(DisasContext *s, uint32_t insn, bool isread, default: g_assert_not_reached(); } - if ((ri->type & ARM_CP_FPU) && !fp_access_check(s)) { + if ((ri->type & ARM_CP_FPU) && !fp_access_check_only(s)) { return; } else if ((ri->type & ARM_CP_SVE) && !sve_access_check(s)) { return; @@ -XXX,XX +XXX,XX @@ static void disas_data_proc_simd_fp(DisasContext *s, uint32_t insn) } } +/* + * Include the generated SME FA64 decoder. + */ + +#include "decode-sme-fa64.c.inc" + +static bool trans_OK(DisasContext *s, arg_OK *a) +{ + return true; +} + +static bool trans_FAIL(DisasContext *s, arg_OK *a) +{ + s->is_nonstreaming = true; + return true; +} + /** * is_guarded_page: * @env: The cpu environment @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_init_disas_context(DisasContextBase *dcbase, dc->mte_active[1] = EX_TBFLAG_A64(tb_flags, MTE0_ACTIVE); dc->pstate_sm = EX_TBFLAG_A64(tb_flags, PSTATE_SM); dc->pstate_za = EX_TBFLAG_A64(tb_flags, PSTATE_ZA); + dc->sme_trap_nonstreaming = EX_TBFLAG_A64(tb_flags, SME_TRAP_NONSTREAMING); dc->vec_len = 0; dc->vec_stride = 0; dc->cp_regs = arm_cpu->cp_regs; @@ -XXX,XX +XXX,XX @@ static void aarch64_tr_translate_insn(DisasContextBase *dcbase, CPUState *cpu) } } + s->is_nonstreaming = false; + if (s->sme_trap_nonstreaming) { + disas_sme_fa64(s, insn); + } + switch (extract32(insn, 25, 4)) { case 0x0: if (!extract32(insn, 31, 1) || !disas_sme(s, insn)) { diff --git a/target/arm/translate-vfp.c b/target/arm/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-vfp.c +++ b/target/arm/translate-vfp.c @@ -XXX,XX +XXX,XX @@ static bool vfp_access_check_a(DisasContext *s, bool ignore_vfp_enabled) return false; } + /* + * Note that rebuild_hflags_a32 has already accounted for being in EL0 + * and the higher EL in A64 mode, etc. Unlike A64 mode, there do not + * appear to be any insns which touch VFP which are allowed. + */ + if (s->sme_trap_nonstreaming) { + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_smetrap(SME_ET_Streaming, + s->base.pc_next - s->pc_curr == 2)); + return false; + } + if (!s->vfp_enabled && !ignore_vfp_enabled) { assert(!arm_dc_feature(s, ARM_FEATURE_M)); unallocated_encoding(s); diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void arm_tr_init_disas_context(DisasContextBase *dcbase, CPUState *cs) dc->vec_len = EX_TBFLAG_A32(tb_flags, VECLEN); dc->vec_stride = EX_TBFLAG_A32(tb_flags, VECSTRIDE); } + dc->sme_trap_nonstreaming = + EX_TBFLAG_A32(tb_flags, SME_TRAP_NONSTREAMING); } dc->cp_regs = cpu->cp_regs; dc->features = env->features; diff --git a/target/arm/meson.build b/target/arm/meson.build index XXXXXXX..XXXXXXX 100644 --- a/target/arm/meson.build +++ b/target/arm/meson.build @@ -XXX,XX +XXX,XX @@ gen = [ decodetree.process('sve.decode', extra_args: '--decode=disas_sve'), decodetree.process('sme.decode', extra_args: '--decode=disas_sme'), + decodetree.process('sme-fa64.decode', extra_args: '--static-decode=disas_sme_fa64'), decodetree.process('neon-shared.decode', extra_args: '--decode=disas_neon_shared'), decodetree.process('neon-dp.decode', extra_args: '--decode=disas_neon_dp'), decodetree.process('neon-ls.decode', extra_args: '--decode=disas_neon_ls'), -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark ADR as a non-streaming instruction, which should trap if full a64 support is not enabled in streaming mode. Removing entries from sme-fa64.decode is an easy way to see what remains to be done. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate.h | 7 +++++++ target/arm/sme-fa64.decode | 1 - target/arm/translate-sve.c | 8 ++++---- 3 files changed, 11 insertions(+), 5 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ uint64_t asimd_imm_const(uint32_t imm, int cmode, int op); static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \ { return dc_isar_feature(FEAT, s) && FUNC(s, __VA_ARGS__); } +#define TRANS_FEAT_NONSTREAMING(NAME, FEAT, FUNC, ...) \ + static bool trans_##NAME(DisasContext *s, arg_##NAME *a) \ + { \ + s->is_nonstreaming = true; \ + return dc_isar_feature(FEAT, s) && FUNC(s, __VA_ARGS__); \ + } + #endif /* TARGET_ARM_TRANSLATE_H */ diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0000 0100 --1- ---- 1010 ---- ---- ---- # ADR FAIL 0000 0100 --1- ---- 1011 -0-- ---- ---- # FTSSEL, FEXPA FAIL 0000 0101 --10 0001 100- ---- ---- ---- # COMPACT FAIL 0010 0101 --01 100- 1111 000- ---0 ---- # RDFFR, RDFFRS diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_adr(DisasContext *s, arg_rrri *a, gen_helper_gvec_3 *fn) return gen_gvec_ool_zzz(s, fn, a->rd, a->rn, a->rm, a->imm); } -TRANS_FEAT(ADR_p32, aa64_sve, do_adr, a, gen_helper_sve_adr_p32) -TRANS_FEAT(ADR_p64, aa64_sve, do_adr, a, gen_helper_sve_adr_p64) -TRANS_FEAT(ADR_s32, aa64_sve, do_adr, a, gen_helper_sve_adr_s32) -TRANS_FEAT(ADR_u32, aa64_sve, do_adr, a, gen_helper_sve_adr_u32) +TRANS_FEAT_NONSTREAMING(ADR_p32, aa64_sve, do_adr, a, gen_helper_sve_adr_p32) +TRANS_FEAT_NONSTREAMING(ADR_p64, aa64_sve, do_adr, a, gen_helper_sve_adr_p64) +TRANS_FEAT_NONSTREAMING(ADR_s32, aa64_sve, do_adr, a, gen_helper_sve_adr_s32) +TRANS_FEAT_NONSTREAMING(ADR_u32, aa64_sve, do_adr, a, gen_helper_sve_adr_u32) /* *** SVE Integer Misc - Unpredicated Group -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 2 -- target/arm/translate-sve.c | 9 ++++++--- 2 files changed, 6 insertions(+), 5 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS FAIL 0000 0100 --1- ---- 1011 -0-- ---- ---- # FTSSEL, FEXPA FAIL 0000 0101 --10 0001 100- ---- ---- ---- # COMPACT -FAIL 0010 0101 --01 100- 1111 000- ---0 ---- # RDFFR, RDFFRS -FAIL 0010 0101 --10 1--- 1001 ---- ---- ---- # WRFFR, SETFFR FAIL 0100 0101 --0- ---- 1011 ---- ---- ---- # BDEP, BEXT, BGRP FAIL 0100 0101 000- ---- 0110 1--- ---- ---- # PMULLB, PMULLT (128b result) FAIL 0110 0100 --1- ---- 1110 01-- ---- ---- # FMMLA, BFMMLA diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_predset(DisasContext *s, int esz, int rd, int pat, bool setflag) TRANS_FEAT(PTRUE, aa64_sve, do_predset, a->esz, a->rd, a->pat, a->s) /* Note pat == 31 is #all, to set all elements. */ -TRANS_FEAT(SETFFR, aa64_sve, do_predset, 0, FFR_PRED_NUM, 31, false) +TRANS_FEAT_NONSTREAMING(SETFFR, aa64_sve, + do_predset, 0, FFR_PRED_NUM, 31, false) /* Note pat == 32 is #unimp, to set no elements. */ TRANS_FEAT(PFALSE, aa64_sve, do_predset, 0, a->rd, 32, false) @@ -XXX,XX +XXX,XX @@ static bool trans_RDFFR_p(DisasContext *s, arg_RDFFR_p *a) .rd = a->rd, .pg = a->pg, .s = a->s, .rn = FFR_PRED_NUM, .rm = FFR_PRED_NUM, }; + + s->is_nonstreaming = true; return trans_AND_pppp(s, &alt_a); } -TRANS_FEAT(RDFFR, aa64_sve, do_mov_p, a->rd, FFR_PRED_NUM) -TRANS_FEAT(WRFFR, aa64_sve, do_mov_p, FFR_PRED_NUM, a->rn) +TRANS_FEAT_NONSTREAMING(RDFFR, aa64_sve, do_mov_p, a->rd, FFR_PRED_NUM) +TRANS_FEAT_NONSTREAMING(WRFFR, aa64_sve, do_mov_p, FFR_PRED_NUM, a->rn) static bool do_pfirst_pnext(DisasContext *s, arg_rr_esz *a, void (*gen_fn)(TCGv_i32, TCGv_ptr, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 3 --- target/arm/translate-sve.c | 22 ++++++++++++---------- 2 files changed, 12 insertions(+), 13 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0000 0100 --1- ---- 1011 -0-- ---- ---- # FTSSEL, FEXPA -FAIL 0000 0101 --10 0001 100- ---- ---- ---- # COMPACT -FAIL 0100 0101 --0- ---- 1011 ---- ---- ---- # BDEP, BEXT, BGRP FAIL 0100 0101 000- ---- 0110 1--- ---- ---- # PMULLB, PMULLT (128b result) FAIL 0110 0100 --1- ---- 1110 01-- ---- ---- # FMMLA, BFMMLA FAIL 0110 0101 --0- ---- 0000 11-- ---- ---- # FTSMUL diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_2 * const fexpa_fns[4] = { NULL, gen_helper_sve_fexpa_h, gen_helper_sve_fexpa_s, gen_helper_sve_fexpa_d, }; -TRANS_FEAT(FEXPA, aa64_sve, gen_gvec_ool_zz, - fexpa_fns[a->esz], a->rd, a->rn, 0) +TRANS_FEAT_NONSTREAMING(FEXPA, aa64_sve, gen_gvec_ool_zz, + fexpa_fns[a->esz], a->rd, a->rn, 0) static gen_helper_gvec_3 * const ftssel_fns[4] = { NULL, gen_helper_sve_ftssel_h, gen_helper_sve_ftssel_s, gen_helper_sve_ftssel_d, }; -TRANS_FEAT(FTSSEL, aa64_sve, gen_gvec_ool_arg_zzz, ftssel_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(FTSSEL, aa64_sve, gen_gvec_ool_arg_zzz, + ftssel_fns[a->esz], a, 0) /* *** SVE Predicate Logical Operations Group @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(TRN2_q, aa64_sve_f64mm, gen_gvec_ool_arg_zzz, static gen_helper_gvec_3 * const compact_fns[4] = { NULL, NULL, gen_helper_sve_compact_s, gen_helper_sve_compact_d }; -TRANS_FEAT(COMPACT, aa64_sve, gen_gvec_ool_arg_zpz, compact_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(COMPACT, aa64_sve, gen_gvec_ool_arg_zpz, + compact_fns[a->esz], a, 0) /* Call the helper that computes the ARM LastActiveElement pseudocode * function, scaled by the element size. This includes the not found @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3 * const bext_fns[4] = { gen_helper_sve2_bext_b, gen_helper_sve2_bext_h, gen_helper_sve2_bext_s, gen_helper_sve2_bext_d, }; -TRANS_FEAT(BEXT, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, - bext_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(BEXT, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, + bext_fns[a->esz], a, 0) static gen_helper_gvec_3 * const bdep_fns[4] = { gen_helper_sve2_bdep_b, gen_helper_sve2_bdep_h, gen_helper_sve2_bdep_s, gen_helper_sve2_bdep_d, }; -TRANS_FEAT(BDEP, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, - bdep_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(BDEP, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, + bdep_fns[a->esz], a, 0) static gen_helper_gvec_3 * const bgrp_fns[4] = { gen_helper_sve2_bgrp_b, gen_helper_sve2_bgrp_h, gen_helper_sve2_bgrp_s, gen_helper_sve2_bgrp_d, }; -TRANS_FEAT(BGRP, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, - bgrp_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(BGRP, aa64_sve2_bitperm, gen_gvec_ool_arg_zzz, + bgrp_fns[a->esz], a, 0) static gen_helper_gvec_3 * const cadd_fns[4] = { gen_helper_sve2_cadd_b, gen_helper_sve2_cadd_h, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 2 -- target/arm/translate-sve.c | 24 +++++++++++++++--------- 2 files changed, 15 insertions(+), 11 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0100 0101 000- ---- 0110 1--- ---- ---- # PMULLB, PMULLT (128b result) -FAIL 0110 0100 --1- ---- 1110 01-- ---- ---- # FMMLA, BFMMLA FAIL 0110 0101 --0- ---- 0000 11-- ---- ---- # FTSMUL FAIL 0110 0101 --01 0--- 100- ---- ---- ---- # FTMAD FAIL 0110 0101 --01 1--- 001- ---- ---- ---- # FADDA diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_trans_pmull(DisasContext *s, arg_rrr_esz *a, bool sel) gen_helper_gvec_pmull_q, gen_helper_sve2_pmull_h, NULL, gen_helper_sve2_pmull_d, }; - if (a->esz == 0 - ? !dc_isar_feature(aa64_sve2_pmull128, s) - : !dc_isar_feature(aa64_sve, s)) { + + if (a->esz == 0) { + if (!dc_isar_feature(aa64_sve2_pmull128, s)) { + return false; + } + s->is_nonstreaming = true; + } else if (!dc_isar_feature(aa64_sve, s)) { return false; } return gen_gvec_ool_arg_zzz(s, fns[a->esz], a, sel); @@ -XXX,XX +XXX,XX @@ DO_ZPZZ_FP(FMINP, aa64_sve2, sve2_fminp_zpzz) * SVE Integer Multiply-Add (unpredicated) */ -TRANS_FEAT(FMMLA_s, aa64_sve_f32mm, gen_gvec_fpst_zzzz, gen_helper_fmmla_s, - a->rd, a->rn, a->rm, a->ra, 0, FPST_FPCR) -TRANS_FEAT(FMMLA_d, aa64_sve_f64mm, gen_gvec_fpst_zzzz, gen_helper_fmmla_d, - a->rd, a->rn, a->rm, a->ra, 0, FPST_FPCR) +TRANS_FEAT_NONSTREAMING(FMMLA_s, aa64_sve_f32mm, gen_gvec_fpst_zzzz, + gen_helper_fmmla_s, a->rd, a->rn, a->rm, a->ra, + 0, FPST_FPCR) +TRANS_FEAT_NONSTREAMING(FMMLA_d, aa64_sve_f64mm, gen_gvec_fpst_zzzz, + gen_helper_fmmla_d, a->rd, a->rn, a->rm, a->ra, + 0, FPST_FPCR) static gen_helper_gvec_4 * const sqdmlal_zzzw_fns[] = { NULL, gen_helper_sve2_sqdmlal_zzzw_h, @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(BFDOT_zzzz, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, TRANS_FEAT(BFDOT_zzxz, aa64_sve_bf16, gen_gvec_ool_arg_zzxz, gen_helper_gvec_bfdot_idx, a) -TRANS_FEAT(BFMMLA, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, - gen_helper_gvec_bfmmla, a, 0) +TRANS_FEAT_NONSTREAMING(BFMMLA, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_bfmmla, a, 0) static bool do_BFMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) { -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 3 --- target/arm/translate-sve.c | 15 +++++++++++---- 2 files changed, 11 insertions(+), 7 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0110 0101 --0- ---- 0000 11-- ---- ---- # FTSMUL -FAIL 0110 0101 --01 0--- 100- ---- ---- ---- # FTMAD -FAIL 0110 0101 --01 1--- 001- ---- ---- ---- # FADDA FAIL 0100 0101 --0- ---- 1001 10-- ---- ---- # SMMLA, UMMLA, USMMLA FAIL 0100 0101 --1- ---- 1--- ---- ---- ---- # SVE2 string/histo/crypto instructions FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const ftmad_fns[4] = { NULL, gen_helper_sve_ftmad_h, gen_helper_sve_ftmad_s, gen_helper_sve_ftmad_d, }; -TRANS_FEAT(FTMAD, aa64_sve, gen_gvec_fpst_zzz, - ftmad_fns[a->esz], a->rd, a->rn, a->rm, a->imm, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) +TRANS_FEAT_NONSTREAMING(FTMAD, aa64_sve, gen_gvec_fpst_zzz, + ftmad_fns[a->esz], a->rd, a->rn, a->rm, a->imm, + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) /* *** SVE Floating Point Accumulating Reduction Group @@ -XXX,XX +XXX,XX @@ static bool trans_FADDA(DisasContext *s, arg_rprr_esz *a) if (a->esz == 0 || !dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_FADDA(DisasContext *s, arg_rprr_esz *a) DO_FP3(FADD_zzz, fadd) DO_FP3(FSUB_zzz, fsub) DO_FP3(FMUL_zzz, fmul) -DO_FP3(FTSMUL, ftsmul) DO_FP3(FRECPS, recps) DO_FP3(FRSQRTS, rsqrts) #undef DO_FP3 +static gen_helper_gvec_3_ptr * const ftsmul_fns[4] = { + NULL, gen_helper_gvec_ftsmul_h, + gen_helper_gvec_ftsmul_s, gen_helper_gvec_ftsmul_d +}; +TRANS_FEAT_NONSTREAMING(FTSMUL, aa64_sve, gen_gvec_fpst_arg_zzz, + ftsmul_fns[a->esz], a, 0) + /* *** SVE Floating Point Arithmetic - Predicated Group */ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 1 - target/arm/translate-sve.c | 12 ++++++------ 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0100 0101 --0- ---- 1001 10-- ---- ---- # SMMLA, UMMLA, USMMLA FAIL 0100 0101 --1- ---- 1--- ---- ---- ---- # SVE2 string/histo/crypto instructions FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FMLALT_zzxw, aa64_sve2, do_FMLAL_zzxw, a, false, true) TRANS_FEAT(FMLSLB_zzxw, aa64_sve2, do_FMLAL_zzxw, a, true, false) TRANS_FEAT(FMLSLT_zzxw, aa64_sve2, do_FMLAL_zzxw, a, true, true) -TRANS_FEAT(SMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, - gen_helper_gvec_smmla_b, a, 0) -TRANS_FEAT(USMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, - gen_helper_gvec_usmmla_b, a, 0) -TRANS_FEAT(UMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, - gen_helper_gvec_ummla_b, a, 0) +TRANS_FEAT_NONSTREAMING(SMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_smmla_b, a, 0) +TRANS_FEAT_NONSTREAMING(USMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_usmmla_b, a, 0) +TRANS_FEAT_NONSTREAMING(UMMLA, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, + gen_helper_gvec_ummla_b, a, 0) TRANS_FEAT(BFDOT_zzzz, aa64_sve_bf16, gen_gvec_ool_arg_zzzz, gen_helper_gvec_bfdot, a, 0) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 1 - target/arm/translate-sve.c | 35 ++++++++++++++++++----------------- 2 files changed, 18 insertions(+), 18 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 0100 0101 --1- ---- 1--- ---- ---- ---- # SVE2 string/histo/crypto instructions FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) FAIL 1000 0100 0-1- ---- 0--- ---- ---- ---- # SVE 32-bit gather prefetch (scalar+vector) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ DO_SVE2_ZZZ_NARROW(RSUBHNT, rsubhnt) static gen_helper_gvec_flags_4 * const match_fns[4] = { gen_helper_sve2_match_ppzz_b, gen_helper_sve2_match_ppzz_h, NULL, NULL }; -TRANS_FEAT(MATCH, aa64_sve2, do_ppzz_flags, a, match_fns[a->esz]) +TRANS_FEAT_NONSTREAMING(MATCH, aa64_sve2, do_ppzz_flags, a, match_fns[a->esz]) static gen_helper_gvec_flags_4 * const nmatch_fns[4] = { gen_helper_sve2_nmatch_ppzz_b, gen_helper_sve2_nmatch_ppzz_h, NULL, NULL }; -TRANS_FEAT(NMATCH, aa64_sve2, do_ppzz_flags, a, nmatch_fns[a->esz]) +TRANS_FEAT_NONSTREAMING(NMATCH, aa64_sve2, do_ppzz_flags, a, nmatch_fns[a->esz]) static gen_helper_gvec_4 * const histcnt_fns[4] = { NULL, NULL, gen_helper_sve2_histcnt_s, gen_helper_sve2_histcnt_d }; -TRANS_FEAT(HISTCNT, aa64_sve2, gen_gvec_ool_arg_zpzz, - histcnt_fns[a->esz], a, 0) +TRANS_FEAT_NONSTREAMING(HISTCNT, aa64_sve2, gen_gvec_ool_arg_zpzz, + histcnt_fns[a->esz], a, 0) -TRANS_FEAT(HISTSEG, aa64_sve2, gen_gvec_ool_arg_zzz, - a->esz == 0 ? gen_helper_sve2_histseg : NULL, a, 0) +TRANS_FEAT_NONSTREAMING(HISTSEG, aa64_sve2, gen_gvec_ool_arg_zzz, + a->esz == 0 ? gen_helper_sve2_histseg : NULL, a, 0) DO_ZPZZ_FP(FADDP, aa64_sve2, sve2_faddp_zpzz) DO_ZPZZ_FP(FMAXNMP, aa64_sve2, sve2_fmaxnmp_zpzz) @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SQRDCMLAH_zzzz, aa64_sve2, gen_gvec_ool_zzzz, TRANS_FEAT(USDOT_zzzz, aa64_sve_i8mm, gen_gvec_ool_arg_zzzz, a->esz == 2 ? gen_helper_gvec_usdot_b : NULL, a, 0) -TRANS_FEAT(AESMC, aa64_sve2_aes, gen_gvec_ool_zz, - gen_helper_crypto_aesmc, a->rd, a->rd, a->decrypt) +TRANS_FEAT_NONSTREAMING(AESMC, aa64_sve2_aes, gen_gvec_ool_zz, + gen_helper_crypto_aesmc, a->rd, a->rd, a->decrypt) -TRANS_FEAT(AESE, aa64_sve2_aes, gen_gvec_ool_arg_zzz, - gen_helper_crypto_aese, a, false) -TRANS_FEAT(AESD, aa64_sve2_aes, gen_gvec_ool_arg_zzz, - gen_helper_crypto_aese, a, true) +TRANS_FEAT_NONSTREAMING(AESE, aa64_sve2_aes, gen_gvec_ool_arg_zzz, + gen_helper_crypto_aese, a, false) +TRANS_FEAT_NONSTREAMING(AESD, aa64_sve2_aes, gen_gvec_ool_arg_zzz, + gen_helper_crypto_aese, a, true) -TRANS_FEAT(SM4E, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, - gen_helper_crypto_sm4e, a, 0) -TRANS_FEAT(SM4EKEY, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, - gen_helper_crypto_sm4ekey, a, 0) +TRANS_FEAT_NONSTREAMING(SM4E, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, + gen_helper_crypto_sm4e, a, 0) +TRANS_FEAT_NONSTREAMING(SM4EKEY, aa64_sve2_sm4, gen_gvec_ool_arg_zzz, + gen_helper_crypto_sm4ekey, a, 0) -TRANS_FEAT(RAX1, aa64_sve2_sha3, gen_gvec_fn_arg_zzz, gen_gvec_rax1, a) +TRANS_FEAT_NONSTREAMING(RAX1, aa64_sve2_sha3, gen_gvec_fn_arg_zzz, + gen_gvec_rax1, a) TRANS_FEAT(FCVTNT_sh, aa64_sve2, gen_gvec_fpst_arg_zpz, gen_helper_sve2_fcvtnt_sh, a, 0, FPST_FPCR) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 9 --------- target/arm/translate-sve.c | 6 ++++++ 2 files changed, 6 insertions(+), 9 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 1000 010- -00- ---- 10-- ---- ---- ---- # SVE2 32-bit gather NT load (vector+scalar) FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) FAIL 1000 0100 0-1- ---- 0--- ---- ---- ---- # SVE 32-bit gather prefetch (scalar+vector) -FAIL 1000 010- -01- ---- 1--- ---- ---- ---- # SVE 32-bit gather load (vector+imm) -FAIL 1000 0100 0-0- ---- 0--- ---- ---- ---- # SVE 32-bit gather load byte (scalar+vector) -FAIL 1000 0100 1--- ---- 0--- ---- ---- ---- # SVE 32-bit gather load half (scalar+vector) -FAIL 1000 0101 0--- ---- 0--- ---- ---- ---- # SVE 32-bit gather load word (scalar+vector) FAIL 1010 010- ---- ---- 011- ---- ---- ---- # SVE contiguous FF load (scalar+scalar) FAIL 1010 010- ---1 ---- 101- ---- ---- ---- # SVE contiguous NF load (scalar+imm) FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) FAIL 1100 010- ---- ---- ---- ---- ---- ---- # SVE 64-bit gather load/prefetch -FAIL 1110 010- -00- ---- 001- ---- ---- ---- # SVE2 64-bit scatter NT store (vector+scalar) -FAIL 1110 010- -10- ---- 001- ---- ---- ---- # SVE2 32-bit scatter NT store (vector+scalar) -FAIL 1110 010- ---- ---- 1-0- ---- ---- ---- # SVE scatter store (scalar+32-bit vector) -FAIL 1110 010- ---- ---- 101- ---- ---- ---- # SVE scatter store (misc) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zprz(DisasContext *s, arg_LD1_zprz *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_LD1_zpiz(DisasContext *s, arg_LD1_zpiz *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_LDNT1_zprz(DisasContext *s, arg_LD1_zprz *a) if (!dc_isar_feature(aa64_sve2, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zprz(DisasContext *s, arg_ST1_zprz *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_ST1_zpiz(DisasContext *s, arg_ST1_zpiz *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_STNT1_zprz(DisasContext *s, arg_ST1_zprz *a) if (!dc_isar_feature(aa64_sve2, s)) { return false; } + s->is_nonstreaming = true; if (!sve_access_check(s)) { return true; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. In this case, introduce PRF_ns (prefetch non-streaming) to handle the checks. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 3 --- target/arm/sve.decode | 10 +++++----- target/arm/translate-sve.c | 11 +++++++++++ 3 files changed, 16 insertions(+), 8 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 1000 010- -00- ---- 111- ---- ---- ---- # SVE 32-bit gather prefetch (vector+imm) -FAIL 1000 0100 0-1- ---- 0--- ---- ---- ---- # SVE 32-bit gather prefetch (scalar+vector) FAIL 1010 010- ---- ---- 011- ---- ---- ---- # SVE contiguous FF load (scalar+scalar) FAIL 1010 010- ---1 ---- 101- ---- ---- ---- # SVE contiguous NF load (scalar+imm) FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) -FAIL 1100 010- ---- ---- ---- ---- ---- ---- # SVE 64-bit gather load/prefetch diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ LD1RO_zpri 1010010 .. 01 0.... 001 ... ..... ..... \ @rpri_load_msz nreg=0 # SVE 32-bit gather prefetch (scalar plus 32-bit scaled offsets) -PRF 1000010 00 -1 ----- 0-- --- ----- 0 ---- +PRF_ns 1000010 00 -1 ----- 0-- --- ----- 0 ---- # SVE 32-bit gather prefetch (vector plus immediate) -PRF 1000010 -- 00 ----- 111 --- ----- 0 ---- +PRF_ns 1000010 -- 00 ----- 111 --- ----- 0 ---- # SVE contiguous prefetch (scalar plus immediate) PRF 1000010 11 1- ----- 0-- --- ----- 0 ---- @@ -XXX,XX +XXX,XX @@ LD1_zpiz 1100010 .. 01 ..... 1.. ... ..... ..... \ @rpri_g_load esz=3 # SVE 64-bit gather prefetch (scalar plus 64-bit scaled offsets) -PRF 1100010 00 11 ----- 1-- --- ----- 0 ---- +PRF_ns 1100010 00 11 ----- 1-- --- ----- 0 ---- # SVE 64-bit gather prefetch (scalar plus unpacked 32-bit scaled offsets) -PRF 1100010 00 -1 ----- 0-- --- ----- 0 ---- +PRF_ns 1100010 00 -1 ----- 0-- --- ----- 0 ---- # SVE 64-bit gather prefetch (vector plus immediate) -PRF 1100010 -- 00 ----- 111 --- ----- 0 ---- +PRF_ns 1100010 -- 00 ----- 111 --- ----- 0 ---- ### SVE Memory Store Group diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_PRF_rr(DisasContext *s, arg_PRF_rr *a) return true; } +static bool trans_PRF_ns(DisasContext *s, arg_PRF_ns *a) +{ + if (!dc_isar_feature(aa64_sve, s)) { + return false; + } + /* Prefetch is a nop within QEMU. */ + s->is_nonstreaming = true; + (void)sve_access_check(s); + return true; +} + /* * Move Prefix * -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 2 -- target/arm/translate-sve.c | 2 ++ 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) -FAIL 1010 010- ---- ---- 011- ---- ---- ---- # SVE contiguous FF load (scalar+scalar) -FAIL 1010 010- ---1 ---- 101- ---- ---- ---- # SVE contiguous NF load (scalar+imm) FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LDFF1_zprr(DisasContext *s, arg_rprr_load *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (sve_access_check(s)) { TCGv_i64 addr = new_tmp_a64(s); tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype)); @@ -XXX,XX +XXX,XX @@ static bool trans_LDNF1_zpri(DisasContext *s, arg_rpri_load *a) if (!dc_isar_feature(aa64_sve, s)) { return false; } + s->is_nonstreaming = true; if (sve_access_check(s)) { int vsz = vec_full_reg_size(s); int elements = vsz >> dtype_esz[a->dtype]; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Mark these as a non-streaming instructions, which should trap if full a64 support is not enabled in streaming mode. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-15-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme-fa64.decode | 3 --- target/arm/translate-sve.c | 2 ++ 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/target/arm/sme-fa64.decode b/target/arm/sme-fa64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme-fa64.decode +++ b/target/arm/sme-fa64.decode @@ -XXX,XX +XXX,XX @@ FAIL 0001 1110 0111 1110 0000 00-- ---- ---- # FJCVTZS # --11 1100 --0- ---- ---- ---- ---- ---- # Load/store FP register (unscaled imm) # --11 1100 --1- ---- ---- ---- ---- --10 # Load/store FP register (register offset) # --11 1101 ---- ---- ---- ---- ---- ---- # Load/store FP register (scaled imm) - -FAIL 1010 010- -01- ---- 000- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+scalar) -FAIL 1010 010- -010 ---- 001- ---- ---- ---- # SVE load & replicate 32 bytes (scalar+imm) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_LD1RO_zprr(DisasContext *s, arg_rprr_load *a) if (a->rm == 31) { return false; } + s->is_nonstreaming = true; if (sve_access_check(s)) { TCGv_i64 addr = new_tmp_a64(s); tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), dtype_msz(a->dtype)); @@ -XXX,XX +XXX,XX @@ static bool trans_LD1RO_zpri(DisasContext *s, arg_rpri_load *a) if (!dc_isar_feature(aa64_sve_f64mm, s)) { return false; } + s->is_nonstreaming = true; if (sve_access_check(s)) { TCGv_i64 addr = new_tmp_a64(s); tcg_gen_addi_i64(addr, cpu_reg_sp(s, a->rn), a->imm * 32); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> These functions will be used to verify that the cpu is in the correct state for a given instruction. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-16-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 21 +++++++++++++++++++++ target/arm/translate-a64.c | 34 ++++++++++++++++++++++++++++++++++ 2 files changed, 55 insertions(+) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ void write_fp_dreg(DisasContext *s, int reg, TCGv_i64 v); bool logic_imm_decode_wmask(uint64_t *result, unsigned int immn, unsigned int imms, unsigned int immr); bool sve_access_check(DisasContext *s); +bool sme_enabled_check(DisasContext *s); +bool sme_enabled_check_with_svcr(DisasContext *s, unsigned); + +/* This function corresponds to CheckStreamingSVEEnabled. */ +static inline bool sme_sm_enabled_check(DisasContext *s) +{ + return sme_enabled_check_with_svcr(s, R_SVCR_SM_MASK); +} + +/* This function corresponds to CheckSMEAndZAEnabled. */ +static inline bool sme_za_enabled_check(DisasContext *s) +{ + return sme_enabled_check_with_svcr(s, R_SVCR_ZA_MASK); +} + +/* Note that this function corresponds to CheckStreamingSVEAndZAEnabled. */ +static inline bool sme_smza_enabled_check(DisasContext *s) +{ + return sme_enabled_check_with_svcr(s, R_SVCR_SM_MASK | R_SVCR_ZA_MASK); +} + TCGv_i64 clean_data_tbi(DisasContext *s, TCGv_i64 addr); TCGv_i64 gen_mte_check1(DisasContext *s, TCGv_i64 addr, bool is_write, bool tag_checked, int log2_size); diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool sme_access_check(DisasContext *s) return true; } +/* This function corresponds to CheckSMEEnabled. */ +bool sme_enabled_check(DisasContext *s) +{ + /* + * Note that unlike sve_excp_el, we have not constrained sme_excp_el + * to be zero when fp_excp_el has priority. This is because we need + * sme_excp_el by itself for cpregs access checks. + */ + if (!s->fp_excp_el || s->sme_excp_el < s->fp_excp_el) { + s->fp_access_checked = true; + return sme_access_check(s); + } + return fp_access_check_only(s); +} + +/* Common subroutine for CheckSMEAnd*Enabled. */ +bool sme_enabled_check_with_svcr(DisasContext *s, unsigned req) +{ + if (!sme_enabled_check(s)) { + return false; + } + if (FIELD_EX64(req, SVCR, SM) && !s->pstate_sm) { + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_smetrap(SME_ET_NotStreaming, false)); + return false; + } + if (FIELD_EX64(req, SVCR, ZA) && !s->pstate_za) { + gen_exception_insn(s, s->pc_curr, EXCP_UDEF, + syn_smetrap(SME_ET_InactiveZA, false)); + return false; + } + return true; +} + /* * This utility function is for doing register extension with an * optional shift. You will likely want to pass a temporary for the -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> The pseudocode for CheckSVEEnabled gains a check for Streaming SVE mode, and for SME present but SVE absent. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-17-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.c | 22 ++++++++++++++++------ 1 file changed, 16 insertions(+), 6 deletions(-) diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool fp_access_check(DisasContext *s) return true; } -/* Check that SVE access is enabled. If it is, return true. +/* + * Check that SVE access is enabled. If it is, return true. * If not, emit code to generate an appropriate exception and return false. + * This function corresponds to CheckSVEEnabled(). */ bool sve_access_check(DisasContext *s) { - if (s->sve_excp_el) { - assert(!s->sve_access_checked); - s->sve_access_checked = true; - + if (s->pstate_sm || !dc_isar_feature(aa64_sve, s)) { + assert(dc_isar_feature(aa64_sme, s)); + if (!sme_sm_enabled_check(s)) { + goto fail_exit; + } + } else if (s->sve_excp_el) { gen_exception_insn_el(s, s->pc_curr, EXCP_UDEF, syn_sve_access_trap(), s->sve_excp_el); - return false; + goto fail_exit; } s->sve_access_checked = true; return fp_access_check(s); + + fail_exit: + /* Assert that we only raise one exception per instruction. */ + assert(!s->sve_access_checked); + s->sve_access_checked = true; + return false; } /* -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> These SME instructions are nominally within the SVE decode space, so we add them to sve.decode and translate-sve.c. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-18-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 12 ++++++++++++ target/arm/sve.decode | 5 ++++- target/arm/translate-sve.c | 38 ++++++++++++++++++++++++++++++++++++++ 3 files changed, 54 insertions(+), 1 deletion(-) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ static inline int vec_full_reg_size(DisasContext *s) return s->vl; } +/* Return the byte size of the vector register, SVL / 8. */ +static inline int streaming_vec_reg_size(DisasContext *s) +{ + return s->svl; +} + /* * Return the offset info CPUARMState of the predicate vector register Pn. * Note for this purpose, FFR is P16. @@ -XXX,XX +XXX,XX @@ static inline int pred_full_reg_size(DisasContext *s) return s->vl >> 3; } +/* Return the byte size of the predicate register, SVL / 64. */ +static inline int streaming_pred_reg_size(DisasContext *s) +{ + return s->svl >> 3; +} + /* * Round up the size of a register to a size allowed by * the tcg vector infrastructure. Any operation which uses this diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ INDEX_ri 00000100 esz:2 1 imm:s5 010001 rn:5 rd:5 # SVE index generation (register start, register increment) INDEX_rr 00000100 .. 1 ..... 010011 ..... ..... @rd_rn_rm -### SVE Stack Allocation Group +### SVE / Streaming SVE Stack Allocation Group # SVE stack frame adjustment ADDVL 00000100 001 ..... 01010 ...... ..... @rd_rn_i6 +ADDSVL 00000100 001 ..... 01011 ...... ..... @rd_rn_i6 ADDPL 00000100 011 ..... 01010 ...... ..... @rd_rn_i6 +ADDSPL 00000100 011 ..... 01011 ...... ..... @rd_rn_i6 # SVE stack frame size RDVL 00000100 101 11111 01010 imm:s6 rd:5 +RDSVL 00000100 101 11111 01011 imm:s6 rd:5 ### SVE Bitwise Shift - Unpredicated Group diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_ADDVL(DisasContext *s, arg_ADDVL *a) return true; } +static bool trans_ADDSVL(DisasContext *s, arg_ADDSVL *a) +{ + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (sme_enabled_check(s)) { + TCGv_i64 rd = cpu_reg_sp(s, a->rd); + TCGv_i64 rn = cpu_reg_sp(s, a->rn); + tcg_gen_addi_i64(rd, rn, a->imm * streaming_vec_reg_size(s)); + } + return true; +} + static bool trans_ADDPL(DisasContext *s, arg_ADDPL *a) { if (!dc_isar_feature(aa64_sve, s)) { @@ -XXX,XX +XXX,XX @@ static bool trans_ADDPL(DisasContext *s, arg_ADDPL *a) return true; } +static bool trans_ADDSPL(DisasContext *s, arg_ADDSPL *a) +{ + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (sme_enabled_check(s)) { + TCGv_i64 rd = cpu_reg_sp(s, a->rd); + TCGv_i64 rn = cpu_reg_sp(s, a->rn); + tcg_gen_addi_i64(rd, rn, a->imm * streaming_pred_reg_size(s)); + } + return true; +} + static bool trans_RDVL(DisasContext *s, arg_RDVL *a) { if (!dc_isar_feature(aa64_sve, s)) { @@ -XXX,XX +XXX,XX @@ static bool trans_RDVL(DisasContext *s, arg_RDVL *a) return true; } +static bool trans_RDSVL(DisasContext *s, arg_RDSVL *a) +{ + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (sme_enabled_check(s)) { + TCGv_i64 reg = cpu_reg(s, a->rd); + tcg_gen_movi_i64(reg, a->imm * streaming_vec_reg_size(s)); + } + return true; +} + /* *** SVE Compute Vector Address Group */ -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-19-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 2 ++ target/arm/sme.decode | 4 ++++ target/arm/sme_helper.c | 25 +++++++++++++++++++++++++ target/arm/translate-sme.c | 13 +++++++++++++ 4 files changed, 44 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(set_pstate_sm, TCG_CALL_NO_RWG, void, env, i32) DEF_HELPER_FLAGS_2(set_pstate_za, TCG_CALL_NO_RWG, void, env, i32) + +DEF_HELPER_FLAGS_3(sme_zero, TCG_CALL_NO_RWG, void, env, i32, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ # # This file is processed by scripts/decodetree.py # + +### SME Misc + +ZERO 11000000 00 001 00000000000 imm:8 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ void helper_set_pstate_za(CPUARMState *env, uint32_t i) memset(env->zarray, 0, sizeof(env->zarray)); } } + +void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl) +{ + uint32_t i; + + /* + * Special case clearing the entire ZA space. + * This falls into the CONSTRAINED UNPREDICTABLE zeroing of any + * parts of the ZA storage outside of SVL. + */ + if (imm == 0xff) { + memset(env->zarray, 0, sizeof(env->zarray)); + return; + } + + /* + * Recall that ZAnH.D[m] is spread across ZA[n+8*m], + * so each row is discontiguous within ZA[]. + */ + for (i = 0; i < svl; i++) { + if (imm & (1 << (i % 8))) { + memset(&env->zarray[i], 0, svl); + } + } +} diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ */ #include "decode-sme.c.inc" + + +static bool trans_ZERO(DisasContext *s, arg_ZERO *a) +{ + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (sme_za_enabled_check(s)) { + gen_helper_sme_zero(cpu_env, tcg_constant_i32(a->imm), + tcg_constant_i32(streaming_vec_reg_size(s))); + } + return true; +} -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We can reuse the SVE functions for implementing moves to/from horizontal tile slices, but we need new ones for moves to/from vertical tile slices. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-20-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 12 +++ target/arm/helper-sve.h | 2 + target/arm/translate-a64.h | 8 ++ target/arm/translate.h | 5 ++ target/arm/sme.decode | 15 ++++ target/arm/sme_helper.c | 151 ++++++++++++++++++++++++++++++++++++- target/arm/sve_helper.c | 12 +++ target/arm/translate-sme.c | 127 +++++++++++++++++++++++++++++++ 8 files changed, 331 insertions(+), 1 deletion(-) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(set_pstate_sm, TCG_CALL_NO_RWG, void, env, i32) DEF_HELPER_FLAGS_2(set_pstate_za, TCG_CALL_NO_RWG, void, env, i32) DEF_HELPER_FLAGS_3(sme_zero, TCG_CALL_NO_RWG, void, env, i32, i32) + +/* Move to/from vertical array slices, i.e. columns, so 'c'. */ +DEF_HELPER_FLAGS_4(sme_mova_cz_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_cz_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_cz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_cz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_cz_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_mova_zc_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sve_sel_zpzz_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve_sel_zpzz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sve_sel_zpzz_q, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sve2_addp_zpzz_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ static inline int pred_gvec_reg_size(DisasContext *s) return size_for_gvec(pred_full_reg_size(s)); } +/* Return a newly allocated pointer to the predicate register. */ +static inline TCGv_ptr pred_full_reg_ptr(DisasContext *s, int regno) +{ + TCGv_ptr ret = tcg_temp_new_ptr(); + tcg_gen_addi_ptr(ret, cpu_env, pred_full_reg_offset(s, regno)); + return ret; +} + bool disas_sve(DisasContext *, uint32_t); bool disas_sme(DisasContext *, uint32_t); diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline int plus_2(DisasContext *s, int x) return x + 2; } +static inline int plus_12(DisasContext *s, int x) +{ + return x + 12; +} + static inline int times_2(DisasContext *s, int x) { return x * 2; diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ ### SME Misc ZERO 11000000 00 001 00000000000 imm:8 + +### SME Move into/from Array + +%mova_rs 13:2 !function=plus_12 +&mova esz rs pg zr za_imm v:bool to_vec:bool + +MOVA 11000000 esz:2 00000 0 v:1 .. pg:3 zr:5 0 za_imm:4 \ + &mova to_vec=0 rs=%mova_rs +MOVA 11000000 11 00000 1 v:1 .. pg:3 zr:5 0 za_imm:4 \ + &mova to_vec=0 rs=%mova_rs esz=4 + +MOVA 11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5 \ + &mova to_vec=1 rs=%mova_rs +MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za_imm:4 zr:5 \ + &mova to_vec=1 rs=%mova_rs esz=4 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" -#include "internals.h" +#include "tcg/tcg-gvec-desc.h" #include "exec/helper-proto.h" +#include "qemu/int128.h" +#include "vec_internal.h" /* ResetSVEState */ void arm_reset_sve_state(CPUARMState *env) @@ -XXX,XX +XXX,XX @@ void helper_sme_zero(CPUARMState *env, uint32_t imm, uint32_t svl) } } } + + +/* + * When considering the ZA storage as an array of elements of + * type T, the index within that array of the Nth element of + * a vertical slice of a tile can be calculated like this, + * regardless of the size of type T. This is because the tiles + * are interleaved, so if type T is size N bytes then row 1 of + * the tile is N rows away from row 0. The division by N to + * convert a byte offset into an array index and the multiplication + * by N to convert from vslice-index-within-the-tile to + * the index within the ZA storage cancel out. + */ +#define tile_vslice_index(i) ((i) * sizeof(ARMVectorReg)) + +/* + * When doing byte arithmetic on the ZA storage, the element + * byteoff bytes away in a tile vertical slice is always this + * many bytes away in the ZA storage, regardless of the + * size of the tile element, assuming that byteoff is a multiple + * of the element size. Again this is because of the interleaving + * of the tiles. For instance if we have 1 byte per element then + * each row of the ZA storage has one byte of the vslice data, + * and (counting from 0) byte 8 goes in row 8 of the storage + * at offset (8 * row-size-in-bytes). + * If we have 8 bytes per element then each row of the ZA storage + * has 8 bytes of the data, but there are 8 interleaved tiles and + * so byte 8 of the data goes into row 1 of the tile, + * which is again row 8 of the storage, so the offset is still + * (8 * row-size-in-bytes). Similarly for other element sizes. + */ +#define tile_vslice_offset(byteoff) ((byteoff) * sizeof(ARMVectorReg)) + + +/* + * Move Zreg vector to ZArray column. + */ +#define DO_MOVA_C(NAME, TYPE, H) \ +void HELPER(NAME)(void *za, void *vn, void *vg, uint32_t desc) \ +{ \ + int i, oprsz = simd_oprsz(desc); \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + if (pg & 1) { \ + *(TYPE *)(za + tile_vslice_offset(i)) = *(TYPE *)(vn + H(i)); \ + } \ + i += sizeof(TYPE); \ + pg >>= sizeof(TYPE); \ + } while (i & 15); \ + } \ +} + +DO_MOVA_C(sme_mova_cz_b, uint8_t, H1) +DO_MOVA_C(sme_mova_cz_h, uint16_t, H1_2) +DO_MOVA_C(sme_mova_cz_s, uint32_t, H1_4) + +void HELPER(sme_mova_cz_d)(void *za, void *vn, void *vg, uint32_t desc) +{ + int i, oprsz = simd_oprsz(desc) / 8; + uint8_t *pg = vg; + uint64_t *n = vn; + uint64_t *a = za; + + for (i = 0; i < oprsz; i++) { + if (pg[H1(i)] & 1) { + a[tile_vslice_index(i)] = n[i]; + } + } +} + +void HELPER(sme_mova_cz_q)(void *za, void *vn, void *vg, uint32_t desc) +{ + int i, oprsz = simd_oprsz(desc) / 16; + uint16_t *pg = vg; + Int128 *n = vn; + Int128 *a = za; + + /* + * Int128 is used here simply to copy 16 bytes, and to simplify + * the address arithmetic. + */ + for (i = 0; i < oprsz; i++) { + if (pg[H2(i)] & 1) { + a[tile_vslice_index(i)] = n[i]; + } + } +} + +#undef DO_MOVA_C + +/* + * Move ZArray column to Zreg vector. + */ +#define DO_MOVA_Z(NAME, TYPE, H) \ +void HELPER(NAME)(void *vd, void *za, void *vg, uint32_t desc) \ +{ \ + int i, oprsz = simd_oprsz(desc); \ + for (i = 0; i < oprsz; ) { \ + uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)); \ + do { \ + if (pg & 1) { \ + *(TYPE *)(vd + H(i)) = *(TYPE *)(za + tile_vslice_offset(i)); \ + } \ + i += sizeof(TYPE); \ + pg >>= sizeof(TYPE); \ + } while (i & 15); \ + } \ +} + +DO_MOVA_Z(sme_mova_zc_b, uint8_t, H1) +DO_MOVA_Z(sme_mova_zc_h, uint16_t, H1_2) +DO_MOVA_Z(sme_mova_zc_s, uint32_t, H1_4) + +void HELPER(sme_mova_zc_d)(void *vd, void *za, void *vg, uint32_t desc) +{ + int i, oprsz = simd_oprsz(desc) / 8; + uint8_t *pg = vg; + uint64_t *d = vd; + uint64_t *a = za; + + for (i = 0; i < oprsz; i++) { + if (pg[H1(i)] & 1) { + d[i] = a[tile_vslice_index(i)]; + } + } +} + +void HELPER(sme_mova_zc_q)(void *vd, void *za, void *vg, uint32_t desc) +{ + int i, oprsz = simd_oprsz(desc) / 16; + uint16_t *pg = vg; + Int128 *d = vd; + Int128 *a = za; + + /* + * Int128 is used here simply to copy 16 bytes, and to simplify + * the address arithmetic. + */ + for (i = 0; i < oprsz; i++, za += sizeof(ARMVectorReg)) { + if (pg[H2(i)] & 1) { + d[i] = a[tile_vslice_index(i)]; + } + } +} + +#undef DO_MOVA_Z diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sve_sel_zpzz_d)(void *vd, void *vn, void *vm, } } +void HELPER(sve_sel_zpzz_q)(void *vd, void *vn, void *vm, + void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 16; + Int128 *d = vd, *n = vn, *m = vm; + uint16_t *pg = vg; + + for (i = 0; i < opr_sz; i += 1) { + d[i] = (pg[H2(i)] & 1 ? n : m)[i]; + } +} + /* Two operand comparison controlled by a predicate. * ??? It is very tempting to want to be able to expand this inline * with x86 instructions, e.g. diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ #include "decode-sme.c.inc" +/* + * Resolve tile.size[index] to a host pointer, where tile and index + * are always decoded together, dependent on the element size. + */ +static TCGv_ptr get_tile_rowcol(DisasContext *s, int esz, int rs, + int tile_index, bool vertical) +{ + int tile = tile_index >> (4 - esz); + int index = esz == MO_128 ? 0 : extract32(tile_index, 0, 4 - esz); + int pos, len, offset; + TCGv_i32 tmp; + TCGv_ptr addr; + + /* Compute the final index, which is Rs+imm. */ + tmp = tcg_temp_new_i32(); + tcg_gen_trunc_tl_i32(tmp, cpu_reg(s, rs)); + tcg_gen_addi_i32(tmp, tmp, index); + + /* Prepare a power-of-two modulo via extraction of @len bits. */ + len = ctz32(streaming_vec_reg_size(s)) - esz; + + if (vertical) { + /* + * Compute the byte offset of the index within the tile: + * (index % (svl / size)) * size + * = (index % (svl >> esz)) << esz + * Perform the power-of-two modulo via extraction of the low @len bits. + * Perform the multiply by shifting left by @pos bits. + * Perform these operations simultaneously via deposit into zero. + */ + pos = esz; + tcg_gen_deposit_z_i32(tmp, tmp, pos, len); + + /* + * For big-endian, adjust the indexed column byte offset within + * the uint64_t host words that make up env->zarray[]. + */ + if (HOST_BIG_ENDIAN && esz < MO_64) { + tcg_gen_xori_i32(tmp, tmp, 8 - (1 << esz)); + } + } else { + /* + * Compute the byte offset of the index within the tile: + * (index % (svl / size)) * (size * sizeof(row)) + * = (index % (svl >> esz)) << (esz + log2(sizeof(row))) + */ + pos = esz + ctz32(sizeof(ARMVectorReg)); + tcg_gen_deposit_z_i32(tmp, tmp, pos, len); + + /* Row slices are always aligned and need no endian adjustment. */ + } + + /* The tile byte offset within env->zarray is the row. */ + offset = tile * sizeof(ARMVectorReg); + + /* Include the byte offset of zarray to make this relative to env. */ + offset += offsetof(CPUARMState, zarray); + tcg_gen_addi_i32(tmp, tmp, offset); + + /* Add the byte offset to env to produce the final pointer. */ + addr = tcg_temp_new_ptr(); + tcg_gen_ext_i32_ptr(addr, tmp); + tcg_temp_free_i32(tmp); + tcg_gen_add_ptr(addr, addr, cpu_env); + + return addr; +} + static bool trans_ZERO(DisasContext *s, arg_ZERO *a) { if (!dc_isar_feature(aa64_sme, s)) { @@ -XXX,XX +XXX,XX @@ static bool trans_ZERO(DisasContext *s, arg_ZERO *a) } return true; } + +static bool trans_MOVA(DisasContext *s, arg_MOVA *a) +{ + static gen_helper_gvec_4 * const h_fns[5] = { + gen_helper_sve_sel_zpzz_b, gen_helper_sve_sel_zpzz_h, + gen_helper_sve_sel_zpzz_s, gen_helper_sve_sel_zpzz_d, + gen_helper_sve_sel_zpzz_q + }; + static gen_helper_gvec_3 * const cz_fns[5] = { + gen_helper_sme_mova_cz_b, gen_helper_sme_mova_cz_h, + gen_helper_sme_mova_cz_s, gen_helper_sme_mova_cz_d, + gen_helper_sme_mova_cz_q, + }; + static gen_helper_gvec_3 * const zc_fns[5] = { + gen_helper_sme_mova_zc_b, gen_helper_sme_mova_zc_h, + gen_helper_sme_mova_zc_s, gen_helper_sme_mova_zc_d, + gen_helper_sme_mova_zc_q, + }; + + TCGv_ptr t_za, t_zr, t_pg; + TCGv_i32 t_desc; + int svl; + + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (!sme_smza_enabled_check(s)) { + return true; + } + + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v); + t_zr = vec_full_reg_ptr(s, a->zr); + t_pg = pred_full_reg_ptr(s, a->pg); + + svl = streaming_vec_reg_size(s); + t_desc = tcg_constant_i32(simd_desc(svl, svl, 0)); + + if (a->v) { + /* Vertical slice -- use sme mova helpers. */ + if (a->to_vec) { + zc_fns[a->esz](t_zr, t_za, t_pg, t_desc); + } else { + cz_fns[a->esz](t_za, t_zr, t_pg, t_desc); + } + } else { + /* Horizontal slice -- reuse sve sel helpers. */ + if (a->to_vec) { + h_fns[a->esz](t_zr, t_za, t_zr, t_pg, t_desc); + } else { + h_fns[a->esz](t_za, t_zr, t_za, t_pg, t_desc); + } + } + + tcg_temp_free_ptr(t_za); + tcg_temp_free_ptr(t_zr); + tcg_temp_free_ptr(t_pg); + + return true; +} -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We cannot reuse the SVE functions for LD[1-4] and ST[1-4], because those functions accept only a Zreg register number. For SME, we want to pass a pointer into ZA storage. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-21-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 82 +++++ target/arm/sme.decode | 9 + target/arm/sme_helper.c | 595 +++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 70 +++++ 4 files changed, 756 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sme_mova_cz_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme_mova_zc_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme_mova_cz_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sme_mova_zc_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(sme_ld1b_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1b_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1b_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1b_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_ld1h_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1h_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_ld1s_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1s_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_ld1d_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1d_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_ld1q_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_ld1q_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1b_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1b_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1b_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1b_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1h_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1h_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1s_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1s_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1d_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1d_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_st1q_be_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_le_h, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_be_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_le_v, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) +DEF_HELPER_FLAGS_5(sme_st1q_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ MOVA 11000000 esz:2 00001 0 v:1 .. pg:3 0 za_imm:4 zr:5 \ &mova to_vec=1 rs=%mova_rs MOVA 11000000 11 00001 1 v:1 .. pg:3 0 za_imm:4 zr:5 \ &mova to_vec=1 rs=%mova_rs esz=4 + +### SME Memory + +&ldst esz rs pg rn rm za_imm v:bool st:bool + +LDST1 1110000 0 esz:2 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ + &ldst rs=%mova_rs +LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ + &ldst esz=4 rs=%mova_rs diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "cpu.h" +#include "internals.h" #include "tcg/tcg-gvec-desc.h" #include "exec/helper-proto.h" +#include "exec/cpu_ldst.h" +#include "exec/exec-all.h" #include "qemu/int128.h" #include "vec_internal.h" +#include "sve_ldst_internal.h" /* ResetSVEState */ void arm_reset_sve_state(CPUARMState *env) @@ -XXX,XX +XXX,XX @@ void HELPER(sme_mova_zc_q)(void *vd, void *za, void *vg, uint32_t desc) } #undef DO_MOVA_Z + +/* + * Clear elements in a tile slice comprising len bytes. + */ + +typedef void ClearFn(void *ptr, size_t off, size_t len); + +static void clear_horizontal(void *ptr, size_t off, size_t len) +{ + memset(ptr + off, 0, len); +} + +static void clear_vertical_b(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; ++i) { + *(uint8_t *)(vptr + tile_vslice_offset(i + off)) = 0; + } +} + +static void clear_vertical_h(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; i += 2) { + *(uint16_t *)(vptr + tile_vslice_offset(i + off)) = 0; + } +} + +static void clear_vertical_s(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; i += 4) { + *(uint32_t *)(vptr + tile_vslice_offset(i + off)) = 0; + } +} + +static void clear_vertical_d(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; i += 8) { + *(uint64_t *)(vptr + tile_vslice_offset(i + off)) = 0; + } +} + +static void clear_vertical_q(void *vptr, size_t off, size_t len) +{ + for (size_t i = 0; i < len; i += 16) { + memset(vptr + tile_vslice_offset(i + off), 0, 16); + } +} + +/* + * Copy elements from an array into a tile slice comprising len bytes. + */ + +typedef void CopyFn(void *dst, const void *src, size_t len); + +static void copy_horizontal(void *dst, const void *src, size_t len) +{ + memcpy(dst, src, len); +} + +static void copy_vertical_b(void *vdst, const void *vsrc, size_t len) +{ + const uint8_t *src = vsrc; + uint8_t *dst = vdst; + size_t i; + + for (i = 0; i < len; ++i) { + dst[tile_vslice_index(i)] = src[i]; + } +} + +static void copy_vertical_h(void *vdst, const void *vsrc, size_t len) +{ + const uint16_t *src = vsrc; + uint16_t *dst = vdst; + size_t i; + + for (i = 0; i < len / 2; ++i) { + dst[tile_vslice_index(i)] = src[i]; + } +} + +static void copy_vertical_s(void *vdst, const void *vsrc, size_t len) +{ + const uint32_t *src = vsrc; + uint32_t *dst = vdst; + size_t i; + + for (i = 0; i < len / 4; ++i) { + dst[tile_vslice_index(i)] = src[i]; + } +} + +static void copy_vertical_d(void *vdst, const void *vsrc, size_t len) +{ + const uint64_t *src = vsrc; + uint64_t *dst = vdst; + size_t i; + + for (i = 0; i < len / 8; ++i) { + dst[tile_vslice_index(i)] = src[i]; + } +} + +static void copy_vertical_q(void *vdst, const void *vsrc, size_t len) +{ + for (size_t i = 0; i < len; i += 16) { + memcpy(vdst + tile_vslice_offset(i), vsrc + i, 16); + } +} + +/* + * Host and TLB primitives for vertical tile slice addressing. + */ + +#define DO_LD(NAME, TYPE, HOST, TLB) \ +static inline void sme_##NAME##_v_host(void *za, intptr_t off, void *host) \ +{ \ + TYPE val = HOST(host); \ + *(TYPE *)(za + tile_vslice_offset(off)) = val; \ +} \ +static inline void sme_##NAME##_v_tlb(CPUARMState *env, void *za, \ + intptr_t off, target_ulong addr, uintptr_t ra) \ +{ \ + TYPE val = TLB(env, useronly_clean_ptr(addr), ra); \ + *(TYPE *)(za + tile_vslice_offset(off)) = val; \ +} + +#define DO_ST(NAME, TYPE, HOST, TLB) \ +static inline void sme_##NAME##_v_host(void *za, intptr_t off, void *host) \ +{ \ + TYPE val = *(TYPE *)(za + tile_vslice_offset(off)); \ + HOST(host, val); \ +} \ +static inline void sme_##NAME##_v_tlb(CPUARMState *env, void *za, \ + intptr_t off, target_ulong addr, uintptr_t ra) \ +{ \ + TYPE val = *(TYPE *)(za + tile_vslice_offset(off)); \ + TLB(env, useronly_clean_ptr(addr), val, ra); \ +} + +/* + * The ARMVectorReg elements are stored in host-endian 64-bit units. + * For 128-bit quantities, the sequence defined by the Elem[] pseudocode + * corresponds to storing the two 64-bit pieces in little-endian order. + */ +#define DO_LDQ(HNAME, VNAME, BE, HOST, TLB) \ +static inline void HNAME##_host(void *za, intptr_t off, void *host) \ +{ \ + uint64_t val0 = HOST(host), val1 = HOST(host + 8); \ + uint64_t *ptr = za + off; \ + ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1; \ +} \ +static inline void VNAME##_v_host(void *za, intptr_t off, void *host) \ +{ \ + HNAME##_host(za, tile_vslice_offset(off), host); \ +} \ +static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off, \ + target_ulong addr, uintptr_t ra) \ +{ \ + uint64_t val0 = TLB(env, useronly_clean_ptr(addr), ra); \ + uint64_t val1 = TLB(env, useronly_clean_ptr(addr + 8), ra); \ + uint64_t *ptr = za + off; \ + ptr[0] = BE ? val1 : val0, ptr[1] = BE ? val0 : val1; \ +} \ +static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off, \ + target_ulong addr, uintptr_t ra) \ +{ \ + HNAME##_tlb(env, za, tile_vslice_offset(off), addr, ra); \ +} + +#define DO_STQ(HNAME, VNAME, BE, HOST, TLB) \ +static inline void HNAME##_host(void *za, intptr_t off, void *host) \ +{ \ + uint64_t *ptr = za + off; \ + HOST(host, ptr[BE]); \ + HOST(host + 1, ptr[!BE]); \ +} \ +static inline void VNAME##_v_host(void *za, intptr_t off, void *host) \ +{ \ + HNAME##_host(za, tile_vslice_offset(off), host); \ +} \ +static inline void HNAME##_tlb(CPUARMState *env, void *za, intptr_t off, \ + target_ulong addr, uintptr_t ra) \ +{ \ + uint64_t *ptr = za + off; \ + TLB(env, useronly_clean_ptr(addr), ptr[BE], ra); \ + TLB(env, useronly_clean_ptr(addr + 8), ptr[!BE], ra); \ +} \ +static inline void VNAME##_v_tlb(CPUARMState *env, void *za, intptr_t off, \ + target_ulong addr, uintptr_t ra) \ +{ \ + HNAME##_tlb(env, za, tile_vslice_offset(off), addr, ra); \ +} + +DO_LD(ld1b, uint8_t, ldub_p, cpu_ldub_data_ra) +DO_LD(ld1h_be, uint16_t, lduw_be_p, cpu_lduw_be_data_ra) +DO_LD(ld1h_le, uint16_t, lduw_le_p, cpu_lduw_le_data_ra) +DO_LD(ld1s_be, uint32_t, ldl_be_p, cpu_ldl_be_data_ra) +DO_LD(ld1s_le, uint32_t, ldl_le_p, cpu_ldl_le_data_ra) +DO_LD(ld1d_be, uint64_t, ldq_be_p, cpu_ldq_be_data_ra) +DO_LD(ld1d_le, uint64_t, ldq_le_p, cpu_ldq_le_data_ra) + +DO_LDQ(sve_ld1qq_be, sme_ld1q_be, 1, ldq_be_p, cpu_ldq_be_data_ra) +DO_LDQ(sve_ld1qq_le, sme_ld1q_le, 0, ldq_le_p, cpu_ldq_le_data_ra) + +DO_ST(st1b, uint8_t, stb_p, cpu_stb_data_ra) +DO_ST(st1h_be, uint16_t, stw_be_p, cpu_stw_be_data_ra) +DO_ST(st1h_le, uint16_t, stw_le_p, cpu_stw_le_data_ra) +DO_ST(st1s_be, uint32_t, stl_be_p, cpu_stl_be_data_ra) +DO_ST(st1s_le, uint32_t, stl_le_p, cpu_stl_le_data_ra) +DO_ST(st1d_be, uint64_t, stq_be_p, cpu_stq_be_data_ra) +DO_ST(st1d_le, uint64_t, stq_le_p, cpu_stq_le_data_ra) + +DO_STQ(sve_st1qq_be, sme_st1q_be, 1, stq_be_p, cpu_stq_be_data_ra) +DO_STQ(sve_st1qq_le, sme_st1q_le, 0, stq_le_p, cpu_stq_le_data_ra) + +#undef DO_LD +#undef DO_ST +#undef DO_LDQ +#undef DO_STQ + +/* + * Common helper for all contiguous predicated loads. + */ + +static inline QEMU_ALWAYS_INLINE +void sme_ld1(CPUARMState *env, void *za, uint64_t *vg, + const target_ulong addr, uint32_t desc, const uintptr_t ra, + const int esz, uint32_t mtedesc, bool vertical, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn, + ClearFn *clr_fn, + CopyFn *cpy_fn) +{ + const intptr_t reg_max = simd_oprsz(desc); + const intptr_t esize = 1 << esz; + intptr_t reg_off, reg_last; + SVEContLdSt info; + void *host; + int flags; + + /* Find the active elements. */ + if (!sve_cont_ldst_elements(&info, addr, vg, reg_max, esz, esize)) { + /* The entire predicate was false; no load occurs. */ + clr_fn(za, 0, reg_max); + return; + } + + /* Probe the page(s). Exit with exception for any invalid page. */ + sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_LOAD, ra); + + /* Handle watchpoints for all active elements. */ + sve_cont_ldst_watchpoints(&info, env, vg, addr, esize, esize, + BP_MEM_READ, ra); + + /* + * Handle mte checks for all active elements. + * Since TBI must be set for MTE, !mtedesc => !mte_active. + */ + if (mtedesc) { + sve_cont_ldst_mte_check(&info, env, vg, addr, esize, esize, + mtedesc, ra); + } + + flags = info.page[0].flags | info.page[1].flags; + if (unlikely(flags != 0)) { +#ifdef CONFIG_USER_ONLY + g_assert_not_reached(); +#else + /* + * At least one page includes MMIO. + * Any bus operation can fail with cpu_transaction_failed, + * which for ARM will raise SyncExternal. Perform the load + * into scratch memory to preserve register state until the end. + */ + ARMVectorReg scratch = { }; + + reg_off = info.reg_off_first[0]; + reg_last = info.reg_off_last[1]; + if (reg_last < 0) { + reg_last = info.reg_off_split; + if (reg_last < 0) { + reg_last = info.reg_off_last[0]; + } + } + + do { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + tlb_fn(env, &scratch, reg_off, addr + reg_off, ra); + } + reg_off += esize; + } while (reg_off & 63); + } while (reg_off <= reg_last); + + cpy_fn(za, &scratch, reg_max); + return; +#endif + } + + /* The entire operation is in RAM, on valid pages. */ + + reg_off = info.reg_off_first[0]; + reg_last = info.reg_off_last[0]; + host = info.page[0].host; + + if (!vertical) { + memset(za, 0, reg_max); + } else if (reg_off) { + clr_fn(za, 0, reg_off); + } + + while (reg_off <= reg_last) { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + host_fn(za, reg_off, host + reg_off); + } else if (vertical) { + clr_fn(za, reg_off, esize); + } + reg_off += esize; + } while (reg_off <= reg_last && (reg_off & 63)); + } + + /* + * Use the slow path to manage the cross-page misalignment. + * But we know this is RAM and cannot trap. + */ + reg_off = info.reg_off_split; + if (unlikely(reg_off >= 0)) { + tlb_fn(env, za, reg_off, addr + reg_off, ra); + } + + reg_off = info.reg_off_first[1]; + if (unlikely(reg_off >= 0)) { + reg_last = info.reg_off_last[1]; + host = info.page[1].host; + + do { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + host_fn(za, reg_off, host + reg_off); + } else if (vertical) { + clr_fn(za, reg_off, esize); + } + reg_off += esize; + } while (reg_off & 63); + } while (reg_off <= reg_last); + } +} + +static inline QEMU_ALWAYS_INLINE +void sme_ld1_mte(CPUARMState *env, void *za, uint64_t *vg, + target_ulong addr, uint32_t desc, uintptr_t ra, + const int esz, bool vertical, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn, + ClearFn *clr_fn, + CopyFn *cpy_fn) +{ + uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + int bit55 = extract64(addr, 55, 1); + + /* Remove mtedesc from the normal sve descriptor. */ + desc = extract32(desc, 0, SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + + /* Perform gross MTE suppression early. */ + if (!tbi_check(desc, bit55) || + tcma_check(desc, bit55, allocation_tag_from_addr(addr))) { + mtedesc = 0; + } + + sme_ld1(env, za, vg, addr, desc, ra, esz, mtedesc, vertical, + host_fn, tlb_fn, clr_fn, cpy_fn); +} + +#define DO_LD(L, END, ESZ) \ +void HELPER(sme_ld1##L##END##_h)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_ld1(env, za, vg, addr, desc, GETPC(), ESZ, 0, false, \ + sve_ld1##L##L##END##_host, sve_ld1##L##L##END##_tlb, \ + clear_horizontal, copy_horizontal); \ +} \ +void HELPER(sme_ld1##L##END##_v)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_ld1(env, za, vg, addr, desc, GETPC(), ESZ, 0, true, \ + sme_ld1##L##END##_v_host, sme_ld1##L##END##_v_tlb, \ + clear_vertical_##L, copy_vertical_##L); \ +} \ +void HELPER(sme_ld1##L##END##_h_mte)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_ld1_mte(env, za, vg, addr, desc, GETPC(), ESZ, false, \ + sve_ld1##L##L##END##_host, sve_ld1##L##L##END##_tlb, \ + clear_horizontal, copy_horizontal); \ +} \ +void HELPER(sme_ld1##L##END##_v_mte)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_ld1_mte(env, za, vg, addr, desc, GETPC(), ESZ, true, \ + sme_ld1##L##END##_v_host, sme_ld1##L##END##_v_tlb, \ + clear_vertical_##L, copy_vertical_##L); \ +} + +DO_LD(b, , MO_8) +DO_LD(h, _be, MO_16) +DO_LD(h, _le, MO_16) +DO_LD(s, _be, MO_32) +DO_LD(s, _le, MO_32) +DO_LD(d, _be, MO_64) +DO_LD(d, _le, MO_64) +DO_LD(q, _be, MO_128) +DO_LD(q, _le, MO_128) + +#undef DO_LD + +/* + * Common helper for all contiguous predicated stores. + */ + +static inline QEMU_ALWAYS_INLINE +void sme_st1(CPUARMState *env, void *za, uint64_t *vg, + const target_ulong addr, uint32_t desc, const uintptr_t ra, + const int esz, uint32_t mtedesc, bool vertical, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn) +{ + const intptr_t reg_max = simd_oprsz(desc); + const intptr_t esize = 1 << esz; + intptr_t reg_off, reg_last; + SVEContLdSt info; + void *host; + int flags; + + /* Find the active elements. */ + if (!sve_cont_ldst_elements(&info, addr, vg, reg_max, esz, esize)) { + /* The entire predicate was false; no store occurs. */ + return; + } + + /* Probe the page(s). Exit with exception for any invalid page. */ + sve_cont_ldst_pages(&info, FAULT_ALL, env, addr, MMU_DATA_STORE, ra); + + /* Handle watchpoints for all active elements. */ + sve_cont_ldst_watchpoints(&info, env, vg, addr, esize, esize, + BP_MEM_WRITE, ra); + + /* + * Handle mte checks for all active elements. + * Since TBI must be set for MTE, !mtedesc => !mte_active. + */ + if (mtedesc) { + sve_cont_ldst_mte_check(&info, env, vg, addr, esize, esize, + mtedesc, ra); + } + + flags = info.page[0].flags | info.page[1].flags; + if (unlikely(flags != 0)) { +#ifdef CONFIG_USER_ONLY + g_assert_not_reached(); +#else + /* + * At least one page includes MMIO. + * Any bus operation can fail with cpu_transaction_failed, + * which for ARM will raise SyncExternal. We cannot avoid + * this fault and will leave with the store incomplete. + */ + reg_off = info.reg_off_first[0]; + reg_last = info.reg_off_last[1]; + if (reg_last < 0) { + reg_last = info.reg_off_split; + if (reg_last < 0) { + reg_last = info.reg_off_last[0]; + } + } + + do { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + tlb_fn(env, za, reg_off, addr + reg_off, ra); + } + reg_off += esize; + } while (reg_off & 63); + } while (reg_off <= reg_last); + return; +#endif + } + + reg_off = info.reg_off_first[0]; + reg_last = info.reg_off_last[0]; + host = info.page[0].host; + + while (reg_off <= reg_last) { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + host_fn(za, reg_off, host + reg_off); + } + reg_off += 1 << esz; + } while (reg_off <= reg_last && (reg_off & 63)); + } + + /* + * Use the slow path to manage the cross-page misalignment. + * But we know this is RAM and cannot trap. + */ + reg_off = info.reg_off_split; + if (unlikely(reg_off >= 0)) { + tlb_fn(env, za, reg_off, addr + reg_off, ra); + } + + reg_off = info.reg_off_first[1]; + if (unlikely(reg_off >= 0)) { + reg_last = info.reg_off_last[1]; + host = info.page[1].host; + + do { + uint64_t pg = vg[reg_off >> 6]; + do { + if ((pg >> (reg_off & 63)) & 1) { + host_fn(za, reg_off, host + reg_off); + } + reg_off += 1 << esz; + } while (reg_off & 63); + } while (reg_off <= reg_last); + } +} + +static inline QEMU_ALWAYS_INLINE +void sme_st1_mte(CPUARMState *env, void *za, uint64_t *vg, target_ulong addr, + uint32_t desc, uintptr_t ra, int esz, bool vertical, + sve_ldst1_host_fn *host_fn, + sve_ldst1_tlb_fn *tlb_fn) +{ + uint32_t mtedesc = desc >> (SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + int bit55 = extract64(addr, 55, 1); + + /* Remove mtedesc from the normal sve descriptor. */ + desc = extract32(desc, 0, SIMD_DATA_SHIFT + SVE_MTEDESC_SHIFT); + + /* Perform gross MTE suppression early. */ + if (!tbi_check(desc, bit55) || + tcma_check(desc, bit55, allocation_tag_from_addr(addr))) { + mtedesc = 0; + } + + sme_st1(env, za, vg, addr, desc, ra, esz, mtedesc, + vertical, host_fn, tlb_fn); +} + +#define DO_ST(L, END, ESZ) \ +void HELPER(sme_st1##L##END##_h)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_st1(env, za, vg, addr, desc, GETPC(), ESZ, 0, false, \ + sve_st1##L##L##END##_host, sve_st1##L##L##END##_tlb); \ +} \ +void HELPER(sme_st1##L##END##_v)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_st1(env, za, vg, addr, desc, GETPC(), ESZ, 0, true, \ + sme_st1##L##END##_v_host, sme_st1##L##END##_v_tlb); \ +} \ +void HELPER(sme_st1##L##END##_h_mte)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_st1_mte(env, za, vg, addr, desc, GETPC(), ESZ, false, \ + sve_st1##L##L##END##_host, sve_st1##L##L##END##_tlb); \ +} \ +void HELPER(sme_st1##L##END##_v_mte)(CPUARMState *env, void *za, void *vg, \ + target_ulong addr, uint32_t desc) \ +{ \ + sme_st1_mte(env, za, vg, addr, desc, GETPC(), ESZ, true, \ + sme_st1##L##END##_v_host, sme_st1##L##END##_v_tlb); \ +} + +DO_ST(b, , MO_8) +DO_ST(h, _be, MO_16) +DO_ST(h, _le, MO_16) +DO_ST(s, _be, MO_32) +DO_ST(s, _le, MO_32) +DO_ST(d, _be, MO_64) +DO_ST(d, _le, MO_64) +DO_ST(q, _be, MO_128) +DO_ST(q, _le, MO_128) + +#undef DO_ST diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ static bool trans_MOVA(DisasContext *s, arg_MOVA *a) return true; } + +static bool trans_LDST1(DisasContext *s, arg_LDST1 *a) +{ + typedef void GenLdSt1(TCGv_env, TCGv_ptr, TCGv_ptr, TCGv, TCGv_i32); + + /* + * Indexed by [esz][be][v][mte][st], which is (except for load/store) + * also the order in which the elements appear in the function names, + * and so how we must concatenate the pieces. + */ + +#define FN_LS(F) { gen_helper_sme_ld1##F, gen_helper_sme_st1##F } +#define FN_MTE(F) { FN_LS(F), FN_LS(F##_mte) } +#define FN_HV(F) { FN_MTE(F##_h), FN_MTE(F##_v) } +#define FN_END(L, B) { FN_HV(L), FN_HV(B) } + + static GenLdSt1 * const fns[5][2][2][2][2] = { + FN_END(b, b), + FN_END(h_le, h_be), + FN_END(s_le, s_be), + FN_END(d_le, d_be), + FN_END(q_le, q_be), + }; + +#undef FN_LS +#undef FN_MTE +#undef FN_HV +#undef FN_END + + TCGv_ptr t_za, t_pg; + TCGv_i64 addr; + int svl, desc = 0; + bool be = s->be_data == MO_BE; + bool mte = s->mte_active[0]; + + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (!sme_smza_enabled_check(s)) { + return true; + } + + t_za = get_tile_rowcol(s, a->esz, a->rs, a->za_imm, a->v); + t_pg = pred_full_reg_ptr(s, a->pg); + addr = tcg_temp_new_i64(); + + tcg_gen_shli_i64(addr, cpu_reg(s, a->rm), a->esz); + tcg_gen_add_i64(addr, addr, cpu_reg_sp(s, a->rn)); + + if (mte) { + desc = FIELD_DP32(desc, MTEDESC, MIDX, get_mem_index(s)); + desc = FIELD_DP32(desc, MTEDESC, TBI, s->tbid); + desc = FIELD_DP32(desc, MTEDESC, TCMA, s->tcma); + desc = FIELD_DP32(desc, MTEDESC, WRITE, a->st); + desc = FIELD_DP32(desc, MTEDESC, SIZEM1, (1 << a->esz) - 1); + desc <<= SVE_MTEDESC_SHIFT; + } else { + addr = clean_data_tbi(s, addr); + } + svl = streaming_vec_reg_size(s); + desc = simd_desc(svl, svl, desc); + + fns[a->esz][be][a->v][mte][a->st](cpu_env, t_za, t_pg, addr, + tcg_constant_i32(desc)); + + tcg_temp_free_ptr(t_za); + tcg_temp_free_ptr(t_pg); + tcg_temp_free_i64(addr); + return true; +} -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Add a TCGv_ptr base argument, which will be cpu_env for SVE. We will reuse this for SME save and restore array insns. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-22-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/translate-a64.h | 3 +++ target/arm/translate-sve.c | 48 ++++++++++++++++++++++++++++---------- 2 files changed, 39 insertions(+), 12 deletions(-) diff --git a/target/arm/translate-a64.h b/target/arm/translate-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.h +++ b/target/arm/translate-a64.h @@ -XXX,XX +XXX,XX @@ void gen_gvec_xar(unsigned vece, uint32_t rd_ofs, uint32_t rn_ofs, uint32_t rm_ofs, int64_t shift, uint32_t opr_sz, uint32_t max_sz); +void gen_sve_ldr(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm); +void gen_sve_str(DisasContext *s, TCGv_ptr, int vofs, int len, int rn, int imm); + #endif /* TARGET_ARM_TRANSLATE_A64_H */ diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz, * The load should begin at the address Rn + IMM. */ -static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) +void gen_sve_ldr(DisasContext *s, TCGv_ptr base, int vofs, + int len, int rn, int imm) { int len_align = QEMU_ALIGN_DOWN(len, 8); int len_remain = len % 8; @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) t0 = tcg_temp_new_i64(); for (i = 0; i < len_align; i += 8) { tcg_gen_qemu_ld_i64(t0, clean_addr, midx, MO_LEUQ); - tcg_gen_st_i64(t0, cpu_env, vofs + i); + tcg_gen_st_i64(t0, base, vofs + i); tcg_gen_addi_i64(clean_addr, clean_addr, 8); } tcg_temp_free_i64(t0); @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) clean_addr = new_tmp_a64_local(s); tcg_gen_mov_i64(clean_addr, t0); + if (base != cpu_env) { + TCGv_ptr b = tcg_temp_local_new_ptr(); + tcg_gen_mov_ptr(b, base); + base = b; + } + gen_set_label(loop); t0 = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) tcg_gen_addi_i64(clean_addr, clean_addr, 8); tp = tcg_temp_new_ptr(); - tcg_gen_add_ptr(tp, cpu_env, i); + tcg_gen_add_ptr(tp, base, i); tcg_gen_addi_ptr(i, i, 8); tcg_gen_st_i64(t0, tp, vofs); tcg_temp_free_ptr(tp); @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop); tcg_temp_free_ptr(i); + + if (base != cpu_env) { + tcg_temp_free_ptr(base); + assert(len_remain == 0); + } } /* @@ -XXX,XX +XXX,XX @@ static void do_ldr(DisasContext *s, uint32_t vofs, int len, int rn, int imm) default: g_assert_not_reached(); } - tcg_gen_st_i64(t0, cpu_env, vofs + len_align); + tcg_gen_st_i64(t0, base, vofs + len_align); tcg_temp_free_i64(t0); } } /* Similarly for stores. */ -static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm) +void gen_sve_str(DisasContext *s, TCGv_ptr base, int vofs, + int len, int rn, int imm) { int len_align = QEMU_ALIGN_DOWN(len, 8); int len_remain = len % 8; @@ -XXX,XX +XXX,XX @@ static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm) t0 = tcg_temp_new_i64(); for (i = 0; i < len_align; i += 8) { - tcg_gen_ld_i64(t0, cpu_env, vofs + i); + tcg_gen_ld_i64(t0, base, vofs + i); tcg_gen_qemu_st_i64(t0, clean_addr, midx, MO_LEUQ); tcg_gen_addi_i64(clean_addr, clean_addr, 8); } @@ -XXX,XX +XXX,XX @@ static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm) clean_addr = new_tmp_a64_local(s); tcg_gen_mov_i64(clean_addr, t0); + if (base != cpu_env) { + TCGv_ptr b = tcg_temp_local_new_ptr(); + tcg_gen_mov_ptr(b, base); + base = b; + } + gen_set_label(loop); t0 = tcg_temp_new_i64(); tp = tcg_temp_new_ptr(); - tcg_gen_add_ptr(tp, cpu_env, i); + tcg_gen_add_ptr(tp, base, i); tcg_gen_ld_i64(t0, tp, vofs); tcg_gen_addi_ptr(i, i, 8); tcg_temp_free_ptr(tp); @@ -XXX,XX +XXX,XX @@ static void do_str(DisasContext *s, uint32_t vofs, int len, int rn, int imm) tcg_gen_brcondi_ptr(TCG_COND_LTU, i, len_align, loop); tcg_temp_free_ptr(i); + + if (base != cpu_env) { + tcg_temp_free_ptr(base); + assert(len_remain == 0); + } } /* Predicate register stores can be any multiple of 2. */ if (len_remain) { t0 = tcg_temp_new_i64(); - tcg_gen_ld_i64(t0, cpu_env, vofs + len_align); + tcg_gen_ld_i64(t0, base, vofs + len_align); switch (len_remain) { case 2: @@ -XXX,XX +XXX,XX @@ static bool trans_LDR_zri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = vec_full_reg_size(s); int off = vec_full_reg_offset(s, a->rd); - do_ldr(s, off, size, a->rn, a->imm * size); + gen_sve_ldr(s, cpu_env, off, size, a->rn, a->imm * size); } return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_LDR_pri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = pred_full_reg_size(s); int off = pred_full_reg_offset(s, a->rd); - do_ldr(s, off, size, a->rn, a->imm * size); + gen_sve_ldr(s, cpu_env, off, size, a->rn, a->imm * size); } return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_STR_zri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = vec_full_reg_size(s); int off = vec_full_reg_offset(s, a->rd); - do_str(s, off, size, a->rn, a->imm * size); + gen_sve_str(s, cpu_env, off, size, a->rn, a->imm * size); } return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_STR_pri(DisasContext *s, arg_rri *a) if (sve_access_check(s)) { int size = pred_full_reg_size(s); int off = pred_full_reg_offset(s, a->rd); - do_str(s, off, size, a->rn, a->imm * size); + gen_sve_str(s, cpu_env, off, size, a->rn, a->imm * size); } return true; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We can reuse the SVE functions for LDR and STR, passing in the base of the ZA vector and a zero offset. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-23-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sme.decode | 7 +++++++ target/arm/translate-sme.c | 24 ++++++++++++++++++++++++ 2 files changed, 31 insertions(+) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ LDST1 1110000 0 esz:2 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ &ldst rs=%mova_rs LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ &ldst esz=4 rs=%mova_rs + +&ldstr rv rn imm +@ldstr ....... ... . ...... .. ... rn:5 . imm:4 \ + &ldstr rv=%mova_rs + +LDR 1110000 100 0 000000 .. 000 ..... 0 .... @ldstr +STR 1110000 100 1 000000 .. 000 ..... 0 .... @ldstr diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ static bool trans_LDST1(DisasContext *s, arg_LDST1 *a) tcg_temp_free_i64(addr); return true; } + +typedef void GenLdStR(DisasContext *, TCGv_ptr, int, int, int, int); + +static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn) +{ + int svl = streaming_vec_reg_size(s); + int imm = a->imm; + TCGv_ptr base; + + if (!sme_za_enabled_check(s)) { + return true; + } + + /* ZA[n] equates to ZA0H.B[n]. */ + base = get_tile_rowcol(s, MO_8, a->rv, imm, false); + + fn(s, base, 0, svl, a->rn, imm * svl); + + tcg_temp_free_ptr(base); + return true; +} + +TRANS_FEAT(LDR, aa64_sme, do_ldst_r, a, gen_sve_ldr) +TRANS_FEAT(STR, aa64_sme, do_ldst_r, a, gen_sve_str) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-24-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 5 +++ target/arm/sme.decode | 11 +++++ target/arm/sme_helper.c | 90 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 31 +++++++++++++ 4 files changed, 137 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme_st1q_be_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i DEF_HELPER_FLAGS_5(sme_st1q_le_h_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_5(sme_st1q_be_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) DEF_HELPER_FLAGS_5(sme_st1q_le_v_mte, TCG_CALL_NO_WG, void, env, ptr, ptr, tl, i32) + +DEF_HELPER_FLAGS_5(sme_addha_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme_addva_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ LDST1 1110000 111 st:1 rm:5 v:1 .. pg:3 rn:5 0 za_imm:4 \ LDR 1110000 100 0 000000 .. 000 ..... 0 .... @ldstr STR 1110000 100 1 000000 .. 000 ..... 0 .... @ldstr + +### SME Add Vector to Array + +&adda zad zn pm pn +@adda_32 ........ .. ..... . pm:3 pn:3 zn:5 ... zad:2 &adda +@adda_64 ........ .. ..... . pm:3 pn:3 zn:5 .. zad:3 &adda + +ADDHA_s 11000000 10 01000 0 ... ... ..... 000 .. @adda_32 +ADDVA_s 11000000 10 01000 1 ... ... ..... 000 .. @adda_32 +ADDHA_d 11000000 11 01000 0 ... ... ..... 00 ... @adda_64 +ADDVA_d 11000000 11 01000 1 ... ... ..... 00 ... @adda_64 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ DO_ST(q, _be, MO_128) DO_ST(q, _le, MO_128) #undef DO_ST + +void HELPER(sme_addha_s)(void *vzda, void *vzn, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 4; + uint64_t *pn = vpn, *pm = vpm; + uint32_t *zda = vzda, *zn = vzn; + + for (row = 0; row < oprsz; ) { + uint64_t pa = pn[row >> 4]; + do { + if (pa & 1) { + for (col = 0; col < oprsz; ) { + uint64_t pb = pm[col >> 4]; + do { + if (pb & 1) { + zda[tile_vslice_index(row) + H4(col)] += zn[H4(col)]; + } + pb >>= 4; + } while (++col & 15); + } + } + pa >>= 4; + } while (++row & 15); + } +} + +void HELPER(sme_addha_d)(void *vzda, void *vzn, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 8; + uint8_t *pn = vpn, *pm = vpm; + uint64_t *zda = vzda, *zn = vzn; + + for (row = 0; row < oprsz; ++row) { + if (pn[H1(row)] & 1) { + for (col = 0; col < oprsz; ++col) { + if (pm[H1(col)] & 1) { + zda[tile_vslice_index(row) + col] += zn[col]; + } + } + } + } +} + +void HELPER(sme_addva_s)(void *vzda, void *vzn, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 4; + uint64_t *pn = vpn, *pm = vpm; + uint32_t *zda = vzda, *zn = vzn; + + for (row = 0; row < oprsz; ) { + uint64_t pa = pn[row >> 4]; + do { + if (pa & 1) { + uint32_t zn_row = zn[H4(row)]; + for (col = 0; col < oprsz; ) { + uint64_t pb = pm[col >> 4]; + do { + if (pb & 1) { + zda[tile_vslice_index(row) + H4(col)] += zn_row; + } + pb >>= 4; + } while (++col & 15); + } + } + pa >>= 4; + } while (++row & 15); + } +} + +void HELPER(sme_addva_d)(void *vzda, void *vzn, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 8; + uint8_t *pn = vpn, *pm = vpm; + uint64_t *zda = vzda, *zn = vzn; + + for (row = 0; row < oprsz; ++row) { + if (pn[H1(row)] & 1) { + uint64_t zn_row = zn[row]; + for (col = 0; col < oprsz; ++col) { + if (pm[H1(col)] & 1) { + zda[tile_vslice_index(row) + col] += zn_row; + } + } + } + } +} diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ static bool do_ldst_r(DisasContext *s, arg_ldstr *a, GenLdStR *fn) TRANS_FEAT(LDR, aa64_sme, do_ldst_r, a, gen_sve_ldr) TRANS_FEAT(STR, aa64_sme, do_ldst_r, a, gen_sve_str) + +static bool do_adda(DisasContext *s, arg_adda *a, MemOp esz, + gen_helper_gvec_4 *fn) +{ + int svl = streaming_vec_reg_size(s); + uint32_t desc = simd_desc(svl, svl, 0); + TCGv_ptr za, zn, pn, pm; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + /* Sum XZR+zad to find ZAd. */ + za = get_tile_rowcol(s, esz, 31, a->zad, false); + zn = vec_full_reg_ptr(s, a->zn); + pn = pred_full_reg_ptr(s, a->pn); + pm = pred_full_reg_ptr(s, a->pm); + + fn(za, zn, pn, pm, tcg_constant_i32(desc)); + + tcg_temp_free_ptr(za); + tcg_temp_free_ptr(zn); + tcg_temp_free_ptr(pn); + tcg_temp_free_ptr(pm); + return true; +} + +TRANS_FEAT(ADDHA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addha_s) +TRANS_FEAT(ADDVA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addva_s) +TRANS_FEAT(ADDHA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addha_d) +TRANS_FEAT(ADDVA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addva_d) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-25-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 5 +++ target/arm/sme.decode | 9 +++++ target/arm/sme_helper.c | 69 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 32 ++++++++++++++++++ 4 files changed, 115 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme_addha_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addva_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ ADDHA_s 11000000 10 01000 0 ... ... ..... 000 .. @adda_32 ADDVA_s 11000000 10 01000 1 ... ... ..... 000 .. @adda_32 ADDHA_d 11000000 11 01000 0 ... ... ..... 00 ... @adda_64 ADDVA_d 11000000 11 01000 1 ... ... ..... 00 ... @adda_64 + +### SME Outer Product + +&op zad zn zm pm pn sub:bool +@op_32 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 .. zad:2 &op +@op_64 ........ ... zm:5 pm:3 pn:3 zn:5 sub:1 . zad:3 &op + +FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32 +FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ #include "exec/cpu_ldst.h" #include "exec/exec-all.h" #include "qemu/int128.h" +#include "fpu/softfloat.h" #include "vec_internal.h" #include "sve_ldst_internal.h" @@ -XXX,XX +XXX,XX @@ void HELPER(sme_addva_d)(void *vzda, void *vzn, void *vpn, } } } + +void HELPER(sme_fmopa_s)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, void *vst, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_maxsz(desc); + uint32_t neg = simd_data(desc) << 31; + uint16_t *pn = vpn, *pm = vpm; + float_status fpst; + + /* + * Make a copy of float_status because this operation does not + * update the cumulative fp exception status. It also produces + * default nans. + */ + fpst = *(float_status *)vst; + set_default_nan_mode(true, &fpst); + + for (row = 0; row < oprsz; ) { + uint16_t pa = pn[H2(row >> 4)]; + do { + if (pa & 1) { + void *vza_row = vza + tile_vslice_offset(row); + uint32_t n = *(uint32_t *)(vzn + H1_4(row)) ^ neg; + + for (col = 0; col < oprsz; ) { + uint16_t pb = pm[H2(col >> 4)]; + do { + if (pb & 1) { + uint32_t *a = vza_row + H1_4(col); + uint32_t *m = vzm + H1_4(col); + *a = float32_muladd(n, *m, *a, 0, vst); + } + col += 4; + pb >>= 4; + } while (col & 15); + } + } + row += 4; + pa >>= 4; + } while (row & 15); + } +} + +void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, void *vst, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 8; + uint64_t neg = (uint64_t)simd_data(desc) << 63; + uint64_t *za = vza, *zn = vzn, *zm = vzm; + uint8_t *pn = vpn, *pm = vpm; + float_status fpst = *(float_status *)vst; + + set_default_nan_mode(true, &fpst); + + for (row = 0; row < oprsz; ++row) { + if (pn[H1(row)] & 1) { + uint64_t *za_row = &za[tile_vslice_index(row)]; + uint64_t n = zn[row] ^ neg; + + for (col = 0; col < oprsz; ++col) { + if (pm[H1(col)] & 1) { + uint64_t *a = &za_row[col]; + *a = float64_muladd(n, zm[col], *a, 0, &fpst); + } + } + } + } +} diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(ADDHA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addha_s) TRANS_FEAT(ADDVA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addva_s) TRANS_FEAT(ADDHA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addha_d) TRANS_FEAT(ADDVA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addva_d) + +static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz, + gen_helper_gvec_5_ptr *fn) +{ + int svl = streaming_vec_reg_size(s); + uint32_t desc = simd_desc(svl, svl, a->sub); + TCGv_ptr za, zn, zm, pn, pm, fpst; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + /* Sum XZR+zad to find ZAd. */ + za = get_tile_rowcol(s, esz, 31, a->zad, false); + zn = vec_full_reg_ptr(s, a->zn); + zm = vec_full_reg_ptr(s, a->zm); + pn = pred_full_reg_ptr(s, a->pn); + pm = pred_full_reg_ptr(s, a->pm); + fpst = fpstatus_ptr(FPST_FPCR); + + fn(za, zn, zm, pn, pm, fpst, tcg_constant_i32(desc)); + + tcg_temp_free_ptr(za); + tcg_temp_free_ptr(zn); + tcg_temp_free_ptr(pn); + tcg_temp_free_ptr(pm); + tcg_temp_free_ptr(fpst); + return true; +} + +TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, gen_helper_sme_fmopa_s) +TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, gen_helper_sme_fmopa_d) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-26-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 2 ++ target/arm/sme.decode | 2 ++ target/arm/sme_helper.c | 56 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 30 ++++++++++++++++++++ 4 files changed, 90 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_bfmopa, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ ADDVA_d 11000000 11 01000 1 ... ... ..... 00 ... @adda_64 FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 + +BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_d)(void *vza, void *vzn, void *vzm, void *vpn, } } } + +/* + * Alter PAIR as needed for controlling predicates being false, + * and for NEG on an enabled row element. + */ +static inline uint32_t f16mop_adj_pair(uint32_t pair, uint32_t pg, uint32_t neg) +{ + /* + * The pseudocode uses a conditional negate after the conditional zero. + * It is simpler here to unconditionally negate before conditional zero. + */ + pair ^= neg; + if (!(pg & 1)) { + pair &= 0xffff0000u; + } + if (!(pg & 4)) { + pair &= 0x0000ffffu; + } + return pair; +} + +void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_maxsz(desc); + uint32_t neg = simd_data(desc) * 0x80008000u; + uint16_t *pn = vpn, *pm = vpm; + + for (row = 0; row < oprsz; ) { + uint16_t prow = pn[H2(row >> 4)]; + do { + void *vza_row = vza + tile_vslice_offset(row); + uint32_t n = *(uint32_t *)(vzn + H1_4(row)); + + n = f16mop_adj_pair(n, prow, neg); + + for (col = 0; col < oprsz; ) { + uint16_t pcol = pm[H2(col >> 4)]; + do { + if (prow & pcol & 0b0101) { + uint32_t *a = vza_row + H1_4(col); + uint32_t m = *(uint32_t *)(vzm + H1_4(col)); + + m = f16mop_adj_pair(m, pcol, 0); + *a = bfdotadd(*a, n, m); + + col += 4; + pcol >>= 4; + } + } while (col & 15); + } + row += 4; + prow >>= 4; + } while (row & 15); + } +} diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(ADDVA_s, aa64_sme, do_adda, a, MO_32, gen_helper_sme_addva_s) TRANS_FEAT(ADDHA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addha_d) TRANS_FEAT(ADDVA_d, aa64_sme_i16i64, do_adda, a, MO_64, gen_helper_sme_addva_d) +static bool do_outprod(DisasContext *s, arg_op *a, MemOp esz, + gen_helper_gvec_5 *fn) +{ + int svl = streaming_vec_reg_size(s); + uint32_t desc = simd_desc(svl, svl, a->sub); + TCGv_ptr za, zn, zm, pn, pm; + + if (!sme_smza_enabled_check(s)) { + return true; + } + + /* Sum XZR+zad to find ZAd. */ + za = get_tile_rowcol(s, esz, 31, a->zad, false); + zn = vec_full_reg_ptr(s, a->zn); + zm = vec_full_reg_ptr(s, a->zm); + pn = pred_full_reg_ptr(s, a->pn); + pm = pred_full_reg_ptr(s, a->pm); + + fn(za, zn, zm, pn, pm, tcg_constant_i32(desc)); + + tcg_temp_free_ptr(za); + tcg_temp_free_ptr(zn); + tcg_temp_free_ptr(pn); + tcg_temp_free_ptr(pm); + return true; +} + static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz, gen_helper_gvec_5_ptr *fn) { @@ -XXX,XX +XXX,XX @@ static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz, TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, gen_helper_sme_fmopa_s) TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, gen_helper_sme_fmopa_d) + +/* TODO: FEAT_EBF16 */ +TRANS_FEAT(BFMOPA, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_bfmopa) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-27-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 2 ++ target/arm/sme.decode | 1 + target/arm/sme_helper.c | 74 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 1 + 4 files changed, 78 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_5(sme_addva_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addha_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_5(sme_addva_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_7(sme_fmopa_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_7(sme_fmopa_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ FMOPA_s 10000000 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32 +FMOPA_h 10000001 101 ..... ... ... ..... . 00 .. @op_32 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t f16mop_adj_pair(uint32_t pair, uint32_t pg, uint32_t neg) return pair; } +static float32 f16_dotadd(float32 sum, uint32_t e1, uint32_t e2, + float_status *s_std, float_status *s_odd) +{ + float64 e1r = float16_to_float64(e1 & 0xffff, true, s_std); + float64 e1c = float16_to_float64(e1 >> 16, true, s_std); + float64 e2r = float16_to_float64(e2 & 0xffff, true, s_std); + float64 e2c = float16_to_float64(e2 >> 16, true, s_std); + float64 t64; + float32 t32; + + /* + * The ARM pseudocode function FPDot performs both multiplies + * and the add with a single rounding operation. Emulate this + * by performing the first multiply in round-to-odd, then doing + * the second multiply as fused multiply-add, and rounding to + * float32 all in one step. + */ + t64 = float64_mul(e1r, e2r, s_odd); + t64 = float64r32_muladd(e1c, e2c, t64, 0, s_std); + + /* This conversion is exact, because we've already rounded. */ + t32 = float64_to_float32(t64, s_std); + + /* The final accumulation step is not fused. */ + return float32_add(sum, t32, s_std); +} + +void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, + void *vpm, void *vst, uint32_t desc) +{ + intptr_t row, col, oprsz = simd_maxsz(desc); + uint32_t neg = simd_data(desc) * 0x80008000u; + uint16_t *pn = vpn, *pm = vpm; + float_status fpst_odd, fpst_std; + + /* + * Make a copy of float_status because this operation does not + * update the cumulative fp exception status. It also produces + * default nans. Make a second copy with round-to-odd -- see above. + */ + fpst_std = *(float_status *)vst; + set_default_nan_mode(true, &fpst_std); + fpst_odd = fpst_std; + set_float_rounding_mode(float_round_to_odd, &fpst_odd); + + for (row = 0; row < oprsz; ) { + uint16_t prow = pn[H2(row >> 4)]; + do { + void *vza_row = vza + tile_vslice_offset(row); + uint32_t n = *(uint32_t *)(vzn + H1_4(row)); + + n = f16mop_adj_pair(n, prow, neg); + + for (col = 0; col < oprsz; ) { + uint16_t pcol = pm[H2(col >> 4)]; + do { + if (prow & pcol & 0b0101) { + uint32_t *a = vza_row + H1_4(col); + uint32_t m = *(uint32_t *)(vzm + H1_4(col)); + + m = f16mop_adj_pair(m, pcol, 0); + *a = f16_dotadd(*a, n, m, &fpst_std, &fpst_odd); + + col += 4; + pcol >>= 4; + } + } while (col & 15); + } + row += 4; + prow >>= 4; + } while (row & 15); + } +} + void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn, void *vpm, uint32_t desc) { diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ static bool do_outprod_fpst(DisasContext *s, arg_op *a, MemOp esz, return true; } +TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_fpst, a, MO_32, gen_helper_sme_fmopa_h) TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, MO_32, gen_helper_sme_fmopa_s) TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, gen_helper_sme_fmopa_d) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This is SMOPA, SUMOPA, USMOPA_s, UMOPA, for both Int8 and Int16. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-28-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sme.h | 16 ++++++++ target/arm/sme.decode | 10 +++++ target/arm/sme_helper.c | 82 ++++++++++++++++++++++++++++++++++++++ target/arm/translate-sme.c | 10 +++++ 4 files changed, 118 insertions(+) diff --git a/target/arm/helper-sme.h b/target/arm/helper-sme.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sme.h +++ b/target/arm/helper-sme.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_7(sme_fmopa_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_6(sme_bfmopa, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_smopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_umopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_sumopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_usmopa_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_smopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_umopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_sumopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_6(sme_usmopa_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, ptr, i32) diff --git a/target/arm/sme.decode b/target/arm/sme.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme.decode +++ b/target/arm/sme.decode @@ -XXX,XX +XXX,XX @@ FMOPA_d 10000000 110 ..... ... ... ..... . 0 ... @op_64 BFMOPA 10000001 100 ..... ... ... ..... . 00 .. @op_32 FMOPA_h 10000001 101 ..... ... ... ..... . 00 .. @op_32 + +SMOPA_s 1010000 0 10 0 ..... ... ... ..... . 00 .. @op_32 +SUMOPA_s 1010000 0 10 1 ..... ... ... ..... . 00 .. @op_32 +USMOPA_s 1010000 1 10 0 ..... ... ... ..... . 00 .. @op_32 +UMOPA_s 1010000 1 10 1 ..... ... ... ..... . 00 .. @op_32 + +SMOPA_d 1010000 0 11 0 ..... ... ... ..... . 0 ... @op_64 +SUMOPA_d 1010000 0 11 1 ..... ... ... ..... . 0 ... @op_64 +USMOPA_d 1010000 1 11 0 ..... ... ... ..... . 0 ... @op_64 +UMOPA_d 1010000 1 11 1 ..... ... ... ..... . 0 ... @op_64 diff --git a/target/arm/sme_helper.c b/target/arm/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sme_helper.c +++ b/target/arm/sme_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sme_bfmopa)(void *vza, void *vzn, void *vzm, void *vpn, } while (row & 15); } } + +typedef uint64_t IMOPFn(uint64_t, uint64_t, uint64_t, uint8_t, bool); + +static inline void do_imopa(uint64_t *za, uint64_t *zn, uint64_t *zm, + uint8_t *pn, uint8_t *pm, + uint32_t desc, IMOPFn *fn) +{ + intptr_t row, col, oprsz = simd_oprsz(desc) / 8; + bool neg = simd_data(desc); + + for (row = 0; row < oprsz; ++row) { + uint8_t pa = pn[H1(row)]; + uint64_t *za_row = &za[tile_vslice_index(row)]; + uint64_t n = zn[row]; + + for (col = 0; col < oprsz; ++col) { + uint8_t pb = pm[H1(col)]; + uint64_t *a = &za_row[col]; + + *a = fn(n, zm[col], *a, pa & pb, neg); + } + } +} + +#define DEF_IMOP_32(NAME, NTYPE, MTYPE) \ +static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \ +{ \ + uint32_t sum0 = 0, sum1 = 0; \ + /* Apply P to N as a mask, making the inactive elements 0. */ \ + n &= expand_pred_b(p); \ + sum0 += (NTYPE)(n >> 0) * (MTYPE)(m >> 0); \ + sum0 += (NTYPE)(n >> 8) * (MTYPE)(m >> 8); \ + sum0 += (NTYPE)(n >> 16) * (MTYPE)(m >> 16); \ + sum0 += (NTYPE)(n >> 24) * (MTYPE)(m >> 24); \ + sum1 += (NTYPE)(n >> 32) * (MTYPE)(m >> 32); \ + sum1 += (NTYPE)(n >> 40) * (MTYPE)(m >> 40); \ + sum1 += (NTYPE)(n >> 48) * (MTYPE)(m >> 48); \ + sum1 += (NTYPE)(n >> 56) * (MTYPE)(m >> 56); \ + if (neg) { \ + sum0 = (uint32_t)a - sum0, sum1 = (uint32_t)(a >> 32) - sum1; \ + } else { \ + sum0 = (uint32_t)a + sum0, sum1 = (uint32_t)(a >> 32) + sum1; \ + } \ + return ((uint64_t)sum1 << 32) | sum0; \ +} + +#define DEF_IMOP_64(NAME, NTYPE, MTYPE) \ +static uint64_t NAME(uint64_t n, uint64_t m, uint64_t a, uint8_t p, bool neg) \ +{ \ + uint64_t sum = 0; \ + /* Apply P to N as a mask, making the inactive elements 0. */ \ + n &= expand_pred_h(p); \ + sum += (NTYPE)(n >> 0) * (MTYPE)(m >> 0); \ + sum += (NTYPE)(n >> 16) * (MTYPE)(m >> 16); \ + sum += (NTYPE)(n >> 32) * (MTYPE)(m >> 32); \ + sum += (NTYPE)(n >> 48) * (MTYPE)(m >> 48); \ + return neg ? a - sum : a + sum; \ +} + +DEF_IMOP_32(smopa_s, int8_t, int8_t) +DEF_IMOP_32(umopa_s, uint8_t, uint8_t) +DEF_IMOP_32(sumopa_s, int8_t, uint8_t) +DEF_IMOP_32(usmopa_s, uint8_t, int8_t) + +DEF_IMOP_64(smopa_d, int16_t, int16_t) +DEF_IMOP_64(umopa_d, uint16_t, uint16_t) +DEF_IMOP_64(sumopa_d, int16_t, uint16_t) +DEF_IMOP_64(usmopa_d, uint16_t, int16_t) + +#define DEF_IMOPH(NAME) \ + void HELPER(sme_##NAME)(void *vza, void *vzn, void *vzm, void *vpn, \ + void *vpm, uint32_t desc) \ + { do_imopa(vza, vzn, vzm, vpn, vpm, desc, NAME); } + +DEF_IMOPH(smopa_s) +DEF_IMOPH(umopa_s) +DEF_IMOPH(sumopa_s) +DEF_IMOPH(usmopa_s) +DEF_IMOPH(smopa_d) +DEF_IMOPH(umopa_d) +DEF_IMOPH(sumopa_d) +DEF_IMOPH(usmopa_d) diff --git a/target/arm/translate-sme.c b/target/arm/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sme.c +++ b/target/arm/translate-sme.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, MO_64, gen_helper_sme_f /* TODO: FEAT_EBF16 */ TRANS_FEAT(BFMOPA, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_bfmopa) + +TRANS_FEAT(SMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_smopa_s) +TRANS_FEAT(UMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_umopa_s) +TRANS_FEAT(SUMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_sumopa_s) +TRANS_FEAT(USMOPA_s, aa64_sme, do_outprod, a, MO_32, gen_helper_sme_usmopa_s) + +TRANS_FEAT(SMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_smopa_d) +TRANS_FEAT(UMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_umopa_d) +TRANS_FEAT(SUMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_sumopa_d) +TRANS_FEAT(USMOPA_d, aa64_sme_i16i64, do_outprod, a, MO_64, gen_helper_sme_usmopa_d) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This is an SVE instruction that operates using the SVE vector length but that it is present only if SME is implemented. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-29-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/sve.decode | 20 +++++++++++++ target/arm/translate-sve.c | 57 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 77 insertions(+) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ BFMLALT_zzxw 01100100 11 1 ..... 0100.1 ..... ..... @rrxr_3a esz=2 ### SVE2 floating-point bfloat16 dot-product (indexed) BFDOT_zzxz 01100100 01 1 ..... 010000 ..... ..... @rrxr_2 esz=2 + +### SVE broadcast predicate element + +&psel esz pd pn pm rv imm +%psel_rv 16:2 !function=plus_12 +%psel_imm_b 22:2 19:2 +%psel_imm_h 22:2 20:1 +%psel_imm_s 22:2 +%psel_imm_d 23:1 +@psel ........ .. . ... .. .. pn:4 . pm:4 . pd:4 \ + &psel rv=%psel_rv + +PSEL 00100101 .. 1 ..1 .. 01 .... 0 .... 0 .... \ + @psel esz=0 imm=%psel_imm_b +PSEL 00100101 .. 1 .10 .. 01 .... 0 .... 0 .... \ + @psel esz=1 imm=%psel_imm_h +PSEL 00100101 .. 1 100 .. 01 .... 0 .... 0 .... \ + @psel esz=2 imm=%psel_imm_s +PSEL 00100101 .1 1 000 .. 01 .... 0 .... 0 .... \ + @psel esz=3 imm=%psel_imm_d diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool do_BFMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel) TRANS_FEAT(BFMLALB_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, false) TRANS_FEAT(BFMLALT_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, true) + +static bool trans_PSEL(DisasContext *s, arg_psel *a) +{ + int vl = vec_full_reg_size(s); + int pl = pred_gvec_reg_size(s); + int elements = vl >> a->esz; + TCGv_i64 tmp, didx, dbit; + TCGv_ptr ptr; + + if (!dc_isar_feature(aa64_sme, s)) { + return false; + } + if (!sve_access_check(s)) { + return true; + } + + tmp = tcg_temp_new_i64(); + dbit = tcg_temp_new_i64(); + didx = tcg_temp_new_i64(); + ptr = tcg_temp_new_ptr(); + + /* Compute the predicate element. */ + tcg_gen_addi_i64(tmp, cpu_reg(s, a->rv), a->imm); + if (is_power_of_2(elements)) { + tcg_gen_andi_i64(tmp, tmp, elements - 1); + } else { + tcg_gen_remu_i64(tmp, tmp, tcg_constant_i64(elements)); + } + + /* Extract the predicate byte and bit indices. */ + tcg_gen_shli_i64(tmp, tmp, a->esz); + tcg_gen_andi_i64(dbit, tmp, 7); + tcg_gen_shri_i64(didx, tmp, 3); + if (HOST_BIG_ENDIAN) { + tcg_gen_xori_i64(didx, didx, 7); + } + + /* Load the predicate word. */ + tcg_gen_trunc_i64_ptr(ptr, didx); + tcg_gen_add_ptr(ptr, ptr, cpu_env); + tcg_gen_ld8u_i64(tmp, ptr, pred_full_reg_offset(s, a->pm)); + + /* Extract the predicate bit and replicate to MO_64. */ + tcg_gen_shr_i64(tmp, tmp, dbit); + tcg_gen_andi_i64(tmp, tmp, 1); + tcg_gen_neg_i64(tmp, tmp); + + /* Apply to either copy the source, or write zeros. */ + tcg_gen_gvec_ands(MO_64, pred_full_reg_offset(s, a->pd), + pred_full_reg_offset(s, a->pn), tmp, pl, pl); + + tcg_temp_free_i64(tmp); + tcg_temp_free_i64(dbit); + tcg_temp_free_i64(didx); + tcg_temp_free_ptr(ptr); + return true; +} -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This is an SVE instruction that operates using the SVE vector length but that it is present only if SME is implemented. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-30-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper-sve.h | 2 ++ target/arm/sve.decode | 1 + target/arm/sve_helper.c | 16 ++++++++++++++++ target/arm/translate-sve.c | 2 ++ 4 files changed, 21 insertions(+) diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper-sve.h +++ b/target/arm/helper-sve.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_4(sve_revh_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_revw_d, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_4(sme_revd_q, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve_rbit_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_rbit_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve_rbit_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ REVB 00000101 .. 1001 00 100 ... ..... ..... @rd_pg_rn REVH 00000101 .. 1001 01 100 ... ..... ..... @rd_pg_rn REVW 00000101 .. 1001 10 100 ... ..... ..... @rd_pg_rn RBIT 00000101 .. 1001 11 100 ... ..... ..... @rd_pg_rn +REVD 00000101 00 1011 10 100 ... ..... ..... @rd_pg_rn_e0 # SVE vector splice (predicated, destructive) SPLICE 00000101 .. 101 100 100 ... ..... ..... @rdn_pg_rm diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve_helper.c +++ b/target/arm/sve_helper.c @@ -XXX,XX +XXX,XX @@ DO_ZPZ_D(sve_revh_d, uint64_t, hswap64) DO_ZPZ_D(sve_revw_d, uint64_t, wswap64) +void HELPER(sme_revd_q)(void *vd, void *vn, void *vg, uint32_t desc) +{ + intptr_t i, opr_sz = simd_oprsz(desc) / 8; + uint64_t *d = vd, *n = vn; + uint8_t *pg = vg; + + for (i = 0; i < opr_sz; i += 2) { + if (pg[H1(i)] & 1) { + uint64_t n0 = n[i + 0]; + uint64_t n1 = n[i + 1]; + d[i + 0] = n1; + d[i + 1] = n0; + } + } +} + DO_ZPZ(sve_rbit_b, uint8_t, H1, revbit8) DO_ZPZ(sve_rbit_h, uint16_t, H1_2, revbit16) DO_ZPZ(sve_rbit_s, uint32_t, H1_4, revbit32) diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(REVH, aa64_sve, gen_gvec_ool_arg_zpz, revh_fns[a->esz], a, 0) TRANS_FEAT(REVW, aa64_sve, gen_gvec_ool_arg_zpz, a->esz == 3 ? gen_helper_sve_revw_d : NULL, a, 0) +TRANS_FEAT(REVD, aa64_sme, gen_gvec_ool_arg_zpz, gen_helper_sme_revd_q, a, 0) + TRANS_FEAT(SPLICE, aa64_sve, gen_gvec_ool_arg_zpzz, gen_helper_sve_splice, a, a->esz) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> This is an SVE instruction that operates using the SVE vector length but that it is present only if SME is implemented. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-31-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 18 +++++++ target/arm/sve.decode | 5 ++ target/arm/translate-sve.c | 102 +++++++++++++++++++++++++++++++++++++ target/arm/vec_helper.c | 24 +++++++++ 4 files changed, 149 insertions(+) diff --git a/target/arm/helper.h b/target/arm/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_6(gvec_bfmlal, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_6(gvec_bfmlal_idx, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sclamp_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sclamp_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sclamp_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_sclamp_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(gvec_uclamp_b, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uclamp_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uclamp_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(gvec_uclamp_d, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + #ifdef TARGET_AARCH64 #include "helper-a64.h" #include "helper-sve.h" diff --git a/target/arm/sve.decode b/target/arm/sve.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/sve.decode +++ b/target/arm/sve.decode @@ -XXX,XX +XXX,XX @@ PSEL 00100101 .. 1 100 .. 01 .... 0 .... 0 .... \ @psel esz=2 imm=%psel_imm_s PSEL 00100101 .1 1 000 .. 01 .... 0 .... 0 .... \ @psel esz=3 imm=%psel_imm_d + +### SVE clamp + +SCLAMP 01000100 .. 0 ..... 110000 ..... ..... @rda_rn_rm +UCLAMP 01000100 .. 0 ..... 110001 ..... ..... @rda_rn_rm diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-sve.c +++ b/target/arm/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool trans_PSEL(DisasContext *s, arg_psel *a) tcg_temp_free_ptr(ptr); return true; } + +static void gen_sclamp_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_i32 a) +{ + tcg_gen_smax_i32(d, a, n); + tcg_gen_smin_i32(d, d, m); +} + +static void gen_sclamp_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 a) +{ + tcg_gen_smax_i64(d, a, n); + tcg_gen_smin_i64(d, d, m); +} + +static void gen_sclamp_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec a) +{ + tcg_gen_smax_vec(vece, d, a, n); + tcg_gen_smin_vec(vece, d, d, m); +} + +static void gen_sclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const TCGOpcode vecop[] = { + INDEX_op_smin_vec, INDEX_op_smax_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_sclamp_vec, + .fno = gen_helper_gvec_sclamp_b, + .opt_opc = vecop, + .vece = MO_8 }, + { .fniv = gen_sclamp_vec, + .fno = gen_helper_gvec_sclamp_h, + .opt_opc = vecop, + .vece = MO_16 }, + { .fni4 = gen_sclamp_i32, + .fniv = gen_sclamp_vec, + .fno = gen_helper_gvec_sclamp_s, + .opt_opc = vecop, + .vece = MO_32 }, + { .fni8 = gen_sclamp_i64, + .fniv = gen_sclamp_vec, + .fno = gen_helper_gvec_sclamp_d, + .opt_opc = vecop, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64 } + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]); +} + +TRANS_FEAT(SCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_sclamp, a) + +static void gen_uclamp_i32(TCGv_i32 d, TCGv_i32 n, TCGv_i32 m, TCGv_i32 a) +{ + tcg_gen_umax_i32(d, a, n); + tcg_gen_umin_i32(d, d, m); +} + +static void gen_uclamp_i64(TCGv_i64 d, TCGv_i64 n, TCGv_i64 m, TCGv_i64 a) +{ + tcg_gen_umax_i64(d, a, n); + tcg_gen_umin_i64(d, d, m); +} + +static void gen_uclamp_vec(unsigned vece, TCGv_vec d, TCGv_vec n, + TCGv_vec m, TCGv_vec a) +{ + tcg_gen_umax_vec(vece, d, a, n); + tcg_gen_umin_vec(vece, d, d, m); +} + +static void gen_uclamp(unsigned vece, uint32_t d, uint32_t n, uint32_t m, + uint32_t a, uint32_t oprsz, uint32_t maxsz) +{ + static const TCGOpcode vecop[] = { + INDEX_op_umin_vec, INDEX_op_umax_vec, 0 + }; + static const GVecGen4 ops[4] = { + { .fniv = gen_uclamp_vec, + .fno = gen_helper_gvec_uclamp_b, + .opt_opc = vecop, + .vece = MO_8 }, + { .fniv = gen_uclamp_vec, + .fno = gen_helper_gvec_uclamp_h, + .opt_opc = vecop, + .vece = MO_16 }, + { .fni4 = gen_uclamp_i32, + .fniv = gen_uclamp_vec, + .fno = gen_helper_gvec_uclamp_s, + .opt_opc = vecop, + .vece = MO_32 }, + { .fni8 = gen_uclamp_i64, + .fniv = gen_uclamp_vec, + .fno = gen_helper_gvec_uclamp_d, + .opt_opc = vecop, + .vece = MO_64, + .prefer_i64 = TCG_TARGET_REG_BITS == 64 } + }; + tcg_gen_gvec_4(d, n, m, a, oprsz, maxsz, &ops[vece]); +} + +TRANS_FEAT(UCLAMP, aa64_sme, gen_gvec_fn_arg_zzzz, gen_uclamp, a) diff --git a/target/arm/vec_helper.c b/target/arm/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vec_helper.c +++ b/target/arm/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_bfmlal_idx)(void *vd, void *vn, void *vm, } clear_tail(d, opr_sz, simd_maxsz(desc)); } + +#define DO_CLAMP(NAME, TYPE) \ +void HELPER(NAME)(void *d, void *n, void *m, void *a, uint32_t desc) \ +{ \ + intptr_t i, opr_sz = simd_oprsz(desc); \ + for (i = 0; i < opr_sz; i += sizeof(TYPE)) { \ + TYPE aa = *(TYPE *)(a + i); \ + TYPE nn = *(TYPE *)(n + i); \ + TYPE mm = *(TYPE *)(m + i); \ + TYPE dd = MIN(MAX(aa, nn), mm); \ + *(TYPE *)(d + i) = dd; \ + } \ + clear_tail(d, opr_sz, simd_maxsz(desc)); \ +} + +DO_CLAMP(gvec_sclamp_b, int8_t) +DO_CLAMP(gvec_sclamp_h, int16_t) +DO_CLAMP(gvec_sclamp_s, int32_t) +DO_CLAMP(gvec_sclamp_d, int64_t) + +DO_CLAMP(gvec_uclamp_b, uint8_t) +DO_CLAMP(gvec_uclamp_h, uint16_t) +DO_CLAMP(gvec_uclamp_s, uint32_t) +DO_CLAMP(gvec_uclamp_d, uint64_t) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> We can handle both exception entry and exception return by hooking into aarch64_sve_change_el. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-32-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ void aarch64_sve_change_el(CPUARMState *env, int old_el, return; } + old_a64 = old_el ? arm_el_is_aa64(env, old_el) : el0_a64; + new_a64 = new_el ? arm_el_is_aa64(env, new_el) : el0_a64; + + /* + * Both AArch64.TakeException and AArch64.ExceptionReturn + * invoke ResetSVEState when taking an exception from, or + * returning to, AArch32 state when PSTATE.SM is enabled. + */ + if (old_a64 != new_a64 && FIELD_EX64(env->svcr, SVCR, SM)) { + arm_reset_sve_state(env); + return; + } + /* * DDI0584A.d sec 3.2: "If SVE instructions are disabled or trapped * at ELx, or not available because the EL is in AArch32 state, then @@ -XXX,XX +XXX,XX @@ void aarch64_sve_change_el(CPUARMState *env, int old_el, * we already have the correct register contents when encountering the * vq0->vq0 transition between EL0->EL1. */ - old_a64 = old_el ? arm_el_is_aa64(env, old_el) : el0_a64; old_len = (old_a64 && !sve_exception_el(env, old_el) ? sve_vqm1_for_el(env, old_el) : 0); - new_a64 = new_el ? arm_el_is_aa64(env, new_el) : el0_a64; new_len = (new_a64 && !sve_exception_el(env, new_el) ? sve_vqm1_for_el(env, new_el) : 0); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Note that SME remains effectively disabled for user-only, because we do not yet set CPACR_EL1.SMEN. This needs to wait until the kernel ABI is implemented. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-33-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 4 ++++ target/arm/cpu64.c | 11 +++++++++++ 2 files changed, 15 insertions(+) diff --git a/docs/system/arm/emulation.rst b/docs/system/arm/emulation.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -XXX,XX +XXX,XX @@ the following architecture extensions: - FEAT_SHA512 (Advanced SIMD SHA512 instructions) - FEAT_SM3 (Advanced SIMD SM3 instructions) - FEAT_SM4 (Advanced SIMD SM4 instructions) +- FEAT_SME (Scalable Matrix Extension) +- FEAT_SME_FA64 (Full A64 instruction set in Streaming SVE mode) +- FEAT_SME_F64F64 (Double-precision floating-point outer product instructions) +- FEAT_SME_I16I64 (16-bit to 64-bit integer widening outer product instructions) - FEAT_SPECRES (Speculation restriction instructions) - FEAT_SSBS (Speculative Store Bypass Safe) - FEAT_TLBIOS (TLB invalidate instructions in Outer Shareable domain) diff --git a/target/arm/cpu64.c b/target/arm/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu64.c +++ b/target/arm/cpu64.c @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) */ t = FIELD_DP64(t, ID_AA64PFR1, MTE, 3); /* FEAT_MTE3 */ t = FIELD_DP64(t, ID_AA64PFR1, RAS_FRAC, 0); /* FEAT_RASv1p1 + FEAT_DoubleFault */ + t = FIELD_DP64(t, ID_AA64PFR1, SME, 1); /* FEAT_SME */ t = FIELD_DP64(t, ID_AA64PFR1, CSV2_FRAC, 0); /* FEAT_CSV2_2 */ cpu->isar.id_aa64pfr1 = t; @@ -XXX,XX +XXX,XX @@ static void aarch64_max_initfn(Object *obj) t = FIELD_DP64(t, ID_AA64DFR0, PMUVER, 5); /* FEAT_PMUv3p4 */ cpu->isar.id_aa64dfr0 = t; + t = cpu->isar.id_aa64smfr0; + t = FIELD_DP64(t, ID_AA64SMFR0, F32F32, 1); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, B16F32, 1); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, F16F32, 1); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, I8I32, 0xf); /* FEAT_SME */ + t = FIELD_DP64(t, ID_AA64SMFR0, F64F64, 1); /* FEAT_SME_F64F64 */ + t = FIELD_DP64(t, ID_AA64SMFR0, I16I64, 0xf); /* FEAT_SME_I16I64 */ + t = FIELD_DP64(t, ID_AA64SMFR0, FA64, 1); /* FEAT_SME_FA64 */ + cpu->isar.id_aa64smfr0 = t; + /* Replicate the same data to the 32-bit id registers. */ aa32_max_features(cpu); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-34-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/target_cpu.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/linux-user/aarch64/target_cpu.h b/linux-user/aarch64/target_cpu.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/target_cpu.h +++ b/linux-user/aarch64/target_cpu.h @@ -XXX,XX +XXX,XX @@ static inline void cpu_clone_regs_parent(CPUARMState *env, unsigned flags) static inline void cpu_set_tls(CPUARMState *env, target_ulong newtls) { - /* Note that AArch64 Linux keeps the TLS pointer in TPIDR; this is + /* + * Note that AArch64 Linux keeps the TLS pointer in TPIDR; this is * different from AArch32 Linux, which uses TPIDRRO. */ env->cp15.tpidr_el[0] = newtls; + /* TPIDR2_EL0 is cleared with CLONE_SETTLS. */ + env->cp15.tpidr2_el0 = 0; } static inline abi_ulong get_sp_from_cpustate(CPUARMState *state) -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-35-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/cpu_loop.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/linux-user/aarch64/cpu_loop.c b/linux-user/aarch64/cpu_loop.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/cpu_loop.c +++ b/linux-user/aarch64/cpu_loop.c @@ -XXX,XX +XXX,XX @@ void cpu_loop(CPUARMState *env) switch (trapnr) { case EXCP_SWI: + /* + * On syscall, PSTATE.ZA is preserved, along with the ZA matrix. + * PSTATE.SM is cleared, per SMSTOP, which does ResetSVEState. + */ + if (FIELD_EX64(env->svcr, SVCR, SM)) { + env->svcr = FIELD_DP64(env->svcr, SVCR, SM, 0); + arm_rebuild_hflags(env); + arm_reset_sve_state(env); + } ret = do_syscall(env, env->xregs[8], env->xregs[0], -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Make sure to zero the currently reserved fields. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-36-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ struct target_extra_context { struct target_sve_context { struct target_aarch64_ctx head; uint16_t vl; - uint16_t reserved[3]; + uint16_t flags; + uint16_t reserved[2]; /* The actual SVE data immediately follows. It is laid out * according to TARGET_SVE_SIG_{Z,P}REG_OFFSET, based off of * the original struct pointer. @@ -XXX,XX +XXX,XX @@ struct target_sve_context { #define TARGET_SVE_SIG_CONTEXT_SIZE(VQ) \ (TARGET_SVE_SIG_PREG_OFFSET(VQ, 17)) +#define TARGET_SVE_SIG_FLAG_SM 1 + struct target_rt_sigframe { struct target_siginfo info; struct target_ucontext uc; @@ -XXX,XX +XXX,XX @@ static void target_setup_sve_record(struct target_sve_context *sve, { int i, j; + memset(sve, 0, sizeof(*sve)); __put_user(TARGET_SVE_MAGIC, &sve->head.magic); __put_user(size, &sve->head.size); __put_user(vq * TARGET_SVE_VQ_BYTES, &sve->vl); + if (FIELD_EX64(env->svcr, SVCR, SM)) { + __put_user(TARGET_SVE_SIG_FLAG_SM, &sve->flags); + } /* Note that SVE regs are stored as a byte stream, with each byte element * at a subsequent address. This corresponds to a little-endian store -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Fold the return value setting into the goto, so each point of failure need not do both. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-37-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 26 +++++++++++--------------- 1 file changed, 11 insertions(+), 15 deletions(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, struct target_sve_context *sve = NULL; uint64_t extra_datap = 0; bool used_extra = false; - bool err = false; int vq = 0, sve_size = 0; target_restore_general_frame(env, sf); @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, switch (magic) { case 0: if (size != 0) { - err = true; - goto exit; + goto err; } if (used_extra) { ctx = NULL; @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, case TARGET_FPSIMD_MAGIC: if (fpsimd || size != sizeof(struct target_fpsimd_context)) { - err = true; - goto exit; + goto err; } fpsimd = (struct target_fpsimd_context *)ctx; break; @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, break; } } - err = true; - goto exit; + goto err; case TARGET_EXTRA_MAGIC: if (extra || size != sizeof(struct target_extra_context)) { - err = true; - goto exit; + goto err; } __get_user(extra_datap, &((struct target_extra_context *)ctx)->datap); @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, /* Unknown record -- we certainly didn't generate it. * Did we in fact get out of sync? */ - err = true; - goto exit; + goto err; } ctx = (void *)ctx + size; } @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, if (fpsimd) { target_restore_fpsimd_record(env, fpsimd); } else { - err = true; + goto err; } /* SVE data, if present, overwrites FPSIMD data. */ if (sve) { target_restore_sve_record(env, sve, vq); } - - exit: unlock_user(extra, extra_datap, 0); - return err; + return 0; + + err: + unlock_user(extra, extra_datap, 0); + return 1; } static abi_ulong get_sigframe(struct target_sigaction *ka, -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> In parse_user_sigframe, the kernel rejects duplicate sve records, or records that are smaller than the header. We were silently allowing these cases to pass, dropping the record. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-38-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, break; case TARGET_SVE_MAGIC: + if (sve || size < sizeof(struct target_sve_context)) { + goto err; + } if (cpu_isar_feature(aa64_sve, env_archcpu(env))) { vq = sve_vq(env); sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(vq), 16); - if (!sve && size == sve_size) { + if (size == sve_size) { sve = (struct target_sve_context *)ctx; break; } -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-39-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, __get_user(extra_size, &((struct target_extra_context *)ctx)->size); extra = lock_user(VERIFY_READ, extra_datap, extra_size, 0); + if (!extra) { + return 1; + } break; default: -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Move the checks out of the parsing loop and into the restore function. This more closely mirrors the code structure in the kernel, and is slightly clearer. Reject rather than silently skip incorrect VL and SVE record sizes, bringing our checks in to line with those the kernel does. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-40-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 51 +++++++++++++++++++++++++------------ 1 file changed, 35 insertions(+), 16 deletions(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ static void target_restore_fpsimd_record(CPUARMState *env, } } -static void target_restore_sve_record(CPUARMState *env, - struct target_sve_context *sve, int vq) +static bool target_restore_sve_record(CPUARMState *env, + struct target_sve_context *sve, + int size) { - int i, j; + int i, j, vl, vq; - /* Note that SVE regs are stored as a byte stream, with each byte element + if (!cpu_isar_feature(aa64_sve, env_archcpu(env))) { + return false; + } + + __get_user(vl, &sve->vl); + vq = sve_vq(env); + + /* Reject mismatched VL. */ + if (vl != vq * TARGET_SVE_VQ_BYTES) { + return false; + } + + /* Accept empty record -- used to clear PSTATE.SM. */ + if (size <= sizeof(*sve)) { + return true; + } + + /* Reject non-empty but incomplete record. */ + if (size < TARGET_SVE_SIG_CONTEXT_SIZE(vq)) { + return false; + } + + /* + * Note that SVE regs are stored as a byte stream, with each byte element * at a subsequent address. This corresponds to a little-endian load * of our 64-bit hunks. */ @@ -XXX,XX +XXX,XX @@ static void target_restore_sve_record(CPUARMState *env, } } } + return true; } static int target_restore_sigframe(CPUARMState *env, @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, struct target_sve_context *sve = NULL; uint64_t extra_datap = 0; bool used_extra = false; - int vq = 0, sve_size = 0; + int sve_size = 0; target_restore_general_frame(env, sf); @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, if (sve || size < sizeof(struct target_sve_context)) { goto err; } - if (cpu_isar_feature(aa64_sve, env_archcpu(env))) { - vq = sve_vq(env); - sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(vq), 16); - if (size == sve_size) { - sve = (struct target_sve_context *)ctx; - break; - } - } - goto err; + sve = (struct target_sve_context *)ctx; + sve_size = size; + break; case TARGET_EXTRA_MAGIC: if (extra || size != sizeof(struct target_extra_context)) { @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, } /* SVE data, if present, overwrites FPSIMD data. */ - if (sve) { - target_restore_sve_record(env, sve, vq); + if (sve && !target_restore_sve_record(env, sve, sve_size)) { + goto err; } unlock_user(extra, extra_datap, 0); return 0; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Set the SM bit in the SVE record on signal delivery, create the ZA record. Restore SM and ZA state according to the records present on return. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-41-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/signal.c | 167 +++++++++++++++++++++++++++++++++--- 1 file changed, 154 insertions(+), 13 deletions(-) diff --git a/linux-user/aarch64/signal.c b/linux-user/aarch64/signal.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/signal.c +++ b/linux-user/aarch64/signal.c @@ -XXX,XX +XXX,XX @@ struct target_sve_context { #define TARGET_SVE_SIG_FLAG_SM 1 +#define TARGET_ZA_MAGIC 0x54366345 + +struct target_za_context { + struct target_aarch64_ctx head; + uint16_t vl; + uint16_t reserved[3]; + /* The actual ZA data immediately follows. */ +}; + +#define TARGET_ZA_SIG_REGS_OFFSET \ + QEMU_ALIGN_UP(sizeof(struct target_za_context), TARGET_SVE_VQ_BYTES) +#define TARGET_ZA_SIG_ZAV_OFFSET(VQ, N) \ + (TARGET_ZA_SIG_REGS_OFFSET + (VQ) * TARGET_SVE_VQ_BYTES * (N)) +#define TARGET_ZA_SIG_CONTEXT_SIZE(VQ) \ + TARGET_ZA_SIG_ZAV_OFFSET(VQ, VQ * TARGET_SVE_VQ_BYTES) + struct target_rt_sigframe { struct target_siginfo info; struct target_ucontext uc; @@ -XXX,XX +XXX,XX @@ static void target_setup_end_record(struct target_aarch64_ctx *end) } static void target_setup_sve_record(struct target_sve_context *sve, - CPUARMState *env, int vq, int size) + CPUARMState *env, int size) { - int i, j; + int i, j, vq = sve_vq(env); memset(sve, 0, sizeof(*sve)); __put_user(TARGET_SVE_MAGIC, &sve->head.magic); @@ -XXX,XX +XXX,XX @@ static void target_setup_sve_record(struct target_sve_context *sve, } } +static void target_setup_za_record(struct target_za_context *za, + CPUARMState *env, int size) +{ + int vq = sme_vq(env); + int vl = vq * TARGET_SVE_VQ_BYTES; + int i, j; + + memset(za, 0, sizeof(*za)); + __put_user(TARGET_ZA_MAGIC, &za->head.magic); + __put_user(size, &za->head.size); + __put_user(vl, &za->vl); + + if (size == TARGET_ZA_SIG_CONTEXT_SIZE(0)) { + return; + } + assert(size == TARGET_ZA_SIG_CONTEXT_SIZE(vq)); + + /* + * Note that ZA vectors are stored as a byte stream, + * with each byte element at a subsequent address. + */ + for (i = 0; i < vl; ++i) { + uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i); + for (j = 0; j < vq * 2; ++j) { + __put_user_e(env->zarray[i].d[j], z + j, le); + } + } +} + static void target_restore_general_frame(CPUARMState *env, struct target_rt_sigframe *sf) { @@ -XXX,XX +XXX,XX @@ static void target_restore_fpsimd_record(CPUARMState *env, static bool target_restore_sve_record(CPUARMState *env, struct target_sve_context *sve, - int size) + int size, int *svcr) { - int i, j, vl, vq; + int i, j, vl, vq, flags; + bool sm; - if (!cpu_isar_feature(aa64_sve, env_archcpu(env))) { + __get_user(vl, &sve->vl); + __get_user(flags, &sve->flags); + + sm = flags & TARGET_SVE_SIG_FLAG_SM; + + /* The cpu must support Streaming or Non-streaming SVE. */ + if (sm + ? !cpu_isar_feature(aa64_sme, env_archcpu(env)) + : !cpu_isar_feature(aa64_sve, env_archcpu(env))) { return false; } - __get_user(vl, &sve->vl); - vq = sve_vq(env); + /* + * Note that we cannot use sve_vq() because that depends on the + * current setting of PSTATE.SM, not the state to be restored. + */ + vq = sve_vqm1_for_el_sm(env, 0, sm) + 1; /* Reject mismatched VL. */ if (vl != vq * TARGET_SVE_VQ_BYTES) { @@ -XXX,XX +XXX,XX @@ static bool target_restore_sve_record(CPUARMState *env, return false; } + *svcr = FIELD_DP64(*svcr, SVCR, SM, sm); + /* * Note that SVE regs are stored as a byte stream, with each byte element * at a subsequent address. This corresponds to a little-endian load @@ -XXX,XX +XXX,XX @@ static bool target_restore_sve_record(CPUARMState *env, return true; } +static bool target_restore_za_record(CPUARMState *env, + struct target_za_context *za, + int size, int *svcr) +{ + int i, j, vl, vq; + + if (!cpu_isar_feature(aa64_sme, env_archcpu(env))) { + return false; + } + + __get_user(vl, &za->vl); + vq = sme_vq(env); + + /* Reject mismatched VL. */ + if (vl != vq * TARGET_SVE_VQ_BYTES) { + return false; + } + + /* Accept empty record -- used to clear PSTATE.ZA. */ + if (size <= TARGET_ZA_SIG_CONTEXT_SIZE(0)) { + return true; + } + + /* Reject non-empty but incomplete record. */ + if (size < TARGET_ZA_SIG_CONTEXT_SIZE(vq)) { + return false; + } + + *svcr = FIELD_DP64(*svcr, SVCR, ZA, 1); + + for (i = 0; i < vl; ++i) { + uint64_t *z = (void *)za + TARGET_ZA_SIG_ZAV_OFFSET(vq, i); + for (j = 0; j < vq * 2; ++j) { + __get_user_e(env->zarray[i].d[j], z + j, le); + } + } + return true; +} + static int target_restore_sigframe(CPUARMState *env, struct target_rt_sigframe *sf) { struct target_aarch64_ctx *ctx, *extra = NULL; struct target_fpsimd_context *fpsimd = NULL; struct target_sve_context *sve = NULL; + struct target_za_context *za = NULL; uint64_t extra_datap = 0; bool used_extra = false; int sve_size = 0; + int za_size = 0; + int svcr = 0; target_restore_general_frame(env, sf); @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, sve_size = size; break; + case TARGET_ZA_MAGIC: + if (za || size < sizeof(struct target_za_context)) { + goto err; + } + za = (struct target_za_context *)ctx; + za_size = size; + break; + case TARGET_EXTRA_MAGIC: if (extra || size != sizeof(struct target_extra_context)) { goto err; @@ -XXX,XX +XXX,XX @@ static int target_restore_sigframe(CPUARMState *env, } /* SVE data, if present, overwrites FPSIMD data. */ - if (sve && !target_restore_sve_record(env, sve, sve_size)) { + if (sve && !target_restore_sve_record(env, sve, sve_size, &svcr)) { goto err; } + if (za && !target_restore_za_record(env, za, za_size, &svcr)) { + goto err; + } + if (env->svcr != svcr) { + env->svcr = svcr; + arm_rebuild_hflags(env); + } unlock_user(extra, extra_datap, 0); return 0; @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, .total_size = offsetof(struct target_rt_sigframe, uc.tuc_mcontext.__reserved), }; - int fpsimd_ofs, fr_ofs, sve_ofs = 0, vq = 0, sve_size = 0; + int fpsimd_ofs, fr_ofs, sve_ofs = 0, za_ofs = 0; + int sve_size = 0, za_size = 0; struct target_rt_sigframe *frame; struct target_rt_frame_record *fr; abi_ulong frame_addr, return_addr; @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, &layout); /* SVE state needs saving only if it exists. */ - if (cpu_isar_feature(aa64_sve, env_archcpu(env))) { - vq = sve_vq(env); - sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(vq), 16); + if (cpu_isar_feature(aa64_sve, env_archcpu(env)) || + cpu_isar_feature(aa64_sme, env_archcpu(env))) { + sve_size = QEMU_ALIGN_UP(TARGET_SVE_SIG_CONTEXT_SIZE(sve_vq(env)), 16); sve_ofs = alloc_sigframe_space(sve_size, &layout); } + if (cpu_isar_feature(aa64_sme, env_archcpu(env))) { + /* ZA state needs saving only if it is enabled. */ + if (FIELD_EX64(env->svcr, SVCR, ZA)) { + za_size = TARGET_ZA_SIG_CONTEXT_SIZE(sme_vq(env)); + } else { + za_size = TARGET_ZA_SIG_CONTEXT_SIZE(0); + } + za_ofs = alloc_sigframe_space(za_size, &layout); + } if (layout.extra_ofs) { /* Reserve space for the extra end marker. The standard end marker @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, target_setup_end_record((void *)frame + layout.extra_end_ofs); } if (sve_ofs) { - target_setup_sve_record((void *)frame + sve_ofs, env, vq, sve_size); + target_setup_sve_record((void *)frame + sve_ofs, env, sve_size); + } + if (za_ofs) { + target_setup_za_record((void *)frame + za_ofs, env, za_size); } /* Set up the stack frame for unwinding. */ @@ -XXX,XX +XXX,XX @@ static void target_setup_frame(int usig, struct target_sigaction *ka, env->btype = 2; } + /* + * Invoke the signal handler with both SM and ZA disabled. + * When clearing SM, ResetSVEState, per SMSTOP. + */ + if (FIELD_EX64(env->svcr, SVCR, SM)) { + arm_reset_sve_state(env); + } + if (env->svcr) { + env->svcr = 0; + arm_rebuild_hflags(env); + } + if (info) { tswap_siginfo(&frame->info, info); env->xregs[1] = frame_addr + offsetof(struct target_rt_sigframe, info); -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Add "sve" to the sve prctl functions, to distinguish them from the coming "sme" prctls with similar names. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-42-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/target_prctl.h | 8 ++++---- linux-user/syscall.c | 12 ++++++------ 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/linux-user/aarch64/target_prctl.h b/linux-user/aarch64/target_prctl.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/target_prctl.h +++ b/linux-user/aarch64/target_prctl.h @@ -XXX,XX +XXX,XX @@ #ifndef AARCH64_TARGET_PRCTL_H #define AARCH64_TARGET_PRCTL_H -static abi_long do_prctl_get_vl(CPUArchState *env) +static abi_long do_prctl_sve_get_vl(CPUArchState *env) { ARMCPU *cpu = env_archcpu(env); if (cpu_isar_feature(aa64_sve, cpu)) { @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_get_vl(CPUArchState *env) } return -TARGET_EINVAL; } -#define do_prctl_get_vl do_prctl_get_vl +#define do_prctl_sve_get_vl do_prctl_sve_get_vl -static abi_long do_prctl_set_vl(CPUArchState *env, abi_long arg2) +static abi_long do_prctl_sve_set_vl(CPUArchState *env, abi_long arg2) { /* * We cannot support either PR_SVE_SET_VL_ONEXEC or PR_SVE_VL_INHERIT. @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_set_vl(CPUArchState *env, abi_long arg2) } return -TARGET_EINVAL; } -#define do_prctl_set_vl do_prctl_set_vl +#define do_prctl_sve_set_vl do_prctl_sve_set_vl static abi_long do_prctl_reset_keys(CPUArchState *env, abi_long arg2) { diff --git a/linux-user/syscall.c b/linux-user/syscall.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_inval1(CPUArchState *env, abi_long arg2) #ifndef do_prctl_set_fp_mode #define do_prctl_set_fp_mode do_prctl_inval1 #endif -#ifndef do_prctl_get_vl -#define do_prctl_get_vl do_prctl_inval0 +#ifndef do_prctl_sve_get_vl +#define do_prctl_sve_get_vl do_prctl_inval0 #endif -#ifndef do_prctl_set_vl -#define do_prctl_set_vl do_prctl_inval1 +#ifndef do_prctl_sve_set_vl +#define do_prctl_sve_set_vl do_prctl_inval1 #endif #ifndef do_prctl_reset_keys #define do_prctl_reset_keys do_prctl_inval1 @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl(CPUArchState *env, abi_long option, abi_long arg2, case PR_SET_FP_MODE: return do_prctl_set_fp_mode(env, arg2); case PR_SVE_GET_VL: - return do_prctl_get_vl(env); + return do_prctl_sve_get_vl(env); case PR_SVE_SET_VL: - return do_prctl_set_vl(env, arg2); + return do_prctl_sve_set_vl(env, arg2); case PR_PAC_RESET_KEYS: if (arg3 || arg4 || arg5) { return -TARGET_EINVAL; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> These prctl set the Streaming SVE vector length, which may be completely different from the Normal SVE vector length. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-43-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/aarch64/target_prctl.h | 54 +++++++++++++++++++++++++++++++ linux-user/syscall.c | 16 +++++++++ 2 files changed, 70 insertions(+) diff --git a/linux-user/aarch64/target_prctl.h b/linux-user/aarch64/target_prctl.h index XXXXXXX..XXXXXXX 100644 --- a/linux-user/aarch64/target_prctl.h +++ b/linux-user/aarch64/target_prctl.h @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_sve_get_vl(CPUArchState *env) { ARMCPU *cpu = env_archcpu(env); if (cpu_isar_feature(aa64_sve, cpu)) { + /* PSTATE.SM is always unset on syscall entry. */ return sve_vq(env) * 16; } return -TARGET_EINVAL; @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_sve_set_vl(CPUArchState *env, abi_long arg2) && arg2 >= 0 && arg2 <= 512 * 16 && !(arg2 & 15)) { uint32_t vq, old_vq; + /* PSTATE.SM is always unset on syscall entry. */ old_vq = sve_vq(env); /* @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_sve_set_vl(CPUArchState *env, abi_long arg2) } #define do_prctl_sve_set_vl do_prctl_sve_set_vl +static abi_long do_prctl_sme_get_vl(CPUArchState *env) +{ + ARMCPU *cpu = env_archcpu(env); + if (cpu_isar_feature(aa64_sme, cpu)) { + return sme_vq(env) * 16; + } + return -TARGET_EINVAL; +} +#define do_prctl_sme_get_vl do_prctl_sme_get_vl + +static abi_long do_prctl_sme_set_vl(CPUArchState *env, abi_long arg2) +{ + /* + * We cannot support either PR_SME_SET_VL_ONEXEC or PR_SME_VL_INHERIT. + * Note the kernel definition of sve_vl_valid allows for VQ=512, + * i.e. VL=8192, even though the architectural maximum is VQ=16. + */ + if (cpu_isar_feature(aa64_sme, env_archcpu(env)) + && arg2 >= 0 && arg2 <= 512 * 16 && !(arg2 & 15)) { + int vq, old_vq; + + old_vq = sme_vq(env); + + /* + * Bound the value of vq, so that we know that it fits into + * the 4-bit field in SMCR_EL1. Because PSTATE.SM is cleared + * on syscall entry, we are not modifying the current SVE + * vector length. + */ + vq = MAX(arg2 / 16, 1); + vq = MIN(vq, 16); + env->vfp.smcr_el[1] = + FIELD_DP64(env->vfp.smcr_el[1], SMCR, LEN, vq - 1); + + /* Delay rebuilding hflags until we know if ZA must change. */ + vq = sve_vqm1_for_el_sm(env, 0, true) + 1; + + if (vq != old_vq) { + /* + * PSTATE.ZA state is cleared on any change to SVL. + * We need not call arm_rebuild_hflags because PSTATE.SM was + * cleared on syscall entry, so this hasn't changed VL. + */ + env->svcr = FIELD_DP64(env->svcr, SVCR, ZA, 0); + arm_rebuild_hflags(env); + } + return vq * 16; + } + return -TARGET_EINVAL; +} +#define do_prctl_sme_set_vl do_prctl_sme_set_vl + static abi_long do_prctl_reset_keys(CPUArchState *env, abi_long arg2) { ARMCPU *cpu = env_archcpu(env); diff --git a/linux-user/syscall.c b/linux-user/syscall.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/syscall.c +++ b/linux-user/syscall.c @@ -XXX,XX +XXX,XX @@ abi_long do_arch_prctl(CPUX86State *env, int code, abi_ulong addr) #ifndef PR_SET_SYSCALL_USER_DISPATCH # define PR_SET_SYSCALL_USER_DISPATCH 59 #endif +#ifndef PR_SME_SET_VL +# define PR_SME_SET_VL 63 +# define PR_SME_GET_VL 64 +# define PR_SME_VL_LEN_MASK 0xffff +# define PR_SME_VL_INHERIT (1 << 17) +#endif #include "target_prctl.h" @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl_inval1(CPUArchState *env, abi_long arg2) #ifndef do_prctl_set_unalign #define do_prctl_set_unalign do_prctl_inval1 #endif +#ifndef do_prctl_sme_get_vl +#define do_prctl_sme_get_vl do_prctl_inval0 +#endif +#ifndef do_prctl_sme_set_vl +#define do_prctl_sme_set_vl do_prctl_inval1 +#endif static abi_long do_prctl(CPUArchState *env, abi_long option, abi_long arg2, abi_long arg3, abi_long arg4, abi_long arg5) @@ -XXX,XX +XXX,XX @@ static abi_long do_prctl(CPUArchState *env, abi_long option, abi_long arg2, return do_prctl_sve_get_vl(env); case PR_SVE_SET_VL: return do_prctl_sve_set_vl(env, arg2); + case PR_SME_GET_VL: + return do_prctl_sme_get_vl(env); + case PR_SME_SET_VL: + return do_prctl_sme_set_vl(env, arg2); case PR_PAC_RESET_KEYS: if (arg3 || arg4 || arg5) { return -TARGET_EINVAL; -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> There's no reason to set CPACR_EL1.ZEN if SVE disabled. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-44-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(DeviceState *dev) /* and to the FP/Neon instructions */ env->cp15.cpacr_el1 = FIELD_DP64(env->cp15.cpacr_el1, CPACR_EL1, FPEN, 3); - /* and to the SVE instructions */ - env->cp15.cpacr_el1 = FIELD_DP64(env->cp15.cpacr_el1, - CPACR_EL1, ZEN, 3); - /* with reasonable vector length */ + /* and to the SVE instructions, with default vector length */ if (cpu_isar_feature(aa64_sve, cpu)) { + env->cp15.cpacr_el1 = FIELD_DP64(env->cp15.cpacr_el1, + CPACR_EL1, ZEN, 3); env->vfp.zcr_el[1] = cpu->sve_default_vq - 1; } /* -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Enable SME, TPIDR2_EL0, and FA64 if supported by the cpu. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-45-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.c | 11 +++++++++++ 1 file changed, 11 insertions(+) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset(DeviceState *dev) CPACR_EL1, ZEN, 3); env->vfp.zcr_el[1] = cpu->sve_default_vq - 1; } + /* and for SME instructions, with default vector length, and TPIDR2 */ + if (cpu_isar_feature(aa64_sme, cpu)) { + env->cp15.sctlr_el[1] |= SCTLR_EnTP2; + env->cp15.cpacr_el1 = FIELD_DP64(env->cp15.cpacr_el1, + CPACR_EL1, SMEN, 3); + env->vfp.smcr_el[1] = cpu->sme_default_vq - 1; + if (cpu_isar_feature(aa64_sme_fa64, cpu)) { + env->vfp.smcr_el[1] = FIELD_DP64(env->vfp.smcr_el[1], + SMCR, FA64, 1); + } + } /* * Enable 48-bit address space (TODO: take reserved_va into account). * Enable TBI0 but not TBI1. -- 2.25.1 From: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20220708151540.18136-46-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/elfload.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/linux-user/elfload.c b/linux-user/elfload.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/elfload.c +++ b/linux-user/elfload.c @@ -XXX,XX +XXX,XX @@ enum { ARM_HWCAP2_A64_RNG = 1 << 16, ARM_HWCAP2_A64_BTI = 1 << 17, ARM_HWCAP2_A64_MTE = 1 << 18, + ARM_HWCAP2_A64_ECV = 1 << 19, + ARM_HWCAP2_A64_AFP = 1 << 20, + ARM_HWCAP2_A64_RPRES = 1 << 21, + ARM_HWCAP2_A64_MTE3 = 1 << 22, + ARM_HWCAP2_A64_SME = 1 << 23, + ARM_HWCAP2_A64_SME_I16I64 = 1 << 24, + ARM_HWCAP2_A64_SME_F64F64 = 1 << 25, + ARM_HWCAP2_A64_SME_I8I32 = 1 << 26, + ARM_HWCAP2_A64_SME_F16F32 = 1 << 27, + ARM_HWCAP2_A64_SME_B16F32 = 1 << 28, + ARM_HWCAP2_A64_SME_F32F32 = 1 << 29, + ARM_HWCAP2_A64_SME_FA64 = 1 << 30, }; #define ELF_HWCAP get_elf_hwcap() @@ -XXX,XX +XXX,XX @@ static uint32_t get_elf_hwcap2(void) GET_FEATURE_ID(aa64_rndr, ARM_HWCAP2_A64_RNG); GET_FEATURE_ID(aa64_bti, ARM_HWCAP2_A64_BTI); GET_FEATURE_ID(aa64_mte, ARM_HWCAP2_A64_MTE); + GET_FEATURE_ID(aa64_sme, (ARM_HWCAP2_A64_SME | + ARM_HWCAP2_A64_SME_F32F32 | + ARM_HWCAP2_A64_SME_B16F32 | + ARM_HWCAP2_A64_SME_F16F32 | + ARM_HWCAP2_A64_SME_I8I32)); + GET_FEATURE_ID(aa64_sme_f64f64, ARM_HWCAP2_A64_SME_F64F64); + GET_FEATURE_ID(aa64_sme_i16i64, ARM_HWCAP2_A64_SME_I16I64); + GET_FEATURE_ID(aa64_sme_fa64, ARM_HWCAP2_A64_SME_FA64); return hwcaps; } -- 2.25.1