The following changes since commit b6d32a06fc0984e537091cba08f2e1ed9f775d74: Merge tag 'pull-trivial-patches' of https://gitlab.com/mjt0k/qemu into staging (2024-06-30 16:12:24 -0700) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20240701 for you to fetch changes up to 58c782de557beb496bfb4c5ade721bbbd2480c72: tests/qtest: Ensure STM32L4x5 EXTI state is correct at the end of QTests (2024-07-01 15:40:54 +0100) ---------------------------------------------------------------- target-arm queue: * tests/avocado: update firmware for sbsa-ref and use all cores * hw/arm/smmu-common: Replace smmu_iommu_mr with smmu_find_sdev * arm: Fix VCMLA Dd, Dn, Dm[idx] * arm: Fix SQDMULH (by element) with Q=0 * arm: Fix FJCVTZS vs flush-to-zero * arm: More conversion of A64 AdvSIMD to decodetree * arm: Enable FEAT_Debugv8p8 for -cpu max * MAINTAINERS: Update family name for Patrick Leis * hw/arm/xilinx_zynq: Add boot-mode property * docs/system/arm: Add a doc for zynq board * hw/misc: In STM32L4x5 EXTI, correct configurable interrupts * tests/qtest: fix minor issues in STM32L4x5 tests ---------------------------------------------------------------- Gustavo Romero (3): target/arm: Fix indentation target/arm: Move initialization of debug ID registers target/arm: Enable FEAT_Debugv8p8 for -cpu max Inès Varhol (3): tests/qtest: Fix STM32L4x5 SYSCFG irq line 15 state assumption hw/misc: In STM32L4x5 EXTI, correct configurable interrupts tests/qtest: Ensure STM32L4x5 EXTI state is correct at the end of QTests Marcin Juszkiewicz (2): tests/avocado: update firmware for sbsa-ref tests/avocado: use default amount of cores on sbsa-ref Nicolin Chen (1): hw/arm/smmu-common: Replace smmu_iommu_mr with smmu_find_sdev Patrick Leis (1): MAINTAINERS: Update my family name Rayhan Faizel (3): hw/nvram: Add BCM2835 OTP device hw/arm: Connect OTP device to BCM2835 hw/misc: Implement mailbox properties for customer OTP and device specific private keys Richard Henderson (13): target/arm: Fix VCMLA Dd, Dn, Dm[idx] target/arm: Fix SQDMULH (by element) with Q=0 target/arm: Fix FJCVTZS vs flush-to-zero target/arm: Convert SQRDMLAH, SQRDMLSH to decodetree target/arm: Convert SDOT, UDOT to decodetree target/arm: Convert SUDOT, USDOT to decodetree target/arm: Convert BFDOT to decodetree target/arm: Convert BFMLALB, BFMLALT to decodetree target/arm: Convert BFMMLA, SMMLA, UMMLA, USMMLA to decodetree target/arm: Add data argument to do_fp3_vector target/arm: Convert FCADD to decodetree target/arm: Convert FCMLA to decodetree target/arm: Delete dead code from disas_simd_indexed Sai Pavan Boddu (3): hw/misc/zynq_slcr: Add boot-mode property hw/arm/xilinx_zynq: Add boot-mode property docs/system/arm: Add a doc for zynq board MAINTAINERS | 3 +- docs/system/arm/emulation.rst | 1 + docs/system/arm/xlnx-zynq.rst | 47 ++ docs/system/target-arm.rst | 1 + include/hw/arm/bcm2835_peripherals.h | 3 +- include/hw/arm/raspberrypi-fw-defs.h | 2 + include/hw/arm/smmu-common.h | 4 +- include/hw/misc/bcm2835_property.h | 2 + include/hw/misc/stm32l4x5_exti.h | 2 + include/hw/nvram/bcm2835_otp.h | 68 +++ target/arm/cpu.h | 2 + target/arm/helper.h | 10 + target/arm/tcg/a64.decode | 43 ++ hw/arm/bcm2835_peripherals.c | 15 +- hw/arm/smmu-common.c | 8 +- hw/arm/smmuv3.c | 12 +- hw/arm/xilinx_zynq.c | 31 ++ hw/misc/bcm2835_property.c | 87 ++++ hw/misc/stm32l4x5_exti.c | 28 +- hw/misc/zynq_slcr.c | 22 +- hw/nvram/bcm2835_otp.c | 187 +++++++ target/arm/tcg/cpu32.c | 35 +- target/arm/tcg/cpu64.c | 4 +- target/arm/tcg/translate-a64.c | 808 ++++++++++--------------------- target/arm/tcg/vec_helper.c | 100 +++- target/arm/vfp_helper.c | 18 +- tests/qtest/stm32l4x5_exti-test.c | 8 + tests/qtest/stm32l4x5_syscfg-test.c | 16 +- tests/tcg/aarch64/test-2375.c | 21 + hw/nvram/meson.build | 1 + tests/avocado/machine_aarch64_sbsaref.py | 16 +- tests/tcg/aarch64/Makefile.target | 3 +- 32 files changed, 967 insertions(+), 641 deletions(-) create mode 100644 docs/system/arm/xlnx-zynq.rst create mode 100644 include/hw/nvram/bcm2835_otp.h create mode 100644 hw/nvram/bcm2835_otp.c create mode 100644 tests/tcg/aarch64/test-2375.c From: Rayhan Faizel <rayhan.faizel@gmail.com> The OTP device registers are currently stubbed. For now, the device houses the OTP rows which will be accessed directly by other peripherals. Signed-off-by: Rayhan Faizel <rayhan.faizel@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/nvram/bcm2835_otp.h | 68 ++++++++++++ hw/nvram/bcm2835_otp.c | 187 +++++++++++++++++++++++++++++++++ hw/nvram/meson.build | 1 + 3 files changed, 256 insertions(+) create mode 100644 include/hw/nvram/bcm2835_otp.h create mode 100644 hw/nvram/bcm2835_otp.c diff --git a/include/hw/nvram/bcm2835_otp.h b/include/hw/nvram/bcm2835_otp.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/nvram/bcm2835_otp.h @@ -XXX,XX +XXX,XX @@ +/* + * BCM2835 One-Time Programmable (OTP) Memory + * + * Copyright (c) 2024 Rayhan Faizel <rayhan.faizel@gmail.com> + * + * SPDX-License-Identifier: MIT + */ + +#ifndef BCM2835_OTP_H +#define BCM2835_OTP_H + +#include "hw/sysbus.h" +#include "qom/object.h" + +#define TYPE_BCM2835_OTP "bcm2835-otp" +OBJECT_DECLARE_SIMPLE_TYPE(BCM2835OTPState, BCM2835_OTP) + +#define BCM2835_OTP_ROW_COUNT 66 + +/* https://elinux.org/BCM2835_registers#OTP */ +#define BCM2835_OTP_BOOTMODE_REG 0x00 +#define BCM2835_OTP_CONFIG_REG 0x04 +#define BCM2835_OTP_CTRL_LO_REG 0x08 +#define BCM2835_OTP_CTRL_HI_REG 0x0c +#define BCM2835_OTP_STATUS_REG 0x10 +#define BCM2835_OTP_BITSEL_REG 0x14 +#define BCM2835_OTP_DATA_REG 0x18 +#define BCM2835_OTP_ADDR_REG 0x1c +#define BCM2835_OTP_WRITE_DATA_READ_REG 0x20 +#define BCM2835_OTP_INIT_STATUS_REG 0x24 + + +/* -- Row 32: Undocumented -- */ + +#define BCM2835_OTP_ROW_32 32 + +/* Lock OTP Programming (Customer OTP and private key) */ +#define BCM2835_OTP_ROW_32_LOCK BIT(6) + +/* -- Row 36-43: Customer OTP -- */ + +#define BCM2835_OTP_CUSTOMER_OTP 36 +#define BCM2835_OTP_CUSTOMER_OTP_LEN 8 + +/* Magic numbers to lock programming of customer OTP and private key */ +#define BCM2835_OTP_LOCK_NUM1 0xffffffff +#define BCM2835_OTP_LOCK_NUM2 0xaffe0000 + +/* -- Row 56-63: Device-specific private key -- */ + +#define BCM2835_OTP_PRIVATE_KEY 56 +#define BCM2835_OTP_PRIVATE_KEY_LEN 8 + + +struct BCM2835OTPState { + /* <private> */ + SysBusDevice parent_obj; + + /* <public> */ + MemoryRegion iomem; + uint32_t otp_rows[BCM2835_OTP_ROW_COUNT]; +}; + + +uint32_t bcm2835_otp_get_row(BCM2835OTPState *s, unsigned int row); +void bcm2835_otp_set_row(BCM2835OTPState *s, unsigned int row, uint32_t value); + +#endif diff --git a/hw/nvram/bcm2835_otp.c b/hw/nvram/bcm2835_otp.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/nvram/bcm2835_otp.c @@ -XXX,XX +XXX,XX @@ +/* + * BCM2835 One-Time Programmable (OTP) Memory + * + * The OTP implementation is mostly a stub except for the OTP rows + * which are accessed directly by other peripherals such as the mailbox. + * + * The OTP registers are unimplemented due to lack of documentation. + * + * Copyright (c) 2024 Rayhan Faizel <rayhan.faizel@gmail.com> + * + * SPDX-License-Identifier: MIT + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "hw/nvram/bcm2835_otp.h" +#include "migration/vmstate.h" + +/* OTP rows are 1-indexed */ +uint32_t bcm2835_otp_get_row(BCM2835OTPState *s, unsigned int row) +{ + assert(row <= BCM2835_OTP_ROW_COUNT && row >= 1); + + return s->otp_rows[row - 1]; +} + +void bcm2835_otp_set_row(BCM2835OTPState *s, unsigned int row, + uint32_t value) +{ + assert(row <= BCM2835_OTP_ROW_COUNT && row >= 1); + + /* Real OTP rows work as e-fuses */ + s->otp_rows[row - 1] |= value; +} + +static uint64_t bcm2835_otp_read(void *opaque, hwaddr addr, unsigned size) +{ + switch (addr) { + case BCM2835_OTP_BOOTMODE_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_BOOTMODE_REG\n"); + break; + case BCM2835_OTP_CONFIG_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_CONFIG_REG\n"); + break; + case BCM2835_OTP_CTRL_LO_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_CTRL_LO_REG\n"); + break; + case BCM2835_OTP_CTRL_HI_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_CTRL_HI_REG\n"); + break; + case BCM2835_OTP_STATUS_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_STATUS_REG\n"); + break; + case BCM2835_OTP_BITSEL_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_BITSEL_REG\n"); + break; + case BCM2835_OTP_DATA_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_DATA_REG\n"); + break; + case BCM2835_OTP_ADDR_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_ADDR_REG\n"); + break; + case BCM2835_OTP_WRITE_DATA_READ_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_WRITE_DATA_READ_REG\n"); + break; + case BCM2835_OTP_INIT_STATUS_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_INIT_STATUS_REG\n"); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, addr); + } + + return 0; +} + +static void bcm2835_otp_write(void *opaque, hwaddr addr, + uint64_t value, unsigned int size) +{ + switch (addr) { + case BCM2835_OTP_BOOTMODE_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_BOOTMODE_REG\n"); + break; + case BCM2835_OTP_CONFIG_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_CONFIG_REG\n"); + break; + case BCM2835_OTP_CTRL_LO_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_CTRL_LO_REG\n"); + break; + case BCM2835_OTP_CTRL_HI_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_CTRL_HI_REG\n"); + break; + case BCM2835_OTP_STATUS_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_STATUS_REG\n"); + break; + case BCM2835_OTP_BITSEL_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_BITSEL_REG\n"); + break; + case BCM2835_OTP_DATA_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_DATA_REG\n"); + break; + case BCM2835_OTP_ADDR_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_ADDR_REG\n"); + break; + case BCM2835_OTP_WRITE_DATA_READ_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_WRITE_DATA_READ_REG\n"); + break; + case BCM2835_OTP_INIT_STATUS_REG: + qemu_log_mask(LOG_UNIMP, + "bcm2835_otp: BCM2835_OTP_INIT_STATUS_REG\n"); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, addr); + } +} + +static const MemoryRegionOps bcm2835_otp_ops = { + .read = bcm2835_otp_read, + .write = bcm2835_otp_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .impl = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void bcm2835_otp_realize(DeviceState *dev, Error **errp) +{ + BCM2835OTPState *s = BCM2835_OTP(dev); + memory_region_init_io(&s->iomem, OBJECT(dev), &bcm2835_otp_ops, s, + TYPE_BCM2835_OTP, 0x80); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); + + memset(s->otp_rows, 0x00, sizeof(s->otp_rows)); +} + +static const VMStateDescription vmstate_bcm2835_otp = { + .name = TYPE_BCM2835_OTP, + .version_id = 1, + .minimum_version_id = 1, + .fields = (const VMStateField[]) { + VMSTATE_UINT32_ARRAY(otp_rows, BCM2835OTPState, BCM2835_OTP_ROW_COUNT), + VMSTATE_END_OF_LIST() + } +}; + +static void bcm2835_otp_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = bcm2835_otp_realize; + dc->vmsd = &vmstate_bcm2835_otp; +} + +static const TypeInfo bcm2835_otp_info = { + .name = TYPE_BCM2835_OTP, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(BCM2835OTPState), + .class_init = bcm2835_otp_class_init, +}; + +static void bcm2835_otp_register_types(void) +{ + type_register_static(&bcm2835_otp_info); +} + +type_init(bcm2835_otp_register_types) diff --git a/hw/nvram/meson.build b/hw/nvram/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/nvram/meson.build +++ b/hw/nvram/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(files('fw_cfg-interface.c')) system_ss.add(files('fw_cfg.c')) +system_ss.add(when: 'CONFIG_RASPI', if_true: files('bcm2835_otp.c')) system_ss.add(when: 'CONFIG_CHRP_NVRAM', if_true: files('chrp_nvram.c')) system_ss.add(when: 'CONFIG_DS1225Y', if_true: files('ds1225y.c')) system_ss.add(when: 'CONFIG_NMC93XX_EEPROM', if_true: files('eeprom93xx.c')) -- 2.34.1 From: Rayhan Faizel <rayhan.faizel@gmail.com> Replace stubbed OTP memory region with the new OTP device. Signed-off-by: Rayhan Faizel <rayhan.faizel@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/bcm2835_peripherals.h | 3 ++- hw/arm/bcm2835_peripherals.c | 13 ++++++++++++- 2 files changed, 14 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/usb/hcd-dwc2.h" #include "hw/ssi/bcm2835_spi.h" #include "hw/i2c/bcm2835_i2c.h" +#include "hw/nvram/bcm2835_otp.h" #include "hw/misc/unimp.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct BCMSocPeripheralBaseState { BCM2835SPIState spi[1]; BCM2835I2CState i2c[3]; OrIRQState orgated_i2c_irq; - UnimplementedDeviceState otp; + BCM2835OTPState otp; UnimplementedDeviceState dbus; UnimplementedDeviceState ave0; UnimplementedDeviceState v3d; 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 raspi_peripherals_base_init(Object *obj) object_property_add_const_link(OBJECT(&s->fb), "dma-mr", OBJECT(&s->gpu_bus_mr)); + /* OTP */ + object_initialize_child(obj, "bcm2835-otp", &s->otp, + TYPE_BCM2835_OTP); + /* Property channel */ object_initialize_child(obj, "property", &s->property, TYPE_BCM2835_PROPERTY); @@ -XXX,XX +XXX,XX @@ void bcm_soc_peripherals_common_realize(DeviceState *dev, Error **errp) sysbus_connect_irq(SYS_BUS_DEVICE(&s->fb), 0, qdev_get_gpio_in(DEVICE(&s->mboxes), MBOX_CHAN_FB)); + /* OTP */ + if (!sysbus_realize(SYS_BUS_DEVICE(&s->otp), errp)) { + return; + } + + memory_region_add_subregion(&s->peri_mr, OTP_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->otp), 0)); + /* Property channel */ if (!sysbus_realize(SYS_BUS_DEVICE(&s->property), errp)) { return; @@ -XXX,XX +XXX,XX @@ void bcm_soc_peripherals_common_realize(DeviceState *dev, Error **errp) create_unimp(s, &s->i2s, "bcm2835-i2s", I2S_OFFSET, 0x100); create_unimp(s, &s->smi, "bcm2835-smi", SMI_OFFSET, 0x100); create_unimp(s, &s->bscsl, "bcm2835-spis", BSC_SL_OFFSET, 0x100); - create_unimp(s, &s->otp, "bcm2835-otp", OTP_OFFSET, 0x80); create_unimp(s, &s->dbus, "bcm2835-dbus", DBUS_OFFSET, 0x8000); create_unimp(s, &s->ave0, "bcm2835-ave0", AVE0_OFFSET, 0x8000); create_unimp(s, &s->v3d, "bcm2835-v3d", V3D_OFFSET, 0x1000); -- 2.34.1 From: Rayhan Faizel <rayhan.faizel@gmail.com> Four mailbox properties are implemented as follows: 1. Customer OTP: GET_CUSTOMER_OTP and SET_CUSTOMER_OTP 2. Device-specific private key: GET_PRIVATE_KEY and SET_PRIVATE_KEY. The customer OTP is located in the rows 36-43. The device-specific private key is located in the rows 56-63. The customer OTP can be locked with the magic numbers 0xffffffff 0xaffe0000 when running the SET_CUSTOMER_OTP mailbox command. Bit 6 of row 32 indicates this lock, which is undocumented. The lock also applies to the device-specific private key. Signed-off-by: Rayhan Faizel <rayhan.faizel@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/raspberrypi-fw-defs.h | 2 + include/hw/misc/bcm2835_property.h | 2 + hw/arm/bcm2835_peripherals.c | 2 + hw/misc/bcm2835_property.c | 87 ++++++++++++++++++++++++++++ 4 files changed, 93 insertions(+) diff --git a/include/hw/arm/raspberrypi-fw-defs.h b/include/hw/arm/raspberrypi-fw-defs.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/raspberrypi-fw-defs.h +++ b/include/hw/arm/raspberrypi-fw-defs.h @@ -XXX,XX +XXX,XX @@ enum rpi_firmware_property_tag { RPI_FWREQ_GET_THROTTLED = 0x00030046, RPI_FWREQ_GET_CLOCK_MEASURED = 0x00030047, RPI_FWREQ_NOTIFY_REBOOT = 0x00030048, + RPI_FWREQ_GET_PRIVATE_KEY = 0x00030081, RPI_FWREQ_SET_CLOCK_STATE = 0x00038001, RPI_FWREQ_SET_CLOCK_RATE = 0x00038002, RPI_FWREQ_SET_VOLTAGE = 0x00038003, @@ -XXX,XX +XXX,XX @@ enum rpi_firmware_property_tag { RPI_FWREQ_SET_PERIPH_REG = 0x00038045, RPI_FWREQ_GET_POE_HAT_VAL = 0x00030049, RPI_FWREQ_SET_POE_HAT_VAL = 0x00038049, + RPI_FWREQ_SET_PRIVATE_KEY = 0x00038081, RPI_FWREQ_SET_POE_HAT_VAL_OLD = 0x00030050, RPI_FWREQ_NOTIFY_XHCI_RESET = 0x00030058, RPI_FWREQ_GET_REBOOT_FLAGS = 0x00030064, diff --git a/include/hw/misc/bcm2835_property.h b/include/hw/misc/bcm2835_property.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/bcm2835_property.h +++ b/include/hw/misc/bcm2835_property.h @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "net/net.h" #include "hw/display/bcm2835_fb.h" +#include "hw/nvram/bcm2835_otp.h" #include "qom/object.h" #define TYPE_BCM2835_PROPERTY "bcm2835-property" @@ -XXX,XX +XXX,XX @@ struct BCM2835PropertyState { MemoryRegion iomem; qemu_irq mbox_irq; BCM2835FBState *fbdev; + BCM2835OTPState *otp; MACAddr macaddr; uint32_t board_rev; 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 raspi_peripherals_base_init(Object *obj) OBJECT(&s->fb)); object_property_add_const_link(OBJECT(&s->property), "dma-mr", OBJECT(&s->gpu_bus_mr)); + object_property_add_const_link(OBJECT(&s->property), "otp", + OBJECT(&s->otp)); /* Extended Mass Media Controller */ object_initialize_child(obj, "sdhci", &s->sdhci, TYPE_SYSBUS_SDHCI); diff --git a/hw/misc/bcm2835_property.c b/hw/misc/bcm2835_property.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/bcm2835_property.c +++ b/hw/misc/bcm2835_property.c @@ -XXX,XX +XXX,XX @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value) uint32_t tmp; int n; uint32_t offset, length, color; + uint32_t start_num, number, otp_row; /* * Copy the current state of the framebuffer config; we will update @@ -XXX,XX +XXX,XX @@ static void bcm2835_property_mbox_push(BCM2835PropertyState *s, uint32_t value) 0); resplen = VCHI_BUSADDR_SIZE; break; + + /* Customer OTP */ + + case RPI_FWREQ_GET_CUSTOMER_OTP: + start_num = ldl_le_phys(&s->dma_as, value + 12); + number = ldl_le_phys(&s->dma_as, value + 16); + + resplen = 8 + 4 * number; + + for (n = start_num; n < start_num + number && + n < BCM2835_OTP_CUSTOMER_OTP_LEN; n++) { + otp_row = bcm2835_otp_get_row(s->otp, + BCM2835_OTP_CUSTOMER_OTP + n); + stl_le_phys(&s->dma_as, + value + 20 + ((n - start_num) << 2), otp_row); + } + break; + case RPI_FWREQ_SET_CUSTOMER_OTP: + start_num = ldl_le_phys(&s->dma_as, value + 12); + number = ldl_le_phys(&s->dma_as, value + 16); + + resplen = 4; + + /* Magic numbers to permanently lock customer OTP */ + if (start_num == BCM2835_OTP_LOCK_NUM1 && + number == BCM2835_OTP_LOCK_NUM2) { + bcm2835_otp_set_row(s->otp, + BCM2835_OTP_ROW_32, + BCM2835_OTP_ROW_32_LOCK); + break; + } + + /* If row 32 has the lock bit, don't allow further writes */ + if (bcm2835_otp_get_row(s->otp, BCM2835_OTP_ROW_32) & + BCM2835_OTP_ROW_32_LOCK) { + break; + } + + for (n = start_num; n < start_num + number && + n < BCM2835_OTP_CUSTOMER_OTP_LEN; n++) { + otp_row = ldl_le_phys(&s->dma_as, + value + 20 + ((n - start_num) << 2)); + bcm2835_otp_set_row(s->otp, + BCM2835_OTP_CUSTOMER_OTP + n, otp_row); + } + break; + + /* Device-specific private key */ + + case RPI_FWREQ_GET_PRIVATE_KEY: + start_num = ldl_le_phys(&s->dma_as, value + 12); + number = ldl_le_phys(&s->dma_as, value + 16); + + resplen = 8 + 4 * number; + + for (n = start_num; n < start_num + number && + n < BCM2835_OTP_PRIVATE_KEY_LEN; n++) { + otp_row = bcm2835_otp_get_row(s->otp, + BCM2835_OTP_PRIVATE_KEY + n); + stl_le_phys(&s->dma_as, + value + 20 + ((n - start_num) << 2), otp_row); + } + break; + case RPI_FWREQ_SET_PRIVATE_KEY: + start_num = ldl_le_phys(&s->dma_as, value + 12); + number = ldl_le_phys(&s->dma_as, value + 16); + + resplen = 4; + + /* If row 32 has the lock bit, don't allow further writes */ + if (bcm2835_otp_get_row(s->otp, BCM2835_OTP_ROW_32) & + BCM2835_OTP_ROW_32_LOCK) { + break; + } + + for (n = start_num; n < start_num + number && + n < BCM2835_OTP_PRIVATE_KEY_LEN; n++) { + otp_row = ldl_le_phys(&s->dma_as, + value + 20 + ((n - start_num) << 2)); + bcm2835_otp_set_row(s->otp, + BCM2835_OTP_PRIVATE_KEY + n, otp_row); + } + break; default: qemu_log_mask(LOG_UNIMP, "bcm2835_property: unhandled tag 0x%08x\n", tag); @@ -XXX,XX +XXX,XX @@ static void bcm2835_property_realize(DeviceState *dev, Error **errp) s->dma_mr = MEMORY_REGION(obj); address_space_init(&s->dma_as, s->dma_mr, TYPE_BCM2835_PROPERTY "-memory"); + obj = object_property_get_link(OBJECT(dev), "otp", &error_abort); + s->otp = BCM2835_OTP(obj); + /* TODO: connect to MAC address of USB NIC device, once we emulate it */ qemu_macaddr_default_if_unset(&s->macaddr); -- 2.34.1 From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Update firmware to have graphics card memory fix from EDK2 commit c1d1910be6e04a8b1a73090cf2881fb698947a6e: OvmfPkg/QemuVideoDxe: add feature PCD to remap framebuffer W/C Some platforms (such as SBSA-QEMU on recent builds of the emulator) only tolerate misaligned accesses to normal memory, and raise alignment faults on such accesses to device memory, which is the default for PCIe MMIO BARs. When emulating a PCIe graphics controller, the framebuffer is typically exposed via a MMIO BAR, while the disposition of the region is closer to memory (no side effects on reads or writes, except for the changing picture on the screen; direct random access to any pixel in the image). In order to permit the use of such controllers on platforms that only tolerate these types of accesses for normal memory, it is necessary to remap the memory. Use the DXE services to set the desired capabilities and attributes. Hide this behavior under a feature PCD so only platforms that really need it can enable it. (OVMF on x86 has no need for this) With this fix enabled we can boot sbsa-ref with more than one cpu core. Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240620-b4-new-firmware-v3-1-29a3a2f1be1e@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/avocado/machine_aarch64_sbsaref.py | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tests/avocado/machine_aarch64_sbsaref.py b/tests/avocado/machine_aarch64_sbsaref.py index XXXXXXX..XXXXXXX 100644 --- a/tests/avocado/machine_aarch64_sbsaref.py +++ b/tests/avocado/machine_aarch64_sbsaref.py @@ -XXX,XX +XXX,XX @@ def fetch_firmware(self): Used components: - - Trusted Firmware 2.11.0 - - Tianocore EDK2 stable202405 - - Tianocore EDK2-platforms commit 4bbd0ed + - Trusted Firmware v2.11.0 + - Tianocore EDK2 4d4f569924 + - Tianocore EDK2-platforms 3f08401 """ # Secure BootRom (TF-A code) fs0_xz_url = ( "https://artifacts.codelinaro.org/artifactory/linaro-419-sbsa-ref/" - "20240528-140808/edk2/SBSA_FLASH0.fd.xz" + "20240619-148232/edk2/SBSA_FLASH0.fd.xz" ) - fs0_xz_hash = "fa6004900b67172914c908b78557fec4d36a5f784f4c3dd08f49adb75e1892a9" + fs0_xz_hash = "0c954842a590988f526984de22e21ae0ab9cb351a0c99a8a58e928f0c7359cf7" tar_xz_path = self.fetch_asset(fs0_xz_url, asset_hash=fs0_xz_hash, algorithm='sha256') archive.extract(tar_xz_path, self.workdir) @@ -XXX,XX +XXX,XX @@ def fetch_firmware(self): # Non-secure rom (UEFI and EFI variables) fs1_xz_url = ( "https://artifacts.codelinaro.org/artifactory/linaro-419-sbsa-ref/" - "20240528-140808/edk2/SBSA_FLASH1.fd.xz" + "20240619-148232/edk2/SBSA_FLASH1.fd.xz" ) - fs1_xz_hash = "5f3747d4000bc416d9641e33ff4ac60c3cc8cb74ca51b6e932e58531c62eb6f7" + fs1_xz_hash = "c6ec39374c4d79bb9e9cdeeb6db44732d90bb4a334cec92002b3f4b9cac4b5ee" tar_xz_path = self.fetch_asset(fs1_xz_url, asset_hash=fs1_xz_hash, algorithm='sha256') archive.extract(tar_xz_path, self.workdir) -- 2.34.1 From: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> The version of the sbsa-ref EDK2 firmware we used to use in this test had a bug where it might make an unaligned access to the framebuffer, which causes a guest crash on newer versions of QEMU where we enforce the architectural requirement that unaligned accesses to Device memory should take an exception. We happened to not notice this because our test was booting with "-smp 1" and through luck this didn't write the boot logo to the framebuffer at an unaligned address; but trying to boot the same firmware with two CPUs would result in a guest crash. Now we have updated the firmware we're using for the test, we can make the test use all the cores on the board, so we are testing the SMP boot path. Signed-off-by: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240620-b4-new-firmware-v3-2-29a3a2f1be1e@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/avocado/machine_aarch64_sbsaref.py | 2 -- 1 file changed, 2 deletions(-) diff --git a/tests/avocado/machine_aarch64_sbsaref.py b/tests/avocado/machine_aarch64_sbsaref.py index XXXXXXX..XXXXXXX 100644 --- a/tests/avocado/machine_aarch64_sbsaref.py +++ b/tests/avocado/machine_aarch64_sbsaref.py @@ -XXX,XX +XXX,XX @@ def fetch_firmware(self): f"if=pflash,file={fs0_path},format=raw", "-drive", f"if=pflash,file={fs1_path},format=raw", - "-smp", - "1", "-machine", "sbsa-ref", ) -- 2.34.1 From: Nicolin Chen <nicolinc@nvidia.com> The caller of smmu_iommu_mr wants to get sdev for smmuv3_flush_config(). Do it directly instead of bridging with an iommu mr pointer. Signed-off-by: Nicolin Chen <nicolinc@nvidia.com> Message-id: 20240619002218.926674-1-nicolinc@nvidia.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/smmu-common.h | 4 ++-- hw/arm/smmu-common.c | 8 ++------ hw/arm/smmuv3.c | 12 ++++-------- 3 files changed, 8 insertions(+), 16 deletions(-) diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/smmu-common.h +++ b/include/hw/arm/smmu-common.h @@ -XXX,XX +XXX,XX @@ int smmu_ptw(SMMUTransCfg *cfg, dma_addr_t iova, IOMMUAccessFlags perm, */ SMMUTransTableInfo *select_tt(SMMUTransCfg *cfg, dma_addr_t iova); -/* Return the iommu mr associated to @sid, or NULL if none */ -IOMMUMemoryRegion *smmu_iommu_mr(SMMUState *s, uint32_t sid); +/* Return the SMMUDevice associated to @sid, or NULL if none */ +SMMUDevice *smmu_find_sdev(SMMUState *s, uint32_t sid); #define SMMU_IOTLB_MAX_SIZE 256 diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmu-common.c +++ b/hw/arm/smmu-common.c @@ -XXX,XX +XXX,XX @@ static const PCIIOMMUOps smmu_ops = { .get_address_space = smmu_find_add_as, }; -IOMMUMemoryRegion *smmu_iommu_mr(SMMUState *s, uint32_t sid) +SMMUDevice *smmu_find_sdev(SMMUState *s, uint32_t sid) { uint8_t bus_n, devfn; SMMUPciBus *smmu_bus; - SMMUDevice *smmu; bus_n = PCI_BUS_NUM(sid); smmu_bus = smmu_find_smmu_pcibus(s, bus_n); if (smmu_bus) { devfn = SMMU_PCI_DEVFN(sid); - smmu = smmu_bus->pbdev[devfn]; - if (smmu) { - return &smmu->iommu; - } + return smmu_bus->pbdev[devfn]; } return NULL; } diff --git a/hw/arm/smmuv3.c b/hw/arm/smmuv3.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s) case SMMU_CMD_CFGI_STE: { uint32_t sid = CMD_SID(&cmd); - IOMMUMemoryRegion *mr = smmu_iommu_mr(bs, sid); - SMMUDevice *sdev; + SMMUDevice *sdev = smmu_find_sdev(bs, sid); if (CMD_SSEC(&cmd)) { cmd_error = SMMU_CERROR_ILL; break; } - if (!mr) { + if (!sdev) { break; } trace_smmuv3_cmdq_cfgi_ste(sid); - sdev = container_of(mr, SMMUDevice, iommu); smmuv3_flush_config(sdev); break; @@ -XXX,XX +XXX,XX @@ static int smmuv3_cmdq_consume(SMMUv3State *s) case SMMU_CMD_CFGI_CD_ALL: { uint32_t sid = CMD_SID(&cmd); - IOMMUMemoryRegion *mr = smmu_iommu_mr(bs, sid); - SMMUDevice *sdev; + SMMUDevice *sdev = smmu_find_sdev(bs, sid); if (CMD_SSEC(&cmd)) { cmd_error = SMMU_CERROR_ILL; break; } - if (!mr) { + if (!sdev) { break; } trace_smmuv3_cmdq_cfgi_cd(sid); - sdev = container_of(mr, SMMUDevice, iommu); smmuv3_flush_config(sdev); break; } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> The inner loop, bounded by eltspersegment, must not be larger than the outer loop, bounded by elements. Cc: qemu-stable@nongnu.org Fixes: 18fc2405781 ("target/arm: Implement SVE fp complex multiply add (indexed)") Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2376 Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240625183536.1672454-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/vec_helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlah_idx)(void *vd, void *vn, void *vm, void *va, intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 2, 2); uint32_t neg_real = flip ^ neg_imag; intptr_t elements = opr_sz / sizeof(float16); - intptr_t eltspersegment = 16 / sizeof(float16); + intptr_t eltspersegment = MIN(16 / sizeof(float16), elements); intptr_t i, j; /* Shift boolean to the sign bit so we can xor to negate. */ @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fcmlas_idx)(void *vd, void *vn, void *vm, void *va, intptr_t index = extract32(desc, SIMD_DATA_SHIFT + 2, 2); uint32_t neg_real = flip ^ neg_imag; intptr_t elements = opr_sz / sizeof(float32); - intptr_t eltspersegment = 16 / sizeof(float32); + intptr_t eltspersegment = MIN(16 / sizeof(float32), elements); intptr_t i, j; /* Shift boolean to the sign bit so we can xor to negate. */ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> The inner loop, bounded by eltspersegment, must not be larger than the outer loop, bounded by elements. Cc: qemu-stable@nongnu.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240625183536.1672454-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/vec_helper.c | 24 ++++++++++++++++-------- 1 file changed, 16 insertions(+), 8 deletions(-) diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(neon_sqdmulh_idx_h)(void *vd, void *vn, void *vm, intptr_t i, j, opr_sz = simd_oprsz(desc); int idx = simd_data(desc); int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx); + intptr_t elements = opr_sz / 2; + intptr_t eltspersegment = MIN(16 / 2, elements); - for (i = 0; i < opr_sz / 2; i += 16 / 2) { + for (i = 0; i < elements; i += 16 / 2) { int16_t mm = m[i]; - for (j = 0; j < 16 / 2; ++j) { + for (j = 0; j < eltspersegment; ++j) { d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, false, vq); } } @@ -XXX,XX +XXX,XX @@ void HELPER(neon_sqrdmulh_idx_h)(void *vd, void *vn, void *vm, intptr_t i, j, opr_sz = simd_oprsz(desc); int idx = simd_data(desc); int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx); + intptr_t elements = opr_sz / 2; + intptr_t eltspersegment = MIN(16 / 2, elements); - for (i = 0; i < opr_sz / 2; i += 16 / 2) { + for (i = 0; i < elements; i += 16 / 2) { int16_t mm = m[i]; - for (j = 0; j < 16 / 2; ++j) { + for (j = 0; j < eltspersegment; ++j) { d[i + j] = do_sqrdmlah_h(n[i + j], mm, 0, false, true, vq); } } @@ -XXX,XX +XXX,XX @@ void HELPER(neon_sqdmulh_idx_s)(void *vd, void *vn, void *vm, intptr_t i, j, opr_sz = simd_oprsz(desc); int idx = simd_data(desc); int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx); + intptr_t elements = opr_sz / 4; + intptr_t eltspersegment = MIN(16 / 4, elements); - for (i = 0; i < opr_sz / 4; i += 16 / 4) { + for (i = 0; i < elements; i += 16 / 4) { int32_t mm = m[i]; - for (j = 0; j < 16 / 4; ++j) { + for (j = 0; j < eltspersegment; ++j) { d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, false, vq); } } @@ -XXX,XX +XXX,XX @@ void HELPER(neon_sqrdmulh_idx_s)(void *vd, void *vn, void *vm, intptr_t i, j, opr_sz = simd_oprsz(desc); int idx = simd_data(desc); int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx); + intptr_t elements = opr_sz / 4; + intptr_t eltspersegment = MIN(16 / 4, elements); - for (i = 0; i < opr_sz / 4; i += 16 / 4) { + for (i = 0; i < elements; i += 16 / 4) { int32_t mm = m[i]; - for (j = 0; j < 16 / 4; ++j) { + for (j = 0; j < eltspersegment; ++j) { d[i + j] = do_sqrdmlah_s(n[i + j], mm, 0, false, true, vq); } } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Input denormals cause the Javascript inexact bit (output to Z) to be set. Cc: qemu-stable@nongnu.org Fixes: 6c1f6f2733a ("target/arm: Implement ARMv8.3-JSConv") Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2375 Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240625183536.1672454-4-richard.henderson@linaro.org [PMM: fixed hardcoded tab in test case] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/vfp_helper.c | 18 +++++++++--------- tests/tcg/aarch64/test-2375.c | 21 +++++++++++++++++++++ tests/tcg/aarch64/Makefile.target | 3 ++- 3 files changed, 32 insertions(+), 10 deletions(-) create mode 100644 tests/tcg/aarch64/test-2375.c diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ const FloatRoundMode arm_rmode_to_sf_map[] = { uint64_t HELPER(fjcvtzs)(float64 value, void *vstatus) { float_status *status = vstatus; - uint32_t inexact, frac; - uint32_t e_old, e_new; + uint32_t frac, e_old, e_new; + bool inexact; e_old = get_float_exception_flags(status); set_float_exception_flags(0, status); @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(fjcvtzs)(float64 value, void *vstatus) e_new = get_float_exception_flags(status); set_float_exception_flags(e_old | e_new, status); - if (value == float64_chs(float64_zero)) { - /* While not inexact for IEEE FP, -0.0 is inexact for JavaScript. */ - inexact = 1; - } else { - /* Normal inexact or overflow or NaN */ - inexact = e_new & (float_flag_inexact | float_flag_invalid); - } + /* Normal inexact, denormal with flush-to-zero, or overflow or NaN */ + inexact = e_new & (float_flag_inexact | + float_flag_input_denormal | + float_flag_invalid); + + /* While not inexact for IEEE FP, -0.0 is inexact for JavaScript. */ + inexact |= value == float64_chs(float64_zero); /* Pack the result and the env->ZF representation of Z together. */ return deposit64(frac, 32, 32, inexact); diff --git a/tests/tcg/aarch64/test-2375.c b/tests/tcg/aarch64/test-2375.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/tcg/aarch64/test-2375.c @@ -XXX,XX +XXX,XX @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (c) 2024 Linaro Ltd */ +/* See https://gitlab.com/qemu-project/qemu/-/issues/2375 */ + +#include <assert.h> + +int main(void) +{ + int r, z; + + asm("msr fpcr, %2\n\t" + "fjcvtzs %w0, %d3\n\t" + "cset %1, eq" + : "=r"(r), "=r"(z) + : "r"(0x01000000L), /* FZ = 1 */ + "w"(0xfcff00L)); /* denormal */ + + assert(r == 0); + assert(z == 0); + return 0; +} diff --git a/tests/tcg/aarch64/Makefile.target b/tests/tcg/aarch64/Makefile.target index XXXXXXX..XXXXXXX 100644 --- a/tests/tcg/aarch64/Makefile.target +++ b/tests/tcg/aarch64/Makefile.target @@ -XXX,XX +XXX,XX @@ endif # Pauth Tests ifneq ($(CROSS_CC_HAS_ARMV8_3),) -AARCH64_TESTS += pauth-1 pauth-2 pauth-4 pauth-5 +AARCH64_TESTS += pauth-1 pauth-2 pauth-4 pauth-5 test-2375 pauth-%: CFLAGS += -march=armv8.3-a +test-2375: CFLAGS += -march=armv8.3-a run-pauth-1: QEMU_OPTS += -cpu max run-pauth-2: QEMU_OPTS += -cpu max # Choose a cpu with FEAT_Pauth but without FEAT_FPAC for pauth-[45]. -- 2.34.1 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: 20240625183536.1672454-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/helper.h | 10 ++ target/arm/tcg/a64.decode | 16 +++ target/arm/tcg/translate-a64.c | 206 +++++++++++++-------------------- target/arm/tcg/vec_helper.c | 72 ++++++++++++ 4 files changed, 180 insertions(+), 124 deletions(-) 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_5(neon_sqrdmulh_idx_h, TCG_CALL_NO_RWG, DEF_HELPER_FLAGS_5(neon_sqrdmulh_idx_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqrdmlah_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqrdmlah_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + +DEF_HELPER_FLAGS_5(neon_sqrdmlsh_idx_h, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) +DEF_HELPER_FLAGS_5(neon_sqrdmlsh_idx_s, TCG_CALL_NO_RWG, + void, ptr, ptr, ptr, ptr, i32) + DEF_HELPER_FLAGS_4(sve2_sqdmulh_b, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqdmulh_h, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) DEF_HELPER_FLAGS_4(sve2_sqdmulh_s, TCG_CALL_NO_RWG, void, ptr, ptr, ptr, i32) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ CMEQ_s 0111 1110 111 ..... 10001 1 ..... ..... @rrr_d SQDMULH_s 0101 1110 ..1 ..... 10110 1 ..... ..... @rrr_e SQRDMULH_s 0111 1110 ..1 ..... 10110 1 ..... ..... @rrr_e +SQRDMLAH_s 0111 1110 ..0 ..... 10000 1 ..... ..... @rrr_e +SQRDMLSH_s 0111 1110 ..0 ..... 10001 1 ..... ..... @rrr_e ### Advanced SIMD scalar pairwise @@ -XXX,XX +XXX,XX @@ MLS_v 0.10 1110 ..1 ..... 10010 1 ..... ..... @qrrr_e SQDMULH_v 0.00 1110 ..1 ..... 10110 1 ..... ..... @qrrr_e SQRDMULH_v 0.10 1110 ..1 ..... 10110 1 ..... ..... @qrrr_e +SQRDMLAH_v 0.10 1110 ..0 ..... 10000 1 ..... ..... @qrrr_e +SQRDMLSH_v 0.10 1110 ..0 ..... 10001 1 ..... ..... @qrrr_e ### Advanced SIMD scalar x indexed element @@ -XXX,XX +XXX,XX @@ SQDMULH_si 0101 1111 10 .. .... 1100 . 0 ..... ..... @rrx_s SQRDMULH_si 0101 1111 01 .. .... 1101 . 0 ..... ..... @rrx_h SQRDMULH_si 0101 1111 10 . ..... 1101 . 0 ..... ..... @rrx_s +SQRDMLAH_si 0111 1111 01 .. .... 1101 . 0 ..... ..... @rrx_h +SQRDMLAH_si 0111 1111 10 .. .... 1101 . 0 ..... ..... @rrx_s + +SQRDMLSH_si 0111 1111 01 .. .... 1111 . 0 ..... ..... @rrx_h +SQRDMLSH_si 0111 1111 10 .. .... 1111 . 0 ..... ..... @rrx_s + ### Advanced SIMD vector x indexed element FMUL_vi 0.00 1111 00 .. .... 1001 . 0 ..... ..... @qrrx_h @@ -XXX,XX +XXX,XX @@ SQDMULH_vi 0.00 1111 10 . ..... 1100 . 0 ..... ..... @qrrx_s SQRDMULH_vi 0.00 1111 01 .. .... 1101 . 0 ..... ..... @qrrx_h SQRDMULH_vi 0.00 1111 10 . ..... 1101 . 0 ..... ..... @qrrx_s +SQRDMLAH_vi 0.10 1111 01 .. .... 1101 . 0 ..... ..... @qrrx_h +SQRDMLAH_vi 0.10 1111 10 .. .... 1101 . 0 ..... ..... @qrrx_s + +SQRDMLSH_vi 0.10 1111 01 .. .... 1111 . 0 ..... ..... @qrrx_h +SQRDMLSH_vi 0.10 1111 10 .. .... 1111 . 0 ..... ..... @qrrx_s + # Floating-point conditional select FCSEL 0001 1110 .. 1 rm:5 cond:4 11 rn:5 rd:5 esz=%esz_hsd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static const ENVScalar2 f_scalar_sqrdmulh = { }; TRANS(SQRDMULH_s, do_env_scalar2_hs, a, &f_scalar_sqrdmulh) +typedef struct ENVScalar3 { + NeonGenThreeOpEnvFn *gen_hs[2]; +} ENVScalar3; + +static bool do_env_scalar3_hs(DisasContext *s, arg_rrr_e *a, + const ENVScalar3 *f) +{ + TCGv_i32 t0, t1, t2; + + if (a->esz != MO_16 && a->esz != MO_32) { + return false; + } + if (!fp_access_check(s)) { + return true; + } + + t0 = tcg_temp_new_i32(); + t1 = tcg_temp_new_i32(); + t2 = tcg_temp_new_i32(); + read_vec_element_i32(s, t0, a->rn, 0, a->esz); + read_vec_element_i32(s, t1, a->rm, 0, a->esz); + read_vec_element_i32(s, t2, a->rd, 0, a->esz); + f->gen_hs[a->esz - 1](t0, tcg_env, t0, t1, t2); + write_fp_sreg(s, a->rd, t0); + return true; +} + +static const ENVScalar3 f_scalar_sqrdmlah = { + { gen_helper_neon_qrdmlah_s16, gen_helper_neon_qrdmlah_s32 } +}; +TRANS_FEAT(SQRDMLAH_s, aa64_rdm, do_env_scalar3_hs, a, &f_scalar_sqrdmlah) + +static const ENVScalar3 f_scalar_sqrdmlsh = { + { gen_helper_neon_qrdmlsh_s16, gen_helper_neon_qrdmlsh_s32 } +}; +TRANS_FEAT(SQRDMLSH_s, aa64_rdm, do_env_scalar3_hs, a, &f_scalar_sqrdmlsh) + static bool do_cmop_d(DisasContext *s, arg_rrr_e *a, TCGCond cond) { if (fp_access_check(s)) { @@ -XXX,XX +XXX,XX @@ TRANS(CMTST_v, do_gvec_fn3, a, gen_gvec_cmtst) TRANS(SQDMULH_v, do_gvec_fn3_no8_no64, a, gen_gvec_sqdmulh_qc) TRANS(SQRDMULH_v, do_gvec_fn3_no8_no64, a, gen_gvec_sqrdmulh_qc) +TRANS_FEAT(SQRDMLAH_v, aa64_rdm, do_gvec_fn3_no8_no64, a, gen_gvec_sqrdmlah_qc) +TRANS_FEAT(SQRDMLSH_v, aa64_rdm, do_gvec_fn3_no8_no64, a, gen_gvec_sqrdmlsh_qc) /* * Advanced SIMD scalar/vector x indexed element @@ -XXX,XX +XXX,XX @@ static bool do_env_scalar2_idx_hs(DisasContext *s, arg_rrx_e *a, TRANS(SQDMULH_si, do_env_scalar2_idx_hs, a, &f_scalar_sqdmulh) TRANS(SQRDMULH_si, do_env_scalar2_idx_hs, a, &f_scalar_sqrdmulh) +static bool do_env_scalar3_idx_hs(DisasContext *s, arg_rrx_e *a, + const ENVScalar3 *f) +{ + if (a->esz < MO_16 || a->esz > MO_32) { + return false; + } + if (fp_access_check(s)) { + TCGv_i32 t0 = tcg_temp_new_i32(); + TCGv_i32 t1 = tcg_temp_new_i32(); + TCGv_i32 t2 = tcg_temp_new_i32(); + + read_vec_element_i32(s, t0, a->rn, 0, a->esz); + read_vec_element_i32(s, t1, a->rm, a->idx, a->esz); + read_vec_element_i32(s, t2, a->rd, 0, a->esz); + f->gen_hs[a->esz - 1](t0, tcg_env, t0, t1, t2); + write_fp_sreg(s, a->rd, t0); + } + return true; +} + +TRANS_FEAT(SQRDMLAH_si, aa64_rdm, do_env_scalar3_idx_hs, a, &f_scalar_sqrdmlah) +TRANS_FEAT(SQRDMLSH_si, aa64_rdm, do_env_scalar3_idx_hs, a, &f_scalar_sqrdmlsh) + static bool do_fp3_vector_idx(DisasContext *s, arg_qrrx_e *a, gen_helper_gvec_3_ptr * const fns[3]) { @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_4 * const f_vector_idx_sqrdmulh[2] = { }; TRANS(SQRDMULH_vi, do_int3_qc_vector_idx, a, f_vector_idx_sqrdmulh) +static gen_helper_gvec_4 * const f_vector_idx_sqrdmlah[2] = { + gen_helper_neon_sqrdmlah_idx_h, + gen_helper_neon_sqrdmlah_idx_s, +}; +TRANS_FEAT(SQRDMLAH_vi, aa64_rdm, do_int3_qc_vector_idx, a, + f_vector_idx_sqrdmlah) + +static gen_helper_gvec_4 * const f_vector_idx_sqrdmlsh[2] = { + gen_helper_neon_sqrdmlsh_idx_h, + gen_helper_neon_sqrdmlsh_idx_s, +}; +TRANS_FEAT(SQRDMLSH_vi, aa64_rdm, do_int3_qc_vector_idx, a, + f_vector_idx_sqrdmlsh) + /* * Advanced SIMD scalar pairwise */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_scalar_three_reg_diff(DisasContext *s, uint32_t insn) } } -/* AdvSIMD scalar three same extra - * 31 30 29 28 24 23 22 21 20 16 15 14 11 10 9 5 4 0 - * +-----+---+-----------+------+---+------+---+--------+---+----+----+ - * | 0 1 | U | 1 1 1 1 0 | size | 0 | Rm | 1 | opcode | 1 | Rn | Rd | - * +-----+---+-----------+------+---+------+---+--------+---+----+----+ - */ -static void disas_simd_scalar_three_reg_same_extra(DisasContext *s, - uint32_t insn) -{ - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int opcode = extract32(insn, 11, 4); - int rm = extract32(insn, 16, 5); - int size = extract32(insn, 22, 2); - bool u = extract32(insn, 29, 1); - TCGv_i32 ele1, ele2, ele3; - TCGv_i64 res; - bool feature; - - switch (u * 16 + opcode) { - case 0x10: /* SQRDMLAH (vector) */ - case 0x11: /* SQRDMLSH (vector) */ - if (size != 1 && size != 2) { - unallocated_encoding(s); - return; - } - feature = dc_isar_feature(aa64_rdm, s); - break; - default: - unallocated_encoding(s); - return; - } - if (!feature) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - - /* Do a single operation on the lowest element in the vector. - * We use the standard Neon helpers and rely on 0 OP 0 == 0 - * with no side effects for all these operations. - * OPTME: special-purpose helpers would avoid doing some - * unnecessary work in the helper for the 16 bit cases. - */ - ele1 = tcg_temp_new_i32(); - ele2 = tcg_temp_new_i32(); - ele3 = tcg_temp_new_i32(); - - read_vec_element_i32(s, ele1, rn, 0, size); - read_vec_element_i32(s, ele2, rm, 0, size); - read_vec_element_i32(s, ele3, rd, 0, size); - - switch (opcode) { - case 0x0: /* SQRDMLAH */ - if (size == 1) { - gen_helper_neon_qrdmlah_s16(ele3, tcg_env, ele1, ele2, ele3); - } else { - gen_helper_neon_qrdmlah_s32(ele3, tcg_env, ele1, ele2, ele3); - } - break; - case 0x1: /* SQRDMLSH */ - if (size == 1) { - gen_helper_neon_qrdmlsh_s16(ele3, tcg_env, ele1, ele2, ele3); - } else { - gen_helper_neon_qrdmlsh_s32(ele3, tcg_env, ele1, ele2, ele3); - } - break; - default: - g_assert_not_reached(); - } - - res = tcg_temp_new_i64(); - tcg_gen_extu_i32_i64(res, ele3); - write_fp_dreg(s, rd, res); -} - static void handle_2misc_64(DisasContext *s, int opcode, bool u, TCGv_i64 tcg_rd, TCGv_i64 tcg_rn, TCGv_i32 tcg_rmode, TCGv_ptr tcg_fpstatus) @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) int rot; switch (u * 16 + opcode) { - case 0x10: /* SQRDMLAH (vector) */ - case 0x11: /* SQRDMLSH (vector) */ - if (size != 1 && size != 2) { - unallocated_encoding(s); - return; - } - feature = dc_isar_feature(aa64_rdm, s); - break; case 0x02: /* SDOT (vector) */ case 0x12: /* UDOT (vector) */ if (size != MO_32) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } break; default: + case 0x10: /* SQRDMLAH (vector) */ + case 0x11: /* SQRDMLSH (vector) */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x0: /* SQRDMLAH (vector) */ - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqrdmlah_qc, size); - return; - - case 0x1: /* SQRDMLSH (vector) */ - gen_gvec_fn3(s, is_q, rd, rn, rm, gen_gvec_sqrdmlsh_qc, size); - return; - case 0x2: /* SDOT / UDOT */ gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b); @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x0b: /* SQDMULL, SQDMULL2 */ is_long = true; break; - case 0x1d: /* SQRDMLAH */ - case 0x1f: /* SQRDMLSH */ - if (!dc_isar_feature(aa64_rdm, s)) { - unallocated_encoding(s); - return; - } - break; case 0x0e: /* SDOT */ case 0x1e: /* UDOT */ if (is_scalar || size != MO_32 || !dc_isar_feature(aa64_dp, s)) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x18: /* FMLAL2 */ case 0x19: /* FMULX */ case 0x1c: /* FMLSL2 */ + case 0x1d: /* SQRDMLAH */ + case 0x1f: /* SQRDMLSH */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) tcg_op, tcg_idx); } break; - case 0x1d: /* SQRDMLAH */ - read_vec_element_i32(s, tcg_res, rd, pass, - is_scalar ? size : MO_32); - if (size == 1) { - gen_helper_neon_qrdmlah_s16(tcg_res, tcg_env, - tcg_op, tcg_idx, tcg_res); - } else { - gen_helper_neon_qrdmlah_s32(tcg_res, tcg_env, - tcg_op, tcg_idx, tcg_res); - } - break; - case 0x1f: /* SQRDMLSH */ - read_vec_element_i32(s, tcg_res, rd, pass, - is_scalar ? size : MO_32); - if (size == 1) { - gen_helper_neon_qrdmlsh_s16(tcg_res, tcg_env, - tcg_op, tcg_idx, tcg_res); - } else { - gen_helper_neon_qrdmlsh_s32(tcg_res, tcg_env, - tcg_op, tcg_idx, tcg_res); - } - break; default: case 0x01: /* FMLA */ case 0x05: /* FMLS */ case 0x09: /* FMUL */ case 0x19: /* FMULX */ + case 0x1d: /* SQRDMLAH */ + case 0x1f: /* SQRDMLSH */ g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static const AArch64DecodeTable data_proc_simd[] = { { 0x0e000000, 0xbf208c00, disas_simd_tb }, { 0x0e000800, 0xbf208c00, disas_simd_zip_trn }, { 0x2e000000, 0xbf208400, disas_simd_ext }, - { 0x5e008400, 0xdf208400, disas_simd_scalar_three_reg_same_extra }, { 0x5e200000, 0xdf200c00, disas_simd_scalar_three_reg_diff }, { 0x5e200800, 0xdf3e0c00, disas_simd_scalar_two_reg_misc }, { 0x5f000000, 0xdf000400, disas_simd_indexed }, /* scalar indexed */ diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(neon_sqrdmulh_idx_h)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } +void HELPER(neon_sqrdmlah_idx_h)(void *vd, void *vn, void *vm, + void *vq, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx); + intptr_t elements = opr_sz / 2; + intptr_t eltspersegment = MIN(16 / 2, elements); + + for (i = 0; i < elements; i += 16 / 2) { + int16_t mm = m[i]; + for (j = 0; j < eltspersegment; ++j) { + d[i + j] = do_sqrdmlah_h(n[i + j], mm, d[i + j], false, true, vq); + } + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(neon_sqrdmlsh_idx_h)(void *vd, void *vn, void *vm, + void *vq, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int16_t *d = vd, *n = vn, *m = (int16_t *)vm + H2(idx); + intptr_t elements = opr_sz / 2; + intptr_t eltspersegment = MIN(16 / 2, elements); + + for (i = 0; i < elements; i += 16 / 2) { + int16_t mm = m[i]; + for (j = 0; j < eltspersegment; ++j) { + d[i + j] = do_sqrdmlah_h(n[i + j], mm, d[i + j], true, true, vq); + } + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + void HELPER(sve2_sqrdmlah_h)(void *vd, void *vn, void *vm, void *va, uint32_t desc) { @@ -XXX,XX +XXX,XX @@ void HELPER(neon_sqrdmulh_idx_s)(void *vd, void *vn, void *vm, clear_tail(d, opr_sz, simd_maxsz(desc)); } +void HELPER(neon_sqrdmlah_idx_s)(void *vd, void *vn, void *vm, + void *vq, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx); + intptr_t elements = opr_sz / 4; + intptr_t eltspersegment = MIN(16 / 4, elements); + + for (i = 0; i < elements; i += 16 / 4) { + int32_t mm = m[i]; + for (j = 0; j < eltspersegment; ++j) { + d[i + j] = do_sqrdmlah_s(n[i + j], mm, d[i + j], false, true, vq); + } + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + +void HELPER(neon_sqrdmlsh_idx_s)(void *vd, void *vn, void *vm, + void *vq, uint32_t desc) +{ + intptr_t i, j, opr_sz = simd_oprsz(desc); + int idx = simd_data(desc); + int32_t *d = vd, *n = vn, *m = (int32_t *)vm + H4(idx); + intptr_t elements = opr_sz / 4; + intptr_t eltspersegment = MIN(16 / 4, elements); + + for (i = 0; i < elements; i += 16 / 4) { + int32_t mm = m[i]; + for (j = 0; j < eltspersegment; ++j) { + d[i + j] = do_sqrdmlah_s(n[i + j], mm, d[i + j], true, true, vq); + } + } + clear_tail(d, opr_sz, simd_maxsz(desc)); +} + void HELPER(sve2_sqrdmlah_s)(void *vd, void *vn, void *vm, void *va, uint32_t desc) { -- 2.34.1 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: 20240625183536.1672454-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 7 +++++ target/arm/tcg/translate-a64.c | 54 ++++++++++++++++++---------------- 2 files changed, 35 insertions(+), 26 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ @qrrr_b . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=0 @qrrr_h . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=1 +@qrrr_s . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=2 @qrrr_sd . q:1 ...... ... rm:5 ...... rn:5 rd:5 &qrrr_e esz=%esz_sd @qrrr_e . q:1 ...... esz:2 . rm:5 ...... rn:5 rd:5 &qrrr_e @qr2r_e . q:1 ...... esz:2 . ..... ...... rm:5 rd:5 &qrrr_e rn=%rd @@ -XXX,XX +XXX,XX @@ SQRDMULH_v 0.10 1110 ..1 ..... 10110 1 ..... ..... @qrrr_e SQRDMLAH_v 0.10 1110 ..0 ..... 10000 1 ..... ..... @qrrr_e SQRDMLSH_v 0.10 1110 ..0 ..... 10001 1 ..... ..... @qrrr_e +SDOT_v 0.00 1110 100 ..... 10010 1 ..... ..... @qrrr_s +UDOT_v 0.10 1110 100 ..... 10010 1 ..... ..... @qrrr_s + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h @@ -XXX,XX +XXX,XX @@ SQRDMLAH_vi 0.10 1111 10 .. .... 1101 . 0 ..... ..... @qrrx_s SQRDMLSH_vi 0.10 1111 01 .. .... 1111 . 0 ..... ..... @qrrx_h SQRDMLSH_vi 0.10 1111 10 .. .... 1111 . 0 ..... ..... @qrrx_s +SDOT_vi 0.00 1111 10 .. .... 1110 . 0 ..... ..... @qrrx_s +UDOT_vi 0.10 1111 10 .. .... 1110 . 0 ..... ..... @qrrx_s + # Floating-point conditional select FCSEL 0001 1110 .. 1 rm:5 cond:4 11 rn:5 rd:5 esz=%esz_hsd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS(SQRDMULH_v, do_gvec_fn3_no8_no64, a, gen_gvec_sqrdmulh_qc) TRANS_FEAT(SQRDMLAH_v, aa64_rdm, do_gvec_fn3_no8_no64, a, gen_gvec_sqrdmlah_qc) TRANS_FEAT(SQRDMLSH_v, aa64_rdm, do_gvec_fn3_no8_no64, a, gen_gvec_sqrdmlsh_qc) +static bool do_dot_vector(DisasContext *s, arg_qrrr_e *a, + gen_helper_gvec_4 *fn) +{ + if (fp_access_check(s)) { + gen_gvec_op4_ool(s, a->q, a->rd, a->rn, a->rm, a->rd, 0, fn); + } + return true; +} + +TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_b) +TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_b) + /* * Advanced SIMD scalar/vector x indexed element */ @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_4 * const f_vector_idx_sqrdmlsh[2] = { TRANS_FEAT(SQRDMLSH_vi, aa64_rdm, do_int3_qc_vector_idx, a, f_vector_idx_sqrdmlsh) +static bool do_dot_vector_idx(DisasContext *s, arg_qrrx_e *a, + gen_helper_gvec_4 *fn) +{ + if (fp_access_check(s)) { + gen_gvec_op4_ool(s, a->q, a->rd, a->rn, a->rm, a->rd, a->idx, fn); + } + return true; +} + +TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_b) +TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_b) + /* * Advanced SIMD scalar pairwise */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) int rot; switch (u * 16 + opcode) { - case 0x02: /* SDOT (vector) */ - case 0x12: /* UDOT (vector) */ - if (size != MO_32) { - unallocated_encoding(s); - return; - } - feature = dc_isar_feature(aa64_dp, s); - break; case 0x03: /* USDOT */ if (size != MO_32) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } break; default: + case 0x02: /* SDOT (vector) */ case 0x10: /* SQRDMLAH (vector) */ case 0x11: /* SQRDMLSH (vector) */ + case 0x12: /* UDOT (vector) */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x2: /* SDOT / UDOT */ - gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, - u ? gen_helper_gvec_udot_b : gen_helper_gvec_sdot_b); - return; - case 0x3: /* USDOT */ gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_usdot_b); return; @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x0b: /* SQDMULL, SQDMULL2 */ is_long = true; break; - case 0x0e: /* SDOT */ - case 0x1e: /* UDOT */ - if (is_scalar || size != MO_32 || !dc_isar_feature(aa64_dp, s)) { - unallocated_encoding(s); - return; - } - break; case 0x0f: switch (size) { case 0: /* SUDOT */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x09: /* FMUL */ case 0x0c: /* SQDMULH */ case 0x0d: /* SQRDMULH */ + case 0x0e: /* SDOT */ case 0x10: /* MLA */ case 0x14: /* MLS */ case 0x18: /* FMLAL2 */ case 0x19: /* FMULX */ case 0x1c: /* FMLSL2 */ case 0x1d: /* SQRDMLAH */ + case 0x1e: /* UDOT */ case 0x1f: /* SQRDMLSH */ unallocated_encoding(s); return; @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } switch (16 * u + opcode) { - case 0x0e: /* SDOT */ - case 0x1e: /* UDOT */ - gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index, - u ? gen_helper_gvec_udot_idx_b - : gen_helper_gvec_sdot_idx_b); - return; case 0x0f: switch (extract32(insn, 22, 2)) { case 0: /* SUDOT */ -- 2.34.1 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: 20240625183536.1672454-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 3 +++ target/arm/tcg/translate-a64.c | 35 ++++++++-------------------------- 2 files changed, 11 insertions(+), 27 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ SQRDMLSH_v 0.10 1110 ..0 ..... 10001 1 ..... ..... @qrrr_e SDOT_v 0.00 1110 100 ..... 10010 1 ..... ..... @qrrr_s UDOT_v 0.10 1110 100 ..... 10010 1 ..... ..... @qrrr_s +USDOT_v 0.00 1110 100 ..... 10011 1 ..... ..... @qrrr_s ### Advanced SIMD scalar x indexed element @@ -XXX,XX +XXX,XX @@ SQRDMLSH_vi 0.10 1111 10 .. .... 1111 . 0 ..... ..... @qrrx_s SDOT_vi 0.00 1111 10 .. .... 1110 . 0 ..... ..... @qrrx_s UDOT_vi 0.10 1111 10 .. .... 1110 . 0 ..... ..... @qrrx_s +SUDOT_vi 0.00 1111 00 .. .... 1111 . 0 ..... ..... @qrrx_s +USDOT_vi 0.00 1111 10 .. .... 1111 . 0 ..... ..... @qrrx_s # Floating-point conditional select diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool do_dot_vector(DisasContext *s, arg_qrrr_e *a, TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_b) TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_b) +TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_b) /* * Advanced SIMD scalar/vector x indexed element @@ -XXX,XX +XXX,XX @@ static bool do_dot_vector_idx(DisasContext *s, arg_qrrx_e *a, TRANS_FEAT(SDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_sdot_idx_b) TRANS_FEAT(UDOT_vi, aa64_dp, do_dot_vector_idx, a, gen_helper_gvec_udot_idx_b) +TRANS_FEAT(SUDOT_vi, aa64_i8mm, do_dot_vector_idx, a, + gen_helper_gvec_sudot_idx_b) +TRANS_FEAT(USDOT_vi, aa64_i8mm, do_dot_vector_idx, a, + gen_helper_gvec_usdot_idx_b) /* * Advanced SIMD scalar pairwise @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) int rot; switch (u * 16 + opcode) { - case 0x03: /* USDOT */ - if (size != MO_32) { - unallocated_encoding(s); - return; - } - feature = dc_isar_feature(aa64_i8mm, s); - break; case 0x04: /* SMMLA */ case 0x14: /* UMMLA */ case 0x05: /* USMMLA */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) break; default: case 0x02: /* SDOT (vector) */ + case 0x03: /* USDOT */ case 0x10: /* SQRDMLAH (vector) */ case 0x11: /* SQRDMLSH (vector) */ case 0x12: /* UDOT (vector) */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x3: /* USDOT */ - gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_usdot_b); - return; - case 0x04: /* SMMLA, UMMLA */ gen_gvec_op4_ool(s, 1, rd, rn, rm, rd, 0, u ? gen_helper_gvec_ummla_b @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) break; case 0x0f: switch (size) { - case 0: /* SUDOT */ - case 2: /* USDOT */ - if (is_scalar || !dc_isar_feature(aa64_i8mm, s)) { - unallocated_encoding(s); - return; - } - size = MO_32; - break; case 1: /* BFDOT */ if (is_scalar || !dc_isar_feature(aa64_bf16, s)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) size = MO_16; break; default: + case 0: /* SUDOT */ + case 2: /* USDOT */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) switch (16 * u + opcode) { case 0x0f: switch (extract32(insn, 22, 2)) { - case 0: /* SUDOT */ - gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index, - gen_helper_gvec_sudot_idx_b); - return; case 1: /* BFDOT */ gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index, gen_helper_gvec_bfdot_idx); return; - case 2: /* USDOT */ - gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index, - gen_helper_gvec_usdot_idx_b); - return; case 3: /* BFMLAL{B,T} */ gen_gvec_op4_fpst(s, 1, rd, rn, rm, rd, 0, (index << 1) | is_q, gen_helper_gvec_bfmlal_idx); -- 2.34.1 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: 20240625183536.1672454-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 2 ++ target/arm/tcg/translate-a64.c | 20 +++++--------------- 2 files changed, 7 insertions(+), 15 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ SQRDMLSH_v 0.10 1110 ..0 ..... 10001 1 ..... ..... @qrrr_e SDOT_v 0.00 1110 100 ..... 10010 1 ..... ..... @qrrr_s UDOT_v 0.10 1110 100 ..... 10010 1 ..... ..... @qrrr_s USDOT_v 0.00 1110 100 ..... 10011 1 ..... ..... @qrrr_s +BFDOT_v 0.10 1110 010 ..... 11111 1 ..... ..... @qrrr_s ### Advanced SIMD scalar x indexed element @@ -XXX,XX +XXX,XX @@ SDOT_vi 0.00 1111 10 .. .... 1110 . 0 ..... ..... @qrrx_s UDOT_vi 0.10 1111 10 .. .... 1110 . 0 ..... ..... @qrrx_s SUDOT_vi 0.00 1111 00 .. .... 1111 . 0 ..... ..... @qrrx_s USDOT_vi 0.00 1111 10 .. .... 1111 . 0 ..... ..... @qrrx_s +BFDOT_vi 0.00 1111 01 .. .... 1111 . 0 ..... ..... @qrrx_s # Floating-point conditional select diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool do_dot_vector(DisasContext *s, arg_qrrr_e *a, TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_b) TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_b) TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_b) +TRANS_FEAT(BFDOT_v, aa64_bf16, do_dot_vector, a, gen_helper_gvec_bfdot) /* * Advanced SIMD scalar/vector x indexed element @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SUDOT_vi, aa64_i8mm, do_dot_vector_idx, a, gen_helper_gvec_sudot_idx_b) TRANS_FEAT(USDOT_vi, aa64_i8mm, do_dot_vector_idx, a, gen_helper_gvec_usdot_idx_b) +TRANS_FEAT(BFDOT_vi, aa64_bf16, do_dot_vector_idx, a, + gen_helper_gvec_bfdot_idx) /* * Advanced SIMD scalar pairwise @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) break; case 0x1f: switch (size) { - case 1: /* BFDOT */ case 3: /* BFMLAL{B,T} */ feature = dc_isar_feature(aa64_bf16, s); break; default: + case 1: /* BFDOT */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) return; case 0xf: switch (size) { - case 1: /* BFDOT */ - gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_bfdot); - break; case 3: /* BFMLAL{B,T} */ gen_gvec_op4_fpst(s, 1, rd, rn, rm, rd, false, is_q, gen_helper_gvec_bfmlal); @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) break; case 0x0f: switch (size) { - case 1: /* BFDOT */ - if (is_scalar || !dc_isar_feature(aa64_bf16, s)) { - unallocated_encoding(s); - return; - } - size = MO_32; - break; case 3: /* BFMLAL{B,T} */ if (is_scalar || !dc_isar_feature(aa64_bf16, s)) { unallocated_encoding(s); @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) break; default: case 0: /* SUDOT */ + case 1: /* BFDOT */ case 2: /* USDOT */ unallocated_encoding(s); return; @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) switch (16 * u + opcode) { case 0x0f: switch (extract32(insn, 22, 2)) { - case 1: /* BFDOT */ - gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, index, - gen_helper_gvec_bfdot_idx); - return; case 3: /* BFMLAL{B,T} */ gen_gvec_op4_fpst(s, 1, rd, rn, rm, rd, 0, (index << 1) | is_q, gen_helper_gvec_bfmlal_idx); -- 2.34.1 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: 20240625183536.1672454-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 2 + target/arm/tcg/translate-a64.c | 77 +++++++++++++--------------------- 2 files changed, 31 insertions(+), 48 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ SDOT_v 0.00 1110 100 ..... 10010 1 ..... ..... @qrrr_s UDOT_v 0.10 1110 100 ..... 10010 1 ..... ..... @qrrr_s USDOT_v 0.00 1110 100 ..... 10011 1 ..... ..... @qrrr_s BFDOT_v 0.10 1110 010 ..... 11111 1 ..... ..... @qrrr_s +BFMLAL_v 0.10 1110 110 ..... 11111 1 ..... ..... @qrrr_h ### Advanced SIMD scalar x indexed element @@ -XXX,XX +XXX,XX @@ UDOT_vi 0.10 1111 10 .. .... 1110 . 0 ..... ..... @qrrx_s SUDOT_vi 0.00 1111 00 .. .... 1111 . 0 ..... ..... @qrrx_s USDOT_vi 0.00 1111 10 .. .... 1111 . 0 ..... ..... @qrrx_s BFDOT_vi 0.00 1111 01 .. .... 1111 . 0 ..... ..... @qrrx_s +BFMLAL_vi 0.00 1111 11 .. .... 1111 . 0 ..... ..... @qrrx_h # Floating-point conditional select diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_b) TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_b) TRANS_FEAT(BFDOT_v, aa64_bf16, do_dot_vector, a, gen_helper_gvec_bfdot) +static bool trans_BFMLAL_v(DisasContext *s, arg_qrrr_e *a) +{ + if (!dc_isar_feature(aa64_bf16, s)) { + return false; + } + if (fp_access_check(s)) { + /* Q bit selects BFMLALB vs BFMLALT. */ + gen_gvec_op4_fpst(s, true, a->rd, a->rn, a->rm, a->rd, false, a->q, + gen_helper_gvec_bfmlal); + } + return true; +} + /* * Advanced SIMD scalar/vector x indexed element */ @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(USDOT_vi, aa64_i8mm, do_dot_vector_idx, a, TRANS_FEAT(BFDOT_vi, aa64_bf16, do_dot_vector_idx, a, gen_helper_gvec_bfdot_idx) +static bool trans_BFMLAL_vi(DisasContext *s, arg_qrrx_e *a) +{ + if (!dc_isar_feature(aa64_bf16, s)) { + return false; + } + if (fp_access_check(s)) { + /* Q bit selects BFMLALB vs BFMLALT. */ + gen_gvec_op4_fpst(s, true, a->rd, a->rn, a->rm, a->rd, 0, + (a->idx << 1) | a->q, + gen_helper_gvec_bfmlal_idx); + } + return true; +} + /* * Advanced SIMD scalar pairwise */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } feature = dc_isar_feature(aa64_bf16, s); break; - case 0x1f: - switch (size) { - case 3: /* BFMLAL{B,T} */ - feature = dc_isar_feature(aa64_bf16, s); - break; - default: - case 1: /* BFDOT */ - unallocated_encoding(s); - return; - } - break; default: case 0x02: /* SDOT (vector) */ case 0x03: /* USDOT */ case 0x10: /* SQRDMLAH (vector) */ case 0x11: /* SQRDMLSH (vector) */ case 0x12: /* UDOT (vector) */ + case 0x1f: /* BFDOT / BFMLAL */ unallocated_encoding(s); return; } @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) case 0xd: /* BFMMLA */ gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_bfmmla); return; - case 0xf: - switch (size) { - case 3: /* BFMLAL{B,T} */ - gen_gvec_op4_fpst(s, 1, rd, rn, rm, rd, false, is_q, - gen_helper_gvec_bfmlal); - break; - default: - g_assert_not_reached(); - } - return; - default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x0b: /* SQDMULL, SQDMULL2 */ is_long = true; break; - case 0x0f: - switch (size) { - case 3: /* BFMLAL{B,T} */ - if (is_scalar || !dc_isar_feature(aa64_bf16, s)) { - unallocated_encoding(s); - return; - } - /* can't set is_fp without other incorrect size checks */ - size = MO_16; - break; - default: - case 0: /* SUDOT */ - case 1: /* BFDOT */ - case 2: /* USDOT */ - unallocated_encoding(s); - return; - } - break; case 0x11: /* FCMLA #0 */ case 0x13: /* FCMLA #90 */ case 0x15: /* FCMLA #180 */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x0c: /* SQDMULH */ case 0x0d: /* SQRDMULH */ case 0x0e: /* SDOT */ + case 0x0f: /* SUDOT / BFDOT / USDOT / BFMLAL */ case 0x10: /* MLA */ case 0x14: /* MLS */ case 0x18: /* FMLAL2 */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) } switch (16 * u + opcode) { - case 0x0f: - switch (extract32(insn, 22, 2)) { - case 3: /* BFMLAL{B,T} */ - gen_gvec_op4_fpst(s, 1, rd, rn, rm, rd, 0, (index << 1) | is_q, - gen_helper_gvec_bfmlal_idx); - return; - } - g_assert_not_reached(); case 0x11: /* FCMLA #0 */ case 0x13: /* FCMLA #90 */ case 0x15: /* FCMLA #180 */ -- 2.34.1 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: 20240625183536.1672454-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 4 ++++ target/arm/tcg/translate-a64.c | 36 ++++++++-------------------------- 2 files changed, 12 insertions(+), 28 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ UDOT_v 0.10 1110 100 ..... 10010 1 ..... ..... @qrrr_s USDOT_v 0.00 1110 100 ..... 10011 1 ..... ..... @qrrr_s BFDOT_v 0.10 1110 010 ..... 11111 1 ..... ..... @qrrr_s BFMLAL_v 0.10 1110 110 ..... 11111 1 ..... ..... @qrrr_h +BFMMLA 0110 1110 010 ..... 11101 1 ..... ..... @rrr_q1e0 +SMMLA 0100 1110 100 ..... 10100 1 ..... ..... @rrr_q1e0 +UMMLA 0110 1110 100 ..... 10100 1 ..... ..... @rrr_q1e0 +USMMLA 0100 1110 100 ..... 10101 1 ..... ..... @rrr_q1e0 ### Advanced SIMD scalar x indexed element diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_sdot_b) TRANS_FEAT(UDOT_v, aa64_dp, do_dot_vector, a, gen_helper_gvec_udot_b) TRANS_FEAT(USDOT_v, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usdot_b) TRANS_FEAT(BFDOT_v, aa64_bf16, do_dot_vector, a, gen_helper_gvec_bfdot) +TRANS_FEAT(BFMMLA, aa64_bf16, do_dot_vector, a, gen_helper_gvec_bfmmla) +TRANS_FEAT(SMMLA, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_smmla_b) +TRANS_FEAT(UMMLA, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_ummla_b) +TRANS_FEAT(USMMLA, aa64_i8mm, do_dot_vector, a, gen_helper_gvec_usmmla_b) static bool trans_BFMLAL_v(DisasContext *s, arg_qrrr_e *a) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) int rot; switch (u * 16 + opcode) { - case 0x04: /* SMMLA */ - case 0x14: /* UMMLA */ - case 0x05: /* USMMLA */ - if (!is_q || size != MO_32) { - unallocated_encoding(s); - return; - } - feature = dc_isar_feature(aa64_i8mm, s); - break; case 0x18: /* FCMLA, #0 */ case 0x19: /* FCMLA, #90 */ case 0x1a: /* FCMLA, #180 */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } feature = dc_isar_feature(aa64_fcma, s); break; - case 0x1d: /* BFMMLA */ - if (size != MO_16 || !is_q) { - unallocated_encoding(s); - return; - } - feature = dc_isar_feature(aa64_bf16, s); - break; default: case 0x02: /* SDOT (vector) */ case 0x03: /* USDOT */ + case 0x04: /* SMMLA */ + case 0x05: /* USMMLA */ case 0x10: /* SQRDMLAH (vector) */ case 0x11: /* SQRDMLSH (vector) */ case 0x12: /* UDOT (vector) */ + case 0x14: /* UMMLA */ + case 0x1d: /* BFMMLA */ case 0x1f: /* BFDOT / BFMLAL */ unallocated_encoding(s); return; @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } switch (opcode) { - case 0x04: /* SMMLA, UMMLA */ - gen_gvec_op4_ool(s, 1, rd, rn, rm, rd, 0, - u ? gen_helper_gvec_ummla_b - : gen_helper_gvec_smmla_b); - return; - case 0x05: /* USMMLA */ - gen_gvec_op4_ool(s, 1, rd, rn, rm, rd, 0, gen_helper_gvec_usmmla_b); - return; - case 0x8: /* FCMLA, #0 */ case 0x9: /* FCMLA, #90 */ case 0xa: /* FCMLA, #180 */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } return; - case 0xd: /* BFMMLA */ - gen_gvec_op4_ool(s, is_q, rd, rn, rm, rd, 0, gen_helper_gvec_bfmmla); - return; default: g_assert_not_reached(); } -- 2.34.1 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: 20240625183536.1672454-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.c | 52 +++++++++++++++++----------------- 1 file changed, 26 insertions(+), 26 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ TRANS(CMHS_s, do_cmop_d, a, TCG_COND_GEU) TRANS(CMEQ_s, do_cmop_d, a, TCG_COND_EQ) TRANS(CMTST_s, do_cmop_d, a, TCG_COND_TSTNE) -static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, +static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, int data, gen_helper_gvec_3_ptr * const fns[3]) { MemOp esz = a->esz; @@ -XXX,XX +XXX,XX @@ static bool do_fp3_vector(DisasContext *s, arg_qrrr_e *a, } if (fp_access_check(s)) { gen_gvec_op3_fpst(s, a->q, a->rd, a->rn, a->rm, - esz == MO_16, 0, fns[esz - 1]); + esz == MO_16, data, fns[esz - 1]); } return true; } @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fadd[3] = { gen_helper_gvec_fadd_s, gen_helper_gvec_fadd_d, }; -TRANS(FADD_v, do_fp3_vector, a, f_vector_fadd) +TRANS(FADD_v, do_fp3_vector, a, 0, f_vector_fadd) static gen_helper_gvec_3_ptr * const f_vector_fsub[3] = { gen_helper_gvec_fsub_h, gen_helper_gvec_fsub_s, gen_helper_gvec_fsub_d, }; -TRANS(FSUB_v, do_fp3_vector, a, f_vector_fsub) +TRANS(FSUB_v, do_fp3_vector, a, 0, f_vector_fsub) static gen_helper_gvec_3_ptr * const f_vector_fdiv[3] = { gen_helper_gvec_fdiv_h, gen_helper_gvec_fdiv_s, gen_helper_gvec_fdiv_d, }; -TRANS(FDIV_v, do_fp3_vector, a, f_vector_fdiv) +TRANS(FDIV_v, do_fp3_vector, a, 0, f_vector_fdiv) static gen_helper_gvec_3_ptr * const f_vector_fmul[3] = { gen_helper_gvec_fmul_h, gen_helper_gvec_fmul_s, gen_helper_gvec_fmul_d, }; -TRANS(FMUL_v, do_fp3_vector, a, f_vector_fmul) +TRANS(FMUL_v, do_fp3_vector, a, 0, f_vector_fmul) static gen_helper_gvec_3_ptr * const f_vector_fmax[3] = { gen_helper_gvec_fmax_h, gen_helper_gvec_fmax_s, gen_helper_gvec_fmax_d, }; -TRANS(FMAX_v, do_fp3_vector, a, f_vector_fmax) +TRANS(FMAX_v, do_fp3_vector, a, 0, f_vector_fmax) static gen_helper_gvec_3_ptr * const f_vector_fmin[3] = { gen_helper_gvec_fmin_h, gen_helper_gvec_fmin_s, gen_helper_gvec_fmin_d, }; -TRANS(FMIN_v, do_fp3_vector, a, f_vector_fmin) +TRANS(FMIN_v, do_fp3_vector, a, 0, f_vector_fmin) static gen_helper_gvec_3_ptr * const f_vector_fmaxnm[3] = { gen_helper_gvec_fmaxnum_h, gen_helper_gvec_fmaxnum_s, gen_helper_gvec_fmaxnum_d, }; -TRANS(FMAXNM_v, do_fp3_vector, a, f_vector_fmaxnm) +TRANS(FMAXNM_v, do_fp3_vector, a, 0, f_vector_fmaxnm) static gen_helper_gvec_3_ptr * const f_vector_fminnm[3] = { gen_helper_gvec_fminnum_h, gen_helper_gvec_fminnum_s, gen_helper_gvec_fminnum_d, }; -TRANS(FMINNM_v, do_fp3_vector, a, f_vector_fminnm) +TRANS(FMINNM_v, do_fp3_vector, a, 0, f_vector_fminnm) static gen_helper_gvec_3_ptr * const f_vector_fmulx[3] = { gen_helper_gvec_fmulx_h, gen_helper_gvec_fmulx_s, gen_helper_gvec_fmulx_d, }; -TRANS(FMULX_v, do_fp3_vector, a, f_vector_fmulx) +TRANS(FMULX_v, do_fp3_vector, a, 0, f_vector_fmulx) static gen_helper_gvec_3_ptr * const f_vector_fmla[3] = { gen_helper_gvec_vfma_h, gen_helper_gvec_vfma_s, gen_helper_gvec_vfma_d, }; -TRANS(FMLA_v, do_fp3_vector, a, f_vector_fmla) +TRANS(FMLA_v, do_fp3_vector, a, 0, f_vector_fmla) static gen_helper_gvec_3_ptr * const f_vector_fmls[3] = { gen_helper_gvec_vfms_h, gen_helper_gvec_vfms_s, gen_helper_gvec_vfms_d, }; -TRANS(FMLS_v, do_fp3_vector, a, f_vector_fmls) +TRANS(FMLS_v, do_fp3_vector, a, 0, f_vector_fmls) static gen_helper_gvec_3_ptr * const f_vector_fcmeq[3] = { gen_helper_gvec_fceq_h, gen_helper_gvec_fceq_s, gen_helper_gvec_fceq_d, }; -TRANS(FCMEQ_v, do_fp3_vector, a, f_vector_fcmeq) +TRANS(FCMEQ_v, do_fp3_vector, a, 0, f_vector_fcmeq) static gen_helper_gvec_3_ptr * const f_vector_fcmge[3] = { gen_helper_gvec_fcge_h, gen_helper_gvec_fcge_s, gen_helper_gvec_fcge_d, }; -TRANS(FCMGE_v, do_fp3_vector, a, f_vector_fcmge) +TRANS(FCMGE_v, do_fp3_vector, a, 0, f_vector_fcmge) static gen_helper_gvec_3_ptr * const f_vector_fcmgt[3] = { gen_helper_gvec_fcgt_h, gen_helper_gvec_fcgt_s, gen_helper_gvec_fcgt_d, }; -TRANS(FCMGT_v, do_fp3_vector, a, f_vector_fcmgt) +TRANS(FCMGT_v, do_fp3_vector, a, 0, f_vector_fcmgt) static gen_helper_gvec_3_ptr * const f_vector_facge[3] = { gen_helper_gvec_facge_h, gen_helper_gvec_facge_s, gen_helper_gvec_facge_d, }; -TRANS(FACGE_v, do_fp3_vector, a, f_vector_facge) +TRANS(FACGE_v, do_fp3_vector, a, 0, f_vector_facge) static gen_helper_gvec_3_ptr * const f_vector_facgt[3] = { gen_helper_gvec_facgt_h, gen_helper_gvec_facgt_s, gen_helper_gvec_facgt_d, }; -TRANS(FACGT_v, do_fp3_vector, a, f_vector_facgt) +TRANS(FACGT_v, do_fp3_vector, a, 0, f_vector_facgt) static gen_helper_gvec_3_ptr * const f_vector_fabd[3] = { gen_helper_gvec_fabd_h, gen_helper_gvec_fabd_s, gen_helper_gvec_fabd_d, }; -TRANS(FABD_v, do_fp3_vector, a, f_vector_fabd) +TRANS(FABD_v, do_fp3_vector, a, 0, f_vector_fabd) static gen_helper_gvec_3_ptr * const f_vector_frecps[3] = { gen_helper_gvec_recps_h, gen_helper_gvec_recps_s, gen_helper_gvec_recps_d, }; -TRANS(FRECPS_v, do_fp3_vector, a, f_vector_frecps) +TRANS(FRECPS_v, do_fp3_vector, a, 0, f_vector_frecps) static gen_helper_gvec_3_ptr * const f_vector_frsqrts[3] = { gen_helper_gvec_rsqrts_h, gen_helper_gvec_rsqrts_s, gen_helper_gvec_rsqrts_d, }; -TRANS(FRSQRTS_v, do_fp3_vector, a, f_vector_frsqrts) +TRANS(FRSQRTS_v, do_fp3_vector, a, 0, f_vector_frsqrts) static gen_helper_gvec_3_ptr * const f_vector_faddp[3] = { gen_helper_gvec_faddp_h, gen_helper_gvec_faddp_s, gen_helper_gvec_faddp_d, }; -TRANS(FADDP_v, do_fp3_vector, a, f_vector_faddp) +TRANS(FADDP_v, do_fp3_vector, a, 0, f_vector_faddp) static gen_helper_gvec_3_ptr * const f_vector_fmaxp[3] = { gen_helper_gvec_fmaxp_h, gen_helper_gvec_fmaxp_s, gen_helper_gvec_fmaxp_d, }; -TRANS(FMAXP_v, do_fp3_vector, a, f_vector_fmaxp) +TRANS(FMAXP_v, do_fp3_vector, a, 0, f_vector_fmaxp) static gen_helper_gvec_3_ptr * const f_vector_fminp[3] = { gen_helper_gvec_fminp_h, gen_helper_gvec_fminp_s, gen_helper_gvec_fminp_d, }; -TRANS(FMINP_v, do_fp3_vector, a, f_vector_fminp) +TRANS(FMINP_v, do_fp3_vector, a, 0, f_vector_fminp) static gen_helper_gvec_3_ptr * const f_vector_fmaxnmp[3] = { gen_helper_gvec_fmaxnump_h, gen_helper_gvec_fmaxnump_s, gen_helper_gvec_fmaxnump_d, }; -TRANS(FMAXNMP_v, do_fp3_vector, a, f_vector_fmaxnmp) +TRANS(FMAXNMP_v, do_fp3_vector, a, 0, f_vector_fmaxnmp) static gen_helper_gvec_3_ptr * const f_vector_fminnmp[3] = { gen_helper_gvec_fminnump_h, gen_helper_gvec_fminnump_s, gen_helper_gvec_fminnump_d, }; -TRANS(FMINNMP_v, do_fp3_vector, a, f_vector_fminnmp) +TRANS(FMINNMP_v, do_fp3_vector, a, 0, f_vector_fminnmp) static bool do_fmlal(DisasContext *s, arg_qrrr_e *a, bool is_s, bool is_2) { -- 2.34.1 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: 20240625183536.1672454-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 3 +++ target/arm/tcg/translate-a64.c | 33 ++++++++++----------------------- 2 files changed, 13 insertions(+), 23 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ SMMLA 0100 1110 100 ..... 10100 1 ..... ..... @rrr_q1e0 UMMLA 0110 1110 100 ..... 10100 1 ..... ..... @rrr_q1e0 USMMLA 0100 1110 100 ..... 10101 1 ..... ..... @rrr_q1e0 +FCADD_90 0.10 1110 ..0 ..... 11100 1 ..... ..... @qrrr_e +FCADD_270 0.10 1110 ..0 ..... 11110 1 ..... ..... @qrrr_e + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_BFMLAL_v(DisasContext *s, arg_qrrr_e *a) return true; } +static gen_helper_gvec_3_ptr * const f_vector_fcadd[3] = { + gen_helper_gvec_fcaddh, + gen_helper_gvec_fcadds, + gen_helper_gvec_fcaddd, +}; +TRANS_FEAT(FCADD_90, aa64_fcma, do_fp3_vector, a, 0, f_vector_fcadd) +TRANS_FEAT(FCADD_270, aa64_fcma, do_fp3_vector, a, 1, f_vector_fcadd) + /* * Advanced SIMD scalar/vector x indexed element */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) case 0x19: /* FCMLA, #90 */ case 0x1a: /* FCMLA, #180 */ case 0x1b: /* FCMLA, #270 */ - case 0x1c: /* FCADD, #90 */ - case 0x1e: /* FCADD, #270 */ if (size == 0 || (size == 1 && !dc_isar_feature(aa64_fp16, s)) || (size == 3 && !is_q)) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) case 0x11: /* SQRDMLSH (vector) */ case 0x12: /* UDOT (vector) */ case 0x14: /* UMMLA */ + case 0x1c: /* FCADD, #90 */ case 0x1d: /* BFMMLA */ + case 0x1e: /* FCADD, #270 */ case 0x1f: /* BFDOT / BFMLAL */ unallocated_encoding(s); return; @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) } return; - case 0xc: /* FCADD, #90 */ - case 0xe: /* FCADD, #270 */ - rot = extract32(opcode, 1, 1); - switch (size) { - case 1: - gen_gvec_op3_fpst(s, is_q, rd, rn, rm, size == 1, rot, - gen_helper_gvec_fcaddh); - break; - case 2: - gen_gvec_op3_fpst(s, is_q, rd, rn, rm, size == 1, rot, - gen_helper_gvec_fcadds); - break; - case 3: - gen_gvec_op3_fpst(s, is_q, rd, rn, rm, size == 1, rot, - gen_helper_gvec_fcaddd); - break; - default: - g_assert_not_reached(); - } - return; - default: g_assert_not_reached(); } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240625183536.1672454-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/a64.decode | 6 + target/arm/tcg/translate-a64.c | 238 ++++++++++----------------------- 2 files changed, 74 insertions(+), 170 deletions(-) diff --git a/target/arm/tcg/a64.decode b/target/arm/tcg/a64.decode index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -XXX,XX +XXX,XX @@ USMMLA 0100 1110 100 ..... 10101 1 ..... ..... @rrr_q1e0 FCADD_90 0.10 1110 ..0 ..... 11100 1 ..... ..... @qrrr_e FCADD_270 0.10 1110 ..0 ..... 11110 1 ..... ..... @qrrr_e +FCMLA_v 0 q:1 10 1110 esz:2 0 rm:5 110 rot:2 1 rn:5 rd:5 + ### Advanced SIMD scalar x indexed element FMUL_si 0101 1111 00 .. .... 1001 . 0 ..... ..... @rrx_h @@ -XXX,XX +XXX,XX @@ USDOT_vi 0.00 1111 10 .. .... 1111 . 0 ..... ..... @qrrx_s BFDOT_vi 0.00 1111 01 .. .... 1111 . 0 ..... ..... @qrrx_s BFMLAL_vi 0.00 1111 11 .. .... 1111 . 0 ..... ..... @qrrx_h +FCMLA_vi 0 0 10 1111 01 idx:1 rm:5 0 rot:2 1 0 0 rn:5 rd:5 esz=1 q=0 +FCMLA_vi 0 1 10 1111 01 . rm:5 0 rot:2 1 . 0 rn:5 rd:5 esz=1 idx=%hl q=1 +FCMLA_vi 0 1 10 1111 10 0 rm:5 0 rot:2 1 idx:1 0 rn:5 rd:5 esz=2 q=1 + # Floating-point conditional select FCSEL 0001 1110 .. 1 rm:5 cond:4 11 rn:5 rd:5 esz=%esz_hsd diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const f_vector_fcadd[3] = { TRANS_FEAT(FCADD_90, aa64_fcma, do_fp3_vector, a, 0, f_vector_fcadd) TRANS_FEAT(FCADD_270, aa64_fcma, do_fp3_vector, a, 1, f_vector_fcadd) +static bool trans_FCMLA_v(DisasContext *s, arg_FCMLA_v *a) +{ + gen_helper_gvec_4_ptr *fn; + + if (!dc_isar_feature(aa64_fcma, s)) { + return false; + } + switch (a->esz) { + case MO_64: + if (!a->q) { + return false; + } + fn = gen_helper_gvec_fcmlad; + break; + case MO_32: + fn = gen_helper_gvec_fcmlas; + break; + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return false; + } + fn = gen_helper_gvec_fcmlah; + break; + default: + return false; + } + if (fp_access_check(s)) { + gen_gvec_op4_fpst(s, a->q, a->rd, a->rn, a->rm, a->rd, + a->esz == MO_16, a->rot, fn); + } + return true; +} + /* * Advanced SIMD scalar/vector x indexed element */ @@ -XXX,XX +XXX,XX @@ static bool trans_BFMLAL_vi(DisasContext *s, arg_qrrx_e *a) return true; } +static bool trans_FCMLA_vi(DisasContext *s, arg_FCMLA_vi *a) +{ + gen_helper_gvec_4_ptr *fn; + + if (!dc_isar_feature(aa64_fcma, s)) { + return false; + } + switch (a->esz) { + case MO_16: + if (!dc_isar_feature(aa64_fp16, s)) { + return false; + } + fn = gen_helper_gvec_fcmlah_idx; + break; + case MO_32: + fn = gen_helper_gvec_fcmlas_idx; + break; + default: + g_assert_not_reached(); + } + if (fp_access_check(s)) { + gen_gvec_op4_fpst(s, a->q, a->rd, a->rn, a->rm, a->rd, + a->esz == MO_16, (a->idx << 2) | a->rot, fn); + } + return true; +} + /* * Advanced SIMD scalar pairwise */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_three_reg_diff(DisasContext *s, uint32_t insn) } } -/* AdvSIMD three same extra - * 31 30 29 28 24 23 22 21 20 16 15 14 11 10 9 5 4 0 - * +---+---+---+-----------+------+---+------+---+--------+---+----+----+ - * | 0 | Q | U | 0 1 1 1 0 | size | 0 | Rm | 1 | opcode | 1 | Rn | Rd | - * +---+---+---+-----------+------+---+------+---+--------+---+----+----+ - */ -static void disas_simd_three_reg_same_extra(DisasContext *s, uint32_t insn) -{ - int rd = extract32(insn, 0, 5); - int rn = extract32(insn, 5, 5); - int opcode = extract32(insn, 11, 4); - int rm = extract32(insn, 16, 5); - int size = extract32(insn, 22, 2); - bool u = extract32(insn, 29, 1); - bool is_q = extract32(insn, 30, 1); - bool feature; - int rot; - - switch (u * 16 + opcode) { - case 0x18: /* FCMLA, #0 */ - case 0x19: /* FCMLA, #90 */ - case 0x1a: /* FCMLA, #180 */ - case 0x1b: /* FCMLA, #270 */ - if (size == 0 - || (size == 1 && !dc_isar_feature(aa64_fp16, s)) - || (size == 3 && !is_q)) { - unallocated_encoding(s); - return; - } - feature = dc_isar_feature(aa64_fcma, s); - break; - default: - case 0x02: /* SDOT (vector) */ - case 0x03: /* USDOT */ - case 0x04: /* SMMLA */ - case 0x05: /* USMMLA */ - case 0x10: /* SQRDMLAH (vector) */ - case 0x11: /* SQRDMLSH (vector) */ - case 0x12: /* UDOT (vector) */ - case 0x14: /* UMMLA */ - case 0x1c: /* FCADD, #90 */ - case 0x1d: /* BFMMLA */ - case 0x1e: /* FCADD, #270 */ - case 0x1f: /* BFDOT / BFMLAL */ - unallocated_encoding(s); - return; - } - if (!feature) { - unallocated_encoding(s); - return; - } - if (!fp_access_check(s)) { - return; - } - - switch (opcode) { - case 0x8: /* FCMLA, #0 */ - case 0x9: /* FCMLA, #90 */ - case 0xa: /* FCMLA, #180 */ - case 0xb: /* FCMLA, #270 */ - rot = extract32(opcode, 0, 2); - switch (size) { - case 1: - gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, true, rot, - gen_helper_gvec_fcmlah); - break; - case 2: - gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, false, rot, - gen_helper_gvec_fcmlas); - break; - case 3: - gen_gvec_op4_fpst(s, is_q, rd, rn, rm, rd, false, rot, - gen_helper_gvec_fcmlad); - break; - default: - g_assert_not_reached(); - } - return; - - default: - g_assert_not_reached(); - } -} - static void handle_2misc_widening(DisasContext *s, int opcode, bool is_q, int size, int rn, int rd) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); bool is_long = false; - int is_fp = 0; - bool is_fp16 = false; int index; - TCGv_ptr fpst; switch (16 * u + opcode) { case 0x02: /* SMLAL, SMLAL2 */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x0b: /* SQDMULL, SQDMULL2 */ is_long = true; break; - case 0x11: /* FCMLA #0 */ - case 0x13: /* FCMLA #90 */ - case 0x15: /* FCMLA #180 */ - case 0x17: /* FCMLA #270 */ - if (is_scalar || !dc_isar_feature(aa64_fcma, s)) { - unallocated_encoding(s); - return; - } - is_fp = 2; - break; default: case 0x00: /* FMLAL */ case 0x01: /* FMLA */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) case 0x0e: /* SDOT */ case 0x0f: /* SUDOT / BFDOT / USDOT / BFMLAL */ case 0x10: /* MLA */ + case 0x11: /* FCMLA #0 */ + case 0x13: /* FCMLA #90 */ case 0x14: /* MLS */ + case 0x15: /* FCMLA #180 */ + case 0x17: /* FCMLA #270 */ case 0x18: /* FMLAL2 */ case 0x19: /* FMULX */ case 0x1c: /* FMLSL2 */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) return; } - switch (is_fp) { - case 1: /* normal fp */ - unallocated_encoding(s); /* in decodetree */ - return; - - case 2: /* complex fp */ - /* Each indexable element is a complex pair. */ - size += 1; - switch (size) { - case MO_32: - if (h && !is_q) { - unallocated_encoding(s); - return; - } - is_fp16 = true; - break; - case MO_64: - break; - default: - unallocated_encoding(s); - return; - } - break; - - default: /* integer */ - switch (size) { - case MO_8: - case MO_64: - unallocated_encoding(s); - return; - } - break; - } - if (is_fp16 && !dc_isar_feature(aa64_fp16, s)) { - unallocated_encoding(s); - return; - } - /* Given MemOp size, adjust register and indexing. */ switch (size) { + case MO_8: + case MO_64: + unallocated_encoding(s); + return; case MO_16: index = h << 2 | l << 1 | m; break; @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) index = h << 1 | l; rm |= m << 4; break; - case MO_64: - if (l || !is_q) { - unallocated_encoding(s); - return; - } - index = h; - rm |= m << 4; - break; default: g_assert_not_reached(); } @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) return; } - if (is_fp) { - fpst = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_FPCR); - } else { - fpst = NULL; - } - - switch (16 * u + opcode) { - case 0x11: /* FCMLA #0 */ - case 0x13: /* FCMLA #90 */ - case 0x15: /* FCMLA #180 */ - case 0x17: /* FCMLA #270 */ - { - int rot = extract32(insn, 13, 2); - int data = (index << 2) | rot; - tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, rd), - vec_full_reg_offset(s, rn), - vec_full_reg_offset(s, rm), - vec_full_reg_offset(s, rd), fpst, - is_q ? 16 : 8, vec_full_reg_size(s), data, - size == MO_64 - ? gen_helper_gvec_fcmlas_idx - : gen_helper_gvec_fcmlah_idx); - } - return; - } - if (size == 3) { g_assert_not_reached(); } else if (!is_long) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) */ static const AArch64DecodeTable data_proc_simd[] = { /* pattern , mask , fn */ - { 0x0e008400, 0x9f208400, disas_simd_three_reg_same_extra }, { 0x0e200000, 0x9f200c00, disas_simd_three_reg_diff }, { 0x0e200800, 0x9f3e0c00, disas_simd_two_reg_misc }, { 0x0e300800, 0x9f3e0c00, disas_simd_across_lanes }, -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> MLA, MLS, SQDMULH, SQRDMULH, were converted with 8db93dcd3def and f80701cb44d, and this code should have been removed then. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240625183536.1672454-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate-a64.c | 93 ---------------------------------- 1 file changed, 93 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) int h = extract32(insn, 11, 1); int rn = extract32(insn, 5, 5); int rd = extract32(insn, 0, 5); - bool is_long = false; int index; switch (16 * u + opcode) { @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) unallocated_encoding(s); return; } - is_long = true; break; case 0x03: /* SQDMLAL, SQDMLAL2 */ case 0x07: /* SQDMLSL, SQDMLSL2 */ case 0x0b: /* SQDMULL, SQDMULL2 */ - is_long = true; break; default: case 0x00: /* FMLAL */ @@ -XXX,XX +XXX,XX @@ static void disas_simd_indexed(DisasContext *s, uint32_t insn) if (size == 3) { g_assert_not_reached(); - } else if (!is_long) { - /* 32 bit floating point, or 16 or 32 bit integer. - * For the 16 bit scalar case we use the usual Neon helpers and - * rely on the fact that 0 op 0 == 0 with no side effects. - */ - TCGv_i32 tcg_idx = tcg_temp_new_i32(); - int pass, maxpasses; - - if (is_scalar) { - maxpasses = 1; - } else { - maxpasses = is_q ? 4 : 2; - } - - read_vec_element_i32(s, tcg_idx, rm, index, size); - - if (size == 1 && !is_scalar) { - /* The simplest way to handle the 16x16 indexed ops is to duplicate - * the index into both halves of the 32 bit tcg_idx and then use - * the usual Neon helpers. - */ - tcg_gen_deposit_i32(tcg_idx, tcg_idx, tcg_idx, 16, 16); - } - - for (pass = 0; pass < maxpasses; pass++) { - TCGv_i32 tcg_op = tcg_temp_new_i32(); - TCGv_i32 tcg_res = tcg_temp_new_i32(); - - read_vec_element_i32(s, tcg_op, rn, pass, is_scalar ? size : MO_32); - - switch (16 * u + opcode) { - case 0x10: /* MLA */ - case 0x14: /* MLS */ - { - static NeonGenTwoOpFn * const fns[2][2] = { - { gen_helper_neon_add_u16, gen_helper_neon_sub_u16 }, - { tcg_gen_add_i32, tcg_gen_sub_i32 }, - }; - NeonGenTwoOpFn *genfn; - bool is_sub = opcode == 0x4; - - if (size == 1) { - gen_helper_neon_mul_u16(tcg_res, tcg_op, tcg_idx); - } else { - tcg_gen_mul_i32(tcg_res, tcg_op, tcg_idx); - } - if (opcode == 0x8) { - break; - } - read_vec_element_i32(s, tcg_op, rd, pass, MO_32); - genfn = fns[size - 1][is_sub]; - genfn(tcg_res, tcg_op, tcg_res); - break; - } - case 0x0c: /* SQDMULH */ - if (size == 1) { - gen_helper_neon_qdmulh_s16(tcg_res, tcg_env, - tcg_op, tcg_idx); - } else { - gen_helper_neon_qdmulh_s32(tcg_res, tcg_env, - tcg_op, tcg_idx); - } - break; - case 0x0d: /* SQRDMULH */ - if (size == 1) { - gen_helper_neon_qrdmulh_s16(tcg_res, tcg_env, - tcg_op, tcg_idx); - } else { - gen_helper_neon_qrdmulh_s32(tcg_res, tcg_env, - tcg_op, tcg_idx); - } - break; - default: - case 0x01: /* FMLA */ - case 0x05: /* FMLS */ - case 0x09: /* FMUL */ - case 0x19: /* FMULX */ - case 0x1d: /* SQRDMLAH */ - case 0x1f: /* SQRDMLSH */ - g_assert_not_reached(); - } - - if (is_scalar) { - write_fp_sreg(s, rd, tcg_res); - } else { - write_vec_element_i32(s, tcg_res, rd, pass, MO_32); - } - } - - clear_vec_high(s, is_q, rd); } else { /* long ops: 16x16->32 or 32x32->64 */ TCGv_i64 tcg_res[2]; -- 2.34.1 From: Gustavo Romero <gustavo.romero@linaro.org> Fix comment indentation adding a missing space. Signed-off-by: Gustavo Romero <gustavo.romero@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240624180915.4528-2-gustavo.romero@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/cpu64.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) t = cpu->isar.id_aa64isar2; t = FIELD_DP64(t, ID_AA64ISAR2, MOPS, 1); /* FEAT_MOPS */ - t = FIELD_DP64(t, ID_AA64ISAR2, BC, 1); /* FEAT_HBC */ + t = FIELD_DP64(t, ID_AA64ISAR2, BC, 1); /* FEAT_HBC */ t = FIELD_DP64(t, ID_AA64ISAR2, WFXT, 2); /* FEAT_WFxT */ cpu->isar.id_aa64isar2 = t; -- 2.34.1 From: Gustavo Romero <gustavo.romero@linaro.org> Move the initialization of the debug ID registers to aa32_max_features, which is used to set the 32-bit ID registers. This ensures that the debug ID registers are consistently set for the max CPU in a single place. Signed-off-by: Gustavo Romero <gustavo.romero@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240624180915.4528-3-gustavo.romero@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 2 ++ target/arm/tcg/cpu32.c | 31 ++++++++++++++++++++++++++++--- 2 files changed, 30 insertions(+), 3 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ FIELD(DBGDEVID, DOUBLELOCK, 20, 4) FIELD(DBGDEVID, AUXREGS, 24, 4) FIELD(DBGDEVID, CIDMASK, 28, 4) +FIELD(DBGDEVID1, PCSROFFSET, 0, 4) + FIELD(MVFR0, SIMDREG, 0, 4) FIELD(MVFR0, FPSP, 4, 4) FIELD(MVFR0, FPDP, 8, 4) diff --git a/target/arm/tcg/cpu32.c b/target/arm/tcg/cpu32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu32.c +++ b/target/arm/tcg/cpu32.c @@ -XXX,XX +XXX,XX @@ void aa32_max_features(ARMCPU *cpu) t = FIELD_DP32(t, ID_DFR0, PERFMON, 6); /* FEAT_PMUv3p5 */ cpu->isar.id_dfr0 = t; + /* Debug ID registers. */ + + /* Bit[15] is RES1, Bit[13] and Bits[11:0] are RES0. */ + t = 0x00008000; + t = FIELD_DP32(t, DBGDIDR, SE_IMP, 1); + t = FIELD_DP32(t, DBGDIDR, NSUHD_IMP, 1); + t = FIELD_DP32(t, DBGDIDR, VERSION, 6); /* Armv8 debug */ + t = FIELD_DP32(t, DBGDIDR, CTX_CMPS, 1); + t = FIELD_DP32(t, DBGDIDR, BRPS, 5); + t = FIELD_DP32(t, DBGDIDR, WRPS, 3); + cpu->isar.dbgdidr = t; + + t = 0; + t = FIELD_DP32(t, DBGDEVID, PCSAMPLE, 3); + t = FIELD_DP32(t, DBGDEVID, WPADDRMASK, 1); + t = FIELD_DP32(t, DBGDEVID, BPADDRMASK, 15); + t = FIELD_DP32(t, DBGDEVID, VECTORCATCH, 0); + t = FIELD_DP32(t, DBGDEVID, VIRTEXTNS, 1); + t = FIELD_DP32(t, DBGDEVID, DOUBLELOCK, 1); + t = FIELD_DP32(t, DBGDEVID, AUXREGS, 0); + t = FIELD_DP32(t, DBGDEVID, CIDMASK, 0); + cpu->isar.dbgdevid = t; + + /* Bits[31:4] are RES0. */ + t = 0; + t = FIELD_DP32(t, DBGDEVID1, PCSROFFSET, 2); + cpu->isar.dbgdevid1 = t; + t = cpu->isar.id_dfr1; t = FIELD_DP32(t, ID_DFR1, HPMN0, 1); /* FEAT_HPMN0 */ cpu->isar.id_dfr1 = t; @@ -XXX,XX +XXX,XX @@ static void arm_max_initfn(Object *obj) cpu->isar.id_isar4 = 0x00011142; cpu->isar.id_isar5 = 0x00011121; cpu->isar.id_isar6 = 0; - cpu->isar.dbgdidr = 0x3516d000; - cpu->isar.dbgdevid = 0x00110f13; - cpu->isar.dbgdevid1 = 0x2; cpu->isar.reset_pmcr_el0 = 0x41013000; cpu->clidr = 0x0a200023; cpu->ccsidr[0] = 0x701fe00a; /* 32KB L1 dcache */ -- 2.34.1 From: Gustavo Romero <gustavo.romero@linaro.org> Enable FEAT_Debugv8p8 for max CPU. This feature is out of scope for QEMU since it concerns the external debug interface for JTAG, but is mandatory in Armv8.8 implementations, hence it is reported as supported in the ID registers. Signed-off-by: Gustavo Romero <gustavo.romero@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240624180915.4528-4-gustavo.romero@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/emulation.rst | 1 + target/arm/tcg/cpu32.c | 6 +++--- target/arm/tcg/cpu64.c | 2 +- 3 files changed, 5 insertions(+), 4 deletions(-) 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_Debugv8p1 (Debug with VHE) - FEAT_Debugv8p2 (Debug changes for v8.2) - FEAT_Debugv8p4 (Debug changes for v8.4) +- FEAT_Debugv8p8 (Debug changes for v8.8) - FEAT_DotProd (Advanced SIMD dot product instructions) - FEAT_DoubleFault (Double Fault Extension) - FEAT_E0PD (Preventing EL0 access to halves of address maps) diff --git a/target/arm/tcg/cpu32.c b/target/arm/tcg/cpu32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu32.c +++ b/target/arm/tcg/cpu32.c @@ -XXX,XX +XXX,XX @@ void aa32_max_features(ARMCPU *cpu) cpu->isar.id_pfr2 = t; t = cpu->isar.id_dfr0; - t = FIELD_DP32(t, ID_DFR0, COPDBG, 9); /* FEAT_Debugv8p4 */ - t = FIELD_DP32(t, ID_DFR0, COPSDBG, 9); /* FEAT_Debugv8p4 */ + t = FIELD_DP32(t, ID_DFR0, COPDBG, 10); /* FEAT_Debugv8p8 */ + t = FIELD_DP32(t, ID_DFR0, COPSDBG, 10); /* FEAT_Debugv8p8 */ t = FIELD_DP32(t, ID_DFR0, PERFMON, 6); /* FEAT_PMUv3p5 */ cpu->isar.id_dfr0 = t; @@ -XXX,XX +XXX,XX @@ void aa32_max_features(ARMCPU *cpu) t = 0x00008000; t = FIELD_DP32(t, DBGDIDR, SE_IMP, 1); t = FIELD_DP32(t, DBGDIDR, NSUHD_IMP, 1); - t = FIELD_DP32(t, DBGDIDR, VERSION, 6); /* Armv8 debug */ + t = FIELD_DP32(t, DBGDIDR, VERSION, 10); /* FEAT_Debugv8p8 */ t = FIELD_DP32(t, DBGDIDR, CTX_CMPS, 1); t = FIELD_DP32(t, DBGDIDR, BRPS, 5); t = FIELD_DP32(t, DBGDIDR, WRPS, 3); diff --git a/target/arm/tcg/cpu64.c b/target/arm/tcg/cpu64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -XXX,XX +XXX,XX @@ void aarch64_max_tcg_initfn(Object *obj) cpu->isar.id_aa64zfr0 = t; t = cpu->isar.id_aa64dfr0; - t = FIELD_DP64(t, ID_AA64DFR0, DEBUGVER, 9); /* FEAT_Debugv8p4 */ + t = FIELD_DP64(t, ID_AA64DFR0, DEBUGVER, 10); /* FEAT_Debugv8p8 */ t = FIELD_DP64(t, ID_AA64DFR0, PMUVER, 6); /* FEAT_PMUv3p5 */ t = FIELD_DP64(t, ID_AA64DFR0, HPMN0, 1); /* FEAT_HPMN0 */ cpu->isar.id_aa64dfr0 = t; -- 2.34.1 From: Patrick Leis <venture@google.com> Signed-off-by: Patrick Leis <venture@google.com> Message-id: 20240626211623.3510701-1-venture@google.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/net/tulip.c F: hw/net/tulip.h pca954x -M: Patrick Venture <venture@google.com> +M: Patrick Leis <venture@google.com> S: Maintained F: hw/i2c/i2c_mux_pca954x.c F: include/hw/i2c/i2c_mux_pca954x.h -- 2.34.1 From: Sai Pavan Boddu <sai.pavan.boddu@amd.com> boot-mode property sets user values into BOOT_MODE register, on hardware these are derived from board switches. Signed-off-by: Sai Pavan Boddu <sai.pavan.boddu@amd.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20240621125906.1300995-2-sai.pavan.boddu@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/zynq_slcr.c | 22 +++++++++++++++++++++- 1 file changed, 21 insertions(+), 1 deletion(-) diff --git a/hw/misc/zynq_slcr.c b/hw/misc/zynq_slcr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/zynq_slcr.c +++ b/hw/misc/zynq_slcr.c @@ -XXX,XX +XXX,XX @@ #include "hw/registerfields.h" #include "hw/qdev-clock.h" #include "qom/object.h" +#include "hw/qdev-properties.h" +#include "qapi/error.h" #ifndef ZYNQ_SLCR_ERR_DEBUG #define ZYNQ_SLCR_ERR_DEBUG 0 @@ -XXX,XX +XXX,XX @@ REG32(RST_REASON, 0x250) REG32(REBOOT_STATUS, 0x258) REG32(BOOT_MODE, 0x25c) + FIELD(BOOT_MODE, BOOT_MODE, 0, 4) REG32(APU_CTRL, 0x300) REG32(WDT_CLK_SEL, 0x304) @@ -XXX,XX +XXX,XX @@ struct ZynqSLCRState { Clock *ps_clk; Clock *uart0_ref_clk; Clock *uart1_ref_clk; + uint8_t boot_mode; }; /* @@ -XXX,XX +XXX,XX @@ static void zynq_slcr_reset_init(Object *obj, ResetType type) s->regs[R_FPGA_RST_CTRL] = 0x01F33F0F; s->regs[R_RST_REASON] = 0x00000040; - s->regs[R_BOOT_MODE] = 0x00000001; + s->regs[R_BOOT_MODE] = s->boot_mode & R_BOOT_MODE_BOOT_MODE_MASK; /* 0x700 - 0x7D4 */ for (i = 0; i < 54; i++) { @@ -XXX,XX +XXX,XX @@ static const ClockPortInitArray zynq_slcr_clocks = { QDEV_CLOCK_END }; +static void zynq_slcr_realize(DeviceState *dev, Error **errp) +{ + ZynqSLCRState *s = ZYNQ_SLCR(dev); + + if (s->boot_mode > 0xF) { + error_setg(errp, "Invalid boot mode %d specified", s->boot_mode); + } +} + static void zynq_slcr_init(Object *obj) { ZynqSLCRState *s = ZYNQ_SLCR(obj); @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_zynq_slcr = { } }; +static Property zynq_slcr_props[] = { + DEFINE_PROP_UINT8("boot-mode", ZynqSLCRState, boot_mode, 1), + DEFINE_PROP_END_OF_LIST(), +}; + static void zynq_slcr_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); ResettableClass *rc = RESETTABLE_CLASS(klass); dc->vmsd = &vmstate_zynq_slcr; + dc->realize = zynq_slcr_realize; rc->phases.enter = zynq_slcr_reset_init; rc->phases.hold = zynq_slcr_reset_hold; rc->phases.exit = zynq_slcr_reset_exit; + device_class_set_props(dc, zynq_slcr_props); } static const TypeInfo zynq_slcr_info = { -- 2.34.1 From: Sai Pavan Boddu <sai.pavan.boddu@amd.com> Read boot-mode value as machine property and propagate that to SLCR.BOOT_MODE register. Signed-off-by: Sai Pavan Boddu <sai.pavan.boddu@amd.com> Acked-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20240621125906.1300995-3-sai.pavan.boddu@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/xilinx_zynq.c | 31 +++++++++++++++++++++++++++++++ 1 file changed, 31 insertions(+) diff --git a/hw/arm/xilinx_zynq.c b/hw/arm/xilinx_zynq.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -XXX,XX +XXX,XX @@ #include "qom/object.h" #include "exec/tswap.h" #include "target/arm/cpu-qom.h" +#include "qapi/visitor.h" #define TYPE_ZYNQ_MACHINE MACHINE_TYPE_NAME("xilinx-zynq-a9") OBJECT_DECLARE_SIMPLE_TYPE(ZynqMachineState, ZYNQ_MACHINE) @@ -XXX,XX +XXX,XX @@ struct ZynqMachineState { MachineState parent; Clock *ps_clk; ARMCPU *cpu[ZYNQ_MAX_CPUS]; + uint8_t boot_mode; }; static void zynq_write_board_setup(ARMCPU *cpu, @@ -XXX,XX +XXX,XX @@ static inline int zynq_init_spi_flashes(uint32_t base_addr, qemu_irq irq, return unit; } +static void zynq_set_boot_mode(Object *obj, const char *str, + Error **errp) +{ + ZynqMachineState *m = ZYNQ_MACHINE(obj); + uint8_t mode = 0; + + if (!strncasecmp(str, "qspi", 4)) { + mode = 1; + } else if (!strncasecmp(str, "sd", 2)) { + mode = 5; + } else if (!strncasecmp(str, "nor", 3)) { + mode = 2; + } else if (!strncasecmp(str, "jtag", 4)) { + mode = 0; + } else { + error_setg(errp, "%s boot mode not supported", str); + return; + } + m->boot_mode = mode; +} + static void zynq_init(MachineState *machine) { ZynqMachineState *zynq_machine = ZYNQ_MACHINE(machine); @@ -XXX,XX +XXX,XX @@ static void zynq_init(MachineState *machine) /* Create slcr, keep a pointer to connect clocks */ slcr = qdev_new("xilinx-zynq_slcr"); qdev_connect_clock_in(slcr, "ps_clk", zynq_machine->ps_clk); + qdev_prop_set_uint8(slcr, "boot-mode", zynq_machine->boot_mode); sysbus_realize_and_unref(SYS_BUS_DEVICE(slcr), &error_fatal); sysbus_mmio_map(SYS_BUS_DEVICE(slcr), 0, 0xF8000000); @@ -XXX,XX +XXX,XX @@ static void zynq_machine_class_init(ObjectClass *oc, void *data) NULL }; MachineClass *mc = MACHINE_CLASS(oc); + ObjectProperty *prop; mc->desc = "Xilinx Zynq Platform Baseboard for Cortex-A9"; mc->init = zynq_init; mc->max_cpus = ZYNQ_MAX_CPUS; @@ -XXX,XX +XXX,XX @@ static void zynq_machine_class_init(ObjectClass *oc, void *data) mc->ignore_memory_transaction_failures = true; mc->valid_cpu_types = valid_cpu_types; mc->default_ram_id = "zynq.ext_ram"; + prop = object_class_property_add_str(oc, "boot-mode", NULL, + zynq_set_boot_mode); + object_class_property_set_description(oc, "boot-mode", + "Supported boot modes:" + " jtag qspi sd nor"); + object_property_set_default_str(prop, "qspi"); } static const TypeInfo zynq_machine_type = { -- 2.34.1 From: Sai Pavan Boddu <sai.pavan.boddu@amd.com> Added the supported device list and an example command. Signed-off-by: Sai Pavan Boddu <sai.pavan.boddu@amd.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@amd.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20240621125906.1300995-4-sai.pavan.boddu@amd.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 1 + docs/system/arm/xlnx-zynq.rst | 47 +++++++++++++++++++++++++++++++++++ docs/system/target-arm.rst | 1 + 3 files changed, 49 insertions(+) create mode 100644 docs/system/arm/xlnx-zynq.rst diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/adc/zynq-xadc.c F: include/hw/misc/zynq_slcr.h F: include/hw/adc/zynq-xadc.h X: hw/ssi/xilinx_* +F: docs/system/arm/xlnx-zynq.rst Xilinx ZynqMP and Versal M: Alistair Francis <alistair@alistair23.me> diff --git a/docs/system/arm/xlnx-zynq.rst b/docs/system/arm/xlnx-zynq.rst new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/docs/system/arm/xlnx-zynq.rst @@ -XXX,XX +XXX,XX @@ +Xilinx Zynq board (``xilinx-zynq-a9``) +====================================== +The Zynq 7000 family is based on the AMD SoC architecture. These products +integrate a feature-rich dual or single-core Arm Cortex-A9 MPCore based +processing system (PS) and AMD programmable logic (PL) in a single device. + +More details here: +https://docs.amd.com/r/en-US/ug585-zynq-7000-SoC-TRM/Zynq-7000-SoC-Technical-Reference-Manual + +QEMU xilinx-zynq-a9 board supports following devices: + - A9 MPCORE + - cortex-a9 + - GIC v1 + - Generic timer + - wdt + - OCM 256KB + - SMC SRAM@0xe2000000 64MB + - Zynq SLCR + - SPI x2 + - QSPI + - UART + - TTC x2 + - Gigabit Ethernet Controller x2 + - SD Controller x2 + - XADC + - Arm PrimeCell DMA Controller + - DDR Memory + - USB 2.0 x2 + +Running +""""""" +Direct Linux boot of a generic ARM upstream Linux kernel: + +.. code-block:: bash + + $ qemu-system-aarch64 -M xilinx-zynq-a9 \ + -dtb zynq-zc702.dtb -serial null -serial mon:stdio \ + -display none -m 1024 \ + -initrd rootfs.cpio.gz -kernel zImage + +For configuring the boot-mode provide the following on the command line: + +.. code-block:: bash + + -machine boot-mode=qspi + +Supported values are jtag, sd, qspi, nor. diff --git a/docs/system/target-arm.rst b/docs/system/target-arm.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -XXX,XX +XXX,XX @@ undocumented; you can get a complete list by running arm/virt arm/xenpvh arm/xlnx-versal-virt + arm/xlnx-zynq Emulated CPU architecture support ================================= -- 2.34.1 From: Inès Varhol <ines.varhol@telecom-paris.fr> The QTest `test_irq_pin_multiplexer` makes the assumption that the reset state of irq line 15 is low, which is false since STM32L4x5 GPIO was implemented (the reset state of pin GPIOA15 is high because there's pull-up and it results in the irq line 15 also being high at reset). It wasn't triggering an error because `test_interrupt` was mistakenly "resetting" the line low. This commit corrects these two mistakes by : - not setting the line low in `test_interrupt` - using an irq line in `test_irq_pin_multiplexer` which is low at reset Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Message-id: 20240629104454.366283-1-ines.varhol@telecom-paris.fr Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/stm32l4x5_syscfg-test.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/tests/qtest/stm32l4x5_syscfg-test.c b/tests/qtest/stm32l4x5_syscfg-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/stm32l4x5_syscfg-test.c +++ b/tests/qtest/stm32l4x5_syscfg-test.c @@ -XXX,XX +XXX,XX @@ static void test_interrupt(void) /* Clean the test */ syscfg_writel(SYSCFG_EXTICR1, 0x00000000); syscfg_set_irq(0, 0); - syscfg_set_irq(15, 0); + /* irq 15 is high at reset because GPIOA15 is high at reset */ syscfg_set_irq(17, 0); } @@ -XXX,XX +XXX,XX @@ static void test_irq_pin_multiplexer(void) syscfg_set_irq(0, 1); - /* Check that irq 0 was set and irq 15 wasn't */ + /* Check that irq 0 was set and irq 2 wasn't */ g_assert_true(get_irq(0)); - g_assert_false(get_irq(15)); + g_assert_false(get_irq(2)); /* Clean the test */ syscfg_set_irq(0, 0); - syscfg_set_irq(15, 1); + syscfg_set_irq(2, 1); - /* Check that irq 15 was set and irq 0 wasn't */ - g_assert_true(get_irq(15)); + /* Check that irq 2 was set and irq 0 wasn't */ + g_assert_true(get_irq(2)); g_assert_false(get_irq(0)); /* Clean the test */ - syscfg_set_irq(15, 0); + syscfg_set_irq(2, 0); } static void test_irq_gpio_multiplexer(void) -- 2.34.1 From: Inès Varhol <ines.varhol@telecom-paris.fr> The implementation of configurable interrupts (interrupts supporting edge selection) was incorrectly expecting alternating input levels : this commits adds a new status field `irq_levels` to actually detect edges. Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Message-id: 20240629110800.539969-2-ines.varhol@telecom-paris.fr Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/stm32l4x5_exti.h | 2 ++ hw/misc/stm32l4x5_exti.c | 28 +++++++++++++--------------- 2 files changed, 15 insertions(+), 15 deletions(-) diff --git a/include/hw/misc/stm32l4x5_exti.h b/include/hw/misc/stm32l4x5_exti.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/stm32l4x5_exti.h +++ b/include/hw/misc/stm32l4x5_exti.h @@ -XXX,XX +XXX,XX @@ struct Stm32l4x5ExtiState { uint32_t swier[EXTI_NUM_REGISTER]; uint32_t pr[EXTI_NUM_REGISTER]; + /* used for edge detection */ + uint32_t irq_levels[EXTI_NUM_REGISTER]; qemu_irq irq[EXTI_NUM_INTERRUPT_OUT_LINES]; }; diff --git a/hw/misc/stm32l4x5_exti.c b/hw/misc/stm32l4x5_exti.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/stm32l4x5_exti.c +++ b/hw/misc/stm32l4x5_exti.c @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_exti_reset_hold(Object *obj, ResetType type) s->ftsr[bank] = 0x00000000; s->swier[bank] = 0x00000000; s->pr[bank] = 0x00000000; + s->irq_levels[bank] = 0x00000000; } } @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_exti_set_irq(void *opaque, int irq, int level) /* Shift the value to enable access in x2 registers. */ irq %= EXTI_MAX_IRQ_PER_BANK; + if (level == extract32(s->irq_levels[bank], irq, 1)) { + /* No change in IRQ line state: do nothing */ + return; + } + s->irq_levels[bank] = deposit32(s->irq_levels[bank], irq, 1, level); + /* If the interrupt is masked, pr won't be raised */ if (!extract32(s->imr[bank], irq, 1)) { return; } - if (((1 << irq) & s->rtsr[bank]) && level) { - /* Rising Edge */ - s->pr[bank] |= 1 << irq; - qemu_irq_pulse(s->irq[oirq]); - } else if (((1 << irq) & s->ftsr[bank]) && !level) { - /* Falling Edge */ + if ((level && extract32(s->rtsr[bank], irq, 1)) || + (!level && extract32(s->ftsr[bank], irq, 1))) { + s->pr[bank] |= 1 << irq; qemu_irq_pulse(s->irq[oirq]); } - /* - * In the following situations : - * - falling edge but rising trigger selected - * - rising edge but falling trigger selected - * - no trigger selected - * No action is required - */ } static uint64_t stm32l4x5_exti_read(void *opaque, hwaddr addr, @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_exti_init(Object *obj) static const VMStateDescription vmstate_stm32l4x5_exti = { .name = TYPE_STM32L4X5_EXTI, - .version_id = 1, - .minimum_version_id = 1, + .version_id = 2, + .minimum_version_id = 2, .fields = (VMStateField[]) { VMSTATE_UINT32_ARRAY(imr, Stm32l4x5ExtiState, EXTI_NUM_REGISTER), VMSTATE_UINT32_ARRAY(emr, Stm32l4x5ExtiState, EXTI_NUM_REGISTER), @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_stm32l4x5_exti = { VMSTATE_UINT32_ARRAY(ftsr, Stm32l4x5ExtiState, EXTI_NUM_REGISTER), VMSTATE_UINT32_ARRAY(swier, Stm32l4x5ExtiState, EXTI_NUM_REGISTER), VMSTATE_UINT32_ARRAY(pr, Stm32l4x5ExtiState, EXTI_NUM_REGISTER), + VMSTATE_UINT32_ARRAY(irq_levels, Stm32l4x5ExtiState, EXTI_NUM_REGISTER), VMSTATE_END_OF_LIST() } }; -- 2.34.1 From: Inès Varhol <ines.varhol@telecom-paris.fr> EXTI's new field `irq_levels` tracks irq levels between tests when using `global_qtest`. This happens in `stm32l4x5_exti-test.c`, `stm32l4x5_syscfg-test.c` and `stm32l4x5_gpio-test.c` (`dm163.c` doesn't use `global_qtest`). To ensure that `irq_levels` has the same value before and after each QTest, this commit toggles back the irq lines that were changed at the end of each problematic test. Most QTests were already doing this. Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Message-id: 20240629110800.539969-3-ines.varhol@telecom-paris.fr Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/stm32l4x5_exti-test.c | 8 ++++++++ tests/qtest/stm32l4x5_syscfg-test.c | 2 +- 2 files changed, 9 insertions(+), 1 deletion(-) diff --git a/tests/qtest/stm32l4x5_exti-test.c b/tests/qtest/stm32l4x5_exti-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/stm32l4x5_exti-test.c +++ b/tests/qtest/stm32l4x5_exti-test.c @@ -XXX,XX +XXX,XX @@ static void test_masked_interrupt(void) g_assert_cmphex(exti_readl(EXTI_PR1), ==, 0x00000000); /* Check that the interrupt isn't pending in NVIC */ g_assert_false(check_nvic_pending(EXTI1_IRQ)); + + /* Clean EXTI */ + exti_set_irq(1, 0); } static void test_interrupt(void) @@ -XXX,XX +XXX,XX @@ static void test_interrupt(void) /* Clean NVIC */ unpend_nvic_irq(EXTI1_IRQ); g_assert_false(check_nvic_pending(EXTI1_IRQ)); + + /* Clean EXTI */ + exti_set_irq(1, 0); } static void test_orred_interrupts(void) @@ -XXX,XX +XXX,XX @@ static void test_orred_interrupts(void) unpend_nvic_irq(EXTI5_9_IRQ); g_assert_false(check_nvic_pending(EXTI5_9_IRQ)); + + exti_set_irq(i, 0); } } diff --git a/tests/qtest/stm32l4x5_syscfg-test.c b/tests/qtest/stm32l4x5_syscfg-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/stm32l4x5_syscfg-test.c +++ b/tests/qtest/stm32l4x5_syscfg-test.c @@ -XXX,XX +XXX,XX @@ static void test_interrupt(void) g_assert_true(get_irq(1)); /* Clean the test */ - syscfg_writel(SYSCFG_EXTICR1, 0x00000000); syscfg_set_irq(0, 0); /* irq 15 is high at reset because GPIOA15 is high at reset */ syscfg_set_irq(17, 0); + syscfg_writel(SYSCFG_EXTICR1, 0x00000000); } static void test_irq_pin_multiplexer(void) -- 2.34.1 The following changes since commit 131c58469f6fb68c89b38fee6aba8bbb20c7f4bf: rust: add --rust-target option for bindgen (2025-02-06 13:51:46 -0500) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20250210 for you to fetch changes up to 27a8d899c7a100fd5aa040a8b993bb257687c393: linux-user: Do not define struct sched_attr if libc headers do (2025-02-07 16:09:20 +0000) ---------------------------------------------------------------- target-arm queue: * Deprecate pxa2xx CPUs, iwMMXt emulation, -old-param option * Drop unused AArch64DecodeTable typedefs * Minor code cleanups * hw/net/cadence_gem: Fix the mask/compare/disable-mask logic * linux-user: Do not define struct sched_attr if libc headers do ---------------------------------------------------------------- Andrew Yuan (1): hw/net/cadence_gem: Fix the mask/compare/disable-mask logic Khem Raj (1): linux-user: Do not define struct sched_attr if libc headers do Peter Maydell (4): target/arm: deprecate the pxa2xx CPUs and iwMMXt emulation tests/tcg/arm: Remove test-arm-iwmmxt test target/arm: Drop unused AArch64DecodeTable typedefs qemu-options: Deprecate -old-param command line option Philippe Mathieu-Daudé (6): hw/arm/boot: Propagate vCPU to arm_load_dtb() hw/arm/fsl-imx6: Add local 'mpcore/gic' variables hw/arm/fsl-imx6ul: Add local 'mpcore/gic' variables hw/arm/fsl-imx7: Add local 'mpcore/gic' variables hw/cpu/arm: Alias 'num-cpu' property on TYPE_REALVIEW_MPCORE hw/cpu/arm: Declare CPU QOM types using DEFINE_TYPES() macro docs/about/deprecated.rst | 34 ++++++++++++++++++++++ include/hw/arm/boot.h | 4 ++- target/arm/cpu.h | 1 + hw/arm/boot.c | 11 +++---- hw/arm/fsl-imx6.c | 52 ++++++++++++++------------------- hw/arm/fsl-imx6ul.c | 64 +++++++++++++++++------------------------ hw/arm/fsl-imx7.c | 52 +++++++++++++++------------------ hw/arm/virt.c | 2 +- hw/cpu/a15mpcore.c | 21 ++++++-------- hw/cpu/a9mpcore.c | 21 ++++++-------- hw/cpu/arm11mpcore.c | 21 ++++++-------- hw/cpu/realview_mpcore.c | 29 +++++++------------ hw/net/cadence_gem.c | 26 +++++++++++++---- linux-user/syscall.c | 4 ++- system/vl.c | 1 + target/arm/cpu.c | 3 ++ target/arm/tcg/cpu32.c | 36 +++++++++++++++-------- target/arm/tcg/translate-a64.c | 11 ------- tests/tcg/arm/Makefile.target | 7 ----- tests/tcg/arm/README | 5 ---- tests/tcg/arm/test-arm-iwmmxt.S | 49 ------------------------------- 21 files changed, 205 insertions(+), 249 deletions(-) delete mode 100644 tests/tcg/arm/test-arm-iwmmxt.S The pxa2xx CPUs are now only useful with user-mode emulation, because we dropped all the machine types that used them in 9.2. (Technically you could alse use "-cpu pxa270" with a board model like versatilepb which doesn't sanity-check the CPU type, but that has never been a supported config.) To use them (or iwMMXt emulation) with QEMU user-mode you would need to explicitly select them with the -cpu option or the QEMU_CPU environment variable. A google search finds no examples of anybody doing this in the last decade; I don't believe the GCC folks are using QEMU to test their iwMMXt codegen either. In fact, GCC is in the process of dropping support for iwMMXT entirely. The iwMMXt emulation is thousands of lines of code in QEMU, and is now the only bit of Arm insn decode which doesn't use decodetree. We have no way to test or validate changes to it. This code is just dead weight that is almost certainly not being used by anybody. Mark it as deprecated. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20250127112715.2936555-2-peter.maydell@linaro.org --- docs/about/deprecated.rst | 21 +++++++++++++++++++++ target/arm/cpu.h | 1 + target/arm/cpu.c | 3 +++ target/arm/tcg/cpu32.c | 36 ++++++++++++++++++++++++------------ 4 files changed, 49 insertions(+), 12 deletions(-) diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -XXX,XX +XXX,XX @@ is going to be so much slower it wouldn't make sense for any serious instrumentation. Due to implementation differences there will also be anomalies in things like memory instrumentation. +linux-user mode CPUs +-------------------- + +iwMMXt emulation and the ``pxa`` CPUs (since 10.0) +'''''''''''''''''''''''''''''''''''''''''''''''''' + +The ``pxa`` CPU family (``pxa250``, ``pxa255``, ``pxa260``, +``pxa261``, ``pxa262``, ``pxa270-a0``, ``pxa270-a1``, ``pxa270``, +``pxa270-b0``, ``pxa270-b1``, ``pxa270-c0``, ``pxa270-c5``) are no +longer used in system emulation, because all the machine types which +used these CPUs were removed in the QEMU 9.2 release. These CPUs can +now only be used in linux-user mode, and to do that you would have to +explicitly select one of these CPUs with the ``-cpu`` command line +option or the ``QEMU_CPU`` environment variable. + +We don't believe that anybody is using the iwMMXt emulation, and we do +not have any tests to validate it or any real hardware or similar +known-good implementation to test against. GCC is in the process of +dropping their support for iwMMXt codegen. These CPU types are +therefore deprecated in QEMU, and will be removed in a future release. + System emulator CPUs -------------------- diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ struct ArchCPU { typedef struct ARMCPUInfo { const char *name; + const char *deprecation_note; void (*initfn)(Object *obj); void (*class_init)(ObjectClass *oc, void *data); } ARMCPUInfo; 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 cpu_register_class_init(ObjectClass *oc, void *data) acc->info = data; cc->gdb_core_xml_file = "arm-core.xml"; + if (acc->info->deprecation_note) { + cc->deprecation_note = acc->info->deprecation_note; + } } void arm_cpu_register(const ARMCPUInfo *info) diff --git a/target/arm/tcg/cpu32.c b/target/arm/tcg/cpu32.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/cpu32.c +++ b/target/arm/tcg/cpu32.c @@ -XXX,XX +XXX,XX @@ static const ARMCPUInfo arm_tcg_cpus[] = { { .name = "ti925t", .initfn = ti925t_initfn }, { .name = "sa1100", .initfn = sa1100_initfn }, { .name = "sa1110", .initfn = sa1110_initfn }, - { .name = "pxa250", .initfn = pxa250_initfn }, - { .name = "pxa255", .initfn = pxa255_initfn }, - { .name = "pxa260", .initfn = pxa260_initfn }, - { .name = "pxa261", .initfn = pxa261_initfn }, - { .name = "pxa262", .initfn = pxa262_initfn }, + { .name = "pxa250", .initfn = pxa250_initfn, + .deprecation_note = "iwMMXt CPUs are no longer supported", }, + { .name = "pxa255", .initfn = pxa255_initfn, + .deprecation_note = "iwMMXt CPUs are no longer supported", }, + { .name = "pxa260", .initfn = pxa260_initfn, + .deprecation_note = "iwMMXt CPUs are no longer supported", }, + { .name = "pxa261", .initfn = pxa261_initfn, + .deprecation_note = "iwMMXt CPUs are no longer supported", }, + { .name = "pxa262", .initfn = pxa262_initfn, + .deprecation_note = "iwMMXt CPUs are no longer supported", }, /* "pxa270" is an alias for "pxa270-a0" */ - { .name = "pxa270", .initfn = pxa270a0_initfn }, - { .name = "pxa270-a0", .initfn = pxa270a0_initfn }, - { .name = "pxa270-a1", .initfn = pxa270a1_initfn }, - { .name = "pxa270-b0", .initfn = pxa270b0_initfn }, - { .name = "pxa270-b1", .initfn = pxa270b1_initfn }, - { .name = "pxa270-c0", .initfn = pxa270c0_initfn }, - { .name = "pxa270-c5", .initfn = pxa270c5_initfn }, + { .name = "pxa270", .initfn = pxa270a0_initfn, + .deprecation_note = "iwMMXt CPUs are no longer supported", }, + { .name = "pxa270-a0", .initfn = pxa270a0_initfn, + .deprecation_note = "iwMMXt CPUs are no longer supported", }, + { .name = "pxa270-a1", .initfn = pxa270a1_initfn, + .deprecation_note = "iwMMXt CPUs are no longer supported", }, + { .name = "pxa270-b0", .initfn = pxa270b0_initfn, + .deprecation_note = "iwMMXt CPUs are no longer supported", }, + { .name = "pxa270-b1", .initfn = pxa270b1_initfn, + .deprecation_note = "iwMMXt CPUs are no longer supported", }, + { .name = "pxa270-c0", .initfn = pxa270c0_initfn, + .deprecation_note = "iwMMXt CPUs are no longer supported", }, + { .name = "pxa270-c5", .initfn = pxa270c5_initfn, + .deprecation_note = "iwMMXt CPUs are no longer supported", }, #ifndef TARGET_AARCH64 { .name = "max", .initfn = arm_max_initfn }, #endif -- 2.34.1 The test-arm-iwmmmxt test isn't testing what it thinks it's testing. If you run it with a CPU type that supports iwMMXt then it will crash immediately with a SIGILL, because (even with -marm) GCC will link it against startup code that is in Thumb mode, and no iwMMXt CPU has Thumb: 00010338 <_start>: 10338: f04f 0b00 mov.w fp, #0 1033c: f04f 0e00 mov.w lr, #0 If you run it with a CPU type which does *not* support iwMMXt, which is what 'make check-tcg' does, then QEMU will not try to handle the insns as iwMMXt. Instead the translator turns them into illegal instructions. Then in the linux-user cpu_loop() code we identify them as FPA11 instructions inside emulate_arm_fpa11(), because the FPA11 happened to use the same coprocessor number as these iwMMXt insns. So we execute a completely different set of FPA11 insns, which means we don't crash, but we will print garbage to stdout. Then the test binary always exits with a 0 return code, so 'make check-tcg' thinks the test passes. Modern gnueabihf toolchains assume in their startup code that the CPU is not so old as to not support Thumb, so there's no way to get them to generate a binary that actually does what the test wants. Since we're deprecating iwMMXt emulation anyway, it's not worth trying to salvage the test case to get it to really test the iwMMXt insns. Delete the test entirely. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20250127112715.2936555-3-peter.maydell@linaro.org --- tests/tcg/arm/Makefile.target | 7 ----- tests/tcg/arm/README | 5 ---- tests/tcg/arm/test-arm-iwmmxt.S | 49 --------------------------------- 3 files changed, 61 deletions(-) delete mode 100644 tests/tcg/arm/test-arm-iwmmxt.S diff --git a/tests/tcg/arm/Makefile.target b/tests/tcg/arm/Makefile.target index XXXXXXX..XXXXXXX 100644 --- a/tests/tcg/arm/Makefile.target +++ b/tests/tcg/arm/Makefile.target @@ -XXX,XX +XXX,XX @@ ARM_TESTS = hello-arm hello-arm: CFLAGS+=-marm -ffreestanding -fno-stack-protector hello-arm: LDFLAGS+=-nostdlib -# IWMXT floating point extensions -ARM_TESTS += test-arm-iwmmxt -# Clang assembler does not support IWMXT, so use the external assembler. -test-arm-iwmmxt: CFLAGS += -marm -march=iwmmxt -mabi=aapcs -mfpu=fpv4-sp-d16 $(CROSS_CC_HAS_FNIA) -test-arm-iwmmxt: test-arm-iwmmxt.S - $(CC) $(CFLAGS) -Wa,--noexecstack $< -o $@ $(LDFLAGS) - # Float-convert Tests ARM_TESTS += fcvt fcvt: LDFLAGS += -lm diff --git a/tests/tcg/arm/README b/tests/tcg/arm/README index XXXXXXX..XXXXXXX 100644 --- a/tests/tcg/arm/README +++ b/tests/tcg/arm/README @@ -XXX,XX +XXX,XX @@ hello-arm --------- A very simple inline assembly, write syscall based hello world - -test-arm-iwmmxt ---------------- - -A simple test case for older iwmmxt extended ARMs diff --git a/tests/tcg/arm/test-arm-iwmmxt.S b/tests/tcg/arm/test-arm-iwmmxt.S deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/tests/tcg/arm/test-arm-iwmmxt.S +++ /dev/null @@ -XXX,XX +XXX,XX @@ -@ Checks whether iwMMXt is functional. -.code 32 -.globl main - -main: -ldr r0, =data0 -ldr r1, =data1 -ldr r2, =data2 -#ifndef FPA -wldrd wr0, [r0, #0] -wldrd wr1, [r0, #8] -wldrd wr2, [r1, #0] -wldrd wr3, [r1, #8] -wsubb wr2, wr2, wr0 -wsubb wr3, wr3, wr1 -wldrd wr0, [r2, #0] -wldrd wr1, [r2, #8] -waddb wr0, wr0, wr2 -waddb wr1, wr1, wr3 -wstrd wr0, [r2, #0] -wstrd wr1, [r2, #8] -#else -ldfe f0, [r0, #0] -ldfe f1, [r0, #8] -ldfe f2, [r1, #0] -ldfe f3, [r1, #8] -adfdp f2, f2, f0 -adfdp f3, f3, f1 -ldfe f0, [r2, #0] -ldfe f1, [r2, #8] -adfd f0, f0, f2 -adfd f1, f1, f3 -stfe f0, [r2, #0] -stfe f1, [r2, #8] -#endif -mov r0, #1 -mov r1, r2 -mov r2, #0x11 -swi #0x900004 -mov r0, #0 -swi #0x900001 - -.data -data0: -.string "aaaabbbbccccdddd" -data1: -.string "bbbbccccddddeeee" -data2: -.string "hvLLWs\x1fsdrs9\x1fNJ-\n" -- 2.34.1 We removed the old table-based decoder in favour of decodetree, but we left a couple of typedefs that are now unused; delete them. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250128135046.4108775-1-peter.maydell@linaro.org --- target/arm/tcg/translate-a64.c | 11 ----------- 1 file changed, 11 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static int scale_by_log2_tag_granule(DisasContext *s, int x) #include "decode-sme-fa64.c.inc" #include "decode-a64.c.inc" -/* Table based decoder typedefs - used when the relevant bits for decode - * are too awkwardly scattered across the instruction (eg SIMD). - */ -typedef void AArch64DecodeFn(DisasContext *s, uint32_t insn); - -typedef struct AArch64DecodeTable { - uint32_t pattern; - uint32_t mask; - AArch64DecodeFn *disas_fn; -} AArch64DecodeTable; - /* initialize TCG globals. */ void a64_translate_init(void) { -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> In heterogeneous setup the first vCPU might not be the one expected, better pass it explicitly. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Cédric Le Goater <clg@kaod.org> Message-id: 20250130112615.3219-2-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/boot.h | 4 +++- hw/arm/boot.c | 11 ++++++----- hw/arm/virt.c | 2 +- 3 files changed, 10 insertions(+), 7 deletions(-) diff --git a/include/hw/arm/boot.h b/include/hw/arm/boot.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/boot.h +++ b/include/hw/arm/boot.h @@ -XXX,XX +XXX,XX @@ AddressSpace *arm_boot_address_space(ARMCPU *cpu, * @binfo: struct describing the boot environment * @addr_limit: upper limit of the available memory area at @addr * @as: address space to load image to + * @cpu: ARM CPU object * * Load a device tree supplied by the machine or by the user with the * '-dtb' command line option, and put it at offset @addr in target @@ -XXX,XX +XXX,XX @@ AddressSpace *arm_boot_address_space(ARMCPU *cpu, * Note: Must not be called unless have_dtb(binfo) is true. */ int arm_load_dtb(hwaddr addr, const struct arm_boot_info *binfo, - hwaddr addr_limit, AddressSpace *as, MachineState *ms); + hwaddr addr_limit, AddressSpace *as, MachineState *ms, + ARMCPU *cpu); /* Write a secure board setup routine with a dummy handler for SMCs */ void arm_write_secure_board_setup_dummy_smc(ARMCPU *cpu, diff --git a/hw/arm/boot.c b/hw/arm/boot.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/boot.c +++ b/hw/arm/boot.c @@ -XXX,XX +XXX,XX @@ out: return ret; } -static void fdt_add_psci_node(void *fdt) +static void fdt_add_psci_node(void *fdt, ARMCPU *armcpu) { uint32_t cpu_suspend_fn; uint32_t cpu_off_fn; uint32_t cpu_on_fn; uint32_t migrate_fn; - ARMCPU *armcpu = ARM_CPU(qemu_get_cpu(0)); const char *psci_method; int64_t psci_conduit; int rc; @@ -XXX,XX +XXX,XX @@ static void fdt_add_psci_node(void *fdt) } int arm_load_dtb(hwaddr addr, const struct arm_boot_info *binfo, - hwaddr addr_limit, AddressSpace *as, MachineState *ms) + hwaddr addr_limit, AddressSpace *as, MachineState *ms, + ARMCPU *cpu) { void *fdt = NULL; int size, rc, n = 0; @@ -XXX,XX +XXX,XX @@ int arm_load_dtb(hwaddr addr, const struct arm_boot_info *binfo, } } - fdt_add_psci_node(fdt); + fdt_add_psci_node(fdt, cpu); if (binfo->modify_dtb) { binfo->modify_dtb(binfo, fdt); @@ -XXX,XX +XXX,XX @@ void arm_load_kernel(ARMCPU *cpu, MachineState *ms, struct arm_boot_info *info) * decided whether to enable PSCI and set the psci-conduit CPU properties. */ if (!info->skip_dtb_autoload && have_dtb(info)) { - if (arm_load_dtb(info->dtb_start, info, info->dtb_limit, as, ms) < 0) { + if (arm_load_dtb(info->dtb_start, info, info->dtb_limit, + as, ms, cpu) < 0) { exit(1); } } diff --git a/hw/arm/virt.c b/hw/arm/virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/virt.c +++ b/hw/arm/virt.c @@ -XXX,XX +XXX,XX @@ void virt_machine_done(Notifier *notifier, void *data) vms->memmap[VIRT_PLATFORM_BUS].size, vms->irqmap[VIRT_PLATFORM_BUS]); } - if (arm_load_dtb(info->dtb_start, info, info->dtb_limit, as, ms) < 0) { + if (arm_load_dtb(info->dtb_start, info, info->dtb_limit, as, ms, cpu) < 0) { exit(1); } -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> The A9MPCore forward the IRQs from its internal GIC. To make the code clearer, add the 'mpcore' and 'gic' variables. Reviewed-by: Cédric Le Goater <clg@kaod.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20250130112615.3219-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx6.c | 52 +++++++++++++++++++---------------------------- 1 file changed, 21 insertions(+), 31 deletions(-) diff --git a/hw/arm/fsl-imx6.c b/hw/arm/fsl-imx6.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx6.c +++ b/hw/arm/fsl-imx6.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp) uint16_t i; qemu_irq irq; unsigned int smp_cpus = ms->smp.cpus; + DeviceState *mpcore = DEVICE(&s->a9mpcore); + DeviceState *gic; if (smp_cpus > FSL_IMX6_NUM_CPUS) { error_setg(errp, "%s: Only %d CPUs are supported (%d requested)", @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp) } } - object_property_set_int(OBJECT(&s->a9mpcore), "num-cpu", smp_cpus, - &error_abort); + object_property_set_int(OBJECT(mpcore), "num-cpu", smp_cpus, &error_abort); - object_property_set_int(OBJECT(&s->a9mpcore), "num-irq", + object_property_set_int(OBJECT(mpcore), "num-irq", FSL_IMX6_MAX_IRQ + GIC_INTERNAL, &error_abort); - if (!sysbus_realize(SYS_BUS_DEVICE(&s->a9mpcore), errp)) { + if (!sysbus_realize(SYS_BUS_DEVICE(mpcore), errp)) { return; } - sysbus_mmio_map(SYS_BUS_DEVICE(&s->a9mpcore), 0, FSL_IMX6_A9MPCORE_ADDR); + sysbus_mmio_map(SYS_BUS_DEVICE(mpcore), 0, FSL_IMX6_A9MPCORE_ADDR); + gic = mpcore; for (i = 0; i < smp_cpus; i++) { - sysbus_connect_irq(SYS_BUS_DEVICE(&s->a9mpcore), i, + sysbus_connect_irq(SYS_BUS_DEVICE(gic), i, qdev_get_gpio_in(DEVICE(&s->cpu[i]), ARM_CPU_IRQ)); - sysbus_connect_irq(SYS_BUS_DEVICE(&s->a9mpcore), i + smp_cpus, + sysbus_connect_irq(SYS_BUS_DEVICE(gic), i + smp_cpus, qdev_get_gpio_in(DEVICE(&s->cpu[i]), ARM_CPU_FIQ)); } @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->uart[i]), 0, serial_table[i].addr); sysbus_connect_irq(SYS_BUS_DEVICE(&s->uart[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a9mpcore), - serial_table[i].irq)); + qdev_get_gpio_in(gic, serial_table[i].irq)); } s->gpt.ccm = IMX_CCM(&s->ccm); @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpt), 0, FSL_IMX6_GPT_ADDR); sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpt), 0, - qdev_get_gpio_in(DEVICE(&s->a9mpcore), - FSL_IMX6_GPT_IRQ)); + qdev_get_gpio_in(gic, FSL_IMX6_GPT_IRQ)); /* Initialize all EPIT timers */ for (i = 0; i < FSL_IMX6_NUM_EPITS; i++) { @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->epit[i]), 0, epit_table[i].addr); sysbus_connect_irq(SYS_BUS_DEVICE(&s->epit[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a9mpcore), - epit_table[i].irq)); + qdev_get_gpio_in(gic, epit_table[i].irq)); } /* Initialize all I2C */ @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c[i]), 0, i2c_table[i].addr); sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a9mpcore), - i2c_table[i].irq)); + qdev_get_gpio_in(gic, i2c_table[i].irq)); } /* Initialize all GPIOs */ @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpio[i]), 0, gpio_table[i].addr); sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a9mpcore), - gpio_table[i].irq_low)); + qdev_get_gpio_in(gic, gpio_table[i].irq_low)); sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio[i]), 1, - qdev_get_gpio_in(DEVICE(&s->a9mpcore), - gpio_table[i].irq_high)); + qdev_get_gpio_in(gic, gpio_table[i].irq_high)); } /* Initialize all SDHC */ @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp) } sysbus_mmio_map(SYS_BUS_DEVICE(&s->esdhc[i]), 0, esdhc_table[i].addr); sysbus_connect_irq(SYS_BUS_DEVICE(&s->esdhc[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a9mpcore), - esdhc_table[i].irq)); + qdev_get_gpio_in(gic, esdhc_table[i].irq)); } /* USB */ @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->usb[i]), 0, FSL_IMX6_USBOH3_USB_ADDR + i * 0x200); sysbus_connect_irq(SYS_BUS_DEVICE(&s->usb[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a9mpcore), - FSL_IMX6_USBn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX6_USBn_IRQ[i])); } /* Initialize all ECSPI */ @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->spi[i]), 0, spi_table[i].addr); sysbus_connect_irq(SYS_BUS_DEVICE(&s->spi[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a9mpcore), - spi_table[i].irq)); + qdev_get_gpio_in(gic, spi_table[i].irq)); } object_property_set_uint(OBJECT(&s->eth), "phy-num", s->phy_num, @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp) } sysbus_mmio_map(SYS_BUS_DEVICE(&s->eth), 0, FSL_IMX6_ENET_ADDR); sysbus_connect_irq(SYS_BUS_DEVICE(&s->eth), 0, - qdev_get_gpio_in(DEVICE(&s->a9mpcore), - FSL_IMX6_ENET_MAC_IRQ)); + qdev_get_gpio_in(gic, FSL_IMX6_ENET_MAC_IRQ)); sysbus_connect_irq(SYS_BUS_DEVICE(&s->eth), 1, - qdev_get_gpio_in(DEVICE(&s->a9mpcore), - FSL_IMX6_ENET_MAC_1588_IRQ)); + qdev_get_gpio_in(gic, FSL_IMX6_ENET_MAC_1588_IRQ)); /* * SNVS @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->wdt[i]), 0, FSL_IMX6_WDOGn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->wdt[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a9mpcore), - FSL_IMX6_WDOGn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX6_WDOGn_IRQ[i])); } /* -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> The A7MPCore forward the IRQs from its internal GIC. To make the code clearer, add the 'mpcore' and 'gic' variables. Rename 'd' variable as 'cpu'. Reviewed-by: Cédric Le Goater <clg@kaod.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20250130112615.3219-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx6ul.c | 64 +++++++++++++++++++-------------------------- 1 file changed, 27 insertions(+), 37 deletions(-) diff --git a/hw/arm/fsl-imx6ul.c b/hw/arm/fsl-imx6ul.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx6ul.c +++ b/hw/arm/fsl-imx6ul.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) { MachineState *ms = MACHINE(qdev_get_machine()); FslIMX6ULState *s = FSL_IMX6UL(dev); + DeviceState *mpcore = DEVICE(&s->a7mpcore); int i; char name[NAME_SIZE]; - SysBusDevice *sbd; - DeviceState *d; + DeviceState *gic; + SysBusDevice *gicsbd; + DeviceState *cpu; if (ms->smp.cpus > 1) { error_setg(errp, "%s: Only a single CPU is supported (%d requested)", @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) /* * A7MPCORE */ - object_property_set_int(OBJECT(&s->a7mpcore), "num-cpu", 1, &error_abort); - object_property_set_int(OBJECT(&s->a7mpcore), "num-irq", + object_property_set_int(OBJECT(mpcore), "num-cpu", 1, &error_abort); + object_property_set_int(OBJECT(mpcore), "num-irq", FSL_IMX6UL_MAX_IRQ + GIC_INTERNAL, &error_abort); - sysbus_realize(SYS_BUS_DEVICE(&s->a7mpcore), &error_abort); - sysbus_mmio_map(SYS_BUS_DEVICE(&s->a7mpcore), 0, FSL_IMX6UL_A7MPCORE_ADDR); + sysbus_realize(SYS_BUS_DEVICE(mpcore), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(mpcore), 0, FSL_IMX6UL_A7MPCORE_ADDR); - sbd = SYS_BUS_DEVICE(&s->a7mpcore); - d = DEVICE(&s->cpu); - - sysbus_connect_irq(sbd, 0, qdev_get_gpio_in(d, ARM_CPU_IRQ)); - sysbus_connect_irq(sbd, 1, qdev_get_gpio_in(d, ARM_CPU_FIQ)); - sysbus_connect_irq(sbd, 2, qdev_get_gpio_in(d, ARM_CPU_VIRQ)); - sysbus_connect_irq(sbd, 3, qdev_get_gpio_in(d, ARM_CPU_VFIQ)); + gic = mpcore; + gicsbd = SYS_BUS_DEVICE(gic); + cpu = DEVICE(&s->cpu); + sysbus_connect_irq(gicsbd, 0, qdev_get_gpio_in(cpu, ARM_CPU_IRQ)); + sysbus_connect_irq(gicsbd, 1, qdev_get_gpio_in(cpu, ARM_CPU_FIQ)); + sysbus_connect_irq(gicsbd, 2, qdev_get_gpio_in(cpu, ARM_CPU_VIRQ)); + sysbus_connect_irq(gicsbd, 3, qdev_get_gpio_in(cpu, ARM_CPU_VFIQ)); /* * A7MPCORE DAP @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) FSL_IMX6UL_GPTn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpt[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX6UL_GPTn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX6UL_GPTn_IRQ[i])); } /* @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) FSL_IMX6UL_EPITn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->epit[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX6UL_EPITn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX6UL_EPITn_IRQ[i])); } /* @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) FSL_IMX6UL_GPIOn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX6UL_GPIOn_LOW_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX6UL_GPIOn_LOW_IRQ[i])); sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio[i]), 1, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX6UL_GPIOn_HIGH_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX6UL_GPIOn_HIGH_IRQ[i])); } /* @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) FSL_IMX6UL_SPIn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->spi[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX6UL_SPIn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX6UL_SPIn_IRQ[i])); } /* @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c[i]), 0, FSL_IMX6UL_I2Cn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX6UL_I2Cn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX6UL_I2Cn_IRQ[i])); } /* @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) FSL_IMX6UL_UARTn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->uart[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX6UL_UARTn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX6UL_UARTn_IRQ[i])); } /* @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) FSL_IMX6UL_ENETn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->eth[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX6UL_ENETn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX6UL_ENETn_IRQ[i])); sysbus_connect_irq(SYS_BUS_DEVICE(&s->eth[i]), 1, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX6UL_ENETn_TIMER_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX6UL_ENETn_TIMER_IRQ[i])); } /* @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->usb[i]), 0, FSL_IMX6UL_USB02_USBn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->usb[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX6UL_USBn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX6UL_USBn_IRQ[i])); } /* @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) FSL_IMX6UL_USDHCn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->usdhc[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX6UL_USDHCn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX6UL_USDHCn_IRQ[i])); } /* @@ -XXX,XX +XXX,XX @@ static void fsl_imx6ul_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->wdt[i]), 0, FSL_IMX6UL_WDOGn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->wdt[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX6UL_WDOGn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX6UL_WDOGn_IRQ[i])); } /* -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> The A7MPCore forward the IRQs from its internal GIC. To make the code clearer, add the 'mpcore' and 'gic' variables. Reviewed-by: Cédric Le Goater <clg@kaod.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20250130112615.3219-5-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/fsl-imx7.c | 52 +++++++++++++++++++++-------------------------- 1 file changed, 23 insertions(+), 29 deletions(-) diff --git a/hw/arm/fsl-imx7.c b/hw/arm/fsl-imx7.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx7.c +++ b/hw/arm/fsl-imx7.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) { MachineState *ms = MACHINE(qdev_get_machine()); FslIMX7State *s = FSL_IMX7(dev); - Object *o; + DeviceState *mpcore = DEVICE(&s->a7mpcore); + DeviceState *gic; int i; qemu_irq irq; char name[NAME_SIZE]; @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) * CPUs */ for (i = 0; i < smp_cpus; i++) { - o = OBJECT(&s->cpu[i]); + Object *o = OBJECT(&s->cpu[i]); /* On uniprocessor, the CBAR is set to 0 */ if (smp_cpus > 1) { @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) /* * A7MPCORE */ - object_property_set_int(OBJECT(&s->a7mpcore), "num-cpu", smp_cpus, - &error_abort); - object_property_set_int(OBJECT(&s->a7mpcore), "num-irq", + object_property_set_int(OBJECT(mpcore), "num-cpu", smp_cpus, &error_abort); + object_property_set_int(OBJECT(mpcore), "num-irq", FSL_IMX7_MAX_IRQ + GIC_INTERNAL, &error_abort); + sysbus_realize(SYS_BUS_DEVICE(mpcore), &error_abort); + sysbus_mmio_map(SYS_BUS_DEVICE(mpcore), 0, FSL_IMX7_A7MPCORE_ADDR); - sysbus_realize(SYS_BUS_DEVICE(&s->a7mpcore), &error_abort); - sysbus_mmio_map(SYS_BUS_DEVICE(&s->a7mpcore), 0, FSL_IMX7_A7MPCORE_ADDR); - + gic = mpcore; for (i = 0; i < smp_cpus; i++) { - SysBusDevice *sbd = SYS_BUS_DEVICE(&s->a7mpcore); + SysBusDevice *sbd = SYS_BUS_DEVICE(gic); DeviceState *d = DEVICE(qemu_get_cpu(i)); irq = qdev_get_gpio_in(d, ARM_CPU_IRQ); @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) sysbus_realize(SYS_BUS_DEVICE(&s->gpt[i]), &error_abort); sysbus_mmio_map(SYS_BUS_DEVICE(&s->gpt[i]), 0, FSL_IMX7_GPTn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpt[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX7_GPTn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX7_GPTn_IRQ[i])); } /* @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) FSL_IMX7_GPIOn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX7_GPIOn_LOW_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX7_GPIOn_LOW_IRQ[i])); sysbus_connect_irq(SYS_BUS_DEVICE(&s->gpio[i]), 1, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX7_GPIOn_HIGH_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX7_GPIOn_HIGH_IRQ[i])); } /* @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->spi[i]), 0, FSL_IMX7_SPIn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->spi[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX7_SPIn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX7_SPIn_IRQ[i])); } /* @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->i2c[i]), 0, FSL_IMX7_I2Cn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX7_I2Cn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX7_I2Cn_IRQ[i])); } /* @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->uart[i]), 0, FSL_IMX7_UARTn_ADDR[i]); - irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_UARTn_IRQ[i]); + irq = qdev_get_gpio_in(gic, FSL_IMX7_UARTn_IRQ[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->uart[i]), 0, irq); } @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->eth[i]), 0, FSL_IMX7_ENETn_ADDR[i]); - irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_ENET_IRQ(i, 0)); + irq = qdev_get_gpio_in(gic, FSL_IMX7_ENET_IRQ(i, 0)); sysbus_connect_irq(SYS_BUS_DEVICE(&s->eth[i]), 0, irq); - irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_ENET_IRQ(i, 3)); + irq = qdev_get_gpio_in(gic, FSL_IMX7_ENET_IRQ(i, 3)); sysbus_connect_irq(SYS_BUS_DEVICE(&s->eth[i]), 1, irq); } @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->usdhc[i]), 0, FSL_IMX7_USDHCn_ADDR[i]); - irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_USDHCn_IRQ[i]); + irq = qdev_get_gpio_in(gic, FSL_IMX7_USDHCn_IRQ[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->usdhc[i]), 0, irq); } @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->wdt[i]), 0, FSL_IMX7_WDOGn_ADDR[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->wdt[i]), 0, - qdev_get_gpio_in(DEVICE(&s->a7mpcore), - FSL_IMX7_WDOGn_IRQ[i])); + qdev_get_gpio_in(gic, FSL_IMX7_WDOGn_IRQ[i])); } /* @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_PCI_INTD_MSI_IRQ); qdev_connect_gpio_out(DEVICE(&s->pcie4_msi_irq), 0, irq); - irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_PCI_INTA_IRQ); + irq = qdev_get_gpio_in(gic, FSL_IMX7_PCI_INTA_IRQ); sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 0, irq); - irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_PCI_INTB_IRQ); + irq = qdev_get_gpio_in(gic, FSL_IMX7_PCI_INTB_IRQ); sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 1, irq); - irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_PCI_INTC_IRQ); + irq = qdev_get_gpio_in(gic, FSL_IMX7_PCI_INTC_IRQ); sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 2, irq); irq = qdev_get_gpio_in(DEVICE(&s->pcie4_msi_irq), 0); sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 3, irq); @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->usb[i]), 0, FSL_IMX7_USBn_ADDR[i]); - irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_USBn_IRQ[i]); + irq = qdev_get_gpio_in(gic, FSL_IMX7_USBn_IRQ[i]); sysbus_connect_irq(SYS_BUS_DEVICE(&s->usb[i]), 0, irq); snprintf(name, NAME_SIZE, "usbmisc%d", i); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> No need to duplicate and forward the 'num-cpu' property from TYPE_ARM11MPCORE_PRIV to TYPE_REALVIEW_MPCORE, alias it with QOM object_property_add_alias(). Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Cédric Le Goater <clg@kaod.org> Message-id: 20250130112615.3219-6-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/cpu/realview_mpcore.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/hw/cpu/realview_mpcore.c b/hw/cpu/realview_mpcore.c index XXXXXXX..XXXXXXX 100644 --- a/hw/cpu/realview_mpcore.c +++ b/hw/cpu/realview_mpcore.c @@ -XXX,XX +XXX,XX @@ #include "hw/cpu/arm11mpcore.h" #include "hw/intc/realview_gic.h" #include "hw/irq.h" -#include "hw/qdev-properties.h" #include "qom/object.h" #define TYPE_REALVIEW_MPCORE_RIRQ "realview_mpcore" @@ -XXX,XX +XXX,XX @@ static void realview_mpcore_realize(DeviceState *dev, Error **errp) int n; int i; - qdev_prop_set_uint32(priv, "num-cpu", s->num_cpu); if (!sysbus_realize(SYS_BUS_DEVICE(&s->priv), errp)) { return; } @@ -XXX,XX +XXX,XX @@ static void mpcore_rirq_init(Object *obj) int i; object_initialize_child(obj, "a11priv", &s->priv, TYPE_ARM11MPCORE_PRIV); + object_property_add_alias(obj, "num-cpu", OBJECT(&s->priv), "num-cpu"); privbusdev = SYS_BUS_DEVICE(&s->priv); sysbus_init_mmio(sbd, sysbus_mmio_get_region(privbusdev, 0)); @@ -XXX,XX +XXX,XX @@ static void mpcore_rirq_init(Object *obj) } } -static const Property mpcore_rirq_properties[] = { - DEFINE_PROP_UINT32("num-cpu", mpcore_rirq_state, num_cpu, 1), -}; - static void mpcore_rirq_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); dc->realize = realview_mpcore_realize; - device_class_set_props(dc, mpcore_rirq_properties); } static const TypeInfo mpcore_rirq_info = { -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> When multiple QOM types are registered in the same file, it is simpler to use the the DEFINE_TYPES() macro. In particular because type array declared with such macro are easier to review. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Cédric Le Goater <clg@kaod.org> Message-id: 20250130112615.3219-7-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/cpu/a15mpcore.c | 21 +++++++++------------ hw/cpu/a9mpcore.c | 21 +++++++++------------ hw/cpu/arm11mpcore.c | 21 +++++++++------------ hw/cpu/realview_mpcore.c | 21 +++++++++------------ 4 files changed, 36 insertions(+), 48 deletions(-) diff --git a/hw/cpu/a15mpcore.c b/hw/cpu/a15mpcore.c index XXXXXXX..XXXXXXX 100644 --- a/hw/cpu/a15mpcore.c +++ b/hw/cpu/a15mpcore.c @@ -XXX,XX +XXX,XX @@ static void a15mp_priv_class_init(ObjectClass *klass, void *data) /* We currently have no saveable state */ } -static const TypeInfo a15mp_priv_info = { - .name = TYPE_A15MPCORE_PRIV, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(A15MPPrivState), - .instance_init = a15mp_priv_initfn, - .class_init = a15mp_priv_class_init, +static const TypeInfo a15mp_types[] = { + { + .name = TYPE_A15MPCORE_PRIV, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(A15MPPrivState), + .instance_init = a15mp_priv_initfn, + .class_init = a15mp_priv_class_init, + }, }; -static void a15mp_register_types(void) -{ - type_register_static(&a15mp_priv_info); -} - -type_init(a15mp_register_types) +DEFINE_TYPES(a15mp_types) diff --git a/hw/cpu/a9mpcore.c b/hw/cpu/a9mpcore.c index XXXXXXX..XXXXXXX 100644 --- a/hw/cpu/a9mpcore.c +++ b/hw/cpu/a9mpcore.c @@ -XXX,XX +XXX,XX @@ static void a9mp_priv_class_init(ObjectClass *klass, void *data) device_class_set_props(dc, a9mp_priv_properties); } -static const TypeInfo a9mp_priv_info = { - .name = TYPE_A9MPCORE_PRIV, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(A9MPPrivState), - .instance_init = a9mp_priv_initfn, - .class_init = a9mp_priv_class_init, +static const TypeInfo a9mp_types[] = { + { + .name = TYPE_A9MPCORE_PRIV, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(A9MPPrivState), + .instance_init = a9mp_priv_initfn, + .class_init = a9mp_priv_class_init, + }, }; -static void a9mp_register_types(void) -{ - type_register_static(&a9mp_priv_info); -} - -type_init(a9mp_register_types) +DEFINE_TYPES(a9mp_types) diff --git a/hw/cpu/arm11mpcore.c b/hw/cpu/arm11mpcore.c index XXXXXXX..XXXXXXX 100644 --- a/hw/cpu/arm11mpcore.c +++ b/hw/cpu/arm11mpcore.c @@ -XXX,XX +XXX,XX @@ static void mpcore_priv_class_init(ObjectClass *klass, void *data) device_class_set_props(dc, mpcore_priv_properties); } -static const TypeInfo mpcore_priv_info = { - .name = TYPE_ARM11MPCORE_PRIV, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(ARM11MPCorePriveState), - .instance_init = mpcore_priv_initfn, - .class_init = mpcore_priv_class_init, +static const TypeInfo arm11mp_types[] = { + { + .name = TYPE_ARM11MPCORE_PRIV, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(ARM11MPCorePriveState), + .instance_init = mpcore_priv_initfn, + .class_init = mpcore_priv_class_init, + }, }; -static void arm11mpcore_register_types(void) -{ - type_register_static(&mpcore_priv_info); -} - -type_init(arm11mpcore_register_types) +DEFINE_TYPES(arm11mp_types) diff --git a/hw/cpu/realview_mpcore.c b/hw/cpu/realview_mpcore.c index XXXXXXX..XXXXXXX 100644 --- a/hw/cpu/realview_mpcore.c +++ b/hw/cpu/realview_mpcore.c @@ -XXX,XX +XXX,XX @@ static void mpcore_rirq_class_init(ObjectClass *klass, void *data) dc->realize = realview_mpcore_realize; } -static const TypeInfo mpcore_rirq_info = { - .name = TYPE_REALVIEW_MPCORE_RIRQ, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(mpcore_rirq_state), - .instance_init = mpcore_rirq_init, - .class_init = mpcore_rirq_class_init, +static const TypeInfo realview_mpcore_types[] = { + { + .name = TYPE_REALVIEW_MPCORE_RIRQ, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(mpcore_rirq_state), + .instance_init = mpcore_rirq_init, + .class_init = mpcore_rirq_class_init, + }, }; -static void realview_mpcore_register_types(void) -{ - type_register_static(&mpcore_rirq_info); -} - -type_init(realview_mpcore_register_types) +DEFINE_TYPES(realview_mpcore_types) -- 2.34.1 From: Andrew Yuan <andrew.yuan@jaguarmicro.com> Our current handling of the mask/compare logic in the Cadence GEM ethernet device is wrong: (1) we load the same byte twice from rx_buf when creating the compare value (2) we ignore the DISABLE_MASK flag The "Cadence IP for Gigabit Ethernet MAC Part Number: IP7014 IP Rev: R1p12 - Doc Rev: 1.3 User Guide" states that if the DISABLE_MASK bit in type2_compare_x_word_1 is set, the mask_value field in type2_compare_x_word_0 is used as an additional 2 byte Compare Value. Correct these bugs: * in the !disable_mask codepath, use lduw_le_p() so we correctly load a 16-bit value for comparison * in the disable_mask codepath, we load a full 4-byte value from rx_buf for the comparison, set the compare value to the whole of the cr0 register (i.e. the concatenation of the mask and compare fields), and set mask to 0xffffffff to force a 32-bit comparison Signed-off-by: Andrew Yuan <andrew.yuan@jaguarmicro.com> Message-id: 20241219061658.805-1-andrew.yuan@jaguarmicro.com Suggested-by: Philippe Mathieu-Daudé <philmd@linaro.org> [PMM: Expand commit message and comment] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@gmail.com> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/cadence_gem.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/hw/net/cadence_gem.c b/hw/net/cadence_gem.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/cadence_gem.c +++ b/hw/net/cadence_gem.c @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, /* Compare A, B, C */ for (j = 0; j < 3; j++) { - uint32_t cr0, cr1, mask, compare; - uint16_t rx_cmp; + uint32_t cr0, cr1, mask, compare, disable_mask; + uint32_t rx_cmp; int offset; int cr_idx = extract32(reg, R_SCREENING_TYPE2_REG0_COMPARE_A_SHIFT + j * 6, R_SCREENING_TYPE2_REG0_COMPARE_A_LENGTH); @@ -XXX,XX +XXX,XX @@ static int get_queue_from_screen(CadenceGEMState *s, uint8_t *rxbuf_ptr, break; } - rx_cmp = rxbuf_ptr[offset] << 8 | rxbuf_ptr[offset]; - mask = FIELD_EX32(cr0, TYPE2_COMPARE_0_WORD_0, MASK_VALUE); - compare = FIELD_EX32(cr0, TYPE2_COMPARE_0_WORD_0, COMPARE_VALUE); + disable_mask = + FIELD_EX32(cr1, TYPE2_COMPARE_0_WORD_1, DISABLE_MASK); + if (disable_mask) { + /* + * If disable_mask is set, mask_value is used as an + * additional 2 byte Compare Value; that is equivalent + * to using the whole cr0 register as the comparison value. + * Load 32 bits of data from rx_buf, and set mask to + * all-ones so we compare all 32 bits. + */ + rx_cmp = ldl_le_p(rxbuf_ptr + offset); + mask = 0xFFFFFFFF; + compare = cr0; + } else { + rx_cmp = lduw_le_p(rxbuf_ptr + offset); + mask = FIELD_EX32(cr0, TYPE2_COMPARE_0_WORD_0, MASK_VALUE); + compare = + FIELD_EX32(cr0, TYPE2_COMPARE_0_WORD_0, COMPARE_VALUE); + } if ((rx_cmp & mask) == (compare & mask)) { matched = true; -- 2.34.1 The '-old-param' command line option is specific to Arm targets; it is very briefly documented as "old param mode". What this option actually does is change the behaviour when directly booting a guest kernel, so that command line arguments are passed to the kernel using the extremely old "param_struct" ABI, rather than the newer ATAGS or even newer DTB mechanisms. This support was added back in 2007 to support an old vendor kernel on the akita/terrier board types: https://mail.gnu.org/archive/html/qemu-devel/2007-07/msg00344.html Even then, it was an out-of-date mechanism from the kernel's point of view -- the kernel has had a comment since 2001 marking it as deprecated. As of mid-2024, the kernel only retained param_struct support for the RiscPC and Footbridge platforms: https://lore.kernel.org/linux-arm-kernel/2831c5a6-cfbf-4fe0-b51c-0396e5b0aeb7@app.fastmail.com/ None of the board types QEMU supports need param_struct support; mark this option as deprecated. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Daniel P. Berrangé <berrange@redhat.com> Message-id: 20250127123113.2947620-1-peter.maydell@linaro.org --- docs/about/deprecated.rst | 13 +++++++++++++ system/vl.c | 1 + 2 files changed, 14 insertions(+) diff --git a/docs/about/deprecated.rst b/docs/about/deprecated.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/about/deprecated.rst +++ b/docs/about/deprecated.rst @@ -XXX,XX +XXX,XX @@ configurations (e.g. -smp drawers=1,books=1,clusters=1 for x86 PC machine) is marked deprecated since 9.0, users have to ensure that all the topology members described with -smp are supported by the target machine. +``-old-param`` option for booting Arm kernels via param_struct (since 10.0) +''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''''' + +The ``-old-param`` command line option is specific to Arm targets: +it is used when directly booting a guest kernel to pass it the +command line and other information via the old ``param_struct`` ABI, +rather than the newer ATAGS or DTB mechanisms. This option was only +ever needed to support ancient kernels on some old board types +like the ``akita`` or ``terrier``; it has been deprecated in the +kernel since 2001. None of the board types QEMU supports need +``param_struct`` support, so this option has been deprecated and will +be removed in a future QEMU version. + User-mode emulator command line arguments ----------------------------------------- diff --git a/system/vl.c b/system/vl.c index XXXXXXX..XXXXXXX 100644 --- a/system/vl.c +++ b/system/vl.c @@ -XXX,XX +XXX,XX @@ void qemu_init(int argc, char **argv) nb_prom_envs++; break; case QEMU_OPTION_old_param: + warn_report("-old-param is deprecated"); old_param = 1; break; case QEMU_OPTION_rtc: -- 2.34.1 From: Khem Raj <raj.khem@gmail.com> glibc 2.41+ has added [1] definitions for sched_setattr and sched_getattr functions and struct sched_attr. Therefore, it needs to be checked for here as well before defining sched_attr, to avoid a compilation failure. Define sched_attr conditionally only when SCHED_ATTR_SIZE_VER0 is not defined. [1] https://sourceware.org/git/?p=glibc.git;a=commitdiff;h=21571ca0d70302909cf72707b2a7736cf12190a0;hp=298bc488fdc047da37482f4003023cb9adef78f8 Signed-off-by: Khem Raj <raj.khem@gmail.com> Resolves: https://gitlab.com/qemu-project/qemu/-/issues/2799 Cc: qemu-stable@nongnu.org Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- linux-user/syscall.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) 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 @@ _syscall3(int, sys_sched_getaffinity, pid_t, pid, unsigned int, len, #define __NR_sys_sched_setaffinity __NR_sched_setaffinity _syscall3(int, sys_sched_setaffinity, pid_t, pid, unsigned int, len, unsigned long *, user_mask_ptr); -/* sched_attr is not defined in glibc */ +/* sched_attr is not defined in glibc < 2.41 */ +#ifndef SCHED_ATTR_SIZE_VER0 struct sched_attr { uint32_t size; uint32_t sched_policy; @@ -XXX,XX +XXX,XX @@ struct sched_attr { uint32_t sched_util_min; uint32_t sched_util_max; }; +#endif #define __NR_sys_sched_getattr __NR_sched_getattr _syscall4(int, sys_sched_getattr, pid_t, pid, struct sched_attr *, attr, unsigned int, size, unsigned int, flags); -- 2.34.1