From c1bf754041f4a9101059c0151475ed69df1c7e2e Mon Sep 17 00:00:00 2001 From: Rayhan Faizel Date: Sun, 19 May 2024 15:11:04 +0530 Subject: [PATCH 01/29] hw/nvram: Add BCM2835 OTP device 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 Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- hw/nvram/bcm2835_otp.c | 187 +++++++++++++++++++++++++++++++++ hw/nvram/meson.build | 1 + include/hw/nvram/bcm2835_otp.h | 68 ++++++++++++ 3 files changed, 256 insertions(+) create mode 100644 hw/nvram/bcm2835_otp.c create mode 100644 include/hw/nvram/bcm2835_otp.h diff --git a/hw/nvram/bcm2835_otp.c b/hw/nvram/bcm2835_otp.c new file mode 100644 index 0000000000..c4aed28472 --- /dev/null +++ b/hw/nvram/bcm2835_otp.c @@ -0,0 +1,187 @@ +/* + * 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 + * + * 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 4996c72456..10f3639db6 100644 --- a/hw/nvram/meson.build +++ b/hw/nvram/meson.build @@ -1,5 +1,6 @@ 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')) diff --git a/include/hw/nvram/bcm2835_otp.h b/include/hw/nvram/bcm2835_otp.h new file mode 100644 index 0000000000..1df33700bd --- /dev/null +++ b/include/hw/nvram/bcm2835_otp.h @@ -0,0 +1,68 @@ +/* + * BCM2835 One-Time Programmable (OTP) Memory + * + * Copyright (c) 2024 Rayhan Faizel + * + * 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 { + /* */ + SysBusDevice parent_obj; + + /* */ + 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 From 6bf7993921827817eb313f44509bf4ba7ebf88bb Mon Sep 17 00:00:00 2001 From: Rayhan Faizel Date: Sun, 19 May 2024 15:11:05 +0530 Subject: [PATCH 02/29] hw/arm: Connect OTP device to BCM2835 Replace stubbed OTP memory region with the new OTP device. Signed-off-by: Rayhan Faizel Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- hw/arm/bcm2835_peripherals.c | 13 ++++++++++++- include/hw/arm/bcm2835_peripherals.h | 3 ++- 2 files changed, 14 insertions(+), 2 deletions(-) diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c index 1695d8b453..7d735bb56c 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -116,6 +116,10 @@ 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); @@ -374,6 +378,14 @@ 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; @@ -500,7 +512,6 @@ 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); diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h index 636203baa5..1eeaeec9e0 100644 --- a/include/hw/arm/bcm2835_peripherals.h +++ b/include/hw/arm/bcm2835_peripherals.h @@ -33,6 +33,7 @@ #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" @@ -71,7 +72,7 @@ struct BCMSocPeripheralBaseState { BCM2835SPIState spi[1]; BCM2835I2CState i2c[3]; OrIRQState orgated_i2c_irq; - UnimplementedDeviceState otp; + BCM2835OTPState otp; UnimplementedDeviceState dbus; UnimplementedDeviceState ave0; UnimplementedDeviceState v3d; From 5d5f1b60916aa6bbebe192d74acb762414377430 Mon Sep 17 00:00:00 2001 From: Rayhan Faizel Date: Sun, 19 May 2024 15:11:06 +0530 Subject: [PATCH 03/29] hw/misc: Implement mailbox properties for customer OTP and device specific private keys 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 Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- hw/arm/bcm2835_peripherals.c | 2 + hw/misc/bcm2835_property.c | 87 ++++++++++++++++++++++++++++ include/hw/arm/raspberrypi-fw-defs.h | 2 + include/hw/misc/bcm2835_property.h | 2 + 4 files changed, 93 insertions(+) diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c index 7d735bb56c..ac153a96b9 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -132,6 +132,8 @@ 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 bdd9a6bbce..63de3db621 100644 --- a/hw/misc/bcm2835_property.c +++ b/hw/misc/bcm2835_property.c @@ -32,6 +32,7 @@ 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 @@ -322,6 +323,89 @@ 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); @@ -449,6 +533,9 @@ 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); diff --git a/include/hw/arm/raspberrypi-fw-defs.h b/include/hw/arm/raspberrypi-fw-defs.h index 8b404e0533..60b8e5b451 100644 --- a/include/hw/arm/raspberrypi-fw-defs.h +++ b/include/hw/arm/raspberrypi-fw-defs.h @@ -56,6 +56,7 @@ 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, @@ -73,6 +74,7 @@ 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 ba8896610c..2f93fd0c75 100644 --- a/include/hw/misc/bcm2835_property.h +++ b/include/hw/misc/bcm2835_property.h @@ -11,6 +11,7 @@ #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" @@ -26,6 +27,7 @@ struct BCM2835PropertyState { MemoryRegion iomem; qemu_irq mbox_irq; BCM2835FBState *fbdev; + BCM2835OTPState *otp; MACAddr macaddr; uint32_t board_rev; From 24a7cd6a7c21f82f1ce9bd5ecf6fb54eb7bf4602 Mon Sep 17 00:00:00 2001 From: Marcin Juszkiewicz Date: Thu, 20 Jun 2024 12:19:48 +0200 Subject: [PATCH 04/29] tests/avocado: update firmware for sbsa-ref MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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 Reviewed-by: Philippe Mathieu-Daudé Tested-by: Philippe Mathieu-Daudé Message-id: 20240620-b4-new-firmware-v3-1-29a3a2f1be1e@linaro.org Signed-off-by: Peter Maydell --- 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 6bb82f2a03..e854ec6a1a 100644 --- a/tests/avocado/machine_aarch64_sbsaref.py +++ b/tests/avocado/machine_aarch64_sbsaref.py @@ -37,18 +37,18 @@ class Aarch64SbsarefMachine(QemuSystemTest): 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) @@ -57,9 +57,9 @@ class Aarch64SbsarefMachine(QemuSystemTest): # 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) From 6c84daac58f0d75a908626faf89a832fc0532140 Mon Sep 17 00:00:00 2001 From: Marcin Juszkiewicz Date: Thu, 20 Jun 2024 12:19:49 +0200 Subject: [PATCH 05/29] tests/avocado: use default amount of cores on sbsa-ref MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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 Reviewed-by: Philippe Mathieu-Daudé Tested-by: Philippe Mathieu-Daudé Message-id: 20240620-b4-new-firmware-v3-2-29a3a2f1be1e@linaro.org Signed-off-by: Peter Maydell --- 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 e854ec6a1a..e920bbf08c 100644 --- a/tests/avocado/machine_aarch64_sbsaref.py +++ b/tests/avocado/machine_aarch64_sbsaref.py @@ -75,8 +75,6 @@ class Aarch64SbsarefMachine(QemuSystemTest): f"if=pflash,file={fs0_path},format=raw", "-drive", f"if=pflash,file={fs1_path},format=raw", - "-smp", - "1", "-machine", "sbsa-ref", ) From 69970205edb661f79a7f6d6046785c521c6da80b Mon Sep 17 00:00:00 2001 From: Nicolin Chen Date: Tue, 18 Jun 2024 17:22:18 -0700 Subject: [PATCH 06/29] hw/arm/smmu-common: Replace smmu_iommu_mr with smmu_find_sdev 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 Message-id: 20240619002218.926674-1-nicolinc@nvidia.com Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- hw/arm/smmu-common.c | 8 ++------ hw/arm/smmuv3.c | 12 ++++-------- include/hw/arm/smmu-common.h | 4 ++-- 3 files changed, 8 insertions(+), 16 deletions(-) diff --git a/hw/arm/smmu-common.c b/hw/arm/smmu-common.c index 1ce706bf94..b6601cc102 100644 --- a/hw/arm/smmu-common.c +++ b/hw/arm/smmu-common.c @@ -620,20 +620,16 @@ 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 2d1e0d55ec..445e04ddf7 100644 --- a/hw/arm/smmuv3.c +++ b/hw/arm/smmuv3.c @@ -1218,20 +1218,18 @@ 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; @@ -1260,20 +1258,18 @@ 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; } diff --git a/include/hw/arm/smmu-common.h b/include/hw/arm/smmu-common.h index 5ec2e6c1a4..687b7ca132 100644 --- a/include/hw/arm/smmu-common.h +++ b/include/hw/arm/smmu-common.h @@ -182,8 +182,8 @@ 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 From 76bccf3cb9d9383da0128bbc6d1300cddbe3ae8f Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 25 Jun 2024 11:35:24 -0700 Subject: [PATCH 07/29] target/arm: Fix VCMLA Dd, Dn, Dm[idx] 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 Signed-off-by: Richard Henderson Message-id: 20240625183536.1672454-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- 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 b05922b425..7b34cc98af 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -907,7 +907,7 @@ 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. */ @@ -969,7 +969,7 @@ 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. */ From a5b72ccc0f21183e7863745b0d82f144ecfb59f5 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 25 Jun 2024 11:35:25 -0700 Subject: [PATCH 08/29] target/arm: Fix SQDMULH (by element) with Q=0 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 Signed-off-by: Richard Henderson Message-id: 20240625183536.1672454-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- 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 7b34cc98af..d477479bb1 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -317,10 +317,12 @@ 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); } } @@ -333,10 +335,12 @@ 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); } } @@ -512,10 +516,12 @@ 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); } } @@ -528,10 +534,12 @@ 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); } } From 7619129f0d4a14d918227c5c47ad7433662e9ccc Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 25 Jun 2024 11:35:26 -0700 Subject: [PATCH 09/29] target/arm: Fix FJCVTZS vs flush-to-zero 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 Signed-off-by: Richard Henderson Message-id: 20240625183536.1672454-4-richard.henderson@linaro.org [PMM: fixed hardcoded tab in test case] Signed-off-by: Peter Maydell --- target/arm/vfp_helper.c | 18 +++++++++--------- tests/tcg/aarch64/Makefile.target | 3 ++- tests/tcg/aarch64/test-2375.c | 21 +++++++++++++++++++++ 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 ce26b8a71a..50d7042fa9 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -1091,8 +1091,8 @@ 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); @@ -1100,13 +1100,13 @@ 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/Makefile.target b/tests/tcg/aarch64/Makefile.target index 70d728ae9a..4ecbca6a41 100644 --- a/tests/tcg/aarch64/Makefile.target +++ b/tests/tcg/aarch64/Makefile.target @@ -41,8 +41,9 @@ 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]. diff --git a/tests/tcg/aarch64/test-2375.c b/tests/tcg/aarch64/test-2375.c new file mode 100644 index 0000000000..84c7e7de71 --- /dev/null +++ b/tests/tcg/aarch64/test-2375.c @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* Copyright (c) 2024 Linaro Ltd */ +/* See https://gitlab.com/qemu-project/qemu/-/issues/2375 */ + +#include + +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; +} From f698e4527064da714859892ba49d25a0a2afd12d Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 25 Jun 2024 11:35:27 -0700 Subject: [PATCH 10/29] target/arm: Convert SQRDMLAH, SQRDMLSH to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240625183536.1672454-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- 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 eca2043fc2..970d059dec 100644 --- a/target/arm/helper.h +++ b/target/arm/helper.h @@ -979,6 +979,16 @@ 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 2b7a3254a0..613cc9365c 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -781,6 +781,8 @@ 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 @@ -941,6 +943,8 @@ 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 @@ -966,6 +970,12 @@ 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 @@ -1004,6 +1014,12 @@ 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 93543da39c..32c24c7422 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5235,6 +5235,43 @@ 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)) { @@ -5552,6 +5589,8 @@ 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 @@ -5681,6 +5720,29 @@ 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]) { @@ -5838,6 +5900,20 @@ 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 */ @@ -9536,84 +9612,6 @@ 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) @@ -10892,14 +10890,6 @@ 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) { @@ -10957,6 +10947,8 @@ 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; } @@ -10969,14 +10961,6 @@ 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); @@ -12059,13 +12043,6 @@ 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)) { @@ -12127,6 +12104,8 @@ 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; } @@ -12320,33 +12299,13 @@ 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(); } @@ -12538,7 +12497,6 @@ 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 d477479bb1..98604d170f 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -347,6 +347,42 @@ 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) { @@ -546,6 +582,42 @@ 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) { From 65dd60a65b83191c14ad2c144a2c189b6eb00b46 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 25 Jun 2024 11:35:28 -0700 Subject: [PATCH 11/29] target/arm: Convert SDOT, UDOT to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240625183536.1672454-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- 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 613cc9365c..7411d4ba97 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -61,6 +61,7 @@ @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 @@ -946,6 +947,9 @@ 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 @@ -1020,6 +1024,9 @@ 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 32c24c7422..f2e7d8d75c 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5592,6 +5592,18 @@ 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 */ @@ -5914,6 +5926,18 @@ 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 */ @@ -10890,14 +10914,6 @@ 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); @@ -10947,8 +10963,10 @@ 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; } @@ -10961,11 +10979,6 @@ 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; @@ -12043,13 +12056,6 @@ 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 */ @@ -12099,12 +12105,14 @@ 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; @@ -12180,12 +12188,6 @@ 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 */ From 849b7c1661d1784dad4bb56998ba8952d2c8a5d1 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 25 Jun 2024 11:35:29 -0700 Subject: [PATCH 12/29] target/arm: Convert SUDOT, USDOT to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240625183536.1672454-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- 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 7411d4ba97..8a0251f83c 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -949,6 +949,7 @@ 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 @@ -1026,6 +1027,8 @@ 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 f2e7d8d75c..9a658ca876 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5603,6 +5603,7 @@ 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 @@ -5937,6 +5938,10 @@ 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 @@ -10914,13 +10919,6 @@ 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 */ @@ -10964,6 +10962,7 @@ 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) */ @@ -10979,10 +10978,6 @@ 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 @@ -12058,14 +12053,6 @@ 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); @@ -12082,6 +12069,8 @@ 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; } @@ -12190,18 +12179,10 @@ 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); From 9130827c4c7976a52dcc70db8beb699a200c35a3 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 25 Jun 2024 11:35:30 -0700 Subject: [PATCH 13/29] target/arm: Convert BFDOT to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240625183536.1672454-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- 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 8a0251f83c..6819fd2587 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -950,6 +950,7 @@ 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 @@ -1029,6 +1030,7 @@ 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 9a658ca876..0f44cd5aee 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5604,6 +5604,7 @@ 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 @@ -5942,6 +5943,8 @@ 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 @@ -10951,11 +10954,11 @@ 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; } @@ -11036,9 +11039,6 @@ 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); @@ -12053,13 +12053,6 @@ 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); @@ -12070,6 +12063,7 @@ 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; @@ -12179,10 +12173,6 @@ 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); From 1c6ecab43172b9a5c345df38de5e8b4fb5c285e1 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 25 Jun 2024 11:35:31 -0700 Subject: [PATCH 14/29] target/arm: Convert BFMLALB, BFMLALT to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240625183536.1672454-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- 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 6819fd2587..15344a73de 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -951,6 +951,7 @@ 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 @@ -1031,6 +1032,7 @@ 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 0f44cd5aee..95be862dde 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5606,6 +5606,19 @@ 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 */ @@ -5946,6 +5959,20 @@ 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 */ @@ -10952,23 +10979,13 @@ 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; } @@ -11037,17 +11054,6 @@ 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(); } @@ -12051,24 +12057,6 @@ 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 */ @@ -12089,6 +12077,7 @@ 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 */ @@ -12171,14 +12160,6 @@ 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 */ From 9676c9d9b5a937e432118de8070261648fe14706 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 25 Jun 2024 11:35:32 -0700 Subject: [PATCH 15/29] target/arm: Convert BFMMLA, SMMLA, UMMLA, USMMLA to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240625183536.1672454-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- 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 15344a73de..b2c7e36969 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -952,6 +952,10 @@ 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 95be862dde..2697c4b305 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5605,6 +5605,10 @@ 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) { @@ -10949,15 +10953,6 @@ 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 */ @@ -10972,19 +10967,16 @@ 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; @@ -10998,15 +10990,6 @@ 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 */ @@ -11051,9 +11034,6 @@ 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(); } From 6515b13e87c83f8c3a9f6ad5e6a3f45ba31c70ca Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 25 Jun 2024 11:35:33 -0700 Subject: [PATCH 16/29] target/arm: Add data argument to do_fp3_vector Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240625183536.1672454-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- 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 2697c4b305..57cdde008e 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5290,7 +5290,7 @@ 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; @@ -5313,7 +5313,7 @@ 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; } @@ -5323,168 +5323,168 @@ 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) { From 0f46ebee6318238c375df35c0c0f56d04f075c50 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 25 Jun 2024 11:35:34 -0700 Subject: [PATCH 17/29] target/arm: Convert FCADD to decodetree Reviewed-by: Peter Maydell Signed-off-by: Richard Henderson Message-id: 20240625183536.1672454-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell --- 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 b2c7e36969..f330919851 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -957,6 +957,9 @@ 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 57cdde008e..a1b338263f 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5623,6 +5623,14 @@ 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 */ @@ -10957,8 +10965,6 @@ 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)) { @@ -10976,7 +10982,9 @@ 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; @@ -11013,27 +11021,6 @@ 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(); } From 80b02a565e518414ba3ced137571ed4597595082 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 25 Jun 2024 11:35:35 -0700 Subject: [PATCH 18/29] target/arm: Convert FCMLA to decodetree Signed-off-by: Richard Henderson Message-id: 20240625183536.1672454-13-richard.henderson@linaro.org Signed-off-by: Peter Maydell Reviewed-by: Peter Maydell --- 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 f330919851..223eac3cac 100644 --- a/target/arm/tcg/a64.decode +++ b/target/arm/tcg/a64.decode @@ -960,6 +960,8 @@ 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 @@ -1041,6 +1043,10 @@ 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 a1b338263f..161fa2659c 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -5631,6 +5631,39 @@ 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 */ @@ -5985,6 +6018,33 @@ 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 */ @@ -10942,90 +11002,6 @@ 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) { @@ -12001,10 +11977,7 @@ 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 */ @@ -12024,16 +11997,6 @@ 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 */ @@ -12046,7 +12009,11 @@ 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 */ @@ -12057,46 +12024,12 @@ 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; @@ -12104,14 +12037,6 @@ 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(); } @@ -12120,32 +12045,6 @@ 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) { @@ -12407,7 +12306,6 @@ 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 }, From 2cd5078d5784ef57935d2b157bf6d5566e86eac9 Mon Sep 17 00:00:00 2001 From: Richard Henderson Date: Tue, 25 Jun 2024 11:35:36 -0700 Subject: [PATCH 19/29] target/arm: Delete dead code from disas_simd_indexed MLA, MLS, SQDMULH, SQRDMULH, were converted with 8db93dcd3def and f80701cb44d, and this code should have been removed then. Signed-off-by: Richard Henderson Message-id: 20240625183536.1672454-14-richard.henderson@linaro.org Signed-off-by: Peter Maydell Reviewed-by: Peter Maydell --- 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 161fa2659c..6c07aeaf3b 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -11976,7 +11976,6 @@ 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) { @@ -11990,12 +11989,10 @@ 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 */ @@ -12047,96 +12044,6 @@ 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]; From 4df378ab5164635d0431086b800adb770c037a64 Mon Sep 17 00:00:00 2001 From: Gustavo Romero Date: Mon, 24 Jun 2024 18:09:13 +0000 Subject: [PATCH 20/29] target/arm: Fix indentation Fix comment indentation adding a missing space. Signed-off-by: Gustavo Romero Reviewed-by: Richard Henderson Message-id: 20240624180915.4528-2-gustavo.romero@linaro.org Signed-off-by: Peter Maydell --- 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 0899251eef..71e1bfcd4e 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -1167,7 +1167,7 @@ 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; From c5f9e8bb9300d0cae42d2cb19f6a4d340813f8b5 Mon Sep 17 00:00:00 2001 From: Gustavo Romero Date: Mon, 24 Jun 2024 18:09:14 +0000 Subject: [PATCH 21/29] target/arm: Move initialization of debug ID registers 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 Reviewed-by: Richard Henderson Message-id: 20240624180915.4528-3-gustavo.romero@linaro.org Signed-off-by: Peter Maydell --- 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 3841359d0f..d8eb986a04 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -2299,6 +2299,8 @@ 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 bdd82d912a..28a5c033bb 100644 --- a/target/arm/tcg/cpu32.c +++ b/target/arm/tcg/cpu32.c @@ -87,6 +87,34 @@ 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; @@ -955,9 +983,6 @@ 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 */ From 02ff2add77099f9deb7d6a18c9b4110572771f6a Mon Sep 17 00:00:00 2001 From: Gustavo Romero Date: Mon, 24 Jun 2024 18:09:15 +0000 Subject: [PATCH 22/29] target/arm: Enable FEAT_Debugv8p8 for -cpu max 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 Reviewed-by: Richard Henderson Message-id: 20240624180915.4528-4-gustavo.romero@linaro.org Signed-off-by: Peter Maydell --- 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 1a06a5feb6..3ab6e72667 100644 --- a/docs/system/arm/emulation.rst +++ b/docs/system/arm/emulation.rst @@ -41,6 +41,7 @@ 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 28a5c033bb..20c2737f17 100644 --- a/target/arm/tcg/cpu32.c +++ b/target/arm/tcg/cpu32.c @@ -82,8 +82,8 @@ 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; @@ -93,7 +93,7 @@ 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 71e1bfcd4e..fe232eb306 100644 --- a/target/arm/tcg/cpu64.c +++ b/target/arm/tcg/cpu64.c @@ -1253,7 +1253,7 @@ 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; From 6529511a8412a54afbcad850a62c0f39b4a9fc6c Mon Sep 17 00:00:00 2001 From: Patrick Leis Date: Wed, 26 Jun 2024 21:16:22 +0000 Subject: [PATCH 23/29] MAINTAINERS: Update my family name Signed-off-by: Patrick Leis Message-id: 20240626211623.3510701-1-venture@google.com Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- MAINTAINERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/MAINTAINERS b/MAINTAINERS index 19f67dc5d2..13255d4a3b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2496,7 +2496,7 @@ F: hw/net/tulip.c F: hw/net/tulip.h pca954x -M: Patrick Venture +M: Patrick Leis S: Maintained F: hw/i2c/i2c_mux_pca954x.c F: include/hw/i2c/i2c_mux_pca954x.h From 247f24507f78ed80314b6bd474db8ae1ac7c0253 Mon Sep 17 00:00:00 2001 From: Sai Pavan Boddu Date: Fri, 21 Jun 2024 18:29:04 +0530 Subject: [PATCH 24/29] hw/misc/zynq_slcr: Add boot-mode property boot-mode property sets user values into BOOT_MODE register, on hardware these are derived from board switches. Signed-off-by: Sai Pavan Boddu Reviewed-by: Edgar E. Iglesias Reviewed-by: Francisco Iglesias Message-id: 20240621125906.1300995-2-sai.pavan.boddu@amd.com Signed-off-by: Peter Maydell --- 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 3412ff099e..ad814c3a79 100644 --- a/hw/misc/zynq_slcr.c +++ b/hw/misc/zynq_slcr.c @@ -24,6 +24,8 @@ #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 @@ -121,6 +123,7 @@ 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) @@ -195,6 +198,7 @@ struct ZynqSLCRState { Clock *ps_clk; Clock *uart0_ref_clk; Clock *uart1_ref_clk; + uint8_t boot_mode; }; /* @@ -371,7 +375,7 @@ 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++) { @@ -588,6 +592,15 @@ 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); @@ -610,15 +623,22 @@ 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 = { From 7df3747c92d13a56ddfd8b8fdec06c7c6fddfd66 Mon Sep 17 00:00:00 2001 From: Sai Pavan Boddu Date: Fri, 21 Jun 2024 18:29:05 +0530 Subject: [PATCH 25/29] hw/arm/xilinx_zynq: Add boot-mode property Read boot-mode value as machine property and propagate that to SLCR.BOOT_MODE register. Signed-off-by: Sai Pavan Boddu Acked-by: Edgar E. Iglesias Reviewed-by: Francisco Iglesias Message-id: 20240621125906.1300995-3-sai.pavan.boddu@amd.com Signed-off-by: Peter Maydell --- 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 c79661bbc1..3c56b9abe1 100644 --- a/hw/arm/xilinx_zynq.c +++ b/hw/arm/xilinx_zynq.c @@ -38,6 +38,7 @@ #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) @@ -90,6 +91,7 @@ struct ZynqMachineState { MachineState parent; Clock *ps_clk; ARMCPU *cpu[ZYNQ_MAX_CPUS]; + uint8_t boot_mode; }; static void zynq_write_board_setup(ARMCPU *cpu, @@ -176,6 +178,27 @@ 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); @@ -241,6 +264,7 @@ 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); @@ -373,6 +397,7 @@ 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; @@ -380,6 +405,12 @@ 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 = { From 2d30506d065743008184a3b0269529bd9159560e Mon Sep 17 00:00:00 2001 From: Sai Pavan Boddu Date: Fri, 21 Jun 2024 18:29:06 +0530 Subject: [PATCH 26/29] docs/system/arm: Add a doc for zynq board Added the supported device list and an example command. Signed-off-by: Sai Pavan Boddu Reviewed-by: Edgar E. Iglesias Reviewed-by: Francisco Iglesias Message-id: 20240621125906.1300995-4-sai.pavan.boddu@amd.com Signed-off-by: Peter Maydell --- 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 13255d4a3b..6725913c8b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1033,6 +1033,7 @@ 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 diff --git a/docs/system/arm/xlnx-zynq.rst b/docs/system/arm/xlnx-zynq.rst new file mode 100644 index 0000000000..ade18a3fe1 --- /dev/null +++ b/docs/system/arm/xlnx-zynq.rst @@ -0,0 +1,47 @@ +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 870d30e350..7b99272284 100644 --- a/docs/system/target-arm.rst +++ b/docs/system/target-arm.rst @@ -109,6 +109,7 @@ undocumented; you can get a complete list by running arm/virt arm/xenpvh arm/xlnx-versal-virt + arm/xlnx-zynq Emulated CPU architecture support ================================= From 7d9b3c34f30045eb50d1c890be46bfde4100bf65 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?In=C3=A8s=20Varhol?= Date: Sat, 29 Jun 2024 12:44:49 +0200 Subject: [PATCH 27/29] tests/qtest: Fix STM32L4x5 SYSCFG irq line 15 state assumption MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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 Message-id: 20240629104454.366283-1-ines.varhol@telecom-paris.fr Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- 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 506ca08bc2..1cdf8f05c8 100644 --- a/tests/qtest/stm32l4x5_syscfg-test.c +++ b/tests/qtest/stm32l4x5_syscfg-test.c @@ -223,7 +223,7 @@ 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); } @@ -237,21 +237,21 @@ 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) From 9c4887e3b68a362f2f5a4e86daab98a51b3b769e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?In=C3=A8s=20Varhol?= Date: Sat, 29 Jun 2024 13:07:08 +0200 Subject: [PATCH 28/29] hw/misc: In STM32L4x5 EXTI, correct configurable interrupts MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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 Message-id: 20240629110800.539969-2-ines.varhol@telecom-paris.fr Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- hw/misc/stm32l4x5_exti.c | 28 +++++++++++++--------------- include/hw/misc/stm32l4x5_exti.h | 2 ++ 2 files changed, 15 insertions(+), 15 deletions(-) diff --git a/hw/misc/stm32l4x5_exti.c b/hw/misc/stm32l4x5_exti.c index 495a0004ab..6a2ec62d78 100644 --- a/hw/misc/stm32l4x5_exti.c +++ b/hw/misc/stm32l4x5_exti.c @@ -88,6 +88,7 @@ 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; } } @@ -102,27 +103,23 @@ 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, @@ -255,8 +252,8 @@ 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), @@ -264,6 +261,7 @@ 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() } }; diff --git a/include/hw/misc/stm32l4x5_exti.h b/include/hw/misc/stm32l4x5_exti.h index be961d2f01..55f763fa37 100644 --- a/include/hw/misc/stm32l4x5_exti.h +++ b/include/hw/misc/stm32l4x5_exti.h @@ -45,6 +45,8 @@ 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]; }; From 58c782de557beb496bfb4c5ade721bbbd2480c72 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?In=C3=A8s=20Varhol?= Date: Sat, 29 Jun 2024 13:07:09 +0200 Subject: [PATCH 29/29] tests/qtest: Ensure STM32L4x5 EXTI state is correct at the end of QTests MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit 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 Message-id: 20240629110800.539969-3-ines.varhol@telecom-paris.fr Reviewed-by: Peter Maydell Signed-off-by: Peter Maydell --- 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 7092860b9b..7e39c992fd 100644 --- a/tests/qtest/stm32l4x5_exti-test.c +++ b/tests/qtest/stm32l4x5_exti-test.c @@ -448,6 +448,9 @@ 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) @@ -498,6 +501,9 @@ 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) @@ -531,6 +537,8 @@ 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 1cdf8f05c8..258417cd88 100644 --- a/tests/qtest/stm32l4x5_syscfg-test.c +++ b/tests/qtest/stm32l4x5_syscfg-test.c @@ -221,10 +221,10 @@ 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)