The following changes since commit 4eac9dfbd72d346505642fb45ac3141c7eb2c516: Merge tag 'pull-tcg-20240301' of https://gitlab.com/rth7680/qemu into staging (2024-03-05 09:45:22 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20240305 for you to fetch changes up to 7558300c53057126514ee0fd5cf629c65ccc20e1: qemu-options.hx: Don't claim "-serial" has limit of 4 serial ports (2024-03-05 13:22:56 +0000) ---------------------------------------------------------------- target-arm queue: * raspi: Implement Broadcom Serial Controller (BSC) for BCM2835 boards * hw/char/pl011: Add support for loopback * STM32L4x5: Implement RCC clock control device * target/arm: Do memory type alignment checks * atomic.h: Reword confusing comment for qatomic_cmpxchg * qemu-options.hx: Don't claim "-serial" has limit of 4 serial ports ---------------------------------------------------------------- Arnaud Minier (8): hw/misc/stm32l4x5_rcc: Implement STM32L4x5_RCC skeleton hw/misc/stm32l4x5_rcc: Add an internal clock multiplexer object hw/misc/stm32l4x5_rcc: Add an internal PLL Clock object hw/misc/stm32l4x5_rcc: Initialize PLLs and clock multiplexers hw/misc/stm32l4x5_rcc: Handle Register Updates hw/misc/stm32l4x5_rcc: Add write protections to CR register hw/arm/stm32l4x5_soc.c: Use the RCC Sysclk tests/qtest/stm32l4x5_rcc-test.c: Add tests for the STM32L4x5_RCC Peter Maydell (1): atomic.h: Reword confusing comment for qatomic_cmpxchg Rayhan Faizel (3): hw/i2c: Implement Broadcom Serial Controller (BSC) hw/arm: Connect BSC to BCM2835 board as I2C0, I2C1 and I2C2 tests/qtest: Add testcase for BCM2835 BSC Richard Henderson (6): target/arm: Support 32-byte alignment in pow2_align exec/memattrs: Remove target_tlb_bit* accel/tcg: Add tlb_fill_flags to CPUTLBEntryFull accel/tcg: Add TLB_CHECK_ALIGNED target/arm: Do memory type alignment check when translation disabled target/arm: Do memory type alignment check when translation enabled Steven Shen (1): qemu-options.hx: Don't claim "-serial" has limit of 4 serial ports Tong Ho (1): hw/char/pl011: Add support for loopback MAINTAINERS | 5 +- docs/system/arm/b-l475e-iot01a.rst | 2 +- docs/system/arm/raspi.rst | 1 + include/exec/cpu-all.h | 4 +- include/exec/memattrs.h | 12 - include/hw/arm/bcm2835_peripherals.h | 4 +- include/hw/arm/stm32l4x5_soc.h | 5 +- include/hw/core/cpu.h | 3 + include/hw/i2c/bcm2835_i2c.h | 80 ++ include/hw/misc/stm32l4x5_rcc.h | 239 +++++ include/hw/misc/stm32l4x5_rcc_internals.h | 1042 +++++++++++++++++++++ include/qemu/atomic.h | 2 +- accel/tcg/cputlb.c | 35 +- hw/arm/b-l475e-iot01a.c | 10 +- hw/arm/bcm2835_peripherals.c | 45 +- hw/arm/stm32l4x5_soc.c | 45 +- hw/char/pl011.c | 110 ++- hw/i2c/bcm2835_i2c.c | 282 ++++++ hw/misc/stm32l4x5_rcc.c | 1457 +++++++++++++++++++++++++++++ target/arm/ptw.c | 39 + target/arm/tcg/hflags.c | 34 +- target/arm/tcg/translate.c | 8 +- target/sparc/mmu_helper.c | 2 +- tests/qtest/bcm2835-i2c-test.c | 115 +++ tests/qtest/stm32l4x5_rcc-test.c | 189 ++++ hw/arm/Kconfig | 2 + hw/i2c/Kconfig | 4 + hw/i2c/meson.build | 1 + hw/misc/Kconfig | 3 + hw/misc/meson.build | 1 + hw/misc/trace-events | 14 + qemu-options.hx | 2 +- tests/qtest/meson.build | 5 +- 33 files changed, 3718 insertions(+), 84 deletions(-) create mode 100644 include/hw/i2c/bcm2835_i2c.h create mode 100644 include/hw/misc/stm32l4x5_rcc.h create mode 100644 include/hw/misc/stm32l4x5_rcc_internals.h create mode 100644 hw/i2c/bcm2835_i2c.c create mode 100644 hw/misc/stm32l4x5_rcc.c create mode 100644 tests/qtest/bcm2835-i2c-test.c create mode 100644 tests/qtest/stm32l4x5_rcc-test.c From: Rayhan Faizel <rayhan.faizel@gmail.com> A few deficiencies in the current device model need to be noted. 1. FIFOs are not used. All sends and receives are done directly. 2. Repeated starts are not emulated. Repeated starts can be triggered in real hardware by sending a new read transfer request in the window time between transfer active set of write transfer request and done bit set of the same. Signed-off-by: Rayhan Faizel <rayhan.faizel@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240224191038.2409945-2-rayhan.faizel@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- docs/system/arm/raspi.rst | 1 + include/hw/i2c/bcm2835_i2c.h | 80 ++++++++++ hw/i2c/bcm2835_i2c.c | 282 +++++++++++++++++++++++++++++++++++ hw/i2c/Kconfig | 4 + hw/i2c/meson.build | 1 + 5 files changed, 368 insertions(+) create mode 100644 include/hw/i2c/bcm2835_i2c.h create mode 100644 hw/i2c/bcm2835_i2c.c diff --git a/docs/system/arm/raspi.rst b/docs/system/arm/raspi.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/raspi.rst +++ b/docs/system/arm/raspi.rst @@ -XXX,XX +XXX,XX @@ Implemented devices * MailBox controller (MBOX) * VideoCore firmware (property) * Peripheral SPI controller (SPI) + * Broadcom Serial Controller (I2C) Missing devices --------------- diff --git a/include/hw/i2c/bcm2835_i2c.h b/include/hw/i2c/bcm2835_i2c.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/i2c/bcm2835_i2c.h @@ -XXX,XX +XXX,XX @@ +/* + * Broadcom Serial Controller (BSC) + * + * Copyright (c) 2024 Rayhan Faizel <rayhan.faizel@gmail.com> + * + * SPDX-License-Identifier: MIT + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "hw/sysbus.h" +#include "hw/i2c/i2c.h" +#include "qom/object.h" + +#define TYPE_BCM2835_I2C "bcm2835-i2c" +OBJECT_DECLARE_SIMPLE_TYPE(BCM2835I2CState, BCM2835_I2C) + +#define BCM2835_I2C_C 0x0 /* Control */ +#define BCM2835_I2C_S 0x4 /* Status */ +#define BCM2835_I2C_DLEN 0x8 /* Data Length */ +#define BCM2835_I2C_A 0xc /* Slave Address */ +#define BCM2835_I2C_FIFO 0x10 /* FIFO */ +#define BCM2835_I2C_DIV 0x14 /* Clock Divider */ +#define BCM2835_I2C_DEL 0x18 /* Data Delay */ +#define BCM2835_I2C_CLKT 0x20 /* Clock Stretch Timeout */ + +#define BCM2835_I2C_C_I2CEN BIT(15) /* I2C enable */ +#define BCM2835_I2C_C_INTR BIT(10) /* Interrupt on RXR */ +#define BCM2835_I2C_C_INTT BIT(9) /* Interrupt on TXW */ +#define BCM2835_I2C_C_INTD BIT(8) /* Interrupt on DONE */ +#define BCM2835_I2C_C_ST BIT(7) /* Start transfer */ +#define BCM2835_I2C_C_CLEAR (BIT(5) | BIT(4)) /* Clear FIFO */ +#define BCM2835_I2C_C_READ BIT(0) /* I2C read mode */ + +#define BCM2835_I2C_S_CLKT BIT(9) /* Clock stretch timeout */ +#define BCM2835_I2C_S_ERR BIT(8) /* Slave error */ +#define BCM2835_I2C_S_RXF BIT(7) /* RX FIFO full */ +#define BCM2835_I2C_S_TXE BIT(6) /* TX FIFO empty */ +#define BCM2835_I2C_S_RXD BIT(5) /* RX bytes available */ +#define BCM2835_I2C_S_TXD BIT(4) /* TX space available */ +#define BCM2835_I2C_S_RXR BIT(3) /* RX FIFO needs reading */ +#define BCM2835_I2C_S_TXW BIT(2) /* TX FIFO needs writing */ +#define BCM2835_I2C_S_DONE BIT(1) /* I2C Transfer complete */ +#define BCM2835_I2C_S_TA BIT(0) /* I2C Transfer active */ + +struct BCM2835I2CState { + /* <private> */ + SysBusDevice parent_obj; + + /* <public> */ + MemoryRegion iomem; + I2CBus *bus; + qemu_irq irq; + + uint32_t c; + uint32_t s; + uint32_t dlen; + uint32_t a; + uint32_t div; + uint32_t del; + uint32_t clkt; + + uint32_t last_dlen; +}; diff --git a/hw/i2c/bcm2835_i2c.c b/hw/i2c/bcm2835_i2c.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/i2c/bcm2835_i2c.c @@ -XXX,XX +XXX,XX @@ +/* + * Broadcom Serial Controller (BSC) + * + * Copyright (c) 2024 Rayhan Faizel <rayhan.faizel@gmail.com> + * + * SPDX-License-Identifier: MIT + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "hw/i2c/bcm2835_i2c.h" +#include "hw/irq.h" +#include "migration/vmstate.h" + +static void bcm2835_i2c_update_interrupt(BCM2835I2CState *s) +{ + int do_interrupt = 0; + /* Interrupt on RXR (Needs reading) */ + if (s->c & BCM2835_I2C_C_INTR && s->s & BCM2835_I2C_S_RXR) { + do_interrupt = 1; + } + + /* Interrupt on TXW (Needs writing) */ + if (s->c & BCM2835_I2C_C_INTT && s->s & BCM2835_I2C_S_TXW) { + do_interrupt = 1; + } + + /* Interrupt on DONE (Transfer complete) */ + if (s->c & BCM2835_I2C_C_INTD && s->s & BCM2835_I2C_S_DONE) { + do_interrupt = 1; + } + qemu_set_irq(s->irq, do_interrupt); +} + +static void bcm2835_i2c_begin_transfer(BCM2835I2CState *s) +{ + int direction = s->c & BCM2835_I2C_C_READ; + if (i2c_start_transfer(s->bus, s->a, direction)) { + s->s |= BCM2835_I2C_S_ERR; + } + s->s |= BCM2835_I2C_S_TA; + + if (direction) { + s->s |= BCM2835_I2C_S_RXR | BCM2835_I2C_S_RXD; + } else { + s->s |= BCM2835_I2C_S_TXW; + } +} + +static void bcm2835_i2c_finish_transfer(BCM2835I2CState *s) +{ + /* + * STOP is sent when DLEN counts down to zero. + * + * https://github.com/torvalds/linux/blob/v6.7/drivers/i2c/busses/i2c-bcm2835.c#L223-L261 + * It is possible to initiate repeated starts on real hardware. + * However, this requires sending another ST request before the bytes in + * TX FIFO are shifted out. + * + * This is not emulated currently. + */ + i2c_end_transfer(s->bus); + s->s |= BCM2835_I2C_S_DONE; + + /* Ensure RXD is cleared, otherwise the driver registers an error */ + s->s &= ~(BCM2835_I2C_S_TA | BCM2835_I2C_S_RXR | + BCM2835_I2C_S_TXW | BCM2835_I2C_S_RXD); +} + +static uint64_t bcm2835_i2c_read(void *opaque, hwaddr addr, unsigned size) +{ + BCM2835I2CState *s = opaque; + uint32_t readval = 0; + + switch (addr) { + case BCM2835_I2C_C: + readval = s->c; + break; + case BCM2835_I2C_S: + readval = s->s; + break; + case BCM2835_I2C_DLEN: + readval = s->dlen; + break; + case BCM2835_I2C_A: + readval = s->a; + break; + case BCM2835_I2C_FIFO: + /* We receive I2C messages directly instead of using FIFOs */ + if (s->s & BCM2835_I2C_S_TA) { + readval = i2c_recv(s->bus); + s->dlen -= 1; + + if (s->dlen == 0) { + bcm2835_i2c_finish_transfer(s); + } + } + bcm2835_i2c_update_interrupt(s); + break; + case BCM2835_I2C_DIV: + readval = s->div; + break; + case BCM2835_I2C_DEL: + readval = s->del; + break; + case BCM2835_I2C_CLKT: + readval = s->clkt; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, addr); + } + + return readval; +} + +static void bcm2835_i2c_write(void *opaque, hwaddr addr, + uint64_t value, unsigned int size) +{ + BCM2835I2CState *s = opaque; + uint32_t writeval = value; + + switch (addr) { + case BCM2835_I2C_C: + /* ST is a one-shot operation; it must read back as 0 */ + s->c = writeval & ~BCM2835_I2C_C_ST; + + /* Start transfer */ + if (writeval & (BCM2835_I2C_C_ST | BCM2835_I2C_C_I2CEN)) { + bcm2835_i2c_begin_transfer(s); + /* + * Handle special case where transfer starts with zero data length. + * Required for zero length i2c quick messages to work. + */ + if (s->dlen == 0) { + bcm2835_i2c_finish_transfer(s); + } + } + + bcm2835_i2c_update_interrupt(s); + break; + case BCM2835_I2C_S: + if (writeval & BCM2835_I2C_S_DONE && s->s & BCM2835_I2C_S_DONE) { + /* When DONE is cleared, DLEN should read last written value. */ + s->dlen = s->last_dlen; + } + + /* Clear DONE, CLKT and ERR by writing 1 */ + s->s &= ~(writeval & (BCM2835_I2C_S_DONE | + BCM2835_I2C_S_ERR | BCM2835_I2C_S_CLKT)); + break; + case BCM2835_I2C_DLEN: + s->dlen = writeval; + s->last_dlen = writeval; + break; + case BCM2835_I2C_A: + s->a = writeval; + break; + case BCM2835_I2C_FIFO: + /* We send I2C messages directly instead of using FIFOs */ + if (s->s & BCM2835_I2C_S_TA) { + if (s->s & BCM2835_I2C_S_TXD) { + if (!i2c_send(s->bus, writeval & 0xff)) { + s->dlen -= 1; + } else { + s->s |= BCM2835_I2C_S_ERR; + } + } + + if (s->dlen == 0) { + bcm2835_i2c_finish_transfer(s); + } + } + bcm2835_i2c_update_interrupt(s); + break; + case BCM2835_I2C_DIV: + s->div = writeval; + break; + case BCM2835_I2C_DEL: + s->del = writeval; + break; + case BCM2835_I2C_CLKT: + s->clkt = writeval; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%" HWADDR_PRIx "\n", __func__, addr); + } +} + +static const MemoryRegionOps bcm2835_i2c_ops = { + .read = bcm2835_i2c_read, + .write = bcm2835_i2c_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void bcm2835_i2c_realize(DeviceState *dev, Error **errp) +{ + BCM2835I2CState *s = BCM2835_I2C(dev); + s->bus = i2c_init_bus(dev, NULL); + + memory_region_init_io(&s->iomem, OBJECT(dev), &bcm2835_i2c_ops, s, + TYPE_BCM2835_I2C, 0x24); + sysbus_init_mmio(SYS_BUS_DEVICE(dev), &s->iomem); + sysbus_init_irq(SYS_BUS_DEVICE(dev), &s->irq); +} + +static void bcm2835_i2c_reset(DeviceState *dev) +{ + BCM2835I2CState *s = BCM2835_I2C(dev); + + /* Reset values according to BCM2835 Peripheral Documentation */ + s->c = 0x0; + s->s = BCM2835_I2C_S_TXD | BCM2835_I2C_S_TXE; + s->dlen = 0x0; + s->a = 0x0; + s->div = 0x5dc; + s->del = 0x00300030; + s->clkt = 0x40; +} + +static const VMStateDescription vmstate_bcm2835_i2c = { + .name = TYPE_BCM2835_I2C, + .version_id = 1, + .minimum_version_id = 1, + .fields = (const VMStateField[]) { + VMSTATE_UINT32(c, BCM2835I2CState), + VMSTATE_UINT32(s, BCM2835I2CState), + VMSTATE_UINT32(dlen, BCM2835I2CState), + VMSTATE_UINT32(a, BCM2835I2CState), + VMSTATE_UINT32(div, BCM2835I2CState), + VMSTATE_UINT32(del, BCM2835I2CState), + VMSTATE_UINT32(clkt, BCM2835I2CState), + VMSTATE_UINT32(last_dlen, BCM2835I2CState), + VMSTATE_END_OF_LIST() + } +}; + +static void bcm2835_i2c_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = bcm2835_i2c_reset; + dc->realize = bcm2835_i2c_realize; + dc->vmsd = &vmstate_bcm2835_i2c; +} + +static const TypeInfo bcm2835_i2c_info = { + .name = TYPE_BCM2835_I2C, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(BCM2835I2CState), + .class_init = bcm2835_i2c_class_init, +}; + +static void bcm2835_i2c_register_types(void) +{ + type_register_static(&bcm2835_i2c_info); +} + +type_init(bcm2835_i2c_register_types) diff --git a/hw/i2c/Kconfig b/hw/i2c/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/Kconfig +++ b/hw/i2c/Kconfig @@ -XXX,XX +XXX,XX @@ config PCA954X config PMBUS bool select SMBUS + +config BCM2835_I2C + bool + select I2C diff --git a/hw/i2c/meson.build b/hw/i2c/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/i2c/meson.build +++ b/hw/i2c/meson.build @@ -XXX,XX +XXX,XX @@ i2c_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_i2c.c')) i2c_ss.add(when: 'CONFIG_PPC4XX', if_true: files('ppc4xx_i2c.c')) i2c_ss.add(when: 'CONFIG_PCA954X', if_true: files('i2c_mux_pca954x.c')) i2c_ss.add(when: 'CONFIG_PMBUS', if_true: files('pmbus_device.c')) +i2c_ss.add(when: 'CONFIG_BCM2835_I2C', if_true: files('bcm2835_i2c.c')) system_ss.add_all(when: 'CONFIG_I2C', if_true: i2c_ss) -- 2.34.1 From: Rayhan Faizel <rayhan.faizel@gmail.com> BCM2835 has three I2C controllers. All of them share the same interrupt line. Signed-off-by: Rayhan Faizel <rayhan.faizel@gmail.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20240224191038.2409945-3-rayhan.faizel@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/bcm2835_peripherals.h | 4 ++- hw/arm/bcm2835_peripherals.c | 45 ++++++++++++++++++++++++++-- hw/arm/Kconfig | 1 + 3 files changed, 46 insertions(+), 4 deletions(-) diff --git a/include/hw/arm/bcm2835_peripherals.h b/include/hw/arm/bcm2835_peripherals.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/bcm2835_peripherals.h +++ b/include/hw/arm/bcm2835_peripherals.h @@ -XXX,XX +XXX,XX @@ #include "hw/timer/bcm2835_systmr.h" #include "hw/usb/hcd-dwc2.h" #include "hw/ssi/bcm2835_spi.h" +#include "hw/i2c/bcm2835_i2c.h" #include "hw/misc/unimp.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct BCMSocPeripheralBaseState { BCM2835SDHostState sdhost; UnimplementedDeviceState i2s; BCM2835SPIState spi[1]; - UnimplementedDeviceState i2c[3]; + BCM2835I2CState i2c[3]; + OrIRQState orgated_i2c_irq; UnimplementedDeviceState otp; UnimplementedDeviceState dbus; UnimplementedDeviceState ave0; diff --git a/hw/arm/bcm2835_peripherals.c b/hw/arm/bcm2835_peripherals.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/bcm2835_peripherals.c +++ b/hw/arm/bcm2835_peripherals.c @@ -XXX,XX +XXX,XX @@ #define SEPARATE_DMA_IRQ_MAX 10 #define ORGATED_DMA_IRQ_COUNT 4 +/* All three I2C controllers share the same IRQ */ +#define ORGATED_I2C_IRQ_COUNT 3 + void create_unimp(BCMSocPeripheralBaseState *ps, UnimplementedDeviceState *uds, const char *name, hwaddr ofs, hwaddr size) @@ -XXX,XX +XXX,XX @@ static void raspi_peripherals_base_init(Object *obj) /* SPI */ object_initialize_child(obj, "bcm2835-spi0", &s->spi[0], TYPE_BCM2835_SPI); + + /* I2C */ + object_initialize_child(obj, "bcm2835-i2c0", &s->i2c[0], + TYPE_BCM2835_I2C); + object_initialize_child(obj, "bcm2835-i2c1", &s->i2c[1], + TYPE_BCM2835_I2C); + object_initialize_child(obj, "bcm2835-i2c2", &s->i2c[2], + TYPE_BCM2835_I2C); + + object_initialize_child(obj, "orgated-i2c-irq", + &s->orgated_i2c_irq, TYPE_OR_IRQ); + object_property_set_int(OBJECT(&s->orgated_i2c_irq), "num-lines", + ORGATED_I2C_IRQ_COUNT, &error_abort); } static void bcm2835_peripherals_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ void bcm_soc_peripherals_common_realize(DeviceState *dev, Error **errp) BCM2835_IC_GPU_IRQ, INTERRUPT_SPI)); + /* I2C */ + for (n = 0; n < 3; n++) { + if (!sysbus_realize(SYS_BUS_DEVICE(&s->i2c[n]), errp)) { + return; + } + } + + memory_region_add_subregion(&s->peri_mr, BSC0_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->i2c[0]), 0)); + memory_region_add_subregion(&s->peri_mr, BSC1_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->i2c[1]), 0)); + memory_region_add_subregion(&s->peri_mr, BSC2_OFFSET, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->i2c[2]), 0)); + + if (!qdev_realize(DEVICE(&s->orgated_i2c_irq), NULL, errp)) { + return; + } + for (n = 0; n < ORGATED_I2C_IRQ_COUNT; n++) { + sysbus_connect_irq(SYS_BUS_DEVICE(&s->i2c[n]), 0, + qdev_get_gpio_in(DEVICE(&s->orgated_i2c_irq), n)); + } + qdev_connect_gpio_out(DEVICE(&s->orgated_i2c_irq), 0, + qdev_get_gpio_in_named(DEVICE(&s->ic), + BCM2835_IC_GPU_IRQ, + INTERRUPT_I2C)); + create_unimp(s, &s->txp, "bcm2835-txp", TXP_OFFSET, 0x1000); create_unimp(s, &s->armtmr, "bcm2835-sp804", ARMCTRL_TIMER0_1_OFFSET, 0x40); 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->i2c[0], "bcm2835-i2c0", BSC0_OFFSET, 0x20); - create_unimp(s, &s->i2c[1], "bcm2835-i2c1", BSC1_OFFSET, 0x20); - create_unimp(s, &s->i2c[2], "bcm2835-i2c2", BSC2_OFFSET, 0x20); 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); diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config RASPI select SDHCI select USB_DWC2 select BCM2835_SPI + select BCM2835_I2C config STM32F100_SOC bool -- 2.34.1 From: Rayhan Faizel <rayhan.faizel@gmail.com> Simple testcase for validating proper operation of read and write for all three BSC controllers. Signed-off-by: Rayhan Faizel <rayhan.faizel@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240224191038.2409945-4-rayhan.faizel@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/bcm2835-i2c-test.c | 115 +++++++++++++++++++++++++++++++++ tests/qtest/meson.build | 2 +- 2 files changed, 116 insertions(+), 1 deletion(-) create mode 100644 tests/qtest/bcm2835-i2c-test.c diff --git a/tests/qtest/bcm2835-i2c-test.c b/tests/qtest/bcm2835-i2c-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/bcm2835-i2c-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTest testcase for Broadcom Serial Controller (BSC) + * + * Copyright (c) 2024 Rayhan Faizel <rayhan.faizel@gmail.com> + * + * SPDX-License-Identifier: MIT + * + * Permission is hereby granted, free of charge, to any person obtaining a copy + * of this software and associated documentation files (the "Software"), to deal + * in the Software without restriction, including without limitation the rights + * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell + * copies of the Software, and to permit persons to whom the Software is + * furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, + * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN + * THE SOFTWARE. + */ + +#include "qemu/osdep.h" +#include "libqtest-single.h" + +#include "hw/i2c/bcm2835_i2c.h" +#include "hw/sensor/tmp105_regs.h" + +static const uint32_t bsc_base_addrs[] = { + 0x3f205000, /* I2C0 */ + 0x3f804000, /* I2C1 */ + 0x3f805000, /* I2C2 */ +}; + +static void bcm2835_i2c_init_transfer(uint32_t base_addr, bool read) +{ + /* read flag is bit 0 so we can write it directly */ + int interrupt = read ? BCM2835_I2C_C_INTR : BCM2835_I2C_C_INTT; + + writel(base_addr + BCM2835_I2C_C, + BCM2835_I2C_C_I2CEN | BCM2835_I2C_C_INTD | + BCM2835_I2C_C_ST | BCM2835_I2C_C_CLEAR | interrupt | read); +} + +static void test_i2c_read_write(gconstpointer data) +{ + uint32_t i2cdata; + intptr_t index = (intptr_t) data; + uint32_t base_addr = bsc_base_addrs[index]; + + /* Write to TMP105 register */ + writel(base_addr + BCM2835_I2C_A, 0x50); + writel(base_addr + BCM2835_I2C_DLEN, 3); + + bcm2835_i2c_init_transfer(base_addr, 0); + + writel(base_addr + BCM2835_I2C_FIFO, TMP105_REG_T_HIGH); + writel(base_addr + BCM2835_I2C_FIFO, 0xde); + writel(base_addr + BCM2835_I2C_FIFO, 0xad); + + /* Clear flags */ + writel(base_addr + BCM2835_I2C_S, BCM2835_I2C_S_DONE | BCM2835_I2C_S_ERR | + BCM2835_I2C_S_CLKT); + + /* Read from TMP105 register */ + writel(base_addr + BCM2835_I2C_A, 0x50); + writel(base_addr + BCM2835_I2C_DLEN, 1); + + bcm2835_i2c_init_transfer(base_addr, 0); + + writel(base_addr + BCM2835_I2C_FIFO, TMP105_REG_T_HIGH); + + writel(base_addr + BCM2835_I2C_DLEN, 2); + bcm2835_i2c_init_transfer(base_addr, 1); + + i2cdata = readl(base_addr + BCM2835_I2C_FIFO); + g_assert_cmpint(i2cdata, ==, 0xde); + + i2cdata = readl(base_addr + BCM2835_I2C_FIFO); + g_assert_cmpint(i2cdata, ==, 0xad); + + /* Clear flags */ + writel(base_addr + BCM2835_I2C_S, BCM2835_I2C_S_DONE | BCM2835_I2C_S_ERR | + BCM2835_I2C_S_CLKT); + +} + +int main(int argc, char **argv) +{ + int ret; + int i; + + g_test_init(&argc, &argv, NULL); + + for (i = 0; i < 3; i++) { + g_autofree char *test_name = + g_strdup_printf("/bcm2835/bcm2835-i2c%d/read_write", i); + qtest_add_data_func(test_name, (void *)(intptr_t) i, + test_i2c_read_write); + } + + /* Run I2C tests with TMP105 slaves on all three buses */ + qtest_start("-M raspi3b " + "-device tmp105,address=0x50,bus=i2c-bus.0 " + "-device tmp105,address=0x50,bus=i2c-bus.1 " + "-device tmp105,address=0x50,bus=i2c-bus.2"); + ret = g_test_run(); + qtest_end(); + + return ret; +} diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qtests_aarch64 = \ ['tpm-tis-device-test', 'tpm-tis-device-swtpm-test'] : []) + \ (config_all_devices.has_key('CONFIG_XLNX_ZYNQMP_ARM') ? ['xlnx-can-test', 'fuzz-xlnx-dp-test'] : []) + \ (config_all_devices.has_key('CONFIG_XLNX_VERSAL') ? ['xlnx-canfd-test', 'xlnx-versal-trng-test'] : []) + \ - (config_all_devices.has_key('CONFIG_RASPI') ? ['bcm2835-dma-test'] : []) + \ + (config_all_devices.has_key('CONFIG_RASPI') ? ['bcm2835-dma-test', 'bcm2835-i2c-test'] : []) + \ (config_all_accel.has_key('CONFIG_TCG') and \ config_all_devices.has_key('CONFIG_TPM_TIS_I2C') ? ['tpm-tis-i2c-test'] : []) + \ ['arm-cpu-features', -- 2.34.1 From: Tong Ho <tong.ho@amd.com> This patch adds loopback for sent characters, sent BREAK, and modem-control signals. Loopback of send and modem-control is often used for uart self tests in real hardware but missing from current pl011 model, resulting in self-test failures when running in QEMU. This implementation matches what is observed in real pl011 hardware placed in loopback mode: 1. Input characters and BREAK events from serial backend are ignored, but 2. Both TX characters and BREAK events are still sent to serial backend, in addition to be looped back to RX. Signed-off-by: Tong Ho <tong.ho@amd.com> Signed-off-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20240227054855.44204-1-tong.ho@amd.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/pl011.c | 110 +++++++++++++++++++++++++++++++++++++++++++++++- 1 file changed, 108 insertions(+), 2 deletions(-) diff --git a/hw/char/pl011.c b/hw/char/pl011.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/pl011.c +++ b/hw/char/pl011.c @@ -XXX,XX +XXX,XX @@ DeviceState *pl011_create(hwaddr addr, qemu_irq irq, Chardev *chr) } /* Flag Register, UARTFR */ +#define PL011_FLAG_RI 0x100 #define PL011_FLAG_TXFE 0x80 #define PL011_FLAG_RXFF 0x40 #define PL011_FLAG_TXFF 0x20 #define PL011_FLAG_RXFE 0x10 +#define PL011_FLAG_DCD 0x04 +#define PL011_FLAG_DSR 0x02 +#define PL011_FLAG_CTS 0x01 /* Data Register, UARTDR */ #define DR_BE (1 << 10) @@ -XXX,XX +XXX,XX @@ DeviceState *pl011_create(hwaddr addr, qemu_irq irq, Chardev *chr) #define LCR_FEN (1 << 4) #define LCR_BRK (1 << 0) +/* Control Register, UARTCR */ +#define CR_OUT2 (1 << 13) +#define CR_OUT1 (1 << 12) +#define CR_RTS (1 << 11) +#define CR_DTR (1 << 10) +#define CR_LBE (1 << 7) + static const unsigned char pl011_id_arm[8] = { 0x11, 0x10, 0x14, 0x00, 0x0d, 0xf0, 0x05, 0xb1 }; static const unsigned char pl011_id_luminary[8] = @@ -XXX,XX +XXX,XX @@ static void pl011_trace_baudrate_change(const PL011State *s) s->ibrd, s->fbrd); } +static bool pl011_loopback_enabled(PL011State *s) +{ + return !!(s->cr & CR_LBE); +} + +static void pl011_loopback_mdmctrl(PL011State *s) +{ + uint32_t cr, fr, il; + + if (!pl011_loopback_enabled(s)) { + return; + } + + /* + * Loopback software-driven modem control outputs to modem status inputs: + * FR.RI <= CR.Out2 + * FR.DCD <= CR.Out1 + * FR.CTS <= CR.RTS + * FR.DSR <= CR.DTR + * + * The loopback happens immediately even if this call is triggered + * by setting only CR.LBE. + * + * CTS/RTS updates due to enabled hardware flow controls are not + * dealt with here. + */ + cr = s->cr; + fr = s->flags & ~(PL011_FLAG_RI | PL011_FLAG_DCD | + PL011_FLAG_DSR | PL011_FLAG_CTS); + fr |= (cr & CR_OUT2) ? PL011_FLAG_RI : 0; + fr |= (cr & CR_OUT1) ? PL011_FLAG_DCD : 0; + fr |= (cr & CR_RTS) ? PL011_FLAG_CTS : 0; + fr |= (cr & CR_DTR) ? PL011_FLAG_DSR : 0; + + /* Change interrupts based on updated FR */ + il = s->int_level & ~(INT_DSR | INT_DCD | INT_CTS | INT_RI); + il |= (fr & PL011_FLAG_DSR) ? INT_DSR : 0; + il |= (fr & PL011_FLAG_DCD) ? INT_DCD : 0; + il |= (fr & PL011_FLAG_CTS) ? INT_CTS : 0; + il |= (fr & PL011_FLAG_RI) ? INT_RI : 0; + + s->flags = fr; + s->int_level = il; + pl011_update(s); +} + +static void pl011_put_fifo(void *opaque, uint32_t value); + +static void pl011_loopback_tx(PL011State *s, uint32_t value) +{ + if (!pl011_loopback_enabled(s)) { + return; + } + + /* + * Caveat: + * + * In real hardware, TX loopback happens at the serial-bit level + * and then reassembled by the RX logics back into bytes and placed + * into the RX fifo. That is, loopback happens after TX fifo. + * + * Because the real hardware TX fifo is time-drained at the frame + * rate governed by the configured serial format, some loopback + * bytes in TX fifo may still be able to get into the RX fifo + * that could be full at times while being drained at software + * pace. + * + * In such scenario, the RX draining pace is the major factor + * deciding which loopback bytes get into the RX fifo, unless + * hardware flow-control is enabled. + * + * For simplicity, the above described is not emulated. + */ + pl011_put_fifo(s, value); +} + +static void pl011_loopback_break(PL011State *s, int brk_enable) +{ + if (brk_enable) { + pl011_loopback_tx(s, DR_BE); + } +} + static void pl011_write(void *opaque, hwaddr offset, uint64_t value, unsigned size) { @@ -XXX,XX +XXX,XX @@ static void pl011_write(void *opaque, hwaddr offset, /* XXX this blocks entire thread. Rewrite to use * qemu_chr_fe_write and background I/O callbacks */ qemu_chr_fe_write_all(&s->chr, &ch, 1); + pl011_loopback_tx(s, ch); s->int_level |= INT_TX; pl011_update(s); break; @@ -XXX,XX +XXX,XX @@ static void pl011_write(void *opaque, hwaddr offset, int break_enable = value & LCR_BRK; qemu_chr_fe_ioctl(&s->chr, CHR_IOCTL_SERIAL_SET_BREAK, &break_enable); + pl011_loopback_break(s, break_enable); } s->lcr = value; pl011_set_read_trigger(s); break; case 12: /* UARTCR */ - /* ??? Need to implement the enable and loopback bits. */ + /* ??? Need to implement the enable bit. */ s->cr = value; + pl011_loopback_mdmctrl(s); break; case 13: /* UARTIFS */ s->ifl = value; @@ -XXX,XX +XXX,XX @@ static void pl011_put_fifo(void *opaque, uint32_t value) static void pl011_receive(void *opaque, const uint8_t *buf, int size) { + /* + * In loopback mode, the RX input signal is internally disconnected + * from the entire receiving logics; thus, all inputs are ignored, + * and BREAK detection on RX input signal is also not performed. + */ + if (pl011_loopback_enabled(opaque)) { + return; + } + pl011_put_fifo(opaque, *buf); } static void pl011_event(void *opaque, QEMUChrEvent event) { - if (event == CHR_EVENT_BREAK) { + if (event == CHR_EVENT_BREAK && !pl011_loopback_enabled(opaque)) { pl011_put_fifo(opaque, DR_BE); } } -- 2.34.1 From: Arnaud Minier <arnaud.minier@telecom-paris.fr> Add the necessary files to add a simple RCC implementation with just reads from and writes to registers. Also instantiate the RCC in the STM32L4x5_SoC. It is needed for accurate emulation of all the SoC clocks and timers. Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Acked-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240303140643.81957-2-arnaud.minier@telecom-paris.fr Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 5 +- docs/system/arm/b-l475e-iot01a.rst | 2 +- include/hw/arm/stm32l4x5_soc.h | 2 + include/hw/misc/stm32l4x5_rcc.h | 80 ++++ include/hw/misc/stm32l4x5_rcc_internals.h | 286 ++++++++++++++ hw/arm/stm32l4x5_soc.c | 12 +- hw/misc/stm32l4x5_rcc.c | 446 ++++++++++++++++++++++ hw/arm/Kconfig | 1 + hw/misc/Kconfig | 3 + hw/misc/meson.build | 1 + hw/misc/trace-events | 4 + 11 files changed, 839 insertions(+), 3 deletions(-) create mode 100644 include/hw/misc/stm32l4x5_rcc.h create mode 100644 include/hw/misc/stm32l4x5_rcc_internals.h create mode 100644 hw/misc/stm32l4x5_rcc.c diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Inès Varhol <ines.varhol@telecom-paris.fr> L: qemu-arm@nongnu.org S: Maintained F: hw/arm/stm32l4x5_soc.c -F: include/hw/arm/stm32l4x5_soc.h +F: hw/misc/stm32l4x5_exti.c +F: hw/misc/stm32l4x5_syscfg.c +F: hw/misc/stm32l4x5_rcc.c +F: include/hw/*/stm32l4x5_*.h B-L475E-IOT01A IoT Node M: Arnaud Minier <arnaud.minier@telecom-paris.fr> diff --git a/docs/system/arm/b-l475e-iot01a.rst b/docs/system/arm/b-l475e-iot01a.rst index XXXXXXX..XXXXXXX 100644 --- a/docs/system/arm/b-l475e-iot01a.rst +++ b/docs/system/arm/b-l475e-iot01a.rst @@ -XXX,XX +XXX,XX @@ Currently B-L475E-IOT01A machine's only supports the following devices: - Cortex-M4F based STM32L4x5 SoC - STM32L4x5 EXTI (Extended interrupts and events controller) - STM32L4x5 SYSCFG (System configuration controller) +- STM32L4x5 RCC (Reset and clock control) Missing devices """"""""""""""" The B-L475E-IOT01A does *not* support the following devices: -- Reset and clock control (RCC) - Serial ports (UART) - General-purpose I/Os (GPIO) - Analog to Digital Converter (ADC) diff --git a/include/hw/arm/stm32l4x5_soc.h b/include/hw/arm/stm32l4x5_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/stm32l4x5_soc.h +++ b/include/hw/arm/stm32l4x5_soc.h @@ -XXX,XX +XXX,XX @@ #include "hw/or-irq.h" #include "hw/misc/stm32l4x5_syscfg.h" #include "hw/misc/stm32l4x5_exti.h" +#include "hw/misc/stm32l4x5_rcc.h" #include "qom/object.h" #define TYPE_STM32L4X5_SOC "stm32l4x5-soc" @@ -XXX,XX +XXX,XX @@ struct Stm32l4x5SocState { Stm32l4x5ExtiState exti; OrIRQState exti_or_gates[NUM_EXTI_OR_GATES]; Stm32l4x5SyscfgState syscfg; + Stm32l4x5RccState rcc; MemoryRegion sram1; MemoryRegion sram2; diff --git a/include/hw/misc/stm32l4x5_rcc.h b/include/hw/misc/stm32l4x5_rcc.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/stm32l4x5_rcc.h @@ -XXX,XX +XXX,XX @@ +/* + * STM32L4X5 RCC (Reset and clock control) + * + * Copyright (c) 2023 Arnaud Minier <arnaud.minier@telecom-paris.fr> + * Copyright (c) 2023 Inès Varhol <ines.varhol@telecom-paris.fr> + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + * The reference used is the STMicroElectronics RM0351 Reference manual + * for STM32L4x5 and STM32L4x6 advanced Arm ® -based 32-bit MCUs. + * + * Inspired by the BCM2835 CPRMAN clock manager by Luc Michel. + */ + +#ifndef HW_STM32L4X5_RCC_H +#define HW_STM32L4X5_RCC_H + +#include "hw/sysbus.h" +#include "qom/object.h" + +#define TYPE_STM32L4X5_RCC "stm32l4x5-rcc" +OBJECT_DECLARE_SIMPLE_TYPE(Stm32l4x5RccState, STM32L4X5_RCC) + +/* In the Stm32l4x5 clock tree, mux have at most 7 sources */ +#define RCC_NUM_CLOCK_MUX_SRC 7 +struct Stm32l4x5RccState { + SysBusDevice parent_obj; + + MemoryRegion mmio; + + uint32_t cr; + uint32_t icscr; + uint32_t cfgr; + uint32_t pllcfgr; + uint32_t pllsai1cfgr; + uint32_t pllsai2cfgr; + uint32_t cier; + uint32_t cifr; + uint32_t ahb1rstr; + uint32_t ahb2rstr; + uint32_t ahb3rstr; + uint32_t apb1rstr1; + uint32_t apb1rstr2; + uint32_t apb2rstr; + uint32_t ahb1enr; + uint32_t ahb2enr; + uint32_t ahb3enr; + uint32_t apb1enr1; + uint32_t apb1enr2; + uint32_t apb2enr; + uint32_t ahb1smenr; + uint32_t ahb2smenr; + uint32_t ahb3smenr; + uint32_t apb1smenr1; + uint32_t apb1smenr2; + uint32_t apb2smenr; + uint32_t ccipr; + uint32_t bdcr; + uint32_t csr; + + /* Clock sources */ + Clock *gnd; + Clock *hsi16_rc; + Clock *msi_rc; + Clock *hse; + Clock *lsi_rc; + Clock *lse_crystal; + Clock *sai1_extclk; + Clock *sai2_extclk; + + qemu_irq irq; + uint64_t hse_frequency; + uint64_t sai1_extclk_frequency; + uint64_t sai2_extclk_frequency; +}; + +#endif /* HW_STM32L4X5_RCC_H */ diff --git a/include/hw/misc/stm32l4x5_rcc_internals.h b/include/hw/misc/stm32l4x5_rcc_internals.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/stm32l4x5_rcc_internals.h @@ -XXX,XX +XXX,XX @@ +/* + * STM32L4X5 RCC (Reset and clock control) + * + * Copyright (c) 2023 Arnaud Minier <arnaud.minier@telecom-paris.fr> + * Copyright (c) 2023 Inès Varhol <ines.varhol@telecom-paris.fr> + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + * The reference used is the STMicroElectronics RM0351 Reference manual + * for STM32L4x5 and STM32L4x6 advanced Arm ® -based 32-bit MCUs. + * + * Inspired by the BCM2835 CPRMAN clock manager implementation by Luc Michel. + */ + +#ifndef HW_STM32L4X5_RCC_INTERNALS_H +#define HW_STM32L4X5_RCC_INTERNALS_H + +#include "hw/registerfields.h" +#include "hw/misc/stm32l4x5_rcc.h" + + +/* Register map */ +REG32(CR, 0x00) + FIELD(CR, PLLSAI2RDY, 29, 1) + FIELD(CR, PLLSAI2ON, 28, 1) + FIELD(CR, PLLSAI1RDY, 27, 1) + FIELD(CR, PLLSAI1ON, 26, 1) + FIELD(CR, PLLRDY, 25, 1) + FIELD(CR, PLLON, 24, 1) + FIELD(CR, CSSON, 19, 1) + FIELD(CR, HSEBYP, 18, 1) + FIELD(CR, HSERDY, 17, 1) + FIELD(CR, HSEON, 16, 1) + FIELD(CR, HSIASFS, 11, 1) + FIELD(CR, HSIRDY, 10, 1) + FIELD(CR, HSIKERON, 9, 1) + FIELD(CR, HSION, 8, 1) + FIELD(CR, MSIRANGE, 4, 4) + FIELD(CR, MSIRGSEL, 3, 1) + FIELD(CR, MSIPLLEN, 2, 1) + FIELD(CR, MSIRDY, 1, 1) + FIELD(CR, MSION, 0, 1) +REG32(ICSCR, 0x04) + FIELD(ICSCR, HSITRIM, 24, 7) + FIELD(ICSCR, HSICAL, 16, 8) + FIELD(ICSCR, MSITRIM, 8, 8) + FIELD(ICSCR, MSICAL, 0, 8) +REG32(CFGR, 0x08) + FIELD(CFGR, MCOPRE, 28, 3) + /* MCOSEL[2:0] only for STM32L475xx/476xx/486xx devices */ + FIELD(CFGR, MCOSEL, 24, 3) + FIELD(CFGR, STOPWUCK, 15, 1) + FIELD(CFGR, PPRE2, 11, 3) + FIELD(CFGR, PPRE1, 8, 3) + FIELD(CFGR, HPRE, 4, 4) + FIELD(CFGR, SWS, 2, 2) + FIELD(CFGR, SW, 0, 2) +REG32(PLLCFGR, 0x0C) + FIELD(PLLCFGR, PLLPDIV, 27, 5) + FIELD(PLLCFGR, PLLR, 25, 2) + FIELD(PLLCFGR, PLLREN, 24, 1) + FIELD(PLLCFGR, PLLQ, 21, 2) + FIELD(PLLCFGR, PLLQEN, 20, 1) + FIELD(PLLCFGR, PLLP, 17, 1) + FIELD(PLLCFGR, PLLPEN, 16, 1) + FIELD(PLLCFGR, PLLN, 8, 7) + FIELD(PLLCFGR, PLLM, 4, 3) + FIELD(PLLCFGR, PLLSRC, 0, 2) +REG32(PLLSAI1CFGR, 0x10) + FIELD(PLLSAI1CFGR, PLLSAI1PDIV, 27, 5) + FIELD(PLLSAI1CFGR, PLLSAI1R, 25, 2) + FIELD(PLLSAI1CFGR, PLLSAI1REN, 24, 1) + FIELD(PLLSAI1CFGR, PLLSAI1Q, 21, 2) + FIELD(PLLSAI1CFGR, PLLSAI1QEN, 20, 1) + FIELD(PLLSAI1CFGR, PLLSAI1P, 17, 1) + FIELD(PLLSAI1CFGR, PLLSAI1PEN, 16, 1) + FIELD(PLLSAI1CFGR, PLLSAI1N, 8, 7) +REG32(PLLSAI2CFGR, 0x14) + FIELD(PLLSAI2CFGR, PLLSAI2PDIV, 27, 5) + FIELD(PLLSAI2CFGR, PLLSAI2R, 25, 2) + FIELD(PLLSAI2CFGR, PLLSAI2REN, 24, 1) + FIELD(PLLSAI2CFGR, PLLSAI2Q, 21, 2) + FIELD(PLLSAI2CFGR, PLLSAI2QEN, 20, 1) + FIELD(PLLSAI2CFGR, PLLSAI2P, 17, 1) + FIELD(PLLSAI2CFGR, PLLSAI2PEN, 16, 1) + FIELD(PLLSAI2CFGR, PLLSAI2N, 8, 7) +REG32(CIER, 0x18) + /* HSI48RDYIE: only on STM32L496xx/4A6xx devices */ + FIELD(CIER, LSECSSIE, 9, 1) + FIELD(CIER, PLLSAI2RDYIE, 7, 1) + FIELD(CIER, PLLSAI1RDYIE, 6, 1) + FIELD(CIER, PLLRDYIE, 5, 1) + FIELD(CIER, HSERDYIE, 4, 1) + FIELD(CIER, HSIRDYIE, 3, 1) + FIELD(CIER, MSIRDYIE, 2, 1) + FIELD(CIER, LSERDYIE, 1, 1) + FIELD(CIER, LSIRDYIE, 0, 1) +REG32(CIFR, 0x1C) + /* HSI48RDYF: only on STM32L496xx/4A6xx devices */ + FIELD(CIFR, LSECSSF, 9, 1) + FIELD(CIFR, CSSF, 8, 1) + FIELD(CIFR, PLLSAI2RDYF, 7, 1) + FIELD(CIFR, PLLSAI1RDYF, 6, 1) + FIELD(CIFR, PLLRDYF, 5, 1) + FIELD(CIFR, HSERDYF, 4, 1) + FIELD(CIFR, HSIRDYF, 3, 1) + FIELD(CIFR, MSIRDYF, 2, 1) + FIELD(CIFR, LSERDYF, 1, 1) + FIELD(CIFR, LSIRDYF, 0, 1) +REG32(CICR, 0x20) + /* HSI48RDYC: only on STM32L496xx/4A6xx devices */ + FIELD(CICR, LSECSSC, 9, 1) + FIELD(CICR, CSSC, 8, 1) + FIELD(CICR, PLLSAI2RDYC, 7, 1) + FIELD(CICR, PLLSAI1RDYC, 6, 1) + FIELD(CICR, PLLRDYC, 5, 1) + FIELD(CICR, HSERDYC, 4, 1) + FIELD(CICR, HSIRDYC, 3, 1) + FIELD(CICR, MSIRDYC, 2, 1) + FIELD(CICR, LSERDYC, 1, 1) + FIELD(CICR, LSIRDYC, 0, 1) +REG32(AHB1RSTR, 0x28) +REG32(AHB2RSTR, 0x2C) +REG32(AHB3RSTR, 0x30) +REG32(APB1RSTR1, 0x38) +REG32(APB1RSTR2, 0x3C) +REG32(APB2RSTR, 0x40) +REG32(AHB1ENR, 0x48) + /* DMA2DEN: reserved for STM32L475xx */ + FIELD(AHB1ENR, TSCEN, 16, 1) + FIELD(AHB1ENR, CRCEN, 12, 1) + FIELD(AHB1ENR, FLASHEN, 8, 1) + FIELD(AHB1ENR, DMA2EN, 1, 1) + FIELD(AHB1ENR, DMA1EN, 0, 1) +REG32(AHB2ENR, 0x4C) + FIELD(AHB2ENR, RNGEN, 18, 1) + /* HASHEN: reserved for STM32L475xx */ + FIELD(AHB2ENR, AESEN, 16, 1) + /* DCMIEN: reserved for STM32L475xx */ + FIELD(AHB2ENR, ADCEN, 13, 1) + FIELD(AHB2ENR, OTGFSEN, 12, 1) + /* GPIOIEN: reserved for STM32L475xx */ + FIELD(AHB2ENR, GPIOHEN, 7, 1) + FIELD(AHB2ENR, GPIOGEN, 6, 1) + FIELD(AHB2ENR, GPIOFEN, 5, 1) + FIELD(AHB2ENR, GPIOEEN, 4, 1) + FIELD(AHB2ENR, GPIODEN, 3, 1) + FIELD(AHB2ENR, GPIOCEN, 2, 1) + FIELD(AHB2ENR, GPIOBEN, 1, 1) + FIELD(AHB2ENR, GPIOAEN, 0, 1) +REG32(AHB3ENR, 0x50) + FIELD(AHB3ENR, QSPIEN, 8, 1) + FIELD(AHB3ENR, FMCEN, 0, 1) +REG32(APB1ENR1, 0x58) + FIELD(APB1ENR1, LPTIM1EN, 31, 1) + FIELD(APB1ENR1, OPAMPEN, 30, 1) + FIELD(APB1ENR1, DAC1EN, 29, 1) + FIELD(APB1ENR1, PWREN, 28, 1) + FIELD(APB1ENR1, CAN2EN, 26, 1) + FIELD(APB1ENR1, CAN1EN, 25, 1) + /* CRSEN: reserved for STM32L475xx */ + FIELD(APB1ENR1, I2C3EN, 23, 1) + FIELD(APB1ENR1, I2C2EN, 22, 1) + FIELD(APB1ENR1, I2C1EN, 21, 1) + FIELD(APB1ENR1, UART5EN, 20, 1) + FIELD(APB1ENR1, UART4EN, 19, 1) + FIELD(APB1ENR1, USART3EN, 18, 1) + FIELD(APB1ENR1, USART2EN, 17, 1) + FIELD(APB1ENR1, SPI3EN, 15, 1) + FIELD(APB1ENR1, SPI2EN, 14, 1) + FIELD(APB1ENR1, WWDGEN, 11, 1) + /* RTCAPBEN: reserved for STM32L475xx */ + FIELD(APB1ENR1, LCDEN, 9, 1) + FIELD(APB1ENR1, TIM7EN, 5, 1) + FIELD(APB1ENR1, TIM6EN, 4, 1) + FIELD(APB1ENR1, TIM5EN, 3, 1) + FIELD(APB1ENR1, TIM4EN, 2, 1) + FIELD(APB1ENR1, TIM3EN, 1, 1) + FIELD(APB1ENR1, TIM2EN, 0, 1) +REG32(APB1ENR2, 0x5C) + FIELD(APB1ENR2, LPTIM2EN, 5, 1) + FIELD(APB1ENR2, SWPMI1EN, 2, 1) + /* I2C4EN: reserved for STM32L475xx */ + FIELD(APB1ENR2, LPUART1EN, 0, 1) +REG32(APB2ENR, 0x60) + FIELD(APB2ENR, DFSDM1EN, 24, 1) + FIELD(APB2ENR, SAI2EN, 22, 1) + FIELD(APB2ENR, SAI1EN, 21, 1) + FIELD(APB2ENR, TIM17EN, 18, 1) + FIELD(APB2ENR, TIM16EN, 17, 1) + FIELD(APB2ENR, TIM15EN, 16, 1) + FIELD(APB2ENR, USART1EN, 14, 1) + FIELD(APB2ENR, TIM8EN, 13, 1) + FIELD(APB2ENR, SPI1EN, 12, 1) + FIELD(APB2ENR, TIM1EN, 11, 1) + FIELD(APB2ENR, SDMMC1EN, 10, 1) + FIELD(APB2ENR, FWEN, 7, 1) + FIELD(APB2ENR, SYSCFGEN, 0, 1) +REG32(AHB1SMENR, 0x68) +REG32(AHB2SMENR, 0x6C) +REG32(AHB3SMENR, 0x70) +REG32(APB1SMENR1, 0x78) +REG32(APB1SMENR2, 0x7C) +REG32(APB2SMENR, 0x80) +REG32(CCIPR, 0x88) + FIELD(CCIPR, DFSDM1SEL, 31, 1) + FIELD(CCIPR, SWPMI1SEL, 30, 1) + FIELD(CCIPR, ADCSEL, 28, 2) + FIELD(CCIPR, CLK48SEL, 26, 2) + FIELD(CCIPR, SAI2SEL, 24, 2) + FIELD(CCIPR, SAI1SEL, 22, 2) + FIELD(CCIPR, LPTIM2SEL, 20, 2) + FIELD(CCIPR, LPTIM1SEL, 18, 2) + FIELD(CCIPR, I2C3SEL, 16, 2) + FIELD(CCIPR, I2C2SEL, 14, 2) + FIELD(CCIPR, I2C1SEL, 12, 2) + FIELD(CCIPR, LPUART1SEL, 10, 2) + FIELD(CCIPR, UART5SEL, 8, 2) + FIELD(CCIPR, UART4SEL, 6, 2) + FIELD(CCIPR, USART3SEL, 4, 2) + FIELD(CCIPR, USART2SEL, 2, 2) + FIELD(CCIPR, USART1SEL, 0, 2) +REG32(BDCR, 0x90) + FIELD(BDCR, LSCOSEL, 25, 1) + FIELD(BDCR, LSCOEN, 24, 1) + FIELD(BDCR, BDRST, 16, 1) + FIELD(BDCR, RTCEN, 15, 1) + FIELD(BDCR, RTCSEL, 8, 2) + FIELD(BDCR, LSECSSD, 6, 1) + FIELD(BDCR, LSECSSON, 5, 1) + FIELD(BDCR, LSEDRV, 3, 2) + FIELD(BDCR, LSEBYP, 2, 1) + FIELD(BDCR, LSERDY, 1, 1) + FIELD(BDCR, LSEON, 0, 1) +REG32(CSR, 0x94) + FIELD(CSR, LPWRRSTF, 31, 1) + FIELD(CSR, WWDGRSTF, 30, 1) + FIELD(CSR, IWWGRSTF, 29, 1) + FIELD(CSR, SFTRSTF, 28, 1) + FIELD(CSR, BORRSTF, 27, 1) + FIELD(CSR, PINRSTF, 26, 1) + FIELD(CSR, OBLRSTF, 25, 1) + FIELD(CSR, FWRSTF, 24, 1) + FIELD(CSR, RMVF, 23, 1) + FIELD(CSR, MSISRANGE, 8, 4) + FIELD(CSR, LSIRDY, 1, 1) + FIELD(CSR, LSION, 0, 1) +/* CRRCR and CCIPR2 registers are present on L496/L4A6 devices only. */ + +/* Read Only masks to prevent writes in unauthorized bits */ +#define CR_READ_ONLY_MASK (R_CR_PLLSAI2RDY_MASK | \ + R_CR_PLLSAI1RDY_MASK | \ + R_CR_PLLRDY_MASK | \ + R_CR_HSERDY_MASK | \ + R_CR_HSIRDY_MASK | \ + R_CR_MSIRDY_MASK) +#define CR_READ_SET_MASK (R_CR_CSSON_MASK | R_CR_MSIRGSEL_MASK) +#define ICSCR_READ_ONLY_MASK (R_ICSCR_HSICAL_MASK | R_ICSCR_MSICAL_MASK) +#define CFGR_READ_ONLY_MASK (R_CFGR_SWS_MASK) +#define CIFR_READ_ONLY_MASK (R_CIFR_LSECSSF_MASK | \ + R_CIFR_CSSF_MASK | \ + R_CIFR_PLLSAI2RDYF_MASK | \ + R_CIFR_PLLSAI1RDYF_MASK | \ + R_CIFR_PLLRDYF_MASK | \ + R_CIFR_HSERDYF_MASK | \ + R_CIFR_HSIRDYF_MASK | \ + R_CIFR_MSIRDYF_MASK | \ + R_CIFR_LSERDYF_MASK | \ + R_CIFR_LSIRDYF_MASK) +#define CIFR_IRQ_MASK CIFR_READ_ONLY_MASK +#define APB2ENR_READ_SET_MASK (R_APB2ENR_FWEN_MASK) +#define BDCR_READ_ONLY_MASK (R_BDCR_LSECSSD_MASK | R_BDCR_LSERDY_MASK) +#define CSR_READ_ONLY_MASK (R_CSR_LPWRRSTF_MASK | \ + R_CSR_WWDGRSTF_MASK | \ + R_CSR_IWWGRSTF_MASK | \ + R_CSR_SFTRSTF_MASK | \ + R_CSR_BORRSTF_MASK | \ + R_CSR_PINRSTF_MASK | \ + R_CSR_OBLRSTF_MASK | \ + R_CSR_FWRSTF_MASK | \ + R_CSR_LSIRDY_MASK) + +#endif /* HW_STM32L4X5_RCC_INTERNALS_H */ diff --git a/hw/arm/stm32l4x5_soc.c b/hw/arm/stm32l4x5_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32l4x5_soc.c +++ b/hw/arm/stm32l4x5_soc.c @@ -XXX,XX +XXX,XX @@ static const int exti_irq[NUM_EXTI_IRQ] = { -1, -1, -1, -1, /* PVM[1..4] OR gate 1 */ 78 /* LCD wakeup, Direct */ }; +#define RCC_BASE_ADDRESS 0x40021000 +#define RCC_IRQ 5 static const int exti_or_gates_out[NUM_EXTI_OR_GATES] = { 23, 40, 63, 1, @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_soc_initfn(Object *obj) TYPE_OR_IRQ); } object_initialize_child(obj, "syscfg", &s->syscfg, TYPE_STM32L4X5_SYSCFG); + object_initialize_child(obj, "rcc", &s->rcc, TYPE_STM32L4X5_RCC); s->sysclk = qdev_init_clock_in(DEVICE(s), "sysclk", NULL, NULL, 0); s->refclk = qdev_init_clock_in(DEVICE(s), "refclk", NULL, NULL, 0); @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_soc_realize(DeviceState *dev_soc, Error **errp) qdev_get_gpio_in(DEVICE(&s->exti), i)); } + /* RCC device */ + busdev = SYS_BUS_DEVICE(&s->rcc); + if (!sysbus_realize(busdev, errp)) { + return; + } + sysbus_mmio_map(busdev, 0, RCC_BASE_ADDRESS); + sysbus_connect_irq(busdev, 0, qdev_get_gpio_in(armv7m, RCC_IRQ)); + /* APB1 BUS */ create_unimplemented_device("TIM2", 0x40000000, 0x400); create_unimplemented_device("TIM3", 0x40000400, 0x400); @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_soc_realize(DeviceState *dev_soc, Error **errp) create_unimplemented_device("DMA1", 0x40020000, 0x400); create_unimplemented_device("DMA2", 0x40020400, 0x400); /* RESERVED: 0x40020800, 0x800 */ - create_unimplemented_device("RCC", 0x40021000, 0x400); /* RESERVED: 0x40021400, 0xC00 */ create_unimplemented_device("FLASH", 0x40022000, 0x400); /* RESERVED: 0x40022400, 0xC00 */ diff --git a/hw/misc/stm32l4x5_rcc.c b/hw/misc/stm32l4x5_rcc.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/stm32l4x5_rcc.c @@ -XXX,XX +XXX,XX @@ +/* + * STM32L4X5 RCC (Reset and clock control) + * + * Copyright (c) 2023 Arnaud Minier <arnaud.minier@telecom-paris.fr> + * Copyright (c) 2023 Inès Varhol <ines.varhol@telecom-paris.fr> + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + * + * The reference used is the STMicroElectronics RM0351 Reference manual + * for STM32L4x5 and STM32L4x6 advanced Arm ® -based 32-bit MCUs. + * + * Inspired by the BCM2835 CPRMAN clock manager implementation by Luc Michel. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "qemu/module.h" +#include "qemu/timer.h" +#include "qapi/error.h" +#include "migration/vmstate.h" +#include "hw/misc/stm32l4x5_rcc.h" +#include "hw/misc/stm32l4x5_rcc_internals.h" +#include "hw/clock.h" +#include "hw/irq.h" +#include "hw/qdev-clock.h" +#include "hw/qdev-properties.h" +#include "hw/qdev-properties-system.h" +#include "trace.h" + +#define HSE_DEFAULT_FRQ 48000000ULL +#define HSI_FRQ 16000000ULL +#define MSI_DEFAULT_FRQ 4000000ULL +#define LSE_FRQ 32768ULL +#define LSI_FRQ 32000ULL + +static void rcc_update_irq(Stm32l4x5RccState *s) +{ + if (s->cifr & CIFR_IRQ_MASK) { + qemu_irq_raise(s->irq); + } else { + qemu_irq_lower(s->irq); + } +} + +static void stm32l4x5_rcc_reset_hold(Object *obj) +{ + Stm32l4x5RccState *s = STM32L4X5_RCC(obj); + s->cr = 0x00000063; + /* + * Factory-programmed calibration data + * From the reference manual: 0x10XX 00XX + * Value taken from a real card. + */ + s->icscr = 0x106E0082; + s->cfgr = 0x0; + s->pllcfgr = 0x00001000; + s->pllsai1cfgr = 0x00001000; + s->pllsai2cfgr = 0x00001000; + s->cier = 0x0; + s->cifr = 0x0; + s->ahb1rstr = 0x0; + s->ahb2rstr = 0x0; + s->ahb3rstr = 0x0; + s->apb1rstr1 = 0x0; + s->apb1rstr2 = 0x0; + s->apb2rstr = 0x0; + s->ahb1enr = 0x00000100; + s->ahb2enr = 0x0; + s->ahb3enr = 0x0; + s->apb1enr1 = 0x0; + s->apb1enr2 = 0x0; + s->apb2enr = 0x0; + s->ahb1smenr = 0x00011303; + s->ahb2smenr = 0x000532FF; + s->ahb3smenr = 0x00000101; + s->apb1smenr1 = 0xF2FECA3F; + s->apb1smenr2 = 0x00000025; + s->apb2smenr = 0x01677C01; + s->ccipr = 0x0; + s->bdcr = 0x0; + s->csr = 0x0C000600; +} + +static uint64_t stm32l4x5_rcc_read(void *opaque, hwaddr addr, + unsigned int size) +{ + Stm32l4x5RccState *s = opaque; + uint64_t retvalue = 0; + + switch (addr) { + case A_CR: + retvalue = s->cr; + break; + case A_ICSCR: + retvalue = s->icscr; + break; + case A_CFGR: + retvalue = s->cfgr; + break; + case A_PLLCFGR: + retvalue = s->pllcfgr; + break; + case A_PLLSAI1CFGR: + retvalue = s->pllsai1cfgr; + break; + case A_PLLSAI2CFGR: + retvalue = s->pllsai2cfgr; + break; + case A_CIER: + retvalue = s->cier; + break; + case A_CIFR: + retvalue = s->cifr; + break; + case A_CICR: + /* CICR is write only, return the reset value = 0 */ + break; + case A_AHB1RSTR: + retvalue = s->ahb1rstr; + break; + case A_AHB2RSTR: + retvalue = s->ahb2rstr; + break; + case A_AHB3RSTR: + retvalue = s->ahb3rstr; + break; + case A_APB1RSTR1: + retvalue = s->apb1rstr1; + break; + case A_APB1RSTR2: + retvalue = s->apb1rstr2; + break; + case A_APB2RSTR: + retvalue = s->apb2rstr; + break; + case A_AHB1ENR: + retvalue = s->ahb1enr; + break; + case A_AHB2ENR: + retvalue = s->ahb2enr; + break; + case A_AHB3ENR: + retvalue = s->ahb3enr; + break; + case A_APB1ENR1: + retvalue = s->apb1enr1; + break; + case A_APB1ENR2: + retvalue = s->apb1enr2; + break; + case A_APB2ENR: + retvalue = s->apb2enr; + break; + case A_AHB1SMENR: + retvalue = s->ahb1smenr; + break; + case A_AHB2SMENR: + retvalue = s->ahb2smenr; + break; + case A_AHB3SMENR: + retvalue = s->ahb3smenr; + break; + case A_APB1SMENR1: + retvalue = s->apb1smenr1; + break; + case A_APB1SMENR2: + retvalue = s->apb1smenr2; + break; + case A_APB2SMENR: + retvalue = s->apb2smenr; + break; + case A_CCIPR: + retvalue = s->ccipr; + break; + case A_BDCR: + retvalue = s->bdcr; + break; + case A_CSR: + retvalue = s->csr; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%"HWADDR_PRIx"\n", __func__, addr); + break; + } + + trace_stm32l4x5_rcc_read(addr, retvalue); + + return retvalue; +} + +static void stm32l4x5_rcc_write(void *opaque, hwaddr addr, + uint64_t val64, unsigned int size) +{ + Stm32l4x5RccState *s = opaque; + const uint32_t value = val64; + + trace_stm32l4x5_rcc_write(addr, value); + + switch (addr) { + case A_CR: + s->cr = (s->cr & CR_READ_SET_MASK) | + (value & (CR_READ_SET_MASK | ~CR_READ_ONLY_MASK)); + break; + case A_ICSCR: + s->icscr = value & ~ICSCR_READ_ONLY_MASK; + break; + case A_CFGR: + s->cfgr = value & ~CFGR_READ_ONLY_MASK; + break; + case A_PLLCFGR: + s->pllcfgr = value; + break; + case A_PLLSAI1CFGR: + s->pllsai1cfgr = value; + break; + case A_PLLSAI2CFGR: + s->pllsai2cfgr = value; + break; + case A_CIER: + s->cier = value; + break; + case A_CIFR: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Write attempt into read-only register (CIFR) 0x%"PRIx32"\n", + __func__, value); + break; + case A_CICR: + /* Clear interrupt flags by writing a 1 to the CICR register */ + s->cifr &= ~value; + rcc_update_irq(s); + break; + /* Reset behaviors are not implemented */ + case A_AHB1RSTR: + s->ahb1rstr = value; + break; + case A_AHB2RSTR: + s->ahb2rstr = value; + break; + case A_AHB3RSTR: + s->ahb3rstr = value; + break; + case A_APB1RSTR1: + s->apb1rstr1 = value; + break; + case A_APB1RSTR2: + s->apb1rstr2 = value; + break; + case A_APB2RSTR: + s->apb2rstr = value; + break; + case A_AHB1ENR: + s->ahb1enr = value; + break; + case A_AHB2ENR: + s->ahb2enr = value; + break; + case A_AHB3ENR: + s->ahb3enr = value; + break; + case A_APB1ENR1: + s->apb1enr1 = value; + break; + case A_APB1ENR2: + s->apb1enr2 = value; + break; + case A_APB2ENR: + s->apb2enr = (s->apb2enr & APB2ENR_READ_SET_MASK) | value; + break; + /* Behaviors for Sleep and Stop modes are not implemented */ + case A_AHB1SMENR: + s->ahb1smenr = value; + break; + case A_AHB2SMENR: + s->ahb2smenr = value; + break; + case A_AHB3SMENR: + s->ahb3smenr = value; + break; + case A_APB1SMENR1: + s->apb1smenr1 = value; + break; + case A_APB1SMENR2: + s->apb1smenr2 = value; + break; + case A_APB2SMENR: + s->apb2smenr = value; + break; + case A_CCIPR: + s->ccipr = value; + break; + case A_BDCR: + s->bdcr = value & ~BDCR_READ_ONLY_MASK; + break; + case A_CSR: + s->csr = value & ~CSR_READ_ONLY_MASK; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Bad offset 0x%"HWADDR_PRIx"\n", __func__, addr); + } +} + +static const MemoryRegionOps stm32l4x5_rcc_ops = { + .read = stm32l4x5_rcc_read, + .write = stm32l4x5_rcc_write, + .endianness = DEVICE_NATIVE_ENDIAN, + .valid = { + .max_access_size = 4, + .min_access_size = 4, + .unaligned = false + }, + .impl = { + .max_access_size = 4, + .min_access_size = 4, + .unaligned = false + }, +}; + +static const ClockPortInitArray stm32l4x5_rcc_clocks = { + QDEV_CLOCK_IN(Stm32l4x5RccState, hsi16_rc, NULL, 0), + QDEV_CLOCK_IN(Stm32l4x5RccState, msi_rc, NULL, 0), + QDEV_CLOCK_IN(Stm32l4x5RccState, hse, NULL, 0), + QDEV_CLOCK_IN(Stm32l4x5RccState, lsi_rc, NULL, 0), + QDEV_CLOCK_IN(Stm32l4x5RccState, lse_crystal, NULL, 0), + QDEV_CLOCK_IN(Stm32l4x5RccState, sai1_extclk, NULL, 0), + QDEV_CLOCK_IN(Stm32l4x5RccState, sai2_extclk, NULL, 0), + QDEV_CLOCK_END +}; + + +static void stm32l4x5_rcc_init(Object *obj) +{ + Stm32l4x5RccState *s = STM32L4X5_RCC(obj); + + sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq); + + memory_region_init_io(&s->mmio, obj, &stm32l4x5_rcc_ops, s, + TYPE_STM32L4X5_RCC, 0x400); + sysbus_init_mmio(SYS_BUS_DEVICE(obj), &s->mmio); + + qdev_init_clocks(DEVICE(s), stm32l4x5_rcc_clocks); + + s->gnd = clock_new(obj, "gnd"); +} + +static const VMStateDescription vmstate_stm32l4x5_rcc = { + .name = TYPE_STM32L4X5_RCC, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(cr, Stm32l4x5RccState), + VMSTATE_UINT32(icscr, Stm32l4x5RccState), + VMSTATE_UINT32(cfgr, Stm32l4x5RccState), + VMSTATE_UINT32(pllcfgr, Stm32l4x5RccState), + VMSTATE_UINT32(pllsai1cfgr, Stm32l4x5RccState), + VMSTATE_UINT32(pllsai2cfgr, Stm32l4x5RccState), + VMSTATE_UINT32(cier, Stm32l4x5RccState), + VMSTATE_UINT32(cifr, Stm32l4x5RccState), + VMSTATE_UINT32(ahb1rstr, Stm32l4x5RccState), + VMSTATE_UINT32(ahb2rstr, Stm32l4x5RccState), + VMSTATE_UINT32(ahb3rstr, Stm32l4x5RccState), + VMSTATE_UINT32(apb1rstr1, Stm32l4x5RccState), + VMSTATE_UINT32(apb1rstr2, Stm32l4x5RccState), + VMSTATE_UINT32(apb2rstr, Stm32l4x5RccState), + VMSTATE_UINT32(ahb1enr, Stm32l4x5RccState), + VMSTATE_UINT32(ahb2enr, Stm32l4x5RccState), + VMSTATE_UINT32(ahb3enr, Stm32l4x5RccState), + VMSTATE_UINT32(apb1enr1, Stm32l4x5RccState), + VMSTATE_UINT32(apb1enr2, Stm32l4x5RccState), + VMSTATE_UINT32(apb2enr, Stm32l4x5RccState), + VMSTATE_UINT32(ahb1smenr, Stm32l4x5RccState), + VMSTATE_UINT32(ahb2smenr, Stm32l4x5RccState), + VMSTATE_UINT32(ahb3smenr, Stm32l4x5RccState), + VMSTATE_UINT32(apb1smenr1, Stm32l4x5RccState), + VMSTATE_UINT32(apb1smenr2, Stm32l4x5RccState), + VMSTATE_UINT32(apb2smenr, Stm32l4x5RccState), + VMSTATE_UINT32(ccipr, Stm32l4x5RccState), + VMSTATE_UINT32(bdcr, Stm32l4x5RccState), + VMSTATE_UINT32(csr, Stm32l4x5RccState), + VMSTATE_CLOCK(hsi16_rc, Stm32l4x5RccState), + VMSTATE_CLOCK(msi_rc, Stm32l4x5RccState), + VMSTATE_CLOCK(hse, Stm32l4x5RccState), + VMSTATE_CLOCK(lsi_rc, Stm32l4x5RccState), + VMSTATE_CLOCK(lse_crystal, Stm32l4x5RccState), + VMSTATE_CLOCK(sai1_extclk, Stm32l4x5RccState), + VMSTATE_CLOCK(sai2_extclk, Stm32l4x5RccState), + VMSTATE_END_OF_LIST() + } +}; + + +static void stm32l4x5_rcc_realize(DeviceState *dev, Error **errp) +{ + Stm32l4x5RccState *s = STM32L4X5_RCC(dev); + + if (s->hse_frequency < 4000000ULL || + s->hse_frequency > 48000000ULL) { + error_setg(errp, + "HSE frequency is outside of the allowed [4-48]Mhz range: %" PRIx64 "", + s->hse_frequency); + return; + } + + clock_update_hz(s->msi_rc, MSI_DEFAULT_FRQ); + clock_update_hz(s->sai1_extclk, s->sai1_extclk_frequency); + clock_update_hz(s->sai2_extclk, s->sai2_extclk_frequency); + clock_update(s->gnd, 0); +} + +static Property stm32l4x5_rcc_properties[] = { + DEFINE_PROP_UINT64("hse_frequency", Stm32l4x5RccState, + hse_frequency, HSE_DEFAULT_FRQ), + DEFINE_PROP_UINT64("sai1_extclk_frequency", Stm32l4x5RccState, + sai1_extclk_frequency, 0), + DEFINE_PROP_UINT64("sai2_extclk_frequency", Stm32l4x5RccState, + sai2_extclk_frequency, 0), + DEFINE_PROP_END_OF_LIST(), +}; + +static void stm32l4x5_rcc_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + + rc->phases.hold = stm32l4x5_rcc_reset_hold; + device_class_set_props(dc, stm32l4x5_rcc_properties); + dc->realize = stm32l4x5_rcc_realize; + dc->vmsd = &vmstate_stm32l4x5_rcc; +} + +static const TypeInfo stm32l4x5_rcc_types[] = { + { + .name = TYPE_STM32L4X5_RCC, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(Stm32l4x5RccState), + .instance_init = stm32l4x5_rcc_init, + .class_init = stm32l4x5_rcc_class_init, + } +}; + +DEFINE_TYPES(stm32l4x5_rcc_types) diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config STM32L4X5_SOC select OR_IRQ select STM32L4X5_SYSCFG select STM32L4X5_EXTI + select STM32L4X5_RCC config XLNX_ZYNQMP_ARM bool diff --git a/hw/misc/Kconfig b/hw/misc/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Kconfig +++ b/hw/misc/Kconfig @@ -XXX,XX +XXX,XX @@ config STM32L4X5_EXTI config STM32L4X5_SYSCFG bool +config STM32L4X5_RCC + bool + config MIPS_ITU bool diff --git a/hw/misc/meson.build b/hw/misc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/meson.build +++ b/hw/misc/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_STM32F4XX_SYSCFG', if_true: files('stm32f4xx_syscfg. system_ss.add(when: 'CONFIG_STM32F4XX_EXTI', if_true: files('stm32f4xx_exti.c')) system_ss.add(when: 'CONFIG_STM32L4X5_EXTI', if_true: files('stm32l4x5_exti.c')) system_ss.add(when: 'CONFIG_STM32L4X5_SYSCFG', if_true: files('stm32l4x5_syscfg.c')) +system_ss.add(when: 'CONFIG_STM32L4X5_RCC', if_true: files('stm32l4x5_rcc.c')) system_ss.add(when: 'CONFIG_MPS2_FPGAIO', if_true: files('mps2-fpgaio.c')) system_ss.add(when: 'CONFIG_MPS2_SCC', if_true: files('mps2-scc.c')) diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ stm32l4x5_exti_set_irq(int irq, int level) "Set EXTI: %d to %d" stm32l4x5_exti_read(uint64_t addr, uint64_t data) "reg read: addr: 0x%" PRIx64 " val: 0x%" PRIx64 "" stm32l4x5_exti_write(uint64_t addr, uint64_t data) "reg write: addr: 0x%" PRIx64 " val: 0x%" PRIx64 "" +# stm32l4x5_rcc.c +stm32l4x5_rcc_read(uint64_t addr, uint32_t data) "RCC: Read <0x%" PRIx64 "> -> 0x%" PRIx32 +stm32l4x5_rcc_write(uint64_t addr, uint32_t data) "RCC: Write <0x%" PRIx64 "> <- 0x%" PRIx32 + # tz-mpc.c tz_mpc_reg_read(uint32_t offset, uint64_t data, unsigned size) "TZ MPC regs read: offset 0x%x data 0x%" PRIx64 " size %u" tz_mpc_reg_write(uint32_t offset, uint64_t data, unsigned size) "TZ MPC regs write: offset 0x%x data 0x%" PRIx64 " size %u" -- 2.34.1 From: Arnaud Minier <arnaud.minier@telecom-paris.fr> This object is used to represent every multiplexer in the clock tree as well as every clock output, every presecaler, frequency multiplier, etc. This allows to use a generic approach for every component of the clock tree (except the PLLs). The migration handling is based on hw/misc/zynq_sclr.c. Three phase reset will be handled in a later commit. Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Acked-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20240303140643.81957-3-arnaud.minier@telecom-paris.fr Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/stm32l4x5_rcc.h | 119 ++++++++++++++++ include/hw/misc/stm32l4x5_rcc_internals.h | 29 ++++ hw/misc/stm32l4x5_rcc.c | 160 ++++++++++++++++++++++ hw/misc/trace-events | 5 + 4 files changed, 313 insertions(+) diff --git a/include/hw/misc/stm32l4x5_rcc.h b/include/hw/misc/stm32l4x5_rcc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/stm32l4x5_rcc.h +++ b/include/hw/misc/stm32l4x5_rcc.h @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(Stm32l4x5RccState, STM32L4X5_RCC) /* In the Stm32l4x5 clock tree, mux have at most 7 sources */ #define RCC_NUM_CLOCK_MUX_SRC 7 +/* NB: Prescaler are assimilated to mux with one source and one output */ +typedef enum RccClockMux { + /* Internal muxes that arent't exposed publicly to other peripherals */ + RCC_CLOCK_MUX_SYSCLK, + RCC_CLOCK_MUX_PLL_INPUT, + RCC_CLOCK_MUX_HCLK, + RCC_CLOCK_MUX_PCLK1, + RCC_CLOCK_MUX_PCLK2, + RCC_CLOCK_MUX_HSE_OVER_32, + RCC_CLOCK_MUX_LCD_AND_RTC_COMMON, + + /* Muxes with a publicly available output */ + RCC_CLOCK_MUX_CORTEX_REFCLK, + RCC_CLOCK_MUX_USART1, + RCC_CLOCK_MUX_USART2, + RCC_CLOCK_MUX_USART3, + RCC_CLOCK_MUX_UART4, + RCC_CLOCK_MUX_UART5, + RCC_CLOCK_MUX_LPUART1, + RCC_CLOCK_MUX_I2C1, + RCC_CLOCK_MUX_I2C2, + RCC_CLOCK_MUX_I2C3, + RCC_CLOCK_MUX_LPTIM1, + RCC_CLOCK_MUX_LPTIM2, + RCC_CLOCK_MUX_SWPMI1, + RCC_CLOCK_MUX_MCO, + RCC_CLOCK_MUX_LSCO, + RCC_CLOCK_MUX_DFSDM1, + RCC_CLOCK_MUX_ADC, + RCC_CLOCK_MUX_CLK48, + RCC_CLOCK_MUX_SAI1, + RCC_CLOCK_MUX_SAI2, + + /* + * Mux that have only one input and one output assigned to as peripheral. + * They could be direct lines but it is simpler + * to use the same logic for all outputs. + */ + /* - AHB1 */ + RCC_CLOCK_MUX_TSC, + RCC_CLOCK_MUX_CRC, + RCC_CLOCK_MUX_FLASH, + RCC_CLOCK_MUX_DMA2, + RCC_CLOCK_MUX_DMA1, + + /* - AHB2 */ + RCC_CLOCK_MUX_RNG, + RCC_CLOCK_MUX_AES, + RCC_CLOCK_MUX_OTGFS, + RCC_CLOCK_MUX_GPIOA, + RCC_CLOCK_MUX_GPIOB, + RCC_CLOCK_MUX_GPIOC, + RCC_CLOCK_MUX_GPIOD, + RCC_CLOCK_MUX_GPIOE, + RCC_CLOCK_MUX_GPIOF, + RCC_CLOCK_MUX_GPIOG, + RCC_CLOCK_MUX_GPIOH, + + /* - AHB3 */ + RCC_CLOCK_MUX_QSPI, + RCC_CLOCK_MUX_FMC, + + /* - APB1 */ + RCC_CLOCK_MUX_OPAMP, + RCC_CLOCK_MUX_DAC1, + RCC_CLOCK_MUX_PWR, + RCC_CLOCK_MUX_CAN1, + RCC_CLOCK_MUX_SPI3, + RCC_CLOCK_MUX_SPI2, + RCC_CLOCK_MUX_WWDG, + RCC_CLOCK_MUX_LCD, + RCC_CLOCK_MUX_TIM7, + RCC_CLOCK_MUX_TIM6, + RCC_CLOCK_MUX_TIM5, + RCC_CLOCK_MUX_TIM4, + RCC_CLOCK_MUX_TIM3, + RCC_CLOCK_MUX_TIM2, + + /* - APB2 */ + RCC_CLOCK_MUX_TIM17, + RCC_CLOCK_MUX_TIM16, + RCC_CLOCK_MUX_TIM15, + RCC_CLOCK_MUX_TIM8, + RCC_CLOCK_MUX_SPI1, + RCC_CLOCK_MUX_TIM1, + RCC_CLOCK_MUX_SDMMC1, + RCC_CLOCK_MUX_FW, + RCC_CLOCK_MUX_SYSCFG, + + /* - BDCR */ + RCC_CLOCK_MUX_RTC, + + /* - OTHER */ + RCC_CLOCK_MUX_CORTEX_FCLK, + + RCC_NUM_CLOCK_MUX +} RccClockMux; + +typedef struct RccClockMuxState { + DeviceState parent_obj; + + RccClockMux id; + Clock *srcs[RCC_NUM_CLOCK_MUX_SRC]; + Clock *out; + bool enabled; + uint32_t src; + uint32_t multiplier; + uint32_t divider; + + /* + * Used by clock srcs update callback to retrieve both the clock and the + * source number. + */ + struct RccClockMuxState *backref[RCC_NUM_CLOCK_MUX_SRC]; +} RccClockMuxState; + struct Stm32l4x5RccState { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct Stm32l4x5RccState { Clock *sai1_extclk; Clock *sai2_extclk; + /* Muxes ~= outputs */ + RccClockMuxState clock_muxes[RCC_NUM_CLOCK_MUX]; + qemu_irq irq; uint64_t hse_frequency; uint64_t sai1_extclk_frequency; diff --git a/include/hw/misc/stm32l4x5_rcc_internals.h b/include/hw/misc/stm32l4x5_rcc_internals.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/stm32l4x5_rcc_internals.h +++ b/include/hw/misc/stm32l4x5_rcc_internals.h @@ -XXX,XX +XXX,XX @@ #include "hw/registerfields.h" #include "hw/misc/stm32l4x5_rcc.h" +#define TYPE_RCC_CLOCK_MUX "stm32l4x5-rcc-clock-mux" +OBJECT_DECLARE_SIMPLE_TYPE(RccClockMuxState, RCC_CLOCK_MUX) /* Register map */ REG32(CR, 0x00) @@ -XXX,XX +XXX,XX @@ REG32(CSR, 0x94) R_CSR_FWRSTF_MASK | \ R_CSR_LSIRDY_MASK) +typedef enum RccClockMuxSource { + RCC_CLOCK_MUX_SRC_GND = 0, + RCC_CLOCK_MUX_SRC_HSI, + RCC_CLOCK_MUX_SRC_HSE, + RCC_CLOCK_MUX_SRC_MSI, + RCC_CLOCK_MUX_SRC_LSI, + RCC_CLOCK_MUX_SRC_LSE, + RCC_CLOCK_MUX_SRC_SAI1_EXTCLK, + RCC_CLOCK_MUX_SRC_SAI2_EXTCLK, + RCC_CLOCK_MUX_SRC_PLL, + RCC_CLOCK_MUX_SRC_PLLSAI1, + RCC_CLOCK_MUX_SRC_PLLSAI2, + RCC_CLOCK_MUX_SRC_PLLSAI3, + RCC_CLOCK_MUX_SRC_PLL48M1, + RCC_CLOCK_MUX_SRC_PLL48M2, + RCC_CLOCK_MUX_SRC_PLLADC1, + RCC_CLOCK_MUX_SRC_PLLADC2, + RCC_CLOCK_MUX_SRC_SYSCLK, + RCC_CLOCK_MUX_SRC_HCLK, + RCC_CLOCK_MUX_SRC_PCLK1, + RCC_CLOCK_MUX_SRC_PCLK2, + RCC_CLOCK_MUX_SRC_HSE_OVER_32, + RCC_CLOCK_MUX_SRC_LCD_AND_RTC_COMMON, + + RCC_CLOCK_MUX_SRC_NUMBER, +} RccClockMuxSource; + #endif /* HW_STM32L4X5_RCC_INTERNALS_H */ diff --git a/hw/misc/stm32l4x5_rcc.c b/hw/misc/stm32l4x5_rcc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/stm32l4x5_rcc.c +++ b/hw/misc/stm32l4x5_rcc.c @@ -XXX,XX +XXX,XX @@ #define LSE_FRQ 32768ULL #define LSI_FRQ 32000ULL +static void clock_mux_update(RccClockMuxState *mux) +{ + uint64_t src_freq; + Clock *current_source = mux->srcs[mux->src]; + uint32_t freq_multiplier = 0; + /* + * To avoid rounding errors, we use the clock period instead of the + * frequency. + * This means that the multiplier of the mux becomes the divider of + * the clock and the divider of the mux becomes the multiplier of the + * clock. + */ + if (mux->enabled && mux->divider) { + freq_multiplier = mux->divider; + } + + clock_set_mul_div(mux->out, freq_multiplier, mux->multiplier); + clock_update(mux->out, clock_get(current_source)); + + src_freq = clock_get_hz(current_source); + /* TODO: can we simply detect if the config changed so that we reduce log spam ? */ + trace_stm32l4x5_rcc_mux_update(mux->id, mux->src, src_freq, + mux->multiplier, mux->divider); +} + +static void clock_mux_src_update(void *opaque, ClockEvent event) +{ + RccClockMuxState **backref = opaque; + RccClockMuxState *s = *backref; + /* + * The backref value is equal to: + * s->backref + (sizeof(RccClockMuxState *) * update_src). + * By subtracting we can get back the index of the updated clock. + */ + const uint32_t update_src = backref - s->backref; + /* Only update if the clock that was updated is the current source */ + if (update_src == s->src) { + clock_mux_update(s); + } +} + +static void clock_mux_init(Object *obj) +{ + RccClockMuxState *s = RCC_CLOCK_MUX(obj); + size_t i; + + for (i = 0; i < RCC_NUM_CLOCK_MUX_SRC; i++) { + char *name = g_strdup_printf("srcs[%zu]", i); + s->backref[i] = s; + s->srcs[i] = qdev_init_clock_in(DEVICE(s), name, + clock_mux_src_update, + &s->backref[i], + ClockUpdate); + g_free(name); + } + + s->out = qdev_init_clock_out(DEVICE(s), "out"); +} + +static void clock_mux_reset_hold(Object *obj) +{ } + +static const VMStateDescription clock_mux_vmstate = { + .name = TYPE_RCC_CLOCK_MUX, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(id, RccClockMuxState), + VMSTATE_ARRAY_CLOCK(srcs, RccClockMuxState, + RCC_NUM_CLOCK_MUX_SRC), + VMSTATE_BOOL(enabled, RccClockMuxState), + VMSTATE_UINT32(src, RccClockMuxState), + VMSTATE_UINT32(multiplier, RccClockMuxState), + VMSTATE_UINT32(divider, RccClockMuxState), + VMSTATE_END_OF_LIST() + } +}; + +static void clock_mux_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.hold = clock_mux_reset_hold; + dc->vmsd = &clock_mux_vmstate; +} + +static void clock_mux_set_enable(RccClockMuxState *mux, bool enabled) +{ + if (mux->enabled == enabled) { + return; + } + + if (enabled) { + trace_stm32l4x5_rcc_mux_enable(mux->id); + } else { + trace_stm32l4x5_rcc_mux_disable(mux->id); + } + + mux->enabled = enabled; + clock_mux_update(mux); +} + +static void clock_mux_set_factor(RccClockMuxState *mux, + uint32_t multiplier, uint32_t divider) +{ + if (mux->multiplier == multiplier && mux->divider == divider) { + return; + } + trace_stm32l4x5_rcc_mux_set_factor(mux->id, + mux->multiplier, multiplier, mux->divider, divider); + + mux->multiplier = multiplier; + mux->divider = divider; + clock_mux_update(mux); +} + +static void clock_mux_set_source(RccClockMuxState *mux, RccClockMuxSource src) +{ + if (mux->src == src) { + return; + } + + trace_stm32l4x5_rcc_mux_set_src(mux->id, mux->src, src); + mux->src = src; + clock_mux_update(mux); +} + static void rcc_update_irq(Stm32l4x5RccState *s) { if (s->cifr & CIFR_IRQ_MASK) { @@ -XXX,XX +XXX,XX @@ static const ClockPortInitArray stm32l4x5_rcc_clocks = { static void stm32l4x5_rcc_init(Object *obj) { Stm32l4x5RccState *s = STM32L4X5_RCC(obj); + size_t i; sysbus_init_irq(SYS_BUS_DEVICE(obj), &s->irq); @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_rcc_init(Object *obj) qdev_init_clocks(DEVICE(s), stm32l4x5_rcc_clocks); + for (i = 0; i < RCC_NUM_CLOCK_MUX; i++) { + + object_initialize_child(obj, "clock[*]", + &s->clock_muxes[i], + TYPE_RCC_CLOCK_MUX); + + } + s->gnd = clock_new(obj, "gnd"); } @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_stm32l4x5_rcc = { static void stm32l4x5_rcc_realize(DeviceState *dev, Error **errp) { Stm32l4x5RccState *s = STM32L4X5_RCC(dev); + size_t i; if (s->hse_frequency < 4000000ULL || s->hse_frequency > 48000000ULL) { @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_rcc_realize(DeviceState *dev, Error **errp) return; } + for (i = 0; i < RCC_NUM_CLOCK_MUX; i++) { + RccClockMuxState *clock_mux = &s->clock_muxes[i]; + + if (!qdev_realize(DEVICE(clock_mux), NULL, errp)) { + return; + } + } + clock_update_hz(s->msi_rc, MSI_DEFAULT_FRQ); clock_update_hz(s->sai1_extclk, s->sai1_extclk_frequency); clock_update_hz(s->sai2_extclk, s->sai2_extclk_frequency); clock_update(s->gnd, 0); + + /* + * Dummy values to make compilation pass. + * Removed in later commits. + */ + clock_mux_set_source(&s->clock_muxes[0], RCC_CLOCK_MUX_SRC_GND); + clock_mux_set_enable(&s->clock_muxes[0], true); + clock_mux_set_factor(&s->clock_muxes[0], 1, 1); } static Property stm32l4x5_rcc_properties[] = { @@ -XXX,XX +XXX,XX @@ static const TypeInfo stm32l4x5_rcc_types[] = { .instance_size = sizeof(Stm32l4x5RccState), .instance_init = stm32l4x5_rcc_init, .class_init = stm32l4x5_rcc_class_init, + }, { + .name = TYPE_RCC_CLOCK_MUX, + .parent = TYPE_DEVICE, + .instance_size = sizeof(RccClockMuxState), + .instance_init = clock_mux_init, + .class_init = clock_mux_class_init, } }; diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ stm32l4x5_exti_write(uint64_t addr, uint64_t data) "reg write: addr: 0x%" PRIx64 # stm32l4x5_rcc.c stm32l4x5_rcc_read(uint64_t addr, uint32_t data) "RCC: Read <0x%" PRIx64 "> -> 0x%" PRIx32 stm32l4x5_rcc_write(uint64_t addr, uint32_t data) "RCC: Write <0x%" PRIx64 "> <- 0x%" PRIx32 +stm32l4x5_rcc_mux_enable(uint32_t mux_id) "RCC: Mux %d enabled" +stm32l4x5_rcc_mux_disable(uint32_t mux_id) "RCC: Mux %d disabled" +stm32l4x5_rcc_mux_set_factor(uint32_t mux_id, uint32_t old_multiplier, uint32_t new_multiplier, uint32_t old_divider, uint32_t new_divider) "RCC: Mux %d factor changed: multiplier (%u -> %u), divider (%u -> %u)" +stm32l4x5_rcc_mux_set_src(uint32_t mux_id, uint32_t old_src, uint32_t new_src) "RCC: Mux %d source changed: from %u to %u" +stm32l4x5_rcc_mux_update(uint32_t mux_id, uint32_t src, uint64_t src_freq, uint32_t multiplier, uint32_t divider) "RCC: Mux %d src %d update: src_freq %" PRIu64 " multiplier %" PRIu32 " divider %" PRIu32 # tz-mpc.c tz_mpc_reg_read(uint32_t offset, uint64_t data, unsigned size) "TZ MPC regs read: offset 0x%x data 0x%" PRIx64 " size %u" -- 2.34.1 From: Arnaud Minier <arnaud.minier@telecom-paris.fr> This object represents the PLLs and their channels. The PLLs allow for a more fine-grained control of the clocks frequency. The migration handling is based on hw/misc/zynq_sclr.c. Three phase reset will be handled in a later commit. Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Message-id: 20240303140643.81957-4-arnaud.minier@telecom-paris.fr Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/stm32l4x5_rcc.h | 40 +++++ include/hw/misc/stm32l4x5_rcc_internals.h | 22 +++ hw/misc/stm32l4x5_rcc.c | 176 ++++++++++++++++++++++ hw/misc/trace-events | 5 + 4 files changed, 243 insertions(+) diff --git a/include/hw/misc/stm32l4x5_rcc.h b/include/hw/misc/stm32l4x5_rcc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/stm32l4x5_rcc.h +++ b/include/hw/misc/stm32l4x5_rcc.h @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(Stm32l4x5RccState, STM32L4X5_RCC) /* In the Stm32l4x5 clock tree, mux have at most 7 sources */ #define RCC_NUM_CLOCK_MUX_SRC 7 + +typedef enum PllCommonChannels { + RCC_PLL_COMMON_CHANNEL_P = 0, + RCC_PLL_COMMON_CHANNEL_Q = 1, + RCC_PLL_COMMON_CHANNEL_R = 2, + + RCC_NUM_CHANNEL_PLL_OUT = 3 +} PllCommonChannels; + /* NB: Prescaler are assimilated to mux with one source and one output */ typedef enum RccClockMux { /* Internal muxes that arent't exposed publicly to other peripherals */ @@ -XXX,XX +XXX,XX @@ typedef enum RccClockMux { RCC_NUM_CLOCK_MUX } RccClockMux; +typedef enum RccPll { + RCC_PLL_PLL, + RCC_PLL_PLLSAI1, + RCC_PLL_PLLSAI2, + + RCC_NUM_PLL +} RccPll; + typedef struct RccClockMuxState { DeviceState parent_obj; @@ -XXX,XX +XXX,XX @@ typedef struct RccClockMuxState { struct RccClockMuxState *backref[RCC_NUM_CLOCK_MUX_SRC]; } RccClockMuxState; +typedef struct RccPllState { + DeviceState parent_obj; + + RccPll id; + Clock *in; + uint32_t vco_multiplier; + Clock *channels[RCC_NUM_CHANNEL_PLL_OUT]; + /* Global pll enabled flag */ + bool enabled; + /* 'enabled' refers to the runtime configuration */ + bool channel_enabled[RCC_NUM_CHANNEL_PLL_OUT]; + /* + * 'exists' refers to the physical configuration + * It should only be set at pll initialization. + * e.g. pllsai2 doesn't have a Q output. + */ + bool channel_exists[RCC_NUM_CHANNEL_PLL_OUT]; + uint32_t channel_divider[RCC_NUM_CHANNEL_PLL_OUT]; +} RccPllState; + struct Stm32l4x5RccState { SysBusDevice parent_obj; @@ -XXX,XX +XXX,XX @@ struct Stm32l4x5RccState { Clock *sai1_extclk; Clock *sai2_extclk; + /* PLLs */ + RccPllState plls[RCC_NUM_PLL]; + /* Muxes ~= outputs */ RccClockMuxState clock_muxes[RCC_NUM_CLOCK_MUX]; diff --git a/include/hw/misc/stm32l4x5_rcc_internals.h b/include/hw/misc/stm32l4x5_rcc_internals.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/stm32l4x5_rcc_internals.h +++ b/include/hw/misc/stm32l4x5_rcc_internals.h @@ -XXX,XX +XXX,XX @@ #include "hw/misc/stm32l4x5_rcc.h" #define TYPE_RCC_CLOCK_MUX "stm32l4x5-rcc-clock-mux" +#define TYPE_RCC_PLL "stm32l4x5-rcc-pll" + OBJECT_DECLARE_SIMPLE_TYPE(RccClockMuxState, RCC_CLOCK_MUX) +OBJECT_DECLARE_SIMPLE_TYPE(RccPllState, RCC_PLL) /* Register map */ REG32(CR, 0x00) @@ -XXX,XX +XXX,XX @@ REG32(CSR, 0x94) R_CSR_FWRSTF_MASK | \ R_CSR_LSIRDY_MASK) +/* Pll Channels */ +enum PllChannels { + RCC_PLL_CHANNEL_PLLSAI3CLK = 0, + RCC_PLL_CHANNEL_PLL48M1CLK = 1, + RCC_PLL_CHANNEL_PLLCLK = 2, +}; + +enum PllSai1Channels { + RCC_PLLSAI1_CHANNEL_PLLSAI1CLK = 0, + RCC_PLLSAI1_CHANNEL_PLL48M2CLK = 1, + RCC_PLLSAI1_CHANNEL_PLLADC1CLK = 2, +}; + +enum PllSai2Channels { + RCC_PLLSAI2_CHANNEL_PLLSAI2CLK = 0, + /* No Q channel */ + RCC_PLLSAI2_CHANNEL_PLLADC2CLK = 2, +}; + typedef enum RccClockMuxSource { RCC_CLOCK_MUX_SRC_GND = 0, RCC_CLOCK_MUX_SRC_HSI, diff --git a/hw/misc/stm32l4x5_rcc.c b/hw/misc/stm32l4x5_rcc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/stm32l4x5_rcc.c +++ b/hw/misc/stm32l4x5_rcc.c @@ -XXX,XX +XXX,XX @@ static void clock_mux_set_source(RccClockMuxState *mux, RccClockMuxSource src) clock_mux_update(mux); } +static void pll_update(RccPllState *pll) +{ + uint64_t vco_freq, old_channel_freq, channel_freq; + int i; + + /* The common PLLM factor is handled by the PLL mux */ + vco_freq = muldiv64(clock_get_hz(pll->in), pll->vco_multiplier, 1); + + for (i = 0; i < RCC_NUM_CHANNEL_PLL_OUT; i++) { + if (!pll->channel_exists[i]) { + continue; + } + + old_channel_freq = clock_get_hz(pll->channels[i]); + if (!pll->enabled || + !pll->channel_enabled[i] || + !pll->channel_divider[i]) { + channel_freq = 0; + } else { + channel_freq = muldiv64(vco_freq, + 1, + pll->channel_divider[i]); + } + + /* No change, early continue to avoid log spam and useless propagation */ + if (old_channel_freq == channel_freq) { + continue; + } + + clock_update_hz(pll->channels[i], channel_freq); + trace_stm32l4x5_rcc_pll_update(pll->id, i, vco_freq, + old_channel_freq, channel_freq); + } +} + +static void pll_src_update(void *opaque, ClockEvent event) +{ + RccPllState *s = opaque; + pll_update(s); +} + +static void pll_init(Object *obj) +{ + RccPllState *s = RCC_PLL(obj); + size_t i; + + s->in = qdev_init_clock_in(DEVICE(s), "in", + pll_src_update, s, ClockUpdate); + + const char *names[] = { + "out-p", "out-q", "out-r", + }; + + for (i = 0; i < RCC_NUM_CHANNEL_PLL_OUT; i++) { + s->channels[i] = qdev_init_clock_out(DEVICE(s), names[i]); + } +} + +static void pll_reset_hold(Object *obj) +{ } + +static const VMStateDescription pll_vmstate = { + .name = TYPE_RCC_PLL, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(id, RccPllState), + VMSTATE_CLOCK(in, RccPllState), + VMSTATE_ARRAY_CLOCK(channels, RccPllState, + RCC_NUM_CHANNEL_PLL_OUT), + VMSTATE_BOOL(enabled, RccPllState), + VMSTATE_UINT32(vco_multiplier, RccPllState), + VMSTATE_BOOL_ARRAY(channel_enabled, RccPllState, RCC_NUM_CHANNEL_PLL_OUT), + VMSTATE_BOOL_ARRAY(channel_exists, RccPllState, RCC_NUM_CHANNEL_PLL_OUT), + VMSTATE_UINT32_ARRAY(channel_divider, RccPllState, RCC_NUM_CHANNEL_PLL_OUT), + VMSTATE_END_OF_LIST() + } +}; + +static void pll_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.hold = pll_reset_hold; + dc->vmsd = &pll_vmstate; +} + +static void pll_set_vco_multiplier(RccPllState *pll, uint32_t vco_multiplier) +{ + if (pll->vco_multiplier == vco_multiplier) { + return; + } + + if (vco_multiplier < 8 || vco_multiplier > 86) { + qemu_log_mask(LOG_GUEST_ERROR, + "%s: VCO multiplier is out of bound (%u) for PLL %u\n", + __func__, vco_multiplier, pll->id); + return; + } + + trace_stm32l4x5_rcc_pll_set_vco_multiplier(pll->id, + pll->vco_multiplier, vco_multiplier); + + pll->vco_multiplier = vco_multiplier; + pll_update(pll); +} + +static void pll_set_enable(RccPllState *pll, bool enabled) +{ + if (pll->enabled == enabled) { + return; + } + + pll->enabled = enabled; + pll_update(pll); +} + +static void pll_set_channel_enable(RccPllState *pll, + PllCommonChannels channel, + bool enabled) +{ + if (pll->channel_enabled[channel] == enabled) { + return; + } + + if (enabled) { + trace_stm32l4x5_rcc_pll_channel_enable(pll->id, channel); + } else { + trace_stm32l4x5_rcc_pll_channel_disable(pll->id, channel); + } + + pll->channel_enabled[channel] = enabled; + pll_update(pll); +} + +static void pll_set_channel_divider(RccPllState *pll, + PllCommonChannels channel, + uint32_t divider) +{ + if (pll->channel_divider[channel] == divider) { + return; + } + + trace_stm32l4x5_rcc_pll_set_channel_divider(pll->id, + channel, pll->channel_divider[channel], divider); + + pll->channel_divider[channel] = divider; + pll_update(pll); +} + static void rcc_update_irq(Stm32l4x5RccState *s) { if (s->cifr & CIFR_IRQ_MASK) { @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_rcc_init(Object *obj) qdev_init_clocks(DEVICE(s), stm32l4x5_rcc_clocks); + for (i = 0; i < RCC_NUM_PLL; i++) { + object_initialize_child(obj, "pll[*]", + &s->plls[i], TYPE_RCC_PLL); + } + for (i = 0; i < RCC_NUM_CLOCK_MUX; i++) { object_initialize_child(obj, "clock[*]", @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_rcc_realize(DeviceState *dev, Error **errp) return; } + for (i = 0; i < RCC_NUM_PLL; i++) { + RccPllState *pll = &s->plls[i]; + + clock_set_source(pll->in, s->clock_muxes[RCC_CLOCK_MUX_PLL_INPUT].out); + + if (!qdev_realize(DEVICE(pll), NULL, errp)) { + return; + } + } + for (i = 0; i < RCC_NUM_CLOCK_MUX; i++) { RccClockMuxState *clock_mux = &s->clock_muxes[i]; @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_rcc_realize(DeviceState *dev, Error **errp) clock_mux_set_source(&s->clock_muxes[0], RCC_CLOCK_MUX_SRC_GND); clock_mux_set_enable(&s->clock_muxes[0], true); clock_mux_set_factor(&s->clock_muxes[0], 1, 1); + pll_set_channel_divider(&s->plls[0], 0, 1); + pll_set_enable(&s->plls[0], true); + pll_set_channel_enable(&s->plls[0], 0, true); + pll_set_vco_multiplier(&s->plls[0], 1); } static Property stm32l4x5_rcc_properties[] = { @@ -XXX,XX +XXX,XX @@ static const TypeInfo stm32l4x5_rcc_types[] = { .instance_size = sizeof(RccClockMuxState), .instance_init = clock_mux_init, .class_init = clock_mux_class_init, + }, { + .name = TYPE_RCC_PLL, + .parent = TYPE_DEVICE, + .instance_size = sizeof(RccPllState), + .instance_init = pll_init, + .class_init = pll_class_init, } }; diff --git a/hw/misc/trace-events b/hw/misc/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/trace-events +++ b/hw/misc/trace-events @@ -XXX,XX +XXX,XX @@ stm32l4x5_rcc_mux_disable(uint32_t mux_id) "RCC: Mux %d disabled" stm32l4x5_rcc_mux_set_factor(uint32_t mux_id, uint32_t old_multiplier, uint32_t new_multiplier, uint32_t old_divider, uint32_t new_divider) "RCC: Mux %d factor changed: multiplier (%u -> %u), divider (%u -> %u)" stm32l4x5_rcc_mux_set_src(uint32_t mux_id, uint32_t old_src, uint32_t new_src) "RCC: Mux %d source changed: from %u to %u" stm32l4x5_rcc_mux_update(uint32_t mux_id, uint32_t src, uint64_t src_freq, uint32_t multiplier, uint32_t divider) "RCC: Mux %d src %d update: src_freq %" PRIu64 " multiplier %" PRIu32 " divider %" PRIu32 +stm32l4x5_rcc_pll_set_vco_multiplier(uint32_t pll_id, uint32_t old_multiplier, uint32_t new_multiplier) "RCC: PLL %u: vco_multiplier changed (%u -> %u)" +stm32l4x5_rcc_pll_channel_enable(uint32_t pll_id, uint32_t channel_id) "RCC: PLL %u, channel %u enabled" +stm32l4x5_rcc_pll_channel_disable(uint32_t pll_id, uint32_t channel_id) "RCC: PLL %u, channel %u disabled" +stm32l4x5_rcc_pll_set_channel_divider(uint32_t pll_id, uint32_t channel_id, uint32_t old_divider, uint32_t new_divider) "RCC: PLL %u, channel %u: divider changed (%u -> %u)" +stm32l4x5_rcc_pll_update(uint32_t pll_id, uint32_t channel_id, uint64_t vco_freq, uint64_t old_freq, uint64_t new_freq) "RCC: PLL %d channel %d update: vco_freq %" PRIu64 " old_freq %" PRIu64 " new_freq %" PRIu64 # tz-mpc.c tz_mpc_reg_read(uint32_t offset, uint64_t data, unsigned size) "TZ MPC regs read: offset 0x%x data 0x%" PRIx64 " size %u" -- 2.34.1 From: Arnaud Minier <arnaud.minier@telecom-paris.fr> Instantiate the whole clock tree and using the Clock multiplexers and the PLLs defined in the previous commits. This allows to statically define the clock tree and easily follow the clock signal from one end to another. Also handle three-phase reset now that we have defined a known base state for every object. (Reset handling based on hw/misc/zynq_sclr.c) Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Message-id: 20240303140643.81957-5-arnaud.minier@telecom-paris.fr Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/misc/stm32l4x5_rcc_internals.h | 705 ++++++++++++++++++++++ hw/misc/stm32l4x5_rcc.c | 145 ++++- 2 files changed, 833 insertions(+), 17 deletions(-) diff --git a/include/hw/misc/stm32l4x5_rcc_internals.h b/include/hw/misc/stm32l4x5_rcc_internals.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/misc/stm32l4x5_rcc_internals.h +++ b/include/hw/misc/stm32l4x5_rcc_internals.h @@ -XXX,XX +XXX,XX @@ typedef enum RccClockMuxSource { RCC_CLOCK_MUX_SRC_NUMBER, } RccClockMuxSource; +/* PLL init info */ +typedef struct PllInitInfo { + const char *name; + + const char *channel_name[RCC_NUM_CHANNEL_PLL_OUT]; + bool channel_exists[RCC_NUM_CHANNEL_PLL_OUT]; + uint32_t default_channel_divider[RCC_NUM_CHANNEL_PLL_OUT]; + + RccClockMuxSource src_mapping[RCC_NUM_CLOCK_MUX_SRC]; +} PllInitInfo; + +static const PllInitInfo PLL_INIT_INFO[] = { + [RCC_PLL_PLL] = { + .name = "pll", + .channel_name = { + "pllsai3clk", + "pll48m1clk", + "pllclk" + }, + .channel_exists = { + true, true, true + }, + /* From PLLCFGR register documentation */ + .default_channel_divider = { + 7, 2, 2 + } + }, + [RCC_PLL_PLLSAI1] = { + .name = "pllsai1", + .channel_name = { + "pllsai1clk", + "pll48m2clk", + "plladc1clk" + }, + .channel_exists = { + true, true, true + }, + /* From PLLSAI1CFGR register documentation */ + .default_channel_divider = { + 7, 2, 2 + } + }, + [RCC_PLL_PLLSAI2] = { + .name = "pllsai2", + .channel_name = { + "pllsai2clk", + NULL, + "plladc2clk" + }, + .channel_exists = { + true, false, true + }, + /* From PLLSAI2CFGR register documentation */ + .default_channel_divider = { + 7, 0, 2 + } + } +}; + +static inline void set_pll_init_info(RccPllState *pll, + RccPll id) +{ + int i; + + pll->id = id; + pll->vco_multiplier = 1; + for (i = 0; i < RCC_NUM_CHANNEL_PLL_OUT; i++) { + pll->channel_enabled[i] = false; + pll->channel_exists[i] = PLL_INIT_INFO[id].channel_exists[i]; + pll->channel_divider[i] = PLL_INIT_INFO[id].default_channel_divider[i]; + } +} + +/* Clock mux init info */ +typedef struct ClockMuxInitInfo { + const char *name; + + uint32_t multiplier; + uint32_t divider; + bool enabled; + /* If this is true, the clock will not be exposed outside of the device */ + bool hidden; + + RccClockMuxSource src_mapping[RCC_NUM_CLOCK_MUX_SRC]; +} ClockMuxInitInfo; + +#define FILL_DEFAULT_FACTOR \ + .multiplier = 1, \ + .divider = 1 + +#define FILL_DEFAULT_INIT_ENABLED \ + FILL_DEFAULT_FACTOR, \ + .enabled = true + +#define FILL_DEFAULT_INIT_DISABLED \ + FILL_DEFAULT_FACTOR, \ + .enabled = false + + +static const ClockMuxInitInfo CLOCK_MUX_INIT_INFO[] = { + [RCC_CLOCK_MUX_SYSCLK] = { + .name = "sysclk", + /* Same mapping as: CFGR_SW */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_MSI, + RCC_CLOCK_MUX_SRC_HSI, + RCC_CLOCK_MUX_SRC_HSE, + RCC_CLOCK_MUX_SRC_PLL, + }, + .hidden = true, + FILL_DEFAULT_INIT_ENABLED, + }, + [RCC_CLOCK_MUX_PLL_INPUT] = { + .name = "pll-input", + /* Same mapping as: PLLCFGR_PLLSRC */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_MSI, + RCC_CLOCK_MUX_SRC_HSI, + RCC_CLOCK_MUX_SRC_HSE, + }, + .hidden = true, + FILL_DEFAULT_INIT_ENABLED, + }, + [RCC_CLOCK_MUX_HCLK] = { + .name = "hclk", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + .hidden = true, + FILL_DEFAULT_INIT_ENABLED, + }, + [RCC_CLOCK_MUX_PCLK1] = { + .name = "pclk1", + .src_mapping = { + RCC_CLOCK_MUX_SRC_HCLK, + }, + .hidden = true, + FILL_DEFAULT_INIT_ENABLED, + }, + [RCC_CLOCK_MUX_PCLK2] = { + .name = "pclk2", + .src_mapping = { + RCC_CLOCK_MUX_SRC_HCLK, + }, + .hidden = true, + FILL_DEFAULT_INIT_ENABLED, + }, + [RCC_CLOCK_MUX_HSE_OVER_32] = { + .name = "hse-divided-by-32", + .multiplier = 1, + .divider = 32, + .enabled = true, + .src_mapping = { + RCC_CLOCK_MUX_SRC_HSE, + }, + .hidden = true, + }, + [RCC_CLOCK_MUX_LCD_AND_RTC_COMMON] = { + .name = "lcd-and-rtc-common-mux", + /* Same mapping as: BDCR_RTCSEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_GND, + RCC_CLOCK_MUX_SRC_LSE, + RCC_CLOCK_MUX_SRC_LSI, + RCC_CLOCK_MUX_SRC_HSE_OVER_32, + }, + .hidden = true, + FILL_DEFAULT_INIT_ENABLED, + }, + /* From now on, muxes with a publicly available output */ + [RCC_CLOCK_MUX_CORTEX_REFCLK] = { + .name = "cortex-refclk", + .multiplier = 1, + /* REFCLK is always HCLK/8 */ + .divider = 8, + .enabled = true, + .src_mapping = { + RCC_CLOCK_MUX_SRC_HCLK, + } + }, + [RCC_CLOCK_MUX_USART1] = { + .name = "usart1", + /* Same mapping as: CCIPR_USART1SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK2, + RCC_CLOCK_MUX_SRC_SYSCLK, + RCC_CLOCK_MUX_SRC_HSI, + RCC_CLOCK_MUX_SRC_LSE, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_USART2] = { + .name = "usart2", + /* Same mapping as: CCIPR_USART2SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + RCC_CLOCK_MUX_SRC_SYSCLK, + RCC_CLOCK_MUX_SRC_HSI, + RCC_CLOCK_MUX_SRC_LSE, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_USART3] = { + .name = "usart3", + /* Same mapping as: CCIPR_USART3SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + RCC_CLOCK_MUX_SRC_SYSCLK, + RCC_CLOCK_MUX_SRC_HSI, + RCC_CLOCK_MUX_SRC_LSE, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_UART4] = { + .name = "uart4", + /* Same mapping as: CCIPR_UART4SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + RCC_CLOCK_MUX_SRC_SYSCLK, + RCC_CLOCK_MUX_SRC_HSI, + RCC_CLOCK_MUX_SRC_LSE, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_UART5] = { + .name = "uart5", + /* Same mapping as: CCIPR_UART5SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + RCC_CLOCK_MUX_SRC_SYSCLK, + RCC_CLOCK_MUX_SRC_HSI, + RCC_CLOCK_MUX_SRC_LSE, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_LPUART1] = { + .name = "lpuart1", + /* Same mapping as: CCIPR_LPUART1SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + RCC_CLOCK_MUX_SRC_SYSCLK, + RCC_CLOCK_MUX_SRC_HSI, + RCC_CLOCK_MUX_SRC_LSE, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_I2C1] = { + .name = "i2c1", + /* Same mapping as: CCIPR_I2C1SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + RCC_CLOCK_MUX_SRC_SYSCLK, + RCC_CLOCK_MUX_SRC_HSI, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_I2C2] = { + .name = "i2c2", + /* Same mapping as: CCIPR_I2C2SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + RCC_CLOCK_MUX_SRC_SYSCLK, + RCC_CLOCK_MUX_SRC_HSI, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_I2C3] = { + .name = "i2c3", + /* Same mapping as: CCIPR_I2C3SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + RCC_CLOCK_MUX_SRC_SYSCLK, + RCC_CLOCK_MUX_SRC_HSI, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_LPTIM1] = { + .name = "lptim1", + /* Same mapping as: CCIPR_LPTIM1SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + RCC_CLOCK_MUX_SRC_LSI, + RCC_CLOCK_MUX_SRC_HSI, + RCC_CLOCK_MUX_SRC_LSE, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_LPTIM2] = { + .name = "lptim2", + /* Same mapping as: CCIPR_LPTIM2SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + RCC_CLOCK_MUX_SRC_LSI, + RCC_CLOCK_MUX_SRC_HSI, + RCC_CLOCK_MUX_SRC_LSE, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_SWPMI1] = { + .name = "swpmi1", + /* Same mapping as: CCIPR_SWPMI1SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + RCC_CLOCK_MUX_SRC_HSI, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_MCO] = { + .name = "mco", + /* Same mapping as: CFGR_MCOSEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + RCC_CLOCK_MUX_SRC_MSI, + RCC_CLOCK_MUX_SRC_HSI, + RCC_CLOCK_MUX_SRC_HSE, + RCC_CLOCK_MUX_SRC_PLL, + RCC_CLOCK_MUX_SRC_LSI, + RCC_CLOCK_MUX_SRC_LSE, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_LSCO] = { + .name = "lsco", + /* Same mapping as: BDCR_LSCOSEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_LSI, + RCC_CLOCK_MUX_SRC_LSE, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_DFSDM1] = { + .name = "dfsdm1", + /* Same mapping as: CCIPR_DFSDM1SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK2, + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_ADC] = { + .name = "adc", + /* Same mapping as: CCIPR_ADCSEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_GND, + RCC_CLOCK_MUX_SRC_PLLADC1, + RCC_CLOCK_MUX_SRC_PLLADC2, + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_CLK48] = { + .name = "clk48", + /* Same mapping as: CCIPR_CLK48SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_GND, + RCC_CLOCK_MUX_SRC_PLL48M2, + RCC_CLOCK_MUX_SRC_PLL48M1, + RCC_CLOCK_MUX_SRC_MSI, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_SAI2] = { + .name = "sai2", + /* Same mapping as: CCIPR_SAI2SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PLLSAI1, + RCC_CLOCK_MUX_SRC_PLLSAI2, + RCC_CLOCK_MUX_SRC_PLLSAI3, + RCC_CLOCK_MUX_SRC_SAI2_EXTCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_SAI1] = { + .name = "sai1", + /* Same mapping as: CCIPR_SAI1SEL */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_PLLSAI1, + RCC_CLOCK_MUX_SRC_PLLSAI2, + RCC_CLOCK_MUX_SRC_PLLSAI3, + RCC_CLOCK_MUX_SRC_SAI1_EXTCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + /* From now on, these muxes only have one valid source */ + [RCC_CLOCK_MUX_TSC] = { + .name = "tsc", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_CRC] = { + .name = "crc", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_FLASH] = { + .name = "flash", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_DMA2] = { + .name = "dma2", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_DMA1] = { + .name = "dma1", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_RNG] = { + .name = "rng", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_AES] = { + .name = "aes", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_OTGFS] = { + .name = "otgfs", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_GPIOA] = { + .name = "gpioa", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_GPIOB] = { + .name = "gpiob", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_GPIOC] = { + .name = "gpioc", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_GPIOD] = { + .name = "gpiod", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_GPIOE] = { + .name = "gpioe", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_GPIOF] = { + .name = "gpiof", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_GPIOG] = { + .name = "gpiog", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_GPIOH] = { + .name = "gpioh", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_QSPI] = { + .name = "qspi", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_FMC] = { + .name = "fmc", + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_OPAMP] = { + .name = "opamp", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_DAC1] = { + .name = "dac1", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_PWR] = { + .name = "pwr", + /* + * PWREN is in the APB1ENR1 register, + * but PWR uses SYSCLK according to the clock tree. + */ + .src_mapping = { + RCC_CLOCK_MUX_SRC_SYSCLK, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_CAN1] = { + .name = "can1", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_SPI3] = { + .name = "spi3", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_SPI2] = { + .name = "spi2", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_WWDG] = { + .name = "wwdg", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_LCD] = { + .name = "lcd", + .src_mapping = { + RCC_CLOCK_MUX_SRC_LCD_AND_RTC_COMMON, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_TIM7] = { + .name = "tim7", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_TIM6] = { + .name = "tim6", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_TIM5] = { + .name = "tim5", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_TIM4] = { + .name = "tim4", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_TIM3] = { + .name = "tim3", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_TIM2] = { + .name = "tim2", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK1, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_TIM17] = { + .name = "tim17", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK2, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_TIM16] = { + .name = "tim16", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK2, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_TIM15] = { + .name = "tim15", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK2, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_TIM8] = { + .name = "tim8", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK2, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_SPI1] = { + .name = "spi1", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK2, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_TIM1] = { + .name = "tim1", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK2, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_SDMMC1] = { + .name = "sdmmc1", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK2, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_FW] = { + .name = "fw", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK2, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_SYSCFG] = { + .name = "syscfg", + .src_mapping = { + RCC_CLOCK_MUX_SRC_PCLK2, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_RTC] = { + .name = "rtc", + .src_mapping = { + RCC_CLOCK_MUX_SRC_LCD_AND_RTC_COMMON, + }, + FILL_DEFAULT_INIT_DISABLED, + }, + [RCC_CLOCK_MUX_CORTEX_FCLK] = { + .name = "cortex-fclk", + .src_mapping = { + RCC_CLOCK_MUX_SRC_HCLK, + }, + FILL_DEFAULT_INIT_ENABLED, + }, +}; + +static inline void set_clock_mux_init_info(RccClockMuxState *mux, + RccClockMux id) +{ + mux->id = id; + mux->multiplier = CLOCK_MUX_INIT_INFO[id].multiplier; + mux->divider = CLOCK_MUX_INIT_INFO[id].divider; + mux->enabled = CLOCK_MUX_INIT_INFO[id].enabled; + /* + * Every peripheral has the first source of their source list as + * as their default source. + */ + mux->src = 0; +} + #endif /* HW_STM32L4X5_RCC_INTERNALS_H */ diff --git a/hw/misc/stm32l4x5_rcc.c b/hw/misc/stm32l4x5_rcc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/stm32l4x5_rcc.c +++ b/hw/misc/stm32l4x5_rcc.c @@ -XXX,XX +XXX,XX @@ #define LSE_FRQ 32768ULL #define LSI_FRQ 32000ULL -static void clock_mux_update(RccClockMuxState *mux) +/* + * Function to simply acknowledge and propagate changes in a clock mux + * frequency. + * `bypass_source` allows to bypass the period of the current source and just + * consider it equal to 0. This is useful during the hold phase of reset. + */ +static void clock_mux_update(RccClockMuxState *mux, bool bypass_source) { uint64_t src_freq; Clock *current_source = mux->srcs[mux->src]; @@ -XXX,XX +XXX,XX @@ static void clock_mux_update(RccClockMuxState *mux) * the clock and the divider of the mux becomes the multiplier of the * clock. */ - if (mux->enabled && mux->divider) { + if (!bypass_source && mux->enabled && mux->divider) { freq_multiplier = mux->divider; } @@ -XXX,XX +XXX,XX @@ static void clock_mux_src_update(void *opaque, ClockEvent event) const uint32_t update_src = backref - s->backref; /* Only update if the clock that was updated is the current source */ if (update_src == s->src) { - clock_mux_update(s); + clock_mux_update(s, false); } } @@ -XXX,XX +XXX,XX @@ static void clock_mux_init(Object *obj) s->out = qdev_init_clock_out(DEVICE(s), "out"); } +static void clock_mux_reset_enter(Object *obj, ResetType type) +{ + RccClockMuxState *s = RCC_CLOCK_MUX(obj); + set_clock_mux_init_info(s, s->id); +} + static void clock_mux_reset_hold(Object *obj) -{ } +{ + RccClockMuxState *s = RCC_CLOCK_MUX(obj); + clock_mux_update(s, true); +} + +static void clock_mux_reset_exit(Object *obj) +{ + RccClockMuxState *s = RCC_CLOCK_MUX(obj); + clock_mux_update(s, false); +} static const VMStateDescription clock_mux_vmstate = { .name = TYPE_RCC_CLOCK_MUX, @@ -XXX,XX +XXX,XX @@ static void clock_mux_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); ResettableClass *rc = RESETTABLE_CLASS(klass); + rc->phases.enter = clock_mux_reset_enter; rc->phases.hold = clock_mux_reset_hold; + rc->phases.exit = clock_mux_reset_exit; dc->vmsd = &clock_mux_vmstate; } @@ -XXX,XX +XXX,XX @@ static void clock_mux_set_enable(RccClockMuxState *mux, bool enabled) } mux->enabled = enabled; - clock_mux_update(mux); + clock_mux_update(mux, false); } static void clock_mux_set_factor(RccClockMuxState *mux, @@ -XXX,XX +XXX,XX @@ static void clock_mux_set_factor(RccClockMuxState *mux, mux->multiplier = multiplier; mux->divider = divider; - clock_mux_update(mux); + clock_mux_update(mux, false); } static void clock_mux_set_source(RccClockMuxState *mux, RccClockMuxSource src) @@ -XXX,XX +XXX,XX @@ static void clock_mux_set_source(RccClockMuxState *mux, RccClockMuxSource src) trace_stm32l4x5_rcc_mux_set_src(mux->id, mux->src, src); mux->src = src; - clock_mux_update(mux); + clock_mux_update(mux, false); } -static void pll_update(RccPllState *pll) +/* + * Acknowledge and propagate changes in a PLL frequency. + * `bypass_source` allows to bypass the period of the current source and just + * consider it equal to 0. This is useful during the hold phase of reset. + */ +static void pll_update(RccPllState *pll, bool bypass_source) { uint64_t vco_freq, old_channel_freq, channel_freq; int i; @@ -XXX,XX +XXX,XX @@ static void pll_update(RccPllState *pll) } old_channel_freq = clock_get_hz(pll->channels[i]); - if (!pll->enabled || + if (bypass_source || + !pll->enabled || !pll->channel_enabled[i] || !pll->channel_divider[i]) { channel_freq = 0; @@ -XXX,XX +XXX,XX @@ static void pll_update(RccPllState *pll) static void pll_src_update(void *opaque, ClockEvent event) { RccPllState *s = opaque; - pll_update(s); + pll_update(s, false); } static void pll_init(Object *obj) @@ -XXX,XX +XXX,XX @@ static void pll_init(Object *obj) } } +static void pll_reset_enter(Object *obj, ResetType type) +{ + RccPllState *s = RCC_PLL(obj); + set_pll_init_info(s, s->id); +} + static void pll_reset_hold(Object *obj) -{ } +{ + RccPllState *s = RCC_PLL(obj); + pll_update(s, true); +} + +static void pll_reset_exit(Object *obj) +{ + RccPllState *s = RCC_PLL(obj); + pll_update(s, false); +} static const VMStateDescription pll_vmstate = { .name = TYPE_RCC_PLL, @@ -XXX,XX +XXX,XX @@ static void pll_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); ResettableClass *rc = RESETTABLE_CLASS(klass); + rc->phases.enter = pll_reset_enter; rc->phases.hold = pll_reset_hold; + rc->phases.exit = pll_reset_exit; dc->vmsd = &pll_vmstate; } @@ -XXX,XX +XXX,XX @@ static void pll_set_vco_multiplier(RccPllState *pll, uint32_t vco_multiplier) pll->vco_multiplier, vco_multiplier); pll->vco_multiplier = vco_multiplier; - pll_update(pll); + pll_update(pll, false); } static void pll_set_enable(RccPllState *pll, bool enabled) @@ -XXX,XX +XXX,XX @@ static void pll_set_enable(RccPllState *pll, bool enabled) } pll->enabled = enabled; - pll_update(pll); + pll_update(pll, false); } static void pll_set_channel_enable(RccPllState *pll, @@ -XXX,XX +XXX,XX @@ static void pll_set_channel_enable(RccPllState *pll, } pll->channel_enabled[channel] = enabled; - pll_update(pll); + pll_update(pll, false); } static void pll_set_channel_divider(RccPllState *pll, @@ -XXX,XX +XXX,XX @@ static void pll_set_channel_divider(RccPllState *pll, channel, pll->channel_divider[channel], divider); pll->channel_divider[channel] = divider; - pll_update(pll); + pll_update(pll, false); } static void rcc_update_irq(Stm32l4x5RccState *s) @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_rcc_init(Object *obj) qdev_init_clocks(DEVICE(s), stm32l4x5_rcc_clocks); for (i = 0; i < RCC_NUM_PLL; i++) { - object_initialize_child(obj, "pll[*]", + object_initialize_child(obj, PLL_INIT_INFO[i].name, &s->plls[i], TYPE_RCC_PLL); + set_pll_init_info(&s->plls[i], i); } for (i = 0; i < RCC_NUM_CLOCK_MUX; i++) { + char *alias; - object_initialize_child(obj, "clock[*]", + object_initialize_child(obj, CLOCK_MUX_INIT_INFO[i].name, &s->clock_muxes[i], TYPE_RCC_CLOCK_MUX); + set_clock_mux_init_info(&s->clock_muxes[i], i); + if (!CLOCK_MUX_INIT_INFO[i].hidden) { + /* Expose muxes output as RCC outputs */ + alias = g_strdup_printf("%s-out", CLOCK_MUX_INIT_INFO[i].name); + qdev_alias_clock(DEVICE(&s->clock_muxes[i]), "out", DEVICE(obj), alias); + g_free(alias); + } } s->gnd = clock_new(obj, "gnd"); } +static void connect_mux_sources(Stm32l4x5RccState *s, + RccClockMuxState *mux, + const RccClockMuxSource *clk_mapping) +{ + size_t i; + + Clock * const CLK_SRC_MAPPING[] = { + [RCC_CLOCK_MUX_SRC_GND] = s->gnd, + [RCC_CLOCK_MUX_SRC_HSI] = s->hsi16_rc, + [RCC_CLOCK_MUX_SRC_HSE] = s->hse, + [RCC_CLOCK_MUX_SRC_MSI] = s->msi_rc, + [RCC_CLOCK_MUX_SRC_LSI] = s->lsi_rc, + [RCC_CLOCK_MUX_SRC_LSE] = s->lse_crystal, + [RCC_CLOCK_MUX_SRC_SAI1_EXTCLK] = s->sai1_extclk, + [RCC_CLOCK_MUX_SRC_SAI2_EXTCLK] = s->sai2_extclk, + [RCC_CLOCK_MUX_SRC_PLL] = + s->plls[RCC_PLL_PLL].channels[RCC_PLL_CHANNEL_PLLCLK], + [RCC_CLOCK_MUX_SRC_PLLSAI1] = + s->plls[RCC_PLL_PLLSAI1].channels[RCC_PLLSAI1_CHANNEL_PLLSAI1CLK], + [RCC_CLOCK_MUX_SRC_PLLSAI2] = + s->plls[RCC_PLL_PLLSAI2].channels[RCC_PLLSAI2_CHANNEL_PLLSAI2CLK], + [RCC_CLOCK_MUX_SRC_PLLSAI3] = + s->plls[RCC_PLL_PLL].channels[RCC_PLL_CHANNEL_PLLSAI3CLK], + [RCC_CLOCK_MUX_SRC_PLL48M1] = + s->plls[RCC_PLL_PLL].channels[RCC_PLL_CHANNEL_PLL48M1CLK], + [RCC_CLOCK_MUX_SRC_PLL48M2] = + s->plls[RCC_PLL_PLLSAI1].channels[RCC_PLLSAI1_CHANNEL_PLL48M2CLK], + [RCC_CLOCK_MUX_SRC_PLLADC1] = + s->plls[RCC_PLL_PLLSAI1].channels[RCC_PLLSAI1_CHANNEL_PLLADC1CLK], + [RCC_CLOCK_MUX_SRC_PLLADC2] = + s->plls[RCC_PLL_PLLSAI2] .channels[RCC_PLLSAI2_CHANNEL_PLLADC2CLK], + [RCC_CLOCK_MUX_SRC_SYSCLK] = s->clock_muxes[RCC_CLOCK_MUX_SYSCLK].out, + [RCC_CLOCK_MUX_SRC_HCLK] = s->clock_muxes[RCC_CLOCK_MUX_HCLK].out, + [RCC_CLOCK_MUX_SRC_PCLK1] = s->clock_muxes[RCC_CLOCK_MUX_PCLK1].out, + [RCC_CLOCK_MUX_SRC_PCLK2] = s->clock_muxes[RCC_CLOCK_MUX_PCLK2].out, + [RCC_CLOCK_MUX_SRC_HSE_OVER_32] = s->clock_muxes[RCC_CLOCK_MUX_HSE_OVER_32].out, + [RCC_CLOCK_MUX_SRC_LCD_AND_RTC_COMMON] = + s->clock_muxes[RCC_CLOCK_MUX_LCD_AND_RTC_COMMON].out, + }; + + assert(ARRAY_SIZE(CLK_SRC_MAPPING) == RCC_CLOCK_MUX_SRC_NUMBER); + + for (i = 0; i < RCC_NUM_CLOCK_MUX_SRC; i++) { + RccClockMuxSource mapping = clk_mapping[i]; + clock_set_source(mux->srcs[i], CLK_SRC_MAPPING[mapping]); + } +} + + static const VMStateDescription vmstate_stm32l4x5_rcc = { .name = TYPE_STM32L4X5_RCC, .version_id = 1, @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_rcc_realize(DeviceState *dev, Error **errp) for (i = 0; i < RCC_NUM_CLOCK_MUX; i++) { RccClockMuxState *clock_mux = &s->clock_muxes[i]; + connect_mux_sources(s, clock_mux, CLOCK_MUX_INIT_INFO[i].src_mapping); + if (!qdev_realize(DEVICE(clock_mux), NULL, errp)) { return; } } + /* + * Start clocks after everything is connected + * to propagate the frequencies along the tree. + */ clock_update_hz(s->msi_rc, MSI_DEFAULT_FRQ); clock_update_hz(s->sai1_extclk, s->sai1_extclk_frequency); clock_update_hz(s->sai2_extclk, s->sai2_extclk_frequency); @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_rcc_class_init(ObjectClass *klass, void *data) DeviceClass *dc = DEVICE_CLASS(klass); ResettableClass *rc = RESETTABLE_CLASS(klass); + assert(ARRAY_SIZE(CLOCK_MUX_INIT_INFO) == RCC_NUM_CLOCK_MUX); rc->phases.hold = stm32l4x5_rcc_reset_hold; device_class_set_props(dc, stm32l4x5_rcc_properties); -- 2.34.1 From: Arnaud Minier <arnaud.minier@telecom-paris.fr> Update the RCC state and propagate frequency changes when writing to the RCC registers. Currently, ICSCR, CIER, the reset registers and the stop mode registers are not implemented. Some fields have not been implemented due to uncertainty about how to handle them (Like the clock security system or bypassing mecanisms). Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Message-id: 20240303140643.81957-6-arnaud.minier@telecom-paris.fr Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/stm32l4x5_rcc.c | 524 +++++++++++++++++++++++++++++++++++++++- 1 file changed, 512 insertions(+), 12 deletions(-) diff --git a/hw/misc/stm32l4x5_rcc.c b/hw/misc/stm32l4x5_rcc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/stm32l4x5_rcc.c +++ b/hw/misc/stm32l4x5_rcc.c @@ -XXX,XX +XXX,XX @@ #include "hw/qdev-clock.h" #include "hw/qdev-properties.h" #include "hw/qdev-properties-system.h" +#include "hw/registerfields.h" #include "trace.h" #define HSE_DEFAULT_FRQ 48000000ULL @@ -XXX,XX +XXX,XX @@ static void pll_set_channel_divider(RccPllState *pll, static void rcc_update_irq(Stm32l4x5RccState *s) { + /* + * TODO: Handle LSECSSF and CSSF flags when the CSS is implemented. + */ if (s->cifr & CIFR_IRQ_MASK) { qemu_irq_raise(s->irq); } else { @@ -XXX,XX +XXX,XX @@ static void rcc_update_irq(Stm32l4x5RccState *s) } } +static void rcc_update_cr_register(Stm32l4x5RccState *s) +{ + int val; + + /* PLLSAI2ON and update PLLSAI2RDY */ + val = FIELD_EX32(s->cr, CR, PLLSAI2ON); + pll_set_enable(&s->plls[RCC_PLL_PLLSAI2], val); + s->cr = (s->cr & ~R_CR_PLLSAI2RDY_MASK) | + (val << R_CR_PLLSAI2RDY_SHIFT); + if (s->cier & R_CIER_PLLSAI2RDYIE_MASK) { + s->cifr |= R_CIFR_PLLSAI2RDYF_MASK; + } + + /* PLLSAI1ON and update PLLSAI1RDY */ + val = FIELD_EX32(s->cr, CR, PLLSAI1ON); + pll_set_enable(&s->plls[RCC_PLL_PLLSAI1], val); + s->cr = (s->cr & ~R_CR_PLLSAI1RDY_MASK) | + (val << R_CR_PLLSAI1RDY_SHIFT); + if (s->cier & R_CIER_PLLSAI1RDYIE_MASK) { + s->cifr |= R_CIFR_PLLSAI1RDYF_MASK; + } + + /* PLLON and update PLLRDY */ + val = FIELD_EX32(s->cr, CR, PLLON); + pll_set_enable(&s->plls[RCC_PLL_PLL], val); + s->cr = (s->cr & ~R_CR_PLLRDY_MASK) | + (val << R_CR_PLLRDY_SHIFT); + if (s->cier & R_CIER_PLLRDYIE_MASK) { + s->cifr |= R_CIFR_PLLRDYF_MASK; + } + + /* CSSON: TODO */ + /* HSEBYP: TODO */ + + /* HSEON and update HSERDY */ + val = FIELD_EX32(s->cr, CR, HSEON); + s->cr = (s->cr & ~R_CR_HSERDY_MASK) | + (val << R_CR_HSERDY_SHIFT); + if (val) { + clock_update_hz(s->hse, s->hse_frequency); + if (s->cier & R_CIER_HSERDYIE_MASK) { + s->cifr |= R_CIFR_HSERDYF_MASK; + } + } else { + clock_update(s->hse, 0); + } + + /* HSIAFS: TODO*/ + /* HSIKERON: TODO*/ + + /* HSION and update HSIRDY*/ + val = FIELD_EX32(s->cr, CR, HSION); + s->cr = (s->cr & ~R_CR_HSIRDY_MASK) | + (val << R_CR_HSIRDY_SHIFT); + if (val) { + clock_update_hz(s->hsi16_rc, HSI_FRQ); + if (s->cier & R_CIER_HSIRDYIE_MASK) { + s->cifr |= R_CIFR_HSIRDYF_MASK; + } + } else { + clock_update(s->hsi16_rc, 0); + } + + static const uint32_t msirange[] = { + 100000, 200000, 400000, 800000, 1000000, 2000000, + 4000000, 8000000, 16000000, 24000000, 32000000, 48000000 + }; + /* MSIRANGE and MSIRGSEL */ + val = FIELD_EX32(s->cr, CR, MSIRGSEL); + if (val) { + /* MSIRGSEL is set, use the MSIRANGE field */ + val = FIELD_EX32(s->cr, CR, MSIRANGE); + } else { + /* MSIRGSEL is not set, use the MSISRANGE field */ + val = FIELD_EX32(s->csr, CSR, MSISRANGE); + } + + if (val < ARRAY_SIZE(msirange)) { + clock_update_hz(s->msi_rc, msirange[val]); + } else { + clock_update_hz(s->msi_rc, MSI_DEFAULT_FRQ); + /* TODO: there is a write protection if the value is out of bound, + implement that instead of setting the default */ + } + + /* MSIPLLEN */ + + /* MSION and update MSIRDY */ + val = FIELD_EX32(s->cr, CR, MSION); + s->cr = (s->cr & ~R_CR_MSIRDY_MASK) | + (val << R_CR_MSIRDY_SHIFT); + if (s->cier & R_CIER_MSIRDYIE_MASK) { + s->cifr |= R_CIFR_MSIRDYF_MASK; + } + rcc_update_irq(s); +} + +static void rcc_update_cfgr_register(Stm32l4x5RccState *s) +{ + uint32_t val; + /* MCOPRE */ + val = FIELD_EX32(s->cfgr, CFGR, MCOPRE); + assert(val <= 0b100); + clock_mux_set_factor(&s->clock_muxes[RCC_CLOCK_MUX_MCO], + 1, 1 << val); + + /* MCOSEL */ + val = FIELD_EX32(s->cfgr, CFGR, MCOSEL); + assert(val <= 0b111); + if (val == 0) { + clock_mux_set_enable(&s->clock_muxes[RCC_CLOCK_MUX_MCO], false); + } else { + clock_mux_set_enable(&s->clock_muxes[RCC_CLOCK_MUX_MCO], true); + clock_mux_set_source(&s->clock_muxes[RCC_CLOCK_MUX_MCO], + val - 1); + } + + /* STOPWUCK */ + /* TODO */ + + /* PPRE2 */ + val = FIELD_EX32(s->cfgr, CFGR, PPRE2); + if (val < 0b100) { + clock_mux_set_factor(&s->clock_muxes[RCC_CLOCK_MUX_PCLK2], + 1, 1); + } else { + clock_mux_set_factor(&s->clock_muxes[RCC_CLOCK_MUX_PCLK2], + 1, 1 << (val - 0b11)); + } + + /* PPRE1 */ + val = FIELD_EX32(s->cfgr, CFGR, PPRE1); + if (val < 0b100) { + clock_mux_set_factor(&s->clock_muxes[RCC_CLOCK_MUX_PCLK1], + 1, 1); + } else { + clock_mux_set_factor(&s->clock_muxes[RCC_CLOCK_MUX_PCLK1], + 1, 1 << (val - 0b11)); + } + + /* HPRE */ + val = FIELD_EX32(s->cfgr, CFGR, HPRE); + if (val < 0b1000) { + clock_mux_set_factor(&s->clock_muxes[RCC_CLOCK_MUX_HCLK], + 1, 1); + } else { + clock_mux_set_factor(&s->clock_muxes[RCC_CLOCK_MUX_HCLK], + 1, 1 << (val - 0b111)); + } + + /* Update SWS */ + val = FIELD_EX32(s->cfgr, CFGR, SW); + clock_mux_set_source(&s->clock_muxes[RCC_CLOCK_MUX_SYSCLK], + val); + s->cfgr &= ~R_CFGR_SWS_MASK; + s->cfgr |= val << R_CFGR_SWS_SHIFT; +} + +static void rcc_update_ahb1enr(Stm32l4x5RccState *s) +{ + #define AHB1ENR_SET_ENABLE(_peripheral_name) \ + clock_mux_set_enable(&s->clock_muxes[RCC_CLOCK_MUX_##_peripheral_name], \ + FIELD_EX32(s->ahb1enr, AHB1ENR, _peripheral_name##EN)) + + /* DMA2DEN: reserved for STM32L475xx */ + AHB1ENR_SET_ENABLE(TSC); + AHB1ENR_SET_ENABLE(CRC); + AHB1ENR_SET_ENABLE(FLASH); + AHB1ENR_SET_ENABLE(DMA2); + AHB1ENR_SET_ENABLE(DMA1); + + #undef AHB1ENR_SET_ENABLE +} + +static void rcc_update_ahb2enr(Stm32l4x5RccState *s) +{ + #define AHB2ENR_SET_ENABLE(_peripheral_name) \ + clock_mux_set_enable(&s->clock_muxes[RCC_CLOCK_MUX_##_peripheral_name], \ + FIELD_EX32(s->ahb2enr, AHB2ENR, _peripheral_name##EN)) + + AHB2ENR_SET_ENABLE(RNG); + /* HASHEN: reserved for STM32L475xx */ + AHB2ENR_SET_ENABLE(AES); + /* DCMIEN: reserved for STM32L475xx */ + AHB2ENR_SET_ENABLE(ADC); + AHB2ENR_SET_ENABLE(OTGFS); + /* GPIOIEN: reserved for STM32L475xx */ + AHB2ENR_SET_ENABLE(GPIOA); + AHB2ENR_SET_ENABLE(GPIOB); + AHB2ENR_SET_ENABLE(GPIOC); + AHB2ENR_SET_ENABLE(GPIOD); + AHB2ENR_SET_ENABLE(GPIOE); + AHB2ENR_SET_ENABLE(GPIOF); + AHB2ENR_SET_ENABLE(GPIOG); + AHB2ENR_SET_ENABLE(GPIOH); + + #undef AHB2ENR_SET_ENABLE +} + +static void rcc_update_ahb3enr(Stm32l4x5RccState *s) +{ + #define AHB3ENR_SET_ENABLE(_peripheral_name) \ + clock_mux_set_enable(&s->clock_muxes[RCC_CLOCK_MUX_##_peripheral_name], \ + FIELD_EX32(s->ahb3enr, AHB3ENR, _peripheral_name##EN)) + + AHB3ENR_SET_ENABLE(QSPI); + AHB3ENR_SET_ENABLE(FMC); + + #undef AHB3ENR_SET_ENABLE +} + +static void rcc_update_apb1enr(Stm32l4x5RccState *s) +{ + #define APB1ENR1_SET_ENABLE(_peripheral_name) \ + clock_mux_set_enable(&s->clock_muxes[RCC_CLOCK_MUX_##_peripheral_name], \ + FIELD_EX32(s->apb1enr1, APB1ENR1, _peripheral_name##EN)) + #define APB1ENR2_SET_ENABLE(_peripheral_name) \ + clock_mux_set_enable(&s->clock_muxes[RCC_CLOCK_MUX_##_peripheral_name], \ + FIELD_EX32(s->apb1enr2, APB1ENR2, _peripheral_name##EN)) + + /* APB1ENR1 */ + APB1ENR1_SET_ENABLE(LPTIM1); + APB1ENR1_SET_ENABLE(OPAMP); + APB1ENR1_SET_ENABLE(DAC1); + APB1ENR1_SET_ENABLE(PWR); + /* CAN2: reserved for STM32L4x5 */ + APB1ENR1_SET_ENABLE(CAN1); + /* CRSEN: reserved for STM32L4x5 */ + APB1ENR1_SET_ENABLE(I2C3); + APB1ENR1_SET_ENABLE(I2C2); + APB1ENR1_SET_ENABLE(I2C1); + APB1ENR1_SET_ENABLE(UART5); + APB1ENR1_SET_ENABLE(UART4); + APB1ENR1_SET_ENABLE(USART3); + APB1ENR1_SET_ENABLE(USART2); + APB1ENR1_SET_ENABLE(SPI3); + APB1ENR1_SET_ENABLE(SPI2); + APB1ENR1_SET_ENABLE(WWDG); + /* RTCAPB: reserved for STM32L4x5 */ + APB1ENR1_SET_ENABLE(LCD); + APB1ENR1_SET_ENABLE(TIM7); + APB1ENR1_SET_ENABLE(TIM6); + APB1ENR1_SET_ENABLE(TIM5); + APB1ENR1_SET_ENABLE(TIM4); + APB1ENR1_SET_ENABLE(TIM3); + APB1ENR1_SET_ENABLE(TIM2); + + /* APB1ENR2 */ + APB1ENR2_SET_ENABLE(LPTIM2); + APB1ENR2_SET_ENABLE(SWPMI1); + /* I2C4EN: reserved for STM32L4x5 */ + APB1ENR2_SET_ENABLE(LPUART1); + + #undef APB1ENR1_SET_ENABLE + #undef APB1ENR2_SET_ENABLE +} + +static void rcc_update_apb2enr(Stm32l4x5RccState *s) +{ + #define APB2ENR_SET_ENABLE(_peripheral_name) \ + clock_mux_set_enable(&s->clock_muxes[RCC_CLOCK_MUX_##_peripheral_name], \ + FIELD_EX32(s->apb2enr, APB2ENR, _peripheral_name##EN)) + + APB2ENR_SET_ENABLE(DFSDM1); + APB2ENR_SET_ENABLE(SAI2); + APB2ENR_SET_ENABLE(SAI1); + APB2ENR_SET_ENABLE(TIM17); + APB2ENR_SET_ENABLE(TIM16); + APB2ENR_SET_ENABLE(TIM15); + APB2ENR_SET_ENABLE(USART1); + APB2ENR_SET_ENABLE(TIM8); + APB2ENR_SET_ENABLE(SPI1); + APB2ENR_SET_ENABLE(TIM1); + APB2ENR_SET_ENABLE(SDMMC1); + APB2ENR_SET_ENABLE(FW); + APB2ENR_SET_ENABLE(SYSCFG); + + #undef APB2ENR_SET_ENABLE +} + +/* + * The 3 PLLs share the same register layout + * so we can use the same function for all of them + * Note: no frequency bounds checking is done here. + */ +static void rcc_update_pllsaixcfgr(Stm32l4x5RccState *s, RccPll pll_id) +{ + uint32_t reg, val; + switch (pll_id) { + case RCC_PLL_PLL: + reg = s->pllcfgr; + break; + case RCC_PLL_PLLSAI1: + reg = s->pllsai1cfgr; + break; + case RCC_PLL_PLLSAI2: + reg = s->pllsai2cfgr; + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Invalid PLL ID: %u\n", __func__, pll_id); + return; + } + + /* PLLPDIV */ + val = FIELD_EX32(reg, PLLCFGR, PLLPDIV); + /* 1 is a reserved value */ + if (val == 0) { + /* Get PLLP value */ + val = FIELD_EX32(reg, PLLCFGR, PLLP); + pll_set_channel_divider(&s->plls[pll_id], RCC_PLL_COMMON_CHANNEL_P, + (val ? 17 : 7)); + } else if (val > 1) { + pll_set_channel_divider(&s->plls[pll_id], RCC_PLL_COMMON_CHANNEL_P, + val); + } + + + /* PLLR */ + val = FIELD_EX32(reg, PLLCFGR, PLLR); + pll_set_channel_divider(&s->plls[pll_id], RCC_PLL_COMMON_CHANNEL_R, + 2 * (val + 1)); + + /* PLLREN */ + val = FIELD_EX32(reg, PLLCFGR, PLLREN); + pll_set_channel_enable(&s->plls[pll_id], RCC_PLL_COMMON_CHANNEL_R, val); + + /* PLLQ */ + val = FIELD_EX32(reg, PLLCFGR, PLLQ); + pll_set_channel_divider(&s->plls[pll_id], RCC_PLL_COMMON_CHANNEL_Q, + 2 * (val + 1)); + + /* PLLQEN */ + val = FIELD_EX32(reg, PLLCFGR, PLLQEN); + pll_set_channel_enable(&s->plls[pll_id], RCC_PLL_COMMON_CHANNEL_Q, val); + + /* PLLPEN */ + val = FIELD_EX32(reg, PLLCFGR, PLLPEN); + pll_set_channel_enable(&s->plls[pll_id], RCC_PLL_COMMON_CHANNEL_P, val); + + /* PLLN */ + val = FIELD_EX32(reg, PLLCFGR, PLLN); + pll_set_vco_multiplier(&s->plls[pll_id], val); +} + +static void rcc_update_pllcfgr(Stm32l4x5RccState *s) +{ + int val; + + /* Use common layout */ + rcc_update_pllsaixcfgr(s, RCC_PLL_PLL); + + /* Fetch specific fields for pllcfgr */ + + /* PLLM */ + val = FIELD_EX32(s->pllcfgr, PLLCFGR, PLLM); + clock_mux_set_factor(&s->clock_muxes[RCC_CLOCK_MUX_PLL_INPUT], 1, (val + 1)); + + /* PLLSRC */ + val = FIELD_EX32(s->pllcfgr, PLLCFGR, PLLSRC); + if (val == 0) { + clock_mux_set_enable(&s->clock_muxes[RCC_CLOCK_MUX_PLL_INPUT], false); + } else { + clock_mux_set_source(&s->clock_muxes[RCC_CLOCK_MUX_PLL_INPUT], val - 1); + clock_mux_set_enable(&s->clock_muxes[RCC_CLOCK_MUX_PLL_INPUT], true); + } +} + +static void rcc_update_ccipr(Stm32l4x5RccState *s) +{ + #define CCIPR_SET_SOURCE(_peripheral_name) \ + clock_mux_set_source(&s->clock_muxes[RCC_CLOCK_MUX_##_peripheral_name], \ + FIELD_EX32(s->ccipr, CCIPR, _peripheral_name##SEL)) + + CCIPR_SET_SOURCE(DFSDM1); + CCIPR_SET_SOURCE(SWPMI1); + CCIPR_SET_SOURCE(ADC); + CCIPR_SET_SOURCE(CLK48); + CCIPR_SET_SOURCE(SAI2); + CCIPR_SET_SOURCE(SAI1); + CCIPR_SET_SOURCE(LPTIM2); + CCIPR_SET_SOURCE(LPTIM1); + CCIPR_SET_SOURCE(I2C3); + CCIPR_SET_SOURCE(I2C2); + CCIPR_SET_SOURCE(I2C1); + CCIPR_SET_SOURCE(LPUART1); + CCIPR_SET_SOURCE(UART5); + CCIPR_SET_SOURCE(UART4); + CCIPR_SET_SOURCE(USART3); + CCIPR_SET_SOURCE(USART2); + CCIPR_SET_SOURCE(USART1); + + #undef CCIPR_SET_SOURCE +} + +static void rcc_update_bdcr(Stm32l4x5RccState *s) +{ + int val; + + /* LSCOSEL */ + val = FIELD_EX32(s->bdcr, BDCR, LSCOSEL); + clock_mux_set_source(&s->clock_muxes[RCC_CLOCK_MUX_LSCO], val); + + val = FIELD_EX32(s->bdcr, BDCR, LSCOEN); + clock_mux_set_enable(&s->clock_muxes[RCC_CLOCK_MUX_LSCO], val); + + /* BDRST */ + /* + * The documentation is not clear if the RTCEN flag disables the RTC and + * the LCD common mux or if it only affects the RTC. + * As the LCDEN flag exists, we assume here that it only affects the RTC. + */ + val = FIELD_EX32(s->bdcr, BDCR, RTCEN); + clock_mux_set_enable(&s->clock_muxes[RCC_CLOCK_MUX_RTC], val); + /* LCD and RTC share the same clock */ + val = FIELD_EX32(s->bdcr, BDCR, RTCSEL); + clock_mux_set_source(&s->clock_muxes[RCC_CLOCK_MUX_LCD_AND_RTC_COMMON], val); + + /* LSECSSON */ + /* LSEDRV[1:0] */ + /* LSEBYP */ + + /* LSEON: Update LSERDY at the same time */ + val = FIELD_EX32(s->bdcr, BDCR, LSEON); + if (val) { + clock_update_hz(s->lse_crystal, LSE_FRQ); + s->bdcr |= R_BDCR_LSERDY_MASK; + if (s->cier & R_CIER_LSERDYIE_MASK) { + s->cifr |= R_CIFR_LSERDYF_MASK; + } + } else { + clock_update(s->lse_crystal, 0); + s->bdcr &= ~R_BDCR_LSERDY_MASK; + } + + rcc_update_irq(s); +} + +static void rcc_update_csr(Stm32l4x5RccState *s) +{ + int val; + + /* Reset flags: Not implemented */ + /* MSISRANGE: Not implemented after reset */ + + /* LSION: Update LSIRDY at the same time */ + val = FIELD_EX32(s->csr, CSR, LSION); + if (val) { + clock_update_hz(s->lsi_rc, LSI_FRQ); + s->csr |= R_CSR_LSIRDY_MASK; + if (s->cier & R_CIER_LSIRDYIE_MASK) { + s->cifr |= R_CIFR_LSIRDYF_MASK; + } + } else { + /* + * TODO: Handle when the LSI is set independently of LSION. + * E.g. when the LSI is set by the RTC. + * See the reference manual for more details. + */ + clock_update(s->lsi_rc, 0); + s->csr &= ~R_CSR_LSIRDY_MASK; + } + + rcc_update_irq(s); +} + static void stm32l4x5_rcc_reset_hold(Object *obj) { Stm32l4x5RccState *s = STM32L4X5_RCC(obj); @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_rcc_write(void *opaque, hwaddr addr, case A_CR: s->cr = (s->cr & CR_READ_SET_MASK) | (value & (CR_READ_SET_MASK | ~CR_READ_ONLY_MASK)); + rcc_update_cr_register(s); break; case A_ICSCR: s->icscr = value & ~ICSCR_READ_ONLY_MASK; + qemu_log_mask(LOG_UNIMP, + "%s: Side-effects not implemented for ICSCR\n", __func__); break; case A_CFGR: s->cfgr = value & ~CFGR_READ_ONLY_MASK; + rcc_update_cfgr_register(s); break; case A_PLLCFGR: s->pllcfgr = value; + rcc_update_pllcfgr(s); break; case A_PLLSAI1CFGR: s->pllsai1cfgr = value; + rcc_update_pllsaixcfgr(s, RCC_PLL_PLLSAI1); break; case A_PLLSAI2CFGR: s->pllsai2cfgr = value; + rcc_update_pllsaixcfgr(s, RCC_PLL_PLLSAI2); break; case A_CIER: s->cier = value; + qemu_log_mask(LOG_UNIMP, + "%s: Side-effects not implemented for CIER\n", __func__); break; case A_CIFR: qemu_log_mask(LOG_GUEST_ERROR, @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_rcc_write(void *opaque, hwaddr addr, /* Reset behaviors are not implemented */ case A_AHB1RSTR: s->ahb1rstr = value; + qemu_log_mask(LOG_UNIMP, + "%s: Side-effects not implemented for AHB1RSTR\n", __func__); break; case A_AHB2RSTR: s->ahb2rstr = value; + qemu_log_mask(LOG_UNIMP, + "%s: Side-effects not implemented for AHB2RSTR\n", __func__); break; case A_AHB3RSTR: s->ahb3rstr = value; + qemu_log_mask(LOG_UNIMP, + "%s: Side-effects not implemented for AHB3RSTR\n", __func__); break; case A_APB1RSTR1: s->apb1rstr1 = value; + qemu_log_mask(LOG_UNIMP, + "%s: Side-effects not implemented for APB1RSTR1\n", __func__); break; case A_APB1RSTR2: s->apb1rstr2 = value; + qemu_log_mask(LOG_UNIMP, + "%s: Side-effects not implemented for APB1RSTR2\n", __func__); break; case A_APB2RSTR: s->apb2rstr = value; + qemu_log_mask(LOG_UNIMP, + "%s: Side-effects not implemented for APB2RSTR\n", __func__); break; case A_AHB1ENR: s->ahb1enr = value; + rcc_update_ahb1enr(s); break; case A_AHB2ENR: s->ahb2enr = value; + rcc_update_ahb2enr(s); break; case A_AHB3ENR: s->ahb3enr = value; + rcc_update_ahb3enr(s); break; case A_APB1ENR1: s->apb1enr1 = value; + rcc_update_apb1enr(s); break; case A_APB1ENR2: s->apb1enr2 = value; + rcc_update_apb1enr(s); break; case A_APB2ENR: s->apb2enr = (s->apb2enr & APB2ENR_READ_SET_MASK) | value; + rcc_update_apb2enr(s); break; /* Behaviors for Sleep and Stop modes are not implemented */ case A_AHB1SMENR: s->ahb1smenr = value; + qemu_log_mask(LOG_UNIMP, + "%s: Side-effects not implemented for AHB1SMENR\n", __func__); break; case A_AHB2SMENR: s->ahb2smenr = value; + qemu_log_mask(LOG_UNIMP, + "%s: Side-effects not implemented for AHB2SMENR\n", __func__); break; case A_AHB3SMENR: s->ahb3smenr = value; + qemu_log_mask(LOG_UNIMP, + "%s: Side-effects not implemented for AHB3SMENR\n", __func__); break; case A_APB1SMENR1: s->apb1smenr1 = value; + qemu_log_mask(LOG_UNIMP, + "%s: Side-effects not implemented for APB1SMENR1\n", __func__); break; case A_APB1SMENR2: s->apb1smenr2 = value; + qemu_log_mask(LOG_UNIMP, + "%s: Side-effects not implemented for APB1SMENR2\n", __func__); break; case A_APB2SMENR: s->apb2smenr = value; + qemu_log_mask(LOG_UNIMP, + "%s: Side-effects not implemented for APB2SMENR\n", __func__); break; case A_CCIPR: s->ccipr = value; + rcc_update_ccipr(s); break; case A_BDCR: s->bdcr = value & ~BDCR_READ_ONLY_MASK; + rcc_update_bdcr(s); break; case A_CSR: s->csr = value & ~CSR_READ_ONLY_MASK; + rcc_update_csr(s); break; default: qemu_log_mask(LOG_GUEST_ERROR, @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_rcc_realize(DeviceState *dev, Error **errp) clock_update_hz(s->sai1_extclk, s->sai1_extclk_frequency); clock_update_hz(s->sai2_extclk, s->sai2_extclk_frequency); clock_update(s->gnd, 0); - - /* - * Dummy values to make compilation pass. - * Removed in later commits. - */ - clock_mux_set_source(&s->clock_muxes[0], RCC_CLOCK_MUX_SRC_GND); - clock_mux_set_enable(&s->clock_muxes[0], true); - clock_mux_set_factor(&s->clock_muxes[0], 1, 1); - pll_set_channel_divider(&s->plls[0], 0, 1); - pll_set_enable(&s->plls[0], true); - pll_set_channel_enable(&s->plls[0], 0, true); - pll_set_vco_multiplier(&s->plls[0], 1); } static Property stm32l4x5_rcc_properties[] = { -- 2.34.1 From: Arnaud Minier <arnaud.minier@telecom-paris.fr> Add write protections for the fields in the CR register. PLL configuration write protections (among others) have not been handled yet. This is planned in a future patch set. Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Message-id: 20240303140643.81957-7-arnaud.minier@telecom-paris.fr Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/stm32l4x5_rcc.c | 166 ++++++++++++++++++++++++++++------------ 1 file changed, 115 insertions(+), 51 deletions(-) diff --git a/hw/misc/stm32l4x5_rcc.c b/hw/misc/stm32l4x5_rcc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/stm32l4x5_rcc.c +++ b/hw/misc/stm32l4x5_rcc.c @@ -XXX,XX +XXX,XX @@ static void rcc_update_irq(Stm32l4x5RccState *s) } } -static void rcc_update_cr_register(Stm32l4x5RccState *s) +static void rcc_update_msi(Stm32l4x5RccState *s, uint32_t previous_value) +{ + uint32_t val; + + static const uint32_t msirange[] = { + 100000, 200000, 400000, 800000, 1000000, 2000000, + 4000000, 8000000, 16000000, 24000000, 32000000, 48000000 + }; + /* MSIRANGE and MSIRGSEL */ + val = extract32(s->cr, R_CR_MSIRGSEL_SHIFT, R_CR_MSIRGSEL_LENGTH); + if (val) { + /* MSIRGSEL is set, use the MSIRANGE field */ + val = extract32(s->cr, R_CR_MSIRANGE_SHIFT, R_CR_MSIRANGE_LENGTH); + } else { + /* MSIRGSEL is not set, use the MSISRANGE field */ + val = extract32(s->csr, R_CSR_MSISRANGE_SHIFT, R_CSR_MSISRANGE_LENGTH); + } + + if (val < ARRAY_SIZE(msirange)) { + clock_update_hz(s->msi_rc, msirange[val]); + } else { + /* + * There is a hardware write protection if the value is out of bound. + * Restore the previous value. + */ + s->cr = (s->cr & ~R_CSR_MSISRANGE_MASK) | + (previous_value & R_CSR_MSISRANGE_MASK); + } +} + +/* + * TODO: Add write-protection for all registers: + * DONE: CR + */ + +static void rcc_update_cr_register(Stm32l4x5RccState *s, uint32_t previous_value) { int val; + const RccClockMuxSource current_pll_src = + CLOCK_MUX_INIT_INFO[RCC_CLOCK_MUX_PLL_INPUT].src_mapping[ + s->clock_muxes[RCC_CLOCK_MUX_PLL_INPUT].src]; /* PLLSAI2ON and update PLLSAI2RDY */ val = FIELD_EX32(s->cr, CR, PLLSAI2ON); @@ -XXX,XX +XXX,XX @@ static void rcc_update_cr_register(Stm32l4x5RccState *s) s->cifr |= R_CIFR_PLLSAI1RDYF_MASK; } - /* PLLON and update PLLRDY */ + /* + * PLLON and update PLLRDY + * PLLON cannot be reset if the PLL clock is used as the system clock. + */ val = FIELD_EX32(s->cr, CR, PLLON); - pll_set_enable(&s->plls[RCC_PLL_PLL], val); - s->cr = (s->cr & ~R_CR_PLLRDY_MASK) | - (val << R_CR_PLLRDY_SHIFT); - if (s->cier & R_CIER_PLLRDYIE_MASK) { - s->cifr |= R_CIFR_PLLRDYF_MASK; + if (FIELD_EX32(s->cfgr, CFGR, SWS) != 0b11) { + pll_set_enable(&s->plls[RCC_PLL_PLL], val); + s->cr = (s->cr & ~R_CR_PLLRDY_MASK) | + (val << R_CR_PLLRDY_SHIFT); + if (s->cier & R_CIER_PLLRDYIE_MASK) { + s->cifr |= R_CIFR_PLLRDYF_MASK; + } + } else { + s->cr |= R_CR_PLLON_MASK; } /* CSSON: TODO */ /* HSEBYP: TODO */ - /* HSEON and update HSERDY */ + /* + * HSEON and update HSERDY. + * HSEON cannot be reset if the HSE oscillator is used directly or + * indirectly as the system clock. + */ val = FIELD_EX32(s->cr, CR, HSEON); - s->cr = (s->cr & ~R_CR_HSERDY_MASK) | - (val << R_CR_HSERDY_SHIFT); - if (val) { - clock_update_hz(s->hse, s->hse_frequency); - if (s->cier & R_CIER_HSERDYIE_MASK) { - s->cifr |= R_CIFR_HSERDYF_MASK; + if (FIELD_EX32(s->cfgr, CFGR, SWS) != 0b10 && + current_pll_src != RCC_CLOCK_MUX_SRC_HSE) { + s->cr = (s->cr & ~R_CR_HSERDY_MASK) | + (val << R_CR_HSERDY_SHIFT); + if (val) { + clock_update_hz(s->hse, s->hse_frequency); + if (s->cier & R_CIER_HSERDYIE_MASK) { + s->cifr |= R_CIFR_HSERDYF_MASK; + } + } else { + clock_update(s->hse, 0); } } else { - clock_update(s->hse, 0); + s->cr |= R_CR_HSEON_MASK; } /* HSIAFS: TODO*/ /* HSIKERON: TODO*/ - /* HSION and update HSIRDY*/ - val = FIELD_EX32(s->cr, CR, HSION); - s->cr = (s->cr & ~R_CR_HSIRDY_MASK) | - (val << R_CR_HSIRDY_SHIFT); - if (val) { + /* + * HSION and update HSIRDY + * HSION is set by hardware if the HSI16 is used directly + * or indirectly as system clock. + */ + if (FIELD_EX32(s->cfgr, CFGR, SWS) == 0b01 || + current_pll_src == RCC_CLOCK_MUX_SRC_HSI) { + s->cr |= (R_CR_HSION_MASK | R_CR_HSIRDY_MASK); clock_update_hz(s->hsi16_rc, HSI_FRQ); if (s->cier & R_CIER_HSIRDYIE_MASK) { s->cifr |= R_CIFR_HSIRDYF_MASK; } } else { - clock_update(s->hsi16_rc, 0); + val = FIELD_EX32(s->cr, CR, HSION); + if (val) { + clock_update_hz(s->hsi16_rc, HSI_FRQ); + s->cr |= R_CR_HSIRDY_MASK; + if (s->cier & R_CIER_HSIRDYIE_MASK) { + s->cifr |= R_CIFR_HSIRDYF_MASK; + } + } else { + clock_update(s->hsi16_rc, 0); + s->cr &= ~R_CR_HSIRDY_MASK; + } } - static const uint32_t msirange[] = { - 100000, 200000, 400000, 800000, 1000000, 2000000, - 4000000, 8000000, 16000000, 24000000, 32000000, 48000000 - }; - /* MSIRANGE and MSIRGSEL */ - val = FIELD_EX32(s->cr, CR, MSIRGSEL); - if (val) { - /* MSIRGSEL is set, use the MSIRANGE field */ - val = FIELD_EX32(s->cr, CR, MSIRANGE); + /* MSIPLLEN: TODO */ + + /* + * MSION and update MSIRDY + * Set by hardware when used directly or indirectly as system clock. + */ + if (FIELD_EX32(s->cfgr, CFGR, SWS) == 0b00 || + current_pll_src == RCC_CLOCK_MUX_SRC_MSI) { + s->cr |= (R_CR_MSION_MASK | R_CR_MSIRDY_MASK); + if (!(previous_value & R_CR_MSION_MASK) && (s->cier & R_CIER_MSIRDYIE_MASK)) { + s->cifr |= R_CIFR_MSIRDYF_MASK; + } + rcc_update_msi(s, previous_value); } else { - /* MSIRGSEL is not set, use the MSISRANGE field */ - val = FIELD_EX32(s->csr, CSR, MSISRANGE); - } - - if (val < ARRAY_SIZE(msirange)) { - clock_update_hz(s->msi_rc, msirange[val]); - } else { - clock_update_hz(s->msi_rc, MSI_DEFAULT_FRQ); - /* TODO: there is a write protection if the value is out of bound, - implement that instead of setting the default */ - } - - /* MSIPLLEN */ - - /* MSION and update MSIRDY */ - val = FIELD_EX32(s->cr, CR, MSION); - s->cr = (s->cr & ~R_CR_MSIRDY_MASK) | - (val << R_CR_MSIRDY_SHIFT); - if (s->cier & R_CIER_MSIRDYIE_MASK) { - s->cifr |= R_CIFR_MSIRDYF_MASK; + val = FIELD_EX32(s->cr, CR, MSION); + if (val) { + s->cr |= R_CR_MSIRDY_MASK; + rcc_update_msi(s, previous_value); + if (s->cier & R_CIER_MSIRDYIE_MASK) { + s->cifr |= R_CIFR_MSIRDYF_MASK; + } + } else { + s->cr &= ~R_CR_MSIRDY_MASK; + clock_update(s->msi_rc, 0); + } } rcc_update_irq(s); } @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_rcc_write(void *opaque, hwaddr addr, uint64_t val64, unsigned int size) { Stm32l4x5RccState *s = opaque; + uint32_t previous_value = 0; const uint32_t value = val64; trace_stm32l4x5_rcc_write(addr, value); switch (addr) { case A_CR: + previous_value = s->cr; s->cr = (s->cr & CR_READ_SET_MASK) | (value & (CR_READ_SET_MASK | ~CR_READ_ONLY_MASK)); - rcc_update_cr_register(s); + rcc_update_cr_register(s, previous_value); break; case A_ICSCR: s->icscr = value & ~ICSCR_READ_ONLY_MASK; -- 2.34.1 From: Arnaud Minier <arnaud.minier@telecom-paris.fr> Now that we can generate reliable clock frequencies from the RCC, remove the hacky definition of the sysclk in the b_l475e_iot01a initialisation code and use the correct RCC clock. Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Acked-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20240303140643.81957-8-arnaud.minier@telecom-paris.fr Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/stm32l4x5_soc.h | 3 --- hw/arm/b-l475e-iot01a.c | 10 +--------- hw/arm/stm32l4x5_soc.c | 33 ++++----------------------------- 3 files changed, 5 insertions(+), 41 deletions(-) diff --git a/include/hw/arm/stm32l4x5_soc.h b/include/hw/arm/stm32l4x5_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/stm32l4x5_soc.h +++ b/include/hw/arm/stm32l4x5_soc.h @@ -XXX,XX +XXX,XX @@ struct Stm32l4x5SocState { MemoryRegion sram2; MemoryRegion flash; MemoryRegion flash_alias; - - Clock *sysclk; - Clock *refclk; }; struct Stm32l4x5SocClass { diff --git a/hw/arm/b-l475e-iot01a.c b/hw/arm/b-l475e-iot01a.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/b-l475e-iot01a.c +++ b/hw/arm/b-l475e-iot01a.c @@ -XXX,XX +XXX,XX @@ #include "qapi/error.h" #include "hw/boards.h" #include "hw/qdev-properties.h" -#include "hw/qdev-clock.h" #include "qemu/error-report.h" #include "hw/arm/stm32l4x5_soc.h" #include "hw/arm/boot.h" -/* Main SYSCLK frequency in Hz (80MHz) */ -#define MAIN_SYSCLK_FREQ_HZ 80000000ULL +/* B-L475E-IOT01A implementation is derived from netduinoplus2 */ static void b_l475e_iot01a_init(MachineState *machine) { const Stm32l4x5SocClass *sc; DeviceState *dev; - Clock *sysclk; - - /* This clock doesn't need migration because it is fixed-frequency */ - sysclk = clock_new(OBJECT(machine), "SYSCLK"); - clock_set_hz(sysclk, MAIN_SYSCLK_FREQ_HZ); dev = qdev_new(TYPE_STM32L4X5XG_SOC); object_property_add_child(OBJECT(machine), "soc", OBJECT(dev)); - qdev_connect_clock_in(dev, "sysclk", sysclk); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); sc = STM32L4X5_SOC_GET_CLASS(dev); diff --git a/hw/arm/stm32l4x5_soc.c b/hw/arm/stm32l4x5_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32l4x5_soc.c +++ b/hw/arm/stm32l4x5_soc.c @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_soc_initfn(Object *obj) } object_initialize_child(obj, "syscfg", &s->syscfg, TYPE_STM32L4X5_SYSCFG); object_initialize_child(obj, "rcc", &s->rcc, TYPE_STM32L4X5_RCC); - - s->sysclk = qdev_init_clock_in(DEVICE(s), "sysclk", NULL, NULL, 0); - s->refclk = qdev_init_clock_in(DEVICE(s), "refclk", NULL, NULL, 0); } static void stm32l4x5_soc_realize(DeviceState *dev_soc, Error **errp) @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_soc_realize(DeviceState *dev_soc, Error **errp) DeviceState *armv7m; SysBusDevice *busdev; - /* - * We use s->refclk internally and only define it with qdev_init_clock_in() - * so it is correctly parented and not leaked on an init/deinit; it is not - * intended as an externally exposed clock. - */ - if (clock_has_source(s->refclk)) { - error_setg(errp, "refclk clock must not be wired up by the board code"); - return; - } - - if (!clock_has_source(s->sysclk)) { - error_setg(errp, "sysclk clock must be wired up by the board code"); - return; - } - - /* - * TODO: ideally we should model the SoC RCC and its ability to - * change the sysclk frequency and define different sysclk sources. - */ - - /* The refclk always runs at frequency HCLK / 8 */ - clock_set_mul_div(s->refclk, 8, 1); - clock_set_source(s->refclk, s->sysclk); - if (!memory_region_init_rom(&s->flash, OBJECT(dev_soc), "flash", sc->flash_size, errp)) { return; @@ -XXX,XX +XXX,XX @@ static void stm32l4x5_soc_realize(DeviceState *dev_soc, Error **errp) qdev_prop_set_uint32(armv7m, "num-prio-bits", 4); qdev_prop_set_string(armv7m, "cpu-type", ARM_CPU_TYPE_NAME("cortex-m4")); qdev_prop_set_bit(armv7m, "enable-bitband", true); - qdev_connect_clock_in(armv7m, "cpuclk", s->sysclk); - qdev_connect_clock_in(armv7m, "refclk", s->refclk); + qdev_connect_clock_in(armv7m, "cpuclk", + qdev_get_clock_out(DEVICE(&(s->rcc)), "cortex-fclk-out")); + qdev_connect_clock_in(armv7m, "refclk", + qdev_get_clock_out(DEVICE(&(s->rcc)), "cortex-refclk-out")); object_property_set_link(OBJECT(&s->armv7m), "memory", OBJECT(system_memory), &error_abort); if (!sysbus_realize(SYS_BUS_DEVICE(&s->armv7m), errp)) { -- 2.34.1 From: Arnaud Minier <arnaud.minier@telecom-paris.fr> Tests: - the ability to change the sysclk of the device - the ability to enable/disable/configure the PLLs - if the clock multiplexers work - the register flags and the generation of irqs Signed-off-by: Arnaud Minier <arnaud.minier@telecom-paris.fr> Signed-off-by: Inès Varhol <ines.varhol@telecom-paris.fr> Acked-by: Thomas Huth <thuth@redhat.com> Message-id: 20240303140643.81957-9-arnaud.minier@telecom-paris.fr Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- tests/qtest/stm32l4x5_rcc-test.c | 189 +++++++++++++++++++++++++++++++ tests/qtest/meson.build | 3 +- 2 files changed, 191 insertions(+), 1 deletion(-) create mode 100644 tests/qtest/stm32l4x5_rcc-test.c diff --git a/tests/qtest/stm32l4x5_rcc-test.c b/tests/qtest/stm32l4x5_rcc-test.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/qtest/stm32l4x5_rcc-test.c @@ -XXX,XX +XXX,XX @@ +/* + * QTest testcase for STM32L4x5_RCC + * + * Copyright (c) 2023 Arnaud Minier <arnaud.minier@telecom-paris.fr> + * Copyright (c) 2023 Inès Varhol <ines.varhol@telecom-paris.fr> + * + * SPDX-License-Identifier: GPL-2.0-or-later + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "hw/registerfields.h" +#include "libqtest-single.h" +#include "hw/misc/stm32l4x5_rcc_internals.h" + +#define RCC_BASE_ADDR 0x40021000 +#define NVIC_ISER 0xE000E100 +#define NVIC_ISPR 0xE000E200 +#define NVIC_ICPR 0xE000E280 +#define RCC_IRQ 5 + +static void enable_nvic_irq(unsigned int n) +{ + writel(NVIC_ISER, 1 << n); +} + +static void unpend_nvic_irq(unsigned int n) +{ + writel(NVIC_ICPR, 1 << n); +} + +static bool check_nvic_pending(unsigned int n) +{ + return readl(NVIC_ISPR) & (1 << n); +} + +static void rcc_writel(unsigned int offset, uint32_t value) +{ + writel(RCC_BASE_ADDR + offset, value); +} + +static uint32_t rcc_readl(unsigned int offset) +{ + return readl(RCC_BASE_ADDR + offset); +} + +static void test_init_msi(void) +{ + /* MSIRANGE can be set only when MSI is OFF or READY */ + rcc_writel(A_CR, R_CR_MSION_MASK); + /* Wait until MSI is stable */ + g_assert_true((rcc_readl(A_CR) & R_CR_MSIRDY_MASK) == R_CR_MSIRDY_MASK); + /* TODO find a way to test MSI value */ +} + +static void test_set_msi_as_sysclk(void) +{ + /* Clocking from MSI, in case MSI was not the default source */ + rcc_writel(A_CFGR, 0); + /* Wait until MSI is selected and stable */ + g_assert_true((rcc_readl(A_CFGR) & R_CFGR_SWS_MASK) == 0); +} + +static void test_init_pll(void) +{ + uint32_t value; + + /* + * Update PLL and set MSI as the source clock. + * PLLM = 1 --> 000 + * PLLN = 40 --> 40 + * PPLLR = 2 --> 00 + * PLLDIV = unused, PLLP = unused (SAI3), PLLQ = unused (48M1) + * SRC = MSI --> 01 + */ + rcc_writel(A_PLLCFGR, R_PLLCFGR_PLLREN_MASK | + (40 << R_PLLCFGR_PLLN_SHIFT) | + (0b01 << R_PLLCFGR_PLLSRC_SHIFT)); + + /* PLL activation */ + value = rcc_readl(A_CR); + rcc_writel(A_CR, value | R_CR_PLLON_MASK); + + /* Waiting for PLL lock. */ + g_assert_true((rcc_readl(A_CR) & R_CR_PLLRDY_MASK) == R_CR_PLLRDY_MASK); + + /* Switches on the PLL clock source */ + value = rcc_readl(A_CFGR); + rcc_writel(A_CFGR, (value & ~R_CFGR_SW_MASK) | + (0b11 << R_CFGR_SW_SHIFT)); + + /* Wait until SYSCLK is stable. */ + g_assert_true((rcc_readl(A_CFGR) & R_CFGR_SWS_MASK) == + (0b11 << R_CFGR_SWS_SHIFT)); +} + +static void test_activate_lse(void) +{ + /* LSE activation, no LSE Bypass */ + rcc_writel(A_BDCR, R_BDCR_LSEDRV_MASK | R_BDCR_LSEON_MASK); + g_assert_true((rcc_readl(A_BDCR) & R_BDCR_LSERDY_MASK) == R_BDCR_LSERDY_MASK); +} + +static void test_irq(void) +{ + enable_nvic_irq(RCC_IRQ); + + rcc_writel(A_CIER, R_CIER_LSIRDYIE_MASK); + rcc_writel(A_CSR, R_CSR_LSION_MASK); + g_assert_true(check_nvic_pending(RCC_IRQ)); + rcc_writel(A_CICR, R_CICR_LSIRDYC_MASK); + unpend_nvic_irq(RCC_IRQ); + + rcc_writel(A_CIER, R_CIER_LSERDYIE_MASK); + rcc_writel(A_BDCR, R_BDCR_LSEON_MASK); + g_assert_true(check_nvic_pending(RCC_IRQ)); + rcc_writel(A_CICR, R_CICR_LSERDYC_MASK); + unpend_nvic_irq(RCC_IRQ); + + /* + * MSI has been enabled by previous tests, + * shouln't generate an interruption. + */ + rcc_writel(A_CIER, R_CIER_MSIRDYIE_MASK); + rcc_writel(A_CR, R_CR_MSION_MASK); + g_assert_false(check_nvic_pending(RCC_IRQ)); + + rcc_writel(A_CIER, R_CIER_HSIRDYIE_MASK); + rcc_writel(A_CR, R_CR_HSION_MASK); + g_assert_true(check_nvic_pending(RCC_IRQ)); + rcc_writel(A_CICR, R_CICR_HSIRDYC_MASK); + unpend_nvic_irq(RCC_IRQ); + + rcc_writel(A_CIER, R_CIER_HSERDYIE_MASK); + rcc_writel(A_CR, R_CR_HSEON_MASK); + g_assert_true(check_nvic_pending(RCC_IRQ)); + rcc_writel(A_CICR, R_CICR_HSERDYC_MASK); + unpend_nvic_irq(RCC_IRQ); + + /* + * PLL has been enabled by previous tests, + * shouln't generate an interruption. + */ + rcc_writel(A_CIER, R_CIER_PLLRDYIE_MASK); + rcc_writel(A_CR, R_CR_PLLON_MASK); + g_assert_false(check_nvic_pending(RCC_IRQ)); + + rcc_writel(A_CIER, R_CIER_PLLSAI1RDYIE_MASK); + rcc_writel(A_CR, R_CR_PLLSAI1ON_MASK); + g_assert_true(check_nvic_pending(RCC_IRQ)); + rcc_writel(A_CICR, R_CICR_PLLSAI1RDYC_MASK); + unpend_nvic_irq(RCC_IRQ); + + rcc_writel(A_CIER, R_CIER_PLLSAI2RDYIE_MASK); + rcc_writel(A_CR, R_CR_PLLSAI2ON_MASK); + g_assert_true(check_nvic_pending(RCC_IRQ)); + rcc_writel(A_CICR, R_CICR_PLLSAI2RDYC_MASK); + unpend_nvic_irq(RCC_IRQ); +} + +int main(int argc, char **argv) +{ + int ret; + + g_test_init(&argc, &argv, NULL); + g_test_set_nonfatal_assertions(); + /* + * These test separately that we can enable the plls, change the sysclk, + * and enable different devices. + * They are dependent on one another. + * We assume that all operations that would take some time to have an effect + * (e.g. changing the PLL frequency) are done instantaneously. + */ + qtest_add_func("stm32l4x5/rcc/init_msi", test_init_msi); + qtest_add_func("stm32l4x5/rcc/set_msi_as_sysclk", + test_set_msi_as_sysclk); + qtest_add_func("stm32l4x5/rcc/activate_lse", test_activate_lse); + qtest_add_func("stm32l4x5/rcc/init_pll", test_init_pll); + + qtest_add_func("stm32l4x5/rcc/irq", test_irq); + + qtest_start("-machine b-l475e-iot01a"); + ret = g_test_run(); + qtest_end(); + + return ret; +} diff --git a/tests/qtest/meson.build b/tests/qtest/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/qtest/meson.build +++ b/tests/qtest/meson.build @@ -XXX,XX +XXX,XX @@ qtests_aspeed = \ qtests_stm32l4x5 = \ ['stm32l4x5_exti-test', - 'stm32l4x5_syscfg-test'] + 'stm32l4x5_syscfg-test', + 'stm32l4x5_rcc-test'] qtests_arm = \ (config_all_devices.has_key('CONFIG_MPS2') ? ['sse-timer-test'] : []) + \ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Now that we have removed TARGET_PAGE_BITS_MIN-6 from TLB_FLAGS_MASK, we can test for 32-byte alignment. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240301204110.656742-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/translate.c | 8 +------- 1 file changed, 1 insertion(+), 7 deletions(-) diff --git a/target/arm/tcg/translate.c b/target/arm/tcg/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.c +++ b/target/arm/tcg/translate.c @@ -XXX,XX +XXX,XX @@ static inline void store_reg_from_load(DisasContext *s, int reg, TCGv_i32 var) MemOp pow2_align(unsigned i) { static const MemOp mop_align[] = { - 0, MO_ALIGN_2, MO_ALIGN_4, MO_ALIGN_8, MO_ALIGN_16, - /* - * FIXME: TARGET_PAGE_BITS_MIN affects TLB_FLAGS_MASK such - * that 256-bit alignment (MO_ALIGN_32) cannot be supported: - * see get_alignment_bits(). Enforce only 128-bit alignment for now. - */ - MO_ALIGN_16 + 0, MO_ALIGN_2, MO_ALIGN_4, MO_ALIGN_8, MO_ALIGN_16, MO_ALIGN_32 }; g_assert(i < ARRAY_SIZE(mop_align)); return mop_align[i]; -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> These fields are no longer used since 937f224559. Target specific extensions to the page tables should be done with TARGET_PAGE_ENTRY_EXTRA. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240301204110.656742-3-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/exec/memattrs.h | 10 ---------- 1 file changed, 10 deletions(-) diff --git a/include/exec/memattrs.h b/include/exec/memattrs.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memattrs.h +++ b/include/exec/memattrs.h @@ -XXX,XX +XXX,XX @@ typedef struct MemTxAttrs { unsigned int requester_id:16; /* Invert endianness for this page */ unsigned int byte_swap:1; - /* - * The following are target-specific page-table bits. These are not - * related to actual memory transactions at all. However, this structure - * is part of the tlb_fill interface, cached in the cputlb structure, - * and has unused bits. These fields will be read by target-specific - * helpers using env->iotlb[mmu_idx][tlb_index()].attrs.target_tlb_bitN. - */ - unsigned int target_tlb_bit0 : 1; - unsigned int target_tlb_bit1 : 1; - unsigned int target_tlb_bit2 : 1; } MemTxAttrs; /* Bus masters which don't specify any attributes will get this, -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Allow the target to set tlb flags to apply to all of the comparators. Remove MemTxAttrs.byte_swap, as the bit is not relevant to memory transactions, only the page mapping. Adjust target/sparc to set TLB_BSWAP directly. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240301204110.656742-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/exec/memattrs.h | 2 -- include/hw/core/cpu.h | 3 +++ accel/tcg/cputlb.c | 5 +---- target/sparc/mmu_helper.c | 2 +- 4 files changed, 5 insertions(+), 7 deletions(-) diff --git a/include/exec/memattrs.h b/include/exec/memattrs.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/memattrs.h +++ b/include/exec/memattrs.h @@ -XXX,XX +XXX,XX @@ typedef struct MemTxAttrs { unsigned int memory:1; /* Requester ID (for MSI for example) */ unsigned int requester_id:16; - /* Invert endianness for this page */ - unsigned int byte_swap:1; } MemTxAttrs; /* Bus masters which don't specify any attributes will get this, diff --git a/include/hw/core/cpu.h b/include/hw/core/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/core/cpu.h +++ b/include/hw/core/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUTLBEntryFull { /* @lg_page_size contains the log2 of the page size. */ uint8_t lg_page_size; + /* Additional tlb flags requested by tlb_fill. */ + uint8_t tlb_fill_flags; + /* * Additional tlb flags for use by the slow path. If non-zero, * the corresponding CPUTLBEntry comparator must have TLB_FORCE_SLOW. diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ void tlb_set_page_full(CPUState *cpu, int mmu_idx, " prot=%x idx=%d\n", addr, full->phys_addr, prot, mmu_idx); - read_flags = 0; + read_flags = full->tlb_fill_flags; if (full->lg_page_size < TARGET_PAGE_BITS) { /* Repeat the MMU check and TLB fill on every access. */ read_flags |= TLB_INVALID_MASK; } - if (full->attrs.byte_swap) { - read_flags |= TLB_BSWAP; - } is_ram = memory_region_is_ram(section->mr); is_romd = memory_region_is_romd(section->mr); diff --git a/target/sparc/mmu_helper.c b/target/sparc/mmu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/mmu_helper.c +++ b/target/sparc/mmu_helper.c @@ -XXX,XX +XXX,XX @@ static int get_physical_address_data(CPUSPARCState *env, CPUTLBEntryFull *full, int do_fault = 0; if (TTE_IS_IE(env->dtlb[i].tte)) { - full->attrs.byte_swap = true; + full->tlb_fill_flags |= TLB_BSWAP; } /* access ok? */ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> This creates a per-page method for checking of alignment. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240301204110.656742-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/exec/cpu-all.h | 4 +++- accel/tcg/cputlb.c | 30 +++++++++++++++++++++++++++--- 2 files changed, 30 insertions(+), 4 deletions(-) diff --git a/include/exec/cpu-all.h b/include/exec/cpu-all.h index XXXXXXX..XXXXXXX 100644 --- a/include/exec/cpu-all.h +++ b/include/exec/cpu-all.h @@ -XXX,XX +XXX,XX @@ static inline int cpu_mmu_index(CPUState *cs, bool ifetch) #define TLB_BSWAP (1 << 0) /* Set if TLB entry contains a watchpoint. */ #define TLB_WATCHPOINT (1 << 1) +/* Set if TLB entry requires aligned accesses. */ +#define TLB_CHECK_ALIGNED (1 << 2) -#define TLB_SLOW_FLAGS_MASK (TLB_BSWAP | TLB_WATCHPOINT) +#define TLB_SLOW_FLAGS_MASK (TLB_BSWAP | TLB_WATCHPOINT | TLB_CHECK_ALIGNED) /* The two sets of flags must not overlap. */ QEMU_BUILD_BUG_ON(TLB_FLAGS_MASK & TLB_SLOW_FLAGS_MASK); diff --git a/accel/tcg/cputlb.c b/accel/tcg/cputlb.c index XXXXXXX..XXXXXXX 100644 --- a/accel/tcg/cputlb.c +++ b/accel/tcg/cputlb.c @@ -XXX,XX +XXX,XX @@ static int probe_access_internal(CPUState *cpu, vaddr addr, flags |= full->slow_flags[access_type]; /* Fold all "mmio-like" bits into TLB_MMIO. This is not RAM. */ - if (unlikely(flags & ~(TLB_WATCHPOINT | TLB_NOTDIRTY)) - || - (access_type != MMU_INST_FETCH && force_mmio)) { + if (unlikely(flags & ~(TLB_WATCHPOINT | TLB_NOTDIRTY | TLB_CHECK_ALIGNED)) + || (access_type != MMU_INST_FETCH && force_mmio)) { *phost = NULL; return TLB_MMIO; } @@ -XXX,XX +XXX,XX @@ static bool mmu_lookup(CPUState *cpu, vaddr addr, MemOpIdx oi, tcg_debug_assert((flags & TLB_BSWAP) == 0); } + /* + * This alignment check differs from the one above, in that this is + * based on the atomicity of the operation. The intended use case is + * the ARM memory type field of each PTE, where access to pages with + * Device memory type require alignment. + */ + if (unlikely(flags & TLB_CHECK_ALIGNED)) { + MemOp size = l->memop & MO_SIZE; + + switch (l->memop & MO_ATOM_MASK) { + case MO_ATOM_NONE: + size = MO_8; + break; + case MO_ATOM_IFALIGN_PAIR: + case MO_ATOM_WITHIN16_PAIR: + size = size ? size - 1 : 0; + break; + default: + break; + } + if (addr & ((1 << size) - 1)) { + cpu_unaligned_access(cpu, addr, type, l->mmu_idx, ra); + } + } + return crosspage; } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> If translation is disabled, the default memory type is Device, which requires alignment checking. This is more optimally done early via the MemOp given to the TCG memory operation. Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reported-by: Idan Horowitz <idan.horowitz@gmail.com> Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240301204110.656742-6-richard.henderson@linaro.org Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1204 Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/hflags.c | 34 ++++++++++++++++++++++++++++++++-- 1 file changed, 32 insertions(+), 2 deletions(-) diff --git a/target/arm/tcg/hflags.c b/target/arm/tcg/hflags.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/hflags.c +++ b/target/arm/tcg/hflags.c @@ -XXX,XX +XXX,XX @@ static inline bool fgt_svc(CPUARMState *env, int el) FIELD_EX64(env->cp15.fgt_exec[FGTREG_HFGITR], HFGITR_EL2, SVC_EL1); } +/* Return true if memory alignment should be enforced. */ +static bool aprofile_require_alignment(CPUARMState *env, int el, uint64_t sctlr) +{ +#ifdef CONFIG_USER_ONLY + return false; +#else + /* Check the alignment enable bit. */ + if (sctlr & SCTLR_A) { + return true; + } + + /* + * If translation is disabled, then the default memory type is + * Device(-nGnRnE) instead of Normal, which requires that alignment + * be enforced. Since this affects all ram, it is most efficient + * to handle this during translation. + */ + if (sctlr & SCTLR_M) { + /* Translation enabled: memory type in PTE via MAIR_ELx. */ + return false; + } + if (el < 2 && (arm_hcr_el2_eff(env) & (HCR_DC | HCR_VM))) { + /* Stage 2 translation enabled: memory type in PTE. */ + return false; + } + return true; +#endif +} + static CPUARMTBFlags rebuild_hflags_common(CPUARMState *env, int fp_el, ARMMMUIdx mmu_idx, CPUARMTBFlags flags) @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a32(CPUARMState *env, int fp_el, { CPUARMTBFlags flags = {}; int el = arm_current_el(env); + uint64_t sctlr = arm_sctlr(env, el); - if (arm_sctlr(env, el) & SCTLR_A) { + if (aprofile_require_alignment(env, el, sctlr)) { DP_TBFLAG_ANY(flags, ALIGN_MEM, 1); } @@ -XXX,XX +XXX,XX @@ static CPUARMTBFlags rebuild_hflags_a64(CPUARMState *env, int el, int fp_el, sctlr = regime_sctlr(env, stage1); - if (sctlr & SCTLR_A) { + if (aprofile_require_alignment(env, el, sctlr)) { DP_TBFLAG_ANY(flags, ALIGN_MEM, 1); } -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> If translation is enabled, and the PTE memory type is Device, enable checking alignment via TLB_CHECK_ALIGNMENT. While the check is done later than it should be per the ARM, it's better than not performing the check at all. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20240301204110.656742-7-richard.henderson@linaro.org [PMM: tweaks to comment text] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/ptw.c | 39 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/target/arm/ptw.c b/target/arm/ptw.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/ptw.c +++ b/target/arm/ptw.c @@ -XXX,XX +XXX,XX @@ static bool granule_protection_check(CPUARMState *env, uint64_t paddress, return false; } +static bool S1_attrs_are_device(uint8_t attrs) +{ + /* + * This slightly under-decodes the MAIR_ELx field: + * 0b0000dd01 is Device with FEAT_XS, otherwise UNPREDICTABLE; + * 0b0000dd1x is UNPREDICTABLE. + */ + return (attrs & 0xf0) == 0; +} + static bool S2_attrs_are_device(uint64_t hcr, uint8_t attrs) { /* @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, bool aarch64 = arm_el_is_aa64(env, el); uint64_t descriptor, new_descriptor; ARMSecuritySpace out_space; + bool device; /* TODO: This code does not support shareability levels. */ if (aarch64) { @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, if (regime_is_stage2(mmu_idx)) { result->cacheattrs.is_s2_format = true; result->cacheattrs.attrs = extract32(attrs, 2, 4); + /* + * Security state does not really affect HCR_EL2.FWB; + * we only need to filter FWB for aa32 or other FEAT. + */ + device = S2_attrs_are_device(arm_hcr_el2_eff(env), + result->cacheattrs.attrs); } else { /* Index into MAIR registers for cache attributes */ uint8_t attrindx = extract32(attrs, 2, 3); @@ -XXX,XX +XXX,XX @@ static bool get_phys_addr_lpae(CPUARMState *env, S1Translate *ptw, if (aarch64 && cpu_isar_feature(aa64_bti, cpu)) { result->f.extra.arm.guarded = extract64(attrs, 50, 1); /* GP */ } + device = S1_attrs_are_device(result->cacheattrs.attrs); + } + + /* + * Enable alignment checks on Device memory. + * + * Per R_XCHFJ, this check is mis-ordered. The correct ordering + * for alignment, permission, and stage 2 faults should be: + * - Alignment fault caused by the memory type + * - Permission fault + * - A stage 2 fault on the memory access + * but due to the way the TCG softmmu TLB operates, we will have + * implicitly done the permission check and the stage2 lookup in + * finding the TLB entry, so the alignment check cannot be done sooner. + * + * In v7, for a CPU without the Virtualization Extensions this + * access is UNPREDICTABLE; we choose to make it take the alignment + * fault as is required for a v7VE CPU. (QEMU doesn't emulate any + * CPUs with ARM_FEATURE_LPAE but not ARM_FEATURE_V7VE anyway.) + */ + if (device) { + result->f.tlb_fill_flags |= TLB_CHECK_ALIGNED; } /* -- 2.34.1 The qatomic_cmpxchg() and qatomic_cmpxchg__nocheck() macros have a comment that reads: Returns the eventual value, failed or not This is somewhere between cryptic and wrong, since the value actually returned is the value that was in memory before the cmpxchg. Reword to match how we describe these macros in atomics.rst. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> Reviewed-by: Zhao Liu <zhao1.liu@intel.com> Message-id: 20240223182035.1048541-1-peter.maydell@linaro.org --- include/qemu/atomic.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/qemu/atomic.h b/include/qemu/atomic.h index XXXXXXX..XXXXXXX 100644 --- a/include/qemu/atomic.h +++ b/include/qemu/atomic.h @@ -XXX,XX +XXX,XX @@ qatomic_xchg__nocheck(ptr, i); \ }) -/* Returns the eventual value, failed or not */ +/* Returns the old value of '*ptr' (whether the cmpxchg failed or not) */ #define qatomic_cmpxchg__nocheck(ptr, old, new) ({ \ typeof_strip_qual(*ptr) _old = (old); \ (void)__atomic_compare_exchange_n(ptr, &_old, new, false, \ -- 2.34.1 From: Steven Shen <steven.shen@jaguarmicro.com> Before v2.12, the implementation of serial ports was limited to a value of MAX_SERIAL_PORTS = 4. We now dynamically allocate the data structures for serial ports, so this limit is no longer present, but the documentation for the -serial options still reads: "This option can be used several times to simulate up to 4 serial ports." Update to "This option can be used several times to simulate multiple serial ports." to avoid misleading. Signed-off-by: Steven Shen <steven.shen@jaguarmicro.com> Message-id: 20240305013016.2268-1-steven.shen@jaguarmicro.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> [PMM: tweaked commit message] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- qemu-options.hx | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/qemu-options.hx b/qemu-options.hx index XXXXXXX..XXXXXXX 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -XXX,XX +XXX,XX @@ SRST default device is ``vc`` in graphical mode and ``stdio`` in non graphical mode. - This option can be used several times to simulate up to 4 serial + This option can be used several times to simulate multiple serial ports. You can use ``-serial none`` to suppress the creation of default -- 2.34.1 First arm pullreq of the cycle; this is mostly my softfloat NaN handling series. (Lots more in my to-review queue, but I don't like pullreqs growing too close to a hundred patches at a time :-)) thanks -- PMM The following changes since commit 97f2796a3736ed37a1b85dc1c76a6c45b829dd17: Open 10.0 development tree (2024-12-10 17:41:17 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20241211 for you to fetch changes up to 1abe28d519239eea5cf9620bb13149423e5665f8: MAINTAINERS: Add correct email address for Vikram Garhwal (2024-12-11 15:31:09 +0000) ---------------------------------------------------------------- target-arm queue: * hw/net/lan9118: Extract PHY model, reuse with imx_fec, fix bugs * fpu: Make muladd NaN handling runtime-selected, not compile-time * fpu: Make default NaN pattern runtime-selected, not compile-time * fpu: Minor NaN-related cleanups * MAINTAINERS: email address updates ---------------------------------------------------------------- Bernhard Beschow (5): hw/net/lan9118: Extract lan9118_phy hw/net/lan9118_phy: Reuse in imx_fec and consolidate implementations hw/net/lan9118_phy: Fix off-by-one error in MII_ANLPAR register hw/net/lan9118_phy: Reuse MII constants hw/net/lan9118_phy: Add missing 100 mbps full duplex advertisement Leif Lindholm (1): MAINTAINERS: update email address for Leif Lindholm Peter Maydell (54): fpu: handle raising Invalid for infzero in pick_nan_muladd fpu: Check for default_nan_mode before calling pickNaNMulAdd softfloat: Allow runtime choice of inf * 0 + NaN result tests/fp: Explicitly set inf-zero-nan rule target/arm: Set FloatInfZeroNaNRule explicitly target/s390: Set FloatInfZeroNaNRule explicitly target/ppc: Set FloatInfZeroNaNRule explicitly target/mips: Set FloatInfZeroNaNRule explicitly target/sparc: Set FloatInfZeroNaNRule explicitly target/xtensa: Set FloatInfZeroNaNRule explicitly target/x86: Set FloatInfZeroNaNRule explicitly target/loongarch: Set FloatInfZeroNaNRule explicitly target/hppa: Set FloatInfZeroNaNRule explicitly softfloat: Pass have_snan to pickNaNMulAdd softfloat: Allow runtime choice of NaN propagation for muladd tests/fp: Explicitly set 3-NaN propagation rule target/arm: Set Float3NaNPropRule explicitly target/loongarch: Set Float3NaNPropRule explicitly target/ppc: Set Float3NaNPropRule explicitly target/s390x: Set Float3NaNPropRule explicitly target/sparc: Set Float3NaNPropRule explicitly target/mips: Set Float3NaNPropRule explicitly target/xtensa: Set Float3NaNPropRule explicitly target/i386: Set Float3NaNPropRule explicitly target/hppa: Set Float3NaNPropRule explicitly fpu: Remove use_first_nan field from float_status target/m68k: Don't pass NULL float_status to floatx80_default_nan() softfloat: Create floatx80 default NaN from parts64_default_nan target/loongarch: Use normal float_status in fclass_s and fclass_d helpers target/m68k: In frem helper, initialize local float_status from env->fp_status target/m68k: Init local float_status from env fp_status in gdb get/set reg target/sparc: Initialize local scratch float_status from env->fp_status target/ppc: Use env->fp_status in helper_compute_fprf functions fpu: Allow runtime choice of default NaN value tests/fp: Set default NaN pattern explicitly target/microblaze: Set default NaN pattern explicitly target/i386: Set default NaN pattern explicitly target/hppa: Set default NaN pattern explicitly target/alpha: Set default NaN pattern explicitly target/arm: Set default NaN pattern explicitly target/loongarch: Set default NaN pattern explicitly target/m68k: Set default NaN pattern explicitly target/mips: Set default NaN pattern explicitly target/openrisc: Set default NaN pattern explicitly target/ppc: Set default NaN pattern explicitly target/sh4: Set default NaN pattern explicitly target/rx: Set default NaN pattern explicitly target/s390x: Set default NaN pattern explicitly target/sparc: Set default NaN pattern explicitly target/xtensa: Set default NaN pattern explicitly target/hexagon: Set default NaN pattern explicitly target/riscv: Set default NaN pattern explicitly target/tricore: Set default NaN pattern explicitly fpu: Remove default handling for dnan_pattern Richard Henderson (11): target/arm: Copy entire float_status in is_ebf softfloat: Inline pickNaNMulAdd softfloat: Use goto for default nan case in pick_nan_muladd softfloat: Remove which from parts_pick_nan_muladd softfloat: Pad array size in pick_nan_muladd softfloat: Move propagateFloatx80NaN to softfloat.c softfloat: Use parts_pick_nan in propagateFloatx80NaN softfloat: Inline pickNaN softfloat: Share code between parts_pick_nan cases softfloat: Sink frac_cmp in parts_pick_nan until needed softfloat: Replace WHICH with RET in parts_pick_nan Vikram Garhwal (1): MAINTAINERS: Add correct email address for Vikram Garhwal MAINTAINERS | 4 +- include/fpu/softfloat-helpers.h | 38 +++- include/fpu/softfloat-types.h | 89 +++++++- include/hw/net/imx_fec.h | 9 +- include/hw/net/lan9118_phy.h | 37 ++++ include/hw/net/mii.h | 6 + target/mips/fpu_helper.h | 20 ++ target/sparc/helper.h | 4 +- fpu/softfloat.c | 19 ++ hw/net/imx_fec.c | 146 ++------------ hw/net/lan9118.c | 137 ++----------- hw/net/lan9118_phy.c | 222 ++++++++++++++++++++ linux-user/arm/nwfpe/fpa11.c | 5 + target/alpha/cpu.c | 2 + target/arm/cpu.c | 10 + target/arm/tcg/vec_helper.c | 20 +- target/hexagon/cpu.c | 2 + target/hppa/fpu_helper.c | 12 ++ target/i386/tcg/fpu_helper.c | 12 ++ target/loongarch/tcg/fpu_helper.c | 14 +- target/m68k/cpu.c | 14 +- target/m68k/fpu_helper.c | 6 +- target/m68k/helper.c | 6 +- target/microblaze/cpu.c | 2 + target/mips/msa.c | 10 + target/openrisc/cpu.c | 2 + target/ppc/cpu_init.c | 19 ++ target/ppc/fpu_helper.c | 3 +- target/riscv/cpu.c | 2 + target/rx/cpu.c | 2 + target/s390x/cpu.c | 5 + target/sh4/cpu.c | 2 + target/sparc/cpu.c | 6 + target/sparc/fop_helper.c | 8 +- target/sparc/translate.c | 4 +- target/tricore/helper.c | 2 + target/xtensa/cpu.c | 4 + target/xtensa/fpu_helper.c | 3 +- tests/fp/fp-bench.c | 7 + tests/fp/fp-test-log2.c | 1 + tests/fp/fp-test.c | 7 + fpu/softfloat-parts.c.inc | 152 +++++++++++--- fpu/softfloat-specialize.c.inc | 412 ++------------------------------------ .mailmap | 5 +- hw/net/Kconfig | 5 + hw/net/meson.build | 1 + hw/net/trace-events | 10 +- 47 files changed, 778 insertions(+), 730 deletions(-) create mode 100644 include/hw/net/lan9118_phy.h create mode 100644 hw/net/lan9118_phy.c From: Bernhard Beschow <shentey@gmail.com> A very similar implementation of the same device exists in imx_fec. Prepare for a common implementation by extracting a device model into its own files. Some migration state has been moved into the new device model which breaks migration compatibility for the following machines: * smdkc210 * realview-* * vexpress-* * kzm * mps2-* While breaking migration ABI, fix the size of the MII registers to be 16 bit, as defined by IEEE 802.3u. Signed-off-by: Bernhard Beschow <shentey@gmail.com> Tested-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241102125724.532843-2-shentey@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/net/lan9118_phy.h | 37 ++++++++ hw/net/lan9118.c | 137 +++++----------------------- hw/net/lan9118_phy.c | 169 +++++++++++++++++++++++++++++++++++ hw/net/Kconfig | 4 + hw/net/meson.build | 1 + 5 files changed, 233 insertions(+), 115 deletions(-) create mode 100644 include/hw/net/lan9118_phy.h create mode 100644 hw/net/lan9118_phy.c diff --git a/include/hw/net/lan9118_phy.h b/include/hw/net/lan9118_phy.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/net/lan9118_phy.h @@ -XXX,XX +XXX,XX @@ +/* + * SMSC LAN9118 PHY emulation + * + * Copyright (c) 2009 CodeSourcery, LLC. + * Written by Paul Brook + * + * This work is licensed under the terms of the GNU GPL, version 2 or later. + * See the COPYING file in the top-level directory. + */ + +#ifndef HW_NET_LAN9118_PHY_H +#define HW_NET_LAN9118_PHY_H + +#include "qom/object.h" +#include "hw/sysbus.h" + +#define TYPE_LAN9118_PHY "lan9118-phy" +OBJECT_DECLARE_SIMPLE_TYPE(Lan9118PhyState, LAN9118_PHY) + +typedef struct Lan9118PhyState { + SysBusDevice parent_obj; + + uint16_t status; + uint16_t control; + uint16_t advertise; + uint16_t ints; + uint16_t int_mask; + qemu_irq irq; + bool link_down; +} Lan9118PhyState; + +void lan9118_phy_update_link(Lan9118PhyState *s, bool link_down); +void lan9118_phy_reset(Lan9118PhyState *s); +uint16_t lan9118_phy_read(Lan9118PhyState *s, int reg); +void lan9118_phy_write(Lan9118PhyState *s, int reg, uint16_t val); + +#endif diff --git a/hw/net/lan9118.c b/hw/net/lan9118.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/lan9118.c +++ b/hw/net/lan9118.c @@ -XXX,XX +XXX,XX @@ #include "net/net.h" #include "net/eth.h" #include "hw/irq.h" +#include "hw/net/lan9118_phy.h" #include "hw/net/lan9118.h" #include "hw/ptimer.h" #include "hw/qdev-properties.h" @@ -XXX,XX +XXX,XX @@ do { printf("lan9118: " fmt , ## __VA_ARGS__); } while (0) #define MAC_CR_RXEN 0x00000004 #define MAC_CR_RESERVED 0x7f404213 -#define PHY_INT_ENERGYON 0x80 -#define PHY_INT_AUTONEG_COMPLETE 0x40 -#define PHY_INT_FAULT 0x20 -#define PHY_INT_DOWN 0x10 -#define PHY_INT_AUTONEG_LP 0x08 -#define PHY_INT_PARFAULT 0x04 -#define PHY_INT_AUTONEG_PAGE 0x02 - #define GPT_TIMER_EN 0x20000000 /* @@ -XXX,XX +XXX,XX @@ struct lan9118_state { uint32_t mac_mii_data; uint32_t mac_flow; - uint32_t phy_status; - uint32_t phy_control; - uint32_t phy_advertise; - uint32_t phy_int; - uint32_t phy_int_mask; + Lan9118PhyState mii; + IRQState mii_irq; int32_t eeprom_writable; uint8_t eeprom[128]; @@ -XXX,XX +XXX,XX @@ struct lan9118_state { static const VMStateDescription vmstate_lan9118 = { .name = "lan9118", - .version_id = 2, - .minimum_version_id = 1, + .version_id = 3, + .minimum_version_id = 3, .fields = (const VMStateField[]) { VMSTATE_PTIMER(timer, lan9118_state), VMSTATE_UINT32(irq_cfg, lan9118_state), @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_lan9118 = { VMSTATE_UINT32(mac_mii_acc, lan9118_state), VMSTATE_UINT32(mac_mii_data, lan9118_state), VMSTATE_UINT32(mac_flow, lan9118_state), - VMSTATE_UINT32(phy_status, lan9118_state), - VMSTATE_UINT32(phy_control, lan9118_state), - VMSTATE_UINT32(phy_advertise, lan9118_state), - VMSTATE_UINT32(phy_int, lan9118_state), - VMSTATE_UINT32(phy_int_mask, lan9118_state), VMSTATE_INT32(eeprom_writable, lan9118_state), VMSTATE_UINT8_ARRAY(eeprom, lan9118_state, 128), VMSTATE_INT32(tx_fifo_size, lan9118_state), @@ -XXX,XX +XXX,XX @@ static void lan9118_reload_eeprom(lan9118_state *s) lan9118_mac_changed(s); } -static void phy_update_irq(lan9118_state *s) +static void lan9118_update_irq(void *opaque, int n, int level) { - if (s->phy_int & s->phy_int_mask) { + lan9118_state *s = opaque; + + if (level) { s->int_sts |= PHY_INT; } else { s->int_sts &= ~PHY_INT; @@ -XXX,XX +XXX,XX @@ static void phy_update_irq(lan9118_state *s) lan9118_update(s); } -static void phy_update_link(lan9118_state *s) -{ - /* Autonegotiation status mirrors link status. */ - if (qemu_get_queue(s->nic)->link_down) { - s->phy_status &= ~0x0024; - s->phy_int |= PHY_INT_DOWN; - } else { - s->phy_status |= 0x0024; - s->phy_int |= PHY_INT_ENERGYON; - s->phy_int |= PHY_INT_AUTONEG_COMPLETE; - } - phy_update_irq(s); -} - static void lan9118_set_link(NetClientState *nc) { - phy_update_link(qemu_get_nic_opaque(nc)); -} - -static void phy_reset(lan9118_state *s) -{ - s->phy_status = 0x7809; - s->phy_control = 0x3000; - s->phy_advertise = 0x01e1; - s->phy_int_mask = 0; - s->phy_int = 0; - phy_update_link(s); + lan9118_phy_update_link(&LAN9118(qemu_get_nic_opaque(nc))->mii, + nc->link_down); } static void lan9118_reset(DeviceState *d) @@ -XXX,XX +XXX,XX @@ static void lan9118_reset(DeviceState *d) s->read_word_n = 0; s->write_word_n = 0; - phy_reset(s); - s->eeprom_writable = 0; lan9118_reload_eeprom(s); } @@ -XXX,XX +XXX,XX @@ static void do_tx_packet(lan9118_state *s) uint32_t status; /* FIXME: Honor TX disable, and allow queueing of packets. */ - if (s->phy_control & 0x4000) { + if (s->mii.control & 0x4000) { /* This assumes the receive routine doesn't touch the VLANClient. */ qemu_receive_packet(qemu_get_queue(s->nic), s->txp->data, s->txp->len); } else { @@ -XXX,XX +XXX,XX @@ static void tx_fifo_push(lan9118_state *s, uint32_t val) } } -static uint32_t do_phy_read(lan9118_state *s, int reg) -{ - uint32_t val; - - switch (reg) { - case 0: /* Basic Control */ - return s->phy_control; - case 1: /* Basic Status */ - return s->phy_status; - case 2: /* ID1 */ - return 0x0007; - case 3: /* ID2 */ - return 0xc0d1; - case 4: /* Auto-neg advertisement */ - return s->phy_advertise; - case 5: /* Auto-neg Link Partner Ability */ - return 0x0f71; - case 6: /* Auto-neg Expansion */ - return 1; - /* TODO 17, 18, 27, 29, 30, 31 */ - case 29: /* Interrupt source. */ - val = s->phy_int; - s->phy_int = 0; - phy_update_irq(s); - return val; - case 30: /* Interrupt mask */ - return s->phy_int_mask; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "do_phy_read: PHY read reg %d\n", reg); - return 0; - } -} - -static void do_phy_write(lan9118_state *s, int reg, uint32_t val) -{ - switch (reg) { - case 0: /* Basic Control */ - if (val & 0x8000) { - phy_reset(s); - break; - } - s->phy_control = val & 0x7980; - /* Complete autonegotiation immediately. */ - if (val & 0x1000) { - s->phy_status |= 0x0020; - } - break; - case 4: /* Auto-neg advertisement */ - s->phy_advertise = (val & 0x2d7f) | 0x80; - break; - /* TODO 17, 18, 27, 31 */ - case 30: /* Interrupt mask */ - s->phy_int_mask = val & 0xff; - phy_update_irq(s); - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, - "do_phy_write: PHY write reg %d = 0x%04x\n", reg, val); - } -} - static void do_mac_write(lan9118_state *s, int reg, uint32_t val) { switch (reg) { @@ -XXX,XX +XXX,XX @@ static void do_mac_write(lan9118_state *s, int reg, uint32_t val) if (val & 2) { DPRINTF("PHY write %d = 0x%04x\n", (val >> 6) & 0x1f, s->mac_mii_data); - do_phy_write(s, (val >> 6) & 0x1f, s->mac_mii_data); + lan9118_phy_write(&s->mii, (val >> 6) & 0x1f, s->mac_mii_data); } else { - s->mac_mii_data = do_phy_read(s, (val >> 6) & 0x1f); + s->mac_mii_data = lan9118_phy_read(&s->mii, (val >> 6) & 0x1f); DPRINTF("PHY read %d = 0x%04x\n", (val >> 6) & 0x1f, s->mac_mii_data); } @@ -XXX,XX +XXX,XX @@ static void lan9118_writel(void *opaque, hwaddr offset, break; case CSR_PMT_CTRL: if (val & 0x400) { - phy_reset(s); + lan9118_phy_reset(&s->mii); } s->pmt_ctrl &= ~0x34e; s->pmt_ctrl |= (val & 0x34e); @@ -XXX,XX +XXX,XX @@ static void lan9118_realize(DeviceState *dev, Error **errp) const MemoryRegionOps *mem_ops = s->mode_16bit ? &lan9118_16bit_mem_ops : &lan9118_mem_ops; + qemu_init_irq(&s->mii_irq, lan9118_update_irq, s, 0); + object_initialize_child(OBJECT(s), "mii", &s->mii, TYPE_LAN9118_PHY); + if (!sysbus_realize_and_unref(SYS_BUS_DEVICE(&s->mii), errp)) { + return; + } + qdev_connect_gpio_out(DEVICE(&s->mii), 0, &s->mii_irq); + memory_region_init_io(&s->mmio, OBJECT(dev), mem_ops, s, "lan9118-mmio", 0x100); sysbus_init_mmio(sbd, &s->mmio); diff --git a/hw/net/lan9118_phy.c b/hw/net/lan9118_phy.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/net/lan9118_phy.c @@ -XXX,XX +XXX,XX @@ +/* + * SMSC LAN9118 PHY emulation + * + * Copyright (c) 2009 CodeSourcery, LLC. + * Written by Paul Brook + * + * This code is licensed under the GNU GPL v2 + * + * Contributions after 2012-01-13 are licensed under the terms of the + * GNU GPL, version 2 or (at your option) any later version. + */ + +#include "qemu/osdep.h" +#include "hw/net/lan9118_phy.h" +#include "hw/irq.h" +#include "hw/resettable.h" +#include "migration/vmstate.h" +#include "qemu/log.h" + +#define PHY_INT_ENERGYON (1 << 7) +#define PHY_INT_AUTONEG_COMPLETE (1 << 6) +#define PHY_INT_FAULT (1 << 5) +#define PHY_INT_DOWN (1 << 4) +#define PHY_INT_AUTONEG_LP (1 << 3) +#define PHY_INT_PARFAULT (1 << 2) +#define PHY_INT_AUTONEG_PAGE (1 << 1) + +static void lan9118_phy_update_irq(Lan9118PhyState *s) +{ + qemu_set_irq(s->irq, !!(s->ints & s->int_mask)); +} + +uint16_t lan9118_phy_read(Lan9118PhyState *s, int reg) +{ + uint16_t val; + + switch (reg) { + case 0: /* Basic Control */ + return s->control; + case 1: /* Basic Status */ + return s->status; + case 2: /* ID1 */ + return 0x0007; + case 3: /* ID2 */ + return 0xc0d1; + case 4: /* Auto-neg advertisement */ + return s->advertise; + case 5: /* Auto-neg Link Partner Ability */ + return 0x0f71; + case 6: /* Auto-neg Expansion */ + return 1; + /* TODO 17, 18, 27, 29, 30, 31 */ + case 29: /* Interrupt source. */ + val = s->ints; + s->ints = 0; + lan9118_phy_update_irq(s); + return val; + case 30: /* Interrupt mask */ + return s->int_mask; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "lan9118_phy_read: PHY read reg %d\n", reg); + return 0; + } +} + +void lan9118_phy_write(Lan9118PhyState *s, int reg, uint16_t val) +{ + switch (reg) { + case 0: /* Basic Control */ + if (val & 0x8000) { + lan9118_phy_reset(s); + break; + } + s->control = val & 0x7980; + /* Complete autonegotiation immediately. */ + if (val & 0x1000) { + s->status |= 0x0020; + } + break; + case 4: /* Auto-neg advertisement */ + s->advertise = (val & 0x2d7f) | 0x80; + break; + /* TODO 17, 18, 27, 31 */ + case 30: /* Interrupt mask */ + s->int_mask = val & 0xff; + lan9118_phy_update_irq(s); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "lan9118_phy_write: PHY write reg %d = 0x%04x\n", reg, val); + } +} + +void lan9118_phy_update_link(Lan9118PhyState *s, bool link_down) +{ + s->link_down = link_down; + + /* Autonegotiation status mirrors link status. */ + if (link_down) { + s->status &= ~0x0024; + s->ints |= PHY_INT_DOWN; + } else { + s->status |= 0x0024; + s->ints |= PHY_INT_ENERGYON; + s->ints |= PHY_INT_AUTONEG_COMPLETE; + } + lan9118_phy_update_irq(s); +} + +void lan9118_phy_reset(Lan9118PhyState *s) +{ + s->control = 0x3000; + s->status = 0x7809; + s->advertise = 0x01e1; + s->int_mask = 0; + s->ints = 0; + lan9118_phy_update_link(s, s->link_down); +} + +static void lan9118_phy_reset_hold(Object *obj, ResetType type) +{ + Lan9118PhyState *s = LAN9118_PHY(obj); + + lan9118_phy_reset(s); +} + +static void lan9118_phy_init(Object *obj) +{ + Lan9118PhyState *s = LAN9118_PHY(obj); + + qdev_init_gpio_out(DEVICE(s), &s->irq, 1); +} + +static const VMStateDescription vmstate_lan9118_phy = { + .name = "lan9118-phy", + .version_id = 1, + .minimum_version_id = 1, + .fields = (const VMStateField[]) { + VMSTATE_UINT16(control, Lan9118PhyState), + VMSTATE_UINT16(status, Lan9118PhyState), + VMSTATE_UINT16(advertise, Lan9118PhyState), + VMSTATE_UINT16(ints, Lan9118PhyState), + VMSTATE_UINT16(int_mask, Lan9118PhyState), + VMSTATE_BOOL(link_down, Lan9118PhyState), + VMSTATE_END_OF_LIST() + } +}; + +static void lan9118_phy_class_init(ObjectClass *klass, void *data) +{ + ResettableClass *rc = RESETTABLE_CLASS(klass); + DeviceClass *dc = DEVICE_CLASS(klass); + + rc->phases.hold = lan9118_phy_reset_hold; + dc->vmsd = &vmstate_lan9118_phy; +} + +static const TypeInfo types[] = { + { + .name = TYPE_LAN9118_PHY, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(Lan9118PhyState), + .instance_init = lan9118_phy_init, + .class_init = lan9118_phy_class_init, + } +}; + +DEFINE_TYPES(types) diff --git a/hw/net/Kconfig b/hw/net/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/net/Kconfig +++ b/hw/net/Kconfig @@ -XXX,XX +XXX,XX @@ config VMXNET3_PCI config SMC91C111 bool +config LAN9118_PHY + bool + config LAN9118 bool + select LAN9118_PHY select PTIMER config NE2000_ISA diff --git a/hw/net/meson.build b/hw/net/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/net/meson.build +++ b/hw/net/meson.build @@ -XXX,XX +XXX,XX @@ system_ss.add(when: 'CONFIG_VMXNET3_PCI', if_true: files('vmxnet3.c')) system_ss.add(when: 'CONFIG_SMC91C111', if_true: files('smc91c111.c')) system_ss.add(when: 'CONFIG_LAN9118', if_true: files('lan9118.c')) +system_ss.add(when: 'CONFIG_LAN9118_PHY', if_true: files('lan9118_phy.c')) system_ss.add(when: 'CONFIG_NE2000_ISA', if_true: files('ne2000-isa.c')) system_ss.add(when: 'CONFIG_OPENCORES_ETH', if_true: files('opencores_eth.c')) system_ss.add(when: 'CONFIG_XGMAC', if_true: files('xgmac.c')) -- 2.34.1 From: Bernhard Beschow <shentey@gmail.com> imx_fec models the same PHY as lan9118_phy. The code is almost the same with imx_fec having more logging and tracing. Merge these improvements into lan9118_phy and reuse in imx_fec to fix the code duplication. Some migration state how resides in the new device model which breaks migration compatibility for the following machines: * imx25-pdk * sabrelite * mcimx7d-sabre * mcimx6ul-evk Signed-off-by: Bernhard Beschow <shentey@gmail.com> Tested-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241102125724.532843-3-shentey@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/net/imx_fec.h | 9 ++- hw/net/imx_fec.c | 146 ++++----------------------------------- hw/net/lan9118_phy.c | 82 ++++++++++++++++------ hw/net/Kconfig | 1 + hw/net/trace-events | 10 +-- 5 files changed, 85 insertions(+), 163 deletions(-) diff --git a/include/hw/net/imx_fec.h b/include/hw/net/imx_fec.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/net/imx_fec.h +++ b/include/hw/net/imx_fec.h @@ -XXX,XX +XXX,XX @@ OBJECT_DECLARE_SIMPLE_TYPE(IMXFECState, IMX_FEC) #define TYPE_IMX_ENET "imx.enet" #include "hw/sysbus.h" +#include "hw/net/lan9118_phy.h" +#include "hw/irq.h" #include "net/net.h" #define ENET_EIR 1 @@ -XXX,XX +XXX,XX @@ struct IMXFECState { uint32_t tx_descriptor[ENET_TX_RING_NUM]; uint32_t tx_ring_num; - uint32_t phy_status; - uint32_t phy_control; - uint32_t phy_advertise; - uint32_t phy_int; - uint32_t phy_int_mask; + Lan9118PhyState mii; + IRQState mii_irq; uint32_t phy_num; bool phy_connected; struct IMXFECState *phy_consumer; diff --git a/hw/net/imx_fec.c b/hw/net/imx_fec.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/imx_fec.c +++ b/hw/net/imx_fec.c @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_imx_eth_txdescs = { static const VMStateDescription vmstate_imx_eth = { .name = TYPE_IMX_FEC, - .version_id = 2, - .minimum_version_id = 2, + .version_id = 3, + .minimum_version_id = 3, .fields = (const VMStateField[]) { VMSTATE_UINT32_ARRAY(regs, IMXFECState, ENET_MAX), VMSTATE_UINT32(rx_descriptor, IMXFECState), VMSTATE_UINT32(tx_descriptor[0], IMXFECState), - VMSTATE_UINT32(phy_status, IMXFECState), - VMSTATE_UINT32(phy_control, IMXFECState), - VMSTATE_UINT32(phy_advertise, IMXFECState), - VMSTATE_UINT32(phy_int, IMXFECState), - VMSTATE_UINT32(phy_int_mask, IMXFECState), VMSTATE_END_OF_LIST() }, .subsections = (const VMStateDescription * const []) { @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_imx_eth = { }, }; -#define PHY_INT_ENERGYON (1 << 7) -#define PHY_INT_AUTONEG_COMPLETE (1 << 6) -#define PHY_INT_FAULT (1 << 5) -#define PHY_INT_DOWN (1 << 4) -#define PHY_INT_AUTONEG_LP (1 << 3) -#define PHY_INT_PARFAULT (1 << 2) -#define PHY_INT_AUTONEG_PAGE (1 << 1) - static void imx_eth_update(IMXFECState *s); /* @@ -XXX,XX +XXX,XX @@ static void imx_eth_update(IMXFECState *s); * For now we don't handle any GPIO/interrupt line, so the OS will * have to poll for the PHY status. */ -static void imx_phy_update_irq(IMXFECState *s) +static void imx_phy_update_irq(void *opaque, int n, int level) { - imx_eth_update(s); -} - -static void imx_phy_update_link(IMXFECState *s) -{ - /* Autonegotiation status mirrors link status. */ - if (qemu_get_queue(s->nic)->link_down) { - trace_imx_phy_update_link("down"); - s->phy_status &= ~0x0024; - s->phy_int |= PHY_INT_DOWN; - } else { - trace_imx_phy_update_link("up"); - s->phy_status |= 0x0024; - s->phy_int |= PHY_INT_ENERGYON; - s->phy_int |= PHY_INT_AUTONEG_COMPLETE; - } - imx_phy_update_irq(s); + imx_eth_update(opaque); } static void imx_eth_set_link(NetClientState *nc) { - imx_phy_update_link(IMX_FEC(qemu_get_nic_opaque(nc))); -} - -static void imx_phy_reset(IMXFECState *s) -{ - trace_imx_phy_reset(); - - s->phy_status = 0x7809; - s->phy_control = 0x3000; - s->phy_advertise = 0x01e1; - s->phy_int_mask = 0; - s->phy_int = 0; - imx_phy_update_link(s); + lan9118_phy_update_link(&IMX_FEC(qemu_get_nic_opaque(nc))->mii, + nc->link_down); } static uint32_t imx_phy_read(IMXFECState *s, int reg) { - uint32_t val; uint32_t phy = reg / 32; if (!s->phy_connected) { @@ -XXX,XX +XXX,XX @@ static uint32_t imx_phy_read(IMXFECState *s, int reg) reg %= 32; - switch (reg) { - case 0: /* Basic Control */ - val = s->phy_control; - break; - case 1: /* Basic Status */ - val = s->phy_status; - break; - case 2: /* ID1 */ - val = 0x0007; - break; - case 3: /* ID2 */ - val = 0xc0d1; - break; - case 4: /* Auto-neg advertisement */ - val = s->phy_advertise; - break; - case 5: /* Auto-neg Link Partner Ability */ - val = 0x0f71; - break; - case 6: /* Auto-neg Expansion */ - val = 1; - break; - case 29: /* Interrupt source. */ - val = s->phy_int; - s->phy_int = 0; - imx_phy_update_irq(s); - break; - case 30: /* Interrupt mask */ - val = s->phy_int_mask; - break; - case 17: - case 18: - case 27: - case 31: - qemu_log_mask(LOG_UNIMP, "[%s.phy]%s: reg %d not implemented\n", - TYPE_IMX_FEC, __func__, reg); - val = 0; - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, "[%s.phy]%s: Bad address at offset %d\n", - TYPE_IMX_FEC, __func__, reg); - val = 0; - break; - } - - trace_imx_phy_read(val, phy, reg); - - return val; + return lan9118_phy_read(&s->mii, reg); } static void imx_phy_write(IMXFECState *s, int reg, uint32_t val) @@ -XXX,XX +XXX,XX @@ static void imx_phy_write(IMXFECState *s, int reg, uint32_t val) reg %= 32; - trace_imx_phy_write(val, phy, reg); - - switch (reg) { - case 0: /* Basic Control */ - if (val & 0x8000) { - imx_phy_reset(s); - } else { - s->phy_control = val & 0x7980; - /* Complete autonegotiation immediately. */ - if (val & 0x1000) { - s->phy_status |= 0x0020; - } - } - break; - case 4: /* Auto-neg advertisement */ - s->phy_advertise = (val & 0x2d7f) | 0x80; - break; - case 30: /* Interrupt mask */ - s->phy_int_mask = val & 0xff; - imx_phy_update_irq(s); - break; - case 17: - case 18: - case 27: - case 31: - qemu_log_mask(LOG_UNIMP, "[%s.phy)%s: reg %d not implemented\n", - TYPE_IMX_FEC, __func__, reg); - break; - default: - qemu_log_mask(LOG_GUEST_ERROR, "[%s.phy]%s: Bad address at offset %d\n", - TYPE_IMX_FEC, __func__, reg); - break; - } + lan9118_phy_write(&s->mii, reg, val); } static void imx_fec_read_bd(IMXFECBufDesc *bd, dma_addr_t addr) @@ -XXX,XX +XXX,XX @@ static void imx_eth_reset(DeviceState *d) s->rx_descriptor = 0; memset(s->tx_descriptor, 0, sizeof(s->tx_descriptor)); - - /* We also reset the PHY */ - imx_phy_reset(s); } static uint32_t imx_default_read(IMXFECState *s, uint32_t index) @@ -XXX,XX +XXX,XX @@ static void imx_eth_realize(DeviceState *dev, Error **errp) sysbus_init_irq(sbd, &s->irq[0]); sysbus_init_irq(sbd, &s->irq[1]); + qemu_init_irq(&s->mii_irq, imx_phy_update_irq, s, 0); + object_initialize_child(OBJECT(s), "mii", &s->mii, TYPE_LAN9118_PHY); + if (!sysbus_realize_and_unref(SYS_BUS_DEVICE(&s->mii), errp)) { + return; + } + qdev_connect_gpio_out(DEVICE(&s->mii), 0, &s->mii_irq); + qemu_macaddr_default_if_unset(&s->conf.macaddr); s->nic = qemu_new_nic(&imx_eth_net_info, &s->conf, diff --git a/hw/net/lan9118_phy.c b/hw/net/lan9118_phy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/lan9118_phy.c +++ b/hw/net/lan9118_phy.c @@ -XXX,XX +XXX,XX @@ * Copyright (c) 2009 CodeSourcery, LLC. * Written by Paul Brook * + * Copyright (c) 2013 Jean-Christophe Dubois. <jcd@tribudubois.net> + * * This code is licensed under the GNU GPL v2 * * Contributions after 2012-01-13 are licensed under the terms of the @@ -XXX,XX +XXX,XX @@ #include "hw/resettable.h" #include "migration/vmstate.h" #include "qemu/log.h" +#include "trace.h" #define PHY_INT_ENERGYON (1 << 7) #define PHY_INT_AUTONEG_COMPLETE (1 << 6) @@ -XXX,XX +XXX,XX @@ uint16_t lan9118_phy_read(Lan9118PhyState *s, int reg) switch (reg) { case 0: /* Basic Control */ - return s->control; + val = s->control; + break; case 1: /* Basic Status */ - return s->status; + val = s->status; + break; case 2: /* ID1 */ - return 0x0007; + val = 0x0007; + break; case 3: /* ID2 */ - return 0xc0d1; + val = 0xc0d1; + break; case 4: /* Auto-neg advertisement */ - return s->advertise; + val = s->advertise; + break; case 5: /* Auto-neg Link Partner Ability */ - return 0x0f71; + val = 0x0f71; + break; case 6: /* Auto-neg Expansion */ - return 1; - /* TODO 17, 18, 27, 29, 30, 31 */ + val = 1; + break; case 29: /* Interrupt source. */ val = s->ints; s->ints = 0; lan9118_phy_update_irq(s); - return val; + break; case 30: /* Interrupt mask */ - return s->int_mask; + val = s->int_mask; + break; + case 17: + case 18: + case 27: + case 31: + qemu_log_mask(LOG_UNIMP, "%s: reg %d not implemented\n", + __func__, reg); + val = 0; + break; default: - qemu_log_mask(LOG_GUEST_ERROR, - "lan9118_phy_read: PHY read reg %d\n", reg); - return 0; + qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad address at offset %d\n", + __func__, reg); + val = 0; + break; } + + trace_lan9118_phy_read(val, reg); + + return val; } void lan9118_phy_write(Lan9118PhyState *s, int reg, uint16_t val) { + trace_lan9118_phy_write(val, reg); + switch (reg) { case 0: /* Basic Control */ if (val & 0x8000) { lan9118_phy_reset(s); - break; - } - s->control = val & 0x7980; - /* Complete autonegotiation immediately. */ - if (val & 0x1000) { - s->status |= 0x0020; + } else { + s->control = val & 0x7980; + /* Complete autonegotiation immediately. */ + if (val & 0x1000) { + s->status |= 0x0020; + } } break; case 4: /* Auto-neg advertisement */ s->advertise = (val & 0x2d7f) | 0x80; break; - /* TODO 17, 18, 27, 31 */ case 30: /* Interrupt mask */ s->int_mask = val & 0xff; lan9118_phy_update_irq(s); break; + case 17: + case 18: + case 27: + case 31: + qemu_log_mask(LOG_UNIMP, "%s: reg %d not implemented\n", + __func__, reg); + break; default: - qemu_log_mask(LOG_GUEST_ERROR, - "lan9118_phy_write: PHY write reg %d = 0x%04x\n", reg, val); + qemu_log_mask(LOG_GUEST_ERROR, "%s: Bad address at offset %d\n", + __func__, reg); + break; } } @@ -XXX,XX +XXX,XX @@ void lan9118_phy_update_link(Lan9118PhyState *s, bool link_down) /* Autonegotiation status mirrors link status. */ if (link_down) { + trace_lan9118_phy_update_link("down"); s->status &= ~0x0024; s->ints |= PHY_INT_DOWN; } else { + trace_lan9118_phy_update_link("up"); s->status |= 0x0024; s->ints |= PHY_INT_ENERGYON; s->ints |= PHY_INT_AUTONEG_COMPLETE; @@ -XXX,XX +XXX,XX @@ void lan9118_phy_update_link(Lan9118PhyState *s, bool link_down) void lan9118_phy_reset(Lan9118PhyState *s) { + trace_lan9118_phy_reset(); + s->control = 0x3000; s->status = 0x7809; s->advertise = 0x01e1; @@ -XXX,XX +XXX,XX @@ static const VMStateDescription vmstate_lan9118_phy = { .version_id = 1, .minimum_version_id = 1, .fields = (const VMStateField[]) { - VMSTATE_UINT16(control, Lan9118PhyState), VMSTATE_UINT16(status, Lan9118PhyState), + VMSTATE_UINT16(control, Lan9118PhyState), VMSTATE_UINT16(advertise, Lan9118PhyState), VMSTATE_UINT16(ints, Lan9118PhyState), VMSTATE_UINT16(int_mask, Lan9118PhyState), diff --git a/hw/net/Kconfig b/hw/net/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/net/Kconfig +++ b/hw/net/Kconfig @@ -XXX,XX +XXX,XX @@ config ALLWINNER_SUN8I_EMAC config IMX_FEC bool + select LAN9118_PHY config CADENCE bool diff --git a/hw/net/trace-events b/hw/net/trace-events index XXXXXXX..XXXXXXX 100644 --- a/hw/net/trace-events +++ b/hw/net/trace-events @@ -XXX,XX +XXX,XX @@ allwinner_sun8i_emac_set_link(bool active) "Set link: active=%u" allwinner_sun8i_emac_read(uint64_t offset, uint64_t val) "MMIO read: offset=0x%" PRIx64 " value=0x%" PRIx64 allwinner_sun8i_emac_write(uint64_t offset, uint64_t val) "MMIO write: offset=0x%" PRIx64 " value=0x%" PRIx64 +# lan9118_phy.c +lan9118_phy_read(uint16_t val, int reg) "[0x%02x] -> 0x%04" PRIx16 +lan9118_phy_write(uint16_t val, int reg) "[0x%02x] <- 0x%04" PRIx16 +lan9118_phy_update_link(const char *s) "%s" +lan9118_phy_reset(void) "" + # lance.c lance_mem_readw(uint64_t addr, uint32_t ret) "addr=0x%"PRIx64"val=0x%04x" lance_mem_writew(uint64_t addr, uint32_t val) "addr=0x%"PRIx64"val=0x%04x" @@ -XXX,XX +XXX,XX @@ i82596_set_multicast(uint16_t count) "Added %d multicast entries" i82596_channel_attention(void *s) "%p: Received CHANNEL ATTENTION" # imx_fec.c -imx_phy_read(uint32_t val, int phy, int reg) "0x%04"PRIx32" <= phy[%d].reg[%d]" imx_phy_read_num(int phy, int configured) "read request from unconfigured phy %d (configured %d)" -imx_phy_write(uint32_t val, int phy, int reg) "0x%04"PRIx32" => phy[%d].reg[%d]" imx_phy_write_num(int phy, int configured) "write request to unconfigured phy %d (configured %d)" -imx_phy_update_link(const char *s) "%s" -imx_phy_reset(void) "" imx_fec_read_bd(uint64_t addr, int flags, int len, int data) "tx_bd 0x%"PRIx64" flags 0x%04x len %d data 0x%08x" imx_enet_read_bd(uint64_t addr, int flags, int len, int data, int options, int status) "tx_bd 0x%"PRIx64" flags 0x%04x len %d data 0x%08x option 0x%04x status 0x%04x" imx_eth_tx_bd_busy(void) "tx_bd ran out of descriptors to transmit" -- 2.34.1 From: Bernhard Beschow <shentey@gmail.com> Turns 0x70 into 0xe0 (== 0x70 << 1) which adds the missing MII_ANLPAR_TX and fixes the MSB of selector field to be zero, as specified in the datasheet. Fixes: 2a424990170b "LAN9118 emulation" Signed-off-by: Bernhard Beschow <shentey@gmail.com> Tested-by: Guenter Roeck <linux@roeck-us.net> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241102125724.532843-4-shentey@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/lan9118_phy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/net/lan9118_phy.c b/hw/net/lan9118_phy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/lan9118_phy.c +++ b/hw/net/lan9118_phy.c @@ -XXX,XX +XXX,XX @@ uint16_t lan9118_phy_read(Lan9118PhyState *s, int reg) val = s->advertise; break; case 5: /* Auto-neg Link Partner Ability */ - val = 0x0f71; + val = 0x0fe1; break; case 6: /* Auto-neg Expansion */ val = 1; -- 2.34.1 From: Bernhard Beschow <shentey@gmail.com> Prefer named constants over magic values for better readability. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Bernhard Beschow <shentey@gmail.com> Tested-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20241102125724.532843-5-shentey@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/net/mii.h | 6 +++++ hw/net/lan9118_phy.c | 63 ++++++++++++++++++++++++++++---------------- 2 files changed, 46 insertions(+), 23 deletions(-) diff --git a/include/hw/net/mii.h b/include/hw/net/mii.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/net/mii.h +++ b/include/hw/net/mii.h @@ -XXX,XX +XXX,XX @@ #define MII_BMSR_JABBER (1 << 1) /* Jabber detected */ #define MII_BMSR_EXTCAP (1 << 0) /* Ext-reg capability */ +#define MII_ANAR_RFAULT (1 << 13) /* Say we can detect faults */ #define MII_ANAR_PAUSE_ASYM (1 << 11) /* Try for asymmetric pause */ #define MII_ANAR_PAUSE (1 << 10) /* Try for pause */ #define MII_ANAR_TXFD (1 << 8) @@ -XXX,XX +XXX,XX @@ #define MII_ANAR_10FD (1 << 6) #define MII_ANAR_10 (1 << 5) #define MII_ANAR_CSMACD (1 << 0) +#define MII_ANAR_SELECT (0x001f) /* Selector bits */ #define MII_ANLPAR_ACK (1 << 14) #define MII_ANLPAR_PAUSEASY (1 << 11) /* can pause asymmetrically */ @@ -XXX,XX +XXX,XX @@ #define RTL8201CP_PHYID1 0x0000 #define RTL8201CP_PHYID2 0x8201 +/* SMSC LAN9118 */ +#define SMSCLAN9118_PHYID1 0x0007 +#define SMSCLAN9118_PHYID2 0xc0d1 + /* RealTek 8211E */ #define RTL8211E_PHYID1 0x001c #define RTL8211E_PHYID2 0xc915 diff --git a/hw/net/lan9118_phy.c b/hw/net/lan9118_phy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/lan9118_phy.c +++ b/hw/net/lan9118_phy.c @@ -XXX,XX +XXX,XX @@ #include "qemu/osdep.h" #include "hw/net/lan9118_phy.h" +#include "hw/net/mii.h" #include "hw/irq.h" #include "hw/resettable.h" #include "migration/vmstate.h" @@ -XXX,XX +XXX,XX @@ uint16_t lan9118_phy_read(Lan9118PhyState *s, int reg) uint16_t val; switch (reg) { - case 0: /* Basic Control */ + case MII_BMCR: val = s->control; break; - case 1: /* Basic Status */ + case MII_BMSR: val = s->status; break; - case 2: /* ID1 */ - val = 0x0007; + case MII_PHYID1: + val = SMSCLAN9118_PHYID1; break; - case 3: /* ID2 */ - val = 0xc0d1; + case MII_PHYID2: + val = SMSCLAN9118_PHYID2; break; - case 4: /* Auto-neg advertisement */ + case MII_ANAR: val = s->advertise; break; - case 5: /* Auto-neg Link Partner Ability */ - val = 0x0fe1; + case MII_ANLPAR: + val = MII_ANLPAR_PAUSEASY | MII_ANLPAR_PAUSE | MII_ANLPAR_T4 | + MII_ANLPAR_TXFD | MII_ANLPAR_TX | MII_ANLPAR_10FD | + MII_ANLPAR_10 | MII_ANLPAR_CSMACD; break; - case 6: /* Auto-neg Expansion */ - val = 1; + case MII_ANER: + val = MII_ANER_NWAY; break; case 29: /* Interrupt source. */ val = s->ints; @@ -XXX,XX +XXX,XX @@ void lan9118_phy_write(Lan9118PhyState *s, int reg, uint16_t val) trace_lan9118_phy_write(val, reg); switch (reg) { - case 0: /* Basic Control */ - if (val & 0x8000) { + case MII_BMCR: + if (val & MII_BMCR_RESET) { lan9118_phy_reset(s); } else { - s->control = val & 0x7980; + s->control = val & (MII_BMCR_LOOPBACK | MII_BMCR_SPEED100 | + MII_BMCR_AUTOEN | MII_BMCR_PDOWN | MII_BMCR_FD | + MII_BMCR_CTST); /* Complete autonegotiation immediately. */ - if (val & 0x1000) { - s->status |= 0x0020; + if (val & MII_BMCR_AUTOEN) { + s->status |= MII_BMSR_AN_COMP; } } break; - case 4: /* Auto-neg advertisement */ - s->advertise = (val & 0x2d7f) | 0x80; + case MII_ANAR: + s->advertise = (val & (MII_ANAR_RFAULT | MII_ANAR_PAUSE_ASYM | + MII_ANAR_PAUSE | MII_ANAR_10FD | MII_ANAR_10 | + MII_ANAR_SELECT)) + | MII_ANAR_TX; break; case 30: /* Interrupt mask */ s->int_mask = val & 0xff; @@ -XXX,XX +XXX,XX @@ void lan9118_phy_update_link(Lan9118PhyState *s, bool link_down) /* Autonegotiation status mirrors link status. */ if (link_down) { trace_lan9118_phy_update_link("down"); - s->status &= ~0x0024; + s->status &= ~(MII_BMSR_AN_COMP | MII_BMSR_LINK_ST); s->ints |= PHY_INT_DOWN; } else { trace_lan9118_phy_update_link("up"); - s->status |= 0x0024; + s->status |= MII_BMSR_AN_COMP | MII_BMSR_LINK_ST; s->ints |= PHY_INT_ENERGYON; s->ints |= PHY_INT_AUTONEG_COMPLETE; } @@ -XXX,XX +XXX,XX @@ void lan9118_phy_reset(Lan9118PhyState *s) { trace_lan9118_phy_reset(); - s->control = 0x3000; - s->status = 0x7809; - s->advertise = 0x01e1; + s->control = MII_BMCR_AUTOEN | MII_BMCR_SPEED100; + s->status = MII_BMSR_100TX_FD + | MII_BMSR_100TX_HD + | MII_BMSR_10T_FD + | MII_BMSR_10T_HD + | MII_BMSR_AUTONEG + | MII_BMSR_EXTCAP; + s->advertise = MII_ANAR_TXFD + | MII_ANAR_TX + | MII_ANAR_10FD + | MII_ANAR_10 + | MII_ANAR_CSMACD; s->int_mask = 0; s->ints = 0; lan9118_phy_update_link(s, s->link_down); -- 2.34.1 From: Bernhard Beschow <shentey@gmail.com> The real device advertises this mode and the device model already advertises 100 mbps half duplex and 10 mbps full+half duplex. So advertise this mode to make the model more realistic. Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Bernhard Beschow <shentey@gmail.com> Tested-by: Guenter Roeck <linux@roeck-us.net> Message-id: 20241102125724.532843-6-shentey@gmail.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/net/lan9118_phy.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/hw/net/lan9118_phy.c b/hw/net/lan9118_phy.c index XXXXXXX..XXXXXXX 100644 --- a/hw/net/lan9118_phy.c +++ b/hw/net/lan9118_phy.c @@ -XXX,XX +XXX,XX @@ void lan9118_phy_write(Lan9118PhyState *s, int reg, uint16_t val) break; case MII_ANAR: s->advertise = (val & (MII_ANAR_RFAULT | MII_ANAR_PAUSE_ASYM | - MII_ANAR_PAUSE | MII_ANAR_10FD | MII_ANAR_10 | - MII_ANAR_SELECT)) + MII_ANAR_PAUSE | MII_ANAR_TXFD | MII_ANAR_10FD | + MII_ANAR_10 | MII_ANAR_SELECT)) | MII_ANAR_TX; break; case 30: /* Interrupt mask */ -- 2.34.1 For IEEE fused multiply-add, the (0 * inf) + NaN case should raise Invalid for the multiplication of 0 by infinity. Currently we handle this in the per-architecture ifdef ladder in pickNaNMulAdd(). However, since this isn't really architecture specific we can hoist it up to the generic code. For the cases where the infzero test in pickNaNMulAdd was returning 2, we can delete the check entirely and allow the code to fall into the normal pick-a-NaN handling, because this will return 2 anyway (input 'c' being the only NaN in this case). For the cases where infzero was returning 3 to indicate "return the default NaN", we must retain that "return 3". For Arm, this looks like it might be a behaviour change because we used to set float_flag_invalid | float_flag_invalid_imz only if C is a quiet NaN. However, it is not, because Arm target code never looks at float_flag_invalid_imz, and for the (0 * inf) + SNaN case we already raised float_flag_invalid via the "abc_mask & float_cmask_snan" check in pick_nan_muladd. For any target architecture using the "default implementation" at the bottom of the ifdef, this is a behaviour change but will be fixing a bug (where we failed to raise the Invalid exception for (0 * inf + QNaN). The architectures using the default case are: * hppa * i386 * sh4 * tricore The x86, Tricore and SH4 CPU architecture manuals are clear that this should have raised Invalid; HPPA is a bit vaguer but still seems clear enough. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-2-peter.maydell@linaro.org --- fpu/softfloat-parts.c.inc | 13 +++++++------ fpu/softfloat-specialize.c.inc | 29 +---------------------------- 2 files changed, 8 insertions(+), 34 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, int ab_mask, int abc_mask) { int which; + bool infzero = (ab_mask == float_cmask_infzero); if (unlikely(abc_mask & float_cmask_snan)) { float_raise(float_flag_invalid | float_flag_invalid_snan, s); } - which = pickNaNMulAdd(a->cls, b->cls, c->cls, - ab_mask == float_cmask_infzero, s); + if (infzero) { + /* This is (0 * inf) + NaN or (inf * 0) + NaN */ + float_raise(float_flag_invalid | float_flag_invalid_imz, s); + } + + which = pickNaNMulAdd(a->cls, b->cls, c->cls, infzero, s); if (s->default_nan_mode || which == 3) { - /* - * Note that this check is after pickNaNMulAdd so that function - * has an opportunity to set the Invalid flag for infzero. - */ parts_default_nan(a, s); return a; } diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * the default NaN */ if (infzero && is_qnan(c_cls)) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); return 3; } @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * case sets InvalidOp and returns the default NaN */ if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); return 3; } /* Prefer sNaN over qNaN, in the a, b, c order. */ @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * For MIPS systems that conform to IEEE754-2008, the (inf,zero,nan) * case sets InvalidOp and returns the input value 'c' */ - if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); - return 2; - } /* Prefer sNaN over qNaN, in the c, a, b order. */ if (is_snan(c_cls)) { return 2; @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) * case sets InvalidOp and returns the input value 'c' */ - if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); - return 2; - } + /* Prefer sNaN over qNaN, in the c, a, b order. */ if (is_snan(c_cls)) { return 2; @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * to return an input NaN if we have one (ie c) rather than generating * a default NaN */ - if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); - return 2; - } /* If fRA is a NaN return it; otherwise if fRB is a NaN return it; * otherwise return fRC. Note that muladd on PPC is (fRA * fRC) + frB @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, return 1; } #elif defined(TARGET_RISCV) - /* For RISC-V, InvalidOp is set when multiplicands are Inf and zero */ - if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); - } return 3; /* default NaN */ #elif defined(TARGET_S390X) if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); return 3; } @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, return 2; } #elif defined(TARGET_SPARC) - /* For (inf,0,nan) return c. */ - if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); - return 2; - } /* Prefer SNaN over QNaN, order C, B, A. */ if (is_snan(c_cls)) { return 2; @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * For Xtensa, the (inf,zero,nan) case sets InvalidOp and returns * an input NaN if we have one (ie c). */ - if (infzero) { - float_raise(float_flag_invalid | float_flag_invalid_imz, status); - return 2; - } if (status->use_first_nan) { if (is_nan(a_cls)) { return 0; -- 2.34.1 If the target sets default_nan_mode then we're always going to return the default NaN, and pickNaNMulAdd() no longer has any side effects. For consistency with pickNaN(), check for default_nan_mode before calling pickNaNMulAdd(). When we convert pickNaNMulAdd() to allow runtime selection of the NaN propagation rule, this means we won't have to make the targets which use default_nan_mode also set a propagation rule. Since RiscV always uses default_nan_mode, this allows us to remove its ifdef case from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-3-peter.maydell@linaro.org --- fpu/softfloat-parts.c.inc | 8 ++++++-- fpu/softfloat-specialize.c.inc | 9 +++++++-- 2 files changed, 13 insertions(+), 4 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, float_raise(float_flag_invalid | float_flag_invalid_imz, s); } - which = pickNaNMulAdd(a->cls, b->cls, c->cls, infzero, s); + if (s->default_nan_mode) { + which = 3; + } else { + which = pickNaNMulAdd(a->cls, b->cls, c->cls, infzero, s); + } - if (s->default_nan_mode || which == 3) { + if (which == 3) { parts_default_nan(a, s); return a; } diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaN(FloatClass a_cls, FloatClass b_cls, static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, bool infzero, float_status *status) { + /* + * We guarantee not to require the target to tell us how to + * pick a NaN if we're always returning the default NaN. + * But if we're not in default-NaN mode then the target must + * specify. + */ + assert(!status->default_nan_mode); #if defined(TARGET_ARM) /* For ARM, the (inf,zero,qnan) case sets InvalidOp and returns * the default NaN @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } else { return 1; } -#elif defined(TARGET_RISCV) - return 3; /* default NaN */ #elif defined(TARGET_S390X) if (infzero) { return 3; -- 2.34.1 IEEE 758 does not define a fixed rule for what NaN to return in the case of a fused multiply-add of inf * 0 + NaN. Different architectures thus do different things: * some return the default NaN * some return the input NaN * Arm returns the default NaN if the input NaN is quiet, and the input NaN if it is signalling We want to make this logic be runtime selected rather than hardcoded into the binary, because: * this will let us have multiple targets in one QEMU binary * the Arm FEAT_AFP architectural feature includes letting the guest select a NaN propagation rule at runtime In this commit we add an enum for the propagation rule, the field in float_status, and the corresponding getters and setters. We change pickNaNMulAdd to honour this, but because all targets still leave this field at its default 0 value, the fallback logic will pick the rule type with the old ifdef ladder. Note that four architectures both use the muladd softfloat functions and did not have a branch of the ifdef ladder to specify their behaviour (and so were ending up with the "default" case, probably wrongly): i386, HPPA, SH4 and Tricore. SH4 and Tricore both set default_nan_mode, and so will never get into pickNaNMulAdd(). For HPPA and i386 we retain the same behaviour as the old default-case, which is to not ever return the default NaN. This might not be correct but it is not a behaviour change. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-4-peter.maydell@linaro.org --- include/fpu/softfloat-helpers.h | 11 ++++ include/fpu/softfloat-types.h | 23 +++++++++ fpu/softfloat-specialize.c.inc | 91 ++++++++++++++++++++++----------- 3 files changed, 95 insertions(+), 30 deletions(-) diff --git a/include/fpu/softfloat-helpers.h b/include/fpu/softfloat-helpers.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-helpers.h +++ b/include/fpu/softfloat-helpers.h @@ -XXX,XX +XXX,XX @@ static inline void set_float_2nan_prop_rule(Float2NaNPropRule rule, status->float_2nan_prop_rule = rule; } +static inline void set_float_infzeronan_rule(FloatInfZeroNaNRule rule, + float_status *status) +{ + status->float_infzeronan_rule = rule; +} + static inline void set_flush_to_zero(bool val, float_status *status) { status->flush_to_zero = val; @@ -XXX,XX +XXX,XX @@ static inline Float2NaNPropRule get_float_2nan_prop_rule(float_status *status) return status->float_2nan_prop_rule; } +static inline FloatInfZeroNaNRule get_float_infzeronan_rule(float_status *status) +{ + return status->float_infzeronan_rule; +} + static inline bool get_flush_to_zero(float_status *status) { return status->flush_to_zero; diff --git a/include/fpu/softfloat-types.h b/include/fpu/softfloat-types.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-types.h +++ b/include/fpu/softfloat-types.h @@ -XXX,XX +XXX,XX @@ typedef enum __attribute__((__packed__)) { float_2nan_prop_x87, } Float2NaNPropRule; +/* + * Rule for result of fused multiply-add 0 * Inf + NaN. + * This must be a NaN, but implementations differ on whether this + * is the input NaN or the default NaN. + * + * You don't need to set this if default_nan_mode is enabled. + * When not in default-NaN mode, it is an error for the target + * not to set the rule in float_status if it uses muladd, and we + * will assert if we need to handle an input NaN and no rule was + * selected. + */ +typedef enum __attribute__((__packed__)) { + /* No propagation rule specified */ + float_infzeronan_none = 0, + /* Result is never the default NaN (so always the input NaN) */ + float_infzeronan_dnan_never, + /* Result is always the default NaN */ + float_infzeronan_dnan_always, + /* Result is the default NaN if the input NaN is quiet */ + float_infzeronan_dnan_if_qnan, +} FloatInfZeroNaNRule; + /* * Floating Point Status. Individual architectures may maintain * several versions of float_status for different functions. The @@ -XXX,XX +XXX,XX @@ typedef struct float_status { FloatRoundMode float_rounding_mode; FloatX80RoundPrec floatx80_rounding_precision; Float2NaNPropRule float_2nan_prop_rule; + FloatInfZeroNaNRule float_infzeronan_rule; bool tininess_before_rounding; /* should denormalised results go to zero and set the inexact flag? */ bool flush_to_zero; diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaN(FloatClass a_cls, FloatClass b_cls, static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, bool infzero, float_status *status) { + FloatInfZeroNaNRule rule = status->float_infzeronan_rule; + /* * We guarantee not to require the target to tell us how to * pick a NaN if we're always returning the default NaN. @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * specify. */ assert(!status->default_nan_mode); + + if (rule == float_infzeronan_none) { + /* + * Temporarily fall back to ifdef ladder + */ #if defined(TARGET_ARM) - /* For ARM, the (inf,zero,qnan) case sets InvalidOp and returns - * the default NaN - */ - if (infzero && is_qnan(c_cls)) { - return 3; + /* + * For ARM, the (inf,zero,qnan) case returns the default NaN, + * but (inf,zero,snan) returns the input NaN. + */ + rule = float_infzeronan_dnan_if_qnan; +#elif defined(TARGET_MIPS) + if (snan_bit_is_one(status)) { + /* + * For MIPS systems that conform to IEEE754-1985, the (inf,zero,nan) + * case sets InvalidOp and returns the default NaN + */ + rule = float_infzeronan_dnan_always; + } else { + /* + * For MIPS systems that conform to IEEE754-2008, the (inf,zero,nan) + * case sets InvalidOp and returns the input value 'c' + */ + rule = float_infzeronan_dnan_never; + } +#elif defined(TARGET_PPC) || defined(TARGET_SPARC) || \ + defined(TARGET_XTENSA) || defined(TARGET_HPPA) || \ + defined(TARGET_I386) || defined(TARGET_LOONGARCH) + /* + * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) + * case sets InvalidOp and returns the input value 'c' + */ + /* + * For PPC, the (inf,zero,qnan) case sets InvalidOp, but we prefer + * to return an input NaN if we have one (ie c) rather than generating + * a default NaN + */ + rule = float_infzeronan_dnan_never; +#elif defined(TARGET_S390X) + rule = float_infzeronan_dnan_always; +#endif } + if (infzero) { + /* + * Inf * 0 + NaN -- some implementations return the default NaN here, + * and some return the input NaN. + */ + switch (rule) { + case float_infzeronan_dnan_never: + return 2; + case float_infzeronan_dnan_always: + return 3; + case float_infzeronan_dnan_if_qnan: + return is_qnan(c_cls) ? 3 : 2; + default: + g_assert_not_reached(); + } + } + +#if defined(TARGET_ARM) + /* This looks different from the ARM ARM pseudocode, because the ARM ARM * puts the operands to a fused mac operation (a*b)+c in the order c,a,b. */ @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } #elif defined(TARGET_MIPS) if (snan_bit_is_one(status)) { - /* - * For MIPS systems that conform to IEEE754-1985, the (inf,zero,nan) - * case sets InvalidOp and returns the default NaN - */ - if (infzero) { - return 3; - } /* Prefer sNaN over qNaN, in the a, b, c order. */ if (is_snan(a_cls)) { return 0; @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, return 2; } } else { - /* - * For MIPS systems that conform to IEEE754-2008, the (inf,zero,nan) - * case sets InvalidOp and returns the input value 'c' - */ /* Prefer sNaN over qNaN, in the c, a, b order. */ if (is_snan(c_cls)) { return 2; @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } } #elif defined(TARGET_LOONGARCH64) - /* - * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) - * case sets InvalidOp and returns the input value 'c' - */ - /* Prefer sNaN over qNaN, in the c, a, b order. */ if (is_snan(c_cls)) { return 2; @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, return 1; } #elif defined(TARGET_PPC) - /* For PPC, the (inf,zero,qnan) case sets InvalidOp, but we prefer - * to return an input NaN if we have one (ie c) rather than generating - * a default NaN - */ - /* If fRA is a NaN return it; otherwise if fRB is a NaN return it; * otherwise return fRC. Note that muladd on PPC is (fRA * fRC) + frB */ @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, return 1; } #elif defined(TARGET_S390X) - if (infzero) { - return 3; - } - if (is_snan(a_cls)) { return 0; } else if (is_snan(b_cls)) { -- 2.34.1 Explicitly set a rule in the softfloat tests for the inf-zero-nan muladd special case. In meson.build we put -DTARGET_ARM in fpcflags, and so we should select here the Arm rule of float_infzeronan_dnan_if_qnan. Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241202131347.498124-5-peter.maydell@linaro.org --- tests/fp/fp-bench.c | 5 +++++ tests/fp/fp-test.c | 5 +++++ 2 files changed, 10 insertions(+) diff --git a/tests/fp/fp-bench.c b/tests/fp/fp-bench.c index XXXXXXX..XXXXXXX 100644 --- a/tests/fp/fp-bench.c +++ b/tests/fp/fp-bench.c @@ -XXX,XX +XXX,XX @@ static void run_bench(void) { bench_func_t f; + /* + * These implementation-defined choices for various things IEEE + * doesn't specify match those used by the Arm architecture. + */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &soft_status); + set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, &soft_status); f = bench_funcs[operation][precision]; g_assert(f); diff --git a/tests/fp/fp-test.c b/tests/fp/fp-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/fp/fp-test.c +++ b/tests/fp/fp-test.c @@ -XXX,XX +XXX,XX @@ void run_test(void) { unsigned int i; + /* + * These implementation-defined choices for various things IEEE + * doesn't specify match those used by the Arm architecture. + */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &qsf); + set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, &qsf); genCases_setLevel(test_level); verCases_maxErrorCount = n_max_errors; -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the Arm target, so we can remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-6-peter.maydell@linaro.org --- target/arm/cpu.c | 3 +++ fpu/softfloat-specialize.c.inc | 8 +------- 2 files changed, 4 insertions(+), 7 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ void arm_register_el_change_hook(ARMCPU *cpu, ARMELChangeHookFn *hook, * * tininess-before-rounding * * 2-input NaN propagation prefers SNaN over QNaN, and then * operand A over operand B (see FPProcessNaNs() pseudocode) + * * 0 * Inf + NaN returns the default NaN if the input NaN is quiet, + * and the input NaN if it is signalling */ static void arm_set_default_fp_behaviours(float_status *s) { set_float_detect_tininess(float_tininess_before_rounding, s); set_float_2nan_prop_rule(float_2nan_prop_s_ab, s); + set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, s); } static void cp_reg_reset(gpointer key, gpointer value, gpointer opaque) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, /* * Temporarily fall back to ifdef ladder */ -#if defined(TARGET_ARM) - /* - * For ARM, the (inf,zero,qnan) case returns the default NaN, - * but (inf,zero,snan) returns the input NaN. - */ - rule = float_infzeronan_dnan_if_qnan; -#elif defined(TARGET_MIPS) +#if defined(TARGET_MIPS) if (snan_bit_is_one(status)) { /* * For MIPS systems that conform to IEEE754-1985, the (inf,zero,nan) -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for s390, so we can remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-7-peter.maydell@linaro.org --- target/s390x/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/cpu.c +++ b/target/s390x/cpu.c @@ -XXX,XX +XXX,XX @@ static void s390_cpu_reset_hold(Object *obj, ResetType type) set_float_detect_tininess(float_tininess_before_rounding, &env->fpu_status); set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->fpu_status); + set_float_infzeronan_rule(float_infzeronan_dnan_always, + &env->fpu_status); /* fall through */ case RESET_TYPE_S390_CPU_NORMAL: env->psw.mask &= ~PSW_MASK_RI; diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * a default NaN */ rule = float_infzeronan_dnan_never; -#elif defined(TARGET_S390X) - rule = float_infzeronan_dnan_always; #endif } -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the PPC target, so we can remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-8-peter.maydell@linaro.org --- target/ppc/cpu_init.c | 7 +++++++ fpu/softfloat-specialize.c.inc | 7 +------ 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/cpu_init.c +++ b/target/ppc/cpu_init.c @@ -XXX,XX +XXX,XX @@ static void ppc_cpu_reset_hold(Object *obj, ResetType type) */ set_float_2nan_prop_rule(float_2nan_prop_ab, &env->fp_status); set_float_2nan_prop_rule(float_2nan_prop_ab, &env->vec_status); + /* + * For PPC, the (inf,zero,qnan) case sets InvalidOp, but we prefer + * to return an input NaN if we have one (ie c) rather than generating + * a default NaN + */ + set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); + set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->vec_status); for (i = 0; i < ARRAY_SIZE(env->spr_cb); i++) { ppc_spr_t *spr = &env->spr_cb[i]; diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, */ rule = float_infzeronan_dnan_never; } -#elif defined(TARGET_PPC) || defined(TARGET_SPARC) || \ +#elif defined(TARGET_SPARC) || \ defined(TARGET_XTENSA) || defined(TARGET_HPPA) || \ defined(TARGET_I386) || defined(TARGET_LOONGARCH) /* * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) * case sets InvalidOp and returns the input value 'c' */ - /* - * For PPC, the (inf,zero,qnan) case sets InvalidOp, but we prefer - * to return an input NaN if we have one (ie c) rather than generating - * a default NaN - */ rule = float_infzeronan_dnan_never; #endif } -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the MIPS target, so we can remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-9-peter.maydell@linaro.org --- target/mips/fpu_helper.h | 9 +++++++++ target/mips/msa.c | 4 ++++ fpu/softfloat-specialize.c.inc | 16 +--------------- 3 files changed, 14 insertions(+), 15 deletions(-) diff --git a/target/mips/fpu_helper.h b/target/mips/fpu_helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/mips/fpu_helper.h +++ b/target/mips/fpu_helper.h @@ -XXX,XX +XXX,XX @@ static inline void restore_flush_mode(CPUMIPSState *env) static inline void restore_snan_bit_mode(CPUMIPSState *env) { bool nan2008 = env->active_fpu.fcr31 & (1 << FCR31_NAN2008); + FloatInfZeroNaNRule izn_rule; /* * With nan2008, SNaNs are silenced in the usual way. @@ -XXX,XX +XXX,XX @@ static inline void restore_snan_bit_mode(CPUMIPSState *env) */ set_snan_bit_is_one(!nan2008, &env->active_fpu.fp_status); set_default_nan_mode(!nan2008, &env->active_fpu.fp_status); + /* + * For MIPS systems that conform to IEEE754-1985, the (inf,zero,nan) + * case sets InvalidOp and returns the default NaN. + * For MIPS systems that conform to IEEE754-2008, the (inf,zero,nan) + * case sets InvalidOp and returns the input value 'c'. + */ + izn_rule = nan2008 ? float_infzeronan_dnan_never : float_infzeronan_dnan_always; + set_float_infzeronan_rule(izn_rule, &env->active_fpu.fp_status); } static inline void restore_fp_status(CPUMIPSState *env) diff --git a/target/mips/msa.c b/target/mips/msa.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/msa.c +++ b/target/mips/msa.c @@ -XXX,XX +XXX,XX @@ void msa_reset(CPUMIPSState *env) /* set proper signanling bit meaning ("1" means "quiet") */ set_snan_bit_is_one(0, &env->active_tc.msa_fp_status); + + /* Inf * 0 + NaN returns the input NaN */ + set_float_infzeronan_rule(float_infzeronan_dnan_never, + &env->active_tc.msa_fp_status); } diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, /* * Temporarily fall back to ifdef ladder */ -#if defined(TARGET_MIPS) - if (snan_bit_is_one(status)) { - /* - * For MIPS systems that conform to IEEE754-1985, the (inf,zero,nan) - * case sets InvalidOp and returns the default NaN - */ - rule = float_infzeronan_dnan_always; - } else { - /* - * For MIPS systems that conform to IEEE754-2008, the (inf,zero,nan) - * case sets InvalidOp and returns the input value 'c' - */ - rule = float_infzeronan_dnan_never; - } -#elif defined(TARGET_SPARC) || \ +#if defined(TARGET_SPARC) || \ defined(TARGET_XTENSA) || defined(TARGET_HPPA) || \ defined(TARGET_I386) || defined(TARGET_LOONGARCH) /* -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the SPARC target, so we can remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-10-peter.maydell@linaro.org --- target/sparc/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 3 +-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/cpu.c +++ b/target/sparc/cpu.c @@ -XXX,XX +XXX,XX @@ static void sparc_cpu_realizefn(DeviceState *dev, Error **errp) * the CPU state struct so it won't get zeroed on reset. */ set_float_2nan_prop_rule(float_2nan_prop_s_ba, &env->fp_status); + /* For inf * 0 + NaN, return the input NaN */ + set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); cpu_exec_realizefn(cs, &local_err); if (local_err != NULL) { diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, /* * Temporarily fall back to ifdef ladder */ -#if defined(TARGET_SPARC) || \ - defined(TARGET_XTENSA) || defined(TARGET_HPPA) || \ +#if defined(TARGET_XTENSA) || defined(TARGET_HPPA) || \ defined(TARGET_I386) || defined(TARGET_LOONGARCH) /* * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the xtensa target, so we can remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-11-peter.maydell@linaro.org --- target/xtensa/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/target/xtensa/cpu.c b/target/xtensa/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/cpu.c +++ b/target/xtensa/cpu.c @@ -XXX,XX +XXX,XX @@ static void xtensa_cpu_reset_hold(Object *obj, ResetType type) reset_mmu(env); cs->halted = env->runstall; #endif + /* For inf * 0 + NaN, return the input NaN */ + set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); set_no_signaling_nans(!dfpu, &env->fp_status); xtensa_use_first_nan(env, !dfpu); } diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, /* * Temporarily fall back to ifdef ladder */ -#if defined(TARGET_XTENSA) || defined(TARGET_HPPA) || \ +#if defined(TARGET_HPPA) || \ defined(TARGET_I386) || defined(TARGET_LOONGARCH) /* * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the x86 target. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-12-peter.maydell@linaro.org --- target/i386/tcg/fpu_helper.c | 7 +++++++ fpu/softfloat-specialize.c.inc | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/target/i386/tcg/fpu_helper.c b/target/i386/tcg/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/tcg/fpu_helper.c +++ b/target/i386/tcg/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void cpu_init_fp_statuses(CPUX86State *env) */ set_float_2nan_prop_rule(float_2nan_prop_x87, &env->mmx_status); set_float_2nan_prop_rule(float_2nan_prop_x87, &env->sse_status); + /* + * Only SSE has multiply-add instructions. In the SDM Section 14.5.2 + * "Fused-Multiply-ADD (FMA) Numeric Behavior" the NaN handling is + * specified -- for 0 * inf + NaN the input NaN is selected, and if + * there are multiple input NaNs they are selected in the order a, b, c. + */ + set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->sse_status); } static inline uint8_t save_exception_flags(CPUX86State *env) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, * Temporarily fall back to ifdef ladder */ #if defined(TARGET_HPPA) || \ - defined(TARGET_I386) || defined(TARGET_LOONGARCH) + defined(TARGET_LOONGARCH) /* * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) * case sets InvalidOp and returns the input value 'c' -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the loongarch target. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-13-peter.maydell@linaro.org --- target/loongarch/tcg/fpu_helper.c | 5 +++++ fpu/softfloat-specialize.c.inc | 7 +------ 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/target/loongarch/tcg/fpu_helper.c b/target/loongarch/tcg/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/tcg/fpu_helper.c +++ b/target/loongarch/tcg/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void restore_fp_status(CPULoongArchState *env) &env->fp_status); set_flush_to_zero(0, &env->fp_status); set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->fp_status); + /* + * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) + * case sets InvalidOp and returns the input value 'c' + */ + set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); } int ieee_ex_to_loongarch(int xcpt) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, /* * Temporarily fall back to ifdef ladder */ -#if defined(TARGET_HPPA) || \ - defined(TARGET_LOONGARCH) - /* - * For LoongArch systems that conform to IEEE754-2008, the (inf,zero,nan) - * case sets InvalidOp and returns the input value 'c' - */ +#if defined(TARGET_HPPA) rule = float_infzeronan_dnan_never; #endif } -- 2.34.1 Set the FloatInfZeroNaNRule explicitly for the HPPA target, so we can remove the ifdef from pickNaNMulAdd(). As this is the last target to be converted to explicitly setting the rule, we can remove the fallback code in pickNaNMulAdd() entirely. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-14-peter.maydell@linaro.org --- target/hppa/fpu_helper.c | 2 ++ fpu/softfloat-specialize.c.inc | 13 +------------ 2 files changed, 3 insertions(+), 12 deletions(-) diff --git a/target/hppa/fpu_helper.c b/target/hppa/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/hppa/fpu_helper.c +++ b/target/hppa/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(loaded_fr0)(CPUHPPAState *env) * HPPA does note implement a CPU reset method at all... */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->fp_status); + /* For inf * 0 + NaN, return the input NaN */ + set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); } void cpu_hppa_loaded_fr0(CPUHPPAState *env) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaN(FloatClass a_cls, FloatClass b_cls, static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, bool infzero, float_status *status) { - FloatInfZeroNaNRule rule = status->float_infzeronan_rule; - /* * We guarantee not to require the target to tell us how to * pick a NaN if we're always returning the default NaN. @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, */ assert(!status->default_nan_mode); - if (rule == float_infzeronan_none) { - /* - * Temporarily fall back to ifdef ladder - */ -#if defined(TARGET_HPPA) - rule = float_infzeronan_dnan_never; -#endif - } - if (infzero) { /* * Inf * 0 + NaN -- some implementations return the default NaN here, * and some return the input NaN. */ - switch (rule) { + switch (status->float_infzeronan_rule) { case float_infzeronan_dnan_never: return 2; case float_infzeronan_dnan_always: -- 2.34.1 The new implementation of pickNaNMulAdd() will find it convenient to know whether at least one of the three arguments to the muladd was a signaling NaN. We already calculate that in the caller, so pass it in as a new bool have_snan. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-15-peter.maydell@linaro.org --- fpu/softfloat-parts.c.inc | 5 +++-- fpu/softfloat-specialize.c.inc | 2 +- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, { int which; bool infzero = (ab_mask == float_cmask_infzero); + bool have_snan = (abc_mask & float_cmask_snan); - if (unlikely(abc_mask & float_cmask_snan)) { + if (unlikely(have_snan)) { float_raise(float_flag_invalid | float_flag_invalid_snan, s); } @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, if (s->default_nan_mode) { which = 3; } else { - which = pickNaNMulAdd(a->cls, b->cls, c->cls, infzero, s); + which = pickNaNMulAdd(a->cls, b->cls, c->cls, infzero, have_snan, s); } if (which == 3) { diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaN(FloatClass a_cls, FloatClass b_cls, | Return values : 0 : a; 1 : b; 2 : c; 3 : default-NaN *----------------------------------------------------------------------------*/ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, - bool infzero, float_status *status) + bool infzero, bool have_snan, float_status *status) { /* * We guarantee not to require the target to tell us how to -- 2.34.1 IEEE 758 does not define a fixed rule for which NaN to pick as the result if both operands of a 3-operand fused multiply-add operation are NaNs. As a result different architectures have ended up with different rules for propagating NaNs. QEMU currently hardcodes the NaN propagation logic into the binary because pickNaNMulAdd() has an ifdef ladder for different targets. We want to make the propagation rule instead be selectable at runtime, because: * this will let us have multiple targets in one QEMU binary * the Arm FEAT_AFP architectural feature includes letting the guest select a NaN propagation rule at runtime In this commit we add an enum for the propagation rule, the field in float_status, and the corresponding getters and setters. We change pickNaNMulAdd to honour this, but because all targets still leave this field at its default 0 value, the fallback logic will pick the rule type with the old ifdef ladder. It's valid not to set a propagation rule if default_nan_mode is enabled, because in that case there's no need to pick a NaN; all the callers of pickNaNMulAdd() catch this case and skip calling it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-16-peter.maydell@linaro.org --- include/fpu/softfloat-helpers.h | 11 +++ include/fpu/softfloat-types.h | 55 +++++++++++ fpu/softfloat-specialize.c.inc | 167 ++++++++------------------------ 3 files changed, 107 insertions(+), 126 deletions(-) diff --git a/include/fpu/softfloat-helpers.h b/include/fpu/softfloat-helpers.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-helpers.h +++ b/include/fpu/softfloat-helpers.h @@ -XXX,XX +XXX,XX @@ static inline void set_float_2nan_prop_rule(Float2NaNPropRule rule, status->float_2nan_prop_rule = rule; } +static inline void set_float_3nan_prop_rule(Float3NaNPropRule rule, + float_status *status) +{ + status->float_3nan_prop_rule = rule; +} + static inline void set_float_infzeronan_rule(FloatInfZeroNaNRule rule, float_status *status) { @@ -XXX,XX +XXX,XX @@ static inline Float2NaNPropRule get_float_2nan_prop_rule(float_status *status) return status->float_2nan_prop_rule; } +static inline Float3NaNPropRule get_float_3nan_prop_rule(float_status *status) +{ + return status->float_3nan_prop_rule; +} + static inline FloatInfZeroNaNRule get_float_infzeronan_rule(float_status *status) { return status->float_infzeronan_rule; diff --git a/include/fpu/softfloat-types.h b/include/fpu/softfloat-types.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-types.h +++ b/include/fpu/softfloat-types.h @@ -XXX,XX +XXX,XX @@ this code that are retained. #ifndef SOFTFLOAT_TYPES_H #define SOFTFLOAT_TYPES_H +#include "hw/registerfields.h" + /* * Software IEC/IEEE floating-point types. */ @@ -XXX,XX +XXX,XX @@ typedef enum __attribute__((__packed__)) { float_2nan_prop_x87, } Float2NaNPropRule; +/* + * 3-input NaN propagation rule, for fused multiply-add. Individual + * architectures have different rules for which input NaN is + * propagated to the output when there is more than one NaN on the + * input. + * + * If default_nan_mode is enabled then it is valid not to set a NaN + * propagation rule, because the softfloat code guarantees not to try + * to pick a NaN to propagate in default NaN mode. When not in + * default-NaN mode, it is an error for the target not to set the rule + * in float_status if it uses a muladd, and we will assert if we need + * to handle an input NaN and no rule was selected. + * + * The naming scheme for Float3NaNPropRule values is: + * float_3nan_prop_s_abc: + * = "Prefer SNaN over QNaN, then operand A over B over C" + * float_3nan_prop_abc: + * = "Prefer A over B over C regardless of SNaN vs QNAN" + * + * For QEMU, the multiply-add operation is A * B + C. + */ + +/* + * We set the Float3NaNPropRule enum values up so we can select the + * right value in pickNaNMulAdd in a data driven way. + */ +FIELD(3NAN, 1ST, 0, 2) /* which operand is most preferred ? */ +FIELD(3NAN, 2ND, 2, 2) /* which operand is next most preferred ? */ +FIELD(3NAN, 3RD, 4, 2) /* which operand is least preferred ? */ +FIELD(3NAN, SNAN, 6, 1) /* do we prefer SNaN over QNaN ? */ + +#define PROPRULE(X, Y, Z) \ + ((X << R_3NAN_1ST_SHIFT) | (Y << R_3NAN_2ND_SHIFT) | (Z << R_3NAN_3RD_SHIFT)) + +typedef enum __attribute__((__packed__)) { + float_3nan_prop_none = 0, /* No propagation rule specified */ + float_3nan_prop_abc = PROPRULE(0, 1, 2), + float_3nan_prop_acb = PROPRULE(0, 2, 1), + float_3nan_prop_bac = PROPRULE(1, 0, 2), + float_3nan_prop_bca = PROPRULE(1, 2, 0), + float_3nan_prop_cab = PROPRULE(2, 0, 1), + float_3nan_prop_cba = PROPRULE(2, 1, 0), + float_3nan_prop_s_abc = float_3nan_prop_abc | R_3NAN_SNAN_MASK, + float_3nan_prop_s_acb = float_3nan_prop_acb | R_3NAN_SNAN_MASK, + float_3nan_prop_s_bac = float_3nan_prop_bac | R_3NAN_SNAN_MASK, + float_3nan_prop_s_bca = float_3nan_prop_bca | R_3NAN_SNAN_MASK, + float_3nan_prop_s_cab = float_3nan_prop_cab | R_3NAN_SNAN_MASK, + float_3nan_prop_s_cba = float_3nan_prop_cba | R_3NAN_SNAN_MASK, +} Float3NaNPropRule; + +#undef PROPRULE + /* * Rule for result of fused multiply-add 0 * Inf + NaN. * This must be a NaN, but implementations differ on whether this @@ -XXX,XX +XXX,XX @@ typedef struct float_status { FloatRoundMode float_rounding_mode; FloatX80RoundPrec floatx80_rounding_precision; Float2NaNPropRule float_2nan_prop_rule; + Float3NaNPropRule float_3nan_prop_rule; FloatInfZeroNaNRule float_infzeronan_rule; bool tininess_before_rounding; /* should denormalised results go to zero and set the inexact flag? */ diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaN(FloatClass a_cls, FloatClass b_cls, static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, bool infzero, bool have_snan, float_status *status) { + FloatClass cls[3] = { a_cls, b_cls, c_cls }; + Float3NaNPropRule rule = status->float_3nan_prop_rule; + int which; + /* * We guarantee not to require the target to tell us how to * pick a NaN if we're always returning the default NaN. @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } } + if (rule == float_3nan_prop_none) { #if defined(TARGET_ARM) - - /* This looks different from the ARM ARM pseudocode, because the ARM ARM - * puts the operands to a fused mac operation (a*b)+c in the order c,a,b. - */ - if (is_snan(c_cls)) { - return 2; - } else if (is_snan(a_cls)) { - return 0; - } else if (is_snan(b_cls)) { - return 1; - } else if (is_qnan(c_cls)) { - return 2; - } else if (is_qnan(a_cls)) { - return 0; - } else { - return 1; - } + /* + * This looks different from the ARM ARM pseudocode, because the ARM ARM + * puts the operands to a fused mac operation (a*b)+c in the order c,a,b + */ + rule = float_3nan_prop_s_cab; #elif defined(TARGET_MIPS) - if (snan_bit_is_one(status)) { - /* Prefer sNaN over qNaN, in the a, b, c order. */ - if (is_snan(a_cls)) { - return 0; - } else if (is_snan(b_cls)) { - return 1; - } else if (is_snan(c_cls)) { - return 2; - } else if (is_qnan(a_cls)) { - return 0; - } else if (is_qnan(b_cls)) { - return 1; + if (snan_bit_is_one(status)) { + rule = float_3nan_prop_s_abc; } else { - return 2; + rule = float_3nan_prop_s_cab; } - } else { - /* Prefer sNaN over qNaN, in the c, a, b order. */ - if (is_snan(c_cls)) { - return 2; - } else if (is_snan(a_cls)) { - return 0; - } else if (is_snan(b_cls)) { - return 1; - } else if (is_qnan(c_cls)) { - return 2; - } else if (is_qnan(a_cls)) { - return 0; - } else { - return 1; - } - } #elif defined(TARGET_LOONGARCH64) - /* Prefer sNaN over qNaN, in the c, a, b order. */ - if (is_snan(c_cls)) { - return 2; - } else if (is_snan(a_cls)) { - return 0; - } else if (is_snan(b_cls)) { - return 1; - } else if (is_qnan(c_cls)) { - return 2; - } else if (is_qnan(a_cls)) { - return 0; - } else { - return 1; - } + rule = float_3nan_prop_s_cab; #elif defined(TARGET_PPC) - /* If fRA is a NaN return it; otherwise if fRB is a NaN return it; - * otherwise return fRC. Note that muladd on PPC is (fRA * fRC) + frB - */ - if (is_nan(a_cls)) { - return 0; - } else if (is_nan(c_cls)) { - return 2; - } else { - return 1; - } + /* + * If fRA is a NaN return it; otherwise if fRB is a NaN return it; + * otherwise return fRC. Note that muladd on PPC is (fRA * fRC) + frB + */ + rule = float_3nan_prop_acb; #elif defined(TARGET_S390X) - if (is_snan(a_cls)) { - return 0; - } else if (is_snan(b_cls)) { - return 1; - } else if (is_snan(c_cls)) { - return 2; - } else if (is_qnan(a_cls)) { - return 0; - } else if (is_qnan(b_cls)) { - return 1; - } else { - return 2; - } + rule = float_3nan_prop_s_abc; #elif defined(TARGET_SPARC) - /* Prefer SNaN over QNaN, order C, B, A. */ - if (is_snan(c_cls)) { - return 2; - } else if (is_snan(b_cls)) { - return 1; - } else if (is_snan(a_cls)) { - return 0; - } else if (is_qnan(c_cls)) { - return 2; - } else if (is_qnan(b_cls)) { - return 1; - } else { - return 0; - } + rule = float_3nan_prop_s_cba; #elif defined(TARGET_XTENSA) - /* - * For Xtensa, the (inf,zero,nan) case sets InvalidOp and returns - * an input NaN if we have one (ie c). - */ - if (status->use_first_nan) { - if (is_nan(a_cls)) { - return 0; - } else if (is_nan(b_cls)) { - return 1; + if (status->use_first_nan) { + rule = float_3nan_prop_abc; } else { - return 2; + rule = float_3nan_prop_cba; } - } else { - if (is_nan(c_cls)) { - return 2; - } else if (is_nan(b_cls)) { - return 1; - } else { - return 0; - } - } #else - /* A default implementation: prefer a to b to c. - * This is unlikely to actually match any real implementation. - */ - if (is_nan(a_cls)) { - return 0; - } else if (is_nan(b_cls)) { - return 1; - } else { - return 2; - } + rule = float_3nan_prop_abc; #endif + } + + assert(rule != float_3nan_prop_none); + if (have_snan && (rule & R_3NAN_SNAN_MASK)) { + /* We have at least one SNaN input and should prefer it */ + do { + which = rule & R_3NAN_1ST_MASK; + rule >>= R_3NAN_1ST_LENGTH; + } while (!is_snan(cls[which])); + } else { + do { + which = rule & R_3NAN_1ST_MASK; + rule >>= R_3NAN_1ST_LENGTH; + } while (!is_nan(cls[which])); + } + return which; } /*---------------------------------------------------------------------------- -- 2.34.1 Explicitly set a rule in the softfloat tests for propagating NaNs in the muladd case. In meson.build we put -DTARGET_ARM in fpcflags, and so we should select here the Arm rule of float_3nan_prop_s_cab. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-17-peter.maydell@linaro.org --- tests/fp/fp-bench.c | 1 + tests/fp/fp-test.c | 1 + 2 files changed, 2 insertions(+) diff --git a/tests/fp/fp-bench.c b/tests/fp/fp-bench.c index XXXXXXX..XXXXXXX 100644 --- a/tests/fp/fp-bench.c +++ b/tests/fp/fp-bench.c @@ -XXX,XX +XXX,XX @@ static void run_bench(void) * doesn't specify match those used by the Arm architecture. */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &soft_status); + set_float_3nan_prop_rule(float_3nan_prop_s_cab, &soft_status); set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, &soft_status); f = bench_funcs[operation][precision]; diff --git a/tests/fp/fp-test.c b/tests/fp/fp-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/fp/fp-test.c +++ b/tests/fp/fp-test.c @@ -XXX,XX +XXX,XX @@ void run_test(void) * doesn't specify match those used by the Arm architecture. */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &qsf); + set_float_3nan_prop_rule(float_3nan_prop_s_cab, &qsf); set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, &qsf); genCases_setLevel(test_level); -- 2.34.1 Set the Float3NaNPropRule explicitly for Arm, and remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-18-peter.maydell@linaro.org --- target/arm/cpu.c | 5 +++++ fpu/softfloat-specialize.c.inc | 8 +------- 2 files changed, 6 insertions(+), 7 deletions(-) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ void arm_register_el_change_hook(ARMCPU *cpu, ARMELChangeHookFn *hook, * * tininess-before-rounding * * 2-input NaN propagation prefers SNaN over QNaN, and then * operand A over operand B (see FPProcessNaNs() pseudocode) + * * 3-input NaN propagation prefers SNaN over QNaN, and then + * operand C over A over B (see FPProcessNaNs3() pseudocode, + * but note that for QEMU muladd is a * b + c, whereas for + * the pseudocode function the arguments are in the order c, a, b. * * 0 * Inf + NaN returns the default NaN if the input NaN is quiet, * and the input NaN if it is signalling */ @@ -XXX,XX +XXX,XX @@ static void arm_set_default_fp_behaviours(float_status *s) { set_float_detect_tininess(float_tininess_before_rounding, s); set_float_2nan_prop_rule(float_2nan_prop_s_ab, s); + set_float_3nan_prop_rule(float_3nan_prop_s_cab, s); set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, s); } diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } if (rule == float_3nan_prop_none) { -#if defined(TARGET_ARM) - /* - * This looks different from the ARM ARM pseudocode, because the ARM ARM - * puts the operands to a fused mac operation (a*b)+c in the order c,a,b - */ - rule = float_3nan_prop_s_cab; -#elif defined(TARGET_MIPS) +#if defined(TARGET_MIPS) if (snan_bit_is_one(status)) { rule = float_3nan_prop_s_abc; } else { -- 2.34.1 Set the Float3NaNPropRule explicitly for loongarch, and remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-19-peter.maydell@linaro.org --- target/loongarch/tcg/fpu_helper.c | 1 + fpu/softfloat-specialize.c.inc | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/target/loongarch/tcg/fpu_helper.c b/target/loongarch/tcg/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/tcg/fpu_helper.c +++ b/target/loongarch/tcg/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void restore_fp_status(CPULoongArchState *env) * case sets InvalidOp and returns the input value 'c' */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); + set_float_3nan_prop_rule(float_3nan_prop_s_cab, &env->fp_status); } int ieee_ex_to_loongarch(int xcpt) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } else { rule = float_3nan_prop_s_cab; } -#elif defined(TARGET_LOONGARCH64) - rule = float_3nan_prop_s_cab; #elif defined(TARGET_PPC) /* * If fRA is a NaN return it; otherwise if fRB is a NaN return it; -- 2.34.1 Set the Float3NaNPropRule explicitly for PPC, and remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-20-peter.maydell@linaro.org --- target/ppc/cpu_init.c | 8 ++++++++ fpu/softfloat-specialize.c.inc | 6 ------ 2 files changed, 8 insertions(+), 6 deletions(-) diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/cpu_init.c +++ b/target/ppc/cpu_init.c @@ -XXX,XX +XXX,XX @@ static void ppc_cpu_reset_hold(Object *obj, ResetType type) */ set_float_2nan_prop_rule(float_2nan_prop_ab, &env->fp_status); set_float_2nan_prop_rule(float_2nan_prop_ab, &env->vec_status); + /* + * NaN propagation for fused multiply-add: + * if fRA is a NaN return it; otherwise if fRB is a NaN return it; + * otherwise return fRC. Note that muladd on PPC is (fRA * fRC) + frB + * whereas QEMU labels the operands as (a * b) + c. + */ + set_float_3nan_prop_rule(float_3nan_prop_acb, &env->fp_status); + set_float_3nan_prop_rule(float_3nan_prop_acb, &env->vec_status); /* * For PPC, the (inf,zero,qnan) case sets InvalidOp, but we prefer * to return an input NaN if we have one (ie c) rather than generating diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } else { rule = float_3nan_prop_s_cab; } -#elif defined(TARGET_PPC) - /* - * If fRA is a NaN return it; otherwise if fRB is a NaN return it; - * otherwise return fRC. Note that muladd on PPC is (fRA * fRC) + frB - */ - rule = float_3nan_prop_acb; #elif defined(TARGET_S390X) rule = float_3nan_prop_s_abc; #elif defined(TARGET_SPARC) -- 2.34.1 Set the Float3NaNPropRule explicitly for s390x, and remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-21-peter.maydell@linaro.org --- target/s390x/cpu.c | 1 + fpu/softfloat-specialize.c.inc | 2 -- 2 files changed, 1 insertion(+), 2 deletions(-) diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/cpu.c +++ b/target/s390x/cpu.c @@ -XXX,XX +XXX,XX @@ static void s390_cpu_reset_hold(Object *obj, ResetType type) set_float_detect_tininess(float_tininess_before_rounding, &env->fpu_status); set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->fpu_status); + set_float_3nan_prop_rule(float_3nan_prop_s_abc, &env->fpu_status); set_float_infzeronan_rule(float_infzeronan_dnan_always, &env->fpu_status); /* fall through */ diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } else { rule = float_3nan_prop_s_cab; } -#elif defined(TARGET_S390X) - rule = float_3nan_prop_s_abc; #elif defined(TARGET_SPARC) rule = float_3nan_prop_s_cba; #elif defined(TARGET_XTENSA) -- 2.34.1 Set the Float3NaNPropRule explicitly for SPARC, and remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-22-peter.maydell@linaro.org --- target/sparc/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 2 -- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/cpu.c +++ b/target/sparc/cpu.c @@ -XXX,XX +XXX,XX @@ static void sparc_cpu_realizefn(DeviceState *dev, Error **errp) * the CPU state struct so it won't get zeroed on reset. */ set_float_2nan_prop_rule(float_2nan_prop_s_ba, &env->fp_status); + /* For fused-multiply add, prefer SNaN over QNaN, then C->B->A */ + set_float_3nan_prop_rule(float_3nan_prop_s_cba, &env->fp_status); /* For inf * 0 + NaN, return the input NaN */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } else { rule = float_3nan_prop_s_cab; } -#elif defined(TARGET_SPARC) - rule = float_3nan_prop_s_cba; #elif defined(TARGET_XTENSA) if (status->use_first_nan) { rule = float_3nan_prop_abc; -- 2.34.1 Set the Float3NaNPropRule explicitly for Arm, and remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-23-peter.maydell@linaro.org --- target/mips/fpu_helper.h | 4 ++++ target/mips/msa.c | 3 +++ fpu/softfloat-specialize.c.inc | 8 +------- 3 files changed, 8 insertions(+), 7 deletions(-) diff --git a/target/mips/fpu_helper.h b/target/mips/fpu_helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/mips/fpu_helper.h +++ b/target/mips/fpu_helper.h @@ -XXX,XX +XXX,XX @@ static inline void restore_snan_bit_mode(CPUMIPSState *env) { bool nan2008 = env->active_fpu.fcr31 & (1 << FCR31_NAN2008); FloatInfZeroNaNRule izn_rule; + Float3NaNPropRule nan3_rule; /* * With nan2008, SNaNs are silenced in the usual way. @@ -XXX,XX +XXX,XX @@ static inline void restore_snan_bit_mode(CPUMIPSState *env) */ izn_rule = nan2008 ? float_infzeronan_dnan_never : float_infzeronan_dnan_always; set_float_infzeronan_rule(izn_rule, &env->active_fpu.fp_status); + nan3_rule = nan2008 ? float_3nan_prop_s_cab : float_3nan_prop_s_abc; + set_float_3nan_prop_rule(nan3_rule, &env->active_fpu.fp_status); + } static inline void restore_fp_status(CPUMIPSState *env) diff --git a/target/mips/msa.c b/target/mips/msa.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/msa.c +++ b/target/mips/msa.c @@ -XXX,XX +XXX,XX @@ void msa_reset(CPUMIPSState *env) set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->active_tc.msa_fp_status); + set_float_3nan_prop_rule(float_3nan_prop_s_cab, + &env->active_tc.msa_fp_status); + /* clear float_status exception flags */ set_float_exception_flags(0, &env->active_tc.msa_fp_status); diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } if (rule == float_3nan_prop_none) { -#if defined(TARGET_MIPS) - if (snan_bit_is_one(status)) { - rule = float_3nan_prop_s_abc; - } else { - rule = float_3nan_prop_s_cab; - } -#elif defined(TARGET_XTENSA) +#if defined(TARGET_XTENSA) if (status->use_first_nan) { rule = float_3nan_prop_abc; } else { -- 2.34.1 Set the Float3NaNPropRule explicitly for xtensa, and remove the ifdef from pickNaNMulAdd(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-24-peter.maydell@linaro.org --- target/xtensa/fpu_helper.c | 2 ++ fpu/softfloat-specialize.c.inc | 8 -------- 2 files changed, 2 insertions(+), 8 deletions(-) diff --git a/target/xtensa/fpu_helper.c b/target/xtensa/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/fpu_helper.c +++ b/target/xtensa/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void xtensa_use_first_nan(CPUXtensaState *env, bool use_first) set_use_first_nan(use_first, &env->fp_status); set_float_2nan_prop_rule(use_first ? float_2nan_prop_ab : float_2nan_prop_ba, &env->fp_status); + set_float_3nan_prop_rule(use_first ? float_3nan_prop_abc : float_3nan_prop_cba, + &env->fp_status); } void HELPER(wur_fpu2k_fcr)(CPUXtensaState *env, uint32_t v) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } if (rule == float_3nan_prop_none) { -#if defined(TARGET_XTENSA) - if (status->use_first_nan) { - rule = float_3nan_prop_abc; - } else { - rule = float_3nan_prop_cba; - } -#else rule = float_3nan_prop_abc; -#endif } assert(rule != float_3nan_prop_none); -- 2.34.1 Set the Float3NaNPropRule explicitly for i386. We had no i386-specific behaviour in the old ifdef ladder, so we were using the default "prefer a then b then c" fallback; this is actually the correct per-the-spec handling for i386. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-25-peter.maydell@linaro.org --- target/i386/tcg/fpu_helper.c | 1 + 1 file changed, 1 insertion(+) diff --git a/target/i386/tcg/fpu_helper.c b/target/i386/tcg/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/tcg/fpu_helper.c +++ b/target/i386/tcg/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void cpu_init_fp_statuses(CPUX86State *env) * there are multiple input NaNs they are selected in the order a, b, c. */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->sse_status); + set_float_3nan_prop_rule(float_3nan_prop_abc, &env->sse_status); } static inline uint8_t save_exception_flags(CPUX86State *env) -- 2.34.1 Set the Float3NaNPropRule explicitly for HPPA, and remove the ifdef from pickNaNMulAdd(). HPPA is the only target that was using the default branch of the ifdef ladder (other targets either do not use muladd or set default_nan_mode), so we can remove the ifdef fallback entirely now (allowing the "rule not set" case to fall into the default of the switch statement and assert). We add a TODO note that the HPPA rule is probably wrong; this is not a behavioural change for this refactoring. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-26-peter.maydell@linaro.org --- target/hppa/fpu_helper.c | 8 ++++++++ fpu/softfloat-specialize.c.inc | 4 ---- 2 files changed, 8 insertions(+), 4 deletions(-) diff --git a/target/hppa/fpu_helper.c b/target/hppa/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/hppa/fpu_helper.c +++ b/target/hppa/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(loaded_fr0)(CPUHPPAState *env) * HPPA does note implement a CPU reset method at all... */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &env->fp_status); + /* + * TODO: The HPPA architecture reference only documents its NaN + * propagation rule for 2-operand operations. Testing on real hardware + * might be necessary to confirm whether this order for muladd is correct. + * Not preferring the SNaN is almost certainly incorrect as it diverges + * from the documented rules for 2-operand operations. + */ + set_float_3nan_prop_rule(float_3nan_prop_abc, &env->fp_status); /* For inf * 0 + NaN, return the input NaN */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); } diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, } } - if (rule == float_3nan_prop_none) { - rule = float_3nan_prop_abc; - } - assert(rule != float_3nan_prop_none); if (have_snan && (rule & R_3NAN_SNAN_MASK)) { /* We have at least one SNaN input and should prefer it */ -- 2.34.1 The use_first_nan field in float_status was an xtensa-specific way to select at runtime from two different NaN propagation rules. Now that xtensa is using the target-agnostic NaN propagation rule selection that we've just added, we can remove use_first_nan, because there is no longer any code that reads it. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-27-peter.maydell@linaro.org --- include/fpu/softfloat-helpers.h | 5 ----- include/fpu/softfloat-types.h | 1 - target/xtensa/fpu_helper.c | 1 - 3 files changed, 7 deletions(-) diff --git a/include/fpu/softfloat-helpers.h b/include/fpu/softfloat-helpers.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-helpers.h +++ b/include/fpu/softfloat-helpers.h @@ -XXX,XX +XXX,XX @@ static inline void set_snan_bit_is_one(bool val, float_status *status) status->snan_bit_is_one = val; } -static inline void set_use_first_nan(bool val, float_status *status) -{ - status->use_first_nan = val; -} - static inline void set_no_signaling_nans(bool val, float_status *status) { status->no_signaling_nans = val; diff --git a/include/fpu/softfloat-types.h b/include/fpu/softfloat-types.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-types.h +++ b/include/fpu/softfloat-types.h @@ -XXX,XX +XXX,XX @@ typedef struct float_status { * softfloat-specialize.inc.c) */ bool snan_bit_is_one; - bool use_first_nan; bool no_signaling_nans; /* should overflowed results subtract re_bias to its exponent? */ bool rebias_overflow; diff --git a/target/xtensa/fpu_helper.c b/target/xtensa/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/fpu_helper.c +++ b/target/xtensa/fpu_helper.c @@ -XXX,XX +XXX,XX @@ static const struct { void xtensa_use_first_nan(CPUXtensaState *env, bool use_first) { - set_use_first_nan(use_first, &env->fp_status); set_float_2nan_prop_rule(use_first ? float_2nan_prop_ab : float_2nan_prop_ba, &env->fp_status); set_float_3nan_prop_rule(use_first ? float_3nan_prop_abc : float_3nan_prop_cba, -- 2.34.1 Currently m68k_cpu_reset_hold() calls floatx80_default_nan(NULL) to get the NaN bit pattern to reset the FPU registers. This works because it happens that our implementation of floatx80_default_nan() doesn't actually look at the float_status pointer except for TARGET_MIPS. However, this isn't guaranteed, and to be able to remove the ifdef in floatx80_default_nan() we're going to need a real float_status here. Rearrange m68k_cpu_reset_hold() so that we initialize env->fp_status earlier, and thus can pass it to floatx80_default_nan(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-28-peter.maydell@linaro.org --- target/m68k/cpu.c | 12 +++++++----- 1 file changed, 7 insertions(+), 5 deletions(-) diff --git a/target/m68k/cpu.c b/target/m68k/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/cpu.c +++ b/target/m68k/cpu.c @@ -XXX,XX +XXX,XX @@ static void m68k_cpu_reset_hold(Object *obj, ResetType type) CPUState *cs = CPU(obj); M68kCPUClass *mcc = M68K_CPU_GET_CLASS(obj); CPUM68KState *env = cpu_env(cs); - floatx80 nan = floatx80_default_nan(NULL); + floatx80 nan; int i; if (mcc->parent_phases.hold) { @@ -XXX,XX +XXX,XX @@ static void m68k_cpu_reset_hold(Object *obj, ResetType type) #else cpu_m68k_set_sr(env, SR_S | SR_I); #endif - for (i = 0; i < 8; i++) { - env->fregs[i].d = nan; - } - cpu_m68k_set_fpcr(env, 0); /* * M68000 FAMILY PROGRAMMER'S REFERENCE MANUAL * 3.4 FLOATING-POINT INSTRUCTION DETAILS @@ -XXX,XX +XXX,XX @@ static void m68k_cpu_reset_hold(Object *obj, ResetType type) * preceding paragraph for nonsignaling NaNs. */ set_float_2nan_prop_rule(float_2nan_prop_ab, &env->fp_status); + + nan = floatx80_default_nan(&env->fp_status); + for (i = 0; i < 8; i++) { + env->fregs[i].d = nan; + } + cpu_m68k_set_fpcr(env, 0); env->fpsr = 0; /* TODO: We should set PC from the interrupt vector. */ -- 2.34.1 We create our 128-bit default NaN by calling parts64_default_nan() and then adjusting the result. We can do the same trick for creating the floatx80 default NaN, which lets us drop a target ifdef. floatx80 is used only by: i386 m68k arm nwfpe old floating-point emulation emulation support (which is essentially dead, especially the parts involving floatx80) PPC (only in the xsrqpxp instruction, which just rounds an input value by converting to floatx80 and back, so will never generate the default NaN) The floatx80 default NaN as currently implemented is: m68k: sign = 0, exp = 1...1, int = 1, frac = 1....1 i386: sign = 1, exp = 1...1, int = 1, frac = 10...0 These are the same as the parts64_default_nan for these architectures. This is technically a possible behaviour change for arm linux-user nwfpe emulation emulation, because the default NaN will now have the sign bit clear. But we were already generating a different floatx80 default NaN from the real kernel emulation we are supposedly following, which appears to use an all-bits-1 value: https://elixir.bootlin.com/linux/v6.12/source/arch/arm/nwfpe/softfloat-specialize#L267 This won't affect the only "real" use of the nwfpe emulation, which is ancient binaries that used it as part of the old floating point calling convention; that only uses loads and stores of 32 and 64 bit floats, not any of the floatx80 behaviour the original hardware had. We also get the nwfpe float64 default NaN value wrong: https://elixir.bootlin.com/linux/v6.12/source/arch/arm/nwfpe/softfloat-specialize#L166 so if we ever cared about this obscure corner the right fix would be to correct that so nwfpe used its own default-NaN setting rather than the Arm VFP one. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-29-peter.maydell@linaro.org --- fpu/softfloat-specialize.c.inc | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts128_silence_nan(FloatParts128 *p, float_status *status) floatx80 floatx80_default_nan(float_status *status) { floatx80 r; + /* + * Extrapolate from the choices made by parts64_default_nan to fill + * in the floatx80 format. We assume that floatx80's explicit + * integer bit is always set (this is true for i386 and m68k, + * which are the only real users of this format). + */ + FloatParts64 p64; + parts64_default_nan(&p64, status); - /* None of the targets that have snan_bit_is_one use floatx80. */ - assert(!snan_bit_is_one(status)); -#if defined(TARGET_M68K) - r.low = UINT64_C(0xFFFFFFFFFFFFFFFF); - r.high = 0x7FFF; -#else - /* X86 */ - r.low = UINT64_C(0xC000000000000000); - r.high = 0xFFFF; -#endif + r.high = 0x7FFF | (p64.sign << 15); + r.low = (1ULL << DECOMPOSED_BINARY_POINT) | p64.frac; return r; } -- 2.34.1 In target/loongarch's helper_fclass_s() and helper_fclass_d() we pass a zero-initialized float_status struct to float32_is_quiet_nan() and float64_is_quiet_nan(), with the cryptic comment "for snan_bit_is_one". This pattern appears to have been copied from target/riscv, where it is used because the functions there do not have ready access to the CPU state struct. The comment presumably refers to the fact that the main reason the is_quiet_nan() functions want the float_state is because they want to know about the snan_bit_is_one config. In the loongarch helpers, though, we have the CPU state struct to hand. Use the usual env->fp_status here. This avoids our needing to track that we need to update the initializer of the local float_status structs when the core softfloat code adds new options for targets to configure their behaviour. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-30-peter.maydell@linaro.org --- target/loongarch/tcg/fpu_helper.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/target/loongarch/tcg/fpu_helper.c b/target/loongarch/tcg/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/tcg/fpu_helper.c +++ b/target/loongarch/tcg/fpu_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t helper_fclass_s(CPULoongArchState *env, uint64_t fj) } else if (float32_is_zero_or_denormal(f)) { return sign ? 1 << 4 : 1 << 8; } else if (float32_is_any_nan(f)) { - float_status s = { }; /* for snan_bit_is_one */ - return float32_is_quiet_nan(f, &s) ? 1 << 1 : 1 << 0; + return float32_is_quiet_nan(f, &env->fp_status) ? 1 << 1 : 1 << 0; } else { return sign ? 1 << 3 : 1 << 7; } @@ -XXX,XX +XXX,XX @@ uint64_t helper_fclass_d(CPULoongArchState *env, uint64_t fj) } else if (float64_is_zero_or_denormal(f)) { return sign ? 1 << 4 : 1 << 8; } else if (float64_is_any_nan(f)) { - float_status s = { }; /* for snan_bit_is_one */ - return float64_is_quiet_nan(f, &s) ? 1 << 1 : 1 << 0; + return float64_is_quiet_nan(f, &env->fp_status) ? 1 << 1 : 1 << 0; } else { return sign ? 1 << 3 : 1 << 7; } -- 2.34.1 In the frem helper, we have a local float_status because we want to execute the floatx80_div() with a custom rounding mode. Instead of zero-initializing the local float_status and then having to set it up with the m68k standard behaviour (including the NaN propagation rule and copying the rounding precision from env->fp_status), initialize it as a complete copy of env->fp_status. This will avoid our having to add new code in this function for every new config knob we add to fp_status. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-31-peter.maydell@linaro.org --- target/m68k/fpu_helper.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) diff --git a/target/m68k/fpu_helper.c b/target/m68k/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/fpu_helper.c +++ b/target/m68k/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(frem)(CPUM68KState *env, FPReg *res, FPReg *val0, FPReg *val1) fp_rem = floatx80_rem(val1->d, val0->d, &env->fp_status); if (!floatx80_is_any_nan(fp_rem)) { - float_status fp_status = { }; + /* Use local temporary fp_status to set different rounding mode */ + float_status fp_status = env->fp_status; uint32_t quotient; int sign; /* Calculate quotient directly using round to nearest mode */ - set_float_2nan_prop_rule(float_2nan_prop_ab, &fp_status); set_float_rounding_mode(float_round_nearest_even, &fp_status); - set_floatx80_rounding_precision( - get_floatx80_rounding_precision(&env->fp_status), &fp_status); fp_quot.d = floatx80_div(val1->d, val0->d, &fp_status); sign = extractFloatx80Sign(fp_quot.d); -- 2.34.1 In cf_fpu_gdb_get_reg() and cf_fpu_gdb_set_reg() we do the conversion from float64 to floatx80 using a scratch float_status, because we don't want the conversion to affect the CPU's floating point exception status. Currently we use a zero-initialized float_status. This will get steadily more awkward as we add config knobs to float_status that the target must initialize. Avoid having to add any of that configuration here by instead initializing our local float_status from the env->fp_status. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-32-peter.maydell@linaro.org --- target/m68k/helper.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/target/m68k/helper.c b/target/m68k/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/helper.c +++ b/target/m68k/helper.c @@ -XXX,XX +XXX,XX @@ static int cf_fpu_gdb_get_reg(CPUState *cs, GByteArray *mem_buf, int n) CPUM68KState *env = &cpu->env; if (n < 8) { - float_status s = {}; + /* Use scratch float_status so any exceptions don't change CPU state */ + float_status s = env->fp_status; return gdb_get_reg64(mem_buf, floatx80_to_float64(env->fregs[n].d, &s)); } switch (n) { @@ -XXX,XX +XXX,XX @@ static int cf_fpu_gdb_set_reg(CPUState *cs, uint8_t *mem_buf, int n) CPUM68KState *env = &cpu->env; if (n < 8) { - float_status s = {}; + /* Use scratch float_status so any exceptions don't change CPU state */ + float_status s = env->fp_status; env->fregs[n].d = float64_to_floatx80(ldq_be_p(mem_buf), &s); return 8; } -- 2.34.1 In the helper functions flcmps and flcmpd we use a scratch float_status so that we don't change the CPU state if the comparison raises any floating point exception flags. Instead of zero-initializing this scratch float_status, initialize it as a copy of env->fp_status. This avoids the need to explicitly initialize settings like the NaN propagation rule or others we might add to softfloat in future. To do this we need to pass the CPU env pointer in to the helper. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-33-peter.maydell@linaro.org --- target/sparc/helper.h | 4 ++-- target/sparc/fop_helper.c | 8 ++++---- target/sparc/translate.c | 4 ++-- 3 files changed, 8 insertions(+), 8 deletions(-) diff --git a/target/sparc/helper.h b/target/sparc/helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/helper.h +++ b/target/sparc/helper.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_3(fcmpd, TCG_CALL_NO_WG, i32, env, f64, f64) DEF_HELPER_FLAGS_3(fcmped, TCG_CALL_NO_WG, i32, env, f64, f64) DEF_HELPER_FLAGS_3(fcmpq, TCG_CALL_NO_WG, i32, env, i128, i128) DEF_HELPER_FLAGS_3(fcmpeq, TCG_CALL_NO_WG, i32, env, i128, i128) -DEF_HELPER_FLAGS_2(flcmps, TCG_CALL_NO_RWG_SE, i32, f32, f32) -DEF_HELPER_FLAGS_2(flcmpd, TCG_CALL_NO_RWG_SE, i32, f64, f64) +DEF_HELPER_FLAGS_3(flcmps, TCG_CALL_NO_RWG_SE, i32, env, f32, f32) +DEF_HELPER_FLAGS_3(flcmpd, TCG_CALL_NO_RWG_SE, i32, env, f64, f64) DEF_HELPER_2(raise_exception, noreturn, env, int) DEF_HELPER_FLAGS_3(faddd, TCG_CALL_NO_WG, f64, env, f64, f64) diff --git a/target/sparc/fop_helper.c b/target/sparc/fop_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/fop_helper.c +++ b/target/sparc/fop_helper.c @@ -XXX,XX +XXX,XX @@ uint32_t helper_fcmpeq(CPUSPARCState *env, Int128 src1, Int128 src2) return finish_fcmp(env, r, GETPC()); } -uint32_t helper_flcmps(float32 src1, float32 src2) +uint32_t helper_flcmps(CPUSPARCState *env, float32 src1, float32 src2) { /* * FLCMP never raises an exception nor modifies any FSR fields. * Perform the comparison with a dummy fp environment. */ - float_status discard = { }; + float_status discard = env->fp_status; FloatRelation r; set_float_2nan_prop_rule(float_2nan_prop_s_ba, &discard); @@ -XXX,XX +XXX,XX @@ uint32_t helper_flcmps(float32 src1, float32 src2) g_assert_not_reached(); } -uint32_t helper_flcmpd(float64 src1, float64 src2) +uint32_t helper_flcmpd(CPUSPARCState *env, float64 src1, float64 src2) { - float_status discard = { }; + float_status discard = env->fp_status; FloatRelation r; set_float_2nan_prop_rule(float_2nan_prop_s_ba, &discard); diff --git a/target/sparc/translate.c b/target/sparc/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/translate.c +++ b/target/sparc/translate.c @@ -XXX,XX +XXX,XX @@ static bool trans_FLCMPs(DisasContext *dc, arg_FLCMPs *a) src1 = gen_load_fpr_F(dc, a->rs1); src2 = gen_load_fpr_F(dc, a->rs2); - gen_helper_flcmps(cpu_fcc[a->cc], src1, src2); + gen_helper_flcmps(cpu_fcc[a->cc], tcg_env, src1, src2); return advance_pc(dc); } @@ -XXX,XX +XXX,XX @@ static bool trans_FLCMPd(DisasContext *dc, arg_FLCMPd *a) src1 = gen_load_fpr_D(dc, a->rs1); src2 = gen_load_fpr_D(dc, a->rs2); - gen_helper_flcmpd(cpu_fcc[a->cc], src1, src2); + gen_helper_flcmpd(cpu_fcc[a->cc], tcg_env, src1, src2); return advance_pc(dc); } -- 2.34.1 In the helper_compute_fprf functions, we pass a dummy float_status in to the is_signaling_nan() function. This is unnecessary, because we have convenient access to the CPU env pointer here and that is already set up with the correct values for the snan_bit_is_one and no_signaling_nans config settings. is_signaling_nan() doesn't ever update the fp_status with any exception flags, so there is no reason not to use env->fp_status here. Use env->fp_status instead of the dummy fp_status. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-34-peter.maydell@linaro.org --- target/ppc/fpu_helper.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/target/ppc/fpu_helper.c b/target/ppc/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/fpu_helper.c +++ b/target/ppc/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void helper_compute_fprf_##tp(CPUPPCState *env, tp arg) \ } else if (tp##_is_infinity(arg)) { \ fprf = neg ? 0x09 << FPSCR_FPRF : 0x05 << FPSCR_FPRF; \ } else { \ - float_status dummy = { }; /* snan_bit_is_one = 0 */ \ - if (tp##_is_signaling_nan(arg, &dummy)) { \ + if (tp##_is_signaling_nan(arg, &env->fp_status)) { \ fprf = 0x00 << FPSCR_FPRF; \ } else { \ fprf = 0x11 << FPSCR_FPRF; \ -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Now that float_status has a bunch of fp parameters, it is easier to copy an existing structure than create one from scratch. Begin by copying the structure that corresponds to the FPSR and make only the adjustments required for BFloat16 semantics. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241203203949.483774-2-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/tcg/vec_helper.c | 20 +++++++------------- 1 file changed, 7 insertions(+), 13 deletions(-) diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -XXX,XX +XXX,XX @@ bool is_ebf(CPUARMState *env, float_status *statusp, float_status *oddstatusp) * no effect on AArch32 instructions. */ bool ebf = is_a64(env) && env->vfp.fpcr & FPCR_EBF; - *statusp = (float_status){ - .tininess_before_rounding = float_tininess_before_rounding, - .float_rounding_mode = float_round_to_odd_inf, - .flush_to_zero = true, - .flush_inputs_to_zero = true, - .default_nan_mode = true, - }; + + *statusp = env->vfp.fp_status; + set_default_nan_mode(true, statusp); if (ebf) { - float_status *fpst = &env->vfp.fp_status; - set_flush_to_zero(get_flush_to_zero(fpst), statusp); - set_flush_inputs_to_zero(get_flush_inputs_to_zero(fpst), statusp); - set_float_rounding_mode(get_float_rounding_mode(fpst), statusp); - /* EBF=1 needs to do a step with round-to-odd semantics */ *oddstatusp = *statusp; set_float_rounding_mode(float_round_to_odd, oddstatusp); + } else { + set_flush_to_zero(true, statusp); + set_flush_inputs_to_zero(true, statusp); + set_float_rounding_mode(float_round_to_odd_inf, statusp); } - return ebf; } -- 2.34.1 Currently we hardcode the default NaN value in parts64_default_nan() using a compile-time ifdef ladder. This is awkward for two cases: * for single-QEMU-binary we can't hard-code target-specifics like this * for Arm FEAT_AFP the default NaN value depends on FPCR.AH (specifically the sign bit is different) Add a field to float_status to specify the default NaN value; fall back to the old ifdef behaviour if these are not set. The default NaN value is specified by setting a uint8_t to a pattern corresponding to the sign and upper fraction parts of the NaN; the lower bits of the fraction are set from bit 0 of the pattern. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-35-peter.maydell@linaro.org --- include/fpu/softfloat-helpers.h | 11 +++++++ include/fpu/softfloat-types.h | 10 ++++++ fpu/softfloat-specialize.c.inc | 55 ++++++++++++++++++++------------- 3 files changed, 54 insertions(+), 22 deletions(-) diff --git a/include/fpu/softfloat-helpers.h b/include/fpu/softfloat-helpers.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-helpers.h +++ b/include/fpu/softfloat-helpers.h @@ -XXX,XX +XXX,XX @@ static inline void set_float_infzeronan_rule(FloatInfZeroNaNRule rule, status->float_infzeronan_rule = rule; } +static inline void set_float_default_nan_pattern(uint8_t dnan_pattern, + float_status *status) +{ + status->default_nan_pattern = dnan_pattern; +} + static inline void set_flush_to_zero(bool val, float_status *status) { status->flush_to_zero = val; @@ -XXX,XX +XXX,XX @@ static inline FloatInfZeroNaNRule get_float_infzeronan_rule(float_status *status return status->float_infzeronan_rule; } +static inline uint8_t get_float_default_nan_pattern(float_status *status) +{ + return status->default_nan_pattern; +} + static inline bool get_flush_to_zero(float_status *status) { return status->flush_to_zero; diff --git a/include/fpu/softfloat-types.h b/include/fpu/softfloat-types.h index XXXXXXX..XXXXXXX 100644 --- a/include/fpu/softfloat-types.h +++ b/include/fpu/softfloat-types.h @@ -XXX,XX +XXX,XX @@ typedef struct float_status { /* should denormalised inputs go to zero and set the input_denormal flag? */ bool flush_inputs_to_zero; bool default_nan_mode; + /* + * The pattern to use for the default NaN. Here the high bit specifies + * the default NaN's sign bit, and bits 6..0 specify the high bits of the + * fractional part. The low bits of the fractional part are copies of bit 0. + * The exponent of the default NaN is (as for any NaN) always all 1s. + * Note that a value of 0 here is not a valid NaN. The target must set + * this to the correct non-zero value, or we will assert when trying to + * create a default NaN. + */ + uint8_t default_nan_pattern; /* * The flags below are not used on all specializations and may * constant fold away (see snan_bit_is_one()/no_signalling_nans() in diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) { bool sign = 0; uint64_t frac; + uint8_t dnan_pattern = status->default_nan_pattern; + if (dnan_pattern == 0) { #if defined(TARGET_SPARC) || defined(TARGET_M68K) - /* !snan_bit_is_one, set all bits */ - frac = (1ULL << DECOMPOSED_BINARY_POINT) - 1; -#elif defined(TARGET_I386) || defined(TARGET_X86_64) \ + /* Sign bit clear, all frac bits set */ + dnan_pattern = 0b01111111; +#elif defined(TARGET_I386) || defined(TARGET_X86_64) \ || defined(TARGET_MICROBLAZE) - /* !snan_bit_is_one, set sign and msb */ - frac = 1ULL << (DECOMPOSED_BINARY_POINT - 1); - sign = 1; + /* Sign bit set, most significant frac bit set */ + dnan_pattern = 0b11000000; #elif defined(TARGET_HPPA) - /* snan_bit_is_one, set msb-1. */ - frac = 1ULL << (DECOMPOSED_BINARY_POINT - 2); + /* Sign bit clear, msb-1 frac bit set */ + dnan_pattern = 0b00100000; #elif defined(TARGET_HEXAGON) - sign = 1; - frac = ~0ULL; + /* Sign bit set, all frac bits set. */ + dnan_pattern = 0b11111111; #else - /* - * This case is true for Alpha, ARM, MIPS, OpenRISC, PPC, RISC-V, - * S390, SH4, TriCore, and Xtensa. Our other supported targets - * do not have floating-point. - */ - if (snan_bit_is_one(status)) { - /* set all bits other than msb */ - frac = (1ULL << (DECOMPOSED_BINARY_POINT - 1)) - 1; - } else { - /* set msb */ - frac = 1ULL << (DECOMPOSED_BINARY_POINT - 1); - } + /* + * This case is true for Alpha, ARM, MIPS, OpenRISC, PPC, RISC-V, + * S390, SH4, TriCore, and Xtensa. Our other supported targets + * do not have floating-point. + */ + if (snan_bit_is_one(status)) { + /* sign bit clear, set all frac bits other than msb */ + dnan_pattern = 0b00111111; + } else { + /* sign bit clear, set frac msb */ + dnan_pattern = 0b01000000; + } #endif + } + assert(dnan_pattern != 0); + + sign = dnan_pattern >> 7; + /* + * Place default_nan_pattern [6:0] into bits [62:56], + * and replecate bit [0] down into [55:0] + */ + frac = deposit64(0, DECOMPOSED_BINARY_POINT - 7, 7, dnan_pattern); + frac = deposit64(frac, 0, DECOMPOSED_BINARY_POINT - 7, -(dnan_pattern & 1)); *p = (FloatParts64) { .cls = float_class_qnan, -- 2.34.1 Set the default NaN pattern explicitly for the tests/fp code. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-36-peter.maydell@linaro.org --- tests/fp/fp-bench.c | 1 + tests/fp/fp-test-log2.c | 1 + tests/fp/fp-test.c | 1 + 3 files changed, 3 insertions(+) diff --git a/tests/fp/fp-bench.c b/tests/fp/fp-bench.c index XXXXXXX..XXXXXXX 100644 --- a/tests/fp/fp-bench.c +++ b/tests/fp/fp-bench.c @@ -XXX,XX +XXX,XX @@ static void run_bench(void) set_float_2nan_prop_rule(float_2nan_prop_s_ab, &soft_status); set_float_3nan_prop_rule(float_3nan_prop_s_cab, &soft_status); set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, &soft_status); + set_float_default_nan_pattern(0b01000000, &soft_status); f = bench_funcs[operation][precision]; g_assert(f); diff --git a/tests/fp/fp-test-log2.c b/tests/fp/fp-test-log2.c index XXXXXXX..XXXXXXX 100644 --- a/tests/fp/fp-test-log2.c +++ b/tests/fp/fp-test-log2.c @@ -XXX,XX +XXX,XX @@ int main(int ac, char **av) int i; set_float_2nan_prop_rule(float_2nan_prop_s_ab, &qsf); + set_float_default_nan_pattern(0b01000000, &qsf); set_float_rounding_mode(float_round_nearest_even, &qsf); test.d = 0.0; diff --git a/tests/fp/fp-test.c b/tests/fp/fp-test.c index XXXXXXX..XXXXXXX 100644 --- a/tests/fp/fp-test.c +++ b/tests/fp/fp-test.c @@ -XXX,XX +XXX,XX @@ void run_test(void) */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &qsf); set_float_3nan_prop_rule(float_3nan_prop_s_cab, &qsf); + set_float_default_nan_pattern(0b01000000, &qsf); set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, &qsf); genCases_setLevel(test_level); -- 2.34.1 Set the default NaN pattern explicitly, and remove the ifdef from parts64_default_nan(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-37-peter.maydell@linaro.org --- target/microblaze/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 3 +-- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/target/microblaze/cpu.c b/target/microblaze/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/microblaze/cpu.c +++ b/target/microblaze/cpu.c @@ -XXX,XX +XXX,XX @@ static void mb_cpu_reset_hold(Object *obj, ResetType type) * this architecture. */ set_float_2nan_prop_rule(float_2nan_prop_x87, &env->fp_status); + /* Default NaN: sign bit set, most significant frac bit set */ + set_float_default_nan_pattern(0b11000000, &env->fp_status); #if defined(CONFIG_USER_ONLY) /* start in user mode with interrupts enabled. */ diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) #if defined(TARGET_SPARC) || defined(TARGET_M68K) /* Sign bit clear, all frac bits set */ dnan_pattern = 0b01111111; -#elif defined(TARGET_I386) || defined(TARGET_X86_64) \ - || defined(TARGET_MICROBLAZE) +#elif defined(TARGET_I386) || defined(TARGET_X86_64) /* Sign bit set, most significant frac bit set */ dnan_pattern = 0b11000000; #elif defined(TARGET_HPPA) -- 2.34.1 Set the default NaN pattern explicitly, and remove the ifdef from parts64_default_nan(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-38-peter.maydell@linaro.org --- target/i386/tcg/fpu_helper.c | 4 ++++ fpu/softfloat-specialize.c.inc | 3 --- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/target/i386/tcg/fpu_helper.c b/target/i386/tcg/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/i386/tcg/fpu_helper.c +++ b/target/i386/tcg/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void cpu_init_fp_statuses(CPUX86State *env) */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->sse_status); set_float_3nan_prop_rule(float_3nan_prop_abc, &env->sse_status); + /* Default NaN: sign bit set, most significant frac bit set */ + set_float_default_nan_pattern(0b11000000, &env->fp_status); + set_float_default_nan_pattern(0b11000000, &env->mmx_status); + set_float_default_nan_pattern(0b11000000, &env->sse_status); } static inline uint8_t save_exception_flags(CPUX86State *env) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) #if defined(TARGET_SPARC) || defined(TARGET_M68K) /* Sign bit clear, all frac bits set */ dnan_pattern = 0b01111111; -#elif defined(TARGET_I386) || defined(TARGET_X86_64) - /* Sign bit set, most significant frac bit set */ - dnan_pattern = 0b11000000; #elif defined(TARGET_HPPA) /* Sign bit clear, msb-1 frac bit set */ dnan_pattern = 0b00100000; -- 2.34.1 Set the default NaN pattern explicitly, and remove the ifdef from parts64_default_nan(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-39-peter.maydell@linaro.org --- target/hppa/fpu_helper.c | 2 ++ fpu/softfloat-specialize.c.inc | 3 --- 2 files changed, 2 insertions(+), 3 deletions(-) diff --git a/target/hppa/fpu_helper.c b/target/hppa/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/hppa/fpu_helper.c +++ b/target/hppa/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(loaded_fr0)(CPUHPPAState *env) set_float_3nan_prop_rule(float_3nan_prop_abc, &env->fp_status); /* For inf * 0 + NaN, return the input NaN */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); + /* Default NaN: sign bit clear, msb-1 frac bit set */ + set_float_default_nan_pattern(0b00100000, &env->fp_status); } void cpu_hppa_loaded_fr0(CPUHPPAState *env) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) #if defined(TARGET_SPARC) || defined(TARGET_M68K) /* Sign bit clear, all frac bits set */ dnan_pattern = 0b01111111; -#elif defined(TARGET_HPPA) - /* Sign bit clear, msb-1 frac bit set */ - dnan_pattern = 0b00100000; #elif defined(TARGET_HEXAGON) /* Sign bit set, all frac bits set. */ dnan_pattern = 0b11111111; -- 2.34.1 Set the default NaN pattern explicitly for the alpha target. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-40-peter.maydell@linaro.org --- target/alpha/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/alpha/cpu.c b/target/alpha/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/alpha/cpu.c +++ b/target/alpha/cpu.c @@ -XXX,XX +XXX,XX @@ static void alpha_cpu_initfn(Object *obj) * operand in Fa. That is float_2nan_prop_ba. */ set_float_2nan_prop_rule(float_2nan_prop_x87, &env->fp_status); + /* Default NaN: sign bit clear, msb frac bit set */ + set_float_default_nan_pattern(0b01000000, &env->fp_status); #if defined(CONFIG_USER_ONLY) env->flags = ENV_FLAG_PS_USER | ENV_FLAG_FEN; cpu_alpha_store_fpcr(env, (uint64_t)(FPCR_INVD | FPCR_DZED | FPCR_OVFD -- 2.34.1 Set the default NaN pattern explicitly for the arm target. This includes setting it for the old linux-user nwfpe emulation. For nwfpe, our default doesn't match the real kernel, but we avoid making a behaviour change in this commit. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-41-peter.maydell@linaro.org --- linux-user/arm/nwfpe/fpa11.c | 5 +++++ target/arm/cpu.c | 2 ++ 2 files changed, 7 insertions(+) diff --git a/linux-user/arm/nwfpe/fpa11.c b/linux-user/arm/nwfpe/fpa11.c index XXXXXXX..XXXXXXX 100644 --- a/linux-user/arm/nwfpe/fpa11.c +++ b/linux-user/arm/nwfpe/fpa11.c @@ -XXX,XX +XXX,XX @@ void resetFPA11(void) * this late date. */ set_float_2nan_prop_rule(float_2nan_prop_s_ab, &fpa11->fp_status); + /* + * Use the same default NaN value as Arm VFP. This doesn't match + * the Linux kernel's nwfpe emulation, which uses an all-1s value. + */ + set_float_default_nan_pattern(0b01000000, &fpa11->fp_status); } void SetRoundingMode(const unsigned int opcode) diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ void arm_register_el_change_hook(ARMCPU *cpu, ARMELChangeHookFn *hook, * the pseudocode function the arguments are in the order c, a, b. * * 0 * Inf + NaN returns the default NaN if the input NaN is quiet, * and the input NaN if it is signalling + * * Default NaN has sign bit clear, msb frac bit set */ static void arm_set_default_fp_behaviours(float_status *s) { @@ -XXX,XX +XXX,XX @@ static void arm_set_default_fp_behaviours(float_status *s) set_float_2nan_prop_rule(float_2nan_prop_s_ab, s); set_float_3nan_prop_rule(float_3nan_prop_s_cab, s); set_float_infzeronan_rule(float_infzeronan_dnan_if_qnan, s); + set_float_default_nan_pattern(0b01000000, s); } static void cp_reg_reset(gpointer key, gpointer value, gpointer opaque) -- 2.34.1 Set the default NaN pattern explicitly for loongarch. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-42-peter.maydell@linaro.org --- target/loongarch/tcg/fpu_helper.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/loongarch/tcg/fpu_helper.c b/target/loongarch/tcg/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/loongarch/tcg/fpu_helper.c +++ b/target/loongarch/tcg/fpu_helper.c @@ -XXX,XX +XXX,XX @@ void restore_fp_status(CPULoongArchState *env) */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); set_float_3nan_prop_rule(float_3nan_prop_s_cab, &env->fp_status); + /* Default NaN: sign bit clear, msb frac bit set */ + set_float_default_nan_pattern(0b01000000, &env->fp_status); } int ieee_ex_to_loongarch(int xcpt) -- 2.34.1 Set the default NaN pattern explicitly for m68k. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-43-peter.maydell@linaro.org --- target/m68k/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 2 +- 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/target/m68k/cpu.c b/target/m68k/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/m68k/cpu.c +++ b/target/m68k/cpu.c @@ -XXX,XX +XXX,XX @@ static void m68k_cpu_reset_hold(Object *obj, ResetType type) * preceding paragraph for nonsignaling NaNs. */ set_float_2nan_prop_rule(float_2nan_prop_ab, &env->fp_status); + /* Default NaN: sign bit clear, all frac bits set */ + set_float_default_nan_pattern(0b01111111, &env->fp_status); nan = floatx80_default_nan(&env->fp_status); for (i = 0; i < 8; i++) { diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) uint8_t dnan_pattern = status->default_nan_pattern; if (dnan_pattern == 0) { -#if defined(TARGET_SPARC) || defined(TARGET_M68K) +#if defined(TARGET_SPARC) /* Sign bit clear, all frac bits set */ dnan_pattern = 0b01111111; #elif defined(TARGET_HEXAGON) -- 2.34.1 Set the default NaN pattern explicitly for MIPS. Note that this is our only target which currently changes the default NaN at runtime (which it was previously doing indirectly when it changed the snan_bit_is_one setting). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-44-peter.maydell@linaro.org --- target/mips/fpu_helper.h | 7 +++++++ target/mips/msa.c | 3 +++ 2 files changed, 10 insertions(+) diff --git a/target/mips/fpu_helper.h b/target/mips/fpu_helper.h index XXXXXXX..XXXXXXX 100644 --- a/target/mips/fpu_helper.h +++ b/target/mips/fpu_helper.h @@ -XXX,XX +XXX,XX @@ static inline void restore_snan_bit_mode(CPUMIPSState *env) set_float_infzeronan_rule(izn_rule, &env->active_fpu.fp_status); nan3_rule = nan2008 ? float_3nan_prop_s_cab : float_3nan_prop_s_abc; set_float_3nan_prop_rule(nan3_rule, &env->active_fpu.fp_status); + /* + * With nan2008, the default NaN value has the sign bit clear and the + * frac msb set; with the older mode, the sign bit is clear, and all + * frac bits except the msb are set. + */ + set_float_default_nan_pattern(nan2008 ? 0b01000000 : 0b00111111, + &env->active_fpu.fp_status); } diff --git a/target/mips/msa.c b/target/mips/msa.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/msa.c +++ b/target/mips/msa.c @@ -XXX,XX +XXX,XX @@ void msa_reset(CPUMIPSState *env) /* Inf * 0 + NaN returns the input NaN */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->active_tc.msa_fp_status); + /* Default NaN: sign bit clear, frac msb set */ + set_float_default_nan_pattern(0b01000000, + &env->active_tc.msa_fp_status); } -- 2.34.1 Set the default NaN pattern explicitly for openrisc. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-45-peter.maydell@linaro.org --- target/openrisc/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/openrisc/cpu.c b/target/openrisc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/openrisc/cpu.c +++ b/target/openrisc/cpu.c @@ -XXX,XX +XXX,XX @@ static void openrisc_cpu_reset_hold(Object *obj, ResetType type) */ set_float_2nan_prop_rule(float_2nan_prop_x87, &cpu->env.fp_status); + /* Default NaN: sign bit clear, frac msb set */ + set_float_default_nan_pattern(0b01000000, &cpu->env.fp_status); #ifndef CONFIG_USER_ONLY cpu->env.picmr = 0x00000000; -- 2.34.1 Set the default NaN pattern explicitly for ppc. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-46-peter.maydell@linaro.org --- target/ppc/cpu_init.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/target/ppc/cpu_init.c b/target/ppc/cpu_init.c index XXXXXXX..XXXXXXX 100644 --- a/target/ppc/cpu_init.c +++ b/target/ppc/cpu_init.c @@ -XXX,XX +XXX,XX @@ static void ppc_cpu_reset_hold(Object *obj, ResetType type) set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->vec_status); + /* Default NaN: sign bit clear, set frac msb */ + set_float_default_nan_pattern(0b01000000, &env->fp_status); + set_float_default_nan_pattern(0b01000000, &env->vec_status); + for (i = 0; i < ARRAY_SIZE(env->spr_cb); i++) { ppc_spr_t *spr = &env->spr_cb[i]; -- 2.34.1 Set the default NaN pattern explicitly for sh4. Note that sh4 is one of the only three targets (the others being HPPA and sometimes MIPS) that has snan_bit_is_one set. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-47-peter.maydell@linaro.org --- target/sh4/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/sh4/cpu.c b/target/sh4/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sh4/cpu.c +++ b/target/sh4/cpu.c @@ -XXX,XX +XXX,XX @@ static void superh_cpu_reset_hold(Object *obj, ResetType type) set_flush_to_zero(1, &env->fp_status); #endif set_default_nan_mode(1, &env->fp_status); + /* sign bit clear, set all frac bits other than msb */ + set_float_default_nan_pattern(0b00111111, &env->fp_status); } static void superh_cpu_disas_set_info(CPUState *cpu, disassemble_info *info) -- 2.34.1 Set the default NaN pattern explicitly for rx. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-48-peter.maydell@linaro.org --- target/rx/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/rx/cpu.c b/target/rx/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/rx/cpu.c +++ b/target/rx/cpu.c @@ -XXX,XX +XXX,XX @@ static void rx_cpu_reset_hold(Object *obj, ResetType type) * then prefer dest over source", which is float_2nan_prop_s_ab. */ set_float_2nan_prop_rule(float_2nan_prop_x87, &env->fp_status); + /* Default NaN value: sign bit clear, set frac msb */ + set_float_default_nan_pattern(0b01000000, &env->fp_status); } static ObjectClass *rx_cpu_class_by_name(const char *cpu_model) -- 2.34.1 Set the default NaN pattern explicitly for s390x. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-49-peter.maydell@linaro.org --- target/s390x/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/s390x/cpu.c b/target/s390x/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/s390x/cpu.c +++ b/target/s390x/cpu.c @@ -XXX,XX +XXX,XX @@ static void s390_cpu_reset_hold(Object *obj, ResetType type) set_float_3nan_prop_rule(float_3nan_prop_s_abc, &env->fpu_status); set_float_infzeronan_rule(float_infzeronan_dnan_always, &env->fpu_status); + /* Default NaN value: sign bit clear, frac msb set */ + set_float_default_nan_pattern(0b01000000, &env->fpu_status); /* fall through */ case RESET_TYPE_S390_CPU_NORMAL: env->psw.mask &= ~PSW_MASK_RI; -- 2.34.1 Set the default NaN pattern explicitly for SPARC, and remove the ifdef from parts64_default_nan. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-50-peter.maydell@linaro.org --- target/sparc/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 5 +---- 2 files changed, 3 insertions(+), 4 deletions(-) diff --git a/target/sparc/cpu.c b/target/sparc/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/sparc/cpu.c +++ b/target/sparc/cpu.c @@ -XXX,XX +XXX,XX @@ static void sparc_cpu_realizefn(DeviceState *dev, Error **errp) set_float_3nan_prop_rule(float_3nan_prop_s_cba, &env->fp_status); /* For inf * 0 + NaN, return the input NaN */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); + /* Default NaN value: sign bit clear, all frac bits set */ + set_float_default_nan_pattern(0b01111111, &env->fp_status); cpu_exec_realizefn(cs, &local_err); if (local_err != NULL) { diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) uint8_t dnan_pattern = status->default_nan_pattern; if (dnan_pattern == 0) { -#if defined(TARGET_SPARC) - /* Sign bit clear, all frac bits set */ - dnan_pattern = 0b01111111; -#elif defined(TARGET_HEXAGON) +#if defined(TARGET_HEXAGON) /* Sign bit set, all frac bits set. */ dnan_pattern = 0b11111111; #else -- 2.34.1 Set the default NaN pattern explicitly for xtensa. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-51-peter.maydell@linaro.org --- target/xtensa/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/xtensa/cpu.c b/target/xtensa/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/xtensa/cpu.c +++ b/target/xtensa/cpu.c @@ -XXX,XX +XXX,XX @@ static void xtensa_cpu_reset_hold(Object *obj, ResetType type) /* For inf * 0 + NaN, return the input NaN */ set_float_infzeronan_rule(float_infzeronan_dnan_never, &env->fp_status); set_no_signaling_nans(!dfpu, &env->fp_status); + /* Default NaN value: sign bit clear, set frac msb */ + set_float_default_nan_pattern(0b01000000, &env->fp_status); xtensa_use_first_nan(env, !dfpu); } -- 2.34.1 Set the default NaN pattern explicitly for hexagon. Remove the ifdef from parts64_default_nan(); the only remaining unconverted targets all use the default case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-52-peter.maydell@linaro.org --- target/hexagon/cpu.c | 2 ++ fpu/softfloat-specialize.c.inc | 5 ----- 2 files changed, 2 insertions(+), 5 deletions(-) diff --git a/target/hexagon/cpu.c b/target/hexagon/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/hexagon/cpu.c +++ b/target/hexagon/cpu.c @@ -XXX,XX +XXX,XX @@ static void hexagon_cpu_reset_hold(Object *obj, ResetType type) set_default_nan_mode(1, &env->fp_status); set_float_detect_tininess(float_tininess_before_rounding, &env->fp_status); + /* Default NaN value: sign bit set, all frac bits set */ + set_float_default_nan_pattern(0b11111111, &env->fp_status); } static void hexagon_cpu_disas_set_info(CPUState *s, disassemble_info *info) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) uint8_t dnan_pattern = status->default_nan_pattern; if (dnan_pattern == 0) { -#if defined(TARGET_HEXAGON) - /* Sign bit set, all frac bits set. */ - dnan_pattern = 0b11111111; -#else /* * This case is true for Alpha, ARM, MIPS, OpenRISC, PPC, RISC-V, * S390, SH4, TriCore, and Xtensa. Our other supported targets @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) /* sign bit clear, set frac msb */ dnan_pattern = 0b01000000; } -#endif } assert(dnan_pattern != 0); -- 2.34.1 Set the default NaN pattern explicitly for riscv. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-53-peter.maydell@linaro.org --- target/riscv/cpu.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/riscv/cpu.c b/target/riscv/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/riscv/cpu.c +++ b/target/riscv/cpu.c @@ -XXX,XX +XXX,XX @@ static void riscv_cpu_reset_hold(Object *obj, ResetType type) cs->exception_index = RISCV_EXCP_NONE; env->load_res = -1; set_default_nan_mode(1, &env->fp_status); + /* Default NaN value: sign bit clear, frac msb set */ + set_float_default_nan_pattern(0b01000000, &env->fp_status); env->vill = true; #ifndef CONFIG_USER_ONLY -- 2.34.1 Set the default NaN pattern explicitly for tricore. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-54-peter.maydell@linaro.org --- target/tricore/helper.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/target/tricore/helper.c b/target/tricore/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/tricore/helper.c +++ b/target/tricore/helper.c @@ -XXX,XX +XXX,XX @@ void fpu_set_state(CPUTriCoreState *env) set_flush_to_zero(1, &env->fp_status); set_float_detect_tininess(float_tininess_before_rounding, &env->fp_status); set_default_nan_mode(1, &env->fp_status); + /* Default NaN pattern: sign bit clear, frac msb set */ + set_float_default_nan_pattern(0b01000000, &env->fp_status); } uint32_t psw_read(CPUTriCoreState *env) -- 2.34.1 Now that all our targets have bene converted to explicitly specify their pattern for the default NaN value we can remove the remaining fallback code in parts64_default_nan(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241202131347.498124-55-peter.maydell@linaro.org --- fpu/softfloat-specialize.c.inc | 14 -------------- 1 file changed, 14 deletions(-) diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static void parts64_default_nan(FloatParts64 *p, float_status *status) uint64_t frac; uint8_t dnan_pattern = status->default_nan_pattern; - if (dnan_pattern == 0) { - /* - * This case is true for Alpha, ARM, MIPS, OpenRISC, PPC, RISC-V, - * S390, SH4, TriCore, and Xtensa. Our other supported targets - * do not have floating-point. - */ - if (snan_bit_is_one(status)) { - /* sign bit clear, set all frac bits other than msb */ - dnan_pattern = 0b00111111; - } else { - /* sign bit clear, set frac msb */ - dnan_pattern = 0b01000000; - } - } assert(dnan_pattern != 0); sign = dnan_pattern >> 7; -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Inline pickNaNMulAdd into its only caller. This makes one assert redundant with the immediately preceding IF. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241203203949.483774-3-richard.henderson@linaro.org [PMM: keep comment from old code in new location] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 41 +++++++++++++++++++++++++- fpu/softfloat-specialize.c.inc | 54 ---------------------------------- 2 files changed, 40 insertions(+), 55 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, } if (s->default_nan_mode) { + /* + * We guarantee not to require the target to tell us how to + * pick a NaN if we're always returning the default NaN. + * But if we're not in default-NaN mode then the target must + * specify. + */ which = 3; + } else if (infzero) { + /* + * Inf * 0 + NaN -- some implementations return the + * default NaN here, and some return the input NaN. + */ + switch (s->float_infzeronan_rule) { + case float_infzeronan_dnan_never: + which = 2; + break; + case float_infzeronan_dnan_always: + which = 3; + break; + case float_infzeronan_dnan_if_qnan: + which = is_qnan(c->cls) ? 3 : 2; + break; + default: + g_assert_not_reached(); + } } else { - which = pickNaNMulAdd(a->cls, b->cls, c->cls, infzero, have_snan, s); + FloatClass cls[3] = { a->cls, b->cls, c->cls }; + Float3NaNPropRule rule = s->float_3nan_prop_rule; + + assert(rule != float_3nan_prop_none); + if (have_snan && (rule & R_3NAN_SNAN_MASK)) { + /* We have at least one SNaN input and should prefer it */ + do { + which = rule & R_3NAN_1ST_MASK; + rule >>= R_3NAN_1ST_LENGTH; + } while (!is_snan(cls[which])); + } else { + do { + which = rule & R_3NAN_1ST_MASK; + rule >>= R_3NAN_1ST_LENGTH; + } while (!is_nan(cls[which])); + } } if (which == 3) { diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ static int pickNaN(FloatClass a_cls, FloatClass b_cls, } } -/*---------------------------------------------------------------------------- -| Select which NaN to propagate for a three-input operation. -| For the moment we assume that no CPU needs the 'larger significand' -| information. -| Return values : 0 : a; 1 : b; 2 : c; 3 : default-NaN -*----------------------------------------------------------------------------*/ -static int pickNaNMulAdd(FloatClass a_cls, FloatClass b_cls, FloatClass c_cls, - bool infzero, bool have_snan, float_status *status) -{ - FloatClass cls[3] = { a_cls, b_cls, c_cls }; - Float3NaNPropRule rule = status->float_3nan_prop_rule; - int which; - - /* - * We guarantee not to require the target to tell us how to - * pick a NaN if we're always returning the default NaN. - * But if we're not in default-NaN mode then the target must - * specify. - */ - assert(!status->default_nan_mode); - - if (infzero) { - /* - * Inf * 0 + NaN -- some implementations return the default NaN here, - * and some return the input NaN. - */ - switch (status->float_infzeronan_rule) { - case float_infzeronan_dnan_never: - return 2; - case float_infzeronan_dnan_always: - return 3; - case float_infzeronan_dnan_if_qnan: - return is_qnan(c_cls) ? 3 : 2; - default: - g_assert_not_reached(); - } - } - - assert(rule != float_3nan_prop_none); - if (have_snan && (rule & R_3NAN_SNAN_MASK)) { - /* We have at least one SNaN input and should prefer it */ - do { - which = rule & R_3NAN_1ST_MASK; - rule >>= R_3NAN_1ST_LENGTH; - } while (!is_snan(cls[which])); - } else { - do { - which = rule & R_3NAN_1ST_MASK; - rule >>= R_3NAN_1ST_LENGTH; - } while (!is_nan(cls[which])); - } - return which; -} - /*---------------------------------------------------------------------------- | Returns 1 if the double-precision floating-point value `a' is a quiet | NaN; otherwise returns 0. -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Remove "3" as a special case for which and simply branch to return the desired value. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241203203949.483774-4-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, * But if we're not in default-NaN mode then the target must * specify. */ - which = 3; + goto default_nan; } else if (infzero) { /* * Inf * 0 + NaN -- some implementations return the @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, */ switch (s->float_infzeronan_rule) { case float_infzeronan_dnan_never: - which = 2; break; case float_infzeronan_dnan_always: - which = 3; - break; + goto default_nan; case float_infzeronan_dnan_if_qnan: - which = is_qnan(c->cls) ? 3 : 2; + if (is_qnan(c->cls)) { + goto default_nan; + } break; default: g_assert_not_reached(); } + which = 2; } else { FloatClass cls[3] = { a->cls, b->cls, c->cls }; Float3NaNPropRule rule = s->float_3nan_prop_rule; @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, } } - if (which == 3) { - parts_default_nan(a, s); - return a; - } - switch (which) { case 0: break; @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, parts_silence_nan(a, s); } return a; + + default_nan: + parts_default_nan(a, s); + return a; } /* -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Assign the pointer return value to 'a' directly, rather than going through an intermediary index. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241203203949.483774-5-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 32 ++++++++++---------------------- 1 file changed, 10 insertions(+), 22 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, FloatPartsN *c, float_status *s, int ab_mask, int abc_mask) { - int which; bool infzero = (ab_mask == float_cmask_infzero); bool have_snan = (abc_mask & float_cmask_snan); + FloatPartsN *ret; if (unlikely(have_snan)) { float_raise(float_flag_invalid | float_flag_invalid_snan, s); @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, default: g_assert_not_reached(); } - which = 2; + ret = c; } else { - FloatClass cls[3] = { a->cls, b->cls, c->cls }; + FloatPartsN *val[3] = { a, b, c }; Float3NaNPropRule rule = s->float_3nan_prop_rule; assert(rule != float_3nan_prop_none); if (have_snan && (rule & R_3NAN_SNAN_MASK)) { /* We have at least one SNaN input and should prefer it */ do { - which = rule & R_3NAN_1ST_MASK; + ret = val[rule & R_3NAN_1ST_MASK]; rule >>= R_3NAN_1ST_LENGTH; - } while (!is_snan(cls[which])); + } while (!is_snan(ret->cls)); } else { do { - which = rule & R_3NAN_1ST_MASK; + ret = val[rule & R_3NAN_1ST_MASK]; rule >>= R_3NAN_1ST_LENGTH; - } while (!is_nan(cls[which])); + } while (!is_nan(ret->cls)); } } - switch (which) { - case 0: - break; - case 1: - a = b; - break; - case 2: - a = c; - break; - default: - g_assert_not_reached(); + if (is_snan(ret->cls)) { + parts_silence_nan(ret, s); } - if (is_snan(a->cls)) { - parts_silence_nan(a, s); - } - return a; + return ret; default_nan: parts_default_nan(a, s); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> While all indices into val[] should be in [0-2], the mask applied is two bits. To help static analysis see there is no possibility of read beyond the end of the array, pad the array to 4 entries, with the final being (implicitly) NULL. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241203203949.483774-6-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, } ret = c; } else { - FloatPartsN *val[3] = { a, b, c }; + FloatPartsN *val[R_3NAN_1ST_MASK + 1] = { a, b, c }; Float3NaNPropRule rule = s->float_3nan_prop_rule; assert(rule != float_3nan_prop_none); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> This function is part of the public interface and is not "specialized" to any target in any way. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241203203949.483774-7-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat.c | 52 ++++++++++++++++++++++++++++++++++ fpu/softfloat-specialize.c.inc | 52 ---------------------------------- 2 files changed, 52 insertions(+), 52 deletions(-) diff --git a/fpu/softfloat.c b/fpu/softfloat.c index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -XXX,XX +XXX,XX @@ void normalizeFloatx80Subnormal(uint64_t aSig, int32_t *zExpPtr, *zExpPtr = 1 - shiftCount; } +/*---------------------------------------------------------------------------- +| Takes two extended double-precision floating-point values `a' and `b', one +| of which is a NaN, and returns the appropriate NaN result. If either `a' or +| `b' is a signaling NaN, the invalid exception is raised. +*----------------------------------------------------------------------------*/ + +floatx80 propagateFloatx80NaN(floatx80 a, floatx80 b, float_status *status) +{ + bool aIsLargerSignificand; + FloatClass a_cls, b_cls; + + /* This is not complete, but is good enough for pickNaN. */ + a_cls = (!floatx80_is_any_nan(a) + ? float_class_normal + : floatx80_is_signaling_nan(a, status) + ? float_class_snan + : float_class_qnan); + b_cls = (!floatx80_is_any_nan(b) + ? float_class_normal + : floatx80_is_signaling_nan(b, status) + ? float_class_snan + : float_class_qnan); + + if (is_snan(a_cls) || is_snan(b_cls)) { + float_raise(float_flag_invalid, status); + } + + if (status->default_nan_mode) { + return floatx80_default_nan(status); + } + + if (a.low < b.low) { + aIsLargerSignificand = 0; + } else if (b.low < a.low) { + aIsLargerSignificand = 1; + } else { + aIsLargerSignificand = (a.high < b.high) ? 1 : 0; + } + + if (pickNaN(a_cls, b_cls, aIsLargerSignificand, status)) { + if (is_snan(b_cls)) { + return floatx80_silence_nan(b, status); + } + return b; + } else { + if (is_snan(a_cls)) { + return floatx80_silence_nan(a, status); + } + return a; + } +} + /*---------------------------------------------------------------------------- | Takes an abstract floating-point value having sign `zSign', exponent `zExp', | and extended significand formed by the concatenation of `zSig0' and `zSig1', diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ floatx80 floatx80_silence_nan(floatx80 a, float_status *status) return a; } -/*---------------------------------------------------------------------------- -| Takes two extended double-precision floating-point values `a' and `b', one -| of which is a NaN, and returns the appropriate NaN result. If either `a' or -| `b' is a signaling NaN, the invalid exception is raised. -*----------------------------------------------------------------------------*/ - -floatx80 propagateFloatx80NaN(floatx80 a, floatx80 b, float_status *status) -{ - bool aIsLargerSignificand; - FloatClass a_cls, b_cls; - - /* This is not complete, but is good enough for pickNaN. */ - a_cls = (!floatx80_is_any_nan(a) - ? float_class_normal - : floatx80_is_signaling_nan(a, status) - ? float_class_snan - : float_class_qnan); - b_cls = (!floatx80_is_any_nan(b) - ? float_class_normal - : floatx80_is_signaling_nan(b, status) - ? float_class_snan - : float_class_qnan); - - if (is_snan(a_cls) || is_snan(b_cls)) { - float_raise(float_flag_invalid, status); - } - - if (status->default_nan_mode) { - return floatx80_default_nan(status); - } - - if (a.low < b.low) { - aIsLargerSignificand = 0; - } else if (b.low < a.low) { - aIsLargerSignificand = 1; - } else { - aIsLargerSignificand = (a.high < b.high) ? 1 : 0; - } - - if (pickNaN(a_cls, b_cls, aIsLargerSignificand, status)) { - if (is_snan(b_cls)) { - return floatx80_silence_nan(b, status); - } - return b; - } else { - if (is_snan(a_cls)) { - return floatx80_silence_nan(a, status); - } - return a; - } -} - /*---------------------------------------------------------------------------- | Returns 1 if the quadruple-precision floating-point value `a' is a quiet | NaN; otherwise returns 0. -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Unpacking and repacking the parts may be slightly more work than we did before, but we get to reuse more code. For a code path handling exceptional values, this is an improvement. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20241203203949.483774-8-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat.c | 43 +++++-------------------------------------- 1 file changed, 5 insertions(+), 38 deletions(-) diff --git a/fpu/softfloat.c b/fpu/softfloat.c index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat.c +++ b/fpu/softfloat.c @@ -XXX,XX +XXX,XX @@ void normalizeFloatx80Subnormal(uint64_t aSig, int32_t *zExpPtr, floatx80 propagateFloatx80NaN(floatx80 a, floatx80 b, float_status *status) { - bool aIsLargerSignificand; - FloatClass a_cls, b_cls; + FloatParts128 pa, pb, *pr; - /* This is not complete, but is good enough for pickNaN. */ - a_cls = (!floatx80_is_any_nan(a) - ? float_class_normal - : floatx80_is_signaling_nan(a, status) - ? float_class_snan - : float_class_qnan); - b_cls = (!floatx80_is_any_nan(b) - ? float_class_normal - : floatx80_is_signaling_nan(b, status) - ? float_class_snan - : float_class_qnan); - - if (is_snan(a_cls) || is_snan(b_cls)) { - float_raise(float_flag_invalid, status); - } - - if (status->default_nan_mode) { + if (!floatx80_unpack_canonical(&pa, a, status) || + !floatx80_unpack_canonical(&pb, b, status)) { return floatx80_default_nan(status); } - if (a.low < b.low) { - aIsLargerSignificand = 0; - } else if (b.low < a.low) { - aIsLargerSignificand = 1; - } else { - aIsLargerSignificand = (a.high < b.high) ? 1 : 0; - } - - if (pickNaN(a_cls, b_cls, aIsLargerSignificand, status)) { - if (is_snan(b_cls)) { - return floatx80_silence_nan(b, status); - } - return b; - } else { - if (is_snan(a_cls)) { - return floatx80_silence_nan(a, status); - } - return a; - } + pr = parts_pick_nan(&pa, &pb, status); + return floatx80_round_pack_canonical(pr, status); } /*---------------------------------------------------------------------------- -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Inline pickNaN into its only caller. This makes one assert redundant with the immediately preceding IF. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241203203949.483774-9-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 82 +++++++++++++++++++++++++---- fpu/softfloat-specialize.c.inc | 96 ---------------------------------- 2 files changed, 73 insertions(+), 105 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static void partsN(return_nan)(FloatPartsN *a, float_status *s) static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, float_status *s) { + int cmp, which; + if (is_snan(a->cls) || is_snan(b->cls)) { float_raise(float_flag_invalid | float_flag_invalid_snan, s); } if (s->default_nan_mode) { parts_default_nan(a, s); - } else { - int cmp = frac_cmp(a, b); - if (cmp == 0) { - cmp = a->sign < b->sign; - } + return a; + } - if (pickNaN(a->cls, b->cls, cmp > 0, s)) { - a = b; - } + cmp = frac_cmp(a, b); + if (cmp == 0) { + cmp = a->sign < b->sign; + } + + switch (s->float_2nan_prop_rule) { + case float_2nan_prop_s_ab: if (is_snan(a->cls)) { - parts_silence_nan(a, s); + which = 0; + } else if (is_snan(b->cls)) { + which = 1; + } else if (is_qnan(a->cls)) { + which = 0; + } else { + which = 1; } + break; + case float_2nan_prop_s_ba: + if (is_snan(b->cls)) { + which = 1; + } else if (is_snan(a->cls)) { + which = 0; + } else if (is_qnan(b->cls)) { + which = 1; + } else { + which = 0; + } + break; + case float_2nan_prop_ab: + which = is_nan(a->cls) ? 0 : 1; + break; + case float_2nan_prop_ba: + which = is_nan(b->cls) ? 1 : 0; + break; + case float_2nan_prop_x87: + /* + * This implements x87 NaN propagation rules: + * SNaN + QNaN => return the QNaN + * two SNaNs => return the one with the larger significand, silenced + * two QNaNs => return the one with the larger significand + * SNaN and a non-NaN => return the SNaN, silenced + * QNaN and a non-NaN => return the QNaN + * + * If we get down to comparing significands and they are the same, + * return the NaN with the positive sign bit (if any). + */ + if (is_snan(a->cls)) { + if (is_snan(b->cls)) { + which = cmp > 0 ? 0 : 1; + } else { + which = is_qnan(b->cls) ? 1 : 0; + } + } else if (is_qnan(a->cls)) { + if (is_snan(b->cls) || !is_qnan(b->cls)) { + which = 0; + } else { + which = cmp > 0 ? 0 : 1; + } + } else { + which = 1; + } + break; + default: + g_assert_not_reached(); + } + + if (which) { + a = b; + } + if (is_snan(a->cls)) { + parts_silence_nan(a, s); } return a; } diff --git a/fpu/softfloat-specialize.c.inc b/fpu/softfloat-specialize.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-specialize.c.inc +++ b/fpu/softfloat-specialize.c.inc @@ -XXX,XX +XXX,XX @@ bool float32_is_signaling_nan(float32 a_, float_status *status) } } -/*---------------------------------------------------------------------------- -| Select which NaN to propagate for a two-input operation. -| IEEE754 doesn't specify all the details of this, so the -| algorithm is target-specific. -| The routine is passed various bits of information about the -| two NaNs and should return 0 to select NaN a and 1 for NaN b. -| Note that signalling NaNs are always squashed to quiet NaNs -| by the caller, by calling floatXX_silence_nan() before -| returning them. -| -| aIsLargerSignificand is only valid if both a and b are NaNs -| of some kind, and is true if a has the larger significand, -| or if both a and b have the same significand but a is -| positive but b is negative. It is only needed for the x87 -| tie-break rule. -*----------------------------------------------------------------------------*/ - -static int pickNaN(FloatClass a_cls, FloatClass b_cls, - bool aIsLargerSignificand, float_status *status) -{ - /* - * We guarantee not to require the target to tell us how to - * pick a NaN if we're always returning the default NaN. - * But if we're not in default-NaN mode then the target must - * specify via set_float_2nan_prop_rule(). - */ - assert(!status->default_nan_mode); - - switch (status->float_2nan_prop_rule) { - case float_2nan_prop_s_ab: - if (is_snan(a_cls)) { - return 0; - } else if (is_snan(b_cls)) { - return 1; - } else if (is_qnan(a_cls)) { - return 0; - } else { - return 1; - } - break; - case float_2nan_prop_s_ba: - if (is_snan(b_cls)) { - return 1; - } else if (is_snan(a_cls)) { - return 0; - } else if (is_qnan(b_cls)) { - return 1; - } else { - return 0; - } - break; - case float_2nan_prop_ab: - if (is_nan(a_cls)) { - return 0; - } else { - return 1; - } - break; - case float_2nan_prop_ba: - if (is_nan(b_cls)) { - return 1; - } else { - return 0; - } - break; - case float_2nan_prop_x87: - /* - * This implements x87 NaN propagation rules: - * SNaN + QNaN => return the QNaN - * two SNaNs => return the one with the larger significand, silenced - * two QNaNs => return the one with the larger significand - * SNaN and a non-NaN => return the SNaN, silenced - * QNaN and a non-NaN => return the QNaN - * - * If we get down to comparing significands and they are the same, - * return the NaN with the positive sign bit (if any). - */ - if (is_snan(a_cls)) { - if (is_snan(b_cls)) { - return aIsLargerSignificand ? 0 : 1; - } - return is_qnan(b_cls) ? 1 : 0; - } else if (is_qnan(a_cls)) { - if (is_snan(b_cls) || !is_qnan(b_cls)) { - return 0; - } else { - return aIsLargerSignificand ? 0 : 1; - } - } else { - return 1; - } - default: - g_assert_not_reached(); - } -} - /*---------------------------------------------------------------------------- | Returns 1 if the double-precision floating-point value `a' is a quiet | NaN; otherwise returns 0. -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Remember if there was an SNaN, and use that to simplify float_2nan_prop_s_{ab,ba} to only the snan component. Then, fall through to the corresponding float_2nan_prop_{ab,ba} case to handle any remaining nans, which must be quiet. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241203203949.483774-10-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 32 ++++++++++++-------------------- 1 file changed, 12 insertions(+), 20 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static void partsN(return_nan)(FloatPartsN *a, float_status *s) static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, float_status *s) { + bool have_snan = false; int cmp, which; if (is_snan(a->cls) || is_snan(b->cls)) { float_raise(float_flag_invalid | float_flag_invalid_snan, s); + have_snan = true; } if (s->default_nan_mode) { @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, switch (s->float_2nan_prop_rule) { case float_2nan_prop_s_ab: - if (is_snan(a->cls)) { - which = 0; - } else if (is_snan(b->cls)) { - which = 1; - } else if (is_qnan(a->cls)) { - which = 0; - } else { - which = 1; + if (have_snan) { + which = is_snan(a->cls) ? 0 : 1; + break; } - break; - case float_2nan_prop_s_ba: - if (is_snan(b->cls)) { - which = 1; - } else if (is_snan(a->cls)) { - which = 0; - } else if (is_qnan(b->cls)) { - which = 1; - } else { - which = 0; - } - break; + /* fall through */ case float_2nan_prop_ab: which = is_nan(a->cls) ? 0 : 1; break; + case float_2nan_prop_s_ba: + if (have_snan) { + which = is_snan(b->cls) ? 1 : 0; + break; + } + /* fall through */ case float_2nan_prop_ba: which = is_nan(b->cls) ? 1 : 0; break; -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Move the fractional comparison to the end of the float_2nan_prop_x87 case. This is not required for any other 2nan propagation rule. Reorganize the x87 case itself to break out of the switch when the fractional comparison is not required. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20241203203949.483774-11-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 19 +++++++++---------- 1 file changed, 9 insertions(+), 10 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, return a; } - cmp = frac_cmp(a, b); - if (cmp == 0) { - cmp = a->sign < b->sign; - } - switch (s->float_2nan_prop_rule) { case float_2nan_prop_s_ab: if (have_snan) { @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, * return the NaN with the positive sign bit (if any). */ if (is_snan(a->cls)) { - if (is_snan(b->cls)) { - which = cmp > 0 ? 0 : 1; - } else { + if (!is_snan(b->cls)) { which = is_qnan(b->cls) ? 1 : 0; + break; } } else if (is_qnan(a->cls)) { if (is_snan(b->cls) || !is_qnan(b->cls)) { which = 0; - } else { - which = cmp > 0 ? 0 : 1; + break; } } else { which = 1; + break; } + cmp = frac_cmp(a, b); + if (cmp == 0) { + cmp = a->sign < b->sign; + } + which = cmp > 0 ? 0 : 1; break; default: g_assert_not_reached(); -- 2.34.1 From: Richard Henderson <richard.henderson@linaro.org> Replace the "index" selecting between A and B with a result variable of the proper type. This improves clarity within the function. Signed-off-by: Richard Henderson <richard.henderson@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241203203949.483774-12-richard.henderson@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- fpu/softfloat-parts.c.inc | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) diff --git a/fpu/softfloat-parts.c.inc b/fpu/softfloat-parts.c.inc index XXXXXXX..XXXXXXX 100644 --- a/fpu/softfloat-parts.c.inc +++ b/fpu/softfloat-parts.c.inc @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, float_status *s) { bool have_snan = false; - int cmp, which; + FloatPartsN *ret; + int cmp; if (is_snan(a->cls) || is_snan(b->cls)) { float_raise(float_flag_invalid | float_flag_invalid_snan, s); @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, switch (s->float_2nan_prop_rule) { case float_2nan_prop_s_ab: if (have_snan) { - which = is_snan(a->cls) ? 0 : 1; + ret = is_snan(a->cls) ? a : b; break; } /* fall through */ case float_2nan_prop_ab: - which = is_nan(a->cls) ? 0 : 1; + ret = is_nan(a->cls) ? a : b; break; case float_2nan_prop_s_ba: if (have_snan) { - which = is_snan(b->cls) ? 1 : 0; + ret = is_snan(b->cls) ? b : a; break; } /* fall through */ case float_2nan_prop_ba: - which = is_nan(b->cls) ? 1 : 0; + ret = is_nan(b->cls) ? b : a; break; case float_2nan_prop_x87: /* @@ -XXX,XX +XXX,XX @@ static FloatPartsN *partsN(pick_nan)(FloatPartsN *a, FloatPartsN *b, */ if (is_snan(a->cls)) { if (!is_snan(b->cls)) { - which = is_qnan(b->cls) ? 1 : 0; + ret = is_qnan(b->cls) ? b : a; break; } } else if (is_qnan(a->cls)) { if (is_snan(b->cls) || !is_qnan(b->cls)) { - which = 0; + ret = a; break; } } else { - which = 1; + ret = b; break; } cmp = frac_cmp(a, b); if (cmp == 0) { cmp = a->sign < b->sign; } - which = cmp > 0 ? 0 : 1; + ret = cmp > 0 ? a : b; break; default: g_assert_not_reached(); } - if (which) { - a = b; + if (is_snan(ret->cls)) { + parts_silence_nan(ret, s); } - if (is_snan(a->cls)) { - parts_silence_nan(a, s); - } - return a; + return ret; } static FloatPartsN *partsN(pick_nan_muladd)(FloatPartsN *a, FloatPartsN *b, -- 2.34.1 From: Leif Lindholm <quic_llindhol@quicinc.com> I'm migrating to Qualcomm's new open source email infrastructure, so update my email address, and update the mailmap to match. Signed-off-by: Leif Lindholm <leif.lindholm@oss.qualcomm.com> Reviewed-by: Leif Lindholm <quic_llindhol@quicinc.com> Reviewed-by: Brian Cain <brian.cain@oss.qualcomm.com> Reviewed-by: Philippe Mathieu-Daudé <philmd@linaro.org> Tested-by: Philippe Mathieu-Daudé <philmd@linaro.org> Message-id: 20241205114047.1125842-1-leif.lindholm@oss.qualcomm.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 2 +- .mailmap | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: include/hw/ssi/imx_spi.h SBSA-REF M: Radoslaw Biernacki <rad@semihalf.com> M: Peter Maydell <peter.maydell@linaro.org> -R: Leif Lindholm <quic_llindhol@quicinc.com> +R: Leif Lindholm <leif.lindholm@oss.qualcomm.com> R: Marcin Juszkiewicz <marcin.juszkiewicz@linaro.org> L: qemu-arm@nongnu.org S: Maintained diff --git a/.mailmap b/.mailmap index XXXXXXX..XXXXXXX 100644 --- a/.mailmap +++ b/.mailmap @@ -XXX,XX +XXX,XX @@ Huacai Chen <chenhuacai@kernel.org> <chenhc@lemote.com> Huacai Chen <chenhuacai@kernel.org> <chenhuacai@loongson.cn> James Hogan <jhogan@kernel.org> <james.hogan@imgtec.com> Juan Quintela <quintela@trasno.org> <quintela@redhat.com> -Leif Lindholm <quic_llindhol@quicinc.com> <leif.lindholm@linaro.org> -Leif Lindholm <quic_llindhol@quicinc.com> <leif@nuviainc.com> +Leif Lindholm <leif.lindholm@oss.qualcomm.com> <quic_llindhol@quicinc.com> +Leif Lindholm <leif.lindholm@oss.qualcomm.com> <leif.lindholm@linaro.org> +Leif Lindholm <leif.lindholm@oss.qualcomm.com> <leif@nuviainc.com> Luc Michel <luc@lmichel.fr> <luc.michel@git.antfield.fr> Luc Michel <luc@lmichel.fr> <luc.michel@greensocs.com> Luc Michel <luc@lmichel.fr> <lmichel@kalray.eu> -- 2.34.1 From: Vikram Garhwal <vikram.garhwal@bytedance.com> Previously, maintainer role was paused due to inactive email id. Commit id: c009d715721861984c4987bcc78b7ee183e86d75. Signed-off-by: Vikram Garhwal <vikram.garhwal@bytedance.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@amd.com> Message-id: 20241204184205.12952-1-vikram.garhwal@bytedance.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 2 ++ 1 file changed, 2 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: tests/qtest/fuzz-sb16-test.c Xilinx CAN M: Francisco Iglesias <francisco.iglesias@amd.com> +M: Vikram Garhwal <vikram.garhwal@bytedance.com> S: Maintained F: hw/net/can/xlnx-* F: include/hw/net/xlnx-* @@ -XXX,XX +XXX,XX @@ F: include/hw/rx/ CAN bus subsystem and hardware M: Pavel Pisa <pisa@cmp.felk.cvut.cz> M: Francisco Iglesias <francisco.iglesias@amd.com> +M: Vikram Garhwal <vikram.garhwal@bytedance.com> S: Maintained W: https://canbus.pages.fel.cvut.cz/ F: net/can/* -- 2.34.1