A grab-bag of minor stuff for the end of the year. My to-review queue is not empty, but it it at least in single figures... -- PMM The following changes since commit 5bfbd8170ce7acb98a1834ff49ed7340b0837144: Merge remote-tracking branch 'remotes/vivier2/tags/trivial-branch-for-6.0-pull-request' into staging (2020-12-14 20:32:38 +0000) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20201215 for you to fetch changes up to 23af268566069183285bebbdf95b1b37cb7c0942: hw/block/m25p80: Fix Numonyx fast read dummy cycle count (2020-12-15 13:39:30 +0000) ---------------------------------------------------------------- target-arm queue: * gdbstub: Correct misparsing of vCont C/S requests * openrisc: Move pic_cpu code into CPU object proper * nios2: Move IIC code into CPU object proper * Improve reporting of ROM overlap errors * xlnx-versal: Add USB support * hw/misc/zynq_slcr: Avoid #DIV/0! error * Numonyx: Fix dummy cycles and check for SPI mode on cmds ---------------------------------------------------------------- Joe Komlodi (4): hw/block/m25p80: Make Numonyx config field names more accurate hw/block/m25p80: Fix when VCFG XIP bit is set for Numonyx hw/block/m25p80: Check SPI mode before running some Numonyx commands hw/block/m25p80: Fix Numonyx fast read dummy cycle count Peter Maydell (11): gdbstub: Correct misparsing of vCont C/S requests hw/openrisc/openrisc_sim: Use IRQ splitter when connecting IRQ to multiple CPUs hw/openrisc/openrisc_sim: Abstract out "get IRQ x of CPU y" target/openrisc: Move pic_cpu code into CPU object proper target/nios2: Move IIC code into CPU object proper target/nios2: Move nios2_check_interrupts() into target/nios2 target/nios2: Use deposit32() to update ipending register hw/core/loader.c: Track last-seen ROM in rom_check_and_register_reset() hw/core/loader.c: Improve reporting of ROM overlap errors elf_ops.h: Don't truncate name of the ROM blobs we create elf_ops.h: Be more verbose with ROM blob names Philippe Mathieu-Daudé (1): hw/misc/zynq_slcr: Avoid #DIV/0! error Sai Pavan Boddu (2): usb: Add versal-usb2-ctrl-regs module usb: xlnx-usb-subsystem: Add xilinx usb subsystem Vikram Garhwal (2): usb: Add DWC3 model arm: xlnx-versal: Connect usb to virt-versal include/hw/arm/xlnx-versal.h | 9 + include/hw/elf_ops.h | 5 +- include/hw/usb/hcd-dwc3.h | 55 +++ include/hw/usb/xlnx-usb-subsystem.h | 45 ++ include/hw/usb/xlnx-versal-usb2-ctrl-regs.h | 45 ++ target/nios2/cpu.h | 3 - target/openrisc/cpu.h | 1 - gdbstub.c | 2 +- hw/arm/xlnx-versal-virt.c | 55 +++ hw/arm/xlnx-versal.c | 26 ++ hw/block/m25p80.c | 158 +++++-- hw/core/loader.c | 67 ++- hw/intc/nios2_iic.c | 95 ---- hw/misc/zynq_slcr.c | 5 + hw/nios2/10m50_devboard.c | 13 +- hw/nios2/cpu_pic.c | 67 --- hw/openrisc/openrisc_sim.c | 46 +- hw/openrisc/pic_cpu.c | 61 --- hw/usb/hcd-dwc3.c | 689 ++++++++++++++++++++++++++++ hw/usb/xlnx-usb-subsystem.c | 94 ++++ hw/usb/xlnx-versal-usb2-ctrl-regs.c | 229 +++++++++ softmmu/vl.c | 1 - target/nios2/cpu.c | 29 ++ target/nios2/op_helper.c | 9 + target/openrisc/cpu.c | 32 ++ MAINTAINERS | 1 - hw/intc/meson.build | 1 - hw/nios2/meson.build | 2 +- hw/openrisc/Kconfig | 1 + hw/openrisc/meson.build | 2 +- hw/usb/Kconfig | 10 + hw/usb/meson.build | 3 + 32 files changed, 1557 insertions(+), 304 deletions(-) create mode 100644 include/hw/usb/hcd-dwc3.h create mode 100644 include/hw/usb/xlnx-usb-subsystem.h create mode 100644 include/hw/usb/xlnx-versal-usb2-ctrl-regs.h delete mode 100644 hw/intc/nios2_iic.c delete mode 100644 hw/nios2/cpu_pic.c delete mode 100644 hw/openrisc/pic_cpu.c create mode 100644 hw/usb/hcd-dwc3.c create mode 100644 hw/usb/xlnx-usb-subsystem.c create mode 100644 hw/usb/xlnx-versal-usb2-ctrl-regs.c In the vCont packet, two of the command actions (C and S) take an argument specifying the signal to be sent to the process/thread, which is sent as an ASCII string of two hex digits which immediately follow the 'C' or 'S' character. Our code for parsing this packet accidentally skipped the first of the two bytes of the signal value, because it started parsing the hex string at 'p + 1' when the preceding code had already moved past the 'C' or 'S' with "cur_action = *p++". This meant that we would only do the right thing for signals below 10, and would misinterpret the rest. For instance, when the debugger wants to send the process a SIGPROF (27 on x86-64) we mangle this into a SIGSEGV (11). Remove the accidental double increment. Fixes: https://bugs.launchpad.net/qemu/+bug/1773743 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <philmd@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20201121210342.10089-1-peter.maydell@linaro.org --- gdbstub.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/gdbstub.c b/gdbstub.c index XXXXXXX..XXXXXXX 100644 --- a/gdbstub.c +++ b/gdbstub.c @@ -XXX,XX +XXX,XX @@ static int gdb_handle_vcont(const char *p) cur_action = *p++; if (cur_action == 'C' || cur_action == 'S') { cur_action = qemu_tolower(cur_action); - res = qemu_strtoul(p + 1, &p, 16, &tmp); + res = qemu_strtoul(p, &p, 16, &tmp); if (res) { goto out; } -- 2.20.1 openrisc_sim_net_init() attempts to connect the IRQ line from the ethernet device to both CPUs in an SMP configuration by simply caling sysbus_connect_irq() for it twice. This doesn't work, because the second connection simply overrides the first. Fix this by creating a TYPE_SPLIT_IRQ to split the IRQ in the SMP case. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Stafford Horne <shorne@gmail.com> Message-id: 20201127225127.14770-2-peter.maydell@linaro.org --- hw/openrisc/openrisc_sim.c | 13 +++++++++++-- hw/openrisc/Kconfig | 1 + 2 files changed, 12 insertions(+), 2 deletions(-) diff --git a/hw/openrisc/openrisc_sim.c b/hw/openrisc/openrisc_sim.c index XXXXXXX..XXXXXXX 100644 --- a/hw/openrisc/openrisc_sim.c +++ b/hw/openrisc/openrisc_sim.c @@ -XXX,XX +XXX,XX @@ #include "hw/sysbus.h" #include "sysemu/qtest.h" #include "sysemu/reset.h" +#include "hw/core/split-irq.h" #define KERNEL_LOAD_ADDR 0x100 @@ -XXX,XX +XXX,XX @@ static void openrisc_sim_net_init(hwaddr base, hwaddr descriptors, s = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(s, &error_fatal); - for (i = 0; i < num_cpus; i++) { - sysbus_connect_irq(s, 0, cpu_irqs[i][irq_pin]); + if (num_cpus > 1) { + DeviceState *splitter = qdev_new(TYPE_SPLIT_IRQ); + qdev_prop_set_uint32(splitter, "num-lines", num_cpus); + qdev_realize_and_unref(splitter, NULL, &error_fatal); + for (i = 0; i < num_cpus; i++) { + qdev_connect_gpio_out(splitter, i, cpu_irqs[i][irq_pin]); + } + sysbus_connect_irq(s, 0, qdev_get_gpio_in(splitter, 0)); + } else { + sysbus_connect_irq(s, 0, cpu_irqs[0][irq_pin]); } sysbus_mmio_map(s, 0, base); sysbus_mmio_map(s, 1, descriptors); diff --git a/hw/openrisc/Kconfig b/hw/openrisc/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/openrisc/Kconfig +++ b/hw/openrisc/Kconfig @@ -XXX,XX +XXX,XX @@ config OR1K_SIM select SERIAL select OPENCORES_ETH select OMPIC + select SPLIT_IRQ -- 2.20.1 We're about to refactor the OpenRISC pic_cpu code in a way that means that just grabbing the whole qemu_irq[] array of inbound IRQs for a CPU won't be possible any more. Abstract out a function for "return the qemu_irq for IRQ x input of CPU y" so we can more easily replace the implementation. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Stafford Horne <shorne@gmail.com> Message-id: 20201127225127.14770-3-peter.maydell@linaro.org --- hw/openrisc/openrisc_sim.c | 38 +++++++++++++++++++++----------------- 1 file changed, 21 insertions(+), 17 deletions(-) diff --git a/hw/openrisc/openrisc_sim.c b/hw/openrisc/openrisc_sim.c index XXXXXXX..XXXXXXX 100644 --- a/hw/openrisc/openrisc_sim.c +++ b/hw/openrisc/openrisc_sim.c @@ -XXX,XX +XXX,XX @@ static void main_cpu_reset(void *opaque) cpu_set_pc(cs, boot_info.bootstrap_pc); } +static qemu_irq get_cpu_irq(OpenRISCCPU *cpus[], int cpunum, int irq_pin) +{ + return cpus[cpunum]->env.irq[irq_pin]; +} + static void openrisc_sim_net_init(hwaddr base, hwaddr descriptors, - int num_cpus, qemu_irq **cpu_irqs, + int num_cpus, OpenRISCCPU *cpus[], int irq_pin, NICInfo *nd) { DeviceState *dev; @@ -XXX,XX +XXX,XX @@ static void openrisc_sim_net_init(hwaddr base, hwaddr descriptors, qdev_prop_set_uint32(splitter, "num-lines", num_cpus); qdev_realize_and_unref(splitter, NULL, &error_fatal); for (i = 0; i < num_cpus; i++) { - qdev_connect_gpio_out(splitter, i, cpu_irqs[i][irq_pin]); + qdev_connect_gpio_out(splitter, i, get_cpu_irq(cpus, i, irq_pin)); } sysbus_connect_irq(s, 0, qdev_get_gpio_in(splitter, 0)); } else { - sysbus_connect_irq(s, 0, cpu_irqs[0][irq_pin]); + sysbus_connect_irq(s, 0, get_cpu_irq(cpus, 0, irq_pin)); } sysbus_mmio_map(s, 0, base); sysbus_mmio_map(s, 1, descriptors); } static void openrisc_sim_ompic_init(hwaddr base, int num_cpus, - qemu_irq **cpu_irqs, int irq_pin) + OpenRISCCPU *cpus[], int irq_pin) { DeviceState *dev; SysBusDevice *s; @@ -XXX,XX +XXX,XX @@ static void openrisc_sim_ompic_init(hwaddr base, int num_cpus, s = SYS_BUS_DEVICE(dev); sysbus_realize_and_unref(s, &error_fatal); for (i = 0; i < num_cpus; i++) { - sysbus_connect_irq(s, i, cpu_irqs[i][irq_pin]); + sysbus_connect_irq(s, i, get_cpu_irq(cpus, i, irq_pin)); } sysbus_mmio_map(s, 0, base); } @@ -XXX,XX +XXX,XX @@ static void openrisc_sim_init(MachineState *machine) { ram_addr_t ram_size = machine->ram_size; const char *kernel_filename = machine->kernel_filename; - OpenRISCCPU *cpu = NULL; + OpenRISCCPU *cpus[2] = {}; MemoryRegion *ram; - qemu_irq *cpu_irqs[2]; qemu_irq serial_irq; int n; unsigned int smp_cpus = machine->smp.cpus; assert(smp_cpus >= 1 && smp_cpus <= 2); for (n = 0; n < smp_cpus; n++) { - cpu = OPENRISC_CPU(cpu_create(machine->cpu_type)); - if (cpu == NULL) { + cpus[n] = OPENRISC_CPU(cpu_create(machine->cpu_type)); + if (cpus[n] == NULL) { fprintf(stderr, "Unable to find CPU definition!\n"); exit(1); } - cpu_openrisc_pic_init(cpu); - cpu_irqs[n] = (qemu_irq *) cpu->env.irq; + cpu_openrisc_pic_init(cpus[n]); - cpu_openrisc_clock_init(cpu); + cpu_openrisc_clock_init(cpus[n]); - qemu_register_reset(main_cpu_reset, cpu); + qemu_register_reset(main_cpu_reset, cpus[n]); } ram = g_malloc(sizeof(*ram)); @@ -XXX,XX +XXX,XX @@ static void openrisc_sim_init(MachineState *machine) if (nd_table[0].used) { openrisc_sim_net_init(0x92000000, 0x92000400, smp_cpus, - cpu_irqs, 4, nd_table); + cpus, 4, nd_table); } if (smp_cpus > 1) { - openrisc_sim_ompic_init(0x98000000, smp_cpus, cpu_irqs, 1); + openrisc_sim_ompic_init(0x98000000, smp_cpus, cpus, 1); - serial_irq = qemu_irq_split(cpu_irqs[0][2], cpu_irqs[1][2]); + serial_irq = qemu_irq_split(get_cpu_irq(cpus, 0, 2), + get_cpu_irq(cpus, 1, 2)); } else { - serial_irq = cpu_irqs[0][2]; + serial_irq = get_cpu_irq(cpus, 0, 2); } serial_mm_init(get_system_memory(), 0x90000000, 0, serial_irq, -- 2.20.1 The openrisc code uses an old style of interrupt handling, where a separate standalone set of qemu_irqs invoke a function openrisc_pic_cpu_handler() which signals the interrupt to the CPU proper by directly calling cpu_interrupt() and cpu_reset_interrupt(). Because CPU objects now inherit (indirectly) from TYPE_DEVICE, they can have GPIO input lines themselves, and the neater modern way to implement this is to simply have the CPU object itself provide the input IRQ lines. Create GPIO inputs to the OpenRISC CPU object, and make the only user of cpu_openrisc_pic_init() wire up directly to those instead. This allows us to delete the hw/openrisc/pic_cpu.c file entirely. This fixes a trivial memory leak reported by Coverity of the IRQs allocated in cpu_openrisc_pic_init(). Fixes: Coverity CID 1421934 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Stafford Horne <shorne@gmail.com> Message-id: 20201127225127.14770-4-peter.maydell@linaro.org --- target/openrisc/cpu.h | 1 - hw/openrisc/openrisc_sim.c | 3 +- hw/openrisc/pic_cpu.c | 61 -------------------------------------- target/openrisc/cpu.c | 32 ++++++++++++++++++++ hw/openrisc/meson.build | 2 +- 5 files changed, 34 insertions(+), 65 deletions(-) delete mode 100644 hw/openrisc/pic_cpu.c diff --git a/target/openrisc/cpu.h b/target/openrisc/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/openrisc/cpu.h +++ b/target/openrisc/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUOpenRISCState { uint32_t picmr; /* Interrupt mask register */ uint32_t picsr; /* Interrupt contrl register*/ #endif - void *irq[32]; /* Interrupt irq input */ } CPUOpenRISCState; /** diff --git a/hw/openrisc/openrisc_sim.c b/hw/openrisc/openrisc_sim.c index XXXXXXX..XXXXXXX 100644 --- a/hw/openrisc/openrisc_sim.c +++ b/hw/openrisc/openrisc_sim.c @@ -XXX,XX +XXX,XX @@ static void main_cpu_reset(void *opaque) static qemu_irq get_cpu_irq(OpenRISCCPU *cpus[], int cpunum, int irq_pin) { - return cpus[cpunum]->env.irq[irq_pin]; + return qdev_get_gpio_in_named(DEVICE(cpus[cpunum]), "IRQ", irq_pin); } static void openrisc_sim_net_init(hwaddr base, hwaddr descriptors, @@ -XXX,XX +XXX,XX @@ static void openrisc_sim_init(MachineState *machine) fprintf(stderr, "Unable to find CPU definition!\n"); exit(1); } - cpu_openrisc_pic_init(cpus[n]); cpu_openrisc_clock_init(cpus[n]); diff --git a/hw/openrisc/pic_cpu.c b/hw/openrisc/pic_cpu.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/openrisc/pic_cpu.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * OpenRISC Programmable Interrupt Controller support. - * - * Copyright (c) 2011-2012 Jia Liu <proljc@gmail.com> - * Feng Gao <gf91597@gmail.com> - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see <http://www.gnu.org/licenses/>. - */ - -#include "qemu/osdep.h" -#include "hw/irq.h" -#include "cpu.h" - -/* OpenRISC pic handler */ -static void openrisc_pic_cpu_handler(void *opaque, int irq, int level) -{ - OpenRISCCPU *cpu = (OpenRISCCPU *)opaque; - CPUState *cs = CPU(cpu); - uint32_t irq_bit; - - if (irq > 31 || irq < 0) { - return; - } - - irq_bit = 1U << irq; - - if (level) { - cpu->env.picsr |= irq_bit; - } else { - cpu->env.picsr &= ~irq_bit; - } - - if (cpu->env.picsr & cpu->env.picmr) { - cpu_interrupt(cs, CPU_INTERRUPT_HARD); - } else { - cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); - cpu->env.picsr = 0; - } -} - -void cpu_openrisc_pic_init(OpenRISCCPU *cpu) -{ - int i; - qemu_irq *qi; - qi = qemu_allocate_irqs(openrisc_pic_cpu_handler, cpu, NR_IRQS); - - for (i = 0; i < NR_IRQS; i++) { - cpu->env.irq[i] = qi[i]; - } -} 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(DeviceState *dev) #endif } +#ifndef CONFIG_USER_ONLY +static void openrisc_cpu_set_irq(void *opaque, int irq, int level) +{ + OpenRISCCPU *cpu = (OpenRISCCPU *)opaque; + CPUState *cs = CPU(cpu); + uint32_t irq_bit; + + if (irq > 31 || irq < 0) { + return; + } + + irq_bit = 1U << irq; + + if (level) { + cpu->env.picsr |= irq_bit; + } else { + cpu->env.picsr &= ~irq_bit; + } + + if (cpu->env.picsr & cpu->env.picmr) { + cpu_interrupt(cs, CPU_INTERRUPT_HARD); + } else { + cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); + cpu->env.picsr = 0; + } +} +#endif + static void openrisc_cpu_realizefn(DeviceState *dev, Error **errp) { CPUState *cs = CPU(dev); @@ -XXX,XX +XXX,XX @@ static void openrisc_cpu_initfn(Object *obj) OpenRISCCPU *cpu = OPENRISC_CPU(obj); cpu_set_cpustate_pointers(cpu); + +#ifndef CONFIG_USER_ONLY + qdev_init_gpio_in_named(DEVICE(cpu), openrisc_cpu_set_irq, "IRQ", NR_IRQS); +#endif } /* CPU models */ diff --git a/hw/openrisc/meson.build b/hw/openrisc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/openrisc/meson.build +++ b/hw/openrisc/meson.build @@ -XXX,XX +XXX,XX @@ openrisc_ss = ss.source_set() -openrisc_ss.add(files('pic_cpu.c', 'cputimer.c')) +openrisc_ss.add(files('cputimer.c')) openrisc_ss.add(when: 'CONFIG_OR1K_SIM', if_true: files('openrisc_sim.c')) hw_arch += {'openrisc': openrisc_ss} -- 2.20.1 The Nios2 architecture supports two different interrupt controller options: * The IIC (Internal Interrupt Controller) is part of the CPU itself; it has 32 IRQ input lines and no NMI support. Interrupt status is queried and controlled via the CPU's ipending and istatus registers. * The EIC (External Interrupt Controller) interface allows the CPU to connect to an external interrupt controller. The interface allows the interrupt controller to present a packet of information containing: - handler address - interrupt level - register set - NMI mode QEMU does not model an EIC currently. We do model the IIC, but its implementation is split across code in hw/nios2/cpu_pic.c and hw/intc/nios2_iic.c. The code in those two files has no state of its own -- the IIC state is in the Nios2CPU state struct. Because CPU objects now inherit (indirectly) from TYPE_DEVICE, they can have GPIO input lines themselves, so we can implement the IIC directly in the CPU object the same way that real hardware does. Create named "IRQ" GPIO inputs to the Nios2 CPU object, and make the only user of the IIC wire up directly to those instead. Note that the old code had an "NMI" concept which was entirely unused and also as far as I can see not architecturally correct, since only the EIC has a concept of an NMI. This fixes a Coverity-reported trivial memory leak of the IRQ array allocated in nios2_cpu_pic_init(). Fixes: Coverity CID 1421916 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20201129174022.26530-2-peter.maydell@linaro.org Reviewed-by: Wentong Wu <wentong.wu@intel.com> Tested-by: Wentong Wu <wentong.wu@intel.com> --- target/nios2/cpu.h | 1 - hw/intc/nios2_iic.c | 95 --------------------------------------- hw/nios2/10m50_devboard.c | 13 +----- hw/nios2/cpu_pic.c | 31 ------------- target/nios2/cpu.c | 30 +++++++++++++ MAINTAINERS | 1 - hw/intc/meson.build | 1 - 7 files changed, 32 insertions(+), 140 deletions(-) delete mode 100644 hw/intc/nios2_iic.c diff --git a/target/nios2/cpu.h b/target/nios2/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/nios2/cpu.h +++ b/target/nios2/cpu.h @@ -XXX,XX +XXX,XX @@ void nios2_cpu_do_unaligned_access(CPUState *cpu, vaddr addr, MMUAccessType access_type, int mmu_idx, uintptr_t retaddr); -qemu_irq *nios2_cpu_pic_init(Nios2CPU *cpu); void nios2_check_interrupts(CPUNios2State *env); void do_nios2_semihosting(CPUNios2State *env); diff --git a/hw/intc/nios2_iic.c b/hw/intc/nios2_iic.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/intc/nios2_iic.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * QEMU Altera Internal Interrupt Controller. - * - * Copyright (c) 2012 Chris Wulff <crwulff@gmail.com> - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see - * <http://www.gnu.org/licenses/lgpl-2.1.html> - */ - -#include "qemu/osdep.h" -#include "qemu/module.h" -#include "qapi/error.h" - -#include "hw/irq.h" -#include "hw/sysbus.h" -#include "cpu.h" -#include "qom/object.h" - -#define TYPE_ALTERA_IIC "altera,iic" -OBJECT_DECLARE_SIMPLE_TYPE(AlteraIIC, ALTERA_IIC) - -struct AlteraIIC { - SysBusDevice parent_obj; - void *cpu; - qemu_irq parent_irq; -}; - -static void update_irq(AlteraIIC *pv) -{ - CPUNios2State *env = &((Nios2CPU *)(pv->cpu))->env; - - qemu_set_irq(pv->parent_irq, - env->regs[CR_IPENDING] & env->regs[CR_IENABLE]); -} - -static void irq_handler(void *opaque, int irq, int level) -{ - AlteraIIC *pv = opaque; - CPUNios2State *env = &((Nios2CPU *)(pv->cpu))->env; - - env->regs[CR_IPENDING] &= ~(1 << irq); - env->regs[CR_IPENDING] |= !!level << irq; - - update_irq(pv); -} - -static void altera_iic_init(Object *obj) -{ - AlteraIIC *pv = ALTERA_IIC(obj); - - qdev_init_gpio_in(DEVICE(pv), irq_handler, 32); - sysbus_init_irq(SYS_BUS_DEVICE(obj), &pv->parent_irq); -} - -static void altera_iic_realize(DeviceState *dev, Error **errp) -{ - struct AlteraIIC *pv = ALTERA_IIC(dev); - - pv->cpu = object_property_get_link(OBJECT(dev), "cpu", &error_abort); -} - -static void altera_iic_class_init(ObjectClass *klass, void *data) -{ - DeviceClass *dc = DEVICE_CLASS(klass); - - /* Reason: needs to be wired up, e.g. by nios2_10m50_ghrd_init() */ - dc->user_creatable = false; - dc->realize = altera_iic_realize; -} - -static TypeInfo altera_iic_info = { - .name = TYPE_ALTERA_IIC, - .parent = TYPE_SYS_BUS_DEVICE, - .instance_size = sizeof(AlteraIIC), - .instance_init = altera_iic_init, - .class_init = altera_iic_class_init, -}; - -static void altera_iic_register(void) -{ - type_register_static(&altera_iic_info); -} - -type_init(altera_iic_register) diff --git a/hw/nios2/10m50_devboard.c b/hw/nios2/10m50_devboard.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nios2/10m50_devboard.c +++ b/hw/nios2/10m50_devboard.c @@ -XXX,XX +XXX,XX @@ static void nios2_10m50_ghrd_init(MachineState *machine) ram_addr_t tcm_size = 0x1000; /* 1 kiB, but QEMU limit is 4 kiB */ ram_addr_t ram_base = 0x08000000; ram_addr_t ram_size = 0x08000000; - qemu_irq *cpu_irq, irq[32]; + qemu_irq irq[32]; int i; /* Physical TCM (tb_ram_1k) with alias at 0xc0000000 */ @@ -XXX,XX +XXX,XX @@ static void nios2_10m50_ghrd_init(MachineState *machine) /* Create CPU -- FIXME */ cpu = NIOS2_CPU(cpu_create(TYPE_NIOS2_CPU)); - - /* Register: CPU interrupt controller (PIC) */ - cpu_irq = nios2_cpu_pic_init(cpu); - - /* Register: Internal Interrupt Controller (IIC) */ - dev = qdev_new("altera,iic"); - object_property_add_const_link(OBJECT(dev), "cpu", OBJECT(cpu)); - sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, cpu_irq[0]); for (i = 0; i < 32; i++) { - irq[i] = qdev_get_gpio_in(dev, i); + irq[i] = qdev_get_gpio_in_named(DEVICE(cpu), "IRQ", i); } /* Register: Altera 16550 UART */ diff --git a/hw/nios2/cpu_pic.c b/hw/nios2/cpu_pic.c index XXXXXXX..XXXXXXX 100644 --- a/hw/nios2/cpu_pic.c +++ b/hw/nios2/cpu_pic.c @@ -XXX,XX +XXX,XX @@ #include "boot.h" -static void nios2_pic_cpu_handler(void *opaque, int irq, int level) -{ - Nios2CPU *cpu = opaque; - CPUNios2State *env = &cpu->env; - CPUState *cs = CPU(cpu); - int type = irq ? CPU_INTERRUPT_NMI : CPU_INTERRUPT_HARD; - - if (type == CPU_INTERRUPT_HARD) { - env->irq_pending = level; - - if (level && (env->regs[CR_STATUS] & CR_STATUS_PIE)) { - env->irq_pending = 0; - cpu_interrupt(cs, type); - } else if (!level) { - env->irq_pending = 0; - cpu_reset_interrupt(cs, type); - } - } else { - if (level) { - cpu_interrupt(cs, type); - } else { - cpu_reset_interrupt(cs, type); - } - } -} - void nios2_check_interrupts(CPUNios2State *env) { if (env->irq_pending && @@ -XXX,XX +XXX,XX @@ void nios2_check_interrupts(CPUNios2State *env) cpu_interrupt(env_cpu(env), CPU_INTERRUPT_HARD); } } - -qemu_irq *nios2_cpu_pic_init(Nios2CPU *cpu) -{ - return qemu_allocate_irqs(nios2_pic_cpu_handler, cpu, 2); -} diff --git a/target/nios2/cpu.c b/target/nios2/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/nios2/cpu.c +++ b/target/nios2/cpu.c @@ -XXX,XX +XXX,XX @@ static void nios2_cpu_reset(DeviceState *dev) #endif } +#ifndef CONFIG_USER_ONLY +static void nios2_cpu_set_irq(void *opaque, int irq, int level) +{ + Nios2CPU *cpu = opaque; + CPUNios2State *env = &cpu->env; + CPUState *cs = CPU(cpu); + + env->regs[CR_IPENDING] &= ~(1 << irq); + env->regs[CR_IPENDING] |= !!level << irq; + + env->irq_pending = env->regs[CR_IPENDING] & env->regs[CR_IENABLE]; + + if (env->irq_pending && (env->regs[CR_STATUS] & CR_STATUS_PIE)) { + env->irq_pending = 0; + cpu_interrupt(cs, CPU_INTERRUPT_HARD); + } else if (!env->irq_pending) { + cpu_reset_interrupt(cs, CPU_INTERRUPT_HARD); + } +} +#endif + static void nios2_cpu_initfn(Object *obj) { Nios2CPU *cpu = NIOS2_CPU(obj); @@ -XXX,XX +XXX,XX @@ static void nios2_cpu_initfn(Object *obj) #if !defined(CONFIG_USER_ONLY) mmu_init(&cpu->env); + + /* + * These interrupt lines model the IIC (internal interrupt + * controller). QEMU does not currently support the EIC + * (external interrupt controller) -- if we did it would be + * a separate device in hw/intc with a custom interface to + * the CPU, and boards using it would not wire up these IRQ lines. + */ + qdev_init_gpio_in_named(DEVICE(cpu), nios2_cpu_set_irq, "IRQ", 32); #endif } diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ M: Marek Vasut <marex@denx.de> S: Maintained F: target/nios2/ F: hw/nios2/ -F: hw/intc/nios2_iic.c F: disas/nios2.c F: default-configs/nios2-softmmu.mak diff --git a/hw/intc/meson.build b/hw/intc/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/intc/meson.build +++ b/hw/intc/meson.build @@ -XXX,XX +XXX,XX @@ specific_ss.add(when: 'CONFIG_IBEX', if_true: files('ibex_plic.c')) specific_ss.add(when: 'CONFIG_IOAPIC', if_true: files('ioapic.c')) specific_ss.add(when: 'CONFIG_LOONGSON_LIOINTC', if_true: files('loongson_liointc.c')) specific_ss.add(when: 'CONFIG_MIPS_CPS', if_true: files('mips_gic.c')) -specific_ss.add(when: 'CONFIG_NIOS2', if_true: files('nios2_iic.c')) specific_ss.add(when: 'CONFIG_OMAP', if_true: files('omap_intc.c')) specific_ss.add(when: 'CONFIG_OMPIC', if_true: files('ompic.c')) specific_ss.add(when: 'CONFIG_OPENPIC_KVM', if_true: files('openpic_kvm.c')) -- 2.20.1 The function nios2_check_interrupts)() looks only at CPU-internal state; it belongs in target/nios2, not hw/nios2. Move it into the same file as its only caller, so it can just be local to that file. This removes the only remaining code from cpu_pic.c, so we can delete that file entirely. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20201129174022.26530-3-peter.maydell@linaro.org Reviewed-by: Wentong Wu <wentong.wu@intel.com> Tested-by: Wentong Wu <wentong.wu@intel.com> --- target/nios2/cpu.h | 2 -- hw/nios2/cpu_pic.c | 36 ------------------------------------ target/nios2/op_helper.c | 9 +++++++++ hw/nios2/meson.build | 2 +- 4 files changed, 10 insertions(+), 39 deletions(-) delete mode 100644 hw/nios2/cpu_pic.c diff --git a/target/nios2/cpu.h b/target/nios2/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/nios2/cpu.h +++ b/target/nios2/cpu.h @@ -XXX,XX +XXX,XX @@ void nios2_cpu_do_unaligned_access(CPUState *cpu, vaddr addr, MMUAccessType access_type, int mmu_idx, uintptr_t retaddr); -void nios2_check_interrupts(CPUNios2State *env); - void do_nios2_semihosting(CPUNios2State *env); #define CPU_RESOLVING_TYPE TYPE_NIOS2_CPU diff --git a/hw/nios2/cpu_pic.c b/hw/nios2/cpu_pic.c deleted file mode 100644 index XXXXXXX..XXXXXXX --- a/hw/nios2/cpu_pic.c +++ /dev/null @@ -XXX,XX +XXX,XX @@ -/* - * Altera Nios2 CPU PIC - * - * Copyright (c) 2016 Marek Vasut <marek.vasut@gmail.com> - * - * This library is free software; you can redistribute it and/or - * modify it under the terms of the GNU Lesser General Public - * License as published by the Free Software Foundation; either - * version 2.1 of the License, or (at your option) any later version. - * - * This library is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * Lesser General Public License for more details. - * - * You should have received a copy of the GNU Lesser General Public - * License along with this library; if not, see - * <http://www.gnu.org/licenses/lgpl-2.1.html> - */ - -#include "qemu/osdep.h" -#include "cpu.h" -#include "hw/irq.h" - -#include "qemu/config-file.h" - -#include "boot.h" - -void nios2_check_interrupts(CPUNios2State *env) -{ - if (env->irq_pending && - (env->regs[CR_STATUS] & CR_STATUS_PIE)) { - env->irq_pending = 0; - cpu_interrupt(env_cpu(env), CPU_INTERRUPT_HARD); - } -} diff --git a/target/nios2/op_helper.c b/target/nios2/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/nios2/op_helper.c +++ b/target/nios2/op_helper.c @@ -XXX,XX +XXX,XX @@ void helper_mmu_write(CPUNios2State *env, uint32_t rn, uint32_t v) mmu_write(env, rn, v); } +static void nios2_check_interrupts(CPUNios2State *env) +{ + if (env->irq_pending && + (env->regs[CR_STATUS] & CR_STATUS_PIE)) { + env->irq_pending = 0; + cpu_interrupt(env_cpu(env), CPU_INTERRUPT_HARD); + } +} + void helper_check_interrupts(CPUNios2State *env) { qemu_mutex_lock_iothread(); diff --git a/hw/nios2/meson.build b/hw/nios2/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/nios2/meson.build +++ b/hw/nios2/meson.build @@ -XXX,XX +XXX,XX @@ nios2_ss = ss.source_set() -nios2_ss.add(files('boot.c', 'cpu_pic.c')) +nios2_ss.add(files('boot.c')) nios2_ss.add(when: 'CONFIG_NIOS2_10M50', if_true: files('10m50_devboard.c')) nios2_ss.add(when: 'CONFIG_NIOS2_GENERIC_NOMMU', if_true: files('generic_nommu.c')) -- 2.20.1 In nios2_cpu_set_irq(), use deposit32() rather than raw shift-and-mask operations to set the appropriate bit in the ipending register. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Message-id: 20201129174022.26530-4-peter.maydell@linaro.org --- target/nios2/cpu.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/target/nios2/cpu.c b/target/nios2/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/nios2/cpu.c +++ b/target/nios2/cpu.c @@ -XXX,XX +XXX,XX @@ static void nios2_cpu_set_irq(void *opaque, int irq, int level) CPUNios2State *env = &cpu->env; CPUState *cs = CPU(cpu); - env->regs[CR_IPENDING] &= ~(1 << irq); - env->regs[CR_IPENDING] |= !!level << irq; + env->regs[CR_IPENDING] = deposit32(env->regs[CR_IPENDING], irq, 1, !!level); env->irq_pending = env->regs[CR_IPENDING] & env->regs[CR_IENABLE]; -- 2.20.1 In rom_check_and_register_reset() we detect overlaps by looking at whether the ROM blob we're currently examining is in the same address space and starts before the previous ROM blob ends. (This works because the ROM list is kept sorted in order by AddressSpace and then by address.) Instead of keeping the AddressSpace and last address of the previous ROM blob in local variables, just keep a pointer to it. This will allow us to print more useful information when we do detect an overlap. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201129203923.10622-2-peter.maydell@linaro.org --- hw/core/loader.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) diff --git a/hw/core/loader.c b/hw/core/loader.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/loader.c +++ b/hw/core/loader.c @@ -XXX,XX +XXX,XX @@ static void rom_reset(void *unused) } } +/* Return true if two consecutive ROMs in the ROM list overlap */ +static bool roms_overlap(Rom *last_rom, Rom *this_rom) +{ + if (!last_rom) { + return false; + } + return last_rom->as == this_rom->as && + last_rom->addr + last_rom->romsize > this_rom->addr; +} + int rom_check_and_register_reset(void) { - hwaddr addr = 0; MemoryRegionSection section; - Rom *rom; - AddressSpace *as = NULL; + Rom *rom, *last_rom = NULL; QTAILQ_FOREACH(rom, &roms, next) { if (rom->fw_file) { continue; } if (!rom->mr) { - if ((addr > rom->addr) && (as == rom->as)) { + if (roms_overlap(last_rom, rom)) { fprintf(stderr, "rom: requested regions overlap " "(rom %s. free=0x" TARGET_FMT_plx ", addr=0x" TARGET_FMT_plx ")\n", - rom->name, addr, rom->addr); + rom->name, last_rom->addr + last_rom->romsize, + rom->addr); return -1; } - addr = rom->addr; - addr += rom->romsize; - as = rom->as; + last_rom = rom; } section = memory_region_find(rom->mr ? rom->mr : get_system_memory(), rom->addr, 1); -- 2.20.1 In rom_check_and_register_reset() we report to the user if there is a "ROM region overlap". This has a couple of problems: * the reported information is not very easy to intepret * the function just prints the overlap to stderr (and relies on its single callsite in vl.c to do an error_report() and exit) * only the first overlap encountered is diagnosed Make this function use error_report() and error_printf() and report a more user-friendly report with all the overlaps diagnosed. Sample old output: rom: requested regions overlap (rom dtb. free=0x0000000000008000, addr=0x0000000000000000) qemu-system-aarch64: rom check and register reset failed Sample new output: qemu-system-aarch64: Some ROM regions are overlapping These ROM regions might have been loaded by direct user request or by default. They could be BIOS/firmware images, a guest kernel, initrd or some other file loaded into guest memory. Check whether you intended to load all this guest code, and whether it has been built to load to the correct addresses. The following two regions overlap (in the cpu-memory-0 address space): phdr #0: /home/petmay01/linaro/qemu-misc-tests/ldmia-fault.axf (addresses 0x0000000000000000 - 0x0000000000008000) dtb (addresses 0x0000000000000000 - 0x0000000000100000) The following two regions overlap (in the cpu-memory-0 address space): phdr #1: /home/petmay01/linaro/qemu-misc-tests/bad-psci-call.axf (addresses 0x0000000040000000 - 0x0000000040000010) phdr #0: /home/petmay01/linaro/qemu-misc-tests/bp-test.elf (addresses 0x0000000040000000 - 0x0000000040000020) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201129203923.10622-3-peter.maydell@linaro.org --- hw/core/loader.c | 48 ++++++++++++++++++++++++++++++++++++++++++------ softmmu/vl.c | 1 - 2 files changed, 42 insertions(+), 7 deletions(-) diff --git a/hw/core/loader.c b/hw/core/loader.c index XXXXXXX..XXXXXXX 100644 --- a/hw/core/loader.c +++ b/hw/core/loader.c @@ -XXX,XX +XXX,XX @@ static bool roms_overlap(Rom *last_rom, Rom *this_rom) last_rom->addr + last_rom->romsize > this_rom->addr; } +static const char *rom_as_name(Rom *rom) +{ + const char *name = rom->as ? rom->as->name : NULL; + return name ?: "anonymous"; +} + +static void rom_print_overlap_error_header(void) +{ + error_report("Some ROM regions are overlapping"); + error_printf( + "These ROM regions might have been loaded by " + "direct user request or by default.\n" + "They could be BIOS/firmware images, a guest kernel, " + "initrd or some other file loaded into guest memory.\n" + "Check whether you intended to load all this guest code, and " + "whether it has been built to load to the correct addresses.\n"); +} + +static void rom_print_one_overlap_error(Rom *last_rom, Rom *rom) +{ + error_printf( + "\nThe following two regions overlap (in the %s address space):\n", + rom_as_name(rom)); + error_printf( + " %s (addresses 0x" TARGET_FMT_plx " - 0x" TARGET_FMT_plx ")\n", + last_rom->name, last_rom->addr, last_rom->addr + last_rom->romsize); + error_printf( + " %s (addresses 0x" TARGET_FMT_plx " - 0x" TARGET_FMT_plx ")\n", + rom->name, rom->addr, rom->addr + rom->romsize); +} + int rom_check_and_register_reset(void) { MemoryRegionSection section; Rom *rom, *last_rom = NULL; + bool found_overlap = false; QTAILQ_FOREACH(rom, &roms, next) { if (rom->fw_file) { @@ -XXX,XX +XXX,XX @@ int rom_check_and_register_reset(void) } if (!rom->mr) { if (roms_overlap(last_rom, rom)) { - fprintf(stderr, "rom: requested regions overlap " - "(rom %s. free=0x" TARGET_FMT_plx - ", addr=0x" TARGET_FMT_plx ")\n", - rom->name, last_rom->addr + last_rom->romsize, - rom->addr); - return -1; + if (!found_overlap) { + found_overlap = true; + rom_print_overlap_error_header(); + } + rom_print_one_overlap_error(last_rom, rom); + /* Keep going through the list so we report all overlaps */ } last_rom = rom; } @@ -XXX,XX +XXX,XX @@ int rom_check_and_register_reset(void) rom->isrom = int128_nz(section.size) && memory_region_is_rom(section.mr); memory_region_unref(section.mr); } + if (found_overlap) { + return -1; + } + qemu_register_reset(rom_reset, NULL); roms_loaded = 1; return 0; diff --git a/softmmu/vl.c b/softmmu/vl.c index XXXXXXX..XXXXXXX 100644 --- a/softmmu/vl.c +++ b/softmmu/vl.c @@ -XXX,XX +XXX,XX @@ static void qemu_machine_creation_done(void) qemu_run_machine_init_done_notifiers(); if (rom_check_and_register_reset() != 0) { - error_report("rom check and register reset failed"); exit(1); } -- 2.20.1 Currently the load_elf code assembles the ROM blob name into a local 128 byte fixed-size array. Use g_strdup_printf() instead so that we don't truncate the pathname if it happens to be long. (This matters mostly for monitor 'info roms' output and for the error messages if ROM blobs overlap.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201129203923.10622-4-peter.maydell@linaro.org --- include/hw/elf_ops.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/include/hw/elf_ops.h b/include/hw/elf_ops.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/elf_ops.h +++ b/include/hw/elf_ops.h @@ -XXX,XX +XXX,XX @@ static int glue(load_elf, SZ)(const char *name, int fd, uint64_t addr, low = (uint64_t)-1, high = 0; GMappedFile *mapped_file = NULL; uint8_t *data = NULL; - char label[128]; int ret = ELF_LOAD_FAILED; if (read(fd, &ehdr, sizeof(ehdr)) != sizeof(ehdr)) @@ -XXX,XX +XXX,XX @@ static int glue(load_elf, SZ)(const char *name, int fd, */ if (mem_size != 0) { if (load_rom) { - snprintf(label, sizeof(label), "phdr #%d: %s", i, name); + g_autofree char *label = + g_strdup_printf("phdr #%d: %s", i, name); /* * rom_add_elf_program() takes its own reference to -- 2.20.1 Instead of making the ROM blob name something like: phdr #0: /home/petmay01/linaro/qemu-misc-tests/ldmia-fault.axf make it a little more self-explanatory for people who don't know ELF format details: /home/petmay01/linaro/qemu-misc-tests/ldmia-fault.axf ELF program header segment 0 Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20201129203923.10622-5-peter.maydell@linaro.org --- include/hw/elf_ops.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/hw/elf_ops.h b/include/hw/elf_ops.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/elf_ops.h +++ b/include/hw/elf_ops.h @@ -XXX,XX +XXX,XX @@ static int glue(load_elf, SZ)(const char *name, int fd, if (mem_size != 0) { if (load_rom) { g_autofree char *label = - g_strdup_printf("phdr #%d: %s", i, name); + g_strdup_printf("%s ELF program header segment %d", + name, i); /* * rom_add_elf_program() takes its own reference to -- 2.20.1 From: Sai Pavan Boddu <sai.pavan.boddu@xilinx.com> This module emulates control registers of versal usb2 controller, this is added just to make guest happy. In general this module would control the phy-reset signal from usb controller, data coherency of the transactions, signals the host system errors received from controller. Signed-off-by: Sai Pavan Boddu <sai.pavan.boddu@xilinx.com> Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1607023357-5096-2-git-send-email-sai.pavan.boddu@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/usb/xlnx-versal-usb2-ctrl-regs.h | 45 ++++ hw/usb/xlnx-versal-usb2-ctrl-regs.c | 229 ++++++++++++++++++++ hw/usb/meson.build | 1 + 3 files changed, 275 insertions(+) create mode 100644 include/hw/usb/xlnx-versal-usb2-ctrl-regs.h create mode 100644 hw/usb/xlnx-versal-usb2-ctrl-regs.c diff --git a/include/hw/usb/xlnx-versal-usb2-ctrl-regs.h b/include/hw/usb/xlnx-versal-usb2-ctrl-regs.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/usb/xlnx-versal-usb2-ctrl-regs.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the VersalUsb2CtrlRegs Register control/Status block for + * USB2.0 controller + * + * Copyright (c) 2020 Xilinx Inc. Vikram Garhwal <fnu.vikram@xilinx.com> + * + * 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. + */ + +#ifndef _XLNX_USB2_REGS_H_ +#define _XLNX_USB2_REGS_H_ + +#define TYPE_XILINX_VERSAL_USB2_CTRL_REGS "xlnx.versal-usb2-ctrl-regs" + +#define XILINX_VERSAL_USB2_CTRL_REGS(obj) \ + OBJECT_CHECK(VersalUsb2CtrlRegs, (obj), TYPE_XILINX_VERSAL_USB2_CTRL_REGS) + +#define USB2_REGS_R_MAX ((0x78 / 4) + 1) + +typedef struct VersalUsb2CtrlRegs { + SysBusDevice parent_obj; + MemoryRegion iomem; + qemu_irq irq_ir; + + uint32_t regs[USB2_REGS_R_MAX]; + RegisterInfo regs_info[USB2_REGS_R_MAX]; +} VersalUsb2CtrlRegs; + +#endif diff --git a/hw/usb/xlnx-versal-usb2-ctrl-regs.c b/hw/usb/xlnx-versal-usb2-ctrl-regs.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/usb/xlnx-versal-usb2-ctrl-regs.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the VersalUsb2CtrlRegs Register control/Status block for + * USB2.0 controller + * + * This module should control phy_reset, permanent device plugs, frame length + * time adjust & setting of coherency paths. None of which are emulated in + * present model. + * + * Copyright (c) 2020 Xilinx Inc. Vikram Garhwal <fnu.vikram@xilinx.com> + * + * 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 "hw/sysbus.h" +#include "hw/irq.h" +#include "hw/register.h" +#include "qemu/bitops.h" +#include "qemu/log.h" +#include "qom/object.h" +#include "migration/vmstate.h" +#include "hw/usb/xlnx-versal-usb2-ctrl-regs.h" + +#ifndef XILINX_VERSAL_USB2_CTRL_REGS_ERR_DEBUG +#define XILINX_VERSAL_USB2_CTRL_REGS_ERR_DEBUG 0 +#endif + +REG32(BUS_FILTER, 0x30) + FIELD(BUS_FILTER, BYPASS, 0, 4) +REG32(PORT, 0x34) + FIELD(PORT, HOST_SMI_BAR_WR, 4, 1) + FIELD(PORT, HOST_SMI_PCI_CMD_REG_WR, 3, 1) + FIELD(PORT, HOST_MSI_ENABLE, 2, 1) + FIELD(PORT, PWR_CTRL_PRSNT, 1, 1) + FIELD(PORT, HUB_PERM_ATTACH, 0, 1) +REG32(JITTER_ADJUST, 0x38) + FIELD(JITTER_ADJUST, FLADJ, 0, 6) +REG32(BIGENDIAN, 0x40) + FIELD(BIGENDIAN, ENDIAN_GS, 0, 1) +REG32(COHERENCY, 0x44) + FIELD(COHERENCY, USB_COHERENCY, 0, 1) +REG32(XHC_BME, 0x48) + FIELD(XHC_BME, XHC_BME, 0, 1) +REG32(REG_CTRL, 0x60) + FIELD(REG_CTRL, SLVERR_ENABLE, 0, 1) +REG32(IR_STATUS, 0x64) + FIELD(IR_STATUS, HOST_SYS_ERR, 1, 1) + FIELD(IR_STATUS, ADDR_DEC_ERR, 0, 1) +REG32(IR_MASK, 0x68) + FIELD(IR_MASK, HOST_SYS_ERR, 1, 1) + FIELD(IR_MASK, ADDR_DEC_ERR, 0, 1) +REG32(IR_ENABLE, 0x6c) + FIELD(IR_ENABLE, HOST_SYS_ERR, 1, 1) + FIELD(IR_ENABLE, ADDR_DEC_ERR, 0, 1) +REG32(IR_DISABLE, 0x70) + FIELD(IR_DISABLE, HOST_SYS_ERR, 1, 1) + FIELD(IR_DISABLE, ADDR_DEC_ERR, 0, 1) +REG32(USB3, 0x78) + +static void ir_update_irq(VersalUsb2CtrlRegs *s) +{ + bool pending = s->regs[R_IR_STATUS] & ~s->regs[R_IR_MASK]; + qemu_set_irq(s->irq_ir, pending); +} + +static void ir_status_postw(RegisterInfo *reg, uint64_t val64) +{ + VersalUsb2CtrlRegs *s = XILINX_VERSAL_USB2_CTRL_REGS(reg->opaque); + /* + * TODO: This should also clear USBSTS.HSE field in USB XHCI register. + * May be combine both the modules. + */ + ir_update_irq(s); +} + +static uint64_t ir_enable_prew(RegisterInfo *reg, uint64_t val64) +{ + VersalUsb2CtrlRegs *s = XILINX_VERSAL_USB2_CTRL_REGS(reg->opaque); + uint32_t val = val64; + + s->regs[R_IR_MASK] &= ~val; + ir_update_irq(s); + return 0; +} + +static uint64_t ir_disable_prew(RegisterInfo *reg, uint64_t val64) +{ + VersalUsb2CtrlRegs *s = XILINX_VERSAL_USB2_CTRL_REGS(reg->opaque); + uint32_t val = val64; + + s->regs[R_IR_MASK] |= val; + ir_update_irq(s); + return 0; +} + +static const RegisterAccessInfo usb2_ctrl_regs_regs_info[] = { + { .name = "BUS_FILTER", .addr = A_BUS_FILTER, + .rsvd = 0xfffffff0, + },{ .name = "PORT", .addr = A_PORT, + .rsvd = 0xffffffe0, + },{ .name = "JITTER_ADJUST", .addr = A_JITTER_ADJUST, + .reset = 0x20, + .rsvd = 0xffffffc0, + },{ .name = "BIGENDIAN", .addr = A_BIGENDIAN, + .rsvd = 0xfffffffe, + },{ .name = "COHERENCY", .addr = A_COHERENCY, + .rsvd = 0xfffffffe, + },{ .name = "XHC_BME", .addr = A_XHC_BME, + .reset = 0x1, + .rsvd = 0xfffffffe, + },{ .name = "REG_CTRL", .addr = A_REG_CTRL, + .rsvd = 0xfffffffe, + },{ .name = "IR_STATUS", .addr = A_IR_STATUS, + .rsvd = 0xfffffffc, + .w1c = 0x3, + .post_write = ir_status_postw, + },{ .name = "IR_MASK", .addr = A_IR_MASK, + .reset = 0x3, + .rsvd = 0xfffffffc, + .ro = 0x3, + },{ .name = "IR_ENABLE", .addr = A_IR_ENABLE, + .rsvd = 0xfffffffc, + .pre_write = ir_enable_prew, + },{ .name = "IR_DISABLE", .addr = A_IR_DISABLE, + .rsvd = 0xfffffffc, + .pre_write = ir_disable_prew, + },{ .name = "USB3", .addr = A_USB3, + } +}; + +static void usb2_ctrl_regs_reset_init(Object *obj, ResetType type) +{ + VersalUsb2CtrlRegs *s = XILINX_VERSAL_USB2_CTRL_REGS(obj); + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(s->regs_info); ++i) { + register_reset(&s->regs_info[i]); + } +} + +static void usb2_ctrl_regs_reset_hold(Object *obj) +{ + VersalUsb2CtrlRegs *s = XILINX_VERSAL_USB2_CTRL_REGS(obj); + + ir_update_irq(s); +} + +static const MemoryRegionOps usb2_ctrl_regs_ops = { + .read = register_read_memory, + .write = register_write_memory, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void usb2_ctrl_regs_init(Object *obj) +{ + VersalUsb2CtrlRegs *s = XILINX_VERSAL_USB2_CTRL_REGS(obj); + SysBusDevice *sbd = SYS_BUS_DEVICE(obj); + RegisterInfoArray *reg_array; + + memory_region_init(&s->iomem, obj, TYPE_XILINX_VERSAL_USB2_CTRL_REGS, + USB2_REGS_R_MAX * 4); + reg_array = + register_init_block32(DEVICE(obj), usb2_ctrl_regs_regs_info, + ARRAY_SIZE(usb2_ctrl_regs_regs_info), + s->regs_info, s->regs, + &usb2_ctrl_regs_ops, + XILINX_VERSAL_USB2_CTRL_REGS_ERR_DEBUG, + USB2_REGS_R_MAX * 4); + memory_region_add_subregion(&s->iomem, + 0x0, + &reg_array->mem); + sysbus_init_mmio(sbd, &s->iomem); + sysbus_init_irq(sbd, &s->irq_ir); +} + +static const VMStateDescription vmstate_usb2_ctrl_regs = { + .name = TYPE_XILINX_VERSAL_USB2_CTRL_REGS, + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, VersalUsb2CtrlRegs, USB2_REGS_R_MAX), + VMSTATE_END_OF_LIST(), + } +}; + +static void usb2_ctrl_regs_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + ResettableClass *rc = RESETTABLE_CLASS(klass); + + rc->phases.enter = usb2_ctrl_regs_reset_init; + rc->phases.hold = usb2_ctrl_regs_reset_hold; + dc->vmsd = &vmstate_usb2_ctrl_regs; +} + +static const TypeInfo usb2_ctrl_regs_info = { + .name = TYPE_XILINX_VERSAL_USB2_CTRL_REGS, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(VersalUsb2CtrlRegs), + .class_init = usb2_ctrl_regs_class_init, + .instance_init = usb2_ctrl_regs_init, +}; + +static void usb2_ctrl_regs_register_types(void) +{ + type_register_static(&usb2_ctrl_regs_info); +} + +type_init(usb2_ctrl_regs_register_types) diff --git a/hw/usb/meson.build b/hw/usb/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/meson.build +++ b/hw/usb/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_USB_DWC2', if_true: files('hcd-dwc2.c')) softmmu_ss.add(when: 'CONFIG_TUSB6010', if_true: files('tusb6010.c')) softmmu_ss.add(when: 'CONFIG_IMX', if_true: files('chipidea.c')) softmmu_ss.add(when: 'CONFIG_IMX_USBPHY', if_true: files('imx-usb-phy.c')) +specific_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files('xlnx-versal-usb2-ctrl-regs.c')) # emulated usb devices softmmu_ss.add(when: 'CONFIG_USB', if_true: files('dev-hub.c')) -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> This patch adds skeleton model of dwc3 usb controller attached to xhci-sysbus device. It defines global register space of DWC3 controller, global registers control the AXI/AHB interfaces properties, external FIFO support and event count support. All of which are unimplemented at present,we are only supporting core reset and read of ID register. Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Signed-off-by: Sai Pavan Boddu <sai.pavan.boddu@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 1607023357-5096-3-git-send-email-sai.pavan.boddu@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/usb/hcd-dwc3.h | 55 +++ hw/usb/hcd-dwc3.c | 689 ++++++++++++++++++++++++++++++++++++++ hw/usb/Kconfig | 5 + hw/usb/meson.build | 1 + 4 files changed, 750 insertions(+) create mode 100644 include/hw/usb/hcd-dwc3.h create mode 100644 hw/usb/hcd-dwc3.c diff --git a/include/hw/usb/hcd-dwc3.h b/include/hw/usb/hcd-dwc3.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/usb/hcd-dwc3.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the USB DWC3 host controller emulation. + * + * Copyright (c) 2020 Xilinx Inc. + * + * Written by Vikram Garhwal<fnu.vikram@xilinx.com> + * + * 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. + */ +#ifndef HCD_DWC3_H +#define HCD_DWC3_H + +#include "hw/usb/hcd-xhci.h" +#include "hw/usb/hcd-xhci-sysbus.h" + +#define TYPE_USB_DWC3 "usb_dwc3" + +#define USB_DWC3(obj) \ + OBJECT_CHECK(USBDWC3, (obj), TYPE_USB_DWC3) + +#define USB_DWC3_R_MAX ((0x530 / 4) + 1) +#define DWC3_SIZE 0x10000 + +typedef struct USBDWC3 { + SysBusDevice parent_obj; + MemoryRegion iomem; + XHCISysbusState sysbus_xhci; + + uint32_t regs[USB_DWC3_R_MAX]; + RegisterInfo regs_info[USB_DWC3_R_MAX]; + + struct { + uint8_t mode; + uint32_t dwc_usb3_user; + } cfg; + +} USBDWC3; + +#endif diff --git a/hw/usb/hcd-dwc3.c b/hw/usb/hcd-dwc3.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/usb/hcd-dwc3.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the USB DWC3 host controller emulation. + * + * This model defines global register space of DWC3 controller. Global + * registers control the AXI/AHB interfaces properties, external FIFO support + * and event count support. All of which are unimplemented at present. We are + * only supporting core reset and read of ID register. + * + * Copyright (c) 2020 Xilinx Inc. Vikram Garhwal<fnu.vikram@xilinx.com> + * + * 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 "hw/sysbus.h" +#include "hw/register.h" +#include "qemu/bitops.h" +#include "qemu/log.h" +#include "qom/object.h" +#include "migration/vmstate.h" +#include "hw/qdev-properties.h" +#include "hw/usb/hcd-dwc3.h" +#include "qapi/error.h" + +#ifndef USB_DWC3_ERR_DEBUG +#define USB_DWC3_ERR_DEBUG 0 +#endif + +#define HOST_MODE 1 +#define FIFO_LEN 0x1000 + +REG32(GSBUSCFG0, 0x00) + FIELD(GSBUSCFG0, DATRDREQINFO, 28, 4) + FIELD(GSBUSCFG0, DESRDREQINFO, 24, 4) + FIELD(GSBUSCFG0, DATWRREQINFO, 20, 4) + FIELD(GSBUSCFG0, DESWRREQINFO, 16, 4) + FIELD(GSBUSCFG0, RESERVED_15_12, 12, 4) + FIELD(GSBUSCFG0, DATBIGEND, 11, 1) + FIELD(GSBUSCFG0, DESBIGEND, 10, 1) + FIELD(GSBUSCFG0, RESERVED_9_8, 8, 2) + FIELD(GSBUSCFG0, INCR256BRSTENA, 7, 1) + FIELD(GSBUSCFG0, INCR128BRSTENA, 6, 1) + FIELD(GSBUSCFG0, INCR64BRSTENA, 5, 1) + FIELD(GSBUSCFG0, INCR32BRSTENA, 4, 1) + FIELD(GSBUSCFG0, INCR16BRSTENA, 3, 1) + FIELD(GSBUSCFG0, INCR8BRSTENA, 2, 1) + FIELD(GSBUSCFG0, INCR4BRSTENA, 1, 1) + FIELD(GSBUSCFG0, INCRBRSTENA, 0, 1) +REG32(GSBUSCFG1, 0x04) + FIELD(GSBUSCFG1, RESERVED_31_13, 13, 19) + FIELD(GSBUSCFG1, EN1KPAGE, 12, 1) + FIELD(GSBUSCFG1, PIPETRANSLIMIT, 8, 4) + FIELD(GSBUSCFG1, RESERVED_7_0, 0, 8) +REG32(GTXTHRCFG, 0x08) + FIELD(GTXTHRCFG, RESERVED_31, 31, 1) + FIELD(GTXTHRCFG, RESERVED_30, 30, 1) + FIELD(GTXTHRCFG, USBTXPKTCNTSEL, 29, 1) + FIELD(GTXTHRCFG, RESERVED_28, 28, 1) + FIELD(GTXTHRCFG, USBTXPKTCNT, 24, 4) + FIELD(GTXTHRCFG, USBMAXTXBURSTSIZE, 16, 8) + FIELD(GTXTHRCFG, RESERVED_15, 15, 1) + FIELD(GTXTHRCFG, RESERVED_14, 14, 1) + FIELD(GTXTHRCFG, RESERVED_13_11, 11, 3) + FIELD(GTXTHRCFG, RESERVED_10_0, 0, 11) +REG32(GRXTHRCFG, 0x0c) + FIELD(GRXTHRCFG, RESERVED_31_30, 30, 2) + FIELD(GRXTHRCFG, USBRXPKTCNTSEL, 29, 1) + FIELD(GRXTHRCFG, RESERVED_28, 28, 1) + FIELD(GRXTHRCFG, USBRXPKTCNT, 24, 4) + FIELD(GRXTHRCFG, USBMAXRXBURSTSIZE, 19, 5) + FIELD(GRXTHRCFG, RESERVED_18_16, 16, 3) + FIELD(GRXTHRCFG, RESERVED_15, 15, 1) + FIELD(GRXTHRCFG, RESERVED_14_13, 13, 2) + FIELD(GRXTHRCFG, RESVISOCOUTSPC, 0, 13) +REG32(GCTL, 0x10) + FIELD(GCTL, PWRDNSCALE, 19, 13) + FIELD(GCTL, MASTERFILTBYPASS, 18, 1) + FIELD(GCTL, BYPSSETADDR, 17, 1) + FIELD(GCTL, U2RSTECN, 16, 1) + FIELD(GCTL, FRMSCLDWN, 14, 2) + FIELD(GCTL, PRTCAPDIR, 12, 2) + FIELD(GCTL, CORESOFTRESET, 11, 1) + FIELD(GCTL, U1U2TIMERSCALE, 9, 1) + FIELD(GCTL, DEBUGATTACH, 8, 1) + FIELD(GCTL, RAMCLKSEL, 6, 2) + FIELD(GCTL, SCALEDOWN, 4, 2) + FIELD(GCTL, DISSCRAMBLE, 3, 1) + FIELD(GCTL, U2EXIT_LFPS, 2, 1) + FIELD(GCTL, GBLHIBERNATIONEN, 1, 1) + FIELD(GCTL, DSBLCLKGTNG, 0, 1) +REG32(GPMSTS, 0x14) +REG32(GSTS, 0x18) + FIELD(GSTS, CBELT, 20, 12) + FIELD(GSTS, RESERVED_19_12, 12, 8) + FIELD(GSTS, SSIC_IP, 11, 1) + FIELD(GSTS, OTG_IP, 10, 1) + FIELD(GSTS, BC_IP, 9, 1) + FIELD(GSTS, ADP_IP, 8, 1) + FIELD(GSTS, HOST_IP, 7, 1) + FIELD(GSTS, DEVICE_IP, 6, 1) + FIELD(GSTS, CSRTIMEOUT, 5, 1) + FIELD(GSTS, BUSERRADDRVLD, 4, 1) + FIELD(GSTS, RESERVED_3_2, 2, 2) + FIELD(GSTS, CURMOD, 0, 2) +REG32(GUCTL1, 0x1c) + FIELD(GUCTL1, RESUME_OPMODE_HS_HOST, 10, 1) +REG32(GSNPSID, 0x20) +REG32(GGPIO, 0x24) + FIELD(GGPIO, GPO, 16, 16) + FIELD(GGPIO, GPI, 0, 16) +REG32(GUID, 0x28) +REG32(GUCTL, 0x2c) + FIELD(GUCTL, REFCLKPER, 22, 10) + FIELD(GUCTL, NOEXTRDL, 21, 1) + FIELD(GUCTL, RESERVED_20_18, 18, 3) + FIELD(GUCTL, SPRSCTRLTRANSEN, 17, 1) + FIELD(GUCTL, RESBWHSEPS, 16, 1) + FIELD(GUCTL, RESERVED_15, 15, 1) + FIELD(GUCTL, USBHSTINAUTORETRYEN, 14, 1) + FIELD(GUCTL, ENOVERLAPCHK, 13, 1) + FIELD(GUCTL, EXTCAPSUPPTEN, 12, 1) + FIELD(GUCTL, INSRTEXTRFSBODI, 11, 1) + FIELD(GUCTL, DTCT, 9, 2) + FIELD(GUCTL, DTFT, 0, 9) +REG32(GBUSERRADDRLO, 0x30) +REG32(GBUSERRADDRHI, 0x34) +REG32(GHWPARAMS0, 0x40) + FIELD(GHWPARAMS0, GHWPARAMS0_31_24, 24, 8) + FIELD(GHWPARAMS0, GHWPARAMS0_23_16, 16, 8) + FIELD(GHWPARAMS0, GHWPARAMS0_15_8, 8, 8) + FIELD(GHWPARAMS0, GHWPARAMS0_7_6, 6, 2) + FIELD(GHWPARAMS0, GHWPARAMS0_5_3, 3, 3) + FIELD(GHWPARAMS0, GHWPARAMS0_2_0, 0, 3) +REG32(GHWPARAMS1, 0x44) + FIELD(GHWPARAMS1, GHWPARAMS1_31, 31, 1) + FIELD(GHWPARAMS1, GHWPARAMS1_30, 30, 1) + FIELD(GHWPARAMS1, GHWPARAMS1_29, 29, 1) + FIELD(GHWPARAMS1, GHWPARAMS1_28, 28, 1) + FIELD(GHWPARAMS1, GHWPARAMS1_27, 27, 1) + FIELD(GHWPARAMS1, GHWPARAMS1_26, 26, 1) + FIELD(GHWPARAMS1, GHWPARAMS1_25_24, 24, 2) + FIELD(GHWPARAMS1, GHWPARAMS1_23, 23, 1) + FIELD(GHWPARAMS1, GHWPARAMS1_22_21, 21, 2) + FIELD(GHWPARAMS1, GHWPARAMS1_20_15, 15, 6) + FIELD(GHWPARAMS1, GHWPARAMS1_14_12, 12, 3) + FIELD(GHWPARAMS1, GHWPARAMS1_11_9, 9, 3) + FIELD(GHWPARAMS1, GHWPARAMS1_8_6, 6, 3) + FIELD(GHWPARAMS1, GHWPARAMS1_5_3, 3, 3) + FIELD(GHWPARAMS1, GHWPARAMS1_2_0, 0, 3) +REG32(GHWPARAMS2, 0x48) +REG32(GHWPARAMS3, 0x4c) + FIELD(GHWPARAMS3, GHWPARAMS3_31, 31, 1) + FIELD(GHWPARAMS3, GHWPARAMS3_30_23, 23, 8) + FIELD(GHWPARAMS3, GHWPARAMS3_22_18, 18, 5) + FIELD(GHWPARAMS3, GHWPARAMS3_17_12, 12, 6) + FIELD(GHWPARAMS3, GHWPARAMS3_11, 11, 1) + FIELD(GHWPARAMS3, GHWPARAMS3_10, 10, 1) + FIELD(GHWPARAMS3, GHWPARAMS3_9_8, 8, 2) + FIELD(GHWPARAMS3, GHWPARAMS3_7_6, 6, 2) + FIELD(GHWPARAMS3, GHWPARAMS3_5_4, 4, 2) + FIELD(GHWPARAMS3, GHWPARAMS3_3_2, 2, 2) + FIELD(GHWPARAMS3, GHWPARAMS3_1_0, 0, 2) +REG32(GHWPARAMS4, 0x50) + FIELD(GHWPARAMS4, GHWPARAMS4_31_28, 28, 4) + FIELD(GHWPARAMS4, GHWPARAMS4_27_24, 24, 4) + FIELD(GHWPARAMS4, GHWPARAMS4_23, 23, 1) + FIELD(GHWPARAMS4, GHWPARAMS4_22, 22, 1) + FIELD(GHWPARAMS4, GHWPARAMS4_21, 21, 1) + FIELD(GHWPARAMS4, GHWPARAMS4_20_17, 17, 4) + FIELD(GHWPARAMS4, GHWPARAMS4_16_13, 13, 4) + FIELD(GHWPARAMS4, GHWPARAMS4_12, 12, 1) + FIELD(GHWPARAMS4, GHWPARAMS4_11, 11, 1) + FIELD(GHWPARAMS4, GHWPARAMS4_10_9, 9, 2) + FIELD(GHWPARAMS4, GHWPARAMS4_8_7, 7, 2) + FIELD(GHWPARAMS4, GHWPARAMS4_6, 6, 1) + FIELD(GHWPARAMS4, GHWPARAMS4_5_0, 0, 6) +REG32(GHWPARAMS5, 0x54) + FIELD(GHWPARAMS5, GHWPARAMS5_31_28, 28, 4) + FIELD(GHWPARAMS5, GHWPARAMS5_27_22, 22, 6) + FIELD(GHWPARAMS5, GHWPARAMS5_21_16, 16, 6) + FIELD(GHWPARAMS5, GHWPARAMS5_15_10, 10, 6) + FIELD(GHWPARAMS5, GHWPARAMS5_9_4, 4, 6) + FIELD(GHWPARAMS5, GHWPARAMS5_3_0, 0, 4) +REG32(GHWPARAMS6, 0x58) + FIELD(GHWPARAMS6, GHWPARAMS6_31_16, 16, 16) + FIELD(GHWPARAMS6, BUSFLTRSSUPPORT, 15, 1) + FIELD(GHWPARAMS6, BCSUPPORT, 14, 1) + FIELD(GHWPARAMS6, OTG_SS_SUPPORT, 13, 1) + FIELD(GHWPARAMS6, ADPSUPPORT, 12, 1) + FIELD(GHWPARAMS6, HNPSUPPORT, 11, 1) + FIELD(GHWPARAMS6, SRPSUPPORT, 10, 1) + FIELD(GHWPARAMS6, GHWPARAMS6_9_8, 8, 2) + FIELD(GHWPARAMS6, GHWPARAMS6_7, 7, 1) + FIELD(GHWPARAMS6, GHWPARAMS6_6, 6, 1) + FIELD(GHWPARAMS6, GHWPARAMS6_5_0, 0, 6) +REG32(GHWPARAMS7, 0x5c) + FIELD(GHWPARAMS7, GHWPARAMS7_31_16, 16, 16) + FIELD(GHWPARAMS7, GHWPARAMS7_15_0, 0, 16) +REG32(GDBGFIFOSPACE, 0x60) + FIELD(GDBGFIFOSPACE, SPACE_AVAILABLE, 16, 16) + FIELD(GDBGFIFOSPACE, RESERVED_15_9, 9, 7) + FIELD(GDBGFIFOSPACE, FIFO_QUEUE_SELECT, 0, 9) +REG32(GUCTL2, 0x9c) + FIELD(GUCTL2, RESERVED_31_26, 26, 6) + FIELD(GUCTL2, EN_HP_PM_TIMER, 19, 7) + FIELD(GUCTL2, NOLOWPWRDUR, 15, 4) + FIELD(GUCTL2, RST_ACTBITLATER, 14, 1) + FIELD(GUCTL2, RESERVED_13, 13, 1) + FIELD(GUCTL2, DISABLECFC, 11, 1) +REG32(GUSB2PHYCFG, 0x100) + FIELD(GUSB2PHYCFG, U2_FREECLK_EXISTS, 30, 1) + FIELD(GUSB2PHYCFG, ULPI_LPM_WITH_OPMODE_CHK, 29, 1) + FIELD(GUSB2PHYCFG, RESERVED_25, 25, 1) + FIELD(GUSB2PHYCFG, LSTRD, 22, 3) + FIELD(GUSB2PHYCFG, LSIPD, 19, 3) + FIELD(GUSB2PHYCFG, ULPIEXTVBUSINDIACTOR, 18, 1) + FIELD(GUSB2PHYCFG, ULPIEXTVBUSDRV, 17, 1) + FIELD(GUSB2PHYCFG, RESERVED_16, 16, 1) + FIELD(GUSB2PHYCFG, ULPIAUTORES, 15, 1) + FIELD(GUSB2PHYCFG, RESERVED_14, 14, 1) + FIELD(GUSB2PHYCFG, USBTRDTIM, 10, 4) + FIELD(GUSB2PHYCFG, XCVRDLY, 9, 1) + FIELD(GUSB2PHYCFG, ENBLSLPM, 8, 1) + FIELD(GUSB2PHYCFG, PHYSEL, 7, 1) + FIELD(GUSB2PHYCFG, SUSPENDUSB20, 6, 1) + FIELD(GUSB2PHYCFG, FSINTF, 5, 1) + FIELD(GUSB2PHYCFG, ULPI_UTMI_SEL, 4, 1) + FIELD(GUSB2PHYCFG, PHYIF, 3, 1) + FIELD(GUSB2PHYCFG, TOUTCAL, 0, 3) +REG32(GUSB2I2CCTL, 0x140) +REG32(GUSB2PHYACC_ULPI, 0x180) + FIELD(GUSB2PHYACC_ULPI, RESERVED_31_27, 27, 5) + FIELD(GUSB2PHYACC_ULPI, DISUIPIDRVR, 26, 1) + FIELD(GUSB2PHYACC_ULPI, NEWREGREQ, 25, 1) + FIELD(GUSB2PHYACC_ULPI, VSTSDONE, 24, 1) + FIELD(GUSB2PHYACC_ULPI, VSTSBSY, 23, 1) + FIELD(GUSB2PHYACC_ULPI, REGWR, 22, 1) + FIELD(GUSB2PHYACC_ULPI, REGADDR, 16, 6) + FIELD(GUSB2PHYACC_ULPI, EXTREGADDR, 8, 8) + FIELD(GUSB2PHYACC_ULPI, REGDATA, 0, 8) +REG32(GTXFIFOSIZ0, 0x200) + FIELD(GTXFIFOSIZ0, TXFSTADDR_N, 16, 16) + FIELD(GTXFIFOSIZ0, TXFDEP_N, 0, 16) +REG32(GTXFIFOSIZ1, 0x204) + FIELD(GTXFIFOSIZ1, TXFSTADDR_N, 16, 16) + FIELD(GTXFIFOSIZ1, TXFDEP_N, 0, 16) +REG32(GTXFIFOSIZ2, 0x208) + FIELD(GTXFIFOSIZ2, TXFSTADDR_N, 16, 16) + FIELD(GTXFIFOSIZ2, TXFDEP_N, 0, 16) +REG32(GTXFIFOSIZ3, 0x20c) + FIELD(GTXFIFOSIZ3, TXFSTADDR_N, 16, 16) + FIELD(GTXFIFOSIZ3, TXFDEP_N, 0, 16) +REG32(GTXFIFOSIZ4, 0x210) + FIELD(GTXFIFOSIZ4, TXFSTADDR_N, 16, 16) + FIELD(GTXFIFOSIZ4, TXFDEP_N, 0, 16) +REG32(GTXFIFOSIZ5, 0x214) + FIELD(GTXFIFOSIZ5, TXFSTADDR_N, 16, 16) + FIELD(GTXFIFOSIZ5, TXFDEP_N, 0, 16) +REG32(GRXFIFOSIZ0, 0x280) + FIELD(GRXFIFOSIZ0, RXFSTADDR_N, 16, 16) + FIELD(GRXFIFOSIZ0, RXFDEP_N, 0, 16) +REG32(GRXFIFOSIZ1, 0x284) + FIELD(GRXFIFOSIZ1, RXFSTADDR_N, 16, 16) + FIELD(GRXFIFOSIZ1, RXFDEP_N, 0, 16) +REG32(GRXFIFOSIZ2, 0x288) + FIELD(GRXFIFOSIZ2, RXFSTADDR_N, 16, 16) + FIELD(GRXFIFOSIZ2, RXFDEP_N, 0, 16) +REG32(GEVNTADRLO_0, 0x300) +REG32(GEVNTADRHI_0, 0x304) +REG32(GEVNTSIZ_0, 0x308) + FIELD(GEVNTSIZ_0, EVNTINTRPTMASK, 31, 1) + FIELD(GEVNTSIZ_0, RESERVED_30_16, 16, 15) + FIELD(GEVNTSIZ_0, EVENTSIZ, 0, 16) +REG32(GEVNTCOUNT_0, 0x30c) + FIELD(GEVNTCOUNT_0, EVNT_HANDLER_BUSY, 31, 1) + FIELD(GEVNTCOUNT_0, RESERVED_30_16, 16, 15) + FIELD(GEVNTCOUNT_0, EVNTCOUNT, 0, 16) +REG32(GEVNTADRLO_1, 0x310) +REG32(GEVNTADRHI_1, 0x314) +REG32(GEVNTSIZ_1, 0x318) + FIELD(GEVNTSIZ_1, EVNTINTRPTMASK, 31, 1) + FIELD(GEVNTSIZ_1, RESERVED_30_16, 16, 15) + FIELD(GEVNTSIZ_1, EVENTSIZ, 0, 16) +REG32(GEVNTCOUNT_1, 0x31c) + FIELD(GEVNTCOUNT_1, EVNT_HANDLER_BUSY, 31, 1) + FIELD(GEVNTCOUNT_1, RESERVED_30_16, 16, 15) + FIELD(GEVNTCOUNT_1, EVNTCOUNT, 0, 16) +REG32(GEVNTADRLO_2, 0x320) +REG32(GEVNTADRHI_2, 0x324) +REG32(GEVNTSIZ_2, 0x328) + FIELD(GEVNTSIZ_2, EVNTINTRPTMASK, 31, 1) + FIELD(GEVNTSIZ_2, RESERVED_30_16, 16, 15) + FIELD(GEVNTSIZ_2, EVENTSIZ, 0, 16) +REG32(GEVNTCOUNT_2, 0x32c) + FIELD(GEVNTCOUNT_2, EVNT_HANDLER_BUSY, 31, 1) + FIELD(GEVNTCOUNT_2, RESERVED_30_16, 16, 15) + FIELD(GEVNTCOUNT_2, EVNTCOUNT, 0, 16) +REG32(GEVNTADRLO_3, 0x330) +REG32(GEVNTADRHI_3, 0x334) +REG32(GEVNTSIZ_3, 0x338) + FIELD(GEVNTSIZ_3, EVNTINTRPTMASK, 31, 1) + FIELD(GEVNTSIZ_3, RESERVED_30_16, 16, 15) + FIELD(GEVNTSIZ_3, EVENTSIZ, 0, 16) +REG32(GEVNTCOUNT_3, 0x33c) + FIELD(GEVNTCOUNT_3, EVNT_HANDLER_BUSY, 31, 1) + FIELD(GEVNTCOUNT_3, RESERVED_30_16, 16, 15) + FIELD(GEVNTCOUNT_3, EVNTCOUNT, 0, 16) +REG32(GHWPARAMS8, 0x500) +REG32(GTXFIFOPRIDEV, 0x510) + FIELD(GTXFIFOPRIDEV, RESERVED_31_N, 6, 26) + FIELD(GTXFIFOPRIDEV, GTXFIFOPRIDEV, 0, 6) +REG32(GTXFIFOPRIHST, 0x518) + FIELD(GTXFIFOPRIHST, RESERVED_31_16, 3, 29) + FIELD(GTXFIFOPRIHST, GTXFIFOPRIHST, 0, 3) +REG32(GRXFIFOPRIHST, 0x51c) + FIELD(GRXFIFOPRIHST, RESERVED_31_16, 3, 29) + FIELD(GRXFIFOPRIHST, GRXFIFOPRIHST, 0, 3) +REG32(GDMAHLRATIO, 0x524) + FIELD(GDMAHLRATIO, RESERVED_31_13, 13, 19) + FIELD(GDMAHLRATIO, HSTRXFIFO, 8, 5) + FIELD(GDMAHLRATIO, RESERVED_7_5, 5, 3) + FIELD(GDMAHLRATIO, HSTTXFIFO, 0, 5) +REG32(GFLADJ, 0x530) + FIELD(GFLADJ, GFLADJ_REFCLK_240MHZDECR_PLS1, 31, 1) + FIELD(GFLADJ, GFLADJ_REFCLK_240MHZ_DECR, 24, 7) + FIELD(GFLADJ, GFLADJ_REFCLK_LPM_SEL, 23, 1) + FIELD(GFLADJ, RESERVED_22, 22, 1) + FIELD(GFLADJ, GFLADJ_REFCLK_FLADJ, 8, 14) + FIELD(GFLADJ, GFLADJ_30MHZ_SDBND_SEL, 7, 1) + FIELD(GFLADJ, GFLADJ_30MHZ, 0, 6) + +#define DWC3_GLOBAL_OFFSET 0xC100 +static void reset_csr(USBDWC3 * s) +{ + int i = 0; + /* + * We reset all CSR regs except GCTL, GUCTL, GSTS, GSNPSID, GGPIO, GUID, + * GUSB2PHYCFGn registers and GUSB3PIPECTLn registers. We will skip PHY + * register as we don't implement them. + */ + for (i = 0; i < USB_DWC3_R_MAX; i++) { + switch (i) { + case R_GCTL: + break; + case R_GSTS: + break; + case R_GSNPSID: + break; + case R_GGPIO: + break; + case R_GUID: + break; + case R_GUCTL: + break; + case R_GHWPARAMS0...R_GHWPARAMS7: + break; + case R_GHWPARAMS8: + break; + default: + register_reset(&s->regs_info[i]); + break; + } + } + + xhci_sysbus_reset(DEVICE(&s->sysbus_xhci)); +} + +static void usb_dwc3_gctl_postw(RegisterInfo *reg, uint64_t val64) +{ + USBDWC3 *s = USB_DWC3(reg->opaque); + + if (ARRAY_FIELD_EX32(s->regs, GCTL, CORESOFTRESET)) { + reset_csr(s); + } +} + +static void usb_dwc3_guid_postw(RegisterInfo *reg, uint64_t val64) +{ + USBDWC3 *s = USB_DWC3(reg->opaque); + + s->regs[R_GUID] = s->cfg.dwc_usb3_user; +} + +static const RegisterAccessInfo usb_dwc3_regs_info[] = { + { .name = "GSBUSCFG0", .addr = A_GSBUSCFG0, + .ro = 0xf300, + .unimp = 0xffffffff, + },{ .name = "GSBUSCFG1", .addr = A_GSBUSCFG1, + .reset = 0x300, + .ro = 0xffffe0ff, + .unimp = 0xffffffff, + },{ .name = "GTXTHRCFG", .addr = A_GTXTHRCFG, + .ro = 0xd000ffff, + .unimp = 0xffffffff, + },{ .name = "GRXTHRCFG", .addr = A_GRXTHRCFG, + .ro = 0xd007e000, + .unimp = 0xffffffff, + },{ .name = "GCTL", .addr = A_GCTL, + .reset = 0x30c13004, .post_write = usb_dwc3_gctl_postw, + },{ .name = "GPMSTS", .addr = A_GPMSTS, + .ro = 0xfffffff, + .unimp = 0xffffffff, + },{ .name = "GSTS", .addr = A_GSTS, + .reset = 0x7e800000, + .ro = 0xffffffcf, + .w1c = 0x30, + .unimp = 0xffffffff, + },{ .name = "GUCTL1", .addr = A_GUCTL1, + .reset = 0x198a, + .ro = 0x7800, + .unimp = 0xffffffff, + },{ .name = "GSNPSID", .addr = A_GSNPSID, + .reset = 0x5533330a, + .ro = 0xffffffff, + },{ .name = "GGPIO", .addr = A_GGPIO, + .ro = 0xffff, + .unimp = 0xffffffff, + },{ .name = "GUID", .addr = A_GUID, + .reset = 0x12345678, .post_write = usb_dwc3_guid_postw, + },{ .name = "GUCTL", .addr = A_GUCTL, + .reset = 0x0c808010, + .ro = 0x1c8000, + .unimp = 0xffffffff, + },{ .name = "GBUSERRADDRLO", .addr = A_GBUSERRADDRLO, + .ro = 0xffffffff, + },{ .name = "GBUSERRADDRHI", .addr = A_GBUSERRADDRHI, + .ro = 0xffffffff, + },{ .name = "GHWPARAMS0", .addr = A_GHWPARAMS0, + .ro = 0xffffffff, + },{ .name = "GHWPARAMS1", .addr = A_GHWPARAMS1, + .ro = 0xffffffff, + },{ .name = "GHWPARAMS2", .addr = A_GHWPARAMS2, + .ro = 0xffffffff, + },{ .name = "GHWPARAMS3", .addr = A_GHWPARAMS3, + .ro = 0xffffffff, + },{ .name = "GHWPARAMS4", .addr = A_GHWPARAMS4, + .ro = 0xffffffff, + },{ .name = "GHWPARAMS5", .addr = A_GHWPARAMS5, + .ro = 0xffffffff, + },{ .name = "GHWPARAMS6", .addr = A_GHWPARAMS6, + .ro = 0xffffffff, + },{ .name = "GHWPARAMS7", .addr = A_GHWPARAMS7, + .ro = 0xffffffff, + },{ .name = "GDBGFIFOSPACE", .addr = A_GDBGFIFOSPACE, + .reset = 0xa0000, + .ro = 0xfffffe00, + .unimp = 0xffffffff, + },{ .name = "GUCTL2", .addr = A_GUCTL2, + .reset = 0x40d, + .ro = 0x2000, + .unimp = 0xffffffff, + },{ .name = "GUSB2PHYCFG", .addr = A_GUSB2PHYCFG, + .reset = 0x40102410, + .ro = 0x1e014030, + .unimp = 0xffffffff, + },{ .name = "GUSB2I2CCTL", .addr = A_GUSB2I2CCTL, + .ro = 0xffffffff, + .unimp = 0xffffffff, + },{ .name = "GUSB2PHYACC_ULPI", .addr = A_GUSB2PHYACC_ULPI, + .ro = 0xfd000000, + .unimp = 0xffffffff, + },{ .name = "GTXFIFOSIZ0", .addr = A_GTXFIFOSIZ0, + .reset = 0x2c7000a, + .unimp = 0xffffffff, + },{ .name = "GTXFIFOSIZ1", .addr = A_GTXFIFOSIZ1, + .reset = 0x2d10103, + .unimp = 0xffffffff, + },{ .name = "GTXFIFOSIZ2", .addr = A_GTXFIFOSIZ2, + .reset = 0x3d40103, + .unimp = 0xffffffff, + },{ .name = "GTXFIFOSIZ3", .addr = A_GTXFIFOSIZ3, + .reset = 0x4d70083, + .unimp = 0xffffffff, + },{ .name = "GTXFIFOSIZ4", .addr = A_GTXFIFOSIZ4, + .reset = 0x55a0083, + .unimp = 0xffffffff, + },{ .name = "GTXFIFOSIZ5", .addr = A_GTXFIFOSIZ5, + .reset = 0x5dd0083, + .unimp = 0xffffffff, + },{ .name = "GRXFIFOSIZ0", .addr = A_GRXFIFOSIZ0, + .reset = 0x1c20105, + .unimp = 0xffffffff, + },{ .name = "GRXFIFOSIZ1", .addr = A_GRXFIFOSIZ1, + .reset = 0x2c70000, + .unimp = 0xffffffff, + },{ .name = "GRXFIFOSIZ2", .addr = A_GRXFIFOSIZ2, + .reset = 0x2c70000, + .unimp = 0xffffffff, + },{ .name = "GEVNTADRLO_0", .addr = A_GEVNTADRLO_0, + .unimp = 0xffffffff, + },{ .name = "GEVNTADRHI_0", .addr = A_GEVNTADRHI_0, + .unimp = 0xffffffff, + },{ .name = "GEVNTSIZ_0", .addr = A_GEVNTSIZ_0, + .ro = 0x7fff0000, + .unimp = 0xffffffff, + },{ .name = "GEVNTCOUNT_0", .addr = A_GEVNTCOUNT_0, + .ro = 0x7fff0000, + .unimp = 0xffffffff, + },{ .name = "GEVNTADRLO_1", .addr = A_GEVNTADRLO_1, + .unimp = 0xffffffff, + },{ .name = "GEVNTADRHI_1", .addr = A_GEVNTADRHI_1, + .unimp = 0xffffffff, + },{ .name = "GEVNTSIZ_1", .addr = A_GEVNTSIZ_1, + .ro = 0x7fff0000, + .unimp = 0xffffffff, + },{ .name = "GEVNTCOUNT_1", .addr = A_GEVNTCOUNT_1, + .ro = 0x7fff0000, + .unimp = 0xffffffff, + },{ .name = "GEVNTADRLO_2", .addr = A_GEVNTADRLO_2, + .unimp = 0xffffffff, + },{ .name = "GEVNTADRHI_2", .addr = A_GEVNTADRHI_2, + .unimp = 0xffffffff, + },{ .name = "GEVNTSIZ_2", .addr = A_GEVNTSIZ_2, + .ro = 0x7fff0000, + .unimp = 0xffffffff, + },{ .name = "GEVNTCOUNT_2", .addr = A_GEVNTCOUNT_2, + .ro = 0x7fff0000, + .unimp = 0xffffffff, + },{ .name = "GEVNTADRLO_3", .addr = A_GEVNTADRLO_3, + .unimp = 0xffffffff, + },{ .name = "GEVNTADRHI_3", .addr = A_GEVNTADRHI_3, + .unimp = 0xffffffff, + },{ .name = "GEVNTSIZ_3", .addr = A_GEVNTSIZ_3, + .ro = 0x7fff0000, + .unimp = 0xffffffff, + },{ .name = "GEVNTCOUNT_3", .addr = A_GEVNTCOUNT_3, + .ro = 0x7fff0000, + .unimp = 0xffffffff, + },{ .name = "GHWPARAMS8", .addr = A_GHWPARAMS8, + .ro = 0xffffffff, + },{ .name = "GTXFIFOPRIDEV", .addr = A_GTXFIFOPRIDEV, + .ro = 0xffffffc0, + .unimp = 0xffffffff, + },{ .name = "GTXFIFOPRIHST", .addr = A_GTXFIFOPRIHST, + .ro = 0xfffffff8, + .unimp = 0xffffffff, + },{ .name = "GRXFIFOPRIHST", .addr = A_GRXFIFOPRIHST, + .ro = 0xfffffff8, + .unimp = 0xffffffff, + },{ .name = "GDMAHLRATIO", .addr = A_GDMAHLRATIO, + .ro = 0xffffe0e0, + .unimp = 0xffffffff, + },{ .name = "GFLADJ", .addr = A_GFLADJ, + .reset = 0xc83f020, + .rsvd = 0x40, + .ro = 0x400040, + .unimp = 0xffffffff, + } +}; + +static void usb_dwc3_reset(DeviceState *dev) +{ + USBDWC3 *s = USB_DWC3(dev); + unsigned int i; + + for (i = 0; i < ARRAY_SIZE(s->regs_info); ++i) { + switch (i) { + case R_GHWPARAMS0...R_GHWPARAMS7: + break; + case R_GHWPARAMS8: + break; + default: + register_reset(&s->regs_info[i]); + }; + } + + xhci_sysbus_reset(DEVICE(&s->sysbus_xhci)); +} + +static const MemoryRegionOps usb_dwc3_ops = { + .read = register_read_memory, + .write = register_write_memory, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid = { + .min_access_size = 4, + .max_access_size = 4, + }, +}; + +static void usb_dwc3_realize(DeviceState *dev, Error **errp) +{ + USBDWC3 *s = USB_DWC3(dev); + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + Error *err = NULL; + + sysbus_realize(SYS_BUS_DEVICE(&s->sysbus_xhci), &err); + if (err) { + error_propagate(errp, err); + return; + } + + memory_region_add_subregion(&s->iomem, 0, + sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->sysbus_xhci), 0)); + sysbus_init_mmio(sbd, &s->iomem); + + /* + * Device Configuration + */ + s->regs[R_GHWPARAMS0] = 0x40204048 | s->cfg.mode; + s->regs[R_GHWPARAMS1] = 0x222493b; + s->regs[R_GHWPARAMS2] = 0x12345678; + s->regs[R_GHWPARAMS3] = 0x618c088; + s->regs[R_GHWPARAMS4] = 0x47822004; + s->regs[R_GHWPARAMS5] = 0x4202088; + s->regs[R_GHWPARAMS6] = 0x7850c20; + s->regs[R_GHWPARAMS7] = 0x0; + s->regs[R_GHWPARAMS8] = 0x478; +} + +static void usb_dwc3_init(Object *obj) +{ + USBDWC3 *s = USB_DWC3(obj); + RegisterInfoArray *reg_array; + + memory_region_init(&s->iomem, obj, TYPE_USB_DWC3, DWC3_SIZE); + reg_array = + register_init_block32(DEVICE(obj), usb_dwc3_regs_info, + ARRAY_SIZE(usb_dwc3_regs_info), + s->regs_info, s->regs, + &usb_dwc3_ops, + USB_DWC3_ERR_DEBUG, + USB_DWC3_R_MAX * 4); + memory_region_add_subregion(&s->iomem, + DWC3_GLOBAL_OFFSET, + &reg_array->mem); + object_initialize_child(obj, "dwc3-xhci", &s->sysbus_xhci, + TYPE_XHCI_SYSBUS); + qdev_alias_all_properties(DEVICE(&s->sysbus_xhci), obj); + + s->cfg.mode = HOST_MODE; +} + +static const VMStateDescription vmstate_usb_dwc3 = { + .name = "usb-dwc3", + .version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32_ARRAY(regs, USBDWC3, USB_DWC3_R_MAX), + VMSTATE_UINT8(cfg.mode, USBDWC3), + VMSTATE_UINT32(cfg.dwc_usb3_user, USBDWC3), + VMSTATE_END_OF_LIST() + } +}; + +static Property usb_dwc3_properties[] = { + DEFINE_PROP_UINT32("DWC_USB3_USERID", USBDWC3, cfg.dwc_usb3_user, + 0x12345678), + DEFINE_PROP_END_OF_LIST(), +}; + +static void usb_dwc3_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->reset = usb_dwc3_reset; + dc->realize = usb_dwc3_realize; + dc->vmsd = &vmstate_usb_dwc3; + device_class_set_props(dc, usb_dwc3_properties); +} + +static const TypeInfo usb_dwc3_info = { + .name = TYPE_USB_DWC3, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(USBDWC3), + .class_init = usb_dwc3_class_init, + .instance_init = usb_dwc3_init, +}; + +static void usb_dwc3_register_types(void) +{ + type_register_static(&usb_dwc3_info); +} + +type_init(usb_dwc3_register_types) diff --git a/hw/usb/Kconfig b/hw/usb/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/Kconfig +++ b/hw/usb/Kconfig @@ -XXX,XX +XXX,XX @@ config IMX_USBPHY bool default y depends on USB + +config USB_DWC3 + bool + select USB_XHCI_SYSBUS + select REGISTER diff --git a/hw/usb/meson.build b/hw/usb/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/meson.build +++ b/hw/usb/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_USB_XHCI_SYSBUS', if_true: files('hcd-xhci-sysbus.c softmmu_ss.add(when: 'CONFIG_USB_XHCI_NEC', if_true: files('hcd-xhci-nec.c')) softmmu_ss.add(when: 'CONFIG_USB_MUSB', if_true: files('hcd-musb.c')) softmmu_ss.add(when: 'CONFIG_USB_DWC2', if_true: files('hcd-dwc2.c')) +softmmu_ss.add(when: 'CONFIG_USB_DWC3', if_true: files('hcd-dwc3.c')) softmmu_ss.add(when: 'CONFIG_TUSB6010', if_true: files('tusb6010.c')) softmmu_ss.add(when: 'CONFIG_IMX', if_true: files('chipidea.c')) -- 2.20.1 From: Sai Pavan Boddu <sai.pavan.boddu@xilinx.com> This model is a top level integration wrapper for hcd-dwc3 and versal-usb2-ctrl-regs modules, this is used by xilinx versal soc's and future xilinx usb subsystems would also be part of it. Signed-off-by: Sai Pavan Boddu <sai.pavan.boddu@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1607023357-5096-4-git-send-email-sai.pavan.boddu@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/usb/xlnx-usb-subsystem.h | 45 ++++++++++++++ hw/usb/xlnx-usb-subsystem.c | 94 +++++++++++++++++++++++++++++ hw/usb/Kconfig | 5 ++ hw/usb/meson.build | 1 + 4 files changed, 145 insertions(+) create mode 100644 include/hw/usb/xlnx-usb-subsystem.h create mode 100644 hw/usb/xlnx-usb-subsystem.c diff --git a/include/hw/usb/xlnx-usb-subsystem.h b/include/hw/usb/xlnx-usb-subsystem.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/usb/xlnx-usb-subsystem.h @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Xilinx usb subsystem + * + * Copyright (c) 2020 Xilinx Inc. Sai Pavan Boddu <sai.pavan.boddu@xilinx.com> + * + * 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. + */ + +#ifndef _XLNX_VERSAL_USB_SUBSYSTEM_H_ +#define _XLNX_VERSAL_USB_SUBSYSTEM_H_ + +#include "hw/usb/xlnx-versal-usb2-ctrl-regs.h" +#include "hw/usb/hcd-dwc3.h" + +#define TYPE_XILINX_VERSAL_USB2 "xlnx.versal-usb2" + +#define VERSAL_USB2(obj) \ + OBJECT_CHECK(VersalUsb2, (obj), TYPE_XILINX_VERSAL_USB2) + +typedef struct VersalUsb2 { + SysBusDevice parent_obj; + MemoryRegion dwc3_mr; + MemoryRegion usb2Ctrl_mr; + + VersalUsb2CtrlRegs usb2Ctrl; + USBDWC3 dwc3; +} VersalUsb2; + +#endif diff --git a/hw/usb/xlnx-usb-subsystem.c b/hw/usb/xlnx-usb-subsystem.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/usb/xlnx-usb-subsystem.c @@ -XXX,XX +XXX,XX @@ +/* + * QEMU model of the Xilinx usb subsystem + * + * Copyright (c) 2020 Xilinx Inc. Sai Pavan Boddu <sai.pava.boddu@xilinx.com> + * + * 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 "hw/sysbus.h" +#include "hw/irq.h" +#include "hw/register.h" +#include "qemu/bitops.h" +#include "qemu/log.h" +#include "qom/object.h" +#include "qapi/error.h" +#include "hw/qdev-properties.h" +#include "hw/usb/xlnx-usb-subsystem.h" + +static void versal_usb2_realize(DeviceState *dev, Error **errp) +{ + VersalUsb2 *s = VERSAL_USB2(dev); + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + Error *err = NULL; + + sysbus_realize(SYS_BUS_DEVICE(&s->dwc3), &err); + if (err) { + error_propagate(errp, err); + return; + } + sysbus_realize(SYS_BUS_DEVICE(&s->usb2Ctrl), &err); + if (err) { + error_propagate(errp, err); + return; + } + sysbus_init_mmio(sbd, &s->dwc3_mr); + sysbus_init_mmio(sbd, &s->usb2Ctrl_mr); + qdev_pass_gpios(DEVICE(&s->dwc3.sysbus_xhci), dev, SYSBUS_DEVICE_GPIO_IRQ); +} + +static void versal_usb2_init(Object *obj) +{ + VersalUsb2 *s = VERSAL_USB2(obj); + + object_initialize_child(obj, "versal.dwc3", &s->dwc3, + TYPE_USB_DWC3); + object_initialize_child(obj, "versal.usb2-ctrl", &s->usb2Ctrl, + TYPE_XILINX_VERSAL_USB2_CTRL_REGS); + memory_region_init_alias(&s->dwc3_mr, obj, "versal.dwc3_alias", + &s->dwc3.iomem, 0, DWC3_SIZE); + memory_region_init_alias(&s->usb2Ctrl_mr, obj, "versal.usb2Ctrl_alias", + &s->usb2Ctrl.iomem, 0, USB2_REGS_R_MAX * 4); + qdev_alias_all_properties(DEVICE(&s->dwc3), obj); + qdev_alias_all_properties(DEVICE(&s->dwc3.sysbus_xhci), obj); + object_property_add_alias(obj, "dma", OBJECT(&s->dwc3.sysbus_xhci), "dma"); +} + +static void versal_usb2_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = versal_usb2_realize; +} + +static const TypeInfo versal_usb2_info = { + .name = TYPE_XILINX_VERSAL_USB2, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(VersalUsb2), + .class_init = versal_usb2_class_init, + .instance_init = versal_usb2_init, +}; + +static void versal_usb_types(void) +{ + type_register_static(&versal_usb2_info); +} + +type_init(versal_usb_types) diff --git a/hw/usb/Kconfig b/hw/usb/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/Kconfig +++ b/hw/usb/Kconfig @@ -XXX,XX +XXX,XX @@ config USB_DWC3 bool select USB_XHCI_SYSBUS select REGISTER + +config XLNX_USB_SUBSYS + bool + default y if XLNX_VERSAL + select USB_DWC3 diff --git a/hw/usb/meson.build b/hw/usb/meson.build index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/meson.build +++ b/hw/usb/meson.build @@ -XXX,XX +XXX,XX @@ softmmu_ss.add(when: 'CONFIG_TUSB6010', if_true: files('tusb6010.c')) softmmu_ss.add(when: 'CONFIG_IMX', if_true: files('chipidea.c')) softmmu_ss.add(when: 'CONFIG_IMX_USBPHY', if_true: files('imx-usb-phy.c')) specific_ss.add(when: 'CONFIG_XLNX_VERSAL', if_true: files('xlnx-versal-usb2-ctrl-regs.c')) +specific_ss.add(when: 'CONFIG_XLNX_USB_SUBSYS', if_true: files('xlnx-usb-subsystem.c')) # emulated usb devices softmmu_ss.add(when: 'CONFIG_USB', if_true: files('dev-hub.c')) -- 2.20.1 From: Vikram Garhwal <fnu.vikram@xilinx.com> Connect VersalUsb2 subsystem to xlnx-versal SOC, its placed in iou of lpd domain and configure it as dual port host controller. Add the respective guest dts nodes for "xlnx-versal-virt" machine. Signed-off-by: Vikram Garhwal <fnu.vikram@xilinx.com> Signed-off-by: Sai Pavan Boddu <sai.pavan.boddu@xilinx.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Message-id: 1607023357-5096-5-git-send-email-sai.pavan.boddu@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/xlnx-versal.h | 9 ++++++ hw/arm/xlnx-versal-virt.c | 55 ++++++++++++++++++++++++++++++++++++ hw/arm/xlnx-versal.c | 26 +++++++++++++++++ 3 files changed, 90 insertions(+) diff --git a/include/hw/arm/xlnx-versal.h b/include/hw/arm/xlnx-versal.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/xlnx-versal.h +++ b/include/hw/arm/xlnx-versal.h @@ -XXX,XX +XXX,XX @@ #include "hw/net/cadence_gem.h" #include "hw/rtc/xlnx-zynqmp-rtc.h" #include "qom/object.h" +#include "hw/usb/xlnx-usb-subsystem.h" #define TYPE_XLNX_VERSAL "xlnx-versal" OBJECT_DECLARE_SIMPLE_TYPE(Versal, XLNX_VERSAL) @@ -XXX,XX +XXX,XX @@ struct Versal { PL011State uart[XLNX_VERSAL_NR_UARTS]; CadenceGEMState gem[XLNX_VERSAL_NR_GEMS]; XlnxZDMA adma[XLNX_VERSAL_NR_ADMAS]; + VersalUsb2 usb; } iou; } lpd; @@ -XXX,XX +XXX,XX @@ struct Versal { #define VERSAL_UART0_IRQ_0 18 #define VERSAL_UART1_IRQ_0 19 +#define VERSAL_USB0_IRQ_0 22 #define VERSAL_GEM0_IRQ_0 56 #define VERSAL_GEM0_WAKE_IRQ_0 57 #define VERSAL_GEM1_IRQ_0 58 @@ -XXX,XX +XXX,XX @@ struct Versal { #define MM_OCM 0xfffc0000U #define MM_OCM_SIZE 0x40000 +#define MM_USB2_CTRL_REGS 0xFF9D0000 +#define MM_USB2_CTRL_REGS_SIZE 0x10000 + +#define MM_USB_0 0xFE200000 +#define MM_USB_0_SIZE 0x10000 + #define MM_TOP_DDR 0x0 #define MM_TOP_DDR_SIZE 0x80000000U #define MM_TOP_DDR_2 0x800000000ULL diff --git a/hw/arm/xlnx-versal-virt.c b/hw/arm/xlnx-versal-virt.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal-virt.c +++ b/hw/arm/xlnx-versal-virt.c @@ -XXX,XX +XXX,XX @@ struct VersalVirt { uint32_t ethernet_phy[2]; uint32_t clk_125Mhz; uint32_t clk_25Mhz; + uint32_t usb; + uint32_t dwc; } phandle; struct arm_boot_info binfo; @@ -XXX,XX +XXX,XX @@ static void fdt_create(VersalVirt *s) s->phandle.clk_25Mhz = qemu_fdt_alloc_phandle(s->fdt); s->phandle.clk_125Mhz = qemu_fdt_alloc_phandle(s->fdt); + s->phandle.usb = qemu_fdt_alloc_phandle(s->fdt); + s->phandle.dwc = qemu_fdt_alloc_phandle(s->fdt); /* Create /chosen node for load_dtb. */ qemu_fdt_add_subnode(s->fdt, "/chosen"); @@ -XXX,XX +XXX,XX @@ static void fdt_add_timer_nodes(VersalVirt *s) compat, sizeof(compat)); } +static void fdt_add_usb_xhci_nodes(VersalVirt *s) +{ + const char clocknames[] = "bus_clk\0ref_clk"; + const char irq_name[] = "dwc_usb3"; + const char compatVersalDWC3[] = "xlnx,versal-dwc3"; + const char compatDWC3[] = "snps,dwc3"; + char *name = g_strdup_printf("/usb@%" PRIx32, MM_USB2_CTRL_REGS); + + qemu_fdt_add_subnode(s->fdt, name); + qemu_fdt_setprop(s->fdt, name, "compatible", + compatVersalDWC3, sizeof(compatVersalDWC3)); + qemu_fdt_setprop_sized_cells(s->fdt, name, "reg", + 2, MM_USB2_CTRL_REGS, + 2, MM_USB2_CTRL_REGS_SIZE); + qemu_fdt_setprop(s->fdt, name, "clock-names", + clocknames, sizeof(clocknames)); + qemu_fdt_setprop_cells(s->fdt, name, "clocks", + s->phandle.clk_25Mhz, s->phandle.clk_125Mhz); + qemu_fdt_setprop(s->fdt, name, "ranges", NULL, 0); + qemu_fdt_setprop_cell(s->fdt, name, "#address-cells", 2); + qemu_fdt_setprop_cell(s->fdt, name, "#size-cells", 2); + qemu_fdt_setprop_cell(s->fdt, name, "phandle", s->phandle.usb); + g_free(name); + + name = g_strdup_printf("/usb@%" PRIx32 "/dwc3@%" PRIx32, + MM_USB2_CTRL_REGS, MM_USB_0); + qemu_fdt_add_subnode(s->fdt, name); + qemu_fdt_setprop(s->fdt, name, "compatible", + compatDWC3, sizeof(compatDWC3)); + qemu_fdt_setprop_sized_cells(s->fdt, name, "reg", + 2, MM_USB_0, 2, MM_USB_0_SIZE); + qemu_fdt_setprop(s->fdt, name, "interrupt-names", + irq_name, sizeof(irq_name)); + qemu_fdt_setprop_cells(s->fdt, name, "interrupts", + GIC_FDT_IRQ_TYPE_SPI, VERSAL_USB0_IRQ_0, + GIC_FDT_IRQ_FLAGS_LEVEL_HI); + qemu_fdt_setprop_cell(s->fdt, name, + "snps,quirk-frame-length-adjustment", 0x20); + qemu_fdt_setprop_cells(s->fdt, name, "#stream-id-cells", 1); + qemu_fdt_setprop_string(s->fdt, name, "dr_mode", "host"); + qemu_fdt_setprop_string(s->fdt, name, "phy-names", "usb3-phy"); + qemu_fdt_setprop(s->fdt, name, "snps,dis_u2_susphy_quirk", NULL, 0); + qemu_fdt_setprop(s->fdt, name, "snps,dis_u3_susphy_quirk", NULL, 0); + qemu_fdt_setprop(s->fdt, name, "snps,refclk_fladj", NULL, 0); + qemu_fdt_setprop(s->fdt, name, "snps,mask_phy_reset", NULL, 0); + qemu_fdt_setprop_cell(s->fdt, name, "phandle", s->phandle.dwc); + qemu_fdt_setprop_string(s->fdt, name, "maximum-speed", "high-speed"); + g_free(name); +} + static void fdt_add_uart_nodes(VersalVirt *s) { uint64_t addrs[] = { MM_UART1, MM_UART0 }; @@ -XXX,XX +XXX,XX @@ static void versal_virt_init(MachineState *machine) fdt_add_gic_nodes(s); fdt_add_timer_nodes(s); fdt_add_zdma_nodes(s); + fdt_add_usb_xhci_nodes(s); fdt_add_sd_nodes(s); fdt_add_rtc_node(s); fdt_add_cpu_nodes(s, psci_conduit); diff --git a/hw/arm/xlnx-versal.c b/hw/arm/xlnx-versal.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/xlnx-versal.c +++ b/hw/arm/xlnx-versal.c @@ -XXX,XX +XXX,XX @@ static void versal_create_uarts(Versal *s, qemu_irq *pic) } } +static void versal_create_usbs(Versal *s, qemu_irq *pic) +{ + DeviceState *dev; + MemoryRegion *mr; + + object_initialize_child(OBJECT(s), "usb2", &s->lpd.iou.usb, + TYPE_XILINX_VERSAL_USB2); + dev = DEVICE(&s->lpd.iou.usb); + + object_property_set_link(OBJECT(dev), "dma", OBJECT(&s->mr_ps), + &error_abort); + qdev_prop_set_uint32(dev, "intrs", 1); + qdev_prop_set_uint32(dev, "slots", 2); + + sysbus_realize(SYS_BUS_DEVICE(dev), &error_fatal); + + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 0); + memory_region_add_subregion(&s->mr_ps, MM_USB_0, mr); + + sysbus_connect_irq(SYS_BUS_DEVICE(dev), 0, pic[VERSAL_USB0_IRQ_0]); + + mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(dev), 1); + memory_region_add_subregion(&s->mr_ps, MM_USB2_CTRL_REGS, mr); +} + static void versal_create_gems(Versal *s, qemu_irq *pic) { int i; @@ -XXX,XX +XXX,XX @@ static void versal_realize(DeviceState *dev, Error **errp) versal_create_apu_cpus(s); versal_create_apu_gic(s, pic); versal_create_uarts(s, pic); + versal_create_usbs(s, pic); versal_create_gems(s, pic); versal_create_admas(s, pic); versal_create_sds(s, pic); -- 2.20.1 From: Philippe Mathieu-Daudé <f4bug@amsat.org> Malicious user can set the feedback divisor for the PLLs to zero, triggering a floating-point exception (SIGFPE). As the datasheet [*] is not clear how hardware behaves when these bits are zeroes, use the maximum divisor possible (128) to avoid the software FPE. [*] Zynq-7000 TRM, UG585 (v1.12.2) B.28 System Level Control Registers (slcr) -> "Register (slcr) ARM_PLL_CTRL" 25.10.4 PLLs -> "Software-Controlled PLL Update" Fixes: 38867cb7ec9 ("hw/misc/zynq_slcr: add clock generation for uarts") Reported-by: Gaoning Pan <pgn@zju.edu.cn> Signed-off-by: Philippe Mathieu-Daudé <f4bug@amsat.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> Reviewed-by: Damien Hedde <damien.hedde@greensocs.com> Message-id: 20201210141610.884600-1-f4bug@amsat.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/misc/zynq_slcr.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/hw/misc/zynq_slcr.c b/hw/misc/zynq_slcr.c index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/zynq_slcr.c +++ b/hw/misc/zynq_slcr.c @@ -XXX,XX +XXX,XX @@ static uint64_t zynq_slcr_compute_pll(uint64_t input, uint32_t ctrl_reg) return 0; } + /* Consider zero feedback as maximum divide ratio possible */ + if (!mult) { + mult = 1 << R_xxx_PLL_CTRL_PLL_FPDIV_LENGTH; + } + /* frequency multiplier -> period division */ return input / mult; } -- 2.20.1 From: Joe Komlodi <joe.komlodi@xilinx.com> The previous naming of the configuration registers made it sound like that if the bits were set the settings would be enabled, while the opposite is true. Signed-off-by: Joe Komlodi <komlodi@xilinx.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Message-id: 1605568264-26376-2-git-send-email-komlodi@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/block/m25p80.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/m25p80.c +++ b/hw/block/m25p80.c @@ -XXX,XX +XXX,XX @@ typedef struct FlashPartInfo { #define VCFG_WRAP_SEQUENTIAL 0x2 #define NVCFG_XIP_MODE_DISABLED (7 << 9) #define NVCFG_XIP_MODE_MASK (7 << 9) -#define VCFG_XIP_MODE_ENABLED (1 << 3) +#define VCFG_XIP_MODE_DISABLED (1 << 3) #define CFG_DUMMY_CLK_LEN 4 #define NVCFG_DUMMY_CLK_POS 12 #define VCFG_DUMMY_CLK_POS 4 @@ -XXX,XX +XXX,XX @@ typedef struct FlashPartInfo { #define EVCFG_VPP_ACCELERATOR (1 << 3) #define EVCFG_RESET_HOLD_ENABLED (1 << 4) #define NVCFG_DUAL_IO_MASK (1 << 2) -#define EVCFG_DUAL_IO_ENABLED (1 << 6) +#define EVCFG_DUAL_IO_DISABLED (1 << 6) #define NVCFG_QUAD_IO_MASK (1 << 3) -#define EVCFG_QUAD_IO_ENABLED (1 << 7) +#define EVCFG_QUAD_IO_DISABLED (1 << 7) #define NVCFG_4BYTE_ADDR_MASK (1 << 0) #define NVCFG_LOWER_SEGMENT_MASK (1 << 1) @@ -XXX,XX +XXX,XX @@ static void reset_memory(Flash *s) s->volatile_cfg |= VCFG_WRAP_SEQUENTIAL; if ((s->nonvolatile_cfg & NVCFG_XIP_MODE_MASK) != NVCFG_XIP_MODE_DISABLED) { - s->volatile_cfg |= VCFG_XIP_MODE_ENABLED; + s->volatile_cfg |= VCFG_XIP_MODE_DISABLED; } s->volatile_cfg |= deposit32(s->volatile_cfg, VCFG_DUMMY_CLK_POS, @@ -XXX,XX +XXX,XX @@ static void reset_memory(Flash *s) s->enh_volatile_cfg |= EVCFG_VPP_ACCELERATOR; s->enh_volatile_cfg |= EVCFG_RESET_HOLD_ENABLED; if (s->nonvolatile_cfg & NVCFG_DUAL_IO_MASK) { - s->enh_volatile_cfg |= EVCFG_DUAL_IO_ENABLED; + s->enh_volatile_cfg |= EVCFG_DUAL_IO_DISABLED; } if (s->nonvolatile_cfg & NVCFG_QUAD_IO_MASK) { - s->enh_volatile_cfg |= EVCFG_QUAD_IO_ENABLED; + s->enh_volatile_cfg |= EVCFG_QUAD_IO_DISABLED; } if (!(s->nonvolatile_cfg & NVCFG_4BYTE_ADDR_MASK)) { s->four_bytes_address_mode = true; -- 2.20.1 From: Joe Komlodi <joe.komlodi@xilinx.com> VCFG XIP is set (disabled) when the NVCFG XIP bits are all set (disabled). Signed-off-by: Joe Komlodi <komlodi@xilinx.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Message-id: 1605568264-26376-3-git-send-email-komlodi@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/block/m25p80.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/m25p80.c +++ b/hw/block/m25p80.c @@ -XXX,XX +XXX,XX @@ static void reset_memory(Flash *s) s->volatile_cfg |= VCFG_DUMMY; s->volatile_cfg |= VCFG_WRAP_SEQUENTIAL; if ((s->nonvolatile_cfg & NVCFG_XIP_MODE_MASK) - != NVCFG_XIP_MODE_DISABLED) { + == NVCFG_XIP_MODE_DISABLED) { s->volatile_cfg |= VCFG_XIP_MODE_DISABLED; } s->volatile_cfg |= deposit32(s->volatile_cfg, -- 2.20.1 From: Joe Komlodi <joe.komlodi@xilinx.com> Some Numonyx flash commands cannot be executed in DIO and QIO mode, such as trying to do DPP or DOR when in QIO mode. Signed-off-by: Joe Komlodi <komlodi@xilinx.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Message-id: 1605568264-26376-4-git-send-email-komlodi@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/block/m25p80.c | 114 ++++++++++++++++++++++++++++++++++++++-------- 1 file changed, 95 insertions(+), 19 deletions(-) diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/m25p80.c +++ b/hw/block/m25p80.c @@ -XXX,XX +XXX,XX @@ typedef enum { MAN_GENERIC, } Manufacturer; +typedef enum { + MODE_STD = 0, + MODE_DIO = 1, + MODE_QIO = 2 +} SPIMode; + #define M25P80_INTERNAL_DATA_BUFFER_SZ 16 struct Flash { @@ -XXX,XX +XXX,XX @@ static void reset_memory(Flash *s) trace_m25p80_reset_done(s); } +static uint8_t numonyx_mode(Flash *s) +{ + if (!(s->enh_volatile_cfg & EVCFG_QUAD_IO_DISABLED)) { + return MODE_QIO; + } else if (!(s->enh_volatile_cfg & EVCFG_DUAL_IO_DISABLED)) { + return MODE_DIO; + } else { + return MODE_STD; + } +} + static void decode_fast_read_cmd(Flash *s) { s->needed_bytes = get_addr_length(s); @@ -XXX,XX +XXX,XX @@ static void decode_new_cmd(Flash *s, uint32_t value) case ERASE4_32K: case ERASE_SECTOR: case ERASE4_SECTOR: - case READ: - case READ4: - case DPP: - case QPP: - case QPP_4: case PP: case PP4: - case PP4_4: case DIE_ERASE: case RDID_90: case RDID_AB: @@ -XXX,XX +XXX,XX @@ static void decode_new_cmd(Flash *s, uint32_t value) s->len = 0; s->state = STATE_COLLECTING_DATA; break; + case READ: + case READ4: + if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) == MODE_STD) { + s->needed_bytes = get_addr_length(s); + s->pos = 0; + s->len = 0; + s->state = STATE_COLLECTING_DATA; + } else { + qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute cmd %x in " + "DIO or QIO mode\n", s->cmd_in_progress); + } + break; + case DPP: + if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) != MODE_QIO) { + s->needed_bytes = get_addr_length(s); + s->pos = 0; + s->len = 0; + s->state = STATE_COLLECTING_DATA; + } else { + qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute cmd %x in " + "QIO mode\n", s->cmd_in_progress); + } + break; + case QPP: + case QPP_4: + case PP4_4: + if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) != MODE_DIO) { + s->needed_bytes = get_addr_length(s); + s->pos = 0; + s->len = 0; + s->state = STATE_COLLECTING_DATA; + } else { + qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute cmd %x in " + "DIO mode\n", s->cmd_in_progress); + } + break; case FAST_READ: case FAST_READ4: + decode_fast_read_cmd(s); + break; case DOR: case DOR4: + if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) != MODE_QIO) { + decode_fast_read_cmd(s); + } else { + qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute cmd %x in " + "QIO mode\n", s->cmd_in_progress); + } + break; case QOR: case QOR4: - decode_fast_read_cmd(s); + if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) != MODE_DIO) { + decode_fast_read_cmd(s); + } else { + qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute cmd %x in " + "DIO mode\n", s->cmd_in_progress); + } break; case DIOR: case DIOR4: - decode_dio_read_cmd(s); + if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) != MODE_QIO) { + decode_dio_read_cmd(s); + } else { + qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute cmd %x in " + "QIO mode\n", s->cmd_in_progress); + } break; case QIOR: case QIOR4: - decode_qio_read_cmd(s); + if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) != MODE_DIO) { + decode_qio_read_cmd(s); + } else { + qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute cmd %x in " + "DIO mode\n", s->cmd_in_progress); + } break; case WRSR: @@ -XXX,XX +XXX,XX @@ static void decode_new_cmd(Flash *s, uint32_t value) break; case JEDEC_READ: - trace_m25p80_populated_jedec(s); - for (i = 0; i < s->pi->id_len; i++) { - s->data[i] = s->pi->id[i]; - } - for (; i < SPI_NOR_MAX_ID_LEN; i++) { - s->data[i] = 0; - } + if (get_man(s) != MAN_NUMONYX || numonyx_mode(s) == MODE_STD) { + trace_m25p80_populated_jedec(s); + for (i = 0; i < s->pi->id_len; i++) { + s->data[i] = s->pi->id[i]; + } + for (; i < SPI_NOR_MAX_ID_LEN; i++) { + s->data[i] = 0; + } - s->len = SPI_NOR_MAX_ID_LEN; - s->pos = 0; - s->state = STATE_READING_DATA; + s->len = SPI_NOR_MAX_ID_LEN; + s->pos = 0; + s->state = STATE_READING_DATA; + } else { + qemu_log_mask(LOG_GUEST_ERROR, "M25P80: Cannot execute JEDEC read " + "in DIO or QIO mode\n"); + } break; case RDCR: -- 2.20.1 From: Joe Komlodi <joe.komlodi@xilinx.com> Numonyx chips determine the number of cycles to wait based on bits 7:4 in the volatile configuration register. However, if these bits are 0x0 or 0xF, the number of dummy cycles to wait is 10 for QIOR and QIOR4 commands or when in QIO mode, and otherwise 8 for the currently supported fast read commands. [1] [1] https://www.micron.com/-/media/client/global/documents/products/data-sheet/nor-flash/serial-nor/mt25q/die-rev-b/mt25q_qlkt_u_02g_cbb_0.pdf?rev=9b167fbf2b3645efba6385949a72e453 Signed-off-by: Joe Komlodi <komlodi@xilinx.com> Reviewed-by: Francisco Iglesias <francisco.iglesias@xilinx.com> Message-id: 1605568264-26376-5-git-send-email-komlodi@xilinx.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/block/m25p80.c | 30 +++++++++++++++++++++++++++--- 1 file changed, 27 insertions(+), 3 deletions(-) diff --git a/hw/block/m25p80.c b/hw/block/m25p80.c index XXXXXXX..XXXXXXX 100644 --- a/hw/block/m25p80.c +++ b/hw/block/m25p80.c @@ -XXX,XX +XXX,XX @@ static uint8_t numonyx_mode(Flash *s) } } +static uint8_t numonyx_extract_cfg_num_dummies(Flash *s) +{ + uint8_t num_dummies; + uint8_t mode; + assert(get_man(s) == MAN_NUMONYX); + + mode = numonyx_mode(s); + num_dummies = extract32(s->volatile_cfg, 4, 4); + + if (num_dummies == 0x0 || num_dummies == 0xf) { + switch (s->cmd_in_progress) { + case QIOR: + case QIOR4: + num_dummies = 10; + break; + default: + num_dummies = (mode == MODE_QIO) ? 10 : 8; + break; + } + } + + return num_dummies; +} + static void decode_fast_read_cmd(Flash *s) { s->needed_bytes = get_addr_length(s); @@ -XXX,XX +XXX,XX @@ static void decode_fast_read_cmd(Flash *s) s->needed_bytes += 8; break; case MAN_NUMONYX: - s->needed_bytes += extract32(s->volatile_cfg, 4, 4); + s->needed_bytes += numonyx_extract_cfg_num_dummies(s); break; case MAN_MACRONIX: if (extract32(s->volatile_cfg, 6, 2) == 1) { @@ -XXX,XX +XXX,XX @@ static void decode_dio_read_cmd(Flash *s) ); break; case MAN_NUMONYX: - s->needed_bytes += extract32(s->volatile_cfg, 4, 4); + s->needed_bytes += numonyx_extract_cfg_num_dummies(s); break; case MAN_MACRONIX: switch (extract32(s->volatile_cfg, 6, 2)) { @@ -XXX,XX +XXX,XX @@ static void decode_qio_read_cmd(Flash *s) ); break; case MAN_NUMONYX: - s->needed_bytes += extract32(s->volatile_cfg, 4, 4); + s->needed_bytes += numonyx_extract_cfg_num_dummies(s); break; case MAN_MACRONIX: switch (extract32(s->volatile_cfg, 6, 2)) { -- 2.20.1 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