A random mix of items here, nothing very major. thanks -- PMM The following changes since commit d0dff238a87fa81393ed72754d4dc8b09e50b08b: Merge remote-tracking branch 'remotes/juanquintela/tags/migration/20170206' into staging (2017-02-07 15:29:26 +0000) are available in the git repository at: git://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20170207 for you to fetch changes up to 7727b832886fafbdec7299eb7773dc9071bf4cdd: stellaris: Use the 'unimplemented' device for parts we don't implement (2017-02-07 18:30:00 +0000) ---------------------------------------------------------------- target-arm: * new "unimplemented" device for stubbing out devices in a system model so accesses can be logged * stellaris: document the SoC memory map * arm: create instruction syndromes for AArch32 data aborts * arm: Correctly handle watchpoints for BE32 CPUs * Fix Thumb-1 BE32 execution and disassembly * arm: Add cfgend parameter for ARM CPU selection * sd: sdhci: check data length during dma_memory_read * aspeed: add a watchdog controller * integratorcp: adding vmstate for save/restore ---------------------------------------------------------------- Cédric Le Goater (2): wdt: Add Aspeed watchdog device model aspeed: add a watchdog controller Julian Brown (4): hw/arm/integratorcp: Support specifying features via -cpu target/arm: Add cfgend parameter for ARM CPU selection. Fix Thumb-1 BE32 execution and disassembly. arm: Correctly handle watchpoints for BE32 CPUs Pavel Dovgalyuk (1): integratorcp: adding vmstate for save/restore Peter Maydell (5): target/arm: Abstract out pbit/wbit tests in ARM ldr/str decode target/arm: A32, T32: Create Instruction Syndromes for Data Aborts stellaris: Document memory map and which SoC devices are unimplemented hw/misc: New "unimplemented" sysbus device stellaris: Use the 'unimplemented' device for parts we don't implement Prasad J Pandit (1): sd: sdhci: check data length during dma_memory_read hw/misc/Makefile.objs | 2 + hw/watchdog/Makefile.objs | 1 + include/disas/bfd.h | 7 ++ include/hw/arm/aspeed_soc.h | 2 + include/hw/misc/unimp.h | 39 +++++++ include/hw/watchdog/wdt_aspeed.h | 32 ++++++ include/qom/cpu.h | 3 + target/arm/arm_ldst.h | 10 +- target/arm/cpu.h | 7 ++ target/arm/internals.h | 5 + target/arm/translate.h | 14 +++ disas.c | 1 + exec.c | 1 + hw/arm/aspeed_soc.c | 13 +++ hw/arm/integratorcp.c | 78 +++++++++++++- hw/arm/stellaris.c | 48 +++++++++ hw/misc/unimp.c | 107 +++++++++++++++++++ hw/sd/sdhci.c | 2 +- hw/watchdog/wdt_aspeed.c | 225 +++++++++++++++++++++++++++++++++++++++ qom/cpu.c | 6 ++ target/arm/cpu.c | 39 +++++++ target/arm/op_helper.c | 22 ++++ target/arm/translate-a64.c | 14 --- target/arm/translate.c | 193 ++++++++++++++++++++++++--------- 24 files changed, 801 insertions(+), 70 deletions(-) create mode 100644 include/hw/misc/unimp.h create mode 100644 include/hw/watchdog/wdt_aspeed.h create mode 100644 hw/misc/unimp.c create mode 100644 hw/watchdog/wdt_aspeed.c From: Pavel Dovgalyuk <Pavel.Dovgaluk@ispras.ru> VMState added by this patch preserves correct loading of the integratorcp device state. Signed-off-by: Pavel Dovgalyuk <pavel.dovgaluk@ispras.ru> Message-id: 20170131114310.6768.79416.stgit@PASHA-ISP [PMM: removed unnecessary minimum_version_id_old lines] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/integratorcp.c | 59 +++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 59 insertions(+) diff --git a/hw/arm/integratorcp.c b/hw/arm/integratorcp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/integratorcp.c +++ b/hw/arm/integratorcp.c @@ -XXX,XX +XXX,XX @@ static uint8_t integrator_spd[128] = { 0xe, 4, 0x1c, 1, 2, 0x20, 0xc0, 0, 0, 0, 0, 0x30, 0x28, 0x30, 0x28, 0x40 }; +static const VMStateDescription vmstate_integratorcm = { + .name = "integratorcm", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(cm_osc, IntegratorCMState), + VMSTATE_UINT32(cm_ctrl, IntegratorCMState), + VMSTATE_UINT32(cm_lock, IntegratorCMState), + VMSTATE_UINT32(cm_auxosc, IntegratorCMState), + VMSTATE_UINT32(cm_sdram, IntegratorCMState), + VMSTATE_UINT32(cm_init, IntegratorCMState), + VMSTATE_UINT32(cm_flags, IntegratorCMState), + VMSTATE_UINT32(cm_nvflags, IntegratorCMState), + VMSTATE_UINT32(int_level, IntegratorCMState), + VMSTATE_UINT32(irq_enabled, IntegratorCMState), + VMSTATE_UINT32(fiq_enabled, IntegratorCMState), + VMSTATE_END_OF_LIST() + } +}; + static uint64_t integratorcm_read(void *opaque, hwaddr offset, unsigned size) { @@ -XXX,XX +XXX,XX @@ typedef struct icp_pic_state { qemu_irq parent_fiq; } icp_pic_state; +static const VMStateDescription vmstate_icp_pic = { + .name = "icp_pic", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(level, icp_pic_state), + VMSTATE_UINT32(irq_enabled, icp_pic_state), + VMSTATE_UINT32(fiq_enabled, icp_pic_state), + VMSTATE_END_OF_LIST() + } +}; + static void icp_pic_update(icp_pic_state *s) { uint32_t flags; @@ -XXX,XX +XXX,XX @@ typedef struct ICPCtrlRegsState { #define ICP_INTREG_WPROT (1 << 0) #define ICP_INTREG_CARDIN (1 << 3) +static const VMStateDescription vmstate_icp_control = { + .name = "icp_control", + .version_id = 1, + .minimum_version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_UINT32(intreg_state, ICPCtrlRegsState), + VMSTATE_END_OF_LIST() + } +}; + static uint64_t icp_control_read(void *opaque, hwaddr offset, unsigned size) { @@ -XXX,XX +XXX,XX @@ static void core_class_init(ObjectClass *klass, void *data) dc->props = core_properties; dc->realize = integratorcm_realize; + dc->vmsd = &vmstate_integratorcm; +} + +static void icp_pic_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->vmsd = &vmstate_icp_pic; +} + +static void icp_control_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->vmsd = &vmstate_icp_control; } static const TypeInfo core_info = { @@ -XXX,XX +XXX,XX @@ static const TypeInfo icp_pic_info = { .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(icp_pic_state), .instance_init = icp_pic_init, + .class_init = icp_pic_class_init, }; static const TypeInfo icp_ctrl_regs_info = { @@ -XXX,XX +XXX,XX @@ static const TypeInfo icp_ctrl_regs_info = { .parent = TYPE_SYS_BUS_DEVICE, .instance_size = sizeof(ICPCtrlRegsState), .instance_init = icp_control_init, + .class_init = icp_control_class_init, }; static void integratorcp_register_types(void) -- 2.7.4 From: Cédric Le Goater <clg@kaod.org> The Aspeed SoC includes a set of watchdog timers using 32-bit decrement counters, which can be based either on the APB clock or a 1 MHz clock. The watchdog timer is designed to prevent system deadlock and, in general, it should be restarted before timeout. When a timeout occurs, different types of signals can be generated, ARM reset, SOC reset, System reset, CPU Interrupt, external signal or boot from alternate block. The current model only performs the system reset function as this is used by U-Boot and Linux. Signed-off-by: Joel Stanley <joel@jms.id.au> Message-id: 1485452251-1593-2-git-send-email-clg@kaod.org [clg: - fixed compile breakage - fixed io region size - added watchdog_perform_action() on timer expiry - wrote a commit log - merged fixes from Andrew Jeffery to scale the reload value ] Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/watchdog/Makefile.objs | 1 + include/hw/watchdog/wdt_aspeed.h | 32 ++++++ hw/watchdog/wdt_aspeed.c | 225 +++++++++++++++++++++++++++++++++++++++ 3 files changed, 258 insertions(+) create mode 100644 include/hw/watchdog/wdt_aspeed.h create mode 100644 hw/watchdog/wdt_aspeed.c diff --git a/hw/watchdog/Makefile.objs b/hw/watchdog/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/watchdog/Makefile.objs +++ b/hw/watchdog/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-y += watchdog.o common-obj-$(CONFIG_WDT_IB6300ESB) += wdt_i6300esb.o common-obj-$(CONFIG_WDT_IB700) += wdt_ib700.o common-obj-$(CONFIG_WDT_DIAG288) += wdt_diag288.o +common-obj-$(CONFIG_ASPEED_SOC) += wdt_aspeed.o diff --git a/include/hw/watchdog/wdt_aspeed.h b/include/hw/watchdog/wdt_aspeed.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/watchdog/wdt_aspeed.h @@ -XXX,XX +XXX,XX @@ +/* + * ASPEED Watchdog Controller + * + * Copyright (C) 2016-2017 IBM Corp. + * + * This code is licensed under the GPL version 2 or later. See the + * COPYING file in the top-level directory. + */ +#ifndef ASPEED_WDT_H +#define ASPEED_WDT_H + +#include "hw/sysbus.h" + +#define TYPE_ASPEED_WDT "aspeed.wdt" +#define ASPEED_WDT(obj) \ + OBJECT_CHECK(AspeedWDTState, (obj), TYPE_ASPEED_WDT) + +#define ASPEED_WDT_REGS_MAX (0x20 / 4) + +typedef struct AspeedWDTState { + /*< private >*/ + SysBusDevice parent_obj; + QEMUTimer *timer; + + /*< public >*/ + MemoryRegion iomem; + uint32_t regs[ASPEED_WDT_REGS_MAX]; + + uint32_t pclk_freq; +} AspeedWDTState; + +#endif /* ASPEED_WDT_H */ diff --git a/hw/watchdog/wdt_aspeed.c b/hw/watchdog/wdt_aspeed.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/watchdog/wdt_aspeed.c @@ -XXX,XX +XXX,XX @@ +/* + * ASPEED Watchdog Controller + * + * Copyright (C) 2016-2017 IBM Corp. + * + * This code is licensed under the GPL version 2 or later. See the + * COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu/log.h" +#include "sysemu/watchdog.h" +#include "hw/sysbus.h" +#include "qemu/timer.h" +#include "hw/watchdog/wdt_aspeed.h" + +#define WDT_STATUS (0x00 / 4) +#define WDT_RELOAD_VALUE (0x04 / 4) +#define WDT_RESTART (0x08 / 4) +#define WDT_CTRL (0x0C / 4) +#define WDT_CTRL_RESET_MODE_SOC (0x00 << 5) +#define WDT_CTRL_RESET_MODE_FULL_CHIP (0x01 << 5) +#define WDT_CTRL_1MHZ_CLK BIT(4) +#define WDT_CTRL_WDT_EXT BIT(3) +#define WDT_CTRL_WDT_INTR BIT(2) +#define WDT_CTRL_RESET_SYSTEM BIT(1) +#define WDT_CTRL_ENABLE BIT(0) + +#define WDT_TIMEOUT_STATUS (0x10 / 4) +#define WDT_TIMEOUT_CLEAR (0x14 / 4) +#define WDT_RESET_WDITH (0x18 / 4) + +#define WDT_RESTART_MAGIC 0x4755 + +static bool aspeed_wdt_is_enabled(const AspeedWDTState *s) +{ + return s->regs[WDT_CTRL] & WDT_CTRL_ENABLE; +} + +static uint64_t aspeed_wdt_read(void *opaque, hwaddr offset, unsigned size) +{ + AspeedWDTState *s = ASPEED_WDT(opaque); + + offset >>= 2; + + switch (offset) { + case WDT_STATUS: + return s->regs[WDT_STATUS]; + case WDT_RELOAD_VALUE: + return s->regs[WDT_RELOAD_VALUE]; + case WDT_RESTART: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: read from write-only reg at offset 0x%" + HWADDR_PRIx "\n", __func__, offset); + return 0; + case WDT_CTRL: + return s->regs[WDT_CTRL]; + case WDT_TIMEOUT_STATUS: + case WDT_TIMEOUT_CLEAR: + case WDT_RESET_WDITH: + qemu_log_mask(LOG_UNIMP, + "%s: uninmplemented read at offset 0x%" HWADDR_PRIx "\n", + __func__, offset); + return 0; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Out-of-bounds read at offset 0x%" HWADDR_PRIx "\n", + __func__, offset); + return 0; + } + +} + +static void aspeed_wdt_reload(AspeedWDTState *s, bool pclk) +{ + uint32_t reload; + + if (pclk) { + reload = muldiv64(s->regs[WDT_RELOAD_VALUE], NANOSECONDS_PER_SECOND, + s->pclk_freq); + } else { + reload = s->regs[WDT_RELOAD_VALUE] * 1000; + } + + if (aspeed_wdt_is_enabled(s)) { + timer_mod(s->timer, qemu_clock_get_ns(QEMU_CLOCK_VIRTUAL) + reload); + } +} + +static void aspeed_wdt_write(void *opaque, hwaddr offset, uint64_t data, + unsigned size) +{ + AspeedWDTState *s = ASPEED_WDT(opaque); + bool enable = data & WDT_CTRL_ENABLE; + + offset >>= 2; + + switch (offset) { + case WDT_STATUS: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: write to read-only reg at offset 0x%" + HWADDR_PRIx "\n", __func__, offset); + break; + case WDT_RELOAD_VALUE: + s->regs[WDT_RELOAD_VALUE] = data; + break; + case WDT_RESTART: + if ((data & 0xFFFF) == WDT_RESTART_MAGIC) { + s->regs[WDT_STATUS] = s->regs[WDT_RELOAD_VALUE]; + aspeed_wdt_reload(s, !(data & WDT_CTRL_1MHZ_CLK)); + } + break; + case WDT_CTRL: + if (enable && !aspeed_wdt_is_enabled(s)) { + s->regs[WDT_CTRL] = data; + aspeed_wdt_reload(s, !(data & WDT_CTRL_1MHZ_CLK)); + } else if (!enable && aspeed_wdt_is_enabled(s)) { + s->regs[WDT_CTRL] = data; + timer_del(s->timer); + } + break; + case WDT_TIMEOUT_STATUS: + case WDT_TIMEOUT_CLEAR: + case WDT_RESET_WDITH: + qemu_log_mask(LOG_UNIMP, + "%s: uninmplemented write at offset 0x%" HWADDR_PRIx "\n", + __func__, offset); + break; + default: + qemu_log_mask(LOG_GUEST_ERROR, + "%s: Out-of-bounds write at offset 0x%" HWADDR_PRIx "\n", + __func__, offset); + } + return; +} + +static WatchdogTimerModel model = { + .wdt_name = TYPE_ASPEED_WDT, + .wdt_description = "Aspeed watchdog device", +}; + +static const VMStateDescription vmstate_aspeed_wdt = { + .name = "vmstate_aspeed_wdt", + .version_id = 0, + .minimum_version_id = 0, + .fields = (VMStateField[]) { + VMSTATE_TIMER_PTR(timer, AspeedWDTState), + VMSTATE_UINT32_ARRAY(regs, AspeedWDTState, ASPEED_WDT_REGS_MAX), + VMSTATE_END_OF_LIST() + } +}; + +static const MemoryRegionOps aspeed_wdt_ops = { + .read = aspeed_wdt_read, + .write = aspeed_wdt_write, + .endianness = DEVICE_LITTLE_ENDIAN, + .valid.min_access_size = 4, + .valid.max_access_size = 4, + .valid.unaligned = false, +}; + +static void aspeed_wdt_reset(DeviceState *dev) +{ + AspeedWDTState *s = ASPEED_WDT(dev); + + s->regs[WDT_STATUS] = 0x3EF1480; + s->regs[WDT_RELOAD_VALUE] = 0x03EF1480; + s->regs[WDT_RESTART] = 0; + s->regs[WDT_CTRL] = 0; + + timer_del(s->timer); +} + +static void aspeed_wdt_timer_expired(void *dev) +{ + AspeedWDTState *s = ASPEED_WDT(dev); + + qemu_log_mask(CPU_LOG_RESET, "Watchdog timer expired.\n"); + watchdog_perform_action(); + timer_del(s->timer); +} + +#define PCLK_HZ 24000000 + +static void aspeed_wdt_realize(DeviceState *dev, Error **errp) +{ + SysBusDevice *sbd = SYS_BUS_DEVICE(dev); + AspeedWDTState *s = ASPEED_WDT(dev); + + s->timer = timer_new_ns(QEMU_CLOCK_VIRTUAL, aspeed_wdt_timer_expired, dev); + + /* FIXME: This setting should be derived from the SCU hw strapping + * register SCU70 + */ + s->pclk_freq = PCLK_HZ; + + memory_region_init_io(&s->iomem, OBJECT(s), &aspeed_wdt_ops, s, + TYPE_ASPEED_WDT, ASPEED_WDT_REGS_MAX * 4); + sysbus_init_mmio(sbd, &s->iomem); +} + +static void aspeed_wdt_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = aspeed_wdt_realize; + dc->reset = aspeed_wdt_reset; + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + dc->vmsd = &vmstate_aspeed_wdt; +} + +static const TypeInfo aspeed_wdt_info = { + .parent = TYPE_SYS_BUS_DEVICE, + .name = TYPE_ASPEED_WDT, + .instance_size = sizeof(AspeedWDTState), + .class_init = aspeed_wdt_class_init, +}; + +static void wdt_aspeed_register_types(void) +{ + watchdog_add_model(&model); + type_register_static(&aspeed_wdt_info); +} + +type_init(wdt_aspeed_register_types) -- 2.7.4 From: Cédric Le Goater <clg@kaod.org> This enables reboot of a guest from U-Boot and Linux. Signed-off-by: Cédric Le Goater <clg@kaod.org> Reviewed-by: Joel Stanley <joel@jms.id.au> Message-id: 1485452251-1593-3-git-send-email-clg@kaod.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/aspeed_soc.h | 2 ++ hw/arm/aspeed_soc.c | 13 +++++++++++++ 2 files changed, 15 insertions(+) diff --git a/include/hw/arm/aspeed_soc.h b/include/hw/arm/aspeed_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/aspeed_soc.h +++ b/include/hw/arm/aspeed_soc.h @@ -XXX,XX +XXX,XX @@ #include "hw/timer/aspeed_timer.h" #include "hw/i2c/aspeed_i2c.h" #include "hw/ssi/aspeed_smc.h" +#include "hw/watchdog/wdt_aspeed.h" #define ASPEED_SPIS_NUM 2 @@ -XXX,XX +XXX,XX @@ typedef struct AspeedSoCState { AspeedSMCState fmc; AspeedSMCState spi[ASPEED_SPIS_NUM]; AspeedSDMCState sdmc; + AspeedWDTState wdt; } AspeedSoCState; #define TYPE_ASPEED_SOC "aspeed-soc" diff --git a/hw/arm/aspeed_soc.c b/hw/arm/aspeed_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/aspeed_soc.c +++ b/hw/arm/aspeed_soc.c @@ -XXX,XX +XXX,XX @@ #define ASPEED_SOC_SCU_BASE 0x1E6E2000 #define ASPEED_SOC_SRAM_BASE 0x1E720000 #define ASPEED_SOC_TIMER_BASE 0x1E782000 +#define ASPEED_SOC_WDT_BASE 0x1E785000 #define ASPEED_SOC_I2C_BASE 0x1E78A000 static const int uart_irqs[] = { 9, 32, 33, 34, 10 }; @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_init(Object *obj) sc->info->silicon_rev); object_property_add_alias(obj, "ram-size", OBJECT(&s->sdmc), "ram-size", &error_abort); + + object_initialize(&s->wdt, sizeof(s->wdt), TYPE_ASPEED_WDT); + object_property_add_child(obj, "wdt", OBJECT(&s->wdt), NULL); + qdev_set_parent_bus(DEVICE(&s->wdt), sysbus_get_default()); } static void aspeed_soc_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void aspeed_soc_realize(DeviceState *dev, Error **errp) return; } sysbus_mmio_map(SYS_BUS_DEVICE(&s->sdmc), 0, ASPEED_SOC_SDMC_BASE); + + /* Watch dog */ + object_property_set_bool(OBJECT(&s->wdt), true, "realized", &err); + if (err) { + error_propagate(errp, err); + return; + } + sysbus_mmio_map(SYS_BUS_DEVICE(&s->wdt), 0, ASPEED_SOC_WDT_BASE); } static void aspeed_soc_class_init(ObjectClass *oc, void *data) -- 2.7.4 From: Prasad J Pandit <pjp@fedoraproject.org> While doing multi block SDMA transfer in routine 'sdhci_sdma_transfer_multi_blocks', the 's->fifo_buffer' starting index 'begin' and data length 's->data_count' could end up to be same. This could lead to an OOB access issue. Correct transfer data length to avoid it. Cc: qemu-stable@nongnu.org Reported-by: Jiang Xin <jiangxin1@huawei.com> Signed-off-by: Prasad J Pandit <pjp@fedoraproject.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20170130064736.9236-1-ppandit@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/sd/sdhci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/hw/sd/sdhci.c b/hw/sd/sdhci.c index XXXXXXX..XXXXXXX 100644 --- a/hw/sd/sdhci.c +++ b/hw/sd/sdhci.c @@ -XXX,XX +XXX,XX @@ static void sdhci_sdma_transfer_multi_blocks(SDHCIState *s) boundary_count -= block_size - begin; } dma_memory_read(&address_space_memory, s->sdmasysad, - &s->fifo_buffer[begin], s->data_count); + &s->fifo_buffer[begin], s->data_count - begin); s->sdmasysad += s->data_count - begin; if (s->data_count == block_size) { for (n = 0; n < block_size; n++) { -- 2.7.4 From: Julian Brown <julian@codesourcery.com> Since the integratorcp board creates the CPU object directly rather than via cpu_arm_init(), we have to call the CPU class parse_features() method ourselves if we want to support the user passing features via the -cpu command line argument as well as just the cpu name. Do so. Signed-off-by: Julian Brown <julian@codesourcery.com> [PMM: split out into its own patch] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/integratorcp.c | 19 +++++++++++++++++-- 1 file changed, 17 insertions(+), 2 deletions(-) diff --git a/hw/arm/integratorcp.c b/hw/arm/integratorcp.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/integratorcp.c +++ b/hw/arm/integratorcp.c @@ -XXX,XX +XXX,XX @@ static void integratorcp_init(MachineState *machine) const char *kernel_filename = machine->kernel_filename; const char *kernel_cmdline = machine->kernel_cmdline; const char *initrd_filename = machine->initrd_filename; + char **cpustr; ObjectClass *cpu_oc; + CPUClass *cc; Object *cpuobj; ARMCPU *cpu; + const char *typename; MemoryRegion *address_space_mem = get_system_memory(); MemoryRegion *ram = g_new(MemoryRegion, 1); MemoryRegion *ram_alias = g_new(MemoryRegion, 1); qemu_irq pic[32]; DeviceState *dev, *sic, *icp; int i; + Error *err = NULL; if (!cpu_model) { cpu_model = "arm926"; } - cpu_oc = cpu_class_by_name(TYPE_ARM_CPU, cpu_model); + cpustr = g_strsplit(cpu_model, ",", 2); + + cpu_oc = cpu_class_by_name(TYPE_ARM_CPU, cpustr[0]); if (!cpu_oc) { fprintf(stderr, "Unable to find CPU definition\n"); exit(1); } + typename = object_class_get_name(cpu_oc); + + cc = CPU_CLASS(cpu_oc); + cc->parse_features(typename, cpustr[1], &err); + g_strfreev(cpustr); + if (err) { + error_report_err(err); + exit(1); + } - cpuobj = object_new(object_class_get_name(cpu_oc)); + cpuobj = object_new(typename); /* By default ARM1176 CPUs have EL3 enabled. This board does not * currently support EL3 so the CPU EL3 property is disabled before -- 2.7.4 From: Julian Brown <julian@codesourcery.com> Add a new "cfgend" property which selects whether the CPU resets into big-endian mode or not. This setting affects whether we reset with SCTLR_B (ARMv6 and earlier) or SCTLR_EE (ARMv7 and later) set. Signed-off-by: Julian Brown <julian@codesourcery.com> Message-id: 11420d1c49636c1790e60578ee996e51f0f0b835.1484929304.git.julian@codesourcery.com [PMM: use error_report_err() rather than error_report(); move the integratorcp changes to their own patch; drop an unnecessary extra #include; rephrase commit message accordingly; move setting of reset_sctlr above registration of cpregs so it actually has an effect] Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- target/arm/cpu.h | 7 +++++++ target/arm/cpu.c | 13 +++++++++++++ 2 files changed, 20 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ struct ARMCPU { int gic_vpribits; /* number of virtual priority bits */ int gic_vprebits; /* number of virtual preemption bits */ + /* Whether the cfgend input is high (i.e. this CPU should reset into + * big-endian mode). This setting isn't used directly: instead it modifies + * the reset_sctlr value to have SCTLR_B or SCTLR_EE set, depending on the + * architecture version. + */ + bool cfgend; + ARMELChangeHook *el_change_hook; void *el_change_hook_opaque; }; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static Property arm_cpu_has_el2_property = static Property arm_cpu_has_el3_property = DEFINE_PROP_BOOL("has_el3", ARMCPU, has_el3, true); +static Property arm_cpu_cfgend_property = + DEFINE_PROP_BOOL("cfgend", ARMCPU, cfgend, false); + /* use property name "pmu" to match other archs and virt tools */ static Property arm_cpu_has_pmu_property = DEFINE_PROP_BOOL("pmu", ARMCPU, has_pmu, true); @@ -XXX,XX +XXX,XX @@ static void arm_cpu_post_init(Object *obj) } } + qdev_property_add_static(DEVICE(obj), &arm_cpu_cfgend_property, + &error_abort); } static void arm_cpu_finalizefn(Object *obj) @@ -XXX,XX +XXX,XX @@ static void arm_cpu_realizefn(DeviceState *dev, Error **errp) cpu->reset_sctlr |= (1 << 13); } + if (cpu->cfgend) { + if (arm_feature(&cpu->env, ARM_FEATURE_V7)) { + cpu->reset_sctlr |= SCTLR_EE; + } else { + cpu->reset_sctlr |= SCTLR_B; + } + } + if (!cpu->has_el3) { /* If the has_el3 CPU property is disabled then we need to disable the * feature. -- 2.7.4 From: Julian Brown <julian@codesourcery.com> Thumb-1 code has some issues in BE32 mode (as currently implemented). In short, since bytes are swapped within words at load time for BE32 executables, this also swaps pairs of adjacent Thumb-1 instructions. This patch un-swaps those pairs of instructions again, both for execution, and for disassembly. (The previous version of the patch always read four bytes in arm_read_memory_func and then extracted the proper two bytes, in a probably misguided attempt to match the behaviour of actual hardware as described by e.g. the ARM9TDMI TRM, section 3.3 "Endian effects for instruction fetches". It's less complicated to just read the correct two bytes though.) Signed-off-by: Julian Brown <julian@codesourcery.com> Message-id: ca20462a044848000370318a8bd41dd0a4ed273f.1484929304.git.julian@codesourcery.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/disas/bfd.h | 7 +++++++ target/arm/arm_ldst.h | 10 +++++++++- disas.c | 1 + target/arm/cpu.c | 23 +++++++++++++++++++++++ 4 files changed, 40 insertions(+), 1 deletion(-) diff --git a/include/disas/bfd.h b/include/disas/bfd.h index XXXXXXX..XXXXXXX 100644 --- a/include/disas/bfd.h +++ b/include/disas/bfd.h @@ -XXX,XX +XXX,XX @@ typedef struct disassemble_info { The bottom 16 bits are for the internal use of the disassembler. */ unsigned long flags; #define INSN_HAS_RELOC 0x80000000 +#define INSN_ARM_BE32 0x00010000 PTR private_data; /* Function used to get bytes to disassemble. MEMADDR is the @@ -XXX,XX +XXX,XX @@ typedef struct disassemble_info { (bfd_vma memaddr, bfd_byte *myaddr, int length, struct disassemble_info *info); + /* A place to stash the real read_memory_func if read_memory_func wants to + do some funky address arithmetic or similar (e.g. for ARM BE32 mode). */ + int (*read_memory_inner_func) + (bfd_vma memaddr, bfd_byte *myaddr, int length, + struct disassemble_info *info); + /* Function which should be called if we get an error that we can't recover from. STATUS is the errno value from read_memory_func and MEMADDR is the address that we were trying to read. INFO is a diff --git a/target/arm/arm_ldst.h b/target/arm/arm_ldst.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/arm_ldst.h +++ b/target/arm/arm_ldst.h @@ -XXX,XX +XXX,XX @@ static inline uint32_t arm_ldl_code(CPUARMState *env, target_ulong addr, static inline uint16_t arm_lduw_code(CPUARMState *env, target_ulong addr, bool sctlr_b) { - uint16_t insn = cpu_lduw_code(env, addr); + uint16_t insn; +#ifndef CONFIG_USER_ONLY + /* In big-endian (BE32) mode, adjacent Thumb instructions have been swapped + within each word. Undo that now. */ + if (sctlr_b) { + addr ^= 2; + } +#endif + insn = cpu_lduw_code(env, addr); if (bswap_code(sctlr_b)) { return bswap16(insn); } diff --git a/disas.c b/disas.c index XXXXXXX..XXXXXXX 100644 --- a/disas.c +++ b/disas.c @@ -XXX,XX +XXX,XX @@ void target_disas(FILE *out, CPUState *cpu, target_ulong code, s.cpu = cpu; s.info.read_memory_func = target_read_memory; + s.info.read_memory_inner_func = NULL; s.info.buffer_vma = code; s.info.buffer_length = size; s.info.print_address_func = generic_print_address; 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 @@ print_insn_thumb1(bfd_vma pc, disassemble_info *info) return print_insn_arm(pc | 1, info); } +static int arm_read_memory_func(bfd_vma memaddr, bfd_byte *b, + int length, struct disassemble_info *info) +{ + assert(info->read_memory_inner_func); + assert((info->flags & INSN_ARM_BE32) == 0 || length == 2 || length == 4); + + if ((info->flags & INSN_ARM_BE32) != 0 && length == 2) { + assert(info->endian == BFD_ENDIAN_LITTLE); + return info->read_memory_inner_func(memaddr ^ 2, (bfd_byte *)b, 2, + info); + } else { + return info->read_memory_inner_func(memaddr, b, length, info); + } +} + static void arm_disas_set_info(CPUState *cpu, disassemble_info *info) { ARMCPU *ac = ARM_CPU(cpu); @@ -XXX,XX +XXX,XX @@ static void arm_disas_set_info(CPUState *cpu, disassemble_info *info) info->endian = BFD_ENDIAN_BIG; #endif } + if (info->read_memory_inner_func == NULL) { + info->read_memory_inner_func = info->read_memory_func; + info->read_memory_func = arm_read_memory_func; + } + info->flags &= ~INSN_ARM_BE32; + if (arm_sctlr_b(env)) { + info->flags |= INSN_ARM_BE32; + } } static void arm_cpu_initfn(Object *obj) -- 2.7.4 From: Julian Brown <julian@codesourcery.com> In BE32 mode, sub-word size watchpoints can fail to trigger because the address of the access is adjusted in the opcode helpers before being compared with the watchpoint registers. This patch reverses the address adjustment before performing the comparison with the help of a new CPUClass hook. This version of the patch augments and tidies up comments a little. Signed-off-by: Julian Brown <julian@codesourcery.com> Message-id: caaf64ffc72f6ae183015337b7afdbd4b8989cb6.1484929304.git.julian@codesourcery.com Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/qom/cpu.h | 3 +++ target/arm/internals.h | 5 +++++ exec.c | 1 + qom/cpu.c | 6 ++++++ target/arm/cpu.c | 3 +++ target/arm/op_helper.c | 22 ++++++++++++++++++++++ 6 files changed, 40 insertions(+) diff --git a/include/qom/cpu.h b/include/qom/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/include/qom/cpu.h +++ b/include/qom/cpu.h @@ -XXX,XX +XXX,XX @@ struct TranslationBlock; * @cpu_exec_exit: Callback for cpu_exec cleanup. * @cpu_exec_interrupt: Callback for processing interrupts in cpu_exec. * @disas_set_info: Setup architecture specific components of disassembly info + * @adjust_watchpoint_address: Perform a target-specific adjustment to an + * address before attempting to match it against watchpoints. * * Represents a CPU family or model. */ @@ -XXX,XX +XXX,XX @@ typedef struct CPUClass { bool (*cpu_exec_interrupt)(CPUState *cpu, int interrupt_request); void (*disas_set_info)(CPUState *cpu, disassemble_info *info); + vaddr (*adjust_watchpoint_address)(CPUState *cpu, vaddr addr, int len); } CPUClass; #ifdef HOST_WORDS_BIGENDIAN diff --git a/target/arm/internals.h b/target/arm/internals.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/internals.h +++ b/target/arm/internals.h @@ -XXX,XX +XXX,XX @@ void hw_breakpoint_update_all(ARMCPU *cpu); /* Callback function for checking if a watchpoint should trigger. */ bool arm_debug_check_watchpoint(CPUState *cs, CPUWatchpoint *wp); +/* Adjust addresses (in BE32 mode) before testing against watchpoint + * addresses. + */ +vaddr arm_adjust_watchpoint_address(CPUState *cs, vaddr addr, int len); + /* Callback function for when a watchpoint or breakpoint triggers. */ void arm_debug_excp_handler(CPUState *cs); diff --git a/exec.c b/exec.c index XXXXXXX..XXXXXXX 100644 --- a/exec.c +++ b/exec.c @@ -XXX,XX +XXX,XX @@ static void check_watchpoint(int offset, int len, MemTxAttrs attrs, int flags) return; } vaddr = (cpu->mem_io_vaddr & TARGET_PAGE_MASK) + offset; + vaddr = cc->adjust_watchpoint_address(cpu, vaddr, len); QTAILQ_FOREACH(wp, &cpu->watchpoints, entry) { if (cpu_watchpoint_address_matches(wp, vaddr, len) && (wp->flags & flags)) { diff --git a/qom/cpu.c b/qom/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/qom/cpu.c +++ b/qom/cpu.c @@ -XXX,XX +XXX,XX @@ static int64_t cpu_common_get_arch_id(CPUState *cpu) return cpu->cpu_index; } +static vaddr cpu_adjust_watchpoint_address(CPUState *cpu, vaddr addr, int len) +{ + return addr; +} + static void cpu_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); @@ -XXX,XX +XXX,XX @@ static void cpu_class_init(ObjectClass *klass, void *data) k->cpu_exec_enter = cpu_common_noop; k->cpu_exec_exit = cpu_common_noop; k->cpu_exec_interrupt = cpu_common_exec_interrupt; + k->adjust_watchpoint_address = cpu_adjust_watchpoint_address; set_bit(DEVICE_CATEGORY_CPU, dc->categories); dc->realize = cpu_common_realizefn; dc->unrealize = cpu_common_unrealizefn; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_class_init(ObjectClass *oc, void *data) cc->gdb_stop_before_watchpoint = true; cc->debug_excp_handler = arm_debug_excp_handler; cc->debug_check_watchpoint = arm_debug_check_watchpoint; +#if !defined(CONFIG_USER_ONLY) + cc->adjust_watchpoint_address = arm_adjust_watchpoint_address; +#endif cc->disas_set_info = arm_disas_set_info; } diff --git a/target/arm/op_helper.c b/target/arm/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/op_helper.c +++ b/target/arm/op_helper.c @@ -XXX,XX +XXX,XX @@ bool arm_debug_check_watchpoint(CPUState *cs, CPUWatchpoint *wp) return check_watchpoints(cpu); } +vaddr arm_adjust_watchpoint_address(CPUState *cs, vaddr addr, int len) +{ + ARMCPU *cpu = ARM_CPU(cs); + CPUARMState *env = &cpu->env; + + /* In BE32 system mode, target memory is stored byteswapped (on a + * little-endian host system), and by the time we reach here (via an + * opcode helper) the addresses of subword accesses have been adjusted + * to account for that, which means that watchpoints will not match. + * Undo the adjustment here. + */ + if (arm_sctlr_b(env)) { + if (len == 1) { + addr ^= 3; + } else if (len == 2) { + addr ^= 2; + } + } + + return addr; +} + void arm_debug_excp_handler(CPUState *cs) { /* Called by core code when a watchpoint or breakpoint fires; -- 2.7.4 In the ARM ldr/str decode path, rather than directly testing "insn & (1 << 21)" and "insn & (1 << 24)", abstract these bits out into wbit and pbit local flags. (We will want to do more tests against them to determine whether we need to provide syndrome information.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> --- target/arm/translate.c | 9 ++++++--- 1 file changed, 6 insertions(+), 3 deletions(-) diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) } else { int address_offset; bool load = insn & (1 << 20); + bool wbit = insn & (1 << 21); + bool pbit = insn & (1 << 24); bool doubleword = false; /* Misc load/store */ rn = (insn >> 16) & 0xf; @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) } addr = load_reg(s, rn); - if (insn & (1 << 24)) + if (pbit) { gen_add_datah_offset(s, insn, 0, addr); + } address_offset = 0; if (doubleword) { @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) ensure correct behavior with overlapping index registers. ldrd with base writeback is undefined if the destination and index registers overlap. */ - if (!(insn & (1 << 24))) { + if (!pbit) { gen_add_datah_offset(s, insn, address_offset, addr); store_reg(s, rn, addr); - } else if (insn & (1 << 21)) { + } else if (wbit) { if (address_offset) tcg_gen_addi_i32(addr, addr, address_offset); store_reg(s, rn, addr); -- 2.7.4 Add support for generating the ISS (Instruction Specific Syndrome) for Data Abort exceptions taken from AArch32. These syndromes are used by hypervisors for example to trap and emulate memory accesses. This is the equivalent for AArch32 guests of the work done for AArch64 guests in commit aaa1f954d4cab243. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Edgar E. Iglesias <edgar.iglesias@xilinx.com> --- target/arm/translate.h | 14 ++++ target/arm/translate-a64.c | 14 ---- target/arm/translate.c | 184 +++++++++++++++++++++++++++++++++------------ 3 files changed, 149 insertions(+), 63 deletions(-) diff --git a/target/arm/translate.h b/target/arm/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.h +++ b/target/arm/translate.h @@ -XXX,XX +XXX,XX @@ static inline int default_exception_el(DisasContext *s) ? 3 : MAX(1, s->current_el); } +static void disas_set_insn_syndrome(DisasContext *s, uint32_t syn) +{ + /* We don't need to save all of the syndrome so we mask and shift + * out unneeded bits to help the sleb128 encoder do a better job. + */ + syn &= ARM_INSN_START_WORD2_MASK; + syn >>= ARM_INSN_START_WORD2_SHIFT; + + /* We check and clear insn_start_idx to catch multiple updates. */ + assert(s->insn_start_idx != 0); + tcg_set_insn_param(s->insn_start_idx, 2, syn); + s->insn_start_idx = 0; +} + /* target-specific extra values for is_jmp */ /* These instructions trap after executing, so the A32/T32 decoder must * defer them until after the conditional execution state has been updated. diff --git a/target/arm/translate-a64.c b/target/arm/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate-a64.c +++ b/target/arm/translate-a64.c @@ -XXX,XX +XXX,XX @@ static inline void gen_goto_tb(DisasContext *s, int n, uint64_t dest) } } -static void disas_set_insn_syndrome(DisasContext *s, uint32_t syn) -{ - /* We don't need to save all of the syndrome so we mask and shift - * out uneeded bits to help the sleb128 encoder do a better job. - */ - syn &= ARM_INSN_START_WORD2_MASK; - syn >>= ARM_INSN_START_WORD2_SHIFT; - - /* We check and clear insn_start_idx to catch multiple updates. */ - assert(s->insn_start_idx != 0); - tcg_set_insn_param(s->insn_start_idx, 2, syn); - s->insn_start_idx = 0; -} - static void unallocated_encoding(DisasContext *s) { /* Unallocated and reserved encodings are uncategorized */ diff --git a/target/arm/translate.c b/target/arm/translate.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/translate.c +++ b/target/arm/translate.c @@ -XXX,XX +XXX,XX @@ void arm_translate_init(void) a64_translate_init(); } +/* Flags for the disas_set_da_iss info argument: + * lower bits hold the Rt register number, higher bits are flags. + */ +typedef enum ISSInfo { + ISSNone = 0, + ISSRegMask = 0x1f, + ISSInvalid = (1 << 5), + ISSIsAcqRel = (1 << 6), + ISSIsWrite = (1 << 7), + ISSIs16Bit = (1 << 8), +} ISSInfo; + +/* Save the syndrome information for a Data Abort */ +static void disas_set_da_iss(DisasContext *s, TCGMemOp memop, ISSInfo issinfo) +{ + uint32_t syn; + int sas = memop & MO_SIZE; + bool sse = memop & MO_SIGN; + bool is_acqrel = issinfo & ISSIsAcqRel; + bool is_write = issinfo & ISSIsWrite; + bool is_16bit = issinfo & ISSIs16Bit; + int srt = issinfo & ISSRegMask; + + if (issinfo & ISSInvalid) { + /* Some callsites want to conditionally provide ISS info, + * eg "only if this was not a writeback" + */ + return; + } + + if (srt == 15) { + /* For AArch32, insns where the src/dest is R15 never generate + * ISS information. Catching that here saves checking at all + * the call sites. + */ + return; + } + + syn = syn_data_abort_with_iss(0, sas, sse, srt, 0, is_acqrel, + 0, 0, 0, is_write, 0, is_16bit); + disas_set_insn_syndrome(s, syn); +} + static inline ARMMMUIdx get_a32_user_mem_index(DisasContext *s) { /* Return the mmu_idx to use for A32/T32 "unprivileged load/store" @@ -XXX,XX +XXX,XX @@ static inline void gen_aa32_ld##SUFF(DisasContext *s, TCGv_i32 val, \ TCGv_i32 a32, int index) \ { \ gen_aa32_ld_i32(s, val, a32, index, OPC | s->be_data); \ +} \ +static inline void gen_aa32_ld##SUFF##_iss(DisasContext *s, \ + TCGv_i32 val, \ + TCGv_i32 a32, int index, \ + ISSInfo issinfo) \ +{ \ + gen_aa32_ld_i32(s, val, a32, index, OPC | s->be_data); \ + disas_set_da_iss(s, OPC, issinfo); \ } #define DO_GEN_ST(SUFF, OPC) \ @@ -XXX,XX +XXX,XX @@ static inline void gen_aa32_st##SUFF(DisasContext *s, TCGv_i32 val, \ TCGv_i32 a32, int index) \ { \ gen_aa32_st_i32(s, val, a32, index, OPC | s->be_data); \ +} \ +static inline void gen_aa32_st##SUFF##_iss(DisasContext *s, \ + TCGv_i32 val, \ + TCGv_i32 a32, int index, \ + ISSInfo issinfo) \ +{ \ + gen_aa32_st_i32(s, val, a32, index, OPC | s->be_data); \ + disas_set_da_iss(s, OPC, issinfo | ISSIsWrite); \ } static inline void gen_aa32_frob64(DisasContext *s, TCGv_i64 val) @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) tmp = tcg_temp_new_i32(); switch (op1) { case 0: /* lda */ - gen_aa32_ld32u(s, tmp, addr, - get_mem_index(s)); + gen_aa32_ld32u_iss(s, tmp, addr, + get_mem_index(s), + rd | ISSIsAcqRel); break; case 2: /* ldab */ - gen_aa32_ld8u(s, tmp, addr, - get_mem_index(s)); + gen_aa32_ld8u_iss(s, tmp, addr, + get_mem_index(s), + rd | ISSIsAcqRel); break; case 3: /* ldah */ - gen_aa32_ld16u(s, tmp, addr, - get_mem_index(s)); + gen_aa32_ld16u_iss(s, tmp, addr, + get_mem_index(s), + rd | ISSIsAcqRel); break; default: abort(); @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) tmp = load_reg(s, rm); switch (op1) { case 0: /* stl */ - gen_aa32_st32(s, tmp, addr, - get_mem_index(s)); + gen_aa32_st32_iss(s, tmp, addr, + get_mem_index(s), + rm | ISSIsAcqRel); break; case 2: /* stlb */ - gen_aa32_st8(s, tmp, addr, - get_mem_index(s)); + gen_aa32_st8_iss(s, tmp, addr, + get_mem_index(s), + rm | ISSIsAcqRel); break; case 3: /* stlh */ - gen_aa32_st16(s, tmp, addr, - get_mem_index(s)); + gen_aa32_st16_iss(s, tmp, addr, + get_mem_index(s), + rm | ISSIsAcqRel); break; default: abort(); @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) bool wbit = insn & (1 << 21); bool pbit = insn & (1 << 24); bool doubleword = false; + ISSInfo issinfo; + /* Misc load/store */ rn = (insn >> 16) & 0xf; rd = (insn >> 12) & 0xf; + /* ISS not valid if writeback */ + issinfo = (pbit & !wbit) ? rd : ISSInvalid; + if (!load && (sh & 2)) { /* doubleword */ ARCH(5TE); @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) tmp = tcg_temp_new_i32(); switch (sh) { case 1: - gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld16u_iss(s, tmp, addr, get_mem_index(s), + issinfo); break; case 2: - gen_aa32_ld8s(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld8s_iss(s, tmp, addr, get_mem_index(s), + issinfo); break; default: case 3: - gen_aa32_ld16s(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld16s_iss(s, tmp, addr, get_mem_index(s), + issinfo); break; } } else { /* store */ tmp = load_reg(s, rd); - gen_aa32_st16(s, tmp, addr, get_mem_index(s)); + gen_aa32_st16_iss(s, tmp, addr, get_mem_index(s), issinfo); tcg_temp_free_i32(tmp); } /* Perform base writeback before the loaded value to @@ -XXX,XX +XXX,XX @@ static void disas_arm_insn(DisasContext *s, unsigned int insn) /* load */ tmp = tcg_temp_new_i32(); if (insn & (1 << 22)) { - gen_aa32_ld8u(s, tmp, tmp2, i); + gen_aa32_ld8u_iss(s, tmp, tmp2, i, rd); } else { - gen_aa32_ld32u(s, tmp, tmp2, i); + gen_aa32_ld32u_iss(s, tmp, tmp2, i, rd); } } else { /* store */ tmp = load_reg(s, rd); if (insn & (1 << 22)) { - gen_aa32_st8(s, tmp, tmp2, i); + gen_aa32_st8_iss(s, tmp, tmp2, i, rd); } else { - gen_aa32_st32(s, tmp, tmp2, i); + gen_aa32_st32_iss(s, tmp, tmp2, i, rd); } tcg_temp_free_i32(tmp); } @@ -XXX,XX +XXX,XX @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw tmp = tcg_temp_new_i32(); switch (op) { case 0: /* ldab */ - gen_aa32_ld8u(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld8u_iss(s, tmp, addr, get_mem_index(s), + rs | ISSIsAcqRel); break; case 1: /* ldah */ - gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld16u_iss(s, tmp, addr, get_mem_index(s), + rs | ISSIsAcqRel); break; case 2: /* lda */ - gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld32u_iss(s, tmp, addr, get_mem_index(s), + rs | ISSIsAcqRel); break; default: abort(); @@ -XXX,XX +XXX,XX @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw tmp = load_reg(s, rs); switch (op) { case 0: /* stlb */ - gen_aa32_st8(s, tmp, addr, get_mem_index(s)); + gen_aa32_st8_iss(s, tmp, addr, get_mem_index(s), + rs | ISSIsAcqRel); break; case 1: /* stlh */ - gen_aa32_st16(s, tmp, addr, get_mem_index(s)); + gen_aa32_st16_iss(s, tmp, addr, get_mem_index(s), + rs | ISSIsAcqRel); break; case 2: /* stl */ - gen_aa32_st32(s, tmp, addr, get_mem_index(s)); + gen_aa32_st32_iss(s, tmp, addr, get_mem_index(s), + rs | ISSIsAcqRel); break; default: abort(); @@ -XXX,XX +XXX,XX @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw int postinc = 0; int writeback = 0; int memidx; + ISSInfo issinfo; + if ((insn & 0x01100000) == 0x01000000) { if (disas_neon_ls_insn(s, insn)) { goto illegal_op; @@ -XXX,XX +XXX,XX @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw } } } + + issinfo = writeback ? ISSInvalid : rs; + if (insn & (1 << 20)) { /* Load. */ tmp = tcg_temp_new_i32(); switch (op) { case 0: - gen_aa32_ld8u(s, tmp, addr, memidx); + gen_aa32_ld8u_iss(s, tmp, addr, memidx, issinfo); break; case 4: - gen_aa32_ld8s(s, tmp, addr, memidx); + gen_aa32_ld8s_iss(s, tmp, addr, memidx, issinfo); break; case 1: - gen_aa32_ld16u(s, tmp, addr, memidx); + gen_aa32_ld16u_iss(s, tmp, addr, memidx, issinfo); break; case 5: - gen_aa32_ld16s(s, tmp, addr, memidx); + gen_aa32_ld16s_iss(s, tmp, addr, memidx, issinfo); break; case 2: - gen_aa32_ld32u(s, tmp, addr, memidx); + gen_aa32_ld32u_iss(s, tmp, addr, memidx, issinfo); break; default: tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static int disas_thumb2_insn(CPUARMState *env, DisasContext *s, uint16_t insn_hw tmp = load_reg(s, rs); switch (op) { case 0: - gen_aa32_st8(s, tmp, addr, memidx); + gen_aa32_st8_iss(s, tmp, addr, memidx, issinfo); break; case 1: - gen_aa32_st16(s, tmp, addr, memidx); + gen_aa32_st16_iss(s, tmp, addr, memidx, issinfo); break; case 2: - gen_aa32_st32(s, tmp, addr, memidx); + gen_aa32_st32_iss(s, tmp, addr, memidx, issinfo); break; default: tcg_temp_free_i32(tmp); @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s) addr = tcg_temp_new_i32(); tcg_gen_movi_i32(addr, val); tmp = tcg_temp_new_i32(); - gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld32u_iss(s, tmp, addr, get_mem_index(s), + rd | ISSIs16Bit); tcg_temp_free_i32(addr); store_reg(s, rd, tmp); break; @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s) switch (op) { case 0: /* str */ - gen_aa32_st32(s, tmp, addr, get_mem_index(s)); + gen_aa32_st32_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); break; case 1: /* strh */ - gen_aa32_st16(s, tmp, addr, get_mem_index(s)); + gen_aa32_st16_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); break; case 2: /* strb */ - gen_aa32_st8(s, tmp, addr, get_mem_index(s)); + gen_aa32_st8_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); break; case 3: /* ldrsb */ - gen_aa32_ld8s(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld8s_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); break; case 4: /* ldr */ - gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld32u_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); break; case 5: /* ldrh */ - gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld16u_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); break; case 6: /* ldrb */ - gen_aa32_ld8u(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld8u_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); break; case 7: /* ldrsh */ - gen_aa32_ld16s(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld16s_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); break; } if (op >= 3) { /* load */ @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s) if (insn & (1 << 11)) { /* load */ tmp = tcg_temp_new_i32(); - gen_aa32_ld8u(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld8u_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); store_reg(s, rd, tmp); } else { /* store */ tmp = load_reg(s, rd); - gen_aa32_st8(s, tmp, addr, get_mem_index(s)); + gen_aa32_st8_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); tcg_temp_free_i32(tmp); } tcg_temp_free_i32(addr); @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s) if (insn & (1 << 11)) { /* load */ tmp = tcg_temp_new_i32(); - gen_aa32_ld16u(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld16u_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); store_reg(s, rd, tmp); } else { /* store */ tmp = load_reg(s, rd); - gen_aa32_st16(s, tmp, addr, get_mem_index(s)); + gen_aa32_st16_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); tcg_temp_free_i32(tmp); } tcg_temp_free_i32(addr); @@ -XXX,XX +XXX,XX @@ static void disas_thumb_insn(CPUARMState *env, DisasContext *s) if (insn & (1 << 11)) { /* load */ tmp = tcg_temp_new_i32(); - gen_aa32_ld32u(s, tmp, addr, get_mem_index(s)); + gen_aa32_ld32u_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); store_reg(s, rd, tmp); } else { /* store */ tmp = load_reg(s, rd); - gen_aa32_st32(s, tmp, addr, get_mem_index(s)); + gen_aa32_st32_iss(s, tmp, addr, get_mem_index(s), rd | ISSIs16Bit); tcg_temp_free_i32(tmp); } tcg_temp_free_i32(addr); @@ -XXX,XX +XXX,XX @@ void gen_intermediate_code(CPUARMState *env, TranslationBlock *tb) store_cpu_field(tmp, condexec_bits); } do { + dc->insn_start_idx = tcg_op_buf_count(); tcg_gen_insn_start(dc->pc, (dc->condexec_cond << 4) | (dc->condexec_mask >> 1), 0); -- 2.7.4 Add a comment documenting the memory map of the SoC devices and which are not implemented. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 1484247815-15279-2-git-send-email-peter.maydell@linaro.org --- hw/arm/stellaris.c | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_init(const char *kernel_filename, const char *cpu_model, 0x40024000, 0x40025000, 0x40026000}; static const int gpio_irq[7] = {0, 1, 2, 3, 4, 30, 31}; + /* Memory map of SoC devices, from + * Stellaris LM3S6965 Microcontroller Data Sheet (rev I) + * http://www.ti.com/lit/ds/symlink/lm3s6965.pdf + * + * 40000000 wdtimer (unimplemented) + * 40002000 i2c (unimplemented) + * 40004000 GPIO + * 40005000 GPIO + * 40006000 GPIO + * 40007000 GPIO + * 40008000 SSI + * 4000c000 UART + * 4000d000 UART + * 4000e000 UART + * 40020000 i2c + * 40021000 i2c (unimplemented) + * 40024000 GPIO + * 40025000 GPIO + * 40026000 GPIO + * 40028000 PWM (unimplemented) + * 4002c000 QEI (unimplemented) + * 4002d000 QEI (unimplemented) + * 40030000 gptimer + * 40031000 gptimer + * 40032000 gptimer + * 40033000 gptimer + * 40038000 ADC + * 4003c000 analogue comparator (unimplemented) + * 40048000 ethernet + * 400fc000 hibernation module (unimplemented) + * 400fd000 flash memory control (unimplemented) + * 400fe000 system control + */ + DeviceState *gpio_dev[7], *nvic; qemu_irq gpio_in[7][8]; qemu_irq gpio_out[7][8]; -- 2.7.4 Create a new "unimplemented" sysbus device, which simply accepts all read and write accesses, and implements them as read-as-zero, write-ignored, with logging of the access as LOG_UNIMP. This is useful for stubbing out bits of an SoC or board model which haven't been written yet. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 1484247815-15279-3-git-send-email-peter.maydell@linaro.org --- hw/misc/Makefile.objs | 2 + include/hw/misc/unimp.h | 39 ++++++++++++++++++ hw/misc/unimp.c | 107 ++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 148 insertions(+) create mode 100644 include/hw/misc/unimp.h create mode 100644 hw/misc/unimp.c diff --git a/hw/misc/Makefile.objs b/hw/misc/Makefile.objs index XXXXXXX..XXXXXXX 100644 --- a/hw/misc/Makefile.objs +++ b/hw/misc/Makefile.objs @@ -XXX,XX +XXX,XX @@ common-obj-$(CONFIG_SGA) += sga.o common-obj-$(CONFIG_ISA_TESTDEV) += pc-testdev.o common-obj-$(CONFIG_PCI_TESTDEV) += pci-testdev.o +common-obj-y += unimp.o + obj-$(CONFIG_VMPORT) += vmport.o # ARM devices diff --git a/include/hw/misc/unimp.h b/include/hw/misc/unimp.h new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/include/hw/misc/unimp.h @@ -XXX,XX +XXX,XX @@ +/* + * "Unimplemented" device + * + * Copyright Linaro Limited, 2017 + * Written by Peter Maydell + */ + +#ifndef HW_MISC_UNIMP_H +#define HW_MISC_UNIMP_H + +#define TYPE_UNIMPLEMENTED_DEVICE "unimplemented-device" + +/** + * create_unimplemented_device: create and map a dummy device + * @name: name of the device for debug logging + * @base: base address of the device's MMIO region + * @size: size of the device's MMIO region + * + * This utility function creates and maps an instance of unimplemented-device, + * which is a dummy device which simply logs all guest accesses to + * it via the qemu_log LOG_UNIMP debug log. + * The device is mapped at priority -1000, which means that you can + * use it to cover a large region and then map other devices on top of it + * if necessary. + */ +static inline void create_unimplemented_device(const char *name, + hwaddr base, + hwaddr size) +{ + DeviceState *dev = qdev_create(NULL, TYPE_UNIMPLEMENTED_DEVICE); + + qdev_prop_set_string(dev, "name", name); + qdev_prop_set_uint64(dev, "size", size); + qdev_init_nofail(dev); + + sysbus_mmio_map_overlap(SYS_BUS_DEVICE(dev), 0, base, -1000); +} + +#endif diff --git a/hw/misc/unimp.c b/hw/misc/unimp.c new file mode 100644 index XXXXXXX..XXXXXXX --- /dev/null +++ b/hw/misc/unimp.c @@ -XXX,XX +XXX,XX @@ +/* "Unimplemented" device + * + * This is a dummy device which accepts and logs all accesses. + * It's useful for stubbing out regions of an SoC or board + * map which correspond to devices that have not yet been + * implemented. This is often sufficient to placate initial + * guest device driver probing such that the system will + * come up. + * + * Copyright Linaro Limited, 2017 + * Written by Peter Maydell + */ + +#include "qemu/osdep.h" +#include "hw/hw.h" +#include "hw/sysbus.h" +#include "hw/misc/unimp.h" +#include "qemu/log.h" +#include "qapi/error.h" + +#define UNIMPLEMENTED_DEVICE(obj) \ + OBJECT_CHECK(UnimplementedDeviceState, (obj), TYPE_UNIMPLEMENTED_DEVICE) + +typedef struct { + SysBusDevice parent_obj; + MemoryRegion iomem; + char *name; + uint64_t size; +} UnimplementedDeviceState; + +static uint64_t unimp_read(void *opaque, hwaddr offset, unsigned size) +{ + UnimplementedDeviceState *s = UNIMPLEMENTED_DEVICE(opaque); + + qemu_log_mask(LOG_UNIMP, "%s: unimplemented device read " + "(size %d, offset 0x%" HWADDR_PRIx ")\n", + s->name, size, offset); + return 0; +} + +static void unimp_write(void *opaque, hwaddr offset, + uint64_t value, unsigned size) +{ + UnimplementedDeviceState *s = UNIMPLEMENTED_DEVICE(opaque); + + qemu_log_mask(LOG_UNIMP, "%s: unimplemented device write " + "(size %d, value 0x%" PRIx64 + ", offset 0x%" HWADDR_PRIx ")\n", + s->name, size, value, offset); +} + +static const MemoryRegionOps unimp_ops = { + .read = unimp_read, + .write = unimp_write, + .impl.min_access_size = 1, + .impl.max_access_size = 8, + .valid.min_access_size = 1, + .valid.max_access_size = 8, + .endianness = DEVICE_NATIVE_ENDIAN, +}; + +static void unimp_realize(DeviceState *dev, Error **errp) +{ + UnimplementedDeviceState *s = UNIMPLEMENTED_DEVICE(dev); + + if (s->size == 0) { + error_setg(errp, "property 'size' not specified or zero"); + return; + } + + if (s->name == NULL) { + error_setg(errp, "property 'name' not specified"); + return; + } + + memory_region_init_io(&s->iomem, OBJECT(s), &unimp_ops, s, + s->name, s->size); + sysbus_init_mmio(SYS_BUS_DEVICE(s), &s->iomem); +} + +static Property unimp_properties[] = { + DEFINE_PROP_UINT64("size", UnimplementedDeviceState, size, 0), + DEFINE_PROP_STRING("name", UnimplementedDeviceState, name), + DEFINE_PROP_END_OF_LIST(), +}; + +static void unimp_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + + dc->realize = unimp_realize; + dc->props = unimp_properties; +} + +static const TypeInfo unimp_info = { + .name = TYPE_UNIMPLEMENTED_DEVICE, + .parent = TYPE_SYS_BUS_DEVICE, + .instance_size = sizeof(UnimplementedDeviceState), + .class_init = unimp_class_init, +}; + +static void unimp_register_types(void) +{ + type_register_static(&unimp_info); +} + +type_init(unimp_register_types) -- 2.7.4 Use the 'unimplemented' dummy device to cover regions of the SoC device memory map which we don't have proper device implementations for yet. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 1484247815-15279-4-git-send-email-peter.maydell@linaro.org --- hw/arm/stellaris.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ #include "exec/address-spaces.h" #include "sysemu/sysemu.h" #include "hw/char/pl011.h" +#include "hw/misc/unimp.h" #define GPIO_A 0 #define GPIO_B 1 @@ -XXX,XX +XXX,XX @@ static void stellaris_init(const char *kernel_filename, const char *cpu_model, } } } + + /* Add dummy regions for the devices we don't implement yet, + * so guest accesses don't cause unlogged crashes. + */ + create_unimplemented_device("wdtimer", 0x40000000, 0x1000); + create_unimplemented_device("i2c-0", 0x40002000, 0x1000); + create_unimplemented_device("i2c-2", 0x40021000, 0x1000); + create_unimplemented_device("PWM", 0x40028000, 0x1000); + create_unimplemented_device("QEI-0", 0x4002c000, 0x1000); + create_unimplemented_device("QEI-1", 0x4002d000, 0x1000); + create_unimplemented_device("analogue-comparator", 0x4003c000, 0x1000); + create_unimplemented_device("hibernation", 0x400fc000, 0x1000); + create_unimplemented_device("flash-control", 0x400fd000, 0x1000); } /* FIXME: Figure out how to generate these from stellaris_boards. */ -- 2.7.4 Hi; here's another arm pullreq; by volume most of this is refactoring from me, but there are also some bugfixes and other bits and pieces here. thanks -- PMM The following changes since commit ed734377ab3f3f3cc15d7aa301a87ab6370f2eed: Merge tag 'linux-user-fix-gupnp-pull-request' of https://github.com/hdeller/qemu-hppa into staging (2025-01-24 14:43:07 -0500) are available in the Git repository at: https://git.linaro.org/people/pmaydell/qemu-arm.git tags/pull-target-arm-20250128-1 for you to fetch changes up to 664280abddcb3cacc9c6204706bb739fcc1316f7: hw/usb/canokey: Fix buffer overflow for OUT packet (2025-01-28 18:40:19 +0000) ---------------------------------------------------------------- target-arm queue: * hw/arm: Remove various uses of first_cpu global * hw/char/imx_serial: Fix reset value of UFCR register * hw/char/imx_serial: Update all state before restarting ageing timer * hw/pci-host/designware: Expose MSI IRQ * hw/arm/stellaris: refactoring, cleanup * hw/arm/stellaris: map both I2C controllers * tests/functional: Add a test for the arm microbit machine * target/arm: arm_reset_sve_state() should set FPSR, not FPCR * target/arm: refactorings preparatory to FEAT_AFP implementation * fpu: Rename float_flag_input_denormal to float_flag_input_denormal_flushed * fpu: Rename float_flag_output_denormal to float_flag_output_denormal_flushed * hw/usb/canokey: Fix buffer overflow for OUT packet ---------------------------------------------------------------- Bernhard Beschow (3): hw/char/imx_serial: Fix reset value of UFCR register hw/char/imx_serial: Update all state before restarting ageing timer hw/pci-host/designware: Expose MSI IRQ Hongren Zheng (1): hw/usb/canokey: Fix buffer overflow for OUT packet Peter Maydell (22): target/arm: arm_reset_sve_state() should set FPSR, not FPCR target/arm: Use FPSR_ constants in vfp_exceptbits_from_host() target/arm: Use uint32_t in vfp_exceptbits_from_host() target/arm: Define new fp_status_a32 and fp_status_a64 target/arm: Use vfp.fp_status_a64 in A64-only helper functions target/arm: Use fp_status_a64 or fp_status_a32 in is_ebf() target/arm: Use fp_status_a32 in vjvct helper target/arm: Use fp_status_a32 in vfp_cmp helpers target/arm: Use FPST_A32 in A32 decoder target/arm: Use FPST_A64 in A64 decoder target/arm: Remove now-unused vfp.fp_status and FPST_FPCR target/arm: Define new fp_status_f16_a32 and fp_status_f16_a64 target/arm: Use fp_status_f16_a32 in AArch32-only helpers target/arm: Use fp_status_f16_a64 in AArch64-only helpers target/arm: Use FPST_A32_F16 in A32 decoder target/arm: Use FPST_A64_F16 in A64 decoder target/arm: Remove now-unused vfp.fp_status_f16 and FPST_FPCR_F16 fpu: Rename float_flag_input_denormal to float_flag_input_denormal_flushed fpu: Rename float_flag_output_denormal to float_flag_output_denormal_flushed fpu: Fix a comment in softfloat-types.h target/arm: Remove redundant advsimd float16 helpers target/arm: Use FPST_A64_F16 for halfprec-to-other conversions Philippe Mathieu-Daudé (9): hw/arm/nrf51: Rename ARMv7MState 'cpu' -> 'armv7m' hw/arm/stellaris: Add 'armv7m' local variable hw/arm/v7m: Remove use of &first_cpu in machine_init() hw/arm/stellaris: Link each board schematic hw/arm/stellaris: Constify read-only arrays hw/arm/stellaris: Remove incorrect unimplemented i2c-0 at 0x40002000 hw/arm/stellaris: Replace magic numbers by definitions hw/arm/stellaris: Use DEVCAP macro to access DeviceCapability registers hw/arm/stellaris: Map both I2C controllers Thomas Huth (1): tests/functional: Add a test for the arm microbit machine MAINTAINERS | 1 + hw/usb/canokey.h | 4 -- include/fpu/softfloat-types.h | 10 +-- include/hw/arm/fsl-imx6.h | 4 +- include/hw/arm/fsl-imx7.h | 4 +- include/hw/arm/nrf51_soc.h | 2 +- include/hw/char/imx_serial.h | 2 +- include/hw/pci-host/designware.h | 1 + target/arm/cpu.h | 12 ++-- target/arm/tcg/helper-a64.h | 8 --- target/arm/tcg/translate.h | 32 ++++++--- fpu/softfloat.c | 6 +- hw/arm/b-l475e-iot01a.c | 2 +- hw/arm/fsl-imx6.c | 13 +++- hw/arm/fsl-imx7.c | 13 +++- hw/arm/microbit.c | 2 +- hw/arm/mps2-tz.c | 2 +- hw/arm/mps2.c | 2 +- hw/arm/msf2-som.c | 2 +- hw/arm/musca.c | 2 +- hw/arm/netduino2.c | 2 +- hw/arm/netduinoplus2.c | 2 +- hw/arm/nrf51_soc.c | 18 ++--- hw/arm/olimex-stm32-h405.c | 2 +- hw/arm/stellaris.c | 118 +++++++++++++++++++----------- hw/arm/stm32vldiscovery.c | 2 +- hw/char/imx_serial.c | 7 +- hw/pci-host/designware.c | 7 +- hw/usb/canokey.c | 6 +- target/arm/cpu.c | 6 +- target/arm/helper.c | 2 +- target/arm/tcg/helper-a64.c | 9 --- target/arm/tcg/sme_helper.c | 6 +- target/arm/tcg/sve_helper.c | 6 +- target/arm/tcg/translate-a64.c | 103 ++++++++++++++------------- target/arm/tcg/translate-sme.c | 4 +- target/arm/tcg/translate-sve.c | 130 +++++++++++++++++----------------- target/arm/tcg/translate-vfp.c | 78 ++++++++++---------- target/arm/tcg/vec_helper.c | 22 +++--- target/arm/vfp_helper.c | 73 +++++++++++-------- target/i386/tcg/fpu_helper.c | 8 +-- target/m68k/fpu_helper.c | 2 +- target/mips/tcg/msa_helper.c | 4 +- target/rx/op_helper.c | 4 +- target/tricore/fpu_helper.c | 6 +- fpu/softfloat-parts.c.inc | 4 +- hw/arm/Kconfig | 2 + tests/functional/meson.build | 1 + tests/functional/test_arm_microbit.py | 31 ++++++++ 49 files changed, 452 insertions(+), 337 deletions(-) create mode 100755 tests/functional/test_arm_microbit.py From: Philippe Mathieu-Daudé <philmd@linaro.org> The ARMv7MState object is not simply a CPU, it also contains the NVIC, SysTick timer, and various MemoryRegions. Rename the field as 'armv7m', like other Cortex-M boards. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20250112225614.33723-2-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/nrf51_soc.h | 2 +- hw/arm/nrf51_soc.c | 18 +++++++++--------- 2 files changed, 10 insertions(+), 10 deletions(-) diff --git a/include/hw/arm/nrf51_soc.h b/include/hw/arm/nrf51_soc.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/nrf51_soc.h +++ b/include/hw/arm/nrf51_soc.h @@ -XXX,XX +XXX,XX @@ struct NRF51State { SysBusDevice parent_obj; /*< public >*/ - ARMv7MState cpu; + ARMv7MState armv7m; NRF51UARTState uart; NRF51RNGState rng; diff --git a/hw/arm/nrf51_soc.c b/hw/arm/nrf51_soc.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/nrf51_soc.c +++ b/hw/arm/nrf51_soc.c @@ -XXX,XX +XXX,XX @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp) } /* This clock doesn't need migration because it is fixed-frequency */ clock_set_hz(s->sysclk, HCLK_FRQ); - qdev_connect_clock_in(DEVICE(&s->cpu), "cpuclk", s->sysclk); + qdev_connect_clock_in(DEVICE(&s->armv7m), "cpuclk", s->sysclk); /* * This SoC has no systick device, so don't connect refclk. * TODO: model the lack of systick (currently the armv7m object * will always provide one). */ - object_property_set_link(OBJECT(&s->cpu), "memory", OBJECT(&s->container), + object_property_set_link(OBJECT(&s->armv7m), "memory", OBJECT(&s->container), &error_abort); - if (!sysbus_realize(SYS_BUS_DEVICE(&s->cpu), errp)) { + if (!sysbus_realize(SYS_BUS_DEVICE(&s->armv7m), errp)) { return; } @@ -XXX,XX +XXX,XX @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp) mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->uart), 0); memory_region_add_subregion_overlap(&s->container, NRF51_UART_BASE, mr, 0); sysbus_connect_irq(SYS_BUS_DEVICE(&s->uart), 0, - qdev_get_gpio_in(DEVICE(&s->cpu), + qdev_get_gpio_in(DEVICE(&s->armv7m), BASE_TO_IRQ(NRF51_UART_BASE))); /* RNG */ @@ -XXX,XX +XXX,XX @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp) mr = sysbus_mmio_get_region(SYS_BUS_DEVICE(&s->rng), 0); memory_region_add_subregion_overlap(&s->container, NRF51_RNG_BASE, mr, 0); sysbus_connect_irq(SYS_BUS_DEVICE(&s->rng), 0, - qdev_get_gpio_in(DEVICE(&s->cpu), + qdev_get_gpio_in(DEVICE(&s->armv7m), BASE_TO_IRQ(NRF51_RNG_BASE))); /* UICR, FICR, NVMC, FLASH */ @@ -XXX,XX +XXX,XX @@ static void nrf51_soc_realize(DeviceState *dev_soc, Error **errp) sysbus_mmio_map(SYS_BUS_DEVICE(&s->timer[i]), 0, base_addr); sysbus_connect_irq(SYS_BUS_DEVICE(&s->timer[i]), 0, - qdev_get_gpio_in(DEVICE(&s->cpu), + qdev_get_gpio_in(DEVICE(&s->armv7m), BASE_TO_IRQ(base_addr))); } @@ -XXX,XX +XXX,XX @@ static void nrf51_soc_init(Object *obj) memory_region_init(&s->container, obj, "nrf51-container", UINT64_MAX); - object_initialize_child(OBJECT(s), "armv6m", &s->cpu, TYPE_ARMV7M); - qdev_prop_set_string(DEVICE(&s->cpu), "cpu-type", + object_initialize_child(OBJECT(s), "armv6m", &s->armv7m, TYPE_ARMV7M); + qdev_prop_set_string(DEVICE(&s->armv7m), "cpu-type", ARM_CPU_TYPE_NAME("cortex-m0")); - qdev_prop_set_uint32(DEVICE(&s->cpu), "num-irq", 32); + qdev_prop_set_uint32(DEVICE(&s->armv7m), "num-irq", 32); object_initialize_child(obj, "uart", &s->uart, TYPE_NRF51_UART); object_property_add_alias(obj, "serial0", OBJECT(&s->uart), "chardev"); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> While the TYPE_ARMV7M object forward its NVIC interrupt lines, it is somehow misleading to name it 'nvic'. Add the 'armv7m' local variable for clarity, but also keep the 'nvic' variable behaving like before when used for wiring IRQ lines. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Message-id: 20250112225614.33723-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 21 +++++++++++---------- 1 file changed, 11 insertions(+), 10 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) */ Object *soc_container; - DeviceState *gpio_dev[7], *nvic; + DeviceState *gpio_dev[7], *armv7m, *nvic; qemu_irq gpio_in[7][8]; qemu_irq gpio_out[7][8]; qemu_irq adc; @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) qdev_prop_set_uint32(ssys_dev, "dc4", board->dc4); sysbus_realize_and_unref(SYS_BUS_DEVICE(ssys_dev), &error_fatal); - nvic = qdev_new(TYPE_ARMV7M); - object_property_add_child(soc_container, "v7m", OBJECT(nvic)); - qdev_prop_set_uint32(nvic, "num-irq", NUM_IRQ_LINES); - qdev_prop_set_uint8(nvic, "num-prio-bits", NUM_PRIO_BITS); - qdev_prop_set_string(nvic, "cpu-type", ms->cpu_type); - qdev_prop_set_bit(nvic, "enable-bitband", true); - qdev_connect_clock_in(nvic, "cpuclk", + armv7m = qdev_new(TYPE_ARMV7M); + object_property_add_child(soc_container, "v7m", OBJECT(armv7m)); + qdev_prop_set_uint32(armv7m, "num-irq", NUM_IRQ_LINES); + qdev_prop_set_uint8(armv7m, "num-prio-bits", NUM_PRIO_BITS); + qdev_prop_set_string(armv7m, "cpu-type", ms->cpu_type); + qdev_prop_set_bit(armv7m, "enable-bitband", true); + qdev_connect_clock_in(armv7m, "cpuclk", qdev_get_clock_out(ssys_dev, "SYSCLK")); /* This SoC does not connect the systick reference clock */ - object_property_set_link(OBJECT(nvic), "memory", + object_property_set_link(OBJECT(armv7m), "memory", OBJECT(get_system_memory()), &error_abort); /* This will exit with an error if the user passed us a bad cpu_type */ - sysbus_realize_and_unref(SYS_BUS_DEVICE(nvic), &error_fatal); + sysbus_realize_and_unref(SYS_BUS_DEVICE(armv7m), &error_fatal); + nvic = armv7m; /* Now we can wire up the IRQ and MMIO of the system registers */ sysbus_mmio_map(SYS_BUS_DEVICE(ssys_dev), 0, 0x400fe000); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> When instanciating the machine model, the machine_init() implementations usually create the CPUs, so have access to its first CPU. Use that rather then the &first_cpu global. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Alistair Francis <alistair.francis@wdc.com> Reviewed-by: Samuel Tardieu <sam@rfc1149.net> Message-id: 20250112225614.33723-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/b-l475e-iot01a.c | 2 +- hw/arm/microbit.c | 2 +- hw/arm/mps2-tz.c | 2 +- hw/arm/mps2.c | 2 +- hw/arm/msf2-som.c | 2 +- hw/arm/musca.c | 2 +- hw/arm/netduino2.c | 2 +- hw/arm/netduinoplus2.c | 2 +- hw/arm/olimex-stm32-h405.c | 2 +- hw/arm/stellaris.c | 2 +- hw/arm/stm32vldiscovery.c | 2 +- 11 files changed, 11 insertions(+), 11 deletions(-) diff --git a/hw/arm/b-l475e-iot01a.c b/hw/arm/b-l475e-iot01a.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/b-l475e-iot01a.c +++ b/hw/arm/b-l475e-iot01a.c @@ -XXX,XX +XXX,XX @@ static void bl475e_init(MachineState *machine) sysbus_realize(SYS_BUS_DEVICE(&s->soc), &error_fatal); sc = STM32L4X5_SOC_GET_CLASS(&s->soc); - armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, 0, + armv7m_load_kernel(s->soc.armv7m.cpu, machine->kernel_filename, 0, sc->flash_size); if (object_class_by_name(TYPE_DM163)) { diff --git a/hw/arm/microbit.c b/hw/arm/microbit.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/microbit.c +++ b/hw/arm/microbit.c @@ -XXX,XX +XXX,XX @@ static void microbit_init(MachineState *machine) memory_region_add_subregion_overlap(&s->nrf51.container, NRF51_TWI_BASE, mr, -1); - armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, + armv7m_load_kernel(s->nrf51.armv7m.cpu, machine->kernel_filename, 0, s->nrf51.flash_size); } diff --git a/hw/arm/mps2-tz.c b/hw/arm/mps2-tz.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2-tz.c +++ b/hw/arm/mps2-tz.c @@ -XXX,XX +XXX,XX @@ static void mps2tz_common_init(MachineState *machine) mms->remap_irq); } - armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, + armv7m_load_kernel(mms->iotkit.armv7m[0].cpu, machine->kernel_filename, 0, boot_ram_size(mms)); } diff --git a/hw/arm/mps2.c b/hw/arm/mps2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/mps2.c +++ b/hw/arm/mps2.c @@ -XXX,XX +XXX,XX @@ static void mps2_common_init(MachineState *machine) qdev_get_gpio_in(armv7m, mmc->fpga_type == FPGA_AN511 ? 47 : 13)); - armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, + armv7m_load_kernel(mms->armv7m.cpu, machine->kernel_filename, 0, 0x400000); } diff --git a/hw/arm/msf2-som.c b/hw/arm/msf2-som.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/msf2-som.c +++ b/hw/arm/msf2-som.c @@ -XXX,XX +XXX,XX @@ static void emcraft_sf2_s2s010_init(MachineState *machine) cs_line = qdev_get_gpio_in_named(spi_flash, SSI_GPIO_CS, 0); sysbus_connect_irq(SYS_BUS_DEVICE(&soc->spi[0]), 1, cs_line); - armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, + armv7m_load_kernel(soc->armv7m.cpu, machine->kernel_filename, 0, soc->envm_size); } diff --git a/hw/arm/musca.c b/hw/arm/musca.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/musca.c +++ b/hw/arm/musca.c @@ -XXX,XX +XXX,XX @@ static void musca_init(MachineState *machine) "cfg_sec_resp", 0)); } - armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, + armv7m_load_kernel(mms->sse.armv7m[0].cpu, machine->kernel_filename, 0, 0x2000000); } diff --git a/hw/arm/netduino2.c b/hw/arm/netduino2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/netduino2.c +++ b/hw/arm/netduino2.c @@ -XXX,XX +XXX,XX @@ static void netduino2_init(MachineState *machine) qdev_connect_clock_in(dev, "sysclk", sysclk); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - armv7m_load_kernel(ARM_CPU(first_cpu), machine->kernel_filename, + armv7m_load_kernel(STM32F205_SOC(dev)->armv7m.cpu, machine->kernel_filename, 0, FLASH_SIZE); } diff --git a/hw/arm/netduinoplus2.c b/hw/arm/netduinoplus2.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/netduinoplus2.c +++ b/hw/arm/netduinoplus2.c @@ -XXX,XX +XXX,XX @@ static void netduinoplus2_init(MachineState *machine) qdev_connect_clock_in(dev, "sysclk", sysclk); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - armv7m_load_kernel(ARM_CPU(first_cpu), + armv7m_load_kernel(STM32F405_SOC(dev)->armv7m.cpu, machine->kernel_filename, 0, FLASH_SIZE); } diff --git a/hw/arm/olimex-stm32-h405.c b/hw/arm/olimex-stm32-h405.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/olimex-stm32-h405.c +++ b/hw/arm/olimex-stm32-h405.c @@ -XXX,XX +XXX,XX @@ static void olimex_stm32_h405_init(MachineState *machine) qdev_connect_clock_in(dev, "sysclk", sysclk); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - armv7m_load_kernel(ARM_CPU(first_cpu), + armv7m_load_kernel(STM32F405_SOC(dev)->armv7m.cpu, machine->kernel_filename, 0, FLASH_SIZE); } diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) create_unimplemented_device("hibernation", 0x400fc000, 0x1000); create_unimplemented_device("flash-control", 0x400fd000, 0x1000); - armv7m_load_kernel(ARM_CPU(first_cpu), ms->kernel_filename, 0, flash_size); + armv7m_load_kernel(ARMV7M(armv7m)->cpu, ms->kernel_filename, 0, flash_size); } /* FIXME: Figure out how to generate these from stellaris_boards. */ diff --git a/hw/arm/stm32vldiscovery.c b/hw/arm/stm32vldiscovery.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stm32vldiscovery.c +++ b/hw/arm/stm32vldiscovery.c @@ -XXX,XX +XXX,XX @@ static void stm32vldiscovery_init(MachineState *machine) qdev_connect_clock_in(dev, "sysclk", sysclk); sysbus_realize_and_unref(SYS_BUS_DEVICE(dev), &error_fatal); - armv7m_load_kernel(ARM_CPU(first_cpu), + armv7m_load_kernel(STM32F100_SOC(dev)->armv7m.cpu, machine->kernel_filename, 0, FLASH_SIZE); } -- 2.34.1 From: Bernhard Beschow <shentey@gmail.com> The value of the UCFR register is respected when echoing characters to the terminal, but its reset value is reserved. Fix the reset value to the one documented in the datasheet. While at it move the related attribute out of the section of unimplemented registers since its value is actually respected. Signed-off-by: Bernhard Beschow <shentey@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/char/imx_serial.h | 2 +- hw/char/imx_serial.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/include/hw/char/imx_serial.h b/include/hw/char/imx_serial.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/char/imx_serial.h +++ b/include/hw/char/imx_serial.h @@ -XXX,XX +XXX,XX @@ struct IMXSerialState { uint32_t ucr1; uint32_t ucr2; uint32_t uts1; + uint32_t ufcr; /* * The registers below are implemented just so that the * guest OS sees what it has written */ uint32_t onems; - uint32_t ufcr; uint32_t ubmr; uint32_t ubrc; uint32_t ucr3; diff --git a/hw/char/imx_serial.c b/hw/char/imx_serial.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/imx_serial.c +++ b/hw/char/imx_serial.c @@ -XXX,XX +XXX,XX @@ static void imx_serial_reset(IMXSerialState *s) s->ucr3 = 0x700; s->ubmr = 0; s->ubrc = 4; + s->ufcr = BIT(11) | BIT(0); fifo32_reset(&s->rx_fifo); timer_del(&s->ageing_timer); -- 2.34.1 From: Bernhard Beschow <shentey@gmail.com> Fixes characters to be "echoed" after each keystroke rather than after every other since imx_serial_rx_fifo_ageing_timer_restart() would see ~UTS1_RXEMPTY only after every other keystroke. Signed-off-by: Bernhard Beschow <shentey@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/char/imx_serial.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/hw/char/imx_serial.c b/hw/char/imx_serial.c index XXXXXXX..XXXXXXX 100644 --- a/hw/char/imx_serial.c +++ b/hw/char/imx_serial.c @@ -XXX,XX +XXX,XX @@ static void imx_put_data(void *opaque, uint32_t value) if (fifo32_num_used(&s->rx_fifo) >= rxtl) { s->usr1 |= USR1_RRDY; } - - imx_serial_rx_fifo_ageing_timer_restart(s); - s->usr2 |= USR2_RDR; s->uts1 &= ~UTS1_RXEMPTY; if (value & URXD_BRK) { s->usr2 |= USR2_BRCD; } + + imx_serial_rx_fifo_ageing_timer_restart(s); + imx_update(s); } -- 2.34.1 From: Bernhard Beschow <shentey@gmail.com> Fixes INTD and MSI interrupts poking the same IRQ line without keeping track of each other's IRQ level. Furthermore, SoCs such as the i.MX 8M Plus don't share the MSI IRQ with the INTx lines, so expose it as a dedicated pin. Signed-off-by: Bernhard Beschow <shentey@gmail.com> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- include/hw/arm/fsl-imx6.h | 4 +++- include/hw/arm/fsl-imx7.h | 4 +++- include/hw/pci-host/designware.h | 1 + hw/arm/fsl-imx6.c | 13 ++++++++++++- hw/arm/fsl-imx7.c | 13 ++++++++++++- hw/pci-host/designware.c | 7 +++---- hw/arm/Kconfig | 2 ++ 7 files changed, 36 insertions(+), 8 deletions(-) diff --git a/include/hw/arm/fsl-imx6.h b/include/hw/arm/fsl-imx6.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx6.h +++ b/include/hw/arm/fsl-imx6.h @@ -XXX,XX +XXX,XX @@ #include "hw/usb/chipidea.h" #include "hw/usb/imx-usb-phy.h" #include "hw/pci-host/designware.h" +#include "hw/or-irq.h" #include "exec/memory.h" #include "cpu.h" #include "qom/object.h" @@ -XXX,XX +XXX,XX @@ struct FslIMX6State { ChipideaState usb[FSL_IMX6_NUM_USBS]; IMXFECState eth; DesignwarePCIEHost pcie; + OrIRQState pcie4_msi_irq; MemoryRegion rom; MemoryRegion caam; MemoryRegion ocram; @@ -XXX,XX +XXX,XX @@ struct FslIMX6State { #define FSL_IMX6_PCIE1_IRQ 120 #define FSL_IMX6_PCIE2_IRQ 121 #define FSL_IMX6_PCIE3_IRQ 122 -#define FSL_IMX6_PCIE4_IRQ 123 +#define FSL_IMX6_PCIE4_MSI_IRQ 123 #define FSL_IMX6_DCIC1_IRQ 124 #define FSL_IMX6_DCIC2_IRQ 125 #define FSL_IMX6_MLB150_HIGH_IRQ 126 diff --git a/include/hw/arm/fsl-imx7.h b/include/hw/arm/fsl-imx7.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/arm/fsl-imx7.h +++ b/include/hw/arm/fsl-imx7.h @@ -XXX,XX +XXX,XX @@ #include "hw/net/imx_fec.h" #include "hw/pci-host/designware.h" #include "hw/usb/chipidea.h" +#include "hw/or-irq.h" #include "cpu.h" #include "qom/object.h" #include "qemu/units.h" @@ -XXX,XX +XXX,XX @@ struct FslIMX7State { IMX7GPRState gpr; ChipideaState usb[FSL_IMX7_NUM_USBS]; DesignwarePCIEHost pcie; + OrIRQState pcie4_msi_irq; MemoryRegion rom; MemoryRegion caam; MemoryRegion ocram; @@ -XXX,XX +XXX,XX @@ enum FslIMX7IRQs { FSL_IMX7_PCI_INTA_IRQ = 125, FSL_IMX7_PCI_INTB_IRQ = 124, FSL_IMX7_PCI_INTC_IRQ = 123, - FSL_IMX7_PCI_INTD_IRQ = 122, + FSL_IMX7_PCI_INTD_MSI_IRQ = 122, FSL_IMX7_UART7_IRQ = 126, diff --git a/include/hw/pci-host/designware.h b/include/hw/pci-host/designware.h index XXXXXXX..XXXXXXX 100644 --- a/include/hw/pci-host/designware.h +++ b/include/hw/pci-host/designware.h @@ -XXX,XX +XXX,XX @@ struct DesignwarePCIEHost { MemoryRegion io; qemu_irq irqs[4]; + qemu_irq msi; } pci; MemoryRegion mmio; diff --git a/hw/arm/fsl-imx6.c b/hw/arm/fsl-imx6.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx6.c +++ b/hw/arm/fsl-imx6.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_init(Object *obj) object_initialize_child(obj, "eth", &s->eth, TYPE_IMX_ENET); object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST); + object_initialize_child(obj, "pcie4-msi-irq", &s->pcie4_msi_irq, + TYPE_OR_IRQ); } static void fsl_imx6_realize(DeviceState *dev, Error **errp) @@ -XXX,XX +XXX,XX @@ static void fsl_imx6_realize(DeviceState *dev, Error **errp) sysbus_realize(SYS_BUS_DEVICE(&s->pcie), &error_abort); sysbus_mmio_map(SYS_BUS_DEVICE(&s->pcie), 0, FSL_IMX6_PCIe_REG_ADDR); + object_property_set_int(OBJECT(&s->pcie4_msi_irq), "num-lines", 2, + &error_abort); + qdev_realize(DEVICE(&s->pcie4_msi_irq), NULL, &error_abort); + + irq = qdev_get_gpio_in(DEVICE(&s->a9mpcore), FSL_IMX6_PCIE4_MSI_IRQ); + qdev_connect_gpio_out(DEVICE(&s->pcie4_msi_irq), 0, irq); + irq = qdev_get_gpio_in(DEVICE(&s->a9mpcore), FSL_IMX6_PCIE1_IRQ); sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 0, irq); irq = qdev_get_gpio_in(DEVICE(&s->a9mpcore), FSL_IMX6_PCIE2_IRQ); sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 1, irq); irq = qdev_get_gpio_in(DEVICE(&s->a9mpcore), FSL_IMX6_PCIE3_IRQ); sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 2, irq); - irq = qdev_get_gpio_in(DEVICE(&s->a9mpcore), FSL_IMX6_PCIE4_IRQ); + irq = qdev_get_gpio_in(DEVICE(&s->pcie4_msi_irq), 0); sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 3, irq); + irq = qdev_get_gpio_in(DEVICE(&s->pcie4_msi_irq), 1); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 4, irq); /* * PCIe PHY diff --git a/hw/arm/fsl-imx7.c b/hw/arm/fsl-imx7.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/fsl-imx7.c +++ b/hw/arm/fsl-imx7.c @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_init(Object *obj) * PCIE */ object_initialize_child(obj, "pcie", &s->pcie, TYPE_DESIGNWARE_PCIE_HOST); + object_initialize_child(obj, "pcie4-msi-irq", &s->pcie4_msi_irq, + TYPE_OR_IRQ); /* * USBs @@ -XXX,XX +XXX,XX @@ static void fsl_imx7_realize(DeviceState *dev, Error **errp) sysbus_realize(SYS_BUS_DEVICE(&s->pcie), &error_abort); sysbus_mmio_map(SYS_BUS_DEVICE(&s->pcie), 0, FSL_IMX7_PCIE_REG_ADDR); + object_property_set_int(OBJECT(&s->pcie4_msi_irq), "num-lines", 2, + &error_abort); + qdev_realize(DEVICE(&s->pcie4_msi_irq), NULL, &error_abort); + + irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_PCI_INTD_MSI_IRQ); + qdev_connect_gpio_out(DEVICE(&s->pcie4_msi_irq), 0, irq); + irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_PCI_INTA_IRQ); sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 0, irq); irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_PCI_INTB_IRQ); sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 1, irq); irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_PCI_INTC_IRQ); sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 2, irq); - irq = qdev_get_gpio_in(DEVICE(&s->a7mpcore), FSL_IMX7_PCI_INTD_IRQ); + irq = qdev_get_gpio_in(DEVICE(&s->pcie4_msi_irq), 0); sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 3, irq); + irq = qdev_get_gpio_in(DEVICE(&s->pcie4_msi_irq), 1); + sysbus_connect_irq(SYS_BUS_DEVICE(&s->pcie), 4, irq); /* * USBs diff --git a/hw/pci-host/designware.c b/hw/pci-host/designware.c index XXXXXXX..XXXXXXX 100644 --- a/hw/pci-host/designware.c +++ b/hw/pci-host/designware.c @@ -XXX,XX +XXX,XX @@ #define DESIGNWARE_PCIE_ATU_DEVFN(x) (((x) >> 16) & 0xff) #define DESIGNWARE_PCIE_ATU_UPPER_TARGET 0x91C -#define DESIGNWARE_PCIE_IRQ_MSI 3 - static DesignwarePCIEHost * designware_pcie_root_to_host(DesignwarePCIERoot *root) { @@ -XXX,XX +XXX,XX @@ static void designware_pcie_root_msi_write(void *opaque, hwaddr addr, root->msi.intr[0].status |= BIT(val) & root->msi.intr[0].enable; if (root->msi.intr[0].status & ~root->msi.intr[0].mask) { - qemu_set_irq(host->pci.irqs[DESIGNWARE_PCIE_IRQ_MSI], 1); + qemu_set_irq(host->pci.msi, 1); } } @@ -XXX,XX +XXX,XX @@ static void designware_pcie_root_config_write(PCIDevice *d, uint32_t address, case DESIGNWARE_PCIE_MSI_INTR0_STATUS: root->msi.intr[0].status ^= val; if (!root->msi.intr[0].status) { - qemu_set_irq(host->pci.irqs[DESIGNWARE_PCIE_IRQ_MSI], 0); + qemu_set_irq(host->pci.msi, 0); } break; @@ -XXX,XX +XXX,XX @@ static void designware_pcie_host_realize(DeviceState *dev, Error **errp) for (i = 0; i < ARRAY_SIZE(s->pci.irqs); i++) { sysbus_init_irq(sbd, &s->pci.irqs[i]); } + sysbus_init_irq(sbd, &s->pci.msi); memory_region_init_io(&s->mmio, OBJECT(s), diff --git a/hw/arm/Kconfig b/hw/arm/Kconfig index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/Kconfig +++ b/hw/arm/Kconfig @@ -XXX,XX +XXX,XX @@ config FSL_IMX6 select PL310 # cache controller select PCI_EXPRESS_DESIGNWARE select SDHCI + select OR_IRQ config ASPEED_SOC bool @@ -XXX,XX +XXX,XX @@ config FSL_IMX7 select WDT_IMX2 select PCI_EXPRESS_DESIGNWARE select SDHCI + select OR_IRQ select UNIMP config ARM_SMMUV3 -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Board schematic is useful to corroborate GPIOs/IRQs wiring. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250110160204.74997-2-philmd@linaro.org [PMM: Use https:// URLs] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void lm3s6965evb_init(MachineState *machine) stellaris_init(machine, &stellaris_boards[1]); } +/* + * Stellaris LM3S811 Evaluation Board Schematics: + * https://www.ti.com/lit/ug/symlink/spmu030.pdf + */ static void lm3s811evb_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); @@ -XXX,XX +XXX,XX @@ static const TypeInfo lm3s811evb_type = { .class_init = lm3s811evb_class_init, }; +/* + * Stellaris: LM3S6965 Evaluation Board Schematics: + * https://www.ti.com/lit/ug/symlink/spmu029.pdf + */ static void lm3s6965evb_class_init(ObjectClass *oc, void *data) { MachineClass *mc = MACHINE_CLASS(oc); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250110160204.74997-3-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void ssys_update(ssys_state *s) qemu_set_irq(s->irq, (s->int_status & s->int_mask) != 0); } -static uint32_t pllcfg_sandstorm[16] = { +static const uint32_t pllcfg_sandstorm[16] = { 0x31c0, /* 1 Mhz */ 0x1ae0, /* 1.8432 Mhz */ 0x18c0, /* 2 Mhz */ @@ -XXX,XX +XXX,XX @@ static uint32_t pllcfg_sandstorm[16] = { 0x585b /* 8.192 Mhz */ }; -static uint32_t pllcfg_fury[16] = { +static const uint32_t pllcfg_fury[16] = { 0x3200, /* 1 Mhz */ 0x1b20, /* 1.8432 Mhz */ 0x1900, /* 2 Mhz */ @@ -XXX,XX +XXX,XX @@ static void stellaris_adc_init(Object *obj) } /* Board init. */ -static stellaris_board_info stellaris_boards[] = { +static const stellaris_board_info stellaris_boards[] = { { "LM3S811EVB", 0, 0x0032000e, -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> There is nothing mapped at 0x40002000. I2C#0 is already mapped at 0x40021000. Remove the invalid mapping added in commits aecfbbc97a2 & 394c8bbfb7a. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250110160204.74997-4-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) * http://www.ti.com/lit/ds/symlink/lm3s6965.pdf * * 40000000 wdtimer - * 40002000 i2c (unimplemented) * 40004000 GPIO * 40005000 GPIO * 40006000 GPIO @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) /* Add dummy regions for the devices we don't implement yet, * so guest accesses don't cause unlogged crashes. */ - create_unimplemented_device("i2c-0", 0x40002000, 0x1000); create_unimplemented_device("i2c-2", 0x40021000, 0x1000); create_unimplemented_device("PWM", 0x40028000, 0x1000); create_unimplemented_device("QEI-0", 0x4002c000, 0x1000); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Add definitions for the number of controllers. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250110160204.74997-5-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 25 +++++++++++++++---------- 1 file changed, 15 insertions(+), 10 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ #define NUM_IRQ_LINES 64 #define NUM_PRIO_BITS 3 +#define NUM_GPIO 7 +#define NUM_UART 4 +#define NUM_GPTM 4 +#define NUM_I2C 2 + typedef const struct { const char *name; uint32_t did0; @@ -XXX,XX +XXX,XX @@ static const stellaris_board_info stellaris_boards[] = { static void stellaris_init(MachineState *ms, stellaris_board_info *board) { - static const int uart_irq[] = {5, 6, 33, 34}; - static const int timer_irq[] = {19, 21, 23, 35}; - static const uint32_t gpio_addr[7] = + static const int uart_irq[NUM_UART] = {5, 6, 33, 34}; + static const int timer_irq[NUM_GPTM] = {19, 21, 23, 35}; + static const uint32_t gpio_addr[NUM_GPIO] = { 0x40004000, 0x40005000, 0x40006000, 0x40007000, 0x40024000, 0x40025000, 0x40026000}; - static const int gpio_irq[7] = {0, 1, 2, 3, 4, 30, 31}; + static const int gpio_irq[NUM_GPIO] = {0, 1, 2, 3, 4, 30, 31}; /* Memory map of SoC devices, from * Stellaris LM3S6965 Microcontroller Data Sheet (rev I) @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) */ Object *soc_container; - DeviceState *gpio_dev[7], *armv7m, *nvic; - qemu_irq gpio_in[7][8]; - qemu_irq gpio_out[7][8]; + DeviceState *gpio_dev[NUM_GPIO], *armv7m, *nvic; + qemu_irq gpio_in[NUM_GPIO][8]; + qemu_irq gpio_out[NUM_GPIO][8]; qemu_irq adc; int sram_size; int flash_size; @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) } else { adc = NULL; } - for (i = 0; i < 4; i++) { + for (i = 0; i < NUM_GPTM; i++) { if (board->dc2 & (0x10000 << i)) { SysBusDevice *sbd; @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) } - for (i = 0; i < 7; i++) { + for (i = 0; i < NUM_GPIO; i++) { if (board->dc4 & (1 << i)) { gpio_dev[i] = sysbus_create_simple("pl061_luminary", gpio_addr[i], qdev_get_gpio_in(nvic, @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) } } - for (i = 0; i < 4; i++) { + for (i = 0; i < NUM_UART; i++) { if (board->dc2 & (1 << i)) { SysBusDevice *sbd; -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> Add definitions (DCx_periph) for the DeviceCapability bits, replace direct bitmask checks with the DEV_CAP() macro, which use the extract/deposit API. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250110160204.74997-6-philmd@linaro.org Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 37 +++++++++++++++++++++++++++++-------- 1 file changed, 29 insertions(+), 8 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ */ #include "qemu/osdep.h" +#include "qemu/bitops.h" #include "qapi/error.h" #include "hw/core/split-irq.h" #include "hw/sysbus.h" @@ -XXX,XX +XXX,XX @@ #define NUM_GPTM 4 #define NUM_I2C 2 +/* + * See Stellaris Data Sheet chapter 5.2.5 "System Control", + * Register 13 .. 17: Device Capabilities 0 .. 4 (DC0 .. DC4). + */ +#define DC1_WDT 3 +#define DC1_HIB 6 +#define DC1_MPU 7 +#define DC1_ADC 16 +#define DC1_PWM 20 +#define DC2_UART(n) (n) +#define DC2_SSI 4 +#define DC2_QEI(n) (8 + n) +#define DC2_I2C(n) (12 + 2 * n) +#define DC2_GPTM(n) (16 + n) +#define DC2_COMP(n) (24 + n) +#define DC4_GPIO(n) (n) +#define DC4_EMAC 28 + +#define DEV_CAP(_dc, _cap) extract32(board->dc##_dc, DC##_dc##_##_cap, 1) + typedef const struct { const char *name; uint32_t did0; @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) sysbus_mmio_map(SYS_BUS_DEVICE(ssys_dev), 0, 0x400fe000); sysbus_connect_irq(SYS_BUS_DEVICE(ssys_dev), 0, qdev_get_gpio_in(nvic, 28)); - if (board->dc1 & (1 << 16)) { + if (DEV_CAP(1, ADC)) { dev = sysbus_create_varargs(TYPE_STELLARIS_ADC, 0x40038000, qdev_get_gpio_in(nvic, 14), qdev_get_gpio_in(nvic, 15), @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) adc = NULL; } for (i = 0; i < NUM_GPTM; i++) { - if (board->dc2 & (0x10000 << i)) { + if (DEV_CAP(2, GPTM(i))) { SysBusDevice *sbd; dev = qdev_new(TYPE_STELLARIS_GPTM); @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) } } - if (board->dc1 & (1 << 3)) { /* watchdog present */ + if (DEV_CAP(1, WDT)) { dev = qdev_new(TYPE_LUMINARY_WATCHDOG); object_property_add_child(soc_container, "wdg", OBJECT(dev)); qdev_connect_clock_in(dev, "WDOGCLK", @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) for (i = 0; i < NUM_GPIO; i++) { - if (board->dc4 & (1 << i)) { + if (DEV_CAP(4, GPIO(i))) { gpio_dev[i] = sysbus_create_simple("pl061_luminary", gpio_addr[i], qdev_get_gpio_in(nvic, gpio_irq[i])); @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) } } - if (board->dc2 & (1 << 12)) { + if (DEV_CAP(2, I2C(0))) { dev = sysbus_create_simple(TYPE_STELLARIS_I2C, 0x40020000, qdev_get_gpio_in(nvic, 8)); i2c = (I2CBus *)qdev_get_child_bus(dev, "i2c"); @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) } for (i = 0; i < NUM_UART; i++) { - if (board->dc2 & (1 << i)) { + if (DEV_CAP(2, UART(i))) { SysBusDevice *sbd; dev = qdev_new("pl011_luminary"); @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) sysbus_connect_irq(sbd, 0, qdev_get_gpio_in(nvic, uart_irq[i])); } } - if (board->dc2 & (1 << 4)) { + if (DEV_CAP(2, SSI)) { dev = sysbus_create_simple("pl022", 0x40008000, qdev_get_gpio_in(nvic, 7)); if (board->peripherals & BP_OLED_SSI) { @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) qemu_irq_raise(gpio_out[GPIO_D][0]); } } - if (board->dc4 & (1 << 28)) { + if (DEV_CAP(4, EMAC)) { DeviceState *enet; enet = qdev_new("stellaris_enet"); -- 2.34.1 From: Philippe Mathieu-Daudé <philmd@linaro.org> There are 2 I2C controllers, map them both, removing the unimplemented one. Keep the OLED controller on the first I2C bus. Signed-off-by: Philippe Mathieu-Daudé <philmd@linaro.org> Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250110160204.74997-7-philmd@linaro.org [PMM: tweak to appease maybe-use-uninitialized warning] Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/arm/stellaris.c | 21 +++++++++++++-------- 1 file changed, 13 insertions(+), 8 deletions(-) diff --git a/hw/arm/stellaris.c b/hw/arm/stellaris.c index XXXXXXX..XXXXXXX 100644 --- a/hw/arm/stellaris.c +++ b/hw/arm/stellaris.c @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) { 0x40004000, 0x40005000, 0x40006000, 0x40007000, 0x40024000, 0x40025000, 0x40026000}; static const int gpio_irq[NUM_GPIO] = {0, 1, 2, 3, 4, 30, 31}; + static const uint32_t i2c_addr[NUM_I2C] = {0x40020000, 0x40021000}; + static const int i2c_irq[NUM_I2C] = {8, 37}; /* Memory map of SoC devices, from * Stellaris LM3S6965 Microcontroller Data Sheet (rev I) @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) qemu_irq adc; int sram_size; int flash_size; - I2CBus *i2c; + DeviceState *i2c_dev[NUM_I2C] = { }; DeviceState *dev; DeviceState *ssys_dev; int i; @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) } } - if (DEV_CAP(2, I2C(0))) { - dev = sysbus_create_simple(TYPE_STELLARIS_I2C, 0x40020000, - qdev_get_gpio_in(nvic, 8)); - i2c = (I2CBus *)qdev_get_child_bus(dev, "i2c"); - if (board->peripherals & BP_OLED_I2C) { - i2c_slave_create_simple(i2c, "ssd0303", 0x3d); + for (i = 0; i < NUM_I2C; i++) { + if (DEV_CAP(2, I2C(i))) { + i2c_dev[i] = sysbus_create_simple(TYPE_STELLARIS_I2C, i2c_addr[i], + qdev_get_gpio_in(nvic, + i2c_irq[i])); } } + if (board->peripherals & BP_OLED_I2C) { + I2CBus *bus = (I2CBus *)qdev_get_child_bus(i2c_dev[0], "i2c"); + + i2c_slave_create_simple(bus, "ssd0303", 0x3d); + } for (i = 0; i < NUM_UART; i++) { if (DEV_CAP(2, UART(i))) { @@ -XXX,XX +XXX,XX @@ static void stellaris_init(MachineState *ms, stellaris_board_info *board) /* Add dummy regions for the devices we don't implement yet, * so guest accesses don't cause unlogged crashes. */ - create_unimplemented_device("i2c-2", 0x40021000, 0x1000); create_unimplemented_device("PWM", 0x40028000, 0x1000); create_unimplemented_device("QEI-0", 0x4002c000, 0x1000); create_unimplemented_device("QEI-1", 0x4002d000, 0x1000); -- 2.34.1 From: Thomas Huth <thuth@redhat.com> We don't have any functional tests for this machine yet, thus let's add a test with a MicroPython binary that is available online (thanks to Joel Stanley for providing it, see: https://www.mail-archive.com/qemu-devel@nongnu.org/msg606064.html ). Signed-off-by: Thomas Huth <thuth@redhat.com> Reviewed-by: Alex Bennée <alex.bennee@linaro.org> Message-id: 20250124101709.1591761-1-thuth@redhat.com Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- MAINTAINERS | 1 + tests/functional/meson.build | 1 + tests/functional/test_arm_microbit.py | 31 +++++++++++++++++++++++++++ 3 files changed, 33 insertions(+) create mode 100755 tests/functional/test_arm_microbit.py diff --git a/MAINTAINERS b/MAINTAINERS index XXXXXXX..XXXXXXX 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -XXX,XX +XXX,XX @@ F: hw/*/microbit*.c F: include/hw/*/nrf51*.h F: include/hw/*/microbit*.h F: tests/qtest/microbit-test.c +F: tests/functional/test_arm_microbit.py F: docs/system/arm/nrf.rst ARM PL011 Rust device diff --git a/tests/functional/meson.build b/tests/functional/meson.build index XXXXXXX..XXXXXXX 100644 --- a/tests/functional/meson.build +++ b/tests/functional/meson.build @@ -XXX,XX +XXX,XX @@ tests_arm_system_thorough = [ 'arm_cubieboard', 'arm_emcraft_sf2', 'arm_integratorcp', + 'arm_microbit', 'arm_orangepi', 'arm_quanta_gsj', 'arm_raspi2', diff --git a/tests/functional/test_arm_microbit.py b/tests/functional/test_arm_microbit.py new file mode 100755 index XXXXXXX..XXXXXXX --- /dev/null +++ b/tests/functional/test_arm_microbit.py @@ -XXX,XX +XXX,XX @@ +#!/usr/bin/env python3 +# +# SPDX-License-Identifier: GPL-2.0-or-later +# +# Copyright 2025, The QEMU Project Developers. +# +# A functional test that runs MicroPython on the arm microbit machine. + +from qemu_test import QemuSystemTest, Asset, exec_command_and_wait_for_pattern +from qemu_test import wait_for_console_pattern + + +class MicrobitMachine(QemuSystemTest): + + ASSET_MICRO = Asset('https://ozlabs.org/~joel/microbit-micropython.hex', + '021641f93dfb11767d4978dbb3ca7f475d1b13c69e7f4aec3382f212636bffd6') + + def test_arm_microbit(self): + self.set_machine('microbit') + + micropython = self.ASSET_MICRO.fetch() + self.vm.set_console() + self.vm.add_args('-device', f'loader,file={micropython}') + self.vm.launch() + wait_for_console_pattern(self, 'Type "help()" for more information.') + exec_command_and_wait_for_pattern(self, 'import machine as mch', '>>>') + exec_command_and_wait_for_pattern(self, 'mch.reset()', 'MicroPython') + wait_for_console_pattern(self, '>>>') + +if __name__ == '__main__': + QemuSystemTest.main() -- 2.34.1 The pseudocode ResetSVEState() does: FPSR = ZeroExtend(0x0800009f<31:0>, 64); but QEMU's arm_reset_sve_state() called vfp_set_fpcr() by accident. Before the advent of FEAT_AFP, this was only setting a collection of RES0 bits, which vfp_set_fpsr() would then ignore, so the only effect was that we didn't actually set the FPSR the way we are supposed to do. Once FEAT_AFP is implemented, setting the bottom bits of FPSR will change the floating point behaviour. Call vfp_set_fpsr(), as we ought to. (Note for stable backports: commit 7f2a01e7368f9 moved this function from sme_helper.c to helper.c, but it had the same bug before the move too.) Cc: qemu-stable@nongnu.org Fixes: f84734b87461 ("target/arm: Implement SMSTART, SMSTOP") Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-4-peter.maydell@linaro.org --- target/arm/helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/helper.c b/target/arm/helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/helper.c +++ b/target/arm/helper.c @@ -XXX,XX +XXX,XX @@ static void arm_reset_sve_state(CPUARMState *env) memset(env->vfp.zregs, 0, sizeof(env->vfp.zregs)); /* Recall that FFR is stored as pregs[16]. */ memset(env->vfp.pregs, 0, sizeof(env->vfp.pregs)); - vfp_set_fpcr(env, 0x0800009f); + vfp_set_fpsr(env, 0x0800009f); } void aarch64_set_svcr(CPUARMState *env, uint64_t new, uint64_t mask) -- 2.34.1 Use the FPSR_ named constants in vfp_exceptbits_from_host(), rather than hardcoded magic numbers. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-5-peter.maydell@linaro.org --- target/arm/vfp_helper.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ static inline int vfp_exceptbits_from_host(int host_bits) int target_bits = 0; if (host_bits & float_flag_invalid) { - target_bits |= 1; + target_bits |= FPSR_IOC; } if (host_bits & float_flag_divbyzero) { - target_bits |= 2; + target_bits |= FPSR_DZC; } if (host_bits & float_flag_overflow) { - target_bits |= 4; + target_bits |= FPSR_OFC; } if (host_bits & (float_flag_underflow | float_flag_output_denormal)) { - target_bits |= 8; + target_bits |= FPSR_UFC; } if (host_bits & float_flag_inexact) { - target_bits |= 0x10; + target_bits |= FPSR_IXC; } if (host_bits & float_flag_input_denormal) { - target_bits |= 0x80; + target_bits |= FPSR_IDC; } return target_bits; } -- 2.34.1 In vfp_exceptbits_from_host(), we accumulate the FPSR flags in an "int", and our return type is also "int". However, the only callsite returns the same information as a uint32_t, and more generally we handle FPSR values in the code as uint32_t, not int. Bring this function in to line with that convention. There is no behaviour change because none of the FPSR bits we set in this function are bit 31. The input argument to the function remains 'int' because that is the return type of the softfloat get_float_exception_flags(). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-6-peter.maydell@linaro.org --- target/arm/vfp_helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ #ifdef CONFIG_TCG /* Convert host exception flags to vfp form. */ -static inline int vfp_exceptbits_from_host(int host_bits) +static inline uint32_t vfp_exceptbits_from_host(int host_bits) { - int target_bits = 0; + uint32_t target_bits = 0; if (host_bits & float_flag_invalid) { target_bits |= FPSR_IOC; -- 2.34.1 We want to split the existing fp_status in the Arm CPUState into separate float_status fields for AArch32 and AArch64. (This is because new control bits defined by FEAT_AFP only have an effect for AArch64, not AArch32.) To make this split we will: * define new fp_status_a32 and fp_status_a64 which have identical behaviour to the existing fp_status * move existing uses of fp_status to fp_status_a32 or fp_status_a64 as appropriate * delete the old fp_status when it has no uses left In this patch we add the new float_status fields. We will also need to split fp_status_f16, but we will do that as a separate series of patches. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-7-peter.maydell@linaro.org --- target/arm/cpu.h | 4 ++++ target/arm/tcg/translate.h | 12 ++++++++++++ target/arm/cpu.c | 2 ++ target/arm/vfp_helper.c | 12 ++++++++++++ 4 files changed, 30 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUArchState { /* There are a number of distinct float control structures: * * fp_status: is the "normal" fp status. + * fp_status_a32: is the "normal" fp status for AArch32 insns + * fp_status_a64: is the "normal" fp status for AArch64 insns * fp_status_fp16: used for half-precision calculations * standard_fp_status : the ARM "Standard FPSCR Value" * standard_fp_status_fp16 : used for half-precision @@ -XXX,XX +XXX,XX @@ typedef struct CPUArchState { * an explicit FPSCR read. */ float_status fp_status; + float_status fp_status_a32; + float_status fp_status_a64; float_status fp_status_f16; float_status standard_fp_status; float_status standard_fp_status_f16; diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ static inline CPUARMTBFlags arm_tbflags_from_tb(const TranslationBlock *tb) */ typedef enum ARMFPStatusFlavour { FPST_FPCR, + FPST_A32, + FPST_A64, FPST_FPCR_F16, FPST_STD, FPST_STD_F16, @@ -XXX,XX +XXX,XX @@ typedef enum ARMFPStatusFlavour { * * FPST_FPCR * for non-FP16 operations controlled by the FPCR + * FPST_A32 + * for AArch32 non-FP16 operations controlled by the FPCR + * FPST_A64 + * for AArch64 non-FP16 operations controlled by the FPCR * FPST_FPCR_F16 * for operations controlled by the FPCR where FPCR.FZ16 is to be used * FPST_STD @@ -XXX,XX +XXX,XX @@ static inline TCGv_ptr fpstatus_ptr(ARMFPStatusFlavour flavour) case FPST_FPCR: offset = offsetof(CPUARMState, vfp.fp_status); break; + case FPST_A32: + offset = offsetof(CPUARMState, vfp.fp_status_a32); + break; + case FPST_A64: + offset = offsetof(CPUARMState, vfp.fp_status_a64); + break; case FPST_FPCR_F16: offset = offsetof(CPUARMState, vfp.fp_status_f16); break; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset_hold(Object *obj, ResetType type) set_default_nan_mode(1, &env->vfp.standard_fp_status); set_default_nan_mode(1, &env->vfp.standard_fp_status_f16); arm_set_default_fp_behaviours(&env->vfp.fp_status); + arm_set_default_fp_behaviours(&env->vfp.fp_status_a32); + arm_set_default_fp_behaviours(&env->vfp.fp_status_a64); arm_set_default_fp_behaviours(&env->vfp.standard_fp_status); arm_set_default_fp_behaviours(&env->vfp.fp_status_f16); arm_set_default_fp_behaviours(&env->vfp.standard_fp_status_f16); diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ static uint32_t vfp_get_fpsr_from_host(CPUARMState *env) uint32_t i; i = get_float_exception_flags(&env->vfp.fp_status); + i |= get_float_exception_flags(&env->vfp.fp_status_a32); + i |= get_float_exception_flags(&env->vfp.fp_status_a64); i |= get_float_exception_flags(&env->vfp.standard_fp_status); /* FZ16 does not generate an input denormal exception. */ i |= (get_float_exception_flags(&env->vfp.fp_status_f16) @@ -XXX,XX +XXX,XX @@ static void vfp_clear_float_status_exc_flags(CPUARMState *env) * be the architecturally up-to-date exception flag information first. */ set_float_exception_flags(0, &env->vfp.fp_status); + set_float_exception_flags(0, &env->vfp.fp_status_a32); + set_float_exception_flags(0, &env->vfp.fp_status_a64); set_float_exception_flags(0, &env->vfp.fp_status_f16); set_float_exception_flags(0, &env->vfp.standard_fp_status); set_float_exception_flags(0, &env->vfp.standard_fp_status_f16); @@ -XXX,XX +XXX,XX @@ static void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) break; } set_float_rounding_mode(i, &env->vfp.fp_status); + set_float_rounding_mode(i, &env->vfp.fp_status_a32); + set_float_rounding_mode(i, &env->vfp.fp_status_a64); set_float_rounding_mode(i, &env->vfp.fp_status_f16); } if (changed & FPCR_FZ16) { @@ -XXX,XX +XXX,XX @@ static void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) bool ftz_enabled = val & FPCR_FZ; set_flush_to_zero(ftz_enabled, &env->vfp.fp_status); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status); + set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_a32); + set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status_a32); + set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_a64); + set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status_a64); } if (changed & FPCR_DN) { bool dnan_enabled = val & FPCR_DN; set_default_nan_mode(dnan_enabled, &env->vfp.fp_status); + set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_a32); + set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_a64); set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_f16); } } -- 2.34.1 Switch from vfp.fp_status to vfp.fp_status_a64 for helpers which: * directly reference an fp_status field * are called only from the A64 decoder * are not called inside a set_rmode/restore_rmode sequence Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Message-id: 20250124162836.2332150-8-peter.maydell@linaro.org Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/tcg/sme_helper.c | 2 +- target/arm/tcg/vec_helper.c | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme_helper.c +++ b/target/arm/tcg/sme_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, * round-to-odd -- see above. */ fpst_f16 = env->vfp.fp_status_f16; - fpst_std = env->vfp.fp_status; + fpst_std = env->vfp.fp_status_a64; set_default_nan_mode(true, &fpst_std); set_default_nan_mode(true, &fpst_f16); fpst_odd = fpst_std; diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fmlal_a32)(void *vd, void *vn, void *vm, void HELPER(gvec_fmlal_a64)(void *vd, void *vn, void *vm, CPUARMState *env, uint32_t desc) { - do_fmlal(vd, vn, vm, &env->vfp.fp_status, desc, + do_fmlal(vd, vn, vm, &env->vfp.fp_status_a64, desc, get_flush_inputs_to_zero(&env->vfp.fp_status_f16)); } @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_fmlal_zzzw_s)(void *vd, void *vn, void *vm, void *va, intptr_t i, oprsz = simd_oprsz(desc); uint16_t negn = extract32(desc, SIMD_DATA_SHIFT, 1) << 15; intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16); - float_status *status = &env->vfp.fp_status; + float_status *status = &env->vfp.fp_status_a64; bool fz16 = get_flush_inputs_to_zero(&env->vfp.fp_status_f16); for (i = 0; i < oprsz; i += sizeof(float32)) { @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fmlal_idx_a32)(void *vd, void *vn, void *vm, void HELPER(gvec_fmlal_idx_a64)(void *vd, void *vn, void *vm, CPUARMState *env, uint32_t desc) { - do_fmlal_idx(vd, vn, vm, &env->vfp.fp_status, desc, + do_fmlal_idx(vd, vn, vm, &env->vfp.fp_status_a64, desc, get_flush_inputs_to_zero(&env->vfp.fp_status_f16)); } @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_fmlal_zzxw_s)(void *vd, void *vn, void *vm, void *va, uint16_t negn = extract32(desc, SIMD_DATA_SHIFT, 1) << 15; intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16); intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 3) * sizeof(float16); - float_status *status = &env->vfp.fp_status; + float_status *status = &env->vfp.fp_status_a64; bool fz16 = get_flush_inputs_to_zero(&env->vfp.fp_status_f16); for (i = 0; i < oprsz; i += 16) { -- 2.34.1 In is_ebf(), we might be called for A64 or A32, but we have the CPUARMState* so we can select fp_status_a64 or fp_status_a32 accordingly. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> --- target/arm/tcg/vec_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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) */ bool ebf = is_a64(env) && env->vfp.fpcr & FPCR_EBF; - *statusp = env->vfp.fp_status; + *statusp = is_a64(env) ? env->vfp.fp_status_a64 : env->vfp.fp_status_a32; set_default_nan_mode(true, statusp); if (ebf) { -- 2.34.1 Use fp_status_a32 in the vjcvt helper function; this is called only from the A32/T32 decoder and is not used inside a set_rmode/restore_rmode sequence. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-9-peter.maydell@linaro.org --- target/arm/vfp_helper.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(fjcvtzs)(float64 value, float_status *status) uint32_t HELPER(vjcvt)(float64 value, CPUARMState *env) { - uint64_t pair = HELPER(fjcvtzs)(value, &env->vfp.fp_status); + uint64_t pair = HELPER(fjcvtzs)(value, &env->vfp.fp_status_a32); uint32_t result = pair; uint32_t z = (pair >> 32) == 0; -- 2.34.1 The helpers vfp_cmps, vfp_cmpes, vfp_cmpd, vfp_cmped are used only from the A32 decoder; the A64 decoder uses separate vfp_cmps_a64 etc helpers (because for A64 we update the main NZCV flags and for A32 we update the FPSCR NZCV flags). So we can make these helpers use the fp_status_a32 field instead of fp_status. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-10-peter.maydell@linaro.org --- target/arm/vfp_helper.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ void VFP_HELPER(cmpe, P)(ARGTYPE a, ARGTYPE b, CPUARMState *env) \ FLOATTYPE ## _compare(a, b, &env->vfp.FPST)); \ } DO_VFP_cmp(h, float16, dh_ctype_f16, fp_status_f16) -DO_VFP_cmp(s, float32, float32, fp_status) -DO_VFP_cmp(d, float64, float64, fp_status) +DO_VFP_cmp(s, float32, float32, fp_status_a32) +DO_VFP_cmp(d, float64, float64, fp_status_a32) #undef DO_VFP_cmp /* Integer to float and float to integer conversions */ -- 2.34.1 In the A32 decoder, use FPST_A32 rather than FPST_FPCR. By doing an automated conversion of the whole file we avoid possibly using more than one fpst value in a set_rmode/op/restore_rmode sequence. Patch created with perl -p -i -e 's/FPST_FPCR(?!_)/FPST_A32/g' target/arm/tcg/translate-vfp.c Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-11-peter.maydell@linaro.org --- target/arm/tcg/translate-vfp.c | 54 +++++++++++++++++----------------- 1 file changed, 27 insertions(+), 27 deletions(-) diff --git a/target/arm/tcg/translate-vfp.c b/target/arm/tcg/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-vfp.c +++ b/target/arm/tcg/translate-vfp.c @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) if (sz == 1) { fpst = fpstatus_ptr(FPST_FPCR_F16); } else { - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); } tcg_rmode = gen_set_rmode(rounding, fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) if (sz == 1) { fpst = fpstatus_ptr(FPST_FPCR_F16); } else { - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); } tcg_shift = tcg_constant_i32(0); @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_sp(DisasContext *s, VFPGen3OpSPFn *fn, f0 = tcg_temp_new_i32(); f1 = tcg_temp_new_i32(); fd = tcg_temp_new_i32(); - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); vfp_load_reg32(f0, vn); vfp_load_reg32(f1, vm); @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_dp(DisasContext *s, VFPGen3OpDPFn *fn, f0 = tcg_temp_new_i64(); f1 = tcg_temp_new_i64(); fd = tcg_temp_new_i64(); - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); vfp_load_reg64(f0, vn); vfp_load_reg64(f1, vm); @@ -XXX,XX +XXX,XX @@ static bool do_vfm_sp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) /* VFNMA, VFNMS */ gen_vfp_negs(vd, vd); } - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); gen_helper_vfp_muladds(vd, vn, vm, vd, fpst); vfp_store_reg32(vd, a->vd); return true; @@ -XXX,XX +XXX,XX @@ static bool do_vfm_dp(DisasContext *s, arg_VFMA_dp *a, bool neg_n, bool neg_d) /* VFNMA, VFNMS */ gen_vfp_negd(vd, vd); } - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); gen_helper_vfp_muladdd(vd, vn, vm, vd, fpst); vfp_store_reg64(vd, a->vd); return true; @@ -XXX,XX +XXX,XX @@ static void gen_VSQRT_hp(TCGv_i32 vd, TCGv_i32 vm) static void gen_VSQRT_sp(TCGv_i32 vd, TCGv_i32 vm) { - gen_helper_vfp_sqrts(vd, vm, fpstatus_ptr(FPST_FPCR)); + gen_helper_vfp_sqrts(vd, vm, fpstatus_ptr(FPST_A32)); } static void gen_VSQRT_dp(TCGv_i64 vd, TCGv_i64 vm) { - gen_helper_vfp_sqrtd(vd, vm, fpstatus_ptr(FPST_FPCR)); + gen_helper_vfp_sqrtd(vd, vm, fpstatus_ptr(FPST_A32)); } DO_VFP_2OP(VSQRT, hp, gen_VSQRT_hp, aa32_fp16_arith) @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f32_f16(DisasContext *s, arg_VCVT_f32_f16 *a) return true; } - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); ahp_mode = get_ahp_flag(); tmp = tcg_temp_new_i32(); /* The T bit tells us if we want the low or high 16 bits of Vm */ @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f64_f16(DisasContext *s, arg_VCVT_f64_f16 *a) return true; } - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); ahp_mode = get_ahp_flag(); tmp = tcg_temp_new_i32(); /* The T bit tells us if we want the low or high 16 bits of Vm */ @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_b16_f32(DisasContext *s, arg_VCVT_b16_f32 *a) return true; } - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); tmp = tcg_temp_new_i32(); vfp_load_reg32(tmp, a->vm); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f16_f32(DisasContext *s, arg_VCVT_f16_f32 *a) return true; } - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); ahp_mode = get_ahp_flag(); tmp = tcg_temp_new_i32(); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_f16_f64(DisasContext *s, arg_VCVT_f16_f64 *a) return true; } - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); ahp_mode = get_ahp_flag(); tmp = tcg_temp_new_i32(); vm = tcg_temp_new_i64(); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_sp(DisasContext *s, arg_VRINTR_sp *a) tmp = tcg_temp_new_i32(); vfp_load_reg32(tmp, a->vm); - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); gen_helper_rints(tmp, tmp, fpst); vfp_store_reg32(tmp, a->vd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_dp(DisasContext *s, arg_VRINTR_dp *a) tmp = tcg_temp_new_i64(); vfp_load_reg64(tmp, a->vm); - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); gen_helper_rintd(tmp, tmp, fpst); vfp_store_reg64(tmp, a->vd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_sp(DisasContext *s, arg_VRINTZ_sp *a) tmp = tcg_temp_new_i32(); vfp_load_reg32(tmp, a->vm); - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); tcg_rmode = gen_set_rmode(FPROUNDING_ZERO, fpst); gen_helper_rints(tmp, tmp, fpst); gen_restore_rmode(tcg_rmode, fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_dp(DisasContext *s, arg_VRINTZ_dp *a) tmp = tcg_temp_new_i64(); vfp_load_reg64(tmp, a->vm); - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); tcg_rmode = gen_set_rmode(FPROUNDING_ZERO, fpst); gen_helper_rintd(tmp, tmp, fpst); gen_restore_rmode(tcg_rmode, fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_sp(DisasContext *s, arg_VRINTX_sp *a) tmp = tcg_temp_new_i32(); vfp_load_reg32(tmp, a->vm); - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); gen_helper_rints_exact(tmp, tmp, fpst); vfp_store_reg32(tmp, a->vd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_dp(DisasContext *s, arg_VRINTX_dp *a) tmp = tcg_temp_new_i64(); vfp_load_reg64(tmp, a->vm); - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); gen_helper_rintd_exact(tmp, tmp, fpst); vfp_store_reg64(tmp, a->vd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp(DisasContext *s, arg_VCVT_sp *a) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i64(); vfp_load_reg32(vm, a->vm); - gen_helper_vfp_fcvtds(vd, vm, fpstatus_ptr(FPST_FPCR)); + gen_helper_vfp_fcvtds(vd, vm, fpstatus_ptr(FPST_A32)); vfp_store_reg64(vd, a->vd); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp(DisasContext *s, arg_VCVT_dp *a) vd = tcg_temp_new_i32(); vm = tcg_temp_new_i64(); vfp_load_reg64(vm, a->vm); - gen_helper_vfp_fcvtsd(vd, vm, fpstatus_ptr(FPST_FPCR)); + gen_helper_vfp_fcvtsd(vd, vm, fpstatus_ptr(FPST_A32)); vfp_store_reg32(vd, a->vd); return true; } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_sp(DisasContext *s, arg_VCVT_int_sp *a) vm = tcg_temp_new_i32(); vfp_load_reg32(vm, a->vm); - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); if (a->s) { /* i32 -> f32 */ gen_helper_vfp_sitos(vm, vm, fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_dp(DisasContext *s, arg_VCVT_int_dp *a) vm = tcg_temp_new_i32(); vd = tcg_temp_new_i64(); vfp_load_reg32(vm, a->vm); - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); if (a->s) { /* i32 -> f64 */ gen_helper_vfp_sitod(vd, vm, fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_sp(DisasContext *s, arg_VCVT_fix_sp *a) vd = tcg_temp_new_i32(); vfp_load_reg32(vd, a->vd); - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); shift = tcg_constant_i32(frac_bits); /* Switch on op:U:sx bits */ @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_dp(DisasContext *s, arg_VCVT_fix_dp *a) vd = tcg_temp_new_i64(); vfp_load_reg64(vd, a->vd); - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); shift = tcg_constant_i32(frac_bits); /* Switch on op:U:sx bits */ @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_sp_int(DisasContext *s, arg_VCVT_sp_int *a) return true; } - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); vm = tcg_temp_new_i32(); vfp_load_reg32(vm, a->vm); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_dp_int(DisasContext *s, arg_VCVT_dp_int *a) return true; } - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A32); vm = tcg_temp_new_i64(); vd = tcg_temp_new_i32(); vfp_load_reg64(vm, a->vm); -- 2.34.1 In the A64 decoder, use FPST_A64 rather than FPST_FPCR. By doing an automated conversion of the whole file we avoid possibly using more than one fpst value in a set_rmode/op/restore_rmode sequence. Patch created with perl -p -i -e 's/FPST_FPCR(?!_)/FPST_A64/g' target/arm/tcg/translate-{a64,sve,sme}.c Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-12-peter.maydell@linaro.org --- target/arm/tcg/translate-a64.c | 70 +++++++++++----------- target/arm/tcg/translate-sme.c | 4 +- target/arm/tcg/translate-sve.c | 106 ++++++++++++++++----------------- 3 files changed, 90 insertions(+), 90 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_gvec_op3_fpst(DisasContext *s, bool is_q, int rd, int rn, int rm, bool is_fp16, int data, gen_helper_gvec_3_ptr *fn) { - TCGv_ptr fpst = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_FPCR); + TCGv_ptr fpst = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_A64); tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn), vec_full_reg_offset(s, rm), fpst, @@ -XXX,XX +XXX,XX @@ static void gen_gvec_op4_fpst(DisasContext *s, bool is_q, int rd, int rn, int rm, int ra, bool is_fp16, int data, gen_helper_gvec_4_ptr *fn) { - TCGv_ptr fpst = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_FPCR); + TCGv_ptr fpst = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_A64); tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn), vec_full_reg_offset(s, rm), @@ -XXX,XX +XXX,XX @@ static bool do_fp3_scalar(DisasContext *s, arg_rrr_e *a, const FPScalar *f) if (fp_access_check(s)) { TCGv_i64 t0 = read_fp_dreg(s, a->rn); TCGv_i64 t1 = read_fp_dreg(s, a->rm); - f->gen_d(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + f->gen_d(t0, t0, t1, fpstatus_ptr(FPST_A64)); write_fp_dreg(s, a->rd, t0); } break; @@ -XXX,XX +XXX,XX @@ static bool do_fp3_scalar(DisasContext *s, arg_rrr_e *a, const FPScalar *f) if (fp_access_check(s)) { TCGv_i32 t0 = read_fp_sreg(s, a->rn); TCGv_i32 t1 = read_fp_sreg(s, a->rm); - f->gen_s(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + f->gen_s(t0, t0, t1, fpstatus_ptr(FPST_A64)); write_fp_sreg(s, a->rd, t0); } break; @@ -XXX,XX +XXX,XX @@ static bool do_fcmp0_s(DisasContext *s, arg_rr_e *a, TCGv_i64 t0 = read_fp_dreg(s, a->rn); TCGv_i64 t1 = tcg_constant_i64(0); if (swap) { - f->gen_d(t0, t1, t0, fpstatus_ptr(FPST_FPCR)); + f->gen_d(t0, t1, t0, fpstatus_ptr(FPST_A64)); } else { - f->gen_d(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + f->gen_d(t0, t0, t1, fpstatus_ptr(FPST_A64)); } write_fp_dreg(s, a->rd, t0); } @@ -XXX,XX +XXX,XX @@ static bool do_fcmp0_s(DisasContext *s, arg_rr_e *a, TCGv_i32 t0 = read_fp_sreg(s, a->rn); TCGv_i32 t1 = tcg_constant_i32(0); if (swap) { - f->gen_s(t0, t1, t0, fpstatus_ptr(FPST_FPCR)); + f->gen_s(t0, t1, t0, fpstatus_ptr(FPST_A64)); } else { - f->gen_s(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + f->gen_s(t0, t0, t1, fpstatus_ptr(FPST_A64)); } write_fp_sreg(s, a->rd, t0); } @@ -XXX,XX +XXX,XX @@ static bool do_fp3_scalar_idx(DisasContext *s, arg_rrx_e *a, const FPScalar *f) TCGv_i64 t1 = tcg_temp_new_i64(); read_vec_element(s, t1, a->rm, a->idx, MO_64); - f->gen_d(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + f->gen_d(t0, t0, t1, fpstatus_ptr(FPST_A64)); write_fp_dreg(s, a->rd, t0); } break; @@ -XXX,XX +XXX,XX @@ static bool do_fp3_scalar_idx(DisasContext *s, arg_rrx_e *a, const FPScalar *f) TCGv_i32 t1 = tcg_temp_new_i32(); read_vec_element_i32(s, t1, a->rm, a->idx, MO_32); - f->gen_s(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + f->gen_s(t0, t0, t1, fpstatus_ptr(FPST_A64)); write_fp_sreg(s, a->rd, t0); } break; @@ -XXX,XX +XXX,XX @@ static bool do_fmla_scalar_idx(DisasContext *s, arg_rrx_e *a, bool neg) if (neg) { gen_vfp_negd(t1, t1); } - gen_helper_vfp_muladdd(t0, t1, t2, t0, fpstatus_ptr(FPST_FPCR)); + gen_helper_vfp_muladdd(t0, t1, t2, t0, fpstatus_ptr(FPST_A64)); write_fp_dreg(s, a->rd, t0); } break; @@ -XXX,XX +XXX,XX @@ static bool do_fmla_scalar_idx(DisasContext *s, arg_rrx_e *a, bool neg) if (neg) { gen_vfp_negs(t1, t1); } - gen_helper_vfp_muladds(t0, t1, t2, t0, fpstatus_ptr(FPST_FPCR)); + gen_helper_vfp_muladds(t0, t1, t2, t0, fpstatus_ptr(FPST_A64)); write_fp_sreg(s, a->rd, t0); } break; @@ -XXX,XX +XXX,XX @@ static bool do_fp3_scalar_pair(DisasContext *s, arg_rr_e *a, const FPScalar *f) read_vec_element(s, t0, a->rn, 0, MO_64); read_vec_element(s, t1, a->rn, 1, MO_64); - f->gen_d(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + f->gen_d(t0, t0, t1, fpstatus_ptr(FPST_A64)); write_fp_dreg(s, a->rd, t0); } break; @@ -XXX,XX +XXX,XX @@ static bool do_fp3_scalar_pair(DisasContext *s, arg_rr_e *a, const FPScalar *f) read_vec_element_i32(s, t0, a->rn, 0, MO_32); read_vec_element_i32(s, t1, a->rn, 1, MO_32); - f->gen_s(t0, t0, t1, fpstatus_ptr(FPST_FPCR)); + f->gen_s(t0, t0, t1, fpstatus_ptr(FPST_A64)); write_fp_sreg(s, a->rd, t0); } break; @@ -XXX,XX +XXX,XX @@ static bool do_fmadd(DisasContext *s, arg_rrrr_e *a, bool neg_a, bool neg_n) if (neg_n) { gen_vfp_negd(tn, tn); } - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A64); gen_helper_vfp_muladdd(ta, tn, tm, ta, fpst); write_fp_dreg(s, a->rd, ta); } @@ -XXX,XX +XXX,XX @@ static bool do_fmadd(DisasContext *s, arg_rrrr_e *a, bool neg_a, bool neg_n) if (neg_n) { gen_vfp_negs(tn, tn); } - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A64); gen_helper_vfp_muladds(ta, tn, tm, ta, fpst); write_fp_sreg(s, a->rd, ta); } @@ -XXX,XX +XXX,XX @@ static bool do_fp_reduction(DisasContext *s, arg_qrr_e *a, if (fp_access_check(s)) { MemOp esz = a->esz; int elts = (a->q ? 16 : 8) >> esz; - TCGv_ptr fpst = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + TCGv_ptr fpst = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); TCGv_i32 res = do_reduction_op(s, a->rn, esz, 0, elts, fpst, fn); write_fp_sreg(s, a->rd, res); } @@ -XXX,XX +XXX,XX @@ static void handle_fp_compare(DisasContext *s, int size, bool cmp_with_zero, bool signal_all_nans) { TCGv_i64 tcg_flags = tcg_temp_new_i64(); - TCGv_ptr fpst = fpstatus_ptr(size == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + TCGv_ptr fpst = fpstatus_ptr(size == MO_16 ? FPST_FPCR_F16 : FPST_A64); if (size == MO_64) { TCGv_i64 tcg_vn, tcg_vm; @@ -XXX,XX +XXX,XX @@ static bool do_fp1_scalar(DisasContext *s, arg_rr_e *a, return check == 0; } - fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); if (rmode >= 0) { tcg_rmode = gen_set_rmode(rmode, fpst); } @@ -XXX,XX +XXX,XX @@ static bool trans_FCVT_s_ds(DisasContext *s, arg_rr *a) if (fp_access_check(s)) { TCGv_i32 tcg_rn = read_fp_sreg(s, a->rn); TCGv_i64 tcg_rd = tcg_temp_new_i64(); - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); + TCGv_ptr fpst = fpstatus_ptr(FPST_A64); gen_helper_vfp_fcvtds(tcg_rd, tcg_rn, fpst); write_fp_dreg(s, a->rd, tcg_rd); @@ -XXX,XX +XXX,XX @@ static bool trans_FCVT_s_hs(DisasContext *s, arg_rr *a) if (fp_access_check(s)) { TCGv_i32 tmp = read_fp_sreg(s, a->rn); TCGv_i32 ahp = get_ahp_flag(); - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); + TCGv_ptr fpst = fpstatus_ptr(FPST_A64); gen_helper_vfp_fcvt_f32_to_f16(tmp, tmp, fpst, ahp); /* write_fp_sreg is OK here because top half of result is zero */ @@ -XXX,XX +XXX,XX @@ static bool trans_FCVT_s_sd(DisasContext *s, arg_rr *a) if (fp_access_check(s)) { TCGv_i64 tcg_rn = read_fp_dreg(s, a->rn); TCGv_i32 tcg_rd = tcg_temp_new_i32(); - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); + TCGv_ptr fpst = fpstatus_ptr(FPST_A64); gen_helper_vfp_fcvtsd(tcg_rd, tcg_rn, fpst); write_fp_sreg(s, a->rd, tcg_rd); @@ -XXX,XX +XXX,XX @@ static bool trans_FCVT_s_hd(DisasContext *s, arg_rr *a) TCGv_i64 tcg_rn = read_fp_dreg(s, a->rn); TCGv_i32 tcg_rd = tcg_temp_new_i32(); TCGv_i32 ahp = get_ahp_flag(); - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); + TCGv_ptr fpst = fpstatus_ptr(FPST_A64); gen_helper_vfp_fcvt_f64_to_f16(tcg_rd, tcg_rn, fpst, ahp); /* write_fp_sreg is OK here because top half of tcg_rd is zero */ @@ -XXX,XX +XXX,XX @@ static bool trans_FCVT_s_sh(DisasContext *s, arg_rr *a) if (fp_access_check(s)) { TCGv_i32 tcg_rn = read_fp_hreg(s, a->rn); TCGv_i32 tcg_rd = tcg_temp_new_i32(); - TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_FPCR); + TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_A64); TCGv_i32 tcg_ahp = get_ahp_flag(); gen_helper_vfp_fcvt_f16_to_f32(tcg_rd, tcg_rn, tcg_fpst, tcg_ahp); @@ -XXX,XX +XXX,XX @@ static bool trans_FCVT_s_dh(DisasContext *s, arg_rr *a) if (fp_access_check(s)) { TCGv_i32 tcg_rn = read_fp_hreg(s, a->rn); TCGv_i64 tcg_rd = tcg_temp_new_i64(); - TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_FPCR); + TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_A64); TCGv_i32 tcg_ahp = get_ahp_flag(); gen_helper_vfp_fcvt_f16_to_f64(tcg_rd, tcg_rn, tcg_fpst, tcg_ahp); @@ -XXX,XX +XXX,XX @@ static bool do_cvtf_scalar(DisasContext *s, MemOp esz, int rd, int shift, TCGv_i32 tcg_shift, tcg_single; TCGv_i64 tcg_double; - tcg_fpstatus = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + tcg_fpstatus = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); tcg_shift = tcg_constant_i32(shift); switch (esz) { @@ -XXX,XX +XXX,XX @@ static void do_fcvt_scalar(DisasContext *s, MemOp out, MemOp esz, TCGv_ptr tcg_fpstatus; TCGv_i32 tcg_shift, tcg_rmode, tcg_single; - tcg_fpstatus = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + tcg_fpstatus = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); tcg_shift = tcg_constant_i32(shift); tcg_rmode = gen_set_rmode(rmode, tcg_fpstatus); @@ -XXX,XX +XXX,XX @@ static bool trans_FJCVTZS(DisasContext *s, arg_FJCVTZS *a) } if (fp_access_check(s)) { TCGv_i64 t = read_fp_dreg(s, a->rn); - TCGv_ptr fpstatus = fpstatus_ptr(FPST_FPCR); + TCGv_ptr fpstatus = fpstatus_ptr(FPST_A64); gen_helper_fjcvtzs(t, t, fpstatus); @@ -XXX,XX +XXX,XX @@ static void gen_fcvtxn_sd(TCGv_i64 d, TCGv_i64 n) * with von Neumann rounding (round to odd) */ TCGv_i32 tmp = tcg_temp_new_i32(); - gen_helper_fcvtx_f64_to_f32(tmp, n, fpstatus_ptr(FPST_FPCR)); + gen_helper_fcvtx_f64_to_f32(tmp, n, fpstatus_ptr(FPST_A64)); tcg_gen_extu_i32_i64(d, tmp); } @@ -XXX,XX +XXX,XX @@ static void gen_fcvtn_hs(TCGv_i64 d, TCGv_i64 n) { TCGv_i32 tcg_lo = tcg_temp_new_i32(); TCGv_i32 tcg_hi = tcg_temp_new_i32(); - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); + TCGv_ptr fpst = fpstatus_ptr(FPST_A64); TCGv_i32 ahp = get_ahp_flag(); tcg_gen_extr_i64_i32(tcg_lo, tcg_hi, n); @@ -XXX,XX +XXX,XX @@ static void gen_fcvtn_hs(TCGv_i64 d, TCGv_i64 n) static void gen_fcvtn_sd(TCGv_i64 d, TCGv_i64 n) { TCGv_i32 tmp = tcg_temp_new_i32(); - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); + TCGv_ptr fpst = fpstatus_ptr(FPST_A64); gen_helper_vfp_fcvtsd(tmp, n, fpst); tcg_gen_extu_i32_i64(d, tmp); @@ -XXX,XX +XXX,XX @@ TRANS(FCVTXN_v, do_2misc_narrow_vector, a, f_scalar_fcvtxn) static void gen_bfcvtn_hs(TCGv_i64 d, TCGv_i64 n) { - TCGv_ptr fpst = fpstatus_ptr(FPST_FPCR); + TCGv_ptr fpst = fpstatus_ptr(FPST_A64); TCGv_i32 tmp = tcg_temp_new_i32(); gen_helper_bfcvt_pair(tmp, n, fpst); tcg_gen_extu_i32_i64(d, tmp); @@ -XXX,XX +XXX,XX @@ static bool do_fp1_vector(DisasContext *s, arg_qrr_e *a, return check == 0; } - fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); if (rmode >= 0) { tcg_rmode = gen_set_rmode(rmode, fpst); } @@ -XXX,XX +XXX,XX @@ static bool do_gvec_op2_fpst(DisasContext *s, MemOp esz, bool is_q, return check == 0; } - fpst = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + fpst = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn), fpst, is_q ? 16 : 8, vec_full_reg_size(s), @@ -XXX,XX +XXX,XX @@ static bool trans_FCVTL_v(DisasContext *s, arg_qrr_e *a) return true; } - fpst = fpstatus_ptr(FPST_FPCR); + fpst = fpstatus_ptr(FPST_A64); if (a->esz == MO_64) { /* 32 -> 64 bit fp conversion */ TCGv_i64 tcg_res[2]; diff --git a/target/arm/tcg/translate-sme.c b/target/arm/tcg/translate-sme.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-sme.c +++ b/target/arm/tcg/translate-sme.c @@ -XXX,XX +XXX,XX @@ static bool do_outprod_env(DisasContext *s, arg_op *a, MemOp esz, TRANS_FEAT(FMOPA_h, aa64_sme, do_outprod_env, a, MO_32, gen_helper_sme_fmopa_h) TRANS_FEAT(FMOPA_s, aa64_sme, do_outprod_fpst, a, - MO_32, FPST_FPCR, gen_helper_sme_fmopa_s) + MO_32, FPST_A64, gen_helper_sme_fmopa_s) TRANS_FEAT(FMOPA_d, aa64_sme_f64f64, do_outprod_fpst, a, - MO_64, FPST_FPCR, gen_helper_sme_fmopa_d) + MO_64, FPST_A64, gen_helper_sme_fmopa_d) TRANS_FEAT(BFMOPA, aa64_sme, do_outprod_env, a, MO_32, gen_helper_sme_bfmopa) diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-sve.c +++ b/target/arm/tcg/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_fpst_arg_zz(DisasContext *s, gen_helper_gvec_2_ptr *fn, arg_rr_esz *a, int data) { return gen_gvec_fpst_zz(s, fn, a->rd, a->rn, data, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); } /* Invoke an out-of-line helper on 3 Zregs. */ @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_fpst_arg_zzz(DisasContext *s, gen_helper_gvec_3_ptr *fn, arg_rrr_esz *a, int data) { return gen_gvec_fpst_zzz(s, fn, a->rd, a->rn, a->rm, data, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); } /* Invoke an out-of-line helper on 4 Zregs. */ @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_fpst_arg_zpzz(DisasContext *s, gen_helper_gvec_4_ptr *fn, arg_rprr_esz *a) { return gen_gvec_fpst_zzzp(s, fn, a->rd, a->rn, a->rm, a->pg, 0, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); } /* Invoke a vector expander on two Zregs and an immediate. */ @@ -XXX,XX +XXX,XX @@ static bool do_FMLA_zzxz(DisasContext *s, arg_rrxr_esz *a, bool sub) }; return gen_gvec_fpst_zzzz(s, fns[a->esz], a->rd, a->rn, a->rm, a->ra, (a->index << 1) | sub, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); } TRANS_FEAT(FMLA_zzxz, aa64_sve, do_FMLA_zzxz, a, false) @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const fmul_idx_fns[4] = { }; TRANS_FEAT(FMUL_zzx, aa64_sve, gen_gvec_fpst_zzz, fmul_idx_fns[a->esz], a->rd, a->rn, a->rm, a->index, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) /* *** SVE Floating Point Fast Reduction Group @@ -XXX,XX +XXX,XX @@ static bool do_reduce(DisasContext *s, arg_rpr_esz *a, tcg_gen_addi_ptr(t_zn, tcg_env, vec_full_reg_offset(s, a->rn)); tcg_gen_addi_ptr(t_pg, tcg_env, pred_full_reg_offset(s, a->pg)); - status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); fn(temp, t_zn, t_pg, status, t_desc); @@ -XXX,XX +XXX,XX @@ static bool do_ppz_fp(DisasContext *s, arg_rpr_esz *a, if (sve_access_check(s)) { unsigned vsz = vec_full_reg_size(s); TCGv_ptr status = - fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); tcg_gen_gvec_3_ptr(pred_full_reg_offset(s, a->rd), vec_full_reg_offset(s, a->rn), @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const ftmad_fns[4] = { }; TRANS_FEAT_NONSTREAMING(FTMAD, aa64_sve, gen_gvec_fpst_zzz, ftmad_fns[a->esz], a->rd, a->rn, a->rm, a->imm, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) /* *** SVE Floating Point Accumulating Reduction Group @@ -XXX,XX +XXX,XX @@ static bool trans_FADDA(DisasContext *s, arg_rprr_esz *a) t_pg = tcg_temp_new_ptr(); tcg_gen_addi_ptr(t_rm, tcg_env, vec_full_reg_offset(s, a->rm)); tcg_gen_addi_ptr(t_pg, tcg_env, pred_full_reg_offset(s, a->pg)); - t_fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + t_fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); t_desc = tcg_constant_i32(simd_desc(vsz, vsz, 0)); fns[a->esz - 1](t_val, t_val, t_rm, t_pg, t_fpst, t_desc); @@ -XXX,XX +XXX,XX @@ static void do_fp_scalar(DisasContext *s, int zd, int zn, int pg, bool is_fp16, tcg_gen_addi_ptr(t_zn, tcg_env, vec_full_reg_offset(s, zn)); tcg_gen_addi_ptr(t_pg, tcg_env, pred_full_reg_offset(s, pg)); - status = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_FPCR); + status = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_A64); desc = tcg_constant_i32(simd_desc(vsz, vsz, 0)); fn(t_zd, t_zn, t_pg, scalar, status, desc); } @@ -XXX,XX +XXX,XX @@ static bool do_fp_cmp(DisasContext *s, arg_rprr_esz *a, } if (sve_access_check(s)) { unsigned vsz = vec_full_reg_size(s); - TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); tcg_gen_gvec_4_ptr(pred_full_reg_offset(s, a->rd), vec_full_reg_offset(s, a->rn), vec_full_reg_offset(s, a->rm), @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_4_ptr * const fcadd_fns[] = { }; TRANS_FEAT(FCADD, aa64_sve, gen_gvec_fpst_zzzp, fcadd_fns[a->esz], a->rd, a->rn, a->rm, a->pg, a->rot, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) #define DO_FMLA(NAME, name) \ static gen_helper_gvec_5_ptr * const name##_fns[4] = { \ @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FCADD, aa64_sve, gen_gvec_fpst_zzzp, fcadd_fns[a->esz], }; \ TRANS_FEAT(NAME, aa64_sve, gen_gvec_fpst_zzzzp, name##_fns[a->esz], \ a->rd, a->rn, a->rm, a->ra, a->pg, 0, \ - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) DO_FMLA(FMLA_zpzzz, fmla_zpzzz) DO_FMLA(FMLS_zpzzz, fmls_zpzzz) @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_5_ptr * const fcmla_fns[4] = { }; TRANS_FEAT(FCMLA_zpzzz, aa64_sve, gen_gvec_fpst_zzzzp, fcmla_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->pg, a->rot, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) static gen_helper_gvec_4_ptr * const fcmla_idx_fns[4] = { NULL, gen_helper_gvec_fcmlah_idx, gen_helper_gvec_fcmlas_idx, NULL }; TRANS_FEAT(FCMLA_zzxz, aa64_sve, gen_gvec_fpst_zzzz, fcmla_idx_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->index * 4 + a->rot, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) + a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) /* *** SVE Floating Point Unary Operations Predicated Group */ TRANS_FEAT(FCVT_sh, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvt_sh, a, 0, FPST_FPCR) + gen_helper_sve_fcvt_sh, a, 0, FPST_A64) TRANS_FEAT(FCVT_hs, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvt_hs, a, 0, FPST_FPCR) + gen_helper_sve_fcvt_hs, a, 0, FPST_A64) TRANS_FEAT(BFCVT, aa64_sve_bf16, gen_gvec_fpst_arg_zpz, - gen_helper_sve_bfcvt, a, 0, FPST_FPCR) + gen_helper_sve_bfcvt, a, 0, FPST_A64) TRANS_FEAT(FCVT_dh, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvt_dh, a, 0, FPST_FPCR) + gen_helper_sve_fcvt_dh, a, 0, FPST_A64) TRANS_FEAT(FCVT_hd, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvt_hd, a, 0, FPST_FPCR) + gen_helper_sve_fcvt_hd, a, 0, FPST_A64) TRANS_FEAT(FCVT_ds, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvt_ds, a, 0, FPST_FPCR) + gen_helper_sve_fcvt_ds, a, 0, FPST_A64) TRANS_FEAT(FCVT_sd, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvt_sd, a, 0, FPST_FPCR) + gen_helper_sve_fcvt_sd, a, 0, FPST_A64) TRANS_FEAT(FCVTZS_hh, aa64_sve, gen_gvec_fpst_arg_zpz, gen_helper_sve_fcvtzs_hh, a, 0, FPST_FPCR_F16) @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FCVTZU_hd, aa64_sve, gen_gvec_fpst_arg_zpz, gen_helper_sve_fcvtzu_hd, a, 0, FPST_FPCR_F16) TRANS_FEAT(FCVTZS_ss, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvtzs_ss, a, 0, FPST_FPCR) + gen_helper_sve_fcvtzs_ss, a, 0, FPST_A64) TRANS_FEAT(FCVTZU_ss, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvtzu_ss, a, 0, FPST_FPCR) + gen_helper_sve_fcvtzu_ss, a, 0, FPST_A64) TRANS_FEAT(FCVTZS_sd, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvtzs_sd, a, 0, FPST_FPCR) + gen_helper_sve_fcvtzs_sd, a, 0, FPST_A64) TRANS_FEAT(FCVTZU_sd, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvtzu_sd, a, 0, FPST_FPCR) + gen_helper_sve_fcvtzu_sd, a, 0, FPST_A64) TRANS_FEAT(FCVTZS_ds, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvtzs_ds, a, 0, FPST_FPCR) + gen_helper_sve_fcvtzs_ds, a, 0, FPST_A64) TRANS_FEAT(FCVTZU_ds, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvtzu_ds, a, 0, FPST_FPCR) + gen_helper_sve_fcvtzu_ds, a, 0, FPST_A64) TRANS_FEAT(FCVTZS_dd, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvtzs_dd, a, 0, FPST_FPCR) + gen_helper_sve_fcvtzs_dd, a, 0, FPST_A64) TRANS_FEAT(FCVTZU_dd, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvtzu_dd, a, 0, FPST_FPCR) + gen_helper_sve_fcvtzu_dd, a, 0, FPST_A64) static gen_helper_gvec_3_ptr * const frint_fns[] = { NULL, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const frint_fns[] = { gen_helper_sve_frint_d }; TRANS_FEAT(FRINTI, aa64_sve, gen_gvec_fpst_arg_zpz, frint_fns[a->esz], - a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) + a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) static gen_helper_gvec_3_ptr * const frintx_fns[] = { NULL, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const frintx_fns[] = { gen_helper_sve_frintx_d }; TRANS_FEAT(FRINTX, aa64_sve, gen_gvec_fpst_arg_zpz, frintx_fns[a->esz], - a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); static bool do_frint_mode(DisasContext *s, arg_rpr_esz *a, ARMFPRounding mode, gen_helper_gvec_3_ptr *fn) @@ -XXX,XX +XXX,XX @@ static bool do_frint_mode(DisasContext *s, arg_rpr_esz *a, } vsz = vec_full_reg_size(s); - status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR); + status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); tmode = gen_set_rmode(mode, status); tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const frecpx_fns[] = { gen_helper_sve_frecpx_s, gen_helper_sve_frecpx_d, }; TRANS_FEAT(FRECPX, aa64_sve, gen_gvec_fpst_arg_zpz, frecpx_fns[a->esz], - a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) + a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) static gen_helper_gvec_3_ptr * const fsqrt_fns[] = { NULL, gen_helper_sve_fsqrt_h, gen_helper_sve_fsqrt_s, gen_helper_sve_fsqrt_d, }; TRANS_FEAT(FSQRT, aa64_sve, gen_gvec_fpst_arg_zpz, fsqrt_fns[a->esz], - a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) + a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) TRANS_FEAT(SCVTF_hh, aa64_sve, gen_gvec_fpst_arg_zpz, gen_helper_sve_scvt_hh, a, 0, FPST_FPCR_F16) @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SCVTF_dh, aa64_sve, gen_gvec_fpst_arg_zpz, gen_helper_sve_scvt_dh, a, 0, FPST_FPCR_F16) TRANS_FEAT(SCVTF_ss, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_scvt_ss, a, 0, FPST_FPCR) + gen_helper_sve_scvt_ss, a, 0, FPST_A64) TRANS_FEAT(SCVTF_ds, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_scvt_ds, a, 0, FPST_FPCR) + gen_helper_sve_scvt_ds, a, 0, FPST_A64) TRANS_FEAT(SCVTF_sd, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_scvt_sd, a, 0, FPST_FPCR) + gen_helper_sve_scvt_sd, a, 0, FPST_A64) TRANS_FEAT(SCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_scvt_dd, a, 0, FPST_FPCR) + gen_helper_sve_scvt_dd, a, 0, FPST_A64) TRANS_FEAT(UCVTF_hh, aa64_sve, gen_gvec_fpst_arg_zpz, gen_helper_sve_ucvt_hh, a, 0, FPST_FPCR_F16) @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(UCVTF_dh, aa64_sve, gen_gvec_fpst_arg_zpz, gen_helper_sve_ucvt_dh, a, 0, FPST_FPCR_F16) TRANS_FEAT(UCVTF_ss, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_ucvt_ss, a, 0, FPST_FPCR) + gen_helper_sve_ucvt_ss, a, 0, FPST_A64) TRANS_FEAT(UCVTF_ds, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_ucvt_ds, a, 0, FPST_FPCR) + gen_helper_sve_ucvt_ds, a, 0, FPST_A64) TRANS_FEAT(UCVTF_sd, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_ucvt_sd, a, 0, FPST_FPCR) + gen_helper_sve_ucvt_sd, a, 0, FPST_A64) TRANS_FEAT(UCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_ucvt_dd, a, 0, FPST_FPCR) + gen_helper_sve_ucvt_dd, a, 0, FPST_A64) /* *** SVE Memory - 32-bit Gather and Unsized Contiguous Group @@ -XXX,XX +XXX,XX @@ DO_ZPZZ_FP(FMINP, aa64_sve2, sve2_fminp_zpzz) TRANS_FEAT_NONSTREAMING(FMMLA_s, aa64_sve_f32mm, gen_gvec_fpst_zzzz, gen_helper_fmmla_s, a->rd, a->rn, a->rm, a->ra, - 0, FPST_FPCR) + 0, FPST_A64) TRANS_FEAT_NONSTREAMING(FMMLA_d, aa64_sve_f64mm, gen_gvec_fpst_zzzz, gen_helper_fmmla_d, a->rd, a->rn, a->rm, a->ra, - 0, FPST_FPCR) + 0, FPST_A64) static gen_helper_gvec_4 * const sqdmlal_zzzw_fns[] = { NULL, gen_helper_sve2_sqdmlal_zzzw_h, @@ -XXX,XX +XXX,XX @@ TRANS_FEAT_NONSTREAMING(RAX1, aa64_sve2_sha3, gen_gvec_fn_arg_zzz, gen_gvec_rax1, a) TRANS_FEAT(FCVTNT_sh, aa64_sve2, gen_gvec_fpst_arg_zpz, - gen_helper_sve2_fcvtnt_sh, a, 0, FPST_FPCR) + gen_helper_sve2_fcvtnt_sh, a, 0, FPST_A64) TRANS_FEAT(FCVTNT_ds, aa64_sve2, gen_gvec_fpst_arg_zpz, - gen_helper_sve2_fcvtnt_ds, a, 0, FPST_FPCR) + gen_helper_sve2_fcvtnt_ds, a, 0, FPST_A64) TRANS_FEAT(BFCVTNT, aa64_sve_bf16, gen_gvec_fpst_arg_zpz, - gen_helper_sve_bfcvtnt, a, 0, FPST_FPCR) + gen_helper_sve_bfcvtnt, a, 0, FPST_A64) TRANS_FEAT(FCVTLT_hs, aa64_sve2, gen_gvec_fpst_arg_zpz, - gen_helper_sve2_fcvtlt_hs, a, 0, FPST_FPCR) + gen_helper_sve2_fcvtlt_hs, a, 0, FPST_A64) TRANS_FEAT(FCVTLT_sd, aa64_sve2, gen_gvec_fpst_arg_zpz, - gen_helper_sve2_fcvtlt_sd, a, 0, FPST_FPCR) + gen_helper_sve2_fcvtlt_sd, a, 0, FPST_A64) TRANS_FEAT(FCVTX_ds, aa64_sve2, do_frint_mode, a, FPROUNDING_ODD, gen_helper_sve_fcvt_ds) @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const flogb_fns[] = { gen_helper_flogb_s, gen_helper_flogb_d }; TRANS_FEAT(FLOGB, aa64_sve2, gen_gvec_fpst_arg_zpz, flogb_fns[a->esz], - a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_FPCR) + a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) static bool do_FMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sub, bool sel) { @@ -XXX,XX +XXX,XX @@ TRANS_FEAT_NONSTREAMING(BFMMLA, aa64_sve_bf16, gen_gvec_env_arg_zzzz, static bool do_BFMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel) { return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlal, - a->rd, a->rn, a->rm, a->ra, sel, FPST_FPCR); + a->rd, a->rn, a->rm, a->ra, sel, FPST_A64); } TRANS_FEAT(BFMLALB_zzzw, aa64_sve_bf16, do_BFMLAL_zzzw, a, false) @@ -XXX,XX +XXX,XX @@ static bool do_BFMLAL_zzxw(DisasContext *s, arg_rrxr_esz *a, bool sel) { return gen_gvec_fpst_zzzz(s, gen_helper_gvec_bfmlal_idx, a->rd, a->rn, a->rm, a->ra, - (a->index << 1) | sel, FPST_FPCR); + (a->index << 1) | sel, FPST_A64); } TRANS_FEAT(BFMLALB_zzxw, aa64_sve_bf16, do_BFMLAL_zzxw, a, false) -- 2.34.1 Now we have moved all the uses of vfp.fp_status and FPST_FPCR to either the A32 or A64 fields, we can remove these. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-13-peter.maydell@linaro.org --- target/arm/cpu.h | 2 -- target/arm/tcg/translate.h | 6 ------ target/arm/cpu.c | 1 - target/arm/vfp_helper.c | 8 +------- 4 files changed, 1 insertion(+), 16 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUArchState { /* There are a number of distinct float control structures: * - * fp_status: is the "normal" fp status. * fp_status_a32: is the "normal" fp status for AArch32 insns * fp_status_a64: is the "normal" fp status for AArch64 insns * fp_status_fp16: used for half-precision calculations @@ -XXX,XX +XXX,XX @@ typedef struct CPUArchState { * only thing which needs to read the exception flags being * an explicit FPSCR read. */ - float_status fp_status; float_status fp_status_a32; float_status fp_status_a64; float_status fp_status_f16; diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ static inline CPUARMTBFlags arm_tbflags_from_tb(const TranslationBlock *tb) * Enum for argument to fpstatus_ptr(). */ typedef enum ARMFPStatusFlavour { - FPST_FPCR, FPST_A32, FPST_A64, FPST_FPCR_F16, @@ -XXX,XX +XXX,XX @@ typedef enum ARMFPStatusFlavour { * been set up to point to the requested field in the CPU state struct. * The options are: * - * FPST_FPCR - * for non-FP16 operations controlled by the FPCR * FPST_A32 * for AArch32 non-FP16 operations controlled by the FPCR * FPST_A64 @@ -XXX,XX +XXX,XX @@ static inline TCGv_ptr fpstatus_ptr(ARMFPStatusFlavour flavour) int offset; switch (flavour) { - case FPST_FPCR: - offset = offsetof(CPUARMState, vfp.fp_status); - break; case FPST_A32: offset = offsetof(CPUARMState, vfp.fp_status_a32); break; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset_hold(Object *obj, ResetType type) set_flush_inputs_to_zero(1, &env->vfp.standard_fp_status); set_default_nan_mode(1, &env->vfp.standard_fp_status); set_default_nan_mode(1, &env->vfp.standard_fp_status_f16); - arm_set_default_fp_behaviours(&env->vfp.fp_status); arm_set_default_fp_behaviours(&env->vfp.fp_status_a32); arm_set_default_fp_behaviours(&env->vfp.fp_status_a64); arm_set_default_fp_behaviours(&env->vfp.standard_fp_status); diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t vfp_exceptbits_from_host(int host_bits) static uint32_t vfp_get_fpsr_from_host(CPUARMState *env) { - uint32_t i; + uint32_t i = 0; - i = get_float_exception_flags(&env->vfp.fp_status); i |= get_float_exception_flags(&env->vfp.fp_status_a32); i |= get_float_exception_flags(&env->vfp.fp_status_a64); i |= get_float_exception_flags(&env->vfp.standard_fp_status); @@ -XXX,XX +XXX,XX @@ static void vfp_clear_float_status_exc_flags(CPUARMState *env) * values. The caller should have arranged for env->vfp.fpsr to * be the architecturally up-to-date exception flag information first. */ - set_float_exception_flags(0, &env->vfp.fp_status); set_float_exception_flags(0, &env->vfp.fp_status_a32); set_float_exception_flags(0, &env->vfp.fp_status_a64); set_float_exception_flags(0, &env->vfp.fp_status_f16); @@ -XXX,XX +XXX,XX @@ static void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) i = float_round_to_zero; break; } - set_float_rounding_mode(i, &env->vfp.fp_status); set_float_rounding_mode(i, &env->vfp.fp_status_a32); set_float_rounding_mode(i, &env->vfp.fp_status_a64); set_float_rounding_mode(i, &env->vfp.fp_status_f16); @@ -XXX,XX +XXX,XX @@ static void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) } if (changed & FPCR_FZ) { bool ftz_enabled = val & FPCR_FZ; - set_flush_to_zero(ftz_enabled, &env->vfp.fp_status); - set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status); set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_a32); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status_a32); set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_a64); @@ -XXX,XX +XXX,XX @@ static void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) } if (changed & FPCR_DN) { bool dnan_enabled = val & FPCR_DN; - set_default_nan_mode(dnan_enabled, &env->vfp.fp_status); set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_a32); set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_a64); set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_f16); -- 2.34.1 As the first part of splitting the existing fp_status_f16 into separate float_status fields for AArch32 and AArch64 (so that we can make FEAT_AFP control bits apply only for AArch64), define the two new fp_status_f16_a32 and fp_status_f16_a64 fields, but don't use them yet. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-14-peter.maydell@linaro.org --- target/arm/cpu.h | 4 ++++ target/arm/tcg/translate.h | 12 ++++++++++++ target/arm/cpu.c | 2 ++ target/arm/vfp_helper.c | 14 ++++++++++++++ 4 files changed, 32 insertions(+) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUArchState { * fp_status_a32: is the "normal" fp status for AArch32 insns * fp_status_a64: is the "normal" fp status for AArch64 insns * fp_status_fp16: used for half-precision calculations + * fp_status_fp16_a32: used for AArch32 half-precision calculations + * fp_status_fp16_a64: used for AArch64 half-precision calculations * standard_fp_status : the ARM "Standard FPSCR Value" * standard_fp_status_fp16 : used for half-precision * calculations with the ARM "Standard FPSCR Value" @@ -XXX,XX +XXX,XX @@ typedef struct CPUArchState { float_status fp_status_a32; float_status fp_status_a64; float_status fp_status_f16; + float_status fp_status_f16_a32; + float_status fp_status_f16_a64; float_status standard_fp_status; float_status standard_fp_status_f16; diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ typedef enum ARMFPStatusFlavour { FPST_A32, FPST_A64, FPST_FPCR_F16, + FPST_A32_F16, + FPST_A64_F16, FPST_STD, FPST_STD_F16, } ARMFPStatusFlavour; @@ -XXX,XX +XXX,XX @@ typedef enum ARMFPStatusFlavour { * for AArch64 non-FP16 operations controlled by the FPCR * FPST_FPCR_F16 * for operations controlled by the FPCR where FPCR.FZ16 is to be used + * FPST_A32_F16 + * for AArch32 operations controlled by the FPCR where FPCR.FZ16 is to be used + * FPST_A64_F16 + * for AArch64 operations controlled by the FPCR where FPCR.FZ16 is to be used * FPST_STD * for A32/T32 Neon operations using the "standard FPSCR value" * FPST_STD_F16 @@ -XXX,XX +XXX,XX @@ static inline TCGv_ptr fpstatus_ptr(ARMFPStatusFlavour flavour) case FPST_FPCR_F16: offset = offsetof(CPUARMState, vfp.fp_status_f16); break; + case FPST_A32_F16: + offset = offsetof(CPUARMState, vfp.fp_status_f16_a32); + break; + case FPST_A64_F16: + offset = offsetof(CPUARMState, vfp.fp_status_f16_a64); + break; case FPST_STD: offset = offsetof(CPUARMState, vfp.standard_fp_status); break; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset_hold(Object *obj, ResetType type) arm_set_default_fp_behaviours(&env->vfp.fp_status_a64); arm_set_default_fp_behaviours(&env->vfp.standard_fp_status); arm_set_default_fp_behaviours(&env->vfp.fp_status_f16); + arm_set_default_fp_behaviours(&env->vfp.fp_status_f16_a32); + arm_set_default_fp_behaviours(&env->vfp.fp_status_f16_a64); arm_set_default_fp_behaviours(&env->vfp.standard_fp_status_f16); #ifndef CONFIG_USER_ONLY diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ static uint32_t vfp_get_fpsr_from_host(CPUARMState *env) /* FZ16 does not generate an input denormal exception. */ i |= (get_float_exception_flags(&env->vfp.fp_status_f16) & ~float_flag_input_denormal); + i |= (get_float_exception_flags(&env->vfp.fp_status_f16_a32) + & ~float_flag_input_denormal); + i |= (get_float_exception_flags(&env->vfp.fp_status_f16_a64) + & ~float_flag_input_denormal); i |= (get_float_exception_flags(&env->vfp.standard_fp_status_f16) & ~float_flag_input_denormal); return vfp_exceptbits_from_host(i); @@ -XXX,XX +XXX,XX @@ static void vfp_clear_float_status_exc_flags(CPUARMState *env) set_float_exception_flags(0, &env->vfp.fp_status_a32); set_float_exception_flags(0, &env->vfp.fp_status_a64); set_float_exception_flags(0, &env->vfp.fp_status_f16); + set_float_exception_flags(0, &env->vfp.fp_status_f16_a32); + set_float_exception_flags(0, &env->vfp.fp_status_f16_a64); set_float_exception_flags(0, &env->vfp.standard_fp_status); set_float_exception_flags(0, &env->vfp.standard_fp_status_f16); } @@ -XXX,XX +XXX,XX @@ static void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) set_float_rounding_mode(i, &env->vfp.fp_status_a32); set_float_rounding_mode(i, &env->vfp.fp_status_a64); set_float_rounding_mode(i, &env->vfp.fp_status_f16); + set_float_rounding_mode(i, &env->vfp.fp_status_f16_a32); + set_float_rounding_mode(i, &env->vfp.fp_status_f16_a64); } if (changed & FPCR_FZ16) { bool ftz_enabled = val & FPCR_FZ16; set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_f16); + set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_f16_a32); + set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_f16_a64); set_flush_to_zero(ftz_enabled, &env->vfp.standard_fp_status_f16); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status_f16); + set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status_f16_a32); + set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status_f16_a64); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.standard_fp_status_f16); } if (changed & FPCR_FZ) { @@ -XXX,XX +XXX,XX @@ static void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_a32); set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_a64); set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_f16); + set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_f16_a32); + set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_f16_a64); } } -- 2.34.1 We directly use fp_status_f16 in a handful of helpers that are AArch32-specific; switch to fp_status_f16_a32 for these. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-15-peter.maydell@linaro.org --- target/arm/tcg/vec_helper.c | 4 ++-- target/arm/vfp_helper.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fmlal_a32)(void *vd, void *vn, void *vm, CPUARMState *env, uint32_t desc) { do_fmlal(vd, vn, vm, &env->vfp.standard_fp_status, desc, - get_flush_inputs_to_zero(&env->vfp.fp_status_f16)); + get_flush_inputs_to_zero(&env->vfp.fp_status_f16_a32)); } void HELPER(gvec_fmlal_a64)(void *vd, void *vn, void *vm, @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fmlal_idx_a32)(void *vd, void *vn, void *vm, CPUARMState *env, uint32_t desc) { do_fmlal_idx(vd, vn, vm, &env->vfp.standard_fp_status, desc, - get_flush_inputs_to_zero(&env->vfp.fp_status_f16)); + get_flush_inputs_to_zero(&env->vfp.fp_status_f16_a32)); } void HELPER(gvec_fmlal_idx_a64)(void *vd, void *vn, void *vm, diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ void VFP_HELPER(cmpe, P)(ARGTYPE a, ARGTYPE b, CPUARMState *env) \ softfloat_to_vfp_compare(env, \ FLOATTYPE ## _compare(a, b, &env->vfp.FPST)); \ } -DO_VFP_cmp(h, float16, dh_ctype_f16, fp_status_f16) +DO_VFP_cmp(h, float16, dh_ctype_f16, fp_status_f16_a32) DO_VFP_cmp(s, float32, float32, fp_status_a32) DO_VFP_cmp(d, float64, float64, fp_status_a32) #undef DO_VFP_cmp -- 2.34.1 We directly use fp_status_f16 in a handful of helpers that are AArch64-specific; switch to fp_status_f16_a64 for these. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-16-peter.maydell@linaro.org --- target/arm/tcg/sme_helper.c | 4 ++-- target/arm/tcg/vec_helper.c | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) diff --git a/target/arm/tcg/sme_helper.c b/target/arm/tcg/sme_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sme_helper.c +++ b/target/arm/tcg/sme_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(sme_fmopa_h)(void *vza, void *vzn, void *vzm, void *vpn, float_status fpst_odd, fpst_std, fpst_f16; /* - * Make copies of fp_status and fp_status_f16, because this operation + * Make copies of the fp status fields we use, because this operation * does not update the cumulative fp exception status. It also * produces default NaNs. We also need a second copy of fp_status with * round-to-odd -- see above. */ - fpst_f16 = env->vfp.fp_status_f16; + fpst_f16 = env->vfp.fp_status_f16_a64; fpst_std = env->vfp.fp_status_a64; set_default_nan_mode(true, &fpst_std); set_default_nan_mode(true, &fpst_f16); diff --git a/target/arm/tcg/vec_helper.c b/target/arm/tcg/vec_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/vec_helper.c +++ b/target/arm/tcg/vec_helper.c @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fmlal_a64)(void *vd, void *vn, void *vm, CPUARMState *env, uint32_t desc) { do_fmlal(vd, vn, vm, &env->vfp.fp_status_a64, desc, - get_flush_inputs_to_zero(&env->vfp.fp_status_f16)); + get_flush_inputs_to_zero(&env->vfp.fp_status_f16_a64)); } void HELPER(sve2_fmlal_zzzw_s)(void *vd, void *vn, void *vm, void *va, @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_fmlal_zzzw_s)(void *vd, void *vn, void *vm, void *va, uint16_t negn = extract32(desc, SIMD_DATA_SHIFT, 1) << 15; intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16); float_status *status = &env->vfp.fp_status_a64; - bool fz16 = get_flush_inputs_to_zero(&env->vfp.fp_status_f16); + bool fz16 = get_flush_inputs_to_zero(&env->vfp.fp_status_f16_a64); for (i = 0; i < oprsz; i += sizeof(float32)) { float16 nn_16 = *(float16 *)(vn + H1_2(i + sel)) ^ negn; @@ -XXX,XX +XXX,XX @@ void HELPER(gvec_fmlal_idx_a64)(void *vd, void *vn, void *vm, CPUARMState *env, uint32_t desc) { do_fmlal_idx(vd, vn, vm, &env->vfp.fp_status_a64, desc, - get_flush_inputs_to_zero(&env->vfp.fp_status_f16)); + get_flush_inputs_to_zero(&env->vfp.fp_status_f16_a64)); } void HELPER(sve2_fmlal_zzxw_s)(void *vd, void *vn, void *vm, void *va, @@ -XXX,XX +XXX,XX @@ void HELPER(sve2_fmlal_zzxw_s)(void *vd, void *vn, void *vm, void *va, intptr_t sel = extract32(desc, SIMD_DATA_SHIFT + 1, 1) * sizeof(float16); intptr_t idx = extract32(desc, SIMD_DATA_SHIFT + 2, 3) * sizeof(float16); float_status *status = &env->vfp.fp_status_a64; - bool fz16 = get_flush_inputs_to_zero(&env->vfp.fp_status_f16); + bool fz16 = get_flush_inputs_to_zero(&env->vfp.fp_status_f16_a64); for (i = 0; i < oprsz; i += 16) { float16 mm_16 = *(float16 *)(vm + i + idx); -- 2.34.1 In the A32 decoder, use FPST_A32_F16 rather than FPST_FPCR_F16. By doing an automated conversion of the whole file we avoid possibly using more than one fpst value in a set_rmode/op/restore_rmode sequence. Patch created with perl -p -i -e 's/FPST_FPCR_F16(?!_)/FPST_A32_F16/g' target/arm/tcg/translate-vfp.c Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-17-peter.maydell@linaro.org --- target/arm/tcg/translate-vfp.c | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/target/arm/tcg/translate-vfp.c b/target/arm/tcg/translate-vfp.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-vfp.c +++ b/target/arm/tcg/translate-vfp.c @@ -XXX,XX +XXX,XX @@ static bool trans_VRINT(DisasContext *s, arg_VRINT *a) } if (sz == 1) { - fpst = fpstatus_ptr(FPST_FPCR_F16); + fpst = fpstatus_ptr(FPST_A32_F16); } else { fpst = fpstatus_ptr(FPST_A32); } @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT(DisasContext *s, arg_VCVT *a) } if (sz == 1) { - fpst = fpstatus_ptr(FPST_FPCR_F16); + fpst = fpstatus_ptr(FPST_A32_F16); } else { fpst = fpstatus_ptr(FPST_A32); } @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_hp(DisasContext *s, VFPGen3OpSPFn *fn, /* * Do a half-precision operation. Functionally this is * the same as do_vfp_3op_sp(), except: - * - it uses the FPST_FPCR_F16 + * - it uses the FPST_A32_F16 * - it doesn't need the VFP vector handling (fp16 is a * v8 feature, and in v8 VFP vectors don't exist) * - it does the aa32_fp16_arith feature test @@ -XXX,XX +XXX,XX @@ static bool do_vfp_3op_hp(DisasContext *s, VFPGen3OpSPFn *fn, f0 = tcg_temp_new_i32(); f1 = tcg_temp_new_i32(); fd = tcg_temp_new_i32(); - fpst = fpstatus_ptr(FPST_FPCR_F16); + fpst = fpstatus_ptr(FPST_A32_F16); vfp_load_reg16(f0, vn); vfp_load_reg16(f1, vm); @@ -XXX,XX +XXX,XX @@ static bool do_vfm_hp(DisasContext *s, arg_VFMA_sp *a, bool neg_n, bool neg_d) /* VFNMA, VFNMS */ gen_vfp_negh(vd, vd); } - fpst = fpstatus_ptr(FPST_FPCR_F16); + fpst = fpstatus_ptr(FPST_A32_F16); gen_helper_vfp_muladdh(vd, vn, vm, vd, fpst); vfp_store_reg32(vd, a->vd); return true; @@ -XXX,XX +XXX,XX @@ DO_VFP_2OP(VNEG, dp, gen_vfp_negd, aa32_fpdp_v2) static void gen_VSQRT_hp(TCGv_i32 vd, TCGv_i32 vm) { - gen_helper_vfp_sqrth(vd, vm, fpstatus_ptr(FPST_FPCR_F16)); + gen_helper_vfp_sqrth(vd, vm, fpstatus_ptr(FPST_A32_F16)); } static void gen_VSQRT_sp(TCGv_i32 vd, TCGv_i32 vm) @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTR_hp(DisasContext *s, arg_VRINTR_sp *a) tmp = tcg_temp_new_i32(); vfp_load_reg16(tmp, a->vm); - fpst = fpstatus_ptr(FPST_FPCR_F16); + fpst = fpstatus_ptr(FPST_A32_F16); gen_helper_rinth(tmp, tmp, fpst); vfp_store_reg32(tmp, a->vd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTZ_hp(DisasContext *s, arg_VRINTZ_sp *a) tmp = tcg_temp_new_i32(); vfp_load_reg16(tmp, a->vm); - fpst = fpstatus_ptr(FPST_FPCR_F16); + fpst = fpstatus_ptr(FPST_A32_F16); tcg_rmode = gen_set_rmode(FPROUNDING_ZERO, fpst); gen_helper_rinth(tmp, tmp, fpst); gen_restore_rmode(tcg_rmode, fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VRINTX_hp(DisasContext *s, arg_VRINTX_sp *a) tmp = tcg_temp_new_i32(); vfp_load_reg16(tmp, a->vm); - fpst = fpstatus_ptr(FPST_FPCR_F16); + fpst = fpstatus_ptr(FPST_A32_F16); gen_helper_rinth_exact(tmp, tmp, fpst); vfp_store_reg32(tmp, a->vd); return true; @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_int_hp(DisasContext *s, arg_VCVT_int_sp *a) vm = tcg_temp_new_i32(); vfp_load_reg32(vm, a->vm); - fpst = fpstatus_ptr(FPST_FPCR_F16); + fpst = fpstatus_ptr(FPST_A32_F16); if (a->s) { /* i32 -> f16 */ gen_helper_vfp_sitoh(vm, vm, fpst); @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_fix_hp(DisasContext *s, arg_VCVT_fix_sp *a) vd = tcg_temp_new_i32(); vfp_load_reg32(vd, a->vd); - fpst = fpstatus_ptr(FPST_FPCR_F16); + fpst = fpstatus_ptr(FPST_A32_F16); shift = tcg_constant_i32(frac_bits); /* Switch on op:U:sx bits */ @@ -XXX,XX +XXX,XX @@ static bool trans_VCVT_hp_int(DisasContext *s, arg_VCVT_sp_int *a) return true; } - fpst = fpstatus_ptr(FPST_FPCR_F16); + fpst = fpstatus_ptr(FPST_A32_F16); vm = tcg_temp_new_i32(); vfp_load_reg16(vm, a->vm); -- 2.34.1 In the A32 decoder, use FPST_A64_F16 rather than FPST_FPCR_F16. By doing an automated conversion of the whole file we avoid possibly using more than one fpst value in a set_rmode/op/restore_rmode sequence. Patch created with perl -p -i -e 's/FPST_FPCR_F16(?!_)/FPST_A64_F16/g' target/arm/tcg/translate-{a64,sve,sme}.c Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-18-peter.maydell@linaro.org --- target/arm/tcg/translate-a64.c | 32 ++++++++--------- target/arm/tcg/translate-sve.c | 66 +++++++++++++++++----------------- 2 files changed, 49 insertions(+), 49 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static void gen_gvec_op3_fpst(DisasContext *s, bool is_q, int rd, int rn, int rm, bool is_fp16, int data, gen_helper_gvec_3_ptr *fn) { - TCGv_ptr fpst = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_A64); + TCGv_ptr fpst = fpstatus_ptr(is_fp16 ? FPST_A64_F16 : FPST_A64); tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn), vec_full_reg_offset(s, rm), fpst, @@ -XXX,XX +XXX,XX @@ static void gen_gvec_op4_fpst(DisasContext *s, bool is_q, int rd, int rn, int rm, int ra, bool is_fp16, int data, gen_helper_gvec_4_ptr *fn) { - TCGv_ptr fpst = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_A64); + TCGv_ptr fpst = fpstatus_ptr(is_fp16 ? FPST_A64_F16 : FPST_A64); tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn), vec_full_reg_offset(s, rm), @@ -XXX,XX +XXX,XX @@ static bool do_fp3_scalar(DisasContext *s, arg_rrr_e *a, const FPScalar *f) if (fp_access_check(s)) { TCGv_i32 t0 = read_fp_hreg(s, a->rn); TCGv_i32 t1 = read_fp_hreg(s, a->rm); - f->gen_h(t0, t0, t1, fpstatus_ptr(FPST_FPCR_F16)); + f->gen_h(t0, t0, t1, fpstatus_ptr(FPST_A64_F16)); write_fp_sreg(s, a->rd, t0); } break; @@ -XXX,XX +XXX,XX @@ static bool do_fcmp0_s(DisasContext *s, arg_rr_e *a, TCGv_i32 t0 = read_fp_hreg(s, a->rn); TCGv_i32 t1 = tcg_constant_i32(0); if (swap) { - f->gen_h(t0, t1, t0, fpstatus_ptr(FPST_FPCR_F16)); + f->gen_h(t0, t1, t0, fpstatus_ptr(FPST_A64_F16)); } else { - f->gen_h(t0, t0, t1, fpstatus_ptr(FPST_FPCR_F16)); + f->gen_h(t0, t0, t1, fpstatus_ptr(FPST_A64_F16)); } write_fp_sreg(s, a->rd, t0); } @@ -XXX,XX +XXX,XX @@ static bool do_fp3_scalar_idx(DisasContext *s, arg_rrx_e *a, const FPScalar *f) TCGv_i32 t1 = tcg_temp_new_i32(); read_vec_element_i32(s, t1, a->rm, a->idx, MO_16); - f->gen_h(t0, t0, t1, fpstatus_ptr(FPST_FPCR_F16)); + f->gen_h(t0, t0, t1, fpstatus_ptr(FPST_A64_F16)); write_fp_sreg(s, a->rd, t0); } break; @@ -XXX,XX +XXX,XX @@ static bool do_fmla_scalar_idx(DisasContext *s, arg_rrx_e *a, bool neg) gen_vfp_negh(t1, t1); } gen_helper_advsimd_muladdh(t0, t1, t2, t0, - fpstatus_ptr(FPST_FPCR_F16)); + fpstatus_ptr(FPST_A64_F16)); write_fp_sreg(s, a->rd, t0); } break; @@ -XXX,XX +XXX,XX @@ static bool do_fp3_scalar_pair(DisasContext *s, arg_rr_e *a, const FPScalar *f) read_vec_element_i32(s, t0, a->rn, 0, MO_16); read_vec_element_i32(s, t1, a->rn, 1, MO_16); - f->gen_h(t0, t0, t1, fpstatus_ptr(FPST_FPCR_F16)); + f->gen_h(t0, t0, t1, fpstatus_ptr(FPST_A64_F16)); write_fp_sreg(s, a->rd, t0); } break; @@ -XXX,XX +XXX,XX @@ static bool do_fmadd(DisasContext *s, arg_rrrr_e *a, bool neg_a, bool neg_n) if (neg_n) { gen_vfp_negh(tn, tn); } - fpst = fpstatus_ptr(FPST_FPCR_F16); + fpst = fpstatus_ptr(FPST_A64_F16); gen_helper_advsimd_muladdh(ta, tn, tm, ta, fpst); write_fp_sreg(s, a->rd, ta); } @@ -XXX,XX +XXX,XX @@ static bool do_fp_reduction(DisasContext *s, arg_qrr_e *a, if (fp_access_check(s)) { MemOp esz = a->esz; int elts = (a->q ? 16 : 8) >> esz; - TCGv_ptr fpst = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + TCGv_ptr fpst = fpstatus_ptr(esz == MO_16 ? FPST_A64_F16 : FPST_A64); TCGv_i32 res = do_reduction_op(s, a->rn, esz, 0, elts, fpst, fn); write_fp_sreg(s, a->rd, res); } @@ -XXX,XX +XXX,XX @@ static void handle_fp_compare(DisasContext *s, int size, bool cmp_with_zero, bool signal_all_nans) { TCGv_i64 tcg_flags = tcg_temp_new_i64(); - TCGv_ptr fpst = fpstatus_ptr(size == MO_16 ? FPST_FPCR_F16 : FPST_A64); + TCGv_ptr fpst = fpstatus_ptr(size == MO_16 ? FPST_A64_F16 : FPST_A64); if (size == MO_64) { TCGv_i64 tcg_vn, tcg_vm; @@ -XXX,XX +XXX,XX @@ static bool do_fp1_scalar(DisasContext *s, arg_rr_e *a, return check == 0; } - fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); if (rmode >= 0) { tcg_rmode = gen_set_rmode(rmode, fpst); } @@ -XXX,XX +XXX,XX @@ static bool do_cvtf_scalar(DisasContext *s, MemOp esz, int rd, int shift, TCGv_i32 tcg_shift, tcg_single; TCGv_i64 tcg_double; - tcg_fpstatus = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + tcg_fpstatus = fpstatus_ptr(esz == MO_16 ? FPST_A64_F16 : FPST_A64); tcg_shift = tcg_constant_i32(shift); switch (esz) { @@ -XXX,XX +XXX,XX @@ static void do_fcvt_scalar(DisasContext *s, MemOp out, MemOp esz, TCGv_ptr tcg_fpstatus; TCGv_i32 tcg_shift, tcg_rmode, tcg_single; - tcg_fpstatus = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + tcg_fpstatus = fpstatus_ptr(esz == MO_16 ? FPST_A64_F16 : FPST_A64); tcg_shift = tcg_constant_i32(shift); tcg_rmode = gen_set_rmode(rmode, tcg_fpstatus); @@ -XXX,XX +XXX,XX @@ static bool do_fp1_vector(DisasContext *s, arg_qrr_e *a, return check == 0; } - fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); if (rmode >= 0) { tcg_rmode = gen_set_rmode(rmode, fpst); } @@ -XXX,XX +XXX,XX @@ static bool do_gvec_op2_fpst(DisasContext *s, MemOp esz, bool is_q, return check == 0; } - fpst = fpstatus_ptr(esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + fpst = fpstatus_ptr(esz == MO_16 ? FPST_A64_F16 : FPST_A64); tcg_gen_gvec_2_ptr(vec_full_reg_offset(s, rd), vec_full_reg_offset(s, rn), fpst, is_q ? 16 : 8, vec_full_reg_size(s), diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-sve.c +++ b/target/arm/tcg/translate-sve.c @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_fpst_arg_zz(DisasContext *s, gen_helper_gvec_2_ptr *fn, arg_rr_esz *a, int data) { return gen_gvec_fpst_zz(s, fn, a->rd, a->rn, data, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); } /* Invoke an out-of-line helper on 3 Zregs. */ @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_fpst_arg_zzz(DisasContext *s, gen_helper_gvec_3_ptr *fn, arg_rrr_esz *a, int data) { return gen_gvec_fpst_zzz(s, fn, a->rd, a->rn, a->rm, data, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); } /* Invoke an out-of-line helper on 4 Zregs. */ @@ -XXX,XX +XXX,XX @@ static bool gen_gvec_fpst_arg_zpzz(DisasContext *s, gen_helper_gvec_4_ptr *fn, arg_rprr_esz *a) { return gen_gvec_fpst_zzzp(s, fn, a->rd, a->rn, a->rm, a->pg, 0, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); } /* Invoke a vector expander on two Zregs and an immediate. */ @@ -XXX,XX +XXX,XX @@ static bool do_FMLA_zzxz(DisasContext *s, arg_rrxr_esz *a, bool sub) }; return gen_gvec_fpst_zzzz(s, fns[a->esz], a->rd, a->rn, a->rm, a->ra, (a->index << 1) | sub, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); } TRANS_FEAT(FMLA_zzxz, aa64_sve, do_FMLA_zzxz, a, false) @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const fmul_idx_fns[4] = { }; TRANS_FEAT(FMUL_zzx, aa64_sve, gen_gvec_fpst_zzz, fmul_idx_fns[a->esz], a->rd, a->rn, a->rm, a->index, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) /* *** SVE Floating Point Fast Reduction Group @@ -XXX,XX +XXX,XX @@ static bool do_reduce(DisasContext *s, arg_rpr_esz *a, tcg_gen_addi_ptr(t_zn, tcg_env, vec_full_reg_offset(s, a->rn)); tcg_gen_addi_ptr(t_pg, tcg_env, pred_full_reg_offset(s, a->pg)); - status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + status = fpstatus_ptr(a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); fn(temp, t_zn, t_pg, status, t_desc); @@ -XXX,XX +XXX,XX @@ static bool do_ppz_fp(DisasContext *s, arg_rpr_esz *a, if (sve_access_check(s)) { unsigned vsz = vec_full_reg_size(s); TCGv_ptr status = - fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + fpstatus_ptr(a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); tcg_gen_gvec_3_ptr(pred_full_reg_offset(s, a->rd), vec_full_reg_offset(s, a->rn), @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const ftmad_fns[4] = { }; TRANS_FEAT_NONSTREAMING(FTMAD, aa64_sve, gen_gvec_fpst_zzz, ftmad_fns[a->esz], a->rd, a->rn, a->rm, a->imm, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) /* *** SVE Floating Point Accumulating Reduction Group @@ -XXX,XX +XXX,XX @@ static bool trans_FADDA(DisasContext *s, arg_rprr_esz *a) t_pg = tcg_temp_new_ptr(); tcg_gen_addi_ptr(t_rm, tcg_env, vec_full_reg_offset(s, a->rm)); tcg_gen_addi_ptr(t_pg, tcg_env, pred_full_reg_offset(s, a->pg)); - t_fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + t_fpst = fpstatus_ptr(a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); t_desc = tcg_constant_i32(simd_desc(vsz, vsz, 0)); fns[a->esz - 1](t_val, t_val, t_rm, t_pg, t_fpst, t_desc); @@ -XXX,XX +XXX,XX @@ static void do_fp_scalar(DisasContext *s, int zd, int zn, int pg, bool is_fp16, tcg_gen_addi_ptr(t_zn, tcg_env, vec_full_reg_offset(s, zn)); tcg_gen_addi_ptr(t_pg, tcg_env, pred_full_reg_offset(s, pg)); - status = fpstatus_ptr(is_fp16 ? FPST_FPCR_F16 : FPST_A64); + status = fpstatus_ptr(is_fp16 ? FPST_A64_F16 : FPST_A64); desc = tcg_constant_i32(simd_desc(vsz, vsz, 0)); fn(t_zd, t_zn, t_pg, scalar, status, desc); } @@ -XXX,XX +XXX,XX @@ static bool do_fp_cmp(DisasContext *s, arg_rprr_esz *a, } if (sve_access_check(s)) { unsigned vsz = vec_full_reg_size(s); - TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + TCGv_ptr status = fpstatus_ptr(a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); tcg_gen_gvec_4_ptr(pred_full_reg_offset(s, a->rd), vec_full_reg_offset(s, a->rn), vec_full_reg_offset(s, a->rm), @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_4_ptr * const fcadd_fns[] = { }; TRANS_FEAT(FCADD, aa64_sve, gen_gvec_fpst_zzzp, fcadd_fns[a->esz], a->rd, a->rn, a->rm, a->pg, a->rot, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) #define DO_FMLA(NAME, name) \ static gen_helper_gvec_5_ptr * const name##_fns[4] = { \ @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FCADD, aa64_sve, gen_gvec_fpst_zzzp, fcadd_fns[a->esz], }; \ TRANS_FEAT(NAME, aa64_sve, gen_gvec_fpst_zzzzp, name##_fns[a->esz], \ a->rd, a->rn, a->rm, a->ra, a->pg, 0, \ - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) DO_FMLA(FMLA_zpzzz, fmla_zpzzz) DO_FMLA(FMLS_zpzzz, fmls_zpzzz) @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_5_ptr * const fcmla_fns[4] = { }; TRANS_FEAT(FCMLA_zpzzz, aa64_sve, gen_gvec_fpst_zzzzp, fcmla_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->pg, a->rot, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) static gen_helper_gvec_4_ptr * const fcmla_idx_fns[4] = { NULL, gen_helper_gvec_fcmlah_idx, gen_helper_gvec_fcmlas_idx, NULL }; TRANS_FEAT(FCMLA_zzxz, aa64_sve, gen_gvec_fpst_zzzz, fcmla_idx_fns[a->esz], a->rd, a->rn, a->rm, a->ra, a->index * 4 + a->rot, - a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) + a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) /* *** SVE Floating Point Unary Operations Predicated Group @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FCVT_sd, aa64_sve, gen_gvec_fpst_arg_zpz, gen_helper_sve_fcvt_sd, a, 0, FPST_A64) TRANS_FEAT(FCVTZS_hh, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvtzs_hh, a, 0, FPST_FPCR_F16) + gen_helper_sve_fcvtzs_hh, a, 0, FPST_A64_F16) TRANS_FEAT(FCVTZU_hh, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvtzu_hh, a, 0, FPST_FPCR_F16) + gen_helper_sve_fcvtzu_hh, a, 0, FPST_A64_F16) TRANS_FEAT(FCVTZS_hs, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvtzs_hs, a, 0, FPST_FPCR_F16) + gen_helper_sve_fcvtzs_hs, a, 0, FPST_A64_F16) TRANS_FEAT(FCVTZU_hs, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvtzu_hs, a, 0, FPST_FPCR_F16) + gen_helper_sve_fcvtzu_hs, a, 0, FPST_A64_F16) TRANS_FEAT(FCVTZS_hd, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvtzs_hd, a, 0, FPST_FPCR_F16) + gen_helper_sve_fcvtzs_hd, a, 0, FPST_A64_F16) TRANS_FEAT(FCVTZU_hd, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvtzu_hd, a, 0, FPST_FPCR_F16) + gen_helper_sve_fcvtzu_hd, a, 0, FPST_A64_F16) TRANS_FEAT(FCVTZS_ss, aa64_sve, gen_gvec_fpst_arg_zpz, gen_helper_sve_fcvtzs_ss, a, 0, FPST_A64) @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const frint_fns[] = { gen_helper_sve_frint_d }; TRANS_FEAT(FRINTI, aa64_sve, gen_gvec_fpst_arg_zpz, frint_fns[a->esz], - a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) + a, 0, a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) static gen_helper_gvec_3_ptr * const frintx_fns[] = { NULL, @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const frintx_fns[] = { gen_helper_sve_frintx_d }; TRANS_FEAT(FRINTX, aa64_sve, gen_gvec_fpst_arg_zpz, frintx_fns[a->esz], - a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + a, 0, a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); static bool do_frint_mode(DisasContext *s, arg_rpr_esz *a, ARMFPRounding mode, gen_helper_gvec_3_ptr *fn) @@ -XXX,XX +XXX,XX @@ static bool do_frint_mode(DisasContext *s, arg_rpr_esz *a, } vsz = vec_full_reg_size(s); - status = fpstatus_ptr(a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64); + status = fpstatus_ptr(a->esz == MO_16 ? FPST_A64_F16 : FPST_A64); tmode = gen_set_rmode(mode, status); tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, a->rd), @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const frecpx_fns[] = { gen_helper_sve_frecpx_s, gen_helper_sve_frecpx_d, }; TRANS_FEAT(FRECPX, aa64_sve, gen_gvec_fpst_arg_zpz, frecpx_fns[a->esz], - a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) + a, 0, a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) static gen_helper_gvec_3_ptr * const fsqrt_fns[] = { NULL, gen_helper_sve_fsqrt_h, gen_helper_sve_fsqrt_s, gen_helper_sve_fsqrt_d, }; TRANS_FEAT(FSQRT, aa64_sve, gen_gvec_fpst_arg_zpz, fsqrt_fns[a->esz], - a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) + a, 0, a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) TRANS_FEAT(SCVTF_hh, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_scvt_hh, a, 0, FPST_FPCR_F16) + gen_helper_sve_scvt_hh, a, 0, FPST_A64_F16) TRANS_FEAT(SCVTF_sh, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_scvt_sh, a, 0, FPST_FPCR_F16) + gen_helper_sve_scvt_sh, a, 0, FPST_A64_F16) TRANS_FEAT(SCVTF_dh, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_scvt_dh, a, 0, FPST_FPCR_F16) + gen_helper_sve_scvt_dh, a, 0, FPST_A64_F16) TRANS_FEAT(SCVTF_ss, aa64_sve, gen_gvec_fpst_arg_zpz, gen_helper_sve_scvt_ss, a, 0, FPST_A64) @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(SCVTF_dd, aa64_sve, gen_gvec_fpst_arg_zpz, gen_helper_sve_scvt_dd, a, 0, FPST_A64) TRANS_FEAT(UCVTF_hh, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_ucvt_hh, a, 0, FPST_FPCR_F16) + gen_helper_sve_ucvt_hh, a, 0, FPST_A64_F16) TRANS_FEAT(UCVTF_sh, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_ucvt_sh, a, 0, FPST_FPCR_F16) + gen_helper_sve_ucvt_sh, a, 0, FPST_A64_F16) TRANS_FEAT(UCVTF_dh, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_ucvt_dh, a, 0, FPST_FPCR_F16) + gen_helper_sve_ucvt_dh, a, 0, FPST_A64_F16) TRANS_FEAT(UCVTF_ss, aa64_sve, gen_gvec_fpst_arg_zpz, gen_helper_sve_ucvt_ss, a, 0, FPST_A64) @@ -XXX,XX +XXX,XX @@ static gen_helper_gvec_3_ptr * const flogb_fns[] = { gen_helper_flogb_s, gen_helper_flogb_d }; TRANS_FEAT(FLOGB, aa64_sve2, gen_gvec_fpst_arg_zpz, flogb_fns[a->esz], - a, 0, a->esz == MO_16 ? FPST_FPCR_F16 : FPST_A64) + a, 0, a->esz == MO_16 ? FPST_A64_F16 : FPST_A64) static bool do_FMLAL_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sub, bool sel) { -- 2.34.1 Now we have moved all the uses of vfp.fp_status_f16 and FPST_FPCR_F16 to the new A32 or A64 fields, we can remove these. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-19-peter.maydell@linaro.org --- target/arm/cpu.h | 2 -- target/arm/tcg/translate.h | 6 ------ target/arm/cpu.c | 1 - target/arm/vfp_helper.c | 7 ------- 4 files changed, 16 deletions(-) diff --git a/target/arm/cpu.h b/target/arm/cpu.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.h +++ b/target/arm/cpu.h @@ -XXX,XX +XXX,XX @@ typedef struct CPUArchState { * * fp_status_a32: is the "normal" fp status for AArch32 insns * fp_status_a64: is the "normal" fp status for AArch64 insns - * fp_status_fp16: used for half-precision calculations * fp_status_fp16_a32: used for AArch32 half-precision calculations * fp_status_fp16_a64: used for AArch64 half-precision calculations * standard_fp_status : the ARM "Standard FPSCR Value" @@ -XXX,XX +XXX,XX @@ typedef struct CPUArchState { */ float_status fp_status_a32; float_status fp_status_a64; - float_status fp_status_f16; float_status fp_status_f16_a32; float_status fp_status_f16_a64; float_status standard_fp_status; diff --git a/target/arm/tcg/translate.h b/target/arm/tcg/translate.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate.h +++ b/target/arm/tcg/translate.h @@ -XXX,XX +XXX,XX @@ static inline CPUARMTBFlags arm_tbflags_from_tb(const TranslationBlock *tb) typedef enum ARMFPStatusFlavour { FPST_A32, FPST_A64, - FPST_FPCR_F16, FPST_A32_F16, FPST_A64_F16, FPST_STD, @@ -XXX,XX +XXX,XX @@ typedef enum ARMFPStatusFlavour { * for AArch32 non-FP16 operations controlled by the FPCR * FPST_A64 * for AArch64 non-FP16 operations controlled by the FPCR - * FPST_FPCR_F16 - * for operations controlled by the FPCR where FPCR.FZ16 is to be used * FPST_A32_F16 * for AArch32 operations controlled by the FPCR where FPCR.FZ16 is to be used * FPST_A64_F16 @@ -XXX,XX +XXX,XX @@ static inline TCGv_ptr fpstatus_ptr(ARMFPStatusFlavour flavour) case FPST_A64: offset = offsetof(CPUARMState, vfp.fp_status_a64); break; - case FPST_FPCR_F16: - offset = offsetof(CPUARMState, vfp.fp_status_f16); - break; case FPST_A32_F16: offset = offsetof(CPUARMState, vfp.fp_status_f16_a32); break; diff --git a/target/arm/cpu.c b/target/arm/cpu.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/cpu.c +++ b/target/arm/cpu.c @@ -XXX,XX +XXX,XX @@ static void arm_cpu_reset_hold(Object *obj, ResetType type) arm_set_default_fp_behaviours(&env->vfp.fp_status_a32); arm_set_default_fp_behaviours(&env->vfp.fp_status_a64); arm_set_default_fp_behaviours(&env->vfp.standard_fp_status); - arm_set_default_fp_behaviours(&env->vfp.fp_status_f16); arm_set_default_fp_behaviours(&env->vfp.fp_status_f16_a32); arm_set_default_fp_behaviours(&env->vfp.fp_status_f16_a64); arm_set_default_fp_behaviours(&env->vfp.standard_fp_status_f16); diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ static uint32_t vfp_get_fpsr_from_host(CPUARMState *env) i |= get_float_exception_flags(&env->vfp.fp_status_a64); i |= get_float_exception_flags(&env->vfp.standard_fp_status); /* FZ16 does not generate an input denormal exception. */ - i |= (get_float_exception_flags(&env->vfp.fp_status_f16) - & ~float_flag_input_denormal); i |= (get_float_exception_flags(&env->vfp.fp_status_f16_a32) & ~float_flag_input_denormal); i |= (get_float_exception_flags(&env->vfp.fp_status_f16_a64) @@ -XXX,XX +XXX,XX @@ static void vfp_clear_float_status_exc_flags(CPUARMState *env) */ set_float_exception_flags(0, &env->vfp.fp_status_a32); set_float_exception_flags(0, &env->vfp.fp_status_a64); - set_float_exception_flags(0, &env->vfp.fp_status_f16); set_float_exception_flags(0, &env->vfp.fp_status_f16_a32); set_float_exception_flags(0, &env->vfp.fp_status_f16_a64); set_float_exception_flags(0, &env->vfp.standard_fp_status); @@ -XXX,XX +XXX,XX @@ static void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) } set_float_rounding_mode(i, &env->vfp.fp_status_a32); set_float_rounding_mode(i, &env->vfp.fp_status_a64); - set_float_rounding_mode(i, &env->vfp.fp_status_f16); set_float_rounding_mode(i, &env->vfp.fp_status_f16_a32); set_float_rounding_mode(i, &env->vfp.fp_status_f16_a64); } if (changed & FPCR_FZ16) { bool ftz_enabled = val & FPCR_FZ16; - set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_f16); set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_f16_a32); set_flush_to_zero(ftz_enabled, &env->vfp.fp_status_f16_a64); set_flush_to_zero(ftz_enabled, &env->vfp.standard_fp_status_f16); - set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status_f16); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status_f16_a32); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.fp_status_f16_a64); set_flush_inputs_to_zero(ftz_enabled, &env->vfp.standard_fp_status_f16); @@ -XXX,XX +XXX,XX @@ static void vfp_set_fpcr_to_host(CPUARMState *env, uint32_t val, uint32_t mask) bool dnan_enabled = val & FPCR_DN; set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_a32); set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_a64); - set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_f16); set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_f16_a32); set_default_nan_mode(dnan_enabled, &env->vfp.fp_status_f16_a64); } -- 2.34.1 Our float_flag_input_denormal exception flag is set when the fpu code flushes an input denormal to zero. This is what many guest architectures (eg classic Arm behaviour) require, but it is not the only donarmal-related reason we might want to set an exception flag. The x86 behaviour (which we do not currently model correctly) wants to see an exception flag when a denormal input is *not* flushed to zero and is actually used in an arithmetic operation. Arm's FEAT_AFP also wants these semantics. Rename float_flag_input_denormal to float_flag_input_denormal_flushed to make it clearer when it is set and to allow us to add a new float_flag_input_denormal_used next to it for the x86/FEAT_AFP semantics. Commit created with for f in `git grep -l float_flag_input_denormal`; do sed -i -e 's/float_flag_input_denormal/float_flag_input_denormal_flushed/' $f; done and manual editing of softfloat-types.h and softfloat.c to clean up the indentation afterwards and to fix a comment which wasn't using the full name of the flag. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-20-peter.maydell@linaro.org --- include/fpu/softfloat-types.h | 5 +++-- fpu/softfloat.c | 4 ++-- target/arm/tcg/sve_helper.c | 6 +++--- target/arm/vfp_helper.c | 10 +++++----- target/i386/tcg/fpu_helper.c | 6 +++--- target/mips/tcg/msa_helper.c | 2 +- target/rx/op_helper.c | 2 +- fpu/softfloat-parts.c.inc | 2 +- 8 files changed, 19 insertions(+), 18 deletions(-) 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 @@ enum { float_flag_overflow = 0x0004, float_flag_underflow = 0x0008, float_flag_inexact = 0x0010, - float_flag_input_denormal = 0x0020, + /* We flushed an input denormal to 0 (because of flush_inputs_to_zero) */ + float_flag_input_denormal_flushed = 0x0020, float_flag_output_denormal = 0x0040, float_flag_invalid_isi = 0x0080, /* inf - inf */ float_flag_invalid_imz = 0x0100, /* inf * 0 */ @@ -XXX,XX +XXX,XX @@ typedef struct float_status { bool tininess_before_rounding; /* should denormalised results go to zero and set the inexact flag? */ bool flush_to_zero; - /* should denormalised inputs go to zero and set the input_denormal flag? */ + /* should denormalised inputs go to zero and set input_denormal_flushed? */ bool flush_inputs_to_zero; bool default_nan_mode; /* 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 @@ this code that are retained. if (unlikely(soft_t ## _is_denormal(*a))) { \ *a = soft_t ## _set_sign(soft_t ## _zero, \ soft_t ## _is_neg(*a)); \ - float_raise(float_flag_input_denormal, s); \ + float_raise(float_flag_input_denormal_flushed, s); \ } \ } @@ -XXX,XX +XXX,XX @@ float128 float128_silence_nan(float128 a, float_status *status) static bool parts_squash_denormal(FloatParts64 p, float_status *status) { if (p.exp == 0 && p.frac != 0) { - float_raise(float_flag_input_denormal, status); + float_raise(float_flag_input_denormal_flushed, status); return true; } diff --git a/target/arm/tcg/sve_helper.c b/target/arm/tcg/sve_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/sve_helper.c +++ b/target/arm/tcg/sve_helper.c @@ -XXX,XX +XXX,XX @@ static int16_t do_float16_logb_as_int(float16 a, float_status *s) return -15 - clz32(frac); } /* flush to zero */ - float_raise(float_flag_input_denormal, s); + float_raise(float_flag_input_denormal_flushed, s); } } else if (unlikely(exp == 0x1f)) { if (frac == 0) { @@ -XXX,XX +XXX,XX @@ static int32_t do_float32_logb_as_int(float32 a, float_status *s) return -127 - clz32(frac); } /* flush to zero */ - float_raise(float_flag_input_denormal, s); + float_raise(float_flag_input_denormal_flushed, s); } } else if (unlikely(exp == 0xff)) { if (frac == 0) { @@ -XXX,XX +XXX,XX @@ static int64_t do_float64_logb_as_int(float64 a, float_status *s) return -1023 - clz64(frac); } /* flush to zero */ - float_raise(float_flag_input_denormal, s); + float_raise(float_flag_input_denormal_flushed, s); } } else if (unlikely(exp == 0x7ff)) { if (frac == 0) { diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t vfp_exceptbits_from_host(int host_bits) if (host_bits & float_flag_inexact) { target_bits |= FPSR_IXC; } - if (host_bits & float_flag_input_denormal) { + if (host_bits & float_flag_input_denormal_flushed) { target_bits |= FPSR_IDC; } return target_bits; @@ -XXX,XX +XXX,XX @@ static uint32_t vfp_get_fpsr_from_host(CPUARMState *env) i |= get_float_exception_flags(&env->vfp.standard_fp_status); /* FZ16 does not generate an input denormal exception. */ i |= (get_float_exception_flags(&env->vfp.fp_status_f16_a32) - & ~float_flag_input_denormal); + & ~float_flag_input_denormal_flushed); i |= (get_float_exception_flags(&env->vfp.fp_status_f16_a64) - & ~float_flag_input_denormal); + & ~float_flag_input_denormal_flushed); i |= (get_float_exception_flags(&env->vfp.standard_fp_status_f16) - & ~float_flag_input_denormal); + & ~float_flag_input_denormal_flushed); return vfp_exceptbits_from_host(i); } @@ -XXX,XX +XXX,XX @@ uint64_t HELPER(fjcvtzs)(float64 value, float_status *status) /* Normal inexact, denormal with flush-to-zero, or overflow or NaN */ inexact = e_new & (float_flag_inexact | - float_flag_input_denormal | + float_flag_input_denormal_flushed | float_flag_invalid); /* While not inexact for IEEE FP, -0.0 is inexact for JavaScript. */ 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 @@ static void merge_exception_flags(CPUX86State *env, uint8_t old_flags) (new_flags & float_flag_overflow ? FPUS_OE : 0) | (new_flags & float_flag_underflow ? FPUS_UE : 0) | (new_flags & float_flag_inexact ? FPUS_PE : 0) | - (new_flags & float_flag_input_denormal ? FPUS_DE : 0))); + (new_flags & float_flag_input_denormal_flushed ? FPUS_DE : 0))); } static inline floatx80 helper_fdiv(CPUX86State *env, floatx80 a, floatx80 b) @@ -XXX,XX +XXX,XX @@ void helper_fxtract(CPUX86State *env) int shift = clz64(temp.l.lower); temp.l.lower <<= shift; expdif = 1 - EXPBIAS - shift; - float_raise(float_flag_input_denormal, &env->fp_status); + float_raise(float_flag_input_denormal_flushed, &env->fp_status); } else { expdif = EXPD(temp) - EXPBIAS; } @@ -XXX,XX +XXX,XX @@ void update_mxcsr_from_sse_status(CPUX86State *env) uint8_t flags = get_float_exception_flags(&env->sse_status); /* * The MXCSR denormal flag has opposite semantics to - * float_flag_input_denormal (the softfloat code sets that flag + * float_flag_input_denormal_flushed (the softfloat code sets that flag * only when flushing input denormals to zero, but SSE sets it * only when not flushing them to zero), so is not converted * here. diff --git a/target/mips/tcg/msa_helper.c b/target/mips/tcg/msa_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/msa_helper.c +++ b/target/mips/tcg/msa_helper.c @@ -XXX,XX +XXX,XX @@ static inline int update_msacsr(CPUMIPSState *env, int action, int denormal) enable = GET_FP_ENABLE(env->active_tc.msacsr) | FP_UNIMPLEMENTED; /* Set Inexact (I) when flushing inputs to zero */ - if ((ieee_exception_flags & float_flag_input_denormal) && + if ((ieee_exception_flags & float_flag_input_denormal_flushed) && (env->active_tc.msacsr & MSACSR_FS_MASK) != 0) { if (action & CLEAR_IS_INEXACT) { mips_exception_flags &= ~FP_INEXACT; diff --git a/target/rx/op_helper.c b/target/rx/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/rx/op_helper.c +++ b/target/rx/op_helper.c @@ -XXX,XX +XXX,XX @@ static void update_fpsw(CPURXState *env, float32 ret, uintptr_t retaddr) if (xcpt & float_flag_inexact) { SET_FPSW(X); } - if ((xcpt & (float_flag_input_denormal + if ((xcpt & (float_flag_input_denormal_flushed | float_flag_output_denormal)) && !FIELD_EX32(env->fpsw, FPSW, DN)) { env->fpsw = FIELD_DP32(env->fpsw, FPSW, CE, 1); 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(canonicalize)(FloatPartsN *p, float_status *status, if (likely(frac_eqz(p))) { p->cls = float_class_zero; } else if (status->flush_inputs_to_zero) { - float_raise(float_flag_input_denormal, status); + float_raise(float_flag_input_denormal_flushed, status); p->cls = float_class_zero; frac_clear(p); } else { -- 2.34.1 Our float_flag_output_denormal exception flag is set when the fpu code flushes an output denormal to zero. Rename it to float_flag_output_denormal_flushed: * this keeps it parallel with the flag for flushing input denormals, which we just renamed * it makes it clearer that it doesn't mean "set when the output is a denormal" Commit created with for f in `git grep -l float_flag_output_denormal`; do sed -i -e 's/float_flag_output_denormal/float_flag_output_denormal_flushed/' $f; done Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-21-peter.maydell@linaro.org --- include/fpu/softfloat-types.h | 3 ++- fpu/softfloat.c | 2 +- target/arm/vfp_helper.c | 2 +- target/i386/tcg/fpu_helper.c | 2 +- target/m68k/fpu_helper.c | 2 +- target/mips/tcg/msa_helper.c | 2 +- target/rx/op_helper.c | 2 +- target/tricore/fpu_helper.c | 6 +++--- fpu/softfloat-parts.c.inc | 2 +- 9 files changed, 12 insertions(+), 11 deletions(-) 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 @@ enum { float_flag_inexact = 0x0010, /* We flushed an input denormal to 0 (because of flush_inputs_to_zero) */ float_flag_input_denormal_flushed = 0x0020, - float_flag_output_denormal = 0x0040, + /* We flushed an output denormal to 0 (because of flush_to_zero) */ + float_flag_output_denormal_flushed = 0x0040, float_flag_invalid_isi = 0x0080, /* inf - inf */ float_flag_invalid_imz = 0x0100, /* inf * 0 */ float_flag_invalid_idi = 0x0200, /* inf / inf */ 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 @@ floatx80 roundAndPackFloatx80(FloatX80RoundPrec roundingPrecision, bool zSign, } if ( zExp <= 0 ) { if (status->flush_to_zero) { - float_raise(float_flag_output_denormal, status); + float_raise(float_flag_output_denormal_flushed, status); return packFloatx80(zSign, 0, 0); } isTiny = status->tininess_before_rounding diff --git a/target/arm/vfp_helper.c b/target/arm/vfp_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/vfp_helper.c +++ b/target/arm/vfp_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint32_t vfp_exceptbits_from_host(int host_bits) if (host_bits & float_flag_overflow) { target_bits |= FPSR_OFC; } - if (host_bits & (float_flag_underflow | float_flag_output_denormal)) { + if (host_bits & (float_flag_underflow | float_flag_output_denormal_flushed)) { target_bits |= FPSR_UFC; } if (host_bits & float_flag_inexact) { 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 update_mxcsr_from_sse_status(CPUX86State *env) (flags & float_flag_overflow ? FPUS_OE : 0) | (flags & float_flag_underflow ? FPUS_UE : 0) | (flags & float_flag_inexact ? FPUS_PE : 0) | - (flags & float_flag_output_denormal ? FPUS_UE | FPUS_PE : + (flags & float_flag_output_denormal_flushed ? FPUS_UE | FPUS_PE : 0)); } 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 @@ static int cpu_m68k_exceptbits_from_host(int host_bits) if (host_bits & float_flag_overflow) { target_bits |= 0x40; } - if (host_bits & (float_flag_underflow | float_flag_output_denormal)) { + if (host_bits & (float_flag_underflow | float_flag_output_denormal_flushed)) { target_bits |= 0x20; } if (host_bits & float_flag_divbyzero) { diff --git a/target/mips/tcg/msa_helper.c b/target/mips/tcg/msa_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/mips/tcg/msa_helper.c +++ b/target/mips/tcg/msa_helper.c @@ -XXX,XX +XXX,XX @@ static inline int update_msacsr(CPUMIPSState *env, int action, int denormal) } /* Set Inexact (I) and Underflow (U) when flushing outputs to zero */ - if ((ieee_exception_flags & float_flag_output_denormal) && + if ((ieee_exception_flags & float_flag_output_denormal_flushed) && (env->active_tc.msacsr & MSACSR_FS_MASK) != 0) { mips_exception_flags |= FP_INEXACT; if (action & CLEAR_FS_UNDERFLOW) { diff --git a/target/rx/op_helper.c b/target/rx/op_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/rx/op_helper.c +++ b/target/rx/op_helper.c @@ -XXX,XX +XXX,XX @@ static void update_fpsw(CPURXState *env, float32 ret, uintptr_t retaddr) SET_FPSW(X); } if ((xcpt & (float_flag_input_denormal_flushed - | float_flag_output_denormal)) + | float_flag_output_denormal_flushed)) && !FIELD_EX32(env->fpsw, FPSW, DN)) { env->fpsw = FIELD_DP32(env->fpsw, FPSW, CE, 1); } diff --git a/target/tricore/fpu_helper.c b/target/tricore/fpu_helper.c index XXXXXXX..XXXXXXX 100644 --- a/target/tricore/fpu_helper.c +++ b/target/tricore/fpu_helper.c @@ -XXX,XX +XXX,XX @@ static inline uint8_t f_get_excp_flags(CPUTriCoreState *env) & (float_flag_invalid | float_flag_overflow | float_flag_underflow - | float_flag_output_denormal + | float_flag_output_denormal_flushed | float_flag_divbyzero | float_flag_inexact); } @@ -XXX,XX +XXX,XX @@ static void f_update_psw_flags(CPUTriCoreState *env, uint8_t flags) some_excp = 1; } - if (flags & float_flag_underflow || flags & float_flag_output_denormal) { + if (flags & float_flag_underflow || flags & float_flag_output_denormal_flushed) { env->FPU_FU = 1 << 31; some_excp = 1; } @@ -XXX,XX +XXX,XX @@ static void f_update_psw_flags(CPUTriCoreState *env, uint8_t flags) some_excp = 1; } - if (flags & float_flag_inexact || flags & float_flag_output_denormal) { + if (flags & float_flag_inexact || flags & float_flag_output_denormal_flushed) { env->PSW |= 1 << 26; some_excp = 1; } 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(uncanon_normal)(FloatPartsN *p, float_status *s, } frac_shr(p, frac_shift); } else if (s->flush_to_zero) { - flags |= float_flag_output_denormal; + flags |= float_flag_output_denormal_flushed; p->cls = float_class_zero; exp = 0; frac_clear(p); -- 2.34.1 In softfloat-types.h a comment documents that if the float_status field flush_to_zero is set then we flush denormalised results to 0 and set the inexact flag. This isn't correct: the status flag that we set when flush_to_zero causes us to flush an output to zero is float_flag_output_denormal_flushed. Correct the comment. Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-22-peter.maydell@linaro.org --- include/fpu/softfloat-types.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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 { Float3NaNPropRule float_3nan_prop_rule; FloatInfZeroNaNRule float_infzeronan_rule; bool tininess_before_rounding; - /* should denormalised results go to zero and set the inexact flag? */ + /* should denormalised results go to zero and set output_denormal_flushed? */ bool flush_to_zero; /* should denormalised inputs go to zero and set input_denormal_flushed? */ bool flush_inputs_to_zero; -- 2.34.1 The advsimd_addh etc helpers defined in helper-a64.c are identical to the vfp_addh etc helpers defined in helper-vfp.c: both take two float16 inputs (in a uint32_t type) plus a float_status* and are simple wrappers around the softfloat float16_* functions. (The duplication seems to be a historical accident: we added the advsimd helpers in 2018 as part of the A64 implementation, and at that time there was no f16 emulation in A32. Then later we added the A32 f16 handling by extending the existing VFP helper macros to generate f16 versions as well as f32 and f64, and didn't realise we could clean things up.) Remove the now-unnecessary advsimd helpers and make the places that generated calls to them use the vfp helpers instead. Many of the helper functions were already unused. (The remaining advsimd_ helpers are those which don't have vfp versions.) Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-26-peter.maydell@linaro.org --- target/arm/tcg/helper-a64.h | 8 -------- target/arm/tcg/helper-a64.c | 9 --------- target/arm/tcg/translate-a64.c | 16 ++++++++-------- 3 files changed, 8 insertions(+), 25 deletions(-) diff --git a/target/arm/tcg/helper-a64.h b/target/arm/tcg/helper-a64.h index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.h +++ b/target/arm/tcg/helper-a64.h @@ -XXX,XX +XXX,XX @@ DEF_HELPER_FLAGS_2(frecpx_f16, TCG_CALL_NO_RWG, f16, f16, fpst) DEF_HELPER_FLAGS_2(fcvtx_f64_to_f32, TCG_CALL_NO_RWG, f32, f64, fpst) DEF_HELPER_FLAGS_3(crc32_64, TCG_CALL_NO_RWG_SE, i64, i64, i64, i32) DEF_HELPER_FLAGS_3(crc32c_64, TCG_CALL_NO_RWG_SE, i64, i64, i64, i32) -DEF_HELPER_FLAGS_3(advsimd_maxh, TCG_CALL_NO_RWG, f16, f16, f16, fpst) -DEF_HELPER_FLAGS_3(advsimd_minh, TCG_CALL_NO_RWG, f16, f16, f16, fpst) -DEF_HELPER_FLAGS_3(advsimd_maxnumh, TCG_CALL_NO_RWG, f16, f16, f16, fpst) -DEF_HELPER_FLAGS_3(advsimd_minnumh, TCG_CALL_NO_RWG, f16, f16, f16, fpst) -DEF_HELPER_3(advsimd_addh, f16, f16, f16, fpst) -DEF_HELPER_3(advsimd_subh, f16, f16, f16, fpst) -DEF_HELPER_3(advsimd_mulh, f16, f16, f16, fpst) -DEF_HELPER_3(advsimd_divh, f16, f16, f16, fpst) DEF_HELPER_3(advsimd_ceq_f16, i32, f16, f16, fpst) DEF_HELPER_3(advsimd_cge_f16, i32, f16, f16, fpst) DEF_HELPER_3(advsimd_cgt_f16, i32, f16, f16, fpst) diff --git a/target/arm/tcg/helper-a64.c b/target/arm/tcg/helper-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/helper-a64.c +++ b/target/arm/tcg/helper-a64.c @@ -XXX,XX +XXX,XX @@ uint32_t ADVSIMD_HELPER(name, h)(uint32_t a, uint32_t b, float_status *fpst) \ return float16_ ## name(a, b, fpst); \ } -ADVSIMD_HALFOP(add) -ADVSIMD_HALFOP(sub) -ADVSIMD_HALFOP(mul) -ADVSIMD_HALFOP(div) -ADVSIMD_HALFOP(min) -ADVSIMD_HALFOP(max) -ADVSIMD_HALFOP(minnum) -ADVSIMD_HALFOP(maxnum) - #define ADVSIMD_TWOHALFOP(name) \ uint32_t ADVSIMD_HELPER(name, 2h)(uint32_t two_a, uint32_t two_b, \ float_status *fpst) \ diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static const FPScalar f_scalar_fmul = { TRANS(FMUL_s, do_fp3_scalar, a, &f_scalar_fmul) static const FPScalar f_scalar_fmax = { - gen_helper_advsimd_maxh, + gen_helper_vfp_maxh, gen_helper_vfp_maxs, gen_helper_vfp_maxd, }; TRANS(FMAX_s, do_fp3_scalar, a, &f_scalar_fmax) static const FPScalar f_scalar_fmin = { - gen_helper_advsimd_minh, + gen_helper_vfp_minh, gen_helper_vfp_mins, gen_helper_vfp_mind, }; TRANS(FMIN_s, do_fp3_scalar, a, &f_scalar_fmin) static const FPScalar f_scalar_fmaxnm = { - gen_helper_advsimd_maxnumh, + gen_helper_vfp_maxnumh, gen_helper_vfp_maxnums, gen_helper_vfp_maxnumd, }; TRANS(FMAXNM_s, do_fp3_scalar, a, &f_scalar_fmaxnm) static const FPScalar f_scalar_fminnm = { - gen_helper_advsimd_minnumh, + gen_helper_vfp_minnumh, gen_helper_vfp_minnums, gen_helper_vfp_minnumd, }; @@ -XXX,XX +XXX,XX @@ static bool do_fp_reduction(DisasContext *s, arg_qrr_e *a, return true; } -TRANS_FEAT(FMAXNMV_h, aa64_fp16, do_fp_reduction, a, gen_helper_advsimd_maxnumh) -TRANS_FEAT(FMINNMV_h, aa64_fp16, do_fp_reduction, a, gen_helper_advsimd_minnumh) -TRANS_FEAT(FMAXV_h, aa64_fp16, do_fp_reduction, a, gen_helper_advsimd_maxh) -TRANS_FEAT(FMINV_h, aa64_fp16, do_fp_reduction, a, gen_helper_advsimd_minh) +TRANS_FEAT(FMAXNMV_h, aa64_fp16, do_fp_reduction, a, gen_helper_vfp_maxnumh) +TRANS_FEAT(FMINNMV_h, aa64_fp16, do_fp_reduction, a, gen_helper_vfp_minnumh) +TRANS_FEAT(FMAXV_h, aa64_fp16, do_fp_reduction, a, gen_helper_vfp_maxh) +TRANS_FEAT(FMINV_h, aa64_fp16, do_fp_reduction, a, gen_helper_vfp_minh) TRANS(FMAXNMV_s, do_fp_reduction, a, gen_helper_vfp_maxnums) TRANS(FMINNMV_s, do_fp_reduction, a, gen_helper_vfp_minnums) -- 2.34.1 We should be using the F16-specific float_status for conversions from half-precision, because halfprec inputs never set Input Denormal. Without FEAT_AHP, using the wrong fpst here had no effect, because the only difference between the A64_F16 and A64 fpst is its handling of flush-to-zero on input and output, and the helper functions vfp_fcvt_f16_to_* and vfp_fcvt_*_to_f16 all explicitly squash the relevant flushing flags, and flush_inputs_to_zero was the only way that IDC could be set. With FEAT_AHP, the FPCR.AH=1 behaviour sets IDC for input_denormal_used, which we will only ignore in vfp_get_fpsr_from_host() for the A64_F16 fpst; so it matters that we use that one for f16 inputs (and the normal one for single/double to f16 conversions). Signed-off-by: Peter Maydell <peter.maydell@linaro.org> Reviewed-by: Richard Henderson <richard.henderson@linaro.org> Message-id: 20250124162836.2332150-27-peter.maydell@linaro.org --- target/arm/tcg/translate-a64.c | 9 ++++++--- target/arm/tcg/translate-sve.c | 4 ++-- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/target/arm/tcg/translate-a64.c b/target/arm/tcg/translate-a64.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-a64.c +++ b/target/arm/tcg/translate-a64.c @@ -XXX,XX +XXX,XX @@ static bool trans_FCVT_s_sh(DisasContext *s, arg_rr *a) if (fp_access_check(s)) { TCGv_i32 tcg_rn = read_fp_hreg(s, a->rn); TCGv_i32 tcg_rd = tcg_temp_new_i32(); - TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_A64); + TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_A64_F16); TCGv_i32 tcg_ahp = get_ahp_flag(); gen_helper_vfp_fcvt_f16_to_f32(tcg_rd, tcg_rn, tcg_fpst, tcg_ahp); @@ -XXX,XX +XXX,XX @@ static bool trans_FCVT_s_dh(DisasContext *s, arg_rr *a) if (fp_access_check(s)) { TCGv_i32 tcg_rn = read_fp_hreg(s, a->rn); TCGv_i64 tcg_rd = tcg_temp_new_i64(); - TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_A64); + TCGv_ptr tcg_fpst = fpstatus_ptr(FPST_A64_F16); TCGv_i32 tcg_ahp = get_ahp_flag(); gen_helper_vfp_fcvt_f16_to_f64(tcg_rd, tcg_rn, tcg_fpst, tcg_ahp); @@ -XXX,XX +XXX,XX @@ static bool trans_FCVTL_v(DisasContext *s, arg_qrr_e *a) return true; } - fpst = fpstatus_ptr(FPST_A64); if (a->esz == MO_64) { /* 32 -> 64 bit fp conversion */ TCGv_i64 tcg_res[2]; TCGv_i32 tcg_op = tcg_temp_new_i32(); int srcelt = a->q ? 2 : 0; + fpst = fpstatus_ptr(FPST_A64); + for (pass = 0; pass < 2; pass++) { tcg_res[pass] = tcg_temp_new_i64(); read_vec_element_i32(s, tcg_op, a->rn, srcelt + pass, MO_32); @@ -XXX,XX +XXX,XX @@ static bool trans_FCVTL_v(DisasContext *s, arg_qrr_e *a) TCGv_i32 tcg_res[4]; TCGv_i32 ahp = get_ahp_flag(); + fpst = fpstatus_ptr(FPST_A64_F16); + for (pass = 0; pass < 4; pass++) { tcg_res[pass] = tcg_temp_new_i32(); read_vec_element_i32(s, tcg_res[pass], a->rn, srcelt + pass, MO_16); diff --git a/target/arm/tcg/translate-sve.c b/target/arm/tcg/translate-sve.c index XXXXXXX..XXXXXXX 100644 --- a/target/arm/tcg/translate-sve.c +++ b/target/arm/tcg/translate-sve.c @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(FCMLA_zzxz, aa64_sve, gen_gvec_fpst_zzzz, fcmla_idx_fns[a->esz], TRANS_FEAT(FCVT_sh, aa64_sve, gen_gvec_fpst_arg_zpz, gen_helper_sve_fcvt_sh, a, 0, FPST_A64) TRANS_FEAT(FCVT_hs, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvt_hs, a, 0, FPST_A64) + gen_helper_sve_fcvt_hs, a, 0, FPST_A64_F16) TRANS_FEAT(BFCVT, aa64_sve_bf16, gen_gvec_fpst_arg_zpz, gen_helper_sve_bfcvt, a, 0, FPST_A64) @@ -XXX,XX +XXX,XX @@ TRANS_FEAT(BFCVT, aa64_sve_bf16, gen_gvec_fpst_arg_zpz, TRANS_FEAT(FCVT_dh, aa64_sve, gen_gvec_fpst_arg_zpz, gen_helper_sve_fcvt_dh, a, 0, FPST_A64) TRANS_FEAT(FCVT_hd, aa64_sve, gen_gvec_fpst_arg_zpz, - gen_helper_sve_fcvt_hd, a, 0, FPST_A64) + gen_helper_sve_fcvt_hd, a, 0, FPST_A64_F16) TRANS_FEAT(FCVT_ds, aa64_sve, gen_gvec_fpst_arg_zpz, gen_helper_sve_fcvt_ds, a, 0, FPST_A64) TRANS_FEAT(FCVT_sd, aa64_sve, gen_gvec_fpst_arg_zpz, -- 2.34.1 From: Hongren Zheng <i@zenithal.me> When USBPacket in OUT direction has larger payload than the ep_out_buffer (of size 512), a buffer overflow would occur. It could be fixed by limiting the size of usb_packet_copy to be at most buffer size. Further optimization gets rid of the ep_out_buffer and directly uses ep_out as the target buffer. This is reported by a security researcher who artificially constructed an OUT packet of size 2047. The report has gone through the QEMU security process, and as this device is for testing purpose and no deployment of it in virtualization environment is observed, it is triaged not to be a security bug. Cc: qemu-stable@nongnu.org Fixes: d7d34918551dc48 ("hw/usb: Add CanoKey Implementation") Reported-by: Juan Jose Lopez Jaimez <thatjiaozi@gmail.com> Signed-off-by: Hongren Zheng <i@zenithal.me> Message-id: Z4TfMOrZz6IQYl_h@Sun Reviewed-by: Peter Maydell <peter.maydell@linaro.org> Signed-off-by: Peter Maydell <peter.maydell@linaro.org> --- hw/usb/canokey.h | 4 ---- hw/usb/canokey.c | 6 +++--- 2 files changed, 3 insertions(+), 7 deletions(-) diff --git a/hw/usb/canokey.h b/hw/usb/canokey.h index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/canokey.h +++ b/hw/usb/canokey.h @@ -XXX,XX +XXX,XX @@ #define CANOKEY_EP_NUM 3 /* BULK/INTR IN can be up to 1352 bytes, e.g. get key info */ #define CANOKEY_EP_IN_BUFFER_SIZE 2048 -/* BULK OUT can be up to 270 bytes, e.g. PIV import cert */ -#define CANOKEY_EP_OUT_BUFFER_SIZE 512 typedef enum { CANOKEY_EP_IN_WAIT, @@ -XXX,XX +XXX,XX @@ typedef struct CanoKeyState { /* OUT pointer to canokey recv buffer */ uint8_t *ep_out[CANOKEY_EP_NUM]; uint32_t ep_out_size[CANOKEY_EP_NUM]; - /* For large BULK OUT, multiple write to ep_out is needed */ - uint8_t ep_out_buffer[CANOKEY_EP_NUM][CANOKEY_EP_OUT_BUFFER_SIZE]; /* Properties */ char *file; /* canokey-file */ diff --git a/hw/usb/canokey.c b/hw/usb/canokey.c index XXXXXXX..XXXXXXX 100644 --- a/hw/usb/canokey.c +++ b/hw/usb/canokey.c @@ -XXX,XX +XXX,XX @@ static void canokey_handle_data(USBDevice *dev, USBPacket *p) switch (p->pid) { case USB_TOKEN_OUT: trace_canokey_handle_data_out(ep_out, p->iov.size); - usb_packet_copy(p, key->ep_out_buffer[ep_out], p->iov.size); out_pos = 0; + /* segment packet into (possibly multiple) ep_out */ while (out_pos != p->iov.size) { /* * key->ep_out[ep_out] set by prepare_receive @@ -XXX,XX +XXX,XX @@ static void canokey_handle_data(USBDevice *dev, USBPacket *p) * to be the buffer length */ out_len = MIN(p->iov.size - out_pos, key->ep_out_size[ep_out]); - memcpy(key->ep_out[ep_out], - key->ep_out_buffer[ep_out] + out_pos, out_len); + /* usb_packet_copy would update the pos offset internally */ + usb_packet_copy(p, key->ep_out[ep_out], out_len); out_pos += out_len; /* update ep_out_size to actual len */ key->ep_out_size[ep_out] = out_len; -- 2.34.1